Xen project Mailing List

[Xen-changelog] Update linux sparse tree to subarch layout.

From: Xen patchbot -unstable <patchbot-unstable@xxxxxxxxxxxxxxxxxxx>

Date: Tue, 31 Jan 2006 00:08:06 +0000

Delivery-date: Tue, 31 Jan 2006 00:21:25 +0000

List-id: BK change log <xen-changelog.lists.xensource.com>

# HG changeset patch # User cl349@xxxxxxxxxxxxxxxxxxxx # Node ID fd9b2c1bb577a90ad8a01e67255a7c87bab2cbc4 # Parent 690fc13948db7651eabbce8cc4b963342c8634dd Update linux sparse tree to subarch layout. Sparse tree is based on 2.6.12 branch of linux-2.6-xen.hg. Signed-off-by: Christian Limpach <Christian.Limpach@xxxxxxxxxxxx> diff -r 690fc13948db -r fd9b2c1bb577 buildconfigs/Rules.mk --- a/buildconfigs/Rules.mk Mon Jan 30 12:35:43 2006 +++ b/buildconfigs/Rules.mk Mon Jan 30 17:18:27 2006 @@ -12,11 +12,11 @@ PRISTINE_SRC_PATH ?= .:.. vpath pristine-% $(PRISTINE_SRC_PATH) -# By default, build Linux with ARCH=xen (overridden by some non arch's) -ifneq ($(XEN_TARGET_ARCH),ia64) -LINUX_ARCH ?= xen +# Let XEN_TARGET_ARCH override ARCH. +ifeq ($(XEN_TARGET_ARCH),x86_32) +LINUX_ARCH ?= i386 else -LINUX_ARCH ?= ia64 +LINUX_ARCH ?= $(XEN_TARGET_ARCH) endif # Expand Linux series to Linux version diff -r 690fc13948db -r fd9b2c1bb577 buildconfigs/mk.linux-2.6-xen --- a/buildconfigs/mk.linux-2.6-xen Mon Jan 30 12:35:43 2006 +++ b/buildconfigs/mk.linux-2.6-xen Mon Jan 30 17:18:27 2006 @@ -30,7 +30,7 @@ CONFIG_VERSION=$$(sed -ne 's/^EXTRAVERSION = //p' $(LINUX_DIR)/Makefile); \ [ -r $(DESTDIR)/boot/config-$(LINUX_VER)$$CONFIG_VERSION-$(EXTRAVERSION) ] && \ cp $(DESTDIR)/boot/config-$(LINUX_VER)$$CONFIG_VERSION-$(EXTRAVERSION) $(LINUX_DIR)/.config \ - || cp $(LINUX_DIR)/arch/xen/configs/$(EXTRAVERSION)_defconfig_$(XEN_TARGET_ARCH)$(XEN_SYSTYPE) \ + || cp buildconfigs/linux-defconfig_$(EXTRAVERSION)_$(XEN_TARGET_ARCH)$(XEN_SYSTYPE) \ $(LINUX_DIR)/.config # See if we need to munge config to enable PAE $(MAKE) CONFIG_FILE=$(LINUX_DIR)/.config -f buildconfigs/Rules.mk config-update-pae diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/Makefile --- a/linux-2.6-xen-sparse/drivers/Makefile Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/Makefile Mon Jan 30 17:18:27 2006 @@ -30,7 +30,7 @@ obj-$(CONFIG_NUBUS) += nubus/ obj-$(CONFIG_ATM) += atm/ obj-$(CONFIG_PPC_PMAC) += macintosh/ -obj-$(CONFIG_ARCH_XEN) += xen/ +obj-$(CONFIG_XEN) += xen/ obj-$(CONFIG_IDE) += ide/ obj-$(CONFIG_FC4) += fc4/ obj-$(CONFIG_SCSI) += scsi/ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/acpi/tables.c --- a/linux-2.6-xen-sparse/drivers/acpi/tables.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/acpi/tables.c Mon Jan 30 17:18:27 2006 @@ -565,7 +565,7 @@ * * result: sdt_entry[] is initialized */ -#if defined(CONFIG_XEN_X86) || defined(CONFIG_XEN_X86_64) +#if defined(CONFIG_X86_XEN) || defined(CONFIG_X86_64_XEN) #define acpi_rsdp_phys_to_va(rsdp_phys) isa_bus_to_virt(rsdp_phys) #else #define acpi_rsdp_phys_to_va(rsdp_phys) __va(rsdp_phys) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/char/tpm/Kconfig --- a/linux-2.6-xen-sparse/drivers/char/tpm/Kconfig Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/char/tpm/Kconfig Mon Jan 30 17:18:27 2006 @@ -6,7 +6,7 @@ config TCG_TPM tristate "TPM Hardware Support" - depends on EXPERIMENTAL && PCI + depends on EXPERIMENTAL && (PCI || XEN) ---help--- If you have a TPM security chip in your system, which implements the Trusted Computing Group's specification, @@ -20,7 +20,7 @@ config TCG_NSC tristate "National Semiconductor TPM Interface" - depends on TCG_TPM + depends on TCG_TPM && !XEN_UNPRIVILEGED_GUEST ---help--- If you have a TPM security chip from National Semicondutor say Yes and it will be accessible from within Linux. To @@ -29,7 +29,7 @@ config TCG_ATMEL tristate "Atmel TPM Interface" - depends on TCG_TPM + depends on TCG_TPM && !XEN_UNPRIVILEGED_GUEST ---help--- If you have a TPM security chip from Atmel say Yes and it will be accessible from within Linux. To compile this driver @@ -37,7 +37,7 @@ config TCG_XEN tristate "XEN TPM Interface" - depends on TCG_TPM && ARCH_XEN && XEN_TPMDEV_FRONTEND + depends on TCG_TPM && XEN && XEN_TPMDEV_FRONTEND ---help--- If you want to make TPM support available to a Xen user domain, say Yes and it will diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/char/tpm/Makefile --- a/linux-2.6-xen-sparse/drivers/char/tpm/Makefile Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/char/tpm/Makefile Mon Jan 30 17:18:27 2006 @@ -1,13 +1,7 @@ # # Makefile for the kernel tpm device drivers. # -ifeq ($(CONFIG_XEN_PHYSDEV_ACCESS),y) obj-$(CONFIG_TCG_TPM) += tpm.o obj-$(CONFIG_TCG_NSC) += tpm_nsc.o obj-$(CONFIG_TCG_ATMEL) += tpm_atmel.o -obj-$(CONFIG_TCG_TIS) += tpm_tis.o obj-$(CONFIG_TCG_XEN) += tpm_xen.o -else -obj-$(CONFIG_TCG_TPM) += tpm.o -obj-$(CONFIG_TCG_XEN) += tpm_xen.o -endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/char/tpm/tpm_xen.c --- a/linux-2.6-xen-sparse/drivers/char/tpm/tpm_xen.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/char/tpm/tpm_xen.c Mon Jan 30 17:18:27 2006 @@ -22,7 +22,7 @@ #include <asm/uaccess.h> #include <linux/list.h> -#include <asm-xen/tpmfe.h> +#include <xen/tpmfe.h> #include <linux/device.h> #include <linux/interrupt.h> #include "tpm.h" diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/char/tty_io.c --- a/linux-2.6-xen-sparse/drivers/char/tty_io.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/char/tty_io.c Mon Jan 30 17:18:27 2006 @@ -2968,19 +2968,17 @@ #endif #ifdef CONFIG_VT - if (console_use_vt) { - cdev_init(&vc0_cdev, &console_fops); - if (cdev_add(&vc0_cdev, MKDEV(TTY_MAJOR, 0), 1) || - register_chrdev_region(MKDEV(TTY_MAJOR, 0), 1, - "/dev/vc/0") < 0) - panic("Couldn't register /dev/tty0 driver\n"); - devfs_mk_cdev(MKDEV(TTY_MAJOR, 0), S_IFCHR|S_IRUSR|S_IWUSR, - "vc/0"); - class_simple_device_add(tty_class, MKDEV(TTY_MAJOR, 0), NULL, - "tty0"); - - vty_init(); - } + if (!console_use_vt) + goto out_vt; + cdev_init(&vc0_cdev, &console_fops); + if (cdev_add(&vc0_cdev, MKDEV(TTY_MAJOR, 0), 1) || + register_chrdev_region(MKDEV(TTY_MAJOR, 0), 1, "/dev/vc/0") < 0) + panic("Couldn't register /dev/tty0 driver\n"); + devfs_mk_cdev(MKDEV(TTY_MAJOR, 0), S_IFCHR|S_IRUSR|S_IWUSR, "vc/0"); + class_simple_device_add(tty_class, MKDEV(TTY_MAJOR, 0), NULL, "tty0"); + + vty_init(); + out_vt: #endif return 0; } diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/Makefile --- a/linux-2.6-xen-sparse/drivers/xen/Makefile Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/Makefile Mon Jan 30 17:18:27 2006 @@ -2,6 +2,7 @@ obj-y += net_driver_util.o obj-y += util.o +obj-y += core/ obj-y += char/ obj-y += console/ obj-y += evtchn/ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/balloon/balloon.c --- a/linux-2.6-xen-sparse/drivers/xen/balloon/balloon.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/balloon/balloon.c Mon Jan 30 17:18:27 2006 @@ -41,17 +41,17 @@ #include <linux/bootmem.h> #include <linux/highmem.h> #include <linux/vmalloc.h> -#include <asm-xen/xen_proc.h> +#include <xen/xen_proc.h> #include <asm/hypervisor.h> -#include <asm-xen/balloon.h> -#include <asm-xen/xen-public/memory.h> +#include <xen/balloon.h> +#include <xen/interface/memory.h> #include <asm/pgalloc.h> #include <asm/pgtable.h> #include <asm/uaccess.h> #include <asm/tlb.h> #include <linux/list.h> -#include<asm-xen/xenbus.h> +#include <xen/xenbus.h> #define PAGES2KB(_p) ((_p)<<(PAGE_SHIFT-10)) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/blkback/blkback.c --- a/linux-2.6-xen-sparse/drivers/xen/blkback/blkback.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/blkback/blkback.c Mon Jan 30 17:18:27 2006 @@ -14,7 +14,7 @@ #include <linux/spinlock.h> #include <linux/kthread.h> #include <linux/list.h> -#include <asm-xen/balloon.h> +#include <xen/balloon.h> #include <asm/hypervisor.h> #include "common.h" diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/blkback/common.h --- a/linux-2.6-xen-sparse/drivers/xen/blkback/common.h Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/blkback/common.h Mon Jan 30 17:18:27 2006 @@ -12,12 +12,12 @@ #include <asm/io.h> #include <asm/setup.h> #include <asm/pgalloc.h> -#include <asm-xen/evtchn.h> +#include <xen/evtchn.h> #include <asm/hypervisor.h> -#include <asm-xen/xen-public/io/blkif.h> -#include <asm-xen/xen-public/io/ring.h> -#include <asm-xen/gnttab.h> -#include <asm-xen/driver_util.h> +#include <xen/interface/io/blkif.h> +#include <xen/interface/io/ring.h> +#include <xen/gnttab.h> +#include <xen/driver_util.h> #define DPRINTK(_f, _a...) pr_debug("(file=%s, line=%d) " _f, \ __FILE__ , __LINE__ , ## _a ) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/blkback/interface.c --- a/linux-2.6-xen-sparse/drivers/xen/blkback/interface.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/blkback/interface.c Mon Jan 30 17:18:27 2006 @@ -7,7 +7,7 @@ */ #include "common.h" -#include <asm-xen/evtchn.h> +#include <xen/evtchn.h> static kmem_cache_t *blkif_cachep; diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/blkback/vbd.c --- a/linux-2.6-xen-sparse/drivers/xen/blkback/vbd.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/blkback/vbd.c Mon Jan 30 17:18:27 2006 @@ -7,7 +7,7 @@ */ #include "common.h" -#include <asm-xen/xenbus.h> +#include <xen/xenbus.h> #define vbd_sz(_v) ((_v)->bdev->bd_part ? \ (_v)->bdev->bd_part->nr_sects : (_v)->bdev->bd_disk->capacity) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/blkback/xenbus.c --- a/linux-2.6-xen-sparse/drivers/xen/blkback/xenbus.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/blkback/xenbus.c Mon Jan 30 17:18:27 2006 @@ -21,7 +21,7 @@ #include <stdarg.h> #include <linux/module.h> #include <linux/kthread.h> -#include <asm-xen/xenbus.h> +#include <xen/xenbus.h> #include "common.h" #undef DPRINTK diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/blkfront/blkfront.c --- a/linux-2.6-xen-sparse/drivers/xen/blkfront/blkfront.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/blkfront/blkfront.c Mon Jan 30 17:18:27 2006 @@ -41,10 +41,10 @@ #include <linux/sched.h> #include <linux/interrupt.h> #include <scsi/scsi.h> -#include <asm-xen/evtchn.h> -#include <asm-xen/xenbus.h> -#include <asm-xen/xen-public/grant_table.h> -#include <asm-xen/gnttab.h> +#include <xen/evtchn.h> +#include <xen/xenbus.h> +#include <xen/interface/grant_table.h> +#include <xen/gnttab.h> #include <asm/hypervisor.h> #define BLKIF_STATE_DISCONNECTED 0 diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/blkfront/block.h --- a/linux-2.6-xen-sparse/drivers/xen/blkfront/block.h Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/blkfront/block.h Mon Jan 30 17:18:27 2006 @@ -46,11 +46,11 @@ #include <linux/major.h> #include <linux/devfs_fs_kernel.h> #include <asm/hypervisor.h> -#include <asm-xen/xenbus.h> -#include <asm-xen/gnttab.h> -#include <asm-xen/xen-public/xen.h> -#include <asm-xen/xen-public/io/blkif.h> -#include <asm-xen/xen-public/io/ring.h> +#include <xen/xenbus.h> +#include <xen/gnttab.h> +#include <xen/interface/xen.h> +#include <xen/interface/io/blkif.h> +#include <xen/interface/io/ring.h> #include <asm/io.h> #include <asm/atomic.h> #include <asm/uaccess.h> diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/blktap/blktap.c --- a/linux-2.6-xen-sparse/drivers/xen/blktap/blktap.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/blktap/blktap.c Mon Jan 30 17:18:27 2006 @@ -8,7 +8,7 @@ #include <linux/kernel.h> #include <linux/spinlock.h> -#include <asm-xen/balloon.h> +#include <xen/balloon.h> #include <linux/kernel.h> #include <linux/fs.h> #include <linux/mm.h> diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/blktap/common.h --- a/linux-2.6-xen-sparse/drivers/xen/blktap/common.h Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/blktap/common.h Mon Jan 30 17:18:27 2006 @@ -12,12 +12,12 @@ #include <asm/io.h> #include <asm/setup.h> #include <asm/pgalloc.h> -#include <asm-xen/evtchn.h> +#include <xen/evtchn.h> #include <asm/hypervisor.h> -#include <asm-xen/xen-public/io/blkif.h> -#include <asm-xen/xen-public/io/ring.h> -#include <asm-xen/gnttab.h> -#include <asm-xen/driver_util.h> +#include <xen/interface/io/blkif.h> +#include <xen/interface/io/ring.h> +#include <xen/gnttab.h> +#include <xen/driver_util.h> #define DPRINTK(_f, _a...) pr_debug("(file=%s, line=%d) " _f, \ __FILE__ , __LINE__ , ## _a ) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/blktap/interface.c --- a/linux-2.6-xen-sparse/drivers/xen/blktap/interface.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/blktap/interface.c Mon Jan 30 17:18:27 2006 @@ -7,7 +7,7 @@ */ #include "common.h" -#include <asm-xen/evtchn.h> +#include <xen/evtchn.h> static kmem_cache_t *blkif_cachep; diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/blktap/xenbus.c --- a/linux-2.6-xen-sparse/drivers/xen/blktap/xenbus.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/blktap/xenbus.c Mon Jan 30 17:18:27 2006 @@ -23,7 +23,7 @@ #include <stdarg.h> #include <linux/module.h> -#include <asm-xen/xenbus.h> +#include <xen/xenbus.h> #include "common.h" struct backend_info diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/console/console.c --- a/linux-2.6-xen-sparse/drivers/xen/console/console.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/console/console.c Mon Jan 30 17:18:27 2006 @@ -49,11 +49,11 @@ #include <asm/io.h> #include <asm/irq.h> #include <asm/uaccess.h> -#include <asm-xen/xen-public/xen.h> -#include <asm-xen/xen-public/event_channel.h> +#include <xen/interface/xen.h> +#include <xen/interface/event_channel.h> #include <asm/hypervisor.h> -#include <asm-xen/evtchn.h> -#include <asm-xen/xencons.h> +#include <xen/evtchn.h> +#include <xen/xencons.h> /* * Modes: diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/console/xencons_ring.c --- a/linux-2.6-xen-sparse/drivers/xen/console/xencons_ring.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/console/xencons_ring.c Mon Jan 30 17:18:27 2006 @@ -14,13 +14,13 @@ #include <linux/slab.h> #include <asm/hypervisor.h> -#include <asm-xen/evtchn.h> -#include <asm-xen/xencons.h> +#include <xen/evtchn.h> +#include <xen/xencons.h> #include <linux/wait.h> #include <linux/interrupt.h> #include <linux/sched.h> #include <linux/err.h> -#include <asm-xen/xen-public/io/console.h> +#include <xen/interface/io/console.h> static int xencons_irq; diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/evtchn/evtchn.c --- a/linux-2.6-xen-sparse/drivers/xen/evtchn/evtchn.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/evtchn/evtchn.c Mon Jan 30 17:18:27 2006 @@ -45,8 +45,8 @@ #include <linux/irq.h> #include <linux/init.h> #include <linux/gfp.h> -#include <asm-xen/evtchn.h> -#include <asm-xen/linux-public/evtchn.h> +#include <xen/evtchn.h> +#include <xen/public/evtchn.h> struct per_user_data { /* Notification ring, accessed via /dev/xen/evtchn. */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/net_driver_util.c --- a/linux-2.6-xen-sparse/drivers/xen/net_driver_util.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/net_driver_util.c Mon Jan 30 17:18:27 2006 @@ -30,7 +30,7 @@ #include <linux/if_ether.h> #include <linux/err.h> -#include <asm-xen/net_driver_util.h> +#include <xen/net_driver_util.h> int xen_net_read_mac(struct xenbus_device *dev, u8 mac[]) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/netback/common.h --- a/linux-2.6-xen-sparse/drivers/xen/netback/common.h Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/netback/common.h Mon Jan 30 17:18:27 2006 @@ -14,13 +14,13 @@ #include <linux/in.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> -#include <asm-xen/evtchn.h> -#include <asm-xen/xen-public/io/netif.h> +#include <xen/evtchn.h> +#include <xen/interface/io/netif.h> #include <asm/io.h> #include <asm/pgalloc.h> -#include <asm-xen/xen-public/grant_table.h> -#include <asm-xen/gnttab.h> -#include <asm-xen/driver_util.h> +#include <xen/interface/grant_table.h> +#include <xen/gnttab.h> +#include <xen/driver_util.h> #define DPRINTK(_f, _a...) pr_debug("(file=%s, line=%d) " _f, \ __FILE__ , __LINE__ , ## _a ) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/netback/netback.c --- a/linux-2.6-xen-sparse/drivers/xen/netback/netback.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/netback/netback.c Mon Jan 30 17:18:27 2006 @@ -11,8 +11,8 @@ */ #include "common.h" -#include <asm-xen/balloon.h> -#include <asm-xen/xen-public/memory.h> +#include <xen/balloon.h> +#include <xen/interface/memory.h> /*#define NETBE_DEBUG_INTERRUPT*/ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/netback/xenbus.c --- a/linux-2.6-xen-sparse/drivers/xen/netback/xenbus.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/netback/xenbus.c Mon Jan 30 17:18:27 2006 @@ -20,8 +20,8 @@ #include <stdarg.h> #include <linux/module.h> -#include <asm-xen/xenbus.h> -#include <asm-xen/net_driver_util.h> +#include <xen/xenbus.h> +#include <xen/net_driver_util.h> #include "common.h" diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/netfront/netfront.c --- a/linux-2.6-xen-sparse/drivers/xen/netfront/netfront.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/netfront/netfront.c Mon Jan 30 17:18:27 2006 @@ -51,16 +51,16 @@ #include <net/route.h> #include <asm/io.h> #include <asm/uaccess.h> -#include <asm-xen/evtchn.h> -#include <asm-xen/xenbus.h> -#include <asm-xen/xen-public/io/netif.h> -#include <asm-xen/xen-public/memory.h> -#include <asm-xen/balloon.h> +#include <xen/evtchn.h> +#include <xen/xenbus.h> +#include <xen/interface/io/netif.h> +#include <xen/interface/memory.h> +#include <xen/balloon.h> #include <asm/page.h> #include <asm/uaccess.h> -#include <asm-xen/xen-public/grant_table.h> -#include <asm-xen/gnttab.h> -#include <asm-xen/net_driver_util.h> +#include <xen/interface/grant_table.h> +#include <xen/gnttab.h> +#include <xen/net_driver_util.h> #define GRANT_INVALID_REF 0 diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/privcmd/privcmd.c --- a/linux-2.6-xen-sparse/drivers/xen/privcmd/privcmd.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/privcmd/privcmd.c Mon Jan 30 17:18:27 2006 @@ -27,10 +27,10 @@ #include <asm/uaccess.h> #include <asm/tlb.h> #include <asm/hypervisor.h> -#include <asm-xen/linux-public/privcmd.h> -#include <asm-xen/xen-public/xen.h> -#include <asm-xen/xen-public/dom0_ops.h> -#include <asm-xen/xen_proc.h> +#include <xen/public/privcmd.h> +#include <xen/interface/xen.h> +#include <xen/interface/dom0_ops.h> +#include <xen/xen_proc.h> static struct proc_dir_entry *privcmd_intf; static struct proc_dir_entry *capabilities_intf; diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/tpmback/common.h --- a/linux-2.6-xen-sparse/drivers/xen/tpmback/common.h Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/tpmback/common.h Mon Jan 30 17:18:27 2006 @@ -10,10 +10,10 @@ #include <linux/module.h> #include <linux/interrupt.h> #include <linux/slab.h> -#include <asm-xen/evtchn.h> -#include <asm-xen/driver_util.h> -#include <asm-xen/xen-public/grant_table.h> -#include <asm-xen/xen-public/io/tpmif.h> +#include <xen/evtchn.h> +#include <xen/driver_util.h> +#include <xen/interface/grant_table.h> +#include <xen/interface/io/tpmif.h> #include <asm/io.h> #include <asm/pgalloc.h> diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/tpmback/interface.c --- a/linux-2.6-xen-sparse/drivers/xen/tpmback/interface.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/tpmback/interface.c Mon Jan 30 17:18:27 2006 @@ -12,7 +12,7 @@ */ #include "common.h" -#include <asm-xen/balloon.h> +#include <xen/balloon.h> #define TPMIF_HASHSZ (2 << 5) #define TPMIF_HASH(_d,_h) (((int)(_d)^(int)(_h))&(TPMIF_HASHSZ-1)) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/tpmback/tpmback.c --- a/linux-2.6-xen-sparse/drivers/xen/tpmback/tpmback.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/tpmback/tpmback.c Mon Jan 30 17:18:27 2006 @@ -12,15 +12,15 @@ */ #include "common.h" -#include <asm-xen/evtchn.h> +#include <xen/evtchn.h> #include <linux/types.h> #include <linux/list.h> #include <linux/miscdevice.h> #include <linux/poll.h> #include <asm/uaccess.h> -#include <asm-xen/xenbus.h> -#include <asm-xen/xen-public/grant_table.h> +#include <xen/xenbus.h> +#include <xen/interface/grant_table.h> /* local data structures */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/tpmback/xenbus.c --- a/linux-2.6-xen-sparse/drivers/xen/tpmback/xenbus.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/tpmback/xenbus.c Mon Jan 30 17:18:27 2006 @@ -18,7 +18,7 @@ */ #include <stdarg.h> #include <linux/module.h> -#include <asm-xen/xenbus.h> +#include <xen/xenbus.h> #include "common.h" struct backend_info diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/tpmfront/tpmfront.c --- a/linux-2.6-xen-sparse/drivers/xen/tpmfront/tpmfront.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/tpmfront/tpmfront.c Mon Jan 30 17:18:27 2006 @@ -38,17 +38,17 @@ #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/init.h> -#include <asm-xen/tpmfe.h> +#include <xen/tpmfe.h> #include <linux/err.h> #include <asm/semaphore.h> #include <asm/io.h> -#include <asm-xen/evtchn.h> -#include <asm-xen/xen-public/grant_table.h> -#include <asm-xen/xen-public/io/tpmif.h> +#include <xen/evtchn.h> +#include <xen/interface/grant_table.h> +#include <xen/interface/io/tpmif.h> #include <asm/uaccess.h> -#include <asm-xen/xenbus.h> -#include <asm-xen/xen-public/grant_table.h> +#include <xen/xenbus.h> +#include <xen/interface/grant_table.h> #include "tpmfront.h" diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/util.c --- a/linux-2.6-xen-sparse/drivers/xen/util.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/util.c Mon Jan 30 17:18:27 2006 @@ -4,7 +4,7 @@ #include <linux/slab.h> #include <linux/vmalloc.h> #include <asm/uaccess.h> -#include <asm-xen/driver_util.h> +#include <xen/driver_util.h> static int f(pte_t *pte, struct page *pte_page, unsigned long addr, void *data) { diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_client.c --- a/linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_client.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_client.c Mon Jan 30 17:18:27 2006 @@ -27,9 +27,9 @@ * IN THE SOFTWARE. */ -#include <asm-xen/evtchn.h> -#include <asm-xen/gnttab.h> -#include <asm-xen/xenbus.h> +#include <xen/evtchn.h> +#include <xen/gnttab.h> +#include <xen/xenbus.h> /* xenbus_probe.c */ extern char *kasprintf(const char *fmt, ...); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_comms.c --- a/linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_comms.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_comms.c Mon Jan 30 17:18:27 2006 @@ -28,12 +28,12 @@ */ #include <asm/hypervisor.h> -#include <asm-xen/evtchn.h> +#include <xen/evtchn.h> #include <linux/wait.h> #include <linux/interrupt.h> #include <linux/sched.h> #include <linux/err.h> -#include <asm-xen/xenbus.h> +#include <xen/xenbus.h> #include "xenbus_comms.h" static int xenbus_irq; diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_dev.c --- a/linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_dev.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_dev.c Mon Jan 30 17:18:27 2006 @@ -41,8 +41,8 @@ #include <asm/uaccess.h> #include <asm/hypervisor.h> -#include <asm-xen/xenbus.h> -#include <asm-xen/xen_proc.h> +#include <xen/xenbus.h> +#include <xen/xen_proc.h> #include <asm/hypervisor.h> struct xenbus_dev_transaction { diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_probe.c --- a/linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_probe.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_probe.c Mon Jan 30 17:18:27 2006 @@ -43,11 +43,11 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/hypervisor.h> -#include <asm-xen/xenbus.h> -#include <asm-xen/xen_proc.h> -#include <asm-xen/balloon.h> -#include <asm-xen/evtchn.h> -#include <asm-xen/linux-public/evtchn.h> +#include <xen/xenbus.h> +#include <xen/xen_proc.h> +#include <xen/balloon.h> +#include <xen/evtchn.h> +#include <xen/public/evtchn.h> #include "xenbus_comms.h" diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_xs.c --- a/linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_xs.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/xenbus/xenbus_xs.c Mon Jan 30 17:18:27 2006 @@ -38,7 +38,7 @@ #include <linux/slab.h> #include <linux/fcntl.h> #include <linux/kthread.h> -#include <asm-xen/xenbus.h> +#include <xen/xenbus.h> #include "xenbus_comms.h" /* xenbus_probe.c */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/linux/gfp.h --- a/linux-2.6-xen-sparse/include/linux/gfp.h Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/linux/gfp.h Mon Jan 30 17:18:27 2006 @@ -77,12 +77,12 @@ * optimized to &contig_page_data at compile-time. */ +#ifndef HAVE_ARCH_FREE_PAGE /* * If arch_free_page returns non-zero then the generic free_page code can * immediately bail: the arch-specific function has done all the work. */ -#ifndef HAVE_ARCH_FREE_PAGE -#define arch_free_page(page, order) 0 +static inline int arch_free_page(struct page *page, int order) { return 0; } #endif extern struct page * diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/linux/highmem.h --- a/linux-2.6-xen-sparse/include/linux/highmem.h Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/linux/highmem.h Mon Jan 30 17:18:27 2006 @@ -13,12 +13,16 @@ /* declarations for linux/mm/highmem.c */ unsigned int nr_free_highpages(void); +#ifdef CONFIG_XEN void kmap_flush_unused(void); +#endif #else /* CONFIG_HIGHMEM */ static inline unsigned int nr_free_highpages(void) { return 0; } +#ifdef CONFIG_XEN static inline void kmap_flush_unused(void) { } +#endif static inline void *kmap(struct page *page) { diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/linux/irq.h --- a/linux-2.6-xen-sparse/include/linux/irq.h Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/linux/irq.h Mon Jan 30 17:18:27 2006 @@ -74,7 +74,9 @@ #include <asm/hw_irq.h> /* the arch dependent stuff */ extern int setup_irq(unsigned int irq, struct irqaction * new); +#ifdef CONFIG_XEN extern int teardown_irq(unsigned int irq, struct irqaction * old); +#endif #ifdef CONFIG_GENERIC_HARDIRQS extern cpumask_t irq_affinity[NR_IRQS]; diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/linux/mm.h --- a/linux-2.6-xen-sparse/include/linux/mm.h Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/linux/mm.h Mon Jan 30 17:18:27 2006 @@ -161,7 +161,9 @@ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ #define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu mmap) */ +#ifdef CONFIG_XEN #define VM_FOREIGN 0x02000000 /* Has pages belonging to another VM */ +#endif #ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS @@ -817,12 +819,13 @@ int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long, unsigned long, pgprot_t); +#ifdef CONFIG_XEN typedef int (*pte_fn_t)(pte_t *pte, struct page *pte_page, unsigned long addr, void *data); extern int generic_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); - +#endif #ifdef CONFIG_PROC_FS void __vm_stat_account(struct mm_struct *, unsigned long, struct file *, long); #else diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/linux/skbuff.h --- a/linux-2.6-xen-sparse/include/linux/skbuff.h Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/linux/skbuff.h Mon Jan 30 17:18:27 2006 @@ -254,8 +254,10 @@ unsigned char local_df, cloned:1, nohdr:1, +#ifdef CONFIG_XEN proto_csum_valid:1, proto_csum_blank:1, +#endif pkt_type, ip_summed; __u32 priority; diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/kernel/irq/manage.c --- a/linux-2.6-xen-sparse/kernel/irq/manage.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/kernel/irq/manage.c Mon Jan 30 17:18:27 2006 @@ -146,14 +146,9 @@ return !action; } -/** - * setup_irq - register an irqaction structure - * @irq: Interrupt to register - * @irqaction: The irqaction structure to be registered - * - * Normally called by request_irq, this function can be used - * directly to allocate special interrupts that are part of the - * architecture. +/* + * Internal function to register an irqaction - typically used to + * allocate special interrupts that are part of the architecture. */ int setup_irq(unsigned int irq, struct irqaction * new) { @@ -222,6 +217,7 @@ return 0; } +#ifdef CONFIG_XEN /* * teardown_irq - unregister an irqaction * @irq: Interrupt line being freed @@ -318,6 +314,67 @@ spin_unlock_irqrestore(&desc->lock,flags); return; } + +#else +/** + * free_irq - free an interrupt + * @irq: Interrupt line to free + * @dev_id: Device identity to free + * + * Remove an interrupt handler. The handler is removed and if the + * interrupt line is no longer in use by any driver it is disabled. + * On a shared IRQ the caller must ensure the interrupt is disabled + * on the card it drives before calling this function. The function + * does not return until any executing interrupts for this IRQ + * have completed. + * + * This function must not be called from interrupt context. + */ +void free_irq(unsigned int irq, void *dev_id) +{ + struct irq_desc *desc; + struct irqaction **p; + unsigned long flags; + + if (irq >= NR_IRQS) + return; + + desc = irq_desc + irq; + spin_lock_irqsave(&desc->lock,flags); + p = &desc->action; + for (;;) { + struct irqaction * action = *p; + + if (action) { + struct irqaction **pp = p; + + p = &action->next; + if (action->dev_id != dev_id) + continue; + + /* Found it - now remove it from the list of entries */ + *pp = action->next; + if (!desc->action) { + desc->status |= IRQ_DISABLED; + if (desc->handler->shutdown) + desc->handler->shutdown(irq); + else + desc->handler->disable(irq); + } + spin_unlock_irqrestore(&desc->lock,flags); + unregister_handler_proc(irq, action); + + /* Make sure it's not being used on another CPU */ + synchronize_irq(irq); + kfree(action); + return; + } + printk(KERN_ERR "Trying to free free IRQ%d\n",irq); + spin_unlock_irqrestore(&desc->lock,flags); + return; + } +} +#endif EXPORT_SYMBOL(free_irq); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/mkbuildtree --- a/linux-2.6-xen-sparse/mkbuildtree Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/mkbuildtree Mon Jan 30 17:18:27 2006 @@ -108,9 +108,9 @@ rm -f mkbuildtree # Create links to the shared definitions of the Xen interfaces. -rm -rf ${AD}/include/asm-xen/xen-public -mkdir ${AD}/include/asm-xen/xen-public -cd ${AD}/include/asm-xen/xen-public +rm -rf ${AD}/include/xen/interface +mkdir ${AD}/include/xen/interface +cd ${AD}/include/xen/interface relative_lndir ../../../${RS}/../xen/include/public # Arch-specific post-processing diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/mm/highmem.c --- a/linux-2.6-xen-sparse/mm/highmem.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/mm/highmem.c Mon Jan 30 17:18:27 2006 @@ -148,6 +148,7 @@ return vaddr; } +#ifdef CONFIG_XEN void kmap_flush_unused(void) { spin_lock(&kmap_lock); @@ -156,6 +157,7 @@ } EXPORT_SYMBOL(kmap_flush_unused); +#endif void fastcall *kmap_high(struct page *page) { diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/mm/memory.c --- a/linux-2.6-xen-sparse/mm/memory.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/mm/memory.c Mon Jan 30 17:18:27 2006 @@ -940,24 +940,23 @@ continue; } - if (vma && (vma->vm_flags & VM_FOREIGN)) - { - struct page **map = vma->vm_private_data; - int offset = (start - vma->vm_start) >> PAGE_SHIFT; - - if (map[offset] != NULL) { - if (pages) { - pages[i] = map[offset]; - } - if (vmas) - vmas[i] = vma; - i++; - start += PAGE_SIZE; - len--; - continue; - } +#ifdef CONFIG_XEN + if (vma && (vma->vm_flags & VM_FOREIGN)) { + struct page **map = vma->vm_private_data; + int offset = (start - vma->vm_start) >> PAGE_SHIFT; + + if (map[offset] != NULL) { + if (pages) + pages[i] = map[offset]; + if (vmas) + vmas[i] = vma; + i++; + start += PAGE_SIZE; + len--; + continue; + } } - +#endif if (!vma || (vma->vm_flags & VM_IO) || !(flags & vma->vm_flags)) return i ? : -EFAULT; @@ -1213,9 +1212,10 @@ } EXPORT_SYMBOL(remap_pfn_range); +#ifdef CONFIG_XEN static inline int generic_pte_range(struct mm_struct *mm, - pmd_t *pmd, - unsigned long addr, + pmd_t *pmd, + unsigned long addr, unsigned long end, pte_fn_t fn, void *data) { @@ -1223,7 +1223,7 @@ int err; struct page *pte_page; - pte = (mm == &init_mm) ? + pte = (mm == &init_mm) ? pte_alloc_kernel(mm, pmd, addr) : pte_alloc_map(mm, pmd, addr); if (!pte) @@ -1244,8 +1244,8 @@ } static inline int generic_pmd_range(struct mm_struct *mm, - pud_t *pud, - unsigned long addr, + pud_t *pud, + unsigned long addr, unsigned long end, pte_fn_t fn, void *data) { @@ -1265,7 +1265,7 @@ return err; } -static inline int generic_pud_range(struct mm_struct *mm, pgd_t *pgd, +static inline int generic_pud_range(struct mm_struct *mm, pgd_t *pgd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data) @@ -1290,7 +1290,7 @@ * Scan a region of virtual memory, filling in page tables as necessary * and calling a provided function on each leaf page table. */ -int generic_page_range(struct mm_struct *mm, unsigned long addr, +int generic_page_range(struct mm_struct *mm, unsigned long addr, unsigned long size, pte_fn_t fn, void *data) { pgd_t *pgd; @@ -1310,6 +1310,7 @@ spin_unlock(&mm->page_table_lock); return err; } +#endif /* * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when @@ -1365,15 +1366,33 @@ struct page *old_page, *new_page; unsigned long pfn = pte_pfn(pte); pte_t entry; +#ifdef CONFIG_XEN struct page invalid_page; +#endif if (unlikely(!pfn_valid(pfn))) { +#ifdef CONFIG_XEN /* This can happen with /dev/mem (PROT_WRITE, MAP_PRIVATE). */ invalid_page.flags = (1<<PG_reserved) | (1<<PG_locked); old_page = &invalid_page; } else { old_page = pfn_to_page(pfn); - } +#else + /* + * This should really halt the system so it can be debugged or + * at least the kernel stops what it's doing before it corrupts + * data, but for the moment just pretend this is OOM. + */ + pte_unmap(page_table); + printk(KERN_ERR "do_wp_page: bogus page at address %08lx\n", + address); + spin_unlock(&mm->page_table_lock); + return VM_FAULT_OOM; +#endif + } +#ifndef CONFIG_XEN + old_page = pfn_to_page(pfn); +#endif if (!TestSetPageLocked(old_page)) { int reuse = can_share_swap_page(old_page); @@ -1409,6 +1428,9 @@ new_page = alloc_page_vma(GFP_HIGHUSER, vma, address); if (!new_page) goto no_new_page; +#ifndef CONFIG_XEN + copy_user_highpage(new_page, old_page, address); +#else if (old_page == &invalid_page) { char *vto = kmap_atomic(new_page, KM_USER1); copy_page(vto, (void *)(address & PAGE_MASK)); @@ -1416,6 +1438,7 @@ } else { copy_user_highpage(new_page, old_page, address); } +#endif } /* * Re-check the pte - we dropped the lock diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/mm/mmap.c --- a/linux-2.6-xen-sparse/mm/mmap.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/mm/mmap.c Mon Jan 30 17:18:27 2006 @@ -1907,7 +1907,6 @@ #ifdef arch_exit_mmap arch_exit_mmap(mm); #endif - lru_add_drain(); spin_lock(&mm->page_table_lock); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/net/core/dev.c --- a/linux-2.6-xen-sparse/net/core/dev.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/net/core/dev.c Mon Jan 30 17:18:27 2006 @@ -115,10 +115,11 @@ #endif /* CONFIG_NET_RADIO */ #include <asm/current.h> +#ifdef CONFIG_XEN #include <net/ip.h> #include <linux/tcp.h> #include <linux/udp.h> - +#endif /* This define, if set, will randomly drop a packet when congestion * is more than moderate. It helps fairness in the multi-interface @@ -1266,6 +1267,7 @@ __skb_linearize(skb, GFP_ATOMIC)) goto out_kfree_skb; +#ifdef CONFIG_XEN /* If a checksum-deferred packet is forwarded to a device that needs a * checksum, correct the pointers and force checksumming. */ @@ -1294,6 +1296,7 @@ goto out_kfree_skb; skb->ip_summed = CHECKSUM_HW; } +#endif /* If packet is not checksummed and device does not support * checksumming for this protocol, complete checksumming here. @@ -1714,6 +1717,7 @@ } #endif +#ifdef CONFIG_XEN switch (skb->ip_summed) { case CHECKSUM_UNNECESSARY: skb->proto_csum_valid = 1; @@ -1724,6 +1728,7 @@ skb->proto_csum_valid = 0; break; } +#endif list_for_each_entry_rcu(ptype, &ptype_all, list) { if (!ptype->dev || ptype->dev == skb->dev) { diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/net/core/skbuff.c --- a/linux-2.6-xen-sparse/net/core/skbuff.c Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/net/core/skbuff.c Mon Jan 30 17:18:27 2006 @@ -355,8 +355,10 @@ C(local_df); n->cloned = 1; n->nohdr = 0; +#ifdef CONFIG_XEN C(proto_csum_valid); C(proto_csum_blank); +#endif C(pkt_type); C(ip_summed); C(priority); diff -r 690fc13948db -r fd9b2c1bb577 tools/Rules.mk --- a/tools/Rules.mk Mon Jan 30 12:35:43 2006 +++ b/tools/Rules.mk Mon Jan 30 17:18:27 2006 @@ -41,4 +41,4 @@ ( cd xen/io && ln -sf ../../$(XEN_ROOT)/xen/include/public/io/*.h . ) mkdir -p xen/linux ( cd xen/linux && \ - ln -sf ../../$(LINUX_ROOT)/include/asm-xen/linux-public/*.h . ) + ln -sf ../../$(LINUX_ROOT)/include/xen/public/*.h . ) diff -r 690fc13948db -r fd9b2c1bb577 tools/debugger/pdb/linux-2.6-module/debug.c --- a/tools/debugger/pdb/linux-2.6-module/debug.c Mon Jan 30 12:35:43 2006 +++ b/tools/debugger/pdb/linux-2.6-module/debug.c Mon Jan 30 17:18:27 2006 @@ -7,10 +7,10 @@ #include <linux/mm.h> #include <linux/sched.h> #include <asm-i386/kdebug.h> -#include <asm-xen/asm-i386/processor.h> -#include <asm-xen/asm-i386/ptrace.h> -#include <asm-xen/asm-i386/tlbflush.h> -#include <asm-xen/xen-public/xen.h> +#include <asm-i386/mach-xen/asm/processor.h> +#include <asm-i386/mach-xen/asm/ptrace.h> +#include <asm-i386/mach-xen/asm/tlbflush.h> +#include <xen/interface/xen.h> #include "pdb_module.h" #include "pdb_debug.h" diff -r 690fc13948db -r fd9b2c1bb577 tools/debugger/pdb/linux-2.6-module/module.c --- a/tools/debugger/pdb/linux-2.6-module/module.c Mon Jan 30 12:35:43 2006 +++ b/tools/debugger/pdb/linux-2.6-module/module.c Mon Jan 30 17:18:27 2006 @@ -13,13 +13,13 @@ #include <asm-i386/kdebug.h> -#include <asm-xen/evtchn.h> -#include <asm-xen/ctrl_if.h> -#include <asm-xen/hypervisor.h> -#include <asm-xen/xen-public/io/domain_controller.h> -#include <asm-xen/xen-public/xen.h> - -#include <asm-xen/xen-public/io/ring.h> +#include <xen/evtchn.h> +#include <xen/ctrl_if.h> +#include <xen/hypervisor.h> +#include <xen/interface/io/domain_controller.h> +#include <xen/interface/xen.h> + +#include <xen/interface/io/ring.h> #include "pdb_module.h" #include "pdb_debug.h" diff -r 690fc13948db -r fd9b2c1bb577 tools/guest-headers/Makefile --- a/tools/guest-headers/Makefile Mon Jan 30 12:35:43 2006 +++ b/tools/guest-headers/Makefile Mon Jan 30 17:18:27 2006 @@ -8,6 +8,6 @@ install: mkdir -p $(DESTDIR)/usr/include/xen/linux - install -m0644 $(linuxsparsetree)/include/asm-xen/linux-public/*.h $(DESTDIR)/usr/include/xen/linux + install -m0644 $(linuxsparsetree)/include/xen/public/*.h $(DESTDIR)/usr/include/xen/linux clean: diff -r 690fc13948db -r fd9b2c1bb577 buildconfigs/linux-defconfig_xen0_x86_32 --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/buildconfigs/linux-defconfig_xen0_x86_32 Mon Jan 30 17:18:27 2006 @@ -0,0 +1,1232 @@ +# +# Automatically generated make config: don't edit +# Linux kernel version: 2.6.12.6-xen0 +# Wed Jan 25 17:29:15 2006 +# +CONFIG_X86=y +CONFIG_MMU=y +CONFIG_UID16=y +CONFIG_GENERIC_ISA_DMA=y +CONFIG_GENERIC_IOMAP=y + +# +# Code maturity level options +# +CONFIG_EXPERIMENTAL=y +# CONFIG_CLEAN_COMPILE is not set +CONFIG_BROKEN=y +CONFIG_BROKEN_ON_SMP=y +CONFIG_INIT_ENV_ARG_LIMIT=32 + +# +# General setup +# +CONFIG_LOCALVERSION="" +CONFIG_SWAP=y +CONFIG_SYSVIPC=y +# CONFIG_POSIX_MQUEUE is not set +# CONFIG_BSD_PROCESS_ACCT is not set +CONFIG_SYSCTL=y +# CONFIG_AUDIT is not set +CONFIG_HOTPLUG=y +CONFIG_KOBJECT_UEVENT=y +# CONFIG_IKCONFIG is not set +# CONFIG_EMBEDDED is not set +CONFIG_KALLSYMS=y +# CONFIG_KALLSYMS_ALL is not set +# CONFIG_KALLSYMS_EXTRA_PASS is not set +CONFIG_PRINTK=y +CONFIG_BUG=y +CONFIG_BASE_FULL=y +CONFIG_FUTEX=y +CONFIG_EPOLL=y +CONFIG_SHMEM=y +CONFIG_CC_ALIGN_FUNCTIONS=0 +CONFIG_CC_ALIGN_LABELS=0 +CONFIG_CC_ALIGN_LOOPS=0 +CONFIG_CC_ALIGN_JUMPS=0 +# CONFIG_TINY_SHMEM is not set +CONFIG_BASE_SMALL=0 + +# +# Loadable module support +# +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_MODULE_FORCE_UNLOAD is not set +CONFIG_OBSOLETE_MODPARM=y +# CONFIG_MODVERSIONS is not set +# CONFIG_MODULE_SRCVERSION_ALL is not set +CONFIG_KMOD=y + +# +# Processor type and features +# +# CONFIG_X86_PC is not set +CONFIG_X86_XEN=y +# CONFIG_X86_ELAN is not set +# CONFIG_X86_VOYAGER is not set +# CONFIG_X86_NUMAQ is not set +# CONFIG_X86_SUMMIT is not set +# CONFIG_X86_BIGSMP is not set +# CONFIG_X86_VISWS is not set +# CONFIG_X86_GENERICARCH is not set +# CONFIG_X86_ES7000 is not set +# CONFIG_M386 is not set +# CONFIG_M486 is not set +# CONFIG_M586 is not set +# CONFIG_M586TSC is not set +# CONFIG_M586MMX is not set +CONFIG_M686=y +# CONFIG_MPENTIUMII is not set +# CONFIG_MPENTIUMIII is not set +# CONFIG_MPENTIUMM is not set +# CONFIG_MPENTIUM4 is not set +# CONFIG_MK6 is not set +# CONFIG_MK7 is not set +# CONFIG_MK8 is not set +# CONFIG_MCRUSOE is not set +# CONFIG_MEFFICEON is not set +# CONFIG_MWINCHIPC6 is not set +# CONFIG_MWINCHIP2 is not set +# CONFIG_MWINCHIP3D is not set +# CONFIG_MGEODEGX1 is not set +# CONFIG_MCYRIXIII is not set +# CONFIG_MVIAC3_2 is not set +# CONFIG_X86_GENERIC is not set +CONFIG_X86_CMPXCHG=y +CONFIG_X86_XADD=y +CONFIG_X86_L1_CACHE_SHIFT=5 +CONFIG_RWSEM_XCHGADD_ALGORITHM=y +CONFIG_GENERIC_CALIBRATE_DELAY=y +CONFIG_X86_PPRO_FENCE=y +CONFIG_X86_WP_WORKS_OK=y +CONFIG_X86_INVLPG=y +CONFIG_X86_BSWAP=y +CONFIG_X86_POPAD_OK=y +CONFIG_X86_GOOD_APIC=y +CONFIG_X86_USE_PPRO_CHECKSUM=y +# CONFIG_SMP is not set +CONFIG_X86_UP_APIC=y +CONFIG_X86_UP_IOAPIC=y +CONFIG_X86_LOCAL_APIC=y +CONFIG_X86_IO_APIC=y +# CONFIG_TOSHIBA is not set +# CONFIG_I8K is not set +# CONFIG_X86_REBOOTFIXUPS is not set +CONFIG_MICROCODE=y +CONFIG_X86_CPUID=y +CONFIG_SWIOTLB=y + +# +# Firmware Drivers +# +# CONFIG_NOHIGHMEM is not set +CONFIG_HIGHMEM4G=y +# CONFIG_HIGHMEM64G is not set +CONFIG_HIGHMEM=y +CONFIG_MTRR=y +# CONFIG_REGPARM is not set +CONFIG_SECCOMP=y + +# +# Power management options (ACPI, APM) +# + +# +# ACPI (Advanced Configuration and Power Interface) Support +# +CONFIG_ACPI=y +CONFIG_ACPI_BOOT=y +CONFIG_ACPI_INTERPRETER=y +CONFIG_ACPI_AC=m +CONFIG_ACPI_BATTERY=m +CONFIG_ACPI_BUTTON=m +CONFIG_ACPI_VIDEO=m +CONFIG_ACPI_FAN=m +CONFIG_ACPI_PROCESSOR=m +CONFIG_ACPI_THERMAL=m +CONFIG_ACPI_ASUS=m +CONFIG_ACPI_IBM=m +CONFIG_ACPI_TOSHIBA=m +# CONFIG_ACPI_CUSTOM_DSDT is not set +CONFIG_ACPI_BLACKLIST_YEAR=0 +# CONFIG_ACPI_DEBUG is not set +CONFIG_ACPI_BUS=y +CONFIG_ACPI_EC=y +CONFIG_ACPI_POWER=y +CONFIG_ACPI_PCI=y +CONFIG_ACPI_SYSTEM=y +# CONFIG_X86_PM_TIMER is not set +# CONFIG_ACPI_CONTAINER is not set + +# +# CPU Frequency scaling +# +# CONFIG_CPU_FREQ is not set + +# +# Bus options (PCI, PCMCIA, EISA, MCA, ISA) +# +CONFIG_PCI=y +# CONFIG_PCI_GOBIOS is not set +# CONFIG_PCI_GOMMCONFIG is not set +# CONFIG_PCI_GODIRECT is not set +CONFIG_PCI_GOANY=y +CONFIG_PCI_DIRECT=y +CONFIG_PCI_MMCONFIG=y +# CONFIG_PCIEPORTBUS is not set +CONFIG_PCI_LEGACY_PROC=y +# CONFIG_PCI_NAMES is not set +# CONFIG_PCI_DEBUG is not set +# CONFIG_SCx200 is not set + +# +# PCCARD (PCMCIA/CardBus) support +# +# CONFIG_PCCARD is not set + +# +# PCI Hotplug Support +# +# CONFIG_HOTPLUG_PCI is not set + +# +# Executable file formats +# +CONFIG_BINFMT_ELF=y +# CONFIG_BINFMT_AOUT is not set +# CONFIG_BINFMT_MISC is not set + +# +# Device Drivers +# + +# +# Generic Driver Options +# +# CONFIG_STANDALONE is not set +CONFIG_PREVENT_FIRMWARE_BUILD=y +# CONFIG_FW_LOADER is not set +# CONFIG_DEBUG_DRIVER is not set + +# +# Memory Technology Devices (MTD) +# +# CONFIG_MTD is not set + +# +# Parallel port support +# +# CONFIG_PARPORT is not set + +# +# Plug and Play support +# +# CONFIG_PNP is not set + +# +# Block devices +# +CONFIG_BLK_DEV_FD=y +# CONFIG_BLK_CPQ_DA is not set +CONFIG_BLK_CPQ_CISS_DA=y +# CONFIG_CISS_SCSI_TAPE is not set +# CONFIG_BLK_DEV_DAC960 is not set +# CONFIG_BLK_DEV_UMEM is not set +# CONFIG_BLK_DEV_COW_COMMON is not set +CONFIG_BLK_DEV_LOOP=y +# CONFIG_BLK_DEV_CRYPTOLOOP is not set +# CONFIG_BLK_DEV_NBD is not set +# CONFIG_BLK_DEV_SX8 is not set +# CONFIG_BLK_DEV_UB is not set +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_COUNT=16 +CONFIG_BLK_DEV_RAM_SIZE=4096 +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="" +# CONFIG_LBD is not set +# CONFIG_CDROM_PKTCDVD is not set + +# +# IO Schedulers +# +CONFIG_IOSCHED_NOOP=y +CONFIG_IOSCHED_AS=y +CONFIG_IOSCHED_DEADLINE=y +CONFIG_IOSCHED_CFQ=y +# CONFIG_ATA_OVER_ETH is not set + +# +# ATA/ATAPI/MFM/RLL support +# +CONFIG_IDE=y +CONFIG_BLK_DEV_IDE=y + +# +# Please see Documentation/ide.txt for help/info on IDE drives +# +# CONFIG_BLK_DEV_IDE_SATA is not set +# CONFIG_BLK_DEV_HD_IDE is not set +CONFIG_BLK_DEV_IDEDISK=y +# CONFIG_IDEDISK_MULTI_MODE is not set +CONFIG_BLK_DEV_IDECD=y +# CONFIG_BLK_DEV_IDETAPE is not set +# CONFIG_BLK_DEV_IDEFLOPPY is not set +# CONFIG_BLK_DEV_IDESCSI is not set +# CONFIG_IDE_TASK_IOCTL is not set + +# +# IDE chipset support/bugfixes +# +CONFIG_IDE_GENERIC=y +# CONFIG_BLK_DEV_CMD640 is not set +CONFIG_BLK_DEV_IDEPCI=y +# CONFIG_IDEPCI_SHARE_IRQ is not set +# CONFIG_BLK_DEV_OFFBOARD is not set +CONFIG_BLK_DEV_GENERIC=y +# CONFIG_BLK_DEV_OPTI621 is not set +# CONFIG_BLK_DEV_RZ1000 is not set +CONFIG_BLK_DEV_IDEDMA_PCI=y +# CONFIG_BLK_DEV_IDEDMA_FORCED is not set +CONFIG_IDEDMA_PCI_AUTO=y +# CONFIG_IDEDMA_ONLYDISK is not set +# CONFIG_BLK_DEV_AEC62XX is not set +# CONFIG_BLK_DEV_ALI15X3 is not set +# CONFIG_BLK_DEV_AMD74XX is not set +# CONFIG_BLK_DEV_ATIIXP is not set +# CONFIG_BLK_DEV_CMD64X is not set +# CONFIG_BLK_DEV_TRIFLEX is not set +# CONFIG_BLK_DEV_CY82C693 is not set +# CONFIG_BLK_DEV_CS5520 is not set +# CONFIG_BLK_DEV_CS5530 is not set +# CONFIG_BLK_DEV_HPT34X is not set +# CONFIG_BLK_DEV_HPT366 is not set +# CONFIG_BLK_DEV_SC1200 is not set +CONFIG_BLK_DEV_PIIX=y +# CONFIG_BLK_DEV_NS87415 is not set +# CONFIG_BLK_DEV_PDC202XX_OLD is not set +# CONFIG_BLK_DEV_PDC202XX_NEW is not set +CONFIG_BLK_DEV_SVWKS=y +# CONFIG_BLK_DEV_SIIMAGE is not set +# CONFIG_BLK_DEV_SIS5513 is not set +# CONFIG_BLK_DEV_SLC90E66 is not set +# CONFIG_BLK_DEV_TRM290 is not set +# CONFIG_BLK_DEV_VIA82CXXX is not set +# CONFIG_IDE_ARM is not set +CONFIG_BLK_DEV_IDEDMA=y +# CONFIG_IDEDMA_IVB is not set +CONFIG_IDEDMA_AUTO=y +# CONFIG_BLK_DEV_HD is not set + +# +# SCSI device support +# +CONFIG_SCSI=y +CONFIG_SCSI_PROC_FS=y + +# +# SCSI support type (disk, tape, CD-ROM) +# +CONFIG_BLK_DEV_SD=y +# CONFIG_CHR_DEV_ST is not set +# CONFIG_CHR_DEV_OSST is not set +# CONFIG_BLK_DEV_SR is not set +# CONFIG_CHR_DEV_SG is not set + +# +# Some SCSI devices (e.g. CD jukebox) support multiple LUNs +# +# CONFIG_SCSI_MULTI_LUN is not set +# CONFIG_SCSI_CONSTANTS is not set +# CONFIG_SCSI_LOGGING is not set + +# +# SCSI Transport Attributes +# +CONFIG_SCSI_SPI_ATTRS=y +# CONFIG_SCSI_FC_ATTRS is not set +# CONFIG_SCSI_ISCSI_ATTRS is not set + +# +# SCSI low-level drivers +# +CONFIG_BLK_DEV_3W_XXXX_RAID=y +# CONFIG_SCSI_3W_9XXX is not set +# CONFIG_SCSI_ACARD is not set +CONFIG_SCSI_AACRAID=y +CONFIG_SCSI_AIC7XXX=y +CONFIG_AIC7XXX_CMDS_PER_DEVICE=32 +CONFIG_AIC7XXX_RESET_DELAY_MS=15000 +CONFIG_AIC7XXX_DEBUG_ENABLE=y +CONFIG_AIC7XXX_DEBUG_MASK=0 +CONFIG_AIC7XXX_REG_PRETTY_PRINT=y +# CONFIG_SCSI_AIC7XXX_OLD is not set +CONFIG_SCSI_AIC79XX=y +CONFIG_AIC79XX_CMDS_PER_DEVICE=32 +CONFIG_AIC79XX_RESET_DELAY_MS=15000 +# CONFIG_AIC79XX_ENABLE_RD_STRM is not set +CONFIG_AIC79XX_DEBUG_ENABLE=y +CONFIG_AIC79XX_DEBUG_MASK=0 +CONFIG_AIC79XX_REG_PRETTY_PRINT=y +# CONFIG_SCSI_DPT_I2O is not set +# CONFIG_SCSI_ADVANSYS is not set +CONFIG_MEGARAID_NEWGEN=y +# CONFIG_MEGARAID_MM is not set +CONFIG_SCSI_SATA=y +# CONFIG_SCSI_SATA_AHCI is not set +# CONFIG_SCSI_SATA_SVW is not set +CONFIG_SCSI_ATA_PIIX=y +# CONFIG_SCSI_SATA_NV is not set +CONFIG_SCSI_SATA_PROMISE=y +# CONFIG_SCSI_SATA_QSTOR is not set +CONFIG_SCSI_SATA_SX4=y +CONFIG_SCSI_SATA_SIL=y +# CONFIG_SCSI_SATA_SIS is not set +# CONFIG_SCSI_SATA_ULI is not set +# CONFIG_SCSI_SATA_VIA is not set +# CONFIG_SCSI_SATA_VITESSE is not set +# CONFIG_SCSI_CPQFCTS is not set +# CONFIG_SCSI_DMX3191D is not set +# CONFIG_SCSI_EATA_PIO is not set +# CONFIG_SCSI_FUTURE_DOMAIN is not set +# CONFIG_SCSI_IPS is not set +# CONFIG_SCSI_INITIO is not set +# CONFIG_SCSI_INIA100 is not set +# CONFIG_SCSI_SYM53C8XX_2 is not set +# CONFIG_SCSI_IPR is not set +# CONFIG_SCSI_PCI2000 is not set +# CONFIG_SCSI_PCI2220I is not set +# CONFIG_SCSI_QLOGIC_ISP is not set +# CONFIG_SCSI_QLOGIC_FC is not set +# CONFIG_SCSI_QLOGIC_1280 is not set +CONFIG_SCSI_QLA2XXX=y +# CONFIG_SCSI_QLA21XX is not set +# CONFIG_SCSI_QLA22XX is not set +# CONFIG_SCSI_QLA2300 is not set +# CONFIG_SCSI_QLA2322 is not set +# CONFIG_SCSI_QLA6312 is not set +# CONFIG_SCSI_LPFC is not set +# CONFIG_SCSI_DC395x is not set +# CONFIG_SCSI_DC390T is not set +# CONFIG_SCSI_NSP32 is not set +# CONFIG_SCSI_DEBUG is not set + +# +# Multi-device support (RAID and LVM) +# +CONFIG_MD=y +CONFIG_BLK_DEV_MD=y +# CONFIG_MD_LINEAR is not set +CONFIG_MD_RAID0=y +CONFIG_MD_RAID1=y +# CONFIG_MD_RAID10 is not set +CONFIG_MD_RAID5=y +# CONFIG_MD_RAID6 is not set +# CONFIG_MD_MULTIPATH is not set +# CONFIG_MD_FAULTY is not set +CONFIG_BLK_DEV_DM=y +# CONFIG_DM_CRYPT is not set +CONFIG_DM_SNAPSHOT=y +CONFIG_DM_MIRROR=y +# CONFIG_DM_ZERO is not set +# CONFIG_DM_MULTIPATH is not set + +# +# Fusion MPT device support +# +CONFIG_FUSION=y +CONFIG_FUSION_MAX_SGE=40 +# CONFIG_FUSION_CTL is not set + +# +# IEEE 1394 (FireWire) support +# +# CONFIG_IEEE1394 is not set + +# +# I2O device support +# +# CONFIG_I2O is not set + +# +# Networking support +# +CONFIG_NET=y + +# +# Networking options +# +CONFIG_PACKET=y +# CONFIG_PACKET_MMAP is not set +CONFIG_UNIX=y +# CONFIG_NET_KEY is not set +CONFIG_INET=y +# CONFIG_IP_MULTICAST is not set +# CONFIG_IP_ADVANCED_ROUTER is not set +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +# CONFIG_IP_PNP_BOOTP is not set +# CONFIG_IP_PNP_RARP is not set +# CONFIG_NET_IPIP is not set +# CONFIG_NET_IPGRE is not set +# CONFIG_ARPD is not set +# CONFIG_SYN_COOKIES is not set +# CONFIG_INET_AH is not set +# CONFIG_INET_ESP is not set +# CONFIG_INET_IPCOMP is not set +# CONFIG_INET_TUNNEL is not set +CONFIG_IP_TCPDIAG=y +# CONFIG_IP_TCPDIAG_IPV6 is not set + +# +# IP: Virtual Server Configuration +# +# CONFIG_IP_VS is not set +# CONFIG_IPV6 is not set +CONFIG_NETFILTER=y +# CONFIG_NETFILTER_DEBUG is not set +CONFIG_BRIDGE_NETFILTER=y + +# +# IP: Netfilter Configuration +# +CONFIG_IP_NF_CONNTRACK=m +CONFIG_IP_NF_CT_ACCT=y +# CONFIG_IP_NF_CONNTRACK_MARK is not set +# CONFIG_IP_NF_CT_PROTO_SCTP is not set +CONFIG_IP_NF_FTP=m +# CONFIG_IP_NF_IRC is not set +# CONFIG_IP_NF_TFTP is not set +# CONFIG_IP_NF_AMANDA is not set +# CONFIG_IP_NF_QUEUE is not set +CONFIG_IP_NF_IPTABLES=m +# CONFIG_IP_NF_MATCH_LIMIT is not set +CONFIG_IP_NF_MATCH_IPRANGE=m +# CONFIG_IP_NF_MATCH_MAC is not set +# CONFIG_IP_NF_MATCH_PKTTYPE is not set +# CONFIG_IP_NF_MATCH_MARK is not set +# CONFIG_IP_NF_MATCH_MULTIPORT is not set +# CONFIG_IP_NF_MATCH_TOS is not set +# CONFIG_IP_NF_MATCH_RECENT is not set +# CONFIG_IP_NF_MATCH_ECN is not set +# CONFIG_IP_NF_MATCH_DSCP is not set +# CONFIG_IP_NF_MATCH_AH_ESP is not set +# CONFIG_IP_NF_MATCH_LENGTH is not set +# CONFIG_IP_NF_MATCH_TTL is not set +# CONFIG_IP_NF_MATCH_TCPMSS is not set +# CONFIG_IP_NF_MATCH_HELPER is not set +# CONFIG_IP_NF_MATCH_STATE is not set +# CONFIG_IP_NF_MATCH_CONNTRACK is not set +# CONFIG_IP_NF_MATCH_OWNER is not set +CONFIG_IP_NF_MATCH_PHYSDEV=m +# CONFIG_IP_NF_MATCH_ADDRTYPE is not set +# CONFIG_IP_NF_MATCH_REALM is not set +# CONFIG_IP_NF_MATCH_SCTP is not set +# CONFIG_IP_NF_MATCH_COMMENT is not set +# CONFIG_IP_NF_MATCH_HASHLIMIT is not set +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_TARGET_REJECT=m +# CONFIG_IP_NF_TARGET_LOG is not set +# CONFIG_IP_NF_TARGET_ULOG is not set +# CONFIG_IP_NF_TARGET_TCPMSS is not set +CONFIG_IP_NF_NAT=m +CONFIG_IP_NF_NAT_NEEDED=y +CONFIG_IP_NF_TARGET_MASQUERADE=m +# CONFIG_IP_NF_TARGET_REDIRECT is not set +# CONFIG_IP_NF_TARGET_NETMAP is not set +# CONFIG_IP_NF_TARGET_SAME is not set +# CONFIG_IP_NF_NAT_SNMP_BASIC is not set +CONFIG_IP_NF_NAT_FTP=m +# CONFIG_IP_NF_MANGLE is not set +# CONFIG_IP_NF_RAW is not set +# CONFIG_IP_NF_ARPTABLES is not set + +# +# Bridge: Netfilter Configuration +# +# CONFIG_BRIDGE_NF_EBTABLES is not set + +# +# SCTP Configuration (EXPERIMENTAL) +# +# CONFIG_IP_SCTP is not set +# CONFIG_ATM is not set +CONFIG_BRIDGE=y +# CONFIG_VLAN_8021Q is not set +# CONFIG_DECNET is not set +# CONFIG_LLC2 is not set +# CONFIG_IPX is not set +# CONFIG_ATALK is not set +# CONFIG_X25 is not set +# CONFIG_LAPB is not set +# CONFIG_NET_DIVERT is not set +# CONFIG_ECONET is not set +# CONFIG_WAN_ROUTER is not set + +# +# QoS and/or fair queueing +# +# CONFIG_NET_SCHED is not set +# CONFIG_NET_CLS_ROUTE is not set + +# +# Network testing +# +# CONFIG_NET_PKTGEN is not set +# CONFIG_NETPOLL is not set +# CONFIG_NET_POLL_CONTROLLER is not set +# CONFIG_HAMRADIO is not set +# CONFIG_IRDA is not set +# CONFIG_BT is not set +CONFIG_NETDEVICES=y +# CONFIG_DUMMY is not set +# CONFIG_BONDING is not set +# CONFIG_EQUALIZER is not set +CONFIG_TUN=y + +# +# ARCnet devices +# +# CONFIG_ARCNET is not set + +# +# Ethernet (10 or 100Mbit) +# +CONFIG_NET_ETHERNET=y +CONFIG_MII=y +# CONFIG_HAPPYMEAL is not set +# CONFIG_SUNGEM is not set +CONFIG_NET_VENDOR_3COM=y +CONFIG_VORTEX=y +# CONFIG_TYPHOON is not set + +# +# Tulip family network device support +# +CONFIG_NET_TULIP=y +# CONFIG_DE2104X is not set +CONFIG_TULIP=y +# CONFIG_TULIP_MWI is not set +# CONFIG_TULIP_MMIO is not set +# CONFIG_TULIP_NAPI is not set +# CONFIG_DE4X5 is not set +# CONFIG_WINBOND_840 is not set +# CONFIG_DM9102 is not set +# CONFIG_HP100 is not set +CONFIG_NET_PCI=y +CONFIG_PCNET32=y +# CONFIG_AMD8111_ETH is not set +# CONFIG_ADAPTEC_STARFIRE is not set +# CONFIG_B44 is not set +# CONFIG_FORCEDETH is not set +# CONFIG_DGRS is not set +# CONFIG_EEPRO100 is not set +CONFIG_E100=y +# CONFIG_FEALNX is not set +# CONFIG_NATSEMI is not set +CONFIG_NE2K_PCI=y +# CONFIG_8139CP is not set +CONFIG_8139TOO=y +CONFIG_8139TOO_PIO=y +# CONFIG_8139TOO_TUNE_TWISTER is not set +# CONFIG_8139TOO_8129 is not set +# CONFIG_8139_OLD_RX_RESET is not set +# CONFIG_SIS900 is not set +# CONFIG_EPIC100 is not set +# CONFIG_SUNDANCE is not set +# CONFIG_TLAN is not set +CONFIG_VIA_RHINE=y +# CONFIG_VIA_RHINE_MMIO is not set + +# +# Ethernet (1000 Mbit) +# +CONFIG_ACENIC=y +# CONFIG_ACENIC_OMIT_TIGON_I is not set +# CONFIG_DL2K is not set +CONFIG_E1000=y +# CONFIG_E1000_NAPI is not set +# CONFIG_NS83820 is not set +# CONFIG_HAMACHI is not set +# CONFIG_YELLOWFIN is not set +# CONFIG_R8169 is not set +CONFIG_SK98LIN=y +# CONFIG_VIA_VELOCITY is not set +CONFIG_TIGON3=y +# CONFIG_BNX2 is not set + +# +# Ethernet (10000 Mbit) +# +# CONFIG_IXGB is not set +# CONFIG_S2IO is not set + +# +# Token Ring devices +# +# CONFIG_TR is not set + +# +# Wireless LAN (non-hamradio) +# +# CONFIG_NET_RADIO is not set + +# +# Wan interfaces +# +# CONFIG_WAN is not set +# CONFIG_FDDI is not set +# CONFIG_HIPPI is not set +# CONFIG_PPP is not set +# CONFIG_SLIP is not set +# CONFIG_NET_FC is not set +# CONFIG_SHAPER is not set +# CONFIG_NETCONSOLE is not set + +# +# ISDN subsystem +# +# CONFIG_ISDN is not set + +# +# Telephony Support +# +# CONFIG_PHONE is not set + +# +# Input device support +# +CONFIG_INPUT=y + +# +# Userland interfaces +# +CONFIG_INPUT_MOUSEDEV=y +CONFIG_INPUT_MOUSEDEV_PSAUX=y +CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024 +CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 +# CONFIG_INPUT_JOYDEV is not set +# CONFIG_INPUT_TSDEV is not set +# CONFIG_INPUT_EVDEV is not set +# CONFIG_INPUT_EVBUG is not set + +# +# Input Device Drivers +# +CONFIG_INPUT_KEYBOARD=y +CONFIG_KEYBOARD_ATKBD=y +# CONFIG_KEYBOARD_SUNKBD is not set +# CONFIG_KEYBOARD_LKKBD is not set +# CONFIG_KEYBOARD_XTKBD is not set +# CONFIG_KEYBOARD_NEWTON is not set +CONFIG_INPUT_MOUSE=y +CONFIG_MOUSE_PS2=y +# CONFIG_MOUSE_SERIAL is not set +# CONFIG_MOUSE_VSXXXAA is not set +# CONFIG_INPUT_JOYSTICK is not set +# CONFIG_INPUT_TOUCHSCREEN is not set +# CONFIG_INPUT_MISC is not set + +# +# Hardware I/O ports +# +CONFIG_SERIO=y +CONFIG_SERIO_I8042=y +CONFIG_SERIO_SERPORT=y +# CONFIG_SERIO_CT82C710 is not set +# CONFIG_SERIO_PCIPS2 is not set +CONFIG_SERIO_LIBPS2=y +# CONFIG_SERIO_RAW is not set +# CONFIG_GAMEPORT is not set + +# +# Character devices +# +CONFIG_VT=y +CONFIG_VT_CONSOLE=y +CONFIG_HW_CONSOLE=y +# CONFIG_SERIAL_NONSTANDARD is not set + +# +# Serial drivers +# +# CONFIG_SERIAL_8250 is not set + +# +# Non-8250 serial port support +# +# CONFIG_SERIAL_JSM is not set +CONFIG_UNIX98_PTYS=y +CONFIG_LEGACY_PTYS=y +CONFIG_LEGACY_PTY_COUNT=256 + +# +# IPMI +# +# CONFIG_IPMI_HANDLER is not set + +# +# Watchdog Cards +# +# CONFIG_WATCHDOG is not set +# CONFIG_HW_RANDOM is not set +# CONFIG_NVRAM is not set +# CONFIG_RTC is not set +# CONFIG_GEN_RTC is not set +# CONFIG_DTLK is not set +# CONFIG_R3964 is not set +# CONFIG_APPLICOM is not set +# CONFIG_SONYPI is not set + +# +# Ftape, the floppy tape device driver +# +# CONFIG_FTAPE is not set +CONFIG_AGP=m +CONFIG_AGP_ALI=m +CONFIG_AGP_ATI=m +CONFIG_AGP_AMD=m +CONFIG_AGP_AMD64=m +CONFIG_AGP_INTEL=m +CONFIG_AGP_NVIDIA=m +CONFIG_AGP_SIS=m +CONFIG_AGP_SWORKS=m +CONFIG_AGP_VIA=m +# CONFIG_AGP_EFFICEON is not set +CONFIG_DRM=m +CONFIG_DRM_TDFX=m +# CONFIG_DRM_GAMMA is not set +CONFIG_DRM_R128=m +CONFIG_DRM_RADEON=m +CONFIG_DRM_I810=m +CONFIG_DRM_I830=m +CONFIG_DRM_I915=m +CONFIG_DRM_MGA=m +CONFIG_DRM_SIS=m +# CONFIG_MWAVE is not set +# CONFIG_RAW_DRIVER is not set +# CONFIG_HPET is not set +# CONFIG_HANGCHECK_TIMER is not set + +# +# TPM devices +# +# CONFIG_TCG_TPM is not set + +# +# I2C support +# +# CONFIG_I2C is not set + +# +# Dallas's 1-wire bus +# +# CONFIG_W1 is not set + +# +# Misc devices +# +# CONFIG_IBM_ASM is not set + +# +# Multimedia devices +# +# CONFIG_VIDEO_DEV is not set + +# +# Digital Video Broadcasting Devices +# +# CONFIG_DVB is not set + +# +# Graphics support +# +# CONFIG_FB is not set +# CONFIG_VIDEO_SELECT is not set + +# +# Console display driver support +# +CONFIG_VGA_CONSOLE=y +CONFIG_DUMMY_CONSOLE=y + +# +# Sound +# +# CONFIG_SOUND is not set + +# +# USB support +# +CONFIG_USB_ARCH_HAS_HCD=y +CONFIG_USB_ARCH_HAS_OHCI=y +CONFIG_USB=y +# CONFIG_USB_DEBUG is not set + +# +# Miscellaneous USB options +# +# CONFIG_USB_DEVICEFS is not set +# CONFIG_USB_BANDWIDTH is not set +# CONFIG_USB_DYNAMIC_MINORS is not set +# CONFIG_USB_OTG is not set + +# +# USB Host Controller Drivers +# +# CONFIG_USB_EHCI_HCD is not set +CONFIG_USB_OHCI_HCD=y +# CONFIG_USB_OHCI_BIG_ENDIAN is not set +CONFIG_USB_OHCI_LITTLE_ENDIAN=y +CONFIG_USB_UHCI_HCD=y +# CONFIG_USB_SL811_HCD is not set + +# +# USB Device Class drivers +# +# CONFIG_USB_BLUETOOTH_TTY is not set +# CONFIG_USB_ACM is not set +# CONFIG_USB_PRINTER is not set + +# +# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed; see USB_STORAGE Help for more information +# +# CONFIG_USB_STORAGE is not set + +# +# USB Input Devices +# +CONFIG_USB_HID=y +CONFIG_USB_HIDINPUT=y +# CONFIG_HID_FF is not set +# CONFIG_USB_HIDDEV is not set +# CONFIG_USB_AIPTEK is not set +# CONFIG_USB_WACOM is not set +# CONFIG_USB_KBTAB is not set +# CONFIG_USB_POWERMATE is not set +# CONFIG_USB_MTOUCH is not set +# CONFIG_USB_EGALAX is not set +# CONFIG_USB_XPAD is not set +# CONFIG_USB_ATI_REMOTE is not set + +# +# USB Imaging devices +# +# CONFIG_USB_MDC800 is not set +# CONFIG_USB_MICROTEK is not set + +# +# USB Multimedia devices +# +# CONFIG_USB_DABUSB is not set + +# +# Video4Linux support is needed for USB Multimedia device support +# + +# +# USB Network Adapters +# +# CONFIG_USB_CATC is not set +# CONFIG_USB_KAWETH is not set +# CONFIG_USB_PEGASUS is not set +# CONFIG_USB_RTL8150 is not set +# CONFIG_USB_USBNET is not set +CONFIG_USB_MON=y + +# +# USB port drivers +# + +# +# USB Serial Converter support +# +# CONFIG_USB_SERIAL is not set + +# +# USB Miscellaneous drivers +# +# CONFIG_USB_EMI62 is not set +# CONFIG_USB_EMI26 is not set +# CONFIG_USB_AUERSWALD is not set +# CONFIG_USB_RIO500 is not set +# CONFIG_USB_LEGOTOWER is not set +# CONFIG_USB_LCD is not set +# CONFIG_USB_LED is not set +# CONFIG_USB_CYTHERM is not set +# CONFIG_USB_PHIDGETKIT is not set +# CONFIG_USB_PHIDGETSERVO is not set +# CONFIG_USB_IDMOUSE is not set + +# +# USB ATM/DSL drivers +# + +# +# USB Gadget Support +# +# CONFIG_USB_GADGET is not set + +# +# MMC/SD Card support +# +# CONFIG_MMC is not set + +# +# InfiniBand support +# +# CONFIG_INFINIBAND is not set + +# +# File systems +# +CONFIG_EXT2_FS=y +# CONFIG_EXT2_FS_XATTR is not set +CONFIG_EXT3_FS=y +CONFIG_EXT3_FS_XATTR=y +# CONFIG_EXT3_FS_POSIX_ACL is not set +# CONFIG_EXT3_FS_SECURITY is not set +CONFIG_JBD=y +# CONFIG_JBD_DEBUG is not set +CONFIG_FS_MBCACHE=y +CONFIG_REISERFS_FS=y +# CONFIG_REISERFS_CHECK is not set +# CONFIG_REISERFS_PROC_INFO is not set +# CONFIG_REISERFS_FS_XATTR is not set +# CONFIG_JFS_FS is not set + +# +# XFS support +# +# CONFIG_XFS_FS is not set +# CONFIG_MINIX_FS is not set +# CONFIG_ROMFS_FS is not set +# CONFIG_QUOTA is not set +CONFIG_DNOTIFY=y +CONFIG_AUTOFS_FS=y +CONFIG_AUTOFS4_FS=y + +# +# CD-ROM/DVD Filesystems +# +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_ZISOFS_FS=y +# CONFIG_UDF_FS is not set + +# +# DOS/FAT/NT Filesystems +# +CONFIG_FAT_FS=m +CONFIG_MSDOS_FS=m +CONFIG_VFAT_FS=m +CONFIG_FAT_DEFAULT_CODEPAGE=437 +CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" +# CONFIG_NTFS_FS is not set + +# +# Pseudo filesystems +# +CONFIG_PROC_FS=y +CONFIG_PROC_KCORE=y +CONFIG_SYSFS=y +# CONFIG_DEVFS_FS is not set +# CONFIG_DEVPTS_FS_XATTR is not set +CONFIG_TMPFS=y +# CONFIG_TMPFS_XATTR is not set +# CONFIG_HUGETLB_PAGE is not set +CONFIG_RAMFS=y + +# +# Miscellaneous filesystems +# +# CONFIG_ADFS_FS is not set +# CONFIG_AFFS_FS is not set +# CONFIG_HFS_FS is not set +# CONFIG_HFSPLUS_FS is not set +# CONFIG_BEFS_FS is not set +# CONFIG_BFS_FS is not set +# CONFIG_EFS_FS is not set +CONFIG_CRAMFS=y +# CONFIG_VXFS_FS is not set +# CONFIG_HPFS_FS is not set +# CONFIG_QNX4FS_FS is not set +# CONFIG_SYSV_FS is not set +# CONFIG_UFS_FS is not set + +# +# Network File Systems +# +CONFIG_NFS_FS=y +CONFIG_NFS_V3=y +# CONFIG_NFS_V4 is not set +# CONFIG_NFS_DIRECTIO is not set +CONFIG_NFSD=m +CONFIG_NFSD_V3=y +# CONFIG_NFSD_V4 is not set +CONFIG_NFSD_TCP=y +CONFIG_ROOT_NFS=y +CONFIG_LOCKD=y +CONFIG_LOCKD_V4=y +CONFIG_EXPORTFS=m +CONFIG_SUNRPC=y +# CONFIG_RPCSEC_GSS_KRB5 is not set +# CONFIG_RPCSEC_GSS_SPKM3 is not set +# CONFIG_SMB_FS is not set +# CONFIG_CIFS is not set +# CONFIG_NCP_FS is not set +# CONFIG_CODA_FS is not set +# CONFIG_AFS_FS is not set + +# +# Partition Types +# +# CONFIG_PARTITION_ADVANCED is not set +CONFIG_MSDOS_PARTITION=y + +# +# Native Language Support +# +CONFIG_NLS=y +CONFIG_NLS_DEFAULT="iso8859-1" +CONFIG_NLS_CODEPAGE_437=y +# CONFIG_NLS_CODEPAGE_737 is not set +# CONFIG_NLS_CODEPAGE_775 is not set +# CONFIG_NLS_CODEPAGE_850 is not set +# CONFIG_NLS_CODEPAGE_852 is not set +# CONFIG_NLS_CODEPAGE_855 is not set +# CONFIG_NLS_CODEPAGE_857 is not set +# CONFIG_NLS_CODEPAGE_860 is not set +# CONFIG_NLS_CODEPAGE_861 is not set +# CONFIG_NLS_CODEPAGE_862 is not set +# CONFIG_NLS_CODEPAGE_863 is not set +# CONFIG_NLS_CODEPAGE_864 is not set +# CONFIG_NLS_CODEPAGE_865 is not set +# CONFIG_NLS_CODEPAGE_866 is not set +# CONFIG_NLS_CODEPAGE_869 is not set +# CONFIG_NLS_CODEPAGE_936 is not set +# CONFIG_NLS_CODEPAGE_950 is not set +# CONFIG_NLS_CODEPAGE_932 is not set +# CONFIG_NLS_CODEPAGE_949 is not set +# CONFIG_NLS_CODEPAGE_874 is not set +# CONFIG_NLS_ISO8859_8 is not set +# CONFIG_NLS_CODEPAGE_1250 is not set +# CONFIG_NLS_CODEPAGE_1251 is not set +# CONFIG_NLS_ASCII is not set +CONFIG_NLS_ISO8859_1=y +# CONFIG_NLS_ISO8859_2 is not set +# CONFIG_NLS_ISO8859_3 is not set +# CONFIG_NLS_ISO8859_4 is not set +# CONFIG_NLS_ISO8859_5 is not set +# CONFIG_NLS_ISO8859_6 is not set +# CONFIG_NLS_ISO8859_7 is not set +# CONFIG_NLS_ISO8859_9 is not set +# CONFIG_NLS_ISO8859_13 is not set +# CONFIG_NLS_ISO8859_14 is not set +# CONFIG_NLS_ISO8859_15 is not set +# CONFIG_NLS_KOI8_R is not set +# CONFIG_NLS_KOI8_U is not set +# CONFIG_NLS_UTF8 is not set + +# +# Kernel hacking +# +# CONFIG_PRINTK_TIME is not set +CONFIG_DEBUG_KERNEL=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_LOG_BUF_SHIFT=14 +# CONFIG_SCHEDSTATS is not set +# CONFIG_DEBUG_SLAB is not set +# CONFIG_DEBUG_SPINLOCK is not set +# CONFIG_DEBUG_SPINLOCK_SLEEP is not set +# CONFIG_DEBUG_KOBJECT is not set +# CONFIG_DEBUG_HIGHMEM is not set +CONFIG_DEBUG_BUGVERBOSE=y +# CONFIG_DEBUG_INFO is not set +# CONFIG_DEBUG_FS is not set +# CONFIG_FRAME_POINTER is not set +CONFIG_EARLY_PRINTK=y +# CONFIG_DEBUG_STACKOVERFLOW is not set +# CONFIG_KPROBES is not set +# CONFIG_DEBUG_STACK_USAGE is not set +# CONFIG_DEBUG_PAGEALLOC is not set +# CONFIG_4KSTACKS is not set +CONFIG_X86_FIND_SMP_CONFIG=y +CONFIG_X86_MPPARSE=y + +# +# Security options +# +# CONFIG_KEYS is not set +# CONFIG_SECURITY is not set + +# +# Cryptographic options +# +CONFIG_CRYPTO=y +CONFIG_CRYPTO_HMAC=y +# CONFIG_CRYPTO_NULL is not set +# CONFIG_CRYPTO_MD4 is not set +CONFIG_CRYPTO_MD5=m +CONFIG_CRYPTO_SHA1=m +# CONFIG_CRYPTO_SHA256 is not set +# CONFIG_CRYPTO_SHA512 is not set +# CONFIG_CRYPTO_WP512 is not set +# CONFIG_CRYPTO_TGR192 is not set +CONFIG_CRYPTO_DES=m +# CONFIG_CRYPTO_BLOWFISH is not set +# CONFIG_CRYPTO_TWOFISH is not set +# CONFIG_CRYPTO_SERPENT is not set +# CONFIG_CRYPTO_AES_586 is not set +# CONFIG_CRYPTO_CAST5 is not set +# CONFIG_CRYPTO_CAST6 is not set +# CONFIG_CRYPTO_TEA is not set +# CONFIG_CRYPTO_ARC4 is not set +# CONFIG_CRYPTO_KHAZAD is not set +# CONFIG_CRYPTO_ANUBIS is not set +# CONFIG_CRYPTO_DEFLATE is not set +# CONFIG_CRYPTO_MICHAEL_MIC is not set +CONFIG_CRYPTO_CRC32C=m +# CONFIG_CRYPTO_TEST is not set + +# +# Hardware crypto devices +# +# CONFIG_CRYPTO_DEV_PADLOCK is not set +CONFIG_XEN=y +CONFIG_NO_IDLE_HZ=y + +# +# XEN +# +CONFIG_XEN_PRIVILEGED_GUEST=y +# CONFIG_XEN_UNPRIVILEGED_GUEST is not set +CONFIG_XEN_PHYSDEV_ACCESS=y +CONFIG_XEN_BLKDEV_BACKEND=y +# CONFIG_XEN_BLKDEV_TAP_BE is not set +CONFIG_XEN_NETDEV_BACKEND=y +# CONFIG_XEN_NETDEV_PIPELINED_TRANSMITTER is not set +# CONFIG_XEN_TPMDEV_BACKEND is not set +CONFIG_XEN_BLKDEV_FRONTEND=y +CONFIG_XEN_NETDEV_FRONTEND=y +# CONFIG_XEN_BLKDEV_TAP is not set +# CONFIG_XEN_TPMDEV_FRONTEND is not set +# CONFIG_XEN_SHADOW_MODE is not set +CONFIG_XEN_SCRUB_PAGES=y +CONFIG_XEN_DISABLE_SERIAL=y +CONFIG_HAVE_ARCH_ALLOC_SKB=y +CONFIG_HAVE_ARCH_DEV_ALLOC_SKB=y + +# +# Library routines +# +# CONFIG_CRC_CCITT is not set +CONFIG_CRC32=y +CONFIG_LIBCRC32C=y +CONFIG_ZLIB_INFLATE=y +CONFIG_GENERIC_HARDIRQS=y +CONFIG_GENERIC_IRQ_PROBE=y +CONFIG_X86_BIOS_REBOOT=y +CONFIG_PC=y diff -r 690fc13948db -r fd9b2c1bb577 buildconfigs/linux-defconfig_xen0_x86_64 --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/buildconfigs/linux-defconfig_xen0_x86_64 Mon Jan 30 17:18:27 2006 @@ -0,0 +1,1162 @@ +# +# Automatically generated make config: don't edit +# Linux kernel version: 2.6.12.6-xen0 +# Wed Jan 25 17:27:39 2006 +# +CONFIG_X86_64=y +CONFIG_64BIT=y +CONFIG_X86=y +CONFIG_MMU=y +CONFIG_RWSEM_GENERIC_SPINLOCK=y +CONFIG_GENERIC_CALIBRATE_DELAY=y +CONFIG_X86_CMPXCHG=y +CONFIG_EARLY_PRINTK=y +CONFIG_GENERIC_ISA_DMA=y +CONFIG_GENERIC_IOMAP=y + +# +# Code maturity level options +# +CONFIG_EXPERIMENTAL=y +# CONFIG_CLEAN_COMPILE is not set +CONFIG_BROKEN=y +CONFIG_BROKEN_ON_SMP=y +CONFIG_INIT_ENV_ARG_LIMIT=32 + +# +# General setup +# +CONFIG_LOCALVERSION="" +CONFIG_SWAP=y +CONFIG_SYSVIPC=y +# CONFIG_POSIX_MQUEUE is not set +# CONFIG_BSD_PROCESS_ACCT is not set +CONFIG_SYSCTL=y +# CONFIG_AUDIT is not set +CONFIG_HOTPLUG=y +CONFIG_KOBJECT_UEVENT=y +# CONFIG_IKCONFIG is not set +# CONFIG_EMBEDDED is not set +CONFIG_KALLSYMS=y +# CONFIG_KALLSYMS_ALL is not set +# CONFIG_KALLSYMS_EXTRA_PASS is not set +CONFIG_PRINTK=y +CONFIG_BUG=y +CONFIG_BASE_FULL=y +CONFIG_FUTEX=y +CONFIG_EPOLL=y +CONFIG_SHMEM=y +CONFIG_CC_ALIGN_FUNCTIONS=0 +CONFIG_CC_ALIGN_LABELS=0 +CONFIG_CC_ALIGN_LOOPS=0 +CONFIG_CC_ALIGN_JUMPS=0 +# CONFIG_TINY_SHMEM is not set +CONFIG_BASE_SMALL=0 + +# +# Loadable module support +# +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_MODULE_FORCE_UNLOAD is not set +CONFIG_OBSOLETE_MODPARM=y +# CONFIG_MODVERSIONS is not set +# CONFIG_MODULE_SRCVERSION_ALL is not set +CONFIG_KMOD=y + +# +# Processor type and features +# +# CONFIG_MK8 is not set +# CONFIG_MPSC is not set +CONFIG_GENERIC_CPU=y +CONFIG_X86_64_XEN=y +CONFIG_X86_L1_CACHE_BYTES=128 +CONFIG_X86_L1_CACHE_SHIFT=7 +CONFIG_X86_GOOD_APIC=y +CONFIG_MICROCODE=y +# CONFIG_X86_MSR is not set +# CONFIG_X86_CPUID is not set +CONFIG_X86_IO_APIC=y +CONFIG_X86_XEN_GENAPIC=y +CONFIG_X86_LOCAL_APIC=y +# CONFIG_SMP is not set +# CONFIG_NUMA is not set +CONFIG_SWIOTLB=y +CONFIG_DUMMY_IOMMU=y +CONFIG_SECCOMP=y +CONFIG_GENERIC_HARDIRQS=y +CONFIG_GENERIC_IRQ_PROBE=y +CONFIG_ISA_DMA_API=y + +# +# Power management options +# + +# +# ACPI (Advanced Configuration and Power Interface) Support +# +CONFIG_ACPI=y +CONFIG_ACPI_BOOT=y +CONFIG_ACPI_INTERPRETER=y +CONFIG_ACPI_AC=m +CONFIG_ACPI_BATTERY=m +CONFIG_ACPI_BUTTON=m +CONFIG_ACPI_VIDEO=m +CONFIG_ACPI_FAN=m +CONFIG_ACPI_PROCESSOR=m +CONFIG_ACPI_THERMAL=m +CONFIG_ACPI_ASUS=m +CONFIG_ACPI_IBM=m +CONFIG_ACPI_TOSHIBA=m +CONFIG_ACPI_BLACKLIST_YEAR=0 +# CONFIG_ACPI_DEBUG is not set +CONFIG_ACPI_BUS=y +CONFIG_ACPI_EC=y +CONFIG_ACPI_POWER=y +CONFIG_ACPI_PCI=y +CONFIG_ACPI_SYSTEM=y +# CONFIG_ACPI_CONTAINER is not set + +# +# Bus options (PCI etc.) +# +CONFIG_PCI=y +CONFIG_PCI_DIRECT=y +# CONFIG_PCI_MMCONFIG is not set +# CONFIG_UNORDERED_IO is not set + +# +# Executable file formats / Emulations +# +CONFIG_BINFMT_ELF=y +CONFIG_BINFMT_MISC=y +CONFIG_IA32_EMULATION=y +# CONFIG_IA32_AOUT is not set +CONFIG_COMPAT=y +CONFIG_SYSVIPC_COMPAT=y +CONFIG_UID16=y + +# +# Device Drivers +# + +# +# Generic Driver Options +# +CONFIG_STANDALONE=y +# CONFIG_PREVENT_FIRMWARE_BUILD is not set +# CONFIG_FW_LOADER is not set +# CONFIG_DEBUG_DRIVER is not set + +# +# Memory Technology Devices (MTD) +# +# CONFIG_MTD is not set + +# +# Parallel port support +# +# CONFIG_PARPORT is not set + +# +# Plug and Play support +# +# CONFIG_PNP is not set + +# +# Block devices +# +CONFIG_BLK_DEV_FD=y +# CONFIG_BLK_CPQ_DA is not set +CONFIG_BLK_CPQ_CISS_DA=y +# CONFIG_CISS_SCSI_TAPE is not set +# CONFIG_BLK_DEV_DAC960 is not set +# CONFIG_BLK_DEV_UMEM is not set +# CONFIG_BLK_DEV_COW_COMMON is not set +CONFIG_BLK_DEV_LOOP=y +# CONFIG_BLK_DEV_CRYPTOLOOP is not set +# CONFIG_BLK_DEV_NBD is not set +# CONFIG_BLK_DEV_SX8 is not set +# CONFIG_BLK_DEV_UB is not set +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_COUNT=16 +CONFIG_BLK_DEV_RAM_SIZE=16384 +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="" +# CONFIG_LBD is not set +# CONFIG_CDROM_PKTCDVD is not set + +# +# IO Schedulers +# +CONFIG_IOSCHED_NOOP=y +CONFIG_IOSCHED_AS=y +CONFIG_IOSCHED_DEADLINE=y +CONFIG_IOSCHED_CFQ=y +# CONFIG_ATA_OVER_ETH is not set + +# +# ATA/ATAPI/MFM/RLL support +# +CONFIG_IDE=y +CONFIG_BLK_DEV_IDE=y + +# +# Please see Documentation/ide.txt for help/info on IDE drives +# +# CONFIG_BLK_DEV_IDE_SATA is not set +# CONFIG_BLK_DEV_HD_IDE is not set +CONFIG_BLK_DEV_IDEDISK=y +# CONFIG_IDEDISK_MULTI_MODE is not set +CONFIG_BLK_DEV_IDECD=y +# CONFIG_BLK_DEV_IDETAPE is not set +# CONFIG_BLK_DEV_IDEFLOPPY is not set +# CONFIG_BLK_DEV_IDESCSI is not set +# CONFIG_IDE_TASK_IOCTL is not set + +# +# IDE chipset support/bugfixes +# +CONFIG_IDE_GENERIC=y +# CONFIG_BLK_DEV_CMD640 is not set +CONFIG_BLK_DEV_IDEPCI=y +# CONFIG_IDEPCI_SHARE_IRQ is not set +# CONFIG_BLK_DEV_OFFBOARD is not set +CONFIG_BLK_DEV_GENERIC=y +# CONFIG_BLK_DEV_OPTI621 is not set +# CONFIG_BLK_DEV_RZ1000 is not set +CONFIG_BLK_DEV_IDEDMA_PCI=y +# CONFIG_BLK_DEV_IDEDMA_FORCED is not set +CONFIG_IDEDMA_PCI_AUTO=y +# CONFIG_IDEDMA_ONLYDISK is not set +# CONFIG_BLK_DEV_AEC62XX is not set +# CONFIG_BLK_DEV_ALI15X3 is not set +# CONFIG_BLK_DEV_AMD74XX is not set +# CONFIG_BLK_DEV_ATIIXP is not set +# CONFIG_BLK_DEV_CMD64X is not set +# CONFIG_BLK_DEV_TRIFLEX is not set +# CONFIG_BLK_DEV_CY82C693 is not set +# CONFIG_BLK_DEV_CS5520 is not set +# CONFIG_BLK_DEV_CS5530 is not set +# CONFIG_BLK_DEV_HPT34X is not set +# CONFIG_BLK_DEV_HPT366 is not set +# CONFIG_BLK_DEV_SC1200 is not set +CONFIG_BLK_DEV_PIIX=y +# CONFIG_BLK_DEV_NS87415 is not set +# CONFIG_BLK_DEV_PDC202XX_OLD is not set +# CONFIG_BLK_DEV_PDC202XX_NEW is not set +CONFIG_BLK_DEV_SVWKS=y +# CONFIG_BLK_DEV_SIIMAGE is not set +# CONFIG_BLK_DEV_SIS5513 is not set +# CONFIG_BLK_DEV_SLC90E66 is not set +# CONFIG_BLK_DEV_TRM290 is not set +# CONFIG_BLK_DEV_VIA82CXXX is not set +# CONFIG_IDE_ARM is not set +CONFIG_BLK_DEV_IDEDMA=y +# CONFIG_IDEDMA_IVB is not set +CONFIG_IDEDMA_AUTO=y +# CONFIG_BLK_DEV_HD is not set + +# +# SCSI device support +# +CONFIG_SCSI=y +CONFIG_SCSI_PROC_FS=y + +# +# SCSI support type (disk, tape, CD-ROM) +# +CONFIG_BLK_DEV_SD=y +# CONFIG_CHR_DEV_ST is not set +# CONFIG_CHR_DEV_OSST is not set +# CONFIG_BLK_DEV_SR is not set +# CONFIG_CHR_DEV_SG is not set + +# +# Some SCSI devices (e.g. CD jukebox) support multiple LUNs +# +# CONFIG_SCSI_MULTI_LUN is not set +# CONFIG_SCSI_CONSTANTS is not set +# CONFIG_SCSI_LOGGING is not set + +# +# SCSI Transport Attributes +# +CONFIG_SCSI_SPI_ATTRS=y +# CONFIG_SCSI_FC_ATTRS is not set +# CONFIG_SCSI_ISCSI_ATTRS is not set + +# +# SCSI low-level drivers +# +CONFIG_BLK_DEV_3W_XXXX_RAID=y +# CONFIG_SCSI_3W_9XXX is not set +# CONFIG_SCSI_ACARD is not set +CONFIG_SCSI_AACRAID=y +CONFIG_SCSI_AIC7XXX=y +CONFIG_AIC7XXX_CMDS_PER_DEVICE=32 +CONFIG_AIC7XXX_RESET_DELAY_MS=15000 +# CONFIG_AIC7XXX_BUILD_FIRMWARE is not set +CONFIG_AIC7XXX_DEBUG_ENABLE=y +CONFIG_AIC7XXX_DEBUG_MASK=0 +CONFIG_AIC7XXX_REG_PRETTY_PRINT=y +# CONFIG_SCSI_AIC7XXX_OLD is not set +CONFIG_SCSI_AIC79XX=y +CONFIG_AIC79XX_CMDS_PER_DEVICE=32 +CONFIG_AIC79XX_RESET_DELAY_MS=15000 +# CONFIG_AIC79XX_BUILD_FIRMWARE is not set +# CONFIG_AIC79XX_ENABLE_RD_STRM is not set +CONFIG_AIC79XX_DEBUG_ENABLE=y +CONFIG_AIC79XX_DEBUG_MASK=0 +CONFIG_AIC79XX_REG_PRETTY_PRINT=y +# CONFIG_SCSI_ADVANSYS is not set +CONFIG_MEGARAID_NEWGEN=y +# CONFIG_MEGARAID_MM is not set +CONFIG_SCSI_SATA=y +# CONFIG_SCSI_SATA_AHCI is not set +# CONFIG_SCSI_SATA_SVW is not set +CONFIG_SCSI_ATA_PIIX=y +# CONFIG_SCSI_SATA_NV is not set +CONFIG_SCSI_SATA_PROMISE=y +# CONFIG_SCSI_SATA_QSTOR is not set +CONFIG_SCSI_SATA_SX4=y +CONFIG_SCSI_SATA_SIL=y +# CONFIG_SCSI_SATA_SIS is not set +# CONFIG_SCSI_SATA_ULI is not set +# CONFIG_SCSI_SATA_VIA is not set +# CONFIG_SCSI_SATA_VITESSE is not set +CONFIG_SCSI_BUSLOGIC=y +# CONFIG_SCSI_OMIT_FLASHPOINT is not set +# CONFIG_SCSI_CPQFCTS is not set +# CONFIG_SCSI_DMX3191D is not set +# CONFIG_SCSI_EATA is not set +# CONFIG_SCSI_EATA_PIO is not set +# CONFIG_SCSI_FUTURE_DOMAIN is not set +# CONFIG_SCSI_GDTH is not set +# CONFIG_SCSI_IPS is not set +# CONFIG_SCSI_INITIO is not set +# CONFIG_SCSI_INIA100 is not set +# CONFIG_SCSI_SYM53C8XX_2 is not set +# CONFIG_SCSI_IPR is not set +# CONFIG_SCSI_PCI2000 is not set +# CONFIG_SCSI_PCI2220I is not set +# CONFIG_SCSI_QLOGIC_ISP is not set +# CONFIG_SCSI_QLOGIC_FC is not set +# CONFIG_SCSI_QLOGIC_1280 is not set +CONFIG_SCSI_QLA2XXX=y +# CONFIG_SCSI_QLA21XX is not set +# CONFIG_SCSI_QLA22XX is not set +# CONFIG_SCSI_QLA2300 is not set +# CONFIG_SCSI_QLA2322 is not set +# CONFIG_SCSI_QLA6312 is not set +# CONFIG_SCSI_LPFC is not set +# CONFIG_SCSI_DC395x is not set +# CONFIG_SCSI_DC390T is not set +# CONFIG_SCSI_DEBUG is not set + +# +# Multi-device support (RAID and LVM) +# +CONFIG_MD=y +CONFIG_BLK_DEV_MD=y +CONFIG_MD_LINEAR=y +CONFIG_MD_RAID0=y +CONFIG_MD_RAID1=y +# CONFIG_MD_RAID10 is not set +# CONFIG_MD_RAID5 is not set +# CONFIG_MD_RAID6 is not set +CONFIG_MD_MULTIPATH=y +# CONFIG_MD_FAULTY is not set +CONFIG_BLK_DEV_DM=y +CONFIG_DM_CRYPT=y +CONFIG_DM_SNAPSHOT=y +CONFIG_DM_MIRROR=y +# CONFIG_DM_ZERO is not set +CONFIG_DM_MULTIPATH=y +CONFIG_DM_MULTIPATH_EMC=y + +# +# Fusion MPT device support +# +CONFIG_FUSION=y +CONFIG_FUSION_MAX_SGE=40 +# CONFIG_FUSION_CTL is not set + +# +# IEEE 1394 (FireWire) support +# +# CONFIG_IEEE1394 is not set + +# +# I2O device support +# +# CONFIG_I2O is not set + +# +# Networking support +# +CONFIG_NET=y + +# +# Networking options +# +CONFIG_PACKET=y +# CONFIG_PACKET_MMAP is not set +CONFIG_UNIX=y +# CONFIG_NET_KEY is not set +CONFIG_INET=y +# CONFIG_IP_MULTICAST is not set +# CONFIG_IP_ADVANCED_ROUTER is not set +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +# CONFIG_IP_PNP_BOOTP is not set +# CONFIG_IP_PNP_RARP is not set +# CONFIG_NET_IPIP is not set +# CONFIG_NET_IPGRE is not set +# CONFIG_ARPD is not set +# CONFIG_SYN_COOKIES is not set +# CONFIG_INET_AH is not set +# CONFIG_INET_ESP is not set +# CONFIG_INET_IPCOMP is not set +# CONFIG_INET_TUNNEL is not set +CONFIG_IP_TCPDIAG=y +# CONFIG_IP_TCPDIAG_IPV6 is not set + +# +# IP: Virtual Server Configuration +# +# CONFIG_IP_VS is not set +# CONFIG_IPV6 is not set +CONFIG_NETFILTER=y +# CONFIG_NETFILTER_DEBUG is not set +CONFIG_BRIDGE_NETFILTER=y + +# +# IP: Netfilter Configuration +# +CONFIG_IP_NF_CONNTRACK=m +CONFIG_IP_NF_CT_ACCT=y +# CONFIG_IP_NF_CONNTRACK_MARK is not set +# CONFIG_IP_NF_CT_PROTO_SCTP is not set +CONFIG_IP_NF_FTP=m +# CONFIG_IP_NF_IRC is not set +# CONFIG_IP_NF_TFTP is not set +# CONFIG_IP_NF_AMANDA is not set +# CONFIG_IP_NF_QUEUE is not set +CONFIG_IP_NF_IPTABLES=m +# CONFIG_IP_NF_MATCH_LIMIT is not set +CONFIG_IP_NF_MATCH_IPRANGE=m +# CONFIG_IP_NF_MATCH_MAC is not set +# CONFIG_IP_NF_MATCH_PKTTYPE is not set +# CONFIG_IP_NF_MATCH_MARK is not set +# CONFIG_IP_NF_MATCH_MULTIPORT is not set +# CONFIG_IP_NF_MATCH_TOS is not set +# CONFIG_IP_NF_MATCH_RECENT is not set +# CONFIG_IP_NF_MATCH_ECN is not set +# CONFIG_IP_NF_MATCH_DSCP is not set +# CONFIG_IP_NF_MATCH_AH_ESP is not set +# CONFIG_IP_NF_MATCH_LENGTH is not set +# CONFIG_IP_NF_MATCH_TTL is not set +# CONFIG_IP_NF_MATCH_TCPMSS is not set +# CONFIG_IP_NF_MATCH_HELPER is not set +# CONFIG_IP_NF_MATCH_STATE is not set +# CONFIG_IP_NF_MATCH_CONNTRACK is not set +# CONFIG_IP_NF_MATCH_OWNER is not set +CONFIG_IP_NF_MATCH_PHYSDEV=m +# CONFIG_IP_NF_MATCH_ADDRTYPE is not set +# CONFIG_IP_NF_MATCH_REALM is not set +# CONFIG_IP_NF_MATCH_SCTP is not set +# CONFIG_IP_NF_MATCH_COMMENT is not set +# CONFIG_IP_NF_MATCH_HASHLIMIT is not set +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_TARGET_REJECT=m +# CONFIG_IP_NF_TARGET_LOG is not set +# CONFIG_IP_NF_TARGET_ULOG is not set +# CONFIG_IP_NF_TARGET_TCPMSS is not set +CONFIG_IP_NF_NAT=m +CONFIG_IP_NF_NAT_NEEDED=y +CONFIG_IP_NF_TARGET_MASQUERADE=m +# CONFIG_IP_NF_TARGET_REDIRECT is not set +# CONFIG_IP_NF_TARGET_NETMAP is not set +# CONFIG_IP_NF_TARGET_SAME is not set +# CONFIG_IP_NF_NAT_SNMP_BASIC is not set +CONFIG_IP_NF_NAT_FTP=m +# CONFIG_IP_NF_MANGLE is not set +# CONFIG_IP_NF_RAW is not set +# CONFIG_IP_NF_ARPTABLES is not set + +# +# Bridge: Netfilter Configuration +# +# CONFIG_BRIDGE_NF_EBTABLES is not set + +# +# SCTP Configuration (EXPERIMENTAL) +# +# CONFIG_IP_SCTP is not set +# CONFIG_ATM is not set +CONFIG_BRIDGE=y +# CONFIG_VLAN_8021Q is not set +# CONFIG_DECNET is not set +# CONFIG_LLC2 is not set +# CONFIG_IPX is not set +# CONFIG_ATALK is not set +# CONFIG_X25 is not set +# CONFIG_LAPB is not set +# CONFIG_NET_DIVERT is not set +# CONFIG_ECONET is not set +# CONFIG_WAN_ROUTER is not set + +# +# QoS and/or fair queueing +# +# CONFIG_NET_SCHED is not set +# CONFIG_NET_CLS_ROUTE is not set + +# +# Network testing +# +# CONFIG_NET_PKTGEN is not set +# CONFIG_NETPOLL is not set +# CONFIG_NET_POLL_CONTROLLER is not set +# CONFIG_HAMRADIO is not set +# CONFIG_IRDA is not set +# CONFIG_BT is not set +CONFIG_NETDEVICES=y +# CONFIG_DUMMY is not set +# CONFIG_BONDING is not set +# CONFIG_EQUALIZER is not set +CONFIG_TUN=y + +# +# ARCnet devices +# +# CONFIG_ARCNET is not set + +# +# Ethernet (10 or 100Mbit) +# +CONFIG_NET_ETHERNET=y +CONFIG_MII=y +# CONFIG_HAPPYMEAL is not set +# CONFIG_SUNGEM is not set +CONFIG_NET_VENDOR_3COM=y +CONFIG_VORTEX=y +# CONFIG_TYPHOON is not set + +# +# Tulip family network device support +# +CONFIG_NET_TULIP=y +# CONFIG_DE2104X is not set +CONFIG_TULIP=y +# CONFIG_TULIP_MWI is not set +# CONFIG_TULIP_MMIO is not set +# CONFIG_TULIP_NAPI is not set +# CONFIG_DE4X5 is not set +# CONFIG_WINBOND_840 is not set +# CONFIG_DM9102 is not set +# CONFIG_HP100 is not set +CONFIG_NET_PCI=y +CONFIG_PCNET32=y +# CONFIG_AMD8111_ETH is not set +# CONFIG_ADAPTEC_STARFIRE is not set +# CONFIG_B44 is not set +# CONFIG_FORCEDETH is not set +# CONFIG_DGRS is not set +# CONFIG_EEPRO100 is not set +CONFIG_E100=y +# CONFIG_FEALNX is not set +# CONFIG_NATSEMI is not set +CONFIG_NE2K_PCI=y +# CONFIG_8139CP is not set +CONFIG_8139TOO=y +CONFIG_8139TOO_PIO=y +# CONFIG_8139TOO_TUNE_TWISTER is not set +# CONFIG_8139TOO_8129 is not set +# CONFIG_8139_OLD_RX_RESET is not set +# CONFIG_SIS900 is not set +# CONFIG_EPIC100 is not set +# CONFIG_SUNDANCE is not set +CONFIG_VIA_RHINE=y +# CONFIG_VIA_RHINE_MMIO is not set + +# +# Ethernet (1000 Mbit) +# +CONFIG_ACENIC=y +# CONFIG_ACENIC_OMIT_TIGON_I is not set +# CONFIG_DL2K is not set +CONFIG_E1000=y +# CONFIG_E1000_NAPI is not set +# CONFIG_NS83820 is not set +# CONFIG_HAMACHI is not set +# CONFIG_YELLOWFIN is not set +# CONFIG_R8169 is not set +CONFIG_SK98LIN=y +# CONFIG_VIA_VELOCITY is not set +CONFIG_TIGON3=y +# CONFIG_BNX2 is not set + +# +# Ethernet (10000 Mbit) +# +# CONFIG_IXGB is not set +# CONFIG_S2IO is not set + +# +# Token Ring devices +# +# CONFIG_TR is not set + +# +# Wireless LAN (non-hamradio) +# +# CONFIG_NET_RADIO is not set + +# +# Wan interfaces +# +# CONFIG_WAN is not set +# CONFIG_FDDI is not set +# CONFIG_HIPPI is not set +# CONFIG_PPP is not set +# CONFIG_SLIP is not set +# CONFIG_NET_FC is not set +# CONFIG_SHAPER is not set +# CONFIG_NETCONSOLE is not set + +# +# ISDN subsystem +# +# CONFIG_ISDN is not set + +# +# Telephony Support +# +# CONFIG_PHONE is not set + +# +# Input device support +# +CONFIG_INPUT=y + +# +# Userland interfaces +# +CONFIG_INPUT_MOUSEDEV=y +CONFIG_INPUT_MOUSEDEV_PSAUX=y +CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024 +CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 +# CONFIG_INPUT_JOYDEV is not set +# CONFIG_INPUT_TSDEV is not set +# CONFIG_INPUT_EVDEV is not set +# CONFIG_INPUT_EVBUG is not set + +# +# Input Device Drivers +# +CONFIG_INPUT_KEYBOARD=y +CONFIG_KEYBOARD_ATKBD=y +# CONFIG_KEYBOARD_SUNKBD is not set +# CONFIG_KEYBOARD_LKKBD is not set +# CONFIG_KEYBOARD_XTKBD is not set +# CONFIG_KEYBOARD_NEWTON is not set +CONFIG_INPUT_MOUSE=y +CONFIG_MOUSE_PS2=y +# CONFIG_MOUSE_SERIAL is not set +# CONFIG_MOUSE_VSXXXAA is not set +# CONFIG_INPUT_JOYSTICK is not set +# CONFIG_INPUT_TOUCHSCREEN is not set +# CONFIG_INPUT_MISC is not set + +# +# Hardware I/O ports +# +CONFIG_SERIO=y +CONFIG_SERIO_I8042=y +CONFIG_SERIO_SERPORT=y +# CONFIG_SERIO_CT82C710 is not set +# CONFIG_SERIO_PCIPS2 is not set +CONFIG_SERIO_LIBPS2=y +# CONFIG_SERIO_RAW is not set +# CONFIG_GAMEPORT is not set + +# +# Character devices +# +CONFIG_VT=y +CONFIG_VT_CONSOLE=y +CONFIG_HW_CONSOLE=y +# CONFIG_SERIAL_NONSTANDARD is not set + +# +# Serial drivers +# +# CONFIG_SERIAL_8250 is not set + +# +# Non-8250 serial port support +# +# CONFIG_SERIAL_JSM is not set +CONFIG_UNIX98_PTYS=y +CONFIG_LEGACY_PTYS=y +CONFIG_LEGACY_PTY_COUNT=256 + +# +# IPMI +# +# CONFIG_IPMI_HANDLER is not set + +# +# Watchdog Cards +# +# CONFIG_WATCHDOG is not set +# CONFIG_HW_RANDOM is not set +# CONFIG_NVRAM is not set +CONFIG_RTC=y +# CONFIG_DTLK is not set +# CONFIG_R3964 is not set +# CONFIG_APPLICOM is not set + +# +# Ftape, the floppy tape device driver +# +# CONFIG_FTAPE is not set +CONFIG_AGP=m +CONFIG_AGP_AMD64=m +# CONFIG_AGP_INTEL is not set +CONFIG_DRM=m +CONFIG_DRM_TDFX=m +# CONFIG_DRM_GAMMA is not set +CONFIG_DRM_R128=m +CONFIG_DRM_RADEON=m +CONFIG_DRM_MGA=m +CONFIG_DRM_SIS=m +# CONFIG_MWAVE is not set +# CONFIG_RAW_DRIVER is not set +# CONFIG_HPET is not set +# CONFIG_HANGCHECK_TIMER is not set + +# +# TPM devices +# +# CONFIG_TCG_TPM is not set + +# +# I2C support +# +# CONFIG_I2C is not set + +# +# Dallas's 1-wire bus +# +# CONFIG_W1 is not set + +# +# Misc devices +# +# CONFIG_IBM_ASM is not set + +# +# Multimedia devices +# +# CONFIG_VIDEO_DEV is not set + +# +# Digital Video Broadcasting Devices +# +# CONFIG_DVB is not set + +# +# Graphics support +# +# CONFIG_FB is not set +# CONFIG_VIDEO_SELECT is not set + +# +# Console display driver support +# +CONFIG_VGA_CONSOLE=y +CONFIG_DUMMY_CONSOLE=y + +# +# Sound +# +# CONFIG_SOUND is not set + +# +# USB support +# +CONFIG_USB_ARCH_HAS_HCD=y +CONFIG_USB_ARCH_HAS_OHCI=y +CONFIG_USB=y +# CONFIG_USB_DEBUG is not set + +# +# Miscellaneous USB options +# +# CONFIG_USB_DEVICEFS is not set +# CONFIG_USB_BANDWIDTH is not set +# CONFIG_USB_DYNAMIC_MINORS is not set +# CONFIG_USB_OTG is not set + +# +# USB Host Controller Drivers +# +# CONFIG_USB_EHCI_HCD is not set +CONFIG_USB_OHCI_HCD=y +# CONFIG_USB_OHCI_BIG_ENDIAN is not set +CONFIG_USB_OHCI_LITTLE_ENDIAN=y +CONFIG_USB_UHCI_HCD=y +# CONFIG_USB_SL811_HCD is not set + +# +# USB Device Class drivers +# +# CONFIG_USB_BLUETOOTH_TTY is not set +# CONFIG_USB_ACM is not set +# CONFIG_USB_PRINTER is not set + +# +# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed; see USB_STORAGE Help for more information +# +# CONFIG_USB_STORAGE is not set + +# +# USB Input Devices +# +CONFIG_USB_HID=y +CONFIG_USB_HIDINPUT=y +# CONFIG_HID_FF is not set +# CONFIG_USB_HIDDEV is not set +# CONFIG_USB_AIPTEK is not set +# CONFIG_USB_WACOM is not set +# CONFIG_USB_KBTAB is not set +# CONFIG_USB_POWERMATE is not set +# CONFIG_USB_MTOUCH is not set +# CONFIG_USB_EGALAX is not set +# CONFIG_USB_XPAD is not set +# CONFIG_USB_ATI_REMOTE is not set + +# +# USB Imaging devices +# +# CONFIG_USB_MDC800 is not set +# CONFIG_USB_MICROTEK is not set + +# +# USB Multimedia devices +# +# CONFIG_USB_DABUSB is not set + +# +# Video4Linux support is needed for USB Multimedia device support +# + +# +# USB Network Adapters +# +# CONFIG_USB_CATC is not set +# CONFIG_USB_KAWETH is not set +# CONFIG_USB_PEGASUS is not set +# CONFIG_USB_RTL8150 is not set +# CONFIG_USB_USBNET is not set +CONFIG_USB_MON=y + +# +# USB port drivers +# + +# +# USB Serial Converter support +# +# CONFIG_USB_SERIAL is not set + +# +# USB Miscellaneous drivers +# +# CONFIG_USB_EMI62 is not set +# CONFIG_USB_EMI26 is not set +# CONFIG_USB_AUERSWALD is not set +# CONFIG_USB_RIO500 is not set +# CONFIG_USB_LEGOTOWER is not set +# CONFIG_USB_LCD is not set +# CONFIG_USB_LED is not set +# CONFIG_USB_CYTHERM is not set +# CONFIG_USB_PHIDGETKIT is not set +# CONFIG_USB_PHIDGETSERVO is not set +# CONFIG_USB_IDMOUSE is not set + +# +# USB ATM/DSL drivers +# + +# +# USB Gadget Support +# +# CONFIG_USB_GADGET is not set + +# +# MMC/SD Card support +# +# CONFIG_MMC is not set + +# +# InfiniBand support +# +CONFIG_INFINIBAND=y +CONFIG_INFINIBAND_MTHCA=y +CONFIG_INFINIBAND_MTHCA_DEBUG=y +CONFIG_INFINIBAND_IPOIB=y +CONFIG_INFINIBAND_IPOIB_DEBUG=y +CONFIG_INFINIBAND_IPOIB_DEBUG_DATA=y + +# +# Firmware Drivers +# + +# +# File systems +# +CONFIG_EXT2_FS=y +# CONFIG_EXT2_FS_XATTR is not set +CONFIG_EXT3_FS=y +CONFIG_EXT3_FS_XATTR=y +# CONFIG_EXT3_FS_POSIX_ACL is not set +# CONFIG_EXT3_FS_SECURITY is not set +CONFIG_JBD=y +# CONFIG_JBD_DEBUG is not set +CONFIG_FS_MBCACHE=y +CONFIG_REISERFS_FS=y +# CONFIG_REISERFS_CHECK is not set +# CONFIG_REISERFS_PROC_INFO is not set +# CONFIG_REISERFS_FS_XATTR is not set +# CONFIG_JFS_FS is not set + +# +# XFS support +# +# CONFIG_XFS_FS is not set +# CONFIG_MINIX_FS is not set +# CONFIG_ROMFS_FS is not set +# CONFIG_QUOTA is not set +CONFIG_DNOTIFY=y +CONFIG_AUTOFS_FS=y +CONFIG_AUTOFS4_FS=y + +# +# CD-ROM/DVD Filesystems +# +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_ZISOFS_FS=y +# CONFIG_UDF_FS is not set + +# +# DOS/FAT/NT Filesystems +# +CONFIG_FAT_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_FAT_DEFAULT_CODEPAGE=437 +CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" +# CONFIG_NTFS_FS is not set + +# +# Pseudo filesystems +# +CONFIG_PROC_FS=y +CONFIG_PROC_KCORE=y +CONFIG_SYSFS=y +# CONFIG_DEVFS_FS is not set +# CONFIG_DEVPTS_FS_XATTR is not set +CONFIG_TMPFS=y +# CONFIG_TMPFS_XATTR is not set +# CONFIG_HUGETLB_PAGE is not set +CONFIG_RAMFS=y + +# +# Miscellaneous filesystems +# +# CONFIG_ADFS_FS is not set +# CONFIG_AFFS_FS is not set +# CONFIG_HFS_FS is not set +# CONFIG_HFSPLUS_FS is not set +# CONFIG_BEFS_FS is not set +# CONFIG_BFS_FS is not set +# CONFIG_EFS_FS is not set +CONFIG_CRAMFS=y +# CONFIG_VXFS_FS is not set +# CONFIG_HPFS_FS is not set +# CONFIG_QNX4FS_FS is not set +# CONFIG_SYSV_FS is not set +# CONFIG_UFS_FS is not set + +# +# Network File Systems +# +CONFIG_NFS_FS=y +CONFIG_NFS_V3=y +# CONFIG_NFS_V4 is not set +# CONFIG_NFS_DIRECTIO is not set +CONFIG_NFSD=m +CONFIG_NFSD_V3=y +# CONFIG_NFSD_V4 is not set +CONFIG_NFSD_TCP=y +CONFIG_ROOT_NFS=y +CONFIG_LOCKD=y +CONFIG_LOCKD_V4=y +CONFIG_EXPORTFS=m +CONFIG_SUNRPC=y +# CONFIG_RPCSEC_GSS_KRB5 is not set +# CONFIG_RPCSEC_GSS_SPKM3 is not set +# CONFIG_SMB_FS is not set +# CONFIG_CIFS is not set +# CONFIG_NCP_FS is not set +# CONFIG_CODA_FS is not set +# CONFIG_AFS_FS is not set + +# +# Partition Types +# +# CONFIG_PARTITION_ADVANCED is not set +CONFIG_MSDOS_PARTITION=y + +# +# Native Language Support +# +CONFIG_NLS=y +CONFIG_NLS_DEFAULT="iso8859-1" +CONFIG_NLS_CODEPAGE_437=y +# CONFIG_NLS_CODEPAGE_737 is not set +# CONFIG_NLS_CODEPAGE_775 is not set +# CONFIG_NLS_CODEPAGE_850 is not set +# CONFIG_NLS_CODEPAGE_852 is not set +# CONFIG_NLS_CODEPAGE_855 is not set +# CONFIG_NLS_CODEPAGE_857 is not set +# CONFIG_NLS_CODEPAGE_860 is not set +# CONFIG_NLS_CODEPAGE_861 is not set +# CONFIG_NLS_CODEPAGE_862 is not set +# CONFIG_NLS_CODEPAGE_863 is not set +# CONFIG_NLS_CODEPAGE_864 is not set +# CONFIG_NLS_CODEPAGE_865 is not set +# CONFIG_NLS_CODEPAGE_866 is not set +# CONFIG_NLS_CODEPAGE_869 is not set +# CONFIG_NLS_CODEPAGE_936 is not set +# CONFIG_NLS_CODEPAGE_950 is not set +# CONFIG_NLS_CODEPAGE_932 is not set +# CONFIG_NLS_CODEPAGE_949 is not set +# CONFIG_NLS_CODEPAGE_874 is not set +# CONFIG_NLS_ISO8859_8 is not set +# CONFIG_NLS_CODEPAGE_1250 is not set +# CONFIG_NLS_CODEPAGE_1251 is not set +# CONFIG_NLS_ASCII is not set +CONFIG_NLS_ISO8859_1=y +# CONFIG_NLS_ISO8859_2 is not set +# CONFIG_NLS_ISO8859_3 is not set +# CONFIG_NLS_ISO8859_4 is not set +# CONFIG_NLS_ISO8859_5 is not set +# CONFIG_NLS_ISO8859_6 is not set +# CONFIG_NLS_ISO8859_7 is not set +# CONFIG_NLS_ISO8859_9 is not set +# CONFIG_NLS_ISO8859_13 is not set +# CONFIG_NLS_ISO8859_14 is not set +# CONFIG_NLS_ISO8859_15 is not set +# CONFIG_NLS_KOI8_R is not set +# CONFIG_NLS_KOI8_U is not set +# CONFIG_NLS_UTF8 is not set + +# +# Profiling support +# +# CONFIG_PROFILING is not set + +# +# Kernel hacking +# +# CONFIG_PRINTK_TIME is not set +CONFIG_DEBUG_KERNEL=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_LOG_BUF_SHIFT=15 +# CONFIG_SCHEDSTATS is not set +# CONFIG_DEBUG_SLAB is not set +# CONFIG_DEBUG_SPINLOCK is not set +# CONFIG_DEBUG_SPINLOCK_SLEEP is not set +# CONFIG_DEBUG_KOBJECT is not set +# CONFIG_DEBUG_FS is not set +# CONFIG_CHECKING is not set +# CONFIG_INIT_DEBUG is not set +# CONFIG_KPROBES is not set + +# +# Security options +# +# CONFIG_KEYS is not set +# CONFIG_SECURITY is not set + +# +# Cryptographic options +# +CONFIG_CRYPTO=y +CONFIG_CRYPTO_HMAC=y +# CONFIG_CRYPTO_NULL is not set +# CONFIG_CRYPTO_MD4 is not set +CONFIG_CRYPTO_MD5=m +CONFIG_CRYPTO_SHA1=m +# CONFIG_CRYPTO_SHA256 is not set +# CONFIG_CRYPTO_SHA512 is not set +# CONFIG_CRYPTO_WP512 is not set +# CONFIG_CRYPTO_TGR192 is not set +CONFIG_CRYPTO_DES=m +# CONFIG_CRYPTO_BLOWFISH is not set +# CONFIG_CRYPTO_TWOFISH is not set +# CONFIG_CRYPTO_SERPENT is not set +# CONFIG_CRYPTO_AES is not set +# CONFIG_CRYPTO_CAST5 is not set +# CONFIG_CRYPTO_CAST6 is not set +# CONFIG_CRYPTO_TEA is not set +# CONFIG_CRYPTO_ARC4 is not set +# CONFIG_CRYPTO_KHAZAD is not set +# CONFIG_CRYPTO_ANUBIS is not set +# CONFIG_CRYPTO_DEFLATE is not set +# CONFIG_CRYPTO_MICHAEL_MIC is not set +CONFIG_CRYPTO_CRC32C=m +# CONFIG_CRYPTO_TEST is not set + +# +# Hardware crypto devices +# +CONFIG_XEN=y +CONFIG_NO_IDLE_HZ=y + +# +# XEN +# +CONFIG_XEN_PRIVILEGED_GUEST=y +# CONFIG_XEN_UNPRIVILEGED_GUEST is not set +CONFIG_XEN_PHYSDEV_ACCESS=y +CONFIG_XEN_BLKDEV_BACKEND=y +# CONFIG_XEN_BLKDEV_TAP_BE is not set +CONFIG_XEN_NETDEV_BACKEND=y +# CONFIG_XEN_NETDEV_PIPELINED_TRANSMITTER is not set +# CONFIG_XEN_TPMDEV_BACKEND is not set +CONFIG_XEN_BLKDEV_FRONTEND=y +CONFIG_XEN_NETDEV_FRONTEND=y +# CONFIG_XEN_BLKDEV_TAP is not set +# CONFIG_XEN_TPMDEV_FRONTEND is not set +# CONFIG_XEN_SHADOW_MODE is not set +CONFIG_XEN_SCRUB_PAGES=y +CONFIG_XEN_DISABLE_SERIAL=y +CONFIG_HAVE_ARCH_ALLOC_SKB=y +CONFIG_HAVE_ARCH_DEV_ALLOC_SKB=y + +# +# Library routines +# +# CONFIG_CRC_CCITT is not set +CONFIG_CRC32=y +CONFIG_LIBCRC32C=m +CONFIG_ZLIB_INFLATE=y diff -r 690fc13948db -r fd9b2c1bb577 buildconfigs/linux-defconfig_xenU_x86_32 --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/buildconfigs/linux-defconfig_xenU_x86_32 Mon Jan 30 17:18:27 2006 @@ -0,0 +1,555 @@ +# +# Automatically generated make config: don't edit +# Linux kernel version: 2.6.12.6-xenU +# Wed Jan 25 17:29:40 2006 +# +CONFIG_X86=y +CONFIG_MMU=y +CONFIG_UID16=y +CONFIG_GENERIC_ISA_DMA=y +CONFIG_GENERIC_IOMAP=y + +# +# Code maturity level options +# +CONFIG_EXPERIMENTAL=y +CONFIG_CLEAN_COMPILE=y +CONFIG_LOCK_KERNEL=y +CONFIG_INIT_ENV_ARG_LIMIT=32 + +# +# General setup +# +CONFIG_LOCALVERSION="" +CONFIG_SWAP=y +CONFIG_SYSVIPC=y +# CONFIG_POSIX_MQUEUE is not set +# CONFIG_BSD_PROCESS_ACCT is not set +CONFIG_SYSCTL=y +# CONFIG_AUDIT is not set +CONFIG_HOTPLUG=y +CONFIG_KOBJECT_UEVENT=y +# CONFIG_IKCONFIG is not set +# CONFIG_CPUSETS is not set +# CONFIG_EMBEDDED is not set +CONFIG_KALLSYMS=y +# CONFIG_KALLSYMS_ALL is not set +# CONFIG_KALLSYMS_EXTRA_PASS is not set +CONFIG_PRINTK=y +CONFIG_BUG=y +CONFIG_BASE_FULL=y +CONFIG_FUTEX=y +CONFIG_EPOLL=y +CONFIG_SHMEM=y +CONFIG_CC_ALIGN_FUNCTIONS=0 +CONFIG_CC_ALIGN_LABELS=0 +CONFIG_CC_ALIGN_LOOPS=0 +CONFIG_CC_ALIGN_JUMPS=0 +# CONFIG_TINY_SHMEM is not set +CONFIG_BASE_SMALL=0 + +# +# Loadable module support +# +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_MODULE_FORCE_UNLOAD is not set +CONFIG_OBSOLETE_MODPARM=y +# CONFIG_MODVERSIONS is not set +# CONFIG_MODULE_SRCVERSION_ALL is not set +CONFIG_KMOD=y +CONFIG_STOP_MACHINE=y + +# +# Processor type and features +# +# CONFIG_X86_PC is not set +CONFIG_X86_XEN=y +# CONFIG_X86_ELAN is not set +# CONFIG_X86_VOYAGER is not set +# CONFIG_X86_NUMAQ is not set +# CONFIG_X86_SUMMIT is not set +# CONFIG_X86_BIGSMP is not set +# CONFIG_X86_VISWS is not set +# CONFIG_X86_GENERICARCH is not set +# CONFIG_X86_ES7000 is not set +# CONFIG_M386 is not set +# CONFIG_M486 is not set +# CONFIG_M586 is not set +# CONFIG_M586TSC is not set +# CONFIG_M586MMX is not set +CONFIG_M686=y +# CONFIG_MPENTIUMII is not set +# CONFIG_MPENTIUMIII is not set +# CONFIG_MPENTIUMM is not set +# CONFIG_MPENTIUM4 is not set +# CONFIG_MK6 is not set +# CONFIG_MK7 is not set +# CONFIG_MK8 is not set +# CONFIG_MCRUSOE is not set +# CONFIG_MEFFICEON is not set +# CONFIG_MWINCHIPC6 is not set +# CONFIG_MWINCHIP2 is not set +# CONFIG_MWINCHIP3D is not set +# CONFIG_MGEODEGX1 is not set +# CONFIG_MCYRIXIII is not set +# CONFIG_MVIAC3_2 is not set +# CONFIG_X86_GENERIC is not set +CONFIG_X86_CMPXCHG=y +CONFIG_X86_XADD=y +CONFIG_X86_L1_CACHE_SHIFT=5 +CONFIG_RWSEM_XCHGADD_ALGORITHM=y +CONFIG_GENERIC_CALIBRATE_DELAY=y +CONFIG_X86_PPRO_FENCE=y +CONFIG_X86_WP_WORKS_OK=y +CONFIG_X86_INVLPG=y +CONFIG_X86_BSWAP=y +CONFIG_X86_POPAD_OK=y +CONFIG_X86_GOOD_APIC=y +CONFIG_X86_USE_PPRO_CHECKSUM=y +CONFIG_SMP=y +CONFIG_SMP_ALTERNATIVES=y +CONFIG_NR_CPUS=8 +# CONFIG_TOSHIBA is not set +# CONFIG_I8K is not set +# CONFIG_X86_REBOOTFIXUPS is not set +CONFIG_X86_CPUID=y +# CONFIG_SWIOTLB is not set + +# +# Firmware Drivers +# +# CONFIG_NOHIGHMEM is not set +CONFIG_HIGHMEM4G=y +# CONFIG_HIGHMEM64G is not set +CONFIG_HIGHMEM=y +CONFIG_HAVE_DEC_LOCK=y +# CONFIG_REGPARM is not set +CONFIG_SECCOMP=y + +# +# Executable file formats +# +CONFIG_BINFMT_ELF=y +# CONFIG_BINFMT_AOUT is not set +# CONFIG_BINFMT_MISC is not set + +# +# Device Drivers +# + +# +# Generic Driver Options +# +CONFIG_STANDALONE=y +CONFIG_PREVENT_FIRMWARE_BUILD=y +# CONFIG_FW_LOADER is not set +# CONFIG_DEBUG_DRIVER is not set + +# +# Block devices +# +# CONFIG_BLK_DEV_FD is not set +# CONFIG_BLK_DEV_COW_COMMON is not set +CONFIG_BLK_DEV_LOOP=m +# CONFIG_BLK_DEV_CRYPTOLOOP is not set +CONFIG_BLK_DEV_NBD=m +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_COUNT=16 +CONFIG_BLK_DEV_RAM_SIZE=4096 +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="" +# CONFIG_LBD is not set +# CONFIG_CDROM_PKTCDVD is not set + +# +# IO Schedulers +# +CONFIG_IOSCHED_NOOP=y +CONFIG_IOSCHED_AS=y +CONFIG_IOSCHED_DEADLINE=y +CONFIG_IOSCHED_CFQ=y +# CONFIG_ATA_OVER_ETH is not set + +# +# SCSI device support +# +CONFIG_SCSI=m +CONFIG_SCSI_PROC_FS=y + +# +# SCSI support type (disk, tape, CD-ROM) +# +CONFIG_BLK_DEV_SD=m +# CONFIG_CHR_DEV_ST is not set +# CONFIG_CHR_DEV_OSST is not set +# CONFIG_BLK_DEV_SR is not set +# CONFIG_CHR_DEV_SG is not set + +# +# Some SCSI devices (e.g. CD jukebox) support multiple LUNs +# +# CONFIG_SCSI_MULTI_LUN is not set +# CONFIG_SCSI_CONSTANTS is not set +# CONFIG_SCSI_LOGGING is not set + +# +# SCSI Transport Attributes +# +# CONFIG_SCSI_SPI_ATTRS is not set +# CONFIG_SCSI_FC_ATTRS is not set +# CONFIG_SCSI_ISCSI_ATTRS is not set + +# +# SCSI low-level drivers +# +# CONFIG_SCSI_SATA is not set +# CONFIG_SCSI_DEBUG is not set + +# +# Multi-device support (RAID and LVM) +# +# CONFIG_MD is not set + +# +# Networking support +# +CONFIG_NET=y + +# +# Networking options +# +CONFIG_PACKET=y +# CONFIG_PACKET_MMAP is not set +CONFIG_UNIX=y +# CONFIG_NET_KEY is not set +CONFIG_INET=y +# CONFIG_IP_MULTICAST is not set +# CONFIG_IP_ADVANCED_ROUTER is not set +CONFIG_IP_PNP=y +# CONFIG_IP_PNP_DHCP is not set +# CONFIG_IP_PNP_BOOTP is not set +# CONFIG_IP_PNP_RARP is not set +# CONFIG_NET_IPIP is not set +# CONFIG_NET_IPGRE is not set +# CONFIG_ARPD is not set +# CONFIG_SYN_COOKIES is not set +# CONFIG_INET_AH is not set +# CONFIG_INET_ESP is not set +# CONFIG_INET_IPCOMP is not set +# CONFIG_INET_TUNNEL is not set +CONFIG_IP_TCPDIAG=y +# CONFIG_IP_TCPDIAG_IPV6 is not set +# CONFIG_IPV6 is not set +# CONFIG_NETFILTER is not set + +# +# SCTP Configuration (EXPERIMENTAL) +# +# CONFIG_IP_SCTP is not set +# CONFIG_ATM is not set +# CONFIG_BRIDGE is not set +# CONFIG_VLAN_8021Q is not set +# CONFIG_DECNET is not set +# CONFIG_LLC2 is not set +# CONFIG_IPX is not set +# CONFIG_ATALK is not set +# CONFIG_X25 is not set +# CONFIG_LAPB is not set +# CONFIG_NET_DIVERT is not set +# CONFIG_ECONET is not set +# CONFIG_WAN_ROUTER is not set + +# +# QoS and/or fair queueing +# +# CONFIG_NET_SCHED is not set +# CONFIG_NET_CLS_ROUTE is not set + +# +# Network testing +# +# CONFIG_NET_PKTGEN is not set +# CONFIG_NETPOLL is not set +# CONFIG_NET_POLL_CONTROLLER is not set +# CONFIG_HAMRADIO is not set +# CONFIG_IRDA is not set +# CONFIG_BT is not set +CONFIG_NETDEVICES=y +# CONFIG_DUMMY is not set +# CONFIG_BONDING is not set +# CONFIG_EQUALIZER is not set +# CONFIG_TUN is not set + +# +# Ethernet (10 or 100Mbit) +# +# CONFIG_NET_ETHERNET is not set + +# +# Ethernet (1000 Mbit) +# + +# +# Ethernet (10000 Mbit) +# + +# +# Token Ring devices +# + +# +# Wireless LAN (non-hamradio) +# +# CONFIG_NET_RADIO is not set + +# +# Wan interfaces +# +# CONFIG_WAN is not set +# CONFIG_PPP is not set +# CONFIG_SLIP is not set +# CONFIG_SHAPER is not set +# CONFIG_NETCONSOLE is not set + +# +# File systems +# +CONFIG_EXT2_FS=y +# CONFIG_EXT2_FS_XATTR is not set +CONFIG_EXT3_FS=y +CONFIG_EXT3_FS_XATTR=y +# CONFIG_EXT3_FS_POSIX_ACL is not set +# CONFIG_EXT3_FS_SECURITY is not set +CONFIG_JBD=y +# CONFIG_JBD_DEBUG is not set +CONFIG_FS_MBCACHE=y +CONFIG_REISERFS_FS=y +# CONFIG_REISERFS_CHECK is not set +# CONFIG_REISERFS_PROC_INFO is not set +# CONFIG_REISERFS_FS_XATTR is not set +# CONFIG_JFS_FS is not set + +# +# XFS support +# +# CONFIG_XFS_FS is not set +# CONFIG_MINIX_FS is not set +# CONFIG_ROMFS_FS is not set +# CONFIG_QUOTA is not set +CONFIG_DNOTIFY=y +CONFIG_AUTOFS_FS=y +CONFIG_AUTOFS4_FS=y + +# +# CD-ROM/DVD Filesystems +# +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_ZISOFS_FS=y +# CONFIG_UDF_FS is not set + +# +# DOS/FAT/NT Filesystems +# +CONFIG_FAT_FS=m +CONFIG_MSDOS_FS=m +CONFIG_VFAT_FS=m +CONFIG_FAT_DEFAULT_CODEPAGE=437 +CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" +# CONFIG_NTFS_FS is not set + +# +# Pseudo filesystems +# +CONFIG_PROC_FS=y +CONFIG_PROC_KCORE=y +CONFIG_SYSFS=y +# CONFIG_DEVFS_FS is not set +CONFIG_TMPFS=y +# CONFIG_TMPFS_XATTR is not set +# CONFIG_HUGETLB_PAGE is not set +CONFIG_RAMFS=y + +# +# Miscellaneous filesystems +# +# CONFIG_ADFS_FS is not set +# CONFIG_AFFS_FS is not set +# CONFIG_HFS_FS is not set +# CONFIG_HFSPLUS_FS is not set +# CONFIG_BEFS_FS is not set +# CONFIG_BFS_FS is not set +# CONFIG_EFS_FS is not set +CONFIG_CRAMFS=y +# CONFIG_VXFS_FS is not set +# CONFIG_HPFS_FS is not set +# CONFIG_QNX4FS_FS is not set +# CONFIG_SYSV_FS is not set +# CONFIG_UFS_FS is not set + +# +# Network File Systems +# +CONFIG_NFS_FS=y +CONFIG_NFS_V3=y +# CONFIG_NFS_V4 is not set +# CONFIG_NFS_DIRECTIO is not set +# CONFIG_NFSD is not set +CONFIG_ROOT_NFS=y +CONFIG_LOCKD=y +CONFIG_LOCKD_V4=y +CONFIG_SUNRPC=y +# CONFIG_RPCSEC_GSS_KRB5 is not set +# CONFIG_RPCSEC_GSS_SPKM3 is not set +# CONFIG_SMB_FS is not set +# CONFIG_CIFS is not set +# CONFIG_NCP_FS is not set +# CONFIG_CODA_FS is not set +# CONFIG_AFS_FS is not set + +# +# Partition Types +# +# CONFIG_PARTITION_ADVANCED is not set +CONFIG_MSDOS_PARTITION=y + +# +# Native Language Support +# +CONFIG_NLS=y +CONFIG_NLS_DEFAULT="iso8859-1" +CONFIG_NLS_CODEPAGE_437=y +# CONFIG_NLS_CODEPAGE_737 is not set +# CONFIG_NLS_CODEPAGE_775 is not set +# CONFIG_NLS_CODEPAGE_850 is not set +# CONFIG_NLS_CODEPAGE_852 is not set +# CONFIG_NLS_CODEPAGE_855 is not set +# CONFIG_NLS_CODEPAGE_857 is not set +# CONFIG_NLS_CODEPAGE_860 is not set +# CONFIG_NLS_CODEPAGE_861 is not set +# CONFIG_NLS_CODEPAGE_862 is not set +# CONFIG_NLS_CODEPAGE_863 is not set +# CONFIG_NLS_CODEPAGE_864 is not set +# CONFIG_NLS_CODEPAGE_865 is not set +# CONFIG_NLS_CODEPAGE_866 is not set +# CONFIG_NLS_CODEPAGE_869 is not set +# CONFIG_NLS_CODEPAGE_936 is not set +# CONFIG_NLS_CODEPAGE_950 is not set +# CONFIG_NLS_CODEPAGE_932 is not set +# CONFIG_NLS_CODEPAGE_949 is not set +# CONFIG_NLS_CODEPAGE_874 is not set +# CONFIG_NLS_ISO8859_8 is not set +# CONFIG_NLS_CODEPAGE_1250 is not set +# CONFIG_NLS_CODEPAGE_1251 is not set +# CONFIG_NLS_ASCII is not set +CONFIG_NLS_ISO8859_1=y +# CONFIG_NLS_ISO8859_2 is not set +# CONFIG_NLS_ISO8859_3 is not set +# CONFIG_NLS_ISO8859_4 is not set +# CONFIG_NLS_ISO8859_5 is not set +# CONFIG_NLS_ISO8859_6 is not set +# CONFIG_NLS_ISO8859_7 is not set +# CONFIG_NLS_ISO8859_9 is not set +# CONFIG_NLS_ISO8859_13 is not set +# CONFIG_NLS_ISO8859_14 is not set +# CONFIG_NLS_ISO8859_15 is not set +# CONFIG_NLS_KOI8_R is not set +# CONFIG_NLS_KOI8_U is not set +# CONFIG_NLS_UTF8 is not set + +# +# Kernel hacking +# +# CONFIG_PRINTK_TIME is not set +CONFIG_DEBUG_KERNEL=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_LOG_BUF_SHIFT=14 +# CONFIG_SCHEDSTATS is not set +# CONFIG_DEBUG_SLAB is not set +# CONFIG_DEBUG_SPINLOCK is not set +# CONFIG_DEBUG_SPINLOCK_SLEEP is not set +# CONFIG_DEBUG_KOBJECT is not set +# CONFIG_DEBUG_HIGHMEM is not set +CONFIG_DEBUG_BUGVERBOSE=y +# CONFIG_DEBUG_INFO is not set +# CONFIG_DEBUG_FS is not set +# CONFIG_FRAME_POINTER is not set +CONFIG_EARLY_PRINTK=y +# CONFIG_DEBUG_STACKOVERFLOW is not set +# CONFIG_KPROBES is not set +# CONFIG_DEBUG_STACK_USAGE is not set +# CONFIG_DEBUG_PAGEALLOC is not set +# CONFIG_4KSTACKS is not set + +# +# Security options +# +# CONFIG_KEYS is not set +# CONFIG_SECURITY is not set + +# +# Cryptographic options +# +CONFIG_CRYPTO=y +# CONFIG_CRYPTO_HMAC is not set +# CONFIG_CRYPTO_NULL is not set +# CONFIG_CRYPTO_MD4 is not set +CONFIG_CRYPTO_MD5=m +# CONFIG_CRYPTO_SHA1 is not set +# CONFIG_CRYPTO_SHA256 is not set +# CONFIG_CRYPTO_SHA512 is not set +# CONFIG_CRYPTO_WP512 is not set +# CONFIG_CRYPTO_TGR192 is not set +# CONFIG_CRYPTO_DES is not set +# CONFIG_CRYPTO_BLOWFISH is not set +# CONFIG_CRYPTO_TWOFISH is not set +# CONFIG_CRYPTO_SERPENT is not set +# CONFIG_CRYPTO_AES_586 is not set +# CONFIG_CRYPTO_CAST5 is not set +# CONFIG_CRYPTO_CAST6 is not set +# CONFIG_CRYPTO_TEA is not set +# CONFIG_CRYPTO_ARC4 is not set +# CONFIG_CRYPTO_KHAZAD is not set +# CONFIG_CRYPTO_ANUBIS is not set +# CONFIG_CRYPTO_DEFLATE is not set +# CONFIG_CRYPTO_MICHAEL_MIC is not set +CONFIG_CRYPTO_CRC32C=m +# CONFIG_CRYPTO_TEST is not set + +# +# Hardware crypto devices +# +# CONFIG_CRYPTO_DEV_PADLOCK is not set +CONFIG_XEN=y +CONFIG_NO_IDLE_HZ=y + +# +# XEN +# +# CONFIG_XEN_PRIVILEGED_GUEST is not set +CONFIG_XEN_UNPRIVILEGED_GUEST=y +CONFIG_XEN_BLKDEV_FRONTEND=y +CONFIG_XEN_NETDEV_FRONTEND=y +# CONFIG_XEN_BLKDEV_TAP is not set +# CONFIG_XEN_TPMDEV_FRONTEND is not set +# CONFIG_XEN_SHADOW_MODE is not set +CONFIG_XEN_SCRUB_PAGES=y +CONFIG_XEN_DISABLE_SERIAL=y +CONFIG_HAVE_ARCH_ALLOC_SKB=y +CONFIG_HAVE_ARCH_DEV_ALLOC_SKB=y + +# +# Library routines +# +# CONFIG_CRC_CCITT is not set +# CONFIG_CRC32 is not set +CONFIG_LIBCRC32C=m +CONFIG_ZLIB_INFLATE=y +CONFIG_GENERIC_HARDIRQS=y +CONFIG_GENERIC_IRQ_PROBE=y +CONFIG_X86_SMP=y +CONFIG_X86_BIOS_REBOOT=y +CONFIG_X86_TRAMPOLINE=y +CONFIG_PC=y diff -r 690fc13948db -r fd9b2c1bb577 buildconfigs/linux-defconfig_xenU_x86_64 --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/buildconfigs/linux-defconfig_xenU_x86_64 Mon Jan 30 17:18:27 2006 @@ -0,0 +1,903 @@ +# +# Automatically generated make config: don't edit +# Linux kernel version: 2.6.12.6-xenU +# Wed Jan 25 17:28:26 2006 +# +CONFIG_X86_64=y +CONFIG_64BIT=y +CONFIG_X86=y +CONFIG_MMU=y +CONFIG_RWSEM_GENERIC_SPINLOCK=y +CONFIG_GENERIC_CALIBRATE_DELAY=y +CONFIG_X86_CMPXCHG=y +CONFIG_EARLY_PRINTK=y +CONFIG_GENERIC_ISA_DMA=y +CONFIG_GENERIC_IOMAP=y + +# +# Code maturity level options +# +CONFIG_EXPERIMENTAL=y +CONFIG_CLEAN_COMPILE=y +CONFIG_LOCK_KERNEL=y +CONFIG_INIT_ENV_ARG_LIMIT=32 + +# +# General setup +# +CONFIG_LOCALVERSION="" +CONFIG_SWAP=y +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +CONFIG_BSD_PROCESS_ACCT=y +# CONFIG_BSD_PROCESS_ACCT_V3 is not set +CONFIG_SYSCTL=y +CONFIG_AUDIT=y +CONFIG_AUDITSYSCALL=y +CONFIG_HOTPLUG=y +CONFIG_KOBJECT_UEVENT=y +# CONFIG_IKCONFIG is not set +# CONFIG_CPUSETS is not set +# CONFIG_EMBEDDED is not set +CONFIG_KALLSYMS=y +# CONFIG_KALLSYMS_ALL is not set +CONFIG_KALLSYMS_EXTRA_PASS=y +CONFIG_PRINTK=y +CONFIG_BUG=y +CONFIG_BASE_FULL=y +CONFIG_FUTEX=y +CONFIG_EPOLL=y +CONFIG_SHMEM=y +CONFIG_CC_ALIGN_FUNCTIONS=0 +CONFIG_CC_ALIGN_LABELS=0 +CONFIG_CC_ALIGN_LOOPS=0 +CONFIG_CC_ALIGN_JUMPS=0 +# CONFIG_TINY_SHMEM is not set +CONFIG_BASE_SMALL=0 + +# +# Loadable module support +# +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_MODULE_FORCE_UNLOAD is not set +CONFIG_OBSOLETE_MODPARM=y +CONFIG_MODVERSIONS=y +# CONFIG_MODULE_SRCVERSION_ALL is not set +CONFIG_KMOD=y +CONFIG_STOP_MACHINE=y + +# +# Processor type and features +# +# CONFIG_MK8 is not set +CONFIG_MPSC=y +# CONFIG_GENERIC_CPU is not set +CONFIG_X86_64_XEN=y +CONFIG_X86_L1_CACHE_BYTES=128 +CONFIG_X86_L1_CACHE_SHIFT=7 +CONFIG_X86_GOOD_APIC=y +# CONFIG_MICROCODE is not set +# CONFIG_X86_MSR is not set +CONFIG_X86_CPUID=y +CONFIG_X86_XEN_GENAPIC=y +CONFIG_SMP=y +# CONFIG_NUMA is not set +CONFIG_HAVE_DEC_LOCK=y +CONFIG_NR_CPUS=8 +CONFIG_DUMMY_IOMMU=y +CONFIG_SECCOMP=y +CONFIG_GENERIC_HARDIRQS=y +CONFIG_GENERIC_IRQ_PROBE=y +CONFIG_ISA_DMA_API=y + +# +# Bus options (PCI etc.) +# +# CONFIG_PCI is not set +# CONFIG_UNORDERED_IO is not set + +# +# Executable file formats / Emulations +# +CONFIG_BINFMT_ELF=y +CONFIG_BINFMT_MISC=y +CONFIG_IA32_EMULATION=y +# CONFIG_IA32_AOUT is not set +CONFIG_COMPAT=y +CONFIG_SYSVIPC_COMPAT=y +CONFIG_UID16=y + +# +# Device Drivers +# + +# +# Generic Driver Options +# +CONFIG_STANDALONE=y +CONFIG_PREVENT_FIRMWARE_BUILD=y +CONFIG_FW_LOADER=y +# CONFIG_DEBUG_DRIVER is not set + +# +# Block devices +# +CONFIG_BLK_DEV_FD=m +# CONFIG_BLK_DEV_COW_COMMON is not set +CONFIG_BLK_DEV_LOOP=m +CONFIG_BLK_DEV_CRYPTOLOOP=m +CONFIG_BLK_DEV_NBD=m +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_COUNT=16 +CONFIG_BLK_DEV_RAM_SIZE=16384 +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="" +CONFIG_LBD=y +# CONFIG_CDROM_PKTCDVD is not set + +# +# IO Schedulers +# +CONFIG_IOSCHED_NOOP=y +CONFIG_IOSCHED_AS=y +CONFIG_IOSCHED_DEADLINE=y +CONFIG_IOSCHED_CFQ=y +# CONFIG_ATA_OVER_ETH is not set + +# +# SCSI device support +# +CONFIG_SCSI=m +CONFIG_SCSI_PROC_FS=y + +# +# SCSI support type (disk, tape, CD-ROM) +# +CONFIG_BLK_DEV_SD=m +CONFIG_CHR_DEV_ST=m +CONFIG_CHR_DEV_OSST=m +CONFIG_BLK_DEV_SR=m +CONFIG_BLK_DEV_SR_VENDOR=y +CONFIG_CHR_DEV_SG=m + +# +# Some SCSI devices (e.g. CD jukebox) support multiple LUNs +# +# CONFIG_SCSI_MULTI_LUN is not set +CONFIG_SCSI_CONSTANTS=y +CONFIG_SCSI_LOGGING=y + +# +# SCSI Transport Attributes +# +CONFIG_SCSI_SPI_ATTRS=m +CONFIG_SCSI_FC_ATTRS=m +# CONFIG_SCSI_ISCSI_ATTRS is not set + +# +# SCSI low-level drivers +# +CONFIG_SCSI_SATA=y +# CONFIG_SCSI_DEBUG is not set + +# +# Multi-device support (RAID and LVM) +# +CONFIG_MD=y +CONFIG_BLK_DEV_MD=y +CONFIG_MD_LINEAR=m +CONFIG_MD_RAID0=m +CONFIG_MD_RAID1=m +CONFIG_MD_RAID10=m +CONFIG_MD_RAID5=m +CONFIG_MD_RAID6=m +CONFIG_MD_MULTIPATH=m +# CONFIG_MD_FAULTY is not set +CONFIG_BLK_DEV_DM=m +CONFIG_DM_CRYPT=m +CONFIG_DM_SNAPSHOT=m +CONFIG_DM_MIRROR=m +CONFIG_DM_ZERO=m +# CONFIG_DM_MULTIPATH is not set + +# +# Networking support +# +CONFIG_NET=y + +# +# Networking options +# +CONFIG_PACKET=y +CONFIG_PACKET_MMAP=y +CONFIG_UNIX=y +CONFIG_NET_KEY=m +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_ROUTE_FWMARK=y +CONFIG_IP_ROUTE_MULTIPATH=y +# CONFIG_IP_ROUTE_MULTIPATH_CACHED is not set +CONFIG_IP_ROUTE_VERBOSE=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +CONFIG_NET_IPIP=m +CONFIG_NET_IPGRE=m +CONFIG_NET_IPGRE_BROADCAST=y +CONFIG_IP_MROUTE=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +# CONFIG_ARPD is not set +CONFIG_SYN_COOKIES=y +CONFIG_INET_AH=m +CONFIG_INET_ESP=m +CONFIG_INET_IPCOMP=m +CONFIG_INET_TUNNEL=m +CONFIG_IP_TCPDIAG=y +# CONFIG_IP_TCPDIAG_IPV6 is not set + +# +# IP: Virtual Server Configuration +# +CONFIG_IP_VS=m +# CONFIG_IP_VS_DEBUG is not set +CONFIG_IP_VS_TAB_BITS=12 + +# +# IPVS transport protocol load balancing support +# +CONFIG_IP_VS_PROTO_TCP=y +CONFIG_IP_VS_PROTO_UDP=y +CONFIG_IP_VS_PROTO_ESP=y +CONFIG_IP_VS_PROTO_AH=y + +# +# IPVS scheduler +# +CONFIG_IP_VS_RR=m +CONFIG_IP_VS_WRR=m +CONFIG_IP_VS_LC=m +CONFIG_IP_VS_WLC=m +CONFIG_IP_VS_LBLC=m +CONFIG_IP_VS_LBLCR=m +CONFIG_IP_VS_DH=m +CONFIG_IP_VS_SH=m +CONFIG_IP_VS_SED=m +CONFIG_IP_VS_NQ=m + +# +# IPVS application helper +# +CONFIG_IP_VS_FTP=m +CONFIG_IPV6=m +CONFIG_IPV6_PRIVACY=y +CONFIG_INET6_AH=m +CONFIG_INET6_ESP=m +CONFIG_INET6_IPCOMP=m +CONFIG_INET6_TUNNEL=m +CONFIG_IPV6_TUNNEL=m +CONFIG_NETFILTER=y +# CONFIG_NETFILTER_DEBUG is not set +CONFIG_BRIDGE_NETFILTER=y + +# +# IP: Netfilter Configuration +# +CONFIG_IP_NF_CONNTRACK=m +CONFIG_IP_NF_CT_ACCT=y +# CONFIG_IP_NF_CONNTRACK_MARK is not set +CONFIG_IP_NF_CT_PROTO_SCTP=m +CONFIG_IP_NF_FTP=m +CONFIG_IP_NF_IRC=m +CONFIG_IP_NF_TFTP=m +CONFIG_IP_NF_AMANDA=m +CONFIG_IP_NF_QUEUE=m +CONFIG_IP_NF_IPTABLES=m +CONFIG_IP_NF_MATCH_LIMIT=m +CONFIG_IP_NF_MATCH_IPRANGE=m +CONFIG_IP_NF_MATCH_MAC=m +CONFIG_IP_NF_MATCH_PKTTYPE=m +CONFIG_IP_NF_MATCH_MARK=m +CONFIG_IP_NF_MATCH_MULTIPORT=m +CONFIG_IP_NF_MATCH_TOS=m +CONFIG_IP_NF_MATCH_RECENT=m +CONFIG_IP_NF_MATCH_ECN=m +CONFIG_IP_NF_MATCH_DSCP=m +CONFIG_IP_NF_MATCH_AH_ESP=m +CONFIG_IP_NF_MATCH_LENGTH=m +CONFIG_IP_NF_MATCH_TTL=m +CONFIG_IP_NF_MATCH_TCPMSS=m +CONFIG_IP_NF_MATCH_HELPER=m +CONFIG_IP_NF_MATCH_STATE=m +CONFIG_IP_NF_MATCH_CONNTRACK=m +CONFIG_IP_NF_MATCH_OWNER=m +CONFIG_IP_NF_MATCH_PHYSDEV=m +CONFIG_IP_NF_MATCH_ADDRTYPE=m +CONFIG_IP_NF_MATCH_REALM=m +CONFIG_IP_NF_MATCH_SCTP=m +CONFIG_IP_NF_MATCH_COMMENT=m +# CONFIG_IP_NF_MATCH_HASHLIMIT is not set +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP_NF_TARGET_LOG=m +CONFIG_IP_NF_TARGET_ULOG=m +CONFIG_IP_NF_TARGET_TCPMSS=m +CONFIG_IP_NF_NAT=m +CONFIG_IP_NF_NAT_NEEDED=y +CONFIG_IP_NF_TARGET_MASQUERADE=m +CONFIG_IP_NF_TARGET_REDIRECT=m +CONFIG_IP_NF_TARGET_NETMAP=m +CONFIG_IP_NF_TARGET_SAME=m +CONFIG_IP_NF_NAT_SNMP_BASIC=m +CONFIG_IP_NF_NAT_IRC=m +CONFIG_IP_NF_NAT_FTP=m +CONFIG_IP_NF_NAT_TFTP=m +CONFIG_IP_NF_NAT_AMANDA=m +CONFIG_IP_NF_MANGLE=m +CONFIG_IP_NF_TARGET_TOS=m +CONFIG_IP_NF_TARGET_ECN=m +CONFIG_IP_NF_TARGET_DSCP=m +CONFIG_IP_NF_TARGET_MARK=m +CONFIG_IP_NF_TARGET_CLASSIFY=m +CONFIG_IP_NF_RAW=m +CONFIG_IP_NF_TARGET_NOTRACK=m +CONFIG_IP_NF_ARPTABLES=m +CONFIG_IP_NF_ARPFILTER=m +CONFIG_IP_NF_ARP_MANGLE=m + +# +# IPv6: Netfilter Configuration (EXPERIMENTAL) +# +# CONFIG_IP6_NF_QUEUE is not set +CONFIG_IP6_NF_IPTABLES=m +CONFIG_IP6_NF_MATCH_LIMIT=m +CONFIG_IP6_NF_MATCH_MAC=m +CONFIG_IP6_NF_MATCH_RT=m +CONFIG_IP6_NF_MATCH_OPTS=m +CONFIG_IP6_NF_MATCH_FRAG=m +CONFIG_IP6_NF_MATCH_HL=m +CONFIG_IP6_NF_MATCH_MULTIPORT=m +CONFIG_IP6_NF_MATCH_OWNER=m +CONFIG_IP6_NF_MATCH_MARK=m +CONFIG_IP6_NF_MATCH_IPV6HEADER=m +CONFIG_IP6_NF_MATCH_AHESP=m +CONFIG_IP6_NF_MATCH_LENGTH=m +CONFIG_IP6_NF_MATCH_EUI64=m +CONFIG_IP6_NF_MATCH_PHYSDEV=m +CONFIG_IP6_NF_FILTER=m +CONFIG_IP6_NF_TARGET_LOG=m +CONFIG_IP6_NF_MANGLE=m +CONFIG_IP6_NF_TARGET_MARK=m +CONFIG_IP6_NF_RAW=m + +# +# Bridge: Netfilter Configuration +# +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_BRIDGE_EBT_T_FILTER=m +CONFIG_BRIDGE_EBT_T_NAT=m +CONFIG_BRIDGE_EBT_802_3=m +CONFIG_BRIDGE_EBT_AMONG=m +CONFIG_BRIDGE_EBT_ARP=m +CONFIG_BRIDGE_EBT_IP=m +CONFIG_BRIDGE_EBT_LIMIT=m +CONFIG_BRIDGE_EBT_MARK=m +CONFIG_BRIDGE_EBT_PKTTYPE=m +CONFIG_BRIDGE_EBT_STP=m +CONFIG_BRIDGE_EBT_VLAN=m +CONFIG_BRIDGE_EBT_ARPREPLY=m +CONFIG_BRIDGE_EBT_DNAT=m +CONFIG_BRIDGE_EBT_MARK_T=m +CONFIG_BRIDGE_EBT_REDIRECT=m +CONFIG_BRIDGE_EBT_SNAT=m +CONFIG_BRIDGE_EBT_LOG=m +# CONFIG_BRIDGE_EBT_ULOG is not set +CONFIG_XFRM=y +CONFIG_XFRM_USER=y + +# +# SCTP Configuration (EXPERIMENTAL) +# +CONFIG_IP_SCTP=m +# CONFIG_SCTP_DBG_MSG is not set +# CONFIG_SCTP_DBG_OBJCNT is not set +# CONFIG_SCTP_HMAC_NONE is not set +# CONFIG_SCTP_HMAC_SHA1 is not set +CONFIG_SCTP_HMAC_MD5=y +CONFIG_ATM=m +CONFIG_ATM_CLIP=m +# CONFIG_ATM_CLIP_NO_ICMP is not set +CONFIG_ATM_LANE=m +# CONFIG_ATM_MPOA is not set +CONFIG_ATM_BR2684=m +# CONFIG_ATM_BR2684_IPFILTER is not set +CONFIG_BRIDGE=m +CONFIG_VLAN_8021Q=m +# CONFIG_DECNET is not set +CONFIG_LLC=m +# CONFIG_LLC2 is not set +CONFIG_IPX=m +# CONFIG_IPX_INTERN is not set +CONFIG_ATALK=m +CONFIG_DEV_APPLETALK=y +CONFIG_IPDDP=m +CONFIG_IPDDP_ENCAP=y +CONFIG_IPDDP_DECAP=y +# CONFIG_X25 is not set +# CONFIG_LAPB is not set +CONFIG_NET_DIVERT=y +# CONFIG_ECONET is not set +CONFIG_WAN_ROUTER=m + +# +# QoS and/or fair queueing +# +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_CLK_JIFFIES=y +# CONFIG_NET_SCH_CLK_GETTIMEOFDAY is not set +# CONFIG_NET_SCH_CLK_CPU is not set +CONFIG_NET_SCH_CBQ=m +CONFIG_NET_SCH_HTB=m +CONFIG_NET_SCH_HFSC=m +CONFIG_NET_SCH_ATM=m +CONFIG_NET_SCH_PRIO=m +CONFIG_NET_SCH_RED=m +CONFIG_NET_SCH_SFQ=m +CONFIG_NET_SCH_TEQL=m +CONFIG_NET_SCH_TBF=m +CONFIG_NET_SCH_GRED=m +CONFIG_NET_SCH_DSMARK=m +CONFIG_NET_SCH_NETEM=m +CONFIG_NET_SCH_INGRESS=m +CONFIG_NET_QOS=y +CONFIG_NET_ESTIMATOR=y +CONFIG_NET_CLS=y +# CONFIG_NET_CLS_BASIC is not set +CONFIG_NET_CLS_TCINDEX=m +CONFIG_NET_CLS_ROUTE4=m +CONFIG_NET_CLS_ROUTE=y +CONFIG_NET_CLS_FW=m +CONFIG_NET_CLS_U32=m +CONFIG_CLS_U32_PERF=y +CONFIG_NET_CLS_IND=y +# CONFIG_CLS_U32_MARK is not set +CONFIG_NET_CLS_RSVP=m +CONFIG_NET_CLS_RSVP6=m +# CONFIG_NET_EMATCH is not set +# CONFIG_NET_CLS_ACT is not set +CONFIG_NET_CLS_POLICE=y + +# +# Network testing +# +# CONFIG_NET_PKTGEN is not set +CONFIG_NETPOLL=y +# CONFIG_NETPOLL_RX is not set +CONFIG_NETPOLL_TRAP=y +CONFIG_NET_POLL_CONTROLLER=y +# CONFIG_HAMRADIO is not set +CONFIG_IRDA=m + +# +# IrDA protocols +# +CONFIG_IRLAN=m +CONFIG_IRNET=m +CONFIG_IRCOMM=m +# CONFIG_IRDA_ULTRA is not set + +# +# IrDA options +# +CONFIG_IRDA_CACHE_LAST_LSAP=y +CONFIG_IRDA_FAST_RR=y +# CONFIG_IRDA_DEBUG is not set + +# +# Infrared-port device drivers +# + +# +# SIR device drivers +# +CONFIG_IRTTY_SIR=m + +# +# Dongle support +# +CONFIG_DONGLE=y +CONFIG_ESI_DONGLE=m +CONFIG_ACTISYS_DONGLE=m +CONFIG_TEKRAM_DONGLE=m +CONFIG_LITELINK_DONGLE=m +CONFIG_MA600_DONGLE=m +CONFIG_GIRBIL_DONGLE=m +CONFIG_MCP2120_DONGLE=m +CONFIG_OLD_BELKIN_DONGLE=m +CONFIG_ACT200L_DONGLE=m + +# +# Old SIR device drivers +# + +# +# Old Serial dongle support +# + +# +# FIR device drivers +# +# CONFIG_NSC_FIR is not set +# CONFIG_WINBOND_FIR is not set +# CONFIG_SMC_IRCC_FIR is not set +# CONFIG_ALI_FIR is not set +# CONFIG_VIA_FIR is not set +CONFIG_BT=m +CONFIG_BT_L2CAP=m +CONFIG_BT_SCO=m +CONFIG_BT_RFCOMM=m +CONFIG_BT_RFCOMM_TTY=y +CONFIG_BT_BNEP=m +CONFIG_BT_BNEP_MC_FILTER=y +CONFIG_BT_BNEP_PROTO_FILTER=y +CONFIG_BT_HIDP=m + +# +# Bluetooth device drivers +# +CONFIG_BT_HCIUART=m +CONFIG_BT_HCIUART_H4=y +CONFIG_BT_HCIUART_BCSP=y +CONFIG_BT_HCIUART_BCSP_TXCRC=y +CONFIG_BT_HCIVHCI=m +CONFIG_NETDEVICES=y +CONFIG_DUMMY=m +CONFIG_BONDING=m +CONFIG_EQUALIZER=m +CONFIG_TUN=m + +# +# Ethernet (10 or 100Mbit) +# +CONFIG_NET_ETHERNET=y +CONFIG_MII=m + +# +# Ethernet (1000 Mbit) +# + +# +# Ethernet (10000 Mbit) +# + +# +# Token Ring devices +# + +# +# Wireless LAN (non-hamradio) +# +CONFIG_NET_RADIO=y + +# +# Obsolete Wireless cards support (pre-802.11) +# +# CONFIG_STRIP is not set +CONFIG_ATMEL=m + +# +# Wan interfaces +# +# CONFIG_WAN is not set + +# +# ATM drivers +# +CONFIG_ATM_TCP=m +CONFIG_PPP=m +CONFIG_PPP_MULTILINK=y +CONFIG_PPP_FILTER=y +CONFIG_PPP_ASYNC=m +CONFIG_PPP_SYNC_TTY=m +CONFIG_PPP_DEFLATE=m +# CONFIG_PPP_BSDCOMP is not set +CONFIG_PPPOE=m +CONFIG_PPPOATM=m +# CONFIG_SLIP is not set +# CONFIG_SHAPER is not set +CONFIG_NETCONSOLE=m +CONFIG_INPUT=m + +# +# Firmware Drivers +# + +# +# File systems +# +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_EXT2_FS_POSIX_ACL=y +CONFIG_EXT2_FS_SECURITY=y +CONFIG_EXT3_FS=y +CONFIG_EXT3_FS_XATTR=y +# CONFIG_EXT3_FS_POSIX_ACL is not set +# CONFIG_EXT3_FS_SECURITY is not set +CONFIG_JBD=y +# CONFIG_JBD_DEBUG is not set +CONFIG_FS_MBCACHE=y +CONFIG_REISERFS_FS=y +# CONFIG_REISERFS_CHECK is not set +CONFIG_REISERFS_PROC_INFO=y +CONFIG_REISERFS_FS_XATTR=y +CONFIG_REISERFS_FS_POSIX_ACL=y +CONFIG_REISERFS_FS_SECURITY=y +CONFIG_JFS_FS=m +CONFIG_JFS_POSIX_ACL=y +# CONFIG_JFS_SECURITY is not set +# CONFIG_JFS_DEBUG is not set +# CONFIG_JFS_STATISTICS is not set +CONFIG_FS_POSIX_ACL=y + +# +# XFS support +# +CONFIG_XFS_FS=m +CONFIG_XFS_EXPORT=y +# CONFIG_XFS_RT is not set +CONFIG_XFS_QUOTA=y +CONFIG_XFS_SECURITY=y +CONFIG_XFS_POSIX_ACL=y +CONFIG_MINIX_FS=m +CONFIG_ROMFS_FS=m +CONFIG_QUOTA=y +# CONFIG_QFMT_V1 is not set +CONFIG_QFMT_V2=y +CONFIG_QUOTACTL=y +CONFIG_DNOTIFY=y +CONFIG_AUTOFS_FS=m +CONFIG_AUTOFS4_FS=m + +# +# CD-ROM/DVD Filesystems +# +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_ZISOFS_FS=y +CONFIG_UDF_FS=m +CONFIG_UDF_NLS=y + +# +# DOS/FAT/NT Filesystems +# +CONFIG_FAT_FS=m +CONFIG_MSDOS_FS=m +CONFIG_VFAT_FS=m +CONFIG_FAT_DEFAULT_CODEPAGE=437 +CONFIG_FAT_DEFAULT_IOCHARSET="ascii" +# CONFIG_NTFS_FS is not set + +# +# Pseudo filesystems +# +CONFIG_PROC_FS=y +CONFIG_PROC_KCORE=y +CONFIG_SYSFS=y +# CONFIG_DEVFS_FS is not set +CONFIG_TMPFS=y +CONFIG_TMPFS_XATTR=y +CONFIG_TMPFS_SECURITY=y +# CONFIG_HUGETLB_PAGE is not set +CONFIG_RAMFS=y + +# +# Miscellaneous filesystems +# +# CONFIG_ADFS_FS is not set +CONFIG_AFFS_FS=m +CONFIG_HFS_FS=m +CONFIG_HFSPLUS_FS=m +CONFIG_BEFS_FS=m +# CONFIG_BEFS_DEBUG is not set +CONFIG_BFS_FS=m +CONFIG_EFS_FS=m +CONFIG_CRAMFS=y +CONFIG_VXFS_FS=m +# CONFIG_HPFS_FS is not set +CONFIG_QNX4FS_FS=m +CONFIG_SYSV_FS=m +CONFIG_UFS_FS=m +# CONFIG_UFS_FS_WRITE is not set + +# +# Network File Systems +# +CONFIG_NFS_FS=m +CONFIG_NFS_V3=y +CONFIG_NFS_V4=y +CONFIG_NFS_DIRECTIO=y +CONFIG_NFSD=m +CONFIG_NFSD_V3=y +CONFIG_NFSD_V4=y +CONFIG_NFSD_TCP=y +CONFIG_LOCKD=m +CONFIG_LOCKD_V4=y +CONFIG_EXPORTFS=m +CONFIG_SUNRPC=m +CONFIG_SUNRPC_GSS=m +CONFIG_RPCSEC_GSS_KRB5=m +CONFIG_RPCSEC_GSS_SPKM3=m +CONFIG_SMB_FS=m +# CONFIG_SMB_NLS_DEFAULT is not set +CONFIG_CIFS=m +# CONFIG_CIFS_STATS is not set +CONFIG_CIFS_XATTR=y +CONFIG_CIFS_POSIX=y +# CONFIG_CIFS_EXPERIMENTAL is not set +CONFIG_NCP_FS=m +CONFIG_NCPFS_PACKET_SIGNING=y +CONFIG_NCPFS_IOCTL_LOCKING=y +CONFIG_NCPFS_STRONG=y +CONFIG_NCPFS_NFS_NS=y +CONFIG_NCPFS_OS2_NS=y +CONFIG_NCPFS_SMALLDOS=y +CONFIG_NCPFS_NLS=y +CONFIG_NCPFS_EXTRAS=y +# CONFIG_CODA_FS is not set +# CONFIG_AFS_FS is not set + +# +# Partition Types +# +CONFIG_PARTITION_ADVANCED=y +# CONFIG_ACORN_PARTITION is not set +CONFIG_OSF_PARTITION=y +# CONFIG_AMIGA_PARTITION is not set +# CONFIG_ATARI_PARTITION is not set +CONFIG_MAC_PARTITION=y +CONFIG_MSDOS_PARTITION=y +CONFIG_BSD_DISKLABEL=y +CONFIG_MINIX_SUBPARTITION=y +CONFIG_SOLARIS_X86_PARTITION=y +CONFIG_UNIXWARE_DISKLABEL=y +# CONFIG_LDM_PARTITION is not set +CONFIG_SGI_PARTITION=y +# CONFIG_ULTRIX_PARTITION is not set +CONFIG_SUN_PARTITION=y +CONFIG_EFI_PARTITION=y + +# +# Native Language Support +# +CONFIG_NLS=y +CONFIG_NLS_DEFAULT="utf8" +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_CODEPAGE_737=m +CONFIG_NLS_CODEPAGE_775=m +CONFIG_NLS_CODEPAGE_850=m +CONFIG_NLS_CODEPAGE_852=m +CONFIG_NLS_CODEPAGE_855=m +CONFIG_NLS_CODEPAGE_857=m +CONFIG_NLS_CODEPAGE_860=m +CONFIG_NLS_CODEPAGE_861=m +CONFIG_NLS_CODEPAGE_862=m +CONFIG_NLS_CODEPAGE_863=m +CONFIG_NLS_CODEPAGE_864=m +CONFIG_NLS_CODEPAGE_865=m +CONFIG_NLS_CODEPAGE_866=m +CONFIG_NLS_CODEPAGE_869=m +CONFIG_NLS_CODEPAGE_936=m +CONFIG_NLS_CODEPAGE_950=m +CONFIG_NLS_CODEPAGE_932=m +CONFIG_NLS_CODEPAGE_949=m +CONFIG_NLS_CODEPAGE_874=m +CONFIG_NLS_ISO8859_8=m +CONFIG_NLS_CODEPAGE_1250=m +CONFIG_NLS_CODEPAGE_1251=m +CONFIG_NLS_ASCII=y +CONFIG_NLS_ISO8859_1=m +CONFIG_NLS_ISO8859_2=m +CONFIG_NLS_ISO8859_3=m +CONFIG_NLS_ISO8859_4=m +CONFIG_NLS_ISO8859_5=m +CONFIG_NLS_ISO8859_6=m +CONFIG_NLS_ISO8859_7=m +CONFIG_NLS_ISO8859_9=m +CONFIG_NLS_ISO8859_13=m +CONFIG_NLS_ISO8859_14=m +CONFIG_NLS_ISO8859_15=m +CONFIG_NLS_KOI8_R=m +CONFIG_NLS_KOI8_U=m +CONFIG_NLS_UTF8=m + +# +# Profiling support +# +# CONFIG_PROFILING is not set + +# +# Kernel hacking +# +# CONFIG_PRINTK_TIME is not set +CONFIG_DEBUG_KERNEL=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_LOG_BUF_SHIFT=15 +# CONFIG_SCHEDSTATS is not set +# CONFIG_DEBUG_SLAB is not set +# CONFIG_DEBUG_SPINLOCK is not set +# CONFIG_DEBUG_SPINLOCK_SLEEP is not set +# CONFIG_DEBUG_KOBJECT is not set +# CONFIG_DEBUG_FS is not set +# CONFIG_INIT_DEBUG is not set +# CONFIG_KPROBES is not set + +# +# Security options +# +# CONFIG_KEYS is not set +# CONFIG_SECURITY is not set + +# +# Cryptographic options +# +CONFIG_CRYPTO=y +CONFIG_CRYPTO_HMAC=y +CONFIG_CRYPTO_NULL=m +CONFIG_CRYPTO_MD4=m +CONFIG_CRYPTO_MD5=m +CONFIG_CRYPTO_SHA1=y +CONFIG_CRYPTO_SHA256=m +CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_WP512=m +# CONFIG_CRYPTO_TGR192 is not set +CONFIG_CRYPTO_DES=m +CONFIG_CRYPTO_BLOWFISH=m +CONFIG_CRYPTO_TWOFISH=m +CONFIG_CRYPTO_SERPENT=m +# CONFIG_CRYPTO_AES is not set +CONFIG_CRYPTO_CAST5=m +CONFIG_CRYPTO_CAST6=m +CONFIG_CRYPTO_TEA=m +CONFIG_CRYPTO_ARC4=m +CONFIG_CRYPTO_KHAZAD=m +# CONFIG_CRYPTO_ANUBIS is not set +CONFIG_CRYPTO_DEFLATE=m +CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_CRC32C=m +# CONFIG_CRYPTO_TEST is not set + +# +# Hardware crypto devices +# +CONFIG_XEN=y +CONFIG_NO_IDLE_HZ=y + +# +# XEN +# +# CONFIG_XEN_PRIVILEGED_GUEST is not set +CONFIG_XEN_UNPRIVILEGED_GUEST=y +CONFIG_XEN_BLKDEV_FRONTEND=y +CONFIG_XEN_NETDEV_FRONTEND=y +# CONFIG_XEN_BLKDEV_TAP is not set +# CONFIG_XEN_TPMDEV_FRONTEND is not set +# CONFIG_XEN_SHADOW_MODE is not set +CONFIG_XEN_SCRUB_PAGES=y +CONFIG_XEN_DISABLE_SERIAL=y +CONFIG_HAVE_ARCH_ALLOC_SKB=y +CONFIG_HAVE_ARCH_DEV_ALLOC_SKB=y + +# +# Library routines +# +CONFIG_CRC_CCITT=m +CONFIG_CRC32=y +CONFIG_LIBCRC32C=m +CONFIG_ZLIB_INFLATE=y +CONFIG_ZLIB_DEFLATE=m diff -r 690fc13948db -r fd9b2c1bb577 buildconfigs/linux-defconfig_xen_x86_32 --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/buildconfigs/linux-defconfig_xen_x86_32 Mon Jan 30 17:18:27 2006 @@ -0,0 +1,2773 @@ +# +# Automatically generated make config: don't edit +# Linux kernel version: 2.6.12.6-xen +# Wed Jan 25 17:30:02 2006 +# +CONFIG_X86=y +CONFIG_MMU=y +CONFIG_UID16=y +CONFIG_GENERIC_ISA_DMA=y +CONFIG_GENERIC_IOMAP=y + +# +# Code maturity level options +# +CONFIG_EXPERIMENTAL=y +# CONFIG_CLEAN_COMPILE is not set +CONFIG_BROKEN=y +CONFIG_BROKEN_ON_SMP=y +CONFIG_LOCK_KERNEL=y +CONFIG_INIT_ENV_ARG_LIMIT=32 + +# +# General setup +# +CONFIG_LOCALVERSION="" +CONFIG_SWAP=y +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +CONFIG_BSD_PROCESS_ACCT=y +# CONFIG_BSD_PROCESS_ACCT_V3 is not set +CONFIG_SYSCTL=y +# CONFIG_AUDIT is not set +CONFIG_HOTPLUG=y +CONFIG_KOBJECT_UEVENT=y +# CONFIG_IKCONFIG is not set +# CONFIG_CPUSETS is not set +CONFIG_EMBEDDED=y +CONFIG_KALLSYMS=y +# CONFIG_KALLSYMS_ALL is not set +# CONFIG_KALLSYMS_EXTRA_PASS is not set +CONFIG_PRINTK=y +CONFIG_BUG=y +CONFIG_BASE_FULL=y +CONFIG_FUTEX=y +CONFIG_EPOLL=y +# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set +CONFIG_SHMEM=y +CONFIG_CC_ALIGN_FUNCTIONS=0 +CONFIG_CC_ALIGN_LABELS=0 +CONFIG_CC_ALIGN_LOOPS=0 +CONFIG_CC_ALIGN_JUMPS=0 +# CONFIG_TINY_SHMEM is not set +CONFIG_BASE_SMALL=0 + +# +# Loadable module support +# +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODULE_FORCE_UNLOAD=y +CONFIG_OBSOLETE_MODPARM=y +CONFIG_MODVERSIONS=y +# CONFIG_MODULE_SRCVERSION_ALL is not set +CONFIG_KMOD=y +CONFIG_STOP_MACHINE=y + +# +# Processor type and features +# +# CONFIG_X86_PC is not set +CONFIG_X86_XEN=y +# CONFIG_X86_ELAN is not set +# CONFIG_X86_VOYAGER is not set +# CONFIG_X86_NUMAQ is not set +# CONFIG_X86_SUMMIT is not set +# CONFIG_X86_BIGSMP is not set +# CONFIG_X86_VISWS is not set +# CONFIG_X86_GENERICARCH is not set +# CONFIG_X86_ES7000 is not set +# CONFIG_M386 is not set +# CONFIG_M486 is not set +# CONFIG_M586 is not set +# CONFIG_M586TSC is not set +# CONFIG_M586MMX is not set +CONFIG_M686=y +# CONFIG_MPENTIUMII is not set +# CONFIG_MPENTIUMIII is not set +# CONFIG_MPENTIUMM is not set +# CONFIG_MPENTIUM4 is not set +# CONFIG_MK6 is not set +# CONFIG_MK7 is not set +# CONFIG_MK8 is not set +# CONFIG_MCRUSOE is not set +# CONFIG_MEFFICEON is not set +# CONFIG_MWINCHIPC6 is not set +# CONFIG_MWINCHIP2 is not set +# CONFIG_MWINCHIP3D is not set +# CONFIG_MGEODEGX1 is not set +# CONFIG_MCYRIXIII is not set +# CONFIG_MVIAC3_2 is not set +# CONFIG_X86_GENERIC is not set +CONFIG_X86_CMPXCHG=y +CONFIG_X86_XADD=y +CONFIG_X86_L1_CACHE_SHIFT=5 +CONFIG_RWSEM_XCHGADD_ALGORITHM=y +CONFIG_GENERIC_CALIBRATE_DELAY=y +CONFIG_X86_PPRO_FENCE=y +CONFIG_X86_WP_WORKS_OK=y +CONFIG_X86_INVLPG=y +CONFIG_X86_BSWAP=y +CONFIG_X86_POPAD_OK=y +CONFIG_X86_GOOD_APIC=y +CONFIG_X86_USE_PPRO_CHECKSUM=y +CONFIG_SMP=y +CONFIG_SMP_ALTERNATIVES=y +CONFIG_NR_CPUS=8 +CONFIG_X86_LOCAL_APIC=y +CONFIG_X86_IO_APIC=y +# CONFIG_TOSHIBA is not set +# CONFIG_I8K is not set +# CONFIG_X86_REBOOTFIXUPS is not set +CONFIG_MICROCODE=y +CONFIG_X86_CPUID=m +CONFIG_SWIOTLB=y + +# +# Firmware Drivers +# +# CONFIG_NOHIGHMEM is not set +CONFIG_HIGHMEM4G=y +# CONFIG_HIGHMEM64G is not set +CONFIG_HIGHMEM=y +CONFIG_MTRR=y +CONFIG_HAVE_DEC_LOCK=y +# CONFIG_REGPARM is not set +CONFIG_SECCOMP=y + +# +# Power management options (ACPI, APM) +# + +# +# ACPI (Advanced Configuration and Power Interface) Support +# +CONFIG_ACPI=y +CONFIG_ACPI_BOOT=y +CONFIG_ACPI_INTERPRETER=y +CONFIG_ACPI_AC=m +CONFIG_ACPI_BATTERY=m +CONFIG_ACPI_BUTTON=m +CONFIG_ACPI_VIDEO=m +CONFIG_ACPI_FAN=m +CONFIG_ACPI_PROCESSOR=m +CONFIG_ACPI_THERMAL=m +CONFIG_ACPI_ASUS=m +CONFIG_ACPI_IBM=m +CONFIG_ACPI_TOSHIBA=m +CONFIG_ACPI_BLACKLIST_YEAR=0 +# CONFIG_ACPI_DEBUG is not set +CONFIG_ACPI_BUS=y +CONFIG_ACPI_EC=y +CONFIG_ACPI_POWER=y +CONFIG_ACPI_PCI=y +CONFIG_ACPI_SYSTEM=y +# CONFIG_X86_PM_TIMER is not set +# CONFIG_ACPI_CONTAINER is not set + +# +# CPU Frequency scaling +# +# CONFIG_CPU_FREQ is not set + +# +# Bus options (PCI, PCMCIA, EISA, MCA, ISA) +# +CONFIG_PCI=y +# CONFIG_PCI_GOBIOS is not set +# CONFIG_PCI_GOMMCONFIG is not set +# CONFIG_PCI_GODIRECT is not set +CONFIG_PCI_GOANY=y +CONFIG_PCI_DIRECT=y +CONFIG_PCI_MMCONFIG=y +# CONFIG_PCIEPORTBUS is not set +# CONFIG_PCI_LEGACY_PROC is not set +CONFIG_PCI_NAMES=y +# CONFIG_PCI_DEBUG is not set +CONFIG_SCx200=m + +# +# PCCARD (PCMCIA/CardBus) support +# +CONFIG_PCCARD=m +# CONFIG_PCMCIA_DEBUG is not set +CONFIG_PCMCIA=m +CONFIG_CARDBUS=y + +# +# PC-card bridges +# +CONFIG_YENTA=m +CONFIG_PD6729=m +CONFIG_I82092=m +CONFIG_TCIC=m +CONFIG_PCCARD_NONSTATIC=m + +# +# PCI Hotplug Support +# +CONFIG_HOTPLUG_PCI=m +CONFIG_HOTPLUG_PCI_FAKE=m +# CONFIG_HOTPLUG_PCI_ACPI is not set +CONFIG_HOTPLUG_PCI_CPCI=y +CONFIG_HOTPLUG_PCI_CPCI_ZT5550=m +CONFIG_HOTPLUG_PCI_CPCI_GENERIC=m +CONFIG_HOTPLUG_PCI_SHPC=m +# CONFIG_HOTPLUG_PCI_SHPC_POLL_EVENT_MODE is not set + +# +# Executable file formats +# +CONFIG_BINFMT_ELF=y +CONFIG_BINFMT_AOUT=m +CONFIG_BINFMT_MISC=m + +# +# Device Drivers +# + +# +# Generic Driver Options +# +CONFIG_STANDALONE=y +CONFIG_PREVENT_FIRMWARE_BUILD=y +CONFIG_FW_LOADER=m +# CONFIG_DEBUG_DRIVER is not set + +# +# Memory Technology Devices (MTD) +# +CONFIG_MTD=m +# CONFIG_MTD_DEBUG is not set +CONFIG_MTD_CONCAT=m +CONFIG_MTD_PARTITIONS=y +CONFIG_MTD_REDBOOT_PARTS=m +CONFIG_MTD_REDBOOT_DIRECTORY_BLOCK=-1 +# CONFIG_MTD_REDBOOT_PARTS_UNALLOCATED is not set +# CONFIG_MTD_REDBOOT_PARTS_READONLY is not set +# CONFIG_MTD_CMDLINE_PARTS is not set + +# +# User Modules And Translation Layers +# +CONFIG_MTD_CHAR=m +CONFIG_MTD_BLOCK=m +CONFIG_MTD_BLOCK_RO=m +CONFIG_FTL=m +CONFIG_NFTL=m +CONFIG_NFTL_RW=y +CONFIG_INFTL=m + +# +# RAM/ROM/Flash chip drivers +# +CONFIG_MTD_CFI=m +CONFIG_MTD_JEDECPROBE=m +CONFIG_MTD_GEN_PROBE=m +# CONFIG_MTD_CFI_ADV_OPTIONS is not set +CONFIG_MTD_MAP_BANK_WIDTH_1=y +CONFIG_MTD_MAP_BANK_WIDTH_2=y +CONFIG_MTD_MAP_BANK_WIDTH_4=y +# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set +# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set +# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set +CONFIG_MTD_CFI_I1=y +CONFIG_MTD_CFI_I2=y +# CONFIG_MTD_CFI_I4 is not set +# CONFIG_MTD_CFI_I8 is not set +CONFIG_MTD_CFI_INTELEXT=m +CONFIG_MTD_CFI_AMDSTD=m +CONFIG_MTD_CFI_AMDSTD_RETRY=0 +CONFIG_MTD_CFI_STAA=m +CONFIG_MTD_CFI_UTIL=m +CONFIG_MTD_RAM=m +CONFIG_MTD_ROM=m +CONFIG_MTD_ABSENT=m +# CONFIG_MTD_OBSOLETE_CHIPS is not set + +# +# Mapping drivers for chip access +# +CONFIG_MTD_COMPLEX_MAPPINGS=y +CONFIG_MTD_PHYSMAP=m +CONFIG_MTD_PHYSMAP_START=0x8000000 +CONFIG_MTD_PHYSMAP_LEN=0x4000000 +CONFIG_MTD_PHYSMAP_BANKWIDTH=2 +CONFIG_MTD_PNC2000=m +CONFIG_MTD_SC520CDP=m +CONFIG_MTD_NETSC520=m +CONFIG_MTD_TS5500=m +CONFIG_MTD_SBC_GXX=m +CONFIG_MTD_ELAN_104NC=m +CONFIG_MTD_SCx200_DOCFLASH=m +# CONFIG_MTD_AMD76XROM is not set +# CONFIG_MTD_ICHXROM is not set +# CONFIG_MTD_SCB2_FLASH is not set +CONFIG_MTD_NETtel=m +CONFIG_MTD_DILNETPC=m +CONFIG_MTD_DILNETPC_BOOTSIZE=0x80000 +# CONFIG_MTD_L440GX is not set +CONFIG_MTD_PCI=m +CONFIG_MTD_PCMCIA=m + +# +# Self-contained MTD device drivers +# +CONFIG_MTD_PMC551=m +# CONFIG_MTD_PMC551_BUGFIX is not set +# CONFIG_MTD_PMC551_DEBUG is not set +CONFIG_MTD_SLRAM=m +CONFIG_MTD_PHRAM=m +CONFIG_MTD_MTDRAM=m +CONFIG_MTDRAM_TOTAL_SIZE=4096 +CONFIG_MTDRAM_ERASE_SIZE=128 +CONFIG_MTD_BLKMTD=m +# CONFIG_MTD_BLOCK2MTD is not set + +# +# Disk-On-Chip Device Drivers +# +CONFIG_MTD_DOC2000=m +CONFIG_MTD_DOC2001=m +CONFIG_MTD_DOC2001PLUS=m +CONFIG_MTD_DOCPROBE=m +CONFIG_MTD_DOCECC=m +# CONFIG_MTD_DOCPROBE_ADVANCED is not set +CONFIG_MTD_DOCPROBE_ADDRESS=0 + +# +# NAND Flash Device Drivers +# +CONFIG_MTD_NAND=m +# CONFIG_MTD_NAND_VERIFY_WRITE is not set +CONFIG_MTD_NAND_IDS=m +CONFIG_MTD_NAND_DISKONCHIP=m +# CONFIG_MTD_NAND_DISKONCHIP_PROBE_ADVANCED is not set +CONFIG_MTD_NAND_DISKONCHIP_PROBE_ADDRESS=0 +# CONFIG_MTD_NAND_DISKONCHIP_BBTWRITE is not set +# CONFIG_MTD_NAND_NANDSIM is not set + +# +# Parallel port support +# +CONFIG_PARPORT=m +CONFIG_PARPORT_PC=m +CONFIG_PARPORT_SERIAL=m +CONFIG_PARPORT_PC_FIFO=y +# CONFIG_PARPORT_PC_SUPERIO is not set +CONFIG_PARPORT_PC_PCMCIA=m +CONFIG_PARPORT_NOT_PC=y +# CONFIG_PARPORT_GSC is not set +CONFIG_PARPORT_1284=y + +# +# Plug and Play support +# +CONFIG_PNP=y +# CONFIG_PNP_DEBUG is not set + +# +# Protocols +# +# CONFIG_PNPACPI is not set + +# +# Block devices +# +CONFIG_BLK_DEV_FD=m +CONFIG_PARIDE=m +CONFIG_PARIDE_PARPORT=m + +# +# Parallel IDE high-level drivers +# +CONFIG_PARIDE_PD=m +CONFIG_PARIDE_PCD=m +CONFIG_PARIDE_PF=m +CONFIG_PARIDE_PT=m +CONFIG_PARIDE_PG=m + +# +# Parallel IDE protocol modules +# +CONFIG_PARIDE_ATEN=m +CONFIG_PARIDE_BPCK=m +CONFIG_PARIDE_BPCK6=m +CONFIG_PARIDE_COMM=m +CONFIG_PARIDE_DSTR=m +CONFIG_PARIDE_FIT2=m +CONFIG_PARIDE_FIT3=m +CONFIG_PARIDE_EPAT=m +# CONFIG_PARIDE_EPATC8 is not set +CONFIG_PARIDE_EPIA=m +CONFIG_PARIDE_FRIQ=m +CONFIG_PARIDE_FRPW=m +CONFIG_PARIDE_KBIC=m +CONFIG_PARIDE_KTTI=m +CONFIG_PARIDE_ON20=m +CONFIG_PARIDE_ON26=m +CONFIG_BLK_CPQ_DA=m +CONFIG_BLK_CPQ_CISS_DA=m +CONFIG_CISS_SCSI_TAPE=y +CONFIG_BLK_DEV_DAC960=m +CONFIG_BLK_DEV_UMEM=m +# CONFIG_BLK_DEV_COW_COMMON is not set +CONFIG_BLK_DEV_LOOP=m +CONFIG_BLK_DEV_CRYPTOLOOP=m +CONFIG_BLK_DEV_NBD=m +CONFIG_BLK_DEV_SX8=m +# CONFIG_BLK_DEV_UB is not set +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_COUNT=16 +CONFIG_BLK_DEV_RAM_SIZE=16384 +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="" +CONFIG_LBD=y +CONFIG_CDROM_PKTCDVD=m +CONFIG_CDROM_PKTCDVD_BUFFERS=8 +# CONFIG_CDROM_PKTCDVD_WCACHE is not set + +# +# IO Schedulers +# +CONFIG_IOSCHED_NOOP=y +CONFIG_IOSCHED_AS=y +CONFIG_IOSCHED_DEADLINE=y +CONFIG_IOSCHED_CFQ=y +CONFIG_ATA_OVER_ETH=m + +# +# ATA/ATAPI/MFM/RLL support +# +CONFIG_IDE=y +CONFIG_BLK_DEV_IDE=y + +# +# Please see Documentation/ide.txt for help/info on IDE drives +# +# CONFIG_BLK_DEV_IDE_SATA is not set +# CONFIG_BLK_DEV_HD_IDE is not set +CONFIG_BLK_DEV_IDEDISK=y +CONFIG_IDEDISK_MULTI_MODE=y +CONFIG_BLK_DEV_IDECS=m +CONFIG_BLK_DEV_IDECD=y +CONFIG_BLK_DEV_IDETAPE=m +CONFIG_BLK_DEV_IDEFLOPPY=y +CONFIG_BLK_DEV_IDESCSI=m +# CONFIG_IDE_TASK_IOCTL is not set + +# +# IDE chipset support/bugfixes +# +CONFIG_IDE_GENERIC=y +CONFIG_BLK_DEV_CMD640=y +CONFIG_BLK_DEV_CMD640_ENHANCED=y +CONFIG_BLK_DEV_IDEPNP=y +CONFIG_BLK_DEV_IDEPCI=y +CONFIG_IDEPCI_SHARE_IRQ=y +# CONFIG_BLK_DEV_OFFBOARD is not set +CONFIG_BLK_DEV_GENERIC=y +CONFIG_BLK_DEV_OPTI621=m +CONFIG_BLK_DEV_RZ1000=y +CONFIG_BLK_DEV_IDEDMA_PCI=y +# CONFIG_BLK_DEV_IDEDMA_FORCED is not set +CONFIG_IDEDMA_PCI_AUTO=y +# CONFIG_IDEDMA_ONLYDISK is not set +CONFIG_BLK_DEV_AEC62XX=y +CONFIG_BLK_DEV_ALI15X3=y +# CONFIG_WDC_ALI15X3 is not set +CONFIG_BLK_DEV_AMD74XX=y +CONFIG_BLK_DEV_ATIIXP=y +CONFIG_BLK_DEV_CMD64X=y +CONFIG_BLK_DEV_TRIFLEX=y +CONFIG_BLK_DEV_CY82C693=y +CONFIG_BLK_DEV_CS5520=y +CONFIG_BLK_DEV_CS5530=y +CONFIG_BLK_DEV_HPT34X=y +# CONFIG_HPT34X_AUTODMA is not set +CONFIG_BLK_DEV_HPT366=y +CONFIG_BLK_DEV_SC1200=m +CONFIG_BLK_DEV_PIIX=y +CONFIG_BLK_DEV_NS87415=m +CONFIG_BLK_DEV_PDC202XX_OLD=y +CONFIG_PDC202XX_BURST=y +CONFIG_BLK_DEV_PDC202XX_NEW=y +CONFIG_PDC202XX_FORCE=y +CONFIG_BLK_DEV_SVWKS=y +CONFIG_BLK_DEV_SIIMAGE=y +CONFIG_BLK_DEV_SIS5513=y +CONFIG_BLK_DEV_SLC90E66=y +CONFIG_BLK_DEV_TRM290=m +CONFIG_BLK_DEV_VIA82CXXX=y +# CONFIG_IDE_ARM is not set +CONFIG_BLK_DEV_IDEDMA=y +# CONFIG_IDEDMA_IVB is not set +CONFIG_IDEDMA_AUTO=y +# CONFIG_BLK_DEV_HD is not set + +# +# SCSI device support +# +CONFIG_SCSI=m +CONFIG_SCSI_PROC_FS=y + +# +# SCSI support type (disk, tape, CD-ROM) +# +CONFIG_BLK_DEV_SD=m +CONFIG_CHR_DEV_ST=m +CONFIG_CHR_DEV_OSST=m +CONFIG_BLK_DEV_SR=m +# CONFIG_BLK_DEV_SR_VENDOR is not set +CONFIG_CHR_DEV_SG=m + +# +# Some SCSI devices (e.g. CD jukebox) support multiple LUNs +# +CONFIG_SCSI_MULTI_LUN=y +CONFIG_SCSI_CONSTANTS=y +CONFIG_SCSI_LOGGING=y + +# +# SCSI Transport Attributes +# +CONFIG_SCSI_SPI_ATTRS=m +CONFIG_SCSI_FC_ATTRS=m +# CONFIG_SCSI_ISCSI_ATTRS is not set + +# +# SCSI low-level drivers +# +CONFIG_BLK_DEV_3W_XXXX_RAID=m +CONFIG_SCSI_3W_9XXX=m +CONFIG_SCSI_ACARD=m +CONFIG_SCSI_AACRAID=m +CONFIG_SCSI_AIC7XXX=m +CONFIG_AIC7XXX_CMDS_PER_DEVICE=8 +CONFIG_AIC7XXX_RESET_DELAY_MS=15000 +CONFIG_AIC7XXX_DEBUG_ENABLE=y +CONFIG_AIC7XXX_DEBUG_MASK=0 +CONFIG_AIC7XXX_REG_PRETTY_PRINT=y +CONFIG_SCSI_AIC7XXX_OLD=m +CONFIG_SCSI_AIC79XX=m +CONFIG_AIC79XX_CMDS_PER_DEVICE=32 +CONFIG_AIC79XX_RESET_DELAY_MS=15000 +CONFIG_AIC79XX_ENABLE_RD_STRM=y +CONFIG_AIC79XX_DEBUG_ENABLE=y +CONFIG_AIC79XX_DEBUG_MASK=0 +CONFIG_AIC79XX_REG_PRETTY_PRINT=y +CONFIG_SCSI_DPT_I2O=m +CONFIG_SCSI_ADVANSYS=m +CONFIG_MEGARAID_NEWGEN=y +CONFIG_MEGARAID_MM=m +CONFIG_MEGARAID_MAILBOX=m +CONFIG_SCSI_SATA=y +CONFIG_SCSI_SATA_AHCI=m +CONFIG_SCSI_SATA_SVW=m +CONFIG_SCSI_ATA_PIIX=m +CONFIG_SCSI_SATA_NV=m +CONFIG_SCSI_SATA_PROMISE=m +# CONFIG_SCSI_SATA_QSTOR is not set +CONFIG_SCSI_SATA_SX4=m +CONFIG_SCSI_SATA_SIL=m +CONFIG_SCSI_SATA_SIS=m +CONFIG_SCSI_SATA_ULI=m +CONFIG_SCSI_SATA_VIA=m +CONFIG_SCSI_SATA_VITESSE=m +# CONFIG_SCSI_CPQFCTS is not set +CONFIG_SCSI_DMX3191D=m +CONFIG_SCSI_EATA_PIO=m +CONFIG_SCSI_FUTURE_DOMAIN=m +CONFIG_SCSI_IPS=m +# CONFIG_SCSI_INITIO is not set +# CONFIG_SCSI_INIA100 is not set +CONFIG_SCSI_PPA=m +CONFIG_SCSI_IMM=m +# CONFIG_SCSI_IZIP_EPP16 is not set +# CONFIG_SCSI_IZIP_SLOW_CTR is not set +CONFIG_SCSI_SYM53C8XX_2=m +CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=1 +CONFIG_SCSI_SYM53C8XX_DEFAULT_TAGS=16 +CONFIG_SCSI_SYM53C8XX_MAX_TAGS=64 +# CONFIG_SCSI_SYM53C8XX_IOMAPPED is not set +CONFIG_SCSI_IPR=m +# CONFIG_SCSI_IPR_TRACE is not set +# CONFIG_SCSI_IPR_DUMP is not set +# CONFIG_SCSI_PCI2000 is not set +# CONFIG_SCSI_PCI2220I is not set +CONFIG_SCSI_QLOGIC_ISP=m +CONFIG_SCSI_QLOGIC_FC=m +CONFIG_SCSI_QLOGIC_FC_FIRMWARE=y +CONFIG_SCSI_QLOGIC_1280=m +CONFIG_SCSI_QLOGIC_1280_1040=y +CONFIG_SCSI_QLA2XXX=m +CONFIG_SCSI_QLA21XX=m +CONFIG_SCSI_QLA22XX=m +CONFIG_SCSI_QLA2300=m +CONFIG_SCSI_QLA2322=m +CONFIG_SCSI_QLA6312=m +CONFIG_SCSI_LPFC=m +CONFIG_SCSI_DC395x=m +CONFIG_SCSI_DC390T=m +CONFIG_SCSI_NSP32=m +CONFIG_SCSI_DEBUG=m + +# +# PCMCIA SCSI adapter support +# +CONFIG_PCMCIA_AHA152X=m +CONFIG_PCMCIA_FDOMAIN=m +CONFIG_PCMCIA_NINJA_SCSI=m +CONFIG_PCMCIA_QLOGIC=m +CONFIG_PCMCIA_SYM53C500=m + +# +# Multi-device support (RAID and LVM) +# +CONFIG_MD=y +CONFIG_BLK_DEV_MD=m +CONFIG_MD_LINEAR=m +CONFIG_MD_RAID0=m +CONFIG_MD_RAID1=m +CONFIG_MD_RAID10=m +CONFIG_MD_RAID5=m +CONFIG_MD_RAID6=m +CONFIG_MD_MULTIPATH=m +CONFIG_MD_FAULTY=m +CONFIG_BLK_DEV_DM=m +CONFIG_DM_CRYPT=m +CONFIG_DM_SNAPSHOT=m +CONFIG_DM_MIRROR=m +CONFIG_DM_ZERO=m +CONFIG_DM_MULTIPATH=m +CONFIG_DM_MULTIPATH_EMC=m + +# +# Fusion MPT device support +# +CONFIG_FUSION=m +CONFIG_FUSION_MAX_SGE=40 +CONFIG_FUSION_CTL=m +CONFIG_FUSION_LAN=m + +# +# IEEE 1394 (FireWire) support +# +CONFIG_IEEE1394=m + +# +# Subsystem Options +# +# CONFIG_IEEE1394_VERBOSEDEBUG is not set +# CONFIG_IEEE1394_OUI_DB is not set +CONFIG_IEEE1394_EXTRA_CONFIG_ROMS=y +CONFIG_IEEE1394_CONFIG_ROM_IP1394=y + +# +# Device Drivers +# +CONFIG_IEEE1394_PCILYNX=m +CONFIG_IEEE1394_OHCI1394=m + +# +# Protocol Drivers +# +CONFIG_IEEE1394_VIDEO1394=m +CONFIG_IEEE1394_SBP2=m +# CONFIG_IEEE1394_SBP2_PHYS_DMA is not set +CONFIG_IEEE1394_ETH1394=m +CONFIG_IEEE1394_DV1394=m +CONFIG_IEEE1394_RAWIO=m +CONFIG_IEEE1394_CMP=m +CONFIG_IEEE1394_AMDTP=m + +# +# I2O device support +# +CONFIG_I2O=m +CONFIG_I2O_CONFIG=m +CONFIG_I2O_BLOCK=m +CONFIG_I2O_SCSI=m +CONFIG_I2O_PROC=m + +# +# Networking support +# +CONFIG_NET=y + +# +# Networking options +# +CONFIG_PACKET=m +CONFIG_PACKET_MMAP=y +CONFIG_UNIX=m +CONFIG_NET_KEY=m +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_ROUTE_FWMARK=y +CONFIG_IP_ROUTE_MULTIPATH=y +# CONFIG_IP_ROUTE_MULTIPATH_CACHED is not set +CONFIG_IP_ROUTE_VERBOSE=y +# CONFIG_IP_PNP is not set +CONFIG_NET_IPIP=m +CONFIG_NET_IPGRE=m +CONFIG_NET_IPGRE_BROADCAST=y +CONFIG_IP_MROUTE=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +# CONFIG_ARPD is not set +CONFIG_SYN_COOKIES=y +CONFIG_INET_AH=m +CONFIG_INET_ESP=m +CONFIG_INET_IPCOMP=m +CONFIG_INET_TUNNEL=m +CONFIG_IP_TCPDIAG=m +CONFIG_IP_TCPDIAG_IPV6=y + +# +# IP: Virtual Server Configuration +# +CONFIG_IP_VS=m +# CONFIG_IP_VS_DEBUG is not set +CONFIG_IP_VS_TAB_BITS=12 + +# +# IPVS transport protocol load balancing support +# +CONFIG_IP_VS_PROTO_TCP=y +CONFIG_IP_VS_PROTO_UDP=y +CONFIG_IP_VS_PROTO_ESP=y +CONFIG_IP_VS_PROTO_AH=y + +# +# IPVS scheduler +# +CONFIG_IP_VS_RR=m +CONFIG_IP_VS_WRR=m +CONFIG_IP_VS_LC=m +CONFIG_IP_VS_WLC=m +CONFIG_IP_VS_LBLC=m +CONFIG_IP_VS_LBLCR=m +CONFIG_IP_VS_DH=m +CONFIG_IP_VS_SH=m +CONFIG_IP_VS_SED=m +CONFIG_IP_VS_NQ=m + +# +# IPVS application helper +# +CONFIG_IP_VS_FTP=m +CONFIG_IPV6=m +CONFIG_IPV6_PRIVACY=y +CONFIG_INET6_AH=m +CONFIG_INET6_ESP=m +CONFIG_INET6_IPCOMP=m +CONFIG_INET6_TUNNEL=m +CONFIG_IPV6_TUNNEL=m +CONFIG_NETFILTER=y +# CONFIG_NETFILTER_DEBUG is not set +CONFIG_BRIDGE_NETFILTER=y + +# +# IP: Netfilter Configuration +# +CONFIG_IP_NF_CONNTRACK=m +CONFIG_IP_NF_CT_ACCT=y +CONFIG_IP_NF_CONNTRACK_MARK=y +CONFIG_IP_NF_CT_PROTO_SCTP=m +CONFIG_IP_NF_FTP=m +CONFIG_IP_NF_IRC=m +CONFIG_IP_NF_TFTP=m +CONFIG_IP_NF_AMANDA=m +CONFIG_IP_NF_QUEUE=m +CONFIG_IP_NF_IPTABLES=m +CONFIG_IP_NF_MATCH_LIMIT=m +CONFIG_IP_NF_MATCH_IPRANGE=m +CONFIG_IP_NF_MATCH_MAC=m +CONFIG_IP_NF_MATCH_PKTTYPE=m +CONFIG_IP_NF_MATCH_MARK=m +CONFIG_IP_NF_MATCH_MULTIPORT=m +CONFIG_IP_NF_MATCH_TOS=m +CONFIG_IP_NF_MATCH_RECENT=m +CONFIG_IP_NF_MATCH_ECN=m +CONFIG_IP_NF_MATCH_DSCP=m +CONFIG_IP_NF_MATCH_AH_ESP=m +CONFIG_IP_NF_MATCH_LENGTH=m +CONFIG_IP_NF_MATCH_TTL=m +CONFIG_IP_NF_MATCH_TCPMSS=m +CONFIG_IP_NF_MATCH_HELPER=m +CONFIG_IP_NF_MATCH_STATE=m +CONFIG_IP_NF_MATCH_CONNTRACK=m +CONFIG_IP_NF_MATCH_OWNER=m +CONFIG_IP_NF_MATCH_PHYSDEV=m +CONFIG_IP_NF_MATCH_ADDRTYPE=m +CONFIG_IP_NF_MATCH_REALM=m +CONFIG_IP_NF_MATCH_SCTP=m +CONFIG_IP_NF_MATCH_COMMENT=m +CONFIG_IP_NF_MATCH_CONNMARK=m +CONFIG_IP_NF_MATCH_HASHLIMIT=m +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP_NF_TARGET_LOG=m +CONFIG_IP_NF_TARGET_ULOG=m +CONFIG_IP_NF_TARGET_TCPMSS=m +CONFIG_IP_NF_NAT=m +CONFIG_IP_NF_NAT_NEEDED=y +CONFIG_IP_NF_TARGET_MASQUERADE=m +CONFIG_IP_NF_TARGET_REDIRECT=m +CONFIG_IP_NF_TARGET_NETMAP=m +CONFIG_IP_NF_TARGET_SAME=m +CONFIG_IP_NF_NAT_SNMP_BASIC=m +CONFIG_IP_NF_NAT_IRC=m +CONFIG_IP_NF_NAT_FTP=m +CONFIG_IP_NF_NAT_TFTP=m +CONFIG_IP_NF_NAT_AMANDA=m +CONFIG_IP_NF_MANGLE=m +CONFIG_IP_NF_TARGET_TOS=m +CONFIG_IP_NF_TARGET_ECN=m +CONFIG_IP_NF_TARGET_DSCP=m +CONFIG_IP_NF_TARGET_MARK=m +CONFIG_IP_NF_TARGET_CLASSIFY=m +CONFIG_IP_NF_TARGET_CONNMARK=m +CONFIG_IP_NF_TARGET_CLUSTERIP=m +CONFIG_IP_NF_RAW=m +CONFIG_IP_NF_TARGET_NOTRACK=m +CONFIG_IP_NF_ARPTABLES=m +CONFIG_IP_NF_ARPFILTER=m +CONFIG_IP_NF_ARP_MANGLE=m + +# +# IPv6: Netfilter Configuration (EXPERIMENTAL) +# +CONFIG_IP6_NF_QUEUE=m +CONFIG_IP6_NF_IPTABLES=m +CONFIG_IP6_NF_MATCH_LIMIT=m +CONFIG_IP6_NF_MATCH_MAC=m +CONFIG_IP6_NF_MATCH_RT=m +CONFIG_IP6_NF_MATCH_OPTS=m +CONFIG_IP6_NF_MATCH_FRAG=m +CONFIG_IP6_NF_MATCH_HL=m +CONFIG_IP6_NF_MATCH_MULTIPORT=m +CONFIG_IP6_NF_MATCH_OWNER=m +CONFIG_IP6_NF_MATCH_MARK=m +CONFIG_IP6_NF_MATCH_IPV6HEADER=m +CONFIG_IP6_NF_MATCH_AHESP=m +CONFIG_IP6_NF_MATCH_LENGTH=m +CONFIG_IP6_NF_MATCH_EUI64=m +CONFIG_IP6_NF_MATCH_PHYSDEV=m +CONFIG_IP6_NF_FILTER=m +CONFIG_IP6_NF_TARGET_LOG=m +CONFIG_IP6_NF_MANGLE=m +CONFIG_IP6_NF_TARGET_MARK=m +CONFIG_IP6_NF_RAW=m + +# +# DECnet: Netfilter Configuration +# +CONFIG_DECNET_NF_GRABULATOR=m + +# +# Bridge: Netfilter Configuration +# +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_BRIDGE_EBT_T_FILTER=m +CONFIG_BRIDGE_EBT_T_NAT=m +CONFIG_BRIDGE_EBT_802_3=m +CONFIG_BRIDGE_EBT_AMONG=m +CONFIG_BRIDGE_EBT_ARP=m +CONFIG_BRIDGE_EBT_IP=m +CONFIG_BRIDGE_EBT_LIMIT=m +CONFIG_BRIDGE_EBT_MARK=m +CONFIG_BRIDGE_EBT_PKTTYPE=m +CONFIG_BRIDGE_EBT_STP=m +CONFIG_BRIDGE_EBT_VLAN=m +CONFIG_BRIDGE_EBT_ARPREPLY=m +CONFIG_BRIDGE_EBT_DNAT=m +CONFIG_BRIDGE_EBT_MARK_T=m +CONFIG_BRIDGE_EBT_REDIRECT=m +CONFIG_BRIDGE_EBT_SNAT=m +CONFIG_BRIDGE_EBT_LOG=m +# CONFIG_BRIDGE_EBT_ULOG is not set +CONFIG_XFRM=y +CONFIG_XFRM_USER=m + +# +# SCTP Configuration (EXPERIMENTAL) +# +CONFIG_IP_SCTP=m +# CONFIG_SCTP_DBG_MSG is not set +# CONFIG_SCTP_DBG_OBJCNT is not set +# CONFIG_SCTP_HMAC_NONE is not set +# CONFIG_SCTP_HMAC_SHA1 is not set +CONFIG_SCTP_HMAC_MD5=y +CONFIG_ATM=y +CONFIG_ATM_CLIP=y +# CONFIG_ATM_CLIP_NO_ICMP is not set +CONFIG_ATM_LANE=m +CONFIG_ATM_MPOA=m +CONFIG_ATM_BR2684=m +# CONFIG_ATM_BR2684_IPFILTER is not set +CONFIG_BRIDGE=m +CONFIG_VLAN_8021Q=m +CONFIG_DECNET=m +# CONFIG_DECNET_ROUTER is not set +CONFIG_LLC=y +CONFIG_LLC2=m +CONFIG_IPX=m +# CONFIG_IPX_INTERN is not set +CONFIG_ATALK=m +CONFIG_DEV_APPLETALK=y +CONFIG_IPDDP=m +CONFIG_IPDDP_ENCAP=y +CONFIG_IPDDP_DECAP=y +CONFIG_X25=m +CONFIG_LAPB=m +# CONFIG_NET_DIVERT is not set +CONFIG_ECONET=m +CONFIG_ECONET_AUNUDP=y +CONFIG_ECONET_NATIVE=y +CONFIG_WAN_ROUTER=m + +# +# QoS and/or fair queueing +# +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_CLK_JIFFIES=y +# CONFIG_NET_SCH_CLK_GETTIMEOFDAY is not set +# CONFIG_NET_SCH_CLK_CPU is not set +CONFIG_NET_SCH_CBQ=m +CONFIG_NET_SCH_HTB=m +CONFIG_NET_SCH_HFSC=m +CONFIG_NET_SCH_ATM=m +CONFIG_NET_SCH_PRIO=m +CONFIG_NET_SCH_RED=m +CONFIG_NET_SCH_SFQ=m +CONFIG_NET_SCH_TEQL=m +CONFIG_NET_SCH_TBF=m +CONFIG_NET_SCH_GRED=m +CONFIG_NET_SCH_DSMARK=m +CONFIG_NET_SCH_NETEM=m +CONFIG_NET_SCH_INGRESS=m +CONFIG_NET_QOS=y +CONFIG_NET_ESTIMATOR=y +CONFIG_NET_CLS=y +CONFIG_NET_CLS_BASIC=m +CONFIG_NET_CLS_TCINDEX=m +CONFIG_NET_CLS_ROUTE4=m +CONFIG_NET_CLS_ROUTE=y +CONFIG_NET_CLS_FW=m +CONFIG_NET_CLS_U32=m +# CONFIG_CLS_U32_PERF is not set +# CONFIG_NET_CLS_IND is not set +# CONFIG_CLS_U32_MARK is not set +CONFIG_NET_CLS_RSVP=m +CONFIG_NET_CLS_RSVP6=m +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_STACK=32 +CONFIG_NET_EMATCH_CMP=m +CONFIG_NET_EMATCH_NBYTE=m +CONFIG_NET_EMATCH_U32=m +CONFIG_NET_EMATCH_META=m +# CONFIG_NET_CLS_ACT is not set +CONFIG_NET_CLS_POLICE=y + +# +# Network testing +# +CONFIG_NET_PKTGEN=m +CONFIG_NETPOLL=y +# CONFIG_NETPOLL_RX is not set +# CONFIG_NETPOLL_TRAP is not set +CONFIG_NET_POLL_CONTROLLER=y +CONFIG_HAMRADIO=y + +# +# Packet Radio protocols +# +CONFIG_AX25=m +# CONFIG_AX25_DAMA_SLAVE is not set +CONFIG_NETROM=m +CONFIG_ROSE=m + +# +# AX.25 network device drivers +# +CONFIG_MKISS=m +CONFIG_6PACK=m +CONFIG_BPQETHER=m +CONFIG_BAYCOM_SER_FDX=m +CONFIG_BAYCOM_SER_HDX=m +CONFIG_BAYCOM_PAR=m +CONFIG_BAYCOM_EPP=m +CONFIG_YAM=m +CONFIG_IRDA=m + +# +# IrDA protocols +# +CONFIG_IRLAN=m +CONFIG_IRNET=m +CONFIG_IRCOMM=m +# CONFIG_IRDA_ULTRA is not set + +# +# IrDA options +# +CONFIG_IRDA_CACHE_LAST_LSAP=y +CONFIG_IRDA_FAST_RR=y +CONFIG_IRDA_DEBUG=y + +# +# Infrared-port device drivers +# + +# +# SIR device drivers +# +CONFIG_IRTTY_SIR=m + +# +# Dongle support +# +CONFIG_DONGLE=y +CONFIG_ESI_DONGLE=m +CONFIG_ACTISYS_DONGLE=m +CONFIG_TEKRAM_DONGLE=m +CONFIG_LITELINK_DONGLE=m +CONFIG_MA600_DONGLE=m +CONFIG_GIRBIL_DONGLE=m +CONFIG_MCP2120_DONGLE=m +CONFIG_OLD_BELKIN_DONGLE=m +CONFIG_ACT200L_DONGLE=m + +# +# Old SIR device drivers +# +CONFIG_IRPORT_SIR=m + +# +# Old Serial dongle support +# +# CONFIG_DONGLE_OLD is not set + +# +# FIR device drivers +# +CONFIG_USB_IRDA=m +CONFIG_SIGMATEL_FIR=m +# CONFIG_TOSHIBA_FIR is not set +CONFIG_VLSI_FIR=m +CONFIG_BT=m +CONFIG_BT_L2CAP=m +CONFIG_BT_SCO=m +CONFIG_BT_RFCOMM=m +CONFIG_BT_RFCOMM_TTY=y +CONFIG_BT_BNEP=m +CONFIG_BT_BNEP_MC_FILTER=y +CONFIG_BT_BNEP_PROTO_FILTER=y +CONFIG_BT_CMTP=m +CONFIG_BT_HIDP=m + +# +# Bluetooth device drivers +# +CONFIG_BT_HCIUSB=m +CONFIG_BT_HCIUSB_SCO=y +CONFIG_BT_HCIUART=m +CONFIG_BT_HCIUART_H4=y +CONFIG_BT_HCIUART_BCSP=y +# CONFIG_BT_HCIUART_BCSP_TXCRC is not set +CONFIG_BT_HCIBCM203X=m +# CONFIG_BT_HCIBPA10X is not set +CONFIG_BT_HCIBFUSB=m +CONFIG_BT_HCIDTL1=m +CONFIG_BT_HCIBT3C=m +CONFIG_BT_HCIBLUECARD=m +CONFIG_BT_HCIBTUART=m +CONFIG_BT_HCIVHCI=m +CONFIG_NETDEVICES=y +CONFIG_DUMMY=m +CONFIG_BONDING=m +CONFIG_EQUALIZER=m +CONFIG_TUN=m +CONFIG_NET_SB1000=m + +# +# ARCnet devices +# +CONFIG_ARCNET=m +CONFIG_ARCNET_1201=m +CONFIG_ARCNET_1051=m +CONFIG_ARCNET_RAW=m +# CONFIG_ARCNET_CAP is not set +CONFIG_ARCNET_COM90xx=m +CONFIG_ARCNET_COM90xxIO=m +CONFIG_ARCNET_RIM_I=m +CONFIG_ARCNET_COM20020=m +CONFIG_ARCNET_COM20020_PCI=m + +# +# Ethernet (10 or 100Mbit) +# +CONFIG_NET_ETHERNET=y +CONFIG_MII=m +CONFIG_HAPPYMEAL=m +CONFIG_SUNGEM=m +CONFIG_NET_VENDOR_3COM=y +CONFIG_VORTEX=m +CONFIG_TYPHOON=m + +# +# Tulip family network device support +# +CONFIG_NET_TULIP=y +CONFIG_DE2104X=m +CONFIG_TULIP=m +# CONFIG_TULIP_MWI is not set +# CONFIG_TULIP_MMIO is not set +# CONFIG_TULIP_NAPI is not set +CONFIG_DE4X5=m +CONFIG_WINBOND_840=m +CONFIG_DM9102=m +CONFIG_PCMCIA_XIRCOM=m +# CONFIG_PCMCIA_XIRTULIP is not set +CONFIG_HP100=m +CONFIG_NET_PCI=y +CONFIG_PCNET32=m +CONFIG_AMD8111_ETH=m +# CONFIG_AMD8111E_NAPI is not set +CONFIG_ADAPTEC_STARFIRE=m +# CONFIG_ADAPTEC_STARFIRE_NAPI is not set +CONFIG_B44=m +CONFIG_FORCEDETH=m +# CONFIG_DGRS is not set +CONFIG_EEPRO100=m +CONFIG_E100=m +CONFIG_FEALNX=m +CONFIG_NATSEMI=m +CONFIG_NE2K_PCI=m +CONFIG_8139CP=m +CONFIG_8139TOO=m +CONFIG_8139TOO_PIO=y +CONFIG_8139TOO_TUNE_TWISTER=y +CONFIG_8139TOO_8129=y +# CONFIG_8139_OLD_RX_RESET is not set +CONFIG_SIS900=m +CONFIG_EPIC100=m +CONFIG_SUNDANCE=m +# CONFIG_SUNDANCE_MMIO is not set +CONFIG_TLAN=m +CONFIG_VIA_RHINE=m +# CONFIG_VIA_RHINE_MMIO is not set + +# +# Ethernet (1000 Mbit) +# +# CONFIG_ACENIC is not set +CONFIG_DL2K=m +CONFIG_E1000=m +# CONFIG_E1000_NAPI is not set +CONFIG_NS83820=m +CONFIG_HAMACHI=m +CONFIG_YELLOWFIN=m +CONFIG_R8169=m +# CONFIG_R8169_NAPI is not set +# CONFIG_R8169_VLAN is not set +CONFIG_SK98LIN=m +CONFIG_VIA_VELOCITY=m +CONFIG_TIGON3=m +CONFIG_BNX2=m + +# +# Ethernet (10000 Mbit) +# +CONFIG_IXGB=m +# CONFIG_IXGB_NAPI is not set +CONFIG_S2IO=m +# CONFIG_S2IO_NAPI is not set +# CONFIG_2BUFF_MODE is not set + +# +# Token Ring devices +# +CONFIG_TR=y +CONFIG_IBMOL=m +CONFIG_IBMLS=m +CONFIG_3C359=m +CONFIG_TMS380TR=m +CONFIG_TMSPCI=m +CONFIG_ABYSS=m + +# +# Wireless LAN (non-hamradio) +# +CONFIG_NET_RADIO=y + +# +# Obsolete Wireless cards support (pre-802.11) +# +CONFIG_STRIP=m +CONFIG_PCMCIA_WAVELAN=m +CONFIG_PCMCIA_NETWAVE=m + +# +# Wireless 802.11 Frequency Hopping cards support +# +CONFIG_PCMCIA_RAYCS=m + +# +# Wireless 802.11b ISA/PCI cards support +# +CONFIG_HERMES=m +CONFIG_PLX_HERMES=m +CONFIG_TMD_HERMES=m +CONFIG_PCI_HERMES=m +CONFIG_ATMEL=m +CONFIG_PCI_ATMEL=m + +# +# Wireless 802.11b Pcmcia/Cardbus cards support +# +CONFIG_PCMCIA_HERMES=m +CONFIG_AIRO_CS=m +CONFIG_PCMCIA_ATMEL=m +CONFIG_PCMCIA_WL3501=m + +# +# Prism GT/Duette 802.11(a/b/g) PCI/Cardbus support +# +CONFIG_PRISM54=m +CONFIG_NET_WIRELESS=y + +# +# PCMCIA network device support +# +CONFIG_NET_PCMCIA=y +CONFIG_PCMCIA_3C589=m +CONFIG_PCMCIA_3C574=m +CONFIG_PCMCIA_FMVJ18X=m +CONFIG_PCMCIA_PCNET=m +CONFIG_PCMCIA_NMCLAN=m +CONFIG_PCMCIA_SMC91C92=m +CONFIG_PCMCIA_XIRC2PS=m +CONFIG_PCMCIA_AXNET=m +CONFIG_ARCNET_COM20020_CS=m +CONFIG_PCMCIA_IBMTR=m + +# +# Wan interfaces +# +CONFIG_WAN=y +CONFIG_DSCC4=m +CONFIG_DSCC4_PCISYNC=y +CONFIG_DSCC4_PCI_RST=y +CONFIG_LANMEDIA=m +CONFIG_SYNCLINK_SYNCPPP=m +CONFIG_HDLC=m +CONFIG_HDLC_RAW=y +CONFIG_HDLC_RAW_ETH=y +CONFIG_HDLC_CISCO=y +CONFIG_HDLC_FR=y +CONFIG_HDLC_PPP=y +CONFIG_HDLC_X25=y +CONFIG_PCI200SYN=m +CONFIG_WANXL=m +CONFIG_PC300=m +CONFIG_PC300_MLPPP=y +CONFIG_FARSYNC=m +CONFIG_DLCI=m +CONFIG_DLCI_COUNT=24 +CONFIG_DLCI_MAX=8 +CONFIG_WAN_ROUTER_DRIVERS=y +# CONFIG_VENDOR_SANGOMA is not set +CONFIG_CYCLADES_SYNC=m +CONFIG_CYCLOMX_X25=y +CONFIG_LAPBETHER=m +CONFIG_X25_ASY=m +CONFIG_SBNI=m +# CONFIG_SBNI_MULTILINE is not set + +# +# ATM drivers +# +CONFIG_ATM_TCP=m +CONFIG_ATM_LANAI=m +CONFIG_ATM_ENI=m +# CONFIG_ATM_ENI_DEBUG is not set +# CONFIG_ATM_ENI_TUNE_BURST is not set +CONFIG_ATM_FIRESTREAM=m +CONFIG_ATM_ZATM=m +# CONFIG_ATM_ZATM_DEBUG is not set +CONFIG_ATM_NICSTAR=m +# CONFIG_ATM_NICSTAR_USE_SUNI is not set +# CONFIG_ATM_NICSTAR_USE_IDT77105 is not set +CONFIG_ATM_IDT77252=m +# CONFIG_ATM_IDT77252_DEBUG is not set +# CONFIG_ATM_IDT77252_RCV_ALL is not set +CONFIG_ATM_IDT77252_USE_SUNI=y +CONFIG_ATM_AMBASSADOR=m +# CONFIG_ATM_AMBASSADOR_DEBUG is not set +CONFIG_ATM_HORIZON=m +# CONFIG_ATM_HORIZON_DEBUG is not set +CONFIG_ATM_IA=m +# CONFIG_ATM_IA_DEBUG is not set +CONFIG_ATM_FORE200E_MAYBE=m +CONFIG_ATM_FORE200E_PCA=y +CONFIG_ATM_FORE200E_PCA_DEFAULT_FW=y +# CONFIG_ATM_FORE200E_USE_TASKLET is not set +CONFIG_ATM_FORE200E_TX_RETRY=16 +CONFIG_ATM_FORE200E_DEBUG=0 +CONFIG_ATM_FORE200E=m +CONFIG_ATM_HE=m +CONFIG_ATM_HE_USE_SUNI=y +CONFIG_FDDI=y +CONFIG_DEFXX=m +CONFIG_SKFP=m +CONFIG_HIPPI=y +CONFIG_ROADRUNNER=m +# CONFIG_ROADRUNNER_LARGE_RINGS is not set +CONFIG_PLIP=m +CONFIG_PPP=m +CONFIG_PPP_MULTILINK=y +CONFIG_PPP_FILTER=y +CONFIG_PPP_ASYNC=m +CONFIG_PPP_SYNC_TTY=m +CONFIG_PPP_DEFLATE=m +CONFIG_PPP_BSDCOMP=m +CONFIG_PPPOE=m +CONFIG_PPPOATM=m +CONFIG_SLIP=m +CONFIG_SLIP_COMPRESSED=y +CONFIG_SLIP_SMART=y +CONFIG_SLIP_MODE_SLIP6=y +CONFIG_NET_FC=y +CONFIG_SHAPER=m +CONFIG_NETCONSOLE=m + +# +# ISDN subsystem +# +CONFIG_ISDN=m + +# +# Old ISDN4Linux +# +CONFIG_ISDN_I4L=m +CONFIG_ISDN_PPP=y +CONFIG_ISDN_PPP_VJ=y +CONFIG_ISDN_MPP=y +CONFIG_IPPP_FILTER=y +CONFIG_ISDN_PPP_BSDCOMP=m +CONFIG_ISDN_AUDIO=y +CONFIG_ISDN_TTY_FAX=y +CONFIG_ISDN_X25=y + +# +# ISDN feature submodules +# +# CONFIG_ISDN_DRV_LOOP is not set +# CONFIG_ISDN_DIVERSION is not set + +# +# ISDN4Linux hardware drivers +# + +# +# Passive cards +# +CONFIG_ISDN_DRV_HISAX=m + +# +# D-channel protocol features +# +CONFIG_HISAX_EURO=y +CONFIG_DE_AOC=y +# CONFIG_HISAX_NO_SENDCOMPLETE is not set +# CONFIG_HISAX_NO_LLC is not set +# CONFIG_HISAX_NO_KEYPAD is not set +CONFIG_HISAX_1TR6=y +CONFIG_HISAX_NI1=y +CONFIG_HISAX_MAX_CARDS=8 + +# +# HiSax supported cards +# +CONFIG_HISAX_16_3=y +CONFIG_HISAX_TELESPCI=y +CONFIG_HISAX_S0BOX=y +CONFIG_HISAX_FRITZPCI=y +CONFIG_HISAX_AVM_A1_PCMCIA=y +CONFIG_HISAX_ELSA=y +CONFIG_HISAX_DIEHLDIVA=y +CONFIG_HISAX_SEDLBAUER=y +CONFIG_HISAX_NETJET=y +CONFIG_HISAX_NETJET_U=y +CONFIG_HISAX_NICCY=y +CONFIG_HISAX_BKM_A4T=y +CONFIG_HISAX_SCT_QUADRO=y +CONFIG_HISAX_GAZEL=y +CONFIG_HISAX_HFC_PCI=y +CONFIG_HISAX_W6692=y +CONFIG_HISAX_HFC_SX=y +CONFIG_HISAX_ENTERNOW_PCI=y +# CONFIG_HISAX_DEBUG is not set + +# +# HiSax PCMCIA card service modules +# +CONFIG_HISAX_SEDLBAUER_CS=m +CONFIG_HISAX_ELSA_CS=m +CONFIG_HISAX_AVM_A1_CS=m +CONFIG_HISAX_TELES_CS=m + +# +# HiSax sub driver modules +# +CONFIG_HISAX_ST5481=m +CONFIG_HISAX_HFCUSB=m +CONFIG_HISAX_HFC4S8S=m +CONFIG_HISAX_FRITZ_PCIPNP=m +CONFIG_HISAX_HDLC=y + +# +# Active cards +# +# CONFIG_HYSDN is not set + +# +# CAPI subsystem +# +CONFIG_ISDN_CAPI=m +CONFIG_ISDN_DRV_AVMB1_VERBOSE_REASON=y +CONFIG_ISDN_CAPI_MIDDLEWARE=y +CONFIG_ISDN_CAPI_CAPI20=m +CONFIG_ISDN_CAPI_CAPIFS_BOOL=y +CONFIG_ISDN_CAPI_CAPIFS=m +CONFIG_ISDN_CAPI_CAPIDRV=m + +# +# CAPI hardware drivers +# + +# +# Active AVM cards +# +CONFIG_CAPI_AVM=y +CONFIG_ISDN_DRV_AVMB1_B1PCI=m +CONFIG_ISDN_DRV_AVMB1_B1PCIV4=y +CONFIG_ISDN_DRV_AVMB1_B1PCMCIA=m +CONFIG_ISDN_DRV_AVMB1_AVM_CS=m +CONFIG_ISDN_DRV_AVMB1_T1PCI=m +CONFIG_ISDN_DRV_AVMB1_C4=m + +# +# Active Eicon DIVA Server cards +# +CONFIG_CAPI_EICON=y +CONFIG_ISDN_DIVAS=m +CONFIG_ISDN_DIVAS_BRIPCI=y +CONFIG_ISDN_DIVAS_PRIPCI=y +CONFIG_ISDN_DIVAS_DIVACAPI=m +CONFIG_ISDN_DIVAS_USERIDI=m +CONFIG_ISDN_DIVAS_MAINT=m + +# +# Telephony Support +# +CONFIG_PHONE=m +CONFIG_PHONE_IXJ=m +CONFIG_PHONE_IXJ_PCMCIA=m + +# +# Input device support +# +CONFIG_INPUT=y + +# +# Userland interfaces +# +CONFIG_INPUT_MOUSEDEV=y +CONFIG_INPUT_MOUSEDEV_PSAUX=y +CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024 +CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 +CONFIG_INPUT_JOYDEV=m +CONFIG_INPUT_TSDEV=m +CONFIG_INPUT_TSDEV_SCREEN_X=240 +CONFIG_INPUT_TSDEV_SCREEN_Y=320 +CONFIG_INPUT_EVDEV=m +CONFIG_INPUT_EVBUG=m + +# +# Input Device Drivers +# +CONFIG_INPUT_KEYBOARD=y +CONFIG_KEYBOARD_ATKBD=y +CONFIG_KEYBOARD_SUNKBD=m +CONFIG_KEYBOARD_LKKBD=m +CONFIG_KEYBOARD_XTKBD=m +CONFIG_KEYBOARD_NEWTON=m +CONFIG_INPUT_MOUSE=y +CONFIG_MOUSE_PS2=y +CONFIG_MOUSE_SERIAL=m +CONFIG_MOUSE_VSXXXAA=m +CONFIG_INPUT_JOYSTICK=y +CONFIG_JOYSTICK_ANALOG=m +CONFIG_JOYSTICK_A3D=m +CONFIG_JOYSTICK_ADI=m +CONFIG_JOYSTICK_COBRA=m +CONFIG_JOYSTICK_GF2K=m +CONFIG_JOYSTICK_GRIP=m +CONFIG_JOYSTICK_GRIP_MP=m +CONFIG_JOYSTICK_GUILLEMOT=m +CONFIG_JOYSTICK_INTERACT=m +CONFIG_JOYSTICK_SIDEWINDER=m +CONFIG_JOYSTICK_TMDC=m +CONFIG_JOYSTICK_IFORCE=m +CONFIG_JOYSTICK_IFORCE_USB=y +CONFIG_JOYSTICK_IFORCE_232=y +CONFIG_JOYSTICK_WARRIOR=m +CONFIG_JOYSTICK_MAGELLAN=m +CONFIG_JOYSTICK_SPACEORB=m +CONFIG_JOYSTICK_SPACEBALL=m +CONFIG_JOYSTICK_STINGER=m +CONFIG_JOYSTICK_TWIDJOY=m +CONFIG_JOYSTICK_DB9=m +CONFIG_JOYSTICK_GAMECON=m +CONFIG_JOYSTICK_TURBOGRAFX=m +CONFIG_JOYSTICK_JOYDUMP=m +CONFIG_INPUT_TOUCHSCREEN=y +CONFIG_TOUCHSCREEN_GUNZE=m +CONFIG_TOUCHSCREEN_ELO=m +CONFIG_TOUCHSCREEN_MTOUCH=m +CONFIG_TOUCHSCREEN_MK712=m +CONFIG_INPUT_MISC=y +CONFIG_INPUT_PCSPKR=m +CONFIG_INPUT_UINPUT=m + +# +# Hardware I/O ports +# +CONFIG_SERIO=y +CONFIG_SERIO_I8042=y +CONFIG_SERIO_SERPORT=m +CONFIG_SERIO_CT82C710=m +CONFIG_SERIO_PARKBD=m +CONFIG_SERIO_PCIPS2=m +CONFIG_SERIO_LIBPS2=y +CONFIG_SERIO_RAW=m +CONFIG_GAMEPORT=m +CONFIG_GAMEPORT_NS558=m +CONFIG_GAMEPORT_L4=m +CONFIG_GAMEPORT_EMU10K1=m +CONFIG_GAMEPORT_VORTEX=m +CONFIG_GAMEPORT_FM801=m +# CONFIG_GAMEPORT_CS461X is not set + +# +# Character devices +# +CONFIG_VT=y +CONFIG_VT_CONSOLE=y +CONFIG_HW_CONSOLE=y +# CONFIG_SERIAL_NONSTANDARD is not set + +# +# Serial drivers +# +CONFIG_SERIAL_8250=m +# CONFIG_SERIAL_8250_CS is not set +# CONFIG_SERIAL_8250_ACPI is not set +CONFIG_SERIAL_8250_NR_UARTS=4 +# CONFIG_SERIAL_8250_EXTENDED is not set + +# +# Non-8250 serial port support +# +CONFIG_SERIAL_CORE=m +CONFIG_SERIAL_JSM=m +CONFIG_UNIX98_PTYS=y +CONFIG_LEGACY_PTYS=y +CONFIG_LEGACY_PTY_COUNT=256 +CONFIG_PRINTER=m +# CONFIG_LP_CONSOLE is not set +CONFIG_PPDEV=m +CONFIG_TIPAR=m + +# +# IPMI +# +CONFIG_IPMI_HANDLER=m +# CONFIG_IPMI_PANIC_EVENT is not set +CONFIG_IPMI_DEVICE_INTERFACE=m +CONFIG_IPMI_SI=m +CONFIG_IPMI_WATCHDOG=m +CONFIG_IPMI_POWEROFF=m + +# +# Watchdog Cards +# +CONFIG_WATCHDOG=y +# CONFIG_WATCHDOG_NOWAYOUT is not set + +# +# Watchdog Device Drivers +# +CONFIG_SOFT_WATCHDOG=m +CONFIG_ACQUIRE_WDT=m +CONFIG_ADVANTECH_WDT=m +CONFIG_ALIM1535_WDT=m +CONFIG_ALIM7101_WDT=m +CONFIG_SC520_WDT=m +CONFIG_EUROTECH_WDT=m +CONFIG_IB700_WDT=m +CONFIG_WAFER_WDT=m +CONFIG_I8XX_TCO=m +CONFIG_SC1200_WDT=m +CONFIG_SCx200_WDT=m +CONFIG_60XX_WDT=m +CONFIG_CPU5_WDT=m +CONFIG_W83627HF_WDT=m +CONFIG_W83877F_WDT=m +CONFIG_MACHZ_WDT=m + +# +# PCI-based Watchdog Cards +# +CONFIG_PCIPCWATCHDOG=m +CONFIG_WDTPCI=m +CONFIG_WDT_501_PCI=y + +# +# USB-based Watchdog Cards +# +CONFIG_USBPCWATCHDOG=m +CONFIG_HW_RANDOM=m +CONFIG_NVRAM=m +CONFIG_RTC=m +CONFIG_GEN_RTC=m +CONFIG_GEN_RTC_X=y +CONFIG_DTLK=m +CONFIG_R3964=m +CONFIG_APPLICOM=m +CONFIG_SONYPI=m + +# +# Ftape, the floppy tape device driver +# +# CONFIG_FTAPE is not set +CONFIG_AGP=m +CONFIG_AGP_ALI=m +CONFIG_AGP_ATI=m +CONFIG_AGP_AMD=m +CONFIG_AGP_AMD64=m +CONFIG_AGP_INTEL=m +CONFIG_AGP_NVIDIA=m +CONFIG_AGP_SIS=m +CONFIG_AGP_SWORKS=m +CONFIG_AGP_VIA=m +CONFIG_AGP_EFFICEON=m +CONFIG_DRM=m +CONFIG_DRM_TDFX=m +# CONFIG_DRM_GAMMA is not set +CONFIG_DRM_R128=m +CONFIG_DRM_RADEON=m +CONFIG_DRM_I810=m +CONFIG_DRM_I830=m +CONFIG_DRM_I915=m +CONFIG_DRM_MGA=m +CONFIG_DRM_SIS=m + +# +# PCMCIA character devices +# +CONFIG_SYNCLINK_CS=m +CONFIG_MWAVE=m +CONFIG_SCx200_GPIO=m +CONFIG_RAW_DRIVER=m +# CONFIG_HPET is not set +CONFIG_MAX_RAW_DEVS=256 +CONFIG_HANGCHECK_TIMER=m + +# +# TPM devices +# +# CONFIG_TCG_TPM is not set + +# +# I2C support +# +CONFIG_I2C=m +CONFIG_I2C_CHARDEV=m + +# +# I2C Algorithms +# +CONFIG_I2C_ALGOBIT=m +CONFIG_I2C_ALGOPCF=m +CONFIG_I2C_ALGOPCA=m + +# +# I2C Hardware Bus support +# +CONFIG_I2C_ALI1535=m +CONFIG_I2C_ALI1563=m +CONFIG_I2C_ALI15X3=m +CONFIG_I2C_AMD756=m +CONFIG_I2C_AMD756_S4882=m +CONFIG_I2C_AMD8111=m +CONFIG_I2C_I801=m +CONFIG_I2C_I810=m +CONFIG_I2C_PIIX4=m +CONFIG_I2C_ISA=m +CONFIG_I2C_NFORCE2=m +CONFIG_I2C_PARPORT=m +CONFIG_I2C_PARPORT_LIGHT=m +CONFIG_I2C_PROSAVAGE=m +CONFIG_I2C_SAVAGE4=m +CONFIG_SCx200_I2C=m +CONFIG_SCx200_I2C_SCL=12 +CONFIG_SCx200_I2C_SDA=13 +CONFIG_SCx200_ACB=m +CONFIG_I2C_SIS5595=m +CONFIG_I2C_SIS630=m +CONFIG_I2C_SIS96X=m +CONFIG_I2C_STUB=m +CONFIG_I2C_VIA=m +CONFIG_I2C_VIAPRO=m +CONFIG_I2C_VOODOO3=m +CONFIG_I2C_PCA_ISA=m + +# +# Hardware Sensors Chip support +# +CONFIG_I2C_SENSOR=m +CONFIG_SENSORS_ADM1021=m +CONFIG_SENSORS_ADM1025=m +CONFIG_SENSORS_ADM1026=m +CONFIG_SENSORS_ADM1031=m +CONFIG_SENSORS_ASB100=m +CONFIG_SENSORS_DS1621=m +CONFIG_SENSORS_FSCHER=m +CONFIG_SENSORS_FSCPOS=m +CONFIG_SENSORS_GL518SM=m +CONFIG_SENSORS_GL520SM=m +CONFIG_SENSORS_IT87=m +CONFIG_SENSORS_LM63=m +CONFIG_SENSORS_LM75=m +CONFIG_SENSORS_LM77=m +CONFIG_SENSORS_LM78=m +CONFIG_SENSORS_LM80=m +CONFIG_SENSORS_LM83=m +CONFIG_SENSORS_LM85=m +CONFIG_SENSORS_LM87=m +CONFIG_SENSORS_LM90=m +CONFIG_SENSORS_LM92=m +CONFIG_SENSORS_MAX1619=m +CONFIG_SENSORS_PC87360=m +# CONFIG_SENSORS_SMSC47B397 is not set +CONFIG_SENSORS_SIS5595=m +CONFIG_SENSORS_SMSC47M1=m +CONFIG_SENSORS_VIA686A=m +CONFIG_SENSORS_W83781D=m +CONFIG_SENSORS_W83L785TS=m +CONFIG_SENSORS_W83627HF=m + +# +# Other I2C Chip support +# +CONFIG_SENSORS_DS1337=m +CONFIG_SENSORS_EEPROM=m +CONFIG_SENSORS_PCF8574=m +CONFIG_SENSORS_PCF8591=m +CONFIG_SENSORS_RTC8564=m +# CONFIG_I2C_DEBUG_CORE is not set +# CONFIG_I2C_DEBUG_ALGO is not set +# CONFIG_I2C_DEBUG_BUS is not set +# CONFIG_I2C_DEBUG_CHIP is not set + +# +# Dallas's 1-wire bus +# +CONFIG_W1=m +CONFIG_W1_MATROX=m +CONFIG_W1_DS9490=m +CONFIG_W1_DS9490_BRIDGE=m +CONFIG_W1_THERM=m +CONFIG_W1_SMEM=m + +# +# Misc devices +# +CONFIG_IBM_ASM=m + +# +# Multimedia devices +# +CONFIG_VIDEO_DEV=m + +# +# Video For Linux +# + +# +# Video Adapters +# +CONFIG_VIDEO_BT848=m +CONFIG_VIDEO_BWQCAM=m +CONFIG_VIDEO_CQCAM=m +CONFIG_VIDEO_W9966=m +CONFIG_VIDEO_CPIA=m +CONFIG_VIDEO_CPIA_PP=m +CONFIG_VIDEO_CPIA_USB=m +CONFIG_VIDEO_SAA5246A=m +CONFIG_VIDEO_SAA5249=m +CONFIG_TUNER_3036=m +CONFIG_VIDEO_STRADIS=m +CONFIG_VIDEO_ZORAN=m +CONFIG_VIDEO_ZORAN_BUZ=m +CONFIG_VIDEO_ZORAN_DC10=m +CONFIG_VIDEO_ZORAN_DC30=m +CONFIG_VIDEO_ZORAN_LML33=m +CONFIG_VIDEO_ZORAN_LML33R10=m +# CONFIG_VIDEO_ZR36120 is not set +CONFIG_VIDEO_MEYE=m +# CONFIG_VIDEO_SAA7134 is not set +CONFIG_VIDEO_MXB=m +CONFIG_VIDEO_DPC=m +CONFIG_VIDEO_HEXIUM_ORION=m +CONFIG_VIDEO_HEXIUM_GEMINI=m +CONFIG_VIDEO_CX88=m +# CONFIG_VIDEO_CX88_DVB is not set +CONFIG_VIDEO_OVCAMCHIP=m + +# +# Radio Adapters +# +CONFIG_RADIO_GEMTEK_PCI=m +CONFIG_RADIO_MAXIRADIO=m +CONFIG_RADIO_MAESTRO=m + +# +# Digital Video Broadcasting Devices +# +CONFIG_DVB=y +CONFIG_DVB_CORE=m + +# +# Supported SAA7146 based PCI Adapters +# +CONFIG_DVB_AV7110=m +# CONFIG_DVB_AV7110_OSD is not set +CONFIG_DVB_BUDGET=m +CONFIG_DVB_BUDGET_CI=m +CONFIG_DVB_BUDGET_AV=m +CONFIG_DVB_BUDGET_PATCH=m + +# +# Supported USB Adapters +# +CONFIG_DVB_TTUSB_BUDGET=m +CONFIG_DVB_TTUSB_DEC=m +CONFIG_DVB_DIBUSB=m +CONFIG_DVB_DIBUSB_MISDESIGNED_DEVICES=y +# CONFIG_DVB_DIBCOM_DEBUG is not set +CONFIG_DVB_CINERGYT2=m +# CONFIG_DVB_CINERGYT2_TUNING is not set + +# +# Supported FlexCopII (B2C2) Adapters +# +CONFIG_DVB_B2C2_FLEXCOP=m +CONFIG_DVB_B2C2_FLEXCOP_PCI=m +CONFIG_DVB_B2C2_FLEXCOP_USB=m +# CONFIG_DVB_B2C2_FLEXCOP_DEBUG is not set +CONFIG_DVB_B2C2_SKYSTAR=m + +# +# Supported BT878 Adapters +# +CONFIG_DVB_BT8XX=m + +# +# Supported DVB Frontends +# + +# +# Customise DVB Frontends +# + +# +# DVB-S (satellite) frontends +# +CONFIG_DVB_STV0299=m +CONFIG_DVB_CX24110=m +CONFIG_DVB_TDA8083=m +CONFIG_DVB_TDA80XX=m +CONFIG_DVB_MT312=m +CONFIG_DVB_VES1X93=m + +# +# DVB-T (terrestrial) frontends +# +CONFIG_DVB_SP8870=m +CONFIG_DVB_SP887X=m +CONFIG_DVB_CX22700=m +CONFIG_DVB_CX22702=m +CONFIG_DVB_L64781=m +CONFIG_DVB_TDA1004X=m +CONFIG_DVB_NXT6000=m +CONFIG_DVB_MT352=m +CONFIG_DVB_DIB3000MB=m +CONFIG_DVB_DIB3000MC=m + +# +# DVB-C (cable) frontends +# +CONFIG_DVB_ATMEL_AT76C651=m +CONFIG_DVB_VES1820=m +CONFIG_DVB_TDA10021=m +CONFIG_DVB_STV0297=m + +# +# ATSC (North American/Korean Terresterial DTV) frontends +# +CONFIG_DVB_NXT2002=m +CONFIG_DVB_OR51211=m +CONFIG_DVB_OR51132=m +CONFIG_VIDEO_SAA7146=m +CONFIG_VIDEO_SAA7146_VV=m +CONFIG_VIDEO_VIDEOBUF=m +CONFIG_VIDEO_TUNER=m +CONFIG_VIDEO_BUF=m +CONFIG_VIDEO_BTCX=m +CONFIG_VIDEO_IR=m +CONFIG_VIDEO_TVEEPROM=m + +# +# Graphics support +# +CONFIG_FB=y +CONFIG_FB_CFB_FILLRECT=m +CONFIG_FB_CFB_COPYAREA=m +CONFIG_FB_CFB_IMAGEBLIT=m +CONFIG_FB_SOFT_CURSOR=m +# CONFIG_FB_MACMODES is not set +CONFIG_FB_MODE_HELPERS=y +CONFIG_FB_TILEBLITTING=y +CONFIG_FB_CIRRUS=m +CONFIG_FB_PM2=m +CONFIG_FB_PM2_FIFO_DISCONNECT=y +CONFIG_FB_CYBER2000=m +# CONFIG_FB_ASILIANT is not set +# CONFIG_FB_IMSTT is not set +CONFIG_FB_VGA16=m +# CONFIG_FB_VESA is not set +CONFIG_VIDEO_SELECT=y +CONFIG_FB_HGA=m +# CONFIG_FB_HGA_ACCEL is not set +CONFIG_FB_NVIDIA=m +CONFIG_FB_NVIDIA_I2C=y +CONFIG_FB_RIVA=m +CONFIG_FB_RIVA_I2C=y +CONFIG_FB_RIVA_DEBUG=y +CONFIG_FB_I810=m +# CONFIG_FB_I810_GTF is not set +CONFIG_FB_INTEL=m +# CONFIG_FB_INTEL_DEBUG is not set +CONFIG_FB_MATROX=m +CONFIG_FB_MATROX_MILLENIUM=y +CONFIG_FB_MATROX_MYSTIQUE=y +# CONFIG_FB_MATROX_G is not set +CONFIG_FB_MATROX_I2C=m +CONFIG_FB_MATROX_MULTIHEAD=y +CONFIG_FB_RADEON_OLD=m +CONFIG_FB_RADEON=m +CONFIG_FB_RADEON_I2C=y +# CONFIG_FB_RADEON_DEBUG is not set +CONFIG_FB_ATY128=m +CONFIG_FB_ATY=m +CONFIG_FB_ATY_CT=y +CONFIG_FB_ATY_GENERIC_LCD=y +CONFIG_FB_ATY_XL_INIT=y +CONFIG_FB_ATY_GX=y +CONFIG_FB_SAVAGE=m +CONFIG_FB_SAVAGE_I2C=y +CONFIG_FB_SAVAGE_ACCEL=y +CONFIG_FB_SIS=m +CONFIG_FB_SIS_300=y +CONFIG_FB_SIS_315=y +CONFIG_FB_NEOMAGIC=m +CONFIG_FB_KYRO=m +CONFIG_FB_3DFX=m +# CONFIG_FB_3DFX_ACCEL is not set +CONFIG_FB_VOODOO1=m +CONFIG_FB_TRIDENT=m +# CONFIG_FB_TRIDENT_ACCEL is not set +# CONFIG_FB_PM3 is not set +CONFIG_FB_GEODE=y +CONFIG_FB_GEODE_GX1=m +CONFIG_FB_S1D13XXX=m +CONFIG_FB_VIRTUAL=m + +# +# Console display driver support +# +CONFIG_VGA_CONSOLE=y +CONFIG_DUMMY_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE=m +# CONFIG_FONTS is not set +CONFIG_FONT_8x8=y +CONFIG_FONT_8x16=y + +# +# Logo configuration +# +# CONFIG_LOGO is not set +# CONFIG_BACKLIGHT_LCD_SUPPORT is not set + +# +# Sound +# +CONFIG_SOUND=m + +# +# Advanced Linux Sound Architecture +# +CONFIG_SND=m +CONFIG_SND_TIMER=m +CONFIG_SND_PCM=m +CONFIG_SND_HWDEP=m +CONFIG_SND_RAWMIDI=m +CONFIG_SND_SEQUENCER=m +CONFIG_SND_SEQ_DUMMY=m +CONFIG_SND_OSSEMUL=y +CONFIG_SND_MIXER_OSS=m +CONFIG_SND_PCM_OSS=m +CONFIG_SND_SEQUENCER_OSS=y +CONFIG_SND_RTCTIMER=m +# CONFIG_SND_VERBOSE_PRINTK is not set +# CONFIG_SND_DEBUG is not set + +# +# Generic devices +# +CONFIG_SND_MPU401_UART=m +CONFIG_SND_OPL3_LIB=m +CONFIG_SND_VX_LIB=m +CONFIG_SND_DUMMY=m +CONFIG_SND_VIRMIDI=m +CONFIG_SND_MTPAV=m +CONFIG_SND_SERIAL_U16550=m +CONFIG_SND_MPU401=m + +# +# PCI devices +# +CONFIG_SND_AC97_CODEC=m +CONFIG_SND_ALI5451=m +CONFIG_SND_ATIIXP=m +CONFIG_SND_ATIIXP_MODEM=m +CONFIG_SND_AU8810=m +CONFIG_SND_AU8820=m +CONFIG_SND_AU8830=m +CONFIG_SND_AZT3328=m +CONFIG_SND_BT87X=m +# CONFIG_SND_BT87X_OVERCLOCK is not set +CONFIG_SND_CS46XX=m +CONFIG_SND_CS46XX_NEW_DSP=y +CONFIG_SND_CS4281=m +CONFIG_SND_EMU10K1=m +# CONFIG_SND_EMU10K1X is not set +# CONFIG_SND_CA0106 is not set +CONFIG_SND_KORG1212=m +CONFIG_SND_MIXART=m +CONFIG_SND_NM256=m +CONFIG_SND_RME32=m +CONFIG_SND_RME96=m +CONFIG_SND_RME9652=m +CONFIG_SND_HDSP=m +CONFIG_SND_TRIDENT=m +CONFIG_SND_YMFPCI=m +CONFIG_SND_ALS4000=m +CONFIG_SND_CMIPCI=m +CONFIG_SND_ENS1370=m +CONFIG_SND_ENS1371=m +CONFIG_SND_ES1938=m +CONFIG_SND_ES1968=m +CONFIG_SND_MAESTRO3=m +CONFIG_SND_FM801=m +CONFIG_SND_FM801_TEA575X=m +CONFIG_SND_ICE1712=m +CONFIG_SND_ICE1724=m +CONFIG_SND_INTEL8X0=m +CONFIG_SND_INTEL8X0M=m +CONFIG_SND_SONICVIBES=m +CONFIG_SND_VIA82XX=m +# CONFIG_SND_VIA82XX_MODEM is not set +CONFIG_SND_VX222=m +CONFIG_SND_HDA_INTEL=m + +# +# USB devices +# +CONFIG_SND_USB_AUDIO=m +CONFIG_SND_USB_USX2Y=m + +# +# PCMCIA devices +# + +# +# Open Sound System +# +CONFIG_SOUND_PRIME=m +CONFIG_SOUND_BT878=m +CONFIG_SOUND_CMPCI=m +# CONFIG_SOUND_CMPCI_FM is not set +# CONFIG_SOUND_CMPCI_MIDI is not set +CONFIG_SOUND_CMPCI_JOYSTICK=y +CONFIG_SOUND_EMU10K1=m +CONFIG_MIDI_EMU10K1=y +CONFIG_SOUND_FUSION=m +CONFIG_SOUND_CS4281=m +CONFIG_SOUND_ES1370=m +CONFIG_SOUND_ES1371=m +CONFIG_SOUND_ESSSOLO1=m +CONFIG_SOUND_MAESTRO=m +CONFIG_SOUND_MAESTRO3=m +CONFIG_SOUND_ICH=m +CONFIG_SOUND_SONICVIBES=m +CONFIG_SOUND_TRIDENT=m +# CONFIG_SOUND_MSNDCLAS is not set +# CONFIG_SOUND_MSNDPIN is not set +CONFIG_SOUND_VIA82CXXX=m +CONFIG_MIDI_VIA82CXXX=y +CONFIG_SOUND_OSS=m +# CONFIG_SOUND_TRACEINIT is not set +# CONFIG_SOUND_DMAP is not set +# CONFIG_SOUND_AD1816 is not set +CONFIG_SOUND_AD1889=m +CONFIG_SOUND_SGALAXY=m +CONFIG_SOUND_ADLIB=m +CONFIG_SOUND_ACI_MIXER=m +CONFIG_SOUND_CS4232=m +CONFIG_SOUND_SSCAPE=m +CONFIG_SOUND_GUS=m +CONFIG_SOUND_GUS16=y +CONFIG_SOUND_GUSMAX=y +CONFIG_SOUND_VMIDI=m +CONFIG_SOUND_TRIX=m +CONFIG_SOUND_MSS=m +CONFIG_SOUND_MPU401=m +CONFIG_SOUND_NM256=m +CONFIG_SOUND_MAD16=m +CONFIG_MAD16_OLDCARD=y +CONFIG_SOUND_PAS=m +CONFIG_SOUND_PSS=m +CONFIG_PSS_MIXER=y +CONFIG_SOUND_SB=m +# CONFIG_SOUND_AWE32_SYNTH is not set +CONFIG_SOUND_WAVEFRONT=m +CONFIG_SOUND_MAUI=m +CONFIG_SOUND_YM3812=m +CONFIG_SOUND_OPL3SA1=m +CONFIG_SOUND_OPL3SA2=m +CONFIG_SOUND_YMFPCI=m +# CONFIG_SOUND_YMFPCI_LEGACY is not set +CONFIG_SOUND_UART6850=m +CONFIG_SOUND_AEDSP16=m +CONFIG_SC6600=y +CONFIG_SC6600_JOY=y +CONFIG_SC6600_CDROM=4 +CONFIG_SC6600_CDROMBASE=0x0 +# CONFIG_AEDSP16_MSS is not set +# CONFIG_AEDSP16_SBPRO is not set +# CONFIG_AEDSP16_MPU401 is not set +CONFIG_SOUND_TVMIXER=m +CONFIG_SOUND_KAHLUA=m +CONFIG_SOUND_ALI5455=m +CONFIG_SOUND_FORTE=m +CONFIG_SOUND_RME96XX=m +CONFIG_SOUND_AD1980=m + +# +# USB support +# +CONFIG_USB_ARCH_HAS_HCD=y +CONFIG_USB_ARCH_HAS_OHCI=y +CONFIG_USB=y +# CONFIG_USB_DEBUG is not set + +# +# Miscellaneous USB options +# +CONFIG_USB_DEVICEFS=y +CONFIG_USB_BANDWIDTH=y +# CONFIG_USB_DYNAMIC_MINORS is not set +# CONFIG_USB_OTG is not set + +# +# USB Host Controller Drivers +# +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_EHCI_SPLIT_ISO=y +CONFIG_USB_EHCI_ROOT_HUB_TT=y +CONFIG_USB_OHCI_HCD=m +# CONFIG_USB_OHCI_BIG_ENDIAN is not set +CONFIG_USB_OHCI_LITTLE_ENDIAN=y +CONFIG_USB_UHCI_HCD=m +CONFIG_USB_SL811_HCD=m +CONFIG_USB_SL811_CS=m + +# +# USB Device Class drivers +# +CONFIG_USB_AUDIO=m + +# +# USB Bluetooth TTY can only be used with disabled Bluetooth subsystem +# +CONFIG_USB_MIDI=m +CONFIG_USB_ACM=m +CONFIG_USB_PRINTER=m + +# +# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed; see USB_STORAGE Help for more information +# +CONFIG_USB_STORAGE=m +# CONFIG_USB_STORAGE_DEBUG is not set +CONFIG_USB_STORAGE_DATAFAB=y +CONFIG_USB_STORAGE_FREECOM=y +CONFIG_USB_STORAGE_ISD200=y +CONFIG_USB_STORAGE_DPCM=y +CONFIG_USB_STORAGE_USBAT=y +CONFIG_USB_STORAGE_SDDR09=y +CONFIG_USB_STORAGE_SDDR55=y +CONFIG_USB_STORAGE_JUMPSHOT=y + +# +# USB Input Devices +# +CONFIG_USB_HID=m +CONFIG_USB_HIDINPUT=y +# CONFIG_HID_FF is not set +CONFIG_USB_HIDDEV=y + +# +# USB HID Boot Protocol drivers +# +CONFIG_USB_KBD=m +CONFIG_USB_MOUSE=m +CONFIG_USB_AIPTEK=m +CONFIG_USB_WACOM=m +CONFIG_USB_KBTAB=m +CONFIG_USB_POWERMATE=m +CONFIG_USB_MTOUCH=m +CONFIG_USB_EGALAX=m +CONFIG_USB_XPAD=m +CONFIG_USB_ATI_REMOTE=m + +# +# USB Imaging devices +# +CONFIG_USB_MDC800=m +CONFIG_USB_MICROTEK=m + +# +# USB Multimedia devices +# +# CONFIG_USB_DABUSB is not set +CONFIG_USB_VICAM=m +CONFIG_USB_DSBR=m +CONFIG_USB_IBMCAM=m +CONFIG_USB_KONICAWC=m +CONFIG_USB_OV511=m +CONFIG_USB_SE401=m +CONFIG_USB_SN9C102=m +CONFIG_USB_STV680=m +CONFIG_USB_W9968CF=m +CONFIG_USB_PWC=m + +# +# USB Network Adapters +# +CONFIG_USB_CATC=m +CONFIG_USB_KAWETH=m +CONFIG_USB_PEGASUS=m +CONFIG_USB_RTL8150=m +CONFIG_USB_USBNET=m + +# +# USB Host-to-Host Cables +# +CONFIG_USB_ALI_M5632=y +CONFIG_USB_AN2720=y +CONFIG_USB_BELKIN=y +CONFIG_USB_GENESYS=y +CONFIG_USB_NET1080=y +CONFIG_USB_PL2301=y +CONFIG_USB_KC2190=y + +# +# Intelligent USB Devices/Gadgets +# +CONFIG_USB_ARMLINUX=y +CONFIG_USB_EPSON2888=y +CONFIG_USB_ZAURUS=y +CONFIG_USB_CDCETHER=y + +# +# USB Network Adapters +# +CONFIG_USB_AX8817X=y +CONFIG_USB_ZD1201=m +CONFIG_USB_MON=m + +# +# USB port drivers +# +CONFIG_USB_USS720=m + +# +# USB Serial Converter support +# +CONFIG_USB_SERIAL=m +CONFIG_USB_SERIAL_GENERIC=y +CONFIG_USB_SERIAL_AIRPRIME=m +CONFIG_USB_SERIAL_BELKIN=m +CONFIG_USB_SERIAL_WHITEHEAT=m +CONFIG_USB_SERIAL_DIGI_ACCELEPORT=m +CONFIG_USB_SERIAL_CP2101=m +CONFIG_USB_SERIAL_CYPRESS_M8=m +CONFIG_USB_SERIAL_EMPEG=m +CONFIG_USB_SERIAL_FTDI_SIO=m +CONFIG_USB_SERIAL_VISOR=m +CONFIG_USB_SERIAL_IPAQ=m +CONFIG_USB_SERIAL_IR=m +CONFIG_USB_SERIAL_EDGEPORT=m +CONFIG_USB_SERIAL_EDGEPORT_TI=m +# CONFIG_USB_SERIAL_GARMIN is not set +CONFIG_USB_SERIAL_IPW=m +CONFIG_USB_SERIAL_KEYSPAN_PDA=m +CONFIG_USB_SERIAL_KEYSPAN=m +# CONFIG_USB_SERIAL_KEYSPAN_MPR is not set +# CONFIG_USB_SERIAL_KEYSPAN_USA28 is not set +# CONFIG_USB_SERIAL_KEYSPAN_USA28X is not set +# CONFIG_USB_SERIAL_KEYSPAN_USA28XA is not set +# CONFIG_USB_SERIAL_KEYSPAN_USA28XB is not set +# CONFIG_USB_SERIAL_KEYSPAN_USA19 is not set +# CONFIG_USB_SERIAL_KEYSPAN_USA18X is not set +# CONFIG_USB_SERIAL_KEYSPAN_USA19W is not set +# CONFIG_USB_SERIAL_KEYSPAN_USA19QW is not set +# CONFIG_USB_SERIAL_KEYSPAN_USA19QI is not set +# CONFIG_USB_SERIAL_KEYSPAN_USA49W is not set +# CONFIG_USB_SERIAL_KEYSPAN_USA49WLC is not set +CONFIG_USB_SERIAL_KLSI=m +CONFIG_USB_SERIAL_KOBIL_SCT=m +CONFIG_USB_SERIAL_MCT_U232=m +CONFIG_USB_SERIAL_PL2303=m +CONFIG_USB_SERIAL_HP4X=m +CONFIG_USB_SERIAL_SAFE=m +# CONFIG_USB_SERIAL_SAFE_PADDED is not set +# CONFIG_USB_SERIAL_TI is not set +CONFIG_USB_SERIAL_CYBERJACK=m +CONFIG_USB_SERIAL_XIRCOM=m +CONFIG_USB_SERIAL_OPTION=m +CONFIG_USB_SERIAL_OMNINET=m +CONFIG_USB_EZUSB=y + +# +# USB Miscellaneous drivers +# +# CONFIG_USB_EMI62 is not set +# CONFIG_USB_EMI26 is not set +CONFIG_USB_AUERSWALD=m +CONFIG_USB_RIO500=m +CONFIG_USB_LEGOTOWER=m +CONFIG_USB_LCD=m +CONFIG_USB_LED=m +CONFIG_USB_CYTHERM=m +CONFIG_USB_PHIDGETKIT=m +CONFIG_USB_PHIDGETSERVO=m +# CONFIG_USB_IDMOUSE is not set +CONFIG_USB_SISUSBVGA=m +CONFIG_USB_TEST=m + +# +# USB ATM/DSL drivers +# +CONFIG_USB_ATM=m +CONFIG_USB_SPEEDTOUCH=m + +# +# USB Gadget Support +# +CONFIG_USB_GADGET=m +# CONFIG_USB_GADGET_DEBUG_FILES is not set +CONFIG_USB_GADGET_NET2280=y +CONFIG_USB_NET2280=m +# CONFIG_USB_GADGET_PXA2XX is not set +# CONFIG_USB_GADGET_GOKU is not set +# CONFIG_USB_GADGET_LH7A40X is not set +# CONFIG_USB_GADGET_OMAP is not set +# CONFIG_USB_GADGET_DUMMY_HCD is not set +CONFIG_USB_GADGET_DUALSPEED=y +CONFIG_USB_ZERO=m +CONFIG_USB_ETH=m +CONFIG_USB_ETH_RNDIS=y +CONFIG_USB_GADGETFS=m +CONFIG_USB_FILE_STORAGE=m +# CONFIG_USB_FILE_STORAGE_TEST is not set +CONFIG_USB_G_SERIAL=m + +# +# MMC/SD Card support +# +# CONFIG_MMC is not set + +# +# InfiniBand support +# +# CONFIG_INFINIBAND is not set + +# +# File systems +# +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_EXT2_FS_POSIX_ACL=y +CONFIG_EXT2_FS_SECURITY=y +CONFIG_EXT3_FS=m +CONFIG_EXT3_FS_XATTR=y +CONFIG_EXT3_FS_POSIX_ACL=y +CONFIG_EXT3_FS_SECURITY=y +CONFIG_JBD=m +# CONFIG_JBD_DEBUG is not set +CONFIG_FS_MBCACHE=y +CONFIG_REISERFS_FS=m +# CONFIG_REISERFS_CHECK is not set +# CONFIG_REISERFS_PROC_INFO is not set +# CONFIG_REISERFS_FS_XATTR is not set +CONFIG_JFS_FS=m +CONFIG_JFS_POSIX_ACL=y +# CONFIG_JFS_SECURITY is not set +# CONFIG_JFS_DEBUG is not set +CONFIG_JFS_STATISTICS=y +CONFIG_FS_POSIX_ACL=y + +# +# XFS support +# +CONFIG_XFS_FS=m +CONFIG_XFS_EXPORT=y +CONFIG_XFS_RT=y +CONFIG_XFS_QUOTA=y +CONFIG_XFS_SECURITY=y +CONFIG_XFS_POSIX_ACL=y +CONFIG_MINIX_FS=m +CONFIG_ROMFS_FS=m +CONFIG_QUOTA=y +CONFIG_QFMT_V1=m +CONFIG_QFMT_V2=m +CONFIG_QUOTACTL=y +CONFIG_DNOTIFY=y +CONFIG_AUTOFS_FS=m +CONFIG_AUTOFS4_FS=m + +# +# CD-ROM/DVD Filesystems +# +CONFIG_ISO9660_FS=m +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_ZISOFS_FS=m +CONFIG_UDF_FS=m +CONFIG_UDF_NLS=y + +# +# DOS/FAT/NT Filesystems +# +CONFIG_FAT_FS=m +CONFIG_MSDOS_FS=m +CONFIG_VFAT_FS=m +CONFIG_FAT_DEFAULT_CODEPAGE=437 +CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" +CONFIG_NTFS_FS=m +# CONFIG_NTFS_DEBUG is not set +# CONFIG_NTFS_RW is not set + +# +# Pseudo filesystems +# +CONFIG_PROC_FS=y +CONFIG_PROC_KCORE=y +CONFIG_SYSFS=y +# CONFIG_DEVFS_FS is not set +CONFIG_DEVPTS_FS_XATTR=y +CONFIG_DEVPTS_FS_SECURITY=y +CONFIG_TMPFS=y +CONFIG_TMPFS_XATTR=y +CONFIG_TMPFS_SECURITY=y +# CONFIG_HUGETLB_PAGE is not set +CONFIG_RAMFS=y + +# +# Miscellaneous filesystems +# +CONFIG_ADFS_FS=m +# CONFIG_ADFS_FS_RW is not set +CONFIG_AFFS_FS=m +CONFIG_HFS_FS=m +CONFIG_HFSPLUS_FS=m +CONFIG_BEFS_FS=m +# CONFIG_BEFS_DEBUG is not set +CONFIG_BFS_FS=m +CONFIG_EFS_FS=m +CONFIG_JFFS_FS=m +CONFIG_JFFS_FS_VERBOSE=0 +CONFIG_JFFS_PROC_FS=y +CONFIG_JFFS2_FS=m +CONFIG_JFFS2_FS_DEBUG=0 +# CONFIG_JFFS2_FS_NAND is not set +# CONFIG_JFFS2_FS_NOR_ECC is not set +# CONFIG_JFFS2_COMPRESSION_OPTIONS is not set +CONFIG_JFFS2_ZLIB=y +CONFIG_JFFS2_RTIME=y +# CONFIG_JFFS2_RUBIN is not set +CONFIG_CRAMFS=y +CONFIG_VXFS_FS=m +CONFIG_HPFS_FS=m +CONFIG_QNX4FS_FS=m +# CONFIG_QNX4FS_RW is not set +CONFIG_SYSV_FS=m +CONFIG_UFS_FS=m +# CONFIG_UFS_FS_WRITE is not set + +# +# Network File Systems +# +CONFIG_NFS_FS=m +CONFIG_NFS_V3=y +CONFIG_NFS_V4=y +CONFIG_NFS_DIRECTIO=y +CONFIG_NFSD=m +CONFIG_NFSD_V3=y +CONFIG_NFSD_V4=y +CONFIG_NFSD_TCP=y +CONFIG_LOCKD=m +CONFIG_LOCKD_V4=y +CONFIG_EXPORTFS=m +CONFIG_SUNRPC=m +CONFIG_SUNRPC_GSS=m +CONFIG_RPCSEC_GSS_KRB5=m +CONFIG_RPCSEC_GSS_SPKM3=m +CONFIG_SMB_FS=m +# CONFIG_SMB_NLS_DEFAULT is not set +CONFIG_CIFS=m +# CONFIG_CIFS_STATS is not set +# CONFIG_CIFS_XATTR is not set +# CONFIG_CIFS_EXPERIMENTAL is not set +CONFIG_NCP_FS=m +CONFIG_NCPFS_PACKET_SIGNING=y +CONFIG_NCPFS_IOCTL_LOCKING=y +CONFIG_NCPFS_STRONG=y +CONFIG_NCPFS_NFS_NS=y +CONFIG_NCPFS_OS2_NS=y +# CONFIG_NCPFS_SMALLDOS is not set +CONFIG_NCPFS_NLS=y +CONFIG_NCPFS_EXTRAS=y +CONFIG_CODA_FS=m +# CONFIG_CODA_FS_OLD_API is not set +CONFIG_AFS_FS=m +CONFIG_RXRPC=m + +# +# Partition Types +# +CONFIG_PARTITION_ADVANCED=y +CONFIG_ACORN_PARTITION=y +CONFIG_ACORN_PARTITION_CUMANA=y +# CONFIG_ACORN_PARTITION_EESOX is not set +CONFIG_ACORN_PARTITION_ICS=y +# CONFIG_ACORN_PARTITION_ADFS is not set +# CONFIG_ACORN_PARTITION_POWERTEC is not set +CONFIG_ACORN_PARTITION_RISCIX=y +CONFIG_OSF_PARTITION=y +CONFIG_AMIGA_PARTITION=y +CONFIG_ATARI_PARTITION=y +CONFIG_MAC_PARTITION=y +CONFIG_MSDOS_PARTITION=y +CONFIG_BSD_DISKLABEL=y +CONFIG_MINIX_SUBPARTITION=y +CONFIG_SOLARIS_X86_PARTITION=y +CONFIG_UNIXWARE_DISKLABEL=y +CONFIG_LDM_PARTITION=y +# CONFIG_LDM_DEBUG is not set +CONFIG_SGI_PARTITION=y +CONFIG_ULTRIX_PARTITION=y +CONFIG_SUN_PARTITION=y +CONFIG_EFI_PARTITION=y + +# +# Native Language Support +# +CONFIG_NLS=y +CONFIG_NLS_DEFAULT="cp437" +CONFIG_NLS_CODEPAGE_437=m +CONFIG_NLS_CODEPAGE_737=m +CONFIG_NLS_CODEPAGE_775=m +CONFIG_NLS_CODEPAGE_850=m +CONFIG_NLS_CODEPAGE_852=m +CONFIG_NLS_CODEPAGE_855=m +CONFIG_NLS_CODEPAGE_857=m +CONFIG_NLS_CODEPAGE_860=m +CONFIG_NLS_CODEPAGE_861=m +CONFIG_NLS_CODEPAGE_862=m +CONFIG_NLS_CODEPAGE_863=m +CONFIG_NLS_CODEPAGE_864=m +CONFIG_NLS_CODEPAGE_865=m +CONFIG_NLS_CODEPAGE_866=m +CONFIG_NLS_CODEPAGE_869=m +CONFIG_NLS_CODEPAGE_936=m +CONFIG_NLS_CODEPAGE_950=m +CONFIG_NLS_CODEPAGE_932=m +CONFIG_NLS_CODEPAGE_949=m +CONFIG_NLS_CODEPAGE_874=m +CONFIG_NLS_ISO8859_8=m +CONFIG_NLS_CODEPAGE_1250=m +CONFIG_NLS_CODEPAGE_1251=m +CONFIG_NLS_ASCII=m +CONFIG_NLS_ISO8859_1=m +CONFIG_NLS_ISO8859_2=m +CONFIG_NLS_ISO8859_3=m +CONFIG_NLS_ISO8859_4=m +CONFIG_NLS_ISO8859_5=m +CONFIG_NLS_ISO8859_6=m +CONFIG_NLS_ISO8859_7=m +CONFIG_NLS_ISO8859_9=m +CONFIG_NLS_ISO8859_13=m +CONFIG_NLS_ISO8859_14=m +CONFIG_NLS_ISO8859_15=m +CONFIG_NLS_KOI8_R=m +CONFIG_NLS_KOI8_U=m +CONFIG_NLS_UTF8=m + +# +# Kernel hacking +# +# CONFIG_PRINTK_TIME is not set +CONFIG_DEBUG_KERNEL=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_LOG_BUF_SHIFT=14 +# CONFIG_SCHEDSTATS is not set +# CONFIG_DEBUG_SLAB is not set +# CONFIG_DEBUG_SPINLOCK is not set +# CONFIG_DEBUG_SPINLOCK_SLEEP is not set +# CONFIG_DEBUG_KOBJECT is not set +# CONFIG_DEBUG_HIGHMEM is not set +# CONFIG_DEBUG_BUGVERBOSE is not set +# CONFIG_DEBUG_INFO is not set +# CONFIG_DEBUG_FS is not set +# CONFIG_FRAME_POINTER is not set +# CONFIG_EARLY_PRINTK is not set +# CONFIG_DEBUG_STACKOVERFLOW is not set +# CONFIG_KPROBES is not set +# CONFIG_DEBUG_STACK_USAGE is not set +# CONFIG_DEBUG_PAGEALLOC is not set +# CONFIG_4KSTACKS is not set +CONFIG_X86_FIND_SMP_CONFIG=y +CONFIG_X86_MPPARSE=y + +# +# Security options +# +CONFIG_KEYS=y +# CONFIG_KEYS_DEBUG_PROC_KEYS is not set +CONFIG_SECURITY=y +# CONFIG_SECURITY_NETWORK is not set +CONFIG_SECURITY_CAPABILITIES=y +CONFIG_SECURITY_ROOTPLUG=m +CONFIG_SECURITY_SECLVL=m +CONFIG_SECURITY_SELINUX=y +CONFIG_SECURITY_SELINUX_BOOTPARAM=y +CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0 +CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_SECURITY_SELINUX_DEVELOP=y +CONFIG_SECURITY_SELINUX_AVC_STATS=y +CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1 + +# +# Cryptographic options +# +CONFIG_CRYPTO=y +CONFIG_CRYPTO_HMAC=y +CONFIG_CRYPTO_NULL=m +CONFIG_CRYPTO_MD4=m +CONFIG_CRYPTO_MD5=y +CONFIG_CRYPTO_SHA1=m +CONFIG_CRYPTO_SHA256=m +CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_WP512=m +CONFIG_CRYPTO_TGR192=m +CONFIG_CRYPTO_DES=m +CONFIG_CRYPTO_BLOWFISH=m +CONFIG_CRYPTO_TWOFISH=m +CONFIG_CRYPTO_SERPENT=m +CONFIG_CRYPTO_AES_586=m +CONFIG_CRYPTO_CAST5=m +CONFIG_CRYPTO_CAST6=m +CONFIG_CRYPTO_TEA=m +CONFIG_CRYPTO_ARC4=m +CONFIG_CRYPTO_KHAZAD=m +CONFIG_CRYPTO_ANUBIS=m +CONFIG_CRYPTO_DEFLATE=m +CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_CRC32C=m +CONFIG_CRYPTO_TEST=m + +# +# Hardware crypto devices +# +# CONFIG_CRYPTO_DEV_PADLOCK is not set +CONFIG_XEN=y +CONFIG_NO_IDLE_HZ=y + +# +# XEN +# +CONFIG_XEN_PRIVILEGED_GUEST=y +# CONFIG_XEN_UNPRIVILEGED_GUEST is not set +CONFIG_XEN_PHYSDEV_ACCESS=y +CONFIG_XEN_BLKDEV_BACKEND=y +# CONFIG_XEN_BLKDEV_TAP_BE is not set +CONFIG_XEN_NETDEV_BACKEND=y +# CONFIG_XEN_NETDEV_PIPELINED_TRANSMITTER is not set +# CONFIG_XEN_TPMDEV_BACKEND is not set +CONFIG_XEN_BLKDEV_FRONTEND=y +CONFIG_XEN_NETDEV_FRONTEND=y +# CONFIG_XEN_BLKDEV_TAP is not set +# CONFIG_XEN_TPMDEV_FRONTEND is not set +# CONFIG_XEN_SHADOW_MODE is not set +CONFIG_XEN_SCRUB_PAGES=y +CONFIG_XEN_DISABLE_SERIAL=y +CONFIG_HAVE_ARCH_ALLOC_SKB=y +CONFIG_HAVE_ARCH_DEV_ALLOC_SKB=y + +# +# Library routines +# +CONFIG_CRC_CCITT=m +CONFIG_CRC32=y +CONFIG_LIBCRC32C=m +CONFIG_ZLIB_INFLATE=y +CONFIG_ZLIB_DEFLATE=m +CONFIG_REED_SOLOMON=m +CONFIG_REED_SOLOMON_DEC16=y +CONFIG_GENERIC_HARDIRQS=y +CONFIG_GENERIC_IRQ_PROBE=y +CONFIG_X86_SMP=y +CONFIG_X86_BIOS_REBOOT=y +CONFIG_X86_TRAMPOLINE=y diff -r 690fc13948db -r fd9b2c1bb577 buildconfigs/linux-defconfig_xen_x86_64 --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/buildconfigs/linux-defconfig_xen_x86_64 Mon Jan 30 17:18:27 2006 @@ -0,0 +1,2399 @@ +# +# Automatically generated make config: don't edit +# Linux kernel version: 2.6.12.6-xen +# Wed Jan 25 17:29:17 2006 +# +CONFIG_X86_64=y +CONFIG_64BIT=y +CONFIG_X86=y +CONFIG_MMU=y +CONFIG_RWSEM_GENERIC_SPINLOCK=y +CONFIG_GENERIC_CALIBRATE_DELAY=y +CONFIG_X86_CMPXCHG=y +CONFIG_EARLY_PRINTK=y +CONFIG_GENERIC_ISA_DMA=y +CONFIG_GENERIC_IOMAP=y + +# +# Code maturity level options +# +CONFIG_EXPERIMENTAL=y +# CONFIG_CLEAN_COMPILE is not set +CONFIG_BROKEN=y +CONFIG_BROKEN_ON_SMP=y +CONFIG_LOCK_KERNEL=y +CONFIG_INIT_ENV_ARG_LIMIT=32 + +# +# General setup +# +CONFIG_LOCALVERSION="" +CONFIG_SWAP=y +CONFIG_SYSVIPC=y +# CONFIG_POSIX_MQUEUE is not set +# CONFIG_BSD_PROCESS_ACCT is not set +CONFIG_SYSCTL=y +# CONFIG_AUDIT is not set +CONFIG_HOTPLUG=y +CONFIG_KOBJECT_UEVENT=y +# CONFIG_IKCONFIG is not set +# CONFIG_CPUSETS is not set +# CONFIG_EMBEDDED is not set +CONFIG_KALLSYMS=y +# CONFIG_KALLSYMS_ALL is not set +CONFIG_KALLSYMS_EXTRA_PASS=y +CONFIG_PRINTK=y +CONFIG_BUG=y +CONFIG_BASE_FULL=y +CONFIG_FUTEX=y +CONFIG_EPOLL=y +CONFIG_SHMEM=y +CONFIG_CC_ALIGN_FUNCTIONS=0 +CONFIG_CC_ALIGN_LABELS=0 +CONFIG_CC_ALIGN_LOOPS=0 +CONFIG_CC_ALIGN_JUMPS=0 +# CONFIG_TINY_SHMEM is not set +CONFIG_BASE_SMALL=0 + +# +# Loadable module support +# +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +# CONFIG_MODULE_FORCE_UNLOAD is not set +CONFIG_OBSOLETE_MODPARM=y +# CONFIG_MODVERSIONS is not set +CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_KMOD=y +CONFIG_STOP_MACHINE=y + +# +# Processor type and features +# +# CONFIG_MK8 is not set +# CONFIG_MPSC is not set +CONFIG_GENERIC_CPU=y +CONFIG_X86_64_XEN=y +CONFIG_X86_L1_CACHE_BYTES=128 +CONFIG_X86_L1_CACHE_SHIFT=7 +CONFIG_X86_GOOD_APIC=y +CONFIG_MICROCODE=y +# CONFIG_X86_MSR is not set +# CONFIG_X86_CPUID is not set +CONFIG_X86_IO_APIC=y +CONFIG_X86_XEN_GENAPIC=y +CONFIG_X86_LOCAL_APIC=y +CONFIG_SMP=y +# CONFIG_NUMA is not set +CONFIG_HAVE_DEC_LOCK=y +CONFIG_NR_CPUS=8 +CONFIG_SWIOTLB=y +CONFIG_DUMMY_IOMMU=y +CONFIG_SECCOMP=y +CONFIG_GENERIC_HARDIRQS=y +CONFIG_GENERIC_IRQ_PROBE=y +CONFIG_ISA_DMA_API=y + +# +# Power management options +# + +# +# ACPI (Advanced Configuration and Power Interface) Support +# +CONFIG_ACPI=y +CONFIG_ACPI_BOOT=y +CONFIG_ACPI_INTERPRETER=y +CONFIG_ACPI_AC=m +CONFIG_ACPI_BATTERY=m +CONFIG_ACPI_BUTTON=m +CONFIG_ACPI_VIDEO=m +CONFIG_ACPI_FAN=m +CONFIG_ACPI_PROCESSOR=m +CONFIG_ACPI_THERMAL=m +CONFIG_ACPI_ASUS=m +CONFIG_ACPI_IBM=m +CONFIG_ACPI_TOSHIBA=m +CONFIG_ACPI_BLACKLIST_YEAR=0 +# CONFIG_ACPI_DEBUG is not set +CONFIG_ACPI_BUS=y +CONFIG_ACPI_EC=y +CONFIG_ACPI_POWER=y +CONFIG_ACPI_PCI=y +CONFIG_ACPI_SYSTEM=y +# CONFIG_ACPI_CONTAINER is not set + +# +# Bus options (PCI etc.) +# +CONFIG_PCI=y +CONFIG_PCI_DIRECT=y +# CONFIG_PCI_MMCONFIG is not set +# CONFIG_UNORDERED_IO is not set + +# +# Executable file formats / Emulations +# +CONFIG_BINFMT_ELF=y +CONFIG_BINFMT_MISC=y +CONFIG_IA32_EMULATION=y +# CONFIG_IA32_AOUT is not set +CONFIG_COMPAT=y +CONFIG_SYSVIPC_COMPAT=y +CONFIG_UID16=y + +# +# Device Drivers +# + +# +# Generic Driver Options +# +CONFIG_STANDALONE=y +CONFIG_PREVENT_FIRMWARE_BUILD=y +CONFIG_FW_LOADER=y +# CONFIG_DEBUG_DRIVER is not set + +# +# Memory Technology Devices (MTD) +# +CONFIG_MTD=m +# CONFIG_MTD_DEBUG is not set +CONFIG_MTD_CONCAT=m +CONFIG_MTD_PARTITIONS=y +CONFIG_MTD_REDBOOT_PARTS=m +CONFIG_MTD_REDBOOT_DIRECTORY_BLOCK=-1 +# CONFIG_MTD_REDBOOT_PARTS_UNALLOCATED is not set +# CONFIG_MTD_REDBOOT_PARTS_READONLY is not set +CONFIG_MTD_CMDLINE_PARTS=y + +# +# User Modules And Translation Layers +# +CONFIG_MTD_CHAR=m +CONFIG_MTD_BLOCK=m +CONFIG_MTD_BLOCK_RO=m +CONFIG_FTL=m +CONFIG_NFTL=m +CONFIG_NFTL_RW=y +CONFIG_INFTL=m + +# +# RAM/ROM/Flash chip drivers +# +CONFIG_MTD_CFI=m +CONFIG_MTD_JEDECPROBE=m +CONFIG_MTD_GEN_PROBE=m +# CONFIG_MTD_CFI_ADV_OPTIONS is not set +CONFIG_MTD_MAP_BANK_WIDTH_1=y +CONFIG_MTD_MAP_BANK_WIDTH_2=y +CONFIG_MTD_MAP_BANK_WIDTH_4=y +# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set +# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set +# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set +CONFIG_MTD_CFI_I1=y +CONFIG_MTD_CFI_I2=y +# CONFIG_MTD_CFI_I4 is not set +# CONFIG_MTD_CFI_I8 is not set +CONFIG_MTD_CFI_INTELEXT=m +CONFIG_MTD_CFI_AMDSTD=m +CONFIG_MTD_CFI_AMDSTD_RETRY=3 +CONFIG_MTD_CFI_STAA=m +CONFIG_MTD_CFI_UTIL=m +CONFIG_MTD_RAM=m +CONFIG_MTD_ROM=m +CONFIG_MTD_ABSENT=m +# CONFIG_MTD_OBSOLETE_CHIPS is not set + +# +# Mapping drivers for chip access +# +CONFIG_MTD_COMPLEX_MAPPINGS=y +# CONFIG_MTD_PHYSMAP is not set +# CONFIG_MTD_PNC2000 is not set +CONFIG_MTD_SC520CDP=m +CONFIG_MTD_NETSC520=m +CONFIG_MTD_TS5500=m +CONFIG_MTD_SBC_GXX=m +CONFIG_MTD_ELAN_104NC=m +# CONFIG_MTD_AMD76XROM is not set +# CONFIG_MTD_ICHXROM is not set +CONFIG_MTD_SCB2_FLASH=m +# CONFIG_MTD_NETtel is not set +# CONFIG_MTD_DILNETPC is not set +# CONFIG_MTD_L440GX is not set +CONFIG_MTD_PCI=m + +# +# Self-contained MTD device drivers +# +CONFIG_MTD_PMC551=m +# CONFIG_MTD_PMC551_BUGFIX is not set +# CONFIG_MTD_PMC551_DEBUG is not set +# CONFIG_MTD_SLRAM is not set +# CONFIG_MTD_PHRAM is not set +CONFIG_MTD_MTDRAM=m +CONFIG_MTDRAM_TOTAL_SIZE=4096 +CONFIG_MTDRAM_ERASE_SIZE=128 +# CONFIG_MTD_BLKMTD is not set +CONFIG_MTD_BLOCK2MTD=m + +# +# Disk-On-Chip Device Drivers +# +CONFIG_MTD_DOC2000=m +# CONFIG_MTD_DOC2001 is not set +CONFIG_MTD_DOC2001PLUS=m +CONFIG_MTD_DOCPROBE=m +CONFIG_MTD_DOCECC=m +# CONFIG_MTD_DOCPROBE_ADVANCED is not set +CONFIG_MTD_DOCPROBE_ADDRESS=0 + +# +# NAND Flash Device Drivers +# +CONFIG_MTD_NAND=m +# CONFIG_MTD_NAND_VERIFY_WRITE is not set +CONFIG_MTD_NAND_IDS=m +# CONFIG_MTD_NAND_DISKONCHIP is not set +# CONFIG_MTD_NAND_NANDSIM is not set + +# +# Parallel port support +# +CONFIG_PARPORT=m +CONFIG_PARPORT_PC=m +# CONFIG_PARPORT_PC_FIFO is not set +# CONFIG_PARPORT_PC_SUPERIO is not set +CONFIG_PARPORT_NOT_PC=y +# CONFIG_PARPORT_GSC is not set +CONFIG_PARPORT_1284=y + +# +# Plug and Play support +# +# CONFIG_PNP is not set + +# +# Block devices +# +CONFIG_BLK_DEV_FD=m +CONFIG_PARIDE=m +CONFIG_PARIDE_PARPORT=m + +# +# Parallel IDE high-level drivers +# +CONFIG_PARIDE_PD=m +CONFIG_PARIDE_PCD=m +CONFIG_PARIDE_PF=m +CONFIG_PARIDE_PT=m +CONFIG_PARIDE_PG=m + +# +# Parallel IDE protocol modules +# +CONFIG_PARIDE_ATEN=m +CONFIG_PARIDE_BPCK=m +CONFIG_PARIDE_COMM=m +CONFIG_PARIDE_DSTR=m +CONFIG_PARIDE_FIT2=m +CONFIG_PARIDE_FIT3=m +CONFIG_PARIDE_EPAT=m +CONFIG_PARIDE_EPATC8=y +CONFIG_PARIDE_EPIA=m +CONFIG_PARIDE_FRIQ=m +CONFIG_PARIDE_FRPW=m +CONFIG_PARIDE_KBIC=m +CONFIG_PARIDE_KTTI=m +CONFIG_PARIDE_ON20=m +CONFIG_PARIDE_ON26=m +CONFIG_BLK_CPQ_DA=m +CONFIG_BLK_CPQ_CISS_DA=m +CONFIG_CISS_SCSI_TAPE=y +CONFIG_BLK_DEV_DAC960=m +CONFIG_BLK_DEV_UMEM=m +# CONFIG_BLK_DEV_COW_COMMON is not set +CONFIG_BLK_DEV_LOOP=m +CONFIG_BLK_DEV_CRYPTOLOOP=m +CONFIG_BLK_DEV_NBD=m +CONFIG_BLK_DEV_SX8=m +# CONFIG_BLK_DEV_UB is not set +CONFIG_BLK_DEV_RAM=y +CONFIG_BLK_DEV_RAM_COUNT=16 +CONFIG_BLK_DEV_RAM_SIZE=16384 +CONFIG_BLK_DEV_INITRD=y +CONFIG_INITRAMFS_SOURCE="" +CONFIG_LBD=y +CONFIG_CDROM_PKTCDVD=m +CONFIG_CDROM_PKTCDVD_BUFFERS=8 +# CONFIG_CDROM_PKTCDVD_WCACHE is not set + +# +# IO Schedulers +# +CONFIG_IOSCHED_NOOP=y +CONFIG_IOSCHED_AS=y +CONFIG_IOSCHED_DEADLINE=y +CONFIG_IOSCHED_CFQ=y +CONFIG_ATA_OVER_ETH=m + +# +# ATA/ATAPI/MFM/RLL support +# +CONFIG_IDE=y +CONFIG_BLK_DEV_IDE=y + +# +# Please see Documentation/ide.txt for help/info on IDE drives +# +# CONFIG_BLK_DEV_IDE_SATA is not set +# CONFIG_BLK_DEV_HD_IDE is not set +CONFIG_BLK_DEV_IDEDISK=y +CONFIG_IDEDISK_MULTI_MODE=y +CONFIG_BLK_DEV_IDECD=y +# CONFIG_BLK_DEV_IDETAPE is not set +CONFIG_BLK_DEV_IDEFLOPPY=y +CONFIG_BLK_DEV_IDESCSI=m +# CONFIG_IDE_TASK_IOCTL is not set + +# +# IDE chipset support/bugfixes +# +CONFIG_IDE_GENERIC=y +CONFIG_BLK_DEV_CMD640=y +CONFIG_BLK_DEV_CMD640_ENHANCED=y +CONFIG_BLK_DEV_IDEPCI=y +CONFIG_IDEPCI_SHARE_IRQ=y +# CONFIG_BLK_DEV_OFFBOARD is not set +CONFIG_BLK_DEV_GENERIC=y +# CONFIG_BLK_DEV_OPTI621 is not set +CONFIG_BLK_DEV_RZ1000=y +CONFIG_BLK_DEV_IDEDMA_PCI=y +# CONFIG_BLK_DEV_IDEDMA_FORCED is not set +CONFIG_IDEDMA_PCI_AUTO=y +# CONFIG_IDEDMA_ONLYDISK is not set +CONFIG_BLK_DEV_AEC62XX=y +CONFIG_BLK_DEV_ALI15X3=y +# CONFIG_WDC_ALI15X3 is not set +CONFIG_BLK_DEV_AMD74XX=y +CONFIG_BLK_DEV_ATIIXP=y +CONFIG_BLK_DEV_CMD64X=y +CONFIG_BLK_DEV_TRIFLEX=y +CONFIG_BLK_DEV_CY82C693=y +CONFIG_BLK_DEV_CS5520=y +CONFIG_BLK_DEV_CS5530=y +CONFIG_BLK_DEV_HPT34X=y +# CONFIG_HPT34X_AUTODMA is not set +CONFIG_BLK_DEV_HPT366=y +# CONFIG_BLK_DEV_SC1200 is not set +CONFIG_BLK_DEV_PIIX=y +# CONFIG_BLK_DEV_NS87415 is not set +CONFIG_BLK_DEV_PDC202XX_OLD=y +# CONFIG_PDC202XX_BURST is not set +CONFIG_BLK_DEV_PDC202XX_NEW=y +CONFIG_PDC202XX_FORCE=y +CONFIG_BLK_DEV_SVWKS=y +CONFIG_BLK_DEV_SIIMAGE=y +CONFIG_BLK_DEV_SIS5513=y +CONFIG_BLK_DEV_SLC90E66=y +# CONFIG_BLK_DEV_TRM290 is not set +CONFIG_BLK_DEV_VIA82CXXX=y +# CONFIG_IDE_ARM is not set +CONFIG_BLK_DEV_IDEDMA=y +# CONFIG_IDEDMA_IVB is not set +CONFIG_IDEDMA_AUTO=y +# CONFIG_BLK_DEV_HD is not set + +# +# SCSI device support +# +CONFIG_SCSI=y +CONFIG_SCSI_PROC_FS=y + +# +# SCSI support type (disk, tape, CD-ROM) +# +CONFIG_BLK_DEV_SD=y +CONFIG_CHR_DEV_ST=m +CONFIG_CHR_DEV_OSST=m +CONFIG_BLK_DEV_SR=m +CONFIG_BLK_DEV_SR_VENDOR=y +CONFIG_CHR_DEV_SG=m + +# +# Some SCSI devices (e.g. CD jukebox) support multiple LUNs +# +CONFIG_SCSI_MULTI_LUN=y +CONFIG_SCSI_CONSTANTS=y +CONFIG_SCSI_LOGGING=y + +# +# SCSI Transport Attributes +# +CONFIG_SCSI_SPI_ATTRS=m +CONFIG_SCSI_FC_ATTRS=m +CONFIG_SCSI_ISCSI_ATTRS=m + +# +# SCSI low-level drivers +# +CONFIG_BLK_DEV_3W_XXXX_RAID=m +CONFIG_SCSI_3W_9XXX=m +CONFIG_SCSI_ACARD=m +CONFIG_SCSI_AACRAID=m +CONFIG_SCSI_AIC7XXX=m +CONFIG_AIC7XXX_CMDS_PER_DEVICE=4 +CONFIG_AIC7XXX_RESET_DELAY_MS=15000 +# CONFIG_AIC7XXX_DEBUG_ENABLE is not set +CONFIG_AIC7XXX_DEBUG_MASK=0 +# CONFIG_AIC7XXX_REG_PRETTY_PRINT is not set +CONFIG_SCSI_AIC7XXX_OLD=m +CONFIG_SCSI_AIC79XX=m +CONFIG_AIC79XX_CMDS_PER_DEVICE=4 +CONFIG_AIC79XX_RESET_DELAY_MS=15000 +# CONFIG_AIC79XX_ENABLE_RD_STRM is not set +# CONFIG_AIC79XX_DEBUG_ENABLE is not set +CONFIG_AIC79XX_DEBUG_MASK=0 +# CONFIG_AIC79XX_REG_PRETTY_PRINT is not set +# CONFIG_SCSI_ADVANSYS is not set +CONFIG_MEGARAID_NEWGEN=y +CONFIG_MEGARAID_MM=m +CONFIG_MEGARAID_MAILBOX=m +CONFIG_SCSI_SATA=y +CONFIG_SCSI_SATA_AHCI=m +CONFIG_SCSI_SATA_SVW=m +CONFIG_SCSI_ATA_PIIX=y +CONFIG_SCSI_SATA_NV=m +CONFIG_SCSI_SATA_PROMISE=m +CONFIG_SCSI_SATA_QSTOR=m +CONFIG_SCSI_SATA_SX4=m +CONFIG_SCSI_SATA_SIL=m +CONFIG_SCSI_SATA_SIS=m +CONFIG_SCSI_SATA_ULI=m +CONFIG_SCSI_SATA_VIA=m +CONFIG_SCSI_SATA_VITESSE=m +CONFIG_SCSI_BUSLOGIC=m +# CONFIG_SCSI_OMIT_FLASHPOINT is not set +# CONFIG_SCSI_CPQFCTS is not set +# CONFIG_SCSI_DMX3191D is not set +# CONFIG_SCSI_EATA is not set +# CONFIG_SCSI_EATA_PIO is not set +# CONFIG_SCSI_FUTURE_DOMAIN is not set +CONFIG_SCSI_GDTH=m +CONFIG_SCSI_IPS=m +CONFIG_SCSI_INITIO=m +CONFIG_SCSI_INIA100=m +CONFIG_SCSI_PPA=m +CONFIG_SCSI_IMM=m +# CONFIG_SCSI_IZIP_EPP16 is not set +# CONFIG_SCSI_IZIP_SLOW_CTR is not set +CONFIG_SCSI_SYM53C8XX_2=m +CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=1 +CONFIG_SCSI_SYM53C8XX_DEFAULT_TAGS=16 +CONFIG_SCSI_SYM53C8XX_MAX_TAGS=64 +# CONFIG_SCSI_SYM53C8XX_IOMAPPED is not set +# CONFIG_SCSI_IPR is not set +# CONFIG_SCSI_PCI2000 is not set +# CONFIG_SCSI_PCI2220I is not set +# CONFIG_SCSI_QLOGIC_ISP is not set +# CONFIG_SCSI_QLOGIC_FC is not set +CONFIG_SCSI_QLOGIC_1280=m +CONFIG_SCSI_QLOGIC_1280_1040=y +CONFIG_SCSI_QLA2XXX=y +CONFIG_SCSI_QLA21XX=m +CONFIG_SCSI_QLA22XX=m +CONFIG_SCSI_QLA2300=m +CONFIG_SCSI_QLA2322=m +CONFIG_SCSI_QLA6312=m +CONFIG_SCSI_LPFC=m +CONFIG_SCSI_DC395x=m +CONFIG_SCSI_DC390T=m +# CONFIG_SCSI_DEBUG is not set + +# +# Multi-device support (RAID and LVM) +# +CONFIG_MD=y +CONFIG_BLK_DEV_MD=y +CONFIG_MD_LINEAR=m +CONFIG_MD_RAID0=m +CONFIG_MD_RAID1=m +CONFIG_MD_RAID10=m +CONFIG_MD_RAID5=m +CONFIG_MD_RAID6=m +CONFIG_MD_MULTIPATH=m +CONFIG_MD_FAULTY=m +CONFIG_BLK_DEV_DM=m +CONFIG_DM_CRYPT=m +CONFIG_DM_SNAPSHOT=m +CONFIG_DM_MIRROR=m +CONFIG_DM_ZERO=m +CONFIG_DM_MULTIPATH=m +CONFIG_DM_MULTIPATH_EMC=m + +# +# Fusion MPT device support +# +CONFIG_FUSION=m +CONFIG_FUSION_MAX_SGE=40 +CONFIG_FUSION_CTL=m +CONFIG_FUSION_LAN=m + +# +# IEEE 1394 (FireWire) support +# +CONFIG_IEEE1394=m + +# +# Subsystem Options +# +# CONFIG_IEEE1394_VERBOSEDEBUG is not set +CONFIG_IEEE1394_OUI_DB=y +CONFIG_IEEE1394_EXTRA_CONFIG_ROMS=y +CONFIG_IEEE1394_CONFIG_ROM_IP1394=y + +# +# Device Drivers +# +CONFIG_IEEE1394_PCILYNX=m +CONFIG_IEEE1394_OHCI1394=m + +# +# Protocol Drivers +# +CONFIG_IEEE1394_VIDEO1394=m +CONFIG_IEEE1394_SBP2=m +# CONFIG_IEEE1394_SBP2_PHYS_DMA is not set +CONFIG_IEEE1394_ETH1394=m +CONFIG_IEEE1394_DV1394=m +CONFIG_IEEE1394_RAWIO=m +CONFIG_IEEE1394_CMP=m +CONFIG_IEEE1394_AMDTP=m + +# +# I2O device support +# +CONFIG_I2O=m +CONFIG_I2O_CONFIG=m +CONFIG_I2O_BLOCK=m +CONFIG_I2O_SCSI=m +CONFIG_I2O_PROC=m + +# +# Networking support +# +CONFIG_NET=y + +# +# Networking options +# +CONFIG_PACKET=y +CONFIG_PACKET_MMAP=y +CONFIG_UNIX=y +CONFIG_NET_KEY=m +CONFIG_INET=y +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_MULTIPLE_TABLES=y +CONFIG_IP_ROUTE_FWMARK=y +CONFIG_IP_ROUTE_MULTIPATH=y +# CONFIG_IP_ROUTE_MULTIPATH_CACHED is not set +CONFIG_IP_ROUTE_VERBOSE=y +# CONFIG_IP_PNP is not set +CONFIG_NET_IPIP=m +CONFIG_NET_IPGRE=m +CONFIG_NET_IPGRE_BROADCAST=y +CONFIG_IP_MROUTE=y +CONFIG_IP_PIMSM_V1=y +CONFIG_IP_PIMSM_V2=y +# CONFIG_ARPD is not set +CONFIG_SYN_COOKIES=y +CONFIG_INET_AH=m +CONFIG_INET_ESP=m +CONFIG_INET_IPCOMP=m +CONFIG_INET_TUNNEL=m +CONFIG_IP_TCPDIAG=m +CONFIG_IP_TCPDIAG_IPV6=y + +# +# IP: Virtual Server Configuration +# +CONFIG_IP_VS=m +# CONFIG_IP_VS_DEBUG is not set +CONFIG_IP_VS_TAB_BITS=12 + +# +# IPVS transport protocol load balancing support +# +CONFIG_IP_VS_PROTO_TCP=y +CONFIG_IP_VS_PROTO_UDP=y +CONFIG_IP_VS_PROTO_ESP=y +CONFIG_IP_VS_PROTO_AH=y + +# +# IPVS scheduler +# +CONFIG_IP_VS_RR=m +CONFIG_IP_VS_WRR=m +CONFIG_IP_VS_LC=m +CONFIG_IP_VS_WLC=m +CONFIG_IP_VS_LBLC=m +CONFIG_IP_VS_LBLCR=m +CONFIG_IP_VS_DH=m +CONFIG_IP_VS_SH=m +CONFIG_IP_VS_SED=m +CONFIG_IP_VS_NQ=m + +# +# IPVS application helper +# +CONFIG_IP_VS_FTP=m +CONFIG_IPV6=m +CONFIG_IPV6_PRIVACY=y +CONFIG_INET6_AH=m +CONFIG_INET6_ESP=m +CONFIG_INET6_IPCOMP=m +CONFIG_INET6_TUNNEL=m +CONFIG_IPV6_TUNNEL=m +CONFIG_NETFILTER=y +# CONFIG_NETFILTER_DEBUG is not set +CONFIG_BRIDGE_NETFILTER=y + +# +# IP: Netfilter Configuration +# +CONFIG_IP_NF_CONNTRACK=m +CONFIG_IP_NF_CT_ACCT=y +CONFIG_IP_NF_CONNTRACK_MARK=y +CONFIG_IP_NF_CT_PROTO_SCTP=m +CONFIG_IP_NF_FTP=m +CONFIG_IP_NF_IRC=m +CONFIG_IP_NF_TFTP=m +CONFIG_IP_NF_AMANDA=m +CONFIG_IP_NF_QUEUE=m +CONFIG_IP_NF_IPTABLES=m +CONFIG_IP_NF_MATCH_LIMIT=m +CONFIG_IP_NF_MATCH_IPRANGE=m +CONFIG_IP_NF_MATCH_MAC=m +CONFIG_IP_NF_MATCH_PKTTYPE=m +CONFIG_IP_NF_MATCH_MARK=m +CONFIG_IP_NF_MATCH_MULTIPORT=m +CONFIG_IP_NF_MATCH_TOS=m +CONFIG_IP_NF_MATCH_RECENT=m +CONFIG_IP_NF_MATCH_ECN=m +CONFIG_IP_NF_MATCH_DSCP=m +CONFIG_IP_NF_MATCH_AH_ESP=m +CONFIG_IP_NF_MATCH_LENGTH=m +CONFIG_IP_NF_MATCH_TTL=m +CONFIG_IP_NF_MATCH_TCPMSS=m +CONFIG_IP_NF_MATCH_HELPER=m +CONFIG_IP_NF_MATCH_STATE=m +CONFIG_IP_NF_MATCH_CONNTRACK=m +CONFIG_IP_NF_MATCH_OWNER=m +CONFIG_IP_NF_MATCH_PHYSDEV=m +CONFIG_IP_NF_MATCH_ADDRTYPE=m +CONFIG_IP_NF_MATCH_REALM=m +CONFIG_IP_NF_MATCH_SCTP=m +CONFIG_IP_NF_MATCH_COMMENT=m +CONFIG_IP_NF_MATCH_CONNMARK=m +CONFIG_IP_NF_MATCH_HASHLIMIT=m +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP_NF_TARGET_LOG=m +CONFIG_IP_NF_TARGET_ULOG=m +CONFIG_IP_NF_TARGET_TCPMSS=m +CONFIG_IP_NF_NAT=m +CONFIG_IP_NF_NAT_NEEDED=y +CONFIG_IP_NF_TARGET_MASQUERADE=m +CONFIG_IP_NF_TARGET_REDIRECT=m +CONFIG_IP_NF_TARGET_NETMAP=m +CONFIG_IP_NF_TARGET_SAME=m +CONFIG_IP_NF_NAT_SNMP_BASIC=m +CONFIG_IP_NF_NAT_IRC=m +CONFIG_IP_NF_NAT_FTP=m +CONFIG_IP_NF_NAT_TFTP=m +CONFIG_IP_NF_NAT_AMANDA=m +CONFIG_IP_NF_MANGLE=m +CONFIG_IP_NF_TARGET_TOS=m +CONFIG_IP_NF_TARGET_ECN=m +CONFIG_IP_NF_TARGET_DSCP=m +CONFIG_IP_NF_TARGET_MARK=m +CONFIG_IP_NF_TARGET_CLASSIFY=m +CONFIG_IP_NF_TARGET_CONNMARK=m +CONFIG_IP_NF_TARGET_CLUSTERIP=m +CONFIG_IP_NF_RAW=m +CONFIG_IP_NF_TARGET_NOTRACK=m +CONFIG_IP_NF_ARPTABLES=m +CONFIG_IP_NF_ARPFILTER=m +CONFIG_IP_NF_ARP_MANGLE=m + +# +# IPv6: Netfilter Configuration (EXPERIMENTAL) +# +CONFIG_IP6_NF_QUEUE=m +CONFIG_IP6_NF_IPTABLES=m +CONFIG_IP6_NF_MATCH_LIMIT=m +CONFIG_IP6_NF_MATCH_MAC=m +CONFIG_IP6_NF_MATCH_RT=m +CONFIG_IP6_NF_MATCH_OPTS=m +CONFIG_IP6_NF_MATCH_FRAG=m +CONFIG_IP6_NF_MATCH_HL=m +CONFIG_IP6_NF_MATCH_MULTIPORT=m +CONFIG_IP6_NF_MATCH_OWNER=m +CONFIG_IP6_NF_MATCH_MARK=m +CONFIG_IP6_NF_MATCH_IPV6HEADER=m +CONFIG_IP6_NF_MATCH_AHESP=m +CONFIG_IP6_NF_MATCH_LENGTH=m +CONFIG_IP6_NF_MATCH_EUI64=m +CONFIG_IP6_NF_MATCH_PHYSDEV=m +CONFIG_IP6_NF_FILTER=m +CONFIG_IP6_NF_TARGET_LOG=m +CONFIG_IP6_NF_MANGLE=m +CONFIG_IP6_NF_TARGET_MARK=m +CONFIG_IP6_NF_RAW=m + +# +# Bridge: Netfilter Configuration +# +CONFIG_BRIDGE_NF_EBTABLES=m +CONFIG_BRIDGE_EBT_BROUTE=m +CONFIG_BRIDGE_EBT_T_FILTER=m +CONFIG_BRIDGE_EBT_T_NAT=m +CONFIG_BRIDGE_EBT_802_3=m +CONFIG_BRIDGE_EBT_AMONG=m +CONFIG_BRIDGE_EBT_ARP=m +CONFIG_BRIDGE_EBT_IP=m +CONFIG_BRIDGE_EBT_LIMIT=m +CONFIG_BRIDGE_EBT_MARK=m +CONFIG_BRIDGE_EBT_PKTTYPE=m +CONFIG_BRIDGE_EBT_STP=m +CONFIG_BRIDGE_EBT_VLAN=m +CONFIG_BRIDGE_EBT_ARPREPLY=m +CONFIG_BRIDGE_EBT_DNAT=m +CONFIG_BRIDGE_EBT_MARK_T=m +CONFIG_BRIDGE_EBT_REDIRECT=m +CONFIG_BRIDGE_EBT_SNAT=m +CONFIG_BRIDGE_EBT_LOG=m +CONFIG_BRIDGE_EBT_ULOG=m +CONFIG_XFRM=y +CONFIG_XFRM_USER=y + +# +# SCTP Configuration (EXPERIMENTAL) +# +CONFIG_IP_SCTP=m +# CONFIG_SCTP_DBG_MSG is not set +# CONFIG_SCTP_DBG_OBJCNT is not set +# CONFIG_SCTP_HMAC_NONE is not set +# CONFIG_SCTP_HMAC_SHA1 is not set +CONFIG_SCTP_HMAC_MD5=y +CONFIG_ATM=m +CONFIG_ATM_CLIP=m +# CONFIG_ATM_CLIP_NO_ICMP is not set +CONFIG_ATM_LANE=m +# CONFIG_ATM_MPOA is not set +CONFIG_ATM_BR2684=m +# CONFIG_ATM_BR2684_IPFILTER is not set +CONFIG_BRIDGE=m +CONFIG_VLAN_8021Q=m +# CONFIG_DECNET is not set +CONFIG_LLC=y +# CONFIG_LLC2 is not set +CONFIG_IPX=m +# CONFIG_IPX_INTERN is not set +CONFIG_ATALK=m +CONFIG_DEV_APPLETALK=y +CONFIG_IPDDP=m +CONFIG_IPDDP_ENCAP=y +CONFIG_IPDDP_DECAP=y +# CONFIG_X25 is not set +# CONFIG_LAPB is not set +CONFIG_NET_DIVERT=y +# CONFIG_ECONET is not set +CONFIG_WAN_ROUTER=m + +# +# QoS and/or fair queueing +# +CONFIG_NET_SCHED=y +CONFIG_NET_SCH_CLK_JIFFIES=y +# CONFIG_NET_SCH_CLK_GETTIMEOFDAY is not set +# CONFIG_NET_SCH_CLK_CPU is not set +CONFIG_NET_SCH_CBQ=m +CONFIG_NET_SCH_HTB=m +CONFIG_NET_SCH_HFSC=m +CONFIG_NET_SCH_ATM=m +CONFIG_NET_SCH_PRIO=m +CONFIG_NET_SCH_RED=m +CONFIG_NET_SCH_SFQ=m +CONFIG_NET_SCH_TEQL=m +CONFIG_NET_SCH_TBF=m +CONFIG_NET_SCH_GRED=m +CONFIG_NET_SCH_DSMARK=m +CONFIG_NET_SCH_NETEM=m +CONFIG_NET_SCH_INGRESS=m +CONFIG_NET_QOS=y +CONFIG_NET_ESTIMATOR=y +CONFIG_NET_CLS=y +CONFIG_NET_CLS_BASIC=m +CONFIG_NET_CLS_TCINDEX=m +CONFIG_NET_CLS_ROUTE4=m +CONFIG_NET_CLS_ROUTE=y +CONFIG_NET_CLS_FW=m +CONFIG_NET_CLS_U32=m +CONFIG_CLS_U32_PERF=y +CONFIG_NET_CLS_IND=y +CONFIG_CLS_U32_MARK=y +CONFIG_NET_CLS_RSVP=m +CONFIG_NET_CLS_RSVP6=m +CONFIG_NET_EMATCH=y +CONFIG_NET_EMATCH_STACK=32 +CONFIG_NET_EMATCH_CMP=m +CONFIG_NET_EMATCH_NBYTE=m +CONFIG_NET_EMATCH_U32=m +CONFIG_NET_EMATCH_META=m +# CONFIG_NET_CLS_ACT is not set +CONFIG_NET_CLS_POLICE=y + +# +# Network testing +# +# CONFIG_NET_PKTGEN is not set +CONFIG_NETPOLL=y +# CONFIG_NETPOLL_RX is not set +CONFIG_NETPOLL_TRAP=y +CONFIG_NET_POLL_CONTROLLER=y +# CONFIG_HAMRADIO is not set +CONFIG_IRDA=m + +# +# IrDA protocols +# +CONFIG_IRLAN=m +CONFIG_IRNET=m +CONFIG_IRCOMM=m +# CONFIG_IRDA_ULTRA is not set + +# +# IrDA options +# +CONFIG_IRDA_CACHE_LAST_LSAP=y +CONFIG_IRDA_FAST_RR=y +# CONFIG_IRDA_DEBUG is not set + +# +# Infrared-port device drivers +# + +# +# SIR device drivers +# +CONFIG_IRTTY_SIR=m + +# +# Dongle support +# +CONFIG_DONGLE=y +CONFIG_ESI_DONGLE=m +CONFIG_ACTISYS_DONGLE=m +CONFIG_TEKRAM_DONGLE=m +CONFIG_LITELINK_DONGLE=m +CONFIG_MA600_DONGLE=m +CONFIG_GIRBIL_DONGLE=m +CONFIG_MCP2120_DONGLE=m +CONFIG_OLD_BELKIN_DONGLE=m +CONFIG_ACT200L_DONGLE=m + +# +# Old SIR device drivers +# +CONFIG_IRPORT_SIR=m + +# +# Old Serial dongle support +# +# CONFIG_DONGLE_OLD is not set + +# +# FIR device drivers +# +CONFIG_USB_IRDA=m +CONFIG_SIGMATEL_FIR=m +CONFIG_NSC_FIR=m +CONFIG_WINBOND_FIR=m +CONFIG_SMC_IRCC_FIR=m +CONFIG_ALI_FIR=m +CONFIG_VLSI_FIR=m +CONFIG_VIA_FIR=m +CONFIG_BT=m +CONFIG_BT_L2CAP=m +CONFIG_BT_SCO=m +CONFIG_BT_RFCOMM=m +CONFIG_BT_RFCOMM_TTY=y +CONFIG_BT_BNEP=m +CONFIG_BT_BNEP_MC_FILTER=y +CONFIG_BT_BNEP_PROTO_FILTER=y +CONFIG_BT_CMTP=m +CONFIG_BT_HIDP=m + +# +# Bluetooth device drivers +# +CONFIG_BT_HCIUSB=m +CONFIG_BT_HCIUSB_SCO=y +CONFIG_BT_HCIUART=m +CONFIG_BT_HCIUART_H4=y +CONFIG_BT_HCIUART_BCSP=y +CONFIG_BT_HCIUART_BCSP_TXCRC=y +CONFIG_BT_HCIBCM203X=m +CONFIG_BT_HCIBPA10X=m +CONFIG_BT_HCIBFUSB=m +CONFIG_BT_HCIVHCI=m +CONFIG_NETDEVICES=y +CONFIG_DUMMY=m +CONFIG_BONDING=m +CONFIG_EQUALIZER=m +CONFIG_TUN=m + +# +# ARCnet devices +# +# CONFIG_ARCNET is not set + +# +# Ethernet (10 or 100Mbit) +# +CONFIG_NET_ETHERNET=y +CONFIG_MII=m +CONFIG_HAPPYMEAL=m +CONFIG_SUNGEM=m +CONFIG_NET_VENDOR_3COM=y +CONFIG_VORTEX=m +CONFIG_TYPHOON=m + +# +# Tulip family network device support +# +CONFIG_NET_TULIP=y +CONFIG_DE2104X=m +CONFIG_TULIP=m +# CONFIG_TULIP_MWI is not set +CONFIG_TULIP_MMIO=y +# CONFIG_TULIP_NAPI is not set +CONFIG_DE4X5=m +CONFIG_WINBOND_840=m +CONFIG_DM9102=m +# CONFIG_HP100 is not set +CONFIG_NET_PCI=y +CONFIG_PCNET32=m +CONFIG_AMD8111_ETH=m +CONFIG_AMD8111E_NAPI=y +CONFIG_ADAPTEC_STARFIRE=m +CONFIG_ADAPTEC_STARFIRE_NAPI=y +CONFIG_B44=m +CONFIG_FORCEDETH=m +CONFIG_DGRS=m +CONFIG_EEPRO100=m +CONFIG_E100=m +CONFIG_FEALNX=m +CONFIG_NATSEMI=m +CONFIG_NE2K_PCI=m +CONFIG_8139CP=m +CONFIG_8139TOO=m +CONFIG_8139TOO_PIO=y +# CONFIG_8139TOO_TUNE_TWISTER is not set +CONFIG_8139TOO_8129=y +# CONFIG_8139_OLD_RX_RESET is not set +CONFIG_SIS900=m +CONFIG_EPIC100=m +CONFIG_SUNDANCE=m +# CONFIG_SUNDANCE_MMIO is not set +CONFIG_VIA_RHINE=m +CONFIG_VIA_RHINE_MMIO=y + +# +# Ethernet (1000 Mbit) +# +CONFIG_ACENIC=m +# CONFIG_ACENIC_OMIT_TIGON_I is not set +CONFIG_DL2K=m +CONFIG_E1000=m +CONFIG_E1000_NAPI=y +CONFIG_NS83820=m +CONFIG_HAMACHI=m +CONFIG_YELLOWFIN=m +CONFIG_R8169=m +CONFIG_R8169_NAPI=y +CONFIG_R8169_VLAN=y +CONFIG_SK98LIN=m +CONFIG_VIA_VELOCITY=m +CONFIG_TIGON3=m +CONFIG_BNX2=m + +# +# Ethernet (10000 Mbit) +# +CONFIG_IXGB=m +CONFIG_IXGB_NAPI=y +CONFIG_S2IO=m +CONFIG_S2IO_NAPI=y +# CONFIG_2BUFF_MODE is not set + +# +# Token Ring devices +# +CONFIG_TR=y +CONFIG_IBMOL=m +CONFIG_3C359=m +CONFIG_TMS380TR=m +CONFIG_TMSPCI=m +CONFIG_ABYSS=m + +# +# Wireless LAN (non-hamradio) +# +CONFIG_NET_RADIO=y + +# +# Obsolete Wireless cards support (pre-802.11) +# +# CONFIG_STRIP is not set + +# +# Wireless 802.11b ISA/PCI cards support +# +CONFIG_HERMES=m +CONFIG_PLX_HERMES=m +CONFIG_TMD_HERMES=m +CONFIG_PCI_HERMES=m +CONFIG_ATMEL=m +CONFIG_PCI_ATMEL=m + +# +# Prism GT/Duette 802.11(a/b/g) PCI/Cardbus support +# +CONFIG_PRISM54=m +CONFIG_NET_WIRELESS=y + +# +# Wan interfaces +# +# CONFIG_WAN is not set + +# +# ATM drivers +# +CONFIG_ATM_TCP=m +CONFIG_ATM_LANAI=m +CONFIG_ATM_ENI=m +# CONFIG_ATM_ENI_DEBUG is not set +# CONFIG_ATM_ENI_TUNE_BURST is not set +CONFIG_ATM_FIRESTREAM=m +# CONFIG_ATM_ZATM is not set +CONFIG_ATM_IDT77252=m +# CONFIG_ATM_IDT77252_DEBUG is not set +# CONFIG_ATM_IDT77252_RCV_ALL is not set +CONFIG_ATM_IDT77252_USE_SUNI=y +CONFIG_ATM_AMBASSADOR=m +# CONFIG_ATM_AMBASSADOR_DEBUG is not set +CONFIG_ATM_HORIZON=m +# CONFIG_ATM_HORIZON_DEBUG is not set +CONFIG_ATM_FORE200E_MAYBE=m +# CONFIG_ATM_FORE200E_PCA is not set +CONFIG_ATM_HE=m +# CONFIG_ATM_HE_USE_SUNI is not set +CONFIG_FDDI=y +# CONFIG_DEFXX is not set +CONFIG_SKFP=m +# CONFIG_HIPPI is not set +CONFIG_PLIP=m +CONFIG_PPP=m +CONFIG_PPP_MULTILINK=y +CONFIG_PPP_FILTER=y +CONFIG_PPP_ASYNC=m +CONFIG_PPP_SYNC_TTY=m +CONFIG_PPP_DEFLATE=m +# CONFIG_PPP_BSDCOMP is not set +CONFIG_PPPOE=m +CONFIG_PPPOATM=m +CONFIG_SLIP=m +CONFIG_SLIP_COMPRESSED=y +CONFIG_SLIP_SMART=y +# CONFIG_SLIP_MODE_SLIP6 is not set +CONFIG_NET_FC=y +# CONFIG_SHAPER is not set +CONFIG_NETCONSOLE=m + +# +# ISDN subsystem +# +CONFIG_ISDN=m + +# +# Old ISDN4Linux +# +CONFIG_ISDN_I4L=m +CONFIG_ISDN_PPP=y +CONFIG_ISDN_PPP_VJ=y +CONFIG_ISDN_MPP=y +CONFIG_IPPP_FILTER=y +# CONFIG_ISDN_PPP_BSDCOMP is not set +CONFIG_ISDN_AUDIO=y +CONFIG_ISDN_TTY_FAX=y + +# +# ISDN feature submodules +# +CONFIG_ISDN_DRV_LOOP=m +CONFIG_ISDN_DIVERSION=m + +# +# ISDN4Linux hardware drivers +# + +# +# Passive cards +# +CONFIG_ISDN_DRV_HISAX=m + +# +# D-channel protocol features +# +CONFIG_HISAX_EURO=y +CONFIG_DE_AOC=y +CONFIG_HISAX_NO_SENDCOMPLETE=y +CONFIG_HISAX_NO_LLC=y +CONFIG_HISAX_NO_KEYPAD=y +CONFIG_HISAX_1TR6=y +CONFIG_HISAX_NI1=y +CONFIG_HISAX_MAX_CARDS=8 + +# +# HiSax supported cards +# +CONFIG_HISAX_16_3=y +CONFIG_HISAX_TELESPCI=y +CONFIG_HISAX_S0BOX=y +CONFIG_HISAX_FRITZPCI=y +CONFIG_HISAX_AVM_A1_PCMCIA=y +CONFIG_HISAX_ELSA=y +CONFIG_HISAX_DIEHLDIVA=y +CONFIG_HISAX_SEDLBAUER=y +CONFIG_HISAX_NETJET=y +CONFIG_HISAX_NETJET_U=y +CONFIG_HISAX_NICCY=y +CONFIG_HISAX_BKM_A4T=y +CONFIG_HISAX_SCT_QUADRO=y +CONFIG_HISAX_GAZEL=y +CONFIG_HISAX_HFC_PCI=y +CONFIG_HISAX_W6692=y +CONFIG_HISAX_HFC_SX=y +CONFIG_HISAX_ENTERNOW_PCI=y +# CONFIG_HISAX_DEBUG is not set + +# +# HiSax PCMCIA card service modules +# + +# +# HiSax sub driver modules +# +CONFIG_HISAX_ST5481=m +CONFIG_HISAX_HFCUSB=m +CONFIG_HISAX_HFC4S8S=m +CONFIG_HISAX_FRITZ_PCIPNP=m +CONFIG_HISAX_HDLC=y + +# +# Active cards +# +CONFIG_HYSDN=m +CONFIG_HYSDN_CAPI=y + +# +# CAPI subsystem +# +CONFIG_ISDN_CAPI=m +CONFIG_ISDN_DRV_AVMB1_VERBOSE_REASON=y +CONFIG_ISDN_CAPI_MIDDLEWARE=y +CONFIG_ISDN_CAPI_CAPI20=m +CONFIG_ISDN_CAPI_CAPIFS_BOOL=y +CONFIG_ISDN_CAPI_CAPIFS=m +CONFIG_ISDN_CAPI_CAPIDRV=m + +# +# CAPI hardware drivers +# + +# +# Active AVM cards +# +CONFIG_CAPI_AVM=y +CONFIG_ISDN_DRV_AVMB1_B1PCI=m +CONFIG_ISDN_DRV_AVMB1_B1PCIV4=y +CONFIG_ISDN_DRV_AVMB1_B1PCMCIA=m +CONFIG_ISDN_DRV_AVMB1_T1PCI=m +CONFIG_ISDN_DRV_AVMB1_C4=m + +# +# Active Eicon DIVA Server cards +# +# CONFIG_CAPI_EICON is not set + +# +# Telephony Support +# +# CONFIG_PHONE is not set + +# +# Input device support +# +CONFIG_INPUT=y + +# +# Userland interfaces +# +CONFIG_INPUT_MOUSEDEV=y +# CONFIG_INPUT_MOUSEDEV_PSAUX is not set +CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024 +CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 +CONFIG_INPUT_JOYDEV=m +# CONFIG_INPUT_TSDEV is not set +CONFIG_INPUT_EVDEV=y +# CONFIG_INPUT_EVBUG is not set + +# +# Input Device Drivers +# +CONFIG_INPUT_KEYBOARD=y +CONFIG_KEYBOARD_ATKBD=y +# CONFIG_KEYBOARD_SUNKBD is not set +# CONFIG_KEYBOARD_LKKBD is not set +# CONFIG_KEYBOARD_XTKBD is not set +# CONFIG_KEYBOARD_NEWTON is not set +CONFIG_INPUT_MOUSE=y +CONFIG_MOUSE_PS2=y +CONFIG_MOUSE_SERIAL=m +CONFIG_MOUSE_VSXXXAA=m +CONFIG_INPUT_JOYSTICK=y +CONFIG_JOYSTICK_ANALOG=m +CONFIG_JOYSTICK_A3D=m +CONFIG_JOYSTICK_ADI=m +CONFIG_JOYSTICK_COBRA=m +CONFIG_JOYSTICK_GF2K=m +CONFIG_JOYSTICK_GRIP=m +CONFIG_JOYSTICK_GRIP_MP=m +CONFIG_JOYSTICK_GUILLEMOT=m +CONFIG_JOYSTICK_INTERACT=m +CONFIG_JOYSTICK_SIDEWINDER=m +CONFIG_JOYSTICK_TMDC=m +CONFIG_JOYSTICK_IFORCE=m +CONFIG_JOYSTICK_IFORCE_USB=y +CONFIG_JOYSTICK_IFORCE_232=y +CONFIG_JOYSTICK_WARRIOR=m +CONFIG_JOYSTICK_MAGELLAN=m +CONFIG_JOYSTICK_SPACEORB=m +CONFIG_JOYSTICK_SPACEBALL=m +CONFIG_JOYSTICK_STINGER=m +CONFIG_JOYSTICK_TWIDJOY=m +CONFIG_JOYSTICK_DB9=m +CONFIG_JOYSTICK_GAMECON=m +CONFIG_JOYSTICK_TURBOGRAFX=m +CONFIG_JOYSTICK_JOYDUMP=m +CONFIG_INPUT_TOUCHSCREEN=y +CONFIG_TOUCHSCREEN_GUNZE=m +CONFIG_TOUCHSCREEN_ELO=m +CONFIG_TOUCHSCREEN_MTOUCH=m +CONFIG_TOUCHSCREEN_MK712=m +CONFIG_INPUT_MISC=y +CONFIG_INPUT_PCSPKR=m +CONFIG_INPUT_UINPUT=m + +# +# Hardware I/O ports +# +CONFIG_SERIO=y +CONFIG_SERIO_I8042=y +CONFIG_SERIO_SERPORT=y +# CONFIG_SERIO_CT82C710 is not set +# CONFIG_SERIO_PARKBD is not set +# CONFIG_SERIO_PCIPS2 is not set +CONFIG_SERIO_LIBPS2=y +# CONFIG_SERIO_RAW is not set +CONFIG_GAMEPORT=m +CONFIG_GAMEPORT_NS558=m +CONFIG_GAMEPORT_L4=m +CONFIG_GAMEPORT_EMU10K1=m +CONFIG_GAMEPORT_VORTEX=m +CONFIG_GAMEPORT_FM801=m +CONFIG_GAMEPORT_CS461X=m + +# +# Character devices +# +CONFIG_VT=y +CONFIG_VT_CONSOLE=y +CONFIG_HW_CONSOLE=y +# CONFIG_SERIAL_NONSTANDARD is not set + +# +# Serial drivers +# +# CONFIG_SERIAL_8250 is not set + +# +# Non-8250 serial port support +# +# CONFIG_SERIAL_JSM is not set +CONFIG_UNIX98_PTYS=y +# CONFIG_LEGACY_PTYS is not set +CONFIG_PRINTER=m +CONFIG_LP_CONSOLE=y +CONFIG_PPDEV=m +CONFIG_TIPAR=m + +# +# IPMI +# +CONFIG_IPMI_HANDLER=m +# CONFIG_IPMI_PANIC_EVENT is not set +CONFIG_IPMI_DEVICE_INTERFACE=m +CONFIG_IPMI_SI=m +CONFIG_IPMI_WATCHDOG=m +CONFIG_IPMI_POWEROFF=m + +# +# Watchdog Cards +# +CONFIG_WATCHDOG=y +# CONFIG_WATCHDOG_NOWAYOUT is not set + +# +# Watchdog Device Drivers +# +CONFIG_SOFT_WATCHDOG=m +CONFIG_ACQUIRE_WDT=m +CONFIG_ADVANTECH_WDT=m +CONFIG_ALIM1535_WDT=m +CONFIG_ALIM7101_WDT=m +CONFIG_SC520_WDT=m +CONFIG_EUROTECH_WDT=m +CONFIG_IB700_WDT=m +CONFIG_WAFER_WDT=m +CONFIG_I8XX_TCO=m +CONFIG_SC1200_WDT=m +# CONFIG_60XX_WDT is not set +CONFIG_CPU5_WDT=m +CONFIG_W83627HF_WDT=m +CONFIG_W83877F_WDT=m +CONFIG_MACHZ_WDT=m + +# +# PCI-based Watchdog Cards +# +CONFIG_PCIPCWATCHDOG=m +CONFIG_WDTPCI=m +CONFIG_WDT_501_PCI=y + +# +# USB-based Watchdog Cards +# +CONFIG_USBPCWATCHDOG=m +CONFIG_HW_RANDOM=m +# CONFIG_NVRAM is not set +CONFIG_RTC=y +CONFIG_DTLK=m +CONFIG_R3964=m +# CONFIG_APPLICOM is not set + +# +# Ftape, the floppy tape device driver +# +# CONFIG_FTAPE is not set +# CONFIG_AGP is not set +CONFIG_DRM=m +CONFIG_DRM_TDFX=m +# CONFIG_DRM_GAMMA is not set +CONFIG_DRM_R128=m +CONFIG_DRM_RADEON=m +# CONFIG_MWAVE is not set +# CONFIG_RAW_DRIVER is not set +# CONFIG_HPET is not set +CONFIG_HANGCHECK_TIMER=m + +# +# TPM devices +# +# CONFIG_TCG_TPM is not set + +# +# I2C support +# +CONFIG_I2C=m +CONFIG_I2C_CHARDEV=m + +# +# I2C Algorithms +# +CONFIG_I2C_ALGOBIT=m +CONFIG_I2C_ALGOPCF=m +CONFIG_I2C_ALGOPCA=m + +# +# I2C Hardware Bus support +# +# CONFIG_I2C_ALI1535 is not set +# CONFIG_I2C_ALI1563 is not set +# CONFIG_I2C_ALI15X3 is not set +CONFIG_I2C_AMD756=m +CONFIG_I2C_AMD756_S4882=m +CONFIG_I2C_AMD8111=m +# CONFIG_I2C_I801 is not set +# CONFIG_I2C_I810 is not set +# CONFIG_I2C_PIIX4 is not set +CONFIG_I2C_ISA=m +CONFIG_I2C_NFORCE2=m +# CONFIG_I2C_PARPORT is not set +# CONFIG_I2C_PARPORT_LIGHT is not set +CONFIG_I2C_PROSAVAGE=m +CONFIG_I2C_SAVAGE4=m +# CONFIG_SCx200_ACB is not set +# CONFIG_I2C_SIS5595 is not set +# CONFIG_I2C_SIS630 is not set +CONFIG_I2C_SIS96X=m +CONFIG_I2C_STUB=m +CONFIG_I2C_VIA=m +CONFIG_I2C_VIAPRO=m +CONFIG_I2C_VOODOO3=m +CONFIG_I2C_PCA_ISA=m + +# +# Hardware Sensors Chip support +# +CONFIG_I2C_SENSOR=m +CONFIG_SENSORS_ADM1021=m +CONFIG_SENSORS_ADM1025=m +CONFIG_SENSORS_ADM1026=m +CONFIG_SENSORS_ADM1031=m +CONFIG_SENSORS_ASB100=m +CONFIG_SENSORS_DS1621=m +CONFIG_SENSORS_FSCHER=m +CONFIG_SENSORS_FSCPOS=m +CONFIG_SENSORS_GL518SM=m +CONFIG_SENSORS_GL520SM=m +CONFIG_SENSORS_IT87=m +CONFIG_SENSORS_LM63=m +CONFIG_SENSORS_LM75=m +CONFIG_SENSORS_LM77=m +CONFIG_SENSORS_LM78=m +CONFIG_SENSORS_LM80=m +CONFIG_SENSORS_LM83=m +CONFIG_SENSORS_LM85=m +CONFIG_SENSORS_LM87=m +CONFIG_SENSORS_LM90=m +CONFIG_SENSORS_LM92=m +CONFIG_SENSORS_MAX1619=m +CONFIG_SENSORS_PC87360=m +CONFIG_SENSORS_SMSC47B397=m +CONFIG_SENSORS_SIS5595=m +CONFIG_SENSORS_SMSC47M1=m +CONFIG_SENSORS_VIA686A=m +CONFIG_SENSORS_W83781D=m +CONFIG_SENSORS_W83L785TS=m +CONFIG_SENSORS_W83627HF=m + +# +# Other I2C Chip support +# +CONFIG_SENSORS_DS1337=m +CONFIG_SENSORS_EEPROM=m +CONFIG_SENSORS_PCF8574=m +CONFIG_SENSORS_PCF8591=m +CONFIG_SENSORS_RTC8564=m +# CONFIG_I2C_DEBUG_CORE is not set +# CONFIG_I2C_DEBUG_ALGO is not set +# CONFIG_I2C_DEBUG_BUS is not set +# CONFIG_I2C_DEBUG_CHIP is not set + +# +# Dallas's 1-wire bus +# +CONFIG_W1=m +CONFIG_W1_MATROX=m +CONFIG_W1_DS9490=m +CONFIG_W1_DS9490_BRIDGE=m +CONFIG_W1_THERM=m +CONFIG_W1_SMEM=m + +# +# Misc devices +# +# CONFIG_IBM_ASM is not set + +# +# Multimedia devices +# +CONFIG_VIDEO_DEV=m + +# +# Video For Linux +# + +# +# Video Adapters +# +CONFIG_VIDEO_BT848=m +CONFIG_VIDEO_BWQCAM=m +CONFIG_VIDEO_CQCAM=m +CONFIG_VIDEO_W9966=m +CONFIG_VIDEO_CPIA=m +CONFIG_VIDEO_CPIA_PP=m +CONFIG_VIDEO_CPIA_USB=m +CONFIG_VIDEO_SAA5246A=m +CONFIG_VIDEO_SAA5249=m +CONFIG_TUNER_3036=m +CONFIG_VIDEO_STRADIS=m +CONFIG_VIDEO_ZORAN=m +CONFIG_VIDEO_ZORAN_BUZ=m +CONFIG_VIDEO_ZORAN_DC10=m +CONFIG_VIDEO_ZORAN_DC30=m +CONFIG_VIDEO_ZORAN_LML33=m +CONFIG_VIDEO_ZORAN_LML33R10=m +# CONFIG_VIDEO_ZR36120 is not set +CONFIG_VIDEO_SAA7134=m +CONFIG_VIDEO_SAA7134_DVB=m +CONFIG_VIDEO_MXB=m +CONFIG_VIDEO_DPC=m +CONFIG_VIDEO_HEXIUM_ORION=m +CONFIG_VIDEO_HEXIUM_GEMINI=m +CONFIG_VIDEO_CX88=m +CONFIG_VIDEO_CX88_DVB=m +CONFIG_VIDEO_OVCAMCHIP=m + +# +# Radio Adapters +# +CONFIG_RADIO_GEMTEK_PCI=m +CONFIG_RADIO_MAXIRADIO=m +CONFIG_RADIO_MAESTRO=m + +# +# Digital Video Broadcasting Devices +# +CONFIG_DVB=y +CONFIG_DVB_CORE=m + +# +# Supported SAA7146 based PCI Adapters +# +CONFIG_DVB_AV7110=m +CONFIG_DVB_AV7110_OSD=y +CONFIG_DVB_BUDGET=m +CONFIG_DVB_BUDGET_CI=m +CONFIG_DVB_BUDGET_AV=m +CONFIG_DVB_BUDGET_PATCH=m + +# +# Supported USB Adapters +# +CONFIG_DVB_TTUSB_BUDGET=m +CONFIG_DVB_TTUSB_DEC=m +CONFIG_DVB_DIBUSB=m +CONFIG_DVB_DIBUSB_MISDESIGNED_DEVICES=y +# CONFIG_DVB_DIBCOM_DEBUG is not set +CONFIG_DVB_CINERGYT2=m +CONFIG_DVB_CINERGYT2_TUNING=y +CONFIG_DVB_CINERGYT2_STREAM_URB_COUNT=32 +CONFIG_DVB_CINERGYT2_STREAM_BUF_SIZE=512 +CONFIG_DVB_CINERGYT2_QUERY_INTERVAL=250 +CONFIG_DVB_CINERGYT2_ENABLE_RC_INPUT_DEVICE=y +CONFIG_DVB_CINERGYT2_RC_QUERY_INTERVAL=100 + +# +# Supported FlexCopII (B2C2) Adapters +# +CONFIG_DVB_B2C2_FLEXCOP=m +CONFIG_DVB_B2C2_FLEXCOP_PCI=m +CONFIG_DVB_B2C2_FLEXCOP_USB=m +# CONFIG_DVB_B2C2_FLEXCOP_DEBUG is not set +CONFIG_DVB_B2C2_SKYSTAR=m + +# +# Supported BT878 Adapters +# +CONFIG_DVB_BT8XX=m + +# +# Supported DVB Frontends +# + +# +# Customise DVB Frontends +# + +# +# DVB-S (satellite) frontends +# +CONFIG_DVB_STV0299=m +CONFIG_DVB_CX24110=m +CONFIG_DVB_TDA8083=m +CONFIG_DVB_TDA80XX=m +CONFIG_DVB_MT312=m +CONFIG_DVB_VES1X93=m + +# +# DVB-T (terrestrial) frontends +# +CONFIG_DVB_SP8870=m +CONFIG_DVB_SP887X=m +CONFIG_DVB_CX22700=m +CONFIG_DVB_CX22702=m +CONFIG_DVB_L64781=m +CONFIG_DVB_TDA1004X=m +CONFIG_DVB_NXT6000=m +CONFIG_DVB_MT352=m +CONFIG_DVB_DIB3000MB=m +CONFIG_DVB_DIB3000MC=m + +# +# DVB-C (cable) frontends +# +CONFIG_DVB_ATMEL_AT76C651=m +CONFIG_DVB_VES1820=m +CONFIG_DVB_TDA10021=m +CONFIG_DVB_STV0297=m + +# +# ATSC (North American/Korean Terresterial DTV) frontends +# +CONFIG_DVB_NXT2002=m +CONFIG_DVB_OR51211=m +CONFIG_DVB_OR51132=m +CONFIG_VIDEO_SAA7146=m +CONFIG_VIDEO_SAA7146_VV=m +CONFIG_VIDEO_VIDEOBUF=m +CONFIG_VIDEO_TUNER=m +CONFIG_VIDEO_BUF=m +CONFIG_VIDEO_BUF_DVB=m +CONFIG_VIDEO_BTCX=m +CONFIG_VIDEO_IR=m +CONFIG_VIDEO_TVEEPROM=m + +# +# Graphics support +# +CONFIG_FB=y +CONFIG_FB_CFB_FILLRECT=y +CONFIG_FB_CFB_COPYAREA=y +CONFIG_FB_CFB_IMAGEBLIT=y +CONFIG_FB_SOFT_CURSOR=y +# CONFIG_FB_MACMODES is not set +CONFIG_FB_MODE_HELPERS=y +CONFIG_FB_TILEBLITTING=y +CONFIG_FB_CIRRUS=m +# CONFIG_FB_PM2 is not set +# CONFIG_FB_CYBER2000 is not set +# CONFIG_FB_ASILIANT is not set +# CONFIG_FB_IMSTT is not set +CONFIG_FB_VGA16=m +CONFIG_FB_VESA=y +CONFIG_VIDEO_SELECT=y +# CONFIG_FB_HGA is not set +# CONFIG_FB_NVIDIA is not set +CONFIG_FB_RIVA=m +# CONFIG_FB_RIVA_I2C is not set +# CONFIG_FB_RIVA_DEBUG is not set +CONFIG_FB_MATROX=m +CONFIG_FB_MATROX_MILLENIUM=y +CONFIG_FB_MATROX_MYSTIQUE=y +CONFIG_FB_MATROX_G=y +CONFIG_FB_MATROX_I2C=m +CONFIG_FB_MATROX_MAVEN=m +CONFIG_FB_MATROX_MULTIHEAD=y +# CONFIG_FB_RADEON_OLD is not set +CONFIG_FB_RADEON=m +CONFIG_FB_RADEON_I2C=y +# CONFIG_FB_RADEON_DEBUG is not set +CONFIG_FB_ATY128=m +CONFIG_FB_ATY=m +CONFIG_FB_ATY_CT=y +CONFIG_FB_ATY_GENERIC_LCD=y +# CONFIG_FB_ATY_XL_INIT is not set +CONFIG_FB_ATY_GX=y +CONFIG_FB_SAVAGE=m +CONFIG_FB_SAVAGE_I2C=y +CONFIG_FB_SAVAGE_ACCEL=y +# CONFIG_FB_SIS is not set +CONFIG_FB_NEOMAGIC=m +CONFIG_FB_KYRO=m +CONFIG_FB_3DFX=m +CONFIG_FB_3DFX_ACCEL=y +CONFIG_FB_VOODOO1=m +CONFIG_FB_TRIDENT=m +CONFIG_FB_TRIDENT_ACCEL=y +# CONFIG_FB_PM3 is not set +# CONFIG_FB_GEODE is not set +# CONFIG_FB_S1D13XXX is not set +# CONFIG_FB_VIRTUAL is not set + +# +# Console display driver support +# +CONFIG_VGA_CONSOLE=y +CONFIG_DUMMY_CONSOLE=y +CONFIG_FRAMEBUFFER_CONSOLE=y +# CONFIG_FONTS is not set +CONFIG_FONT_8x8=y +CONFIG_FONT_8x16=y + +# +# Logo configuration +# +CONFIG_LOGO=y +# CONFIG_LOGO_LINUX_MONO is not set +# CONFIG_LOGO_LINUX_VGA16 is not set +CONFIG_LOGO_LINUX_CLUT224=y +CONFIG_BACKLIGHT_LCD_SUPPORT=y +CONFIG_BACKLIGHT_CLASS_DEVICE=m +CONFIG_BACKLIGHT_DEVICE=y +CONFIG_LCD_CLASS_DEVICE=m +CONFIG_LCD_DEVICE=y + +# +# Sound +# +CONFIG_SOUND=m + +# +# Advanced Linux Sound Architecture +# +CONFIG_SND=m +CONFIG_SND_TIMER=m +CONFIG_SND_PCM=m +CONFIG_SND_HWDEP=m +CONFIG_SND_RAWMIDI=m +CONFIG_SND_SEQUENCER=m +CONFIG_SND_SEQ_DUMMY=m +CONFIG_SND_OSSEMUL=y +CONFIG_SND_MIXER_OSS=m +CONFIG_SND_PCM_OSS=m +CONFIG_SND_SEQUENCER_OSS=y +CONFIG_SND_RTCTIMER=m +# CONFIG_SND_VERBOSE_PRINTK is not set +# CONFIG_SND_DEBUG is not set + +# +# Generic devices +# +CONFIG_SND_MPU401_UART=m +CONFIG_SND_OPL3_LIB=m +CONFIG_SND_VX_LIB=m +CONFIG_SND_DUMMY=m +CONFIG_SND_VIRMIDI=m +CONFIG_SND_MTPAV=m +# CONFIG_SND_SERIAL_U16550 is not set +CONFIG_SND_MPU401=m + +# +# PCI devices +# +CONFIG_SND_AC97_CODEC=m +CONFIG_SND_ALI5451=m +CONFIG_SND_ATIIXP=m +CONFIG_SND_ATIIXP_MODEM=m +CONFIG_SND_AU8810=m +CONFIG_SND_AU8820=m +CONFIG_SND_AU8830=m +CONFIG_SND_AZT3328=m +CONFIG_SND_BT87X=m +# CONFIG_SND_BT87X_OVERCLOCK is not set +CONFIG_SND_CS46XX=m +CONFIG_SND_CS46XX_NEW_DSP=y +CONFIG_SND_CS4281=m +CONFIG_SND_EMU10K1=m +CONFIG_SND_EMU10K1X=m +CONFIG_SND_CA0106=m +CONFIG_SND_KORG1212=m +CONFIG_SND_MIXART=m +CONFIG_SND_NM256=m +CONFIG_SND_RME32=m +CONFIG_SND_RME96=m +CONFIG_SND_RME9652=m +CONFIG_SND_HDSP=m +CONFIG_SND_TRIDENT=m +CONFIG_SND_YMFPCI=m +CONFIG_SND_ALS4000=m +CONFIG_SND_CMIPCI=m +CONFIG_SND_ENS1370=m +CONFIG_SND_ENS1371=m +CONFIG_SND_ES1938=m +CONFIG_SND_ES1968=m +CONFIG_SND_MAESTRO3=m +CONFIG_SND_FM801=m +CONFIG_SND_FM801_TEA575X=m +CONFIG_SND_ICE1712=m +CONFIG_SND_ICE1724=m +CONFIG_SND_INTEL8X0=m +CONFIG_SND_INTEL8X0M=m +CONFIG_SND_SONICVIBES=m +CONFIG_SND_VIA82XX=m +CONFIG_SND_VIA82XX_MODEM=m +CONFIG_SND_VX222=m +CONFIG_SND_HDA_INTEL=m + +# +# USB devices +# +CONFIG_SND_USB_AUDIO=m +CONFIG_SND_USB_USX2Y=m + +# +# Open Sound System +# +# CONFIG_SOUND_PRIME is not set + +# +# USB support +# +CONFIG_USB_ARCH_HAS_HCD=y +CONFIG_USB_ARCH_HAS_OHCI=y +CONFIG_USB=y +# CONFIG_USB_DEBUG is not set + +# +# Miscellaneous USB options +# +CONFIG_USB_DEVICEFS=y +# CONFIG_USB_BANDWIDTH is not set +# CONFIG_USB_DYNAMIC_MINORS is not set +# CONFIG_USB_OTG is not set + +# +# USB Host Controller Drivers +# +CONFIG_USB_EHCI_HCD=m +CONFIG_USB_EHCI_SPLIT_ISO=y +CONFIG_USB_EHCI_ROOT_HUB_TT=y +CONFIG_USB_OHCI_HCD=m +# CONFIG_USB_OHCI_BIG_ENDIAN is not set +CONFIG_USB_OHCI_LITTLE_ENDIAN=y +CONFIG_USB_UHCI_HCD=m +CONFIG_USB_SL811_HCD=m + +# +# USB Device Class drivers +# +# CONFIG_USB_AUDIO is not set + +# +# USB Bluetooth TTY can only be used with disabled Bluetooth subsystem +# +CONFIG_USB_MIDI=m +CONFIG_USB_ACM=m +CONFIG_USB_PRINTER=m + +# +# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed; see USB_STORAGE Help for more information +# +CONFIG_USB_STORAGE=m +# CONFIG_USB_STORAGE_DEBUG is not set +CONFIG_USB_STORAGE_DATAFAB=y +CONFIG_USB_STORAGE_FREECOM=y +CONFIG_USB_STORAGE_ISD200=y +CONFIG_USB_STORAGE_DPCM=y +CONFIG_USB_STORAGE_USBAT=y +CONFIG_USB_STORAGE_SDDR09=y +CONFIG_USB_STORAGE_SDDR55=y +CONFIG_USB_STORAGE_JUMPSHOT=y + +# +# USB Input Devices +# +CONFIG_USB_HID=y +CONFIG_USB_HIDINPUT=y +CONFIG_HID_FF=y +CONFIG_HID_PID=y +CONFIG_LOGITECH_FF=y +CONFIG_THRUSTMASTER_FF=y +CONFIG_USB_HIDDEV=y +CONFIG_USB_AIPTEK=m +CONFIG_USB_WACOM=m +CONFIG_USB_KBTAB=m +CONFIG_USB_POWERMATE=m +CONFIG_USB_MTOUCH=m +CONFIG_USB_EGALAX=m +CONFIG_USB_XPAD=m +CONFIG_USB_ATI_REMOTE=m + +# +# USB Imaging devices +# +CONFIG_USB_MDC800=m +CONFIG_USB_MICROTEK=m + +# +# USB Multimedia devices +# +CONFIG_USB_DABUSB=m +CONFIG_USB_VICAM=m +CONFIG_USB_DSBR=m +CONFIG_USB_IBMCAM=m +CONFIG_USB_KONICAWC=m +CONFIG_USB_OV511=m +CONFIG_USB_SE401=m +CONFIG_USB_SN9C102=m +CONFIG_USB_STV680=m +CONFIG_USB_W9968CF=m +CONFIG_USB_PWC=m + +# +# USB Network Adapters +# +CONFIG_USB_CATC=m +CONFIG_USB_KAWETH=m +CONFIG_USB_PEGASUS=m +CONFIG_USB_RTL8150=m +CONFIG_USB_USBNET=m + +# +# USB Host-to-Host Cables +# +CONFIG_USB_ALI_M5632=y +CONFIG_USB_AN2720=y +CONFIG_USB_BELKIN=y +CONFIG_USB_GENESYS=y +CONFIG_USB_NET1080=y +CONFIG_USB_PL2301=y +CONFIG_USB_KC2190=y + +# +# Intelligent USB Devices/Gadgets +# +CONFIG_USB_ARMLINUX=y +CONFIG_USB_EPSON2888=y +CONFIG_USB_ZAURUS=y +CONFIG_USB_CDCETHER=y + +# +# USB Network Adapters +# +CONFIG_USB_AX8817X=y +CONFIG_USB_ZD1201=m +CONFIG_USB_MON=m + +# +# USB port drivers +# +CONFIG_USB_USS720=m + +# +# USB Serial Converter support +# +CONFIG_USB_SERIAL=m +CONFIG_USB_SERIAL_GENERIC=y +CONFIG_USB_SERIAL_AIRPRIME=m +CONFIG_USB_SERIAL_BELKIN=m +CONFIG_USB_SERIAL_WHITEHEAT=m +CONFIG_USB_SERIAL_DIGI_ACCELEPORT=m +CONFIG_USB_SERIAL_CP2101=m +CONFIG_USB_SERIAL_CYPRESS_M8=m +CONFIG_USB_SERIAL_EMPEG=m +CONFIG_USB_SERIAL_FTDI_SIO=m +CONFIG_USB_SERIAL_VISOR=m +CONFIG_USB_SERIAL_IPAQ=m +CONFIG_USB_SERIAL_IR=m +CONFIG_USB_SERIAL_EDGEPORT=m +CONFIG_USB_SERIAL_EDGEPORT_TI=m +CONFIG_USB_SERIAL_GARMIN=m +CONFIG_USB_SERIAL_IPW=m +CONFIG_USB_SERIAL_KEYSPAN_PDA=m +CONFIG_USB_SERIAL_KEYSPAN=m +CONFIG_USB_SERIAL_KEYSPAN_MPR=y +CONFIG_USB_SERIAL_KEYSPAN_USA28=y +CONFIG_USB_SERIAL_KEYSPAN_USA28X=y +CONFIG_USB_SERIAL_KEYSPAN_USA28XA=y +CONFIG_USB_SERIAL_KEYSPAN_USA28XB=y +CONFIG_USB_SERIAL_KEYSPAN_USA19=y +CONFIG_USB_SERIAL_KEYSPAN_USA18X=y +CONFIG_USB_SERIAL_KEYSPAN_USA19W=y +CONFIG_USB_SERIAL_KEYSPAN_USA19QW=y +CONFIG_USB_SERIAL_KEYSPAN_USA19QI=y +CONFIG_USB_SERIAL_KEYSPAN_USA49W=y +CONFIG_USB_SERIAL_KEYSPAN_USA49WLC=y +CONFIG_USB_SERIAL_KLSI=m +CONFIG_USB_SERIAL_KOBIL_SCT=m +CONFIG_USB_SERIAL_MCT_U232=m +CONFIG_USB_SERIAL_PL2303=m +CONFIG_USB_SERIAL_HP4X=m +CONFIG_USB_SERIAL_SAFE=m +CONFIG_USB_SERIAL_SAFE_PADDED=y +CONFIG_USB_SERIAL_TI=m +CONFIG_USB_SERIAL_CYBERJACK=m +CONFIG_USB_SERIAL_XIRCOM=m +CONFIG_USB_SERIAL_OMNINET=m +CONFIG_USB_EZUSB=y + +# +# USB Miscellaneous drivers +# +CONFIG_USB_EMI62=m +# CONFIG_USB_EMI26 is not set +CONFIG_USB_AUERSWALD=m +CONFIG_USB_RIO500=m +CONFIG_USB_LEGOTOWER=m +CONFIG_USB_LCD=m +CONFIG_USB_LED=m +# CONFIG_USB_CYTHERM is not set +CONFIG_USB_PHIDGETKIT=m +CONFIG_USB_PHIDGETSERVO=m +CONFIG_USB_IDMOUSE=m +CONFIG_USB_SISUSBVGA=m +CONFIG_USB_TEST=m + +# +# USB ATM/DSL drivers +# +CONFIG_USB_ATM=m +CONFIG_USB_SPEEDTOUCH=m + +# +# USB Gadget Support +# +# CONFIG_USB_GADGET is not set + +# +# MMC/SD Card support +# +CONFIG_MMC=m +# CONFIG_MMC_DEBUG is not set +CONFIG_MMC_BLOCK=m +CONFIG_MMC_WBSD=m + +# +# InfiniBand support +# +CONFIG_INFINIBAND=m +CONFIG_INFINIBAND_MTHCA=m +# CONFIG_INFINIBAND_MTHCA_DEBUG is not set +CONFIG_INFINIBAND_IPOIB=m +# CONFIG_INFINIBAND_IPOIB_DEBUG is not set + +# +# Firmware Drivers +# + +# +# File systems +# +CONFIG_EXT2_FS=y +CONFIG_EXT2_FS_XATTR=y +CONFIG_EXT2_FS_POSIX_ACL=y +CONFIG_EXT2_FS_SECURITY=y +CONFIG_EXT3_FS=m +CONFIG_EXT3_FS_XATTR=y +CONFIG_EXT3_FS_POSIX_ACL=y +CONFIG_EXT3_FS_SECURITY=y +CONFIG_JBD=m +# CONFIG_JBD_DEBUG is not set +CONFIG_FS_MBCACHE=y +CONFIG_REISERFS_FS=m +# CONFIG_REISERFS_CHECK is not set +CONFIG_REISERFS_PROC_INFO=y +CONFIG_REISERFS_FS_XATTR=y +CONFIG_REISERFS_FS_POSIX_ACL=y +CONFIG_REISERFS_FS_SECURITY=y +CONFIG_JFS_FS=m +CONFIG_JFS_POSIX_ACL=y +CONFIG_JFS_SECURITY=y +# CONFIG_JFS_DEBUG is not set +# CONFIG_JFS_STATISTICS is not set +CONFIG_FS_POSIX_ACL=y + +# +# XFS support +# +CONFIG_XFS_FS=m +CONFIG_XFS_EXPORT=y +# CONFIG_XFS_RT is not set +CONFIG_XFS_QUOTA=y +CONFIG_XFS_SECURITY=y +CONFIG_XFS_POSIX_ACL=y +CONFIG_MINIX_FS=m +CONFIG_ROMFS_FS=m +CONFIG_QUOTA=y +# CONFIG_QFMT_V1 is not set +CONFIG_QFMT_V2=y +CONFIG_QUOTACTL=y +CONFIG_DNOTIFY=y +CONFIG_AUTOFS_FS=m +CONFIG_AUTOFS4_FS=m + +# +# CD-ROM/DVD Filesystems +# +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_ZISOFS_FS=y +CONFIG_UDF_FS=m +CONFIG_UDF_NLS=y + +# +# DOS/FAT/NT Filesystems +# +CONFIG_FAT_FS=m +CONFIG_MSDOS_FS=m +CONFIG_VFAT_FS=m +CONFIG_FAT_DEFAULT_CODEPAGE=437 +CONFIG_FAT_DEFAULT_IOCHARSET="ascii" +# CONFIG_NTFS_FS is not set + +# +# Pseudo filesystems +# +CONFIG_PROC_FS=y +CONFIG_PROC_KCORE=y +CONFIG_SYSFS=y +# CONFIG_DEVFS_FS is not set +CONFIG_DEVPTS_FS_XATTR=y +CONFIG_DEVPTS_FS_SECURITY=y +CONFIG_TMPFS=y +CONFIG_TMPFS_XATTR=y +CONFIG_TMPFS_SECURITY=y +# CONFIG_HUGETLB_PAGE is not set +CONFIG_RAMFS=y + +# +# Miscellaneous filesystems +# +# CONFIG_ADFS_FS is not set +CONFIG_AFFS_FS=m +CONFIG_HFS_FS=m +CONFIG_HFSPLUS_FS=m +CONFIG_BEFS_FS=m +# CONFIG_BEFS_DEBUG is not set +CONFIG_BFS_FS=m +CONFIG_EFS_FS=m +# CONFIG_JFFS_FS is not set +CONFIG_JFFS2_FS=m +CONFIG_JFFS2_FS_DEBUG=0 +CONFIG_JFFS2_FS_NAND=y +# CONFIG_JFFS2_FS_NOR_ECC is not set +# CONFIG_JFFS2_COMPRESSION_OPTIONS is not set +CONFIG_JFFS2_ZLIB=y +CONFIG_JFFS2_RTIME=y +# CONFIG_JFFS2_RUBIN is not set +CONFIG_CRAMFS=y +CONFIG_VXFS_FS=m +# CONFIG_HPFS_FS is not set +CONFIG_QNX4FS_FS=m +# CONFIG_QNX4FS_RW is not set +CONFIG_SYSV_FS=m +CONFIG_UFS_FS=m +# CONFIG_UFS_FS_WRITE is not set + +# +# Network File Systems +# +CONFIG_NFS_FS=m +CONFIG_NFS_V3=y +CONFIG_NFS_V4=y +CONFIG_NFS_DIRECTIO=y +CONFIG_NFSD=m +CONFIG_NFSD_V3=y +CONFIG_NFSD_V4=y +CONFIG_NFSD_TCP=y +CONFIG_LOCKD=m +CONFIG_LOCKD_V4=y +CONFIG_EXPORTFS=m +CONFIG_SUNRPC=m +CONFIG_SUNRPC_GSS=m +CONFIG_RPCSEC_GSS_KRB5=m +CONFIG_RPCSEC_GSS_SPKM3=m +CONFIG_SMB_FS=m +# CONFIG_SMB_NLS_DEFAULT is not set +CONFIG_CIFS=m +# CONFIG_CIFS_STATS is not set +CONFIG_CIFS_XATTR=y +CONFIG_CIFS_POSIX=y +# CONFIG_CIFS_EXPERIMENTAL is not set +CONFIG_NCP_FS=m +CONFIG_NCPFS_PACKET_SIGNING=y +CONFIG_NCPFS_IOCTL_LOCKING=y +CONFIG_NCPFS_STRONG=y +CONFIG_NCPFS_NFS_NS=y +CONFIG_NCPFS_OS2_NS=y +CONFIG_NCPFS_SMALLDOS=y +CONFIG_NCPFS_NLS=y +CONFIG_NCPFS_EXTRAS=y +# CONFIG_CODA_FS is not set +# CONFIG_AFS_FS is not set + +# +# Partition Types +# +CONFIG_PARTITION_ADVANCED=y +# CONFIG_ACORN_PARTITION is not set +CONFIG_OSF_PARTITION=y +CONFIG_AMIGA_PARTITION=y +# CONFIG_ATARI_PARTITION is not set +CONFIG_MAC_PARTITION=y +CONFIG_MSDOS_PARTITION=y +CONFIG_BSD_DISKLABEL=y +CONFIG_MINIX_SUBPARTITION=y +CONFIG_SOLARIS_X86_PARTITION=y +CONFIG_UNIXWARE_DISKLABEL=y +# CONFIG_LDM_PARTITION is not set +CONFIG_SGI_PARTITION=y +# CONFIG_ULTRIX_PARTITION is not set +CONFIG_SUN_PARTITION=y +CONFIG_EFI_PARTITION=y + +# +# Native Language Support +# +CONFIG_NLS=y +CONFIG_NLS_DEFAULT="utf8" +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_CODEPAGE_737=m +CONFIG_NLS_CODEPAGE_775=m +CONFIG_NLS_CODEPAGE_850=m +CONFIG_NLS_CODEPAGE_852=m +CONFIG_NLS_CODEPAGE_855=m +CONFIG_NLS_CODEPAGE_857=m +CONFIG_NLS_CODEPAGE_860=m +CONFIG_NLS_CODEPAGE_861=m +CONFIG_NLS_CODEPAGE_862=m +CONFIG_NLS_CODEPAGE_863=m +CONFIG_NLS_CODEPAGE_864=m +CONFIG_NLS_CODEPAGE_865=m +CONFIG_NLS_CODEPAGE_866=m +CONFIG_NLS_CODEPAGE_869=m +CONFIG_NLS_CODEPAGE_936=m +CONFIG_NLS_CODEPAGE_950=m +CONFIG_NLS_CODEPAGE_932=m +CONFIG_NLS_CODEPAGE_949=m +CONFIG_NLS_CODEPAGE_874=m +CONFIG_NLS_ISO8859_8=m +CONFIG_NLS_CODEPAGE_1250=m +CONFIG_NLS_CODEPAGE_1251=m +CONFIG_NLS_ASCII=y +CONFIG_NLS_ISO8859_1=m +CONFIG_NLS_ISO8859_2=m +CONFIG_NLS_ISO8859_3=m +CONFIG_NLS_ISO8859_4=m +CONFIG_NLS_ISO8859_5=m +CONFIG_NLS_ISO8859_6=m +CONFIG_NLS_ISO8859_7=m +CONFIG_NLS_ISO8859_9=m +CONFIG_NLS_ISO8859_13=m +CONFIG_NLS_ISO8859_14=m +CONFIG_NLS_ISO8859_15=m +CONFIG_NLS_KOI8_R=m +CONFIG_NLS_KOI8_U=m +CONFIG_NLS_UTF8=m + +# +# Profiling support +# +# CONFIG_PROFILING is not set + +# +# Kernel hacking +# +# CONFIG_PRINTK_TIME is not set +CONFIG_DEBUG_KERNEL=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_LOG_BUF_SHIFT=15 +# CONFIG_SCHEDSTATS is not set +# CONFIG_DEBUG_SLAB is not set +# CONFIG_DEBUG_SPINLOCK is not set +# CONFIG_DEBUG_SPINLOCK_SLEEP is not set +# CONFIG_DEBUG_KOBJECT is not set +# CONFIG_DEBUG_FS is not set +# CONFIG_INIT_DEBUG is not set +# CONFIG_KPROBES is not set + +# +# Security options +# +CONFIG_KEYS=y +CONFIG_KEYS_DEBUG_PROC_KEYS=y +CONFIG_SECURITY=y +CONFIG_SECURITY_NETWORK=y +CONFIG_SECURITY_CAPABILITIES=y +# CONFIG_SECURITY_ROOTPLUG is not set +# CONFIG_SECURITY_SECLVL is not set +CONFIG_SECURITY_SELINUX=y +CONFIG_SECURITY_SELINUX_BOOTPARAM=y +CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=1 +CONFIG_SECURITY_SELINUX_DISABLE=y +CONFIG_SECURITY_SELINUX_DEVELOP=y +CONFIG_SECURITY_SELINUX_AVC_STATS=y +CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1 + +# +# Cryptographic options +# +CONFIG_CRYPTO=y +CONFIG_CRYPTO_HMAC=y +CONFIG_CRYPTO_NULL=m +CONFIG_CRYPTO_MD4=m +CONFIG_CRYPTO_MD5=m +CONFIG_CRYPTO_SHA1=y +CONFIG_CRYPTO_SHA256=m +CONFIG_CRYPTO_SHA512=m +CONFIG_CRYPTO_WP512=m +CONFIG_CRYPTO_TGR192=m +CONFIG_CRYPTO_DES=m +CONFIG_CRYPTO_BLOWFISH=m +CONFIG_CRYPTO_TWOFISH=m +CONFIG_CRYPTO_SERPENT=m +CONFIG_CRYPTO_AES=m +CONFIG_CRYPTO_CAST5=m +CONFIG_CRYPTO_CAST6=m +CONFIG_CRYPTO_TEA=m +CONFIG_CRYPTO_ARC4=m +CONFIG_CRYPTO_KHAZAD=m +CONFIG_CRYPTO_ANUBIS=m +CONFIG_CRYPTO_DEFLATE=m +CONFIG_CRYPTO_MICHAEL_MIC=m +CONFIG_CRYPTO_CRC32C=m +# CONFIG_CRYPTO_TEST is not set + +# +# Hardware crypto devices +# +CONFIG_XEN=y +CONFIG_NO_IDLE_HZ=y + +# +# XEN +# +CONFIG_XEN_PRIVILEGED_GUEST=y +# CONFIG_XEN_UNPRIVILEGED_GUEST is not set +CONFIG_XEN_PHYSDEV_ACCESS=y +CONFIG_XEN_BLKDEV_BACKEND=y +# CONFIG_XEN_BLKDEV_TAP_BE is not set +CONFIG_XEN_NETDEV_BACKEND=y +# CONFIG_XEN_NETDEV_PIPELINED_TRANSMITTER is not set +# CONFIG_XEN_TPMDEV_BACKEND is not set +CONFIG_XEN_BLKDEV_FRONTEND=y +CONFIG_XEN_NETDEV_FRONTEND=y +# CONFIG_XEN_BLKDEV_TAP is not set +# CONFIG_XEN_TPMDEV_FRONTEND is not set +# CONFIG_XEN_SHADOW_MODE is not set +CONFIG_XEN_SCRUB_PAGES=y +CONFIG_XEN_DISABLE_SERIAL=y +CONFIG_HAVE_ARCH_ALLOC_SKB=y +CONFIG_HAVE_ARCH_DEV_ALLOC_SKB=y + +# +# Library routines +# +CONFIG_CRC_CCITT=m +CONFIG_CRC32=y +CONFIG_LIBCRC32C=m +CONFIG_ZLIB_INFLATE=y +CONFIG_ZLIB_DEFLATE=m diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/Kconfig --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/Kconfig Mon Jan 30 17:18:27 2006 @@ -0,0 +1,1331 @@ +# +# For a description of the syntax of this configuration file, +# see Documentation/kbuild/kconfig-language.txt. +# + +mainmenu "Linux Kernel Configuration" + +config X86 + bool + default y + help + This is Linux's home port. Linux was originally native to the Intel + 386, and runs on all the later x86 processors including the Intel + 486, 586, Pentiums, and various instruction-set-compatible chips by + AMD, Cyrix, and others. + +config MMU + bool + default y + +config SBUS + bool + +config UID16 + bool + default y + +config GENERIC_ISA_DMA + bool + default y + +config GENERIC_IOMAP + bool + default y + +source "init/Kconfig" + +menu "Processor type and features" + +choice + prompt "Subarchitecture Type" + default X86_PC + +config X86_PC + bool "PC-compatible" + help + Choose this option if your computer is a standard PC or compatible. + +config X86_XEN + bool "Xen-compatible" + select X86_UP_APIC if !SMP && XEN_PRIVILEGED_GUEST + select X86_UP_IOAPIC if !SMP && XEN_PRIVILEGED_GUEST + select SWIOTLB if XEN_PHYSDEV_ACCESS + help + Choose this option is you plan to run this kernel on top of Xen + Hypervisor. + +config X86_ELAN + bool "AMD Elan" + help + Select this for an AMD Elan processor. + + Do not use this option for K6/Athlon/Opteron processors! + + If unsure, choose "PC-compatible" instead. + +config X86_VOYAGER + bool "Voyager (NCR)" + help + Voyager is an MCA-based 32-way capable SMP architecture proprietary + to NCR Corp. Machine classes 345x/35xx/4100/51xx are Voyager-based. + + *** WARNING *** + + If you do not specifically know you have a Voyager based machine, + say N here, otherwise the kernel you build will not be bootable. + +config X86_NUMAQ + bool "NUMAQ (IBM/Sequent)" + select DISCONTIGMEM + select NUMA + help + This option is used for getting Linux to run on a (IBM/Sequent) NUMA + multiquad box. This changes the way that processors are bootstrapped, + and uses Clustered Logical APIC addressing mode instead of Flat Logical. + You will need a new lynxer.elf file to flash your firmware with - send + email to <Martin.Bligh@xxxxxxxxxx>. + +config X86_SUMMIT + bool "Summit/EXA (IBM x440)" + depends on SMP + help + This option is needed for IBM systems that use the Summit/EXA chipset. + In particular, it is needed for the x440. + + If you don't have one of these computers, you should say N here. + +config X86_BIGSMP + bool "Support for other sub-arch SMP systems with more than 8 CPUs" + depends on SMP + help + This option is needed for the systems that have more than 8 CPUs + and if the system is not of any sub-arch type above. + + If you don't have such a system, you should say N here. + +config X86_VISWS + bool "SGI 320/540 (Visual Workstation)" + help + The SGI Visual Workstation series is an IA32-based workstation + based on SGI systems chips with some legacy PC hardware attached. + + Say Y here to create a kernel to run on the SGI 320 or 540. + + A kernel compiled for the Visual Workstation will not run on PCs + and vice versa. See <file:Documentation/sgi-visws.txt> for details. + +config X86_GENERICARCH + bool "Generic architecture (Summit, bigsmp, ES7000, default)" + depends on SMP + help + This option compiles in the Summit, bigsmp, ES7000, default subarchitectures. + It is intended for a generic binary kernel. + +config X86_ES7000 + bool "Support for Unisys ES7000 IA32 series" + depends on SMP + help + Support for Unisys ES7000 systems. Say 'Y' here if this kernel is + supposed to run on an IA32-based Unisys ES7000 system. + Only choose this option if you have such a system, otherwise you + should say N here. + +endchoice + +config ACPI_SRAT + bool + default y + depends on NUMA && (X86_SUMMIT || X86_GENERICARCH) + +config X86_SUMMIT_NUMA + bool + default y + depends on NUMA && (X86_SUMMIT || X86_GENERICARCH) + +config X86_CYCLONE_TIMER + bool + default y + depends on X86_SUMMIT || X86_GENERICARCH + +config ES7000_CLUSTERED_APIC + bool + default y + depends on SMP && X86_ES7000 && MPENTIUMIII + +if !X86_ELAN + +choice + prompt "Processor family" + default M686 + +config M386 + bool "386" + ---help--- + This is the processor type of your CPU. This information is used for + optimizing purposes. In order to compile a kernel that can run on + all x86 CPU types (albeit not optimally fast), you can specify + "386" here. + + The kernel will not necessarily run on earlier architectures than + the one you have chosen, e.g. a Pentium optimized kernel will run on + a PPro, but not necessarily on a i486. + + Here are the settings recommended for greatest speed: + - "386" for the AMD/Cyrix/Intel 386DX/DXL/SL/SLC/SX, Cyrix/TI + 486DLC/DLC2, UMC 486SX-S and NexGen Nx586. Only "386" kernels + will run on a 386 class machine. + - "486" for the AMD/Cyrix/IBM/Intel 486DX/DX2/DX4 or + SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or U5S. + - "586" for generic Pentium CPUs lacking the TSC + (time stamp counter) register. + - "Pentium-Classic" for the Intel Pentium. + - "Pentium-MMX" for the Intel Pentium MMX. + - "Pentium-Pro" for the Intel Pentium Pro. + - "Pentium-II" for the Intel Pentium II or pre-Coppermine Celeron. + - "Pentium-III" for the Intel Pentium III or Coppermine Celeron. + - "Pentium-4" for the Intel Pentium 4 or P4-based Celeron. + - "K6" for the AMD K6, K6-II and K6-III (aka K6-3D). + - "Athlon" for the AMD K7 family (Athlon/Duron/Thunderbird). + - "Crusoe" for the Transmeta Crusoe series. + - "Efficeon" for the Transmeta Efficeon series. + - "Winchip-C6" for original IDT Winchip. + - "Winchip-2" for IDT Winchip 2. + - "Winchip-2A" for IDT Winchips with 3dNow! capabilities. + - "GeodeGX1" for Geode GX1 (Cyrix MediaGX). + - "CyrixIII/VIA C3" for VIA Cyrix III or VIA C3. + - "VIA C3-2 for VIA C3-2 "Nehemiah" (model 9 and above). + + If you don't know what to do, choose "386". + +config M486 + bool "486" + help + Select this for a 486 series processor, either Intel or one of the + compatible processors from AMD, Cyrix, IBM, or Intel. Includes DX, + DX2, and DX4 variants; also SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or + U5S. + +config M586 + bool "586/K5/5x86/6x86/6x86MX" + help + Select this for an 586 or 686 series processor such as the AMD K5, + the Cyrix 5x86, 6x86 and 6x86MX. This choice does not + assume the RDTSC (Read Time Stamp Counter) instruction. + +config M586TSC + bool "Pentium-Classic" + help + Select this for a Pentium Classic processor with the RDTSC (Read + Time Stamp Counter) instruction for benchmarking. + +config M586MMX + bool "Pentium-MMX" + help + Select this for a Pentium with the MMX graphics/multimedia + extended instructions. + +config M686 + bool "Pentium-Pro" + help + Select this for Intel Pentium Pro chips. This enables the use of + Pentium Pro extended instructions, and disables the init-time guard + against the f00f bug found in earlier Pentiums. + +config MPENTIUMII + bool "Pentium-II/Celeron(pre-Coppermine)" + help + Select this for Intel chips based on the Pentium-II and + pre-Coppermine Celeron core. This option enables an unaligned + copy optimization, compiles the kernel with optimization flags + tailored for the chip, and applies any applicable Pentium Pro + optimizations. + +config MPENTIUMIII + bool "Pentium-III/Celeron(Coppermine)/Pentium-III Xeon" + help + Select this for Intel chips based on the Pentium-III and + Celeron-Coppermine core. This option enables use of some + extended prefetch instructions in addition to the Pentium II + extensions. + +config MPENTIUMM + bool "Pentium M" + help + Select this for Intel Pentium M (not Pentium-4 M) + notebook chips. + +config MPENTIUM4 + bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/Xeon" + help + Select this for Intel Pentium 4 chips. This includes the + Pentium 4, P4-based Celeron and Xeon, and Pentium-4 M + (not Pentium M) chips. This option enables compile flags + optimized for the chip, uses the correct cache shift, and + applies any applicable Pentium III optimizations. + +config MK6 + bool "K6/K6-II/K6-III" + help + Select this for an AMD K6-family processor. Enables use of + some extended instructions, and passes appropriate optimization + flags to GCC. + +config MK7 + bool "Athlon/Duron/K7" + help + Select this for an AMD Athlon K7-family processor. Enables use of + some extended instructions, and passes appropriate optimization + flags to GCC. + +config MK8 + bool "Opteron/Athlon64/Hammer/K8" + help + Select this for an AMD Opteron or Athlon64 Hammer-family processor. Enables + use of some extended instructions, and passes appropriate optimization + flags to GCC. + +config MCRUSOE + bool "Crusoe" + help + Select this for a Transmeta Crusoe processor. Treats the processor + like a 586 with TSC, and sets some GCC optimization flags (like a + Pentium Pro with no alignment requirements). + +config MEFFICEON + bool "Efficeon" + help + Select this for a Transmeta Efficeon processor. + +config MWINCHIPC6 + bool "Winchip-C6" + help + Select this for an IDT Winchip C6 chip. Linux and GCC + treat this chip as a 586TSC with some extended instructions + and alignment requirements. + +config MWINCHIP2 + bool "Winchip-2" + help + Select this for an IDT Winchip-2. Linux and GCC + treat this chip as a 586TSC with some extended instructions + and alignment requirements. + +config MWINCHIP3D + bool "Winchip-2A/Winchip-3" + help + Select this for an IDT Winchip-2A or 3. Linux and GCC + treat this chip as a 586TSC with some extended instructions + and alignment reqirements. Also enable out of order memory + stores for this CPU, which can increase performance of some + operations. + +config MGEODEGX1 + bool "GeodeGX1" + help + Select this for a Geode GX1 (Cyrix MediaGX) chip. + +config MCYRIXIII + bool "CyrixIII/VIA-C3" + help + Select this for a Cyrix III or C3 chip. Presently Linux and GCC + treat this chip as a generic 586. Whilst the CPU is 686 class, + it lacks the cmov extension which gcc assumes is present when + generating 686 code. + Note that Nehemiah (Model 9) and above will not boot with this + kernel due to them lacking the 3DNow! instructions used in earlier + incarnations of the CPU. + +config MVIAC3_2 + bool "VIA C3-2 (Nehemiah)" + help + Select this for a VIA C3 "Nehemiah". Selecting this enables usage + of SSE and tells gcc to treat the CPU as a 686. + Note, this kernel will not boot on older (pre model 9) C3s. + +endchoice + +config X86_GENERIC + bool "Generic x86 support" + help + Instead of just including optimizations for the selected + x86 variant (e.g. PII, Crusoe or Athlon), include some more + generic optimizations as well. This will make the kernel + perform better on x86 CPUs other than that selected. + + This is really intended for distributors who need more + generic optimizations. + +endif + +# +# Define implied options from the CPU selection here +# +config X86_CMPXCHG + bool + depends on !M386 + default y + +config X86_XADD + bool + depends on !M386 + default y + +config X86_L1_CACHE_SHIFT + int + default "7" if MPENTIUM4 || X86_GENERIC + default "4" if X86_ELAN || M486 || M386 + default "5" if MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODEGX1 + default "6" if MK7 || MK8 || MPENTIUMM + +config RWSEM_GENERIC_SPINLOCK + bool + depends on M386 + default y + +config RWSEM_XCHGADD_ALGORITHM + bool + depends on !M386 + default y + +config GENERIC_CALIBRATE_DELAY + bool + default y + +config X86_PPRO_FENCE + bool + depends on M686 || M586MMX || M586TSC || M586 || M486 || M386 || MGEODEGX1 + default y + +config X86_F00F_BUG + bool + depends on M586MMX || M586TSC || M586 || M486 || M386 + default y + +config X86_WP_WORKS_OK + bool + depends on !M386 + default y + +config X86_INVLPG + bool + depends on !M386 + default y + +config X86_BSWAP + bool + depends on !M386 + default y + +config X86_POPAD_OK + bool + depends on !M386 + default y + +config X86_ALIGNMENT_16 + bool + depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII || X86_ELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1 + default y + +config X86_GOOD_APIC + bool + depends on MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || MK8 || MEFFICEON + default y + +config X86_INTEL_USERCOPY + bool + depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON + default y + +config X86_USE_PPRO_CHECKSUM + bool + depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON + default y + +config X86_USE_3DNOW + bool + depends on MCYRIXIII || MK7 + default y + +config X86_OOSTORE + bool + depends on (MWINCHIP3D || MWINCHIP2 || MWINCHIPC6) && MTRR + default y + +config HPET_TIMER + bool "HPET Timer Support" + depends on !X86_XEN + help + This enables the use of the HPET for the kernel's internal timer. + HPET is the next generation timer replacing legacy 8254s. + You can safely choose Y here. However, HPET will only be + activated if the platform and the BIOS support this feature. + Otherwise the 8254 will be used for timing services. + + Choose N to continue using the legacy 8254 timer. + +config HPET_EMULATE_RTC + bool "Provide RTC interrupt" + depends on HPET_TIMER && RTC=y + +config SMP + bool "Symmetric multi-processing support" + ---help--- + This enables support for systems with more than one CPU. If you have + a system with only one CPU, like most personal computers, say N. If + you have a system with more than one CPU, say Y. + + If you say N here, the kernel will run on single and multiprocessor + machines, but will use only one CPU of a multiprocessor machine. If + you say Y here, the kernel will run on many, but not all, + singleprocessor machines. On a singleprocessor machine, the kernel + will run faster if you say N here. + + Note that if you say Y here and choose architecture "586" or + "Pentium" under "Processor family", the kernel will not work on 486 + architectures. Similarly, multiprocessor kernels for the "PPro" + architecture may not work on all Pentium based boards. + + People using multiprocessor machines who say Y here should also say + Y to "Enhanced Real Time Clock Support", below. The "Advanced Power + Management" code will be disabled if you say Y here. + + See also the <file:Documentation/smp.txt>, + <file:Documentation/i386/IO-APIC.txt>, + <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO available at + <http://www.tldp.org/docs.html#howto>. + + If you don't know what to do here, say N. + +config SMP_ALTERNATIVES + bool "SMP alternatives support (EXPERIMENTAL)" + depends on SMP && EXPERIMENTAL + help + Try to reduce the overhead of running an SMP kernel on a uniprocessor + host slightly by replacing certain key instruction sequences + according to whether we currently have more than one CPU available. + This should provide a noticeable boost to performance when + running SMP kernels on UP machines, and have negligible impact + when running on an true SMP host. + + If unsure, say N. + +config NR_CPUS + int "Maximum number of CPUs (2-255)" + range 2 255 + depends on SMP + default "32" if X86_NUMAQ || X86_SUMMIT || X86_BIGSMP || X86_ES7000 + default "8" + help + This allows you to specify the maximum number of CPUs which this + kernel will support. The maximum supported value is 255 and the + minimum value which makes sense is 2. + + This is purely to save memory - each supported CPU adds + approximately eight kilobytes to the kernel image. + +config SCHED_SMT + bool "SMT (Hyperthreading) scheduler support" + depends on SMP && !X86_XEN + default off + help + SMT scheduler support improves the CPU scheduler's decision making + when dealing with Intel Pentium 4 chips with HyperThreading at a + cost of slightly increased overhead in some places. If unsure say + N here. + +config PREEMPT + bool "Preemptible Kernel" + depends on !X86_XEN + help + This option reduces the latency of the kernel when reacting to + real-time or interactive events by allowing a low priority process to + be preempted even if it is in kernel mode executing a system call. + This allows applications to run more reliably even when the system is + under load. + + Say Y here if you are building a kernel for a desktop, embedded + or real-time system. Say N if you are unsure. + +config PREEMPT_BKL + bool "Preempt The Big Kernel Lock" + depends on PREEMPT + default y + help + This option reduces the latency of the kernel by making the + big kernel lock preemptible. + + Say Y here if you are building a kernel for a desktop system. + Say N if you are unsure. + +config X86_UP_APIC + bool "Local APIC support on uniprocessors" + depends on !SMP && !(X86_VISWS || X86_VOYAGER || XEN_UNPRIVILEGED_GUEST) + help + A local APIC (Advanced Programmable Interrupt Controller) is an + integrated interrupt controller in the CPU. If you have a single-CPU + system which has a processor with a local APIC, you can say Y here to + enable and use it. If you say Y here even though your machine doesn't + have a local APIC, then the kernel will still run with no slowdown at + all. The local APIC supports CPU-generated self-interrupts (timer, + performance counters), and the NMI watchdog which detects hard + lockups. + +config X86_UP_IOAPIC + bool "IO-APIC support on uniprocessors" + depends on X86_UP_APIC + help + An IO-APIC (I/O Advanced Programmable Interrupt Controller) is an + SMP-capable replacement for PC-style interrupt controllers. Most + SMP systems and many recent uniprocessor systems have one. + + If you have a single-CPU system with an IO-APIC, you can say Y here + to use it. If you say Y here even though your machine doesn't have + an IO-APIC, then the kernel will still run with no slowdown at all. + +config X86_LOCAL_APIC + bool + depends on X86_UP_APIC || ((X86_VISWS || SMP) && !(X86_VOYAGER || XEN_UNPRIVILEGED_GUEST)) + default y + +config X86_IO_APIC + bool + depends on X86_UP_IOAPIC || (SMP && !(X86_VISWS || X86_VOYAGER || XEN_UNPRIVILEGED_GUEST)) + default y + +config X86_VISWS_APIC + bool + depends on X86_VISWS + default y + +config X86_TSC + bool + depends on (MWINCHIP3D || MWINCHIP2 || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MGEODEGX1) && !X86_NUMAQ && !X86_XEN + default y + +config X86_MCE + bool "Machine Check Exception" + depends on !(X86_VOYAGER || X86_XEN) + ---help--- + Machine Check Exception support allows the processor to notify the + kernel if it detects a problem (e.g. overheating, component failure). + The action the kernel takes depends on the severity of the problem, + ranging from a warning message on the console, to halting the machine. + Your processor must be a Pentium or newer to support this - check the + flags in /proc/cpuinfo for mce. Note that some older Pentium systems + have a design flaw which leads to false MCE events - hence MCE is + disabled on all P5 processors, unless explicitly enabled with "mce" + as a boot argument. Similarly, if MCE is built in and creates a + problem on some new non-standard machine, you can boot with "nomce" + to disable it. MCE support simply ignores non-MCE processors like + the 386 and 486, so nearly everyone can say Y here. + +config X86_MCE_NONFATAL + tristate "Check for non-fatal errors on AMD Athlon/Duron / Intel Pentium 4" + depends on X86_MCE + help + Enabling this feature starts a timer that triggers every 5 seconds which + will look at the machine check registers to see if anything happened. + Non-fatal problems automatically get corrected (but still logged). + Disable this if you don't want to see these messages. + Seeing the messages this option prints out may be indicative of dying hardware, + or out-of-spec (ie, overclocked) hardware. + This option only does something on certain CPUs. + (AMD Athlon/Duron and Intel Pentium 4) + +config X86_MCE_P4THERMAL + bool "check for P4 thermal throttling interrupt." + depends on X86_MCE && (X86_UP_APIC || SMP) && !X86_VISWS + help + Enabling this feature will cause a message to be printed when the P4 + enters thermal throttling. + +config TOSHIBA + tristate "Toshiba Laptop support" + ---help--- + This adds a driver to safely access the System Management Mode of + the CPU on Toshiba portables with a genuine Toshiba BIOS. It does + not work on models with a Phoenix BIOS. The System Management Mode + is used to set the BIOS and power saving options on Toshiba portables. + + For information on utilities to make use of this driver see the + Toshiba Linux utilities web site at: + <http://www.buzzard.org.uk/toshiba/>. + + Say Y if you intend to run this kernel on a Toshiba portable. + Say N otherwise. + +config I8K + tristate "Dell laptop support" + ---help--- + This adds a driver to safely access the System Management Mode + of the CPU on the Dell Inspiron 8000. The System Management Mode + is used to read cpu temperature and cooling fan status and to + control the fans on the I8K portables. + + This driver has been tested only on the Inspiron 8000 but it may + also work with other Dell laptops. You can force loading on other + models by passing the parameter `force=1' to the module. Use at + your own risk. + + For information on utilities to make use of this driver see the + I8K Linux utilities web site at: + <http://people.debian.org/~dz/i8k/> + + Say Y if you intend to run this kernel on a Dell Inspiron 8000. + Say N otherwise. + +config X86_REBOOTFIXUPS + bool "Enable X86 board specific fixups for reboot" + depends on X86 + default n + ---help--- + This enables chipset and/or board specific fixups to be done + in order to get reboot to work correctly. This is only needed on + some combinations of hardware and BIOS. The symptom, for which + this config is intended, is when reboot ends with a stalled/hung + system. + + Currently, the only fixup is for the Geode GX1/CS5530A/TROM2.1. + combination. + + Say Y if you want to enable the fixup. Currently, it's safe to + enable this option even if you don't need it. + Say N otherwise. + +config MICROCODE + tristate "/dev/cpu/microcode - Intel IA32 CPU microcode support" + depends on !XEN_UNPRIVILEGED_GUEST + ---help--- + If you say Y here and also to "/dev file system support" in the + 'File systems' section, you will be able to update the microcode on + Intel processors in the IA32 family, e.g. Pentium Pro, Pentium II, + Pentium III, Pentium 4, Xeon etc. You will obviously need the + actual microcode binary data itself which is not shipped with the + Linux kernel. + + For latest news and information on obtaining all the required + ingredients for this driver, check: + <http://www.urbanmyth.org/microcode/>. + + To compile this driver as a module, choose M here: the + module will be called microcode. + +config X86_MSR + tristate "/dev/cpu/*/msr - Model-specific register support" + depends on !X86_XEN + help + This device gives privileged processes access to the x86 + Model-Specific Registers (MSRs). It is a character device with + major 202 and minors 0 to 31 for /dev/cpu/0/msr to /dev/cpu/31/msr. + MSR accesses are directed to a specific CPU on multi-processor + systems. + +config X86_CPUID + tristate "/dev/cpu/*/cpuid - CPU information support" + help + This device gives processes access to the x86 CPUID instruction to + be executed on a specific processor. It is a character device + with major 203 and minors 0 to 31 for /dev/cpu/0/cpuid to + /dev/cpu/31/cpuid. + +config SWIOTLB + bool + default n + +source "drivers/firmware/Kconfig" + +choice + prompt "High Memory Support" + default NOHIGHMEM + +config NOHIGHMEM + bool "off" + ---help--- + Linux can use up to 64 Gigabytes of physical memory on x86 systems. + However, the address space of 32-bit x86 processors is only 4 + Gigabytes large. That means that, if you have a large amount of + physical memory, not all of it can be "permanently mapped" by the + kernel. The physical memory that's not permanently mapped is called + "high memory". + + If you are compiling a kernel which will never run on a machine with + more than 1 Gigabyte total physical RAM, answer "off" here (default + choice and suitable for most users). This will result in a "3GB/1GB" + split: 3GB are mapped so that each process sees a 3GB virtual memory + space and the remaining part of the 4GB virtual memory space is used + by the kernel to permanently map as much physical memory as + possible. + + If the machine has between 1 and 4 Gigabytes physical RAM, then + answer "4GB" here. + + If more than 4 Gigabytes is used then answer "64GB" here. This + selection turns Intel PAE (Physical Address Extension) mode on. + PAE implements 3-level paging on IA32 processors. PAE is fully + supported by Linux, PAE mode is implemented on all recent Intel + processors (Pentium Pro and better). NOTE: If you say "64GB" here, + then the kernel will not boot on CPUs that don't support PAE! + + The actual amount of total physical memory will either be + auto detected or can be forced by using a kernel command line option + such as "mem=256M". (Try "man bootparam" or see the documentation of + your boot loader (lilo or loadlin) about how to pass options to the + kernel at boot time.) + + If unsure, say "off". + +config HIGHMEM4G + bool "4GB" + help + Select this if you have a 32-bit processor and between 1 and 4 + gigabytes of physical RAM. + +config HIGHMEM64G + bool "64GB" + help + Select this if you have a 32-bit processor and more than 4 + gigabytes of physical RAM. + +endchoice + +config HIGHMEM + bool + depends on HIGHMEM64G || HIGHMEM4G + default y + +config X86_PAE + bool + depends on HIGHMEM64G + default y + +# Common NUMA Features +config NUMA + bool "Numa Memory Allocation and Scheduler Support" + depends on SMP && HIGHMEM64G && (X86_NUMAQ || X86_GENERICARCH || (X86_SUMMIT && ACPI)) + default n if X86_PC + default y if (X86_NUMAQ || X86_SUMMIT) + +# Need comments to help the hapless user trying to turn on NUMA support +comment "NUMA (NUMA-Q) requires SMP, 64GB highmem support" + depends on X86_NUMAQ && (!HIGHMEM64G || !SMP) + +comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI" + depends on X86_SUMMIT && (!HIGHMEM64G || !ACPI) + +config DISCONTIGMEM + bool + depends on NUMA + default y + +config HAVE_ARCH_BOOTMEM_NODE + bool + depends on NUMA + default y + +config HAVE_MEMORY_PRESENT + bool + depends on DISCONTIGMEM + default y + +config NEED_NODE_MEMMAP_SIZE + bool + depends on DISCONTIGMEM + default y + +config HIGHPTE + bool "Allocate 3rd-level pagetables from highmem" + depends on (HIGHMEM4G || HIGHMEM64G) && !X86_XEN + help + The VM uses one page table entry for each page of physical memory. + For systems with a lot of RAM, this can be wasteful of precious + low memory. Setting this option will put user-space page table + entries in high memory. + +config MATH_EMULATION + bool "Math emulation" + depends on !X86_XEN + ---help--- + Linux can emulate a math coprocessor (used for floating point + operations) if you don't have one. 486DX and Pentium processors have + a math coprocessor built in, 486SX and 386 do not, unless you added + a 487DX or 387, respectively. (The messages during boot time can + give you some hints here ["man dmesg"].) Everyone needs either a + coprocessor or this emulation. + + If you don't have a math coprocessor, you need to say Y here; if you + say Y here even though you have a coprocessor, the coprocessor will + be used nevertheless. (This behavior can be changed with the kernel + command line option "no387", which comes handy if your coprocessor + is broken. Try "man bootparam" or see the documentation of your boot + loader (lilo or loadlin) about how to pass options to the kernel at + boot time.) This means that it is a good idea to say Y here if you + intend to use this kernel on different machines. + + More information about the internals of the Linux math coprocessor + emulation can be found in <file:arch/i386/math-emu/README>. + + If you are not sure, say Y; apart from resulting in a 66 KB bigger + kernel, it won't hurt. + +config MTRR + bool "MTRR (Memory Type Range Register) support" + depends on !XEN_UNPRIVILEGED_GUEST + default y if X86_XEN + ---help--- + On Intel P6 family processors (Pentium Pro, Pentium II and later) + the Memory Type Range Registers (MTRRs) may be used to control + processor access to memory ranges. This is most useful if you have + a video (VGA) card on a PCI or AGP bus. Enabling write-combining + allows bus write transfers to be combined into a larger transfer + before bursting over the PCI/AGP bus. This can increase performance + of image write operations 2.5 times or more. Saying Y here creates a + /proc/mtrr file which may be used to manipulate your processor's + MTRRs. Typically the X server should use this. + + This code has a reasonably generic interface so that similar + control registers on other processors can be easily supported + as well: + + The Cyrix 6x86, 6x86MX and M II processors have Address Range + Registers (ARRs) which provide a similar functionality to MTRRs. For + these, the ARRs are used to emulate the MTRRs. + The AMD K6-2 (stepping 8 and above) and K6-3 processors have two + MTRRs. The Centaur C6 (WinChip) has 8 MCRs, allowing + write-combining. All of these processors are supported by this code + and it makes sense to say Y here if you have one of them. + + Saying Y here also fixes a problem with buggy SMP BIOSes which only + set the MTRRs for the boot CPU and not for the secondary CPUs. This + can lead to all sorts of problems, so it's good to say Y here. + + You can safely say Y even if your machine doesn't have MTRRs, you'll + just add about 9 KB to your kernel. + + See <file:Documentation/mtrr.txt> for more information. + +config EFI + bool "Boot from EFI support (EXPERIMENTAL)" + depends on ACPI && !X86_XEN + default n + ---help--- + This enables the the kernel to boot on EFI platforms using + system configuration information passed to it from the firmware. + This also enables the kernel to use any EFI runtime services that are + available (such as the EFI variable services). + + This option is only useful on systems that have EFI firmware + and will result in a kernel image that is ~8k larger. In addition, + you must use the latest ELILO loader available at + <http://elilo.sourceforge.net> in order to take advantage of + kernel initialization using EFI information (neither GRUB nor LILO know + anything about EFI). However, even with this option, the resultant + kernel should continue to boot on existing non-EFI platforms. + +config IRQBALANCE + bool "Enable kernel irq balancing" + depends on SMP && X86_IO_APIC && !X86_XEN + default y + help + The default yes will allow the kernel to do irq load balancing. + Saying no will keep the kernel from doing irq load balancing. + +config HAVE_DEC_LOCK + bool + depends on (SMP || PREEMPT) && X86_CMPXCHG + default y + +# turning this on wastes a bunch of space. +# Summit needs it only when NUMA is on +config BOOT_IOREMAP + bool + depends on (((X86_SUMMIT || X86_GENERICARCH) && NUMA) || (X86 && EFI)) + default y + +config REGPARM + bool "Use register arguments (EXPERIMENTAL)" + depends on EXPERIMENTAL + default n + help + Compile the kernel with -mregparm=3. This uses a different ABI + and passes the first three arguments of a function call in registers. + This will probably break binary only modules. + + This feature is only enabled for gcc-3.0 and later - earlier compilers + generate incorrect output with certain kernel constructs when + -mregparm=3 is used. + +config SECCOMP + bool "Enable seccomp to safely compute untrusted bytecode" + depends on PROC_FS + default y + help + This kernel feature is useful for number crunching applications + that may need to compute untrusted bytecode during their + execution. By using pipes or other transports made available to + the process as file descriptors supporting the read/write + syscalls, it's possible to isolate those applications in + their own address space using seccomp. Once seccomp is + enabled via /proc/<pid>/seccomp, it cannot be disabled + and the task is only allowed to execute a few safe syscalls + defined by each seccomp mode. + + If unsure, say Y. Only embedded should say N here. + +endmenu + + +menu "Power management options (ACPI, APM)" + depends on !(X86_VOYAGER || XEN_UNPRIVILEGED_GUEST) + +if !X86_XEN +source kernel/power/Kconfig +endif + +source "drivers/acpi/Kconfig" + +menu "APM (Advanced Power Management) BIOS Support" +depends on PM && !(X86_VISWS || X86_XEN) + +config APM + tristate "APM (Advanced Power Management) BIOS support" + depends on PM + ---help--- + APM is a BIOS specification for saving power using several different + techniques. This is mostly useful for battery powered laptops with + APM compliant BIOSes. If you say Y here, the system time will be + reset after a RESUME operation, the /proc/apm device will provide + battery status information, and user-space programs will receive + notification of APM "events" (e.g. battery status change). + + If you select "Y" here, you can disable actual use of the APM + BIOS by passing the "apm=off" option to the kernel at boot time. + + Note that the APM support is almost completely disabled for + machines with more than one CPU. + + In order to use APM, you will need supporting software. For location + and more information, read <file:Documentation/pm.txt> and the + Battery Powered Linux mini-HOWTO, available from + <http://www.tldp.org/docs.html#howto>. + + This driver does not spin down disk drives (see the hdparm(8) + manpage ("man 8 hdparm") for that), and it doesn't turn off + VESA-compliant "green" monitors. + + This driver does not support the TI 4000M TravelMate and the ACER + 486/DX4/75 because they don't have compliant BIOSes. Many "green" + desktop machines also don't have compliant BIOSes, and this driver + may cause those machines to panic during the boot phase. + + Generally, if you don't have a battery in your machine, there isn't + much point in using this driver and you should say N. If you get + random kernel OOPSes or reboots that don't seem to be related to + anything, try disabling/enabling this option (or disabling/enabling + APM in your BIOS). + + Some other things you should try when experiencing seemingly random, + "weird" problems: + + 1) make sure that you have enough swap space and that it is + enabled. + 2) pass the "no-hlt" option to the kernel + 3) switch on floating point emulation in the kernel and pass + the "no387" option to the kernel + 4) pass the "floppy=nodma" option to the kernel + 5) pass the "mem=4M" option to the kernel (thereby disabling + all but the first 4 MB of RAM) + 6) make sure that the CPU is not over clocked. + 7) read the sig11 FAQ at <http://www.bitwizard.nl/sig11/> + 8) disable the cache from your BIOS settings + 9) install a fan for the video card or exchange video RAM + 10) install a better fan for the CPU + 11) exchange RAM chips + 12) exchange the motherboard. + + To compile this driver as a module, choose M here: the + module will be called apm. + +config APM_IGNORE_USER_SUSPEND + bool "Ignore USER SUSPEND" + depends on APM + help + This option will ignore USER SUSPEND requests. On machines with a + compliant APM BIOS, you want to say N. However, on the NEC Versa M + series notebooks, it is necessary to say Y because of a BIOS bug. + +config APM_DO_ENABLE + bool "Enable PM at boot time" + depends on APM + ---help--- + Enable APM features at boot time. From page 36 of the APM BIOS + specification: "When disabled, the APM BIOS does not automatically + power manage devices, enter the Standby State, enter the Suspend + State, or take power saving steps in response to CPU Idle calls." + This driver will make CPU Idle calls when Linux is idle (unless this + feature is turned off -- see "Do CPU IDLE calls", below). This + should always save battery power, but more complicated APM features + will be dependent on your BIOS implementation. You may need to turn + this option off if your computer hangs at boot time when using APM + support, or if it beeps continuously instead of suspending. Turn + this off if you have a NEC UltraLite Versa 33/C or a Toshiba + T400CDT. This is off by default since most machines do fine without + this feature. + +config APM_CPU_IDLE + bool "Make CPU Idle calls when idle" + depends on APM + help + Enable calls to APM CPU Idle/CPU Busy inside the kernel's idle loop. + On some machines, this can activate improved power savings, such as + a slowed CPU clock rate, when the machine is idle. These idle calls + are made after the idle loop has run for some length of time (e.g., + 333 mS). On some machines, this will cause a hang at boot time or + whenever the CPU becomes idle. (On machines with more than one CPU, + this option does nothing.) + +config APM_DISPLAY_BLANK + bool "Enable console blanking using APM" + depends on APM + help + Enable console blanking using the APM. Some laptops can use this to + turn off the LCD backlight when the screen blanker of the Linux + virtual console blanks the screen. Note that this is only used by + the virtual console screen blanker, and won't turn off the backlight + when using the X Window system. This also doesn't have anything to + do with your VESA-compliant power-saving monitor. Further, this + option doesn't work for all laptops -- it might not turn off your + backlight at all, or it might print a lot of errors to the console, + especially if you are using gpm. + +config APM_RTC_IS_GMT + bool "RTC stores time in GMT" + depends on APM + help + Say Y here if your RTC (Real Time Clock a.k.a. hardware clock) + stores the time in GMT (Greenwich Mean Time). Say N if your RTC + stores localtime. + + It is in fact recommended to store GMT in your RTC, because then you + don't have to worry about daylight savings time changes. The only + reason not to use GMT in your RTC is if you also run a broken OS + that doesn't understand GMT. + +config APM_ALLOW_INTS + bool "Allow interrupts during APM BIOS calls" + depends on APM + help + Normally we disable external interrupts while we are making calls to + the APM BIOS as a measure to lessen the effects of a badly behaving + BIOS implementation. The BIOS should reenable interrupts if it + needs to. Unfortunately, some BIOSes do not -- especially those in + many of the newer IBM Thinkpads. If you experience hangs when you + suspend, try setting this to Y. Otherwise, say N. + +config APM_REAL_MODE_POWER_OFF + bool "Use real mode APM BIOS call to power off" + depends on APM + help + Use real mode APM BIOS calls to switch off the computer. This is + a work-around for a number of buggy BIOSes. Switch this option on if + your computer crashes instead of powering off properly. + +endmenu + +source "arch/i386/kernel/cpu/cpufreq/Kconfig" + +endmenu + +menu "Bus options (PCI, PCMCIA, EISA, MCA, ISA)" + depends on !XEN_UNPRIVILEGED_GUEST + +config PCI + bool "PCI support" if !X86_VISWS + depends on !X86_VOYAGER + default y if X86_VISWS + help + Find out whether you have a PCI motherboard. PCI is the name of a + bus system, i.e. the way the CPU talks to the other stuff inside + your box. Other bus systems are ISA, EISA, MicroChannel (MCA) or + VESA. If you have PCI, say Y, otherwise N. + + The PCI-HOWTO, available from + <http://www.tldp.org/docs.html#howto>, contains valuable + information about which PCI hardware does work under Linux and which + doesn't. + +choice + prompt "PCI access mode" + depends on PCI && !X86_VISWS + default PCI_GOANY + ---help--- + On PCI systems, the BIOS can be used to detect the PCI devices and + determine their configuration. However, some old PCI motherboards + have BIOS bugs and may crash if this is done. Also, some embedded + PCI-based systems don't have any BIOS at all. Linux can also try to + detect the PCI hardware directly without using the BIOS. + + With this option, you can specify how Linux should detect the + PCI devices. If you choose "BIOS", the BIOS will be used, + if you choose "Direct", the BIOS won't be used, and if you + choose "MMConfig", then PCI Express MMCONFIG will be used. + If you choose "Any", the kernel will try MMCONFIG, then the + direct access method and falls back to the BIOS if that doesn't + work. If unsure, go with the default, which is "Any". + +config PCI_GOBIOS + bool "BIOS" + depends on !X86_XEN + +config PCI_GOMMCONFIG + bool "MMConfig" + +config PCI_GODIRECT + bool "Direct" + +config PCI_GOANY + bool "Any" + +endchoice + +config PCI_BIOS + bool + depends on !(X86_VISWS || X86_XEN) && PCI && (PCI_GOBIOS || PCI_GOANY) + default y + +config PCI_DIRECT + bool + depends on PCI && ((PCI_GODIRECT || PCI_GOANY) || X86_VISWS) + default y + +config PCI_MMCONFIG + bool + depends on PCI && ACPI && (PCI_GOMMCONFIG || PCI_GOANY) + select ACPI_BOOT + default y + +source "drivers/pci/pcie/Kconfig" + +source "drivers/pci/Kconfig" + +config ISA_DMA_API + bool + depends on !X86_XEN + default y + +config ISA + bool "ISA support" + depends on !(X86_VOYAGER || X86_VISWS || X86_XEN) + help + Find out whether you have ISA slots on your motherboard. ISA is the + name of a bus system, i.e. the way the CPU talks to the other stuff + inside your box. Other bus systems are PCI, EISA, MicroChannel + (MCA) or VESA. ISA is an older system, now being displaced by PCI; + newer boards don't support it. If you have ISA, say Y, otherwise N. + +config EISA + bool "EISA support" + depends on ISA + ---help--- + The Extended Industry Standard Architecture (EISA) bus was + developed as an open alternative to the IBM MicroChannel bus. + + The EISA bus provided some of the features of the IBM MicroChannel + bus while maintaining backward compatibility with cards made for + the older ISA bus. The EISA bus saw limited use between 1988 and + 1995 when it was made obsolete by the PCI bus. + + Say Y here if you are building a kernel for an EISA-based machine. + + Otherwise, say N. + +source "drivers/eisa/Kconfig" + +config MCA + bool "MCA support" if !(X86_VISWS || X86_VOYAGER || X86_XEN) + default y if X86_VOYAGER + help + MicroChannel Architecture is found in some IBM PS/2 machines and + laptops. It is a bus system similar to PCI or ISA. See + <file:Documentation/mca.txt> (and especially the web page given + there) before attempting to build an MCA bus kernel. + +source "drivers/mca/Kconfig" + +config SCx200 + tristate "NatSemi SCx200 support" + depends on !X86_VOYAGER + help + This provides basic support for the National Semiconductor SCx200 + processor. Right now this is just a driver for the GPIO pins. + + If you don't know what to do here, say N. + + This support is also available as a module. If compiled as a + module, it will be called scx200. + +source "drivers/pcmcia/Kconfig" + +source "drivers/pci/hotplug/Kconfig" + +endmenu + +menu "Executable file formats" + +source "fs/Kconfig.binfmt" + +endmenu + +source "drivers/Kconfig" + +source "fs/Kconfig" + +if !X86_XEN +source "arch/i386/oprofile/Kconfig" +endif + +source "arch/i386/Kconfig.debug" + +source "security/Kconfig" + +source "crypto/Kconfig" + +source "drivers/xen/Kconfig" + +source "lib/Kconfig" + +# +# Use the generic interrupt handling code in kernel/irq/: +# +config GENERIC_HARDIRQS + bool + default y + +config GENERIC_IRQ_PROBE + bool + default y + +config X86_SMP + bool + depends on SMP && !X86_VOYAGER + default y + +config X86_HT + bool + depends on SMP && !(X86_VISWS || X86_VOYAGER || X86_XEN) + default y + +config X86_BIOS_REBOOT + bool + depends on !(X86_VISWS || X86_VOYAGER) + default y + +config X86_TRAMPOLINE + bool + depends on X86_SMP || (X86_VOYAGER && SMP) + default y + +config PC + bool + depends on X86 && !EMBEDDED + default y diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/Makefile --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/Makefile Mon Jan 30 17:18:27 2006 @@ -0,0 +1,192 @@ +# +# i386/Makefile +# +# This file is included by the global makefile so that you can add your own +# architecture-specific flags and dependencies. Remember to do have actions +# for "archclean" cleaning up for this architecture. +# +# This file is subject to the terms and conditions of the GNU General Public +# License. See the file "COPYING" in the main directory of this archive +# for more details. +# +# Copyright (C) 1994 by Linus Torvalds +# +# 19990713 Artur Skawina <skawina@xxxxxxxxxxxxx> +# Added '-march' and '-mpreferred-stack-boundary' support +# +# 20050320 Kianusch Sayah Karadji <kianusch@xxxxxxxxxxx> +# Added support for GEODE CPU + +LDFLAGS := -m elf_i386 +OBJCOPYFLAGS := -O binary -R .note -R .comment -S +LDFLAGS_vmlinux := +CHECKFLAGS += -D__i386__ + +CFLAGS += -pipe -msoft-float + +# prevent gcc from keeping the stack 16 byte aligned +CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2) + +align := $(cc-option-align) +cflags-$(CONFIG_M386) += -march=i386 +cflags-$(CONFIG_M486) += -march=i486 +cflags-$(CONFIG_M586) += -march=i586 +cflags-$(CONFIG_M586TSC) += -march=i586 +cflags-$(CONFIG_M586MMX) += $(call cc-option,-march=pentium-mmx,-march=i586) +cflags-$(CONFIG_M686) += -march=i686 +cflags-$(CONFIG_MPENTIUMII) += -march=i686 $(call cc-option,-mtune=pentium2) +cflags-$(CONFIG_MPENTIUMIII) += -march=i686 $(call cc-option,-mtune=pentium3) +cflags-$(CONFIG_MPENTIUMM) += -march=i686 $(call cc-option,-mtune=pentium3) +cflags-$(CONFIG_MPENTIUM4) += -march=i686 $(call cc-option,-mtune=pentium4) +cflags-$(CONFIG_MK6) += -march=k6 +# Please note, that patches that add -march=athlon-xp and friends are pointless. +# They make zero difference whatsosever to performance at this time. +cflags-$(CONFIG_MK7) += $(call cc-option,-march=athlon,-march=i686 $(align)-functions=4) +cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8,$(call cc-option,-march=athlon,-march=i686 $(align)-functions=4)) +cflags-$(CONFIG_MCRUSOE) += -march=i686 $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0 +cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call cc-option,-mtune=pentium3) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0 +cflags-$(CONFIG_MWINCHIPC6) += $(call cc-option,-march=winchip-c6,-march=i586) +cflags-$(CONFIG_MWINCHIP2) += $(call cc-option,-march=winchip2,-march=i586) +cflags-$(CONFIG_MWINCHIP3D) += $(call cc-option,-march=winchip2,-march=i586) +cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0 +cflags-$(CONFIG_MVIAC3_2) += $(call cc-option,-march=c3-2,-march=i686) + +# AMD Elan support +cflags-$(CONFIG_X86_ELAN) += -march=i486 + +# Geode GX1 support +cflags-$(CONFIG_MGEODEGX1) += $(call cc-option,-march=pentium-mmx,-march=i486) + +# -mregparm=3 works ok on gcc-3.0 and later +# +GCC_VERSION := $(call cc-version) +cflags-$(CONFIG_REGPARM) += $(shell if [ $(GCC_VERSION) -ge 0300 ] ; then echo "-mregparm=3"; fi ;) + +# Disable unit-at-a-time mode, it makes gcc use a lot more stack +# due to the lack of sharing of stacklots. +CFLAGS += $(call cc-option,-fno-unit-at-a-time) + +CFLAGS += $(cflags-y) + +# Default subarch .c files +mcore-y := mach-default + +# Voyager subarch support +mflags-$(CONFIG_X86_VOYAGER) := -Iinclude/asm-i386/mach-voyager +mcore-$(CONFIG_X86_VOYAGER) := mach-voyager + +# VISWS subarch support +mflags-$(CONFIG_X86_VISWS) := -Iinclude/asm-i386/mach-visws +mcore-$(CONFIG_X86_VISWS) := mach-visws + +# NUMAQ subarch support +mflags-$(CONFIG_X86_NUMAQ) := -Iinclude/asm-i386/mach-numaq +mcore-$(CONFIG_X86_NUMAQ) := mach-default + +# BIGSMP subarch support +mflags-$(CONFIG_X86_BIGSMP) := -Iinclude/asm-i386/mach-bigsmp +mcore-$(CONFIG_X86_BIGSMP) := mach-default + +#Summit subarch support +mflags-$(CONFIG_X86_SUMMIT) := -Iinclude/asm-i386/mach-summit +mcore-$(CONFIG_X86_SUMMIT) := mach-default + +# Xen subarch support +mflags-$(CONFIG_X86_XEN) := -Iinclude/asm-i386/mach-xen +mcore-$(CONFIG_X86_XEN) := mach-xen + +# generic subarchitecture +mflags-$(CONFIG_X86_GENERICARCH) := -Iinclude/asm-i386/mach-generic +mcore-$(CONFIG_X86_GENERICARCH) := mach-default +core-$(CONFIG_X86_GENERICARCH) += arch/i386/mach-generic/ + +# ES7000 subarch support +mflags-$(CONFIG_X86_ES7000) := -Iinclude/asm-i386/mach-es7000 +mcore-$(CONFIG_X86_ES7000) := mach-default +core-$(CONFIG_X86_ES7000) := arch/i386/mach-es7000/ + +# default subarch .h files +mflags-y += -Iinclude/asm-i386/mach-default + +head-y := arch/i386/kernel/head.o arch/i386/kernel/init_task.o + +libs-y += arch/i386/lib/ +core-y += arch/i386/kernel/ \ + arch/i386/mm/ \ + arch/i386/$(mcore-y)/ \ + arch/i386/crypto/ +drivers-$(CONFIG_MATH_EMULATION) += arch/i386/math-emu/ +drivers-$(CONFIG_PCI) += arch/i386/pci/ +# must be linked after kernel/ +drivers-$(CONFIG_OPROFILE) += arch/i386/oprofile/ +drivers-$(CONFIG_PM) += arch/i386/power/ + +CFLAGS += $(mflags-y) +AFLAGS += $(mflags-y) + +boot := arch/i386/boot + +.PHONY: zImage bzImage compressed zlilo bzlilo \ + zdisk bzdisk fdimage fdimage144 fdimage288 install kernel_install + +ifdef CONFIG_XEN +CPPFLAGS := -D__KERNEL__ -Iinclude$(if $(KBUILD_SRC),2)/asm/mach-xen $(LINUXINCLUDE) +head-y := arch/i386/kernel/head-xen.o arch/i386/kernel/init_task-xen.o +boot := arch/i386/boot-xen +.PHONY: vmlinuz +all: vmlinuz + +vmlinuz: vmlinux + $(Q)$(MAKE) $(build)=$(boot) $@ + +install: vmlinux + $(Q)$(MAKE) $(build)=$(boot) XENGUEST=$(XENGUEST) $@ +else +all: bzImage + +# KBUILD_IMAGE specify target image being built + KBUILD_IMAGE := $(boot)/bzImage +zImage zlilo zdisk: KBUILD_IMAGE := arch/i386/boot/zImage + +zImage bzImage: vmlinux + $(Q)$(MAKE) $(build)=$(boot) $(KBUILD_IMAGE) + +compressed: zImage + +zlilo bzlilo: vmlinux + $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) zlilo + +zdisk bzdisk: vmlinux + $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) zdisk + +fdimage fdimage144 fdimage288: vmlinux + $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) $@ + +install: vmlinux +install kernel_install: + $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(KBUILD_IMAGE) install +endif + +prepare: include/asm-$(ARCH)/asm_offsets.h +CLEAN_FILES += include/asm-$(ARCH)/asm_offsets.h + +arch/$(ARCH)/kernel/asm-offsets.s: include/asm include/linux/version.h \ + include/config/MARKER + +include/asm-$(ARCH)/asm_offsets.h: arch/$(ARCH)/kernel/asm-offsets.s + $(call filechk,gen-asm-offsets) + +archclean: + $(Q)$(MAKE) $(clean)=arch/i386/boot + +define archhelp + echo '* bzImage - Compressed kernel image (arch/$(ARCH)/boot/bzImage)' + echo ' install - Install kernel using' + echo ' (your) ~/bin/installkernel or' + echo ' (distribution) /sbin/installkernel or' + echo ' install to $$(INSTALL_PATH) and run lilo' + echo ' bzdisk - Create a boot floppy in /dev/fd0' + echo ' fdimage - Create a boot floppy image' +endef + +CLEAN_FILES += arch/$(ARCH)/boot/fdimage arch/$(ARCH)/boot/mtools.conf diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/boot-xen/Makefile --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/boot-xen/Makefile Mon Jan 30 17:18:27 2006 @@ -0,0 +1,21 @@ + +OBJCOPYFLAGS := -g --strip-unneeded + +vmlinuz: vmlinux-stripped FORCE + $(call if_changed,gzip) + +vmlinux-stripped: vmlinux FORCE + $(call if_changed,objcopy) + +INSTALL_ROOT := $(patsubst %/boot,%,$(INSTALL_PATH)) + +XINSTALL_NAME ?= $(KERNELRELEASE) +install: vmlinuz + mkdir -p $(INSTALL_ROOT)/boot + ln -f -s vmlinuz-$(XINSTALL_NAME)$(INSTALL_SUFFIX) $(INSTALL_ROOT)/boot/vmlinuz-$(VERSION).$(PATCHLEVEL).$(SUBLEVEL)$(XENGUEST)$(INSTALL_SUFFIX) + rm -f $(INSTALL_ROOT)/boot/vmlinuz-$(XINSTALL_NAME)$(INSTALL_SUFFIX) + install -m0644 vmlinuz $(INSTALL_ROOT)/boot/vmlinuz-$(XINSTALL_NAME)$(INSTALL_SUFFIX) + install -m0644 vmlinux $(INSTALL_ROOT)/boot/vmlinux-syms-$(XINSTALL_NAME)$(INSTALL_SUFFIX) + install -m0664 .config $(INSTALL_ROOT)/boot/config-$(XINSTALL_NAME)$(INSTALL_SUFFIX) + install -m0664 System.map $(INSTALL_ROOT)/boot/System.map-$(XINSTALL_NAME)$(INSTALL_SUFFIX) + ln -f -s vmlinuz-$(XINSTALL_NAME)$(INSTALL_SUFFIX) $(INSTALL_ROOT)/boot/vmlinuz-$(VERSION).$(PATCHLEVEL)$(XENGUEST)$(INSTALL_SUFFIX) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/Makefile --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/Makefile Mon Jan 30 17:18:27 2006 @@ -0,0 +1,93 @@ +# +# Makefile for the linux kernel. +# + +extra-y := head.o init_task.o vmlinux.lds + +obj-y := process.o semaphore.o signal.o entry.o traps.o irq.o vm86.o \ + ptrace.o time.o ioport.o ldt.o setup.o i8259.o sys_i386.o \ + pci-dma.o i386_ksyms.o i387.o dmi_scan.o bootflag.o \ + doublefault.o quirks.o + +obj-y += cpu/ +obj-y += timers/ +obj-$(CONFIG_ACPI_BOOT) += acpi/ +obj-$(CONFIG_X86_BIOS_REBOOT) += reboot.o +obj-$(CONFIG_MCA) += mca.o +obj-$(CONFIG_X86_MSR) += msr.o +obj-$(CONFIG_X86_CPUID) += cpuid.o +obj-$(CONFIG_MICROCODE) += microcode.o +obj-$(CONFIG_APM) += apm.o +obj-$(CONFIG_X86_SMP) += smp.o smpboot.o +obj-$(CONFIG_X86_TRAMPOLINE) += trampoline.o +obj-$(CONFIG_X86_MPPARSE) += mpparse.o +obj-$(CONFIG_X86_LOCAL_APIC) += apic.o nmi.o +obj-$(CONFIG_X86_IO_APIC) += io_apic.o +obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups.o +obj-$(CONFIG_X86_NUMAQ) += numaq.o +obj-$(CONFIG_X86_SUMMIT_NUMA) += summit.o +obj-$(CONFIG_KPROBES) += kprobes.o +obj-$(CONFIG_MODULES) += module.o +obj-y += sysenter.o vsyscall.o +obj-$(CONFIG_ACPI_SRAT) += srat.o +obj-$(CONFIG_HPET_TIMER) += time_hpet.o +obj-$(CONFIG_EFI) += efi.o efi_stub.o +obj-$(CONFIG_EARLY_PRINTK) += early_printk.o +obj-$(CONFIG_SMP_ALTERNATIVES) += smpalts.o +obj-$(CONFIG_SWIOTLB) += swiotlb.o + +EXTRA_AFLAGS := -traditional + +obj-$(CONFIG_SCx200) += scx200.o + +ifdef CONFIG_XEN +vsyscall_note := vsyscall-note-xen.o +else +vsyscall_note := vsyscall-note.o +endif + +# vsyscall.o contains the vsyscall DSO images as __initdata. +# We must build both images before we can assemble it. +# Note: kbuild does not track this dependency due to usage of .incbin +$(obj)/vsyscall.o: $(obj)/vsyscall-int80.so $(obj)/vsyscall-sysenter.so +targets += $(foreach F,int80 sysenter,vsyscall-$F.o vsyscall-$F.so) +targets += $(vsyscall_note) vsyscall.lds + +# The DSO images are built using a special linker script. +quiet_cmd_syscall = SYSCALL $@ + cmd_syscall = $(CC) -m elf_i386 -nostdlib $(SYSCFLAGS_$(@F)) \ + -Wl,-T,$(filter-out FORCE,$^) -o $@ + +export CPPFLAGS_vsyscall.lds += -P -C -U$(ARCH) + +vsyscall-flags = -shared -s -Wl,-soname=linux-gate.so.1 +SYSCFLAGS_vsyscall-sysenter.so = $(vsyscall-flags) +SYSCFLAGS_vsyscall-int80.so = $(vsyscall-flags) + +$(obj)/vsyscall-int80.so $(obj)/vsyscall-sysenter.so: \ +$(obj)/vsyscall-%.so: $(src)/vsyscall.lds \ + $(obj)/vsyscall-%.o $(obj)/$(vsyscall_note) FORCE + $(call if_changed,syscall) + +# We also create a special relocatable object that should mirror the symbol +# table and layout of the linked DSO. With ld -R we can then refer to +# these symbols in the kernel code rather than hand-coded addresses. +extra-y += vsyscall-syms.o +$(obj)/built-in.o: $(obj)/vsyscall-syms.o +$(obj)/built-in.o: ld_flags += -R $(obj)/vsyscall-syms.o + +SYSCFLAGS_vsyscall-syms.o = -r +$(obj)/vsyscall-syms.o: $(src)/vsyscall.lds \ + $(obj)/vsyscall-sysenter.o $(obj)/$(vsyscall_note) FORCE + $(call if_changed,syscall) + +ifdef CONFIG_XEN +include $(srctree)/scripts/Makefile.xen + +obj-y += fixup.o +n-obj-xen := i8259.o doublefault.o timers/ reboot.o smpboot.o trampoline.o + +obj-y := $(call filterxen, $(obj-y), $(n-obj-xen)) +obj-y := $(call cherrypickxen, $(obj-y)) +extra-y := $(call cherrypickxen, $(extra-y)) +endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/acpi/Makefile --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/acpi/Makefile Mon Jan 30 17:18:27 2006 @@ -0,0 +1,8 @@ +obj-$(CONFIG_ACPI_BOOT) := boot.o +obj-$(CONFIG_X86_IO_APIC) += earlyquirk.o +obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup.o + +ifdef CONFIG_XEN +include $(srctree)/scripts/Makefile.xen +obj-y := $(call cherrypickxen, $(obj-y), $(src)) +endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/acpi/boot-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/acpi/boot-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,920 @@ +/* + * boot.c - Architecture-Specific Low-Level ACPI Boot Support + * + * Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@xxxxxxxxx> + * Copyright (C) 2001 Jun Nakajima <jun.nakajima@xxxxxxxxx> + * + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + */ + +#include <linux/init.h> +#include <linux/config.h> +#include <linux/acpi.h> +#include <linux/efi.h> +#include <linux/irq.h> +#include <linux/module.h> + +#include <asm/pgtable.h> +#include <asm/io_apic.h> +#include <asm/apic.h> +#include <asm/io.h> +#include <asm/irq.h> +#include <asm/mpspec.h> +#ifdef CONFIG_XEN +#include <asm/fixmap.h> +#endif + +#ifdef CONFIG_X86_64 + +static inline void acpi_madt_oem_check(char *oem_id, char *oem_table_id) { } +extern void __init clustered_apic_check(void); +static inline int ioapic_setup_disabled(void) { return 0; } +#include <asm/proto.h> + +#else /* X86 */ + +#ifdef CONFIG_X86_LOCAL_APIC +#include <mach_apic.h> +#include <mach_mpparse.h> +#endif /* CONFIG_X86_LOCAL_APIC */ + +#endif /* X86 */ + +#define BAD_MADT_ENTRY(entry, end) ( \ + (!entry) || (unsigned long)entry + sizeof(*entry) > end || \ + ((acpi_table_entry_header *)entry)->length != sizeof(*entry)) + +#define PREFIX "ACPI: " + +#ifdef CONFIG_ACPI_PCI +int acpi_noirq __initdata; /* skip ACPI IRQ initialization */ +int acpi_pci_disabled __initdata; /* skip ACPI PCI scan and IRQ initialization */ +#else +int acpi_noirq __initdata = 1; +int acpi_pci_disabled __initdata = 1; +#endif +int acpi_ht __initdata = 1; /* enable HT */ + +int acpi_lapic; +int acpi_ioapic; +int acpi_strict; +EXPORT_SYMBOL(acpi_strict); + +acpi_interrupt_flags acpi_sci_flags __initdata; +int acpi_sci_override_gsi __initdata; +int acpi_skip_timer_override __initdata; + +#ifdef CONFIG_X86_LOCAL_APIC +static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; +#endif + +#ifndef __HAVE_ARCH_CMPXCHG +#warning ACPI uses CMPXCHG, i486 and later hardware +#endif + +#define MAX_MADT_ENTRIES 256 +u8 x86_acpiid_to_apicid[MAX_MADT_ENTRIES] = + { [0 ... MAX_MADT_ENTRIES-1] = 0xff }; +EXPORT_SYMBOL(x86_acpiid_to_apicid); + +/* -------------------------------------------------------------------------- + Boot-time Configuration + -------------------------------------------------------------------------- */ + +/* + * The default interrupt routing model is PIC (8259). This gets + * overriden if IOAPICs are enumerated (below). + */ +enum acpi_irq_model_id acpi_irq_model = ACPI_IRQ_MODEL_PIC; + +#if defined(CONFIG_X86_64) && !defined(CONFIG_XEN) + +/* rely on all ACPI tables being in the direct mapping */ +char *__acpi_map_table(unsigned long phys_addr, unsigned long size) +{ + if (!phys_addr || !size) + return NULL; + + if (phys_addr < (end_pfn_map << PAGE_SHIFT)) + return __va(phys_addr); + + return NULL; +} + +#else + +/* + * Temporarily use the virtual area starting from FIX_IO_APIC_BASE_END, + * to map the target physical address. The problem is that set_fixmap() + * provides a single page, and it is possible that the page is not + * sufficient. + * By using this area, we can map up to MAX_IO_APICS pages temporarily, + * i.e. until the next __va_range() call. + * + * Important Safety Note: The fixed I/O APIC page numbers are *subtracted* + * from the fixed base. That's why we start at FIX_IO_APIC_BASE_END and + * count idx down while incrementing the phys address. + */ +char *__acpi_map_table(unsigned long phys, unsigned long size) +{ + unsigned long base, offset, mapped_size; + int idx; + +#ifndef CONFIG_XEN + if (phys + size < 8*1024*1024) + return __va(phys); +#endif + + offset = phys & (PAGE_SIZE - 1); + mapped_size = PAGE_SIZE - offset; + set_fixmap(FIX_ACPI_END, phys); + base = fix_to_virt(FIX_ACPI_END); + + /* + * Most cases can be covered by the below. + */ + idx = FIX_ACPI_END; + while (mapped_size < size) { + if (--idx < FIX_ACPI_BEGIN) + return NULL; /* cannot handle this */ + phys += PAGE_SIZE; + set_fixmap(idx, phys); + mapped_size += PAGE_SIZE; + } + + return ((unsigned char *) base + offset); +} +#endif + +#ifdef CONFIG_PCI_MMCONFIG +static int __init acpi_parse_mcfg(unsigned long phys_addr, unsigned long size) +{ + struct acpi_table_mcfg *mcfg; + + if (!phys_addr || !size) + return -EINVAL; + + mcfg = (struct acpi_table_mcfg *) __acpi_map_table(phys_addr, size); + if (!mcfg) { + printk(KERN_WARNING PREFIX "Unable to map MCFG\n"); + return -ENODEV; + } + + if (mcfg->base_reserved) { + printk(KERN_ERR PREFIX "MMCONFIG not in low 4GB of memory\n"); + return -ENODEV; + } + + pci_mmcfg_base_addr = mcfg->base_address; + + return 0; +} +#else +#define acpi_parse_mcfg NULL +#endif /* !CONFIG_PCI_MMCONFIG */ + +#ifdef CONFIG_X86_LOCAL_APIC +static int __init +acpi_parse_madt ( + unsigned long phys_addr, + unsigned long size) +{ + struct acpi_table_madt *madt = NULL; + + if (!phys_addr || !size) + return -EINVAL; + + madt = (struct acpi_table_madt *) __acpi_map_table(phys_addr, size); + if (!madt) { + printk(KERN_WARNING PREFIX "Unable to map MADT\n"); + return -ENODEV; + } + + if (madt->lapic_address) { + acpi_lapic_addr = (u64) madt->lapic_address; + + printk(KERN_DEBUG PREFIX "Local APIC address 0x%08x\n", + madt->lapic_address); + } + + acpi_madt_oem_check(madt->header.oem_id, madt->header.oem_table_id); + + return 0; +} + + +static int __init +acpi_parse_lapic ( + acpi_table_entry_header *header, const unsigned long end) +{ + struct acpi_table_lapic *processor = NULL; + + processor = (struct acpi_table_lapic*) header; + + if (BAD_MADT_ENTRY(processor, end)) + return -EINVAL; + + acpi_table_print_madt_entry(header); + + /* no utility in registering a disabled processor */ + if (processor->flags.enabled == 0) + return 0; + + x86_acpiid_to_apicid[processor->acpi_id] = processor->id; + + mp_register_lapic ( + processor->id, /* APIC ID */ + processor->flags.enabled); /* Enabled? */ + + return 0; +} + +static int __init +acpi_parse_lapic_addr_ovr ( + acpi_table_entry_header *header, const unsigned long end) +{ + struct acpi_table_lapic_addr_ovr *lapic_addr_ovr = NULL; + + lapic_addr_ovr = (struct acpi_table_lapic_addr_ovr*) header; + + if (BAD_MADT_ENTRY(lapic_addr_ovr, end)) + return -EINVAL; + + acpi_lapic_addr = lapic_addr_ovr->address; + + return 0; +} + +static int __init +acpi_parse_lapic_nmi ( + acpi_table_entry_header *header, const unsigned long end) +{ + struct acpi_table_lapic_nmi *lapic_nmi = NULL; + + lapic_nmi = (struct acpi_table_lapic_nmi*) header; + + if (BAD_MADT_ENTRY(lapic_nmi, end)) + return -EINVAL; + + acpi_table_print_madt_entry(header); + + if (lapic_nmi->lint != 1) + printk(KERN_WARNING PREFIX "NMI not connected to LINT 1!\n"); + + return 0; +} + + +#endif /*CONFIG_X86_LOCAL_APIC*/ + +#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_ACPI_INTERPRETER) + +static int __init +acpi_parse_ioapic ( + acpi_table_entry_header *header, const unsigned long end) +{ + struct acpi_table_ioapic *ioapic = NULL; + + ioapic = (struct acpi_table_ioapic*) header; + + if (BAD_MADT_ENTRY(ioapic, end)) + return -EINVAL; + + acpi_table_print_madt_entry(header); + + mp_register_ioapic ( + ioapic->id, + ioapic->address, + ioapic->global_irq_base); + + return 0; +} + +/* + * Parse Interrupt Source Override for the ACPI SCI + */ +static void +acpi_sci_ioapic_setup(u32 gsi, u16 polarity, u16 trigger) +{ + if (trigger == 0) /* compatible SCI trigger is level */ + trigger = 3; + + if (polarity == 0) /* compatible SCI polarity is low */ + polarity = 3; + + /* Command-line over-ride via acpi_sci= */ + if (acpi_sci_flags.trigger) + trigger = acpi_sci_flags.trigger; + + if (acpi_sci_flags.polarity) + polarity = acpi_sci_flags.polarity; + + /* + * mp_config_acpi_legacy_irqs() already setup IRQs < 16 + * If GSI is < 16, this will update its flags, + * else it will create a new mp_irqs[] entry. + */ + mp_override_legacy_irq(gsi, polarity, trigger, gsi); + + /* + * stash over-ride to indicate we've been here + * and for later update of acpi_fadt + */ + acpi_sci_override_gsi = gsi; + return; +} + +static int __init +acpi_parse_int_src_ovr ( + acpi_table_entry_header *header, const unsigned long end) +{ + struct acpi_table_int_src_ovr *intsrc = NULL; + + intsrc = (struct acpi_table_int_src_ovr*) header; + + if (BAD_MADT_ENTRY(intsrc, end)) + return -EINVAL; + + acpi_table_print_madt_entry(header); + + if (intsrc->bus_irq == acpi_fadt.sci_int) { + acpi_sci_ioapic_setup(intsrc->global_irq, + intsrc->flags.polarity, intsrc->flags.trigger); + return 0; + } + + if (acpi_skip_timer_override && + intsrc->bus_irq == 0 && intsrc->global_irq == 2) { + printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n"); + return 0; + } + + mp_override_legacy_irq ( + intsrc->bus_irq, + intsrc->flags.polarity, + intsrc->flags.trigger, + intsrc->global_irq); + + return 0; +} + + +static int __init +acpi_parse_nmi_src ( + acpi_table_entry_header *header, const unsigned long end) +{ + struct acpi_table_nmi_src *nmi_src = NULL; + + nmi_src = (struct acpi_table_nmi_src*) header; + + if (BAD_MADT_ENTRY(nmi_src, end)) + return -EINVAL; + + acpi_table_print_madt_entry(header); + + /* TBD: Support nimsrc entries? */ + + return 0; +} + +#endif /* CONFIG_X86_IO_APIC */ + +#ifdef CONFIG_ACPI_BUS + +/* + * acpi_pic_sci_set_trigger() + * + * use ELCR to set PIC-mode trigger type for SCI + * + * If a PIC-mode SCI is not recognized or gives spurious IRQ7's + * it may require Edge Trigger -- use "acpi_sci=edge" + * + * Port 0x4d0-4d1 are ECLR1 and ECLR2, the Edge/Level Control Registers + * for the 8259 PIC. bit[n] = 1 means irq[n] is Level, otherwise Edge. + * ECLR1 is IRQ's 0-7 (IRQ 0, 1, 2 must be 0) + * ECLR2 is IRQ's 8-15 (IRQ 8, 13 must be 0) + */ + +void __init +acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) +{ + unsigned int mask = 1 << irq; + unsigned int old, new; + + /* Real old ELCR mask */ + old = inb(0x4d0) | (inb(0x4d1) << 8); + + /* + * If we use ACPI to set PCI irq's, then we should clear ELCR + * since we will set it correctly as we enable the PCI irq + * routing. + */ + new = acpi_noirq ? old : 0; + + /* + * Update SCI information in the ELCR, it isn't in the PCI + * routing tables.. + */ + switch (trigger) { + case 1: /* Edge - clear */ + new &= ~mask; + break; + case 3: /* Level - set */ + new |= mask; + break; + } + + if (old == new) + return; + + printk(PREFIX "setting ELCR to %04x (from %04x)\n", new, old); + outb(new, 0x4d0); + outb(new >> 8, 0x4d1); +} + + +#endif /* CONFIG_ACPI_BUS */ + +int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) +{ +#ifdef CONFIG_X86_IO_APIC + if (use_pci_vector() && !platform_legacy_irq(gsi)) + *irq = IO_APIC_VECTOR(gsi); + else +#endif + *irq = gsi; + return 0; +} + +unsigned int acpi_register_gsi(u32 gsi, int edge_level, int active_high_low) +{ + unsigned int irq; + unsigned int plat_gsi = gsi; + +#ifdef CONFIG_PCI + /* + * Make sure all (legacy) PCI IRQs are set as level-triggered. + */ + if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) { + extern void eisa_set_level_irq(unsigned int irq); + + if (edge_level == ACPI_LEVEL_SENSITIVE) + eisa_set_level_irq(gsi); + } +#endif + +#ifdef CONFIG_X86_IO_APIC + if (acpi_irq_model == ACPI_IRQ_MODEL_IOAPIC) { + plat_gsi = mp_register_gsi(gsi, edge_level, active_high_low); + } +#endif + acpi_gsi_to_irq(plat_gsi, &irq); + return irq; +} +EXPORT_SYMBOL(acpi_register_gsi); + +/* + * ACPI based hotplug support for CPU + */ +#ifdef CONFIG_ACPI_HOTPLUG_CPU +int +acpi_map_lsapic(acpi_handle handle, int *pcpu) +{ + /* TBD */ + return -EINVAL; +} +EXPORT_SYMBOL(acpi_map_lsapic); + + +int +acpi_unmap_lsapic(int cpu) +{ + /* TBD */ + return -EINVAL; +} +EXPORT_SYMBOL(acpi_unmap_lsapic); +#endif /* CONFIG_ACPI_HOTPLUG_CPU */ + +static unsigned long __init +acpi_scan_rsdp ( + unsigned long start, + unsigned long length) +{ + unsigned long offset = 0; + unsigned long sig_len = sizeof("RSD PTR ") - 1; + unsigned long vstart = (unsigned long)isa_bus_to_virt(start); + + /* + * Scan all 16-byte boundaries of the physical memory region for the + * RSDP signature. + */ + for (offset = 0; offset < length; offset += 16) { + if (strncmp((char *) (vstart + offset), "RSD PTR ", sig_len)) + continue; + return (start + offset); + } + + return 0; +} + +static int __init acpi_parse_sbf(unsigned long phys_addr, unsigned long size) +{ + struct acpi_table_sbf *sb; + + if (!phys_addr || !size) + return -EINVAL; + + sb = (struct acpi_table_sbf *) __acpi_map_table(phys_addr, size); + if (!sb) { + printk(KERN_WARNING PREFIX "Unable to map SBF\n"); + return -ENODEV; + } + + sbf_port = sb->sbf_cmos; /* Save CMOS port */ + + return 0; +} + + +#ifdef CONFIG_HPET_TIMER + +static int __init acpi_parse_hpet(unsigned long phys, unsigned long size) +{ + struct acpi_table_hpet *hpet_tbl; + + if (!phys || !size) + return -EINVAL; + + hpet_tbl = (struct acpi_table_hpet *) __acpi_map_table(phys, size); + if (!hpet_tbl) { + printk(KERN_WARNING PREFIX "Unable to map HPET\n"); + return -ENODEV; + } + + if (hpet_tbl->addr.space_id != ACPI_SPACE_MEM) { + printk(KERN_WARNING PREFIX "HPET timers must be located in " + "memory.\n"); + return -1; + } + +#ifdef CONFIG_X86_64 + vxtime.hpet_address = hpet_tbl->addr.addrl | + ((long) hpet_tbl->addr.addrh << 32); + + printk(KERN_INFO PREFIX "HPET id: %#x base: %#lx\n", + hpet_tbl->id, vxtime.hpet_address); +#else /* X86 */ + { + extern unsigned long hpet_address; + + hpet_address = hpet_tbl->addr.addrl; + printk(KERN_INFO PREFIX "HPET id: %#x base: %#lx\n", + hpet_tbl->id, hpet_address); + } +#endif /* X86 */ + + return 0; +} +#else +#define acpi_parse_hpet NULL +#endif + +#ifdef CONFIG_X86_PM_TIMER +extern u32 pmtmr_ioport; +#endif + +static int __init acpi_parse_fadt(unsigned long phys, unsigned long size) +{ + struct fadt_descriptor_rev2 *fadt = NULL; + + fadt = (struct fadt_descriptor_rev2*) __acpi_map_table(phys,size); + if(!fadt) { + printk(KERN_WARNING PREFIX "Unable to map FADT\n"); + return 0; + } + +#ifdef CONFIG_ACPI_INTERPRETER + /* initialize sci_int early for INT_SRC_OVR MADT parsing */ + acpi_fadt.sci_int = fadt->sci_int; +#endif + +#ifdef CONFIG_ACPI_BUS + /* initialize rev and apic_phys_dest_mode for x86_64 genapic */ + acpi_fadt.revision = fadt->revision; + acpi_fadt.force_apic_physical_destination_mode = fadt->force_apic_physical_destination_mode; +#endif + +#if defined(CONFIG_X86_PM_TIMER) && !defined(CONFIG_XEN) + /* detect the location of the ACPI PM Timer */ + if (fadt->revision >= FADT2_REVISION_ID) { + /* FADT rev. 2 */ + if (fadt->xpm_tmr_blk.address_space_id != ACPI_ADR_SPACE_SYSTEM_IO) + return 0; + + pmtmr_ioport = fadt->xpm_tmr_blk.address; + } else { + /* FADT rev. 1 */ + pmtmr_ioport = fadt->V1_pm_tmr_blk; + } + if (pmtmr_ioport) + printk(KERN_INFO PREFIX "PM-Timer IO Port: %#x\n", pmtmr_ioport); +#endif + return 0; +} + + +unsigned long __init +acpi_find_rsdp (void) +{ + unsigned long rsdp_phys = 0; + + if (efi_enabled) { + if (efi.acpi20) + return __pa(efi.acpi20); + else if (efi.acpi) + return __pa(efi.acpi); + } + /* + * Scan memory looking for the RSDP signature. First search EBDA (low + * memory) paragraphs and then search upper memory (E0000-FFFFF). + */ + rsdp_phys = acpi_scan_rsdp (0, 0x400); + if (!rsdp_phys) + rsdp_phys = acpi_scan_rsdp (0xE0000, 0x20000); + + return rsdp_phys; +} + +#ifdef CONFIG_X86_LOCAL_APIC +/* + * Parse LAPIC entries in MADT + * returns 0 on success, < 0 on error + */ +static int __init +acpi_parse_madt_lapic_entries(void) +{ + int count; + + /* + * Note that the LAPIC address is obtained from the MADT (32-bit value) + * and (optionally) overriden by a LAPIC_ADDR_OVR entry (64-bit value). + */ + + count = acpi_table_parse_madt(ACPI_MADT_LAPIC_ADDR_OVR, acpi_parse_lapic_addr_ovr, 0); + if (count < 0) { + printk(KERN_ERR PREFIX "Error parsing LAPIC address override entry\n"); + return count; + } + + mp_register_lapic_address(acpi_lapic_addr); + + count = acpi_table_parse_madt(ACPI_MADT_LAPIC, acpi_parse_lapic, + MAX_APICS); + if (!count) { + printk(KERN_ERR PREFIX "No LAPIC entries present\n"); + /* TBD: Cleanup to allow fallback to MPS */ + return -ENODEV; + } + else if (count < 0) { + printk(KERN_ERR PREFIX "Error parsing LAPIC entry\n"); + /* TBD: Cleanup to allow fallback to MPS */ + return count; + } + + count = acpi_table_parse_madt(ACPI_MADT_LAPIC_NMI, acpi_parse_lapic_nmi, 0); + if (count < 0) { + printk(KERN_ERR PREFIX "Error parsing LAPIC NMI entry\n"); + /* TBD: Cleanup to allow fallback to MPS */ + return count; + } + return 0; +} +#endif /* CONFIG_X86_LOCAL_APIC */ + +#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_ACPI_INTERPRETER) +/* + * Parse IOAPIC related entries in MADT + * returns 0 on success, < 0 on error + */ +static int __init +acpi_parse_madt_ioapic_entries(void) +{ + int count; + + /* + * ACPI interpreter is required to complete interrupt setup, + * so if it is off, don't enumerate the io-apics with ACPI. + * If MPS is present, it will handle them, + * otherwise the system will stay in PIC mode + */ + if (acpi_disabled || acpi_noirq) { + return -ENODEV; + } + + /* + * if "noapic" boot option, don't look for IO-APICs + */ + if (skip_ioapic_setup) { + printk(KERN_INFO PREFIX "Skipping IOAPIC probe " + "due to 'noapic' option.\n"); + return -ENODEV; + } + + count = acpi_table_parse_madt(ACPI_MADT_IOAPIC, acpi_parse_ioapic, MAX_IO_APICS); + if (!count) { + printk(KERN_ERR PREFIX "No IOAPIC entries present\n"); + return -ENODEV; + } + else if (count < 0) { + printk(KERN_ERR PREFIX "Error parsing IOAPIC entry\n"); + return count; + } + + count = acpi_table_parse_madt(ACPI_MADT_INT_SRC_OVR, acpi_parse_int_src_ovr, NR_IRQ_VECTORS); + if (count < 0) { + printk(KERN_ERR PREFIX "Error parsing interrupt source overrides entry\n"); + /* TBD: Cleanup to allow fallback to MPS */ + return count; + } + + /* + * If BIOS did not supply an INT_SRC_OVR for the SCI + * pretend we got one so we can set the SCI flags. + */ + if (!acpi_sci_override_gsi) + acpi_sci_ioapic_setup(acpi_fadt.sci_int, 0, 0); + + /* Fill in identity legacy mapings where no override */ + mp_config_acpi_legacy_irqs(); + + count = acpi_table_parse_madt(ACPI_MADT_NMI_SRC, acpi_parse_nmi_src, NR_IRQ_VECTORS); + if (count < 0) { + printk(KERN_ERR PREFIX "Error parsing NMI SRC entry\n"); + /* TBD: Cleanup to allow fallback to MPS */ + return count; + } + + return 0; +} +#else +static inline int acpi_parse_madt_ioapic_entries(void) +{ + return -1; +} +#endif /* !(CONFIG_X86_IO_APIC && CONFIG_ACPI_INTERPRETER) */ + + +static void __init +acpi_process_madt(void) +{ +#ifdef CONFIG_X86_LOCAL_APIC + int count, error; + + count = acpi_table_parse(ACPI_APIC, acpi_parse_madt); + if (count >= 1) { + + /* + * Parse MADT LAPIC entries + */ + error = acpi_parse_madt_lapic_entries(); + if (!error) { + acpi_lapic = 1; + + /* + * Parse MADT IO-APIC entries + */ + error = acpi_parse_madt_ioapic_entries(); + if (!error) { + acpi_irq_model = ACPI_IRQ_MODEL_IOAPIC; + acpi_irq_balance_set(NULL); + acpi_ioapic = 1; + + smp_found_config = 1; + clustered_apic_check(); + } + } + if (error == -EINVAL) { + /* + * Dell Precision Workstation 410, 610 come here. + */ + printk(KERN_ERR PREFIX "Invalid BIOS MADT, disabling ACPI\n"); + disable_acpi(); + } + } +#endif + return; +} + +/* + * acpi_boot_table_init() and acpi_boot_init() + * called from setup_arch(), always. + * 1. checksums all tables + * 2. enumerates lapics + * 3. enumerates io-apics + * + * acpi_table_init() is separate to allow reading SRAT without + * other side effects. + * + * side effects of acpi_boot_init: + * acpi_lapic = 1 if LAPIC found + * acpi_ioapic = 1 if IOAPIC found + * if (acpi_lapic && acpi_ioapic) smp_found_config = 1; + * if acpi_blacklisted() acpi_disabled = 1; + * acpi_irq_model=... + * ... + * + * return value: (currently ignored) + * 0: success + * !0: failure + */ + +int __init +acpi_boot_table_init(void) +{ + int error; + + /* + * If acpi_disabled, bail out + * One exception: acpi=ht continues far enough to enumerate LAPICs + */ + if (acpi_disabled && !acpi_ht) + return 1; + + /* + * Initialize the ACPI boot-time table parser. + */ + error = acpi_table_init(); + if (error) { + disable_acpi(); + return error; + } + +#ifdef __i386__ + check_acpi_pci(); +#endif + + acpi_table_parse(ACPI_BOOT, acpi_parse_sbf); + + /* + * blacklist may disable ACPI entirely + */ + error = acpi_blacklisted(); + if (error) { + extern int acpi_force; + + if (acpi_force) { + printk(KERN_WARNING PREFIX "acpi=force override\n"); + } else { + printk(KERN_WARNING PREFIX "Disabling ACPI support\n"); + disable_acpi(); + return error; + } + } + + return 0; +} + + +int __init acpi_boot_init(void) +{ + /* + * If acpi_disabled, bail out + * One exception: acpi=ht continues far enough to enumerate LAPICs + */ + if (acpi_disabled && !acpi_ht) + return 1; + + acpi_table_parse(ACPI_BOOT, acpi_parse_sbf); + + /* + * set sci_int and PM timer address + */ + acpi_table_parse(ACPI_FADT, acpi_parse_fadt); + + /* + * Process the Multiple APIC Description Table (MADT), if present + */ + acpi_process_madt(); + + acpi_table_parse(ACPI_HPET, acpi_parse_hpet); + acpi_table_parse(ACPI_MCFG, acpi_parse_mcfg); + + return 0; +} + diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/apic-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/apic-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,83 @@ +/* + * Local APIC handling, local APIC timers + * + * (c) 1999, 2000 Ingo Molnar <mingo@xxxxxxxxxx> + * + * Fixes + * Maciej W. Rozycki : Bits for genuine 82489DX APICs; + * thanks to Eric Gilmore + * and Rolf G. Tews + * for testing these extensively. + * Maciej W. Rozycki : Various updates and fixes. + * Mikael Pettersson : Power Management for UP-APIC. + * Pavel Machek and + * Mikael Pettersson : PM converted to driver model. + */ + +#include <linux/config.h> +#include <linux/init.h> + +#include <linux/mm.h> +#include <linux/irq.h> +#include <linux/delay.h> +#include <linux/bootmem.h> +#include <linux/smp_lock.h> +#include <linux/interrupt.h> +#include <linux/mc146818rtc.h> +#include <linux/kernel_stat.h> +#include <linux/sysdev.h> + +#include <asm/atomic.h> +#include <asm/smp.h> +#include <asm/mtrr.h> +#include <asm/mpspec.h> +#include <asm/desc.h> +#include <asm/arch_hooks.h> +#include <asm/hpet.h> + +#include <mach_apic.h> + +#include "io_ports.h" + +/* + * Debug level + */ +int apic_verbosity; + +int get_physical_broadcast(void) +{ + return 0xff; +} + +/* + * 'what should we do if we get a hw irq event on an illegal vector'. + * each architecture has to answer this themselves. + */ +void ack_bad_irq(unsigned int irq) +{ + printk("unexpected IRQ trap at vector %02x\n", irq); + /* + * Currently unexpected vectors happen only on SMP and APIC. + * We _must_ ack these because every local APIC has only N + * irq slots per priority level, and a 'hanging, unacked' IRQ + * holds up an irq slot - in excessive cases (when multiple + * unexpected vectors occur) that might lock up the APIC + * completely. + */ + ack_APIC_irq(); +} + +/* + * This initializes the IO-APIC and APIC hardware if this is + * a UP kernel. + */ +int __init APIC_init_uniprocessor (void) +{ +#ifdef CONFIG_X86_IO_APIC + if (smp_found_config) + if (!skip_ioapic_setup && nr_ioapics) + setup_IO_APIC(); +#endif + + return 0; +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/apm.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/apm.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,2428 @@ +/* -*- linux-c -*- + * APM BIOS driver for Linux + * Copyright 1994-2001 Stephen Rothwell (sfr@xxxxxxxxxxxxxxxx) + * + * Initial development of this driver was funded by NEC Australia P/L + * and NEC Corporation + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2, or (at your option) any + * later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * October 1995, Rik Faith (faith@xxxxxxxxxx): + * Minor enhancements and updates (to the patch set) for 1.3.x + * Documentation + * January 1996, Rik Faith (faith@xxxxxxxxxx): + * Make /proc/apm easy to format (bump driver version) + * March 1996, Rik Faith (faith@xxxxxxxxxx): + * Prohibit APM BIOS calls unless apm_enabled. + * (Thanks to Ulrich Windl <Ulrich.Windl@xxxxxxxxxxxxxxxxxxxx>) + * April 1996, Stephen Rothwell (sfr@xxxxxxxxxxxxxxxx) + * Version 1.0 and 1.1 + * May 1996, Version 1.2 + * Feb 1998, Version 1.3 + * Feb 1998, Version 1.4 + * Aug 1998, Version 1.5 + * Sep 1998, Version 1.6 + * Nov 1998, Version 1.7 + * Jan 1999, Version 1.8 + * Jan 1999, Version 1.9 + * Oct 1999, Version 1.10 + * Nov 1999, Version 1.11 + * Jan 2000, Version 1.12 + * Feb 2000, Version 1.13 + * Nov 2000, Version 1.14 + * Oct 2001, Version 1.15 + * Jan 2002, Version 1.16 + * Oct 2002, Version 1.16ac + * + * History: + * 0.6b: first version in official kernel, Linux 1.3.46 + * 0.7: changed /proc/apm format, Linux 1.3.58 + * 0.8: fixed gcc 2.7.[12] compilation problems, Linux 1.3.59 + * 0.9: only call bios if bios is present, Linux 1.3.72 + * 1.0: use fixed device number, consolidate /proc/apm into this file, + * Linux 1.3.85 + * 1.1: support user-space standby and suspend, power off after system + * halted, Linux 1.3.98 + * 1.2: When resetting RTC after resume, take care so that the time + * is only incorrect by 30-60mS (vs. 1S previously) (Gabor J. Toth + * <jtoth@xxxxxxxxxxxxx>); improve interaction between + * screen-blanking and gpm (Stephen Rothwell); Linux 1.99.4 + * 1.2a:Simple change to stop mysterious bug reports with SMP also added + * levels to the printk calls. APM is not defined for SMP machines. + * The new replacment for it is, but Linux doesn't yet support this. + * Alan Cox Linux 2.1.55 + * 1.3: Set up a valid data descriptor 0x40 for buggy BIOS's + * 1.4: Upgraded to support APM 1.2. Integrated ThinkPad suspend patch by + * Dean Gaudet <dgaudet@xxxxxxxxxx>. + * C. Scott Ananian <cananian@xxxxxxxxxxxxxxxxxxxx> Linux 2.1.87 + * 1.5: Fix segment register reloading (in case of bad segments saved + * across BIOS call). + * Stephen Rothwell + * 1.6: Cope with complier/assembler differences. + * Only try to turn off the first display device. + * Fix OOPS at power off with no APM BIOS by Jan Echternach + * <echter@xxxxxxxxxxxxxxxxxxxxxxxxx> + * Stephen Rothwell + * 1.7: Modify driver's cached copy of the disabled/disengaged flags + * to reflect current state of APM BIOS. + * Chris Rankin <rankinc@xxxxxxxxxxxxx> + * Reset interrupt 0 timer to 100Hz after suspend + * Chad Miller <cmiller@xxxxxxxxxxxxx> + * Add CONFIG_APM_IGNORE_SUSPEND_BOUNCE + * Richard Gooch <rgooch@xxxxxxxxxxxxx> + * Allow boot time disabling of APM + * Make boot messages far less verbose by default + * Make asm safer + * Stephen Rothwell + * 1.8: Add CONFIG_APM_RTC_IS_GMT + * Richard Gooch <rgooch@xxxxxxxxxxxxx> + * change APM_NOINTS to CONFIG_APM_ALLOW_INTS + * remove dependency on CONFIG_PROC_FS + * Stephen Rothwell + * 1.9: Fix small typo. <laslo@xxxxxxxxxxxxxx> + * Try to cope with BIOS's that need to have all display + * devices blanked and not just the first one. + * Ross Paterson <ross@xxxxxxxxxxxxxx> + * Fix segment limit setting it has always been wrong as + * the segments needed to have byte granularity. + * Mark a few things __init. + * Add hack to allow power off of SMP systems by popular request. + * Use CONFIG_SMP instead of __SMP__ + * Ignore BOUNCES for three seconds. + * Stephen Rothwell + * 1.10: Fix for Thinkpad return code. + * Merge 2.2 and 2.3 drivers. + * Remove APM dependencies in arch/i386/kernel/process.c + * Remove APM dependencies in drivers/char/sysrq.c + * Reset time across standby. + * Allow more inititialisation on SMP. + * Remove CONFIG_APM_POWER_OFF and make it boot time + * configurable (default on). + * Make debug only a boot time parameter (remove APM_DEBUG). + * Try to blank all devices on any error. + * 1.11: Remove APM dependencies in drivers/char/console.c + * Check nr_running to detect if we are idle (from + * Borislav Deianov <borislav@xxxxxxxxxxxxxxxxxxxx>) + * Fix for bioses that don't zero the top part of the + * entrypoint offset (Mario Sitta <sitta@xxxxxxxxxxxx>) + * (reported by Panos Katsaloulis <teras@xxxxxxxxxxx>). + * Real mode power off patch (Walter Hofmann + * <Walter.Hofmann@xxxxxxxxxxxxxxxxxxxxxxxxxxx>). + * 1.12: Remove CONFIG_SMP as the compiler will optimize + * the code away anyway (smp_num_cpus == 1 in UP) + * noted by Artur Skawina <skawina@xxxxxxxxxxxxx>. + * Make power off under SMP work again. + * Fix thinko with initial engaging of BIOS. + * Make sure power off only happens on CPU 0 + * (Paul "Rusty" Russell <rusty@xxxxxxxxxxxxxxx>). + * Do error notification to user mode if BIOS calls fail. + * Move entrypoint offset fix to ...boot/setup.S + * where it belongs (Cosmos <gis88564@xxxxxxxxxxxxxxx>). + * Remove smp-power-off. SMP users must now specify + * "apm=power-off" on the kernel command line. Suggested + * by Jim Avera <jima@xxxxxxx>, modified by Alan Cox + * <alan@xxxxxxxxxxxxxxxxxxx>. + * Register the /proc/apm entry even on SMP so that + * scripts that check for it before doing power off + * work (Jim Avera <jima@xxxxxxx>). + * 1.13: Changes for new pm_ interfaces (Andy Henroid + * <andy_henroid@xxxxxxxxx>). + * Modularize the code. + * Fix the Thinkpad (again) :-( (CONFIG_APM_IGNORE_MULTIPLE_SUSPENDS + * is now the way life works). + * Fix thinko in suspend() (wrong return). + * Notify drivers on critical suspend. + * Make kapmd absorb more idle time (Pavel Machek <pavel@xxxxxxx> + * modified by sfr). + * Disable interrupts while we are suspended (Andy Henroid + * <andy_henroid@xxxxxxxxx> fixed by sfr). + * Make power off work on SMP again (Tony Hoyle + * <tmh@xxxxxxxxxxxxxxxxx> and <zlatko@xxxxxxxx>) modified by sfr. + * Remove CONFIG_APM_SUSPEND_BOUNCE. The bounce ignore + * interval is now configurable. + * 1.14: Make connection version persist across module unload/load. + * Enable and engage power management earlier. + * Disengage power management on module unload. + * Changed to use the sysrq-register hack for registering the + * power off function called by magic sysrq based upon discussions + * in irc://irc.openprojects.net/#kernelnewbies + * (Crutcher Dunnavant <crutcher+kernel@xxxxxxxxxxxxxx>). + * Make CONFIG_APM_REAL_MODE_POWER_OFF run time configurable. + * (Arjan van de Ven <arjanv@xxxxxxxxxx>) modified by sfr. + * Work around byte swap bug in one of the Vaio's BIOS's + * (Marc Boucher <marc@xxxxxxx>). + * Exposed the disable flag to dmi so that we can handle known + * broken APM (Alan Cox <alan@xxxxxxxxxx>). + * 1.14ac: If the BIOS says "I slowed the CPU down" then don't spin + * calling it - instead idle. (Alan Cox <alan@xxxxxxxxxx>) + * If an APM idle fails log it and idle sensibly + * 1.15: Don't queue events to clients who open the device O_WRONLY. + * Don't expect replies from clients who open the device O_RDONLY. + * (Idea from Thomas Hood) + * Minor waitqueue cleanups. (John Fremlin <chief@xxxxxxxxxxx>) + * 1.16: Fix idle calling. (Andreas Steinmetz <ast@xxxxxxxx> et al.) + * Notify listeners of standby or suspend events before notifying + * drivers. Return EBUSY to ioctl() if suspend is rejected. + * (Russell King <rmk@xxxxxxxxxxxxxxxx> and Thomas Hood) + * Ignore first resume after we generate our own resume event + * after a suspend (Thomas Hood) + * Daemonize now gets rid of our controlling terminal (sfr). + * CONFIG_APM_CPU_IDLE now just affects the default value of + * idle_threshold (sfr). + * Change name of kernel apm daemon (as it no longer idles) (sfr). + * 1.16ac: Fix up SMP support somewhat. You can now force SMP on and we + * make _all_ APM calls on the CPU#0. Fix unsafe sign bug. + * TODO: determine if its "boot CPU" or "CPU0" we want to lock to. + * + * APM 1.1 Reference: + * + * Intel Corporation, Microsoft Corporation. Advanced Power Management + * (APM) BIOS Interface Specification, Revision 1.1, September 1993. + * Intel Order Number 241704-001. Microsoft Part Number 781-110-X01. + * + * [This document is available free from Intel by calling 800.628.8686 (fax + * 916.356.6100) or 800.548.4725; or via anonymous ftp from + * ftp://ftp.intel.com/pub/IAL/software_specs/apmv11.doc. It is also + * available from Microsoft by calling 206.882.8080.] + * + * APM 1.2 Reference: + * Intel Corporation, Microsoft Corporation. Advanced Power Management + * (APM) BIOS Interface Specification, Revision 1.2, February 1996. + * + * [This document is available from Microsoft at: + * http://www.microsoft.com/hwdev/busbios/amp_12.htm] + */ + +#include <linux/config.h> +#include <linux/module.h> + +#include <linux/poll.h> +#include <linux/types.h> +#include <linux/stddef.h> +#include <linux/timer.h> +#include <linux/fcntl.h> +#include <linux/slab.h> +#include <linux/stat.h> +#include <linux/proc_fs.h> +#include <linux/miscdevice.h> +#include <linux/apm_bios.h> +#include <linux/init.h> +#include <linux/time.h> +#include <linux/sched.h> +#include <linux/pm.h> +#include <linux/device.h> +#include <linux/kernel.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/dmi.h> +#include <linux/suspend.h> + +#include <asm/system.h> +#include <asm/uaccess.h> +#include <asm/desc.h> + +#include "io_ports.h" + +extern spinlock_t i8253_lock; +extern unsigned long get_cmos_time(void); +extern void machine_real_restart(unsigned char *, int); + +#if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT) +extern int (*console_blank_hook)(int); +#endif + +/* + * The apm_bios device is one of the misc char devices. + * This is its minor number. + */ +#define APM_MINOR_DEV 134 + +/* + * See Documentation/Config.help for the configuration options. + * + * Various options can be changed at boot time as follows: + * (We allow underscores for compatibility with the modules code) + * apm=on/off enable/disable APM + * [no-]allow[-_]ints allow interrupts during BIOS calls + * [no-]broken[-_]psr BIOS has a broken GetPowerStatus call + * [no-]realmode[-_]power[-_]off switch to real mode before + * powering off + * [no-]debug log some debugging messages + * [no-]power[-_]off power off on shutdown + * [no-]smp Use apm even on an SMP box + * bounce[-_]interval=<n> number of ticks to ignore suspend + * bounces + * idle[-_]threshold=<n> System idle percentage above which to + * make APM BIOS idle calls. Set it to + * 100 to disable. + * idle[-_]period=<n> Period (in 1/100s of a second) over + * which the idle percentage is + * calculated. + */ + +/* KNOWN PROBLEM MACHINES: + * + * U: TI 4000M TravelMate: BIOS is *NOT* APM compliant + * [Confirmed by TI representative] + * ?: ACER 486DX4/75: uses dseg 0040, in violation of APM specification + * [Confirmed by BIOS disassembly] + * [This may work now ...] + * P: Toshiba 1950S: battery life information only gets updated after resume + * P: Midwest Micro Soundbook Elite DX2/66 monochrome: screen blanking + * broken in BIOS [Reported by Garst R. Reese <reese@xxxxxxx>] + * ?: AcerNote-950: oops on reading /proc/apm - workaround is a WIP + * Neale Banks <neale@xxxxxxxxxxxxxxxx> December 2000 + * + * Legend: U = unusable with APM patches + * P = partially usable with APM patches + */ + +/* + * Define as 1 to make the driver always call the APM BIOS busy + * routine even if the clock was not reported as slowed by the + * idle routine. Otherwise, define as 0. + */ +#define ALWAYS_CALL_BUSY 1 + +/* + * Define to make the APM BIOS calls zero all data segment registers (so + * that an incorrect BIOS implementation will cause a kernel panic if it + * tries to write to arbitrary memory). + */ +#define APM_ZERO_SEGS + +#include "apm.h" + +/* + * Define to make all _set_limit calls use 64k limits. The APM 1.1 BIOS is + * supposed to provide limit information that it recognizes. Many machines + * do this correctly, but many others do not restrict themselves to their + * claimed limit. When this happens, they will cause a segmentation + * violation in the kernel at boot time. Most BIOS's, however, will + * respect a 64k limit, so we use that. If you want to be pedantic and + * hold your BIOS to its claims, then undefine this. + */ +#define APM_RELAX_SEGMENTS + +/* + * Define to re-initialize the interrupt 0 timer to 100 Hz after a suspend. + * This patched by Chad Miller <cmiller@xxxxxxxxxxxxx>, original code by + * David Chen <chen@xxxxxxxxxxxxxx> + */ +#undef INIT_TIMER_AFTER_SUSPEND + +#ifdef INIT_TIMER_AFTER_SUSPEND +#include <linux/timex.h> +#include <asm/io.h> +#include <linux/delay.h> +#endif + +/* + * Need to poll the APM BIOS every second + */ +#define APM_CHECK_TIMEOUT (HZ) + +/* + * Ignore suspend events for this amount of time after a resume + */ +#define DEFAULT_BOUNCE_INTERVAL (3 * HZ) + +/* + * Maximum number of events stored + */ +#define APM_MAX_EVENTS 20 + +/* + * The per-file APM data + */ +struct apm_user { + int magic; + struct apm_user * next; + int suser: 1; + int writer: 1; + int reader: 1; + int suspend_wait: 1; + int suspend_result; + int suspends_pending; + int standbys_pending; + int suspends_read; + int standbys_read; + int event_head; + int event_tail; + apm_event_t events[APM_MAX_EVENTS]; +}; + +/* + * The magic number in apm_user + */ +#define APM_BIOS_MAGIC 0x4101 + +/* + * idle percentage above which bios idle calls are done + */ +#ifdef CONFIG_APM_CPU_IDLE +#define DEFAULT_IDLE_THRESHOLD 95 +#else +#define DEFAULT_IDLE_THRESHOLD 100 +#endif +#define DEFAULT_IDLE_PERIOD (100 / 3) + +/* + * Local variables + */ +static struct { + unsigned long offset; + unsigned short segment; +} apm_bios_entry; +static int clock_slowed; +static int idle_threshold = DEFAULT_IDLE_THRESHOLD; +static int idle_period = DEFAULT_IDLE_PERIOD; +static int set_pm_idle; +static int suspends_pending; +static int standbys_pending; +static int ignore_sys_suspend; +static int ignore_normal_resume; +static int bounce_interval = DEFAULT_BOUNCE_INTERVAL; + +#ifdef CONFIG_APM_RTC_IS_GMT +# define clock_cmos_diff 0 +# define got_clock_diff 1 +#else +static long clock_cmos_diff; +static int got_clock_diff; +#endif +static int debug; +static int smp; +static int apm_disabled = -1; +#ifdef CONFIG_SMP +static int power_off; +#else +static int power_off = 1; +#endif +#ifdef CONFIG_APM_REAL_MODE_POWER_OFF +static int realmode_power_off = 1; +#else +static int realmode_power_off; +#endif +static int exit_kapmd; +static int kapmd_running; +#ifdef CONFIG_APM_ALLOW_INTS +static int allow_ints = 1; +#else +static int allow_ints; +#endif +static int broken_psr; + +static DECLARE_WAIT_QUEUE_HEAD(apm_waitqueue); +static DECLARE_WAIT_QUEUE_HEAD(apm_suspend_waitqueue); +static struct apm_user * user_list; +static DEFINE_SPINLOCK(user_list_lock); +static struct desc_struct bad_bios_desc = { 0, 0x00409200 }; + +static char driver_version[] = "1.16ac"; /* no spaces */ + +/* + * APM event names taken from the APM 1.2 specification. These are + * the message codes that the BIOS uses to tell us about events + */ +static char * apm_event_name[] = { + "system standby", + "system suspend", + "normal resume", + "critical resume", + "low battery", + "power status change", + "update time", + "critical suspend", + "user standby", + "user suspend", + "system standby resume", + "capabilities change" +}; +#define NR_APM_EVENT_NAME \ + (sizeof(apm_event_name) / sizeof(apm_event_name[0])) + +typedef struct lookup_t { + int key; + char * msg; +} lookup_t; + +/* + * The BIOS returns a set of standard error codes in AX when the + * carry flag is set. + */ + +static const lookup_t error_table[] = { +/* N/A { APM_SUCCESS, "Operation succeeded" }, */ + { APM_DISABLED, "Power management disabled" }, + { APM_CONNECTED, "Real mode interface already connected" }, + { APM_NOT_CONNECTED, "Interface not connected" }, + { APM_16_CONNECTED, "16 bit interface already connected" }, +/* N/A { APM_16_UNSUPPORTED, "16 bit interface not supported" }, */ + { APM_32_CONNECTED, "32 bit interface already connected" }, + { APM_32_UNSUPPORTED, "32 bit interface not supported" }, + { APM_BAD_DEVICE, "Unrecognized device ID" }, + { APM_BAD_PARAM, "Parameter out of range" }, + { APM_NOT_ENGAGED, "Interface not engaged" }, + { APM_BAD_FUNCTION, "Function not supported" }, + { APM_RESUME_DISABLED, "Resume timer disabled" }, + { APM_BAD_STATE, "Unable to enter requested state" }, +/* N/A { APM_NO_EVENTS, "No events pending" }, */ + { APM_NO_ERROR, "BIOS did not set a return code" }, + { APM_NOT_PRESENT, "No APM present" } +}; +#define ERROR_COUNT (sizeof(error_table)/sizeof(lookup_t)) + +/** + * apm_error - display an APM error + * @str: information string + * @err: APM BIOS return code + * + * Write a meaningful log entry to the kernel log in the event of + * an APM error. + */ + +static void apm_error(char *str, int err) +{ + int i; + + for (i = 0; i < ERROR_COUNT; i++) + if (error_table[i].key == err) break; + if (i < ERROR_COUNT) + printk(KERN_NOTICE "apm: %s: %s\n", str, error_table[i].msg); + else + printk(KERN_NOTICE "apm: %s: unknown error code %#2.2x\n", + str, err); +} + +/* + * Lock APM functionality to physical CPU 0 + */ + +#ifdef CONFIG_SMP + +static cpumask_t apm_save_cpus(void) +{ + cpumask_t x = current->cpus_allowed; + /* Some bioses don't like being called from CPU != 0 */ + set_cpus_allowed(current, cpumask_of_cpu(0)); + BUG_ON(smp_processor_id() != 0); + return x; +} + +static inline void apm_restore_cpus(cpumask_t mask) +{ + set_cpus_allowed(current, mask); +} + +#else + +/* + * No CPU lockdown needed on a uniprocessor + */ + +#define apm_save_cpus() (current->cpus_allowed) +#define apm_restore_cpus(x) (void)(x) + +#endif + +/* + * These are the actual BIOS calls. Depending on APM_ZERO_SEGS and + * apm_info.allow_ints, we are being really paranoid here! Not only + * are interrupts disabled, but all the segment registers (except SS) + * are saved and zeroed this means that if the BIOS tries to reference + * any data without explicitly loading the segment registers, the kernel + * will fault immediately rather than have some unforeseen circumstances + * for the rest of the kernel. And it will be very obvious! :-) Doing + * this depends on CS referring to the same physical memory as DS so that + * DS can be zeroed before the call. Unfortunately, we can't do anything + * about the stack segment/pointer. Also, we tell the compiler that + * everything could change. + * + * Also, we KNOW that for the non error case of apm_bios_call, there + * is no useful data returned in the low order 8 bits of eax. + */ +#define APM_DO_CLI \ + if (apm_info.allow_ints) \ + local_irq_enable(); \ + else \ + local_irq_disable(); + +#ifdef APM_ZERO_SEGS +# define APM_DECL_SEGS \ + unsigned int saved_fs; unsigned int saved_gs; +# define APM_DO_SAVE_SEGS \ + savesegment(fs, saved_fs); savesegment(gs, saved_gs) +# define APM_DO_RESTORE_SEGS \ + loadsegment(fs, saved_fs); loadsegment(gs, saved_gs) +#else +# define APM_DECL_SEGS +# define APM_DO_SAVE_SEGS +# define APM_DO_RESTORE_SEGS +#endif + +/** + * apm_bios_call - Make an APM BIOS 32bit call + * @func: APM function to execute + * @ebx_in: EBX register for call entry + * @ecx_in: ECX register for call entry + * @eax: EAX register return + * @ebx: EBX register return + * @ecx: ECX register return + * @edx: EDX register return + * @esi: ESI register return + * + * Make an APM call using the 32bit protected mode interface. The + * caller is responsible for knowing if APM BIOS is configured and + * enabled. This call can disable interrupts for a long period of + * time on some laptops. The return value is in AH and the carry + * flag is loaded into AL. If there is an error, then the error + * code is returned in AH (bits 8-15 of eax) and this function + * returns non-zero. + */ + +static u8 apm_bios_call(u32 func, u32 ebx_in, u32 ecx_in, + u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, u32 *esi) +{ + APM_DECL_SEGS + unsigned long flags; + cpumask_t cpus; + int cpu; + struct desc_struct save_desc_40; + + cpus = apm_save_cpus(); + + cpu = get_cpu(); + save_desc_40 = get_cpu_gdt_table(cpu)[0x40 / 8]; + get_cpu_gdt_table(cpu)[0x40 / 8] = bad_bios_desc; + + local_save_flags(flags); + APM_DO_CLI; + APM_DO_SAVE_SEGS; + apm_bios_call_asm(func, ebx_in, ecx_in, eax, ebx, ecx, edx, esi); + APM_DO_RESTORE_SEGS; + local_irq_restore(flags); + get_cpu_gdt_table(cpu)[0x40 / 8] = save_desc_40; + put_cpu(); + apm_restore_cpus(cpus); + + return *eax & 0xff; +} + +/** + * apm_bios_call_simple - make a simple APM BIOS 32bit call + * @func: APM function to invoke + * @ebx_in: EBX register value for BIOS call + * @ecx_in: ECX register value for BIOS call + * @eax: EAX register on return from the BIOS call + * + * Make a BIOS call that does only returns one value, or just status. + * If there is an error, then the error code is returned in AH + * (bits 8-15 of eax) and this function returns non-zero. This is + * used for simpler BIOS operations. This call may hold interrupts + * off for a long time on some laptops. + */ + +static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax) +{ + u8 error; + APM_DECL_SEGS + unsigned long flags; + cpumask_t cpus; + int cpu; + struct desc_struct save_desc_40; + + + cpus = apm_save_cpus(); + + cpu = get_cpu(); + save_desc_40 = get_cpu_gdt_table(cpu)[0x40 / 8]; + get_cpu_gdt_table(cpu)[0x40 / 8] = bad_bios_desc; + + local_save_flags(flags); + APM_DO_CLI; + APM_DO_SAVE_SEGS; + error = apm_bios_call_simple_asm(func, ebx_in, ecx_in, eax); + APM_DO_RESTORE_SEGS; + local_irq_restore(flags); + get_cpu_gdt_table(cpu)[0x40 / 8] = save_desc_40; + put_cpu(); + apm_restore_cpus(cpus); + return error; +} + +/** + * apm_driver_version - APM driver version + * @val: loaded with the APM version on return + * + * Retrieve the APM version supported by the BIOS. This is only + * supported for APM 1.1 or higher. An error indicates APM 1.0 is + * probably present. + * + * On entry val should point to a value indicating the APM driver + * version with the high byte being the major and the low byte the + * minor number both in BCD + * + * On return it will hold the BIOS revision supported in the + * same format. + */ + +static int apm_driver_version(u_short *val) +{ + u32 eax; + + if (apm_bios_call_simple(APM_FUNC_VERSION, 0, *val, &eax)) + return (eax >> 8) & 0xff; + *val = eax; + return APM_SUCCESS; +} + +/** + * apm_get_event - get an APM event from the BIOS + * @event: pointer to the event + * @info: point to the event information + * + * The APM BIOS provides a polled information for event + * reporting. The BIOS expects to be polled at least every second + * when events are pending. When a message is found the caller should + * poll until no more messages are present. However, this causes + * problems on some laptops where a suspend event notification is + * not cleared until it is acknowledged. + * + * Additional information is returned in the info pointer, providing + * that APM 1.2 is in use. If no messges are pending the value 0x80 + * is returned (No power management events pending). + */ + +static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info) +{ + u32 eax; + u32 ebx; + u32 ecx; + u32 dummy; + + if (apm_bios_call(APM_FUNC_GET_EVENT, 0, 0, &eax, &ebx, &ecx, + &dummy, &dummy)) + return (eax >> 8) & 0xff; + *event = ebx; + if (apm_info.connection_version < 0x0102) + *info = ~0; /* indicate info not valid */ + else + *info = ecx; + return APM_SUCCESS; +} + +/** + * set_power_state - set the power management state + * @what: which items to transition + * @state: state to transition to + * + * Request an APM change of state for one or more system devices. The + * processor state must be transitioned last of all. what holds the + * class of device in the upper byte and the device number (0xFF for + * all) for the object to be transitioned. + * + * The state holds the state to transition to, which may in fact + * be an acceptance of a BIOS requested state change. + */ + +static int set_power_state(u_short what, u_short state) +{ + u32 eax; + + if (apm_bios_call_simple(APM_FUNC_SET_STATE, what, state, &eax)) + return (eax >> 8) & 0xff; + return APM_SUCCESS; +} + +/** + * set_system_power_state - set system wide power state + * @state: which state to enter + * + * Transition the entire system into a new APM power state. + */ + +static int set_system_power_state(u_short state) +{ + return set_power_state(APM_DEVICE_ALL, state); +} + +/** + * apm_do_idle - perform power saving + * + * This function notifies the BIOS that the processor is (in the view + * of the OS) idle. It returns -1 in the event that the BIOS refuses + * to handle the idle request. On a success the function returns 1 + * if the BIOS did clock slowing or 0 otherwise. + */ + +static int apm_do_idle(void) +{ + u32 eax; + + if (apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax)) { + static unsigned long t; + + /* This always fails on some SMP boards running UP kernels. + * Only report the failure the first 5 times. + */ + if (++t < 5) + { + printk(KERN_DEBUG "apm_do_idle failed (%d)\n", + (eax >> 8) & 0xff); + t = jiffies; + } + return -1; + } + clock_slowed = (apm_info.bios.flags & APM_IDLE_SLOWS_CLOCK) != 0; + return clock_slowed; +} + +/** + * apm_do_busy - inform the BIOS the CPU is busy + * + * Request that the BIOS brings the CPU back to full performance. + */ + +static void apm_do_busy(void) +{ + u32 dummy; + + if (clock_slowed || ALWAYS_CALL_BUSY) { + (void) apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy); + clock_slowed = 0; + } +} + +/* + * If no process has really been interested in + * the CPU for some time, we want to call BIOS + * power management - we probably want + * to conserve power. + */ +#define IDLE_CALC_LIMIT (HZ * 100) +#define IDLE_LEAKY_MAX 16 + +static void (*original_pm_idle)(void); + +extern void default_idle(void); + +/** + * apm_cpu_idle - cpu idling for APM capable Linux + * + * This is the idling function the kernel executes when APM is available. It + * tries to do BIOS powermanagement based on the average system idle time. + * Furthermore it calls the system default idle routine. + */ + +static void apm_cpu_idle(void) +{ + static int use_apm_idle; /* = 0 */ + static unsigned int last_jiffies; /* = 0 */ + static unsigned int last_stime; /* = 0 */ + + int apm_idle_done = 0; + unsigned int jiffies_since_last_check = jiffies - last_jiffies; + unsigned int bucket; + +recalc: + if (jiffies_since_last_check > IDLE_CALC_LIMIT) { + use_apm_idle = 0; + last_jiffies = jiffies; + last_stime = current->stime; + } else if (jiffies_since_last_check > idle_period) { + unsigned int idle_percentage; + + idle_percentage = current->stime - last_stime; + idle_percentage *= 100; + idle_percentage /= jiffies_since_last_check; + use_apm_idle = (idle_percentage > idle_threshold); + if (apm_info.forbid_idle) + use_apm_idle = 0; + last_jiffies = jiffies; + last_stime = current->stime; + } + + bucket = IDLE_LEAKY_MAX; + + while (!need_resched()) { + if (use_apm_idle) { + unsigned int t; + + t = jiffies; + switch (apm_do_idle()) { + case 0: apm_idle_done = 1; + if (t != jiffies) { + if (bucket) { + bucket = IDLE_LEAKY_MAX; + continue; + } + } else if (bucket) { + bucket--; + continue; + } + break; + case 1: apm_idle_done = 1; + break; + default: /* BIOS refused */ + break; + } + } + if (original_pm_idle) + original_pm_idle(); + else + default_idle(); + jiffies_since_last_check = jiffies - last_jiffies; + if (jiffies_since_last_check > idle_period) + goto recalc; + } + + if (apm_idle_done) + apm_do_busy(); +} + +/** + * apm_power_off - ask the BIOS to power off + * + * Handle the power off sequence. This is the one piece of code we + * will execute even on SMP machines. In order to deal with BIOS + * bugs we support real mode APM BIOS power off calls. We also make + * the SMP call on CPU0 as some systems will only honour this call + * on their first cpu. + */ + +static void apm_power_off(void) +{ + unsigned char po_bios_call[] = { + 0xb8, 0x00, 0x10, /* movw $0x1000,ax */ + 0x8e, 0xd0, /* movw ax,ss */ + 0xbc, 0x00, 0xf0, /* movw $0xf000,sp */ + 0xb8, 0x07, 0x53, /* movw $0x5307,ax */ + 0xbb, 0x01, 0x00, /* movw $0x0001,bx */ + 0xb9, 0x03, 0x00, /* movw $0x0003,cx */ + 0xcd, 0x15 /* int $0x15 */ + }; + + /* + * This may be called on an SMP machine. + */ +#ifdef CONFIG_SMP + /* Some bioses don't like being called from CPU != 0 */ + set_cpus_allowed(current, cpumask_of_cpu(0)); + BUG_ON(smp_processor_id() != 0); +#endif + if (apm_info.realmode_power_off) + { + (void)apm_save_cpus(); + machine_real_restart(po_bios_call, sizeof(po_bios_call)); + } + else + (void) set_system_power_state(APM_STATE_OFF); +} + +#ifdef CONFIG_APM_DO_ENABLE + +/** + * apm_enable_power_management - enable BIOS APM power management + * @enable: enable yes/no + * + * Enable or disable the APM BIOS power services. + */ + +static int apm_enable_power_management(int enable) +{ + u32 eax; + + if ((enable == 0) && (apm_info.bios.flags & APM_BIOS_DISENGAGED)) + return APM_NOT_ENGAGED; + if (apm_bios_call_simple(APM_FUNC_ENABLE_PM, APM_DEVICE_BALL, + enable, &eax)) + return (eax >> 8) & 0xff; + if (enable) + apm_info.bios.flags &= ~APM_BIOS_DISABLED; + else + apm_info.bios.flags |= APM_BIOS_DISABLED; + return APM_SUCCESS; +} +#endif + +/** + * apm_get_power_status - get current power state + * @status: returned status + * @bat: battery info + * @life: estimated life + * + * Obtain the current power status from the APM BIOS. We return a + * status which gives the rough battery status, and current power + * source. The bat value returned give an estimate as a percentage + * of life and a status value for the battery. The estimated life + * if reported is a lifetime in secodnds/minutes at current powwer + * consumption. + */ + +static int apm_get_power_status(u_short *status, u_short *bat, u_short *life) +{ + u32 eax; + u32 ebx; + u32 ecx; + u32 edx; + u32 dummy; + + if (apm_info.get_power_status_broken) + return APM_32_UNSUPPORTED; + if (apm_bios_call(APM_FUNC_GET_STATUS, APM_DEVICE_ALL, 0, + &eax, &ebx, &ecx, &edx, &dummy)) + return (eax >> 8) & 0xff; + *status = ebx; + *bat = ecx; + if (apm_info.get_power_status_swabinminutes) { + *life = swab16((u16)edx); + *life |= 0x8000; + } else + *life = edx; + return APM_SUCCESS; +} + +#if 0 +static int apm_get_battery_status(u_short which, u_short *status, + u_short *bat, u_short *life, u_short *nbat) +{ + u32 eax; + u32 ebx; + u32 ecx; + u32 edx; + u32 esi; + + if (apm_info.connection_version < 0x0102) { + /* pretend we only have one battery. */ + if (which != 1) + return APM_BAD_DEVICE; + *nbat = 1; + return apm_get_power_status(status, bat, life); + } + + if (apm_bios_call(APM_FUNC_GET_STATUS, (0x8000 | (which)), 0, &eax, + &ebx, &ecx, &edx, &esi)) + return (eax >> 8) & 0xff; + *status = ebx; + *bat = ecx; + *life = edx; + *nbat = esi; + return APM_SUCCESS; +} +#endif + +/** + * apm_engage_power_management - enable PM on a device + * @device: identity of device + * @enable: on/off + * + * Activate or deactive power management on either a specific device + * or the entire system (%APM_DEVICE_ALL). + */ + +static int apm_engage_power_management(u_short device, int enable) +{ + u32 eax; + + if ((enable == 0) && (device == APM_DEVICE_ALL) + && (apm_info.bios.flags & APM_BIOS_DISABLED)) + return APM_DISABLED; + if (apm_bios_call_simple(APM_FUNC_ENGAGE_PM, device, enable, &eax)) + return (eax >> 8) & 0xff; + if (device == APM_DEVICE_ALL) { + if (enable) + apm_info.bios.flags &= ~APM_BIOS_DISENGAGED; + else + apm_info.bios.flags |= APM_BIOS_DISENGAGED; + } + return APM_SUCCESS; +} + +#if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT) + +/** + * apm_console_blank - blank the display + * @blank: on/off + * + * Attempt to blank the console, firstly by blanking just video device + * zero, and if that fails (some BIOSes don't support it) then it blanks + * all video devices. Typically the BIOS will do laptop backlight and + * monitor powerdown for us. + */ + +static int apm_console_blank(int blank) +{ + int error; + u_short state; + + state = blank ? APM_STATE_STANDBY : APM_STATE_READY; + /* Blank the first display device */ + error = set_power_state(0x100, state); + if ((error != APM_SUCCESS) && (error != APM_NO_ERROR)) { + /* try to blank them all instead */ + error = set_power_state(0x1ff, state); + if ((error != APM_SUCCESS) && (error != APM_NO_ERROR)) + /* try to blank device one instead */ + error = set_power_state(0x101, state); + } + if ((error == APM_SUCCESS) || (error == APM_NO_ERROR)) + return 1; + if (error == APM_NOT_ENGAGED) { + static int tried; + int eng_error; + if (tried++ == 0) { + eng_error = apm_engage_power_management(APM_DEVICE_ALL, 1); + if (eng_error) { + apm_error("set display", error); + apm_error("engage interface", eng_error); + return 0; + } else + return apm_console_blank(blank); + } + } + apm_error("set display", error); + return 0; +} +#endif + +static int queue_empty(struct apm_user *as) +{ + return as->event_head == as->event_tail; +} + +static apm_event_t get_queued_event(struct apm_user *as) +{ + as->event_tail = (as->event_tail + 1) % APM_MAX_EVENTS; + return as->events[as->event_tail]; +} + +static void queue_event(apm_event_t event, struct apm_user *sender) +{ + struct apm_user * as; + + spin_lock(&user_list_lock); + if (user_list == NULL) + goto out; + for (as = user_list; as != NULL; as = as->next) { + if ((as == sender) || (!as->reader)) + continue; + as->event_head = (as->event_head + 1) % APM_MAX_EVENTS; + if (as->event_head == as->event_tail) { + static int notified; + + if (notified++ == 0) + printk(KERN_ERR "apm: an event queue overflowed\n"); + as->event_tail = (as->event_tail + 1) % APM_MAX_EVENTS; + } + as->events[as->event_head] = event; + if ((!as->suser) || (!as->writer)) + continue; + switch (event) { + case APM_SYS_SUSPEND: + case APM_USER_SUSPEND: + as->suspends_pending++; + suspends_pending++; + break; + + case APM_SYS_STANDBY: + case APM_USER_STANDBY: + as->standbys_pending++; + standbys_pending++; + break; + } + } + wake_up_interruptible(&apm_waitqueue); +out: + spin_unlock(&user_list_lock); +} + +static void set_time(void) +{ + if (got_clock_diff) { /* Must know time zone in order to set clock */ + xtime.tv_sec = get_cmos_time() + clock_cmos_diff; + xtime.tv_nsec = 0; + } +} + +static void get_time_diff(void) +{ +#ifndef CONFIG_APM_RTC_IS_GMT + /* + * Estimate time zone so that set_time can update the clock + */ + clock_cmos_diff = -get_cmos_time(); + clock_cmos_diff += get_seconds(); + got_clock_diff = 1; +#endif +} + +static void reinit_timer(void) +{ +#ifdef INIT_TIMER_AFTER_SUSPEND + unsigned long flags; + extern spinlock_t i8253_lock; + + spin_lock_irqsave(&i8253_lock, flags); + /* set the clock to 100 Hz */ + outb_p(0x34, PIT_MODE); /* binary, mode 2, LSB/MSB, ch 0 */ + udelay(10); + outb_p(LATCH & 0xff, PIT_CH0); /* LSB */ + udelay(10); + outb(LATCH >> 8, PIT_CH0); /* MSB */ + udelay(10); + spin_unlock_irqrestore(&i8253_lock, flags); +#endif +} + +static int suspend(int vetoable) +{ + int err; + struct apm_user *as; + + if (pm_send_all(PM_SUSPEND, (void *)3)) { + /* Vetoed */ + if (vetoable) { + if (apm_info.connection_version > 0x100) + set_system_power_state(APM_STATE_REJECT); + err = -EBUSY; + ignore_sys_suspend = 0; + printk(KERN_WARNING "apm: suspend was vetoed.\n"); + goto out; + } + printk(KERN_CRIT "apm: suspend was vetoed, but suspending anyway.\n"); + } + + device_suspend(PMSG_SUSPEND); + local_irq_disable(); + device_power_down(PMSG_SUSPEND); + + /* serialize with the timer interrupt */ + write_seqlock(&xtime_lock); + + /* protect against access to timer chip registers */ + spin_lock(&i8253_lock); + + get_time_diff(); + /* + * Irq spinlock must be dropped around set_system_power_state. + * We'll undo any timer changes due to interrupts below. + */ + spin_unlock(&i8253_lock); + write_sequnlock(&xtime_lock); + local_irq_enable(); + + save_processor_state(); + err = set_system_power_state(APM_STATE_SUSPEND); + ignore_normal_resume = 1; + restore_processor_state(); + + local_irq_disable(); + write_seqlock(&xtime_lock); + spin_lock(&i8253_lock); + reinit_timer(); + set_time(); + + spin_unlock(&i8253_lock); + write_sequnlock(&xtime_lock); + + if (err == APM_NO_ERROR) + err = APM_SUCCESS; + if (err != APM_SUCCESS) + apm_error("suspend", err); + err = (err == APM_SUCCESS) ? 0 : -EIO; + device_power_up(); + local_irq_enable(); + device_resume(); + pm_send_all(PM_RESUME, (void *)0); + queue_event(APM_NORMAL_RESUME, NULL); + out: + spin_lock(&user_list_lock); + for (as = user_list; as != NULL; as = as->next) { + as->suspend_wait = 0; + as->suspend_result = err; + } + spin_unlock(&user_list_lock); + wake_up_interruptible(&apm_suspend_waitqueue); + return err; +} + +static void standby(void) +{ + int err; + + local_irq_disable(); + device_power_down(PMSG_SUSPEND); + /* serialize with the timer interrupt */ + write_seqlock(&xtime_lock); + /* If needed, notify drivers here */ + get_time_diff(); + write_sequnlock(&xtime_lock); + local_irq_enable(); + + err = set_system_power_state(APM_STATE_STANDBY); + if ((err != APM_SUCCESS) && (err != APM_NO_ERROR)) + apm_error("standby", err); + + local_irq_disable(); + device_power_up(); + local_irq_enable(); +} + +static apm_event_t get_event(void) +{ + int error; + apm_event_t event; + apm_eventinfo_t info; + + static int notified; + + /* we don't use the eventinfo */ + error = apm_get_event(&event, &info); + if (error == APM_SUCCESS) + return event; + + if ((error != APM_NO_EVENTS) && (notified++ == 0)) + apm_error("get_event", error); + + return 0; +} + +static void check_events(void) +{ + apm_event_t event; + static unsigned long last_resume; + static int ignore_bounce; + + while ((event = get_event()) != 0) { + if (debug) { + if (event <= NR_APM_EVENT_NAME) + printk(KERN_DEBUG "apm: received %s notify\n", + apm_event_name[event - 1]); + else + printk(KERN_DEBUG "apm: received unknown " + "event 0x%02x\n", event); + } + if (ignore_bounce + && ((jiffies - last_resume) > bounce_interval)) + ignore_bounce = 0; + + switch (event) { + case APM_SYS_STANDBY: + case APM_USER_STANDBY: + queue_event(event, NULL); + if (standbys_pending <= 0) + standby(); + break; + + case APM_USER_SUSPEND: +#ifdef CONFIG_APM_IGNORE_USER_SUSPEND + if (apm_info.connection_version > 0x100) + set_system_power_state(APM_STATE_REJECT); + break; +#endif + case APM_SYS_SUSPEND: + if (ignore_bounce) { + if (apm_info.connection_version > 0x100) + set_system_power_state(APM_STATE_REJECT); + break; + } + /* + * If we are already processing a SUSPEND, + * then further SUSPEND events from the BIOS + * will be ignored. We also return here to + * cope with the fact that the Thinkpads keep + * sending a SUSPEND event until something else + * happens! + */ + if (ignore_sys_suspend) + return; + ignore_sys_suspend = 1; + queue_event(event, NULL); + if (suspends_pending <= 0) + (void) suspend(1); + break; + + case APM_NORMAL_RESUME: + case APM_CRITICAL_RESUME: + case APM_STANDBY_RESUME: + ignore_sys_suspend = 0; + last_resume = jiffies; + ignore_bounce = 1; + if ((event != APM_NORMAL_RESUME) + || (ignore_normal_resume == 0)) { + write_seqlock_irq(&xtime_lock); + set_time(); + write_sequnlock_irq(&xtime_lock); + device_resume(); + pm_send_all(PM_RESUME, (void *)0); + queue_event(event, NULL); + } + ignore_normal_resume = 0; + break; + + case APM_CAPABILITY_CHANGE: + case APM_LOW_BATTERY: + case APM_POWER_STATUS_CHANGE: + queue_event(event, NULL); + /* If needed, notify drivers here */ + break; + + case APM_UPDATE_TIME: + write_seqlock_irq(&xtime_lock); + set_time(); + write_sequnlock_irq(&xtime_lock); + break; + + case APM_CRITICAL_SUSPEND: + /* + * We are not allowed to reject a critical suspend. + */ + (void) suspend(0); + break; + } + } +} + +static void apm_event_handler(void) +{ + static int pending_count = 4; + int err; + + if ((standbys_pending > 0) || (suspends_pending > 0)) { + if ((apm_info.connection_version > 0x100) && + (pending_count-- <= 0)) { + pending_count = 4; + if (debug) + printk(KERN_DEBUG "apm: setting state busy\n"); + err = set_system_power_state(APM_STATE_BUSY); + if (err) + apm_error("busy", err); + } + } else + pending_count = 4; + check_events(); +} + +/* + * This is the APM thread main loop. + */ + +static void apm_mainloop(void) +{ + DECLARE_WAITQUEUE(wait, current); + + add_wait_queue(&apm_waitqueue, &wait); + set_current_state(TASK_INTERRUPTIBLE); + for (;;) { + schedule_timeout(APM_CHECK_TIMEOUT); + if (exit_kapmd) + break; + /* + * Ok, check all events, check for idle (and mark us sleeping + * so as not to count towards the load average).. + */ + set_current_state(TASK_INTERRUPTIBLE); + apm_event_handler(); + } + remove_wait_queue(&apm_waitqueue, &wait); +} + +static int check_apm_user(struct apm_user *as, const char *func) +{ + if ((as == NULL) || (as->magic != APM_BIOS_MAGIC)) { + printk(KERN_ERR "apm: %s passed bad filp\n", func); + return 1; + } + return 0; +} + +static ssize_t do_read(struct file *fp, char __user *buf, size_t count, loff_t *ppos) +{ + struct apm_user * as; + int i; + apm_event_t event; + + as = fp->private_data; + if (check_apm_user(as, "read")) + return -EIO; + if ((int)count < sizeof(apm_event_t)) + return -EINVAL; + if ((queue_empty(as)) && (fp->f_flags & O_NONBLOCK)) + return -EAGAIN; + wait_event_interruptible(apm_waitqueue, !queue_empty(as)); + i = count; + while ((i >= sizeof(event)) && !queue_empty(as)) { + event = get_queued_event(as); + if (copy_to_user(buf, &event, sizeof(event))) { + if (i < count) + break; + return -EFAULT; + } + switch (event) { + case APM_SYS_SUSPEND: + case APM_USER_SUSPEND: + as->suspends_read++; + break; + + case APM_SYS_STANDBY: + case APM_USER_STANDBY: + as->standbys_read++; + break; + } + buf += sizeof(event); + i -= sizeof(event); + } + if (i < count) + return count - i; + if (signal_pending(current)) + return -ERESTARTSYS; + return 0; +} + +static unsigned int do_poll(struct file *fp, poll_table * wait) +{ + struct apm_user * as; + + as = fp->private_data; + if (check_apm_user(as, "poll")) + return 0; + poll_wait(fp, &apm_waitqueue, wait); + if (!queue_empty(as)) + return POLLIN | POLLRDNORM; + return 0; +} + +static int do_ioctl(struct inode * inode, struct file *filp, + u_int cmd, u_long arg) +{ + struct apm_user * as; + + as = filp->private_data; + if (check_apm_user(as, "ioctl")) + return -EIO; + if ((!as->suser) || (!as->writer)) + return -EPERM; + switch (cmd) { + case APM_IOC_STANDBY: + if (as->standbys_read > 0) { + as->standbys_read--; + as->standbys_pending--; + standbys_pending--; + } else + queue_event(APM_USER_STANDBY, as); + if (standbys_pending <= 0) + standby(); + break; + case APM_IOC_SUSPEND: + if (as->suspends_read > 0) { + as->suspends_read--; + as->suspends_pending--; + suspends_pending--; + } else + queue_event(APM_USER_SUSPEND, as); + if (suspends_pending <= 0) { + return suspend(1); + } else { + as->suspend_wait = 1; + wait_event_interruptible(apm_suspend_waitqueue, + as->suspend_wait == 0); + return as->suspend_result; + } + break; + default: + return -EINVAL; + } + return 0; +} + +static int do_release(struct inode * inode, struct file * filp) +{ + struct apm_user * as; + + as = filp->private_data; + if (check_apm_user(as, "release")) + return 0; + filp->private_data = NULL; + if (as->standbys_pending > 0) { + standbys_pending -= as->standbys_pending; + if (standbys_pending <= 0) + standby(); + } + if (as->suspends_pending > 0) { + suspends_pending -= as->suspends_pending; + if (suspends_pending <= 0) + (void) suspend(1); + } + spin_lock(&user_list_lock); + if (user_list == as) + user_list = as->next; + else { + struct apm_user * as1; + + for (as1 = user_list; + (as1 != NULL) && (as1->next != as); + as1 = as1->next) + ; + if (as1 == NULL) + printk(KERN_ERR "apm: filp not in user list\n"); + else + as1->next = as->next; + } + spin_unlock(&user_list_lock); + kfree(as); + return 0; +} + +static int do_open(struct inode * inode, struct file * filp) +{ + struct apm_user * as; + + as = (struct apm_user *)kmalloc(sizeof(*as), GFP_KERNEL); + if (as == NULL) { + printk(KERN_ERR "apm: cannot allocate struct of size %d bytes\n", + sizeof(*as)); + return -ENOMEM; + } + as->magic = APM_BIOS_MAGIC; + as->event_tail = as->event_head = 0; + as->suspends_pending = as->standbys_pending = 0; + as->suspends_read = as->standbys_read = 0; + /* + * XXX - this is a tiny bit broken, when we consider BSD + * process accounting. If the device is opened by root, we + * instantly flag that we used superuser privs. Who knows, + * we might close the device immediately without doing a + * privileged operation -- cevans + */ + as->suser = capable(CAP_SYS_ADMIN); + as->writer = (filp->f_mode & FMODE_WRITE) == FMODE_WRITE; + as->reader = (filp->f_mode & FMODE_READ) == FMODE_READ; + spin_lock(&user_list_lock); + as->next = user_list; + user_list = as; + spin_unlock(&user_list_lock); + filp->private_data = as; + return 0; +} + +static int apm_get_info(char *buf, char **start, off_t fpos, int length) +{ + char * p; + unsigned short bx; + unsigned short cx; + unsigned short dx; + int error; + unsigned short ac_line_status = 0xff; + unsigned short battery_status = 0xff; + unsigned short battery_flag = 0xff; + int percentage = -1; + int time_units = -1; + char *units = "?"; + + p = buf; + + if ((num_online_cpus() == 1) && + !(error = apm_get_power_status(&bx, &cx, &dx))) { + ac_line_status = (bx >> 8) & 0xff; + battery_status = bx & 0xff; + if ((cx & 0xff) != 0xff) + percentage = cx & 0xff; + + if (apm_info.connection_version > 0x100) { + battery_flag = (cx >> 8) & 0xff; + if (dx != 0xffff) { + units = (dx & 0x8000) ? "min" : "sec"; + time_units = dx & 0x7fff; + } + } + } + /* Arguments, with symbols from linux/apm_bios.h. Information is + from the Get Power Status (0x0a) call unless otherwise noted. + + 0) Linux driver version (this will change if format changes) + 1) APM BIOS Version. Usually 1.0, 1.1 or 1.2. + 2) APM flags from APM Installation Check (0x00): + bit 0: APM_16_BIT_SUPPORT + bit 1: APM_32_BIT_SUPPORT + bit 2: APM_IDLE_SLOWS_CLOCK + bit 3: APM_BIOS_DISABLED + bit 4: APM_BIOS_DISENGAGED + 3) AC line status + 0x00: Off-line + 0x01: On-line + 0x02: On backup power (BIOS >= 1.1 only) + 0xff: Unknown + 4) Battery status + 0x00: High + 0x01: Low + 0x02: Critical + 0x03: Charging + 0x04: Selected battery not present (BIOS >= 1.2 only) + 0xff: Unknown + 5) Battery flag + bit 0: High + bit 1: Low + bit 2: Critical + bit 3: Charging + bit 7: No system battery + 0xff: Unknown + 6) Remaining battery life (percentage of charge): + 0-100: valid + -1: Unknown + 7) Remaining battery life (time units): + Number of remaining minutes or seconds + -1: Unknown + 8) min = minutes; sec = seconds */ + + p += sprintf(p, "%s %d.%d 0x%02x 0x%02x 0x%02x 0x%02x %d%% %d %s\n", + driver_version, + (apm_info.bios.version >> 8) & 0xff, + apm_info.bios.version & 0xff, + apm_info.bios.flags, + ac_line_status, + battery_status, + battery_flag, + percentage, + time_units, + units); + + return p - buf; +} + +static int apm(void *unused) +{ + unsigned short bx; + unsigned short cx; + unsigned short dx; + int error; + char * power_stat; + char * bat_stat; + + kapmd_running = 1; + + daemonize("kapmd"); + + current->flags |= PF_NOFREEZE; + +#ifdef CONFIG_SMP + /* 2002/08/01 - WT + * This is to avoid random crashes at boot time during initialization + * on SMP systems in case of "apm=power-off" mode. Seen on ASUS A7M266D. + * Some bioses don't like being called from CPU != 0. + * Method suggested by Ingo Molnar. + */ + set_cpus_allowed(current, cpumask_of_cpu(0)); + BUG_ON(smp_processor_id() != 0); +#endif + + if (apm_info.connection_version == 0) { + apm_info.connection_version = apm_info.bios.version; + if (apm_info.connection_version > 0x100) { + /* + * We only support BIOSs up to version 1.2 + */ + if (apm_info.connection_version > 0x0102) + apm_info.connection_version = 0x0102; + error = apm_driver_version(&apm_info.connection_version); + if (error != APM_SUCCESS) { + apm_error("driver version", error); + /* Fall back to an APM 1.0 connection. */ + apm_info.connection_version = 0x100; + } + } + } + + if (debug) + printk(KERN_INFO "apm: Connection version %d.%d\n", + (apm_info.connection_version >> 8) & 0xff, + apm_info.connection_version & 0xff); + +#ifdef CONFIG_APM_DO_ENABLE + if (apm_info.bios.flags & APM_BIOS_DISABLED) { + /* + * This call causes my NEC UltraLite Versa 33/C to hang if it + * is booted with PM disabled but not in the docking station. + * Unfortunate ... + */ + error = apm_enable_power_management(1); + if (error) { + apm_error("enable power management", error); + return -1; + } + } +#endif + + if ((apm_info.bios.flags & APM_BIOS_DISENGAGED) + && (apm_info.connection_version > 0x0100)) { + error = apm_engage_power_management(APM_DEVICE_ALL, 1); + if (error) { + apm_error("engage power management", error); + return -1; + } + } + + if (debug && (num_online_cpus() == 1 || smp )) { + error = apm_get_power_status(&bx, &cx, &dx); + if (error) + printk(KERN_INFO "apm: power status not available\n"); + else { + switch ((bx >> 8) & 0xff) { + case 0: power_stat = "off line"; break; + case 1: power_stat = "on line"; break; + case 2: power_stat = "on backup power"; break; + default: power_stat = "unknown"; break; + } + switch (bx & 0xff) { + case 0: bat_stat = "high"; break; + case 1: bat_stat = "low"; break; + case 2: bat_stat = "critical"; break; + case 3: bat_stat = "charging"; break; + default: bat_stat = "unknown"; break; + } + printk(KERN_INFO + "apm: AC %s, battery status %s, battery life ", + power_stat, bat_stat); + if ((cx & 0xff) == 0xff) + printk("unknown\n"); + else + printk("%d%%\n", cx & 0xff); + if (apm_info.connection_version > 0x100) { + printk(KERN_INFO + "apm: battery flag 0x%02x, battery life ", + (cx >> 8) & 0xff); + if (dx == 0xffff) + printk("unknown\n"); + else + printk("%d %s\n", dx & 0x7fff, + (dx & 0x8000) ? + "minutes" : "seconds"); + } + } + } + + /* Install our power off handler.. */ + if (power_off) + pm_power_off = apm_power_off; + + if (num_online_cpus() == 1 || smp) { +#if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT) + console_blank_hook = apm_console_blank; +#endif + apm_mainloop(); +#if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT) + console_blank_hook = NULL; +#endif + } + kapmd_running = 0; + + return 0; +} + +#ifndef MODULE +static int __init apm_setup(char *str) +{ + int invert; + + while ((str != NULL) && (*str != '\0')) { + if (strncmp(str, "off", 3) == 0) + apm_disabled = 1; + if (strncmp(str, "on", 2) == 0) + apm_disabled = 0; + if ((strncmp(str, "bounce-interval=", 16) == 0) || + (strncmp(str, "bounce_interval=", 16) == 0)) + bounce_interval = simple_strtol(str + 16, NULL, 0); + if ((strncmp(str, "idle-threshold=", 15) == 0) || + (strncmp(str, "idle_threshold=", 15) == 0)) + idle_threshold = simple_strtol(str + 15, NULL, 0); + if ((strncmp(str, "idle-period=", 12) == 0) || + (strncmp(str, "idle_period=", 12) == 0)) + idle_period = simple_strtol(str + 12, NULL, 0); + invert = (strncmp(str, "no-", 3) == 0) || + (strncmp(str, "no_", 3) == 0); + if (invert) + str += 3; + if (strncmp(str, "debug", 5) == 0) + debug = !invert; + if ((strncmp(str, "power-off", 9) == 0) || + (strncmp(str, "power_off", 9) == 0)) + power_off = !invert; + if (strncmp(str, "smp", 3) == 0) + { + smp = !invert; + idle_threshold = 100; + } + if ((strncmp(str, "allow-ints", 10) == 0) || + (strncmp(str, "allow_ints", 10) == 0)) + apm_info.allow_ints = !invert; + if ((strncmp(str, "broken-psr", 10) == 0) || + (strncmp(str, "broken_psr", 10) == 0)) + apm_info.get_power_status_broken = !invert; + if ((strncmp(str, "realmode-power-off", 18) == 0) || + (strncmp(str, "realmode_power_off", 18) == 0)) + apm_info.realmode_power_off = !invert; + str = strchr(str, ','); + if (str != NULL) + str += strspn(str, ", \t"); + } + return 1; +} + +__setup("apm=", apm_setup); +#endif + +static struct file_operations apm_bios_fops = { + .owner = THIS_MODULE, + .read = do_read, + .poll = do_poll, + .ioctl = do_ioctl, + .open = do_open, + .release = do_release, +}; + +static struct miscdevice apm_device = { + APM_MINOR_DEV, + "apm_bios", + &apm_bios_fops +}; + + +/* Simple "print if true" callback */ +static int __init print_if_true(struct dmi_system_id *d) +{ + printk("%s\n", d->ident); + return 0; +} + +/* + * Some Bioses enable the PS/2 mouse (touchpad) at resume, even if it was + * disabled before the suspend. Linux used to get terribly confused by that. + */ +static int __init broken_ps2_resume(struct dmi_system_id *d) +{ + printk(KERN_INFO "%s machine detected. Mousepad Resume Bug workaround hopefully not needed.\n", d->ident); + return 0; +} + +/* Some bioses have a broken protected mode poweroff and need to use realmode */ +static int __init set_realmode_power_off(struct dmi_system_id *d) +{ + if (apm_info.realmode_power_off == 0) { + apm_info.realmode_power_off = 1; + printk(KERN_INFO "%s bios detected. Using realmode poweroff only.\n", d->ident); + } + return 0; +} + +/* Some laptops require interrupts to be enabled during APM calls */ +static int __init set_apm_ints(struct dmi_system_id *d) +{ + if (apm_info.allow_ints == 0) { + apm_info.allow_ints = 1; + printk(KERN_INFO "%s machine detected. Enabling interrupts during APM calls.\n", d->ident); + } + return 0; +} + +/* Some APM bioses corrupt memory or just plain do not work */ +static int __init apm_is_horked(struct dmi_system_id *d) +{ + if (apm_info.disabled == 0) { + apm_info.disabled = 1; + printk(KERN_INFO "%s machine detected. Disabling APM.\n", d->ident); + } + return 0; +} + +static int __init apm_is_horked_d850md(struct dmi_system_id *d) +{ + if (apm_info.disabled == 0) { + apm_info.disabled = 1; + printk(KERN_INFO "%s machine detected. Disabling APM.\n", d->ident); + printk(KERN_INFO "This bug is fixed in bios P15 which is available for \n"); + printk(KERN_INFO "download from support.intel.com \n"); + } + return 0; +} + +/* Some APM bioses hang on APM idle calls */ +static int __init apm_likes_to_melt(struct dmi_system_id *d) +{ + if (apm_info.forbid_idle == 0) { + apm_info.forbid_idle = 1; + printk(KERN_INFO "%s machine detected. Disabling APM idle calls.\n", d->ident); + } + return 0; +} + +/* + * Check for clue free BIOS implementations who use + * the following QA technique + * + * [ Write BIOS Code ]<------ + * | ^ + * < Does it Compile >----N-- + * |Y ^ + * < Does it Boot Win98 >-N-- + * |Y + * [Ship It] + * + * Phoenix A04 08/24/2000 is known bad (Dell Inspiron 5000e) + * Phoenix A07 09/29/2000 is known good (Dell Inspiron 5000) + */ +static int __init broken_apm_power(struct dmi_system_id *d) +{ + apm_info.get_power_status_broken = 1; + printk(KERN_WARNING "BIOS strings suggest APM bugs, disabling power status reporting.\n"); + return 0; +} + +/* + * This bios swaps the APM minute reporting bytes over (Many sony laptops + * have this problem). + */ +static int __init swab_apm_power_in_minutes(struct dmi_system_id *d) +{ + apm_info.get_power_status_swabinminutes = 1; + printk(KERN_WARNING "BIOS strings suggest APM reports battery life in minutes and wrong byte order.\n"); + return 0; +} + +static struct dmi_system_id __initdata apm_dmi_table[] = { + { + print_if_true, + KERN_WARNING "IBM T23 - BIOS 1.03b+ and controller firmware 1.02+ may be needed for Linux APM.", + { DMI_MATCH(DMI_SYS_VENDOR, "IBM"), + DMI_MATCH(DMI_BIOS_VERSION, "1AET38WW (1.01b)"), }, + }, + { /* Handle problems with APM on the C600 */ + broken_ps2_resume, "Dell Latitude C600", + { DMI_MATCH(DMI_SYS_VENDOR, "Dell"), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude C600"), }, + }, + { /* Allow interrupts during suspend on Dell Latitude laptops*/ + set_apm_ints, "Dell Latitude", + { DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "Latitude C510"), } + }, + { /* APM crashes */ + apm_is_horked, "Dell Inspiron 2500", + { DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 2500"), + DMI_MATCH(DMI_BIOS_VENDOR,"Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION,"A11"), }, + }, + { /* Allow interrupts during suspend on Dell Inspiron laptops*/ + set_apm_ints, "Dell Inspiron", { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 4000"), }, + }, + { /* Handle problems with APM on Inspiron 5000e */ + broken_apm_power, "Dell Inspiron 5000e", + { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION, "A04"), + DMI_MATCH(DMI_BIOS_DATE, "08/24/2000"), }, + }, + { /* Handle problems with APM on Inspiron 2500 */ + broken_apm_power, "Dell Inspiron 2500", + { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION, "A12"), + DMI_MATCH(DMI_BIOS_DATE, "02/04/2002"), }, + }, + { /* APM crashes */ + apm_is_horked, "Dell Dimension 4100", + { DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "XPS-Z"), + DMI_MATCH(DMI_BIOS_VENDOR,"Intel Corp."), + DMI_MATCH(DMI_BIOS_VERSION,"A11"), }, + }, + { /* Allow interrupts during suspend on Compaq Laptops*/ + set_apm_ints, "Compaq 12XL125", + { DMI_MATCH(DMI_SYS_VENDOR, "Compaq"), + DMI_MATCH(DMI_PRODUCT_NAME, "Compaq PC"), + DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION,"4.06"), }, + }, + { /* Allow interrupts during APM or the clock goes slow */ + set_apm_ints, "ASUSTeK", + { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "L8400K series Notebook PC"), }, + }, + { /* APM blows on shutdown */ + apm_is_horked, "ABIT KX7-333[R]", + { DMI_MATCH(DMI_BOARD_VENDOR, "ABIT"), + DMI_MATCH(DMI_BOARD_NAME, "VT8367-8233A (KX7-333[R])"), }, + }, + { /* APM crashes */ + apm_is_horked, "Trigem Delhi3", + { DMI_MATCH(DMI_SYS_VENDOR, "TriGem Computer, Inc"), + DMI_MATCH(DMI_PRODUCT_NAME, "Delhi3"), }, + }, + { /* APM crashes */ + apm_is_horked, "Fujitsu-Siemens", + { DMI_MATCH(DMI_BIOS_VENDOR, "hoenix/FUJITSU SIEMENS"), + DMI_MATCH(DMI_BIOS_VERSION, "Version1.01"), }, + }, + { /* APM crashes */ + apm_is_horked_d850md, "Intel D850MD", + { DMI_MATCH(DMI_BIOS_VENDOR, "Intel Corp."), + DMI_MATCH(DMI_BIOS_VERSION, "MV85010A.86A.0016.P07.0201251536"), }, + }, + { /* APM crashes */ + apm_is_horked, "Intel D810EMO", + { DMI_MATCH(DMI_BIOS_VENDOR, "Intel Corp."), + DMI_MATCH(DMI_BIOS_VERSION, "MO81010A.86A.0008.P04.0004170800"), }, + }, + { /* APM crashes */ + apm_is_horked, "Dell XPS-Z", + { DMI_MATCH(DMI_BIOS_VENDOR, "Intel Corp."), + DMI_MATCH(DMI_BIOS_VERSION, "A11"), + DMI_MATCH(DMI_PRODUCT_NAME, "XPS-Z"), }, + }, + { /* APM crashes */ + apm_is_horked, "Sharp PC-PJ/AX", + { DMI_MATCH(DMI_SYS_VENDOR, "SHARP"), + DMI_MATCH(DMI_PRODUCT_NAME, "PC-PJ/AX"), + DMI_MATCH(DMI_BIOS_VENDOR,"SystemSoft"), + DMI_MATCH(DMI_BIOS_VERSION,"Version R2.08"), }, + }, + { /* APM crashes */ + apm_is_horked, "Dell Inspiron 2500", + { DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"), + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 2500"), + DMI_MATCH(DMI_BIOS_VENDOR,"Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION,"A11"), }, + }, + { /* APM idle hangs */ + apm_likes_to_melt, "Jabil AMD", + { DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."), + DMI_MATCH(DMI_BIOS_VERSION, "0AASNP06"), }, + }, + { /* APM idle hangs */ + apm_likes_to_melt, "AMI Bios", + { DMI_MATCH(DMI_BIOS_VENDOR, "American Megatrends Inc."), + DMI_MATCH(DMI_BIOS_VERSION, "0AASNP05"), }, + }, + { /* Handle problems with APM on Sony Vaio PCG-N505X(DE) */ + swab_apm_power_in_minutes, "Sony VAIO", + { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION, "R0206H"), + DMI_MATCH(DMI_BIOS_DATE, "08/23/99"), }, + }, + { /* Handle problems with APM on Sony Vaio PCG-N505VX */ + swab_apm_power_in_minutes, "Sony VAIO", + { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION, "W2K06H0"), + DMI_MATCH(DMI_BIOS_DATE, "02/03/00"), }, + }, + { /* Handle problems with APM on Sony Vaio PCG-XG29 */ + swab_apm_power_in_minutes, "Sony VAIO", + { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION, "R0117A0"), + DMI_MATCH(DMI_BIOS_DATE, "04/25/00"), }, + }, + { /* Handle problems with APM on Sony Vaio PCG-Z600NE */ + swab_apm_power_in_minutes, "Sony VAIO", + { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION, "R0121Z1"), + DMI_MATCH(DMI_BIOS_DATE, "05/11/00"), }, + }, + { /* Handle problems with APM on Sony Vaio PCG-Z600NE */ + swab_apm_power_in_minutes, "Sony VAIO", + { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION, "WME01Z1"), + DMI_MATCH(DMI_BIOS_DATE, "08/11/00"), }, + }, + { /* Handle problems with APM on Sony Vaio PCG-Z600LEK(DE) */ + swab_apm_power_in_minutes, "Sony VAIO", + { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION, "R0206Z3"), + DMI_MATCH(DMI_BIOS_DATE, "12/25/00"), }, + }, + { /* Handle problems with APM on Sony Vaio PCG-Z505LS */ + swab_apm_power_in_minutes, "Sony VAIO", + { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION, "R0203D0"), + DMI_MATCH(DMI_BIOS_DATE, "05/12/00"), }, + }, + { /* Handle problems with APM on Sony Vaio PCG-Z505LS */ + swab_apm_power_in_minutes, "Sony VAIO", + { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION, "R0203Z3"), + DMI_MATCH(DMI_BIOS_DATE, "08/25/00"), }, + }, + { /* Handle problems with APM on Sony Vaio PCG-Z505LS (with updated BIOS) */ + swab_apm_power_in_minutes, "Sony VAIO", + { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION, "R0209Z3"), + DMI_MATCH(DMI_BIOS_DATE, "05/12/01"), }, + }, + { /* Handle problems with APM on Sony Vaio PCG-F104K */ + swab_apm_power_in_minutes, "Sony VAIO", + { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION, "R0204K2"), + DMI_MATCH(DMI_BIOS_DATE, "08/28/00"), }, + }, + + { /* Handle problems with APM on Sony Vaio PCG-C1VN/C1VE */ + swab_apm_power_in_minutes, "Sony VAIO", + { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION, "R0208P1"), + DMI_MATCH(DMI_BIOS_DATE, "11/09/00"), }, + }, + { /* Handle problems with APM on Sony Vaio PCG-C1VE */ + swab_apm_power_in_minutes, "Sony VAIO", + { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION, "R0204P1"), + DMI_MATCH(DMI_BIOS_DATE, "09/12/00"), }, + }, + { /* Handle problems with APM on Sony Vaio PCG-C1VE */ + swab_apm_power_in_minutes, "Sony VAIO", + { DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies LTD"), + DMI_MATCH(DMI_BIOS_VERSION, "WXPO1Z3"), + DMI_MATCH(DMI_BIOS_DATE, "10/26/01"), }, + }, + { /* broken PM poweroff bios */ + set_realmode_power_off, "Award Software v4.60 PGMA", + { DMI_MATCH(DMI_BIOS_VENDOR, "Award Software International, Inc."), + DMI_MATCH(DMI_BIOS_VERSION, "4.60 PGMA"), + DMI_MATCH(DMI_BIOS_DATE, "134526184"), }, + }, + + /* Generic per vendor APM settings */ + + { /* Allow interrupts during suspend on IBM laptops */ + set_apm_ints, "IBM", + { DMI_MATCH(DMI_SYS_VENDOR, "IBM"), }, + }, + + { } +}; + +/* + * Just start the APM thread. We do NOT want to do APM BIOS + * calls from anything but the APM thread, if for no other reason + * than the fact that we don't trust the APM BIOS. This way, + * most common APM BIOS problems that lead to protection errors + * etc will have at least some level of being contained... + * + * In short, if something bad happens, at least we have a choice + * of just killing the apm thread.. + */ +static int __init apm_init(void) +{ + struct proc_dir_entry *apm_proc; + int ret; + int i; + + dmi_check_system(apm_dmi_table); + + if (apm_info.bios.version == 0) { + printk(KERN_INFO "apm: BIOS not found.\n"); + return -ENODEV; + } + printk(KERN_INFO + "apm: BIOS version %d.%d Flags 0x%02x (Driver version %s)\n", + ((apm_info.bios.version >> 8) & 0xff), + (apm_info.bios.version & 0xff), + apm_info.bios.flags, + driver_version); + if ((apm_info.bios.flags & APM_32_BIT_SUPPORT) == 0) { + printk(KERN_INFO "apm: no 32 bit BIOS support\n"); + return -ENODEV; + } + + if (allow_ints) + apm_info.allow_ints = 1; + if (broken_psr) + apm_info.get_power_status_broken = 1; + if (realmode_power_off) + apm_info.realmode_power_off = 1; + /* User can override, but default is to trust DMI */ + if (apm_disabled != -1) + apm_info.disabled = apm_disabled; + + /* + * Fix for the Compaq Contura 3/25c which reports BIOS version 0.1 + * but is reportedly a 1.0 BIOS. + */ + if (apm_info.bios.version == 0x001) + apm_info.bios.version = 0x100; + + /* BIOS < 1.2 doesn't set cseg_16_len */ + if (apm_info.bios.version < 0x102) + apm_info.bios.cseg_16_len = 0; /* 64k */ + + if (debug) { + printk(KERN_INFO "apm: entry %x:%lx cseg16 %x dseg %x", + apm_info.bios.cseg, apm_info.bios.offset, + apm_info.bios.cseg_16, apm_info.bios.dseg); + if (apm_info.bios.version > 0x100) + printk(" cseg len %x, dseg len %x", + apm_info.bios.cseg_len, + apm_info.bios.dseg_len); + if (apm_info.bios.version > 0x101) + printk(" cseg16 len %x", apm_info.bios.cseg_16_len); + printk("\n"); + } + + if (apm_info.disabled) { + printk(KERN_NOTICE "apm: disabled on user request.\n"); + return -ENODEV; + } + if ((num_online_cpus() > 1) && !power_off && !smp) { + printk(KERN_NOTICE "apm: disabled - APM is not SMP safe.\n"); + apm_info.disabled = 1; + return -ENODEV; + } + if (PM_IS_ACTIVE()) { + printk(KERN_NOTICE "apm: overridden by ACPI.\n"); + apm_info.disabled = 1; + return -ENODEV; + } + pm_active = 1; + + /* + * Set up a segment that references the real mode segment 0x40 + * that extends up to the end of page zero (that we have reserved). + * This is for buggy BIOS's that refer to (real mode) segment 0x40 + * even though they are called in protected mode. + */ + set_base(bad_bios_desc, __va((unsigned long)0x40 << 4)); + _set_limit((char *)&bad_bios_desc, 4095 - (0x40 << 4)); + + apm_bios_entry.offset = apm_info.bios.offset; + apm_bios_entry.segment = APM_CS; + + for (i = 0; i < NR_CPUS; i++) { + set_base(get_cpu_gdt_table(i)[APM_CS >> 3], + __va((unsigned long)apm_info.bios.cseg << 4)); + set_base(get_cpu_gdt_table(i)[APM_CS_16 >> 3], + __va((unsigned long)apm_info.bios.cseg_16 << 4)); + set_base(get_cpu_gdt_table(i)[APM_DS >> 3], + __va((unsigned long)apm_info.bios.dseg << 4)); +#ifndef APM_RELAX_SEGMENTS + if (apm_info.bios.version == 0x100) { +#endif + /* For ASUS motherboard, Award BIOS rev 110 (and others?) */ + _set_limit((char *)&get_cpu_gdt_table(i)[APM_CS >> 3], 64 * 1024 - 1); + /* For some unknown machine. */ + _set_limit((char *)&get_cpu_gdt_table(i)[APM_CS_16 >> 3], 64 * 1024 - 1); + /* For the DEC Hinote Ultra CT475 (and others?) */ + _set_limit((char *)&get_cpu_gdt_table(i)[APM_DS >> 3], 64 * 1024 - 1); +#ifndef APM_RELAX_SEGMENTS + } else { + _set_limit((char *)&get_cpu_gdt_table(i)[APM_CS >> 3], + (apm_info.bios.cseg_len - 1) & 0xffff); + _set_limit((char *)&get_cpu_gdt_table(i)[APM_CS_16 >> 3], + (apm_info.bios.cseg_16_len - 1) & 0xffff); + _set_limit((char *)&get_cpu_gdt_table(i)[APM_DS >> 3], + (apm_info.bios.dseg_len - 1) & 0xffff); + /* workaround for broken BIOSes */ + if (apm_info.bios.cseg_len <= apm_info.bios.offset) + _set_limit((char *)&get_cpu_gdt_table(i)[APM_CS >> 3], 64 * 1024 -1); + if (apm_info.bios.dseg_len <= 0x40) { /* 0x40 * 4kB == 64kB */ + /* for the BIOS that assumes granularity = 1 */ + get_cpu_gdt_table(i)[APM_DS >> 3].b |= 0x800000; + printk(KERN_NOTICE "apm: we set the granularity of dseg.\n"); + } + } +#endif + } + + apm_proc = create_proc_info_entry("apm", 0, NULL, apm_get_info); + if (apm_proc) + apm_proc->owner = THIS_MODULE; + + ret = kernel_thread(apm, NULL, CLONE_KERNEL | SIGCHLD); + if (ret < 0) { + printk(KERN_ERR "apm: disabled - Unable to start kernel thread.\n"); + return -ENOMEM; + } + + if (num_online_cpus() > 1 && !smp ) { + printk(KERN_NOTICE + "apm: disabled - APM is not SMP safe (power off active).\n"); + return 0; + } + + misc_register(&apm_device); + + if (HZ != 100) + idle_period = (idle_period * HZ) / 100; + if (idle_threshold < 100) { + original_pm_idle = pm_idle; + pm_idle = apm_cpu_idle; + set_pm_idle = 1; + } + + return 0; +} + +static void __exit apm_exit(void) +{ + int error; + + if (set_pm_idle) { + pm_idle = original_pm_idle; + /* + * We are about to unload the current idle thread pm callback + * (pm_idle), Wait for all processors to update cached/local + * copies of pm_idle before proceeding. + */ + cpu_idle_wait(); + } + if (((apm_info.bios.flags & APM_BIOS_DISENGAGED) == 0) + && (apm_info.connection_version > 0x0100)) { + error = apm_engage_power_management(APM_DEVICE_ALL, 0); + if (error) + apm_error("disengage power management", error); + } + misc_deregister(&apm_device); + remove_proc_entry("apm", NULL); + if (power_off) + pm_power_off = NULL; + exit_kapmd = 1; + while (kapmd_running) + schedule(); + pm_active = 0; +} + +module_init(apm_init); +module_exit(apm_exit); + +MODULE_AUTHOR("Stephen Rothwell"); +MODULE_DESCRIPTION("Advanced Power Management"); +MODULE_LICENSE("GPL"); +module_param(debug, bool, 0644); +MODULE_PARM_DESC(debug, "Enable debug mode"); +module_param(power_off, bool, 0444); +MODULE_PARM_DESC(power_off, "Enable power off"); +module_param(bounce_interval, int, 0444); +MODULE_PARM_DESC(bounce_interval, + "Set the number of ticks to ignore suspend bounces"); +module_param(allow_ints, bool, 0444); +MODULE_PARM_DESC(allow_ints, "Allow interrupts during BIOS calls"); +module_param(broken_psr, bool, 0444); +MODULE_PARM_DESC(broken_psr, "BIOS has a broken GetPowerStatus call"); +module_param(realmode_power_off, bool, 0444); +MODULE_PARM_DESC(realmode_power_off, + "Switch to real mode before powering off"); +module_param(idle_threshold, int, 0444); +MODULE_PARM_DESC(idle_threshold, + "System idle percentage above which to make APM BIOS idle calls"); +module_param(idle_period, int, 0444); +MODULE_PARM_DESC(idle_period, + "Period (in sec/100) over which to caculate the idle percentage"); +module_param(smp, bool, 0444); +MODULE_PARM_DESC(smp, + "Set this to enable APM use on an SMP platform. Use with caution on older systems"); +MODULE_ALIAS_MISCDEV(APM_MINOR_DEV); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/cpu/Makefile --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/cpu/Makefile Mon Jan 30 17:18:27 2006 @@ -0,0 +1,24 @@ +# +# Makefile for x86-compatible CPU details and quirks +# + +obj-y := common.o proc.o + +obj-y += amd.o +obj-y += cyrix.o +obj-y += centaur.o +obj-y += transmeta.o +obj-y += intel.o intel_cacheinfo.o +obj-y += rise.o +obj-y += nexgen.o +obj-y += umc.o + +obj-$(CONFIG_X86_MCE) += mcheck/ + +obj-$(CONFIG_MTRR) += mtrr/ +obj-$(CONFIG_CPU_FREQ) += cpufreq/ + +ifdef CONFIG_XEN +include $(srctree)/scripts/Makefile.xen +obj-y := $(call cherrypickxen, $(obj-y), $(src)) +endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/cpu/common-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/cpu/common-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,653 @@ +#include <linux/init.h> +#include <linux/string.h> +#include <linux/delay.h> +#include <linux/smp.h> +#include <linux/module.h> +#include <linux/percpu.h> +#include <asm/semaphore.h> +#include <asm/processor.h> +#include <asm/i387.h> +#include <asm/msr.h> +#include <asm/io.h> +#include <asm/mmu_context.h> +#ifdef CONFIG_X86_LOCAL_APIC +#include <asm/mpspec.h> +#include <asm/apic.h> +#include <mach_apic.h> +#endif +#include <asm/hypervisor.h> + +#include "cpu.h" + +#ifndef CONFIG_XEN +DEFINE_PER_CPU(struct desc_struct, cpu_gdt_table[GDT_ENTRIES]); +EXPORT_PER_CPU_SYMBOL(cpu_gdt_table); + +DEFINE_PER_CPU(unsigned char, cpu_16bit_stack[CPU_16BIT_STACK_SIZE]); +EXPORT_PER_CPU_SYMBOL(cpu_16bit_stack); +#endif + +static int cachesize_override __initdata = -1; +static int disable_x86_fxsr __initdata = 0; +static int disable_x86_serial_nr __initdata = 1; + +struct cpu_dev * cpu_devs[X86_VENDOR_NUM] = {}; + +extern void mcheck_init(struct cpuinfo_x86 *c); + +extern void machine_specific_modify_cpu_capabilities(struct cpuinfo_x86 *c); + +extern int disable_pse; + +static void default_init(struct cpuinfo_x86 * c) +{ + /* Not much we can do here... */ + /* Check if at least it has cpuid */ + if (c->cpuid_level == -1) { + /* No cpuid. It must be an ancient CPU */ + if (c->x86 == 4) + strcpy(c->x86_model_id, "486"); + else if (c->x86 == 3) + strcpy(c->x86_model_id, "386"); + } +} + +static struct cpu_dev default_cpu = { + .c_init = default_init, +}; +static struct cpu_dev * this_cpu = &default_cpu; + +static int __init cachesize_setup(char *str) +{ + get_option (&str, &cachesize_override); + return 1; +} +__setup("cachesize=", cachesize_setup); + +int __init get_model_name(struct cpuinfo_x86 *c) +{ + unsigned int *v; + char *p, *q; + + if (cpuid_eax(0x80000000) < 0x80000004) + return 0; + + v = (unsigned int *) c->x86_model_id; + cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]); + cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]); + cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]); + c->x86_model_id[48] = 0; + + /* Intel chips right-justify this string for some dumb reason; + undo that brain damage */ + p = q = &c->x86_model_id[0]; + while ( *p == ' ' ) + p++; + if ( p != q ) { + while ( *p ) + *q++ = *p++; + while ( q <= &c->x86_model_id[48] ) + *q++ = '\0'; /* Zero-pad the rest */ + } + + return 1; +} + + +void __init display_cacheinfo(struct cpuinfo_x86 *c) +{ + unsigned int n, dummy, ecx, edx, l2size; + + n = cpuid_eax(0x80000000); + + if (n >= 0x80000005) { + cpuid(0x80000005, &dummy, &dummy, &ecx, &edx); + printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), D cache %dK (%d bytes/line)\n", + edx>>24, edx&0xFF, ecx>>24, ecx&0xFF); + c->x86_cache_size=(ecx>>24)+(edx>>24); + } + + if (n < 0x80000006) /* Some chips just has a large L1. */ + return; + + ecx = cpuid_ecx(0x80000006); + l2size = ecx >> 16; + + /* do processor-specific cache resizing */ + if (this_cpu->c_size_cache) + l2size = this_cpu->c_size_cache(c,l2size); + + /* Allow user to override all this if necessary. */ + if (cachesize_override != -1) + l2size = cachesize_override; + + if ( l2size == 0 ) + return; /* Again, no L2 cache is possible */ + + c->x86_cache_size = l2size; + + printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n", + l2size, ecx & 0xFF); +} + +/* Naming convention should be: <Name> [(<Codename>)] */ +/* This table only is used unless init_<vendor>() below doesn't set it; */ +/* in particular, if CPUID levels 0x80000002..4 are supported, this isn't used */ + +/* Look up CPU names by table lookup. */ +static char __init *table_lookup_model(struct cpuinfo_x86 *c) +{ + struct cpu_model_info *info; + + if ( c->x86_model >= 16 ) + return NULL; /* Range check */ + + if (!this_cpu) + return NULL; + + info = this_cpu->c_models; + + while (info && info->family) { + if (info->family == c->x86) + return info->model_names[c->x86_model]; + info++; + } + return NULL; /* Not found */ +} + + +void __init get_cpu_vendor(struct cpuinfo_x86 *c, int early) +{ + char *v = c->x86_vendor_id; + int i; + + for (i = 0; i < X86_VENDOR_NUM; i++) { + if (cpu_devs[i]) { + if (!strcmp(v,cpu_devs[i]->c_ident[0]) || + (cpu_devs[i]->c_ident[1] && + !strcmp(v,cpu_devs[i]->c_ident[1]))) { + c->x86_vendor = i; + if (!early) + this_cpu = cpu_devs[i]; + break; + } + } + } +} + + +static int __init x86_fxsr_setup(char * s) +{ + disable_x86_fxsr = 1; + return 1; +} +__setup("nofxsr", x86_fxsr_setup); + + +/* Standard macro to see if a specific flag is changeable */ +static inline int flag_is_changeable_p(u32 flag) +{ + u32 f1, f2; + + asm("pushfl\n\t" + "pushfl\n\t" + "popl %0\n\t" + "movl %0,%1\n\t" + "xorl %2,%0\n\t" + "pushl %0\n\t" + "popfl\n\t" + "pushfl\n\t" + "popl %0\n\t" + "popfl\n\t" + : "=&r" (f1), "=&r" (f2) + : "ir" (flag)); + + return ((f1^f2) & flag) != 0; +} + + +/* Probe for the CPUID instruction */ +static int __init have_cpuid_p(void) +{ + return flag_is_changeable_p(X86_EFLAGS_ID); +} + +/* Do minimum CPU detection early. + Fields really needed: vendor, cpuid_level, family, model, mask, cache alignment. + The others are not touched to avoid unwanted side effects. */ +static void __init early_cpu_detect(void) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + + c->x86_cache_alignment = 32; + + if (!have_cpuid_p()) + return; + + /* Get vendor name */ + cpuid(0x00000000, &c->cpuid_level, + (int *)&c->x86_vendor_id[0], + (int *)&c->x86_vendor_id[8], + (int *)&c->x86_vendor_id[4]); + + get_cpu_vendor(c, 1); + + c->x86 = 4; + if (c->cpuid_level >= 0x00000001) { + u32 junk, tfms, cap0, misc; + cpuid(0x00000001, &tfms, &misc, &junk, &cap0); + c->x86 = (tfms >> 8) & 15; + c->x86_model = (tfms >> 4) & 15; + if (c->x86 == 0xf) { + c->x86 += (tfms >> 20) & 0xff; + c->x86_model += ((tfms >> 16) & 0xF) << 4; + } + c->x86_mask = tfms & 15; + if (cap0 & (1<<19)) + c->x86_cache_alignment = ((misc >> 8) & 0xff) * 8; + } + + early_intel_workaround(c); + +#ifdef CONFIG_X86_HT + phys_proc_id[smp_processor_id()] = (cpuid_ebx(1) >> 24) & 0xff; +#endif +} + +void __init generic_identify(struct cpuinfo_x86 * c) +{ + u32 tfms, xlvl; + int junk; + + if (have_cpuid_p()) { + /* Get vendor name */ + cpuid(0x00000000, &c->cpuid_level, + (int *)&c->x86_vendor_id[0], + (int *)&c->x86_vendor_id[8], + (int *)&c->x86_vendor_id[4]); + + get_cpu_vendor(c, 0); + /* Initialize the standard set of capabilities */ + /* Note that the vendor-specific code below might override */ + + /* Intel-defined flags: level 0x00000001 */ + if ( c->cpuid_level >= 0x00000001 ) { + u32 capability, excap; + cpuid(0x00000001, &tfms, &junk, &excap, &capability); + c->x86_capability[0] = capability; + c->x86_capability[4] = excap; + c->x86 = (tfms >> 8) & 15; + c->x86_model = (tfms >> 4) & 15; + if (c->x86 == 0xf) { + c->x86 += (tfms >> 20) & 0xff; + c->x86_model += ((tfms >> 16) & 0xF) << 4; + } + c->x86_mask = tfms & 15; + } else { + /* Have CPUID level 0 only - unheard of */ + c->x86 = 4; + } + + /* AMD-defined flags: level 0x80000001 */ + xlvl = cpuid_eax(0x80000000); + if ( (xlvl & 0xffff0000) == 0x80000000 ) { + if ( xlvl >= 0x80000001 ) { + c->x86_capability[1] = cpuid_edx(0x80000001); + c->x86_capability[6] = cpuid_ecx(0x80000001); + } + if ( xlvl >= 0x80000004 ) + get_model_name(c); /* Default name */ + } + } +} + +static void __init squash_the_stupid_serial_number(struct cpuinfo_x86 *c) +{ + if (cpu_has(c, X86_FEATURE_PN) && disable_x86_serial_nr ) { + /* Disable processor serial number */ + unsigned long lo,hi; + rdmsr(MSR_IA32_BBL_CR_CTL,lo,hi); + lo |= 0x200000; + wrmsr(MSR_IA32_BBL_CR_CTL,lo,hi); + printk(KERN_NOTICE "CPU serial number disabled.\n"); + clear_bit(X86_FEATURE_PN, c->x86_capability); + + /* Disabling the serial number may affect the cpuid level */ + c->cpuid_level = cpuid_eax(0); + } +} + +static int __init x86_serial_nr_setup(char *s) +{ + disable_x86_serial_nr = 0; + return 1; +} +__setup("serialnumber", x86_serial_nr_setup); + + + +/* + * This does the hard work of actually picking apart the CPU stuff... + */ +void __init identify_cpu(struct cpuinfo_x86 *c) +{ + int i; + + c->loops_per_jiffy = loops_per_jiffy; + c->x86_cache_size = -1; + c->x86_vendor = X86_VENDOR_UNKNOWN; + c->cpuid_level = -1; /* CPUID not detected */ + c->x86_model = c->x86_mask = 0; /* So far unknown... */ + c->x86_vendor_id[0] = '\0'; /* Unset */ + c->x86_model_id[0] = '\0'; /* Unset */ + c->x86_num_cores = 1; + memset(&c->x86_capability, 0, sizeof c->x86_capability); + + if (!have_cpuid_p()) { + /* First of all, decide if this is a 486 or higher */ + /* It's a 486 if we can modify the AC flag */ + if ( flag_is_changeable_p(X86_EFLAGS_AC) ) + c->x86 = 4; + else + c->x86 = 3; + } + + generic_identify(c); + + printk(KERN_DEBUG "CPU: After generic identify, caps:"); + for (i = 0; i < NCAPINTS; i++) + printk(" %08lx", c->x86_capability[i]); + printk("\n"); + + if (this_cpu->c_identify) { + this_cpu->c_identify(c); + + printk(KERN_DEBUG "CPU: After vendor identify, caps:"); + for (i = 0; i < NCAPINTS; i++) + printk(" %08lx", c->x86_capability[i]); + printk("\n"); + } + + /* + * Vendor-specific initialization. In this section we + * canonicalize the feature flags, meaning if there are + * features a certain CPU supports which CPUID doesn't + * tell us, CPUID claiming incorrect flags, or other bugs, + * we handle them here. + * + * At the end of this section, c->x86_capability better + * indicate the features this CPU genuinely supports! + */ + if (this_cpu->c_init) + this_cpu->c_init(c); + + /* Disable the PN if appropriate */ + squash_the_stupid_serial_number(c); + + /* + * The vendor-specific functions might have changed features. Now + * we do "generic changes." + */ + + /* TSC disabled? */ + if ( tsc_disable ) + clear_bit(X86_FEATURE_TSC, c->x86_capability); + + /* FXSR disabled? */ + if (disable_x86_fxsr) { + clear_bit(X86_FEATURE_FXSR, c->x86_capability); + clear_bit(X86_FEATURE_XMM, c->x86_capability); + } + + if (disable_pse) + clear_bit(X86_FEATURE_PSE, c->x86_capability); + + /* If the model name is still unset, do table lookup. */ + if ( !c->x86_model_id[0] ) { + char *p; + p = table_lookup_model(c); + if ( p ) + strcpy(c->x86_model_id, p); + else + /* Last resort... */ + sprintf(c->x86_model_id, "%02x/%02x", + c->x86_vendor, c->x86_model); + } + + machine_specific_modify_cpu_capabilities(c); + + /* Now the feature flags better reflect actual CPU features! */ + + printk(KERN_DEBUG "CPU: After all inits, caps:"); + for (i = 0; i < NCAPINTS; i++) + printk(" %08lx", c->x86_capability[i]); + printk("\n"); + + /* + * On SMP, boot_cpu_data holds the common feature set between + * all CPUs; so make sure that we indicate which features are + * common between the CPUs. The first time this routine gets + * executed, c == &boot_cpu_data. + */ + if ( c != &boot_cpu_data ) { + /* AND the already accumulated flags with these */ + for ( i = 0 ; i < NCAPINTS ; i++ ) + boot_cpu_data.x86_capability[i] &= c->x86_capability[i]; + } + + /* Init Machine Check Exception if available. */ +#ifdef CONFIG_X86_MCE + mcheck_init(c); +#endif +} + +#ifdef CONFIG_X86_HT +void __init detect_ht(struct cpuinfo_x86 *c) +{ + u32 eax, ebx, ecx, edx; + int index_msb, tmp; + int cpu = smp_processor_id(); + + if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY)) + return; + + cpuid(1, &eax, &ebx, &ecx, &edx); + smp_num_siblings = (ebx & 0xff0000) >> 16; + + if (smp_num_siblings == 1) { + printk(KERN_INFO "CPU: Hyper-Threading is disabled\n"); + } else if (smp_num_siblings > 1 ) { + index_msb = 31; + + if (smp_num_siblings > NR_CPUS) { + printk(KERN_WARNING "CPU: Unsupported number of the siblings %d", smp_num_siblings); + smp_num_siblings = 1; + return; + } + tmp = smp_num_siblings; + while ((tmp & 0x80000000 ) == 0) { + tmp <<=1 ; + index_msb--; + } + if (smp_num_siblings & (smp_num_siblings - 1)) + index_msb++; + phys_proc_id[cpu] = phys_pkg_id((ebx >> 24) & 0xFF, index_msb); + + printk(KERN_INFO "CPU: Physical Processor ID: %d\n", + phys_proc_id[cpu]); + + smp_num_siblings = smp_num_siblings / c->x86_num_cores; + + tmp = smp_num_siblings; + index_msb = 31; + while ((tmp & 0x80000000) == 0) { + tmp <<=1 ; + index_msb--; + } + + if (smp_num_siblings & (smp_num_siblings - 1)) + index_msb++; + + cpu_core_id[cpu] = phys_pkg_id((ebx >> 24) & 0xFF, index_msb); + + if (c->x86_num_cores > 1) + printk(KERN_INFO "CPU: Processor Core ID: %d\n", + cpu_core_id[cpu]); + } +} +#endif + +void __init print_cpu_info(struct cpuinfo_x86 *c) +{ + char *vendor = NULL; + + if (c->x86_vendor < X86_VENDOR_NUM) + vendor = this_cpu->c_vendor; + else if (c->cpuid_level >= 0) + vendor = c->x86_vendor_id; + + if (vendor && strncmp(c->x86_model_id, vendor, strlen(vendor))) + printk("%s ", vendor); + + if (!c->x86_model_id[0]) + printk("%d86", c->x86); + else + printk("%s", c->x86_model_id); + + if (c->x86_mask || c->cpuid_level >= 0) + printk(" stepping %02x\n", c->x86_mask); + else + printk("\n"); +} + +cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE; + +/* This is hacky. :) + * We're emulating future behavior. + * In the future, the cpu-specific init functions will be called implicitly + * via the magic of initcalls. + * They will insert themselves into the cpu_devs structure. + * Then, when cpu_init() is called, we can just iterate over that array. + */ + +extern int intel_cpu_init(void); +extern int cyrix_init_cpu(void); +extern int nsc_init_cpu(void); +extern int amd_init_cpu(void); +extern int centaur_init_cpu(void); +extern int transmeta_init_cpu(void); +extern int rise_init_cpu(void); +extern int nexgen_init_cpu(void); +extern int umc_init_cpu(void); + +void __init early_cpu_init(void) +{ + intel_cpu_init(); + cyrix_init_cpu(); + nsc_init_cpu(); + amd_init_cpu(); + centaur_init_cpu(); + transmeta_init_cpu(); + rise_init_cpu(); + nexgen_init_cpu(); + umc_init_cpu(); + early_cpu_detect(); + +#ifdef CONFIG_DEBUG_PAGEALLOC + /* pse is not compatible with on-the-fly unmapping, + * disable it even if the cpus claim to support it. + */ + clear_bit(X86_FEATURE_PSE, boot_cpu_data.x86_capability); + disable_pse = 1; +#endif +} + +void __cpuinit cpu_gdt_init(struct Xgt_desc_struct *gdt_descr) +{ + unsigned long frames[16]; + unsigned long va; + int f; + + for (va = gdt_descr->address, f = 0; + va < gdt_descr->address + gdt_descr->size; + va += PAGE_SIZE, f++) { + frames[f] = virt_to_mfn(va); + make_lowmem_page_readonly( + (void *)va, XENFEAT_writable_descriptor_tables); + } + if (HYPERVISOR_set_gdt(frames, gdt_descr->size / 8)) + BUG(); + lgdt_finish(); +} + +/* + * cpu_init() initializes state that is per-CPU. Some data is already + * initialized (naturally) in the bootstrap process, such as the GDT + * and IDT. We reload them nevertheless, this function acts as a + * 'CPU state barrier', nothing should get across. + */ +void __cpuinit cpu_init (void) +{ + int cpu = smp_processor_id(); + struct tss_struct * t = &per_cpu(init_tss, cpu); + struct thread_struct *thread = &current->thread; + + if (cpu_test_and_set(cpu, cpu_initialized)) { + printk(KERN_WARNING "CPU#%d already initialized!\n", cpu); + for (;;) local_irq_enable(); + } + printk(KERN_INFO "Initializing CPU#%d\n", cpu); + + if (cpu_has_vme || cpu_has_de) + clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); + if (tsc_disable && cpu_has_tsc) { + printk(KERN_NOTICE "Disabling TSC...\n"); + /**** FIX-HPA: DOES THIS REALLY BELONG HERE? ****/ + clear_bit(X86_FEATURE_TSC, boot_cpu_data.x86_capability); + set_in_cr4(X86_CR4_TSD); + } + + /* + * Set up the per-thread TLS descriptor cache: + */ + memcpy(thread->tls_array, &get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN], + GDT_ENTRY_TLS_ENTRIES * 8); + + cpu_gdt_init(&cpu_gdt_descr[cpu]); + + /* + * Delete NT + */ + __asm__("pushfl ; andl $0xffffbfff,(%esp) ; popfl"); + + /* + * Set up and load the per-CPU TSS and LDT + */ + atomic_inc(&init_mm.mm_count); + current->active_mm = &init_mm; + if (current->mm) + BUG(); + enter_lazy_tlb(&init_mm, current); + + load_esp0(t, thread); + + load_LDT(&init_mm.context); + + /* Clear %fs and %gs. */ + asm volatile ("xorl %eax, %eax; movl %eax, %fs; movl %eax, %gs"); + + /* Clear all 6 debug registers: */ + +#define CD(register) HYPERVISOR_set_debugreg(register, 0) + + CD(0); CD(1); CD(2); CD(3); /* no db4 and db5 */; CD(6); CD(7); + +#undef CD + + /* + * Force FPU initialization: + */ + current_thread_info()->status = 0; + clear_used_math(); + mxcsr_feature_mask_init(); +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/cpu/mtrr/Makefile --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/cpu/mtrr/Makefile Mon Jan 30 17:18:27 2006 @@ -0,0 +1,12 @@ +obj-y := main.o if.o generic.o state.o +obj-y += amd.o +obj-y += cyrix.o +obj-y += centaur.o + +ifdef CONFIG_XEN +include $(srctree)/scripts/Makefile.xen +n-obj-xen := generic.o state.o amd.o cyrix.o centaur.o + +obj-y := $(call filterxen, $(obj-y), $(n-obj-xen)) +obj-y := $(call cherrypickxen, $(obj-y)) +endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/cpu/mtrr/main-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/cpu/mtrr/main-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,172 @@ +#include <linux/init.h> +#include <linux/proc_fs.h> +#include <linux/ctype.h> +#include <linux/module.h> +#include <linux/seq_file.h> +#include <asm/uaccess.h> + +#include <asm/mtrr.h> +#include "mtrr.h" + +void generic_get_mtrr(unsigned int reg, unsigned long *base, + unsigned int *size, mtrr_type * type) +{ + dom0_op_t op; + + op.cmd = DOM0_READ_MEMTYPE; + op.u.read_memtype.reg = reg; + (void)HYPERVISOR_dom0_op(&op); + + *size = op.u.read_memtype.nr_pfns; + *base = op.u.read_memtype.pfn; + *type = op.u.read_memtype.type; +} + +struct mtrr_ops generic_mtrr_ops = { + .use_intel_if = 1, + .get = generic_get_mtrr, +}; + +struct mtrr_ops *mtrr_if = &generic_mtrr_ops; +unsigned int num_var_ranges; +unsigned int *usage_table; + +static void __init set_num_var_ranges(void) +{ + dom0_op_t op; + + for (num_var_ranges = 0; ; num_var_ranges++) { + op.cmd = DOM0_READ_MEMTYPE; + op.u.read_memtype.reg = num_var_ranges; + if (HYPERVISOR_dom0_op(&op) != 0) + break; + } +} + +static void __init init_table(void) +{ + int i, max; + + max = num_var_ranges; + if ((usage_table = kmalloc(max * sizeof *usage_table, GFP_KERNEL)) + == NULL) { + printk(KERN_ERR "mtrr: could not allocate\n"); + return; + } + for (i = 0; i < max; i++) + usage_table[i] = 0; +} + +int mtrr_add_page(unsigned long base, unsigned long size, + unsigned int type, char increment) +{ + int error; + dom0_op_t op; + + op.cmd = DOM0_ADD_MEMTYPE; + op.u.add_memtype.pfn = base; + op.u.add_memtype.nr_pfns = size; + op.u.add_memtype.type = type; + error = HYPERVISOR_dom0_op(&op); + if (error) { + BUG_ON(error > 0); + return error; + } + + if (increment) + ++usage_table[op.u.add_memtype.reg]; + + return op.u.add_memtype.reg; +} + +int +mtrr_add(unsigned long base, unsigned long size, unsigned int type, + char increment) +{ + if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) { + printk(KERN_WARNING "mtrr: size and base must be multiples of 4 kiB\n"); + printk(KERN_DEBUG "mtrr: size: 0x%lx base: 0x%lx\n", size, base); + return -EINVAL; + } + return mtrr_add_page(base >> PAGE_SHIFT, size >> PAGE_SHIFT, type, + increment); +} + +int mtrr_del_page(int reg, unsigned long base, unsigned long size) +{ + int i, max; + mtrr_type ltype; + unsigned long lbase; + unsigned int lsize; + int error = -EINVAL; + dom0_op_t op; + + max = num_var_ranges; + if (reg < 0) { + /* Search for existing MTRR */ + for (i = 0; i < max; ++i) { + mtrr_if->get(i, &lbase, &lsize, &ltype); + if (lbase == base && lsize == size) { + reg = i; + break; + } + } + if (reg < 0) { + printk(KERN_DEBUG "mtrr: no MTRR for %lx000,%lx000 found\n", base, + size); + goto out; + } + } + if (usage_table[reg] < 1) { + printk(KERN_WARNING "mtrr: reg: %d has count=0\n", reg); + goto out; + } + if (--usage_table[reg] < 1) { + op.cmd = DOM0_DEL_MEMTYPE; + op.u.del_memtype.handle = 0; + op.u.del_memtype.reg = reg; + error = HYPERVISOR_dom0_op(&op); + if (error) { + BUG_ON(error > 0); + goto out; + } + } + error = reg; + out: + return error; +} + +int +mtrr_del(int reg, unsigned long base, unsigned long size) +{ + if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) { + printk(KERN_INFO "mtrr: size and base must be multiples of 4 kiB\n"); + printk(KERN_DEBUG "mtrr: size: 0x%lx base: 0x%lx\n", size, base); + return -EINVAL; + } + return mtrr_del_page(reg, base >> PAGE_SHIFT, size >> PAGE_SHIFT); +} + +EXPORT_SYMBOL(mtrr_add); +EXPORT_SYMBOL(mtrr_del); + +static int __init mtrr_init(void) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + + if (!(xen_start_info->flags & SIF_PRIVILEGED)) + return -ENODEV; + + if ((!cpu_has(c, X86_FEATURE_MTRR)) && + (!cpu_has(c, X86_FEATURE_K6_MTRR)) && + (!cpu_has(c, X86_FEATURE_CYRIX_ARR)) && + (!cpu_has(c, X86_FEATURE_CENTAUR_MCR))) + return -ENODEV; + + set_num_var_ranges(); + init_table(); + + return 0; +} + +subsys_initcall(mtrr_init); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/early_printk-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/early_printk-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,2 @@ + +#include "../../x86_64/kernel/early_printk-xen.c" diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/entry-xen.S --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/entry-xen.S Mon Jan 30 17:18:27 2006 @@ -0,0 +1,842 @@ +/* + * linux/arch/i386/entry.S + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +/* + * entry.S contains the system-call and fault low-level handling routines. + * This also contains the timer-interrupt handler, as well as all interrupts + * and faults that can result in a task-switch. + * + * NOTE: This code handles signal-recognition, which happens every time + * after a timer-interrupt and after each system call. + * + * I changed all the .align's to 4 (16 byte alignment), as that's faster + * on a 486. + * + * Stack layout in 'ret_from_system_call': + * ptrace needs to have all regs on the stack. + * if the order here is changed, it needs to be + * updated in fork.c:copy_process, signal.c:do_signal, + * ptrace.c and ptrace.h + * + * 0(%esp) - %ebx + * 4(%esp) - %ecx + * 8(%esp) - %edx + * C(%esp) - %esi + * 10(%esp) - %edi + * 14(%esp) - %ebp + * 18(%esp) - %eax + * 1C(%esp) - %ds + * 20(%esp) - %es + * 24(%esp) - orig_eax + * 28(%esp) - %eip + * 2C(%esp) - %cs + * 30(%esp) - %eflags + * 34(%esp) - %oldesp + * 38(%esp) - %oldss + * + * "current" is in register %ebx during any slow entries. + */ + +#include <linux/config.h> +#include <linux/linkage.h> +#include <asm/thread_info.h> +#include <asm/errno.h> +#include <asm/segment.h> +#include <asm/smp.h> +#include <asm/page.h> +#include <asm/desc.h> +#include "irq_vectors.h" +#include <xen/interface/xen.h> + +#define nr_syscalls ((syscall_table_size)/4) + +EBX = 0x00 +ECX = 0x04 +EDX = 0x08 +ESI = 0x0C +EDI = 0x10 +EBP = 0x14 +EAX = 0x18 +DS = 0x1C +ES = 0x20 +ORIG_EAX = 0x24 +EIP = 0x28 +CS = 0x2C +EVENT_MASK = 0x2E +EFLAGS = 0x30 +OLDESP = 0x34 +OLDSS = 0x38 + +CF_MASK = 0x00000001 +TF_MASK = 0x00000100 +IF_MASK = 0x00000200 +DF_MASK = 0x00000400 +NT_MASK = 0x00004000 +VM_MASK = 0x00020000 +/* Pseudo-eflags. */ +NMI_MASK = 0x80000000 + +/* Offsets into shared_info_t. */ +#define evtchn_upcall_pending /* 0 */ +#define evtchn_upcall_mask 1 + +#define sizeof_vcpu_shift 6 + +#ifdef CONFIG_SMP +#define preempt_disable(reg) incl TI_preempt_count(reg) +#define preempt_enable(reg) decl TI_preempt_count(reg) +#define XEN_GET_VCPU_INFO(reg) preempt_disable(%ebp) ; \ + movl TI_cpu(%ebp),reg ; \ + shl $sizeof_vcpu_shift,reg ; \ + addl HYPERVISOR_shared_info,reg +#define XEN_PUT_VCPU_INFO(reg) preempt_enable(%ebp) +#define XEN_PUT_VCPU_INFO_fixup .byte 0xff,0xff,0xff +#else +#define XEN_GET_VCPU_INFO(reg) movl HYPERVISOR_shared_info,reg +#define XEN_PUT_VCPU_INFO(reg) +#define XEN_PUT_VCPU_INFO_fixup +#endif + +#define XEN_LOCKED_BLOCK_EVENTS(reg) movb $1,evtchn_upcall_mask(reg) +#define XEN_LOCKED_UNBLOCK_EVENTS(reg) movb $0,evtchn_upcall_mask(reg) +#define XEN_BLOCK_EVENTS(reg) XEN_GET_VCPU_INFO(reg) ; \ + XEN_LOCKED_BLOCK_EVENTS(reg) ; \ + XEN_PUT_VCPU_INFO(reg) +#define XEN_UNBLOCK_EVENTS(reg) XEN_GET_VCPU_INFO(reg) ; \ + XEN_LOCKED_UNBLOCK_EVENTS(reg) ; \ + XEN_PUT_VCPU_INFO(reg) +#define XEN_TEST_PENDING(reg) testb $0xFF,evtchn_upcall_pending(reg) + +#ifdef CONFIG_PREEMPT +#define preempt_stop GET_THREAD_INFO(%ebp) ; \ + XEN_BLOCK_EVENTS(%esi) +#else +#define preempt_stop +#define resume_kernel restore_nocheck +#endif + +#define SAVE_ALL \ + cld; \ + pushl %es; \ + pushl %ds; \ + pushl %eax; \ + pushl %ebp; \ + pushl %edi; \ + pushl %esi; \ + pushl %edx; \ + pushl %ecx; \ + pushl %ebx; \ + movl $(__USER_DS), %edx; \ + movl %edx, %ds; \ + movl %edx, %es; + +#define RESTORE_INT_REGS \ + popl %ebx; \ + popl %ecx; \ + popl %edx; \ + popl %esi; \ + popl %edi; \ + popl %ebp; \ + popl %eax + +#define RESTORE_REGS \ + RESTORE_INT_REGS; \ +1: popl %ds; \ +2: popl %es; \ +.section .fixup,"ax"; \ +3: movl $0,(%esp); \ + jmp 1b; \ +4: movl $0,(%esp); \ + jmp 2b; \ +.previous; \ +.section __ex_table,"a";\ + .align 4; \ + .long 1b,3b; \ + .long 2b,4b; \ +.previous + + +#define RESTORE_ALL \ + RESTORE_REGS \ + addl $4, %esp; \ +1: iret; \ +.section .fixup,"ax"; \ +2: pushl $0; \ + pushl $do_iret_error; \ + jmp error_code; \ +.previous; \ +.section __ex_table,"a";\ + .align 4; \ + .long 1b,2b; \ +.previous + + +ENTRY(ret_from_fork) + pushl %eax + call schedule_tail + GET_THREAD_INFO(%ebp) + popl %eax + jmp syscall_exit + +/* + * Return to user mode is not as complex as all this looks, + * but we want the default path for a system call return to + * go as quickly as possible which is why some of this is + * less clear than it otherwise should be. + */ + + # userspace resumption stub bypassing syscall exit tracing + ALIGN +ret_from_exception: + preempt_stop +ret_from_intr: + GET_THREAD_INFO(%ebp) + movl EFLAGS(%esp), %eax # mix EFLAGS and CS + movb CS(%esp), %al + testl $(VM_MASK | 2), %eax + jz resume_kernel +ENTRY(resume_userspace) + XEN_BLOCK_EVENTS(%esi) # make sure we don't miss an interrupt + # setting need_resched or sigpending + # between sampling and the iret + movl TI_flags(%ebp), %ecx + andl $_TIF_WORK_MASK, %ecx # is there any work to be done on + # int/exception return? + jne work_pending + jmp restore_all + +#ifdef CONFIG_PREEMPT +ENTRY(resume_kernel) + XEN_BLOCK_EVENTS(%esi) + cmpl $0,TI_preempt_count(%ebp) # non-zero preempt_count ? + jnz restore_nocheck +need_resched: + movl TI_flags(%ebp), %ecx # need_resched set ? + testb $_TIF_NEED_RESCHED, %cl + jz restore_all + testb $0xFF,EVENT_MASK(%esp) # interrupts off (exception path) ? + jnz restore_all + call preempt_schedule_irq + jmp need_resched +#endif + +/* SYSENTER_RETURN points to after the "sysenter" instruction in + the vsyscall page. See vsyscall-sysentry.S, which defines the symbol. */ + + # sysenter call handler stub +ENTRY(sysenter_entry) + movl TSS_sysenter_esp0(%esp),%esp +sysenter_past_esp: + sti + pushl $(__USER_DS) + pushl %ebp + pushfl + pushl $(__USER_CS) + pushl $SYSENTER_RETURN + +/* + * Load the potential sixth argument from user stack. + * Careful about security. + */ + cmpl $__PAGE_OFFSET-3,%ebp + jae syscall_fault +1: movl (%ebp),%ebp +.section __ex_table,"a" + .align 4 + .long 1b,syscall_fault +.previous + + pushl %eax + SAVE_ALL + GET_THREAD_INFO(%ebp) + + /* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */ + testw $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),TI_flags(%ebp) + jnz syscall_trace_entry + cmpl $(nr_syscalls), %eax + jae syscall_badsys + call *sys_call_table(,%eax,4) + movl %eax,EAX(%esp) + cli + movl TI_flags(%ebp), %ecx + testw $_TIF_ALLWORK_MASK, %cx + jne syscall_exit_work +/* if something modifies registers it must also disable sysexit */ + movl EIP(%esp), %edx + movl OLDESP(%esp), %ecx + xorl %ebp,%ebp + sti + sysexit + + + # system call handler stub +ENTRY(system_call) + pushl %eax # save orig_eax + SAVE_ALL + GET_THREAD_INFO(%ebp) + # system call tracing in operation + /* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */ + testw $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),TI_flags(%ebp) + jnz syscall_trace_entry + cmpl $(nr_syscalls), %eax + jae syscall_badsys +syscall_call: + call *sys_call_table(,%eax,4) + movl %eax,EAX(%esp) # store the return value +syscall_exit: + XEN_BLOCK_EVENTS(%esi) # make sure we don't miss an interrupt + # setting need_resched or sigpending + # between sampling and the iret + movl TI_flags(%ebp), %ecx + testw $_TIF_ALLWORK_MASK, %cx # current->work + jne syscall_exit_work + +restore_all: +#if 0 /* XEN */ + movl EFLAGS(%esp), %eax # mix EFLAGS, SS and CS + # Warning: OLDSS(%esp) contains the wrong/random values if we + # are returning to the kernel. + # See comments in process.c:copy_thread() for details. + movb OLDSS(%esp), %ah + movb CS(%esp), %al + andl $(VM_MASK | (4 << 8) | 3), %eax + cmpl $((4 << 8) | 3), %eax + je ldt_ss # returning to user-space with LDT SS +#endif /* XEN */ +restore_nocheck: + testl $(VM_MASK|NMI_MASK), EFLAGS(%esp) + jnz hypervisor_iret + movb EVENT_MASK(%esp), %al + notb %al # %al == ~saved_mask + XEN_GET_VCPU_INFO(%esi) + andb evtchn_upcall_mask(%esi),%al + andb $1,%al # %al == mask & ~saved_mask + jnz restore_all_enable_events # != 0 => reenable event delivery + XEN_PUT_VCPU_INFO(%esi) + RESTORE_REGS + addl $4, %esp +1: iret +.section .fixup,"ax" +iret_exc: + pushl $0 # no error code + pushl $do_iret_error + jmp error_code +.previous +.section __ex_table,"a" + .align 4 + .long 1b,iret_exc +.previous + +hypervisor_iret: + andl $~NMI_MASK, EFLAGS(%esp) + RESTORE_REGS + addl $4, %esp + jmp hypercall_page + (__HYPERVISOR_iret * 32) + +#if 0 /* XEN */ +ldt_ss: + larl OLDSS(%esp), %eax + jnz restore_nocheck + testl $0x00400000, %eax # returning to 32bit stack? + jnz restore_nocheck # allright, normal return + /* If returning to userspace with 16bit stack, + * try to fix the higher word of ESP, as the CPU + * won't restore it. + * This is an "official" bug of all the x86-compatible + * CPUs, which we can try to work around to make + * dosemu and wine happy. */ + subl $8, %esp # reserve space for switch16 pointer + cli + movl %esp, %eax + /* Set up the 16bit stack frame with switch32 pointer on top, + * and a switch16 pointer on top of the current frame. */ + call setup_x86_bogus_stack + RESTORE_REGS + lss 20+4(%esp), %esp # switch to 16bit stack +1: iret +.section __ex_table,"a" + .align 4 + .long 1b,iret_exc +.previous +#endif /* XEN */ + + # perform work that needs to be done immediately before resumption + ALIGN +work_pending: + testb $_TIF_NEED_RESCHED, %cl + jz work_notifysig +work_resched: + call schedule + XEN_BLOCK_EVENTS(%esi) # make sure we don't miss an interrupt + # setting need_resched or sigpending + # between sampling and the iret + movl TI_flags(%ebp), %ecx + andl $_TIF_WORK_MASK, %ecx # is there any work to be done other + # than syscall tracing? + jz restore_all + testb $_TIF_NEED_RESCHED, %cl + jnz work_resched + +work_notifysig: # deal with pending signals and + # notify-resume requests + testl $VM_MASK, EFLAGS(%esp) + movl %esp, %eax + jne work_notifysig_v86 # returning to kernel-space or + # vm86-space + xorl %edx, %edx + call do_notify_resume + jmp restore_all + + ALIGN +work_notifysig_v86: + pushl %ecx # save ti_flags for do_notify_resume + call save_v86_state # %eax contains pt_regs pointer + popl %ecx + movl %eax, %esp + xorl %edx, %edx + call do_notify_resume + jmp restore_all + + # perform syscall exit tracing + ALIGN +syscall_trace_entry: + movl $-ENOSYS,EAX(%esp) + movl %esp, %eax + xorl %edx,%edx + call do_syscall_trace + movl ORIG_EAX(%esp), %eax + cmpl $(nr_syscalls), %eax + jnae syscall_call + jmp syscall_exit + + # perform syscall exit tracing + ALIGN +syscall_exit_work: + testb $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP), %cl + jz work_pending + XEN_UNBLOCK_EVENTS(%esi) # could let do_syscall_trace() call + # schedule() instead + movl %esp, %eax + movl $1, %edx + call do_syscall_trace + jmp resume_userspace + + ALIGN +syscall_fault: + pushl %eax # save orig_eax + SAVE_ALL + GET_THREAD_INFO(%ebp) + movl $-EFAULT,EAX(%esp) + jmp resume_userspace + + ALIGN +syscall_badsys: + movl $-ENOSYS,EAX(%esp) + jmp resume_userspace + +#if 0 /* XEN */ +#define FIXUP_ESPFIX_STACK \ + movl %esp, %eax; \ + /* switch to 32bit stack using the pointer on top of 16bit stack */ \ + lss %ss:CPU_16BIT_STACK_SIZE-8, %esp; \ + /* copy data from 16bit stack to 32bit stack */ \ + call fixup_x86_bogus_stack; \ + /* put ESP to the proper location */ \ + movl %eax, %esp; +#define UNWIND_ESPFIX_STACK \ + pushl %eax; \ + movl %ss, %eax; \ + /* see if on 16bit stack */ \ + cmpw $__ESPFIX_SS, %ax; \ + jne 28f; \ + movl $__KERNEL_DS, %edx; \ + movl %edx, %ds; \ + movl %edx, %es; \ + /* switch to 32bit stack */ \ + FIXUP_ESPFIX_STACK \ +28: popl %eax; + +/* + * Build the entry stubs and pointer table with + * some assembler magic. + */ +.data +ENTRY(interrupt) +.text + +vector=0 +ENTRY(irq_entries_start) +.rept NR_IRQS + ALIGN +1: pushl $vector-256 + jmp common_interrupt +.data + .long 1b +.text +vector=vector+1 +.endr + + ALIGN +common_interrupt: + SAVE_ALL + movl %esp,%eax + call do_IRQ + jmp ret_from_intr + +#define BUILD_INTERRUPT(name, nr) \ +ENTRY(name) \ + pushl $nr-256; \ + SAVE_ALL \ + movl %esp,%eax; \ + call smp_/**/name; \ + jmp ret_from_intr; + +/* The include is where all of the SMP etc. interrupts come from */ +#include "entry_arch.h" +#endif /* XEN */ + +ENTRY(divide_error) + pushl $0 # no error code + pushl $do_divide_error + ALIGN +error_code: + pushl %ds + pushl %eax + xorl %eax, %eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + decl %eax # eax = -1 + pushl %ecx + pushl %ebx + cld + pushl %es +# UNWIND_ESPFIX_STACK + popl %ecx + movl ES(%esp), %edi # get the function address + movl ORIG_EAX(%esp), %edx # get the error code + movl %eax, ORIG_EAX(%esp) + movl %ecx, ES(%esp) + movl $(__USER_DS), %ecx + movl %ecx, %ds + movl %ecx, %es + movl %esp,%eax # pt_regs pointer + call *%edi + jmp ret_from_exception + +# A note on the "critical region" in our callback handler. +# We want to avoid stacking callback handlers due to events occurring +# during handling of the last event. To do this, we keep events disabled +# until we've done all processing. HOWEVER, we must enable events before +# popping the stack frame (can't be done atomically) and so it would still +# be possible to get enough handler activations to overflow the stack. +# Although unlikely, bugs of that kind are hard to track down, so we'd +# like to avoid the possibility. +# So, on entry to the handler we detect whether we interrupted an +# existing activation in its critical region -- if so, we pop the current +# activation and restart the handler using the previous one. +ENTRY(hypervisor_callback) + pushl %eax + SAVE_ALL + movl EIP(%esp),%eax + cmpl $scrit,%eax + jb 11f + cmpl $ecrit,%eax + jb critical_region_fixup +11: push %esp + call evtchn_do_upcall + add $4,%esp + jmp ret_from_intr + + ALIGN +restore_all_enable_events: + XEN_LOCKED_UNBLOCK_EVENTS(%esi) +scrit: /**** START OF CRITICAL REGION ****/ + XEN_TEST_PENDING(%esi) + jnz 14f # process more events if necessary... + XEN_PUT_VCPU_INFO(%esi) + RESTORE_ALL +14: XEN_LOCKED_BLOCK_EVENTS(%esi) + XEN_PUT_VCPU_INFO(%esi) + jmp 11b +ecrit: /**** END OF CRITICAL REGION ****/ +# [How we do the fixup]. We want to merge the current stack frame with the +# just-interrupted frame. How we do this depends on where in the critical +# region the interrupted handler was executing, and so how many saved +# registers are in each frame. We do this quickly using the lookup table +# 'critical_fixup_table'. For each byte offset in the critical region, it +# provides the number of bytes which have already been popped from the +# interrupted stack frame. +critical_region_fixup: + addl $critical_fixup_table-scrit,%eax + movzbl (%eax),%eax # %eax contains num bytes popped + cmpb $0xff,%al # 0xff => vcpu_info critical region + jne 15f + GET_THREAD_INFO(%ebp) + XEN_PUT_VCPU_INFO(%esi) # abort vcpu_info critical region + xorl %eax,%eax +15: mov %esp,%esi + add %eax,%esi # %esi points at end of src region + mov %esp,%edi + add $0x34,%edi # %edi points at end of dst region + mov %eax,%ecx + shr $2,%ecx # convert words to bytes + je 17f # skip loop if nothing to copy +16: subl $4,%esi # pre-decrementing copy loop + subl $4,%edi + movl (%esi),%eax + movl %eax,(%edi) + loop 16b +17: movl %edi,%esp # final %edi is top of merged stack + jmp 11b + +critical_fixup_table: + .byte 0xff,0xff,0xff # testb $0xff,(%esi) = XEN_TEST_PENDING + .byte 0xff,0xff # jnz 14f + XEN_PUT_VCPU_INFO_fixup + .byte 0x00 # pop %ebx + .byte 0x04 # pop %ecx + .byte 0x08 # pop %edx + .byte 0x0c # pop %esi + .byte 0x10 # pop %edi + .byte 0x14 # pop %ebp + .byte 0x18 # pop %eax + .byte 0x1c # pop %ds + .byte 0x20 # pop %es + .byte 0x24,0x24,0x24 # add $4,%esp + .byte 0x28 # iret + .byte 0xff,0xff,0xff,0xff # movb $1,1(%esi) + XEN_PUT_VCPU_INFO_fixup + .byte 0x00,0x00 # jmp 11b + +# Hypervisor uses this for application faults while it executes. +ENTRY(failsafe_callback) +1: popl %ds +2: popl %es +3: popl %fs +4: popl %gs + subl $4,%esp + SAVE_ALL + jmp ret_from_exception +.section .fixup,"ax"; \ +6: movl $0,(%esp); \ + jmp 1b; \ +7: movl $0,(%esp); \ + jmp 2b; \ +8: movl $0,(%esp); \ + jmp 3b; \ +9: movl $0,(%esp); \ + jmp 4b; \ +.previous; \ +.section __ex_table,"a";\ + .align 4; \ + .long 1b,6b; \ + .long 2b,7b; \ + .long 3b,8b; \ + .long 4b,9b; \ +.previous + +ENTRY(coprocessor_error) + pushl $0 + pushl $do_coprocessor_error + jmp error_code + +ENTRY(simd_coprocessor_error) + pushl $0 + pushl $do_simd_coprocessor_error + jmp error_code + +ENTRY(device_not_available) + pushl $-1 # mark this as an int + SAVE_ALL + #preempt_stop /* This is already an interrupt gate on Xen. */ + call math_state_restore + jmp ret_from_exception + +/* + * Debug traps and NMI can happen at the one SYSENTER instruction + * that sets up the real kernel stack. Check here, since we can't + * allow the wrong stack to be used. + * + * "TSS_sysenter_esp0+12" is because the NMI/debug handler will have + * already pushed 3 words if it hits on the sysenter instruction: + * eflags, cs and eip. + * + * We just load the right stack, and push the three (known) values + * by hand onto the new stack - while updating the return eip past + * the instruction that would have done it for sysenter. + */ +#define FIX_STACK(offset, ok, label) \ + cmpw $__KERNEL_CS,4(%esp); \ + jne ok; \ +label: \ + movl TSS_sysenter_esp0+offset(%esp),%esp; \ + pushfl; \ + pushl $__KERNEL_CS; \ + pushl $sysenter_past_esp + +ENTRY(debug) + cmpl $sysenter_entry,(%esp) + jne debug_stack_correct + FIX_STACK(12, debug_stack_correct, debug_esp_fix_insn) +debug_stack_correct: + pushl $-1 # mark this as an int + SAVE_ALL + xorl %edx,%edx # error code 0 + movl %esp,%eax # pt_regs pointer + call do_debug + jmp ret_from_exception + +ENTRY(nmi) + pushl %eax + SAVE_ALL + xorl %edx,%edx # zero error code + movl %esp,%eax # pt_regs pointer + call do_nmi + orl $NMI_MASK, EFLAGS(%esp) + jmp restore_all + +#if 0 /* XEN */ +/* + * NMI is doubly nasty. It can happen _while_ we're handling + * a debug fault, and the debug fault hasn't yet been able to + * clear up the stack. So we first check whether we got an + * NMI on the sysenter entry path, but after that we need to + * check whether we got an NMI on the debug path where the debug + * fault happened on the sysenter path. + */ +ENTRY(nmi) + pushl %eax + movl %ss, %eax + cmpw $__ESPFIX_SS, %ax + popl %eax + je nmi_16bit_stack + cmpl $sysenter_entry,(%esp) + je nmi_stack_fixup + pushl %eax + movl %esp,%eax + /* Do not access memory above the end of our stack page, + * it might not exist. + */ + andl $(THREAD_SIZE-1),%eax + cmpl $(THREAD_SIZE-20),%eax + popl %eax + jae nmi_stack_correct + cmpl $sysenter_entry,12(%esp) + je nmi_debug_stack_check +nmi_stack_correct: + pushl %eax + SAVE_ALL + xorl %edx,%edx # zero error code + movl %esp,%eax # pt_regs pointer + call do_nmi + jmp restore_all + +nmi_stack_fixup: + FIX_STACK(12,nmi_stack_correct, 1) + jmp nmi_stack_correct +nmi_debug_stack_check: + cmpw $__KERNEL_CS,16(%esp) + jne nmi_stack_correct + cmpl $debug - 1,(%esp) + jle nmi_stack_correct + cmpl $debug_esp_fix_insn,(%esp) + jle nmi_debug_stack_fixup +nmi_debug_stack_fixup: + FIX_STACK(24,nmi_stack_correct, 1) + jmp nmi_stack_correct + +nmi_16bit_stack: + /* create the pointer to lss back */ + pushl %ss + pushl %esp + movzwl %sp, %esp + addw $4, (%esp) + /* copy the iret frame of 12 bytes */ + .rept 3 + pushl 16(%esp) + .endr + pushl %eax + SAVE_ALL + FIXUP_ESPFIX_STACK # %eax == %esp + xorl %edx,%edx # zero error code + call do_nmi + RESTORE_REGS + lss 12+4(%esp), %esp # back to 16bit stack +1: iret +.section __ex_table,"a" + .align 4 + .long 1b,iret_exc +.previous +#endif /* XEN */ + +ENTRY(int3) + pushl $-1 # mark this as an int + SAVE_ALL + xorl %edx,%edx # zero error code + movl %esp,%eax # pt_regs pointer + call do_int3 + jmp ret_from_exception + +ENTRY(overflow) + pushl $0 + pushl $do_overflow + jmp error_code + +ENTRY(bounds) + pushl $0 + pushl $do_bounds + jmp error_code + +ENTRY(invalid_op) + pushl $0 + pushl $do_invalid_op + jmp error_code + +ENTRY(coprocessor_segment_overrun) + pushl $0 + pushl $do_coprocessor_segment_overrun + jmp error_code + +ENTRY(invalid_TSS) + pushl $do_invalid_TSS + jmp error_code + +ENTRY(segment_not_present) + pushl $do_segment_not_present + jmp error_code + +ENTRY(stack_segment) + pushl $do_stack_segment + jmp error_code + +ENTRY(general_protection) + pushl $do_general_protection + jmp error_code + +ENTRY(alignment_check) + pushl $do_alignment_check + jmp error_code + +ENTRY(page_fault) + pushl $do_page_fault + jmp error_code + +#ifdef CONFIG_X86_MCE +ENTRY(machine_check) + pushl $0 + pushl machine_check_vector + jmp error_code +#endif + +ENTRY(fixup_4gb_segment) + pushl $do_fixup_4gb_segment + jmp error_code + +#include "syscall_table.S" + +syscall_table_size=(.-sys_call_table) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/fixup.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/fixup.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,95 @@ +/****************************************************************************** + * fixup.c + * + * Binary-rewriting of certain IA32 instructions, on notification by Xen. + * Used to avoid repeated slow emulation of common instructions used by the + * user-space TLS (Thread-Local Storage) libraries. + * + * **** NOTE **** + * Issues with the binary rewriting have caused it to be removed. Instead + * we rely on Xen's emulator to boot the kernel, and then print a banner + * message recommending that the user disables /lib/tls. + * + * Copyright (c) 2004, K A Fraser + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include <linux/config.h> +#include <linux/init.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/kernel.h> +#include <linux/delay.h> +#include <linux/version.h> + +#define DP(_f, _args...) printk(KERN_ALERT " " _f "\n" , ## _args ) + +fastcall void do_fixup_4gb_segment(struct pt_regs *regs, long error_code) +{ + static unsigned long printed = 0; + char info[100]; + int i; + + if (test_and_set_bit(0, &printed)) + return; + + HYPERVISOR_vm_assist( + VMASST_CMD_disable, VMASST_TYPE_4gb_segments_notify); + + sprintf(info, "%s (pid=%d)", current->comm, current->tgid); + + + DP(""); + DP("***************************************************************"); + DP("***************************************************************"); + DP("** WARNING: Currently emulating unsupported memory accesses **"); + DP("** in /lib/tls glibc libraries. The emulation is **"); + DP("** slow. To ensure full performance you should **"); + DP("** install a 'xen-friendly' (nosegneg) version of **"); + DP("** the library, or disable tls support by executing **"); + DP("** the following as root: **"); + DP("** mv /lib/tls /lib/tls.disabled **"); + DP("** Offending process: %-38.38s **", info); + DP("***************************************************************"); + DP("***************************************************************"); + DP(""); + + for (i = 5; i > 0; i--) { + printk("Pausing... %d", i); + mdelay(1000); + printk("\b\b\b\b\b\b\b\b\b\b\b\b"); + } + + printk("Continuing...\n\n"); +} + +static int __init fixup_init(void) +{ + HYPERVISOR_vm_assist( + VMASST_CMD_enable, VMASST_TYPE_4gb_segments_notify); + return 0; +} +__initcall(fixup_init); + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/head-xen.S --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/head-xen.S Mon Jan 30 17:18:27 2006 @@ -0,0 +1,198 @@ + +#include <linux/config.h> + +.section __xen_guest + .ascii "GUEST_OS=linux,GUEST_VER=2.6" + .ascii ",XEN_VER=xen-3.0" + .ascii ",VIRT_BASE=0xC0000000" + .ascii ",HYPERCALL_PAGE=0x104" /* __pa(hypercall_page) >> 12 */ +#ifdef CONFIG_X86_PAE + .ascii ",PAE=yes" +#else + .ascii ",PAE=no" +#endif +#ifdef CONFIG_XEN_SHADOW_MODE + .ascii ",SHADOW=translate" +#endif + .ascii ",LOADER=generic" + .byte 0 + +.text +#include <linux/threads.h> +#include <linux/linkage.h> +#include <asm/segment.h> +#include <asm/thread_info.h> +#include <asm/asm_offsets.h> +#include <xen/interface/arch-x86_32.h> + +/* + * References to members of the new_cpu_data structure. + */ + +#define X86 new_cpu_data+CPUINFO_x86 +#define X86_VENDOR new_cpu_data+CPUINFO_x86_vendor +#define X86_MODEL new_cpu_data+CPUINFO_x86_model +#define X86_MASK new_cpu_data+CPUINFO_x86_mask +#define X86_HARD_MATH new_cpu_data+CPUINFO_hard_math +#define X86_CPUID new_cpu_data+CPUINFO_cpuid_level +#define X86_CAPABILITY new_cpu_data+CPUINFO_x86_capability +#define X86_VENDOR_ID new_cpu_data+CPUINFO_x86_vendor_id + +ENTRY(startup_32) + movl %esi,xen_start_info + +#if 0 +ENTRY(startup_32_smp) +#endif /* CONFIG_SMP */ + + cld + + /* Set up the stack pointer */ + lss stack_start,%esp + +checkCPUtype: + + /* get vendor info */ + xorl %eax,%eax # call CPUID with 0 -> return vendor ID + cpuid + movl %eax,X86_CPUID # save CPUID level + movl %ebx,X86_VENDOR_ID # lo 4 chars + movl %edx,X86_VENDOR_ID+4 # next 4 chars + movl %ecx,X86_VENDOR_ID+8 # last 4 chars + + movl $1,%eax # Use the CPUID instruction to get CPU type + cpuid + movb %al,%cl # save reg for future use + andb $0x0f,%ah # mask processor family + movb %ah,X86 + andb $0xf0,%al # mask model + shrb $4,%al + movb %al,X86_MODEL + andb $0x0f,%cl # mask mask revision + movb %cl,X86_MASK + movl %edx,X86_CAPABILITY + + incb ready + + xorl %eax,%eax # Clear FS/GS and LDT + movl %eax,%fs + movl %eax,%gs + cld # gcc2 wants the direction flag cleared at all times + +#if 0 + movb ready, %cl + cmpb $1,%cl + je 1f # the first CPU calls start_kernel + # all other CPUs call initialize_secondary + call initialize_secondary + jmp L6 +1: +#endif /* CONFIG_SMP */ + call start_kernel +L6: + jmp L6 # main should never return here, but + # just in case, we know what happens. + +ENTRY(lgdt_finish) + movl $(__KERNEL_DS),%eax # reload all the segment registers + movw %ax,%ss # after changing gdt. + + movl $(__USER_DS),%eax # DS/ES contains default USER segment + movw %ax,%ds + movw %ax,%es + + popl %eax # reload CS by intersegment return + pushl $(__KERNEL_CS) + pushl %eax + lret + +ENTRY(stack_start) + .long init_thread_union+THREAD_SIZE + .long __BOOT_DS + +ready: .byte 0 + +.globl idt_descr +.globl cpu_gdt_descr + + ALIGN + .word 0 # 32-bit align idt_desc.address +idt_descr: + .word IDT_ENTRIES*8-1 # idt contains 256 entries + .long idt_table + +# boot GDT descriptor (later on used by CPU#0): + .word 0 # 32 bit align gdt_desc.address +cpu_gdt_descr: + .word GDT_SIZE + .long cpu_gdt_table + + .fill NR_CPUS-1,8,0 # space for the other GDT descriptors + +.org 0x1000 +ENTRY(empty_zero_page) + +.org 0x2000 +ENTRY(cpu_gdt_table) + .quad 0x0000000000000000 /* NULL descriptor */ + .quad 0x0000000000000000 /* 0x0b reserved */ + .quad 0x0000000000000000 /* 0x13 reserved */ + .quad 0x0000000000000000 /* 0x1b reserved */ + .quad 0x0000000000000000 /* 0x20 unused */ + .quad 0x0000000000000000 /* 0x28 unused */ + .quad 0x0000000000000000 /* 0x33 TLS entry 1 */ + .quad 0x0000000000000000 /* 0x3b TLS entry 2 */ + .quad 0x0000000000000000 /* 0x43 TLS entry 3 */ + .quad 0x0000000000000000 /* 0x4b reserved */ + .quad 0x0000000000000000 /* 0x53 reserved */ + .quad 0x0000000000000000 /* 0x5b reserved */ + +#ifdef CONFIG_X86_PAE + .quad 0x00cfbb00000067ff /* 0x60 kernel 4GB code at 0x00000000 */ + .quad 0x00cfb300000067ff /* 0x68 kernel 4GB data at 0x00000000 */ + .quad 0x00cffb00000067ff /* 0x73 user 4GB code at 0x00000000 */ + .quad 0x00cff300000067ff /* 0x7b user 4GB data at 0x00000000 */ +#else + .quad 0x00cfbb000000c3ff /* 0x60 kernel 4GB code at 0x00000000 */ + .quad 0x00cfb3000000c3ff /* 0x68 kernel 4GB data at 0x00000000 */ + .quad 0x00cffb000000c3ff /* 0x73 user 4GB code at 0x00000000 */ + .quad 0x00cff3000000c3ff /* 0x7b user 4GB data at 0x00000000 */ +#endif + + .quad 0x0000000000000000 /* 0x80 TSS descriptor */ + .quad 0x0000000000000000 /* 0x88 LDT descriptor */ + + /* Segments used for calling PnP BIOS */ + .quad 0x0000000000000000 /* 0x90 32-bit code */ + .quad 0x0000000000000000 /* 0x98 16-bit code */ + .quad 0x0000000000000000 /* 0xa0 16-bit data */ + .quad 0x0000000000000000 /* 0xa8 16-bit data */ + .quad 0x0000000000000000 /* 0xb0 16-bit data */ + /* + * The APM segments have byte granularity and their bases + * and limits are set at run time. + */ + .quad 0x0000000000000000 /* 0xb8 APM CS code */ + .quad 0x0000000000000000 /* 0xc0 APM CS 16 code (16 bit) */ + .quad 0x0000000000000000 /* 0xc8 APM DS data */ + + .quad 0x0000000000000000 /* 0xd0 - ESPFIX 16-bit SS */ + .quad 0x0000000000000000 /* 0xd8 - unused */ + .quad 0x0000000000000000 /* 0xe0 - unused */ + .quad 0x0000000000000000 /* 0xe8 - unused */ + .quad 0x0000000000000000 /* 0xf0 - unused */ + .quad 0x0000000000000000 /* 0xf8 - GDT entry 31: double-fault TSS */ + .fill GDT_ENTRIES-32,8,0 + +.org 0x3000 +ENTRY(default_ldt) + +.org 0x4000 +ENTRY(hypercall_page) + +.org 0x5000 +/* + * Real beginning of normal "text" segment + */ +ENTRY(stext) +ENTRY(_stext) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/i386_ksyms-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/i386_ksyms-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,185 @@ +#include <linux/config.h> +#include <linux/module.h> +#include <linux/smp.h> +#include <linux/user.h> +#include <linux/elfcore.h> +#include <linux/mca.h> +#include <linux/sched.h> +#include <linux/in6.h> +#include <linux/interrupt.h> +#include <linux/smp_lock.h> +#include <linux/pm.h> +#include <linux/pci.h> +#include <linux/apm_bios.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/tty.h> +#include <linux/highmem.h> +#include <linux/time.h> + +#include <asm/semaphore.h> +#include <asm/processor.h> +#include <asm/i387.h> +#include <asm/uaccess.h> +#include <asm/checksum.h> +#include <asm/io.h> +#include <asm/delay.h> +#include <asm/irq.h> +#include <asm/mmx.h> +#include <asm/desc.h> +#include <asm/pgtable.h> +#include <asm/tlbflush.h> +#include <asm/nmi.h> +#include <asm/ist.h> +#include <asm/kdebug.h> + +extern void dump_thread(struct pt_regs *, struct user *); +extern spinlock_t rtc_lock; + +/* This is definitely a GPL-only symbol */ +EXPORT_SYMBOL_GPL(cpu_gdt_table); + +#if defined(CONFIG_APM_MODULE) +extern void machine_real_restart(unsigned char *, int); +EXPORT_SYMBOL(machine_real_restart); +extern void default_idle(void); +EXPORT_SYMBOL(default_idle); +#endif + +#ifdef CONFIG_SMP +extern void FASTCALL( __write_lock_failed(rwlock_t *rw)); +extern void FASTCALL( __read_lock_failed(rwlock_t *rw)); +#endif + +#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_HD) || defined(CONFIG_BLK_DEV_IDE_MODULE) || defined(CONFIG_BLK_DEV_HD_MODULE) +extern struct drive_info_struct drive_info; +EXPORT_SYMBOL(drive_info); +#endif + +extern unsigned long cpu_khz; +extern unsigned long get_cmos_time(void); + +/* platform dependent support */ +EXPORT_SYMBOL(boot_cpu_data); +#ifdef CONFIG_DISCONTIGMEM +EXPORT_SYMBOL(node_data); +EXPORT_SYMBOL(physnode_map); +#endif +#ifdef CONFIG_X86_NUMAQ +EXPORT_SYMBOL(xquad_portio); +#endif +EXPORT_SYMBOL(dump_thread); +EXPORT_SYMBOL(dump_fpu); +EXPORT_SYMBOL_GPL(kernel_fpu_begin); +EXPORT_SYMBOL(__ioremap); +EXPORT_SYMBOL(ioremap_nocache); +EXPORT_SYMBOL(iounmap); +EXPORT_SYMBOL(kernel_thread); +EXPORT_SYMBOL(pm_idle); +EXPORT_SYMBOL(pm_power_off); +EXPORT_SYMBOL(get_cmos_time); +EXPORT_SYMBOL(cpu_khz); +EXPORT_SYMBOL(apm_info); + +EXPORT_SYMBOL(__down_failed); +EXPORT_SYMBOL(__down_failed_interruptible); +EXPORT_SYMBOL(__down_failed_trylock); +EXPORT_SYMBOL(__up_wakeup); +/* Networking helper routines. */ +EXPORT_SYMBOL(csum_partial_copy_generic); +/* Delay loops */ +EXPORT_SYMBOL(__ndelay); +EXPORT_SYMBOL(__udelay); +EXPORT_SYMBOL(__delay); +EXPORT_SYMBOL(__const_udelay); + +EXPORT_SYMBOL(__get_user_1); +EXPORT_SYMBOL(__get_user_2); +EXPORT_SYMBOL(__get_user_4); + +EXPORT_SYMBOL(__put_user_1); +EXPORT_SYMBOL(__put_user_2); +EXPORT_SYMBOL(__put_user_4); +EXPORT_SYMBOL(__put_user_8); + +EXPORT_SYMBOL(strpbrk); +EXPORT_SYMBOL(strstr); + +EXPORT_SYMBOL(strncpy_from_user); +EXPORT_SYMBOL(__strncpy_from_user); +EXPORT_SYMBOL(clear_user); +EXPORT_SYMBOL(__clear_user); +EXPORT_SYMBOL(__copy_from_user_ll); +EXPORT_SYMBOL(__copy_to_user_ll); +EXPORT_SYMBOL(strnlen_user); + +#ifdef CONFIG_PCI +EXPORT_SYMBOL(pci_mem_start); +#endif + +#ifdef CONFIG_PCI_BIOS +EXPORT_SYMBOL(pcibios_set_irq_routing); +EXPORT_SYMBOL(pcibios_get_irq_routing_table); +#endif + +#ifdef CONFIG_X86_USE_3DNOW +EXPORT_SYMBOL(_mmx_memcpy); +EXPORT_SYMBOL(mmx_clear_page); +EXPORT_SYMBOL(mmx_copy_page); +#endif + +#ifdef CONFIG_X86_HT +EXPORT_SYMBOL(smp_num_siblings); +EXPORT_SYMBOL(cpu_sibling_map); +#endif + +#ifdef CONFIG_SMP +EXPORT_SYMBOL(__write_lock_failed); +EXPORT_SYMBOL(__read_lock_failed); + +/* Global SMP stuff */ +EXPORT_SYMBOL(smp_call_function); + +/* TLB flushing */ +EXPORT_SYMBOL(flush_tlb_page); +#endif + +#ifdef CONFIG_X86_IO_APIC +EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); +#endif + +#ifdef CONFIG_MCA +EXPORT_SYMBOL(machine_id); +#endif + +#ifdef CONFIG_VT +EXPORT_SYMBOL(screen_info); +#endif + +EXPORT_SYMBOL(get_wchan); + +EXPORT_SYMBOL(rtc_lock); + +EXPORT_SYMBOL_GPL(set_nmi_callback); +EXPORT_SYMBOL_GPL(unset_nmi_callback); + +EXPORT_SYMBOL(register_die_notifier); +#ifdef CONFIG_HAVE_DEC_LOCK +EXPORT_SYMBOL(_atomic_dec_and_lock); +#endif + +EXPORT_SYMBOL(__PAGE_KERNEL); + +#ifdef CONFIG_HIGHMEM +EXPORT_SYMBOL(kmap); +EXPORT_SYMBOL(kunmap); +EXPORT_SYMBOL(kmap_atomic); +EXPORT_SYMBOL(kunmap_atomic); +EXPORT_SYMBOL(kmap_atomic_to_page); +#endif + +#if defined(CONFIG_X86_SPEEDSTEP_SMI) || defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE) +EXPORT_SYMBOL(ist_info); +#endif + +EXPORT_SYMBOL(csum_partial); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/init_task-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/init_task-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,49 @@ +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/init_task.h> +#include <linux/fs.h> +#include <linux/mqueue.h> + +#include <asm/uaccess.h> +#include <asm/pgtable.h> +#include <asm/desc.h> + +static struct fs_struct init_fs = INIT_FS; +static struct files_struct init_files = INIT_FILES; +static struct signal_struct init_signals = INIT_SIGNALS(init_signals); +static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); + +#define swapper_pg_dir ((pgd_t *)NULL) +struct mm_struct init_mm = INIT_MM(init_mm); +#undef swapper_pg_dir + +EXPORT_SYMBOL(init_mm); + +/* + * Initial thread structure. + * + * We need to make sure that this is THREAD_SIZE aligned due to the + * way process stacks are handled. This is done by having a special + * "init_task" linker map entry.. + */ +union thread_union init_thread_union + __attribute__((__section__(".data.init_task"))) = + { INIT_THREAD_INFO(init_task) }; + +/* + * Initial task structure. + * + * All other task structs will be allocated on slabs in fork.c + */ +struct task_struct init_task = INIT_TASK(init_task); + +EXPORT_SYMBOL(init_task); + +/* + * per-CPU TSS segments. Threads are completely 'soft' on Linux, + * no more per-task TSS's. + */ +DEFINE_PER_CPU(struct tss_struct, init_tss) ____cacheline_maxaligned_in_smp = INIT_TSS; + diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/io_apic-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/io_apic-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,2611 @@ +/* + * Intel IO-APIC support for multi-Pentium hosts. + * + * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar, Hajnalka Szabo + * + * Many thanks to Stig Venaas for trying out countless experimental + * patches and reporting/debugging problems patiently! + * + * (c) 1999, Multiple IO-APIC support, developed by + * Ken-ichi Yaku <yaku@xxxxxxxxxxxxxxxxxxxx> and + * Hidemi Kishimoto <kisimoto@xxxxxxxxxxxxxxxxxxxx>, + * further tested and cleaned up by Zach Brown <zab@xxxxxxxxxx> + * and Ingo Molnar <mingo@xxxxxxxxxx> + * + * Fixes + * Maciej W. Rozycki : Bits for genuine 82489DX APICs; + * thanks to Eric Gilmore + * and Rolf G. Tews + * for testing these extensively + * Paul Diefenbaugh : Added full ACPI support + */ + +#include <linux/mm.h> +#include <linux/irq.h> +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/sched.h> +#include <linux/config.h> +#include <linux/smp_lock.h> +#include <linux/mc146818rtc.h> +#include <linux/compiler.h> +#include <linux/acpi.h> + +#include <linux/sysdev.h> +#include <asm/io.h> +#include <asm/smp.h> +#include <asm/desc.h> +#include <asm/timer.h> + +#include <mach_apic.h> + +#include "io_ports.h" + +#ifdef CONFIG_XEN + +#include <xen/interface/xen.h> +#include <xen/interface/physdev.h> + +/* Fake i8259 */ +#define make_8259A_irq(_irq) (io_apic_irqs &= ~(1UL<<(_irq))) +#define disable_8259A_irq(_irq) ((void)0) +#define i8259A_irq_pending(_irq) (0) + +unsigned long io_apic_irqs; + +static inline unsigned int xen_io_apic_read(unsigned int apic, unsigned int reg) +{ + physdev_op_t op; + int ret; + + op.cmd = PHYSDEVOP_APIC_READ; + op.u.apic_op.apic = mp_ioapics[apic].mpc_apicid; + op.u.apic_op.offset = reg; + ret = HYPERVISOR_physdev_op(&op); + if (ret) + return ret; + return op.u.apic_op.value; +} + +static inline void xen_io_apic_write(unsigned int apic, unsigned int reg, unsigned int value) +{ + physdev_op_t op; + + op.cmd = PHYSDEVOP_APIC_WRITE; + op.u.apic_op.apic = mp_ioapics[apic].mpc_apicid; + op.u.apic_op.offset = reg; + op.u.apic_op.value = value; + HYPERVISOR_physdev_op(&op); +} + +#define io_apic_read(a,r) xen_io_apic_read(a,r) +#define io_apic_write(a,r,v) xen_io_apic_write(a,r,v) + +#endif /* CONFIG_XEN */ + +int (*ioapic_renumber_irq)(int ioapic, int irq); +atomic_t irq_mis_count; + +static DEFINE_SPINLOCK(ioapic_lock); + +/* + * Is the SiS APIC rmw bug present ? + * -1 = don't know, 0 = no, 1 = yes + */ +int sis_apic_bug = -1; + +/* + * # of IRQ routing registers + */ +int nr_ioapic_registers[MAX_IO_APICS]; + +/* + * Rough estimation of how many shared IRQs there are, can + * be changed anytime. + */ +#define MAX_PLUS_SHARED_IRQS NR_IRQS +#define PIN_MAP_SIZE (MAX_PLUS_SHARED_IRQS + NR_IRQS) + +/* + * This is performance-critical, we want to do it O(1) + * + * the indexing order of this array favors 1:1 mappings + * between pins and IRQs. + */ + +static struct irq_pin_list { + int apic, pin, next; +} irq_2_pin[PIN_MAP_SIZE]; + +int vector_irq[NR_VECTORS] = { [0 ... NR_VECTORS - 1] = -1}; +#ifdef CONFIG_PCI_MSI +#define vector_to_irq(vector) \ + (platform_legacy_irq(vector) ? vector : vector_irq[vector]) +#else +#define vector_to_irq(vector) (vector) +#endif + +/* + * The common case is 1:1 IRQ<->pin mappings. Sometimes there are + * shared ISA-space IRQs, so we have to support them. We are super + * fast in the common case, and fast for shared ISA-space IRQs. + */ +static void add_pin_to_irq(unsigned int irq, int apic, int pin) +{ + static int first_free_entry = NR_IRQS; + struct irq_pin_list *entry = irq_2_pin + irq; + + while (entry->next) + entry = irq_2_pin + entry->next; + + if (entry->pin != -1) { + entry->next = first_free_entry; + entry = irq_2_pin + entry->next; + if (++first_free_entry >= PIN_MAP_SIZE) + panic("io_apic.c: whoops"); + } + entry->apic = apic; + entry->pin = pin; +} + +#ifndef CONFIG_XEN +/* + * Reroute an IRQ to a different pin. + */ +static void __init replace_pin_at_irq(unsigned int irq, + int oldapic, int oldpin, + int newapic, int newpin) +{ + struct irq_pin_list *entry = irq_2_pin + irq; + + while (1) { + if (entry->apic == oldapic && entry->pin == oldpin) { + entry->apic = newapic; + entry->pin = newpin; + } + if (!entry->next) + break; + entry = irq_2_pin + entry->next; + } +} + +static void __modify_IO_APIC_irq (unsigned int irq, unsigned long enable, unsigned long disable) +{ + struct irq_pin_list *entry = irq_2_pin + irq; + unsigned int pin, reg; + + for (;;) { + pin = entry->pin; + if (pin == -1) + break; + reg = io_apic_read(entry->apic, 0x10 + pin*2); + reg &= ~disable; + reg |= enable; + io_apic_modify(entry->apic, 0x10 + pin*2, reg); + if (!entry->next) + break; + entry = irq_2_pin + entry->next; + } +} + +/* mask = 1 */ +static void __mask_IO_APIC_irq (unsigned int irq) +{ + __modify_IO_APIC_irq(irq, 0x00010000, 0); +} + +/* mask = 0 */ +static void __unmask_IO_APIC_irq (unsigned int irq) +{ + __modify_IO_APIC_irq(irq, 0, 0x00010000); +} + +/* mask = 1, trigger = 0 */ +static void __mask_and_edge_IO_APIC_irq (unsigned int irq) +{ + __modify_IO_APIC_irq(irq, 0x00010000, 0x00008000); +} + +/* mask = 0, trigger = 1 */ +static void __unmask_and_level_IO_APIC_irq (unsigned int irq) +{ + __modify_IO_APIC_irq(irq, 0x00008000, 0x00010000); +} + +static void mask_IO_APIC_irq (unsigned int irq) +{ + unsigned long flags; + + spin_lock_irqsave(&ioapic_lock, flags); + __mask_IO_APIC_irq(irq); + spin_unlock_irqrestore(&ioapic_lock, flags); +} + +static void unmask_IO_APIC_irq (unsigned int irq) +{ + unsigned long flags; + + spin_lock_irqsave(&ioapic_lock, flags); + __unmask_IO_APIC_irq(irq); + spin_unlock_irqrestore(&ioapic_lock, flags); +} + +static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) +{ + struct IO_APIC_route_entry entry; + unsigned long flags; + + /* Check delivery_mode to be sure we're not clearing an SMI pin */ + spin_lock_irqsave(&ioapic_lock, flags); + *(((int*)&entry) + 0) = io_apic_read(apic, 0x10 + 2 * pin); + *(((int*)&entry) + 1) = io_apic_read(apic, 0x11 + 2 * pin); + spin_unlock_irqrestore(&ioapic_lock, flags); + if (entry.delivery_mode == dest_SMI) + return; + + /* + * Disable it in the IO-APIC irq-routing table: + */ + memset(&entry, 0, sizeof(entry)); + entry.mask = 1; + spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(apic, 0x10 + 2 * pin, *(((int *)&entry) + 0)); + io_apic_write(apic, 0x11 + 2 * pin, *(((int *)&entry) + 1)); + spin_unlock_irqrestore(&ioapic_lock, flags); +} + +static void clear_IO_APIC (void) +{ + int apic, pin; + + for (apic = 0; apic < nr_ioapics; apic++) + for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) + clear_IO_APIC_pin(apic, pin); +} + +static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask) +{ + unsigned long flags; + int pin; + struct irq_pin_list *entry = irq_2_pin + irq; + unsigned int apicid_value; + + apicid_value = cpu_mask_to_apicid(cpumask); + /* Prepare to do the io_apic_write */ + apicid_value = apicid_value << 24; + spin_lock_irqsave(&ioapic_lock, flags); + for (;;) { + pin = entry->pin; + if (pin == -1) + break; + io_apic_write(entry->apic, 0x10 + 1 + pin*2, apicid_value); + if (!entry->next) + break; + entry = irq_2_pin + entry->next; + } + spin_unlock_irqrestore(&ioapic_lock, flags); +} +#else +#define clear_IO_APIC() ((void)0) +#endif + +#if defined(CONFIG_IRQBALANCE) +# include <asm/processor.h> /* kernel_thread() */ +# include <linux/kernel_stat.h> /* kstat */ +# include <linux/slab.h> /* kmalloc() */ +# include <linux/timer.h> /* time_after() */ + +# ifdef CONFIG_BALANCED_IRQ_DEBUG +# define TDprintk(x...) do { printk("<%ld:%s:%d>: ", jiffies, __FILE__, __LINE__); printk(x); } while (0) +# define Dprintk(x...) do { TDprintk(x); } while (0) +# else +# define TDprintk(x...) +# define Dprintk(x...) +# endif + +cpumask_t __cacheline_aligned pending_irq_balance_cpumask[NR_IRQS]; + +#define IRQBALANCE_CHECK_ARCH -999 +static int irqbalance_disabled = IRQBALANCE_CHECK_ARCH; +static int physical_balance = 0; + +static struct irq_cpu_info { + unsigned long * last_irq; + unsigned long * irq_delta; + unsigned long irq; +} irq_cpu_data[NR_CPUS]; + +#define CPU_IRQ(cpu) (irq_cpu_data[cpu].irq) +#define LAST_CPU_IRQ(cpu,irq) (irq_cpu_data[cpu].last_irq[irq]) +#define IRQ_DELTA(cpu,irq) (irq_cpu_data[cpu].irq_delta[irq]) + +#define IDLE_ENOUGH(cpu,now) \ + (idle_cpu(cpu) && ((now) - per_cpu(irq_stat, (cpu)).idle_timestamp > 1)) + +#define IRQ_ALLOWED(cpu, allowed_mask) cpu_isset(cpu, allowed_mask) + +#define CPU_TO_PACKAGEINDEX(i) (first_cpu(cpu_sibling_map[i])) + +#define MAX_BALANCED_IRQ_INTERVAL (5*HZ) +#define MIN_BALANCED_IRQ_INTERVAL (HZ/2) +#define BALANCED_IRQ_MORE_DELTA (HZ/10) +#define BALANCED_IRQ_LESS_DELTA (HZ) + +static long balanced_irq_interval = MAX_BALANCED_IRQ_INTERVAL; + +static unsigned long move(int curr_cpu, cpumask_t allowed_mask, + unsigned long now, int direction) +{ + int search_idle = 1; + int cpu = curr_cpu; + + goto inside; + + do { + if (unlikely(cpu == curr_cpu)) + search_idle = 0; +inside: + if (direction == 1) { + cpu++; + if (cpu >= NR_CPUS) + cpu = 0; + } else { + cpu--; + if (cpu == -1) + cpu = NR_CPUS-1; + } + } while (!cpu_online(cpu) || !IRQ_ALLOWED(cpu,allowed_mask) || + (search_idle && !IDLE_ENOUGH(cpu,now))); + + return cpu; +} + +static inline void balance_irq(int cpu, int irq) +{ + unsigned long now = jiffies; + cpumask_t allowed_mask; + unsigned int new_cpu; + + if (irqbalance_disabled) + return; + + cpus_and(allowed_mask, cpu_online_map, irq_affinity[irq]); + new_cpu = move(cpu, allowed_mask, now, 1); + if (cpu != new_cpu) { + irq_desc_t *desc = irq_desc + irq; + unsigned long flags; + + spin_lock_irqsave(&desc->lock, flags); + pending_irq_balance_cpumask[irq] = cpumask_of_cpu(new_cpu); + spin_unlock_irqrestore(&desc->lock, flags); + } +} + +static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold) +{ + int i, j; + Dprintk("Rotating IRQs among CPUs.\n"); + for (i = 0; i < NR_CPUS; i++) { + for (j = 0; cpu_online(i) && (j < NR_IRQS); j++) { + if (!irq_desc[j].action) + continue; + /* Is it a significant load ? */ + if (IRQ_DELTA(CPU_TO_PACKAGEINDEX(i),j) < + useful_load_threshold) + continue; + balance_irq(i, j); + } + } + balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL, + balanced_irq_interval - BALANCED_IRQ_LESS_DELTA); + return; +} + +static void do_irq_balance(void) +{ + int i, j; + unsigned long max_cpu_irq = 0, min_cpu_irq = (~0); + unsigned long move_this_load = 0; + int max_loaded = 0, min_loaded = 0; + int load; + unsigned long useful_load_threshold = balanced_irq_interval + 10; + int selected_irq; + int tmp_loaded, first_attempt = 1; + unsigned long tmp_cpu_irq; + unsigned long imbalance = 0; + cpumask_t allowed_mask, target_cpu_mask, tmp; + + for (i = 0; i < NR_CPUS; i++) { + int package_index; + CPU_IRQ(i) = 0; + if (!cpu_online(i)) + continue; + package_index = CPU_TO_PACKAGEINDEX(i); + for (j = 0; j < NR_IRQS; j++) { + unsigned long value_now, delta; + /* Is this an active IRQ? */ + if (!irq_desc[j].action) + continue; + if ( package_index == i ) + IRQ_DELTA(package_index,j) = 0; + /* Determine the total count per processor per IRQ */ + value_now = (unsigned long) kstat_cpu(i).irqs[j]; + + /* Determine the activity per processor per IRQ */ + delta = value_now - LAST_CPU_IRQ(i,j); + + /* Update last_cpu_irq[][] for the next time */ + LAST_CPU_IRQ(i,j) = value_now; + + /* Ignore IRQs whose rate is less than the clock */ + if (delta < useful_load_threshold) + continue; + /* update the load for the processor or package total */ + IRQ_DELTA(package_index,j) += delta; + + /* Keep track of the higher numbered sibling as well */ + if (i != package_index) + CPU_IRQ(i) += delta; + /* + * We have sibling A and sibling B in the package + * + * cpu_irq[A] = load for cpu A + load for cpu B + * cpu_irq[B] = load for cpu B + */ + CPU_IRQ(package_index) += delta; + } + } + /* Find the least loaded processor package */ + for (i = 0; i < NR_CPUS; i++) { + if (!cpu_online(i)) + continue; + if (i != CPU_TO_PACKAGEINDEX(i)) + continue; + if (min_cpu_irq > CPU_IRQ(i)) { + min_cpu_irq = CPU_IRQ(i); + min_loaded = i; + } + } + max_cpu_irq = ULONG_MAX; + +tryanothercpu: + /* Look for heaviest loaded processor. + * We may come back to get the next heaviest loaded processor. + * Skip processors with trivial loads. + */ + tmp_cpu_irq = 0; + tmp_loaded = -1; + for (i = 0; i < NR_CPUS; i++) { + if (!cpu_online(i)) + continue; + if (i != CPU_TO_PACKAGEINDEX(i)) + continue; + if (max_cpu_irq <= CPU_IRQ(i)) + continue; + if (tmp_cpu_irq < CPU_IRQ(i)) { + tmp_cpu_irq = CPU_IRQ(i); + tmp_loaded = i; + } + } + + if (tmp_loaded == -1) { + /* In the case of small number of heavy interrupt sources, + * loading some of the cpus too much. We use Ingo's original + * approach to rotate them around. + */ + if (!first_attempt && imbalance >= useful_load_threshold) { + rotate_irqs_among_cpus(useful_load_threshold); + return; + } + goto not_worth_the_effort; + } + + first_attempt = 0; /* heaviest search */ + max_cpu_irq = tmp_cpu_irq; /* load */ + max_loaded = tmp_loaded; /* processor */ + imbalance = (max_cpu_irq - min_cpu_irq) / 2; + + Dprintk("max_loaded cpu = %d\n", max_loaded); + Dprintk("min_loaded cpu = %d\n", min_loaded); + Dprintk("max_cpu_irq load = %ld\n", max_cpu_irq); + Dprintk("min_cpu_irq load = %ld\n", min_cpu_irq); + Dprintk("load imbalance = %lu\n", imbalance); + + /* if imbalance is less than approx 10% of max load, then + * observe diminishing returns action. - quit + */ + if (imbalance < (max_cpu_irq >> 3)) { + Dprintk("Imbalance too trivial\n"); + goto not_worth_the_effort; + } + +tryanotherirq: + /* if we select an IRQ to move that can't go where we want, then + * see if there is another one to try. + */ + move_this_load = 0; + selected_irq = -1; + for (j = 0; j < NR_IRQS; j++) { + /* Is this an active IRQ? */ + if (!irq_desc[j].action) + continue; + if (imbalance <= IRQ_DELTA(max_loaded,j)) + continue; + /* Try to find the IRQ that is closest to the imbalance + * without going over. + */ + if (move_this_load < IRQ_DELTA(max_loaded,j)) { + move_this_load = IRQ_DELTA(max_loaded,j); + selected_irq = j; + } + } + if (selected_irq == -1) { + goto tryanothercpu; + } + + imbalance = move_this_load; + + /* For physical_balance case, we accumlated both load + * values in the one of the siblings cpu_irq[], + * to use the same code for physical and logical processors + * as much as possible. + * + * NOTE: the cpu_irq[] array holds the sum of the load for + * sibling A and sibling B in the slot for the lowest numbered + * sibling (A), _AND_ the load for sibling B in the slot for + * the higher numbered sibling. + * + * We seek the least loaded sibling by making the comparison + * (A+B)/2 vs B + */ + load = CPU_IRQ(min_loaded) >> 1; + for_each_cpu_mask(j, cpu_sibling_map[min_loaded]) { + if (load > CPU_IRQ(j)) { + /* This won't change cpu_sibling_map[min_loaded] */ + load = CPU_IRQ(j); + min_loaded = j; + } + } + + cpus_and(allowed_mask, cpu_online_map, irq_affinity[selected_irq]); + target_cpu_mask = cpumask_of_cpu(min_loaded); + cpus_and(tmp, target_cpu_mask, allowed_mask); + + if (!cpus_empty(tmp)) { + irq_desc_t *desc = irq_desc + selected_irq; + unsigned long flags; + + Dprintk("irq = %d moved to cpu = %d\n", + selected_irq, min_loaded); + /* mark for change destination */ + spin_lock_irqsave(&desc->lock, flags); + pending_irq_balance_cpumask[selected_irq] = + cpumask_of_cpu(min_loaded); + spin_unlock_irqrestore(&desc->lock, flags); + /* Since we made a change, come back sooner to + * check for more variation. + */ + balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL, + balanced_irq_interval - BALANCED_IRQ_LESS_DELTA); + return; + } + goto tryanotherirq; + +not_worth_the_effort: + /* + * if we did not find an IRQ to move, then adjust the time interval + * upward + */ + balanced_irq_interval = min((long)MAX_BALANCED_IRQ_INTERVAL, + balanced_irq_interval + BALANCED_IRQ_MORE_DELTA); + Dprintk("IRQ worth rotating not found\n"); + return; +} + +static int balanced_irq(void *unused) +{ + int i; + unsigned long prev_balance_time = jiffies; + long time_remaining = balanced_irq_interval; + + daemonize("kirqd"); + + /* push everything to CPU 0 to give us a starting point. */ + for (i = 0 ; i < NR_IRQS ; i++) { + pending_irq_balance_cpumask[i] = cpumask_of_cpu(0); + } + + for ( ; ; ) { + set_current_state(TASK_INTERRUPTIBLE); + time_remaining = schedule_timeout(time_remaining); + try_to_freeze(PF_FREEZE); + if (time_after(jiffies, + prev_balance_time+balanced_irq_interval)) { + preempt_disable(); + do_irq_balance(); + prev_balance_time = jiffies; + time_remaining = balanced_irq_interval; + preempt_enable(); + } + } + return 0; +} + +static int __init balanced_irq_init(void) +{ + int i; + struct cpuinfo_x86 *c; + cpumask_t tmp; + + cpus_shift_right(tmp, cpu_online_map, 2); + c = &boot_cpu_data; + /* When not overwritten by the command line ask subarchitecture. */ + if (irqbalance_disabled == IRQBALANCE_CHECK_ARCH) + irqbalance_disabled = NO_BALANCE_IRQ; + if (irqbalance_disabled) + return 0; + + /* disable irqbalance completely if there is only one processor online */ + if (num_online_cpus() < 2) { + irqbalance_disabled = 1; + return 0; + } + /* + * Enable physical balance only if more than 1 physical processor + * is present + */ + if (smp_num_siblings > 1 && !cpus_empty(tmp)) + physical_balance = 1; + + for (i = 0; i < NR_CPUS; i++) { + if (!cpu_online(i)) + continue; + irq_cpu_data[i].irq_delta = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL); + irq_cpu_data[i].last_irq = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL); + if (irq_cpu_data[i].irq_delta == NULL || irq_cpu_data[i].last_irq == NULL) { + printk(KERN_ERR "balanced_irq_init: out of memory"); + goto failed; + } + memset(irq_cpu_data[i].irq_delta,0,sizeof(unsigned long) * NR_IRQS); + memset(irq_cpu_data[i].last_irq,0,sizeof(unsigned long) * NR_IRQS); + } + + printk(KERN_INFO "Starting balanced_irq\n"); + if (kernel_thread(balanced_irq, NULL, CLONE_KERNEL) >= 0) + return 0; + else + printk(KERN_ERR "balanced_irq_init: failed to spawn balanced_irq"); +failed: + for (i = 0; i < NR_CPUS; i++) { + if(irq_cpu_data[i].irq_delta) + kfree(irq_cpu_data[i].irq_delta); + if(irq_cpu_data[i].last_irq) + kfree(irq_cpu_data[i].last_irq); + } + return 0; +} + +int __init irqbalance_disable(char *str) +{ + irqbalance_disabled = 1; + return 0; +} + +__setup("noirqbalance", irqbalance_disable); + +static inline void move_irq(int irq) +{ + /* note - we hold the desc->lock */ + if (unlikely(!cpus_empty(pending_irq_balance_cpumask[irq]))) { + set_ioapic_affinity_irq(irq, pending_irq_balance_cpumask[irq]); + cpus_clear(pending_irq_balance_cpumask[irq]); + } +} + +late_initcall(balanced_irq_init); + +#else /* !CONFIG_IRQBALANCE */ +static inline void move_irq(int irq) { } +#endif /* CONFIG_IRQBALANCE */ + +#ifndef CONFIG_SMP +void fastcall send_IPI_self(int vector) +{ +#ifndef CONFIG_XEN + unsigned int cfg; + + /* + * Wait for idle. + */ + apic_wait_icr_idle(); + cfg = APIC_DM_FIXED | APIC_DEST_SELF | vector | APIC_DEST_LOGICAL; + /* + * Send the IPI. The write to APIC_ICR fires this off. + */ + apic_write_around(APIC_ICR, cfg); +#endif +} +#endif /* !CONFIG_SMP */ + + +/* + * support for broken MP BIOSs, enables hand-redirection of PIRQ0-7 to + * specific CPU-side IRQs. + */ + +#define MAX_PIRQS 8 +static int pirq_entries [MAX_PIRQS]; +static int pirqs_enabled; +int skip_ioapic_setup; + +static int __init ioapic_setup(char *str) +{ + skip_ioapic_setup = 1; + return 1; +} + +__setup("noapic", ioapic_setup); + +static int __init ioapic_pirq_setup(char *str) +{ + int i, max; + int ints[MAX_PIRQS+1]; + + get_options(str, ARRAY_SIZE(ints), ints); + + for (i = 0; i < MAX_PIRQS; i++) + pirq_entries[i] = -1; + + pirqs_enabled = 1; + apic_printk(APIC_VERBOSE, KERN_INFO + "PIRQ redirection, working around broken MP-BIOS.\n"); + max = MAX_PIRQS; + if (ints[0] < MAX_PIRQS) + max = ints[0]; + + for (i = 0; i < max; i++) { + apic_printk(APIC_VERBOSE, KERN_DEBUG + "... PIRQ%d -> IRQ %d\n", i, ints[i+1]); + /* + * PIRQs are mapped upside down, usually. + */ + pirq_entries[MAX_PIRQS-i-1] = ints[i+1]; + } + return 1; +} + +__setup("pirq=", ioapic_pirq_setup); + +/* + * Find the IRQ entry number of a certain pin. + */ +static int find_irq_entry(int apic, int pin, int type) +{ + int i; + + for (i = 0; i < mp_irq_entries; i++) + if (mp_irqs[i].mpc_irqtype == type && + (mp_irqs[i].mpc_dstapic == mp_ioapics[apic].mpc_apicid || + mp_irqs[i].mpc_dstapic == MP_APIC_ALL) && + mp_irqs[i].mpc_dstirq == pin) + return i; + + return -1; +} + +#ifndef CONFIG_XEN +/* + * Find the pin to which IRQ[irq] (ISA) is connected + */ +static int find_isa_irq_pin(int irq, int type) +{ + int i; + + for (i = 0; i < mp_irq_entries; i++) { + int lbus = mp_irqs[i].mpc_srcbus; + + if ((mp_bus_id_to_type[lbus] == MP_BUS_ISA || + mp_bus_id_to_type[lbus] == MP_BUS_EISA || + mp_bus_id_to_type[lbus] == MP_BUS_MCA || + mp_bus_id_to_type[lbus] == MP_BUS_NEC98 + ) && + (mp_irqs[i].mpc_irqtype == type) && + (mp_irqs[i].mpc_srcbusirq == irq)) + + return mp_irqs[i].mpc_dstirq; + } + return -1; +} +#endif + +/* + * Find a specific PCI IRQ entry. + * Not an __init, possibly needed by modules + */ +static int pin_2_irq(int idx, int apic, int pin); + +int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin) +{ + int apic, i, best_guess = -1; + + apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, " + "slot:%d, pin:%d.\n", bus, slot, pin); + if (mp_bus_id_to_pci_bus[bus] == -1) { + printk(KERN_WARNING "PCI BIOS passed nonexistent PCI bus %d!\n", bus); + return -1; + } + for (i = 0; i < mp_irq_entries; i++) { + int lbus = mp_irqs[i].mpc_srcbus; + + for (apic = 0; apic < nr_ioapics; apic++) + if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic || + mp_irqs[i].mpc_dstapic == MP_APIC_ALL) + break; + + if ((mp_bus_id_to_type[lbus] == MP_BUS_PCI) && + !mp_irqs[i].mpc_irqtype && + (bus == lbus) && + (slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) { + int irq = pin_2_irq(i,apic,mp_irqs[i].mpc_dstirq); + + if (!(apic || IO_APIC_IRQ(irq))) + continue; + + if (pin == (mp_irqs[i].mpc_srcbusirq & 3)) + return irq; + /* + * Use the first all-but-pin matching entry as a + * best-guess fuzzy result for broken mptables. + */ + if (best_guess < 0) + best_guess = irq; + } + } + return best_guess; +} + +#ifndef CONFIG_XEN +/* + * This function currently is only a helper for the i386 smp boot process where + * we need to reprogram the ioredtbls to cater for the cpus which have come online + * so mask in all cases should simply be TARGET_CPUS + */ +void __init setup_ioapic_dest(void) +{ + int pin, ioapic, irq, irq_entry; + + if (skip_ioapic_setup == 1) + return; + + for (ioapic = 0; ioapic < nr_ioapics; ioapic++) { + for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) { + irq_entry = find_irq_entry(ioapic, pin, mp_INT); + if (irq_entry == -1) + continue; + irq = pin_2_irq(irq_entry, ioapic, pin); + set_ioapic_affinity_irq(irq, TARGET_CPUS); + } + + } +} +#endif /* !CONFIG_XEN */ + +/* + * EISA Edge/Level control register, ELCR + */ +static int EISA_ELCR(unsigned int irq) +{ + if (irq < 16) { + unsigned int port = 0x4d0 + (irq >> 3); + return (inb(port) >> (irq & 7)) & 1; + } + apic_printk(APIC_VERBOSE, KERN_INFO + "Broken MPtable reports ISA irq %d\n", irq); + return 0; +} + +/* EISA interrupts are always polarity zero and can be edge or level + * trigger depending on the ELCR value. If an interrupt is listed as + * EISA conforming in the MP table, that means its trigger type must + * be read in from the ELCR */ + +#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].mpc_srcbusirq)) +#define default_EISA_polarity(idx) (0) + +/* ISA interrupts are always polarity zero edge triggered, + * when listed as conforming in the MP table. */ + +#define default_ISA_trigger(idx) (0) +#define default_ISA_polarity(idx) (0) + +/* PCI interrupts are always polarity one level triggered, + * when listed as conforming in the MP table. */ + +#define default_PCI_trigger(idx) (1) +#define default_PCI_polarity(idx) (1) + +/* MCA interrupts are always polarity zero level triggered, + * when listed as conforming in the MP table. */ + +#define default_MCA_trigger(idx) (1) +#define default_MCA_polarity(idx) (0) + +/* NEC98 interrupts are always polarity zero edge triggered, + * when listed as conforming in the MP table. */ + +#define default_NEC98_trigger(idx) (0) +#define default_NEC98_polarity(idx) (0) + +static int __init MPBIOS_polarity(int idx) +{ + int bus = mp_irqs[idx].mpc_srcbus; + int polarity; + + /* + * Determine IRQ line polarity (high active or low active): + */ + switch (mp_irqs[idx].mpc_irqflag & 3) + { + case 0: /* conforms, ie. bus-type dependent polarity */ + { + switch (mp_bus_id_to_type[bus]) + { + case MP_BUS_ISA: /* ISA pin */ + { + polarity = default_ISA_polarity(idx); + break; + } + case MP_BUS_EISA: /* EISA pin */ + { + polarity = default_EISA_polarity(idx); + break; + } + case MP_BUS_PCI: /* PCI pin */ + { + polarity = default_PCI_polarity(idx); + break; + } + case MP_BUS_MCA: /* MCA pin */ + { + polarity = default_MCA_polarity(idx); + break; + } + case MP_BUS_NEC98: /* NEC 98 pin */ + { + polarity = default_NEC98_polarity(idx); + break; + } + default: + { + printk(KERN_WARNING "broken BIOS!!\n"); + polarity = 1; + break; + } + } + break; + } + case 1: /* high active */ + { + polarity = 0; + break; + } + case 2: /* reserved */ + { + printk(KERN_WARNING "broken BIOS!!\n"); + polarity = 1; + break; + } + case 3: /* low active */ + { + polarity = 1; + break; + } + default: /* invalid */ + { + printk(KERN_WARNING "broken BIOS!!\n"); + polarity = 1; + break; + } + } + return polarity; +} + +static int MPBIOS_trigger(int idx) +{ + int bus = mp_irqs[idx].mpc_srcbus; + int trigger; + + /* + * Determine IRQ trigger mode (edge or level sensitive): + */ + switch ((mp_irqs[idx].mpc_irqflag>>2) & 3) + { + case 0: /* conforms, ie. bus-type dependent */ + { + switch (mp_bus_id_to_type[bus]) + { + case MP_BUS_ISA: /* ISA pin */ + { + trigger = default_ISA_trigger(idx); + break; + } + case MP_BUS_EISA: /* EISA pin */ + { + trigger = default_EISA_trigger(idx); + break; + } + case MP_BUS_PCI: /* PCI pin */ + { + trigger = default_PCI_trigger(idx); + break; + } + case MP_BUS_MCA: /* MCA pin */ + { + trigger = default_MCA_trigger(idx); + break; + } + case MP_BUS_NEC98: /* NEC 98 pin */ + { + trigger = default_NEC98_trigger(idx); + break; + } + default: + { + printk(KERN_WARNING "broken BIOS!!\n"); + trigger = 1; + break; + } + } + break; + } + case 1: /* edge */ + { + trigger = 0; + break; + } + case 2: /* reserved */ + { + printk(KERN_WARNING "broken BIOS!!\n"); + trigger = 1; + break; + } + case 3: /* level */ + { + trigger = 1; + break; + } + default: /* invalid */ + { + printk(KERN_WARNING "broken BIOS!!\n"); + trigger = 0; + break; + } + } + return trigger; +} + +static inline int irq_polarity(int idx) +{ + return MPBIOS_polarity(idx); +} + +static inline int irq_trigger(int idx) +{ + return MPBIOS_trigger(idx); +} + +static int pin_2_irq(int idx, int apic, int pin) +{ + int irq, i; + int bus = mp_irqs[idx].mpc_srcbus; + + /* + * Debugging check, we are in big trouble if this message pops up! + */ + if (mp_irqs[idx].mpc_dstirq != pin) + printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n"); + + switch (mp_bus_id_to_type[bus]) + { + case MP_BUS_ISA: /* ISA pin */ + case MP_BUS_EISA: + case MP_BUS_MCA: + case MP_BUS_NEC98: + { + irq = mp_irqs[idx].mpc_srcbusirq; + break; + } + case MP_BUS_PCI: /* PCI pin */ + { + /* + * PCI IRQs are mapped in order + */ + i = irq = 0; + while (i < apic) + irq += nr_ioapic_registers[i++]; + irq += pin; + + /* + * For MPS mode, so far only needed by ES7000 platform + */ + if (ioapic_renumber_irq) + irq = ioapic_renumber_irq(apic, irq); + + break; + } + default: + { + printk(KERN_ERR "unknown bus type %d.\n",bus); + irq = 0; + break; + } + } + + /* + * PCI IRQ command line redirection. Yes, limits are hardcoded. + */ + if ((pin >= 16) && (pin <= 23)) { + if (pirq_entries[pin-16] != -1) { + if (!pirq_entries[pin-16]) { + apic_printk(APIC_VERBOSE, KERN_DEBUG + "disabling PIRQ%d\n", pin-16); + } else { + irq = pirq_entries[pin-16]; + apic_printk(APIC_VERBOSE, KERN_DEBUG + "using PIRQ%d -> IRQ %d\n", + pin-16, irq); + } + } + } + return irq; +} + +static inline int IO_APIC_irq_trigger(int irq) +{ + int apic, idx, pin; + + for (apic = 0; apic < nr_ioapics; apic++) { + for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { + idx = find_irq_entry(apic,pin,mp_INT); + if ((idx != -1) && (irq == pin_2_irq(idx,apic,pin))) + return irq_trigger(idx); + } + } + /* + * nonexistent IRQs are edge default + */ + return 0; +} + +/* irq_vectors is indexed by the sum of all RTEs in all I/O APICs. */ +u8 irq_vector[NR_IRQ_VECTORS]; /* = { FIRST_DEVICE_VECTOR , 0 }; */ + +int assign_irq_vector(int irq) +{ + static int current_vector = FIRST_DEVICE_VECTOR; + physdev_op_t op; + + BUG_ON(irq >= NR_IRQ_VECTORS); + if (irq != AUTO_ASSIGN && IO_APIC_VECTOR(irq) > 0) + return IO_APIC_VECTOR(irq); + + op.cmd = PHYSDEVOP_ASSIGN_VECTOR; + op.u.irq_op.irq = irq; + if (HYPERVISOR_physdev_op(&op)) + return -ENOSPC; + current_vector = op.u.irq_op.vector; + + vector_irq[current_vector] = irq; + if (irq != AUTO_ASSIGN) + IO_APIC_VECTOR(irq) = current_vector; + + return current_vector; +} + +#ifndef CONFIG_XEN +static struct hw_interrupt_type ioapic_level_type; +static struct hw_interrupt_type ioapic_edge_type; + +#define IOAPIC_AUTO -1 +#define IOAPIC_EDGE 0 +#define IOAPIC_LEVEL 1 + +static inline void ioapic_register_intr(int irq, int vector, unsigned long trigger) +{ + if (use_pci_vector() && !platform_legacy_irq(irq)) { + if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) || + trigger == IOAPIC_LEVEL) + irq_desc[vector].handler = &ioapic_level_type; + else + irq_desc[vector].handler = &ioapic_edge_type; + set_intr_gate(vector, interrupt[vector]); + } else { + if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) || + trigger == IOAPIC_LEVEL) + irq_desc[irq].handler = &ioapic_level_type; + else + irq_desc[irq].handler = &ioapic_edge_type; + set_intr_gate(vector, interrupt[irq]); + } +} +#else +#define ioapic_register_intr(_irq,_vector,_trigger) ((void)0) +#endif + +static void __init setup_IO_APIC_irqs(void) +{ + struct IO_APIC_route_entry entry; + int apic, pin, idx, irq, first_notcon = 1, vector; + unsigned long flags; + + apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n"); + + for (apic = 0; apic < nr_ioapics; apic++) { + for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { + + /* + * add it to the IO-APIC irq-routing table: + */ + memset(&entry,0,sizeof(entry)); + + entry.delivery_mode = INT_DELIVERY_MODE; + entry.dest_mode = INT_DEST_MODE; + entry.mask = 0; /* enable IRQ */ + entry.dest.logical.logical_dest = + cpu_mask_to_apicid(TARGET_CPUS); + + idx = find_irq_entry(apic,pin,mp_INT); + if (idx == -1) { + if (first_notcon) { + apic_printk(APIC_VERBOSE, KERN_DEBUG + " IO-APIC (apicid-pin) %d-%d", + mp_ioapics[apic].mpc_apicid, + pin); + first_notcon = 0; + } else + apic_printk(APIC_VERBOSE, ", %d-%d", + mp_ioapics[apic].mpc_apicid, pin); + continue; + } + + entry.trigger = irq_trigger(idx); + entry.polarity = irq_polarity(idx); + + if (irq_trigger(idx)) { + entry.trigger = 1; + entry.mask = 1; + } + + irq = pin_2_irq(idx, apic, pin); + /* + * skip adding the timer int on secondary nodes, which causes + * a small but painful rift in the time-space continuum + */ + if (multi_timer_check(apic, irq)) + continue; + else + add_pin_to_irq(irq, apic, pin); + + if (/*!apic &&*/ !IO_APIC_IRQ(irq)) + continue; + + if (IO_APIC_IRQ(irq)) { + vector = assign_irq_vector(irq); + entry.vector = vector; + ioapic_register_intr(irq, vector, IOAPIC_AUTO); + + if (!apic && (irq < 16)) + disable_8259A_irq(irq); + } + spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(apic, 0x11+2*pin, *(((int *)&entry)+1)); + io_apic_write(apic, 0x10+2*pin, *(((int *)&entry)+0)); + spin_unlock_irqrestore(&ioapic_lock, flags); + } + } + + if (!first_notcon) + apic_printk(APIC_VERBOSE, " not connected.\n"); +} + +/* + * Set up the 8259A-master output pin: + */ +#ifndef CONFIG_XEN +static void __init setup_ExtINT_IRQ0_pin(unsigned int pin, int vector) +{ + struct IO_APIC_route_entry entry; + unsigned long flags; + + memset(&entry,0,sizeof(entry)); + + disable_8259A_irq(0); + + /* mask LVT0 */ + apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); + + /* + * We use logical delivery to get the timer IRQ + * to the first CPU. + */ + entry.dest_mode = INT_DEST_MODE; + entry.mask = 0; /* unmask IRQ now */ + entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS); + entry.delivery_mode = INT_DELIVERY_MODE; + entry.polarity = 0; + entry.trigger = 0; + entry.vector = vector; + + /* + * The timer IRQ doesn't have to know that behind the + * scene we have a 8259A-master in AEOI mode ... + */ + irq_desc[0].handler = &ioapic_edge_type; + + /* + * Add it to the IO-APIC irq-routing table: + */ + spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(0, 0x11+2*pin, *(((int *)&entry)+1)); + io_apic_write(0, 0x10+2*pin, *(((int *)&entry)+0)); + spin_unlock_irqrestore(&ioapic_lock, flags); + + enable_8259A_irq(0); +} + +static inline void UNEXPECTED_IO_APIC(void) +{ +} + +void __init print_IO_APIC(void) +{ + int apic, i; + union IO_APIC_reg_00 reg_00; + union IO_APIC_reg_01 reg_01; + union IO_APIC_reg_02 reg_02; + union IO_APIC_reg_03 reg_03; + unsigned long flags; + + if (apic_verbosity == APIC_QUIET) + return; + + printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries); + for (i = 0; i < nr_ioapics; i++) + printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n", + mp_ioapics[i].mpc_apicid, nr_ioapic_registers[i]); + + /* + * We are a bit conservative about what we expect. We have to + * know about every hardware change ASAP. + */ + printk(KERN_INFO "testing the IO APIC.......................\n"); + + for (apic = 0; apic < nr_ioapics; apic++) { + + spin_lock_irqsave(&ioapic_lock, flags); + reg_00.raw = io_apic_read(apic, 0); + reg_01.raw = io_apic_read(apic, 1); + if (reg_01.bits.version >= 0x10) + reg_02.raw = io_apic_read(apic, 2); + if (reg_01.bits.version >= 0x20) + reg_03.raw = io_apic_read(apic, 3); + spin_unlock_irqrestore(&ioapic_lock, flags); + + printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mpc_apicid); + printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw); + printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID); + printk(KERN_DEBUG "....... : Delivery Type: %X\n", reg_00.bits.delivery_type); + printk(KERN_DEBUG "....... : LTS : %X\n", reg_00.bits.LTS); + if (reg_00.bits.ID >= get_physical_broadcast()) + UNEXPECTED_IO_APIC(); + if (reg_00.bits.__reserved_1 || reg_00.bits.__reserved_2) + UNEXPECTED_IO_APIC(); + + printk(KERN_DEBUG ".... register #01: %08X\n", reg_01.raw); + printk(KERN_DEBUG "....... : max redirection entries: %04X\n", reg_01.bits.entries); + if ( (reg_01.bits.entries != 0x0f) && /* older (Neptune) boards */ + (reg_01.bits.entries != 0x17) && /* typical ISA+PCI boards */ + (reg_01.bits.entries != 0x1b) && /* Compaq Proliant boards */ + (reg_01.bits.entries != 0x1f) && /* dual Xeon boards */ + (reg_01.bits.entries != 0x22) && /* bigger Xeon boards */ + (reg_01.bits.entries != 0x2E) && + (reg_01.bits.entries != 0x3F) + ) + UNEXPECTED_IO_APIC(); + + printk(KERN_DEBUG "....... : PRQ implemented: %X\n", reg_01.bits.PRQ); + printk(KERN_DEBUG "....... : IO APIC version: %04X\n", reg_01.bits.version); + if ( (reg_01.bits.version != 0x01) && /* 82489DX IO-APICs */ + (reg_01.bits.version != 0x10) && /* oldest IO-APICs */ + (reg_01.bits.version != 0x11) && /* Pentium/Pro IO-APICs */ + (reg_01.bits.version != 0x13) && /* Xeon IO-APICs */ + (reg_01.bits.version != 0x20) /* Intel P64H (82806 AA) */ + ) + UNEXPECTED_IO_APIC(); + if (reg_01.bits.__reserved_1 || reg_01.bits.__reserved_2) + UNEXPECTED_IO_APIC(); + + /* + * Some Intel chipsets with IO APIC VERSION of 0x1? don't have reg_02, + * but the value of reg_02 is read as the previous read register + * value, so ignore it if reg_02 == reg_01. + */ + if (reg_01.bits.version >= 0x10 && reg_02.raw != reg_01.raw) { + printk(KERN_DEBUG ".... register #02: %08X\n", reg_02.raw); + printk(KERN_DEBUG "....... : arbitration: %02X\n", reg_02.bits.arbitration); + if (reg_02.bits.__reserved_1 || reg_02.bits.__reserved_2) + UNEXPECTED_IO_APIC(); + } + + /* + * Some Intel chipsets with IO APIC VERSION of 0x2? don't have reg_02 + * or reg_03, but the value of reg_0[23] is read as the previous read + * register value, so ignore it if reg_03 == reg_0[12]. + */ + if (reg_01.bits.version >= 0x20 && reg_03.raw != reg_02.raw && + reg_03.raw != reg_01.raw) { + printk(KERN_DEBUG ".... register #03: %08X\n", reg_03.raw); + printk(KERN_DEBUG "....... : Boot DT : %X\n", reg_03.bits.boot_DT); + if (reg_03.bits.__reserved_1) + UNEXPECTED_IO_APIC(); + } + + printk(KERN_DEBUG ".... IRQ redirection table:\n"); + + printk(KERN_DEBUG " NR Log Phy Mask Trig IRR Pol" + " Stat Dest Deli Vect: \n"); + + for (i = 0; i <= reg_01.bits.entries; i++) { + struct IO_APIC_route_entry entry; + + spin_lock_irqsave(&ioapic_lock, flags); + *(((int *)&entry)+0) = io_apic_read(apic, 0x10+i*2); + *(((int *)&entry)+1) = io_apic_read(apic, 0x11+i*2); + spin_unlock_irqrestore(&ioapic_lock, flags); + + printk(KERN_DEBUG " %02x %03X %02X ", + i, + entry.dest.logical.logical_dest, + entry.dest.physical.physical_dest + ); + + printk("%1d %1d %1d %1d %1d %1d %1d %02X\n", + entry.mask, + entry.trigger, + entry.irr, + entry.polarity, + entry.delivery_status, + entry.dest_mode, + entry.delivery_mode, + entry.vector + ); + } + } + if (use_pci_vector()) + printk(KERN_INFO "Using vector-based indexing\n"); + printk(KERN_DEBUG "IRQ to pin mappings:\n"); + for (i = 0; i < NR_IRQS; i++) { + struct irq_pin_list *entry = irq_2_pin + i; + if (entry->pin < 0) + continue; + if (use_pci_vector() && !platform_legacy_irq(i)) + printk(KERN_DEBUG "IRQ%d ", IO_APIC_VECTOR(i)); + else + printk(KERN_DEBUG "IRQ%d ", i); + for (;;) { + printk("-> %d:%d", entry->apic, entry->pin); + if (!entry->next) + break; + entry = irq_2_pin + entry->next; + } + printk("\n"); + } + + printk(KERN_INFO ".................................... done.\n"); + + return; +} + +static void print_APIC_bitfield (int base) +{ + unsigned int v; + int i, j; + + if (apic_verbosity == APIC_QUIET) + return; + + printk(KERN_DEBUG "0123456789abcdef0123456789abcdef\n" KERN_DEBUG); + for (i = 0; i < 8; i++) { + v = apic_read(base + i*0x10); + for (j = 0; j < 32; j++) { + if (v & (1<<j)) + printk("1"); + else + printk("0"); + } + printk("\n"); + } +} + +void /*__init*/ print_local_APIC(void * dummy) +{ + unsigned int v, ver, maxlvt; + + if (apic_verbosity == APIC_QUIET) + return; + + printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n", + smp_processor_id(), hard_smp_processor_id()); + v = apic_read(APIC_ID); + printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, GET_APIC_ID(v)); + v = apic_read(APIC_LVR); + printk(KERN_INFO "... APIC VERSION: %08x\n", v); + ver = GET_APIC_VERSION(v); + maxlvt = get_maxlvt(); + + v = apic_read(APIC_TASKPRI); + printk(KERN_DEBUG "... APIC TASKPRI: %08x (%02x)\n", v, v & APIC_TPRI_MASK); + + if (APIC_INTEGRATED(ver)) { /* !82489DX */ + v = apic_read(APIC_ARBPRI); + printk(KERN_DEBUG "... APIC ARBPRI: %08x (%02x)\n", v, + v & APIC_ARBPRI_MASK); + v = apic_read(APIC_PROCPRI); + printk(KERN_DEBUG "... APIC PROCPRI: %08x\n", v); + } + + v = apic_read(APIC_EOI); + printk(KERN_DEBUG "... APIC EOI: %08x\n", v); + v = apic_read(APIC_RRR); + printk(KERN_DEBUG "... APIC RRR: %08x\n", v); + v = apic_read(APIC_LDR); + printk(KERN_DEBUG "... APIC LDR: %08x\n", v); + v = apic_read(APIC_DFR); + printk(KERN_DEBUG "... APIC DFR: %08x\n", v); + v = apic_read(APIC_SPIV); + printk(KERN_DEBUG "... APIC SPIV: %08x\n", v); + + printk(KERN_DEBUG "... APIC ISR field:\n"); + print_APIC_bitfield(APIC_ISR); + printk(KERN_DEBUG "... APIC TMR field:\n"); + print_APIC_bitfield(APIC_TMR); + printk(KERN_DEBUG "... APIC IRR field:\n"); + print_APIC_bitfield(APIC_IRR); + + if (APIC_INTEGRATED(ver)) { /* !82489DX */ + if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ + apic_write(APIC_ESR, 0); + v = apic_read(APIC_ESR); + printk(KERN_DEBUG "... APIC ESR: %08x\n", v); + } + + v = apic_read(APIC_ICR); + printk(KERN_DEBUG "... APIC ICR: %08x\n", v); + v = apic_read(APIC_ICR2); + printk(KERN_DEBUG "... APIC ICR2: %08x\n", v); + + v = apic_read(APIC_LVTT); + printk(KERN_DEBUG "... APIC LVTT: %08x\n", v); + + if (maxlvt > 3) { /* PC is LVT#4. */ + v = apic_read(APIC_LVTPC); + printk(KERN_DEBUG "... APIC LVTPC: %08x\n", v); + } + v = apic_read(APIC_LVT0); + printk(KERN_DEBUG "... APIC LVT0: %08x\n", v); + v = apic_read(APIC_LVT1); + printk(KERN_DEBUG "... APIC LVT1: %08x\n", v); + + if (maxlvt > 2) { /* ERR is LVT#3. */ + v = apic_read(APIC_LVTERR); + printk(KERN_DEBUG "... APIC LVTERR: %08x\n", v); + } + + v = apic_read(APIC_TMICT); + printk(KERN_DEBUG "... APIC TMICT: %08x\n", v); + v = apic_read(APIC_TMCCT); + printk(KERN_DEBUG "... APIC TMCCT: %08x\n", v); + v = apic_read(APIC_TDCR); + printk(KERN_DEBUG "... APIC TDCR: %08x\n", v); + printk("\n"); +} + +void print_all_local_APICs (void) +{ + on_each_cpu(print_local_APIC, NULL, 1, 1); +} + +void /*__init*/ print_PIC(void) +{ + extern spinlock_t i8259A_lock; + unsigned int v; + unsigned long flags; + + if (apic_verbosity == APIC_QUIET) + return; + + printk(KERN_DEBUG "\nprinting PIC contents\n"); + + spin_lock_irqsave(&i8259A_lock, flags); + + v = inb(0xa1) << 8 | inb(0x21); + printk(KERN_DEBUG "... PIC IMR: %04x\n", v); + + v = inb(0xa0) << 8 | inb(0x20); + printk(KERN_DEBUG "... PIC IRR: %04x\n", v); + + outb(0x0b,0xa0); + outb(0x0b,0x20); + v = inb(0xa0) << 8 | inb(0x20); + outb(0x0a,0xa0); + outb(0x0a,0x20); + + spin_unlock_irqrestore(&i8259A_lock, flags); + + printk(KERN_DEBUG "... PIC ISR: %04x\n", v); + + v = inb(0x4d1) << 8 | inb(0x4d0); + printk(KERN_DEBUG "... PIC ELCR: %04x\n", v); +} +#else +void __init print_IO_APIC(void) { } +#endif /* !CONFIG_XEN */ + +static void __init enable_IO_APIC(void) +{ + union IO_APIC_reg_01 reg_01; + int i; + unsigned long flags; + + for (i = 0; i < PIN_MAP_SIZE; i++) { + irq_2_pin[i].pin = -1; + irq_2_pin[i].next = 0; + } + if (!pirqs_enabled) + for (i = 0; i < MAX_PIRQS; i++) + pirq_entries[i] = -1; + + /* + * The number of IO-APIC IRQ registers (== #pins): + */ + for (i = 0; i < nr_ioapics; i++) { + spin_lock_irqsave(&ioapic_lock, flags); + reg_01.raw = io_apic_read(i, 1); + spin_unlock_irqrestore(&ioapic_lock, flags); + nr_ioapic_registers[i] = reg_01.bits.entries+1; + } + + /* + * Do not trust the IO-APIC being empty at bootup + */ + clear_IO_APIC(); +} + +/* + * Not an __init, needed by the reboot code + */ +void disable_IO_APIC(void) +{ + /* + * Clear the IO-APIC before rebooting: + */ + clear_IO_APIC(); + +#ifndef CONFIG_XEN + disconnect_bsp_APIC(); +#endif +} + +/* + * function to set the IO-APIC physical IDs based on the + * values stored in the MPC table. + * + * by Matt Domsch <Matt_Domsch@xxxxxxxx> Tue Dec 21 12:25:05 CST 1999 + */ + +#if !defined(CONFIG_XEN) && !defined(CONFIG_X86_NUMAQ) +static void __init setup_ioapic_ids_from_mpc(void) +{ + union IO_APIC_reg_00 reg_00; + physid_mask_t phys_id_present_map; + int apic; + int i; + unsigned char old_id; + unsigned long flags; + + /* + * This is broken; anything with a real cpu count has to + * circumvent this idiocy regardless. + */ + phys_id_present_map = ioapic_phys_id_map(phys_cpu_present_map); + + /* + * Set the IOAPIC ID to the value stored in the MPC table. + */ + for (apic = 0; apic < nr_ioapics; apic++) { + + /* Read the register 0 value */ + spin_lock_irqsave(&ioapic_lock, flags); + reg_00.raw = io_apic_read(apic, 0); + spin_unlock_irqrestore(&ioapic_lock, flags); + + old_id = mp_ioapics[apic].mpc_apicid; + + if (mp_ioapics[apic].mpc_apicid >= get_physical_broadcast()) { + printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the MPC table!...\n", + apic, mp_ioapics[apic].mpc_apicid); + printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n", + reg_00.bits.ID); + mp_ioapics[apic].mpc_apicid = reg_00.bits.ID; + } + + /* Don't check I/O APIC IDs for some xAPIC systems. They have + * no meaning without the serial APIC bus. */ + if (NO_IOAPIC_CHECK) + continue; + /* + * Sanity check, is the ID really free? Every APIC in a + * system must have a unique ID or we get lots of nice + * 'stuck on smp_invalidate_needed IPI wait' messages. + */ + if (check_apicid_used(phys_id_present_map, + mp_ioapics[apic].mpc_apicid)) { + printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n", + apic, mp_ioapics[apic].mpc_apicid); + for (i = 0; i < get_physical_broadcast(); i++) + if (!physid_isset(i, phys_id_present_map)) + break; + if (i >= get_physical_broadcast()) + panic("Max APIC ID exceeded!\n"); + printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n", + i); + physid_set(i, phys_id_present_map); + mp_ioapics[apic].mpc_apicid = i; + } else { + physid_mask_t tmp; + tmp = apicid_to_cpu_present(mp_ioapics[apic].mpc_apicid); + apic_printk(APIC_VERBOSE, "Setting %d in the " + "phys_id_present_map\n", + mp_ioapics[apic].mpc_apicid); + physids_or(phys_id_present_map, phys_id_present_map, tmp); + } + + + /* + * We need to adjust the IRQ routing table + * if the ID changed. + */ + if (old_id != mp_ioapics[apic].mpc_apicid) + for (i = 0; i < mp_irq_entries; i++) + if (mp_irqs[i].mpc_dstapic == old_id) + mp_irqs[i].mpc_dstapic + = mp_ioapics[apic].mpc_apicid; + + /* + * Read the right value from the MPC table and + * write it into the ID register. + */ + apic_printk(APIC_VERBOSE, KERN_INFO + "...changing IO-APIC physical APIC ID to %d ...", + mp_ioapics[apic].mpc_apicid); + + reg_00.bits.ID = mp_ioapics[apic].mpc_apicid; + spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(apic, 0, reg_00.raw); + spin_unlock_irqrestore(&ioapic_lock, flags); + + /* + * Sanity check + */ + spin_lock_irqsave(&ioapic_lock, flags); + reg_00.raw = io_apic_read(apic, 0); + spin_unlock_irqrestore(&ioapic_lock, flags); + if (reg_00.bits.ID != mp_ioapics[apic].mpc_apicid) + printk("could not set ID!\n"); + else + apic_printk(APIC_VERBOSE, " ok.\n"); + } +} +#else +static void __init setup_ioapic_ids_from_mpc(void) { } +#endif + +#ifndef CONFIG_XEN +/* + * There is a nasty bug in some older SMP boards, their mptable lies + * about the timer IRQ. We do the following to work around the situation: + * + * - timer IRQ defaults to IO-APIC IRQ + * - if this function detects that timer IRQs are defunct, then we fall + * back to ISA timer IRQs + */ +static int __init timer_irq_works(void) +{ + unsigned long t1 = jiffies; + + local_irq_enable(); + /* Let ten ticks pass... */ + mdelay((10 * 1000) / HZ); + + /* + * Expect a few ticks at least, to be sure some possible + * glue logic does not lock up after one or two first + * ticks in a non-ExtINT mode. Also the local APIC + * might have cached one ExtINT interrupt. Finally, at + * least one tick may be lost due to delays. + */ + if (jiffies - t1 > 4) + return 1; + + return 0; +} + +/* + * In the SMP+IOAPIC case it might happen that there are an unspecified + * number of pending IRQ events unhandled. These cases are very rare, + * so we 'resend' these IRQs via IPIs, to the same CPU. It's much + * better to do it this way as thus we do not have to be aware of + * 'pending' interrupts in the IRQ path, except at this point. + */ +/* + * Edge triggered needs to resend any interrupt + * that was delayed but this is now handled in the device + * independent code. + */ + +/* + * Starting up a edge-triggered IO-APIC interrupt is + * nasty - we need to make sure that we get the edge. + * If it is already asserted for some reason, we need + * return 1 to indicate that is was pending. + * + * This is not complete - we should be able to fake + * an edge even if it isn't on the 8259A... + */ +static unsigned int startup_edge_ioapic_irq(unsigned int irq) +{ + int was_pending = 0; + unsigned long flags; + + spin_lock_irqsave(&ioapic_lock, flags); + if (irq < 16) { + disable_8259A_irq(irq); + if (i8259A_irq_pending(irq)) + was_pending = 1; + } + __unmask_IO_APIC_irq(irq); + spin_unlock_irqrestore(&ioapic_lock, flags); + + return was_pending; +} + +/* + * Once we have recorded IRQ_PENDING already, we can mask the + * interrupt for real. This prevents IRQ storms from unhandled + * devices. + */ +static void ack_edge_ioapic_irq(unsigned int irq) +{ + move_irq(irq); + if ((irq_desc[irq].status & (IRQ_PENDING | IRQ_DISABLED)) + == (IRQ_PENDING | IRQ_DISABLED)) + mask_IO_APIC_irq(irq); + ack_APIC_irq(); +} + +/* + * Level triggered interrupts can just be masked, + * and shutting down and starting up the interrupt + * is the same as enabling and disabling them -- except + * with a startup need to return a "was pending" value. + * + * Level triggered interrupts are special because we + * do not touch any IO-APIC register while handling + * them. We ack the APIC in the end-IRQ handler, not + * in the start-IRQ-handler. Protection against reentrance + * from the same interrupt is still provided, both by the + * generic IRQ layer and by the fact that an unacked local + * APIC does not accept IRQs. + */ +static unsigned int startup_level_ioapic_irq (unsigned int irq) +{ + unmask_IO_APIC_irq(irq); + + return 0; /* don't check for pending */ +} + +static void end_level_ioapic_irq (unsigned int irq) +{ + unsigned long v; + int i; + + move_irq(irq); +/* + * It appears there is an erratum which affects at least version 0x11 + * of I/O APIC (that's the 82093AA and cores integrated into various + * chipsets). Under certain conditions a level-triggered interrupt is + * erroneously delivered as edge-triggered one but the respective IRR + * bit gets set nevertheless. As a result the I/O unit expects an EOI + * message but it will never arrive and further interrupts are blocked + * from the source. The exact reason is so far unknown, but the + * phenomenon was observed when two consecutive interrupt requests + * from a given source get delivered to the same CPU and the source is + * temporarily disabled in between. + * + * A workaround is to simulate an EOI message manually. We achieve it + * by setting the trigger mode to edge and then to level when the edge + * trigger mode gets detected in the TMR of a local APIC for a + * level-triggered interrupt. We mask the source for the time of the + * operation to prevent an edge-triggered interrupt escaping meanwhile. + * The idea is from Manfred Spraul. --macro + */ + i = IO_APIC_VECTOR(irq); + + v = apic_read(APIC_TMR + ((i & ~0x1f) >> 1)); + + ack_APIC_irq(); + + if (!(v & (1 << (i & 0x1f)))) { + atomic_inc(&irq_mis_count); + spin_lock(&ioapic_lock); + __mask_and_edge_IO_APIC_irq(irq); + __unmask_and_level_IO_APIC_irq(irq); + spin_unlock(&ioapic_lock); + } +} + +#ifdef CONFIG_PCI_MSI +static unsigned int startup_edge_ioapic_vector(unsigned int vector) +{ + int irq = vector_to_irq(vector); + + return startup_edge_ioapic_irq(irq); +} + +static void ack_edge_ioapic_vector(unsigned int vector) +{ + int irq = vector_to_irq(vector); + + ack_edge_ioapic_irq(irq); +} + +static unsigned int startup_level_ioapic_vector (unsigned int vector) +{ + int irq = vector_to_irq(vector); + + return startup_level_ioapic_irq (irq); +} + +static void end_level_ioapic_vector (unsigned int vector) +{ + int irq = vector_to_irq(vector); + + end_level_ioapic_irq(irq); +} + +static void mask_IO_APIC_vector (unsigned int vector) +{ + int irq = vector_to_irq(vector); + + mask_IO_APIC_irq(irq); +} + +static void unmask_IO_APIC_vector (unsigned int vector) +{ + int irq = vector_to_irq(vector); + + unmask_IO_APIC_irq(irq); +} + +static void set_ioapic_affinity_vector (unsigned int vector, + cpumask_t cpu_mask) +{ + int irq = vector_to_irq(vector); + + set_ioapic_affinity_irq(irq, cpu_mask); +} +#endif + +/* + * Level and edge triggered IO-APIC interrupts need different handling, + * so we use two separate IRQ descriptors. Edge triggered IRQs can be + * handled with the level-triggered descriptor, but that one has slightly + * more overhead. Level-triggered interrupts cannot be handled with the + * edge-triggered handler, without risking IRQ storms and other ugly + * races. + */ +static struct hw_interrupt_type ioapic_edge_type = { + .typename = "IO-APIC-edge", + .startup = startup_edge_ioapic, + .shutdown = shutdown_edge_ioapic, + .enable = enable_edge_ioapic, + .disable = disable_edge_ioapic, + .ack = ack_edge_ioapic, + .end = end_edge_ioapic, + .set_affinity = set_ioapic_affinity, +}; + +static struct hw_interrupt_type ioapic_level_type = { + .typename = "IO-APIC-level", + .startup = startup_level_ioapic, + .shutdown = shutdown_level_ioapic, + .enable = enable_level_ioapic, + .disable = disable_level_ioapic, + .ack = mask_and_ack_level_ioapic, + .end = end_level_ioapic, + .set_affinity = set_ioapic_affinity, +}; +#endif /* !CONFIG_XEN */ + +static inline void init_IO_APIC_traps(void) +{ + int irq; + + /* + * NOTE! The local APIC isn't very good at handling + * multiple interrupts at the same interrupt level. + * As the interrupt level is determined by taking the + * vector number and shifting that right by 4, we + * want to spread these out a bit so that they don't + * all fall in the same interrupt level. + * + * Also, we've got to be careful not to trash gate + * 0x80, because int 0x80 is hm, kind of importantish. ;) + */ + for (irq = 0; irq < NR_IRQS ; irq++) { + int tmp = irq; + if (use_pci_vector()) { + if (!platform_legacy_irq(tmp)) + if ((tmp = vector_to_irq(tmp)) == -1) + continue; + } + if (IO_APIC_IRQ(tmp) && !IO_APIC_VECTOR(tmp)) { + /* + * Hmm.. We don't have an entry for this, + * so default to an old-fashioned 8259 + * interrupt if we can.. + */ + if (irq < 16) + make_8259A_irq(irq); +#ifndef CONFIG_XEN + else + /* Strange. Oh, well.. */ + irq_desc[irq].handler = &no_irq_type; +#endif + } + } +} + +#ifndef CONFIG_XEN +static void enable_lapic_irq (unsigned int irq) +{ + unsigned long v; + + v = apic_read(APIC_LVT0); + apic_write_around(APIC_LVT0, v & ~APIC_LVT_MASKED); +} + +static void disable_lapic_irq (unsigned int irq) +{ + unsigned long v; + + v = apic_read(APIC_LVT0); + apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED); +} + +static void ack_lapic_irq (unsigned int irq) +{ + ack_APIC_irq(); +} + +static void end_lapic_irq (unsigned int i) { /* nothing */ } + +static struct hw_interrupt_type lapic_irq_type = { + .typename = "local-APIC-edge", + .startup = NULL, /* startup_irq() not used for IRQ0 */ + .shutdown = NULL, /* shutdown_irq() not used for IRQ0 */ + .enable = enable_lapic_irq, + .disable = disable_lapic_irq, + .ack = ack_lapic_irq, + .end = end_lapic_irq +}; + +static void setup_nmi (void) +{ + /* + * Dirty trick to enable the NMI watchdog ... + * We put the 8259A master into AEOI mode and + * unmask on all local APICs LVT0 as NMI. + * + * The idea to use the 8259A in AEOI mode ('8259A Virtual Wire') + * is from Maciej W. Rozycki - so we do not have to EOI from + * the NMI handler or the timer interrupt. + */ + apic_printk(APIC_VERBOSE, KERN_INFO "activating NMI Watchdog ..."); + + on_each_cpu(enable_NMI_through_LVT0, NULL, 1, 1); + + apic_printk(APIC_VERBOSE, " done.\n"); +} + +/* + * This looks a bit hackish but it's about the only one way of sending + * a few INTA cycles to 8259As and any associated glue logic. ICR does + * not support the ExtINT mode, unfortunately. We need to send these + * cycles as some i82489DX-based boards have glue logic that keeps the + * 8259A interrupt line asserted until INTA. --macro + */ +static inline void unlock_ExtINT_logic(void) +{ + int pin, i; + struct IO_APIC_route_entry entry0, entry1; + unsigned char save_control, save_freq_select; + unsigned long flags; + + pin = find_isa_irq_pin(8, mp_INT); + if (pin == -1) + return; + + spin_lock_irqsave(&ioapic_lock, flags); + *(((int *)&entry0) + 1) = io_apic_read(0, 0x11 + 2 * pin); + *(((int *)&entry0) + 0) = io_apic_read(0, 0x10 + 2 * pin); + spin_unlock_irqrestore(&ioapic_lock, flags); + clear_IO_APIC_pin(0, pin); + + memset(&entry1, 0, sizeof(entry1)); + + entry1.dest_mode = 0; /* physical delivery */ + entry1.mask = 0; /* unmask IRQ now */ + entry1.dest.physical.physical_dest = hard_smp_processor_id(); + entry1.delivery_mode = dest_ExtINT; + entry1.polarity = entry0.polarity; + entry1.trigger = 0; + entry1.vector = 0; + + spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry1) + 1)); + io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry1) + 0)); + spin_unlock_irqrestore(&ioapic_lock, flags); + + save_control = CMOS_READ(RTC_CONTROL); + save_freq_select = CMOS_READ(RTC_FREQ_SELECT); + CMOS_WRITE((save_freq_select & ~RTC_RATE_SELECT) | 0x6, + RTC_FREQ_SELECT); + CMOS_WRITE(save_control | RTC_PIE, RTC_CONTROL); + + i = 100; + while (i-- > 0) { + mdelay(10); + if ((CMOS_READ(RTC_INTR_FLAGS) & RTC_PF) == RTC_PF) + i -= 10; + } + + CMOS_WRITE(save_control, RTC_CONTROL); + CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); + clear_IO_APIC_pin(0, pin); + + spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry0) + 1)); + io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry0) + 0)); + spin_unlock_irqrestore(&ioapic_lock, flags); +} + +/* + * This code may look a bit paranoid, but it's supposed to cooperate with + * a wide range of boards and BIOS bugs. Fortunately only the timer IRQ + * is so screwy. Thanks to Brian Perkins for testing/hacking this beast + * fanatically on his truly buggy board. + */ +static inline void check_timer(void) +{ + int pin1, pin2; + int vector; + + /* + * get/set the timer IRQ vector: + */ + disable_8259A_irq(0); + vector = assign_irq_vector(0); + set_intr_gate(vector, interrupt[0]); + + /* + * Subtle, code in do_timer_interrupt() expects an AEOI + * mode for the 8259A whenever interrupts are routed + * through I/O APICs. Also IRQ0 has to be enabled in + * the 8259A which implies the virtual wire has to be + * disabled in the local APIC. + */ + apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); + init_8259A(1); + timer_ack = 1; + enable_8259A_irq(0); + + pin1 = find_isa_irq_pin(0, mp_INT); + pin2 = find_isa_irq_pin(0, mp_ExtINT); + + printk(KERN_INFO "..TIMER: vector=0x%02X pin1=%d pin2=%d\n", vector, pin1, pin2); + + if (pin1 != -1) { + /* + * Ok, does IRQ0 through the IOAPIC work? + */ + unmask_IO_APIC_irq(0); + if (timer_irq_works()) { + if (nmi_watchdog == NMI_IO_APIC) { + disable_8259A_irq(0); + setup_nmi(); + enable_8259A_irq(0); + } + return; + } + clear_IO_APIC_pin(0, pin1); + printk(KERN_ERR "..MP-BIOS bug: 8254 timer not connected to IO-APIC\n"); + } + + printk(KERN_INFO "...trying to set up timer (IRQ0) through the 8259A ... "); + if (pin2 != -1) { + printk("\n..... (found pin %d) ...", pin2); + /* + * legacy devices should be connected to IO APIC #0 + */ + setup_ExtINT_IRQ0_pin(pin2, vector); + if (timer_irq_works()) { + printk("works.\n"); + if (pin1 != -1) + replace_pin_at_irq(0, 0, pin1, 0, pin2); + else + add_pin_to_irq(0, 0, pin2); + if (nmi_watchdog == NMI_IO_APIC) { + setup_nmi(); + } + return; + } + /* + * Cleanup, just in case ... + */ + clear_IO_APIC_pin(0, pin2); + } + printk(" failed.\n"); + + if (nmi_watchdog == NMI_IO_APIC) { + printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n"); + nmi_watchdog = 0; + } + + printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ..."); + + disable_8259A_irq(0); + irq_desc[0].handler = &lapic_irq_type; + apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector); /* Fixed mode */ + enable_8259A_irq(0); + + if (timer_irq_works()) { + printk(" works.\n"); + return; + } + apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | vector); + printk(" failed.\n"); + + printk(KERN_INFO "...trying to set up timer as ExtINT IRQ..."); + + timer_ack = 0; + init_8259A(0); + make_8259A_irq(0); + apic_write_around(APIC_LVT0, APIC_DM_EXTINT); + + unlock_ExtINT_logic(); + + if (timer_irq_works()) { + printk(" works.\n"); + return; + } + printk(" failed :(.\n"); + panic("IO-APIC + timer doesn't work! Boot with apic=debug and send a " + "report. Then try booting with the 'noapic' option"); +} +#else +#define check_timer() ((void)0) +#endif + +/* + * + * IRQ's that are handled by the PIC in the MPS IOAPIC case. + * - IRQ2 is the cascade IRQ, and cannot be a io-apic IRQ. + * Linux doesn't really care, as it's not actually used + * for any interrupt handling anyway. + */ +#define PIC_IRQS (1 << PIC_CASCADE_IR) + +void __init setup_IO_APIC(void) +{ + enable_IO_APIC(); + + if (acpi_ioapic) + io_apic_irqs = ~0; /* all IRQs go through IOAPIC */ + else + io_apic_irqs = ~PIC_IRQS; + + printk("ENABLING IO-APIC IRQs\n"); + + /* + * Set up IO-APIC IRQ routing. + */ + if (!acpi_ioapic) + setup_ioapic_ids_from_mpc(); +#ifndef CONFIG_XEN + sync_Arb_IDs(); +#endif + setup_IO_APIC_irqs(); + init_IO_APIC_traps(); + check_timer(); + if (!acpi_ioapic) + print_IO_APIC(); +} + +/* + * Called after all the initialization is done. If we didnt find any + * APIC bugs then we can allow the modify fast path + */ + +static int __init io_apic_bug_finalize(void) +{ + if(sis_apic_bug == -1) + sis_apic_bug = 0; + return 0; +} + +late_initcall(io_apic_bug_finalize); + +struct sysfs_ioapic_data { + struct sys_device dev; + struct IO_APIC_route_entry entry[0]; +}; +static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS]; + +static int ioapic_suspend(struct sys_device *dev, pm_message_t state) +{ + struct IO_APIC_route_entry *entry; + struct sysfs_ioapic_data *data; + unsigned long flags; + int i; + + data = container_of(dev, struct sysfs_ioapic_data, dev); + entry = data->entry; + spin_lock_irqsave(&ioapic_lock, flags); + for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) { + *(((int *)entry) + 1) = io_apic_read(dev->id, 0x11 + 2 * i); + *(((int *)entry) + 0) = io_apic_read(dev->id, 0x10 + 2 * i); + } + spin_unlock_irqrestore(&ioapic_lock, flags); + + return 0; +} + +static int ioapic_resume(struct sys_device *dev) +{ + struct IO_APIC_route_entry *entry; + struct sysfs_ioapic_data *data; + unsigned long flags; + union IO_APIC_reg_00 reg_00; + int i; + + data = container_of(dev, struct sysfs_ioapic_data, dev); + entry = data->entry; + + spin_lock_irqsave(&ioapic_lock, flags); + reg_00.raw = io_apic_read(dev->id, 0); + if (reg_00.bits.ID != mp_ioapics[dev->id].mpc_apicid) { + reg_00.bits.ID = mp_ioapics[dev->id].mpc_apicid; + io_apic_write(dev->id, 0, reg_00.raw); + } + for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) { + io_apic_write(dev->id, 0x11+2*i, *(((int *)entry)+1)); + io_apic_write(dev->id, 0x10+2*i, *(((int *)entry)+0)); + } + spin_unlock_irqrestore(&ioapic_lock, flags); + + return 0; +} + +static struct sysdev_class ioapic_sysdev_class = { + set_kset_name("ioapic"), + .suspend = ioapic_suspend, + .resume = ioapic_resume, +}; + +static int __init ioapic_init_sysfs(void) +{ + struct sys_device * dev; + int i, size, error = 0; + + error = sysdev_class_register(&ioapic_sysdev_class); + if (error) + return error; + + for (i = 0; i < nr_ioapics; i++ ) { + size = sizeof(struct sys_device) + nr_ioapic_registers[i] + * sizeof(struct IO_APIC_route_entry); + mp_ioapic_data[i] = kmalloc(size, GFP_KERNEL); + if (!mp_ioapic_data[i]) { + printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i); + continue; + } + memset(mp_ioapic_data[i], 0, size); + dev = &mp_ioapic_data[i]->dev; + dev->id = i; + dev->cls = &ioapic_sysdev_class; + error = sysdev_register(dev); + if (error) { + kfree(mp_ioapic_data[i]); + mp_ioapic_data[i] = NULL; + printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i); + continue; + } + } + + return 0; +} + +device_initcall(ioapic_init_sysfs); + +/* -------------------------------------------------------------------------- + ACPI-based IOAPIC Configuration + -------------------------------------------------------------------------- */ + +#ifdef CONFIG_ACPI_BOOT + +int __init io_apic_get_unique_id (int ioapic, int apic_id) +{ +#ifndef CONFIG_XEN + union IO_APIC_reg_00 reg_00; + static physid_mask_t apic_id_map = PHYSID_MASK_NONE; + physid_mask_t tmp; + unsigned long flags; + int i = 0; + + /* + * The P4 platform supports up to 256 APIC IDs on two separate APIC + * buses (one for LAPICs, one for IOAPICs), where predecessors only + * supports up to 16 on one shared APIC bus. + * + * TBD: Expand LAPIC/IOAPIC support on P4-class systems to take full + * advantage of new APIC bus architecture. + */ + + if (physids_empty(apic_id_map)) + apic_id_map = ioapic_phys_id_map(phys_cpu_present_map); + + spin_lock_irqsave(&ioapic_lock, flags); + reg_00.raw = io_apic_read(ioapic, 0); + spin_unlock_irqrestore(&ioapic_lock, flags); + + if (apic_id >= get_physical_broadcast()) { + printk(KERN_WARNING "IOAPIC[%d]: Invalid apic_id %d, trying " + "%d\n", ioapic, apic_id, reg_00.bits.ID); + apic_id = reg_00.bits.ID; + } + + /* + * Every APIC in a system must have a unique ID or we get lots of nice + * 'stuck on smp_invalidate_needed IPI wait' messages. + */ + if (check_apicid_used(apic_id_map, apic_id)) { + + for (i = 0; i < get_physical_broadcast(); i++) { + if (!check_apicid_used(apic_id_map, i)) + break; + } + + if (i == get_physical_broadcast()) + panic("Max apic_id exceeded!\n"); + + printk(KERN_WARNING "IOAPIC[%d]: apic_id %d already used, " + "trying %d\n", ioapic, apic_id, i); + + apic_id = i; + } + + tmp = apicid_to_cpu_present(apic_id); + physids_or(apic_id_map, apic_id_map, tmp); + + if (reg_00.bits.ID != apic_id) { + reg_00.bits.ID = apic_id; + + spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(ioapic, 0, reg_00.raw); + reg_00.raw = io_apic_read(ioapic, 0); + spin_unlock_irqrestore(&ioapic_lock, flags); + + /* Sanity check */ + if (reg_00.bits.ID != apic_id) + panic("IOAPIC[%d]: Unable change apic_id!\n", ioapic); + } + + apic_printk(APIC_VERBOSE, KERN_INFO + "IOAPIC[%d]: Assigned apic_id %d\n", ioapic, apic_id); +#endif /* !CONFIG_XEN */ + + return apic_id; +} + + +int __init io_apic_get_version (int ioapic) +{ + union IO_APIC_reg_01 reg_01; + unsigned long flags; + + spin_lock_irqsave(&ioapic_lock, flags); + reg_01.raw = io_apic_read(ioapic, 1); + spin_unlock_irqrestore(&ioapic_lock, flags); + + return reg_01.bits.version; +} + + +int __init io_apic_get_redir_entries (int ioapic) +{ + union IO_APIC_reg_01 reg_01; + unsigned long flags; + + spin_lock_irqsave(&ioapic_lock, flags); + reg_01.raw = io_apic_read(ioapic, 1); + spin_unlock_irqrestore(&ioapic_lock, flags); + + return reg_01.bits.entries; +} + + +int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int active_high_low) +{ + struct IO_APIC_route_entry entry; + unsigned long flags; + + if (!IO_APIC_IRQ(irq)) { + printk(KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n", + ioapic); + return -EINVAL; + } + + /* + * Generate a PCI IRQ routing entry and program the IOAPIC accordingly. + * Note that we mask (disable) IRQs now -- these get enabled when the + * corresponding device driver registers for this IRQ. + */ + + memset(&entry,0,sizeof(entry)); + + entry.delivery_mode = INT_DELIVERY_MODE; + entry.dest_mode = INT_DEST_MODE; + entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS); + entry.trigger = edge_level; + entry.polarity = active_high_low; + entry.mask = 1; + + /* + * IRQs < 16 are already in the irq_2_pin[] map + */ + if (irq >= 16) + add_pin_to_irq(irq, ioapic, pin); + + entry.vector = assign_irq_vector(irq); + + apic_printk(APIC_DEBUG, KERN_DEBUG "IOAPIC[%d]: Set PCI routing entry " + "(%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i)\n", ioapic, + mp_ioapics[ioapic].mpc_apicid, pin, entry.vector, irq, + edge_level, active_high_low); + + ioapic_register_intr(irq, entry.vector, edge_level); + + if (!ioapic && (irq < 16)) + disable_8259A_irq(irq); + + spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(ioapic, 0x11+2*pin, *(((int *)&entry)+1)); + io_apic_write(ioapic, 0x10+2*pin, *(((int *)&entry)+0)); + spin_unlock_irqrestore(&ioapic_lock, flags); + + return 0; +} + +#endif /*CONFIG_ACPI_BOOT*/ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/ioport-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/ioport-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,125 @@ +/* + * linux/arch/i386/kernel/ioport.c + * + * This contains the io-permission bitmap code - written by obz, with changes + * by Linus. + */ + +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/ioport.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/stddef.h> +#include <linux/slab.h> +#include <linux/thread_info.h> +#include <xen/interface/physdev.h> + +/* Set EXTENT bits starting at BASE in BITMAP to value TURN_ON. */ +static void set_bitmap(unsigned long *bitmap, unsigned int base, unsigned int extent, int new_value) +{ + unsigned long mask; + unsigned long *bitmap_base = bitmap + (base / BITS_PER_LONG); + unsigned int low_index = base & (BITS_PER_LONG-1); + int length = low_index + extent; + + if (low_index != 0) { + mask = (~0UL << low_index); + if (length < BITS_PER_LONG) + mask &= ~(~0UL << length); + if (new_value) + *bitmap_base++ |= mask; + else + *bitmap_base++ &= ~mask; + length -= BITS_PER_LONG; + } + + mask = (new_value ? ~0UL : 0UL); + while (length >= BITS_PER_LONG) { + *bitmap_base++ = mask; + length -= BITS_PER_LONG; + } + + if (length > 0) { + mask = ~(~0UL << length); + if (new_value) + *bitmap_base++ |= mask; + else + *bitmap_base++ &= ~mask; + } +} + + +/* + * this changes the io permissions bitmap in the current task. + */ +asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) +{ + struct thread_struct * t = &current->thread; + unsigned long *bitmap; + physdev_op_t op; + + if ((from + num <= from) || (from + num > IO_BITMAP_BITS)) + return -EINVAL; + if (turn_on && !capable(CAP_SYS_RAWIO)) + return -EPERM; + + /* + * If it's the first ioperm() call in this thread's lifetime, set the + * IO bitmap up. ioperm() is much less timing critical than clone(), + * this is why we delay this operation until now: + */ + if (!t->io_bitmap_ptr) { + bitmap = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL); + if (!bitmap) + return -ENOMEM; + + memset(bitmap, 0xff, IO_BITMAP_BYTES); + t->io_bitmap_ptr = bitmap; + + op.cmd = PHYSDEVOP_SET_IOBITMAP; + op.u.set_iobitmap.bitmap = (char *)bitmap; + op.u.set_iobitmap.nr_ports = IO_BITMAP_BITS; + HYPERVISOR_physdev_op(&op); + } + + set_bitmap(t->io_bitmap_ptr, from, num, !turn_on); + + return 0; +} + +/* + * sys_iopl has to be used when you want to access the IO ports + * beyond the 0x3ff range: to get the full 65536 ports bitmapped + * you'd need 8kB of bitmaps/process, which is a bit excessive. + * + * Here we just change the eflags value on the stack: we allow + * only the super-user to do it. This depends on the stack-layout + * on system-call entry - see also fork() and the signal handling + * code. + */ + +asmlinkage long sys_iopl(unsigned int new_io_pl) +{ + unsigned int old_io_pl = current->thread.io_pl; + physdev_op_t op; + + if (new_io_pl > 3) + return -EINVAL; + + /* Need "raw I/O" privileges for direct port access. */ + if ((new_io_pl > old_io_pl) && !capable(CAP_SYS_RAWIO)) + return -EPERM; + + /* Change our version of the privilege levels. */ + current->thread.io_pl = new_io_pl; + + /* Force the change at ring 0. */ + op.cmd = PHYSDEVOP_SET_IOPL; + op.u.set_iopl.iopl = (new_io_pl == 0) ? 1 : new_io_pl; + HYPERVISOR_physdev_op(&op); + + return 0; +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/irq-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/irq-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,300 @@ +/* + * linux/arch/i386/kernel/irq.c + * + * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar + * + * This file contains the lowest level x86-specific interrupt + * entry, irq-stacks and irq statistics code. All the remaining + * irq logic is done by the generic kernel/irq/ code and + * by the x86-specific irq controller code. (e.g. i8259.c and + * io_apic.c.) + */ + +#include <asm/uaccess.h> +#include <linux/module.h> +#include <linux/seq_file.h> +#include <linux/interrupt.h> +#include <linux/kernel_stat.h> +#include <linux/notifier.h> +#include <linux/cpu.h> +#include <linux/delay.h> + +DEFINE_PER_CPU(irq_cpustat_t, irq_stat) ____cacheline_maxaligned_in_smp; +EXPORT_PER_CPU_SYMBOL(irq_stat); + +#ifndef CONFIG_X86_LOCAL_APIC +/* + * 'what should we do if we get a hw irq event on an illegal vector'. + * each architecture has to answer this themselves. + */ +void ack_bad_irq(unsigned int irq) +{ + printk("unexpected IRQ trap at vector %02x\n", irq); +} +#endif + +#ifdef CONFIG_4KSTACKS +/* + * per-CPU IRQ handling contexts (thread information and stack) + */ +union irq_ctx { + struct thread_info tinfo; + u32 stack[THREAD_SIZE/sizeof(u32)]; +}; + +static union irq_ctx *hardirq_ctx[NR_CPUS]; +static union irq_ctx *softirq_ctx[NR_CPUS]; +#endif + +/* + * do_IRQ handles all normal device IRQ's (the special + * SMP cross-CPU interrupts have their own specific + * handlers). + */ +fastcall unsigned int do_IRQ(struct pt_regs *regs) +{ + /* high bits used in ret_from_ code */ + int irq = regs->orig_eax & __IRQ_MASK(HARDIRQ_BITS); +#ifdef CONFIG_4KSTACKS + union irq_ctx *curctx, *irqctx; + u32 *isp; +#endif + + irq_enter(); +#ifdef CONFIG_DEBUG_STACKOVERFLOW + /* Debugging check for stack overflow: is there less than 1KB free? */ + { + long esp; + + __asm__ __volatile__("andl %%esp,%0" : + "=r" (esp) : "0" (THREAD_SIZE - 1)); + if (unlikely(esp < (sizeof(struct thread_info) + STACK_WARN))) { + printk("do_IRQ: stack overflow: %ld\n", + esp - sizeof(struct thread_info)); + dump_stack(); + } + } +#endif + +#ifdef CONFIG_4KSTACKS + + curctx = (union irq_ctx *) current_thread_info(); + irqctx = hardirq_ctx[smp_processor_id()]; + + /* + * this is where we switch to the IRQ stack. However, if we are + * already using the IRQ stack (because we interrupted a hardirq + * handler) we can't do that and just have to keep using the + * current stack (which is the irq stack already after all) + */ + if (curctx != irqctx) { + int arg1, arg2, ebx; + + /* build the stack frame on the IRQ stack */ + isp = (u32*) ((char*)irqctx + sizeof(*irqctx)); + irqctx->tinfo.task = curctx->tinfo.task; + irqctx->tinfo.previous_esp = current_stack_pointer; + + asm volatile( + " xchgl %%ebx,%%esp \n" + " call __do_IRQ \n" + " movl %%ebx,%%esp \n" + : "=a" (arg1), "=d" (arg2), "=b" (ebx) + : "0" (irq), "1" (regs), "2" (isp) + : "memory", "cc", "ecx" + ); + } else +#endif + __do_IRQ(irq, regs); + + irq_exit(); + + return 1; +} + +#ifdef CONFIG_4KSTACKS + +/* + * These should really be __section__(".bss.page_aligned") as well, but + * gcc's 3.0 and earlier don't handle that correctly. + */ +static char softirq_stack[NR_CPUS * THREAD_SIZE] + __attribute__((__aligned__(THREAD_SIZE))); + +static char hardirq_stack[NR_CPUS * THREAD_SIZE] + __attribute__((__aligned__(THREAD_SIZE))); + +/* + * allocate per-cpu stacks for hardirq and for softirq processing + */ +void irq_ctx_init(int cpu) +{ + union irq_ctx *irqctx; + + if (hardirq_ctx[cpu]) + return; + + irqctx = (union irq_ctx*) &hardirq_stack[cpu*THREAD_SIZE]; + irqctx->tinfo.task = NULL; + irqctx->tinfo.exec_domain = NULL; + irqctx->tinfo.cpu = cpu; + irqctx->tinfo.preempt_count = HARDIRQ_OFFSET; + irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); + + hardirq_ctx[cpu] = irqctx; + + irqctx = (union irq_ctx*) &softirq_stack[cpu*THREAD_SIZE]; + irqctx->tinfo.task = NULL; + irqctx->tinfo.exec_domain = NULL; + irqctx->tinfo.cpu = cpu; + irqctx->tinfo.preempt_count = SOFTIRQ_OFFSET; + irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); + + softirq_ctx[cpu] = irqctx; + + printk("CPU %u irqstacks, hard=%p soft=%p\n", + cpu,hardirq_ctx[cpu],softirq_ctx[cpu]); +} + +extern asmlinkage void __do_softirq(void); + +asmlinkage void do_softirq(void) +{ + unsigned long flags; + struct thread_info *curctx; + union irq_ctx *irqctx; + u32 *isp; + + if (in_interrupt()) + return; + + local_irq_save(flags); + + if (local_softirq_pending()) { + curctx = current_thread_info(); + irqctx = softirq_ctx[smp_processor_id()]; + irqctx->tinfo.task = curctx->task; + irqctx->tinfo.previous_esp = current_stack_pointer; + + /* build the stack frame on the softirq stack */ + isp = (u32*) ((char*)irqctx + sizeof(*irqctx)); + + asm volatile( + " xchgl %%ebx,%%esp \n" + " call __do_softirq \n" + " movl %%ebx,%%esp \n" + : "=b"(isp) + : "0"(isp) + : "memory", "cc", "edx", "ecx", "eax" + ); + } + + local_irq_restore(flags); +} + +EXPORT_SYMBOL(do_softirq); +#endif + +/* + * Interrupt statistics: + */ + +atomic_t irq_err_count; + +/* + * /proc/interrupts printing: + */ + +int show_interrupts(struct seq_file *p, void *v) +{ + int i = *(loff_t *) v, j; + struct irqaction * action; + unsigned long flags; + + if (i == 0) { + seq_printf(p, " "); + for_each_cpu(j) + seq_printf(p, "CPU%d ",j); + seq_putc(p, '\n'); + } + + if (i < NR_IRQS) { + spin_lock_irqsave(&irq_desc[i].lock, flags); + action = irq_desc[i].action; + if (!action) + goto skip; + seq_printf(p, "%3d: ",i); +#ifndef CONFIG_SMP + seq_printf(p, "%10u ", kstat_irqs(i)); +#else + for_each_cpu(j) + seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]); +#endif + seq_printf(p, " %14s", irq_desc[i].handler->typename); + seq_printf(p, " %s", action->name); + + for (action=action->next; action; action = action->next) + seq_printf(p, ", %s", action->name); + + seq_putc(p, '\n'); +skip: + spin_unlock_irqrestore(&irq_desc[i].lock, flags); + } else if (i == NR_IRQS) { + seq_printf(p, "NMI: "); + for_each_cpu(j) + seq_printf(p, "%10u ", nmi_count(j)); + seq_putc(p, '\n'); +#ifdef CONFIG_X86_LOCAL_APIC + seq_printf(p, "LOC: "); + for_each_cpu(j) + seq_printf(p, "%10u ", per_cpu(irq_stat,j).apic_timer_irqs); + seq_putc(p, '\n'); +#endif + seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count)); +#if defined(CONFIG_X86_IO_APIC) + seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count)); +#endif + } + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU + +void fixup_irqs(cpumask_t map) +{ + unsigned int irq; + static int warned; + + for (irq = 0; irq < NR_IRQS; irq++) { + cpumask_t mask; + if (irq == 2) + continue; + + cpus_and(mask, irq_affinity[irq], map); + if (any_online_cpu(mask) == NR_CPUS) { + /*printk("Breaking affinity for irq %i\n", irq);*/ + mask = map; + } + if (irq_desc[irq].handler->set_affinity) + irq_desc[irq].handler->set_affinity(irq, mask); + else if (irq_desc[irq].action && !(warned++)) + printk("Cannot set affinity for irq %i\n", irq); + } + +#if 0 + barrier(); + /* Ingo Molnar says: "after the IO-APIC masks have been redirected + [note the nop - the interrupt-enable boundary on x86 is two + instructions from sti] - to flush out pending hardirqs and + IPIs. After this point nothing is supposed to reach this CPU." */ + __asm__ __volatile__("sti; nop; cli"); + barrier(); +#else + /* That doesn't seem sufficient. Give it 1ms. */ + local_irq_enable(); + mdelay(1); + local_irq_disable(); +#endif +} +#endif + diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/ldt-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/ldt-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,268 @@ +/* + * linux/kernel/ldt.c + * + * Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds + * Copyright (C) 1999 Ingo Molnar <mingo@xxxxxxxxxx> + */ + +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/string.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/vmalloc.h> +#include <linux/slab.h> + +#include <asm/uaccess.h> +#include <asm/system.h> +#include <asm/ldt.h> +#include <asm/desc.h> + +#ifdef CONFIG_SMP /* avoids "defined but not used" warnig */ +static void flush_ldt(void *null) +{ + if (current->active_mm) + load_LDT(&current->active_mm->context); +} +#endif + +static int alloc_ldt(mm_context_t *pc, int mincount, int reload) +{ + void *oldldt; + void *newldt; + int oldsize; + + if (mincount <= pc->size) + return 0; + oldsize = pc->size; + mincount = (mincount+511)&(~511); + if (mincount*LDT_ENTRY_SIZE > PAGE_SIZE) + newldt = vmalloc(mincount*LDT_ENTRY_SIZE); + else + newldt = kmalloc(mincount*LDT_ENTRY_SIZE, GFP_KERNEL); + + if (!newldt) + return -ENOMEM; + + if (oldsize) + memcpy(newldt, pc->ldt, oldsize*LDT_ENTRY_SIZE); + oldldt = pc->ldt; + memset(newldt+oldsize*LDT_ENTRY_SIZE, 0, (mincount-oldsize)*LDT_ENTRY_SIZE); + pc->ldt = newldt; + wmb(); + pc->size = mincount; + wmb(); + + if (reload) { +#ifdef CONFIG_SMP + cpumask_t mask; + preempt_disable(); +#endif + make_pages_readonly( + pc->ldt, + (pc->size * LDT_ENTRY_SIZE) / PAGE_SIZE, + XENFEAT_writable_descriptor_tables); + load_LDT(pc); +#ifdef CONFIG_SMP + mask = cpumask_of_cpu(smp_processor_id()); + if (!cpus_equal(current->mm->cpu_vm_mask, mask)) + smp_call_function(flush_ldt, NULL, 1, 1); + preempt_enable(); +#endif + } + if (oldsize) { + make_pages_writable( + oldldt, + (oldsize * LDT_ENTRY_SIZE) / PAGE_SIZE, + XENFEAT_writable_descriptor_tables); + if (oldsize*LDT_ENTRY_SIZE > PAGE_SIZE) + vfree(oldldt); + else + kfree(oldldt); + } + return 0; +} + +static inline int copy_ldt(mm_context_t *new, mm_context_t *old) +{ + int err = alloc_ldt(new, old->size, 0); + if (err < 0) + return err; + memcpy(new->ldt, old->ldt, old->size*LDT_ENTRY_SIZE); + make_pages_readonly( + new->ldt, + (new->size * LDT_ENTRY_SIZE) / PAGE_SIZE, + XENFEAT_writable_descriptor_tables); + return 0; +} + +/* + * we do not have to muck with descriptors here, that is + * done in switch_mm() as needed. + */ +int init_new_context(struct task_struct *tsk, struct mm_struct *mm) +{ + struct mm_struct * old_mm; + int retval = 0; + + init_MUTEX(&mm->context.sem); + mm->context.size = 0; + old_mm = current->mm; + if (old_mm && old_mm->context.size > 0) { + down(&old_mm->context.sem); + retval = copy_ldt(&mm->context, &old_mm->context); + up(&old_mm->context.sem); + } + return retval; +} + +/* + * No need to lock the MM as we are the last user + */ +void destroy_context(struct mm_struct *mm) +{ + if (mm->context.size) { + if (mm == current->active_mm) + clear_LDT(); + make_pages_writable( + mm->context.ldt, + (mm->context.size * LDT_ENTRY_SIZE) / PAGE_SIZE, + XENFEAT_writable_descriptor_tables); + if (mm->context.size*LDT_ENTRY_SIZE > PAGE_SIZE) + vfree(mm->context.ldt); + else + kfree(mm->context.ldt); + mm->context.size = 0; + } +} + +static int read_ldt(void __user * ptr, unsigned long bytecount) +{ + int err; + unsigned long size; + struct mm_struct * mm = current->mm; + + if (!mm->context.size) + return 0; + if (bytecount > LDT_ENTRY_SIZE*LDT_ENTRIES) + bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES; + + down(&mm->context.sem); + size = mm->context.size*LDT_ENTRY_SIZE; + if (size > bytecount) + size = bytecount; + + err = 0; + if (copy_to_user(ptr, mm->context.ldt, size)) + err = -EFAULT; + up(&mm->context.sem); + if (err < 0) + goto error_return; + if (size != bytecount) { + /* zero-fill the rest */ + if (clear_user(ptr+size, bytecount-size) != 0) { + err = -EFAULT; + goto error_return; + } + } + return bytecount; +error_return: + return err; +} + +static int read_default_ldt(void __user * ptr, unsigned long bytecount) +{ + int err; + unsigned long size; + void *address; + + err = 0; + address = &default_ldt[0]; + size = 5*sizeof(struct desc_struct); + if (size > bytecount) + size = bytecount; + + err = size; + if (copy_to_user(ptr, address, size)) + err = -EFAULT; + + return err; +} + +static int write_ldt(void __user * ptr, unsigned long bytecount, int oldmode) +{ + struct mm_struct * mm = current->mm; + __u32 entry_1, entry_2; + int error; + struct user_desc ldt_info; + + error = -EINVAL; + if (bytecount != sizeof(ldt_info)) + goto out; + error = -EFAULT; + if (copy_from_user(&ldt_info, ptr, sizeof(ldt_info))) + goto out; + + error = -EINVAL; + if (ldt_info.entry_number >= LDT_ENTRIES) + goto out; + if (ldt_info.contents == 3) { + if (oldmode) + goto out; + if (ldt_info.seg_not_present == 0) + goto out; + } + + down(&mm->context.sem); + if (ldt_info.entry_number >= mm->context.size) { + error = alloc_ldt(&current->mm->context, ldt_info.entry_number+1, 1); + if (error < 0) + goto out_unlock; + } + + /* Allow LDTs to be cleared by the user. */ + if (ldt_info.base_addr == 0 && ldt_info.limit == 0) { + if (oldmode || LDT_empty(&ldt_info)) { + entry_1 = 0; + entry_2 = 0; + goto install; + } + } + + entry_1 = LDT_entry_a(&ldt_info); + entry_2 = LDT_entry_b(&ldt_info); + if (oldmode) + entry_2 &= ~(1 << 20); + + /* Install the new entry ... */ +install: + error = write_ldt_entry(mm->context.ldt, ldt_info.entry_number, + entry_1, entry_2); + +out_unlock: + up(&mm->context.sem); +out: + return error; +} + +asmlinkage int sys_modify_ldt(int func, void __user *ptr, unsigned long bytecount) +{ + int ret = -ENOSYS; + + switch (func) { + case 0: + ret = read_ldt(ptr, bytecount); + break; + case 1: + ret = write_ldt(ptr, bytecount, 1); + break; + case 2: + ret = read_default_ldt(ptr, bytecount); + break; + case 0x11: + ret = write_ldt(ptr, bytecount, 0); + break; + } + return ret; +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/microcode-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/microcode-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,163 @@ +/* + * Intel CPU Microcode Update Driver for Linux + * + * Copyright (C) 2000-2004 Tigran Aivazian + * + * This driver allows to upgrade microcode on Intel processors + * belonging to IA-32 family - PentiumPro, Pentium II, + * Pentium III, Xeon, Pentium 4, etc. + * + * Reference: Section 8.10 of Volume III, Intel Pentium 4 Manual, + * Order Number 245472 or free download from: + * + * http://developer.intel.com/design/pentium4/manuals/245472.htm + * + * For more information, go to http://www.urbanmyth.org/microcode + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +//#define DEBUG /* pr_debug */ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/sched.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/miscdevice.h> +#include <linux/spinlock.h> +#include <linux/mm.h> +#include <linux/syscalls.h> + +#include <asm/msr.h> +#include <asm/uaccess.h> +#include <asm/processor.h> + +MODULE_DESCRIPTION("Intel CPU (IA-32) Microcode Update Driver"); +MODULE_AUTHOR("Tigran Aivazian <tigran@xxxxxxxxxxx>"); +MODULE_LICENSE("GPL"); + +#define MICROCODE_VERSION "1.14-xen" + +#define DEFAULT_UCODE_DATASIZE (2000) /* 2000 bytes */ +#define MC_HEADER_SIZE (sizeof (microcode_header_t)) /* 48 bytes */ +#define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE) /* 2048 bytes */ + +/* no concurrent ->write()s are allowed on /dev/cpu/microcode */ +static DECLARE_MUTEX(microcode_sem); + +static void __user *user_buffer; /* user area microcode data buffer */ +static unsigned int user_buffer_size; /* it's size */ + +static int microcode_open (struct inode *unused1, struct file *unused2) +{ + return capable(CAP_SYS_RAWIO) ? 0 : -EPERM; +} + + +static int do_microcode_update (void) +{ + int err; + dom0_op_t op; + + err = sys_mlock((unsigned long)user_buffer, user_buffer_size); + if (err != 0) + return err; + + op.cmd = DOM0_MICROCODE; + op.u.microcode.data = user_buffer; + op.u.microcode.length = user_buffer_size; + err = HYPERVISOR_dom0_op(&op); + + (void)sys_munlock((unsigned long)user_buffer, user_buffer_size); + + return err; +} + +static ssize_t microcode_write (struct file *file, const char __user *buf, size_t len, loff_t *ppos) +{ + ssize_t ret; + + if (len < DEFAULT_UCODE_TOTALSIZE) { + printk(KERN_ERR "microcode: not enough data\n"); + return -EINVAL; + } + + if ((len >> PAGE_SHIFT) > num_physpages) { + printk(KERN_ERR "microcode: too much data (max %ld pages)\n", num_physpages); + return -EINVAL; + } + + down(&microcode_sem); + + user_buffer = (void __user *) buf; + user_buffer_size = (int) len; + + ret = do_microcode_update(); + if (!ret) + ret = (ssize_t)len; + + up(&microcode_sem); + + return ret; +} + +static int microcode_ioctl (struct inode *inode, struct file *file, + unsigned int cmd, unsigned long arg) +{ + switch (cmd) { + /* + * XXX: will be removed after microcode_ctl + * is updated to ignore failure of this ioctl() + */ + case MICROCODE_IOCFREE: + return 0; + default: + return -EINVAL; + } + return -EINVAL; +} + +static struct file_operations microcode_fops = { + .owner = THIS_MODULE, + .write = microcode_write, + .ioctl = microcode_ioctl, + .open = microcode_open, +}; + +static struct miscdevice microcode_dev = { + .minor = MICROCODE_MINOR, + .name = "microcode", + .devfs_name = "cpu/microcode", + .fops = &microcode_fops, +}; + +static int __init microcode_init (void) +{ + int error; + + error = misc_register(&microcode_dev); + if (error) { + printk(KERN_ERR + "microcode: can't misc_register on minor=%d\n", + MICROCODE_MINOR); + return error; + } + + printk(KERN_INFO + "IA-32 Microcode Update Driver: v" MICROCODE_VERSION " <tigran@xxxxxxxxxxx>\n"); + return 0; +} + +static void __exit microcode_exit (void) +{ + misc_deregister(&microcode_dev); + printk(KERN_INFO "IA-32 Microcode Update Driver v" MICROCODE_VERSION " unregistered\n"); +} + +module_init(microcode_init) +module_exit(microcode_exit) +MODULE_ALIAS_MISCDEV(MICROCODE_MINOR); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/mpparse-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/mpparse-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,1126 @@ +/* + * Intel Multiprocessor Specification 1.1 and 1.4 + * compliant MP-table parsing routines. + * + * (c) 1995 Alan Cox, Building #3 <alan@xxxxxxxxxx> + * (c) 1998, 1999, 2000 Ingo Molnar <mingo@xxxxxxxxxx> + * + * Fixes + * Erich Boleyn : MP v1.4 and additional changes. + * Alan Cox : Added EBDA scanning + * Ingo Molnar : various cleanups and rewrites + * Maciej W. Rozycki: Bits for default MP configurations + * Paul Diefenbaugh: Added full ACPI support + */ + +#include <linux/mm.h> +#include <linux/irq.h> +#include <linux/init.h> +#include <linux/acpi.h> +#include <linux/delay.h> +#include <linux/config.h> +#include <linux/bootmem.h> +#include <linux/smp_lock.h> +#include <linux/kernel_stat.h> +#include <linux/mc146818rtc.h> +#include <linux/bitops.h> + +#include <asm/smp.h> +#include <asm/acpi.h> +#include <asm/mtrr.h> +#include <asm/mpspec.h> +#include <asm/io_apic.h> + +#include <mach_apic.h> +#include <mach_mpparse.h> +#include <bios_ebda.h> + +/* Have we found an MP table */ +int smp_found_config; +unsigned int __initdata maxcpus = NR_CPUS; + +/* + * Various Linux-internal data structures created from the + * MP-table. + */ +int apic_version [MAX_APICS]; +int mp_bus_id_to_type [MAX_MP_BUSSES]; +int mp_bus_id_to_node [MAX_MP_BUSSES]; +int mp_bus_id_to_local [MAX_MP_BUSSES]; +int quad_local_to_mp_bus_id [NR_CPUS/4][4]; +int mp_bus_id_to_pci_bus [MAX_MP_BUSSES] = { [0 ... MAX_MP_BUSSES-1] = -1 }; +static int mp_current_pci_id; + +/* I/O APIC entries */ +struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS]; + +/* # of MP IRQ source entries */ +struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES]; + +/* MP IRQ source entries */ +int mp_irq_entries; + +int nr_ioapics; + +int pic_mode; +unsigned long mp_lapic_addr; + +/* Processor that is doing the boot up */ +unsigned int boot_cpu_physical_apicid = -1U; +unsigned int boot_cpu_logical_apicid = -1U; +/* Internal processor count */ +static unsigned int __initdata num_processors; + +/* Bitmask of physically existing CPUs */ +physid_mask_t phys_cpu_present_map; + +u8 bios_cpu_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; + +/* + * Intel MP BIOS table parsing routines: + */ + + +/* + * Checksum an MP configuration block. + */ + +static int __init mpf_checksum(unsigned char *mp, int len) +{ + int sum = 0; + + while (len--) + sum += *mp++; + + return sum & 0xFF; +} + +/* + * Have to match translation table entries to main table entries by counter + * hence the mpc_record variable .... can't see a less disgusting way of + * doing this .... + */ + +static int mpc_record; +static struct mpc_config_translation *translation_table[MAX_MPC_ENTRY] __initdata; + +#ifdef CONFIG_X86_NUMAQ +static int MP_valid_apicid(int apicid, int version) +{ + return hweight_long(apicid & 0xf) == 1 && (apicid >> 4) != 0xf; +} +#elif !defined(CONFIG_XEN) +static int MP_valid_apicid(int apicid, int version) +{ + if (version >= 0x14) + return apicid < 0xff; + else + return apicid < 0xf; +} +#endif + +#ifndef CONFIG_XEN +static void __init MP_processor_info (struct mpc_config_processor *m) +{ + int ver, apicid; + physid_mask_t tmp; + + if (!(m->mpc_cpuflag & CPU_ENABLED)) + return; + + apicid = mpc_apic_id(m, translation_table[mpc_record]); + + if (m->mpc_featureflag&(1<<0)) + Dprintk(" Floating point unit present.\n"); + if (m->mpc_featureflag&(1<<7)) + Dprintk(" Machine Exception supported.\n"); + if (m->mpc_featureflag&(1<<8)) + Dprintk(" 64 bit compare & exchange supported.\n"); + if (m->mpc_featureflag&(1<<9)) + Dprintk(" Internal APIC present.\n"); + if (m->mpc_featureflag&(1<<11)) + Dprintk(" SEP present.\n"); + if (m->mpc_featureflag&(1<<12)) + Dprintk(" MTRR present.\n"); + if (m->mpc_featureflag&(1<<13)) + Dprintk(" PGE present.\n"); + if (m->mpc_featureflag&(1<<14)) + Dprintk(" MCA present.\n"); + if (m->mpc_featureflag&(1<<15)) + Dprintk(" CMOV present.\n"); + if (m->mpc_featureflag&(1<<16)) + Dprintk(" PAT present.\n"); + if (m->mpc_featureflag&(1<<17)) + Dprintk(" PSE present.\n"); + if (m->mpc_featureflag&(1<<18)) + Dprintk(" PSN present.\n"); + if (m->mpc_featureflag&(1<<19)) + Dprintk(" Cache Line Flush Instruction present.\n"); + /* 20 Reserved */ + if (m->mpc_featureflag&(1<<21)) + Dprintk(" Debug Trace and EMON Store present.\n"); + if (m->mpc_featureflag&(1<<22)) + Dprintk(" ACPI Thermal Throttle Registers present.\n"); + if (m->mpc_featureflag&(1<<23)) + Dprintk(" MMX present.\n"); + if (m->mpc_featureflag&(1<<24)) + Dprintk(" FXSR present.\n"); + if (m->mpc_featureflag&(1<<25)) + Dprintk(" XMM present.\n"); + if (m->mpc_featureflag&(1<<26)) + Dprintk(" Willamette New Instructions present.\n"); + if (m->mpc_featureflag&(1<<27)) + Dprintk(" Self Snoop present.\n"); + if (m->mpc_featureflag&(1<<28)) + Dprintk(" HT present.\n"); + if (m->mpc_featureflag&(1<<29)) + Dprintk(" Thermal Monitor present.\n"); + /* 30, 31 Reserved */ + + + if (m->mpc_cpuflag & CPU_BOOTPROCESSOR) { + Dprintk(" Bootup CPU\n"); + boot_cpu_physical_apicid = m->mpc_apicid; + boot_cpu_logical_apicid = apicid; + } + + if (num_processors >= NR_CPUS) { + printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached." + " Processor ignored.\n", NR_CPUS); + return; + } + + if (num_processors >= maxcpus) { + printk(KERN_WARNING "WARNING: maxcpus limit of %i reached." + " Processor ignored.\n", maxcpus); + return; + } + num_processors++; + ver = m->mpc_apicver; + + if (!MP_valid_apicid(apicid, ver)) { + printk(KERN_WARNING "Processor #%d INVALID. (Max ID: %d).\n", + m->mpc_apicid, MAX_APICS); + --num_processors; + return; + } + + tmp = apicid_to_cpu_present(apicid); + physids_or(phys_cpu_present_map, phys_cpu_present_map, tmp); + + /* + * Validate version + */ + if (ver == 0x0) { + printk(KERN_WARNING "BIOS bug, APIC version is 0 for CPU#%d! fixing up to 0x10. (tell your hw vendor)\n", m->mpc_apicid); + ver = 0x10; + } + apic_version[m->mpc_apicid] = ver; + bios_cpu_apicid[num_processors - 1] = m->mpc_apicid; +} +#else +void __init MP_processor_info (struct mpc_config_processor *m) +{ + num_processors++; +} +#endif /* CONFIG_XEN */ + +static void __init MP_bus_info (struct mpc_config_bus *m) +{ + char str[7]; + + memcpy(str, m->mpc_bustype, 6); + str[6] = 0; + + mpc_oem_bus_info(m, str, translation_table[mpc_record]); + + if (strncmp(str, BUSTYPE_ISA, sizeof(BUSTYPE_ISA)-1) == 0) { + mp_bus_id_to_type[m->mpc_busid] = MP_BUS_ISA; + } else if (strncmp(str, BUSTYPE_EISA, sizeof(BUSTYPE_EISA)-1) == 0) { + mp_bus_id_to_type[m->mpc_busid] = MP_BUS_EISA; + } else if (strncmp(str, BUSTYPE_PCI, sizeof(BUSTYPE_PCI)-1) == 0) { + mpc_oem_pci_bus(m, translation_table[mpc_record]); + mp_bus_id_to_type[m->mpc_busid] = MP_BUS_PCI; + mp_bus_id_to_pci_bus[m->mpc_busid] = mp_current_pci_id; + mp_current_pci_id++; + } else if (strncmp(str, BUSTYPE_MCA, sizeof(BUSTYPE_MCA)-1) == 0) { + mp_bus_id_to_type[m->mpc_busid] = MP_BUS_MCA; + } else if (strncmp(str, BUSTYPE_NEC98, sizeof(BUSTYPE_NEC98)-1) == 0) { + mp_bus_id_to_type[m->mpc_busid] = MP_BUS_NEC98; + } else { + printk(KERN_WARNING "Unknown bustype %s - ignoring\n", str); + } +} + +static void __init MP_ioapic_info (struct mpc_config_ioapic *m) +{ + if (!(m->mpc_flags & MPC_APIC_USABLE)) + return; + + printk(KERN_INFO "I/O APIC #%d Version %d at 0x%lX.\n", + m->mpc_apicid, m->mpc_apicver, m->mpc_apicaddr); + if (nr_ioapics >= MAX_IO_APICS) { + printk(KERN_CRIT "Max # of I/O APICs (%d) exceeded (found %d).\n", + MAX_IO_APICS, nr_ioapics); + panic("Recompile kernel with bigger MAX_IO_APICS!.\n"); + } + if (!m->mpc_apicaddr) { + printk(KERN_ERR "WARNING: bogus zero I/O APIC address" + " found in MP table, skipping!\n"); + return; + } + mp_ioapics[nr_ioapics] = *m; + nr_ioapics++; +} + +static void __init MP_intsrc_info (struct mpc_config_intsrc *m) +{ + mp_irqs [mp_irq_entries] = *m; + Dprintk("Int: type %d, pol %d, trig %d, bus %d," + " IRQ %02x, APIC ID %x, APIC INT %02x\n", + m->mpc_irqtype, m->mpc_irqflag & 3, + (m->mpc_irqflag >> 2) & 3, m->mpc_srcbus, + m->mpc_srcbusirq, m->mpc_dstapic, m->mpc_dstirq); + if (++mp_irq_entries == MAX_IRQ_SOURCES) + panic("Max # of irq sources exceeded!!\n"); +} + +static void __init MP_lintsrc_info (struct mpc_config_lintsrc *m) +{ + Dprintk("Lint: type %d, pol %d, trig %d, bus %d," + " IRQ %02x, APIC ID %x, APIC LINT %02x\n", + m->mpc_irqtype, m->mpc_irqflag & 3, + (m->mpc_irqflag >> 2) &3, m->mpc_srcbusid, + m->mpc_srcbusirq, m->mpc_destapic, m->mpc_destapiclint); + /* + * Well it seems all SMP boards in existence + * use ExtINT/LVT1 == LINT0 and + * NMI/LVT2 == LINT1 - the following check + * will show us if this assumptions is false. + * Until then we do not have to add baggage. + */ + if ((m->mpc_irqtype == mp_ExtINT) && + (m->mpc_destapiclint != 0)) + BUG(); + if ((m->mpc_irqtype == mp_NMI) && + (m->mpc_destapiclint != 1)) + BUG(); +} + +#ifdef CONFIG_X86_NUMAQ +static void __init MP_translation_info (struct mpc_config_translation *m) +{ + printk(KERN_INFO "Translation: record %d, type %d, quad %d, global %d, local %d\n", mpc_record, m->trans_type, m->trans_quad, m->trans_global, m->trans_local); + + if (mpc_record >= MAX_MPC_ENTRY) + printk(KERN_ERR "MAX_MPC_ENTRY exceeded!\n"); + else + translation_table[mpc_record] = m; /* stash this for later */ + if (m->trans_quad < MAX_NUMNODES && !node_online(m->trans_quad)) + node_set_online(m->trans_quad); +} + +/* + * Read/parse the MPC oem tables + */ + +static void __init smp_read_mpc_oem(struct mp_config_oemtable *oemtable, \ + unsigned short oemsize) +{ + int count = sizeof (*oemtable); /* the header size */ + unsigned char *oemptr = ((unsigned char *)oemtable)+count; + + mpc_record = 0; + printk(KERN_INFO "Found an OEM MPC table at %8p - parsing it ... \n", oemtable); + if (memcmp(oemtable->oem_signature,MPC_OEM_SIGNATURE,4)) + { + printk(KERN_WARNING "SMP mpc oemtable: bad signature [%c%c%c%c]!\n", + oemtable->oem_signature[0], + oemtable->oem_signature[1], + oemtable->oem_signature[2], + oemtable->oem_signature[3]); + return; + } + if (mpf_checksum((unsigned char *)oemtable,oemtable->oem_length)) + { + printk(KERN_WARNING "SMP oem mptable: checksum error!\n"); + return; + } + while (count < oemtable->oem_length) { + switch (*oemptr) { + case MP_TRANSLATION: + { + struct mpc_config_translation *m= + (struct mpc_config_translation *)oemptr; + MP_translation_info(m); + oemptr += sizeof(*m); + count += sizeof(*m); + ++mpc_record; + break; + } + default: + { + printk(KERN_WARNING "Unrecognised OEM table entry type! - %d\n", (int) *oemptr); + return; + } + } + } +} + +static inline void mps_oem_check(struct mp_config_table *mpc, char *oem, + char *productid) +{ + if (strncmp(oem, "IBM NUMA", 8)) + printk("Warning! May not be a NUMA-Q system!\n"); + if (mpc->mpc_oemptr) + smp_read_mpc_oem((struct mp_config_oemtable *) mpc->mpc_oemptr, + mpc->mpc_oemsize); +} +#endif /* CONFIG_X86_NUMAQ */ + +/* + * Read/parse the MPC + */ + +static int __init smp_read_mpc(struct mp_config_table *mpc) +{ + char str[16]; + char oem[10]; + int count=sizeof(*mpc); + unsigned char *mpt=((unsigned char *)mpc)+count; + + if (memcmp(mpc->mpc_signature,MPC_SIGNATURE,4)) { + printk(KERN_ERR "SMP mptable: bad signature [0x%x]!\n", + *(u32 *)mpc->mpc_signature); + return 0; + } + if (mpf_checksum((unsigned char *)mpc,mpc->mpc_length)) { + printk(KERN_ERR "SMP mptable: checksum error!\n"); + return 0; + } + if (mpc->mpc_spec!=0x01 && mpc->mpc_spec!=0x04) { + printk(KERN_ERR "SMP mptable: bad table version (%d)!!\n", + mpc->mpc_spec); + return 0; + } + if (!mpc->mpc_lapic) { + printk(KERN_ERR "SMP mptable: null local APIC address!\n"); + return 0; + } + memcpy(oem,mpc->mpc_oem,8); + oem[8]=0; + printk(KERN_INFO "OEM ID: %s ",oem); + + memcpy(str,mpc->mpc_productid,12); + str[12]=0; + printk("Product ID: %s ",str); + + mps_oem_check(mpc, oem, str); + + printk("APIC at: 0x%lX\n",mpc->mpc_lapic); + + /* + * Save the local APIC address (it might be non-default) -- but only + * if we're not using ACPI. + */ + if (!acpi_lapic) + mp_lapic_addr = mpc->mpc_lapic; + + /* + * Now process the configuration blocks. + */ + mpc_record = 0; + while (count < mpc->mpc_length) { + switch(*mpt) { + case MP_PROCESSOR: + { + struct mpc_config_processor *m= + (struct mpc_config_processor *)mpt; + /* ACPI may have already provided this data */ + if (!acpi_lapic) + MP_processor_info(m); + mpt += sizeof(*m); + count += sizeof(*m); + break; + } + case MP_BUS: + { + struct mpc_config_bus *m= + (struct mpc_config_bus *)mpt; + MP_bus_info(m); + mpt += sizeof(*m); + count += sizeof(*m); + break; + } + case MP_IOAPIC: + { + struct mpc_config_ioapic *m= + (struct mpc_config_ioapic *)mpt; + MP_ioapic_info(m); + mpt+=sizeof(*m); + count+=sizeof(*m); + break; + } + case MP_INTSRC: + { + struct mpc_config_intsrc *m= + (struct mpc_config_intsrc *)mpt; + + MP_intsrc_info(m); + mpt+=sizeof(*m); + count+=sizeof(*m); + break; + } + case MP_LINTSRC: + { + struct mpc_config_lintsrc *m= + (struct mpc_config_lintsrc *)mpt; + MP_lintsrc_info(m); + mpt+=sizeof(*m); + count+=sizeof(*m); + break; + } + default: + { + count = mpc->mpc_length; + break; + } + } + ++mpc_record; + } + clustered_apic_check(); + if (!num_processors) + printk(KERN_ERR "SMP mptable: no processors registered!\n"); + return num_processors; +} + +static int __init ELCR_trigger(unsigned int irq) +{ + unsigned int port; + + port = 0x4d0 + (irq >> 3); + return (inb(port) >> (irq & 7)) & 1; +} + +static void __init construct_default_ioirq_mptable(int mpc_default_type) +{ + struct mpc_config_intsrc intsrc; + int i; + int ELCR_fallback = 0; + + intsrc.mpc_type = MP_INTSRC; + intsrc.mpc_irqflag = 0; /* conforming */ + intsrc.mpc_srcbus = 0; + intsrc.mpc_dstapic = mp_ioapics[0].mpc_apicid; + + intsrc.mpc_irqtype = mp_INT; + + /* + * If true, we have an ISA/PCI system with no IRQ entries + * in the MP table. To prevent the PCI interrupts from being set up + * incorrectly, we try to use the ELCR. The sanity check to see if + * there is good ELCR data is very simple - IRQ0, 1, 2 and 13 can + * never be level sensitive, so we simply see if the ELCR agrees. + * If it does, we assume it's valid. + */ + if (mpc_default_type == 5) { + printk(KERN_INFO "ISA/PCI bus type with no IRQ information... falling back to ELCR\n"); + + if (ELCR_trigger(0) || ELCR_trigger(1) || ELCR_trigger(2) || ELCR_trigger(13)) + printk(KERN_WARNING "ELCR contains invalid data... not using ELCR\n"); + else { + printk(KERN_INFO "Using ELCR to identify PCI interrupts\n"); + ELCR_fallback = 1; + } + } + + for (i = 0; i < 16; i++) { + switch (mpc_default_type) { + case 2: + if (i == 0 || i == 13) + continue; /* IRQ0 & IRQ13 not connected */ + /* fall through */ + default: + if (i == 2) + continue; /* IRQ2 is never connected */ + } + + if (ELCR_fallback) { + /* + * If the ELCR indicates a level-sensitive interrupt, we + * copy that information over to the MP table in the + * irqflag field (level sensitive, active high polarity). + */ + if (ELCR_trigger(i)) + intsrc.mpc_irqflag = 13; + else + intsrc.mpc_irqflag = 0; + } + + intsrc.mpc_srcbusirq = i; + intsrc.mpc_dstirq = i ? i : 2; /* IRQ0 to INTIN2 */ + MP_intsrc_info(&intsrc); + } + + intsrc.mpc_irqtype = mp_ExtINT; + intsrc.mpc_srcbusirq = 0; + intsrc.mpc_dstirq = 0; /* 8259A to INTIN0 */ + MP_intsrc_info(&intsrc); +} + +static inline void __init construct_default_ISA_mptable(int mpc_default_type) +{ + struct mpc_config_processor processor; + struct mpc_config_bus bus; + struct mpc_config_ioapic ioapic; + struct mpc_config_lintsrc lintsrc; + int linttypes[2] = { mp_ExtINT, mp_NMI }; + int i; + + /* + * local APIC has default address + */ + mp_lapic_addr = APIC_DEFAULT_PHYS_BASE; + + /* + * 2 CPUs, numbered 0 & 1. + */ + processor.mpc_type = MP_PROCESSOR; + /* Either an integrated APIC or a discrete 82489DX. */ + processor.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01; + processor.mpc_cpuflag = CPU_ENABLED; + processor.mpc_cpufeature = (boot_cpu_data.x86 << 8) | + (boot_cpu_data.x86_model << 4) | + boot_cpu_data.x86_mask; + processor.mpc_featureflag = boot_cpu_data.x86_capability[0]; + processor.mpc_reserved[0] = 0; + processor.mpc_reserved[1] = 0; + for (i = 0; i < 2; i++) { + processor.mpc_apicid = i; + MP_processor_info(&processor); + } + + bus.mpc_type = MP_BUS; + bus.mpc_busid = 0; + switch (mpc_default_type) { + default: + printk("???\n"); + printk(KERN_ERR "Unknown standard configuration %d\n", + mpc_default_type); + /* fall through */ + case 1: + case 5: + memcpy(bus.mpc_bustype, "ISA ", 6); + break; + case 2: + case 6: + case 3: + memcpy(bus.mpc_bustype, "EISA ", 6); + break; + case 4: + case 7: + memcpy(bus.mpc_bustype, "MCA ", 6); + } + MP_bus_info(&bus); + if (mpc_default_type > 4) { + bus.mpc_busid = 1; + memcpy(bus.mpc_bustype, "PCI ", 6); + MP_bus_info(&bus); + } + + ioapic.mpc_type = MP_IOAPIC; + ioapic.mpc_apicid = 2; + ioapic.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01; + ioapic.mpc_flags = MPC_APIC_USABLE; + ioapic.mpc_apicaddr = 0xFEC00000; + MP_ioapic_info(&ioapic); + + /* + * We set up most of the low 16 IO-APIC pins according to MPS rules. + */ + construct_default_ioirq_mptable(mpc_default_type); + + lintsrc.mpc_type = MP_LINTSRC; + lintsrc.mpc_irqflag = 0; /* conforming */ + lintsrc.mpc_srcbusid = 0; + lintsrc.mpc_srcbusirq = 0; + lintsrc.mpc_destapic = MP_APIC_ALL; + for (i = 0; i < 2; i++) { + lintsrc.mpc_irqtype = linttypes[i]; + lintsrc.mpc_destapiclint = i; + MP_lintsrc_info(&lintsrc); + } +} + +static struct intel_mp_floating *mpf_found; + +/* + * Scan the memory blocks for an SMP configuration block. + */ +void __init get_smp_config (void) +{ + struct intel_mp_floating *mpf = mpf_found; + + /* + * ACPI may be used to obtain the entire SMP configuration or just to + * enumerate/configure processors (CONFIG_ACPI_BOOT). Note that + * ACPI supports both logical (e.g. Hyper-Threading) and physical + * processors, where MPS only supports physical. + */ + if (acpi_lapic && acpi_ioapic) { + printk(KERN_INFO "Using ACPI (MADT) for SMP configuration information\n"); + return; + } + else if (acpi_lapic) + printk(KERN_INFO "Using ACPI for processor (LAPIC) configuration information\n"); + + printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n", mpf->mpf_specification); + if (mpf->mpf_feature2 & (1<<7)) { + printk(KERN_INFO " IMCR and PIC compatibility mode.\n"); + pic_mode = 1; + } else { + printk(KERN_INFO " Virtual Wire compatibility mode.\n"); + pic_mode = 0; + } + + /* + * Now see if we need to read further. + */ + if (mpf->mpf_feature1 != 0) { + + printk(KERN_INFO "Default MP configuration #%d\n", mpf->mpf_feature1); + construct_default_ISA_mptable(mpf->mpf_feature1); + + } else if (mpf->mpf_physptr) { + + /* + * Read the physical hardware table. Anything here will + * override the defaults. + */ + if (!smp_read_mpc(isa_bus_to_virt(mpf->mpf_physptr))) { + smp_found_config = 0; + printk(KERN_ERR "BIOS bug, MP table errors detected!...\n"); + printk(KERN_ERR "... disabling SMP support. (tell your hw vendor)\n"); + return; + } + /* + * If there are no explicit MP IRQ entries, then we are + * broken. We set up most of the low 16 IO-APIC pins to + * ISA defaults and hope it will work. + */ + if (!mp_irq_entries) { + struct mpc_config_bus bus; + + printk(KERN_ERR "BIOS bug, no explicit IRQ entries, using default mptable. (tell your hw vendor)\n"); + + bus.mpc_type = MP_BUS; + bus.mpc_busid = 0; + memcpy(bus.mpc_bustype, "ISA ", 6); + MP_bus_info(&bus); + + construct_default_ioirq_mptable(0); + } + + } else + BUG(); + + printk(KERN_INFO "Processors: %d\n", num_processors); + /* + * Only use the first configuration found. + */ +} + +static int __init smp_scan_config (unsigned long base, unsigned long length) +{ + unsigned long *bp = isa_bus_to_virt(base); + struct intel_mp_floating *mpf; + + Dprintk("Scan SMP from %p for %ld bytes.\n", bp,length); + if (sizeof(*mpf) != 16) + printk("Error: MPF size\n"); + + while (length > 0) { + mpf = (struct intel_mp_floating *)bp; + if ((*bp == SMP_MAGIC_IDENT) && + (mpf->mpf_length == 1) && + !mpf_checksum((unsigned char *)bp, 16) && + ((mpf->mpf_specification == 1) + || (mpf->mpf_specification == 4)) ) { + + smp_found_config = 1; +#ifndef CONFIG_XEN + printk(KERN_INFO "found SMP MP-table at %08lx\n", + virt_to_phys(mpf)); + reserve_bootmem(virt_to_phys(mpf), PAGE_SIZE); + if (mpf->mpf_physptr) { + /* + * We cannot access to MPC table to compute + * table size yet, as only few megabytes from + * the bottom is mapped now. + * PC-9800's MPC table places on the very last + * of physical memory; so that simply reserving + * PAGE_SIZE from mpg->mpf_physptr yields BUG() + * in reserve_bootmem. + */ + unsigned long size = PAGE_SIZE; + unsigned long end = max_low_pfn * PAGE_SIZE; + if (mpf->mpf_physptr + size > end) + size = end - mpf->mpf_physptr; + reserve_bootmem(mpf->mpf_physptr, size); + } +#else + printk(KERN_INFO "found SMP MP-table at %08lx\n", + ((unsigned long)bp - (unsigned long)isa_bus_to_virt(base)) + base); +#endif + + mpf_found = mpf; + return 1; + } + bp += 4; + length -= 16; + } + return 0; +} + +void __init find_smp_config (void) +{ +#ifndef CONFIG_XEN + unsigned int address; +#endif + + /* + * FIXME: Linux assumes you have 640K of base ram.. + * this continues the error... + * + * 1) Scan the bottom 1K for a signature + * 2) Scan the top 1K of base RAM + * 3) Scan the 64K of bios + */ + if (smp_scan_config(0x0,0x400) || + smp_scan_config(639*0x400,0x400) || + smp_scan_config(0xF0000,0x10000)) + return; + /* + * If it is an SMP machine we should know now, unless the + * configuration is in an EISA/MCA bus machine with an + * extended bios data area. + * + * there is a real-mode segmented pointer pointing to the + * 4K EBDA area at 0x40E, calculate and scan it here. + * + * NOTE! There are Linux loaders that will corrupt the EBDA + * area, and as such this kind of SMP config may be less + * trustworthy, simply because the SMP table may have been + * stomped on during early boot. These loaders are buggy and + * should be fixed. + * + * MP1.4 SPEC states to only scan first 1K of 4K EBDA. + */ + +#ifndef CONFIG_XEN + address = get_bios_ebda(); + if (address) + smp_scan_config(address, 0x400); +#endif +} + +/* -------------------------------------------------------------------------- + ACPI-based MP Configuration + -------------------------------------------------------------------------- */ + +#ifdef CONFIG_ACPI_BOOT + +void __init mp_register_lapic_address ( + u64 address) +{ +#ifndef CONFIG_XEN + mp_lapic_addr = (unsigned long) address; + + if (boot_cpu_physical_apicid == -1U) + boot_cpu_physical_apicid = GET_APIC_ID(apic_read(APIC_ID)); + + Dprintk("Boot CPU = %d\n", boot_cpu_physical_apicid); +#endif +} + + +void __init mp_register_lapic ( + u8 id, + u8 enabled) +{ + struct mpc_config_processor processor; + int boot_cpu = 0; + + if (MAX_APICS - id <= 0) { + printk(KERN_WARNING "Processor #%d invalid (max %d)\n", + id, MAX_APICS); + return; + } + + if (id == boot_cpu_physical_apicid) + boot_cpu = 1; + +#ifndef CONFIG_XEN + processor.mpc_type = MP_PROCESSOR; + processor.mpc_apicid = id; + processor.mpc_apicver = GET_APIC_VERSION(apic_read(APIC_LVR)); + processor.mpc_cpuflag = (enabled ? CPU_ENABLED : 0); + processor.mpc_cpuflag |= (boot_cpu ? CPU_BOOTPROCESSOR : 0); + processor.mpc_cpufeature = (boot_cpu_data.x86 << 8) | + (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask; + processor.mpc_featureflag = boot_cpu_data.x86_capability[0]; + processor.mpc_reserved[0] = 0; + processor.mpc_reserved[1] = 0; +#endif + + MP_processor_info(&processor); +} + +#if defined(CONFIG_X86_IO_APIC) && (defined(CONFIG_ACPI_INTERPRETER) || defined(CONFIG_ACPI_BOOT)) + +#define MP_ISA_BUS 0 +#define MP_MAX_IOAPIC_PIN 127 + +static struct mp_ioapic_routing { + int apic_id; + int gsi_base; + int gsi_end; + u32 pin_programmed[4]; +} mp_ioapic_routing[MAX_IO_APICS]; + + +static int mp_find_ioapic ( + int gsi) +{ + int i = 0; + + /* Find the IOAPIC that manages this GSI. */ + for (i = 0; i < nr_ioapics; i++) { + if ((gsi >= mp_ioapic_routing[i].gsi_base) + && (gsi <= mp_ioapic_routing[i].gsi_end)) + return i; + } + + printk(KERN_ERR "ERROR: Unable to locate IOAPIC for GSI %d\n", gsi); + + return -1; +} + + +void __init mp_register_ioapic ( + u8 id, + u32 address, + u32 gsi_base) +{ + int idx = 0; + + if (nr_ioapics >= MAX_IO_APICS) { + printk(KERN_ERR "ERROR: Max # of I/O APICs (%d) exceeded " + "(found %d)\n", MAX_IO_APICS, nr_ioapics); + panic("Recompile kernel with bigger MAX_IO_APICS!\n"); + } + if (!address) { + printk(KERN_ERR "WARNING: Bogus (zero) I/O APIC address" + " found in MADT table, skipping!\n"); + return; + } + + idx = nr_ioapics++; + + mp_ioapics[idx].mpc_type = MP_IOAPIC; + mp_ioapics[idx].mpc_flags = MPC_APIC_USABLE; + mp_ioapics[idx].mpc_apicaddr = address; + + mp_ioapics[idx].mpc_apicid = io_apic_get_unique_id(idx, id); + mp_ioapics[idx].mpc_apicver = io_apic_get_version(idx); + + /* + * Build basic GSI lookup table to facilitate gsi->io_apic lookups + * and to prevent reprogramming of IOAPIC pins (PCI GSIs). + */ + mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].mpc_apicid; + mp_ioapic_routing[idx].gsi_base = gsi_base; + mp_ioapic_routing[idx].gsi_end = gsi_base + + io_apic_get_redir_entries(idx); + + printk("IOAPIC[%d]: apic_id %d, version %d, address 0x%lx, " + "GSI %d-%d\n", idx, mp_ioapics[idx].mpc_apicid, + mp_ioapics[idx].mpc_apicver, mp_ioapics[idx].mpc_apicaddr, + mp_ioapic_routing[idx].gsi_base, + mp_ioapic_routing[idx].gsi_end); + + return; +} + + +void __init mp_override_legacy_irq ( + u8 bus_irq, + u8 polarity, + u8 trigger, + u32 gsi) +{ + struct mpc_config_intsrc intsrc; + int ioapic = -1; + int pin = -1; + + /* + * Convert 'gsi' to 'ioapic.pin'. + */ + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) + return; + pin = gsi - mp_ioapic_routing[ioapic].gsi_base; + + /* + * TBD: This check is for faulty timer entries, where the override + * erroneously sets the trigger to level, resulting in a HUGE + * increase of timer interrupts! + */ + if ((bus_irq == 0) && (trigger == 3)) + trigger = 1; + + intsrc.mpc_type = MP_INTSRC; + intsrc.mpc_irqtype = mp_INT; + intsrc.mpc_irqflag = (trigger << 2) | polarity; + intsrc.mpc_srcbus = MP_ISA_BUS; + intsrc.mpc_srcbusirq = bus_irq; /* IRQ */ + intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid; /* APIC ID */ + intsrc.mpc_dstirq = pin; /* INTIN# */ + + Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, %d-%d\n", + intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3, + (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus, + intsrc.mpc_srcbusirq, intsrc.mpc_dstapic, intsrc.mpc_dstirq); + + mp_irqs[mp_irq_entries] = intsrc; + if (++mp_irq_entries == MAX_IRQ_SOURCES) + panic("Max # of irq sources exceeded!\n"); + + return; +} + +int es7000_plat; + +void __init mp_config_acpi_legacy_irqs (void) +{ + struct mpc_config_intsrc intsrc; + int i = 0; + int ioapic = -1; + + /* + * Fabricate the legacy ISA bus (bus #31). + */ + mp_bus_id_to_type[MP_ISA_BUS] = MP_BUS_ISA; + Dprintk("Bus #%d is ISA\n", MP_ISA_BUS); + + /* + * Older generations of ES7000 have no legacy identity mappings + */ + if (es7000_plat == 1) + return; + + /* + * Locate the IOAPIC that manages the ISA IRQs (0-15). + */ + ioapic = mp_find_ioapic(0); + if (ioapic < 0) + return; + + intsrc.mpc_type = MP_INTSRC; + intsrc.mpc_irqflag = 0; /* Conforming */ + intsrc.mpc_srcbus = MP_ISA_BUS; + intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid; + + /* + * Use the default configuration for the IRQs 0-15. Unless + * overriden by (MADT) interrupt source override entries. + */ + for (i = 0; i < 16; i++) { + int idx; + + for (idx = 0; idx < mp_irq_entries; idx++) { + struct mpc_config_intsrc *irq = mp_irqs + idx; + + /* Do we already have a mapping for this ISA IRQ? */ + if (irq->mpc_srcbus == MP_ISA_BUS && irq->mpc_srcbusirq == i) + break; + + /* Do we already have a mapping for this IOAPIC pin */ + if ((irq->mpc_dstapic == intsrc.mpc_dstapic) && + (irq->mpc_dstirq == i)) + break; + } + + if (idx != mp_irq_entries) { + printk(KERN_DEBUG "ACPI: IRQ%d used by override.\n", i); + continue; /* IRQ already used */ + } + + intsrc.mpc_irqtype = mp_INT; + intsrc.mpc_srcbusirq = i; /* Identity mapped */ + intsrc.mpc_dstirq = i; + + Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, " + "%d-%d\n", intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3, + (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus, + intsrc.mpc_srcbusirq, intsrc.mpc_dstapic, + intsrc.mpc_dstirq); + + mp_irqs[mp_irq_entries] = intsrc; + if (++mp_irq_entries == MAX_IRQ_SOURCES) + panic("Max # of irq sources exceeded!\n"); + } +} + +int mp_register_gsi (u32 gsi, int edge_level, int active_high_low) +{ + int ioapic = -1; + int ioapic_pin = 0; + int idx, bit = 0; + +#ifdef CONFIG_ACPI_BUS + /* Don't set up the ACPI SCI because it's already set up */ + if (acpi_fadt.sci_int == gsi) + return gsi; +#endif + + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) { + printk(KERN_WARNING "No IOAPIC for GSI %u\n", gsi); + return gsi; + } + + ioapic_pin = gsi - mp_ioapic_routing[ioapic].gsi_base; + + if (ioapic_renumber_irq) + gsi = ioapic_renumber_irq(ioapic, gsi); + + /* + * Avoid pin reprogramming. PRTs typically include entries + * with redundant pin->gsi mappings (but unique PCI devices); + * we only program the IOAPIC on the first. + */ + bit = ioapic_pin % 32; + idx = (ioapic_pin < 32) ? 0 : (ioapic_pin / 32); + if (idx > 3) { + printk(KERN_ERR "Invalid reference to IOAPIC pin " + "%d-%d\n", mp_ioapic_routing[ioapic].apic_id, + ioapic_pin); + return gsi; + } + if ((1<<bit) & mp_ioapic_routing[ioapic].pin_programmed[idx]) { + Dprintk(KERN_DEBUG "Pin %d-%d already programmed\n", + mp_ioapic_routing[ioapic].apic_id, ioapic_pin); + return gsi; + } + + mp_ioapic_routing[ioapic].pin_programmed[idx] |= (1<<bit); + + io_apic_set_pci_routing(ioapic, ioapic_pin, gsi, + edge_level == ACPI_EDGE_SENSITIVE ? 0 : 1, + active_high_low == ACPI_ACTIVE_HIGH ? 0 : 1); + return gsi; +} + +#endif /*CONFIG_X86_IO_APIC && (CONFIG_ACPI_INTERPRETER || CONFIG_ACPI_BOOT)*/ +#endif /*CONFIG_ACPI_BOOT*/ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/pci-dma-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/pci-dma-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,319 @@ +/* + * Dynamic DMA mapping support. + * + * On i386 there is no hardware dynamic DMA address translation, + * so consistent alloc/free are merely page allocation/freeing. + * The rest of the dynamic DMA mapping interface is implemented + * in asm/pci.h. + */ + +#include <linux/types.h> +#include <linux/mm.h> +#include <linux/string.h> +#include <linux/pci.h> +#include <linux/version.h> +#include <asm/io.h> +#include <xen/balloon.h> +#include <asm/tlbflush.h> +#include <asm/swiotlb.h> + +struct dma_coherent_mem { + void *virt_base; + u32 device_base; + int size; + int flags; + unsigned long *bitmap; +}; + +#define IOMMU_BUG_ON(test) \ +do { \ + if (unlikely(test)) { \ + printk(KERN_ALERT "Fatal DMA error! " \ + "Please use 'swiotlb=force'\n"); \ + BUG(); \ + } \ +} while (0) + +int +dma_map_sg(struct device *hwdev, struct scatterlist *sg, int nents, + enum dma_data_direction direction) +{ + int i, rc; + + BUG_ON(direction == DMA_NONE); + + if (swiotlb) { + rc = swiotlb_map_sg(hwdev, sg, nents, direction); + } else { + for (i = 0; i < nents; i++ ) { + sg[i].dma_address = + page_to_phys(sg[i].page) + sg[i].offset; + sg[i].dma_length = sg[i].length; + BUG_ON(!sg[i].page); + IOMMU_BUG_ON(address_needs_mapping( + hwdev, sg[i].dma_address)); + } + rc = nents; + } + + flush_write_buffers(); + return rc; +} +EXPORT_SYMBOL(dma_map_sg); + +void +dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents, + enum dma_data_direction direction) +{ + BUG_ON(direction == DMA_NONE); + if (swiotlb) + swiotlb_unmap_sg(hwdev, sg, nents, direction); +} +EXPORT_SYMBOL(dma_unmap_sg); + +dma_addr_t +dma_map_page(struct device *dev, struct page *page, unsigned long offset, + size_t size, enum dma_data_direction direction) +{ + dma_addr_t dma_addr; + + BUG_ON(direction == DMA_NONE); + + if (swiotlb) { + dma_addr = swiotlb_map_page( + dev, page, offset, size, direction); + } else { + dma_addr = page_to_phys(page) + offset; + IOMMU_BUG_ON(address_needs_mapping(dev, dma_addr)); + } + + return dma_addr; +} +EXPORT_SYMBOL(dma_map_page); + +void +dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, + enum dma_data_direction direction) +{ + BUG_ON(direction == DMA_NONE); + if (swiotlb) + swiotlb_unmap_page(dev, dma_address, size, direction); +} +EXPORT_SYMBOL(dma_unmap_page); + +int +dma_mapping_error(dma_addr_t dma_addr) +{ + if (swiotlb) + return swiotlb_dma_mapping_error(dma_addr); + return 0; +} +EXPORT_SYMBOL(dma_mapping_error); + +int +dma_supported(struct device *dev, u64 mask) +{ + if (swiotlb) + return swiotlb_dma_supported(dev, mask); + /* + * By default we'll BUG when an infeasible DMA is requested, and + * request swiotlb=force (see IOMMU_BUG_ON). + */ + return 1; +} +EXPORT_SYMBOL(dma_supported); + +void *dma_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, unsigned int __nocast gfp) +{ + void *ret; + struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL; + unsigned int order = get_order(size); + unsigned long vstart; + /* ignore region specifiers */ + gfp &= ~(__GFP_DMA | __GFP_HIGHMEM); + + if (mem) { + int page = bitmap_find_free_region(mem->bitmap, mem->size, + order); + if (page >= 0) { + *dma_handle = mem->device_base + (page << PAGE_SHIFT); + ret = mem->virt_base + (page << PAGE_SHIFT); + memset(ret, 0, size); + return ret; + } + if (mem->flags & DMA_MEMORY_EXCLUSIVE) + return NULL; + } + + if (dev == NULL || (dev->coherent_dma_mask < 0xffffffff)) + gfp |= GFP_DMA; + + vstart = __get_free_pages(gfp, order); + ret = (void *)vstart; + + if (ret != NULL) { + /* NB. Hardcode 31 address bits for now: aacraid limitation. */ + if (xen_create_contiguous_region(vstart, order, 31) != 0) { + free_pages(vstart, order); + return NULL; + } + memset(ret, 0, size); + *dma_handle = virt_to_bus(ret); + } + return ret; +} +EXPORT_SYMBOL(dma_alloc_coherent); + +void dma_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle) +{ + struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL; + int order = get_order(size); + + if (mem && vaddr >= mem->virt_base && vaddr < (mem->virt_base + (mem->size << PAGE_SHIFT))) { + int page = (vaddr - mem->virt_base) >> PAGE_SHIFT; + + bitmap_release_region(mem->bitmap, page, order); + } else { + xen_destroy_contiguous_region((unsigned long)vaddr, order); + free_pages((unsigned long)vaddr, order); + } +} +EXPORT_SYMBOL(dma_free_coherent); + +int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, + dma_addr_t device_addr, size_t size, int flags) +{ + void __iomem *mem_base; + int pages = size >> PAGE_SHIFT; + int bitmap_size = (pages + 31)/32; + + if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0) + goto out; + if (!size) + goto out; + if (dev->dma_mem) + goto out; + + /* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */ + + mem_base = ioremap(bus_addr, size); + if (!mem_base) + goto out; + + dev->dma_mem = kmalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL); + if (!dev->dma_mem) + goto out; + memset(dev->dma_mem, 0, sizeof(struct dma_coherent_mem)); + dev->dma_mem->bitmap = kmalloc(bitmap_size, GFP_KERNEL); + if (!dev->dma_mem->bitmap) + goto free1_out; + memset(dev->dma_mem->bitmap, 0, bitmap_size); + + dev->dma_mem->virt_base = mem_base; + dev->dma_mem->device_base = device_addr; + dev->dma_mem->size = pages; + dev->dma_mem->flags = flags; + + if (flags & DMA_MEMORY_MAP) + return DMA_MEMORY_MAP; + + return DMA_MEMORY_IO; + + free1_out: + kfree(dev->dma_mem->bitmap); + out: + return 0; +} +EXPORT_SYMBOL(dma_declare_coherent_memory); + +void dma_release_declared_memory(struct device *dev) +{ + struct dma_coherent_mem *mem = dev->dma_mem; + + if(!mem) + return; + dev->dma_mem = NULL; + iounmap(mem->virt_base); + kfree(mem->bitmap); + kfree(mem); +} +EXPORT_SYMBOL(dma_release_declared_memory); + +void *dma_mark_declared_memory_occupied(struct device *dev, + dma_addr_t device_addr, size_t size) +{ + struct dma_coherent_mem *mem = dev->dma_mem; + int pages = (size + (device_addr & ~PAGE_MASK) + PAGE_SIZE - 1) >> PAGE_SHIFT; + int pos, err; + + if (!mem) + return ERR_PTR(-EINVAL); + + pos = (device_addr - mem->device_base) >> PAGE_SHIFT; + err = bitmap_allocate_region(mem->bitmap, pos, get_order(pages)); + if (err != 0) + return ERR_PTR(err); + return mem->virt_base + (pos << PAGE_SHIFT); +} +EXPORT_SYMBOL(dma_mark_declared_memory_occupied); + +dma_addr_t +dma_map_single(struct device *dev, void *ptr, size_t size, + enum dma_data_direction direction) +{ + dma_addr_t dma; + + BUG_ON(direction == DMA_NONE); + + if (swiotlb) { + dma = swiotlb_map_single(dev, ptr, size, direction); + } else { + dma = virt_to_bus(ptr); + IOMMU_BUG_ON(range_straddles_page_boundary(ptr, size)); + IOMMU_BUG_ON(address_needs_mapping(dev, dma)); + } + + flush_write_buffers(); + return dma; +} +EXPORT_SYMBOL(dma_map_single); + +void +dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size, + enum dma_data_direction direction) +{ + BUG_ON(direction == DMA_NONE); + if (swiotlb) + swiotlb_unmap_single(dev, dma_addr, size, direction); +} +EXPORT_SYMBOL(dma_unmap_single); + +void +dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, + enum dma_data_direction direction) +{ + if (swiotlb) + swiotlb_sync_single_for_cpu(dev, dma_handle, size, direction); +} +EXPORT_SYMBOL(dma_sync_single_for_cpu); + +void +dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size, + enum dma_data_direction direction) +{ + if (swiotlb) + swiotlb_sync_single_for_device(dev, dma_handle, size, direction); +} +EXPORT_SYMBOL(dma_sync_single_for_device); + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/process-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/process-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,770 @@ +/* + * linux/arch/i386/kernel/process.c + * + * Copyright (C) 1995 Linus Torvalds + * + * Pentium III FXSR, SSE support + * Gareth Hughes <gareth@xxxxxxxxxxx>, May 2000 + */ + +/* + * This file handles the architecture-dependent parts of process handling.. + */ + +#include <stdarg.h> + +#include <linux/cpu.h> +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/elfcore.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/stddef.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/user.h> +#include <linux/a.out.h> +#include <linux/interrupt.h> +#include <linux/config.h> +#include <linux/utsname.h> +#include <linux/delay.h> +#include <linux/reboot.h> +#include <linux/init.h> +#include <linux/mc146818rtc.h> +#include <linux/module.h> +#include <linux/kallsyms.h> +#include <linux/ptrace.h> +#include <linux/random.h> + +#include <asm/uaccess.h> +#include <asm/pgtable.h> +#include <asm/system.h> +#include <asm/io.h> +#include <asm/ldt.h> +#include <asm/processor.h> +#include <asm/i387.h> +#include <asm/irq.h> +#include <asm/desc.h> +#include <xen/interface/physdev.h> +#include <xen/interface/vcpu.h> +#ifdef CONFIG_MATH_EMULATION +#include <asm/math_emu.h> +#endif + +#include <linux/irq.h> +#include <linux/err.h> + +#include <asm/tlbflush.h> +#include <asm/cpu.h> + +asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); + +static int hlt_counter; + +unsigned long boot_option_idle_override = 0; +EXPORT_SYMBOL(boot_option_idle_override); + +/* + * Return saved PC of a blocked thread. + */ +unsigned long thread_saved_pc(struct task_struct *tsk) +{ + return ((unsigned long *)tsk->thread.esp)[3]; +} + +/* + * Powermanagement idle function, if any.. + */ +void (*pm_idle)(void); +static DEFINE_PER_CPU(unsigned int, cpu_idle_state); + +void disable_hlt(void) +{ + hlt_counter++; +} + +EXPORT_SYMBOL(disable_hlt); + +void enable_hlt(void) +{ + hlt_counter--; +} + +EXPORT_SYMBOL(enable_hlt); + +/* XXX XEN doesn't use default_idle(), poll_idle(). Use xen_idle() instead. */ +extern void stop_hz_timer(void); +extern void start_hz_timer(void); +void xen_idle(void) +{ + local_irq_disable(); + + if (need_resched()) { + local_irq_enable(); + } else { + stop_hz_timer(); + /* Blocking includes an implicit local_irq_enable(). */ + HYPERVISOR_sched_op(SCHEDOP_block, 0); + start_hz_timer(); + } +} + +/* + * The idle thread. There's no useful work to be + * done, so just try to conserve power and have a + * low exit latency (ie sit in a loop waiting for + * somebody to say that they'd like to reschedule) + */ +void cpu_idle (void) +{ +#if defined(CONFIG_HOTPLUG_CPU) + int cpu = _smp_processor_id(); +#endif + + /* endless idle loop with no priority at all */ + while (1) { + while (!need_resched()) { + + if (__get_cpu_var(cpu_idle_state)) + __get_cpu_var(cpu_idle_state) = 0; + rmb(); + +#if defined(CONFIG_HOTPLUG_CPU) + if (cpu_is_offline(cpu)) { + HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL); + local_irq_enable(); + } +#endif + + __get_cpu_var(irq_stat).idle_timestamp = jiffies; + xen_idle(); + } + schedule(); + } +} + +void cpu_idle_wait(void) +{ + unsigned int cpu, this_cpu = get_cpu(); + cpumask_t map; + + set_cpus_allowed(current, cpumask_of_cpu(this_cpu)); + put_cpu(); + + cpus_clear(map); + for_each_online_cpu(cpu) { + per_cpu(cpu_idle_state, cpu) = 1; + cpu_set(cpu, map); + } + + __get_cpu_var(cpu_idle_state) = 0; + + wmb(); + do { + ssleep(1); + for_each_online_cpu(cpu) { + if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu)) + cpu_clear(cpu, map); + } + cpus_and(map, map, cpu_online_map); + } while (!cpus_empty(map)); +} +EXPORT_SYMBOL_GPL(cpu_idle_wait); + +/* XXX XEN doesn't use mwait_idle(), select_idle_routine(), idle_setup(). */ +/* Always use xen_idle() instead. */ +void __init select_idle_routine(const struct cpuinfo_x86 *c) {} + +void show_regs(struct pt_regs * regs) +{ + printk("\n"); + printk("Pid: %d, comm: %20s\n", current->pid, current->comm); + printk("EIP: %04x:[<%08lx>] CPU: %d\n",0xffff & regs->xcs,regs->eip, smp_processor_id()); + print_symbol("EIP is at %s\n", regs->eip); + + if (regs->xcs & 2) + printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp); + printk(" EFLAGS: %08lx %s (%s)\n", + regs->eflags, print_tainted(), system_utsname.release); + printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n", + regs->eax,regs->ebx,regs->ecx,regs->edx); + printk("ESI: %08lx EDI: %08lx EBP: %08lx", + regs->esi, regs->edi, regs->ebp); + printk(" DS: %04x ES: %04x\n", + 0xffff & regs->xds,0xffff & regs->xes); + + show_trace(NULL, &regs->esp); +} + +/* + * This gets run with %ebx containing the + * function to call, and %edx containing + * the "args". + */ +extern void kernel_thread_helper(void); +__asm__(".section .text\n" + ".align 4\n" + "kernel_thread_helper:\n\t" + "movl %edx,%eax\n\t" + "pushl %edx\n\t" + "call *%ebx\n\t" + "pushl %eax\n\t" + "call do_exit\n" + ".previous"); + +/* + * Create a kernel thread + */ +int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) +{ + struct pt_regs regs; + + memset(&regs, 0, sizeof(regs)); + + regs.ebx = (unsigned long) fn; + regs.edx = (unsigned long) arg; + + regs.xds = __USER_DS; + regs.xes = __USER_DS; + regs.orig_eax = -1; + regs.eip = (unsigned long) kernel_thread_helper; + regs.xcs = __KERNEL_CS; + regs.eflags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2; + + /* Ok, create the new process.. */ + return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs, 0, NULL, NULL); +} + +/* + * Free current thread data structures etc.. + */ +void exit_thread(void) +{ + struct task_struct *tsk = current; + struct thread_struct *t = &tsk->thread; + + /* The process may have allocated an io port bitmap... nuke it. */ + if (unlikely(NULL != t->io_bitmap_ptr)) { + physdev_op_t op = { 0 }; + op.cmd = PHYSDEVOP_SET_IOBITMAP; + HYPERVISOR_physdev_op(&op); + kfree(t->io_bitmap_ptr); + t->io_bitmap_ptr = NULL; + } +} + +void flush_thread(void) +{ + struct task_struct *tsk = current; + + memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8); + memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); + /* + * Forget coprocessor state.. + */ + clear_fpu(tsk); + clear_used_math(); +} + +void release_thread(struct task_struct *dead_task) +{ + if (dead_task->mm) { + // temporary debugging check + if (dead_task->mm->context.size) { + printk("WARNING: dead process %8s still has LDT? <%p/%d>\n", + dead_task->comm, + dead_task->mm->context.ldt, + dead_task->mm->context.size); + BUG(); + } + } + + release_vm86_irqs(dead_task); +} + +/* + * This gets called before we allocate a new thread and copy + * the current task into it. + */ +void prepare_to_copy(struct task_struct *tsk) +{ + unlazy_fpu(tsk); +} + +int copy_thread(int nr, unsigned long clone_flags, unsigned long esp, + unsigned long unused, + struct task_struct * p, struct pt_regs * regs) +{ + struct pt_regs * childregs; + struct task_struct *tsk; + int err; + + childregs = ((struct pt_regs *) (THREAD_SIZE + (unsigned long) p->thread_info)) - 1; + /* + * The below -8 is to reserve 8 bytes on top of the ring0 stack. + * This is necessary to guarantee that the entire "struct pt_regs" + * is accessable even if the CPU haven't stored the SS/ESP registers + * on the stack (interrupt gate does not save these registers + * when switching to the same priv ring). + * Therefore beware: accessing the xss/esp fields of the + * "struct pt_regs" is possible, but they may contain the + * completely wrong values. + */ + childregs = (struct pt_regs *) ((unsigned long) childregs - 8); + *childregs = *regs; + childregs->eax = 0; + childregs->esp = esp; + + p->thread.esp = (unsigned long) childregs; + p->thread.esp0 = (unsigned long) (childregs+1); + + p->thread.eip = (unsigned long) ret_from_fork; + + savesegment(fs,p->thread.fs); + savesegment(gs,p->thread.gs); + + tsk = current; + if (unlikely(NULL != tsk->thread.io_bitmap_ptr)) { + p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL); + if (!p->thread.io_bitmap_ptr) { + p->thread.io_bitmap_max = 0; + return -ENOMEM; + } + memcpy(p->thread.io_bitmap_ptr, tsk->thread.io_bitmap_ptr, + IO_BITMAP_BYTES); + } + + /* + * Set a new TLS for the child thread? + */ + if (clone_flags & CLONE_SETTLS) { + struct desc_struct *desc; + struct user_desc info; + int idx; + + err = -EFAULT; + if (copy_from_user(&info, (void __user *)childregs->esi, sizeof(info))) + goto out; + err = -EINVAL; + if (LDT_empty(&info)) + goto out; + + idx = info.entry_number; + if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX) + goto out; + + desc = p->thread.tls_array + idx - GDT_ENTRY_TLS_MIN; + desc->a = LDT_entry_a(&info); + desc->b = LDT_entry_b(&info); + } + + p->thread.io_pl = current->thread.io_pl; + + err = 0; + out: + if (err && p->thread.io_bitmap_ptr) { + kfree(p->thread.io_bitmap_ptr); + p->thread.io_bitmap_max = 0; + } + return err; +} + +/* + * fill in the user structure for a core dump.. + */ +void dump_thread(struct pt_regs * regs, struct user * dump) +{ + int i; + +/* changed the size calculations - should hopefully work better. lbt */ + dump->magic = CMAGIC; + dump->start_code = 0; + dump->start_stack = regs->esp & ~(PAGE_SIZE - 1); + dump->u_tsize = ((unsigned long) current->mm->end_code) >> PAGE_SHIFT; + dump->u_dsize = ((unsigned long) (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT; + dump->u_dsize -= dump->u_tsize; + dump->u_ssize = 0; + for (i = 0; i < 8; i++) + dump->u_debugreg[i] = current->thread.debugreg[i]; + + if (dump->start_stack < TASK_SIZE) + dump->u_ssize = ((unsigned long) (TASK_SIZE - dump->start_stack)) >> PAGE_SHIFT; + + dump->regs.ebx = regs->ebx; + dump->regs.ecx = regs->ecx; + dump->regs.edx = regs->edx; + dump->regs.esi = regs->esi; + dump->regs.edi = regs->edi; + dump->regs.ebp = regs->ebp; + dump->regs.eax = regs->eax; + dump->regs.ds = regs->xds; + dump->regs.es = regs->xes; + savesegment(fs,dump->regs.fs); + savesegment(gs,dump->regs.gs); + dump->regs.orig_eax = regs->orig_eax; + dump->regs.eip = regs->eip; + dump->regs.cs = regs->xcs; + dump->regs.eflags = regs->eflags; + dump->regs.esp = regs->esp; + dump->regs.ss = regs->xss; + + dump->u_fpvalid = dump_fpu (regs, &dump->i387); +} + +/* + * Capture the user space registers if the task is not running (in user space) + */ +int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs) +{ + struct pt_regs ptregs; + + ptregs = *(struct pt_regs *) + ((unsigned long)tsk->thread_info+THREAD_SIZE - sizeof(ptregs)); + ptregs.xcs &= 0xffff; + ptregs.xds &= 0xffff; + ptregs.xes &= 0xffff; + ptregs.xss &= 0xffff; + + elf_core_copy_regs(regs, &ptregs); + + boot_option_idle_override = 1; + return 1; +} + +/* + * switch_to(x,yn) should switch tasks from x to y. + * + * We fsave/fwait so that an exception goes off at the right time + * (as a call from the fsave or fwait in effect) rather than to + * the wrong process. Lazy FP saving no longer makes any sense + * with modern CPU's, and this simplifies a lot of things (SMP + * and UP become the same). + * + * NOTE! We used to use the x86 hardware context switching. The + * reason for not using it any more becomes apparent when you + * try to recover gracefully from saved state that is no longer + * valid (stale segment register values in particular). With the + * hardware task-switch, there is no way to fix up bad state in + * a reasonable manner. + * + * The fact that Intel documents the hardware task-switching to + * be slow is a fairly red herring - this code is not noticeably + * faster. However, there _is_ some room for improvement here, + * so the performance issues may eventually be a valid point. + * More important, however, is the fact that this allows us much + * more flexibility. + * + * The return value (in %eax) will be the "prev" task after + * the task-switch, and shows up in ret_from_fork in entry.S, + * for example. + */ +struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct task_struct *next_p) +{ + struct thread_struct *prev = &prev_p->thread, + *next = &next_p->thread; + int cpu = smp_processor_id(); + struct tss_struct *tss = &per_cpu(init_tss, cpu); + physdev_op_t iopl_op, iobmp_op; + multicall_entry_t _mcl[8], *mcl = _mcl; + + /* XEN NOTE: FS/GS saved in switch_mm(), not here. */ + + /* + * This is basically '__unlazy_fpu', except that we queue a + * multicall to indicate FPU task switch, rather than + * synchronously trapping to Xen. + */ + if (prev_p->thread_info->status & TS_USEDFPU) { + __save_init_fpu(prev_p); /* _not_ save_init_fpu() */ + mcl->op = __HYPERVISOR_fpu_taskswitch; + mcl->args[0] = 1; + mcl++; + } +#if 0 /* lazy fpu sanity check */ + else BUG_ON(!(read_cr0() & 8)); +#endif + + /* + * Reload esp0, LDT and the page table pointer: + * This is load_esp0(tss, next) with a multicall. + */ + tss->esp0 = next->esp0; + mcl->op = __HYPERVISOR_stack_switch; + mcl->args[0] = tss->ss0; + mcl->args[1] = tss->esp0; + mcl++; + + /* + * Load the per-thread Thread-Local Storage descriptor. + * This is load_TLS(next, cpu) with multicalls. + */ +#define C(i) do { \ + if (unlikely(next->tls_array[i].a != prev->tls_array[i].a || \ + next->tls_array[i].b != prev->tls_array[i].b)) { \ + mcl->op = __HYPERVISOR_update_descriptor; \ + *(u64 *)&mcl->args[0] = virt_to_machine( \ + &get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN + i]);\ + *(u64 *)&mcl->args[2] = *(u64 *)&next->tls_array[i]; \ + mcl++; \ + } \ +} while (0) + C(0); C(1); C(2); +#undef C + + if (unlikely(prev->io_pl != next->io_pl)) { + iopl_op.cmd = PHYSDEVOP_SET_IOPL; + iopl_op.u.set_iopl.iopl = (next->io_pl == 0) ? 1 : next->io_pl; + mcl->op = __HYPERVISOR_physdev_op; + mcl->args[0] = (unsigned long)&iopl_op; + mcl++; + } + + if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr)) { + iobmp_op.cmd = + PHYSDEVOP_SET_IOBITMAP; + iobmp_op.u.set_iobitmap.bitmap = + (char *)next->io_bitmap_ptr; + iobmp_op.u.set_iobitmap.nr_ports = + next->io_bitmap_ptr ? IO_BITMAP_BITS : 0; + mcl->op = __HYPERVISOR_physdev_op; + mcl->args[0] = (unsigned long)&iobmp_op; + mcl++; + } + + (void)HYPERVISOR_multicall(_mcl, mcl - _mcl); + + /* + * Restore %fs and %gs if needed. + */ + if (unlikely(next->fs | next->gs)) { + loadsegment(fs, next->fs); + loadsegment(gs, next->gs); + } + + /* + * Now maybe reload the debug registers + */ + if (unlikely(next->debugreg[7])) { + loaddebug(next, 0); + loaddebug(next, 1); + loaddebug(next, 2); + loaddebug(next, 3); + /* no 4 and 5 */ + loaddebug(next, 6); + loaddebug(next, 7); + } + + return prev_p; +} + +asmlinkage int sys_fork(struct pt_regs regs) +{ + return do_fork(SIGCHLD, regs.esp, &regs, 0, NULL, NULL); +} + +asmlinkage int sys_clone(struct pt_regs regs) +{ + unsigned long clone_flags; + unsigned long newsp; + int __user *parent_tidptr, *child_tidptr; + + clone_flags = regs.ebx; + newsp = regs.ecx; + parent_tidptr = (int __user *)regs.edx; + child_tidptr = (int __user *)regs.edi; + if (!newsp) + newsp = regs.esp; + return do_fork(clone_flags, newsp, &regs, 0, parent_tidptr, child_tidptr); +} + +/* + * This is trivial, and on the face of it looks like it + * could equally well be done in user mode. + * + * Not so, for quite unobvious reasons - register pressure. + * In user mode vfork() cannot have a stack frame, and if + * done by calling the "clone()" system call directly, you + * do not have enough call-clobbered registers to hold all + * the information you need. + */ +asmlinkage int sys_vfork(struct pt_regs regs) +{ + return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs.esp, &regs, 0, NULL, NULL); +} + +/* + * sys_execve() executes a new program. + */ +asmlinkage int sys_execve(struct pt_regs regs) +{ + int error; + char * filename; + + filename = getname((char __user *) regs.ebx); + error = PTR_ERR(filename); + if (IS_ERR(filename)) + goto out; + error = do_execve(filename, + (char __user * __user *) regs.ecx, + (char __user * __user *) regs.edx, + &regs); + if (error == 0) { + task_lock(current); + current->ptrace &= ~PT_DTRACE; + task_unlock(current); + /* Make sure we don't return using sysenter.. */ + set_thread_flag(TIF_IRET); + } + putname(filename); +out: + return error; +} + +#define top_esp (THREAD_SIZE - sizeof(unsigned long)) +#define top_ebp (THREAD_SIZE - 2*sizeof(unsigned long)) + +unsigned long get_wchan(struct task_struct *p) +{ + unsigned long ebp, esp, eip; + unsigned long stack_page; + int count = 0; + if (!p || p == current || p->state == TASK_RUNNING) + return 0; + stack_page = (unsigned long)p->thread_info; + esp = p->thread.esp; + if (!stack_page || esp < stack_page || esp > top_esp+stack_page) + return 0; + /* include/asm-i386/system.h:switch_to() pushes ebp last. */ + ebp = *(unsigned long *) esp; + do { + if (ebp < stack_page || ebp > top_ebp+stack_page) + return 0; + eip = *(unsigned long *) (ebp+4); + if (!in_sched_functions(eip)) + return eip; + ebp = *(unsigned long *) ebp; + } while (count++ < 16); + return 0; +} + +/* + * sys_alloc_thread_area: get a yet unused TLS descriptor index. + */ +static int get_free_idx(void) +{ + struct thread_struct *t = &current->thread; + int idx; + + for (idx = 0; idx < GDT_ENTRY_TLS_ENTRIES; idx++) + if (desc_empty(t->tls_array + idx)) + return idx + GDT_ENTRY_TLS_MIN; + return -ESRCH; +} + +/* + * Set a given TLS descriptor: + */ +asmlinkage int sys_set_thread_area(struct user_desc __user *u_info) +{ + struct thread_struct *t = &current->thread; + struct user_desc info; + struct desc_struct *desc; + int cpu, idx; + + if (copy_from_user(&info, u_info, sizeof(info))) + return -EFAULT; + idx = info.entry_number; + + /* + * index -1 means the kernel should try to find and + * allocate an empty descriptor: + */ + if (idx == -1) { + idx = get_free_idx(); + if (idx < 0) + return idx; + if (put_user(idx, &u_info->entry_number)) + return -EFAULT; + } + + if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX) + return -EINVAL; + + desc = t->tls_array + idx - GDT_ENTRY_TLS_MIN; + + /* + * We must not get preempted while modifying the TLS. + */ + cpu = get_cpu(); + + if (LDT_empty(&info)) { + desc->a = 0; + desc->b = 0; + } else { + desc->a = LDT_entry_a(&info); + desc->b = LDT_entry_b(&info); + } + load_TLS(t, cpu); + + put_cpu(); + + return 0; +} + +/* + * Get the current Thread-Local Storage area: + */ + +#define GET_BASE(desc) ( \ + (((desc)->a >> 16) & 0x0000ffff) | \ + (((desc)->b << 16) & 0x00ff0000) | \ + ( (desc)->b & 0xff000000) ) + +#define GET_LIMIT(desc) ( \ + ((desc)->a & 0x0ffff) | \ + ((desc)->b & 0xf0000) ) + +#define GET_32BIT(desc) (((desc)->b >> 22) & 1) +#define GET_CONTENTS(desc) (((desc)->b >> 10) & 3) +#define GET_WRITABLE(desc) (((desc)->b >> 9) & 1) +#define GET_LIMIT_PAGES(desc) (((desc)->b >> 23) & 1) +#define GET_PRESENT(desc) (((desc)->b >> 15) & 1) +#define GET_USEABLE(desc) (((desc)->b >> 20) & 1) + +asmlinkage int sys_get_thread_area(struct user_desc __user *u_info) +{ + struct user_desc info; + struct desc_struct *desc; + int idx; + + if (get_user(idx, &u_info->entry_number)) + return -EFAULT; + if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX) + return -EINVAL; + + desc = current->thread.tls_array + idx - GDT_ENTRY_TLS_MIN; + + info.entry_number = idx; + info.base_addr = GET_BASE(desc); + info.limit = GET_LIMIT(desc); + info.seg_32bit = GET_32BIT(desc); + info.contents = GET_CONTENTS(desc); + info.read_exec_only = !GET_WRITABLE(desc); + info.limit_in_pages = GET_LIMIT_PAGES(desc); + info.seg_not_present = !GET_PRESENT(desc); + info.useable = GET_USEABLE(desc); + + if (copy_to_user(u_info, &info, sizeof(info))) + return -EFAULT; + return 0; +} + +unsigned long arch_align_stack(unsigned long sp) +{ + if (randomize_va_space) + sp -= get_random_int() % 8192; + return sp & ~0xf; +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/quirks-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/quirks-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,49 @@ +/* + * This file contains work-arounds for x86 and x86_64 platform bugs. + */ +#include <linux/config.h> +#include <linux/pci.h> +#include <linux/irq.h> + +#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_SMP) && defined(CONFIG_PCI) + +static void __devinit quirk_intel_irqbalance(struct pci_dev *dev) +{ + u8 config, rev; + u32 word; + + /* BIOS may enable hardware IRQ balancing for + * E7520/E7320/E7525(revision ID 0x9 and below) + * based platforms. + * Disable SW irqbalance/affinity on those platforms. + */ + pci_read_config_byte(dev, PCI_CLASS_REVISION, &rev); + if (rev > 0x9) + return; + + printk(KERN_INFO "Intel E7520/7320/7525 detected."); + + /* enable access to config space*/ + pci_read_config_byte(dev, 0xf4, &config); + config |= 0x2; + pci_write_config_byte(dev, 0xf4, config); + + /* read xTPR register */ + raw_pci_ops->read(0, 0, 0x40, 0x4c, 2, &word); + + if (!(word & (1 << 13))) { + dom0_op_t op; + printk(KERN_INFO "Disabling irq balancing and affinity\n"); + op.cmd = DOM0_PLATFORM_QUIRK; + op.u.platform_quirk.quirk_id = QUIRK_NOIRQBALANCING; + (void)HYPERVISOR_dom0_op(&op); + } + + config &= ~0x2; + /* disable access to config space*/ + pci_write_config_byte(dev, 0xf4, config); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7320_MCH, quirk_intel_irqbalance); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7525_MCH, quirk_intel_irqbalance); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7520_MCH, quirk_intel_irqbalance); +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/setup-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/setup-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,1790 @@ +/* + * linux/arch/i386/kernel/setup.c + * + * Copyright (C) 1995 Linus Torvalds + * + * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 + * + * Memory region support + * David Parsons <orc@xxxxxxxxxxxxxx>, July-August 1999 + * + * Added E820 sanitization routine (removes overlapping memory regions); + * Brian Moyle <bmoyle@xxxxxxxxxx>, February 2001 + * + * Moved CPU detection code to cpu/${cpu}.c + * Patrick Mochel <mochel@xxxxxxxx>, March 2002 + * + * Provisions for empty E820 memory regions (reported by certain BIOSes). + * Alex Achenbach <xela@xxxxxxx>, December 2002. + * + */ + +/* + * This file handles the architecture-dependent parts of initialization + */ + +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/tty.h> +#include <linux/ioport.h> +#include <linux/acpi.h> +#include <linux/apm_bios.h> +#include <linux/initrd.h> +#include <linux/bootmem.h> +#include <linux/seq_file.h> +#include <linux/console.h> +#include <linux/mca.h> +#include <linux/root_dev.h> +#include <linux/highmem.h> +#include <linux/module.h> +#include <linux/efi.h> +#include <linux/init.h> +#include <linux/edd.h> +#include <linux/nodemask.h> +#include <linux/kernel.h> +#include <linux/percpu.h> +#include <linux/notifier.h> +#include <video/edid.h> +#include <asm/e820.h> +#include <asm/mpspec.h> +#include <asm/setup.h> +#include <asm/arch_hooks.h> +#include <asm/sections.h> +#include <asm/io_apic.h> +#include <asm/ist.h> +#include <asm/io.h> +#include <asm/hypervisor.h> +#include <xen/interface/physdev.h> +#include <xen/interface/memory.h> +#include <xen/features.h> +#include "setup_arch_pre.h" +#include <bios_ebda.h> + +/* Allows setting of maximum possible memory size */ +static unsigned long xen_override_max_pfn; + +static int xen_panic_event(struct notifier_block *, unsigned long, void *); +static struct notifier_block xen_panic_block = { + xen_panic_event, NULL, 0 /* try to go last */ +}; + +extern char hypercall_page[PAGE_SIZE]; +EXPORT_SYMBOL(hypercall_page); + +int disable_pse __initdata = 0; + +/* + * Machine setup.. + */ + +#ifdef CONFIG_EFI +int efi_enabled = 0; +EXPORT_SYMBOL(efi_enabled); +#endif + +/* cpu data as detected by the assembly code in head.S */ +struct cpuinfo_x86 new_cpu_data __initdata = { 0, 0, 0, 0, -1, 0, 1, 0, -1 }; +/* common cpu data for all cpus */ +struct cpuinfo_x86 boot_cpu_data = { 0, 0, 0, 0, -1, 0, 1, 0, -1 }; + +unsigned long mmu_cr4_features; + +#ifdef CONFIG_ACPI_INTERPRETER + int acpi_disabled = 0; +#else + int acpi_disabled = 1; +#endif +EXPORT_SYMBOL(acpi_disabled); + +#ifdef CONFIG_ACPI_BOOT +int __initdata acpi_force = 0; +extern acpi_interrupt_flags acpi_sci_flags; +#endif + +/* for MCA, but anyone else can use it if they want */ +unsigned int machine_id; +unsigned int machine_submodel_id; +unsigned int BIOS_revision; +unsigned int mca_pentium_flag; + +/* For PCI or other memory-mapped resources */ +unsigned long pci_mem_start = 0x10000000; + +/* Boot loader ID as an integer, for the benefit of proc_dointvec */ +int bootloader_type; + +/* user-defined highmem size */ +static unsigned int highmem_pages = -1; + +/* + * Setup options + */ +struct drive_info_struct { char dummy[32]; } drive_info; +struct screen_info screen_info; +struct apm_info apm_info; +struct sys_desc_table_struct { + unsigned short length; + unsigned char table[0]; +}; +struct edid_info edid_info; +struct ist_info ist_info; +struct e820map e820; + +extern void early_cpu_init(void); +extern void dmi_scan_machine(void); +extern void generic_apic_probe(char *); +extern int root_mountflags; + +unsigned long saved_videomode; + +#define RAMDISK_IMAGE_START_MASK 0x07FF +#define RAMDISK_PROMPT_FLAG 0x8000 +#define RAMDISK_LOAD_FLAG 0x4000 + +static char command_line[COMMAND_LINE_SIZE]; + +unsigned char __initdata boot_params[PARAM_SIZE]; + +static struct resource data_resource = { + .name = "Kernel data", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_MEM +}; + +static struct resource code_resource = { + .name = "Kernel code", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_MEM +}; + +#ifdef CONFIG_XEN_PRIVILEGED_GUEST +static struct resource system_rom_resource = { + .name = "System ROM", + .start = 0xf0000, + .end = 0xfffff, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +}; + +static struct resource extension_rom_resource = { + .name = "Extension ROM", + .start = 0xe0000, + .end = 0xeffff, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +}; + +static struct resource adapter_rom_resources[] = { { + .name = "Adapter ROM", + .start = 0xc8000, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +}, { + .name = "Adapter ROM", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +}, { + .name = "Adapter ROM", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +}, { + .name = "Adapter ROM", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +}, { + .name = "Adapter ROM", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +}, { + .name = "Adapter ROM", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +} }; + +#define ADAPTER_ROM_RESOURCES \ + (sizeof adapter_rom_resources / sizeof adapter_rom_resources[0]) + +static struct resource video_rom_resource = { + .name = "Video ROM", + .start = 0xc0000, + .end = 0xc7fff, + .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM +}; +#endif + +static struct resource video_ram_resource = { + .name = "Video RAM area", + .start = 0xa0000, + .end = 0xbffff, + .flags = IORESOURCE_BUSY | IORESOURCE_MEM +}; + +static struct resource standard_io_resources[] = { { + .name = "dma1", + .start = 0x0000, + .end = 0x001f, + .flags = IORESOURCE_BUSY | IORESOURCE_IO +}, { + .name = "pic1", + .start = 0x0020, + .end = 0x0021, + .flags = IORESOURCE_BUSY | IORESOURCE_IO +}, { + .name = "timer0", + .start = 0x0040, + .end = 0x0043, + .flags = IORESOURCE_BUSY | IORESOURCE_IO +}, { + .name = "timer1", + .start = 0x0050, + .end = 0x0053, + .flags = IORESOURCE_BUSY | IORESOURCE_IO +}, { + .name = "keyboard", + .start = 0x0060, + .end = 0x006f, + .flags = IORESOURCE_BUSY | IORESOURCE_IO +}, { + .name = "dma page reg", + .start = 0x0080, + .end = 0x008f, + .flags = IORESOURCE_BUSY | IORESOURCE_IO +}, { + .name = "pic2", + .start = 0x00a0, + .end = 0x00a1, + .flags = IORESOURCE_BUSY | IORESOURCE_IO +}, { + .name = "dma2", + .start = 0x00c0, + .end = 0x00df, + .flags = IORESOURCE_BUSY | IORESOURCE_IO +}, { + .name = "fpu", + .start = 0x00f0, + .end = 0x00ff, + .flags = IORESOURCE_BUSY | IORESOURCE_IO +} }; + +#define STANDARD_IO_RESOURCES \ + (sizeof standard_io_resources / sizeof standard_io_resources[0]) + +#ifdef CONFIG_XEN_PRIVILEGED_GUEST +#define romsignature(x) (*(unsigned short *)(x) == 0xaa55) + +static int __init romchecksum(unsigned char *rom, unsigned long length) +{ + unsigned char *p, sum = 0; + + for (p = rom; p < rom + length; p++) + sum += *p; + return sum == 0; +} + +static void __init probe_roms(void) +{ + unsigned long start, length, upper; + unsigned char *rom; + int i; + + /* Nothing to do if not running in dom0. */ + if (!(xen_start_info->flags & SIF_INITDOMAIN)) + return; + + /* video rom */ + upper = adapter_rom_resources[0].start; + for (start = video_rom_resource.start; start < upper; start += 2048) { + rom = isa_bus_to_virt(start); + if (!romsignature(rom)) + continue; + + video_rom_resource.start = start; + + /* 0 < length <= 0x7f * 512, historically */ + length = rom[2] * 512; + + /* if checksum okay, trust length byte */ + if (length && romchecksum(rom, length)) + video_rom_resource.end = start + length - 1; + + request_resource(&iomem_resource, &video_rom_resource); + break; + } + + start = (video_rom_resource.end + 1 + 2047) & ~2047UL; + if (start < upper) + start = upper; + + /* system rom */ + request_resource(&iomem_resource, &system_rom_resource); + upper = system_rom_resource.start; + + /* check for extension rom (ignore length byte!) */ + rom = isa_bus_to_virt(extension_rom_resource.start); + if (romsignature(rom)) { + length = extension_rom_resource.end - extension_rom_resource.start + 1; + if (romchecksum(rom, length)) { + request_resource(&iomem_resource, &extension_rom_resource); + upper = extension_rom_resource.start; + } + } + + /* check for adapter roms on 2k boundaries */ + for (i = 0; i < ADAPTER_ROM_RESOURCES && start < upper; start += 2048) { + rom = isa_bus_to_virt(start); + if (!romsignature(rom)) + continue; + + /* 0 < length <= 0x7f * 512, historically */ + length = rom[2] * 512; + + /* but accept any length that fits if checksum okay */ + if (!length || start + length > upper || !romchecksum(rom, length)) + continue; + + adapter_rom_resources[i].start = start; + adapter_rom_resources[i].end = start + length - 1; + request_resource(&iomem_resource, &adapter_rom_resources[i]); + + start = adapter_rom_resources[i++].end & ~2047UL; + } +} +#endif + +/* + * Point at the empty zero page to start with. We map the real shared_info + * page as soon as fixmap is up and running. + */ +shared_info_t *HYPERVISOR_shared_info = (shared_info_t *)empty_zero_page; +EXPORT_SYMBOL(HYPERVISOR_shared_info); + +unsigned long *phys_to_machine_mapping; +unsigned long *pfn_to_mfn_frame_list_list, *pfn_to_mfn_frame_list[16]; +EXPORT_SYMBOL(phys_to_machine_mapping); + +/* Raw start-of-day parameters from the hypervisor. */ +start_info_t *xen_start_info; +EXPORT_SYMBOL(xen_start_info); + +static void __init limit_regions(unsigned long long size) +{ + unsigned long long current_addr = 0; + int i; + + if (efi_enabled) { + for (i = 0; i < memmap.nr_map; i++) { + current_addr = memmap.map[i].phys_addr + + (memmap.map[i].num_pages << 12); + if (memmap.map[i].type == EFI_CONVENTIONAL_MEMORY) { + if (current_addr >= size) { + memmap.map[i].num_pages -= + (((current_addr-size) + PAGE_SIZE-1) >> PAGE_SHIFT); + memmap.nr_map = i + 1; + return; + } + } + } + } + for (i = 0; i < e820.nr_map; i++) { + if (e820.map[i].type == E820_RAM) { + current_addr = e820.map[i].addr + e820.map[i].size; + if (current_addr >= size) { + e820.map[i].size -= current_addr-size; + e820.nr_map = i + 1; + return; + } + } + } +} + +static void __init add_memory_region(unsigned long long start, + unsigned long long size, int type) +{ + int x; + + if (!efi_enabled) { + x = e820.nr_map; + + if (x == E820MAX) { + printk(KERN_ERR "Ooops! Too many entries in the memory map!\n"); + return; + } + + e820.map[x].addr = start; + e820.map[x].size = size; + e820.map[x].type = type; + e820.nr_map++; + } +} /* add_memory_region */ + +#define E820_DEBUG 1 + +static void __init print_memory_map(char *who) +{ + int i; + + for (i = 0; i < e820.nr_map; i++) { + printk(" %s: %016Lx - %016Lx ", who, + e820.map[i].addr, + e820.map[i].addr + e820.map[i].size); + switch (e820.map[i].type) { + case E820_RAM: printk("(usable)\n"); + break; + case E820_RESERVED: + printk("(reserved)\n"); + break; + case E820_ACPI: + printk("(ACPI data)\n"); + break; + case E820_NVS: + printk("(ACPI NVS)\n"); + break; + default: printk("type %lu\n", e820.map[i].type); + break; + } + } +} + +#if 0 +/* + * Sanitize the BIOS e820 map. + * + * Some e820 responses include overlapping entries. The following + * replaces the original e820 map with a new one, removing overlaps. + * + */ +struct change_member { + struct e820entry *pbios; /* pointer to original bios entry */ + unsigned long long addr; /* address for this change point */ +}; +static struct change_member change_point_list[2*E820MAX] __initdata; +static struct change_member *change_point[2*E820MAX] __initdata; +static struct e820entry *overlap_list[E820MAX] __initdata; +static struct e820entry new_bios[E820MAX] __initdata; + +static int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map) +{ + struct change_member *change_tmp; + unsigned long current_type, last_type; + unsigned long long last_addr; + int chgidx, still_changing; + int overlap_entries; + int new_bios_entry; + int old_nr, new_nr, chg_nr; + int i; + + /* + Visually we're performing the following (1,2,3,4 = memory types)... + + Sample memory map (w/overlaps): + ____22__________________ + ______________________4_ + ____1111________________ + _44_____________________ + 11111111________________ + ____________________33__ + ___________44___________ + __________33333_________ + ______________22________ + ___________________2222_ + _________111111111______ + _____________________11_ + _________________4______ + + Sanitized equivalent (no overlap): + 1_______________________ + _44_____________________ + ___1____________________ + ____22__________________ + ______11________________ + _________1______________ + __________3_____________ + ___________44___________ + _____________33_________ + _______________2________ + ________________1_______ + _________________4______ + ___________________2____ + ____________________33__ + ______________________4_ + */ + + /* if there's only one memory region, don't bother */ + if (*pnr_map < 2) + return -1; + + old_nr = *pnr_map; + + /* bail out if we find any unreasonable addresses in bios map */ + for (i=0; i<old_nr; i++) + if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr) + return -1; + + /* create pointers for initial change-point information (for sorting) */ + for (i=0; i < 2*old_nr; i++) + change_point[i] = &change_point_list[i]; + + /* record all known change-points (starting and ending addresses), + omitting those that are for empty memory regions */ + chgidx = 0; + for (i=0; i < old_nr; i++) { + if (biosmap[i].size != 0) { + change_point[chgidx]->addr = biosmap[i].addr; + change_point[chgidx++]->pbios = &biosmap[i]; + change_point[chgidx]->addr = biosmap[i].addr + biosmap[i].size; + change_point[chgidx++]->pbios = &biosmap[i]; + } + } + chg_nr = chgidx; /* true number of change-points */ + + /* sort change-point list by memory addresses (low -> high) */ + still_changing = 1; + while (still_changing) { + still_changing = 0; + for (i=1; i < chg_nr; i++) { + /* if <current_addr> > <last_addr>, swap */ + /* or, if current=<start_addr> & last=<end_addr>, swap */ + if ((change_point[i]->addr < change_point[i-1]->addr) || + ((change_point[i]->addr == change_point[i-1]->addr) && + (change_point[i]->addr == change_point[i]->pbios->addr) && + (change_point[i-1]->addr != change_point[i-1]->pbios->addr)) + ) + { + change_tmp = change_point[i]; + change_point[i] = change_point[i-1]; + change_point[i-1] = change_tmp; + still_changing=1; + } + } + } + + /* create a new bios memory map, removing overlaps */ + overlap_entries=0; /* number of entries in the overlap table */ + new_bios_entry=0; /* index for creating new bios map entries */ + last_type = 0; /* start with undefined memory type */ + last_addr = 0; /* start with 0 as last starting address */ + /* loop through change-points, determining affect on the new bios map */ + for (chgidx=0; chgidx < chg_nr; chgidx++) + { + /* keep track of all overlapping bios entries */ + if (change_point[chgidx]->addr == change_point[chgidx]->pbios->addr) + { + /* add map entry to overlap list (> 1 entry implies an overlap) */ + overlap_list[overlap_entries++]=change_point[chgidx]->pbios; + } + else + { + /* remove entry from list (order independent, so swap with last) */ + for (i=0; i<overlap_entries; i++) + { + if (overlap_list[i] == change_point[chgidx]->pbios) + overlap_list[i] = overlap_list[overlap_entries-1]; + } + overlap_entries--; + } + /* if there are overlapping entries, decide which "type" to use */ + /* (larger value takes precedence -- 1=usable, 2,3,4,4+=unusable) */ + current_type = 0; + for (i=0; i<overlap_entries; i++) + if (overlap_list[i]->type > current_type) + current_type = overlap_list[i]->type; + /* continue building up new bios map based on this information */ + if (current_type != last_type) { + if (last_type != 0) { + new_bios[new_bios_entry].size = + change_point[chgidx]->addr - last_addr; + /* move forward only if the new size was non-zero */ + if (new_bios[new_bios_entry].size != 0) + if (++new_bios_entry >= E820MAX) + break; /* no more space left for new bios entries */ + } + if (current_type != 0) { + new_bios[new_bios_entry].addr = change_point[chgidx]->addr; + new_bios[new_bios_entry].type = current_type; + last_addr=change_point[chgidx]->addr; + } + last_type = current_type; + } + } + new_nr = new_bios_entry; /* retain count for new bios entries */ + + /* copy new bios mapping into original location */ + memcpy(biosmap, new_bios, new_nr*sizeof(struct e820entry)); + *pnr_map = new_nr; + + return 0; +} + +/* + * Copy the BIOS e820 map into a safe place. + * + * Sanity-check it while we're at it.. + * + * If we're lucky and live on a modern system, the setup code + * will have given us a memory map that we can use to properly + * set up memory. If we aren't, we'll fake a memory map. + * + * We check to see that the memory map contains at least 2 elements + * before we'll use it, because the detection code in setup.S may + * not be perfect and most every PC known to man has two memory + * regions: one from 0 to 640k, and one from 1mb up. (The IBM + * thinkpad 560x, for example, does not cooperate with the memory + * detection code.) + */ +static int __init copy_e820_map(struct e820entry * biosmap, int nr_map) +{ + /* Only one memory region (or negative)? Ignore it */ + if (nr_map < 2) + return -1; + + do { + unsigned long long start = biosmap->addr; + unsigned long long size = biosmap->size; + unsigned long long end = start + size; + unsigned long type = biosmap->type; + + /* Overflow in 64 bits? Ignore the memory map. */ + if (start > end) + return -1; + + /* + * Some BIOSes claim RAM in the 640k - 1M region. + * Not right. Fix it up. + */ + if (type == E820_RAM) { + if (start < 0x100000ULL && end > 0xA0000ULL) { + if (start < 0xA0000ULL) + add_memory_region(start, 0xA0000ULL-start, type); + if (end <= 0x100000ULL) + continue; + start = 0x100000ULL; + size = end - start; + } + } + add_memory_region(start, size, type); + } while (biosmap++,--nr_map); + return 0; +} +#endif + +#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE) +struct edd edd; +#ifdef CONFIG_EDD_MODULE +EXPORT_SYMBOL(edd); +#endif +/** + * copy_edd() - Copy the BIOS EDD information + * from boot_params into a safe place. + * + */ +static inline void copy_edd(void) +{ + memcpy(edd.mbr_signature, EDD_MBR_SIGNATURE, sizeof(edd.mbr_signature)); + memcpy(edd.edd_info, EDD_BUF, sizeof(edd.edd_info)); + edd.mbr_signature_nr = EDD_MBR_SIG_NR; + edd.edd_info_nr = EDD_NR; +} +#else +static inline void copy_edd(void) +{ +} +#endif + +/* + * Do NOT EVER look at the BIOS memory size location. + * It does not work on many machines. + */ +#define LOWMEMSIZE() (0x9f000) + +static void __init parse_cmdline_early (char ** cmdline_p) +{ + char c = ' ', *to = command_line, *from = saved_command_line; + int len = 0, max_cmdline; + int userdef = 0; + + if ((max_cmdline = MAX_GUEST_CMDLINE) > COMMAND_LINE_SIZE) + max_cmdline = COMMAND_LINE_SIZE; + memcpy(saved_command_line, xen_start_info->cmd_line, max_cmdline); + /* Save unparsed command line copy for /proc/cmdline */ + saved_command_line[max_cmdline-1] = '\0'; + + for (;;) { + if (c != ' ') + goto next_char; + /* + * "mem=nopentium" disables the 4MB page tables. + * "mem=XXX[kKmM]" defines a memory region from HIGH_MEM + * to <mem>, overriding the bios size. + * "memmap=XXX[KkmM]@XXX[KkmM]" defines a memory region from + * <start> to <start>+<mem>, overriding the bios size. + * + * HPA tells me bootloaders need to parse mem=, so no new + * option should be mem= [also see Documentation/i386/boot.txt] + */ + if (!memcmp(from, "mem=", 4)) { + if (to != command_line) + to--; + if (!memcmp(from+4, "nopentium", 9)) { + from += 9+4; + clear_bit(X86_FEATURE_PSE, boot_cpu_data.x86_capability); + disable_pse = 1; + } else { + /* If the user specifies memory size, we + * limit the BIOS-provided memory map to + * that size. exactmap can be used to specify + * the exact map. mem=number can be used to + * trim the existing memory map. + */ + unsigned long long mem_size; + + mem_size = memparse(from+4, &from); +#if 0 + limit_regions(mem_size); + userdef=1; +#else + xen_override_max_pfn = + (unsigned long)(mem_size>>PAGE_SHIFT); +#endif + } + } + + else if (!memcmp(from, "memmap=", 7)) { + if (to != command_line) + to--; + if (!memcmp(from+7, "exactmap", 8)) { + from += 8+7; + e820.nr_map = 0; + userdef = 1; + } else { + /* If the user specifies memory size, we + * limit the BIOS-provided memory map to + * that size. exactmap can be used to specify + * the exact map. mem=number can be used to + * trim the existing memory map. + */ + unsigned long long start_at, mem_size; + + mem_size = memparse(from+7, &from); + if (*from == '@') { + start_at = memparse(from+1, &from); + add_memory_region(start_at, mem_size, E820_RAM); + } else if (*from == '#') { + start_at = memparse(from+1, &from); + add_memory_region(start_at, mem_size, E820_ACPI); + } else if (*from == '$') { + start_at = memparse(from+1, &from); + add_memory_region(start_at, mem_size, E820_RESERVED); + } else { + limit_regions(mem_size); + userdef=1; + } + } + } + + else if (!memcmp(from, "noexec=", 7)) + noexec_setup(from + 7); + + +#ifdef CONFIG_X86_MPPARSE + /* + * If the BIOS enumerates physical processors before logical, + * maxcpus=N at enumeration-time can be used to disable HT. + */ + else if (!memcmp(from, "maxcpus=", 8)) { + extern unsigned int maxcpus; + + maxcpus = simple_strtoul(from + 8, NULL, 0); + } +#endif + +#ifdef CONFIG_ACPI_BOOT + /* "acpi=off" disables both ACPI table parsing and interpreter */ + else if (!memcmp(from, "acpi=off", 8)) { + disable_acpi(); + } + + /* acpi=force to over-ride black-list */ + else if (!memcmp(from, "acpi=force", 10)) { + acpi_force = 1; + acpi_ht = 1; + acpi_disabled = 0; + } + + /* acpi=strict disables out-of-spec workarounds */ + else if (!memcmp(from, "acpi=strict", 11)) { + acpi_strict = 1; + } + + /* Limit ACPI just to boot-time to enable HT */ + else if (!memcmp(from, "acpi=ht", 7)) { + if (!acpi_force) + disable_acpi(); + acpi_ht = 1; + } + + /* "pci=noacpi" disable ACPI IRQ routing and PCI scan */ + else if (!memcmp(from, "pci=noacpi", 10)) { + acpi_disable_pci(); + } + /* "acpi=noirq" disables ACPI interrupt routing */ + else if (!memcmp(from, "acpi=noirq", 10)) { + acpi_noirq_set(); + } + + else if (!memcmp(from, "acpi_sci=edge", 13)) + acpi_sci_flags.trigger = 1; + + else if (!memcmp(from, "acpi_sci=level", 14)) + acpi_sci_flags.trigger = 3; + + else if (!memcmp(from, "acpi_sci=high", 13)) + acpi_sci_flags.polarity = 1; + + else if (!memcmp(from, "acpi_sci=low", 12)) + acpi_sci_flags.polarity = 3; + +#ifdef CONFIG_X86_IO_APIC + else if (!memcmp(from, "acpi_skip_timer_override", 24)) + acpi_skip_timer_override = 1; +#endif + +#ifdef CONFIG_X86_LOCAL_APIC + /* disable IO-APIC */ + else if (!memcmp(from, "noapic", 6)) + disable_ioapic_setup(); +#endif /* CONFIG_X86_LOCAL_APIC */ +#endif /* CONFIG_ACPI_BOOT */ + + /* + * highmem=size forces highmem to be exactly 'size' bytes. + * This works even on boxes that have no highmem otherwise. + * This also works to reduce highmem size on bigger boxes. + */ + else if (!memcmp(from, "highmem=", 8)) + highmem_pages = memparse(from+8, &from) >> PAGE_SHIFT; + + /* + * vmalloc=size forces the vmalloc area to be exactly 'size' + * bytes. This can be used to increase (or decrease) the + * vmalloc area - the default is 128m. + */ + else if (!memcmp(from, "vmalloc=", 8)) + __VMALLOC_RESERVE = memparse(from+8, &from); + + next_char: + c = *(from++); + if (!c) + break; + if (COMMAND_LINE_SIZE <= ++len) + break; + *(to++) = c; + } + *to = '\0'; + *cmdline_p = command_line; + if (userdef) { + printk(KERN_INFO "user-defined physical RAM map:\n"); + print_memory_map("user"); + } +} + +#if 0 /* !XEN */ +/* + * Callback for efi_memory_walk. + */ +static int __init +efi_find_max_pfn(unsigned long start, unsigned long end, void *arg) +{ + unsigned long *max_pfn = arg, pfn; + + if (start < end) { + pfn = PFN_UP(end -1); + if (pfn > *max_pfn) + *max_pfn = pfn; + } + return 0; +} + + +/* + * Find the highest page frame number we have available + */ +void __init find_max_pfn(void) +{ + int i; + + max_pfn = 0; + if (efi_enabled) { + efi_memmap_walk(efi_find_max_pfn, &max_pfn); + return; + } + + for (i = 0; i < e820.nr_map; i++) { + unsigned long start, end; + /* RAM? */ + if (e820.map[i].type != E820_RAM) + continue; + start = PFN_UP(e820.map[i].addr); + end = PFN_DOWN(e820.map[i].addr + e820.map[i].size); + if (start >= end) + continue; + if (end > max_pfn) + max_pfn = end; + } +} +#else +/* We don't use the fake e820 because we need to respond to user override. */ +void __init find_max_pfn(void) +{ + if (xen_override_max_pfn == 0) { + max_pfn = xen_start_info->nr_pages; + /* Default 8MB slack (to balance backend allocations). */ + max_pfn += 8 << (20 - PAGE_SHIFT); + } else if (xen_override_max_pfn > xen_start_info->nr_pages) { + max_pfn = xen_override_max_pfn; + } else { + max_pfn = xen_start_info->nr_pages; + } +} +#endif /* XEN */ + +/* + * Determine low and high memory ranges: + */ +unsigned long __init find_max_low_pfn(void) +{ + unsigned long max_low_pfn; + + max_low_pfn = max_pfn; + if (max_low_pfn > MAXMEM_PFN) { + if (highmem_pages == -1) + highmem_pages = max_pfn - MAXMEM_PFN; + if (highmem_pages + MAXMEM_PFN < max_pfn) + max_pfn = MAXMEM_PFN + highmem_pages; + if (highmem_pages + MAXMEM_PFN > max_pfn) { + printk("only %luMB highmem pages available, ignoring highmem size of %uMB.\n", pages_to_mb(max_pfn - MAXMEM_PFN), pages_to_mb(highmem_pages)); + highmem_pages = 0; + } + max_low_pfn = MAXMEM_PFN; +#ifndef CONFIG_HIGHMEM + /* Maximum memory usable is what is directly addressable */ + printk(KERN_WARNING "Warning only %ldMB will be used.\n", + MAXMEM>>20); + if (max_pfn > MAX_NONPAE_PFN) + printk(KERN_WARNING "Use a PAE enabled kernel.\n"); + else + printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n"); + max_pfn = MAXMEM_PFN; +#else /* !CONFIG_HIGHMEM */ +#ifndef CONFIG_X86_PAE + if (max_pfn > MAX_NONPAE_PFN) { + max_pfn = MAX_NONPAE_PFN; + printk(KERN_WARNING "Warning only 4GB will be used.\n"); + printk(KERN_WARNING "Use a PAE enabled kernel.\n"); + } +#endif /* !CONFIG_X86_PAE */ +#endif /* !CONFIG_HIGHMEM */ + } else { + if (highmem_pages == -1) + highmem_pages = 0; +#ifdef CONFIG_HIGHMEM + if (highmem_pages >= max_pfn) { + printk(KERN_ERR "highmem size specified (%uMB) is bigger than pages available (%luMB)!.\n", pages_to_mb(highmem_pages), pages_to_mb(max_pfn)); + highmem_pages = 0; + } + if (highmem_pages) { + if (max_low_pfn-highmem_pages < 64*1024*1024/PAGE_SIZE){ + printk(KERN_ERR "highmem size %uMB results in smaller than 64MB lowmem, ignoring it.\n", pages_to_mb(highmem_pages)); + highmem_pages = 0; + } + max_low_pfn -= highmem_pages; + } +#else + if (highmem_pages) + printk(KERN_ERR "ignoring highmem size on non-highmem kernel!\n"); +#endif + } + return max_low_pfn; +} + +/* + * Free all available memory for boot time allocation. Used + * as a callback function by efi_memory_walk() + */ + +static int __init +free_available_memory(unsigned long start, unsigned long end, void *arg) +{ + /* check max_low_pfn */ + if (start >= ((max_low_pfn + 1) << PAGE_SHIFT)) + return 0; + if (end >= ((max_low_pfn + 1) << PAGE_SHIFT)) + end = (max_low_pfn + 1) << PAGE_SHIFT; + if (start < end) + free_bootmem(start, end - start); + + return 0; +} +/* + * Register fully available low RAM pages with the bootmem allocator. + */ +static void __init register_bootmem_low_pages(unsigned long max_low_pfn) +{ + int i; + + if (efi_enabled) { + efi_memmap_walk(free_available_memory, NULL); + return; + } + for (i = 0; i < e820.nr_map; i++) { + unsigned long curr_pfn, last_pfn, size; + /* + * Reserve usable low memory + */ + if (e820.map[i].type != E820_RAM) + continue; + /* + * We are rounding up the start address of usable memory: + */ + curr_pfn = PFN_UP(e820.map[i].addr); + if (curr_pfn >= max_low_pfn) + continue; + /* + * ... and at the end of the usable range downwards: + */ + last_pfn = PFN_DOWN(e820.map[i].addr + e820.map[i].size); + + if (last_pfn > max_low_pfn) + last_pfn = max_low_pfn; + + /* + * .. finally, did all the rounding and playing + * around just make the area go away? + */ + if (last_pfn <= curr_pfn) + continue; + + size = last_pfn - curr_pfn; + free_bootmem(PFN_PHYS(curr_pfn), PFN_PHYS(size)); + } +} + +#ifndef CONFIG_XEN +/* + * workaround for Dell systems that neglect to reserve EBDA + */ +static void __init reserve_ebda_region(void) +{ + unsigned int addr; + addr = get_bios_ebda(); + if (addr) + reserve_bootmem(addr, PAGE_SIZE); +} +#endif + +#ifndef CONFIG_DISCONTIGMEM +void __init setup_bootmem_allocator(void); +static unsigned long __init setup_memory(void) +{ + /* + * partially used pages are not usable - thus + * we are rounding upwards: + */ + min_low_pfn = PFN_UP(__pa(xen_start_info->pt_base)) + + xen_start_info->nr_pt_frames; + + find_max_pfn(); + + max_low_pfn = find_max_low_pfn(); + +#ifdef CONFIG_HIGHMEM + highstart_pfn = highend_pfn = max_pfn; + if (max_pfn > max_low_pfn) { + highstart_pfn = max_low_pfn; + } + printk(KERN_NOTICE "%ldMB HIGHMEM available.\n", + pages_to_mb(highend_pfn - highstart_pfn)); +#endif + printk(KERN_NOTICE "%ldMB LOWMEM available.\n", + pages_to_mb(max_low_pfn)); + + setup_bootmem_allocator(); + + return max_low_pfn; +} + +void __init zone_sizes_init(void) +{ + unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0}; + unsigned int max_dma, low; + + /* + * XEN: Our notion of "DMA memory" is fake when running over Xen. + * We simply put all RAM in the DMA zone so that those drivers which + * needlessly specify GFP_DMA do not get starved of RAM unnecessarily. + * Those drivers that *do* require lowmem are screwed anyway when + * running over Xen! + */ + max_dma = max_low_pfn; + low = max_low_pfn; + + if (low < max_dma) + zones_size[ZONE_DMA] = low; + else { + zones_size[ZONE_DMA] = max_dma; + zones_size[ZONE_NORMAL] = low - max_dma; +#ifdef CONFIG_HIGHMEM + zones_size[ZONE_HIGHMEM] = highend_pfn - low; +#endif + } + free_area_init(zones_size); +} +#else +extern unsigned long setup_memory(void); +extern void zone_sizes_init(void); +#endif /* !CONFIG_DISCONTIGMEM */ + +void __init setup_bootmem_allocator(void) +{ + unsigned long bootmap_size; + /* + * Initialize the boot-time allocator (with low memory only): + */ + bootmap_size = init_bootmem(min_low_pfn, max_low_pfn); + + register_bootmem_low_pages(max_low_pfn); + + /* + * Reserve the bootmem bitmap itself as well. We do this in two + * steps (first step was init_bootmem()) because this catches + * the (very unlikely) case of us accidentally initializing the + * bootmem allocator with an invalid RAM area. + */ + reserve_bootmem(HIGH_MEMORY, (PFN_PHYS(min_low_pfn) + + bootmap_size + PAGE_SIZE-1) - (HIGH_MEMORY)); + +#ifndef CONFIG_XEN + /* + * reserve physical page 0 - it's a special BIOS page on many boxes, + * enabling clean reboots, SMP operation, laptop functions. + */ + reserve_bootmem(0, PAGE_SIZE); + + /* reserve EBDA region, it's a 4K region */ + reserve_ebda_region(); + + /* could be an AMD 768MPX chipset. Reserve a page before VGA to prevent + PCI prefetch into it (errata #56). Usually the page is reserved anyways, + unless you have no PS/2 mouse plugged in. */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD && + boot_cpu_data.x86 == 6) + reserve_bootmem(0xa0000 - 4096, 4096); + +#ifdef CONFIG_SMP + /* + * But first pinch a few for the stack/trampoline stuff + * FIXME: Don't need the extra page at 4K, but need to fix + * trampoline before removing it. (see the GDT stuff) + */ + reserve_bootmem(PAGE_SIZE, PAGE_SIZE); +#endif +#ifdef CONFIG_ACPI_SLEEP + /* + * Reserve low memory region for sleep support. + */ + acpi_reserve_bootmem(); +#endif +#endif /* !CONFIG_XEN */ + +#ifdef CONFIG_BLK_DEV_INITRD + if (xen_start_info->mod_start) { + if (INITRD_START + INITRD_SIZE <= (max_low_pfn << PAGE_SHIFT)) { + /*reserve_bootmem(INITRD_START, INITRD_SIZE);*/ + initrd_start = INITRD_START + PAGE_OFFSET; + initrd_end = initrd_start+INITRD_SIZE; + initrd_below_start_ok = 1; + } + else { + printk(KERN_ERR "initrd extends beyond end of memory " + "(0x%08lx > 0x%08lx)\ndisabling initrd\n", + INITRD_START + INITRD_SIZE, + max_low_pfn << PAGE_SHIFT); + initrd_start = 0; + } + } +#endif + + phys_to_machine_mapping = (unsigned long *)xen_start_info->mfn_list; +} + +/* + * The node 0 pgdat is initialized before all of these because + * it's needed for bootmem. node>0 pgdats have their virtual + * space allocated before the pagetables are in place to access + * them, so they can't be cleared then. + * + * This should all compile down to nothing when NUMA is off. + */ +void __init remapped_pgdat_init(void) +{ + int nid; + + for_each_online_node(nid) { + if (nid != 0) + memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); + } +} + +/* + * Request address space for all standard RAM and ROM resources + * and also for regions reported as reserved by the e820. + */ +static void __init +legacy_init_iomem_resources(struct resource *code_resource, struct resource *data_resource) +{ + int i; +#ifdef CONFIG_XEN + dom0_op_t op; + struct dom0_memory_map_entry *map; + unsigned long gapstart, gapsize; + unsigned long long last; +#endif + +#ifdef CONFIG_XEN_PRIVILEGED_GUEST + probe_roms(); +#endif + +#ifdef CONFIG_XEN + map = alloc_bootmem_low_pages(PAGE_SIZE); + op.cmd = DOM0_PHYSICAL_MEMORY_MAP; + op.u.physical_memory_map.memory_map = map; + op.u.physical_memory_map.max_map_entries = + PAGE_SIZE / sizeof(struct dom0_memory_map_entry); + BUG_ON(HYPERVISOR_dom0_op(&op)); + + last = 0x100000000ULL; + gapstart = 0x10000000; + gapsize = 0x400000; + + for (i = op.u.physical_memory_map.nr_map_entries - 1; i >= 0; i--) { + struct resource *res; + + if ((last > map[i].end) && ((last - map[i].end) > gapsize)) { + gapsize = last - map[i].end; + gapstart = map[i].end; + } + if (map[i].start < last) + last = map[i].start; + + if (map[i].end > 0x100000000ULL) + continue; + res = alloc_bootmem_low(sizeof(struct resource)); + res->name = map[i].is_ram ? "System RAM" : "reserved"; + res->start = map[i].start; + res->end = map[i].end - 1; + res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + request_resource(&iomem_resource, res); + } + + free_bootmem(__pa(map), PAGE_SIZE); + + /* + * Start allocating dynamic PCI memory a bit into the gap, + * aligned up to the nearest megabyte. + * + * Question: should we try to pad it up a bit (do something + * like " + (gapsize >> 3)" in there too?). We now have the + * technology. + */ + pci_mem_start = (gapstart + 0xfffff) & ~0xfffff; + + printk("Allocating PCI resources starting at %08lx (gap: %08lx:%08lx)\n", + pci_mem_start, gapstart, gapsize); +#else + for (i = 0; i < e820.nr_map; i++) { + struct resource *res; + if (e820.map[i].addr + e820.map[i].size > 0x100000000ULL) + continue; + res = alloc_bootmem_low(sizeof(struct resource)); + switch (e820.map[i].type) { + case E820_RAM: res->name = "System RAM"; break; + case E820_ACPI: res->name = "ACPI Tables"; break; + case E820_NVS: res->name = "ACPI Non-volatile Storage"; break; + default: res->name = "reserved"; + } + res->start = e820.map[i].addr; + res->end = res->start + e820.map[i].size - 1; + res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + request_resource(&iomem_resource, res); + if (e820.map[i].type == E820_RAM) { + /* + * We don't know which RAM region contains kernel data, + * so we try it repeatedly and let the resource manager + * test it. + */ + request_resource(res, code_resource); + request_resource(res, data_resource); + } + } +#endif +} + +/* + * Request address space for all standard resources + */ +static void __init register_memory(void) +{ +#ifndef CONFIG_XEN + unsigned long gapstart, gapsize; + unsigned long long last; +#endif + int i; + + /* Nothing to do if not running in dom0. */ + if (!(xen_start_info->flags & SIF_INITDOMAIN)) + return; + + if (efi_enabled) + efi_initialize_iomem_resources(&code_resource, &data_resource); + else + legacy_init_iomem_resources(&code_resource, &data_resource); + + /* EFI systems may still have VGA */ + request_resource(&iomem_resource, &video_ram_resource); + + /* request I/O space for devices used on all i[345]86 PCs */ + for (i = 0; i < STANDARD_IO_RESOURCES; i++) + request_resource(&ioport_resource, &standard_io_resources[i]); + +#ifndef CONFIG_XEN + /* + * Search for the bigest gap in the low 32 bits of the e820 + * memory space. + */ + last = 0x100000000ull; + gapstart = 0x10000000; + gapsize = 0x400000; + i = e820.nr_map; + while (--i >= 0) { + unsigned long long start = e820.map[i].addr; + unsigned long long end = start + e820.map[i].size; + + /* + * Since "last" is at most 4GB, we know we'll + * fit in 32 bits if this condition is true + */ + if (last > end) { + unsigned long gap = last - end; + + if (gap > gapsize) { + gapsize = gap; + gapstart = end; + } + } + if (start < last) + last = start; + } + + /* + * Start allocating dynamic PCI memory a bit into the gap, + * aligned up to the nearest megabyte. + * + * Question: should we try to pad it up a bit (do something + * like " + (gapsize >> 3)" in there too?). We now have the + * technology. + */ + pci_mem_start = (gapstart + 0xfffff) & ~0xfffff; + + printk("Allocating PCI resources starting at %08lx (gap: %08lx:%08lx)\n", + pci_mem_start, gapstart, gapsize); +#endif +} + +/* Use inline assembly to define this because the nops are defined + as inline assembly strings in the include files and we cannot + get them easily into strings. */ +asm("\t.data\nintelnops: " + GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6 + GENERIC_NOP7 GENERIC_NOP8); +asm("\t.data\nk8nops: " + K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6 + K8_NOP7 K8_NOP8); +asm("\t.data\nk7nops: " + K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6 + K7_NOP7 K7_NOP8); + +extern unsigned char intelnops[], k8nops[], k7nops[]; +static unsigned char *intel_nops[ASM_NOP_MAX+1] = { + NULL, + intelnops, + intelnops + 1, + intelnops + 1 + 2, + intelnops + 1 + 2 + 3, + intelnops + 1 + 2 + 3 + 4, + intelnops + 1 + 2 + 3 + 4 + 5, + intelnops + 1 + 2 + 3 + 4 + 5 + 6, + intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7, +}; +static unsigned char *k8_nops[ASM_NOP_MAX+1] = { + NULL, + k8nops, + k8nops + 1, + k8nops + 1 + 2, + k8nops + 1 + 2 + 3, + k8nops + 1 + 2 + 3 + 4, + k8nops + 1 + 2 + 3 + 4 + 5, + k8nops + 1 + 2 + 3 + 4 + 5 + 6, + k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7, +}; +static unsigned char *k7_nops[ASM_NOP_MAX+1] = { + NULL, + k7nops, + k7nops + 1, + k7nops + 1 + 2, + k7nops + 1 + 2 + 3, + k7nops + 1 + 2 + 3 + 4, + k7nops + 1 + 2 + 3 + 4 + 5, + k7nops + 1 + 2 + 3 + 4 + 5 + 6, + k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7, +}; +static struct nop { + int cpuid; + unsigned char **noptable; +} noptypes[] = { + { X86_FEATURE_K8, k8_nops }, + { X86_FEATURE_K7, k7_nops }, + { -1, NULL } +}; + +/* Replace instructions with better alternatives for this CPU type. + + This runs before SMP is initialized to avoid SMP problems with + self modifying code. This implies that assymetric systems where + APs have less capabilities than the boot processor are not handled. + In this case boot with "noreplacement". */ +void apply_alternatives(void *start, void *end) +{ + struct alt_instr *a; + int diff, i, k; + unsigned char **noptable = intel_nops; + for (i = 0; noptypes[i].cpuid >= 0; i++) { + if (boot_cpu_has(noptypes[i].cpuid)) { + noptable = noptypes[i].noptable; + break; + } + } + for (a = start; (void *)a < end; a++) { + if (!boot_cpu_has(a->cpuid)) + continue; + BUG_ON(a->replacementlen > a->instrlen); + memcpy(a->instr, a->replacement, a->replacementlen); + diff = a->instrlen - a->replacementlen; + /* Pad the rest with nops */ + for (i = a->replacementlen; diff > 0; diff -= k, i += k) { + k = diff; + if (k > ASM_NOP_MAX) + k = ASM_NOP_MAX; + memcpy(a->instr + i, noptable[k], k); + } + } +} + +static int no_replacement __initdata = 0; + +void __init alternative_instructions(void) +{ + extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; + if (no_replacement) + return; + apply_alternatives(__alt_instructions, __alt_instructions_end); +} + +static int __init noreplacement_setup(char *s) +{ + no_replacement = 1; + return 0; +} + +__setup("noreplacement", noreplacement_setup); + +static char * __init machine_specific_memory_setup(void); + +#ifdef CONFIG_MCA +static void set_mca_bus(int x) +{ + MCA_bus = x; +} +#else +static void set_mca_bus(int x) { } +#endif + +/* + * Determine if we were loaded by an EFI loader. If so, then we have also been + * passed the efi memmap, systab, etc., so we should use these data structures + * for initialization. Note, the efi init code path is determined by the + * global efi_enabled. This allows the same kernel image to be used on existing + * systems (with a traditional BIOS) as well as on EFI systems. + */ +void __init setup_arch(char **cmdline_p) +{ + int i, j, k, fpp; + physdev_op_t op; + unsigned long max_low_pfn; + + /* Force a quick death if the kernel panics. */ + extern int panic_timeout; + if (panic_timeout == 0) + panic_timeout = 1; + + /* Register a call for panic conditions. */ + notifier_chain_register(&panic_notifier_list, &xen_panic_block); + + HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments); + HYPERVISOR_vm_assist(VMASST_CMD_enable, + VMASST_TYPE_writable_pagetables); + + memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); + early_cpu_init(); + + /* + * FIXME: This isn't an official loader_type right + * now but does currently work with elilo. + * If we were configured as an EFI kernel, check to make + * sure that we were loaded correctly from elilo and that + * the system table is valid. If not, then initialize normally. + */ +#ifdef CONFIG_EFI + if ((LOADER_TYPE == 0x50) && EFI_SYSTAB) + efi_enabled = 1; +#endif + + /* This must be initialized to UNNAMED_MAJOR for ipconfig to work + properly. Setting ROOT_DEV to default to /dev/ram0 breaks initrd. + */ + ROOT_DEV = MKDEV(UNNAMED_MAJOR,0); + drive_info = DRIVE_INFO; + screen_info = SCREEN_INFO; + edid_info = EDID_INFO; + apm_info.bios = APM_BIOS_INFO; + ist_info = IST_INFO; + saved_videomode = VIDEO_MODE; + if( SYS_DESC_TABLE.length != 0 ) { + set_mca_bus(SYS_DESC_TABLE.table[3] & 0x2); + machine_id = SYS_DESC_TABLE.table[0]; + machine_submodel_id = SYS_DESC_TABLE.table[1]; + BIOS_revision = SYS_DESC_TABLE.table[2]; + } + bootloader_type = LOADER_TYPE; + +#ifdef CONFIG_XEN_PHYSDEV_ACCESS + /* This is drawn from a dump from vgacon:startup in standard Linux. */ + screen_info.orig_video_mode = 3; + screen_info.orig_video_isVGA = 1; + screen_info.orig_video_lines = 25; + screen_info.orig_video_cols = 80; + screen_info.orig_video_ega_bx = 3; + screen_info.orig_video_points = 16; +#endif + +#ifdef CONFIG_BLK_DEV_RAM + rd_image_start = RAMDISK_FLAGS & RAMDISK_IMAGE_START_MASK; + rd_prompt = ((RAMDISK_FLAGS & RAMDISK_PROMPT_FLAG) != 0); + rd_doload = ((RAMDISK_FLAGS & RAMDISK_LOAD_FLAG) != 0); +#endif + + setup_xen_features(); + + ARCH_SETUP + if (efi_enabled) + efi_init(); + else { + printk(KERN_INFO "BIOS-provided physical RAM map:\n"); + print_memory_map(machine_specific_memory_setup()); + } + + copy_edd(); + + if (!MOUNT_ROOT_RDONLY) + root_mountflags &= ~MS_RDONLY; + init_mm.start_code = (unsigned long) _text; + init_mm.end_code = (unsigned long) _etext; + init_mm.end_data = (unsigned long) _edata; + init_mm.brk = (PFN_UP(__pa(xen_start_info->pt_base)) + + xen_start_info->nr_pt_frames) << PAGE_SHIFT; + + /* XEN: This is nonsense: kernel may not even be contiguous in RAM. */ + /*code_resource.start = virt_to_phys(_text);*/ + /*code_resource.end = virt_to_phys(_etext)-1;*/ + /*data_resource.start = virt_to_phys(_etext);*/ + /*data_resource.end = virt_to_phys(_edata)-1;*/ + + parse_cmdline_early(cmdline_p); + + max_low_pfn = setup_memory(); + + /* + * NOTE: before this point _nobody_ is allowed to allocate + * any memory using the bootmem allocator. Although the + * alloctor is now initialised only the first 8Mb of the kernel + * virtual address space has been mapped. All allocations before + * paging_init() has completed must use the alloc_bootmem_low_pages() + * variant (which allocates DMA'able memory) and care must be taken + * not to exceed the 8Mb limit. + */ + +#ifdef CONFIG_SMP + smp_alloc_memory(); /* AP processor realmode stacks in low memory*/ +#endif + paging_init(); + remapped_pgdat_init(); + zone_sizes_init(); + +#ifdef CONFIG_X86_FIND_SMP_CONFIG + /* + * Find and reserve possible boot-time SMP configuration: + */ + find_smp_config(); +#endif + + /* Make sure we have a correctly sized P->M table. */ + phys_to_machine_mapping = alloc_bootmem_low_pages( + max_pfn * sizeof(unsigned long)); + memset(phys_to_machine_mapping, ~0, + max_pfn * sizeof(unsigned long)); + memcpy(phys_to_machine_mapping, + (unsigned long *)xen_start_info->mfn_list, + xen_start_info->nr_pages * sizeof(unsigned long)); + free_bootmem( + __pa(xen_start_info->mfn_list), + PFN_PHYS(PFN_UP(xen_start_info->nr_pages * + sizeof(unsigned long)))); + + /* + * Initialise the list of the frames that specify the list of + * frames that make up the p2m table. Used by save/restore + */ + pfn_to_mfn_frame_list_list = alloc_bootmem_low_pages(PAGE_SIZE); + HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = + virt_to_mfn(pfn_to_mfn_frame_list_list); + + fpp = PAGE_SIZE/sizeof(unsigned long); + for ( i=0, j=0, k=-1; i< max_pfn; i+=fpp, j++ ) + { + if ( (j % fpp) == 0 ) + { + k++; + BUG_ON(k>=16); + pfn_to_mfn_frame_list[k] = alloc_bootmem_low_pages(PAGE_SIZE); + pfn_to_mfn_frame_list_list[k] = + virt_to_mfn(pfn_to_mfn_frame_list[k]); + j=0; + } + pfn_to_mfn_frame_list[k][j] = + virt_to_mfn(&phys_to_machine_mapping[i]); + } + HYPERVISOR_shared_info->arch.max_pfn = max_pfn; + + /* + * NOTE: at this point the bootmem allocator is fully available. + */ + +#ifdef CONFIG_EARLY_PRINTK + { + char *s = strstr(*cmdline_p, "earlyprintk="); + if (s) { + extern void setup_early_printk(char *); + + setup_early_printk(s); + printk("early console enabled\n"); + } + } +#endif + + if (xen_start_info->flags & SIF_INITDOMAIN) + dmi_scan_machine(); + +#ifdef CONFIG_X86_GENERICARCH + generic_apic_probe(*cmdline_p); +#endif + if (efi_enabled) + efi_map_memmap(); + + op.cmd = PHYSDEVOP_SET_IOPL; + op.u.set_iopl.iopl = 1; + HYPERVISOR_physdev_op(&op); + +#ifdef CONFIG_ACPI_BOOT + if (!(xen_start_info->flags & SIF_INITDOMAIN)) { + printk(KERN_INFO "ACPI in unprivileged domain disabled\n"); + acpi_disabled = 1; + acpi_ht = 0; + } +#endif + +#ifdef CONFIG_ACPI_BOOT + /* + * Parse the ACPI tables for possible boot-time SMP configuration. + */ + acpi_boot_table_init(); + acpi_boot_init(); +#endif + +#ifdef CONFIG_X86_LOCAL_APIC + if (smp_found_config) + get_smp_config(); +#endif + + /* XXX Disable irqdebug until we have a way to avoid interrupt + * conflicts. */ + noirqdebug_setup(""); + + register_memory(); + + if (xen_start_info->flags & SIF_INITDOMAIN) { + if (!(xen_start_info->flags & SIF_PRIVILEGED)) + panic("Xen granted us console access " + "but not privileged status"); + +#ifdef CONFIG_VT +#if defined(CONFIG_VGA_CONSOLE) + if (!efi_enabled || + (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY)) + conswitchp = &vga_con; +#elif defined(CONFIG_DUMMY_CONSOLE) + conswitchp = &dummy_con; +#endif +#endif + } else { +#ifdef CONFIG_XEN_PHYSDEV_ACCESS + extern const struct consw xennull_con; + extern int console_use_vt; +#if defined(CONFIG_VGA_CONSOLE) + /* disable VGA driver */ + ORIG_VIDEO_ISVGA = VIDEO_TYPE_VLFB; +#endif + conswitchp = &xennull_con; + console_use_vt = 0; +#endif + } +} + +static int +xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr) +{ + HYPERVISOR_sched_op(SCHEDOP_shutdown, SHUTDOWN_crash); + /* we're never actually going to get here... */ + return NOTIFY_DONE; +} + +#include "setup_arch_post.h" +/* + * Local Variables: + * mode:c + * c-file-style:"k&r" + * c-basic-offset:8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/signal-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/signal-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,665 @@ +/* + * linux/arch/i386/kernel/signal.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson + * 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes + */ + +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/kernel.h> +#include <linux/signal.h> +#include <linux/errno.h> +#include <linux/wait.h> +#include <linux/unistd.h> +#include <linux/stddef.h> +#include <linux/personality.h> +#include <linux/suspend.h> +#include <linux/ptrace.h> +#include <linux/elf.h> +#include <asm/processor.h> +#include <asm/ucontext.h> +#include <asm/uaccess.h> +#include <asm/i387.h> +#include "sigframe.h" + +#define DEBUG_SIG 0 + +#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) + +/* + * Atomically swap in the new signal mask, and wait for a signal. + */ +asmlinkage int +sys_sigsuspend(int history0, int history1, old_sigset_t mask) +{ + struct pt_regs * regs = (struct pt_regs *) &history0; + sigset_t saveset; + + mask &= _BLOCKABLE; + spin_lock_irq(&current->sighand->siglock); + saveset = current->blocked; + siginitset(&current->blocked, mask); + recalc_sigpending(); + spin_unlock_irq(&current->sighand->siglock); + + regs->eax = -EINTR; + while (1) { + current->state = TASK_INTERRUPTIBLE; + schedule(); + if (do_signal(regs, &saveset)) + return -EINTR; + } +} + +asmlinkage int +sys_rt_sigsuspend(struct pt_regs regs) +{ + sigset_t saveset, newset; + + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (regs.ecx != sizeof(sigset_t)) + return -EINVAL; + + if (copy_from_user(&newset, (sigset_t __user *)regs.ebx, sizeof(newset))) + return -EFAULT; + sigdelsetmask(&newset, ~_BLOCKABLE); + + spin_lock_irq(&current->sighand->siglock); + saveset = current->blocked; + current->blocked = newset; + recalc_sigpending(); + spin_unlock_irq(&current->sighand->siglock); + + regs.eax = -EINTR; + while (1) { + current->state = TASK_INTERRUPTIBLE; + schedule(); + if (do_signal(&regs, &saveset)) + return -EINTR; + } +} + +asmlinkage int +sys_sigaction(int sig, const struct old_sigaction __user *act, + struct old_sigaction __user *oact) +{ + struct k_sigaction new_ka, old_ka; + int ret; + + if (act) { + old_sigset_t mask; + if (!access_ok(VERIFY_READ, act, sizeof(*act)) || + __get_user(new_ka.sa.sa_handler, &act->sa_handler) || + __get_user(new_ka.sa.sa_restorer, &act->sa_restorer)) + return -EFAULT; + __get_user(new_ka.sa.sa_flags, &act->sa_flags); + __get_user(mask, &act->sa_mask); + siginitset(&new_ka.sa.sa_mask, mask); + } + + ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); + + if (!ret && oact) { + if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || + __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || + __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer)) + return -EFAULT; + __put_user(old_ka.sa.sa_flags, &oact->sa_flags); + __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask); + } + + return ret; +} + +asmlinkage int +sys_sigaltstack(unsigned long ebx) +{ + /* This is needed to make gcc realize it doesn't own the "struct pt_regs" */ + struct pt_regs *regs = (struct pt_regs *)&ebx; + const stack_t __user *uss = (const stack_t __user *)ebx; + stack_t __user *uoss = (stack_t __user *)regs->ecx; + + return do_sigaltstack(uss, uoss, regs->esp); +} + + +/* + * Do a signal return; undo the signal stack. + */ + +static int +restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *peax) +{ + unsigned int err = 0; + + /* Always make any pending restarted system calls return -EINTR */ + current_thread_info()->restart_block.fn = do_no_restart_syscall; + +#define COPY(x) err |= __get_user(regs->x, &sc->x) + +#define COPY_SEG(seg) \ + { unsigned short tmp; \ + err |= __get_user(tmp, &sc->seg); \ + regs->x##seg = tmp; } + +#define COPY_SEG_STRICT(seg) \ + { unsigned short tmp; \ + err |= __get_user(tmp, &sc->seg); \ + regs->x##seg = tmp|3; } + +#define GET_SEG(seg) \ + { unsigned short tmp; \ + err |= __get_user(tmp, &sc->seg); \ + loadsegment(seg,tmp); } + +#define FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | X86_EFLAGS_DF | \ + X86_EFLAGS_TF | X86_EFLAGS_SF | X86_EFLAGS_ZF | \ + X86_EFLAGS_AF | X86_EFLAGS_PF | X86_EFLAGS_CF) + + GET_SEG(gs); + GET_SEG(fs); + COPY_SEG(es); + COPY_SEG(ds); + COPY(edi); + COPY(esi); + COPY(ebp); + COPY(esp); + COPY(ebx); + COPY(edx); + COPY(ecx); + COPY(eip); + COPY_SEG_STRICT(cs); + COPY_SEG_STRICT(ss); + + { + unsigned int tmpflags; + err |= __get_user(tmpflags, &sc->eflags); + regs->eflags = (regs->eflags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); + regs->orig_eax = -1; /* disable syscall checks */ + } + + { + struct _fpstate __user * buf; + err |= __get_user(buf, &sc->fpstate); + if (buf) { + if (!access_ok(VERIFY_READ, buf, sizeof(*buf))) + goto badframe; + err |= restore_i387(buf); + } else { + struct task_struct *me = current; + if (used_math()) { + clear_fpu(me); + clear_used_math(); + } + } + } + + err |= __get_user(*peax, &sc->eax); + return err; + +badframe: + return 1; +} + +asmlinkage int sys_sigreturn(unsigned long __unused) +{ + struct pt_regs *regs = (struct pt_regs *) &__unused; + struct sigframe __user *frame = (struct sigframe __user *)(regs->esp - 8); + sigset_t set; + int eax; + + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) + goto badframe; + if (__get_user(set.sig[0], &frame->sc.oldmask) + || (_NSIG_WORDS > 1 + && __copy_from_user(&set.sig[1], &frame->extramask, + sizeof(frame->extramask)))) + goto badframe; + + sigdelsetmask(&set, ~_BLOCKABLE); + spin_lock_irq(&current->sighand->siglock); + current->blocked = set; + recalc_sigpending(); + spin_unlock_irq(&current->sighand->siglock); + + if (restore_sigcontext(regs, &frame->sc, &eax)) + goto badframe; + return eax; + +badframe: + force_sig(SIGSEGV, current); + return 0; +} + +asmlinkage int sys_rt_sigreturn(unsigned long __unused) +{ + struct pt_regs *regs = (struct pt_regs *) &__unused; + struct rt_sigframe __user *frame = (struct rt_sigframe __user *)(regs->esp - 4); + sigset_t set; + int eax; + + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) + goto badframe; + if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) + goto badframe; + + sigdelsetmask(&set, ~_BLOCKABLE); + spin_lock_irq(&current->sighand->siglock); + current->blocked = set; + recalc_sigpending(); + spin_unlock_irq(&current->sighand->siglock); + + if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &eax)) + goto badframe; + + if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->esp) == -EFAULT) + goto badframe; + + return eax; + +badframe: + force_sig(SIGSEGV, current); + return 0; +} + +/* + * Set up a signal frame. + */ + +static int +setup_sigcontext(struct sigcontext __user *sc, struct _fpstate __user *fpstate, + struct pt_regs *regs, unsigned long mask) +{ + int tmp, err = 0; + + tmp = 0; + __asm__("movl %%gs,%0" : "=r"(tmp): "0"(tmp)); + err |= __put_user(tmp, (unsigned int __user *)&sc->gs); + __asm__("movl %%fs,%0" : "=r"(tmp): "0"(tmp)); + err |= __put_user(tmp, (unsigned int __user *)&sc->fs); + + err |= __put_user(regs->xes, (unsigned int __user *)&sc->es); + err |= __put_user(regs->xds, (unsigned int __user *)&sc->ds); + err |= __put_user(regs->edi, &sc->edi); + err |= __put_user(regs->esi, &sc->esi); + err |= __put_user(regs->ebp, &sc->ebp); + err |= __put_user(regs->esp, &sc->esp); + err |= __put_user(regs->ebx, &sc->ebx); + err |= __put_user(regs->edx, &sc->edx); + err |= __put_user(regs->ecx, &sc->ecx); + err |= __put_user(regs->eax, &sc->eax); + err |= __put_user(current->thread.trap_no, &sc->trapno); + err |= __put_user(current->thread.error_code, &sc->err); + err |= __put_user(regs->eip, &sc->eip); + err |= __put_user(regs->xcs, (unsigned int __user *)&sc->cs); + err |= __put_user(regs->eflags, &sc->eflags); + err |= __put_user(regs->esp, &sc->esp_at_signal); + err |= __put_user(regs->xss, (unsigned int __user *)&sc->ss); + + tmp = save_i387(fpstate); + if (tmp < 0) + err = 1; + else + err |= __put_user(tmp ? fpstate : NULL, &sc->fpstate); + + /* non-iBCS2 extensions.. */ + err |= __put_user(mask, &sc->oldmask); + err |= __put_user(current->thread.cr2, &sc->cr2); + + return err; +} + +/* + * Determine which stack to use.. + */ +static inline void __user * +get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size) +{ + unsigned long esp; + + /* Default to using normal stack */ + esp = regs->esp; + + /* This is the X/Open sanctioned signal stack switching. */ + if (ka->sa.sa_flags & SA_ONSTACK) { + if (sas_ss_flags(esp) == 0) + esp = current->sas_ss_sp + current->sas_ss_size; + } + + /* This is the legacy signal stack switching. */ + else if ((regs->xss & 0xffff) != __USER_DS && + !(ka->sa.sa_flags & SA_RESTORER) && + ka->sa.sa_restorer) { + esp = (unsigned long) ka->sa.sa_restorer; + } + + return (void __user *)((esp - frame_size) & -8ul); +} + +/* These symbols are defined with the addresses in the vsyscall page. + See vsyscall-sigreturn.S. */ +extern void __user __kernel_sigreturn; +extern void __user __kernel_rt_sigreturn; + +static void setup_frame(int sig, struct k_sigaction *ka, + sigset_t *set, struct pt_regs * regs) +{ + void __user *restorer; + struct sigframe __user *frame; + int err = 0; + int usig; + + frame = get_sigframe(ka, regs, sizeof(*frame)); + + if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) + goto give_sigsegv; + + usig = current_thread_info()->exec_domain + && current_thread_info()->exec_domain->signal_invmap + && sig < 32 + ? current_thread_info()->exec_domain->signal_invmap[sig] + : sig; + + err = __put_user(usig, &frame->sig); + if (err) + goto give_sigsegv; + + err = setup_sigcontext(&frame->sc, &frame->fpstate, regs, set->sig[0]); + if (err) + goto give_sigsegv; + + if (_NSIG_WORDS > 1) { + err = __copy_to_user(&frame->extramask, &set->sig[1], + sizeof(frame->extramask)); + if (err) + goto give_sigsegv; + } + + restorer = &__kernel_sigreturn; + if (ka->sa.sa_flags & SA_RESTORER) + restorer = ka->sa.sa_restorer; + + /* Set up to return from userspace. */ + err |= __put_user(restorer, &frame->pretcode); + + /* + * This is popl %eax ; movl $,%eax ; int $0x80 + * + * WE DO NOT USE IT ANY MORE! It's only left here for historical + * reasons and because gdb uses it as a signature to notice + * signal handler stack frames. + */ + err |= __put_user(0xb858, (short __user *)(frame->retcode+0)); + err |= __put_user(__NR_sigreturn, (int __user *)(frame->retcode+2)); + err |= __put_user(0x80cd, (short __user *)(frame->retcode+6)); + + if (err) + goto give_sigsegv; + + /* Set up registers for signal handler */ + regs->esp = (unsigned long) frame; + regs->eip = (unsigned long) ka->sa.sa_handler; + regs->eax = (unsigned long) sig; + regs->edx = (unsigned long) 0; + regs->ecx = (unsigned long) 0; + + set_fs(USER_DS); + regs->xds = __USER_DS; + regs->xes = __USER_DS; + regs->xss = __USER_DS; + regs->xcs = __USER_CS; + + /* + * Clear TF when entering the signal handler, but + * notify any tracer that was single-stepping it. + * The tracer may want to single-step inside the + * handler too. + */ + regs->eflags &= ~TF_MASK; + if (test_thread_flag(TIF_SINGLESTEP)) + ptrace_notify(SIGTRAP); + +#if DEBUG_SIG + printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n", + current->comm, current->pid, frame, regs->eip, frame->pretcode); +#endif + + return; + +give_sigsegv: + force_sigsegv(sig, current); +} + +static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, + sigset_t *set, struct pt_regs * regs) +{ + void __user *restorer; + struct rt_sigframe __user *frame; + int err = 0; + int usig; + + frame = get_sigframe(ka, regs, sizeof(*frame)); + + if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) + goto give_sigsegv; + + usig = current_thread_info()->exec_domain + && current_thread_info()->exec_domain->signal_invmap + && sig < 32 + ? current_thread_info()->exec_domain->signal_invmap[sig] + : sig; + + err |= __put_user(usig, &frame->sig); + err |= __put_user(&frame->info, &frame->pinfo); + err |= __put_user(&frame->uc, &frame->puc); + err |= copy_siginfo_to_user(&frame->info, info); + if (err) + goto give_sigsegv; + + /* Create the ucontext. */ + err |= __put_user(0, &frame->uc.uc_flags); + err |= __put_user(0, &frame->uc.uc_link); + err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); + err |= __put_user(sas_ss_flags(regs->esp), + &frame->uc.uc_stack.ss_flags); + err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate, + regs, set->sig[0]); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + if (err) + goto give_sigsegv; + + /* Set up to return from userspace. */ + restorer = &__kernel_rt_sigreturn; + if (ka->sa.sa_flags & SA_RESTORER) + restorer = ka->sa.sa_restorer; + err |= __put_user(restorer, &frame->pretcode); + + /* + * This is movl $,%eax ; int $0x80 + * + * WE DO NOT USE IT ANY MORE! It's only left here for historical + * reasons and because gdb uses it as a signature to notice + * signal handler stack frames. + */ + err |= __put_user(0xb8, (char __user *)(frame->retcode+0)); + err |= __put_user(__NR_rt_sigreturn, (int __user *)(frame->retcode+1)); + err |= __put_user(0x80cd, (short __user *)(frame->retcode+5)); + + if (err) + goto give_sigsegv; + + /* Set up registers for signal handler */ + regs->esp = (unsigned long) frame; + regs->eip = (unsigned long) ka->sa.sa_handler; + regs->eax = (unsigned long) usig; + regs->edx = (unsigned long) &frame->info; + regs->ecx = (unsigned long) &frame->uc; + + set_fs(USER_DS); + regs->xds = __USER_DS; + regs->xes = __USER_DS; + regs->xss = __USER_DS; + regs->xcs = __USER_CS; + + /* + * Clear TF when entering the signal handler, but + * notify any tracer that was single-stepping it. + * The tracer may want to single-step inside the + * handler too. + */ + regs->eflags &= ~TF_MASK; + if (test_thread_flag(TIF_SINGLESTEP)) + ptrace_notify(SIGTRAP); + +#if DEBUG_SIG + printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n", + current->comm, current->pid, frame, regs->eip, frame->pretcode); +#endif + + return; + +give_sigsegv: + force_sigsegv(sig, current); +} + +/* + * OK, we're invoking a handler + */ + +static void +handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, + sigset_t *oldset, struct pt_regs * regs) +{ + /* Are we from a system call? */ + if (regs->orig_eax >= 0) { + /* If so, check system call restarting.. */ + switch (regs->eax) { + case -ERESTART_RESTARTBLOCK: + case -ERESTARTNOHAND: + regs->eax = -EINTR; + break; + + case -ERESTARTSYS: + if (!(ka->sa.sa_flags & SA_RESTART)) { + regs->eax = -EINTR; + break; + } + /* fallthrough */ + case -ERESTARTNOINTR: + regs->eax = regs->orig_eax; + regs->eip -= 2; + } + } + + /* + * If TF is set due to a debugger (PT_DTRACE), clear the TF flag so + * that register information in the sigcontext is correct. + */ + if (unlikely(regs->eflags & TF_MASK) + && likely(current->ptrace & PT_DTRACE)) { + current->ptrace &= ~PT_DTRACE; + regs->eflags &= ~TF_MASK; + } + + /* Set up the stack frame */ + if (ka->sa.sa_flags & SA_SIGINFO) + setup_rt_frame(sig, ka, info, oldset, regs); + else + setup_frame(sig, ka, oldset, regs); + + if (!(ka->sa.sa_flags & SA_NODEFER)) { + spin_lock_irq(&current->sighand->siglock); + sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask); + sigaddset(&current->blocked,sig); + recalc_sigpending(); + spin_unlock_irq(&current->sighand->siglock); + } +} + +/* + * Note that 'init' is a special process: it doesn't get signals it doesn't + * want to handle. Thus you cannot kill init even with a SIGKILL even by + * mistake. + */ +int fastcall do_signal(struct pt_regs *regs, sigset_t *oldset) +{ + siginfo_t info; + int signr; + struct k_sigaction ka; + + /* + * We want the common case to go fast, which + * is why we may in certain cases get here from + * kernel mode. Just return without doing anything + * if so. + */ + if ((regs->xcs & 2) != 2) + return 1; + + if (current->flags & PF_FREEZE) { + refrigerator(0); + goto no_signal; + } + + if (!oldset) + oldset = &current->blocked; + + signr = get_signal_to_deliver(&info, &ka, regs, NULL); + if (signr > 0) { + /* Reenable any watchpoints before delivering the + * signal to user space. The processor register will + * have been cleared if the watchpoint triggered + * inside the kernel. + */ + if (unlikely(current->thread.debugreg[7])) { + loaddebug(&current->thread, 7); + } + + /* Whee! Actually deliver the signal. */ + handle_signal(signr, &info, &ka, oldset, regs); + return 1; + } + + no_signal: + /* Did we come from a system call? */ + if (regs->orig_eax >= 0) { + /* Restart the system call - no handlers present */ + if (regs->eax == -ERESTARTNOHAND || + regs->eax == -ERESTARTSYS || + regs->eax == -ERESTARTNOINTR) { + regs->eax = regs->orig_eax; + regs->eip -= 2; + } + if (regs->eax == -ERESTART_RESTARTBLOCK){ + regs->eax = __NR_restart_syscall; + regs->eip -= 2; + } + } + return 0; +} + +/* + * notification of userspace execution resumption + * - triggered by current->work.notify_resume + */ +__attribute__((regparm(3))) +void do_notify_resume(struct pt_regs *regs, sigset_t *oldset, + __u32 thread_info_flags) +{ + /* Pending single-step? */ + if (thread_info_flags & _TIF_SINGLESTEP) { + regs->eflags |= TF_MASK; + clear_thread_flag(TIF_SINGLESTEP); + } + /* deal with pending signal delivery */ + if (thread_info_flags & _TIF_SIGPENDING) + do_signal(regs,oldset); + + clear_thread_flag(TIF_IRET); +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/smp-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/smp-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,606 @@ +/* + * Intel SMP support routines. + * + * (c) 1995 Alan Cox, Building #3 <alan@xxxxxxxxxx> + * (c) 1998-99, 2000 Ingo Molnar <mingo@xxxxxxxxxx> + * + * This code is released under the GNU General Public License version 2 or + * later. + */ + +#include <linux/init.h> + +#include <linux/mm.h> +#include <linux/irq.h> +#include <linux/delay.h> +#include <linux/spinlock.h> +#include <linux/smp_lock.h> +#include <linux/kernel_stat.h> +#include <linux/mc146818rtc.h> +#include <linux/cache.h> +#include <linux/interrupt.h> +#include <linux/cpu.h> + +#include <asm/mtrr.h> +#include <asm/tlbflush.h> +#if 0 +#include <mach_apic.h> +#endif +#include <xen/evtchn.h> + +/* + * Some notes on x86 processor bugs affecting SMP operation: + * + * Pentium, Pentium Pro, II, III (and all CPUs) have bugs. + * The Linux implications for SMP are handled as follows: + * + * Pentium III / [Xeon] + * None of the E1AP-E3AP errata are visible to the user. + * + * E1AP. see PII A1AP + * E2AP. see PII A2AP + * E3AP. see PII A3AP + * + * Pentium II / [Xeon] + * None of the A1AP-A3AP errata are visible to the user. + * + * A1AP. see PPro 1AP + * A2AP. see PPro 2AP + * A3AP. see PPro 7AP + * + * Pentium Pro + * None of 1AP-9AP errata are visible to the normal user, + * except occasional delivery of 'spurious interrupt' as trap #15. + * This is very rare and a non-problem. + * + * 1AP. Linux maps APIC as non-cacheable + * 2AP. worked around in hardware + * 3AP. fixed in C0 and above steppings microcode update. + * Linux does not use excessive STARTUP_IPIs. + * 4AP. worked around in hardware + * 5AP. symmetric IO mode (normal Linux operation) not affected. + * 'noapic' mode has vector 0xf filled out properly. + * 6AP. 'noapic' mode might be affected - fixed in later steppings + * 7AP. We do not assume writes to the LVT deassering IRQs + * 8AP. We do not enable low power mode (deep sleep) during MP bootup + * 9AP. We do not use mixed mode + * + * Pentium + * There is a marginal case where REP MOVS on 100MHz SMP + * machines with B stepping processors can fail. XXX should provide + * an L1cache=Writethrough or L1cache=off option. + * + * B stepping CPUs may hang. There are hardware work arounds + * for this. We warn about it in case your board doesn't have the work + * arounds. Basically thats so I can tell anyone with a B stepping + * CPU and SMP problems "tough". + * + * Specific items [From Pentium Processor Specification Update] + * + * 1AP. Linux doesn't use remote read + * 2AP. Linux doesn't trust APIC errors + * 3AP. We work around this + * 4AP. Linux never generated 3 interrupts of the same priority + * to cause a lost local interrupt. + * 5AP. Remote read is never used + * 6AP. not affected - worked around in hardware + * 7AP. not affected - worked around in hardware + * 8AP. worked around in hardware - we get explicit CS errors if not + * 9AP. only 'noapic' mode affected. Might generate spurious + * interrupts, we log only the first one and count the + * rest silently. + * 10AP. not affected - worked around in hardware + * 11AP. Linux reads the APIC between writes to avoid this, as per + * the documentation. Make sure you preserve this as it affects + * the C stepping chips too. + * 12AP. not affected - worked around in hardware + * 13AP. not affected - worked around in hardware + * 14AP. we always deassert INIT during bootup + * 15AP. not affected - worked around in hardware + * 16AP. not affected - worked around in hardware + * 17AP. not affected - worked around in hardware + * 18AP. not affected - worked around in hardware + * 19AP. not affected - worked around in BIOS + * + * If this sounds worrying believe me these bugs are either ___RARE___, + * or are signal timing bugs worked around in hardware and there's + * about nothing of note with C stepping upwards. + */ + +DEFINE_PER_CPU(struct tlb_state, cpu_tlbstate) ____cacheline_aligned = { &init_mm, 0, }; + +/* + * the following functions deal with sending IPIs between CPUs. + * + * We use 'broadcast', CPU->CPU IPIs and self-IPIs too. + */ + +static inline int __prepare_ICR (unsigned int shortcut, int vector) +{ + return APIC_DM_FIXED | shortcut | vector | APIC_DEST_LOGICAL; +} + +static inline int __prepare_ICR2 (unsigned int mask) +{ + return SET_APIC_DEST_FIELD(mask); +} + +DECLARE_PER_CPU(int, ipi_to_irq[NR_IPIS]); + +static inline void __send_IPI_one(unsigned int cpu, int vector) +{ + int irq = per_cpu(ipi_to_irq, cpu)[vector]; + BUG_ON(irq < 0); + notify_remote_via_irq(irq); +} + +void __send_IPI_shortcut(unsigned int shortcut, int vector) +{ + int cpu; + + switch (shortcut) { + case APIC_DEST_SELF: + __send_IPI_one(smp_processor_id(), vector); + break; + case APIC_DEST_ALLBUT: + for (cpu = 0; cpu < NR_CPUS; ++cpu) { + if (cpu == smp_processor_id()) + continue; + if (cpu_isset(cpu, cpu_online_map)) { + __send_IPI_one(cpu, vector); + } + } + break; + default: + printk("XXXXXX __send_IPI_shortcut %08x vector %d\n", shortcut, + vector); + break; + } +} + +void fastcall send_IPI_self(int vector) +{ + __send_IPI_shortcut(APIC_DEST_SELF, vector); +} + +/* + * This is only used on smaller machines. + */ +void send_IPI_mask_bitmask(cpumask_t mask, int vector) +{ + unsigned long flags; + unsigned int cpu; + + local_irq_save(flags); + WARN_ON(cpus_addr(mask)[0] & ~cpus_addr(cpu_online_map)[0]); + + for (cpu = 0; cpu < NR_CPUS; ++cpu) { + if (cpu_isset(cpu, mask)) { + __send_IPI_one(cpu, vector); + } + } + + local_irq_restore(flags); +} + +void send_IPI_mask_sequence(cpumask_t mask, int vector) +{ + + send_IPI_mask_bitmask(mask, vector); +} + +#include <mach_ipi.h> /* must come after the send_IPI functions above for inlining */ + +#if 0 /* XEN */ +/* + * Smarter SMP flushing macros. + * c/o Linus Torvalds. + * + * These mean you can really definitely utterly forget about + * writing to user space from interrupts. (Its not allowed anyway). + * + * Optimizations Manfred Spraul <manfred@xxxxxxxxxxxxxxxx> + */ + +static cpumask_t flush_cpumask; +static struct mm_struct * flush_mm; +static unsigned long flush_va; +static DEFINE_SPINLOCK(tlbstate_lock); +#define FLUSH_ALL 0xffffffff + +/* + * We cannot call mmdrop() because we are in interrupt context, + * instead update mm->cpu_vm_mask. + * + * We need to reload %cr3 since the page tables may be going + * away from under us.. + */ +static inline void leave_mm (unsigned long cpu) +{ + if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK) + BUG(); + cpu_clear(cpu, per_cpu(cpu_tlbstate, cpu).active_mm->cpu_vm_mask); + load_cr3(swapper_pg_dir); +} + +/* + * + * The flush IPI assumes that a thread switch happens in this order: + * [cpu0: the cpu that switches] + * 1) switch_mm() either 1a) or 1b) + * 1a) thread switch to a different mm + * 1a1) cpu_clear(cpu, old_mm->cpu_vm_mask); + * Stop ipi delivery for the old mm. This is not synchronized with + * the other cpus, but smp_invalidate_interrupt ignore flush ipis + * for the wrong mm, and in the worst case we perform a superflous + * tlb flush. + * 1a2) set cpu_tlbstate to TLBSTATE_OK + * Now the smp_invalidate_interrupt won't call leave_mm if cpu0 + * was in lazy tlb mode. + * 1a3) update cpu_tlbstate[].active_mm + * Now cpu0 accepts tlb flushes for the new mm. + * 1a4) cpu_set(cpu, new_mm->cpu_vm_mask); + * Now the other cpus will send tlb flush ipis. + * 1a4) change cr3. + * 1b) thread switch without mm change + * cpu_tlbstate[].active_mm is correct, cpu0 already handles + * flush ipis. + * 1b1) set cpu_tlbstate to TLBSTATE_OK + * 1b2) test_and_set the cpu bit in cpu_vm_mask. + * Atomically set the bit [other cpus will start sending flush ipis], + * and test the bit. + * 1b3) if the bit was 0: leave_mm was called, flush the tlb. + * 2) switch %%esp, ie current + * + * The interrupt must handle 2 special cases: + * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm. + * - the cpu performs speculative tlb reads, i.e. even if the cpu only + * runs in kernel space, the cpu could load tlb entries for user space + * pages. + * + * The good news is that cpu_tlbstate is local to each cpu, no + * write/read ordering problems. + */ + +/* + * TLB flush IPI: + * + * 1) Flush the tlb entries if the cpu uses the mm that's being flushed. + * 2) Leave the mm if we are in the lazy tlb mode. + */ + +irqreturn_t smp_invalidate_interrupt(int irq, void *dev_id, + struct pt_regs *regs) +{ + unsigned long cpu; + + cpu = get_cpu(); + + if (!cpu_isset(cpu, flush_cpumask)) + goto out; + /* + * This was a BUG() but until someone can quote me the + * line from the intel manual that guarantees an IPI to + * multiple CPUs is retried _only_ on the erroring CPUs + * its staying as a return + * + * BUG(); + */ + + if (flush_mm == per_cpu(cpu_tlbstate, cpu).active_mm) { + if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK) { + if (flush_va == FLUSH_ALL) + local_flush_tlb(); + else + __flush_tlb_one(flush_va); + } else + leave_mm(cpu); + } + smp_mb__before_clear_bit(); + cpu_clear(cpu, flush_cpumask); + smp_mb__after_clear_bit(); +out: + put_cpu_no_resched(); + + return IRQ_HANDLED; +} + +static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm, + unsigned long va) +{ + /* + * A couple of (to be removed) sanity checks: + * + * - current CPU must not be in mask + * - mask must exist :) + */ + BUG_ON(cpus_empty(cpumask)); + BUG_ON(cpu_isset(smp_processor_id(), cpumask)); + BUG_ON(!mm); + + /* If a CPU which we ran on has gone down, OK. */ + cpus_and(cpumask, cpumask, cpu_online_map); + if (cpus_empty(cpumask)) + return; + + /* + * i'm not happy about this global shared spinlock in the + * MM hot path, but we'll see how contended it is. + * Temporarily this turns IRQs off, so that lockups are + * detected by the NMI watchdog. + */ + spin_lock(&tlbstate_lock); + + flush_mm = mm; + flush_va = va; +#if NR_CPUS <= BITS_PER_LONG + atomic_set_mask(cpumask, &flush_cpumask); +#else + { + int k; + unsigned long *flush_mask = (unsigned long *)&flush_cpumask; + unsigned long *cpu_mask = (unsigned long *)&cpumask; + for (k = 0; k < BITS_TO_LONGS(NR_CPUS); ++k) + atomic_set_mask(cpu_mask[k], &flush_mask[k]); + } +#endif + /* + * We have to send the IPI only to + * CPUs affected. + */ + send_IPI_mask(cpumask, INVALIDATE_TLB_VECTOR); + + while (!cpus_empty(flush_cpumask)) + /* nothing. lockup detection does not belong here */ + mb(); + + flush_mm = NULL; + flush_va = 0; + spin_unlock(&tlbstate_lock); +} + +void flush_tlb_current_task(void) +{ + struct mm_struct *mm = current->mm; + cpumask_t cpu_mask; + + preempt_disable(); + cpu_mask = mm->cpu_vm_mask; + cpu_clear(smp_processor_id(), cpu_mask); + + local_flush_tlb(); + if (!cpus_empty(cpu_mask)) + flush_tlb_others(cpu_mask, mm, FLUSH_ALL); + preempt_enable(); +} + +void flush_tlb_mm (struct mm_struct * mm) +{ + cpumask_t cpu_mask; + + preempt_disable(); + cpu_mask = mm->cpu_vm_mask; + cpu_clear(smp_processor_id(), cpu_mask); + + if (current->active_mm == mm) { + if (current->mm) + local_flush_tlb(); + else + leave_mm(smp_processor_id()); + } + if (!cpus_empty(cpu_mask)) + flush_tlb_others(cpu_mask, mm, FLUSH_ALL); + + preempt_enable(); +} + +void flush_tlb_page(struct vm_area_struct * vma, unsigned long va) +{ + struct mm_struct *mm = vma->vm_mm; + cpumask_t cpu_mask; + + preempt_disable(); + cpu_mask = mm->cpu_vm_mask; + cpu_clear(smp_processor_id(), cpu_mask); + + if (current->active_mm == mm) { + if(current->mm) + __flush_tlb_one(va); + else + leave_mm(smp_processor_id()); + } + + if (!cpus_empty(cpu_mask)) + flush_tlb_others(cpu_mask, mm, va); + + preempt_enable(); +} + +static void do_flush_tlb_all(void* info) +{ + unsigned long cpu = smp_processor_id(); + + __flush_tlb_all(); + if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_LAZY) + leave_mm(cpu); +} + +void flush_tlb_all(void) +{ + on_each_cpu(do_flush_tlb_all, NULL, 1, 1); +} + +#else + +irqreturn_t smp_invalidate_interrupt(int irq, void *dev_id, + struct pt_regs *regs) +{ return 0; } +void flush_tlb_current_task(void) +{ xen_tlb_flush_mask(&current->mm->cpu_vm_mask); } +void flush_tlb_mm(struct mm_struct * mm) +{ xen_tlb_flush_mask(&mm->cpu_vm_mask); } +void flush_tlb_page(struct vm_area_struct *vma, unsigned long va) +{ xen_invlpg_mask(&vma->vm_mm->cpu_vm_mask, va); } +void flush_tlb_all(void) +{ xen_tlb_flush_all(); } + +#endif /* XEN */ + +/* + * this function sends a 'reschedule' IPI to another CPU. + * it goes straight through and wastes no time serializing + * anything. Worst case is that we lose a reschedule ... + */ +void smp_send_reschedule(int cpu) +{ + WARN_ON(cpu_is_offline(cpu)); + send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR); +} + +/* + * Structure and data for smp_call_function(). This is designed to minimise + * static memory requirements. It also looks cleaner. + */ +static DEFINE_SPINLOCK(call_lock); + +struct call_data_struct { + void (*func) (void *info); + void *info; + atomic_t started; + atomic_t finished; + int wait; +}; + +static struct call_data_struct * call_data; + +/* + * this function sends a 'generic call function' IPI to all other CPUs + * in the system. + */ + +int smp_call_function (void (*func) (void *info), void *info, int nonatomic, + int wait) +/* + * [SUMMARY] Run a function on all other CPUs. + * <func> The function to run. This must be fast and non-blocking. + * <info> An arbitrary pointer to pass to the function. + * <nonatomic> currently unused. + * <wait> If true, wait (atomically) until function has completed on other CPUs. + * [RETURNS] 0 on success, else a negative status code. Does not return until + * remote CPUs are nearly ready to execute <<func>> or are or have executed. + * + * You must not call this function with disabled interrupts or from a + * hardware interrupt handler or from a bottom half handler. + */ +{ + struct call_data_struct data; + int cpus; + + /* Holding any lock stops cpus from going down. */ + spin_lock(&call_lock); + cpus = num_online_cpus()-1; + + if (!cpus) { + spin_unlock(&call_lock); + return 0; + } + + /* Can deadlock when called with interrupts disabled */ + WARN_ON(irqs_disabled()); + + data.func = func; + data.info = info; + atomic_set(&data.started, 0); + data.wait = wait; + if (wait) + atomic_set(&data.finished, 0); + + call_data = &data; + mb(); + + /* Send a message to all other CPUs and wait for them to respond */ + send_IPI_allbutself(CALL_FUNCTION_VECTOR); + + /* Wait for response */ + while (atomic_read(&data.started) != cpus) + barrier(); + + if (wait) + while (atomic_read(&data.finished) != cpus) + barrier(); + spin_unlock(&call_lock); + + return 0; +} + +static void stop_this_cpu (void * dummy) +{ + /* + * Remove this CPU: + */ + cpu_clear(smp_processor_id(), cpu_online_map); + local_irq_disable(); +#if 0 + disable_local_APIC(); +#endif + if (cpu_data[smp_processor_id()].hlt_works_ok) + for(;;) __asm__("hlt"); + for (;;); +} + +/* + * this function calls the 'stop' function on all other CPUs in the system. + */ + +void smp_send_stop(void) +{ + smp_call_function(stop_this_cpu, NULL, 1, 0); + + local_irq_disable(); +#if 0 + disable_local_APIC(); +#endif + local_irq_enable(); +} + +/* + * Reschedule call back. Nothing to do, + * all the work is done automatically when + * we return from the interrupt. + */ +irqreturn_t smp_reschedule_interrupt(int irq, void *dev_id, + struct pt_regs *regs) +{ + + return IRQ_HANDLED; +} + +#include <linux/kallsyms.h> +irqreturn_t smp_call_function_interrupt(int irq, void *dev_id, + struct pt_regs *regs) +{ + void (*func) (void *info) = call_data->func; + void *info = call_data->info; + int wait = call_data->wait; + + /* + * Notify initiating CPU that I've grabbed the data and am + * about to execute the function + */ + mb(); + atomic_inc(&call_data->started); + /* + * At this point the info structure may be out of scope unless wait==1 + */ + irq_enter(); + (*func)(info); + irq_exit(); + + if (wait) { + mb(); + atomic_inc(&call_data->finished); + } + + return IRQ_HANDLED; +} + diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/smpalts.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/smpalts.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,85 @@ +#include <linux/kernel.h> +#include <asm/system.h> +#include <asm/smp_alt.h> +#include <asm/processor.h> +#include <asm/string.h> + +struct smp_replacement_record { + unsigned char targ_size; + unsigned char smp1_size; + unsigned char smp2_size; + unsigned char up_size; + unsigned char feature; + unsigned char data[0]; +}; + +struct smp_alternative_record { + void *targ_start; + struct smp_replacement_record *repl; +}; + +extern struct smp_alternative_record __start_smp_alternatives_table, + __stop_smp_alternatives_table; +extern unsigned long __init_begin, __init_end; + +void prepare_for_smp(void) +{ + struct smp_alternative_record *r; + printk(KERN_INFO "Enabling SMP...\n"); + for (r = &__start_smp_alternatives_table; + r != &__stop_smp_alternatives_table; + r++) { + BUG_ON(r->repl->targ_size < r->repl->smp1_size); + BUG_ON(r->repl->targ_size < r->repl->smp2_size); + BUG_ON(r->repl->targ_size < r->repl->up_size); + if (system_state == SYSTEM_RUNNING && + r->targ_start >= (void *)&__init_begin && + r->targ_start < (void *)&__init_end) + continue; + if (r->repl->feature != (unsigned char)-1 && + boot_cpu_has(r->repl->feature)) { + memcpy(r->targ_start, + r->repl->data + r->repl->smp1_size, + r->repl->smp2_size); + memset(r->targ_start + r->repl->smp2_size, + 0x90, + r->repl->targ_size - r->repl->smp2_size); + } else { + memcpy(r->targ_start, + r->repl->data, + r->repl->smp1_size); + memset(r->targ_start + r->repl->smp1_size, + 0x90, + r->repl->targ_size - r->repl->smp1_size); + } + } + /* Paranoia */ + asm volatile ("jmp 1f\n1:"); + mb(); +} + +void unprepare_for_smp(void) +{ + struct smp_alternative_record *r; + printk(KERN_INFO "Disabling SMP...\n"); + for (r = &__start_smp_alternatives_table; + r != &__stop_smp_alternatives_table; + r++) { + BUG_ON(r->repl->targ_size < r->repl->smp1_size); + BUG_ON(r->repl->targ_size < r->repl->smp2_size); + BUG_ON(r->repl->targ_size < r->repl->up_size); + if (system_state == SYSTEM_RUNNING && + r->targ_start >= (void *)&__init_begin && + r->targ_start < (void *)&__init_end) + continue; + memcpy(r->targ_start, + r->repl->data + r->repl->smp1_size + r->repl->smp2_size, + r->repl->up_size); + memset(r->targ_start + r->repl->up_size, + 0x90, + r->repl->targ_size - r->repl->up_size); + } + /* Paranoia */ + asm volatile ("jmp 1f\n1:"); + mb(); +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/smpboot.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/smpboot.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,1182 @@ +/* + * x86 SMP booting functions + * + * (c) 1995 Alan Cox, Building #3 <alan@xxxxxxxxxx> + * (c) 1998, 1999, 2000 Ingo Molnar <mingo@xxxxxxxxxx> + * + * Much of the core SMP work is based on previous work by Thomas Radke, to + * whom a great many thanks are extended. + * + * Thanks to Intel for making available several different Pentium, + * Pentium Pro and Pentium-II/Xeon MP machines. + * Original development of Linux SMP code supported by Caldera. + * + * This code is released under the GNU General Public License version 2 or + * later. + * + * Fixes + * Felix Koop : NR_CPUS used properly + * Jose Renau : Handle single CPU case. + * Alan Cox : By repeated request 8) - Total BogoMIPS report. + * Greg Wright : Fix for kernel stacks panic. + * Erich Boleyn : MP v1.4 and additional changes. + * Matthias Sattler : Changes for 2.1 kernel map. + * Michel Lespinasse : Changes for 2.1 kernel map. + * Michael Chastain : Change trampoline.S to gnu as. + * Alan Cox : Dumb bug: 'B' step PPro's are fine + * Ingo Molnar : Added APIC timers, based on code + * from Jose Renau + * Ingo Molnar : various cleanups and rewrites + * Tigran Aivazian : fixed "0.00 in /proc/uptime on SMP" bug. + * Maciej W. Rozycki : Bits for genuine 82489DX APICs + * Martin J. Bligh : Added support for multi-quad systems + * Dave Jones : Report invalid combinations of Athlon CPUs. +* Rusty Russell : Hacked into shape for new "hotplug" boot process. */ + +#include <linux/module.h> +#include <linux/config.h> +#include <linux/init.h> +#include <linux/kernel.h> + +#include <linux/mm.h> +#include <linux/sched.h> +#include <linux/kernel_stat.h> +#include <linux/smp_lock.h> +#include <linux/irq.h> +#include <linux/bootmem.h> + +#include <linux/delay.h> +#include <linux/mc146818rtc.h> +#include <asm/tlbflush.h> +#include <asm/desc.h> +#include <asm/arch_hooks.h> + +#include <mach_apic.h> +#include <mach_wakecpu.h> +#include <smpboot_hooks.h> + +/* Set if we find a B stepping CPU */ +static int __initdata smp_b_stepping; + +/* Number of siblings per CPU package */ +int smp_num_siblings = 1; +int phys_proc_id[NR_CPUS]; /* Package ID of each logical CPU */ +EXPORT_SYMBOL(phys_proc_id); +int cpu_core_id[NR_CPUS]; /* Core ID of each logical CPU */ +EXPORT_SYMBOL(cpu_core_id); + +/* bitmap of online cpus */ +cpumask_t cpu_online_map; + +cpumask_t cpu_callin_map; +cpumask_t cpu_callout_map; +static cpumask_t smp_commenced_mask; + +/* Per CPU bogomips and other parameters */ +struct cpuinfo_x86 cpu_data[NR_CPUS] __cacheline_aligned; + +u8 x86_cpu_to_apicid[NR_CPUS] = + { [0 ... NR_CPUS-1] = 0xff }; +EXPORT_SYMBOL(x86_cpu_to_apicid); + +/* + * Trampoline 80x86 program as an array. + */ + +extern unsigned char trampoline_data []; +extern unsigned char trampoline_end []; +static unsigned char *trampoline_base; +static int trampoline_exec; + +static void map_cpu_to_logical_apicid(void); + +/* + * Currently trivial. Write the real->protected mode + * bootstrap into the page concerned. The caller + * has made sure it's suitably aligned. + */ + +static unsigned long __init setup_trampoline(void) +{ + memcpy(trampoline_base, trampoline_data, trampoline_end - trampoline_data); + return virt_to_phys(trampoline_base); +} + +/* + * We are called very early to get the low memory for the + * SMP bootup trampoline page. + */ +void __init smp_alloc_memory(void) +{ + trampoline_base = (void *) alloc_bootmem_low_pages(PAGE_SIZE); + /* + * Has to be in very low memory so we can execute + * real-mode AP code. + */ + if (__pa(trampoline_base) >= 0x9F000) + BUG(); + /* + * Make the SMP trampoline executable: + */ + trampoline_exec = set_kernel_exec((unsigned long)trampoline_base, 1); +} + +/* + * The bootstrap kernel entry code has set these up. Save them for + * a given CPU + */ + +static void __init smp_store_cpu_info(int id) +{ + struct cpuinfo_x86 *c = cpu_data + id; + + *c = boot_cpu_data; + if (id!=0) + identify_cpu(c); + /* + * Mask B, Pentium, but not Pentium MMX + */ + if (c->x86_vendor == X86_VENDOR_INTEL && + c->x86 == 5 && + c->x86_mask >= 1 && c->x86_mask <= 4 && + c->x86_model <= 3) + /* + * Remember we have B step Pentia with bugs + */ + smp_b_stepping = 1; + + /* + * Certain Athlons might work (for various values of 'work') in SMP + * but they are not certified as MP capable. + */ + if ((c->x86_vendor == X86_VENDOR_AMD) && (c->x86 == 6)) { + + /* Athlon 660/661 is valid. */ + if ((c->x86_model==6) && ((c->x86_mask==0) || (c->x86_mask==1))) + goto valid_k7; + + /* Duron 670 is valid */ + if ((c->x86_model==7) && (c->x86_mask==0)) + goto valid_k7; + + /* + * Athlon 662, Duron 671, and Athlon >model 7 have capability bit. + * It's worth noting that the A5 stepping (662) of some Athlon XP's + * have the MP bit set. + * See http://www.heise.de/newsticker/data/jow-18.10.01-000 for more. + */ + if (((c->x86_model==6) && (c->x86_mask>=2)) || + ((c->x86_model==7) && (c->x86_mask>=1)) || + (c->x86_model> 7)) + if (cpu_has_mp) + goto valid_k7; + + /* If we get here, it's not a certified SMP capable AMD system. */ + tainted |= TAINT_UNSAFE_SMP; + } + +valid_k7: + ; +} + +/* + * TSC synchronization. + * + * We first check whether all CPUs have their TSC's synchronized, + * then we print a warning if not, and always resync. + */ + +static atomic_t tsc_start_flag = ATOMIC_INIT(0); +static atomic_t tsc_count_start = ATOMIC_INIT(0); +static atomic_t tsc_count_stop = ATOMIC_INIT(0); +static unsigned long long tsc_values[NR_CPUS]; + +#define NR_LOOPS 5 + +static void __init synchronize_tsc_bp (void) +{ + int i; + unsigned long long t0; + unsigned long long sum, avg; + long long delta; + unsigned long one_usec; + int buggy = 0; + + printk(KERN_INFO "checking TSC synchronization across %u CPUs: ", num_booting_cpus()); + + /* convert from kcyc/sec to cyc/usec */ + one_usec = cpu_khz / 1000; + + atomic_set(&tsc_start_flag, 1); + wmb(); + + /* + * We loop a few times to get a primed instruction cache, + * then the last pass is more or less synchronized and + * the BP and APs set their cycle counters to zero all at + * once. This reduces the chance of having random offsets + * between the processors, and guarantees that the maximum + * delay between the cycle counters is never bigger than + * the latency of information-passing (cachelines) between + * two CPUs. + */ + for (i = 0; i < NR_LOOPS; i++) { + /* + * all APs synchronize but they loop on '== num_cpus' + */ + while (atomic_read(&tsc_count_start) != num_booting_cpus()-1) + mb(); + atomic_set(&tsc_count_stop, 0); + wmb(); + /* + * this lets the APs save their current TSC: + */ + atomic_inc(&tsc_count_start); + + rdtscll(tsc_values[smp_processor_id()]); + /* + * We clear the TSC in the last loop: + */ + if (i == NR_LOOPS-1) + write_tsc(0, 0); + + /* + * Wait for all APs to leave the synchronization point: + */ + while (atomic_read(&tsc_count_stop) != num_booting_cpus()-1) + mb(); + atomic_set(&tsc_count_start, 0); + wmb(); + atomic_inc(&tsc_count_stop); + } + + sum = 0; + for (i = 0; i < NR_CPUS; i++) { + if (cpu_isset(i, cpu_callout_map)) { + t0 = tsc_values[i]; + sum += t0; + } + } + avg = sum; + do_div(avg, num_booting_cpus()); + + sum = 0; + for (i = 0; i < NR_CPUS; i++) { + if (!cpu_isset(i, cpu_callout_map)) + continue; + delta = tsc_values[i] - avg; + if (delta < 0) + delta = -delta; + /* + * We report bigger than 2 microseconds clock differences. + */ + if (delta > 2*one_usec) { + long realdelta; + if (!buggy) { + buggy = 1; + printk("\n"); + } + realdelta = delta; + do_div(realdelta, one_usec); + if (tsc_values[i] < avg) + realdelta = -realdelta; + + printk(KERN_INFO "CPU#%d had %ld usecs TSC skew, fixed it up.\n", i, realdelta); + } + + sum += delta; + } + if (!buggy) + printk("passed.\n"); +} + +static void __init synchronize_tsc_ap (void) +{ + int i; + + /* + * Not every cpu is online at the time + * this gets called, so we first wait for the BP to + * finish SMP initialization: + */ + while (!atomic_read(&tsc_start_flag)) mb(); + + for (i = 0; i < NR_LOOPS; i++) { + atomic_inc(&tsc_count_start); + while (atomic_read(&tsc_count_start) != num_booting_cpus()) + mb(); + + rdtscll(tsc_values[smp_processor_id()]); + if (i == NR_LOOPS-1) + write_tsc(0, 0); + + atomic_inc(&tsc_count_stop); + while (atomic_read(&tsc_count_stop) != num_booting_cpus()) mb(); + } +} +#undef NR_LOOPS + +extern void calibrate_delay(void); + +static atomic_t init_deasserted; + +static void __init smp_callin(void) +{ + int cpuid, phys_id; + unsigned long timeout; + + /* + * If waken up by an INIT in an 82489DX configuration + * we may get here before an INIT-deassert IPI reaches + * our local APIC. We have to wait for the IPI or we'll + * lock up on an APIC access. + */ + wait_for_init_deassert(&init_deasserted); + + /* + * (This works even if the APIC is not enabled.) + */ + phys_id = GET_APIC_ID(apic_read(APIC_ID)); + cpuid = smp_processor_id(); + if (cpu_isset(cpuid, cpu_callin_map)) { + printk("huh, phys CPU#%d, CPU#%d already present??\n", + phys_id, cpuid); + BUG(); + } + Dprintk("CPU#%d (phys ID: %d) waiting for CALLOUT\n", cpuid, phys_id); + + /* + * STARTUP IPIs are fragile beasts as they might sometimes + * trigger some glue motherboard logic. Complete APIC bus + * silence for 1 second, this overestimates the time the + * boot CPU is spending to send the up to 2 STARTUP IPIs + * by a factor of two. This should be enough. + */ + + /* + * Waiting 2s total for startup (udelay is not yet working) + */ + timeout = jiffies + 2*HZ; + while (time_before(jiffies, timeout)) { + /* + * Has the boot CPU finished it's STARTUP sequence? + */ + if (cpu_isset(cpuid, cpu_callout_map)) + break; + rep_nop(); + } + + if (!time_before(jiffies, timeout)) { + printk("BUG: CPU%d started up but did not get a callout!\n", + cpuid); + BUG(); + } + + /* + * the boot CPU has finished the init stage and is spinning + * on callin_map until we finish. We are free to set up this + * CPU, first the APIC. (this is probably redundant on most + * boards) + */ + + Dprintk("CALLIN, before setup_local_APIC().\n"); + smp_callin_clear_local_apic(); + setup_local_APIC(); + map_cpu_to_logical_apicid(); + + /* + * Get our bogomips. + */ + calibrate_delay(); + Dprintk("Stack at about %p\n",&cpuid); + + /* + * Save our processor parameters + */ + smp_store_cpu_info(cpuid); + + disable_APIC_timer(); + + /* + * Allow the master to continue. + */ + cpu_set(cpuid, cpu_callin_map); + + /* + * Synchronize the TSC with the BP + */ + if (cpu_has_tsc && cpu_khz) + synchronize_tsc_ap(); +} + +static int cpucount; + +/* + * Activate a secondary processor. + */ +static void __init start_secondary(void *unused) +{ + /* + * Dont put anything before smp_callin(), SMP + * booting is too fragile that we want to limit the + * things done here to the most necessary things. + */ + cpu_init(); + smp_callin(); + while (!cpu_isset(smp_processor_id(), smp_commenced_mask)) + rep_nop(); + setup_secondary_APIC_clock(); + if (nmi_watchdog == NMI_IO_APIC) { + disable_8259A_irq(0); + enable_NMI_through_LVT0(NULL); + enable_8259A_irq(0); + } + enable_APIC_timer(); + /* + * low-memory mappings have been cleared, flush them from + * the local TLBs too. + */ + local_flush_tlb(); + cpu_set(smp_processor_id(), cpu_online_map); + + /* We can take interrupts now: we're officially "up". */ + local_irq_enable(); + + wmb(); + cpu_idle(); +} + +/* + * Everything has been set up for the secondary + * CPUs - they just need to reload everything + * from the task structure + * This function must not return. + */ +void __init initialize_secondary(void) +{ + /* + * We don't actually need to load the full TSS, + * basically just the stack pointer and the eip. + */ + + asm volatile( + "movl %0,%%esp\n\t" + "jmp *%1" + : + :"r" (current->thread.esp),"r" (current->thread.eip)); +} + +extern struct { + void * esp; + unsigned short ss; +} stack_start; + +#ifdef CONFIG_NUMA + +/* which logical CPUs are on which nodes */ +cpumask_t node_2_cpu_mask[MAX_NUMNODES] = + { [0 ... MAX_NUMNODES-1] = CPU_MASK_NONE }; +/* which node each logical CPU is on */ +int cpu_2_node[NR_CPUS] = { [0 ... NR_CPUS-1] = 0 }; +EXPORT_SYMBOL(cpu_2_node); + +/* set up a mapping between cpu and node. */ +static inline void map_cpu_to_node(int cpu, int node) +{ + printk("Mapping cpu %d to node %d\n", cpu, node); + cpu_set(cpu, node_2_cpu_mask[node]); + cpu_2_node[cpu] = node; +} + +/* undo a mapping between cpu and node. */ +static inline void unmap_cpu_to_node(int cpu) +{ + int node; + + printk("Unmapping cpu %d from all nodes\n", cpu); + for (node = 0; node < MAX_NUMNODES; node ++) + cpu_clear(cpu, node_2_cpu_mask[node]); + cpu_2_node[cpu] = 0; +} +#else /* !CONFIG_NUMA */ + +#define map_cpu_to_node(cpu, node) ({}) +#define unmap_cpu_to_node(cpu) ({}) + +#endif /* CONFIG_NUMA */ + +u8 cpu_2_logical_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; + +static void map_cpu_to_logical_apicid(void) +{ + int cpu = smp_processor_id(); + int apicid = logical_smp_processor_id(); + + cpu_2_logical_apicid[cpu] = apicid; + map_cpu_to_node(cpu, apicid_to_node(apicid)); +} + +static void unmap_cpu_to_logical_apicid(int cpu) +{ + cpu_2_logical_apicid[cpu] = BAD_APICID; + unmap_cpu_to_node(cpu); +} + +#if APIC_DEBUG +static inline void __inquire_remote_apic(int apicid) +{ + int i, regs[] = { APIC_ID >> 4, APIC_LVR >> 4, APIC_SPIV >> 4 }; + char *names[] = { "ID", "VERSION", "SPIV" }; + int timeout, status; + + printk("Inquiring remote APIC #%d...\n", apicid); + + for (i = 0; i < sizeof(regs) / sizeof(*regs); i++) { + printk("... APIC #%d %s: ", apicid, names[i]); + + /* + * Wait for idle. + */ + apic_wait_icr_idle(); + + apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(apicid)); + apic_write_around(APIC_ICR, APIC_DM_REMRD | regs[i]); + + timeout = 0; + do { + udelay(100); + status = apic_read(APIC_ICR) & APIC_ICR_RR_MASK; + } while (status == APIC_ICR_RR_INPROG && timeout++ < 1000); + + switch (status) { + case APIC_ICR_RR_VALID: + status = apic_read(APIC_RRR); + printk("%08x\n", status); + break; + default: + printk("failed\n"); + } + } +} +#endif + +#ifdef WAKE_SECONDARY_VIA_NMI +/* + * Poke the other CPU in the eye via NMI to wake it up. Remember that the normal + * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this + * won't ... remember to clear down the APIC, etc later. + */ +static int __init +wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip) +{ + unsigned long send_status = 0, accept_status = 0; + int timeout, maxlvt; + + /* Target chip */ + apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(logical_apicid)); + + /* Boot on the stack */ + /* Kick the second */ + apic_write_around(APIC_ICR, APIC_DM_NMI | APIC_DEST_LOGICAL); + + Dprintk("Waiting for send to finish...\n"); + timeout = 0; + do { + Dprintk("+"); + udelay(100); + send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY; + } while (send_status && (timeout++ < 1000)); + + /* + * Give the other CPU some time to accept the IPI. + */ + udelay(200); + /* + * Due to the Pentium erratum 3AP. + */ + maxlvt = get_maxlvt(); + if (maxlvt > 3) { + apic_read_around(APIC_SPIV); + apic_write(APIC_ESR, 0); + } + accept_status = (apic_read(APIC_ESR) & 0xEF); + Dprintk("NMI sent.\n"); + + if (send_status) + printk("APIC never delivered???\n"); + if (accept_status) + printk("APIC delivery error (%lx).\n", accept_status); + + return (send_status | accept_status); +} +#endif /* WAKE_SECONDARY_VIA_NMI */ + +#ifdef WAKE_SECONDARY_VIA_INIT +static int __init +wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip) +{ + unsigned long send_status = 0, accept_status = 0; + int maxlvt, timeout, num_starts, j; + + /* + * Be paranoid about clearing APIC errors. + */ + if (APIC_INTEGRATED(apic_version[phys_apicid])) { + apic_read_around(APIC_SPIV); + apic_write(APIC_ESR, 0); + apic_read(APIC_ESR); + } + + Dprintk("Asserting INIT.\n"); + + /* + * Turn INIT on target chip + */ + apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid)); + + /* + * Send IPI + */ + apic_write_around(APIC_ICR, APIC_INT_LEVELTRIG | APIC_INT_ASSERT + | APIC_DM_INIT); + + Dprintk("Waiting for send to finish...\n"); + timeout = 0; + do { + Dprintk("+"); + udelay(100); + send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY; + } while (send_status && (timeout++ < 1000)); + + mdelay(10); + + Dprintk("Deasserting INIT.\n"); + + /* Target chip */ + apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid)); + + /* Send IPI */ + apic_write_around(APIC_ICR, APIC_INT_LEVELTRIG | APIC_DM_INIT); + + Dprintk("Waiting for send to finish...\n"); + timeout = 0; + do { + Dprintk("+"); + udelay(100); + send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY; + } while (send_status && (timeout++ < 1000)); + + atomic_set(&init_deasserted, 1); + + /* + * Should we send STARTUP IPIs ? + * + * Determine this based on the APIC version. + * If we don't have an integrated APIC, don't send the STARTUP IPIs. + */ + if (APIC_INTEGRATED(apic_version[phys_apicid])) + num_starts = 2; + else + num_starts = 0; + + /* + * Run STARTUP IPI loop. + */ + Dprintk("#startup loops: %d.\n", num_starts); + + maxlvt = get_maxlvt(); + + for (j = 1; j <= num_starts; j++) { + Dprintk("Sending STARTUP #%d.\n",j); + apic_read_around(APIC_SPIV); + apic_write(APIC_ESR, 0); + apic_read(APIC_ESR); + Dprintk("After apic_write.\n"); + + /* + * STARTUP IPI + */ + + /* Target chip */ + apic_write_around(APIC_ICR2, SET_APIC_DEST_FIELD(phys_apicid)); + + /* Boot on the stack */ + /* Kick the second */ + apic_write_around(APIC_ICR, APIC_DM_STARTUP + | (start_eip >> 12)); + + /* + * Give the other CPU some time to accept the IPI. + */ + udelay(300); + + Dprintk("Startup point 1.\n"); + + Dprintk("Waiting for send to finish...\n"); + timeout = 0; + do { + Dprintk("+"); + udelay(100); + send_status = apic_read(APIC_ICR) & APIC_ICR_BUSY; + } while (send_status && (timeout++ < 1000)); + + /* + * Give the other CPU some time to accept the IPI. + */ + udelay(200); + /* + * Due to the Pentium erratum 3AP. + */ + if (maxlvt > 3) { + apic_read_around(APIC_SPIV); + apic_write(APIC_ESR, 0); + } + accept_status = (apic_read(APIC_ESR) & 0xEF); + if (send_status || accept_status) + break; + } + Dprintk("After Startup.\n"); + + if (send_status) + printk("APIC never delivered???\n"); + if (accept_status) + printk("APIC delivery error (%lx).\n", accept_status); + + return (send_status | accept_status); +} +#endif /* WAKE_SECONDARY_VIA_INIT */ + +extern cpumask_t cpu_initialized; + +static int __init do_boot_cpu(int apicid) +/* + * NOTE - on most systems this is a PHYSICAL apic ID, but on multiquad + * (ie clustered apic addressing mode), this is a LOGICAL apic ID. + * Returns zero if CPU booted OK, else error code from wakeup_secondary_cpu. + */ +{ + struct task_struct *idle; + unsigned long boot_error; + int timeout, cpu; + unsigned long start_eip; + unsigned short nmi_high = 0, nmi_low = 0; + + cpu = ++cpucount; + /* + * We can't use kernel_thread since we must avoid to + * reschedule the child. + */ + idle = fork_idle(cpu); + if (IS_ERR(idle)) + panic("failed fork for CPU %d", cpu); + idle->thread.eip = (unsigned long) start_secondary; + /* start_eip had better be page-aligned! */ + start_eip = setup_trampoline(); + + /* So we see what's up */ + printk("Booting processor %d/%d eip %lx\n", cpu, apicid, start_eip); + /* Stack for startup_32 can be just as for start_secondary onwards */ + stack_start.esp = (void *) idle->thread.esp; + + irq_ctx_init(cpu); + + /* + * This grunge runs the startup process for + * the targeted processor. + */ + + atomic_set(&init_deasserted, 0); + + Dprintk("Setting warm reset code and vector.\n"); + + store_NMI_vector(&nmi_high, &nmi_low); + + smpboot_setup_warm_reset_vector(start_eip); + + /* + * Starting actual IPI sequence... + */ + boot_error = wakeup_secondary_cpu(apicid, start_eip); + + if (!boot_error) { + /* + * allow APs to start initializing. + */ + Dprintk("Before Callout %d.\n", cpu); + cpu_set(cpu, cpu_callout_map); + Dprintk("After Callout %d.\n", cpu); + + /* + * Wait 5s total for a response + */ + for (timeout = 0; timeout < 50000; timeout++) { + if (cpu_isset(cpu, cpu_callin_map)) + break; /* It has booted */ + udelay(100); + } + + if (cpu_isset(cpu, cpu_callin_map)) { + /* number CPUs logically, starting from 1 (BSP is 0) */ + Dprintk("OK.\n"); + printk("CPU%d: ", cpu); + print_cpu_info(&cpu_data[cpu]); + Dprintk("CPU has booted.\n"); + } else { + boot_error= 1; + if (*((volatile unsigned char *)trampoline_base) + == 0xA5) + /* trampoline started but...? */ + printk("Stuck ??\n"); + else + /* trampoline code not run */ + printk("Not responding.\n"); + inquire_remote_apic(apicid); + } + } + x86_cpu_to_apicid[cpu] = apicid; + if (boot_error) { + /* Try to put things back the way they were before ... */ + unmap_cpu_to_logical_apicid(cpu); + cpu_clear(cpu, cpu_callout_map); /* was set here (do_boot_cpu()) */ + cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */ + cpucount--; + } + + /* mark "stuck" area as not stuck */ + *((volatile unsigned long *)trampoline_base) = 0; + + return boot_error; +} + +static void smp_tune_scheduling (void) +{ + unsigned long cachesize; /* kB */ + unsigned long bandwidth = 350; /* MB/s */ + /* + * Rough estimation for SMP scheduling, this is the number of + * cycles it takes for a fully memory-limited process to flush + * the SMP-local cache. + * + * (For a P5 this pretty much means we will choose another idle + * CPU almost always at wakeup time (this is due to the small + * L1 cache), on PIIs it's around 50-100 usecs, depending on + * the cache size) + */ + + if (!cpu_khz) { + /* + * this basically disables processor-affinity + * scheduling on SMP without a TSC. + */ + return; + } else { + cachesize = boot_cpu_data.x86_cache_size; + if (cachesize == -1) { + cachesize = 16; /* Pentiums, 2x8kB cache */ + bandwidth = 100; + } + } +} + +/* + * Cycle through the processors sending APIC IPIs to boot each. + */ + +static int boot_cpu_logical_apicid; +/* Where the IO area was mapped on multiquad, always 0 otherwise */ +void *xquad_portio; + +cpumask_t cpu_sibling_map[NR_CPUS] __cacheline_aligned; +cpumask_t cpu_core_map[NR_CPUS] __cacheline_aligned; +EXPORT_SYMBOL(cpu_core_map); + +static void __init smp_boot_cpus(unsigned int max_cpus) +{ + int apicid, cpu, bit, kicked; + unsigned long bogosum = 0; + + /* + * Setup boot CPU information + */ + smp_store_cpu_info(0); /* Final full version of the data */ + printk("CPU%d: ", 0); + print_cpu_info(&cpu_data[0]); + + boot_cpu_physical_apicid = GET_APIC_ID(apic_read(APIC_ID)); + boot_cpu_logical_apicid = logical_smp_processor_id(); + x86_cpu_to_apicid[0] = boot_cpu_physical_apicid; + + current_thread_info()->cpu = 0; + smp_tune_scheduling(); + cpus_clear(cpu_sibling_map[0]); + cpu_set(0, cpu_sibling_map[0]); + + cpus_clear(cpu_core_map[0]); + cpu_set(0, cpu_core_map[0]); + + /* + * If we couldn't find an SMP configuration at boot time, + * get out of here now! + */ + if (!smp_found_config && !acpi_lapic) { + printk(KERN_NOTICE "SMP motherboard not detected.\n"); + smpboot_clear_io_apic_irqs(); + phys_cpu_present_map = physid_mask_of_physid(0); + if (APIC_init_uniprocessor()) + printk(KERN_NOTICE "Local APIC not detected." + " Using dummy APIC emulation.\n"); + map_cpu_to_logical_apicid(); + cpu_set(0, cpu_sibling_map[0]); + cpu_set(0, cpu_core_map[0]); + return; + } + + /* + * Should not be necessary because the MP table should list the boot + * CPU too, but we do it for the sake of robustness anyway. + * Makes no sense to do this check in clustered apic mode, so skip it + */ + if (!check_phys_apicid_present(boot_cpu_physical_apicid)) { + printk("weird, boot CPU (#%d) not listed by the BIOS.\n", + boot_cpu_physical_apicid); + physid_set(hard_smp_processor_id(), phys_cpu_present_map); + } + + /* + * If we couldn't find a local APIC, then get out of here now! + */ + if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid]) && !cpu_has_apic) { + printk(KERN_ERR "BIOS bug, local APIC #%d not detected!...\n", + boot_cpu_physical_apicid); + printk(KERN_ERR "... forcing use of dummy APIC emulation. (tell your hw vendor)\n"); + smpboot_clear_io_apic_irqs(); + phys_cpu_present_map = physid_mask_of_physid(0); + cpu_set(0, cpu_sibling_map[0]); + cpu_set(0, cpu_core_map[0]); + return; + } + + verify_local_APIC(); + + /* + * If SMP should be disabled, then really disable it! + */ + if (!max_cpus) { + smp_found_config = 0; + printk(KERN_INFO "SMP mode deactivated, forcing use of dummy APIC emulation.\n"); + smpboot_clear_io_apic_irqs(); + phys_cpu_present_map = physid_mask_of_physid(0); + cpu_set(0, cpu_sibling_map[0]); + cpu_set(0, cpu_core_map[0]); + return; + } + + connect_bsp_APIC(); + setup_local_APIC(); + map_cpu_to_logical_apicid(); + + + setup_portio_remap(); + + /* + * Scan the CPU present map and fire up the other CPUs via do_boot_cpu + * + * In clustered apic mode, phys_cpu_present_map is a constructed thus: + * bits 0-3 are quad0, 4-7 are quad1, etc. A perverse twist on the + * clustered apic ID. + */ + Dprintk("CPU present map: %lx\n", physids_coerce(phys_cpu_present_map)); + + kicked = 1; + for (bit = 0; kicked < NR_CPUS && bit < MAX_APICS; bit++) { + apicid = cpu_present_to_apicid(bit); + /* + * Don't even attempt to start the boot CPU! + */ + if ((apicid == boot_cpu_apicid) || (apicid == BAD_APICID)) + continue; + + if (!check_apicid_present(bit)) + continue; + if (max_cpus <= cpucount+1) + continue; + +#ifdef CONFIG_SMP_ALTERNATIVES + if (kicked == 1) + prepare_for_smp(); +#endif + + if (do_boot_cpu(apicid)) + printk("CPU #%d not responding - cannot use it.\n", + apicid); + else + ++kicked; + } + + /* + * Cleanup possible dangling ends... + */ + smpboot_restore_warm_reset_vector(); + + /* + * Allow the user to impress friends. + */ + Dprintk("Before bogomips.\n"); + for (cpu = 0; cpu < NR_CPUS; cpu++) + if (cpu_isset(cpu, cpu_callout_map)) + bogosum += cpu_data[cpu].loops_per_jiffy; + printk(KERN_INFO + "Total of %d processors activated (%lu.%02lu BogoMIPS).\n", + cpucount+1, + bogosum/(500000/HZ), + (bogosum/(5000/HZ))%100); + + Dprintk("Before bogocount - setting activated=1.\n"); + + if (smp_b_stepping) + printk(KERN_WARNING "WARNING: SMP operation may be unreliable with B stepping processors.\n"); + + /* + * Don't taint if we are running SMP kernel on a single non-MP + * approved Athlon + */ + if (tainted & TAINT_UNSAFE_SMP) { + if (cpucount) + printk (KERN_INFO "WARNING: This combination of AMD processors is not suitable for SMP.\n"); + else + tainted &= ~TAINT_UNSAFE_SMP; + } + + Dprintk("Boot done.\n"); + + /* + * construct cpu_sibling_map[], so that we can tell sibling CPUs + * efficiently. + */ + for (cpu = 0; cpu < NR_CPUS; cpu++) { + cpus_clear(cpu_sibling_map[cpu]); + cpus_clear(cpu_core_map[cpu]); + } + + for (cpu = 0; cpu < NR_CPUS; cpu++) { + struct cpuinfo_x86 *c = cpu_data + cpu; + int siblings = 0; + int i; + if (!cpu_isset(cpu, cpu_callout_map)) + continue; + + if (smp_num_siblings > 1) { + for (i = 0; i < NR_CPUS; i++) { + if (!cpu_isset(i, cpu_callout_map)) + continue; + if (cpu_core_id[cpu] == cpu_core_id[i]) { + siblings++; + cpu_set(i, cpu_sibling_map[cpu]); + } + } + } else { + siblings++; + cpu_set(cpu, cpu_sibling_map[cpu]); + } + + if (siblings != smp_num_siblings) { + printk(KERN_WARNING "WARNING: %d siblings found for CPU%d, should be %d\n", siblings, cpu, smp_num_siblings); + smp_num_siblings = siblings; + } + + if (c->x86_num_cores > 1) { + for (i = 0; i < NR_CPUS; i++) { + if (!cpu_isset(i, cpu_callout_map)) + continue; + if (phys_proc_id[cpu] == phys_proc_id[i]) { + cpu_set(i, cpu_core_map[cpu]); + } + } + } else { + cpu_core_map[cpu] = cpu_sibling_map[cpu]; + } + } + + smpboot_setup_io_apic(); + + setup_boot_APIC_clock(); + + /* + * Synchronize the TSC with the AP + */ + if (cpu_has_tsc && cpucount && cpu_khz) + synchronize_tsc_bp(); +} + +/* These are wrappers to interface to the new boot process. Someone + who understands all this stuff should rewrite it properly. --RR 15/Jul/02 */ +void __init smp_prepare_cpus(unsigned int max_cpus) +{ + smp_boot_cpus(max_cpus); +} + +void __devinit smp_prepare_boot_cpu(void) +{ + cpu_set(smp_processor_id(), cpu_online_map); + cpu_set(smp_processor_id(), cpu_callout_map); +} + +int __devinit __cpu_up(unsigned int cpu) +{ + /* This only works at boot for x86. See "rewrite" above. */ + if (cpu_isset(cpu, smp_commenced_mask)) { + local_irq_enable(); + return -ENOSYS; + } + + /* In case one didn't come up */ + if (!cpu_isset(cpu, cpu_callin_map)) { + local_irq_enable(); + return -EIO; + } + +#ifdef CONFIG_SMP_ALTERNATIVES + if (num_online_cpus() == 1) + prepare_for_smp(); +#endif + + local_irq_enable(); + /* Unleash the CPU! */ + cpu_set(cpu, smp_commenced_mask); + while (!cpu_isset(cpu, cpu_online_map)) + mb(); + return 0; +} + +void __init smp_cpus_done(unsigned int max_cpus) +{ +#ifdef CONFIG_X86_IO_APIC + setup_ioapic_dest(); +#endif + zap_low_mappings(); + /* + * Disable executability of the SMP trampoline: + */ + set_kernel_exec((unsigned long)trampoline_base, trampoline_exec); +} + +void __init smp_intr_init(void) +{ + /* + * IRQ0 must be given a fixed assignment and initialized, + * because it's used before the IO-APIC is set up. + */ + set_intr_gate(FIRST_DEVICE_VECTOR, interrupt[0]); + + /* + * The reschedule interrupt is a CPU-to-CPU reschedule-helper + * IPI, driven by wakeup. + */ + set_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt); + + /* IPI for invalidation */ + set_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt); + + /* IPI for generic function call */ + set_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt); +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/swiotlb.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/swiotlb.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,671 @@ +/* + * Dynamic DMA mapping support. + * + * This implementation is a fallback for platforms that do not support + * I/O TLBs (aka DMA address translation hardware). + * Copyright (C) 2000 Asit Mallick <Asit.K.Mallick@xxxxxxxxx> + * Copyright (C) 2000 Goutham Rao <goutham.rao@xxxxxxxxx> + * Copyright (C) 2000, 2003 Hewlett-Packard Co + * David Mosberger-Tang <davidm@xxxxxxxxxx> + * Copyright (C) 2005 Keir Fraser <keir@xxxxxxxxxxxxx> + */ + +#include <linux/cache.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/spinlock.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/ctype.h> +#include <linux/init.h> +#include <linux/bootmem.h> +#include <linux/highmem.h> +#include <asm/io.h> +#include <asm/pci.h> +#include <asm/dma.h> +#include <asm/uaccess.h> +#include <xen/interface/memory.h> + +#define OFFSET(val,align) ((unsigned long)((val) & ( (align) - 1))) + +#define SG_ENT_PHYS_ADDRESS(sg) (page_to_phys((sg)->page) + (sg)->offset) + +/* + * Maximum allowable number of contiguous slabs to map, + * must be a power of 2. What is the appropriate value ? + * The complexity of {map,unmap}_single is linearly dependent on this value. + */ +#define IO_TLB_SEGSIZE 128 + +/* + * log of the size of each IO TLB slab. The number of slabs is command line + * controllable. + */ +#define IO_TLB_SHIFT 11 + +static int swiotlb_force; +static char *iotlb_virt_start; +static unsigned long iotlb_nslabs; + +/* + * Used to do a quick range check in swiotlb_unmap_single and + * swiotlb_sync_single_*, to see if the memory was in fact allocated by this + * API. + */ +static dma_addr_t iotlb_bus_start, iotlb_bus_end, iotlb_bus_mask; + +/* Does the given dma address reside within the swiotlb aperture? */ +#define in_swiotlb_aperture(a) (!(((a) ^ iotlb_bus_start) & iotlb_bus_mask)) + +/* + * When the IOMMU overflows we return a fallback buffer. This sets the size. + */ +static unsigned long io_tlb_overflow = 32*1024; + +void *io_tlb_overflow_buffer; + +/* + * This is a free list describing the number of free entries available from + * each index + */ +static unsigned int *io_tlb_list; +static unsigned int io_tlb_index; + +/* + * We need to save away the original address corresponding to a mapped entry + * for the sync operations. + */ +static struct phys_addr { + struct page *page; + unsigned int offset; +} *io_tlb_orig_addr; + +/* + * Protect the above data structures in the map and unmap calls + */ +static DEFINE_SPINLOCK(io_tlb_lock); + +static int __init +setup_io_tlb_npages(char *str) +{ + /* Unlike ia64, the size is aperture in megabytes, not 'slabs'! */ + if (isdigit(*str)) { + iotlb_nslabs = simple_strtoul(str, &str, 0) << + (20 - IO_TLB_SHIFT); + iotlb_nslabs = ALIGN(iotlb_nslabs, IO_TLB_SEGSIZE); + /* Round up to power of two (xen_create_contiguous_region). */ + while (iotlb_nslabs & (iotlb_nslabs-1)) + iotlb_nslabs += iotlb_nslabs & ~(iotlb_nslabs-1); + } + if (*str == ',') + ++str; + /* + * NB. 'force' enables the swiotlb, but doesn't force its use for + * every DMA like it does on native Linux. 'off' forcibly disables + * use of the swiotlb. + */ + if (!strcmp(str, "force")) + swiotlb_force = 1; + else if (!strcmp(str, "off")) + swiotlb_force = -1; + return 1; +} +__setup("swiotlb=", setup_io_tlb_npages); +/* make io_tlb_overflow tunable too? */ + +/* + * Statically reserve bounce buffer space and initialize bounce buffer data + * structures for the software IO TLB used to implement the PCI DMA API. + */ +void +swiotlb_init_with_default_size (size_t default_size) +{ + unsigned long i, bytes; + int rc; + + if (!iotlb_nslabs) { + iotlb_nslabs = (default_size >> IO_TLB_SHIFT); + iotlb_nslabs = ALIGN(iotlb_nslabs, IO_TLB_SEGSIZE); + /* Round up to power of two (xen_create_contiguous_region). */ + while (iotlb_nslabs & (iotlb_nslabs-1)) + iotlb_nslabs += iotlb_nslabs & ~(iotlb_nslabs-1); + } + + bytes = iotlb_nslabs * (1UL << IO_TLB_SHIFT); + + /* + * Get IO TLB memory from the low pages + */ + iotlb_virt_start = alloc_bootmem_low_pages(bytes); + if (!iotlb_virt_start) + panic("Cannot allocate SWIOTLB buffer!\n" + "Use dom0_mem Xen boot parameter to reserve\n" + "some DMA memory (e.g., dom0_mem=-128M).\n"); + + /* Hardcode 31 address bits for now: aacraid limitation. */ + rc = xen_create_contiguous_region( + (unsigned long)iotlb_virt_start, get_order(bytes), 31); + BUG_ON(rc); + + /* + * Allocate and initialize the free list array. This array is used + * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE. + */ + io_tlb_list = alloc_bootmem(iotlb_nslabs * sizeof(int)); + for (i = 0; i < iotlb_nslabs; i++) + io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); + io_tlb_index = 0; + io_tlb_orig_addr = alloc_bootmem( + iotlb_nslabs * sizeof(*io_tlb_orig_addr)); + + /* + * Get the overflow emergency buffer + */ + io_tlb_overflow_buffer = alloc_bootmem_low(io_tlb_overflow); + + iotlb_bus_start = virt_to_bus(iotlb_virt_start); + iotlb_bus_end = iotlb_bus_start + bytes; + iotlb_bus_mask = ~(dma_addr_t)(bytes - 1); + + printk(KERN_INFO "Software IO TLB enabled: \n" + " Aperture: %lu megabytes\n" + " Bus range: 0x%016lx - 0x%016lx\n" + " Kernel range: 0x%016lx - 0x%016lx\n", + bytes >> 20, + (unsigned long)iotlb_bus_start, + (unsigned long)iotlb_bus_end, + (unsigned long)iotlb_virt_start, + (unsigned long)iotlb_virt_start + bytes); +} + +void +swiotlb_init(void) +{ + long ram_end; + size_t defsz = 64 * (1 << 20); /* 64MB default size */ + + if (swiotlb_force == 1) { + swiotlb = 1; + } else if ((swiotlb_force != -1) && + (xen_start_info->flags & SIF_INITDOMAIN)) { + /* Domain 0 always has a swiotlb. */ + ram_end = HYPERVISOR_memory_op(XENMEM_maximum_ram_page, NULL); + if (ram_end <= 0x7ffff) + defsz = 2 * (1 << 20); /* 2MB on <2GB on systems. */ + swiotlb = 1; + } + + if (swiotlb) + swiotlb_init_with_default_size(defsz); + else + printk(KERN_INFO "Software IO TLB disabled\n"); +} + +/* + * We use __copy_to_user to transfer to the host buffer because the buffer + * may be mapped read-only (e.g, in blkback driver) but lower-level + * drivers map the buffer for DMA_BIDIRECTIONAL access. This causes an + * unnecessary copy from the aperture to the host buffer, and a page fault. + */ +static void +__sync_single(struct phys_addr buffer, char *dma_addr, size_t size, int dir) +{ + if (PageHighMem(buffer.page)) { + size_t len, bytes; + char *dev, *host, *kmp; + len = size; + while (len != 0) { + if (((bytes = len) + buffer.offset) > PAGE_SIZE) + bytes = PAGE_SIZE - buffer.offset; + kmp = kmap_atomic(buffer.page, KM_SWIOTLB); + dev = dma_addr + size - len; + host = kmp + buffer.offset; + if (dir == DMA_FROM_DEVICE) { + if (__copy_to_user(host, dev, bytes)) + /* inaccessible */; + } else + memcpy(dev, host, bytes); + kunmap_atomic(kmp, KM_SWIOTLB); + len -= bytes; + buffer.page++; + buffer.offset = 0; + } + } else { + char *host = (char *)phys_to_virt( + page_to_pseudophys(buffer.page)) + buffer.offset; + if (dir == DMA_FROM_DEVICE) { + if (__copy_to_user(host, dma_addr, size)) + /* inaccessible */; + } else if (dir == DMA_TO_DEVICE) + memcpy(dma_addr, host, size); + } +} + +/* + * Allocates bounce buffer and returns its kernel virtual address. + */ +static void * +map_single(struct device *hwdev, struct phys_addr buffer, size_t size, int dir) +{ + unsigned long flags; + char *dma_addr; + unsigned int nslots, stride, index, wrap; + int i; + + /* + * For mappings greater than a page, we limit the stride (and + * hence alignment) to a page size. + */ + nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; + if (size > PAGE_SIZE) + stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT)); + else + stride = 1; + + BUG_ON(!nslots); + + /* + * Find suitable number of IO TLB entries size that will fit this + * request and allocate a buffer from that IO TLB pool. + */ + spin_lock_irqsave(&io_tlb_lock, flags); + { + wrap = index = ALIGN(io_tlb_index, stride); + + if (index >= iotlb_nslabs) + wrap = index = 0; + + do { + /* + * If we find a slot that indicates we have 'nslots' + * number of contiguous buffers, we allocate the + * buffers from that slot and mark the entries as '0' + * indicating unavailable. + */ + if (io_tlb_list[index] >= nslots) { + int count = 0; + + for (i = index; i < (int)(index + nslots); i++) + io_tlb_list[i] = 0; + for (i = index - 1; + (OFFSET(i, IO_TLB_SEGSIZE) != + IO_TLB_SEGSIZE -1) && io_tlb_list[i]; + i--) + io_tlb_list[i] = ++count; + dma_addr = iotlb_virt_start + + (index << IO_TLB_SHIFT); + + /* + * Update the indices to avoid searching in + * the next round. + */ + io_tlb_index = + ((index + nslots) < iotlb_nslabs + ? (index + nslots) : 0); + + goto found; + } + index += stride; + if (index >= iotlb_nslabs) + index = 0; + } while (index != wrap); + + spin_unlock_irqrestore(&io_tlb_lock, flags); + return NULL; + } + found: + spin_unlock_irqrestore(&io_tlb_lock, flags); + + /* + * Save away the mapping from the original address to the DMA address. + * This is needed when we sync the memory. Then we sync the buffer if + * needed. + */ + io_tlb_orig_addr[index] = buffer; + if ((dir == DMA_TO_DEVICE) || (dir == DMA_BIDIRECTIONAL)) + __sync_single(buffer, dma_addr, size, DMA_TO_DEVICE); + + return dma_addr; +} + +/* + * dma_addr is the kernel virtual address of the bounce buffer to unmap. + */ +static void +unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir) +{ + unsigned long flags; + int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; + int index = (dma_addr - iotlb_virt_start) >> IO_TLB_SHIFT; + struct phys_addr buffer = io_tlb_orig_addr[index]; + + /* + * First, sync the memory before unmapping the entry + */ + if ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)) + __sync_single(buffer, dma_addr, size, DMA_FROM_DEVICE); + + /* + * Return the buffer to the free list by setting the corresponding + * entries to indicate the number of contigous entries available. + * While returning the entries to the free list, we merge the entries + * with slots below and above the pool being returned. + */ + spin_lock_irqsave(&io_tlb_lock, flags); + { + count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ? + io_tlb_list[index + nslots] : 0); + /* + * Step 1: return the slots to the free list, merging the + * slots with superceeding slots + */ + for (i = index + nslots - 1; i >= index; i--) + io_tlb_list[i] = ++count; + /* + * Step 2: merge the returned slots with the preceding slots, + * if available (non zero) + */ + for (i = index - 1; + (OFFSET(i, IO_TLB_SEGSIZE) != + IO_TLB_SEGSIZE -1) && io_tlb_list[i]; + i--) + io_tlb_list[i] = ++count; + } + spin_unlock_irqrestore(&io_tlb_lock, flags); +} + +static void +sync_single(struct device *hwdev, char *dma_addr, size_t size, int dir) +{ + int index = (dma_addr - iotlb_virt_start) >> IO_TLB_SHIFT; + struct phys_addr buffer = io_tlb_orig_addr[index]; + BUG_ON((dir != DMA_FROM_DEVICE) && (dir != DMA_TO_DEVICE)); + __sync_single(buffer, dma_addr, size, dir); +} + +static void +swiotlb_full(struct device *dev, size_t size, int dir, int do_panic) +{ + /* + * Ran out of IOMMU space for this operation. This is very bad. + * Unfortunately the drivers cannot handle this operation properly. + * unless they check for pci_dma_mapping_error (most don't) + * When the mapping is small enough return a static buffer to limit + * the damage, or panic when the transfer is too big. + */ + printk(KERN_ERR "PCI-DMA: Out of SW-IOMMU space for %lu bytes at " + "device %s\n", (unsigned long)size, dev ? dev->bus_id : "?"); + + if (size > io_tlb_overflow && do_panic) { + if (dir == PCI_DMA_FROMDEVICE || dir == PCI_DMA_BIDIRECTIONAL) + panic("PCI-DMA: Memory would be corrupted\n"); + if (dir == PCI_DMA_TODEVICE || dir == PCI_DMA_BIDIRECTIONAL) + panic("PCI-DMA: Random memory would be DMAed\n"); + } +} + +/* + * Map a single buffer of the indicated size for DMA in streaming mode. The + * PCI address to use is returned. + * + * Once the device is given the dma address, the device owns this memory until + * either swiotlb_unmap_single or swiotlb_dma_sync_single is performed. + */ +dma_addr_t +swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir) +{ + dma_addr_t dev_addr = virt_to_bus(ptr); + void *map; + struct phys_addr buffer; + + BUG_ON(dir == DMA_NONE); + + /* + * If the pointer passed in happens to be in the device's DMA window, + * we can safely return the device addr and not worry about bounce + * buffering it. + */ + if (!range_straddles_page_boundary(ptr, size) && + !address_needs_mapping(hwdev, dev_addr)) + return dev_addr; + + /* + * Oh well, have to allocate and map a bounce buffer. + */ + buffer.page = virt_to_page(ptr); + buffer.offset = (unsigned long)ptr & ~PAGE_MASK; + map = map_single(hwdev, buffer, size, dir); + if (!map) { + swiotlb_full(hwdev, size, dir, 1); + map = io_tlb_overflow_buffer; + } + + dev_addr = virt_to_bus(map); + return dev_addr; +} + +/* + * Unmap a single streaming mode DMA translation. The dma_addr and size must + * match what was provided for in a previous swiotlb_map_single call. All + * other usages are undefined. + * + * After this call, reads by the cpu to the buffer are guaranteed to see + * whatever the device wrote there. + */ +void +swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size, + int dir) +{ + BUG_ON(dir == DMA_NONE); + if (in_swiotlb_aperture(dev_addr)) + unmap_single(hwdev, bus_to_virt(dev_addr), size, dir); +} + +/* + * Make physical memory consistent for a single streaming mode DMA translation + * after a transfer. + * + * If you perform a swiotlb_map_single() but wish to interrogate the buffer + * using the cpu, yet do not wish to teardown the PCI dma mapping, you must + * call this function before doing so. At the next point you give the PCI dma + * address back to the card, you must first perform a + * swiotlb_dma_sync_for_device, and then the device again owns the buffer + */ +void +swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, + size_t size, int dir) +{ + BUG_ON(dir == DMA_NONE); + if (in_swiotlb_aperture(dev_addr)) + sync_single(hwdev, bus_to_virt(dev_addr), size, dir); +} + +void +swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, + size_t size, int dir) +{ + BUG_ON(dir == DMA_NONE); + if (in_swiotlb_aperture(dev_addr)) + sync_single(hwdev, bus_to_virt(dev_addr), size, dir); +} + +/* + * Map a set of buffers described by scatterlist in streaming mode for DMA. + * This is the scatter-gather version of the above swiotlb_map_single + * interface. Here the scatter gather list elements are each tagged with the + * appropriate dma address and length. They are obtained via + * sg_dma_{address,length}(SG). + * + * NOTE: An implementation may be able to use a smaller number of + * DMA address/length pairs than there are SG table elements. + * (for example via virtual mapping capabilities) + * The routine returns the number of addr/length pairs actually + * used, at most nents. + * + * Device ownership issues as mentioned above for swiotlb_map_single are the + * same here. + */ +int +swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nelems, + int dir) +{ + struct phys_addr buffer; + dma_addr_t dev_addr; + char *map; + int i; + + BUG_ON(dir == DMA_NONE); + + for (i = 0; i < nelems; i++, sg++) { + dev_addr = SG_ENT_PHYS_ADDRESS(sg); + if (address_needs_mapping(hwdev, dev_addr)) { + buffer.page = sg->page; + buffer.offset = sg->offset; + map = map_single(hwdev, buffer, sg->length, dir); + if (!map) { + /* Don't panic here, we expect map_sg users + to do proper error handling. */ + swiotlb_full(hwdev, sg->length, dir, 0); + swiotlb_unmap_sg(hwdev, sg - i, i, dir); + sg[0].dma_length = 0; + return 0; + } + sg->dma_address = (dma_addr_t)virt_to_bus(map); + } else + sg->dma_address = dev_addr; + sg->dma_length = sg->length; + } + return nelems; +} + +/* + * Unmap a set of streaming mode DMA translations. Again, cpu read rules + * concerning calls here are the same as for swiotlb_unmap_single() above. + */ +void +swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nelems, + int dir) +{ + int i; + + BUG_ON(dir == DMA_NONE); + + for (i = 0; i < nelems; i++, sg++) + if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) + unmap_single(hwdev, + (void *)bus_to_virt(sg->dma_address), + sg->dma_length, dir); +} + +/* + * Make physical memory consistent for a set of streaming mode DMA translations + * after a transfer. + * + * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules + * and usage. + */ +void +swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, + int nelems, int dir) +{ + int i; + + BUG_ON(dir == DMA_NONE); + + for (i = 0; i < nelems; i++, sg++) + if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) + sync_single(hwdev, + (void *)bus_to_virt(sg->dma_address), + sg->dma_length, dir); +} + +void +swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, + int nelems, int dir) +{ + int i; + + BUG_ON(dir == DMA_NONE); + + for (i = 0; i < nelems; i++, sg++) + if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) + sync_single(hwdev, + (void *)bus_to_virt(sg->dma_address), + sg->dma_length, dir); +} + +dma_addr_t +swiotlb_map_page(struct device *hwdev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction direction) +{ + struct phys_addr buffer; + dma_addr_t dev_addr; + char *map; + + dev_addr = page_to_phys(page) + offset; + if (address_needs_mapping(hwdev, dev_addr)) { + buffer.page = page; + buffer.offset = offset; + map = map_single(hwdev, buffer, size, direction); + if (!map) { + swiotlb_full(hwdev, size, direction, 1); + map = io_tlb_overflow_buffer; + } + dev_addr = (dma_addr_t)virt_to_bus(map); + } + + return dev_addr; +} + +void +swiotlb_unmap_page(struct device *hwdev, dma_addr_t dma_address, + size_t size, enum dma_data_direction direction) +{ + BUG_ON(direction == DMA_NONE); + if (in_swiotlb_aperture(dma_address)) + unmap_single(hwdev, bus_to_virt(dma_address), size, direction); +} + +int +swiotlb_dma_mapping_error(dma_addr_t dma_addr) +{ + return (dma_addr == virt_to_bus(io_tlb_overflow_buffer)); +} + +/* + * Return whether the given PCI device DMA address mask can be supported + * properly. For example, if your device can only drive the low 24-bits + * during PCI bus mastering, then you would pass 0x00ffffff as the mask to + * this function. + */ +int +swiotlb_dma_supported (struct device *hwdev, u64 mask) +{ + return (mask >= (iotlb_bus_end - 1)); +} + +EXPORT_SYMBOL(swiotlb_init); +EXPORT_SYMBOL(swiotlb_map_single); +EXPORT_SYMBOL(swiotlb_unmap_single); +EXPORT_SYMBOL(swiotlb_map_sg); +EXPORT_SYMBOL(swiotlb_unmap_sg); +EXPORT_SYMBOL(swiotlb_sync_single_for_cpu); +EXPORT_SYMBOL(swiotlb_sync_single_for_device); +EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu); +EXPORT_SYMBOL(swiotlb_sync_sg_for_device); +EXPORT_SYMBOL(swiotlb_map_page); +EXPORT_SYMBOL(swiotlb_unmap_page); +EXPORT_SYMBOL(swiotlb_dma_mapping_error); +EXPORT_SYMBOL(swiotlb_dma_supported); + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/time-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/time-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,927 @@ +/* + * linux/arch/i386/kernel/time.c + * + * Copyright (C) 1991, 1992, 1995 Linus Torvalds + * + * This file contains the PC-specific time handling details: + * reading the RTC at bootup, etc.. + * 1994-07-02 Alan Modra + * fixed set_rtc_mmss, fixed time.year for >= 2000, new mktime + * 1995-03-26 Markus Kuhn + * fixed 500 ms bug at call to set_rtc_mmss, fixed DS12887 + * precision CMOS clock update + * 1996-05-03 Ingo Molnar + * fixed time warps in do_[slow|fast]_gettimeoffset() + * 1997-09-10 Updated NTP code according to technical memorandum Jan '96 + * "A Kernel Model for Precision Timekeeping" by Dave Mills + * 1998-09-05 (Various) + * More robust do_fast_gettimeoffset() algorithm implemented + * (works with APM, Cyrix 6x86MX and Centaur C6), + * monotonic gettimeofday() with fast_get_timeoffset(), + * drift-proof precision TSC calibration on boot + * (C. Scott Ananian <cananian@xxxxxxxxxxxxxxxxxxxx>, Andrew D. + * Balsa <andrebalsa@xxxxxxxxxx>, Philip Gladstone <philip@xxxxxxxxxx>; + * ported from 2.0.35 Jumbo-9 by Michael Krause <m.krause@xxxxxxxxxxxxx>). + * 1998-12-16 Andrea Arcangeli + * Fixed Jumbo-9 code in 2.1.131: do_gettimeofday was missing 1 jiffy + * because was not accounting lost_ticks. + * 1998-12-24 Copyright (C) 1998 Andrea Arcangeli + * Fixed a xtime SMP race (we need the xtime_lock rw spinlock to + * serialize accesses to xtime/lost_ticks). + */ + +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/param.h> +#include <linux/string.h> +#include <linux/mm.h> +#include <linux/interrupt.h> +#include <linux/time.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/smp.h> +#include <linux/module.h> +#include <linux/sysdev.h> +#include <linux/bcd.h> +#include <linux/efi.h> +#include <linux/mca.h> +#include <linux/sysctl.h> +#include <linux/percpu.h> + +#include <asm/io.h> +#include <asm/smp.h> +#include <asm/irq.h> +#include <asm/msr.h> +#include <asm/delay.h> +#include <asm/mpspec.h> +#include <asm/uaccess.h> +#include <asm/processor.h> +#include <asm/timer.h> + +#include "mach_time.h" + +#include <linux/timex.h> +#include <linux/config.h> + +#include <asm/hpet.h> + +#include <asm/arch_hooks.h> + +#include "io_ports.h" + +#include <xen/evtchn.h> + +extern spinlock_t i8259A_lock; +int pit_latch_buggy; /* extern */ + +u64 jiffies_64 = INITIAL_JIFFIES; + +EXPORT_SYMBOL(jiffies_64); + +#if defined(__x86_64__) +unsigned long vxtime_hz = PIT_TICK_RATE; +struct vxtime_data __vxtime __section_vxtime; /* for vsyscalls */ +volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES; +unsigned long __wall_jiffies __section_wall_jiffies = INITIAL_JIFFIES; +struct timespec __xtime __section_xtime; +struct timezone __sys_tz __section_sys_tz; +#endif + +#if defined(__x86_64__) +unsigned int cpu_khz; /* Detected as we calibrate the TSC */ +#else +unsigned long cpu_khz; /* Detected as we calibrate the TSC */ +#endif + +extern unsigned long wall_jiffies; + +DEFINE_SPINLOCK(rtc_lock); + +DEFINE_SPINLOCK(i8253_lock); +EXPORT_SYMBOL(i8253_lock); + +extern struct init_timer_opts timer_tsc_init; +extern struct timer_opts timer_tsc; +struct timer_opts *cur_timer = &timer_tsc; + +/* These are peridically updated in shared_info, and then copied here. */ +struct shadow_time_info { + u64 tsc_timestamp; /* TSC at last update of time vals. */ + u64 system_timestamp; /* Time, in nanosecs, since boot. */ + u32 tsc_to_nsec_mul; + u32 tsc_to_usec_mul; + int tsc_shift; + u32 version; +}; +static DEFINE_PER_CPU(struct shadow_time_info, shadow_time); +static struct timespec shadow_tv; +static u32 shadow_tv_version; + +/* Keep track of last time we did processing/updating of jiffies and xtime. */ +static u64 processed_system_time; /* System time (ns) at last processing. */ +static DEFINE_PER_CPU(u64, processed_system_time); + +/* Must be signed, as it's compared with s64 quantities which can be -ve. */ +#define NS_PER_TICK (1000000000LL/HZ) + +static inline void __normalize_time(time_t *sec, s64 *nsec) +{ + while (*nsec >= NSEC_PER_SEC) { + (*nsec) -= NSEC_PER_SEC; + (*sec)++; + } + while (*nsec < 0) { + (*nsec) += NSEC_PER_SEC; + (*sec)--; + } +} + +/* Does this guest OS track Xen time, or set its wall clock independently? */ +static int independent_wallclock = 0; +static int __init __independent_wallclock(char *str) +{ + independent_wallclock = 1; + return 1; +} +__setup("independent_wallclock", __independent_wallclock); + +int tsc_disable __initdata = 0; + +static void delay_tsc(unsigned long loops) +{ + unsigned long bclock, now; + + rdtscl(bclock); + do + { + rep_nop(); + rdtscl(now); + } while ((now-bclock) < loops); +} + +struct timer_opts timer_tsc = { + .name = "tsc", + .delay = delay_tsc, +}; + +/* + * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction, + * yielding a 64-bit result. + */ +static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift) +{ + u64 product; +#ifdef __i386__ + u32 tmp1, tmp2; +#endif + + if ( shift < 0 ) + delta >>= -shift; + else + delta <<= shift; + +#ifdef __i386__ + __asm__ ( + "mul %5 ; " + "mov %4,%%eax ; " + "mov %%edx,%4 ; " + "mul %5 ; " + "xor %5,%5 ; " + "add %4,%%eax ; " + "adc %5,%%edx ; " + : "=A" (product), "=r" (tmp1), "=r" (tmp2) + : "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) ); +#else + __asm__ ( + "mul %%rdx ; shrd $32,%%rdx,%%rax" + : "=a" (product) : "0" (delta), "d" ((u64)mul_frac) ); +#endif + + return product; +} + +void init_cpu_khz(void) +{ + u64 __cpu_khz = 1000000ULL << 32; + struct vcpu_time_info *info; + info = &HYPERVISOR_shared_info->vcpu_info[0].time; + do_div(__cpu_khz, info->tsc_to_system_mul); + if ( info->tsc_shift < 0 ) + cpu_khz = __cpu_khz << -info->tsc_shift; + else + cpu_khz = __cpu_khz >> info->tsc_shift; +} + +static u64 get_nsec_offset(struct shadow_time_info *shadow) +{ + u64 now, delta; + rdtscll(now); + delta = now - shadow->tsc_timestamp; + return scale_delta(delta, shadow->tsc_to_nsec_mul, shadow->tsc_shift); +} + +static unsigned long get_usec_offset(struct shadow_time_info *shadow) +{ + u64 now, delta; + rdtscll(now); + delta = now - shadow->tsc_timestamp; + return scale_delta(delta, shadow->tsc_to_usec_mul, shadow->tsc_shift); +} + +static void __update_wallclock(time_t sec, long nsec) +{ + long wtm_nsec, xtime_nsec; + time_t wtm_sec, xtime_sec; + u64 tmp, wc_nsec; + + /* Adjust wall-clock time base based on wall_jiffies ticks. */ + wc_nsec = processed_system_time; + wc_nsec += sec * (u64)NSEC_PER_SEC; + wc_nsec += nsec; + wc_nsec -= (jiffies - wall_jiffies) * (u64)NS_PER_TICK; + + /* Split wallclock base into seconds and nanoseconds. */ + tmp = wc_nsec; + xtime_nsec = do_div(tmp, 1000000000); + xtime_sec = (time_t)tmp; + + wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - xtime_sec); + wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - xtime_nsec); + + set_normalized_timespec(&xtime, xtime_sec, xtime_nsec); + set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); + + time_adjust = 0; /* stop active adjtime() */ + time_status |= STA_UNSYNC; + time_maxerror = NTP_PHASE_LIMIT; + time_esterror = NTP_PHASE_LIMIT; +} + +static void update_wallclock(void) +{ + shared_info_t *s = HYPERVISOR_shared_info; + + do { + shadow_tv_version = s->wc_version; + rmb(); + shadow_tv.tv_sec = s->wc_sec; + shadow_tv.tv_nsec = s->wc_nsec; + rmb(); + } + while ((s->wc_version & 1) | (shadow_tv_version ^ s->wc_version)); + + if (!independent_wallclock) + __update_wallclock(shadow_tv.tv_sec, shadow_tv.tv_nsec); +} + +/* + * Reads a consistent set of time-base values from Xen, into a shadow data + * area. + */ +static void get_time_values_from_xen(void) +{ + shared_info_t *s = HYPERVISOR_shared_info; + struct vcpu_time_info *src; + struct shadow_time_info *dst; + + src = &s->vcpu_info[smp_processor_id()].time; + dst = &per_cpu(shadow_time, smp_processor_id()); + + do { + dst->version = src->version; + rmb(); + dst->tsc_timestamp = src->tsc_timestamp; + dst->system_timestamp = src->system_time; + dst->tsc_to_nsec_mul = src->tsc_to_system_mul; + dst->tsc_shift = src->tsc_shift; + rmb(); + } + while ((src->version & 1) | (dst->version ^ src->version)); + + dst->tsc_to_usec_mul = dst->tsc_to_nsec_mul / 1000; +} + +static inline int time_values_up_to_date(int cpu) +{ + struct vcpu_time_info *src; + struct shadow_time_info *dst; + + src = &HYPERVISOR_shared_info->vcpu_info[cpu].time; + dst = &per_cpu(shadow_time, cpu); + + return (dst->version == src->version); +} + +/* + * This is a special lock that is owned by the CPU and holds the index + * register we are working with. It is required for NMI access to the + * CMOS/RTC registers. See include/asm-i386/mc146818rtc.h for details. + */ +volatile unsigned long cmos_lock = 0; +EXPORT_SYMBOL(cmos_lock); + +/* Routines for accessing the CMOS RAM/RTC. */ +unsigned char rtc_cmos_read(unsigned char addr) +{ + unsigned char val; + lock_cmos_prefix(addr); + outb_p(addr, RTC_PORT(0)); + val = inb_p(RTC_PORT(1)); + lock_cmos_suffix(addr); + return val; +} +EXPORT_SYMBOL(rtc_cmos_read); + +void rtc_cmos_write(unsigned char val, unsigned char addr) +{ + lock_cmos_prefix(addr); + outb_p(addr, RTC_PORT(0)); + outb_p(val, RTC_PORT(1)); + lock_cmos_suffix(addr); +} +EXPORT_SYMBOL(rtc_cmos_write); + +/* + * This version of gettimeofday has microsecond resolution + * and better than microsecond precision on fast x86 machines with TSC. + */ +void do_gettimeofday(struct timeval *tv) +{ + unsigned long seq; + unsigned long usec, sec; + unsigned long max_ntp_tick; + s64 nsec; + unsigned int cpu; + struct shadow_time_info *shadow; + u32 local_time_version; + + cpu = get_cpu(); + shadow = &per_cpu(shadow_time, cpu); + + do { + unsigned long lost; + + local_time_version = shadow->version; + seq = read_seqbegin(&xtime_lock); + + usec = get_usec_offset(shadow); + lost = jiffies - wall_jiffies; + + /* + * If time_adjust is negative then NTP is slowing the clock + * so make sure not to go into next possible interval. + * Better to lose some accuracy than have time go backwards.. + */ + if (unlikely(time_adjust < 0)) { + max_ntp_tick = (USEC_PER_SEC / HZ) - tickadj; + usec = min(usec, max_ntp_tick); + + if (lost) + usec += lost * max_ntp_tick; + } + else if (unlikely(lost)) + usec += lost * (USEC_PER_SEC / HZ); + + sec = xtime.tv_sec; + usec += (xtime.tv_nsec / NSEC_PER_USEC); + + nsec = shadow->system_timestamp - processed_system_time; + __normalize_time(&sec, &nsec); + usec += (long)nsec / NSEC_PER_USEC; + + if (unlikely(!time_values_up_to_date(cpu))) { + /* + * We may have blocked for a long time, + * rendering our calculations invalid + * (e.g. the time delta may have + * overflowed). Detect that and recalculate + * with fresh values. + */ + get_time_values_from_xen(); + continue; + } + } while (read_seqretry(&xtime_lock, seq) || + (local_time_version != shadow->version)); + + put_cpu(); + + while (usec >= USEC_PER_SEC) { + usec -= USEC_PER_SEC; + sec++; + } + + tv->tv_sec = sec; + tv->tv_usec = usec; +} + +EXPORT_SYMBOL(do_gettimeofday); + +int do_settimeofday(struct timespec *tv) +{ + time_t sec; + s64 nsec; + unsigned int cpu; + struct shadow_time_info *shadow; + dom0_op_t op; + + if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) + return -EINVAL; + + cpu = get_cpu(); + shadow = &per_cpu(shadow_time, cpu); + + write_seqlock_irq(&xtime_lock); + + /* + * Ensure we don't get blocked for a long time so that our time delta + * overflows. If that were to happen then our shadow time values would + * be stale, so we can retry with fresh ones. + */ + for ( ; ; ) { + nsec = tv->tv_nsec - get_nsec_offset(shadow); + if (time_values_up_to_date(cpu)) + break; + get_time_values_from_xen(); + } + sec = tv->tv_sec; + __normalize_time(&sec, &nsec); + + if ((xen_start_info->flags & SIF_INITDOMAIN) && + !independent_wallclock) { + op.cmd = DOM0_SETTIME; + op.u.settime.secs = sec; + op.u.settime.nsecs = nsec; + op.u.settime.system_time = shadow->system_timestamp; + HYPERVISOR_dom0_op(&op); + update_wallclock(); + } else if (independent_wallclock) { + nsec -= shadow->system_timestamp; + __normalize_time(&sec, &nsec); + __update_wallclock(sec, nsec); + } + + write_sequnlock_irq(&xtime_lock); + + put_cpu(); + + clock_was_set(); + return 0; +} + +EXPORT_SYMBOL(do_settimeofday); + +#ifdef CONFIG_XEN_PRIVILEGED_GUEST +static int set_rtc_mmss(unsigned long nowtime) +{ + int retval; + + WARN_ON(irqs_disabled()); + + if (!(xen_start_info->flags & SIF_INITDOMAIN)) + return 0; + + /* gets recalled with irq locally disabled */ + spin_lock_irq(&rtc_lock); + if (efi_enabled) + retval = efi_set_rtc_mmss(nowtime); + else + retval = mach_set_rtc_mmss(nowtime); + spin_unlock_irq(&rtc_lock); + + return retval; +} +#else +static int set_rtc_mmss(unsigned long nowtime) +{ + return 0; +} +#endif + +/* monotonic_clock(): returns # of nanoseconds passed since time_init() + * Note: This function is required to return accurate + * time even in the absence of multiple timer ticks. + */ +unsigned long long monotonic_clock(void) +{ + int cpu = get_cpu(); + struct shadow_time_info *shadow = &per_cpu(shadow_time, cpu); + u64 time; + u32 local_time_version; + + do { + local_time_version = shadow->version; + smp_rmb(); + time = shadow->system_timestamp + get_nsec_offset(shadow); + if (!time_values_up_to_date(cpu)) + get_time_values_from_xen(); + smp_rmb(); + } while (local_time_version != shadow->version); + + put_cpu(); + + return time; +} +EXPORT_SYMBOL(monotonic_clock); + +unsigned long long sched_clock(void) +{ + return monotonic_clock(); +} + +#if defined(CONFIG_SMP) && defined(CONFIG_FRAME_POINTER) +unsigned long profile_pc(struct pt_regs *regs) +{ + unsigned long pc = instruction_pointer(regs); + + if (in_lock_functions(pc)) + return *(unsigned long *)(regs->ebp + 4); + + return pc; +} +EXPORT_SYMBOL(profile_pc); +#endif + +irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) +{ + s64 delta, delta_cpu; + int i, cpu = smp_processor_id(); + struct shadow_time_info *shadow = &per_cpu(shadow_time, cpu); + + write_seqlock(&xtime_lock); + + do { + get_time_values_from_xen(); + + delta = delta_cpu = + shadow->system_timestamp + get_nsec_offset(shadow); + delta -= processed_system_time; + delta_cpu -= per_cpu(processed_system_time, cpu); + } + while (!time_values_up_to_date(cpu)); + + if ((unlikely(delta < -1000000LL) || unlikely(delta_cpu < 0)) + && printk_ratelimit()) { + printk("Timer ISR/%d: Time went backwards: " + "delta=%lld cpu_delta=%lld shadow=%lld " + "off=%lld processed=%lld cpu_processed=%lld\n", + cpu, delta, delta_cpu, shadow->system_timestamp, + (s64)get_nsec_offset(shadow), + processed_system_time, + per_cpu(processed_system_time, cpu)); + for (i = 0; i < num_online_cpus(); i++) + printk(" %d: %lld\n", i, + per_cpu(processed_system_time, i)); + } + + /* System-wide jiffy work. */ + while (delta >= NS_PER_TICK) { + delta -= NS_PER_TICK; + processed_system_time += NS_PER_TICK; + do_timer(regs); + } + + if (shadow_tv_version != HYPERVISOR_shared_info->wc_version) { + update_wallclock(); + clock_was_set(); + } + + write_sequnlock(&xtime_lock); + + /* + * Local CPU jiffy work. No need to hold xtime_lock, and I'm not sure + * if there is risk of deadlock if we do (since update_process_times + * may do scheduler rebalancing work and thus acquire runqueue locks). + */ + while (delta_cpu >= NS_PER_TICK) { + delta_cpu -= NS_PER_TICK; + per_cpu(processed_system_time, cpu) += NS_PER_TICK; + update_process_times(user_mode(regs)); + profile_tick(CPU_PROFILING, regs); + } + + return IRQ_HANDLED; +} + +/* not static: needed by APM */ +unsigned long get_cmos_time(void) +{ + unsigned long retval; + + spin_lock(&rtc_lock); + + if (efi_enabled) + retval = efi_get_time(); + else + retval = mach_get_cmos_time(); + + spin_unlock(&rtc_lock); + + return retval; +} +static void sync_cmos_clock(unsigned long dummy); + +static struct timer_list sync_cmos_timer = + TIMER_INITIALIZER(sync_cmos_clock, 0, 0); + +static void sync_cmos_clock(unsigned long dummy) +{ + struct timeval now, next; + int fail = 1; + + /* + * If we have an externally synchronized Linux clock, then update + * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be + * called as close as possible to 500 ms before the new second starts. + * This code is run on a timer. If the clock is set, that timer + * may not expire at the correct time. Thus, we adjust... + */ + if ((time_status & STA_UNSYNC) != 0) + /* + * Not synced, exit, do not restart a timer (if one is + * running, let it run out). + */ + return; + + do_gettimeofday(&now); + if (now.tv_usec >= USEC_AFTER - ((unsigned) TICK_SIZE) / 2 && + now.tv_usec <= USEC_BEFORE + ((unsigned) TICK_SIZE) / 2) + fail = set_rtc_mmss(now.tv_sec); + + next.tv_usec = USEC_AFTER - now.tv_usec; + if (next.tv_usec <= 0) + next.tv_usec += USEC_PER_SEC; + + if (!fail) + next.tv_sec = 659; + else + next.tv_sec = 0; + + if (next.tv_usec >= USEC_PER_SEC) { + next.tv_sec++; + next.tv_usec -= USEC_PER_SEC; + } + mod_timer(&sync_cmos_timer, jiffies + timeval_to_jiffies(&next)); +} + +void notify_arch_cmos_timer(void) +{ + mod_timer(&sync_cmos_timer, jiffies + 1); +} + +static long clock_cmos_diff, sleep_start; + +static int timer_suspend(struct sys_device *dev, pm_message_t state) +{ + /* + * Estimate time zone so that set_time can update the clock + */ + clock_cmos_diff = -get_cmos_time(); + clock_cmos_diff += get_seconds(); + sleep_start = get_cmos_time(); + return 0; +} + +static int timer_resume(struct sys_device *dev) +{ + unsigned long flags; + unsigned long sec; + unsigned long sleep_length; + +#ifdef CONFIG_HPET_TIMER + if (is_hpet_enabled()) + hpet_reenable(); +#endif + sec = get_cmos_time() + clock_cmos_diff; + sleep_length = (get_cmos_time() - sleep_start) * HZ; + write_seqlock_irqsave(&xtime_lock, flags); + xtime.tv_sec = sec; + xtime.tv_nsec = 0; + write_sequnlock_irqrestore(&xtime_lock, flags); + jiffies += sleep_length; + wall_jiffies += sleep_length; + return 0; +} + +static struct sysdev_class timer_sysclass = { + .resume = timer_resume, + .suspend = timer_suspend, + set_kset_name("timer"), +}; + + +/* XXX this driverfs stuff should probably go elsewhere later -john */ +static struct sys_device device_timer = { + .id = 0, + .cls = &timer_sysclass, +}; + +static int time_init_device(void) +{ + int error = sysdev_class_register(&timer_sysclass); + if (!error) + error = sysdev_register(&device_timer); + return error; +} + +device_initcall(time_init_device); + +#ifdef CONFIG_HPET_TIMER +extern void (*late_time_init)(void); +/* Duplicate of time_init() below, with hpet_enable part added */ +static void __init hpet_time_init(void) +{ + xtime.tv_sec = get_cmos_time(); + xtime.tv_nsec = (INITIAL_JIFFIES % HZ) * (NSEC_PER_SEC / HZ); + set_normalized_timespec(&wall_to_monotonic, + -xtime.tv_sec, -xtime.tv_nsec); + + if ((hpet_enable() >= 0) && hpet_use_timer) { + printk("Using HPET for base-timer\n"); + } + + cur_timer = select_timer(); + printk(KERN_INFO "Using %s for high-res timesource\n",cur_timer->name); + + time_init_hook(); +} +#endif + +/* Dynamically-mapped IRQ. */ +DEFINE_PER_CPU(int, timer_irq); + +extern void (*late_time_init)(void); +static void setup_cpu0_timer_irq(void) +{ + per_cpu(timer_irq, 0) = + bind_virq_to_irqhandler( + VIRQ_TIMER, + 0, + timer_interrupt, + SA_INTERRUPT, + "timer0", + NULL); + BUG_ON(per_cpu(timer_irq, 0) < 0); +} + +void __init time_init(void) +{ +#ifdef CONFIG_HPET_TIMER + if (is_hpet_capable()) { + /* + * HPET initialization needs to do memory-mapped io. So, let + * us do a late initialization after mem_init(). + */ + late_time_init = hpet_time_init; + return; + } +#endif + get_time_values_from_xen(); + + processed_system_time = per_cpu(shadow_time, 0).system_timestamp; + per_cpu(processed_system_time, 0) = processed_system_time; + + update_wallclock(); + + init_cpu_khz(); + printk(KERN_INFO "Xen reported: %lu.%03lu MHz processor.\n", + cpu_khz / 1000, cpu_khz % 1000); + +#if defined(__x86_64__) + vxtime.mode = VXTIME_TSC; + vxtime.quot = (1000000L << 32) / vxtime_hz; + vxtime.tsc_quot = (1000L << 32) / cpu_khz; + vxtime.hz = vxtime_hz; + sync_core(); + rdtscll(vxtime.last_tsc); +#endif + + /* Cannot request_irq() until kmem is initialised. */ + late_time_init = setup_cpu0_timer_irq; +} + +/* Convert jiffies to system time. */ +static inline u64 jiffies_to_st(unsigned long j) +{ + unsigned long seq; + long delta; + u64 st; + + do { + seq = read_seqbegin(&xtime_lock); + delta = j - jiffies; + /* NB. The next check can trigger in some wrap-around cases, + * but that's ok: we'll just end up with a shorter timeout. */ + if (delta < 1) + delta = 1; + st = processed_system_time + (delta * (u64)NS_PER_TICK); + } while (read_seqretry(&xtime_lock, seq)); + + return st; +} + +/* + * stop_hz_timer / start_hz_timer - enter/exit 'tickless mode' on an idle cpu + * These functions are based on implementations from arch/s390/kernel/time.c + */ +void stop_hz_timer(void) +{ + unsigned int cpu = smp_processor_id(); + unsigned long j; + + /* s390 does this /before/ checking rcu_pending(). We copy them. */ + cpu_set(cpu, nohz_cpu_mask); + + /* Leave ourselves in 'tick mode' if rcu or softirq pending. */ + if (rcu_pending(cpu) || local_softirq_pending()) { + cpu_clear(cpu, nohz_cpu_mask); + j = jiffies + 1; + } else { + j = next_timer_interrupt(); + } + + BUG_ON(HYPERVISOR_set_timer_op(jiffies_to_st(j)) != 0); +} + +void start_hz_timer(void) +{ + cpu_clear(smp_processor_id(), nohz_cpu_mask); +} + +/* No locking required. We are only CPU running, and interrupts are off. */ +void time_resume(void) +{ + init_cpu_khz(); + + get_time_values_from_xen(); + + processed_system_time = per_cpu(shadow_time, 0).system_timestamp; + per_cpu(processed_system_time, 0) = processed_system_time; + + update_wallclock(); +} + +#ifdef CONFIG_SMP +static char timer_name[NR_CPUS][15]; + +void local_setup_timer(unsigned int cpu) +{ + int seq; + + BUG_ON(cpu == 0); + + do { + seq = read_seqbegin(&xtime_lock); + /* Use cpu0 timestamp: cpu's shadow is not initialised yet. */ + per_cpu(processed_system_time, cpu) = + per_cpu(shadow_time, 0).system_timestamp; + } while (read_seqretry(&xtime_lock, seq)); + + sprintf(timer_name[cpu], "timer%d", cpu); + per_cpu(timer_irq, cpu) = + bind_virq_to_irqhandler( + VIRQ_TIMER, + cpu, + timer_interrupt, + SA_INTERRUPT, + timer_name[cpu], + NULL); + BUG_ON(per_cpu(timer_irq, cpu) < 0); +} + +void local_teardown_timer(unsigned int cpu) +{ + BUG_ON(cpu == 0); + unbind_from_irqhandler(per_cpu(timer_irq, cpu), NULL); +} +#endif + +/* + * /proc/sys/xen: This really belongs in another file. It can stay here for + * now however. + */ +static ctl_table xen_subtable[] = { + {1, "independent_wallclock", &independent_wallclock, + sizeof(independent_wallclock), 0644, NULL, proc_dointvec}, + {0} +}; +static ctl_table xen_table[] = { + {123, "xen", NULL, 0, 0555, xen_subtable}, + {0} +}; +static int __init xen_sysctl_init(void) +{ + (void)register_sysctl_table(xen_table, 0); + return 0; +} +__initcall(xen_sysctl_init); + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/traps-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/traps-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,1029 @@ +/* + * linux/arch/i386/traps.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * Pentium III FXSR, SSE support + * Gareth Hughes <gareth@xxxxxxxxxxx>, May 2000 + */ + +/* + * 'Traps.c' handles hardware traps and faults after we have saved some + * state in 'asm.s'. + */ +#include <linux/config.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/timer.h> +#include <linux/mm.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/spinlock.h> +#include <linux/interrupt.h> +#include <linux/highmem.h> +#include <linux/kallsyms.h> +#include <linux/ptrace.h> +#include <linux/utsname.h> +#include <linux/kprobes.h> + +#ifdef CONFIG_EISA +#include <linux/ioport.h> +#include <linux/eisa.h> +#endif + +#ifdef CONFIG_MCA +#include <linux/mca.h> +#endif + +#include <asm/processor.h> +#include <asm/system.h> +#include <asm/uaccess.h> +#include <asm/io.h> +#include <asm/atomic.h> +#include <asm/debugreg.h> +#include <asm/desc.h> +#include <asm/i387.h> +#include <asm/nmi.h> + +#include <asm/smp.h> +#include <asm/arch_hooks.h> +#include <asm/kdebug.h> + +#include <linux/irq.h> +#include <linux/module.h> + +#include "mach_traps.h" + +asmlinkage int system_call(void); + +/* Do we ignore FPU interrupts ? */ +char ignore_fpu_irq = 0; + +/* + * The IDT has to be page-aligned to simplify the Pentium + * F0 0F bug workaround.. We have a special link segment + * for this. + */ +struct desc_struct idt_table[256] __attribute__((__section__(".data.idt"))) = { {0, 0}, }; + +asmlinkage void divide_error(void); +asmlinkage void debug(void); +asmlinkage void nmi(void); +asmlinkage void int3(void); +asmlinkage void overflow(void); +asmlinkage void bounds(void); +asmlinkage void invalid_op(void); +asmlinkage void device_not_available(void); +asmlinkage void coprocessor_segment_overrun(void); +asmlinkage void invalid_TSS(void); +asmlinkage void segment_not_present(void); +asmlinkage void stack_segment(void); +asmlinkage void general_protection(void); +asmlinkage void page_fault(void); +asmlinkage void coprocessor_error(void); +asmlinkage void simd_coprocessor_error(void); +asmlinkage void alignment_check(void); +asmlinkage void fixup_4gb_segment(void); +asmlinkage void machine_check(void); + +static int kstack_depth_to_print = 24; +struct notifier_block *i386die_chain; +static DEFINE_SPINLOCK(die_notifier_lock); + +int register_die_notifier(struct notifier_block *nb) +{ + int err = 0; + unsigned long flags; + spin_lock_irqsave(&die_notifier_lock, flags); + err = notifier_chain_register(&i386die_chain, nb); + spin_unlock_irqrestore(&die_notifier_lock, flags); + return err; +} + +static inline int valid_stack_ptr(struct thread_info *tinfo, void *p) +{ + return p > (void *)tinfo && + p < (void *)tinfo + THREAD_SIZE - 3; +} + +static inline unsigned long print_context_stack(struct thread_info *tinfo, + unsigned long *stack, unsigned long ebp) +{ + unsigned long addr; + +#ifdef CONFIG_FRAME_POINTER + while (valid_stack_ptr(tinfo, (void *)ebp)) { + addr = *(unsigned long *)(ebp + 4); + printk(" [<%08lx>] ", addr); + print_symbol("%s", addr); + printk("\n"); + ebp = *(unsigned long *)ebp; + } +#else + while (valid_stack_ptr(tinfo, stack)) { + addr = *stack++; + if (__kernel_text_address(addr)) { + printk(" [<%08lx>]", addr); + print_symbol(" %s", addr); + printk("\n"); + } + } +#endif + return ebp; +} + +void show_trace(struct task_struct *task, unsigned long * stack) +{ + unsigned long ebp; + + if (!task) + task = current; + + if (task == current) { + /* Grab ebp right from our regs */ + asm ("movl %%ebp, %0" : "=r" (ebp) : ); + } else { + /* ebp is the last reg pushed by switch_to */ + ebp = *(unsigned long *) task->thread.esp; + } + + while (1) { + struct thread_info *context; + context = (struct thread_info *) + ((unsigned long)stack & (~(THREAD_SIZE - 1))); + ebp = print_context_stack(context, stack, ebp); + stack = (unsigned long*)context->previous_esp; + if (!stack) + break; + printk(" =======================\n"); + } +} + +void show_stack(struct task_struct *task, unsigned long *esp) +{ + unsigned long *stack; + int i; + + if (esp == NULL) { + if (task) + esp = (unsigned long*)task->thread.esp; + else + esp = (unsigned long *)&esp; + } + + stack = esp; + for(i = 0; i < kstack_depth_to_print; i++) { + if (kstack_end(stack)) + break; + if (i && ((i % 8) == 0)) + printk("\n "); + printk("%08lx ", *stack++); + } + printk("\nCall Trace:\n"); + show_trace(task, esp); +} + +/* + * The architecture-independent dump_stack generator + */ +void dump_stack(void) +{ + unsigned long stack; + + show_trace(current, &stack); +} + +EXPORT_SYMBOL(dump_stack); + +void show_registers(struct pt_regs *regs) +{ + int i; + int in_kernel = 1; + unsigned long esp; + unsigned short ss; + + esp = (unsigned long) (&regs->esp); + ss = __KERNEL_DS; + if (regs->xcs & 2) { + in_kernel = 0; + esp = regs->esp; + ss = regs->xss & 0xffff; + } + print_modules(); + printk("CPU: %d\nEIP: %04x:[<%08lx>] %s VLI\nEFLAGS: %08lx" + " (%s) \n", + smp_processor_id(), 0xffff & regs->xcs, regs->eip, + print_tainted(), regs->eflags, system_utsname.release); + print_symbol("EIP is at %s\n", regs->eip); + printk("eax: %08lx ebx: %08lx ecx: %08lx edx: %08lx\n", + regs->eax, regs->ebx, regs->ecx, regs->edx); + printk("esi: %08lx edi: %08lx ebp: %08lx esp: %08lx\n", + regs->esi, regs->edi, regs->ebp, esp); + printk("ds: %04x es: %04x ss: %04x\n", + regs->xds & 0xffff, regs->xes & 0xffff, ss); + printk("Process %s (pid: %d, threadinfo=%p task=%p)", + current->comm, current->pid, current_thread_info(), current); + /* + * When in-kernel, we also print out the stack and code at the + * time of the fault.. + */ + if (in_kernel) { + u8 *eip; + + printk("\nStack: "); + show_stack(NULL, (unsigned long*)esp); + + printk("Code: "); + + eip = (u8 *)regs->eip - 43; + for (i = 0; i < 64; i++, eip++) { + unsigned char c; + + if (eip < (u8 *)PAGE_OFFSET || __get_user(c, eip)) { + printk(" Bad EIP value."); + break; + } + if (eip == (u8 *)regs->eip) + printk("<%02x> ", c); + else + printk("%02x ", c); + } + } + printk("\n"); +} + +static void handle_BUG(struct pt_regs *regs) +{ + unsigned short ud2; + unsigned short line; + char *file; + char c; + unsigned long eip; + + if (regs->xcs & 2) + goto no_bug; /* Not in kernel */ + + eip = regs->eip; + + if (eip < PAGE_OFFSET) + goto no_bug; + if (__get_user(ud2, (unsigned short *)eip)) + goto no_bug; + if (ud2 != 0x0b0f) + goto no_bug; + if (__get_user(line, (unsigned short *)(eip + 2))) + goto bug; + if (__get_user(file, (char **)(eip + 4)) || + (unsigned long)file < PAGE_OFFSET || __get_user(c, file)) + file = "<bad filename>"; + + printk("------------[ cut here ]------------\n"); + printk(KERN_ALERT "kernel BUG at %s:%d!\n", file, line); + +no_bug: + return; + + /* Here we know it was a BUG but file-n-line is unavailable */ +bug: + printk("Kernel BUG\n"); +} + +void die(const char * str, struct pt_regs * regs, long err) +{ + static struct { + spinlock_t lock; + u32 lock_owner; + int lock_owner_depth; + } die = { + .lock = SPIN_LOCK_UNLOCKED, + .lock_owner = -1, + .lock_owner_depth = 0 + }; + static int die_counter; + + if (die.lock_owner != _smp_processor_id()) { + console_verbose(); + spin_lock_irq(&die.lock); + die.lock_owner = smp_processor_id(); + die.lock_owner_depth = 0; + bust_spinlocks(1); + } + + if (++die.lock_owner_depth < 3) { + int nl = 0; + handle_BUG(regs); + printk(KERN_ALERT "%s: %04lx [#%d]\n", str, err & 0xffff, ++die_counter); +#ifdef CONFIG_PREEMPT + printk("PREEMPT "); + nl = 1; +#endif +#ifdef CONFIG_SMP + printk("SMP "); + nl = 1; +#endif +#ifdef CONFIG_DEBUG_PAGEALLOC + printk("DEBUG_PAGEALLOC"); + nl = 1; +#endif + if (nl) + printk("\n"); + notify_die(DIE_OOPS, (char *)str, regs, err, 255, SIGSEGV); + show_registers(regs); + } else + printk(KERN_ERR "Recursive die() failure, output suppressed\n"); + + bust_spinlocks(0); + die.lock_owner = -1; + spin_unlock_irq(&die.lock); + if (in_interrupt()) + panic("Fatal exception in interrupt"); + + if (panic_on_oops) { + printk(KERN_EMERG "Fatal exception: panic in 5 seconds\n"); + ssleep(5); + panic("Fatal exception"); + } + do_exit(SIGSEGV); +} + +static inline void die_if_kernel(const char * str, struct pt_regs * regs, long err) +{ + if (!(regs->eflags & VM_MASK) && !(2 & regs->xcs)) + die(str, regs, err); +} + +static void do_trap(int trapnr, int signr, char *str, int vm86, + struct pt_regs * regs, long error_code, siginfo_t *info) +{ + if (regs->eflags & VM_MASK) { + if (vm86) + goto vm86_trap; + goto trap_signal; + } + + if (!(regs->xcs & 2)) + goto kernel_trap; + + trap_signal: { + struct task_struct *tsk = current; + tsk->thread.error_code = error_code; + tsk->thread.trap_no = trapnr; + if (info) + force_sig_info(signr, info, tsk); + else + force_sig(signr, tsk); + return; + } + + kernel_trap: { + if (!fixup_exception(regs)) + die(str, regs, error_code); + return; + } + + vm86_trap: { + int ret = handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, trapnr); + if (ret) goto trap_signal; + return; + } +} + +#define DO_ERROR(trapnr, signr, str, name) \ +fastcall void do_##name(struct pt_regs * regs, long error_code) \ +{ \ + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ + == NOTIFY_STOP) \ + return; \ + do_trap(trapnr, signr, str, 0, regs, error_code, NULL); \ +} + +#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ +fastcall void do_##name(struct pt_regs * regs, long error_code) \ +{ \ + siginfo_t info; \ + info.si_signo = signr; \ + info.si_errno = 0; \ + info.si_code = sicode; \ + info.si_addr = (void __user *)siaddr; \ + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ + == NOTIFY_STOP) \ + return; \ + do_trap(trapnr, signr, str, 0, regs, error_code, &info); \ +} + +#define DO_VM86_ERROR(trapnr, signr, str, name) \ +fastcall void do_##name(struct pt_regs * regs, long error_code) \ +{ \ + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ + == NOTIFY_STOP) \ + return; \ + do_trap(trapnr, signr, str, 1, regs, error_code, NULL); \ +} + +#define DO_VM86_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ +fastcall void do_##name(struct pt_regs * regs, long error_code) \ +{ \ + siginfo_t info; \ + info.si_signo = signr; \ + info.si_errno = 0; \ + info.si_code = sicode; \ + info.si_addr = (void __user *)siaddr; \ + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ + == NOTIFY_STOP) \ + return; \ + do_trap(trapnr, signr, str, 1, regs, error_code, &info); \ +} + +DO_VM86_ERROR_INFO( 0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->eip) +#ifndef CONFIG_KPROBES +DO_VM86_ERROR( 3, SIGTRAP, "int3", int3) +#endif +DO_VM86_ERROR( 4, SIGSEGV, "overflow", overflow) +DO_VM86_ERROR( 5, SIGSEGV, "bounds", bounds) +DO_ERROR_INFO( 6, SIGILL, "invalid operand", invalid_op, ILL_ILLOPN, regs->eip) +DO_VM86_ERROR( 7, SIGSEGV, "device not available", device_not_available) +DO_ERROR( 9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun) +DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS) +DO_ERROR(11, SIGBUS, "segment not present", segment_not_present) +DO_ERROR(12, SIGBUS, "stack segment", stack_segment) +DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0) +#ifdef CONFIG_X86_MCE +DO_ERROR(18, SIGBUS, "machine check", machine_check) +#endif +DO_ERROR_INFO(32, SIGSEGV, "iret exception", iret_error, ILL_BADSTK, 0) + +fastcall void do_general_protection(struct pt_regs * regs, long error_code) +{ + /* + * If we trapped on an LDT access then ensure that the default_ldt is + * loaded, if nothing else. We load default_ldt lazily because LDT + * switching costs time and many applications don't need it. + */ + if (unlikely((error_code & 6) == 4)) { + unsigned long ldt; + __asm__ __volatile__ ("sldt %0" : "=r" (ldt)); + if (ldt == 0) { + xen_set_ldt((unsigned long)&default_ldt[0], 5); + return; + } + } + + if (regs->eflags & VM_MASK) + goto gp_in_vm86; + + if (!(regs->xcs & 2)) + goto gp_in_kernel; + + current->thread.error_code = error_code; + current->thread.trap_no = 13; + force_sig(SIGSEGV, current); + return; + +gp_in_vm86: + local_irq_enable(); + handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); + return; + +gp_in_kernel: + if (!fixup_exception(regs)) { + if (notify_die(DIE_GPF, "general protection fault", regs, + error_code, 13, SIGSEGV) == NOTIFY_STOP) + return; + die("general protection fault", regs, error_code); + } +} + +static void mem_parity_error(unsigned char reason, struct pt_regs * regs) +{ + printk("Uhhuh. NMI received. Dazed and confused, but trying to continue\n"); + printk("You probably have a hardware problem with your RAM chips\n"); + + /* Clear and disable the memory parity error line. */ + clear_mem_error(reason); +} + +static void io_check_error(unsigned char reason, struct pt_regs * regs) +{ + printk("NMI: IOCK error (debug interrupt?)\n"); + show_registers(regs); + + /* Re-enable the IOCK line, wait for a few seconds */ + clear_io_check_error(reason); +} + +static void unknown_nmi_error(unsigned char reason, struct pt_regs * regs) +{ +#ifdef CONFIG_MCA + /* Might actually be able to figure out what the guilty party + * is. */ + if( MCA_bus ) { + mca_handle_nmi(); + return; + } +#endif + printk("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n", + reason, smp_processor_id()); + printk("Dazed and confused, but trying to continue\n"); + printk("Do you have a strange power saving mode enabled?\n"); +} + +static DEFINE_SPINLOCK(nmi_print_lock); + +void die_nmi (struct pt_regs *regs, const char *msg) +{ + spin_lock(&nmi_print_lock); + /* + * We are in trouble anyway, lets at least try + * to get a message out. + */ + bust_spinlocks(1); + printk(msg); + printk(" on CPU%d, eip %08lx, registers:\n", + smp_processor_id(), regs->eip); + show_registers(regs); + printk("console shuts up ...\n"); + console_silent(); + spin_unlock(&nmi_print_lock); + bust_spinlocks(0); + do_exit(SIGSEGV); +} + +static void default_do_nmi(struct pt_regs * regs) +{ + unsigned char reason = 0; + + /* Only the BSP gets external NMIs from the system. */ + if (!smp_processor_id()) + reason = get_nmi_reason(); + + if (!(reason & 0xc0)) { + if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 0, SIGINT) + == NOTIFY_STOP) + return; +#ifdef CONFIG_X86_LOCAL_APIC + /* + * Ok, so this is none of the documented NMI sources, + * so it must be the NMI watchdog. + */ + if (nmi_watchdog) { + nmi_watchdog_tick(regs); + return; + } +#endif + unknown_nmi_error(reason, regs); + return; + } + if (notify_die(DIE_NMI, "nmi", regs, reason, 0, SIGINT) == NOTIFY_STOP) + return; + if (reason & 0x80) + mem_parity_error(reason, regs); + if (reason & 0x40) + io_check_error(reason, regs); + /* + * Reassert NMI in case it became active meanwhile + * as it's edge-triggered. + */ + reassert_nmi(); +} + +static int dummy_nmi_callback(struct pt_regs * regs, int cpu) +{ + return 0; +} + +static nmi_callback_t nmi_callback = dummy_nmi_callback; + +fastcall void do_nmi(struct pt_regs * regs, long error_code) +{ + int cpu; + + nmi_enter(); + + cpu = smp_processor_id(); + +#ifdef CONFIG_HOTPLUG_CPU + if (!cpu_online(cpu)) { + nmi_exit(); + return; + } +#endif + + ++nmi_count(cpu); + + if (!nmi_callback(regs, cpu)) + default_do_nmi(regs); + + nmi_exit(); +} + +void set_nmi_callback(nmi_callback_t callback) +{ + nmi_callback = callback; +} + +void unset_nmi_callback(void) +{ + nmi_callback = dummy_nmi_callback; +} + +#ifdef CONFIG_KPROBES +fastcall void do_int3(struct pt_regs *regs, long error_code) +{ + if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) + == NOTIFY_STOP) + return; + /* This is an interrupt gate, because kprobes wants interrupts + disabled. Normal trap handlers don't. */ + restore_interrupts(regs); + do_trap(3, SIGTRAP, "int3", 1, regs, error_code, NULL); +} +#endif + +/* + * Our handling of the processor debug registers is non-trivial. + * We do not clear them on entry and exit from the kernel. Therefore + * it is possible to get a watchpoint trap here from inside the kernel. + * However, the code in ./ptrace.c has ensured that the user can + * only set watchpoints on userspace addresses. Therefore the in-kernel + * watchpoint trap can only occur in code which is reading/writing + * from user space. Such code must not hold kernel locks (since it + * can equally take a page fault), therefore it is safe to call + * force_sig_info even though that claims and releases locks. + * + * Code in ./signal.c ensures that the debug control register + * is restored before we deliver any signal, and therefore that + * user code runs with the correct debug control register even though + * we clear it here. + * + * Being careful here means that we don't have to be as careful in a + * lot of more complicated places (task switching can be a bit lazy + * about restoring all the debug state, and ptrace doesn't have to + * find every occurrence of the TF bit that could be saved away even + * by user code) + */ +fastcall void do_debug(struct pt_regs * regs, long error_code) +{ + unsigned int condition; + struct task_struct *tsk = current; + + condition = HYPERVISOR_get_debugreg(6); + + if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code, + SIGTRAP) == NOTIFY_STOP) + return; + /* It's safe to allow irq's after DR6 has been saved */ + if (regs->eflags & X86_EFLAGS_IF) + local_irq_enable(); + + /* Mask out spurious debug traps due to lazy DR7 setting */ + if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) { + if (!tsk->thread.debugreg[7]) + goto clear_dr7; + } + + if (regs->eflags & VM_MASK) + goto debug_vm86; + + /* Save debug status register where ptrace can see it */ + tsk->thread.debugreg[6] = condition; + + /* + * Single-stepping through TF: make sure we ignore any events in + * kernel space (but re-enable TF when returning to user mode). + */ + if (condition & DR_STEP) { + /* + * We already checked v86 mode above, so we can + * check for kernel mode by just checking the CPL + * of CS. + */ + if ((regs->xcs & 2) == 0) + goto clear_TF_reenable; + } + + /* Ok, finally something we can handle */ + send_sigtrap(tsk, regs, error_code); + + /* Disable additional traps. They'll be re-enabled when + * the signal is delivered. + */ +clear_dr7: + HYPERVISOR_set_debugreg(7, 0); + return; + +debug_vm86: + handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1); + return; + +clear_TF_reenable: + set_tsk_thread_flag(tsk, TIF_SINGLESTEP); + regs->eflags &= ~TF_MASK; + return; +} + +/* + * Note that we play around with the 'TS' bit in an attempt to get + * the correct behaviour even in the presence of the asynchronous + * IRQ13 behaviour + */ +void math_error(void __user *eip) +{ + struct task_struct * task; + siginfo_t info; + unsigned short cwd, swd; + + /* + * Save the info for the exception handler and clear the error. + */ + task = current; + save_init_fpu(task); + task->thread.trap_no = 16; + task->thread.error_code = 0; + info.si_signo = SIGFPE; + info.si_errno = 0; + info.si_code = __SI_FAULT; + info.si_addr = eip; + /* + * (~cwd & swd) will mask out exceptions that are not set to unmasked + * status. 0x3f is the exception bits in these regs, 0x200 is the + * C1 reg you need in case of a stack fault, 0x040 is the stack + * fault bit. We should only be taking one exception at a time, + * so if this combination doesn't produce any single exception, + * then we have a bad program that isn't syncronizing its FPU usage + * and it will suffer the consequences since we won't be able to + * fully reproduce the context of the exception + */ + cwd = get_fpu_cwd(task); + swd = get_fpu_swd(task); + switch (((~cwd) & swd & 0x3f) | (swd & 0x240)) { + case 0x000: + default: + break; + case 0x001: /* Invalid Op */ + case 0x041: /* Stack Fault */ + case 0x241: /* Stack Fault | Direction */ + info.si_code = FPE_FLTINV; + /* Should we clear the SF or let user space do it ???? */ + break; + case 0x002: /* Denormalize */ + case 0x010: /* Underflow */ + info.si_code = FPE_FLTUND; + break; + case 0x004: /* Zero Divide */ + info.si_code = FPE_FLTDIV; + break; + case 0x008: /* Overflow */ + info.si_code = FPE_FLTOVF; + break; + case 0x020: /* Precision */ + info.si_code = FPE_FLTRES; + break; + } + force_sig_info(SIGFPE, &info, task); +} + +fastcall void do_coprocessor_error(struct pt_regs * regs, long error_code) +{ + ignore_fpu_irq = 1; + math_error((void __user *)regs->eip); +} + +static void simd_math_error(void __user *eip) +{ + struct task_struct * task; + siginfo_t info; + unsigned short mxcsr; + + /* + * Save the info for the exception handler and clear the error. + */ + task = current; + save_init_fpu(task); + task->thread.trap_no = 19; + task->thread.error_code = 0; + info.si_signo = SIGFPE; + info.si_errno = 0; + info.si_code = __SI_FAULT; + info.si_addr = eip; + /* + * The SIMD FPU exceptions are handled a little differently, as there + * is only a single status/control register. Thus, to determine which + * unmasked exception was caught we must mask the exception mask bits + * at 0x1f80, and then use these to mask the exception bits at 0x3f. + */ + mxcsr = get_fpu_mxcsr(task); + switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) { + case 0x000: + default: + break; + case 0x001: /* Invalid Op */ + info.si_code = FPE_FLTINV; + break; + case 0x002: /* Denormalize */ + case 0x010: /* Underflow */ + info.si_code = FPE_FLTUND; + break; + case 0x004: /* Zero Divide */ + info.si_code = FPE_FLTDIV; + break; + case 0x008: /* Overflow */ + info.si_code = FPE_FLTOVF; + break; + case 0x020: /* Precision */ + info.si_code = FPE_FLTRES; + break; + } + force_sig_info(SIGFPE, &info, task); +} + +fastcall void do_simd_coprocessor_error(struct pt_regs * regs, + long error_code) +{ + if (cpu_has_xmm) { + /* Handle SIMD FPU exceptions on PIII+ processors. */ + ignore_fpu_irq = 1; + simd_math_error((void __user *)regs->eip); + } else { + /* + * Handle strange cache flush from user space exception + * in all other cases. This is undocumented behaviour. + */ + if (regs->eflags & VM_MASK) { + handle_vm86_fault((struct kernel_vm86_regs *)regs, + error_code); + return; + } + die_if_kernel("cache flush denied", regs, error_code); + current->thread.trap_no = 19; + current->thread.error_code = error_code; + force_sig(SIGSEGV, current); + } +} + +#ifndef CONFIG_XEN +fastcall void setup_x86_bogus_stack(unsigned char * stk) +{ + unsigned long *switch16_ptr, *switch32_ptr; + struct pt_regs *regs; + unsigned long stack_top, stack_bot; + unsigned short iret_frame16_off; + int cpu = smp_processor_id(); + /* reserve the space on 32bit stack for the magic switch16 pointer */ + memmove(stk, stk + 8, sizeof(struct pt_regs)); + switch16_ptr = (unsigned long *)(stk + sizeof(struct pt_regs)); + regs = (struct pt_regs *)stk; + /* now the switch32 on 16bit stack */ + stack_bot = (unsigned long)&per_cpu(cpu_16bit_stack, cpu); + stack_top = stack_bot + CPU_16BIT_STACK_SIZE; + switch32_ptr = (unsigned long *)(stack_top - 8); + iret_frame16_off = CPU_16BIT_STACK_SIZE - 8 - 20; + /* copy iret frame on 16bit stack */ + memcpy((void *)(stack_bot + iret_frame16_off), &regs->eip, 20); + /* fill in the switch pointers */ + switch16_ptr[0] = (regs->esp & 0xffff0000) | iret_frame16_off; + switch16_ptr[1] = __ESPFIX_SS; + switch32_ptr[0] = (unsigned long)stk + sizeof(struct pt_regs) + + 8 - CPU_16BIT_STACK_SIZE; + switch32_ptr[1] = __KERNEL_DS; +} + +fastcall unsigned char * fixup_x86_bogus_stack(unsigned short sp) +{ + unsigned long *switch32_ptr; + unsigned char *stack16, *stack32; + unsigned long stack_top, stack_bot; + int len; + int cpu = smp_processor_id(); + stack_bot = (unsigned long)&per_cpu(cpu_16bit_stack, cpu); + stack_top = stack_bot + CPU_16BIT_STACK_SIZE; + switch32_ptr = (unsigned long *)(stack_top - 8); + /* copy the data from 16bit stack to 32bit stack */ + len = CPU_16BIT_STACK_SIZE - 8 - sp; + stack16 = (unsigned char *)(stack_bot + sp); + stack32 = (unsigned char *) + (switch32_ptr[0] + CPU_16BIT_STACK_SIZE - 8 - len); + memcpy(stack32, stack16, len); + return stack32; +} +#endif + +/* + * 'math_state_restore()' saves the current math information in the + * old math state array, and gets the new ones from the current task + * + * Careful.. There are problems with IBM-designed IRQ13 behaviour. + * Don't touch unless you *really* know how it works. + * + * Must be called with kernel preemption disabled (in this case, + * local interrupts are disabled at the call-site in entry.S). + */ +asmlinkage void math_state_restore(struct pt_regs regs) +{ + struct thread_info *thread = current_thread_info(); + struct task_struct *tsk = thread->task; + + /* NB. 'clts' is done for us by Xen during virtual trap. */ + if (!tsk_used_math(tsk)) + init_fpu(tsk); + restore_fpu(tsk); + thread->status |= TS_USEDFPU; /* So we fnsave on switch_to() */ +} + +#ifndef CONFIG_MATH_EMULATION + +asmlinkage void math_emulate(long arg) +{ + printk("math-emulation not enabled and no coprocessor found.\n"); + printk("killing %s.\n",current->comm); + force_sig(SIGFPE,current); + schedule(); +} + +#endif /* CONFIG_MATH_EMULATION */ + +#ifdef CONFIG_X86_F00F_BUG +void __init trap_init_f00f_bug(void) +{ + __set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO); + + /* + * Update the IDT descriptor and reload the IDT so that + * it uses the read-only mapped virtual address. + */ + idt_descr.address = fix_to_virt(FIX_F00F_IDT); + __asm__ __volatile__("lidt %0" : : "m" (idt_descr)); +} +#endif + + +/* + * NB. All these are "trap gates" (i.e. events_mask isn't set) except + * for those that specify <dpl>|4 in the second field. + */ +static trap_info_t trap_table[] = { + { 0, 0, __KERNEL_CS, (unsigned long)divide_error }, + { 1, 0|4, __KERNEL_CS, (unsigned long)debug }, + { 3, 3|4, __KERNEL_CS, (unsigned long)int3 }, + { 4, 3, __KERNEL_CS, (unsigned long)overflow }, + { 5, 3, __KERNEL_CS, (unsigned long)bounds }, + { 6, 0, __KERNEL_CS, (unsigned long)invalid_op }, + { 7, 0|4, __KERNEL_CS, (unsigned long)device_not_available }, + { 9, 0, __KERNEL_CS, (unsigned long)coprocessor_segment_overrun }, + { 10, 0, __KERNEL_CS, (unsigned long)invalid_TSS }, + { 11, 0, __KERNEL_CS, (unsigned long)segment_not_present }, + { 12, 0, __KERNEL_CS, (unsigned long)stack_segment }, + { 13, 0, __KERNEL_CS, (unsigned long)general_protection }, + { 14, 0|4, __KERNEL_CS, (unsigned long)page_fault }, + { 15, 0, __KERNEL_CS, (unsigned long)fixup_4gb_segment }, + { 16, 0, __KERNEL_CS, (unsigned long)coprocessor_error }, + { 17, 0, __KERNEL_CS, (unsigned long)alignment_check }, +#ifdef CONFIG_X86_MCE + { 18, 0, __KERNEL_CS, (unsigned long)machine_check }, +#endif + { 19, 0, __KERNEL_CS, (unsigned long)simd_coprocessor_error }, + { SYSCALL_VECTOR, 3, __KERNEL_CS, (unsigned long)system_call }, + { 0, 0, 0, 0 } +}; + +void __init trap_init(void) +{ + HYPERVISOR_set_trap_table(trap_table); + + /* + * default LDT is a single-entry callgate to lcall7 for iBCS + * and a callgate to lcall27 for Solaris/x86 binaries + */ + make_lowmem_page_readonly( + &default_ldt[0], XENFEAT_writable_descriptor_tables); + + /* + * Should be a barrier for any external CPU state. + */ + cpu_init(); +} + +void smp_trap_init(trap_info_t *trap_ctxt) +{ + trap_info_t *t = trap_table; + int i; + + for (i = 0; i < 256; i++) { + trap_ctxt[i].vector = i; + trap_ctxt[i].cs = FLAT_KERNEL_CS; + } + + for (t = trap_table; t->address; t++) { + trap_ctxt[t->vector].flags = t->flags; + trap_ctxt[t->vector].cs = t->cs; + trap_ctxt[t->vector].address = t->address; + } +} + +static int __init kstack_setup(char *s) +{ + kstack_depth_to_print = simple_strtoul(s, NULL, 0); + return 0; +} +__setup("kstack=", kstack_setup); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/traps.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/traps.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,1077 @@ +/* + * linux/arch/i386/traps.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * Pentium III FXSR, SSE support + * Gareth Hughes <gareth@xxxxxxxxxxx>, May 2000 + */ + +/* + * 'Traps.c' handles hardware traps and faults after we have saved some + * state in 'asm.s'. + */ +#include <linux/config.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/timer.h> +#include <linux/mm.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/spinlock.h> +#include <linux/interrupt.h> +#include <linux/highmem.h> +#include <linux/kallsyms.h> +#include <linux/ptrace.h> +#include <linux/utsname.h> +#include <linux/kprobes.h> + +#ifdef CONFIG_EISA +#include <linux/ioport.h> +#include <linux/eisa.h> +#endif + +#ifdef CONFIG_MCA +#include <linux/mca.h> +#endif + +#include <asm/processor.h> +#include <asm/system.h> +#include <asm/uaccess.h> +#include <asm/io.h> +#include <asm/atomic.h> +#include <asm/debugreg.h> +#include <asm/desc.h> +#include <asm/i387.h> +#include <asm/nmi.h> + +#include <asm/smp.h> +#include <asm/arch_hooks.h> +#include <asm/kdebug.h> + +#include <linux/irq.h> +#include <linux/module.h> + +#include "mach_traps.h" + +asmlinkage int system_call(void); + +struct desc_struct default_ldt[] = { { 0, 0 }, { 0, 0 }, { 0, 0 }, + { 0, 0 }, { 0, 0 } }; + +/* Do we ignore FPU interrupts ? */ +char ignore_fpu_irq = 0; + +/* + * The IDT has to be page-aligned to simplify the Pentium + * F0 0F bug workaround.. We have a special link segment + * for this. + */ +struct desc_struct idt_table[256] __attribute__((__section__(".data.idt"))) = { {0, 0}, }; + +asmlinkage void divide_error(void); +asmlinkage void debug(void); +asmlinkage void nmi(void); +asmlinkage void int3(void); +asmlinkage void overflow(void); +asmlinkage void bounds(void); +asmlinkage void invalid_op(void); +asmlinkage void device_not_available(void); +asmlinkage void coprocessor_segment_overrun(void); +asmlinkage void invalid_TSS(void); +asmlinkage void segment_not_present(void); +asmlinkage void stack_segment(void); +asmlinkage void general_protection(void); +asmlinkage void page_fault(void); +asmlinkage void coprocessor_error(void); +asmlinkage void simd_coprocessor_error(void); +asmlinkage void alignment_check(void); +asmlinkage void spurious_interrupt_bug(void); +asmlinkage void machine_check(void); + +static int kstack_depth_to_print = 24; +struct notifier_block *i386die_chain; +static DEFINE_SPINLOCK(die_notifier_lock); + +int register_die_notifier(struct notifier_block *nb) +{ + int err = 0; + unsigned long flags; + spin_lock_irqsave(&die_notifier_lock, flags); + err = notifier_chain_register(&i386die_chain, nb); + spin_unlock_irqrestore(&die_notifier_lock, flags); + return err; +} + +static inline int valid_stack_ptr(struct thread_info *tinfo, void *p) +{ + return p > (void *)tinfo && + p < (void *)tinfo + THREAD_SIZE - 3; +} + +static inline unsigned long print_context_stack(struct thread_info *tinfo, + unsigned long *stack, unsigned long ebp) +{ + unsigned long addr; + +#ifdef CONFIG_FRAME_POINTER + while (valid_stack_ptr(tinfo, (void *)ebp)) { + addr = *(unsigned long *)(ebp + 4); + printk(" [<%08lx>] ", addr); + print_symbol("%s", addr); + printk("\n"); + ebp = *(unsigned long *)ebp; + } +#else + while (valid_stack_ptr(tinfo, stack)) { + addr = *stack++; + if (__kernel_text_address(addr)) { + printk(" [<%08lx>]", addr); + print_symbol(" %s", addr); + printk("\n"); + } + } +#endif + return ebp; +} + +void show_trace(struct task_struct *task, unsigned long * stack) +{ + unsigned long ebp; + + if (!task) + task = current; + + if (task == current) { + /* Grab ebp right from our regs */ + asm ("movl %%ebp, %0" : "=r" (ebp) : ); + } else { + /* ebp is the last reg pushed by switch_to */ + ebp = *(unsigned long *) task->thread.esp; + } + + while (1) { + struct thread_info *context; + context = (struct thread_info *) + ((unsigned long)stack & (~(THREAD_SIZE - 1))); + ebp = print_context_stack(context, stack, ebp); + stack = (unsigned long*)context->previous_esp; + if (!stack) + break; + printk(" =======================\n"); + } +} + +void show_stack(struct task_struct *task, unsigned long *esp) +{ + unsigned long *stack; + int i; + + if (esp == NULL) { + if (task) + esp = (unsigned long*)task->thread.esp; + else + esp = (unsigned long *)&esp; + } + + stack = esp; + for(i = 0; i < kstack_depth_to_print; i++) { + if (kstack_end(stack)) + break; + if (i && ((i % 8) == 0)) + printk("\n "); + printk("%08lx ", *stack++); + } + printk("\nCall Trace:\n"); + show_trace(task, esp); +} + +/* + * The architecture-independent dump_stack generator + */ +void dump_stack(void) +{ + unsigned long stack; + + show_trace(current, &stack); +} + +EXPORT_SYMBOL(dump_stack); + +void show_registers(struct pt_regs *regs) +{ + int i; + int in_kernel = 1; + unsigned long esp; + unsigned short ss; + + esp = (unsigned long) (&regs->esp); + ss = __KERNEL_DS; + if (regs->xcs & 3) { + in_kernel = 0; + esp = regs->esp; + ss = regs->xss & 0xffff; + } + print_modules(); + printk("CPU: %d\nEIP: %04x:[<%08lx>] %s VLI\nEFLAGS: %08lx" + " (%s) \n", + smp_processor_id(), 0xffff & regs->xcs, regs->eip, + print_tainted(), regs->eflags, system_utsname.release); + print_symbol("EIP is at %s\n", regs->eip); + printk("eax: %08lx ebx: %08lx ecx: %08lx edx: %08lx\n", + regs->eax, regs->ebx, regs->ecx, regs->edx); + printk("esi: %08lx edi: %08lx ebp: %08lx esp: %08lx\n", + regs->esi, regs->edi, regs->ebp, esp); + printk("ds: %04x es: %04x ss: %04x\n", + regs->xds & 0xffff, regs->xes & 0xffff, ss); + printk("Process %s (pid: %d, threadinfo=%p task=%p)", + current->comm, current->pid, current_thread_info(), current); + /* + * When in-kernel, we also print out the stack and code at the + * time of the fault.. + */ + if (in_kernel) { + u8 *eip; + + printk("\nStack: "); + show_stack(NULL, (unsigned long*)esp); + + printk("Code: "); + + eip = (u8 *)regs->eip - 43; + for (i = 0; i < 64; i++, eip++) { + unsigned char c; + + if (eip < (u8 *)PAGE_OFFSET || __get_user(c, eip)) { + printk(" Bad EIP value."); + break; + } + if (eip == (u8 *)regs->eip) + printk("<%02x> ", c); + else + printk("%02x ", c); + } + } + printk("\n"); +} + +static void handle_BUG(struct pt_regs *regs) +{ + unsigned short ud2; + unsigned short line; + char *file; + char c; + unsigned long eip; + + if (regs->xcs & 3) + goto no_bug; /* Not in kernel */ + + eip = regs->eip; + + if (eip < PAGE_OFFSET) + goto no_bug; + if (__get_user(ud2, (unsigned short *)eip)) + goto no_bug; + if (ud2 != 0x0b0f) + goto no_bug; + if (__get_user(line, (unsigned short *)(eip + 2))) + goto bug; + if (__get_user(file, (char **)(eip + 4)) || + (unsigned long)file < PAGE_OFFSET || __get_user(c, file)) + file = "<bad filename>"; + + printk("------------[ cut here ]------------\n"); + printk(KERN_ALERT "kernel BUG at %s:%d!\n", file, line); + +no_bug: + return; + + /* Here we know it was a BUG but file-n-line is unavailable */ +bug: + printk("Kernel BUG\n"); +} + +void die(const char * str, struct pt_regs * regs, long err) +{ + static struct { + spinlock_t lock; + u32 lock_owner; + int lock_owner_depth; + } die = { + .lock = SPIN_LOCK_UNLOCKED, + .lock_owner = -1, + .lock_owner_depth = 0 + }; + static int die_counter; + + if (die.lock_owner != _smp_processor_id()) { + console_verbose(); + spin_lock_irq(&die.lock); + die.lock_owner = smp_processor_id(); + die.lock_owner_depth = 0; + bust_spinlocks(1); + } + + if (++die.lock_owner_depth < 3) { + int nl = 0; + handle_BUG(regs); + printk(KERN_ALERT "%s: %04lx [#%d]\n", str, err & 0xffff, ++die_counter); +#ifdef CONFIG_PREEMPT + printk("PREEMPT "); + nl = 1; +#endif +#ifdef CONFIG_SMP + printk("SMP "); + nl = 1; +#endif +#ifdef CONFIG_DEBUG_PAGEALLOC + printk("DEBUG_PAGEALLOC"); + nl = 1; +#endif + if (nl) + printk("\n"); + notify_die(DIE_OOPS, (char *)str, regs, err, 255, SIGSEGV); + show_registers(regs); + } else + printk(KERN_ERR "Recursive die() failure, output suppressed\n"); + + bust_spinlocks(0); + die.lock_owner = -1; + spin_unlock_irq(&die.lock); + if (in_interrupt()) + panic("Fatal exception in interrupt"); + + if (panic_on_oops) { + printk(KERN_EMERG "Fatal exception: panic in 5 seconds\n"); + ssleep(5); + panic("Fatal exception"); + } + do_exit(SIGSEGV); +} + +static inline void die_if_kernel(const char * str, struct pt_regs * regs, long err) +{ + if (!(regs->eflags & VM_MASK) && !(3 & regs->xcs)) + die(str, regs, err); +} + +static void do_trap(int trapnr, int signr, char *str, int vm86, + struct pt_regs * regs, long error_code, siginfo_t *info) +{ + if (regs->eflags & VM_MASK) { + if (vm86) + goto vm86_trap; + goto trap_signal; + } + + if (!(regs->xcs & 3)) + goto kernel_trap; + + trap_signal: { + struct task_struct *tsk = current; + tsk->thread.error_code = error_code; + tsk->thread.trap_no = trapnr; + if (info) + force_sig_info(signr, info, tsk); + else + force_sig(signr, tsk); + return; + } + + kernel_trap: { + if (!fixup_exception(regs)) + die(str, regs, error_code); + return; + } + + vm86_trap: { + int ret = handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, trapnr); + if (ret) goto trap_signal; + return; + } +} + +#define DO_ERROR(trapnr, signr, str, name) \ +fastcall void do_##name(struct pt_regs * regs, long error_code) \ +{ \ + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ + == NOTIFY_STOP) \ + return; \ + do_trap(trapnr, signr, str, 0, regs, error_code, NULL); \ +} + +#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ +fastcall void do_##name(struct pt_regs * regs, long error_code) \ +{ \ + siginfo_t info; \ + info.si_signo = signr; \ + info.si_errno = 0; \ + info.si_code = sicode; \ + info.si_addr = (void __user *)siaddr; \ + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ + == NOTIFY_STOP) \ + return; \ + do_trap(trapnr, signr, str, 0, regs, error_code, &info); \ +} + +#define DO_VM86_ERROR(trapnr, signr, str, name) \ +fastcall void do_##name(struct pt_regs * regs, long error_code) \ +{ \ + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ + == NOTIFY_STOP) \ + return; \ + do_trap(trapnr, signr, str, 1, regs, error_code, NULL); \ +} + +#define DO_VM86_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ +fastcall void do_##name(struct pt_regs * regs, long error_code) \ +{ \ + siginfo_t info; \ + info.si_signo = signr; \ + info.si_errno = 0; \ + info.si_code = sicode; \ + info.si_addr = (void __user *)siaddr; \ + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ + == NOTIFY_STOP) \ + return; \ + do_trap(trapnr, signr, str, 1, regs, error_code, &info); \ +} + +DO_VM86_ERROR_INFO( 0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->eip) +#ifndef CONFIG_KPROBES +DO_VM86_ERROR( 3, SIGTRAP, "int3", int3) +#endif +DO_VM86_ERROR( 4, SIGSEGV, "overflow", overflow) +DO_VM86_ERROR( 5, SIGSEGV, "bounds", bounds) +DO_ERROR_INFO( 6, SIGILL, "invalid operand", invalid_op, ILL_ILLOPN, regs->eip) +DO_ERROR( 9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun) +DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS) +DO_ERROR(11, SIGBUS, "segment not present", segment_not_present) +DO_ERROR(12, SIGBUS, "stack segment", stack_segment) +DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0) +DO_ERROR_INFO(32, SIGSEGV, "iret exception", iret_error, ILL_BADSTK, 0) + +fastcall void do_general_protection(struct pt_regs * regs, long error_code) +{ + int cpu = get_cpu(); + struct tss_struct *tss = &per_cpu(init_tss, cpu); + struct thread_struct *thread = &current->thread; + + /* + * Perform the lazy TSS's I/O bitmap copy. If the TSS has an + * invalid offset set (the LAZY one) and the faulting thread has + * a valid I/O bitmap pointer, we copy the I/O bitmap in the TSS + * and we set the offset field correctly. Then we let the CPU to + * restart the faulting instruction. + */ + if (tss->io_bitmap_base == INVALID_IO_BITMAP_OFFSET_LAZY && + thread->io_bitmap_ptr) { + memcpy(tss->io_bitmap, thread->io_bitmap_ptr, + thread->io_bitmap_max); + /* + * If the previously set map was extending to higher ports + * than the current one, pad extra space with 0xff (no access). + */ + if (thread->io_bitmap_max < tss->io_bitmap_max) + memset((char *) tss->io_bitmap + + thread->io_bitmap_max, 0xff, + tss->io_bitmap_max - thread->io_bitmap_max); + tss->io_bitmap_max = thread->io_bitmap_max; + tss->io_bitmap_base = IO_BITMAP_OFFSET; + put_cpu(); + return; + } + put_cpu(); + + if (regs->eflags & VM_MASK) + goto gp_in_vm86; + + if (!(regs->xcs & 3)) + goto gp_in_kernel; + + current->thread.error_code = error_code; + current->thread.trap_no = 13; + force_sig(SIGSEGV, current); + return; + +gp_in_vm86: + local_irq_enable(); + handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); + return; + +gp_in_kernel: + if (!fixup_exception(regs)) { + if (notify_die(DIE_GPF, "general protection fault", regs, + error_code, 13, SIGSEGV) == NOTIFY_STOP) + return; + die("general protection fault", regs, error_code); + } +} + +static void mem_parity_error(unsigned char reason, struct pt_regs * regs) +{ + printk("Uhhuh. NMI received. Dazed and confused, but trying to continue\n"); + printk("You probably have a hardware problem with your RAM chips\n"); + + /* Clear and disable the memory parity error line. */ + clear_mem_error(reason); +} + +static void io_check_error(unsigned char reason, struct pt_regs * regs) +{ + printk("NMI: IOCK error (debug interrupt?)\n"); + show_registers(regs); + + /* Re-enable the IOCK line, wait for a few seconds */ + clear_io_check_error(reason); +} + +static void unknown_nmi_error(unsigned char reason, struct pt_regs * regs) +{ +#ifdef CONFIG_MCA + /* Might actually be able to figure out what the guilty party + * is. */ + if( MCA_bus ) { + mca_handle_nmi(); + return; + } +#endif + printk("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n", + reason, smp_processor_id()); + printk("Dazed and confused, but trying to continue\n"); + printk("Do you have a strange power saving mode enabled?\n"); +} + +static DEFINE_SPINLOCK(nmi_print_lock); + +void die_nmi (struct pt_regs *regs, const char *msg) +{ + spin_lock(&nmi_print_lock); + /* + * We are in trouble anyway, lets at least try + * to get a message out. + */ + bust_spinlocks(1); + printk(msg); + printk(" on CPU%d, eip %08lx, registers:\n", + smp_processor_id(), regs->eip); + show_registers(regs); + printk("console shuts up ...\n"); + console_silent(); + spin_unlock(&nmi_print_lock); + bust_spinlocks(0); + do_exit(SIGSEGV); +} + +static void default_do_nmi(struct pt_regs * regs) +{ + unsigned char reason = 0; + + /* Only the BSP gets external NMIs from the system. */ + if (!smp_processor_id()) + reason = get_nmi_reason(); + + if (!(reason & 0xc0)) { + if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 0, SIGINT) + == NOTIFY_STOP) + return; +#ifdef CONFIG_X86_LOCAL_APIC + /* + * Ok, so this is none of the documented NMI sources, + * so it must be the NMI watchdog. + */ + if (nmi_watchdog) { + nmi_watchdog_tick(regs); + return; + } +#endif + unknown_nmi_error(reason, regs); + return; + } + if (notify_die(DIE_NMI, "nmi", regs, reason, 0, SIGINT) == NOTIFY_STOP) + return; + if (reason & 0x80) + mem_parity_error(reason, regs); + if (reason & 0x40) + io_check_error(reason, regs); + /* + * Reassert NMI in case it became active meanwhile + * as it's edge-triggered. + */ + reassert_nmi(); +} + +static int dummy_nmi_callback(struct pt_regs * regs, int cpu) +{ + return 0; +} + +static nmi_callback_t nmi_callback = dummy_nmi_callback; + +fastcall void do_nmi(struct pt_regs * regs, long error_code) +{ + int cpu; + + nmi_enter(); + + cpu = smp_processor_id(); + ++nmi_count(cpu); + + if (!nmi_callback(regs, cpu)) + default_do_nmi(regs); + + nmi_exit(); +} + +void set_nmi_callback(nmi_callback_t callback) +{ + nmi_callback = callback; +} + +void unset_nmi_callback(void) +{ + nmi_callback = dummy_nmi_callback; +} + +#ifdef CONFIG_KPROBES +fastcall void do_int3(struct pt_regs *regs, long error_code) +{ + if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) + == NOTIFY_STOP) + return; + /* This is an interrupt gate, because kprobes wants interrupts + disabled. Normal trap handlers don't. */ + restore_interrupts(regs); + do_trap(3, SIGTRAP, "int3", 1, regs, error_code, NULL); +} +#endif + +/* + * Our handling of the processor debug registers is non-trivial. + * We do not clear them on entry and exit from the kernel. Therefore + * it is possible to get a watchpoint trap here from inside the kernel. + * However, the code in ./ptrace.c has ensured that the user can + * only set watchpoints on userspace addresses. Therefore the in-kernel + * watchpoint trap can only occur in code which is reading/writing + * from user space. Such code must not hold kernel locks (since it + * can equally take a page fault), therefore it is safe to call + * force_sig_info even though that claims and releases locks. + * + * Code in ./signal.c ensures that the debug control register + * is restored before we deliver any signal, and therefore that + * user code runs with the correct debug control register even though + * we clear it here. + * + * Being careful here means that we don't have to be as careful in a + * lot of more complicated places (task switching can be a bit lazy + * about restoring all the debug state, and ptrace doesn't have to + * find every occurrence of the TF bit that could be saved away even + * by user code) + */ +fastcall void do_debug(struct pt_regs * regs, long error_code) +{ + unsigned int condition; + struct task_struct *tsk = current; + + __asm__ __volatile__("movl %%db6,%0" : "=r" (condition)); + + if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code, + SIGTRAP) == NOTIFY_STOP) + return; + /* It's safe to allow irq's after DR6 has been saved */ + if (regs->eflags & X86_EFLAGS_IF) + local_irq_enable(); + + /* Mask out spurious debug traps due to lazy DR7 setting */ + if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) { + if (!tsk->thread.debugreg[7]) + goto clear_dr7; + } + + if (regs->eflags & VM_MASK) + goto debug_vm86; + + /* Save debug status register where ptrace can see it */ + tsk->thread.debugreg[6] = condition; + + /* + * Single-stepping through TF: make sure we ignore any events in + * kernel space (but re-enable TF when returning to user mode). + */ + if (condition & DR_STEP) { + /* + * We already checked v86 mode above, so we can + * check for kernel mode by just checking the CPL + * of CS. + */ + if ((regs->xcs & 3) == 0) + goto clear_TF_reenable; + } + + /* Ok, finally something we can handle */ + send_sigtrap(tsk, regs, error_code); + + /* Disable additional traps. They'll be re-enabled when + * the signal is delivered. + */ +clear_dr7: + __asm__("movl %0,%%db7" + : /* no output */ + : "r" (0)); + return; + +debug_vm86: + handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1); + return; + +clear_TF_reenable: + set_tsk_thread_flag(tsk, TIF_SINGLESTEP); + regs->eflags &= ~TF_MASK; + return; +} + +/* + * Note that we play around with the 'TS' bit in an attempt to get + * the correct behaviour even in the presence of the asynchronous + * IRQ13 behaviour + */ +void math_error(void __user *eip) +{ + struct task_struct * task; + siginfo_t info; + unsigned short cwd, swd; + + /* + * Save the info for the exception handler and clear the error. + */ + task = current; + save_init_fpu(task); + task->thread.trap_no = 16; + task->thread.error_code = 0; + info.si_signo = SIGFPE; + info.si_errno = 0; + info.si_code = __SI_FAULT; + info.si_addr = eip; + /* + * (~cwd & swd) will mask out exceptions that are not set to unmasked + * status. 0x3f is the exception bits in these regs, 0x200 is the + * C1 reg you need in case of a stack fault, 0x040 is the stack + * fault bit. We should only be taking one exception at a time, + * so if this combination doesn't produce any single exception, + * then we have a bad program that isn't syncronizing its FPU usage + * and it will suffer the consequences since we won't be able to + * fully reproduce the context of the exception + */ + cwd = get_fpu_cwd(task); + swd = get_fpu_swd(task); + switch (((~cwd) & swd & 0x3f) | (swd & 0x240)) { + case 0x000: + default: + break; + case 0x001: /* Invalid Op */ + case 0x041: /* Stack Fault */ + case 0x241: /* Stack Fault | Direction */ + info.si_code = FPE_FLTINV; + /* Should we clear the SF or let user space do it ???? */ + break; + case 0x002: /* Denormalize */ + case 0x010: /* Underflow */ + info.si_code = FPE_FLTUND; + break; + case 0x004: /* Zero Divide */ + info.si_code = FPE_FLTDIV; + break; + case 0x008: /* Overflow */ + info.si_code = FPE_FLTOVF; + break; + case 0x020: /* Precision */ + info.si_code = FPE_FLTRES; + break; + } + force_sig_info(SIGFPE, &info, task); +} + +fastcall void do_coprocessor_error(struct pt_regs * regs, long error_code) +{ + ignore_fpu_irq = 1; + math_error((void __user *)regs->eip); +} + +static void simd_math_error(void __user *eip) +{ + struct task_struct * task; + siginfo_t info; + unsigned short mxcsr; + + /* + * Save the info for the exception handler and clear the error. + */ + task = current; + save_init_fpu(task); + task->thread.trap_no = 19; + task->thread.error_code = 0; + info.si_signo = SIGFPE; + info.si_errno = 0; + info.si_code = __SI_FAULT; + info.si_addr = eip; + /* + * The SIMD FPU exceptions are handled a little differently, as there + * is only a single status/control register. Thus, to determine which + * unmasked exception was caught we must mask the exception mask bits + * at 0x1f80, and then use these to mask the exception bits at 0x3f. + */ + mxcsr = get_fpu_mxcsr(task); + switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) { + case 0x000: + default: + break; + case 0x001: /* Invalid Op */ + info.si_code = FPE_FLTINV; + break; + case 0x002: /* Denormalize */ + case 0x010: /* Underflow */ + info.si_code = FPE_FLTUND; + break; + case 0x004: /* Zero Divide */ + info.si_code = FPE_FLTDIV; + break; + case 0x008: /* Overflow */ + info.si_code = FPE_FLTOVF; + break; + case 0x020: /* Precision */ + info.si_code = FPE_FLTRES; + break; + } + force_sig_info(SIGFPE, &info, task); +} + +fastcall void do_simd_coprocessor_error(struct pt_regs * regs, + long error_code) +{ + if (cpu_has_xmm) { + /* Handle SIMD FPU exceptions on PIII+ processors. */ + ignore_fpu_irq = 1; + simd_math_error((void __user *)regs->eip); + } else { + /* + * Handle strange cache flush from user space exception + * in all other cases. This is undocumented behaviour. + */ + if (regs->eflags & VM_MASK) { + handle_vm86_fault((struct kernel_vm86_regs *)regs, + error_code); + return; + } + die_if_kernel("cache flush denied", regs, error_code); + current->thread.trap_no = 19; + current->thread.error_code = error_code; + force_sig(SIGSEGV, current); + } +} + +fastcall void do_spurious_interrupt_bug(struct pt_regs * regs, + long error_code) +{ +#if 0 + /* No need to warn about this any longer. */ + printk("Ignoring P6 Local APIC Spurious Interrupt Bug...\n"); +#endif +} + +fastcall void setup_x86_bogus_stack(unsigned char * stk) +{ + unsigned long *switch16_ptr, *switch32_ptr; + struct pt_regs *regs; + unsigned long stack_top, stack_bot; + unsigned short iret_frame16_off; + int cpu = smp_processor_id(); + /* reserve the space on 32bit stack for the magic switch16 pointer */ + memmove(stk, stk + 8, sizeof(struct pt_regs)); + switch16_ptr = (unsigned long *)(stk + sizeof(struct pt_regs)); + regs = (struct pt_regs *)stk; + /* now the switch32 on 16bit stack */ + stack_bot = (unsigned long)&per_cpu(cpu_16bit_stack, cpu); + stack_top = stack_bot + CPU_16BIT_STACK_SIZE; + switch32_ptr = (unsigned long *)(stack_top - 8); + iret_frame16_off = CPU_16BIT_STACK_SIZE - 8 - 20; + /* copy iret frame on 16bit stack */ + memcpy((void *)(stack_bot + iret_frame16_off), &regs->eip, 20); + /* fill in the switch pointers */ + switch16_ptr[0] = (regs->esp & 0xffff0000) | iret_frame16_off; + switch16_ptr[1] = __ESPFIX_SS; + switch32_ptr[0] = (unsigned long)stk + sizeof(struct pt_regs) + + 8 - CPU_16BIT_STACK_SIZE; + switch32_ptr[1] = __KERNEL_DS; +} + +fastcall unsigned char * fixup_x86_bogus_stack(unsigned short sp) +{ + unsigned long *switch32_ptr; + unsigned char *stack16, *stack32; + unsigned long stack_top, stack_bot; + int len; + int cpu = smp_processor_id(); + stack_bot = (unsigned long)&per_cpu(cpu_16bit_stack, cpu); + stack_top = stack_bot + CPU_16BIT_STACK_SIZE; + switch32_ptr = (unsigned long *)(stack_top - 8); + /* copy the data from 16bit stack to 32bit stack */ + len = CPU_16BIT_STACK_SIZE - 8 - sp; + stack16 = (unsigned char *)(stack_bot + sp); + stack32 = (unsigned char *) + (switch32_ptr[0] + CPU_16BIT_STACK_SIZE - 8 - len); + memcpy(stack32, stack16, len); + return stack32; +} + +/* + * 'math_state_restore()' saves the current math information in the + * old math state array, and gets the new ones from the current task + * + * Careful.. There are problems with IBM-designed IRQ13 behaviour. + * Don't touch unless you *really* know how it works. + * + * Must be called with kernel preemption disabled (in this case, + * local interrupts are disabled at the call-site in entry.S). + */ +asmlinkage void math_state_restore(struct pt_regs regs) +{ + struct thread_info *thread = current_thread_info(); + struct task_struct *tsk = thread->task; + + clts(); /* Allow maths ops (or we recurse) */ + if (!tsk_used_math(tsk)) + init_fpu(tsk); + restore_fpu(tsk); + thread->status |= TS_USEDFPU; /* So we fnsave on switch_to() */ +} + +#ifndef CONFIG_MATH_EMULATION + +asmlinkage void math_emulate(long arg) +{ + printk("math-emulation not enabled and no coprocessor found.\n"); + printk("killing %s.\n",current->comm); + force_sig(SIGFPE,current); + schedule(); +} + +#endif /* CONFIG_MATH_EMULATION */ + +#ifdef CONFIG_X86_F00F_BUG +void __init trap_init_f00f_bug(void) +{ + __set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO); + + /* + * Update the IDT descriptor and reload the IDT so that + * it uses the read-only mapped virtual address. + */ + idt_descr.address = fix_to_virt(FIX_F00F_IDT); + __asm__ __volatile__("lidt %0" : : "m" (idt_descr)); +} +#endif + +#define _set_gate(gate_addr,type,dpl,addr,seg) \ +do { \ + int __d0, __d1; \ + __asm__ __volatile__ ("movw %%dx,%%ax\n\t" \ + "movw %4,%%dx\n\t" \ + "movl %%eax,%0\n\t" \ + "movl %%edx,%1" \ + :"=m" (*((long *) (gate_addr))), \ + "=m" (*(1+(long *) (gate_addr))), "=&a" (__d0), "=&d" (__d1) \ + :"i" ((short) (0x8000+(dpl<<13)+(type<<8))), \ + "3" ((char *) (addr)),"2" ((seg) << 16)); \ +} while (0) + + +/* + * This needs to use 'idt_table' rather than 'idt', and + * thus use the _nonmapped_ version of the IDT, as the + * Pentium F0 0F bugfix can have resulted in the mapped + * IDT being write-protected. + */ +void set_intr_gate(unsigned int n, void *addr) +{ + _set_gate(idt_table+n,14,0,addr,__KERNEL_CS); +} + +/* + * This routine sets up an interrupt gate at directory privilege level 3. + */ +static inline void set_system_intr_gate(unsigned int n, void *addr) +{ + _set_gate(idt_table+n, 14, 3, addr, __KERNEL_CS); +} + +static void __init set_trap_gate(unsigned int n, void *addr) +{ + _set_gate(idt_table+n,15,0,addr,__KERNEL_CS); +} + +static void __init set_system_gate(unsigned int n, void *addr) +{ + _set_gate(idt_table+n,15,3,addr,__KERNEL_CS); +} + +static void __init set_task_gate(unsigned int n, unsigned int gdt_entry) +{ + _set_gate(idt_table+n,5,0,0,(gdt_entry<<3)); +} + + +void __init trap_init(void) +{ +#ifdef CONFIG_EISA + void __iomem *p = ioremap(0x0FFFD9, 4); + if (readl(p) == 'E'+('I'<<8)+('S'<<16)+('A'<<24)) { + EISA_bus = 1; + } + iounmap(p); +#endif + +#ifdef CONFIG_X86_LOCAL_APIC + init_apic_mappings(); +#endif + + set_trap_gate(0,&divide_error); + set_intr_gate(1,&debug); + set_intr_gate(2,&nmi); + set_system_intr_gate(3, &int3); /* int3-5 can be called from all */ + set_system_gate(4,&overflow); + set_system_gate(5,&bounds); + set_trap_gate(6,&invalid_op); + set_trap_gate(7,&device_not_available); + set_task_gate(8,GDT_ENTRY_DOUBLEFAULT_TSS); + set_trap_gate(9,&coprocessor_segment_overrun); + set_trap_gate(10,&invalid_TSS); + set_trap_gate(11,&segment_not_present); + set_trap_gate(12,&stack_segment); + set_trap_gate(13,&general_protection); + set_intr_gate(14,&page_fault); + set_trap_gate(15,&spurious_interrupt_bug); + set_trap_gate(16,&coprocessor_error); + set_trap_gate(17,&alignment_check); +#ifdef CONFIG_X86_MCE + set_trap_gate(18,&machine_check); +#endif + set_trap_gate(19,&simd_coprocessor_error); + + set_system_gate(SYSCALL_VECTOR,&system_call); + + /* + * Should be a barrier for any external CPU state. + */ + cpu_init(); + + trap_init_hook(); +} + +static int __init kstack_setup(char *s) +{ + kstack_depth_to_print = simple_strtoul(s, NULL, 0); + return 0; +} +__setup("kstack=", kstack_setup); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/vmlinux.lds.S --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/vmlinux.lds.S Mon Jan 30 17:18:27 2006 @@ -0,0 +1,141 @@ +/* ld script to make i386 Linux kernel + * Written by Martin Mares <mj@xxxxxxxxxxxxxxxxxxxxxxxx>; + */ + +#include <asm-generic/vmlinux.lds.h> +#include <asm/thread_info.h> +#include <asm/page.h> + +OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386") +OUTPUT_ARCH(i386) +ENTRY(startup_32) +jiffies = jiffies_64; +SECTIONS +{ + . = __PAGE_OFFSET + 0x100000; + /* read-only */ + _text = .; /* Text and read-only data */ + .text : { + *(.text) + SCHED_TEXT + LOCK_TEXT + *(.fixup) + *(.gnu.warning) + } = 0x9090 + + _etext = .; /* End of text section */ + + . = ALIGN(16); /* Exception table */ + __start___ex_table = .; + __ex_table : { *(__ex_table) } + __stop___ex_table = .; + + . = ALIGN(16); + __start_smp_alternatives_table = .; + __smp_alternatives : { *(__smp_alternatives) } + __stop_smp_alternatives_table = .; + + __smp_replacements : { *(__smp_replacements) } + + RODATA + + /* writeable */ + .data : { /* Data */ + *(.data) + CONSTRUCTORS + } + + . = ALIGN(4096); + __nosave_begin = .; + .data_nosave : { *(.data.nosave) } + . = ALIGN(4096); + __nosave_end = .; + + . = ALIGN(4096); + .data.page_aligned : { *(.data.idt) } + + . = ALIGN(32); + .data.cacheline_aligned : { *(.data.cacheline_aligned) } + + _edata = .; /* End of data section */ + + . = ALIGN(THREAD_SIZE); /* init_task */ + .data.init_task : { *(.data.init_task) } + + /* will be freed after init */ + . = ALIGN(4096); /* Init code and data */ + __init_begin = .; + .init.text : { + _sinittext = .; + *(.init.text) + _einittext = .; + } + .init.data : { *(.init.data) } + . = ALIGN(16); + __setup_start = .; + .init.setup : { *(.init.setup) } + __setup_end = .; + __initcall_start = .; + .initcall.init : { + *(.initcall1.init) + *(.initcall2.init) + *(.initcall3.init) + *(.initcall4.init) + *(.initcall5.init) + *(.initcall6.init) + *(.initcall7.init) + } + __initcall_end = .; + __con_initcall_start = .; + .con_initcall.init : { *(.con_initcall.init) } + __con_initcall_end = .; + SECURITY_INIT + . = ALIGN(4); + __alt_instructions = .; + .altinstructions : { *(.altinstructions) } + __alt_instructions_end = .; + .altinstr_replacement : { *(.altinstr_replacement) } + /* .exit.text is discard at runtime, not link time, to deal with references + from .altinstructions and .eh_frame */ + .exit.text : { *(.exit.text) } + .exit.data : { *(.exit.data) } + . = ALIGN(4096); + __initramfs_start = .; + .init.ramfs : { *(.init.ramfs) } + __initramfs_end = .; + . = ALIGN(32); + __per_cpu_start = .; + .data.percpu : { *(.data.percpu) } + __per_cpu_end = .; + . = ALIGN(4096); + __init_end = .; + /* freed after init ends here */ + + __bss_start = .; /* BSS */ + .bss : { + *(.bss.page_aligned) + *(.bss) + } + . = ALIGN(4); + __bss_stop = .; + + _end = . ; + + /* This is where the kernel creates the early boot page tables */ + . = ALIGN(4096); + pg0 = .; + + /* Sections to be discarded */ + /DISCARD/ : { + *(.exitcall.exit) + } + + /* Stabs debugging sections. */ + .stab 0 : { *(.stab) } + .stabstr 0 : { *(.stabstr) } + .stab.excl 0 : { *(.stab.excl) } + .stab.exclstr 0 : { *(.stab.exclstr) } + .stab.index 0 : { *(.stab.index) } + .stab.indexstr 0 : { *(.stab.indexstr) } + .comment 0 : { *(.comment) } +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/kernel/vsyscall-note-xen.S --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/kernel/vsyscall-note-xen.S Mon Jan 30 17:18:27 2006 @@ -0,0 +1,32 @@ +/* + * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. + * Here we can supply some information useful to userland. + * First we get the vanilla i386 note that supplies the kernel version info. + */ + +#include "vsyscall-note.S" + +/* + * Now we add a special note telling glibc's dynamic linker a fake hardware + * flavor that it will use to choose the search path for libraries in the + * same way it uses real hardware capabilities like "mmx". + * We supply "nosegneg" as the fake capability, to indicate that we + * do not like negative offsets in instructions using segment overrides, + * since we implement those inefficiently. This makes it possible to + * install libraries optimized to avoid those access patterns in someplace + * like /lib/i686/tls/nosegneg. Note that an /etc/ld.so.conf.d/file + * corresponding to the bits here is needed to make ldconfig work right. + * It should contain: + * hwcap 0 nosegneg + * to match the mapping of bit to name that we give here. + */ +#define NOTE_KERNELCAP_BEGIN(ncaps, mask) \ + ASM_ELF_NOTE_BEGIN(".note.kernelcap", "a", "GNU", 2) \ + .long ncaps, mask +#define NOTE_KERNELCAP(bit, name) \ + .byte bit; .asciz name +#define NOTE_KERNELCAP_END ASM_ELF_NOTE_END + +NOTE_KERNELCAP_BEGIN(1, 1) +NOTE_KERNELCAP(1, "nosegneg") /* Change 1 back to 0 when glibc is fixed! */ +NOTE_KERNELCAP_END diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/mach-xen/Makefile --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/mach-xen/Makefile Mon Jan 30 17:18:27 2006 @@ -0,0 +1,7 @@ +# +# Makefile for the linux kernel. +# + +obj-y := topology.o + +topology-y := ../mach-default/topology.o diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/mach-xen/topology.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/mach-xen/topology.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,97 @@ +/* + * arch/i386/mach-generic/topology.c - Populate driverfs with topology information + * + * Written by: Matthew Dobson, IBM Corporation + * Original Code: Paul Dorwin, IBM Corporation, Patrick Mochel, OSDL + * + * Copyright (C) 2002, IBM Corp. + * + * All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for more + * details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * + * Send feedback to <colpatch@xxxxxxxxxx> + */ +#include <linux/init.h> +#include <linux/smp.h> +#include <linux/nodemask.h> +#include <asm/cpu.h> + +static struct i386_cpu cpu_devices[NR_CPUS]; + +int arch_register_cpu(int num){ + struct node *parent = NULL; + +#ifdef CONFIG_NUMA + int node = cpu_to_node(num); + if (node_online(node)) + parent = &node_devices[node].node; +#endif /* CONFIG_NUMA */ + + return register_cpu(&cpu_devices[num].cpu, num, parent); +} + +#ifdef CONFIG_HOTPLUG_CPU + +void arch_unregister_cpu(int num) { + struct node *parent = NULL; + +#ifdef CONFIG_NUMA + int node = cpu_to_node(num); + if (node_online(node)) + parent = &node_devices[node].node; +#endif /* CONFIG_NUMA */ + + return unregister_cpu(&cpu_devices[num].cpu, parent); +} +EXPORT_SYMBOL(arch_register_cpu); +EXPORT_SYMBOL(arch_unregister_cpu); +#endif /*CONFIG_HOTPLUG_CPU*/ + + + +#ifdef CONFIG_NUMA +#include <linux/mmzone.h> +#include <asm/node.h> + +struct i386_node node_devices[MAX_NUMNODES]; + +static int __init topology_init(void) +{ + int i; + + for_each_online_node(i) + arch_register_node(i); + + for_each_present_cpu(i) + arch_register_cpu(i); + return 0; +} + +#else /* !CONFIG_NUMA */ + +static int __init topology_init(void) +{ + int i; + + for_each_present_cpu(i) + arch_register_cpu(i); + return 0; +} + +#endif /* CONFIG_NUMA */ + +subsys_initcall(topology_init); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/mm/Makefile --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/mm/Makefile Mon Jan 30 17:18:27 2006 @@ -0,0 +1,18 @@ +# +# Makefile for the linux i386-specific parts of the memory manager. +# + +obj-y := init.o pgtable.o fault.o ioremap.o extable.o pageattr.o mmap.o + +obj-$(CONFIG_DISCONTIGMEM) += discontig.o +obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o +obj-$(CONFIG_HIGHMEM) += highmem.o +obj-$(CONFIG_BOOT_IOREMAP) += boot_ioremap.o + +ifdef CONFIG_XEN +include $(srctree)/scripts/Makefile.xen + +obj-y += hypervisor.o + +obj-y := $(call cherrypickxen, $(obj-y)) +endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/mm/fault-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/mm/fault-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,620 @@ +/* + * linux/arch/i386/mm/fault.c + * + * Copyright (C) 1995 Linus Torvalds + */ + +#include <linux/signal.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/ptrace.h> +#include <linux/mman.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/tty.h> +#include <linux/vt_kern.h> /* For unblank_screen() */ +#include <linux/highmem.h> +#include <linux/module.h> +#include <linux/percpu.h> + +#include <asm/system.h> +#include <asm/uaccess.h> +#include <asm/desc.h> +#include <asm/kdebug.h> + +extern void die(const char *,struct pt_regs *,long); + +DEFINE_PER_CPU(pgd_t *, cur_pgd); + +/* + * Unlock any spinlocks which will prevent us from getting the + * message out + */ +void bust_spinlocks(int yes) +{ + int loglevel_save = console_loglevel; + + if (yes) { + oops_in_progress = 1; + return; + } +#ifdef CONFIG_VT + unblank_screen(); +#endif + oops_in_progress = 0; + /* + * OK, the message is on the console. Now we call printk() + * without oops_in_progress set so that printk will give klogd + * a poke. Hold onto your hats... + */ + console_loglevel = 15; /* NMI oopser may have shut the console up */ + printk(" "); + console_loglevel = loglevel_save; +} + +/* + * Return EIP plus the CS segment base. The segment limit is also + * adjusted, clamped to the kernel/user address space (whichever is + * appropriate), and returned in *eip_limit. + * + * The segment is checked, because it might have been changed by another + * task between the original faulting instruction and here. + * + * If CS is no longer a valid code segment, or if EIP is beyond the + * limit, or if it is a kernel address when CS is not a kernel segment, + * then the returned value will be greater than *eip_limit. + * + * This is slow, but is very rarely executed. + */ +static inline unsigned long get_segment_eip(struct pt_regs *regs, + unsigned long *eip_limit) +{ + unsigned long eip = regs->eip; + unsigned seg = regs->xcs & 0xffff; + u32 seg_ar, seg_limit, base, *desc; + + /* The standard kernel/user address space limit. */ + *eip_limit = (seg & 2) ? USER_DS.seg : KERNEL_DS.seg; + + /* Unlikely, but must come before segment checks. */ + if (unlikely((regs->eflags & VM_MASK) != 0)) + return eip + (seg << 4); + + /* By far the most common cases. */ + if (likely(seg == __USER_CS || seg == __KERNEL_CS)) + return eip; + + /* Check the segment exists, is within the current LDT/GDT size, + that kernel/user (ring 0..3) has the appropriate privilege, + that it's a code segment, and get the limit. */ + __asm__ ("larl %3,%0; lsll %3,%1" + : "=&r" (seg_ar), "=r" (seg_limit) : "0" (0), "rm" (seg)); + if ((~seg_ar & 0x9800) || eip > seg_limit) { + *eip_limit = 0; + return 1; /* So that returned eip > *eip_limit. */ + } + + /* Get the GDT/LDT descriptor base. + When you look for races in this code remember that + LDT and other horrors are only used in user space. */ + if (seg & (1<<2)) { + /* Must lock the LDT while reading it. */ + down(&current->mm->context.sem); + desc = current->mm->context.ldt; + desc = (void *)desc + (seg & ~7); + } else { + /* Must disable preemption while reading the GDT. */ + desc = (u32 *)get_cpu_gdt_table(get_cpu()); + desc = (void *)desc + (seg & ~7); + } + + /* Decode the code segment base from the descriptor */ + base = get_desc_base((unsigned long *)desc); + + if (seg & (1<<2)) { + up(&current->mm->context.sem); + } else + put_cpu(); + + /* Adjust EIP and segment limit, and clamp at the kernel limit. + It's legitimate for segments to wrap at 0xffffffff. */ + seg_limit += base; + if (seg_limit < *eip_limit && seg_limit >= base) + *eip_limit = seg_limit; + return eip + base; +} + +/* + * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch. + * Check that here and ignore it. + */ +static int __is_prefetch(struct pt_regs *regs, unsigned long addr) +{ + unsigned long limit; + unsigned long instr = get_segment_eip (regs, &limit); + int scan_more = 1; + int prefetch = 0; + int i; + + for (i = 0; scan_more && i < 15; i++) { + unsigned char opcode; + unsigned char instr_hi; + unsigned char instr_lo; + + if (instr > limit) + break; + if (__get_user(opcode, (unsigned char *) instr)) + break; + + instr_hi = opcode & 0xf0; + instr_lo = opcode & 0x0f; + instr++; + + switch (instr_hi) { + case 0x20: + case 0x30: + /* Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes. */ + scan_more = ((instr_lo & 7) == 0x6); + break; + + case 0x60: + /* 0x64 thru 0x67 are valid prefixes in all modes. */ + scan_more = (instr_lo & 0xC) == 0x4; + break; + case 0xF0: + /* 0xF0, 0xF2, and 0xF3 are valid prefixes */ + scan_more = !instr_lo || (instr_lo>>1) == 1; + break; + case 0x00: + /* Prefetch instruction is 0x0F0D or 0x0F18 */ + scan_more = 0; + if (instr > limit) + break; + if (__get_user(opcode, (unsigned char *) instr)) + break; + prefetch = (instr_lo == 0xF) && + (opcode == 0x0D || opcode == 0x18); + break; + default: + scan_more = 0; + break; + } + } + return prefetch; +} + +static inline int is_prefetch(struct pt_regs *regs, unsigned long addr, + unsigned long error_code) +{ + if (unlikely(boot_cpu_data.x86_vendor == X86_VENDOR_AMD && + boot_cpu_data.x86 >= 6)) { + /* Catch an obscure case of prefetch inside an NX page. */ + if (nx_enabled && (error_code & 16)) + return 0; + return __is_prefetch(regs, addr); + } + return 0; +} + +fastcall void do_invalid_op(struct pt_regs *, unsigned long); + +#ifdef CONFIG_X86_PAE +static void dump_fault_path(unsigned long address) +{ + unsigned long *p, page; + unsigned long mfn; + + preempt_disable(); + page = __pa(per_cpu(cur_pgd, smp_processor_id())); + preempt_enable(); + + p = (unsigned long *)__va(page); + p += (address >> 30) * 2; + printk(KERN_ALERT "%08lx -> *pde = %08lx:%08lx\n", page, p[1], p[0]); + if (p[0] & 1) { + mfn = (p[0] >> PAGE_SHIFT) | ((p[1] & 0x7) << 20); + page = mfn_to_pfn(mfn) << PAGE_SHIFT; + p = (unsigned long *)__va(page); + address &= 0x3fffffff; + p += (address >> 21) * 2; + printk(KERN_ALERT "%08lx -> *pme = %08lx:%08lx\n", + page, p[1], p[0]); +#ifndef CONFIG_HIGHPTE + if (p[0] & 1) { + mfn = (p[0] >> PAGE_SHIFT) | ((p[1] & 0x7) << 20); + page = mfn_to_pfn(mfn) << PAGE_SHIFT; + p = (unsigned long *) __va(page); + address &= 0x001fffff; + p += (address >> 12) * 2; + printk(KERN_ALERT "%08lx -> *pte = %08lx:%08lx\n", + page, p[1], p[0]); + } +#endif + } +} +#else +static void dump_fault_path(unsigned long address) +{ + unsigned long page; + + preempt_disable(); + page = ((unsigned long *) per_cpu(cur_pgd, smp_processor_id())) + [address >> 22]; + preempt_enable(); + + page = ((unsigned long *) per_cpu(cur_pgd, get_cpu())) + [address >> 22]; + printk(KERN_ALERT "*pde = ma %08lx pa %08lx\n", page, + machine_to_phys(page)); + /* + * We must not directly access the pte in the highpte + * case, the page table might be allocated in highmem. + * And lets rather not kmap-atomic the pte, just in case + * it's allocated already. + */ +#ifndef CONFIG_HIGHPTE + if (page & 1) { + page &= PAGE_MASK; + address &= 0x003ff000; + page = machine_to_phys(page); + page = ((unsigned long *) __va(page))[address >> PAGE_SHIFT]; + printk(KERN_ALERT "*pte = ma %08lx pa %08lx\n", page, + machine_to_phys(page)); + } +#endif +} +#endif + + +/* + * This routine handles page faults. It determines the address, + * and the problem, and then passes it off to one of the appropriate + * routines. + * + * error_code: + * bit 0 == 0 means no page found, 1 means protection fault + * bit 1 == 0 means read, 1 means write + * bit 2 == 0 means kernel, 1 means user-mode + */ +fastcall void do_page_fault(struct pt_regs *regs, unsigned long error_code) +{ + struct task_struct *tsk; + struct mm_struct *mm; + struct vm_area_struct * vma; + unsigned long address; + int write; + siginfo_t info; + + address = HYPERVISOR_shared_info->vcpu_info[ + smp_processor_id()].arch.cr2; + + /* Set the "privileged fault" bit to something sane. */ + error_code &= ~4; + error_code |= (regs->xcs & 2) << 1; + if (regs->eflags & X86_EFLAGS_VM) + error_code |= 4; + + if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14, + SIGSEGV) == NOTIFY_STOP) + return; + /* It's safe to allow irq's after cr2 has been saved */ + if (regs->eflags & (X86_EFLAGS_IF|VM_MASK)) + local_irq_enable(); + + tsk = current; + + info.si_code = SEGV_MAPERR; + + /* + * We fault-in kernel-space virtual memory on-demand. The + * 'reference' page table is init_mm.pgd. + * + * NOTE! We MUST NOT take any locks for this case. We may + * be in an interrupt or a critical region, and should + * only copy the information from the master page table, + * nothing more. + * + * This verifies that the fault happens in kernel space + * (error_code & 4) == 0, and that the fault was not a + * protection error (error_code & 1) == 0. + */ + if (unlikely(address >= TASK_SIZE)) { + if (!(error_code & 5)) + goto vmalloc_fault; + /* + * Don't take the mm semaphore here. If we fixup a prefetch + * fault we could otherwise deadlock. + */ + goto bad_area_nosemaphore; + } + + mm = tsk->mm; + + /* + * If we're in an interrupt, have no user context or are running in an + * atomic region then we must not take the fault.. + */ + if (in_atomic() || !mm) + goto bad_area_nosemaphore; + + /* When running in the kernel we expect faults to occur only to + * addresses in user space. All other faults represent errors in the + * kernel and should generate an OOPS. Unfortunatly, in the case of an + * erroneous fault occuring in a code path which already holds mmap_sem + * we will deadlock attempting to validate the fault against the + * address space. Luckily the kernel only validly references user + * space from well defined areas of code, which are listed in the + * exceptions table. + * + * As the vast majority of faults will be valid we will only perform + * the source reference check when there is a possibilty of a deadlock. + * Attempt to lock the address space, if we cannot we then validate the + * source. If this is invalid we can skip the address space check, + * thus avoiding the deadlock. + */ + if (!down_read_trylock(&mm->mmap_sem)) { + if ((error_code & 4) == 0 && + !search_exception_tables(regs->eip)) + goto bad_area_nosemaphore; + down_read(&mm->mmap_sem); + } + + vma = find_vma(mm, address); + if (!vma) + goto bad_area; + if (vma->vm_start <= address) + goto good_area; + if (!(vma->vm_flags & VM_GROWSDOWN)) + goto bad_area; + if (error_code & 4) { + /* + * accessing the stack below %esp is always a bug. + * The "+ 32" is there due to some instructions (like + * pusha) doing post-decrement on the stack and that + * doesn't show up until later.. + */ + if (address + 32 < regs->esp) + goto bad_area; + } + if (expand_stack(vma, address)) + goto bad_area; +/* + * Ok, we have a good vm_area for this memory access, so + * we can handle it.. + */ +good_area: + info.si_code = SEGV_ACCERR; + write = 0; + switch (error_code & 3) { + default: /* 3: write, present */ +#ifdef TEST_VERIFY_AREA + if (regs->cs == KERNEL_CS) + printk("WP fault at %08lx\n", regs->eip); +#endif + /* fall through */ + case 2: /* write, not present */ + if (!(vma->vm_flags & VM_WRITE)) + goto bad_area; + write++; + break; + case 1: /* read, present */ + goto bad_area; + case 0: /* read, not present */ + if (!(vma->vm_flags & (VM_READ | VM_EXEC))) + goto bad_area; + } + + survive: + /* + * If for any reason at all we couldn't handle the fault, + * make sure we exit gracefully rather than endlessly redo + * the fault. + */ + switch (handle_mm_fault(mm, vma, address, write)) { + case VM_FAULT_MINOR: + tsk->min_flt++; + break; + case VM_FAULT_MAJOR: + tsk->maj_flt++; + break; + case VM_FAULT_SIGBUS: + goto do_sigbus; + case VM_FAULT_OOM: + goto out_of_memory; + default: + BUG(); + } + + /* + * Did it hit the DOS screen memory VA from vm86 mode? + */ + if (regs->eflags & VM_MASK) { + unsigned long bit = (address - 0xA0000) >> PAGE_SHIFT; + if (bit < 32) + tsk->thread.screen_bitmap |= 1 << bit; + } + up_read(&mm->mmap_sem); + return; + +/* + * Something tried to access memory that isn't in our memory map.. + * Fix it, but check if it's kernel or user first.. + */ +bad_area: + up_read(&mm->mmap_sem); + +bad_area_nosemaphore: + /* User mode accesses just cause a SIGSEGV */ + if (error_code & 4) { + /* + * Valid to do another page fault here because this one came + * from user space. + */ + if (is_prefetch(regs, address, error_code)) + return; + + tsk->thread.cr2 = address; + /* Kernel addresses are always protection faults */ + tsk->thread.error_code = error_code | (address >= TASK_SIZE); + tsk->thread.trap_no = 14; + info.si_signo = SIGSEGV; + info.si_errno = 0; + /* info.si_code has been set above */ + info.si_addr = (void __user *)address; + force_sig_info(SIGSEGV, &info, tsk); + return; + } + +#ifdef CONFIG_X86_F00F_BUG + /* + * Pentium F0 0F C7 C8 bug workaround. + */ + if (boot_cpu_data.f00f_bug) { + unsigned long nr; + + nr = (address - idt_descr.address) >> 3; + + if (nr == 6) { + do_invalid_op(regs, 0); + return; + } + } +#endif + +no_context: + /* Are we prepared to handle this kernel fault? */ + if (fixup_exception(regs)) + return; + + /* + * Valid to do another page fault here, because if this fault + * had been triggered by is_prefetch fixup_exception would have + * handled it. + */ + if (is_prefetch(regs, address, error_code)) + return; + +/* + * Oops. The kernel tried to access some bad page. We'll have to + * terminate things with extreme prejudice. + */ + + bust_spinlocks(1); + +#ifdef CONFIG_X86_PAE + if (error_code & 16) { + pte_t *pte = lookup_address(address); + + if (pte && pte_present(*pte) && !pte_exec_kernel(*pte)) + printk(KERN_CRIT "kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n", current->uid); + } +#endif + if (address < PAGE_SIZE) + printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference"); + else + printk(KERN_ALERT "Unable to handle kernel paging request"); + printk(" at virtual address %08lx\n",address); + printk(KERN_ALERT " printing eip:\n"); + printk("%08lx\n", regs->eip); + dump_fault_path(address); + die("Oops", regs, error_code); + bust_spinlocks(0); + do_exit(SIGKILL); + +/* + * We ran out of memory, or some other thing happened to us that made + * us unable to handle the page fault gracefully. + */ +out_of_memory: + up_read(&mm->mmap_sem); + if (tsk->pid == 1) { + yield(); + down_read(&mm->mmap_sem); + goto survive; + } + printk("VM: killing process %s\n", tsk->comm); + if (error_code & 4) + do_exit(SIGKILL); + goto no_context; + +do_sigbus: + up_read(&mm->mmap_sem); + + /* Kernel mode? Handle exceptions or die */ + if (!(error_code & 4)) + goto no_context; + + /* User space => ok to do another page fault */ + if (is_prefetch(regs, address, error_code)) + return; + + tsk->thread.cr2 = address; + tsk->thread.error_code = error_code; + tsk->thread.trap_no = 14; + info.si_signo = SIGBUS; + info.si_errno = 0; + info.si_code = BUS_ADRERR; + info.si_addr = (void __user *)address; + force_sig_info(SIGBUS, &info, tsk); + return; + +vmalloc_fault: + { + /* + * Synchronize this task's top level page-table + * with the 'reference' page table. + * + * Do _not_ use "tsk" here. We might be inside + * an interrupt in the middle of a task switch.. + */ + int index = pgd_index(address); + pgd_t *pgd, *pgd_k; + pud_t *pud, *pud_k; + pmd_t *pmd, *pmd_k; + pte_t *pte_k; + + preempt_disable(); + pgd = index + per_cpu(cur_pgd, smp_processor_id()); + preempt_enable(); + pgd_k = init_mm.pgd + index; + + if (!pgd_present(*pgd_k)) + goto no_context; + + /* + * set_pgd(pgd, *pgd_k); here would be useless on PAE + * and redundant with the set_pmd() on non-PAE. As would + * set_pud. + */ + + pud = pud_offset(pgd, address); + pud_k = pud_offset(pgd_k, address); + if (!pud_present(*pud_k)) + goto no_context; + + pmd = pmd_offset(pud, address); + pmd_k = pmd_offset(pud_k, address); + if (!pmd_present(*pmd_k)) + goto no_context; +#ifndef CONFIG_XEN + set_pmd(pmd, *pmd_k); +#else + /* + * When running on Xen we must launder *pmd_k through + * pmd_val() to ensure that _PAGE_PRESENT is correctly set. + */ + set_pmd(pmd, __pmd(pmd_val(*pmd_k))); +#endif + + pte_k = pte_offset_kernel(pmd_k, address); + if (!pte_present(*pte_k)) + goto no_context; + return; + } +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/mm/highmem-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/mm/highmem-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,99 @@ +#include <linux/highmem.h> + +void *kmap(struct page *page) +{ + might_sleep(); + if (!PageHighMem(page)) + return page_address(page); + return kmap_high(page); +} + +void kunmap(struct page *page) +{ + if (in_interrupt()) + BUG(); + if (!PageHighMem(page)) + return; + kunmap_high(page); +} + +/* + * kmap_atomic/kunmap_atomic is significantly faster than kmap/kunmap because + * no global lock is needed and because the kmap code must perform a global TLB + * invalidation when the kmap pool wraps. + * + * However when holding an atomic kmap is is not legal to sleep, so atomic + * kmaps are appropriate for short, tight code paths only. + */ +static void *__kmap_atomic(struct page *page, enum km_type type, pgprot_t prot) +{ + enum fixed_addresses idx; + unsigned long vaddr; + + /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ + inc_preempt_count(); + if (!PageHighMem(page)) + return page_address(page); + + idx = type + KM_TYPE_NR*smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); +#ifdef CONFIG_DEBUG_HIGHMEM + if (!pte_none(*(kmap_pte-idx))) + BUG(); +#endif + set_pte_at_sync(&init_mm, vaddr, kmap_pte-idx, mk_pte(page, prot)); + + return (void*) vaddr; +} + +void *kmap_atomic(struct page *page, enum km_type type) +{ + return __kmap_atomic(page, type, kmap_prot); +} + +/* Same as kmap_atomic but with PAGE_KERNEL_RO page protection. */ +void *kmap_atomic_pte(struct page *page, enum km_type type) +{ + return __kmap_atomic(page, type, PAGE_KERNEL_RO); +} + +void kunmap_atomic(void *kvaddr, enum km_type type) +{ +#ifdef CONFIG_DEBUG_HIGHMEM + unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; + enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id(); + + if (vaddr < FIXADDR_START) { // FIXME + dec_preempt_count(); + preempt_check_resched(); + return; + } + + if (vaddr != __fix_to_virt(FIX_KMAP_BEGIN+idx)) + BUG(); + + /* + * force other mappings to Oops if they'll try to access + * this pte without first remap it + */ + pte_clear(&init_mm, vaddr, kmap_pte-idx); + __flush_tlb_one(vaddr); +#endif + + dec_preempt_count(); + preempt_check_resched(); +} + +struct page *kmap_atomic_to_page(void *ptr) +{ + unsigned long idx, vaddr = (unsigned long)ptr; + pte_t *pte; + + if (vaddr < FIXADDR_START) + return virt_to_page(ptr); + + idx = virt_to_fix(vaddr); + pte = kmap_pte - (idx - FIX_KMAP_BEGIN); + return pte_page(*pte); +} + diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/mm/hypervisor.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/mm/hypervisor.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,459 @@ +/****************************************************************************** + * mm/hypervisor.c + * + * Update page tables via the hypervisor. + * + * Copyright (c) 2002-2004, K A Fraser + * + * This file may be distributed separately from the Linux kernel, or + * incorporated into other software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#include <linux/config.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/vmalloc.h> +#include <asm/page.h> +#include <asm/pgtable.h> +#include <asm/hypervisor.h> +#include <xen/balloon.h> +#include <xen/interface/memory.h> +#include <linux/module.h> +#include <linux/percpu.h> +#include <asm/tlbflush.h> + +#ifdef CONFIG_X86_64 +#define pmd_val_ma(v) (v).pmd +#else +#ifdef CONFIG_X86_PAE +# define pmd_val_ma(v) ((v).pmd) +# define pud_val_ma(v) ((v).pgd.pgd) +#else +# define pmd_val_ma(v) ((v).pud.pgd.pgd) +#endif +#endif + +#ifndef CONFIG_XEN_SHADOW_MODE +void xen_l1_entry_update(pte_t *ptr, pte_t val) +{ + mmu_update_t u; + u.ptr = virt_to_machine(ptr); + u.val = pte_val_ma(val); + BUG_ON(HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF) < 0); +} + +void xen_l2_entry_update(pmd_t *ptr, pmd_t val) +{ + mmu_update_t u; + u.ptr = virt_to_machine(ptr); + u.val = pmd_val_ma(val); + BUG_ON(HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF) < 0); +} + +#ifdef CONFIG_X86_PAE +void xen_l3_entry_update(pud_t *ptr, pud_t val) +{ + mmu_update_t u; + u.ptr = virt_to_machine(ptr); + u.val = pud_val_ma(val); + BUG_ON(HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF) < 0); +} +#endif + +#ifdef CONFIG_X86_64 +void xen_l3_entry_update(pud_t *ptr, pud_t val) +{ + mmu_update_t u; + u.ptr = virt_to_machine(ptr); + u.val = val.pud; + BUG_ON(HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF) < 0); +} + +void xen_l4_entry_update(pgd_t *ptr, pgd_t val) +{ + mmu_update_t u; + u.ptr = virt_to_machine(ptr); + u.val = val.pgd; + BUG_ON(HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF) < 0); +} +#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_XEN_SHADOW_MODE */ + +void xen_machphys_update(unsigned long mfn, unsigned long pfn) +{ + mmu_update_t u; + u.ptr = ((unsigned long long)mfn << PAGE_SHIFT) | MMU_MACHPHYS_UPDATE; + u.val = pfn; + BUG_ON(HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF) < 0); +} + +void xen_pt_switch(unsigned long ptr) +{ + struct mmuext_op op; + op.cmd = MMUEXT_NEW_BASEPTR; + op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); + BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); +} + +void xen_new_user_pt(unsigned long ptr) +{ + struct mmuext_op op; + op.cmd = MMUEXT_NEW_USER_BASEPTR; + op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); + BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); +} + +void xen_tlb_flush(void) +{ + struct mmuext_op op; + op.cmd = MMUEXT_TLB_FLUSH_LOCAL; + BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); +} + +void xen_invlpg(unsigned long ptr) +{ + struct mmuext_op op; + op.cmd = MMUEXT_INVLPG_LOCAL; + op.arg1.linear_addr = ptr & PAGE_MASK; + BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); +} + +#ifdef CONFIG_SMP + +void xen_tlb_flush_all(void) +{ + struct mmuext_op op; + op.cmd = MMUEXT_TLB_FLUSH_ALL; + BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); +} + +void xen_tlb_flush_mask(cpumask_t *mask) +{ + struct mmuext_op op; + if ( cpus_empty(*mask) ) + return; + op.cmd = MMUEXT_TLB_FLUSH_MULTI; + op.arg2.vcpumask = mask->bits; + BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); +} + +void xen_invlpg_all(unsigned long ptr) +{ + struct mmuext_op op; + op.cmd = MMUEXT_INVLPG_ALL; + op.arg1.linear_addr = ptr & PAGE_MASK; + BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); +} + +void xen_invlpg_mask(cpumask_t *mask, unsigned long ptr) +{ + struct mmuext_op op; + if ( cpus_empty(*mask) ) + return; + op.cmd = MMUEXT_INVLPG_MULTI; + op.arg1.linear_addr = ptr & PAGE_MASK; + op.arg2.vcpumask = mask->bits; + BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); +} + +#endif /* CONFIG_SMP */ + +#ifndef CONFIG_XEN_SHADOW_MODE +void xen_pgd_pin(unsigned long ptr) +{ + struct mmuext_op op; +#ifdef CONFIG_X86_64 + op.cmd = MMUEXT_PIN_L4_TABLE; +#elif defined(CONFIG_X86_PAE) + op.cmd = MMUEXT_PIN_L3_TABLE; +#else + op.cmd = MMUEXT_PIN_L2_TABLE; +#endif + op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); + BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); +} + +void xen_pgd_unpin(unsigned long ptr) +{ + struct mmuext_op op; + op.cmd = MMUEXT_UNPIN_TABLE; + op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); + BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); +} + +void xen_pte_pin(unsigned long ptr) +{ + struct mmuext_op op; + op.cmd = MMUEXT_PIN_L1_TABLE; + op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); + BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); +} + +void xen_pte_unpin(unsigned long ptr) +{ + struct mmuext_op op; + op.cmd = MMUEXT_UNPIN_TABLE; + op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); + BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); +} + +#ifdef CONFIG_X86_64 +void xen_pud_pin(unsigned long ptr) +{ + struct mmuext_op op; + op.cmd = MMUEXT_PIN_L3_TABLE; + op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); + BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); +} + +void xen_pud_unpin(unsigned long ptr) +{ + struct mmuext_op op; + op.cmd = MMUEXT_UNPIN_TABLE; + op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); + BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); +} + +void xen_pmd_pin(unsigned long ptr) +{ + struct mmuext_op op; + op.cmd = MMUEXT_PIN_L2_TABLE; + op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); + BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); +} + +void xen_pmd_unpin(unsigned long ptr) +{ + struct mmuext_op op; + op.cmd = MMUEXT_UNPIN_TABLE; + op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); + BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); +} +#endif /* CONFIG_X86_64 */ +#endif /* CONFIG_XEN_SHADOW_MODE */ + +void xen_set_ldt(unsigned long ptr, unsigned long len) +{ + struct mmuext_op op; + op.cmd = MMUEXT_SET_LDT; + op.arg1.linear_addr = ptr; + op.arg2.nr_ents = len; + BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); +} + +/* + * Bitmap is indexed by page number. If bit is set, the page is part of a + * xen_create_contiguous_region() area of memory. + */ +unsigned long *contiguous_bitmap; + +static void contiguous_bitmap_set( + unsigned long first_page, unsigned long nr_pages) +{ + unsigned long start_off, end_off, curr_idx, end_idx; + + curr_idx = first_page / BITS_PER_LONG; + start_off = first_page & (BITS_PER_LONG-1); + end_idx = (first_page + nr_pages) / BITS_PER_LONG; + end_off = (first_page + nr_pages) & (BITS_PER_LONG-1); + + if (curr_idx == end_idx) { + contiguous_bitmap[curr_idx] |= + ((1UL<<end_off)-1) & -(1UL<<start_off); + } else { + contiguous_bitmap[curr_idx] |= -(1UL<<start_off); + while ( ++curr_idx < end_idx ) + contiguous_bitmap[curr_idx] = ~0UL; + contiguous_bitmap[curr_idx] |= (1UL<<end_off)-1; + } +} + +static void contiguous_bitmap_clear( + unsigned long first_page, unsigned long nr_pages) +{ + unsigned long start_off, end_off, curr_idx, end_idx; + + curr_idx = first_page / BITS_PER_LONG; + start_off = first_page & (BITS_PER_LONG-1); + end_idx = (first_page + nr_pages) / BITS_PER_LONG; + end_off = (first_page + nr_pages) & (BITS_PER_LONG-1); + + if (curr_idx == end_idx) { + contiguous_bitmap[curr_idx] &= + -(1UL<<end_off) | ((1UL<<start_off)-1); + } else { + contiguous_bitmap[curr_idx] &= (1UL<<start_off)-1; + while ( ++curr_idx != end_idx ) + contiguous_bitmap[curr_idx] = 0; + contiguous_bitmap[curr_idx] &= -(1UL<<end_off); + } +} + +/* Ensure multi-page extents are contiguous in machine memory. */ +int xen_create_contiguous_region( + unsigned long vstart, unsigned int order, unsigned int address_bits) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + unsigned long frame, i, flags; + struct xen_memory_reservation reservation = { + .extent_start = &frame, + .nr_extents = 1, + .extent_order = 0, + .domid = DOMID_SELF + }; + + scrub_pages(vstart, 1 << order); + + balloon_lock(flags); + + /* 1. Zap current PTEs, giving away the underlying pages. */ + for (i = 0; i < (1<<order); i++) { + pgd = pgd_offset_k(vstart + (i*PAGE_SIZE)); + pud = pud_offset(pgd, (vstart + (i*PAGE_SIZE))); + pmd = pmd_offset(pud, (vstart + (i*PAGE_SIZE))); + pte = pte_offset_kernel(pmd, (vstart + (i*PAGE_SIZE))); + frame = pte_mfn(*pte); + BUG_ON(HYPERVISOR_update_va_mapping( + vstart + (i*PAGE_SIZE), __pte_ma(0), 0)); + set_phys_to_machine((__pa(vstart)>>PAGE_SHIFT)+i, + INVALID_P2M_ENTRY); + BUG_ON(HYPERVISOR_memory_op( + XENMEM_decrease_reservation, &reservation) != 1); + } + + /* 2. Get a new contiguous memory extent. */ + reservation.extent_order = order; + reservation.address_bits = address_bits; + frame = __pa(vstart) >> PAGE_SHIFT; + if (HYPERVISOR_memory_op(XENMEM_populate_physmap, + &reservation) != 1) + goto fail; + + /* 3. Map the new extent in place of old pages. */ + for (i = 0; i < (1<<order); i++) { + BUG_ON(HYPERVISOR_update_va_mapping( + vstart + (i*PAGE_SIZE), + pfn_pte_ma(frame+i, PAGE_KERNEL), 0)); + set_phys_to_machine((__pa(vstart)>>PAGE_SHIFT)+i, frame+i); + } + + flush_tlb_all(); + + contiguous_bitmap_set(__pa(vstart) >> PAGE_SHIFT, 1UL << order); + + balloon_unlock(flags); + + return 0; + + fail: + reservation.extent_order = 0; + reservation.address_bits = 0; + + for (i = 0; i < (1<<order); i++) { + frame = (__pa(vstart) >> PAGE_SHIFT) + i; + BUG_ON(HYPERVISOR_memory_op( + XENMEM_populate_physmap, &reservation) != 1); + BUG_ON(HYPERVISOR_update_va_mapping( + vstart + (i*PAGE_SIZE), + pfn_pte_ma(frame, PAGE_KERNEL), 0)); + set_phys_to_machine((__pa(vstart)>>PAGE_SHIFT)+i, frame); + } + + flush_tlb_all(); + + balloon_unlock(flags); + + return -ENOMEM; +} + +void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + unsigned long frame, i, flags; + struct xen_memory_reservation reservation = { + .extent_start = &frame, + .nr_extents = 1, + .extent_order = 0, + .domid = DOMID_SELF + }; + + scrub_pages(vstart, 1 << order); + + balloon_lock(flags); + + contiguous_bitmap_clear(__pa(vstart) >> PAGE_SHIFT, 1UL << order); + + /* 1. Zap current PTEs, giving away the underlying pages. */ + for (i = 0; i < (1<<order); i++) { + pgd = pgd_offset_k(vstart + (i*PAGE_SIZE)); + pud = pud_offset(pgd, (vstart + (i*PAGE_SIZE))); + pmd = pmd_offset(pud, (vstart + (i*PAGE_SIZE))); + pte = pte_offset_kernel(pmd, (vstart + (i*PAGE_SIZE))); + frame = pte_mfn(*pte); + BUG_ON(HYPERVISOR_update_va_mapping( + vstart + (i*PAGE_SIZE), __pte_ma(0), 0)); + set_phys_to_machine((__pa(vstart)>>PAGE_SHIFT)+i, + INVALID_P2M_ENTRY); + BUG_ON(HYPERVISOR_memory_op( + XENMEM_decrease_reservation, &reservation) != 1); + } + + /* 2. Map new pages in place of old pages. */ + for (i = 0; i < (1<<order); i++) { + frame = (__pa(vstart) >> PAGE_SHIFT) + i; + BUG_ON(HYPERVISOR_memory_op( + XENMEM_populate_physmap, &reservation) != 1); + BUG_ON(HYPERVISOR_update_va_mapping( + vstart + (i*PAGE_SIZE), + pfn_pte_ma(frame, PAGE_KERNEL), 0)); + set_phys_to_machine((__pa(vstart)>>PAGE_SHIFT)+i, frame); + } + + flush_tlb_all(); + + balloon_unlock(flags); +} + +#ifdef __i386__ +int write_ldt_entry(void *ldt, int entry, __u32 entry_a, __u32 entry_b) +{ + __u32 *lp = (__u32 *)((char *)ldt + entry * 8); + maddr_t mach_lp = arbitrary_virt_to_machine(lp); + return HYPERVISOR_update_descriptor( + mach_lp, (u64)entry_a | ((u64)entry_b<<32)); +} +#endif + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/mm/init-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/mm/init-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,780 @@ +/* + * linux/arch/i386/mm/init.c + * + * Copyright (C) 1995 Linus Torvalds + * + * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 + */ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/signal.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/ptrace.h> +#include <linux/mman.h> +#include <linux/mm.h> +#include <linux/hugetlb.h> +#include <linux/swap.h> +#include <linux/smp.h> +#include <linux/init.h> +#include <linux/highmem.h> +#include <linux/pagemap.h> +#include <linux/bootmem.h> +#include <linux/slab.h> +#include <linux/proc_fs.h> +#include <linux/efi.h> + +#include <asm/processor.h> +#include <asm/system.h> +#include <asm/uaccess.h> +#include <asm/pgtable.h> +#include <asm/dma.h> +#include <asm/fixmap.h> +#include <asm/e820.h> +#include <asm/apic.h> +#include <asm/tlb.h> +#include <asm/tlbflush.h> +#include <asm/sections.h> +#include <asm/hypervisor.h> + +extern unsigned long *contiguous_bitmap; + +#if defined(CONFIG_SWIOTLB) +extern void swiotlb_init(void); +int swiotlb; +EXPORT_SYMBOL(swiotlb); +#endif + +unsigned int __VMALLOC_RESERVE = 128 << 20; + +DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); +unsigned long highstart_pfn, highend_pfn; + +static int noinline do_test_wp_bit(void); + +/* + * Creates a middle page table and puts a pointer to it in the + * given global directory entry. This only returns the gd entry + * in non-PAE compilation mode, since the middle layer is folded. + */ +static pmd_t * __init one_md_table_init(pgd_t *pgd) +{ + pud_t *pud; + pmd_t *pmd_table; + +#ifdef CONFIG_X86_PAE + pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE); + make_lowmem_page_readonly(pmd_table, XENFEAT_writable_page_tables); + set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT)); + pud = pud_offset(pgd, 0); + if (pmd_table != pmd_offset(pud, 0)) + BUG(); +#else + pud = pud_offset(pgd, 0); + pmd_table = pmd_offset(pud, 0); +#endif + + return pmd_table; +} + +/* + * Create a page table and place a pointer to it in a middle page + * directory entry. + */ +static pte_t * __init one_page_table_init(pmd_t *pmd) +{ + if (pmd_none(*pmd)) { + pte_t *page_table = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE); + make_lowmem_page_readonly(page_table, + XENFEAT_writable_page_tables); + set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE)); + if (page_table != pte_offset_kernel(pmd, 0)) + BUG(); + + return page_table; + } + + return pte_offset_kernel(pmd, 0); +} + +/* + * This function initializes a certain range of kernel virtual memory + * with new bootmem page tables, everywhere page tables are missing in + * the given range. + */ + +/* + * NOTE: The pagetables are allocated contiguous on the physical space + * so we can cache the place of the first one and move around without + * checking the pgd every time. + */ +static void __init page_table_range_init (unsigned long start, unsigned long end, pgd_t *pgd_base) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + int pgd_idx, pmd_idx; + unsigned long vaddr; + + vaddr = start; + pgd_idx = pgd_index(vaddr); + pmd_idx = pmd_index(vaddr); + pgd = pgd_base + pgd_idx; + + for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd++, pgd_idx++) { + if (pgd_none(*pgd)) + one_md_table_init(pgd); + pud = pud_offset(pgd, vaddr); + pmd = pmd_offset(pud, vaddr); + for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end); pmd++, pmd_idx++) { + if (vaddr < HYPERVISOR_VIRT_START && pmd_none(*pmd)) + one_page_table_init(pmd); + + vaddr += PMD_SIZE; + } + pmd_idx = 0; + } +} + +static inline int is_kernel_text(unsigned long addr) +{ + if (addr >= PAGE_OFFSET && addr <= (unsigned long)__init_end) + return 1; + return 0; +} + +/* + * This maps the physical memory to kernel virtual address space, a total + * of max_low_pfn pages, by creating page tables starting from address + * PAGE_OFFSET. + */ +static void __init kernel_physical_mapping_init(pgd_t *pgd_base) +{ + unsigned long pfn; + pgd_t *pgd; + pmd_t *pmd; + pte_t *pte; + int pgd_idx, pmd_idx, pte_ofs; + + unsigned long max_ram_pfn = xen_start_info->nr_pages; + if (max_ram_pfn > max_low_pfn) + max_ram_pfn = max_low_pfn; + + pgd_idx = pgd_index(PAGE_OFFSET); + pgd = pgd_base + pgd_idx; + pfn = 0; + pmd_idx = pmd_index(PAGE_OFFSET); + pte_ofs = pte_index(PAGE_OFFSET); + + for (; pgd_idx < PTRS_PER_PGD; pgd++, pgd_idx++) { +#ifdef CONFIG_XEN + /* + * Native linux hasn't PAE-paging enabled yet at this + * point. When running as xen domain we are in PAE + * mode already, thus we can't simply hook a empty + * pmd. That would kill the mappings we are currently + * using ... + */ + pmd = pmd_offset(pud_offset(pgd, PAGE_OFFSET), PAGE_OFFSET); +#else + pmd = one_md_table_init(pgd); +#endif + if (pfn >= max_low_pfn) + continue; + pmd += pmd_idx; + for (; pmd_idx < PTRS_PER_PMD && pfn < max_low_pfn; pmd++, pmd_idx++) { + unsigned int address = pfn * PAGE_SIZE + PAGE_OFFSET; + if (address >= HYPERVISOR_VIRT_START) + continue; + + /* Map with big pages if possible, otherwise create normal page tables. */ + if (cpu_has_pse) { + unsigned int address2 = (pfn + PTRS_PER_PTE - 1) * PAGE_SIZE + PAGE_OFFSET + PAGE_SIZE-1; + + if (is_kernel_text(address) || is_kernel_text(address2)) + set_pmd(pmd, pfn_pmd(pfn, PAGE_KERNEL_LARGE_EXEC)); + else + set_pmd(pmd, pfn_pmd(pfn, PAGE_KERNEL_LARGE)); + pfn += PTRS_PER_PTE; + } else { + pte = one_page_table_init(pmd); + + pte += pte_ofs; + for (; pte_ofs < PTRS_PER_PTE && pfn < max_low_pfn; pte++, pfn++, pte_ofs++) { + /* XEN: Only map initial RAM allocation. */ + if ((pfn >= max_ram_pfn) || pte_present(*pte)) + continue; + if (is_kernel_text(address)) + set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC)); + else + set_pte(pte, pfn_pte(pfn, PAGE_KERNEL)); + } + pte_ofs = 0; + } + } + pmd_idx = 0; + } +} + +#ifndef CONFIG_XEN + +static inline int page_kills_ppro(unsigned long pagenr) +{ + if (pagenr >= 0x70000 && pagenr <= 0x7003F) + return 1; + return 0; +} + +extern int is_available_memory(efi_memory_desc_t *); + +static inline int page_is_ram(unsigned long pagenr) +{ + int i; + unsigned long addr, end; + + if (efi_enabled) { + efi_memory_desc_t *md; + + for (i = 0; i < memmap.nr_map; i++) { + md = &memmap.map[i]; + if (!is_available_memory(md)) + continue; + addr = (md->phys_addr+PAGE_SIZE-1) >> PAGE_SHIFT; + end = (md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT)) >> PAGE_SHIFT; + + if ((pagenr >= addr) && (pagenr < end)) + return 1; + } + return 0; + } + + for (i = 0; i < e820.nr_map; i++) { + + if (e820.map[i].type != E820_RAM) /* not usable memory */ + continue; + /* + * !!!FIXME!!! Some BIOSen report areas as RAM that + * are not. Notably the 640->1Mb area. We need a sanity + * check here. + */ + addr = (e820.map[i].addr+PAGE_SIZE-1) >> PAGE_SHIFT; + end = (e820.map[i].addr+e820.map[i].size) >> PAGE_SHIFT; + if ((pagenr >= addr) && (pagenr < end)) + return 1; + } + return 0; +} + +#else /* CONFIG_XEN */ + +#define page_kills_ppro(p) 0 +#define page_is_ram(p) 1 + +#endif + +#ifdef CONFIG_HIGHMEM +pte_t *kmap_pte; +pgprot_t kmap_prot; + +#define kmap_get_fixmap_pte(vaddr) \ + pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr), vaddr), (vaddr)), (vaddr)) + +static void __init kmap_init(void) +{ + unsigned long kmap_vstart; + + /* cache the first kmap pte */ + kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN); + kmap_pte = kmap_get_fixmap_pte(kmap_vstart); + + kmap_prot = PAGE_KERNEL; +} + +static void __init permanent_kmaps_init(pgd_t *pgd_base) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + unsigned long vaddr; + + vaddr = PKMAP_BASE; + page_table_range_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base); + + pgd = swapper_pg_dir + pgd_index(vaddr); + pud = pud_offset(pgd, vaddr); + pmd = pmd_offset(pud, vaddr); + pte = pte_offset_kernel(pmd, vaddr); + pkmap_page_table = pte; +} + +void __init one_highpage_init(struct page *page, int pfn, int bad_ppro) +{ + if (page_is_ram(pfn) && !(bad_ppro && page_kills_ppro(pfn))) { + ClearPageReserved(page); + set_bit(PG_highmem, &page->flags); + set_page_count(page, 1); + if (pfn < xen_start_info->nr_pages) + __free_page(page); + totalhigh_pages++; + } else + SetPageReserved(page); +} + +#ifndef CONFIG_DISCONTIGMEM +static void __init set_highmem_pages_init(int bad_ppro) +{ + int pfn; + for (pfn = highstart_pfn; pfn < highend_pfn; pfn++) + one_highpage_init(pfn_to_page(pfn), pfn, bad_ppro); + totalram_pages += totalhigh_pages; +} +#else +extern void set_highmem_pages_init(int); +#endif /* !CONFIG_DISCONTIGMEM */ + +#else +#define kmap_init() do { } while (0) +#define permanent_kmaps_init(pgd_base) do { } while (0) +#define set_highmem_pages_init(bad_ppro) do { } while (0) +#endif /* CONFIG_HIGHMEM */ + +unsigned long long __PAGE_KERNEL = _PAGE_KERNEL; +unsigned long long __PAGE_KERNEL_EXEC = _PAGE_KERNEL_EXEC; + +#ifndef CONFIG_DISCONTIGMEM +#define remap_numa_kva() do {} while (0) +#else +extern void __init remap_numa_kva(void); +#endif + +pgd_t *swapper_pg_dir; + +static void __init pagetable_init (void) +{ + unsigned long vaddr; + pgd_t *pgd_base = (pgd_t *)xen_start_info->pt_base; + int i; + + swapper_pg_dir = pgd_base; + init_mm.pgd = pgd_base; + for (i = 0; i < NR_CPUS; i++) + per_cpu(cur_pgd, i) = pgd_base; + + /* Enable PSE if available */ + if (cpu_has_pse) { + set_in_cr4(X86_CR4_PSE); + } + + /* Enable PGE if available */ + if (cpu_has_pge) { + set_in_cr4(X86_CR4_PGE); + __PAGE_KERNEL |= _PAGE_GLOBAL; + __PAGE_KERNEL_EXEC |= _PAGE_GLOBAL; + } + + kernel_physical_mapping_init(pgd_base); + remap_numa_kva(); + + /* + * Fixed mappings, only the page table structure has to be + * created - mappings will be set by set_fixmap(): + */ + vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK; + page_table_range_init(vaddr, 0, pgd_base); + + permanent_kmaps_init(pgd_base); +} + +#if defined(CONFIG_PM_DISK) || defined(CONFIG_SOFTWARE_SUSPEND) +/* + * Swap suspend & friends need this for resume because things like the intel-agp + * driver might have split up a kernel 4MB mapping. + */ +char __nosavedata swsusp_pg_dir[PAGE_SIZE] + __attribute__ ((aligned (PAGE_SIZE))); + +static inline void save_pg_dir(void) +{ + memcpy(swsusp_pg_dir, swapper_pg_dir, PAGE_SIZE); +} +#else +static inline void save_pg_dir(void) +{ +} +#endif + +void zap_low_mappings (void) +{ + int i; + + save_pg_dir(); + + /* + * Zap initial low-memory mappings. + * + * Note that "pgd_clear()" doesn't do it for + * us, because pgd_clear() is a no-op on i386. + */ + for (i = 0; i < USER_PTRS_PER_PGD; i++) +#if defined(CONFIG_X86_PAE) && !defined(CONFIG_XEN) + set_pgd(swapper_pg_dir+i, __pgd(1 + __pa(empty_zero_page))); +#else + set_pgd(swapper_pg_dir+i, __pgd(0)); +#endif + flush_tlb_all(); +} + +static int disable_nx __initdata = 0; +u64 __supported_pte_mask = ~_PAGE_NX; + +/* + * noexec = on|off + * + * Control non executable mappings. + * + * on Enable + * off Disable + */ +void __init noexec_setup(const char *str) +{ + if (!strncmp(str, "on",2) && cpu_has_nx) { + __supported_pte_mask |= _PAGE_NX; + disable_nx = 0; + } else if (!strncmp(str,"off",3)) { + disable_nx = 1; + __supported_pte_mask &= ~_PAGE_NX; + } +} + +int nx_enabled = 0; +#ifdef CONFIG_X86_PAE + +static void __init set_nx(void) +{ + unsigned int v[4], l, h; + + if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) { + cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]); + if ((v[3] & (1 << 20)) && !disable_nx) { + rdmsr(MSR_EFER, l, h); + l |= EFER_NX; + wrmsr(MSR_EFER, l, h); + nx_enabled = 1; + __supported_pte_mask |= _PAGE_NX; + } + } +} + +/* + * Enables/disables executability of a given kernel page and + * returns the previous setting. + */ +int __init set_kernel_exec(unsigned long vaddr, int enable) +{ + pte_t *pte; + int ret = 1; + + if (!nx_enabled) + goto out; + + pte = lookup_address(vaddr); + BUG_ON(!pte); + + if (!pte_exec_kernel(*pte)) + ret = 0; + + if (enable) + pte->pte_high &= ~(1 << (_PAGE_BIT_NX - 32)); + else + pte->pte_high |= 1 << (_PAGE_BIT_NX - 32); + __flush_tlb_all(); +out: + return ret; +} + +#endif + +/* + * paging_init() sets up the page tables - note that the first 8MB are + * already mapped by head.S. + * + * This routines also unmaps the page at virtual kernel address 0, so + * that we can trap those pesky NULL-reference errors in the kernel. + */ +void __init paging_init(void) +{ +#ifdef CONFIG_XEN_PHYSDEV_ACCESS + int i; +#endif + +#ifdef CONFIG_X86_PAE + set_nx(); + if (nx_enabled) + printk("NX (Execute Disable) protection: active\n"); +#endif + + pagetable_init(); + +#if defined(CONFIG_X86_PAE) && !defined(CONFIG_XEN) + /* + * We will bail out later - printk doesn't work right now so + * the user would just see a hanging kernel. + * when running as xen domain we are already in PAE mode at + * this point. + */ + if (cpu_has_pae) + set_in_cr4(X86_CR4_PAE); +#endif + __flush_tlb_all(); + + kmap_init(); + + /* Switch to the real shared_info page, and clear the dummy page. */ + set_fixmap(FIX_SHARED_INFO, xen_start_info->shared_info); + HYPERVISOR_shared_info = (shared_info_t *)fix_to_virt(FIX_SHARED_INFO); + memset(empty_zero_page, 0, sizeof(empty_zero_page)); + +#ifdef CONFIG_XEN_PHYSDEV_ACCESS + /* Setup mapping of lower 1st MB */ + for (i = 0; i < NR_FIX_ISAMAPS; i++) + if (xen_start_info->flags & SIF_PRIVILEGED) + set_fixmap(FIX_ISAMAP_BEGIN - i, i * PAGE_SIZE); + else + __set_fixmap(FIX_ISAMAP_BEGIN - i, + virt_to_machine(empty_zero_page), + PAGE_KERNEL_RO); +#endif +} + +/* + * Test if the WP bit works in supervisor mode. It isn't supported on 386's + * and also on some strange 486's (NexGen etc.). All 586+'s are OK. This + * used to involve black magic jumps to work around some nasty CPU bugs, + * but fortunately the switch to using exceptions got rid of all that. + */ + +static void __init test_wp_bit(void) +{ + printk("Checking if this processor honours the WP bit even in supervisor mode... "); + + /* Any page-aligned address will do, the test is non-destructive */ + __set_fixmap(FIX_WP_TEST, __pa(&swapper_pg_dir), PAGE_READONLY); + boot_cpu_data.wp_works_ok = do_test_wp_bit(); + clear_fixmap(FIX_WP_TEST); + + if (!boot_cpu_data.wp_works_ok) { + printk("No.\n"); +#ifdef CONFIG_X86_WP_WORKS_OK + panic("This kernel doesn't support CPU's with broken WP. Recompile it for a 386!"); +#endif + } else { + printk("Ok.\n"); + } +} + +static void __init set_max_mapnr_init(void) +{ +#ifdef CONFIG_HIGHMEM + num_physpages = highend_pfn; +#else + num_physpages = max_low_pfn; +#endif +#ifndef CONFIG_DISCONTIGMEM + max_mapnr = num_physpages; +#endif +} + +static struct kcore_list kcore_mem, kcore_vmalloc; + +void __init mem_init(void) +{ + extern int ppro_with_ram_bug(void); + int codesize, reservedpages, datasize, initsize; + int tmp; + int bad_ppro; + unsigned long pfn; + + contiguous_bitmap = alloc_bootmem_low_pages( + (max_low_pfn + 2*BITS_PER_LONG) >> 3); + BUG_ON(!contiguous_bitmap); + memset(contiguous_bitmap, 0, (max_low_pfn + 2*BITS_PER_LONG) >> 3); + +#if defined(CONFIG_SWIOTLB) + swiotlb_init(); +#endif + +#ifndef CONFIG_DISCONTIGMEM + if (!mem_map) + BUG(); +#endif + + bad_ppro = ppro_with_ram_bug(); + +#ifdef CONFIG_HIGHMEM + /* check that fixmap and pkmap do not overlap */ + if (PKMAP_BASE+LAST_PKMAP*PAGE_SIZE >= FIXADDR_START) { + printk(KERN_ERR "fixmap and kmap areas overlap - this will crash\n"); + printk(KERN_ERR "pkstart: %lxh pkend: %lxh fixstart %lxh\n", + PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE, FIXADDR_START); + BUG(); + } +#endif + + set_max_mapnr_init(); + +#ifdef CONFIG_HIGHMEM + high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1; +#else + high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1; +#endif + printk("vmalloc area: %lx-%lx, maxmem %lx\n", + VMALLOC_START,VMALLOC_END,MAXMEM); + BUG_ON(VMALLOC_START > VMALLOC_END); + + /* this will put all low memory onto the freelists */ + totalram_pages += free_all_bootmem(); + /* XEN: init and count low-mem pages outside initial allocation. */ + for (pfn = xen_start_info->nr_pages; pfn < max_low_pfn; pfn++) { + ClearPageReserved(&mem_map[pfn]); + set_page_count(&mem_map[pfn], 1); + totalram_pages++; + } + + reservedpages = 0; + for (tmp = 0; tmp < max_low_pfn; tmp++) + /* + * Only count reserved RAM pages + */ + if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp))) + reservedpages++; + + set_highmem_pages_init(bad_ppro); + + codesize = (unsigned long) &_etext - (unsigned long) &_text; + datasize = (unsigned long) &_edata - (unsigned long) &_etext; + initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; + + kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT); + kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, + VMALLOC_END-VMALLOC_START); + + printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, %dk reserved, %dk data, %dk init, %ldk highmem)\n", + (unsigned long) nr_free_pages() << (PAGE_SHIFT-10), + num_physpages << (PAGE_SHIFT-10), + codesize >> 10, + reservedpages << (PAGE_SHIFT-10), + datasize >> 10, + initsize >> 10, + (unsigned long) (totalhigh_pages << (PAGE_SHIFT-10)) + ); + +#ifdef CONFIG_X86_PAE + if (!cpu_has_pae) + panic("cannot execute a PAE-enabled kernel on a PAE-less CPU!"); +#endif + if (boot_cpu_data.wp_works_ok < 0) + test_wp_bit(); + + /* + * Subtle. SMP is doing it's boot stuff late (because it has to + * fork idle threads) - but it also needs low mappings for the + * protected-mode entry to work. We zap these entries only after + * the WP-bit has been tested. + */ +#ifndef CONFIG_SMP + zap_low_mappings(); +#endif + + set_bit(PG_pinned, &virt_to_page(init_mm.pgd)->flags); +} + +kmem_cache_t *pgd_cache; +kmem_cache_t *pmd_cache; + +void __init pgtable_cache_init(void) +{ + if (PTRS_PER_PMD > 1) { + pmd_cache = kmem_cache_create("pmd", + PTRS_PER_PMD*sizeof(pmd_t), + PTRS_PER_PMD*sizeof(pmd_t), + 0, + pmd_ctor, + NULL); + if (!pmd_cache) + panic("pgtable_cache_init(): cannot create pmd cache"); + } + pgd_cache = kmem_cache_create("pgd", +#ifndef CONFIG_XEN + PTRS_PER_PGD*sizeof(pgd_t), + PTRS_PER_PGD*sizeof(pgd_t), +#else + PAGE_SIZE, + PAGE_SIZE, +#endif + 0, + pgd_ctor, + PTRS_PER_PMD == 1 ? pgd_dtor : NULL); + if (!pgd_cache) + panic("pgtable_cache_init(): Cannot create pgd cache"); +} + +/* + * This function cannot be __init, since exceptions don't work in that + * section. Put this after the callers, so that it cannot be inlined. + */ +static int noinline do_test_wp_bit(void) +{ + char tmp_reg; + int flag; + + __asm__ __volatile__( + " movb %0,%1 \n" + "1: movb %1,%0 \n" + " xorl %2,%2 \n" + "2: \n" + ".section __ex_table,\"a\"\n" + " .align 4 \n" + " .long 1b,2b \n" + ".previous \n" + :"=m" (*(char *)fix_to_virt(FIX_WP_TEST)), + "=q" (tmp_reg), + "=r" (flag) + :"2" (1) + :"memory"); + + return flag; +} + +void free_initmem(void) +{ + unsigned long addr; + + addr = (unsigned long)(&__init_begin); + for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) { + ClearPageReserved(virt_to_page(addr)); + set_page_count(virt_to_page(addr), 1); + memset((void *)addr, 0xcc, PAGE_SIZE); + free_page(addr); + totalram_pages++; + } + printk (KERN_INFO "Freeing unused kernel memory: %dk freed\n", (__init_end - __init_begin) >> 10); +} + +#ifdef CONFIG_BLK_DEV_INITRD +void free_initrd_mem(unsigned long start, unsigned long end) +{ + if (start < end) + printk (KERN_INFO "Freeing initrd memory: %ldk freed\n", (end - start) >> 10); + for (; start < end; start += PAGE_SIZE) { + ClearPageReserved(virt_to_page(start)); + set_page_count(virt_to_page(start), 1); + free_page(start); + totalram_pages++; + } +} +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/mm/ioremap-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/mm/ioremap-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,470 @@ +/* + * arch/i386/mm/ioremap.c + * + * Re-map IO memory to kernel address space so that we can access it. + * This is needed for high PCI addresses that aren't mapped in the + * 640k-1MB IO memory area on PC's + * + * (C) Copyright 1995 1996 Linus Torvalds + */ + +#include <linux/vmalloc.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <asm/io.h> +#include <asm/fixmap.h> +#include <asm/cacheflush.h> +#include <asm/tlbflush.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> + +#define ISA_START_ADDRESS 0x0 +#define ISA_END_ADDRESS 0x100000 + +#if 0 /* not PAE safe */ +/* These hacky macros avoid phys->machine translations. */ +#define __direct_pte(x) ((pte_t) { (x) } ) +#define __direct_mk_pte(page_nr,pgprot) \ + __direct_pte(((page_nr) << PAGE_SHIFT) | pgprot_val(pgprot)) +#define direct_mk_pte_phys(physpage, pgprot) \ + __direct_mk_pte((physpage) >> PAGE_SHIFT, pgprot) +#endif + +static int direct_remap_area_pte_fn(pte_t *pte, + struct page *pte_page, + unsigned long address, + void *data) +{ + mmu_update_t **v = (mmu_update_t **)data; + + (*v)->ptr = ((u64)pfn_to_mfn(page_to_pfn(pte_page)) << + PAGE_SHIFT) | ((unsigned long)pte & ~PAGE_MASK); + (*v)++; + + return 0; +} + +static int __direct_remap_pfn_range(struct mm_struct *mm, + unsigned long address, + unsigned long mfn, + unsigned long size, + pgprot_t prot, + domid_t domid) +{ + int rc; + unsigned long i, start_address; + mmu_update_t *u, *v, *w; + + u = v = w = (mmu_update_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT); + if (u == NULL) + return -ENOMEM; + + start_address = address; + + flush_cache_all(); + + for (i = 0; i < size; i += PAGE_SIZE) { + if ((v - u) == (PAGE_SIZE / sizeof(mmu_update_t))) { + /* Fill in the PTE pointers. */ + rc = generic_page_range(mm, start_address, + address - start_address, + direct_remap_area_pte_fn, &w); + if (rc) + goto out; + w = u; + rc = -EFAULT; + if (HYPERVISOR_mmu_update(u, v - u, NULL, domid) < 0) + goto out; + v = u; + start_address = address; + } + + /* + * Fill in the machine address: PTE ptr is done later by + * __direct_remap_area_pages(). + */ + v->val = pte_val_ma(pfn_pte_ma(mfn, prot)); + + mfn++; + address += PAGE_SIZE; + v++; + } + + if (v != u) { + /* get the ptep's filled in */ + rc = generic_page_range(mm, start_address, address - start_address, + direct_remap_area_pte_fn, &w); + if (rc) + goto out; + rc = -EFAULT; + if (unlikely(HYPERVISOR_mmu_update(u, v - u, NULL, domid) < 0)) + goto out; + } + + rc = 0; + + out: + flush_tlb_all(); + + free_page((unsigned long)u); + + return rc; +} + +int direct_remap_pfn_range(struct vm_area_struct *vma, + unsigned long address, + unsigned long mfn, + unsigned long size, + pgprot_t prot, + domid_t domid) +{ + /* Same as remap_pfn_range(). */ + vma->vm_flags |= VM_IO | VM_RESERVED; + + return __direct_remap_pfn_range( + vma->vm_mm, address, mfn, size, prot, domid); +} +EXPORT_SYMBOL(direct_remap_pfn_range); + +int direct_kernel_remap_pfn_range(unsigned long address, + unsigned long mfn, + unsigned long size, + pgprot_t prot, + domid_t domid) +{ + return __direct_remap_pfn_range( + &init_mm, address, mfn, size, prot, domid); +} +EXPORT_SYMBOL(direct_kernel_remap_pfn_range); + +static int lookup_pte_fn( + pte_t *pte, struct page *pte_page, unsigned long addr, void *data) +{ + uint64_t *ptep = (uint64_t *)data; + if (ptep) + *ptep = ((uint64_t)pfn_to_mfn(page_to_pfn(pte_page)) << + PAGE_SHIFT) | ((unsigned long)pte & ~PAGE_MASK); + return 0; +} + +int create_lookup_pte_addr(struct mm_struct *mm, + unsigned long address, + uint64_t *ptep) +{ + return generic_page_range(mm, address, PAGE_SIZE, lookup_pte_fn, ptep); +} + +EXPORT_SYMBOL(create_lookup_pte_addr); + +static int noop_fn( + pte_t *pte, struct page *pte_page, unsigned long addr, void *data) +{ + return 0; +} + +int touch_pte_range(struct mm_struct *mm, + unsigned long address, + unsigned long size) +{ + return generic_page_range(mm, address, size, noop_fn, NULL); +} + +EXPORT_SYMBOL(touch_pte_range); + +#ifdef CONFIG_XEN_PHYSDEV_ACCESS + +/* + * Does @address reside within a non-highmem page that is local to this virtual + * machine (i.e., not an I/O page, nor a memory page belonging to another VM). + * See the comment that accompanies pte_pfn() in pgtable-2level.h to understand + * why this works. + */ +static inline int is_local_lowmem(unsigned long address) +{ + extern unsigned long max_low_pfn; + unsigned long mfn = address >> PAGE_SHIFT; + unsigned long pfn = mfn_to_pfn(mfn); + return ((pfn < max_low_pfn) && (phys_to_machine_mapping[pfn] == mfn)); +} + +/* + * Generic mapping function (not visible outside): + */ + +/* + * Remap an arbitrary physical address space into the kernel virtual + * address space. Needed when the kernel wants to access high addresses + * directly. + * + * NOTE! We need to allow non-page-aligned mappings too: we will obviously + * have to convert them into an offset in a page-aligned mapping, but the + * caller shouldn't need to know that small detail. + */ +void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned long flags) +{ + void __iomem * addr; + struct vm_struct * area; + unsigned long offset, last_addr; + domid_t domid = DOMID_IO; + + /* Don't allow wraparound or zero size */ + last_addr = phys_addr + size - 1; + if (!size || last_addr < phys_addr) + return NULL; + + /* + * Don't remap the low PCI/ISA area, it's always mapped.. + */ + if (xen_start_info->flags & SIF_PRIVILEGED && + phys_addr >= ISA_START_ADDRESS && last_addr < ISA_END_ADDRESS) + return (void __iomem *) isa_bus_to_virt(phys_addr); + + /* + * Don't allow anybody to remap normal RAM that we're using.. + */ + if (is_local_lowmem(phys_addr)) { + char *t_addr, *t_end; + struct page *page; + + t_addr = bus_to_virt(phys_addr); + t_end = t_addr + (size - 1); + + for(page = virt_to_page(t_addr); page <= virt_to_page(t_end); page++) + if(!PageReserved(page)) + return NULL; + + domid = DOMID_SELF; + } + + /* + * Mappings have to be page-aligned + */ + offset = phys_addr & ~PAGE_MASK; + phys_addr &= PAGE_MASK; + size = PAGE_ALIGN(last_addr+1) - phys_addr; + + /* + * Ok, go for it.. + */ + area = get_vm_area(size, VM_IOREMAP | (flags << 20)); + if (!area) + return NULL; + area->phys_addr = phys_addr; + addr = (void __iomem *) area->addr; + flags |= _PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED; +#ifdef __x86_64__ + flags |= _PAGE_USER; +#endif + if (__direct_remap_pfn_range(&init_mm, (unsigned long)addr, + phys_addr>>PAGE_SHIFT, + size, __pgprot(flags), domid)) { + vunmap((void __force *) addr); + return NULL; + } + return (void __iomem *) (offset + (char __iomem *)addr); +} + + +/** + * ioremap_nocache - map bus memory into CPU space + * @offset: bus address of the memory + * @size: size of the resource to map + * + * ioremap_nocache performs a platform specific sequence of operations to + * make bus memory CPU accessible via the readb/readw/readl/writeb/ + * writew/writel functions and the other mmio helpers. The returned + * address is not guaranteed to be usable directly as a virtual + * address. + * + * This version of ioremap ensures that the memory is marked uncachable + * on the CPU as well as honouring existing caching rules from things like + * the PCI bus. Note that there are other caches and buffers on many + * busses. In particular driver authors should read up on PCI writes + * + * It's useful if some control registers are in such an area and + * write combining or read caching is not desirable: + * + * Must be freed with iounmap. + */ + +void __iomem *ioremap_nocache (unsigned long phys_addr, unsigned long size) +{ + unsigned long last_addr; + void __iomem *p = __ioremap(phys_addr, size, _PAGE_PCD); + if (!p) + return p; + + /* Guaranteed to be > phys_addr, as per __ioremap() */ + last_addr = phys_addr + size - 1; + + if (is_local_lowmem(last_addr)) { + struct page *ppage = virt_to_page(bus_to_virt(phys_addr)); + unsigned long npages; + + phys_addr &= PAGE_MASK; + + /* This might overflow and become zero.. */ + last_addr = PAGE_ALIGN(last_addr); + + /* .. but that's ok, because modulo-2**n arithmetic will make + * the page-aligned "last - first" come out right. + */ + npages = (last_addr - phys_addr) >> PAGE_SHIFT; + + if (change_page_attr(ppage, npages, PAGE_KERNEL_NOCACHE) < 0) { + iounmap(p); + p = NULL; + } + global_flush_tlb(); + } + + return p; +} + +void iounmap(volatile void __iomem *addr) +{ + struct vm_struct *p; + if ((void __force *) addr <= high_memory) + return; + + /* + * __ioremap special-cases the PCI/ISA range by not instantiating a + * vm_area and by simply returning an address into the kernel mapping + * of ISA space. So handle that here. + */ + if ((unsigned long) addr >= fix_to_virt(FIX_ISAMAP_BEGIN)) + return; + + write_lock(&vmlist_lock); + p = __remove_vm_area((void *) (PAGE_MASK & (unsigned long __force) addr)); + if (!p) { + printk("iounmap: bad address %p\n", addr); + goto out_unlock; + } + + if ((p->flags >> 20) && is_local_lowmem(p->phys_addr)) { + /* p->size includes the guard page, but cpa doesn't like that */ + change_page_attr(virt_to_page(bus_to_virt(p->phys_addr)), + (p->size - PAGE_SIZE) >> PAGE_SHIFT, + PAGE_KERNEL); + global_flush_tlb(); + } +out_unlock: + write_unlock(&vmlist_lock); + kfree(p); +} + +#ifdef __i386__ + +void __init *bt_ioremap(unsigned long phys_addr, unsigned long size) +{ + unsigned long offset, last_addr; + unsigned int nrpages; + enum fixed_addresses idx; + + /* Don't allow wraparound or zero size */ + last_addr = phys_addr + size - 1; + if (!size || last_addr < phys_addr) + return NULL; + + /* + * Don't remap the low PCI/ISA area, it's always mapped.. + */ + if (xen_start_info->flags & SIF_PRIVILEGED && + phys_addr >= ISA_START_ADDRESS && last_addr < ISA_END_ADDRESS) + return isa_bus_to_virt(phys_addr); + + /* + * Mappings have to be page-aligned + */ + offset = phys_addr & ~PAGE_MASK; + phys_addr &= PAGE_MASK; + size = PAGE_ALIGN(last_addr) - phys_addr; + + /* + * Mappings have to fit in the FIX_BTMAP area. + */ + nrpages = size >> PAGE_SHIFT; + if (nrpages > NR_FIX_BTMAPS) + return NULL; + + /* + * Ok, go for it.. + */ + idx = FIX_BTMAP_BEGIN; + while (nrpages > 0) { + set_fixmap(idx, phys_addr); + phys_addr += PAGE_SIZE; + --idx; + --nrpages; + } + return (void*) (offset + fix_to_virt(FIX_BTMAP_BEGIN)); +} + +void __init bt_iounmap(void *addr, unsigned long size) +{ + unsigned long virt_addr; + unsigned long offset; + unsigned int nrpages; + enum fixed_addresses idx; + + virt_addr = (unsigned long)addr; + if (virt_addr < fix_to_virt(FIX_BTMAP_BEGIN)) + return; + if (virt_addr >= fix_to_virt(FIX_ISAMAP_BEGIN)) + return; + offset = virt_addr & ~PAGE_MASK; + nrpages = PAGE_ALIGN(offset + size - 1) >> PAGE_SHIFT; + + idx = FIX_BTMAP_BEGIN; + while (nrpages > 0) { + clear_fixmap(idx); + --idx; + --nrpages; + } +} + +#endif /* __i386__ */ + +#else /* CONFIG_XEN_PHYSDEV_ACCESS */ + +void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, + unsigned long flags) +{ + return NULL; +} + +void __iomem *ioremap_nocache (unsigned long phys_addr, unsigned long size) +{ + return NULL; +} + +void iounmap(volatile void __iomem *addr) +{ +} + +#ifdef __i386__ + +void __init *bt_ioremap(unsigned long phys_addr, unsigned long size) +{ + return NULL; +} + +void __init bt_iounmap(void *addr, unsigned long size) +{ +} + +#endif /* __i386__ */ + +#endif /* CONFIG_XEN_PHYSDEV_ACCESS */ + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/mm/pgtable-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/mm/pgtable-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,619 @@ +/* + * linux/arch/i386/mm/pgtable.c + */ + +#include <linux/config.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/mm.h> +#include <linux/swap.h> +#include <linux/smp.h> +#include <linux/highmem.h> +#include <linux/slab.h> +#include <linux/pagemap.h> +#include <linux/spinlock.h> + +#include <asm/system.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/fixmap.h> +#include <asm/e820.h> +#include <asm/tlb.h> +#include <asm/tlbflush.h> +#include <asm/io.h> +#include <asm/mmu_context.h> + +#include <xen/features.h> +#include <xen/foreign_page.h> +#include <asm/hypervisor.h> + +static void pgd_test_and_unpin(pgd_t *pgd); + +void show_mem(void) +{ + int total = 0, reserved = 0; + int shared = 0, cached = 0; + int highmem = 0; + struct page *page; + pg_data_t *pgdat; + unsigned long i; + + printk("Mem-info:\n"); + show_free_areas(); + printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10)); + for_each_pgdat(pgdat) { + for (i = 0; i < pgdat->node_spanned_pages; ++i) { + page = pgdat->node_mem_map + i; + total++; + if (PageHighMem(page)) + highmem++; + if (PageReserved(page)) + reserved++; + else if (PageSwapCache(page)) + cached++; + else if (page_count(page)) + shared += page_count(page) - 1; + } + } + printk("%d pages of RAM\n", total); + printk("%d pages of HIGHMEM\n",highmem); + printk("%d reserved pages\n",reserved); + printk("%d pages shared\n",shared); + printk("%d pages swap cached\n",cached); +} + +/* + * Associate a virtual page frame with a given physical page frame + * and protection flags for that frame. + */ +static void set_pte_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + pgd = swapper_pg_dir + pgd_index(vaddr); + if (pgd_none(*pgd)) { + BUG(); + return; + } + pud = pud_offset(pgd, vaddr); + if (pud_none(*pud)) { + BUG(); + return; + } + pmd = pmd_offset(pud, vaddr); + if (pmd_none(*pmd)) { + BUG(); + return; + } + pte = pte_offset_kernel(pmd, vaddr); + /* <pfn,flags> stored as-is, to permit clearing entries */ + set_pte(pte, pfn_pte(pfn, flags)); + + /* + * It's enough to flush this one mapping. + * (PGE mappings get flushed as well) + */ + __flush_tlb_one(vaddr); +} + +/* + * Associate a virtual page frame with a given physical page frame + * and protection flags for that frame. + */ +static void set_pte_pfn_ma(unsigned long vaddr, unsigned long pfn, + pgprot_t flags) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + pgd = swapper_pg_dir + pgd_index(vaddr); + if (pgd_none(*pgd)) { + BUG(); + return; + } + pud = pud_offset(pgd, vaddr); + if (pud_none(*pud)) { + BUG(); + return; + } + pmd = pmd_offset(pud, vaddr); + if (pmd_none(*pmd)) { + BUG(); + return; + } + pte = pte_offset_kernel(pmd, vaddr); + /* <pfn,flags> stored as-is, to permit clearing entries */ + set_pte(pte, pfn_pte_ma(pfn, flags)); + + /* + * It's enough to flush this one mapping. + * (PGE mappings get flushed as well) + */ + __flush_tlb_one(vaddr); +} + +/* + * Associate a large virtual page frame with a given physical page frame + * and protection flags for that frame. pfn is for the base of the page, + * vaddr is what the page gets mapped to - both must be properly aligned. + * The pmd must already be instantiated. Assumes PAE mode. + */ +void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + + if (vaddr & (PMD_SIZE-1)) { /* vaddr is misaligned */ + printk ("set_pmd_pfn: vaddr misaligned\n"); + return; /* BUG(); */ + } + if (pfn & (PTRS_PER_PTE-1)) { /* pfn is misaligned */ + printk ("set_pmd_pfn: pfn misaligned\n"); + return; /* BUG(); */ + } + pgd = swapper_pg_dir + pgd_index(vaddr); + if (pgd_none(*pgd)) { + printk ("set_pmd_pfn: pgd_none\n"); + return; /* BUG(); */ + } + pud = pud_offset(pgd, vaddr); + pmd = pmd_offset(pud, vaddr); + set_pmd(pmd, pfn_pmd(pfn, flags)); + /* + * It's enough to flush this one mapping. + * (PGE mappings get flushed as well) + */ + __flush_tlb_one(vaddr); +} + +void __set_fixmap (enum fixed_addresses idx, maddr_t phys, pgprot_t flags) +{ + unsigned long address = __fix_to_virt(idx); + + if (idx >= __end_of_fixed_addresses) { + BUG(); + return; + } + switch (idx) { + case FIX_WP_TEST: + case FIX_VSYSCALL: +#ifdef CONFIG_X86_F00F_BUG + case FIX_F00F_IDT: +#endif + set_pte_pfn(address, phys >> PAGE_SHIFT, flags); + break; + default: + set_pte_pfn_ma(address, phys >> PAGE_SHIFT, flags); + break; + } +} + +pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) +{ + pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); + if (pte) + make_lowmem_page_readonly(pte, XENFEAT_writable_page_tables); + return pte; +} + +struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address) +{ + struct page *pte; + +#ifdef CONFIG_HIGHPTE + pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT|__GFP_ZERO, 0); +#else + pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0); + if (pte) { + SetPageForeign(pte, pte_free); + set_page_count(pte, 1); + } +#endif + + return pte; +} + +void pte_free(struct page *pte) +{ + unsigned long va = (unsigned long)__va(page_to_pfn(pte)<<PAGE_SHIFT); + + if (!pte_write(*virt_to_ptep(va))) + BUG_ON(HYPERVISOR_update_va_mapping( + va, pfn_pte(page_to_pfn(pte), PAGE_KERNEL), 0)); + + ClearPageForeign(pte); + set_page_count(pte, 1); + + __free_page(pte); +} + +void pmd_ctor(void *pmd, kmem_cache_t *cache, unsigned long flags) +{ + memset(pmd, 0, PTRS_PER_PMD*sizeof(pmd_t)); +} + +/* + * List of all pgd's needed for non-PAE so it can invalidate entries + * in both cached and uncached pgd's; not needed for PAE since the + * kernel pmd is shared. If PAE were not to share the pmd a similar + * tactic would be needed. This is essentially codepath-based locking + * against pageattr.c; it is the unique case in which a valid change + * of kernel pagetables can't be lazily synchronized by vmalloc faults. + * vmalloc faults work because attached pagetables are never freed. + * The locking scheme was chosen on the basis of manfred's + * recommendations and having no core impact whatsoever. + * -- wli + */ +DEFINE_SPINLOCK(pgd_lock); +struct page *pgd_list; + +static inline void pgd_list_add(pgd_t *pgd) +{ + struct page *page = virt_to_page(pgd); + page->index = (unsigned long)pgd_list; + if (pgd_list) + pgd_list->private = (unsigned long)&page->index; + pgd_list = page; + page->private = (unsigned long)&pgd_list; +} + +static inline void pgd_list_del(pgd_t *pgd) +{ + struct page *next, **pprev, *page = virt_to_page(pgd); + next = (struct page *)page->index; + pprev = (struct page **)page->private; + *pprev = next; + if (next) + next->private = (unsigned long)pprev; +} + +void pgd_ctor(void *pgd, kmem_cache_t *cache, unsigned long unused) +{ + unsigned long flags; + + if (PTRS_PER_PMD > 1) { + /* Ensure pgd resides below 4GB. */ + int rc = xen_create_contiguous_region( + (unsigned long)pgd, 0, 32); + BUG_ON(rc); + if (HAVE_SHARED_KERNEL_PMD) + memcpy((pgd_t *)pgd + USER_PTRS_PER_PGD, + swapper_pg_dir + USER_PTRS_PER_PGD, + (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t)); + } else { + spin_lock_irqsave(&pgd_lock, flags); + memcpy((pgd_t *)pgd + USER_PTRS_PER_PGD, + swapper_pg_dir + USER_PTRS_PER_PGD, + (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t)); + memset(pgd, 0, USER_PTRS_PER_PGD*sizeof(pgd_t)); + pgd_list_add(pgd); + spin_unlock_irqrestore(&pgd_lock, flags); + } +} + +/* never called when PTRS_PER_PMD > 1 */ +void pgd_dtor(void *pgd, kmem_cache_t *cache, unsigned long unused) +{ + unsigned long flags; /* can be called from interrupt context */ + + spin_lock_irqsave(&pgd_lock, flags); + pgd_list_del(pgd); + spin_unlock_irqrestore(&pgd_lock, flags); + + pgd_test_and_unpin(pgd); +} + +pgd_t *pgd_alloc(struct mm_struct *mm) +{ + int i; + pgd_t *pgd = kmem_cache_alloc(pgd_cache, GFP_KERNEL); + + pgd_test_and_unpin(pgd); + + if (PTRS_PER_PMD == 1 || !pgd) + return pgd; + + for (i = 0; i < USER_PTRS_PER_PGD; ++i) { + pmd_t *pmd = kmem_cache_alloc(pmd_cache, GFP_KERNEL); + if (!pmd) + goto out_oom; + set_pgd(&pgd[i], __pgd(1 + __pa(pmd))); + } + + if (!HAVE_SHARED_KERNEL_PMD) { + unsigned long flags; + + for (i = USER_PTRS_PER_PGD; i < PTRS_PER_PGD; i++) { + pmd_t *pmd = kmem_cache_alloc(pmd_cache, GFP_KERNEL); + if (!pmd) + goto out_oom; + set_pgd(&pgd[USER_PTRS_PER_PGD], __pgd(1 + __pa(pmd))); + } + + spin_lock_irqsave(&pgd_lock, flags); + for (i = USER_PTRS_PER_PGD; i < PTRS_PER_PGD; i++) { + unsigned long v = (unsigned long)i << PGDIR_SHIFT; + pgd_t *kpgd = pgd_offset_k(v); + pud_t *kpud = pud_offset(kpgd, v); + pmd_t *kpmd = pmd_offset(kpud, v); + pmd_t *pmd = (void *)__va(pgd_val(pgd[i])-1); + memcpy(pmd, kpmd, PAGE_SIZE); + make_lowmem_page_readonly( + pmd, XENFEAT_writable_page_tables); + } + pgd_list_add(pgd); + spin_unlock_irqrestore(&pgd_lock, flags); + } + + return pgd; + +out_oom: + for (i--; i >= 0; i--) + kmem_cache_free(pmd_cache, (void *)__va(pgd_val(pgd[i])-1)); + kmem_cache_free(pgd_cache, pgd); + return NULL; +} + +void pgd_free(pgd_t *pgd) +{ + int i; + + pgd_test_and_unpin(pgd); + + /* in the PAE case user pgd entries are overwritten before usage */ + if (PTRS_PER_PMD > 1) { + for (i = 0; i < USER_PTRS_PER_PGD; ++i) { + pmd_t *pmd = (void *)__va(pgd_val(pgd[i])-1); + kmem_cache_free(pmd_cache, pmd); + } + if (!HAVE_SHARED_KERNEL_PMD) { + unsigned long flags; + spin_lock_irqsave(&pgd_lock, flags); + pgd_list_del(pgd); + spin_unlock_irqrestore(&pgd_lock, flags); + for (i = USER_PTRS_PER_PGD; i < PTRS_PER_PGD; i++) { + pmd_t *pmd = (void *)__va(pgd_val(pgd[i])-1); + make_lowmem_page_writable( + pmd, XENFEAT_writable_page_tables); + memset(pmd, 0, PTRS_PER_PMD*sizeof(pmd_t)); + kmem_cache_free(pmd_cache, pmd); + } + } + } + /* in the non-PAE case, free_pgtables() clears user pgd entries */ + kmem_cache_free(pgd_cache, pgd); +} + +#ifndef CONFIG_XEN_SHADOW_MODE +void make_lowmem_page_readonly(void *va, unsigned int feature) +{ + pte_t *pte; + int rc; + + if (xen_feature(feature)) + return; + + pte = virt_to_ptep(va); + rc = HYPERVISOR_update_va_mapping( + (unsigned long)va, pte_wrprotect(*pte), 0); + BUG_ON(rc); +} + +void make_lowmem_page_writable(void *va, unsigned int feature) +{ + pte_t *pte; + int rc; + + if (xen_feature(feature)) + return; + + pte = virt_to_ptep(va); + rc = HYPERVISOR_update_va_mapping( + (unsigned long)va, pte_mkwrite(*pte), 0); + BUG_ON(rc); +} + +void make_page_readonly(void *va, unsigned int feature) +{ + pte_t *pte; + int rc; + + if (xen_feature(feature)) + return; + + pte = virt_to_ptep(va); + rc = HYPERVISOR_update_va_mapping( + (unsigned long)va, pte_wrprotect(*pte), 0); + if (rc) /* fallback? */ + xen_l1_entry_update(pte, pte_wrprotect(*pte)); + if ((unsigned long)va >= (unsigned long)high_memory) { + unsigned long pfn = pte_pfn(*pte); +#ifdef CONFIG_HIGHMEM + if (pfn >= highstart_pfn) + kmap_flush_unused(); /* flush stale writable kmaps */ + else +#endif + make_lowmem_page_readonly( + phys_to_virt(pfn << PAGE_SHIFT), feature); + } +} + +void make_page_writable(void *va, unsigned int feature) +{ + pte_t *pte; + int rc; + + if (xen_feature(feature)) + return; + + pte = virt_to_ptep(va); + rc = HYPERVISOR_update_va_mapping( + (unsigned long)va, pte_mkwrite(*pte), 0); + if (rc) /* fallback? */ + xen_l1_entry_update(pte, pte_mkwrite(*pte)); + if ((unsigned long)va >= (unsigned long)high_memory) { + unsigned long pfn = pte_pfn(*pte); +#ifdef CONFIG_HIGHMEM + if (pfn < highstart_pfn) +#endif + make_lowmem_page_writable( + phys_to_virt(pfn << PAGE_SHIFT), feature); + } +} + +void make_pages_readonly(void *va, unsigned int nr, unsigned int feature) +{ + if (xen_feature(feature)) + return; + + while (nr-- != 0) { + make_page_readonly(va, feature); + va = (void *)((unsigned long)va + PAGE_SIZE); + } +} + +void make_pages_writable(void *va, unsigned int nr, unsigned int feature) +{ + if (xen_feature(feature)) + return; + + while (nr-- != 0) { + make_page_writable(va, feature); + va = (void *)((unsigned long)va + PAGE_SIZE); + } +} +#endif /* CONFIG_XEN_SHADOW_MODE */ + +static inline void pgd_walk_set_prot(void *pt, pgprot_t flags) +{ + struct page *page = virt_to_page(pt); + unsigned long pfn = page_to_pfn(page); + + if (PageHighMem(page)) + return; + BUG_ON(HYPERVISOR_update_va_mapping( + (unsigned long)__va(pfn << PAGE_SHIFT), + pfn_pte(pfn, flags), 0)); +} + +static void pgd_walk(pgd_t *pgd_base, pgprot_t flags) +{ + pgd_t *pgd = pgd_base; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + int g, u, m; + + for (g = 0; g < USER_PTRS_PER_PGD; g++, pgd++) { + if (pgd_none(*pgd)) + continue; + pud = pud_offset(pgd, 0); + if (PTRS_PER_PUD > 1) /* not folded */ + pgd_walk_set_prot(pud,flags); + for (u = 0; u < PTRS_PER_PUD; u++, pud++) { + if (pud_none(*pud)) + continue; + pmd = pmd_offset(pud, 0); + if (PTRS_PER_PMD > 1) /* not folded */ + pgd_walk_set_prot(pmd,flags); + for (m = 0; m < PTRS_PER_PMD; m++, pmd++) { + if (pmd_none(*pmd)) + continue; + pte = pte_offset_kernel(pmd,0); + pgd_walk_set_prot(pte,flags); + } + } + } + + BUG_ON(HYPERVISOR_update_va_mapping( + (unsigned long)pgd_base, + pfn_pte(virt_to_phys(pgd_base)>>PAGE_SHIFT, flags), + UVMF_TLB_FLUSH)); +} + +static void __pgd_pin(pgd_t *pgd) +{ + pgd_walk(pgd, PAGE_KERNEL_RO); + xen_pgd_pin(__pa(pgd)); + set_bit(PG_pinned, &virt_to_page(pgd)->flags); +} + +static void __pgd_unpin(pgd_t *pgd) +{ + xen_pgd_unpin(__pa(pgd)); + pgd_walk(pgd, PAGE_KERNEL); + clear_bit(PG_pinned, &virt_to_page(pgd)->flags); +} + +static void pgd_test_and_unpin(pgd_t *pgd) +{ + if (test_bit(PG_pinned, &virt_to_page(pgd)->flags)) + __pgd_unpin(pgd); +} + +void mm_pin(struct mm_struct *mm) +{ + spin_lock(&mm->page_table_lock); + __pgd_pin(mm->pgd); + spin_unlock(&mm->page_table_lock); +} + +void mm_unpin(struct mm_struct *mm) +{ + spin_lock(&mm->page_table_lock); + __pgd_unpin(mm->pgd); + spin_unlock(&mm->page_table_lock); +} + +void mm_pin_all(void) +{ + struct page *page; + for (page = pgd_list; page; page = (struct page *)page->index) { + if (!test_bit(PG_pinned, &page->flags)) + __pgd_pin((pgd_t *)page_address(page)); + } +} + +void _arch_exit_mmap(struct mm_struct *mm) +{ + struct task_struct *tsk = current; + + task_lock(tsk); + + /* + * We aggressively remove defunct pgd from cr3. We execute unmap_vmas() + * *much* faster this way, as no tlb flushes means bigger wrpt batches. + */ + if (tsk->active_mm == mm) { + tsk->active_mm = &init_mm; + atomic_inc(&init_mm.mm_count); + + switch_mm(mm, &init_mm, tsk); + + atomic_dec(&mm->mm_count); + BUG_ON(atomic_read(&mm->mm_count) == 0); + } + + task_unlock(tsk); + + if (test_bit(PG_pinned, &virt_to_page(mm->pgd)->flags) && + (atomic_read(&mm->mm_count) == 1)) + mm_unpin(mm); +} + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/pci/Makefile --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/pci/Makefile Mon Jan 30 17:18:27 2006 @@ -0,0 +1,19 @@ +obj-y := i386.o + +obj-$(CONFIG_PCI_BIOS) += pcbios.o +obj-$(CONFIG_PCI_MMCONFIG) += mmconfig.o +obj-$(CONFIG_PCI_DIRECT) += direct.o + +pci-y := fixup.o +pci-$(CONFIG_ACPI_PCI) += acpi.o +pci-y += legacy.o irq.o + +pci-$(CONFIG_X86_VISWS) := visws.o fixup.o +pci-$(CONFIG_X86_NUMAQ) := numa.o irq.o + +obj-y += $(pci-y) common.o + +ifdef CONFIG_XEN +include $(srctree)/scripts/Makefile.xen +obj-y := $(call cherrypickxen, $(obj-y)) +endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/pci/i386-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/pci/i386-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,304 @@ +/* + * Low-Level PCI Access for i386 machines + * + * Copyright 1993, 1994 Drew Eckhardt + * Visionary Computing + * (Unix and Linux consulting and custom programming) + * Drew@xxxxxxxxxxxx + * +1 (303) 786-7975 + * + * Drew's work was sponsored by: + * iX Multiuser Multitasking Magazine + * Hannover, Germany + * hm@xxxxx + * + * Copyright 1997--2000 Martin Mares <mj@xxxxxx> + * + * For more information, please consult the following manuals (look at + * http://www.pcisig.com/ for how to get them): + * + * PCI BIOS Specification + * PCI Local Bus Specification + * PCI to PCI Bridge Specification + * PCI System Design Guide + * + */ + +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/init.h> +#include <linux/ioport.h> +#include <linux/errno.h> + +#include "pci.h" + +/* + * We need to avoid collisions with `mirrored' VGA ports + * and other strange ISA hardware, so we always want the + * addresses to be allocated in the 0x000-0x0ff region + * modulo 0x400. + * + * Why? Because some silly external IO cards only decode + * the low 10 bits of the IO address. The 0x00-0xff region + * is reserved for motherboard devices that decode all 16 + * bits, so it's ok to allocate at, say, 0x2800-0x28ff, + * but we want to try to avoid allocating at 0x2900-0x2bff + * which might have be mirrored at 0x0100-0x03ff.. + */ +void +pcibios_align_resource(void *data, struct resource *res, + unsigned long size, unsigned long align) +{ + if (res->flags & IORESOURCE_IO) { + unsigned long start = res->start; + + if (start & 0x300) { + start = (start + 0x3ff) & ~0x3ff; + res->start = start; + } + } +} + + +/* + * Handle resources of PCI devices. If the world were perfect, we could + * just allocate all the resource regions and do nothing more. It isn't. + * On the other hand, we cannot just re-allocate all devices, as it would + * require us to know lots of host bridge internals. So we attempt to + * keep as much of the original configuration as possible, but tweak it + * when it's found to be wrong. + * + * Known BIOS problems we have to work around: + * - I/O or memory regions not configured + * - regions configured, but not enabled in the command register + * - bogus I/O addresses above 64K used + * - expansion ROMs left enabled (this may sound harmless, but given + * the fact the PCI specs explicitly allow address decoders to be + * shared between expansion ROMs and other resource regions, it's + * at least dangerous) + * + * Our solution: + * (1) Allocate resources for all buses behind PCI-to-PCI bridges. + * This gives us fixed barriers on where we can allocate. + * (2) Allocate resources for all enabled devices. If there is + * a collision, just mark the resource as unallocated. Also + * disable expansion ROMs during this step. + * (3) Try to allocate resources for disabled devices. If the + * resources were assigned correctly, everything goes well, + * if they weren't, they won't disturb allocation of other + * resources. + * (4) Assign new addresses to resources which were either + * not configured at all or misconfigured. If explicitly + * requested by the user, configure expansion ROM address + * as well. + */ + +static void __init pcibios_allocate_bus_resources(struct list_head *bus_list) +{ + struct pci_bus *bus; + struct pci_dev *dev; + int idx; + struct resource *r, *pr; + + /* Depth-First Search on bus tree */ + list_for_each_entry(bus, bus_list, node) { + if ((dev = bus->self)) { + for (idx = PCI_BRIDGE_RESOURCES; idx < PCI_NUM_RESOURCES; idx++) { + r = &dev->resource[idx]; + if (!r->start) + continue; + pr = pci_find_parent_resource(dev, r); + if (!pr || request_resource(pr, r) < 0) + printk(KERN_ERR "PCI: Cannot allocate resource region %d of bridge %s\n", idx, pci_name(dev)); + } + } + pcibios_allocate_bus_resources(&bus->children); + } +} + +static void __init pcibios_allocate_resources(int pass) +{ + struct pci_dev *dev = NULL; + int idx, disabled; + u16 command; + struct resource *r, *pr; + + for_each_pci_dev(dev) { + pci_read_config_word(dev, PCI_COMMAND, &command); + for(idx = 0; idx < 6; idx++) { + r = &dev->resource[idx]; + if (r->parent) /* Already allocated */ + continue; + if (!r->start) /* Address not assigned at all */ + continue; + if (r->flags & IORESOURCE_IO) + disabled = !(command & PCI_COMMAND_IO); + else + disabled = !(command & PCI_COMMAND_MEMORY); + if (pass == disabled) { + DBG("PCI: Resource %08lx-%08lx (f=%lx, d=%d, p=%d)\n", + r->start, r->end, r->flags, disabled, pass); + pr = pci_find_parent_resource(dev, r); + if (!pr || request_resource(pr, r) < 0) { + printk(KERN_ERR "PCI: Cannot allocate resource region %d of device %s\n", idx, pci_name(dev)); + /* We'll assign a new address later */ + r->end -= r->start; + r->start = 0; + } + } + } + if (!pass) { + r = &dev->resource[PCI_ROM_RESOURCE]; + if (r->flags & IORESOURCE_ROM_ENABLE) { + /* Turn the ROM off, leave the resource region, but keep it unregistered. */ + u32 reg; + DBG("PCI: Switching off ROM of %s\n", pci_name(dev)); + r->flags &= ~IORESOURCE_ROM_ENABLE; + pci_read_config_dword(dev, dev->rom_base_reg, &reg); + pci_write_config_dword(dev, dev->rom_base_reg, reg & ~PCI_ROM_ADDRESS_ENABLE); + } + } + } +} + +static int __init pcibios_assign_resources(void) +{ + struct pci_dev *dev = NULL; + int idx; + struct resource *r; + + for_each_pci_dev(dev) { + int class = dev->class >> 8; + + /* Don't touch classless devices and host bridges */ + if (!class || class == PCI_CLASS_BRIDGE_HOST) + continue; + + for(idx=0; idx<6; idx++) { + r = &dev->resource[idx]; + + /* + * Don't touch IDE controllers and I/O ports of video cards! + */ + if ((class == PCI_CLASS_STORAGE_IDE && idx < 4) || + (class == PCI_CLASS_DISPLAY_VGA && (r->flags & IORESOURCE_IO))) + continue; + + /* + * We shall assign a new address to this resource, either because + * the BIOS forgot to do so or because we have decided the old + * address was unusable for some reason. + */ + if (!r->start && r->end) + pci_assign_resource(dev, idx); + } + + if (pci_probe & PCI_ASSIGN_ROMS) { + r = &dev->resource[PCI_ROM_RESOURCE]; + r->end -= r->start; + r->start = 0; + if (r->end) + pci_assign_resource(dev, PCI_ROM_RESOURCE); + } + } + return 0; +} + +void __init pcibios_resource_survey(void) +{ + DBG("PCI: Allocating resources\n"); + pcibios_allocate_bus_resources(&pci_root_buses); + pcibios_allocate_resources(0); + pcibios_allocate_resources(1); +} + +/** + * called in fs_initcall (one below subsys_initcall), + * give a chance for motherboard reserve resources + */ +fs_initcall(pcibios_assign_resources); + +int pcibios_enable_resources(struct pci_dev *dev, int mask) +{ + u16 cmd, old_cmd; + int idx; + struct resource *r; + + pci_read_config_word(dev, PCI_COMMAND, &cmd); + old_cmd = cmd; + for(idx=0; idx<6; idx++) { + /* Only set up the requested stuff */ + if (!(mask & (1<<idx))) + continue; + + r = &dev->resource[idx]; + if (!r->start && r->end) { + printk(KERN_ERR "PCI: Device %s not available because of resource collisions\n", pci_name(dev)); + return -EINVAL; + } + if (r->flags & IORESOURCE_IO) + cmd |= PCI_COMMAND_IO; + if (r->flags & IORESOURCE_MEM) + cmd |= PCI_COMMAND_MEMORY; + } + if (dev->resource[PCI_ROM_RESOURCE].start) + cmd |= PCI_COMMAND_MEMORY; + if (cmd != old_cmd) { + printk("PCI: Enabling device %s (%04x -> %04x)\n", pci_name(dev), old_cmd, cmd); + pci_write_config_word(dev, PCI_COMMAND, cmd); + } + return 0; +} + +/* + * If we set up a device for bus mastering, we need to check the latency + * timer as certain crappy BIOSes forget to set it properly. + */ +unsigned int pcibios_max_latency = 255; + +void pcibios_set_master(struct pci_dev *dev) +{ + u8 lat; + pci_read_config_byte(dev, PCI_LATENCY_TIMER, &lat); + if (lat < 16) + lat = (64 <= pcibios_max_latency) ? 64 : pcibios_max_latency; + else if (lat > pcibios_max_latency) + lat = pcibios_max_latency; + else + return; + printk(KERN_DEBUG "PCI: Setting latency timer of device %s to %d\n", pci_name(dev), lat); + pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat); +} + +int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, + enum pci_mmap_state mmap_state, int write_combine) +{ + unsigned long prot; + + /* I/O space cannot be accessed via normal processor loads and + * stores on this platform. + */ + if (mmap_state == pci_mmap_io) + return -EINVAL; + + /* Leave vm_pgoff as-is, the PCI space address is the physical + * address on this platform. + */ + vma->vm_flags |= (VM_SHM | VM_LOCKED | VM_IO); + + prot = pgprot_val(vma->vm_page_prot); + if (boot_cpu_data.x86 > 3) + prot |= _PAGE_PCD | _PAGE_PWT; + vma->vm_page_prot = __pgprot(prot); + + /* Write-combine setting is ignored, it is changed via the mtrr + * interfaces on this platform. + */ + if (direct_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, + vma->vm_end - vma->vm_start, + vma->vm_page_prot, DOMID_IO)) + return -EAGAIN; + + return 0; +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/i386/pci/irq-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/i386/pci/irq-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,1120 @@ +/* + * Low-Level PCI Support for PC -- Routing of Interrupts + * + * (c) 1999--2000 Martin Mares <mj@xxxxxx> + */ + +#include <linux/config.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/dmi.h> +#include <asm/io.h> +#include <asm/smp.h> +#include <asm/io_apic.h> +#include <asm/hw_irq.h> +#include <linux/acpi.h> + +#include "pci.h" + +#define PIRQ_SIGNATURE (('$' << 0) + ('P' << 8) + ('I' << 16) + ('R' << 24)) +#define PIRQ_VERSION 0x0100 + +static int broken_hp_bios_irq9; +static int acer_tm360_irqrouting; + +static struct irq_routing_table *pirq_table; + +static int pirq_enable_irq(struct pci_dev *dev); + +/* + * Never use: 0, 1, 2 (timer, keyboard, and cascade) + * Avoid using: 13, 14 and 15 (FP error and IDE). + * Penalize: 3, 4, 6, 7, 12 (known ISA uses: serial, floppy, parallel and mouse) + */ +unsigned int pcibios_irq_mask = 0xfff8; + +static int pirq_penalty[16] = { + 1000000, 1000000, 1000000, 1000, 1000, 0, 1000, 1000, + 0, 0, 0, 0, 1000, 100000, 100000, 100000 +}; + +struct irq_router { + char *name; + u16 vendor, device; + int (*get)(struct pci_dev *router, struct pci_dev *dev, int pirq); + int (*set)(struct pci_dev *router, struct pci_dev *dev, int pirq, int new); +}; + +struct irq_router_handler { + u16 vendor; + int (*probe)(struct irq_router *r, struct pci_dev *router, u16 device); +}; + +int (*pcibios_enable_irq)(struct pci_dev *dev) = NULL; + +/* + * Search 0xf0000 -- 0xfffff for the PCI IRQ Routing Table. + */ + +static struct irq_routing_table * __init pirq_find_routing_table(void) +{ + u8 *addr; + struct irq_routing_table *rt; + int i; + u8 sum; + +#ifdef CONFIG_XEN_PRIVILEGED_GUEST + for(addr = (u8 *) isa_bus_to_virt(0xf0000); addr < (u8 *) isa_bus_to_virt(0x100000); addr += 16) { + rt = (struct irq_routing_table *) addr; + if (rt->signature != PIRQ_SIGNATURE || + rt->version != PIRQ_VERSION || + rt->size % 16 || + rt->size < sizeof(struct irq_routing_table)) + continue; + sum = 0; + for(i=0; i<rt->size; i++) + sum += addr[i]; + if (!sum) { + DBG("PCI: Interrupt Routing Table found at 0x%p\n", rt); + return rt; + } + } +#endif + + return NULL; +} + +/* + * If we have a IRQ routing table, use it to search for peer host + * bridges. It's a gross hack, but since there are no other known + * ways how to get a list of buses, we have to go this way. + */ + +static void __init pirq_peer_trick(void) +{ + struct irq_routing_table *rt = pirq_table; + u8 busmap[256]; + int i; + struct irq_info *e; + + memset(busmap, 0, sizeof(busmap)); + for(i=0; i < (rt->size - sizeof(struct irq_routing_table)) / sizeof(struct irq_info); i++) { + e = &rt->slots[i]; +#ifdef DEBUG + { + int j; + DBG("%02x:%02x slot=%02x", e->bus, e->devfn/8, e->slot); + for(j=0; j<4; j++) + DBG(" %d:%02x/%04x", j, e->irq[j].link, e->irq[j].bitmap); + DBG("\n"); + } +#endif + busmap[e->bus] = 1; + } + for(i = 1; i < 256; i++) { + if (!busmap[i] || pci_find_bus(0, i)) + continue; + if (pci_scan_bus(i, &pci_root_ops, NULL)) + printk(KERN_INFO "PCI: Discovered primary peer bus %02x [IRQ]\n", i); + } + pcibios_last_bus = -1; +} + +/* + * Code for querying and setting of IRQ routes on various interrupt routers. + */ + +void eisa_set_level_irq(unsigned int irq) +{ + unsigned char mask = 1 << (irq & 7); + unsigned int port = 0x4d0 + (irq >> 3); + unsigned char val; + static u16 eisa_irq_mask; + + if (irq >= 16 || (1 << irq) & eisa_irq_mask) + return; + + eisa_irq_mask |= (1 << irq); + printk("PCI: setting IRQ %u as level-triggered\n", irq); + val = inb(port); + if (!(val & mask)) { + DBG(" -> edge"); + outb(val | mask, port); + } +} + +/* + * Common IRQ routing practice: nybbles in config space, + * offset by some magic constant. + */ +static unsigned int read_config_nybble(struct pci_dev *router, unsigned offset, unsigned nr) +{ + u8 x; + unsigned reg = offset + (nr >> 1); + + pci_read_config_byte(router, reg, &x); + return (nr & 1) ? (x >> 4) : (x & 0xf); +} + +static void write_config_nybble(struct pci_dev *router, unsigned offset, unsigned nr, unsigned int val) +{ + u8 x; + unsigned reg = offset + (nr >> 1); + + pci_read_config_byte(router, reg, &x); + x = (nr & 1) ? ((x & 0x0f) | (val << 4)) : ((x & 0xf0) | val); + pci_write_config_byte(router, reg, x); +} + +/* + * ALI pirq entries are damn ugly, and completely undocumented. + * This has been figured out from pirq tables, and it's not a pretty + * picture. + */ +static int pirq_ali_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +{ + static unsigned char irqmap[16] = { 0, 9, 3, 10, 4, 5, 7, 6, 1, 11, 0, 12, 0, 14, 0, 15 }; + + return irqmap[read_config_nybble(router, 0x48, pirq-1)]; +} + +static int pirq_ali_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +{ + static unsigned char irqmap[16] = { 0, 8, 0, 2, 4, 5, 7, 6, 0, 1, 3, 9, 11, 0, 13, 15 }; + unsigned int val = irqmap[irq]; + + if (val) { + write_config_nybble(router, 0x48, pirq-1, val); + return 1; + } + return 0; +} + +/* + * The Intel PIIX4 pirq rules are fairly simple: "pirq" is + * just a pointer to the config space. + */ +static int pirq_piix_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +{ + u8 x; + + pci_read_config_byte(router, pirq, &x); + return (x < 16) ? x : 0; +} + +static int pirq_piix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +{ + pci_write_config_byte(router, pirq, irq); + return 1; +} + +/* + * The VIA pirq rules are nibble-based, like ALI, + * but without the ugly irq number munging. + * However, PIRQD is in the upper instead of lower 4 bits. + */ +static int pirq_via_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +{ + return read_config_nybble(router, 0x55, pirq == 4 ? 5 : pirq); +} + +static int pirq_via_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +{ + write_config_nybble(router, 0x55, pirq == 4 ? 5 : pirq, irq); + return 1; +} + +/* + * ITE 8330G pirq rules are nibble-based + * FIXME: pirqmap may be { 1, 0, 3, 2 }, + * 2+3 are both mapped to irq 9 on my system + */ +static int pirq_ite_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +{ + static unsigned char pirqmap[4] = { 1, 0, 2, 3 }; + return read_config_nybble(router,0x43, pirqmap[pirq-1]); +} + +static int pirq_ite_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +{ + static unsigned char pirqmap[4] = { 1, 0, 2, 3 }; + write_config_nybble(router, 0x43, pirqmap[pirq-1], irq); + return 1; +} + +/* + * OPTI: high four bits are nibble pointer.. + * I wonder what the low bits do? + */ +static int pirq_opti_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +{ + return read_config_nybble(router, 0xb8, pirq >> 4); +} + +static int pirq_opti_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +{ + write_config_nybble(router, 0xb8, pirq >> 4, irq); + return 1; +} + +/* + * Cyrix: nibble offset 0x5C + * 0x5C bits 7:4 is INTB bits 3:0 is INTA + * 0x5D bits 7:4 is INTD bits 3:0 is INTC + */ +static int pirq_cyrix_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +{ + return read_config_nybble(router, 0x5C, (pirq-1)^1); +} + +static int pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +{ + write_config_nybble(router, 0x5C, (pirq-1)^1, irq); + return 1; +} + +/* + * PIRQ routing for SiS 85C503 router used in several SiS chipsets. + * We have to deal with the following issues here: + * - vendors have different ideas about the meaning of link values + * - some onboard devices (integrated in the chipset) have special + * links and are thus routed differently (i.e. not via PCI INTA-INTD) + * - different revision of the router have a different layout for + * the routing registers, particularly for the onchip devices + * + * For all routing registers the common thing is we have one byte + * per routeable link which is defined as: + * bit 7 IRQ mapping enabled (0) or disabled (1) + * bits [6:4] reserved (sometimes used for onchip devices) + * bits [3:0] IRQ to map to + * allowed: 3-7, 9-12, 14-15 + * reserved: 0, 1, 2, 8, 13 + * + * The config-space registers located at 0x41/0x42/0x43/0x44 are + * always used to route the normal PCI INT A/B/C/D respectively. + * Apparently there are systems implementing PCI routing table using + * link values 0x01-0x04 and others using 0x41-0x44 for PCI INTA..D. + * We try our best to handle both link mappings. + * + * Currently (2003-05-21) it appears most SiS chipsets follow the + * definition of routing registers from the SiS-5595 southbridge. + * According to the SiS 5595 datasheets the revision id's of the + * router (ISA-bridge) should be 0x01 or 0xb0. + * + * Furthermore we've also seen lspci dumps with revision 0x00 and 0xb1. + * Looks like these are used in a number of SiS 5xx/6xx/7xx chipsets. + * They seem to work with the current routing code. However there is + * some concern because of the two USB-OHCI HCs (original SiS 5595 + * had only one). YMMV. + * + * Onchip routing for router rev-id 0x01/0xb0 and probably 0x00/0xb1: + * + * 0x61: IDEIRQ: + * bits [6:5] must be written 01 + * bit 4 channel-select primary (0), secondary (1) + * + * 0x62: USBIRQ: + * bit 6 OHCI function disabled (0), enabled (1) + * + * 0x6a: ACPI/SCI IRQ: bits 4-6 reserved + * + * 0x7e: Data Acq. Module IRQ - bits 4-6 reserved + * + * We support USBIRQ (in addition to INTA-INTD) and keep the + * IDE, ACPI and DAQ routing untouched as set by the BIOS. + * + * Currently the only reported exception is the new SiS 65x chipset + * which includes the SiS 69x southbridge. Here we have the 85C503 + * router revision 0x04 and there are changes in the register layout + * mostly related to the different USB HCs with USB 2.0 support. + * + * Onchip routing for router rev-id 0x04 (try-and-error observation) + * + * 0x60/0x61/0x62/0x63: 1xEHCI and 3xOHCI (companion) USB-HCs + * bit 6-4 are probably unused, not like 5595 + */ + +#define PIRQ_SIS_IRQ_MASK 0x0f +#define PIRQ_SIS_IRQ_DISABLE 0x80 +#define PIRQ_SIS_USB_ENABLE 0x40 + +static int pirq_sis_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +{ + u8 x; + int reg; + + reg = pirq; + if (reg >= 0x01 && reg <= 0x04) + reg += 0x40; + pci_read_config_byte(router, reg, &x); + return (x & PIRQ_SIS_IRQ_DISABLE) ? 0 : (x & PIRQ_SIS_IRQ_MASK); +} + +static int pirq_sis_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +{ + u8 x; + int reg; + + reg = pirq; + if (reg >= 0x01 && reg <= 0x04) + reg += 0x40; + pci_read_config_byte(router, reg, &x); + x &= ~(PIRQ_SIS_IRQ_MASK | PIRQ_SIS_IRQ_DISABLE); + x |= irq ? irq: PIRQ_SIS_IRQ_DISABLE; + pci_write_config_byte(router, reg, x); + return 1; +} + + +/* + * VLSI: nibble offset 0x74 - educated guess due to routing table and + * config space of VLSI 82C534 PCI-bridge/router (1004:0102) + * Tested on HP OmniBook 800 covering PIRQ 1, 2, 4, 8 for onboard + * devices, PIRQ 3 for non-pci(!) soundchip and (untested) PIRQ 6 + * for the busbridge to the docking station. + */ + +static int pirq_vlsi_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +{ + if (pirq > 8) { + printk(KERN_INFO "VLSI router pirq escape (%d)\n", pirq); + return 0; + } + return read_config_nybble(router, 0x74, pirq-1); +} + +static int pirq_vlsi_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +{ + if (pirq > 8) { + printk(KERN_INFO "VLSI router pirq escape (%d)\n", pirq); + return 0; + } + write_config_nybble(router, 0x74, pirq-1, irq); + return 1; +} + +/* + * ServerWorks: PCI interrupts mapped to system IRQ lines through Index + * and Redirect I/O registers (0x0c00 and 0x0c01). The Index register + * format is (PCIIRQ## | 0x10), e.g.: PCIIRQ10=0x1a. The Redirect + * register is a straight binary coding of desired PIC IRQ (low nibble). + * + * The 'link' value in the PIRQ table is already in the correct format + * for the Index register. There are some special index values: + * 0x00 for ACPI (SCI), 0x01 for USB, 0x02 for IDE0, 0x04 for IDE1, + * and 0x03 for SMBus. + */ +static int pirq_serverworks_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +{ + outb_p(pirq, 0xc00); + return inb(0xc01) & 0xf; +} + +static int pirq_serverworks_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +{ + outb_p(pirq, 0xc00); + outb_p(irq, 0xc01); + return 1; +} + +/* Support for AMD756 PCI IRQ Routing + * Jhon H. Caicedo <jhcaiced@xxxxxxxxxxx> + * Jun/21/2001 0.2.0 Release, fixed to use "nybble" functions... (jhcaiced) + * Jun/19/2001 Alpha Release 0.1.0 (jhcaiced) + * The AMD756 pirq rules are nibble-based + * offset 0x56 0-3 PIRQA 4-7 PIRQB + * offset 0x57 0-3 PIRQC 4-7 PIRQD + */ +static int pirq_amd756_get(struct pci_dev *router, struct pci_dev *dev, int pirq) +{ + u8 irq; + irq = 0; + if (pirq <= 4) + { + irq = read_config_nybble(router, 0x56, pirq - 1); + } + printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d get irq : %2d\n", + dev->vendor, dev->device, pirq, irq); + return irq; +} + +static int pirq_amd756_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +{ + printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d SET irq : %2d\n", + dev->vendor, dev->device, pirq, irq); + if (pirq <= 4) + { + write_config_nybble(router, 0x56, pirq - 1, irq); + } + return 1; +} + +#ifdef CONFIG_PCI_BIOS + +static int pirq_bios_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) +{ + struct pci_dev *bridge; + int pin = pci_get_interrupt_pin(dev, &bridge); + return pcibios_set_irq_routing(bridge, pin, irq); +} + +#endif + +static __init int intel_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +{ + static struct pci_device_id pirq_440gx[] = { + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443GX_0) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443GX_2) }, + { }, + }; + + /* 440GX has a proprietary PIRQ router -- don't use it */ + if (pci_dev_present(pirq_440gx)) + return 0; + + switch(device) + { + case PCI_DEVICE_ID_INTEL_82371FB_0: + case PCI_DEVICE_ID_INTEL_82371SB_0: + case PCI_DEVICE_ID_INTEL_82371AB_0: + case PCI_DEVICE_ID_INTEL_82371MX: + case PCI_DEVICE_ID_INTEL_82443MX_0: + case PCI_DEVICE_ID_INTEL_82801AA_0: + case PCI_DEVICE_ID_INTEL_82801AB_0: + case PCI_DEVICE_ID_INTEL_82801BA_0: + case PCI_DEVICE_ID_INTEL_82801BA_10: + case PCI_DEVICE_ID_INTEL_82801CA_0: + case PCI_DEVICE_ID_INTEL_82801CA_12: + case PCI_DEVICE_ID_INTEL_82801DB_0: + case PCI_DEVICE_ID_INTEL_82801E_0: + case PCI_DEVICE_ID_INTEL_82801EB_0: + case PCI_DEVICE_ID_INTEL_ESB_1: + case PCI_DEVICE_ID_INTEL_ICH6_0: + case PCI_DEVICE_ID_INTEL_ICH6_1: + case PCI_DEVICE_ID_INTEL_ICH7_0: + case PCI_DEVICE_ID_INTEL_ICH7_1: + case PCI_DEVICE_ID_INTEL_ICH7_30: + case PCI_DEVICE_ID_INTEL_ICH7_31: + case PCI_DEVICE_ID_INTEL_ESB2_0: + r->name = "PIIX/ICH"; + r->get = pirq_piix_get; + r->set = pirq_piix_set; + return 1; + } + return 0; +} + +static __init int via_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +{ + /* FIXME: We should move some of the quirk fixup stuff here */ + switch(device) + { + case PCI_DEVICE_ID_VIA_82C586_0: + case PCI_DEVICE_ID_VIA_82C596: + case PCI_DEVICE_ID_VIA_82C686: + case PCI_DEVICE_ID_VIA_8231: + /* FIXME: add new ones for 8233/5 */ + r->name = "VIA"; + r->get = pirq_via_get; + r->set = pirq_via_set; + return 1; + } + return 0; +} + +static __init int vlsi_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +{ + switch(device) + { + case PCI_DEVICE_ID_VLSI_82C534: + r->name = "VLSI 82C534"; + r->get = pirq_vlsi_get; + r->set = pirq_vlsi_set; + return 1; + } + return 0; +} + + +static __init int serverworks_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +{ + switch(device) + { + case PCI_DEVICE_ID_SERVERWORKS_OSB4: + case PCI_DEVICE_ID_SERVERWORKS_CSB5: + r->name = "ServerWorks"; + r->get = pirq_serverworks_get; + r->set = pirq_serverworks_set; + return 1; + } + return 0; +} + +static __init int sis_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +{ + if (device != PCI_DEVICE_ID_SI_503) + return 0; + + r->name = "SIS"; + r->get = pirq_sis_get; + r->set = pirq_sis_set; + return 1; +} + +static __init int cyrix_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +{ + switch(device) + { + case PCI_DEVICE_ID_CYRIX_5520: + r->name = "NatSemi"; + r->get = pirq_cyrix_get; + r->set = pirq_cyrix_set; + return 1; + } + return 0; +} + +static __init int opti_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +{ + switch(device) + { + case PCI_DEVICE_ID_OPTI_82C700: + r->name = "OPTI"; + r->get = pirq_opti_get; + r->set = pirq_opti_set; + return 1; + } + return 0; +} + +static __init int ite_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +{ + switch(device) + { + case PCI_DEVICE_ID_ITE_IT8330G_0: + r->name = "ITE"; + r->get = pirq_ite_get; + r->set = pirq_ite_set; + return 1; + } + return 0; +} + +static __init int ali_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +{ + switch(device) + { + case PCI_DEVICE_ID_AL_M1533: + case PCI_DEVICE_ID_AL_M1563: + printk("PCI: Using ALI IRQ Router\n"); + r->name = "ALI"; + r->get = pirq_ali_get; + r->set = pirq_ali_set; + return 1; + } + return 0; +} + +static __init int amd_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) +{ + switch(device) + { + case PCI_DEVICE_ID_AMD_VIPER_740B: + r->name = "AMD756"; + break; + case PCI_DEVICE_ID_AMD_VIPER_7413: + r->name = "AMD766"; + break; + case PCI_DEVICE_ID_AMD_VIPER_7443: + r->name = "AMD768"; + break; + default: + return 0; + } + r->get = pirq_amd756_get; + r->set = pirq_amd756_set; + return 1; +} + +static __initdata struct irq_router_handler pirq_routers[] = { + { PCI_VENDOR_ID_INTEL, intel_router_probe }, + { PCI_VENDOR_ID_AL, ali_router_probe }, + { PCI_VENDOR_ID_ITE, ite_router_probe }, + { PCI_VENDOR_ID_VIA, via_router_probe }, + { PCI_VENDOR_ID_OPTI, opti_router_probe }, + { PCI_VENDOR_ID_SI, sis_router_probe }, + { PCI_VENDOR_ID_CYRIX, cyrix_router_probe }, + { PCI_VENDOR_ID_VLSI, vlsi_router_probe }, + { PCI_VENDOR_ID_SERVERWORKS, serverworks_router_probe }, + { PCI_VENDOR_ID_AMD, amd_router_probe }, + /* Someone with docs needs to add the ATI Radeon IGP */ + { 0, NULL } +}; +static struct irq_router pirq_router; +static struct pci_dev *pirq_router_dev; + + +/* + * FIXME: should we have an option to say "generic for + * chipset" ? + */ + +static void __init pirq_find_router(struct irq_router *r) +{ + struct irq_routing_table *rt = pirq_table; + struct irq_router_handler *h; + +#ifdef CONFIG_PCI_BIOS + if (!rt->signature) { + printk(KERN_INFO "PCI: Using BIOS for IRQ routing\n"); + r->set = pirq_bios_set; + r->name = "BIOS"; + return; + } +#endif + + /* Default unless a driver reloads it */ + r->name = "default"; + r->get = NULL; + r->set = NULL; + + DBG("PCI: Attempting to find IRQ router for %04x:%04x\n", + rt->rtr_vendor, rt->rtr_device); + + pirq_router_dev = pci_find_slot(rt->rtr_bus, rt->rtr_devfn); + if (!pirq_router_dev) { + DBG("PCI: Interrupt router not found at %02x:%02x\n", rt->rtr_bus, rt->rtr_devfn); + return; + } + + for( h = pirq_routers; h->vendor; h++) { + /* First look for a router match */ + if (rt->rtr_vendor == h->vendor && h->probe(r, pirq_router_dev, rt->rtr_device)) + break; + /* Fall back to a device match */ + if (pirq_router_dev->vendor == h->vendor && h->probe(r, pirq_router_dev, pirq_router_dev->device)) + break; + } + printk(KERN_INFO "PCI: Using IRQ router %s [%04x/%04x] at %s\n", + pirq_router.name, + pirq_router_dev->vendor, + pirq_router_dev->device, + pci_name(pirq_router_dev)); +} + +static struct irq_info *pirq_get_info(struct pci_dev *dev) +{ + struct irq_routing_table *rt = pirq_table; + int entries = (rt->size - sizeof(struct irq_routing_table)) / sizeof(struct irq_info); + struct irq_info *info; + + for (info = rt->slots; entries--; info++) + if (info->bus == dev->bus->number && PCI_SLOT(info->devfn) == PCI_SLOT(dev->devfn)) + return info; + return NULL; +} + +static int pcibios_lookup_irq(struct pci_dev *dev, int assign) +{ + u8 pin; + struct irq_info *info; + int i, pirq, newirq; + int irq = 0; + u32 mask; + struct irq_router *r = &pirq_router; + struct pci_dev *dev2 = NULL; + char *msg = NULL; + + /* Find IRQ pin */ + pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); + if (!pin) { + DBG(" -> no interrupt pin\n"); + return 0; + } + pin = pin - 1; + + /* Find IRQ routing entry */ + + if (!pirq_table) + return 0; + + DBG("IRQ for %s[%c]", pci_name(dev), 'A' + pin); + info = pirq_get_info(dev); + if (!info) { + DBG(" -> not found in routing table\n"); + return 0; + } + pirq = info->irq[pin].link; + mask = info->irq[pin].bitmap; + if (!pirq) { + DBG(" -> not routed\n"); + return 0; + } + DBG(" -> PIRQ %02x, mask %04x, excl %04x", pirq, mask, pirq_table->exclusive_irqs); + mask &= pcibios_irq_mask; + + /* Work around broken HP Pavilion Notebooks which assign USB to + IRQ 9 even though it is actually wired to IRQ 11 */ + + if (broken_hp_bios_irq9 && pirq == 0x59 && dev->irq == 9) { + dev->irq = 11; + pci_write_config_byte(dev, PCI_INTERRUPT_LINE, 11); + r->set(pirq_router_dev, dev, pirq, 11); + } + + /* same for Acer Travelmate 360, but with CB and irq 11 -> 10 */ + if (acer_tm360_irqrouting && dev->irq == 11 && dev->vendor == PCI_VENDOR_ID_O2) { + pirq = 0x68; + mask = 0x400; + dev->irq = r->get(pirq_router_dev, dev, pirq); + pci_write_config_byte(dev, PCI_INTERRUPT_LINE, dev->irq); + } + + /* + * Find the best IRQ to assign: use the one + * reported by the device if possible. + */ + newirq = dev->irq; + if (!((1 << newirq) & mask)) { + if ( pci_probe & PCI_USE_PIRQ_MASK) newirq = 0; + else printk(KERN_WARNING "PCI: IRQ %i for device %s doesn't match PIRQ mask - try pci=usepirqmask\n", newirq, pci_name(dev)); + } + if (!newirq && assign) { + for (i = 0; i < 16; i++) { + if (!(mask & (1 << i))) + continue; + if (pirq_penalty[i] < pirq_penalty[newirq] && can_request_irq(i, SA_SHIRQ)) + newirq = i; + } + } + DBG(" -> newirq=%d", newirq); + + /* Check if it is hardcoded */ + if ((pirq & 0xf0) == 0xf0) { + irq = pirq & 0xf; + DBG(" -> hardcoded IRQ %d\n", irq); + msg = "Hardcoded"; + } else if ( r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \ + ((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask)) ) { + DBG(" -> got IRQ %d\n", irq); + msg = "Found"; + } else if (newirq && r->set && (dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) { + DBG(" -> assigning IRQ %d", newirq); + if (r->set(pirq_router_dev, dev, pirq, newirq)) { + eisa_set_level_irq(newirq); + DBG(" ... OK\n"); + msg = "Assigned"; + irq = newirq; + } + } + + if (!irq) { + DBG(" ... failed\n"); + if (newirq && mask == (1 << newirq)) { + msg = "Guessed"; + irq = newirq; + } else + return 0; + } + printk(KERN_INFO "PCI: %s IRQ %d for device %s\n", msg, irq, pci_name(dev)); + + /* Update IRQ for all devices with the same pirq value */ + while ((dev2 = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev2)) != NULL) { + pci_read_config_byte(dev2, PCI_INTERRUPT_PIN, &pin); + if (!pin) + continue; + pin--; + info = pirq_get_info(dev2); + if (!info) + continue; + if (info->irq[pin].link == pirq) { + /* We refuse to override the dev->irq information. Give a warning! */ + if ( dev2->irq && dev2->irq != irq && \ + (!(pci_probe & PCI_USE_PIRQ_MASK) || \ + ((1 << dev2->irq) & mask)) ) { +#ifndef CONFIG_PCI_MSI + printk(KERN_INFO "IRQ routing conflict for %s, have irq %d, want irq %d\n", + pci_name(dev2), dev2->irq, irq); +#endif + continue; + } + dev2->irq = irq; + pirq_penalty[irq]++; + if (dev != dev2) + printk(KERN_INFO "PCI: Sharing IRQ %d with %s\n", irq, pci_name(dev2)); + } + } + return 1; +} + +static void __init pcibios_fixup_irqs(void) +{ + struct pci_dev *dev = NULL; + u8 pin; + + DBG("PCI: IRQ fixup\n"); + while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { + /* + * If the BIOS has set an out of range IRQ number, just ignore it. + * Also keep track of which IRQ's are already in use. + */ + if (dev->irq >= 16) { + DBG("%s: ignoring bogus IRQ %d\n", pci_name(dev), dev->irq); + dev->irq = 0; + } + /* If the IRQ is already assigned to a PCI device, ignore its ISA use penalty */ + if (pirq_penalty[dev->irq] >= 100 && pirq_penalty[dev->irq] < 100000) + pirq_penalty[dev->irq] = 0; + pirq_penalty[dev->irq]++; + } + + dev = NULL; + while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { + pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); +#ifdef CONFIG_X86_IO_APIC + /* + * Recalculate IRQ numbers if we use the I/O APIC. + */ + if (io_apic_assign_pci_irqs) + { + int irq; + + if (pin) { + pin--; /* interrupt pins are numbered starting from 1 */ + irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, PCI_SLOT(dev->devfn), pin); + /* + * Busses behind bridges are typically not listed in the MP-table. + * In this case we have to look up the IRQ based on the parent bus, + * parent slot, and pin number. The SMP code detects such bridged + * busses itself so we should get into this branch reliably. + */ + if (irq < 0 && dev->bus->parent) { /* go back to the bridge */ + struct pci_dev * bridge = dev->bus->self; + + pin = (pin + PCI_SLOT(dev->devfn)) % 4; + irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, + PCI_SLOT(bridge->devfn), pin); + if (irq >= 0) + printk(KERN_WARNING "PCI: using PPB %s[%c] to get irq %d\n", + pci_name(bridge), 'A' + pin, irq); + } + if (irq >= 0) { + if (use_pci_vector() && + !platform_legacy_irq(irq)) + irq = IO_APIC_VECTOR(irq); + + printk(KERN_INFO "PCI->APIC IRQ transform: %s[%c] -> IRQ %d\n", + pci_name(dev), 'A' + pin, irq); + dev->irq = irq; + } + } + } +#endif + /* + * Still no IRQ? Try to lookup one... + */ + if (pin && !dev->irq) + pcibios_lookup_irq(dev, 0); + } +} + +/* + * Work around broken HP Pavilion Notebooks which assign USB to + * IRQ 9 even though it is actually wired to IRQ 11 + */ +static int __init fix_broken_hp_bios_irq9(struct dmi_system_id *d) +{ + if (!broken_hp_bios_irq9) { + broken_hp_bios_irq9 = 1; + printk(KERN_INFO "%s detected - fixing broken IRQ routing\n", d->ident); + } + return 0; +} + +/* + * Work around broken Acer TravelMate 360 Notebooks which assign + * Cardbus to IRQ 11 even though it is actually wired to IRQ 10 + */ +static int __init fix_acer_tm360_irqrouting(struct dmi_system_id *d) +{ + if (!acer_tm360_irqrouting) { + acer_tm360_irqrouting = 1; + printk(KERN_INFO "%s detected - fixing broken IRQ routing\n", d->ident); + } + return 0; +} + +static struct dmi_system_id __initdata pciirq_dmi_table[] = { + { + .callback = fix_broken_hp_bios_irq9, + .ident = "HP Pavilion N5400 Series Laptop", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_BIOS_VERSION, "GE.M1.03"), + DMI_MATCH(DMI_PRODUCT_VERSION, "HP Pavilion Notebook Model GE"), + DMI_MATCH(DMI_BOARD_VERSION, "OmniBook N32N-736"), + }, + }, + { + .callback = fix_acer_tm360_irqrouting, + .ident = "Acer TravelMate 36x Laptop", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 360"), + }, + }, + { } +}; + +static int __init pcibios_irq_init(void) +{ + DBG("PCI: IRQ init\n"); + + if (pcibios_enable_irq || raw_pci_ops == NULL) + return 0; + + dmi_check_system(pciirq_dmi_table); + + pirq_table = pirq_find_routing_table(); + +#ifdef CONFIG_PCI_BIOS + if (!pirq_table && (pci_probe & PCI_BIOS_IRQ_SCAN)) + pirq_table = pcibios_get_irq_routing_table(); +#endif + if (pirq_table) { + pirq_peer_trick(); + pirq_find_router(&pirq_router); + if (pirq_table->exclusive_irqs) { + int i; + for (i=0; i<16; i++) + if (!(pirq_table->exclusive_irqs & (1 << i))) + pirq_penalty[i] += 100; + } + /* If we're using the I/O APIC, avoid using the PCI IRQ routing table */ + if (io_apic_assign_pci_irqs) + pirq_table = NULL; + } + + pcibios_enable_irq = pirq_enable_irq; + + pcibios_fixup_irqs(); + return 0; +} + +subsys_initcall(pcibios_irq_init); + + +static void pirq_penalize_isa_irq(int irq) +{ + /* + * If any ISAPnP device reports an IRQ in its list of possible + * IRQ's, we try to avoid assigning it to PCI devices. + */ + if (irq < 16) + pirq_penalty[irq] += 100; +} + +void pcibios_penalize_isa_irq(int irq) +{ +#ifdef CONFIG_ACPI_PCI + if (!acpi_noirq) + acpi_penalize_isa_irq(irq); + else +#endif + pirq_penalize_isa_irq(irq); +} + +static int pirq_enable_irq(struct pci_dev *dev) +{ + u8 pin; + struct pci_dev *temp_dev; + + pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); + if (pin && !pcibios_lookup_irq(dev, 1) && !dev->irq) { + char *msg = ""; + + pin--; /* interrupt pins are numbered starting from 1 */ + + if (io_apic_assign_pci_irqs) { + int irq; + + irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, PCI_SLOT(dev->devfn), pin); + /* + * Busses behind bridges are typically not listed in the MP-table. + * In this case we have to look up the IRQ based on the parent bus, + * parent slot, and pin number. The SMP code detects such bridged + * busses itself so we should get into this branch reliably. + */ + temp_dev = dev; + while (irq < 0 && dev->bus->parent) { /* go back to the bridge */ + struct pci_dev * bridge = dev->bus->self; + + pin = (pin + PCI_SLOT(dev->devfn)) % 4; + irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, + PCI_SLOT(bridge->devfn), pin); + if (irq >= 0) + printk(KERN_WARNING "PCI: using PPB %s[%c] to get irq %d\n", + pci_name(bridge), 'A' + pin, irq); + dev = bridge; + } + dev = temp_dev; + if (irq >= 0) { +#ifdef CONFIG_PCI_MSI + if (!platform_legacy_irq(irq)) + irq = IO_APIC_VECTOR(irq); +#endif + printk(KERN_INFO "PCI->APIC IRQ transform: %s[%c] -> IRQ %d\n", + pci_name(dev), 'A' + pin, irq); + dev->irq = irq; + return 0; + } else + msg = " Probably buggy MP table."; + } else if (pci_probe & PCI_BIOS_IRQ_SCAN) + msg = ""; + else + msg = " Please try using pci=biosirq."; + + /* With IDE legacy devices the IRQ lookup failure is not a problem.. */ + if (dev->class >> 8 == PCI_CLASS_STORAGE_IDE && !(dev->class & 0x5)) + return 0; + + printk(KERN_WARNING "PCI: No IRQ known for interrupt pin %c of device %s.%s\n", + 'A' + pin, pci_name(dev), msg); + } + return 0; +} + +int pci_vector_resources(int last, int nr_released) +{ + int count = nr_released; + + int next = last; + int offset = (last % 8); + + while (next < FIRST_SYSTEM_VECTOR) { + next += 8; +#ifdef CONFIG_X86_64 + if (next == IA32_SYSCALL_VECTOR) + continue; +#else + if (next == SYSCALL_VECTOR) + continue; +#endif + count++; + if (next >= FIRST_SYSTEM_VECTOR) { + if (offset%8) { + next = FIRST_DEVICE_VECTOR + offset; + offset++; + continue; + } + count--; + } + } + + return count; +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/um/kernel/physmem.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/um/kernel/physmem.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,480 @@ +/* + * Copyright (C) 2000 - 2003 Jeff Dike (jdike@xxxxxxxxxxx) + * Licensed under the GPL + */ + +#include "linux/mm.h" +#include "linux/rbtree.h" +#include "linux/slab.h" +#include "linux/vmalloc.h" +#include "linux/bootmem.h" +#include "linux/module.h" +#include "asm/types.h" +#include "asm/pgtable.h" +#include "kern_util.h" +#include "user_util.h" +#include "mode_kern.h" +#include "mem.h" +#include "mem_user.h" +#include "os.h" +#include "kern.h" +#include "init.h" + +struct phys_desc { + struct rb_node rb; + int fd; + __u64 offset; + void *virt; + unsigned long phys; + struct list_head list; +}; + +static struct rb_root phys_mappings = RB_ROOT; + +static struct rb_node **find_rb(void *virt) +{ + struct rb_node **n = &phys_mappings.rb_node; + struct phys_desc *d; + + while(*n != NULL){ + d = rb_entry(*n, struct phys_desc, rb); + if(d->virt == virt) + return(n); + + if(d->virt > virt) + n = &(*n)->rb_left; + else + n = &(*n)->rb_right; + } + + return(n); +} + +static struct phys_desc *find_phys_mapping(void *virt) +{ + struct rb_node **n = find_rb(virt); + + if(*n == NULL) + return(NULL); + + return(rb_entry(*n, struct phys_desc, rb)); +} + +static void insert_phys_mapping(struct phys_desc *desc) +{ + struct rb_node **n = find_rb(desc->virt); + + if(*n != NULL) + panic("Physical remapping for %p already present", + desc->virt); + + rb_link_node(&desc->rb, (*n)->rb_parent, n); + rb_insert_color(&desc->rb, &phys_mappings); +} + +LIST_HEAD(descriptor_mappings); + +struct desc_mapping { + int fd; + struct list_head list; + struct list_head pages; +}; + +static struct desc_mapping *find_mapping(int fd) +{ + struct desc_mapping *desc; + struct list_head *ele; + + list_for_each(ele, &descriptor_mappings){ + desc = list_entry(ele, struct desc_mapping, list); + if(desc->fd == fd) + return(desc); + } + + return(NULL); +} + +static struct desc_mapping *descriptor_mapping(int fd) +{ + struct desc_mapping *desc; + + desc = find_mapping(fd); + if(desc != NULL) + return(desc); + + desc = kmalloc(sizeof(*desc), GFP_ATOMIC); + if(desc == NULL) + return(NULL); + + *desc = ((struct desc_mapping) + { .fd = fd, + .list = LIST_HEAD_INIT(desc->list), + .pages = LIST_HEAD_INIT(desc->pages) }); + list_add(&desc->list, &descriptor_mappings); + + return(desc); +} + +int physmem_subst_mapping(void *virt, int fd, __u64 offset, int w) +{ + struct desc_mapping *fd_maps; + struct phys_desc *desc; + unsigned long phys; + int err; + + fd_maps = descriptor_mapping(fd); + if(fd_maps == NULL) + return(-ENOMEM); + + phys = __pa(virt); + desc = find_phys_mapping(virt); + if(desc != NULL) + panic("Address 0x%p is already substituted\n", virt); + + err = -ENOMEM; + desc = kmalloc(sizeof(*desc), GFP_ATOMIC); + if(desc == NULL) + goto out; + + *desc = ((struct phys_desc) + { .fd = fd, + .offset = offset, + .virt = virt, + .phys = __pa(virt), + .list = LIST_HEAD_INIT(desc->list) }); + insert_phys_mapping(desc); + + list_add(&desc->list, &fd_maps->pages); + + virt = (void *) ((unsigned long) virt & PAGE_MASK); + err = os_map_memory(virt, fd, offset, PAGE_SIZE, 1, w, 0); + if(!err) + goto out; + + rb_erase(&desc->rb, &phys_mappings); + kfree(desc); + out: + return(err); +} + +static int physmem_fd = -1; + +static void remove_mapping(struct phys_desc *desc) +{ + void *virt = desc->virt; + int err; + + rb_erase(&desc->rb, &phys_mappings); + list_del(&desc->list); + kfree(desc); + + err = os_map_memory(virt, physmem_fd, __pa(virt), PAGE_SIZE, 1, 1, 0); + if(err) + panic("Failed to unmap block device page from physical memory, " + "errno = %d", -err); +} + +int physmem_remove_mapping(void *virt) +{ + struct phys_desc *desc; + + virt = (void *) ((unsigned long) virt & PAGE_MASK); + desc = find_phys_mapping(virt); + if(desc == NULL) + return(0); + + remove_mapping(desc); + return(1); +} + +void physmem_forget_descriptor(int fd) +{ + struct desc_mapping *desc; + struct phys_desc *page; + struct list_head *ele, *next; + __u64 offset; + void *addr; + int err; + + desc = find_mapping(fd); + if(desc == NULL) + return; + + list_for_each_safe(ele, next, &desc->pages){ + page = list_entry(ele, struct phys_desc, list); + offset = page->offset; + addr = page->virt; + remove_mapping(page); + err = os_seek_file(fd, offset); + if(err) + panic("physmem_forget_descriptor - failed to seek " + "to %lld in fd %d, error = %d\n", + offset, fd, -err); + err = os_read_file(fd, addr, PAGE_SIZE); + if(err < 0) + panic("physmem_forget_descriptor - failed to read " + "from fd %d to 0x%p, error = %d\n", + fd, addr, -err); + } + + list_del(&desc->list); + kfree(desc); +} + +EXPORT_SYMBOL(physmem_forget_descriptor); +EXPORT_SYMBOL(physmem_remove_mapping); +EXPORT_SYMBOL(physmem_subst_mapping); + +int arch_free_page(struct page *page, int order) +{ + void *virt; + int i; + + for(i = 0; i < (1 << order); i++){ + virt = __va(page_to_phys(page + i)); + physmem_remove_mapping(virt); + } + + return 0; +} + +int is_remapped(void *virt) +{ + struct phys_desc *desc = find_phys_mapping(virt); + + return(desc != NULL); +} + +/* Changed during early boot */ +unsigned long high_physmem; + +extern unsigned long physmem_size; + +void *to_virt(unsigned long phys) +{ + return((void *) uml_physmem + phys); +} + +unsigned long to_phys(void *virt) +{ + return(((unsigned long) virt) - uml_physmem); +} + +int init_maps(unsigned long physmem, unsigned long iomem, unsigned long highmem) +{ + struct page *p, *map; + unsigned long phys_len, phys_pages, highmem_len, highmem_pages; + unsigned long iomem_len, iomem_pages, total_len, total_pages; + int i; + + phys_pages = physmem >> PAGE_SHIFT; + phys_len = phys_pages * sizeof(struct page); + + iomem_pages = iomem >> PAGE_SHIFT; + iomem_len = iomem_pages * sizeof(struct page); + + highmem_pages = highmem >> PAGE_SHIFT; + highmem_len = highmem_pages * sizeof(struct page); + + total_pages = phys_pages + iomem_pages + highmem_pages; + total_len = phys_len + iomem_pages + highmem_len; + + if(kmalloc_ok){ + map = kmalloc(total_len, GFP_KERNEL); + if(map == NULL) + map = vmalloc(total_len); + } + else map = alloc_bootmem_low_pages(total_len); + + if(map == NULL) + return(-ENOMEM); + + for(i = 0; i < total_pages; i++){ + p = &map[i]; + set_page_count(p, 0); + SetPageReserved(p); + INIT_LIST_HEAD(&p->lru); + } + + max_mapnr = total_pages; + return(0); +} + +struct page *phys_to_page(const unsigned long phys) +{ + return(&mem_map[phys >> PAGE_SHIFT]); +} + +struct page *__virt_to_page(const unsigned long virt) +{ + return(&mem_map[__pa(virt) >> PAGE_SHIFT]); +} + +phys_t page_to_phys(struct page *page) +{ + return((page - mem_map) << PAGE_SHIFT); +} + +pte_t mk_pte(struct page *page, pgprot_t pgprot) +{ + pte_t pte; + + pte_set_val(pte, page_to_phys(page), pgprot); + if(pte_present(pte)) + pte_mknewprot(pte_mknewpage(pte)); + return(pte); +} + +/* Changed during early boot */ +static unsigned long kmem_top = 0; + +unsigned long get_kmem_end(void) +{ + if(kmem_top == 0) + kmem_top = CHOOSE_MODE(kmem_end_tt, kmem_end_skas); + return(kmem_top); +} + +void map_memory(unsigned long virt, unsigned long phys, unsigned long len, + int r, int w, int x) +{ + __u64 offset; + int fd, err; + + fd = phys_mapping(phys, &offset); + err = os_map_memory((void *) virt, fd, offset, len, r, w, x); + if(err) { + if(err == -ENOMEM) + printk("try increasing the host's " + "/proc/sys/vm/max_map_count to <physical " + "memory size>/4096\n"); + panic("map_memory(0x%lx, %d, 0x%llx, %ld, %d, %d, %d) failed, " + "err = %d\n", virt, fd, offset, len, r, w, x, err); + } +} + +#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) + +void setup_physmem(unsigned long start, unsigned long reserve_end, + unsigned long len, unsigned long highmem) +{ + unsigned long reserve = reserve_end - start; + int pfn = PFN_UP(__pa(reserve_end)); + int delta = (len - reserve) >> PAGE_SHIFT; + int err, offset, bootmap_size; + + physmem_fd = create_mem_file(len + highmem); + + offset = uml_reserved - uml_physmem; + err = os_map_memory((void *) uml_reserved, physmem_fd, offset, + len - offset, 1, 1, 0); + if(err < 0){ + os_print_error(err, "Mapping memory"); + exit(1); + } + + bootmap_size = init_bootmem(pfn, pfn + delta); + free_bootmem(__pa(reserve_end) + bootmap_size, + len - bootmap_size - reserve); +} + +int phys_mapping(unsigned long phys, __u64 *offset_out) +{ + struct phys_desc *desc = find_phys_mapping(__va(phys & PAGE_MASK)); + int fd = -1; + + if(desc != NULL){ + fd = desc->fd; + *offset_out = desc->offset; + } + else if(phys < physmem_size){ + fd = physmem_fd; + *offset_out = phys; + } + else if(phys < __pa(end_iomem)){ + struct iomem_region *region = iomem_regions; + + while(region != NULL){ + if((phys >= region->phys) && + (phys < region->phys + region->size)){ + fd = region->fd; + *offset_out = phys - region->phys; + break; + } + region = region->next; + } + } + else if(phys < __pa(end_iomem) + highmem){ + fd = physmem_fd; + *offset_out = phys - iomem_size; + } + + return(fd); +} + +static int __init uml_mem_setup(char *line, int *add) +{ + char *retptr; + physmem_size = memparse(line,&retptr); + return 0; +} +__uml_setup("mem=", uml_mem_setup, +"mem=<Amount of desired ram>\n" +" This controls how much \"physical\" memory the kernel allocates\n" +" for the system. The size is specified as a number followed by\n" +" one of 'k', 'K', 'm', 'M', which have the obvious meanings.\n" +" This is not related to the amount of memory in the host. It can\n" +" be more, and the excess, if it's ever used, will just be swapped out.\n" +" Example: mem=64M\n\n" +); + +unsigned long find_iomem(char *driver, unsigned long *len_out) +{ + struct iomem_region *region = iomem_regions; + + while(region != NULL){ + if(!strcmp(region->driver, driver)){ + *len_out = region->size; + return(region->virt); + } + } + + return(0); +} + +int setup_iomem(void) +{ + struct iomem_region *region = iomem_regions; + unsigned long iomem_start = high_physmem + PAGE_SIZE; + int err; + + while(region != NULL){ + err = os_map_memory((void *) iomem_start, region->fd, 0, + region->size, 1, 1, 0); + if(err) + printk("Mapping iomem region for driver '%s' failed, " + "errno = %d\n", region->driver, -err); + else { + region->virt = iomem_start; + region->phys = __pa(region->virt); + } + + iomem_start += region->size + PAGE_SIZE; + region = region->next; + } + + return(0); +} + +__initcall(setup_iomem); + +/* + * Overrides for Emacs so that we follow Linus's tabbing style. + * Emacs will notice this stuff at the end of the file and automatically + * adjust the settings for this buffer only. This must remain at the end + * of the file. + * --------------------------------------------------------------------------- + * Local variables: + * c-file-style: "linux" + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/Kconfig --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/Kconfig Mon Jan 30 17:18:27 2006 @@ -0,0 +1,526 @@ +# +# For a description of the syntax of this configuration file, +# see Documentation/kbuild/kconfig-language.txt. +# +# Note: ISA is disabled and will hopefully never be enabled. +# If you managed to buy an ISA x86-64 box you'll have to fix all the +# ISA drivers you need yourself. +# + +mainmenu "Linux Kernel Configuration" + +config X86_64 + bool + default y + help + Port to the x86-64 architecture. x86-64 is a 64-bit extension to the + classical 32-bit x86 architecture. For details see + <http://www.x86-64.org/>. + +config 64BIT + def_bool y + +config X86 + bool + default y + +config MMU + bool + default y + +config ISA + bool + +config SBUS + bool + +config RWSEM_GENERIC_SPINLOCK + bool + default y + +config RWSEM_XCHGADD_ALGORITHM + bool + +config GENERIC_CALIBRATE_DELAY + bool + default y + +config X86_CMPXCHG + bool + default y + +config EARLY_PRINTK + bool + default y + +config GENERIC_ISA_DMA + bool + default y + +config GENERIC_IOMAP + bool + default y + +source "init/Kconfig" + + +menu "Processor type and features" + +choice + prompt "Processor family" + default MK8 + +config MK8 + bool "AMD-Opteron/Athlon64" + help + Optimize for AMD Opteron/Athlon64/Hammer/K8 CPUs. + +config MPSC + bool "Intel EM64T" + help + Optimize for Intel Pentium 4 and Xeon CPUs with Intel + Extended Memory 64 Technology(EM64T). For details see + <http://www.intel.com/technology/64bitextensions/>. + +config GENERIC_CPU + bool "Generic-x86-64" + help + Generic x86-64 CPU. + +endchoice + +config X86_64_XEN + bool "Enable Xen compatible kernel" + select SWIOTLB if XEN_PHYSDEV_ACCESS + select DUMMY_IOMMU if XEN_PHYSDEV_ACCESS + help + This option will compile a kernel compatible with Xen hypervisor + +# +# Define implied options from the CPU selection here +# +config X86_L1_CACHE_BYTES + int + default "128" if GENERIC_CPU || MPSC + default "64" if MK8 + +config X86_L1_CACHE_SHIFT + int + default "7" if GENERIC_CPU || MPSC + default "6" if MK8 + +config X86_TSC + bool + depends on !X86_64_XEN + default y + +config X86_GOOD_APIC + bool + default y + +config MICROCODE + tristate "/dev/cpu/microcode - Intel CPU microcode support" + ---help--- + If you say Y here the 'File systems' section, you will be + able to update the microcode on Intel processors. You will + obviously need the actual microcode binary data itself which is + not shipped with the Linux kernel. + + For latest news and information on obtaining all the required + ingredients for this driver, check: + <http://www.urbanmyth.org/microcode/>. + + To compile this driver as a module, choose M here: the + module will be called microcode. + If you use modprobe or kmod you may also want to add the line + 'alias char-major-10-184 microcode' to your /etc/modules.conf file. + +config X86_MSR + tristate "/dev/cpu/*/msr - Model-specific register support" + help + This device gives privileged processes access to the x86 + Model-Specific Registers (MSRs). It is a character device with + major 202 and minors 0 to 31 for /dev/cpu/0/msr to /dev/cpu/31/msr. + MSR accesses are directed to a specific CPU on multi-processor + systems. + +config X86_CPUID + tristate "/dev/cpu/*/cpuid - CPU information support" + help + This device gives processes access to the x86 CPUID instruction to + be executed on a specific processor. It is a character device + with major 203 and minors 0 to 31 for /dev/cpu/0/cpuid to + /dev/cpu/31/cpuid. + +# disable it for opteron optimized builds because it pulls in ACPI_BOOT +config X86_HT + bool + depends on SMP && !MK8 && !X86_64_XEN + default y + +config MATH_EMULATION + bool + +config MCA + bool + +config EISA + bool + +config X86_IO_APIC + bool + depends !XEN_UNPRIVILEGED_GUEST + default y + +config X86_XEN_GENAPIC + bool + depends X86_64_XEN + default XEN_PRIVILEGED_GUEST || SMP + +config X86_LOCAL_APIC + bool + depends !XEN_UNPRIVILEGED_GUEST + default y + +config MTRR + bool "MTRR (Memory Type Range Register) support" + depends on !X86_64_XEN + ---help--- + On Intel P6 family processors (Pentium Pro, Pentium II and later) + the Memory Type Range Registers (MTRRs) may be used to control + processor access to memory ranges. This is most useful if you have + a video (VGA) card on a PCI or AGP bus. Enabling write-combining + allows bus write transfers to be combined into a larger transfer + before bursting over the PCI/AGP bus. This can increase performance + of image write operations 2.5 times or more. Saying Y here creates a + /proc/mtrr file which may be used to manipulate your processor's + MTRRs. Typically the X server should use this. + + This code has a reasonably generic interface so that similar + control registers on other processors can be easily supported + as well. + + Saying Y here also fixes a problem with buggy SMP BIOSes which only + set the MTRRs for the boot CPU and not for the secondary CPUs. This + can lead to all sorts of problems, so it's good to say Y here. + + Just say Y here, all x86-64 machines support MTRRs. + + See <file:Documentation/mtrr.txt> for more information. + +config SMP + bool "Symmetric multi-processing support" + ---help--- + This enables support for systems with more than one CPU. If you have + a system with only one CPU, like most personal computers, say N. If + you have a system with more than one CPU, say Y. + + If you say N here, the kernel will run on single and multiprocessor + machines, but will use only one CPU of a multiprocessor machine. If + you say Y here, the kernel will run on many, but not all, + singleprocessor machines. On a singleprocessor machine, the kernel + will run faster if you say N here. + + If you don't know what to do here, say N. + +config PREEMPT + bool "Preemptible Kernel" + depends on !X86_64_XEN + ---help--- + This option reduces the latency of the kernel when reacting to + real-time or interactive events by allowing a low priority process to + be preempted even if it is in kernel mode executing a system call. + This allows applications to run more reliably even when the system is + under load. On contrary it may also break your drivers and add + priority inheritance problems to your system. Don't select it if + you rely on a stable system or have slightly obscure hardware. + It's also not very well tested on x86-64 currently. + You have been warned. + + Say Y here if you are feeling brave and building a kernel for a + desktop, embedded or real-time system. Say N if you are unsure. + +config PREEMPT_BKL + bool "Preempt The Big Kernel Lock" + depends on PREEMPT + default y + help + This option reduces the latency of the kernel by making the + big kernel lock preemptible. + + Say Y here if you are building a kernel for a desktop system. + Say N if you are unsure. + +config SCHED_SMT + bool "SMT (Hyperthreading) scheduler support" + depends on SMP && !X86_64_XEN + default n + help + SMT scheduler support improves the CPU scheduler's decision making + when dealing with Intel Pentium 4 chips with HyperThreading at a + cost of slightly increased overhead in some places. If unsure say + N here. + +config K8_NUMA + bool "K8 NUMA support" + select NUMA + depends on SMP && !X86_64_XEN + help + Enable NUMA (Non Unified Memory Architecture) support for + AMD Opteron Multiprocessor systems. The kernel will try to allocate + memory used by a CPU on the local memory controller of the CPU + and add some more NUMA awareness to the kernel. + This code is recommended on all multiprocessor Opteron systems + and normally doesn't hurt on others. + +config NUMA_EMU + bool "NUMA emulation support" + select NUMA + depends on SMP && !X86_64_XEN + help + Enable NUMA emulation. A flat machine will be split + into virtual nodes when booted with "numa=fake=N", where N is the + number of nodes. This is only useful for debugging. + +config DISCONTIGMEM + bool + depends on NUMA + default y + +config NUMA + bool + default n + +config HAVE_DEC_LOCK + bool + depends on SMP + default y + +config NR_CPUS + int "Maximum number of CPUs (2-256)" + range 2 256 + depends on SMP + default "16" if X86_64_XEN + default "8" + help + This allows you to specify the maximum number of CPUs which this + kernel will support. Current maximum is 256 CPUs due to + APIC addressing limits. Less depending on the hardware. + + This is purely to save memory - each supported CPU requires + memory in the static kernel configuration. + +config HPET_TIMER + bool + depends on !X86_64_XEN + default y + help + Use the IA-PC HPET (High Precision Event Timer) to manage + time in preference to the PIT and RTC, if a HPET is + present. The HPET provides a stable time base on SMP + systems, unlike the TSC, but it is more expensive to access, + as it is off-chip. You can find the HPET spec at + <http://www.intel.com/labs/platcomp/hpet/hpetspec.htm>. + +config X86_PM_TIMER + bool "PM timer" + depends on ACPI && !X86_64_XEN + default y + help + Support the ACPI PM timer for time keeping. This is slow, + but is useful on some chipsets without HPET on systems with more + than one CPU. On a single processor or single socket multi core + system it is normally not required. + When the PM timer is active 64bit vsyscalls are disabled + and should not be enabled (/proc/sys/kernel/vsyscall64 should + not be changed). + The kernel selects the PM timer only as a last resort, so it is + useful to enable just in case. + +config HPET_EMULATE_RTC + bool "Provide RTC interrupt" + depends on HPET_TIMER && RTC=y + +config GART_IOMMU + bool "IOMMU support" + depends on PCI && !X86_64_XEN + help + Support the K8 IOMMU. Needed to run systems with more than 4GB of memory + properly with 32-bit PCI devices that do not support DAC (Double Address + Cycle). The IOMMU can be turned off at runtime with the iommu=off parameter. + Normally the kernel will take the right choice by itself. + If unsure, say Y. + +# need this always enabled with GART_IOMMU for the VIA workaround +config SWIOTLB + bool + depends on GART_IOMMU + default y + +config DUMMY_IOMMU + bool + depends on !GART_IOMMU && !SWIOTLB + default y + help + Don't use IOMMU code. This will cause problems when you have more than 4GB + of memory and any 32-bit devices. Don't turn on unless you know what you + are doing. + +config X86_MCE + bool "Machine check support" if EMBEDDED + depends on !X86_64_XEN + default y + help + Include a machine check error handler to report hardware errors. + This version will require the mcelog utility to decode some + machine check error logs. See + ftp://ftp.x86-64.org/pub/linux/tools/mcelog + +config X86_MCE_INTEL + bool "Intel MCE features" + depends on X86_MCE && X86_LOCAL_APIC + default y + help + Additional support for intel specific MCE features such as + the thermal monitor. + +config SECCOMP + bool "Enable seccomp to safely compute untrusted bytecode" + depends on PROC_FS + default y + help + This kernel feature is useful for number crunching applications + that may need to compute untrusted bytecode during their + execution. By using pipes or other transports made available to + the process as file descriptors supporting the read/write + syscalls, it's possible to isolate those applications in + their own address space using seccomp. Once seccomp is + enabled via /proc/<pid>/seccomp, it cannot be disabled + and the task is only allowed to execute a few safe syscalls + defined by each seccomp mode. + + If unsure, say Y. Only embedded should say N here. + +endmenu + +# +# Use the generic interrupt handling code in kernel/irq/: +# +config GENERIC_HARDIRQS + bool + default y + +config GENERIC_IRQ_PROBE + bool + default y + +# we have no ISA slots, but we do have ISA-style DMA. +config ISA_DMA_API + bool + default y + +menu "Power management options" + depends on !XEN_UNPRIVILEGED_GUEST + +if !X86_64_XEN +source kernel/power/Kconfig +endif + +source "drivers/acpi/Kconfig" + +if !X86_64_XEN +source "arch/x86_64/kernel/cpufreq/Kconfig" +endif + +endmenu + +menu "Bus options (PCI etc.)" + +config PCI + bool "PCI support" + +# x86-64 doesn't support PCI BIOS access from long mode so always go direct. +config PCI_DIRECT + bool + depends on PCI + default y + +config PCI_MMCONFIG + bool "Support mmconfig PCI config space access" + depends on PCI && ACPI + select ACPI_BOOT + +config UNORDERED_IO + bool "Unordered IO mapping access" + depends on EXPERIMENTAL + help + Use unordered stores to access IO memory mappings in device drivers. + Still very experimental. When a driver works on IA64/ppc64/pa-risc it should + work with this option, but it makes the drivers behave differently + from i386. Requires that the driver writer used memory barriers + properly. + +if !X86_64_XEN +source "drivers/pci/pcie/Kconfig" + +source "drivers/pci/Kconfig" + +source "drivers/pcmcia/Kconfig" + +source "drivers/pci/hotplug/Kconfig" +endif + +endmenu + + +menu "Executable file formats / Emulations" + +source "fs/Kconfig.binfmt" + +config IA32_EMULATION + bool "IA32 Emulation" + help + Include code to run 32-bit programs under a 64-bit kernel. You should likely + turn this on, unless you're 100% sure that you don't have any 32-bit programs + left. + +config IA32_AOUT + bool "IA32 a.out support" + depends on IA32_EMULATION + help + Support old a.out binaries in the 32bit emulation. + +config COMPAT + bool + depends on IA32_EMULATION + default y + +config SYSVIPC_COMPAT + bool + depends on COMPAT && SYSVIPC + default y + +config UID16 + bool + depends on IA32_EMULATION + default y + +endmenu + +source drivers/Kconfig + +source "drivers/firmware/Kconfig" + +source fs/Kconfig + +source "arch/x86_64/oprofile/Kconfig" + +source "arch/x86_64/Kconfig.debug" + +source "security/Kconfig" + +source "crypto/Kconfig" + +source "drivers/xen/Kconfig" + +source "lib/Kconfig" diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/Makefile --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/Makefile Mon Jan 30 17:18:27 2006 @@ -0,0 +1,135 @@ +# +# x86_64/Makefile +# +# This file is included by the global makefile so that you can add your own +# architecture-specific flags and dependencies. Remember to do have actions +# for "archclean" and "archdep" for cleaning up and making dependencies for +# this architecture +# +# This file is subject to the terms and conditions of the GNU General Public +# License. See the file "COPYING" in the main directory of this archive +# for more details. +# +# Copyright (C) 1994 by Linus Torvalds +# +# 19990713 Artur Skawina <skawina@xxxxxxxxxxxxx> +# Added '-march' and '-mpreferred-stack-boundary' support +# 20000913 Pavel Machek <pavel@xxxxxxx> +# Converted for x86_64 architecture +# 20010105 Andi Kleen, add IA32 compiler. +# ....and later removed it again.... +# +# $Id: Makefile,v 1.31 2002/03/22 15:56:07 ak Exp $ + +# +# early bootup linking needs 32bit. You can either use real 32bit tools +# here or 64bit tools in 32bit mode. +# +IA32_CC := $(CC) $(CPPFLAGS) -m32 -O2 -fomit-frame-pointer +IA32_LD := $(LD) -m elf_i386 +IA32_AS := $(CC) $(AFLAGS) -m32 -Wa,--32 -traditional -c +IA32_OBJCOPY := $(CROSS_COMPILE)objcopy +IA32_CPP := $(CROSS_COMPILE)gcc -m32 -E +export IA32_CC IA32_LD IA32_AS IA32_OBJCOPY IA32_CPP + + +LDFLAGS := -m elf_x86_64 +OBJCOPYFLAGS := -O binary -R .note -R .comment -S +LDFLAGS_vmlinux := -e stext + +CHECKFLAGS += -D__x86_64__ -m64 + +cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8) +cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona) +CFLAGS += $(cflags-y) + +CFLAGS += -mno-red-zone +CFLAGS += -mcmodel=kernel +CFLAGS += -pipe +# this makes reading assembly source easier, but produces worse code +# actually it makes the kernel smaller too. +CFLAGS += -fno-reorder-blocks +CFLAGS += -Wno-sign-compare +ifneq ($(CONFIG_DEBUG_INFO),y) +CFLAGS += -fno-asynchronous-unwind-tables +# -fweb shrinks the kernel a bit, but the difference is very small +# it also messes up debugging, so don't use it for now. +#CFLAGS += $(call cc-option,-fweb) +endif +# -funit-at-a-time shrinks the kernel .text considerably +# unfortunately it makes reading oopses harder. +CFLAGS += $(call cc-option,-funit-at-a-time) +# prevent gcc from generating any FP code by mistake +CFLAGS += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,) + +head-y := arch/x86_64/kernel/head.o arch/x86_64/kernel/head64.o arch/x86_64/kernel/init_task.o + +libs-y += arch/x86_64/lib/ +core-y += arch/x86_64/kernel/ arch/x86_64/mm/ +core-$(CONFIG_IA32_EMULATION) += arch/x86_64/ia32/ +drivers-$(CONFIG_PCI) += arch/x86_64/pci/ +drivers-$(CONFIG_OPROFILE) += arch/x86_64/oprofile/ + +boot := arch/x86_64/boot + +.PHONY: bzImage bzlilo install archmrproper \ + fdimage fdimage144 fdimage288 archclean + +ifdef CONFIG_XEN +CPPFLAGS := -D__KERNEL__ -Iinclude$(if $(KBUILD_SRC),2)/asm/mach-xen $(LINUXINCLUDE) +head-y := arch/x86_64/kernel/head-xen.o arch/x86_64/kernel/head64-xen.o arch/x86_64/kernel/init_task.o +LDFLAGS_vmlinux := -e _start +boot := arch/i386/boot-xen +.PHONY: vmlinuz +#Default target when executing "make" +all: vmlinuz + +vmlinuz: vmlinux + $(Q)$(MAKE) $(build)=$(boot) $@ + +install: vmlinux + $(Q)$(MAKE) $(build)=$(boot) XENGUEST=$(XENGUEST) $@ +else +#Default target when executing "make" +all: bzImage + +BOOTIMAGE := arch/x86_64/boot/bzImage +KBUILD_IMAGE := $(BOOTIMAGE) + +bzImage: vmlinux + $(Q)$(MAKE) $(build)=$(boot) $(BOOTIMAGE) + +bzlilo: vmlinux + $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(BOOTIMAGE) zlilo + +bzdisk: vmlinux + $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(BOOTIMAGE) zdisk + +install fdimage fdimage144 fdimage288: vmlinux + $(Q)$(MAKE) $(build)=$(boot) BOOTIMAGE=$(BOOTIMAGE) $@ +endif + +archclean: + $(Q)$(MAKE) $(clean)=$(boot) + +prepare: include/asm-$(ARCH)/offset.h + +arch/$(ARCH)/kernel/asm-offsets.s: include/asm include/linux/version.h \ + include/config/MARKER + +include/asm-$(ARCH)/offset.h: arch/$(ARCH)/kernel/asm-offsets.s + $(call filechk,gen-asm-offsets) + +CLEAN_FILES += include/asm-$(ARCH)/offset.h + +define archhelp + echo '* bzImage - Compressed kernel image (arch/$(ARCH)/boot/bzImage)' + echo ' install - Install kernel using' + echo ' (your) ~/bin/installkernel or' + echo ' (distribution) /sbin/installkernel or' + echo ' install to $$(INSTALL_PATH) and run lilo' +endef + +CLEAN_FILES += arch/$(ARCH)/boot/fdimage arch/$(ARCH)/boot/mtools.conf + + diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/ia32/Makefile --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/ia32/Makefile Mon Jan 30 17:18:27 2006 @@ -0,0 +1,46 @@ +# +# Makefile for the ia32 kernel emulation subsystem. +# + +obj-$(CONFIG_IA32_EMULATION) := ia32entry.o sys_ia32.o ia32_ioctl.o \ + ia32_signal.o tls32.o \ + ia32_binfmt.o fpu32.o ptrace32.o syscall32.o + +sysv-$(CONFIG_SYSVIPC) := ipc32.o +obj-$(CONFIG_IA32_EMULATION) += $(sysv-y) + +obj-$(CONFIG_IA32_AOUT) += ia32_aout.o + +$(obj)/syscall32.o: $(src)/syscall32.c \ + $(foreach F,sysenter syscall,$(obj)/vsyscall-$F.so) + +# Teach kbuild about targets +targets := $(foreach F,sysenter syscall,vsyscall-$F.o vsyscall-$F.so) + +# The DSO images are built using a special linker script +quiet_cmd_syscall = SYSCALL $@ + cmd_syscall = $(CC) -m32 -nostdlib -shared -s \ + -Wl,-soname=linux-gate.so.1 -o $@ \ + -Wl,-T,$(filter-out FORCE,$^) + +$(obj)/vsyscall-int80.so \ +$(obj)/vsyscall-sysenter.so $(obj)/vsyscall-syscall.so: \ +$(obj)/vsyscall-%.so: $(src)/vsyscall.lds $(obj)/vsyscall-%.o FORCE + $(call if_changed,syscall) + +AFLAGS_vsyscall-sysenter.o = -m32 +AFLAGS_vsyscall-syscall.o = -m32 +CFLAGS_ia32_ioctl.o += -Ifs/ + +ifdef CONFIG_XEN +AFLAGS_vsyscall-int80.o = -m32 -Iarch/i386/kernel + +$(obj)/syscall32-xen.o: $(src)/syscall32-xen.c \ + $(foreach F,int80 sysenter syscall,$(obj)/vsyscall-$F.so) + +targets := $(foreach F,int80 sysenter syscall,vsyscall-$F.o vsyscall-$F.so) + +include $(srctree)/scripts/Makefile.xen + +obj-y := $(call cherrypickxen, $(obj-y)) +endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/ia32/ia32entry-xen.S --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/ia32/ia32entry-xen.S Mon Jan 30 17:18:27 2006 @@ -0,0 +1,629 @@ +/* + * Compatibility mode system call entry point for x86-64. + * + * Copyright 2000-2002 Andi Kleen, SuSE Labs. + */ + +#include <asm/dwarf2.h> +#include <asm/calling.h> +#include <asm/offset.h> +#include <asm/current.h> +#include <asm/errno.h> +#include <asm/ia32_unistd.h> +#include <asm/thread_info.h> +#include <asm/segment.h> +#include <asm/vsyscall32.h> +#include <linux/linkage.h> + +#define __XEN_X86_64 1 + + .macro IA32_ARG_FIXUP noebp=0 + movl %edi,%r8d + .if \noebp + .else + movl %ebp,%r9d + .endif + xchg %ecx,%esi + movl %ebx,%edi + movl %edx,%edx /* zero extension */ + .endm + + /* clobbers %eax */ + .macro CLEAR_RREGS + xorl %eax,%eax + movq %rax,R11(%rsp) + movq %rax,R10(%rsp) + movq %rax,R9(%rsp) + movq %rax,R8(%rsp) + .endm + +#if defined (__XEN_X86_64) +#include "../kernel/xen_entry.S" + +#define __swapgs +#define __cli +#define __sti +#else +/* + * Use the native instructions + */ +#define __swapgs swapgs +#define __cli cli +#define __sti sti +#endif + +/* + * 32bit SYSENTER instruction entry. + * + * Arguments: + * %eax System call number. + * %ebx Arg1 + * %ecx Arg2 + * %edx Arg3 + * %esi Arg4 + * %edi Arg5 + * %ebp user stack + * 0(%ebp) Arg6 + * + * Interrupts off. + * + * This is purely a fast path. For anything complicated we use the int 0x80 + * path below. Set up a complete hardware stack frame to share code + * with the int 0x80 path. + */ +ENTRY(ia32_sysenter_target) + CFI_STARTPROC + __swapgs + movq %gs:pda_kernelstack, %rsp + addq $(PDA_STACKOFFSET),%rsp + XEN_UNBLOCK_EVENTS(%r11) + __sti + movl %ebp,%ebp /* zero extension */ + pushq $__USER32_DS + pushq %rbp + pushfq + movl $VSYSCALL32_SYSEXIT, %r10d + pushq $__USER32_CS + movl %eax, %eax + pushq %r10 + pushq %rax + cld + SAVE_ARGS 0,0,1 + /* no need to do an access_ok check here because rbp has been + 32bit zero extended */ +1: movl (%rbp),%r9d + .section __ex_table,"a" + .quad 1b,ia32_badarg + .previous + GET_THREAD_INFO(%r10) + testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10) + jnz sysenter_tracesys +sysenter_do_call: + cmpl $(IA32_NR_syscalls),%eax + jae ia32_badsys + IA32_ARG_FIXUP 1 + call *ia32_sys_call_table(,%rax,8) + movq %rax,RAX-ARGOFFSET(%rsp) + GET_THREAD_INFO(%r10) + XEN_BLOCK_EVENTS(%r11) + __cli + testl $_TIF_ALLWORK_MASK,threadinfo_flags(%r10) + jnz int_ret_from_sys_call + /* clear IF, that popfq doesn't enable interrupts early */ + andl $~0x200,EFLAGS-R11(%rsp) + RESTORE_ARGS 1,24,1,1,1,1 + popfq + popq %rcx /* User %esp */ + movl $VSYSCALL32_SYSEXIT,%edx /* User %eip */ + __swapgs + XEN_UNBLOCK_EVENTS(%r11) + __sti /* sti only takes effect after the next instruction */ + /* sysexit */ + .byte 0xf, 0x35 /* TBD */ + +sysenter_tracesys: + SAVE_REST + CLEAR_RREGS + movq $-ENOSYS,RAX(%rsp) /* really needed? */ + movq %rsp,%rdi /* &pt_regs -> arg1 */ + call syscall_trace_enter + LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed it */ + RESTORE_REST + movl %ebp, %ebp + /* no need to do an access_ok check here because rbp has been + 32bit zero extended */ +1: movl (%rbp),%r9d + .section __ex_table,"a" + .quad 1b,ia32_badarg + .previous + jmp sysenter_do_call + CFI_ENDPROC + +/* + * 32bit SYSCALL instruction entry. + * + * Arguments: + * %eax System call number. + * %ebx Arg1 + * %ecx return EIP + * %edx Arg3 + * %esi Arg4 + * %edi Arg5 + * %ebp Arg2 [note: not saved in the stack frame, should not be touched] + * %esp user stack + * 0(%esp) Arg6 + * + * Interrupts off. + * + * This is purely a fast path. For anything complicated we use the int 0x80 + * path below. Set up a complete hardware stack frame to share code + * with the int 0x80 path. + */ +ENTRY(ia32_cstar_target) + CFI_STARTPROC + __swapgs + movl %esp,%r8d + movq %gs:pda_kernelstack,%rsp + XEN_UNBLOCK_EVENTS(%r11) + __sti + SAVE_ARGS 8,1,1 + movl %eax,%eax /* zero extension */ + movq %rax,ORIG_RAX-ARGOFFSET(%rsp) + movq %rcx,RIP-ARGOFFSET(%rsp) + movq %rbp,RCX-ARGOFFSET(%rsp) /* this lies slightly to ptrace */ + movl %ebp,%ecx + movq $__USER32_CS,CS-ARGOFFSET(%rsp) + movq $__USER32_DS,SS-ARGOFFSET(%rsp) + movq %r11,EFLAGS-ARGOFFSET(%rsp) + movq %r8,RSP-ARGOFFSET(%rsp) + /* no need to do an access_ok check here because r8 has been + 32bit zero extended */ + /* hardware stack frame is complete now */ +1: movl (%r8),%r9d + .section __ex_table,"a" + .quad 1b,ia32_badarg + .previous + GET_THREAD_INFO(%r10) + testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10) + jnz cstar_tracesys +cstar_do_call: + cmpl $IA32_NR_syscalls,%eax + jae ia32_badsys + IA32_ARG_FIXUP 1 + call *ia32_sys_call_table(,%rax,8) + movq %rax,RAX-ARGOFFSET(%rsp) + GET_THREAD_INFO(%r10) + XEN_BLOCK_EVENTS(%r11) + __cli + testl $_TIF_ALLWORK_MASK,threadinfo_flags(%r10) + jnz int_ret_from_sys_call + RESTORE_ARGS 1,-ARG_SKIP,1,1,1 + movl RIP-ARGOFFSET(%rsp),%ecx + movl EFLAGS-ARGOFFSET(%rsp),%r11d + movl RSP-ARGOFFSET(%rsp),%esp + __swapgs + sysretl /* TBD */ + +cstar_tracesys: + SAVE_REST + CLEAR_RREGS + movq $-ENOSYS,RAX(%rsp) /* really needed? */ + movq %rsp,%rdi /* &pt_regs -> arg1 */ + call syscall_trace_enter + LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed it */ + RESTORE_REST + movl RSP-ARGOFFSET(%rsp), %r8d + /* no need to do an access_ok check here because r8 has been + 32bit zero extended */ +1: movl (%r8),%r9d + .section __ex_table,"a" + .quad 1b,ia32_badarg + .previous + jmp cstar_do_call + +ia32_badarg: + movq $-EFAULT,%rax + jmp ia32_sysret + CFI_ENDPROC + +/* + * Emulated IA32 system calls via int 0x80. + * + * Arguments: + * %eax System call number. + * %ebx Arg1 + * %ecx Arg2 + * %edx Arg3 + * %esi Arg4 + * %edi Arg5 + * %ebp Arg6 [note: not saved in the stack frame, should not be touched] + * + * Notes: + * Uses the same stack frame as the x86-64 version. + * All registers except %eax must be saved (but ptrace may violate that) + * Arguments are zero extended. For system calls that want sign extension and + * take long arguments a wrapper is needed. Most calls can just be called + * directly. + * Assumes it is only called from user space and entered with interrupts off. + */ + +ENTRY(ia32_syscall) + CFI_STARTPROC + __swapgs + XEN_UNBLOCK_EVENTS(%r11) + __sti + movq (%rsp),%rcx + movq 8(%rsp),%r11 + addq $0x10,%rsp /* skip rcx and r11 */ + movl %eax,%eax + pushq %rax + cld +/* 1: jmp 1b */ + /* note the registers are not zero extended to the sf. + this could be a problem. */ + SAVE_ARGS 0,0,1 + GET_THREAD_INFO(%r10) + testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10) + jnz ia32_tracesys +ia32_do_syscall: + cmpl $(IA32_NR_syscalls),%eax + jae ia32_badsys + IA32_ARG_FIXUP + call *ia32_sys_call_table(,%rax,8) # xxx: rip relative +ia32_sysret: + movq %rax,RAX-ARGOFFSET(%rsp) + jmp int_ret_from_sys_call + +ia32_tracesys: + SAVE_REST + movq $-ENOSYS,RAX(%rsp) /* really needed? */ + movq %rsp,%rdi /* &pt_regs -> arg1 */ + call syscall_trace_enter + LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed it */ + RESTORE_REST + jmp ia32_do_syscall + +ia32_badsys: + movq $0,ORIG_RAX-ARGOFFSET(%rsp) + movq $-ENOSYS,RAX-ARGOFFSET(%rsp) + jmp int_ret_from_sys_call + +ni_syscall: + movq %rax,%rdi + jmp sys32_ni_syscall + +quiet_ni_syscall: + movq $-ENOSYS,%rax + ret + CFI_ENDPROC + + .macro PTREGSCALL label, func, arg + .globl \label +\label: + leaq \func(%rip),%rax + leaq -ARGOFFSET+8(%rsp),\arg /* 8 for return address */ + jmp ia32_ptregs_common + .endm + + PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn, %rdi + PTREGSCALL stub32_sigreturn, sys32_sigreturn, %rdi + PTREGSCALL stub32_sigaltstack, sys32_sigaltstack, %rdx + PTREGSCALL stub32_sigsuspend, sys32_sigsuspend, %rcx + PTREGSCALL stub32_execve, sys32_execve, %rcx + PTREGSCALL stub32_fork, sys_fork, %rdi + PTREGSCALL stub32_clone, sys32_clone, %rdx + PTREGSCALL stub32_vfork, sys_vfork, %rdi + PTREGSCALL stub32_iopl, sys_iopl, %rsi + PTREGSCALL stub32_rt_sigsuspend, sys_rt_sigsuspend, %rdx + +ENTRY(ia32_ptregs_common) + CFI_STARTPROC + popq %r11 + SAVE_REST + call *%rax + RESTORE_REST + jmp ia32_sysret /* misbalances the return cache */ + CFI_ENDPROC + + .data + .align 8 + .globl ia32_sys_call_table +ia32_sys_call_table: + .quad sys_restart_syscall + .quad sys_exit + .quad stub32_fork + .quad sys_read + .quad sys_write + .quad sys32_open /* 5 */ + .quad sys_close + .quad sys32_waitpid + .quad sys_creat + .quad sys_link + .quad sys_unlink /* 10 */ + .quad stub32_execve + .quad sys_chdir + .quad compat_sys_time + .quad sys_mknod + .quad sys_chmod /* 15 */ + .quad sys_lchown16 + .quad quiet_ni_syscall /* old break syscall holder */ + .quad sys_stat + .quad sys32_lseek + .quad sys_getpid /* 20 */ + .quad compat_sys_mount /* mount */ + .quad sys_oldumount /* old_umount */ + .quad sys_setuid16 + .quad sys_getuid16 + .quad compat_sys_stime /* stime */ /* 25 */ + .quad sys32_ptrace /* ptrace */ + .quad sys_alarm + .quad sys_fstat /* (old)fstat */ + .quad sys_pause + .quad compat_sys_utime /* 30 */ + .quad quiet_ni_syscall /* old stty syscall holder */ + .quad quiet_ni_syscall /* old gtty syscall holder */ + .quad sys_access + .quad sys_nice + .quad quiet_ni_syscall /* 35 */ /* old ftime syscall holder */ + .quad sys_sync + .quad sys32_kill + .quad sys_rename + .quad sys_mkdir + .quad sys_rmdir /* 40 */ + .quad sys_dup + .quad sys32_pipe + .quad compat_sys_times + .quad quiet_ni_syscall /* old prof syscall holder */ + .quad sys_brk /* 45 */ + .quad sys_setgid16 + .quad sys_getgid16 + .quad sys_signal + .quad sys_geteuid16 + .quad sys_getegid16 /* 50 */ + .quad sys_acct + .quad sys_umount /* new_umount */ + .quad quiet_ni_syscall /* old lock syscall holder */ + .quad compat_sys_ioctl + .quad compat_sys_fcntl64 /* 55 */ + .quad quiet_ni_syscall /* old mpx syscall holder */ + .quad sys_setpgid + .quad quiet_ni_syscall /* old ulimit syscall holder */ + .quad sys32_olduname + .quad sys_umask /* 60 */ + .quad sys_chroot + .quad sys32_ustat + .quad sys_dup2 + .quad sys_getppid + .quad sys_getpgrp /* 65 */ + .quad sys_setsid + .quad sys32_sigaction + .quad sys_sgetmask + .quad sys_ssetmask + .quad sys_setreuid16 /* 70 */ + .quad sys_setregid16 + .quad stub32_sigsuspend + .quad compat_sys_sigpending + .quad sys_sethostname + .quad compat_sys_setrlimit /* 75 */ + .quad compat_sys_old_getrlimit /* old_getrlimit */ + .quad compat_sys_getrusage + .quad sys32_gettimeofday + .quad sys32_settimeofday + .quad sys_getgroups16 /* 80 */ + .quad sys_setgroups16 + .quad sys32_old_select + .quad sys_symlink + .quad sys_lstat + .quad sys_readlink /* 85 */ +#ifdef CONFIG_IA32_AOUT + .quad sys_uselib +#else + .quad quiet_ni_syscall +#endif + .quad sys_swapon + .quad sys_reboot + .quad compat_sys_old_readdir + .quad sys32_mmap /* 90 */ + .quad sys_munmap + .quad sys_truncate + .quad sys_ftruncate + .quad sys_fchmod + .quad sys_fchown16 /* 95 */ + .quad sys_getpriority + .quad sys_setpriority + .quad quiet_ni_syscall /* old profil syscall holder */ + .quad compat_sys_statfs + .quad compat_sys_fstatfs /* 100 */ + .quad sys_ioperm + .quad compat_sys_socketcall + .quad sys_syslog + .quad compat_sys_setitimer + .quad compat_sys_getitimer /* 105 */ + .quad compat_sys_newstat + .quad compat_sys_newlstat + .quad compat_sys_newfstat + .quad sys32_uname + .quad stub32_iopl /* 110 */ + .quad sys_vhangup + .quad quiet_ni_syscall /* old "idle" system call */ + .quad sys32_vm86_warning /* vm86old */ + .quad compat_sys_wait4 + .quad sys_swapoff /* 115 */ + .quad sys32_sysinfo + .quad sys32_ipc + .quad sys_fsync + .quad stub32_sigreturn + .quad stub32_clone /* 120 */ + .quad sys_setdomainname + .quad sys_uname + .quad sys_modify_ldt + .quad sys32_adjtimex + .quad sys32_mprotect /* 125 */ + .quad compat_sys_sigprocmask + .quad quiet_ni_syscall /* create_module */ + .quad sys_init_module + .quad sys_delete_module + .quad quiet_ni_syscall /* 130 get_kernel_syms */ + .quad sys_quotactl + .quad sys_getpgid + .quad sys_fchdir + .quad quiet_ni_syscall /* bdflush */ + .quad sys_sysfs /* 135 */ + .quad sys_personality + .quad quiet_ni_syscall /* for afs_syscall */ + .quad sys_setfsuid16 + .quad sys_setfsgid16 + .quad sys_llseek /* 140 */ + .quad compat_sys_getdents + .quad compat_sys_select + .quad sys_flock + .quad sys_msync + .quad compat_sys_readv /* 145 */ + .quad compat_sys_writev + .quad sys_getsid + .quad sys_fdatasync + .quad sys32_sysctl /* sysctl */ + .quad sys_mlock /* 150 */ + .quad sys_munlock + .quad sys_mlockall + .quad sys_munlockall + .quad sys_sched_setparam + .quad sys_sched_getparam /* 155 */ + .quad sys_sched_setscheduler + .quad sys_sched_getscheduler + .quad sys_sched_yield + .quad sys_sched_get_priority_max + .quad sys_sched_get_priority_min /* 160 */ + .quad sys_sched_rr_get_interval + .quad compat_sys_nanosleep + .quad sys_mremap + .quad sys_setresuid16 + .quad sys_getresuid16 /* 165 */ + .quad sys32_vm86_warning /* vm86 */ + .quad quiet_ni_syscall /* query_module */ + .quad sys_poll + .quad compat_sys_nfsservctl + .quad sys_setresgid16 /* 170 */ + .quad sys_getresgid16 + .quad sys_prctl + .quad stub32_rt_sigreturn + .quad sys32_rt_sigaction + .quad sys32_rt_sigprocmask /* 175 */ + .quad sys32_rt_sigpending + .quad compat_sys_rt_sigtimedwait + .quad sys32_rt_sigqueueinfo + .quad stub32_rt_sigsuspend + .quad sys32_pread /* 180 */ + .quad sys32_pwrite + .quad sys_chown16 + .quad sys_getcwd + .quad sys_capget + .quad sys_capset + .quad stub32_sigaltstack + .quad sys32_sendfile + .quad quiet_ni_syscall /* streams1 */ + .quad quiet_ni_syscall /* streams2 */ + .quad stub32_vfork /* 190 */ + .quad compat_sys_getrlimit + .quad sys32_mmap2 + .quad sys32_truncate64 + .quad sys32_ftruncate64 + .quad sys32_stat64 /* 195 */ + .quad sys32_lstat64 + .quad sys32_fstat64 + .quad sys_lchown + .quad sys_getuid + .quad sys_getgid /* 200 */ + .quad sys_geteuid + .quad sys_getegid + .quad sys_setreuid + .quad sys_setregid + .quad sys_getgroups /* 205 */ + .quad sys_setgroups + .quad sys_fchown + .quad sys_setresuid + .quad sys_getresuid + .quad sys_setresgid /* 210 */ + .quad sys_getresgid + .quad sys_chown + .quad sys_setuid + .quad sys_setgid + .quad sys_setfsuid /* 215 */ + .quad sys_setfsgid + .quad sys_pivot_root + .quad sys_mincore + .quad sys_madvise + .quad compat_sys_getdents64 /* 220 getdents64 */ + .quad compat_sys_fcntl64 + .quad quiet_ni_syscall /* tux */ + .quad quiet_ni_syscall /* security */ + .quad sys_gettid + .quad sys_readahead /* 225 */ + .quad sys_setxattr + .quad sys_lsetxattr + .quad sys_fsetxattr + .quad sys_getxattr + .quad sys_lgetxattr /* 230 */ + .quad sys_fgetxattr + .quad sys_listxattr + .quad sys_llistxattr + .quad sys_flistxattr + .quad sys_removexattr /* 235 */ + .quad sys_lremovexattr + .quad sys_fremovexattr + .quad sys_tkill + .quad sys_sendfile64 + .quad compat_sys_futex /* 240 */ + .quad compat_sys_sched_setaffinity + .quad compat_sys_sched_getaffinity + .quad sys32_set_thread_area + .quad sys32_get_thread_area + .quad compat_sys_io_setup /* 245 */ + .quad sys_io_destroy + .quad compat_sys_io_getevents + .quad compat_sys_io_submit + .quad sys_io_cancel + .quad sys_fadvise64 /* 250 */ + .quad quiet_ni_syscall /* free_huge_pages */ + .quad sys_exit_group + .quad sys32_lookup_dcookie + .quad sys_epoll_create + .quad sys_epoll_ctl /* 255 */ + .quad sys_epoll_wait + .quad sys_remap_file_pages + .quad sys_set_tid_address + .quad sys32_timer_create + .quad compat_sys_timer_settime /* 260 */ + .quad compat_sys_timer_gettime + .quad sys_timer_getoverrun + .quad sys_timer_delete + .quad compat_sys_clock_settime + .quad compat_sys_clock_gettime /* 265 */ + .quad compat_sys_clock_getres + .quad compat_sys_clock_nanosleep + .quad compat_sys_statfs64 + .quad compat_sys_fstatfs64 + .quad sys_tgkill /* 270 */ + .quad compat_sys_utimes + .quad sys32_fadvise64_64 + .quad quiet_ni_syscall /* sys_vserver */ + .quad sys_mbind + .quad compat_sys_get_mempolicy /* 275 */ + .quad sys_set_mempolicy + .quad compat_sys_mq_open + .quad sys_mq_unlink + .quad compat_sys_mq_timedsend + .quad compat_sys_mq_timedreceive /* 280 */ + .quad compat_sys_mq_notify + .quad compat_sys_mq_getsetattr + .quad quiet_ni_syscall /* reserved for kexec */ + .quad compat_sys_waitid + .quad quiet_ni_syscall /* sys_altroot */ + .quad sys_add_key + .quad sys_request_key + .quad sys_keyctl + /* don't forget to change IA32_NR_syscalls */ +ia32_syscall_end: + .rept IA32_NR_syscalls-(ia32_syscall_end-ia32_sys_call_table)/8 + .quad ni_syscall + .endr diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/ia32/syscall32-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/ia32/syscall32-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,153 @@ +/* Copyright 2002,2003 Andi Kleen, SuSE Labs */ + +/* vsyscall handling for 32bit processes. Map a stub page into it + on demand because 32bit cannot reach the kernel's fixmaps */ + +#include <linux/mm.h> +#include <linux/string.h> +#include <linux/kernel.h> +#include <linux/gfp.h> +#include <linux/init.h> +#include <linux/stringify.h> +#include <linux/security.h> +#include <asm/proto.h> +#include <asm/tlbflush.h> +#include <asm/ia32_unistd.h> + +#define USE_INT80 + +#ifdef USE_INT80 +/* 32bit VDSOs mapped into user space. */ +asm(".section \".init.data\",\"aw\"\n" + "syscall32_int80:\n" + ".incbin \"arch/x86_64/ia32/vsyscall-int80.so\"\n" + "syscall32_int80_end:\n" + "syscall32_syscall:\n" + ".incbin \"arch/x86_64/ia32/vsyscall-syscall.so\"\n" + "syscall32_syscall_end:\n" + "syscall32_sysenter:\n" + ".incbin \"arch/x86_64/ia32/vsyscall-sysenter.so\"\n" + "syscall32_sysenter_end:\n" + ".previous"); + +extern unsigned char syscall32_int80[], syscall32_int80_end[]; +#else +/* 32bit VDSOs mapped into user space. */ +asm(".section \".init.data\",\"aw\"\n" + "syscall32_syscall:\n" + ".incbin \"arch/x86_64/ia32/vsyscall-syscall.so\"\n" + "syscall32_syscall_end:\n" + "syscall32_sysenter:\n" + ".incbin \"arch/x86_64/ia32/vsyscall-sysenter.so\"\n" + "syscall32_sysenter_end:\n" + ".previous"); + +static int use_sysenter = -1; +#endif + +extern unsigned char syscall32_syscall[], syscall32_syscall_end[]; +extern unsigned char syscall32_sysenter[], syscall32_sysenter_end[]; +extern int sysctl_vsyscall32; + +char *syscall32_page; + +static struct page * +syscall32_nopage(struct vm_area_struct *vma, unsigned long adr, int *type) +{ + struct page *p = virt_to_page(adr - vma->vm_start + syscall32_page); + get_page(p); + return p; +} + +/* Prevent VMA merging */ +static void syscall32_vma_close(struct vm_area_struct *vma) +{ +} + +static struct vm_operations_struct syscall32_vm_ops = { + .close = syscall32_vma_close, + .nopage = syscall32_nopage, +}; + +struct linux_binprm; + +/* Setup a VMA at program startup for the vsyscall page */ +int syscall32_setup_pages(struct linux_binprm *bprm, int exstack) +{ + int npages = (VSYSCALL32_END - VSYSCALL32_BASE) >> PAGE_SHIFT; + struct vm_area_struct *vma; + struct mm_struct *mm = current->mm; + + vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL); + if (!vma) + return -ENOMEM; + if (security_vm_enough_memory(npages)) { + kmem_cache_free(vm_area_cachep, vma); + return -ENOMEM; + } + + memset(vma, 0, sizeof(struct vm_area_struct)); + /* Could randomize here */ + vma->vm_start = VSYSCALL32_BASE; + vma->vm_end = VSYSCALL32_END; + /* MAYWRITE to allow gdb to COW and set breakpoints */ + vma->vm_flags = VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYEXEC|VM_MAYEXEC|VM_MAYWRITE; + vma->vm_flags |= mm->def_flags; + vma->vm_page_prot = protection_map[vma->vm_flags & 7]; + vma->vm_ops = &syscall32_vm_ops; + vma->vm_mm = mm; + + down_write(&mm->mmap_sem); + insert_vm_struct(mm, vma); + mm->total_vm += npages; + up_write(&mm->mmap_sem); + return 0; +} + +static int __init init_syscall32(void) +{ + syscall32_page = (void *)get_zeroed_page(GFP_KERNEL); + if (!syscall32_page) + panic("Cannot allocate syscall32 page"); + +#ifdef USE_INT80 + /* + * At this point we use int 0x80. + */ + memcpy(syscall32_page, syscall32_int80, + syscall32_int80_end - syscall32_int80); +#else + + if (use_sysenter > 0) { + memcpy(syscall32_page, syscall32_sysenter, + syscall32_sysenter_end - syscall32_sysenter); + } else { + memcpy(syscall32_page, syscall32_syscall, + syscall32_syscall_end - syscall32_syscall); + } +#endif + return 0; +} + +/* + * This must be done early in case we have an initrd containing 32-bit + * binaries (e.g., hotplug). This could be pushed upstream to arch/x86_64. + */ +core_initcall(init_syscall32); + +/* May not be __init: called during resume */ +void syscall32_cpu_init(void) +{ +#ifndef USE_INT80 + if (use_sysenter < 0) + use_sysenter = (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL); + + /* Load these always in case some future AMD CPU supports + SYSENTER from compat mode too. */ + checking_wrmsrl(MSR_IA32_SYSENTER_CS, (u64)(__KERNEL_CS | 3)); + checking_wrmsrl(MSR_IA32_SYSENTER_ESP, 0ULL); + checking_wrmsrl(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); + + wrmsrl(MSR_CSTAR, ia32_cstar_target); +#endif +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/ia32/vsyscall-int80.S --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/ia32/vsyscall-int80.S Mon Jan 30 17:18:27 2006 @@ -0,0 +1,57 @@ +/* + * Code for the vsyscall page. This version uses the old int $0x80 method. + * + * NOTE: + * 1) __kernel_vsyscall _must_ be first in this page. + * 2) there are alignment constraints on this stub, see vsyscall-sigreturn.S + * for details. + */ +#include <asm/ia32_unistd.h> +#include <asm/offset.h> + + .text + .section .text.vsyscall,"ax" + .globl __kernel_vsyscall + .type __kernel_vsyscall,@function +__kernel_vsyscall: +.LSTART_vsyscall: + int $0x80 + ret +.LEND_vsyscall: + .size __kernel_vsyscall,.-.LSTART_vsyscall + .previous + + .section .eh_frame,"a",@progbits +.LSTARTFRAME: + .long .LENDCIE-.LSTARTCIE +.LSTARTCIE: + .long 0 /* CIE ID */ + .byte 1 /* Version number */ + .string "zR" /* NUL-terminated augmentation string */ + .uleb128 1 /* Code alignment factor */ + .sleb128 -4 /* Data alignment factor */ + .byte 8 /* Return address register column */ + .uleb128 1 /* Augmentation value length */ + .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */ + .byte 0x0c /* DW_CFA_def_cfa */ + .uleb128 4 + .uleb128 4 + .byte 0x88 /* DW_CFA_offset, column 0x8 */ + .uleb128 1 + .align 4 +.LENDCIE: + + .long .LENDFDE1-.LSTARTFDE1 /* Length FDE */ +.LSTARTFDE1: + .long .LSTARTFDE1-.LSTARTFRAME /* CIE pointer */ + .long .LSTART_vsyscall-. /* PC-relative start address */ + .long .LEND_vsyscall-.LSTART_vsyscall + .uleb128 0 /* Augmentation length */ + .align 4 +.LENDFDE1: + +/* + * Get the common code for the sigreturn entry points. + */ +#define SYSCALL_ENTER_KERNEL int $0x80 +#include "vsyscall-sigreturn.S" diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/Makefile --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/Makefile Mon Jan 30 17:18:27 2006 @@ -0,0 +1,63 @@ +# +# Makefile for the linux kernel. +# + +extra-y := head.o head64.o init_task.o vmlinux.lds +EXTRA_AFLAGS := -traditional +obj-y := process.o semaphore.o signal.o entry.o traps.o irq.o \ + ptrace.o time.o ioport.o ldt.o setup.o i8259.o sys_x86_64.o \ + x8664_ksyms.o i387.o syscall.o vsyscall.o \ + setup64.o bootflag.o e820.o reboot.o quirks.o + +obj-$(CONFIG_X86_MCE) += mce.o +obj-$(CONFIG_X86_MCE_INTEL) += mce_intel.o +obj-$(CONFIG_MTRR) += ../../i386/kernel/cpu/mtrr/ +obj-$(CONFIG_ACPI_BOOT) += acpi/ +obj-$(CONFIG_X86_MSR) += msr.o +obj-$(CONFIG_MICROCODE) += microcode.o +obj-$(CONFIG_X86_CPUID) += cpuid.o +obj-$(CONFIG_SMP) += smp.o smpboot.o trampoline.o +obj-$(CONFIG_X86_LOCAL_APIC) += apic.o nmi.o +obj-$(CONFIG_X86_XEN_GENAPIC) += genapic.o genapic_xen.o +obj-$(CONFIG_X86_IO_APIC) += io_apic.o mpparse.o \ + genapic.o genapic_cluster.o genapic_flat.o +obj-$(CONFIG_PM) += suspend.o +obj-$(CONFIG_SOFTWARE_SUSPEND) += suspend_asm.o +obj-$(CONFIG_CPU_FREQ) += cpufreq/ +obj-$(CONFIG_EARLY_PRINTK) += early_printk.o +obj-$(CONFIG_GART_IOMMU) += pci-gart.o aperture.o +obj-$(CONFIG_DUMMY_IOMMU) += pci-nommu.o pci-dma.o +obj-$(CONFIG_SWIOTLB) += swiotlb.o +obj-$(CONFIG_KPROBES) += kprobes.o +obj-$(CONFIG_X86_PM_TIMER) += pmtimer.o + +obj-$(CONFIG_MODULES) += module.o + +obj-y += topology.o +obj-y += intel_cacheinfo.o + +CFLAGS_vsyscall.o := $(PROFILING) -g0 + +bootflag-y += ../../i386/kernel/bootflag.o +cpuid-$(subst m,y,$(CONFIG_X86_CPUID)) += ../../i386/kernel/cpuid.o +topology-y += ../../i386/mach-default/topology.o +swiotlb-$(CONFIG_SWIOTLB) += ../../ia64/lib/swiotlb.o +microcode-$(subst m,y,$(CONFIG_MICROCODE)) += ../../i386/kernel/microcode.o +intel_cacheinfo-y += ../../i386/kernel/cpu/intel_cacheinfo.o +quirks-y += ../../i386/kernel/quirks.o + +ifdef CONFIG_XEN +time-y += ../../i386/kernel/time-xen.o +swiotlb-$(CONFIG_SWIOTLB) := ../../i386/kernel/swiotlb.o +pci-dma-y += ../../i386/kernel/pci-dma-xen.o +microcode-$(subst m,y,$(CONFIG_MICROCODE)) := ../../i386/kernel/microcode-xen.o +quirks-y := ../../i386/kernel/quirks-xen.o + +n-obj-xen := i8259.o reboot.o smpboot.o trampoline.o + +include $(srctree)/scripts/Makefile.xen + +obj-y := $(call filterxen, $(obj-y), $(n-obj-xen)) +obj-y := $(call cherrypickxen, $(obj-y)) +extra-y := $(call cherrypickxen, $(extra-y)) +endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/acpi/Makefile --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/acpi/Makefile Mon Jan 30 17:18:27 2006 @@ -0,0 +1,5 @@ +obj-$(CONFIG_ACPI_BOOT) := boot.o +boot-$(CONFIG_ACPI_BOOT) := ../../../i386/kernel/acpi/boot.o +obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup.o + +boot-$(CONFIG_XEN) := ../../../i386/kernel/acpi/boot-xen.o diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/apic-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/apic-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,201 @@ +/* + * Local APIC handling, local APIC timers + * + * (c) 1999, 2000 Ingo Molnar <mingo@xxxxxxxxxx> + * + * Fixes + * Maciej W. Rozycki : Bits for genuine 82489DX APICs; + * thanks to Eric Gilmore + * and Rolf G. Tews + * for testing these extensively. + * Maciej W. Rozycki : Various updates and fixes. + * Mikael Pettersson : Power Management for UP-APIC. + * Pavel Machek and + * Mikael Pettersson : PM converted to driver model. + */ + +#include <linux/config.h> +#include <linux/init.h> + +#include <linux/mm.h> +#include <linux/irq.h> +#include <linux/delay.h> +#include <linux/bootmem.h> +#include <linux/smp_lock.h> +#include <linux/interrupt.h> +#include <linux/mc146818rtc.h> +#include <linux/kernel_stat.h> +#include <linux/sysdev.h> + +#include <asm/atomic.h> +#include <asm/smp.h> +#include <asm/mtrr.h> +#include <asm/mpspec.h> +#include <asm/desc.h> +#include <asm/arch_hooks.h> +#include <asm/hpet.h> + +#include "io_ports.h" + +/* + * Debug level + */ +int apic_verbosity; +int disable_apic; + +void smp_local_timer_interrupt(struct pt_regs *regs) +{ + + profile_tick(CPU_PROFILING, regs); +#ifndef CONFIG_XEN + int cpu = smp_processor_id(); + + if (--per_cpu(prof_counter, cpu) <= 0) { + /* + * The multiplier may have changed since the last time we got + * to this point as a result of the user writing to + * /proc/profile. In this case we need to adjust the APIC + * timer accordingly. + * + * Interrupts are already masked off at this point. + */ + per_cpu(prof_counter, cpu) = per_cpu(prof_multiplier, cpu); + if (per_cpu(prof_counter, cpu) != + per_cpu(prof_old_multiplier, cpu)) { + __setup_APIC_LVTT(calibration_result/ + per_cpu(prof_counter, cpu)); + per_cpu(prof_old_multiplier, cpu) = + per_cpu(prof_counter, cpu); + } + +#ifdef CONFIG_SMP + update_process_times(user_mode(regs)); +#endif + } +#endif + + /* + * We take the 'long' return path, and there every subsystem + * grabs the appropriate locks (kernel lock/ irq lock). + * + * we might want to decouple profiling from the 'long path', + * and do the profiling totally in assembly. + * + * Currently this isn't too much of an issue (performance wise), + * we can take more than 100K local irqs per second on a 100 MHz P5. + */ +} + +/* + * Local APIC timer interrupt. This is the most natural way for doing + * local interrupts, but local timer interrupts can be emulated by + * broadcast interrupts too. [in case the hw doesn't support APIC timers] + * + * [ if a single-CPU system runs an SMP kernel then we call the local + * interrupt as well. Thus we cannot inline the local irq ... ] + */ +void smp_apic_timer_interrupt(struct pt_regs *regs) +{ + /* + * the NMI deadlock-detector uses this. + */ + add_pda(apic_timer_irqs, 1); + + /* + * NOTE! We'd better ACK the irq immediately, + * because timer handling can be slow. + */ + ack_APIC_irq(); + /* + * update_process_times() expects us to have done irq_enter(). + * Besides, if we don't timer interrupts ignore the global + * interrupt lock, which is the WrongThing (tm) to do. + */ + irq_enter(); + smp_local_timer_interrupt(regs); + irq_exit(); +} + +/* + * This interrupt should _never_ happen with our APIC/SMP architecture + */ +asmlinkage void smp_spurious_interrupt(void) +{ + unsigned int v; + irq_enter(); + /* + * Check if this really is a spurious interrupt and ACK it + * if it is a vectored one. Just in case... + * Spurious interrupts should not be ACKed. + */ + v = apic_read(APIC_ISR + ((SPURIOUS_APIC_VECTOR & ~0x1f) >> 1)); + if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f))) + ack_APIC_irq(); + +#if 0 + static unsigned long last_warning; + static unsigned long skipped; + + /* see sw-dev-man vol 3, chapter 7.4.13.5 */ + if (time_before(last_warning+30*HZ,jiffies)) { + printk(KERN_INFO "spurious APIC interrupt on CPU#%d, %ld skipped.\n", + smp_processor_id(), skipped); + last_warning = jiffies; + skipped = 0; + } else { + skipped++; + } +#endif + irq_exit(); +} + +/* + * This interrupt should never happen with our APIC/SMP architecture + */ + +asmlinkage void smp_error_interrupt(void) +{ + unsigned int v, v1; + + irq_enter(); + /* First tickle the hardware, only then report what went on. -- REW */ + v = apic_read(APIC_ESR); + apic_write(APIC_ESR, 0); + v1 = apic_read(APIC_ESR); + ack_APIC_irq(); + atomic_inc(&irq_err_count); + + /* Here is what the APIC error bits mean: + 0: Send CS error + 1: Receive CS error + 2: Send accept error + 3: Receive accept error + 4: Reserved + 5: Send illegal vector + 6: Received illegal vector + 7: Illegal register address + */ + printk (KERN_DEBUG "APIC error on CPU%d: %02x(%02x)\n", + smp_processor_id(), v , v1); + irq_exit(); +} + +int get_physical_broadcast(void) +{ + return 0xff; +} + +/* + * This initializes the IO-APIC and APIC hardware if this is + * a UP kernel. + */ +int __init APIC_init_uniprocessor (void) +{ +#ifdef CONFIG_X86_IO_APIC + if (smp_found_config) + if (!skip_ioapic_setup && nr_ioapics) + setup_IO_APIC(); +#endif + + return 0; +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/e820-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/e820-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,676 @@ +/* + * Handle the memory map. + * The functions here do the job until bootmem takes over. + * $Id: e820.c,v 1.4 2002/09/19 19:25:32 ak Exp $ + * + * Getting sanitize_e820_map() in sync with i386 version by applying change: + * - Provisions for empty E820 memory regions (reported by certain BIOSes). + * Alex Achenbach <xela@xxxxxxx>, December 2002. + * Venkatesh Pallipadi <venkatesh.pallipadi@xxxxxxxxx> + * + */ +#include <linux/config.h> +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/init.h> +#include <linux/bootmem.h> +#include <linux/ioport.h> +#include <linux/string.h> +#include <asm/page.h> +#include <asm/e820.h> +#include <asm/proto.h> +#include <asm/bootsetup.h> +#include <xen/interface/memory.h> + +unsigned long pci_mem_start = 0xaeedbabe; + +/* + * PFN of last memory page. + */ +unsigned long end_pfn; +unsigned long end_user_pfn = MAXMEM>>PAGE_SHIFT; +unsigned long end_pfn_map; + +/* + * Add a memory region to the kernel e820 map. + */ +void __init add_memory_region(unsigned long start, unsigned long size, int type) +{ + int x = e820.nr_map; + + if (x == E820MAX) { + printk(KERN_ERR "Ooops! Too many entries in the memory map!\n"); + return; + } + + e820.map[x].addr = start; + e820.map[x].size = size; + e820.map[x].type = type; + e820.nr_map++; +} + +#ifndef CONFIG_XEN +extern char _end[]; + +/* + * end_pfn only includes RAM, while end_pfn_map includes all e820 entries. + * The direct mapping extends to end_pfn_map, so that we can directly access + * apertures, ACPI and other tables without having to play with fixmaps. + */ + +/* + * Last pfn which the user wants to use. + */ + +extern struct resource code_resource, data_resource; + +/* Check for some hardcoded bad areas that early boot is not allowed to touch */ +static inline int bad_addr(unsigned long *addrp, unsigned long size) +{ + unsigned long addr = *addrp, last = addr + size; + + /* various gunk below that needed for SMP startup */ + if (addr < 0x8000) { + *addrp = 0x8000; + return 1; + } + + /* direct mapping tables of the kernel */ + if (last >= table_start<<PAGE_SHIFT && addr < table_end<<PAGE_SHIFT) { + *addrp = table_end << PAGE_SHIFT; + return 1; + } + + /* initrd */ +#ifdef CONFIG_BLK_DEV_INITRD + if (LOADER_TYPE && INITRD_START && last >= INITRD_START && + addr < INITRD_START+INITRD_SIZE) { + *addrp = INITRD_START + INITRD_SIZE; + return 1; + } +#endif + /* kernel code + 640k memory hole (later should not be needed, but + be paranoid for now) */ + if (last >= 640*1024 && addr < __pa_symbol(&_end)) { + *addrp = __pa_symbol(&_end); + return 1; + } + /* XXX ramdisk image here? */ + return 0; +} + +int __init e820_mapped(unsigned long start, unsigned long end, unsigned type) +{ + int i; + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + if (type && ei->type != type) + continue; + if (ei->addr >= end || ei->addr + ei->size < start) + continue; + return 1; + } + return 0; +} + +/* + * Find a free area in a specific range. + */ +unsigned long __init find_e820_area(unsigned long start, unsigned long end, unsigned size) +{ + int i; + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + unsigned long addr = ei->addr, last; + if (ei->type != E820_RAM) + continue; + if (addr < start) + addr = start; + if (addr > ei->addr + ei->size) + continue; + while (bad_addr(&addr, size) && addr+size < ei->addr + ei->size) + ; + last = addr + size; + if (last > ei->addr + ei->size) + continue; + if (last > end) + continue; + return addr; + } + return -1UL; +} + +/* + * Free bootmem based on the e820 table for a node. + */ +void __init e820_bootmem_free(pg_data_t *pgdat, unsigned long start,unsigned long end) +{ + int i; + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + unsigned long last, addr; + + if (ei->type != E820_RAM || + ei->addr+ei->size <= start || + ei->addr > end) + continue; + + addr = round_up(ei->addr, PAGE_SIZE); + if (addr < start) + addr = start; + + last = round_down(ei->addr + ei->size, PAGE_SIZE); + if (last >= end) + last = end; + + if (last > addr && last-addr >= PAGE_SIZE) + free_bootmem_node(pgdat, addr, last-addr); + } +} + +/* + * Find the highest page frame number we have available + */ +unsigned long __init e820_end_of_ram(void) +{ + int i; + unsigned long end_pfn = 0; + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + unsigned long start, end; + + start = round_up(ei->addr, PAGE_SIZE); + end = round_down(ei->addr + ei->size, PAGE_SIZE); + if (start >= end) + continue; + if (ei->type == E820_RAM) { + if (end > end_pfn<<PAGE_SHIFT) + end_pfn = end>>PAGE_SHIFT; + } else { + if (end > end_pfn_map<<PAGE_SHIFT) + end_pfn_map = end>>PAGE_SHIFT; + } + } + + if (end_pfn > end_pfn_map) + end_pfn_map = end_pfn; + if (end_pfn_map > MAXMEM>>PAGE_SHIFT) + end_pfn_map = MAXMEM>>PAGE_SHIFT; + if (end_pfn > end_user_pfn) + end_pfn = end_user_pfn; + if (end_pfn > end_pfn_map) + end_pfn = end_pfn_map; + + return end_pfn; +} + +/* + * Mark e820 reserved areas as busy for the resource manager. + */ +void __init e820_reserve_resources(void) +{ + int i; + for (i = 0; i < e820.nr_map; i++) { + struct resource *res; + if (e820.map[i].addr + e820.map[i].size > 0x100000000ULL) + continue; + res = alloc_bootmem_low(sizeof(struct resource)); + switch (e820.map[i].type) { + case E820_RAM: res->name = "System RAM"; break; + case E820_ACPI: res->name = "ACPI Tables"; break; + case E820_NVS: res->name = "ACPI Non-volatile Storage"; break; + default: res->name = "reserved"; + } + res->start = e820.map[i].addr; + res->end = res->start + e820.map[i].size - 1; + res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + request_resource(&iomem_resource, res); + if (e820.map[i].type == E820_RAM) { + /* + * We don't know which RAM region contains kernel data, + * so we try it repeatedly and let the resource manager + * test it. + */ + request_resource(res, &code_resource); + request_resource(res, &data_resource); + } + } +} + +void __init e820_print_map(char *who) +{ + int i; + + for (i = 0; i < e820.nr_map; i++) { + printk(" %s: %016Lx - %016Lx ", who, + (unsigned long long) e820.map[i].addr, + (unsigned long long) (e820.map[i].addr + e820.map[i].size)); + switch (e820.map[i].type) { + case E820_RAM: printk("(usable)\n"); + break; + case E820_RESERVED: + printk("(reserved)\n"); + break; + case E820_ACPI: + printk("(ACPI data)\n"); + break; + case E820_NVS: + printk("(ACPI NVS)\n"); + break; + default: printk("type %u\n", e820.map[i].type); + break; + } + } +} + +/* + * Sanitize the BIOS e820 map. + * + * Some e820 responses include overlapping entries. The following + * replaces the original e820 map with a new one, removing overlaps. + * + */ +static int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map) +{ + struct change_member { + struct e820entry *pbios; /* pointer to original bios entry */ + unsigned long long addr; /* address for this change point */ + }; + static struct change_member change_point_list[2*E820MAX] __initdata; + static struct change_member *change_point[2*E820MAX] __initdata; + static struct e820entry *overlap_list[E820MAX] __initdata; + static struct e820entry new_bios[E820MAX] __initdata; + struct change_member *change_tmp; + unsigned long current_type, last_type; + unsigned long long last_addr; + int chgidx, still_changing; + int overlap_entries; + int new_bios_entry; + int old_nr, new_nr, chg_nr; + int i; + + /* + Visually we're performing the following (1,2,3,4 = memory types)... + + Sample memory map (w/overlaps): + ____22__________________ + ______________________4_ + ____1111________________ + _44_____________________ + 11111111________________ + ____________________33__ + ___________44___________ + __________33333_________ + ______________22________ + ___________________2222_ + _________111111111______ + _____________________11_ + _________________4______ + + Sanitized equivalent (no overlap): + 1_______________________ + _44_____________________ + ___1____________________ + ____22__________________ + ______11________________ + _________1______________ + __________3_____________ + ___________44___________ + _____________33_________ + _______________2________ + ________________1_______ + _________________4______ + ___________________2____ + ____________________33__ + ______________________4_ + */ + + /* if there's only one memory region, don't bother */ + if (*pnr_map < 2) + return -1; + + old_nr = *pnr_map; + + /* bail out if we find any unreasonable addresses in bios map */ + for (i=0; i<old_nr; i++) + if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr) + return -1; + + /* create pointers for initial change-point information (for sorting) */ + for (i=0; i < 2*old_nr; i++) + change_point[i] = &change_point_list[i]; + + /* record all known change-points (starting and ending addresses), + omitting those that are for empty memory regions */ + chgidx = 0; + for (i=0; i < old_nr; i++) { + if (biosmap[i].size != 0) { + change_point[chgidx]->addr = biosmap[i].addr; + change_point[chgidx++]->pbios = &biosmap[i]; + change_point[chgidx]->addr = biosmap[i].addr + biosmap[i].size; + change_point[chgidx++]->pbios = &biosmap[i]; + } + } + chg_nr = chgidx; + + /* sort change-point list by memory addresses (low -> high) */ + still_changing = 1; + while (still_changing) { + still_changing = 0; + for (i=1; i < chg_nr; i++) { + /* if <current_addr> > <last_addr>, swap */ + /* or, if current=<start_addr> & last=<end_addr>, swap */ + if ((change_point[i]->addr < change_point[i-1]->addr) || + ((change_point[i]->addr == change_point[i-1]->addr) && + (change_point[i]->addr == change_point[i]->pbios->addr) && + (change_point[i-1]->addr != change_point[i-1]->pbios->addr)) + ) + { + change_tmp = change_point[i]; + change_point[i] = change_point[i-1]; + change_point[i-1] = change_tmp; + still_changing=1; + } + } + } + + /* create a new bios memory map, removing overlaps */ + overlap_entries=0; /* number of entries in the overlap table */ + new_bios_entry=0; /* index for creating new bios map entries */ + last_type = 0; /* start with undefined memory type */ + last_addr = 0; /* start with 0 as last starting address */ + /* loop through change-points, determining affect on the new bios map */ + for (chgidx=0; chgidx < chg_nr; chgidx++) + { + /* keep track of all overlapping bios entries */ + if (change_point[chgidx]->addr == change_point[chgidx]->pbios->addr) + { + /* add map entry to overlap list (> 1 entry implies an overlap) */ + overlap_list[overlap_entries++]=change_point[chgidx]->pbios; + } + else + { + /* remove entry from list (order independent, so swap with last) */ + for (i=0; i<overlap_entries; i++) + { + if (overlap_list[i] == change_point[chgidx]->pbios) + overlap_list[i] = overlap_list[overlap_entries-1]; + } + overlap_entries--; + } + /* if there are overlapping entries, decide which "type" to use */ + /* (larger value takes precedence -- 1=usable, 2,3,4,4+=unusable) */ + current_type = 0; + for (i=0; i<overlap_entries; i++) + if (overlap_list[i]->type > current_type) + current_type = overlap_list[i]->type; + /* continue building up new bios map based on this information */ + if (current_type != last_type) { + if (last_type != 0) { + new_bios[new_bios_entry].size = + change_point[chgidx]->addr - last_addr; + /* move forward only if the new size was non-zero */ + if (new_bios[new_bios_entry].size != 0) + if (++new_bios_entry >= E820MAX) + break; /* no more space left for new bios entries */ + } + if (current_type != 0) { + new_bios[new_bios_entry].addr = change_point[chgidx]->addr; + new_bios[new_bios_entry].type = current_type; + last_addr=change_point[chgidx]->addr; + } + last_type = current_type; + } + } + new_nr = new_bios_entry; /* retain count for new bios entries */ + + /* copy new bios mapping into original location */ + memcpy(biosmap, new_bios, new_nr*sizeof(struct e820entry)); + *pnr_map = new_nr; + + return 0; +} + +/* + * Copy the BIOS e820 map into a safe place. + * + * Sanity-check it while we're at it.. + * + * If we're lucky and live on a modern system, the setup code + * will have given us a memory map that we can use to properly + * set up memory. If we aren't, we'll fake a memory map. + * + * We check to see that the memory map contains at least 2 elements + * before we'll use it, because the detection code in setup.S may + * not be perfect and most every PC known to man has two memory + * regions: one from 0 to 640k, and one from 1mb up. (The IBM + * thinkpad 560x, for example, does not cooperate with the memory + * detection code.) + */ +static int __init copy_e820_map(struct e820entry * biosmap, int nr_map) +{ + /* Only one memory region (or negative)? Ignore it */ + if (nr_map < 2) + return -1; + + do { + unsigned long start = biosmap->addr; + unsigned long size = biosmap->size; + unsigned long end = start + size; + unsigned long type = biosmap->type; + + /* Overflow in 64 bits? Ignore the memory map. */ + if (start > end) + return -1; + + /* + * Some BIOSes claim RAM in the 640k - 1M region. + * Not right. Fix it up. + * + * This should be removed on Hammer which is supposed to not + * have non e820 covered ISA mappings there, but I had some strange + * problems so it stays for now. -AK + */ + if (type == E820_RAM) { + if (start < 0x100000ULL && end > 0xA0000ULL) { + if (start < 0xA0000ULL) + add_memory_region(start, 0xA0000ULL-start, type); + if (end <= 0x100000ULL) + continue; + start = 0x100000ULL; + size = end - start; + } + } + + add_memory_region(start, size, type); + } while (biosmap++,--nr_map); + return 0; +} + +void __init setup_memory_region(void) +{ + char *who = "BIOS-e820"; + + /* + * Try to copy the BIOS-supplied E820-map. + * + * Otherwise fake a memory map; one section from 0k->640k, + * the next section from 1mb->appropriate_mem_k + */ + sanitize_e820_map(E820_MAP, &E820_MAP_NR); + if (copy_e820_map(E820_MAP, E820_MAP_NR) < 0) { + unsigned long mem_size; + + /* compare results from other methods and take the greater */ + if (ALT_MEM_K < EXT_MEM_K) { + mem_size = EXT_MEM_K; + who = "BIOS-88"; + } else { + mem_size = ALT_MEM_K; + who = "BIOS-e801"; + } + + e820.nr_map = 0; + add_memory_region(0, LOWMEMSIZE(), E820_RAM); + add_memory_region(HIGH_MEMORY, mem_size << 10, E820_RAM); + } + printk(KERN_INFO "BIOS-provided physical RAM map:\n"); + e820_print_map(who); +} + +#else /* CONFIG_XEN */ + +extern unsigned long xen_override_max_pfn; +extern union xen_start_info_union xen_start_info_union; + +unsigned long __init e820_end_of_ram(void) +{ + unsigned long max_end_pfn; + + if (xen_override_max_pfn == 0) { + max_end_pfn = xen_start_info->nr_pages; + /* Default 8MB slack (to balance backend allocations). */ + max_end_pfn += 8 << (20 - PAGE_SHIFT); + } else if (xen_override_max_pfn > xen_start_info->nr_pages) { + max_end_pfn = xen_override_max_pfn; + } else { + max_end_pfn = xen_start_info->nr_pages; + } + + return max_end_pfn; +} + +void __init e820_reserve_resources(void) +{ + dom0_op_t op; + struct dom0_memory_map_entry *map; + unsigned long gapstart, gapsize, last; + int i, found = 0; + + if (!(xen_start_info->flags & SIF_INITDOMAIN)) + return; + + map = alloc_bootmem_low_pages(PAGE_SIZE); + op.cmd = DOM0_PHYSICAL_MEMORY_MAP; + op.u.physical_memory_map.memory_map = map; + op.u.physical_memory_map.max_map_entries = + PAGE_SIZE / sizeof(struct dom0_memory_map_entry); + BUG_ON(HYPERVISOR_dom0_op(&op)); + + last = 0x100000000ULL; + gapstart = 0x10000000; + gapsize = 0x400000; + + for (i = op.u.physical_memory_map.nr_map_entries - 1; i >= 0; i--) { + struct resource *res; + + if ((last > map[i].end) && ((last - map[i].end) > gapsize)) { + gapsize = last - map[i].end; + gapstart = map[i].end; + found = 1; + } + if (map[i].start < last) + last = map[i].start; + + if (map[i].end > 0x100000000ULL) + continue; + res = alloc_bootmem_low(sizeof(struct resource)); + res->name = map[i].is_ram ? "System RAM" : "reserved"; + res->start = map[i].start; + res->end = map[i].end - 1; + res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + request_resource(&iomem_resource, res); + } + + free_bootmem(__pa(map), PAGE_SIZE); + + if (!found) { + gapstart = HYPERVISOR_memory_op(XENMEM_maximum_ram_page, NULL); + gapstart = (gapstart << PAGE_SHIFT) + 1024*1024; + printk(KERN_ERR "PCI: Warning: Cannot find a gap in the 32bit address range\n" + KERN_ERR "PCI: Unassigned devices with 32bit resource registers may break!\n"); + } + + /* + * Start allocating dynamic PCI memory a bit into the gap, + * aligned up to the nearest megabyte. + * + * Question: should we try to pad it up a bit (do something + * like " + (gapsize >> 3)" in there too?). We now have the + * technology. + */ + pci_mem_start = (gapstart + 0xfffff) & ~0xfffff; + + printk(KERN_INFO "Allocating PCI resources starting at %lx (gap: %lx:%lx)\n", + pci_mem_start, gapstart, gapsize); +} + +#endif + +void __init parse_memopt(char *p, char **from) +{ + end_user_pfn = memparse(p, from); + end_user_pfn >>= PAGE_SHIFT; + xen_override_max_pfn = (unsigned long) end_user_pfn; +} + +/* + * Search for the biggest gap in the low 32 bits of the e820 + * memory space. We pass this space to PCI to assign MMIO resources + * for hotplug or unconfigured devices in. + * Hopefully the BIOS let enough space left. + */ +__init void e820_setup_gap(void) +{ +#ifndef CONFIG_XEN + unsigned long gapstart, gapsize; + unsigned long last; + int i; + int found = 0; + + last = 0x100000000ull; + gapstart = 0x10000000; + gapsize = 0x400000; + i = e820.nr_map; + while (--i >= 0) { + unsigned long long start = e820.map[i].addr; + unsigned long long end = start + e820.map[i].size; + + /* + * Since "last" is at most 4GB, we know we'll + * fit in 32 bits if this condition is true + */ + if (last > end) { + unsigned long gap = last - end; + + if (gap > gapsize) { + gapsize = gap; + gapstart = end; + found = 1; + } + } + if (start < last) + last = start; + } + + if (!found) { + gapstart = (end_pfn << PAGE_SHIFT) + 1024*1024; + printk(KERN_ERR "PCI: Warning: Cannot find a gap in the 32bit address range\n" + KERN_ERR "PCI: Unassigned devices with 32bit resource registers may break!\n"); + } + + /* + * Start allocating dynamic PCI memory a bit into the gap, + * aligned up to the nearest megabyte. + * + * Question: should we try to pad it up a bit (do something + * like " + (gapsize >> 3)" in there too?). We now have the + * technology. + */ + pci_mem_start = (gapstart + 0xfffff) & ~0xfffff; + + printk(KERN_INFO "Allocating PCI resources starting at %lx (gap: %lx:%lx)\n", + pci_mem_start, gapstart, gapsize); +#endif +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/early_printk-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/early_printk-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,251 @@ +#include <linux/config.h> +#include <linux/console.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/string.h> +#include <asm/io.h> +#include <asm/processor.h> + +#ifndef CONFIG_XEN + +/* Simple VGA output */ + +#ifdef __i386__ +#define VGABASE (__ISA_IO_base + 0xb8000) +#else +#define VGABASE ((void __iomem *)0xffffffff800b8000UL) +#endif + +#define MAX_YPOS 25 +#define MAX_XPOS 80 + +static int current_ypos = 1, current_xpos = 0; + +static void early_vga_write(struct console *con, const char *str, unsigned n) +{ + char c; + int i, k, j; + + while ((c = *str++) != '\0' && n-- > 0) { + if (current_ypos >= MAX_YPOS) { + /* scroll 1 line up */ + for (k = 1, j = 0; k < MAX_YPOS; k++, j++) { + for (i = 0; i < MAX_XPOS; i++) { + writew(readw(VGABASE + 2*(MAX_XPOS*k + i)), + VGABASE + 2*(MAX_XPOS*j + i)); + } + } + for (i = 0; i < MAX_XPOS; i++) + writew(0x720, VGABASE + 2*(MAX_XPOS*j + i)); + current_ypos = MAX_YPOS-1; + } + if (c == '\n') { + current_xpos = 0; + current_ypos++; + } else if (c != '\r') { + writew(((0x7 << 8) | (unsigned short) c), + VGABASE + 2*(MAX_XPOS*current_ypos + + current_xpos++)); + if (current_xpos >= MAX_XPOS) { + current_xpos = 0; + current_ypos++; + } + } + } +} + +static struct console early_vga_console = { + .name = "earlyvga", + .write = early_vga_write, + .flags = CON_PRINTBUFFER, + .index = -1, +}; + +/* Serial functions loosely based on a similar package from Klaus P. Gerlicher */ + +static int early_serial_base = 0x3f8; /* ttyS0 */ + +#define XMTRDY 0x20 + +#define DLAB 0x80 + +#define TXR 0 /* Transmit register (WRITE) */ +#define RXR 0 /* Receive register (READ) */ +#define IER 1 /* Interrupt Enable */ +#define IIR 2 /* Interrupt ID */ +#define FCR 2 /* FIFO control */ +#define LCR 3 /* Line control */ +#define MCR 4 /* Modem control */ +#define LSR 5 /* Line Status */ +#define MSR 6 /* Modem Status */ +#define DLL 0 /* Divisor Latch Low */ +#define DLH 1 /* Divisor latch High */ + +static int early_serial_putc(unsigned char ch) +{ + unsigned timeout = 0xffff; + while ((inb(early_serial_base + LSR) & XMTRDY) == 0 && --timeout) + cpu_relax(); + outb(ch, early_serial_base + TXR); + return timeout ? 0 : -1; +} + +static void early_serial_write(struct console *con, const char *s, unsigned n) +{ + while (*s && n-- > 0) { + early_serial_putc(*s); + if (*s == '\n') + early_serial_putc('\r'); + s++; + } +} + +#define DEFAULT_BAUD 9600 + +static __init void early_serial_init(char *s) +{ + unsigned char c; + unsigned divisor; + unsigned baud = DEFAULT_BAUD; + char *e; + + if (*s == ',') + ++s; + + if (*s) { + unsigned port; + if (!strncmp(s,"0x",2)) { + early_serial_base = simple_strtoul(s, &e, 16); + } else { + static int bases[] = { 0x3f8, 0x2f8 }; + + if (!strncmp(s,"ttyS",4)) + s += 4; + port = simple_strtoul(s, &e, 10); + if (port > 1 || s == e) + port = 0; + early_serial_base = bases[port]; + } + s += strcspn(s, ","); + if (*s == ',') + s++; + } + + outb(0x3, early_serial_base + LCR); /* 8n1 */ + outb(0, early_serial_base + IER); /* no interrupt */ + outb(0, early_serial_base + FCR); /* no fifo */ + outb(0x3, early_serial_base + MCR); /* DTR + RTS */ + + if (*s) { + baud = simple_strtoul(s, &e, 0); + if (baud == 0 || s == e) + baud = DEFAULT_BAUD; + } + + divisor = 115200 / baud; + c = inb(early_serial_base + LCR); + outb(c | DLAB, early_serial_base + LCR); + outb(divisor & 0xff, early_serial_base + DLL); + outb((divisor >> 8) & 0xff, early_serial_base + DLH); + outb(c & ~DLAB, early_serial_base + LCR); +} + +#else /* CONFIG_XEN */ + +static void +early_serial_write(struct console *con, const char *s, unsigned count) +{ + int n; + + while (count > 0) { + n = HYPERVISOR_console_io(CONSOLEIO_write, count, (char *)s); + if (n <= 0) + break; + count -= n; + s += n; + } +} + +static __init void early_serial_init(char *s) +{ +} + +/* + * No early VGA console on Xen, as we do not have convenient ISA-space + * mappings. Someone should fix this for domain 0. For now, use fake serial. + */ +#define early_vga_console early_serial_console + +#endif + +static struct console early_serial_console = { + .name = "earlyser", + .write = early_serial_write, + .flags = CON_PRINTBUFFER, + .index = -1, +}; + +/* Direct interface for emergencies */ +struct console *early_console = &early_vga_console; +static int early_console_initialized = 0; + +void early_printk(const char *fmt, ...) +{ + char buf[512]; + int n; + va_list ap; + + va_start(ap,fmt); + n = vscnprintf(buf,512,fmt,ap); + early_console->write(early_console,buf,n); + va_end(ap); +} + +static int keep_early; + +int __init setup_early_printk(char *opt) +{ + char *space; + char buf[256]; + + if (early_console_initialized) + return -1; + + opt = strchr(opt, '=') + 1; + + strlcpy(buf,opt,sizeof(buf)); + space = strchr(buf, ' '); + if (space) + *space = 0; + + if (strstr(buf,"keep")) + keep_early = 1; + + if (!strncmp(buf, "serial", 6)) { + early_serial_init(buf + 6); + early_console = &early_serial_console; + } else if (!strncmp(buf, "ttyS", 4)) { + early_serial_init(buf); + early_console = &early_serial_console; + } else if (!strncmp(buf, "vga", 3)) { + early_console = &early_vga_console; + } + early_console_initialized = 1; + register_console(early_console); + return 0; +} + +void __init disable_early_printk(void) +{ + if (!early_console_initialized || !early_console) + return; + if (!keep_early) { + printk("disabling early console\n"); + unregister_console(early_console); + early_console_initialized = 0; + } else { + printk("keeping early console\n"); + } +} + +__setup("earlyprintk=", setup_early_printk); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/entry-xen.S --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/entry-xen.S Mon Jan 30 17:18:27 2006 @@ -0,0 +1,1019 @@ +/* + * linux/arch/x86_64/entry.S + * + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs + * Copyright (C) 2000 Pavel Machek <pavel@xxxxxxx> + * + * $Id$ + * + * Jun Nakajima <jun.nakajima@xxxxxxxxx> + * Asit Mallick <asit.k.mallick@xxxxxxxxx> + * Modified for Xen + */ + +/* + * entry.S contains the system-call and fault low-level handling routines. + * + * NOTE: This code handles signal-recognition, which happens every time + * after an interrupt and after each system call. + * + * Normal syscalls and interrupts don't save a full stack frame, this is + * only done for syscall tracing, signals or fork/exec et.al. + * + * A note on terminology: + * - top of stack: Architecture defined interrupt frame from SS to RIP + * at the top of the kernel process stack. + * - partial stack frame: partially saved registers upto R11. + * - full stack frame: Like partial stack frame, but all register saved. + * + * TODO: + * - schedule it carefully for the final hardware. + */ + +#define ASSEMBLY 1 +#include <linux/config.h> +#include <linux/linkage.h> +#include <asm/segment.h> +#include <asm/smp.h> +#include <asm/cache.h> +#include <asm/errno.h> +#include <asm/dwarf2.h> +#include <asm/calling.h> +#include <asm/offset.h> +#include <asm/msr.h> +#include <asm/unistd.h> +#include <asm/thread_info.h> +#include <asm/hw_irq.h> +#include <asm/errno.h> +#include <xen/interface/arch-x86_64.h> + +#include "irq_vectors.h" + +#include "xen_entry.S" + + .code64 + +#ifndef CONFIG_PREEMPT +#define retint_kernel retint_restore_args +#endif + +/* + * C code is not supposed to know about undefined top of stack. Every time + * a C function with an pt_regs argument is called from the SYSCALL based + * fast path FIXUP_TOP_OF_STACK is needed. + * RESTORE_TOP_OF_STACK syncs the syscall state after any possible ptregs + * manipulation. + */ + + /* %rsp:at FRAMEEND */ + .macro FIXUP_TOP_OF_STACK tmp + movq $__USER_CS,CS(%rsp) + movq $-1,RCX(%rsp) + .endm + + .macro RESTORE_TOP_OF_STACK tmp,offset=0 + .endm + + .macro FAKE_STACK_FRAME child_rip + /* push in order ss, rsp, eflags, cs, rip */ + xorq %rax, %rax + pushq %rax /* ss */ + CFI_ADJUST_CFA_OFFSET 8 + pushq %rax /* rsp */ + CFI_ADJUST_CFA_OFFSET 8 + CFI_OFFSET rip,0 + pushq $(1<<9) /* eflags - interrupts on */ + CFI_ADJUST_CFA_OFFSET 8 + pushq $__KERNEL_CS /* cs */ + CFI_ADJUST_CFA_OFFSET 8 + pushq \child_rip /* rip */ + CFI_ADJUST_CFA_OFFSET 8 + CFI_OFFSET rip,0 + pushq %rax /* orig rax */ + CFI_ADJUST_CFA_OFFSET 8 + .endm + + .macro UNFAKE_STACK_FRAME + addq $8*6, %rsp + CFI_ADJUST_CFA_OFFSET -(6*8) + .endm + + .macro CFI_DEFAULT_STACK + CFI_ADJUST_CFA_OFFSET (SS) + CFI_OFFSET r15,R15-SS + CFI_OFFSET r14,R14-SS + CFI_OFFSET r13,R13-SS + CFI_OFFSET r12,R12-SS + CFI_OFFSET rbp,RBP-SS + CFI_OFFSET rbx,RBX-SS + CFI_OFFSET r11,R11-SS + CFI_OFFSET r10,R10-SS + CFI_OFFSET r9,R9-SS + CFI_OFFSET r8,R8-SS + CFI_OFFSET rax,RAX-SS + CFI_OFFSET rcx,RCX-SS + CFI_OFFSET rdx,RDX-SS + CFI_OFFSET rsi,RSI-SS + CFI_OFFSET rdi,RDI-SS + CFI_OFFSET rsp,RSP-SS + CFI_OFFSET rip,RIP-SS + .endm + + /* + * Must be consistent with the definition in arch-x86_64.h: + * struct iret_context { + * u64 rax, r11, rcx, flags, rip, cs, rflags, rsp, ss; + * }; + * #define VGCF_IN_SYSCALL (1<<8) + */ + .macro HYPERVISOR_IRET flag + pushq $\flag + jmp hypercall_page + (__HYPERVISOR_iret * 32) + .endm + + .macro SWITCH_TO_KERNEL ssoff,adjust=0 + jc 1f + orb $1,\ssoff-\adjust+4(%rsp) +1: + .endm + +/* + * A newly forked process directly context switches into this. + */ +/* rdi: prev */ +ENTRY(ret_from_fork) + CFI_STARTPROC + CFI_DEFAULT_STACK + call schedule_tail + GET_THREAD_INFO(%rcx) + testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%rcx) + jnz rff_trace +rff_action: + RESTORE_REST + testl $3,CS-ARGOFFSET(%rsp) # from kernel_thread? + je int_ret_from_sys_call + testl $_TIF_IA32,threadinfo_flags(%rcx) + jnz int_ret_from_sys_call + RESTORE_TOP_OF_STACK %rdi,ARGOFFSET + jmp ret_from_sys_call +rff_trace: + movq %rsp,%rdi + call syscall_trace_leave + GET_THREAD_INFO(%rcx) + jmp rff_action + CFI_ENDPROC + +/* + * System call entry. Upto 6 arguments in registers are supported. + * + * SYSCALL does not save anything on the stack and does not change the + * stack pointer. + */ + +/* + * Register setup: + * rax system call number + * rdi arg0 + * rcx return address for syscall/sysret, C arg3 + * rsi arg1 + * rdx arg2 + * r10 arg3 (--> moved to rcx for C) + * r8 arg4 + * r9 arg5 + * r11 eflags for syscall/sysret, temporary for C + * r12-r15,rbp,rbx saved by C code, not touched. + * + * Interrupts are off on entry. + * Only called from user space. + * + * XXX if we had a free scratch register we could save the RSP into the stack frame + * and report it properly in ps. Unfortunately we haven't. + */ + +ENTRY(system_call) + CFI_STARTPROC + SAVE_ARGS -8,0 + movq %rax,ORIG_RAX-ARGOFFSET(%rsp) + XEN_UNBLOCK_EVENTS(%r11) + GET_THREAD_INFO(%rcx) + testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%rcx) + jnz tracesys + cmpq $__NR_syscall_max,%rax + ja badsys + movq %r10,%rcx + call *sys_call_table(,%rax,8) # XXX: rip relative + movq %rax,RAX-ARGOFFSET(%rsp) +/* + * Syscall return path ending with SYSRET (fast path) + * Has incomplete stack frame and undefined top of stack. + */ + .globl ret_from_sys_call +ret_from_sys_call: + movl $_TIF_ALLWORK_MASK,%edi + /* edi: flagmask */ +sysret_check: + GET_THREAD_INFO(%rcx) + XEN_BLOCK_EVENTS(%rsi) + movl threadinfo_flags(%rcx),%edx + andl %edi,%edx + jnz sysret_careful + XEN_UNBLOCK_EVENTS(%rsi) + RESTORE_ARGS 0,8,0 + HYPERVISOR_IRET VGCF_IN_SYSCALL + + /* Handle reschedules */ + /* edx: work, edi: workmask */ +sysret_careful: + bt $TIF_NEED_RESCHED,%edx + jnc sysret_signal + XEN_BLOCK_EVENTS(%rsi) + pushq %rdi + call schedule + popq %rdi + jmp sysret_check + + /* Handle a signal */ +sysret_signal: +/* sti */ + XEN_UNBLOCK_EVENTS(%rsi) + testl $(_TIF_SIGPENDING|_TIF_NOTIFY_RESUME|_TIF_SINGLESTEP),%edx + jz 1f + + /* Really a signal */ + /* edx: work flags (arg3) */ + leaq do_notify_resume(%rip),%rax + leaq -ARGOFFSET(%rsp),%rdi # &pt_regs -> arg1 + xorl %esi,%esi # oldset -> arg2 + call ptregscall_common +1: movl $_TIF_NEED_RESCHED,%edi + jmp sysret_check + + /* Do syscall tracing */ +tracesys: + SAVE_REST + movq $-ENOSYS,RAX(%rsp) + FIXUP_TOP_OF_STACK %rdi + movq %rsp,%rdi + call syscall_trace_enter + LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed it */ + RESTORE_REST + cmpq $__NR_syscall_max,%rax + ja 1f + movq %r10,%rcx /* fixup for C */ + call *sys_call_table(,%rax,8) + movq %rax,RAX-ARGOFFSET(%rsp) +1: SAVE_REST + movq %rsp,%rdi + call syscall_trace_leave + RESTORE_TOP_OF_STACK %rbx + RESTORE_REST + jmp ret_from_sys_call + +badsys: + movq $-ENOSYS,RAX-ARGOFFSET(%rsp) + jmp ret_from_sys_call + +/* + * Syscall return path ending with IRET. + * Has correct top of stack, but partial stack frame. + */ +ENTRY(int_ret_from_sys_call) + XEN_BLOCK_EVENTS(%rsi) + testb $3,CS-ARGOFFSET(%rsp) + jnz 1f + /* Need to set the proper %ss (not NULL) for ring 3 iretq */ + movl $__KERNEL_DS,SS-ARGOFFSET(%rsp) + jmp retint_restore_args # retrun from ring3 kernel +1: + movl $_TIF_ALLWORK_MASK,%edi + /* edi: mask to check */ +int_with_check: + GET_THREAD_INFO(%rcx) + movl threadinfo_flags(%rcx),%edx + andl %edi,%edx + jnz int_careful + jmp retint_restore_args + + /* Either reschedule or signal or syscall exit tracking needed. */ + /* First do a reschedule test. */ + /* edx: work, edi: workmask */ +int_careful: + bt $TIF_NEED_RESCHED,%edx + jnc int_very_careful +/* sti */ + XEN_UNBLOCK_EVENTS(%rsi) + pushq %rdi + call schedule + popq %rdi + cli + jmp int_with_check + + /* handle signals and tracing -- both require a full stack frame */ +int_very_careful: +/* sti */ + XEN_UNBLOCK_EVENTS(%rsi) + SAVE_REST + /* Check for syscall exit trace */ + testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP),%edx + jz int_signal + pushq %rdi + leaq 8(%rsp),%rdi # &ptregs -> arg1 + call syscall_trace_leave + popq %rdi + andl $~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP),%edi + cli + jmp int_restore_rest + +int_signal: + testl $(_TIF_NOTIFY_RESUME|_TIF_SIGPENDING|_TIF_SINGLESTEP),%edx + jz 1f + movq %rsp,%rdi # &ptregs -> arg1 + xorl %esi,%esi # oldset -> arg2 + call do_notify_resume +1: movl $_TIF_NEED_RESCHED,%edi +int_restore_rest: + RESTORE_REST + cli + jmp int_with_check + CFI_ENDPROC + +/* + * Certain special system calls that need to save a complete full stack frame. + */ + + .macro PTREGSCALL label,func,arg + .globl \label +\label: + leaq \func(%rip),%rax + leaq -ARGOFFSET+8(%rsp),\arg /* 8 for return address */ + jmp ptregscall_common + .endm + + PTREGSCALL stub_clone, sys_clone, %r8 + PTREGSCALL stub_fork, sys_fork, %rdi + PTREGSCALL stub_vfork, sys_vfork, %rdi + PTREGSCALL stub_rt_sigsuspend, sys_rt_sigsuspend, %rdx + PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx + PTREGSCALL stub_iopl, sys_iopl, %rsi + +ENTRY(ptregscall_common) + CFI_STARTPROC + popq %r11 + CFI_ADJUST_CFA_OFFSET -8 + SAVE_REST + movq %r11, %r15 + FIXUP_TOP_OF_STACK %r11 + call *%rax + RESTORE_TOP_OF_STACK %r11 + movq %r15, %r11 + RESTORE_REST + pushq %r11 + CFI_ADJUST_CFA_OFFSET 8 + ret + CFI_ENDPROC + +ENTRY(stub_execve) + CFI_STARTPROC + popq %r11 + CFI_ADJUST_CFA_OFFSET -8 + SAVE_REST + movq %r11, %r15 + FIXUP_TOP_OF_STACK %r11 + call sys_execve + GET_THREAD_INFO(%rcx) + bt $TIF_IA32,threadinfo_flags(%rcx) + jc exec_32bit + RESTORE_TOP_OF_STACK %r11 + movq %r15, %r11 + RESTORE_REST + push %r11 + ret + +exec_32bit: + CFI_ADJUST_CFA_OFFSET REST_SKIP + movq %rax,RAX(%rsp) + RESTORE_REST + jmp int_ret_from_sys_call + CFI_ENDPROC + +/* + * sigreturn is special because it needs to restore all registers on return. + * This cannot be done with SYSRET, so use the IRET return path instead. + */ +ENTRY(stub_rt_sigreturn) + CFI_STARTPROC + addq $8, %rsp + SAVE_REST + movq %rsp,%rdi + FIXUP_TOP_OF_STACK %r11 + call sys_rt_sigreturn + movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer + RESTORE_REST + jmp int_ret_from_sys_call + CFI_ENDPROC + +/* + * Interrupt entry/exit. + * + * Interrupt entry points save only callee clobbered registers in fast path. + * + * Entry runs with interrupts off. + */ + +/* 0(%rsp): interrupt number */ + .macro interrupt func + CFI_STARTPROC simple + CFI_DEF_CFA rsp,(SS-RDI) + CFI_REL_OFFSET rsp,(RSP-ORIG_RAX) + CFI_REL_OFFSET rip,(RIP-ORIG_RAX) + cld +#ifdef CONFIG_DEBUG_INFO + SAVE_ALL + movq %rsp,%rdi + /* + * Setup a stack frame pointer. This allows gdb to trace + * back to the original stack. + */ + movq %rsp,%rbp + CFI_DEF_CFA_REGISTER rbp +#else + SAVE_ARGS + leaq -ARGOFFSET(%rsp),%rdi # arg1 for handler +#endif +#if 0 /* For Xen we don't need to do this */ + testl $3,CS(%rdi) + je 1f + swapgs +#endif +1: addl $1,%gs:pda_irqcount # RED-PEN should check preempt count + movq %gs:pda_irqstackptr,%rax + cmoveq %rax,%rsp + pushq %rdi # save old stack + call \func + .endm + +retint_check: + movl threadinfo_flags(%rcx),%edx + andl %edi,%edx + jnz retint_careful +retint_restore_args: + movb EVENT_MASK-REST_SKIP(%rsp), %al + notb %al # %al == ~saved_mask + XEN_GET_VCPU_INFO(%rsi) + andb evtchn_upcall_mask(%rsi),%al + andb $1,%al # %al == mask & ~saved_mask + jnz restore_all_enable_events # != 0 => reenable event delivery + XEN_PUT_VCPU_INFO(%rsi) + + RESTORE_ARGS 0,8,0 + testb $3,8(%rsp) # check CS + jnz user_mode +kernel_mode: + orb $3,1*8(%rsp) + iretq +user_mode: + HYPERVISOR_IRET 0 + + /* edi: workmask, edx: work */ +retint_careful: + bt $TIF_NEED_RESCHED,%edx + jnc retint_signal + XEN_UNBLOCK_EVENTS(%rsi) +/* sti */ + pushq %rdi + call schedule + popq %rdi + XEN_BLOCK_EVENTS(%rsi) + GET_THREAD_INFO(%rcx) +/* cli */ + jmp retint_check + +retint_signal: + testl $(_TIF_SIGPENDING|_TIF_NOTIFY_RESUME|_TIF_SINGLESTEP),%edx + jz retint_restore_args + XEN_UNBLOCK_EVENTS(%rsi) + SAVE_REST + movq $-1,ORIG_RAX(%rsp) + xorq %rsi,%rsi # oldset + movq %rsp,%rdi # &pt_regs + call do_notify_resume + RESTORE_REST + XEN_BLOCK_EVENTS(%rsi) + movl $_TIF_NEED_RESCHED,%edi + GET_THREAD_INFO(%rcx) + jmp retint_check + +#ifdef CONFIG_PREEMPT + /* Returning to kernel space. Check if we need preemption */ + /* rcx: threadinfo. interrupts off. */ + .p2align +retint_kernel: + cmpl $0,threadinfo_preempt_count(%rcx) + jnz retint_restore_args + bt $TIF_NEED_RESCHED,threadinfo_flags(%rcx) + jnc retint_restore_args + bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */ + jnc retint_restore_args + call preempt_schedule_irq + jmp retint_kernel /* check again */ +#endif + CFI_ENDPROC + +/* + * APIC interrupts. + */ + .macro apicinterrupt num,func + pushq $\num-256 + interrupt \func + jmp error_entry + CFI_ENDPROC + .endm + +#if 0 +ENTRY(reschedule_interrupt) + apicinterrupt RESCHEDULE_VECTOR,smp_reschedule_interrupt + +ENTRY(invalidate_interrupt) + apicinterrupt INVALIDATE_TLB_VECTOR,smp_invalidate_interrupt + +ENTRY(call_function_interrupt) + apicinterrupt CALL_FUNCTION_VECTOR,smp_call_function_interrupt +#endif + +#ifdef CONFIG_X86_LOCAL_APIC +ENTRY(apic_timer_interrupt) + apicinterrupt LOCAL_TIMER_VECTOR,smp_apic_timer_interrupt + +ENTRY(error_interrupt) + apicinterrupt ERROR_APIC_VECTOR,smp_error_interrupt + +ENTRY(spurious_interrupt) + apicinterrupt SPURIOUS_APIC_VECTOR,smp_spurious_interrupt +#endif + +/* + * Exception entry points. + */ + .macro zeroentry sym + movq (%rsp),%rcx + movq 8(%rsp),%r11 + addq $0x10,%rsp /* skip rcx and r11 */ + pushq $0 /* push error code/oldrax */ + pushq %rax /* push real oldrax to the rdi slot */ + leaq \sym(%rip),%rax + jmp error_entry + .endm + + .macro errorentry sym + movq (%rsp),%rcx + movq 8(%rsp),%r11 + addq $0x10,%rsp /* rsp points to the error code */ + pushq %rax + leaq \sym(%rip),%rax + jmp error_entry + .endm + +#if 0 + /* error code is on the stack already */ + /* handle NMI like exceptions that can happen everywhere */ + .macro paranoidentry sym + movq (%rsp),%rcx + movq 8(%rsp),%r11 + addq $0x10,%rsp /* skip rcx and r11 */ + SAVE_ALL + cld + movl $1,%ebx + movl $MSR_GS_BASE,%ecx + rdmsr + testl %edx,%edx + js 1f +/* swapgs */ + xorl %ebx,%ebx +1: movq %rsp,%rdi + movq ORIG_RAX(%rsp),%rsi + movq $-1,ORIG_RAX(%rsp) + call \sym + cli + .endm +#endif + +/* + * Exception entry point. This expects an error code/orig_rax on the stack + * and the exception handler in %rax. + */ +ENTRY(error_entry) + CFI_STARTPROC simple + CFI_DEF_CFA rsp,(SS-RDI) + CFI_REL_OFFSET rsp,(RSP-RDI) + CFI_REL_OFFSET rip,(RIP-RDI) + /* rdi slot contains rax, oldrax contains error code */ + cld + subq $14*8,%rsp + CFI_ADJUST_CFA_OFFSET (14*8) + movq %rsi,13*8(%rsp) + CFI_REL_OFFSET rsi,RSI + movq 14*8(%rsp),%rsi /* load rax from rdi slot */ + movq %rdx,12*8(%rsp) + CFI_REL_OFFSET rdx,RDX + movq %rcx,11*8(%rsp) + CFI_REL_OFFSET rcx,RCX + movq %rsi,10*8(%rsp) /* store rax */ + CFI_REL_OFFSET rax,RAX + movq %r8, 9*8(%rsp) + CFI_REL_OFFSET r8,R8 + movq %r9, 8*8(%rsp) + CFI_REL_OFFSET r9,R9 + movq %r10,7*8(%rsp) + CFI_REL_OFFSET r10,R10 + movq %r11,6*8(%rsp) + CFI_REL_OFFSET r11,R11 + movq %rbx,5*8(%rsp) + CFI_REL_OFFSET rbx,RBX + movq %rbp,4*8(%rsp) + CFI_REL_OFFSET rbp,RBP + movq %r12,3*8(%rsp) + CFI_REL_OFFSET r12,R12 + movq %r13,2*8(%rsp) + CFI_REL_OFFSET r13,R13 + movq %r14,1*8(%rsp) + CFI_REL_OFFSET r14,R14 + movq %r15,(%rsp) + CFI_REL_OFFSET r15,R15 +#if 0 + cmpl $__KERNEL_CS,CS(%rsp) + je error_kernelspace +#endif +error_call_handler: + movq %rdi, RDI(%rsp) + movq %rsp,%rdi + movq ORIG_RAX(%rsp),%rsi # get error code + movq $-1,ORIG_RAX(%rsp) + call *%rax +error_exit: + RESTORE_REST +/* cli */ + XEN_BLOCK_EVENTS(%rsi) + GET_THREAD_INFO(%rcx) + testb $3,CS-ARGOFFSET(%rsp) + jz retint_kernel + movl threadinfo_flags(%rcx),%edx + movl $_TIF_WORK_MASK,%edi + andl %edi,%edx + jnz retint_careful + jmp retint_restore_args + +error_kernelspace: + /* + * We need to re-write the logic here because we don't do iretq to + * to return to user mode. It's still possible that we get trap/fault + * in the kernel (when accessing buffers pointed to by system calls, + * for example). + * + */ +#if 0 + incl %ebx + /* There are two places in the kernel that can potentially fault with + usergs. Handle them here. The exception handlers after + iret run with kernel gs again, so don't set the user space flag. + B stepping K8s sometimes report an truncated RIP for IRET + exceptions returning to compat mode. Check for these here too. */ + leaq iret_label(%rip),%rbp + cmpq %rbp,RIP(%rsp) + je error_swapgs + movl %ebp,%ebp /* zero extend */ + cmpq %rbp,RIP(%rsp) + je error_swapgs + cmpq $gs_change,RIP(%rsp) + je error_swapgs + jmp error_sti +#endif + +ENTRY(hypervisor_callback) + zeroentry do_hypervisor_callback + +/* + * Copied from arch/xen/i386/kernel/entry.S + */ +# A note on the "critical region" in our callback handler. +# We want to avoid stacking callback handlers due to events occurring +# during handling of the last event. To do this, we keep events disabled +# until we've done all processing. HOWEVER, we must enable events before +# popping the stack frame (can't be done atomically) and so it would still +# be possible to get enough handler activations to overflow the stack. +# Although unlikely, bugs of that kind are hard to track down, so we'd +# like to avoid the possibility. +# So, on entry to the handler we detect whether we interrupted an +# existing activation in its critical region -- if so, we pop the current +# activation and restart the handler using the previous one. +ENTRY(do_hypervisor_callback) # do_hyperviosr_callback(struct *pt_regs) +# Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will +# see the correct pointer to the pt_regs + addq $8, %rsp # we don't return, adjust the stack frame +11: movb $0, EVENT_MASK(%rsp) + call evtchn_do_upcall + jmp error_exit + +#ifdef CONFIG_X86_LOCAL_APIC +ENTRY(nmi) + zeroentry do_nmi_callback +ENTRY(do_nmi_callback) + addq $8, %rsp + call do_nmi + RESTORE_REST + XEN_BLOCK_EVENTS(%rsi) + GET_THREAD_INFO(%rcx) + jmp retint_restore_args +#endif + + ALIGN +restore_all_enable_events: + XEN_UNBLOCK_EVENTS(%rsi) # %rsi is already set up... + +scrit: /**** START OF CRITICAL REGION ****/ + XEN_TEST_PENDING(%rsi) + jnz 14f # process more events if necessary... + XEN_PUT_VCPU_INFO(%rsi) + RESTORE_ARGS 0,8,0 + testb $3,8(%rsp) # check CS + jnz crit_user_mode + orb $3,1*8(%rsp) + iretq +crit_user_mode: + HYPERVISOR_IRET 0 + +14: XEN_LOCKED_BLOCK_EVENTS(%rsi) + XEN_PUT_VCPU_INFO(%rsi) + SAVE_REST + movq %rsp,%rdi # set the argument again + jmp 11b +ecrit: /**** END OF CRITICAL REGION ****/ +# At this point, unlike on x86-32, we don't do the fixup to simplify the +# code and the stack frame is more complex on x86-64. +# When the kernel is interrupted in the critical section, the kernel +# will do IRET in that case, and everything will be restored at that point, +# i.e. it just resumes from the next instruction interrupted with the same context. + +# Hypervisor uses this for application faults while it executes. +ENTRY(failsafe_callback) + addq $0x10,%rsp /* skip rcx and r11 */ +1: mov (%rsp),%ds +2: mov 8(%rsp),%es +3: mov 16(%rsp),%fs +4: mov 24(%rsp),%gs + addq $0x20,%rsp /* skip the above selectors */ + SAVE_ALL + jmp error_exit +.section .fixup,"ax"; \ +6: movq $0,(%rsp); \ + jmp 1b; \ +7: movq $0,8(%rsp); \ + jmp 2b; \ +8: movq $0,16(%rsp); \ + jmp 3b; \ +9: movq $0,24(%rsp); \ + jmp 4b; \ +.previous; \ +.section __ex_table,"a";\ + .align 16; \ + .quad 1b,6b; \ + .quad 2b,7b; \ + .quad 3b,8b; \ + .quad 4b,9b; \ +.previous + +#if 0 + .section __ex_table,"a" + .align 8 + .quad gs_change,bad_gs + .previous + .section .fixup,"ax" + /* running with kernelgs */ +bad_gs: +/* swapgs */ /* switch back to user gs */ + xorl %eax,%eax + movl %eax,%gs + jmp 2b + .previous +#endif + +/* + * Create a kernel thread. + * + * C extern interface: + * extern long kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) + * + * asm input arguments: + * rdi: fn, rsi: arg, rdx: flags + */ +ENTRY(kernel_thread) + CFI_STARTPROC + FAKE_STACK_FRAME $child_rip + SAVE_ALL + + # rdi: flags, rsi: usp, rdx: will be &pt_regs + movq %rdx,%rdi + orq kernel_thread_flags(%rip),%rdi + movq $-1, %rsi + movq %rsp, %rdx + + xorl %r8d,%r8d + xorl %r9d,%r9d + + # clone now + call do_fork + movq %rax,RAX(%rsp) + xorl %edi,%edi + + /* + * It isn't worth to check for reschedule here, + * so internally to the x86_64 port you can rely on kernel_thread() + * not to reschedule the child before returning, this avoids the need + * of hacks for example to fork off the per-CPU idle tasks. + * [Hopefully no generic code relies on the reschedule -AK] + */ + RESTORE_ALL + UNFAKE_STACK_FRAME + ret + CFI_ENDPROC + + +child_rip: + /* + * Here we are in the child and the registers are set as they were + * at kernel_thread() invocation in the parent. + */ + movq %rdi, %rax + movq %rsi, %rdi + call *%rax + # exit + xorq %rdi, %rdi + call do_exit + +/* + * execve(). This function needs to use IRET, not SYSRET, to set up all state properly. + * + * C extern interface: + * extern long execve(char *name, char **argv, char **envp) + * + * asm input arguments: + * rdi: name, rsi: argv, rdx: envp + * + * We want to fallback into: + * extern long sys_execve(char *name, char **argv,char **envp, struct pt_regs regs) + * + * do_sys_execve asm fallback arguments: + * rdi: name, rsi: argv, rdx: envp, fake frame on the stack + */ +ENTRY(execve) + CFI_STARTPROC + FAKE_STACK_FRAME $0 + SAVE_ALL + call sys_execve + movq %rax, RAX(%rsp) + RESTORE_REST + testq %rax,%rax + jne 1f + jmp int_ret_from_sys_call +1: RESTORE_ARGS + UNFAKE_STACK_FRAME + ret + CFI_ENDPROC + +ENTRY(page_fault) + errorentry do_page_fault + +ENTRY(coprocessor_error) + zeroentry do_coprocessor_error + +ENTRY(simd_coprocessor_error) + zeroentry do_simd_coprocessor_error + +ENTRY(device_not_available) + zeroentry math_state_restore + + /* runs on exception stack */ +ENTRY(debug) + CFI_STARTPROC +/* pushq $0 + CFI_ADJUST_CFA_OFFSET 8 */ + zeroentry do_debug +/* jmp paranoid_exit */ + CFI_ENDPROC + +#if 0 + /* runs on exception stack */ +ENTRY(nmi) + CFI_STARTPROC + pushq $-1 + CFI_ADJUST_CFA_OFFSET 8 + paranoidentry do_nmi + /* + * "Paranoid" exit path from exception stack. + * Paranoid because this is used by NMIs and cannot take + * any kernel state for granted. + * We don't do kernel preemption checks here, because only + * NMI should be common and it does not enable IRQs and + * cannot get reschedule ticks. + */ + /* ebx: no swapgs flag */ +paranoid_exit: + testl %ebx,%ebx /* swapgs needed? */ + jnz paranoid_restore + testl $3,CS(%rsp) + jnz paranoid_userspace +paranoid_swapgs: + swapgs +paranoid_restore: + RESTORE_ALL 8 + iretq +paranoid_userspace: + GET_THREAD_INFO(%rcx) + movl threadinfo_flags(%rcx),%ebx + andl $_TIF_WORK_MASK,%ebx + jz paranoid_swapgs + movq %rsp,%rdi /* &pt_regs */ + call sync_regs + movq %rax,%rsp /* switch stack for scheduling */ + testl $_TIF_NEED_RESCHED,%ebx + jnz paranoid_schedule + movl %ebx,%edx /* arg3: thread flags */ + sti + xorl %esi,%esi /* arg2: oldset */ + movq %rsp,%rdi /* arg1: &pt_regs */ + call do_notify_resume + cli + jmp paranoid_userspace +paranoid_schedule: + sti + call schedule + cli + jmp paranoid_userspace + CFI_ENDPROC +#endif + +ENTRY(int3) + zeroentry do_int3 + +ENTRY(overflow) + zeroentry do_overflow + +ENTRY(bounds) + zeroentry do_bounds + +ENTRY(invalid_op) + zeroentry do_invalid_op + +ENTRY(coprocessor_segment_overrun) + zeroentry do_coprocessor_segment_overrun + +ENTRY(reserved) + zeroentry do_reserved + +#if 0 + /* runs on exception stack */ +ENTRY(double_fault) + CFI_STARTPROC + paranoidentry do_double_fault + jmp paranoid_exit + CFI_ENDPROC +#endif + +ENTRY(invalid_TSS) + errorentry do_invalid_TSS + +ENTRY(segment_not_present) + errorentry do_segment_not_present + + /* runs on exception stack */ +ENTRY(stack_segment) + CFI_STARTPROC + errorentry do_stack_segment + CFI_ENDPROC + +ENTRY(general_protection) + errorentry do_general_protection + +ENTRY(alignment_check) + errorentry do_alignment_check + +ENTRY(divide_error) + zeroentry do_divide_error + +ENTRY(spurious_interrupt_bug) + zeroentry do_spurious_interrupt_bug + +#ifdef CONFIG_X86_MCE + /* runs on exception stack */ +ENTRY(machine_check) + CFI_STARTPROC + pushq $0 + CFI_ADJUST_CFA_OFFSET 8 + paranoidentry do_machine_check + jmp paranoid_exit + CFI_ENDPROC +#endif + +ENTRY(call_debug) + zeroentry do_call_debug + diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/genapic-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/genapic-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,123 @@ +/* + * Copyright 2004 James Cleverdon, IBM. + * Subject to the GNU Public License, v.2 + * + * Generic APIC sub-arch probe layer. + * + * Hacked for x86-64 by James Cleverdon from i386 architecture code by + * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and + * James Cleverdon. + */ +#include <linux/config.h> +#include <linux/threads.h> +#include <linux/cpumask.h> +#include <linux/string.h> +#include <linux/kernel.h> +#include <linux/ctype.h> +#include <linux/init.h> +#include <linux/module.h> + +#include <asm/smp.h> +#include <asm/ipi.h> + +#if defined(CONFIG_ACPI_BUS) +#include <acpi/acpi_bus.h> +#endif + +/* which logical CPU number maps to which CPU (physical APIC ID) */ +u8 x86_cpu_to_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; +EXPORT_SYMBOL(x86_cpu_to_apicid); +u8 x86_cpu_to_log_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; + +extern struct genapic apic_cluster; +extern struct genapic apic_flat; + +#ifndef CONFIG_XEN +struct genapic *genapic = &apic_flat; +#else +extern struct genapic apic_xen; +struct genapic *genapic = &apic_xen; +#endif + + +/* + * Check the APIC IDs in bios_cpu_apicid and choose the APIC mode. + */ +void __init clustered_apic_check(void) +{ +#ifndef CONFIG_XEN + long i; + u8 clusters, max_cluster; + u8 id; + u8 cluster_cnt[NUM_APIC_CLUSTERS]; + + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + /* AMD always uses flat mode right now */ + genapic = &apic_flat; + goto print; + } + +#if defined(CONFIG_ACPI_BUS) + /* + * Some x86_64 machines use physical APIC mode regardless of how many + * procs/clusters are present (x86_64 ES7000 is an example). + */ + if (acpi_fadt.revision > FADT2_REVISION_ID) + if (acpi_fadt.force_apic_physical_destination_mode) { + genapic = &apic_cluster; + goto print; + } +#endif + + memset(cluster_cnt, 0, sizeof(cluster_cnt)); + + for (i = 0; i < NR_CPUS; i++) { + id = bios_cpu_apicid[i]; + if (id != BAD_APICID) + cluster_cnt[APIC_CLUSTERID(id)]++; + } + + clusters = 0; + max_cluster = 0; + for (i = 0; i < NUM_APIC_CLUSTERS; i++) { + if (cluster_cnt[i] > 0) { + ++clusters; + if (cluster_cnt[i] > max_cluster) + max_cluster = cluster_cnt[i]; + } + } + + /* + * If we have clusters <= 1 and CPUs <= 8 in cluster 0, then flat mode, + * else if max_cluster <= 4 and cluster_cnt[15] == 0, clustered logical + * else physical mode. + * (We don't use lowest priority delivery + HW APIC IRQ steering, so + * can ignore the clustered logical case and go straight to physical.) + */ + if (clusters <= 1 && max_cluster <= 8 && cluster_cnt[0] == max_cluster) + genapic = &apic_flat; + else + genapic = &apic_cluster; + +print: +#else + /* hardcode to xen apic functions */ + genapic = &apic_xen; +#endif + printk(KERN_INFO "Setting APIC routing to %s\n", genapic->name); +} + +/* Same for both flat and clustered. */ + +#ifdef CONFIG_XEN +extern void xen_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest); +#endif + +void send_IPI_self(int vector) +{ +#ifndef CONFIG_XEN + __send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL); +#else + xen_send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL); +#endif +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/genapic_xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/genapic_xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,162 @@ +/* + * Copyright 2004 James Cleverdon, IBM. + * Subject to the GNU Public License, v.2 + * + * Xen APIC subarch code. Maximum 8 CPUs, logical delivery. + * + * Hacked for x86-64 by James Cleverdon from i386 architecture code by + * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and + * James Cleverdon. + * + * Hacked to pieces for Xen by Chris Wright. + */ +#include <linux/config.h> +#include <linux/threads.h> +#include <linux/cpumask.h> +#include <linux/string.h> +#include <linux/kernel.h> +#include <linux/ctype.h> +#include <linux/init.h> +#ifdef CONFIG_XEN_PRIVILEGED_GUEST +#include <asm/smp.h> +#include <asm/ipi.h> +#else +#include <asm/apic.h> +#include <asm/apicdef.h> +#include <asm/genapic.h> +#endif +#include <xen/evtchn.h> + +DECLARE_PER_CPU(int, ipi_to_irq[NR_IPIS]); + +static inline void __send_IPI_one(unsigned int cpu, int vector) +{ + int irq = per_cpu(ipi_to_irq, cpu)[vector]; + BUG_ON(irq < 0); + notify_remote_via_irq(irq); +} + +void xen_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest) +{ + int cpu; + + switch (shortcut) { + case APIC_DEST_SELF: + __send_IPI_one(smp_processor_id(), vector); + break; + case APIC_DEST_ALLBUT: + for (cpu = 0; cpu < NR_CPUS; ++cpu) { + if (cpu == smp_processor_id()) + continue; + if (cpu_isset(cpu, cpu_online_map)) { + __send_IPI_one(cpu, vector); + } + } + break; + case APIC_DEST_ALLINC: + for (cpu = 0; cpu < NR_CPUS; ++cpu) { + if (cpu_isset(cpu, cpu_online_map)) { + __send_IPI_one(cpu, vector); + } + } + break; + default: + printk("XXXXXX __send_IPI_shortcut %08x vector %d\n", shortcut, + vector); + break; + } +} + +static cpumask_t xen_target_cpus(void) +{ + return cpu_online_map; +} + +/* + * Set up the logical destination ID. + * Do nothing, not called now. + */ +static void xen_init_apic_ldr(void) +{ + Dprintk("%s\n", __FUNCTION__); + return; +} + +static void xen_send_IPI_allbutself(int vector) +{ + /* + * if there are no other CPUs in the system then + * we get an APIC send error if we try to broadcast. + * thus we have to avoid sending IPIs in this case. + */ + Dprintk("%s\n", __FUNCTION__); + if (num_online_cpus() > 1) + xen_send_IPI_shortcut(APIC_DEST_ALLBUT, vector, APIC_DEST_LOGICAL); +} + +static void xen_send_IPI_all(int vector) +{ + Dprintk("%s\n", __FUNCTION__); + xen_send_IPI_shortcut(APIC_DEST_ALLINC, vector, APIC_DEST_LOGICAL); +} + +static void xen_send_IPI_mask(cpumask_t cpumask, int vector) +{ + unsigned long mask = cpus_addr(cpumask)[0]; + unsigned int cpu; + unsigned long flags; + + Dprintk("%s\n", __FUNCTION__); + local_irq_save(flags); + WARN_ON(mask & ~cpus_addr(cpu_online_map)[0]); + + for (cpu = 0; cpu < NR_CPUS; ++cpu) { + if (cpu_isset(cpu, cpumask)) { + __send_IPI_one(cpu, vector); + } + } + local_irq_restore(flags); +} + +#ifdef CONFIG_XEN_PRIVILEGED_GUEST +static int xen_apic_id_registered(void) +{ + /* better be set */ + Dprintk("%s\n", __FUNCTION__); + return physid_isset(smp_processor_id(), phys_cpu_present_map); +} +#endif + +static unsigned int xen_cpu_mask_to_apicid(cpumask_t cpumask) +{ + Dprintk("%s\n", __FUNCTION__); + return cpus_addr(cpumask)[0] & APIC_ALL_CPUS; +} + +static unsigned int phys_pkg_id(int index_msb) +{ + u32 ebx; + + Dprintk("%s\n", __FUNCTION__); + ebx = cpuid_ebx(1); + return ((ebx >> 24) & 0xFF) >> index_msb; +} + +struct genapic apic_xen = { + .name = "xen", +#ifdef CONFIG_XEN_PRIVILEGED_GUEST + .int_delivery_mode = dest_LowestPrio, +#endif + .int_dest_mode = (APIC_DEST_LOGICAL != 0), + .int_delivery_dest = APIC_DEST_LOGICAL | APIC_DM_LOWEST, + .target_cpus = xen_target_cpus, +#ifdef CONFIG_XEN_PRIVILEGED_GUEST + .apic_id_registered = xen_apic_id_registered, +#endif + .init_apic_ldr = xen_init_apic_ldr, + .send_IPI_all = xen_send_IPI_all, + .send_IPI_allbutself = xen_send_IPI_allbutself, + .send_IPI_mask = xen_send_IPI_mask, + .cpu_mask_to_apicid = xen_cpu_mask_to_apicid, + .phys_pkg_id = phys_pkg_id, +}; diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/head-xen.S --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/head-xen.S Mon Jan 30 17:18:27 2006 @@ -0,0 +1,275 @@ +/* + * linux/arch/x86_64/kernel/head.S -- start in 32bit and switch to 64bit + * + * Copyright (C) 2000 Andrea Arcangeli <andrea@xxxxxxx> SuSE + * Copyright (C) 2000 Pavel Machek <pavel@xxxxxxx> + * Copyright (C) 2000 Karsten Keil <kkeil@xxxxxxx> + * Copyright (C) 2001,2002 Andi Kleen <ak@xxxxxxx> + * + * $Id: head.S,v 1.49 2002/03/19 17:39:25 ak Exp $ + * + * Jun Nakajima <jun.nakajima@xxxxxxxxx> + * Modified for Xen + */ + + +#include <linux/linkage.h> + +.section __xen_guest + .ascii "GUEST_OS=linux,GUEST_VER=2.6" + .ascii ",XEN_VER=xen-3.0" + .ascii ",VIRT_BASE=0xffffffff80000000" + .ascii ",HYPERCALL_PAGE=0x10d" /* __pa(hypercall_page) >> 12 */ + .ascii ",LOADER=generic" + .byte 0 + + +#include <linux/threads.h> +#include <asm/desc.h> +#include <asm/segment.h> +#include <asm/page.h> +#include <asm/msr.h> +#include <asm/cache.h> + +/* we are not able to switch in one step to the final KERNEL ADRESS SPACE + * because we need identity-mapped pages on setup so define __START_KERNEL to + * 0x100000 for this stage + * + */ + + .text + .code64 + .globl startup_64 +startup_64: +ENTRY(_start) + movq %rsi,xen_start_info(%rip) + +#ifdef CONFIG_SMP +ENTRY(startup_64_smp) +#endif /* CONFIG_SMP */ + + cld + + movq init_rsp(%rip),%rsp + /* zero EFLAGS after setting rsp */ + pushq $0 + popfq + movq initial_code(%rip),%rax + jmp *%rax + + /* SMP bootup changes these two */ + .globl initial_code +initial_code: + .quad x86_64_start_kernel + .globl init_rsp +init_rsp: + .quad init_thread_union+THREAD_SIZE-8 + +ENTRY(early_idt_handler) + xorl %eax,%eax + movq 8(%rsp),%rsi # get rip + movq (%rsp),%rdx + leaq early_idt_msg(%rip),%rdi +1: hlt # generate #GP + jmp 1b + +early_idt_msg: + .asciz "PANIC: early exception rip %lx error %lx cr2 %lx\n" + +#if 0 +ENTRY(lgdt_finish) + movl $(__USER_DS),%eax # DS/ES contains default USER segment + movw %ax,%ds + movw %ax,%es + movl $(__KERNEL_DS),%eax + movw %ax,%ss # after changing gdt. + popq %rax # get the retrun address + pushq $(__KERNEL_CS) + pushq %rax + lretq +#endif + +ENTRY(stext) +ENTRY(_stext) + + /* + * This default setting generates an ident mapping at address 0x100000 + * and a mapping for the kernel that precisely maps virtual address + * 0xffffffff80000000 to physical address 0x000000. (always using + * 2Mbyte large pages provided by PAE mode) + */ +.org 0x1000 +ENTRY(init_level4_pgt) + .fill 512,8,0 + + /* + * We update two pgd entries to make kernel and user pgd consistent + * at pgd_populate(). It can be used for kernel modules. So we place + * this page here for those cases to avoid memory corruption. + * We also use this page to establish the initiali mapping for + * vsyscall area. + */ +.org 0x2000 +ENTRY(init_level4_user_pgt) + .fill 512,8,0 + + /* + * In Xen the following pre-initialized pgt entries are re-initialized. + */ +.org 0x3000 +ENTRY(level3_kernel_pgt) + .fill 510,8,0 + /* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */ + .quad 0x0000000000105007 /* -> level2_kernel_pgt */ + .fill 1,8,0 + +.org 0x4000 +ENTRY(level2_ident_pgt) + /* 40MB for bootup. */ + .quad 0x0000000000000283 + .quad 0x0000000000200183 + .quad 0x0000000000400183 + .quad 0x0000000000600183 + .quad 0x0000000000800183 + .quad 0x0000000000A00183 + .quad 0x0000000000C00183 + .quad 0x0000000000E00183 + .quad 0x0000000001000183 + .quad 0x0000000001200183 + .quad 0x0000000001400183 + .quad 0x0000000001600183 + .quad 0x0000000001800183 + .quad 0x0000000001A00183 + .quad 0x0000000001C00183 + .quad 0x0000000001E00183 + .quad 0x0000000002000183 + .quad 0x0000000002200183 + .quad 0x0000000002400183 + .quad 0x0000000002600183 + /* Temporary mappings for the super early allocator in arch/x86_64/mm/init.c */ + .globl temp_boot_pmds +temp_boot_pmds: + .fill 492,8,0 + +.org 0x5000 +ENTRY(level2_kernel_pgt) + /* 40MB kernel mapping. The kernel code cannot be bigger than that. + When you change this change KERNEL_TEXT_SIZE in page.h too. */ + /* (2^48-(2*1024*1024*1024)-((2^39)*511)-((2^30)*510)) = 0 */ + .quad 0x0000000000000183 + .quad 0x0000000000200183 + .quad 0x0000000000400183 + .quad 0x0000000000600183 + .quad 0x0000000000800183 + .quad 0x0000000000A00183 + .quad 0x0000000000C00183 + .quad 0x0000000000E00183 + .quad 0x0000000001000183 + .quad 0x0000000001200183 + .quad 0x0000000001400183 + .quad 0x0000000001600183 + .quad 0x0000000001800183 + .quad 0x0000000001A00183 + .quad 0x0000000001C00183 + .quad 0x0000000001E00183 + .quad 0x0000000002000183 + .quad 0x0000000002200183 + .quad 0x0000000002400183 + .quad 0x0000000002600183 + /* Module mapping starts here */ + .fill 492,8,0 + + /* + * This is used for vsyscall area mapping as we have a different + * level4 page table for user. + */ +.org 0x6000 +ENTRY(level3_user_pgt) + .fill 512,8,0 + +.org 0x7000 +ENTRY(cpu_gdt_table) +/* The TLS descriptors are currently at a different place compared to i386. + Hopefully nobody expects them at a fixed place (Wine?) */ + .quad 0x0000000000000000 /* NULL descriptor */ + .quad 0x008ffa000000ffff /* __KERNEL_COMPAT32_CS */ + .quad 0x00affa000000ffff /* __KERNEL_CS */ + .quad 0x00cff2000000ffff /* __KERNEL_DS */ + + .quad 0x00cffa000000ffff /* __USER32_CS */ + .quad 0x00cff2000000ffff /* __USER_DS, __USER32_DS */ + .quad 0x00affa000000ffff /* __USER_CS */ + .quad 0x00cffa000000ffff /* __KERNEL32_CS */ + .quad 0,0 /* TSS */ + .quad 0,0 /* LDT */ + .quad 0,0,0 /* three TLS descriptors */ + .quad 0 /* unused now? __KERNEL16_CS - 16bit PM for S3 wakeup. */ + +gdt_end: +#if 0 + /* asm/segment.h:GDT_ENTRIES must match this */ + /* This should be a multiple of the cache line size */ + /* GDTs of other CPUs: */ + .fill (GDT_SIZE * NR_CPUS) - (gdt_end - cpu_gdt_table) +#endif + +.org 0x8000 +ENTRY(empty_zero_page) + +.org 0x9000 +ENTRY(empty_bad_page) + +.org 0xa000 +ENTRY(empty_bad_pte_table) + +.org 0xb000 +ENTRY(empty_bad_pmd_table) + +.org 0xc000 +ENTRY(level3_physmem_pgt) + .quad 0x0000000000105007 /* -> level2_kernel_pgt (so that __va works even before pagetable_init) */ + +.org 0xd000 +ENTRY(hypercall_page) + +.org 0xe000 +#ifdef CONFIG_ACPI_SLEEP +ENTRY(wakeup_level4_pgt) + .quad 0x0000000000102007 /* -> level3_ident_pgt */ + .fill 255,8,0 + .quad 0x000000000010a007 + .fill 254,8,0 + /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ + .quad 0x0000000000103007 /* -> level3_kernel_pgt */ +#endif + + .data + + .align 16 + .globl cpu_gdt_descr +cpu_gdt_descr: + .word gdt_end-cpu_gdt_table +gdt: + .quad cpu_gdt_table +#ifdef CONFIG_SMP + .rept NR_CPUS-1 + .word 0 + .quad 0 + .endr +#endif + +/* We need valid kernel segments for data and code in long mode too + * IRET will check the segment types kkeil 2000/10/28 + * Also sysret mandates a special GDT layout + */ + +#if 0 +.align L1_CACHE_BYTES +#endif + .align L1_CACHE_BYTES +ENTRY(idt_table) + .rept 256 + .quad 0 + .quad 0 + .endr + diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/head64-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/head64-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,127 @@ +/* + * linux/arch/x86_64/kernel/head64.c -- prepare to run common code + * + * Copyright (C) 2000 Andrea Arcangeli <andrea@xxxxxxx> SuSE + * + * $Id: head64.c,v 1.22 2001/07/06 14:28:20 ak Exp $ + * + * Jun Nakajima <jun.nakajima@xxxxxxxxx> + * Modified for Xen. + */ + +#include <linux/init.h> +#include <linux/linkage.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/percpu.h> + +#include <asm/processor.h> +#include <asm/proto.h> +#include <asm/smp.h> +#include <asm/bootsetup.h> +#include <asm/setup.h> +#include <asm/desc.h> + +unsigned long start_pfn; + +/* Don't add a printk in there. printk relies on the PDA which is not initialized + yet. */ +#if 0 +static void __init clear_bss(void) +{ + extern char __bss_start[], __bss_end[]; + memset(__bss_start, 0, + (unsigned long) __bss_end - (unsigned long) __bss_start); +} +#endif + +#define NEW_CL_POINTER 0x228 /* Relative to real mode data */ +#define OLD_CL_MAGIC_ADDR 0x90020 +#define OLD_CL_MAGIC 0xA33F +#define OLD_CL_BASE_ADDR 0x90000 +#define OLD_CL_OFFSET 0x90022 + +extern char saved_command_line[]; + +#if 0 +static void __init copy_bootdata(char *real_mode_data) +{ + int new_data; + char * command_line; + + memcpy(x86_boot_params, real_mode_data, BOOT_PARAM_SIZE); + new_data = *(int *) (x86_boot_params + NEW_CL_POINTER); + if (!new_data) { + if (OLD_CL_MAGIC != * (u16 *) OLD_CL_MAGIC_ADDR) { + printk("so old bootloader that it does not support commandline?!\n"); + return; + } + new_data = OLD_CL_BASE_ADDR + * (u16 *) OLD_CL_OFFSET; + printk("old bootloader convention, maybe loadlin?\n"); + } + command_line = (char *) ((u64)(new_data)); + memcpy(saved_command_line, command_line, COMMAND_LINE_SIZE); + printk("Bootdata ok (command line is %s)\n", saved_command_line); +} +#endif + +static void __init setup_boot_cpu_data(void) +{ + unsigned int dummy, eax; + + /* get vendor info */ + cpuid(0, (unsigned int *)&boot_cpu_data.cpuid_level, + (unsigned int *)&boot_cpu_data.x86_vendor_id[0], + (unsigned int *)&boot_cpu_data.x86_vendor_id[8], + (unsigned int *)&boot_cpu_data.x86_vendor_id[4]); + + /* get cpu type */ + cpuid(1, &eax, &dummy, &dummy, + (unsigned int *) &boot_cpu_data.x86_capability); + boot_cpu_data.x86 = (eax >> 8) & 0xf; + boot_cpu_data.x86_model = (eax >> 4) & 0xf; + boot_cpu_data.x86_mask = eax & 0xf; +} + +extern char _end[]; + +void __init x86_64_start_kernel(char * real_mode_data) +{ + int i; + + phys_to_machine_mapping = (unsigned long *)xen_start_info->mfn_list; + start_pfn = (__pa(xen_start_info->pt_base) >> PAGE_SHIFT) + + xen_start_info->nr_pt_frames; + + for (i = 0; i < 256; i++) + set_intr_gate(i, early_idt_handler); +#if 0 + asm volatile("lidt %0" :: "m" (idt_descr)); +#endif + pda_init(0); + /* copy_bootdata(real_mode_data); */ +#ifdef CONFIG_SMP + cpu_set(0, cpu_online_map); +#endif +#if 0 + s = strstr(saved_command_line, "earlyprintk="); + if (s != NULL) + setup_early_printk(s); +#endif +#ifdef CONFIG_DISCONTIGMEM + s = strstr(saved_command_line, "numa="); + if (s != NULL) + numa_setup(s+5); +#endif +#ifdef CONFIG_X86_IO_APIC + if (strstr(saved_command_line, "disableapic")) + disable_apic = 1; +#endif + /* You need early console to see that */ + if (__pa_symbol(&_end) >= KERNEL_TEXT_SIZE) + panic("Kernel too big for kernel mapping\n"); + + setup_boot_cpu_data(); + start_kernel(); +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/i387.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/i387.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,155 @@ +/* + * linux/arch/x86_64/kernel/i387.c + * + * Copyright (C) 1994 Linus Torvalds + * Copyright (C) 2002 Andi Kleen, SuSE Labs + * + * Pentium III FXSR, SSE support + * General FPU state handling cleanups + * Gareth Hughes <gareth@xxxxxxxxxxx>, May 2000 + * + * x86-64 rework 2002 Andi Kleen. + * Does direct fxsave in and out of user space now for signal handlers. + * All the FSAVE<->FXSAVE conversion code has been moved to the 32bit emulation, + * the 64bit user space sees a FXSAVE frame directly. + */ + +#include <linux/config.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <asm/processor.h> +#include <asm/i387.h> +#include <asm/sigcontext.h> +#include <asm/user.h> +#include <asm/ptrace.h> +#include <asm/uaccess.h> + +unsigned int mxcsr_feature_mask = 0xffffffff; + +void mxcsr_feature_mask_init(void) +{ + unsigned int mask; + clts(); + memset(&current->thread.i387.fxsave, 0, sizeof(struct i387_fxsave_struct)); + asm volatile("fxsave %0" : : "m" (current->thread.i387.fxsave)); + mask = current->thread.i387.fxsave.mxcsr_mask; + if (mask == 0) mask = 0x0000ffbf; + mxcsr_feature_mask &= mask; + stts(); +} + +/* + * Called at bootup to set up the initial FPU state that is later cloned + * into all processes. + */ +void __cpuinit fpu_init(void) +{ + unsigned long oldcr0 = read_cr0(); + extern void __bad_fxsave_alignment(void); + + if (offsetof(struct task_struct, thread.i387.fxsave) & 15) + __bad_fxsave_alignment(); + set_in_cr4(X86_CR4_OSFXSR); + set_in_cr4(X86_CR4_OSXMMEXCPT); + + write_cr0(oldcr0 & ~((1UL<<3)|(1UL<<2))); /* clear TS and EM */ + + mxcsr_feature_mask_init(); + /* clean state in init */ + current_thread_info()->status = 0; + clear_used_math(); +} + +void init_fpu(struct task_struct *child) +{ + if (tsk_used_math(child)) { + if (child == current) + unlazy_fpu(child); + return; + } + memset(&child->thread.i387.fxsave, 0, sizeof(struct i387_fxsave_struct)); + child->thread.i387.fxsave.cwd = 0x37f; + child->thread.i387.fxsave.mxcsr = 0x1f80; + /* only the device not available exception or ptrace can call init_fpu */ + set_stopped_child_used_math(child); +} + +/* + * Signal frame handlers. + */ + +int save_i387(struct _fpstate __user *buf) +{ + struct task_struct *tsk = current; + int err = 0; + + { + extern void bad_user_i387_struct(void); + if (sizeof(struct user_i387_struct) != sizeof(tsk->thread.i387.fxsave)) + bad_user_i387_struct(); + } + + if ((unsigned long)buf % 16) + printk("save_i387: bad fpstate %p\n",buf); + + if (!used_math()) + return 0; + clear_used_math(); /* trigger finit */ + if (tsk->thread_info->status & TS_USEDFPU) { + err = save_i387_checking((struct i387_fxsave_struct __user *)buf); + if (err) return err; + stts(); + } else { + if (__copy_to_user(buf, &tsk->thread.i387.fxsave, + sizeof(struct i387_fxsave_struct))) + return -1; + } + return 1; +} + +/* + * ptrace request handlers. + */ + +int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *tsk) +{ + init_fpu(tsk); + return __copy_to_user(buf, &tsk->thread.i387.fxsave, + sizeof(struct user_i387_struct)) ? -EFAULT : 0; +} + +int set_fpregs(struct task_struct *tsk, struct user_i387_struct __user *buf) +{ + if (__copy_from_user(&tsk->thread.i387.fxsave, buf, + sizeof(struct user_i387_struct))) + return -EFAULT; + return 0; +} + +/* + * FPU state for core dumps. + */ + +int dump_fpu( struct pt_regs *regs, struct user_i387_struct *fpu ) +{ + struct task_struct *tsk = current; + + if (!used_math()) + return 0; + + unlazy_fpu(tsk); + memcpy(fpu, &tsk->thread.i387.fxsave, sizeof(struct user_i387_struct)); + return 1; +} + +int dump_task_fpu(struct task_struct *tsk, struct user_i387_struct *fpu) +{ + int fpvalid = !!tsk_used_math(tsk); + + if (fpvalid) { + if (tsk == current) + unlazy_fpu(tsk); + memcpy(fpu, &tsk->thread.i387.fxsave, sizeof(struct user_i387_struct)); +} + return fpvalid; +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/io_apic-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/io_apic-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,1992 @@ +/* + * Intel IO-APIC support for multi-Pentium hosts. + * + * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar, Hajnalka Szabo + * + * Many thanks to Stig Venaas for trying out countless experimental + * patches and reporting/debugging problems patiently! + * + * (c) 1999, Multiple IO-APIC support, developed by + * Ken-ichi Yaku <yaku@xxxxxxxxxxxxxxxxxxxx> and + * Hidemi Kishimoto <kisimoto@xxxxxxxxxxxxxxxxxxxx>, + * further tested and cleaned up by Zach Brown <zab@xxxxxxxxxx> + * and Ingo Molnar <mingo@xxxxxxxxxx> + * + * Fixes + * Maciej W. Rozycki : Bits for genuine 82489DX APICs; + * thanks to Eric Gilmore + * and Rolf G. Tews + * for testing these extensively + * Paul Diefenbaugh : Added full ACPI support + */ + +#include <linux/mm.h> +#include <linux/irq.h> +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/sched.h> +#include <linux/config.h> +#include <linux/smp_lock.h> +#include <linux/mc146818rtc.h> +#include <linux/acpi.h> +#include <linux/sysdev.h> + +#include <asm/io.h> +#include <asm/smp.h> +#include <asm/desc.h> +#include <asm/proto.h> +#include <asm/mach_apic.h> +#include <asm/acpi.h> + +#define __apicdebuginit __init + +int sis_apic_bug; /* not actually supported, dummy for compile */ + +static int no_timer_check; + +static DEFINE_SPINLOCK(ioapic_lock); + +/* + * # of IRQ routing registers + */ +int nr_ioapic_registers[MAX_IO_APICS]; + +/* + * Rough estimation of how many shared IRQs there are, can + * be changed anytime. + */ +#define MAX_PLUS_SHARED_IRQS NR_IRQS +#define PIN_MAP_SIZE (MAX_PLUS_SHARED_IRQS + NR_IRQS) + +/* + * This is performance-critical, we want to do it O(1) + * + * the indexing order of this array favors 1:1 mappings + * between pins and IRQs. + */ + +static struct irq_pin_list { + short apic, pin, next; +} irq_2_pin[PIN_MAP_SIZE]; + +int vector_irq[NR_VECTORS] = { [0 ... NR_VECTORS - 1] = -1}; +#ifdef CONFIG_PCI_MSI +#define vector_to_irq(vector) \ + (platform_legacy_irq(vector) ? vector : vector_irq[vector]) +#else +#define vector_to_irq(vector) (vector) +#endif + +#ifdef CONFIG_XEN + +#include <xen/interface/xen.h> +#include <xen/interface/physdev.h> + +/* Fake i8259 */ +#define make_8259A_irq(_irq) (io_apic_irqs &= ~(1UL<<(_irq))) +#define disable_8259A_irq(_irq) ((void)0) +#define i8259A_irq_pending(_irq) (0) + +unsigned long io_apic_irqs; + +static inline unsigned int xen_io_apic_read(unsigned int apic, unsigned int reg) +{ + physdev_op_t op; + int ret; + + op.cmd = PHYSDEVOP_APIC_READ; + op.u.apic_op.apic = mp_ioapics[apic].mpc_apicid; + op.u.apic_op.offset = reg; + ret = HYPERVISOR_physdev_op(&op); + if (ret) + return ret; + return op.u.apic_op.value; +} + +static inline void xen_io_apic_write(unsigned int apic, unsigned int reg, unsigned int value) +{ + physdev_op_t op; + + op.cmd = PHYSDEVOP_APIC_WRITE; + op.u.apic_op.apic = mp_ioapics[apic].mpc_apicid; + op.u.apic_op.offset = reg; + op.u.apic_op.value = value; + HYPERVISOR_physdev_op(&op); +} + +#define io_apic_read(a,r) xen_io_apic_read(a,r) +#define io_apic_write(a,r,v) xen_io_apic_write(a,r,v) + +#define clear_IO_APIC() ((void)0) + +#endif /* !CONFIG_XEN */ + +/* + * The common case is 1:1 IRQ<->pin mappings. Sometimes there are + * shared ISA-space IRQs, so we have to support them. We are super + * fast in the common case, and fast for shared ISA-space IRQs. + */ +static void add_pin_to_irq(unsigned int irq, int apic, int pin) +{ + static int first_free_entry = NR_IRQS; + struct irq_pin_list *entry = irq_2_pin + irq; + + while (entry->next) + entry = irq_2_pin + entry->next; + + if (entry->pin != -1) { + entry->next = first_free_entry; + entry = irq_2_pin + entry->next; + if (++first_free_entry >= PIN_MAP_SIZE) + panic("io_apic.c: whoops"); + } + entry->apic = apic; + entry->pin = pin; +} + +#ifndef CONFIG_XEN +#define __DO_ACTION(R, ACTION, FINAL) \ + \ +{ \ + int pin; \ + struct irq_pin_list *entry = irq_2_pin + irq; \ + \ + for (;;) { \ + unsigned int reg; \ + pin = entry->pin; \ + if (pin == -1) \ + break; \ + reg = io_apic_read(entry->apic, 0x10 + R + pin*2); \ + reg ACTION; \ + io_apic_modify(entry->apic, reg); \ + if (!entry->next) \ + break; \ + entry = irq_2_pin + entry->next; \ + } \ + FINAL; \ +} + +#define DO_ACTION(name,R,ACTION, FINAL) \ + \ + static void name##_IO_APIC_irq (unsigned int irq) \ + __DO_ACTION(R, ACTION, FINAL) + +DO_ACTION( __mask, 0, |= 0x00010000, io_apic_sync(entry->apic) ) + /* mask = 1 */ +DO_ACTION( __unmask, 0, &= 0xfffeffff, ) + /* mask = 0 */ + +static void mask_IO_APIC_irq (unsigned int irq) +{ + unsigned long flags; + + spin_lock_irqsave(&ioapic_lock, flags); + __mask_IO_APIC_irq(irq); + spin_unlock_irqrestore(&ioapic_lock, flags); +} + +static void unmask_IO_APIC_irq (unsigned int irq) +{ + unsigned long flags; + + spin_lock_irqsave(&ioapic_lock, flags); + __unmask_IO_APIC_irq(irq); + spin_unlock_irqrestore(&ioapic_lock, flags); +} + +static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) +{ + struct IO_APIC_route_entry entry; + unsigned long flags; + + /* Check delivery_mode to be sure we're not clearing an SMI pin */ + spin_lock_irqsave(&ioapic_lock, flags); + *(((int*)&entry) + 0) = io_apic_read(apic, 0x10 + 2 * pin); + *(((int*)&entry) + 1) = io_apic_read(apic, 0x11 + 2 * pin); + spin_unlock_irqrestore(&ioapic_lock, flags); + if (entry.delivery_mode == dest_SMI) + return; + /* + * Disable it in the IO-APIC irq-routing table: + */ + memset(&entry, 0, sizeof(entry)); + entry.mask = 1; + spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(apic, 0x10 + 2 * pin, *(((int *)&entry) + 0)); + io_apic_write(apic, 0x11 + 2 * pin, *(((int *)&entry) + 1)); + spin_unlock_irqrestore(&ioapic_lock, flags); +} + +static void clear_IO_APIC (void) +{ + int apic, pin; + + for (apic = 0; apic < nr_ioapics; apic++) + for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) + clear_IO_APIC_pin(apic, pin); +} + +#endif /* !CONFIG_XEN */ + +/* + * support for broken MP BIOSs, enables hand-redirection of PIRQ0-7 to + * specific CPU-side IRQs. + */ + +#define MAX_PIRQS 8 +static int pirq_entries [MAX_PIRQS]; +static int pirqs_enabled; +int skip_ioapic_setup; +int ioapic_force; + +/* dummy parsing: see setup.c */ + +static int __init disable_ioapic_setup(char *str) +{ + skip_ioapic_setup = 1; + return 1; +} + +static int __init enable_ioapic_setup(char *str) +{ + ioapic_force = 1; + skip_ioapic_setup = 0; + return 1; +} + +__setup("noapic", disable_ioapic_setup); +__setup("apic", enable_ioapic_setup); + +#include <asm/pci-direct.h> +#include <linux/pci_ids.h> +#include <linux/pci.h> + +/* Temporary Hack. Nvidia and VIA boards currently only work with IO-APIC + off. Check for an Nvidia or VIA PCI bridge and turn it off. + Use pci direct infrastructure because this runs before the PCI subsystem. + + Can be overwritten with "apic" + + And another hack to disable the IOMMU on VIA chipsets. + + Kludge-O-Rama. */ +void __init check_ioapic(void) +{ + int num,slot,func; + if (ioapic_force) + return; + + /* Poor man's PCI discovery */ + for (num = 0; num < 32; num++) { + for (slot = 0; slot < 32; slot++) { + for (func = 0; func < 8; func++) { + u32 class; + u32 vendor; + u8 type; + class = read_pci_config(num,slot,func, + PCI_CLASS_REVISION); + if (class == 0xffffffff) + break; + + if ((class >> 16) != PCI_CLASS_BRIDGE_PCI) + continue; + + vendor = read_pci_config(num, slot, func, + PCI_VENDOR_ID); + vendor &= 0xffff; + switch (vendor) { + case PCI_VENDOR_ID_VIA: +#ifdef CONFIG_GART_IOMMU + if ((end_pfn >= (0xffffffff>>PAGE_SHIFT) || + force_iommu) && + !iommu_aperture_allowed) { + printk(KERN_INFO + "Looks like a VIA chipset. Disabling IOMMU. Overwrite with \"iommu=allowed\"\n"); + iommu_aperture_disabled = 1; + } +#endif + return; + case PCI_VENDOR_ID_NVIDIA: +#ifdef CONFIG_ACPI + /* All timer overrides on Nvidia + seem to be wrong. Skip them. */ + acpi_skip_timer_override = 1; + printk(KERN_INFO + "Nvidia board detected. Ignoring ACPI timer override.\n"); +#endif + /* RED-PEN skip them on mptables too? */ + return; + } + + /* No multi-function device? */ + type = read_pci_config_byte(num,slot,func, + PCI_HEADER_TYPE); + if (!(type & 0x80)) + break; + } + } + } +} + +static int __init ioapic_pirq_setup(char *str) +{ + int i, max; + int ints[MAX_PIRQS+1]; + + get_options(str, ARRAY_SIZE(ints), ints); + + for (i = 0; i < MAX_PIRQS; i++) + pirq_entries[i] = -1; + + pirqs_enabled = 1; + apic_printk(APIC_VERBOSE, "PIRQ redirection, working around broken MP-BIOS.\n"); + max = MAX_PIRQS; + if (ints[0] < MAX_PIRQS) + max = ints[0]; + + for (i = 0; i < max; i++) { + apic_printk(APIC_VERBOSE, "... PIRQ%d -> IRQ %d\n", i, ints[i+1]); + /* + * PIRQs are mapped upside down, usually. + */ + pirq_entries[MAX_PIRQS-i-1] = ints[i+1]; + } + return 1; +} + +__setup("pirq=", ioapic_pirq_setup); + +/* + * Find the IRQ entry number of a certain pin. + */ +static int find_irq_entry(int apic, int pin, int type) +{ + int i; + + for (i = 0; i < mp_irq_entries; i++) + if (mp_irqs[i].mpc_irqtype == type && + (mp_irqs[i].mpc_dstapic == mp_ioapics[apic].mpc_apicid || + mp_irqs[i].mpc_dstapic == MP_APIC_ALL) && + mp_irqs[i].mpc_dstirq == pin) + return i; + + return -1; +} + +#ifndef CONFIG_XEN +/* + * Find the pin to which IRQ[irq] (ISA) is connected + */ +static int __init find_isa_irq_pin(int irq, int type) +{ + int i; + + for (i = 0; i < mp_irq_entries; i++) { + int lbus = mp_irqs[i].mpc_srcbus; + + if ((mp_bus_id_to_type[lbus] == MP_BUS_ISA || + mp_bus_id_to_type[lbus] == MP_BUS_EISA || + mp_bus_id_to_type[lbus] == MP_BUS_MCA) && + (mp_irqs[i].mpc_irqtype == type) && + (mp_irqs[i].mpc_srcbusirq == irq)) + + return mp_irqs[i].mpc_dstirq; + } + return -1; +} +#endif + +/* + * Find a specific PCI IRQ entry. + * Not an __init, possibly needed by modules + */ +static int pin_2_irq(int idx, int apic, int pin); + +int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin) +{ + int apic, i, best_guess = -1; + + apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n", + bus, slot, pin); + if (mp_bus_id_to_pci_bus[bus] == -1) { + apic_printk(APIC_VERBOSE, "PCI BIOS passed nonexistent PCI bus %d!\n", bus); + return -1; + } + for (i = 0; i < mp_irq_entries; i++) { + int lbus = mp_irqs[i].mpc_srcbus; + + for (apic = 0; apic < nr_ioapics; apic++) + if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic || + mp_irqs[i].mpc_dstapic == MP_APIC_ALL) + break; + + if ((mp_bus_id_to_type[lbus] == MP_BUS_PCI) && + !mp_irqs[i].mpc_irqtype && + (bus == lbus) && + (slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) { + int irq = pin_2_irq(i,apic,mp_irqs[i].mpc_dstirq); + + if (!(apic || IO_APIC_IRQ(irq))) + continue; + + if (pin == (mp_irqs[i].mpc_srcbusirq & 3)) + return irq; + /* + * Use the first all-but-pin matching entry as a + * best-guess fuzzy result for broken mptables. + */ + if (best_guess < 0) + best_guess = irq; + } + } + return best_guess; +} + +/* + * EISA Edge/Level control register, ELCR + */ +static int EISA_ELCR(unsigned int irq) +{ + if (irq < 16) { + unsigned int port = 0x4d0 + (irq >> 3); + return (inb(port) >> (irq & 7)) & 1; + } + apic_printk(APIC_VERBOSE, "Broken MPtable reports ISA irq %d\n", irq); + return 0; +} + +/* EISA interrupts are always polarity zero and can be edge or level + * trigger depending on the ELCR value. If an interrupt is listed as + * EISA conforming in the MP table, that means its trigger type must + * be read in from the ELCR */ + +#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].mpc_srcbusirq)) +#define default_EISA_polarity(idx) (0) + +/* ISA interrupts are always polarity zero edge triggered, + * when listed as conforming in the MP table. */ + +#define default_ISA_trigger(idx) (0) +#define default_ISA_polarity(idx) (0) + +/* PCI interrupts are always polarity one level triggered, + * when listed as conforming in the MP table. */ + +#define default_PCI_trigger(idx) (1) +#define default_PCI_polarity(idx) (1) + +/* MCA interrupts are always polarity zero level triggered, + * when listed as conforming in the MP table. */ + +#define default_MCA_trigger(idx) (1) +#define default_MCA_polarity(idx) (0) + +static int __init MPBIOS_polarity(int idx) +{ + int bus = mp_irqs[idx].mpc_srcbus; + int polarity; + + /* + * Determine IRQ line polarity (high active or low active): + */ + switch (mp_irqs[idx].mpc_irqflag & 3) + { + case 0: /* conforms, ie. bus-type dependent polarity */ + { + switch (mp_bus_id_to_type[bus]) + { + case MP_BUS_ISA: /* ISA pin */ + { + polarity = default_ISA_polarity(idx); + break; + } + case MP_BUS_EISA: /* EISA pin */ + { + polarity = default_EISA_polarity(idx); + break; + } + case MP_BUS_PCI: /* PCI pin */ + { + polarity = default_PCI_polarity(idx); + break; + } + case MP_BUS_MCA: /* MCA pin */ + { + polarity = default_MCA_polarity(idx); + break; + } + default: + { + printk(KERN_WARNING "broken BIOS!!\n"); + polarity = 1; + break; + } + } + break; + } + case 1: /* high active */ + { + polarity = 0; + break; + } + case 2: /* reserved */ + { + printk(KERN_WARNING "broken BIOS!!\n"); + polarity = 1; + break; + } + case 3: /* low active */ + { + polarity = 1; + break; + } + default: /* invalid */ + { + printk(KERN_WARNING "broken BIOS!!\n"); + polarity = 1; + break; + } + } + return polarity; +} + +static int MPBIOS_trigger(int idx) +{ + int bus = mp_irqs[idx].mpc_srcbus; + int trigger; + + /* + * Determine IRQ trigger mode (edge or level sensitive): + */ + switch ((mp_irqs[idx].mpc_irqflag>>2) & 3) + { + case 0: /* conforms, ie. bus-type dependent */ + { + switch (mp_bus_id_to_type[bus]) + { + case MP_BUS_ISA: /* ISA pin */ + { + trigger = default_ISA_trigger(idx); + break; + } + case MP_BUS_EISA: /* EISA pin */ + { + trigger = default_EISA_trigger(idx); + break; + } + case MP_BUS_PCI: /* PCI pin */ + { + trigger = default_PCI_trigger(idx); + break; + } + case MP_BUS_MCA: /* MCA pin */ + { + trigger = default_MCA_trigger(idx); + break; + } + default: + { + printk(KERN_WARNING "broken BIOS!!\n"); + trigger = 1; + break; + } + } + break; + } + case 1: /* edge */ + { + trigger = 0; + break; + } + case 2: /* reserved */ + { + printk(KERN_WARNING "broken BIOS!!\n"); + trigger = 1; + break; + } + case 3: /* level */ + { + trigger = 1; + break; + } + default: /* invalid */ + { + printk(KERN_WARNING "broken BIOS!!\n"); + trigger = 0; + break; + } + } + return trigger; +} + +static inline int irq_polarity(int idx) +{ + return MPBIOS_polarity(idx); +} + +static inline int irq_trigger(int idx) +{ + return MPBIOS_trigger(idx); +} + +static int pin_2_irq(int idx, int apic, int pin) +{ + int irq, i; + int bus = mp_irqs[idx].mpc_srcbus; + + /* + * Debugging check, we are in big trouble if this message pops up! + */ + if (mp_irqs[idx].mpc_dstirq != pin) + printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n"); + + switch (mp_bus_id_to_type[bus]) + { + case MP_BUS_ISA: /* ISA pin */ + case MP_BUS_EISA: + case MP_BUS_MCA: + { + irq = mp_irqs[idx].mpc_srcbusirq; + break; + } + case MP_BUS_PCI: /* PCI pin */ + { + /* + * PCI IRQs are mapped in order + */ + i = irq = 0; + while (i < apic) + irq += nr_ioapic_registers[i++]; + irq += pin; + break; + } + default: + { + printk(KERN_ERR "unknown bus type %d.\n",bus); + irq = 0; + break; + } + } + + /* + * PCI IRQ command line redirection. Yes, limits are hardcoded. + */ + if ((pin >= 16) && (pin <= 23)) { + if (pirq_entries[pin-16] != -1) { + if (!pirq_entries[pin-16]) { + apic_printk(APIC_VERBOSE, "disabling PIRQ%d\n", pin-16); + } else { + irq = pirq_entries[pin-16]; + apic_printk(APIC_VERBOSE, "using PIRQ%d -> IRQ %d\n", + pin-16, irq); + } + } + } + return irq; +} + +static inline int IO_APIC_irq_trigger(int irq) +{ + int apic, idx, pin; + + for (apic = 0; apic < nr_ioapics; apic++) { + for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { + idx = find_irq_entry(apic,pin,mp_INT); + if ((idx != -1) && (irq == pin_2_irq(idx,apic,pin))) + return irq_trigger(idx); + } + } + /* + * nonexistent IRQs are edge default + */ + return 0; +} + +/* irq_vectors is indexed by the sum of all RTEs in all I/O APICs. */ +u8 irq_vector[NR_IRQ_VECTORS]; + +int assign_irq_vector(int irq) +{ + static int current_vector = FIRST_DEVICE_VECTOR; + physdev_op_t op; + + BUG_ON(irq >= NR_IRQ_VECTORS); + if (irq != AUTO_ASSIGN && IO_APIC_VECTOR(irq) > 0) + return IO_APIC_VECTOR(irq); + + op.cmd = PHYSDEVOP_ASSIGN_VECTOR; + op.u.irq_op.irq = irq; + if (HYPERVISOR_physdev_op(&op)) + return -ENOSPC; + current_vector = op.u.irq_op.vector; + + vector_irq[current_vector] = irq; + if (irq != AUTO_ASSIGN) + IO_APIC_VECTOR(irq) = current_vector; + + return current_vector; +} + +extern void (*interrupt[NR_IRQS])(void); +#ifndef CONFIG_XEN +static struct hw_interrupt_type ioapic_level_type; +static struct hw_interrupt_type ioapic_edge_type; + +#define IOAPIC_AUTO -1 +#define IOAPIC_EDGE 0 +#define IOAPIC_LEVEL 1 + +static inline void ioapic_register_intr(int irq, int vector, unsigned long trigger) +{ + if (use_pci_vector() && !platform_legacy_irq(irq)) { + if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) || + trigger == IOAPIC_LEVEL) + irq_desc[vector].handler = &ioapic_level_type; + else + irq_desc[vector].handler = &ioapic_edge_type; + set_intr_gate(vector, interrupt[vector]); + } else { + if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) || + trigger == IOAPIC_LEVEL) + irq_desc[irq].handler = &ioapic_level_type; + else + irq_desc[irq].handler = &ioapic_edge_type; + set_intr_gate(vector, interrupt[irq]); + } +} +#else +#define ioapic_register_intr(_irq,_vector,_trigger) ((void)0) +#endif /* !CONFIG_XEN */ + +static void __init setup_IO_APIC_irqs(void) +{ + struct IO_APIC_route_entry entry; + int apic, pin, idx, irq, first_notcon = 1, vector; + unsigned long flags; + + apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n"); + + for (apic = 0; apic < nr_ioapics; apic++) { + for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { + + /* + * add it to the IO-APIC irq-routing table: + */ + memset(&entry,0,sizeof(entry)); + + entry.delivery_mode = INT_DELIVERY_MODE; + entry.dest_mode = INT_DEST_MODE; + entry.mask = 0; /* enable IRQ */ + entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS); + + idx = find_irq_entry(apic,pin,mp_INT); + if (idx == -1) { + if (first_notcon) { + apic_printk(APIC_VERBOSE, KERN_DEBUG " IO-APIC (apicid-pin) %d-%d", mp_ioapics[apic].mpc_apicid, pin); + first_notcon = 0; + } else + apic_printk(APIC_VERBOSE, ", %d-%d", mp_ioapics[apic].mpc_apicid, pin); + continue; + } + + entry.trigger = irq_trigger(idx); + entry.polarity = irq_polarity(idx); + + if (irq_trigger(idx)) { + entry.trigger = 1; + entry.mask = 1; + entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS); + } + + irq = pin_2_irq(idx, apic, pin); + add_pin_to_irq(irq, apic, pin); + + if (/* !apic && */ !IO_APIC_IRQ(irq)) + continue; + + if (IO_APIC_IRQ(irq)) { + vector = assign_irq_vector(irq); + entry.vector = vector; + + ioapic_register_intr(irq, vector, IOAPIC_AUTO); + if (!apic && (irq < 16)) + disable_8259A_irq(irq); + } + spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(apic, 0x11+2*pin, *(((int *)&entry)+1)); + io_apic_write(apic, 0x10+2*pin, *(((int *)&entry)+0)); + spin_unlock_irqrestore(&ioapic_lock, flags); + } + } + + if (!first_notcon) + apic_printk(APIC_VERBOSE," not connected.\n"); +} + +#ifndef CONFIG_XEN +/* + * Set up the 8259A-master output pin as broadcast to all + * CPUs. + */ +static void __init setup_ExtINT_IRQ0_pin(unsigned int pin, int vector) +{ + struct IO_APIC_route_entry entry; + unsigned long flags; + + memset(&entry,0,sizeof(entry)); + + disable_8259A_irq(0); + + /* mask LVT0 */ + apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); + + /* + * We use logical delivery to get the timer IRQ + * to the first CPU. + */ + entry.dest_mode = INT_DEST_MODE; + entry.mask = 0; /* unmask IRQ now */ + entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS); + entry.delivery_mode = INT_DELIVERY_MODE; + entry.polarity = 0; + entry.trigger = 0; + entry.vector = vector; + + /* + * The timer IRQ doesn't have to know that behind the + * scene we have a 8259A-master in AEOI mode ... + */ + irq_desc[0].handler = &ioapic_edge_type; + + /* + * Add it to the IO-APIC irq-routing table: + */ + spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(0, 0x11+2*pin, *(((int *)&entry)+1)); + io_apic_write(0, 0x10+2*pin, *(((int *)&entry)+0)); + spin_unlock_irqrestore(&ioapic_lock, flags); + + enable_8259A_irq(0); +} + +void __init UNEXPECTED_IO_APIC(void) +{ +} + +void __apicdebuginit print_IO_APIC(void) +{ + int apic, i; + union IO_APIC_reg_00 reg_00; + union IO_APIC_reg_01 reg_01; + union IO_APIC_reg_02 reg_02; + unsigned long flags; + + if (apic_verbosity == APIC_QUIET) + return; + + printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries); + for (i = 0; i < nr_ioapics; i++) + printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n", + mp_ioapics[i].mpc_apicid, nr_ioapic_registers[i]); + + /* + * We are a bit conservative about what we expect. We have to + * know about every hardware change ASAP. + */ + printk(KERN_INFO "testing the IO APIC.......................\n"); + + for (apic = 0; apic < nr_ioapics; apic++) { + + spin_lock_irqsave(&ioapic_lock, flags); + reg_00.raw = io_apic_read(apic, 0); + reg_01.raw = io_apic_read(apic, 1); + if (reg_01.bits.version >= 0x10) + reg_02.raw = io_apic_read(apic, 2); + spin_unlock_irqrestore(&ioapic_lock, flags); + + printk("\n"); + printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mpc_apicid); + printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw); + printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID); + if (reg_00.bits.__reserved_1 || reg_00.bits.__reserved_2) + UNEXPECTED_IO_APIC(); + + printk(KERN_DEBUG ".... register #01: %08X\n", *(int *)&reg_01); + printk(KERN_DEBUG "....... : max redirection entries: %04X\n", reg_01.bits.entries); + if ( (reg_01.bits.entries != 0x0f) && /* older (Neptune) boards */ + (reg_01.bits.entries != 0x17) && /* typical ISA+PCI boards */ + (reg_01.bits.entries != 0x1b) && /* Compaq Proliant boards */ + (reg_01.bits.entries != 0x1f) && /* dual Xeon boards */ + (reg_01.bits.entries != 0x22) && /* bigger Xeon boards */ + (reg_01.bits.entries != 0x2E) && + (reg_01.bits.entries != 0x3F) && + (reg_01.bits.entries != 0x03) + ) + UNEXPECTED_IO_APIC(); + + printk(KERN_DEBUG "....... : PRQ implemented: %X\n", reg_01.bits.PRQ); + printk(KERN_DEBUG "....... : IO APIC version: %04X\n", reg_01.bits.version); + if ( (reg_01.bits.version != 0x01) && /* 82489DX IO-APICs */ + (reg_01.bits.version != 0x02) && /* 82801BA IO-APICs (ICH2) */ + (reg_01.bits.version != 0x10) && /* oldest IO-APICs */ + (reg_01.bits.version != 0x11) && /* Pentium/Pro IO-APICs */ + (reg_01.bits.version != 0x13) && /* Xeon IO-APICs */ + (reg_01.bits.version != 0x20) /* Intel P64H (82806 AA) */ + ) + UNEXPECTED_IO_APIC(); + if (reg_01.bits.__reserved_1 || reg_01.bits.__reserved_2) + UNEXPECTED_IO_APIC(); + + if (reg_01.bits.version >= 0x10) { + printk(KERN_DEBUG ".... register #02: %08X\n", reg_02.raw); + printk(KERN_DEBUG "....... : arbitration: %02X\n", reg_02.bits.arbitration); + if (reg_02.bits.__reserved_1 || reg_02.bits.__reserved_2) + UNEXPECTED_IO_APIC(); + } + + printk(KERN_DEBUG ".... IRQ redirection table:\n"); + + printk(KERN_DEBUG " NR Log Phy Mask Trig IRR Pol" + " Stat Dest Deli Vect: \n"); + + for (i = 0; i <= reg_01.bits.entries; i++) { + struct IO_APIC_route_entry entry; + + spin_lock_irqsave(&ioapic_lock, flags); + *(((int *)&entry)+0) = io_apic_read(apic, 0x10+i*2); + *(((int *)&entry)+1) = io_apic_read(apic, 0x11+i*2); + spin_unlock_irqrestore(&ioapic_lock, flags); + + printk(KERN_DEBUG " %02x %03X %02X ", + i, + entry.dest.logical.logical_dest, + entry.dest.physical.physical_dest + ); + + printk("%1d %1d %1d %1d %1d %1d %1d %02X\n", + entry.mask, + entry.trigger, + entry.irr, + entry.polarity, + entry.delivery_status, + entry.dest_mode, + entry.delivery_mode, + entry.vector + ); + } + } + if (use_pci_vector()) + printk(KERN_INFO "Using vector-based indexing\n"); + printk(KERN_DEBUG "IRQ to pin mappings:\n"); + for (i = 0; i < NR_IRQS; i++) { + struct irq_pin_list *entry = irq_2_pin + i; + if (entry->pin < 0) + continue; + if (use_pci_vector() && !platform_legacy_irq(i)) + printk(KERN_DEBUG "IRQ%d ", IO_APIC_VECTOR(i)); + else + printk(KERN_DEBUG "IRQ%d ", i); + for (;;) { + printk("-> %d:%d", entry->apic, entry->pin); + if (!entry->next) + break; + entry = irq_2_pin + entry->next; + } + printk("\n"); + } + + printk(KERN_INFO ".................................... done.\n"); + + return; +} + +#if 0 + +static __apicdebuginit void print_APIC_bitfield (int base) +{ + unsigned int v; + int i, j; + + if (apic_verbosity == APIC_QUIET) + return; + + printk(KERN_DEBUG "0123456789abcdef0123456789abcdef\n" KERN_DEBUG); + for (i = 0; i < 8; i++) { + v = apic_read(base + i*0x10); + for (j = 0; j < 32; j++) { + if (v & (1<<j)) + printk("1"); + else + printk("0"); + } + printk("\n"); + } +} + +void __apicdebuginit print_local_APIC(void * dummy) +{ + unsigned int v, ver, maxlvt; + + if (apic_verbosity == APIC_QUIET) + return; + + printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n", + smp_processor_id(), hard_smp_processor_id()); + v = apic_read(APIC_ID); + printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, GET_APIC_ID(v)); + v = apic_read(APIC_LVR); + printk(KERN_INFO "... APIC VERSION: %08x\n", v); + ver = GET_APIC_VERSION(v); + maxlvt = get_maxlvt(); + + v = apic_read(APIC_TASKPRI); + printk(KERN_DEBUG "... APIC TASKPRI: %08x (%02x)\n", v, v & APIC_TPRI_MASK); + + if (APIC_INTEGRATED(ver)) { /* !82489DX */ + v = apic_read(APIC_ARBPRI); + printk(KERN_DEBUG "... APIC ARBPRI: %08x (%02x)\n", v, + v & APIC_ARBPRI_MASK); + v = apic_read(APIC_PROCPRI); + printk(KERN_DEBUG "... APIC PROCPRI: %08x\n", v); + } + + v = apic_read(APIC_EOI); + printk(KERN_DEBUG "... APIC EOI: %08x\n", v); + v = apic_read(APIC_RRR); + printk(KERN_DEBUG "... APIC RRR: %08x\n", v); + v = apic_read(APIC_LDR); + printk(KERN_DEBUG "... APIC LDR: %08x\n", v); + v = apic_read(APIC_DFR); + printk(KERN_DEBUG "... APIC DFR: %08x\n", v); + v = apic_read(APIC_SPIV); + printk(KERN_DEBUG "... APIC SPIV: %08x\n", v); + + printk(KERN_DEBUG "... APIC ISR field:\n"); + print_APIC_bitfield(APIC_ISR); + printk(KERN_DEBUG "... APIC TMR field:\n"); + print_APIC_bitfield(APIC_TMR); + printk(KERN_DEBUG "... APIC IRR field:\n"); + print_APIC_bitfield(APIC_IRR); + + if (APIC_INTEGRATED(ver)) { /* !82489DX */ + if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ + apic_write(APIC_ESR, 0); + v = apic_read(APIC_ESR); + printk(KERN_DEBUG "... APIC ESR: %08x\n", v); + } + + v = apic_read(APIC_ICR); + printk(KERN_DEBUG "... APIC ICR: %08x\n", v); + v = apic_read(APIC_ICR2); + printk(KERN_DEBUG "... APIC ICR2: %08x\n", v); + + v = apic_read(APIC_LVTT); + printk(KERN_DEBUG "... APIC LVTT: %08x\n", v); + + if (maxlvt > 3) { /* PC is LVT#4. */ + v = apic_read(APIC_LVTPC); + printk(KERN_DEBUG "... APIC LVTPC: %08x\n", v); + } + v = apic_read(APIC_LVT0); + printk(KERN_DEBUG "... APIC LVT0: %08x\n", v); + v = apic_read(APIC_LVT1); + printk(KERN_DEBUG "... APIC LVT1: %08x\n", v); + + if (maxlvt > 2) { /* ERR is LVT#3. */ + v = apic_read(APIC_LVTERR); + printk(KERN_DEBUG "... APIC LVTERR: %08x\n", v); + } + + v = apic_read(APIC_TMICT); + printk(KERN_DEBUG "... APIC TMICT: %08x\n", v); + v = apic_read(APIC_TMCCT); + printk(KERN_DEBUG "... APIC TMCCT: %08x\n", v); + v = apic_read(APIC_TDCR); + printk(KERN_DEBUG "... APIC TDCR: %08x\n", v); + printk("\n"); +} + +void print_all_local_APICs (void) +{ + on_each_cpu(print_local_APIC, NULL, 1, 1); +} + +void __apicdebuginit print_PIC(void) +{ + extern spinlock_t i8259A_lock; + unsigned int v; + unsigned long flags; + + if (apic_verbosity == APIC_QUIET) + return; + + printk(KERN_DEBUG "\nprinting PIC contents\n"); + + spin_lock_irqsave(&i8259A_lock, flags); + + v = inb(0xa1) << 8 | inb(0x21); + printk(KERN_DEBUG "... PIC IMR: %04x\n", v); + + v = inb(0xa0) << 8 | inb(0x20); + printk(KERN_DEBUG "... PIC IRR: %04x\n", v); + + outb(0x0b,0xa0); + outb(0x0b,0x20); + v = inb(0xa0) << 8 | inb(0x20); + outb(0x0a,0xa0); + outb(0x0a,0x20); + + spin_unlock_irqrestore(&i8259A_lock, flags); + + printk(KERN_DEBUG "... PIC ISR: %04x\n", v); + + v = inb(0x4d1) << 8 | inb(0x4d0); + printk(KERN_DEBUG "... PIC ELCR: %04x\n", v); +} + +#endif /* 0 */ + +#else +void __init print_IO_APIC(void) { } +#endif /* !CONFIG_XEN */ + +static void __init enable_IO_APIC(void) +{ + union IO_APIC_reg_01 reg_01; + int i; + unsigned long flags; + + for (i = 0; i < PIN_MAP_SIZE; i++) { + irq_2_pin[i].pin = -1; + irq_2_pin[i].next = 0; + } + if (!pirqs_enabled) + for (i = 0; i < MAX_PIRQS; i++) + pirq_entries[i] = -1; + + /* + * The number of IO-APIC IRQ registers (== #pins): + */ + for (i = 0; i < nr_ioapics; i++) { + spin_lock_irqsave(&ioapic_lock, flags); + reg_01.raw = io_apic_read(i, 1); + spin_unlock_irqrestore(&ioapic_lock, flags); + nr_ioapic_registers[i] = reg_01.bits.entries+1; + } + + /* + * Do not trust the IO-APIC being empty at bootup + */ + clear_IO_APIC(); +} + +/* + * Not an __init, needed by the reboot code + */ +void disable_IO_APIC(void) +{ + /* + * Clear the IO-APIC before rebooting: + */ + clear_IO_APIC(); + +#ifndef CONFIG_XEN + disconnect_bsp_APIC(); +#endif +} + +/* + * function to set the IO-APIC physical IDs based on the + * values stored in the MPC table. + * + * by Matt Domsch <Matt_Domsch@xxxxxxxx> Tue Dec 21 12:25:05 CST 1999 + */ + +#ifndef CONFIG_XEN +static void __init setup_ioapic_ids_from_mpc (void) +{ + union IO_APIC_reg_00 reg_00; + int apic; + int i; + unsigned char old_id; + unsigned long flags; + + /* + * Set the IOAPIC ID to the value stored in the MPC table. + */ + for (apic = 0; apic < nr_ioapics; apic++) { + + /* Read the register 0 value */ + spin_lock_irqsave(&ioapic_lock, flags); + reg_00.raw = io_apic_read(apic, 0); + spin_unlock_irqrestore(&ioapic_lock, flags); + + old_id = mp_ioapics[apic].mpc_apicid; + + + printk(KERN_INFO "Using IO-APIC %d\n", mp_ioapics[apic].mpc_apicid); + + + /* + * We need to adjust the IRQ routing table + * if the ID changed. + */ + if (old_id != mp_ioapics[apic].mpc_apicid) + for (i = 0; i < mp_irq_entries; i++) + if (mp_irqs[i].mpc_dstapic == old_id) + mp_irqs[i].mpc_dstapic + = mp_ioapics[apic].mpc_apicid; + + /* + * Read the right value from the MPC table and + * write it into the ID register. + */ + apic_printk(APIC_VERBOSE,KERN_INFO "...changing IO-APIC physical APIC ID to %d ...", + mp_ioapics[apic].mpc_apicid); + + reg_00.bits.ID = mp_ioapics[apic].mpc_apicid; + spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(apic, 0, reg_00.raw); + spin_unlock_irqrestore(&ioapic_lock, flags); + + /* + * Sanity check + */ + spin_lock_irqsave(&ioapic_lock, flags); + reg_00.raw = io_apic_read(apic, 0); + spin_unlock_irqrestore(&ioapic_lock, flags); + if (reg_00.bits.ID != mp_ioapics[apic].mpc_apicid) + printk("could not set ID!\n"); + else + apic_printk(APIC_VERBOSE," ok.\n"); + } +} +#else +static void __init setup_ioapic_ids_from_mpc(void) { } +#endif + +/* + * There is a nasty bug in some older SMP boards, their mptable lies + * about the timer IRQ. We do the following to work around the situation: + * + * - timer IRQ defaults to IO-APIC IRQ + * - if this function detects that timer IRQs are defunct, then we fall + * back to ISA timer IRQs + */ +#ifndef CONFIG_XEN +static int __init timer_irq_works(void) +{ + unsigned long t1 = jiffies; + + local_irq_enable(); + /* Let ten ticks pass... */ + mdelay((10 * 1000) / HZ); + + /* + * Expect a few ticks at least, to be sure some possible + * glue logic does not lock up after one or two first + * ticks in a non-ExtINT mode. Also the local APIC + * might have cached one ExtINT interrupt. Finally, at + * least one tick may be lost due to delays. + */ + + /* jiffies wrap? */ + if (jiffies - t1 > 4) + return 1; + return 0; +} + +/* + * In the SMP+IOAPIC case it might happen that there are an unspecified + * number of pending IRQ events unhandled. These cases are very rare, + * so we 'resend' these IRQs via IPIs, to the same CPU. It's much + * better to do it this way as thus we do not have to be aware of + * 'pending' interrupts in the IRQ path, except at this point. + */ +/* + * Edge triggered needs to resend any interrupt + * that was delayed but this is now handled in the device + * independent code. + */ + +/* + * Starting up a edge-triggered IO-APIC interrupt is + * nasty - we need to make sure that we get the edge. + * If it is already asserted for some reason, we need + * return 1 to indicate that is was pending. + * + * This is not complete - we should be able to fake + * an edge even if it isn't on the 8259A... + */ + +static unsigned int startup_edge_ioapic_irq(unsigned int irq) +{ + int was_pending = 0; + unsigned long flags; + + spin_lock_irqsave(&ioapic_lock, flags); + if (irq < 16) { + disable_8259A_irq(irq); + if (i8259A_irq_pending(irq)) + was_pending = 1; + } + __unmask_IO_APIC_irq(irq); + spin_unlock_irqrestore(&ioapic_lock, flags); + + return was_pending; +} + +/* + * Once we have recorded IRQ_PENDING already, we can mask the + * interrupt for real. This prevents IRQ storms from unhandled + * devices. + */ +static void ack_edge_ioapic_irq(unsigned int irq) +{ + if ((irq_desc[irq].status & (IRQ_PENDING | IRQ_DISABLED)) + == (IRQ_PENDING | IRQ_DISABLED)) + mask_IO_APIC_irq(irq); + ack_APIC_irq(); +} + +/* + * Level triggered interrupts can just be masked, + * and shutting down and starting up the interrupt + * is the same as enabling and disabling them -- except + * with a startup need to return a "was pending" value. + * + * Level triggered interrupts are special because we + * do not touch any IO-APIC register while handling + * them. We ack the APIC in the end-IRQ handler, not + * in the start-IRQ-handler. Protection against reentrance + * from the same interrupt is still provided, both by the + * generic IRQ layer and by the fact that an unacked local + * APIC does not accept IRQs. + */ +static unsigned int startup_level_ioapic_irq (unsigned int irq) +{ + unmask_IO_APIC_irq(irq); + + return 0; /* don't check for pending */ +} + +static void end_level_ioapic_irq (unsigned int irq) +{ + ack_APIC_irq(); +} + +static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask) +{ + unsigned long flags; + unsigned int dest; + + dest = cpu_mask_to_apicid(mask); + + /* + * Only the high 8 bits are valid. + */ + dest = SET_APIC_LOGICAL_ID(dest); + + spin_lock_irqsave(&ioapic_lock, flags); + __DO_ACTION(1, = dest, ) + spin_unlock_irqrestore(&ioapic_lock, flags); +} + +#ifdef CONFIG_PCI_MSI +static unsigned int startup_edge_ioapic_vector(unsigned int vector) +{ + int irq = vector_to_irq(vector); + + return startup_edge_ioapic_irq(irq); +} + +static void ack_edge_ioapic_vector(unsigned int vector) +{ + int irq = vector_to_irq(vector); + + ack_edge_ioapic_irq(irq); +} + +static unsigned int startup_level_ioapic_vector (unsigned int vector) +{ + int irq = vector_to_irq(vector); + + return startup_level_ioapic_irq (irq); +} + +static void end_level_ioapic_vector (unsigned int vector) +{ + int irq = vector_to_irq(vector); + + end_level_ioapic_irq(irq); +} + +static void mask_IO_APIC_vector (unsigned int vector) +{ + int irq = vector_to_irq(vector); + + mask_IO_APIC_irq(irq); +} + +static void unmask_IO_APIC_vector (unsigned int vector) +{ + int irq = vector_to_irq(vector); + + unmask_IO_APIC_irq(irq); +} + +static void set_ioapic_affinity_vector (unsigned int vector, + cpumask_t cpu_mask) +{ + int irq = vector_to_irq(vector); + + set_ioapic_affinity_irq(irq, cpu_mask); +} +#endif + +/* + * Level and edge triggered IO-APIC interrupts need different handling, + * so we use two separate IRQ descriptors. Edge triggered IRQs can be + * handled with the level-triggered descriptor, but that one has slightly + * more overhead. Level-triggered interrupts cannot be handled with the + * edge-triggered handler, without risking IRQ storms and other ugly + * races. + */ + +static struct hw_interrupt_type ioapic_edge_type = { + .typename = "IO-APIC-edge", + .startup = startup_edge_ioapic, + .shutdown = shutdown_edge_ioapic, + .enable = enable_edge_ioapic, + .disable = disable_edge_ioapic, + .ack = ack_edge_ioapic, + .end = end_edge_ioapic, + .set_affinity = set_ioapic_affinity, +}; + +static struct hw_interrupt_type ioapic_level_type = { + .typename = "IO-APIC-level", + .startup = startup_level_ioapic, + .shutdown = shutdown_level_ioapic, + .enable = enable_level_ioapic, + .disable = disable_level_ioapic, + .ack = mask_and_ack_level_ioapic, + .end = end_level_ioapic, + .set_affinity = set_ioapic_affinity, +}; +#endif /* !CONFIG_XEN */ + +static inline void init_IO_APIC_traps(void) +{ + int irq; + + /* + * NOTE! The local APIC isn't very good at handling + * multiple interrupts at the same interrupt level. + * As the interrupt level is determined by taking the + * vector number and shifting that right by 4, we + * want to spread these out a bit so that they don't + * all fall in the same interrupt level. + * + * Also, we've got to be careful not to trash gate + * 0x80, because int 0x80 is hm, kind of importantish. ;) + */ + for (irq = 0; irq < NR_IRQS ; irq++) { + int tmp = irq; + if (use_pci_vector()) { + if (!platform_legacy_irq(tmp)) + if ((tmp = vector_to_irq(tmp)) == -1) + continue; + } + if (IO_APIC_IRQ(tmp) && !IO_APIC_VECTOR(tmp)) { + /* + * Hmm.. We don't have an entry for this, + * so default to an old-fashioned 8259 + * interrupt if we can.. + */ + if (irq < 16) + make_8259A_irq(irq); +#ifndef CONFIG_XEN + else + /* Strange. Oh, well.. */ + irq_desc[irq].handler = &no_irq_type; +#endif + } + } +} + +#ifndef CONFIG_XEN +static void enable_lapic_irq (unsigned int irq) +{ + unsigned long v; + + v = apic_read(APIC_LVT0); + apic_write_around(APIC_LVT0, v & ~APIC_LVT_MASKED); +} + +static void disable_lapic_irq (unsigned int irq) +{ + unsigned long v; + + v = apic_read(APIC_LVT0); + apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED); +} + +static void ack_lapic_irq (unsigned int irq) +{ + ack_APIC_irq(); +} + +static void end_lapic_irq (unsigned int i) { /* nothing */ } + +static struct hw_interrupt_type lapic_irq_type = { + .typename = "local-APIC-edge", + .startup = NULL, /* startup_irq() not used for IRQ0 */ + .shutdown = NULL, /* shutdown_irq() not used for IRQ0 */ + .enable = enable_lapic_irq, + .disable = disable_lapic_irq, + .ack = ack_lapic_irq, + .end = end_lapic_irq, +}; + +static void setup_nmi (void) +{ + /* + * Dirty trick to enable the NMI watchdog ... + * We put the 8259A master into AEOI mode and + * unmask on all local APICs LVT0 as NMI. + * + * The idea to use the 8259A in AEOI mode ('8259A Virtual Wire') + * is from Maciej W. Rozycki - so we do not have to EOI from + * the NMI handler or the timer interrupt. + */ + printk(KERN_INFO "activating NMI Watchdog ..."); + + enable_NMI_through_LVT0(NULL); + + printk(" done.\n"); +} + +/* + * This looks a bit hackish but it's about the only one way of sending + * a few INTA cycles to 8259As and any associated glue logic. ICR does + * not support the ExtINT mode, unfortunately. We need to send these + * cycles as some i82489DX-based boards have glue logic that keeps the + * 8259A interrupt line asserted until INTA. --macro + */ +static inline void unlock_ExtINT_logic(void) +{ + int pin, i; + struct IO_APIC_route_entry entry0, entry1; + unsigned char save_control, save_freq_select; + unsigned long flags; + + pin = find_isa_irq_pin(8, mp_INT); + if (pin == -1) + return; + + spin_lock_irqsave(&ioapic_lock, flags); + *(((int *)&entry0) + 1) = io_apic_read(0, 0x11 + 2 * pin); + *(((int *)&entry0) + 0) = io_apic_read(0, 0x10 + 2 * pin); + spin_unlock_irqrestore(&ioapic_lock, flags); + clear_IO_APIC_pin(0, pin); + + memset(&entry1, 0, sizeof(entry1)); + + entry1.dest_mode = 0; /* physical delivery */ + entry1.mask = 0; /* unmask IRQ now */ + entry1.dest.physical.physical_dest = hard_smp_processor_id(); + entry1.delivery_mode = dest_ExtINT; + entry1.polarity = entry0.polarity; + entry1.trigger = 0; + entry1.vector = 0; + + spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry1) + 1)); + io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry1) + 0)); + spin_unlock_irqrestore(&ioapic_lock, flags); + + save_control = CMOS_READ(RTC_CONTROL); + save_freq_select = CMOS_READ(RTC_FREQ_SELECT); + CMOS_WRITE((save_freq_select & ~RTC_RATE_SELECT) | 0x6, + RTC_FREQ_SELECT); + CMOS_WRITE(save_control | RTC_PIE, RTC_CONTROL); + + i = 100; + while (i-- > 0) { + mdelay(10); + if ((CMOS_READ(RTC_INTR_FLAGS) & RTC_PF) == RTC_PF) + i -= 10; + } + + CMOS_WRITE(save_control, RTC_CONTROL); + CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); + clear_IO_APIC_pin(0, pin); + + spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry0) + 1)); + io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry0) + 0)); + spin_unlock_irqrestore(&ioapic_lock, flags); +} + +/* + * This code may look a bit paranoid, but it's supposed to cooperate with + * a wide range of boards and BIOS bugs. Fortunately only the timer IRQ + * is so screwy. Thanks to Brian Perkins for testing/hacking this beast + * fanatically on his truly buggy board. + */ +static inline void check_timer(void) +{ + int pin1, pin2; + int vector; + + /* + * get/set the timer IRQ vector: + */ + disable_8259A_irq(0); + vector = assign_irq_vector(0); + set_intr_gate(vector, interrupt[0]); + + /* + * Subtle, code in do_timer_interrupt() expects an AEOI + * mode for the 8259A whenever interrupts are routed + * through I/O APICs. Also IRQ0 has to be enabled in + * the 8259A which implies the virtual wire has to be + * disabled in the local APIC. + */ + apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); + init_8259A(1); + enable_8259A_irq(0); + + pin1 = find_isa_irq_pin(0, mp_INT); + pin2 = find_isa_irq_pin(0, mp_ExtINT); + + apic_printk(APIC_VERBOSE,KERN_INFO "..TIMER: vector=0x%02X pin1=%d pin2=%d\n", vector, pin1, pin2); + + if (pin1 != -1) { + /* + * Ok, does IRQ0 through the IOAPIC work? + */ + unmask_IO_APIC_irq(0); + if (!no_timer_check && timer_irq_works()) { + nmi_watchdog_default(); + if (nmi_watchdog == NMI_IO_APIC) { + disable_8259A_irq(0); + setup_nmi(); + enable_8259A_irq(0); + } + return; + } + clear_IO_APIC_pin(0, pin1); + apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: 8254 timer not connected to IO-APIC\n"); + } + + apic_printk(APIC_VERBOSE,KERN_INFO "...trying to set up timer (IRQ0) through the 8259A ... "); + if (pin2 != -1) { + apic_printk(APIC_VERBOSE,"\n..... (found pin %d) ...", pin2); + /* + * legacy devices should be connected to IO APIC #0 + */ + setup_ExtINT_IRQ0_pin(pin2, vector); + if (timer_irq_works()) { + printk("works.\n"); + nmi_watchdog_default(); + if (nmi_watchdog == NMI_IO_APIC) { + setup_nmi(); + } + return; + } + /* + * Cleanup, just in case ... + */ + clear_IO_APIC_pin(0, pin2); + } + printk(" failed.\n"); + + if (nmi_watchdog) { + printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n"); + nmi_watchdog = 0; + } + + apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as Virtual Wire IRQ..."); + + disable_8259A_irq(0); + irq_desc[0].handler = &lapic_irq_type; + apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector); /* Fixed mode */ + enable_8259A_irq(0); + + if (timer_irq_works()) { + apic_printk(APIC_QUIET, " works.\n"); + return; + } + apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | vector); + apic_printk(APIC_VERBOSE," failed.\n"); + + apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as ExtINT IRQ..."); + + init_8259A(0); + make_8259A_irq(0); + apic_write_around(APIC_LVT0, APIC_DM_EXTINT); + + unlock_ExtINT_logic(); + + if (timer_irq_works()) { + apic_printk(APIC_VERBOSE," works.\n"); + return; + } + apic_printk(APIC_VERBOSE," failed :(.\n"); + panic("IO-APIC + timer doesn't work! Try using the 'noapic' kernel parameter\n"); +} +#else +#define check_timer() ((void)0) +#endif /* !CONFIG_XEN */ + +static int __init notimercheck(char *s) +{ + no_timer_check = 1; + return 1; +} +__setup("no_timer_check", notimercheck); + +/* + * + * IRQ's that are handled by the PIC in the MPS IOAPIC case. + * - IRQ2 is the cascade IRQ, and cannot be a io-apic IRQ. + * Linux doesn't really care, as it's not actually used + * for any interrupt handling anyway. + */ +#define PIC_IRQS (1<<2) + +void __init setup_IO_APIC(void) +{ + enable_IO_APIC(); + + if (acpi_ioapic) + io_apic_irqs = ~0; /* all IRQs go through IOAPIC */ + else + io_apic_irqs = ~PIC_IRQS; + + apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n"); + + /* + * Set up the IO-APIC IRQ routing table. + */ + if (!acpi_ioapic) + setup_ioapic_ids_from_mpc(); +#ifndef CONFIG_XEN + sync_Arb_IDs(); +#endif /* !CONFIG_XEN */ + setup_IO_APIC_irqs(); + init_IO_APIC_traps(); + check_timer(); + if (!acpi_ioapic) + print_IO_APIC(); +} + +struct sysfs_ioapic_data { + struct sys_device dev; + struct IO_APIC_route_entry entry[0]; +}; +static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS]; + +static int ioapic_suspend(struct sys_device *dev, pm_message_t state) +{ + struct IO_APIC_route_entry *entry; + struct sysfs_ioapic_data *data; + unsigned long flags; + int i; + + data = container_of(dev, struct sysfs_ioapic_data, dev); + entry = data->entry; + spin_lock_irqsave(&ioapic_lock, flags); + for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) { + *(((int *)entry) + 1) = io_apic_read(dev->id, 0x11 + 2 * i); + *(((int *)entry) + 0) = io_apic_read(dev->id, 0x10 + 2 * i); + } + spin_unlock_irqrestore(&ioapic_lock, flags); + + return 0; +} + +static int ioapic_resume(struct sys_device *dev) +{ + struct IO_APIC_route_entry *entry; + struct sysfs_ioapic_data *data; + unsigned long flags; + union IO_APIC_reg_00 reg_00; + int i; + + data = container_of(dev, struct sysfs_ioapic_data, dev); + entry = data->entry; + + spin_lock_irqsave(&ioapic_lock, flags); + reg_00.raw = io_apic_read(dev->id, 0); + if (reg_00.bits.ID != mp_ioapics[dev->id].mpc_apicid) { + reg_00.bits.ID = mp_ioapics[dev->id].mpc_apicid; + io_apic_write(dev->id, 0, reg_00.raw); + } + for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) { + io_apic_write(dev->id, 0x11+2*i, *(((int *)entry)+1)); + io_apic_write(dev->id, 0x10+2*i, *(((int *)entry)+0)); + } + spin_unlock_irqrestore(&ioapic_lock, flags); + + return 0; +} + +static struct sysdev_class ioapic_sysdev_class = { + set_kset_name("ioapic"), + .suspend = ioapic_suspend, + .resume = ioapic_resume, +}; + +static int __init ioapic_init_sysfs(void) +{ + struct sys_device * dev; + int i, size, error = 0; + + error = sysdev_class_register(&ioapic_sysdev_class); + if (error) + return error; + + for (i = 0; i < nr_ioapics; i++ ) { + size = sizeof(struct sys_device) + nr_ioapic_registers[i] + * sizeof(struct IO_APIC_route_entry); + mp_ioapic_data[i] = kmalloc(size, GFP_KERNEL); + if (!mp_ioapic_data[i]) { + printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i); + continue; + } + memset(mp_ioapic_data[i], 0, size); + dev = &mp_ioapic_data[i]->dev; + dev->id = i; + dev->cls = &ioapic_sysdev_class; + error = sysdev_register(dev); + if (error) { + kfree(mp_ioapic_data[i]); + mp_ioapic_data[i] = NULL; + printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i); + continue; + } + } + + return 0; +} + +device_initcall(ioapic_init_sysfs); + +/* -------------------------------------------------------------------------- + ACPI-based IOAPIC Configuration + -------------------------------------------------------------------------- */ + +#ifdef CONFIG_ACPI_BOOT + +#define IO_APIC_MAX_ID 0xFE + +int __init io_apic_get_version (int ioapic) +{ + union IO_APIC_reg_01 reg_01; + unsigned long flags; + + spin_lock_irqsave(&ioapic_lock, flags); + reg_01.raw = io_apic_read(ioapic, 1); + spin_unlock_irqrestore(&ioapic_lock, flags); + + return reg_01.bits.version; +} + + +int __init io_apic_get_redir_entries (int ioapic) +{ + union IO_APIC_reg_01 reg_01; + unsigned long flags; + + spin_lock_irqsave(&ioapic_lock, flags); + reg_01.raw = io_apic_read(ioapic, 1); + spin_unlock_irqrestore(&ioapic_lock, flags); + + return reg_01.bits.entries; +} + + +int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int active_high_low) +{ + struct IO_APIC_route_entry entry; + unsigned long flags; + + if (!IO_APIC_IRQ(irq)) { + apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n", + ioapic); + return -EINVAL; + } + + /* + * Generate a PCI IRQ routing entry and program the IOAPIC accordingly. + * Note that we mask (disable) IRQs now -- these get enabled when the + * corresponding device driver registers for this IRQ. + */ + + memset(&entry,0,sizeof(entry)); + + entry.delivery_mode = INT_DELIVERY_MODE; + entry.dest_mode = INT_DEST_MODE; + entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS); + entry.trigger = edge_level; + entry.polarity = active_high_low; + entry.mask = 1; /* Disabled (masked) */ + + /* + * IRQs < 16 are already in the irq_2_pin[] map + */ + if (irq >= 16) + add_pin_to_irq(irq, ioapic, pin); + + entry.vector = assign_irq_vector(irq); + + apic_printk(APIC_VERBOSE,KERN_DEBUG "IOAPIC[%d]: Set PCI routing entry (%d-%d -> 0x%x -> " + "IRQ %d Mode:%i Active:%i)\n", ioapic, + mp_ioapics[ioapic].mpc_apicid, pin, entry.vector, irq, + edge_level, active_high_low); + + ioapic_register_intr(irq, entry.vector, edge_level); + + if (!ioapic && (irq < 16)) + disable_8259A_irq(irq); + + spin_lock_irqsave(&ioapic_lock, flags); + io_apic_write(ioapic, 0x11+2*pin, *(((int *)&entry)+1)); + io_apic_write(ioapic, 0x10+2*pin, *(((int *)&entry)+0)); + spin_unlock_irqrestore(&ioapic_lock, flags); + + return 0; +} + +#endif /*CONFIG_ACPI_BOOT*/ + + +#ifndef CONFIG_XEN +/* + * This function currently is only a helper for the i386 smp boot process where + * we need to reprogram the ioredtbls to cater for the cpus which have come online + * so mask in all cases should simply be TARGET_CPUS + */ +void __init setup_ioapic_dest(void) +{ + int pin, ioapic, irq, irq_entry; + + if (skip_ioapic_setup == 1) + return; + + for (ioapic = 0; ioapic < nr_ioapics; ioapic++) { + for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) { + irq_entry = find_irq_entry(ioapic, pin, mp_INT); + if (irq_entry == -1) + continue; + irq = pin_2_irq(irq_entry, ioapic, pin); + set_ioapic_affinity_irq(irq, TARGET_CPUS); + } + + } +} +#endif /* !CONFIG_XEN */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/ioport-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/ioport-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,57 @@ +/* + * linux/arch/x86_64/kernel/ioport.c + * + * This contains the io-permission bitmap code - written by obz, with changes + * by Linus. + */ + +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/ioport.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/stddef.h> +#include <linux/slab.h> +#include <linux/thread_info.h> +#include <xen/interface/physdev.h> + +/* + * sys_iopl has to be used when you want to access the IO ports + * beyond the 0x3ff range: to get the full 65536 ports bitmapped + * you'd need 8kB of bitmaps/process, which is a bit excessive. + * + */ + +asmlinkage long sys_iopl(unsigned int new_io_pl, struct pt_regs *regs) +{ + unsigned int old_io_pl = current->thread.io_pl; + physdev_op_t op; + + if (new_io_pl > 3) + return -EINVAL; + + /* Need "raw I/O" privileges for direct port access. */ + if ((new_io_pl > old_io_pl) && !capable(CAP_SYS_RAWIO)) + return -EPERM; + + /* Change our version of the privilege levels. */ + current->thread.io_pl = new_io_pl; + + /* Force the change at ring 0. */ + op.cmd = PHYSDEVOP_SET_IOPL; + op.u.set_iopl.iopl = (new_io_pl == 0) ? 1 : new_io_pl; + HYPERVISOR_physdev_op(&op); + + return 0; +} + +/* + * this changes the io permissions bitmap in the current task. + */ +asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) +{ + return turn_on ? sys_iopl(3, NULL) : 0; +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/irq-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/irq-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,107 @@ +/* + * linux/arch/x86_64/kernel/irq.c + * + * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar + * + * This file contains the lowest level x86_64-specific interrupt + * entry and irq statistics code. All the remaining irq logic is + * done by the generic kernel/irq/ code and in the + * x86_64-specific irq controller code. (e.g. i8259.c and + * io_apic.c.) + */ + +#include <linux/kernel_stat.h> +#include <linux/interrupt.h> +#include <linux/seq_file.h> +#include <linux/module.h> +#include <asm/uaccess.h> +#include <asm/io_apic.h> + +atomic_t irq_err_count; +#ifdef CONFIG_X86_IO_APIC +#ifdef APIC_MISMATCH_DEBUG +atomic_t irq_mis_count; +#endif +#endif + +/* + * Generic, controller-independent functions: + */ + +int show_interrupts(struct seq_file *p, void *v) +{ + int i = *(loff_t *) v, j; + struct irqaction * action; + unsigned long flags; + + if (i == 0) { + seq_printf(p, " "); + for (j=0; j<NR_CPUS; j++) + if (cpu_online(j)) + seq_printf(p, "CPU%d ",j); + seq_putc(p, '\n'); + } + + if (i < NR_IRQS) { + spin_lock_irqsave(&irq_desc[i].lock, flags); + action = irq_desc[i].action; + if (!action) + goto skip; + seq_printf(p, "%3d: ",i); +#ifndef CONFIG_SMP + seq_printf(p, "%10u ", kstat_irqs(i)); +#else + for (j=0; j<NR_CPUS; j++) + if (cpu_online(j)) + seq_printf(p, "%10u ", + kstat_cpu(j).irqs[i]); +#endif + seq_printf(p, " %14s", irq_desc[i].handler->typename); + + seq_printf(p, " %s", action->name); + for (action=action->next; action; action = action->next) + seq_printf(p, ", %s", action->name); + seq_putc(p, '\n'); +skip: + spin_unlock_irqrestore(&irq_desc[i].lock, flags); + } else if (i == NR_IRQS) { + seq_printf(p, "NMI: "); + for (j = 0; j < NR_CPUS; j++) + if (cpu_online(j)) + seq_printf(p, "%10u ", cpu_pda[j].__nmi_count); + seq_putc(p, '\n'); +#ifdef CONFIG_X86_LOCAL_APIC + seq_printf(p, "LOC: "); + for (j = 0; j < NR_CPUS; j++) + if (cpu_online(j)) + seq_printf(p, "%10u ", cpu_pda[j].apic_timer_irqs); + seq_putc(p, '\n'); +#endif + seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count)); +#ifdef CONFIG_X86_IO_APIC +#ifdef APIC_MISMATCH_DEBUG + seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count)); +#endif +#endif + } + return 0; +} + +/* + * do_IRQ handles all normal device IRQ's (the special + * SMP cross-CPU interrupts have their own specific + * handlers). + */ +asmlinkage unsigned int do_IRQ(struct pt_regs *regs) +{ + /* high bits used in ret_from_ code */ + int irq = regs->orig_rax & __IRQ_MASK(HARDIRQ_BITS); + + irq_enter(); + + __do_IRQ(irq, regs); + irq_exit(); + + return 1; +} + diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/ldt-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/ldt-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,282 @@ +/* + * linux/arch/x86_64/kernel/ldt.c + * + * Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds + * Copyright (C) 1999 Ingo Molnar <mingo@xxxxxxxxxx> + * Copyright (C) 2002 Andi Kleen + * + * This handles calls from both 32bit and 64bit mode. + */ + +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/string.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/vmalloc.h> +#include <linux/slab.h> + +#include <asm/uaccess.h> +#include <asm/system.h> +#include <asm/ldt.h> +#include <asm/desc.h> +#include <asm/proto.h> +#include <asm/pgalloc.h> + +#ifdef CONFIG_SMP /* avoids "defined but not used" warnig */ +static void flush_ldt(void *null) +{ + if (current->active_mm) + load_LDT(&current->active_mm->context); +} +#endif + +static int alloc_ldt(mm_context_t *pc, unsigned mincount, int reload) +{ + void *oldldt; + void *newldt; + unsigned oldsize; + + if (mincount <= (unsigned)pc->size) + return 0; + oldsize = pc->size; + mincount = (mincount+511)&(~511); + if (mincount*LDT_ENTRY_SIZE > PAGE_SIZE) + newldt = vmalloc(mincount*LDT_ENTRY_SIZE); + else + newldt = kmalloc(mincount*LDT_ENTRY_SIZE, GFP_KERNEL); + + if (!newldt) + return -ENOMEM; + + if (oldsize) + memcpy(newldt, pc->ldt, oldsize*LDT_ENTRY_SIZE); + oldldt = pc->ldt; + memset(newldt+oldsize*LDT_ENTRY_SIZE, 0, (mincount-oldsize)*LDT_ENTRY_SIZE); + wmb(); + pc->ldt = newldt; + wmb(); + pc->size = mincount; + wmb(); + if (reload) { +#ifdef CONFIG_SMP + cpumask_t mask; + + preempt_disable(); +#endif + make_pages_readonly( + pc->ldt, + (pc->size * LDT_ENTRY_SIZE) / PAGE_SIZE, + XENFEAT_writable_descriptor_tables); + load_LDT(pc); +#ifdef CONFIG_SMP + mask = cpumask_of_cpu(smp_processor_id()); + if (!cpus_equal(current->mm->cpu_vm_mask, mask)) + smp_call_function(flush_ldt, NULL, 1, 1); + preempt_enable(); +#endif + } + if (oldsize) { + make_pages_writable( + oldldt, + (oldsize * LDT_ENTRY_SIZE) / PAGE_SIZE, + XENFEAT_writable_descriptor_tables); + if (oldsize*LDT_ENTRY_SIZE > PAGE_SIZE) + vfree(oldldt); + else + kfree(oldldt); + } + return 0; +} + +static inline int copy_ldt(mm_context_t *new, mm_context_t *old) +{ + int err = alloc_ldt(new, old->size, 0); + if (err < 0) + return err; + memcpy(new->ldt, old->ldt, old->size*LDT_ENTRY_SIZE); + make_pages_readonly( + new->ldt, + (new->size * LDT_ENTRY_SIZE) / PAGE_SIZE, + XENFEAT_writable_descriptor_tables); + return 0; +} + +/* + * we do not have to muck with descriptors here, that is + * done in switch_mm() as needed. + */ +int init_new_context(struct task_struct *tsk, struct mm_struct *mm) +{ + struct mm_struct * old_mm; + int retval = 0; + + memset(&mm->context, 0, sizeof(mm->context)); + init_MUTEX(&mm->context.sem); + old_mm = current->mm; + if (old_mm && old_mm->context.size > 0) { + down(&old_mm->context.sem); + retval = copy_ldt(&mm->context, &old_mm->context); + up(&old_mm->context.sem); + } + if (retval == 0) { + spin_lock(&mm_unpinned_lock); + list_add(&mm->context.unpinned, &mm_unpinned); + spin_unlock(&mm_unpinned_lock); + } + return retval; +} + +/* + * + * Don't touch the LDT register - we're already in the next thread. + */ +void destroy_context(struct mm_struct *mm) +{ + if (mm->context.size) { + if (mm == current->active_mm) + clear_LDT(); + make_pages_writable( + mm->context.ldt, + (mm->context.size * LDT_ENTRY_SIZE) / PAGE_SIZE, + XENFEAT_writable_descriptor_tables); + if (mm->context.size*LDT_ENTRY_SIZE > PAGE_SIZE) + vfree(mm->context.ldt); + else + kfree(mm->context.ldt); + mm->context.size = 0; + } + if (!mm->context.pinned) { + spin_lock(&mm_unpinned_lock); + list_del(&mm->context.unpinned); + spin_unlock(&mm_unpinned_lock); + } +} + +static int read_ldt(void __user * ptr, unsigned long bytecount) +{ + int err; + unsigned long size; + struct mm_struct * mm = current->mm; + + if (!mm->context.size) + return 0; + if (bytecount > LDT_ENTRY_SIZE*LDT_ENTRIES) + bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES; + + down(&mm->context.sem); + size = mm->context.size*LDT_ENTRY_SIZE; + if (size > bytecount) + size = bytecount; + + err = 0; + if (copy_to_user(ptr, mm->context.ldt, size)) + err = -EFAULT; + up(&mm->context.sem); + if (err < 0) + goto error_return; + if (size != bytecount) { + /* zero-fill the rest */ + if (clear_user(ptr+size, bytecount-size) != 0) { + err = -EFAULT; + goto error_return; + } + } + return bytecount; +error_return: + return err; +} + +static int read_default_ldt(void __user * ptr, unsigned long bytecount) +{ + /* Arbitrary number */ + /* x86-64 default LDT is all zeros */ + if (bytecount > 128) + bytecount = 128; + if (clear_user(ptr, bytecount)) + return -EFAULT; + return bytecount; +} + +static int write_ldt(void __user * ptr, unsigned long bytecount, int oldmode) +{ + struct task_struct *me = current; + struct mm_struct * mm = me->mm; + __u32 entry_1, entry_2, *lp; + unsigned long mach_lp; + int error; + struct user_desc ldt_info; + + error = -EINVAL; + + if (bytecount != sizeof(ldt_info)) + goto out; + error = -EFAULT; + if (copy_from_user(&ldt_info, ptr, bytecount)) + goto out; + + error = -EINVAL; + if (ldt_info.entry_number >= LDT_ENTRIES) + goto out; + if (ldt_info.contents == 3) { + if (oldmode) + goto out; + if (ldt_info.seg_not_present == 0) + goto out; + } + + down(&mm->context.sem); + if (ldt_info.entry_number >= (unsigned)mm->context.size) { + error = alloc_ldt(&current->mm->context, ldt_info.entry_number+1, 1); + if (error < 0) + goto out_unlock; + } + + lp = (__u32 *) ((ldt_info.entry_number << 3) + (char *) mm->context.ldt); + mach_lp = arbitrary_virt_to_machine(lp); + + /* Allow LDTs to be cleared by the user. */ + if (ldt_info.base_addr == 0 && ldt_info.limit == 0) { + if (oldmode || LDT_empty(&ldt_info)) { + entry_1 = 0; + entry_2 = 0; + goto install; + } + } + + entry_1 = LDT_entry_a(&ldt_info); + entry_2 = LDT_entry_b(&ldt_info); + if (oldmode) + entry_2 &= ~(1 << 20); + + /* Install the new entry ... */ +install: + error = HYPERVISOR_update_descriptor(mach_lp, (unsigned long)((entry_1 | (unsigned long) entry_2 << 32))); + +out_unlock: + up(&mm->context.sem); +out: + return error; +} + +asmlinkage int sys_modify_ldt(int func, void __user *ptr, unsigned long bytecount) +{ + int ret = -ENOSYS; + + switch (func) { + case 0: + ret = read_ldt(ptr, bytecount); + break; + case 1: + ret = write_ldt(ptr, bytecount, 1); + break; + case 2: + ret = read_default_ldt(ptr, bytecount); + break; + case 0x11: + ret = write_ldt(ptr, bytecount, 0); + break; + } + return ret; +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/mpparse-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/mpparse-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,963 @@ +/* + * Intel Multiprocessor Specification 1.1 and 1.4 + * compliant MP-table parsing routines. + * + * (c) 1995 Alan Cox, Building #3 <alan@xxxxxxxxxx> + * (c) 1998, 1999, 2000 Ingo Molnar <mingo@xxxxxxxxxx> + * + * Fixes + * Erich Boleyn : MP v1.4 and additional changes. + * Alan Cox : Added EBDA scanning + * Ingo Molnar : various cleanups and rewrites + * Maciej W. Rozycki: Bits for default MP configurations + * Paul Diefenbaugh: Added full ACPI support + */ + +#include <linux/mm.h> +#include <linux/irq.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/config.h> +#include <linux/bootmem.h> +#include <linux/smp_lock.h> +#include <linux/kernel_stat.h> +#include <linux/mc146818rtc.h> +#include <linux/acpi.h> + +#include <asm/smp.h> +#include <asm/mtrr.h> +#include <asm/mpspec.h> +#include <asm/pgalloc.h> +#include <asm/io_apic.h> +#include <asm/proto.h> +#include <asm/acpi.h> + +/* Have we found an MP table */ +int smp_found_config; +unsigned int __initdata maxcpus = NR_CPUS; + +int acpi_found_madt; + +/* + * Various Linux-internal data structures created from the + * MP-table. + */ +int apic_version [MAX_APICS]; +unsigned char mp_bus_id_to_type [MAX_MP_BUSSES] = { [0 ... MAX_MP_BUSSES-1] = -1 }; +int mp_bus_id_to_pci_bus [MAX_MP_BUSSES] = { [0 ... MAX_MP_BUSSES-1] = -1 }; +cpumask_t pci_bus_to_cpumask [256] = { [0 ... 255] = CPU_MASK_ALL }; + +static int mp_current_pci_id = 0; +/* I/O APIC entries */ +struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS]; + +/* # of MP IRQ source entries */ +struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES]; + +/* MP IRQ source entries */ +int mp_irq_entries; + +int nr_ioapics; +int pic_mode; +unsigned long mp_lapic_addr = 0; + + + +/* Processor that is doing the boot up */ +unsigned int boot_cpu_id = -1U; +/* Internal processor count */ +static unsigned int num_processors = 0; + +/* Bitmask of physically existing CPUs */ +physid_mask_t phys_cpu_present_map = PHYSID_MASK_NONE; + +/* ACPI MADT entry parsing functions */ +#ifdef CONFIG_ACPI_BOOT +extern struct acpi_boot_flags acpi_boot; +#ifdef CONFIG_X86_LOCAL_APIC +extern int acpi_parse_lapic (acpi_table_entry_header *header); +extern int acpi_parse_lapic_addr_ovr (acpi_table_entry_header *header); +extern int acpi_parse_lapic_nmi (acpi_table_entry_header *header); +#endif /*CONFIG_X86_LOCAL_APIC*/ +#ifdef CONFIG_X86_IO_APIC +extern int acpi_parse_ioapic (acpi_table_entry_header *header); +#endif /*CONFIG_X86_IO_APIC*/ +#endif /*CONFIG_ACPI_BOOT*/ + +u8 bios_cpu_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; + + +/* + * Intel MP BIOS table parsing routines: + */ + +/* + * Checksum an MP configuration block. + */ + +static int __init mpf_checksum(unsigned char *mp, int len) +{ + int sum = 0; + + while (len--) + sum += *mp++; + + return sum & 0xFF; +} + +#ifndef CONFIG_XEN +static void __init MP_processor_info (struct mpc_config_processor *m) +{ + int ver; + static int found_bsp=0; + + if (!(m->mpc_cpuflag & CPU_ENABLED)) + return; + + printk(KERN_INFO "Processor #%d %d:%d APIC version %d\n", + m->mpc_apicid, + (m->mpc_cpufeature & CPU_FAMILY_MASK)>>8, + (m->mpc_cpufeature & CPU_MODEL_MASK)>>4, + m->mpc_apicver); + + if (m->mpc_cpuflag & CPU_BOOTPROCESSOR) { + Dprintk(" Bootup CPU\n"); + boot_cpu_id = m->mpc_apicid; + } + if (num_processors >= NR_CPUS) { + printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached." + " Processor ignored.\n", NR_CPUS); + return; + } + + num_processors++; + + if (m->mpc_apicid > MAX_APICS) { + printk(KERN_ERR "Processor #%d INVALID. (Max ID: %d).\n", + m->mpc_apicid, MAX_APICS); + return; + } + ver = m->mpc_apicver; + + physid_set(m->mpc_apicid, phys_cpu_present_map); + /* + * Validate version + */ + if (ver == 0x0) { + printk(KERN_ERR "BIOS bug, APIC version is 0 for CPU#%d! fixing up to 0x10. (tell your hw vendor)\n", m->mpc_apicid); + ver = 0x10; + } + apic_version[m->mpc_apicid] = ver; + if (m->mpc_cpuflag & CPU_BOOTPROCESSOR) { + /* + * bios_cpu_apicid is required to have processors listed + * in same order as logical cpu numbers. Hence the first + * entry is BSP, and so on. + */ + bios_cpu_apicid[0] = m->mpc_apicid; + x86_cpu_to_apicid[0] = m->mpc_apicid; + found_bsp = 1; + } else { + bios_cpu_apicid[num_processors - found_bsp] = m->mpc_apicid; + x86_cpu_to_apicid[num_processors - found_bsp] = m->mpc_apicid; + } +} +#else +void __init MP_processor_info (struct mpc_config_processor *m) +{ + num_processors++; +} +#endif /* CONFIG_XEN */ + +static void __init MP_bus_info (struct mpc_config_bus *m) +{ + char str[7]; + + memcpy(str, m->mpc_bustype, 6); + str[6] = 0; + Dprintk("Bus #%d is %s\n", m->mpc_busid, str); + + if (strncmp(str, "ISA", 3) == 0) { + mp_bus_id_to_type[m->mpc_busid] = MP_BUS_ISA; + } else if (strncmp(str, "EISA", 4) == 0) { + mp_bus_id_to_type[m->mpc_busid] = MP_BUS_EISA; + } else if (strncmp(str, "PCI", 3) == 0) { + mp_bus_id_to_type[m->mpc_busid] = MP_BUS_PCI; + mp_bus_id_to_pci_bus[m->mpc_busid] = mp_current_pci_id; + mp_current_pci_id++; + } else if (strncmp(str, "MCA", 3) == 0) { + mp_bus_id_to_type[m->mpc_busid] = MP_BUS_MCA; + } else { + printk(KERN_ERR "Unknown bustype %s\n", str); + } +} + +static void __init MP_ioapic_info (struct mpc_config_ioapic *m) +{ + if (!(m->mpc_flags & MPC_APIC_USABLE)) + return; + + printk("I/O APIC #%d Version %d at 0x%X.\n", + m->mpc_apicid, m->mpc_apicver, m->mpc_apicaddr); + if (nr_ioapics >= MAX_IO_APICS) { + printk(KERN_ERR "Max # of I/O APICs (%d) exceeded (found %d).\n", + MAX_IO_APICS, nr_ioapics); + panic("Recompile kernel with bigger MAX_IO_APICS!.\n"); + } + if (!m->mpc_apicaddr) { + printk(KERN_ERR "WARNING: bogus zero I/O APIC address" + " found in MP table, skipping!\n"); + return; + } + mp_ioapics[nr_ioapics] = *m; + nr_ioapics++; +} + +static void __init MP_intsrc_info (struct mpc_config_intsrc *m) +{ + mp_irqs [mp_irq_entries] = *m; + Dprintk("Int: type %d, pol %d, trig %d, bus %d," + " IRQ %02x, APIC ID %x, APIC INT %02x\n", + m->mpc_irqtype, m->mpc_irqflag & 3, + (m->mpc_irqflag >> 2) & 3, m->mpc_srcbus, + m->mpc_srcbusirq, m->mpc_dstapic, m->mpc_dstirq); + if (++mp_irq_entries == MAX_IRQ_SOURCES) + panic("Max # of irq sources exceeded!!\n"); +} + +static void __init MP_lintsrc_info (struct mpc_config_lintsrc *m) +{ + Dprintk("Lint: type %d, pol %d, trig %d, bus %d," + " IRQ %02x, APIC ID %x, APIC LINT %02x\n", + m->mpc_irqtype, m->mpc_irqflag & 3, + (m->mpc_irqflag >> 2) &3, m->mpc_srcbusid, + m->mpc_srcbusirq, m->mpc_destapic, m->mpc_destapiclint); + /* + * Well it seems all SMP boards in existence + * use ExtINT/LVT1 == LINT0 and + * NMI/LVT2 == LINT1 - the following check + * will show us if this assumptions is false. + * Until then we do not have to add baggage. + */ + if ((m->mpc_irqtype == mp_ExtINT) && + (m->mpc_destapiclint != 0)) + BUG(); + if ((m->mpc_irqtype == mp_NMI) && + (m->mpc_destapiclint != 1)) + BUG(); +} + +/* + * Read/parse the MPC + */ + +static int __init smp_read_mpc(struct mp_config_table *mpc) +{ + char str[16]; + int count=sizeof(*mpc); + unsigned char *mpt=((unsigned char *)mpc)+count; + + if (memcmp(mpc->mpc_signature,MPC_SIGNATURE,4)) { + printk("SMP mptable: bad signature [%c%c%c%c]!\n", + mpc->mpc_signature[0], + mpc->mpc_signature[1], + mpc->mpc_signature[2], + mpc->mpc_signature[3]); + return 0; + } + if (mpf_checksum((unsigned char *)mpc,mpc->mpc_length)) { + printk("SMP mptable: checksum error!\n"); + return 0; + } + if (mpc->mpc_spec!=0x01 && mpc->mpc_spec!=0x04) { + printk(KERN_ERR "SMP mptable: bad table version (%d)!!\n", + mpc->mpc_spec); + return 0; + } + if (!mpc->mpc_lapic) { + printk(KERN_ERR "SMP mptable: null local APIC address!\n"); + return 0; + } + memcpy(str,mpc->mpc_oem,8); + str[8]=0; + printk(KERN_INFO "OEM ID: %s ",str); + + memcpy(str,mpc->mpc_productid,12); + str[12]=0; + printk(KERN_INFO "Product ID: %s ",str); + + printk(KERN_INFO "APIC at: 0x%X\n",mpc->mpc_lapic); + + /* save the local APIC address, it might be non-default */ + if (!acpi_lapic) + mp_lapic_addr = mpc->mpc_lapic; + + /* + * Now process the configuration blocks. + */ + while (count < mpc->mpc_length) { + switch(*mpt) { + case MP_PROCESSOR: + { + struct mpc_config_processor *m= + (struct mpc_config_processor *)mpt; + if (!acpi_lapic) + MP_processor_info(m); + mpt += sizeof(*m); + count += sizeof(*m); + break; + } + case MP_BUS: + { + struct mpc_config_bus *m= + (struct mpc_config_bus *)mpt; + MP_bus_info(m); + mpt += sizeof(*m); + count += sizeof(*m); + break; + } + case MP_IOAPIC: + { + struct mpc_config_ioapic *m= + (struct mpc_config_ioapic *)mpt; + MP_ioapic_info(m); + mpt+=sizeof(*m); + count+=sizeof(*m); + break; + } + case MP_INTSRC: + { + struct mpc_config_intsrc *m= + (struct mpc_config_intsrc *)mpt; + + MP_intsrc_info(m); + mpt+=sizeof(*m); + count+=sizeof(*m); + break; + } + case MP_LINTSRC: + { + struct mpc_config_lintsrc *m= + (struct mpc_config_lintsrc *)mpt; + MP_lintsrc_info(m); + mpt+=sizeof(*m); + count+=sizeof(*m); + break; + } + } + } + clustered_apic_check(); + if (!num_processors) + printk(KERN_ERR "SMP mptable: no processors registered!\n"); + return num_processors; +} + +static int __init ELCR_trigger(unsigned int irq) +{ + unsigned int port; + + port = 0x4d0 + (irq >> 3); + return (inb(port) >> (irq & 7)) & 1; +} + +static void __init construct_default_ioirq_mptable(int mpc_default_type) +{ + struct mpc_config_intsrc intsrc; + int i; + int ELCR_fallback = 0; + + intsrc.mpc_type = MP_INTSRC; + intsrc.mpc_irqflag = 0; /* conforming */ + intsrc.mpc_srcbus = 0; + intsrc.mpc_dstapic = mp_ioapics[0].mpc_apicid; + + intsrc.mpc_irqtype = mp_INT; + + /* + * If true, we have an ISA/PCI system with no IRQ entries + * in the MP table. To prevent the PCI interrupts from being set up + * incorrectly, we try to use the ELCR. The sanity check to see if + * there is good ELCR data is very simple - IRQ0, 1, 2 and 13 can + * never be level sensitive, so we simply see if the ELCR agrees. + * If it does, we assume it's valid. + */ + if (mpc_default_type == 5) { + printk(KERN_INFO "ISA/PCI bus type with no IRQ information... falling back to ELCR\n"); + + if (ELCR_trigger(0) || ELCR_trigger(1) || ELCR_trigger(2) || ELCR_trigger(13)) + printk(KERN_ERR "ELCR contains invalid data... not using ELCR\n"); + else { + printk(KERN_INFO "Using ELCR to identify PCI interrupts\n"); + ELCR_fallback = 1; + } + } + + for (i = 0; i < 16; i++) { + switch (mpc_default_type) { + case 2: + if (i == 0 || i == 13) + continue; /* IRQ0 & IRQ13 not connected */ + /* fall through */ + default: + if (i == 2) + continue; /* IRQ2 is never connected */ + } + + if (ELCR_fallback) { + /* + * If the ELCR indicates a level-sensitive interrupt, we + * copy that information over to the MP table in the + * irqflag field (level sensitive, active high polarity). + */ + if (ELCR_trigger(i)) + intsrc.mpc_irqflag = 13; + else + intsrc.mpc_irqflag = 0; + } + + intsrc.mpc_srcbusirq = i; + intsrc.mpc_dstirq = i ? i : 2; /* IRQ0 to INTIN2 */ + MP_intsrc_info(&intsrc); + } + + intsrc.mpc_irqtype = mp_ExtINT; + intsrc.mpc_srcbusirq = 0; + intsrc.mpc_dstirq = 0; /* 8259A to INTIN0 */ + MP_intsrc_info(&intsrc); +} + +static inline void __init construct_default_ISA_mptable(int mpc_default_type) +{ + struct mpc_config_processor processor; + struct mpc_config_bus bus; + struct mpc_config_ioapic ioapic; + struct mpc_config_lintsrc lintsrc; + int linttypes[2] = { mp_ExtINT, mp_NMI }; + int i; + + /* + * local APIC has default address + */ + mp_lapic_addr = APIC_DEFAULT_PHYS_BASE; + + /* + * 2 CPUs, numbered 0 & 1. + */ + processor.mpc_type = MP_PROCESSOR; + /* Either an integrated APIC or a discrete 82489DX. */ + processor.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01; + processor.mpc_cpuflag = CPU_ENABLED; + processor.mpc_cpufeature = (boot_cpu_data.x86 << 8) | + (boot_cpu_data.x86_model << 4) | + boot_cpu_data.x86_mask; + processor.mpc_featureflag = boot_cpu_data.x86_capability[0]; + processor.mpc_reserved[0] = 0; + processor.mpc_reserved[1] = 0; + for (i = 0; i < 2; i++) { + processor.mpc_apicid = i; + MP_processor_info(&processor); + } + + bus.mpc_type = MP_BUS; + bus.mpc_busid = 0; + switch (mpc_default_type) { + default: + printk(KERN_ERR "???\nUnknown standard configuration %d\n", + mpc_default_type); + /* fall through */ + case 1: + case 5: + memcpy(bus.mpc_bustype, "ISA ", 6); + break; + case 2: + case 6: + case 3: + memcpy(bus.mpc_bustype, "EISA ", 6); + break; + case 4: + case 7: + memcpy(bus.mpc_bustype, "MCA ", 6); + } + MP_bus_info(&bus); + if (mpc_default_type > 4) { + bus.mpc_busid = 1; + memcpy(bus.mpc_bustype, "PCI ", 6); + MP_bus_info(&bus); + } + + ioapic.mpc_type = MP_IOAPIC; + ioapic.mpc_apicid = 2; + ioapic.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01; + ioapic.mpc_flags = MPC_APIC_USABLE; + ioapic.mpc_apicaddr = 0xFEC00000; + MP_ioapic_info(&ioapic); + + /* + * We set up most of the low 16 IO-APIC pins according to MPS rules. + */ + construct_default_ioirq_mptable(mpc_default_type); + + lintsrc.mpc_type = MP_LINTSRC; + lintsrc.mpc_irqflag = 0; /* conforming */ + lintsrc.mpc_srcbusid = 0; + lintsrc.mpc_srcbusirq = 0; + lintsrc.mpc_destapic = MP_APIC_ALL; + for (i = 0; i < 2; i++) { + lintsrc.mpc_irqtype = linttypes[i]; + lintsrc.mpc_destapiclint = i; + MP_lintsrc_info(&lintsrc); + } +} + +static struct intel_mp_floating *mpf_found; + +/* + * Scan the memory blocks for an SMP configuration block. + */ +void __init get_smp_config (void) +{ + struct intel_mp_floating *mpf = mpf_found; + + /* + * ACPI may be used to obtain the entire SMP configuration or just to + * enumerate/configure processors (CONFIG_ACPI_BOOT). Note that + * ACPI supports both logical (e.g. Hyper-Threading) and physical + * processors, where MPS only supports physical. + */ + if (acpi_lapic && acpi_ioapic) { + printk(KERN_INFO "Using ACPI (MADT) for SMP configuration information\n"); + return; + } + else if (acpi_lapic) + printk(KERN_INFO "Using ACPI for processor (LAPIC) configuration information\n"); + + printk("Intel MultiProcessor Specification v1.%d\n", mpf->mpf_specification); + if (mpf->mpf_feature2 & (1<<7)) { + printk(KERN_INFO " IMCR and PIC compatibility mode.\n"); + pic_mode = 1; + } else { + printk(KERN_INFO " Virtual Wire compatibility mode.\n"); + pic_mode = 0; + } + + /* + * Now see if we need to read further. + */ + if (mpf->mpf_feature1 != 0) { + + printk(KERN_INFO "Default MP configuration #%d\n", mpf->mpf_feature1); + construct_default_ISA_mptable(mpf->mpf_feature1); + + } else if (mpf->mpf_physptr) { + + /* + * Read the physical hardware table. Anything here will + * override the defaults. + */ + if (!smp_read_mpc(isa_bus_to_virt(mpf->mpf_physptr))) { + smp_found_config = 0; + printk(KERN_ERR "BIOS bug, MP table errors detected!...\n"); + printk(KERN_ERR "... disabling SMP support. (tell your hw vendor)\n"); + return; + } + /* + * If there are no explicit MP IRQ entries, then we are + * broken. We set up most of the low 16 IO-APIC pins to + * ISA defaults and hope it will work. + */ + if (!mp_irq_entries) { + struct mpc_config_bus bus; + + printk(KERN_ERR "BIOS bug, no explicit IRQ entries, using default mptable. (tell your hw vendor)\n"); + + bus.mpc_type = MP_BUS; + bus.mpc_busid = 0; + memcpy(bus.mpc_bustype, "ISA ", 6); + MP_bus_info(&bus); + + construct_default_ioirq_mptable(0); + } + + } else + BUG(); + + printk(KERN_INFO "Processors: %d\n", num_processors); + /* + * Only use the first configuration found. + */ +} + +static int __init smp_scan_config (unsigned long base, unsigned long length) +{ + extern void __bad_mpf_size(void); + unsigned int *bp = isa_bus_to_virt(base); + struct intel_mp_floating *mpf; + + Dprintk("Scan SMP from %p for %ld bytes.\n", bp,length); + if (sizeof(*mpf) != 16) + __bad_mpf_size(); + + while (length > 0) { + mpf = (struct intel_mp_floating *)bp; + if ((*bp == SMP_MAGIC_IDENT) && + (mpf->mpf_length == 1) && + !mpf_checksum((unsigned char *)bp, 16) && + ((mpf->mpf_specification == 1) + || (mpf->mpf_specification == 4)) ) { + + smp_found_config = 1; + mpf_found = mpf; + return 1; + } + bp += 4; + length -= 16; + } + return 0; +} + +void __init find_intel_smp (void) +{ + unsigned int address; + + /* + * FIXME: Linux assumes you have 640K of base ram.. + * this continues the error... + * + * 1) Scan the bottom 1K for a signature + * 2) Scan the top 1K of base RAM + * 3) Scan the 64K of bios + */ + if (smp_scan_config(0x0,0x400) || + smp_scan_config(639*0x400,0x400) || + smp_scan_config(0xF0000,0x10000)) + return; + /* + * If it is an SMP machine we should know now, unless the + * configuration is in an EISA/MCA bus machine with an + * extended bios data area. + * + * there is a real-mode segmented pointer pointing to the + * 4K EBDA area at 0x40E, calculate and scan it here. + * + * NOTE! There are Linux loaders that will corrupt the EBDA + * area, and as such this kind of SMP config may be less + * trustworthy, simply because the SMP table may have been + * stomped on during early boot. These loaders are buggy and + * should be fixed. + */ + + address = *(unsigned short *)phys_to_virt(0x40E); + address <<= 4; + if (smp_scan_config(address, 0x1000)) + return; + + /* If we have come this far, we did not find an MP table */ + printk(KERN_INFO "No mptable found.\n"); +} + +/* + * - Intel MP Configuration Table + */ +void __init find_smp_config (void) +{ +#ifdef CONFIG_X86_LOCAL_APIC + find_intel_smp(); +#endif +} + + +/* -------------------------------------------------------------------------- + ACPI-based MP Configuration + -------------------------------------------------------------------------- */ + +#ifdef CONFIG_ACPI_BOOT + +void __init mp_register_lapic_address ( + u64 address) +{ +#ifndef CONFIG_XEN + mp_lapic_addr = (unsigned long) address; + + if (boot_cpu_id == -1U) + boot_cpu_id = GET_APIC_ID(apic_read(APIC_ID)); + + Dprintk("Boot CPU = %d\n", boot_cpu_physical_apicid); +#endif +} + + +void __init mp_register_lapic ( + u8 id, + u8 enabled) +{ + struct mpc_config_processor processor; + int boot_cpu = 0; + + if (id >= MAX_APICS) { + printk(KERN_WARNING "Processor #%d invalid (max %d)\n", + id, MAX_APICS); + return; + } + + if (id == boot_cpu_physical_apicid) + boot_cpu = 1; + +#ifndef CONFIG_XEN + processor.mpc_type = MP_PROCESSOR; + processor.mpc_apicid = id; + processor.mpc_apicver = 0x10; /* TBD: lapic version */ + processor.mpc_cpuflag = (enabled ? CPU_ENABLED : 0); + processor.mpc_cpuflag |= (boot_cpu ? CPU_BOOTPROCESSOR : 0); + processor.mpc_cpufeature = (boot_cpu_data.x86 << 8) | + (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask; + processor.mpc_featureflag = boot_cpu_data.x86_capability[0]; + processor.mpc_reserved[0] = 0; + processor.mpc_reserved[1] = 0; +#endif + + MP_processor_info(&processor); +} + +#ifdef CONFIG_X86_IO_APIC + +#define MP_ISA_BUS 0 +#define MP_MAX_IOAPIC_PIN 127 + +static struct mp_ioapic_routing { + int apic_id; + int gsi_start; + int gsi_end; + u32 pin_programmed[4]; +} mp_ioapic_routing[MAX_IO_APICS]; + + +static int mp_find_ioapic ( + int gsi) +{ + int i = 0; + + /* Find the IOAPIC that manages this GSI. */ + for (i = 0; i < nr_ioapics; i++) { + if ((gsi >= mp_ioapic_routing[i].gsi_start) + && (gsi <= mp_ioapic_routing[i].gsi_end)) + return i; + } + + printk(KERN_ERR "ERROR: Unable to locate IOAPIC for GSI %d\n", gsi); + + return -1; +} + + +void __init mp_register_ioapic ( + u8 id, + u32 address, + u32 gsi_base) +{ + int idx = 0; + + if (nr_ioapics >= MAX_IO_APICS) { + printk(KERN_ERR "ERROR: Max # of I/O APICs (%d) exceeded " + "(found %d)\n", MAX_IO_APICS, nr_ioapics); + panic("Recompile kernel with bigger MAX_IO_APICS!\n"); + } + if (!address) { + printk(KERN_ERR "WARNING: Bogus (zero) I/O APIC address" + " found in MADT table, skipping!\n"); + return; + } + + idx = nr_ioapics++; + + mp_ioapics[idx].mpc_type = MP_IOAPIC; + mp_ioapics[idx].mpc_flags = MPC_APIC_USABLE; + mp_ioapics[idx].mpc_apicaddr = address; + + mp_ioapics[idx].mpc_apicid = id; + mp_ioapics[idx].mpc_apicver = io_apic_get_version(idx); + + /* + * Build basic IRQ lookup table to facilitate gsi->io_apic lookups + * and to prevent reprogramming of IOAPIC pins (PCI IRQs). + */ + mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].mpc_apicid; + mp_ioapic_routing[idx].gsi_start = gsi_base; + mp_ioapic_routing[idx].gsi_end = gsi_base + + io_apic_get_redir_entries(idx); + + printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, " + "GSI %d-%d\n", idx, mp_ioapics[idx].mpc_apicid, + mp_ioapics[idx].mpc_apicver, mp_ioapics[idx].mpc_apicaddr, + mp_ioapic_routing[idx].gsi_start, + mp_ioapic_routing[idx].gsi_end); + + return; +} + + +void __init mp_override_legacy_irq ( + u8 bus_irq, + u8 polarity, + u8 trigger, + u32 gsi) +{ + struct mpc_config_intsrc intsrc; + int ioapic = -1; + int pin = -1; + + /* + * Convert 'gsi' to 'ioapic.pin'. + */ + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) + return; + pin = gsi - mp_ioapic_routing[ioapic].gsi_start; + + /* + * TBD: This check is for faulty timer entries, where the override + * erroneously sets the trigger to level, resulting in a HUGE + * increase of timer interrupts! + */ + if ((bus_irq == 0) && (trigger == 3)) + trigger = 1; + + intsrc.mpc_type = MP_INTSRC; + intsrc.mpc_irqtype = mp_INT; + intsrc.mpc_irqflag = (trigger << 2) | polarity; + intsrc.mpc_srcbus = MP_ISA_BUS; + intsrc.mpc_srcbusirq = bus_irq; /* IRQ */ + intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid; /* APIC ID */ + intsrc.mpc_dstirq = pin; /* INTIN# */ + + Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, %d-%d\n", + intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3, + (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus, + intsrc.mpc_srcbusirq, intsrc.mpc_dstapic, intsrc.mpc_dstirq); + + mp_irqs[mp_irq_entries] = intsrc; + if (++mp_irq_entries == MAX_IRQ_SOURCES) + panic("Max # of irq sources exceeded!\n"); + + return; +} + + +void __init mp_config_acpi_legacy_irqs (void) +{ + struct mpc_config_intsrc intsrc; + int i = 0; + int ioapic = -1; + + /* + * Fabricate the legacy ISA bus (bus #31). + */ + mp_bus_id_to_type[MP_ISA_BUS] = MP_BUS_ISA; + Dprintk("Bus #%d is ISA\n", MP_ISA_BUS); + + /* + * Locate the IOAPIC that manages the ISA IRQs (0-15). + */ + ioapic = mp_find_ioapic(0); + if (ioapic < 0) + return; + + intsrc.mpc_type = MP_INTSRC; + intsrc.mpc_irqflag = 0; /* Conforming */ + intsrc.mpc_srcbus = MP_ISA_BUS; + intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid; + + /* + * Use the default configuration for the IRQs 0-15. Unless + * overridden by (MADT) interrupt source override entries. + */ + for (i = 0; i < 16; i++) { + int idx; + + for (idx = 0; idx < mp_irq_entries; idx++) { + struct mpc_config_intsrc *irq = mp_irqs + idx; + + /* Do we already have a mapping for this ISA IRQ? */ + if (irq->mpc_srcbus == MP_ISA_BUS && irq->mpc_srcbusirq == i) + break; + + /* Do we already have a mapping for this IOAPIC pin */ + if ((irq->mpc_dstapic == intsrc.mpc_dstapic) && + (irq->mpc_dstirq == i)) + break; + } + + if (idx != mp_irq_entries) { + printk(KERN_DEBUG "ACPI: IRQ%d used by override.\n", i); + continue; /* IRQ already used */ + } + + intsrc.mpc_irqtype = mp_INT; + intsrc.mpc_srcbusirq = i; /* Identity mapped */ + intsrc.mpc_dstirq = i; + + Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, " + "%d-%d\n", intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3, + (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus, + intsrc.mpc_srcbusirq, intsrc.mpc_dstapic, + intsrc.mpc_dstirq); + + mp_irqs[mp_irq_entries] = intsrc; + if (++mp_irq_entries == MAX_IRQ_SOURCES) + panic("Max # of irq sources exceeded!\n"); + } + + return; +} + +int mp_register_gsi(u32 gsi, int edge_level, int active_high_low) +{ + int ioapic = -1; + int ioapic_pin = 0; + int idx, bit = 0; + + if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) + return gsi; + +#ifdef CONFIG_ACPI_BUS + /* Don't set up the ACPI SCI because it's already set up */ + if (acpi_fadt.sci_int == gsi) + return gsi; +#endif + + ioapic = mp_find_ioapic(gsi); + if (ioapic < 0) { + printk(KERN_WARNING "No IOAPIC for GSI %u\n", gsi); + return gsi; + } + + ioapic_pin = gsi - mp_ioapic_routing[ioapic].gsi_start; + + /* + * Avoid pin reprogramming. PRTs typically include entries + * with redundant pin->gsi mappings (but unique PCI devices); + * we only program the IOAPIC on the first. + */ + bit = ioapic_pin % 32; + idx = (ioapic_pin < 32) ? 0 : (ioapic_pin / 32); + if (idx > 3) { + printk(KERN_ERR "Invalid reference to IOAPIC pin " + "%d-%d\n", mp_ioapic_routing[ioapic].apic_id, + ioapic_pin); + return gsi; + } + if ((1<<bit) & mp_ioapic_routing[ioapic].pin_programmed[idx]) { + Dprintk(KERN_DEBUG "Pin %d-%d already programmed\n", + mp_ioapic_routing[ioapic].apic_id, ioapic_pin); + return gsi; + } + + mp_ioapic_routing[ioapic].pin_programmed[idx] |= (1<<bit); + + io_apic_set_pci_routing(ioapic, ioapic_pin, gsi, + edge_level == ACPI_EDGE_SENSITIVE ? 0 : 1, + active_high_low == ACPI_ACTIVE_HIGH ? 0 : 1); + return gsi; +} + +#endif /*CONFIG_X86_IO_APIC*/ +#endif /*CONFIG_ACPI_BOOT*/ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/pci-nommu-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/pci-nommu-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,98 @@ +/* Fallback functions when the main IOMMU code is not compiled in. This + code is roughly equivalent to i386. */ +#include <linux/mm.h> +#include <linux/init.h> +#include <linux/pci.h> +#include <linux/string.h> +#include <asm/proto.h> +#include <asm/processor.h> + +int iommu_merge = 0; +EXPORT_SYMBOL(iommu_merge); + +dma_addr_t bad_dma_address; +EXPORT_SYMBOL(bad_dma_address); + +int iommu_bio_merge = 0; +EXPORT_SYMBOL(iommu_bio_merge); + +int iommu_sac_force = 0; +EXPORT_SYMBOL(iommu_sac_force); + +#if 0 +/* + * Dummy IO MMU functions + */ + +void *dma_alloc_coherent(struct device *hwdev, size_t size, + dma_addr_t *dma_handle, unsigned gfp) +{ + void *ret; + u64 mask; + int order = get_order(size); + + if (hwdev) + mask = hwdev->coherent_dma_mask & *hwdev->dma_mask; + else + mask = 0xffffffff; + for (;;) { + ret = (void *)__get_free_pages(gfp, order); + if (ret == NULL) + return NULL; + *dma_handle = virt_to_bus(ret); + if ((*dma_handle & ~mask) == 0) + break; + free_pages((unsigned long)ret, order); + if (gfp & GFP_DMA) + return NULL; + gfp |= GFP_DMA; + } + + memset(ret, 0, size); + return ret; +} +EXPORT_SYMBOL(dma_alloc_coherent); + +void dma_free_coherent(struct device *hwdev, size_t size, + void *vaddr, dma_addr_t dma_handle) +{ + free_pages((unsigned long)vaddr, get_order(size)); +} +EXPORT_SYMBOL(dma_free_coherent); +#endif + +#if 0 +int dma_supported(struct device *hwdev, u64 mask) +{ + /* + * we fall back to GFP_DMA when the mask isn't all 1s, + * so we can't guarantee allocations that must be + * within a tighter range than GFP_DMA.. + * RED-PEN this won't work for pci_map_single. Caller has to + * use GFP_DMA in the first place. + */ + if (mask < 0x00ffffff) + return 0; + + return 1; +} +EXPORT_SYMBOL(dma_supported); +#endif + +int dma_get_cache_alignment(void) +{ + return boot_cpu_data.x86_clflush_size; +} +EXPORT_SYMBOL(dma_get_cache_alignment); + +static int __init check_ram(void) +{ + if (end_pfn >= 0xffffffff>>PAGE_SHIFT) { + printk( + KERN_ERR "WARNING more than 4GB of memory but IOMMU not compiled in.\n" + KERN_ERR "WARNING 32bit PCI may malfunction.\n"); + } + return 0; +} +__initcall(check_ram); + diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/process-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/process-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,752 @@ +/* + * linux/arch/x86-64/kernel/process.c + * + * Copyright (C) 1995 Linus Torvalds + * + * Pentium III FXSR, SSE support + * Gareth Hughes <gareth@xxxxxxxxxxx>, May 2000 + * + * X86-64 port + * Andi Kleen. + * + * $Id: process.c,v 1.38 2002/01/15 10:08:03 ak Exp $ + * + * Jun Nakajima <jun.nakajima@xxxxxxxxx> + * Modified for Xen + */ + +/* + * This file handles the architecture-dependent parts of process handling.. + */ + +#include <stdarg.h> + +#include <linux/cpu.h> +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/elfcore.h> +#include <linux/smp.h> +#include <linux/slab.h> +#include <linux/user.h> +#include <linux/module.h> +#include <linux/a.out.h> +#include <linux/interrupt.h> +#include <linux/delay.h> +#include <linux/irq.h> +#include <linux/ptrace.h> +#include <linux/utsname.h> +#include <linux/random.h> + +#include <asm/uaccess.h> +#include <asm/pgtable.h> +#include <asm/system.h> +#include <asm/io.h> +#include <asm/processor.h> +#include <asm/i387.h> +#include <asm/mmu_context.h> +#include <asm/pda.h> +#include <asm/prctl.h> +#include <asm/kdebug.h> +#include <xen/interface/dom0_ops.h> +#include <xen/interface/physdev.h> +#include <asm/desc.h> +#include <asm/proto.h> +#include <asm/hardirq.h> +#include <asm/ia32.h> + +asmlinkage extern void ret_from_fork(void); + +unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED; + +static atomic_t hlt_counter = ATOMIC_INIT(0); + +unsigned long boot_option_idle_override = 0; +EXPORT_SYMBOL(boot_option_idle_override); + +/* + * Powermanagement idle function, if any.. + */ +void (*pm_idle)(void); +static DEFINE_PER_CPU(unsigned int, cpu_idle_state); + +void disable_hlt(void) +{ + atomic_inc(&hlt_counter); +} + +EXPORT_SYMBOL(disable_hlt); + +void enable_hlt(void) +{ + atomic_dec(&hlt_counter); +} + +EXPORT_SYMBOL(enable_hlt); + +/* XXX XEN doesn't use default_idle(), poll_idle(). Use xen_idle() instead. */ +extern void stop_hz_timer(void); +extern void start_hz_timer(void); +void xen_idle(void) +{ + local_irq_disable(); + + if (need_resched()) { + local_irq_enable(); + } else { + stop_hz_timer(); + /* Blocking includes an implicit local_irq_enable(). */ + HYPERVISOR_sched_op(SCHEDOP_block, 0); + start_hz_timer(); + } +} + +#ifdef CONFIG_HOTPLUG_CPU +#include <asm/nmi.h> +/* We don't actually take CPU down, just spin without interrupts. */ +static inline void play_dead(void) +{ + /* Ack it */ + __get_cpu_var(cpu_state) = CPU_DEAD; + + /* We shouldn't have to disable interrupts while dead, but + * some interrupts just don't seem to go away, and this makes + * it "work" for testing purposes. */ + /* Death loop */ + while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE) + HYPERVISOR_sched_op(SCHEDOP_yield, 0); + + local_irq_disable(); + __flush_tlb_all(); + cpu_set(smp_processor_id(), cpu_online_map); + local_irq_enable(); +} +#else +static inline void play_dead(void) +{ + BUG(); +} +#endif /* CONFIG_HOTPLUG_CPU */ + +/* + * The idle thread. There's no useful work to be + * done, so just try to conserve power and have a + * low exit latency (ie sit in a loop waiting for + * somebody to say that they'd like to reschedule) + */ +void cpu_idle (void) +{ + int cpu = smp_processor_id(); + + /* endless idle loop with no priority at all */ + while (1) { + while (!need_resched()) { + if (__get_cpu_var(cpu_idle_state)) + __get_cpu_var(cpu_idle_state) = 0; + rmb(); + + if (cpu_is_offline(cpu)) + play_dead(); + + xen_idle(); + } + + schedule(); + } +} + +void cpu_idle_wait(void) +{ + unsigned int cpu, this_cpu = get_cpu(); + cpumask_t map; + + set_cpus_allowed(current, cpumask_of_cpu(this_cpu)); + put_cpu(); + + cpus_clear(map); + for_each_online_cpu(cpu) { + per_cpu(cpu_idle_state, cpu) = 1; + cpu_set(cpu, map); + } + + __get_cpu_var(cpu_idle_state) = 0; + + wmb(); + do { + ssleep(1); + for_each_online_cpu(cpu) { + if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu)) + cpu_clear(cpu, map); + } + cpus_and(map, map, cpu_online_map); + } while (!cpus_empty(map)); +} +EXPORT_SYMBOL_GPL(cpu_idle_wait); + +/* XXX XEN doesn't use mwait_idle(), select_idle_routine(), idle_setup(). */ +/* Always use xen_idle() instead. */ +void __init select_idle_routine(const struct cpuinfo_x86 *c) {} + +/* Prints also some state that isn't saved in the pt_regs */ +void __show_regs(struct pt_regs * regs) +{ + unsigned long fs, gs, shadowgs; + unsigned int fsindex,gsindex; + unsigned int ds,cs,es; + + printk("\n"); + print_modules(); + printk("Pid: %d, comm: %.20s %s %s\n", + current->pid, current->comm, print_tainted(), system_utsname.release); + printk("RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->rip); + printk_address(regs->rip); + printk("\nRSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, regs->rsp, regs->eflags); + printk("RAX: %016lx RBX: %016lx RCX: %016lx\n", + regs->rax, regs->rbx, regs->rcx); + printk("RDX: %016lx RSI: %016lx RDI: %016lx\n", + regs->rdx, regs->rsi, regs->rdi); + printk("RBP: %016lx R08: %016lx R09: %016lx\n", + regs->rbp, regs->r8, regs->r9); + printk("R10: %016lx R11: %016lx R12: %016lx\n", + regs->r10, regs->r11, regs->r12); + printk("R13: %016lx R14: %016lx R15: %016lx\n", + regs->r13, regs->r14, regs->r15); + + asm("mov %%ds,%0" : "=r" (ds)); + asm("mov %%cs,%0" : "=r" (cs)); + asm("mov %%es,%0" : "=r" (es)); + asm("mov %%fs,%0" : "=r" (fsindex)); + asm("mov %%gs,%0" : "=r" (gsindex)); + + rdmsrl(MSR_FS_BASE, fs); + rdmsrl(MSR_GS_BASE, gs); + rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); + + printk("FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", + fs,fsindex,gs,gsindex,shadowgs); + printk("CS: %04x DS: %04x ES: %04x\n", cs, ds, es); + +} + +void show_regs(struct pt_regs *regs) +{ + __show_regs(regs); + show_trace(&regs->rsp); +} + +/* + * Free current thread data structures etc.. + */ +void exit_thread(void) +{ + struct task_struct *me = current; + struct thread_struct *t = &me->thread; + if (me->thread.io_bitmap_ptr) { + struct tss_struct *tss = &per_cpu(init_tss, get_cpu()); + + kfree(t->io_bitmap_ptr); + t->io_bitmap_ptr = NULL; + /* + * Careful, clear this in the TSS too: + */ + memset(tss->io_bitmap, 0xff, t->io_bitmap_max); + t->io_bitmap_max = 0; + put_cpu(); + } +} + +void load_gs_index(unsigned gs) +{ + HYPERVISOR_set_segment_base(SEGBASE_GS_USER_SEL, gs); +} + +void flush_thread(void) +{ + struct task_struct *tsk = current; + struct thread_info *t = current_thread_info(); + + if (t->flags & _TIF_ABI_PENDING) + t->flags ^= (_TIF_ABI_PENDING | _TIF_IA32); + + tsk->thread.debugreg0 = 0; + tsk->thread.debugreg1 = 0; + tsk->thread.debugreg2 = 0; + tsk->thread.debugreg3 = 0; + tsk->thread.debugreg6 = 0; + tsk->thread.debugreg7 = 0; + memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); + /* + * Forget coprocessor state.. + */ + clear_fpu(tsk); + clear_used_math(); +} + +void release_thread(struct task_struct *dead_task) +{ + if (dead_task->mm) { + if (dead_task->mm->context.size) { + printk("WARNING: dead process %8s still has LDT? <%p/%d>\n", + dead_task->comm, + dead_task->mm->context.ldt, + dead_task->mm->context.size); + BUG(); + } + } +} + +static inline void set_32bit_tls(struct task_struct *t, int tls, u32 addr) +{ + struct user_desc ud = { + .base_addr = addr, + .limit = 0xfffff, + .contents = (3 << 3), /* user */ + .seg_32bit = 1, + .limit_in_pages = 1, + .useable = 1, + }; + struct n_desc_struct *desc = (void *)t->thread.tls_array; + desc += tls; + desc->a = LDT_entry_a(&ud); + desc->b = LDT_entry_b(&ud); +} + +static inline u32 read_32bit_tls(struct task_struct *t, int tls) +{ + struct desc_struct *desc = (void *)t->thread.tls_array; + desc += tls; + return desc->base0 | + (((u32)desc->base1) << 16) | + (((u32)desc->base2) << 24); +} + +/* + * This gets called before we allocate a new thread and copy + * the current task into it. + */ +void prepare_to_copy(struct task_struct *tsk) +{ + unlazy_fpu(tsk); +} + +int copy_thread(int nr, unsigned long clone_flags, unsigned long rsp, + unsigned long unused, + struct task_struct * p, struct pt_regs * regs) +{ + int err; + struct pt_regs * childregs; + struct task_struct *me = current; + + childregs = ((struct pt_regs *) (THREAD_SIZE + (unsigned long) p->thread_info)) - 1; + + *childregs = *regs; + + childregs->rax = 0; + childregs->rsp = rsp; + if (rsp == ~0UL) { + childregs->rsp = (unsigned long)childregs; + } + + p->thread.rsp = (unsigned long) childregs; + p->thread.rsp0 = (unsigned long) (childregs+1); + p->thread.userrsp = me->thread.userrsp; + + set_ti_thread_flag(p->thread_info, TIF_FORK); + + p->thread.fs = me->thread.fs; + p->thread.gs = me->thread.gs; + + asm("mov %%gs,%0" : "=m" (p->thread.gsindex)); + asm("mov %%fs,%0" : "=m" (p->thread.fsindex)); + asm("mov %%es,%0" : "=m" (p->thread.es)); + asm("mov %%ds,%0" : "=m" (p->thread.ds)); + + if (unlikely(me->thread.io_bitmap_ptr != NULL)) { + p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL); + if (!p->thread.io_bitmap_ptr) { + p->thread.io_bitmap_max = 0; + return -ENOMEM; + } + memcpy(p->thread.io_bitmap_ptr, me->thread.io_bitmap_ptr, IO_BITMAP_BYTES); + } + + /* + * Set a new TLS for the child thread? + */ + if (clone_flags & CLONE_SETTLS) { +#ifdef CONFIG_IA32_EMULATION + if (test_thread_flag(TIF_IA32)) + err = ia32_child_tls(p, childregs); + else +#endif + err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8); + if (err) + goto out; + } + p->thread.io_pl = current->thread.io_pl; + + err = 0; +out: + if (err && p->thread.io_bitmap_ptr) { + kfree(p->thread.io_bitmap_ptr); + p->thread.io_bitmap_max = 0; + } + return err; +} + +/* + * This special macro can be used to load a debugging register + */ +#define loaddebug(thread,register) \ + HYPERVISOR_set_debugreg((register), \ + (thread->debugreg ## register)) + + +static inline void __save_init_fpu( struct task_struct *tsk ) +{ + asm volatile( "rex64 ; fxsave %0 ; fnclex" + : "=m" (tsk->thread.i387.fxsave)); + tsk->thread_info->status &= ~TS_USEDFPU; +} + +/* + * switch_to(x,y) should switch tasks from x to y. + * + * This could still be optimized: + * - fold all the options into a flag word and test it with a single test. + * - could test fs/gs bitsliced + */ +struct task_struct *__switch_to(struct task_struct *prev_p, struct task_struct *next_p) +{ + struct thread_struct *prev = &prev_p->thread, + *next = &next_p->thread; + int cpu = smp_processor_id(); + struct tss_struct *tss = &per_cpu(init_tss, cpu); + physdev_op_t iopl_op, iobmp_op; + multicall_entry_t _mcl[8], *mcl = _mcl; + + /* + * This is basically '__unlazy_fpu', except that we queue a + * multicall to indicate FPU task switch, rather than + * synchronously trapping to Xen. + */ + if (prev_p->thread_info->status & TS_USEDFPU) { + __save_init_fpu(prev_p); /* _not_ save_init_fpu() */ + mcl->op = __HYPERVISOR_fpu_taskswitch; + mcl->args[0] = 1; + mcl++; + } + + /* + * Reload esp0, LDT and the page table pointer: + */ + tss->rsp0 = next->rsp0; + mcl->op = __HYPERVISOR_stack_switch; + mcl->args[0] = __KERNEL_DS; + mcl->args[1] = tss->rsp0; + mcl++; + + /* + * Load the per-thread Thread-Local Storage descriptor. + * This is load_TLS(next, cpu) with multicalls. + */ +#define C(i) do { \ + if (unlikely(next->tls_array[i] != prev->tls_array[i])) { \ + mcl->op = __HYPERVISOR_update_descriptor; \ + mcl->args[0] = virt_to_machine( \ + &get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN + i]);\ + mcl->args[1] = next->tls_array[i]; \ + mcl++; \ + } \ +} while (0) + C(0); C(1); C(2); +#undef C + + if (unlikely(prev->io_pl != next->io_pl)) { + iopl_op.cmd = PHYSDEVOP_SET_IOPL; + iopl_op.u.set_iopl.iopl = (next->io_pl == 0) ? 1 : next->io_pl; + mcl->op = __HYPERVISOR_physdev_op; + mcl->args[0] = (unsigned long)&iopl_op; + mcl++; + } + + if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr)) { + iobmp_op.cmd = + PHYSDEVOP_SET_IOBITMAP; + iobmp_op.u.set_iobitmap.bitmap = + (char *)next->io_bitmap_ptr; + iobmp_op.u.set_iobitmap.nr_ports = + next->io_bitmap_ptr ? IO_BITMAP_BITS : 0; + mcl->op = __HYPERVISOR_physdev_op; + mcl->args[0] = (unsigned long)&iobmp_op; + mcl++; + } + + (void)HYPERVISOR_multicall(_mcl, mcl - _mcl); + /* + * Switch DS and ES. + * This won't pick up thread selector changes, but I guess that is ok. + */ + if (unlikely(next->es)) + loadsegment(es, next->es); + + if (unlikely(next->ds)) + loadsegment(ds, next->ds); + + /* + * Switch FS and GS. + */ + if (unlikely(next->fsindex)) + loadsegment(fs, next->fsindex); + + if (next->fs) + HYPERVISOR_set_segment_base(SEGBASE_FS, next->fs); + + if (unlikely(next->gsindex)) + load_gs_index(next->gsindex); + + if (next->gs) + HYPERVISOR_set_segment_base(SEGBASE_GS_USER, next->gs); + + /* + * Switch the PDA context. + */ + prev->userrsp = read_pda(oldrsp); + write_pda(oldrsp, next->userrsp); + write_pda(pcurrent, next_p); + write_pda(kernelstack, (unsigned long)next_p->thread_info + THREAD_SIZE - PDA_STACKOFFSET); + + /* + * Now maybe reload the debug registers + */ + if (unlikely(next->debugreg7)) { + loaddebug(next, 0); + loaddebug(next, 1); + loaddebug(next, 2); + loaddebug(next, 3); + /* no 4 and 5 */ + loaddebug(next, 6); + loaddebug(next, 7); + } + + return prev_p; +} + +/* + * sys_execve() executes a new program. + */ +asmlinkage +long sys_execve(char __user *name, char __user * __user *argv, + char __user * __user *envp, struct pt_regs regs) +{ + long error; + char * filename; + + filename = getname(name); + error = PTR_ERR(filename); + if (IS_ERR(filename)) + return error; + error = do_execve(filename, argv, envp, &regs); + if (error == 0) { + task_lock(current); + current->ptrace &= ~PT_DTRACE; + task_unlock(current); + } + putname(filename); + return error; +} + +void set_personality_64bit(void) +{ + /* inherit personality from parent */ + + /* Make sure to be in 64bit mode */ + clear_thread_flag(TIF_IA32); + + /* TBD: overwrites user setup. Should have two bits. + But 64bit processes have always behaved this way, + so it's not too bad. The main problem is just that + 32bit childs are affected again. */ + current->personality &= ~READ_IMPLIES_EXEC; +} + +asmlinkage long sys_fork(struct pt_regs *regs) +{ + return do_fork(SIGCHLD, regs->rsp, regs, 0, NULL, NULL); +} + +asmlinkage long sys_clone(unsigned long clone_flags, unsigned long newsp, void __user *parent_tid, void __user *child_tid, struct pt_regs *regs) +{ + if (!newsp) + newsp = regs->rsp; + return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid); +} + +/* + * This is trivial, and on the face of it looks like it + * could equally well be done in user mode. + * + * Not so, for quite unobvious reasons - register pressure. + * In user mode vfork() cannot have a stack frame, and if + * done by calling the "clone()" system call directly, you + * do not have enough call-clobbered registers to hold all + * the information you need. + */ +asmlinkage long sys_vfork(struct pt_regs *regs) +{ + return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->rsp, regs, 0, + NULL, NULL); +} + +unsigned long get_wchan(struct task_struct *p) +{ + unsigned long stack; + u64 fp,rip; + int count = 0; + + if (!p || p == current || p->state==TASK_RUNNING) + return 0; + stack = (unsigned long)p->thread_info; + if (p->thread.rsp < stack || p->thread.rsp > stack+THREAD_SIZE) + return 0; + fp = *(u64 *)(p->thread.rsp); + do { + if (fp < (unsigned long)stack || fp > (unsigned long)stack+THREAD_SIZE) + return 0; + rip = *(u64 *)(fp+8); + if (!in_sched_functions(rip)) + return rip; + fp = *(u64 *)fp; + } while (count++ < 16); + return 0; +} + +long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) +{ + int ret = 0; + int doit = task == current; + int cpu; + + switch (code) { + case ARCH_SET_GS: + if (addr >= TASK_SIZE) + return -EPERM; + cpu = get_cpu(); + /* handle small bases via the GDT because that's faster to + switch. */ + if (addr <= 0xffffffff) { + set_32bit_tls(task, GS_TLS, addr); + if (doit) { + load_TLS(&task->thread, cpu); + load_gs_index(GS_TLS_SEL); + } + task->thread.gsindex = GS_TLS_SEL; + task->thread.gs = 0; + } else { + task->thread.gsindex = 0; + task->thread.gs = addr; + if (doit) { + load_gs_index(0); + ret = HYPERVISOR_set_segment_base(SEGBASE_GS_USER, addr); + } + } + put_cpu(); + break; + case ARCH_SET_FS: + /* Not strictly needed for fs, but do it for symmetry + with gs */ + if (addr >= TASK_SIZE) + return -EPERM; + cpu = get_cpu(); + /* handle small bases via the GDT because that's faster to + switch. */ + if (addr <= 0xffffffff) { + set_32bit_tls(task, FS_TLS, addr); + if (doit) { + load_TLS(&task->thread, cpu); + asm volatile("mov %0,%%fs" :: "r" (FS_TLS_SEL)); + } + task->thread.fsindex = FS_TLS_SEL; + task->thread.fs = 0; + } else { + task->thread.fsindex = 0; + task->thread.fs = addr; + if (doit) { + /* set the selector to 0 to not confuse + __switch_to */ + asm volatile("mov %0,%%fs" :: "r" (0)); + ret = HYPERVISOR_set_segment_base(SEGBASE_FS, addr); + + } + } + put_cpu(); + break; + case ARCH_GET_FS: { + unsigned long base; + if (task->thread.fsindex == FS_TLS_SEL) + base = read_32bit_tls(task, FS_TLS); + else if (doit) { + rdmsrl(MSR_FS_BASE, base); + } else + base = task->thread.fs; + ret = put_user(base, (unsigned long __user *)addr); + break; + } + case ARCH_GET_GS: { + unsigned long base; + if (task->thread.gsindex == GS_TLS_SEL) + base = read_32bit_tls(task, GS_TLS); + else if (doit) { + rdmsrl(MSR_KERNEL_GS_BASE, base); + } else + base = task->thread.gs; + ret = put_user(base, (unsigned long __user *)addr); + break; + } + + default: + ret = -EINVAL; + break; + } + + return ret; +} + +long sys_arch_prctl(int code, unsigned long addr) +{ + return do_arch_prctl(current, code, addr); +} + +/* + * Capture the user space registers if the task is not running (in user space) + */ +int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs) +{ + struct pt_regs *pp, ptregs; + + pp = (struct pt_regs *)(tsk->thread.rsp0); + --pp; + + ptregs = *pp; + ptregs.cs &= 0xffff; + ptregs.ss &= 0xffff; + + elf_core_copy_regs(regs, &ptregs); + + boot_option_idle_override = 1; + return 1; +} + +unsigned long arch_align_stack(unsigned long sp) +{ + if (randomize_va_space) + sp -= get_random_int() % 8192; + return sp & ~0xf; +} + +#ifndef CONFIG_SMP +void _restore_vcpu(void) +{ +} +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/setup-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/setup-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,1472 @@ +/* + * linux/arch/x86-64/kernel/setup.c + * + * Copyright (C) 1995 Linus Torvalds + * + * Nov 2001 Dave Jones <davej@xxxxxxx> + * Forked from i386 setup code. + * + * $Id$ + */ + +/* + * This file handles the architecture-dependent parts of initialization + */ + +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/stddef.h> +#include <linux/unistd.h> +#include <linux/ptrace.h> +#include <linux/slab.h> +#include <linux/user.h> +#include <linux/a.out.h> +#include <linux/tty.h> +#include <linux/ioport.h> +#include <linux/delay.h> +#include <linux/config.h> +#include <linux/init.h> +#include <linux/initrd.h> +#include <linux/highmem.h> +#include <linux/bootmem.h> +#include <linux/module.h> +#include <asm/processor.h> +#include <linux/console.h> +#include <linux/seq_file.h> +#include <linux/root_dev.h> +#include <linux/pci.h> +#include <linux/acpi.h> +#include <linux/kallsyms.h> +#include <linux/edd.h> +#include <asm/mtrr.h> +#include <asm/uaccess.h> +#include <asm/system.h> +#include <asm/io.h> +#include <asm/smp.h> +#include <asm/msr.h> +#include <asm/desc.h> +#include <video/edid.h> +#include <asm/e820.h> +#include <asm/dma.h> +#include <asm/mpspec.h> +#include <asm/mmu_context.h> +#include <asm/bootsetup.h> +#include <asm/proto.h> +#include <asm/setup.h> +#include <asm/mach_apic.h> +#include <asm/numa.h> +#ifdef CONFIG_XEN +#include <linux/percpu.h> +#include <xen/interface/physdev.h> +#include "setup_arch_pre.h" +#include <asm/hypervisor.h> +#include <xen/interface/nmi.h> +#include <xen/features.h> +#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) +#define PFN_PHYS(x) ((x) << PAGE_SHIFT) +#define end_pfn_map end_pfn +#include <asm/mach-xen/setup_arch_post.h> + +extern unsigned long start_pfn; +extern struct edid_info edid_info; + +shared_info_t *HYPERVISOR_shared_info = (shared_info_t *)empty_zero_page; +EXPORT_SYMBOL(HYPERVISOR_shared_info); + +extern char hypercall_page[PAGE_SIZE]; +EXPORT_SYMBOL(hypercall_page); + +/* Allows setting of maximum possible memory size */ +unsigned long xen_override_max_pfn; + +unsigned long *phys_to_machine_mapping; +unsigned long *pfn_to_mfn_frame_list_list, *pfn_to_mfn_frame_list[512]; + +EXPORT_SYMBOL(phys_to_machine_mapping); + +DEFINE_PER_CPU(multicall_entry_t, multicall_list[8]); +DEFINE_PER_CPU(int, nr_multicall_ents); + +/* Raw start-of-day parameters from the hypervisor. */ +start_info_t *xen_start_info; +EXPORT_SYMBOL(xen_start_info); +#endif + +/* + * Machine setup.. + */ + +struct cpuinfo_x86 boot_cpu_data; + +unsigned long mmu_cr4_features; + +int acpi_disabled; +EXPORT_SYMBOL(acpi_disabled); +#ifdef CONFIG_ACPI_BOOT +extern int __initdata acpi_ht; +extern acpi_interrupt_flags acpi_sci_flags; +int __initdata acpi_force = 0; +#endif + +int acpi_numa __initdata; + +/* Boot loader ID as an integer, for the benefit of proc_dointvec */ +int bootloader_type; + +unsigned long saved_video_mode; + +#ifdef CONFIG_SWIOTLB +int swiotlb; +EXPORT_SYMBOL(swiotlb); +#endif + +/* + * Setup options + */ +struct drive_info_struct { char dummy[32]; } drive_info; +struct screen_info screen_info; +struct sys_desc_table_struct { + unsigned short length; + unsigned char table[0]; +}; + +struct edid_info edid_info; +struct e820map e820; + +extern int root_mountflags; +extern char _text, _etext, _edata, _end; + +char command_line[COMMAND_LINE_SIZE]; + +struct resource standard_io_resources[] = { + { .name = "dma1", .start = 0x00, .end = 0x1f, + .flags = IORESOURCE_BUSY | IORESOURCE_IO }, + { .name = "pic1", .start = 0x20, .end = 0x21, + .flags = IORESOURCE_BUSY | IORESOURCE_IO }, + { .name = "timer0", .start = 0x40, .end = 0x43, + .flags = IORESOURCE_BUSY | IORESOURCE_IO }, + { .name = "timer1", .start = 0x50, .end = 0x53, + .flags = IORESOURCE_BUSY | IORESOURCE_IO }, + { .name = "keyboard", .start = 0x60, .end = 0x6f, + .flags = IORESOURCE_BUSY | IORESOURCE_IO }, + { .name = "dma page reg", .start = 0x80, .end = 0x8f, + .flags = IORESOURCE_BUSY | IORESOURCE_IO }, + { .name = "pic2", .start = 0xa0, .end = 0xa1, + .flags = IORESOURCE_BUSY | IORESOURCE_IO }, + { .name = "dma2", .start = 0xc0, .end = 0xdf, + .flags = IORESOURCE_BUSY | IORESOURCE_IO }, + { .name = "fpu", .start = 0xf0, .end = 0xff, + .flags = IORESOURCE_BUSY | IORESOURCE_IO } +}; + +#define STANDARD_IO_RESOURCES \ + (sizeof standard_io_resources / sizeof standard_io_resources[0]) + +#define IORESOURCE_RAM (IORESOURCE_BUSY | IORESOURCE_MEM) + +struct resource data_resource = { + .name = "Kernel data", + .start = 0, + .end = 0, + .flags = IORESOURCE_RAM, +}; +struct resource code_resource = { + .name = "Kernel code", + .start = 0, + .end = 0, + .flags = IORESOURCE_RAM, +}; + +#define IORESOURCE_ROM (IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM) + +#if defined(CONFIG_XEN_PRIVILEGED_GUEST) || !defined(CONFIG_XEN) +static struct resource system_rom_resource = { + .name = "System ROM", + .start = 0xf0000, + .end = 0xfffff, + .flags = IORESOURCE_ROM, +}; + +static struct resource extension_rom_resource = { + .name = "Extension ROM", + .start = 0xe0000, + .end = 0xeffff, + .flags = IORESOURCE_ROM, +}; + +static struct resource adapter_rom_resources[] = { + { .name = "Adapter ROM", .start = 0xc8000, .end = 0, + .flags = IORESOURCE_ROM }, + { .name = "Adapter ROM", .start = 0, .end = 0, + .flags = IORESOURCE_ROM }, + { .name = "Adapter ROM", .start = 0, .end = 0, + .flags = IORESOURCE_ROM }, + { .name = "Adapter ROM", .start = 0, .end = 0, + .flags = IORESOURCE_ROM }, + { .name = "Adapter ROM", .start = 0, .end = 0, + .flags = IORESOURCE_ROM }, + { .name = "Adapter ROM", .start = 0, .end = 0, + .flags = IORESOURCE_ROM } +}; +#endif + +#define ADAPTER_ROM_RESOURCES \ + (sizeof adapter_rom_resources / sizeof adapter_rom_resources[0]) + +#if defined(CONFIG_XEN_PRIVILEGED_GUEST) || !defined(CONFIG_XEN) +static struct resource video_rom_resource = { + .name = "Video ROM", + .start = 0xc0000, + .end = 0xc7fff, + .flags = IORESOURCE_ROM, +}; +#endif + +static struct resource video_ram_resource = { + .name = "Video RAM area", + .start = 0xa0000, + .end = 0xbffff, + .flags = IORESOURCE_RAM, +}; + +#if defined(CONFIG_XEN_PRIVILEGED_GUEST) || !defined(CONFIG_XEN) +#define romsignature(x) (*(unsigned short *)(x) == 0xaa55) + +static int __init romchecksum(unsigned char *rom, unsigned long length) +{ + unsigned char *p, sum = 0; + + for (p = rom; p < rom + length; p++) + sum += *p; + return sum == 0; +} + +static void __init probe_roms(void) +{ + unsigned long start, length, upper; + unsigned char *rom; + int i; + + /* video rom */ + upper = adapter_rom_resources[0].start; + for (start = video_rom_resource.start; start < upper; start += 2048) { + rom = isa_bus_to_virt(start); + if (!romsignature(rom)) + continue; + + video_rom_resource.start = start; + + /* 0 < length <= 0x7f * 512, historically */ + length = rom[2] * 512; + + /* if checksum okay, trust length byte */ + if (length && romchecksum(rom, length)) + video_rom_resource.end = start + length - 1; + + request_resource(&iomem_resource, &video_rom_resource); + break; + } + + start = (video_rom_resource.end + 1 + 2047) & ~2047UL; + if (start < upper) + start = upper; + + /* system rom */ + request_resource(&iomem_resource, &system_rom_resource); + upper = system_rom_resource.start; + + /* check for extension rom (ignore length byte!) */ + rom = isa_bus_to_virt(extension_rom_resource.start); + if (romsignature(rom)) { + length = extension_rom_resource.end - extension_rom_resource.start + 1; + if (romchecksum(rom, length)) { + request_resource(&iomem_resource, &extension_rom_resource); + upper = extension_rom_resource.start; + } + } + + /* check for adapter roms on 2k boundaries */ + for (i = 0; i < ADAPTER_ROM_RESOURCES && start < upper; start += 2048) { + rom = isa_bus_to_virt(start); + if (!romsignature(rom)) + continue; + + /* 0 < length <= 0x7f * 512, historically */ + length = rom[2] * 512; + + /* but accept any length that fits if checksum okay */ + if (!length || start + length > upper || !romchecksum(rom, length)) + continue; + + adapter_rom_resources[i].start = start; + adapter_rom_resources[i].end = start + length - 1; + request_resource(&iomem_resource, &adapter_rom_resources[i]); + + start = adapter_rom_resources[i++].end & ~2047UL; + } +} +#endif + +static __init void parse_cmdline_early (char ** cmdline_p) +{ + char c = ' ', *to = command_line, *from = COMMAND_LINE; + int len = 0; + + /* Save unparsed command line copy for /proc/cmdline */ +#ifdef CONFIG_XEN + int max_cmdline; + + if ((max_cmdline = MAX_GUEST_CMDLINE) > COMMAND_LINE_SIZE) + max_cmdline = COMMAND_LINE_SIZE; + memcpy(saved_command_line, xen_start_info->cmd_line, max_cmdline); + saved_command_line[max_cmdline-1] = '\0'; +#else + memcpy(saved_command_line, COMMAND_LINE, COMMAND_LINE_SIZE); + saved_command_line[COMMAND_LINE_SIZE-1] = '\0'; +#endif + + for (;;) { + if (c != ' ') + goto next_char; + +#ifdef CONFIG_SMP + /* + * If the BIOS enumerates physical processors before logical, + * maxcpus=N at enumeration-time can be used to disable HT. + */ + else if (!memcmp(from, "maxcpus=", 8)) { + extern unsigned int maxcpus; + + maxcpus = simple_strtoul(from + 8, NULL, 0); + } +#endif +#ifdef CONFIG_ACPI_BOOT + /* "acpi=off" disables both ACPI table parsing and interpreter init */ + if (!memcmp(from, "acpi=off", 8)) + disable_acpi(); + + if (!memcmp(from, "acpi=force", 10)) { + /* add later when we do DMI horrors: */ + acpi_force = 1; + acpi_disabled = 0; + } + + /* acpi=ht just means: do ACPI MADT parsing + at bootup, but don't enable the full ACPI interpreter */ + if (!memcmp(from, "acpi=ht", 7)) { + if (!acpi_force) + disable_acpi(); + acpi_ht = 1; + } + else if (!memcmp(from, "pci=noacpi", 10)) + acpi_disable_pci(); + else if (!memcmp(from, "acpi=noirq", 10)) + acpi_noirq_set(); + + else if (!memcmp(from, "acpi_sci=edge", 13)) + acpi_sci_flags.trigger = 1; + else if (!memcmp(from, "acpi_sci=level", 14)) + acpi_sci_flags.trigger = 3; + else if (!memcmp(from, "acpi_sci=high", 13)) + acpi_sci_flags.polarity = 1; + else if (!memcmp(from, "acpi_sci=low", 12)) + acpi_sci_flags.polarity = 3; + + /* acpi=strict disables out-of-spec workarounds */ + else if (!memcmp(from, "acpi=strict", 11)) { + acpi_strict = 1; + } +#ifdef CONFIG_X86_IO_APIC + else if (!memcmp(from, "acpi_skip_timer_override", 24)) + acpi_skip_timer_override = 1; +#endif +#endif + +#ifndef CONFIG_XEN + if (!memcmp(from, "nolapic", 7) || + !memcmp(from, "disableapic", 11)) + disable_apic = 1; + + if (!memcmp(from, "noapic", 6)) + skip_ioapic_setup = 1; + + if (!memcmp(from, "apic", 4)) { + skip_ioapic_setup = 0; + ioapic_force = 1; + } +#endif + + if (!memcmp(from, "mem=", 4)) + parse_memopt(from+4, &from); + +#ifdef CONFIG_DISCONTIGMEM + if (!memcmp(from, "numa=", 5)) + numa_setup(from+5); +#endif + +#ifdef CONFIG_GART_IOMMU + if (!memcmp(from,"iommu=",6)) { + iommu_setup(from+6); + } +#endif + + if (!memcmp(from,"oops=panic", 10)) + panic_on_oops = 1; + + if (!memcmp(from, "noexec=", 7)) + nonx_setup(from + 7); + + next_char: + c = *(from++); + if (!c) + break; + if (COMMAND_LINE_SIZE <= ++len) + break; + *(to++) = c; + } + *to = '\0'; + *cmdline_p = command_line; +} + +#ifndef CONFIG_DISCONTIGMEM +#ifdef CONFIG_XEN +static void __init contig_initmem_init(void) +{ + unsigned long bootmap_size = init_bootmem(start_pfn, end_pfn); + free_bootmem(0, xen_start_info->nr_pages << PAGE_SHIFT); + reserve_bootmem(HIGH_MEMORY, + (PFN_PHYS(start_pfn) + bootmap_size + PAGE_SIZE-1) + - HIGH_MEMORY); +} +#else +static void __init contig_initmem_init(void) +{ + unsigned long bootmap_size, bootmap; + bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT; + bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size); + if (bootmap == -1L) + panic("Cannot find bootmem map of size %ld\n",bootmap_size); + bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn); + e820_bootmem_free(&contig_page_data, 0, end_pfn << PAGE_SHIFT); + reserve_bootmem(bootmap, bootmap_size); +} +#endif /* !CONFIG_XEN */ +#endif + +/* Use inline assembly to define this because the nops are defined + as inline assembly strings in the include files and we cannot + get them easily into strings. */ +asm("\t.data\nk8nops: " + K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6 + K8_NOP7 K8_NOP8); + +extern unsigned char k8nops[]; +static unsigned char *k8_nops[ASM_NOP_MAX+1] = { + NULL, + k8nops, + k8nops + 1, + k8nops + 1 + 2, + k8nops + 1 + 2 + 3, + k8nops + 1 + 2 + 3 + 4, + k8nops + 1 + 2 + 3 + 4 + 5, + k8nops + 1 + 2 + 3 + 4 + 5 + 6, + k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7, +}; + +/* Replace instructions with better alternatives for this CPU type. + + This runs before SMP is initialized to avoid SMP problems with + self modifying code. This implies that assymetric systems where + APs have less capabilities than the boot processor are not handled. + In this case boot with "noreplacement". */ +void apply_alternatives(void *start, void *end) +{ + struct alt_instr *a; + int diff, i, k; + for (a = start; (void *)a < end; a++) { + if (!boot_cpu_has(a->cpuid)) + continue; + + BUG_ON(a->replacementlen > a->instrlen); + __inline_memcpy(a->instr, a->replacement, a->replacementlen); + diff = a->instrlen - a->replacementlen; + + /* Pad the rest with nops */ + for (i = a->replacementlen; diff > 0; diff -= k, i += k) { + k = diff; + if (k > ASM_NOP_MAX) + k = ASM_NOP_MAX; + __inline_memcpy(a->instr + i, k8_nops[k], k); + } + } +} + +static int no_replacement __initdata = 0; + +void __init alternative_instructions(void) +{ + extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; + if (no_replacement) + return; + apply_alternatives(__alt_instructions, __alt_instructions_end); +} + +static int __init noreplacement_setup(char *s) +{ + no_replacement = 1; + return 0; +} + +__setup("noreplacement", noreplacement_setup); + +#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE) +struct edd edd; +#ifdef CONFIG_EDD_MODULE +EXPORT_SYMBOL(edd); +#endif +/** + * copy_edd() - Copy the BIOS EDD information + * from boot_params into a safe place. + * + */ +static inline void copy_edd(void) +{ + memcpy(edd.mbr_signature, EDD_MBR_SIGNATURE, sizeof(edd.mbr_signature)); + memcpy(edd.edd_info, EDD_BUF, sizeof(edd.edd_info)); + edd.mbr_signature_nr = EDD_MBR_SIG_NR; + edd.edd_info_nr = EDD_NR; +} +#else +static inline void copy_edd(void) +{ +} +#endif + +#ifndef CONFIG_XEN +#define EBDA_ADDR_POINTER 0x40E +static void __init reserve_ebda_region(void) +{ + unsigned int addr; + /** + * there is a real-mode segmented pointer pointing to the + * 4K EBDA area at 0x40E + */ + addr = *(unsigned short *)phys_to_virt(EBDA_ADDR_POINTER); + addr <<= 4; + if (addr) + reserve_bootmem_generic(addr, PAGE_SIZE); +} +#endif + +void __init setup_arch(char **cmdline_p) +{ + unsigned long kernel_end; + +#ifdef CONFIG_XEN + ROOT_DEV = MKDEV(RAMDISK_MAJOR,0); + drive_info = DRIVE_INFO; + kernel_end = 0; /* dummy */ +#ifdef CONFIG_XEN_PHYSDEV_ACCESS + screen_info = SCREEN_INFO; + + /* This is drawn from a dump from vgacon:startup in standard Linux. */ + screen_info.orig_video_mode = 3; + screen_info.orig_video_isVGA = 1; + screen_info.orig_video_lines = 25; + screen_info.orig_video_cols = 80; + screen_info.orig_video_ega_bx = 3; + screen_info.orig_video_points = 16; +#endif + edid_info = EDID_INFO; + saved_video_mode = SAVED_VIDEO_MODE; + bootloader_type = LOADER_TYPE; + +#ifdef CONFIG_BLK_DEV_RAM + rd_image_start = RAMDISK_FLAGS & RAMDISK_IMAGE_START_MASK; + rd_prompt = ((RAMDISK_FLAGS & RAMDISK_PROMPT_FLAG) != 0); + rd_doload = ((RAMDISK_FLAGS & RAMDISK_LOAD_FLAG) != 0); + + +#endif + + setup_xen_features(); + + HYPERVISOR_vm_assist(VMASST_CMD_enable, + VMASST_TYPE_writable_pagetables); + + ARCH_SETUP +#else + ROOT_DEV = old_decode_dev(ORIG_ROOT_DEV); + drive_info = DRIVE_INFO; + screen_info = SCREEN_INFO; + edid_info = EDID_INFO; + saved_video_mode = SAVED_VIDEO_MODE; + bootloader_type = LOADER_TYPE; + +#ifdef CONFIG_BLK_DEV_RAM + rd_image_start = RAMDISK_FLAGS & RAMDISK_IMAGE_START_MASK; + rd_prompt = ((RAMDISK_FLAGS & RAMDISK_PROMPT_FLAG) != 0); + rd_doload = ((RAMDISK_FLAGS & RAMDISK_LOAD_FLAG) != 0); +#endif + setup_memory_region(); + copy_edd(); +#endif /* !CONFIG_XEN */ + + if (!MOUNT_ROOT_RDONLY) + root_mountflags &= ~MS_RDONLY; + init_mm.start_code = (unsigned long) &_text; + init_mm.end_code = (unsigned long) &_etext; + init_mm.end_data = (unsigned long) &_edata; +#ifdef CONFIG_XEN + init_mm.brk = start_pfn << PAGE_SHIFT; +#else + init_mm.brk = (unsigned long) &_end; + + code_resource.start = virt_to_phys(&_text); + code_resource.end = virt_to_phys(&_etext)-1; + data_resource.start = virt_to_phys(&_etext); + data_resource.end = virt_to_phys(&_edata)-1; +#endif + + parse_cmdline_early(cmdline_p); + + early_identify_cpu(&boot_cpu_data); + + /* + * partially used pages are not usable - thus + * we are rounding upwards: + */ + end_pfn = e820_end_of_ram(); + + check_efer(); + + init_memory_mapping(0, (end_pfn_map << PAGE_SHIFT)); + +#ifdef CONFIG_ACPI_NUMA + /* + * Parse SRAT to discover nodes. + */ + acpi_numa_init(); +#endif + +#ifdef CONFIG_DISCONTIGMEM + numa_initmem_init(0, end_pfn); +#else + contig_initmem_init(); +#endif + +#ifndef CONFIG_XEN + /* Reserve direct mapping */ + reserve_bootmem_generic(table_start << PAGE_SHIFT, + (table_end - table_start) << PAGE_SHIFT); + + /* reserve kernel */ + kernel_end = round_up(__pa_symbol(&_end),PAGE_SIZE); + reserve_bootmem_generic(HIGH_MEMORY, kernel_end - HIGH_MEMORY); + + /* + * reserve physical page 0 - it's a special BIOS page on many boxes, + * enabling clean reboots, SMP operation, laptop functions. + */ + reserve_bootmem_generic(0, PAGE_SIZE); + + /* reserve ebda region */ + reserve_ebda_region(); +#endif + +#ifdef CONFIG_SMP + /* + * But first pinch a few for the stack/trampoline stuff + * FIXME: Don't need the extra page at 4K, but need to fix + * trampoline before removing it. (see the GDT stuff) + */ + reserve_bootmem_generic(PAGE_SIZE, PAGE_SIZE); + + /* Reserve SMP trampoline */ + reserve_bootmem_generic(SMP_TRAMPOLINE_BASE, PAGE_SIZE); +#endif + +#ifdef CONFIG_ACPI_SLEEP + /* + * Reserve low memory region for sleep support. + */ + acpi_reserve_bootmem(); +#endif +#ifdef CONFIG_XEN +#ifdef CONFIG_BLK_DEV_INITRD + if (xen_start_info->mod_start) { + if (INITRD_START + INITRD_SIZE <= (end_pfn << PAGE_SHIFT)) { + /*reserve_bootmem_generic(INITRD_START, INITRD_SIZE);*/ + initrd_start = INITRD_START + PAGE_OFFSET; + initrd_end = initrd_start+INITRD_SIZE; + initrd_below_start_ok = 1; + } else { + printk(KERN_ERR "initrd extends beyond end of memory " + "(0x%08lx > 0x%08lx)\ndisabling initrd\n", + (unsigned long)(INITRD_START + INITRD_SIZE), + (unsigned long)(end_pfn << PAGE_SHIFT)); + initrd_start = 0; + } + } +#endif +#else /* CONFIG_XEN */ +#ifdef CONFIG_BLK_DEV_INITRD + if (LOADER_TYPE && INITRD_START) { + if (INITRD_START + INITRD_SIZE <= (end_pfn << PAGE_SHIFT)) { + reserve_bootmem_generic(INITRD_START, INITRD_SIZE); + initrd_start = + INITRD_START ? INITRD_START + PAGE_OFFSET : 0; + initrd_end = initrd_start+INITRD_SIZE; + } + else { + printk(KERN_ERR "initrd extends beyond end of memory " + "(0x%08lx > 0x%08lx)\ndisabling initrd\n", + (unsigned long)(INITRD_START + INITRD_SIZE), + (unsigned long)(end_pfn << PAGE_SHIFT)); + initrd_start = 0; + } + } +#endif +#endif /* !CONFIG_XEN */ + paging_init(); +#ifdef CONFIG_X86_LOCAL_APIC + /* + * Find and reserve possible boot-time SMP configuration: + */ + find_smp_config(); +#endif +#ifdef CONFIG_XEN + { + int i, j, k, fpp; + unsigned long va; + + /* Make sure we have a large enough P->M table. */ + phys_to_machine_mapping = alloc_bootmem( + end_pfn * sizeof(unsigned long)); + memset(phys_to_machine_mapping, ~0, + end_pfn * sizeof(unsigned long)); + memcpy(phys_to_machine_mapping, + (unsigned long *)xen_start_info->mfn_list, + xen_start_info->nr_pages * sizeof(unsigned long)); + free_bootmem( + __pa(xen_start_info->mfn_list), + PFN_PHYS(PFN_UP(xen_start_info->nr_pages * + sizeof(unsigned long)))); + + /* 'Initial mapping' of old p2m table must be destroyed. */ + for (va = xen_start_info->mfn_list; + va < (xen_start_info->mfn_list + + (xen_start_info->nr_pages*sizeof(unsigned long))); + va += PAGE_SIZE) { + HYPERVISOR_update_va_mapping(va, __pte_ma(0), 0); + } + + /* 'Initial mapping' of initrd must be destroyed. */ + for (va = xen_start_info->mod_start; + va < (xen_start_info->mod_start+xen_start_info->mod_len); + va += PAGE_SIZE) { + HYPERVISOR_update_va_mapping(va, __pte_ma(0), 0); + } + + /* + * Initialise the list of the frames that specify the list of + * frames that make up the p2m table. Used by save/restore + */ + pfn_to_mfn_frame_list_list = alloc_bootmem(PAGE_SIZE); + HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = + virt_to_mfn(pfn_to_mfn_frame_list_list); + + fpp = PAGE_SIZE/sizeof(unsigned long); + for ( i=0, j=0, k=-1; i< end_pfn; i+=fpp, j++ ) + { + if ( (j % fpp) == 0 ) + { + k++; + BUG_ON(k>=fpp); + pfn_to_mfn_frame_list[k] = alloc_bootmem(PAGE_SIZE); + pfn_to_mfn_frame_list_list[k] = + virt_to_mfn(pfn_to_mfn_frame_list[k]); + j=0; + } + pfn_to_mfn_frame_list[k][j] = + virt_to_mfn(&phys_to_machine_mapping[i]); + } + HYPERVISOR_shared_info->arch.max_pfn = end_pfn; + + } + + if ( ! (xen_start_info->flags & SIF_INITDOMAIN)) + { + acpi_disabled = 1; +#ifdef CONFIG_ACPI_BOOT + acpi_ht = 0; +#endif + } +#endif + +#ifndef CONFIG_XEN + check_ioapic(); +#endif + +#ifdef CONFIG_ACPI_BOOT + /* + * Initialize the ACPI boot-time table parser (gets the RSDP and SDT). + * Call this early for SRAT node setup. + */ + acpi_boot_table_init(); + + /* + * Read APIC and some other early information from ACPI tables. + */ + acpi_boot_init(); +#endif + +#ifdef CONFIG_X86_LOCAL_APIC + /* + * get boot-time SMP configuration: + */ + if (smp_found_config) + get_smp_config(); +#ifndef CONFIG_XEN + init_apic_mappings(); +#endif +#endif + +#if defined(CONFIG_XEN_PRIVILEGED_GUEST) || !defined(CONFIG_XEN) + /* + * Request address space for all standard RAM and ROM resources + * and also for regions reported as reserved by the e820. + */ + probe_roms(); + e820_reserve_resources(); +#endif + + request_resource(&iomem_resource, &video_ram_resource); + + { + unsigned i; + /* request I/O space for devices used on all i[345]86 PCs */ + for (i = 0; i < STANDARD_IO_RESOURCES; i++) + request_resource(&ioport_resource, &standard_io_resources[i]); + } + + e820_setup_gap(); + +#ifdef CONFIG_GART_IOMMU + iommu_hole_init(); +#endif + +#ifdef CONFIG_XEN + { + physdev_op_t op; + + op.cmd = PHYSDEVOP_SET_IOPL; + op.u.set_iopl.iopl = 1; + HYPERVISOR_physdev_op(&op); + + if (xen_start_info->flags & SIF_INITDOMAIN) { + if (!(xen_start_info->flags & SIF_PRIVILEGED)) + panic("Xen granted us console access " + "but not privileged status"); + +#ifdef CONFIG_VT +#if defined(CONFIG_VGA_CONSOLE) + conswitchp = &vga_con; +#elif defined(CONFIG_DUMMY_CONSOLE) + conswitchp = &dummy_con; +#endif +#endif + } else { +#ifdef CONFIG_XEN_PRIVILEGED_GUEST + extern const struct consw xennull_con; + extern int console_use_vt; +#if defined(CONFIG_VGA_CONSOLE) + /* disable VGA driver */ + ORIG_VIDEO_ISVGA = VIDEO_TYPE_VLFB; +#endif + conswitchp = &xennull_con; + console_use_vt = 0; +#endif + } + } +#else /* CONFIG_XEN */ + +#ifdef CONFIG_VT +#if defined(CONFIG_VGA_CONSOLE) + conswitchp = &vga_con; +#elif defined(CONFIG_DUMMY_CONSOLE) + conswitchp = &dummy_con; +#endif +#endif + +#endif /* !CONFIG_XEN */ +} + +static int __init get_model_name(struct cpuinfo_x86 *c) +{ + unsigned int *v; + + if (c->extended_cpuid_level < 0x80000004) + return 0; + + v = (unsigned int *) c->x86_model_id; + cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]); + cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]); + cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]); + c->x86_model_id[48] = 0; + return 1; +} + + +static void __init display_cacheinfo(struct cpuinfo_x86 *c) +{ + unsigned int n, dummy, eax, ebx, ecx, edx; + + n = c->extended_cpuid_level; + + if (n >= 0x80000005) { + cpuid(0x80000005, &dummy, &ebx, &ecx, &edx); + printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), D cache %dK (%d bytes/line)\n", + edx>>24, edx&0xFF, ecx>>24, ecx&0xFF); + c->x86_cache_size=(ecx>>24)+(edx>>24); + /* On K8 L1 TLB is inclusive, so don't count it */ + c->x86_tlbsize = 0; + } + + if (n >= 0x80000006) { + cpuid(0x80000006, &dummy, &ebx, &ecx, &edx); + ecx = cpuid_ecx(0x80000006); + c->x86_cache_size = ecx >> 16; + c->x86_tlbsize += ((ebx >> 16) & 0xfff) + (ebx & 0xfff); + + printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n", + c->x86_cache_size, ecx & 0xFF); + } + + if (n >= 0x80000007) + cpuid(0x80000007, &dummy, &dummy, &dummy, &c->x86_power); + if (n >= 0x80000008) { + cpuid(0x80000008, &eax, &dummy, &dummy, &dummy); + c->x86_virt_bits = (eax >> 8) & 0xff; + c->x86_phys_bits = eax & 0xff; + } +} + +/* + * On a AMD dual core setup the lower bits of the APIC id distingush the cores. + * Assumes number of cores is a power of two. + */ +static void __init amd_detect_cmp(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + int cpu = smp_processor_id(); + int node = 0; + unsigned bits; + if (c->x86_num_cores == 1) + return; + + bits = 0; + while ((1 << bits) < c->x86_num_cores) + bits++; + + /* Low order bits define the core id (index of core in socket) */ + cpu_core_id[cpu] = phys_proc_id[cpu] & ((1 << bits)-1); + /* Convert the APIC ID into the socket ID */ + phys_proc_id[cpu] >>= bits; + +#ifdef CONFIG_NUMA + /* When an ACPI SRAT table is available use the mappings from SRAT + instead. */ + if (acpi_numa <= 0) { + node = phys_proc_id[cpu]; + if (!node_online(node)) + node = first_node(node_online_map); + cpu_to_node[cpu] = node; + } else { + node = cpu_to_node[cpu]; + } +#endif + + printk(KERN_INFO "CPU %d(%d) -> Node %d -> Core %d\n", + cpu, c->x86_num_cores, node, cpu_core_id[cpu]); +#endif +} + +static int __init init_amd(struct cpuinfo_x86 *c) +{ + int r; + int level; + + /* Bit 31 in normal CPUID used for nonstandard 3DNow ID; + 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */ + clear_bit(0*32+31, &c->x86_capability); + + /* C-stepping K8? */ + level = cpuid_eax(1); + if ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58) + set_bit(X86_FEATURE_K8_C, &c->x86_capability); + + r = get_model_name(c); + if (!r) { + switch (c->x86) { + case 15: + /* Should distinguish Models here, but this is only + a fallback anyways. */ + strcpy(c->x86_model_id, "Hammer"); + break; + } + } + display_cacheinfo(c); + + if (c->extended_cpuid_level >= 0x80000008) { + c->x86_num_cores = (cpuid_ecx(0x80000008) & 0xff) + 1; + if (c->x86_num_cores & (c->x86_num_cores - 1)) + c->x86_num_cores = 1; + + amd_detect_cmp(c); + } + + return r; +} + +static void __init detect_ht(struct cpuinfo_x86 *c) +{ +#ifdef CONFIG_SMP + u32 eax, ebx, ecx, edx; + int index_msb, tmp; + int cpu = smp_processor_id(); + + if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY)) + return; + + cpuid(1, &eax, &ebx, &ecx, &edx); + smp_num_siblings = (ebx & 0xff0000) >> 16; + + if (smp_num_siblings == 1) { + printk(KERN_INFO "CPU: Hyper-Threading is disabled\n"); + } else if (smp_num_siblings > 1) { + index_msb = 31; + /* + * At this point we only support two siblings per + * processor package. + */ + if (smp_num_siblings > NR_CPUS) { + printk(KERN_WARNING "CPU: Unsupported number of the siblings %d", smp_num_siblings); + smp_num_siblings = 1; + return; + } + tmp = smp_num_siblings; + while ((tmp & 0x80000000 ) == 0) { + tmp <<=1 ; + index_msb--; + } + if (smp_num_siblings & (smp_num_siblings - 1)) + index_msb++; + phys_proc_id[cpu] = phys_pkg_id(index_msb); + + printk(KERN_INFO "CPU: Physical Processor ID: %d\n", + phys_proc_id[cpu]); + + smp_num_siblings = smp_num_siblings / c->x86_num_cores; + + tmp = smp_num_siblings; + index_msb = 31; + while ((tmp & 0x80000000) == 0) { + tmp <<=1 ; + index_msb--; + } + if (smp_num_siblings & (smp_num_siblings - 1)) + index_msb++; + + cpu_core_id[cpu] = phys_pkg_id(index_msb); + + if (c->x86_num_cores > 1) + printk(KERN_INFO "CPU: Processor Core ID: %d\n", + cpu_core_id[cpu]); + } +#endif +} + +/* + * find out the number of processor cores on the die + */ +static int __init intel_num_cpu_cores(struct cpuinfo_x86 *c) +{ + unsigned int eax; + + if (c->cpuid_level < 4) + return 1; + + __asm__("cpuid" + : "=a" (eax) + : "0" (4), "c" (0) + : "bx", "dx"); + + if (eax & 0x1f) + return ((eax >> 26) + 1); + else + return 1; +} + +static void __init init_intel(struct cpuinfo_x86 *c) +{ + /* Cache sizes */ + unsigned n; + + init_intel_cacheinfo(c); + n = c->extended_cpuid_level; + if (n >= 0x80000008) { + unsigned eax = cpuid_eax(0x80000008); + c->x86_virt_bits = (eax >> 8) & 0xff; + c->x86_phys_bits = eax & 0xff; + } + + if (c->x86 == 15) + c->x86_cache_alignment = c->x86_clflush_size * 2; + if (c->x86 >= 15) + set_bit(X86_FEATURE_CONSTANT_TSC, &c->x86_capability); + c->x86_num_cores = intel_num_cpu_cores(c); +} + +void __init get_cpu_vendor(struct cpuinfo_x86 *c) +{ + char *v = c->x86_vendor_id; + + if (!strcmp(v, "AuthenticAMD")) + c->x86_vendor = X86_VENDOR_AMD; + else if (!strcmp(v, "GenuineIntel")) + c->x86_vendor = X86_VENDOR_INTEL; + else + c->x86_vendor = X86_VENDOR_UNKNOWN; +} + +struct cpu_model_info { + int vendor; + int family; + char *model_names[16]; +}; + +/* Do some early cpuid on the boot CPU to get some parameter that are + needed before check_bugs. Everything advanced is in identify_cpu + below. */ +void __init early_identify_cpu(struct cpuinfo_x86 *c) +{ + u32 tfms; + + c->loops_per_jiffy = loops_per_jiffy; + c->x86_cache_size = -1; + c->x86_vendor = X86_VENDOR_UNKNOWN; + c->x86_model = c->x86_mask = 0; /* So far unknown... */ + c->x86_vendor_id[0] = '\0'; /* Unset */ + c->x86_model_id[0] = '\0'; /* Unset */ + c->x86_clflush_size = 64; + c->x86_cache_alignment = c->x86_clflush_size; + c->x86_num_cores = 1; + c->extended_cpuid_level = 0; + memset(&c->x86_capability, 0, sizeof c->x86_capability); + + /* Get vendor name */ + cpuid(0x00000000, (unsigned int *)&c->cpuid_level, + (unsigned int *)&c->x86_vendor_id[0], + (unsigned int *)&c->x86_vendor_id[8], + (unsigned int *)&c->x86_vendor_id[4]); + + get_cpu_vendor(c); + + /* Initialize the standard set of capabilities */ + /* Note that the vendor-specific code below might override */ + + /* Intel-defined flags: level 0x00000001 */ + if (c->cpuid_level >= 0x00000001) { + __u32 misc; + cpuid(0x00000001, &tfms, &misc, &c->x86_capability[4], + &c->x86_capability[0]); + c->x86 = (tfms >> 8) & 0xf; + c->x86_model = (tfms >> 4) & 0xf; + c->x86_mask = tfms & 0xf; + if (c->x86 == 0xf) { + c->x86 += (tfms >> 20) & 0xff; + c->x86_model += ((tfms >> 16) & 0xF) << 4; + } + if (c->x86_capability[0] & (1<<19)) + c->x86_clflush_size = ((misc >> 8) & 0xff) * 8; + } else { + /* Have CPUID level 0 only - unheard of */ + c->x86 = 4; + } + +#ifdef CONFIG_SMP + phys_proc_id[smp_processor_id()] = (cpuid_ebx(1) >> 24) & 0xff; +#endif +} + +/* + * This does the hard work of actually picking apart the CPU stuff... + */ +void __init identify_cpu(struct cpuinfo_x86 *c) +{ + int i; + u32 xlvl; + + early_identify_cpu(c); + + /* AMD-defined flags: level 0x80000001 */ + xlvl = cpuid_eax(0x80000000); + c->extended_cpuid_level = xlvl; + if ((xlvl & 0xffff0000) == 0x80000000) { + if (xlvl >= 0x80000001) { + c->x86_capability[1] = cpuid_edx(0x80000001); + c->x86_capability[6] = cpuid_ecx(0x80000001); + } + if (xlvl >= 0x80000004) + get_model_name(c); /* Default name */ + } + + /* Transmeta-defined flags: level 0x80860001 */ + xlvl = cpuid_eax(0x80860000); + if ((xlvl & 0xffff0000) == 0x80860000) { + /* Don't set x86_cpuid_level here for now to not confuse. */ + if (xlvl >= 0x80860001) + c->x86_capability[2] = cpuid_edx(0x80860001); + } + + /* + * Vendor-specific initialization. In this section we + * canonicalize the feature flags, meaning if there are + * features a certain CPU supports which CPUID doesn't + * tell us, CPUID claiming incorrect flags, or other bugs, + * we handle them here. + * + * At the end of this section, c->x86_capability better + * indicate the features this CPU genuinely supports! + */ + switch (c->x86_vendor) { + case X86_VENDOR_AMD: + init_amd(c); + break; + + case X86_VENDOR_INTEL: + init_intel(c); + break; + + case X86_VENDOR_UNKNOWN: + default: + display_cacheinfo(c); + break; + } + + select_idle_routine(c); + detect_ht(c); + + /* + * On SMP, boot_cpu_data holds the common feature set between + * all CPUs; so make sure that we indicate which features are + * common between the CPUs. The first time this routine gets + * executed, c == &boot_cpu_data. + */ + if (c != &boot_cpu_data) { + /* AND the already accumulated flags with these */ + for (i = 0 ; i < NCAPINTS ; i++) + boot_cpu_data.x86_capability[i] &= c->x86_capability[i]; + } + +#ifdef CONFIG_X86_MCE + mcheck_init(c); +#endif +#ifdef CONFIG_NUMA + if (c != &boot_cpu_data) + numa_add_cpu(c - cpu_data); +#endif +} + + +void __init print_cpu_info(struct cpuinfo_x86 *c) +{ + if (c->x86_model_id[0]) + printk("%s", c->x86_model_id); + + if (c->x86_mask || c->cpuid_level >= 0) + printk(" stepping %02x\n", c->x86_mask); + else + printk("\n"); +} + +/* + * Get CPU information for use by the procfs. + */ + +static int show_cpuinfo(struct seq_file *m, void *v) +{ + struct cpuinfo_x86 *c = v; + + /* + * These flag bits must match the definitions in <asm/cpufeature.h>. + * NULL means this bit is undefined or reserved; either way it doesn't + * have meaning as far as Linux is concerned. Note that it's important + * to realize there is a difference between this table and CPUID -- if + * applications want to get the raw CPUID data, they should access + * /dev/cpu/<cpu_nr>/cpuid instead. + */ + static char *x86_cap_flags[] = { + /* Intel-defined */ + "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce", + "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov", + "pat", "pse36", "pn", "clflush", NULL, "dts", "acpi", "mmx", + "fxsr", "sse", "sse2", "ss", "ht", "tm", "ia64", NULL, + + /* AMD-defined */ + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, "nx", NULL, "mmxext", NULL, + NULL, "fxsr_opt", NULL, NULL, NULL, "lm", "3dnowext", "3dnow", + + /* Transmeta-defined */ + "recovery", "longrun", NULL, "lrti", NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + + /* Other (Linux-defined) */ + "cxmmx", NULL, "cyrix_arr", "centaur_mcr", NULL, + "constant_tsc", NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + + /* Intel-defined (#2) */ + "pni", NULL, NULL, "monitor", "ds_cpl", NULL, NULL, "est", + "tm2", NULL, "cid", NULL, NULL, "cx16", "xtpr", NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + + /* VIA/Cyrix/Centaur-defined */ + NULL, NULL, "rng", "rng_en", NULL, NULL, "ace", "ace_en", + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + + /* AMD-defined (#2) */ + "lahf_lm", "cmp_legacy", NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, + }; + static char *x86_power_flags[] = { + "ts", /* temperature sensor */ + "fid", /* frequency id control */ + "vid", /* voltage id control */ + "ttp", /* thermal trip */ + "tm", + "stc" + }; + + +#ifdef CONFIG_SMP + if (!cpu_online(c-cpu_data)) + return 0; +#endif + + seq_printf(m,"processor\t: %u\n" + "vendor_id\t: %s\n" + "cpu family\t: %d\n" + "model\t\t: %d\n" + "model name\t: %s\n", + (unsigned)(c-cpu_data), + c->x86_vendor_id[0] ? c->x86_vendor_id : "unknown", + c->x86, + (int)c->x86_model, + c->x86_model_id[0] ? c->x86_model_id : "unknown"); + + if (c->x86_mask || c->cpuid_level >= 0) + seq_printf(m, "stepping\t: %d\n", c->x86_mask); + else + seq_printf(m, "stepping\t: unknown\n"); + + if (cpu_has(c,X86_FEATURE_TSC)) { + seq_printf(m, "cpu MHz\t\t: %u.%03u\n", + cpu_khz / 1000, (cpu_khz % 1000)); + } + + /* Cache size */ + if (c->x86_cache_size >= 0) + seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size); + +#ifdef CONFIG_SMP + if (smp_num_siblings * c->x86_num_cores > 1) { + int cpu = c - cpu_data; + seq_printf(m, "physical id\t: %d\n", phys_proc_id[cpu]); + seq_printf(m, "siblings\t: %d\n", + c->x86_num_cores * smp_num_siblings); + seq_printf(m, "core id\t\t: %d\n", cpu_core_id[cpu]); + seq_printf(m, "cpu cores\t: %d\n", c->x86_num_cores); + } +#endif + + seq_printf(m, + "fpu\t\t: yes\n" + "fpu_exception\t: yes\n" + "cpuid level\t: %d\n" + "wp\t\t: yes\n" + "flags\t\t:", + c->cpuid_level); + + { + int i; + for ( i = 0 ; i < 32*NCAPINTS ; i++ ) + if ( test_bit(i, &c->x86_capability) && + x86_cap_flags[i] != NULL ) + seq_printf(m, " %s", x86_cap_flags[i]); + } + + seq_printf(m, "\nbogomips\t: %lu.%02lu\n", + c->loops_per_jiffy/(500000/HZ), + (c->loops_per_jiffy/(5000/HZ)) % 100); + + if (c->x86_tlbsize > 0) + seq_printf(m, "TLB size\t: %d 4K pages\n", c->x86_tlbsize); + seq_printf(m, "clflush size\t: %d\n", c->x86_clflush_size); + seq_printf(m, "cache_alignment\t: %d\n", c->x86_cache_alignment); + + seq_printf(m, "address sizes\t: %u bits physical, %u bits virtual\n", + c->x86_phys_bits, c->x86_virt_bits); + + seq_printf(m, "power management:"); + { + unsigned i; + for (i = 0; i < 32; i++) + if (c->x86_power & (1 << i)) { + if (i < ARRAY_SIZE(x86_power_flags)) + seq_printf(m, " %s", x86_power_flags[i]); + else + seq_printf(m, " [%d]", i); + } + } + + seq_printf(m, "\n\n"); + + return 0; +} + +static void *c_start(struct seq_file *m, loff_t *pos) +{ + return *pos < NR_CPUS ? cpu_data + *pos : NULL; +} + +static void *c_next(struct seq_file *m, void *v, loff_t *pos) +{ + ++*pos; + return c_start(m, pos); +} + +static void c_stop(struct seq_file *m, void *v) +{ +} + +struct seq_operations cpuinfo_op = { + .start =c_start, + .next = c_next, + .stop = c_stop, + .show = show_cpuinfo, +}; diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/setup64-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/setup64-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,359 @@ +/* + * X86-64 specific CPU setup. + * Copyright (C) 1995 Linus Torvalds + * Copyright 2001, 2002, 2003 SuSE Labs / Andi Kleen. + * See setup.c for older changelog. + * $Id: setup64.c,v 1.12 2002/03/21 10:09:17 ak Exp $ + * + * Jun Nakajima <jun.nakajima@xxxxxxxxx> + * Modified for Xen + * + */ +#include <linux/config.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/string.h> +#include <linux/bootmem.h> +#include <linux/bitops.h> +#include <asm/bootsetup.h> +#include <asm/pda.h> +#include <asm/pgtable.h> +#include <asm/processor.h> +#include <asm/desc.h> +#include <asm/atomic.h> +#include <asm/mmu_context.h> +#include <asm/smp.h> +#include <asm/i387.h> +#include <asm/percpu.h> +#include <asm/mtrr.h> +#include <asm/proto.h> +#include <asm/mman.h> +#include <asm/numa.h> +#ifdef CONFIG_XEN +#include <asm/hypervisor.h> +#endif + +char x86_boot_params[BOOT_PARAM_SIZE] __initdata = {0,}; + +cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE; + +struct x8664_pda cpu_pda[NR_CPUS] __cacheline_aligned; + +extern struct task_struct init_task; + +extern unsigned char __per_cpu_start[], __per_cpu_end[]; + +extern struct desc_ptr cpu_gdt_descr[]; +struct desc_ptr idt_descr = { 256 * 16, (unsigned long) idt_table }; + +char boot_cpu_stack[IRQSTACKSIZE] __attribute__((section(".bss.page_aligned"))); + +unsigned long __supported_pte_mask = ~0UL; +static int do_not_nx __initdata = 0; + +/* noexec=on|off +Control non executable mappings for 64bit processes. + +on Enable(default) +off Disable +*/ +int __init nonx_setup(char *str) +{ + if (!strncmp(str, "on", 2)) { + __supported_pte_mask |= _PAGE_NX; + do_not_nx = 0; + } else if (!strncmp(str, "off", 3)) { + do_not_nx = 1; + __supported_pte_mask &= ~_PAGE_NX; + } + return 0; +} +__setup("noexec=", nonx_setup); /* parsed early actually */ + +int force_personality32 = READ_IMPLIES_EXEC; + +/* noexec32=on|off +Control non executable heap for 32bit processes. +To control the stack too use noexec=off + +on PROT_READ does not imply PROT_EXEC for 32bit processes +off PROT_READ implies PROT_EXEC (default) +*/ +static int __init nonx32_setup(char *str) +{ + if (!strcmp(str, "on")) + force_personality32 &= ~READ_IMPLIES_EXEC; + else if (!strcmp(str, "off")) + force_personality32 |= READ_IMPLIES_EXEC; + return 0; +} +__setup("noexec32=", nonx32_setup); + +/* + * Great future plan: + * Declare PDA itself and support (irqstack,tss,pgd) as per cpu data. + * Always point %gs to its beginning + */ +void __init setup_per_cpu_areas(void) +{ + int i; + unsigned long size; + + /* Copy section for each CPU (we discard the original) */ + size = ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES); +#ifdef CONFIG_MODULES + if (size < PERCPU_ENOUGH_ROOM) + size = PERCPU_ENOUGH_ROOM; +#endif + + for (i = 0; i < NR_CPUS; i++) { + unsigned char *ptr; + + if (!NODE_DATA(cpu_to_node(i))) { + printk("cpu with no node %d, num_online_nodes %d\n", + i, num_online_nodes()); + ptr = alloc_bootmem(size); + } else { + ptr = alloc_bootmem_node(NODE_DATA(cpu_to_node(i)), size); + } + if (!ptr) + panic("Cannot allocate cpu data for CPU %d\n", i); + cpu_pda[i].data_offset = ptr - __per_cpu_start; + memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start); + } +} + +#ifdef CONFIG_XEN +static void switch_pt(void) +{ + xen_pt_switch(__pa(init_level4_pgt)); + xen_new_user_pt(__pa(init_level4_user_pgt)); +} + +void __cpuinit cpu_gdt_init(struct desc_ptr *gdt_descr) +{ + unsigned long frames[16]; + unsigned long va; + int f; + + for (va = gdt_descr->address, f = 0; + va < gdt_descr->address + gdt_descr->size; + va += PAGE_SIZE, f++) { + frames[f] = virt_to_mfn(va); + make_page_readonly( + (void *)va, XENFEAT_writable_descriptor_tables); + } + if (HYPERVISOR_set_gdt(frames, gdt_descr->size / + sizeof (struct desc_struct))) + BUG(); +} +#else +static void switch_pt(void) +{ + asm volatile("movq %0,%%cr3" :: "r" (__pa_symbol(&init_level4_pgt))); +} + +void __init cpu_gdt_init(struct desc_ptr *gdt_descr) +{ +#ifdef CONFIG_SMP + int cpu = stack_smp_processor_id(); +#else + int cpu = smp_processor_id(); +#endif + + asm volatile("lgdt %0" :: "m" (cpu_gdt_descr[cpu])); + asm volatile("lidt %0" :: "m" (idt_descr)); +} +#endif + +void pda_init(int cpu) +{ + struct x8664_pda *pda = &cpu_pda[cpu]; + + /* Setup up data that may be needed in __get_free_pages early */ + asm volatile("movl %0,%%fs ; movl %0,%%gs" :: "r" (0)); +#ifndef CONFIG_XEN + wrmsrl(MSR_GS_BASE, cpu_pda + cpu); +#else + HYPERVISOR_set_segment_base(SEGBASE_GS_KERNEL, + (unsigned long)(cpu_pda + cpu)); +#endif + + pda->me = pda; + pda->cpunumber = cpu; + pda->irqcount = -1; + pda->kernelstack = + (unsigned long)stack_thread_info() - PDA_STACKOFFSET + THREAD_SIZE; + pda->active_mm = &init_mm; + pda->mmu_state = 0; + + if (cpu == 0) { +#ifdef CONFIG_XEN + xen_init_pt(); +#endif + /* others are initialized in smpboot.c */ + pda->pcurrent = &init_task; + pda->irqstackptr = boot_cpu_stack; + } else { + pda->irqstackptr = (char *) + __get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER); + if (!pda->irqstackptr) + panic("cannot allocate irqstack for cpu %d", cpu); + } + + switch_pt(); + + pda->irqstackptr += IRQSTACKSIZE-64; +} + +char boot_exception_stacks[N_EXCEPTION_STACKS * EXCEPTION_STKSZ] +__attribute__((section(".bss.page_aligned"))); + +/* May not be marked __init: used by software suspend */ +void syscall_init(void) +{ +#ifndef CONFIG_XEN + /* + * LSTAR and STAR live in a bit strange symbiosis. + * They both write to the same internal register. STAR allows to set CS/DS + * but only a 32bit target. LSTAR sets the 64bit rip. + */ + wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 | ((u64)__KERNEL_CS)<<32); + wrmsrl(MSR_LSTAR, system_call); + + /* Flags to clear on syscall */ + wrmsrl(MSR_SYSCALL_MASK, EF_TF|EF_DF|EF_IE|0x3000); +#endif +#ifdef CONFIG_IA32_EMULATION + syscall32_cpu_init (); +#endif +} + +void __cpuinit check_efer(void) +{ + unsigned long efer; + + rdmsrl(MSR_EFER, efer); + if (!(efer & EFER_NX) || do_not_nx) { + __supported_pte_mask &= ~_PAGE_NX; + } +} + +/* + * cpu_init() initializes state that is per-CPU. Some data is already + * initialized (naturally) in the bootstrap process, such as the GDT + * and IDT. We reload them nevertheless, this function acts as a + * 'CPU state barrier', nothing should get across. + * A lot of state is already set up in PDA init. + */ +void __cpuinit cpu_init (void) +{ +#ifdef CONFIG_SMP + int cpu = stack_smp_processor_id(); +#else + int cpu = smp_processor_id(); +#endif + struct tss_struct *t = &per_cpu(init_tss, cpu); + unsigned long v; + char *estacks = NULL; + struct task_struct *me; + int i; + + /* CPU 0 is initialised in head64.c */ + if (cpu != 0) { + pda_init(cpu); + } else + estacks = boot_exception_stacks; + + me = current; + + if (cpu_test_and_set(cpu, cpu_initialized)) + panic("CPU#%d already initialized!\n", cpu); + + printk("Initializing CPU#%d\n", cpu); + + clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); + + /* + * Initialize the per-CPU GDT with the boot GDT, + * and set up the GDT descriptor: + */ +#ifndef CONFIG_XEN + if (cpu) { + memcpy(cpu_gdt_table[cpu], cpu_gdt_table[0], GDT_SIZE); + } + + cpu_gdt_descr[cpu].size = GDT_SIZE; + cpu_gdt_descr[cpu].address = (unsigned long)cpu_gdt_table[cpu]; + + memcpy(me->thread.tls_array, cpu_gdt_table[cpu], GDT_ENTRY_TLS_ENTRIES * 8); +#else + memcpy(me->thread.tls_array, &get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN], + GDT_ENTRY_TLS_ENTRIES * 8); + + cpu_gdt_init(&cpu_gdt_descr[cpu]); +#endif + + /* + * Delete NT + */ + + asm volatile("pushfq ; popq %%rax ; btr $14,%%rax ; pushq %%rax ; popfq" ::: "eax"); + + syscall_init(); + + wrmsrl(MSR_FS_BASE, 0); + wrmsrl(MSR_KERNEL_GS_BASE, 0); + barrier(); + + check_efer(); + + /* + * set up and load the per-CPU TSS + */ + for (v = 0; v < N_EXCEPTION_STACKS; v++) { + if (cpu) { + estacks = (char *)__get_free_pages(GFP_ATOMIC, + EXCEPTION_STACK_ORDER); + if (!estacks) + panic("Cannot allocate exception stack %ld %d\n", + v, cpu); + } + estacks += EXCEPTION_STKSZ; + t->ist[v] = (unsigned long)estacks; + } + + t->io_bitmap_base = offsetof(struct tss_struct, io_bitmap); + /* + * <= is required because the CPU will access up to + * 8 bits beyond the end of the IO permission bitmap. + */ + for (i = 0; i <= IO_BITMAP_LONGS; i++) + t->io_bitmap[i] = ~0UL; + + atomic_inc(&init_mm.mm_count); + me->active_mm = &init_mm; + if (me->mm) + BUG(); + enter_lazy_tlb(&init_mm, me); + +#ifndef CONFIG_XEN + set_tss_desc(cpu, t); + load_TR_desc(); +#endif + load_LDT(&init_mm.context); + + /* + * Clear all 6 debug registers: + */ + + set_debug(0UL, 0); + set_debug(0UL, 1); + set_debug(0UL, 2); + set_debug(0UL, 3); + set_debug(0UL, 6); + set_debug(0UL, 7); + + fpu_init(); +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/signal-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/signal-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,493 @@ +/* + * linux/arch/x86_64/kernel/signal.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs + * + * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson + * 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes + * 2000-2002 x86-64 support by Andi Kleen + * + * $Id: signal.c,v 1.18 2001/10/17 22:30:37 ak Exp $ + */ + +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/kernel.h> +#include <linux/signal.h> +#include <linux/errno.h> +#include <linux/wait.h> +#include <linux/ptrace.h> +#include <linux/unistd.h> +#include <linux/stddef.h> +#include <linux/personality.h> +#include <linux/compiler.h> +#include <asm/ucontext.h> +#include <asm/uaccess.h> +#include <asm/i387.h> +#include <asm/proto.h> +#include <asm/ia32_unistd.h> + +/* #define DEBUG_SIG 1 */ + +#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) + +void ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, + sigset_t *set, struct pt_regs * regs); +void ia32_setup_frame(int sig, struct k_sigaction *ka, + sigset_t *set, struct pt_regs * regs); + +asmlinkage long +sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize, struct pt_regs *regs) +{ + sigset_t saveset, newset; + + /* XXX: Don't preclude handling different sized sigset_t's. */ + if (sigsetsize != sizeof(sigset_t)) + return -EINVAL; + + if (copy_from_user(&newset, unewset, sizeof(newset))) + return -EFAULT; + sigdelsetmask(&newset, ~_BLOCKABLE); + + spin_lock_irq(&current->sighand->siglock); + saveset = current->blocked; + current->blocked = newset; + recalc_sigpending(); + spin_unlock_irq(&current->sighand->siglock); +#ifdef DEBUG_SIG + printk("rt_sigsuspend savset(%lx) newset(%lx) regs(%p) rip(%lx)\n", + saveset, newset, regs, regs->rip); +#endif + regs->rax = -EINTR; + while (1) { + current->state = TASK_INTERRUPTIBLE; + schedule(); + if (do_signal(regs, &saveset)) + return -EINTR; + } +} + +asmlinkage long +sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, + struct pt_regs *regs) +{ + return do_sigaltstack(uss, uoss, regs->rsp); +} + + +/* + * Do a signal return; undo the signal stack. + */ + +struct rt_sigframe +{ + char __user *pretcode; + struct ucontext uc; + struct siginfo info; +}; + +static int +restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, unsigned long *prax) +{ + unsigned int err = 0; + + /* Always make any pending restarted system calls return -EINTR */ + current_thread_info()->restart_block.fn = do_no_restart_syscall; + +#define COPY(x) err |= __get_user(regs->x, &sc->x) + + COPY(rdi); COPY(rsi); COPY(rbp); COPY(rsp); COPY(rbx); + COPY(rdx); COPY(rcx); COPY(rip); + COPY(r8); + COPY(r9); + COPY(r10); + COPY(r11); + COPY(r12); + COPY(r13); + COPY(r14); + COPY(r15); + + { + unsigned int tmpflags; + err |= __get_user(tmpflags, &sc->eflags); + regs->eflags = (regs->eflags & ~0x40DD5) | (tmpflags & 0x40DD5); + regs->orig_rax = -1; /* disable syscall checks */ + } + + { + struct _fpstate __user * buf; + err |= __get_user(buf, &sc->fpstate); + + if (buf) { + if (!access_ok(VERIFY_READ, buf, sizeof(*buf))) + goto badframe; + err |= restore_i387(buf); + } else { + struct task_struct *me = current; + if (used_math()) { + clear_fpu(me); + clear_used_math(); + } + } + } + + err |= __get_user(*prax, &sc->rax); + return err; + +badframe: + return 1; +} + +asmlinkage long sys_rt_sigreturn(struct pt_regs *regs) +{ + struct rt_sigframe __user *frame; + sigset_t set; + unsigned long eax; + + frame = (struct rt_sigframe __user *)(regs->rsp - 8); + if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) { + goto badframe; + } + if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) { + goto badframe; + } + + sigdelsetmask(&set, ~_BLOCKABLE); + spin_lock_irq(&current->sighand->siglock); + current->blocked = set; + recalc_sigpending(); + spin_unlock_irq(&current->sighand->siglock); + + if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &eax)) + goto badframe; + +#ifdef DEBUG_SIG + printk("%d sigreturn rip:%lx rsp:%lx frame:%p rax:%lx\n",current->pid,regs.rip,regs.rsp,frame,eax); +#endif + + if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->rsp) == -EFAULT) + goto badframe; + + return eax; + +badframe: + signal_fault(regs,frame,"sigreturn"); + return 0; +} + +/* + * Set up a signal frame. + */ + +static inline int +setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, unsigned long mask, struct task_struct *me) +{ + int err = 0; + + err |= __put_user(0, &sc->gs); + err |= __put_user(0, &sc->fs); + + err |= __put_user(regs->rdi, &sc->rdi); + err |= __put_user(regs->rsi, &sc->rsi); + err |= __put_user(regs->rbp, &sc->rbp); + err |= __put_user(regs->rsp, &sc->rsp); + err |= __put_user(regs->rbx, &sc->rbx); + err |= __put_user(regs->rdx, &sc->rdx); + err |= __put_user(regs->rcx, &sc->rcx); + err |= __put_user(regs->rax, &sc->rax); + err |= __put_user(regs->r8, &sc->r8); + err |= __put_user(regs->r9, &sc->r9); + err |= __put_user(regs->r10, &sc->r10); + err |= __put_user(regs->r11, &sc->r11); + err |= __put_user(regs->r12, &sc->r12); + err |= __put_user(regs->r13, &sc->r13); + err |= __put_user(regs->r14, &sc->r14); + err |= __put_user(regs->r15, &sc->r15); + err |= __put_user(me->thread.trap_no, &sc->trapno); + err |= __put_user(me->thread.error_code, &sc->err); + err |= __put_user(regs->rip, &sc->rip); + err |= __put_user(regs->eflags, &sc->eflags); + err |= __put_user(mask, &sc->oldmask); + err |= __put_user(me->thread.cr2, &sc->cr2); + + return err; +} + +/* + * Determine which stack to use.. + */ + +static void __user * +get_stack(struct k_sigaction *ka, struct pt_regs *regs, unsigned long size) +{ + unsigned long rsp; + + /* Default to using normal stack - redzone*/ + rsp = regs->rsp - 128; + + /* This is the X/Open sanctioned signal stack switching. */ + /* RED-PEN: redzone on that stack? */ + if (ka->sa.sa_flags & SA_ONSTACK) { + if (sas_ss_flags(rsp) == 0) + rsp = current->sas_ss_sp + current->sas_ss_size; + } + + return (void __user *)round_down(rsp - size, 16); +} + +static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, + sigset_t *set, struct pt_regs * regs) +{ + struct rt_sigframe __user *frame; + struct _fpstate __user *fp = NULL; + int err = 0; + struct task_struct *me = current; + + if (used_math()) { + fp = get_stack(ka, regs, sizeof(struct _fpstate)); + frame = (void __user *)round_down( + (unsigned long)fp - sizeof(struct rt_sigframe), 16) - 8; + + if (!access_ok(VERIFY_WRITE, fp, sizeof(struct _fpstate))) + goto give_sigsegv; + + if (save_i387(fp) < 0) + err |= -1; + } else + frame = get_stack(ka, regs, sizeof(struct rt_sigframe)) - 8; + + if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) + goto give_sigsegv; + + if (ka->sa.sa_flags & SA_SIGINFO) { + err |= copy_siginfo_to_user(&frame->info, info); + if (err) + goto give_sigsegv; + } + + /* Create the ucontext. */ + err |= __put_user(0, &frame->uc.uc_flags); + err |= __put_user(0, &frame->uc.uc_link); + err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp); + err |= __put_user(sas_ss_flags(regs->rsp), + &frame->uc.uc_stack.ss_flags); + err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size); + err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, set->sig[0], me); + err |= __put_user(fp, &frame->uc.uc_mcontext.fpstate); + if (sizeof(*set) == 16) { + __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]); + __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]); + } else + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + + /* Set up to return from userspace. If provided, use a stub + already in userspace. */ + /* x86-64 should always use SA_RESTORER. */ + if (ka->sa.sa_flags & SA_RESTORER) { + err |= __put_user(ka->sa.sa_restorer, &frame->pretcode); + } else { + /* could use a vstub here */ + goto give_sigsegv; + } + + if (err) + goto give_sigsegv; + +#ifdef DEBUG_SIG + printk("%d old rip %lx old rsp %lx old rax %lx\n", current->pid,regs->rip,regs->rsp,regs->rax); +#endif + + /* Set up registers for signal handler */ + { + struct exec_domain *ed = current_thread_info()->exec_domain; + if (unlikely(ed && ed->signal_invmap && sig < 32)) + sig = ed->signal_invmap[sig]; + } + regs->rdi = sig; + /* In case the signal handler was declared without prototypes */ + regs->rax = 0; + + /* This also works for non SA_SIGINFO handlers because they expect the + next argument after the signal number on the stack. */ + regs->rsi = (unsigned long)&frame->info; + regs->rdx = (unsigned long)&frame->uc; + regs->rip = (unsigned long) ka->sa.sa_handler; + + regs->rsp = (unsigned long)frame; + + set_fs(USER_DS); + regs->eflags &= ~TF_MASK; + if (test_thread_flag(TIF_SINGLESTEP)) + ptrace_notify(SIGTRAP); +#ifdef DEBUG_SIG + printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n", + current->comm, current->pid, frame, regs->rip, frame->pretcode); +#endif + + return; + +give_sigsegv: + force_sigsegv(sig, current); +} + +/* + * OK, we're invoking a handler + */ + +static void +handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, + sigset_t *oldset, struct pt_regs *regs) +{ +#ifdef DEBUG_SIG + printk("handle_signal pid:%d sig:%lu rip:%lx rsp:%lx regs=%p\n", + current->pid, sig, + regs->rip, regs->rsp, regs); +#endif + + /* Are we from a system call? */ + if ((long)regs->orig_rax >= 0) { + /* If so, check system call restarting.. */ + switch (regs->rax) { + case -ERESTART_RESTARTBLOCK: + case -ERESTARTNOHAND: + regs->rax = -EINTR; + break; + + case -ERESTARTSYS: + if (!(ka->sa.sa_flags & SA_RESTART)) { + regs->rax = -EINTR; + break; + } + /* fallthrough */ + case -ERESTARTNOINTR: + regs->rax = regs->orig_rax; + regs->rip -= 2; + break; + } + } + + /* + * If TF is set due to a debugger (PT_DTRACE), clear the TF + * flag so that register information in the sigcontext is + * correct. + */ + if (unlikely(regs->eflags & TF_MASK)) { + if (likely(current->ptrace & PT_DTRACE)) { + current->ptrace &= ~PT_DTRACE; + regs->eflags &= ~TF_MASK; + } + } + +#ifdef CONFIG_IA32_EMULATION + if (test_thread_flag(TIF_IA32)) { + if (ka->sa.sa_flags & SA_SIGINFO) + ia32_setup_rt_frame(sig, ka, info, oldset, regs); + else + ia32_setup_frame(sig, ka, oldset, regs); + } else +#endif + setup_rt_frame(sig, ka, info, oldset, regs); + + if (!(ka->sa.sa_flags & SA_NODEFER)) { + spin_lock_irq(&current->sighand->siglock); + sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask); + sigaddset(&current->blocked,sig); + recalc_sigpending(); + spin_unlock_irq(&current->sighand->siglock); + } +} + +/* + * Note that 'init' is a special process: it doesn't get signals it doesn't + * want to handle. Thus you cannot kill init even with a SIGKILL even by + * mistake. + */ +int do_signal(struct pt_regs *regs, sigset_t *oldset) +{ + struct k_sigaction ka; + siginfo_t info; + int signr; + + /* + * We want the common case to go fast, which + * is why we may in certain cases get here from + * kernel mode. Just return without doing anything + * if so. + */ + if ((regs->cs & 2) != 2) + return 1; + + if (try_to_freeze(0)) + goto no_signal; + + if (!oldset) + oldset = &current->blocked; + + signr = get_signal_to_deliver(&info, &ka, regs, NULL); + if (signr > 0) { + /* Reenable any watchpoints before delivering the + * signal to user space. The processor register will + * have been cleared if the watchpoint triggered + * inside the kernel. + */ + if (current->thread.debugreg7) { + HYPERVISOR_set_debugreg(7, + current->thread.debugreg7); + } + + /* Whee! Actually deliver the signal. */ + handle_signal(signr, &info, &ka, oldset, regs); + return 1; + } + + no_signal: + /* Did we come from a system call? */ + if ((long)regs->orig_rax >= 0) { + /* Restart the system call - no handlers present */ + long res = regs->rax; + if (res == -ERESTARTNOHAND || + res == -ERESTARTSYS || + res == -ERESTARTNOINTR) { + regs->rax = regs->orig_rax; + regs->rip -= 2; + } + if (regs->rax == (unsigned long)-ERESTART_RESTARTBLOCK) { + regs->rax = test_thread_flag(TIF_IA32) ? + __NR_ia32_restart_syscall : + __NR_restart_syscall; + regs->rip -= 2; + } + } + return 0; +} + +void do_notify_resume(struct pt_regs *regs, sigset_t *oldset, __u32 thread_info_flags) +{ +#ifdef DEBUG_SIG + printk("do_notify_resume flags:%x rip:%lx rsp:%lx caller:%lx pending:%lx\n", + thread_info_flags, regs->rip, regs->rsp, __builtin_return_address(0),signal_pending(current)); +#endif + + /* Pending single-step? */ + if (thread_info_flags & _TIF_SINGLESTEP) { + regs->eflags |= TF_MASK; + clear_thread_flag(TIF_SINGLESTEP); + } + + /* deal with pending signal delivery */ + if (thread_info_flags & _TIF_SIGPENDING) + do_signal(regs,oldset); +} + +void signal_fault(struct pt_regs *regs, void __user *frame, char *where) +{ + struct task_struct *me = current; + if (exception_trace) + printk("%s[%d] bad frame in %s frame:%p rip:%lx rsp:%lx orax:%lx\n", + me->comm,me->pid,where,frame,regs->rip,regs->rsp,regs->orig_rax); + + force_sig(SIGSEGV, me); +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/smp-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/smp-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,493 @@ +/* + * Intel SMP support routines. + * + * (c) 1995 Alan Cox, Building #3 <alan@xxxxxxxxxx> + * (c) 1998-99, 2000 Ingo Molnar <mingo@xxxxxxxxxx> + * (c) 2002,2003 Andi Kleen, SuSE Labs. + * + * This code is released under the GNU General Public License version 2 or + * later. + */ + +#include <linux/init.h> + +#include <linux/mm.h> +#include <linux/irq.h> +#include <linux/delay.h> +#include <linux/spinlock.h> +#include <linux/smp_lock.h> +#include <linux/smp.h> +#include <linux/kernel_stat.h> +#include <linux/mc146818rtc.h> +#include <linux/interrupt.h> + +#include <asm/mtrr.h> +#include <asm/pgalloc.h> +#include <asm/tlbflush.h> +#include <asm/mach_apic.h> +#include <asm/mmu_context.h> +#include <asm/proto.h> +#include <asm/apicdef.h> +#ifdef CONFIG_XEN +#include <xen/evtchn.h> +#endif + +#ifndef CONFIG_XEN +/* + * Smarter SMP flushing macros. + * c/o Linus Torvalds. + * + * These mean you can really definitely utterly forget about + * writing to user space from interrupts. (Its not allowed anyway). + * + * Optimizations Manfred Spraul <manfred@xxxxxxxxxxxxxxxx> + */ + +static cpumask_t flush_cpumask; +static struct mm_struct * flush_mm; +static unsigned long flush_va; +static DEFINE_SPINLOCK(tlbstate_lock); +#define FLUSH_ALL -1ULL +#endif + +/* + * We cannot call mmdrop() because we are in interrupt context, + * instead update mm->cpu_vm_mask. + */ +static inline void leave_mm (unsigned long cpu) +{ + if (read_pda(mmu_state) == TLBSTATE_OK) + BUG(); + clear_bit(cpu, &read_pda(active_mm)->cpu_vm_mask); + load_cr3(swapper_pg_dir); +} + +#ifndef CONFIG_XEN +/* + * + * The flush IPI assumes that a thread switch happens in this order: + * [cpu0: the cpu that switches] + * 1) switch_mm() either 1a) or 1b) + * 1a) thread switch to a different mm + * 1a1) clear_bit(cpu, &old_mm->cpu_vm_mask); + * Stop ipi delivery for the old mm. This is not synchronized with + * the other cpus, but smp_invalidate_interrupt ignore flush ipis + * for the wrong mm, and in the worst case we perform a superfluous + * tlb flush. + * 1a2) set cpu mmu_state to TLBSTATE_OK + * Now the smp_invalidate_interrupt won't call leave_mm if cpu0 + * was in lazy tlb mode. + * 1a3) update cpu active_mm + * Now cpu0 accepts tlb flushes for the new mm. + * 1a4) set_bit(cpu, &new_mm->cpu_vm_mask); + * Now the other cpus will send tlb flush ipis. + * 1a4) change cr3. + * 1b) thread switch without mm change + * cpu active_mm is correct, cpu0 already handles + * flush ipis. + * 1b1) set cpu mmu_state to TLBSTATE_OK + * 1b2) test_and_set the cpu bit in cpu_vm_mask. + * Atomically set the bit [other cpus will start sending flush ipis], + * and test the bit. + * 1b3) if the bit was 0: leave_mm was called, flush the tlb. + * 2) switch %%esp, ie current + * + * The interrupt must handle 2 special cases: + * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm. + * - the cpu performs speculative tlb reads, i.e. even if the cpu only + * runs in kernel space, the cpu could load tlb entries for user space + * pages. + * + * The good news is that cpu mmu_state is local to each cpu, no + * write/read ordering problems. + */ + +/* + * TLB flush IPI: + * + * 1) Flush the tlb entries if the cpu uses the mm that's being flushed. + * 2) Leave the mm if we are in the lazy tlb mode. + */ + +asmlinkage void smp_invalidate_interrupt (void) +{ + unsigned long cpu; + + cpu = get_cpu(); + + if (!cpu_isset(cpu, flush_cpumask)) + goto out; + /* + * This was a BUG() but until someone can quote me the + * line from the intel manual that guarantees an IPI to + * multiple CPUs is retried _only_ on the erroring CPUs + * its staying as a return + * + * BUG(); + */ + + if (flush_mm == read_pda(active_mm)) { + if (read_pda(mmu_state) == TLBSTATE_OK) { + if (flush_va == FLUSH_ALL) + local_flush_tlb(); + else + __flush_tlb_one(flush_va); + } else + leave_mm(cpu); + } + ack_APIC_irq(); + cpu_clear(cpu, flush_cpumask); + +out: + put_cpu_no_resched(); +} + +static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm, + unsigned long va) +{ + cpumask_t tmp; + /* + * A couple of (to be removed) sanity checks: + * + * - we do not send IPIs to not-yet booted CPUs. + * - current CPU must not be in mask + * - mask must exist :) + */ + BUG_ON(cpus_empty(cpumask)); + cpus_and(tmp, cpumask, cpu_online_map); + BUG_ON(!cpus_equal(tmp, cpumask)); + BUG_ON(cpu_isset(smp_processor_id(), cpumask)); + if (!mm) + BUG(); + + /* + * I'm not happy about this global shared spinlock in the + * MM hot path, but we'll see how contended it is. + * Temporarily this turns IRQs off, so that lockups are + * detected by the NMI watchdog. + */ + spin_lock(&tlbstate_lock); + + flush_mm = mm; + flush_va = va; + cpus_or(flush_cpumask, cpumask, flush_cpumask); + + /* + * We have to send the IPI only to + * CPUs affected. + */ + send_IPI_mask(cpumask, INVALIDATE_TLB_VECTOR); + + while (!cpus_empty(flush_cpumask)) + mb(); /* nothing. lockup detection does not belong here */; + + flush_mm = NULL; + flush_va = 0; + spin_unlock(&tlbstate_lock); +} + +void flush_tlb_current_task(void) +{ + struct mm_struct *mm = current->mm; + cpumask_t cpu_mask; + + preempt_disable(); + cpu_mask = mm->cpu_vm_mask; + cpu_clear(smp_processor_id(), cpu_mask); + + local_flush_tlb(); + if (!cpus_empty(cpu_mask)) + flush_tlb_others(cpu_mask, mm, FLUSH_ALL); + preempt_enable(); +} + +void flush_tlb_mm (struct mm_struct * mm) +{ + cpumask_t cpu_mask; + + preempt_disable(); + cpu_mask = mm->cpu_vm_mask; + cpu_clear(smp_processor_id(), cpu_mask); + + if (current->active_mm == mm) { + if (current->mm) + local_flush_tlb(); + else + leave_mm(smp_processor_id()); + } + if (!cpus_empty(cpu_mask)) + flush_tlb_others(cpu_mask, mm, FLUSH_ALL); + + preempt_enable(); +} + +void flush_tlb_page(struct vm_area_struct * vma, unsigned long va) +{ + struct mm_struct *mm = vma->vm_mm; + cpumask_t cpu_mask; + + preempt_disable(); + cpu_mask = mm->cpu_vm_mask; + cpu_clear(smp_processor_id(), cpu_mask); + + if (current->active_mm == mm) { + if(current->mm) + __flush_tlb_one(va); + else + leave_mm(smp_processor_id()); + } + + if (!cpus_empty(cpu_mask)) + flush_tlb_others(cpu_mask, mm, va); + + preempt_enable(); +} + +static void do_flush_tlb_all(void* info) +{ + unsigned long cpu = smp_processor_id(); + + __flush_tlb_all(); + if (read_pda(mmu_state) == TLBSTATE_LAZY) + leave_mm(cpu); +} + +void flush_tlb_all(void) +{ + on_each_cpu(do_flush_tlb_all, NULL, 1, 1); +} +#else +asmlinkage void smp_invalidate_interrupt (void) +{ return; } +void flush_tlb_current_task(void) +{ xen_tlb_flush_mask(&current->mm->cpu_vm_mask); } +void flush_tlb_mm (struct mm_struct * mm) +{ xen_tlb_flush_mask(&mm->cpu_vm_mask); } +void flush_tlb_page(struct vm_area_struct * vma, unsigned long va) +{ xen_invlpg_mask(&vma->vm_mm->cpu_vm_mask, va); } +void flush_tlb_all(void) +{ xen_tlb_flush_all(); } +#endif /* Xen */ + +void smp_kdb_stop(void) +{ + send_IPI_allbutself(KDB_VECTOR); +} + +/* + * this function sends a 'reschedule' IPI to another CPU. + * it goes straight through and wastes no time serializing + * anything. Worst case is that we lose a reschedule ... + */ + +void smp_send_reschedule(int cpu) +{ + send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR); +} + +/* + * Structure and data for smp_call_function(). This is designed to minimise + * static memory requirements. It also looks cleaner. + */ +static DEFINE_SPINLOCK(call_lock); + +struct call_data_struct { + void (*func) (void *info); + void *info; + atomic_t started; + atomic_t finished; + int wait; +}; + +static struct call_data_struct * call_data; + +/* + * this function sends a 'generic call function' IPI to all other CPUs + * in the system. + */ +static void __smp_call_function (void (*func) (void *info), void *info, + int nonatomic, int wait) +{ + struct call_data_struct data; + int cpus = num_online_cpus()-1; + + if (!cpus) + return; + + data.func = func; + data.info = info; + atomic_set(&data.started, 0); + data.wait = wait; + if (wait) + atomic_set(&data.finished, 0); + + call_data = &data; + wmb(); + /* Send a message to all other CPUs and wait for them to respond */ + send_IPI_allbutself(CALL_FUNCTION_VECTOR); + + /* Wait for response */ + while (atomic_read(&data.started) != cpus) +#ifndef CONFIG_XEN + cpu_relax(); +#else + barrier(); +#endif + + if (!wait) + return; + + while (atomic_read(&data.finished) != cpus) +#ifndef CONFIG_XEN + cpu_relax(); +#else + barrier(); +#endif +} + +/* + * smp_call_function - run a function on all other CPUs. + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @nonatomic: currently unused. + * @wait: If true, wait (atomically) until function has completed on other + * CPUs. + * + * Returns 0 on success, else a negative status code. Does not return until + * remote CPUs are nearly ready to execute func or are or have executed. + * + * You must not call this function with disabled interrupts or from a + * hardware interrupt handler or from a bottom half handler. + * Actually there are a few legal cases, like panic. + */ +int smp_call_function (void (*func) (void *info), void *info, int nonatomic, + int wait) +{ + spin_lock(&call_lock); + __smp_call_function(func,info,nonatomic,wait); + spin_unlock(&call_lock); + return 0; +} + +void smp_stop_cpu(void) +{ + /* + * Remove this CPU: + */ + cpu_clear(smp_processor_id(), cpu_online_map); + local_irq_disable(); +#ifndef CONFIG_XEN + disable_local_APIC(); +#endif + local_irq_enable(); +} + +static void smp_really_stop_cpu(void *dummy) +{ + smp_stop_cpu(); + for (;;) + asm("hlt"); +} + +void smp_send_stop(void) +{ + int nolock = 0; +#ifndef CONFIG_XEN + if (reboot_force) + return; +#endif + /* Don't deadlock on the call lock in panic */ + if (!spin_trylock(&call_lock)) { + /* ignore locking because we have paniced anyways */ + nolock = 1; + } + __smp_call_function(smp_really_stop_cpu, NULL, 0, 0); + if (!nolock) + spin_unlock(&call_lock); + + local_irq_disable(); +#ifndef CONFIG_XEN + disable_local_APIC(); +#endif + local_irq_enable(); +} + +/* + * Reschedule call back. Nothing to do, + * all the work is done automatically when + * we return from the interrupt. + */ +#ifndef CONFIG_XEN +asmlinkage void smp_reschedule_interrupt(void) +#else +asmlinkage irqreturn_t smp_reschedule_interrupt(void) +#endif +{ +#ifndef CONFIG_XEN + ack_APIC_irq(); +#else + return IRQ_HANDLED; +#endif +} + +#ifndef CONFIG_XEN +asmlinkage void smp_call_function_interrupt(void) +#else +asmlinkage irqreturn_t smp_call_function_interrupt(void) +#endif +{ + void (*func) (void *info) = call_data->func; + void *info = call_data->info; + int wait = call_data->wait; + +#ifndef CONFIG_XEN + ack_APIC_irq(); +#endif + /* + * Notify initiating CPU that I've grabbed the data and am + * about to execute the function + */ + mb(); + atomic_inc(&call_data->started); + /* + * At this point the info structure may be out of scope unless wait==1 + */ + irq_enter(); + (*func)(info); + irq_exit(); + if (wait) { + mb(); + atomic_inc(&call_data->finished); + } +#ifdef CONFIG_XEN + return IRQ_HANDLED; +#endif +} + +int safe_smp_processor_id(void) +{ +#ifdef CONFIG_XEN + return smp_processor_id(); +#else + int apicid, i; + + if (disable_apic) + return 0; + + apicid = hard_smp_processor_id(); + if (x86_cpu_to_apicid[apicid] == apicid) + return apicid; + + for (i = 0; i < NR_CPUS; ++i) { + if (x86_cpu_to_apicid[i] == apicid) + return i; + } + + /* No entries in x86_cpu_to_apicid? Either no MPS|ACPI, + * or called too early. Either way, we must be CPU 0. */ + if (x86_cpu_to_apicid[0] == BAD_APICID) + return 0; + + return 0; /* Should not happen */ +#endif +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/traps-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/traps-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,994 @@ +/* + * linux/arch/x86-64/traps.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs + * + * Pentium III FXSR, SSE support + * Gareth Hughes <gareth@xxxxxxxxxxx>, May 2000 + * + * $Id: traps.c,v 1.36 2002/03/24 11:09:10 ak Exp $ + */ + +/* + * 'Traps.c' handles hardware traps and faults after we have saved some + * state in 'entry.S'. + */ +#include <linux/config.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/ptrace.h> +#include <linux/timer.h> +#include <linux/mm.h> +#include <linux/init.h> +#include <linux/delay.h> +#include <linux/spinlock.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/moduleparam.h> +#include <linux/nmi.h> + +#include <asm/system.h> +#include <asm/uaccess.h> +#include <asm/io.h> +#include <asm/atomic.h> +#include <asm/debugreg.h> +#include <asm/desc.h> +#include <asm/i387.h> +#include <asm/kdebug.h> +#include <asm/processor.h> + +#include <asm/smp.h> +#include <asm/pgalloc.h> +#include <asm/pda.h> +#include <asm/proto.h> +#include <asm/nmi.h> + +#include <linux/irq.h> + + +extern struct gate_struct idt_table[256]; + +asmlinkage void divide_error(void); +asmlinkage void debug(void); +asmlinkage void nmi(void); +asmlinkage void int3(void); +asmlinkage void overflow(void); +asmlinkage void bounds(void); +asmlinkage void invalid_op(void); +asmlinkage void device_not_available(void); +asmlinkage void double_fault(void); +asmlinkage void coprocessor_segment_overrun(void); +asmlinkage void invalid_TSS(void); +asmlinkage void segment_not_present(void); +asmlinkage void stack_segment(void); +asmlinkage void general_protection(void); +asmlinkage void page_fault(void); +asmlinkage void coprocessor_error(void); +asmlinkage void simd_coprocessor_error(void); +asmlinkage void reserved(void); +asmlinkage void alignment_check(void); +asmlinkage void machine_check(void); +asmlinkage void spurious_interrupt_bug(void); +asmlinkage void call_debug(void); + +struct notifier_block *die_chain; +static DEFINE_SPINLOCK(die_notifier_lock); + +int register_die_notifier(struct notifier_block *nb) +{ + int err = 0; + unsigned long flags; + spin_lock_irqsave(&die_notifier_lock, flags); + err = notifier_chain_register(&die_chain, nb); + spin_unlock_irqrestore(&die_notifier_lock, flags); + return err; +} + +static inline void conditional_sti(struct pt_regs *regs) +{ + if (regs->eflags & X86_EFLAGS_IF) + local_irq_enable(); +} + +static int kstack_depth_to_print = 10; + +#ifdef CONFIG_KALLSYMS +#include <linux/kallsyms.h> +int printk_address(unsigned long address) +{ + unsigned long offset = 0, symsize; + const char *symname; + char *modname; + char *delim = ":"; + char namebuf[128]; + + symname = kallsyms_lookup(address, &symsize, &offset, &modname, namebuf); + if (!symname) + return printk("[<%016lx>]", address); + if (!modname) + modname = delim = ""; + return printk("<%016lx>{%s%s%s%s%+ld}", + address,delim,modname,delim,symname,offset); +} +#else +int printk_address(unsigned long address) +{ + return printk("[<%016lx>]", address); +} +#endif + +static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, + unsigned *usedp, const char **idp) +{ + static const char ids[N_EXCEPTION_STACKS][8] = { + [DEBUG_STACK - 1] = "#DB", + [NMI_STACK - 1] = "NMI", + [DOUBLEFAULT_STACK - 1] = "#DF", + [STACKFAULT_STACK - 1] = "#SS", + [MCE_STACK - 1] = "#MC", + }; + unsigned k; + + for (k = 0; k < N_EXCEPTION_STACKS; k++) { + unsigned long end; + + end = per_cpu(init_tss, cpu).ist[k]; + if (stack >= end) + continue; + if (stack >= end - EXCEPTION_STKSZ) { + if (*usedp & (1U << k)) + break; + *usedp |= 1U << k; + *idp = ids[k]; + return (unsigned long *)end; + } + } + return NULL; +} + +/* + * x86-64 can have upto three kernel stacks: + * process stack + * interrupt stack + * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack + */ + +void show_trace(unsigned long *stack) +{ + unsigned long addr; + const unsigned cpu = safe_smp_processor_id(); + unsigned long *irqstack_end = (unsigned long *)cpu_pda[cpu].irqstackptr; + int i; + unsigned used = 0; + + printk("\nCall Trace:"); + +#define HANDLE_STACK(cond) \ + do while (cond) { \ + addr = *stack++; \ + if (kernel_text_address(addr)) { \ + /* \ + * If the address is either in the text segment of the \ + * kernel, or in the region which contains vmalloc'ed \ + * memory, it *may* be the address of a calling \ + * routine; if so, print it so that someone tracing \ + * down the cause of the crash will be able to figure \ + * out the call path that was taken. \ + */ \ + i += printk_address(addr); \ + if (i > 50) { \ + printk("\n "); \ + i = 0; \ + } \ + else \ + i += printk(" "); \ + } \ + } while (0) + + for(i = 0; ; ) { + const char *id; + unsigned long *estack_end; + estack_end = in_exception_stack(cpu, (unsigned long)stack, + &used, &id); + + if (estack_end) { + i += printk(" <%s> ", id); + HANDLE_STACK (stack < estack_end); + i += printk(" <EOE> "); + stack = (unsigned long *) estack_end[-2]; + continue; + } + if (irqstack_end) { + unsigned long *irqstack; + irqstack = irqstack_end - + (IRQSTACKSIZE - 64) / sizeof(*irqstack); + + if (stack >= irqstack && stack < irqstack_end) { + i += printk(" <IRQ> "); + HANDLE_STACK (stack < irqstack_end); + stack = (unsigned long *) (irqstack_end[-1]); + irqstack_end = NULL; + i += printk(" <EOI> "); + continue; + } + } + break; + } + + HANDLE_STACK (((long) stack & (THREAD_SIZE-1)) != 0); +#undef HANDLE_STACK + printk("\n"); +} + +void show_stack(struct task_struct *tsk, unsigned long * rsp) +{ + unsigned long *stack; + int i; + const int cpu = safe_smp_processor_id(); + unsigned long *irqstack_end = (unsigned long *) (cpu_pda[cpu].irqstackptr); + unsigned long *irqstack = (unsigned long *) (cpu_pda[cpu].irqstackptr - IRQSTACKSIZE); + + // debugging aid: "show_stack(NULL, NULL);" prints the + // back trace for this cpu. + + if (rsp == NULL) { + if (tsk) + rsp = (unsigned long *)tsk->thread.rsp; + else + rsp = (unsigned long *)&rsp; + } + + stack = rsp; + for(i=0; i < kstack_depth_to_print; i++) { + if (stack >= irqstack && stack <= irqstack_end) { + if (stack == irqstack_end) { + stack = (unsigned long *) (irqstack_end[-1]); + printk(" <EOI> "); + } + } else { + if (((long) stack & (THREAD_SIZE-1)) == 0) + break; + } + if (i && ((i % 4) == 0)) + printk("\n "); + printk("%016lx ", *stack++); + touch_nmi_watchdog(); + } + show_trace((unsigned long *)rsp); +} + +/* + * The architecture-independent dump_stack generator + */ +void dump_stack(void) +{ + unsigned long dummy; + show_trace(&dummy); +} + +EXPORT_SYMBOL(dump_stack); + +void show_registers(struct pt_regs *regs) +{ + int i; + int in_kernel = (regs->cs & 3) == 0; + unsigned long rsp; + const int cpu = safe_smp_processor_id(); + struct task_struct *cur = cpu_pda[cpu].pcurrent; + + rsp = regs->rsp; + + printk("CPU %d ", cpu); + __show_regs(regs); + printk("Process %s (pid: %d, threadinfo %p, task %p)\n", + cur->comm, cur->pid, cur->thread_info, cur); + + /* + * When in-kernel, we also print out the stack and code at the + * time of the fault.. + */ + if (in_kernel) { + + printk("Stack: "); + show_stack(NULL, (unsigned long*)rsp); + + printk("\nCode: "); + if(regs->rip < PAGE_OFFSET) + goto bad; + + for(i=0;i<20;i++) + { + unsigned char c; + if(__get_user(c, &((unsigned char*)regs->rip)[i])) { +bad: + printk(" Bad RIP value."); + break; + } + printk("%02x ", c); + } + } + printk("\n"); +} + +void handle_BUG(struct pt_regs *regs) +{ + struct bug_frame f; + char tmp; + + if (regs->cs & 3) + return; + if (__copy_from_user(&f, (struct bug_frame *) regs->rip, + sizeof(struct bug_frame))) + return; + if ((unsigned long)f.filename < __PAGE_OFFSET || + f.ud2[0] != 0x0f || f.ud2[1] != 0x0b) + return; + if (__get_user(tmp, f.filename)) + f.filename = "unmapped filename"; + printk("----------- [cut here ] --------- [please bite here ] ---------\n"); + printk(KERN_ALERT "Kernel BUG at %.50s:%d\n", f.filename, f.line); +} + +#ifdef CONFIG_BUG +void out_of_line_bug(void) +{ + BUG(); +} +#endif + +static DEFINE_SPINLOCK(die_lock); +static int die_owner = -1; + +void oops_begin(void) +{ + int cpu = safe_smp_processor_id(); + /* racy, but better than risking deadlock. */ + local_irq_disable(); + if (!spin_trylock(&die_lock)) { + if (cpu == die_owner) + /* nested oops. should stop eventually */; + else + spin_lock(&die_lock); + } + die_owner = cpu; + console_verbose(); + bust_spinlocks(1); +} + +void oops_end(void) +{ + die_owner = -1; + bust_spinlocks(0); + spin_unlock(&die_lock); + if (panic_on_oops) + panic("Oops"); +} + +void __die(const char * str, struct pt_regs * regs, long err) +{ + static int die_counter; + printk(KERN_EMERG "%s: %04lx [%u] ", str, err & 0xffff,++die_counter); +#ifdef CONFIG_PREEMPT + printk("PREEMPT "); +#endif +#ifdef CONFIG_SMP + printk("SMP "); +#endif +#ifdef CONFIG_DEBUG_PAGEALLOC + printk("DEBUG_PAGEALLOC"); +#endif + printk("\n"); + notify_die(DIE_OOPS, (char *)str, regs, err, 255, SIGSEGV); + show_registers(regs); + /* Executive summary in case the oops scrolled away */ + printk(KERN_ALERT "RIP "); + printk_address(regs->rip); + printk(" RSP <%016lx>\n", regs->rsp); +} + +void die(const char * str, struct pt_regs * regs, long err) +{ + oops_begin(); + handle_BUG(regs); + __die(str, regs, err); + oops_end(); + do_exit(SIGSEGV); +} +static inline void die_if_kernel(const char * str, struct pt_regs * regs, long err) +{ + if (!(regs->eflags & VM_MASK) && (regs->cs == __KERNEL_CS)) + die(str, regs, err); +} + +#ifdef CONFIG_X86_LOCAL_APIC +void die_nmi(char *str, struct pt_regs *regs) +{ + oops_begin(); + /* + * We are in trouble anyway, lets at least try + * to get a message out. + */ + printk(str, safe_smp_processor_id()); + show_registers(regs); + if (panic_on_timeout || panic_on_oops) + panic("nmi watchdog"); + printk("console shuts up ...\n"); + oops_end(); + do_exit(SIGSEGV); +} +#endif + +static void do_trap(int trapnr, int signr, char *str, + struct pt_regs * regs, long error_code, siginfo_t *info) +{ + conditional_sti(regs); + +#ifdef CONFIG_CHECKING + { + unsigned long gs; + struct x8664_pda *pda = cpu_pda + safe_smp_processor_id(); + rdmsrl(MSR_GS_BASE, gs); + if (gs != (unsigned long)pda) { + wrmsrl(MSR_GS_BASE, pda); + printk("%s: wrong gs %lx expected %p rip %lx\n", str, gs, pda, + regs->rip); + } + } +#endif + + if ((regs->cs & 3) != 0) { + struct task_struct *tsk = current; + + if (exception_trace && unhandled_signal(tsk, signr)) + printk(KERN_INFO + "%s[%d] trap %s rip:%lx rsp:%lx error:%lx\n", + tsk->comm, tsk->pid, str, + regs->rip,regs->rsp,error_code); + + tsk->thread.error_code = error_code; + tsk->thread.trap_no = trapnr; + if (info) + force_sig_info(signr, info, tsk); + else + force_sig(signr, tsk); + return; + } + + + /* kernel trap */ + { + const struct exception_table_entry *fixup; + fixup = search_exception_tables(regs->rip); + if (fixup) { + regs->rip = fixup->fixup; + } else + die(str, regs, error_code); + return; + } +} + +#define DO_ERROR(trapnr, signr, str, name) \ +asmlinkage void do_##name(struct pt_regs * regs, long error_code) \ +{ \ + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ + == NOTIFY_STOP) \ + return; \ + do_trap(trapnr, signr, str, regs, error_code, NULL); \ +} + +#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ +asmlinkage void do_##name(struct pt_regs * regs, long error_code) \ +{ \ + siginfo_t info; \ + info.si_signo = signr; \ + info.si_errno = 0; \ + info.si_code = sicode; \ + info.si_addr = (void __user *)siaddr; \ + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ + == NOTIFY_STOP) \ + return; \ + do_trap(trapnr, signr, str, regs, error_code, &info); \ +} + +DO_ERROR_INFO( 0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->rip) +DO_ERROR( 4, SIGSEGV, "overflow", overflow) +DO_ERROR( 5, SIGSEGV, "bounds", bounds) +DO_ERROR_INFO( 6, SIGILL, "invalid operand", invalid_op, ILL_ILLOPN, regs->rip) +DO_ERROR( 7, SIGSEGV, "device not available", device_not_available) +DO_ERROR( 9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun) +DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS) +DO_ERROR(11, SIGBUS, "segment not present", segment_not_present) +DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0) +DO_ERROR(18, SIGSEGV, "reserved", reserved) +DO_ERROR(12, SIGBUS, "stack segment", stack_segment) +DO_ERROR( 8, SIGSEGV, "double fault", double_fault) + +asmlinkage void do_general_protection(struct pt_regs * regs, long error_code) +{ + conditional_sti(regs); + +#ifdef CONFIG_CHECKING + { + unsigned long gs; + struct x8664_pda *pda = cpu_pda + safe_smp_processor_id(); + rdmsrl(MSR_GS_BASE, gs); + if (gs != (unsigned long)pda) { + wrmsrl(MSR_GS_BASE, pda); + oops_in_progress++; + printk("general protection handler: wrong gs %lx expected %p\n", gs, pda); + oops_in_progress--; + } + } +#endif + + if ((regs->cs & 3)!=0) { + struct task_struct *tsk = current; + + if (exception_trace && unhandled_signal(tsk, SIGSEGV)) + printk(KERN_INFO + "%s[%d] general protection rip:%lx rsp:%lx error:%lx\n", + tsk->comm, tsk->pid, + regs->rip,regs->rsp,error_code); + + tsk->thread.error_code = error_code; + tsk->thread.trap_no = 13; + force_sig(SIGSEGV, tsk); + return; + } + + /* kernel gp */ + { + const struct exception_table_entry *fixup; + fixup = search_exception_tables(regs->rip); + if (fixup) { + regs->rip = fixup->fixup; + return; + } + if (notify_die(DIE_GPF, "general protection fault", regs, + error_code, 13, SIGSEGV) == NOTIFY_STOP) + return; + die("general protection fault", regs, error_code); + } +} + +static void mem_parity_error(unsigned char reason, struct pt_regs * regs) +{ + printk("Uhhuh. NMI received. Dazed and confused, but trying to continue\n"); + printk("You probably have a hardware problem with your RAM chips\n"); + +#if 0 /* XEN */ + /* Clear and disable the memory parity error line. */ + reason = (reason & 0xf) | 4; + outb(reason, 0x61); +#endif /* XEN */ +} + +static void io_check_error(unsigned char reason, struct pt_regs * regs) +{ + printk("NMI: IOCK error (debug interrupt?)\n"); + show_registers(regs); + +#if 0 /* XEN */ + /* Re-enable the IOCK line, wait for a few seconds */ + reason = (reason & 0xf) | 8; + outb(reason, 0x61); + mdelay(2000); + reason &= ~8; + outb(reason, 0x61); +#endif /* XEN */ +} + +static void unknown_nmi_error(unsigned char reason, struct pt_regs * regs) +{ printk("Uhhuh. NMI received for unknown reason %02x.\n", reason); + printk("Dazed and confused, but trying to continue\n"); + printk("Do you have a strange power saving mode enabled?\n"); +} + +/* Runs on IST stack. This code must keep interrupts off all the time. + Nested NMIs are prevented by the CPU. */ +asmlinkage void default_do_nmi(struct pt_regs *regs) +{ + unsigned char reason = 0; + + /* Only the BSP gets external NMIs from the system. */ + if (!smp_processor_id()) + reason = get_nmi_reason(); + + if (!(reason & 0xc0)) { + if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 0, SIGINT) + == NOTIFY_STOP) + return; +#ifdef CONFIG_X86_LOCAL_APIC + /* + * Ok, so this is none of the documented NMI sources, + * so it must be the NMI watchdog. + */ + if (nmi_watchdog > 0) { + nmi_watchdog_tick(regs,reason); + return; + } +#endif + unknown_nmi_error(reason, regs); + return; + } + if (notify_die(DIE_NMI, "nmi", regs, reason, 0, SIGINT) == NOTIFY_STOP) + return; + + /* AK: following checks seem to be broken on modern chipsets. FIXME */ + + if (reason & 0x80) + mem_parity_error(reason, regs); + if (reason & 0x40) + io_check_error(reason, regs); +} + +asmlinkage void do_int3(struct pt_regs * regs, long error_code) +{ + if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) == NOTIFY_STOP) { + return; + } + do_trap(3, SIGTRAP, "int3", regs, error_code, NULL); + return; +} + +/* Help handler running on IST stack to switch back to user stack + for scheduling or signal handling. The actual stack switch is done in + entry.S */ +asmlinkage struct pt_regs *sync_regs(struct pt_regs *eregs) +{ + struct pt_regs *regs = eregs; + /* Did already sync */ + if (eregs == (struct pt_regs *)eregs->rsp) + ; + /* Exception from user space */ + else if (eregs->cs & 3) + regs = ((struct pt_regs *)current->thread.rsp0) - 1; + /* Exception from kernel and interrupts are enabled. Move to + kernel process stack. */ + else if (eregs->eflags & X86_EFLAGS_IF) + regs = (struct pt_regs *)(eregs->rsp -= sizeof(struct pt_regs)); + if (eregs != regs) + *regs = *eregs; + return regs; +} + +/* runs on IST stack. */ +asmlinkage void do_debug(struct pt_regs * regs, unsigned long error_code) +{ + unsigned long condition; + struct task_struct *tsk = current; + siginfo_t info; + +#ifdef CONFIG_CHECKING + { + /* RED-PEN interaction with debugger - could destroy gs */ + unsigned long gs; + struct x8664_pda *pda = cpu_pda + safe_smp_processor_id(); + rdmsrl(MSR_GS_BASE, gs); + if (gs != (unsigned long)pda) { + wrmsrl(MSR_GS_BASE, pda); + printk("debug handler: wrong gs %lx expected %p\n", gs, pda); + } + } +#endif + + asm("movq %%db6,%0" : "=r" (condition)); + + if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code, + SIGTRAP) == NOTIFY_STOP) + return; + + conditional_sti(regs); + + /* Mask out spurious debug traps due to lazy DR7 setting */ + if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) { + if (!tsk->thread.debugreg7) { + goto clear_dr7; + } + } + + tsk->thread.debugreg6 = condition; + + /* Mask out spurious TF errors due to lazy TF clearing */ + if (condition & DR_STEP) { + /* + * The TF error should be masked out only if the current + * process is not traced and if the TRAP flag has been set + * previously by a tracing process (condition detected by + * the PT_DTRACE flag); remember that the i386 TRAP flag + * can be modified by the process itself in user mode, + * allowing programs to debug themselves without the ptrace() + * interface. + */ + if ((regs->cs & 3) == 0) + goto clear_TF_reenable; + /* + * Was the TF flag set by a debugger? If so, clear it now, + * so that register information is correct. + */ + if (tsk->ptrace & PT_DTRACE) { + regs->eflags &= ~TF_MASK; + tsk->ptrace &= ~PT_DTRACE; + } + } + + /* Ok, finally something we can handle */ + tsk->thread.trap_no = 1; + tsk->thread.error_code = error_code; + info.si_signo = SIGTRAP; + info.si_errno = 0; + info.si_code = TRAP_BRKPT; + if ((regs->cs & 3) == 0) + goto clear_dr7; + + info.si_addr = (void __user *)regs->rip; + force_sig_info(SIGTRAP, &info, tsk); +clear_dr7: + asm volatile("movq %0,%%db7"::"r"(0UL)); + return; + +clear_TF_reenable: + set_tsk_thread_flag(tsk, TIF_SINGLESTEP); + regs->eflags &= ~TF_MASK; +} + +static int kernel_math_error(struct pt_regs *regs, char *str) +{ + const struct exception_table_entry *fixup; + fixup = search_exception_tables(regs->rip); + if (fixup) { + regs->rip = fixup->fixup; + return 1; + } + notify_die(DIE_GPF, str, regs, 0, 16, SIGFPE); + /* Illegal floating point operation in the kernel */ + die(str, regs, 0); + return 0; +} + +/* + * Note that we play around with the 'TS' bit in an attempt to get + * the correct behaviour even in the presence of the asynchronous + * IRQ13 behaviour + */ +asmlinkage void do_coprocessor_error(struct pt_regs *regs) +{ + void __user *rip = (void __user *)(regs->rip); + struct task_struct * task; + siginfo_t info; + unsigned short cwd, swd; + + conditional_sti(regs); + if ((regs->cs & 3) == 0 && + kernel_math_error(regs, "kernel x87 math error")) + return; + + /* + * Save the info for the exception handler and clear the error. + */ + task = current; + save_init_fpu(task); + task->thread.trap_no = 16; + task->thread.error_code = 0; + info.si_signo = SIGFPE; + info.si_errno = 0; + info.si_code = __SI_FAULT; + info.si_addr = rip; + /* + * (~cwd & swd) will mask out exceptions that are not set to unmasked + * status. 0x3f is the exception bits in these regs, 0x200 is the + * C1 reg you need in case of a stack fault, 0x040 is the stack + * fault bit. We should only be taking one exception at a time, + * so if this combination doesn't produce any single exception, + * then we have a bad program that isn't synchronizing its FPU usage + * and it will suffer the consequences since we won't be able to + * fully reproduce the context of the exception + */ + cwd = get_fpu_cwd(task); + swd = get_fpu_swd(task); + switch (((~cwd) & swd & 0x3f) | (swd & 0x240)) { + case 0x000: + default: + break; + case 0x001: /* Invalid Op */ + case 0x041: /* Stack Fault */ + case 0x241: /* Stack Fault | Direction */ + info.si_code = FPE_FLTINV; + break; + case 0x002: /* Denormalize */ + case 0x010: /* Underflow */ + info.si_code = FPE_FLTUND; + break; + case 0x004: /* Zero Divide */ + info.si_code = FPE_FLTDIV; + break; + case 0x008: /* Overflow */ + info.si_code = FPE_FLTOVF; + break; + case 0x020: /* Precision */ + info.si_code = FPE_FLTRES; + break; + } + force_sig_info(SIGFPE, &info, task); +} + +asmlinkage void bad_intr(void) +{ + printk("bad interrupt"); +} + +asmlinkage void do_simd_coprocessor_error(struct pt_regs *regs) +{ + void __user *rip = (void __user *)(regs->rip); + struct task_struct * task; + siginfo_t info; + unsigned short mxcsr; + + conditional_sti(regs); + if ((regs->cs & 3) == 0 && + kernel_math_error(regs, "kernel simd math error")) + return; + + /* + * Save the info for the exception handler and clear the error. + */ + task = current; + save_init_fpu(task); + task->thread.trap_no = 19; + task->thread.error_code = 0; + info.si_signo = SIGFPE; + info.si_errno = 0; + info.si_code = __SI_FAULT; + info.si_addr = rip; + /* + * The SIMD FPU exceptions are handled a little differently, as there + * is only a single status/control register. Thus, to determine which + * unmasked exception was caught we must mask the exception mask bits + * at 0x1f80, and then use these to mask the exception bits at 0x3f. + */ + mxcsr = get_fpu_mxcsr(task); + switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) { + case 0x000: + default: + break; + case 0x001: /* Invalid Op */ + info.si_code = FPE_FLTINV; + break; + case 0x002: /* Denormalize */ + case 0x010: /* Underflow */ + info.si_code = FPE_FLTUND; + break; + case 0x004: /* Zero Divide */ + info.si_code = FPE_FLTDIV; + break; + case 0x008: /* Overflow */ + info.si_code = FPE_FLTOVF; + break; + case 0x020: /* Precision */ + info.si_code = FPE_FLTRES; + break; + } + force_sig_info(SIGFPE, &info, task); +} + +asmlinkage void do_spurious_interrupt_bug(struct pt_regs * regs) +{ +} + +#if 0 +asmlinkage void __attribute__((weak)) smp_thermal_interrupt(void) +{ +} +#endif + +/* + * 'math_state_restore()' saves the current math information in the + * old math state array, and gets the new ones from the current task + * + * Careful.. There are problems with IBM-designed IRQ13 behaviour. + * Don't touch unless you *really* know how it works. + */ +asmlinkage void math_state_restore(void) +{ + struct task_struct *me = current; + /* clts(); */ /* 'clts' is done for us by Xen during virtual trap. */ + + if (!used_math()) + init_fpu(me); + restore_fpu_checking(&me->thread.i387.fxsave); + me->thread_info->status |= TS_USEDFPU; +} + +void do_call_debug(struct pt_regs *regs) +{ + notify_die(DIE_CALL, "debug call", regs, 0, 255, SIGINT); +} + + +/* + * NB. All these are "interrupt gates" (i.e. events_mask is set) because we + * specify <dpl>|4 in the second field. + */ +static trap_info_t trap_table[] = { + { 0, 0|4, (__KERNEL_CS|0x3), (unsigned long)divide_error }, + { 1, 0|4, (__KERNEL_CS|0x3), (unsigned long)debug }, + { 3, 3|4, (__KERNEL_CS|0x3), (unsigned long)int3 }, + { 4, 3|4, (__KERNEL_CS|0x3), (unsigned long)overflow }, + { 5, 3|4, (__KERNEL_CS|0x3), (unsigned long)bounds }, + { 6, 0|4, (__KERNEL_CS|0x3), (unsigned long)invalid_op }, + { 7, 0|4, (__KERNEL_CS|0x3), (unsigned long)device_not_available }, + { 9, 0|4, (__KERNEL_CS|0x3), (unsigned long)coprocessor_segment_overrun}, + { 10, 0|4, (__KERNEL_CS|0x3), (unsigned long)invalid_TSS }, + { 11, 0|4, (__KERNEL_CS|0x3), (unsigned long)segment_not_present }, + { 12, 0|4, (__KERNEL_CS|0x3), (unsigned long)stack_segment }, + { 13, 0|4, (__KERNEL_CS|0x3), (unsigned long)general_protection }, + { 14, 0|4, (__KERNEL_CS|0x3), (unsigned long)page_fault }, + { 15, 0|4, (__KERNEL_CS|0x3), (unsigned long)spurious_interrupt_bug }, + { 16, 0|4, (__KERNEL_CS|0x3), (unsigned long)coprocessor_error }, + { 17, 0|4, (__KERNEL_CS|0x3), (unsigned long)alignment_check }, +#ifdef CONFIG_X86_MCE + { 18, 0|4, (__KERNEL_CS|0x3), (unsigned long)machine_check }, +#endif + { 19, 0|4, (__KERNEL_CS|0x3), (unsigned long)simd_coprocessor_error }, +#ifdef CONFIG_IA32_EMULATION + { IA32_SYSCALL_VECTOR, 3|4, (__KERNEL_CS|0x3), (unsigned long)ia32_syscall}, +#endif + { 0, 0, 0, 0 } +}; + +void __init trap_init(void) +{ + int ret; + + ret = HYPERVISOR_set_trap_table(trap_table); + + if (ret) + printk("HYPERVISOR_set_trap_table faild: error %d\n", + ret); + +#ifdef CONFIG_IA32_EMULATION + set_system_gate(IA32_SYSCALL_VECTOR, ia32_syscall); +#endif + + /* + * Should be a barrier for any external CPU state. + */ + cpu_init(); +} + +void smp_trap_init(trap_info_t *trap_ctxt) +{ + trap_info_t *t = trap_table; + int i; + + for (i = 0; i < 256; i++) { + trap_ctxt[i].vector = i; + trap_ctxt[i].cs = FLAT_KERNEL_CS; + } + + for (t = trap_table; t->address; t++) { + trap_ctxt[t->vector].flags = t->flags; + trap_ctxt[t->vector].cs = t->cs; + trap_ctxt[t->vector].address = t->address; + } +} + + +/* Actual parsing is done early in setup.c. */ +static int __init oops_dummy(char *s) +{ + panic_on_oops = 1; + return -1; +} +__setup("oops=", oops_dummy); + +static int __init kstack_setup(char *s) +{ + kstack_depth_to_print = simple_strtoul(s,NULL,0); + return 0; +} +__setup("kstack=", kstack_setup); + diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/vsyscall-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/vsyscall-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,241 @@ +/* + * linux/arch/x86_64/kernel/vsyscall.c + * + * Copyright (C) 2001 Andrea Arcangeli <andrea@xxxxxxx> SuSE + * Copyright 2003 Andi Kleen, SuSE Labs. + * + * Thanks to hpa@xxxxxxxxxxxxx for some useful hint. + * Special thanks to Ingo Molnar for his early experience with + * a different vsyscall implementation for Linux/IA32 and for the name. + * + * vsyscall 1 is located at -10Mbyte, vsyscall 2 is located + * at virtual address -10Mbyte+1024bytes etc... There are at max 4 + * vsyscalls. One vsyscall can reserve more than 1 slot to avoid + * jumping out of line if necessary. We cannot add more with this + * mechanism because older kernels won't return -ENOSYS. + * If we want more than four we need a vDSO. + * + * Note: the concept clashes with user mode linux. If you use UML and + * want per guest time just set the kernel.vsyscall64 sysctl to 0. + */ + +#include <linux/time.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/timer.h> +#include <linux/seqlock.h> +#include <linux/jiffies.h> +#include <linux/sysctl.h> + +#include <asm/vsyscall.h> +#include <asm/pgtable.h> +#include <asm/page.h> +#include <asm/fixmap.h> +#include <asm/errno.h> +#include <asm/io.h> + +#define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr))) +#define force_inline __attribute__((always_inline)) inline + +int __sysctl_vsyscall __section_sysctl_vsyscall = 1; +seqlock_t __xtime_lock __section_xtime_lock = SEQLOCK_UNLOCKED; + +#include <asm/unistd.h> + +static force_inline void timeval_normalize(struct timeval * tv) +{ + time_t __sec; + + __sec = tv->tv_usec / 1000000; + if (__sec) { + tv->tv_usec %= 1000000; + tv->tv_sec += __sec; + } +} + +static force_inline void do_vgettimeofday(struct timeval * tv) +{ + long sequence, t; + unsigned long sec, usec; + + do { + sequence = read_seqbegin(&__xtime_lock); + + sec = __xtime.tv_sec; + usec = (__xtime.tv_nsec / 1000) + + (__jiffies - __wall_jiffies) * (1000000 / HZ); + + if (__vxtime.mode != VXTIME_HPET) { + sync_core(); + rdtscll(t); + if (t < __vxtime.last_tsc) + t = __vxtime.last_tsc; + usec += ((t - __vxtime.last_tsc) * + __vxtime.tsc_quot) >> 32; + /* See comment in x86_64 do_gettimeofday. */ + } else { + usec += ((readl((void *)fix_to_virt(VSYSCALL_HPET) + 0xf0) - + __vxtime.last) * __vxtime.quot) >> 32; + } + } while (read_seqretry(&__xtime_lock, sequence)); + + tv->tv_sec = sec + usec / 1000000; + tv->tv_usec = usec % 1000000; +} + +/* RED-PEN may want to readd seq locking, but then the variable should be write-once. */ +static force_inline void do_get_tz(struct timezone * tz) +{ + *tz = __sys_tz; +} + +static force_inline int gettimeofday(struct timeval *tv, struct timezone *tz) +{ + int ret; + asm volatile("vsysc2: syscall" + : "=a" (ret) + : "0" (__NR_gettimeofday),"D" (tv),"S" (tz) : __syscall_clobber ); + return ret; +} + +static force_inline long time_syscall(long *t) +{ + long secs; + asm volatile("vsysc1: syscall" + : "=a" (secs) + : "0" (__NR_time),"D" (t) : __syscall_clobber); + return secs; +} + +static int __vsyscall(0) vgettimeofday(struct timeval * tv, struct timezone * tz) +{ + if (unlikely(!__sysctl_vsyscall)) + return gettimeofday(tv,tz); + if (tv) + do_vgettimeofday(tv); + if (tz) + do_get_tz(tz); + return 0; +} + +/* This will break when the xtime seconds get inaccurate, but that is + * unlikely */ +static time_t __vsyscall(1) vtime(time_t *t) +{ + if (unlikely(!__sysctl_vsyscall)) + return time_syscall(t); + else if (t) + *t = __xtime.tv_sec; + return __xtime.tv_sec; +} + +static long __vsyscall(2) venosys_0(void) +{ + return -ENOSYS; +} + +static long __vsyscall(3) venosys_1(void) +{ + return -ENOSYS; +} + +#ifdef CONFIG_SYSCTL + +#define SYSCALL 0x050f +#define NOP2 0x9090 + +/* + * NOP out syscall in vsyscall page when not needed. + */ +static int vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + extern u16 vsysc1, vsysc2; + u16 *map1, *map2; + int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + if (!write) + return ret; + /* gcc has some trouble with __va(__pa()), so just do it this + way. */ + map1 = ioremap(__pa_symbol(&vsysc1), 2); + if (!map1) + return -ENOMEM; + map2 = ioremap(__pa_symbol(&vsysc2), 2); + if (!map2) { + ret = -ENOMEM; + goto out; + } + if (!sysctl_vsyscall) { + *map1 = SYSCALL; + *map2 = SYSCALL; + } else { + *map1 = NOP2; + *map2 = NOP2; + } + iounmap(map2); +out: + iounmap(map1); + return ret; +} + +static int vsyscall_sysctl_nostrat(ctl_table *t, int __user *name, int nlen, + void __user *oldval, size_t __user *oldlenp, + void __user *newval, size_t newlen, + void **context) +{ + return -ENOSYS; +} + +static ctl_table kernel_table2[] = { + { .ctl_name = 99, .procname = "vsyscall64", + .data = &sysctl_vsyscall, .maxlen = sizeof(int), .mode = 0644, + .strategy = vsyscall_sysctl_nostrat, + .proc_handler = vsyscall_sysctl_change }, + { 0, } +}; + +static ctl_table kernel_root_table2[] = { + { .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, + .child = kernel_table2 }, + { 0 }, +}; + +#endif + +static void __init map_vsyscall(void) +{ + extern char __vsyscall_0; + unsigned long physaddr_page0 = __pa_symbol(&__vsyscall_0); + + __set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_page0, PAGE_KERNEL_VSYSCALL); +} + +#ifdef CONFIG_XEN +static void __init map_vsyscall_user(void) +{ + extern void __set_fixmap_user(enum fixed_addresses, unsigned long, pgprot_t); + extern char __vsyscall_0; + unsigned long physaddr_page0 = __pa_symbol(&__vsyscall_0); + + __set_fixmap_user(VSYSCALL_FIRST_PAGE, physaddr_page0, PAGE_KERNEL_VSYSCALL); +} +#endif + +static int __init vsyscall_init(void) +{ + BUG_ON(((unsigned long) &vgettimeofday != + VSYSCALL_ADDR(__NR_vgettimeofday))); + BUG_ON((unsigned long) &vtime != VSYSCALL_ADDR(__NR_vtime)); + BUG_ON((VSYSCALL_ADDR(0) != __fix_to_virt(VSYSCALL_FIRST_PAGE))); + map_vsyscall(); +#ifdef CONFIG_XEN + map_vsyscall_user(); + sysctl_vsyscall = 0; /* disable vgettimeofay() */ +#endif +#ifdef CONFIG_SYSCTL + register_sysctl_table(kernel_root_table2, 0); +#endif + return 0; +} + +__initcall(vsyscall_init); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/x8664_ksyms-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/x8664_ksyms-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,208 @@ +#include <linux/config.h> +#include <linux/module.h> +#include <linux/smp.h> +#include <linux/user.h> +#include <linux/sched.h> +#include <linux/in6.h> +#include <linux/interrupt.h> +#include <linux/smp_lock.h> +#include <linux/pm.h> +#include <linux/pci.h> +#include <linux/apm_bios.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/syscalls.h> +#include <linux/tty.h> +#include <linux/ioctl32.h> + +#include <asm/semaphore.h> +#include <asm/processor.h> +#include <asm/i387.h> +#include <asm/uaccess.h> +#include <asm/checksum.h> +#include <asm/io.h> +#include <asm/delay.h> +#include <asm/irq.h> +#include <asm/mmx.h> +#include <asm/desc.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/nmi.h> +#include <asm/kdebug.h> +#include <asm/unistd.h> +#include <asm/tlbflush.h> +#include <asm/kdebug.h> + +extern spinlock_t rtc_lock; + +#ifdef CONFIG_SMP +extern void __write_lock_failed(rwlock_t *rw); +extern void __read_lock_failed(rwlock_t *rw); +#endif + +#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_HD) || defined(CONFIG_BLK_DEV_IDE_MODULE) || defined(CONFIG_BLK_DEV_HD_MODULE) +extern struct drive_info_struct drive_info; +EXPORT_SYMBOL(drive_info); +#endif + +extern unsigned long get_cmos_time(void); + +/* platform dependent support */ +EXPORT_SYMBOL(boot_cpu_data); +//EXPORT_SYMBOL(dump_fpu); +EXPORT_SYMBOL(__ioremap); +EXPORT_SYMBOL(ioremap_nocache); +EXPORT_SYMBOL(iounmap); +EXPORT_SYMBOL(enable_irq); +EXPORT_SYMBOL(disable_irq); +EXPORT_SYMBOL(disable_irq_nosync); +EXPORT_SYMBOL(probe_irq_mask); +EXPORT_SYMBOL(kernel_thread); +EXPORT_SYMBOL(pm_idle); +EXPORT_SYMBOL(pm_power_off); +EXPORT_SYMBOL(get_cmos_time); + +EXPORT_SYMBOL(__down_failed); +EXPORT_SYMBOL(__down_failed_interruptible); +EXPORT_SYMBOL(__down_failed_trylock); +EXPORT_SYMBOL(__up_wakeup); +/* Networking helper routines. */ +EXPORT_SYMBOL(csum_partial_copy_nocheck); +EXPORT_SYMBOL(ip_compute_csum); +/* Delay loops */ +EXPORT_SYMBOL(__udelay); +EXPORT_SYMBOL(__ndelay); +EXPORT_SYMBOL(__delay); +EXPORT_SYMBOL(__const_udelay); + +EXPORT_SYMBOL(__get_user_1); +EXPORT_SYMBOL(__get_user_2); +EXPORT_SYMBOL(__get_user_4); +EXPORT_SYMBOL(__get_user_8); +EXPORT_SYMBOL(__put_user_1); +EXPORT_SYMBOL(__put_user_2); +EXPORT_SYMBOL(__put_user_4); +EXPORT_SYMBOL(__put_user_8); + +EXPORT_SYMBOL(strpbrk); +EXPORT_SYMBOL(strstr); + +EXPORT_SYMBOL(strncpy_from_user); +EXPORT_SYMBOL(__strncpy_from_user); +EXPORT_SYMBOL(clear_user); +EXPORT_SYMBOL(__clear_user); +EXPORT_SYMBOL(copy_user_generic); +EXPORT_SYMBOL(copy_from_user); +EXPORT_SYMBOL(copy_to_user); +EXPORT_SYMBOL(copy_in_user); +EXPORT_SYMBOL(strnlen_user); + +#ifdef CONFIG_PCI +EXPORT_SYMBOL(pci_alloc_consistent); +EXPORT_SYMBOL(pci_free_consistent); +#endif + +#ifdef CONFIG_PCI +EXPORT_SYMBOL(pci_mem_start); +#endif + +EXPORT_SYMBOL(copy_page); +EXPORT_SYMBOL(clear_page); + +EXPORT_SYMBOL(cpu_pda); +#ifdef CONFIG_SMP +EXPORT_SYMBOL(__write_lock_failed); +EXPORT_SYMBOL(__read_lock_failed); + +EXPORT_SYMBOL(synchronize_irq); +EXPORT_SYMBOL(smp_call_function); +#endif + +#ifdef CONFIG_VT +EXPORT_SYMBOL(screen_info); +#endif + +EXPORT_SYMBOL(get_wchan); + +EXPORT_SYMBOL(rtc_lock); + +#ifdef CONFIG_X86_LOCAL_APIC +EXPORT_SYMBOL_GPL(set_nmi_callback); +EXPORT_SYMBOL_GPL(unset_nmi_callback); +#endif + +/* Export string functions. We normally rely on gcc builtin for most of these, + but gcc sometimes decides not to inline them. */ +#undef memcpy +#undef memset +#undef memmove +#undef memchr +#undef strlen +#undef strncmp +#undef strncpy +#undef strchr + +extern void * memset(void *,int,__kernel_size_t); +extern size_t strlen(const char *); +extern void * memmove(void * dest,const void *src,size_t count); +extern void *memchr(const void *s, int c, size_t n); +extern void * memcpy(void *,const void *,__kernel_size_t); +extern void * __memcpy(void *,const void *,__kernel_size_t); + +EXPORT_SYMBOL(memset); +EXPORT_SYMBOL(strlen); +EXPORT_SYMBOL(memmove); +EXPORT_SYMBOL(strncmp); +EXPORT_SYMBOL(strncpy); +EXPORT_SYMBOL(strchr); +EXPORT_SYMBOL(strncat); +EXPORT_SYMBOL(memchr); +EXPORT_SYMBOL(strrchr); +EXPORT_SYMBOL(strnlen); +EXPORT_SYMBOL(memscan); +EXPORT_SYMBOL(memcpy); +EXPORT_SYMBOL(__memcpy); + +#ifdef CONFIG_RWSEM_XCHGADD_ALGORITHM +/* prototypes are wrong, these are assembly with custom calling functions */ +extern void rwsem_down_read_failed_thunk(void); +extern void rwsem_wake_thunk(void); +extern void rwsem_downgrade_thunk(void); +extern void rwsem_down_write_failed_thunk(void); +EXPORT_SYMBOL(rwsem_down_read_failed_thunk); +EXPORT_SYMBOL(rwsem_wake_thunk); +EXPORT_SYMBOL(rwsem_downgrade_thunk); +EXPORT_SYMBOL(rwsem_down_write_failed_thunk); +#endif + +EXPORT_SYMBOL(empty_zero_page); + +#ifdef CONFIG_HAVE_DEC_LOCK +EXPORT_SYMBOL(_atomic_dec_and_lock); +#endif + +EXPORT_SYMBOL(die_chain); +EXPORT_SYMBOL(register_die_notifier); + +#ifdef CONFIG_SMP +EXPORT_SYMBOL(cpu_sibling_map); +EXPORT_SYMBOL(smp_num_siblings); +#endif + +extern void do_softirq_thunk(void); +EXPORT_SYMBOL(do_softirq_thunk); + +#ifdef CONFIG_BUG +EXPORT_SYMBOL(out_of_line_bug); +#endif + +EXPORT_SYMBOL(init_level4_pgt); + +extern unsigned long __supported_pte_mask; +EXPORT_SYMBOL(__supported_pte_mask); + +#ifdef CONFIG_SMP +EXPORT_SYMBOL(flush_tlb_page); +#endif + +EXPORT_SYMBOL(cpu_khz); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/kernel/xen_entry.S --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/xen_entry.S Mon Jan 30 17:18:27 2006 @@ -0,0 +1,41 @@ +/* + * Copied from arch/xen/i386/kernel/entry.S + */ +/* Offsets into shared_info_t. */ +#define evtchn_upcall_pending 0 +#define evtchn_upcall_mask 1 + +#define sizeof_vcpu_shift 6 + +#ifdef CONFIG_SMP +//#define preempt_disable(reg) incl threadinfo_preempt_count(reg) +//#define preempt_enable(reg) decl threadinfo_preempt_count(reg) +#define preempt_disable(reg) +#define preempt_enable(reg) +#define XEN_GET_VCPU_INFO(reg) preempt_disable(%rbp) ; \ + movq %gs:pda_cpunumber,reg ; \ + shl $32, reg ; \ + shr $32-sizeof_vcpu_shift,reg ; \ + addq HYPERVISOR_shared_info,reg +#define XEN_PUT_VCPU_INFO(reg) preempt_enable(%rbp) ; \ +#define XEN_PUT_VCPU_INFO_fixup .byte 0xff,0xff,0xff +#else +#define XEN_GET_VCPU_INFO(reg) movq HYPERVISOR_shared_info,reg +#define XEN_PUT_VCPU_INFO(reg) +#define XEN_PUT_VCPU_INFO_fixup +#endif + +#define XEN_LOCKED_BLOCK_EVENTS(reg) movb $1,evtchn_upcall_mask(reg) +#define XEN_LOCKED_UNBLOCK_EVENTS(reg) movb $0,evtchn_upcall_mask(reg) +#define XEN_BLOCK_EVENTS(reg) XEN_GET_VCPU_INFO(reg) ; \ + XEN_LOCKED_BLOCK_EVENTS(reg) ; \ + XEN_PUT_VCPU_INFO(reg) +#define XEN_UNBLOCK_EVENTS(reg) XEN_GET_VCPU_INFO(reg) ; \ + XEN_LOCKED_UNBLOCK_EVENTS(reg) ; \ + XEN_PUT_VCPU_INFO(reg) +#define XEN_TEST_PENDING(reg) testb $0xFF,evtchn_upcall_pending(reg) + +EVENT_MASK = (CS+4) +VGCF_IN_SYSCALL = (1<<8) + + diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/mm/Makefile --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/mm/Makefile Mon Jan 30 17:18:27 2006 @@ -0,0 +1,21 @@ +# +# Makefile for the linux x86_64-specific parts of the memory manager. +# + +obj-y := init.o fault.o ioremap.o extable.o pageattr.o +obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o +obj-$(CONFIG_DISCONTIGMEM) += numa.o +obj-$(CONFIG_K8_NUMA) += k8topology.o +obj-$(CONFIG_ACPI_NUMA) += srat.o + +hugetlbpage-y = ../../i386/mm/hugetlbpage.o + +ifdef CONFIG_XEN +include $(srctree)/scripts/Makefile.xen + +ioremap-y += ../../i386/mm/ioremap-xen.o +hypervisor-y += ../../i386/mm/hypervisor.o +obj-y += hypervisor.o + +obj-y := $(call cherrypickxen, $(obj-y)) +endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/mm/fault-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/mm/fault-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,596 @@ +/* + * linux/arch/x86-64/mm/fault.c + * + * Copyright (C) 1995 Linus Torvalds + * Copyright (C) 2001,2002 Andi Kleen, SuSE Labs. + */ + +#include <linux/config.h> +#include <linux/signal.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/ptrace.h> +#include <linux/mman.h> +#include <linux/mm.h> +#include <linux/smp.h> +#include <linux/smp_lock.h> +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/tty.h> +#include <linux/vt_kern.h> /* For unblank_screen() */ +#include <linux/compiler.h> +#include <linux/module.h> +#include <linux/percpu.h> +#include <linux/kprobes.h> + +#include <asm/system.h> +#include <asm/uaccess.h> +#include <asm/pgalloc.h> +#include <asm/smp.h> +#include <asm/tlbflush.h> +#include <asm/proto.h> +#include <asm/kdebug.h> +#include <asm-generic/sections.h> +#include <asm/kdebug.h> + +DEFINE_PER_CPU(pgd_t *, cur_pgd); + +void bust_spinlocks(int yes) +{ + int loglevel_save = console_loglevel; + if (yes) { + oops_in_progress = 1; + } else { +#ifdef CONFIG_VT + unblank_screen(); +#endif + oops_in_progress = 0; + /* + * OK, the message is on the console. Now we call printk() + * without oops_in_progress set so that printk will give klogd + * a poke. Hold onto your hats... + */ + console_loglevel = 15; /* NMI oopser may have shut the console up */ + printk(" "); + console_loglevel = loglevel_save; + } +} + +/* Sometimes the CPU reports invalid exceptions on prefetch. + Check that here and ignore. + Opcode checker based on code by Richard Brunner */ +static noinline int is_prefetch(struct pt_regs *regs, unsigned long addr, + unsigned long error_code) +{ + unsigned char *instr; + int scan_more = 1; + int prefetch = 0; + unsigned char *max_instr; + + /* If it was a exec fault ignore */ + if (error_code & (1<<4)) + return 0; + + instr = (unsigned char *)convert_rip_to_linear(current, regs); + max_instr = instr + 15; + + if ((regs->cs & 3) != 0 && instr >= (unsigned char *)TASK_SIZE) + return 0; + + while (scan_more && instr < max_instr) { + unsigned char opcode; + unsigned char instr_hi; + unsigned char instr_lo; + + if (__get_user(opcode, instr)) + break; + + instr_hi = opcode & 0xf0; + instr_lo = opcode & 0x0f; + instr++; + + switch (instr_hi) { + case 0x20: + case 0x30: + /* Values 0x26,0x2E,0x36,0x3E are valid x86 + prefixes. In long mode, the CPU will signal + invalid opcode if some of these prefixes are + present so we will never get here anyway */ + scan_more = ((instr_lo & 7) == 0x6); + break; + + case 0x40: + /* In AMD64 long mode, 0x40 to 0x4F are valid REX prefixes + Need to figure out under what instruction mode the + instruction was issued ... */ + /* Could check the LDT for lm, but for now it's good + enough to assume that long mode only uses well known + segments or kernel. */ + scan_more = ((regs->cs & 3) == 0) || (regs->cs == __USER_CS); + break; + + case 0x60: + /* 0x64 thru 0x67 are valid prefixes in all modes. */ + scan_more = (instr_lo & 0xC) == 0x4; + break; + case 0xF0: + /* 0xF0, 0xF2, and 0xF3 are valid prefixes in all modes. */ + scan_more = !instr_lo || (instr_lo>>1) == 1; + break; + case 0x00: + /* Prefetch instruction is 0x0F0D or 0x0F18 */ + scan_more = 0; + if (__get_user(opcode, instr)) + break; + prefetch = (instr_lo == 0xF) && + (opcode == 0x0D || opcode == 0x18); + break; + default: + scan_more = 0; + break; + } + } + return prefetch; +} + +static int bad_address(void *p) +{ + unsigned long dummy; + return __get_user(dummy, (unsigned long *)p); +} + +void dump_pagetable(unsigned long address) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + preempt_disable(); + pgd = (pgd_t *)per_cpu(cur_pgd, smp_processor_id()); + preempt_enable(); + pgd += pgd_index(address); + printk("PGD %lx ", pgd_val(*pgd)); + if (bad_address(pgd)) goto bad; + if (!pgd_present(*pgd)) goto ret; + + pud = __pud_offset_k((pud_t *)pgd_page(*pgd), address); + if (bad_address(pud)) goto bad; + printk("PUD %lx ", pud_val(*pud)); + if (!pud_present(*pud)) goto ret; + + pmd = pmd_offset(pud, address); + if (bad_address(pmd)) goto bad; + printk("PMD %lx ", pmd_val(*pmd)); + if (!pmd_present(*pmd)) goto ret; + + pte = pte_offset_kernel(pmd, address); + if (bad_address(pte)) goto bad; + printk("PTE %lx", pte_val(*pte)); +ret: + printk("\n"); + return; +bad: + printk("BAD\n"); +} + +static const char errata93_warning[] = +KERN_ERR "******* Your BIOS seems to not contain a fix for K8 errata #93\n" +KERN_ERR "******* Working around it, but it may cause SEGVs or burn power.\n" +KERN_ERR "******* Please consider a BIOS update.\n" +KERN_ERR "******* Disabling USB legacy in the BIOS may also help.\n"; + +/* Workaround for K8 erratum #93 & buggy BIOS. + BIOS SMM functions are required to use a specific workaround + to avoid corruption of the 64bit RIP register on C stepping K8. + A lot of BIOS that didn't get tested properly miss this. + The OS sees this as a page fault with the upper 32bits of RIP cleared. + Try to work around it here. + Note we only handle faults in kernel here. */ + +static int is_errata93(struct pt_regs *regs, unsigned long address) +{ + static int warned; + if (address != regs->rip) + return 0; + if ((address >> 32) != 0) + return 0; + address |= 0xffffffffUL << 32; + if ((address >= (u64)_stext && address <= (u64)_etext) || + (address >= MODULES_VADDR && address <= MODULES_END)) { + if (!warned) { + printk(errata93_warning); + warned = 1; + } + regs->rip = address; + return 1; + } + return 0; +} + +int unhandled_signal(struct task_struct *tsk, int sig) +{ + if (tsk->pid == 1) + return 1; + /* Warn for strace, but not for gdb */ + if (!test_ti_thread_flag(tsk->thread_info, TIF_SYSCALL_TRACE) && + (tsk->ptrace & PT_PTRACED)) + return 0; + return (tsk->sighand->action[sig-1].sa.sa_handler == SIG_IGN) || + (tsk->sighand->action[sig-1].sa.sa_handler == SIG_DFL); +} + +static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs, + unsigned long error_code) +{ + oops_begin(); + printk(KERN_ALERT "%s: Corrupted page table at address %lx\n", + current->comm, address); + dump_pagetable(address); + __die("Bad pagetable", regs, error_code); + oops_end(); + do_exit(SIGKILL); +} + +/* + * Handle a fault on the vmalloc or module mapping area + * + * This assumes no large pages in there. + */ +static int vmalloc_fault(unsigned long address) +{ + pgd_t *pgd, *pgd_ref; + pud_t *pud, *pud_ref; + pmd_t *pmd, *pmd_ref; + pte_t *pte, *pte_ref; + + /* Copy kernel mappings over when needed. This can also + happen within a race in page table update. In the later + case just flush. */ + + /* On Xen the line below does not always work. Needs investigating! */ + /*pgd = pgd_offset(current->mm ?: &init_mm, address);*/ + preempt_disable(); + pgd = (pgd_t *)per_cpu(cur_pgd, smp_processor_id()); + preempt_enable(); + pgd += pgd_index(address); + pgd_ref = pgd_offset_k(address); + if (pgd_none(*pgd_ref)) + return -1; + if (pgd_none(*pgd)) + set_pgd(pgd, *pgd_ref); + + /* Below here mismatches are bugs because these lower tables + are shared */ + + pud = pud_offset(pgd, address); + pud_ref = pud_offset(pgd_ref, address); + if (pud_none(*pud_ref)) + return -1; + if (pud_none(*pud) || pud_page(*pud) != pud_page(*pud_ref)) + BUG(); + pmd = pmd_offset(pud, address); + pmd_ref = pmd_offset(pud_ref, address); + if (pmd_none(*pmd_ref)) + return -1; + if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref)) + BUG(); + pte_ref = pte_offset_kernel(pmd_ref, address); + if (!pte_present(*pte_ref)) + return -1; + pte = pte_offset_kernel(pmd, address); + /* Don't use pte_page here, because the mappings can point + outside mem_map, and the NUMA hash lookup cannot handle + that. */ + if (!pte_present(*pte) || pte_pfn(*pte) != pte_pfn(*pte_ref)) + BUG(); + __flush_tlb_all(); + return 0; +} + +int page_fault_trace = 0; +int exception_trace = 1; + + +#define MEM_VERBOSE 1 + +#ifdef MEM_VERBOSE +#define MEM_LOG(_f, _a...) \ + printk("fault.c:[%d]-> " _f "\n", \ + __LINE__ , ## _a ) +#else +#define MEM_LOG(_f, _a...) ((void)0) +#endif + +/* + * This routine handles page faults. It determines the address, + * and the problem, and then passes it off to one of the appropriate + * routines. + * + * error_code: + * bit 0 == 0 means no page found, 1 means protection fault + * bit 1 == 0 means read, 1 means write + * bit 2 == 0 means kernel, 1 means user-mode + * bit 3 == 1 means fault was an instruction fetch + */ +asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code) +{ + struct task_struct *tsk; + struct mm_struct *mm; + struct vm_area_struct * vma; + unsigned long address; + const struct exception_table_entry *fixup; + int write; + siginfo_t info; + + if (!user_mode(regs)) + error_code &= ~4; /* means kernel */ + +#ifdef CONFIG_CHECKING + { + unsigned long gs; + struct x8664_pda *pda = cpu_pda + stack_smp_processor_id(); + rdmsrl(MSR_GS_BASE, gs); + if (gs != (unsigned long)pda) { + wrmsrl(MSR_GS_BASE, pda); + printk("page_fault: wrong gs %lx expected %p\n", gs, pda); + } + } +#endif + + /* get the address */ + address = HYPERVISOR_shared_info->vcpu_info[ + smp_processor_id()].arch.cr2; + + if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14, + SIGSEGV) == NOTIFY_STOP) + return; + + if (likely(regs->eflags & X86_EFLAGS_IF)) + local_irq_enable(); + + if (unlikely(page_fault_trace)) + printk("pagefault rip:%lx rsp:%lx cs:%lu ss:%lu address %lx error %lx\n", + regs->rip,regs->rsp,regs->cs,regs->ss,address,error_code); + + tsk = current; + mm = tsk->mm; + info.si_code = SEGV_MAPERR; + + + /* + * We fault-in kernel-space virtual memory on-demand. The + * 'reference' page table is init_mm.pgd. + * + * NOTE! We MUST NOT take any locks for this case. We may + * be in an interrupt or a critical region, and should + * only copy the information from the master page table, + * nothing more. + * + * This verifies that the fault happens in kernel space + * (error_code & 4) == 0, and that the fault was not a + * protection error (error_code & 1) == 0. + */ + if (unlikely(address >= TASK_SIZE)) { + if (!(error_code & 5) && + ((address >= VMALLOC_START && address < VMALLOC_END) || + (address >= MODULES_VADDR && address < MODULES_END))) { + if (vmalloc_fault(address) < 0) + goto bad_area_nosemaphore; + return; + } + /* + * Don't take the mm semaphore here. If we fixup a prefetch + * fault we could otherwise deadlock. + */ + goto bad_area_nosemaphore; + } + + if (unlikely(error_code & (1 << 3))) + pgtable_bad(address, regs, error_code); + + /* + * If we're in an interrupt or have no user + * context, we must not take the fault.. + */ + if (unlikely(in_atomic() || !mm)) + goto bad_area_nosemaphore; + + again: + /* When running in the kernel we expect faults to occur only to + * addresses in user space. All other faults represent errors in the + * kernel and should generate an OOPS. Unfortunatly, in the case of an + * erroneous fault occuring in a code path which already holds mmap_sem + * we will deadlock attempting to validate the fault against the + * address space. Luckily the kernel only validly references user + * space from well defined areas of code, which are listed in the + * exceptions table. + * + * As the vast majority of faults will be valid we will only perform + * the source reference check when there is a possibilty of a deadlock. + * Attempt to lock the address space, if we cannot we then validate the + * source. If this is invalid we can skip the address space check, + * thus avoiding the deadlock. + */ + if (!down_read_trylock(&mm->mmap_sem)) { + if ((error_code & 4) == 0 && + !search_exception_tables(regs->rip)) + goto bad_area_nosemaphore; + down_read(&mm->mmap_sem); + } + + vma = find_vma(mm, address); + if (!vma) + goto bad_area; + if (likely(vma->vm_start <= address)) + goto good_area; + if (!(vma->vm_flags & VM_GROWSDOWN)) + goto bad_area; + if (error_code & 4) { + // XXX: align red zone size with ABI + if (address + 128 < regs->rsp) + goto bad_area; + } + if (expand_stack(vma, address)) + goto bad_area; +/* + * Ok, we have a good vm_area for this memory access, so + * we can handle it.. + */ +good_area: + info.si_code = SEGV_ACCERR; + write = 0; + switch (error_code & 3) { + default: /* 3: write, present */ + /* fall through */ + case 2: /* write, not present */ + if (!(vma->vm_flags & VM_WRITE)) + goto bad_area; + write++; + break; + case 1: /* read, present */ + goto bad_area; + case 0: /* read, not present */ + if (!(vma->vm_flags & (VM_READ | VM_EXEC))) + goto bad_area; + } + + /* + * If for any reason at all we couldn't handle the fault, + * make sure we exit gracefully rather than endlessly redo + * the fault. + */ + switch (handle_mm_fault(mm, vma, address, write)) { + case 1: + tsk->min_flt++; + break; + case 2: + tsk->maj_flt++; + break; + case 0: + goto do_sigbus; + default: + goto out_of_memory; + } + + up_read(&mm->mmap_sem); + return; + +/* + * Something tried to access memory that isn't in our memory map.. + * Fix it, but check if it's kernel or user first.. + */ +bad_area: + up_read(&mm->mmap_sem); + +bad_area_nosemaphore: + /* User mode accesses just cause a SIGSEGV */ + if (error_code & 4) { + if (is_prefetch(regs, address, error_code)) + return; + + /* Work around K8 erratum #100 K8 in compat mode + occasionally jumps to illegal addresses >4GB. We + catch this here in the page fault handler because + these addresses are not reachable. Just detect this + case and return. Any code segment in LDT is + compatibility mode. */ + if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) && + (address >> 32)) + return; + + if (exception_trace && unhandled_signal(tsk, SIGSEGV)) { + printk( + "%s%s[%d]: segfault at %016lx rip %016lx rsp %016lx error %lx\n", + tsk->pid > 1 ? KERN_INFO : KERN_EMERG, + tsk->comm, tsk->pid, address, regs->rip, + regs->rsp, error_code); + } + + tsk->thread.cr2 = address; + /* Kernel addresses are always protection faults */ + tsk->thread.error_code = error_code | (address >= TASK_SIZE); + tsk->thread.trap_no = 14; + info.si_signo = SIGSEGV; + info.si_errno = 0; + /* info.si_code has been set above */ + info.si_addr = (void __user *)address; + force_sig_info(SIGSEGV, &info, tsk); + return; + } + +no_context: + + /* Are we prepared to handle this kernel fault? */ + fixup = search_exception_tables(regs->rip); + if (fixup) { + regs->rip = fixup->fixup; + return; + } + + /* + * Hall of shame of CPU/BIOS bugs. + */ + + if (is_prefetch(regs, address, error_code)) + return; + + if (is_errata93(regs, address)) + return; + +/* + * Oops. The kernel tried to access some bad page. We'll have to + * terminate things with extreme prejudice. + */ + + oops_begin(); + + if (address < PAGE_SIZE) + printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference"); + else + printk(KERN_ALERT "Unable to handle kernel paging request"); + printk(" at %016lx RIP: \n" KERN_ALERT,address); + printk_address(regs->rip); + printk("\n"); + dump_pagetable(address); + __die("Oops", regs, error_code); + /* Executive summary in case the body of the oops scrolled away */ + printk(KERN_EMERG "CR2: %016lx\n", address); + oops_end(); + do_exit(SIGKILL); + +/* + * We ran out of memory, or some other thing happened to us that made + * us unable to handle the page fault gracefully. + */ +out_of_memory: + up_read(&mm->mmap_sem); + if (current->pid == 1) { + yield(); + goto again; + } + printk("VM: killing process %s\n", tsk->comm); + if (error_code & 4) + do_exit(SIGKILL); + goto no_context; + +do_sigbus: + up_read(&mm->mmap_sem); + + /* Kernel mode? Handle exceptions or die */ + if (!(error_code & 4)) + goto no_context; + + tsk->thread.cr2 = address; + tsk->thread.error_code = error_code; + tsk->thread.trap_no = 14; + info.si_signo = SIGBUS; + info.si_errno = 0; + info.si_code = BUS_ADRERR; + info.si_addr = (void __user *)address; + force_sig_info(SIGBUS, &info, tsk); + return; +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/mm/init-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/mm/init-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,964 @@ +/* + * linux/arch/x86_64/mm/init.c + * + * Copyright (C) 1995 Linus Torvalds + * Copyright (C) 2000 Pavel Machek <pavel@xxxxxxx> + * Copyright (C) 2002,2003 Andi Kleen <ak@xxxxxxx> + * + * Jun Nakajima <jun.nakajima@xxxxxxxxx> + * Modified for Xen. + */ + +#include <linux/config.h> +#include <linux/signal.h> +#include <linux/sched.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/ptrace.h> +#include <linux/mman.h> +#include <linux/mm.h> +#include <linux/swap.h> +#include <linux/smp.h> +#include <linux/init.h> +#include <linux/pagemap.h> +#include <linux/bootmem.h> +#include <linux/proc_fs.h> + +#include <asm/processor.h> +#include <asm/system.h> +#include <asm/uaccess.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/dma.h> +#include <asm/fixmap.h> +#include <asm/e820.h> +#include <asm/apic.h> +#include <asm/tlb.h> +#include <asm/mmu_context.h> +#include <asm/proto.h> +#include <asm/smp.h> + +#include <xen/features.h> + +#ifndef Dprintk +#define Dprintk(x...) +#endif + +extern unsigned long *contiguous_bitmap; + +#if defined(CONFIG_SWIOTLB) +extern void swiotlb_init(void); +#endif + +extern char _stext[]; + +DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); +extern unsigned long start_pfn; + +/* + * Use this until direct mapping is established, i.e. before __va() is + * available in init_memory_mapping(). + */ + +#define addr_to_page(addr, page) \ + (addr) &= PHYSICAL_PAGE_MASK; \ + (page) = ((unsigned long *) ((unsigned long) \ + (((mfn_to_pfn((addr) >> PAGE_SHIFT)) << PAGE_SHIFT) + \ + __START_KERNEL_map))) + +static void early_make_page_readonly(void *va, unsigned int feature) +{ + unsigned long addr, _va = (unsigned long)va; + pte_t pte, *ptep; + unsigned long *page = (unsigned long *) init_level4_pgt; + + if (xen_feature(feature)) + return; + + addr = (unsigned long) page[pgd_index(_va)]; + addr_to_page(addr, page); + + addr = page[pud_index(_va)]; + addr_to_page(addr, page); + + addr = page[pmd_index(_va)]; + addr_to_page(addr, page); + + ptep = (pte_t *) &page[pte_index(_va)]; + + pte.pte = ptep->pte & ~_PAGE_RW; + if (HYPERVISOR_update_va_mapping(_va, pte, 0)) + BUG(); +} + +void make_page_readonly(void *va, unsigned int feature) +{ + pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t pte, *ptep; + unsigned long addr = (unsigned long) va; + + if (xen_feature(feature)) + return; + + pgd = pgd_offset_k(addr); + pud = pud_offset(pgd, addr); + pmd = pmd_offset(pud, addr); + ptep = pte_offset_kernel(pmd, addr); + + pte.pte = ptep->pte & ~_PAGE_RW; + if (HYPERVISOR_update_va_mapping(addr, pte, 0)) + xen_l1_entry_update(ptep, pte); /* fallback */ + + if ((addr >= VMALLOC_START) && (addr < VMALLOC_END)) + make_page_readonly(__va(pte_pfn(pte) << PAGE_SHIFT), feature); +} + +void make_page_writable(void *va, unsigned int feature) +{ + pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t pte, *ptep; + unsigned long addr = (unsigned long) va; + + if (xen_feature(feature)) + return; + + pgd = pgd_offset_k(addr); + pud = pud_offset(pgd, addr); + pmd = pmd_offset(pud, addr); + ptep = pte_offset_kernel(pmd, addr); + + pte.pte = ptep->pte | _PAGE_RW; + if (HYPERVISOR_update_va_mapping(addr, pte, 0)) + xen_l1_entry_update(ptep, pte); /* fallback */ + + if ((addr >= VMALLOC_START) && (addr < VMALLOC_END)) + make_page_writable(__va(pte_pfn(pte) << PAGE_SHIFT), feature); +} + +void make_pages_readonly(void *va, unsigned nr, unsigned int feature) +{ + if (xen_feature(feature)) + return; + + while (nr-- != 0) { + make_page_readonly(va, feature); + va = (void*)((unsigned long)va + PAGE_SIZE); + } +} + +void make_pages_writable(void *va, unsigned nr, unsigned int feature) +{ + if (xen_feature(feature)) + return; + + while (nr-- != 0) { + make_page_writable(va, feature); + va = (void*)((unsigned long)va + PAGE_SIZE); + } +} + +/* + * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the + * physical space so we can cache the place of the first one and move + * around without checking the pgd every time. + */ + +void show_mem(void) +{ + int i, total = 0, reserved = 0; + int shared = 0, cached = 0; + pg_data_t *pgdat; + struct page *page; + + printk("Mem-info:\n"); + show_free_areas(); + printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10)); + + for_each_pgdat(pgdat) { + for (i = 0; i < pgdat->node_spanned_pages; ++i) { + page = pfn_to_page(pgdat->node_start_pfn + i); + total++; + if (PageReserved(page)) + reserved++; + else if (PageSwapCache(page)) + cached++; + else if (page_count(page)) + shared += page_count(page) - 1; + } + } + printk("%d pages of RAM\n", total); + printk("%d reserved pages\n",reserved); + printk("%d pages shared\n",shared); + printk("%d pages swap cached\n",cached); +} + +/* References to section boundaries */ + +extern char _text, _etext, _edata, __bss_start, _end[]; +extern char __init_begin, __init_end; + +int after_bootmem; + +static void *spp_getpage(void) +{ + void *ptr; + if (after_bootmem) + ptr = (void *) get_zeroed_page(GFP_ATOMIC); + else + ptr = alloc_bootmem_pages(PAGE_SIZE); + if (!ptr || ((unsigned long)ptr & ~PAGE_MASK)) + panic("set_pte_phys: cannot allocate page data %s\n", after_bootmem?"after bootmem":""); + + Dprintk("spp_getpage %p\n", ptr); + return ptr; +} + +#define pgd_offset_u(address) (pgd_t *)(init_level4_user_pgt + pgd_index(address)) + +static inline pud_t *pud_offset_u(unsigned long address) +{ + pud_t *pud = level3_user_pgt; + + return pud + pud_index(address); +} + +static void set_pte_phys(unsigned long vaddr, + unsigned long phys, pgprot_t prot, int user_mode) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte, new_pte; + + Dprintk("set_pte_phys %lx to %lx\n", vaddr, phys); + + pgd = (user_mode ? pgd_offset_u(vaddr) : pgd_offset_k(vaddr)); + if (pgd_none(*pgd)) { + printk("PGD FIXMAP MISSING, it should be setup in head.S!\n"); + return; + } + pud = (user_mode ? pud_offset_u(vaddr) : pud_offset(pgd, vaddr)); + if (pud_none(*pud)) { + pmd = (pmd_t *) spp_getpage(); + make_page_readonly(pmd, XENFEAT_writable_page_tables); + xen_pmd_pin(__pa(pmd)); + set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | _PAGE_USER)); + if (pmd != pmd_offset(pud, 0)) { + printk("PAGETABLE BUG #01! %p <-> %p\n", pmd, pmd_offset(pud,0)); + return; + } + } + pmd = pmd_offset(pud, vaddr); + if (pmd_none(*pmd)) { + pte = (pte_t *) spp_getpage(); + make_page_readonly(pte, XENFEAT_writable_page_tables); + xen_pte_pin(__pa(pte)); + set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE | _PAGE_USER)); + if (pte != pte_offset_kernel(pmd, 0)) { + printk("PAGETABLE BUG #02!\n"); + return; + } + } + new_pte = pfn_pte(phys >> PAGE_SHIFT, prot); + + pte = pte_offset_kernel(pmd, vaddr); + if (!pte_none(*pte) && + pte_val(*pte) != (pte_val(new_pte) & __supported_pte_mask)) + pte_ERROR(*pte); + set_pte(pte, new_pte); + + /* + * It's enough to flush this one mapping. + * (PGE mappings get flushed as well) + */ + __flush_tlb_one(vaddr); +} + +static void set_pte_phys_ma(unsigned long vaddr, + unsigned long phys, pgprot_t prot) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte, new_pte; + + Dprintk("set_pte_phys %lx to %lx\n", vaddr, phys); + + pgd = pgd_offset_k(vaddr); + if (pgd_none(*pgd)) { + printk("PGD FIXMAP MISSING, it should be setup in head.S!\n"); + return; + } + pud = pud_offset(pgd, vaddr); + if (pud_none(*pud)) { + + pmd = (pmd_t *) spp_getpage(); + make_page_readonly(pmd, XENFEAT_writable_page_tables); + xen_pmd_pin(__pa(pmd)); + + set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | _PAGE_USER)); + + if (pmd != pmd_offset(pud, 0)) { + printk("PAGETABLE BUG #01! %p <-> %p\n", pmd, pmd_offset(pud,0)); + return; + } + } + pmd = pmd_offset(pud, vaddr); + + if (pmd_none(*pmd)) { + pte = (pte_t *) spp_getpage(); + make_page_readonly(pte, XENFEAT_writable_page_tables); + xen_pte_pin(__pa(pte)); + + set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE | _PAGE_USER)); + if (pte != pte_offset_kernel(pmd, 0)) { + printk("PAGETABLE BUG #02!\n"); + return; + } + } + + new_pte = pfn_pte_ma(phys >> PAGE_SHIFT, prot); + pte = pte_offset_kernel(pmd, vaddr); + + /* + * Note that the pte page is already RO, thus we want to use + * xen_l1_entry_update(), not set_pte(). + */ + xen_l1_entry_update(pte, + pfn_pte_ma(phys >> PAGE_SHIFT, prot)); + + /* + * It's enough to flush this one mapping. + * (PGE mappings get flushed as well) + */ + __flush_tlb_one(vaddr); +} + +#define SET_FIXMAP_KERNEL 0 +#define SET_FIXMAP_USER 1 + +/* NOTE: this is meant to be run only at boot */ +void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t prot) +{ + unsigned long address = __fix_to_virt(idx); + + if (idx >= __end_of_fixed_addresses) { + printk("Invalid __set_fixmap\n"); + return; + } + switch (idx) { + case VSYSCALL_FIRST_PAGE: + set_pte_phys(address, phys, prot, SET_FIXMAP_KERNEL); + break; + default: + set_pte_phys_ma(address, phys, prot); + break; + } +} + +/* + * At this point it only supports vsyscall area. + */ +void __set_fixmap_user (enum fixed_addresses idx, unsigned long phys, pgprot_t prot) +{ + unsigned long address = __fix_to_virt(idx); + + if (idx >= __end_of_fixed_addresses) { + printk("Invalid __set_fixmap\n"); + return; + } + + set_pte_phys(address, phys, prot, SET_FIXMAP_USER); +} + +unsigned long __initdata table_start, tables_space; + +unsigned long get_machine_pfn(unsigned long addr) +{ + pud_t* pud = pud_offset_k(addr); + pmd_t* pmd = pmd_offset(pud, addr); + pte_t *pte = pte_offset_kernel(pmd, addr); + + return pte_mfn(*pte); +} + +static __init void *alloc_static_page(unsigned long *phys) +{ + unsigned long va = (start_pfn << PAGE_SHIFT) + __START_KERNEL_map; + *phys = start_pfn << PAGE_SHIFT; + start_pfn++; + memset((void *)va, 0, PAGE_SIZE); + return (void *)va; +} + +#define PTE_SIZE PAGE_SIZE + +static inline void __set_pte(pte_t *dst, pte_t val) +{ + *dst = val; +} + +static inline int make_readonly(unsigned long paddr) +{ + int readonly = 0; + + /* Make old and new page tables read-only. */ + if (!xen_feature(XENFEAT_writable_page_tables) + && (paddr >= (xen_start_info->pt_base - __START_KERNEL_map)) + && (paddr < ((table_start << PAGE_SHIFT) + tables_space))) + readonly = 1; + /* + * No need for writable mapping of kernel image. This also ensures that + * page and descriptor tables embedded inside don't have writable + * mappings. + */ + if ((paddr >= __pa_symbol(&_text)) && (paddr < __pa_symbol(&_end))) + readonly = 1; + + return readonly; +} + +static void __init phys_pud_init(pud_t *pud, unsigned long address, unsigned long end) +{ + long i, j, k; + unsigned long paddr; + + i = pud_index(address); + pud = pud + i; + for (; i < PTRS_PER_PUD; pud++, i++) { + unsigned long pmd_phys; + pmd_t *pmd; + + paddr = address + i*PUD_SIZE; + if (paddr >= end) { + for (; i < PTRS_PER_PUD; i++, pud++) + set_pud(pud, __pud(0)); + break; + } + + pmd = alloc_static_page(&pmd_phys); + early_make_page_readonly(pmd, XENFEAT_writable_page_tables); + xen_pmd_pin(pmd_phys); + set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE)); + for (j = 0; j < PTRS_PER_PMD; pmd++, j++) { + unsigned long pte_phys; + pte_t *pte, *pte_save; + + if (paddr >= end) { + for (; j < PTRS_PER_PMD; j++, pmd++) + set_pmd(pmd, __pmd(0)); + break; + } + pte = alloc_static_page(&pte_phys); + pte_save = pte; + for (k = 0; k < PTRS_PER_PTE; pte++, k++, paddr += PTE_SIZE) { + if ((paddr >= end) || + ((paddr >> PAGE_SHIFT) >= + xen_start_info->nr_pages)) { + __set_pte(pte, __pte(0)); + continue; + } + if (make_readonly(paddr)) { + __set_pte(pte, + __pte(paddr | (_KERNPG_TABLE & ~_PAGE_RW))); + continue; + } + __set_pte(pte, __pte(paddr | _KERNPG_TABLE)); + } + pte = pte_save; + early_make_page_readonly( + pte, XENFEAT_writable_page_tables); + xen_pte_pin(pte_phys); + set_pmd(pmd, __pmd(pte_phys | _KERNPG_TABLE)); + } + } + __flush_tlb(); +} + +static void __init find_early_table_space(unsigned long end) +{ + unsigned long puds, pmds, ptes; + + puds = (end + PUD_SIZE - 1) >> PUD_SHIFT; + pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT; + ptes = (end + PTE_SIZE - 1) >> PAGE_SHIFT; + + tables_space = + round_up(puds * 8, PAGE_SIZE) + + round_up(pmds * 8, PAGE_SIZE) + + round_up(ptes * 8, PAGE_SIZE); +} + +void __init xen_init_pt(void) +{ + unsigned long addr, *page; + int i; + + for (i = 0; i < NR_CPUS; i++) + per_cpu(cur_pgd, i) = init_mm.pgd; + + memset((void *)init_level4_pgt, 0, PAGE_SIZE); + memset((void *)level3_kernel_pgt, 0, PAGE_SIZE); + memset((void *)level2_kernel_pgt, 0, PAGE_SIZE); + + /* Find the initial pte page that was built for us. */ + page = (unsigned long *)xen_start_info->pt_base; + addr = page[pgd_index(__START_KERNEL_map)]; + addr_to_page(addr, page); + addr = page[pud_index(__START_KERNEL_map)]; + addr_to_page(addr, page); + + /* Construct mapping of initial pte page in our own directories. */ + init_level4_pgt[pgd_index(__START_KERNEL_map)] = + mk_kernel_pgd(__pa_symbol(level3_kernel_pgt)); + level3_kernel_pgt[pud_index(__START_KERNEL_map)] = + __pud(__pa_symbol(level2_kernel_pgt) | + _KERNPG_TABLE | _PAGE_USER); + memcpy((void *)level2_kernel_pgt, page, PAGE_SIZE); + + early_make_page_readonly(init_level4_pgt, + XENFEAT_writable_page_tables); + early_make_page_readonly(init_level4_user_pgt, + XENFEAT_writable_page_tables); + early_make_page_readonly(level3_kernel_pgt, + XENFEAT_writable_page_tables); + early_make_page_readonly(level3_user_pgt, + XENFEAT_writable_page_tables); + early_make_page_readonly(level2_kernel_pgt, + XENFEAT_writable_page_tables); + + xen_pgd_pin(__pa_symbol(init_level4_pgt)); + xen_pgd_pin(__pa_symbol(init_level4_user_pgt)); + xen_pud_pin(__pa_symbol(level3_kernel_pgt)); + xen_pud_pin(__pa_symbol(level3_user_pgt)); + xen_pmd_pin(__pa_symbol(level2_kernel_pgt)); + + set_pgd((pgd_t *)(init_level4_user_pgt + 511), + mk_kernel_pgd(__pa_symbol(level3_user_pgt))); +} + +void __init extend_init_mapping(void) +{ + unsigned long va = __START_KERNEL_map; + unsigned long phys, addr, *pte_page; + pmd_t *pmd; + pte_t *pte, new_pte; + unsigned long *page = (unsigned long *)init_level4_pgt; + + addr = page[pgd_index(va)]; + addr_to_page(addr, page); + addr = page[pud_index(va)]; + addr_to_page(addr, page); + + /* Kill mapping of low 1MB. */ + while (va < (unsigned long)&_text) { + HYPERVISOR_update_va_mapping(va, __pte_ma(0), 0); + va += PAGE_SIZE; + } + + /* Ensure init mappings cover kernel text/data and initial tables. */ + while (va < (__START_KERNEL_map + + (start_pfn << PAGE_SHIFT) + + tables_space)) { + pmd = (pmd_t *)&page[pmd_index(va)]; + if (pmd_none(*pmd)) { + pte_page = alloc_static_page(&phys); + early_make_page_readonly( + pte_page, XENFEAT_writable_page_tables); + xen_pte_pin(phys); + set_pmd(pmd, __pmd(phys | _KERNPG_TABLE | _PAGE_USER)); + } else { + addr = page[pmd_index(va)]; + addr_to_page(addr, pte_page); + } + pte = (pte_t *)&pte_page[pte_index(va)]; + if (pte_none(*pte)) { + new_pte = pfn_pte( + (va - __START_KERNEL_map) >> PAGE_SHIFT, + __pgprot(_KERNPG_TABLE | _PAGE_USER)); + xen_l1_entry_update(pte, new_pte); + } + va += PAGE_SIZE; + } + + /* Finally, blow away any spurious initial mappings. */ + while (1) { + pmd = (pmd_t *)&page[pmd_index(va)]; + if (pmd_none(*pmd)) + break; + HYPERVISOR_update_va_mapping(va, __pte_ma(0), 0); + va += PAGE_SIZE; + } +} + +/* Setup the direct mapping of the physical memory at PAGE_OFFSET. + This runs before bootmem is initialized and gets pages directly from the + physical memory. To access them they are temporarily mapped. */ +void __init init_memory_mapping(unsigned long start, unsigned long end) +{ + unsigned long next; + + Dprintk("init_memory_mapping\n"); + + find_early_table_space(end); + extend_init_mapping(); + + table_start = start_pfn; + + start = (unsigned long)__va(start); + end = (unsigned long)__va(end); + + for (; start < end; start = next) { + unsigned long pud_phys; + pud_t *pud = alloc_static_page(&pud_phys); + early_make_page_readonly(pud, XENFEAT_writable_page_tables); + xen_pud_pin(pud_phys); + next = start + PGDIR_SIZE; + if (next > end) + next = end; + phys_pud_init(pud, __pa(start), __pa(next)); + set_pgd(pgd_offset_k(start), mk_kernel_pgd(pud_phys)); + } + + printk("kernel direct mapping tables upto %lx @ %lx-%lx\n", + __pa(end), table_start<<PAGE_SHIFT, start_pfn<<PAGE_SHIFT); + + BUG_ON(start_pfn != (table_start + (tables_space >> PAGE_SHIFT))); + + __flush_tlb_all(); +} + +extern struct x8664_pda cpu_pda[NR_CPUS]; + +void zap_low_mappings(void) +{ + /* this is not required for Xen */ +#if 0 + swap_low_mappings(); +#endif +} + +#ifndef CONFIG_DISCONTIGMEM +void __init paging_init(void) +{ + { + unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0}; + /* unsigned int max_dma; */ + /* max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; */ + /* if (end_pfn < max_dma) */ + zones_size[ZONE_DMA] = end_pfn; +#if 0 + else { + zones_size[ZONE_DMA] = max_dma; + zones_size[ZONE_NORMAL] = end_pfn - max_dma; + } +#endif + free_area_init(zones_size); + } + + set_fixmap(FIX_SHARED_INFO, xen_start_info->shared_info); + HYPERVISOR_shared_info = (shared_info_t *)fix_to_virt(FIX_SHARED_INFO); + + memset(empty_zero_page, 0, sizeof(empty_zero_page)); + init_mm.context.pinned = 1; + +#ifdef CONFIG_XEN_PHYSDEV_ACCESS + { + int i; + /* Setup mapping of lower 1st MB */ + for (i = 0; i < NR_FIX_ISAMAPS; i++) + if (xen_start_info->flags & SIF_PRIVILEGED) + set_fixmap(FIX_ISAMAP_BEGIN - i, i * PAGE_SIZE); + else + __set_fixmap(FIX_ISAMAP_BEGIN - i, + virt_to_mfn(empty_zero_page) << PAGE_SHIFT, + PAGE_KERNEL_RO); + } +#endif + +} +#endif + +/* Unmap a kernel mapping if it exists. This is useful to avoid prefetches + from the CPU leading to inconsistent cache lines. address and size + must be aligned to 2MB boundaries. + Does nothing when the mapping doesn't exist. */ +void __init clear_kernel_mapping(unsigned long address, unsigned long size) +{ + unsigned long end = address + size; + + BUG_ON(address & ~LARGE_PAGE_MASK); + BUG_ON(size & ~LARGE_PAGE_MASK); + + for (; address < end; address += LARGE_PAGE_SIZE) { + pgd_t *pgd = pgd_offset_k(address); + pud_t *pud; + pmd_t *pmd; + if (pgd_none(*pgd)) + continue; + pud = pud_offset(pgd, address); + if (pud_none(*pud)) + continue; + pmd = pmd_offset(pud, address); + if (!pmd || pmd_none(*pmd)) + continue; + if (0 == (pmd_val(*pmd) & _PAGE_PSE)) { + /* Could handle this, but it should not happen currently. */ + printk(KERN_ERR + "clear_kernel_mapping: mapping has been split. will leak memory\n"); + pmd_ERROR(*pmd); + } + set_pmd(pmd, __pmd(0)); + } + __flush_tlb_all(); +} + +static inline int page_is_ram (unsigned long pagenr) +{ + return 1; +} + +static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules, + kcore_vsyscall; + +void __init mem_init(void) +{ + int codesize, reservedpages, datasize, initsize; + int tmp; + + contiguous_bitmap = alloc_bootmem_low_pages( + (end_pfn + 2*BITS_PER_LONG) >> 3); + BUG_ON(!contiguous_bitmap); + memset(contiguous_bitmap, 0, (end_pfn + 2*BITS_PER_LONG) >> 3); + +#if defined(CONFIG_SWIOTLB) + swiotlb_init(); +#endif + + /* How many end-of-memory variables you have, grandma! */ + max_low_pfn = end_pfn; + max_pfn = end_pfn; + num_physpages = end_pfn; + high_memory = (void *) __va(end_pfn * PAGE_SIZE); + + /* clear the zero-page */ + memset(empty_zero_page, 0, PAGE_SIZE); + + reservedpages = 0; + + /* this will put all low memory onto the freelists */ +#ifdef CONFIG_DISCONTIGMEM + totalram_pages += numa_free_all_bootmem(); + tmp = 0; + /* should count reserved pages here for all nodes */ +#else + max_mapnr = end_pfn; + if (!mem_map) BUG(); + + totalram_pages += free_all_bootmem(); + + for (tmp = 0; tmp < end_pfn; tmp++) + /* + * Only count reserved RAM pages + */ + if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp))) + reservedpages++; +#endif + + after_bootmem = 1; + + codesize = (unsigned long) &_etext - (unsigned long) &_text; + datasize = (unsigned long) &_edata - (unsigned long) &_etext; + initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; + + /* Register memory areas for /proc/kcore */ + kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT); + kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, + VMALLOC_END-VMALLOC_START); + kclist_add(&kcore_kernel, &_stext, _end - _stext); + kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_LEN); + kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START, + VSYSCALL_END - VSYSCALL_START); + + printk("Memory: %luk/%luk available (%dk kernel code, %dk reserved, %dk data, %dk init)\n", + (unsigned long) nr_free_pages() << (PAGE_SHIFT-10), + end_pfn << (PAGE_SHIFT-10), + codesize >> 10, + reservedpages << (PAGE_SHIFT-10), + datasize >> 10, + initsize >> 10); + + /* + * Subtle. SMP is doing its boot stuff late (because it has to + * fork idle threads) - but it also needs low mappings for the + * protected-mode entry to work. We zap these entries only after + * the WP-bit has been tested. + */ +#ifndef CONFIG_SMP + zap_low_mappings(); +#endif +} + +extern char __initdata_begin[], __initdata_end[]; + +void free_initmem(void) +{ +#ifdef __DO_LATER__ + /* + * Some pages can be pinned, but some are not. Unpinning such pages + * triggers BUG(). + */ + unsigned long addr; + + addr = (unsigned long)(&__init_begin); + for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) { + ClearPageReserved(virt_to_page(addr)); + set_page_count(virt_to_page(addr), 1); + memset((void *)(addr & ~(PAGE_SIZE-1)), 0xcc, PAGE_SIZE); + xen_pte_unpin(__pa(addr)); + make_page_writable( + __va(__pa(addr)), XENFEAT_writable_page_tables); + /* + * Make pages from __PAGE_OFFSET address as well + */ + make_page_writable( + (void *)addr, XENFEAT_writable_page_tables); + free_page(addr); + totalram_pages++; + } + memset(__initdata_begin, 0xba, __initdata_end - __initdata_begin); + printk ("Freeing unused kernel memory: %luk freed\n", (&__init_end - &__init_begin) >> 10); +#endif +} + +#ifdef CONFIG_BLK_DEV_INITRD +void free_initrd_mem(unsigned long start, unsigned long end) +{ + if (start < (unsigned long)&_end) + return; + printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10); + for (; start < end; start += PAGE_SIZE) { + ClearPageReserved(virt_to_page(start)); + set_page_count(virt_to_page(start), 1); + free_page(start); + totalram_pages++; + } +} +#endif + +void __init reserve_bootmem_generic(unsigned long phys, unsigned len) +{ + /* Should check here against the e820 map to avoid double free */ +#ifdef CONFIG_DISCONTIGMEM + int nid = phys_to_nid(phys); + reserve_bootmem_node(NODE_DATA(nid), phys, len); +#else + reserve_bootmem(phys, len); +#endif +} + +int kern_addr_valid(unsigned long addr) +{ + unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + if (above != 0 && above != -1UL) + return 0; + + pgd = pgd_offset_k(addr); + if (pgd_none(*pgd)) + return 0; + + pud = pud_offset_k(addr); + if (pud_none(*pud)) + return 0; + + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return 0; + if (pmd_large(*pmd)) + return pfn_valid(pmd_pfn(*pmd)); + + pte = pte_offset_kernel(pmd, addr); + if (pte_none(*pte)) + return 0; + return pfn_valid(pte_pfn(*pte)); +} + +#ifdef CONFIG_SYSCTL +#include <linux/sysctl.h> + +extern int exception_trace, page_fault_trace; + +static ctl_table debug_table2[] = { + { 99, "exception-trace", &exception_trace, sizeof(int), 0644, NULL, + proc_dointvec }, +#ifdef CONFIG_CHECKING + { 100, "page-fault-trace", &page_fault_trace, sizeof(int), 0644, NULL, + proc_dointvec }, +#endif + { 0, } +}; + +static ctl_table debug_root_table2[] = { + { .ctl_name = CTL_DEBUG, .procname = "debug", .mode = 0555, + .child = debug_table2 }, + { 0 }, +}; + +static __init int x8664_sysctl_init(void) +{ + register_sysctl_table(debug_root_table2, 1); + return 0; +} +__initcall(x8664_sysctl_init); +#endif + +/* A pseudo VMAs to allow ptrace access for the vsyscall page. This only + covers the 64bit vsyscall page now. 32bit has a real VMA now and does + not need special handling anymore. */ + +static struct vm_area_struct gate_vma = { + .vm_start = VSYSCALL_START, + .vm_end = VSYSCALL_END, + .vm_page_prot = PAGE_READONLY +}; + +struct vm_area_struct *get_gate_vma(struct task_struct *tsk) +{ +#ifdef CONFIG_IA32_EMULATION + if (test_tsk_thread_flag(tsk, TIF_IA32)) + return NULL; +#endif + return &gate_vma; +} + +int in_gate_area(struct task_struct *task, unsigned long addr) +{ + struct vm_area_struct *vma = get_gate_vma(task); + if (!vma) + return 0; + return (addr >= vma->vm_start) && (addr < vma->vm_end); +} + +/* Use this when you have no reliable task/vma, typically from interrupt + * context. It is less reliable than using the task's vma and may give + * false positives. + */ +int in_gate_area_no_task(unsigned long addr) +{ + return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END); +} + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/mm/pageattr-xen.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/mm/pageattr-xen.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,382 @@ +/* + * Copyright 2002 Andi Kleen, SuSE Labs. + * Thanks to Ben LaHaise for precious feedback. + */ + +#include <linux/config.h> +#include <linux/mm.h> +#include <linux/sched.h> +#include <linux/highmem.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <asm/uaccess.h> +#include <asm/processor.h> +#include <asm/tlbflush.h> +#include <asm/io.h> + +#ifdef CONFIG_XEN +#include <asm/pgalloc.h> +#include <asm/mmu_context.h> + +LIST_HEAD(mm_unpinned); +DEFINE_SPINLOCK(mm_unpinned_lock); + +static inline void mm_walk_set_prot(void *pt, pgprot_t flags) +{ + struct page *page = virt_to_page(pt); + unsigned long pfn = page_to_pfn(page); + + BUG_ON(HYPERVISOR_update_va_mapping( + (unsigned long)__va(pfn << PAGE_SHIFT), + pfn_pte(pfn, flags), 0)); +} + +static void mm_walk(struct mm_struct *mm, pgprot_t flags) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + int g,u,m; + + pgd = mm->pgd; + for (g = 0; g <= USER_PTRS_PER_PGD; g++, pgd++) { + if (pgd_none(*pgd)) + continue; + pud = pud_offset(pgd, 0); + if (PTRS_PER_PUD > 1) /* not folded */ + mm_walk_set_prot(pud,flags); + for (u = 0; u < PTRS_PER_PUD; u++, pud++) { + if (pud_none(*pud)) + continue; + pmd = pmd_offset(pud, 0); + if (PTRS_PER_PMD > 1) /* not folded */ + mm_walk_set_prot(pmd,flags); + for (m = 0; m < PTRS_PER_PMD; m++, pmd++) { + if (pmd_none(*pmd)) + continue; + pte = pte_offset_kernel(pmd,0); + mm_walk_set_prot(pte,flags); + } + } + } +} + +void mm_pin(struct mm_struct *mm) +{ + spin_lock(&mm->page_table_lock); + + mm_walk(mm, PAGE_KERNEL_RO); + BUG_ON(HYPERVISOR_update_va_mapping( + (unsigned long)mm->pgd, + pfn_pte(virt_to_phys(mm->pgd)>>PAGE_SHIFT, PAGE_KERNEL_RO), + UVMF_TLB_FLUSH)); + BUG_ON(HYPERVISOR_update_va_mapping( + (unsigned long)__user_pgd(mm->pgd), + pfn_pte(virt_to_phys(__user_pgd(mm->pgd))>>PAGE_SHIFT, PAGE_KERNEL_RO), + UVMF_TLB_FLUSH)); + xen_pgd_pin(__pa(mm->pgd)); /* kernel */ + xen_pgd_pin(__pa(__user_pgd(mm->pgd))); /* user */ + mm->context.pinned = 1; + spin_lock(&mm_unpinned_lock); + list_del(&mm->context.unpinned); + spin_unlock(&mm_unpinned_lock); + + spin_unlock(&mm->page_table_lock); +} + +void mm_unpin(struct mm_struct *mm) +{ + spin_lock(&mm->page_table_lock); + + xen_pgd_unpin(__pa(mm->pgd)); + xen_pgd_unpin(__pa(__user_pgd(mm->pgd))); + BUG_ON(HYPERVISOR_update_va_mapping( + (unsigned long)mm->pgd, + pfn_pte(virt_to_phys(mm->pgd)>>PAGE_SHIFT, PAGE_KERNEL), 0)); + BUG_ON(HYPERVISOR_update_va_mapping( + (unsigned long)__user_pgd(mm->pgd), + pfn_pte(virt_to_phys(__user_pgd(mm->pgd))>>PAGE_SHIFT, PAGE_KERNEL), 0)); + mm_walk(mm, PAGE_KERNEL); + xen_tlb_flush(); + mm->context.pinned = 0; + spin_lock(&mm_unpinned_lock); + list_add(&mm->context.unpinned, &mm_unpinned); + spin_unlock(&mm_unpinned_lock); + + spin_unlock(&mm->page_table_lock); +} + +void mm_pin_all(void) +{ + while (!list_empty(&mm_unpinned)) + mm_pin(list_entry(mm_unpinned.next, struct mm_struct, + context.unpinned)); +} + +void _arch_exit_mmap(struct mm_struct *mm) +{ + struct task_struct *tsk = current; + + task_lock(tsk); + + /* + * We aggressively remove defunct pgd from cr3. We execute unmap_vmas() + * *much* faster this way, as no tlb flushes means bigger wrpt batches. + */ + if ( tsk->active_mm == mm ) + { + tsk->active_mm = &init_mm; + atomic_inc(&init_mm.mm_count); + + switch_mm(mm, &init_mm, tsk); + + atomic_dec(&mm->mm_count); + BUG_ON(atomic_read(&mm->mm_count) == 0); + } + + task_unlock(tsk); + + if ( mm->context.pinned && (atomic_read(&mm->mm_count) == 1) ) + mm_unpin(mm); +} + +void pte_free(struct page *pte) +{ + unsigned long va = (unsigned long)__va(page_to_pfn(pte)<<PAGE_SHIFT); + + if (!pte_write(*virt_to_ptep(va))) + BUG_ON(HYPERVISOR_update_va_mapping( + va, pfn_pte(page_to_pfn(pte), PAGE_KERNEL), 0)); + __free_page(pte); +} +#endif /* CONFIG_XEN */ + +static inline pte_t *lookup_address(unsigned long address) +{ + pgd_t *pgd = pgd_offset_k(address); + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + if (pgd_none(*pgd)) + return NULL; + pud = pud_offset(pgd, address); + if (!pud_present(*pud)) + return NULL; + pmd = pmd_offset(pud, address); + if (!pmd_present(*pmd)) + return NULL; + if (pmd_large(*pmd)) + return (pte_t *)pmd; + pte = pte_offset_kernel(pmd, address); + if (pte && !pte_present(*pte)) + pte = NULL; + return pte; +} + +static struct page *split_large_page(unsigned long address, pgprot_t prot, + pgprot_t ref_prot) +{ + int i; + unsigned long addr; + struct page *base = alloc_pages(GFP_KERNEL, 0); + pte_t *pbase; + if (!base) + return NULL; + address = __pa(address); + addr = address & LARGE_PAGE_MASK; + pbase = (pte_t *)page_address(base); + for (i = 0; i < PTRS_PER_PTE; i++, addr += PAGE_SIZE) { + pbase[i] = pfn_pte(addr >> PAGE_SHIFT, + addr == address ? prot : ref_prot); + } + return base; +} + + +static void flush_kernel_map(void *address) +{ + if (0 && address && cpu_has_clflush) { + /* is this worth it? */ + int i; + for (i = 0; i < PAGE_SIZE; i += boot_cpu_data.x86_clflush_size) + asm volatile("clflush (%0)" :: "r" (address + i)); + } else + asm volatile("wbinvd":::"memory"); + if (address) + __flush_tlb_one(address); + else + __flush_tlb_all(); +} + + +static inline void flush_map(unsigned long address) +{ + on_each_cpu(flush_kernel_map, (void *)address, 1, 1); +} + +struct deferred_page { + struct deferred_page *next; + struct page *fpage; + unsigned long address; +}; +static struct deferred_page *df_list; /* protected by init_mm.mmap_sem */ + +static inline void save_page(unsigned long address, struct page *fpage) +{ + struct deferred_page *df; + df = kmalloc(sizeof(struct deferred_page), GFP_KERNEL); + if (!df) { + flush_map(address); + __free_page(fpage); + } else { + df->next = df_list; + df->fpage = fpage; + df->address = address; + df_list = df; + } +} + +/* + * No more special protections in this 2/4MB area - revert to a + * large page again. + */ +static void revert_page(unsigned long address, pgprot_t ref_prot) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t large_pte; + + pgd = pgd_offset_k(address); + BUG_ON(pgd_none(*pgd)); + pud = pud_offset(pgd,address); + BUG_ON(pud_none(*pud)); + pmd = pmd_offset(pud, address); + BUG_ON(pmd_val(*pmd) & _PAGE_PSE); + pgprot_val(ref_prot) |= _PAGE_PSE; + large_pte = mk_pte_phys(__pa(address) & LARGE_PAGE_MASK, ref_prot); + set_pte((pte_t *)pmd, large_pte); +} + +static int +__change_page_attr(unsigned long address, unsigned long pfn, pgprot_t prot, + pgprot_t ref_prot) +{ + pte_t *kpte; + struct page *kpte_page; + unsigned kpte_flags; + kpte = lookup_address(address); + if (!kpte) return 0; + kpte_page = virt_to_page(((unsigned long)kpte) & PAGE_MASK); + kpte_flags = pte_val(*kpte); + if (pgprot_val(prot) != pgprot_val(ref_prot)) { + if ((kpte_flags & _PAGE_PSE) == 0) { + set_pte(kpte, pfn_pte(pfn, prot)); + } else { + /* + * split_large_page will take the reference for this change_page_attr + * on the split page. + */ + struct page *split = split_large_page(address, prot, ref_prot); + if (!split) + return -ENOMEM; + set_pte(kpte,mk_pte(split, ref_prot)); + kpte_page = split; + } + get_page(kpte_page); + } else if ((kpte_flags & _PAGE_PSE) == 0) { + set_pte(kpte, pfn_pte(pfn, ref_prot)); + __put_page(kpte_page); + } else + BUG(); + + /* on x86-64 the direct mapping set at boot is not using 4k pages */ + /* + * ..., but the XEN guest kernels (currently) do: + * If the pte was reserved, it means it was created at boot + * time (not via split_large_page) and in turn we must not + * replace it with a large page. + */ +#ifndef CONFIG_XEN + BUG_ON(PageReserved(kpte_page)); +#else + if (!PageReserved(kpte_page)) +#endif + switch (page_count(kpte_page)) { + case 1: + save_page(address, kpte_page); + revert_page(address, ref_prot); + break; + case 0: + BUG(); /* memleak and failed 2M page regeneration */ + } + return 0; +} + +/* + * Change the page attributes of an page in the linear mapping. + * + * This should be used when a page is mapped with a different caching policy + * than write-back somewhere - some CPUs do not like it when mappings with + * different caching policies exist. This changes the page attributes of the + * in kernel linear mapping too. + * + * The caller needs to ensure that there are no conflicting mappings elsewhere. + * This function only deals with the kernel linear map. + * + * Caller must call global_flush_tlb() after this. + */ +int change_page_attr_addr(unsigned long address, int numpages, pgprot_t prot) +{ + int err = 0; + int i; + + down_write(&init_mm.mmap_sem); + for (i = 0; i < numpages; i++, address += PAGE_SIZE) { + unsigned long pfn = __pa(address) >> PAGE_SHIFT; + + err = __change_page_attr(address, pfn, prot, PAGE_KERNEL); + if (err) + break; + /* Handle kernel mapping too which aliases part of the + * lowmem */ + if (__pa(address) < KERNEL_TEXT_SIZE) { + unsigned long addr2; + pgprot_t prot2 = prot; + addr2 = __START_KERNEL_map + __pa(address); + pgprot_val(prot2) &= ~_PAGE_NX; + err = __change_page_attr(addr2, pfn, prot2, PAGE_KERNEL_EXEC); + } + } + up_write(&init_mm.mmap_sem); + return err; +} + +/* Don't call this for MMIO areas that may not have a mem_map entry */ +int change_page_attr(struct page *page, int numpages, pgprot_t prot) +{ + unsigned long addr = (unsigned long)page_address(page); + return change_page_attr_addr(addr, numpages, prot); +} + +void global_flush_tlb(void) +{ + struct deferred_page *df, *next_df; + + down_read(&init_mm.mmap_sem); + df = xchg(&df_list, NULL); + up_read(&init_mm.mmap_sem); + if (!df) + return; + flush_map((df && !df->next) ? df->address : 0); + for (; df; df = next_df) { + next_df = df->next; + if (df->fpage) + __free_page(df->fpage); + kfree(df); + } +} + +EXPORT_SYMBOL(change_page_attr); +EXPORT_SYMBOL(global_flush_tlb); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/x86_64/pci/Makefile --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/arch/x86_64/pci/Makefile Mon Jan 30 17:18:27 2006 @@ -0,0 +1,32 @@ +# +# Makefile for X86_64 specific PCI routines +# +# Reuse the i386 PCI subsystem +# +CFLAGS += -Iarch/i386/pci + +obj-y := i386.o +obj-$(CONFIG_PCI_DIRECT)+= direct.o +obj-y += fixup.o +obj-$(CONFIG_ACPI_PCI) += acpi.o +obj-y += legacy.o irq.o common.o +# mmconfig has a 64bit special +obj-$(CONFIG_PCI_MMCONFIG) += mmconfig.o + +obj-$(CONFIG_NUMA) += k8-bus.o + +direct-y += ../../i386/pci/direct.o +acpi-y += ../../i386/pci/acpi.o +legacy-y += ../../i386/pci/legacy.o +irq-y += ../../i386/pci/irq.o +common-y += ../../i386/pci/common.o +fixup-y += ../../i386/pci/fixup.o +i386-y += ../../i386/pci/i386.o + +ifdef CONFIG_XEN +irq-y := ../../i386/pci/irq-xen.o +i386-y := ../../i386/pci/i386-xen.o +include $(srctree)/scripts/Makefile.xen + +obj-y := $(call cherrypickxen, $(obj-y)) +endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/Kconfig --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/Kconfig Mon Jan 30 17:18:27 2006 @@ -0,0 +1,71 @@ +# drivers/Kconfig + +menu "Device Drivers" + +source "drivers/base/Kconfig" + +if !XEN || XEN_PHYSDEV_ACCESS +source "drivers/mtd/Kconfig" + +source "drivers/parport/Kconfig" + +source "drivers/pnp/Kconfig" +endif + +source "drivers/block/Kconfig" + +if !XEN || XEN_PHYSDEV_ACCESS +source "drivers/ide/Kconfig" +endif + +source "drivers/scsi/Kconfig" + +if !XEN || XEN_PHYSDEV_ACCESS +source "drivers/cdrom/Kconfig" +endif + +source "drivers/md/Kconfig" + +if !XEN || XEN_PHYSDEV_ACCESS +source "drivers/message/fusion/Kconfig" + +source "drivers/ieee1394/Kconfig" + +source "drivers/message/i2o/Kconfig" + +source "drivers/macintosh/Kconfig" +endif + +source "net/Kconfig" + +if !XEN || XEN_PHYSDEV_ACCESS +source "drivers/isdn/Kconfig" + +source "drivers/telephony/Kconfig" + +# input before char - char/joystick depends on it. As does USB. + +source "drivers/input/Kconfig" + +source "drivers/char/Kconfig" + +source "drivers/i2c/Kconfig" + +source "drivers/w1/Kconfig" + +source "drivers/misc/Kconfig" + +source "drivers/media/Kconfig" + +source "drivers/video/Kconfig" + +source "sound/Kconfig" + +source "drivers/usb/Kconfig" + +source "drivers/mmc/Kconfig" + +source "drivers/infiniband/Kconfig" +endif + +endmenu diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/firmware/Kconfig --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/firmware/Kconfig Mon Jan 30 17:18:27 2006 @@ -0,0 +1,61 @@ +# +# For a description of the syntax of this configuration file, +# see Documentation/kbuild/kconfig-language.txt. +# + +menu "Firmware Drivers" + +config EDD + tristate "BIOS Enhanced Disk Drive calls determine boot disk (EXPERIMENTAL)" + depends on EXPERIMENTAL + depends on !IA64 && !XEN + help + Say Y or M here if you want to enable BIOS Enhanced Disk Drive + Services real mode BIOS calls to determine which disk + BIOS tries boot from. This information is then exported via sysfs. + + This option is experimental and is known to fail to boot on some + obscure configurations. Most disk controller BIOS vendors do + not yet implement this feature. + +config EFI_VARS + tristate "EFI Variable Support via sysfs" + depends on EFI + default n + help + If you say Y here, you are able to get EFI (Extensible Firmware + Interface) variable information via sysfs. You may read, + write, create, and destroy EFI variables through this interface. + + Note that using this driver in concert with efibootmgr requires + at least test release version 0.5.0-test3 or later, which is + available from Matt Domsch's website located at: + <http://linux.dell.com/efibootmgr/testing/efibootmgr-0.5.0-test3.tar.gz> + + Subsequent efibootmgr releases may be found at: + <http://linux.dell.com/efibootmgr> + +config EFI_PCDP + bool "Console device selection via EFI PCDP or HCDP table" + depends on ACPI && EFI && IA64 + default y if IA64 + help + If your firmware supplies the PCDP table, and you want to + automatically use the primary console device it describes + as the Linux console, say Y here. + + If your firmware supplies the HCDP table, and you want to + use the first serial port it describes as the Linux console, + say Y here. If your EFI ConOut path contains only a UART + device, it will become the console automatically. Otherwise, + you must specify the "console=hcdp" kernel boot argument. + + Neither the PCDP nor the HCDP affects naming of serial devices, + so a serial console may be /dev/ttyS0, /dev/ttyS1, etc, depending + on how the driver discovers devices. + + You must also enable the appropriate drivers (serial, VGA, etc.) + + See <http://www.dig64.org/specifications/DIG64_HCDPv20_042804.pdf> + +endmenu diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/pci/Kconfig --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/pci/Kconfig Mon Jan 30 17:18:27 2006 @@ -0,0 +1,60 @@ +# +# PCI configuration +# +config PCI_MSI + bool "Message Signaled Interrupts (MSI and MSI-X)" + depends on PCI + depends on (X86_LOCAL_APIC && X86_IO_APIC) || IA64 + depends on !XEN + help + This allows device drivers to enable MSI (Message Signaled + Interrupts). Message Signaled Interrupts enable a device to + generate an interrupt using an inbound Memory Write on its + PCI bus instead of asserting a device IRQ pin. + + If you don't know what to do here, say N. + +config PCI_LEGACY_PROC + bool "Legacy /proc/pci interface" + depends on PCI + ---help--- + This feature enables a procfs file -- /proc/pci -- that provides a + summary of PCI devices in the system. + + This feature has been deprecated as of v2.5.53, in favor of using the + tool lspci(8). This feature may be removed at a future date. + + lspci can provide the same data, as well as much more. lspci is a part of + the pci-utils package, which should be installed by your distribution. + See <file:Documentation/Changes> for information on where to get the latest + version. + + When in doubt, say N. + +config PCI_NAMES + bool "PCI device name database" + depends on PCI + ---help--- + By default, the kernel contains a database of all known PCI device + names to make the information in /proc/pci, /proc/ioports and + similar files comprehensible to the user. + + This database increases size of the kernel image by about 80KB. This + memory is freed after the system boots up if CONFIG_HOTPLUG is not set. + + Anyway, if you are building an installation floppy or kernel for an + embedded system where kernel image size really matters, you can disable + this feature and you'll get device ID numbers instead of names. + + When in doubt, say Y. + +config PCI_DEBUG + bool "PCI Debugging" + depends on PCI && DEBUG_KERNEL + help + Say Y here if you want the PCI core to produce a bunch of debug + messages to the system log. Select this if you are having a + problem with PCI support and want to see more of what is going on. + + When in doubt, say N. + diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/serial/Kconfig --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/serial/Kconfig Mon Jan 30 17:18:27 2006 @@ -0,0 +1,846 @@ +# +# Serial device configuration +# +# $Id: Kconfig,v 1.11 2004/03/11 18:08:04 lethal Exp $ +# + +menu "Serial drivers" + +# +# The new 8250/16550 serial drivers +config SERIAL_8250 + tristate "8250/16550 and compatible serial support" + depends on (BROKEN || !(SPARC64 || SPARC32 || XEN_DISABLE_SERIAL)) + select SERIAL_CORE + ---help--- + This selects whether you want to include the driver for the standard + serial ports. The standard answer is Y. People who might say N + here are those that are setting up dedicated Ethernet WWW/FTP + servers, or users that have one of the various bus mice instead of a + serial mouse and don't intend to use their machine's standard serial + port for anything. (Note that the Cyclades and Stallion multi + serial port drivers do not need this driver built in for them to + work.) + + To compile this driver as a module, choose M here: the + module will be called serial. + [WARNING: Do not compile this driver as a module if you are using + non-standard serial ports, since the configuration information will + be lost when the driver is unloaded. This limitation may be lifted + in the future.] + + BTW1: If you have a mouseman serial mouse which is not recognized by + the X window system, try running gpm first. + + BTW2: If you intend to use a software modem (also called Winmodem) + under Linux, forget it. These modems are crippled and require + proprietary drivers which are only available under Windows. + + Most people will say Y or M here, so that they can use serial mice, + modems and similar devices connecting to the standard serial ports. + +config SERIAL_8250_CONSOLE + bool "Console on 8250/16550 and compatible serial port" + depends on SERIAL_8250=y + select SERIAL_CORE_CONSOLE + ---help--- + If you say Y here, it will be possible to use a serial port as the + system console (the system console is the device which receives all + kernel messages and warnings and which allows logins in single user + mode). This could be useful if some terminal or printer is connected + to that serial port. + + Even if you say Y here, the currently visible virtual console + (/dev/tty0) will still be used as the system console by default, but + you can alter that using a kernel command line option such as + "console=ttyS1". (Try "man bootparam" or see the documentation of + your boot loader (grub or lilo or loadlin) about how to pass options + to the kernel at boot time.) + + If you don't have a VGA card installed and you say Y here, the + kernel will automatically use the first serial line, /dev/ttyS0, as + system console. + + If unsure, say N. + +config SERIAL_8250_CS + tristate "8250/16550 PCMCIA device support" + depends on PCMCIA && SERIAL_8250 + ---help--- + Say Y here to enable support for 16-bit PCMCIA serial devices, + including serial port cards, modems, and the modem functions of + multi-function Ethernet/modem cards. (PCMCIA- or PC-cards are + credit-card size devices often used with laptops.) + + To compile this driver as a module, choose M here: the + module will be called serial_cs. + + If unsure, say N. + +config SERIAL_8250_ACPI + bool "8250/16550 device discovery via ACPI namespace" + default y if IA64 + depends on ACPI_BUS && SERIAL_8250 + ---help--- + If you wish to enable serial port discovery via the ACPI + namespace, say Y here. If unsure, say N. + +config SERIAL_8250_NR_UARTS + int "Maximum number of non-legacy 8250/16550 serial ports" + depends on SERIAL_8250 + default "4" + ---help--- + Set this to the number of non-legacy serial ports you want + the driver to support. This includes any ports discovered + via ACPI or PCI enumeration and any ports that may be added + at run-time via hot-plug. + +config SERIAL_8250_EXTENDED + bool "Extended 8250/16550 serial driver options" + depends on SERIAL_8250 + help + If you wish to use any non-standard features of the standard "dumb" + driver, say Y here. This includes HUB6 support, shared serial + interrupts, special multiport support, support for more than the + four COM 1/2/3/4 boards, etc. + + Note that the answer to this question won't directly affect the + kernel: saying N will just cause the configurator to skip all + the questions about serial driver options. If unsure, say N. + +config SERIAL_8250_MANY_PORTS + bool "Support more than 4 legacy serial ports" + depends on SERIAL_8250_EXTENDED && !IA64 + help + Say Y here if you have dumb serial boards other than the four + standard COM 1/2/3/4 ports. This may happen if you have an AST + FourPort, Accent Async, Boca (read the Boca mini-HOWTO, available + from <http://www.tldp.org/docs.html#howto>), or other custom + serial port hardware which acts similar to standard serial port + hardware. If you only use the standard COM 1/2/3/4 ports, you can + say N here to save some memory. You can also say Y if you have an + "intelligent" multiport card such as Cyclades, Digiboards, etc. + +config SERIAL_8250_SHARE_IRQ + bool "Support for sharing serial interrupts" + depends on SERIAL_8250_EXTENDED + help + Some serial boards have hardware support which allows multiple dumb + serial ports on the same board to share a single IRQ. To enable + support for this in the serial driver, say Y here. + +config SERIAL_8250_DETECT_IRQ + bool "Autodetect IRQ on standard ports (unsafe)" + depends on SERIAL_8250_EXTENDED + help + Say Y here if you want the kernel to try to guess which IRQ + to use for your serial port. + + This is considered unsafe; it is far better to configure the IRQ in + a boot script using the setserial command. + + If unsure, say N. + +config SERIAL_8250_MULTIPORT + bool "Support special multiport boards" + depends on SERIAL_8250_EXTENDED + help + Some multiport serial ports have special ports which are used to + signal when there are any serial ports on the board which need + servicing. Say Y here to enable the serial driver to take advantage + of those special I/O ports. + +config SERIAL_8250_RSA + bool "Support RSA serial ports" + depends on SERIAL_8250_EXTENDED + help + ::: To be written ::: + +comment "Non-8250 serial port support" + +config SERIAL_8250_ACORN + tristate "Acorn expansion card serial port support" + depends on ARM && ARCH_ACORN && SERIAL_8250 + help + If you have an Atomwide Serial card or Serial Port card for an Acorn + system, say Y to this option. The driver can handle 1, 2, or 3 port + cards. If unsure, say N. + +config SERIAL_AMBA_PL010 + tristate "ARM AMBA PL010 serial port support" + depends on ARM_AMBA + select SERIAL_CORE + help + This selects the ARM(R) AMBA(R) PrimeCell PL010 UART. If you have + an Integrator/AP or Integrator/PP2 platform, say Y or M here. + + If unsure, say N. + +config SERIAL_AMBA_PL010_CONSOLE + bool "Support for console on AMBA serial port" + depends on SERIAL_AMBA_PL010=y + select SERIAL_CORE_CONSOLE + ---help--- + Say Y here if you wish to use an AMBA PrimeCell UART as the system + console (the system console is the device which receives all kernel + messages and warnings and which allows logins in single user mode). + + Even if you say Y here, the currently visible framebuffer console + (/dev/tty0) will still be used as the system console by default, but + you can alter that using a kernel command line option such as + "console=ttyAM0". (Try "man bootparam" or see the documentation of + your boot loader (lilo or loadlin) about how to pass options to the + kernel at boot time.) + +config SERIAL_AMBA_PL011 + tristate "ARM AMBA PL011 serial port support" + depends on ARM_AMBA + select SERIAL_CORE + help + This selects the ARM(R) AMBA(R) PrimeCell PL011 UART. If you have + an Integrator/PP2, Integrator/CP or Versatile platform, say Y or M + here. + + If unsure, say N. + +config SERIAL_AMBA_PL011_CONSOLE + bool "Support for console on AMBA serial port" + depends on SERIAL_AMBA_PL011=y + select SERIAL_CORE_CONSOLE + ---help--- + Say Y here if you wish to use an AMBA PrimeCell UART as the system + console (the system console is the device which receives all kernel + messages and warnings and which allows logins in single user mode). + + Even if you say Y here, the currently visible framebuffer console + (/dev/tty0) will still be used as the system console by default, but + you can alter that using a kernel command line option such as + "console=ttyAM0". (Try "man bootparam" or see the documentation of + your boot loader (lilo or loadlin) about how to pass options to the + kernel at boot time.) + +config SERIAL_CLPS711X + tristate "CLPS711X serial port support" + depends on ARM && ARCH_CLPS711X + select SERIAL_CORE + help + ::: To be written ::: + +config SERIAL_CLPS711X_CONSOLE + bool "Support for console on CLPS711X serial port" + depends on SERIAL_CLPS711X=y + select SERIAL_CORE_CONSOLE + help + Even if you say Y here, the currently visible virtual console + (/dev/tty0) will still be used as the system console by default, but + you can alter that using a kernel command line option such as + "console=ttyCL1". (Try "man bootparam" or see the documentation of + your boot loader (lilo or loadlin) about how to pass options to the + kernel at boot time.) + +config SERIAL_S3C2410 + tristate "Samsung S3C2410 Serial port support" + depends on ARM && ARCH_S3C2410 + select SERIAL_CORE + help + Support for the on-chip UARTs on the Samsung S3C2410X CPU, + providing /dev/ttySAC0, 1 and 2 (note, some machines may not + provide all of these ports, depending on how the serial port + pins are configured. + +config SERIAL_S3C2410_CONSOLE + bool "Support for console on S3C2410 serial port" + depends on SERIAL_S3C2410=y + select SERIAL_CORE_CONSOLE + help + Allow selection of the S3C2410 on-board serial ports for use as + an virtual console. + + Even if you say Y here, the currently visible virtual console + (/dev/tty0) will still be used as the system console by default, but + you can alter that using a kernel command line option such as + "console=ttySACx". (Try "man bootparam" or see the documentation of + your boot loader about how to pass options to the kernel at + boot time.) + +config SERIAL_BAST_SIO + bool "Support for BAST SuperIO serial ports" + depends on ARCH_BAST && SERIAL_8250=y + help + Support for registerin the SuperIO chip on BAST board with + the 8250/16550 uart code. + +config SERIAL_DZ + bool "DECstation DZ serial driver" + depends on MACH_DECSTATION && MIPS32 + select SERIAL_CORE + help + DZ11-family serial controllers for VAXstations, including the + DC7085, M7814, and M7819. + +config SERIAL_DZ_CONSOLE + bool "Support console on DECstation DZ serial driver" + depends on SERIAL_DZ=y + select SERIAL_CORE_CONSOLE + help + If you say Y here, it will be possible to use a serial port as the + system console (the system console is the device which receives all + kernel messages and warnings and which allows logins in single user + mode). Note that the firmware uses ttyS0 as the serial console on + the Maxine and ttyS2 on the others. + + If unsure, say Y. + +config SERIAL_21285 + tristate "DC21285 serial port support" + depends on ARM && FOOTBRIDGE + select SERIAL_CORE + help + If you have a machine based on a 21285 (Footbridge) StrongARM(R)/ + PCI bridge you can enable its onboard serial port by enabling this + option. + +config SERIAL_21285_CONSOLE + bool "Console on DC21285 serial port" + depends on SERIAL_21285=y + select SERIAL_CORE_CONSOLE + help + If you have enabled the serial port on the 21285 footbridge you can + make it the console by answering Y to this option. + + Even if you say Y here, the currently visible virtual console + (/dev/tty0) will still be used as the system console by default, but + you can alter that using a kernel command line option such as + "console=ttyFB". (Try "man bootparam" or see the documentation of + your boot loader (lilo or loadlin) about how to pass options to the + kernel at boot time.) + +config SERIAL_UART00 + bool "Excalibur serial port (uart00) support" + depends on ARM && ARCH_CAMELOT + select SERIAL_CORE + help + Say Y here if you want to use the hard logic uart on Excalibur. This + driver also supports soft logic implementations of this uart core. + +config SERIAL_UART00_CONSOLE + bool "Support for console on Excalibur serial port" + depends on SERIAL_UART00 + select SERIAL_CORE_CONSOLE + help + Say Y here if you want to support a serial console on an Excalibur + hard logic uart or uart00 IP core. + + Even if you say Y here, the currently visible virtual console + (/dev/tty0) will still be used as the system console by default, but + you can alter that using a kernel command line option such as + "console=ttyS1". (Try "man bootparam" or see the documentation of + your boot loader (lilo or loadlin) about how to pass options to the + kernel at boot time.) + +config SERIAL_MPSC + bool "Marvell MPSC serial port support" + depends on PPC32 && MV64X60 + select SERIAL_CORE + help + Say Y here if you want to use the Marvell MPSC serial controller. + +config SERIAL_MPSC_CONSOLE + bool "Support for console on Marvell MPSC serial port" + depends on SERIAL_MPSC + select SERIAL_CORE_CONSOLE + help + Say Y here if you want to support a serial console on a Marvell MPSC. + +config SERIAL_PXA + bool "PXA serial port support" + depends on ARM && ARCH_PXA + select SERIAL_CORE + help + If you have a machine based on an Intel XScale PXA2xx CPU you + can enable its onboard serial ports by enabling this option. + +config SERIAL_PXA_CONSOLE + bool "Console on PXA serial port" + depends on SERIAL_PXA + select SERIAL_CORE_CONSOLE + help + If you have enabled the serial port on the Intel XScale PXA + CPU you can make it the console by answering Y to this option. + + Even if you say Y here, the currently visible virtual console + (/dev/tty0) will still be used as the system console by default, but + you can alter that using a kernel command line option such as + "console=ttySA0". (Try "man bootparam" or see the documentation of + your boot loader (lilo or loadlin) about how to pass options to the + kernel at boot time.) + +config SERIAL_SA1100 + bool "SA1100 serial port support" + depends on ARM && ARCH_SA1100 + select SERIAL_CORE + help + If you have a machine based on a SA1100/SA1110 StrongARM(R) CPU you + can enable its onboard serial port by enabling this option. + Please read <file:Documentation/arm/SA1100/serial_UART> for further + info. + +config SERIAL_SA1100_CONSOLE + bool "Console on SA1100 serial port" + depends on SERIAL_SA1100 + select SERIAL_CORE_CONSOLE + help + If you have enabled the serial port on the SA1100/SA1110 StrongARM + CPU you can make it the console by answering Y to this option. + + Even if you say Y here, the currently visible virtual console + (/dev/tty0) will still be used as the system console by default, but + you can alter that using a kernel command line option such as + "console=ttySA0". (Try "man bootparam" or see the documentation of + your boot loader (lilo or loadlin) about how to pass options to the + kernel at boot time.) + +config SERIAL_IMX + bool "IMX serial port support" + depends on ARM && ARCH_IMX + select SERIAL_CORE + help + If you have a machine based on a Motorola IMX CPU you + can enable its onboard serial port by enabling this option. + +config SERIAL_IMX_CONSOLE + bool "Console on IMX serial port" + depends on SERIAL_IMX + select SERIAL_CORE_CONSOLE + help + If you have enabled the serial port on the Motorola IMX + CPU you can make it the console by answering Y to this option. + + Even if you say Y here, the currently visible virtual console + (/dev/tty0) will still be used as the system console by default, but + you can alter that using a kernel command line option such as + "console=ttySA0". (Try "man bootparam" or see the documentation of + your boot loader (lilo or loadlin) about how to pass options to the + kernel at boot time.) + +config SERIAL_SUNCORE + bool + depends on SPARC32 || SPARC64 + select SERIAL_CORE + select SERIAL_CORE_CONSOLE + default y + +config SERIAL_SUNZILOG + tristate "Sun Zilog8530 serial support" + depends on SPARC32 || SPARC64 + help + This driver supports the Zilog8530 serial ports found on many Sparc + systems. Say Y or M if you want to be able to these serial ports. + +config SERIAL_SUNZILOG_CONSOLE + bool "Console on Sun Zilog8530 serial port" + depends on SERIAL_SUNZILOG=y + help + If you would like to be able to use the Zilog8530 serial port + on your Sparc system as the console, you can do so by answering + Y to this option. + +config SERIAL_SUNSU + tristate "Sun SU serial support" + depends on (SPARC32 || SPARC64) && PCI + help + This driver supports the 8250 serial ports that run the keyboard and + mouse on (PCI) UltraSPARC systems. Say Y or M if you want to be able + to these serial ports. + +config SERIAL_SUNSU_CONSOLE + bool "Console on Sun SU serial port" + depends on SERIAL_SUNSU=y + help + If you would like to be able to use the SU serial port + on your Sparc system as the console, you can do so by answering + Y to this option. + +config SERIAL_MUX + tristate "Serial MUX support" + depends on PARISC + select SERIAL_CORE + default y + ---help--- + Saying Y here will enable the hardware MUX serial driver for + the Nova and K class systems. The hardware MUX is not 8250/16550 + compatible therefore the /dev/ttyB0 device is shared between the + Serial MUX and the PDC software console. The following steps + need to be completed to use the Serial MUX: + + 1. create the device entry (mknod /dev/ttyB0 c 11 0) + 2. Edit the /etc/inittab to start a getty listening on /dev/ttyB0 + 3. Add device ttyB0 to /etc/securetty (if you want to log on as + root on this console.) + 4. Change the kernel command console parameter to: console=ttyB0 + +config SERIAL_MUX_CONSOLE + bool "Support for console on serial MUX" + depends on SERIAL_MUX + select SERIAL_CORE_CONSOLE + default y + +config PDC_CONSOLE + bool "PDC software console support" + depends on PARISC && !SERIAL_MUX && VT + default n + help + Saying Y here will enable the software based PDC console to be + used as the system console. This is useful for machines in + which the hardware based console has not been written yet. The + following steps must be competed to use the PDC console: + + 1. create the device entry (mknod /dev/ttyB0 c 11 0) + 2. Edit the /etc/inittab to start a getty listening on /dev/ttyB0 + 3. Add device ttyB0 to /etc/securetty (if you want to log on as + root on this console.) + 4. Change the kernel command console parameter to: console=ttyB0 + +config SERIAL_SUNSAB + tristate "Sun Siemens SAB82532 serial support" + depends on (SPARC32 || SPARC64) && PCI + help + This driver supports the Siemens SAB82532 DUSCC serial ports on newer + (PCI) UltraSPARC systems. Say Y or M if you want to be able to these + serial ports. + +config SERIAL_SUNSAB_CONSOLE + bool "Console on Sun Siemens SAB82532 serial port" + depends on SERIAL_SUNSAB=y + help + If you would like to be able to use the SAB82532 serial port + on your Sparc system as the console, you can do so by answering + Y to this option. + +config SERIAL_IP22_ZILOG + tristate "IP22 Zilog8530 serial support" + depends on SGI_IP22 + select SERIAL_CORE + help + This driver supports the Zilog8530 serial ports found on SGI IP22 + systems. Say Y or M if you want to be able to these serial ports. + +config SERIAL_IP22_ZILOG_CONSOLE + bool "Console on IP22 Zilog8530 serial port" + depends on SERIAL_IP22_ZILOG=y + select SERIAL_CORE_CONSOLE + +config V850E_UART + bool "NEC V850E on-chip UART support" + depends on V850E_MA1 || V850E_ME2 || V850E_TEG || V850E2_ANNA || V850E_AS85EP1 + select SERIAL_CORE + default y + +config V850E_UARTB + bool + depends V850E_UART && V850E_ME2 + default y + +config V850E_UART_CONSOLE + bool "Use NEC V850E on-chip UART for console" + depends on V850E_UART + select SERIAL_CORE_CONSOLE + +config SERIAL_SH_SCI + tristate "SH SCI(F) serial port support" + depends on SUPERH || H8300 + select SERIAL_CORE + +config SERIAL_SH_SCI_CONSOLE + bool "Support for console on SH SCI(F)" + depends on SERIAL_SH_SCI=y + select SERIAL_CORE_CONSOLE + +config SERIAL_AU1X00 + bool "Enable Au1x00 UART Support" + depends on MIPS && SOC_AU1X00 + select SERIAL_CORE + help + If you have an Alchemy AU1X00 processor (MIPS based) and you want + to use serial ports, say Y. Otherwise, say N. + +config SERIAL_AU1X00_CONSOLE + bool "Enable Au1x00 serial console" + depends on SERIAL_AU1X00 + select SERIAL_CORE_CONSOLE + help + If you have an Alchemy AU1X00 processor (MIPS based) and you want + to use a console on a serial port, say Y. Otherwise, say N. + +config SERIAL_CORE + tristate + +config SERIAL_CORE_CONSOLE + bool + +config SERIAL_68328 + bool "68328 serial support" + depends on M68328 || M68EZ328 || M68VZ328 + help + This driver supports the built-in serial port of the Motorola 68328 + (standard, EZ and VZ varities). + +config SERIAL_68328_RTS_CTS + bool "Support RTS/CTS on 68328 serial port" + depends on SERIAL_68328 + +config SERIAL_COLDFIRE + bool "ColdFire serial support" + depends on COLDFIRE + help + This driver supports the built-in serial ports of the Motorola ColdFire + family of CPUs. + +config SERIAL_68360_SMC + bool "68360 SMC uart support" + depends on M68360 + help + This driver supports the SMC serial ports of the Motorola 68360 CPU. + +config SERIAL_68360_SCC + bool "68360 SCC uart support" + depends on M68360 + help + This driver supports the SCC serial ports of the Motorola 68360 CPU. + +config SERIAL_68360 + bool + depends on SERIAL_68360_SMC || SERIAL_68360_SCC + default y + +config SERIAL_PMACZILOG + tristate "PowerMac z85c30 ESCC support" + depends on PPC_OF && PPC_PMAC + select SERIAL_CORE + help + This driver supports the Zilog z85C30 serial ports found on + PowerMac machines. + Say Y or M if you want to be able to these serial ports. + +config SERIAL_PMACZILOG_CONSOLE + bool "Console on PowerMac z85c30 serial port" + depends on SERIAL_PMACZILOG=y + select SERIAL_CORE_CONSOLE + help + If you would like to be able to use the z85c30 serial port + on your PowerMac as the console, you can do so by answering + Y to this option. + +config SERIAL_LH7A40X + tristate "Sharp LH7A40X embedded UART support" + depends on ARM && ARCH_LH7A40X + select SERIAL_CORE + help + This enables support for the three on-board UARTs of the + Sharp LH7A40X series CPUs. Choose Y or M. + +config SERIAL_LH7A40X_CONSOLE + bool "Support for console on Sharp LH7A40X serial port" + depends on SERIAL_LH7A40X=y + select SERIAL_CORE_CONSOLE + help + Say Y here if you wish to use one of the serial ports as the + system console--the system console is the device which + receives all kernel messages and warnings and which allows + logins in single user mode. + + Even if you say Y here, the currently visible framebuffer console + (/dev/tty0) will still be used as the default system console, but + you can alter that using a kernel command line, for example + "console=ttyAM1". + +config SERIAL_CPM + tristate "CPM SCC/SMC serial port support" + depends on CPM2 || 8xx + select SERIAL_CORE + help + This driver supports the SCC and SMC serial ports on Motorola + embedded PowerPC that contain a CPM1 (8xx) or CPM2 (8xxx) + +config SERIAL_CPM_CONSOLE + bool "Support for console on CPM SCC/SMC serial port" + depends on SERIAL_CPM=y + select SERIAL_CORE_CONSOLE + help + Say Y here if you wish to use a SCC or SMC CPM UART as the system + console (the system console is the device which receives all kernel + messages and warnings and which allows logins in single user mode). + + Even if you say Y here, the currently visible framebuffer console + (/dev/tty0) will still be used as the system console by default, but + you can alter that using a kernel command line option such as + "console=ttyCPM0". (Try "man bootparam" or see the documentation of + your boot loader (lilo or loadlin) about how to pass options to the + kernel at boot time.) + +config SERIAL_CPM_SCC1 + bool "Support for SCC1 serial port" + depends on SERIAL_CPM=y + help + Select the is option to use SCC1 as a serial port + +config SERIAL_CPM_SCC2 + bool "Support for SCC2 serial port" + depends on SERIAL_CPM=y + help + Select the is option to use SCC2 as a serial port + +config SERIAL_CPM_SCC3 + bool "Support for SCC3 serial port" + depends on SERIAL_CPM=y + help + Select the is option to use SCC3 as a serial port + +config SERIAL_CPM_SCC4 + bool "Support for SCC4 serial port" + depends on SERIAL_CPM=y + help + Select the is option to use SCC4 as a serial port + +config SERIAL_CPM_SMC1 + bool "Support for SMC1 serial port" + depends on SERIAL_CPM=y + help + Select the is option to use SMC1 as a serial port + +config SERIAL_CPM_SMC2 + bool "Support for SMC2 serial port" + depends on SERIAL_CPM=y + help + Select the is option to use SMC2 as a serial port + +config SERIAL_SGI_L1_CONSOLE + bool "SGI Altix L1 serial console support" + depends on IA64_GENERIC || IA64_SGI_SN2 + select SERIAL_CORE + select SERIAL_CORE_CONSOLE + help + If you have an SGI Altix and you would like to use the system + controller serial port as your console (you want this!), + say Y. Otherwise, say N. + +config SERIAL_MPC52xx + tristate "Freescale MPC52xx family PSC serial support" + depends on PPC_MPC52xx + select SERIAL_CORE + help + This drivers support the MPC52xx PSC serial ports. If you would + like to use them, you must answer Y or M to this option. Not that + for use as console, it must be included in kernel and not as a + module. + +config SERIAL_MPC52xx_CONSOLE + bool "Console on a Freescale MPC52xx family PSC serial port" + depends on SERIAL_MPC52xx=y + select SERIAL_CORE_CONSOLE + help + Select this options if you'd like to use one of the PSC serial port + of the Freescale MPC52xx family as a console. + +config SERIAL_MPC52xx_CONSOLE_BAUD + int "Freescale MPC52xx family PSC serial port baud" + depends on SERIAL_MPC52xx_CONSOLE=y + default "9600" + help + Select the MPC52xx console baud rate. + This value is only used if the bootloader doesn't pass in the + console baudrate + +config SERIAL_ICOM + tristate "IBM Multiport Serial Adapter" + depends on PPC_ISERIES || PPC_PSERIES + select SERIAL_CORE + help + This driver is for a family of multiport serial adapters + including 2 port RVX, 2 port internal modem, 4 port internal + modem and a split 1 port RVX and 1 port internal modem. + + This driver can also be built as a module. If so, the module + will be called icom. + +config SERIAL_M32R_SIO + bool "M32R SIO I/F" + depends on M32R + default y + select SERIAL_CORE + help + Say Y here if you want to use the M32R serial controller. + +config SERIAL_M32R_SIO_CONSOLE + bool "use SIO console" + depends on SERIAL_M32R_SIO=y + select SERIAL_CORE_CONSOLE + help + Say Y here if you want to support a serial console. + + If you use an M3T-M32700UT or an OPSPUT platform, + please say also y for SERIAL_M32R_PLDSIO. + +config SERIAL_M32R_PLDSIO + bool "M32R SIO I/F on a PLD" + depends on SERIAL_M32R_SIO=y + default n + help + Say Y here if you want to use the M32R serial controller + on a PLD (Programmable Logic Device). + + If you use an M3T-M32700UT or an OPSPUT platform, + please say Y. + +config SERIAL_TXX9 + bool "TMPTX39XX/49XX SIO support" + depends HAS_TXX9_SERIAL + select SERIAL_CORE + default y + +config HAS_TXX9_SERIAL + bool + +config SERIAL_TXX9_CONSOLE + bool "TMPTX39XX/49XX SIO Console support" + depends on SERIAL_TXX9=y + select SERIAL_CORE_CONSOLE + +config SERIAL_TXX9_STDSERIAL + bool "TX39XX/49XX SIO act as standard serial" + depends on !SERIAL_8250 && SERIAL_TXX9 + +config SERIAL_VR41XX + tristate "NEC VR4100 series Serial Interface Unit support" + depends on CPU_VR41XX + select SERIAL_CORE + help + If you have a NEC VR4100 series processor and you want to use + Serial Interface Unit(SIU) or Debug Serial Interface Unit(DSIU) + (not include VR4111/VR4121 DSIU), say Y. Otherwise, say N. + +config SERIAL_VR41XX_CONSOLE + bool "Enable NEC VR4100 series Serial Interface Unit console" + depends on SERIAL_VR41XX + select SERIAL_CORE_CONSOLE + help + If you have a NEC VR4100 series processor and you want to use + a console on a serial port, say Y. Otherwise, say N. + +config SERIAL_JSM + tristate "Digi International NEO PCI Support" + depends on PCI + select SERIAL_CORE + help + This is a driver for Digi International's Neo series + of cards which provide multiple serial ports. You would need + something like this to connect more than two modems to your Linux + box, for instance in order to become a dial-in server. This driver + supports PCI boards only. + If you have a card like this, say Y here and read the file + <file:Documentation/jsm.txt>. + + To compile this driver as a module, choose M here: the + module will be called jsm. + +endmenu diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/Kconfig --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/Kconfig Mon Jan 30 17:18:27 2006 @@ -0,0 +1,175 @@ +# +# This Kconfig describe xen options +# + +mainmenu "Xen Configuration" + +config XEN + bool + default y if X86_XEN || X86_64_XEN + help + This is the Linux Xen port. + +config NO_IDLE_HZ + bool + depends on XEN + default y + +if XEN +menu "XEN" + +config XEN_PRIVILEGED_GUEST + bool "Privileged Guest (domain 0)" + depends XEN + default n + select XEN_PHYSDEV_ACCESS + help + Support for privileged operation (domain 0) + +config XEN_UNPRIVILEGED_GUEST + bool + default !XEN_PRIVILEGED_GUEST + +config XEN_PHYSDEV_ACCESS + bool "Physical device access" + depends XEN_PRIVILEGED_GUEST + default XEN_PRIVILEGED_GUEST + help + Assume access is available to physical hardware devices + (e.g., hard drives, network cards). This allows you to configure + such devices and also includes some low-level support that is + otherwise not compiled into the kernel. + +config XEN_BLKDEV_BACKEND + bool "Block-device backend driver" + depends on XEN_PHYSDEV_ACCESS + default y + help + The block-device backend driver allows the kernel to export its + block devices to other guests via a high-performance shared-memory + interface. + +config XEN_BLKDEV_TAP_BE + bool "Block Tap support for backend driver (DANGEROUS)" + depends on XEN_BLKDEV_BACKEND + default n + help + If you intend to use the block tap driver, the backend domain will + not know the domain id of the real frontend, and so will not be able + to map its data pages. This modifies the backend to attempt to map + from both the tap domain and the real frontend. This presents a + security risk, and so should ONLY be used for development + with the blktap. This option will be removed as the block drivers are + modified to use grant tables. + +config XEN_NETDEV_BACKEND + bool "Network-device backend driver" + depends on XEN_PHYSDEV_ACCESS + default y + help + The network-device backend driver allows the kernel to export its + network devices to other guests via a high-performance shared-memory + interface. + +config XEN_NETDEV_PIPELINED_TRANSMITTER + bool "Pipelined transmitter (DANGEROUS)" + depends on XEN_NETDEV_BACKEND + default n + help + If the net backend is a dumb domain, such as a transparent Ethernet + bridge with no local IP interface, it is safe to say Y here to get + slightly lower network overhead. + If the backend has a local IP interface; or may be doing smart things + like reassembling packets to perform firewall filtering; or if you + are unsure; or if you experience network hangs when this option is + enabled; then you must say N here. + +config XEN_TPMDEV_BACKEND + bool "TPM-device backend driver" + depends on XEN_PHYSDEV_ACCESS + default n + help + The TPM-device backend driver + +config XEN_TPMDEV_CLOSE_IF_VTPM_FAILS + bool "TPM backend closes upon vTPM failure" + depends on XEN_TPMDEV_BACKEND + default n + help + The TPM backend closes the channel if the vTPM in userspace indicates + a failure. The corresponding domain's channel will be closed. + Say Y if you want this feature. + +config XEN_BLKDEV_FRONTEND + tristate "Block-device frontend driver" + depends on XEN + default y + help + The block-device frontend driver allows the kernel to access block + devices mounted within another guest OS. Unless you are building a + dedicated device-driver domain, or your master control domain + (domain 0), then you almost certainly want to say Y here. + +config XEN_NETDEV_FRONTEND + tristate "Network-device frontend driver" + depends on XEN + default y + help + The network-device frontend driver allows the kernel to access + network interfaces within another guest OS. Unless you are building a + dedicated device-driver domain, or your master control domain + (domain 0), then you almost certainly want to say Y here. + +config XEN_BLKDEV_TAP + bool "Block device tap driver" + default n + help + This driver allows a VM to interact on block device channels + to other VMs. Block messages may be passed through or redirected + to a character device, allowing device prototyping in application + space. Odds are that you want to say N here. + +config XEN_TPMDEV_FRONTEND + bool "TPM-device frontend driver" + default n + select TCG_TPM + select TCG_XEN + help + The TPM-device frontend driver. + +config XEN_SHADOW_MODE + bool "Fake shadow mode" + default n + help + fakes out a shadow mode kernel + + +config XEN_SCRUB_PAGES + bool "Scrub memory before freeing it to Xen" + default y + help + Erase memory contents before freeing it back to Xen's global + pool. This ensures that any secrets contained within that + memory (e.g., private keys) cannot be found by other guests that + may be running on the machine. Most people will want to say Y here. + If security is not a concern then you may increase performance by + saying N. + +config XEN_DISABLE_SERIAL + bool "Disable serial port drivers" + default y + help + Disable serial port drivers, allowing the Xen console driver + to provide a serial console at ttyS0. + +endmenu + +config HAVE_ARCH_ALLOC_SKB + bool + default y + +config HAVE_ARCH_DEV_ALLOC_SKB + bool + default y + +endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/core/Makefile --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/core/Makefile Mon Jan 30 17:18:27 2006 @@ -0,0 +1,9 @@ +# +# Makefile for the linux kernel. +# + +obj-y := evtchn.o reboot.o gnttab.o features.o + +obj-$(CONFIG_PROC_FS) += xen_proc.o +obj-$(CONFIG_NET) += skbuff.o +obj-$(CONFIG_SMP) += smpboot.o diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/core/evtchn.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/core/evtchn.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,820 @@ +/****************************************************************************** + * evtchn.c + * + * Communication via Xen event channels. + * + * Copyright (c) 2002-2005, K A Fraser + * + * This file may be distributed separately from the Linux kernel, or + * incorporated into other software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/irq.h> +#include <linux/interrupt.h> +#include <linux/sched.h> +#include <linux/kernel_stat.h> +#include <linux/version.h> +#include <asm/atomic.h> +#include <asm/system.h> +#include <asm/ptrace.h> +#include <asm/synch_bitops.h> +#include <xen/interface/event_channel.h> +#include <xen/interface/physdev.h> +#include <asm/hypervisor.h> +#include <xen/evtchn.h> +#include <linux/mc146818rtc.h> /* RTC_IRQ */ + +/* + * This lock protects updates to the following mapping and reference-count + * arrays. The lock does not need to be acquired to read the mapping tables. + */ +static spinlock_t irq_mapping_update_lock; + +/* IRQ <-> event-channel mappings. */ +static int evtchn_to_irq[NR_EVENT_CHANNELS]; + +/* Packed IRQ information: binding type, sub-type index, and event channel. */ +static u32 irq_info[NR_IRQS]; +/* Binding types. */ +enum { IRQT_UNBOUND, IRQT_PIRQ, IRQT_VIRQ, IRQT_IPI, IRQT_EVTCHN }; +/* Constructor for packed IRQ information. */ +#define mk_irq_info(type, index, evtchn) \ + (((u32)(type) << 24) | ((u32)(index) << 16) | (u32)(evtchn)) +/* Convenient shorthand for packed representation of an unbound IRQ. */ +#define IRQ_UNBOUND mk_irq_info(IRQT_UNBOUND, 0, 0) +/* Accessor macros for packed IRQ information. */ +#define evtchn_from_irq(irq) ((u16)(irq_info[irq])) +#define index_from_irq(irq) ((u8)(irq_info[irq] >> 16)) +#define type_from_irq(irq) ((u8)(irq_info[irq] >> 24)) + +/* IRQ <-> VIRQ mapping. */ +DEFINE_PER_CPU(int, virq_to_irq[NR_VIRQS]); + +/* IRQ <-> IPI mapping. */ +#ifndef NR_IPIS +#define NR_IPIS 1 +#endif +DEFINE_PER_CPU(int, ipi_to_irq[NR_IPIS]); + +/* Reference counts for bindings to IRQs. */ +static int irq_bindcount[NR_IRQS]; + +/* Bitmap indicating which PIRQs require Xen to be notified on unmask. */ +static unsigned long pirq_needs_unmask_notify[NR_PIRQS/sizeof(unsigned long)]; + +#ifdef CONFIG_SMP + +static u8 cpu_evtchn[NR_EVENT_CHANNELS]; +static unsigned long cpu_evtchn_mask[NR_CPUS][NR_EVENT_CHANNELS/BITS_PER_LONG]; + +#define active_evtchns(cpu,sh,idx) \ + ((sh)->evtchn_pending[idx] & \ + cpu_evtchn_mask[cpu][idx] & \ + ~(sh)->evtchn_mask[idx]) + +static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu) +{ + clear_bit(chn, (unsigned long *)cpu_evtchn_mask[cpu_evtchn[chn]]); + set_bit(chn, (unsigned long *)cpu_evtchn_mask[cpu]); + cpu_evtchn[chn] = cpu; +} + +static void init_evtchn_cpu_bindings(void) +{ + /* By default all event channels notify CPU#0. */ + memset(cpu_evtchn, 0, sizeof(cpu_evtchn)); + memset(cpu_evtchn_mask[0], ~0, sizeof(cpu_evtchn_mask[0])); +} + +#define cpu_from_evtchn(evtchn) (cpu_evtchn[evtchn]) + +#else + +#define active_evtchns(cpu,sh,idx) \ + ((sh)->evtchn_pending[idx] & \ + ~(sh)->evtchn_mask[idx]) +#define bind_evtchn_to_cpu(chn,cpu) ((void)0) +#define init_evtchn_cpu_bindings() ((void)0) +#define cpu_from_evtchn(evtchn) (0) + +#endif + +/* Upcall to generic IRQ layer. */ +#ifdef CONFIG_X86 +extern fastcall unsigned int do_IRQ(struct pt_regs *regs); +#if defined (__i386__) +#define IRQ_REG orig_eax +#elif defined (__x86_64__) +#define IRQ_REG orig_rax +#endif +#define do_IRQ(irq, regs) do { \ + (regs)->IRQ_REG = (irq); \ + do_IRQ((regs)); \ +} while (0) +#endif + +/* Xen will never allocate port zero for any purpose. */ +#define VALID_EVTCHN(chn) ((chn) != 0) + +/* + * Force a proper event-channel callback from Xen after clearing the + * callback mask. We do this in a very simple manner, by making a call + * down into Xen. The pending flag will be checked by Xen on return. + */ +void force_evtchn_callback(void) +{ + (void)HYPERVISOR_xen_version(0, NULL); +} +EXPORT_SYMBOL(force_evtchn_callback); + +/* NB. Interrupts are disabled on entry. */ +asmlinkage void evtchn_do_upcall(struct pt_regs *regs) +{ + unsigned long l1, l2; + unsigned int l1i, l2i, port; + int irq, cpu = smp_processor_id(); + shared_info_t *s = HYPERVISOR_shared_info; + vcpu_info_t *vcpu_info = &s->vcpu_info[cpu]; + + vcpu_info->evtchn_upcall_pending = 0; + + /* NB. No need for a barrier here -- XCHG is a barrier on x86. */ + l1 = xchg(&vcpu_info->evtchn_pending_sel, 0); + while (l1 != 0) { + l1i = __ffs(l1); + l1 &= ~(1UL << l1i); + + while ((l2 = active_evtchns(cpu, s, l1i)) != 0) { + l2i = __ffs(l2); + + port = (l1i * BITS_PER_LONG) + l2i; + if ((irq = evtchn_to_irq[port]) != -1) + do_IRQ(irq, regs); + else + evtchn_device_upcall(port); + } + } +} +EXPORT_SYMBOL(evtchn_do_upcall); + +static int find_unbound_irq(void) +{ + int irq; + + for (irq = 0; irq < NR_IRQS; irq++) + if (irq_bindcount[irq] == 0) + break; + + if (irq == NR_IRQS) + panic("No available IRQ to bind to: increase NR_IRQS!\n"); + + return irq; +} + +static int bind_evtchn_to_irq(unsigned int evtchn) +{ + int irq; + + spin_lock(&irq_mapping_update_lock); + + if ((irq = evtchn_to_irq[evtchn]) == -1) { + irq = find_unbound_irq(); + evtchn_to_irq[evtchn] = irq; + irq_info[irq] = mk_irq_info(IRQT_EVTCHN, 0, evtchn); + } + + irq_bindcount[irq]++; + + spin_unlock(&irq_mapping_update_lock); + + return irq; +} + +static int bind_virq_to_irq(unsigned int virq, unsigned int cpu) +{ + evtchn_op_t op = { .cmd = EVTCHNOP_bind_virq }; + int evtchn, irq; + + spin_lock(&irq_mapping_update_lock); + + if ((irq = per_cpu(virq_to_irq, cpu)[virq]) == -1) { + op.u.bind_virq.virq = virq; + op.u.bind_virq.vcpu = cpu; + BUG_ON(HYPERVISOR_event_channel_op(&op) != 0); + evtchn = op.u.bind_virq.port; + + irq = find_unbound_irq(); + evtchn_to_irq[evtchn] = irq; + irq_info[irq] = mk_irq_info(IRQT_VIRQ, virq, evtchn); + + per_cpu(virq_to_irq, cpu)[virq] = irq; + + bind_evtchn_to_cpu(evtchn, cpu); + } + + irq_bindcount[irq]++; + + spin_unlock(&irq_mapping_update_lock); + + return irq; +} + +static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu) +{ + evtchn_op_t op = { .cmd = EVTCHNOP_bind_ipi }; + int evtchn, irq; + + spin_lock(&irq_mapping_update_lock); + + if ((irq = per_cpu(ipi_to_irq, cpu)[ipi]) == -1) { + op.u.bind_ipi.vcpu = cpu; + BUG_ON(HYPERVISOR_event_channel_op(&op) != 0); + evtchn = op.u.bind_ipi.port; + + irq = find_unbound_irq(); + evtchn_to_irq[evtchn] = irq; + irq_info[irq] = mk_irq_info(IRQT_IPI, ipi, evtchn); + + per_cpu(ipi_to_irq, cpu)[ipi] = irq; + + bind_evtchn_to_cpu(evtchn, cpu); + } + + irq_bindcount[irq]++; + + spin_unlock(&irq_mapping_update_lock); + + return irq; +} + +static void unbind_from_irq(unsigned int irq) +{ + evtchn_op_t op = { .cmd = EVTCHNOP_close }; + int evtchn = evtchn_from_irq(irq); + + spin_lock(&irq_mapping_update_lock); + + if ((--irq_bindcount[irq] == 0) && VALID_EVTCHN(evtchn)) { + op.u.close.port = evtchn; + BUG_ON(HYPERVISOR_event_channel_op(&op) != 0); + + switch (type_from_irq(irq)) { + case IRQT_VIRQ: + per_cpu(virq_to_irq, cpu_from_evtchn(evtchn)) + [index_from_irq(irq)] = -1; + break; + case IRQT_IPI: + per_cpu(ipi_to_irq, cpu_from_evtchn(evtchn)) + [index_from_irq(irq)] = -1; + break; + default: + break; + } + + /* Closed ports are implicitly re-bound to VCPU0. */ + bind_evtchn_to_cpu(evtchn, 0); + + evtchn_to_irq[evtchn] = -1; + irq_info[irq] = IRQ_UNBOUND; + } + + spin_unlock(&irq_mapping_update_lock); +} + +int bind_evtchn_to_irqhandler( + unsigned int evtchn, + irqreturn_t (*handler)(int, void *, struct pt_regs *), + unsigned long irqflags, + const char *devname, + void *dev_id) +{ + unsigned int irq; + int retval; + + irq = bind_evtchn_to_irq(evtchn); + retval = request_irq(irq, handler, irqflags, devname, dev_id); + if (retval != 0) { + unbind_from_irq(irq); + return retval; + } + + return irq; +} +EXPORT_SYMBOL(bind_evtchn_to_irqhandler); + +int bind_virq_to_irqhandler( + unsigned int virq, + unsigned int cpu, + irqreturn_t (*handler)(int, void *, struct pt_regs *), + unsigned long irqflags, + const char *devname, + void *dev_id) +{ + unsigned int irq; + int retval; + + irq = bind_virq_to_irq(virq, cpu); + retval = request_irq(irq, handler, irqflags, devname, dev_id); + if (retval != 0) { + unbind_from_irq(irq); + return retval; + } + + return irq; +} +EXPORT_SYMBOL(bind_virq_to_irqhandler); + +int bind_ipi_to_irqhandler( + unsigned int ipi, + unsigned int cpu, + irqreturn_t (*handler)(int, void *, struct pt_regs *), + unsigned long irqflags, + const char *devname, + void *dev_id) +{ + unsigned int irq; + int retval; + + irq = bind_ipi_to_irq(ipi, cpu); + retval = request_irq(irq, handler, irqflags, devname, dev_id); + if (retval != 0) { + unbind_from_irq(irq); + return retval; + } + + return irq; +} +EXPORT_SYMBOL(bind_ipi_to_irqhandler); + +void unbind_from_irqhandler(unsigned int irq, void *dev_id) +{ + free_irq(irq, dev_id); + unbind_from_irq(irq); +} +EXPORT_SYMBOL(unbind_from_irqhandler); + +#ifdef CONFIG_SMP +static void do_nothing_function(void *ign) +{ +} +#endif + +/* Rebind an evtchn so that it gets delivered to a specific cpu */ +static void rebind_irq_to_cpu(unsigned irq, unsigned tcpu) +{ + evtchn_op_t op = { .cmd = EVTCHNOP_bind_vcpu }; + int evtchn; + + spin_lock(&irq_mapping_update_lock); + + evtchn = evtchn_from_irq(irq); + if (!VALID_EVTCHN(evtchn)) { + spin_unlock(&irq_mapping_update_lock); + return; + } + + /* Send future instances of this interrupt to other vcpu. */ + op.u.bind_vcpu.port = evtchn; + op.u.bind_vcpu.vcpu = tcpu; + + /* + * If this fails, it usually just indicates that we're dealing with a + * virq or IPI channel, which don't actually need to be rebound. Ignore + * it, but don't do the xenlinux-level rebind in that case. + */ + if (HYPERVISOR_event_channel_op(&op) >= 0) + bind_evtchn_to_cpu(evtchn, tcpu); + + spin_unlock(&irq_mapping_update_lock); + + /* + * Now send the new target processor a NOP IPI. When this returns, it + * will check for any pending interrupts, and so service any that got + * delivered to the wrong processor by mistake. + * + * XXX: The only time this is called with interrupts disabled is from + * the hotplug/hotunplug path. In that case, all cpus are stopped with + * interrupts disabled, and the missed interrupts will be picked up + * when they start again. This is kind of a hack. + */ + if (!irqs_disabled()) + smp_call_function(do_nothing_function, NULL, 0, 0); +} + + +static void set_affinity_irq(unsigned irq, cpumask_t dest) +{ + unsigned tcpu = first_cpu(dest); + rebind_irq_to_cpu(irq, tcpu); +} + +/* + * Interface to generic handling in irq.c + */ + +static unsigned int startup_dynirq(unsigned int irq) +{ + int evtchn = evtchn_from_irq(irq); + + if (VALID_EVTCHN(evtchn)) + unmask_evtchn(evtchn); + return 0; +} + +static void shutdown_dynirq(unsigned int irq) +{ + int evtchn = evtchn_from_irq(irq); + + if (VALID_EVTCHN(evtchn)) + mask_evtchn(evtchn); +} + +static void enable_dynirq(unsigned int irq) +{ + int evtchn = evtchn_from_irq(irq); + + if (VALID_EVTCHN(evtchn)) + unmask_evtchn(evtchn); +} + +static void disable_dynirq(unsigned int irq) +{ + int evtchn = evtchn_from_irq(irq); + + if (VALID_EVTCHN(evtchn)) + mask_evtchn(evtchn); +} + +static void ack_dynirq(unsigned int irq) +{ + int evtchn = evtchn_from_irq(irq); + + if (VALID_EVTCHN(evtchn)) { + mask_evtchn(evtchn); + clear_evtchn(evtchn); + } +} + +static void end_dynirq(unsigned int irq) +{ + int evtchn = evtchn_from_irq(irq); + + if (VALID_EVTCHN(evtchn) && !(irq_desc[irq].status & IRQ_DISABLED)) + unmask_evtchn(evtchn); +} + +static struct hw_interrupt_type dynirq_type = { + "Dynamic-irq", + startup_dynirq, + shutdown_dynirq, + enable_dynirq, + disable_dynirq, + ack_dynirq, + end_dynirq, + set_affinity_irq +}; + +static inline void pirq_unmask_notify(int pirq) +{ + physdev_op_t op; + if (unlikely(test_bit(pirq, &pirq_needs_unmask_notify[0]))) { + op.cmd = PHYSDEVOP_IRQ_UNMASK_NOTIFY; + (void)HYPERVISOR_physdev_op(&op); + } +} + +static inline void pirq_query_unmask(int pirq) +{ + physdev_op_t op; + op.cmd = PHYSDEVOP_IRQ_STATUS_QUERY; + op.u.irq_status_query.irq = pirq; + (void)HYPERVISOR_physdev_op(&op); + clear_bit(pirq, &pirq_needs_unmask_notify[0]); + if (op.u.irq_status_query.flags & PHYSDEVOP_IRQ_NEEDS_UNMASK_NOTIFY) + set_bit(pirq, &pirq_needs_unmask_notify[0]); +} + +/* + * On startup, if there is no action associated with the IRQ then we are + * probing. In this case we should not share with others as it will confuse us. + */ +#define probing_irq(_irq) (irq_desc[(_irq)].action == NULL) + +static unsigned int startup_pirq(unsigned int irq) +{ + evtchn_op_t op = { .cmd = EVTCHNOP_bind_pirq }; + int evtchn = evtchn_from_irq(irq); + + if (VALID_EVTCHN(evtchn)) + goto out; + + op.u.bind_pirq.pirq = irq; + /* NB. We are happy to share unless we are probing. */ + op.u.bind_pirq.flags = probing_irq(irq) ? 0 : BIND_PIRQ__WILL_SHARE; + if (HYPERVISOR_event_channel_op(&op) != 0) { + if ( !probing_irq(irq) ) + printk(KERN_INFO "Failed to obtain physical " + "IRQ %d\n", irq); + return 0; + } + evtchn = op.u.bind_pirq.port; + + pirq_query_unmask(irq_to_pirq(irq)); + + bind_evtchn_to_cpu(evtchn, 0); + evtchn_to_irq[evtchn] = irq; + irq_info[irq] = mk_irq_info(IRQT_PIRQ, irq, evtchn); + + out: + unmask_evtchn(evtchn); + pirq_unmask_notify(irq_to_pirq(irq)); + + return 0; +} + +static void shutdown_pirq(unsigned int irq) +{ + evtchn_op_t op = { .cmd = EVTCHNOP_close }; + int evtchn = evtchn_from_irq(irq); + + if (!VALID_EVTCHN(evtchn)) + return; + + mask_evtchn(evtchn); + + op.u.close.port = evtchn; + BUG_ON(HYPERVISOR_event_channel_op(&op) != 0); + + bind_evtchn_to_cpu(evtchn, 0); + evtchn_to_irq[evtchn] = -1; + irq_info[irq] = IRQ_UNBOUND; +} + +static void enable_pirq(unsigned int irq) +{ + int evtchn = evtchn_from_irq(irq); + + if (VALID_EVTCHN(evtchn)) { + unmask_evtchn(evtchn); + pirq_unmask_notify(irq_to_pirq(irq)); + } +} + +static void disable_pirq(unsigned int irq) +{ + int evtchn = evtchn_from_irq(irq); + + if (VALID_EVTCHN(evtchn)) + mask_evtchn(evtchn); +} + +static void ack_pirq(unsigned int irq) +{ + int evtchn = evtchn_from_irq(irq); + + if (VALID_EVTCHN(evtchn)) { + mask_evtchn(evtchn); + clear_evtchn(evtchn); + } +} + +static void end_pirq(unsigned int irq) +{ + int evtchn = evtchn_from_irq(irq); + + if (VALID_EVTCHN(evtchn) && !(irq_desc[irq].status & IRQ_DISABLED)) { + unmask_evtchn(evtchn); + pirq_unmask_notify(irq_to_pirq(irq)); + } +} + +static struct hw_interrupt_type pirq_type = { + "Phys-irq", + startup_pirq, + shutdown_pirq, + enable_pirq, + disable_pirq, + ack_pirq, + end_pirq, + set_affinity_irq +}; + +void hw_resend_irq(struct hw_interrupt_type *h, unsigned int i) +{ + int evtchn = evtchn_from_irq(i); + shared_info_t *s = HYPERVISOR_shared_info; + if (!VALID_EVTCHN(evtchn)) + return; + BUG_ON(!synch_test_bit(evtchn, &s->evtchn_mask[0])); + synch_set_bit(evtchn, &s->evtchn_pending[0]); +} + +void notify_remote_via_irq(int irq) +{ + int evtchn = evtchn_from_irq(irq); + + if (VALID_EVTCHN(evtchn)) + notify_remote_via_evtchn(evtchn); +} +EXPORT_SYMBOL(notify_remote_via_irq); + +void mask_evtchn(int port) +{ + shared_info_t *s = HYPERVISOR_shared_info; + synch_set_bit(port, &s->evtchn_mask[0]); +} +EXPORT_SYMBOL(mask_evtchn); + +void unmask_evtchn(int port) +{ + shared_info_t *s = HYPERVISOR_shared_info; + unsigned int cpu = smp_processor_id(); + vcpu_info_t *vcpu_info = &s->vcpu_info[cpu]; + + /* Slow path (hypercall) if this is a non-local port. */ + if (unlikely(cpu != cpu_from_evtchn(port))) { + evtchn_op_t op = { .cmd = EVTCHNOP_unmask, + .u.unmask.port = port }; + (void)HYPERVISOR_event_channel_op(&op); + return; + } + + synch_clear_bit(port, &s->evtchn_mask[0]); + + /* + * The following is basically the equivalent of 'hw_resend_irq'. Just + * like a real IO-APIC we 'lose the interrupt edge' if the channel is + * masked. + */ + if (synch_test_bit(port, &s->evtchn_pending[0]) && + !synch_test_and_set_bit(port / BITS_PER_LONG, + &vcpu_info->evtchn_pending_sel)) { + vcpu_info->evtchn_upcall_pending = 1; + if (!vcpu_info->evtchn_upcall_mask) + force_evtchn_callback(); + } +} +EXPORT_SYMBOL(unmask_evtchn); + +void irq_resume(void) +{ + evtchn_op_t op; + int cpu, pirq, virq, ipi, irq, evtchn; + + init_evtchn_cpu_bindings(); + + /* New event-channel space is not 'live' yet. */ + for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++) + mask_evtchn(evtchn); + + /* Check that no PIRQs are still bound. */ + for (pirq = 0; pirq < NR_PIRQS; pirq++) + BUG_ON(irq_info[pirq_to_irq(pirq)] != IRQ_UNBOUND); + + /* Secondary CPUs must have no VIRQ or IPI bindings. */ + for (cpu = 1; cpu < NR_CPUS; cpu++) { + for (virq = 0; virq < NR_VIRQS; virq++) + BUG_ON(per_cpu(virq_to_irq, cpu)[virq] != -1); + for (ipi = 0; ipi < NR_IPIS; ipi++) + BUG_ON(per_cpu(ipi_to_irq, cpu)[ipi] != -1); + } + + /* No IRQ <-> event-channel mappings. */ + for (irq = 0; irq < NR_IRQS; irq++) + irq_info[irq] &= ~0xFFFF; /* zap event-channel binding */ + for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++) + evtchn_to_irq[evtchn] = -1; + + /* Primary CPU: rebind VIRQs automatically. */ + for (virq = 0; virq < NR_VIRQS; virq++) { + if ((irq = per_cpu(virq_to_irq, 0)[virq]) == -1) + continue; + + BUG_ON(irq_info[irq] != mk_irq_info(IRQT_VIRQ, virq, 0)); + + /* Get a new binding from Xen. */ + memset(&op, 0, sizeof(op)); + op.cmd = EVTCHNOP_bind_virq; + op.u.bind_virq.virq = virq; + op.u.bind_virq.vcpu = 0; + BUG_ON(HYPERVISOR_event_channel_op(&op) != 0); + evtchn = op.u.bind_virq.port; + + /* Record the new mapping. */ + evtchn_to_irq[evtchn] = irq; + irq_info[irq] = mk_irq_info(IRQT_VIRQ, virq, evtchn); + + /* Ready for use. */ + unmask_evtchn(evtchn); + } + + /* Primary CPU: rebind IPIs automatically. */ + for (ipi = 0; ipi < NR_IPIS; ipi++) { + if ((irq = per_cpu(ipi_to_irq, 0)[ipi]) == -1) + continue; + + BUG_ON(irq_info[irq] != mk_irq_info(IRQT_IPI, ipi, 0)); + + /* Get a new binding from Xen. */ + memset(&op, 0, sizeof(op)); + op.cmd = EVTCHNOP_bind_ipi; + op.u.bind_ipi.vcpu = 0; + BUG_ON(HYPERVISOR_event_channel_op(&op) != 0); + evtchn = op.u.bind_ipi.port; + + /* Record the new mapping. */ + evtchn_to_irq[evtchn] = irq; + irq_info[irq] = mk_irq_info(IRQT_IPI, ipi, evtchn); + + /* Ready for use. */ + unmask_evtchn(evtchn); + } +} + +void __init init_IRQ(void) +{ + int i; + int cpu; + + irq_ctx_init(0); + + spin_lock_init(&irq_mapping_update_lock); + + init_evtchn_cpu_bindings(); + + /* No VIRQ or IPI bindings. */ + for (cpu = 0; cpu < NR_CPUS; cpu++) { + for (i = 0; i < NR_VIRQS; i++) + per_cpu(virq_to_irq, cpu)[i] = -1; + for (i = 0; i < NR_IPIS; i++) + per_cpu(ipi_to_irq, cpu)[i] = -1; + } + + /* No event-channel -> IRQ mappings. */ + for (i = 0; i < NR_EVENT_CHANNELS; i++) { + evtchn_to_irq[i] = -1; + mask_evtchn(i); /* No event channels are 'live' right now. */ + } + + /* No IRQ -> event-channel mappings. */ + for (i = 0; i < NR_IRQS; i++) + irq_info[i] = IRQ_UNBOUND; + + /* Dynamic IRQ space is currently unbound. Zero the refcnts. */ + for (i = 0; i < NR_DYNIRQS; i++) { + irq_bindcount[dynirq_to_irq(i)] = 0; + + irq_desc[dynirq_to_irq(i)].status = IRQ_DISABLED; + irq_desc[dynirq_to_irq(i)].action = NULL; + irq_desc[dynirq_to_irq(i)].depth = 1; + irq_desc[dynirq_to_irq(i)].handler = &dynirq_type; + } + + /* Phys IRQ space is statically bound (1:1 mapping). Nail refcnts. */ + for (i = 0; i < NR_PIRQS; i++) + { + irq_bindcount[pirq_to_irq(i)] = 1; + +#ifdef RTC_IRQ + /* If not domain 0, force our RTC driver to fail its probe. */ + if ((i == RTC_IRQ) && + !(xen_start_info->flags & SIF_INITDOMAIN)) + continue; +#endif + + irq_desc[pirq_to_irq(i)].status = IRQ_DISABLED; + irq_desc[pirq_to_irq(i)].action = NULL; + irq_desc[pirq_to_irq(i)].depth = 1; + irq_desc[pirq_to_irq(i)].handler = &pirq_type; + } +} + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/core/features.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/core/features.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,28 @@ +/****************************************************************************** + * features.c + * + * Xen feature flags. + * + * Copyright (c) 2006, Ian Campbell, XenSource Inc. + */ +#include <linux/types.h> +#include <linux/cache.h> +#include <asm/hypervisor.h> +#include <xen/features.h> + +/* When we rebase to a more recent Linux we can use __read_mostly here. */ +unsigned long xen_features[XENFEAT_NR_SUBMAPS] __cacheline_aligned; + +void setup_xen_features(void) +{ + uint32_t *flags = (uint32_t *)&xen_features[0]; + xen_feature_info_t fi; + int i; + + for (i=0; i<XENFEAT_NR_SUBMAPS; i++) { + fi.submap_idx = i; + if (HYPERVISOR_xen_version(XENVER_get_features, &fi) < 0) + break; + flags[i] = fi.submap; + } +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/core/gnttab.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/core/gnttab.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,404 @@ +/****************************************************************************** + * gnttab.c + * + * Granting foreign access to our memory reservation. + * + * Copyright (c) 2005, Christopher Clark + * Copyright (c) 2004-2005, K A Fraser + */ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <asm/pgtable.h> +#include <xen/interface/xen.h> +#include <asm/fixmap.h> +#include <asm/uaccess.h> +#include <xen/public/privcmd.h> +#include <xen/gnttab.h> +#include <asm/synch_bitops.h> + +#if 1 +#define ASSERT(_p) \ + if ( !(_p) ) { printk(KERN_ALERT"Assertion '%s': line %d, file %s\n", \ + #_p , __LINE__, __FILE__); *(int*)0=0; } +#else +#define ASSERT(_p) ((void)0) +#endif + +#define WPRINTK(fmt, args...) \ + printk(KERN_WARNING "xen_grant: " fmt, ##args) + + +EXPORT_SYMBOL(gnttab_grant_foreign_access); +EXPORT_SYMBOL(gnttab_end_foreign_access_ref); +EXPORT_SYMBOL(gnttab_end_foreign_access); +EXPORT_SYMBOL(gnttab_query_foreign_access); +EXPORT_SYMBOL(gnttab_grant_foreign_transfer); +EXPORT_SYMBOL(gnttab_end_foreign_transfer_ref); +EXPORT_SYMBOL(gnttab_end_foreign_transfer); +EXPORT_SYMBOL(gnttab_alloc_grant_references); +EXPORT_SYMBOL(gnttab_free_grant_references); +EXPORT_SYMBOL(gnttab_free_grant_reference); +EXPORT_SYMBOL(gnttab_claim_grant_reference); +EXPORT_SYMBOL(gnttab_release_grant_reference); +EXPORT_SYMBOL(gnttab_request_free_callback); +EXPORT_SYMBOL(gnttab_grant_foreign_access_ref); +EXPORT_SYMBOL(gnttab_grant_foreign_transfer_ref); + +/* External tools reserve first few grant table entries. */ +#define NR_RESERVED_ENTRIES 8 + +#define NR_GRANT_ENTRIES (NR_GRANT_FRAMES * PAGE_SIZE / sizeof(grant_entry_t)) +#define GNTTAB_LIST_END (NR_GRANT_ENTRIES + 1) + +static grant_ref_t gnttab_list[NR_GRANT_ENTRIES]; +static int gnttab_free_count; +static grant_ref_t gnttab_free_head; +static spinlock_t gnttab_list_lock = SPIN_LOCK_UNLOCKED; + +static grant_entry_t *shared; + +static struct gnttab_free_callback *gnttab_free_callback_list = NULL; + +static int +get_free_entries(int count) +{ + unsigned long flags; + int ref; + grant_ref_t head; + spin_lock_irqsave(&gnttab_list_lock, flags); + if (gnttab_free_count < count) { + spin_unlock_irqrestore(&gnttab_list_lock, flags); + return -1; + } + ref = head = gnttab_free_head; + gnttab_free_count -= count; + while (count-- > 1) + head = gnttab_list[head]; + gnttab_free_head = gnttab_list[head]; + gnttab_list[head] = GNTTAB_LIST_END; + spin_unlock_irqrestore(&gnttab_list_lock, flags); + return ref; +} + +#define get_free_entry() get_free_entries(1) + +static void +do_free_callbacks(void) +{ + struct gnttab_free_callback *callback, *next; + + callback = gnttab_free_callback_list; + gnttab_free_callback_list = NULL; + + while (callback != NULL) { + next = callback->next; + if (gnttab_free_count >= callback->count) { + callback->next = NULL; + callback->fn(callback->arg); + } else { + callback->next = gnttab_free_callback_list; + gnttab_free_callback_list = callback; + } + callback = next; + } +} + +static inline void +check_free_callbacks(void) +{ + if (unlikely(gnttab_free_callback_list)) + do_free_callbacks(); +} + +static void +put_free_entry(grant_ref_t ref) +{ + unsigned long flags; + spin_lock_irqsave(&gnttab_list_lock, flags); + gnttab_list[ref] = gnttab_free_head; + gnttab_free_head = ref; + gnttab_free_count++; + check_free_callbacks(); + spin_unlock_irqrestore(&gnttab_list_lock, flags); +} + +/* + * Public grant-issuing interface functions + */ + +int +gnttab_grant_foreign_access(domid_t domid, unsigned long frame, int readonly) +{ + int ref; + + if (unlikely((ref = get_free_entry()) == -1)) + return -ENOSPC; + + shared[ref].frame = frame; + shared[ref].domid = domid; + wmb(); + shared[ref].flags = GTF_permit_access | (readonly ? GTF_readonly : 0); + + return ref; +} + +void +gnttab_grant_foreign_access_ref(grant_ref_t ref, domid_t domid, + unsigned long frame, int readonly) +{ + shared[ref].frame = frame; + shared[ref].domid = domid; + wmb(); + shared[ref].flags = GTF_permit_access | (readonly ? GTF_readonly : 0); +} + + +int +gnttab_query_foreign_access(grant_ref_t ref) +{ + u16 nflags; + + nflags = shared[ref].flags; + + return (nflags & (GTF_reading|GTF_writing)); +} + +int +gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly) +{ + u16 flags, nflags; + + nflags = shared[ref].flags; + do { + if ( (flags = nflags) & (GTF_reading|GTF_writing) ) { + printk(KERN_ALERT "WARNING: g.e. still in use!\n"); + return 0; + } + } + while ((nflags = synch_cmpxchg(&shared[ref].flags, flags, 0)) != + flags); + + return 1; +} + +void +gnttab_end_foreign_access(grant_ref_t ref, int readonly, unsigned long page) +{ + if (gnttab_end_foreign_access_ref(ref, readonly)) { + put_free_entry(ref); + if (page != 0) { + free_page(page); + } + } + else { + /* XXX This needs to be fixed so that the ref and page are + placed on a list to be freed up later. */ + printk(KERN_WARNING + "WARNING: leaking g.e. and page still in use!\n"); + } +} + +int +gnttab_grant_foreign_transfer(domid_t domid) +{ + int ref; + + if (unlikely((ref = get_free_entry()) == -1)) + return -ENOSPC; + + shared[ref].frame = 0; + shared[ref].domid = domid; + wmb(); + shared[ref].flags = GTF_accept_transfer; + + return ref; +} + +void +gnttab_grant_foreign_transfer_ref(grant_ref_t ref, domid_t domid) +{ + shared[ref].frame = 0; + shared[ref].domid = domid; + wmb(); + shared[ref].flags = GTF_accept_transfer; +} + +unsigned long +gnttab_end_foreign_transfer_ref(grant_ref_t ref) +{ + unsigned long frame; + u16 flags; + + /* + * If a transfer is not even yet started, try to reclaim the grant + * reference and return failure (== 0). + */ + while (!((flags = shared[ref].flags) & GTF_transfer_committed)) { + if ( synch_cmpxchg(&shared[ref].flags, flags, 0) == flags ) + return 0; + cpu_relax(); + } + + /* If a transfer is in progress then wait until it is completed. */ + while (!(flags & GTF_transfer_completed)) { + flags = shared[ref].flags; + cpu_relax(); + } + + /* Read the frame number /after/ reading completion status. */ + rmb(); + frame = shared[ref].frame; + BUG_ON(frame == 0); + + return frame; +} + +unsigned long +gnttab_end_foreign_transfer(grant_ref_t ref) +{ + unsigned long frame = gnttab_end_foreign_transfer_ref(ref); + put_free_entry(ref); + return frame; +} + +void +gnttab_free_grant_reference(grant_ref_t ref) +{ + + put_free_entry(ref); +} + +void +gnttab_free_grant_references(grant_ref_t head) +{ + grant_ref_t ref; + unsigned long flags; + int count = 1; + if (head == GNTTAB_LIST_END) + return; + spin_lock_irqsave(&gnttab_list_lock, flags); + ref = head; + while (gnttab_list[ref] != GNTTAB_LIST_END) { + ref = gnttab_list[ref]; + count++; + } + gnttab_list[ref] = gnttab_free_head; + gnttab_free_head = head; + gnttab_free_count += count; + check_free_callbacks(); + spin_unlock_irqrestore(&gnttab_list_lock, flags); +} + +int +gnttab_alloc_grant_references(u16 count, grant_ref_t *head) +{ + int h = get_free_entries(count); + + if (h == -1) + return -ENOSPC; + + *head = h; + + return 0; +} + +int +gnttab_claim_grant_reference(grant_ref_t *private_head) +{ + grant_ref_t g = *private_head; + if (unlikely(g == GNTTAB_LIST_END)) + return -ENOSPC; + *private_head = gnttab_list[g]; + return g; +} + +void +gnttab_release_grant_reference(grant_ref_t *private_head, grant_ref_t release) +{ + gnttab_list[release] = *private_head; + *private_head = release; +} + +void +gnttab_request_free_callback(struct gnttab_free_callback *callback, + void (*fn)(void *), void *arg, u16 count) +{ + unsigned long flags; + spin_lock_irqsave(&gnttab_list_lock, flags); + if (callback->next) + goto out; + callback->fn = fn; + callback->arg = arg; + callback->count = count; + callback->next = gnttab_free_callback_list; + gnttab_free_callback_list = callback; + check_free_callbacks(); + out: + spin_unlock_irqrestore(&gnttab_list_lock, flags); +} + +int +gnttab_resume(void) +{ + gnttab_setup_table_t setup; + unsigned long frames[NR_GRANT_FRAMES]; + int i; + + setup.dom = DOMID_SELF; + setup.nr_frames = NR_GRANT_FRAMES; + setup.frame_list = frames; + + BUG_ON(HYPERVISOR_grant_table_op(GNTTABOP_setup_table, &setup, 1)); + BUG_ON(setup.status != 0); + + for (i = 0; i < NR_GRANT_FRAMES; i++) + set_fixmap(FIX_GNTTAB_END - i, frames[i] << PAGE_SHIFT); + + return 0; +} + +int +gnttab_suspend(void) +{ + int i; + + for (i = 0; i < NR_GRANT_FRAMES; i++) + clear_fixmap(FIX_GNTTAB_END - i); + + return 0; +} + +static int __init +gnttab_init(void) +{ + int i; + + if (xen_init() < 0) + return -ENODEV; + + BUG_ON(gnttab_resume()); + + shared = (grant_entry_t *)fix_to_virt(FIX_GNTTAB_END); + + for (i = NR_RESERVED_ENTRIES; i < NR_GRANT_ENTRIES; i++) + gnttab_list[i] = i + 1; + gnttab_free_count = NR_GRANT_ENTRIES - NR_RESERVED_ENTRIES; + gnttab_free_head = NR_RESERVED_ENTRIES; + + printk("Grant table initialized\n"); + return 0; +} + +core_initcall(gnttab_init); + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/core/reboot.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/core/reboot.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,430 @@ +#define __KERNEL_SYSCALLS__ +#include <linux/version.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/unistd.h> +#include <linux/module.h> +#include <linux/reboot.h> +#include <linux/sysrq.h> +#include <linux/stringify.h> +#include <asm/irq.h> +#include <asm/mmu_context.h> +#include <xen/evtchn.h> +#include <asm/hypervisor.h> +#include <xen/interface/dom0_ops.h> +#include <xen/xenbus.h> +#include <linux/cpu.h> +#include <linux/kthread.h> +#include <xen/xencons.h> + +#if defined(__i386__) || defined(__x86_64__) +/* + * Power off function, if any + */ +void (*pm_power_off)(void); +#endif + +#define SHUTDOWN_INVALID -1 +#define SHUTDOWN_POWEROFF 0 +#define SHUTDOWN_REBOOT 1 +#define SHUTDOWN_SUSPEND 2 +// Code 3 is SHUTDOWN_CRASH, which we don't use because the domain can only +// report a crash, not be instructed to crash! +// HALT is the same as POWEROFF, as far as we're concerned. The tools use +// the distinction when we return the reason code to them. +#define SHUTDOWN_HALT 4 + +void machine_restart(char * __unused) +{ + /* We really want to get pending console data out before we die. */ + xencons_force_flush(); + HYPERVISOR_sched_op(SCHEDOP_shutdown, SHUTDOWN_reboot); +} + +void machine_halt(void) +{ + machine_power_off(); +} + +void machine_power_off(void) +{ + /* We really want to get pending console data out before we die. */ + xencons_force_flush(); + HYPERVISOR_sched_op(SCHEDOP_shutdown, SHUTDOWN_poweroff); +} + +int reboot_thru_bios = 0; /* for dmi_scan.c */ +EXPORT_SYMBOL(machine_restart); +EXPORT_SYMBOL(machine_halt); +EXPORT_SYMBOL(machine_power_off); + + +/****************************************************************************** + * Stop/pickle callback handling. + */ + +/* Ignore multiple shutdown requests. */ +static int shutting_down = SHUTDOWN_INVALID; +static void __shutdown_handler(void *unused); +static DECLARE_WORK(shutdown_work, __shutdown_handler, NULL); + +#ifndef CONFIG_HOTPLUG_CPU +#define cpu_down(x) (-EOPNOTSUPP) +#define cpu_up(x) (-EOPNOTSUPP) +#endif + + +static int __do_suspend(void *ignore) +{ + int i, j, k, fpp; + + extern int gnttab_suspend(void); + extern int gnttab_resume(void); + + extern void time_resume(void); + extern unsigned long max_pfn; + extern unsigned long *pfn_to_mfn_frame_list_list; + extern unsigned long *pfn_to_mfn_frame_list[]; + +#ifdef CONFIG_SMP + cpumask_t prev_online_cpus; + int vcpu_prepare(int vcpu); +#endif + + int err = 0; + + BUG_ON(smp_processor_id() != 0); + BUG_ON(in_interrupt()); + +#if defined(CONFIG_SMP) && !defined(CONFIG_HOTPLUG_CPU) + if (num_online_cpus() > 1) { + printk(KERN_WARNING "Can't suspend SMP guests " + "without CONFIG_HOTPLUG_CPU\n"); + return -EOPNOTSUPP; + } +#endif + + xenbus_suspend(); + + lock_cpu_hotplug(); +#ifdef CONFIG_SMP + /* + * Take all other CPUs offline. We hold the hotplug semaphore to + * avoid other processes bringing up CPUs under our feet. + */ + cpus_clear(prev_online_cpus); + while (num_online_cpus() > 1) { + for_each_online_cpu(i) { + if (i == 0) + continue; + unlock_cpu_hotplug(); + err = cpu_down(i); + lock_cpu_hotplug(); + if (err != 0) { + printk(KERN_CRIT "Failed to take all CPUs " + "down: %d.\n", err); + goto out_reenable_cpus; + } + cpu_set(i, prev_online_cpus); + } + } +#endif + + preempt_disable(); + +#ifdef __i386__ + kmem_cache_shrink(pgd_cache); + mm_pin_all(); +#endif + + __cli(); + preempt_enable(); + unlock_cpu_hotplug(); + + gnttab_suspend(); + + HYPERVISOR_shared_info = (shared_info_t *)empty_zero_page; + clear_fixmap(FIX_SHARED_INFO); + + xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn); + xen_start_info->console_mfn = mfn_to_pfn(xen_start_info->console_mfn); + + /* + * We'll stop somewhere inside this hypercall. When it returns, + * we'll start resuming after the restore. + */ + HYPERVISOR_suspend(virt_to_mfn(xen_start_info)); + + shutting_down = SHUTDOWN_INVALID; + + set_fixmap(FIX_SHARED_INFO, xen_start_info->shared_info); + + HYPERVISOR_shared_info = (shared_info_t *)fix_to_virt(FIX_SHARED_INFO); + + memset(empty_zero_page, 0, PAGE_SIZE); + + HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = + virt_to_mfn(pfn_to_mfn_frame_list_list); + + fpp = PAGE_SIZE/sizeof(unsigned long); + for (i = 0, j = 0, k = -1; i < max_pfn; i += fpp, j++) { + if ((j % fpp) == 0) { + k++; + pfn_to_mfn_frame_list_list[k] = + virt_to_mfn(pfn_to_mfn_frame_list[k]); + j = 0; + } + pfn_to_mfn_frame_list[k][j] = + virt_to_mfn(&phys_to_machine_mapping[i]); + } + HYPERVISOR_shared_info->arch.max_pfn = max_pfn; + + gnttab_resume(); + + irq_resume(); + + time_resume(); + + __sti(); + + xencons_resume(); + +#ifdef CONFIG_SMP + for_each_cpu(i) + vcpu_prepare(i); + +#endif + + /* + * Only resume xenbus /after/ we've prepared our VCPUs; otherwise + * the VCPU hotplug callback can race with our vcpu_prepare + */ + xenbus_resume(); + +#ifdef CONFIG_SMP + out_reenable_cpus: + for_each_cpu_mask(i, prev_online_cpus) { + j = cpu_up(i); + if ((j != 0) && !cpu_online(i)) { + printk(KERN_CRIT "Failed to bring cpu " + "%d back up (%d).\n", + i, j); + err = j; + } + } +#endif + + return err; +} + +static int shutdown_process(void *__unused) +{ + static char *envp[] = { "HOME=/", "TERM=linux", + "PATH=/sbin:/usr/sbin:/bin:/usr/bin", NULL }; + static char *restart_argv[] = { "/sbin/reboot", NULL }; + static char *poweroff_argv[] = { "/sbin/poweroff", NULL }; + + extern asmlinkage long sys_reboot(int magic1, int magic2, + unsigned int cmd, void *arg); + + daemonize("shutdown"); + + switch (shutting_down) { + case SHUTDOWN_POWEROFF: + case SHUTDOWN_HALT: + if (execve("/sbin/poweroff", poweroff_argv, envp) < 0) { + sys_reboot(LINUX_REBOOT_MAGIC1, + LINUX_REBOOT_MAGIC2, + LINUX_REBOOT_CMD_POWER_OFF, + NULL); + } + break; + + case SHUTDOWN_REBOOT: + if (execve("/sbin/reboot", restart_argv, envp) < 0) { + sys_reboot(LINUX_REBOOT_MAGIC1, + LINUX_REBOOT_MAGIC2, + LINUX_REBOOT_CMD_RESTART, + NULL); + } + break; + } + + shutting_down = SHUTDOWN_INVALID; /* could try again */ + + return 0; +} + +static int kthread_create_on_cpu(int (*f)(void *arg), + void *arg, + const char *name, + int cpu) +{ + struct task_struct *p; + p = kthread_create(f, arg, name); + if (IS_ERR(p)) + return PTR_ERR(p); + kthread_bind(p, cpu); + wake_up_process(p); + return 0; +} + +static void __shutdown_handler(void *unused) +{ + int err; + + if (shutting_down != SHUTDOWN_SUSPEND) + err = kernel_thread(shutdown_process, NULL, + CLONE_FS | CLONE_FILES); + else + err = kthread_create_on_cpu(__do_suspend, NULL, "suspend", 0); + + if ( err < 0 ) { + printk(KERN_WARNING "Error creating shutdown process (%d): " + "retrying...\n", -err); + schedule_delayed_work(&shutdown_work, HZ/2); + } +} + +static void shutdown_handler(struct xenbus_watch *watch, + const char **vec, unsigned int len) +{ + char *str; + xenbus_transaction_t xbt; + int err; + + if (shutting_down != SHUTDOWN_INVALID) + return; + + again: + err = xenbus_transaction_start(&xbt); + if (err) + return; + str = (char *)xenbus_read(xbt, "control", "shutdown", NULL); + /* Ignore read errors and empty reads. */ + if (XENBUS_IS_ERR_READ(str)) { + xenbus_transaction_end(xbt, 1); + return; + } + + xenbus_write(xbt, "control", "shutdown", ""); + + err = xenbus_transaction_end(xbt, 0); + if (err == -EAGAIN) { + kfree(str); + goto again; + } + + if (strcmp(str, "poweroff") == 0) + shutting_down = SHUTDOWN_POWEROFF; + else if (strcmp(str, "reboot") == 0) + shutting_down = SHUTDOWN_REBOOT; + else if (strcmp(str, "suspend") == 0) + shutting_down = SHUTDOWN_SUSPEND; + else if (strcmp(str, "halt") == 0) + shutting_down = SHUTDOWN_HALT; + else { + printk("Ignoring shutdown request: %s\n", str); + shutting_down = SHUTDOWN_INVALID; + } + + if (shutting_down != SHUTDOWN_INVALID) + schedule_work(&shutdown_work); + + kfree(str); +} + +#ifdef CONFIG_MAGIC_SYSRQ +static void sysrq_handler(struct xenbus_watch *watch, const char **vec, + unsigned int len) +{ + char sysrq_key = '\0'; + xenbus_transaction_t xbt; + int err; + + again: + err = xenbus_transaction_start(&xbt); + if (err) + return; + if (!xenbus_scanf(xbt, "control", "sysrq", "%c", &sysrq_key)) { + printk(KERN_ERR "Unable to read sysrq code in " + "control/sysrq\n"); + xenbus_transaction_end(xbt, 1); + return; + } + + if (sysrq_key != '\0') + xenbus_printf(xbt, "control", "sysrq", "%c", '\0'); + + err = xenbus_transaction_end(xbt, 0); + if (err == -EAGAIN) + goto again; + + if (sysrq_key != '\0') { + handle_sysrq(sysrq_key, NULL, NULL); + } +} +#endif + +static struct xenbus_watch shutdown_watch = { + .node = "control/shutdown", + .callback = shutdown_handler +}; + +#ifdef CONFIG_MAGIC_SYSRQ +static struct xenbus_watch sysrq_watch = { + .node ="control/sysrq", + .callback = sysrq_handler +}; +#endif + +static struct notifier_block xenstore_notifier; + +static int setup_shutdown_watcher(struct notifier_block *notifier, + unsigned long event, + void *data) +{ + int err1 = 0; +#ifdef CONFIG_MAGIC_SYSRQ + int err2 = 0; +#endif + + err1 = register_xenbus_watch(&shutdown_watch); +#ifdef CONFIG_MAGIC_SYSRQ + err2 = register_xenbus_watch(&sysrq_watch); +#endif + + if (err1) { + printk(KERN_ERR "Failed to set shutdown watcher\n"); + } + +#ifdef CONFIG_MAGIC_SYSRQ + if (err2) { + printk(KERN_ERR "Failed to set sysrq watcher\n"); + } +#endif + + return NOTIFY_DONE; +} + +static int __init setup_shutdown_event(void) +{ + + xenstore_notifier.notifier_call = setup_shutdown_watcher; + + register_xenstore_notifier(&xenstore_notifier); + + return 0; +} + +subsys_initcall(setup_shutdown_event); + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/core/skbuff.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/core/skbuff.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,142 @@ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/version.h> +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/netdevice.h> +#include <linux/inetdevice.h> +#include <linux/etherdevice.h> +#include <linux/skbuff.h> +#include <linux/init.h> +#include <asm/io.h> +#include <asm/page.h> +#include <asm/hypervisor.h> + +/* Referenced in netback.c. */ +/*static*/ kmem_cache_t *skbuff_cachep; + +#define MAX_SKBUFF_ORDER 4 +static kmem_cache_t *skbuff_order_cachep[MAX_SKBUFF_ORDER + 1]; + +static struct { + int size; + kmem_cache_t *cachep; +} skbuff_small[] = { { 512, NULL }, { 2048, NULL } }; + +struct sk_buff *alloc_skb(unsigned int length, int gfp_mask) +{ + int order, i; + kmem_cache_t *cachep; + + length = SKB_DATA_ALIGN(length) + sizeof(struct skb_shared_info); + + if (length <= skbuff_small[ARRAY_SIZE(skbuff_small)-1].size) { + for (i = 0; skbuff_small[i].size < length; i++) + continue; + cachep = skbuff_small[i].cachep; + } else { + order = get_order(length); + if (order > MAX_SKBUFF_ORDER) { + printk(KERN_ALERT "Attempt to allocate order %d " + "skbuff. Increase MAX_SKBUFF_ORDER.\n", order); + return NULL; + } + cachep = skbuff_order_cachep[order]; + } + + length -= sizeof(struct skb_shared_info); + + return alloc_skb_from_cache(cachep, length, gfp_mask); +} + +struct sk_buff *__dev_alloc_skb(unsigned int length, int gfp_mask) +{ + struct sk_buff *skb; + int order; + + length = SKB_DATA_ALIGN(length + 16); + order = get_order(length + sizeof(struct skb_shared_info)); + if (order > MAX_SKBUFF_ORDER) { + printk(KERN_ALERT "Attempt to allocate order %d skbuff. " + "Increase MAX_SKBUFF_ORDER.\n", order); + return NULL; + } + + skb = alloc_skb_from_cache( + skbuff_order_cachep[order], length, gfp_mask); + if (skb != NULL) + skb_reserve(skb, 16); + + return skb; +} + +static void skbuff_ctor(void *buf, kmem_cache_t *cachep, unsigned long unused) +{ + int order = 0; + + while (skbuff_order_cachep[order] != cachep) + order++; + + /* Do our best to allocate contiguous memory but fall back to IOMMU. */ + if (order != 0) + (void)xen_create_contiguous_region( + (unsigned long)buf, order, 0); + + scrub_pages(buf, 1 << order); +} + +static void skbuff_dtor(void *buf, kmem_cache_t *cachep, unsigned long unused) +{ + int order = 0; + + while (skbuff_order_cachep[order] != cachep) + order++; + + if (order != 0) + xen_destroy_contiguous_region((unsigned long)buf, order); +} + +static int __init skbuff_init(void) +{ + static char name[MAX_SKBUFF_ORDER + 1][20]; + static char small_name[ARRAY_SIZE(skbuff_small)][20]; + unsigned long size; + int i, order; + + for (i = 0; i < ARRAY_SIZE(skbuff_small); i++) { + size = skbuff_small[i].size; + sprintf(small_name[i], "xen-skb-%lu", size); + /* + * No ctor/dtor: objects do not span page boundaries, and they + * are only used on transmit path so no need for scrubbing. + */ + skbuff_small[i].cachep = kmem_cache_create( + small_name[i], size, size, 0, NULL, NULL); + } + + for (order = 0; order <= MAX_SKBUFF_ORDER; order++) { + size = PAGE_SIZE << order; + sprintf(name[order], "xen-skb-%lu", size); + skbuff_order_cachep[order] = kmem_cache_create( + name[order], size, size, 0, skbuff_ctor, skbuff_dtor); + } + + skbuff_cachep = skbuff_order_cachep[0]; + + return 0; +} +core_initcall(skbuff_init); + +EXPORT_SYMBOL(__dev_alloc_skb); + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/core/smpboot.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/core/smpboot.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,439 @@ +/* + * Xen SMP booting functions + * + * See arch/i386/kernel/smpboot.c for copyright and credits for derived + * portions of this file. + */ + +#include <linux/module.h> +#include <linux/config.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/sched.h> +#include <linux/kernel_stat.h> +#include <linux/smp_lock.h> +#include <linux/irq.h> +#include <linux/bootmem.h> +#include <linux/notifier.h> +#include <linux/cpu.h> +#include <linux/percpu.h> +#include <asm/desc.h> +#include <asm/arch_hooks.h> +#include <asm/pgalloc.h> +#include <xen/evtchn.h> +#include <xen/interface/vcpu.h> +#include <xen/xenbus.h> + +#ifdef CONFIG_SMP_ALTERNATIVES +#include <asm/smp_alt.h> +#endif + +extern irqreturn_t smp_reschedule_interrupt(int, void *, struct pt_regs *); +extern irqreturn_t smp_call_function_interrupt(int, void *, struct pt_regs *); + +extern void local_setup_timer(unsigned int cpu); +extern void local_teardown_timer(unsigned int cpu); + +extern void hypervisor_callback(void); +extern void failsafe_callback(void); +extern void system_call(void); +extern void smp_trap_init(trap_info_t *); + +extern cpumask_t cpu_initialized; + +/* Number of siblings per CPU package */ +int smp_num_siblings = 1; +int phys_proc_id[NR_CPUS]; /* Package ID of each logical CPU */ +EXPORT_SYMBOL(phys_proc_id); +int cpu_core_id[NR_CPUS]; /* Core ID of each logical CPU */ +EXPORT_SYMBOL(cpu_core_id); + +cpumask_t cpu_online_map; +EXPORT_SYMBOL(cpu_online_map); +cpumask_t cpu_possible_map; +EXPORT_SYMBOL(cpu_possible_map); + +struct cpuinfo_x86 cpu_data[NR_CPUS] __cacheline_aligned; +EXPORT_SYMBOL(cpu_data); + +#ifdef CONFIG_HOTPLUG_CPU +DEFINE_PER_CPU(int, cpu_state) = { 0 }; +#endif + +static DEFINE_PER_CPU(int, resched_irq); +static DEFINE_PER_CPU(int, callfunc_irq); +static char resched_name[NR_CPUS][15]; +static char callfunc_name[NR_CPUS][15]; + +u8 cpu_2_logical_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; + +void *xquad_portio; + +cpumask_t cpu_sibling_map[NR_CPUS] __cacheline_aligned; +cpumask_t cpu_core_map[NR_CPUS] __cacheline_aligned; +EXPORT_SYMBOL(cpu_core_map); + +#if defined(__i386__) +u8 x86_cpu_to_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = 0xff }; +EXPORT_SYMBOL(x86_cpu_to_apicid); +#elif !defined(CONFIG_X86_IO_APIC) +unsigned int maxcpus = NR_CPUS; +#endif + +void __init smp_alloc_memory(void) +{ +} + +static void xen_smp_intr_init(unsigned int cpu) +{ + sprintf(resched_name[cpu], "resched%d", cpu); + per_cpu(resched_irq, cpu) = + bind_ipi_to_irqhandler( + RESCHEDULE_VECTOR, + cpu, + smp_reschedule_interrupt, + SA_INTERRUPT, + resched_name[cpu], + NULL); + BUG_ON(per_cpu(resched_irq, cpu) < 0); + + sprintf(callfunc_name[cpu], "callfunc%d", cpu); + per_cpu(callfunc_irq, cpu) = + bind_ipi_to_irqhandler( + CALL_FUNCTION_VECTOR, + cpu, + smp_call_function_interrupt, + SA_INTERRUPT, + callfunc_name[cpu], + NULL); + BUG_ON(per_cpu(callfunc_irq, cpu) < 0); + + if (cpu != 0) + local_setup_timer(cpu); +} + +#ifdef CONFIG_HOTPLUG_CPU +static void xen_smp_intr_exit(unsigned int cpu) +{ + if (cpu != 0) + local_teardown_timer(cpu); + + unbind_from_irqhandler(per_cpu(resched_irq, cpu), NULL); + unbind_from_irqhandler(per_cpu(callfunc_irq, cpu), NULL); +} +#endif + +static void cpu_bringup(void) +{ + if (!cpu_isset(smp_processor_id(), cpu_initialized)) + cpu_init(); + local_irq_enable(); + cpu_idle(); +} + +void vcpu_prepare(int vcpu) +{ + vcpu_guest_context_t ctxt; + struct task_struct *idle = idle_task(vcpu); + + if (vcpu == 0) + return; + + memset(&ctxt, 0, sizeof(ctxt)); + + ctxt.flags = VGCF_IN_KERNEL; + ctxt.user_regs.ds = __USER_DS; + ctxt.user_regs.es = __USER_DS; + ctxt.user_regs.fs = 0; + ctxt.user_regs.gs = 0; + ctxt.user_regs.ss = __KERNEL_DS; + ctxt.user_regs.eip = (unsigned long)cpu_bringup; + ctxt.user_regs.eflags = X86_EFLAGS_IF | 0x1000; /* IOPL_RING1 */ + + memset(&ctxt.fpu_ctxt, 0, sizeof(ctxt.fpu_ctxt)); + + smp_trap_init(ctxt.trap_ctxt); + + ctxt.ldt_ents = 0; + + ctxt.gdt_frames[0] = virt_to_mfn(cpu_gdt_descr[vcpu].address); + ctxt.gdt_ents = cpu_gdt_descr[vcpu].size / 8; + +#ifdef __i386__ + ctxt.user_regs.cs = __KERNEL_CS; + ctxt.user_regs.esp = idle->thread.esp; + + ctxt.kernel_ss = __KERNEL_DS; + ctxt.kernel_sp = idle->thread.esp0; + + ctxt.event_callback_cs = __KERNEL_CS; + ctxt.event_callback_eip = (unsigned long)hypervisor_callback; + ctxt.failsafe_callback_cs = __KERNEL_CS; + ctxt.failsafe_callback_eip = (unsigned long)failsafe_callback; + + ctxt.ctrlreg[3] = virt_to_mfn(swapper_pg_dir) << PAGE_SHIFT; +#else + ctxt.user_regs.cs = __KERNEL_CS | 3; + ctxt.user_regs.esp = idle->thread.rsp; + + ctxt.kernel_ss = __KERNEL_DS; + ctxt.kernel_sp = idle->thread.rsp0; + + ctxt.event_callback_eip = (unsigned long)hypervisor_callback; + ctxt.failsafe_callback_eip = (unsigned long)failsafe_callback; + ctxt.syscall_callback_eip = (unsigned long)system_call; + + ctxt.ctrlreg[3] = virt_to_mfn(init_level4_pgt) << PAGE_SHIFT; + + ctxt.gs_base_kernel = (unsigned long)(cpu_pda + vcpu); +#endif + + BUG_ON(HYPERVISOR_vcpu_op(VCPUOP_initialise, vcpu, &ctxt)); +} + +void __init smp_prepare_cpus(unsigned int max_cpus) +{ + int cpu, rc; + struct task_struct *idle; + + cpu_data[0] = boot_cpu_data; + + cpu_2_logical_apicid[0] = 0; + x86_cpu_to_apicid[0] = 0; + + current_thread_info()->cpu = 0; + cpu_sibling_map[0] = cpumask_of_cpu(0); + cpu_core_map[0] = cpumask_of_cpu(0); + + if (max_cpus != 0) + xen_smp_intr_init(0); + + for (cpu = 1; cpu < max_cpus; cpu++) { + rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL); + if (rc == -ENOENT) + break; + BUG_ON(rc != 0); + + cpu_data[cpu] = boot_cpu_data; + cpu_2_logical_apicid[cpu] = cpu; + x86_cpu_to_apicid[cpu] = cpu; + + idle = fork_idle(cpu); + if (IS_ERR(idle)) + panic("failed fork for CPU %d", cpu); + +#ifdef __x86_64__ + cpu_pda[cpu].pcurrent = idle; + cpu_pda[cpu].cpunumber = cpu; + per_cpu(init_tss,cpu).rsp0 = idle->thread.rsp; + clear_ti_thread_flag(idle->thread_info, TIF_FORK); +#endif + + irq_ctx_init(cpu); + + cpu_gdt_descr[cpu].address = + __get_free_page(GFP_KERNEL|__GFP_ZERO); + BUG_ON(cpu_gdt_descr[0].size > PAGE_SIZE); + cpu_gdt_descr[cpu].size = cpu_gdt_descr[0].size; + memcpy((void *)cpu_gdt_descr[cpu].address, + (void *)cpu_gdt_descr[0].address, + cpu_gdt_descr[0].size); + make_page_readonly( + (void *)cpu_gdt_descr[cpu].address, + XENFEAT_writable_descriptor_tables); + + cpu_set(cpu, cpu_possible_map); +#ifdef CONFIG_HOTPLUG_CPU + if (xen_start_info->flags & SIF_INITDOMAIN) + cpu_set(cpu, cpu_present_map); +#else + cpu_set(cpu, cpu_present_map); +#endif + + vcpu_prepare(cpu); + } + + /* Currently, Xen gives no dynamic NUMA/HT info. */ + for (cpu = 1; cpu < NR_CPUS; cpu++) { + cpu_sibling_map[cpu] = cpumask_of_cpu(cpu); + cpu_core_map[cpu] = cpumask_of_cpu(cpu); + } + +#ifdef CONFIG_X86_IO_APIC + /* + * Here we can be sure that there is an IO-APIC in the system. Let's + * go and set it up: + */ + if (!skip_ioapic_setup && nr_ioapics) + setup_IO_APIC(); +#endif +} + +void __devinit smp_prepare_boot_cpu(void) +{ + cpu_possible_map = cpumask_of_cpu(0); + cpu_present_map = cpumask_of_cpu(0); + cpu_online_map = cpumask_of_cpu(0); +} + +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Initialize cpu_present_map late to skip SMP boot code in init/main.c. + * But do it early enough to catch critical for_each_present_cpu() loops + * in i386-specific code. + */ +static int __init initialize_cpu_present_map(void) +{ + cpu_present_map = cpu_possible_map; + return 0; +} +core_initcall(initialize_cpu_present_map); + +static void vcpu_hotplug(unsigned int cpu) +{ + int err; + char dir[32], state[32]; + + if ((cpu >= NR_CPUS) || !cpu_possible(cpu)) + return; + + sprintf(dir, "cpu/%d", cpu); + err = xenbus_scanf(XBT_NULL, dir, "availability", "%s", state); + if (err != 1) { + printk(KERN_ERR "XENBUS: Unable to read cpu state\n"); + return; + } + + if (strcmp(state, "online") == 0) { + (void)cpu_up(cpu); + } else if (strcmp(state, "offline") == 0) { + (void)cpu_down(cpu); + } else { + printk(KERN_ERR "XENBUS: unknown state(%s) on CPU%d\n", + state, cpu); + } +} + +static void handle_vcpu_hotplug_event( + struct xenbus_watch *watch, const char **vec, unsigned int len) +{ + int cpu; + char *cpustr; + const char *node = vec[XS_WATCH_PATH]; + + if ((cpustr = strstr(node, "cpu/")) != NULL) { + sscanf(cpustr, "cpu/%d", &cpu); + vcpu_hotplug(cpu); + } +} + +static int setup_cpu_watcher(struct notifier_block *notifier, + unsigned long event, void *data) +{ + int i; + + static struct xenbus_watch cpu_watch = { + .node = "cpu", + .callback = handle_vcpu_hotplug_event }; + (void)register_xenbus_watch(&cpu_watch); + + if (!(xen_start_info->flags & SIF_INITDOMAIN)) { + for_each_cpu(i) + vcpu_hotplug(i); + printk(KERN_INFO "Brought up %ld CPUs\n", + (long)num_online_cpus()); + } + + return NOTIFY_DONE; +} + +static int __init setup_vcpu_hotplug_event(void) +{ + static struct notifier_block xsn_cpu = { + .notifier_call = setup_cpu_watcher }; + register_xenstore_notifier(&xsn_cpu); + return 0; +} + +arch_initcall(setup_vcpu_hotplug_event); + +int __cpu_disable(void) +{ + cpumask_t map = cpu_online_map; + int cpu = smp_processor_id(); + + if (cpu == 0) + return -EBUSY; + + cpu_clear(cpu, map); + fixup_irqs(map); + cpu_clear(cpu, cpu_online_map); + + return 0; +} + +void __cpu_die(unsigned int cpu) +{ + while (HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL)) { + current->state = TASK_UNINTERRUPTIBLE; + schedule_timeout(HZ/10); + } + + xen_smp_intr_exit(cpu); + +#ifdef CONFIG_SMP_ALTERNATIVES + if (num_online_cpus() == 1) + unprepare_for_smp(); +#endif +} + +#else /* !CONFIG_HOTPLUG_CPU */ + +int __cpu_disable(void) +{ + return -ENOSYS; +} + +void __cpu_die(unsigned int cpu) +{ + BUG(); +} + +#endif /* CONFIG_HOTPLUG_CPU */ + +int __devinit __cpu_up(unsigned int cpu) +{ +#ifdef CONFIG_SMP_ALTERNATIVES + if (num_online_cpus() == 1) + prepare_for_smp(); +#endif + + xen_smp_intr_init(cpu); + cpu_set(cpu, cpu_online_map); + if (HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL) != 0) + BUG(); + + return 0; +} + +void __init smp_cpus_done(unsigned int max_cpus) +{ +} + +int setup_profiling_timer(unsigned int multiplier) +{ + /* Dummy function. */ + return 0; +} + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/xen/core/xen_proc.c --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/drivers/xen/core/xen_proc.c Mon Jan 30 17:18:27 2006 @@ -0,0 +1,29 @@ + +#include <linux/config.h> +#include <linux/proc_fs.h> +#include <xen/xen_proc.h> + +static struct proc_dir_entry *xen_base; + +struct proc_dir_entry *create_xen_proc_entry(const char *name, mode_t mode) +{ + if ( xen_base == NULL ) + if ( (xen_base = proc_mkdir("xen", &proc_root)) == NULL ) + panic("Couldn't create /proc/xen"); + return create_proc_entry(name, mode, xen_base); +} + +void remove_xen_proc_entry(const char *name) +{ + remove_proc_entry(name, xen_base); +} + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/fs/Kconfig --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/fs/Kconfig Mon Jan 30 17:18:27 2006 @@ -0,0 +1,1730 @@ +# +# File system configuration +# + +menu "File systems" + +config EXT2_FS + tristate "Second extended fs support" + help + Ext2 is a standard Linux file system for hard disks. + + To compile this file system support as a module, choose M here: the + module will be called ext2. Be aware however that the file system + of your root partition (the one containing the directory /) cannot + be compiled as a module, and so this could be dangerous. + + If unsure, say Y. + +config EXT2_FS_XATTR + bool "Ext2 extended attributes" + depends on EXT2_FS + help + Extended attributes are name:value pairs associated with inodes by + the kernel or by users (see the attr(5) manual page, or visit + <http://acl.bestbits.at/> for details). + + If unsure, say N. + +config EXT2_FS_POSIX_ACL + bool "Ext2 POSIX Access Control Lists" + depends on EXT2_FS_XATTR + help + Posix Access Control Lists (ACLs) support permissions for users and + groups beyond the owner/group/world scheme. + + To learn more about Access Control Lists, visit the Posix ACLs for + Linux website <http://acl.bestbits.at/>. + + If you don't know what Access Control Lists are, say N + +config EXT2_FS_SECURITY + bool "Ext2 Security Labels" + depends on EXT2_FS_XATTR + help + Security labels support alternative access control models + implemented by security modules like SELinux. This option + enables an extended attribute handler for file security + labels in the ext2 filesystem. + + If you are not using a security module that requires using + extended attributes for file security labels, say N. + +config EXT3_FS + tristate "Ext3 journalling file system support" + help + This is the journaling version of the Second extended file system + (often called ext3), the de facto standard Linux file system + (method to organize files on a storage device) for hard disks. + + The journaling code included in this driver means you do not have + to run e2fsck (file system checker) on your file systems after a + crash. The journal keeps track of any changes that were being made + at the time the system crashed, and can ensure that your file system + is consistent without the need for a lengthy check. + + Other than adding the journal to the file system, the on-disk format + of ext3 is identical to ext2. It is possible to freely switch + between using the ext3 driver and the ext2 driver, as long as the + file system has been cleanly unmounted, or e2fsck is run on the file + system. + + To add a journal on an existing ext2 file system or change the + behavior of ext3 file systems, you can use the tune2fs utility ("man + tune2fs"). To modify attributes of files and directories on ext3 + file systems, use chattr ("man chattr"). You need to be using + e2fsprogs version 1.20 or later in order to create ext3 journals + (available at <http://sourceforge.net/projects/e2fsprogs/>). + + To compile this file system support as a module, choose M here: the + module will be called ext3. Be aware however that the file system + of your root partition (the one containing the directory /) cannot + be compiled as a module, and so this may be dangerous. + +config EXT3_FS_XATTR + bool "Ext3 extended attributes" + depends on EXT3_FS + default y + help + Extended attributes are name:value pairs associated with inodes by + the kernel or by users (see the attr(5) manual page, or visit + <http://acl.bestbits.at/> for details). + + If unsure, say N. + + You need this for POSIX ACL support on ext3. + +config EXT3_FS_POSIX_ACL + bool "Ext3 POSIX Access Control Lists" + depends on EXT3_FS_XATTR + help + Posix Access Control Lists (ACLs) support permissions for users and + groups beyond the owner/group/world scheme. + + To learn more about Access Control Lists, visit the Posix ACLs for + Linux website <http://acl.bestbits.at/>. + + If you don't know what Access Control Lists are, say N + +config EXT3_FS_SECURITY + bool "Ext3 Security Labels" + depends on EXT3_FS_XATTR + help + Security labels support alternative access control models + implemented by security modules like SELinux. This option + enables an extended attribute handler for file security + labels in the ext3 filesystem. + + If you are not using a security module that requires using + extended attributes for file security labels, say N. + +config JBD +# CONFIG_JBD could be its own option (even modular), but until there are +# other users than ext3, we will simply make it be the same as CONFIG_EXT3_FS +# dep_tristate ' Journal Block Device support (JBD for ext3)' CONFIG_JBD $CONFIG_EXT3_FS + tristate + default EXT3_FS + help + This is a generic journaling layer for block devices. It is + currently used by the ext3 file system, but it could also be used to + add journal support to other file systems or block devices such as + RAID or LVM. + + If you are using the ext3 file system, you need to say Y here. If + you are not using ext3 then you will probably want to say N. + + To compile this device as a module, choose M here: the module will be + called jbd. If you are compiling ext3 into the kernel, you cannot + compile this code as a module. + +config JBD_DEBUG + bool "JBD (ext3) debugging support" + depends on JBD + help + If you are using the ext3 journaled file system (or potentially any + other file system/device using JBD), this option allows you to + enable debugging output while the system is running, in order to + help track down any problems you are having. By default the + debugging output will be turned off. + + If you select Y here, then you will be able to turn on debugging + with "echo N > /proc/sys/fs/jbd-debug", where N is a number between + 1 and 5, the higher the number, the more debugging output is + generated. To turn debugging off again, do + "echo 0 > /proc/sys/fs/jbd-debug". + +config FS_MBCACHE +# Meta block cache for Extended Attributes (ext2/ext3) + tristate + depends on EXT2_FS_XATTR || EXT3_FS_XATTR + default y if EXT2_FS=y || EXT3_FS=y + default m if EXT2_FS=m || EXT3_FS=m + +config REISERFS_FS + tristate "Reiserfs support" + help + Stores not just filenames but the files themselves in a balanced + tree. Uses journaling. + + Balanced trees are more efficient than traditional file system + architectural foundations. + + In general, ReiserFS is as fast as ext2, but is very efficient with + large directories and small files. Additional patches are needed + for NFS and quotas, please see <http://www.namesys.com/> for links. + + It is more easily extended to have features currently found in + database and keyword search systems than block allocation based file + systems are. The next version will be so extended, and will support + plugins consistent with our motto ``It takes more than a license to + make source code open.'' + + Read <http://www.namesys.com/> to learn more about reiserfs. + + Sponsored by Threshold Networks, Emusic.com, and Bigstorage.com. + + If you like it, you can pay us to add new features to it that you + need, buy a support contract, or pay us to port it to another OS. + +config REISERFS_CHECK + bool "Enable reiserfs debug mode" + depends on REISERFS_FS + help + If you set this to Y, then ReiserFS will perform every check it can + possibly imagine of its internal consistency throughout its + operation. It will also go substantially slower. More than once we + have forgotten that this was on, and then gone despondent over the + latest benchmarks.:-) Use of this option allows our team to go all + out in checking for consistency when debugging without fear of its + effect on end users. If you are on the verge of sending in a bug + report, say Y and you might get a useful error message. Almost + everyone should say N. + +config REISERFS_PROC_INFO + bool "Stats in /proc/fs/reiserfs" + depends on REISERFS_FS + help + Create under /proc/fs/reiserfs a hierarchy of files, displaying + various ReiserFS statistics and internal data at the expense of + making your kernel or module slightly larger (+8 KB). This also + increases the amount of kernel memory required for each mount. + Almost everyone but ReiserFS developers and people fine-tuning + reiserfs or tracing problems should say N. + +config REISERFS_FS_XATTR + bool "ReiserFS extended attributes" + depends on REISERFS_FS + help + Extended attributes are name:value pairs associated with inodes by + the kernel or by users (see the attr(5) manual page, or visit + <http://acl.bestbits.at/> for details). + + If unsure, say N. + +config REISERFS_FS_POSIX_ACL + bool "ReiserFS POSIX Access Control Lists" + depends on REISERFS_FS_XATTR + help + Posix Access Control Lists (ACLs) support permissions for users and + groups beyond the owner/group/world scheme. + + To learn more about Access Control Lists, visit the Posix ACLs for + Linux website <http://acl.bestbits.at/>. + + If you don't know what Access Control Lists are, say N + +config REISERFS_FS_SECURITY + bool "ReiserFS Security Labels" + depends on REISERFS_FS_XATTR + help + Security labels support alternative access control models + implemented by security modules like SELinux. This option + enables an extended attribute handler for file security + labels in the ReiserFS filesystem. + + If you are not using a security module that requires using + extended attributes for file security labels, say N. + +config JFS_FS + tristate "JFS filesystem support" + select NLS + help + This is a port of IBM's Journaled Filesystem . More information is + available in the file <file:Documentation/filesystems/jfs.txt>. + + If you do not intend to use the JFS filesystem, say N. + +config JFS_POSIX_ACL + bool "JFS POSIX Access Control Lists" + depends on JFS_FS + help + Posix Access Control Lists (ACLs) support permissions for users and + groups beyond the owner/group/world scheme. + + To learn more about Access Control Lists, visit the Posix ACLs for + Linux website <http://acl.bestbits.at/>. + + If you don't know what Access Control Lists are, say N + +config JFS_SECURITY + bool "JFS Security Labels" + depends on JFS_FS + help + Security labels support alternative access control models + implemented by security modules like SELinux. This option + enables an extended attribute handler for file security + labels in the jfs filesystem. + + If you are not using a security module that requires using + extended attributes for file security labels, say N. + +config JFS_DEBUG + bool "JFS debugging" + depends on JFS_FS + help + If you are experiencing any problems with the JFS filesystem, say + Y here. This will result in additional debugging messages to be + written to the system log. Under normal circumstances, this + results in very little overhead. + +config JFS_STATISTICS + bool "JFS statistics" + depends on JFS_FS + help + Enabling this option will cause statistics from the JFS file system + to be made available to the user in the /proc/fs/jfs/ directory. + +config FS_POSIX_ACL +# Posix ACL utility routines (for now, only ext2/ext3/jfs/reiserfs) +# +# NOTE: you can implement Posix ACLs without these helpers (XFS does). +# Never use this symbol for ifdefs. +# + bool + depends on EXT2_FS_POSIX_ACL || EXT3_FS_POSIX_ACL || JFS_POSIX_ACL || REISERFS_FS_POSIX_ACL || NFSD_V4 + default y + +source "fs/xfs/Kconfig" + +config MINIX_FS + tristate "Minix fs support" + help + Minix is a simple operating system used in many classes about OS's. + The minix file system (method to organize files on a hard disk + partition or a floppy disk) was the original file system for Linux, + but has been superseded by the second extended file system ext2fs. + You don't want to use the minix file system on your hard disk + because of certain built-in restrictions, but it is sometimes found + on older Linux floppy disks. This option will enlarge your kernel + by about 28 KB. If unsure, say N. + + To compile this file system support as a module, choose M here: the + module will be called minix. Note that the file system of your root + partition (the one containing the directory /) cannot be compiled as + a module. + +config ROMFS_FS + tristate "ROM file system support" + ---help--- + This is a very small read-only file system mainly intended for + initial ram disks of installation disks, but it could be used for + other read-only media as well. Read + <file:Documentation/filesystems/romfs.txt> for details. + + To compile this file system support as a module, choose M here: the + module will be called romfs. Note that the file system of your + root partition (the one containing the directory /) cannot be a + module. + + If you don't know whether you need it, then you don't need it: + answer N. + +config QUOTA + bool "Quota support" + help + If you say Y here, you will be able to set per user limits for disk + usage (also called disk quotas). Currently, it works for the + ext2, ext3, and reiserfs file system. ext3 also supports journalled + quotas for which you don't need to run quotacheck(8) after an unclean + shutdown. You need additional software in order to use quota support + (you can download sources from + <http://www.sf.net/projects/linuxquota/>). For further details, read + the Quota mini-HOWTO, available from + <http://www.tldp.org/docs.html#howto>, or the documentation provided + with the quota tools. Probably the quota support is only useful for + multi user systems. If unsure, say N. + +config QFMT_V1 + tristate "Old quota format support" + depends on QUOTA + help + This quota format was (is) used by kernels earlier than 2.4.22. If + you have quota working and you don't want to convert to new quota + format say Y here. + +config QFMT_V2 + tristate "Quota format v2 support" + depends on QUOTA + help + This quota format allows using quotas with 32-bit UIDs/GIDs. If you + need this functionality say Y here. Note that you will need recent + quota utilities (>= 3.01) for new quota format with this kernel. + +config QUOTACTL + bool + depends on XFS_QUOTA || QUOTA + default y + +config DNOTIFY + bool "Dnotify support" if EMBEDDED + default y + help + Dnotify is a directory-based per-fd file change notification system + that uses signals to communicate events to user-space. There exist + superior alternatives, but some applications may still rely on + dnotify. + + Because of this, if unsure, say Y. + +config AUTOFS_FS + tristate "Kernel automounter support" + help + The automounter is a tool to automatically mount remote file systems + on demand. This implementation is partially kernel-based to reduce + overhead in the already-mounted case; this is unlike the BSD + automounter (amd), which is a pure user space daemon. + + To use the automounter you need the user-space tools from the autofs + package; you can find the location in <file:Documentation/Changes>. + You also want to answer Y to "NFS file system support", below. + + If you want to use the newer version of the automounter with more + features, say N here and say Y to "Kernel automounter v4 support", + below. + + To compile this support as a module, choose M here: the module will be + called autofs. + + If you are not a part of a fairly large, distributed network, you + probably do not need an automounter, and can say N here. + +config AUTOFS4_FS + tristate "Kernel automounter version 4 support (also supports v3)" + help + The automounter is a tool to automatically mount remote file systems + on demand. This implementation is partially kernel-based to reduce + overhead in the already-mounted case; this is unlike the BSD + automounter (amd), which is a pure user space daemon. + + To use the automounter you need the user-space tools from + <ftp://ftp.kernel.org/pub/linux/daemons/autofs/v4/>; you also + want to answer Y to "NFS file system support", below. + + To compile this support as a module, choose M here: the module will be + called autofs4. You will need to add "alias autofs autofs4" to your + modules configuration file. + + If you are not a part of a fairly large, distributed network or + don't have a laptop which needs to dynamically reconfigure to the + local network, you probably do not need an automounter, and can say + N here. + +menu "CD-ROM/DVD Filesystems" + +config ISO9660_FS + tristate "ISO 9660 CDROM file system support" + help + This is the standard file system used on CD-ROMs. It was previously + known as "High Sierra File System" and is called "hsfs" on other + Unix systems. The so-called Rock-Ridge extensions which allow for + long Unix filenames and symbolic links are also supported by this + driver. If you have a CD-ROM drive and want to do more with it than + just listen to audio CDs and watch its LEDs, say Y (and read + <file:Documentation/filesystems/isofs.txt> and the CD-ROM-HOWTO, + available from <http://www.tldp.org/docs.html#howto>), thereby + enlarging your kernel by about 27 KB; otherwise say N. + + To compile this file system support as a module, choose M here: the + module will be called isofs. + +config JOLIET + bool "Microsoft Joliet CDROM extensions" + depends on ISO9660_FS + select NLS + help + Joliet is a Microsoft extension for the ISO 9660 CD-ROM file system + which allows for long filenames in unicode format (unicode is the + new 16 bit character code, successor to ASCII, which encodes the + characters of almost all languages of the world; see + <http://www.unicode.org/> for more information). Say Y here if you + want to be able to read Joliet CD-ROMs under Linux. + +config ZISOFS + bool "Transparent decompression extension" + depends on ISO9660_FS + select ZLIB_INFLATE + help + This is a Linux-specific extension to RockRidge which lets you store + data in compressed form on a CD-ROM and have it transparently + decompressed when the CD-ROM is accessed. See + <http://www.kernel.org/pub/linux/utils/fs/zisofs/> for the tools + necessary to create such a filesystem. Say Y here if you want to be + able to read such compressed CD-ROMs. + +config ZISOFS_FS +# for fs/nls/Config.in + tristate + depends on ZISOFS + default ISO9660_FS + +config UDF_FS + tristate "UDF file system support" + help + This is the new file system used on some CD-ROMs and DVDs. Say Y if + you intend to mount DVD discs or CDRW's written in packet mode, or + if written to by other UDF utilities, such as DirectCD. + Please read <file:Documentation/filesystems/udf.txt>. + + To compile this file system support as a module, choose M here: the + module will be called udf. + + If unsure, say N. + +config UDF_NLS + bool + default y + depends on (UDF_FS=m && NLS) || (UDF_FS=y && NLS=y) + +endmenu + +menu "DOS/FAT/NT Filesystems" + +config FAT_FS + tristate + select NLS + help + If you want to use one of the FAT-based file systems (the MS-DOS and + VFAT (Windows 95) file systems), then you must say Y or M here + to include FAT support. You will then be able to mount partitions or + diskettes with FAT-based file systems and transparently access the + files on them, i.e. MSDOS files will look and behave just like all + other Unix files. + + This FAT support is not a file system in itself, it only provides + the foundation for the other file systems. You will have to say Y or + M to at least one of "MSDOS fs support" or "VFAT fs support" in + order to make use of it. + + Another way to read and write MSDOS floppies and hard drive + partitions from within Linux (but not transparently) is with the + mtools ("man mtools") program suite. You don't need to say Y here in + order to do that. + + If you need to move large files on floppies between a DOS and a + Linux box, say Y here, mount the floppy under Linux with an MSDOS + file system and use GNU tar's M option. GNU tar is a program + available for Unix and DOS ("man tar" or "info tar"). + + It is now also becoming possible to read and write compressed FAT + file systems; read <file:Documentation/filesystems/fat_cvf.txt> for + details. + + The FAT support will enlarge your kernel by about 37 KB. If unsure, + say Y. + + To compile this as a module, choose M here: the module will be called + fat. Note that if you compile the FAT support as a module, you + cannot compile any of the FAT-based file systems into the kernel + -- they will have to be modules as well. + +config MSDOS_FS + tristate "MSDOS fs support" + select FAT_FS + help + This allows you to mount MSDOS partitions of your hard drive (unless + they are compressed; to access compressed MSDOS partitions under + Linux, you can either use the DOS emulator DOSEMU, described in the + DOSEMU-HOWTO, available from + <http://www.tldp.org/docs.html#howto>, or try dmsdosfs in + <ftp://ibiblio.org/pub/Linux/system/filesystems/dosfs/>. If you + intend to use dosemu with a non-compressed MSDOS partition, say Y + here) and MSDOS floppies. This means that file access becomes + transparent, i.e. the MSDOS files look and behave just like all + other Unix files. + + If you have Windows 95 or Windows NT installed on your MSDOS + partitions, you should use the VFAT file system (say Y to "VFAT fs + support" below), or you will not be able to see the long filenames + generated by Windows 95 / Windows NT. + + This option will enlarge your kernel by about 7 KB. If unsure, + answer Y. This will only work if you said Y to "DOS FAT fs support" + as well. To compile this as a module, choose M here: the module will + be called msdos. + +config VFAT_FS + tristate "VFAT (Windows-95) fs support" + select FAT_FS + help + This option provides support for normal Windows file systems with + long filenames. That includes non-compressed FAT-based file systems + used by Windows 95, Windows 98, Windows NT 4.0, and the Unix + programs from the mtools package. + + The VFAT support enlarges your kernel by about 10 KB and it only + works if you said Y to the "DOS FAT fs support" above. Please read + the file <file:Documentation/filesystems/vfat.txt> for details. If + unsure, say Y. + + To compile this as a module, choose M here: the module will be called + vfat. + +config FAT_DEFAULT_CODEPAGE + int "Default codepage for FAT" + depends on MSDOS_FS || VFAT_FS + default 437 + help + This option should be set to the codepage of your FAT filesystems. + It can be overridden with the "codepage" mount option. + See <file:Documentation/filesystems/vfat.txt> for more information. + +config FAT_DEFAULT_IOCHARSET + string "Default iocharset for FAT" + depends on VFAT_FS + default "iso8859-1" + help + Set this to the default input/output character set you'd + like FAT to use. It should probably match the character set + that most of your FAT filesystems use, and can be overridden + with the "iocharset" mount option for FAT filesystems. + Note that "utf8" is not recommended for FAT filesystems. + If unsure, you shouldn't set "utf8" here. + See <file:Documentation/filesystems/vfat.txt> for more information. + +config NTFS_FS + tristate "NTFS file system support" + select NLS + help + NTFS is the file system of Microsoft Windows NT, 2000, XP and 2003. + + Saying Y or M here enables read support. There is partial, but + safe, write support available. For write support you must also + say Y to "NTFS write support" below. + + There are also a number of user-space tools available, called + ntfsprogs. These include ntfsundelete and ntfsresize, that work + without NTFS support enabled in the kernel. + + This is a rewrite from scratch of Linux NTFS support and replaced + the old NTFS code starting with Linux 2.5.11. A backport to + the Linux 2.4 kernel series is separately available as a patch + from the project web site. + + For more information see <file:Documentation/filesystems/ntfs.txt> + and <http://linux-ntfs.sourceforge.net/>. + + To compile this file system support as a module, choose M here: the + module will be called ntfs. + + If you are not using Windows NT, 2000, XP or 2003 in addition to + Linux on your computer it is safe to say N. + +config NTFS_DEBUG + bool "NTFS debugging support" + depends on NTFS_FS + help + If you are experiencing any problems with the NTFS file system, say + Y here. This will result in additional consistency checks to be + performed by the driver as well as additional debugging messages to + be written to the system log. Note that debugging messages are + disabled by default. To enable them, supply the option debug_msgs=1 + at the kernel command line when booting the kernel or as an option + to insmod when loading the ntfs module. Once the driver is active, + you can enable debugging messages by doing (as root): + echo 1 > /proc/sys/fs/ntfs-debug + Replacing the "1" with "0" would disable debug messages. + + If you leave debugging messages disabled, this results in little + overhead, but enabling debug messages results in very significant + slowdown of the system. + + When reporting bugs, please try to have available a full dump of + debugging messages while the misbehaviour was occurring. + +config NTFS_RW + bool "NTFS write support" + depends on NTFS_FS + help + This enables the partial, but safe, write support in the NTFS driver. + + The only supported operation is overwriting existing files, without + changing the file length. No file or directory creation, deletion or + renaming is possible. Note only non-resident files can be written to + so you may find that some very small files (<500 bytes or so) cannot + be written to. + + While we cannot guarantee that it will not damage any data, we have + so far not received a single report where the driver would have + damaged someones data so we assume it is perfectly safe to use. + + Note: While write support is safe in this version (a rewrite from + scratch of the NTFS support), it should be noted that the old NTFS + write support, included in Linux 2.5.10 and before (since 1997), + is not safe. + + This is currently useful with TopologiLinux. TopologiLinux is run + on top of any DOS/Microsoft Windows system without partitioning your + hard disk. Unlike other Linux distributions TopologiLinux does not + need its own partition. For more information see + <http://topologi-linux.sourceforge.net/> + + It is perfectly safe to say N here. + +endmenu + +menu "Pseudo filesystems" + +config PROC_FS + bool "/proc file system support" + help + This is a virtual file system providing information about the status + of the system. "Virtual" means that it doesn't take up any space on + your hard disk: the files are created on the fly by the kernel when + you try to access them. Also, you cannot read the files with older + version of the program less: you need to use more or cat. + + It's totally cool; for example, "cat /proc/interrupts" gives + information about what the different IRQs are used for at the moment + (there is a small number of Interrupt ReQuest lines in your computer + that are used by the attached devices to gain the CPU's attention -- + often a source of trouble if two devices are mistakenly configured + to use the same IRQ). The program procinfo to display some + information about your system gathered from the /proc file system. + + Before you can use the /proc file system, it has to be mounted, + meaning it has to be given a location in the directory hierarchy. + That location should be /proc. A command such as "mount -t proc proc + /proc" or the equivalent line in /etc/fstab does the job. + + The /proc file system is explained in the file + <file:Documentation/filesystems/proc.txt> and on the proc(5) manpage + ("man 5 proc"). + + This option will enlarge your kernel by about 67 KB. Several + programs depend on this, so everyone should say Y here. + +config PROC_KCORE + bool "/proc/kcore support" if !ARM + depends on PROC_FS && MMU + +config SYSFS + bool "sysfs file system support" if EMBEDDED + default y + help + The sysfs filesystem is a virtual filesystem that the kernel uses to + export internal kernel objects, their attributes, and their + relationships to one another. + + Users can use sysfs to ascertain useful information about the running + kernel, such as the devices the kernel has discovered on each bus and + which driver each is bound to. sysfs can also be used to tune devices + and other kernel subsystems. + + Some system agents rely on the information in sysfs to operate. + /sbin/hotplug uses device and object attributes in sysfs to assist in + delegating policy decisions, like persistantly naming devices. + + sysfs is currently used by the block subsystem to mount the root + partition. If sysfs is disabled you must specify the boot device on + the kernel boot command line via its major and minor numbers. For + example, "root=03:01" for /dev/hda1. + + Designers of embedded systems may wish to say N here to conserve space. + +config DEVFS_FS + bool "/dev file system support (OBSOLETE)" + depends on EXPERIMENTAL + help + This is support for devfs, a virtual file system (like /proc) which + provides the file system interface to device drivers, normally found + in /dev. Devfs does not depend on major and minor number + allocations. Device drivers register entries in /dev which then + appear automatically, which means that the system administrator does + not have to create character and block special device files in the + /dev directory using the mknod command (or MAKEDEV script) anymore. + + This is work in progress. If you want to use this, you *must* read + the material in <file:Documentation/filesystems/devfs/>, especially + the file README there. + + Note that devfs no longer manages /dev/pts! If you are using UNIX98 + ptys, you will also need to mount the /dev/pts filesystem (devpts). + + Note that devfs has been obsoleted by udev, + <http://www.kernel.org/pub/linux/utils/kernel/hotplug/>. + It has been stripped down to a bare minimum and is only provided for + legacy installations that use its naming scheme which is + unfortunately different from the names normal Linux installations + use. + + If unsure, say N. + +config DEVFS_MOUNT + bool "Automatically mount at boot" + depends on DEVFS_FS + help + This option appears if you have CONFIG_DEVFS_FS enabled. Setting + this to 'Y' will make the kernel automatically mount devfs onto /dev + when the system is booted, before the init thread is started. + You can override this with the "devfs=nomount" boot option. + + If unsure, say N. + +config DEVFS_DEBUG + bool "Debug devfs" + depends on DEVFS_FS + help + If you say Y here, then the /dev file system code will generate + debugging messages. See the file + <file:Documentation/filesystems/devfs/boot-options> for more + details. + + If unsure, say N. + +config DEVPTS_FS_XATTR + bool "/dev/pts Extended Attributes" + depends on UNIX98_PTYS + help + Extended attributes are name:value pairs associated with inodes by + the kernel or by users (see the attr(5) manual page, or visit + <http://acl.bestbits.at/> for details). + + If unsure, say N. + +config DEVPTS_FS_SECURITY + bool "/dev/pts Security Labels" + depends on DEVPTS_FS_XATTR + help + Security labels support alternative access control models + implemented by security modules like SELinux. This option + enables an extended attribute handler for file security + labels in the /dev/pts filesystem. + + If you are not using a security module that requires using + extended attributes for file security labels, say N. + +config TMPFS + bool "Virtual memory file system support (former shm fs)" + help + Tmpfs is a file system which keeps all files in virtual memory. + + Everything in tmpfs is temporary in the sense that no files will be + created on your hard drive. The files live in memory and swap + space. If you unmount a tmpfs instance, everything stored therein is + lost. + + See <file:Documentation/filesystems/tmpfs.txt> for details. + +config TMPFS_XATTR + bool "tmpfs Extended Attributes" + depends on TMPFS + help + Extended attributes are name:value pairs associated with inodes by + the kernel or by users (see the attr(5) manual page, or visit + <http://acl.bestbits.at/> for details). + + If unsure, say N. + +config TMPFS_SECURITY + bool "tmpfs Security Labels" + depends on TMPFS_XATTR + help + Security labels support alternative access control models + implemented by security modules like SELinux. This option + enables an extended attribute handler for file security + labels in the tmpfs filesystem. + If you are not using a security module that requires using + extended attributes for file security labels, say N. + +config HUGETLBFS + bool "HugeTLB file system support" + depends X86 || IA64 || PPC64 || SPARC64 || SUPERH || X86_64 || BROKEN + depends !XEN + +config HUGETLB_PAGE + def_bool HUGETLBFS + +config RAMFS + bool + default y + ---help--- + Ramfs is a file system which keeps all files in RAM. It allows + read and write access. + + It is more of an programming example than a useable file system. If + you need a file system which lives in RAM with limit checking use + tmpfs. + + To compile this as a module, choose M here: the module will be called + ramfs. + +endmenu + +menu "Miscellaneous filesystems" + +config ADFS_FS + tristate "ADFS file system support (EXPERIMENTAL)" + depends on EXPERIMENTAL + help + The Acorn Disc Filing System is the standard file system of the + RiscOS operating system which runs on Acorn's ARM-based Risc PC + systems and the Acorn Archimedes range of machines. If you say Y + here, Linux will be able to read from ADFS partitions on hard drives + and from ADFS-formatted floppy discs. If you also want to be able to + write to those devices, say Y to "ADFS write support" below. + + The ADFS partition should be the first partition (i.e., + /dev/[hs]d?1) on each of your drives. Please read the file + <file:Documentation/filesystems/adfs.txt> for further details. + + To compile this code as a module, choose M here: the module will be + called adfs. + + If unsure, say N. + +config ADFS_FS_RW + bool "ADFS write support (DANGEROUS)" + depends on ADFS_FS + help + If you say Y here, you will be able to write to ADFS partitions on + hard drives and ADFS-formatted floppy disks. This is experimental + codes, so if you're unsure, say N. + +config AFFS_FS + tristate "Amiga FFS file system support (EXPERIMENTAL)" + depends on EXPERIMENTAL + help + The Fast File System (FFS) is the common file system used on hard + disks by Amiga(tm) systems since AmigaOS Version 1.3 (34.20). Say Y + if you want to be able to read and write files from and to an Amiga + FFS partition on your hard drive. Amiga floppies however cannot be + read with this driver due to an incompatibility of the floppy + controller used in an Amiga and the standard floppy controller in + PCs and workstations. Read <file:Documentation/filesystems/affs.txt> + and <file:fs/affs/Changes>. + + With this driver you can also mount disk files used by Bernd + Schmidt's Un*X Amiga Emulator + (<http://www.freiburg.linux.de/~uae/>). + If you want to do this, you will also need to say Y or M to "Loop + device support", above. + + To compile this file system support as a module, choose M here: the + module will be called affs. If unsure, say N. + +config HFS_FS + tristate "Apple Macintosh file system support (EXPERIMENTAL)" + depends on EXPERIMENTAL + help + If you say Y here, you will be able to mount Macintosh-formatted + floppy disks and hard drive partitions with full read-write access. + Please read <file:fs/hfs/HFS.txt> to learn about the available mount + options. + + To compile this file system support as a module, choose M here: the + module will be called hfs. + +config HFSPLUS_FS + tristate "Apple Extended HFS file system support" + select NLS + select NLS_UTF8 + help + If you say Y here, you will be able to mount extended format + Macintosh-formatted hard drive partitions with full read-write access. + + This file system is often called HFS+ and was introduced with + MacOS 8. It includes all Mac specific filesystem data such as + data forks and creator codes, but it also has several UNIX + style features such as file ownership and permissions. + +config BEFS_FS + tristate "BeOS file system (BeFS) support (read only) (EXPERIMENTAL)" + depends on EXPERIMENTAL + select NLS + help + The BeOS File System (BeFS) is the native file system of Be, Inc's + BeOS. Notable features include support for arbitrary attributes + on files and directories, and database-like indeces on selected + attributes. (Also note that this driver doesn't make those features + available at this time). It is a 64 bit filesystem, so it supports + extremly large volumes and files. + + If you use this filesystem, you should also say Y to at least one + of the NLS (native language support) options below. + + If you don't know what this is about, say N. + + To compile this as a module, choose M here: the module will be + called befs. + +config BEFS_DEBUG + bool "Debug BeFS" + depends on BEFS_FS + help + If you say Y here, you can use the 'debug' mount option to enable + debugging output from the driver. + +config BFS_FS + tristate "BFS file system support (EXPERIMENTAL)" + depends on EXPERIMENTAL + help + Boot File System (BFS) is a file system used under SCO UnixWare to + allow the bootloader access to the kernel image and other important + files during the boot process. It is usually mounted under /stand + and corresponds to the slice marked as "STAND" in the UnixWare + partition. You should say Y if you want to read or write the files + on your /stand slice from within Linux. You then also need to say Y + to "UnixWare slices support", below. More information about the BFS + file system is contained in the file + <file:Documentation/filesystems/bfs.txt>. + + If you don't know what this is about, say N. + + To compile this as a module, choose M here: the module will be called + bfs. Note that the file system of your root partition (the one + containing the directory /) cannot be compiled as a module. + + + +config EFS_FS + tristate "EFS file system support (read only) (EXPERIMENTAL)" + depends on EXPERIMENTAL + help + EFS is an older file system used for non-ISO9660 CD-ROMs and hard + disk partitions by SGI's IRIX operating system (IRIX 6.0 and newer + uses the XFS file system for hard disk partitions however). + + This implementation only offers read-only access. If you don't know + what all this is about, it's safe to say N. For more information + about EFS see its home page at <http://aeschi.ch.eu.org/efs/>. + + To compile the EFS file system support as a module, choose M here: the + module will be called efs. + +config JFFS_FS + tristate "Journalling Flash File System (JFFS) support" + depends on MTD + help + JFFS is the Journaling Flash File System developed by Axis + Communications in Sweden, aimed at providing a crash/powerdown-safe + file system for disk-less embedded devices. Further information is + available at (<http://developer.axis.com/software/jffs/>). + +config JFFS_FS_VERBOSE + int "JFFS debugging verbosity (0 = quiet, 3 = noisy)" + depends on JFFS_FS + default "0" + help + Determines the verbosity level of the JFFS debugging messages. + +config JFFS_PROC_FS + bool "JFFS stats available in /proc filesystem" + depends on JFFS_FS && PROC_FS + help + Enabling this option will cause statistics from mounted JFFS file systems + to be made available to the user in the /proc/fs/jffs/ directory. + +config JFFS2_FS + tristate "Journalling Flash File System v2 (JFFS2) support" + select CRC32 + depends on MTD + help + JFFS2 is the second generation of the Journalling Flash File System + for use on diskless embedded devices. It provides improved wear + levelling, compression and support for hard links. You cannot use + this on normal block devices, only on 'MTD' devices. + + Further information on the design and implementation of JFFS2 is + available at <http://sources.redhat.com/jffs2/>. + +config JFFS2_FS_DEBUG + int "JFFS2 debugging verbosity (0 = quiet, 2 = noisy)" + depends on JFFS2_FS + default "0" + help + This controls the amount of debugging messages produced by the JFFS2 + code. Set it to zero for use in production systems. For evaluation, + testing and debugging, it's advisable to set it to one. This will + enable a few assertions and will print debugging messages at the + KERN_DEBUG loglevel, where they won't normally be visible. Level 2 + is unlikely to be useful - it enables extra debugging in certain + areas which at one point needed debugging, but when the bugs were + located and fixed, the detailed messages were relegated to level 2. + + If reporting bugs, please try to have available a full dump of the + messages at debug level 1 while the misbehaviour was occurring. + +config JFFS2_FS_NAND + bool "JFFS2 support for NAND flash" + depends on JFFS2_FS + default n + help + This enables the support for NAND flash in JFFS2. NAND is a newer + type of flash chip design than the traditional NOR flash, with + higher density but a handful of characteristics which make it more + interesting for the file system to use. + + Say 'N' unless you have NAND flash. + +config JFFS2_FS_NOR_ECC + bool "JFFS2 support for ECC'd NOR flash (EXPERIMENTAL)" + depends on JFFS2_FS && EXPERIMENTAL + default n + help + This enables the experimental support for NOR flash with transparent + ECC for JFFS2. This type of flash chip is not common, however it is + available from ST Microelectronics. + +config JFFS2_COMPRESSION_OPTIONS + bool "Advanced compression options for JFFS2" + depends on JFFS2_FS + default n + help + Enabling this option allows you to explicitly choose which + compression modules, if any, are enabled in JFFS2. Removing + compressors and mean you cannot read existing file systems, + and enabling experimental compressors can mean that you + write a file system which cannot be read by a standard kernel. + + If unsure, you should _definitely_ say 'N'. + +config JFFS2_ZLIB + bool "JFFS2 ZLIB compression support" if JFFS2_COMPRESSION_OPTIONS + select ZLIB_INFLATE + select ZLIB_DEFLATE + depends on JFFS2_FS + default y + help + Zlib is designed to be a free, general-purpose, legally unencumbered, + lossless data-compression library for use on virtually any computer + hardware and operating system. See <http://www.gzip.org/zlib/> for + further information. + + Say 'Y' if unsure. + +config JFFS2_RTIME + bool "JFFS2 RTIME compression support" if JFFS2_COMPRESSION_OPTIONS + depends on JFFS2_FS + default y + help + Rtime does manage to recompress already-compressed data. Say 'Y' if unsure. + +config JFFS2_RUBIN + bool "JFFS2 RUBIN compression support" if JFFS2_COMPRESSION_OPTIONS + depends on JFFS2_FS + default n + help + RUBINMIPS and DYNRUBIN compressors. Say 'N' if unsure. + +choice + prompt "JFFS2 default compression mode" if JFFS2_COMPRESSION_OPTIONS + default JFFS2_CMODE_PRIORITY + depends on JFFS2_FS + help + You can set here the default compression mode of JFFS2 from + the available compression modes. Don't touch if unsure. + +config JFFS2_CMODE_NONE + bool "no compression" + help + Uses no compression. + +config JFFS2_CMODE_PRIORITY + bool "priority" + help + Tries the compressors in a predefinied order and chooses the first + successful one. + +config JFFS2_CMODE_SIZE + bool "size (EXPERIMENTAL)" + help + Tries all compressors and chooses the one which has the smallest + result. + +endchoice + +config CRAMFS + tristate "Compressed ROM file system support (cramfs)" + select ZLIB_INFLATE + help + Saying Y here includes support for CramFs (Compressed ROM File + System). CramFs is designed to be a simple, small, and compressed + file system for ROM based embedded systems. CramFs is read-only, + limited to 256MB file systems (with 16MB files), and doesn't support + 16/32 bits uid/gid, hard links and timestamps. + + See <file:Documentation/filesystems/cramfs.txt> and + <file:fs/cramfs/README> for further information. + + To compile this as a module, choose M here: the module will be called + cramfs. Note that the root file system (the one containing the + directory /) cannot be compiled as a module. + + If unsure, say N. + +config VXFS_FS + tristate "FreeVxFS file system support (VERITAS VxFS(TM) compatible)" + help + FreeVxFS is a file system driver that support the VERITAS VxFS(TM) + file system format. VERITAS VxFS(TM) is the standard file system + of SCO UnixWare (and possibly others) and optionally available + for Sunsoft Solaris, HP-UX and many other operating systems. + Currently only readonly access is supported. + + NOTE: the file system type as used by mount(1), mount(2) and + fstab(5) is 'vxfs' as it describes the file system format, not + the actual driver. + + To compile this as a module, choose M here: the module will be + called freevxfs. If unsure, say N. + + +config HPFS_FS + tristate "OS/2 HPFS file system support" + help + OS/2 is IBM's operating system for PC's, the same as Warp, and HPFS + is the file system used for organizing files on OS/2 hard disk + partitions. Say Y if you want to be able to read files from and + write files to an OS/2 HPFS partition on your hard drive. OS/2 + floppies however are in regular MSDOS format, so you don't need this + option in order to be able to read them. Read + <file:Documentation/filesystems/hpfs.txt>. + + To compile this file system support as a module, choose M here: the + module will be called hpfs. If unsure, say N. + + + +config QNX4FS_FS + tristate "QNX4 file system support (read only)" + help + This is the file system used by the real-time operating systems + QNX 4 and QNX 6 (the latter is also called QNX RTP). + Further information is available at <http://www.qnx.com/>. + Say Y if you intend to mount QNX hard disks or floppies. + Unless you say Y to "QNX4FS read-write support" below, you will + only be able to read these file systems. + + To compile this file system support as a module, choose M here: the + module will be called qnx4. + + If you don't know whether you need it, then you don't need it: + answer N. + +config QNX4FS_RW + bool "QNX4FS write support (DANGEROUS)" + depends on QNX4FS_FS && EXPERIMENTAL && BROKEN + help + Say Y if you want to test write support for QNX4 file systems. + + It's currently broken, so for now: + answer N. + + + +config SYSV_FS + tristate "System V/Xenix/V7/Coherent file system support" + help + SCO, Xenix and Coherent are commercial Unix systems for Intel + machines, and Version 7 was used on the DEC PDP-11. Saying Y + here would allow you to read from their floppies and hard disk + partitions. + + If you have floppies or hard disk partitions like that, it is likely + that they contain binaries from those other Unix systems; in order + to run these binaries, you will want to install linux-abi which is a + a set of kernel modules that lets you run SCO, Xenix, Wyse, + UnixWare, Dell Unix and System V programs under Linux. It is + available via FTP (user: ftp) from + <ftp://ftp.openlinux.org/pub/people/hch/linux-abi/>). + NOTE: that will work only for binaries from Intel-based systems; + PDP ones will have to wait until somebody ports Linux to -11 ;-) + + If you only intend to mount files from some other Unix over the + network using NFS, you don't need the System V file system support + (but you need NFS file system support obviously). + + Note that this option is generally not needed for floppies, since a + good portable way to transport files and directories between unixes + (and even other operating systems) is given by the tar program ("man + tar" or preferably "info tar"). Note also that this option has + nothing whatsoever to do with the option "System V IPC". Read about + the System V file system in + <file:Documentation/filesystems/sysv-fs.txt>. + Saying Y here will enlarge your kernel by about 27 KB. + + To compile this as a module, choose M here: the module will be called + sysv. + + If you haven't heard about all of this before, it's safe to say N. + + + +config UFS_FS + tristate "UFS file system support (read only)" + help + BSD and derivate versions of Unix (such as SunOS, FreeBSD, NetBSD, + OpenBSD and NeXTstep) use a file system called UFS. Some System V + Unixes can create and mount hard disk partitions and diskettes using + this file system as well. Saying Y here will allow you to read from + these partitions; if you also want to write to them, say Y to the + experimental "UFS file system write support", below. Please read the + file <file:Documentation/filesystems/ufs.txt> for more information. + + The recently released UFS2 variant (used in FreeBSD 5.x) is + READ-ONLY supported. + + If you only intend to mount files from some other Unix over the + network using NFS, you don't need the UFS file system support (but + you need NFS file system support obviously). + + Note that this option is generally not needed for floppies, since a + good portable way to transport files and directories between unixes + (and even other operating systems) is given by the tar program ("man + tar" or preferably "info tar"). + + When accessing NeXTstep files, you may need to convert them from the + NeXT character set to the Latin1 character set; use the program + recode ("info recode") for this purpose. + + To compile the UFS file system support as a module, choose M here: the + module will be called ufs. + + If you haven't heard about all of this before, it's safe to say N. + +config UFS_FS_WRITE + bool "UFS file system write support (DANGEROUS)" + depends on UFS_FS && EXPERIMENTAL + help + Say Y here if you want to try writing to UFS partitions. This is + experimental, so you should back up your UFS partitions beforehand. + +endmenu + +menu "Network File Systems" + depends on NET + +config NFS_FS + tristate "NFS file system support" + depends on INET + select LOCKD + select SUNRPC + help + If you are connected to some other (usually local) Unix computer + (using SLIP, PLIP, PPP or Ethernet) and want to mount files residing + on that computer (the NFS server) using the Network File Sharing + protocol, say Y. "Mounting files" means that the client can access + the files with usual UNIX commands as if they were sitting on the + client's hard disk. For this to work, the server must run the + programs nfsd and mountd (but does not need to have NFS file system + support enabled in its kernel). NFS is explained in the Network + Administrator's Guide, available from + <http://www.tldp.org/docs.html#guide>, on its man page: "man + nfs", and in the NFS-HOWTO. + + A superior but less widely used alternative to NFS is provided by + the Coda file system; see "Coda file system support" below. + + If you say Y here, you should have said Y to TCP/IP networking also. + This option would enlarge your kernel by about 27 KB. + + To compile this file system support as a module, choose M here: the + module will be called nfs. + + If you are configuring a diskless machine which will mount its root + file system over NFS at boot time, say Y here and to "Kernel + level IP autoconfiguration" above and to "Root file system on NFS" + below. You cannot compile this driver as a module in this case. + There are two packages designed for booting diskless machines over + the net: netboot, available from + <http://ftp1.sourceforge.net/netboot/>, and Etherboot, + available from <http://ftp1.sourceforge.net/etherboot/>. + + If you don't know what all this is about, say N. + +config NFS_V3 + bool "Provide NFSv3 client support" + depends on NFS_FS + help + Say Y here if you want your NFS client to be able to speak version + 3 of the NFS protocol. + + If unsure, say Y. + +config NFS_V4 + bool "Provide NFSv4 client support (EXPERIMENTAL)" + depends on NFS_FS && EXPERIMENTAL + select RPCSEC_GSS_KRB5 + help + Say Y here if you want your NFS client to be able to speak the newer + version 4 of the NFS protocol. + + Note: Requires auxiliary userspace daemons which may be found on + http://www.citi.umich.edu/projects/nfsv4/ + + If unsure, say N. + +config NFS_DIRECTIO + bool "Allow direct I/O on NFS files (EXPERIMENTAL)" + depends on NFS_FS && EXPERIMENTAL + help + This option enables applications to perform uncached I/O on files + in NFS file systems using the O_DIRECT open() flag. When O_DIRECT + is set for a file, its data is not cached in the system's page + cache. Data is moved to and from user-level application buffers + directly. Unlike local disk-based file systems, NFS O_DIRECT has + no alignment restrictions. + + Unless your program is designed to use O_DIRECT properly, you are + much better off allowing the NFS client to manage data caching for + you. Misusing O_DIRECT can cause poor server performance or network + storms. This kernel build option defaults OFF to avoid exposing + system administrators unwittingly to a potentially hazardous + feature. + + For more details on NFS O_DIRECT, see fs/nfs/direct.c. + + If unsure, say N. This reduces the size of the NFS client, and + causes open() to return EINVAL if a file residing in NFS is + opened with the O_DIRECT flag. + +config NFSD + tristate "NFS server support" + depends on INET + select LOCKD + select SUNRPC + select EXPORTFS + help + If you want your Linux box to act as an NFS *server*, so that other + computers on your local network which support NFS can access certain + directories on your box transparently, you have two options: you can + use the self-contained user space program nfsd, in which case you + should say N here, or you can say Y and use the kernel based NFS + server. The advantage of the kernel based solution is that it is + faster. + + In either case, you will need support software; the respective + locations are given in the file <file:Documentation/Changes> in the + NFS section. + + If you say Y here, you will get support for version 2 of the NFS + protocol (NFSv2). If you also want NFSv3, say Y to the next question + as well. + + Please read the NFS-HOWTO, available from + <http://www.tldp.org/docs.html#howto>. + + To compile the NFS server support as a module, choose M here: the + module will be called nfsd. If unsure, say N. + +config NFSD_V3 + bool "Provide NFSv3 server support" + depends on NFSD + help + If you would like to include the NFSv3 server as well as the NFSv2 + server, say Y here. If unsure, say Y. + +config NFSD_V4 + bool "Provide NFSv4 server support (EXPERIMENTAL)" + depends on NFSD_V3 && EXPERIMENTAL + select NFSD_TCP + help + If you would like to include the NFSv4 server as well as the NFSv2 + and NFSv3 servers, say Y here. This feature is experimental, and + should only be used if you are interested in helping to test NFSv4. + If unsure, say N. + +config NFSD_TCP + bool "Provide NFS server over TCP support" + depends on NFSD + default y + help + If you want your NFS server to support TCP connections, say Y here. + TCP connections usually perform better than the default UDP when + the network is lossy or congested. If unsure, say Y. + +config ROOT_NFS + bool "Root file system on NFS" + depends on NFS_FS=y && IP_PNP + help + If you want your Linux box to mount its whole root file system (the + one containing the directory /) from some other computer over the + net via NFS (presumably because your box doesn't have a hard disk), + say Y. Read <file:Documentation/nfsroot.txt> for details. It is + likely that in this case, you also want to say Y to "Kernel level IP + autoconfiguration" so that your box can discover its network address + at boot time. + + Most people say N here. + +config LOCKD + tristate + +config LOCKD_V4 + bool + depends on NFSD_V3 || NFS_V3 + default y + +config EXPORTFS + tristate + +config SUNRPC + tristate + +config SUNRPC_GSS + tristate + +config RPCSEC_GSS_KRB5 + tristate "Secure RPC: Kerberos V mechanism (EXPERIMENTAL)" + depends on SUNRPC && EXPERIMENTAL + select SUNRPC_GSS + select CRYPTO + select CRYPTO_MD5 + select CRYPTO_DES + help + Provides for secure RPC calls by means of a gss-api + mechanism based on Kerberos V5. This is required for + NFSv4. + + Note: Requires an auxiliary userspace daemon which may be found on + http://www.citi.umich.edu/projects/nfsv4/ + + If unsure, say N. + +config RPCSEC_GSS_SPKM3 + tristate "Secure RPC: SPKM3 mechanism (EXPERIMENTAL)" + depends on SUNRPC && EXPERIMENTAL + select SUNRPC_GSS + select CRYPTO + select CRYPTO_MD5 + select CRYPTO_DES + help + Provides for secure RPC calls by means of a gss-api + mechanism based on the SPKM3 public-key mechanism. + + Note: Requires an auxiliary userspace daemon which may be found on + http://www.citi.umich.edu/projects/nfsv4/ + + If unsure, say N. + +config SMB_FS + tristate "SMB file system support (to mount Windows shares etc.)" + depends on INET + select NLS + help + SMB (Server Message Block) is the protocol Windows for Workgroups + (WfW), Windows 95/98, Windows NT and OS/2 Lan Manager use to share + files and printers over local networks. Saying Y here allows you to + mount their file systems (often called "shares" in this context) and + access them just like any other Unix directory. Currently, this + works only if the Windows machines use TCP/IP as the underlying + transport protocol, and not NetBEUI. For details, read + <file:Documentation/filesystems/smbfs.txt> and the SMB-HOWTO, + available from <http://www.tldp.org/docs.html#howto>. + + Note: if you just want your box to act as an SMB *server* and make + files and printing services available to Windows clients (which need + to have a TCP/IP stack), you don't need to say Y here; you can use + the program SAMBA (available from <ftp://ftp.samba.org/pub/samba/>) + for that. + + General information about how to connect Linux, Windows machines and + Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>. + + To compile the SMB support as a module, choose M here: the module will + be called smbfs. Most people say N, however. + +config SMB_NLS_DEFAULT + bool "Use a default NLS" + depends on SMB_FS + help + Enabling this will make smbfs use nls translations by default. You + need to specify the local charset (CONFIG_NLS_DEFAULT) in the nls + settings and you need to give the default nls for the SMB server as + CONFIG_SMB_NLS_REMOTE. + + The nls settings can be changed at mount time, if your smbmount + supports that, using the codepage and iocharset parameters. + + smbmount from samba 2.2.0 or later supports this. + +config SMB_NLS_REMOTE + string "Default Remote NLS Option" + depends on SMB_NLS_DEFAULT + default "cp437" + help + This setting allows you to specify a default value for which + codepage the server uses. If this field is left blank no + translations will be done by default. The local codepage/charset + default to CONFIG_NLS_DEFAULT. + + The nls settings can be changed at mount time, if your smbmount + supports that, using the codepage and iocharset parameters. + + smbmount from samba 2.2.0 or later supports this. + +config CIFS + tristate "CIFS support (advanced network filesystem for Samba, Window and other CIFS compliant servers)" + depends on INET + select NLS + help + This is the client VFS module for the Common Internet File System + (CIFS) protocol which is the successor to the Server Message Block + (SMB) protocol, the native file sharing mechanism for most early + PC operating systems. The CIFS protocol is fully supported by + file servers such as Windows 2000 (including Windows 2003, NT 4 + and Windows XP) as well by Samba (which provides excellent CIFS + server support for Linux and many other operating systems). Currently + you must use the smbfs client filesystem to access older SMB servers + such as Windows 9x and OS/2. + + The intent of the cifs module is to provide an advanced + network file system client for mounting to CIFS compliant servers, + including support for dfs (hierarchical name space), secure per-user + session establishment, safe distributed caching (oplock), optional + packet signing, Unicode and other internationalization improvements, + and optional Winbind (nsswitch) integration. You do not need to enable + cifs if running only a (Samba) server. It is possible to enable both + smbfs and cifs (e.g. if you are using CIFS for accessing Windows 2003 + and Samba 3 servers, and smbfs for accessing old servers). If you need + to mount to Samba or Windows 2003 servers from this machine, say Y. + +config CIFS_STATS + bool "CIFS statistics" + depends on CIFS + help + Enabling this option will cause statistics for each server share + mounted by the cifs client to be displayed in /proc/fs/cifs/Stats + +config CIFS_XATTR + bool "CIFS extended attributes (EXPERIMENTAL)" + depends on CIFS + help + Extended attributes are name:value pairs associated with inodes by + the kernel or by users (see the attr(5) manual page, or visit + <http://acl.bestbits.at/> for details). CIFS maps the name of + extended attributes beginning with the user namespace prefix + to SMB/CIFS EAs. EAs are stored on Windows servers without the + user namespace prefix, but their names are seen by Linux cifs clients + prefaced by the user namespace prefix. The system namespace + (used by some filesystems to store ACLs) is not supported at + this time. + + If unsure, say N. + +config CIFS_POSIX + bool "CIFS POSIX Extensions (EXPERIMENTAL)" + depends on CIFS_XATTR + help + Enabling this option will cause the cifs client to attempt to + negotiate a newer dialect with servers, such as Samba 3.0.5 + or later, that optionally can handle more POSIX like (rather + than Windows like) file behavior. It also enables + support for POSIX ACLs (getfacl and setfacl) to servers + (such as Samba 3.10 and later) which can negotiate + CIFS POSIX ACL support. If unsure, say N. + +config CIFS_EXPERIMENTAL + bool "CIFS Experimental Features (EXPERIMENTAL)" + depends on CIFS + help + Enables cifs features under testing. These features + are highly experimental. If unsure, say N. + +config NCP_FS + tristate "NCP file system support (to mount NetWare volumes)" + depends on IPX!=n || INET + help + NCP (NetWare Core Protocol) is a protocol that runs over IPX and is + used by Novell NetWare clients to talk to file servers. It is to + IPX what NFS is to TCP/IP, if that helps. Saying Y here allows you + to mount NetWare file server volumes and to access them just like + any other Unix directory. For details, please read the file + <file:Documentation/filesystems/ncpfs.txt> in the kernel source and + the IPX-HOWTO from <http://www.tldp.org/docs.html#howto>. + + You do not have to say Y here if you want your Linux box to act as a + file *server* for Novell NetWare clients. + + General information about how to connect Linux, Windows machines and + Macs is on the WWW at <http://www.eats.com/linux_mac_win.html>. + + To compile this as a module, choose M here: the module will be called + ncpfs. Say N unless you are connected to a Novell network. + +source "fs/ncpfs/Kconfig" + +config CODA_FS + tristate "Coda file system support (advanced network fs)" + depends on INET + help + Coda is an advanced network file system, similar to NFS in that it + enables you to mount file systems of a remote server and access them + with regular Unix commands as if they were sitting on your hard + disk. Coda has several advantages over NFS: support for + disconnected operation (e.g. for laptops), read/write server + replication, security model for authentication and encryption, + persistent client caches and write back caching. + + If you say Y here, your Linux box will be able to act as a Coda + *client*. You will need user level code as well, both for the + client and server. Servers are currently user level, i.e. they need + no kernel support. Please read + <file:Documentation/filesystems/coda.txt> and check out the Coda + home page <http://www.coda.cs.cmu.edu/>. + + To compile the coda client support as a module, choose M here: the + module will be called coda. + +config CODA_FS_OLD_API + bool "Use 96-bit Coda file identifiers" + depends on CODA_FS + help + A new kernel-userspace API had to be introduced for Coda v6.0 + to support larger 128-bit file identifiers as needed by the + new realms implementation. + + However this new API is not backward compatible with older + clients. If you really need to run the old Coda userspace + cache manager then say Y. + + For most cases you probably want to say N. + +config AFS_FS +# for fs/nls/Config.in + tristate "Andrew File System support (AFS) (Experimental)" + depends on INET && EXPERIMENTAL + select RXRPC + help + If you say Y here, you will get an experimental Andrew File System + driver. It currently only supports unsecured read-only AFS access. + + See <file:Documentation/filesystems/afs.txt> for more intormation. + + If unsure, say N. + +config RXRPC + tristate + +endmenu + +menu "Partition Types" + +source "fs/partitions/Kconfig" + +endmenu + +source "fs/nls/Kconfig" + +endmenu + diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/atomic.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/atomic.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,231 @@ +#ifndef __ARCH_I386_ATOMIC__ +#define __ARCH_I386_ATOMIC__ + +#include <linux/config.h> +#include <linux/compiler.h> +#include <asm/processor.h> +#include <asm/smp_alt.h> + +/* + * Atomic operations that C can't guarantee us. Useful for + * resource counting etc.. + */ + +/* + * Make sure gcc doesn't try to be clever and move things around + * on us. We need to use _exactly_ the address the user gave us, + * not some alias that contains the same information. + */ +typedef struct { volatile int counter; } atomic_t; + +#define ATOMIC_INIT(i) { (i) } + +/** + * atomic_read - read atomic variable + * @v: pointer of type atomic_t + * + * Atomically reads the value of @v. + */ +#define atomic_read(v) ((v)->counter) + +/** + * atomic_set - set atomic variable + * @v: pointer of type atomic_t + * @i: required value + * + * Atomically sets the value of @v to @i. + */ +#define atomic_set(v,i) (((v)->counter) = (i)) + +/** + * atomic_add - add integer to atomic variable + * @i: integer value to add + * @v: pointer of type atomic_t + * + * Atomically adds @i to @v. + */ +static __inline__ void atomic_add(int i, atomic_t *v) +{ + __asm__ __volatile__( + LOCK "addl %1,%0" + :"=m" (v->counter) + :"ir" (i), "m" (v->counter)); +} + +/** + * atomic_sub - subtract the atomic variable + * @i: integer value to subtract + * @v: pointer of type atomic_t + * + * Atomically subtracts @i from @v. + */ +static __inline__ void atomic_sub(int i, atomic_t *v) +{ + __asm__ __volatile__( + LOCK "subl %1,%0" + :"=m" (v->counter) + :"ir" (i), "m" (v->counter)); +} + +/** + * atomic_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @v: pointer of type atomic_t + * + * Atomically subtracts @i from @v and returns + * true if the result is zero, or false for all + * other cases. + */ +static __inline__ int atomic_sub_and_test(int i, atomic_t *v) +{ + unsigned char c; + + __asm__ __volatile__( + LOCK "subl %2,%0; sete %1" + :"=m" (v->counter), "=qm" (c) + :"ir" (i), "m" (v->counter) : "memory"); + return c; +} + +/** + * atomic_inc - increment atomic variable + * @v: pointer of type atomic_t + * + * Atomically increments @v by 1. + */ +static __inline__ void atomic_inc(atomic_t *v) +{ + __asm__ __volatile__( + LOCK "incl %0" + :"=m" (v->counter) + :"m" (v->counter)); +} + +/** + * atomic_dec - decrement atomic variable + * @v: pointer of type atomic_t + * + * Atomically decrements @v by 1. + */ +static __inline__ void atomic_dec(atomic_t *v) +{ + __asm__ __volatile__( + LOCK "decl %0" + :"=m" (v->counter) + :"m" (v->counter)); +} + +/** + * atomic_dec_and_test - decrement and test + * @v: pointer of type atomic_t + * + * Atomically decrements @v by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +static __inline__ int atomic_dec_and_test(atomic_t *v) +{ + unsigned char c; + + __asm__ __volatile__( + LOCK "decl %0; sete %1" + :"=m" (v->counter), "=qm" (c) + :"m" (v->counter) : "memory"); + return c != 0; +} + +/** + * atomic_inc_and_test - increment and test + * @v: pointer of type atomic_t + * + * Atomically increments @v by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +static __inline__ int atomic_inc_and_test(atomic_t *v) +{ + unsigned char c; + + __asm__ __volatile__( + LOCK "incl %0; sete %1" + :"=m" (v->counter), "=qm" (c) + :"m" (v->counter) : "memory"); + return c != 0; +} + +/** + * atomic_add_negative - add and test if negative + * @v: pointer of type atomic_t + * @i: integer value to add + * + * Atomically adds @i to @v and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +static __inline__ int atomic_add_negative(int i, atomic_t *v) +{ + unsigned char c; + + __asm__ __volatile__( + LOCK "addl %2,%0; sets %1" + :"=m" (v->counter), "=qm" (c) + :"ir" (i), "m" (v->counter) : "memory"); + return c; +} + +/** + * atomic_add_return - add and return + * @v: pointer of type atomic_t + * @i: integer value to add + * + * Atomically adds @i to @v and returns @i + @v + */ +static __inline__ int atomic_add_return(int i, atomic_t *v) +{ + int __i; +#ifdef CONFIG_M386 + if(unlikely(boot_cpu_data.x86==3)) + goto no_xadd; +#endif + /* Modern 486+ processor */ + __i = i; + __asm__ __volatile__( + LOCK "xaddl %0, %1;" + :"=r"(i) + :"m"(v->counter), "0"(i)); + return i + __i; + +#ifdef CONFIG_M386 +no_xadd: /* Legacy 386 processor */ + local_irq_disable(); + __i = atomic_read(v); + atomic_set(v, i + __i); + local_irq_enable(); + return i + __i; +#endif +} + +static __inline__ int atomic_sub_return(int i, atomic_t *v) +{ + return atomic_add_return(-i,v); +} + +#define atomic_inc_return(v) (atomic_add_return(1,v)) +#define atomic_dec_return(v) (atomic_sub_return(1,v)) + +/* These are x86-specific, used by some header files */ +#define atomic_clear_mask(mask, addr) \ +__asm__ __volatile__(LOCK "andl %0,%1" \ +: : "r" (~(mask)),"m" (*addr) : "memory") + +#define atomic_set_mask(mask, addr) \ +__asm__ __volatile__(LOCK "orl %0,%1" \ +: : "r" (mask),"m" (*(addr)) : "memory") + +/* Atomic operations are already serializing on x86 */ +#define smp_mb__before_atomic_dec() barrier() +#define smp_mb__after_atomic_dec() barrier() +#define smp_mb__before_atomic_inc() barrier() +#define smp_mb__after_atomic_inc() barrier() + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/bitops.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/bitops.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,457 @@ +#ifndef _I386_BITOPS_H +#define _I386_BITOPS_H + +/* + * Copyright 1992, Linus Torvalds. + */ + +#include <linux/config.h> +#include <linux/compiler.h> +#include <asm/smp_alt.h> + +/* + * These have to be done with inline assembly: that way the bit-setting + * is guaranteed to be atomic. All bit operations return 0 if the bit + * was cleared before the operation and != 0 if it was not. + * + * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1). + */ + +#define ADDR (*(volatile long *) addr) + +/** + * set_bit - Atomically set a bit in memory + * @nr: the bit to set + * @addr: the address to start counting from + * + * This function is atomic and may not be reordered. See __set_bit() + * if you do not require the atomic guarantees. + * + * Note: there are no guarantees that this function will not be reordered + * on non x86 architectures, so if you are writting portable code, + * make sure not to rely on its reordering guarantees. + * + * Note that @nr may be almost arbitrarily large; this function is not + * restricted to acting on a single-word quantity. + */ +static inline void set_bit(int nr, volatile unsigned long * addr) +{ + __asm__ __volatile__( LOCK + "btsl %1,%0" + :"=m" (ADDR) + :"Ir" (nr)); +} + +/** + * __set_bit - Set a bit in memory + * @nr: the bit to set + * @addr: the address to start counting from + * + * Unlike set_bit(), this function is non-atomic and may be reordered. + * If it's called on the same region of memory simultaneously, the effect + * may be that only one operation succeeds. + */ +static inline void __set_bit(int nr, volatile unsigned long * addr) +{ + __asm__( + "btsl %1,%0" + :"=m" (ADDR) + :"Ir" (nr)); +} + +/** + * clear_bit - Clears a bit in memory + * @nr: Bit to clear + * @addr: Address to start counting from + * + * clear_bit() is atomic and may not be reordered. However, it does + * not contain a memory barrier, so if it is used for locking purposes, + * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit() + * in order to ensure changes are visible on other processors. + */ +static inline void clear_bit(int nr, volatile unsigned long * addr) +{ + __asm__ __volatile__( LOCK + "btrl %1,%0" + :"=m" (ADDR) + :"Ir" (nr)); +} + +static inline void __clear_bit(int nr, volatile unsigned long * addr) +{ + __asm__ __volatile__( + "btrl %1,%0" + :"=m" (ADDR) + :"Ir" (nr)); +} +#define smp_mb__before_clear_bit() barrier() +#define smp_mb__after_clear_bit() barrier() + +/** + * __change_bit - Toggle a bit in memory + * @nr: the bit to change + * @addr: the address to start counting from + * + * Unlike change_bit(), this function is non-atomic and may be reordered. + * If it's called on the same region of memory simultaneously, the effect + * may be that only one operation succeeds. + */ +static inline void __change_bit(int nr, volatile unsigned long * addr) +{ + __asm__ __volatile__( + "btcl %1,%0" + :"=m" (ADDR) + :"Ir" (nr)); +} + +/** + * change_bit - Toggle a bit in memory + * @nr: Bit to change + * @addr: Address to start counting from + * + * change_bit() is atomic and may not be reordered. It may be + * reordered on other architectures than x86. + * Note that @nr may be almost arbitrarily large; this function is not + * restricted to acting on a single-word quantity. + */ +static inline void change_bit(int nr, volatile unsigned long * addr) +{ + __asm__ __volatile__( LOCK + "btcl %1,%0" + :"=m" (ADDR) + :"Ir" (nr)); +} + +/** + * test_and_set_bit - Set a bit and return its old value + * @nr: Bit to set + * @addr: Address to count from + * + * This operation is atomic and cannot be reordered. + * It may be reordered on other architectures than x86. + * It also implies a memory barrier. + */ +static inline int test_and_set_bit(int nr, volatile unsigned long * addr) +{ + int oldbit; + + __asm__ __volatile__( LOCK + "btsl %2,%1\n\tsbbl %0,%0" + :"=r" (oldbit),"=m" (ADDR) + :"Ir" (nr) : "memory"); + return oldbit; +} + +/** + * __test_and_set_bit - Set a bit and return its old value + * @nr: Bit to set + * @addr: Address to count from + * + * This operation is non-atomic and can be reordered. + * If two examples of this operation race, one can appear to succeed + * but actually fail. You must protect multiple accesses with a lock. + */ +static inline int __test_and_set_bit(int nr, volatile unsigned long * addr) +{ + int oldbit; + + __asm__( + "btsl %2,%1\n\tsbbl %0,%0" + :"=r" (oldbit),"=m" (ADDR) + :"Ir" (nr)); + return oldbit; +} + +/** + * test_and_clear_bit - Clear a bit and return its old value + * @nr: Bit to clear + * @addr: Address to count from + * + * This operation is atomic and cannot be reordered. + * It can be reorderdered on other architectures other than x86. + * It also implies a memory barrier. + */ +static inline int test_and_clear_bit(int nr, volatile unsigned long * addr) +{ + int oldbit; + + __asm__ __volatile__( LOCK + "btrl %2,%1\n\tsbbl %0,%0" + :"=r" (oldbit),"=m" (ADDR) + :"Ir" (nr) : "memory"); + return oldbit; +} + +/** + * __test_and_clear_bit - Clear a bit and return its old value + * @nr: Bit to clear + * @addr: Address to count from + * + * This operation is non-atomic and can be reordered. + * If two examples of this operation race, one can appear to succeed + * but actually fail. You must protect multiple accesses with a lock. + */ +static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) +{ + int oldbit; + + __asm__( + "btrl %2,%1\n\tsbbl %0,%0" + :"=r" (oldbit),"=m" (ADDR) + :"Ir" (nr)); + return oldbit; +} + +/* WARNING: non atomic and it can be reordered! */ +static inline int __test_and_change_bit(int nr, volatile unsigned long *addr) +{ + int oldbit; + + __asm__ __volatile__( + "btcl %2,%1\n\tsbbl %0,%0" + :"=r" (oldbit),"=m" (ADDR) + :"Ir" (nr) : "memory"); + return oldbit; +} + +/** + * test_and_change_bit - Change a bit and return its old value + * @nr: Bit to change + * @addr: Address to count from + * + * This operation is atomic and cannot be reordered. + * It also implies a memory barrier. + */ +static inline int test_and_change_bit(int nr, volatile unsigned long* addr) +{ + int oldbit; + + __asm__ __volatile__( LOCK + "btcl %2,%1\n\tsbbl %0,%0" + :"=r" (oldbit),"=m" (ADDR) + :"Ir" (nr) : "memory"); + return oldbit; +} + +#if 0 /* Fool kernel-doc since it doesn't do macros yet */ +/** + * test_bit - Determine whether a bit is set + * @nr: bit number to test + * @addr: Address to start counting from + */ +static int test_bit(int nr, const volatile void * addr); +#endif + +static inline int constant_test_bit(int nr, const volatile unsigned long *addr) +{ + return ((1UL << (nr & 31)) & (addr[nr >> 5])) != 0; +} + +static inline int variable_test_bit(int nr, const volatile unsigned long * addr) +{ + int oldbit; + + __asm__ __volatile__( + "btl %2,%1\n\tsbbl %0,%0" + :"=r" (oldbit) + :"m" (ADDR),"Ir" (nr)); + return oldbit; +} + +#define test_bit(nr,addr) \ +(__builtin_constant_p(nr) ? \ + constant_test_bit((nr),(addr)) : \ + variable_test_bit((nr),(addr))) + +#undef ADDR + +/** + * find_first_zero_bit - find the first zero bit in a memory region + * @addr: The address to start the search at + * @size: The maximum size to search + * + * Returns the bit-number of the first zero bit, not the number of the byte + * containing a bit. + */ +static inline int find_first_zero_bit(const unsigned long *addr, unsigned size) +{ + int d0, d1, d2; + int res; + + if (!size) + return 0; + /* This looks at memory. Mark it volatile to tell gcc not to move it around */ + __asm__ __volatile__( + "movl $-1,%%eax\n\t" + "xorl %%edx,%%edx\n\t" + "repe; scasl\n\t" + "je 1f\n\t" + "xorl -4(%%edi),%%eax\n\t" + "subl $4,%%edi\n\t" + "bsfl %%eax,%%edx\n" + "1:\tsubl %%ebx,%%edi\n\t" + "shll $3,%%edi\n\t" + "addl %%edi,%%edx" + :"=d" (res), "=&c" (d0), "=&D" (d1), "=&a" (d2) + :"1" ((size + 31) >> 5), "2" (addr), "b" (addr) : "memory"); + return res; +} + +/** + * find_next_zero_bit - find the first zero bit in a memory region + * @addr: The address to base the search on + * @offset: The bitnumber to start searching at + * @size: The maximum size to search + */ +int find_next_zero_bit(const unsigned long *addr, int size, int offset); + +/** + * find_first_bit - find the first set bit in a memory region + * @addr: The address to start the search at + * @size: The maximum size to search + * + * Returns the bit-number of the first set bit, not the number of the byte + * containing a bit. + */ +static inline int find_first_bit(const unsigned long *addr, unsigned size) +{ + int d0, d1; + int res; + + /* This looks at memory. Mark it volatile to tell gcc not to move it around */ + __asm__ __volatile__( + "xorl %%eax,%%eax\n\t" + "repe; scasl\n\t" + "jz 1f\n\t" + "leal -4(%%edi),%%edi\n\t" + "bsfl (%%edi),%%eax\n" + "1:\tsubl %%ebx,%%edi\n\t" + "shll $3,%%edi\n\t" + "addl %%edi,%%eax" + :"=a" (res), "=&c" (d0), "=&D" (d1) + :"1" ((size + 31) >> 5), "2" (addr), "b" (addr) : "memory"); + return res; +} + +/** + * find_next_bit - find the first set bit in a memory region + * @addr: The address to base the search on + * @offset: The bitnumber to start searching at + * @size: The maximum size to search + */ +int find_next_bit(const unsigned long *addr, int size, int offset); + +/** + * ffz - find first zero in word. + * @word: The word to search + * + * Undefined if no zero exists, so code should check against ~0UL first. + */ +static inline unsigned long ffz(unsigned long word) +{ + __asm__("bsfl %1,%0" + :"=r" (word) + :"r" (~word)); + return word; +} + +/** + * __ffs - find first bit in word. + * @word: The word to search + * + * Undefined if no bit exists, so code should check against 0 first. + */ +static inline unsigned long __ffs(unsigned long word) +{ + __asm__("bsfl %1,%0" + :"=r" (word) + :"rm" (word)); + return word; +} + +/* + * fls: find last bit set. + */ + +#define fls(x) generic_fls(x) + +#ifdef __KERNEL__ + +/* + * Every architecture must define this function. It's the fastest + * way of searching a 140-bit bitmap where the first 100 bits are + * unlikely to be set. It's guaranteed that at least one of the 140 + * bits is cleared. + */ +static inline int sched_find_first_bit(const unsigned long *b) +{ + if (unlikely(b[0])) + return __ffs(b[0]); + if (unlikely(b[1])) + return __ffs(b[1]) + 32; + if (unlikely(b[2])) + return __ffs(b[2]) + 64; + if (b[3]) + return __ffs(b[3]) + 96; + return __ffs(b[4]) + 128; +} + +/** + * ffs - find first bit set + * @x: the word to search + * + * This is defined the same way as + * the libc and compiler builtin ffs routines, therefore + * differs in spirit from the above ffz (man ffs). + */ +static inline int ffs(int x) +{ + int r; + + __asm__("bsfl %1,%0\n\t" + "jnz 1f\n\t" + "movl $-1,%0\n" + "1:" : "=r" (r) : "rm" (x)); + return r+1; +} + +/** + * hweightN - returns the hamming weight of a N-bit word + * @x: the word to weigh + * + * The Hamming Weight of a number is the total number of bits set in it. + */ + +#define hweight32(x) generic_hweight32(x) +#define hweight16(x) generic_hweight16(x) +#define hweight8(x) generic_hweight8(x) + +#endif /* __KERNEL__ */ + +#ifdef __KERNEL__ + +#define ext2_set_bit(nr,addr) \ + __test_and_set_bit((nr),(unsigned long*)addr) +#define ext2_set_bit_atomic(lock,nr,addr) \ + test_and_set_bit((nr),(unsigned long*)addr) +#define ext2_clear_bit(nr, addr) \ + __test_and_clear_bit((nr),(unsigned long*)addr) +#define ext2_clear_bit_atomic(lock,nr, addr) \ + test_and_clear_bit((nr),(unsigned long*)addr) +#define ext2_test_bit(nr, addr) test_bit((nr),(unsigned long*)addr) +#define ext2_find_first_zero_bit(addr, size) \ + find_first_zero_bit((unsigned long*)addr, size) +#define ext2_find_next_zero_bit(addr, size, off) \ + find_next_zero_bit((unsigned long*)addr, size, off) + +/* Bitmap functions for the minix filesystem. */ +#define minix_test_and_set_bit(nr,addr) __test_and_set_bit(nr,(void*)addr) +#define minix_set_bit(nr,addr) __set_bit(nr,(void*)addr) +#define minix_test_and_clear_bit(nr,addr) __test_and_clear_bit(nr,(void*)addr) +#define minix_test_bit(nr,addr) test_bit(nr,(void*)addr) +#define minix_find_first_zero_bit(addr,size) \ + find_first_zero_bit((void*)addr,size) + +#endif /* __KERNEL__ */ + +#endif /* _I386_BITOPS_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-default/mach_traps.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-default/mach_traps.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,53 @@ +/* + * include/asm-i386/mach-default/mach_traps.h + * + * Machine specific NMI handling for generic. + * Split out from traps.c by Osamu Tomita <tomita@xxxxxxxxxxx> + */ +#ifndef _MACH_TRAPS_H +#define _MACH_TRAPS_H + +#include <asm/mc146818rtc.h> + +static inline void clear_mem_error(unsigned char reason) +{ + reason = (reason & 0xf) | 4; + outb(reason, 0x61); +} + +static inline void clear_io_check_error(unsigned char reason) +{ + unsigned long i; + + reason = (reason & 0xf) | 8; + outb(reason, 0x61); + i = 2000; + while (--i) udelay(1000); + reason &= ~8; + outb(reason, 0x61); +} + +static inline unsigned char get_nmi_reason(void) +{ + return inb(0x61); +} + +static inline void reassert_nmi(void) +{ + int old_reg = -1; + + if (do_i_have_lock_cmos()) + old_reg = current_lock_cmos_reg(); + else + lock_cmos(0); /* register doesn't matter here */ + outb(0x8f, 0x70); + inb(0x71); /* dummy */ + outb(0x0f, 0x70); + inb(0x71); /* dummy */ + if (old_reg >= 0) + outb(old_reg, 0x70); + else + unlock_cmos(); +} + +#endif /* !_MACH_TRAPS_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/agp.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/agp.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,37 @@ +#ifndef AGP_H +#define AGP_H 1 + +#include <asm/pgtable.h> +#include <asm/cacheflush.h> +#include <asm/system.h> + +/* + * Functions to keep the agpgart mappings coherent with the MMU. + * The GART gives the CPU a physical alias of pages in memory. The alias region is + * mapped uncacheable. Make sure there are no conflicting mappings + * with different cachability attributes for the same page. This avoids + * data corruption on some CPUs. + */ + +int map_page_into_agp(struct page *page); +int unmap_page_from_agp(struct page *page); +#define flush_agp_mappings() global_flush_tlb() + +/* Could use CLFLUSH here if the cpu supports it. But then it would + need to be called for each cacheline of the whole page so it may not be + worth it. Would need a page for it. */ +#define flush_agp_cache() wbinvd() + +/* Convert a physical address to an address suitable for the GART. */ +#define phys_to_gart(x) phys_to_machine(x) +#define gart_to_phys(x) machine_to_phys(x) + +/* GATT allocation. Returns/accepts GATT kernel virtual address. */ +#define alloc_gatt_pages(order) ({ \ + char *_t; dma_addr_t _d; \ + _t = dma_alloc_coherent(NULL,PAGE_SIZE<<(order),&_d,GFP_KERNEL); \ + _t; }) +#define free_gatt_pages(table, order) \ + dma_free_coherent(NULL,PAGE_SIZE<<(order),(table),virt_to_bus(table)) + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/desc.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/desc.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,148 @@ +#ifndef __ARCH_DESC_H +#define __ARCH_DESC_H + +#include <asm/ldt.h> +#include <asm/segment.h> + +#define CPU_16BIT_STACK_SIZE 1024 + +#ifndef __ASSEMBLY__ + +#include <linux/preempt.h> +#include <linux/smp.h> + +#include <asm/mmu.h> + +extern struct desc_struct cpu_gdt_table[NR_CPUS][GDT_ENTRIES]; + +DECLARE_PER_CPU(unsigned char, cpu_16bit_stack[CPU_16BIT_STACK_SIZE]); + +struct Xgt_desc_struct { + unsigned short size; + unsigned long address __attribute__((packed)); + unsigned short pad; +} __attribute__ ((packed)); + +extern struct Xgt_desc_struct idt_descr, cpu_gdt_descr[NR_CPUS]; + +#define load_TR_desc() __asm__ __volatile__("ltr %%ax"::"a" (GDT_ENTRY_TSS*8)) +#define load_LDT_desc() __asm__ __volatile__("lldt %%ax"::"a" (GDT_ENTRY_LDT*8)) + +#define get_cpu_gdt_table(_cpu) ((struct desc_struct *)cpu_gdt_descr[(_cpu)].address) + +/* + * This is the ldt that every process will get unless we need + * something other than this. + */ +extern struct desc_struct default_ldt[]; +extern void set_intr_gate(unsigned int irq, void * addr); + +#define _set_tssldt_desc(n,addr,limit,type) \ +__asm__ __volatile__ ("movw %w3,0(%2)\n\t" \ + "movw %%ax,2(%2)\n\t" \ + "rorl $16,%%eax\n\t" \ + "movb %%al,4(%2)\n\t" \ + "movb %4,5(%2)\n\t" \ + "movb $0,6(%2)\n\t" \ + "movb %%ah,7(%2)\n\t" \ + "rorl $16,%%eax" \ + : "=m"(*(n)) : "a" (addr), "r"(n), "ir"(limit), "i"(type)) + +static inline void __set_tss_desc(unsigned int cpu, unsigned int entry, void *addr) +{ + _set_tssldt_desc(&get_cpu_gdt_table(cpu)[entry], (int)addr, + offsetof(struct tss_struct, __cacheline_filler) - 1, 0x89); +} + +#define set_tss_desc(cpu,addr) __set_tss_desc(cpu, GDT_ENTRY_TSS, addr) + +static inline void set_ldt_desc(unsigned int cpu, void *addr, unsigned int size) +{ + _set_tssldt_desc(&get_cpu_gdt_table(cpu)[GDT_ENTRY_LDT], + (int)addr, ((size << 3)-1), 0x82); +} + +#define LDT_entry_a(info) \ + ((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff)) + +#define LDT_entry_b(info) \ + (((info)->base_addr & 0xff000000) | \ + (((info)->base_addr & 0x00ff0000) >> 16) | \ + ((info)->limit & 0xf0000) | \ + (((info)->read_exec_only ^ 1) << 9) | \ + ((info)->contents << 10) | \ + (((info)->seg_not_present ^ 1) << 15) | \ + ((info)->seg_32bit << 22) | \ + ((info)->limit_in_pages << 23) | \ + ((info)->useable << 20) | \ + 0x7000) + +#define LDT_empty(info) (\ + (info)->base_addr == 0 && \ + (info)->limit == 0 && \ + (info)->contents == 0 && \ + (info)->read_exec_only == 1 && \ + (info)->seg_32bit == 0 && \ + (info)->limit_in_pages == 0 && \ + (info)->seg_not_present == 1 && \ + (info)->useable == 0 ) + +extern int write_ldt_entry(void *ldt, int entry, __u32 entry_a, __u32 entry_b); + +#if TLS_SIZE != 24 +# error update this code. +#endif + +static inline void load_TLS(struct thread_struct *t, unsigned int cpu) +{ +#define C(i) HYPERVISOR_update_descriptor(virt_to_machine(&get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN + i]), *(u64 *)&t->tls_array[i]) + C(0); C(1); C(2); +#undef C +} + +static inline void clear_LDT(void) +{ + int cpu = get_cpu(); + + /* + * NB. We load the default_ldt for lcall7/27 handling on demand, as + * it slows down context switching. Noone uses it anyway. + */ + cpu = cpu; /* XXX avoid compiler warning */ + xen_set_ldt(0UL, 0); + put_cpu(); +} + +/* + * load one particular LDT into the current CPU + */ +static inline void load_LDT_nolock(mm_context_t *pc, int cpu) +{ + void *segments = pc->ldt; + int count = pc->size; + + if (likely(!count)) + segments = NULL; + + xen_set_ldt((unsigned long)segments, count); +} + +static inline void load_LDT(mm_context_t *pc) +{ + int cpu = get_cpu(); + load_LDT_nolock(pc, cpu); + put_cpu(); +} + +static inline unsigned long get_desc_base(unsigned long *desc) +{ + unsigned long base; + base = ((desc[0] >> 16) & 0x0000ffff) | + ((desc[1] << 16) & 0x00ff0000) | + (desc[1] & 0xff000000); + return base; +} + +#endif /* !__ASSEMBLY__ */ + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/dma-mapping.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/dma-mapping.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,156 @@ +#ifndef _ASM_I386_DMA_MAPPING_H +#define _ASM_I386_DMA_MAPPING_H + +/* + * IOMMU interface. See Documentation/DMA-mapping.txt and DMA-API.txt for + * documentation. + */ + +#include <linux/config.h> +#include <linux/mm.h> +#include <asm/cache.h> +#include <asm/io.h> +#include <asm/scatterlist.h> +#include <asm/swiotlb.h> + +static inline int +address_needs_mapping(struct device *hwdev, dma_addr_t addr) +{ + dma_addr_t mask = 0xffffffff; + /* If the device has a mask, use it, otherwise default to 32 bits */ + if (hwdev && hwdev->dma_mask) + mask = *hwdev->dma_mask; + return (addr & ~mask) != 0; +} + +static inline int +range_straddles_page_boundary(void *p, size_t size) +{ + extern unsigned long *contiguous_bitmap; + return (((((unsigned long)p & ~PAGE_MASK) + size) > PAGE_SIZE) && + !test_bit(__pa(p) >> PAGE_SHIFT, contiguous_bitmap)); +} + +#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) +#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h) + +void *dma_alloc_coherent(struct device *dev, size_t size, + dma_addr_t *dma_handle, unsigned int __nocast flag); + +void dma_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle); + +extern dma_addr_t +dma_map_single(struct device *dev, void *ptr, size_t size, + enum dma_data_direction direction); + +extern void +dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size, + enum dma_data_direction direction); + +extern int dma_map_sg(struct device *hwdev, struct scatterlist *sg, + int nents, enum dma_data_direction direction); +extern void dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, + int nents, enum dma_data_direction direction); + +extern dma_addr_t +dma_map_page(struct device *dev, struct page *page, unsigned long offset, + size_t size, enum dma_data_direction direction); + +extern void +dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, + enum dma_data_direction direction); + +extern void +dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, + enum dma_data_direction direction); + +extern void +dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size, + enum dma_data_direction direction); + +static inline void +dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle, + unsigned long offset, size_t size, + enum dma_data_direction direction) +{ + dma_sync_single_for_cpu(dev, dma_handle+offset, size, direction); +} + +static inline void +dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle, + unsigned long offset, size_t size, + enum dma_data_direction direction) +{ + dma_sync_single_for_device(dev, dma_handle+offset, size, direction); +} + +static inline void +dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, + enum dma_data_direction direction) +{ + if (swiotlb) + swiotlb_sync_sg_for_cpu(dev,sg,nelems,direction); + flush_write_buffers(); +} + +static inline void +dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, + enum dma_data_direction direction) +{ + if (swiotlb) + swiotlb_sync_sg_for_device(dev,sg,nelems,direction); + flush_write_buffers(); +} + +extern int +dma_mapping_error(dma_addr_t dma_addr); + +extern int +dma_supported(struct device *dev, u64 mask); + +static inline int +dma_set_mask(struct device *dev, u64 mask) +{ + if(!dev->dma_mask || !dma_supported(dev, mask)) + return -EIO; + + *dev->dma_mask = mask; + + return 0; +} + +#ifdef __i386__ +static inline int +dma_get_cache_alignment(void) +{ + /* no easy way to get cache size on all x86, so return the + * maximum possible, to be safe */ + return (1 << L1_CACHE_SHIFT_MAX); +} +#else +extern int dma_get_cache_alignment(void); +#endif + +#define dma_is_consistent(d) (1) + +static inline void +dma_cache_sync(void *vaddr, size_t size, + enum dma_data_direction direction) +{ + flush_write_buffers(); +} + +#define ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY +extern int +dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, + dma_addr_t device_addr, size_t size, int flags); + +extern void +dma_release_declared_memory(struct device *dev); + +extern void * +dma_mark_declared_memory_occupied(struct device *dev, + dma_addr_t device_addr, size_t size); + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/fixmap.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/fixmap.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,167 @@ +/* + * fixmap.h: compile-time virtual memory allocation + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 1998 Ingo Molnar + * + * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 + */ + +#ifndef _ASM_FIXMAP_H +#define _ASM_FIXMAP_H + +#include <linux/config.h> + +/* used by vmalloc.c, vsyscall.lds.S. + * + * Leave one empty page between vmalloc'ed areas and + * the start of the fixmap. + */ +#define __FIXADDR_TOP (HYPERVISOR_VIRT_START - 2 * PAGE_SIZE) + +#ifndef __ASSEMBLY__ +#include <linux/kernel.h> +#include <asm/acpi.h> +#include <asm/apicdef.h> +#include <asm/page.h> +#include <xen/gnttab.h> +#ifdef CONFIG_HIGHMEM +#include <linux/threads.h> +#include <asm/kmap_types.h> +#endif + +/* + * Here we define all the compile-time 'special' virtual + * addresses. The point is to have a constant address at + * compile time, but to set the physical address only + * in the boot process. We allocate these special addresses + * from the end of virtual memory (0xfffff000) backwards. + * Also this lets us do fail-safe vmalloc(), we + * can guarantee that these special addresses and + * vmalloc()-ed addresses never overlap. + * + * these 'compile-time allocated' memory buffers are + * fixed-size 4k pages. (or larger if used with an increment + * highger than 1) use fixmap_set(idx,phys) to associate + * physical memory with fixmap indices. + * + * TLB entries of such buffers will not be flushed across + * task switches. + */ +enum fixed_addresses { + FIX_HOLE, + FIX_VSYSCALL, +#ifdef CONFIG_X86_LOCAL_APIC + FIX_APIC_BASE, /* local (CPU) APIC) -- required for SMP or not */ +#endif +#ifdef CONFIG_X86_IO_APIC + FIX_IO_APIC_BASE_0, + FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS-1, +#endif +#ifdef CONFIG_X86_VISWS_APIC + FIX_CO_CPU, /* Cobalt timer */ + FIX_CO_APIC, /* Cobalt APIC Redirection Table */ + FIX_LI_PCIA, /* Lithium PCI Bridge A */ + FIX_LI_PCIB, /* Lithium PCI Bridge B */ +#endif +#ifdef CONFIG_X86_F00F_BUG + FIX_F00F_IDT, /* Virtual mapping for IDT */ +#endif +#ifdef CONFIG_X86_CYCLONE_TIMER + FIX_CYCLONE_TIMER, /*cyclone timer register*/ +#endif +#ifdef CONFIG_HIGHMEM + FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ + FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, +#endif +#ifdef CONFIG_ACPI_BOOT + FIX_ACPI_BEGIN, + FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1, +#endif +#ifdef CONFIG_PCI_MMCONFIG + FIX_PCIE_MCFG, +#endif + FIX_SHARED_INFO, + FIX_GNTTAB_BEGIN, + FIX_GNTTAB_END = FIX_GNTTAB_BEGIN + NR_GRANT_FRAMES - 1, +#ifdef CONFIG_XEN_PHYSDEV_ACCESS +#define NR_FIX_ISAMAPS 256 + FIX_ISAMAP_END, + FIX_ISAMAP_BEGIN = FIX_ISAMAP_END + NR_FIX_ISAMAPS - 1, +#endif + __end_of_permanent_fixed_addresses, + /* temporary boot-time mappings, used before ioremap() is functional */ +#define NR_FIX_BTMAPS 16 + FIX_BTMAP_END = __end_of_permanent_fixed_addresses, + FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS - 1, + FIX_WP_TEST, + __end_of_fixed_addresses +}; + +extern void __set_fixmap( + enum fixed_addresses idx, maddr_t phys, pgprot_t flags); + +#define set_fixmap(idx, phys) \ + __set_fixmap(idx, phys, PAGE_KERNEL) +/* + * Some hardware wants to get fixmapped without caching. + */ +#define set_fixmap_nocache(idx, phys) \ + __set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE) + +#define clear_fixmap(idx) \ + __set_fixmap(idx, 0, __pgprot(0)) + +#define FIXADDR_TOP ((unsigned long)__FIXADDR_TOP) + +#define __FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) +#define __FIXADDR_BOOT_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_START (FIXADDR_TOP - __FIXADDR_SIZE) +#define FIXADDR_BOOT_START (FIXADDR_TOP - __FIXADDR_BOOT_SIZE) + +#define __fix_to_virt(x) (FIXADDR_TOP - ((x) << PAGE_SHIFT)) +#define __virt_to_fix(x) ((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT) + +/* + * This is the range that is readable by user mode, and things + * acting like user mode such as get_user_pages. + */ +#define FIXADDR_USER_START (__fix_to_virt(FIX_VSYSCALL)) +#define FIXADDR_USER_END (FIXADDR_USER_START + PAGE_SIZE) + + +extern void __this_fixmap_does_not_exist(void); + +/* + * 'index to address' translation. If anyone tries to use the idx + * directly without tranlation, we catch the bug with a NULL-deference + * kernel oops. Illegal ranges of incoming indices are caught too. + */ +static __always_inline unsigned long fix_to_virt(const unsigned int idx) +{ + /* + * this branch gets completely eliminated after inlining, + * except when someone tries to use fixaddr indices in an + * illegal way. (such as mixing up address types or using + * out-of-range indices). + * + * If it doesn't get removed, the linker will complain + * loudly with a reasonably clear error message.. + */ + if (idx >= __end_of_fixed_addresses) + __this_fixmap_does_not_exist(); + + return __fix_to_virt(idx); +} + +static inline unsigned long virt_to_fix(const unsigned long vaddr) +{ + BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START); + return __virt_to_fix(vaddr); +} + +#endif /* !__ASSEMBLY__ */ +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/floppy.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/floppy.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,147 @@ +/* + * Architecture specific parts of the Floppy driver + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 1995 + * + * Modifications for Xen are Copyright (c) 2004, Keir Fraser. + */ +#ifndef __ASM_XEN_I386_FLOPPY_H +#define __ASM_XEN_I386_FLOPPY_H + +#include <linux/vmalloc.h> + +/* XEN: Hit DMA paths on the head. This trick from asm-m68k/floppy.h. */ +#include <asm/dma.h> +#undef MAX_DMA_ADDRESS +#define MAX_DMA_ADDRESS 0 +#define CROSS_64KB(a,s) (0) + +#define fd_inb(port) inb_p(port) +#define fd_outb(value,port) outb_p(value,port) + +#define fd_request_dma() (0) +#define fd_free_dma() ((void)0) +#define fd_enable_irq() enable_irq(FLOPPY_IRQ) +#define fd_disable_irq() disable_irq(FLOPPY_IRQ) +#define fd_free_irq() free_irq(FLOPPY_IRQ, NULL) +#define fd_get_dma_residue() (virtual_dma_count + virtual_dma_residue) +#define fd_dma_setup(addr, size, mode, io) vdma_dma_setup(addr, size, mode, io) +/* + * Do not use vmalloc/vfree: floppy_release_irq_and_dma() gets called from + * softirq context via motor_off_callback. A generic bug we happen to trigger. + */ +#define fd_dma_mem_alloc(size) __get_free_pages(GFP_KERNEL, get_order(size)) +#define fd_dma_mem_free(addr, size) free_pages(addr, get_order(size)) + +static int virtual_dma_count; +static int virtual_dma_residue; +static char *virtual_dma_addr; +static int virtual_dma_mode; +static int doing_pdma; + +static irqreturn_t floppy_hardint(int irq, void *dev_id, struct pt_regs * regs) +{ + register unsigned char st; + register int lcount; + register char *lptr; + + if (!doing_pdma) + return floppy_interrupt(irq, dev_id, regs); + + st = 1; + for(lcount=virtual_dma_count, lptr=virtual_dma_addr; + lcount; lcount--, lptr++) { + st=inb(virtual_dma_port+4) & 0xa0 ; + if(st != 0xa0) + break; + if(virtual_dma_mode) + outb_p(*lptr, virtual_dma_port+5); + else + *lptr = inb_p(virtual_dma_port+5); + } + virtual_dma_count = lcount; + virtual_dma_addr = lptr; + st = inb(virtual_dma_port+4); + + if(st == 0x20) + return IRQ_HANDLED; + if(!(st & 0x20)) { + virtual_dma_residue += virtual_dma_count; + virtual_dma_count=0; + doing_pdma = 0; + floppy_interrupt(irq, dev_id, regs); + return IRQ_HANDLED; + } + return IRQ_HANDLED; +} + +static void fd_disable_dma(void) +{ + doing_pdma = 0; + virtual_dma_residue += virtual_dma_count; + virtual_dma_count=0; +} + +static int fd_request_irq(void) +{ + return request_irq(FLOPPY_IRQ, floppy_hardint,SA_INTERRUPT, + "floppy", NULL); +} + +static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io) +{ + doing_pdma = 1; + virtual_dma_port = io; + virtual_dma_mode = (mode == DMA_MODE_WRITE); + virtual_dma_addr = addr; + virtual_dma_count = size; + virtual_dma_residue = 0; + return 0; +} + +/* XEN: This trick to force 'virtual DMA' is from include/asm-m68k/floppy.h. */ +#define FDC1 xen_floppy_init() +static int FDC2 = -1; + +static int xen_floppy_init(void) +{ + use_virtual_dma = 1; + can_use_virtual_dma = 1; + return 0x3f0; +} + +/* + * Floppy types are stored in the rtc's CMOS RAM and so rtc_lock + * is needed to prevent corrupted CMOS RAM in case "insmod floppy" + * coincides with another rtc CMOS user. Paul G. + */ +#define FLOPPY0_TYPE ({ \ + unsigned long flags; \ + unsigned char val; \ + spin_lock_irqsave(&rtc_lock, flags); \ + val = (CMOS_READ(0x10) >> 4) & 15; \ + spin_unlock_irqrestore(&rtc_lock, flags); \ + val; \ +}) + +#define FLOPPY1_TYPE ({ \ + unsigned long flags; \ + unsigned char val; \ + spin_lock_irqsave(&rtc_lock, flags); \ + val = CMOS_READ(0x10) & 15; \ + spin_unlock_irqrestore(&rtc_lock, flags); \ + val; \ +}) + +#define N_FDC 2 +#define N_DRIVE 8 + +#define FLOPPY_MOTOR_MASK 0xf0 + +#define EXTRA_FLOPPY_PARAMS + +#endif /* __ASM_XEN_I386_FLOPPY_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/highmem.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/highmem.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,80 @@ +/* + * highmem.h: virtual kernel memory mappings for high memory + * + * Used in CONFIG_HIGHMEM systems for memory pages which + * are not addressable by direct kernel virtual addresses. + * + * Copyright (C) 1999 Gerhard Wichert, Siemens AG + * Gerhard.Wichert@xxxxxxxxxxxxxx + * + * + * Redesigned the x86 32-bit VM architecture to deal with + * up to 16 Terabyte physical memory. With current x86 CPUs + * we now support up to 64 Gigabytes physical RAM. + * + * Copyright (C) 1999 Ingo Molnar <mingo@xxxxxxxxxx> + */ + +#ifndef _ASM_HIGHMEM_H +#define _ASM_HIGHMEM_H + +#ifdef __KERNEL__ + +#include <linux/config.h> +#include <linux/interrupt.h> +#include <linux/threads.h> +#include <asm/kmap_types.h> +#include <asm/tlbflush.h> + +/* declarations for highmem.c */ +extern unsigned long highstart_pfn, highend_pfn; + +extern pte_t *kmap_pte; +extern pgprot_t kmap_prot; +extern pte_t *pkmap_page_table; + +/* + * Right now we initialize only a single pte table. It can be extended + * easily, subsequent pte tables have to be allocated in one physical + * chunk of RAM. + */ +#ifdef CONFIG_X86_PAE +#define LAST_PKMAP 512 +#else +#define LAST_PKMAP 1024 +#endif +/* + * Ordering is: + * + * FIXADDR_TOP + * fixed_addresses + * FIXADDR_START + * temp fixed addresses + * FIXADDR_BOOT_START + * Persistent kmap area + * PKMAP_BASE + * VMALLOC_END + * Vmalloc area + * VMALLOC_START + * high_memory + */ +#define PKMAP_BASE ( (FIXADDR_BOOT_START - PAGE_SIZE*(LAST_PKMAP + 1)) & PMD_MASK ) +#define LAST_PKMAP_MASK (LAST_PKMAP-1) +#define PKMAP_NR(virt) ((virt-PKMAP_BASE) >> PAGE_SHIFT) +#define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT)) + +extern void * FASTCALL(kmap_high(struct page *page)); +extern void FASTCALL(kunmap_high(struct page *page)); + +void *kmap(struct page *page); +void kunmap(struct page *page); +void *kmap_atomic(struct page *page, enum km_type type); +void *kmap_atomic_pte(struct page *page, enum km_type type); +void kunmap_atomic(void *kvaddr, enum km_type type); +struct page *kmap_atomic_to_page(void *ptr); + +#define flush_cache_kmaps() do { } while (0) + +#endif /* __KERNEL__ */ + +#endif /* _ASM_HIGHMEM_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/hw_irq.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/hw_irq.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,71 @@ +#ifndef _ASM_HW_IRQ_H +#define _ASM_HW_IRQ_H + +/* + * linux/include/asm/hw_irq.h + * + * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar + * + * moved some of the old arch/i386/kernel/irq.h to here. VY + * + * IRQ/IPI changes taken from work by Thomas Radke + * <tomsoft@xxxxxxxxxxxxxxxxxxxxxxxxx> + */ + +#include <linux/config.h> +#include <linux/profile.h> +#include <asm/atomic.h> +#include <asm/irq.h> +#include <asm/sections.h> + +/* + * Various low-level irq details needed by irq.c, process.c, + * time.c, io_apic.c and smp.c + * + * Interrupt entry/exit code at both C and assembly level + */ + +extern u8 irq_vector[NR_IRQ_VECTORS]; +#define IO_APIC_VECTOR(irq) (irq_vector[irq]) +#define AUTO_ASSIGN -1 + +extern void (*interrupt[NR_IRQS])(void); + +#ifdef CONFIG_SMP +fastcall void reschedule_interrupt(void); +fastcall void invalidate_interrupt(void); +fastcall void call_function_interrupt(void); +#endif + +#ifdef CONFIG_X86_LOCAL_APIC +fastcall void apic_timer_interrupt(void); +fastcall void error_interrupt(void); +fastcall void spurious_interrupt(void); +fastcall void thermal_interrupt(struct pt_regs *); +#define platform_legacy_irq(irq) ((irq) < 16) +#endif + +void disable_8259A_irq(unsigned int irq); +void enable_8259A_irq(unsigned int irq); +int i8259A_irq_pending(unsigned int irq); +void make_8259A_irq(unsigned int irq); +void init_8259A(int aeoi); +void FASTCALL(send_IPI_self(int vector)); +void init_VISWS_APIC_irqs(void); +void setup_IO_APIC(void); +void disable_IO_APIC(void); +void print_IO_APIC(void); +int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn); +void send_IPI(int dest, int vector); +void setup_ioapic_dest(void); + +extern unsigned long io_apic_irqs; + +extern atomic_t irq_err_count; +extern atomic_t irq_mis_count; + +#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs)) + +extern void hw_resend_irq(struct hw_interrupt_type *h, unsigned int i); + +#endif /* _ASM_HW_IRQ_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/hypercall.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/hypercall.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,323 @@ +/****************************************************************************** + * hypercall.h + * + * Linux-specific hypervisor handling. + * + * Copyright (c) 2002-2004, K A Fraser + * + * This file may be distributed separately from the Linux kernel, or + * incorporated into other software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef __HYPERCALL_H__ +#define __HYPERCALL_H__ + +#include <xen/interface/xen.h> +#include <xen/interface/sched.h> +#include <xen/interface/nmi.h> + +#define __STR(x) #x +#define STR(x) __STR(x) + +#define _hypercall0(type, name) \ +({ \ + long __res; \ + asm volatile ( \ + "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ + : "=a" (__res) \ + : \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall1(type, name, a1) \ +({ \ + long __res, __ign1; \ + asm volatile ( \ + "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ + : "=a" (__res), "=b" (__ign1) \ + : "1" ((long)(a1)) \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall2(type, name, a1, a2) \ +({ \ + long __res, __ign1, __ign2; \ + asm volatile ( \ + "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ + : "=a" (__res), "=b" (__ign1), "=c" (__ign2) \ + : "1" ((long)(a1)), "2" ((long)(a2)) \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall3(type, name, a1, a2, a3) \ +({ \ + long __res, __ign1, __ign2, __ign3; \ + asm volatile ( \ + "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ + : "=a" (__res), "=b" (__ign1), "=c" (__ign2), \ + "=d" (__ign3) \ + : "1" ((long)(a1)), "2" ((long)(a2)), \ + "3" ((long)(a3)) \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall4(type, name, a1, a2, a3, a4) \ +({ \ + long __res, __ign1, __ign2, __ign3, __ign4; \ + asm volatile ( \ + "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ + : "=a" (__res), "=b" (__ign1), "=c" (__ign2), \ + "=d" (__ign3), "=S" (__ign4) \ + : "1" ((long)(a1)), "2" ((long)(a2)), \ + "3" ((long)(a3)), "4" ((long)(a4)) \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall5(type, name, a1, a2, a3, a4, a5) \ +({ \ + long __res, __ign1, __ign2, __ign3, __ign4, __ign5; \ + asm volatile ( \ + "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ + : "=a" (__res), "=b" (__ign1), "=c" (__ign2), \ + "=d" (__ign3), "=S" (__ign4), "=D" (__ign5) \ + : "1" ((long)(a1)), "2" ((long)(a2)), \ + "3" ((long)(a3)), "4" ((long)(a4)), \ + "5" ((long)(a5)) \ + : "memory" ); \ + (type)__res; \ +}) + +static inline int +HYPERVISOR_set_trap_table( + trap_info_t *table) +{ + return _hypercall1(int, set_trap_table, table); +} + +static inline int +HYPERVISOR_mmu_update( + mmu_update_t *req, int count, int *success_count, domid_t domid) +{ + return _hypercall4(int, mmu_update, req, count, success_count, domid); +} + +static inline int +HYPERVISOR_mmuext_op( + struct mmuext_op *op, int count, int *success_count, domid_t domid) +{ + return _hypercall4(int, mmuext_op, op, count, success_count, domid); +} + +static inline int +HYPERVISOR_set_gdt( + unsigned long *frame_list, int entries) +{ + return _hypercall2(int, set_gdt, frame_list, entries); +} + +static inline int +HYPERVISOR_stack_switch( + unsigned long ss, unsigned long esp) +{ + return _hypercall2(int, stack_switch, ss, esp); +} + +static inline int +HYPERVISOR_set_callbacks( + unsigned long event_selector, unsigned long event_address, + unsigned long failsafe_selector, unsigned long failsafe_address) +{ + return _hypercall4(int, set_callbacks, + event_selector, event_address, + failsafe_selector, failsafe_address); +} + +static inline int +HYPERVISOR_fpu_taskswitch( + int set) +{ + return _hypercall1(int, fpu_taskswitch, set); +} + +static inline int +HYPERVISOR_sched_op( + int cmd, unsigned long arg) +{ + return _hypercall2(int, sched_op, cmd, arg); +} + +static inline long +HYPERVISOR_set_timer_op( + u64 timeout) +{ + unsigned long timeout_hi = (unsigned long)(timeout>>32); + unsigned long timeout_lo = (unsigned long)timeout; + return _hypercall2(long, set_timer_op, timeout_lo, timeout_hi); +} + +static inline int +HYPERVISOR_dom0_op( + dom0_op_t *dom0_op) +{ + dom0_op->interface_version = DOM0_INTERFACE_VERSION; + return _hypercall1(int, dom0_op, dom0_op); +} + +static inline int +HYPERVISOR_set_debugreg( + int reg, unsigned long value) +{ + return _hypercall2(int, set_debugreg, reg, value); +} + +static inline unsigned long +HYPERVISOR_get_debugreg( + int reg) +{ + return _hypercall1(unsigned long, get_debugreg, reg); +} + +static inline int +HYPERVISOR_update_descriptor( + u64 ma, u64 desc) +{ + return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32); +} + +static inline int +HYPERVISOR_memory_op( + unsigned int cmd, void *arg) +{ + return _hypercall2(int, memory_op, cmd, arg); +} + +static inline int +HYPERVISOR_multicall( + void *call_list, int nr_calls) +{ + return _hypercall2(int, multicall, call_list, nr_calls); +} + +static inline int +HYPERVISOR_update_va_mapping( + unsigned long va, pte_t new_val, unsigned long flags) +{ + unsigned long pte_hi = 0; +#ifdef CONFIG_X86_PAE + pte_hi = new_val.pte_high; +#endif + return _hypercall4(int, update_va_mapping, va, + new_val.pte_low, pte_hi, flags); +} + +static inline int +HYPERVISOR_event_channel_op( + void *op) +{ + return _hypercall1(int, event_channel_op, op); +} + +static inline int +HYPERVISOR_xen_version( + int cmd, void *arg) +{ + return _hypercall2(int, xen_version, cmd, arg); +} + +static inline int +HYPERVISOR_console_io( + int cmd, int count, char *str) +{ + return _hypercall3(int, console_io, cmd, count, str); +} + +static inline int +HYPERVISOR_physdev_op( + void *physdev_op) +{ + return _hypercall1(int, physdev_op, physdev_op); +} + +static inline int +HYPERVISOR_grant_table_op( + unsigned int cmd, void *uop, unsigned int count) +{ + return _hypercall3(int, grant_table_op, cmd, uop, count); +} + +static inline int +HYPERVISOR_update_va_mapping_otherdomain( + unsigned long va, pte_t new_val, unsigned long flags, domid_t domid) +{ + unsigned long pte_hi = 0; +#ifdef CONFIG_X86_PAE + pte_hi = new_val.pte_high; +#endif + return _hypercall5(int, update_va_mapping_otherdomain, va, + new_val.pte_low, pte_hi, flags, domid); +} + +static inline int +HYPERVISOR_vm_assist( + unsigned int cmd, unsigned int type) +{ + return _hypercall2(int, vm_assist, cmd, type); +} + +static inline int +HYPERVISOR_vcpu_op( + int cmd, int vcpuid, void *extra_args) +{ + return _hypercall3(int, vcpu_op, cmd, vcpuid, extra_args); +} + +static inline int +HYPERVISOR_suspend( + unsigned long srec) +{ + return _hypercall3(int, sched_op, SCHEDOP_shutdown, + SHUTDOWN_suspend, srec); +} + +static inline int +HYPERVISOR_nmi_op( + unsigned long op, + unsigned long arg) +{ + return _hypercall2(int, nmi_op, op, arg); +} + +#endif /* __HYPERCALL_H__ */ + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/hypervisor.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/hypervisor.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,175 @@ +/****************************************************************************** + * hypervisor.h + * + * Linux-specific hypervisor handling. + * + * Copyright (c) 2002-2004, K A Fraser + * + * This file may be distributed separately from the Linux kernel, or + * incorporated into other software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef __HYPERVISOR_H__ +#define __HYPERVISOR_H__ + +#include <linux/config.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/version.h> +#include <xen/interface/xen.h> +#include <xen/interface/dom0_ops.h> +#include <asm/ptrace.h> +#include <asm/page.h> +#if defined(__i386__) +# ifdef CONFIG_X86_PAE +# include <asm-generic/pgtable-nopud.h> +# else +# include <asm-generic/pgtable-nopmd.h> +# endif +#endif + +extern shared_info_t *HYPERVISOR_shared_info; + +/* arch/xen/i386/kernel/setup.c */ +extern start_info_t *xen_start_info; + +/* arch/xen/kernel/evtchn.c */ +/* Force a proper event-channel callback from Xen. */ +void force_evtchn_callback(void); + +/* arch/xen/kernel/process.c */ +void xen_cpu_idle (void); + +/* arch/xen/i386/kernel/hypervisor.c */ +void do_hypervisor_callback(struct pt_regs *regs); + +/* arch/xen/i386/kernel/head.S */ +void lgdt_finish(void); + +/* arch/xen/i386/mm/hypervisor.c */ +/* + * NB. ptr values should be PHYSICAL, not MACHINE. 'vals' should be already + * be MACHINE addresses. + */ + +void xen_pt_switch(unsigned long ptr); +void xen_new_user_pt(unsigned long ptr); /* x86_64 only */ +void xen_load_gs(unsigned int selector); /* x86_64 only */ +void xen_tlb_flush(void); +void xen_invlpg(unsigned long ptr); + +#ifndef CONFIG_XEN_SHADOW_MODE +void xen_l1_entry_update(pte_t *ptr, pte_t val); +void xen_l2_entry_update(pmd_t *ptr, pmd_t val); +void xen_l3_entry_update(pud_t *ptr, pud_t val); /* x86_64/PAE */ +void xen_l4_entry_update(pgd_t *ptr, pgd_t val); /* x86_64 only */ +void xen_pgd_pin(unsigned long ptr); +void xen_pgd_unpin(unsigned long ptr); +void xen_pud_pin(unsigned long ptr); /* x86_64 only */ +void xen_pud_unpin(unsigned long ptr); /* x86_64 only */ +void xen_pmd_pin(unsigned long ptr); /* x86_64 only */ +void xen_pmd_unpin(unsigned long ptr); /* x86_64 only */ +void xen_pte_pin(unsigned long ptr); +void xen_pte_unpin(unsigned long ptr); +#else +#define xen_l1_entry_update(_p, _v) set_pte((_p), (_v)) +#define xen_l2_entry_update(_p, _v) set_pgd((_p), (_v)) +#define xen_pgd_pin(_p) ((void)0) +#define xen_pgd_unpin(_p) ((void)0) +#define xen_pte_pin(_p) ((void)0) +#define xen_pte_unpin(_p) ((void)0) +#endif + +void xen_set_ldt(unsigned long ptr, unsigned long bytes); +void xen_machphys_update(unsigned long mfn, unsigned long pfn); + +#ifdef CONFIG_SMP +#include <linux/cpumask.h> +void xen_tlb_flush_all(void); +void xen_invlpg_all(unsigned long ptr); +void xen_tlb_flush_mask(cpumask_t *mask); +void xen_invlpg_mask(cpumask_t *mask, unsigned long ptr); +#endif + +/* Returns zero on success else negative errno. */ +int xen_create_contiguous_region( + unsigned long vstart, unsigned int order, unsigned int address_bits); +void xen_destroy_contiguous_region( + unsigned long vstart, unsigned int order); + +#include <asm/hypercall.h> + +#if defined(CONFIG_X86_64) +#define MULTI_UVMFLAGS_INDEX 2 +#define MULTI_UVMDOMID_INDEX 3 +#else +#define MULTI_UVMFLAGS_INDEX 3 +#define MULTI_UVMDOMID_INDEX 4 +#endif + +#define xen_init() (0) + +static inline void +MULTI_update_va_mapping( + multicall_entry_t *mcl, unsigned long va, + pte_t new_val, unsigned long flags) +{ + mcl->op = __HYPERVISOR_update_va_mapping; + mcl->args[0] = va; +#if defined(CONFIG_X86_64) + mcl->args[1] = new_val.pte; + mcl->args[2] = flags; +#elif defined(CONFIG_X86_PAE) + mcl->args[1] = new_val.pte_low; + mcl->args[2] = new_val.pte_high; + mcl->args[3] = flags; +#else + mcl->args[1] = new_val.pte_low; + mcl->args[2] = 0; + mcl->args[3] = flags; +#endif +} + +static inline void +MULTI_update_va_mapping_otherdomain( + multicall_entry_t *mcl, unsigned long va, + pte_t new_val, unsigned long flags, domid_t domid) +{ + mcl->op = __HYPERVISOR_update_va_mapping_otherdomain; + mcl->args[0] = va; +#if defined(CONFIG_X86_64) + mcl->args[1] = new_val.pte; + mcl->args[2] = flags; + mcl->args[3] = domid; +#elif defined(CONFIG_X86_PAE) + mcl->args[1] = new_val.pte_low; + mcl->args[2] = new_val.pte_high; + mcl->args[3] = flags; + mcl->args[4] = domid; +#else + mcl->args[1] = new_val.pte_low; + mcl->args[2] = 0; + mcl->args[3] = flags; + mcl->args[4] = domid; +#endif +} + +#endif /* __HYPERVISOR_H__ */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/io.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/io.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,400 @@ +#ifndef _ASM_IO_H +#define _ASM_IO_H + +#include <linux/config.h> +#include <linux/string.h> +#include <linux/compiler.h> + +/* + * This file contains the definitions for the x86 IO instructions + * inb/inw/inl/outb/outw/outl and the "string versions" of the same + * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing" + * versions of the single-IO instructions (inb_p/inw_p/..). + * + * This file is not meant to be obfuscating: it's just complicated + * to (a) handle it all in a way that makes gcc able to optimize it + * as well as possible and (b) trying to avoid writing the same thing + * over and over again with slight variations and possibly making a + * mistake somewhere. + */ + +/* + * Thanks to James van Artsdalen for a better timing-fix than + * the two short jumps: using outb's to a nonexistent port seems + * to guarantee better timings even on fast machines. + * + * On the other hand, I'd like to be sure of a non-existent port: + * I feel a bit unsafe about using 0x80 (should be safe, though) + * + * Linus + */ + + /* + * Bit simplified and optimized by Jan Hubicka + * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999. + * + * isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added, + * isa_read[wl] and isa_write[wl] fixed + * - Arnaldo Carvalho de Melo <acme@xxxxxxxxxxxxxxxx> + */ + +#define IO_SPACE_LIMIT 0xffff + +#define XQUAD_PORTIO_BASE 0xfe400000 +#define XQUAD_PORTIO_QUAD 0x40000 /* 256k per quad. */ + +#ifdef __KERNEL__ + +#include <asm-generic/iomap.h> + +#include <linux/vmalloc.h> +#include <asm/fixmap.h> + +/* + * Convert a physical pointer to a virtual kernel pointer for /dev/mem + * access + */ +#define xlate_dev_mem_ptr(p) __va(p) + +/* + * Convert a virtual cached pointer to an uncached pointer + */ +#define xlate_dev_kmem_ptr(p) p + +/** + * virt_to_phys - map virtual addresses to physical + * @address: address to remap + * + * The returned physical address is the physical (CPU) mapping for + * the memory address given. It is only valid to use this function on + * addresses directly mapped or allocated via kmalloc. + * + * This function does not give bus mappings for DMA transfers. In + * almost all conceivable cases a device driver should not be using + * this function + */ + +static inline unsigned long virt_to_phys(volatile void * address) +{ + return __pa(address); +} + +/** + * phys_to_virt - map physical address to virtual + * @address: address to remap + * + * The returned virtual address is a current CPU mapping for + * the memory address given. It is only valid to use this function on + * addresses that have a kernel mapping + * + * This function does not handle bus mappings for DMA transfers. In + * almost all conceivable cases a device driver should not be using + * this function + */ + +static inline void * phys_to_virt(unsigned long address) +{ + return __va(address); +} + +/* + * Change "struct page" to physical address. + */ +#define page_to_pseudophys(page) ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT) +#define page_to_phys(page) (phys_to_machine(page_to_pseudophys(page))) + +#define bio_to_pseudophys(bio) (page_to_pseudophys(bio_page((bio))) + \ + (unsigned long) bio_offset((bio))) +#define bvec_to_pseudophys(bv) (page_to_pseudophys((bv)->bv_page) + \ + (unsigned long) (bv)->bv_offset) + +#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ + (((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2))) && \ + ((bvec_to_pseudophys((vec1)) + (vec1)->bv_len) == \ + bvec_to_pseudophys((vec2)))) + +extern void __iomem * __ioremap(unsigned long offset, unsigned long size, unsigned long flags); + +/** + * ioremap - map bus memory into CPU space + * @offset: bus address of the memory + * @size: size of the resource to map + * + * ioremap performs a platform specific sequence of operations to + * make bus memory CPU accessible via the readb/readw/readl/writeb/ + * writew/writel functions and the other mmio helpers. The returned + * address is not guaranteed to be usable directly as a virtual + * address. + */ + +static inline void __iomem * ioremap(unsigned long offset, unsigned long size) +{ + return __ioremap(offset, size, 0); +} + +extern void __iomem * ioremap_nocache(unsigned long offset, unsigned long size); +extern void iounmap(volatile void __iomem *addr); + +/* + * bt_ioremap() and bt_iounmap() are for temporary early boot-time + * mappings, before the real ioremap() is functional. + * A boot-time mapping is currently limited to at most 16 pages. + */ +extern void *bt_ioremap(unsigned long offset, unsigned long size); +extern void bt_iounmap(void *addr, unsigned long size); + +/* + * ISA I/O bus memory addresses are 1:1 with the physical address. + */ +#define isa_virt_to_bus(_x) isa_virt_to_bus_is_UNSUPPORTED->x +#define isa_page_to_bus(_x) isa_page_to_bus_is_UNSUPPORTED->x +#ifdef CONFIG_XEN_PHYSDEV_ACCESS +#define isa_bus_to_virt(_x) (void *)(__fix_to_virt(FIX_ISAMAP_BEGIN) + (_x)) +#else +#define isa_bus_to_virt(_x) isa_bus_to_virt_needs_PRIVILEGED_BUILD +#endif + +/* + * However PCI ones are not necessarily 1:1 and therefore these interfaces + * are forbidden in portable PCI drivers. + * + * Allow them on x86 for legacy drivers, though. + */ +#define virt_to_bus(_x) phys_to_machine(__pa(_x)) +#define bus_to_virt(_x) __va(machine_to_phys(_x)) + +/* + * readX/writeX() are used to access memory mapped devices. On some + * architectures the memory mapped IO stuff needs to be accessed + * differently. On the x86 architecture, we just read/write the + * memory location directly. + */ + +static inline unsigned char readb(const volatile void __iomem *addr) +{ + return *(volatile unsigned char __force *) addr; +} +static inline unsigned short readw(const volatile void __iomem *addr) +{ + return *(volatile unsigned short __force *) addr; +} +static inline unsigned int readl(const volatile void __iomem *addr) +{ + return *(volatile unsigned int __force *) addr; +} +#define readb_relaxed(addr) readb(addr) +#define readw_relaxed(addr) readw(addr) +#define readl_relaxed(addr) readl(addr) +#define __raw_readb readb +#define __raw_readw readw +#define __raw_readl readl + +static inline void writeb(unsigned char b, volatile void __iomem *addr) +{ + *(volatile unsigned char __force *) addr = b; +} +static inline void writew(unsigned short b, volatile void __iomem *addr) +{ + *(volatile unsigned short __force *) addr = b; +} +static inline void writel(unsigned int b, volatile void __iomem *addr) +{ + *(volatile unsigned int __force *) addr = b; +} +#define __raw_writeb writeb +#define __raw_writew writew +#define __raw_writel writel + +#define mmiowb() + +static inline void memset_io(volatile void __iomem *addr, unsigned char val, int count) +{ + memset((void __force *) addr, val, count); +} +static inline void memcpy_fromio(void *dst, const volatile void __iomem *src, int count) +{ + __memcpy(dst, (void __force *) src, count); +} +static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int count) +{ + __memcpy((void __force *) dst, src, count); +} + +/* + * ISA space is 'always mapped' on a typical x86 system, no need to + * explicitly ioremap() it. The fact that the ISA IO space is mapped + * to PAGE_OFFSET is pure coincidence - it does not mean ISA values + * are physical addresses. The following constant pointer can be + * used as the IO-area pointer (it can be iounmapped as well, so the + * analogy with PCI is quite large): + */ +#define __ISA_IO_base ((char __iomem *)(fix_to_virt(FIX_ISAMAP_BEGIN))) + +#define isa_readb(a) readb(__ISA_IO_base + (a)) +#define isa_readw(a) readw(__ISA_IO_base + (a)) +#define isa_readl(a) readl(__ISA_IO_base + (a)) +#define isa_writeb(b,a) writeb(b,__ISA_IO_base + (a)) +#define isa_writew(w,a) writew(w,__ISA_IO_base + (a)) +#define isa_writel(l,a) writel(l,__ISA_IO_base + (a)) +#define isa_memset_io(a,b,c) memset_io(__ISA_IO_base + (a),(b),(c)) +#define isa_memcpy_fromio(a,b,c) memcpy_fromio((a),__ISA_IO_base + (b),(c)) +#define isa_memcpy_toio(a,b,c) memcpy_toio(__ISA_IO_base + (a),(b),(c)) + + +/* + * Again, i386 does not require mem IO specific function. + */ + +#define eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void __force *)(b),(c),(d)) +#define isa_eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void __force *)(__ISA_IO_base + (b)),(c),(d)) + +/** + * check_signature - find BIOS signatures + * @io_addr: mmio address to check + * @signature: signature block + * @length: length of signature + * + * Perform a signature comparison with the mmio address io_addr. This + * address should have been obtained by ioremap. + * Returns 1 on a match. + */ + +static inline int check_signature(volatile void __iomem * io_addr, + const unsigned char *signature, int length) +{ + int retval = 0; + do { + if (readb(io_addr) != *signature) + goto out; + io_addr++; + signature++; + length--; + } while (length); + retval = 1; +out: + return retval; +} + +/* + * Cache management + * + * This needed for two cases + * 1. Out of order aware processors + * 2. Accidentally out of order processors (PPro errata #51) + */ + +#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE) + +static inline void flush_write_buffers(void) +{ + __asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory"); +} + +#define dma_cache_inv(_start,_size) flush_write_buffers() +#define dma_cache_wback(_start,_size) flush_write_buffers() +#define dma_cache_wback_inv(_start,_size) flush_write_buffers() + +#else + +/* Nothing to do */ + +#define dma_cache_inv(_start,_size) do { } while (0) +#define dma_cache_wback(_start,_size) do { } while (0) +#define dma_cache_wback_inv(_start,_size) do { } while (0) +#define flush_write_buffers() + +#endif + +#endif /* __KERNEL__ */ + +#ifdef SLOW_IO_BY_JUMPING +#define __SLOW_DOWN_IO "jmp 1f; 1: jmp 1f; 1:" +#else +#define __SLOW_DOWN_IO "outb %%al,$0x80;" +#endif + +static inline void slow_down_io(void) { + __asm__ __volatile__( + __SLOW_DOWN_IO +#ifdef REALLY_SLOW_IO + __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO +#endif + : : ); +} + +#ifdef CONFIG_X86_NUMAQ +extern void *xquad_portio; /* Where the IO area was mapped */ +#define XQUAD_PORT_ADDR(port, quad) (xquad_portio + (XQUAD_PORTIO_QUAD*quad) + port) +#define __BUILDIO(bwl,bw,type) \ +static inline void out##bwl##_quad(unsigned type value, int port, int quad) { \ + if (xquad_portio) \ + write##bwl(value, XQUAD_PORT_ADDR(port, quad)); \ + else \ + out##bwl##_local(value, port); \ +} \ +static inline void out##bwl(unsigned type value, int port) { \ + out##bwl##_quad(value, port, 0); \ +} \ +static inline unsigned type in##bwl##_quad(int port, int quad) { \ + if (xquad_portio) \ + return read##bwl(XQUAD_PORT_ADDR(port, quad)); \ + else \ + return in##bwl##_local(port); \ +} \ +static inline unsigned type in##bwl(int port) { \ + return in##bwl##_quad(port, 0); \ +} +#else +#define __BUILDIO(bwl,bw,type) \ +static inline void out##bwl(unsigned type value, int port) { \ + out##bwl##_local(value, port); \ +} \ +static inline unsigned type in##bwl(int port) { \ + return in##bwl##_local(port); \ +} +#endif + + +#define BUILDIO(bwl,bw,type) \ +static inline void out##bwl##_local(unsigned type value, int port) { \ + __asm__ __volatile__("out" #bwl " %" #bw "0, %w1" : : "a"(value), "Nd"(port)); \ +} \ +static inline unsigned type in##bwl##_local(int port) { \ + unsigned type value; \ + __asm__ __volatile__("in" #bwl " %w1, %" #bw "0" : "=a"(value) : "Nd"(port)); \ + return value; \ +} \ +static inline void out##bwl##_local_p(unsigned type value, int port) { \ + out##bwl##_local(value, port); \ + slow_down_io(); \ +} \ +static inline unsigned type in##bwl##_local_p(int port) { \ + unsigned type value = in##bwl##_local(port); \ + slow_down_io(); \ + return value; \ +} \ +__BUILDIO(bwl,bw,type) \ +static inline void out##bwl##_p(unsigned type value, int port) { \ + out##bwl(value, port); \ + slow_down_io(); \ +} \ +static inline unsigned type in##bwl##_p(int port) { \ + unsigned type value = in##bwl(port); \ + slow_down_io(); \ + return value; \ +} \ +static inline void outs##bwl(int port, const void *addr, unsigned long count) { \ + __asm__ __volatile__("rep; outs" #bwl : "+S"(addr), "+c"(count) : "d"(port)); \ +} \ +static inline void ins##bwl(int port, void *addr, unsigned long count) { \ + __asm__ __volatile__("rep; ins" #bwl : "+D"(addr), "+c"(count) : "d"(port)); \ +} + +BUILDIO(b,b,char) +BUILDIO(w,w,short) +BUILDIO(l,,int) + +/* We will be supplying our own /dev/mem implementation */ +#define ARCH_HAS_DEV_MEM + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/kmap_types.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/kmap_types.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,32 @@ +#ifndef _ASM_KMAP_TYPES_H +#define _ASM_KMAP_TYPES_H + +#include <linux/config.h> + +#ifdef CONFIG_DEBUG_HIGHMEM +# define D(n) __KM_FENCE_##n , +#else +# define D(n) +#endif + +enum km_type { +D(0) KM_BOUNCE_READ, +D(1) KM_SKB_SUNRPC_DATA, +D(2) KM_SKB_DATA_SOFTIRQ, +D(3) KM_USER0, +D(4) KM_USER1, +D(5) KM_BIO_SRC_IRQ, +D(6) KM_BIO_DST_IRQ, +D(7) KM_PTE0, +D(8) KM_PTE1, +D(9) KM_IRQ0, +D(10) KM_IRQ1, +D(11) KM_SOFTIRQ0, +D(12) KM_SOFTIRQ1, +D(13) KM_SWIOTLB, +D(14) KM_TYPE_NR +}; + +#undef D + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/mmu.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/mmu.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,21 @@ +#ifndef __i386_MMU_H +#define __i386_MMU_H + +#include <asm/semaphore.h> +/* + * The i386 doesn't have a mmu context, but + * we put the segment information here. + * + * cpu_vm_mask is used to optimize ldt flushing. + */ +typedef struct { + int size; + struct semaphore sem; + void *ldt; +} mm_context_t; + +/* mm/memory.c:exit_mmap hook */ +extern void _arch_exit_mmap(struct mm_struct *mm); +#define arch_exit_mmap(_mm) _arch_exit_mmap(_mm) + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/mmu_context.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/mmu_context.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,108 @@ +#ifndef __I386_SCHED_H +#define __I386_SCHED_H + +#include <linux/config.h> +#include <asm/desc.h> +#include <asm/atomic.h> +#include <asm/pgalloc.h> +#include <asm/tlbflush.h> + +/* + * Used for LDT copy/destruction. + */ +int init_new_context(struct task_struct *tsk, struct mm_struct *mm); +void destroy_context(struct mm_struct *mm); + + +static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) +{ +#if 0 /* XEN: no lazy tlb */ + unsigned cpu = smp_processor_id(); + if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK) + per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_LAZY; +#endif +} + +#define prepare_arch_switch(rq,next) __prepare_arch_switch() +#define finish_arch_switch(rq, next) spin_unlock_irq(&(rq)->lock) +#define task_running(rq, p) ((rq)->curr == (p)) + +static inline void __prepare_arch_switch(void) +{ + /* + * Save away %fs and %gs. No need to save %es and %ds, as those + * are always kernel segments while inside the kernel. Must + * happen before reload of cr3/ldt (i.e., not in __switch_to). + */ + asm volatile ( "mov %%fs,%0 ; mov %%gs,%1" + : "=m" (current->thread.fs), + "=m" (current->thread.gs)); + asm volatile ( "movl %0,%%fs ; movl %0,%%gs" + : : "r" (0) ); +} + +extern void mm_pin(struct mm_struct *mm); +extern void mm_unpin(struct mm_struct *mm); +void mm_pin_all(void); + +static inline void switch_mm(struct mm_struct *prev, + struct mm_struct *next, + struct task_struct *tsk) +{ + int cpu = smp_processor_id(); + struct mmuext_op _op[2], *op = _op; + + if (likely(prev != next)) { + if (!test_bit(PG_pinned, &virt_to_page(next->pgd)->flags)) + mm_pin(next); + + /* stop flush ipis for the previous mm */ + cpu_clear(cpu, prev->cpu_vm_mask); +#if 0 /* XEN: no lazy tlb */ + per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK; + per_cpu(cpu_tlbstate, cpu).active_mm = next; +#endif + cpu_set(cpu, next->cpu_vm_mask); + + /* Re-load page tables: load_cr3(next->pgd) */ + per_cpu(cur_pgd, cpu) = next->pgd; + op->cmd = MMUEXT_NEW_BASEPTR; + op->arg1.mfn = pfn_to_mfn(__pa(next->pgd) >> PAGE_SHIFT); + op++; + + /* + * load the LDT, if the LDT is different: + */ + if (unlikely(prev->context.ldt != next->context.ldt)) { + /* load_LDT_nolock(&next->context, cpu) */ + op->cmd = MMUEXT_SET_LDT; + op->arg1.linear_addr = (unsigned long)next->context.ldt; + op->arg2.nr_ents = next->context.size; + op++; + } + + BUG_ON(HYPERVISOR_mmuext_op(_op, op-_op, NULL, DOMID_SELF)); + } +#if 0 /* XEN: no lazy tlb */ + else { + per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK; + BUG_ON(per_cpu(cpu_tlbstate, cpu).active_mm != next); + + if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) { + /* We were in lazy tlb mode and leave_mm disabled + * tlb flush IPI delivery. We must reload %cr3. + */ + load_cr3(next->pgd); + load_LDT_nolock(&next->context, cpu); + } + } +#endif +} + +#define deactivate_mm(tsk, mm) \ + asm("movl %0,%%fs ; movl %0,%%gs": :"r" (0)) + +#define activate_mm(prev, next) \ + switch_mm((prev),(next),NULL) + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/page.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/page.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,276 @@ +#ifndef _I386_PAGE_H +#define _I386_PAGE_H + +/* PAGE_SHIFT determines the page size */ +#define PAGE_SHIFT 12 +#define PAGE_SIZE (1UL << PAGE_SHIFT) +#define PAGE_MASK (~(PAGE_SIZE-1)) + +#define LARGE_PAGE_MASK (~(LARGE_PAGE_SIZE-1)) +#define LARGE_PAGE_SIZE (1UL << PMD_SHIFT) + +#ifdef __KERNEL__ +#ifndef __ASSEMBLY__ + +#include <linux/config.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <asm/bug.h> +#include <xen/interface/xen.h> +#include <xen/foreign_page.h> + +#define arch_free_page(_page,_order) \ +({ int foreign = PageForeign(_page); \ + if (foreign) \ + (PageForeignDestructor(_page))(_page); \ + foreign; \ +}) +#define HAVE_ARCH_FREE_PAGE + +#ifdef CONFIG_XEN_SCRUB_PAGES +#define scrub_pages(_p,_n) memset((void *)(_p), 0, (_n) << PAGE_SHIFT) +#else +#define scrub_pages(_p,_n) ((void)0) +#endif + +#ifdef CONFIG_X86_USE_3DNOW + +#include <asm/mmx.h> + +#define clear_page(page) mmx_clear_page((void *)(page)) +#define copy_page(to,from) mmx_copy_page(to,from) + +#else + +#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr) +#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE + +/* + * On older X86 processors it's not a win to use MMX here it seems. + * Maybe the K6-III ? + */ + +#define clear_page(page) memset((void *)(page), 0, PAGE_SIZE) +#define copy_page(to,from) memcpy((void *)(to), (void *)(from), PAGE_SIZE) + +#endif + +#define clear_user_page(page, vaddr, pg) clear_page(page) +#define copy_user_page(to, from, vaddr, pg) copy_page(to, from) + +/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/ +#define INVALID_P2M_ENTRY (~0UL) +#define FOREIGN_FRAME(m) ((m) | (1UL<<31)) +extern unsigned long *phys_to_machine_mapping; +#define pfn_to_mfn(pfn) \ +(phys_to_machine_mapping[(unsigned int)(pfn)] & ~(1UL<<31)) +#define phys_to_machine_mapping_valid(pfn) \ + (phys_to_machine_mapping[pfn] != INVALID_P2M_ENTRY) +static inline unsigned long mfn_to_pfn(unsigned long mfn) +{ + unsigned long pfn; + + /* + * The array access can fail (e.g., device space beyond end of RAM). + * In such cases it doesn't matter what we return (we return garbage), + * but we must handle the fault without crashing! + */ + asm ( + "1: movl %1,%0\n" + "2:\n" + ".section __ex_table,\"a\"\n" + " .align 4\n" + " .long 1b,2b\n" + ".previous" + : "=r" (pfn) : "m" (machine_to_phys_mapping[mfn]) ); + + return pfn; +} + +static inline void set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + phys_to_machine_mapping[pfn] = mfn; +} + +/* Definitions for machine and pseudophysical addresses. */ +#ifdef CONFIG_X86_PAE +typedef unsigned long long paddr_t; +typedef unsigned long long maddr_t; +#else +typedef unsigned long paddr_t; +typedef unsigned long maddr_t; +#endif + +static inline maddr_t phys_to_machine(paddr_t phys) +{ + maddr_t machine = pfn_to_mfn(phys >> PAGE_SHIFT); + machine = (machine << PAGE_SHIFT) | (phys & ~PAGE_MASK); + return machine; +} +static inline paddr_t machine_to_phys(maddr_t machine) +{ + paddr_t phys = mfn_to_pfn(machine >> PAGE_SHIFT); + phys = (phys << PAGE_SHIFT) | (machine & ~PAGE_MASK); + return phys; +} + +/* + * These are used to make use of C type-checking.. + */ +extern int nx_enabled; +#ifdef CONFIG_X86_PAE +extern unsigned long long __supported_pte_mask; +typedef struct { unsigned long pte_low, pte_high; } pte_t; +typedef struct { unsigned long long pmd; } pmd_t; +typedef struct { unsigned long long pgd; } pgd_t; +typedef struct { unsigned long long pgprot; } pgprot_t; +#define __pte(x) ({ unsigned long long _x = (x); \ + if (_x & 1) _x = phys_to_machine(_x); \ + ((pte_t) {(unsigned long)(_x), (unsigned long)(_x>>32)}); }) +#define __pgd(x) ({ unsigned long long _x = (x); \ + (((_x)&1) ? ((pgd_t) {phys_to_machine(_x)}) : ((pgd_t) {(_x)})); }) +#define __pmd(x) ({ unsigned long long _x = (x); \ + (((_x)&1) ? ((pmd_t) {phys_to_machine(_x)}) : ((pmd_t) {(_x)})); }) +static inline unsigned long long pte_val(pte_t x) +{ + unsigned long long ret; + + if (x.pte_low) { + ret = x.pte_low | (unsigned long long)x.pte_high << 32; + ret = machine_to_phys(ret) | 1; + } else { + ret = 0; + } + return ret; +} +static inline unsigned long long pmd_val(pmd_t x) +{ + unsigned long long ret = x.pmd; + if (ret) ret = machine_to_phys(ret) | 1; + return ret; +} +static inline unsigned long long pgd_val(pgd_t x) +{ + unsigned long long ret = x.pgd; + if (ret) ret = machine_to_phys(ret) | 1; + return ret; +} +static inline unsigned long long pte_val_ma(pte_t x) +{ + return (unsigned long long)x.pte_high << 32 | x.pte_low; +} +#define HPAGE_SHIFT 21 +#else +typedef struct { unsigned long pte_low; } pte_t; +typedef struct { unsigned long pgd; } pgd_t; +typedef struct { unsigned long pgprot; } pgprot_t; +#define boot_pte_t pte_t /* or would you rather have a typedef */ +#define pte_val(x) (((x).pte_low & 1) ? machine_to_phys((x).pte_low) : \ + (x).pte_low) +#define pte_val_ma(x) ((x).pte_low) +#define __pte(x) ({ unsigned long _x = (x); \ + (((_x)&1) ? ((pte_t) {phys_to_machine(_x)}) : ((pte_t) {(_x)})); }) +#define __pgd(x) ({ unsigned long _x = (x); \ + (((_x)&1) ? ((pgd_t) {phys_to_machine(_x)}) : ((pgd_t) {(_x)})); }) +static inline unsigned long pgd_val(pgd_t x) +{ + unsigned long ret = x.pgd; + if (ret) ret = machine_to_phys(ret) | 1; + return ret; +} +#define HPAGE_SHIFT 22 +#endif +#define PTE_MASK PAGE_MASK + +#ifdef CONFIG_HUGETLB_PAGE +#define HPAGE_SIZE ((1UL) << HPAGE_SHIFT) +#define HPAGE_MASK (~(HPAGE_SIZE - 1)) +#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) +#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA +#endif + +#define pgprot_val(x) ((x).pgprot) + +#define __pte_ma(x) ((pte_t) { (x) } ) +#define __pgprot(x) ((pgprot_t) { (x) } ) + +#endif /* !__ASSEMBLY__ */ + +/* to align the pointer to the (next) page boundary */ +#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) + +/* + * This handles the memory map.. We could make this a config + * option, but too many people screw it up, and too few need + * it. + * + * A __PAGE_OFFSET of 0xC0000000 means that the kernel has + * a virtual address space of one gigabyte, which limits the + * amount of physical memory you can use to about 950MB. + * + * If you want more physical memory than this then see the CONFIG_HIGHMEM4G + * and CONFIG_HIGHMEM64G options in the kernel configuration. + */ + +#ifndef __ASSEMBLY__ + +/* + * This much address space is reserved for vmalloc() and iomap() + * as well as fixmap mappings. + */ +extern unsigned int __VMALLOC_RESERVE; + +/* Pure 2^n version of get_order */ +static __inline__ int get_order(unsigned long size) +{ + int order; + + size = (size-1) >> (PAGE_SHIFT-1); + order = -1; + do { + size >>= 1; + order++; + } while (size); + return order; +} + +extern int sysctl_legacy_va_layout; + +#endif /* __ASSEMBLY__ */ + +#ifdef __ASSEMBLY__ +#define __PAGE_OFFSET (0xC0000000) +#else +#define __PAGE_OFFSET (0xC0000000UL) +#endif + + +#define PAGE_OFFSET ((unsigned long)__PAGE_OFFSET) +#define VMALLOC_RESERVE ((unsigned long)__VMALLOC_RESERVE) +#define MAXMEM (HYPERVISOR_VIRT_START-__PAGE_OFFSET-__VMALLOC_RESERVE) +#define __pa(x) ((unsigned long)(x)-PAGE_OFFSET) +#define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET)) +#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) +#ifndef CONFIG_DISCONTIGMEM +#define pfn_to_page(pfn) (mem_map + (pfn)) +#define page_to_pfn(page) ((unsigned long)((page) - mem_map)) +#define pfn_valid(pfn) ((pfn) < max_mapnr) +#endif /* !CONFIG_DISCONTIGMEM */ +#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) + +#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) + +#define VM_DATA_DEFAULT_FLAGS \ + (VM_READ | VM_WRITE | \ + ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \ + VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) + +/* VIRT <-> MACHINE conversion */ +#define virt_to_machine(v) (phys_to_machine(__pa(v))) +#define virt_to_mfn(v) (pfn_to_mfn(__pa(v) >> PAGE_SHIFT)) +#define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) + +#endif /* __KERNEL__ */ + +#endif /* _I386_PAGE_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/param.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/param.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,23 @@ +#ifndef _ASMi386_PARAM_H +#define _ASMi386_PARAM_H + +#ifdef __KERNEL__ +# define HZ 100 /* Internal kernel timer frequency */ +# define USER_HZ 100 /* .. some user interfaces are in "ticks" */ +# define CLOCKS_PER_SEC (USER_HZ) /* like times() */ +#endif + +#ifndef HZ +#define HZ 100 +#endif + +#define EXEC_PAGESIZE 4096 + +#ifndef NOGROUP +#define NOGROUP (-1) +#endif + +#define MAXHOSTNAMELEN 64 /* max length of hostname */ +#define COMMAND_LINE_SIZE 256 + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pci.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pci.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,140 @@ +#ifndef __i386_PCI_H +#define __i386_PCI_H + +#include <linux/config.h> + +#ifdef __KERNEL__ +#include <linux/mm.h> /* for struct page */ + +/* Can be used to override the logic in pci_scan_bus for skipping + already-configured bus numbers - to be used for buggy BIOSes + or architectures with incomplete PCI setup by the loader */ + +#ifdef CONFIG_PCI +extern unsigned int pcibios_assign_all_busses(void); +#else +#define pcibios_assign_all_busses() 0 +#endif +#define pcibios_scan_all_fns(a, b) 0 + +extern unsigned long pci_mem_start; +#define PCIBIOS_MIN_IO 0x1000 +#define PCIBIOS_MIN_MEM (pci_mem_start) + +#define PCIBIOS_MIN_CARDBUS_IO 0x4000 + +void pcibios_config_init(void); +struct pci_bus * pcibios_scan_root(int bus); + +void pcibios_set_master(struct pci_dev *dev); +void pcibios_penalize_isa_irq(int irq); +struct irq_routing_table *pcibios_get_irq_routing_table(void); +int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq); + +/* Dynamic DMA mapping stuff. + * i386 has everything mapped statically. + */ + +#include <linux/types.h> +#include <linux/slab.h> +#include <asm/scatterlist.h> +#include <linux/string.h> +#include <asm/io.h> + +struct pci_dev; + +#ifdef CONFIG_SWIOTLB + + +/* On Xen we use SWIOTLB instead of blk-specific bounce buffers. */ +#define PCI_DMA_BUS_IS_PHYS (0) + +#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ + dma_addr_t ADDR_NAME; +#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \ + __u32 LEN_NAME; +#define pci_unmap_addr(PTR, ADDR_NAME) \ + ((PTR)->ADDR_NAME) +#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ + (((PTR)->ADDR_NAME) = (VAL)) +#define pci_unmap_len(PTR, LEN_NAME) \ + ((PTR)->LEN_NAME) +#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ + (((PTR)->LEN_NAME) = (VAL)) + +#else + +/* The PCI address space does equal the physical memory + * address space. The networking and block device layers use + * this boolean for bounce buffer decisions. + */ +#define PCI_DMA_BUS_IS_PHYS (1) + +/* pci_unmap_{page,single} is a nop so... */ +#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) +#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) +#define pci_unmap_addr(PTR, ADDR_NAME) (0) +#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) do { } while (0) +#define pci_unmap_len(PTR, LEN_NAME) (0) +#define pci_unmap_len_set(PTR, LEN_NAME, VAL) do { } while (0) + +#endif + +/* This is always fine. */ +#define pci_dac_dma_supported(pci_dev, mask) (1) + +static inline dma64_addr_t +pci_dac_page_to_dma(struct pci_dev *pdev, struct page *page, unsigned long offset, int direction) +{ + return ((dma64_addr_t) page_to_phys(page) + + (dma64_addr_t) offset); +} + +static inline struct page * +pci_dac_dma_to_page(struct pci_dev *pdev, dma64_addr_t dma_addr) +{ + return pfn_to_page(dma_addr >> PAGE_SHIFT); +} + +static inline unsigned long +pci_dac_dma_to_offset(struct pci_dev *pdev, dma64_addr_t dma_addr) +{ + return (dma_addr & ~PAGE_MASK); +} + +static inline void +pci_dac_dma_sync_single_for_cpu(struct pci_dev *pdev, dma64_addr_t dma_addr, size_t len, int direction) +{ +} + +static inline void +pci_dac_dma_sync_single_for_device(struct pci_dev *pdev, dma64_addr_t dma_addr, size_t len, int direction) +{ + flush_write_buffers(); +} + +#define HAVE_PCI_MMAP +extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, + enum pci_mmap_state mmap_state, int write_combine); + + +static inline void pcibios_add_platform_entries(struct pci_dev *dev) +{ +} + +#endif /* __KERNEL__ */ + +/* implement the pci_ DMA API in terms of the generic device dma_ one */ +#include <asm-generic/pci-dma-compat.h> + +/* generic pci stuff */ +#include <asm-generic/pci.h> + +/* On Xen we have to scan all functions since Xen hides bridges from + * us. If a bridge is at fn=0 and that slot has a multifunction + * device, we won't find the additional devices without scanning all + * functions. */ +#undef pcibios_scan_all_fns +#define pcibios_scan_all_fns(a, b) 1 + +#endif /* __i386_PCI_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgalloc.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgalloc.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,64 @@ +#ifndef _I386_PGALLOC_H +#define _I386_PGALLOC_H + +#include <linux/config.h> +#include <asm/fixmap.h> +#include <linux/threads.h> +#include <linux/mm.h> /* for struct page */ +#include <asm/io.h> /* for phys_to_virt and page_to_pseudophys */ + +/* Is this pagetable pinned? */ +#define PG_pinned PG_arch_1 + +#define pmd_populate_kernel(mm, pmd, pte) \ + set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(pte))) + +#define pmd_populate(mm, pmd, pte) \ +do { \ + if (test_bit(PG_pinned, &virt_to_page((mm)->pgd)->flags)) { \ + if (!PageHighMem(pte)) \ + BUG_ON(HYPERVISOR_update_va_mapping( \ + (unsigned long)__va(page_to_pfn(pte)<<PAGE_SHIFT),\ + pfn_pte(page_to_pfn(pte), PAGE_KERNEL_RO), 0));\ + set_pmd(pmd, __pmd(_PAGE_TABLE + \ + ((unsigned long long)page_to_pfn(pte) << \ + (unsigned long long) PAGE_SHIFT))); \ + } else { \ + *(pmd) = __pmd(_PAGE_TABLE + \ + ((unsigned long long)page_to_pfn(pte) << \ + (unsigned long long) PAGE_SHIFT)); \ + } \ +} while (0) + +/* + * Allocate and free page tables. + */ +extern pgd_t *pgd_alloc(struct mm_struct *); +extern void pgd_free(pgd_t *pgd); + +extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long); +extern struct page *pte_alloc_one(struct mm_struct *, unsigned long); + +static inline void pte_free_kernel(pte_t *pte) +{ + free_page((unsigned long)pte); + make_page_writable(pte, XENFEAT_writable_page_tables); +} + +extern void pte_free(struct page *pte); + +#define __pte_free_tlb(tlb,pte) tlb_remove_page((tlb),(pte)) + +#ifdef CONFIG_X86_PAE +/* + * In the PAE case we free the pmds as part of the pgd. + */ +#define pmd_alloc_one(mm, addr) ({ BUG(); ((pmd_t *)2); }) +#define pmd_free(x) do { } while (0) +#define __pmd_free_tlb(tlb,x) do { } while (0) +#define pud_populate(mm, pmd, pte) BUG() +#endif + +#define check_pgt_cache() do { } while (0) + +#endif /* _I386_PGALLOC_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable-2level-defs.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable-2level-defs.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,21 @@ +#ifndef _I386_PGTABLE_2LEVEL_DEFS_H +#define _I386_PGTABLE_2LEVEL_DEFS_H + +#define HAVE_SHARED_KERNEL_PMD 0 + +/* + * traditional i386 two-level paging structure: + */ + +#define PGDIR_SHIFT 22 +#define PTRS_PER_PGD 1024 +#define PTRS_PER_PGD_NO_HV (HYPERVISOR_VIRT_START >> PGDIR_SHIFT) + +/* + * the i386 is two-level, so we don't really have any + * PMD directory physically. + */ + +#define PTRS_PER_PTE 1024 + +#endif /* _I386_PGTABLE_2LEVEL_DEFS_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable-2level.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable-2level.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,119 @@ +#ifndef _I386_PGTABLE_2LEVEL_H +#define _I386_PGTABLE_2LEVEL_H + +#include <asm-generic/pgtable-nopmd.h> + +#define pte_ERROR(e) \ + printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low) +#define pgd_ERROR(e) \ + printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) + +/* + * Certain architectures need to do special things when PTEs + * within a page table are directly modified. Thus, the following + * hook is made available. + */ +#define set_pte(pteptr, pteval) (*(pteptr) = pteval) + +#define set_pte_at(_mm,addr,ptep,pteval) do { \ + if (((_mm) != current->mm && (_mm) != &init_mm) || \ + HYPERVISOR_update_va_mapping((addr), (pteval), 0)) \ + set_pte((ptep), (pteval)); \ +} while (0) + +#define set_pte_at_sync(_mm,addr,ptep,pteval) do { \ + if (((_mm) != current->mm && (_mm) != &init_mm) || \ + HYPERVISOR_update_va_mapping((addr), (pteval), UVMF_INVLPG)) { \ + set_pte((ptep), (pteval)); \ + xen_invlpg((addr)); \ + } \ +} while (0) + +#define set_pte_atomic(pteptr, pteval) set_pte(pteptr,pteval) + +#ifndef CONFIG_XEN_SHADOW_MODE +#define set_pmd(pmdptr, pmdval) xen_l2_entry_update((pmdptr), (pmdval)) +#else +#define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval)) +#endif + +#define ptep_get_and_clear(mm,addr,xp) __pte_ma(xchg(&(xp)->pte_low, 0)) +#define pte_same(a, b) ((a).pte_low == (b).pte_low) +/* + * We detect special mappings in one of two ways: + * 1. If the MFN is an I/O page then Xen will set the m2p entry + * to be outside our maximum possible pseudophys range. + * 2. If the MFN belongs to a different domain then we will certainly + * not have MFN in our p2m table. Conversely, if the page is ours, + * then we'll have p2m(m2p(MFN))==MFN. + * If we detect a special mapping then it doesn't have a 'struct page'. + * We force !pfn_valid() by returning an out-of-range pointer. + * + * NB. These checks require that, for any MFN that is not in our reservation, + * there is no PFN such that p2m(PFN) == MFN. Otherwise we can get confused if + * we are foreign-mapping the MFN, and the other domain as m2p(MFN) == PFN. + * Yikes! Various places must poke in INVALID_P2M_ENTRY for safety. + * + * NB2. When deliberately mapping foreign pages into the p2m table, you *must* + * use FOREIGN_FRAME(). This will cause pte_pfn() to choke on it, as we + * require. In all the cases we care about, the FOREIGN_FRAME bit is + * masked (e.g., pfn_to_mfn()) so behaviour there is correct. + */ +#define pte_mfn(_pte) ((_pte).pte_low >> PAGE_SHIFT) +#define pte_pfn(_pte) \ +({ \ + unsigned long mfn = pte_mfn(_pte); \ + unsigned long pfn = mfn_to_pfn(mfn); \ + if ((pfn >= max_mapnr) || (phys_to_machine_mapping[pfn] != mfn))\ + pfn = max_mapnr; /* special: force !pfn_valid() */ \ + pfn; \ +}) + +#define pte_page(_pte) pfn_to_page(pte_pfn(_pte)) + +#define pte_none(x) (!(x).pte_low) +#define pfn_pte(pfn, prot) __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) +#define pfn_pte_ma(pfn, prot) __pte_ma(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) +#define pfn_pmd(pfn, prot) __pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) + +#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)) + +#define pmd_page_kernel(pmd) \ +((unsigned long) __va(pmd_val(pmd) & PAGE_MASK)) + +/* + * All present user pages are user-executable: + */ +static inline int pte_exec(pte_t pte) +{ + return pte_user(pte); +} + +/* + * All present pages are kernel-executable: + */ +static inline int pte_exec_kernel(pte_t pte) +{ + return 1; +} + +/* + * Bits 0, 6 and 7 are taken, split up the 29 bits of offset + * into this range: + */ +#define PTE_FILE_MAX_BITS 29 + +#define pte_to_pgoff(pte) \ + ((((pte).pte_low >> 1) & 0x1f ) + (((pte).pte_low >> 8) << 5 )) + +#define pgoff_to_pte(off) \ + ((pte_t) { (((off) & 0x1f) << 1) + (((off) >> 5) << 8) + _PAGE_FILE }) + +/* Encode and de-code a swap entry */ +#define __swp_type(x) (((x).val >> 1) & 0x1f) +#define __swp_offset(x) ((x).val >> 8) +#define __swp_entry(type, offset) ((swp_entry_t) { ((type) << 1) | ((offset) << 8) }) +#define __pte_to_swp_entry(pte) ((swp_entry_t) { (pte).pte_low }) +#define __swp_entry_to_pte(x) ((pte_t) { (x).val }) + +#endif /* _I386_PGTABLE_2LEVEL_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable-3level-defs.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable-3level-defs.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,25 @@ +#ifndef _I386_PGTABLE_3LEVEL_DEFS_H +#define _I386_PGTABLE_3LEVEL_DEFS_H + +#define HAVE_SHARED_KERNEL_PMD 0 + +/* + * PGDIR_SHIFT determines what a top-level page table entry can map + */ +#define PGDIR_SHIFT 30 +#define PTRS_PER_PGD 4 +#define PTRS_PER_PGD_NO_HV 4 + +/* + * PMD_SHIFT determines the size of the area a middle-level + * page table can map + */ +#define PMD_SHIFT 21 +#define PTRS_PER_PMD 512 + +/* + * entries per page directory level + */ +#define PTRS_PER_PTE 512 + +#endif /* _I386_PGTABLE_3LEVEL_DEFS_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable-3level.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable-3level.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,200 @@ +#ifndef _I386_PGTABLE_3LEVEL_H +#define _I386_PGTABLE_3LEVEL_H + +#include <asm-generic/pgtable-nopud.h> + +/* + * Intel Physical Address Extension (PAE) Mode - three-level page + * tables on PPro+ CPUs. + * + * Copyright (C) 1999 Ingo Molnar <mingo@xxxxxxxxxx> + */ + +#define pte_ERROR(e) \ + printk("%s:%d: bad pte %p(%08lx%08lx).\n", __FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low) +#define pmd_ERROR(e) \ + printk("%s:%d: bad pmd %p(%016Lx).\n", __FILE__, __LINE__, &(e), pmd_val(e)) +#define pgd_ERROR(e) \ + printk("%s:%d: bad pgd %p(%016Lx).\n", __FILE__, __LINE__, &(e), pgd_val(e)) + +#define pud_none(pud) 0 +#define pud_bad(pud) 0 +#define pud_present(pud) 1 + +/* + * Is the pte executable? + */ +static inline int pte_x(pte_t pte) +{ + return !(pte_val(pte) & _PAGE_NX); +} + +/* + * All present user-pages with !NX bit are user-executable: + */ +static inline int pte_exec(pte_t pte) +{ + return pte_user(pte) && pte_x(pte); +} +/* + * All present pages with !NX bit are kernel-executable: + */ +static inline int pte_exec_kernel(pte_t pte) +{ + return pte_x(pte); +} + +/* Rules for using set_pte: the pte being assigned *must* be + * either not present or in a state where the hardware will + * not attempt to update the pte. In places where this is + * not possible, use pte_get_and_clear to obtain the old pte + * value and then use set_pte to update it. -ben + */ +#define __HAVE_ARCH_SET_PTE_ATOMIC + +#if 1 +/* use writable pagetables */ +static inline void set_pte(pte_t *ptep, pte_t pte) +{ + ptep->pte_high = pte.pte_high; + smp_wmb(); + ptep->pte_low = pte.pte_low; +} +# define set_pte_atomic(pteptr,pteval) \ + set_64bit((unsigned long long *)(pteptr),pte_val_ma(pteval)) +#else +/* no writable pagetables */ +# define set_pte(pteptr,pteval) \ + xen_l1_entry_update((pteptr), (pteval)) +# define set_pte_atomic(pteptr,pteval) set_pte(pteptr,pteval) +#endif + +#define set_pte_at(_mm,addr,ptep,pteval) do { \ + if (((_mm) != current->mm && (_mm) != &init_mm) || \ + HYPERVISOR_update_va_mapping((addr), (pteval), 0)) \ + set_pte((ptep), (pteval)); \ +} while (0) + +#define set_pte_at_sync(_mm,addr,ptep,pteval) do { \ + if (((_mm) != current->mm && (_mm) != &init_mm) || \ + HYPERVISOR_update_va_mapping((addr), (pteval), UVMF_INVLPG)) { \ + set_pte((ptep), (pteval)); \ + xen_invlpg((addr)); \ + } \ +} while (0) + +#ifdef CONFIG_XEN_SHADOW_MODE +# define set_pmd(pmdptr,pmdval) \ + set_64bit((unsigned long long *)(pmdptr),pmd_val(pmdval)) +# define set_pud(pudptr,pudval) \ + set_64bit((unsigned long long *)(pudptr),pud_val(pudval)) +#else +# define set_pmd(pmdptr,pmdval) \ + xen_l2_entry_update((pmdptr), (pmdval)) +# define set_pud(pudptr,pudval) \ + xen_l3_entry_update((pudptr), (pudval)) +#endif + +/* + * Pentium-II erratum A13: in PAE mode we explicitly have to flush + * the TLB via cr3 if the top-level pgd is changed... + * We do not let the generic code free and clear pgd entries due to + * this erratum. + */ +static inline void pud_clear (pud_t * pud) { } + +#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)) + +#define pmd_page_kernel(pmd) \ +((unsigned long) __va(pmd_val(pmd) & PAGE_MASK)) + +#define pud_page(pud) \ +((struct page *) __va(pud_val(pud) & PAGE_MASK)) + +#define pud_page_kernel(pud) \ +((unsigned long) __va(pud_val(pud) & PAGE_MASK)) + + +/* Find an entry in the second-level page table.. */ +#define pmd_offset(pud, address) ((pmd_t *) pud_page(*(pud)) + \ + pmd_index(address)) + +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) +{ + pte_t res; + + /* xchg acts as a barrier before the setting of the high bits */ + res.pte_low = xchg(&ptep->pte_low, 0); + res.pte_high = ptep->pte_high; + ptep->pte_high = 0; + + return res; +} + +static inline int pte_same(pte_t a, pte_t b) +{ + return a.pte_low == b.pte_low && a.pte_high == b.pte_high; +} + +#define pte_page(x) pfn_to_page(pte_pfn(x)) + +static inline int pte_none(pte_t pte) +{ + return !pte.pte_low && !pte.pte_high; +} + +#define pte_mfn(_pte) ( ((_pte).pte_low >> PAGE_SHIFT) |\ + (((_pte).pte_high & 0xfff) << (32-PAGE_SHIFT)) ) +#define pte_pfn(_pte) \ +({ \ + unsigned long mfn = pte_mfn(_pte); \ + unsigned long pfn = mfn_to_pfn(mfn); \ + if ((pfn >= max_mapnr) || (phys_to_machine_mapping[pfn] != mfn))\ + pfn = max_mapnr; /* special: force !pfn_valid() */ \ + pfn; \ +}) + +extern unsigned long long __supported_pte_mask; + +static inline pte_t pfn_pte_ma(unsigned long page_nr, pgprot_t pgprot) +{ + pte_t pte; + + pte.pte_high = (page_nr >> (32 - PAGE_SHIFT)) | \ + (pgprot_val(pgprot) >> 32); + pte.pte_high &= (__supported_pte_mask >> 32); + pte.pte_low = ((page_nr << PAGE_SHIFT) | pgprot_val(pgprot)) & \ + __supported_pte_mask; + return pte; +} + +static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) +{ + return pfn_pte_ma(pfn_to_mfn(page_nr), pgprot); +} + +static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) +{ + BUG(); panic("needs review"); + return __pmd((((unsigned long long)page_nr << PAGE_SHIFT) | \ + pgprot_val(pgprot)) & __supported_pte_mask); +} + +/* + * Bits 0, 6 and 7 are taken in the low part of the pte, + * put the 32 bits of offset into the high part. + */ +#define pte_to_pgoff(pte) ((pte).pte_high) +#define pgoff_to_pte(off) ((pte_t) { _PAGE_FILE, (off) }) +#define PTE_FILE_MAX_BITS 32 + +/* Encode and de-code a swap entry */ +#define __swp_type(x) (((x).val) & 0x1f) +#define __swp_offset(x) ((x).val >> 5) +#define __swp_entry(type, offset) ((swp_entry_t){(type) | (offset) << 5}) +#define __pte_to_swp_entry(pte) ((swp_entry_t){ (pte).pte_high }) +#define __swp_entry_to_pte(x) ((pte_t){ 0, (x).val }) + +#define __pmd_free_tlb(tlb, x) do { } while (0) + +#endif /* _I386_PGTABLE_3LEVEL_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/pgtable.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,478 @@ +#ifndef _I386_PGTABLE_H +#define _I386_PGTABLE_H + +#include <linux/config.h> +#include <asm/hypervisor.h> + +/* + * The Linux memory management assumes a three-level page table setup. On + * the i386, we use that, but "fold" the mid level into the top-level page + * table, so that we physically have the same two-level page table as the + * i386 mmu expects. + * + * This file contains the functions and defines necessary to modify and use + * the i386 page table tree. + */ +#ifndef __ASSEMBLY__ +#include <asm/processor.h> +#include <asm/fixmap.h> +#include <linux/threads.h> + +#ifndef _I386_BITOPS_H +#include <asm/bitops.h> +#endif + +#include <linux/slab.h> +#include <linux/list.h> +#include <linux/spinlock.h> + +/* + * ZERO_PAGE is a global shared page that is always zero: used + * for zero-mapped memory areas etc.. + */ +#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) +extern unsigned long empty_zero_page[1024]; +extern pgd_t *swapper_pg_dir; +extern kmem_cache_t *pgd_cache; +extern kmem_cache_t *pmd_cache; +extern spinlock_t pgd_lock; +extern struct page *pgd_list; + +void pmd_ctor(void *, kmem_cache_t *, unsigned long); +void pgd_ctor(void *, kmem_cache_t *, unsigned long); +void pgd_dtor(void *, kmem_cache_t *, unsigned long); +void pgtable_cache_init(void); +void paging_init(void); + +/* + * The Linux x86 paging architecture is 'compile-time dual-mode', it + * implements both the traditional 2-level x86 page tables and the + * newer 3-level PAE-mode page tables. + */ +#ifdef CONFIG_X86_PAE +# include <asm/pgtable-3level-defs.h> +# define PMD_SIZE (1UL << PMD_SHIFT) +# define PMD_MASK (~(PMD_SIZE-1)) +#else +# include <asm/pgtable-2level-defs.h> +#endif + +#define PGDIR_SIZE (1UL << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE-1)) + +#define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE) +#define FIRST_USER_ADDRESS 0 + +#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT) +#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS) + +#define TWOLEVEL_PGDIR_SHIFT 22 +#define BOOT_USER_PGD_PTRS (__PAGE_OFFSET >> TWOLEVEL_PGDIR_SHIFT) +#define BOOT_KERNEL_PGD_PTRS (1024-BOOT_USER_PGD_PTRS) + +/* Just any arbitrary offset to the start of the vmalloc VM area: the + * current 8MB value just means that there will be a 8MB "hole" after the + * physical memory until the kernel virtual memory starts. That means that + * any out-of-bounds memory accesses will hopefully be caught. + * The vmalloc() routines leaves a hole of 4kB between each vmalloced + * area for the same reason. ;) + */ +#define VMALLOC_OFFSET (8*1024*1024) +#define VMALLOC_START (((unsigned long) high_memory + vmalloc_earlyreserve + \ + 2*VMALLOC_OFFSET-1) & ~(VMALLOC_OFFSET-1)) +#ifdef CONFIG_HIGHMEM +# define VMALLOC_END (PKMAP_BASE-2*PAGE_SIZE) +#else +# define VMALLOC_END (FIXADDR_START-2*PAGE_SIZE) +#endif + +/* + * The 4MB page is guessing.. Detailed in the infamous "Chapter H" + * of the Pentium details, but assuming intel did the straightforward + * thing, this bit set in the page directory entry just means that + * the page directory entry points directly to a 4MB-aligned block of + * memory. + */ +#define _PAGE_BIT_PRESENT 0 +#define _PAGE_BIT_RW 1 +#define _PAGE_BIT_USER 2 +#define _PAGE_BIT_PWT 3 +#define _PAGE_BIT_PCD 4 +#define _PAGE_BIT_ACCESSED 5 +#define _PAGE_BIT_DIRTY 6 +#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page, Pentium+, if present.. */ +#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */ +#define _PAGE_BIT_UNUSED1 9 /* available for programmer */ +#define _PAGE_BIT_UNUSED2 10 +#define _PAGE_BIT_UNUSED3 11 +#define _PAGE_BIT_NX 63 + +#define _PAGE_PRESENT 0x001 +#define _PAGE_RW 0x002 +#define _PAGE_USER 0x004 +#define _PAGE_PWT 0x008 +#define _PAGE_PCD 0x010 +#define _PAGE_ACCESSED 0x020 +#define _PAGE_DIRTY 0x040 +#define _PAGE_PSE 0x080 /* 4 MB (or 2MB) page, Pentium+, if present.. */ +#define _PAGE_GLOBAL 0x100 /* Global TLB entry PPro+ */ +#define _PAGE_UNUSED1 0x200 /* available for programmer */ +#define _PAGE_UNUSED2 0x400 +#define _PAGE_UNUSED3 0x800 + +#define _PAGE_FILE 0x040 /* set:pagecache unset:swap */ +#define _PAGE_PROTNONE 0x080 /* If not present */ +#ifdef CONFIG_X86_PAE +#define _PAGE_NX (1ULL<<_PAGE_BIT_NX) +#else +#define _PAGE_NX 0 +#endif + +#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY) +#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY) +#define _PAGE_CHG_MASK (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY) + +#define PAGE_NONE \ + __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED) +#define PAGE_SHARED \ + __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED) + +#define PAGE_SHARED_EXEC \ + __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED) +#define PAGE_COPY_NOEXEC \ + __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX) +#define PAGE_COPY_EXEC \ + __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED) +#define PAGE_COPY \ + PAGE_COPY_NOEXEC +#define PAGE_READONLY \ + __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX) +#define PAGE_READONLY_EXEC \ + __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED) + +#define _PAGE_KERNEL \ + (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX) +#define _PAGE_KERNEL_EXEC \ + (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED) + +extern unsigned long long __PAGE_KERNEL, __PAGE_KERNEL_EXEC; +#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW) +#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_PCD) +#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE) +#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE) + +#define PAGE_KERNEL __pgprot(__PAGE_KERNEL) +#define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO) +#define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC) +#define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE) +#define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE) +#define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC) + +/* + * The i386 can't do page protection for execute, and considers that + * the same are read. Also, write permissions imply read permissions. + * This is the closest we can get.. + */ +#define __P000 PAGE_NONE +#define __P001 PAGE_READONLY +#define __P010 PAGE_COPY +#define __P011 PAGE_COPY +#define __P100 PAGE_READONLY_EXEC +#define __P101 PAGE_READONLY_EXEC +#define __P110 PAGE_COPY_EXEC +#define __P111 PAGE_COPY_EXEC + +#define __S000 PAGE_NONE +#define __S001 PAGE_READONLY +#define __S010 PAGE_SHARED +#define __S011 PAGE_SHARED +#define __S100 PAGE_READONLY_EXEC +#define __S101 PAGE_READONLY_EXEC +#define __S110 PAGE_SHARED_EXEC +#define __S111 PAGE_SHARED_EXEC + +/* + * Define this if things work differently on an i386 and an i486: + * it will (on an i486) warn about kernel memory accesses that are + * done without a 'access_ok(VERIFY_WRITE,..)' + */ +#undef TEST_ACCESS_OK + +/* The boot page tables (all created as a single array) */ +extern unsigned long pg0[]; + +#define pte_present(x) ((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE)) +#define pte_clear(mm,addr,xp) do { set_pte_at(mm, addr, xp, __pte(0)); } while (0) + +#define pmd_none(x) (!pmd_val(x)) +/* pmd_present doesn't just test the _PAGE_PRESENT bit since wr.p.t. + can temporarily clear it. */ +#define pmd_present(x) (pmd_val(x)) +#define pmd_clear(xp) do { set_pmd(xp, __pmd(0)); } while (0) +#define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER & ~_PAGE_PRESENT)) != (_KERNPG_TABLE & ~_PAGE_PRESENT)) + + +#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT)) + +/* + * The following only work if pte_present() is true. + * Undefined behaviour if not.. + */ +static inline int pte_user(pte_t pte) { return (pte).pte_low & _PAGE_USER; } +static inline int pte_read(pte_t pte) { return (pte).pte_low & _PAGE_USER; } +static inline int pte_dirty(pte_t pte) { return (pte).pte_low & _PAGE_DIRTY; } +static inline int pte_young(pte_t pte) { return (pte).pte_low & _PAGE_ACCESSED; } +static inline int pte_write(pte_t pte) { return (pte).pte_low & _PAGE_RW; } + +/* + * The following only works if pte_present() is not true. + */ +static inline int pte_file(pte_t pte) { return (pte).pte_low & _PAGE_FILE; } + +static inline pte_t pte_rdprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER; return pte; } +static inline pte_t pte_exprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER; return pte; } +static inline pte_t pte_mkclean(pte_t pte) { (pte).pte_low &= ~_PAGE_DIRTY; return pte; } +static inline pte_t pte_mkold(pte_t pte) { (pte).pte_low &= ~_PAGE_ACCESSED; return pte; } +static inline pte_t pte_wrprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_RW; return pte; } +static inline pte_t pte_mkread(pte_t pte) { (pte).pte_low |= _PAGE_USER; return pte; } +static inline pte_t pte_mkexec(pte_t pte) { (pte).pte_low |= _PAGE_USER; return pte; } +static inline pte_t pte_mkdirty(pte_t pte) { (pte).pte_low |= _PAGE_DIRTY; return pte; } +static inline pte_t pte_mkyoung(pte_t pte) { (pte).pte_low |= _PAGE_ACCESSED; return pte; } +static inline pte_t pte_mkwrite(pte_t pte) { (pte).pte_low |= _PAGE_RW; return pte; } + +#ifdef CONFIG_X86_PAE +# include <asm/pgtable-3level.h> +#else +# include <asm/pgtable-2level.h> +#endif + +static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +{ + if (!pte_dirty(*ptep)) + return 0; + return test_and_clear_bit(_PAGE_BIT_DIRTY, &ptep->pte_low); +} + +static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +{ + if (!pte_young(*ptep)) + return 0; + return test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte_low); +} + +static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) +{ + if (pte_write(*ptep)) + clear_bit(_PAGE_BIT_RW, &ptep->pte_low); +} + +/* + * Macro to mark a page protection value as "uncacheable". On processors which do not support + * it, this is a no-op. + */ +#define pgprot_noncached(prot) ((boot_cpu_data.x86 > 3) \ + ? (__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT)) : (prot)) + +/* + * Conversion functions: convert a page and protection to a page entry, + * and a page entry and page directory to the page they refer to. + */ + +#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot)) +#define mk_pte_huge(entry) ((entry).pte_low |= _PAGE_PRESENT | _PAGE_PSE) + +static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) +{ + pte.pte_low &= _PAGE_CHG_MASK; + pte.pte_low |= pgprot_val(newprot); +#ifdef CONFIG_X86_PAE + /* + * Chop off the NX bit (if present), and add the NX portion of + * the newprot (if present): + */ + pte.pte_high &= ~(1 << (_PAGE_BIT_NX - 32)); + pte.pte_high |= (pgprot_val(newprot) >> 32) & \ + (__supported_pte_mask >> 32); +#endif + return pte; +} + +#define page_pte(page) page_pte_prot(page, __pgprot(0)) + +#define pmd_large(pmd) \ +((pmd_val(pmd) & (_PAGE_PSE|_PAGE_PRESENT)) == (_PAGE_PSE|_PAGE_PRESENT)) + +/* + * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD] + * + * this macro returns the index of the entry in the pgd page which would + * control the given virtual address + */ +#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1)) +#define pgd_index_k(addr) pgd_index(addr) + +/* + * pgd_offset() returns a (pgd_t *) + * pgd_index() is used get the offset into the pgd page's array of pgd_t's; + */ +#define pgd_offset(mm, address) ((mm)->pgd+pgd_index(address)) + +/* + * a shortcut which implies the use of the kernel's pgd, instead + * of a process's + */ +#define pgd_offset_k(address) pgd_offset(&init_mm, address) + +/* + * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD] + * + * this macro returns the index of the entry in the pmd page which would + * control the given virtual address + */ +#define pmd_index(address) \ + (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1)) + +/* + * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE] + * + * this macro returns the index of the entry in the pte page which would + * control the given virtual address + */ +#define pte_index(address) \ + (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +#define pte_offset_kernel(dir, address) \ + ((pte_t *) pmd_page_kernel(*(dir)) + pte_index(address)) + +/* + * Helper function that returns the kernel pagetable entry controlling + * the virtual address 'address'. NULL means no pagetable entry present. + * NOTE: the return type is pte_t but if the pmd is PSE then we return it + * as a pte too. + */ +extern pte_t *lookup_address(unsigned long address); + +/* + * Make a given kernel text page executable/non-executable. + * Returns the previous executability setting of that page (which + * is used to restore the previous state). Used by the SMP bootup code. + * NOTE: this is an __init function for security reasons. + */ +#ifdef CONFIG_X86_PAE + extern int set_kernel_exec(unsigned long vaddr, int enable); +#else + static inline int set_kernel_exec(unsigned long vaddr, int enable) { return 0;} +#endif + +extern void noexec_setup(const char *str); + +#if defined(CONFIG_HIGHPTE) +#define pte_offset_map(dir, address) \ + ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)),KM_PTE0) + \ + pte_index(address)) +#define pte_offset_map_nested(dir, address) \ + ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)),KM_PTE1) + \ + pte_index(address)) +#define pte_unmap(pte) kunmap_atomic(pte, KM_PTE0) +#define pte_unmap_nested(pte) kunmap_atomic(pte, KM_PTE1) +#else +#define pte_offset_map(dir, address) \ + ((pte_t *)page_address(pmd_page(*(dir))) + pte_index(address)) +#define pte_offset_map_nested(dir, address) pte_offset_map(dir, address) +#define pte_unmap(pte) do { } while (0) +#define pte_unmap_nested(pte) do { } while (0) +#endif + +/* + * The i386 doesn't have any external MMU info: the kernel page + * tables contain all the necessary information. + * + * Also, we only update the dirty/accessed state if we set + * the dirty bit by hand in the kernel, since the hardware + * will do the accessed bit for us, and we don't want to + * race with other CPU's that might be updating the dirty + * bit at the same time. + */ +#define update_mmu_cache(vma,address,pte) do { } while (0) +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \ + do { \ + if (__dirty) { \ + if ( likely((__vma)->vm_mm == current->mm) ) { \ + BUG_ON(HYPERVISOR_update_va_mapping((__address), (__entry), UVMF_INVLPG|UVMF_MULTI|(unsigned long)((__vma)->vm_mm->cpu_vm_mask.bits))); \ + } else { \ + xen_l1_entry_update((__ptep), (__entry)); \ + flush_tlb_page((__vma), (__address)); \ + } \ + } \ + } while (0) + +#define __HAVE_ARCH_PTEP_ESTABLISH +#define ptep_establish(__vma, __address, __ptep, __entry) \ +do { \ + ptep_set_access_flags(__vma, __address, __ptep, __entry, 1); \ +} while (0) + +#include <xen/features.h> +void make_lowmem_page_readonly(void *va, unsigned int feature); +void make_lowmem_page_writable(void *va, unsigned int feature); +void make_page_readonly(void *va, unsigned int feature); +void make_page_writable(void *va, unsigned int feature); +void make_pages_readonly(void *va, unsigned int nr, unsigned int feature); +void make_pages_writable(void *va, unsigned int nr, unsigned int feature); + +#define virt_to_ptep(__va) \ +({ \ + pgd_t *__pgd = pgd_offset_k((unsigned long)(__va)); \ + pud_t *__pud = pud_offset(__pgd, (unsigned long)(__va)); \ + pmd_t *__pmd = pmd_offset(__pud, (unsigned long)(__va)); \ + pte_offset_kernel(__pmd, (unsigned long)(__va)); \ +}) + +#define arbitrary_virt_to_machine(__va) \ +({ \ + maddr_t m = (maddr_t)pte_mfn(*virt_to_ptep(__va)) << PAGE_SHIFT;\ + m | ((unsigned long)(__va) & (PAGE_SIZE-1)); \ +}) + +#endif /* !__ASSEMBLY__ */ + +#ifndef CONFIG_DISCONTIGMEM +#define kern_addr_valid(addr) (1) +#endif /* !CONFIG_DISCONTIGMEM */ + +int direct_remap_pfn_range(struct vm_area_struct *vma, + unsigned long address, + unsigned long mfn, + unsigned long size, + pgprot_t prot, + domid_t domid); +int direct_kernel_remap_pfn_range(unsigned long address, + unsigned long mfn, + unsigned long size, + pgprot_t prot, + domid_t domid); +int create_lookup_pte_addr(struct mm_struct *mm, + unsigned long address, + uint64_t *ptep); +int touch_pte_range(struct mm_struct *mm, + unsigned long address, + unsigned long size); + +#define io_remap_page_range(vma,from,phys,size,prot) \ +direct_remap_pfn_range(vma,from,(phys)>>PAGE_SHIFT,size,prot,DOMID_IO) + +#define io_remap_pfn_range(vma,from,pfn,size,prot) \ +direct_remap_pfn_range(vma,from,pfn,size,prot,DOMID_IO) + +#define MK_IOSPACE_PFN(space, pfn) (pfn) +#define GET_IOSPACE(pfn) 0 +#define GET_PFN(pfn) (pfn) + +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +#define __HAVE_ARCH_PTEP_SET_WRPROTECT +#define __HAVE_ARCH_PTE_SAME +#include <asm-generic/pgtable.h> + +#endif /* _I386_PGTABLE_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/processor.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/processor.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,703 @@ +/* + * include/asm-i386/processor.h + * + * Copyright (C) 1994 Linus Torvalds + */ + +#ifndef __ASM_I386_PROCESSOR_H +#define __ASM_I386_PROCESSOR_H + +#include <asm/vm86.h> +#include <asm/math_emu.h> +#include <asm/segment.h> +#include <asm/page.h> +#include <asm/types.h> +#include <asm/sigcontext.h> +#include <asm/cpufeature.h> +#include <asm/msr.h> +#include <asm/system.h> +#include <linux/cache.h> +#include <linux/config.h> +#include <linux/threads.h> +#include <asm/percpu.h> + +/* flag for disabling the tsc */ +extern int tsc_disable; + +struct desc_struct { + unsigned long a,b; +}; + +#define desc_empty(desc) \ + (!((desc)->a + (desc)->b)) + +#define desc_equal(desc1, desc2) \ + (((desc1)->a == (desc2)->a) && ((desc1)->b == (desc2)->b)) +/* + * Default implementation of macro that returns current + * instruction pointer ("program counter"). + */ +#define current_text_addr() ({ void *pc; __asm__("movl $1f,%0\n1:":"=g" (pc)); pc; }) + +/* + * CPU type and hardware bug flags. Kept separately for each CPU. + * Members of this structure are referenced in head.S, so think twice + * before touching them. [mj] + */ + +struct cpuinfo_x86 { + __u8 x86; /* CPU family */ + __u8 x86_vendor; /* CPU vendor */ + __u8 x86_model; + __u8 x86_mask; + char wp_works_ok; /* It doesn't on 386's */ + char hlt_works_ok; /* Problems on some 486Dx4's and old 386's */ + char hard_math; + char rfu; + int cpuid_level; /* Maximum supported CPUID level, -1=no CPUID */ + unsigned long x86_capability[NCAPINTS]; + char x86_vendor_id[16]; + char x86_model_id[64]; + int x86_cache_size; /* in KB - valid for CPUS which support this + call */ + int x86_cache_alignment; /* In bytes */ + int fdiv_bug; + int f00f_bug; + int coma_bug; + unsigned long loops_per_jiffy; + unsigned char x86_num_cores; +} __attribute__((__aligned__(SMP_CACHE_BYTES))); + +#define X86_VENDOR_INTEL 0 +#define X86_VENDOR_CYRIX 1 +#define X86_VENDOR_AMD 2 +#define X86_VENDOR_UMC 3 +#define X86_VENDOR_NEXGEN 4 +#define X86_VENDOR_CENTAUR 5 +#define X86_VENDOR_RISE 6 +#define X86_VENDOR_TRANSMETA 7 +#define X86_VENDOR_NSC 8 +#define X86_VENDOR_NUM 9 +#define X86_VENDOR_UNKNOWN 0xff + +/* + * capabilities of CPUs + */ + +extern struct cpuinfo_x86 boot_cpu_data; +extern struct cpuinfo_x86 new_cpu_data; +extern struct tss_struct doublefault_tss; +DECLARE_PER_CPU(struct tss_struct, init_tss); +DECLARE_PER_CPU(pgd_t *, cur_pgd); + +#ifdef CONFIG_SMP +extern struct cpuinfo_x86 cpu_data[]; +#define current_cpu_data cpu_data[smp_processor_id()] +#else +#define cpu_data (&boot_cpu_data) +#define current_cpu_data boot_cpu_data +#endif + +extern int phys_proc_id[NR_CPUS]; +extern int cpu_core_id[NR_CPUS]; +extern char ignore_fpu_irq; + +extern void identify_cpu(struct cpuinfo_x86 *); +extern void print_cpu_info(struct cpuinfo_x86 *); +extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c); + +#ifdef CONFIG_X86_HT +extern void detect_ht(struct cpuinfo_x86 *c); +#else +static inline void detect_ht(struct cpuinfo_x86 *c) {} +#endif + +/* + * EFLAGS bits + */ +#define X86_EFLAGS_CF 0x00000001 /* Carry Flag */ +#define X86_EFLAGS_PF 0x00000004 /* Parity Flag */ +#define X86_EFLAGS_AF 0x00000010 /* Auxillary carry Flag */ +#define X86_EFLAGS_ZF 0x00000040 /* Zero Flag */ +#define X86_EFLAGS_SF 0x00000080 /* Sign Flag */ +#define X86_EFLAGS_TF 0x00000100 /* Trap Flag */ +#define X86_EFLAGS_IF 0x00000200 /* Interrupt Flag */ +#define X86_EFLAGS_DF 0x00000400 /* Direction Flag */ +#define X86_EFLAGS_OF 0x00000800 /* Overflow Flag */ +#define X86_EFLAGS_IOPL 0x00003000 /* IOPL mask */ +#define X86_EFLAGS_NT 0x00004000 /* Nested Task */ +#define X86_EFLAGS_RF 0x00010000 /* Resume Flag */ +#define X86_EFLAGS_VM 0x00020000 /* Virtual Mode */ +#define X86_EFLAGS_AC 0x00040000 /* Alignment Check */ +#define X86_EFLAGS_VIF 0x00080000 /* Virtual Interrupt Flag */ +#define X86_EFLAGS_VIP 0x00100000 /* Virtual Interrupt Pending */ +#define X86_EFLAGS_ID 0x00200000 /* CPUID detection flag */ + +/* + * Generic CPUID function + * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx + * resulting in stale register contents being returned. + */ +static inline void cpuid(unsigned int op, unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx) +{ + __asm__("cpuid" + : "=a" (*eax), + "=b" (*ebx), + "=c" (*ecx), + "=d" (*edx) + : "0" (op), "c"(0)); +} + +/* Some CPUID calls want 'count' to be placed in ecx */ +static inline void cpuid_count(int op, int count, int *eax, int *ebx, int *ecx, + int *edx) +{ + __asm__("cpuid" + : "=a" (*eax), + "=b" (*ebx), + "=c" (*ecx), + "=d" (*edx) + : "0" (op), "c" (count)); +} + +/* + * CPUID functions returning a single datum + */ +static inline unsigned int cpuid_eax(unsigned int op) +{ + unsigned int eax; + + __asm__("cpuid" + : "=a" (eax) + : "0" (op) + : "bx", "cx", "dx"); + return eax; +} +static inline unsigned int cpuid_ebx(unsigned int op) +{ + unsigned int eax, ebx; + + __asm__("cpuid" + : "=a" (eax), "=b" (ebx) + : "0" (op) + : "cx", "dx" ); + return ebx; +} +static inline unsigned int cpuid_ecx(unsigned int op) +{ + unsigned int eax, ecx; + + __asm__("cpuid" + : "=a" (eax), "=c" (ecx) + : "0" (op) + : "bx", "dx" ); + return ecx; +} +static inline unsigned int cpuid_edx(unsigned int op) +{ + unsigned int eax, edx; + + __asm__("cpuid" + : "=a" (eax), "=d" (edx) + : "0" (op) + : "bx", "cx"); + return edx; +} + +#define load_cr3(pgdir) do { \ + xen_pt_switch(__pa(pgdir)); \ + per_cpu(cur_pgd, smp_processor_id()) = pgdir; \ +} while (/* CONSTCOND */0) + + +/* + * Intel CPU features in CR4 + */ +#define X86_CR4_VME 0x0001 /* enable vm86 extensions */ +#define X86_CR4_PVI 0x0002 /* virtual interrupts flag enable */ +#define X86_CR4_TSD 0x0004 /* disable time stamp at ipl 3 */ +#define X86_CR4_DE 0x0008 /* enable debugging extensions */ +#define X86_CR4_PSE 0x0010 /* enable page size extensions */ +#define X86_CR4_PAE 0x0020 /* enable physical address extensions */ +#define X86_CR4_MCE 0x0040 /* Machine check enable */ +#define X86_CR4_PGE 0x0080 /* enable global pages */ +#define X86_CR4_PCE 0x0100 /* enable performance counters at ipl 3 */ +#define X86_CR4_OSFXSR 0x0200 /* enable fast FPU save and restore */ +#define X86_CR4_OSXMMEXCPT 0x0400 /* enable unmasked SSE exceptions */ + +/* + * Save the cr4 feature set we're using (ie + * Pentium 4MB enable and PPro Global page + * enable), so that any CPU's that boot up + * after us can get the correct flags. + */ +extern unsigned long mmu_cr4_features; + +static inline void set_in_cr4 (unsigned long mask) +{ + mmu_cr4_features |= mask; + switch (mask) { + case X86_CR4_OSFXSR: + case X86_CR4_OSXMMEXCPT: + break; + default: + do { + const char *msg = "Xen unsupported cr4 update\n"; + (void)HYPERVISOR_console_io( + CONSOLEIO_write, __builtin_strlen(msg), + (char *)msg); + BUG(); + } while (0); + } +} + +static inline void clear_in_cr4 (unsigned long mask) +{ + mmu_cr4_features &= ~mask; + __asm__("movl %%cr4,%%eax\n\t" + "andl %0,%%eax\n\t" + "movl %%eax,%%cr4\n" + : : "irg" (~mask) + :"ax"); +} + +/* + * NSC/Cyrix CPU configuration register indexes + */ + +#define CX86_PCR0 0x20 +#define CX86_GCR 0xb8 +#define CX86_CCR0 0xc0 +#define CX86_CCR1 0xc1 +#define CX86_CCR2 0xc2 +#define CX86_CCR3 0xc3 +#define CX86_CCR4 0xe8 +#define CX86_CCR5 0xe9 +#define CX86_CCR6 0xea +#define CX86_CCR7 0xeb +#define CX86_PCR1 0xf0 +#define CX86_DIR0 0xfe +#define CX86_DIR1 0xff +#define CX86_ARR_BASE 0xc4 +#define CX86_RCR_BASE 0xdc + +/* + * NSC/Cyrix CPU indexed register access macros + */ + +#define getCx86(reg) ({ outb((reg), 0x22); inb(0x23); }) + +#define setCx86(reg, data) do { \ + outb((reg), 0x22); \ + outb((data), 0x23); \ +} while (0) + +static inline void __monitor(const void *eax, unsigned long ecx, + unsigned long edx) +{ + /* "monitor %eax,%ecx,%edx;" */ + asm volatile( + ".byte 0x0f,0x01,0xc8;" + : :"a" (eax), "c" (ecx), "d"(edx)); +} + +static inline void __mwait(unsigned long eax, unsigned long ecx) +{ + /* "mwait %eax,%ecx;" */ + asm volatile( + ".byte 0x0f,0x01,0xc9;" + : :"a" (eax), "c" (ecx)); +} + +/* from system description table in BIOS. Mostly for MCA use, but +others may find it useful. */ +extern unsigned int machine_id; +extern unsigned int machine_submodel_id; +extern unsigned int BIOS_revision; +extern unsigned int mca_pentium_flag; + +/* Boot loader type from the setup header */ +extern int bootloader_type; + +/* + * User space process size: 3GB (default). + */ +#define TASK_SIZE (PAGE_OFFSET) + +/* This decides where the kernel will search for a free chunk of vm + * space during mmap's. + */ +#define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 3)) + +#define HAVE_ARCH_PICK_MMAP_LAYOUT + +/* + * Size of io_bitmap. + */ +#define IO_BITMAP_BITS 65536 +#define IO_BITMAP_BYTES (IO_BITMAP_BITS/8) +#define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long)) +#define IO_BITMAP_OFFSET offsetof(struct tss_struct,io_bitmap) +#define INVALID_IO_BITMAP_OFFSET 0x8000 +#define INVALID_IO_BITMAP_OFFSET_LAZY 0x9000 + +struct i387_fsave_struct { + long cwd; + long swd; + long twd; + long fip; + long fcs; + long foo; + long fos; + long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */ + long status; /* software status information */ +}; + +struct i387_fxsave_struct { + unsigned short cwd; + unsigned short swd; + unsigned short twd; + unsigned short fop; + long fip; + long fcs; + long foo; + long fos; + long mxcsr; + long mxcsr_mask; + long st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */ + long xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */ + long padding[56]; +} __attribute__ ((aligned (16))); + +struct i387_soft_struct { + long cwd; + long swd; + long twd; + long fip; + long fcs; + long foo; + long fos; + long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */ + unsigned char ftop, changed, lookahead, no_update, rm, alimit; + struct info *info; + unsigned long entry_eip; +}; + +union i387_union { + struct i387_fsave_struct fsave; + struct i387_fxsave_struct fxsave; + struct i387_soft_struct soft; +}; + +typedef struct { + unsigned long seg; +} mm_segment_t; + +struct thread_struct; + +struct tss_struct { + unsigned short back_link,__blh; + unsigned long esp0; + unsigned short ss0,__ss0h; + unsigned long esp1; + unsigned short ss1,__ss1h; /* ss1 is used to cache MSR_IA32_SYSENTER_CS */ + unsigned long esp2; + unsigned short ss2,__ss2h; + unsigned long __cr3; + unsigned long eip; + unsigned long eflags; + unsigned long eax,ecx,edx,ebx; + unsigned long esp; + unsigned long ebp; + unsigned long esi; + unsigned long edi; + unsigned short es, __esh; + unsigned short cs, __csh; + unsigned short ss, __ssh; + unsigned short ds, __dsh; + unsigned short fs, __fsh; + unsigned short gs, __gsh; + unsigned short ldt, __ldth; + unsigned short trace, io_bitmap_base; + /* + * The extra 1 is there because the CPU will access an + * additional byte beyond the end of the IO permission + * bitmap. The extra byte must be all 1 bits, and must + * be within the limit. + */ + unsigned long io_bitmap[IO_BITMAP_LONGS + 1]; + /* + * Cache the current maximum and the last task that used the bitmap: + */ + unsigned long io_bitmap_max; + struct thread_struct *io_bitmap_owner; + /* + * pads the TSS to be cacheline-aligned (size is 0x100) + */ + unsigned long __cacheline_filler[35]; + /* + * .. and then another 0x100 bytes for emergency kernel stack + */ + unsigned long stack[64]; +} __attribute__((packed)); + +#define ARCH_MIN_TASKALIGN 16 + +struct thread_struct { +/* cached TLS descriptors. */ + struct desc_struct tls_array[GDT_ENTRY_TLS_ENTRIES]; + unsigned long esp0; + unsigned long sysenter_cs; + unsigned long eip; + unsigned long esp; + unsigned long fs; + unsigned long gs; + unsigned int io_pl; +/* Hardware debugging registers */ + unsigned long debugreg[8]; /* %%db0-7 debug registers */ +/* fault info */ + unsigned long cr2, trap_no, error_code; +/* floating point info */ + union i387_union i387; +/* virtual 86 mode info */ + struct vm86_struct __user * vm86_info; + unsigned long screen_bitmap; + unsigned long v86flags, v86mask, saved_esp0; + unsigned int saved_fs, saved_gs; +/* IO permissions */ + unsigned long *io_bitmap_ptr; +/* max allowed port in the bitmap, in bytes: */ + unsigned long io_bitmap_max; +}; + +#define INIT_THREAD { \ + .vm86_info = NULL, \ + .sysenter_cs = __KERNEL_CS, \ + .io_bitmap_ptr = NULL, \ +} + +/* + * Note that the .io_bitmap member must be extra-big. This is because + * the CPU will access an additional byte beyond the end of the IO + * permission bitmap. The extra byte must be all 1 bits, and must + * be within the limit. + */ +#define INIT_TSS { \ + .esp0 = sizeof(init_stack) + (long)&init_stack, \ + .ss0 = __KERNEL_DS, \ + .ss1 = __KERNEL_CS, \ + .ldt = GDT_ENTRY_LDT, \ + .io_bitmap_base = INVALID_IO_BITMAP_OFFSET, \ + .io_bitmap = { [ 0 ... IO_BITMAP_LONGS] = ~0 }, \ +} + +static inline void load_esp0(struct tss_struct *tss, struct thread_struct *thread) +{ + tss->esp0 = thread->esp0; + /* This can only happen when SEP is enabled, no need to test "SEP"arately */ + if (unlikely(tss->ss1 != thread->sysenter_cs)) { + tss->ss1 = thread->sysenter_cs; + wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0); + } + HYPERVISOR_stack_switch(tss->ss0, tss->esp0); +} + +#define start_thread(regs, new_eip, new_esp) do { \ + __asm__("movl %0,%%fs ; movl %0,%%gs": :"r" (0)); \ + set_fs(USER_DS); \ + regs->xds = __USER_DS; \ + regs->xes = __USER_DS; \ + regs->xss = __USER_DS; \ + regs->xcs = __USER_CS; \ + regs->eip = new_eip; \ + regs->esp = new_esp; \ +} while (0) + +/* + * This special macro can be used to load a debugging register + */ +#define loaddebug(thread,register) \ + HYPERVISOR_set_debugreg((register), \ + ((thread)->debugreg[register])) + +/* Forward declaration, a strange C thing */ +struct task_struct; +struct mm_struct; + +/* Free all resources held by a thread. */ +extern void release_thread(struct task_struct *); + +/* Prepare to copy thread state - unlazy all lazy status */ +extern void prepare_to_copy(struct task_struct *tsk); + +/* + * create a kernel thread without removing it from tasklists + */ +extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); + +extern unsigned long thread_saved_pc(struct task_struct *tsk); +void show_trace(struct task_struct *task, unsigned long *stack); + +unsigned long get_wchan(struct task_struct *p); + +#define THREAD_SIZE_LONGS (THREAD_SIZE/sizeof(unsigned long)) +#define KSTK_TOP(info) \ +({ \ + unsigned long *__ptr = (unsigned long *)(info); \ + (unsigned long)(&__ptr[THREAD_SIZE_LONGS]); \ +}) + +#define task_pt_regs(task) \ +({ \ + struct pt_regs *__regs__; \ + __regs__ = (struct pt_regs *)KSTK_TOP((task)->thread_info); \ + __regs__ - 1; \ +}) + +#define KSTK_EIP(task) (task_pt_regs(task)->eip) +#define KSTK_ESP(task) (task_pt_regs(task)->esp) + + +struct microcode_header { + unsigned int hdrver; + unsigned int rev; + unsigned int date; + unsigned int sig; + unsigned int cksum; + unsigned int ldrver; + unsigned int pf; + unsigned int datasize; + unsigned int totalsize; + unsigned int reserved[3]; +}; + +struct microcode { + struct microcode_header hdr; + unsigned int bits[0]; +}; + +typedef struct microcode microcode_t; +typedef struct microcode_header microcode_header_t; + +/* microcode format is extended from prescott processors */ +struct extended_signature { + unsigned int sig; + unsigned int pf; + unsigned int cksum; +}; + +struct extended_sigtable { + unsigned int count; + unsigned int cksum; + unsigned int reserved[3]; + struct extended_signature sigs[0]; +}; +/* '6' because it used to be for P6 only (but now covers Pentium 4 as well) */ +#define MICROCODE_IOCFREE _IO('6',0) + +/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ +static inline void rep_nop(void) +{ + __asm__ __volatile__("rep;nop": : :"memory"); +} + +#define cpu_relax() rep_nop() + +/* generic versions from gas */ +#define GENERIC_NOP1 ".byte 0x90\n" +#define GENERIC_NOP2 ".byte 0x89,0xf6\n" +#define GENERIC_NOP3 ".byte 0x8d,0x76,0x00\n" +#define GENERIC_NOP4 ".byte 0x8d,0x74,0x26,0x00\n" +#define GENERIC_NOP5 GENERIC_NOP1 GENERIC_NOP4 +#define GENERIC_NOP6 ".byte 0x8d,0xb6,0x00,0x00,0x00,0x00\n" +#define GENERIC_NOP7 ".byte 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00\n" +#define GENERIC_NOP8 GENERIC_NOP1 GENERIC_NOP7 + +/* Opteron nops */ +#define K8_NOP1 GENERIC_NOP1 +#define K8_NOP2 ".byte 0x66,0x90\n" +#define K8_NOP3 ".byte 0x66,0x66,0x90\n" +#define K8_NOP4 ".byte 0x66,0x66,0x66,0x90\n" +#define K8_NOP5 K8_NOP3 K8_NOP2 +#define K8_NOP6 K8_NOP3 K8_NOP3 +#define K8_NOP7 K8_NOP4 K8_NOP3 +#define K8_NOP8 K8_NOP4 K8_NOP4 + +/* K7 nops */ +/* uses eax dependencies (arbitary choice) */ +#define K7_NOP1 GENERIC_NOP1 +#define K7_NOP2 ".byte 0x8b,0xc0\n" +#define K7_NOP3 ".byte 0x8d,0x04,0x20\n" +#define K7_NOP4 ".byte 0x8d,0x44,0x20,0x00\n" +#define K7_NOP5 K7_NOP4 ASM_NOP1 +#define K7_NOP6 ".byte 0x8d,0x80,0,0,0,0\n" +#define K7_NOP7 ".byte 0x8D,0x04,0x05,0,0,0,0\n" +#define K7_NOP8 K7_NOP7 ASM_NOP1 + +#ifdef CONFIG_MK8 +#define ASM_NOP1 K8_NOP1 +#define ASM_NOP2 K8_NOP2 +#define ASM_NOP3 K8_NOP3 +#define ASM_NOP4 K8_NOP4 +#define ASM_NOP5 K8_NOP5 +#define ASM_NOP6 K8_NOP6 +#define ASM_NOP7 K8_NOP7 +#define ASM_NOP8 K8_NOP8 +#elif defined(CONFIG_MK7) +#define ASM_NOP1 K7_NOP1 +#define ASM_NOP2 K7_NOP2 +#define ASM_NOP3 K7_NOP3 +#define ASM_NOP4 K7_NOP4 +#define ASM_NOP5 K7_NOP5 +#define ASM_NOP6 K7_NOP6 +#define ASM_NOP7 K7_NOP7 +#define ASM_NOP8 K7_NOP8 +#else +#define ASM_NOP1 GENERIC_NOP1 +#define ASM_NOP2 GENERIC_NOP2 +#define ASM_NOP3 GENERIC_NOP3 +#define ASM_NOP4 GENERIC_NOP4 +#define ASM_NOP5 GENERIC_NOP5 +#define ASM_NOP6 GENERIC_NOP6 +#define ASM_NOP7 GENERIC_NOP7 +#define ASM_NOP8 GENERIC_NOP8 +#endif + +#define ASM_NOP_MAX 8 + +/* Prefetch instructions for Pentium III and AMD Athlon */ +/* It's not worth to care about 3dnow! prefetches for the K6 + because they are microcoded there and very slow. + However we don't do prefetches for pre XP Athlons currently + That should be fixed. */ +#define ARCH_HAS_PREFETCH +extern inline void prefetch(const void *x) +{ + alternative_input(ASM_NOP4, + "prefetchnta (%1)", + X86_FEATURE_XMM, + "r" (x)); +} + +#define ARCH_HAS_PREFETCH +#define ARCH_HAS_PREFETCHW +#define ARCH_HAS_SPINLOCK_PREFETCH + +/* 3dnow! prefetch to get an exclusive cache line. Useful for + spinlocks to avoid one state transition in the cache coherency protocol. */ +extern inline void prefetchw(const void *x) +{ + alternative_input(ASM_NOP4, + "prefetchw (%1)", + X86_FEATURE_3DNOW, + "r" (x)); +} +#define spin_lock_prefetch(x) prefetchw(x) + +extern void select_idle_routine(const struct cpuinfo_x86 *c); + +#define cache_line_size() (boot_cpu_data.x86_cache_alignment) + +extern unsigned long boot_option_idle_override; + +#endif /* __ASM_I386_PROCESSOR_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/ptrace.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/ptrace.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,69 @@ +#ifndef _I386_PTRACE_H +#define _I386_PTRACE_H + +#define EBX 0 +#define ECX 1 +#define EDX 2 +#define ESI 3 +#define EDI 4 +#define EBP 5 +#define EAX 6 +#define DS 7 +#define ES 8 +#define FS 9 +#define GS 10 +#define ORIG_EAX 11 +#define EIP 12 +#define CS 13 +#define EFL 14 +#define UESP 15 +#define SS 16 +#define FRAME_SIZE 17 + +/* this struct defines the way the registers are stored on the + stack during a system call. */ + +struct pt_regs { + long ebx; + long ecx; + long edx; + long esi; + long edi; + long ebp; + long eax; + int xds; + int xes; + long orig_eax; + long eip; + int xcs; + long eflags; + long esp; + int xss; +}; + +/* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */ +#define PTRACE_GETREGS 12 +#define PTRACE_SETREGS 13 +#define PTRACE_GETFPREGS 14 +#define PTRACE_SETFPREGS 15 +#define PTRACE_GETFPXREGS 18 +#define PTRACE_SETFPXREGS 19 + +#define PTRACE_OLDSETOPTIONS 21 + +#define PTRACE_GET_THREAD_AREA 25 +#define PTRACE_SET_THREAD_AREA 26 + +#ifdef __KERNEL__ +struct task_struct; +extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code); +#define user_mode(regs) ((VM_MASK & (regs)->eflags) || (2 & (regs)->xcs)) +#define instruction_pointer(regs) ((regs)->eip) +#if defined(CONFIG_SMP) && defined(CONFIG_FRAME_POINTER) +extern unsigned long profile_pc(struct pt_regs *regs); +#else +#define profile_pc(regs) instruction_pointer(regs) +#endif +#endif + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/scatterlist.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/scatterlist.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,22 @@ +#ifndef _I386_SCATTERLIST_H +#define _I386_SCATTERLIST_H + +struct scatterlist { + struct page *page; + unsigned int offset; + unsigned int length; + dma_addr_t dma_address; + unsigned int dma_length; +}; + +/* These macros should be used after a pci_map_sg call has been done + * to get bus addresses of each of the SG entries and their lengths. + * You should only work with the number of sg entries pci_map_sg + * returns. + */ +#define sg_dma_address(sg) ((sg)->dma_address) +#define sg_dma_len(sg) ((sg)->dma_length) + +#define ISA_DMA_THRESHOLD (0x00ffffff) + +#endif /* !(_I386_SCATTERLIST_H) */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/segment.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/segment.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,99 @@ +#ifndef _ASM_SEGMENT_H +#define _ASM_SEGMENT_H + +/* + * The layout of the per-CPU GDT under Linux: + * + * 0 - null + * 1 - reserved + * 2 - reserved + * 3 - reserved + * + * 4 - unused <==== new cacheline + * 5 - unused + * + * ------- start of TLS (Thread-Local Storage) segments: + * + * 6 - TLS segment #1 [ glibc's TLS segment ] + * 7 - TLS segment #2 [ Wine's %fs Win32 segment ] + * 8 - TLS segment #3 + * 9 - reserved + * 10 - reserved + * 11 - reserved + * + * ------- start of kernel segments: + * + * 12 - kernel code segment <==== new cacheline + * 13 - kernel data segment + * 14 - default user CS + * 15 - default user DS + * 16 - TSS + * 17 - LDT + * 18 - PNPBIOS support (16->32 gate) + * 19 - PNPBIOS support + * 20 - PNPBIOS support + * 21 - PNPBIOS support + * 22 - PNPBIOS support + * 23 - APM BIOS support + * 24 - APM BIOS support + * 25 - APM BIOS support + * + * 26 - ESPFIX small SS + * 27 - unused + * 28 - unused + * 29 - unused + * 30 - unused + * 31 - TSS for double fault handler + */ +#define GDT_ENTRY_TLS_ENTRIES 3 +#define GDT_ENTRY_TLS_MIN 6 +#define GDT_ENTRY_TLS_MAX (GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1) + +#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8) + +#define GDT_ENTRY_DEFAULT_USER_CS 14 +#define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS * 8 + 3) + +#define GDT_ENTRY_DEFAULT_USER_DS 15 +#define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS * 8 + 3) + +#define GDT_ENTRY_KERNEL_BASE 12 + +#define GDT_ENTRY_KERNEL_CS (GDT_ENTRY_KERNEL_BASE + 0) +#define __KERNEL_CS (GDT_ENTRY_KERNEL_CS * 8 + 1) + +#define GDT_ENTRY_KERNEL_DS (GDT_ENTRY_KERNEL_BASE + 1) +#define __KERNEL_DS (GDT_ENTRY_KERNEL_DS * 8 + 1) + +#define GDT_ENTRY_TSS (GDT_ENTRY_KERNEL_BASE + 4) +#define GDT_ENTRY_LDT (GDT_ENTRY_KERNEL_BASE + 5) + +#define GDT_ENTRY_PNPBIOS_BASE (GDT_ENTRY_KERNEL_BASE + 6) +#define GDT_ENTRY_APMBIOS_BASE (GDT_ENTRY_KERNEL_BASE + 11) + +#define GDT_ENTRY_ESPFIX_SS (GDT_ENTRY_KERNEL_BASE + 14) +#define __ESPFIX_SS (GDT_ENTRY_ESPFIX_SS * 8) + +#define GDT_ENTRY_DOUBLEFAULT_TSS 31 + +/* + * The GDT has 32 entries + */ +#define GDT_ENTRIES 32 + +#define GDT_SIZE (GDT_ENTRIES * 8) + +/* Simple and small GDT entries for booting only */ + +#define __BOOT_CS FLAT_KERNEL_CS + +#define __BOOT_DS FLAT_KERNEL_DS + +/* + * The interrupt descriptor table has room for 256 idt's, + * the global descriptor table is dependent on the number + * of tasks we can have.. + */ +#define IDT_ENTRIES 256 + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/setup.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/setup.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,66 @@ +/* + * Just a place holder. We don't want to have to test x86 before + * we include stuff + */ + +#ifndef _i386_SETUP_H +#define _i386_SETUP_H + +#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) +#define PFN_DOWN(x) ((x) >> PAGE_SHIFT) +#define PFN_PHYS(x) ((unsigned long long)(x) << PAGE_SHIFT) + +/* + * Reserved space for vmalloc and iomap - defined in asm/page.h + */ +#define MAXMEM_PFN PFN_DOWN(MAXMEM) +#define MAX_NONPAE_PFN (1 << 20) + +#define PARAM_SIZE 4096 +#define COMMAND_LINE_SIZE 256 + +#define OLD_CL_MAGIC_ADDR 0x90020 +#define OLD_CL_MAGIC 0xA33F +#define OLD_CL_BASE_ADDR 0x90000 +#define OLD_CL_OFFSET 0x90022 +#define NEW_CL_POINTER 0x228 /* Relative to real mode data */ + +#ifndef __ASSEMBLY__ +/* + * This is set up by the setup-routine at boot-time + */ +extern unsigned char boot_params[PARAM_SIZE]; + +#define PARAM (boot_params) +#define SCREEN_INFO (*(struct screen_info *) (PARAM+0)) +#define EXT_MEM_K (*(unsigned short *) (PARAM+2)) +#define ALT_MEM_K (*(unsigned long *) (PARAM+0x1e0)) +#define E820_MAP_NR (*(char*) (PARAM+E820NR)) +#define E820_MAP ((struct e820entry *) (PARAM+E820MAP)) +#define APM_BIOS_INFO (*(struct apm_bios_info *) (PARAM+0x40)) +#define IST_INFO (*(struct ist_info *) (PARAM+0x60)) +#define DRIVE_INFO (*(struct drive_info_struct *) (PARAM+0x80)) +#define SYS_DESC_TABLE (*(struct sys_desc_table_struct*)(PARAM+0xa0)) +#define EFI_SYSTAB ((efi_system_table_t *) *((unsigned long *)(PARAM+0x1c4))) +#define EFI_MEMDESC_SIZE (*((unsigned long *) (PARAM+0x1c8))) +#define EFI_MEMDESC_VERSION (*((unsigned long *) (PARAM+0x1cc))) +#define EFI_MEMMAP ((efi_memory_desc_t *) *((unsigned long *)(PARAM+0x1d0))) +#define EFI_MEMMAP_SIZE (*((unsigned long *) (PARAM+0x1d4))) +#define MOUNT_ROOT_RDONLY (*(unsigned short *) (PARAM+0x1F2)) +#define RAMDISK_FLAGS (*(unsigned short *) (PARAM+0x1F8)) +#define VIDEO_MODE (*(unsigned short *) (PARAM+0x1FA)) +#define ORIG_ROOT_DEV (*(unsigned short *) (PARAM+0x1FC)) +#define AUX_DEVICE_INFO (*(unsigned char *) (PARAM+0x1FF)) +#define LOADER_TYPE (*(unsigned char *) (PARAM+0x210)) +#define KERNEL_START (*(unsigned long *) (PARAM+0x214)) +#define INITRD_START (__pa(xen_start_info->mod_start)) +#define INITRD_SIZE (xen_start_info->mod_len) +#define EDID_INFO (*(struct edid_info *) (PARAM+0x440)) +#define EDD_NR (*(unsigned char *) (PARAM+EDDNR)) +#define EDD_MBR_SIG_NR (*(unsigned char *) (PARAM+EDD_MBR_SIG_NR_BUF)) +#define EDD_MBR_SIGNATURE ((unsigned int *) (PARAM+EDD_MBR_SIG_BUF)) +#define EDD_BUF ((struct edd_info *) (PARAM+EDDBUF)) + +#endif /* __ASSEMBLY__ */ + +#endif /* _i386_SETUP_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/smp.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/smp.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,93 @@ +#ifndef __ASM_SMP_H +#define __ASM_SMP_H + +/* + * We need the APIC definitions automatically as part of 'smp.h' + */ +#ifndef __ASSEMBLY__ +#include <linux/config.h> +#include <linux/kernel.h> +#include <linux/threads.h> +#include <linux/cpumask.h> +#endif + +#ifdef CONFIG_X86_LOCAL_APIC +#ifndef __ASSEMBLY__ +#include <asm/fixmap.h> +#include <asm/bitops.h> +#include <asm/mpspec.h> +#ifdef CONFIG_X86_IO_APIC +#include <asm/io_apic.h> +#endif +#include <asm/apic.h> +#endif +#endif + +#define BAD_APICID 0xFFu +#ifdef CONFIG_SMP +#ifndef __ASSEMBLY__ + +/* + * Private routines/data + */ + +extern void smp_alloc_memory(void); +extern int pic_mode; +extern int smp_num_siblings; +extern cpumask_t cpu_sibling_map[]; +extern cpumask_t cpu_core_map[]; + +extern void smp_flush_tlb(void); +extern void smp_message_irq(int cpl, void *dev_id, struct pt_regs *regs); +extern void smp_invalidate_rcv(void); /* Process an NMI */ +extern void (*mtrr_hook) (void); +extern void zap_low_mappings (void); + +#define MAX_APICID 256 +extern u8 x86_cpu_to_apicid[]; + +/* + * This function is needed by all SMP systems. It must _always_ be valid + * from the initial startup. We map APIC_BASE very early in page_setup(), + * so this is correct in the x86 case. + */ +#define __smp_processor_id() (current_thread_info()->cpu) + +extern cpumask_t cpu_possible_map; +#define cpu_callin_map cpu_possible_map + +/* We don't mark CPUs online until __cpu_up(), so we need another measure */ +static inline int num_booting_cpus(void) +{ + return cpus_weight(cpu_possible_map); +} + +#ifdef CONFIG_X86_LOCAL_APIC + +#ifdef APIC_DEFINITION +extern int hard_smp_processor_id(void); +#else +#include <mach_apicdef.h> +static inline int hard_smp_processor_id(void) +{ + /* we don't want to mark this access volatile - bad code generation */ + return GET_APIC_ID(*(unsigned long *)(APIC_BASE+APIC_ID)); +} +#endif + +static __inline int logical_smp_processor_id(void) +{ + /* we don't want to mark this access volatile - bad code generation */ + return GET_APIC_LOGICAL_ID(*(unsigned long *)(APIC_BASE+APIC_LDR)); +} + +#endif + +extern int __cpu_disable(void); +extern void __cpu_die(unsigned int cpu); +#endif /* !__ASSEMBLY__ */ + +#define NO_PROC_ID 0xFF /* No processor magic marker */ + +#endif +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/spinlock.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/spinlock.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,277 @@ +#ifndef __ASM_SPINLOCK_H +#define __ASM_SPINLOCK_H + +#include <asm/atomic.h> +#include <asm/rwlock.h> +#include <asm/page.h> +#include <linux/config.h> +#include <linux/compiler.h> +#include <asm/smp_alt.h> + +asmlinkage int printk(const char * fmt, ...) + __attribute__ ((format (printf, 1, 2))); + +/* + * Your basic SMP spinlocks, allowing only a single CPU anywhere + */ + +typedef struct { + volatile unsigned int slock; +#ifdef CONFIG_DEBUG_SPINLOCK + unsigned magic; +#endif +#ifdef CONFIG_PREEMPT + unsigned int break_lock; +#endif +} spinlock_t; + +#define SPINLOCK_MAGIC 0xdead4ead + +#ifdef CONFIG_DEBUG_SPINLOCK +#define SPINLOCK_MAGIC_INIT , SPINLOCK_MAGIC +#else +#define SPINLOCK_MAGIC_INIT /* */ +#endif + +#define SPIN_LOCK_UNLOCKED (spinlock_t) { 1 SPINLOCK_MAGIC_INIT } + +#define spin_lock_init(x) do { *(x) = SPIN_LOCK_UNLOCKED; } while(0) + +/* + * Simple spin lock operations. There are two variants, one clears IRQ's + * on the local processor, one does not. + * + * We make no fairness assumptions. They have a cost. + */ + +#define spin_is_locked(x) (*(volatile signed char *)(&(x)->slock) <= 0) +#define spin_unlock_wait(x) do { barrier(); } while(spin_is_locked(x)) + +#define spin_lock_string \ + "1:\n" \ + LOCK \ + "decb %0\n\t" \ + "jns 3f\n" \ + "2:\t" \ + "rep;nop\n\t" \ + "cmpb $0,%0\n\t" \ + "jle 2b\n\t" \ + "jmp 1b\n" \ + "3:\n\t" + +#define spin_lock_string_flags \ + "1:\n" \ + LOCK \ + "decb %0\n\t" \ + "jns 4f\n\t" \ + "2:\t" \ + "testl $0x200, %1\n\t" \ + "jz 3f\n\t" \ + "#sti\n\t" \ + "3:\t" \ + "rep;nop\n\t" \ + "cmpb $0, %0\n\t" \ + "jle 3b\n\t" \ + "#cli\n\t" \ + "jmp 1b\n" \ + "4:\n\t" + +/* + * This works. Despite all the confusion. + * (except on PPro SMP or if we are using OOSTORE) + * (PPro errata 66, 92) + */ + +#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE) + +#define spin_unlock_string \ + "movb $1,%0" \ + :"=m" (lock->slock) : : "memory" + + +static inline void _raw_spin_unlock(spinlock_t *lock) +{ +#ifdef CONFIG_DEBUG_SPINLOCK + BUG_ON(lock->magic != SPINLOCK_MAGIC); + BUG_ON(!spin_is_locked(lock)); +#endif + __asm__ __volatile__( + spin_unlock_string + ); +} + +#else + +#define spin_unlock_string \ + "xchgb %b0, %1" \ + :"=q" (oldval), "=m" (lock->slock) \ + :"0" (oldval) : "memory" + +static inline void _raw_spin_unlock(spinlock_t *lock) +{ + char oldval = 1; +#ifdef CONFIG_DEBUG_SPINLOCK + BUG_ON(lock->magic != SPINLOCK_MAGIC); + BUG_ON(!spin_is_locked(lock)); +#endif + __asm__ __volatile__( + spin_unlock_string + ); +} + +#endif + +static inline int _raw_spin_trylock(spinlock_t *lock) +{ + char oldval; +#ifdef CONFIG_SMP_ALTERNATIVES + __asm__ __volatile__( + "1:movb %1,%b0\n" + "movb $0,%1\n" + "2:" + ".section __smp_alternatives,\"a\"\n" + ".long 1b\n" + ".long 3f\n" + ".previous\n" + ".section __smp_replacements,\"a\"\n" + "3: .byte 2b - 1b\n" + ".byte 5f-4f\n" + ".byte 0\n" + ".byte 6f-5f\n" + ".byte -1\n" + "4: xchgb %b0,%1\n" + "5: movb %1,%b0\n" + "movb $0,%1\n" + "6:\n" + ".previous\n" + :"=q" (oldval), "=m" (lock->slock) + :"0" (0) : "memory"); +#else + __asm__ __volatile__( + "xchgb %b0,%1\n" + :"=q" (oldval), "=m" (lock->slock) + :"0" (0) : "memory"); +#endif + return oldval > 0; +} + +static inline void _raw_spin_lock(spinlock_t *lock) +{ +#ifdef CONFIG_DEBUG_SPINLOCK + if (unlikely(lock->magic != SPINLOCK_MAGIC)) { + printk("eip: %p\n", __builtin_return_address(0)); + BUG(); + } +#endif + __asm__ __volatile__( + spin_lock_string + :"=m" (lock->slock) : : "memory"); +} + +static inline void _raw_spin_lock_flags (spinlock_t *lock, unsigned long flags) +{ +#ifdef CONFIG_DEBUG_SPINLOCK + if (unlikely(lock->magic != SPINLOCK_MAGIC)) { + printk("eip: %p\n", __builtin_return_address(0)); + BUG(); + } +#endif + __asm__ __volatile__( + spin_lock_string_flags + :"=m" (lock->slock) : "r" (flags) : "memory"); +} + +/* + * Read-write spinlocks, allowing multiple readers + * but only one writer. + * + * NOTE! it is quite common to have readers in interrupts + * but no interrupt writers. For those circumstances we + * can "mix" irq-safe locks - any writer needs to get a + * irq-safe write-lock, but readers can get non-irqsafe + * read-locks. + */ +typedef struct { + volatile unsigned int lock; +#ifdef CONFIG_DEBUG_SPINLOCK + unsigned magic; +#endif +#ifdef CONFIG_PREEMPT + unsigned int break_lock; +#endif +} rwlock_t; + +#define RWLOCK_MAGIC 0xdeaf1eed + +#ifdef CONFIG_DEBUG_SPINLOCK +#define RWLOCK_MAGIC_INIT , RWLOCK_MAGIC +#else +#define RWLOCK_MAGIC_INIT /* */ +#endif + +#define RW_LOCK_UNLOCKED (rwlock_t) { RW_LOCK_BIAS RWLOCK_MAGIC_INIT } + +#define rwlock_init(x) do { *(x) = RW_LOCK_UNLOCKED; } while(0) + +/** + * read_can_lock - would read_trylock() succeed? + * @lock: the rwlock in question. + */ +#define read_can_lock(x) ((int)(x)->lock > 0) + +/** + * write_can_lock - would write_trylock() succeed? + * @lock: the rwlock in question. + */ +#define write_can_lock(x) ((x)->lock == RW_LOCK_BIAS) + +/* + * On x86, we implement read-write locks as a 32-bit counter + * with the high bit (sign) being the "contended" bit. + * + * The inline assembly is non-obvious. Think about it. + * + * Changed to use the same technique as rw semaphores. See + * semaphore.h for details. -ben + */ +/* the spinlock helpers are in arch/i386/kernel/semaphore.c */ + +static inline void _raw_read_lock(rwlock_t *rw) +{ +#ifdef CONFIG_DEBUG_SPINLOCK + BUG_ON(rw->magic != RWLOCK_MAGIC); +#endif + __build_read_lock(rw, "__read_lock_failed"); +} + +static inline void _raw_write_lock(rwlock_t *rw) +{ +#ifdef CONFIG_DEBUG_SPINLOCK + BUG_ON(rw->magic != RWLOCK_MAGIC); +#endif + __build_write_lock(rw, "__write_lock_failed"); +} + +#define _raw_read_unlock(rw) asm volatile(LOCK "incl %0" :"=m" ((rw)->lock) : : "memory") +#define _raw_write_unlock(rw) asm volatile(LOCK "addl $" RW_LOCK_BIAS_STR ",%0":"=m" ((rw)->lock) : : "memory") + +static inline int _raw_read_trylock(rwlock_t *lock) +{ + atomic_t *count = (atomic_t *)lock; + atomic_dec(count); + if (atomic_read(count) >= 0) + return 1; + atomic_inc(count); + return 0; +} + +static inline int _raw_write_trylock(rwlock_t *lock) +{ + atomic_t *count = (atomic_t *)lock; + if (atomic_sub_and_test(RW_LOCK_BIAS, count)) + return 1; + atomic_add(RW_LOCK_BIAS, count); + return 0; +} + +#endif /* __ASM_SPINLOCK_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/swiotlb.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/swiotlb.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,42 @@ +#ifndef _ASM_SWIOTLB_H +#define _ASM_SWIOTLB_H 1 + +#include <linux/config.h> + +/* SWIOTLB interface */ + +extern dma_addr_t swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, + int dir); +extern void swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, + size_t size, int dir); +extern void swiotlb_sync_single_for_cpu(struct device *hwdev, + dma_addr_t dev_addr, + size_t size, int dir); +extern void swiotlb_sync_single_for_device(struct device *hwdev, + dma_addr_t dev_addr, + size_t size, int dir); +extern void swiotlb_sync_sg_for_cpu(struct device *hwdev, + struct scatterlist *sg, int nelems, + int dir); +extern void swiotlb_sync_sg_for_device(struct device *hwdev, + struct scatterlist *sg, int nelems, + int dir); +extern int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, + int nents, int direction); +extern void swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, + int nents, int direction); +extern int swiotlb_dma_mapping_error(dma_addr_t dma_addr); +extern dma_addr_t swiotlb_map_page(struct device *hwdev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction direction); +extern void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dma_address, + size_t size, enum dma_data_direction direction); +extern int swiotlb_dma_supported(struct device *hwdev, u64 mask); + +#ifdef CONFIG_SWIOTLB +extern int swiotlb; +#else +#define swiotlb 0 +#endif + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/synch_bitops.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/synch_bitops.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,140 @@ +#ifndef __XEN_SYNCH_BITOPS_H__ +#define __XEN_SYNCH_BITOPS_H__ + +/* + * Copyright 1992, Linus Torvalds. + * Heavily modified to provide guaranteed strong synchronisation + * when communicating with Xen or other guest OSes running on other CPUs. + */ + +#include <linux/config.h> + +#define ADDR (*(volatile long *) addr) + +static __inline__ void synch_set_bit(int nr, volatile void * addr) +{ + __asm__ __volatile__ ( + "lock btsl %1,%0" + : "=m" (ADDR) : "Ir" (nr) : "memory" ); +} + +static __inline__ void synch_clear_bit(int nr, volatile void * addr) +{ + __asm__ __volatile__ ( + "lock btrl %1,%0" + : "=m" (ADDR) : "Ir" (nr) : "memory" ); +} + +static __inline__ void synch_change_bit(int nr, volatile void * addr) +{ + __asm__ __volatile__ ( + "lock btcl %1,%0" + : "=m" (ADDR) : "Ir" (nr) : "memory" ); +} + +static __inline__ int synch_test_and_set_bit(int nr, volatile void * addr) +{ + int oldbit; + __asm__ __volatile__ ( + "lock btsl %2,%1\n\tsbbl %0,%0" + : "=r" (oldbit), "=m" (ADDR) : "Ir" (nr) : "memory"); + return oldbit; +} + +static __inline__ int synch_test_and_clear_bit(int nr, volatile void * addr) +{ + int oldbit; + __asm__ __volatile__ ( + "lock btrl %2,%1\n\tsbbl %0,%0" + : "=r" (oldbit), "=m" (ADDR) : "Ir" (nr) : "memory"); + return oldbit; +} + +static __inline__ int synch_test_and_change_bit(int nr, volatile void * addr) +{ + int oldbit; + + __asm__ __volatile__ ( + "lock btcl %2,%1\n\tsbbl %0,%0" + : "=r" (oldbit), "=m" (ADDR) : "Ir" (nr) : "memory"); + return oldbit; +} + +struct __synch_xchg_dummy { unsigned long a[100]; }; +#define __synch_xg(x) ((struct __synch_xchg_dummy *)(x)) + +#define synch_cmpxchg(ptr, old, new) \ +((__typeof__(*(ptr)))__synch_cmpxchg((ptr),\ + (unsigned long)(old), \ + (unsigned long)(new), \ + sizeof(*(ptr)))) + +static inline unsigned long __synch_cmpxchg(volatile void *ptr, + unsigned long old, + unsigned long new, int size) +{ + unsigned long prev; + switch (size) { + case 1: + __asm__ __volatile__("lock; cmpxchgb %b1,%2" + : "=a"(prev) + : "q"(new), "m"(*__synch_xg(ptr)), + "0"(old) + : "memory"); + return prev; + case 2: + __asm__ __volatile__("lock; cmpxchgw %w1,%2" + : "=a"(prev) + : "q"(new), "m"(*__synch_xg(ptr)), + "0"(old) + : "memory"); + return prev; +#ifdef CONFIG_X86_64 + case 4: + __asm__ __volatile__("lock; cmpxchgl %k1,%2" + : "=a"(prev) + : "q"(new), "m"(*__synch_xg(ptr)), + "0"(old) + : "memory"); + return prev; + case 8: + __asm__ __volatile__("lock; cmpxchgq %1,%2" + : "=a"(prev) + : "q"(new), "m"(*__synch_xg(ptr)), + "0"(old) + : "memory"); + return prev; +#else + case 4: + __asm__ __volatile__("lock; cmpxchgl %1,%2" + : "=a"(prev) + : "q"(new), "m"(*__synch_xg(ptr)), + "0"(old) + : "memory"); + return prev; +#endif + } + return old; +} + +static __inline__ int synch_const_test_bit(int nr, const volatile void * addr) +{ + return ((1UL << (nr & 31)) & + (((const volatile unsigned int *) addr)[nr >> 5])) != 0; +} + +static __inline__ int synch_var_test_bit(int nr, volatile void * addr) +{ + int oldbit; + __asm__ __volatile__ ( + "btl %2,%1\n\tsbbl %0,%0" + : "=r" (oldbit) : "m" (ADDR), "Ir" (nr) ); + return oldbit; +} + +#define synch_test_bit(nr,addr) \ +(__builtin_constant_p(nr) ? \ + synch_const_test_bit((nr),(addr)) : \ + synch_var_test_bit((nr),(addr))) + +#endif /* __XEN_SYNCH_BITOPS_H__ */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/system.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/system.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,588 @@ +#ifndef __ASM_SYSTEM_H +#define __ASM_SYSTEM_H + +#include <linux/config.h> +#include <linux/kernel.h> +#include <linux/bitops.h> +#include <asm/synch_bitops.h> +#include <asm/segment.h> +#include <asm/cpufeature.h> +#include <asm/hypervisor.h> +#include <asm/smp_alt.h> + +#ifdef __KERNEL__ + +struct task_struct; /* one of the stranger aspects of C forward declarations.. */ +extern struct task_struct * FASTCALL(__switch_to(struct task_struct *prev, struct task_struct *next)); + +#define switch_to(prev,next,last) do { \ + unsigned long esi,edi; \ + asm volatile("pushfl\n\t" \ + "pushl %%ebp\n\t" \ + "movl %%esp,%0\n\t" /* save ESP */ \ + "movl %5,%%esp\n\t" /* restore ESP */ \ + "movl $1f,%1\n\t" /* save EIP */ \ + "pushl %6\n\t" /* restore EIP */ \ + "jmp __switch_to\n" \ + "1:\t" \ + "popl %%ebp\n\t" \ + "popfl" \ + :"=m" (prev->thread.esp),"=m" (prev->thread.eip), \ + "=a" (last),"=S" (esi),"=D" (edi) \ + :"m" (next->thread.esp),"m" (next->thread.eip), \ + "2" (prev), "d" (next)); \ +} while (0) + +#define _set_base(addr,base) do { unsigned long __pr; \ +__asm__ __volatile__ ("movw %%dx,%1\n\t" \ + "rorl $16,%%edx\n\t" \ + "movb %%dl,%2\n\t" \ + "movb %%dh,%3" \ + :"=&d" (__pr) \ + :"m" (*((addr)+2)), \ + "m" (*((addr)+4)), \ + "m" (*((addr)+7)), \ + "0" (base) \ + ); } while(0) + +#define _set_limit(addr,limit) do { unsigned long __lr; \ +__asm__ __volatile__ ("movw %%dx,%1\n\t" \ + "rorl $16,%%edx\n\t" \ + "movb %2,%%dh\n\t" \ + "andb $0xf0,%%dh\n\t" \ + "orb %%dh,%%dl\n\t" \ + "movb %%dl,%2" \ + :"=&d" (__lr) \ + :"m" (*(addr)), \ + "m" (*((addr)+6)), \ + "0" (limit) \ + ); } while(0) + +#define set_base(ldt,base) _set_base( ((char *)&(ldt)) , (base) ) +#define set_limit(ldt,limit) _set_limit( ((char *)&(ldt)) , ((limit)-1)>>12 ) + +static inline unsigned long _get_base(char * addr) +{ + unsigned long __base; + __asm__("movb %3,%%dh\n\t" + "movb %2,%%dl\n\t" + "shll $16,%%edx\n\t" + "movw %1,%%dx" + :"=&d" (__base) + :"m" (*((addr)+2)), + "m" (*((addr)+4)), + "m" (*((addr)+7))); + return __base; +} + +#define get_base(ldt) _get_base( ((char *)&(ldt)) ) + +/* + * Load a segment. Fall back on loading the zero + * segment if something goes wrong.. + */ +#define loadsegment(seg,value) \ + asm volatile("\n" \ + "1:\t" \ + "mov %0,%%" #seg "\n" \ + "2:\n" \ + ".section .fixup,\"ax\"\n" \ + "3:\t" \ + "pushl $0\n\t" \ + "popl %%" #seg "\n\t" \ + "jmp 2b\n" \ + ".previous\n" \ + ".section __ex_table,\"a\"\n\t" \ + ".align 4\n\t" \ + ".long 1b,3b\n" \ + ".previous" \ + : :"m" (value)) + +/* + * Save a segment register away + */ +#define savesegment(seg, value) \ + asm volatile("mov %%" #seg ",%0":"=m" (value)) + +/* + * Clear and set 'TS' bit respectively + */ +#define clts() (HYPERVISOR_fpu_taskswitch(0)) +#define read_cr0() ({ \ + unsigned int __dummy; \ + __asm__( \ + "movl %%cr0,%0\n\t" \ + :"=r" (__dummy)); \ + __dummy; \ +}) +#define write_cr0(x) \ + __asm__("movl %0,%%cr0": :"r" (x)); + +#define read_cr4() ({ \ + unsigned int __dummy; \ + __asm__( \ + "movl %%cr4,%0\n\t" \ + :"=r" (__dummy)); \ + __dummy; \ +}) +#define write_cr4(x) \ + __asm__("movl %0,%%cr4": :"r" (x)); +#define stts() (HYPERVISOR_fpu_taskswitch(1)) + +#endif /* __KERNEL__ */ + +#define wbinvd() \ + __asm__ __volatile__ ("wbinvd": : :"memory"); + +static inline unsigned long get_limit(unsigned long segment) +{ + unsigned long __limit; + __asm__("lsll %1,%0" + :"=r" (__limit):"r" (segment)); + return __limit+1; +} + +#define nop() __asm__ __volatile__ ("nop") + +#define xchg(ptr,v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v),(ptr),sizeof(*(ptr)))) + +#define tas(ptr) (xchg((ptr),1)) + +struct __xchg_dummy { unsigned long a[100]; }; +#define __xg(x) ((struct __xchg_dummy *)(x)) + + +/* + * The semantics of XCHGCMP8B are a bit strange, this is why + * there is a loop and the loading of %%eax and %%edx has to + * be inside. This inlines well in most cases, the cached + * cost is around ~38 cycles. (in the future we might want + * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that + * might have an implicit FPU-save as a cost, so it's not + * clear which path to go.) + * + * cmpxchg8b must be used with the lock prefix here to allow + * the instruction to be executed atomically, see page 3-102 + * of the instruction set reference 24319102.pdf. We need + * the reader side to see the coherent 64bit value. + */ +static inline void __set_64bit (unsigned long long * ptr, + unsigned int low, unsigned int high) +{ + __asm__ __volatile__ ( + "\n1:\t" + "movl (%0), %%eax\n\t" + "movl 4(%0), %%edx\n\t" + "lock cmpxchg8b (%0)\n\t" + "jnz 1b" + : /* no outputs */ + : "D"(ptr), + "b"(low), + "c"(high) + : "ax","dx","memory"); +} + +static inline void __set_64bit_constant (unsigned long long *ptr, + unsigned long long value) +{ + __set_64bit(ptr,(unsigned int)(value), (unsigned int)((value)>>32ULL)); +} +#define ll_low(x) *(((unsigned int*)&(x))+0) +#define ll_high(x) *(((unsigned int*)&(x))+1) + +static inline void __set_64bit_var (unsigned long long *ptr, + unsigned long long value) +{ + __set_64bit(ptr,ll_low(value), ll_high(value)); +} + +#define set_64bit(ptr,value) \ +(__builtin_constant_p(value) ? \ + __set_64bit_constant(ptr, value) : \ + __set_64bit_var(ptr, value) ) + +#define _set_64bit(ptr,value) \ +(__builtin_constant_p(value) ? \ + __set_64bit(ptr, (unsigned int)(value), (unsigned int)((value)>>32ULL) ) : \ + __set_64bit(ptr, ll_low(value), ll_high(value)) ) + +/* + * Note: no "lock" prefix even on SMP: xchg always implies lock anyway + * Note 2: xchg has side effect, so that attribute volatile is necessary, + * but generally the primitive is invalid, *ptr is output argument. --ANK + */ +static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size) +{ + switch (size) { + case 1: + __asm__ __volatile__("xchgb %b0,%1" + :"=q" (x) + :"m" (*__xg(ptr)), "0" (x) + :"memory"); + break; + case 2: + __asm__ __volatile__("xchgw %w0,%1" + :"=r" (x) + :"m" (*__xg(ptr)), "0" (x) + :"memory"); + break; + case 4: + __asm__ __volatile__("xchgl %0,%1" + :"=r" (x) + :"m" (*__xg(ptr)), "0" (x) + :"memory"); + break; + } + return x; +} + +/* + * Atomic compare and exchange. Compare OLD with MEM, if identical, + * store NEW in MEM. Return the initial value in MEM. Success is + * indicated by comparing RETURN with OLD. + */ + +#ifdef CONFIG_X86_CMPXCHG +#define __HAVE_ARCH_CMPXCHG 1 +#endif + +static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, + unsigned long new, int size) +{ + unsigned long prev; + switch (size) { + case 1: + __asm__ __volatile__(LOCK "cmpxchgb %b1,%2" + : "=a"(prev) + : "q"(new), "m"(*__xg(ptr)), "0"(old) + : "memory"); + return prev; + case 2: + __asm__ __volatile__(LOCK "cmpxchgw %w1,%2" + : "=a"(prev) + : "q"(new), "m"(*__xg(ptr)), "0"(old) + : "memory"); + return prev; + case 4: + __asm__ __volatile__(LOCK "cmpxchgl %1,%2" + : "=a"(prev) + : "q"(new), "m"(*__xg(ptr)), "0"(old) + : "memory"); + return prev; + } + return old; +} + +#define cmpxchg(ptr,o,n)\ + ((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\ + (unsigned long)(n),sizeof(*(ptr)))) + +#ifdef __KERNEL__ +struct alt_instr { + __u8 *instr; /* original instruction */ + __u8 *replacement; + __u8 cpuid; /* cpuid bit set for replacement */ + __u8 instrlen; /* length of original instruction */ + __u8 replacementlen; /* length of new instruction, <= instrlen */ + __u8 pad; +}; +#endif + +/* + * Alternative instructions for different CPU types or capabilities. + * + * This allows to use optimized instructions even on generic binary + * kernels. + * + * length of oldinstr must be longer or equal the length of newinstr + * It can be padded with nops as needed. + * + * For non barrier like inlines please define new variants + * without volatile and memory clobber. + */ +#define alternative(oldinstr, newinstr, feature) \ + asm volatile ("661:\n\t" oldinstr "\n662:\n" \ + ".section .altinstructions,\"a\"\n" \ + " .align 4\n" \ + " .long 661b\n" /* label */ \ + " .long 663f\n" /* new instruction */ \ + " .byte %c0\n" /* feature bit */ \ + " .byte 662b-661b\n" /* sourcelen */ \ + " .byte 664f-663f\n" /* replacementlen */ \ + ".previous\n" \ + ".section .altinstr_replacement,\"ax\"\n" \ + "663:\n\t" newinstr "\n664:\n" /* replacement */ \ + ".previous" :: "i" (feature) : "memory") + +/* + * Alternative inline assembly with input. + * + * Pecularities: + * No memory clobber here. + * Argument numbers start with 1. + * Best is to use constraints that are fixed size (like (%1) ... "r") + * If you use variable sized constraints like "m" or "g" in the + * replacement maake sure to pad to the worst case length. + */ +#define alternative_input(oldinstr, newinstr, feature, input...) \ + asm volatile ("661:\n\t" oldinstr "\n662:\n" \ + ".section .altinstructions,\"a\"\n" \ + " .align 4\n" \ + " .long 661b\n" /* label */ \ + " .long 663f\n" /* new instruction */ \ + " .byte %c0\n" /* feature bit */ \ + " .byte 662b-661b\n" /* sourcelen */ \ + " .byte 664f-663f\n" /* replacementlen */ \ + ".previous\n" \ + ".section .altinstr_replacement,\"ax\"\n" \ + "663:\n\t" newinstr "\n664:\n" /* replacement */ \ + ".previous" :: "i" (feature), ##input) + +/* + * Force strict CPU ordering. + * And yes, this is required on UP too when we're talking + * to devices. + * + * For now, "wmb()" doesn't actually do anything, as all + * Intel CPU's follow what Intel calls a *Processor Order*, + * in which all writes are seen in the program order even + * outside the CPU. + * + * I expect future Intel CPU's to have a weaker ordering, + * but I'd also expect them to finally get their act together + * and add some real memory barriers if so. + * + * Some non intel clones support out of order store. wmb() ceases to be a + * nop for these. + */ + + +/* + * Actually only lfence would be needed for mb() because all stores done + * by the kernel should be already ordered. But keep a full barrier for now. + */ + +#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2) +#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2) + +/** + * read_barrier_depends - Flush all pending reads that subsequents reads + * depend on. + * + * No data-dependent reads from memory-like regions are ever reordered + * over this barrier. All reads preceding this primitive are guaranteed + * to access memory (but not necessarily other CPUs' caches) before any + * reads following this primitive that depend on the data return by + * any of the preceding reads. This primitive is much lighter weight than + * rmb() on most CPUs, and is never heavier weight than is + * rmb(). + * + * These ordering constraints are respected by both the local CPU + * and the compiler. + * + * Ordering is not guaranteed by anything other than these primitives, + * not even by data dependencies. See the documentation for + * memory_barrier() for examples and URLs to more information. + * + * For example, the following code would force ordering (the initial + * value of "a" is zero, "b" is one, and "p" is "&a"): + * + * <programlisting> + * CPU 0 CPU 1 + * + * b = 2; + * memory_barrier(); + * p = &b; q = p; + * read_barrier_depends(); + * d = *q; + * </programlisting> + * + * because the read of "*q" depends on the read of "p" and these + * two reads are separated by a read_barrier_depends(). However, + * the following code, with the same initial values for "a" and "b": + * + * <programlisting> + * CPU 0 CPU 1 + * + * a = 2; + * memory_barrier(); + * b = 3; y = b; + * read_barrier_depends(); + * x = a; + * </programlisting> + * + * does not enforce ordering, since there is no data dependency between + * the read of "a" and the read of "b". Therefore, on some CPUs, such + * as Alpha, "y" could be set to 3 and "x" to 0. Use rmb() + * in cases like thiswhere there are no data dependencies. + **/ + +#define read_barrier_depends() do { } while(0) + +#ifdef CONFIG_X86_OOSTORE +/* Actually there are no OOO store capable CPUs for now that do SSE, + but make it already an possibility. */ +#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM) +#else +#define wmb() __asm__ __volatile__ ("": : :"memory") +#endif + +#ifdef CONFIG_SMP +#define smp_wmb() wmb() +#if defined(CONFIG_SMP_ALTERNATIVES) && !defined(MODULE) +#define smp_alt_mb(instr) \ +__asm__ __volatile__("6667:\nnop\nnop\nnop\nnop\nnop\nnop\n6668:\n" \ + ".section __smp_alternatives,\"a\"\n" \ + ".long 6667b\n" \ + ".long 6673f\n" \ + ".previous\n" \ + ".section __smp_replacements,\"a\"\n" \ + "6673:.byte 6668b-6667b\n" \ + ".byte 6670f-6669f\n" \ + ".byte 6671f-6670f\n" \ + ".byte 0\n" \ + ".byte %c0\n" \ + "6669:lock;addl $0,0(%%esp)\n" \ + "6670:" instr "\n" \ + "6671:\n" \ + ".previous\n" \ + : \ + : "i" (X86_FEATURE_XMM2) \ + : "memory") +#define smp_rmb() smp_alt_mb("lfence") +#define smp_mb() smp_alt_mb("mfence") +#define set_mb(var, value) do { \ +unsigned long __set_mb_temp; \ +__asm__ __volatile__("6667:movl %1, %0\n6668:\n" \ + ".section __smp_alternatives,\"a\"\n" \ + ".long 6667b\n" \ + ".long 6673f\n" \ + ".previous\n" \ + ".section __smp_replacements,\"a\"\n" \ + "6673: .byte 6668b-6667b\n" \ + ".byte 6670f-6669f\n" \ + ".byte 0\n" \ + ".byte 6671f-6670f\n" \ + ".byte -1\n" \ + "6669: xchg %1, %0\n" \ + "6670:movl %1, %0\n" \ + "6671:\n" \ + ".previous\n" \ + : "=m" (var), "=r" (__set_mb_temp) \ + : "1" (value) \ + : "memory"); } while (0) +#else +#define smp_rmb() rmb() +#define smp_mb() mb() +#define set_mb(var, value) do { xchg(&var, value); } while (0) +#endif +#define smp_read_barrier_depends() read_barrier_depends() +#else +#define smp_mb() barrier() +#define smp_rmb() barrier() +#define smp_wmb() barrier() +#define smp_read_barrier_depends() do { } while(0) +#define set_mb(var, value) do { var = value; barrier(); } while (0) +#endif + +#define set_wmb(var, value) do { var = value; wmb(); } while (0) + +/* interrupt control.. */ + +/* + * The use of 'barrier' in the following reflects their use as local-lock + * operations. Reentrancy must be prevented (e.g., __cli()) /before/ following + * critical operations are executed. All critical operations must complete + * /before/ reentrancy is permitted (e.g., __sti()). Alpha architecture also + * includes these barriers, for example. + */ + +#define __cli() \ +do { \ + vcpu_info_t *_vcpu; \ + preempt_disable(); \ + _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ + _vcpu->evtchn_upcall_mask = 1; \ + preempt_enable_no_resched(); \ + barrier(); \ +} while (0) + +#define __sti() \ +do { \ + vcpu_info_t *_vcpu; \ + barrier(); \ + preempt_disable(); \ + _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ + _vcpu->evtchn_upcall_mask = 0; \ + barrier(); /* unmask then check (avoid races) */ \ + if ( unlikely(_vcpu->evtchn_upcall_pending) ) \ + force_evtchn_callback(); \ + preempt_enable(); \ +} while (0) + +#define __save_flags(x) \ +do { \ + vcpu_info_t *_vcpu; \ + preempt_disable(); \ + _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ + (x) = _vcpu->evtchn_upcall_mask; \ + preempt_enable(); \ +} while (0) + +#define __restore_flags(x) \ +do { \ + vcpu_info_t *_vcpu; \ + barrier(); \ + preempt_disable(); \ + _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ + if ((_vcpu->evtchn_upcall_mask = (x)) == 0) { \ + barrier(); /* unmask then check (avoid races) */ \ + if ( unlikely(_vcpu->evtchn_upcall_pending) ) \ + force_evtchn_callback(); \ + preempt_enable(); \ + } else \ + preempt_enable_no_resched(); \ +} while (0) + +#define safe_halt() ((void)0) + +#define __save_and_cli(x) \ +do { \ + vcpu_info_t *_vcpu; \ + preempt_disable(); \ + _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ + (x) = _vcpu->evtchn_upcall_mask; \ + _vcpu->evtchn_upcall_mask = 1; \ + preempt_enable_no_resched(); \ + barrier(); \ +} while (0) + +#define local_irq_save(x) __save_and_cli(x) +#define local_irq_restore(x) __restore_flags(x) +#define local_save_flags(x) __save_flags(x) +#define local_irq_disable() __cli() +#define local_irq_enable() __sti() + +/* Cannot use preempt_enable() here as we would recurse in preempt_sched(). */ +#define irqs_disabled() \ +({ int ___x; \ + vcpu_info_t *_vcpu; \ + preempt_disable(); \ + _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ + ___x = (_vcpu->evtchn_upcall_mask != 0); \ + preempt_enable_no_resched(); \ + ___x; }) + +/* + * disable hlt during certain critical i/o operations + */ +#define HAVE_DISABLE_HLT +void disable_hlt(void); +void enable_hlt(void); + +extern int es7000_plat; +void cpu_idle_wait(void); + +extern unsigned long arch_align_stack(unsigned long sp); + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/tlbflush.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/tlbflush.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,102 @@ +#ifndef _I386_TLBFLUSH_H +#define _I386_TLBFLUSH_H + +#include <linux/config.h> +#include <linux/mm.h> +#include <asm/processor.h> + +#define __flush_tlb() xen_tlb_flush() +#define __flush_tlb_global() xen_tlb_flush() +#define __flush_tlb_all() xen_tlb_flush() + +extern unsigned long pgkern_mask; + +#define cpu_has_invlpg (boot_cpu_data.x86 > 3) + +#define __flush_tlb_single(addr) xen_invlpg(addr) + +#define __flush_tlb_one(addr) __flush_tlb_single(addr) + +/* + * TLB flushing: + * + * - flush_tlb() flushes the current mm struct TLBs + * - flush_tlb_all() flushes all processes TLBs + * - flush_tlb_mm(mm) flushes the specified mm context TLB's + * - flush_tlb_page(vma, vmaddr) flushes one page + * - flush_tlb_range(vma, start, end) flushes a range of pages + * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages + * - flush_tlb_pgtables(mm, start, end) flushes a range of page tables + * + * ..but the i386 has somewhat limited tlb flushing capabilities, + * and page-granular flushes are available only on i486 and up. + */ + +#ifndef CONFIG_SMP + +#define flush_tlb() __flush_tlb() +#define flush_tlb_all() __flush_tlb_all() +#define local_flush_tlb() __flush_tlb() + +static inline void flush_tlb_mm(struct mm_struct *mm) +{ + if (mm == current->active_mm) + __flush_tlb(); +} + +static inline void flush_tlb_page(struct vm_area_struct *vma, + unsigned long addr) +{ + if (vma->vm_mm == current->active_mm) + __flush_tlb_one(addr); +} + +static inline void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + if (vma->vm_mm == current->active_mm) + __flush_tlb(); +} + +#else + +#include <asm/smp.h> + +#define local_flush_tlb() \ + __flush_tlb() + +extern void flush_tlb_all(void); +extern void flush_tlb_current_task(void); +extern void flush_tlb_mm(struct mm_struct *); +extern void flush_tlb_page(struct vm_area_struct *, unsigned long); + +#define flush_tlb() flush_tlb_current_task() + +static inline void flush_tlb_range(struct vm_area_struct * vma, unsigned long start, unsigned long end) +{ + flush_tlb_mm(vma->vm_mm); +} + +#define TLBSTATE_OK 1 +#define TLBSTATE_LAZY 2 + +struct tlb_state +{ + struct mm_struct *active_mm; + int state; + char __cacheline_padding[L1_CACHE_BYTES-8]; +}; +DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate); + + +#endif + +#define flush_tlb_kernel_range(start, end) flush_tlb_all() + +static inline void flush_tlb_pgtables(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + /* i386 does not keep any page table caches in TLB */ +} + +#endif /* _I386_TLBFLUSH_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/vga.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/asm/vga.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,20 @@ +/* + * Access to VGA videoram + * + * (c) 1998 Martin Mares <mj@xxxxxx> + */ + +#ifndef _LINUX_ASM_VGA_H_ +#define _LINUX_ASM_VGA_H_ + +/* + * On the PC, we can just recalculate addresses and then + * access the videoram directly without any black magic. + */ + +#define VGA_MAP_MEM(x) (unsigned long)isa_bus_to_virt(x) + +#define vga_readb(x) (*(x)) +#define vga_writeb(x,y) (*(y) = (x)) + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/irq_vectors.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/irq_vectors.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,125 @@ +/* + * This file should contain #defines for all of the interrupt vector + * numbers used by this architecture. + * + * In addition, there are some standard defines: + * + * FIRST_EXTERNAL_VECTOR: + * The first free place for external interrupts + * + * SYSCALL_VECTOR: + * The IRQ vector a syscall makes the user to kernel transition + * under. + * + * TIMER_IRQ: + * The IRQ number the timer interrupt comes in at. + * + * NR_IRQS: + * The total number of interrupt vectors (including all the + * architecture specific interrupts) needed. + * + */ +#ifndef _ASM_IRQ_VECTORS_H +#define _ASM_IRQ_VECTORS_H + +/* + * IDT vectors usable for external interrupt sources start + * at 0x20: + */ +#define FIRST_EXTERNAL_VECTOR 0x20 + +#define SYSCALL_VECTOR 0x80 + +/* + * Vectors 0x20-0x2f are used for ISA interrupts. + */ + +#if 0 +/* + * Special IRQ vectors used by the SMP architecture, 0xf0-0xff + * + * some of the following vectors are 'rare', they are merged + * into a single vector (CALL_FUNCTION_VECTOR) to save vector space. + * TLB, reschedule and local APIC vectors are performance-critical. + * + * Vectors 0xf0-0xfa are free (reserved for future Linux use). + */ +#define SPURIOUS_APIC_VECTOR 0xff +#define ERROR_APIC_VECTOR 0xfe +#define INVALIDATE_TLB_VECTOR 0xfd +#define RESCHEDULE_VECTOR 0xfc +#define CALL_FUNCTION_VECTOR 0xfb + +#define THERMAL_APIC_VECTOR 0xf0 +/* + * Local APIC timer IRQ vector is on a different priority level, + * to work around the 'lost local interrupt if more than 2 IRQ + * sources per level' errata. + */ +#define LOCAL_TIMER_VECTOR 0xef +#endif + +#define SPURIOUS_APIC_VECTOR 0xff +#define ERROR_APIC_VECTOR 0xfe + +/* + * First APIC vector available to drivers: (vectors 0x30-0xee) + * we start at 0x31 to spread out vectors evenly between priority + * levels. (0x80 is the syscall vector) + */ +#define FIRST_DEVICE_VECTOR 0x31 +#define FIRST_SYSTEM_VECTOR 0xef + +/* + * 16 8259A IRQ's, 208 potential APIC interrupt sources. + * Right now the APIC is mostly only used for SMP. + * 256 vectors is an architectural limit. (we can have + * more than 256 devices theoretically, but they will + * have to use shared interrupts) + * Since vectors 0x00-0x1f are used/reserved for the CPU, + * the usable vector space is 0x20-0xff (224 vectors) + */ + +#define RESCHEDULE_VECTOR 0 +#define CALL_FUNCTION_VECTOR 1 +#define NR_IPIS 2 + +/* + * The maximum number of vectors supported by i386 processors + * is limited to 256. For processors other than i386, NR_VECTORS + * should be changed accordingly. + */ +#define NR_VECTORS 256 + +#define FPU_IRQ 13 + +#define FIRST_VM86_IRQ 3 +#define LAST_VM86_IRQ 15 +#define invalid_vm86_irq(irq) ((irq) < 3 || (irq) > 15) + +/* + * The flat IRQ space is divided into two regions: + * 1. A one-to-one mapping of real physical IRQs. This space is only used + * if we have physical device-access privilege. This region is at the + * start of the IRQ space so that existing device drivers do not need + * to be modified to translate physical IRQ numbers into our IRQ space. + * 3. A dynamic mapping of inter-domain and Xen-sourced virtual IRQs. These + * are bound using the provided bind/unbind functions. + */ + +#define PIRQ_BASE 0 +#define NR_PIRQS 256 + +#define DYNIRQ_BASE (PIRQ_BASE + NR_PIRQS) +#define NR_DYNIRQS 256 + +#define NR_IRQS (NR_PIRQS + NR_DYNIRQS) +#define NR_IRQ_VECTORS NR_IRQS + +#define pirq_to_irq(_x) ((_x) + PIRQ_BASE) +#define irq_to_pirq(_x) ((_x) - PIRQ_BASE) + +#define dynirq_to_irq(_x) ((_x) + DYNIRQ_BASE) +#define irq_to_dynirq(_x) ((_x) - DYNIRQ_BASE) + +#endif /* _ASM_IRQ_VECTORS_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/mach_traps.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/mach_traps.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,33 @@ +/* + * include/asm-xen/asm-i386/mach-xen/mach_traps.h + * + * Machine specific NMI handling for Xen + */ +#ifndef _MACH_TRAPS_H +#define _MACH_TRAPS_H + +#include <linux/bitops.h> +#include <xen/interface/nmi.h> + +static inline void clear_mem_error(unsigned char reason) {} +static inline void clear_io_check_error(unsigned char reason) {} + +static inline unsigned char get_nmi_reason(void) +{ + shared_info_t *s = HYPERVISOR_shared_info; + unsigned char reason = 0; + + /* construct a value which looks like it came from + * port 0x61. + */ + if (test_bit(_XEN_NMIREASON_io_error, &s->arch.nmi_reason)) + reason |= 0x40; + if (test_bit(_XEN_NMIREASON_parity_error, &s->arch.nmi_reason)) + reason |= 0x80; + + return reason; +} + +static inline void reassert_nmi(void) {} + +#endif /* !_MACH_TRAPS_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/setup_arch_post.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/setup_arch_post.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,43 @@ +/** + * machine_specific_memory_setup - Hook for machine specific memory setup. + * + * Description: + * This is included late in kernel/setup.c so that it can make + * use of all of the static functions. + **/ + +static char * __init machine_specific_memory_setup(void) +{ + unsigned long max_pfn = xen_start_info->nr_pages; + + e820.nr_map = 0; + add_memory_region(0, PFN_PHYS(max_pfn), E820_RAM); + + return "Xen"; +} + +void __init machine_specific_modify_cpu_capabilities(struct cpuinfo_x86 *c) +{ + clear_bit(X86_FEATURE_VME, c->x86_capability); + clear_bit(X86_FEATURE_DE, c->x86_capability); + clear_bit(X86_FEATURE_PSE, c->x86_capability); + clear_bit(X86_FEATURE_PGE, c->x86_capability); + clear_bit(X86_FEATURE_SEP, c->x86_capability); + if (!(xen_start_info->flags & SIF_PRIVILEGED)) + clear_bit(X86_FEATURE_MTRR, c->x86_capability); +} + +extern void hypervisor_callback(void); +extern void failsafe_callback(void); +extern void nmi(void); + +static void __init machine_specific_arch_setup(void) +{ + HYPERVISOR_set_callbacks( + __KERNEL_CS, (unsigned long)hypervisor_callback, + __KERNEL_CS, (unsigned long)failsafe_callback); + + HYPERVISOR_nmi_op(XENNMI_register_callback, (unsigned long)&nmi); + + machine_specific_modify_cpu_capabilities(&boot_cpu_data); +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/mach-xen/setup_arch_pre.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/mach-xen/setup_arch_pre.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,5 @@ +/* Hook to call BIOS initialisation function */ + +#define ARCH_SETUP machine_specific_arch_setup(); + +static void __init machine_specific_arch_setup(void); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/rwsem.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/rwsem.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,289 @@ +/* rwsem.h: R/W semaphores implemented using XADD/CMPXCHG for i486+ + * + * Written by David Howells (dhowells@xxxxxxxxxx). + * + * Derived from asm-i386/semaphore.h + * + * + * The MSW of the count is the negated number of active writers and waiting + * lockers, and the LSW is the total number of active locks + * + * The lock count is initialized to 0 (no active and no waiting lockers). + * + * When a writer subtracts WRITE_BIAS, it'll get 0xffff0001 for the case of an + * uncontended lock. This can be determined because XADD returns the old value. + * Readers increment by 1 and see a positive value when uncontended, negative + * if there are writers (and maybe) readers waiting (in which case it goes to + * sleep). + * + * The value of WAITING_BIAS supports up to 32766 waiting processes. This can + * be extended to 65534 by manually checking the whole MSW rather than relying + * on the S flag. + * + * The value of ACTIVE_BIAS supports up to 65535 active processes. + * + * This should be totally fair - if anything is waiting, a process that wants a + * lock will go to the back of the queue. When the currently active lock is + * released, if there's a writer at the front of the queue, then that and only + * that will be woken up; if there's a bunch of consequtive readers at the + * front, then they'll all be woken up, but no other readers will be. + */ + +#ifndef _I386_RWSEM_H +#define _I386_RWSEM_H + +#ifndef _LINUX_RWSEM_H +#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead" +#endif + +#ifdef __KERNEL__ + +#include <linux/list.h> +#include <linux/spinlock.h> +#include <asm/smp_alt.h> + +struct rwsem_waiter; + +extern struct rw_semaphore *FASTCALL(rwsem_down_read_failed(struct rw_semaphore *sem)); +extern struct rw_semaphore *FASTCALL(rwsem_down_write_failed(struct rw_semaphore *sem)); +extern struct rw_semaphore *FASTCALL(rwsem_wake(struct rw_semaphore *)); +extern struct rw_semaphore *FASTCALL(rwsem_downgrade_wake(struct rw_semaphore *sem)); + +/* + * the semaphore definition + */ +struct rw_semaphore { + signed long count; +#define RWSEM_UNLOCKED_VALUE 0x00000000 +#define RWSEM_ACTIVE_BIAS 0x00000001 +#define RWSEM_ACTIVE_MASK 0x0000ffff +#define RWSEM_WAITING_BIAS (-0x00010000) +#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS +#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) + spinlock_t wait_lock; + struct list_head wait_list; +#if RWSEM_DEBUG + int debug; +#endif +}; + +/* + * initialisation + */ +#if RWSEM_DEBUG +#define __RWSEM_DEBUG_INIT , 0 +#else +#define __RWSEM_DEBUG_INIT /* */ +#endif + +#define __RWSEM_INITIALIZER(name) \ +{ RWSEM_UNLOCKED_VALUE, SPIN_LOCK_UNLOCKED, LIST_HEAD_INIT((name).wait_list) \ + __RWSEM_DEBUG_INIT } + +#define DECLARE_RWSEM(name) \ + struct rw_semaphore name = __RWSEM_INITIALIZER(name) + +static inline void init_rwsem(struct rw_semaphore *sem) +{ + sem->count = RWSEM_UNLOCKED_VALUE; + spin_lock_init(&sem->wait_lock); + INIT_LIST_HEAD(&sem->wait_list); +#if RWSEM_DEBUG + sem->debug = 0; +#endif +} + +/* + * lock for reading + */ +static inline void __down_read(struct rw_semaphore *sem) +{ + __asm__ __volatile__( + "# beginning down_read\n\t" +LOCK " incl (%%eax)\n\t" /* adds 0x00000001, returns the old value */ + " js 2f\n\t" /* jump if we weren't granted the lock */ + "1:\n\t" + LOCK_SECTION_START("") + "2:\n\t" + " pushl %%ecx\n\t" + " pushl %%edx\n\t" + " call rwsem_down_read_failed\n\t" + " popl %%edx\n\t" + " popl %%ecx\n\t" + " jmp 1b\n" + LOCK_SECTION_END + "# ending down_read\n\t" + : "=m"(sem->count) + : "a"(sem), "m"(sem->count) + : "memory", "cc"); +} + +/* + * trylock for reading -- returns 1 if successful, 0 if contention + */ +static inline int __down_read_trylock(struct rw_semaphore *sem) +{ + __s32 result, tmp; + __asm__ __volatile__( + "# beginning __down_read_trylock\n\t" + " movl %0,%1\n\t" + "1:\n\t" + " movl %1,%2\n\t" + " addl %3,%2\n\t" + " jle 2f\n\t" +LOCK " cmpxchgl %2,%0\n\t" + " jnz 1b\n\t" + "2:\n\t" + "# ending __down_read_trylock\n\t" + : "+m"(sem->count), "=&a"(result), "=&r"(tmp) + : "i"(RWSEM_ACTIVE_READ_BIAS) + : "memory", "cc"); + return result>=0 ? 1 : 0; +} + +/* + * lock for writing + */ +static inline void __down_write(struct rw_semaphore *sem) +{ + int tmp; + + tmp = RWSEM_ACTIVE_WRITE_BIAS; + __asm__ __volatile__( + "# beginning down_write\n\t" +LOCK " xadd %%edx,(%%eax)\n\t" /* subtract 0x0000ffff, returns the old value */ + " testl %%edx,%%edx\n\t" /* was the count 0 before? */ + " jnz 2f\n\t" /* jump if we weren't granted the lock */ + "1:\n\t" + LOCK_SECTION_START("") + "2:\n\t" + " pushl %%ecx\n\t" + " call rwsem_down_write_failed\n\t" + " popl %%ecx\n\t" + " jmp 1b\n" + LOCK_SECTION_END + "# ending down_write" + : "=m"(sem->count), "=d"(tmp) + : "a"(sem), "1"(tmp), "m"(sem->count) + : "memory", "cc"); +} + +/* + * trylock for writing -- returns 1 if successful, 0 if contention + */ +static inline int __down_write_trylock(struct rw_semaphore *sem) +{ + signed long ret = cmpxchg(&sem->count, + RWSEM_UNLOCKED_VALUE, + RWSEM_ACTIVE_WRITE_BIAS); + if (ret == RWSEM_UNLOCKED_VALUE) + return 1; + return 0; +} + +/* + * unlock after reading + */ +static inline void __up_read(struct rw_semaphore *sem) +{ + __s32 tmp = -RWSEM_ACTIVE_READ_BIAS; + __asm__ __volatile__( + "# beginning __up_read\n\t" +LOCK " xadd %%edx,(%%eax)\n\t" /* subtracts 1, returns the old value */ + " js 2f\n\t" /* jump if the lock is being waited upon */ + "1:\n\t" + LOCK_SECTION_START("") + "2:\n\t" + " decw %%dx\n\t" /* do nothing if still outstanding active readers */ + " jnz 1b\n\t" + " pushl %%ecx\n\t" + " call rwsem_wake\n\t" + " popl %%ecx\n\t" + " jmp 1b\n" + LOCK_SECTION_END + "# ending __up_read\n" + : "=m"(sem->count), "=d"(tmp) + : "a"(sem), "1"(tmp), "m"(sem->count) + : "memory", "cc"); +} + +/* + * unlock after writing + */ +static inline void __up_write(struct rw_semaphore *sem) +{ + __asm__ __volatile__( + "# beginning __up_write\n\t" + " movl %2,%%edx\n\t" +LOCK " xaddl %%edx,(%%eax)\n\t" /* tries to transition 0xffff0001 -> 0x00000000 */ + " jnz 2f\n\t" /* jump if the lock is being waited upon */ + "1:\n\t" + LOCK_SECTION_START("") + "2:\n\t" + " decw %%dx\n\t" /* did the active count reduce to 0? */ + " jnz 1b\n\t" /* jump back if not */ + " pushl %%ecx\n\t" + " call rwsem_wake\n\t" + " popl %%ecx\n\t" + " jmp 1b\n" + LOCK_SECTION_END + "# ending __up_write\n" + : "=m"(sem->count) + : "a"(sem), "i"(-RWSEM_ACTIVE_WRITE_BIAS), "m"(sem->count) + : "memory", "cc", "edx"); +} + +/* + * downgrade write lock to read lock + */ +static inline void __downgrade_write(struct rw_semaphore *sem) +{ + __asm__ __volatile__( + "# beginning __downgrade_write\n\t" +LOCK " addl %2,(%%eax)\n\t" /* transitions 0xZZZZ0001 -> 0xYYYY0001 */ + " js 2f\n\t" /* jump if the lock is being waited upon */ + "1:\n\t" + LOCK_SECTION_START("") + "2:\n\t" + " pushl %%ecx\n\t" + " pushl %%edx\n\t" + " call rwsem_downgrade_wake\n\t" + " popl %%edx\n\t" + " popl %%ecx\n\t" + " jmp 1b\n" + LOCK_SECTION_END + "# ending __downgrade_write\n" + : "=m"(sem->count) + : "a"(sem), "i"(-RWSEM_WAITING_BIAS), "m"(sem->count) + : "memory", "cc"); +} + +/* + * implement atomic add functionality + */ +static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem) +{ + __asm__ __volatile__( +LOCK "addl %1,%0" + : "=m"(sem->count) + : "ir"(delta), "m"(sem->count)); +} + +/* + * implement exchange and add functionality + */ +static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem) +{ + int tmp = delta; + + __asm__ __volatile__( +LOCK "xadd %0,(%2)" + : "+r"(tmp), "=m"(sem->count) + : "r"(sem), "m"(sem->count) + : "memory"); + + return tmp+delta; +} + +#endif /* __KERNEL__ */ +#endif /* _I386_RWSEM_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/smp_alt.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/smp_alt.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,32 @@ +#ifndef __ASM_SMP_ALT_H__ +#define __ASM_SMP_ALT_H__ + +#include <linux/config.h> + +#ifdef CONFIG_SMP +#if defined(CONFIG_SMP_ALTERNATIVES) && !defined(MODULE) +#define LOCK \ + "6677: nop\n" \ + ".section __smp_alternatives,\"a\"\n" \ + ".long 6677b\n" \ + ".long 6678f\n" \ + ".previous\n" \ + ".section __smp_replacements,\"a\"\n" \ + "6678: .byte 1\n" \ + ".byte 1\n" \ + ".byte 0\n" \ + ".byte 1\n" \ + ".byte -1\n" \ + "lock\n" \ + "nop\n" \ + ".previous\n" +void prepare_for_smp(void); +void unprepare_for_smp(void); +#else +#define LOCK "lock ; " +#endif +#else +#define LOCK "" +#endif + +#endif /* __ASM_SMP_ALT_H__ */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/spinlock.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/spinlock.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,277 @@ +#ifndef __ASM_SPINLOCK_H +#define __ASM_SPINLOCK_H + +#include <asm/atomic.h> +#include <asm/rwlock.h> +#include <asm/page.h> +#include <linux/config.h> +#include <linux/compiler.h> +#include <asm/smp_alt.h> + +asmlinkage int printk(const char * fmt, ...) + __attribute__ ((format (printf, 1, 2))); + +/* + * Your basic SMP spinlocks, allowing only a single CPU anywhere + */ + +typedef struct { + volatile unsigned int slock; +#ifdef CONFIG_DEBUG_SPINLOCK + unsigned magic; +#endif +#ifdef CONFIG_PREEMPT + unsigned int break_lock; +#endif +} spinlock_t; + +#define SPINLOCK_MAGIC 0xdead4ead + +#ifdef CONFIG_DEBUG_SPINLOCK +#define SPINLOCK_MAGIC_INIT , SPINLOCK_MAGIC +#else +#define SPINLOCK_MAGIC_INIT /* */ +#endif + +#define SPIN_LOCK_UNLOCKED (spinlock_t) { 1 SPINLOCK_MAGIC_INIT } + +#define spin_lock_init(x) do { *(x) = SPIN_LOCK_UNLOCKED; } while(0) + +/* + * Simple spin lock operations. There are two variants, one clears IRQ's + * on the local processor, one does not. + * + * We make no fairness assumptions. They have a cost. + */ + +#define spin_is_locked(x) (*(volatile signed char *)(&(x)->slock) <= 0) +#define spin_unlock_wait(x) do { barrier(); } while(spin_is_locked(x)) + +#define spin_lock_string \ + "1:\n" \ + LOCK \ + "decb %0\n\t" \ + "jns 3f\n" \ + "2:\t" \ + "rep;nop\n\t" \ + "cmpb $0,%0\n\t" \ + "jle 2b\n\t" \ + "jmp 1b\n" \ + "3:\n\t" + +#define spin_lock_string_flags \ + "1:\n" \ + LOCK \ + "decb %0\n\t" \ + "jns 4f\n\t" \ + "2:\t" \ + "testl $0x200, %1\n\t" \ + "jz 3f\n\t" \ + "sti\n\t" \ + "3:\t" \ + "rep;nop\n\t" \ + "cmpb $0, %0\n\t" \ + "jle 3b\n\t" \ + "cli\n\t" \ + "jmp 1b\n" \ + "4:\n\t" + +/* + * This works. Despite all the confusion. + * (except on PPro SMP or if we are using OOSTORE) + * (PPro errata 66, 92) + */ + +#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE) + +#define spin_unlock_string \ + "movb $1,%0" \ + :"=m" (lock->slock) : : "memory" + + +static inline void _raw_spin_unlock(spinlock_t *lock) +{ +#ifdef CONFIG_DEBUG_SPINLOCK + BUG_ON(lock->magic != SPINLOCK_MAGIC); + BUG_ON(!spin_is_locked(lock)); +#endif + __asm__ __volatile__( + spin_unlock_string + ); +} + +#else + +#define spin_unlock_string \ + "xchgb %b0, %1" \ + :"=q" (oldval), "=m" (lock->slock) \ + :"0" (oldval) : "memory" + +static inline void _raw_spin_unlock(spinlock_t *lock) +{ + char oldval = 1; +#ifdef CONFIG_DEBUG_SPINLOCK + BUG_ON(lock->magic != SPINLOCK_MAGIC); + BUG_ON(!spin_is_locked(lock)); +#endif + __asm__ __volatile__( + spin_unlock_string + ); +} + +#endif + +static inline int _raw_spin_trylock(spinlock_t *lock) +{ + char oldval; +#ifdef CONFIG_SMP_ALTERNATIVES + __asm__ __volatile__( + "1:movb %1,%b0\n" + "movb $0,%1\n" + "2:" + ".section __smp_alternatives,\"a\"\n" + ".long 1b\n" + ".long 3f\n" + ".previous\n" + ".section __smp_replacements,\"a\"\n" + "3: .byte 2b - 1b\n" + ".byte 5f-4f\n" + ".byte 0\n" + ".byte 6f-5f\n" + ".byte -1\n" + "4: xchgb %b0,%1\n" + "5: movb %1,%b0\n" + "movb $0,%1\n" + "6:\n" + ".previous\n" + :"=q" (oldval), "=m" (lock->slock) + :"0" (0) : "memory"); +#else + __asm__ __volatile__( + "xchgb %b0,%1\n" + :"=q" (oldval), "=m" (lock->slock) + :"0" (0) : "memory"); +#endif + return oldval > 0; +} + +static inline void _raw_spin_lock(spinlock_t *lock) +{ +#ifdef CONFIG_DEBUG_SPINLOCK + if (unlikely(lock->magic != SPINLOCK_MAGIC)) { + printk("eip: %p\n", __builtin_return_address(0)); + BUG(); + } +#endif + __asm__ __volatile__( + spin_lock_string + :"=m" (lock->slock) : : "memory"); +} + +static inline void _raw_spin_lock_flags (spinlock_t *lock, unsigned long flags) +{ +#ifdef CONFIG_DEBUG_SPINLOCK + if (unlikely(lock->magic != SPINLOCK_MAGIC)) { + printk("eip: %p\n", __builtin_return_address(0)); + BUG(); + } +#endif + __asm__ __volatile__( + spin_lock_string_flags + :"=m" (lock->slock) : "r" (flags) : "memory"); +} + +/* + * Read-write spinlocks, allowing multiple readers + * but only one writer. + * + * NOTE! it is quite common to have readers in interrupts + * but no interrupt writers. For those circumstances we + * can "mix" irq-safe locks - any writer needs to get a + * irq-safe write-lock, but readers can get non-irqsafe + * read-locks. + */ +typedef struct { + volatile unsigned int lock; +#ifdef CONFIG_DEBUG_SPINLOCK + unsigned magic; +#endif +#ifdef CONFIG_PREEMPT + unsigned int break_lock; +#endif +} rwlock_t; + +#define RWLOCK_MAGIC 0xdeaf1eed + +#ifdef CONFIG_DEBUG_SPINLOCK +#define RWLOCK_MAGIC_INIT , RWLOCK_MAGIC +#else +#define RWLOCK_MAGIC_INIT /* */ +#endif + +#define RW_LOCK_UNLOCKED (rwlock_t) { RW_LOCK_BIAS RWLOCK_MAGIC_INIT } + +#define rwlock_init(x) do { *(x) = RW_LOCK_UNLOCKED; } while(0) + +/** + * read_can_lock - would read_trylock() succeed? + * @lock: the rwlock in question. + */ +#define read_can_lock(x) ((int)(x)->lock > 0) + +/** + * write_can_lock - would write_trylock() succeed? + * @lock: the rwlock in question. + */ +#define write_can_lock(x) ((x)->lock == RW_LOCK_BIAS) + +/* + * On x86, we implement read-write locks as a 32-bit counter + * with the high bit (sign) being the "contended" bit. + * + * The inline assembly is non-obvious. Think about it. + * + * Changed to use the same technique as rw semaphores. See + * semaphore.h for details. -ben + */ +/* the spinlock helpers are in arch/i386/kernel/semaphore.c */ + +static inline void _raw_read_lock(rwlock_t *rw) +{ +#ifdef CONFIG_DEBUG_SPINLOCK + BUG_ON(rw->magic != RWLOCK_MAGIC); +#endif + __build_read_lock(rw, "__read_lock_failed"); +} + +static inline void _raw_write_lock(rwlock_t *rw) +{ +#ifdef CONFIG_DEBUG_SPINLOCK + BUG_ON(rw->magic != RWLOCK_MAGIC); +#endif + __build_write_lock(rw, "__write_lock_failed"); +} + +#define _raw_read_unlock(rw) asm volatile(LOCK "incl %0" :"=m" ((rw)->lock) : : "memory") +#define _raw_write_unlock(rw) asm volatile(LOCK "addl $" RW_LOCK_BIAS_STR ",%0":"=m" ((rw)->lock) : : "memory") + +static inline int _raw_read_trylock(rwlock_t *lock) +{ + atomic_t *count = (atomic_t *)lock; + atomic_dec(count); + if (atomic_read(count) >= 0) + return 1; + atomic_inc(count); + return 0; +} + +static inline int _raw_write_trylock(rwlock_t *lock) +{ + atomic_t *count = (atomic_t *)lock; + if (atomic_sub_and_test(RW_LOCK_BIAS, count)) + return 1; + atomic_add(RW_LOCK_BIAS, count); + return 0; +} + +#endif /* __ASM_SPINLOCK_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-i386/system.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-i386/system.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,517 @@ +#ifndef __ASM_SYSTEM_H +#define __ASM_SYSTEM_H + +#include <linux/config.h> +#include <linux/kernel.h> +#include <asm/segment.h> +#include <asm/cpufeature.h> +#include <asm/smp_alt.h> + +#ifdef __KERNEL__ + +struct task_struct; /* one of the stranger aspects of C forward declarations.. */ +extern struct task_struct * FASTCALL(__switch_to(struct task_struct *prev, struct task_struct *next)); + +#define switch_to(prev,next,last) do { \ + unsigned long esi,edi; \ + asm volatile("pushfl\n\t" \ + "pushl %%ebp\n\t" \ + "movl %%esp,%0\n\t" /* save ESP */ \ + "movl %5,%%esp\n\t" /* restore ESP */ \ + "movl $1f,%1\n\t" /* save EIP */ \ + "pushl %6\n\t" /* restore EIP */ \ + "jmp __switch_to\n" \ + "1:\t" \ + "popl %%ebp\n\t" \ + "popfl" \ + :"=m" (prev->thread.esp),"=m" (prev->thread.eip), \ + "=a" (last),"=S" (esi),"=D" (edi) \ + :"m" (next->thread.esp),"m" (next->thread.eip), \ + "2" (prev), "d" (next)); \ +} while (0) + +#define _set_base(addr,base) do { unsigned long __pr; \ +__asm__ __volatile__ ("movw %%dx,%1\n\t" \ + "rorl $16,%%edx\n\t" \ + "movb %%dl,%2\n\t" \ + "movb %%dh,%3" \ + :"=&d" (__pr) \ + :"m" (*((addr)+2)), \ + "m" (*((addr)+4)), \ + "m" (*((addr)+7)), \ + "0" (base) \ + ); } while(0) + +#define _set_limit(addr,limit) do { unsigned long __lr; \ +__asm__ __volatile__ ("movw %%dx,%1\n\t" \ + "rorl $16,%%edx\n\t" \ + "movb %2,%%dh\n\t" \ + "andb $0xf0,%%dh\n\t" \ + "orb %%dh,%%dl\n\t" \ + "movb %%dl,%2" \ + :"=&d" (__lr) \ + :"m" (*(addr)), \ + "m" (*((addr)+6)), \ + "0" (limit) \ + ); } while(0) + +#define set_base(ldt,base) _set_base( ((char *)&(ldt)) , (base) ) +#define set_limit(ldt,limit) _set_limit( ((char *)&(ldt)) , ((limit)-1)>>12 ) + +static inline unsigned long _get_base(char * addr) +{ + unsigned long __base; + __asm__("movb %3,%%dh\n\t" + "movb %2,%%dl\n\t" + "shll $16,%%edx\n\t" + "movw %1,%%dx" + :"=&d" (__base) + :"m" (*((addr)+2)), + "m" (*((addr)+4)), + "m" (*((addr)+7))); + return __base; +} + +#define get_base(ldt) _get_base( ((char *)&(ldt)) ) + +/* + * Load a segment. Fall back on loading the zero + * segment if something goes wrong.. + */ +#define loadsegment(seg,value) \ + asm volatile("\n" \ + "1:\t" \ + "mov %0,%%" #seg "\n" \ + "2:\n" \ + ".section .fixup,\"ax\"\n" \ + "3:\t" \ + "pushl $0\n\t" \ + "popl %%" #seg "\n\t" \ + "jmp 2b\n" \ + ".previous\n" \ + ".section __ex_table,\"a\"\n\t" \ + ".align 4\n\t" \ + ".long 1b,3b\n" \ + ".previous" \ + : :"m" (value)) + +/* + * Save a segment register away + */ +#define savesegment(seg, value) \ + asm volatile("mov %%" #seg ",%0":"=m" (value)) + +/* + * Clear and set 'TS' bit respectively + */ +#define clts() __asm__ __volatile__ ("clts") +#define read_cr0() ({ \ + unsigned int __dummy; \ + __asm__( \ + "movl %%cr0,%0\n\t" \ + :"=r" (__dummy)); \ + __dummy; \ +}) +#define write_cr0(x) \ + __asm__("movl %0,%%cr0": :"r" (x)); + +#define read_cr4() ({ \ + unsigned int __dummy; \ + __asm__( \ + "movl %%cr4,%0\n\t" \ + :"=r" (__dummy)); \ + __dummy; \ +}) +#define write_cr4(x) \ + __asm__("movl %0,%%cr4": :"r" (x)); +#define stts() write_cr0(8 | read_cr0()) + +#endif /* __KERNEL__ */ + +#define wbinvd() \ + __asm__ __volatile__ ("wbinvd": : :"memory"); + +static inline unsigned long get_limit(unsigned long segment) +{ + unsigned long __limit; + __asm__("lsll %1,%0" + :"=r" (__limit):"r" (segment)); + return __limit+1; +} + +#define nop() __asm__ __volatile__ ("nop") + +#define xchg(ptr,v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v),(ptr),sizeof(*(ptr)))) + +#define tas(ptr) (xchg((ptr),1)) + +struct __xchg_dummy { unsigned long a[100]; }; +#define __xg(x) ((struct __xchg_dummy *)(x)) + + +/* + * The semantics of XCHGCMP8B are a bit strange, this is why + * there is a loop and the loading of %%eax and %%edx has to + * be inside. This inlines well in most cases, the cached + * cost is around ~38 cycles. (in the future we might want + * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that + * might have an implicit FPU-save as a cost, so it's not + * clear which path to go.) + * + * cmpxchg8b must be used with the lock prefix here to allow + * the instruction to be executed atomically, see page 3-102 + * of the instruction set reference 24319102.pdf. We need + * the reader side to see the coherent 64bit value. + */ +static inline void __set_64bit (unsigned long long * ptr, + unsigned int low, unsigned int high) +{ + __asm__ __volatile__ ( + "\n1:\t" + "movl (%0), %%eax\n\t" + "movl 4(%0), %%edx\n\t" + "lock cmpxchg8b (%0)\n\t" + "jnz 1b" + : /* no outputs */ + : "D"(ptr), + "b"(low), + "c"(high) + : "ax","dx","memory"); +} + +static inline void __set_64bit_constant (unsigned long long *ptr, + unsigned long long value) +{ + __set_64bit(ptr,(unsigned int)(value), (unsigned int)((value)>>32ULL)); +} +#define ll_low(x) *(((unsigned int*)&(x))+0) +#define ll_high(x) *(((unsigned int*)&(x))+1) + +static inline void __set_64bit_var (unsigned long long *ptr, + unsigned long long value) +{ + __set_64bit(ptr,ll_low(value), ll_high(value)); +} + +#define set_64bit(ptr,value) \ +(__builtin_constant_p(value) ? \ + __set_64bit_constant(ptr, value) : \ + __set_64bit_var(ptr, value) ) + +#define _set_64bit(ptr,value) \ +(__builtin_constant_p(value) ? \ + __set_64bit(ptr, (unsigned int)(value), (unsigned int)((value)>>32ULL) ) : \ + __set_64bit(ptr, ll_low(value), ll_high(value)) ) + +/* + * Note: no "lock" prefix even on SMP: xchg always implies lock anyway + * Note 2: xchg has side effect, so that attribute volatile is necessary, + * but generally the primitive is invalid, *ptr is output argument. --ANK + */ +static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size) +{ + switch (size) { + case 1: + __asm__ __volatile__("xchgb %b0,%1" + :"=q" (x) + :"m" (*__xg(ptr)), "0" (x) + :"memory"); + break; + case 2: + __asm__ __volatile__("xchgw %w0,%1" + :"=r" (x) + :"m" (*__xg(ptr)), "0" (x) + :"memory"); + break; + case 4: + __asm__ __volatile__("xchgl %0,%1" + :"=r" (x) + :"m" (*__xg(ptr)), "0" (x) + :"memory"); + break; + } + return x; +} + +/* + * Atomic compare and exchange. Compare OLD with MEM, if identical, + * store NEW in MEM. Return the initial value in MEM. Success is + * indicated by comparing RETURN with OLD. + */ + +#ifdef CONFIG_X86_CMPXCHG +#define __HAVE_ARCH_CMPXCHG 1 +#endif + +static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, + unsigned long new, int size) +{ + unsigned long prev; + switch (size) { + case 1: + __asm__ __volatile__(LOCK "cmpxchgb %b1,%2" + : "=a"(prev) + : "q"(new), "m"(*__xg(ptr)), "0"(old) + : "memory"); + return prev; + case 2: + __asm__ __volatile__(LOCK "cmpxchgw %w1,%2" + : "=a"(prev) + : "q"(new), "m"(*__xg(ptr)), "0"(old) + : "memory"); + return prev; + case 4: + __asm__ __volatile__(LOCK "cmpxchgl %1,%2" + : "=a"(prev) + : "q"(new), "m"(*__xg(ptr)), "0"(old) + : "memory"); + return prev; + } + return old; +} + +#define cmpxchg(ptr,o,n)\ + ((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\ + (unsigned long)(n),sizeof(*(ptr)))) + +#ifdef __KERNEL__ +struct alt_instr { + __u8 *instr; /* original instruction */ + __u8 *replacement; + __u8 cpuid; /* cpuid bit set for replacement */ + __u8 instrlen; /* length of original instruction */ + __u8 replacementlen; /* length of new instruction, <= instrlen */ + __u8 pad; +}; +#endif + +/* + * Alternative instructions for different CPU types or capabilities. + * + * This allows to use optimized instructions even on generic binary + * kernels. + * + * length of oldinstr must be longer or equal the length of newinstr + * It can be padded with nops as needed. + * + * For non barrier like inlines please define new variants + * without volatile and memory clobber. + */ +#define alternative(oldinstr, newinstr, feature) \ + asm volatile ("661:\n\t" oldinstr "\n662:\n" \ + ".section .altinstructions,\"a\"\n" \ + " .align 4\n" \ + " .long 661b\n" /* label */ \ + " .long 663f\n" /* new instruction */ \ + " .byte %c0\n" /* feature bit */ \ + " .byte 662b-661b\n" /* sourcelen */ \ + " .byte 664f-663f\n" /* replacementlen */ \ + ".previous\n" \ + ".section .altinstr_replacement,\"ax\"\n" \ + "663:\n\t" newinstr "\n664:\n" /* replacement */ \ + ".previous" :: "i" (feature) : "memory") + +/* + * Alternative inline assembly with input. + * + * Pecularities: + * No memory clobber here. + * Argument numbers start with 1. + * Best is to use constraints that are fixed size (like (%1) ... "r") + * If you use variable sized constraints like "m" or "g" in the + * replacement maake sure to pad to the worst case length. + */ +#define alternative_input(oldinstr, newinstr, feature, input...) \ + asm volatile ("661:\n\t" oldinstr "\n662:\n" \ + ".section .altinstructions,\"a\"\n" \ + " .align 4\n" \ + " .long 661b\n" /* label */ \ + " .long 663f\n" /* new instruction */ \ + " .byte %c0\n" /* feature bit */ \ + " .byte 662b-661b\n" /* sourcelen */ \ + " .byte 664f-663f\n" /* replacementlen */ \ + ".previous\n" \ + ".section .altinstr_replacement,\"ax\"\n" \ + "663:\n\t" newinstr "\n664:\n" /* replacement */ \ + ".previous" :: "i" (feature), ##input) + +/* + * Force strict CPU ordering. + * And yes, this is required on UP too when we're talking + * to devices. + * + * For now, "wmb()" doesn't actually do anything, as all + * Intel CPU's follow what Intel calls a *Processor Order*, + * in which all writes are seen in the program order even + * outside the CPU. + * + * I expect future Intel CPU's to have a weaker ordering, + * but I'd also expect them to finally get their act together + * and add some real memory barriers if so. + * + * Some non intel clones support out of order store. wmb() ceases to be a + * nop for these. + */ + + +/* + * Actually only lfence would be needed for mb() because all stores done + * by the kernel should be already ordered. But keep a full barrier for now. + */ + +#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2) +#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2) + +/** + * read_barrier_depends - Flush all pending reads that subsequents reads + * depend on. + * + * No data-dependent reads from memory-like regions are ever reordered + * over this barrier. All reads preceding this primitive are guaranteed + * to access memory (but not necessarily other CPUs' caches) before any + * reads following this primitive that depend on the data return by + * any of the preceding reads. This primitive is much lighter weight than + * rmb() on most CPUs, and is never heavier weight than is + * rmb(). + * + * These ordering constraints are respected by both the local CPU + * and the compiler. + * + * Ordering is not guaranteed by anything other than these primitives, + * not even by data dependencies. See the documentation for + * memory_barrier() for examples and URLs to more information. + * + * For example, the following code would force ordering (the initial + * value of "a" is zero, "b" is one, and "p" is "&a"): + * + * <programlisting> + * CPU 0 CPU 1 + * + * b = 2; + * memory_barrier(); + * p = &b; q = p; + * read_barrier_depends(); + * d = *q; + * </programlisting> + * + * because the read of "*q" depends on the read of "p" and these + * two reads are separated by a read_barrier_depends(). However, + * the following code, with the same initial values for "a" and "b": + * + * <programlisting> + * CPU 0 CPU 1 + * + * a = 2; + * memory_barrier(); + * b = 3; y = b; + * read_barrier_depends(); + * x = a; + * </programlisting> + * + * does not enforce ordering, since there is no data dependency between + * the read of "a" and the read of "b". Therefore, on some CPUs, such + * as Alpha, "y" could be set to 3 and "x" to 0. Use rmb() + * in cases like thiswhere there are no data dependencies. + **/ + +#define read_barrier_depends() do { } while(0) + +#ifdef CONFIG_X86_OOSTORE +/* Actually there are no OOO store capable CPUs for now that do SSE, + but make it already an possibility. */ +#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM) +#else +#define wmb() __asm__ __volatile__ ("": : :"memory") +#endif + +#ifdef CONFIG_SMP +#define smp_wmb() wmb() +#if defined(CONFIG_SMP_ALTERNATIVES) && !defined(MODULE) +#define smp_alt_mb(instr) \ +__asm__ __volatile__("6667:\nnop\nnop\nnop\nnop\nnop\nnop\n6668:\n" \ + ".section __smp_alternatives,\"a\"\n" \ + ".long 6667b\n" \ + ".long 6673f\n" \ + ".previous\n" \ + ".section __smp_replacements,\"a\"\n" \ + "6673:.byte 6668b-6667b\n" \ + ".byte 6670f-6669f\n" \ + ".byte 6671f-6670f\n" \ + ".byte 0\n" \ + ".byte %c0\n" \ + "6669:lock;addl $0,0(%%esp)\n" \ + "6670:" instr "\n" \ + "6671:\n" \ + ".previous\n" \ + : \ + : "i" (X86_FEATURE_XMM2) \ + : "memory") +#define smp_rmb() smp_alt_mb("lfence") +#define smp_mb() smp_alt_mb("mfence") +#define set_mb(var, value) do { \ +unsigned long __set_mb_temp; \ +__asm__ __volatile__("6667:movl %1, %0\n6668:\n" \ + ".section __smp_alternatives,\"a\"\n" \ + ".long 6667b\n" \ + ".long 6673f\n" \ + ".previous\n" \ + ".section __smp_replacements,\"a\"\n" \ + "6673: .byte 6668b-6667b\n" \ + ".byte 6670f-6669f\n" \ + ".byte 0\n" \ + ".byte 6671f-6670f\n" \ + ".byte -1\n" \ + "6669: xchg %1, %0\n" \ + "6670:movl %1, %0\n" \ + "6671:\n" \ + ".previous\n" \ + : "=m" (var), "=r" (__set_mb_temp) \ + : "1" (value) \ + : "memory"); } while (0) +#else +#define smp_rmb() rmb() +#define smp_mb() mb() +#define set_mb(var, value) do { xchg(&var, value); } while (0) +#endif +#define smp_read_barrier_depends() read_barrier_depends() +#else +#define smp_mb() barrier() +#define smp_rmb() barrier() +#define smp_wmb() barrier() +#define smp_read_barrier_depends() do { } while(0) +#define set_mb(var, value) do { var = value; barrier(); } while (0) +#endif + +#define set_wmb(var, value) do { var = value; wmb(); } while (0) + +/* interrupt control.. */ +#define local_save_flags(x) do { typecheck(unsigned long,x); __asm__ __volatile__("pushfl ; popl %0":"=g" (x): /* no input */); } while (0) +#define local_irq_restore(x) do { typecheck(unsigned long,x); __asm__ __volatile__("pushl %0 ; popfl": /* no output */ :"g" (x):"memory", "cc"); } while (0) +#define local_irq_disable() __asm__ __volatile__("cli": : :"memory") +#define local_irq_enable() __asm__ __volatile__("sti": : :"memory") +/* used in the idle loop; sti takes one instruction cycle to complete */ +#define safe_halt() __asm__ __volatile__("sti; hlt": : :"memory") + +#define irqs_disabled() \ +({ \ + unsigned long flags; \ + local_save_flags(flags); \ + !(flags & (1<<9)); \ +}) + +/* For spinlocks etc */ +#define local_irq_save(x) __asm__ __volatile__("pushfl ; popl %0 ; cli":"=g" (x): /* no input */ :"memory") + +/* + * disable hlt during certain critical i/o operations + */ +#define HAVE_DISABLE_HLT +void disable_hlt(void); +void enable_hlt(void); + +extern int es7000_plat; +void cpu_idle_wait(void); + +extern unsigned long arch_align_stack(unsigned long sp); + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-ia64/fixmap.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-ia64/fixmap.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,2 @@ +#define clear_fixmap(x) do {} while (0) +#define set_fixmap(x,y) do {} while (0) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-ia64/hypercall.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-ia64/hypercall.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,500 @@ +/****************************************************************************** + * hypercall.h + * + * Linux-specific hypervisor handling. + * + * Copyright (c) 2002-2004, K A Fraser + * + * This file may be distributed separately from the Linux kernel, or + * incorporated into other software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef __HYPERCALL_H__ +#define __HYPERCALL_H__ + +#include <asm-xen/xen-public/xen.h> +#include <asm-xen/xen-public/sched.h> + +/* FIXME: temp place to hold these page related macros */ +#include <asm/page.h> +#define virt_to_machine(v) __pa(v) +#define machine_to_virt(m) __va(m) +//#define virt_to_mfn(v) (__pa(v) >> 14) +//#define mfn_to_virt(m) (__va(m << 14)) +#define virt_to_mfn(v) ((__pa(v)) >> PAGE_SHIFT) +#define mfn_to_virt(m) (__va((m) << PAGE_SHIFT)) + +/* + * Assembler stubs for hyper-calls. + */ + +#if 0 +static inline int +HYPERVISOR_set_trap_table( + trap_info_t *table) +{ +#if 0 + int ret; + unsigned long ignore; + + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ignore) + : "0" (__HYPERVISOR_set_trap_table), "1" (table) + : "memory" ); + + return ret; +#endif + return 1; +} + +static inline int +HYPERVISOR_mmu_update( + mmu_update_t *req, int count, int *success_count, domid_t domid) +{ +#if 0 + int ret; + unsigned long ign1, ign2, ign3, ign4; + + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3), "=S" (ign4) + : "0" (__HYPERVISOR_mmu_update), "1" (req), "2" (count), + "3" (success_count), "4" (domid) + : "memory" ); + + return ret; +#endif + return 1; +} + +static inline int +HYPERVISOR_mmuext_op( + struct mmuext_op *op, int count, int *success_count, domid_t domid) +{ +#if 0 + int ret; + unsigned long ign1, ign2, ign3, ign4; + + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3), "=S" (ign4) + : "0" (__HYPERVISOR_mmuext_op), "1" (op), "2" (count), + "3" (success_count), "4" (domid) + : "memory" ); + + return ret; +#endif + return 1; +} + +static inline int +HYPERVISOR_set_gdt( + unsigned long *frame_list, int entries) +{ +#if 0 + int ret; + unsigned long ign1, ign2; + + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ign1), "=c" (ign2) + : "0" (__HYPERVISOR_set_gdt), "1" (frame_list), "2" (entries) + : "memory" ); + + + return ret; +#endif + return 1; +} + +static inline int +HYPERVISOR_stack_switch( + unsigned long ss, unsigned long esp) +{ +#if 0 + int ret; + unsigned long ign1, ign2; + + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ign1), "=c" (ign2) + : "0" (__HYPERVISOR_stack_switch), "1" (ss), "2" (esp) + : "memory" ); + + return ret; +#endif + return 1; +} + +static inline int +HYPERVISOR_set_callbacks( + unsigned long event_selector, unsigned long event_address, + unsigned long failsafe_selector, unsigned long failsafe_address) +{ +#if 0 + int ret; + unsigned long ign1, ign2, ign3, ign4; + + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3), "=S" (ign4) + : "0" (__HYPERVISOR_set_callbacks), "1" (event_selector), + "2" (event_address), "3" (failsafe_selector), "4" (failsafe_address) + : "memory" ); + + return ret; +#endif + return 1; +} + +static inline int +HYPERVISOR_fpu_taskswitch( + int set) +{ +#if 0 + int ret; + unsigned long ign; + + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ign) + : "0" (__HYPERVISOR_fpu_taskswitch), "1" (set) + : "memory" ); + + return ret; +#endif + return 1; +} + +static inline int +HYPERVISOR_sched_op( + int cmd, unsigned long arg) +{ + return 1; +} + +static inline int +HYPERVISOR_suspend( + unsigned long srec) +{ + return 1; +} + +static inline long +HYPERVISOR_set_timer_op( + u64 timeout) +{ +#if 0 + int ret; + unsigned long timeout_hi = (unsigned long)(timeout>>32); + unsigned long timeout_lo = (unsigned long)timeout; + unsigned long ign1, ign2; + + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ign1), "=c" (ign2) + : "0" (__HYPERVISOR_set_timer_op), "b" (timeout_lo), "c" (timeout_hi) + : "memory"); + + return ret; +#endif + return 1; +} + +static inline int +HYPERVISOR_dom0_op( + dom0_op_t *dom0_op) +{ +#if 0 + int ret; + unsigned long ign1; + + dom0_op->interface_version = DOM0_INTERFACE_VERSION; + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ign1) + : "0" (__HYPERVISOR_dom0_op), "1" (dom0_op) + : "memory"); + + return ret; +#endif + return 1; +} + +static inline int +HYPERVISOR_set_debugreg( + int reg, unsigned long value) +{ +#if 0 + int ret; + unsigned long ign1, ign2; + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ign1), "=c" (ign2) + : "0" (__HYPERVISOR_set_debugreg), "1" (reg), "2" (value) + : "memory" ); + + return ret; +#endif + return 1; +} + +static inline unsigned long +HYPERVISOR_get_debugreg( + int reg) +{ +#if 0 + unsigned long ret; + unsigned long ign; + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ign) + : "0" (__HYPERVISOR_get_debugreg), "1" (reg) + : "memory" ); + + return ret; +#endif + return 1; +} + +static inline int +HYPERVISOR_update_descriptor( + unsigned long ma, unsigned long word1, unsigned long word2) +{ +#if 0 + int ret; + unsigned long ign1, ign2, ign3; + + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3) + : "0" (__HYPERVISOR_update_descriptor), "1" (ma), "2" (word1), + "3" (word2) + : "memory" ); + + return ret; +#endif + return 1; +} + +static inline int +HYPERVISOR_set_fast_trap( + int idx) +{ +#if 0 + int ret; + unsigned long ign; + + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ign) + : "0" (__HYPERVISOR_set_fast_trap), "1" (idx) + : "memory" ); + + return ret; +#endif + return 1; +} + +static inline int +HYPERVISOR_dom_mem_op( + unsigned int op, unsigned long *extent_list, + unsigned long nr_extents, unsigned int extent_order) +{ +#if 0 + int ret; + unsigned long ign1, ign2, ign3, ign4, ign5; + + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3), "=S" (ign4), + "=D" (ign5) + : "0" (__HYPERVISOR_dom_mem_op), "1" (op), "2" (extent_list), + "3" (nr_extents), "4" (extent_order), "5" (DOMID_SELF) + : "memory" ); + + return ret; +#endif + return 1; +} + +static inline int +HYPERVISOR_multicall( + void *call_list, int nr_calls) +{ +#if 0 + int ret; + unsigned long ign1, ign2; + + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ign1), "=c" (ign2) + : "0" (__HYPERVISOR_multicall), "1" (call_list), "2" (nr_calls) + : "memory" ); + + return ret; +#endif + return 1; +} +#endif + +static inline int +HYPERVISOR_update_va_mapping( + unsigned long va, pte_t new_val, unsigned long flags) +{ + /* no-op */ + return 1; +} + +static inline int +HYPERVISOR_memory_op( + unsigned int cmd, void *arg) +{ + int ret; + __asm__ __volatile__ ( ";; mov r14=%2 ; mov r15=%3 ; mov r2=%1 ; break 0x1000 ;; mov %0=r8 ;;" + : "=r" (ret) + : "i" (__HYPERVISOR_memory_op), "r"(cmd), "r"(arg) + : "r14","r15","r2","r8","memory" ); + return ret; +} + +static inline int +HYPERVISOR_event_channel_op( + void *op) +{ + int ret; + __asm__ __volatile__ ( ";; mov r14=%2 ; mov r2=%1 ; break 0x1000 ;; mov %0=r8 ;;" + : "=r" (ret) + : "i" (__HYPERVISOR_event_channel_op), "r"(op) + : "r14","r2","r8","memory" ); + return ret; +} + +#if 0 +static inline int +HYPERVISOR_xen_version( + int cmd) +{ +#if 0 + int ret; + unsigned long ignore; + + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ignore) + : "0" (__HYPERVISOR_xen_version), "1" (cmd) + : "memory" ); + + return ret; +#endif + return 1; +} +#endif + +static inline int +HYPERVISOR_console_io( + int cmd, int count, char *str) +{ + int ret; + __asm__ __volatile__ ( ";; mov r14=%2 ; mov r15=%3 ; mov r16=%4 ; mov r2=%1 ; break 0x1000 ;; mov %0=r8 ;;" + : "=r" (ret) + : "i" (__HYPERVISOR_console_io), "r"(cmd), "r"(count), "r"(str) + : "r14","r15","r16","r2","r8","memory" ); + return ret; +} + +#if 0 +static inline int +HYPERVISOR_physdev_op( + void *physdev_op) +{ +#if 0 + int ret; + unsigned long ign; + + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ign) + : "0" (__HYPERVISOR_physdev_op), "1" (physdev_op) + : "memory" ); + + return ret; +#endif + return 1; +} +#endif + +static inline int +HYPERVISOR_grant_table_op( + unsigned int cmd, void *uop, unsigned int count) +{ + int ret; + __asm__ __volatile__ ( ";; mov r14=%2 ; mov r15=%3 ; mov r16=%4 ; mov r2=%1 ; break 0x1000 ;; mov %0=r8 ;;" + : "=r" (ret) + : "i" (__HYPERVISOR_grant_table_op), "r"(cmd), "r"(uop), "r"(count) + : "r14","r15","r16","r2","r8","memory" ); + return ret; +} + +#if 0 +static inline int +HYPERVISOR_update_va_mapping_otherdomain( + unsigned long va, pte_t new_val, unsigned long flags, domid_t domid) +{ +#if 0 + int ret; + unsigned long ign1, ign2, ign3, ign4; + + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3), "=S" (ign4) + : "0" (__HYPERVISOR_update_va_mapping_otherdomain), + "1" (va), "2" ((new_val).pte_low), "3" (flags), "4" (domid) : + "memory" ); + + return ret; +#endif + return 1; +} + +static inline int +HYPERVISOR_vm_assist( + unsigned int cmd, unsigned int type) +{ +#if 0 + int ret; + unsigned long ign1, ign2; + + __asm__ __volatile__ ( + TRAP_INSTR + : "=a" (ret), "=b" (ign1), "=c" (ign2) + : "0" (__HYPERVISOR_vm_assist), "1" (cmd), "2" (type) + : "memory" ); + + return ret; +#endif + return 1; +} + +#endif + +#endif /* __HYPERCALL_H__ */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-ia64/hypervisor.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-ia64/hypervisor.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,70 @@ +/****************************************************************************** + * hypervisor.h + * + * Linux-specific hypervisor handling. + * + * Copyright (c) 2002-2004, K A Fraser + * + * This file may be distributed separately from the Linux kernel, or + * incorporated into other software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef __HYPERVISOR_H__ +#define __HYPERVISOR_H__ + +#include <linux/config.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/version.h> +#include <asm-xen/xen-public/xen.h> +#include <asm-xen/xen-public/dom0_ops.h> +#include <asm/ptrace.h> +#include <asm/page.h> + +extern shared_info_t *HYPERVISOR_shared_info; +extern start_info_t *xen_start_info; + +void force_evtchn_callback(void); + +#include <asm/hypercall.h> + +// for drivers/xen/privcmd/privcmd.c +#define direct_remap_pfn_range(a,b,c,d,e,f) remap_pfn_range(a,b,c,d,e) +#define pfn_to_mfn(x) (x) +#define mfn_to_pfn(x) (x) +#define machine_to_phys_mapping 0 + +// for drivers/xen/balloon/balloon.c +#ifdef CONFIG_XEN_SCRUB_PAGES +#define scrub_pages(_p,_n) memset((void *)(_p), 0, (_n) << PAGE_SHIFT) +#else +#define scrub_pages(_p,_n) ((void)0) +#endif +#define pte_mfn(_x) pte_pfn(_x) +#define INVALID_P2M_ENTRY (~0UL) +#define __pte_ma(_x) ((pte_t) {(_x)}) +#define phys_to_machine_mapping_valid(_x) (1) +#define kmap_flush_unused() do {} while (0) +#define set_phys_to_machine(_x,_y) do {} while (0) +#define xen_machphys_update(_x,_y) do {} while (0) +#define pfn_pte_ma(_x,_y) __pte_ma(0) + +#endif /* __HYPERVISOR_H__ */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-ia64/synch_bitops.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-ia64/synch_bitops.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,61 @@ +#ifndef __XEN_SYNCH_BITOPS_H__ +#define __XEN_SYNCH_BITOPS_H__ + +/* + * Copyright 1992, Linus Torvalds. + * Heavily modified to provide guaranteed strong synchronisation + * when communicating with Xen or other guest OSes running on other CPUs. + */ + +#include <linux/config.h> + +#define ADDR (*(volatile long *) addr) + +static __inline__ void synch_set_bit(int nr, volatile void * addr) +{ + set_bit(nr, addr); +} + +static __inline__ void synch_clear_bit(int nr, volatile void * addr) +{ + clear_bit(nr, addr); +} + +static __inline__ void synch_change_bit(int nr, volatile void * addr) +{ + change_bit(nr, addr); +} + +static __inline__ int synch_test_and_set_bit(int nr, volatile void * addr) +{ + return test_and_set_bit(nr, addr); +} + +static __inline__ int synch_test_and_clear_bit(int nr, volatile void * addr) +{ + return test_and_clear_bit(nr, addr); +} + +static __inline__ int synch_test_and_change_bit(int nr, volatile void * addr) +{ + return test_and_change_bit(nr, addr); +} + +static __inline__ int synch_const_test_bit(int nr, const volatile void * addr) +{ + return test_bit(nr, addr); +} + +static __inline__ int synch_var_test_bit(int nr, volatile void * addr) +{ + return test_bit(nr, addr); +} + +#define synch_cmpxchg ia64_cmpxchg4_acq + +#define synch_test_bit(nr,addr) \ +(__builtin_constant_p(nr) ? \ + synch_const_test_bit((nr),(addr)) : \ + synch_var_test_bit((nr),(addr))) + +#endif /* __XEN_SYNCH_BITOPS_H__ */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-um/page.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-um/page.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,139 @@ +/* + * Copyright (C) 2000 - 2003 Jeff Dike (jdike@xxxxxxxxxxx) + * Copyright 2003 PathScale, Inc. + * Licensed under the GPL + */ + +#ifndef __UM_PAGE_H +#define __UM_PAGE_H + +struct page; + +#include <linux/config.h> +#include <asm/vm-flags.h> + +/* PAGE_SHIFT determines the page size */ +#define PAGE_SHIFT 12 +#define PAGE_SIZE (1UL << PAGE_SHIFT) +#define PAGE_MASK (~(PAGE_SIZE-1)) + +/* + * These are used to make use of C type-checking.. + */ + +#define clear_page(page) memset((void *)(page), 0, PAGE_SIZE) +#define copy_page(to,from) memcpy((void *)(to), (void *)(from), PAGE_SIZE) + +#define clear_user_page(page, vaddr, pg) clear_page(page) +#define copy_user_page(to, from, vaddr, pg) copy_page(to, from) + +#if defined(CONFIG_3_LEVEL_PGTABLES) && !defined(CONFIG_64BIT) + +typedef struct { unsigned long pte_low, pte_high; } pte_t; +typedef struct { unsigned long long pmd; } pmd_t; +typedef struct { unsigned long pgd; } pgd_t; +#define pte_val(x) ((x).pte_low | ((unsigned long long) (x).pte_high << 32)) + +#define pte_get_bits(pte, bits) ((pte).pte_low & (bits)) +#define pte_set_bits(pte, bits) ((pte).pte_low |= (bits)) +#define pte_clear_bits(pte, bits) ((pte).pte_low &= ~(bits)) +#define pte_copy(to, from) ({ (to).pte_high = (from).pte_high; \ + smp_wmb(); \ + (to).pte_low = (from).pte_low; }) +#define pte_is_zero(pte) (!((pte).pte_low & ~_PAGE_NEWPAGE) && !(pte).pte_high) +#define pte_set_val(pte, phys, prot) \ + ({ (pte).pte_high = (phys) >> 32; \ + (pte).pte_low = (phys) | pgprot_val(prot); }) + +#define pmd_val(x) ((x).pmd) +#define __pmd(x) ((pmd_t) { (x) } ) + +typedef unsigned long long pfn_t; +typedef unsigned long long phys_t; + +#else + +typedef struct { unsigned long pte; } pte_t; +typedef struct { unsigned long pgd; } pgd_t; + +#ifdef CONFIG_3_LEVEL_PGTABLES +typedef struct { unsigned long pmd; } pmd_t; +#define pmd_val(x) ((x).pmd) +#define __pmd(x) ((pmd_t) { (x) } ) +#endif + +#define pte_val(x) ((x).pte) + + +#define pte_get_bits(p, bits) ((p).pte & (bits)) +#define pte_set_bits(p, bits) ((p).pte |= (bits)) +#define pte_clear_bits(p, bits) ((p).pte &= ~(bits)) +#define pte_copy(to, from) ((to).pte = (from).pte) +#define pte_is_zero(p) (!((p).pte & ~_PAGE_NEWPAGE)) +#define pte_set_val(p, phys, prot) (p).pte = (phys | pgprot_val(prot)) + +typedef unsigned long pfn_t; +typedef unsigned long phys_t; + +#endif + +typedef struct { unsigned long pgprot; } pgprot_t; + +#define pgd_val(x) ((x).pgd) +#define pgprot_val(x) ((x).pgprot) + +#define __pte(x) ((pte_t) { (x) } ) +#define __pgd(x) ((pgd_t) { (x) } ) +#define __pgprot(x) ((pgprot_t) { (x) } ) + +/* to align the pointer to the (next) page boundary */ +#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) + +extern unsigned long uml_physmem; + +#define PAGE_OFFSET (uml_physmem) +#define KERNELBASE PAGE_OFFSET + +#define __va_space (8*1024*1024) + +extern unsigned long to_phys(void *virt); +extern void *to_virt(unsigned long phys); + +/* Cast to unsigned long before casting to void * to avoid a warning from + * mmap_kmem about cutting a long long down to a void *. Not sure that + * casting is the right thing, but 32-bit UML can't have 64-bit virtual + * addresses + */ +#define __pa(virt) to_phys((void *) (unsigned long) virt) +#define __va(phys) to_virt((unsigned long) phys) + +#define page_to_pfn(page) ((page) - mem_map) +#define pfn_to_page(pfn) (mem_map + (pfn)) + +#define phys_to_pfn(p) ((p) >> PAGE_SHIFT) +#define pfn_to_phys(pfn) ((pfn) << PAGE_SHIFT) + +#define pfn_valid(pfn) ((pfn) < max_mapnr) +#define virt_addr_valid(v) pfn_valid(phys_to_pfn(__pa(v))) + +/* Pure 2^n version of get_order */ +static __inline__ int get_order(unsigned long size) +{ + int order; + + size = (size-1) >> (PAGE_SHIFT-1); + order = -1; + do { + size >>= 1; + order++; + } while (size); + return order; +} + +extern struct page *arch_validate(struct page *page, int mask, int order); +#define HAVE_ARCH_VALIDATE + +extern int arch_free_page(struct page *page, int order); +#define HAVE_ARCH_FREE_PAGE + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/arch_hooks.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/arch_hooks.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,27 @@ +#ifndef _ASM_ARCH_HOOKS_H +#define _ASM_ARCH_HOOKS_H + +#include <linux/interrupt.h> + +/* + * linux/include/asm/arch_hooks.h + * + * define the architecture specific hooks + */ + +/* these aren't arch hooks, they are generic routines + * that can be used by the hooks */ +extern void init_ISA_irqs(void); +extern void apic_intr_init(void); +extern void smp_intr_init(void); +extern irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs); + +/* these are the defined hooks */ +extern void intr_init_hook(void); +extern void pre_intr_init_hook(void); +extern void pre_setup_arch_hook(void); +extern void trap_init_hook(void); +extern void time_init_hook(void); +extern void mca_nmi_hook(void); + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/bootsetup.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/bootsetup.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,42 @@ + +#ifndef _X86_64_BOOTSETUP_H +#define _X86_64_BOOTSETUP_H 1 + +#define BOOT_PARAM_SIZE 4096 +extern char x86_boot_params[BOOT_PARAM_SIZE]; + +/* + * This is set up by the setup-routine at boot-time + */ +#define PARAM ((unsigned char *)x86_boot_params) +#define SCREEN_INFO (*(struct screen_info *) (PARAM+0)) +#define EXT_MEM_K (*(unsigned short *) (PARAM+2)) +#define ALT_MEM_K (*(unsigned int *) (PARAM+0x1e0)) +#define E820_MAP_NR (*(char*) (PARAM+E820NR)) +#define E820_MAP ((struct e820entry *) (PARAM+E820MAP)) +#define APM_BIOS_INFO (*(struct apm_bios_info *) (PARAM+0x40)) +#define DRIVE_INFO (*(struct drive_info_struct *) (PARAM+0x80)) +#define SYS_DESC_TABLE (*(struct sys_desc_table_struct*)(PARAM+0xa0)) +#define MOUNT_ROOT_RDONLY (*(unsigned short *) (PARAM+0x1F2)) +#define RAMDISK_FLAGS (*(unsigned short *) (PARAM+0x1F8)) +#define SAVED_VIDEO_MODE (*(unsigned short *) (PARAM+0x1FA)) +#define ORIG_ROOT_DEV (*(unsigned short *) (PARAM+0x1FC)) +#define AUX_DEVICE_INFO (*(unsigned char *) (PARAM+0x1FF)) +#define LOADER_TYPE (*(unsigned char *) (PARAM+0x210)) +#define KERNEL_START (*(unsigned int *) (PARAM+0x214)) + +#define INITRD_START (__pa(xen_start_info->mod_start)) +#define INITRD_SIZE (xen_start_info->mod_len) +#define EDID_INFO (*(struct edid_info *) (PARAM+0x440)) + +#define EDD_NR (*(unsigned char *) (PARAM+EDDNR)) +#define EDD_MBR_SIG_NR (*(unsigned char *) (PARAM+EDD_MBR_SIG_NR_BUF)) +#define EDD_MBR_SIGNATURE ((unsigned int *) (PARAM+EDD_MBR_SIG_BUF)) +#define EDD_BUF ((struct edd_info *) (PARAM+EDDBUF)) +#define COMMAND_LINE saved_command_line + +#define RAMDISK_IMAGE_START_MASK 0x07FF +#define RAMDISK_PROMPT_FLAG 0x8000 +#define RAMDISK_LOAD_FLAG 0x4000 + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/desc.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/desc.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,240 @@ +/* Written 2000 by Andi Kleen */ +#ifndef __ARCH_DESC_H +#define __ARCH_DESC_H + +#include <linux/threads.h> +#include <asm/ldt.h> + +#ifndef __ASSEMBLY__ + +#include <linux/string.h> +#include <asm/segment.h> +#include <asm/mmu.h> + +// 8 byte segment descriptor +struct desc_struct { + u16 limit0; + u16 base0; + unsigned base1 : 8, type : 4, s : 1, dpl : 2, p : 1; + unsigned limit : 4, avl : 1, l : 1, d : 1, g : 1, base2 : 8; +} __attribute__((packed)); + +struct n_desc_struct { + unsigned int a,b; +}; + +enum { + GATE_INTERRUPT = 0xE, + GATE_TRAP = 0xF, + GATE_CALL = 0xC, +}; + +// 16byte gate +struct gate_struct { + u16 offset_low; + u16 segment; + unsigned ist : 3, zero0 : 5, type : 5, dpl : 2, p : 1; + u16 offset_middle; + u32 offset_high; + u32 zero1; +} __attribute__((packed)); + +#define PTR_LOW(x) ((unsigned long)(x) & 0xFFFF) +#define PTR_MIDDLE(x) (((unsigned long)(x) >> 16) & 0xFFFF) +#define PTR_HIGH(x) ((unsigned long)(x) >> 32) + +enum { + DESC_TSS = 0x9, + DESC_LDT = 0x2, +}; + +// LDT or TSS descriptor in the GDT. 16 bytes. +struct ldttss_desc { + u16 limit0; + u16 base0; + unsigned base1 : 8, type : 5, dpl : 2, p : 1; + unsigned limit1 : 4, zero0 : 3, g : 1, base2 : 8; + u32 base3; + u32 zero1; +} __attribute__((packed)); + +struct desc_ptr { + unsigned short size; + unsigned long address; +} __attribute__((packed)) ; + +extern struct desc_ptr idt_descr, cpu_gdt_descr[NR_CPUS]; + +extern struct desc_struct cpu_gdt_table[NR_CPUS][GDT_ENTRIES]; + +#define get_cpu_gdt_table(_cpu) ((struct desc_struct *)(cpu_gdt_descr[(_cpu)].address)) + +#define load_TR_desc() asm volatile("ltr %w0"::"r" (GDT_ENTRY_TSS*8)) +#define load_LDT_desc() asm volatile("lldt %w0"::"r" (GDT_ENTRY_LDT*8)) + +static inline void clear_LDT(void) +{ + int cpu = get_cpu(); + + /* + * NB. We load the default_ldt for lcall7/27 handling on demand, as + * it slows down context switching. Noone uses it anyway. + */ + cpu = cpu; /* XXX avoid compiler warning */ + xen_set_ldt(0UL, 0); + put_cpu(); +} + +/* + * This is the ldt that every process will get unless we need + * something other than this. + */ +extern struct desc_struct default_ldt[]; +extern struct gate_struct idt_table[]; + +static inline void _set_gate(void *adr, unsigned type, unsigned long func, unsigned dpl, unsigned ist) +{ + struct gate_struct s; + s.offset_low = PTR_LOW(func); + s.segment = __KERNEL_CS; + s.ist = ist; + s.p = 1; + s.dpl = dpl; + s.zero0 = 0; + s.zero1 = 0; + s.type = type; + s.offset_middle = PTR_MIDDLE(func); + s.offset_high = PTR_HIGH(func); + /* does not need to be atomic because it is only done once at setup time */ + memcpy(adr, &s, 16); +} + +static inline void set_intr_gate(int nr, void *func) +{ + _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 0, 0); +} + +static inline void set_intr_gate_ist(int nr, void *func, unsigned ist) +{ + _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 0, ist); +} + +static inline void set_system_gate(int nr, void *func) +{ + _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 3, 0); +} + +static inline void set_tssldt_descriptor(void *ptr, unsigned long tss, unsigned type, + unsigned size) +{ + struct ldttss_desc d; + memset(&d,0,sizeof(d)); + d.limit0 = size & 0xFFFF; + d.base0 = PTR_LOW(tss); + d.base1 = PTR_MIDDLE(tss) & 0xFF; + d.type = type; + d.p = 1; + d.limit1 = (size >> 16) & 0xF; + d.base2 = (PTR_MIDDLE(tss) >> 8) & 0xFF; + d.base3 = PTR_HIGH(tss); + memcpy(ptr, &d, 16); +} + +static inline void set_tss_desc(unsigned cpu, void *addr) +{ + set_tssldt_descriptor((struct ldttss_desc *)&get_cpu_gdt_table(cpu)[GDT_ENTRY_TSS], + (unsigned long)addr, + DESC_TSS, + sizeof(struct tss_struct) - 1); +} + +static inline void set_ldt_desc(unsigned cpu, void *addr, int size) +{ + set_tssldt_descriptor((struct ldttss_desc *)&get_cpu_gdt_table(cpu)[GDT_ENTRY_LDT], + (unsigned long)addr, + DESC_LDT, size * 8 - 1); +} + +static inline void set_seg_base(unsigned cpu, int entry, void *base) +{ + struct desc_struct *d = (struct desc_struct *)&get_cpu_gdt_table(cpu)[entry]; + u32 addr = (u32)(u64)base; + BUG_ON((u64)base >> 32); + d->base0 = addr & 0xffff; + d->base1 = (addr >> 16) & 0xff; + d->base2 = (addr >> 24) & 0xff; +} + +#define LDT_entry_a(info) \ + ((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff)) +/* Don't allow setting of the lm bit. It is useless anyways because + 64bit system calls require __USER_CS. */ +#define LDT_entry_b(info) \ + (((info)->base_addr & 0xff000000) | \ + (((info)->base_addr & 0x00ff0000) >> 16) | \ + ((info)->limit & 0xf0000) | \ + (((info)->read_exec_only ^ 1) << 9) | \ + ((info)->contents << 10) | \ + (((info)->seg_not_present ^ 1) << 15) | \ + ((info)->seg_32bit << 22) | \ + ((info)->limit_in_pages << 23) | \ + ((info)->useable << 20) | \ + /* ((info)->lm << 21) | */ \ + 0x7000) + +#define LDT_empty(info) (\ + (info)->base_addr == 0 && \ + (info)->limit == 0 && \ + (info)->contents == 0 && \ + (info)->read_exec_only == 1 && \ + (info)->seg_32bit == 0 && \ + (info)->limit_in_pages == 0 && \ + (info)->seg_not_present == 1 && \ + (info)->useable == 0 && \ + (info)->lm == 0) + +#if TLS_SIZE != 24 +# error update this code. +#endif + +static inline void load_TLS(struct thread_struct *t, unsigned int cpu) +{ +#if 0 + u64 *gdt = (u64 *)(cpu_gdt_table[cpu] + GDT_ENTRY_TLS_MIN); + gdt[0] = t->tls_array[0]; + gdt[1] = t->tls_array[1]; + gdt[2] = t->tls_array[2]; +#endif +#define C(i) \ + HYPERVISOR_update_descriptor(virt_to_machine(&get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN + i]), t->tls_array[i]) + + C(0); C(1); C(2); +#undef C +} + +/* + * load one particular LDT into the current CPU + */ +extern inline void load_LDT_nolock (mm_context_t *pc, int cpu) +{ + void *segments = pc->ldt; + int count = pc->size; + + if (likely(!count)) + segments = NULL; + + xen_set_ldt((unsigned long)segments, count); +} + +static inline void load_LDT(mm_context_t *pc) +{ + int cpu = get_cpu(); + load_LDT_nolock(pc, cpu); + put_cpu(); +} + +extern struct desc_ptr idt_descr; + +#endif /* !__ASSEMBLY__ */ + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/dma-mapping.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/dma-mapping.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,1 @@ +#include <asm-i386/mach-xen/asm/dma-mapping.h> diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/fixmap.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/fixmap.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,113 @@ +/* + * fixmap.h: compile-time virtual memory allocation + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 1998 Ingo Molnar + */ + +#ifndef _ASM_FIXMAP_H +#define _ASM_FIXMAP_H + +#include <linux/config.h> +#include <linux/kernel.h> +#include <asm/apicdef.h> +#include <xen/gnttab.h> +#include <asm/page.h> +#include <asm/vsyscall.h> +#include <asm/vsyscall32.h> +#include <asm/acpi.h> + +/* + * Here we define all the compile-time 'special' virtual + * addresses. The point is to have a constant address at + * compile time, but to set the physical address only + * in the boot process. + * + * these 'compile-time allocated' memory buffers are + * fixed-size 4k pages. (or larger if used with an increment + * highger than 1) use fixmap_set(idx,phys) to associate + * physical memory with fixmap indices. + * + * TLB entries of such buffers will not be flushed across + * task switches. + */ + +enum fixed_addresses { + VSYSCALL_LAST_PAGE, + VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1, + VSYSCALL_HPET, + FIX_HPET_BASE, +#ifdef CONFIG_X86_LOCAL_APIC + FIX_APIC_BASE, /* local (CPU) APIC) -- required for SMP or not */ +#endif +#ifdef CONFIG_X86_IO_APIC + FIX_IO_APIC_BASE_0, + FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS-1, +#endif +#ifdef CONFIG_ACPI_BOOT + FIX_ACPI_BEGIN, + FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1, +#endif + FIX_SHARED_INFO, + FIX_GNTTAB_BEGIN, + FIX_GNTTAB_END = FIX_GNTTAB_BEGIN + NR_GRANT_FRAMES - 1, +#ifdef CONFIG_XEN_PHYSDEV_ACCESS +#define NR_FIX_ISAMAPS 256 + FIX_ISAMAP_END, + FIX_ISAMAP_BEGIN = FIX_ISAMAP_END + NR_FIX_ISAMAPS - 1, +#endif + __end_of_fixed_addresses +}; + +extern void __set_fixmap (enum fixed_addresses idx, + unsigned long phys, pgprot_t flags); + +#define set_fixmap(idx, phys) \ + __set_fixmap(idx, phys, PAGE_KERNEL) +/* + * Some hardware wants to get fixmapped without caching. + */ +#define set_fixmap_nocache(idx, phys) \ + __set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE) + +#define clear_fixmap(idx) \ + __set_fixmap(idx, 0, __pgprot(0)) + +#define FIXADDR_TOP (VSYSCALL_END-PAGE_SIZE) +#define FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) + +/* Only covers 32bit vsyscalls currently. Need another set for 64bit. */ +#define FIXADDR_USER_START ((unsigned long)VSYSCALL32_VSYSCALL) +#define FIXADDR_USER_END (FIXADDR_USER_START + PAGE_SIZE) + +#define __fix_to_virt(x) (FIXADDR_TOP - ((x) << PAGE_SHIFT)) + +extern void __this_fixmap_does_not_exist(void); + +/* + * 'index to address' translation. If anyone tries to use the idx + * directly without translation, we catch the bug with a NULL-deference + * kernel oops. Illegal ranges of incoming indices are caught too. + */ +extern inline unsigned long fix_to_virt(const unsigned int idx) +{ + /* + * this branch gets completely eliminated after inlining, + * except when someone tries to use fixaddr indices in an + * illegal way. (such as mixing up address types or using + * out-of-range indices). + * + * If it doesn't get removed, the linker will complain + * loudly with a reasonably clear error message.. + */ + if (idx >= __end_of_fixed_addresses) + __this_fixmap_does_not_exist(); + + return __fix_to_virt(idx); +} + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/floppy.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/floppy.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,204 @@ +/* + * Architecture specific parts of the Floppy driver + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Copyright (C) 1995 + * + * Modifications for Xen are Copyright (c) 2004, Keir Fraser. + */ +#ifndef __ASM_XEN_X86_64_FLOPPY_H +#define __ASM_XEN_X86_64_FLOPPY_H + +#include <linux/vmalloc.h> + + +/* + * The DMA channel used by the floppy controller cannot access data at + * addresses >= 16MB + * + * Went back to the 1MB limit, as some people had problems with the floppy + * driver otherwise. It doesn't matter much for performance anyway, as most + * floppy accesses go through the track buffer. + */ +#define _CROSS_64KB(a,s,vdma) \ +(!(vdma) && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64)) + +#include <linux/vmalloc.h> + +/* XEN: Hit DMA paths on the head. This trick from asm-m68k/floppy.h. */ +#include <asm/dma.h> +#undef MAX_DMA_ADDRESS +#define MAX_DMA_ADDRESS 0 +#define CROSS_64KB(a,s) (0) + +#define fd_inb(port) inb_p(port) +#define fd_outb(value,port) outb_p(value,port) + +#define fd_request_dma() (0) +#define fd_free_dma() ((void)0) +#define fd_enable_irq() enable_irq(FLOPPY_IRQ) +#define fd_disable_irq() disable_irq(FLOPPY_IRQ) +#define fd_free_irq() free_irq(FLOPPY_IRQ, NULL) +#define fd_get_dma_residue() vdma_get_dma_residue(FLOPPY_DMA) +#define fd_dma_mem_alloc(size) vdma_mem_alloc(size) +#define fd_dma_mem_free(addr, size) vdma_mem_free(addr, size) +#define fd_dma_setup(addr, size, mode, io) vdma_dma_setup(addr, size, mode, io) + +static int virtual_dma_count; +static int virtual_dma_residue; +static char *virtual_dma_addr; +static int virtual_dma_mode; +static int doing_pdma; + +static irqreturn_t floppy_hardint(int irq, void *dev_id, struct pt_regs * regs) +{ + register unsigned char st; + +#undef TRACE_FLPY_INT + +#ifdef TRACE_FLPY_INT + static int calls=0; + static int bytes=0; + static int dma_wait=0; +#endif + if (!doing_pdma) + return floppy_interrupt(irq, dev_id, regs); + +#ifdef TRACE_FLPY_INT + if(!calls) + bytes = virtual_dma_count; +#endif + + { + register int lcount; + register char *lptr; + + st = 1; + for(lcount=virtual_dma_count, lptr=virtual_dma_addr; + lcount; lcount--, lptr++) { + st=inb(virtual_dma_port+4) & 0xa0 ; + if(st != 0xa0) + break; + if(virtual_dma_mode) + outb_p(*lptr, virtual_dma_port+5); + else + *lptr = inb_p(virtual_dma_port+5); + } + virtual_dma_count = lcount; + virtual_dma_addr = lptr; + st = inb(virtual_dma_port+4); + } + +#ifdef TRACE_FLPY_INT + calls++; +#endif + if(st == 0x20) + return IRQ_HANDLED; + if(!(st & 0x20)) { + virtual_dma_residue += virtual_dma_count; + virtual_dma_count=0; +#ifdef TRACE_FLPY_INT + printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n", + virtual_dma_count, virtual_dma_residue, calls, bytes, + dma_wait); + calls = 0; + dma_wait=0; +#endif + doing_pdma = 0; + floppy_interrupt(irq, dev_id, regs); + return IRQ_HANDLED; + } +#ifdef TRACE_FLPY_INT + if(!virtual_dma_count) + dma_wait++; +#endif + return IRQ_HANDLED; +} + +static void fd_disable_dma(void) +{ + doing_pdma = 0; + virtual_dma_residue += virtual_dma_count; + virtual_dma_count=0; +} + +static int vdma_get_dma_residue(unsigned int dummy) +{ + return virtual_dma_count + virtual_dma_residue; +} + + +static int fd_request_irq(void) +{ + return request_irq(FLOPPY_IRQ, floppy_hardint,SA_INTERRUPT, + "floppy", NULL); +} + + +static unsigned long vdma_mem_alloc(unsigned long size) +{ + return (unsigned long) vmalloc(size); + +} + +static void vdma_mem_free(unsigned long addr, unsigned long size) +{ + vfree((void *)addr); +} + +static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io) +{ + doing_pdma = 1; + virtual_dma_port = io; + virtual_dma_mode = (mode == DMA_MODE_WRITE); + virtual_dma_addr = addr; + virtual_dma_count = size; + virtual_dma_residue = 0; + return 0; +} + +/* XEN: This trick to force 'virtual DMA' is from include/asm-m68k/floppy.h. */ +#define FDC1 xen_floppy_init() +static int FDC2 = -1; + +static int xen_floppy_init(void) +{ + use_virtual_dma = 1; + can_use_virtual_dma = 1; + return 0x340; +} + +/* + * Floppy types are stored in the rtc's CMOS RAM and so rtc_lock + * is needed to prevent corrupted CMOS RAM in case "insmod floppy" + * coincides with another rtc CMOS user. Paul G. + */ +#define FLOPPY0_TYPE ({ \ + unsigned long flags; \ + unsigned char val; \ + spin_lock_irqsave(&rtc_lock, flags); \ + val = (CMOS_READ(0x10) >> 4) & 15; \ + spin_unlock_irqrestore(&rtc_lock, flags); \ + val; \ +}) + +#define FLOPPY1_TYPE ({ \ + unsigned long flags; \ + unsigned char val; \ + spin_lock_irqsave(&rtc_lock, flags); \ + val = CMOS_READ(0x10) & 15; \ + spin_unlock_irqrestore(&rtc_lock, flags); \ + val; \ +}) + +#define N_FDC 2 +#define N_DRIVE 8 + +#define FLOPPY_MOTOR_MASK 0xf0 + +#define EXTRA_FLOPPY_PARAMS + +#endif /* __ASM_XEN_X86_64_FLOPPY_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/hw_irq.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/hw_irq.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,138 @@ +#ifndef _ASM_HW_IRQ_H +#define _ASM_HW_IRQ_H + +/* + * linux/include/asm/hw_irq.h + * + * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar + * + * moved some of the old arch/i386/kernel/irq.h to here. VY + * + * IRQ/IPI changes taken from work by Thomas Radke + * <tomsoft@xxxxxxxxxxxxxxxxxxxxxxxxx> + * + * hacked by Andi Kleen for x86-64. + * + * $Id: hw_irq.h,v 1.24 2001/09/14 20:55:03 vojtech Exp $ + */ + +#ifndef __ASSEMBLY__ +#include <linux/config.h> +#include <asm/atomic.h> +#include <asm/irq.h> +#include <linux/profile.h> +#include <linux/smp.h> + +struct hw_interrupt_type; +#endif + +/* + * IDT vectors usable for external interrupt sources start + * at 0x20: + */ +#define FIRST_EXTERNAL_VECTOR 0x20 + +#define IA32_SYSCALL_VECTOR 0x80 + + +/* + * Vectors 0x20-0x2f are used for ISA interrupts. + */ + +/* + * Special IRQ vectors used by the SMP architecture, 0xf0-0xff + * + * some of the following vectors are 'rare', they are merged + * into a single vector (CALL_FUNCTION_VECTOR) to save vector space. + * TLB, reschedule and local APIC vectors are performance-critical. + * + * Vectors 0xf0-0xf9 are free (reserved for future Linux use). + */ +#ifndef CONFIG_XEN +#define SPURIOUS_APIC_VECTOR 0xff +#define ERROR_APIC_VECTOR 0xfe +#define INVALIDATE_TLB_VECTOR 0xfd +#define RESCHEDULE_VECTOR 0xfc +#define TASK_MIGRATION_VECTOR 0xfb +#define CALL_FUNCTION_VECTOR 0xfa +#define KDB_VECTOR 0xf9 + +#define THERMAL_APIC_VECTOR 0xf0 +#endif + +/* + * Local APIC timer IRQ vector is on a different priority level, + * to work around the 'lost local interrupt if more than 2 IRQ + * sources per level' errata. + */ +#define LOCAL_TIMER_VECTOR 0xef + +/* + * First APIC vector available to drivers: (vectors 0x30-0xee) + * we start at 0x31 to spread out vectors evenly between priority + * levels. (0x80 is the syscall vector) + */ +#define FIRST_DEVICE_VECTOR 0x31 +#define FIRST_SYSTEM_VECTOR 0xef /* duplicated in irq.h */ + + +#ifndef __ASSEMBLY__ +extern u8 irq_vector[NR_IRQ_VECTORS]; +#define IO_APIC_VECTOR(irq) (irq_vector[irq]) +#define AUTO_ASSIGN -1 + +/* + * Various low-level irq details needed by irq.c, process.c, + * time.c, io_apic.c and smp.c + * + * Interrupt entry/exit code at both C and assembly level + */ + +extern void disable_8259A_irq(unsigned int irq); +extern void enable_8259A_irq(unsigned int irq); +extern int i8259A_irq_pending(unsigned int irq); +extern void make_8259A_irq(unsigned int irq); +extern void init_8259A(int aeoi); +extern void FASTCALL(send_IPI_self(int vector)); +extern void init_VISWS_APIC_irqs(void); +extern void setup_IO_APIC(void); +extern void disable_IO_APIC(void); +extern void print_IO_APIC(void); +extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn); +extern void send_IPI(int dest, int vector); +extern void setup_ioapic_dest(void); + +extern unsigned long io_apic_irqs; + +extern atomic_t irq_err_count; +extern atomic_t irq_mis_count; + +#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs)) + +#define __STR(x) #x +#define STR(x) __STR(x) + +#include <asm/ptrace.h> + +#define IRQ_NAME2(nr) nr##_interrupt(void) +#define IRQ_NAME(nr) IRQ_NAME2(IRQ##nr) + +/* + * SMP has a few special interrupts for IPI messages + */ + +#define BUILD_IRQ(nr) \ +asmlinkage void IRQ_NAME(nr); \ +__asm__( \ +"\n.p2align\n" \ +"IRQ" #nr "_interrupt:\n\t" \ + "push $" #nr "-256 ; " \ + "jmp common_interrupt"); + +extern void hw_resend_irq(struct hw_interrupt_type *h, unsigned int i); + +#define platform_legacy_irq(irq) ((irq) < 16) + +#endif + +#endif /* _ASM_HW_IRQ_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/hypercall.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/hypercall.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,323 @@ +/****************************************************************************** + * hypercall.h + * + * Linux-specific hypervisor handling. + * + * Copyright (c) 2002-2004, K A Fraser + * + * 64-bit updates: + * Benjamin Liu <benjamin.liu@xxxxxxxxx> + * Jun Nakajima <jun.nakajima@xxxxxxxxx> + * + * This file may be distributed separately from the Linux kernel, or + * incorporated into other software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef __HYPERCALL_H__ +#define __HYPERCALL_H__ + +#include <xen/interface/xen.h> +#include <xen/interface/sched.h> + +#define __STR(x) #x +#define STR(x) __STR(x) + +#define _hypercall0(type, name) \ +({ \ + long __res; \ + asm volatile ( \ + "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ + : "=a" (__res) \ + : \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall1(type, name, a1) \ +({ \ + long __res, __ign1; \ + asm volatile ( \ + "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ + : "=a" (__res), "=D" (__ign1) \ + : "1" ((long)(a1)) \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall2(type, name, a1, a2) \ +({ \ + long __res, __ign1, __ign2; \ + asm volatile ( \ + "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ + : "=a" (__res), "=D" (__ign1), "=S" (__ign2) \ + : "1" ((long)(a1)), "2" ((long)(a2)) \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall3(type, name, a1, a2, a3) \ +({ \ + long __res, __ign1, __ign2, __ign3; \ + asm volatile ( \ + "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ + : "=a" (__res), "=D" (__ign1), "=S" (__ign2), \ + "=d" (__ign3) \ + : "1" ((long)(a1)), "2" ((long)(a2)), \ + "3" ((long)(a3)) \ + : "memory" ); \ + (type)__res; \ +}) + +#define _hypercall4(type, name, a1, a2, a3, a4) \ +({ \ + long __res, __ign1, __ign2, __ign3; \ + asm volatile ( \ + "movq %7,%%r10; " \ + "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ + : "=a" (__res), "=D" (__ign1), "=S" (__ign2), \ + "=d" (__ign3) \ + : "1" ((long)(a1)), "2" ((long)(a2)), \ + "3" ((long)(a3)), "g" ((long)(a4)) \ + : "memory", "r10" ); \ + (type)__res; \ +}) + +#define _hypercall5(type, name, a1, a2, a3, a4, a5) \ +({ \ + long __res, __ign1, __ign2, __ign3; \ + asm volatile ( \ + "movq %7,%%r10; movq %8,%%r8; " \ + "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ + : "=a" (__res), "=D" (__ign1), "=S" (__ign2), \ + "=d" (__ign3) \ + : "1" ((long)(a1)), "2" ((long)(a2)), \ + "3" ((long)(a3)), "g" ((long)(a4)), \ + "g" ((long)(a5)) \ + : "memory", "r10", "r8" ); \ + (type)__res; \ +}) + +static inline int +HYPERVISOR_set_trap_table( + trap_info_t *table) +{ + return _hypercall1(int, set_trap_table, table); +} + +static inline int +HYPERVISOR_mmu_update( + mmu_update_t *req, int count, int *success_count, domid_t domid) +{ + return _hypercall4(int, mmu_update, req, count, success_count, domid); +} + +static inline int +HYPERVISOR_mmuext_op( + struct mmuext_op *op, int count, int *success_count, domid_t domid) +{ + return _hypercall4(int, mmuext_op, op, count, success_count, domid); +} + +static inline int +HYPERVISOR_set_gdt( + unsigned long *frame_list, int entries) +{ + return _hypercall2(int, set_gdt, frame_list, entries); +} + +static inline int +HYPERVISOR_stack_switch( + unsigned long ss, unsigned long esp) +{ + return _hypercall2(int, stack_switch, ss, esp); +} + +static inline int +HYPERVISOR_set_callbacks( + unsigned long event_address, unsigned long failsafe_address, + unsigned long syscall_address) +{ + return _hypercall3(int, set_callbacks, + event_address, failsafe_address, syscall_address); +} + +static inline int +HYPERVISOR_fpu_taskswitch( + int set) +{ + return _hypercall1(int, fpu_taskswitch, set); +} + +static inline int +HYPERVISOR_sched_op( + int cmd, unsigned long arg) +{ + return _hypercall2(int, sched_op, cmd, arg); +} + +static inline long +HYPERVISOR_set_timer_op( + u64 timeout) +{ + return _hypercall1(long, set_timer_op, timeout); +} + +static inline int +HYPERVISOR_dom0_op( + dom0_op_t *dom0_op) +{ + dom0_op->interface_version = DOM0_INTERFACE_VERSION; + return _hypercall1(int, dom0_op, dom0_op); +} + +static inline int +HYPERVISOR_set_debugreg( + int reg, unsigned long value) +{ + return _hypercall2(int, set_debugreg, reg, value); +} + +static inline unsigned long +HYPERVISOR_get_debugreg( + int reg) +{ + return _hypercall1(unsigned long, get_debugreg, reg); +} + +static inline int +HYPERVISOR_update_descriptor( + unsigned long ma, unsigned long word) +{ + return _hypercall2(int, update_descriptor, ma, word); +} + +static inline int +HYPERVISOR_memory_op( + unsigned int cmd, void *arg) +{ + return _hypercall2(int, memory_op, cmd, arg); +} + +static inline int +HYPERVISOR_multicall( + void *call_list, int nr_calls) +{ + return _hypercall2(int, multicall, call_list, nr_calls); +} + +static inline int +HYPERVISOR_update_va_mapping( + unsigned long va, pte_t new_val, unsigned long flags) +{ + return _hypercall3(int, update_va_mapping, va, new_val.pte, flags); +} + +static inline int +HYPERVISOR_event_channel_op( + void *op) +{ + return _hypercall1(int, event_channel_op, op); +} + +static inline int +HYPERVISOR_xen_version( + int cmd, void *arg) +{ + return _hypercall2(int, xen_version, cmd, arg); +} + +static inline int +HYPERVISOR_console_io( + int cmd, int count, char *str) +{ + return _hypercall3(int, console_io, cmd, count, str); +} + +static inline int +HYPERVISOR_physdev_op( + void *physdev_op) +{ + return _hypercall1(int, physdev_op, physdev_op); +} + +static inline int +HYPERVISOR_grant_table_op( + unsigned int cmd, void *uop, unsigned int count) +{ + return _hypercall3(int, grant_table_op, cmd, uop, count); +} + +static inline int +HYPERVISOR_update_va_mapping_otherdomain( + unsigned long va, pte_t new_val, unsigned long flags, domid_t domid) +{ + return _hypercall4(int, update_va_mapping_otherdomain, va, + new_val.pte, flags, domid); +} + +static inline int +HYPERVISOR_vm_assist( + unsigned int cmd, unsigned int type) +{ + return _hypercall2(int, vm_assist, cmd, type); +} + +static inline int +HYPERVISOR_vcpu_op( + int cmd, int vcpuid, void *extra_args) +{ + return _hypercall3(int, vcpu_op, cmd, vcpuid, extra_args); +} + +static inline int +HYPERVISOR_set_segment_base( + int reg, unsigned long value) +{ + return _hypercall2(int, set_segment_base, reg, value); +} + +static inline int +HYPERVISOR_suspend( + unsigned long srec) +{ + return _hypercall3(int, sched_op, SCHEDOP_shutdown, + SHUTDOWN_suspend, srec); +} + +static inline int +HYPERVISOR_nmi_op( + unsigned long op, + unsigned long arg) +{ + return _hypercall2(int, nmi_op, op, arg); +} + +#endif /* __HYPERCALL_H__ */ + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/hypervisor.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/hypervisor.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,2 @@ + +#include <asm-i386/mach-xen/asm/hypervisor.h> diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/io.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/io.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,374 @@ +#ifndef _ASM_IO_H +#define _ASM_IO_H + +#include <linux/config.h> +#include <asm/fixmap.h> +/* + * This file contains the definitions for the x86 IO instructions + * inb/inw/inl/outb/outw/outl and the "string versions" of the same + * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing" + * versions of the single-IO instructions (inb_p/inw_p/..). + * + * This file is not meant to be obfuscating: it's just complicated + * to (a) handle it all in a way that makes gcc able to optimize it + * as well as possible and (b) trying to avoid writing the same thing + * over and over again with slight variations and possibly making a + * mistake somewhere. + */ + +/* + * Thanks to James van Artsdalen for a better timing-fix than + * the two short jumps: using outb's to a nonexistent port seems + * to guarantee better timings even on fast machines. + * + * On the other hand, I'd like to be sure of a non-existent port: + * I feel a bit unsafe about using 0x80 (should be safe, though) + * + * Linus + */ + + /* + * Bit simplified and optimized by Jan Hubicka + * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999. + * + * isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added, + * isa_read[wl] and isa_write[wl] fixed + * - Arnaldo Carvalho de Melo <acme@xxxxxxxxxxxxxxxx> + */ + +#define __SLOW_DOWN_IO "\noutb %%al,$0x80" + +#ifdef REALLY_SLOW_IO +#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO +#else +#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO +#endif + +/* + * Talk about misusing macros.. + */ +#define __OUT1(s,x) \ +extern inline void out##s(unsigned x value, unsigned short port) { + +#define __OUT2(s,s1,s2) \ +__asm__ __volatile__ ("out" #s " %" s1 "0,%" s2 "1" + +#define __OUT(s,s1,x) \ +__OUT1(s,x) __OUT2(s,s1,"w") : : "a" (value), "Nd" (port)); } \ +__OUT1(s##_p,x) __OUT2(s,s1,"w") __FULL_SLOW_DOWN_IO : : "a" (value), "Nd" (port));} \ + +#define __IN1(s) \ +extern inline RETURN_TYPE in##s(unsigned short port) { RETURN_TYPE _v; + +#define __IN2(s,s1,s2) \ +__asm__ __volatile__ ("in" #s " %" s2 "1,%" s1 "0" + +#define __IN(s,s1,i...) \ +__IN1(s) __IN2(s,s1,"w") : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \ +__IN1(s##_p) __IN2(s,s1,"w") __FULL_SLOW_DOWN_IO : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \ + +#define __INS(s) \ +extern inline void ins##s(unsigned short port, void * addr, unsigned long count) \ +{ __asm__ __volatile__ ("rep ; ins" #s \ +: "=D" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); } + +#define __OUTS(s) \ +extern inline void outs##s(unsigned short port, const void * addr, unsigned long count) \ +{ __asm__ __volatile__ ("rep ; outs" #s \ +: "=S" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); } + +#define RETURN_TYPE unsigned char +__IN(b,"") +#undef RETURN_TYPE +#define RETURN_TYPE unsigned short +__IN(w,"") +#undef RETURN_TYPE +#define RETURN_TYPE unsigned int +__IN(l,"") +#undef RETURN_TYPE + +__OUT(b,"b",char) +__OUT(w,"w",short) +__OUT(l,,int) + +__INS(b) +__INS(w) +__INS(l) + +__OUTS(b) +__OUTS(w) +__OUTS(l) + +#define IO_SPACE_LIMIT 0xffff + +#if defined(__KERNEL__) && __x86_64__ + +#include <linux/vmalloc.h> + +#ifndef __i386__ +/* + * Change virtual addresses to physical addresses and vv. + * These are pretty trivial + */ +extern inline unsigned long virt_to_phys(volatile void * address) +{ + return __pa(address); +} + +extern inline void * phys_to_virt(unsigned long address) +{ + return __va(address); +} + + +#define virt_to_bus(_x) phys_to_machine(__pa(_x)) +#define bus_to_virt(_x) __va(machine_to_phys(_x)) +#endif + +/* + * Change "struct page" to physical address. + */ +#ifdef CONFIG_DISCONTIGMEM +#include <asm/mmzone.h> +#define page_to_pseudophys(page) ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT) +#define page_to_phys(page) (phys_to_machine(page_to_pseudophys(page))) + +#define bio_to_pseudophys(bio) (page_to_pseudophys(bio_page((bio))) + \ + (unsigned long) bio_offset((bio))) +#define bvec_to_pseudophys(bv) (page_to_pseudophys((bv)->bv_page) + \ + (unsigned long) (bv)->bv_offset) + +#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ + (((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2))) && \ + ((bvec_to_pseudophys((vec1)) + (vec1)->bv_len) == \ + bvec_to_pseudophys((vec2)))) +#else +// #define page_to_phys(page) ((page - mem_map) << PAGE_SHIFT) +#define page_to_pseudophys(page) ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT) +#define page_to_phys(page) (phys_to_machine(page_to_pseudophys(page))) + +#define bio_to_pseudophys(bio) (page_to_pseudophys(bio_page((bio))) + \ + (unsigned long) bio_offset((bio))) +#define bvec_to_pseudophys(bv) (page_to_pseudophys((bv)->bv_page) + \ + (unsigned long) (bv)->bv_offset) + +#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ + (((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2))) && \ + ((bvec_to_pseudophys((vec1)) + (vec1)->bv_len) == \ + bvec_to_pseudophys((vec2)))) +#endif + +#include <asm-generic/iomap.h> + +extern void __iomem *__ioremap(unsigned long offset, unsigned long size, unsigned long flags); + +extern inline void __iomem * ioremap (unsigned long offset, unsigned long size) +{ + return __ioremap(offset, size, 0); +} + +/* + * This one maps high address device memory and turns off caching for that area. + * it's useful if some control registers are in such an area and write combining + * or read caching is not desirable: + */ +extern void __iomem * ioremap_nocache (unsigned long offset, unsigned long size); +extern void iounmap(volatile void __iomem *addr); + +/* + * ISA I/O bus memory addresses are 1:1 with the physical address. + */ + +#define isa_virt_to_bus(_x) isa_virt_to_bus_is_UNSUPPORTED->x +#define isa_page_to_bus(_x) isa_page_to_bus_is_UNSUPPORTED->x +#ifdef CONFIG_XEN_PHYSDEV_ACCESS +#define isa_bus_to_virt(_x) (void *)(__fix_to_virt(FIX_ISAMAP_BEGIN) + (_x)) +#else +#define isa_bus_to_virt(_x) isa_bus_to_virt_needs_PRIVILEGED_BUILD +#endif +/* + * However PCI ones are not necessarily 1:1 and therefore these interfaces + * are forbidden in portable PCI drivers. + * + * Allow them on x86 for legacy drivers, though. + */ +#define virt_to_bus(_x) phys_to_machine(__pa(_x)) +#define bus_to_virt(_x) __va(machine_to_phys(_x)) + +/* + * readX/writeX() are used to access memory mapped devices. On some + * architectures the memory mapped IO stuff needs to be accessed + * differently. On the x86 architecture, we just read/write the + * memory location directly. + */ + +static inline __u8 __readb(const volatile void __iomem *addr) +{ + return *(__force volatile __u8 *)addr; +} +static inline __u16 __readw(const volatile void __iomem *addr) +{ + return *(__force volatile __u16 *)addr; +} +static inline __u32 __readl(const volatile void __iomem *addr) +{ + return *(__force volatile __u32 *)addr; +} +static inline __u64 __readq(const volatile void __iomem *addr) +{ + return *(__force volatile __u64 *)addr; +} +#define readb(x) __readb(x) +#define readw(x) __readw(x) +#define readl(x) __readl(x) +#define readq(x) __readq(x) +#define readb_relaxed(a) readb(a) +#define readw_relaxed(a) readw(a) +#define readl_relaxed(a) readl(a) +#define readq_relaxed(a) readq(a) +#define __raw_readb readb +#define __raw_readw readw +#define __raw_readl readl +#define __raw_readq readq + +#define mmiowb() + +#ifdef CONFIG_UNORDERED_IO +static inline void __writel(__u32 val, volatile void __iomem *addr) +{ + volatile __u32 __iomem *target = addr; + asm volatile("movnti %1,%0" + : "=m" (*target) + : "r" (val) : "memory"); +} + +static inline void __writeq(__u64 val, volatile void __iomem *addr) +{ + volatile __u64 __iomem *target = addr; + asm volatile("movnti %1,%0" + : "=m" (*target) + : "r" (val) : "memory"); +} +#else +static inline void __writel(__u32 b, volatile void __iomem *addr) +{ + *(__force volatile __u32 *)addr = b; +} +static inline void __writeq(__u64 b, volatile void __iomem *addr) +{ + *(__force volatile __u64 *)addr = b; +} +#endif +static inline void __writeb(__u8 b, volatile void __iomem *addr) +{ + *(__force volatile __u8 *)addr = b; +} +static inline void __writew(__u16 b, volatile void __iomem *addr) +{ + *(__force volatile __u16 *)addr = b; +} +#define writeq(val,addr) __writeq((val),(addr)) +#define writel(val,addr) __writel((val),(addr)) +#define writew(val,addr) __writew((val),(addr)) +#define writeb(val,addr) __writeb((val),(addr)) +#define __raw_writeb writeb +#define __raw_writew writew +#define __raw_writel writel +#define __raw_writeq writeq + +void __memcpy_fromio(void*,unsigned long,unsigned); +void __memcpy_toio(unsigned long,const void*,unsigned); + +static inline void memcpy_fromio(void *to, const volatile void __iomem *from, unsigned len) +{ + __memcpy_fromio(to,(unsigned long)from,len); +} +static inline void memcpy_toio(volatile void __iomem *to, const void *from, unsigned len) +{ + __memcpy_toio((unsigned long)to,from,len); +} + +void memset_io(volatile void __iomem *a, int b, size_t c); + +/* + * ISA space is 'always mapped' on a typical x86 system, no need to + * explicitly ioremap() it. The fact that the ISA IO space is mapped + * to PAGE_OFFSET is pure coincidence - it does not mean ISA values + * are physical addresses. The following constant pointer can be + * used as the IO-area pointer (it can be iounmapped as well, so the + * analogy with PCI is quite large): + */ +#define __ISA_IO_base ((char __iomem *)(fix_to_virt(FIX_ISAMAP_BEGIN))) + +#define isa_readb(a) readb(__ISA_IO_base + (a)) +#define isa_readw(a) readw(__ISA_IO_base + (a)) +#define isa_readl(a) readl(__ISA_IO_base + (a)) +#define isa_writeb(b,a) writeb(b,__ISA_IO_base + (a)) +#define isa_writew(w,a) writew(w,__ISA_IO_base + (a)) +#define isa_writel(l,a) writel(l,__ISA_IO_base + (a)) +#define isa_memset_io(a,b,c) memset_io(__ISA_IO_base + (a),(b),(c)) +#define isa_memcpy_fromio(a,b,c) memcpy_fromio((a),__ISA_IO_base + (b),(c)) +#define isa_memcpy_toio(a,b,c) memcpy_toio(__ISA_IO_base + (a),(b),(c)) + + +/* + * Again, x86-64 does not require mem IO specific function. + */ + +#define eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void *)(b),(c),(d)) +#define isa_eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void *)(__ISA_IO_base + (b)),(c),(d)) + +/** + * check_signature - find BIOS signatures + * @io_addr: mmio address to check + * @signature: signature block + * @length: length of signature + * + * Perform a signature comparison with the mmio address io_addr. This + * address should have been obtained by ioremap. + * Returns 1 on a match. + */ + +static inline int check_signature(void __iomem *io_addr, + const unsigned char *signature, int length) +{ + int retval = 0; + do { + if (readb(io_addr) != *signature) + goto out; + io_addr++; + signature++; + length--; + } while (length); + retval = 1; +out: + return retval; +} + +/* Nothing to do */ + +#define dma_cache_inv(_start,_size) do { } while (0) +#define dma_cache_wback(_start,_size) do { } while (0) +#define dma_cache_wback_inv(_start,_size) do { } while (0) + +#define flush_write_buffers() + +extern int iommu_bio_merge; +#define BIO_VMERGE_BOUNDARY iommu_bio_merge + +/* + * Convert a physical pointer to a virtual kernel pointer for /dev/mem + * access + */ +#define xlate_dev_mem_ptr(p) __va(p) + +/* + * Convert a virtual cached pointer to an uncached pointer + */ +#define xlate_dev_kmem_ptr(p) p + +#endif /* __KERNEL__ */ + +#define ARCH_HAS_DEV_MEM + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/irq.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/irq.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,36 @@ +#ifndef _ASM_IRQ_H +#define _ASM_IRQ_H + +/* + * linux/include/asm/irq.h + * + * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar + * + * IRQ/IPI changes taken from work by Thomas Radke + * <tomsoft@xxxxxxxxxxxxxxxxxxxxxxxxx> + */ + +#include <linux/config.h> +#include <linux/sched.h> +/* include comes from machine specific directory */ +#include "irq_vectors.h" +#include <asm/thread_info.h> + +static __inline__ int irq_canonicalize(int irq) +{ + return ((irq == 2) ? 9 : irq); +} + +#ifdef CONFIG_X86_LOCAL_APIC +#define ARCH_HAS_NMI_WATCHDOG /* See include/linux/nmi.h */ +#endif + +#define KDB_VECTOR 0xf9 + +# define irq_ctx_init(cpu) do { } while (0) + +struct irqaction; +struct pt_regs; +int handle_IRQ_event(unsigned int, struct pt_regs *, struct irqaction *); + +#endif /* _ASM_IRQ_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/mmu.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/mmu.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,33 @@ +#ifndef __x86_64_MMU_H +#define __x86_64_MMU_H + +#include <linux/spinlock.h> +#include <asm/semaphore.h> + +/* + * The x86_64 doesn't have a mmu context, but + * we put the segment information here. + * + * cpu_vm_mask is used to optimize ldt flushing. + */ +typedef struct { + void *ldt; + rwlock_t ldtlock; + int size; + struct semaphore sem; +#ifdef CONFIG_XEN + unsigned pinned:1; + struct list_head unpinned; +#endif +} mm_context_t; + +#ifdef CONFIG_XEN +extern struct list_head mm_unpinned; +extern spinlock_t mm_unpinned_lock; + +/* mm/memory.c:exit_mmap hook */ +extern void _arch_exit_mmap(struct mm_struct *mm); +#define arch_exit_mmap(_mm) _arch_exit_mmap(_mm) +#endif + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/mmu_context.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/mmu_context.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,132 @@ +#ifndef __X86_64_MMU_CONTEXT_H +#define __X86_64_MMU_CONTEXT_H + +#include <linux/config.h> +#include <asm/desc.h> +#include <asm/atomic.h> +#include <asm/pgalloc.h> +#include <asm/page.h> +#include <asm/pda.h> +#include <asm/pgtable.h> +#include <asm/tlbflush.h> + +/* + * possibly do the LDT unload here? + */ +int init_new_context(struct task_struct *tsk, struct mm_struct *mm); +void destroy_context(struct mm_struct *mm); + +static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) +{ +#if 0 /* XEN: no lazy tlb */ + if (read_pda(mmu_state) == TLBSTATE_OK) + write_pda(mmu_state, TLBSTATE_LAZY); +#endif +} + +#define prepare_arch_switch(rq,next) __prepare_arch_switch() +#define finish_arch_switch(rq, next) spin_unlock_irq(&(rq)->lock) +#define task_running(rq, p) ((rq)->curr == (p)) + +static inline void __prepare_arch_switch(void) +{ + /* + * Save away %es, %ds, %fs and %gs. Must happen before reload + * of cr3/ldt (i.e., not in __switch_to). + */ + __asm__ __volatile__ ( + "mov %%es,%0 ; mov %%ds,%1 ; mov %%fs,%2 ; mov %%gs,%3" + : "=m" (current->thread.es), + "=m" (current->thread.ds), + "=m" (current->thread.fsindex), + "=m" (current->thread.gsindex) ); + + if (current->thread.ds) + __asm__ __volatile__ ( "movl %0,%%ds" : : "r" (0) ); + + if (current->thread.es) + __asm__ __volatile__ ( "movl %0,%%es" : : "r" (0) ); + + if (current->thread.fsindex) { + __asm__ __volatile__ ( "movl %0,%%fs" : : "r" (0) ); + current->thread.fs = 0; + } + + if (current->thread.gsindex) { + load_gs_index(0); + current->thread.gs = 0; + } +} + +extern void mm_pin(struct mm_struct *mm); +extern void mm_unpin(struct mm_struct *mm); +void mm_pin_all(void); + +static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, + struct task_struct *tsk) +{ + unsigned cpu = smp_processor_id(); + struct mmuext_op _op[3], *op = _op; + + if (likely(prev != next)) { + if (!next->context.pinned) + mm_pin(next); + + /* stop flush ipis for the previous mm */ + clear_bit(cpu, &prev->cpu_vm_mask); +#if 0 /* XEN: no lazy tlb */ + write_pda(mmu_state, TLBSTATE_OK); + write_pda(active_mm, next); +#endif + set_bit(cpu, &next->cpu_vm_mask); + + /* load_cr3(next->pgd) */ + per_cpu(cur_pgd, smp_processor_id()) = next->pgd; + op->cmd = MMUEXT_NEW_BASEPTR; + op->arg1.mfn = pfn_to_mfn(__pa(next->pgd) >> PAGE_SHIFT); + op++; + + /* xen_new_user_pt(__pa(__user_pgd(next->pgd))) */ + op->cmd = MMUEXT_NEW_USER_BASEPTR; + op->arg1.mfn = pfn_to_mfn(__pa(__user_pgd(next->pgd)) >> PAGE_SHIFT); + op++; + + if (unlikely(next->context.ldt != prev->context.ldt)) { + /* load_LDT_nolock(&next->context, cpu) */ + op->cmd = MMUEXT_SET_LDT; + op->arg1.linear_addr = (unsigned long)next->context.ldt; + op->arg2.nr_ents = next->context.size; + op++; + } + + BUG_ON(HYPERVISOR_mmuext_op(_op, op-_op, NULL, DOMID_SELF)); + } + +#if 0 /* XEN: no lazy tlb */ + else { + write_pda(mmu_state, TLBSTATE_OK); + if (read_pda(active_mm) != next) + out_of_line_bug(); + if(!test_and_set_bit(cpu, &next->cpu_vm_mask)) { + /* We were in lazy tlb mode and leave_mm disabled + * tlb flush IPI delivery. We must reload CR3 + * to make sure to use no freed page tables. + */ + load_cr3(next->pgd); + xen_new_user_pt(__pa(__user_pgd(next->pgd))); + load_LDT_nolock(&next->context, cpu); + } + } +#endif +} + +#define deactivate_mm(tsk,mm) do { \ + load_gs_index(0); \ + asm volatile("movl %0,%%fs"::"r"(0)); \ +} while(0) + +#define activate_mm(prev, next) do { \ + switch_mm((prev),(next),NULL); \ +} while (0) + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/nmi.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/nmi.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,75 @@ +/* + * linux/include/asm-i386/nmi.h + */ +#ifndef ASM_NMI_H +#define ASM_NMI_H + +#include <linux/pm.h> + +#include <xen/interface/nmi.h> + +struct pt_regs; + +typedef int (*nmi_callback_t)(struct pt_regs * regs, int cpu); + +/** + * set_nmi_callback + * + * Set a handler for an NMI. Only one handler may be + * set. Return 1 if the NMI was handled. + */ +void set_nmi_callback(nmi_callback_t callback); + +/** + * unset_nmi_callback + * + * Remove the handler previously set. + */ +void unset_nmi_callback(void); + +#ifdef CONFIG_PM + +/** Replace the PM callback routine for NMI. */ +struct pm_dev * set_nmi_pm_callback(pm_callback callback); + +/** Unset the PM callback routine back to the default. */ +void unset_nmi_pm_callback(struct pm_dev * dev); + +#else + +static inline struct pm_dev * set_nmi_pm_callback(pm_callback callback) +{ + return 0; +} + +static inline void unset_nmi_pm_callback(struct pm_dev * dev) +{ +} + +#endif /* CONFIG_PM */ + +extern void default_do_nmi(struct pt_regs *); +extern void die_nmi(char *str, struct pt_regs *regs); + +static inline unsigned char get_nmi_reason(void) +{ + shared_info_t *s = HYPERVISOR_shared_info; + unsigned char reason = 0; + + /* construct a value which looks like it came from + * port 0x61. + */ + if (test_bit(_XEN_NMIREASON_io_error, &s->arch.nmi_reason)) + reason |= 0x40; + if (test_bit(_XEN_NMIREASON_parity_error, &s->arch.nmi_reason)) + reason |= 0x80; + + return reason; +} + +extern int panic_on_timeout; +extern int unknown_nmi_panic; + +extern int check_nmi_watchdog(void); + +#endif /* ASM_NMI_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/page.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/page.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,260 @@ +#ifndef _X86_64_PAGE_H +#define _X86_64_PAGE_H + +#include <linux/config.h> +/* #include <linux/string.h> */ +#ifndef __ASSEMBLY__ +#include <linux/types.h> +#endif +#include <xen/interface/xen.h> +#include <xen/foreign_page.h> + +#define arch_free_page(_page,_order) \ +({ int foreign = PageForeign(_page); \ + if (foreign) \ + (PageForeignDestructor(_page))(_page); \ + foreign; \ +}) +#define HAVE_ARCH_FREE_PAGE + +#ifdef CONFIG_XEN_SCRUB_PAGES +#define scrub_pages(_p,_n) memset((void *)(_p), 0, (_n) << PAGE_SHIFT) +#else +#define scrub_pages(_p,_n) ((void)0) +#endif + +/* PAGE_SHIFT determines the page size */ +#define PAGE_SHIFT 12 +#ifdef __ASSEMBLY__ +#define PAGE_SIZE (0x1 << PAGE_SHIFT) +#else +#define PAGE_SIZE (1UL << PAGE_SHIFT) +#endif +#define PAGE_MASK (~(PAGE_SIZE-1)) +#define PHYSICAL_PAGE_MASK (~(PAGE_SIZE-1) & (__PHYSICAL_MASK << PAGE_SHIFT)) + +#define THREAD_ORDER 1 +#ifdef __ASSEMBLY__ +#define THREAD_SIZE (1 << (PAGE_SHIFT + THREAD_ORDER)) +#else +#define THREAD_SIZE (1UL << (PAGE_SHIFT + THREAD_ORDER)) +#endif +#define CURRENT_MASK (~(THREAD_SIZE-1)) + +#define LARGE_PAGE_MASK (~(LARGE_PAGE_SIZE-1)) +#define LARGE_PAGE_SIZE (1UL << PMD_SHIFT) + +#define HPAGE_SHIFT PMD_SHIFT +#define HPAGE_SIZE ((1UL) << HPAGE_SHIFT) +#define HPAGE_MASK (~(HPAGE_SIZE - 1)) +#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) + +#ifdef __KERNEL__ +#ifndef __ASSEMBLY__ + +void clear_page(void *); +void copy_page(void *, void *); + +#define clear_user_page(page, vaddr, pg) clear_page(page) +#define copy_user_page(to, from, vaddr, pg) copy_page(to, from) + +#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr) +#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE + +/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/ +#define INVALID_P2M_ENTRY (~0UL) +#define FOREIGN_FRAME(m) ((m) | (1UL<<63)) +extern unsigned long *phys_to_machine_mapping; +#define pfn_to_mfn(pfn) \ +(phys_to_machine_mapping[(unsigned int)(pfn)] & ~(1UL << 63)) +#define phys_to_machine_mapping_valid(pfn) \ + (phys_to_machine_mapping[pfn] != INVALID_P2M_ENTRY) +static inline unsigned long mfn_to_pfn(unsigned long mfn) +{ + unsigned long pfn; + + /* + * The array access can fail (e.g., device space beyond end of RAM). + * In such cases it doesn't matter what we return (we return garbage), + * but we must handle the fault without crashing! + */ + asm ( + "1: movq %1,%0\n" + "2:\n" + ".section __ex_table,\"a\"\n" + " .align 8\n" + " .quad 1b,2b\n" + ".previous" + : "=r" (pfn) : "m" (machine_to_phys_mapping[mfn]) ); + + return pfn; +} + +static inline void set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + phys_to_machine_mapping[pfn] = mfn; +} + +/* Definitions for machine and pseudophysical addresses. */ +typedef unsigned long paddr_t; +typedef unsigned long maddr_t; + +static inline maddr_t phys_to_machine(paddr_t phys) +{ + maddr_t machine = pfn_to_mfn(phys >> PAGE_SHIFT); + machine = (machine << PAGE_SHIFT) | (phys & ~PAGE_MASK); + return machine; +} + +static inline paddr_t machine_to_phys(maddr_t machine) +{ + paddr_t phys = mfn_to_pfn(machine >> PAGE_SHIFT); + phys = (phys << PAGE_SHIFT) | (machine & ~PAGE_MASK); + return phys; +} + +/* + * These are used to make use of C type-checking.. + */ +typedef struct { unsigned long pte; } pte_t; +typedef struct { unsigned long pmd; } pmd_t; +typedef struct { unsigned long pud; } pud_t; +typedef struct { unsigned long pgd; } pgd_t; +#define PTE_MASK PHYSICAL_PAGE_MASK + +typedef struct { unsigned long pgprot; } pgprot_t; + +#define pte_val(x) (((x).pte & 1) ? machine_to_phys((x).pte) : \ + (x).pte) +#define pte_val_ma(x) ((x).pte) + +static inline unsigned long pmd_val(pmd_t x) +{ + unsigned long ret = x.pmd; + if (ret) ret = machine_to_phys(ret); + return ret; +} + +static inline unsigned long pud_val(pud_t x) +{ + unsigned long ret = x.pud; + if (ret) ret = machine_to_phys(ret); + return ret; +} + +static inline unsigned long pgd_val(pgd_t x) +{ + unsigned long ret = x.pgd; + if (ret) ret = machine_to_phys(ret); + return ret; +} + +#define pgprot_val(x) ((x).pgprot) + +#define __pte_ma(x) ((pte_t) { (x) } ) + +static inline pte_t __pte(unsigned long x) +{ + if (x & 1) x = phys_to_machine(x); + return ((pte_t) { (x) }); +} + +static inline pmd_t __pmd(unsigned long x) +{ + if ((x & 1)) x = phys_to_machine(x); + return ((pmd_t) { (x) }); +} + +static inline pud_t __pud(unsigned long x) +{ + if ((x & 1)) x = phys_to_machine(x); + return ((pud_t) { (x) }); +} + +static inline pgd_t __pgd(unsigned long x) +{ + if ((x & 1)) x = phys_to_machine(x); + return ((pgd_t) { (x) }); +} + +#define __pgprot(x) ((pgprot_t) { (x) } ) + +#define __START_KERNEL 0xffffffff80100000UL +#define __START_KERNEL_map 0xffffffff80000000UL +#define __PAGE_OFFSET 0xffff880000000000UL + +#else +#define __START_KERNEL 0xffffffff80100000 +#define __START_KERNEL_map 0xffffffff80000000 +#define __PAGE_OFFSET 0xffff880000000000 +#endif /* !__ASSEMBLY__ */ + +/* to align the pointer to the (next) page boundary */ +#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) + +/* See Documentation/x86_64/mm.txt for a description of the memory map. */ +#define __PHYSICAL_MASK_SHIFT 46 +#define __PHYSICAL_MASK ((1UL << __PHYSICAL_MASK_SHIFT) - 1) +#define __VIRTUAL_MASK_SHIFT 48 +#define __VIRTUAL_MASK ((1UL << __VIRTUAL_MASK_SHIFT) - 1) + +#define KERNEL_TEXT_SIZE (40UL*1024*1024) +#define KERNEL_TEXT_START 0xffffffff80000000UL + +#ifndef __ASSEMBLY__ + +#include <asm/bug.h> + +/* Pure 2^n version of get_order */ +extern __inline__ int get_order(unsigned long size) +{ + int order; + + size = (size-1) >> (PAGE_SHIFT-1); + order = -1; + do { + size >>= 1; + order++; + } while (size); + return order; +} + +#endif /* __ASSEMBLY__ */ + +#define PAGE_OFFSET ((unsigned long)__PAGE_OFFSET) + +/* Note: __pa(&symbol_visible_to_c) should be always replaced with __pa_symbol. + Otherwise you risk miscompilation. */ +#define __pa(x) (((unsigned long)(x)>=__START_KERNEL_map)?(unsigned long)(x) - (unsigned long)__START_KERNEL_map:(unsigned long)(x) - PAGE_OFFSET) +/* __pa_symbol should be used for C visible symbols. + This seems to be the official gcc blessed way to do such arithmetic. */ +#define __pa_symbol(x) \ + ({unsigned long v; \ + asm("" : "=r" (v) : "0" (x)); \ + __pa(v); }) + +#define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET)) +#ifndef CONFIG_DISCONTIGMEM +#define pfn_to_page(pfn) (mem_map + (pfn)) +#define page_to_pfn(page) ((unsigned long)((page) - mem_map)) +#define pfn_valid(pfn) ((pfn) < max_mapnr) +#endif + +#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) +#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) +#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) + +/* VIRT <-> MACHINE conversion */ +#define virt_to_machine(v) (phys_to_machine(__pa(v))) +#define virt_to_mfn(v) (pfn_to_mfn(__pa(v) >> PAGE_SHIFT)) +#define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) + +#define VM_DATA_DEFAULT_FLAGS \ + (((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \ + VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) + +#define __HAVE_ARCH_GATE_AREA 1 + +#endif /* __KERNEL__ */ + +#endif /* _X86_64_PAGE_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/param.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/param.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,22 @@ +#ifndef _ASMx86_64_PARAM_H +#define _ASMx86_64_PARAM_H + +#ifdef __KERNEL__ +# define HZ 100 /* Internal kernel timer frequency */ +# define USER_HZ 100 /* .. some user interfaces are in "ticks" */ +# define CLOCKS_PER_SEC (USER_HZ) /* like times() */ +#endif + +#ifndef HZ +#define HZ 100 +#endif + +#define EXEC_PAGESIZE 4096 + +#ifndef NOGROUP +#define NOGROUP (-1) +#endif + +#define MAXHOSTNAMELEN 64 /* max length of hostname */ + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/pci.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/pci.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,167 @@ +#ifndef __x8664_PCI_H +#define __x8664_PCI_H + +#include <linux/config.h> +#include <asm/io.h> + +#ifdef __KERNEL__ + +#include <linux/mm.h> /* for struct page */ + +/* Can be used to override the logic in pci_scan_bus for skipping + already-configured bus numbers - to be used for buggy BIOSes + or architectures with incomplete PCI setup by the loader */ + +#ifdef CONFIG_PCI +extern unsigned int pcibios_assign_all_busses(void); +#else +#define pcibios_assign_all_busses() 0 +#endif +#define pcibios_scan_all_fns(a, b) 0 + +extern int no_iommu, force_iommu; + +extern unsigned long pci_mem_start; +#define PCIBIOS_MIN_IO 0x1000 +#define PCIBIOS_MIN_MEM (pci_mem_start) + +#define PCIBIOS_MIN_CARDBUS_IO 0x4000 + +void pcibios_config_init(void); +struct pci_bus * pcibios_scan_root(int bus); +extern int (*pci_config_read)(int seg, int bus, int dev, int fn, int reg, int len, u32 *value); +extern int (*pci_config_write)(int seg, int bus, int dev, int fn, int reg, int len, u32 value); + +void pcibios_set_master(struct pci_dev *dev); +void pcibios_penalize_isa_irq(int irq); +struct irq_routing_table *pcibios_get_irq_routing_table(void); +int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq); + +#include <linux/types.h> +#include <linux/slab.h> +#include <asm/scatterlist.h> +#include <linux/string.h> +#include <asm/page.h> + +extern int iommu_setup(char *opt); + +#ifdef CONFIG_GART_IOMMU +/* The PCI address space does equal the physical memory + * address space. The networking and block device layers use + * this boolean for bounce buffer decisions + * + * On AMD64 it mostly equals, but we set it to zero to tell some subsystems + * that an IOMMU is available. + */ +#define PCI_DMA_BUS_IS_PHYS (no_iommu ? 1 : 0) + +/* + * x86-64 always supports DAC, but sometimes it is useful to force + * devices through the IOMMU to get automatic sg list merging. + * Optional right now. + */ +extern int iommu_sac_force; +#define pci_dac_dma_supported(pci_dev, mask) (!iommu_sac_force) + +#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ + dma_addr_t ADDR_NAME; +#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \ + __u32 LEN_NAME; +#define pci_unmap_addr(PTR, ADDR_NAME) \ + ((PTR)->ADDR_NAME) +#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ + (((PTR)->ADDR_NAME) = (VAL)) +#define pci_unmap_len(PTR, LEN_NAME) \ + ((PTR)->LEN_NAME) +#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ + (((PTR)->LEN_NAME) = (VAL)) + +#elif defined(CONFIG_SWIOTLB) + +#define PCI_DMA_BUS_IS_PHYS 0 + +#define pci_dac_dma_supported(pci_dev, mask) 1 + +#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ + dma_addr_t ADDR_NAME; +#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \ + __u32 LEN_NAME; +#define pci_unmap_addr(PTR, ADDR_NAME) \ + ((PTR)->ADDR_NAME) +#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ + (((PTR)->ADDR_NAME) = (VAL)) +#define pci_unmap_len(PTR, LEN_NAME) \ + ((PTR)->LEN_NAME) +#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ + (((PTR)->LEN_NAME) = (VAL)) + +#else +/* No IOMMU */ + +#define PCI_DMA_BUS_IS_PHYS 1 +#define pci_dac_dma_supported(pci_dev, mask) 1 + +#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) +#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) +#define pci_unmap_addr(PTR, ADDR_NAME) (0) +#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) do { } while (0) +#define pci_unmap_len(PTR, LEN_NAME) (0) +#define pci_unmap_len_set(PTR, LEN_NAME, VAL) do { } while (0) + +#endif + +#include <asm-generic/pci-dma-compat.h> + +static inline dma64_addr_t +pci_dac_page_to_dma(struct pci_dev *pdev, struct page *page, unsigned long offset, int direction) +{ + return ((dma64_addr_t) page_to_phys(page) + + (dma64_addr_t) offset); +} + +static inline struct page * +pci_dac_dma_to_page(struct pci_dev *pdev, dma64_addr_t dma_addr) +{ + return virt_to_page(__va(dma_addr)); +} + +static inline unsigned long +pci_dac_dma_to_offset(struct pci_dev *pdev, dma64_addr_t dma_addr) +{ + return (dma_addr & ~PAGE_MASK); +} + +static inline void +pci_dac_dma_sync_single_for_cpu(struct pci_dev *pdev, dma64_addr_t dma_addr, size_t len, int direction) +{ +} + +static inline void +pci_dac_dma_sync_single_for_device(struct pci_dev *pdev, dma64_addr_t dma_addr, size_t len, int direction) +{ + flush_write_buffers(); +} + +#define HAVE_PCI_MMAP +extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, + enum pci_mmap_state mmap_state, int write_combine); + +static inline void pcibios_add_platform_entries(struct pci_dev *dev) +{ +} + +#endif /* __KERNEL__ */ + +/* generic pci stuff */ +#ifdef CONFIG_PCI +#include <asm-generic/pci.h> +#endif + +/* On Xen we have to scan all functions since Xen hides bridges from + * us. If a bridge is at fn=0 and that slot has a multifunction + * device, we won't find the additional devices without scanning all + * functions. */ +#undef pcibios_scan_all_fns +#define pcibios_scan_all_fns(a, b) 1 + +#endif /* __x8664_PCI_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/pgalloc.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/pgalloc.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,199 @@ +#ifndef _X86_64_PGALLOC_H +#define _X86_64_PGALLOC_H + +#include <asm/fixmap.h> +#include <asm/pda.h> +#include <linux/threads.h> +#include <linux/mm.h> +#include <asm/io.h> /* for phys_to_virt and page_to_pseudophys */ + +#include <xen/features.h> +void make_page_readonly(void *va, unsigned int feature); +void make_page_writable(void *va, unsigned int feature); +void make_pages_readonly(void *va, unsigned int nr, unsigned int feature); +void make_pages_writable(void *va, unsigned int nr, unsigned int feature); + +#define __user_pgd(pgd) ((pgd) + PTRS_PER_PGD) + +static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) +{ + set_pmd(pmd, __pmd(_PAGE_TABLE | __pa(pte))); +} + +static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte) +{ + if (unlikely((mm)->context.pinned)) { + BUG_ON(HYPERVISOR_update_va_mapping( + (unsigned long)__va(page_to_pfn(pte) << PAGE_SHIFT), + pfn_pte(page_to_pfn(pte), PAGE_KERNEL_RO), 0)); + set_pmd(pmd, __pmd(_PAGE_TABLE | (page_to_pfn(pte) << PAGE_SHIFT))); + } else { + *(pmd) = __pmd(_PAGE_TABLE | (page_to_pfn(pte) << PAGE_SHIFT)); + } +} + +static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) +{ + if (unlikely((mm)->context.pinned)) { + BUG_ON(HYPERVISOR_update_va_mapping( + (unsigned long)pmd, + pfn_pte(virt_to_phys(pmd)>>PAGE_SHIFT, + PAGE_KERNEL_RO), 0)); + set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd))); + } else { + *(pud) = __pud(_PAGE_TABLE | __pa(pmd)); + } +} + +/* + * We need to use the batch mode here, but pgd_pupulate() won't be + * be called frequently. + */ +static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) +{ + if (unlikely((mm)->context.pinned)) { + BUG_ON(HYPERVISOR_update_va_mapping( + (unsigned long)pud, + pfn_pte(virt_to_phys(pud)>>PAGE_SHIFT, + PAGE_KERNEL_RO), 0)); + set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(pud))); + set_pgd(__user_pgd(pgd), __pgd(_PAGE_TABLE | __pa(pud))); + } else { + *(pgd) = __pgd(_PAGE_TABLE | __pa(pud)); + *(__user_pgd(pgd)) = *(pgd); + } +} + +extern __inline__ void pmd_free(pmd_t *pmd) +{ + pte_t *ptep = virt_to_ptep(pmd); + + if (!pte_write(*ptep)) { + BUG_ON(HYPERVISOR_update_va_mapping( + (unsigned long)pmd, + pfn_pte(virt_to_phys(pmd)>>PAGE_SHIFT, PAGE_KERNEL), + 0)); + } + free_page((unsigned long)pmd); +} + +static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) +{ + pmd_t *pmd = (pmd_t *) get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); + return pmd; +} + +static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) +{ + pud_t *pud = (pud_t *) get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); + return pud; +} + +static inline void pud_free(pud_t *pud) +{ + pte_t *ptep = virt_to_ptep(pud); + + if (!pte_write(*ptep)) { + BUG_ON(HYPERVISOR_update_va_mapping( + (unsigned long)pud, + pfn_pte(virt_to_phys(pud)>>PAGE_SHIFT, PAGE_KERNEL), + 0)); + } + free_page((unsigned long)pud); +} + +static inline pgd_t *pgd_alloc(struct mm_struct *mm) +{ + /* + * We allocate two contiguous pages for kernel and user. + */ + unsigned boundary; + pgd_t *pgd = (pgd_t *)__get_free_pages(GFP_KERNEL|__GFP_REPEAT, 1); + + if (!pgd) + return NULL; + /* + * Copy kernel pointers in from init. + * Could keep a freelist or slab cache of those because the kernel + * part never changes. + */ + boundary = pgd_index(__PAGE_OFFSET); + memset(pgd, 0, boundary * sizeof(pgd_t)); + memcpy(pgd + boundary, + init_level4_pgt + boundary, + (PTRS_PER_PGD - boundary) * sizeof(pgd_t)); + + memset(__user_pgd(pgd), 0, PAGE_SIZE); /* clean up user pgd */ + /* + * Set level3_user_pgt for vsyscall area + */ + set_pgd(__user_pgd(pgd) + pgd_index(VSYSCALL_START), + mk_kernel_pgd(__pa_symbol(level3_user_pgt))); + return pgd; +} + +static inline void pgd_free(pgd_t *pgd) +{ + pte_t *ptep = virt_to_ptep(pgd); + + if (!pte_write(*ptep)) { + xen_pgd_unpin(__pa(pgd)); + BUG_ON(HYPERVISOR_update_va_mapping( + (unsigned long)pgd, + pfn_pte(virt_to_phys(pgd)>>PAGE_SHIFT, PAGE_KERNEL), + 0)); + } + + ptep = virt_to_ptep(__user_pgd(pgd)); + + if (!pte_write(*ptep)) { + xen_pgd_unpin(__pa(__user_pgd(pgd))); + BUG_ON(HYPERVISOR_update_va_mapping( + (unsigned long)__user_pgd(pgd), + pfn_pte(virt_to_phys(__user_pgd(pgd))>>PAGE_SHIFT, + PAGE_KERNEL), + 0)); + } + + free_pages((unsigned long)pgd, 1); +} + +static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) +{ + pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); + if (pte) + make_page_readonly(pte, XENFEAT_writable_page_tables); + + return pte; +} + +static inline struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address) +{ + struct page *pte; + + pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0); + return pte; +} + +/* Should really implement gc for free page table pages. This could be + done with a reference count in struct page. */ + +extern __inline__ void pte_free_kernel(pte_t *pte) +{ + BUG_ON((unsigned long)pte & (PAGE_SIZE-1)); + xen_pte_unpin(__pa(pte)); + make_page_writable(pte, XENFEAT_writable_page_tables); + free_page((unsigned long)pte); +} + +extern void pte_free(struct page *pte); + +//#define __pte_free_tlb(tlb,pte) tlb_remove_page((tlb),(pte)) +//#define __pmd_free_tlb(tlb,x) tlb_remove_page((tlb),virt_to_page(x)) +//#define __pud_free_tlb(tlb,x) tlb_remove_page((tlb),virt_to_page(x)) + +#define __pte_free_tlb(tlb,x) pte_free((x)) +#define __pmd_free_tlb(tlb,x) pmd_free((x)) +#define __pud_free_tlb(tlb,x) pud_free((x)) + +#endif /* _X86_64_PGALLOC_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/pgtable.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/pgtable.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,570 @@ +#ifndef _X86_64_PGTABLE_H +#define _X86_64_PGTABLE_H + +/* + * This file contains the functions and defines necessary to modify and use + * the x86-64 page table tree. + */ +#include <asm/processor.h> +#include <asm/fixmap.h> +#include <asm/bitops.h> +#include <linux/threads.h> +#include <linux/sched.h> +#include <asm/pda.h> +#ifdef CONFIG_XEN +#include <asm/hypervisor.h> + +extern pud_t level3_user_pgt[512]; +extern pud_t init_level4_user_pgt[]; + +extern void xen_init_pt(void); + +#define virt_to_ptep(__va) \ +({ \ + pgd_t *__pgd = pgd_offset_k((unsigned long)(__va)); \ + pud_t *__pud = pud_offset(__pgd, (unsigned long)(__va)); \ + pmd_t *__pmd = pmd_offset(__pud, (unsigned long)(__va)); \ + pte_offset_kernel(__pmd, (unsigned long)(__va)); \ +}) + +#define arbitrary_virt_to_machine(__va) \ +({ \ + maddr_t m = (maddr_t)pte_mfn(*virt_to_ptep(__va)) << PAGE_SHIFT;\ + m | ((unsigned long)(__va) & (PAGE_SIZE-1)); \ +}) +#endif + +extern pud_t level3_kernel_pgt[512]; +extern pud_t level3_physmem_pgt[512]; +extern pud_t level3_ident_pgt[512]; +extern pmd_t level2_kernel_pgt[512]; +extern pgd_t init_level4_pgt[]; +extern unsigned long __supported_pte_mask; + +#define swapper_pg_dir init_level4_pgt + +extern int nonx_setup(char *str); +extern void paging_init(void); +extern void clear_kernel_mapping(unsigned long addr, unsigned long size); + +extern unsigned long pgkern_mask; + +/* + * ZERO_PAGE is a global shared page that is always zero: used + * for zero-mapped memory areas etc.. + */ +extern unsigned long empty_zero_page[PAGE_SIZE/sizeof(unsigned long)]; +#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) + +/* + * PGDIR_SHIFT determines what a top-level page table entry can map + */ +#define PGDIR_SHIFT 39 +#define PTRS_PER_PGD 512 + +/* + * 3rd level page + */ +#define PUD_SHIFT 30 +#define PTRS_PER_PUD 512 + +/* + * PMD_SHIFT determines the size of the area a middle-level + * page table can map + */ +#define PMD_SHIFT 21 +#define PTRS_PER_PMD 512 + +/* + * entries per page directory level + */ +#define PTRS_PER_PTE 512 + +#define pte_ERROR(e) \ + printk("%s:%d: bad pte %p(%016lx).\n", __FILE__, __LINE__, &(e), pte_val(e)) +#define pmd_ERROR(e) \ + printk("%s:%d: bad pmd %p(%016lx).\n", __FILE__, __LINE__, &(e), pmd_val(e)) +#define pud_ERROR(e) \ + printk("%s:%d: bad pud %p(%016lx).\n", __FILE__, __LINE__, &(e), pud_val(e)) +#define pgd_ERROR(e) \ + printk("%s:%d: bad pgd %p(%016lx).\n", __FILE__, __LINE__, &(e), pgd_val(e)) + +#define pgd_none(x) (!pgd_val(x)) +#define pud_none(x) (!pud_val(x)) + +#define set_pte_batched(pteptr, pteval) \ + queue_l1_entry_update(pteptr, (pteval)) + +extern inline int pud_present(pud_t pud) { return !pud_none(pud); } + +static inline void set_pte(pte_t *dst, pte_t val) +{ + *dst = val; +} + +#define set_pmd(pmdptr, pmdval) xen_l2_entry_update(pmdptr, (pmdval)) +#define set_pud(pudptr, pudval) xen_l3_entry_update(pudptr, (pudval)) +#define set_pgd(pgdptr, pgdval) xen_l4_entry_update(pgdptr, (pgdval)) + +extern inline void pud_clear (pud_t * pud) +{ + set_pud(pud, __pud(0)); +} + +#define __user_pgd(pgd) ((pgd) + PTRS_PER_PGD) + +extern inline void pgd_clear (pgd_t * pgd) +{ + set_pgd(pgd, __pgd(0)); + set_pgd(__user_pgd(pgd), __pgd(0)); +} + +#define pud_page(pud) \ + ((unsigned long) __va(pud_val(pud) & PHYSICAL_PAGE_MASK)) + +/* + * A note on implementation of this atomic 'get-and-clear' operation. + * This is actually very simple because Xen Linux can only run on a single + * processor. Therefore, we cannot race other processors setting the 'accessed' + * or 'dirty' bits on a page-table entry. + * Even if pages are shared between domains, that is not a problem because + * each domain will have separate page tables, with their own versions of + * accessed & dirty state. + */ +#define ptep_get_and_clear(mm,addr,xp) __pte_ma(xchg(&(xp)->pte, 0)) + +#if 0 +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *xp) +{ + pte_t pte = *xp; + if (pte.pte) + set_pte(xp, __pte_ma(0)); + return pte; +} +#endif + +#define pte_same(a, b) ((a).pte == (b).pte) + +#define PMD_SIZE (1UL << PMD_SHIFT) +#define PMD_MASK (~(PMD_SIZE-1)) +#define PUD_SIZE (1UL << PUD_SHIFT) +#define PUD_MASK (~(PUD_SIZE-1)) +#define PGDIR_SIZE (1UL << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE-1)) + +#define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE) +#define FIRST_USER_ADDRESS 0 + +#ifndef __ASSEMBLY__ +#define MAXMEM 0x3fffffffffffUL +#define VMALLOC_START 0xffffc20000000000UL +#define VMALLOC_END 0xffffe1ffffffffffUL +#define MODULES_VADDR 0xffffffff88000000UL +#define MODULES_END 0xfffffffffff00000UL +#define MODULES_LEN (MODULES_END - MODULES_VADDR) + +#define _PAGE_BIT_PRESENT 0 +#define _PAGE_BIT_RW 1 +#define _PAGE_BIT_USER 2 +#define _PAGE_BIT_PWT 3 +#define _PAGE_BIT_PCD 4 +#define _PAGE_BIT_ACCESSED 5 +#define _PAGE_BIT_DIRTY 6 +#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */ +#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */ +#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ + +#define _PAGE_PRESENT 0x001 +#define _PAGE_RW 0x002 +#define _PAGE_USER 0x004 +#define _PAGE_PWT 0x008 +#define _PAGE_PCD 0x010 +#define _PAGE_ACCESSED 0x020 +#define _PAGE_DIRTY 0x040 +#define _PAGE_PSE 0x080 /* 2MB page */ +#define _PAGE_FILE 0x040 /* set:pagecache, unset:swap */ +#define _PAGE_GLOBAL 0x100 /* Global TLB entry */ + +#define _PAGE_PROTNONE 0x080 /* If not present */ +#define _PAGE_NX (1UL<<_PAGE_BIT_NX) + +#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY) +#define _KERNPG_TABLE _PAGE_TABLE + +#define _PAGE_CHG_MASK (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY) + +#define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED) +#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX) +#define PAGE_SHARED_EXEC __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED) +#define PAGE_COPY_NOEXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX) +#define PAGE_COPY PAGE_COPY_NOEXEC +#define PAGE_COPY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED) +#define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX) +#define PAGE_READONLY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED) +#define __PAGE_KERNEL \ + (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX | _PAGE_USER ) +#define __PAGE_KERNEL_EXEC \ + (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_USER ) +#define __PAGE_KERNEL_NOCACHE \ + (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_PCD | _PAGE_ACCESSED | _PAGE_NX | _PAGE_USER ) +#define __PAGE_KERNEL_RO \ + (_PAGE_PRESENT | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX | _PAGE_USER ) +#define __PAGE_KERNEL_VSYSCALL \ + (_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_USER ) +#define __PAGE_KERNEL_VSYSCALL_NOCACHE \ + (_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_PCD | _PAGE_USER ) +#define __PAGE_KERNEL_LARGE \ + (__PAGE_KERNEL | _PAGE_PSE | _PAGE_USER ) + + +/* + * We don't support GLOBAL page in xenolinux64 + */ +#define MAKE_GLOBAL(x) __pgprot((x)) + +#define PAGE_KERNEL MAKE_GLOBAL(__PAGE_KERNEL) +#define PAGE_KERNEL_EXEC MAKE_GLOBAL(__PAGE_KERNEL_EXEC) +#define PAGE_KERNEL_RO MAKE_GLOBAL(__PAGE_KERNEL_RO) +#define PAGE_KERNEL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE) +#define PAGE_KERNEL_VSYSCALL32 __pgprot(__PAGE_KERNEL_VSYSCALL) +#define PAGE_KERNEL_VSYSCALL MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL) +#define PAGE_KERNEL_LARGE MAKE_GLOBAL(__PAGE_KERNEL_LARGE) +#define PAGE_KERNEL_VSYSCALL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL_NOCACHE) + +/* xwr */ +#define __P000 PAGE_NONE +#define __P001 PAGE_READONLY +#define __P010 PAGE_COPY +#define __P011 PAGE_COPY +#define __P100 PAGE_READONLY_EXEC +#define __P101 PAGE_READONLY_EXEC +#define __P110 PAGE_COPY_EXEC +#define __P111 PAGE_COPY_EXEC + +#define __S000 PAGE_NONE +#define __S001 PAGE_READONLY +#define __S010 PAGE_SHARED +#define __S011 PAGE_SHARED +#define __S100 PAGE_READONLY_EXEC +#define __S101 PAGE_READONLY_EXEC +#define __S110 PAGE_SHARED_EXEC +#define __S111 PAGE_SHARED_EXEC + +static inline unsigned long pgd_bad(pgd_t pgd) +{ + unsigned long val = pgd_val(pgd); + val &= ~PTE_MASK; + val &= ~(_PAGE_USER | _PAGE_DIRTY); + return val & ~(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED); +} + +static inline unsigned long pud_bad(pud_t pud) +{ + unsigned long val = pud_val(pud); + val &= ~PTE_MASK; + val &= ~(_PAGE_USER | _PAGE_DIRTY); + return val & ~(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED); +} + +#define set_pte_at(_mm,addr,ptep,pteval) do { \ + if (((_mm) != current->mm && (_mm) != &init_mm) || \ + HYPERVISOR_update_va_mapping((addr), (pteval), 0)) \ + set_pte((ptep), (pteval)); \ +} while (0) + +#define pte_none(x) (!(x).pte) +#define pte_present(x) ((x).pte & (_PAGE_PRESENT | _PAGE_PROTNONE)) +#define pte_clear(mm,addr,xp) do { set_pte_at(mm, addr, xp, __pte(0)); } while (0) + +#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT)) + +/* + * We detect special mappings in one of two ways: + * 1. If the MFN is an I/O page then Xen will set the m2p entry + * to be outside our maximum possible pseudophys range. + * 2. If the MFN belongs to a different domain then we will certainly + * not have MFN in our p2m table. Conversely, if the page is ours, + * then we'll have p2m(m2p(MFN))==MFN. + * If we detect a special mapping then it doesn't have a 'struct page'. + * We force !pfn_valid() by returning an out-of-range pointer. + * + * NB. These checks require that, for any MFN that is not in our reservation, + * there is no PFN such that p2m(PFN) == MFN. Otherwise we can get confused if + * we are foreign-mapping the MFN, and the other domain as m2p(MFN) == PFN. + * Yikes! Various places must poke in INVALID_P2M_ENTRY for safety. + * + * NB2. When deliberately mapping foreign pages into the p2m table, you *must* + * use FOREIGN_FRAME(). This will cause pte_pfn() to choke on it, as we + * require. In all the cases we care about, the FOREIGN_FRAME bit is + * masked (e.g., pfn_to_mfn()) so behaviour there is correct. + */ +#define pte_mfn(_pte) (((_pte).pte & PTE_MASK) >> PAGE_SHIFT) +#define pte_pfn(_pte) \ +({ \ + unsigned long mfn = pte_mfn(_pte); \ + unsigned long pfn = mfn_to_pfn(mfn); \ + if ((pfn >= max_mapnr) || (phys_to_machine_mapping[pfn] != mfn))\ + pfn = max_mapnr; /* special: force !pfn_valid() */ \ + pfn; \ +}) + +#define pte_page(x) pfn_to_page(pte_pfn(x)) + +static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) +{ + pte_t pte; + + (pte).pte = (pfn_to_mfn(page_nr) << PAGE_SHIFT); + (pte).pte |= pgprot_val(pgprot); + (pte).pte &= __supported_pte_mask; + return pte; +} + +#define pfn_pte_ma(pfn, prot) __pte_ma((((pfn) << PAGE_SHIFT) | pgprot_val(prot)) & __supported_pte_mask) +/* + * The following only work if pte_present() is true. + * Undefined behaviour if not.. + */ +#define __pte_val(x) ((x).pte) + +static inline int pte_user(pte_t pte) { return __pte_val(pte) & _PAGE_USER; } +extern inline int pte_read(pte_t pte) { return __pte_val(pte) & _PAGE_USER; } +extern inline int pte_exec(pte_t pte) { return __pte_val(pte) & _PAGE_USER; } +extern inline int pte_dirty(pte_t pte) { return __pte_val(pte) & _PAGE_DIRTY; } +extern inline int pte_young(pte_t pte) { return __pte_val(pte) & _PAGE_ACCESSED; } +extern inline int pte_write(pte_t pte) { return __pte_val(pte) & _PAGE_RW; } +static inline int pte_file(pte_t pte) { return __pte_val(pte) & _PAGE_FILE; } + +extern inline pte_t pte_rdprotect(pte_t pte) { __pte_val(pte) &= ~_PAGE_USER; return pte; } +extern inline pte_t pte_exprotect(pte_t pte) { __pte_val(pte) &= ~_PAGE_USER; return pte; } +extern inline pte_t pte_mkclean(pte_t pte) { __pte_val(pte) &= ~_PAGE_DIRTY; return pte; } +extern inline pte_t pte_mkold(pte_t pte) { __pte_val(pte) &= ~_PAGE_ACCESSED; return pte; } +extern inline pte_t pte_wrprotect(pte_t pte) { __pte_val(pte) &= ~_PAGE_RW; return pte; } +extern inline pte_t pte_mkread(pte_t pte) { __pte_val(pte) |= _PAGE_USER; return pte; } +extern inline pte_t pte_mkexec(pte_t pte) { __pte_val(pte) |= _PAGE_USER; return pte; } +extern inline pte_t pte_mkdirty(pte_t pte) { __pte_val(pte) |= _PAGE_DIRTY; return pte; } +extern inline pte_t pte_mkyoung(pte_t pte) { __pte_val(pte) |= _PAGE_ACCESSED; return pte; } +extern inline pte_t pte_mkwrite(pte_t pte) { __pte_val(pte) |= _PAGE_RW; return pte; } + +struct vm_area_struct; + +static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +{ + pte_t pte = *ptep; + int ret = pte_dirty(pte); + if (ret) + set_pte(ptep, pte_mkclean(pte)); + return ret; +} + +static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +{ + pte_t pte = *ptep; + int ret = pte_young(pte); + if (ret) + set_pte(ptep, pte_mkold(pte)); + return ret; +} + +static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) +{ + pte_t pte = *ptep; + if (pte_write(pte)) + set_pte(ptep, pte_wrprotect(pte)); +} + +/* + * Macro to mark a page protection value as "uncacheable". + */ +#define pgprot_noncached(prot) (__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT)) + +#define __LARGE_PTE (_PAGE_PSE|_PAGE_PRESENT) +static inline int pmd_large(pmd_t pte) { + return (pmd_val(pte) & __LARGE_PTE) == __LARGE_PTE; +} + + +/* + * Conversion functions: convert a page and protection to a page entry, + * and a page entry and page directory to the page they refer to. + */ + +#define page_pte(page) page_pte_prot(page, __pgprot(0)) + +/* + * Level 4 access. + * Never use these in the common code. + */ +#define pgd_page(pgd) ((unsigned long) __va(pgd_val(pgd) & PTE_MASK)) +#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1)) +#define pgd_offset(mm, addr) ((mm)->pgd + pgd_index(addr)) +#define pgd_offset_k(address) (pgd_t *)(init_level4_pgt + pgd_index(address)) +#define pgd_present(pgd) (pgd_val(pgd) & _PAGE_PRESENT) +#define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE) + +/* PUD - Level3 access */ +/* to find an entry in a page-table-directory. */ +#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) +#define pud_offset(pgd, address) ((pud_t *) pgd_page(*(pgd)) + pud_index(address)) +static inline pud_t *__pud_offset_k(pud_t *pud, unsigned long address) +{ + return pud + pud_index(address); +} + +/* Find correct pud via the hidden fourth level page level: */ + +/* This accesses the reference page table of the boot cpu. + Other CPUs get synced lazily via the page fault handler. */ +static inline pud_t *pud_offset_k(unsigned long address) +{ + return pud_offset(pgd_offset_k(address), address); +} + +/* PMD - Level 2 access */ +#define pmd_page_kernel(pmd) ((unsigned long) __va(pmd_val(pmd) & PTE_MASK)) +#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)) + +#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1)) +#define pmd_offset(dir, address) ((pmd_t *) pud_page(*(dir)) + \ + pmd_index(address)) +#define pmd_none(x) (!pmd_val(x)) +/* pmd_present doesn't just test the _PAGE_PRESENT bit since wr.p.t. + can temporarily clear it. */ +#define pmd_present(x) (pmd_val(x)) +#define pmd_clear(xp) do { set_pmd(xp, __pmd(0)); } while (0) +#define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_PRESENT)) != (_KERNPG_TABLE & ~_PAGE_PRESENT)) +#define pfn_pmd(nr,prot) (__pmd(((nr) << PAGE_SHIFT) | pgprot_val(prot))) +#define pmd_pfn(x) ((pmd_val(x) >> PAGE_SHIFT) & __PHYSICAL_MASK) + +#define pte_to_pgoff(pte) ((pte_val(pte) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT) +#define pgoff_to_pte(off) ((pte_t) { ((off) << PAGE_SHIFT) | _PAGE_FILE }) +#define PTE_FILE_MAX_BITS __PHYSICAL_MASK_SHIFT + +/* PTE - Level 1 access. */ + +/* page, protection -> pte */ +#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot)) +#define mk_pte_huge(entry) (pte_val(entry) |= _PAGE_PRESENT | _PAGE_PSE) + +/* physical address -> PTE */ +static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot) +{ + pte_t pte; + (pte).pte = physpage | pgprot_val(pgprot); + return pte; +} + +/* Change flags of a PTE */ +extern inline pte_t pte_modify(pte_t pte, pgprot_t newprot) +{ + (pte).pte &= _PAGE_CHG_MASK; + (pte).pte |= pgprot_val(newprot); + (pte).pte &= __supported_pte_mask; + return pte; +} + +#define pte_index(address) \ + ((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) +#define pte_offset_kernel(dir, address) ((pte_t *) pmd_page_kernel(*(dir)) + \ + pte_index(address)) + +/* x86-64 always has all page tables mapped. */ +#define pte_offset_map(dir,address) pte_offset_kernel(dir,address) +#define pte_offset_map_nested(dir,address) pte_offset_kernel(dir,address) +#define pte_unmap(pte) /* NOP */ +#define pte_unmap_nested(pte) /* NOP */ + +#define update_mmu_cache(vma,address,pte) do { } while (0) + +/* We only update the dirty/accessed state if we set + * the dirty bit by hand in the kernel, since the hardware + * will do the accessed bit for us, and we don't want to + * race with other CPU's that might be updating the dirty + * bit at the same time. */ +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +#if 0 +#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \ + do { \ + if (__dirty) { \ + set_pte(__ptep, __entry); \ + flush_tlb_page(__vma, __address); \ + } \ + } while (0) +#endif +#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \ + do { \ + if (__dirty) { \ + if ( likely((__vma)->vm_mm == current->mm) ) { \ + BUG_ON(HYPERVISOR_update_va_mapping((__address), (__entry), UVMF_INVLPG|UVMF_MULTI|(unsigned long)((__vma)->vm_mm->cpu_vm_mask.bits))); \ + } else { \ + xen_l1_entry_update((__ptep), (__entry)); \ + flush_tlb_page((__vma), (__address)); \ + } \ + } \ + } while (0) + +/* Encode and de-code a swap entry */ +#define __swp_type(x) (((x).val >> 1) & 0x3f) +#define __swp_offset(x) ((x).val >> 8) +#define __swp_entry(type, offset) ((swp_entry_t) { ((type) << 1) | ((offset) << 8) }) +#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) +#define __swp_entry_to_pte(x) ((pte_t) { (x).val }) + +#endif /* !__ASSEMBLY__ */ + +extern int kern_addr_valid(unsigned long addr); + +#define DOMID_LOCAL (0xFFFFU) + +int direct_remap_pfn_range(struct vm_area_struct *vma, + unsigned long address, + unsigned long mfn, + unsigned long size, + pgprot_t prot, + domid_t domid); + +int direct_kernel_remap_pfn_range(unsigned long address, + unsigned long mfn, + unsigned long size, + pgprot_t prot, + domid_t domid); + +int create_lookup_pte_addr(struct mm_struct *mm, + unsigned long address, + uint64_t *ptep); + +int touch_pte_range(struct mm_struct *mm, + unsigned long address, + unsigned long size); + +#define io_remap_page_range(vma, vaddr, paddr, size, prot) \ + direct_remap_pfn_range(vma,vaddr,(paddr)>>PAGE_SHIFT,size,prot,DOMID_IO) + +#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \ + direct_remap_pfn_range(vma,vaddr,pfn,size,prot,DOMID_IO) + +#define MK_IOSPACE_PFN(space, pfn) (pfn) +#define GET_IOSPACE(pfn) 0 +#define GET_PFN(pfn) (pfn) + +#define HAVE_ARCH_UNMAPPED_AREA + +#define pgtable_cache_init() do { } while (0) +#define check_pgt_cache() do { } while (0) + +#define PAGE_AGP PAGE_KERNEL_NOCACHE +#define HAVE_PAGE_AGP 1 + +/* fs/proc/kcore.c */ +#define kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK) +#define kc_offset_to_vaddr(o) \ + (((o) & (1UL << (__VIRTUAL_MASK_SHIFT-1))) ? ((o) | (~__VIRTUAL_MASK)) : (o)) + +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +#define __HAVE_ARCH_PTEP_SET_WRPROTECT +#define __HAVE_ARCH_PTE_SAME +#include <asm-generic/pgtable.h> + +#endif /* _X86_64_PGTABLE_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/processor.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/processor.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,486 @@ +/* + * include/asm-x86_64/processor.h + * + * Copyright (C) 1994 Linus Torvalds + */ + +#ifndef __ASM_X86_64_PROCESSOR_H +#define __ASM_X86_64_PROCESSOR_H + +#include <asm/segment.h> +#include <asm/page.h> +#include <asm/types.h> +#include <asm/sigcontext.h> +#include <asm/cpufeature.h> +#include <linux/config.h> +#include <linux/threads.h> +#include <asm/msr.h> +#include <asm/current.h> +#include <asm/system.h> +#include <asm/mmsegment.h> +#include <asm/percpu.h> +#include <linux/personality.h> + +#define TF_MASK 0x00000100 +#define IF_MASK 0x00000200 +#define IOPL_MASK 0x00003000 +#define NT_MASK 0x00004000 +#define VM_MASK 0x00020000 +#define AC_MASK 0x00040000 +#define VIF_MASK 0x00080000 /* virtual interrupt flag */ +#define VIP_MASK 0x00100000 /* virtual interrupt pending */ +#define ID_MASK 0x00200000 + +#define desc_empty(desc) \ + (!((desc)->a + (desc)->b)) + +#define desc_equal(desc1, desc2) \ + (((desc1)->a == (desc2)->a) && ((desc1)->b == (desc2)->b)) + +/* + * Default implementation of macro that returns current + * instruction pointer ("program counter"). + */ +#define current_text_addr() ({ void *pc; asm volatile("leaq 1f(%%rip),%0\n1:":"=r"(pc)); pc; }) + +/* + * CPU type and hardware bug flags. Kept separately for each CPU. + */ + +struct cpuinfo_x86 { + __u8 x86; /* CPU family */ + __u8 x86_vendor; /* CPU vendor */ + __u8 x86_model; + __u8 x86_mask; + int cpuid_level; /* Maximum supported CPUID level, -1=no CPUID */ + __u32 x86_capability[NCAPINTS]; + char x86_vendor_id[16]; + char x86_model_id[64]; + int x86_cache_size; /* in KB */ + int x86_clflush_size; + int x86_cache_alignment; + int x86_tlbsize; /* number of 4K pages in DTLB/ITLB combined(in pages)*/ + __u8 x86_virt_bits, x86_phys_bits; + __u8 x86_num_cores; + __u32 x86_power; + __u32 extended_cpuid_level; /* Max extended CPUID function supported */ + unsigned long loops_per_jiffy; +} ____cacheline_aligned; + +#define X86_VENDOR_INTEL 0 +#define X86_VENDOR_CYRIX 1 +#define X86_VENDOR_AMD 2 +#define X86_VENDOR_UMC 3 +#define X86_VENDOR_NEXGEN 4 +#define X86_VENDOR_CENTAUR 5 +#define X86_VENDOR_RISE 6 +#define X86_VENDOR_TRANSMETA 7 +#define X86_VENDOR_NUM 8 +#define X86_VENDOR_UNKNOWN 0xff + +#ifdef CONFIG_SMP +extern struct cpuinfo_x86 cpu_data[]; +#define current_cpu_data cpu_data[smp_processor_id()] +#else +#define cpu_data (&boot_cpu_data) +#define current_cpu_data boot_cpu_data +#endif + +extern char ignore_irq13; + +extern void identify_cpu(struct cpuinfo_x86 *); +extern void print_cpu_info(struct cpuinfo_x86 *); +extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c); + +/* + * EFLAGS bits + */ +#define X86_EFLAGS_CF 0x00000001 /* Carry Flag */ +#define X86_EFLAGS_PF 0x00000004 /* Parity Flag */ +#define X86_EFLAGS_AF 0x00000010 /* Auxillary carry Flag */ +#define X86_EFLAGS_ZF 0x00000040 /* Zero Flag */ +#define X86_EFLAGS_SF 0x00000080 /* Sign Flag */ +#define X86_EFLAGS_TF 0x00000100 /* Trap Flag */ +#define X86_EFLAGS_IF 0x00000200 /* Interrupt Flag */ +#define X86_EFLAGS_DF 0x00000400 /* Direction Flag */ +#define X86_EFLAGS_OF 0x00000800 /* Overflow Flag */ +#define X86_EFLAGS_IOPL 0x00003000 /* IOPL mask */ +#define X86_EFLAGS_NT 0x00004000 /* Nested Task */ +#define X86_EFLAGS_RF 0x00010000 /* Resume Flag */ +#define X86_EFLAGS_VM 0x00020000 /* Virtual Mode */ +#define X86_EFLAGS_AC 0x00040000 /* Alignment Check */ +#define X86_EFLAGS_VIF 0x00080000 /* Virtual Interrupt Flag */ +#define X86_EFLAGS_VIP 0x00100000 /* Virtual Interrupt Pending */ +#define X86_EFLAGS_ID 0x00200000 /* CPUID detection flag */ + +/* + * Intel CPU features in CR4 + */ +#define X86_CR4_VME 0x0001 /* enable vm86 extensions */ +#define X86_CR4_PVI 0x0002 /* virtual interrupts flag enable */ +#define X86_CR4_TSD 0x0004 /* disable time stamp at ipl 3 */ +#define X86_CR4_DE 0x0008 /* enable debugging extensions */ +#define X86_CR4_PSE 0x0010 /* enable page size extensions */ +#define X86_CR4_PAE 0x0020 /* enable physical address extensions */ +#define X86_CR4_MCE 0x0040 /* Machine check enable */ +#define X86_CR4_PGE 0x0080 /* enable global pages */ +#define X86_CR4_PCE 0x0100 /* enable performance counters at ipl 3 */ +#define X86_CR4_OSFXSR 0x0200 /* enable fast FPU save and restore */ +#define X86_CR4_OSXMMEXCPT 0x0400 /* enable unmasked SSE exceptions */ + +/* + * Save the cr4 feature set we're using (ie + * Pentium 4MB enable and PPro Global page + * enable), so that any CPU's that boot up + * after us can get the correct flags. + */ +extern unsigned long mmu_cr4_features; + +static inline void set_in_cr4 (unsigned long mask) +{ + mmu_cr4_features |= mask; + switch (mask) { + case X86_CR4_OSFXSR: + case X86_CR4_OSXMMEXCPT: + break; + default: + do { + const char *msg = "Xen unsupported cr4 update\n"; + (void)HYPERVISOR_console_io( + CONSOLEIO_write, __builtin_strlen(msg), + (char *)msg); + BUG(); + } while (0); + } +} + + +static inline void clear_in_cr4 (unsigned long mask) +{ +#ifndef CONFIG_XEN + mmu_cr4_features &= ~mask; + __asm__("movq %%cr4,%%rax\n\t" + "andq %0,%%rax\n\t" + "movq %%rax,%%cr4\n" + : : "irg" (~mask) + :"ax"); +#endif +} + + +#define load_cr3(pgdir) do { \ + xen_pt_switch(__pa(pgdir)); \ + per_cpu(cur_pgd, smp_processor_id()) = pgdir; \ +} while (/* CONSTCOND */0) + +/* + * Bus types + */ +#define MCA_bus 0 +#define MCA_bus__is_a_macro + + +/* + * User space process size. 47bits minus one guard page. + */ +#define TASK_SIZE (0x800000000000UL - 4096) + +/* This decides where the kernel will search for a free chunk of vm + * space during mmap's. + */ +#define IA32_PAGE_OFFSET ((current->personality & ADDR_LIMIT_3GB) ? 0xc0000000 : 0xFFFFe000) +#define TASK_UNMAPPED_32 PAGE_ALIGN(IA32_PAGE_OFFSET/3) +#define TASK_UNMAPPED_64 PAGE_ALIGN(TASK_SIZE/3) +#define TASK_UNMAPPED_BASE \ + (test_thread_flag(TIF_IA32) ? TASK_UNMAPPED_32 : TASK_UNMAPPED_64) + +/* + * Size of io_bitmap. + */ +#define IO_BITMAP_BITS 65536 +#define IO_BITMAP_BYTES (IO_BITMAP_BITS/8) +#define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long)) +#define IO_BITMAP_OFFSET offsetof(struct tss_struct,io_bitmap) +#define INVALID_IO_BITMAP_OFFSET 0x8000 + +struct i387_fxsave_struct { + u16 cwd; + u16 swd; + u16 twd; + u16 fop; + u64 rip; + u64 rdp; + u32 mxcsr; + u32 mxcsr_mask; + u32 st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */ + u32 xmm_space[64]; /* 16*16 bytes for each XMM-reg = 128 bytes */ + u32 padding[24]; +} __attribute__ ((aligned (16))); + +union i387_union { + struct i387_fxsave_struct fxsave; +}; + +struct tss_struct { + u32 reserved1; + u64 rsp0; + u64 rsp1; + u64 rsp2; + u64 reserved2; + u64 ist[7]; + u32 reserved3; + u32 reserved4; + u16 reserved5; + u16 io_bitmap_base; + /* + * The extra 1 is there because the CPU will access an + * additional byte beyond the end of the IO permission + * bitmap. The extra byte must be all 1 bits, and must + * be within the limit. Thus we have: + * + * 128 bytes, the bitmap itself, for ports 0..0x3ff + * 8 bytes, for an extra "long" of ~0UL + */ + unsigned long io_bitmap[IO_BITMAP_LONGS + 1]; +} __attribute__((packed)) ____cacheline_aligned; + +extern struct cpuinfo_x86 boot_cpu_data; +DECLARE_PER_CPU(struct tss_struct,init_tss); +DECLARE_PER_CPU(pgd_t *, cur_pgd); + +#define ARCH_MIN_TASKALIGN 16 + +struct thread_struct { + unsigned long rsp0; + unsigned long rsp; + unsigned long userrsp; /* Copy from PDA */ + unsigned long fs; + unsigned long gs; + unsigned int io_pl; + unsigned short es, ds, fsindex, gsindex; +/* Hardware debugging registers */ + unsigned long debugreg0; + unsigned long debugreg1; + unsigned long debugreg2; + unsigned long debugreg3; + unsigned long debugreg6; + unsigned long debugreg7; +/* fault info */ + unsigned long cr2, trap_no, error_code; +/* floating point info */ + union i387_union i387 __attribute__((aligned(16))); +/* IO permissions. the bitmap could be moved into the GDT, that would make + switch faster for a limited number of ioperm using tasks. -AK */ + int ioperm; + unsigned long *io_bitmap_ptr; + unsigned io_bitmap_max; +/* cached TLS descriptors. */ + u64 tls_array[GDT_ENTRY_TLS_ENTRIES]; +} __attribute__((aligned(16))); + +#define INIT_THREAD {} + +#define INIT_MMAP \ +{ &init_mm, 0, 0, NULL, PAGE_SHARED, VM_READ | VM_WRITE | VM_EXEC, 1, NULL, NULL } + +#define STACKFAULT_STACK 1 +#define DOUBLEFAULT_STACK 2 +#define NMI_STACK 3 +#define DEBUG_STACK 4 +#define MCE_STACK 5 +#define N_EXCEPTION_STACKS 5 /* hw limit: 7 */ +#define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER) +#define EXCEPTION_STACK_ORDER 0 + +#define start_thread(regs,new_rip,new_rsp) do { \ + asm volatile("movl %0,%%fs; movl %0,%%es; movl %0,%%ds": :"r" (0)); \ + load_gs_index(0); \ + (regs)->rip = (new_rip); \ + (regs)->rsp = (new_rsp); \ + write_pda(oldrsp, (new_rsp)); \ + (regs)->cs = __USER_CS; \ + (regs)->ss = __USER_DS; \ + (regs)->eflags = 0x200; \ + set_fs(USER_DS); \ +} while(0) + +struct task_struct; +struct mm_struct; + +/* Free all resources held by a thread. */ +extern void release_thread(struct task_struct *); + +/* Prepare to copy thread state - unlazy all lazy status */ +extern void prepare_to_copy(struct task_struct *tsk); + +/* + * create a kernel thread without removing it from tasklists + */ +extern long kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); + +/* + * Return saved PC of a blocked thread. + * What is this good for? it will be always the scheduler or ret_from_fork. + */ +#define thread_saved_pc(t) (*(unsigned long *)((t)->thread.rsp - 8)) + +extern unsigned long get_wchan(struct task_struct *p); +#define KSTK_EIP(tsk) \ + (((struct pt_regs *)(tsk->thread.rsp0 - sizeof(struct pt_regs)))->rip) +#define KSTK_ESP(tsk) -1 /* sorry. doesn't work for syscall. */ + + +struct microcode_header { + unsigned int hdrver; + unsigned int rev; + unsigned int date; + unsigned int sig; + unsigned int cksum; + unsigned int ldrver; + unsigned int pf; + unsigned int datasize; + unsigned int totalsize; + unsigned int reserved[3]; +}; + +struct microcode { + struct microcode_header hdr; + unsigned int bits[0]; +}; + +typedef struct microcode microcode_t; +typedef struct microcode_header microcode_header_t; + +/* microcode format is extended from prescott processors */ +struct extended_signature { + unsigned int sig; + unsigned int pf; + unsigned int cksum; +}; + +struct extended_sigtable { + unsigned int count; + unsigned int cksum; + unsigned int reserved[3]; + struct extended_signature sigs[0]; +}; + +/* '6' because it used to be for P6 only (but now covers Pentium 4 as well) */ +#define MICROCODE_IOCFREE _IO('6',0) + + +#define ASM_NOP1 K8_NOP1 +#define ASM_NOP2 K8_NOP2 +#define ASM_NOP3 K8_NOP3 +#define ASM_NOP4 K8_NOP4 +#define ASM_NOP5 K8_NOP5 +#define ASM_NOP6 K8_NOP6 +#define ASM_NOP7 K8_NOP7 +#define ASM_NOP8 K8_NOP8 + +/* Opteron nops */ +#define K8_NOP1 ".byte 0x90\n" +#define K8_NOP2 ".byte 0x66,0x90\n" +#define K8_NOP3 ".byte 0x66,0x66,0x90\n" +#define K8_NOP4 ".byte 0x66,0x66,0x66,0x90\n" +#define K8_NOP5 K8_NOP3 K8_NOP2 +#define K8_NOP6 K8_NOP3 K8_NOP3 +#define K8_NOP7 K8_NOP4 K8_NOP3 +#define K8_NOP8 K8_NOP4 K8_NOP4 + +#define ASM_NOP_MAX 8 + +/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ +extern inline void rep_nop(void) +{ + __asm__ __volatile__("rep;nop": : :"memory"); +} + +/* Stop speculative execution */ +extern inline void sync_core(void) +{ + int tmp; + asm volatile("cpuid" : "=a" (tmp) : "0" (1) : "ebx","ecx","edx","memory"); +} + +#define cpu_has_fpu 1 + +#define ARCH_HAS_PREFETCH +static inline void prefetch(void *x) +{ + asm volatile("prefetcht0 %0" :: "m" (*(unsigned long *)x)); +} + +#define ARCH_HAS_PREFETCHW 1 +static inline void prefetchw(void *x) +{ + alternative_input(ASM_NOP5, + "prefetchw (%1)", + X86_FEATURE_3DNOW, + "r" (x)); +} + +#define ARCH_HAS_SPINLOCK_PREFETCH 1 + +#define spin_lock_prefetch(x) prefetchw(x) + +#define cpu_relax() rep_nop() + +/* + * NSC/Cyrix CPU configuration register indexes + */ +#define CX86_CCR0 0xc0 +#define CX86_CCR1 0xc1 +#define CX86_CCR2 0xc2 +#define CX86_CCR3 0xc3 +#define CX86_CCR4 0xe8 +#define CX86_CCR5 0xe9 +#define CX86_CCR6 0xea +#define CX86_CCR7 0xeb +#define CX86_DIR0 0xfe +#define CX86_DIR1 0xff +#define CX86_ARR_BASE 0xc4 +#define CX86_RCR_BASE 0xdc + +/* + * NSC/Cyrix CPU indexed register access macros + */ + +#define getCx86(reg) ({ outb((reg), 0x22); inb(0x23); }) + +#define setCx86(reg, data) do { \ + outb((reg), 0x22); \ + outb((data), 0x23); \ +} while (0) + +static inline void __monitor(const void *eax, unsigned long ecx, + unsigned long edx) +{ + /* "monitor %eax,%ecx,%edx;" */ + asm volatile( + ".byte 0x0f,0x01,0xc8;" + : :"a" (eax), "c" (ecx), "d"(edx)); +} + +static inline void __mwait(unsigned long eax, unsigned long ecx) +{ + /* "mwait %eax,%ecx;" */ + asm volatile( + ".byte 0x0f,0x01,0xc9;" + : :"a" (eax), "c" (ecx)); +} + +#define stack_current() \ +({ \ + struct thread_info *ti; \ + asm("andq %%rsp,%0; ":"=r" (ti) : "0" (CURRENT_MASK)); \ + ti->task; \ +}) + +#define cache_line_size() (boot_cpu_data.x86_cache_alignment) + +extern unsigned long boot_option_idle_override; +/* Boot loader type from the setup header */ +extern int bootloader_type; + +#endif /* __ASM_X86_64_PROCESSOR_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/ptrace.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/ptrace.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,124 @@ +#ifndef _X86_64_PTRACE_H +#define _X86_64_PTRACE_H + +#if defined(__ASSEMBLY__) || defined(__FRAME_OFFSETS) +#define R15 0 +#define R14 8 +#define R13 16 +#define R12 24 +#define RBP 32 +#define RBX 40 +/* arguments: interrupts/non tracing syscalls only save upto here*/ +#define R11 48 +#define R10 56 +#define R9 64 +#define R8 72 +#define RAX 80 +#define RCX 88 +#define RDX 96 +#define RSI 104 +#define RDI 112 +#define ORIG_RAX 120 /* = ERROR */ +/* end of arguments */ +/* cpu exception frame or undefined in case of fast syscall. */ +#define RIP 128 +#define CS 136 +#define EFLAGS 144 +#define RSP 152 +#define SS 160 +#define ARGOFFSET R11 +#endif /* __ASSEMBLY__ */ + +/* top of stack page */ +#define FRAME_SIZE 168 + +#define PTRACE_OLDSETOPTIONS 21 + +#ifndef __ASSEMBLY__ + +struct pt_regs { + unsigned long r15; + unsigned long r14; + unsigned long r13; + unsigned long r12; + unsigned long rbp; + unsigned long rbx; +/* arguments: non interrupts/non tracing syscalls only save upto here*/ + unsigned long r11; + unsigned long r10; + unsigned long r9; + unsigned long r8; + unsigned long rax; + unsigned long rcx; + unsigned long rdx; + unsigned long rsi; + unsigned long rdi; + unsigned long orig_rax; +/* end of arguments */ +/* cpu exception frame or undefined */ + unsigned long rip; + unsigned long cs; + unsigned long eflags; + unsigned long rsp; + unsigned long ss; +/* top of stack page */ +}; + +#endif + +/* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */ +#define PTRACE_GETREGS 12 +#define PTRACE_SETREGS 13 +#define PTRACE_GETFPREGS 14 +#define PTRACE_SETFPREGS 15 +#define PTRACE_GETFPXREGS 18 +#define PTRACE_SETFPXREGS 19 + +/* only useful for access 32bit programs */ +#define PTRACE_GET_THREAD_AREA 25 +#define PTRACE_SET_THREAD_AREA 26 + +#define PTRACE_ARCH_PRCTL 30 /* arch_prctl for child */ + +#if defined(__KERNEL__) && !defined(__ASSEMBLY__) +#define user_mode(regs) (!!((regs)->cs & 3)) +#define instruction_pointer(regs) ((regs)->rip) +#if defined(CONFIG_SMP) && defined(CONFIG_FRAME_POINTER) +extern unsigned long profile_pc(struct pt_regs *regs); +#else +#define profile_pc(regs) instruction_pointer(regs) +#endif + +void signal_fault(struct pt_regs *regs, void __user *frame, char *where); + +struct task_struct; + +extern unsigned long +convert_rip_to_linear(struct task_struct *child, struct pt_regs *regs); + +enum { + EF_CF = 0x00000001, + EF_PF = 0x00000004, + EF_AF = 0x00000010, + EF_ZF = 0x00000040, + EF_SF = 0x00000080, + EF_TF = 0x00000100, + EF_IE = 0x00000200, + EF_DF = 0x00000400, + EF_OF = 0x00000800, + EF_IOPL = 0x00003000, + EF_IOPL_RING0 = 0x00000000, + EF_IOPL_RING1 = 0x00001000, + EF_IOPL_RING2 = 0x00002000, + EF_NT = 0x00004000, /* nested task */ + EF_RF = 0x00010000, /* resume */ + EF_VM = 0x00020000, /* virtual mode */ + EF_AC = 0x00040000, /* alignment */ + EF_VIF = 0x00080000, /* virtual interrupt */ + EF_VIP = 0x00100000, /* virtual interrupt pending */ + EF_ID = 0x00200000, /* id */ +}; + +#endif + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/segment.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/segment.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,46 @@ +#ifndef _ASM_SEGMENT_H +#define _ASM_SEGMENT_H + +#include <asm/cache.h> + +#define __KERNEL_CS 0x10 +#define __KERNEL_DS 0x1b + +#define __KERNEL32_CS 0x3b + +/* + * we cannot use the same code segment descriptor for user and kernel + * -- not even in the long flat mode, because of different DPL /kkeil + * The segment offset needs to contain a RPL. Grr. -AK + * GDT layout to get 64bit syscall right (sysret hardcodes gdt offsets) + */ + +#define __USER32_CS 0x23 /* 4*8+3 */ +#define __USER_DS 0x2b /* 5*8+3 */ +#define __USER_CS 0x33 /* 6*8+3 */ +#define __USER32_DS __USER_DS +#define __KERNEL16_CS (GDT_ENTRY_KERNELCS16 * 8) +#define __KERNEL_COMPAT32_CS 0x8 + +#define GDT_ENTRY_TLS 1 +#define GDT_ENTRY_TSS 8 /* needs two entries */ +#define GDT_ENTRY_LDT 10 /* needs two entries */ +#define GDT_ENTRY_TLS_MIN 12 +#define GDT_ENTRY_TLS_MAX 14 +#define GDT_ENTRY_KERNELCS16 15 + +#define GDT_ENTRY_TLS_ENTRIES 3 + +/* TLS indexes for 64bit - hardcoded in arch_prctl */ +#define FS_TLS 0 +#define GS_TLS 1 + +#define GS_TLS_SEL ((GDT_ENTRY_TLS_MIN+GS_TLS)*8 + 3) +#define FS_TLS_SEL ((GDT_ENTRY_TLS_MIN+FS_TLS)*8 + 3) + +#define IDT_ENTRIES 256 +#define GDT_ENTRIES 16 +#define GDT_SIZE (GDT_ENTRIES * 8) +#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8) + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/smp.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/smp.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,138 @@ +#ifndef __ASM_SMP_H +#define __ASM_SMP_H + +/* + * We need the APIC definitions automatically as part of 'smp.h' + */ +#ifndef __ASSEMBLY__ +#include <linux/config.h> +#include <linux/threads.h> +#include <linux/cpumask.h> +#include <linux/bitops.h> +extern int disable_apic; +#endif + +#ifdef CONFIG_X86_LOCAL_APIC +#ifndef __ASSEMBLY__ +#include <asm/fixmap.h> +#include <asm/mpspec.h> +#ifdef CONFIG_X86_IO_APIC +#include <asm/io_apic.h> +#endif +#include <asm/apic.h> +#include <asm/thread_info.h> +#endif +#endif + +#ifdef CONFIG_SMP +#ifndef ASSEMBLY + +#include <asm/pda.h> + +struct pt_regs; + +extern cpumask_t cpu_present_mask; +extern cpumask_t cpu_possible_map; +extern cpumask_t cpu_online_map; + +/* + * Private routines/data + */ + +extern void smp_alloc_memory(void); +extern volatile unsigned long smp_invalidate_needed; +extern int pic_mode; +extern int smp_num_siblings; +extern void smp_flush_tlb(void); +extern void smp_message_irq(int cpl, void *dev_id, struct pt_regs *regs); +extern void smp_send_reschedule(int cpu); +extern void smp_invalidate_rcv(void); /* Process an NMI */ +extern void zap_low_mappings(void); +void smp_stop_cpu(void); +extern cpumask_t cpu_sibling_map[NR_CPUS]; +extern cpumask_t cpu_core_map[NR_CPUS]; +extern int phys_proc_id[NR_CPUS]; +extern int cpu_core_id[NR_CPUS]; + +#define SMP_TRAMPOLINE_BASE 0x6000 + +/* + * On x86 all CPUs are mapped 1:1 to the APIC space. + * This simplifies scheduling and IPI sending and + * compresses data structures. + */ + +static inline int num_booting_cpus(void) +{ + return cpus_weight(cpu_possible_map); +} + +#define __smp_processor_id() read_pda(cpunumber) + +#ifdef CONFIG_X86_LOCAL_APIC +extern __inline int hard_smp_processor_id(void) +{ + /* we don't want to mark this access volatile - bad code generation */ + return GET_APIC_ID(*(unsigned int *)(APIC_BASE+APIC_ID)); +} +#endif + +extern int safe_smp_processor_id(void); + +#endif /* !ASSEMBLY */ + +#define NO_PROC_ID 0xFF /* No processor magic marker */ + +#endif + +#ifndef ASSEMBLY +/* + * Some lowlevel functions might want to know about + * the real APIC ID <-> CPU # mapping. + */ +extern u8 x86_cpu_to_apicid[NR_CPUS]; /* physical ID */ +extern u8 x86_cpu_to_log_apicid[NR_CPUS]; +extern u8 bios_cpu_apicid[]; +#ifdef CONFIG_X86_LOCAL_APIC +static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask) +{ + return cpus_addr(cpumask)[0]; +} + +static inline int cpu_present_to_apicid(int mps_cpu) +{ + if (mps_cpu < NR_CPUS) + return (int)bios_cpu_apicid[mps_cpu]; + else + return BAD_APICID; +} +#endif + +#endif /* !ASSEMBLY */ + +#ifndef CONFIG_SMP +#define stack_smp_processor_id() 0 +#define safe_smp_processor_id() 0 +#define cpu_logical_map(x) (x) +#else +#include <asm/thread_info.h> +#define stack_smp_processor_id() \ +({ \ + struct thread_info *ti; \ + __asm__("andq %%rsp,%0; ":"=r" (ti) : "0" (CURRENT_MASK)); \ + ti->cpu; \ +}) +#endif + +#ifndef __ASSEMBLY__ +#ifdef CONFIG_X86_LOCAL_APIC +static __inline int logical_smp_processor_id(void) +{ + /* we don't want to mark this access volatile - bad code generation */ + return GET_APIC_LOGICAL_ID(*(unsigned long *)(APIC_BASE+APIC_LDR)); +} +#endif +#endif + +#endif + diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/synch_bitops.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/synch_bitops.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,2 @@ + +#include <asm-i386/mach-xen/asm/synch_bitops.h> diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/system.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/system.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,414 @@ +#ifndef __ASM_SYSTEM_H +#define __ASM_SYSTEM_H + +#include <linux/config.h> +#include <linux/kernel.h> +#include <asm/segment.h> +#include <asm/synch_bitops.h> +#include <asm/hypervisor.h> +#include <xen/interface/arch-x86_64.h> + +#ifdef __KERNEL__ + +#ifdef CONFIG_SMP +#define LOCK_PREFIX "lock ; " +#else +#define LOCK_PREFIX "" +#endif + +#define __STR(x) #x +#define STR(x) __STR(x) + +#define __SAVE(reg,offset) "movq %%" #reg ",(14-" #offset ")*8(%%rsp)\n\t" +#define __RESTORE(reg,offset) "movq (14-" #offset ")*8(%%rsp),%%" #reg "\n\t" + +/* frame pointer must be last for get_wchan */ +#define SAVE_CONTEXT "pushfq ; pushq %%rbp ; movq %%rsi,%%rbp\n\t" +#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popfq\n\t" + +#define __EXTRA_CLOBBER \ + ,"rcx","rbx","rdx","r8","r9","r10","r11","r12","r13","r14","r15" + +#define switch_to(prev,next,last) \ + asm volatile(SAVE_CONTEXT \ + "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \ + "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \ + "call __switch_to\n\t" \ + ".globl thread_return\n" \ + "thread_return:\n\t" \ + "movq %%gs:%P[pda_pcurrent],%%rsi\n\t" \ + "movq %P[thread_info](%%rsi),%%r8\n\t" \ + LOCK "btr %[tif_fork],%P[ti_flags](%%r8)\n\t" \ + "movq %%rax,%%rdi\n\t" \ + "jc ret_from_fork\n\t" \ + RESTORE_CONTEXT \ + : "=a" (last) \ + : [next] "S" (next), [prev] "D" (prev), \ + [threadrsp] "i" (offsetof(struct task_struct, thread.rsp)), \ + [ti_flags] "i" (offsetof(struct thread_info, flags)),\ + [tif_fork] "i" (TIF_FORK), \ + [thread_info] "i" (offsetof(struct task_struct, thread_info)), \ + [pda_pcurrent] "i" (offsetof(struct x8664_pda, pcurrent)) \ + : "memory", "cc" __EXTRA_CLOBBER) + + +extern void load_gs_index(unsigned); + +/* + * Load a segment. Fall back on loading the zero + * segment if something goes wrong.. + */ +#define loadsegment(seg,value) \ + asm volatile("\n" \ + "1:\t" \ + "movl %k0,%%" #seg "\n" \ + "2:\n" \ + ".section .fixup,\"ax\"\n" \ + "3:\t" \ + "movl %1,%%" #seg "\n\t" \ + "jmp 2b\n" \ + ".previous\n" \ + ".section __ex_table,\"a\"\n\t" \ + ".align 8\n\t" \ + ".quad 1b,3b\n" \ + ".previous" \ + : :"r" (value), "r" (0)) + +#define set_debug(value,register) \ + __asm__("movq %0,%%db" #register \ + : /* no output */ \ + :"r" ((unsigned long) value)) + + +#ifdef __KERNEL__ +struct alt_instr { + __u8 *instr; /* original instruction */ + __u8 *replacement; + __u8 cpuid; /* cpuid bit set for replacement */ + __u8 instrlen; /* length of original instruction */ + __u8 replacementlen; /* length of new instruction, <= instrlen */ + __u8 pad[5]; +}; +#endif + +/* + * Alternative instructions for different CPU types or capabilities. + * + * This allows to use optimized instructions even on generic binary + * kernels. + * + * length of oldinstr must be longer or equal the length of newinstr + * It can be padded with nops as needed. + * + * For non barrier like inlines please define new variants + * without volatile and memory clobber. + */ +#define alternative(oldinstr, newinstr, feature) \ + asm volatile ("661:\n\t" oldinstr "\n662:\n" \ + ".section .altinstructions,\"a\"\n" \ + " .align 8\n" \ + " .quad 661b\n" /* label */ \ + " .quad 663f\n" /* new instruction */ \ + " .byte %c0\n" /* feature bit */ \ + " .byte 662b-661b\n" /* sourcelen */ \ + " .byte 664f-663f\n" /* replacementlen */ \ + ".previous\n" \ + ".section .altinstr_replacement,\"ax\"\n" \ + "663:\n\t" newinstr "\n664:\n" /* replacement */ \ + ".previous" :: "i" (feature) : "memory") + +/* + * Alternative inline assembly with input. + * + * Pecularities: + * No memory clobber here. + * Argument numbers start with 1. + * Best is to use constraints that are fixed size (like (%1) ... "r") + * If you use variable sized constraints like "m" or "g" in the + * replacement maake sure to pad to the worst case length. + */ +#define alternative_input(oldinstr, newinstr, feature, input...) \ + asm volatile ("661:\n\t" oldinstr "\n662:\n" \ + ".section .altinstructions,\"a\"\n" \ + " .align 8\n" \ + " .quad 661b\n" /* label */ \ + " .quad 663f\n" /* new instruction */ \ + " .byte %c0\n" /* feature bit */ \ + " .byte 662b-661b\n" /* sourcelen */ \ + " .byte 664f-663f\n" /* replacementlen */ \ + ".previous\n" \ + ".section .altinstr_replacement,\"ax\"\n" \ + "663:\n\t" newinstr "\n664:\n" /* replacement */ \ + ".previous" :: "i" (feature), ##input) + +/* + * Clear and set 'TS' bit respectively + */ +#define clts() (HYPERVISOR_fpu_taskswitch(0)) + +static inline unsigned long read_cr0(void) +{ + unsigned long cr0; + asm volatile("movq %%cr0,%0" : "=r" (cr0)); + return cr0; +} + +static inline void write_cr0(unsigned long val) +{ + asm volatile("movq %0,%%cr0" :: "r" (val)); +} + +static inline unsigned long read_cr3(void) +{ + unsigned long cr3; + asm("movq %%cr3,%0" : "=r" (cr3)); + return cr3; +} + +static inline unsigned long read_cr4(void) +{ + unsigned long cr4; + asm("movq %%cr4,%0" : "=r" (cr4)); + return cr4; +} + +static inline void write_cr4(unsigned long val) +{ + asm volatile("movq %0,%%cr4" :: "r" (val)); +} + +#define stts() (HYPERVISOR_fpu_taskswitch(1)) + +#define wbinvd() \ + __asm__ __volatile__ ("wbinvd": : :"memory"); + +#endif /* __KERNEL__ */ + +#define nop() __asm__ __volatile__ ("nop") + +#define xchg(ptr,v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v),(ptr),sizeof(*(ptr)))) + +#define tas(ptr) (xchg((ptr),1)) + +#define __xg(x) ((volatile long *)(x)) + +extern inline void set_64bit(volatile unsigned long *ptr, unsigned long val) +{ + *ptr = val; +} + +#define _set_64bit set_64bit + +/* + * Note: no "lock" prefix even on SMP: xchg always implies lock anyway + * Note 2: xchg has side effect, so that attribute volatile is necessary, + * but generally the primitive is invalid, *ptr is output argument. --ANK + */ +static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size) +{ + switch (size) { + case 1: + __asm__ __volatile__("xchgb %b0,%1" + :"=q" (x) + :"m" (*__xg(ptr)), "0" (x) + :"memory"); + break; + case 2: + __asm__ __volatile__("xchgw %w0,%1" + :"=r" (x) + :"m" (*__xg(ptr)), "0" (x) + :"memory"); + break; + case 4: + __asm__ __volatile__("xchgl %k0,%1" + :"=r" (x) + :"m" (*__xg(ptr)), "0" (x) + :"memory"); + break; + case 8: + __asm__ __volatile__("xchgq %0,%1" + :"=r" (x) + :"m" (*__xg(ptr)), "0" (x) + :"memory"); + break; + } + return x; +} + +/* + * Atomic compare and exchange. Compare OLD with MEM, if identical, + * store NEW in MEM. Return the initial value in MEM. Success is + * indicated by comparing RETURN with OLD. + */ + +#define __HAVE_ARCH_CMPXCHG 1 + +static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, + unsigned long new, int size) +{ + unsigned long prev; + switch (size) { + case 1: + __asm__ __volatile__(LOCK_PREFIX "cmpxchgb %b1,%2" + : "=a"(prev) + : "q"(new), "m"(*__xg(ptr)), "0"(old) + : "memory"); + return prev; + case 2: + __asm__ __volatile__(LOCK_PREFIX "cmpxchgw %w1,%2" + : "=a"(prev) + : "q"(new), "m"(*__xg(ptr)), "0"(old) + : "memory"); + return prev; + case 4: + __asm__ __volatile__(LOCK_PREFIX "cmpxchgl %k1,%2" + : "=a"(prev) + : "q"(new), "m"(*__xg(ptr)), "0"(old) + : "memory"); + return prev; + case 8: + __asm__ __volatile__(LOCK_PREFIX "cmpxchgq %1,%2" + : "=a"(prev) + : "q"(new), "m"(*__xg(ptr)), "0"(old) + : "memory"); + return prev; + } + return old; +} + +#define cmpxchg(ptr,o,n)\ + ((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\ + (unsigned long)(n),sizeof(*(ptr)))) + +#ifdef CONFIG_SMP +#define smp_mb() mb() +#define smp_rmb() rmb() +#define smp_wmb() wmb() +#define smp_read_barrier_depends() do {} while(0) +#else +#define smp_mb() barrier() +#define smp_rmb() barrier() +#define smp_wmb() barrier() +#define smp_read_barrier_depends() do {} while(0) +#endif + + +/* + * Force strict CPU ordering. + * And yes, this is required on UP too when we're talking + * to devices. + */ +#define mb() asm volatile("mfence":::"memory") +#define rmb() asm volatile("lfence":::"memory") + +#ifdef CONFIG_UNORDERED_IO +#define wmb() asm volatile("sfence" ::: "memory") +#else +#define wmb() asm volatile("" ::: "memory") +#endif +#define read_barrier_depends() do {} while(0) +#define set_mb(var, value) do { xchg(&var, value); } while (0) +#define set_wmb(var, value) do { var = value; wmb(); } while (0) + +#define warn_if_not_ulong(x) do { unsigned long foo; (void) (&(x) == &foo); } while (0) + + +/* + * The use of 'barrier' in the following reflects their use as local-lock + * operations. Reentrancy must be prevented (e.g., __cli()) /before/ following + * critical operations are executed. All critical operations must complete + * /before/ reentrancy is permitted (e.g., __sti()). Alpha architecture also + * includes these barriers, for example. + */ + +#define __cli() \ +do { \ + vcpu_info_t *_vcpu; \ + preempt_disable(); \ + _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ + _vcpu->evtchn_upcall_mask = 1; \ + preempt_enable_no_resched(); \ + barrier(); \ +} while (0) + +#define __sti() \ +do { \ + vcpu_info_t *_vcpu; \ + barrier(); \ + preempt_disable(); \ + _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ + _vcpu->evtchn_upcall_mask = 0; \ + barrier(); /* unmask then check (avoid races) */ \ + if ( unlikely(_vcpu->evtchn_upcall_pending) ) \ + force_evtchn_callback(); \ + preempt_enable(); \ +} while (0) + +#define __save_flags(x) \ +do { \ + vcpu_info_t *_vcpu; \ + preempt_disable(); \ + _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ + (x) = _vcpu->evtchn_upcall_mask; \ + preempt_enable(); \ +} while (0) + +#define __restore_flags(x) \ +do { \ + vcpu_info_t *_vcpu; \ + barrier(); \ + preempt_disable(); \ + _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ + if ((_vcpu->evtchn_upcall_mask = (x)) == 0) { \ + barrier(); /* unmask then check (avoid races) */ \ + if ( unlikely(_vcpu->evtchn_upcall_pending) ) \ + force_evtchn_callback(); \ + preempt_enable(); \ + } else \ + preempt_enable_no_resched(); \ +} while (0) + +#define safe_halt() ((void)0) + +#define __save_and_cli(x) \ +do { \ + vcpu_info_t *_vcpu; \ + preempt_disable(); \ + _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ + (x) = _vcpu->evtchn_upcall_mask; \ + _vcpu->evtchn_upcall_mask = 1; \ + preempt_enable_no_resched(); \ + barrier(); \ +} while (0) + +void cpu_idle_wait(void); + +#define local_irq_save(x) __save_and_cli(x) +#define local_irq_restore(x) __restore_flags(x) +#define local_save_flags(x) __save_flags(x) +#define local_irq_disable() __cli() +#define local_irq_enable() __sti() + +/* Cannot use preempt_enable() here as we would recurse in preempt_sched(). */ +#define irqs_disabled() \ +({ int ___x; \ + vcpu_info_t *_vcpu; \ + preempt_disable(); \ + _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ + ___x = (_vcpu->evtchn_upcall_mask != 0); \ + preempt_enable_no_resched(); \ + ___x; }) + +/* + * disable hlt during certain critical i/o operations + */ +#define HAVE_DISABLE_HLT +void disable_hlt(void); +void enable_hlt(void); + +#define HAVE_EAT_KEY +void eat_key(void); + +extern unsigned long arch_align_stack(unsigned long sp); + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/timer.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/timer.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,64 @@ +#ifndef _ASMi386_TIMER_H +#define _ASMi386_TIMER_H +#include <linux/init.h> + +/** + * struct timer_ops - used to define a timer source + * + * @name: name of the timer. + * @init: Probes and initializes the timer. Takes clock= override + * string as an argument. Returns 0 on success, anything else + * on failure. + * @mark_offset: called by the timer interrupt. + * @get_offset: called by gettimeofday(). Returns the number of microseconds + * since the last timer interupt. + * @monotonic_clock: returns the number of nanoseconds since the init of the + * timer. + * @delay: delays this many clock cycles. + */ +struct timer_opts { + char* name; + void (*mark_offset)(void); + unsigned long (*get_offset)(void); + unsigned long long (*monotonic_clock)(void); + void (*delay)(unsigned long); +}; + +struct init_timer_opts { + int (*init)(char *override); + struct timer_opts *opts; +}; + +#define TICK_SIZE (tick_nsec / 1000) + +extern struct timer_opts* __init select_timer(void); +extern void clock_fallback(void); +void setup_pit_timer(void); + +/* Modifiers for buggy PIT handling */ + +extern int pit_latch_buggy; + +extern struct timer_opts *cur_timer; +extern int timer_ack; + +/* list of externed timers */ +extern struct timer_opts timer_none; +extern struct timer_opts timer_pit; +extern struct init_timer_opts timer_pit_init; +extern struct init_timer_opts timer_tsc_init; +#ifdef CONFIG_X86_CYCLONE_TIMER +extern struct init_timer_opts timer_cyclone_init; +#endif + +extern unsigned long calibrate_tsc(void); +extern void init_cpu_khz(void); +#ifdef CONFIG_HPET_TIMER +extern struct init_timer_opts timer_hpet_init; +extern unsigned long calibrate_tsc_hpet(unsigned long *tsc_hpet_quotient_ptr); +#endif + +#ifdef CONFIG_X86_PM_TIMER +extern struct init_timer_opts timer_pmtmr_init; +#endif +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/tlbflush.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/tlbflush.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,97 @@ +#ifndef _X8664_TLBFLUSH_H +#define _X8664_TLBFLUSH_H + +#include <linux/config.h> +#include <linux/mm.h> +#include <asm/processor.h> + +#define __flush_tlb() xen_tlb_flush() + +/* + * Global pages have to be flushed a bit differently. Not a real + * performance problem because this does not happen often. + */ +#define __flush_tlb_global() xen_tlb_flush() + + +extern unsigned long pgkern_mask; + +#define __flush_tlb_all() __flush_tlb_global() + +#define __flush_tlb_one(addr) xen_invlpg((unsigned long)addr) + + +/* + * TLB flushing: + * + * - flush_tlb() flushes the current mm struct TLBs + * - flush_tlb_all() flushes all processes TLBs + * - flush_tlb_mm(mm) flushes the specified mm context TLB's + * - flush_tlb_page(vma, vmaddr) flushes one page + * - flush_tlb_range(vma, start, end) flushes a range of pages + * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages + * - flush_tlb_pgtables(mm, start, end) flushes a range of page tables + * + * ..but the x86_64 has somewhat limited tlb flushing capabilities, + * and page-granular flushes are available only on i486 and up. + */ + +#ifndef CONFIG_SMP + +#define flush_tlb() __flush_tlb() +#define flush_tlb_all() __flush_tlb_all() +#define local_flush_tlb() __flush_tlb() + +static inline void flush_tlb_mm(struct mm_struct *mm) +{ + if (mm == current->active_mm) + __flush_tlb(); +} + +static inline void flush_tlb_page(struct vm_area_struct *vma, + unsigned long addr) +{ + if (vma->vm_mm == current->active_mm) + __flush_tlb_one(addr); +} + +static inline void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + if (vma->vm_mm == current->active_mm) + __flush_tlb(); +} + +#else + +#include <asm/smp.h> + +#define local_flush_tlb() \ + __flush_tlb() + +extern void flush_tlb_all(void); +extern void flush_tlb_current_task(void); +extern void flush_tlb_mm(struct mm_struct *); +extern void flush_tlb_page(struct vm_area_struct *, unsigned long); + +#define flush_tlb() flush_tlb_current_task() + +static inline void flush_tlb_range(struct vm_area_struct * vma, unsigned long start, unsigned long end) +{ + flush_tlb_mm(vma->vm_mm); +} + +#define TLBSTATE_OK 1 +#define TLBSTATE_LAZY 2 + +#endif + +#define flush_tlb_kernel_range(start, end) flush_tlb_all() + +static inline void flush_tlb_pgtables(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + /* x86_64 does not keep any page table caches in TLB */ +} + +#endif /* _X8664_TLBFLUSH_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/vga.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/vga.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,20 @@ +/* + * Access to VGA videoram + * + * (c) 1998 Martin Mares <mj@xxxxxx> + */ + +#ifndef _LINUX_ASM_VGA_H_ +#define _LINUX_ASM_VGA_H_ + +/* + * On the PC, we can just recalculate addresses and then + * access the videoram directly without any black magic. + */ + +#define VGA_MAP_MEM(x) (unsigned long)isa_bus_to_virt(x) + +#define vga_readb(x) (*(x)) +#define vga_writeb(x,y) (*(y) = (x)) + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/xor.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/asm/xor.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,328 @@ +/* + * x86-64 changes / gcc fixes from Andi Kleen. + * Copyright 2002 Andi Kleen, SuSE Labs. + * + * This hasn't been optimized for the hammer yet, but there are likely + * no advantages to be gotten from x86-64 here anyways. + */ + +typedef struct { unsigned long a,b; } __attribute__((aligned(16))) xmm_store_t; + +/* Doesn't use gcc to save the XMM registers, because there is no easy way to + tell it to do a clts before the register saving. */ +#define XMMS_SAVE do { \ + preempt_disable(); \ + if (!(current_thread_info()->status & TS_USEDFPU)) \ + clts(); \ + __asm__ __volatile__ ( \ + "movups %%xmm0,(%1) ;\n\t" \ + "movups %%xmm1,0x10(%1) ;\n\t" \ + "movups %%xmm2,0x20(%1) ;\n\t" \ + "movups %%xmm3,0x30(%1) ;\n\t" \ + : "=&r" (cr0) \ + : "r" (xmm_save) \ + : "memory"); \ +} while(0) + +#define XMMS_RESTORE do { \ + asm volatile ( \ + "sfence ;\n\t" \ + "movups (%1),%%xmm0 ;\n\t" \ + "movups 0x10(%1),%%xmm1 ;\n\t" \ + "movups 0x20(%1),%%xmm2 ;\n\t" \ + "movups 0x30(%1),%%xmm3 ;\n\t" \ + : \ + : "r" (cr0), "r" (xmm_save) \ + : "memory"); \ + if (!(current_thread_info()->status & TS_USEDFPU)) \ + stts(); \ + preempt_enable(); \ +} while(0) + +#define OFFS(x) "16*("#x")" +#define PF_OFFS(x) "256+16*("#x")" +#define PF0(x) " prefetchnta "PF_OFFS(x)"(%[p1]) ;\n" +#define LD(x,y) " movaps "OFFS(x)"(%[p1]), %%xmm"#y" ;\n" +#define ST(x,y) " movaps %%xmm"#y", "OFFS(x)"(%[p1]) ;\n" +#define PF1(x) " prefetchnta "PF_OFFS(x)"(%[p2]) ;\n" +#define PF2(x) " prefetchnta "PF_OFFS(x)"(%[p3]) ;\n" +#define PF3(x) " prefetchnta "PF_OFFS(x)"(%[p4]) ;\n" +#define PF4(x) " prefetchnta "PF_OFFS(x)"(%[p5]) ;\n" +#define PF5(x) " prefetchnta "PF_OFFS(x)"(%[p6]) ;\n" +#define XO1(x,y) " xorps "OFFS(x)"(%[p2]), %%xmm"#y" ;\n" +#define XO2(x,y) " xorps "OFFS(x)"(%[p3]), %%xmm"#y" ;\n" +#define XO3(x,y) " xorps "OFFS(x)"(%[p4]), %%xmm"#y" ;\n" +#define XO4(x,y) " xorps "OFFS(x)"(%[p5]), %%xmm"#y" ;\n" +#define XO5(x,y) " xorps "OFFS(x)"(%[p6]), %%xmm"#y" ;\n" + + +static void +xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +{ + unsigned int lines = bytes >> 8; + unsigned long cr0; + xmm_store_t xmm_save[4]; + + XMMS_SAVE; + + asm volatile ( +#undef BLOCK +#define BLOCK(i) \ + LD(i,0) \ + LD(i+1,1) \ + PF1(i) \ + PF1(i+2) \ + LD(i+2,2) \ + LD(i+3,3) \ + PF0(i+4) \ + PF0(i+6) \ + XO1(i,0) \ + XO1(i+1,1) \ + XO1(i+2,2) \ + XO1(i+3,3) \ + ST(i,0) \ + ST(i+1,1) \ + ST(i+2,2) \ + ST(i+3,3) \ + + + PF0(0) + PF0(2) + + " .align 32 ;\n" + " 1: ;\n" + + BLOCK(0) + BLOCK(4) + BLOCK(8) + BLOCK(12) + + " addq %[inc], %[p1] ;\n" + " addq %[inc], %[p2] ;\n" + " decl %[cnt] ; jnz 1b" + : [p1] "+r" (p1), [p2] "+r" (p2), [cnt] "+r" (lines) + : [inc] "r" (256UL) + : "memory"); + + XMMS_RESTORE; +} + +static void +xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3) +{ + unsigned int lines = bytes >> 8; + xmm_store_t xmm_save[4]; + unsigned long cr0; + + XMMS_SAVE; + + __asm__ __volatile__ ( +#undef BLOCK +#define BLOCK(i) \ + PF1(i) \ + PF1(i+2) \ + LD(i,0) \ + LD(i+1,1) \ + LD(i+2,2) \ + LD(i+3,3) \ + PF2(i) \ + PF2(i+2) \ + PF0(i+4) \ + PF0(i+6) \ + XO1(i,0) \ + XO1(i+1,1) \ + XO1(i+2,2) \ + XO1(i+3,3) \ + XO2(i,0) \ + XO2(i+1,1) \ + XO2(i+2,2) \ + XO2(i+3,3) \ + ST(i,0) \ + ST(i+1,1) \ + ST(i+2,2) \ + ST(i+3,3) \ + + + PF0(0) + PF0(2) + + " .align 32 ;\n" + " 1: ;\n" + + BLOCK(0) + BLOCK(4) + BLOCK(8) + BLOCK(12) + + " addq %[inc], %[p1] ;\n" + " addq %[inc], %[p2] ;\n" + " addq %[inc], %[p3] ;\n" + " decl %[cnt] ; jnz 1b" + : [cnt] "+r" (lines), + [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3) + : [inc] "r" (256UL) + : "memory"); + XMMS_RESTORE; +} + +static void +xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3, unsigned long *p4) +{ + unsigned int lines = bytes >> 8; + xmm_store_t xmm_save[4]; + unsigned long cr0; + + XMMS_SAVE; + + __asm__ __volatile__ ( +#undef BLOCK +#define BLOCK(i) \ + PF1(i) \ + PF1(i+2) \ + LD(i,0) \ + LD(i+1,1) \ + LD(i+2,2) \ + LD(i+3,3) \ + PF2(i) \ + PF2(i+2) \ + XO1(i,0) \ + XO1(i+1,1) \ + XO1(i+2,2) \ + XO1(i+3,3) \ + PF3(i) \ + PF3(i+2) \ + PF0(i+4) \ + PF0(i+6) \ + XO2(i,0) \ + XO2(i+1,1) \ + XO2(i+2,2) \ + XO2(i+3,3) \ + XO3(i,0) \ + XO3(i+1,1) \ + XO3(i+2,2) \ + XO3(i+3,3) \ + ST(i,0) \ + ST(i+1,1) \ + ST(i+2,2) \ + ST(i+3,3) \ + + + PF0(0) + PF0(2) + + " .align 32 ;\n" + " 1: ;\n" + + BLOCK(0) + BLOCK(4) + BLOCK(8) + BLOCK(12) + + " addq %[inc], %[p1] ;\n" + " addq %[inc], %[p2] ;\n" + " addq %[inc], %[p3] ;\n" + " addq %[inc], %[p4] ;\n" + " decl %[cnt] ; jnz 1b" + : [cnt] "+c" (lines), + [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4) + : [inc] "r" (256UL) + : "memory" ); + + XMMS_RESTORE; +} + +static void +xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3, unsigned long *p4, unsigned long *p5) +{ + unsigned int lines = bytes >> 8; + xmm_store_t xmm_save[4]; + unsigned long cr0; + + XMMS_SAVE; + + __asm__ __volatile__ ( +#undef BLOCK +#define BLOCK(i) \ + PF1(i) \ + PF1(i+2) \ + LD(i,0) \ + LD(i+1,1) \ + LD(i+2,2) \ + LD(i+3,3) \ + PF2(i) \ + PF2(i+2) \ + XO1(i,0) \ + XO1(i+1,1) \ + XO1(i+2,2) \ + XO1(i+3,3) \ + PF3(i) \ + PF3(i+2) \ + XO2(i,0) \ + XO2(i+1,1) \ + XO2(i+2,2) \ + XO2(i+3,3) \ + PF4(i) \ + PF4(i+2) \ + PF0(i+4) \ + PF0(i+6) \ + XO3(i,0) \ + XO3(i+1,1) \ + XO3(i+2,2) \ + XO3(i+3,3) \ + XO4(i,0) \ + XO4(i+1,1) \ + XO4(i+2,2) \ + XO4(i+3,3) \ + ST(i,0) \ + ST(i+1,1) \ + ST(i+2,2) \ + ST(i+3,3) \ + + + PF0(0) + PF0(2) + + " .align 32 ;\n" + " 1: ;\n" + + BLOCK(0) + BLOCK(4) + BLOCK(8) + BLOCK(12) + + " addq %[inc], %[p1] ;\n" + " addq %[inc], %[p2] ;\n" + " addq %[inc], %[p3] ;\n" + " addq %[inc], %[p4] ;\n" + " addq %[inc], %[p5] ;\n" + " decl %[cnt] ; jnz 1b" + : [cnt] "+c" (lines), + [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4), + [p5] "+r" (p5) + : [inc] "r" (256UL) + : "memory"); + + XMMS_RESTORE; +} + +static struct xor_block_template xor_block_sse = { + .name = "generic_sse", + .do_2 = xor_sse_2, + .do_3 = xor_sse_3, + .do_4 = xor_sse_4, + .do_5 = xor_sse_5, +}; + +#undef XOR_TRY_TEMPLATES +#define XOR_TRY_TEMPLATES \ + do { \ + xor_speed(&xor_block_sse); \ + } while (0) + +/* We force the use of the SSE xor block because it can write around L2. + We may also be able to load into the L1 only depending on how the cpu + deals with a load to a line that is being prefetched. */ +#define XOR_SELECT_TEMPLATE(FASTEST) (&xor_block_sse) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/io_ports.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/io_ports.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,30 @@ +/* + * arch/i386/mach-generic/io_ports.h + * + * Machine specific IO port address definition for generic. + * Written by Osamu Tomita <tomita@xxxxxxxxxxx> + */ +#ifndef _MACH_IO_PORTS_H +#define _MACH_IO_PORTS_H + +/* i8253A PIT registers */ +#define PIT_MODE 0x43 +#define PIT_CH0 0x40 +#define PIT_CH2 0x42 + +/* i8259A PIC registers */ +#define PIC_MASTER_CMD 0x20 +#define PIC_MASTER_IMR 0x21 +#define PIC_MASTER_ISR PIC_MASTER_CMD +#define PIC_MASTER_POLL PIC_MASTER_ISR +#define PIC_MASTER_OCW3 PIC_MASTER_ISR +#define PIC_SLAVE_CMD 0xa0 +#define PIC_SLAVE_IMR 0xa1 + +/* i8259A PIC related value */ +#define PIC_CASCADE_IR 2 +#define MASTER_ICW4_DEFAULT 0x01 +#define SLAVE_ICW4_DEFAULT 0x01 +#define PIC_ICW4_AEOI 2 + +#endif /* !_MACH_IO_PORTS_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/irq_vectors.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/irq_vectors.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,123 @@ +/* + * This file should contain #defines for all of the interrupt vector + * numbers used by this architecture. + * + * In addition, there are some standard defines: + * + * FIRST_EXTERNAL_VECTOR: + * The first free place for external interrupts + * + * SYSCALL_VECTOR: + * The IRQ vector a syscall makes the user to kernel transition + * under. + * + * TIMER_IRQ: + * The IRQ number the timer interrupt comes in at. + * + * NR_IRQS: + * The total number of interrupt vectors (including all the + * architecture specific interrupts) needed. + * + */ +#ifndef _ASM_IRQ_VECTORS_H +#define _ASM_IRQ_VECTORS_H + +/* + * IDT vectors usable for external interrupt sources start + * at 0x20: + */ +#define FIRST_EXTERNAL_VECTOR 0x20 + +#define SYSCALL_VECTOR 0x80 + +/* + * Vectors 0x20-0x2f are used for ISA interrupts. + */ + +#if 0 +/* + * Special IRQ vectors used by the SMP architecture, 0xf0-0xff + * + * some of the following vectors are 'rare', they are merged + * into a single vector (CALL_FUNCTION_VECTOR) to save vector space. + * TLB, reschedule and local APIC vectors are performance-critical. + * + * Vectors 0xf0-0xfa are free (reserved for future Linux use). + */ +#define INVALIDATE_TLB_VECTOR 0xfd +#define RESCHEDULE_VECTOR 0xfc +#define CALL_FUNCTION_VECTOR 0xfb + +#define THERMAL_APIC_VECTOR 0xf0 +/* + * Local APIC timer IRQ vector is on a different priority level, + * to work around the 'lost local interrupt if more than 2 IRQ + * sources per level' errata. + */ +#define LOCAL_TIMER_VECTOR 0xef +#endif + +#define SPURIOUS_APIC_VECTOR 0xff +#define ERROR_APIC_VECTOR 0xfe + +/* + * First APIC vector available to drivers: (vectors 0x30-0xee) + * we start at 0x31 to spread out vectors evenly between priority + * levels. (0x80 is the syscall vector) + */ +#define FIRST_DEVICE_VECTOR 0x31 +#define FIRST_SYSTEM_VECTOR 0xef + +/* + * 16 8259A IRQ's, 208 potential APIC interrupt sources. + * Right now the APIC is mostly only used for SMP. + * 256 vectors is an architectural limit. (we can have + * more than 256 devices theoretically, but they will + * have to use shared interrupts) + * Since vectors 0x00-0x1f are used/reserved for the CPU, + * the usable vector space is 0x20-0xff (224 vectors) + */ + +#define RESCHEDULE_VECTOR 0 +#define CALL_FUNCTION_VECTOR 1 +#define NR_IPIS 2 + +/* + * The maximum number of vectors supported by i386 processors + * is limited to 256. For processors other than i386, NR_VECTORS + * should be changed accordingly. + */ +#define NR_VECTORS 256 + +#define FPU_IRQ 13 + +#define FIRST_VM86_IRQ 3 +#define LAST_VM86_IRQ 15 +#define invalid_vm86_irq(irq) ((irq) < 3 || (irq) > 15) + +/* + * The flat IRQ space is divided into two regions: + * 1. A one-to-one mapping of real physical IRQs. This space is only used + * if we have physical device-access privilege. This region is at the + * start of the IRQ space so that existing device drivers do not need + * to be modified to translate physical IRQ numbers into our IRQ space. + * 3. A dynamic mapping of inter-domain and Xen-sourced virtual IRQs. These + * are bound using the provided bind/unbind functions. + */ + +#define PIRQ_BASE 0 +#define NR_PIRQS 256 + +#define DYNIRQ_BASE (PIRQ_BASE + NR_PIRQS) +#define NR_DYNIRQS 256 + +#define NR_IRQS (NR_PIRQS + NR_DYNIRQS) +#define NR_IRQ_VECTORS NR_IRQS + +#define pirq_to_irq(_x) ((_x) + PIRQ_BASE) +#define irq_to_pirq(_x) ((_x) - PIRQ_BASE) + +#define dynirq_to_irq(_x) ((_x) + DYNIRQ_BASE) +#define irq_to_dynirq(_x) ((_x) - DYNIRQ_BASE) + +#endif /* _ASM_IRQ_VECTORS_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/mach_time.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/mach_time.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,122 @@ +/* + * include/asm-i386/mach-default/mach_time.h + * + * Machine specific set RTC function for generic. + * Split out from time.c by Osamu Tomita <tomita@xxxxxxxxxxx> + */ +#ifndef _MACH_TIME_H +#define _MACH_TIME_H + +#include <asm-i386/mc146818rtc.h> + +/* for check timing call set_rtc_mmss() 500ms */ +/* used in arch/i386/time.c::do_timer_interrupt() */ +#define USEC_AFTER 500000 +#define USEC_BEFORE 500000 + +/* + * In order to set the CMOS clock precisely, set_rtc_mmss has to be + * called 500 ms after the second nowtime has started, because when + * nowtime is written into the registers of the CMOS clock, it will + * jump to the next second precisely 500 ms later. Check the Motorola + * MC146818A or Dallas DS12887 data sheet for details. + * + * BUG: This routine does not handle hour overflow properly; it just + * sets the minutes. Usually you'll only notice that after reboot! + */ +static inline int mach_set_rtc_mmss(unsigned long nowtime) +{ + int retval = 0; + int real_seconds, real_minutes, cmos_minutes; + unsigned char save_control, save_freq_select; + + save_control = CMOS_READ(RTC_CONTROL); /* tell the clock it's being set */ + CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL); + + save_freq_select = CMOS_READ(RTC_FREQ_SELECT); /* stop and reset prescaler */ + CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT); + + cmos_minutes = CMOS_READ(RTC_MINUTES); + if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) + BCD_TO_BIN(cmos_minutes); + + /* + * since we're only adjusting minutes and seconds, + * don't interfere with hour overflow. This avoids + * messing with unknown time zones but requires your + * RTC not to be off by more than 15 minutes + */ + real_seconds = nowtime % 60; + real_minutes = nowtime / 60; + if (((abs(real_minutes - cmos_minutes) + 15)/30) & 1) + real_minutes += 30; /* correct for half hour time zone */ + real_minutes %= 60; + + if (abs(real_minutes - cmos_minutes) < 30) { + if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { + BIN_TO_BCD(real_seconds); + BIN_TO_BCD(real_minutes); + } + CMOS_WRITE(real_seconds,RTC_SECONDS); + CMOS_WRITE(real_minutes,RTC_MINUTES); + } else { + printk(KERN_WARNING + "set_rtc_mmss: can't update from %d to %d\n", + cmos_minutes, real_minutes); + retval = -1; + } + + /* The following flags have to be released exactly in this order, + * otherwise the DS12887 (popular MC146818A clone with integrated + * battery and quartz) will not reset the oscillator and will not + * update precisely 500 ms later. You won't find this mentioned in + * the Dallas Semiconductor data sheets, but who believes data + * sheets anyway ... -- Markus Kuhn + */ + CMOS_WRITE(save_control, RTC_CONTROL); + CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); + + return retval; +} + +static inline unsigned long mach_get_cmos_time(void) +{ + unsigned int year, mon, day, hour, min, sec; + int i; + + /* The Linux interpretation of the CMOS clock register contents: + * When the Update-In-Progress (UIP) flag goes from 1 to 0, the + * RTC registers show the second which has precisely just started. + * Let's hope other operating systems interpret the RTC the same way. + */ + /* read RTC exactly on falling edge of update flag */ + for (i = 0 ; i < 1000000 ; i++) /* may take up to 1 second... */ + if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) + break; + for (i = 0 ; i < 1000000 ; i++) /* must try at least 2.228 ms */ + if (!(CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP)) + break; + do { /* Isn't this overkill ? UIP above should guarantee consistency */ + sec = CMOS_READ(RTC_SECONDS); + min = CMOS_READ(RTC_MINUTES); + hour = CMOS_READ(RTC_HOURS); + day = CMOS_READ(RTC_DAY_OF_MONTH); + mon = CMOS_READ(RTC_MONTH); + year = CMOS_READ(RTC_YEAR); + } while (sec != CMOS_READ(RTC_SECONDS)); + if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) + { + BCD_TO_BIN(sec); + BCD_TO_BIN(min); + BCD_TO_BIN(hour); + BCD_TO_BIN(day); + BCD_TO_BIN(mon); + BCD_TO_BIN(year); + } + if ((year += 1900) < 1970) + year += 100; + + return mktime(year, mon, day, hour, min, sec); +} + +#endif /* !_MACH_TIME_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/mach_timer.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/mach_timer.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,48 @@ +/* + * include/asm-i386/mach-default/mach_timer.h + * + * Machine specific calibrate_tsc() for generic. + * Split out from timer_tsc.c by Osamu Tomita <tomita@xxxxxxxxxxx> + */ +/* ------ Calibrate the TSC ------- + * Return 2^32 * (1 / (TSC clocks per usec)) for do_fast_gettimeoffset(). + * Too much 64-bit arithmetic here to do this cleanly in C, and for + * accuracy's sake we want to keep the overhead on the CTC speaker (channel 2) + * output busy loop as low as possible. We avoid reading the CTC registers + * directly because of the awkward 8-bit access mechanism of the 82C54 + * device. + */ +#ifndef _MACH_TIMER_H +#define _MACH_TIMER_H + +#define CALIBRATE_LATCH (5 * LATCH) + +static inline void mach_prepare_counter(void) +{ + /* Set the Gate high, disable speaker */ + outb((inb(0x61) & ~0x02) | 0x01, 0x61); + + /* + * Now let's take care of CTC channel 2 + * + * Set the Gate high, program CTC channel 2 for mode 0, + * (interrupt on terminal count mode), binary count, + * load 5 * LATCH count, (LSB and MSB) to begin countdown. + * + * Some devices need a delay here. + */ + outb(0xb0, 0x43); /* binary, mode 0, LSB/MSB, Ch 2 */ + outb_p(CALIBRATE_LATCH & 0xff, 0x42); /* LSB of count */ + outb_p(CALIBRATE_LATCH >> 8, 0x42); /* MSB of count */ +} + +static inline void mach_countup(unsigned long *count_p) +{ + unsigned long count = 0; + do { + count++; + } while ((inb_p(0x61) & 0x20) == 0); + *count_p = count; +} + +#endif /* !_MACH_TIMER_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/setup_arch_post.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/setup_arch_post.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,52 @@ +/** + * machine_specific_memory_setup - Hook for machine specific memory setup. + * + * Description: + * This is included late in kernel/setup.c so that it can make + * use of all of the static functions. + **/ + +static char * __init machine_specific_memory_setup(void) +{ + char *who; + unsigned long start_pfn, max_pfn; + + who = "Xen"; + + start_pfn = 0; + max_pfn = xen_start_info->nr_pages; + + e820.nr_map = 0; + add_memory_region(PFN_PHYS(start_pfn), PFN_PHYS(max_pfn) - PFN_PHYS(start_pfn), E820_RAM); + + return who; +} + +void __init machine_specific_modify_cpu_capabilities(struct cpuinfo_x86 *c) +{ + clear_bit(X86_FEATURE_VME, c->x86_capability); + clear_bit(X86_FEATURE_DE, c->x86_capability); + clear_bit(X86_FEATURE_PSE, c->x86_capability); + clear_bit(X86_FEATURE_PGE, c->x86_capability); + clear_bit(X86_FEATURE_SEP, c->x86_capability); + if (!(xen_start_info->flags & SIF_PRIVILEGED)) + clear_bit(X86_FEATURE_MTRR, c->x86_capability); +} + +extern void hypervisor_callback(void); +extern void failsafe_callback(void); +extern void nmi(void); + +static void __init machine_specific_arch_setup(void) +{ + HYPERVISOR_set_callbacks( + (unsigned long) hypervisor_callback, + (unsigned long) failsafe_callback, + (unsigned long) system_call); + +#ifdef CONFIG_X86_LOCAL_APIC + HYPERVISOR_nmi_op(XENNMI_register_callback, (unsigned long)&nmi); +#endif + + machine_specific_modify_cpu_capabilities(&boot_cpu_data); +} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/setup_arch_pre.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/asm-x86_64/mach-xen/setup_arch_pre.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,5 @@ +/* Hook to call BIOS initialisation function */ + +#define ARCH_SETUP machine_specific_arch_setup(); + +static void __init machine_specific_arch_setup(void); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/linux/init.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/linux/init.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,262 @@ +#ifndef _LINUX_INIT_H +#define _LINUX_INIT_H + +#include <linux/config.h> +#include <linux/compiler.h> + +/* These macros are used to mark some functions or + * initialized data (doesn't apply to uninitialized data) + * as `initialization' functions. The kernel can take this + * as hint that the function is used only during the initialization + * phase and free up used memory resources after + * + * Usage: + * For functions: + * + * You should add __init immediately before the function name, like: + * + * static void __init initme(int x, int y) + * { + * extern int z; z = x * y; + * } + * + * If the function has a prototype somewhere, you can also add + * __init between closing brace of the prototype and semicolon: + * + * extern int initialize_foobar_device(int, int, int) __init; + * + * For initialized data: + * You should insert __initdata between the variable name and equal + * sign followed by value, e.g.: + * + * static int init_variable __initdata = 0; + * static char linux_logo[] __initdata = { 0x32, 0x36, ... }; + * + * Don't forget to initialize data not at file scope, i.e. within a function, + * as gcc otherwise puts the data into the bss section and not into the init + * section. + * + * Also note, that this data cannot be "const". + */ + +/* These are for everybody (although not all archs will actually + discard it in modules) */ +#define __init __attribute__ ((__section__ (".init.text"))) +#define __initdata __attribute__ ((__section__ (".init.data"))) +#define __exitdata __attribute__ ((__section__(".exit.data"))) +#define __exit_call __attribute_used__ __attribute__ ((__section__ (".exitcall.exit"))) + +#ifdef MODULE +#define __exit __attribute__ ((__section__(".exit.text"))) +#else +#define __exit __attribute_used__ __attribute__ ((__section__(".exit.text"))) +#endif + +/* For assembly routines */ +#define __INIT .section ".init.text","ax" +#define __FINIT .previous +#define __INITDATA .section ".init.data","aw" + +#ifndef __ASSEMBLY__ +/* + * Used for initialization calls.. + */ +typedef int (*initcall_t)(void); +typedef void (*exitcall_t)(void); + +extern initcall_t __con_initcall_start[], __con_initcall_end[]; +extern initcall_t __security_initcall_start[], __security_initcall_end[]; + +/* Defined in init/main.c */ +extern char saved_command_line[]; +#endif + +#ifndef MODULE + +#ifndef __ASSEMBLY__ + +/* initcalls are now grouped by functionality into separate + * subsections. Ordering inside the subsections is determined + * by link order. + * For backwards compatibility, initcall() puts the call in + * the device init subsection. + */ + +#define __define_initcall(level,fn) \ + static initcall_t __initcall_##fn __attribute_used__ \ + __attribute__((__section__(".initcall" level ".init"))) = fn + +#define core_initcall(fn) __define_initcall("1",fn) +#define postcore_initcall(fn) __define_initcall("2",fn) +#define arch_initcall(fn) __define_initcall("3",fn) +#define subsys_initcall(fn) __define_initcall("4",fn) +#define fs_initcall(fn) __define_initcall("5",fn) +#define device_initcall(fn) __define_initcall("6",fn) +#define late_initcall(fn) __define_initcall("7",fn) + +#define __initcall(fn) device_initcall(fn) + +#define __exitcall(fn) \ + static exitcall_t __exitcall_##fn __exit_call = fn + +#define console_initcall(fn) \ + static initcall_t __initcall_##fn \ + __attribute_used__ __attribute__((__section__(".con_initcall.init")))=fn + +#define security_initcall(fn) \ + static initcall_t __initcall_##fn \ + __attribute_used__ __attribute__((__section__(".security_initcall.init"))) = fn + +struct obs_kernel_param { + const char *str; + int (*setup_func)(char *); + int early; +}; + +/* + * Only for really core code. See moduleparam.h for the normal way. + * + * Force the alignment so the compiler doesn't space elements of the + * obs_kernel_param "array" too far apart in .init.setup. + */ +#define __setup_param(str, unique_id, fn, early) \ + static char __setup_str_##unique_id[] __initdata = str; \ + static struct obs_kernel_param __setup_##unique_id \ + __attribute_used__ \ + __attribute__((__section__(".init.setup"))) \ + __attribute__((aligned((sizeof(long))))) \ + = { __setup_str_##unique_id, fn, early } + +#define __setup_null_param(str, unique_id) \ + __setup_param(str, unique_id, NULL, 0) + +#define __setup(str, fn) \ + __setup_param(str, fn, fn, 0) + +#define __obsolete_setup(str) \ + __setup_null_param(str, __LINE__) + +/* NOTE: fn is as per module_param, not __setup! Emits warning if fn + * returns non-zero. */ +#define early_param(str, fn) \ + __setup_param(str, fn, fn, 1) + +/* Relies on saved_command_line being set */ +void __init parse_early_param(void); +#endif /* __ASSEMBLY__ */ + +/** + * module_init() - driver initialization entry point + * @x: function to be run at kernel boot time or module insertion + * + * module_init() will either be called during do_initcalls (if + * builtin) or at module insertion time (if a module). There can only + * be one per module. + */ +#define module_init(x) __initcall(x); + +/** + * module_exit() - driver exit entry point + * @x: function to be run when driver is removed + * + * module_exit() will wrap the driver clean-up code + * with cleanup_module() when used with rmmod when + * the driver is a module. If the driver is statically + * compiled into the kernel, module_exit() has no effect. + * There can only be one per module. + */ +#define module_exit(x) __exitcall(x); + +#else /* MODULE */ + +/* Don't use these in modules, but some people do... */ +#define core_initcall(fn) module_init(fn) +#define postcore_initcall(fn) module_init(fn) +#define arch_initcall(fn) module_init(fn) +#define subsys_initcall(fn) module_init(fn) +#define fs_initcall(fn) module_init(fn) +#define device_initcall(fn) module_init(fn) +#define late_initcall(fn) module_init(fn) + +#define security_initcall(fn) module_init(fn) + +/* These macros create a dummy inline: gcc 2.9x does not count alias + as usage, hence the `unused function' warning when __init functions + are declared static. We use the dummy __*_module_inline functions + both to kill the warning and check the type of the init/cleanup + function. */ + +/* Each module must use one module_init(), or one no_module_init */ +#define module_init(initfn) \ + static inline initcall_t __inittest(void) \ + { return initfn; } \ + int init_module(void) __attribute__((alias(#initfn))); + +/* This is only required if you want to be unloadable. */ +#define module_exit(exitfn) \ + static inline exitcall_t __exittest(void) \ + { return exitfn; } \ + void cleanup_module(void) __attribute__((alias(#exitfn))); + +#define __setup_param(str, unique_id, fn) /* nothing */ +#define __setup_null_param(str, unique_id) /* nothing */ +#define __setup(str, func) /* nothing */ +#define __obsolete_setup(str) /* nothing */ +#endif + +/* Data marked not to be saved by software_suspend() */ +#define __nosavedata __attribute__ ((__section__ (".data.nosave"))) + +/* This means "can be init if no module support, otherwise module load + may call it." */ +#ifdef CONFIG_MODULES +#define __init_or_module +#define __initdata_or_module +#else +#define __init_or_module __init +#define __initdata_or_module __initdata +#endif /*CONFIG_MODULES*/ + +#ifdef CONFIG_HOTPLUG +#define __devinit +#define __devinitdata +#define __devexit +#define __devexitdata +#else +#define __devinit __init +#define __devinitdata __initdata +#define __devexit __exit +#define __devexitdata __exitdata +#endif + +#ifdef CONFIG_HOTPLUG_CPU +#define __cpuinit +#define __cpuinitdata +#define __cpuexit +#define __cpuexitdata +#else +#define __cpuinit __init +#define __cpuinitdata __initdata +#define __cpuexit __exit +#define __cpuexitdata __exitdata +#endif + +/* Functions marked as __devexit may be discarded at kernel link time, depending + on config options. Newer versions of binutils detect references from + retained sections to discarded sections and flag an error. Pointers to + __devexit functions must use __devexit_p(function_name), the wrapper will + insert either the function_name or NULL, depending on the config options. + */ +#if defined(MODULE) || defined(CONFIG_HOTPLUG) +#define __devexit_p(x) x +#else +#define __devexit_p(x) NULL +#endif + +#ifdef MODULE +#define __exit_p(x) x +#else +#define __exit_p(x) NULL +#endif + +#endif /* _LINUX_INIT_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/xen/balloon.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/xen/balloon.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,70 @@ +/****************************************************************************** + * balloon.h + * + * Xen balloon driver - enables returning/claiming memory to/from Xen. + * + * Copyright (c) 2003, B Dragovic + * Copyright (c) 2003-2004, M Williamson, K Fraser + * + * This file may be distributed separately from the Linux kernel, or + * incorporated into other software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef __ASM_BALLOON_H__ +#define __ASM_BALLOON_H__ + +/* + * Inform the balloon driver that it should allow some slop for device-driver + * memory activities. + */ +extern void +balloon_update_driver_allowance( + long delta); + +/* Allocate an empty low-memory page range. */ +extern struct page * +balloon_alloc_empty_page_range( + unsigned long nr_pages); + +/* Deallocate an empty page range, adding to the balloon. */ +extern void +balloon_dealloc_empty_page_range( + struct page *page, unsigned long nr_pages); + +/* + * Prevent the balloon driver from changing the memory reservation during + * a driver critical region. + */ +extern spinlock_t balloon_lock; +#define balloon_lock(__flags) spin_lock_irqsave(&balloon_lock, __flags) +#define balloon_unlock(__flags) spin_unlock_irqrestore(&balloon_lock, __flags) + +#endif /* __ASM_BALLOON_H__ */ + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/xen/driver_util.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/xen/driver_util.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,26 @@ + +#ifndef __ASM_XEN_DRIVER_UTIL_H__ +#define __ASM_XEN_DRIVER_UTIL_H__ + +#include <linux/config.h> +#include <linux/vmalloc.h> + +/* Allocate/destroy a 'vmalloc' VM area. */ +extern struct vm_struct *alloc_vm_area(unsigned long size); +extern void free_vm_area(struct vm_struct *area); + +/* Lock an area so that PTEs are accessible in the current address space. */ +extern void lock_vm_area(struct vm_struct *area); +extern void unlock_vm_area(struct vm_struct *area); + +#endif /* __ASM_XEN_DRIVER_UTIL_H__ */ + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/xen/evtchn.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/xen/evtchn.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,123 @@ +/****************************************************************************** + * evtchn.h + * + * Communication via Xen event channels. + * Also definitions for the device that demuxes notifications to userspace. + * + * Copyright (c) 2004-2005, K A Fraser + * + * This file may be distributed separately from the Linux kernel, or + * incorporated into other software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef __ASM_EVTCHN_H__ +#define __ASM_EVTCHN_H__ + +#include <linux/config.h> +#include <linux/interrupt.h> +#include <asm/hypervisor.h> +#include <asm/ptrace.h> +#include <asm/synch_bitops.h> +#include <xen/interface/event_channel.h> +#include <linux/smp.h> + +/* + * LOW-LEVEL DEFINITIONS + */ + +/* + * Dynamically bind an event source to an IRQ-like callback handler. + * On some platforms this may not be implemented via the Linux IRQ subsystem. + * The IRQ argument passed to the callback handler is the same as returned + * from the bind call. It may not correspond to a Linux IRQ number. + * Returns IRQ or negative errno. + * UNBIND: Takes IRQ to unbind from; automatically closes the event channel. + */ +extern int bind_evtchn_to_irqhandler( + unsigned int evtchn, + irqreturn_t (*handler)(int, void *, struct pt_regs *), + unsigned long irqflags, + const char *devname, + void *dev_id); +extern int bind_virq_to_irqhandler( + unsigned int virq, + unsigned int cpu, + irqreturn_t (*handler)(int, void *, struct pt_regs *), + unsigned long irqflags, + const char *devname, + void *dev_id); +extern int bind_ipi_to_irqhandler( + unsigned int ipi, + unsigned int cpu, + irqreturn_t (*handler)(int, void *, struct pt_regs *), + unsigned long irqflags, + const char *devname, + void *dev_id); + +/* + * Common unbind function for all event sources. Takes IRQ to unbind from. + * Automatically closes the underlying event channel (even for bindings + * made with bind_evtchn_to_irqhandler()). + */ +extern void unbind_from_irqhandler(unsigned int irq, void *dev_id); + +extern void irq_resume(void); + +/* Entry point for notifications into Linux subsystems. */ +asmlinkage void evtchn_do_upcall(struct pt_regs *regs); + +/* Entry point for notifications into the userland character device. */ +extern void evtchn_device_upcall(int port); + +extern void mask_evtchn(int port); +extern void unmask_evtchn(int port); + +static inline void clear_evtchn(int port) +{ + shared_info_t *s = HYPERVISOR_shared_info; + synch_clear_bit(port, &s->evtchn_pending[0]); +} + +static inline void notify_remote_via_evtchn(int port) +{ + evtchn_op_t op; + op.cmd = EVTCHNOP_send, + op.u.send.port = port; + (void)HYPERVISOR_event_channel_op(&op); +} + +/* + * Unlike notify_remote_via_evtchn(), this is safe to use across + * save/restore. Notifications on a broken connection are silently dropped. + */ +extern void notify_remote_via_irq(int irq); + +#endif /* __ASM_EVTCHN_H__ */ + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/xen/features.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/xen/features.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,20 @@ +/****************************************************************************** + * features.h + * + * Query the features reported by Xen. + * + * Copyright (c) 2006, Ian Campbell + */ + +#ifndef __ASM_XEN_FEATURES_H__ +#define __ASM_XEN_FEATURES_H__ + +#include <xen/interface/version.h> + +extern void setup_xen_features(void); + +extern unsigned long xen_features[XENFEAT_NR_SUBMAPS]; + +#define xen_feature(flag) (test_bit(flag, xen_features)) + +#endif /* __ASM_XEN_FEATURES_H__ */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/xen/foreign_page.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/xen/foreign_page.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,40 @@ +/****************************************************************************** + * foreign_page.h + * + * Provide a "foreign" page type, that is owned by a foreign allocator and + * not the normal buddy allocator in page_alloc.c + * + * Copyright (c) 2004, K A Fraser + */ + +#ifndef __ASM_XEN_FOREIGN_PAGE_H__ +#define __ASM_XEN_FOREIGN_PAGE_H__ + +#define PG_foreign PG_arch_1 + +#define PageForeign(page) test_bit(PG_foreign, &(page)->flags) + +#define SetPageForeign(page, dtor) do { \ + set_bit(PG_foreign, &(page)->flags); \ + (page)->mapping = (void *)dtor; \ +} while (0) + +#define ClearPageForeign(page) do { \ + clear_bit(PG_foreign, &(page)->flags); \ + (page)->mapping = NULL; \ +} while (0) + +#define PageForeignDestructor(page) \ + ( (void (*) (struct page *)) (page)->mapping ) + +#endif /* __ASM_XEN_FOREIGN_PAGE_H__ */ + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/xen/gnttab.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/xen/gnttab.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,98 @@ +/****************************************************************************** + * gnttab.h + * + * Two sets of functionality: + * 1. Granting foreign access to our memory reservation. + * 2. Accessing others' memory reservations via grant references. + * (i.e., mechanisms for both sender and recipient of grant references) + * + * Copyright (c) 2004-2005, K A Fraser + * Copyright (c) 2005, Christopher Clark + */ + +#ifndef __ASM_GNTTAB_H__ +#define __ASM_GNTTAB_H__ + +#include <linux/config.h> +#include <asm/hypervisor.h> +#include <xen/interface/grant_table.h> + +/* NR_GRANT_FRAMES must be less than or equal to that configured in Xen */ +#ifdef __ia64__ +#define NR_GRANT_FRAMES 1 +#else +#define NR_GRANT_FRAMES 4 +#endif + +struct gnttab_free_callback { + struct gnttab_free_callback *next; + void (*fn)(void *); + void *arg; + u16 count; +}; + +int gnttab_grant_foreign_access(domid_t domid, unsigned long frame, + int readonly); + +/* + * End access through the given grant reference, iff the grant entry is no + * longer in use. Return 1 if the grant entry was freed, 0 if it is still in + * use. + */ +int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly); + +/* + * Eventually end access through the given grant reference, and once that + * access has been ended, free the given page too. Access will be ended + * immediately iff the grant entry is not in use, otherwise it will happen + * some time later. page may be 0, in which case no freeing will occur. + */ +void gnttab_end_foreign_access(grant_ref_t ref, int readonly, + unsigned long page); + +int gnttab_grant_foreign_transfer(domid_t domid); + +unsigned long gnttab_end_foreign_transfer_ref(grant_ref_t ref); +unsigned long gnttab_end_foreign_transfer(grant_ref_t ref); + +int gnttab_query_foreign_access(grant_ref_t ref); + +/* + * operations on reserved batches of grant references + */ +int gnttab_alloc_grant_references(u16 count, grant_ref_t *pprivate_head); + +void gnttab_free_grant_reference(grant_ref_t ref); + +void gnttab_free_grant_references(grant_ref_t head); + +int gnttab_claim_grant_reference(grant_ref_t *pprivate_head); + +void gnttab_release_grant_reference(grant_ref_t *private_head, + grant_ref_t release); + +void gnttab_request_free_callback(struct gnttab_free_callback *callback, + void (*fn)(void *), void *arg, u16 count); + +void gnttab_grant_foreign_access_ref(grant_ref_t ref, domid_t domid, + unsigned long frame, int readonly); + +void gnttab_grant_foreign_transfer_ref(grant_ref_t, domid_t domid); + +#ifdef __ia64__ +#define gnttab_map_vaddr(map) __va(map.dev_bus_addr) +#else +#define gnttab_map_vaddr(map) ((void *)(map.host_virt_addr)) +#endif + +#endif /* __ASM_GNTTAB_H__ */ + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/xen/net_driver_util.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/xen/net_driver_util.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,56 @@ +/***************************************************************************** + * + * Utility functions for Xen network devices. + * + * Copyright (c) 2005 XenSource Ltd. + * + * This file may be distributed separately from the Linux kernel, or + * incorporated into other software packages, subject to the following + * license: + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject + * to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +#ifndef _ASM_XEN_NET_DRIVER_UTIL_H +#define _ASM_XEN_NET_DRIVER_UTIL_H + + +#include <xen/xenbus.h> + + +/** + * Read the 'mac' node at the given device's node in the store, and parse that + * as colon-separated octets, placing result the given mac array. mac must be + * a preallocated array of length ETH_ALEN (as declared in linux/if_ether.h). + * Return 0 on success, or -errno on error. + */ +int xen_net_read_mac(struct xenbus_device *dev, u8 mac[]); + + +#endif /* _ASM_XEN_NET_DRIVER_UTIL_H */ + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/xen/public/evtchn.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/xen/public/evtchn.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,98 @@ +/****************************************************************************** + * evtchn.h + * + * Interface to /dev/xen/evtchn. + * + * Copyright (c) 2003-2005, K A Fraser + * + * This file may be distributed separately from the Linux kernel, or + * incorporated into other software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef __LINUX_PUBLIC_EVTCHN_H__ +#define __LINUX_PUBLIC_EVTCHN_H__ + +/* /dev/xen/evtchn resides at device number major=10, minor=201 */ +#define EVTCHN_MINOR 201 + +/* + * Bind a fresh port to VIRQ @virq. + * Return allocated port. + */ +#define IOCTL_EVTCHN_BIND_VIRQ \ + _IOC(_IOC_NONE, 'E', 0, sizeof(struct ioctl_evtchn_bind_virq)) +struct ioctl_evtchn_bind_virq { + unsigned int virq; +}; + +/* + * Bind a fresh port to remote <@remote_domain, @remote_port>. + * Return allocated port. + */ +#define IOCTL_EVTCHN_BIND_INTERDOMAIN \ + _IOC(_IOC_NONE, 'E', 1, sizeof(struct ioctl_evtchn_bind_interdomain)) +struct ioctl_evtchn_bind_interdomain { + unsigned int remote_domain, remote_port; +}; + +/* + * Allocate a fresh port for binding to @remote_domain. + * Return allocated port. + */ +#define IOCTL_EVTCHN_BIND_UNBOUND_PORT \ + _IOC(_IOC_NONE, 'E', 2, sizeof(struct ioctl_evtchn_bind_unbound_port)) +struct ioctl_evtchn_bind_unbound_port { + unsigned int remote_domain; +}; + +/* + * Unbind previously allocated @port. + */ +#define IOCTL_EVTCHN_UNBIND \ + _IOC(_IOC_NONE, 'E', 3, sizeof(struct ioctl_evtchn_unbind)) +struct ioctl_evtchn_unbind { + unsigned int port; +}; + +/* + * Unbind previously allocated @port. + */ +#define IOCTL_EVTCHN_NOTIFY \ + _IOC(_IOC_NONE, 'E', 4, sizeof(struct ioctl_evtchn_notify)) +struct ioctl_evtchn_notify { + unsigned int port; +}; + +/* Clear and reinitialise the event buffer. Clear error condition. */ +#define IOCTL_EVTCHN_RESET \ + _IOC(_IOC_NONE, 'E', 5, 0) + +#endif /* __LINUX_PUBLIC_EVTCHN_H__ */ + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/xen/public/privcmd.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/xen/public/privcmd.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,91 @@ +/****************************************************************************** + * privcmd.h + * + * Interface to /proc/xen/privcmd. + * + * Copyright (c) 2003-2005, K A Fraser + * + * This file may be distributed separately from the Linux kernel, or + * incorporated into other software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef __LINUX_PUBLIC_PRIVCMD_H__ +#define __LINUX_PUBLIC_PRIVCMD_H__ + +#ifndef __user +#define __user +#endif + +typedef struct privcmd_hypercall +{ + unsigned long op; + unsigned long arg[5]; +} privcmd_hypercall_t; + +typedef struct privcmd_mmap_entry { + unsigned long va; + unsigned long mfn; + unsigned long npages; +} privcmd_mmap_entry_t; + +typedef struct privcmd_mmap { + int num; + domid_t dom; /* target domain */ + privcmd_mmap_entry_t __user *entry; +} privcmd_mmap_t; + +typedef struct privcmd_mmapbatch { + int num; /* number of pages to populate */ + domid_t dom; /* target domain */ + unsigned long addr; /* virtual address */ + unsigned long __user *arr; /* array of mfns - top nibble set on err */ +} privcmd_mmapbatch_t; + +typedef struct privcmd_blkmsg +{ + unsigned long op; + void *buf; + int buf_size; +} privcmd_blkmsg_t; + +/* + * @cmd: IOCTL_PRIVCMD_HYPERCALL + * @arg: &privcmd_hypercall_t + * Return: Value returned from execution of the specified hypercall. + */ +#define IOCTL_PRIVCMD_HYPERCALL \ + _IOC(_IOC_NONE, 'P', 0, sizeof(privcmd_hypercall_t)) +#define IOCTL_PRIVCMD_MMAP \ + _IOC(_IOC_NONE, 'P', 2, sizeof(privcmd_mmap_t)) +#define IOCTL_PRIVCMD_MMAPBATCH \ + _IOC(_IOC_NONE, 'P', 3, sizeof(privcmd_mmapbatch_t)) + +#endif /* __LINUX_PUBLIC_PRIVCMD_H__ */ + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/xen/public/xenstored.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/xen/public/xenstored.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,89 @@ +/* + * Simple prototyle Xen Store Daemon providing simple tree-like database. + * Copyright (C) 2005 Rusty Russell IBM Corporation + * + * This file may be distributed separately from the Linux kernel, or + * incorporated into other software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef _XENSTORED_H +#define _XENSTORED_H + +enum xsd_sockmsg_type +{ + XS_DEBUG, + XS_SHUTDOWN, + XS_DIRECTORY, + XS_READ, + XS_GET_PERMS, + XS_WATCH, + XS_WATCH_ACK, + XS_UNWATCH, + XS_TRANSACTION_START, + XS_TRANSACTION_END, + XS_OP_READ_ONLY = XS_TRANSACTION_END, + XS_INTRODUCE, + XS_RELEASE, + XS_GET_DOMAIN_PATH, + XS_WRITE, + XS_MKDIR, + XS_RM, + XS_SET_PERMS, + XS_WATCH_EVENT, + XS_ERROR, +}; + +#define XS_WRITE_NONE "NONE" +#define XS_WRITE_CREATE "CREATE" +#define XS_WRITE_CREATE_EXCL "CREATE|EXCL" + +/* We hand errors as strings, for portability. */ +struct xsd_errors +{ + int errnum; + const char *errstring; +}; +#define XSD_ERROR(x) { x, #x } +static struct xsd_errors xsd_errors[] __attribute__((unused)) = { + XSD_ERROR(EINVAL), + XSD_ERROR(EACCES), + XSD_ERROR(EEXIST), + XSD_ERROR(EISDIR), + XSD_ERROR(ENOENT), + XSD_ERROR(ENOMEM), + XSD_ERROR(ENOSPC), + XSD_ERROR(EIO), + XSD_ERROR(ENOTEMPTY), + XSD_ERROR(ENOSYS), + XSD_ERROR(EROFS), + XSD_ERROR(EBUSY), + XSD_ERROR(EAGAIN), + XSD_ERROR(EISCONN), +}; +struct xsd_sockmsg +{ + u32 type; + u32 len; /* Length of data following this. */ + + /* Generally followed by nul-terminated string(s). */ +}; + +#endif /* _XENSTORED_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/xen/tpmfe.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/xen/tpmfe.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,33 @@ +#ifndef TPM_FE_H +#define TPM_FE_H + +struct tpmfe_device { + /* + * Let upper layer receive data from front-end + */ + int (*receive)(const u8 *buffer, size_t count, const void *ptr); + /* + * Indicate the status of the front-end to the upper + * layer. + */ + void (*status)(unsigned int flags); + + /* + * This field indicates the maximum size the driver can + * transfer in one chunk. It is filled out by the front-end + * driver and should be propagated to the generic tpm driver + * for allocation of buffers. + */ + unsigned int max_tx_size; +}; + +enum { + TPMFE_STATUS_DISCONNECTED = 0x0, + TPMFE_STATUS_CONNECTED = 0x1 +}; + +int tpm_fe_send(const u8 * buf, size_t count, void *ptr); +int tpm_fe_register_receiver(struct tpmfe_device *); +void tpm_fe_unregister_receiver(void); + +#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/xen/xen_proc.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/xen/xen_proc.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,23 @@ + +#ifndef __ASM_XEN_PROC_H__ +#define __ASM_XEN_PROC_H__ + +#include <linux/config.h> +#include <linux/proc_fs.h> + +extern struct proc_dir_entry *create_xen_proc_entry( + const char *name, mode_t mode); +extern void remove_xen_proc_entry( + const char *name); + +#endif /* __ASM_XEN_PROC_H__ */ + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/xen/xenbus.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/xen/xenbus.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,254 @@ +/****************************************************************************** + * xenbus.h + * + * Talks to Xen Store to figure out what devices we have. + * + * Copyright (C) 2005 Rusty Russell, IBM Corporation + * Copyright (C) 2005 XenSource Ltd. + * + * This file may be distributed separately from the Linux kernel, or + * incorporated into other software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef _ASM_XEN_XENBUS_H +#define _ASM_XEN_XENBUS_H + +#include <linux/device.h> +#include <linux/notifier.h> +#include <asm/semaphore.h> +#include <xen/interface/io/xenbus.h> +#include <xen/interface/io/xs_wire.h> + +#define XBT_NULL 0 + +/* Register callback to watch this node. */ +struct xenbus_watch +{ + struct list_head list; + + /* Path being watched. */ + const char *node; + + /* Callback (executed in a process context with no locks held). */ + void (*callback)(struct xenbus_watch *, + const char **vec, unsigned int len); +}; + + +/* A xenbus device. */ +struct xenbus_device { + const char *devicetype; + const char *nodename; + const char *otherend; + int otherend_id; + struct xenbus_watch otherend_watch; + struct device dev; + int has_error; + void *data; +}; + +static inline struct xenbus_device *to_xenbus_device(struct device *dev) +{ + return container_of(dev, struct xenbus_device, dev); +} + +struct xenbus_device_id +{ + /* .../device/<device_type>/<identifier> */ + char devicetype[32]; /* General class of device. */ +}; + +/* A xenbus driver. */ +struct xenbus_driver { + char *name; + struct module *owner; + const struct xenbus_device_id *ids; + int (*probe)(struct xenbus_device *dev, + const struct xenbus_device_id *id); + void (*otherend_changed)(struct xenbus_device *dev, + XenbusState backend_state); + int (*remove)(struct xenbus_device *dev); + int (*suspend)(struct xenbus_device *dev); + int (*resume)(struct xenbus_device *dev); + int (*hotplug)(struct xenbus_device *, char **, int, char *, int); + struct device_driver driver; + int (*read_otherend_details)(struct xenbus_device *dev); +}; + +static inline struct xenbus_driver *to_xenbus_driver(struct device_driver *drv) +{ + return container_of(drv, struct xenbus_driver, driver); +} + +int xenbus_register_frontend(struct xenbus_driver *drv); +int xenbus_register_backend(struct xenbus_driver *drv); +void xenbus_unregister_driver(struct xenbus_driver *drv); + +typedef u32 xenbus_transaction_t; + +char **xenbus_directory(xenbus_transaction_t t, + const char *dir, const char *node, unsigned int *num); +void *xenbus_read(xenbus_transaction_t t, + const char *dir, const char *node, unsigned int *len); +int xenbus_write(xenbus_transaction_t t, + const char *dir, const char *node, const char *string); +int xenbus_mkdir(xenbus_transaction_t t, + const char *dir, const char *node); +int xenbus_exists(xenbus_transaction_t t, + const char *dir, const char *node); +int xenbus_rm(xenbus_transaction_t t, const char *dir, const char *node); +int xenbus_transaction_start(xenbus_transaction_t *t); +int xenbus_transaction_end(xenbus_transaction_t t, int abort); + +/* Single read and scanf: returns -errno or num scanned if > 0. */ +int xenbus_scanf(xenbus_transaction_t t, + const char *dir, const char *node, const char *fmt, ...) + __attribute__((format(scanf, 4, 5))); + +/* Single printf and write: returns -errno or 0. */ +int xenbus_printf(xenbus_transaction_t t, + const char *dir, const char *node, const char *fmt, ...) + __attribute__((format(printf, 4, 5))); + +/* Generic read function: NULL-terminated triples of name, + * sprintf-style type string, and pointer. Returns 0 or errno.*/ +int xenbus_gather(xenbus_transaction_t t, const char *dir, ...); + +/* notifer routines for when the xenstore comes up */ +int register_xenstore_notifier(struct notifier_block *nb); +void unregister_xenstore_notifier(struct notifier_block *nb); + +int register_xenbus_watch(struct xenbus_watch *watch); +void unregister_xenbus_watch(struct xenbus_watch *watch); +void xs_suspend(void); +void xs_resume(void); + +/* Used by xenbus_dev to borrow kernel's store connection. */ +void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg); + +/* Called from xen core code. */ +void xenbus_suspend(void); +void xenbus_resume(void); + +#define XENBUS_IS_ERR_READ(str) ({ \ + if (!IS_ERR(str) && strlen(str) == 0) { \ + kfree(str); \ + str = ERR_PTR(-ERANGE); \ + } \ + IS_ERR(str); \ +}) + +#define XENBUS_EXIST_ERR(err) ((err) == -ENOENT || (err) == -ERANGE) + + +/** + * Register a watch on the given path, using the given xenbus_watch structure + * for storage, and the given callback function as the callback. Return 0 on + * success, or -errno on error. On success, the given path will be saved as + * watch->node, and remains the caller's to free. On error, watch->node will + * be NULL, the device will switch to XenbusStateClosing, and the error will + * be saved in the store. + */ +int xenbus_watch_path(struct xenbus_device *dev, const char *path, + struct xenbus_watch *watch, + void (*callback)(struct xenbus_watch *, + const char **, unsigned int)); + + +/** + * Register a watch on the given path/path2, using the given xenbus_watch + * structure for storage, and the given callback function as the callback. + * Return 0 on success, or -errno on error. On success, the watched path + * (path/path2) will be saved as watch->node, and becomes the caller's to + * kfree(). On error, watch->node will be NULL, so the caller has nothing to + * free, the device will switch to XenbusStateClosing, and the error will be + * saved in the store. + */ +int xenbus_watch_path2(struct xenbus_device *dev, const char *path, + const char *path2, struct xenbus_watch *watch, + void (*callback)(struct xenbus_watch *, + const char **, unsigned int)); + + +/** + * Advertise in the store a change of the given driver to the given new_state. + * Perform the change inside the given transaction xbt. xbt may be NULL, in + * which case this is performed inside its own transaction. Return 0 on + * success, or -errno on error. On error, the device will switch to + * XenbusStateClosing, and the error will be saved in the store. + */ +int xenbus_switch_state(struct xenbus_device *dev, + xenbus_transaction_t xbt, + XenbusState new_state); + + +/** + * Grant access to the given ring_mfn to the peer of the given device. Return + * 0 on success, or -errno on error. On error, the device will switch to + * XenbusStateClosing, and the error will be saved in the store. + */ +int xenbus_grant_ring(struct xenbus_device *dev, unsigned long ring_mfn); + + +/** + * Allocate an event channel for the given xenbus_device, assigning the newly + * created local port to *port. Return 0 on success, or -errno on error. On + * error, the device will switch to XenbusStateClosing, and the error will be + * saved in the store. + */ +int xenbus_alloc_evtchn(struct xenbus_device *dev, int *port); + + +/** + * Return the state of the driver rooted at the given store path, or + * XenbusStateClosed if no state can be read. + */ +XenbusState xenbus_read_driver_state(const char *path); + + +/*** + * Report the given negative errno into the store, along with the given + * formatted message. + */ +void xenbus_dev_error(struct xenbus_device *dev, int err, const char *fmt, + ...); + + +/*** + * Equivalent to xenbus_dev_error(dev, err, fmt, args), followed by + * xenbus_switch_state(dev, NULL, XenbusStateClosing) to schedule an orderly + * closedown of this driver and its peer. + */ +void xenbus_dev_fatal(struct xenbus_device *dev, int err, const char *fmt, + ...); + + +#endif /* _ASM_XEN_XENBUS_H */ + +/* + * Local variables: + * c-file-style: "linux" + * indent-tabs-mode: t + * c-indent-level: 8 + * c-basic-offset: 8 + * tab-width: 8 + * End: + */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/xen/xencons.h --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/include/xen/xencons.h Mon Jan 30 17:18:27 2006 @@ -0,0 +1,14 @@ +#ifndef __ASM_XENCONS_H__ +#define __ASM_XENCONS_H__ + +void xencons_force_flush(void); +void xencons_resume(void); + +/* Interrupt work hooks. Receive data, or kick data out. */ +void xencons_rx(char *buf, unsigned len, struct pt_regs *regs); +void xencons_tx(void); + +int xencons_ring_init(void); +int xencons_ring_send(const char *data, unsigned len); + +#endif /* __ASM_XENCONS_H__ */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/lib/Kconfig.debug --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/lib/Kconfig.debug Mon Jan 30 17:18:27 2006 @@ -0,0 +1,161 @@ + +config PRINTK_TIME + bool "Show timing information on printks" + help + Selecting this option causes timing information to be + included in printk output. This allows you to measure + the interval between kernel operations, including bootup + operations. This is useful for identifying long delays + in kernel startup. + + +config DEBUG_KERNEL + bool "Kernel debugging" + help + Say Y here if you are developing drivers or trying to debug and + identify kernel problems. + +config MAGIC_SYSRQ + bool "Magic SysRq key" + depends on DEBUG_KERNEL && !UML + help + If you say Y here, you will have some control over the system even + if the system crashes for example during kernel debugging (e.g., you + will be able to flush the buffer cache to disk, reboot the system + immediately or dump some status information). This is accomplished + by pressing various keys while holding SysRq (Alt+PrintScreen). It + also works on a serial console (on PC hardware at least), if you + send a BREAK and then within 5 seconds a command keypress. The + keys are documented in <file:Documentation/sysrq.txt>. Don't say Y + unless you really know what this hack does. + +config LOG_BUF_SHIFT + int "Kernel log buffer size (16 => 64KB, 17 => 128KB)" if DEBUG_KERNEL + range 12 21 + default 17 if ARCH_S390 + default 16 if X86_NUMAQ || IA64 + default 15 if SMP + default 14 + help + Select kernel log buffer size as a power of 2. + Defaults and Examples: + 17 => 128 KB for S/390 + 16 => 64 KB for x86 NUMAQ or IA-64 + 15 => 32 KB for SMP + 14 => 16 KB for uniprocessor + 13 => 8 KB + 12 => 4 KB + +config SCHEDSTATS + bool "Collect scheduler statistics" + depends on DEBUG_KERNEL && PROC_FS + help + If you say Y here, additional code will be inserted into the + scheduler and related routines to collect statistics about + scheduler behavior and provide them in /proc/schedstat. These + stats may be useful for both tuning and debugging the scheduler + If you aren't debugging the scheduler or trying to tune a specific + application, you can say N to avoid the very slight overhead + this adds. + +config DEBUG_SLAB + bool "Debug memory allocations" + depends on DEBUG_KERNEL + help + Say Y here to have the kernel do limited verification on memory + allocation as well as poisoning memory on free to catch use of freed + memory. This can make kmalloc/kfree-intensive workloads much slower. + +config DEBUG_PREEMPT + bool "Debug preemptible kernel" + depends on DEBUG_KERNEL && PREEMPT + default y + help + If you say Y here then the kernel will use a debug variant of the + commonly used smp_processor_id() function and will print warnings + if kernel code uses it in a preemption-unsafe way. Also, the kernel + will detect preemption count underflows. + +config DEBUG_SPINLOCK + bool "Spinlock debugging" + depends on DEBUG_KERNEL + help + Say Y here and build SMP to catch missing spinlock initialization + and certain other kinds of spinlock errors commonly made. This is + best used in conjunction with the NMI watchdog so that spinlock + deadlocks are also debuggable. + +config DEBUG_SPINLOCK_SLEEP + bool "Sleep-inside-spinlock checking" + depends on DEBUG_KERNEL + help + If you say Y here, various routines which may sleep will become very + noisy if they are called with a spinlock held. + +config DEBUG_KOBJECT + bool "kobject debugging" + depends on DEBUG_KERNEL + help + If you say Y here, some extra kobject debugging messages will be sent + to the syslog. + +config DEBUG_HIGHMEM + bool "Highmem debugging" + depends on DEBUG_KERNEL && HIGHMEM + help + This options enables addition error checking for high memory systems. + Disable for production systems. + +config DEBUG_BUGVERBOSE + bool "Verbose BUG() reporting (adds 70K)" if DEBUG_KERNEL && EMBEDDED + depends on BUG + depends on ARM || ARM26 || M32R || M68K || SPARC32 || SPARC64 || (X86 && !X86_64) || FRV + default !EMBEDDED + help + Say Y here to make BUG() panics output the file name and line number + of the BUG call as well as the EIP and oops trace. This aids + debugging but costs about 70-100K of memory. + +config DEBUG_INFO + bool "Compile the kernel with debug info" + depends on DEBUG_KERNEL && !X86_64_XEN + help + If you say Y here the resulting kernel image will include + debugging info resulting in a larger kernel image. + Say Y here only if you plan to debug the kernel. + + If unsure, say N. + +config DEBUG_IOREMAP + bool "Enable ioremap() debugging" + depends on DEBUG_KERNEL && PARISC + help + Enabling this option will cause the kernel to distinguish between + ioremapped and physical addresses. It will print a backtrace (at + most one every 10 seconds), hopefully allowing you to see which + drivers need work. Fixing all these problems is a prerequisite + for turning on USE_HPPA_IOREMAP. The warnings are harmless; + the kernel has enough information to fix the broken drivers + automatically, but we'd like to make it more efficient by not + having to do that. + +config DEBUG_FS + bool "Debug Filesystem" + depends on DEBUG_KERNEL + help + debugfs is a virtual file system that kernel developers use to put + debugging files into. Enable this option to be able to read and + write to these files. + + If unsure, say N. + +config FRAME_POINTER + bool "Compile the kernel with frame pointers" + depends on DEBUG_KERNEL && ((X86 && !X86_64) || CRIS || M68K || M68KNOMMU || FRV || UML) + default y if DEBUG_INFO && UML + help + If you say Y here the resulting kernel image will be slightly larger + and slower, but it will give very useful debugging information. + If you don't debug the kernel, you can say N, but we may not be able + to solve problems without frame pointers. + diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/scripts/Makefile.xen --- /dev/null Mon Jan 30 12:35:43 2006 +++ b/linux-2.6-xen-sparse/scripts/Makefile.xen Mon Jan 30 17:18:27 2006 @@ -0,0 +1,14 @@ + +# cherrypickxen($1 = allobj) +cherrypickxen = $(foreach var, $(1), \ + $(shell o=$(var); \ + c=$${o/%.o/-xen.c}; \ + s=$${o/%.o/-xen.S}; \ + oxen=$${o/%.o/-xen.o}; \ + [ -f $(srctree)/$(src)/$${c} ] || \ + [ -f $(srctree)/$(src)/$${s} ] \ + && echo $$oxen \ + || echo $(var) ) \ + ) +# filterxen($1 = allobj, $2 = noobjs) +filterxen = $(filter-out $(2), $(1)) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/Kconfig --- a/linux-2.6-xen-sparse/arch/xen/Kconfig Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,212 +0,0 @@ -# -# For a description of the syntax of this configuration file, -# see Documentation/kbuild/kconfig-language.txt. -# - -mainmenu "Linux Kernel Configuration" - -config XEN - bool - default y - help - This is the Linux Xen port. - -config ARCH_XEN - bool - default y - - -config NO_IDLE_HZ - bool - default y - - -menu "XEN" - -config XEN_PRIVILEGED_GUEST - bool "Privileged Guest (domain 0)" - default n - select XEN_PHYSDEV_ACCESS - help - Support for privileged operation (domain 0) - -config XEN_PHYSDEV_ACCESS - bool "Physical device access" - default XEN_PRIVILEGED_GUEST - help - Assume access is available to physical hardware devices - (e.g., hard drives, network cards). This allows you to configure - such devices and also includes some low-level support that is - otherwise not compiled into the kernel. - -config XEN_BLKDEV_BACKEND - bool "Block-device backend driver" - depends on XEN_PHYSDEV_ACCESS - default y - help - The block-device backend driver allows the kernel to export its - block devices to other guests via a high-performance shared-memory - interface. - -config XEN_BLKDEV_TAP_BE - bool "Block Tap support for backend driver (DANGEROUS)" - depends on XEN_BLKDEV_BACKEND - default n - help - If you intend to use the block tap driver, the backend domain will - not know the domain id of the real frontend, and so will not be able - to map its data pages. This modifies the backend to attempt to map - from both the tap domain and the real frontend. This presents a - security risk, and so should ONLY be used for development - with the blktap. This option will be removed as the block drivers are - modified to use grant tables. - -config XEN_NETDEV_BACKEND - bool "Network-device backend driver" - depends on XEN_PHYSDEV_ACCESS - default y - help - The network-device backend driver allows the kernel to export its - network devices to other guests via a high-performance shared-memory - interface. - -config XEN_NETDEV_PIPELINED_TRANSMITTER - bool "Pipelined transmitter (DANGEROUS)" - depends on XEN_NETDEV_BACKEND - default n - help - If the net backend is a dumb domain, such as a transparent Ethernet - bridge with no local IP interface, it is safe to say Y here to get - slightly lower network overhead. - If the backend has a local IP interface; or may be doing smart things - like reassembling packets to perform firewall filtering; or if you - are unsure; or if you experience network hangs when this option is - enabled; then you must say N here. - -config XEN_TPMDEV_FRONTEND - bool "TPM-device frontend driver" - default n - select TCG_TPM - select TCG_XEN - help - The TPM-device frontend driver. - -config XEN_TPMDEV_BACKEND - bool "TPM-device backend driver" - default n - help - The TPM-device backend driver - -config XEN_TPMDEV_CLOSE_IF_VTPM_FAILS - bool "TPM backend closes upon vTPM failure" - depends on XEN_TPMDEV_BACKEND - default n - help - The TPM backend closes the channel if the vTPM in userspace indicates - a failure. The corresponding domain's channel will be closed. - Say Y if you want this feature. - -config XEN_BLKDEV_FRONTEND - tristate "Block-device frontend driver" - default y - help - The block-device frontend driver allows the kernel to access block - devices mounted within another guest OS. Unless you are building a - dedicated device-driver domain, or your master control domain - (domain 0), then you almost certainly want to say Y here. - -config XEN_NETDEV_FRONTEND - tristate "Network-device frontend driver" - default y - help - The network-device frontend driver allows the kernel to access - network interfaces within another guest OS. Unless you are building a - dedicated device-driver domain, or your master control domain - (domain 0), then you almost certainly want to say Y here. - -config XEN_BLKDEV_TAP - bool "Block device tap driver" - default n - help - This driver allows a VM to interact on block device channels - to other VMs. Block messages may be passed through or redirected - to a character device, allowing device prototyping in application - space. Odds are that you want to say N here. - -config XEN_SHADOW_MODE - bool "Fake shadow mode" - default n - help - fakes out a shadow mode kernel - - -config XEN_SCRUB_PAGES - bool "Scrub memory before freeing it to Xen" - default y - help - Erase memory contents before freeing it back to Xen's global - pool. This ensures that any secrets contained within that - memory (e.g., private keys) cannot be found by other guests that - may be running on the machine. Most people will want to say Y here. - If security is not a concern then you may increase performance by - saying N. - -choice - prompt "Processor Type" - default XEN_X86 - -config XEN_X86 - bool "X86" - help - Choose this option if your computer is a X86 architecture. - -config XEN_X86_64 - bool "X86_64" - help - Choose this option if your computer is a X86_64 architecture. - -endchoice - -endmenu - -config HAVE_ARCH_ALLOC_SKB - bool - default y - -config HAVE_ARCH_DEV_ALLOC_SKB - bool - default y - -source "init/Kconfig" - -if XEN_X86 -source "arch/xen/i386/Kconfig" -endif - -if XEN_X86_64 -source "arch/xen/x86_64/Kconfig" -endif - -menu "Executable file formats" - -source "fs/Kconfig.binfmt" - -endmenu - -source "arch/xen/Kconfig.drivers" - -if XEN_PRIVILEGED_GUEST -menu "Power management options" -source "drivers/acpi/Kconfig" -endmenu -endif - -source "fs/Kconfig" - -source "security/Kconfig" - -source "crypto/Kconfig" - -source "lib/Kconfig" - -source "arch/xen/Kconfig.debug" diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/Kconfig.debug --- a/linux-2.6-xen-sparse/arch/xen/Kconfig.debug Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,129 +0,0 @@ -menu "Kernel hacking" - -source "lib/Kconfig.debug" - -# X86 -config EARLY_PRINTK - bool "Early printk" if EMBEDDED && DEBUG_KERNEL - default y - depends on X86 - help - Write kernel log output directly into the VGA buffer or to a serial - port. - - This is useful for kernel debugging when your machine crashes very - early before the console code is initialized. For normal operation - it is not recommended because it looks ugly and doesn't cooperate - with klogd/syslogd or the X server. You should normally N here, - unless you want to debug such a crash. - -config DEBUG_STACKOVERFLOW - bool "Check for stack overflows" - depends on DEBUG_KERNEL && X86 - -config KPROBES - bool "Kprobes" - depends on DEBUG_KERNEL && X86 - help - Kprobes allows you to trap at almost any kernel address and - execute a callback function. register_kprobe() establishes - a probepoint and specifies the callback. Kprobes is useful - for kernel debugging, non-intrusive instrumentation and testing. - If in doubt, say "N". - -config DEBUG_STACK_USAGE - bool "Stack utilization instrumentation" - depends on DEBUG_KERNEL && X86 - help - Enables the display of the minimum amount of free stack which each - task has ever had available in the sysrq-T and sysrq-P debug output. - - This option will slow down process creation somewhat. - -comment "Page alloc debug is incompatible with Software Suspend on i386" - depends on DEBUG_KERNEL && SOFTWARE_SUSPEND && X86 - -config DEBUG_PAGEALLOC - bool "Page alloc debugging" - depends on DEBUG_KERNEL && !SOFTWARE_SUSPEND && X86 - help - Unmap pages from the kernel linear mapping after free_pages(). - This results in a large slowdown, but helps to find certain types - of memory corruptions. - -config 4KSTACKS - bool "Use 4Kb for kernel stacks instead of 8Kb" - depends on DEBUG_KERNEL && X86 - help - If you say Y here the kernel will use a 4Kb stacksize for the - kernel stack attached to each process/thread. This facilitates - running more threads on a system and also reduces the pressure - on the VM subsystem for higher order allocations. This option - will also use IRQ stacks to compensate for the reduced stackspace. - -config X86_FIND_SMP_CONFIG - bool - depends on X86_LOCAL_APIC || X86_VOYAGER && X86 - default y - -config X86_MPPARSE - bool - depends on X86_LOCAL_APIC && !X86_VISWS && X86 - default y - -# X86_64 - -# !SMP for now because the context switch early causes GPF in segment reloading -# and the GS base checking does the wrong thing then, causing a hang. -config CHECKING - bool "Additional run-time checks" - depends on DEBUG_KERNEL && !SMP && X86_64 - help - Enables some internal consistency checks for kernel debugging. - You should normally say N. - -config INIT_DEBUG - bool "Debug __init statements" - depends on DEBUG_KERNEL && X86_64 - help - Fill __init and __initdata at the end of boot. This helps debugging - illegal uses of __init and __initdata after initialization. - -config IOMMU_DEBUG - depends on GART_IOMMU && DEBUG_KERNEL && X86_64 - bool "Enable IOMMU debugging" - help - Force the IOMMU to on even when you have less than 4GB of - memory and add debugging code. On overflow always panic. And - allow to enable IOMMU leak tracing. Can be disabled at boot - time with iommu=noforce. This will also enable scatter gather - list merging. Currently not recommended for production - code. When you use it make sure you have a big enough - IOMMU/AGP aperture. Most of the options enabled by this can - be set more finegrained using the iommu= command line - options. See Documentation/x86_64/boot-options.txt for more - details. - -config IOMMU_LEAK - bool "IOMMU leak tracing" - depends on DEBUG_KERNEL && X86_64 - depends on IOMMU_DEBUG - help - Add a simple leak tracer to the IOMMU code. This is useful when you - are debugging a buggy device driver that leaks IOMMU mappings. - -#config X86_REMOTE_DEBUG -# bool "kgdb debugging stub" - -# X86 & X86_64 -config KPROBES - bool "Kprobes" - depends on DEBUG_KERNEL - help - Kprobes allows you to trap at almost any kernel address and - execute a callback function. register_kprobe() establishes - a probepoint and specifies the callback. Kprobes is useful - for kernel debugging, non-intrusive instrumentation and testing. - If in doubt, say "N". - -endmenu diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/Kconfig.drivers --- a/linux-2.6-xen-sparse/arch/xen/Kconfig.drivers Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,98 +0,0 @@ -# arch/xen/Kconfig.drivers - -menu "Device Drivers" - -source "drivers/base/Kconfig" - -if XEN_PHYSDEV_ACCESS -source "drivers/mtd/Kconfig" -source "drivers/parport/Kconfig" -source "drivers/pnp/Kconfig" -endif - -source "drivers/block/Kconfig" - -if XEN_PHYSDEV_ACCESS -source "drivers/ide/Kconfig" -endif - -source "drivers/scsi/Kconfig" - -if XEN_PHYSDEV_ACCESS -source "drivers/cdrom/Kconfig" -endif - -source "drivers/md/Kconfig" - -if XEN_PHYSDEV_ACCESS -source "drivers/message/fusion/Kconfig" -source "drivers/ieee1394/Kconfig" -source "drivers/message/i2o/Kconfig" -endif - -source "net/Kconfig" - -if XEN_PHYSDEV_ACCESS -source "drivers/isdn/Kconfig" -source "drivers/telephony/Kconfig" -source "drivers/input/Kconfig" -source "drivers/char/Kconfig" -source "drivers/i2c/Kconfig" -source "drivers/w1/Kconfig" -source "drivers/misc/Kconfig" -source "drivers/media/Kconfig" -source "drivers/video/Kconfig" -source "sound/Kconfig" -source "drivers/usb/Kconfig" -source "drivers/mmc/Kconfig" -source "drivers/infiniband/Kconfig" -endif - -if !XEN_PHYSDEV_ACCESS -source "drivers/char/tpm/Kconfig.domU" -endif - -if !XEN_PHYSDEV_ACCESS - -menu "Character devices" - -config UNIX98_PTYS - bool - default y - -config LEGACY_PTYS - bool "Legacy (BSD) PTY support" - default y - ---help--- - A pseudo terminal (PTY) is a software device consisting of two - halves: a master and a slave. The slave device behaves identical to - a physical terminal; the master device is used by a process to - read data from and write data to the slave, thereby emulating a - terminal. Typical programs for the master side are telnet servers - and xterms. - - Linux has traditionally used the BSD-like names /dev/ptyxx - for masters and /dev/ttyxx for slaves of pseudo - terminals. This scheme has a number of problems, including - security. This option enables these legacy devices; on most - systems, it is safe to say N. - - -config LEGACY_PTY_COUNT - int "Maximum number of legacy PTY in use" - depends on LEGACY_PTYS - range 1 256 - default "256" - ---help--- - The maximum number of legacy PTYs that can be used at any one time. - The default is 256, and should be more than enough. Embedded - systems may want to reduce this to save memory. - - When not in use, each legacy PTY occupies 12 bytes on 32-bit - architectures and 24 bytes on 64-bit architectures. - -endmenu - -endif - -endmenu diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/Makefile --- a/linux-2.6-xen-sparse/arch/xen/Makefile Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,93 +0,0 @@ -# -# xen/Makefile -# -# This file is included by the global makefile so that you can add your own -# architecture-specific flags and dependencies. Remember to do have actions -# for "archclean" cleaning up for this architecture. -# -# This file is subject to the terms and conditions of the GNU General Public -# License. See the file "COPYING" in the main directory of this archive -# for more details. -# -# Copyright (C) 2004 by Christian Limpach -# - -XENARCH := $(subst ",,$(CONFIG_XENARCH)) - -# pick up headers from include/asm-xen/asm in preference over include/asm -NOSTDINC_FLAGS = -nostdinc -iwithprefix include/asm-xen -Iinclude/asm-xen -iwithprefix include -ifneq ($(KBUILD_SRC),) -NOSTDINC_FLAGS += -I$(srctree)/include/asm-xen -endif - -# make uname return the processor arch -UTS_MACHINE := $(XENARCH) - -core-y += arch/xen/kernel/ - -.PHONY: include2/asm -include2/asm: -ifneq ($(KBUILD_SRC),) - @echo ' SYMLINK ../include/asm-$(XENARCH) -> include2/asm' - $(Q)ln -fsn ../include/asm-$(XENARCH) include2/asm -endif - -include/.asm-ignore: include/asm - @rm -f include/.asm-ignore - @mv include/asm include/.asm-ignore - @echo ' SYMLINK include/asm -> include/asm-$(XENARCH)' - $(Q)if [ ! -d include ]; then mkdir -p include; fi; - @ln -fsn $(srctree)/include/asm-$(XENARCH) include/asm - -include/asm-xen/asm: - @echo ' SYMLINK $@ -> include/asm-xen/asm-$(XENARCH)' - @mkdir -p include/asm-xen - @ln -fsn $(srctree)/include/asm-xen/asm-$(XENARCH) $@ - -arch/xen/arch: - @rm -f $@ - @mkdir -p arch/xen - @ln -fsn $(srctree)/arch/xen/$(XENARCH) $@ - -arch/$(XENARCH)/kernel/asm-offsets.s: include/asm include/linux/version.h \ - include/config/MARKER - -include/asm-$(ARCH)/asm_offsets.h: arch/$(XENARCH)/kernel/asm-offsets.s - $(call filechk,gen-asm-offsets) - -prepare: include/.asm-ignore include/asm-xen/asm \ - arch/xen/arch include/asm-$(ARCH)/asm_offsets.h include2/asm ; - -all: vmlinuz - -vmlinuz: vmlinux - $(Q)$(MAKE) $(build)=arch/xen/boot vmlinuz - -bzImage: vmlinuz - $(Q)$(MAKE) $(build)=arch/xen/boot bzImage - -XINSTALL_NAME ?= $(KERNELRELEASE) -install: vmlinuz -install kernel_install: - mkdir -p $(INSTALL_PATH)/boot - ln -f -s vmlinuz-$(XINSTALL_NAME)$(INSTALL_SUFFIX) $(INSTALL_PATH)/boot/vmlinuz-$(VERSION).$(PATCHLEVEL).$(SUBLEVEL)$(XENGUEST)$(INSTALL_SUFFIX) - rm -f $(INSTALL_PATH)/boot/vmlinuz-$(XINSTALL_NAME)$(INSTALL_SUFFIX) - install -m0644 vmlinuz $(INSTALL_PATH)/boot/vmlinuz-$(XINSTALL_NAME)$(INSTALL_SUFFIX) - install -m0644 vmlinux $(INSTALL_PATH)/boot/vmlinux-syms-$(XINSTALL_NAME)$(INSTALL_SUFFIX) - install -m0664 .config $(INSTALL_PATH)/boot/config-$(XINSTALL_NAME)$(INSTALL_SUFFIX) - install -m0664 System.map $(INSTALL_PATH)/boot/System.map-$(XINSTALL_NAME)$(INSTALL_SUFFIX) - ln -f -s vmlinuz-$(XINSTALL_NAME)$(INSTALL_SUFFIX) $(INSTALL_PATH)/boot/vmlinuz-$(VERSION).$(PATCHLEVEL)$(XENGUEST)$(INSTALL_SUFFIX) - -archclean: - @if [ -e arch/xen/arch ]; then $(MAKE) $(clean)=arch/xen/arch; fi; - @rm -f arch/xen/arch include/.asm-ignore include/asm-xen/asm - @rm -f vmlinux-stripped vmlinuz - -define archhelp - echo '* vmlinuz - Compressed kernel image' - echo ' install - Install kernel image and config file' -endef - -ifneq ($(XENARCH),) -include $(srctree)/arch/xen/$(XENARCH)/Makefile -endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/boot/Makefile --- a/linux-2.6-xen-sparse/arch/xen/boot/Makefile Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,11 +0,0 @@ - -OBJCOPYFLAGS := -g --strip-unneeded - -vmlinuz: vmlinux-stripped FORCE - $(call if_changed,gzip) - -vmlinux-stripped: vmlinux FORCE - $(call if_changed,objcopy) - -bzImage: vmlinuz - $(Q)ln -sf ../../../vmlinuz $(srctree)/arch/xen/boot/bzImage diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/configs/xen0_defconfig_ia64 --- a/linux-2.6-xen-sparse/arch/xen/configs/xen0_defconfig_ia64 Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,1405 +0,0 @@ -# -# Automatically generated make config: don't edit -# Linux kernel version: 2.6.12.6-xen0 -# Wed Dec 21 11:17:02 2005 -# - -# -# Code maturity level options -# -CONFIG_EXPERIMENTAL=y -CONFIG_CLEAN_COMPILE=y -CONFIG_LOCK_KERNEL=y -CONFIG_INIT_ENV_ARG_LIMIT=32 - -# -# General setup -# -CONFIG_LOCALVERSION="" -CONFIG_SWAP=y -CONFIG_SYSVIPC=y -CONFIG_POSIX_MQUEUE=y -CONFIG_BSD_PROCESS_ACCT=y -# CONFIG_BSD_PROCESS_ACCT_V3 is not set -CONFIG_SYSCTL=y -# CONFIG_AUDIT is not set -CONFIG_HOTPLUG=y -CONFIG_KOBJECT_UEVENT=y -CONFIG_IKCONFIG=y -CONFIG_IKCONFIG_PROC=y -# CONFIG_CPUSETS is not set -# CONFIG_EMBEDDED is not set -CONFIG_KALLSYMS=y -CONFIG_KALLSYMS_ALL=y -CONFIG_KALLSYMS_EXTRA_PASS=y -CONFIG_PRINTK=y -CONFIG_BUG=y -CONFIG_BASE_FULL=y -CONFIG_FUTEX=y -CONFIG_EPOLL=y -CONFIG_SHMEM=y -CONFIG_CC_ALIGN_FUNCTIONS=0 -CONFIG_CC_ALIGN_LABELS=0 -CONFIG_CC_ALIGN_LOOPS=0 -CONFIG_CC_ALIGN_JUMPS=0 -# CONFIG_TINY_SHMEM is not set -CONFIG_BASE_SMALL=0 - -# -# Loadable module support -# -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_MODULE_FORCE_UNLOAD is not set -CONFIG_OBSOLETE_MODPARM=y -CONFIG_MODVERSIONS=y -CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_KMOD=y -CONFIG_STOP_MACHINE=y - -# -# Processor type and features -# -CONFIG_IA64=y -CONFIG_64BIT=y -CONFIG_MMU=y -CONFIG_RWSEM_XCHGADD_ALGORITHM=y -CONFIG_GENERIC_CALIBRATE_DELAY=y -CONFIG_TIME_INTERPOLATION=y -CONFIG_EFI=y -CONFIG_GENERIC_IOMAP=y -CONFIG_XEN=y -CONFIG_ARCH_XEN=y -CONFIG_XEN_PRIVILEGED_GUEST=y -CONFIG_XEN_PHYSDEV_ACCESS=y -CONFIG_XEN_BLKDEV_GRANT=y -CONFIG_XEN_BLKDEV_FRONTEND=y -CONFIG_XEN_VT=y -CONFIG_VT=y -CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y -# CONFIG_IA64_GENERIC is not set -CONFIG_IA64_DIG=y -# CONFIG_IA64_HP_ZX1 is not set -# CONFIG_IA64_HP_ZX1_SWIOTLB is not set -# CONFIG_IA64_SGI_SN2 is not set -# CONFIG_IA64_HP_SIM is not set -# CONFIG_ITANIUM is not set -CONFIG_MCKINLEY=y -# CONFIG_IA64_PAGE_SIZE_4KB is not set -# CONFIG_IA64_PAGE_SIZE_8KB is not set -CONFIG_IA64_PAGE_SIZE_16KB=y -# CONFIG_IA64_PAGE_SIZE_64KB is not set -CONFIG_IA64_L1_CACHE_SHIFT=7 -# CONFIG_NUMA is not set -CONFIG_VIRTUAL_MEM_MAP=n -CONFIG_IA64_CYCLONE=y -CONFIG_IOSAPIC=y -CONFIG_FORCE_MAX_ZONEORDER=18 -CONFIG_SMP=y -CONFIG_NR_CPUS=4 -CONFIG_HOTPLUG_CPU=y -# CONFIG_SCHED_SMT is not set -# CONFIG_PREEMPT is not set -CONFIG_HAVE_DEC_LOCK=y -# CONFIG_IA32_SUPPORT is not set -CONFIG_IA64_MCA_RECOVERY=y -CONFIG_PERFMON=y -CONFIG_IA64_PALINFO=y -CONFIG_ACPI_DEALLOCATE_IRQ=y - -# -# Firmware Drivers -# -CONFIG_EFI_VARS=y -CONFIG_EFI_PCDP=y -CONFIG_BINFMT_ELF=y -CONFIG_BINFMT_MISC=y - -# -# Power management and ACPI -# -CONFIG_PM=y -CONFIG_ACPI=y - -# -# ACPI (Advanced Configuration and Power Interface) Support -# -CONFIG_ACPI_BOOT=y -CONFIG_ACPI_INTERPRETER=y -CONFIG_ACPI_BUTTON=y -# CONFIG_ACPI_VIDEO is not set -CONFIG_ACPI_FAN=y -CONFIG_ACPI_PROCESSOR=y -# CONFIG_ACPI_HOTPLUG_CPU is not set -CONFIG_ACPI_THERMAL=y -CONFIG_ACPI_BLACKLIST_YEAR=0 -# CONFIG_ACPI_DEBUG is not set -CONFIG_ACPI_BUS=y -CONFIG_ACPI_POWER=y -CONFIG_ACPI_PCI=y -CONFIG_ACPI_SYSTEM=y -# CONFIG_ACPI_CONTAINER is not set - -# -# Bus options (PCI, PCMCIA) -# -CONFIG_PCI=y -CONFIG_PCI_DOMAINS=y -# CONFIG_PCI_MSI is not set -CONFIG_PCI_LEGACY_PROC=y -CONFIG_PCI_NAMES=y -# CONFIG_PCI_DEBUG is not set - -# -# PCI Hotplug Support -# -CONFIG_HOTPLUG_PCI=y -# CONFIG_HOTPLUG_PCI_FAKE is not set -CONFIG_HOTPLUG_PCI_ACPI=y -# CONFIG_HOTPLUG_PCI_ACPI_IBM is not set -# CONFIG_HOTPLUG_PCI_CPCI is not set -# CONFIG_HOTPLUG_PCI_SHPC is not set - -# -# PCCARD (PCMCIA/CardBus) support -# -# CONFIG_PCCARD is not set - -# -# Device Drivers -# - -# -# Generic Driver Options -# -CONFIG_STANDALONE=y -CONFIG_PREVENT_FIRMWARE_BUILD=y -# CONFIG_FW_LOADER is not set -# CONFIG_DEBUG_DRIVER is not set - -# -# Memory Technology Devices (MTD) -# -# CONFIG_MTD is not set - -# -# Parallel port support -# -# CONFIG_PARPORT is not set - -# -# Plug and Play support -# -# CONFIG_PNP is not set - -# -# Block devices -# -# CONFIG_BLK_CPQ_DA is not set -# CONFIG_BLK_CPQ_CISS_DA is not set -# CONFIG_BLK_DEV_DAC960 is not set -# CONFIG_BLK_DEV_UMEM is not set -# CONFIG_BLK_DEV_COW_COMMON is not set -CONFIG_BLK_DEV_LOOP=y -CONFIG_BLK_DEV_CRYPTOLOOP=y -CONFIG_BLK_DEV_NBD=y -# CONFIG_BLK_DEV_SX8 is not set -# CONFIG_BLK_DEV_UB is not set -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_COUNT=16 -CONFIG_BLK_DEV_RAM_SIZE=4096 -CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="" -# CONFIG_CDROM_PKTCDVD is not set - -# -# IO Schedulers -# -CONFIG_IOSCHED_NOOP=y -CONFIG_IOSCHED_AS=y -CONFIG_IOSCHED_DEADLINE=y -CONFIG_IOSCHED_CFQ=y -# CONFIG_ATA_OVER_ETH is not set - -# -# ATA/ATAPI/MFM/RLL support -# -CONFIG_IDE=y -CONFIG_BLK_DEV_IDE=y - -# -# Please see Documentation/ide.txt for help/info on IDE drives -# -# CONFIG_BLK_DEV_IDE_SATA is not set -CONFIG_BLK_DEV_IDEDISK=y -# CONFIG_IDEDISK_MULTI_MODE is not set -CONFIG_BLK_DEV_IDECD=y -# CONFIG_BLK_DEV_IDETAPE is not set -CONFIG_BLK_DEV_IDEFLOPPY=y -CONFIG_BLK_DEV_IDESCSI=y -# CONFIG_IDE_TASK_IOCTL is not set - -# -# IDE chipset support/bugfixes -# -CONFIG_IDE_GENERIC=y -CONFIG_BLK_DEV_IDEPCI=y -# CONFIG_IDEPCI_SHARE_IRQ is not set -# CONFIG_BLK_DEV_OFFBOARD is not set -CONFIG_BLK_DEV_GENERIC=y -# CONFIG_BLK_DEV_OPTI621 is not set -CONFIG_BLK_DEV_IDEDMA_PCI=y -# CONFIG_BLK_DEV_IDEDMA_FORCED is not set -CONFIG_IDEDMA_PCI_AUTO=y -# CONFIG_IDEDMA_ONLYDISK is not set -# CONFIG_BLK_DEV_AEC62XX is not set -# CONFIG_BLK_DEV_ALI15X3 is not set -# CONFIG_BLK_DEV_AMD74XX is not set -CONFIG_BLK_DEV_CMD64X=y -# CONFIG_BLK_DEV_TRIFLEX is not set -# CONFIG_BLK_DEV_CY82C693 is not set -# CONFIG_BLK_DEV_CS5520 is not set -# CONFIG_BLK_DEV_CS5530 is not set -# CONFIG_BLK_DEV_HPT34X is not set -# CONFIG_BLK_DEV_HPT366 is not set -# CONFIG_BLK_DEV_SC1200 is not set -CONFIG_BLK_DEV_PIIX=y -# CONFIG_BLK_DEV_NS87415 is not set -# CONFIG_BLK_DEV_PDC202XX_OLD is not set -# CONFIG_BLK_DEV_PDC202XX_NEW is not set -# CONFIG_BLK_DEV_SVWKS is not set -# CONFIG_BLK_DEV_SIIMAGE is not set -# CONFIG_BLK_DEV_SLC90E66 is not set -# CONFIG_BLK_DEV_TRM290 is not set -# CONFIG_BLK_DEV_VIA82CXXX is not set -# CONFIG_IDE_ARM is not set -CONFIG_BLK_DEV_IDEDMA=y -# CONFIG_IDEDMA_IVB is not set -CONFIG_IDEDMA_AUTO=y -# CONFIG_BLK_DEV_HD is not set - -# -# SCSI device support -# -CONFIG_SCSI=y -CONFIG_SCSI_PROC_FS=y - -# -# SCSI support type (disk, tape, CD-ROM) -# -CONFIG_BLK_DEV_SD=y -CONFIG_CHR_DEV_ST=y -CONFIG_CHR_DEV_OSST=y -CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y -CONFIG_CHR_DEV_SG=y - -# -# Some SCSI devices (e.g. CD jukebox) support multiple LUNs -# -CONFIG_SCSI_MULTI_LUN=y -CONFIG_SCSI_CONSTANTS=y -CONFIG_SCSI_LOGGING=y - -# -# SCSI Transport Attributes -# -CONFIG_SCSI_SPI_ATTRS=y -CONFIG_SCSI_FC_ATTRS=y -# CONFIG_SCSI_ISCSI_ATTRS is not set - -# -# SCSI low-level drivers -# -# CONFIG_BLK_DEV_3W_XXXX_RAID is not set -# CONFIG_SCSI_3W_9XXX is not set -# CONFIG_SCSI_ACARD is not set -# CONFIG_SCSI_AACRAID is not set -# CONFIG_SCSI_AIC7XXX is not set -# CONFIG_SCSI_AIC7XXX_OLD is not set -# CONFIG_SCSI_AIC79XX is not set -# CONFIG_MEGARAID_NEWGEN is not set -# CONFIG_MEGARAID_LEGACY is not set -# CONFIG_SCSI_SATA is not set -# CONFIG_SCSI_DMX3191D is not set -# CONFIG_SCSI_FUTURE_DOMAIN is not set -# CONFIG_SCSI_IPS is not set -# CONFIG_SCSI_INITIO is not set -# CONFIG_SCSI_INIA100 is not set -CONFIG_SCSI_SYM53C8XX_2=y -CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=1 -CONFIG_SCSI_SYM53C8XX_DEFAULT_TAGS=16 -CONFIG_SCSI_SYM53C8XX_MAX_TAGS=64 -# CONFIG_SCSI_SYM53C8XX_IOMAPPED is not set -# CONFIG_SCSI_IPR is not set -CONFIG_SCSI_QLOGIC_FC=y -# CONFIG_SCSI_QLOGIC_FC_FIRMWARE is not set -CONFIG_SCSI_QLOGIC_1280=y -# CONFIG_SCSI_QLOGIC_1280_1040 is not set -CONFIG_SCSI_QLA2XXX=y -CONFIG_SCSI_QLA21XX=y -CONFIG_SCSI_QLA22XX=y -CONFIG_SCSI_QLA2300=y -CONFIG_SCSI_QLA2322=y -# CONFIG_SCSI_QLA6312 is not set -# CONFIG_SCSI_LPFC is not set -# CONFIG_SCSI_DC395x is not set -# CONFIG_SCSI_DC390T is not set -# CONFIG_SCSI_DEBUG is not set - -# -# Multi-device support (RAID and LVM) -# -CONFIG_MD=y -# CONFIG_BLK_DEV_MD is not set -# CONFIG_BLK_DEV_DM is not set - -# -# Fusion MPT device support -# -CONFIG_FUSION=y -CONFIG_FUSION_MAX_SGE=40 -# CONFIG_FUSION_CTL is not set - -# -# IEEE 1394 (FireWire) support -# -# CONFIG_IEEE1394 is not set - -# -# I2O device support -# -# CONFIG_I2O is not set - -# -# Networking support -# -CONFIG_NET=y - -# -# Networking options -# -CONFIG_PACKET=y -# CONFIG_PACKET_MMAP is not set -CONFIG_UNIX=y -# CONFIG_NET_KEY is not set -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -# CONFIG_IP_ADVANCED_ROUTER is not set -# CONFIG_IP_PNP is not set -# CONFIG_NET_IPIP is not set -# CONFIG_NET_IPGRE is not set -# CONFIG_IP_MROUTE is not set -CONFIG_ARPD=y -CONFIG_SYN_COOKIES=y -# CONFIG_INET_AH is not set -# CONFIG_INET_ESP is not set -# CONFIG_INET_IPCOMP is not set -# CONFIG_INET_TUNNEL is not set -CONFIG_IP_TCPDIAG=y -# CONFIG_IP_TCPDIAG_IPV6 is not set - -# -# IP: Virtual Server Configuration -# -# CONFIG_IP_VS is not set -# CONFIG_IPV6 is not set -CONFIG_NETFILTER=y -# CONFIG_NETFILTER_DEBUG is not set -CONFIG_BRIDGE_NETFILTER=y - -# -# IP: Netfilter Configuration -# -# CONFIG_IP_NF_CONNTRACK is not set -# CONFIG_IP_NF_CONNTRACK_MARK is not set -# CONFIG_IP_NF_QUEUE is not set -# CONFIG_IP_NF_IPTABLES is not set -CONFIG_IP_NF_ARPTABLES=y -# CONFIG_IP_NF_ARPFILTER is not set -# CONFIG_IP_NF_ARP_MANGLE is not set - -# -# Bridge: Netfilter Configuration -# -# CONFIG_BRIDGE_NF_EBTABLES is not set - -# -# SCTP Configuration (EXPERIMENTAL) -# -# CONFIG_IP_SCTP is not set -# CONFIG_ATM is not set -CONFIG_BRIDGE=y -# CONFIG_VLAN_8021Q is not set -# CONFIG_DECNET is not set -# CONFIG_LLC2 is not set -# CONFIG_IPX is not set -# CONFIG_ATALK is not set -# CONFIG_X25 is not set -# CONFIG_LAPB is not set -# CONFIG_NET_DIVERT is not set -# CONFIG_ECONET is not set -# CONFIG_WAN_ROUTER is not set - -# -# QoS and/or fair queueing -# -# CONFIG_NET_SCHED is not set -# CONFIG_NET_CLS_ROUTE is not set - -# -# Network testing -# -# CONFIG_NET_PKTGEN is not set -CONFIG_NETPOLL=y -# CONFIG_NETPOLL_RX is not set -# CONFIG_NETPOLL_TRAP is not set -CONFIG_NET_POLL_CONTROLLER=y -# CONFIG_HAMRADIO is not set -# CONFIG_IRDA is not set -# CONFIG_BT is not set -CONFIG_NETDEVICES=y -CONFIG_DUMMY=y -# CONFIG_BONDING is not set -# CONFIG_EQUALIZER is not set -CONFIG_TUN=y - -# -# ARCnet devices -# -CONFIG_ARCNET=y -# CONFIG_ARCNET_1201 is not set -# CONFIG_ARCNET_1051 is not set -# CONFIG_ARCNET_RAW is not set -# CONFIG_ARCNET_CAP is not set -# CONFIG_ARCNET_COM90xx is not set -# CONFIG_ARCNET_COM90xxIO is not set -# CONFIG_ARCNET_RIM_I is not set -# CONFIG_ARCNET_COM20020 is not set - -# -# Ethernet (10 or 100Mbit) -# -CONFIG_NET_ETHERNET=y -CONFIG_MII=y -# CONFIG_HAPPYMEAL is not set -# CONFIG_SUNGEM is not set -# CONFIG_NET_VENDOR_3COM is not set - -# -# Tulip family network device support -# -CONFIG_NET_TULIP=y -# CONFIG_DE2104X is not set -CONFIG_TULIP=y -CONFIG_TULIP_MWI=y -CONFIG_TULIP_MMIO=y -CONFIG_TULIP_NAPI=y -CONFIG_TULIP_NAPI_HW_MITIGATION=y -# CONFIG_DE4X5 is not set -# CONFIG_WINBOND_840 is not set -# CONFIG_DM9102 is not set -# CONFIG_HP100 is not set -CONFIG_NET_PCI=y -# CONFIG_PCNET32 is not set -# CONFIG_AMD8111_ETH is not set -# CONFIG_ADAPTEC_STARFIRE is not set -# CONFIG_B44 is not set -# CONFIG_FORCEDETH is not set -# CONFIG_DGRS is not set -CONFIG_EEPRO100=y -CONFIG_E100=y -# CONFIG_FEALNX is not set -# CONFIG_NATSEMI is not set -# CONFIG_NE2K_PCI is not set -# CONFIG_8139CP is not set -# CONFIG_8139TOO is not set -# CONFIG_SIS900 is not set -# CONFIG_EPIC100 is not set -# CONFIG_SUNDANCE is not set -# CONFIG_VIA_RHINE is not set - -# -# Ethernet (1000 Mbit) -# -# CONFIG_ACENIC is not set -# CONFIG_DL2K is not set -CONFIG_E1000=y -# CONFIG_E1000_NAPI is not set -# CONFIG_NS83820 is not set -# CONFIG_HAMACHI is not set -# CONFIG_YELLOWFIN is not set -# CONFIG_R8169 is not set -# CONFIG_SK98LIN is not set -# CONFIG_VIA_VELOCITY is not set -CONFIG_TIGON3=y -# CONFIG_BNX2 is not set - -# -# Ethernet (10000 Mbit) -# -# CONFIG_IXGB is not set -# CONFIG_S2IO is not set - -# -# Token Ring devices -# -# CONFIG_TR is not set - -# -# Wireless LAN (non-hamradio) -# -# CONFIG_NET_RADIO is not set - -# -# Wan interfaces -# -# CONFIG_WAN is not set -# CONFIG_FDDI is not set -# CONFIG_HIPPI is not set -# CONFIG_PPP is not set -# CONFIG_SLIP is not set -# CONFIG_NET_FC is not set -# CONFIG_SHAPER is not set -CONFIG_NETCONSOLE=y - -# -# ISDN subsystem -# -CONFIG_ISDN=m - -# -# Old ISDN4Linux -# -# CONFIG_ISDN_I4L is not set - -# -# CAPI subsystem -# -# CONFIG_ISDN_CAPI is not set - -# -# Telephony Support -# -# CONFIG_PHONE is not set - -# -# Input device support -# -CONFIG_INPUT=y - -# -# Userland interfaces -# -CONFIG_INPUT_MOUSEDEV=y -CONFIG_INPUT_MOUSEDEV_PSAUX=y -CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024 -CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 -CONFIG_INPUT_JOYDEV=y -# CONFIG_INPUT_TSDEV is not set -CONFIG_INPUT_EVDEV=y -# CONFIG_INPUT_EVBUG is not set - -# -# Input Device Drivers -# -CONFIG_INPUT_KEYBOARD=y -CONFIG_KEYBOARD_ATKBD=y -# CONFIG_KEYBOARD_SUNKBD is not set -# CONFIG_KEYBOARD_LKKBD is not set -# CONFIG_KEYBOARD_XTKBD is not set -# CONFIG_KEYBOARD_NEWTON is not set -CONFIG_INPUT_MOUSE=y -CONFIG_MOUSE_PS2=y -# CONFIG_MOUSE_SERIAL is not set -# CONFIG_MOUSE_VSXXXAA is not set -# CONFIG_INPUT_JOYSTICK is not set -# CONFIG_INPUT_TOUCHSCREEN is not set -# CONFIG_INPUT_MISC is not set - -# -# Hardware I/O ports -# -CONFIG_SERIO=y -CONFIG_SERIO_I8042=y -# CONFIG_SERIO_SERPORT is not set -# CONFIG_SERIO_PCIPS2 is not set -CONFIG_SERIO_LIBPS2=y -# CONFIG_SERIO_RAW is not set -CONFIG_GAMEPORT=y -# CONFIG_GAMEPORT_NS558 is not set -# CONFIG_GAMEPORT_L4 is not set -# CONFIG_GAMEPORT_EMU10K1 is not set -# CONFIG_GAMEPORT_VORTEX is not set -# CONFIG_GAMEPORT_FM801 is not set -# CONFIG_GAMEPORT_CS461X is not set - -# -# Character devices -# -CONFIG_VT_CONSOLE=y -CONFIG_HW_CONSOLE=y -CONFIG_SERIAL_NONSTANDARD=y -# CONFIG_ROCKETPORT is not set -# CONFIG_CYCLADES is not set -# CONFIG_MOXA_SMARTIO is not set -# CONFIG_ISI is not set -# CONFIG_SYNCLINKMP is not set -# CONFIG_N_HDLC is not set -# CONFIG_SPECIALIX is not set -# CONFIG_SX is not set -# CONFIG_STALDRV is not set - -# -# Serial drivers -# -CONFIG_SERIAL_8250=y -CONFIG_SERIAL_8250_CONSOLE=y -CONFIG_SERIAL_8250_ACPI=y -CONFIG_SERIAL_8250_NR_UARTS=6 -CONFIG_SERIAL_8250_EXTENDED=y -CONFIG_SERIAL_8250_SHARE_IRQ=y -# CONFIG_SERIAL_8250_DETECT_IRQ is not set -# CONFIG_SERIAL_8250_MULTIPORT is not set -# CONFIG_SERIAL_8250_RSA is not set - -# -# Non-8250 serial port support -# -CONFIG_SERIAL_CORE=y -CONFIG_SERIAL_CORE_CONSOLE=y -# CONFIG_SERIAL_JSM is not set -CONFIG_UNIX98_PTYS=y -CONFIG_LEGACY_PTYS=y -CONFIG_LEGACY_PTY_COUNT=256 - -# -# IPMI -# -# CONFIG_IPMI_HANDLER is not set - -# -# Watchdog Cards -# -# CONFIG_WATCHDOG is not set -# CONFIG_HW_RANDOM is not set -CONFIG_EFI_RTC=y -# CONFIG_DTLK is not set -# CONFIG_R3964 is not set -# CONFIG_APPLICOM is not set - -# -# Ftape, the floppy tape device driver -# -CONFIG_AGP=y -CONFIG_AGP_I460=y -CONFIG_DRM=y -# CONFIG_DRM_TDFX is not set -# CONFIG_DRM_R128 is not set -# CONFIG_DRM_RADEON is not set -# CONFIG_DRM_MGA is not set -# CONFIG_DRM_SIS is not set -# CONFIG_RAW_DRIVER is not set -# CONFIG_HPET is not set -# CONFIG_HANGCHECK_TIMER is not set - -# -# TPM devices -# -# CONFIG_TCG_TPM is not set - -# -# I2C support -# -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y - -# -# I2C Algorithms -# -CONFIG_I2C_ALGOBIT=y -CONFIG_I2C_ALGOPCF=y -# CONFIG_I2C_ALGOPCA is not set - -# -# I2C Hardware Bus support -# -# CONFIG_I2C_ALI1535 is not set -# CONFIG_I2C_ALI1563 is not set -# CONFIG_I2C_ALI15X3 is not set -# CONFIG_I2C_AMD756 is not set -# CONFIG_I2C_AMD8111 is not set -# CONFIG_I2C_I801 is not set -# CONFIG_I2C_I810 is not set -# CONFIG_I2C_PIIX4 is not set -# CONFIG_I2C_ISA is not set -# CONFIG_I2C_NFORCE2 is not set -# CONFIG_I2C_PARPORT_LIGHT is not set -# CONFIG_I2C_PROSAVAGE is not set -# CONFIG_I2C_SAVAGE4 is not set -# CONFIG_SCx200_ACB is not set -# CONFIG_I2C_SIS5595 is not set -# CONFIG_I2C_SIS630 is not set -# CONFIG_I2C_SIS96X is not set -# CONFIG_I2C_STUB is not set -# CONFIG_I2C_VIA is not set -# CONFIG_I2C_VIAPRO is not set -# CONFIG_I2C_VOODOO3 is not set -# CONFIG_I2C_PCA_ISA is not set - -# -# Hardware Sensors Chip support -# -# CONFIG_I2C_SENSOR is not set -# CONFIG_SENSORS_ADM1021 is not set -# CONFIG_SENSORS_ADM1025 is not set -# CONFIG_SENSORS_ADM1026 is not set -# CONFIG_SENSORS_ADM1031 is not set -# CONFIG_SENSORS_ASB100 is not set -# CONFIG_SENSORS_DS1621 is not set -# CONFIG_SENSORS_FSCHER is not set -# CONFIG_SENSORS_FSCPOS is not set -# CONFIG_SENSORS_GL518SM is not set -# CONFIG_SENSORS_GL520SM is not set -# CONFIG_SENSORS_IT87 is not set -# CONFIG_SENSORS_LM63 is not set -# CONFIG_SENSORS_LM75 is not set -# CONFIG_SENSORS_LM77 is not set -# CONFIG_SENSORS_LM78 is not set -# CONFIG_SENSORS_LM80 is not set -# CONFIG_SENSORS_LM83 is not set -# CONFIG_SENSORS_LM85 is not set -# CONFIG_SENSORS_LM87 is not set -# CONFIG_SENSORS_LM90 is not set -# CONFIG_SENSORS_LM92 is not set -# CONFIG_SENSORS_MAX1619 is not set -# CONFIG_SENSORS_PC87360 is not set -# CONFIG_SENSORS_SMSC47B397 is not set -# CONFIG_SENSORS_SIS5595 is not set -# CONFIG_SENSORS_SMSC47M1 is not set -# CONFIG_SENSORS_VIA686A is not set -# CONFIG_SENSORS_W83781D is not set -# CONFIG_SENSORS_W83L785TS is not set -# CONFIG_SENSORS_W83627HF is not set - -# -# Other I2C Chip support -# -# CONFIG_SENSORS_DS1337 is not set -# CONFIG_SENSORS_EEPROM is not set -# CONFIG_SENSORS_PCF8574 is not set -# CONFIG_SENSORS_PCF8591 is not set -# CONFIG_SENSORS_RTC8564 is not set -# CONFIG_I2C_DEBUG_CORE is not set -# CONFIG_I2C_DEBUG_ALGO is not set -# CONFIG_I2C_DEBUG_BUS is not set -# CONFIG_I2C_DEBUG_CHIP is not set - -# -# Dallas's 1-wire bus -# -# CONFIG_W1 is not set - -# -# Misc devices -# - -# -# Multimedia devices -# -CONFIG_VIDEO_DEV=y - -# -# Video For Linux -# - -# -# Video Adapters -# -# CONFIG_VIDEO_BT848 is not set -# CONFIG_VIDEO_CPIA is not set -# CONFIG_VIDEO_SAA5246A is not set -# CONFIG_VIDEO_SAA5249 is not set -# CONFIG_TUNER_3036 is not set -# CONFIG_VIDEO_STRADIS is not set -# CONFIG_VIDEO_ZORAN is not set -# CONFIG_VIDEO_SAA7134 is not set -# CONFIG_VIDEO_MXB is not set -# CONFIG_VIDEO_DPC is not set -# CONFIG_VIDEO_HEXIUM_ORION is not set -# CONFIG_VIDEO_HEXIUM_GEMINI is not set -# CONFIG_VIDEO_CX88 is not set -# CONFIG_VIDEO_OVCAMCHIP is not set - -# -# Radio Adapters -# -# CONFIG_RADIO_GEMTEK_PCI is not set -# CONFIG_RADIO_MAXIRADIO is not set -# CONFIG_RADIO_MAESTRO is not set - -# -# Digital Video Broadcasting Devices -# -# CONFIG_DVB is not set - -# -# Graphics support -# -CONFIG_FB=y -CONFIG_FB_CFB_FILLRECT=y -CONFIG_FB_CFB_COPYAREA=y -CONFIG_FB_CFB_IMAGEBLIT=y -CONFIG_FB_SOFT_CURSOR=y -# CONFIG_FB_MACMODES is not set -CONFIG_FB_MODE_HELPERS=y -# CONFIG_FB_TILEBLITTING is not set -# CONFIG_FB_CIRRUS is not set -# CONFIG_FB_PM2 is not set -# CONFIG_FB_CYBER2000 is not set -# CONFIG_FB_ASILIANT is not set -# CONFIG_FB_IMSTT is not set -# CONFIG_FB_NVIDIA is not set -# CONFIG_FB_RIVA is not set -# CONFIG_FB_MATROX is not set -# CONFIG_FB_RADEON_OLD is not set -CONFIG_FB_RADEON=y -CONFIG_FB_RADEON_I2C=y -CONFIG_FB_RADEON_DEBUG=y -# CONFIG_FB_ATY128 is not set -# CONFIG_FB_ATY is not set -# CONFIG_FB_SAVAGE is not set -# CONFIG_FB_SIS is not set -# CONFIG_FB_NEOMAGIC is not set -# CONFIG_FB_KYRO is not set -# CONFIG_FB_3DFX is not set -# CONFIG_FB_VOODOO1 is not set -# CONFIG_FB_TRIDENT is not set -# CONFIG_FB_S1D13XXX is not set -# CONFIG_FB_VIRTUAL is not set - -# -# Console display driver support -# -CONFIG_VGA_CONSOLE=y -CONFIG_DUMMY_CONSOLE=y -# CONFIG_FRAMEBUFFER_CONSOLE is not set - -# -# Logo configuration -# -CONFIG_LOGO=y -# CONFIG_LOGO_LINUX_MONO is not set -# CONFIG_LOGO_LINUX_VGA16 is not set -CONFIG_LOGO_LINUX_CLUT224=y -# CONFIG_BACKLIGHT_LCD_SUPPORT is not set - -# -# Sound -# -CONFIG_SOUND=y - -# -# Advanced Linux Sound Architecture -# -CONFIG_SND=y -CONFIG_SND_TIMER=y -CONFIG_SND_PCM=y -CONFIG_SND_HWDEP=y -CONFIG_SND_RAWMIDI=y -CONFIG_SND_SEQUENCER=y -CONFIG_SND_SEQ_DUMMY=y -CONFIG_SND_OSSEMUL=y -CONFIG_SND_MIXER_OSS=y -CONFIG_SND_PCM_OSS=y -CONFIG_SND_SEQUENCER_OSS=y -# CONFIG_SND_VERBOSE_PRINTK is not set -# CONFIG_SND_DEBUG is not set - -# -# Generic devices -# -CONFIG_SND_MPU401_UART=y -CONFIG_SND_OPL3_LIB=y -CONFIG_SND_DUMMY=y -CONFIG_SND_VIRMIDI=y -CONFIG_SND_MTPAV=y -CONFIG_SND_SERIAL_U16550=y -CONFIG_SND_MPU401=y - -# -# PCI devices -# -CONFIG_SND_AC97_CODEC=y -# CONFIG_SND_ALI5451 is not set -CONFIG_SND_ATIIXP=y -# CONFIG_SND_ATIIXP_MODEM is not set -# CONFIG_SND_AU8810 is not set -# CONFIG_SND_AU8820 is not set -# CONFIG_SND_AU8830 is not set -# CONFIG_SND_AZT3328 is not set -# CONFIG_SND_BT87X is not set -# CONFIG_SND_CS46XX is not set -# CONFIG_SND_CS4281 is not set -# CONFIG_SND_EMU10K1 is not set -# CONFIG_SND_EMU10K1X is not set -# CONFIG_SND_CA0106 is not set -# CONFIG_SND_KORG1212 is not set -# CONFIG_SND_MIXART is not set -# CONFIG_SND_NM256 is not set -# CONFIG_SND_RME32 is not set -# CONFIG_SND_RME96 is not set -# CONFIG_SND_RME9652 is not set -# CONFIG_SND_HDSP is not set -# CONFIG_SND_TRIDENT is not set -# CONFIG_SND_YMFPCI is not set -# CONFIG_SND_ALS4000 is not set -# CONFIG_SND_CMIPCI is not set -# CONFIG_SND_ENS1370 is not set -# CONFIG_SND_ENS1371 is not set -# CONFIG_SND_ES1938 is not set -# CONFIG_SND_ES1968 is not set -# CONFIG_SND_MAESTRO3 is not set -CONFIG_SND_FM801=y -CONFIG_SND_FM801_TEA575X=y -# CONFIG_SND_ICE1712 is not set -# CONFIG_SND_ICE1724 is not set -# CONFIG_SND_INTEL8X0 is not set -# CONFIG_SND_INTEL8X0M is not set -# CONFIG_SND_SONICVIBES is not set -# CONFIG_SND_VIA82XX is not set -# CONFIG_SND_VIA82XX_MODEM is not set -# CONFIG_SND_VX222 is not set -# CONFIG_SND_HDA_INTEL is not set - -# -# USB devices -# -# CONFIG_SND_USB_AUDIO is not set - -# -# Open Sound System -# -CONFIG_SOUND_PRIME=y -# CONFIG_SOUND_BT878 is not set -# CONFIG_SOUND_CMPCI is not set -# CONFIG_SOUND_EMU10K1 is not set -# CONFIG_SOUND_FUSION is not set -# CONFIG_SOUND_CS4281 is not set -# CONFIG_SOUND_ES1370 is not set -# CONFIG_SOUND_ES1371 is not set -# CONFIG_SOUND_ESSSOLO1 is not set -# CONFIG_SOUND_MAESTRO is not set -# CONFIG_SOUND_MAESTRO3 is not set -# CONFIG_SOUND_ICH is not set -# CONFIG_SOUND_SONICVIBES is not set -# CONFIG_SOUND_TRIDENT is not set -# CONFIG_SOUND_MSNDCLAS is not set -# CONFIG_SOUND_MSNDPIN is not set -# CONFIG_SOUND_VIA82CXXX is not set -# CONFIG_SOUND_OSS is not set -# CONFIG_SOUND_TVMIXER is not set -# CONFIG_SOUND_ALI5455 is not set -# CONFIG_SOUND_FORTE is not set -# CONFIG_SOUND_RME96XX is not set -# CONFIG_SOUND_AD1980 is not set - -# -# USB support -# -CONFIG_USB_ARCH_HAS_HCD=y -CONFIG_USB_ARCH_HAS_OHCI=y -CONFIG_USB=y -# CONFIG_USB_DEBUG is not set - -# -# Miscellaneous USB options -# -CONFIG_USB_DEVICEFS=y -CONFIG_USB_BANDWIDTH=y -# CONFIG_USB_DYNAMIC_MINORS is not set -# CONFIG_USB_SUSPEND is not set -# CONFIG_USB_OTG is not set - -# -# USB Host Controller Drivers -# -CONFIG_USB_EHCI_HCD=y -# CONFIG_USB_EHCI_SPLIT_ISO is not set -# CONFIG_USB_EHCI_ROOT_HUB_TT is not set -CONFIG_USB_OHCI_HCD=y -# CONFIG_USB_OHCI_BIG_ENDIAN is not set -CONFIG_USB_OHCI_LITTLE_ENDIAN=y -CONFIG_USB_UHCI_HCD=y -# CONFIG_USB_SL811_HCD is not set - -# -# USB Device Class drivers -# -CONFIG_USB_AUDIO=y -# CONFIG_USB_BLUETOOTH_TTY is not set -# CONFIG_USB_MIDI is not set -# CONFIG_USB_ACM is not set -# CONFIG_USB_PRINTER is not set - -# -# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed; see USB_STORAGE Help for more information -# -CONFIG_USB_STORAGE=y -# CONFIG_USB_STORAGE_DEBUG is not set -# CONFIG_USB_STORAGE_DATAFAB is not set -# CONFIG_USB_STORAGE_FREECOM is not set -# CONFIG_USB_STORAGE_ISD200 is not set -# CONFIG_USB_STORAGE_DPCM is not set -# CONFIG_USB_STORAGE_USBAT is not set -# CONFIG_USB_STORAGE_SDDR09 is not set -# CONFIG_USB_STORAGE_SDDR55 is not set -# CONFIG_USB_STORAGE_JUMPSHOT is not set - -# -# USB Input Devices -# -CONFIG_USB_HID=y -CONFIG_USB_HIDINPUT=y -# CONFIG_HID_FF is not set -CONFIG_USB_HIDDEV=y -# CONFIG_USB_AIPTEK is not set -# CONFIG_USB_WACOM is not set -# CONFIG_USB_KBTAB is not set -# CONFIG_USB_POWERMATE is not set -# CONFIG_USB_MTOUCH is not set -# CONFIG_USB_EGALAX is not set -# CONFIG_USB_XPAD is not set -# CONFIG_USB_ATI_REMOTE is not set - -# -# USB Imaging devices -# -# CONFIG_USB_MDC800 is not set -# CONFIG_USB_MICROTEK is not set - -# -# USB Multimedia devices -# -# CONFIG_USB_DABUSB is not set -# CONFIG_USB_VICAM is not set -# CONFIG_USB_DSBR is not set -# CONFIG_USB_IBMCAM is not set -# CONFIG_USB_KONICAWC is not set -# CONFIG_USB_OV511 is not set -# CONFIG_USB_SE401 is not set -# CONFIG_USB_SN9C102 is not set -# CONFIG_USB_STV680 is not set -# CONFIG_USB_PWC is not set - -# -# USB Network Adapters -# -# CONFIG_USB_CATC is not set -# CONFIG_USB_KAWETH is not set -# CONFIG_USB_PEGASUS is not set -# CONFIG_USB_RTL8150 is not set -# CONFIG_USB_USBNET is not set -CONFIG_USB_MON=y - -# -# USB port drivers -# - -# -# USB Serial Converter support -# -# CONFIG_USB_SERIAL is not set - -# -# USB Miscellaneous drivers -# -# CONFIG_USB_EMI62 is not set -# CONFIG_USB_EMI26 is not set -# CONFIG_USB_AUERSWALD is not set -# CONFIG_USB_RIO500 is not set -# CONFIG_USB_LEGOTOWER is not set -# CONFIG_USB_LCD is not set -# CONFIG_USB_LED is not set -# CONFIG_USB_CYTHERM is not set -# CONFIG_USB_PHIDGETKIT is not set -# CONFIG_USB_PHIDGETSERVO is not set -# CONFIG_USB_IDMOUSE is not set -# CONFIG_USB_SISUSBVGA is not set -# CONFIG_USB_TEST is not set - -# -# USB ATM/DSL drivers -# - -# -# USB Gadget Support -# -# CONFIG_USB_GADGET is not set - -# -# MMC/SD Card support -# -# CONFIG_MMC is not set - -# -# InfiniBand support -# -# CONFIG_INFINIBAND is not set - -# -# File systems -# -CONFIG_EXT2_FS=y -CONFIG_EXT2_FS_XATTR=y -CONFIG_EXT2_FS_POSIX_ACL=y -CONFIG_EXT2_FS_SECURITY=y -CONFIG_EXT3_FS=y -CONFIG_EXT3_FS_XATTR=y -CONFIG_EXT3_FS_POSIX_ACL=y -CONFIG_EXT3_FS_SECURITY=y -CONFIG_JBD=y -# CONFIG_JBD_DEBUG is not set -CONFIG_FS_MBCACHE=y -CONFIG_REISERFS_FS=y -# CONFIG_REISERFS_CHECK is not set -# CONFIG_REISERFS_PROC_INFO is not set -CONFIG_REISERFS_FS_XATTR=y -CONFIG_REISERFS_FS_POSIX_ACL=y -CONFIG_REISERFS_FS_SECURITY=y -# CONFIG_JFS_FS is not set -CONFIG_FS_POSIX_ACL=y - -# -# XFS support -# -CONFIG_XFS_FS=y -CONFIG_XFS_EXPORT=y -# CONFIG_XFS_RT is not set -# CONFIG_XFS_QUOTA is not set -# CONFIG_XFS_SECURITY is not set -# CONFIG_XFS_POSIX_ACL is not set -# CONFIG_MINIX_FS is not set -# CONFIG_ROMFS_FS is not set -# CONFIG_QUOTA is not set -CONFIG_DNOTIFY=y -CONFIG_AUTOFS_FS=y -CONFIG_AUTOFS4_FS=y - -# -# CD-ROM/DVD Filesystems -# -CONFIG_ISO9660_FS=y -CONFIG_JOLIET=y -# CONFIG_ZISOFS is not set -CONFIG_UDF_FS=y -CONFIG_UDF_NLS=y - -# -# DOS/FAT/NT Filesystems -# -CONFIG_FAT_FS=y -CONFIG_MSDOS_FS=y -CONFIG_VFAT_FS=y -CONFIG_FAT_DEFAULT_CODEPAGE=437 -CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" -# CONFIG_NTFS_FS is not set - -# -# Pseudo filesystems -# -CONFIG_PROC_FS=y -CONFIG_PROC_KCORE=y -CONFIG_SYSFS=y -# CONFIG_DEVFS_FS is not set -# CONFIG_DEVPTS_FS_XATTR is not set -CONFIG_TMPFS=y -CONFIG_TMPFS_XATTR=y -CONFIG_TMPFS_SECURITY=y -CONFIG_HUGETLBFS=y -CONFIG_HUGETLB_PAGE=y -CONFIG_RAMFS=y - -# -# Miscellaneous filesystems -# -# CONFIG_ADFS_FS is not set -# CONFIG_AFFS_FS is not set -# CONFIG_HFS_FS is not set -# CONFIG_HFSPLUS_FS is not set -# CONFIG_BEFS_FS is not set -# CONFIG_BFS_FS is not set -# CONFIG_EFS_FS is not set -# CONFIG_CRAMFS is not set -# CONFIG_VXFS_FS is not set -# CONFIG_HPFS_FS is not set -# CONFIG_QNX4FS_FS is not set -# CONFIG_SYSV_FS is not set -# CONFIG_UFS_FS is not set - -# -# Network File Systems -# -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -CONFIG_NFS_V4=y -CONFIG_NFS_DIRECTIO=y -CONFIG_NFSD=y -CONFIG_NFSD_V3=y -CONFIG_NFSD_V4=y -CONFIG_NFSD_TCP=y -CONFIG_LOCKD=y -CONFIG_LOCKD_V4=y -CONFIG_EXPORTFS=y -CONFIG_SUNRPC=y -CONFIG_SUNRPC_GSS=y -CONFIG_RPCSEC_GSS_KRB5=y -# CONFIG_RPCSEC_GSS_SPKM3 is not set -CONFIG_SMB_FS=y -CONFIG_SMB_NLS_DEFAULT=y -CONFIG_SMB_NLS_REMOTE="cp437" -CONFIG_CIFS=y -# CONFIG_CIFS_STATS is not set -# CONFIG_CIFS_XATTR is not set -# CONFIG_CIFS_EXPERIMENTAL is not set -# CONFIG_NCP_FS is not set -# CONFIG_CODA_FS is not set -# CONFIG_AFS_FS is not set - -# -# Partition Types -# -CONFIG_PARTITION_ADVANCED=y -# CONFIG_ACORN_PARTITION is not set -# CONFIG_OSF_PARTITION is not set -# CONFIG_AMIGA_PARTITION is not set -# CONFIG_ATARI_PARTITION is not set -# CONFIG_MAC_PARTITION is not set -CONFIG_MSDOS_PARTITION=y -# CONFIG_BSD_DISKLABEL is not set -# CONFIG_MINIX_SUBPARTITION is not set -# CONFIG_SOLARIS_X86_PARTITION is not set -# CONFIG_UNIXWARE_DISKLABEL is not set -# CONFIG_LDM_PARTITION is not set -CONFIG_SGI_PARTITION=y -# CONFIG_ULTRIX_PARTITION is not set -# CONFIG_SUN_PARTITION is not set -CONFIG_EFI_PARTITION=y - -# -# Native Language Support -# -CONFIG_NLS=y -CONFIG_NLS_DEFAULT="iso8859-1" -CONFIG_NLS_CODEPAGE_437=y -CONFIG_NLS_CODEPAGE_737=y -CONFIG_NLS_CODEPAGE_775=y -CONFIG_NLS_CODEPAGE_850=y -CONFIG_NLS_CODEPAGE_852=y -CONFIG_NLS_CODEPAGE_855=y -CONFIG_NLS_CODEPAGE_857=y -CONFIG_NLS_CODEPAGE_860=y -CONFIG_NLS_CODEPAGE_861=y -CONFIG_NLS_CODEPAGE_862=y -CONFIG_NLS_CODEPAGE_863=y -CONFIG_NLS_CODEPAGE_864=y -CONFIG_NLS_CODEPAGE_865=y -CONFIG_NLS_CODEPAGE_866=y -CONFIG_NLS_CODEPAGE_869=y -CONFIG_NLS_CODEPAGE_936=y -CONFIG_NLS_CODEPAGE_950=y -CONFIG_NLS_CODEPAGE_932=y -CONFIG_NLS_CODEPAGE_949=y -CONFIG_NLS_CODEPAGE_874=y -CONFIG_NLS_ISO8859_8=y -# CONFIG_NLS_CODEPAGE_1250 is not set -CONFIG_NLS_CODEPAGE_1251=y -# CONFIG_NLS_ASCII is not set -CONFIG_NLS_ISO8859_1=y -CONFIG_NLS_ISO8859_2=y -CONFIG_NLS_ISO8859_3=y -CONFIG_NLS_ISO8859_4=y -CONFIG_NLS_ISO8859_5=y -CONFIG_NLS_ISO8859_6=y -CONFIG_NLS_ISO8859_7=y -CONFIG_NLS_ISO8859_9=y -CONFIG_NLS_ISO8859_13=y -CONFIG_NLS_ISO8859_14=y -CONFIG_NLS_ISO8859_15=y -CONFIG_NLS_KOI8_R=y -CONFIG_NLS_KOI8_U=y -CONFIG_NLS_UTF8=y - -# -# Library routines -# -# CONFIG_CRC_CCITT is not set -CONFIG_CRC32=y -# CONFIG_LIBCRC32C is not set -CONFIG_GENERIC_HARDIRQS=y -CONFIG_GENERIC_IRQ_PROBE=y - -# -# Profiling support -# -# CONFIG_PROFILING is not set - -# -# Kernel hacking -# -# CONFIG_PRINTK_TIME is not set -CONFIG_DEBUG_KERNEL=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_LOG_BUF_SHIFT=20 -# CONFIG_SCHEDSTATS is not set -# CONFIG_DEBUG_SLAB is not set -# CONFIG_DEBUG_SPINLOCK is not set -# CONFIG_DEBUG_SPINLOCK_SLEEP is not set -# CONFIG_DEBUG_KOBJECT is not set -# CONFIG_DEBUG_INFO is not set -# CONFIG_DEBUG_FS is not set -CONFIG_IA64_GRANULE_16MB=y -# CONFIG_IA64_GRANULE_64MB is not set -CONFIG_IA64_PRINT_HAZARDS=y -# CONFIG_DISABLE_VHPT is not set -# CONFIG_IA64_DEBUG_CMPXCHG is not set -# CONFIG_IA64_DEBUG_IRQ is not set - -# -# Security options -# -# CONFIG_KEYS is not set -# CONFIG_SECURITY is not set - -# -# Cryptographic options -# -CONFIG_CRYPTO=y -# CONFIG_CRYPTO_HMAC is not set -# CONFIG_CRYPTO_NULL is not set -# CONFIG_CRYPTO_MD4 is not set -CONFIG_CRYPTO_MD5=y -# CONFIG_CRYPTO_SHA1 is not set -# CONFIG_CRYPTO_SHA256 is not set -# CONFIG_CRYPTO_SHA512 is not set -# CONFIG_CRYPTO_WP512 is not set -# CONFIG_CRYPTO_TGR192 is not set -CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_BLOWFISH is not set -# CONFIG_CRYPTO_TWOFISH is not set -# CONFIG_CRYPTO_SERPENT is not set -# CONFIG_CRYPTO_AES is not set -# CONFIG_CRYPTO_CAST5 is not set -# CONFIG_CRYPTO_CAST6 is not set -# CONFIG_CRYPTO_TEA is not set -# CONFIG_CRYPTO_ARC4 is not set -# CONFIG_CRYPTO_KHAZAD is not set -# CONFIG_CRYPTO_ANUBIS is not set -# CONFIG_CRYPTO_DEFLATE is not set -# CONFIG_CRYPTO_MICHAEL_MIC is not set -# CONFIG_CRYPTO_CRC32C is not set -# CONFIG_CRYPTO_TEST is not set - -# -# Hardware crypto devices -# diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/configs/xen0_defconfig_x86_32 --- a/linux-2.6-xen-sparse/arch/xen/configs/xen0_defconfig_x86_32 Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,1272 +0,0 @@ -# -# Automatically generated make config: don't edit -# Linux kernel version: 2.6.12.6-xen0 -# Mon Nov 7 17:22:05 2005 -# -CONFIG_XEN=y -CONFIG_ARCH_XEN=y -CONFIG_NO_IDLE_HZ=y - -# -# XEN -# -CONFIG_XEN_PRIVILEGED_GUEST=y -CONFIG_XEN_PHYSDEV_ACCESS=y -CONFIG_XEN_BLKDEV_BACKEND=y -# CONFIG_XEN_BLKDEV_TAP_BE is not set -CONFIG_XEN_NETDEV_BACKEND=y -# CONFIG_XEN_NETDEV_PIPELINED_TRANSMITTER is not set -# CONFIG_XEN_TPMDEV_FRONTEND is not set -# CONFIG_XEN_TPMDEV_BACKEND is not set -CONFIG_XEN_BLKDEV_FRONTEND=y -CONFIG_XEN_NETDEV_FRONTEND=y -# CONFIG_XEN_BLKDEV_TAP is not set -# CONFIG_XEN_SHADOW_MODE is not set -CONFIG_XEN_SCRUB_PAGES=y -CONFIG_XEN_X86=y -# CONFIG_XEN_X86_64 is not set -CONFIG_HAVE_ARCH_ALLOC_SKB=y -CONFIG_HAVE_ARCH_DEV_ALLOC_SKB=y - -# -# Code maturity level options -# -CONFIG_EXPERIMENTAL=y -# CONFIG_CLEAN_COMPILE is not set -CONFIG_BROKEN=y -CONFIG_BROKEN_ON_SMP=y -CONFIG_INIT_ENV_ARG_LIMIT=32 - -# -# General setup -# -CONFIG_LOCALVERSION="" -CONFIG_SWAP=y -CONFIG_SYSVIPC=y -# CONFIG_POSIX_MQUEUE is not set -# CONFIG_BSD_PROCESS_ACCT is not set -CONFIG_SYSCTL=y -# CONFIG_AUDIT is not set -CONFIG_HOTPLUG=y -CONFIG_KOBJECT_UEVENT=y -# CONFIG_IKCONFIG is not set -# CONFIG_EMBEDDED is not set -CONFIG_KALLSYMS=y -# CONFIG_KALLSYMS_ALL is not set -# CONFIG_KALLSYMS_EXTRA_PASS is not set -CONFIG_PRINTK=y -CONFIG_BUG=y -CONFIG_BASE_FULL=y -CONFIG_FUTEX=y -CONFIG_EPOLL=y -CONFIG_SHMEM=y -CONFIG_CC_ALIGN_FUNCTIONS=0 -CONFIG_CC_ALIGN_LABELS=0 -CONFIG_CC_ALIGN_LOOPS=0 -CONFIG_CC_ALIGN_JUMPS=0 -# CONFIG_TINY_SHMEM is not set -CONFIG_BASE_SMALL=0 - -# -# Loadable module support -# -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_MODULE_FORCE_UNLOAD is not set -CONFIG_OBSOLETE_MODPARM=y -# CONFIG_MODVERSIONS is not set -# CONFIG_MODULE_SRCVERSION_ALL is not set -CONFIG_KMOD=y - -# -# X86 Processor Configuration -# -CONFIG_XENARCH="i386" -CONFIG_X86=y -CONFIG_MMU=y -CONFIG_UID16=y -CONFIG_GENERIC_ISA_DMA=y -CONFIG_GENERIC_IOMAP=y -# CONFIG_M386 is not set -# CONFIG_M486 is not set -# CONFIG_M586 is not set -# CONFIG_M586TSC is not set -# CONFIG_M586MMX is not set -CONFIG_M686=y -# CONFIG_MPENTIUMII is not set -# CONFIG_MPENTIUMIII is not set -# CONFIG_MPENTIUMM is not set -# CONFIG_MPENTIUM4 is not set -# CONFIG_MK6 is not set -# CONFIG_MK7 is not set -# CONFIG_MK8 is not set -# CONFIG_MCRUSOE is not set -# CONFIG_MEFFICEON is not set -# CONFIG_MWINCHIPC6 is not set -# CONFIG_MWINCHIP2 is not set -# CONFIG_MWINCHIP3D is not set -# CONFIG_MGEODEGX1 is not set -# CONFIG_MCYRIXIII is not set -# CONFIG_MVIAC3_2 is not set -# CONFIG_X86_GENERIC is not set -CONFIG_X86_CMPXCHG=y -CONFIG_X86_XADD=y -CONFIG_X86_L1_CACHE_SHIFT=5 -CONFIG_RWSEM_XCHGADD_ALGORITHM=y -CONFIG_GENERIC_CALIBRATE_DELAY=y -CONFIG_X86_PPRO_FENCE=y -CONFIG_X86_WP_WORKS_OK=y -CONFIG_X86_INVLPG=y -CONFIG_X86_BSWAP=y -CONFIG_X86_POPAD_OK=y -CONFIG_X86_GOOD_APIC=y -CONFIG_X86_USE_PPRO_CHECKSUM=y -# CONFIG_HPET_TIMER is not set -# CONFIG_HPET_EMULATE_RTC is not set -# CONFIG_SMP is not set -# CONFIG_X86_REBOOTFIXUPS is not set -CONFIG_MICROCODE=y -CONFIG_X86_CPUID=y -CONFIG_SWIOTLB=y - -# -# Firmware Drivers -# -# CONFIG_EDD is not set -# CONFIG_NOHIGHMEM is not set -CONFIG_HIGHMEM4G=y -# CONFIG_HIGHMEM64G is not set -CONFIG_HIGHMEM=y -CONFIG_MTRR=y -# CONFIG_REGPARM is not set -CONFIG_X86_LOCAL_APIC=y -CONFIG_X86_IO_APIC=y - -# -# Bus options (PCI, PCMCIA, EISA, MCA, ISA) -# -CONFIG_X86_UP_APIC=y -CONFIG_X86_UP_IOAPIC=y -CONFIG_PCI=y -# CONFIG_PCI_GOMMCONFIG is not set -# CONFIG_PCI_GODIRECT is not set -CONFIG_PCI_GOANY=y -CONFIG_PCI_DIRECT=y -CONFIG_PCI_MMCONFIG=y -# CONFIG_PCIEPORTBUS is not set -# CONFIG_PCI_MSI is not set -CONFIG_PCI_LEGACY_PROC=y -# CONFIG_PCI_NAMES is not set -# CONFIG_PCI_DEBUG is not set -CONFIG_ISA_DMA_API=y -CONFIG_ISA=y -# CONFIG_EISA is not set -# CONFIG_MCA is not set -# CONFIG_SCx200 is not set - -# -# PCCARD (PCMCIA/CardBus) support -# -# CONFIG_PCCARD is not set - -# -# PCI Hotplug Support -# -# CONFIG_HOTPLUG_PCI is not set -CONFIG_GENERIC_HARDIRQS=y -CONFIG_GENERIC_IRQ_PROBE=y -CONFIG_X86_BIOS_REBOOT=y -CONFIG_PC=y -CONFIG_SECCOMP=y -CONFIG_EARLY_PRINTK=y - -# -# Executable file formats -# -CONFIG_BINFMT_ELF=y -# CONFIG_BINFMT_AOUT is not set -# CONFIG_BINFMT_MISC is not set - -# -# Device Drivers -# - -# -# Generic Driver Options -# -# CONFIG_STANDALONE is not set -CONFIG_PREVENT_FIRMWARE_BUILD=y -# CONFIG_FW_LOADER is not set -# CONFIG_DEBUG_DRIVER is not set - -# -# Memory Technology Devices (MTD) -# -# CONFIG_MTD is not set - -# -# Parallel port support -# -# CONFIG_PARPORT is not set - -# -# Plug and Play support -# -# CONFIG_PNP is not set - -# -# Block devices -# -CONFIG_BLK_DEV_FD=y -# CONFIG_BLK_DEV_XD is not set -# CONFIG_BLK_CPQ_DA is not set -CONFIG_BLK_CPQ_CISS_DA=y -# CONFIG_CISS_SCSI_TAPE is not set -# CONFIG_BLK_DEV_DAC960 is not set -# CONFIG_BLK_DEV_UMEM is not set -# CONFIG_BLK_DEV_COW_COMMON is not set -CONFIG_BLK_DEV_LOOP=y -# CONFIG_BLK_DEV_CRYPTOLOOP is not set -# CONFIG_BLK_DEV_NBD is not set -# CONFIG_BLK_DEV_SX8 is not set -# CONFIG_BLK_DEV_UB is not set -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_COUNT=16 -CONFIG_BLK_DEV_RAM_SIZE=4096 -CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="" -# CONFIG_LBD is not set -# CONFIG_CDROM_PKTCDVD is not set - -# -# IO Schedulers -# -CONFIG_IOSCHED_NOOP=y -CONFIG_IOSCHED_AS=y -CONFIG_IOSCHED_DEADLINE=y -CONFIG_IOSCHED_CFQ=y -# CONFIG_ATA_OVER_ETH is not set - -# -# ATA/ATAPI/MFM/RLL support -# -CONFIG_IDE=y -CONFIG_BLK_DEV_IDE=y - -# -# Please see Documentation/ide.txt for help/info on IDE drives -# -# CONFIG_BLK_DEV_IDE_SATA is not set -# CONFIG_BLK_DEV_HD_IDE is not set -CONFIG_BLK_DEV_IDEDISK=y -# CONFIG_IDEDISK_MULTI_MODE is not set -CONFIG_BLK_DEV_IDECD=y -# CONFIG_BLK_DEV_IDETAPE is not set -# CONFIG_BLK_DEV_IDEFLOPPY is not set -# CONFIG_BLK_DEV_IDESCSI is not set -# CONFIG_IDE_TASK_IOCTL is not set - -# -# IDE chipset support/bugfixes -# -CONFIG_IDE_GENERIC=y -# CONFIG_BLK_DEV_CMD640 is not set -CONFIG_BLK_DEV_IDEPCI=y -# CONFIG_IDEPCI_SHARE_IRQ is not set -# CONFIG_BLK_DEV_OFFBOARD is not set -CONFIG_BLK_DEV_GENERIC=y -# CONFIG_BLK_DEV_OPTI621 is not set -# CONFIG_BLK_DEV_RZ1000 is not set -CONFIG_BLK_DEV_IDEDMA_PCI=y -# CONFIG_BLK_DEV_IDEDMA_FORCED is not set -CONFIG_IDEDMA_PCI_AUTO=y -# CONFIG_IDEDMA_ONLYDISK is not set -# CONFIG_BLK_DEV_AEC62XX is not set -# CONFIG_BLK_DEV_ALI15X3 is not set -# CONFIG_BLK_DEV_AMD74XX is not set -# CONFIG_BLK_DEV_ATIIXP is not set -# CONFIG_BLK_DEV_CMD64X is not set -# CONFIG_BLK_DEV_TRIFLEX is not set -# CONFIG_BLK_DEV_CY82C693 is not set -# CONFIG_BLK_DEV_CS5520 is not set -# CONFIG_BLK_DEV_CS5530 is not set -# CONFIG_BLK_DEV_HPT34X is not set -# CONFIG_BLK_DEV_HPT366 is not set -# CONFIG_BLK_DEV_SC1200 is not set -CONFIG_BLK_DEV_PIIX=y -# CONFIG_BLK_DEV_NS87415 is not set -# CONFIG_BLK_DEV_PDC202XX_OLD is not set -# CONFIG_BLK_DEV_PDC202XX_NEW is not set -CONFIG_BLK_DEV_SVWKS=y -# CONFIG_BLK_DEV_SIIMAGE is not set -# CONFIG_BLK_DEV_SIS5513 is not set -# CONFIG_BLK_DEV_SLC90E66 is not set -# CONFIG_BLK_DEV_TRM290 is not set -# CONFIG_BLK_DEV_VIA82CXXX is not set -# CONFIG_IDE_ARM is not set -# CONFIG_IDE_CHIPSETS is not set -CONFIG_BLK_DEV_IDEDMA=y -# CONFIG_IDEDMA_IVB is not set -CONFIG_IDEDMA_AUTO=y -# CONFIG_BLK_DEV_HD is not set - -# -# SCSI device support -# -CONFIG_SCSI=y -CONFIG_SCSI_PROC_FS=y - -# -# SCSI support type (disk, tape, CD-ROM) -# -CONFIG_BLK_DEV_SD=y -# CONFIG_CHR_DEV_ST is not set -# CONFIG_CHR_DEV_OSST is not set -# CONFIG_BLK_DEV_SR is not set -# CONFIG_CHR_DEV_SG is not set - -# -# Some SCSI devices (e.g. CD jukebox) support multiple LUNs -# -# CONFIG_SCSI_MULTI_LUN is not set -# CONFIG_SCSI_CONSTANTS is not set -# CONFIG_SCSI_LOGGING is not set - -# -# SCSI Transport Attributes -# -CONFIG_SCSI_SPI_ATTRS=y -# CONFIG_SCSI_FC_ATTRS is not set -# CONFIG_SCSI_ISCSI_ATTRS is not set - -# -# SCSI low-level drivers -# -CONFIG_BLK_DEV_3W_XXXX_RAID=y -# CONFIG_SCSI_3W_9XXX is not set -# CONFIG_SCSI_7000FASST is not set -# CONFIG_SCSI_ACARD is not set -# CONFIG_SCSI_AHA152X is not set -# CONFIG_SCSI_AHA1542 is not set -CONFIG_SCSI_AACRAID=y -CONFIG_SCSI_AIC7XXX=y -CONFIG_AIC7XXX_CMDS_PER_DEVICE=32 -CONFIG_AIC7XXX_RESET_DELAY_MS=15000 -CONFIG_AIC7XXX_DEBUG_ENABLE=y -CONFIG_AIC7XXX_DEBUG_MASK=0 -CONFIG_AIC7XXX_REG_PRETTY_PRINT=y -# CONFIG_SCSI_AIC7XXX_OLD is not set -CONFIG_SCSI_AIC79XX=y -CONFIG_AIC79XX_CMDS_PER_DEVICE=32 -CONFIG_AIC79XX_RESET_DELAY_MS=15000 -# CONFIG_AIC79XX_ENABLE_RD_STRM is not set -CONFIG_AIC79XX_DEBUG_ENABLE=y -CONFIG_AIC79XX_DEBUG_MASK=0 -CONFIG_AIC79XX_REG_PRETTY_PRINT=y -# CONFIG_SCSI_DPT_I2O is not set -# CONFIG_SCSI_ADVANSYS is not set -# CONFIG_SCSI_IN2000 is not set -CONFIG_MEGARAID_NEWGEN=y -# CONFIG_MEGARAID_MM is not set -CONFIG_SCSI_SATA=y -# CONFIG_SCSI_SATA_AHCI is not set -# CONFIG_SCSI_SATA_SVW is not set -CONFIG_SCSI_ATA_PIIX=y -# CONFIG_SCSI_SATA_NV is not set -CONFIG_SCSI_SATA_PROMISE=y -# CONFIG_SCSI_SATA_QSTOR is not set -CONFIG_SCSI_SATA_SX4=y -CONFIG_SCSI_SATA_SIL=y -# CONFIG_SCSI_SATA_SIS is not set -# CONFIG_SCSI_SATA_ULI is not set -# CONFIG_SCSI_SATA_VIA is not set -# CONFIG_SCSI_SATA_VITESSE is not set -CONFIG_SCSI_BUSLOGIC=y -# CONFIG_SCSI_OMIT_FLASHPOINT is not set -# CONFIG_SCSI_CPQFCTS is not set -# CONFIG_SCSI_DMX3191D is not set -# CONFIG_SCSI_DTC3280 is not set -# CONFIG_SCSI_EATA is not set -# CONFIG_SCSI_EATA_PIO is not set -# CONFIG_SCSI_FUTURE_DOMAIN is not set -# CONFIG_SCSI_GDTH is not set -# CONFIG_SCSI_GENERIC_NCR5380 is not set -# CONFIG_SCSI_GENERIC_NCR5380_MMIO is not set -# CONFIG_SCSI_IPS is not set -# CONFIG_SCSI_INITIO is not set -# CONFIG_SCSI_INIA100 is not set -# CONFIG_SCSI_NCR53C406A is not set -# CONFIG_SCSI_SYM53C8XX_2 is not set -# CONFIG_SCSI_IPR is not set -# CONFIG_SCSI_PAS16 is not set -# CONFIG_SCSI_PCI2000 is not set -# CONFIG_SCSI_PCI2220I is not set -# CONFIG_SCSI_PSI240I is not set -# CONFIG_SCSI_QLOGIC_FAS is not set -# CONFIG_SCSI_QLOGIC_ISP is not set -# CONFIG_SCSI_QLOGIC_FC is not set -# CONFIG_SCSI_QLOGIC_1280 is not set -CONFIG_SCSI_QLA2XXX=y -# CONFIG_SCSI_QLA21XX is not set -# CONFIG_SCSI_QLA22XX is not set -# CONFIG_SCSI_QLA2300 is not set -# CONFIG_SCSI_QLA2322 is not set -# CONFIG_SCSI_QLA6312 is not set -# CONFIG_SCSI_LPFC is not set -# CONFIG_SCSI_SEAGATE is not set -# CONFIG_SCSI_SYM53C416 is not set -# CONFIG_SCSI_DC395x is not set -# CONFIG_SCSI_DC390T is not set -# CONFIG_SCSI_T128 is not set -# CONFIG_SCSI_U14_34F is not set -# CONFIG_SCSI_ULTRASTOR is not set -# CONFIG_SCSI_NSP32 is not set -# CONFIG_SCSI_DEBUG is not set - -# -# Old CD-ROM drivers (not SCSI, not IDE) -# -# CONFIG_CD_NO_IDESCSI is not set - -# -# Multi-device support (RAID and LVM) -# -CONFIG_MD=y -CONFIG_BLK_DEV_MD=y -# CONFIG_MD_LINEAR is not set -CONFIG_MD_RAID0=y -CONFIG_MD_RAID1=y -# CONFIG_MD_RAID10 is not set -CONFIG_MD_RAID5=y -# CONFIG_MD_RAID6 is not set -# CONFIG_MD_MULTIPATH is not set -# CONFIG_MD_FAULTY is not set -CONFIG_BLK_DEV_DM=y -# CONFIG_DM_CRYPT is not set -CONFIG_DM_SNAPSHOT=y -CONFIG_DM_MIRROR=y -# CONFIG_DM_ZERO is not set -# CONFIG_DM_MULTIPATH is not set - -# -# Fusion MPT device support -# -CONFIG_FUSION=y -CONFIG_FUSION_MAX_SGE=40 -# CONFIG_FUSION_CTL is not set - -# -# IEEE 1394 (FireWire) support -# -# CONFIG_IEEE1394 is not set - -# -# I2O device support -# -# CONFIG_I2O is not set - -# -# Networking support -# -CONFIG_NET=y - -# -# Networking options -# -CONFIG_PACKET=y -# CONFIG_PACKET_MMAP is not set -CONFIG_UNIX=y -# CONFIG_NET_KEY is not set -CONFIG_INET=y -# CONFIG_IP_MULTICAST is not set -# CONFIG_IP_ADVANCED_ROUTER is not set -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -# CONFIG_IP_PNP_BOOTP is not set -# CONFIG_IP_PNP_RARP is not set -# CONFIG_NET_IPIP is not set -# CONFIG_NET_IPGRE is not set -# CONFIG_ARPD is not set -# CONFIG_SYN_COOKIES is not set -# CONFIG_INET_AH is not set -# CONFIG_INET_ESP is not set -# CONFIG_INET_IPCOMP is not set -# CONFIG_INET_TUNNEL is not set -CONFIG_IP_TCPDIAG=y -# CONFIG_IP_TCPDIAG_IPV6 is not set - -# -# IP: Virtual Server Configuration -# -# CONFIG_IP_VS is not set -# CONFIG_IPV6 is not set -CONFIG_NETFILTER=y -# CONFIG_NETFILTER_DEBUG is not set -CONFIG_BRIDGE_NETFILTER=y - -# -# IP: Netfilter Configuration -# -CONFIG_IP_NF_CONNTRACK=m -CONFIG_IP_NF_CT_ACCT=y -# CONFIG_IP_NF_CONNTRACK_MARK is not set -# CONFIG_IP_NF_CT_PROTO_SCTP is not set -CONFIG_IP_NF_FTP=m -# CONFIG_IP_NF_IRC is not set -# CONFIG_IP_NF_TFTP is not set -# CONFIG_IP_NF_AMANDA is not set -# CONFIG_IP_NF_QUEUE is not set -CONFIG_IP_NF_IPTABLES=m -# CONFIG_IP_NF_MATCH_LIMIT is not set -CONFIG_IP_NF_MATCH_IPRANGE=m -# CONFIG_IP_NF_MATCH_MAC is not set -# CONFIG_IP_NF_MATCH_PKTTYPE is not set -# CONFIG_IP_NF_MATCH_MARK is not set -# CONFIG_IP_NF_MATCH_MULTIPORT is not set -# CONFIG_IP_NF_MATCH_TOS is not set -# CONFIG_IP_NF_MATCH_RECENT is not set -# CONFIG_IP_NF_MATCH_ECN is not set -# CONFIG_IP_NF_MATCH_DSCP is not set -# CONFIG_IP_NF_MATCH_AH_ESP is not set -# CONFIG_IP_NF_MATCH_LENGTH is not set -# CONFIG_IP_NF_MATCH_TTL is not set -# CONFIG_IP_NF_MATCH_TCPMSS is not set -# CONFIG_IP_NF_MATCH_HELPER is not set -# CONFIG_IP_NF_MATCH_STATE is not set -# CONFIG_IP_NF_MATCH_CONNTRACK is not set -# CONFIG_IP_NF_MATCH_OWNER is not set -CONFIG_IP_NF_MATCH_PHYSDEV=m -# CONFIG_IP_NF_MATCH_ADDRTYPE is not set -# CONFIG_IP_NF_MATCH_REALM is not set -# CONFIG_IP_NF_MATCH_SCTP is not set -# CONFIG_IP_NF_MATCH_COMMENT is not set -# CONFIG_IP_NF_MATCH_HASHLIMIT is not set -CONFIG_IP_NF_FILTER=m -CONFIG_IP_NF_TARGET_REJECT=m -# CONFIG_IP_NF_TARGET_LOG is not set -# CONFIG_IP_NF_TARGET_ULOG is not set -# CONFIG_IP_NF_TARGET_TCPMSS is not set -CONFIG_IP_NF_NAT=m -CONFIG_IP_NF_NAT_NEEDED=y -CONFIG_IP_NF_TARGET_MASQUERADE=m -# CONFIG_IP_NF_TARGET_REDIRECT is not set -# CONFIG_IP_NF_TARGET_NETMAP is not set -# CONFIG_IP_NF_TARGET_SAME is not set -# CONFIG_IP_NF_NAT_SNMP_BASIC is not set -CONFIG_IP_NF_NAT_FTP=m -# CONFIG_IP_NF_MANGLE is not set -# CONFIG_IP_NF_RAW is not set -# CONFIG_IP_NF_ARPTABLES is not set - -# -# Bridge: Netfilter Configuration -# -# CONFIG_BRIDGE_NF_EBTABLES is not set - -# -# SCTP Configuration (EXPERIMENTAL) -# -# CONFIG_IP_SCTP is not set -# CONFIG_ATM is not set -CONFIG_BRIDGE=y -# CONFIG_VLAN_8021Q is not set -# CONFIG_DECNET is not set -# CONFIG_LLC2 is not set -# CONFIG_IPX is not set -# CONFIG_ATALK is not set -# CONFIG_X25 is not set -# CONFIG_LAPB is not set -# CONFIG_NET_DIVERT is not set -# CONFIG_ECONET is not set -# CONFIG_WAN_ROUTER is not set - -# -# QoS and/or fair queueing -# -# CONFIG_NET_SCHED is not set -# CONFIG_NET_CLS_ROUTE is not set - -# -# Network testing -# -# CONFIG_NET_PKTGEN is not set -# CONFIG_NETPOLL is not set -# CONFIG_NET_POLL_CONTROLLER is not set -# CONFIG_HAMRADIO is not set -# CONFIG_IRDA is not set -# CONFIG_BT is not set -CONFIG_NETDEVICES=y -# CONFIG_DUMMY is not set -# CONFIG_BONDING is not set -# CONFIG_EQUALIZER is not set -CONFIG_TUN=y - -# -# ARCnet devices -# -# CONFIG_ARCNET is not set - -# -# Ethernet (10 or 100Mbit) -# -CONFIG_NET_ETHERNET=y -CONFIG_MII=y -# CONFIG_HAPPYMEAL is not set -# CONFIG_SUNGEM is not set -CONFIG_NET_VENDOR_3COM=y -# CONFIG_EL1 is not set -# CONFIG_EL2 is not set -# CONFIG_ELPLUS is not set -# CONFIG_EL16 is not set -# CONFIG_EL3 is not set -# CONFIG_3C515 is not set -CONFIG_VORTEX=y -# CONFIG_TYPHOON is not set -# CONFIG_LANCE is not set -# CONFIG_NET_VENDOR_SMC is not set -# CONFIG_NET_VENDOR_RACAL is not set - -# -# Tulip family network device support -# -CONFIG_NET_TULIP=y -# CONFIG_DE2104X is not set -CONFIG_TULIP=y -# CONFIG_TULIP_MWI is not set -# CONFIG_TULIP_MMIO is not set -# CONFIG_TULIP_NAPI is not set -# CONFIG_DE4X5 is not set -# CONFIG_WINBOND_840 is not set -# CONFIG_DM9102 is not set -# CONFIG_AT1700 is not set -# CONFIG_DEPCA is not set -# CONFIG_HP100 is not set -# CONFIG_NET_ISA is not set -CONFIG_NET_PCI=y -CONFIG_PCNET32=y -# CONFIG_AMD8111_ETH is not set -# CONFIG_ADAPTEC_STARFIRE is not set -# CONFIG_AC3200 is not set -# CONFIG_APRICOT is not set -# CONFIG_B44 is not set -# CONFIG_FORCEDETH is not set -# CONFIG_CS89x0 is not set -# CONFIG_DGRS is not set -# CONFIG_EEPRO100 is not set -CONFIG_E100=y -# CONFIG_FEALNX is not set -# CONFIG_NATSEMI is not set -CONFIG_NE2K_PCI=y -# CONFIG_8139CP is not set -CONFIG_8139TOO=y -CONFIG_8139TOO_PIO=y -# CONFIG_8139TOO_TUNE_TWISTER is not set -# CONFIG_8139TOO_8129 is not set -# CONFIG_8139_OLD_RX_RESET is not set -# CONFIG_SIS900 is not set -# CONFIG_EPIC100 is not set -# CONFIG_SUNDANCE is not set -# CONFIG_TLAN is not set -CONFIG_VIA_RHINE=y -# CONFIG_VIA_RHINE_MMIO is not set -# CONFIG_NET_POCKET is not set - -# -# Ethernet (1000 Mbit) -# -CONFIG_ACENIC=y -# CONFIG_ACENIC_OMIT_TIGON_I is not set -# CONFIG_DL2K is not set -CONFIG_E1000=y -# CONFIG_E1000_NAPI is not set -# CONFIG_NS83820 is not set -# CONFIG_HAMACHI is not set -# CONFIG_YELLOWFIN is not set -# CONFIG_R8169 is not set -CONFIG_SK98LIN=y -# CONFIG_VIA_VELOCITY is not set -CONFIG_TIGON3=y -# CONFIG_BNX2 is not set - -# -# Ethernet (10000 Mbit) -# -# CONFIG_IXGB is not set -# CONFIG_S2IO is not set - -# -# Token Ring devices -# -# CONFIG_TR is not set - -# -# Wireless LAN (non-hamradio) -# -# CONFIG_NET_RADIO is not set - -# -# Wan interfaces -# -# CONFIG_WAN is not set -# CONFIG_FDDI is not set -# CONFIG_HIPPI is not set -# CONFIG_PPP is not set -# CONFIG_SLIP is not set -# CONFIG_NET_FC is not set -# CONFIG_SHAPER is not set -# CONFIG_NETCONSOLE is not set - -# -# ISDN subsystem -# -# CONFIG_ISDN is not set - -# -# Telephony Support -# -# CONFIG_PHONE is not set - -# -# Input device support -# -CONFIG_INPUT=y - -# -# Userland interfaces -# -CONFIG_INPUT_MOUSEDEV=y -CONFIG_INPUT_MOUSEDEV_PSAUX=y -CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024 -CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 -# CONFIG_INPUT_JOYDEV is not set -# CONFIG_INPUT_TSDEV is not set -# CONFIG_INPUT_EVDEV is not set -# CONFIG_INPUT_EVBUG is not set - -# -# Input Device Drivers -# -CONFIG_INPUT_KEYBOARD=y -CONFIG_KEYBOARD_ATKBD=y -# CONFIG_KEYBOARD_SUNKBD is not set -# CONFIG_KEYBOARD_LKKBD is not set -# CONFIG_KEYBOARD_XTKBD is not set -# CONFIG_KEYBOARD_NEWTON is not set -CONFIG_INPUT_MOUSE=y -CONFIG_MOUSE_PS2=y -# CONFIG_MOUSE_SERIAL is not set -# CONFIG_MOUSE_INPORT is not set -# CONFIG_MOUSE_LOGIBM is not set -# CONFIG_MOUSE_PC110PAD is not set -# CONFIG_MOUSE_VSXXXAA is not set -# CONFIG_INPUT_JOYSTICK is not set -# CONFIG_INPUT_TOUCHSCREEN is not set -# CONFIG_INPUT_MISC is not set - -# -# Hardware I/O ports -# -CONFIG_SERIO=y -CONFIG_SERIO_I8042=y -CONFIG_SERIO_SERPORT=y -# CONFIG_SERIO_CT82C710 is not set -# CONFIG_SERIO_PCIPS2 is not set -CONFIG_SERIO_LIBPS2=y -# CONFIG_SERIO_RAW is not set -# CONFIG_GAMEPORT is not set - -# -# Character devices -# -CONFIG_VT=y -CONFIG_VT_CONSOLE=y -CONFIG_HW_CONSOLE=y -# CONFIG_SERIAL_NONSTANDARD is not set - -# -# Serial drivers -# -# CONFIG_SERIAL_8250 is not set - -# -# Non-8250 serial port support -# -# CONFIG_SERIAL_JSM is not set -CONFIG_UNIX98_PTYS=y -CONFIG_LEGACY_PTYS=y -CONFIG_LEGACY_PTY_COUNT=256 - -# -# IPMI -# -# CONFIG_IPMI_HANDLER is not set - -# -# Watchdog Cards -# -# CONFIG_WATCHDOG is not set -# CONFIG_HW_RANDOM is not set -# CONFIG_NVRAM is not set -# CONFIG_RTC is not set -# CONFIG_GEN_RTC is not set -# CONFIG_DTLK is not set -# CONFIG_R3964 is not set -# CONFIG_APPLICOM is not set -# CONFIG_SONYPI is not set - -# -# Ftape, the floppy tape device driver -# -# CONFIG_FTAPE is not set -CONFIG_AGP=m -CONFIG_AGP_ALI=m -CONFIG_AGP_ATI=m -CONFIG_AGP_AMD=m -CONFIG_AGP_AMD64=m -CONFIG_AGP_INTEL=m -CONFIG_AGP_NVIDIA=m -CONFIG_AGP_SIS=m -CONFIG_AGP_SWORKS=m -CONFIG_AGP_VIA=m -# CONFIG_AGP_EFFICEON is not set -CONFIG_DRM=m -CONFIG_DRM_TDFX=m -# CONFIG_DRM_GAMMA is not set -CONFIG_DRM_R128=m -CONFIG_DRM_RADEON=m -CONFIG_DRM_I810=m -CONFIG_DRM_I830=m -CONFIG_DRM_I915=m -CONFIG_DRM_MGA=m -CONFIG_DRM_SIS=m -# CONFIG_MWAVE is not set -# CONFIG_RAW_DRIVER is not set -# CONFIG_HPET is not set -# CONFIG_HANGCHECK_TIMER is not set - -# -# TPM devices -# -# CONFIG_TCG_TPM is not set - -# -# I2C support -# -# CONFIG_I2C is not set - -# -# Dallas's 1-wire bus -# -# CONFIG_W1 is not set - -# -# Misc devices -# -# CONFIG_IBM_ASM is not set - -# -# Multimedia devices -# -# CONFIG_VIDEO_DEV is not set - -# -# Digital Video Broadcasting Devices -# -# CONFIG_DVB is not set - -# -# Graphics support -# -# CONFIG_FB is not set -# CONFIG_VIDEO_SELECT is not set - -# -# Console display driver support -# -CONFIG_VGA_CONSOLE=y -# CONFIG_MDA_CONSOLE is not set -CONFIG_DUMMY_CONSOLE=y - -# -# Sound -# -# CONFIG_SOUND is not set - -# -# USB support -# -CONFIG_USB_ARCH_HAS_HCD=y -CONFIG_USB_ARCH_HAS_OHCI=y -CONFIG_USB=y -# CONFIG_USB_DEBUG is not set - -# -# Miscellaneous USB options -# -# CONFIG_USB_DEVICEFS is not set -# CONFIG_USB_BANDWIDTH is not set -# CONFIG_USB_DYNAMIC_MINORS is not set -# CONFIG_USB_OTG is not set - -# -# USB Host Controller Drivers -# -# CONFIG_USB_EHCI_HCD is not set -CONFIG_USB_OHCI_HCD=y -# CONFIG_USB_OHCI_BIG_ENDIAN is not set -CONFIG_USB_OHCI_LITTLE_ENDIAN=y -CONFIG_USB_UHCI_HCD=y -# CONFIG_USB_SL811_HCD is not set - -# -# USB Device Class drivers -# -# CONFIG_USB_BLUETOOTH_TTY is not set -# CONFIG_USB_ACM is not set -# CONFIG_USB_PRINTER is not set - -# -# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed; see USB_STORAGE Help for more information -# -# CONFIG_USB_STORAGE is not set - -# -# USB Input Devices -# -CONFIG_USB_HID=y -CONFIG_USB_HIDINPUT=y -# CONFIG_HID_FF is not set -# CONFIG_USB_HIDDEV is not set -# CONFIG_USB_AIPTEK is not set -# CONFIG_USB_WACOM is not set -# CONFIG_USB_KBTAB is not set -# CONFIG_USB_POWERMATE is not set -# CONFIG_USB_MTOUCH is not set -# CONFIG_USB_EGALAX is not set -# CONFIG_USB_XPAD is not set -# CONFIG_USB_ATI_REMOTE is not set - -# -# USB Imaging devices -# -# CONFIG_USB_MDC800 is not set -# CONFIG_USB_MICROTEK is not set - -# -# USB Multimedia devices -# -# CONFIG_USB_DABUSB is not set - -# -# Video4Linux support is needed for USB Multimedia device support -# - -# -# USB Network Adapters -# -# CONFIG_USB_CATC is not set -# CONFIG_USB_KAWETH is not set -# CONFIG_USB_PEGASUS is not set -# CONFIG_USB_RTL8150 is not set -# CONFIG_USB_USBNET is not set -CONFIG_USB_MON=y - -# -# USB port drivers -# - -# -# USB Serial Converter support -# -# CONFIG_USB_SERIAL is not set - -# -# USB Miscellaneous drivers -# -# CONFIG_USB_EMI62 is not set -# CONFIG_USB_EMI26 is not set -# CONFIG_USB_AUERSWALD is not set -# CONFIG_USB_RIO500 is not set -# CONFIG_USB_LEGOTOWER is not set -# CONFIG_USB_LCD is not set -# CONFIG_USB_LED is not set -# CONFIG_USB_CYTHERM is not set -# CONFIG_USB_PHIDGETKIT is not set -# CONFIG_USB_PHIDGETSERVO is not set -# CONFIG_USB_IDMOUSE is not set - -# -# USB ATM/DSL drivers -# - -# -# USB Gadget Support -# -# CONFIG_USB_GADGET is not set - -# -# MMC/SD Card support -# -# CONFIG_MMC is not set - -# -# InfiniBand support -# -# CONFIG_INFINIBAND is not set - -# -# Power management options -# - -# -# ACPI (Advanced Configuration and Power Interface) Support -# -CONFIG_ACPI=y -CONFIG_ACPI_BOOT=y -CONFIG_ACPI_INTERPRETER=y -CONFIG_ACPI_AC=m -CONFIG_ACPI_BATTERY=m -CONFIG_ACPI_BUTTON=m -CONFIG_ACPI_VIDEO=m -CONFIG_ACPI_FAN=m -CONFIG_ACPI_PROCESSOR=m -CONFIG_ACPI_THERMAL=m -CONFIG_ACPI_ASUS=m -CONFIG_ACPI_IBM=m -CONFIG_ACPI_TOSHIBA=m -# CONFIG_ACPI_CUSTOM_DSDT is not set -CONFIG_ACPI_BLACKLIST_YEAR=0 -# CONFIG_ACPI_DEBUG is not set -CONFIG_ACPI_BUS=y -CONFIG_ACPI_EC=y -CONFIG_ACPI_POWER=y -CONFIG_ACPI_PCI=y -CONFIG_ACPI_SYSTEM=y -# CONFIG_X86_PM_TIMER is not set -# CONFIG_ACPI_CONTAINER is not set - -# -# File systems -# -CONFIG_EXT2_FS=y -# CONFIG_EXT2_FS_XATTR is not set -CONFIG_EXT3_FS=y -CONFIG_EXT3_FS_XATTR=y -# CONFIG_EXT3_FS_POSIX_ACL is not set -# CONFIG_EXT3_FS_SECURITY is not set -CONFIG_JBD=y -# CONFIG_JBD_DEBUG is not set -CONFIG_FS_MBCACHE=y -CONFIG_REISERFS_FS=y -# CONFIG_REISERFS_CHECK is not set -# CONFIG_REISERFS_PROC_INFO is not set -# CONFIG_REISERFS_FS_XATTR is not set -# CONFIG_JFS_FS is not set - -# -# XFS support -# -# CONFIG_XFS_FS is not set -# CONFIG_MINIX_FS is not set -# CONFIG_ROMFS_FS is not set -# CONFIG_QUOTA is not set -CONFIG_DNOTIFY=y -CONFIG_AUTOFS_FS=y -CONFIG_AUTOFS4_FS=y - -# -# CD-ROM/DVD Filesystems -# -CONFIG_ISO9660_FS=y -CONFIG_JOLIET=y -CONFIG_ZISOFS=y -CONFIG_ZISOFS_FS=y -# CONFIG_UDF_FS is not set - -# -# DOS/FAT/NT Filesystems -# -CONFIG_FAT_FS=m -CONFIG_MSDOS_FS=m -CONFIG_VFAT_FS=m -CONFIG_FAT_DEFAULT_CODEPAGE=437 -CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" -# CONFIG_NTFS_FS is not set - -# -# Pseudo filesystems -# -CONFIG_PROC_FS=y -CONFIG_PROC_KCORE=y -CONFIG_SYSFS=y -# CONFIG_DEVFS_FS is not set -# CONFIG_DEVPTS_FS_XATTR is not set -CONFIG_TMPFS=y -# CONFIG_TMPFS_XATTR is not set -# CONFIG_HUGETLBFS is not set -# CONFIG_HUGETLB_PAGE is not set -CONFIG_RAMFS=y - -# -# Miscellaneous filesystems -# -# CONFIG_ADFS_FS is not set -# CONFIG_AFFS_FS is not set -# CONFIG_HFS_FS is not set -# CONFIG_HFSPLUS_FS is not set -# CONFIG_BEFS_FS is not set -# CONFIG_BFS_FS is not set -# CONFIG_EFS_FS is not set -CONFIG_CRAMFS=y -# CONFIG_VXFS_FS is not set -# CONFIG_HPFS_FS is not set -# CONFIG_QNX4FS_FS is not set -# CONFIG_SYSV_FS is not set -# CONFIG_UFS_FS is not set - -# -# Network File Systems -# -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -# CONFIG_NFS_V4 is not set -# CONFIG_NFS_DIRECTIO is not set -CONFIG_NFSD=m -CONFIG_NFSD_V3=y -# CONFIG_NFSD_V4 is not set -CONFIG_NFSD_TCP=y -CONFIG_ROOT_NFS=y -CONFIG_LOCKD=y -CONFIG_LOCKD_V4=y -CONFIG_EXPORTFS=m -CONFIG_SUNRPC=y -# CONFIG_RPCSEC_GSS_KRB5 is not set -# CONFIG_RPCSEC_GSS_SPKM3 is not set -# CONFIG_SMB_FS is not set -# CONFIG_CIFS is not set -# CONFIG_NCP_FS is not set -# CONFIG_CODA_FS is not set -# CONFIG_AFS_FS is not set - -# -# Partition Types -# -# CONFIG_PARTITION_ADVANCED is not set -CONFIG_MSDOS_PARTITION=y - -# -# Native Language Support -# -CONFIG_NLS=y -CONFIG_NLS_DEFAULT="iso8859-1" -CONFIG_NLS_CODEPAGE_437=y -# CONFIG_NLS_CODEPAGE_737 is not set -# CONFIG_NLS_CODEPAGE_775 is not set -# CONFIG_NLS_CODEPAGE_850 is not set -# CONFIG_NLS_CODEPAGE_852 is not set -# CONFIG_NLS_CODEPAGE_855 is not set -# CONFIG_NLS_CODEPAGE_857 is not set -# CONFIG_NLS_CODEPAGE_860 is not set -# CONFIG_NLS_CODEPAGE_861 is not set -# CONFIG_NLS_CODEPAGE_862 is not set -# CONFIG_NLS_CODEPAGE_863 is not set -# CONFIG_NLS_CODEPAGE_864 is not set -# CONFIG_NLS_CODEPAGE_865 is not set -# CONFIG_NLS_CODEPAGE_866 is not set -# CONFIG_NLS_CODEPAGE_869 is not set -# CONFIG_NLS_CODEPAGE_936 is not set -# CONFIG_NLS_CODEPAGE_950 is not set -# CONFIG_NLS_CODEPAGE_932 is not set -# CONFIG_NLS_CODEPAGE_949 is not set -# CONFIG_NLS_CODEPAGE_874 is not set -# CONFIG_NLS_ISO8859_8 is not set -# CONFIG_NLS_CODEPAGE_1250 is not set -# CONFIG_NLS_CODEPAGE_1251 is not set -# CONFIG_NLS_ASCII is not set -CONFIG_NLS_ISO8859_1=y -# CONFIG_NLS_ISO8859_2 is not set -# CONFIG_NLS_ISO8859_3 is not set -# CONFIG_NLS_ISO8859_4 is not set -# CONFIG_NLS_ISO8859_5 is not set -# CONFIG_NLS_ISO8859_6 is not set -# CONFIG_NLS_ISO8859_7 is not set -# CONFIG_NLS_ISO8859_9 is not set -# CONFIG_NLS_ISO8859_13 is not set -# CONFIG_NLS_ISO8859_14 is not set -# CONFIG_NLS_ISO8859_15 is not set -# CONFIG_NLS_KOI8_R is not set -# CONFIG_NLS_KOI8_U is not set -# CONFIG_NLS_UTF8 is not set - -# -# Security options -# -# CONFIG_KEYS is not set -# CONFIG_SECURITY is not set - -# -# Cryptographic options -# -CONFIG_CRYPTO=y -CONFIG_CRYPTO_HMAC=y -# CONFIG_CRYPTO_NULL is not set -# CONFIG_CRYPTO_MD4 is not set -CONFIG_CRYPTO_MD5=m -CONFIG_CRYPTO_SHA1=m -# CONFIG_CRYPTO_SHA256 is not set -# CONFIG_CRYPTO_SHA512 is not set -# CONFIG_CRYPTO_WP512 is not set -# CONFIG_CRYPTO_TGR192 is not set -CONFIG_CRYPTO_DES=m -# CONFIG_CRYPTO_BLOWFISH is not set -# CONFIG_CRYPTO_TWOFISH is not set -# CONFIG_CRYPTO_SERPENT is not set -# CONFIG_CRYPTO_AES_586 is not set -# CONFIG_CRYPTO_CAST5 is not set -# CONFIG_CRYPTO_CAST6 is not set -# CONFIG_CRYPTO_TEA is not set -# CONFIG_CRYPTO_ARC4 is not set -# CONFIG_CRYPTO_KHAZAD is not set -# CONFIG_CRYPTO_ANUBIS is not set -# CONFIG_CRYPTO_DEFLATE is not set -# CONFIG_CRYPTO_MICHAEL_MIC is not set -CONFIG_CRYPTO_CRC32C=m -# CONFIG_CRYPTO_TEST is not set - -# -# Hardware crypto devices -# -# CONFIG_CRYPTO_DEV_PADLOCK is not set - -# -# Library routines -# -# CONFIG_CRC_CCITT is not set -CONFIG_CRC32=y -CONFIG_LIBCRC32C=y -CONFIG_ZLIB_INFLATE=y - -# -# Kernel hacking -# -# CONFIG_PRINTK_TIME is not set -CONFIG_DEBUG_KERNEL=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_SCHEDSTATS is not set -# CONFIG_DEBUG_SLAB is not set -# CONFIG_DEBUG_SPINLOCK is not set -# CONFIG_DEBUG_SPINLOCK_SLEEP is not set -# CONFIG_DEBUG_KOBJECT is not set -# CONFIG_DEBUG_HIGHMEM is not set -CONFIG_DEBUG_BUGVERBOSE=y -# CONFIG_DEBUG_INFO is not set -# CONFIG_DEBUG_FS is not set -# CONFIG_FRAME_POINTER is not set -# CONFIG_DEBUG_STACKOVERFLOW is not set -# CONFIG_KPROBES is not set -# CONFIG_DEBUG_STACK_USAGE is not set -# CONFIG_DEBUG_PAGEALLOC is not set -# CONFIG_4KSTACKS is not set -CONFIG_X86_FIND_SMP_CONFIG=y -CONFIG_X86_MPPARSE=y diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/configs/xen0_defconfig_x86_64 --- a/linux-2.6-xen-sparse/arch/xen/configs/xen0_defconfig_x86_64 Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,1184 +0,0 @@ -# -# Automatically generated make config: don't edit -# Linux kernel version: 2.6.12.6-xen0 -# Mon Nov 7 17:24:18 2005 -# -CONFIG_XEN=y -CONFIG_ARCH_XEN=y -CONFIG_NO_IDLE_HZ=y - -# -# XEN -# -CONFIG_XEN_PRIVILEGED_GUEST=y -CONFIG_XEN_PHYSDEV_ACCESS=y -CONFIG_XEN_BLKDEV_BACKEND=y -# CONFIG_XEN_BLKDEV_TAP_BE is not set -CONFIG_XEN_NETDEV_BACKEND=y -# CONFIG_XEN_NETDEV_PIPELINED_TRANSMITTER is not set -# CONFIG_XEN_TPMDEV_FRONTEND is not set -# CONFIG_XEN_TPMDEV_BACKEND is not set -CONFIG_XEN_BLKDEV_FRONTEND=y -CONFIG_XEN_NETDEV_FRONTEND=y -# CONFIG_XEN_BLKDEV_TAP is not set -# CONFIG_XEN_SHADOW_MODE is not set -CONFIG_XEN_SCRUB_PAGES=y -# CONFIG_XEN_X86 is not set -CONFIG_XEN_X86_64=y -CONFIG_HAVE_ARCH_ALLOC_SKB=y -CONFIG_HAVE_ARCH_DEV_ALLOC_SKB=y - -# -# Code maturity level options -# -CONFIG_EXPERIMENTAL=y -# CONFIG_CLEAN_COMPILE is not set -CONFIG_BROKEN=y -CONFIG_BROKEN_ON_SMP=y -CONFIG_INIT_ENV_ARG_LIMIT=32 - -# -# General setup -# -CONFIG_LOCALVERSION="" -CONFIG_SWAP=y -CONFIG_SYSVIPC=y -# CONFIG_POSIX_MQUEUE is not set -# CONFIG_BSD_PROCESS_ACCT is not set -CONFIG_SYSCTL=y -# CONFIG_AUDIT is not set -CONFIG_HOTPLUG=y -CONFIG_KOBJECT_UEVENT=y -# CONFIG_IKCONFIG is not set -# CONFIG_EMBEDDED is not set -CONFIG_KALLSYMS=y -# CONFIG_KALLSYMS_ALL is not set -# CONFIG_KALLSYMS_EXTRA_PASS is not set -CONFIG_PRINTK=y -CONFIG_BUG=y -CONFIG_BASE_FULL=y -CONFIG_FUTEX=y -CONFIG_EPOLL=y -CONFIG_SHMEM=y -CONFIG_CC_ALIGN_FUNCTIONS=0 -CONFIG_CC_ALIGN_LABELS=0 -CONFIG_CC_ALIGN_LOOPS=0 -CONFIG_CC_ALIGN_JUMPS=0 -# CONFIG_TINY_SHMEM is not set -CONFIG_BASE_SMALL=0 - -# -# Loadable module support -# -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_MODULE_FORCE_UNLOAD is not set -CONFIG_OBSOLETE_MODPARM=y -# CONFIG_MODVERSIONS is not set -# CONFIG_MODULE_SRCVERSION_ALL is not set -CONFIG_KMOD=y -CONFIG_XENARCH="x86_64" -CONFIG_X86=y -CONFIG_MMU=y -CONFIG_UID16=y -CONFIG_GENERIC_ISA_DMA=y -CONFIG_GENERIC_IOMAP=y -CONFIG_X86_CMPXCHG=y -CONFIG_X86_L1_CACHE_SHIFT=7 -CONFIG_RWSEM_GENERIC_SPINLOCK=y -CONFIG_GENERIC_CALIBRATE_DELAY=y -CONFIG_X86_GOOD_APIC=y -# CONFIG_HPET_TIMER is not set -# CONFIG_SMP is not set -CONFIG_MICROCODE=y -# CONFIG_X86_CPUID is not set -CONFIG_SWIOTLB=y -# CONFIG_NUMA is not set -# CONFIG_MTRR is not set -CONFIG_X86_LOCAL_APIC=y -CONFIG_X86_IO_APIC=y -CONFIG_PCI=y -CONFIG_PCI_DIRECT=y -# CONFIG_PCI_MMCONFIG is not set -CONFIG_ISA_DMA_API=y -CONFIG_GENERIC_HARDIRQS=y -CONFIG_GENERIC_IRQ_PROBE=y -CONFIG_SECCOMP=y - -# -# X86_64 processor configuration -# -CONFIG_X86_64=y -CONFIG_64BIT=y -CONFIG_EARLY_PRINTK=y - -# -# Processor type and features -# -# CONFIG_MPSC is not set -CONFIG_GENERIC_CPU=y -CONFIG_X86_L1_CACHE_BYTES=128 -# CONFIG_X86_TSC is not set -CONFIG_X86_XEN_GENAPIC=y -# CONFIG_X86_MSR is not set -# CONFIG_GART_IOMMU is not set -CONFIG_DUMMY_IOMMU=y -# CONFIG_X86_MCE is not set - -# -# Power management options -# -# CONFIG_PM is not set - -# -# CPU Frequency scaling -# -# CONFIG_CPU_FREQ is not set - -# -# Bus options (PCI etc.) -# -# CONFIG_UNORDERED_IO is not set - -# -# Executable file formats / Emulations -# -CONFIG_IA32_EMULATION=y -# CONFIG_IA32_AOUT is not set -CONFIG_COMPAT=y -CONFIG_SYSVIPC_COMPAT=y - -# -# Executable file formats -# -CONFIG_BINFMT_ELF=y -CONFIG_BINFMT_MISC=y - -# -# Device Drivers -# - -# -# Generic Driver Options -# -CONFIG_STANDALONE=y -# CONFIG_PREVENT_FIRMWARE_BUILD is not set -# CONFIG_FW_LOADER is not set -# CONFIG_DEBUG_DRIVER is not set - -# -# Memory Technology Devices (MTD) -# -# CONFIG_MTD is not set - -# -# Parallel port support -# -# CONFIG_PARPORT is not set - -# -# Plug and Play support -# -# CONFIG_PNP is not set - -# -# Block devices -# -CONFIG_BLK_DEV_FD=y -# CONFIG_BLK_CPQ_DA is not set -CONFIG_BLK_CPQ_CISS_DA=y -# CONFIG_CISS_SCSI_TAPE is not set -# CONFIG_BLK_DEV_DAC960 is not set -# CONFIG_BLK_DEV_UMEM is not set -# CONFIG_BLK_DEV_COW_COMMON is not set -CONFIG_BLK_DEV_LOOP=y -# CONFIG_BLK_DEV_CRYPTOLOOP is not set -# CONFIG_BLK_DEV_NBD is not set -# CONFIG_BLK_DEV_SX8 is not set -# CONFIG_BLK_DEV_UB is not set -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_COUNT=16 -CONFIG_BLK_DEV_RAM_SIZE=16384 -CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="" -# CONFIG_LBD is not set -# CONFIG_CDROM_PKTCDVD is not set - -# -# IO Schedulers -# -CONFIG_IOSCHED_NOOP=y -CONFIG_IOSCHED_AS=y -CONFIG_IOSCHED_DEADLINE=y -CONFIG_IOSCHED_CFQ=y -# CONFIG_ATA_OVER_ETH is not set - -# -# ATA/ATAPI/MFM/RLL support -# -CONFIG_IDE=y -CONFIG_BLK_DEV_IDE=y - -# -# Please see Documentation/ide.txt for help/info on IDE drives -# -# CONFIG_BLK_DEV_IDE_SATA is not set -# CONFIG_BLK_DEV_HD_IDE is not set -CONFIG_BLK_DEV_IDEDISK=y -# CONFIG_IDEDISK_MULTI_MODE is not set -CONFIG_BLK_DEV_IDECD=y -# CONFIG_BLK_DEV_IDETAPE is not set -# CONFIG_BLK_DEV_IDEFLOPPY is not set -# CONFIG_BLK_DEV_IDESCSI is not set -# CONFIG_IDE_TASK_IOCTL is not set - -# -# IDE chipset support/bugfixes -# -CONFIG_IDE_GENERIC=y -# CONFIG_BLK_DEV_CMD640 is not set -CONFIG_BLK_DEV_IDEPCI=y -# CONFIG_IDEPCI_SHARE_IRQ is not set -# CONFIG_BLK_DEV_OFFBOARD is not set -CONFIG_BLK_DEV_GENERIC=y -# CONFIG_BLK_DEV_OPTI621 is not set -# CONFIG_BLK_DEV_RZ1000 is not set -CONFIG_BLK_DEV_IDEDMA_PCI=y -# CONFIG_BLK_DEV_IDEDMA_FORCED is not set -CONFIG_IDEDMA_PCI_AUTO=y -# CONFIG_IDEDMA_ONLYDISK is not set -# CONFIG_BLK_DEV_AEC62XX is not set -# CONFIG_BLK_DEV_ALI15X3 is not set -# CONFIG_BLK_DEV_AMD74XX is not set -# CONFIG_BLK_DEV_ATIIXP is not set -# CONFIG_BLK_DEV_CMD64X is not set -# CONFIG_BLK_DEV_TRIFLEX is not set -# CONFIG_BLK_DEV_CY82C693 is not set -# CONFIG_BLK_DEV_CS5520 is not set -# CONFIG_BLK_DEV_CS5530 is not set -# CONFIG_BLK_DEV_HPT34X is not set -# CONFIG_BLK_DEV_HPT366 is not set -# CONFIG_BLK_DEV_SC1200 is not set -CONFIG_BLK_DEV_PIIX=y -# CONFIG_BLK_DEV_NS87415 is not set -# CONFIG_BLK_DEV_PDC202XX_OLD is not set -# CONFIG_BLK_DEV_PDC202XX_NEW is not set -CONFIG_BLK_DEV_SVWKS=y -# CONFIG_BLK_DEV_SIIMAGE is not set -# CONFIG_BLK_DEV_SIS5513 is not set -# CONFIG_BLK_DEV_SLC90E66 is not set -# CONFIG_BLK_DEV_TRM290 is not set -# CONFIG_BLK_DEV_VIA82CXXX is not set -# CONFIG_IDE_ARM is not set -CONFIG_BLK_DEV_IDEDMA=y -# CONFIG_IDEDMA_IVB is not set -CONFIG_IDEDMA_AUTO=y -# CONFIG_BLK_DEV_HD is not set - -# -# SCSI device support -# -CONFIG_SCSI=y -CONFIG_SCSI_PROC_FS=y - -# -# SCSI support type (disk, tape, CD-ROM) -# -CONFIG_BLK_DEV_SD=y -# CONFIG_CHR_DEV_ST is not set -# CONFIG_CHR_DEV_OSST is not set -# CONFIG_BLK_DEV_SR is not set -# CONFIG_CHR_DEV_SG is not set - -# -# Some SCSI devices (e.g. CD jukebox) support multiple LUNs -# -# CONFIG_SCSI_MULTI_LUN is not set -# CONFIG_SCSI_CONSTANTS is not set -# CONFIG_SCSI_LOGGING is not set - -# -# SCSI Transport Attributes -# -CONFIG_SCSI_SPI_ATTRS=y -# CONFIG_SCSI_FC_ATTRS is not set -# CONFIG_SCSI_ISCSI_ATTRS is not set - -# -# SCSI low-level drivers -# -CONFIG_BLK_DEV_3W_XXXX_RAID=y -# CONFIG_SCSI_3W_9XXX is not set -# CONFIG_SCSI_ACARD is not set -CONFIG_SCSI_AACRAID=y -CONFIG_SCSI_AIC7XXX=y -CONFIG_AIC7XXX_CMDS_PER_DEVICE=32 -CONFIG_AIC7XXX_RESET_DELAY_MS=15000 -# CONFIG_AIC7XXX_BUILD_FIRMWARE is not set -CONFIG_AIC7XXX_DEBUG_ENABLE=y -CONFIG_AIC7XXX_DEBUG_MASK=0 -CONFIG_AIC7XXX_REG_PRETTY_PRINT=y -# CONFIG_SCSI_AIC7XXX_OLD is not set -CONFIG_SCSI_AIC79XX=y -CONFIG_AIC79XX_CMDS_PER_DEVICE=32 -CONFIG_AIC79XX_RESET_DELAY_MS=15000 -# CONFIG_AIC79XX_BUILD_FIRMWARE is not set -# CONFIG_AIC79XX_ENABLE_RD_STRM is not set -CONFIG_AIC79XX_DEBUG_ENABLE=y -CONFIG_AIC79XX_DEBUG_MASK=0 -CONFIG_AIC79XX_REG_PRETTY_PRINT=y -# CONFIG_SCSI_ADVANSYS is not set -CONFIG_MEGARAID_NEWGEN=y -# CONFIG_MEGARAID_MM is not set -CONFIG_SCSI_SATA=y -# CONFIG_SCSI_SATA_AHCI is not set -# CONFIG_SCSI_SATA_SVW is not set -CONFIG_SCSI_ATA_PIIX=y -# CONFIG_SCSI_SATA_NV is not set -CONFIG_SCSI_SATA_PROMISE=y -# CONFIG_SCSI_SATA_QSTOR is not set -CONFIG_SCSI_SATA_SX4=y -CONFIG_SCSI_SATA_SIL=y -# CONFIG_SCSI_SATA_SIS is not set -# CONFIG_SCSI_SATA_ULI is not set -# CONFIG_SCSI_SATA_VIA is not set -# CONFIG_SCSI_SATA_VITESSE is not set -CONFIG_SCSI_BUSLOGIC=y -# CONFIG_SCSI_OMIT_FLASHPOINT is not set -# CONFIG_SCSI_CPQFCTS is not set -# CONFIG_SCSI_DMX3191D is not set -# CONFIG_SCSI_EATA is not set -# CONFIG_SCSI_EATA_PIO is not set -# CONFIG_SCSI_FUTURE_DOMAIN is not set -# CONFIG_SCSI_GDTH is not set -# CONFIG_SCSI_IPS is not set -# CONFIG_SCSI_INITIO is not set -# CONFIG_SCSI_INIA100 is not set -# CONFIG_SCSI_SYM53C8XX_2 is not set -# CONFIG_SCSI_IPR is not set -# CONFIG_SCSI_PCI2000 is not set -# CONFIG_SCSI_PCI2220I is not set -# CONFIG_SCSI_QLOGIC_ISP is not set -# CONFIG_SCSI_QLOGIC_FC is not set -# CONFIG_SCSI_QLOGIC_1280 is not set -CONFIG_SCSI_QLA2XXX=y -# CONFIG_SCSI_QLA21XX is not set -# CONFIG_SCSI_QLA22XX is not set -# CONFIG_SCSI_QLA2300 is not set -# CONFIG_SCSI_QLA2322 is not set -# CONFIG_SCSI_QLA6312 is not set -# CONFIG_SCSI_LPFC is not set -# CONFIG_SCSI_DC395x is not set -# CONFIG_SCSI_DC390T is not set -# CONFIG_SCSI_DEBUG is not set - -# -# Multi-device support (RAID and LVM) -# -CONFIG_MD=y -CONFIG_BLK_DEV_MD=y -CONFIG_MD_LINEAR=y -CONFIG_MD_RAID0=y -CONFIG_MD_RAID1=y -# CONFIG_MD_RAID10 is not set -# CONFIG_MD_RAID5 is not set -# CONFIG_MD_RAID6 is not set -CONFIG_MD_MULTIPATH=y -# CONFIG_MD_FAULTY is not set -CONFIG_BLK_DEV_DM=y -CONFIG_DM_CRYPT=y -CONFIG_DM_SNAPSHOT=y -CONFIG_DM_MIRROR=y -# CONFIG_DM_ZERO is not set -CONFIG_DM_MULTIPATH=y -CONFIG_DM_MULTIPATH_EMC=y - -# -# Fusion MPT device support -# -CONFIG_FUSION=y -CONFIG_FUSION_MAX_SGE=40 -# CONFIG_FUSION_CTL is not set - -# -# IEEE 1394 (FireWire) support -# -# CONFIG_IEEE1394 is not set - -# -# I2O device support -# -# CONFIG_I2O is not set - -# -# Networking support -# -CONFIG_NET=y - -# -# Networking options -# -CONFIG_PACKET=y -# CONFIG_PACKET_MMAP is not set -CONFIG_UNIX=y -# CONFIG_NET_KEY is not set -CONFIG_INET=y -# CONFIG_IP_MULTICAST is not set -# CONFIG_IP_ADVANCED_ROUTER is not set -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -# CONFIG_IP_PNP_BOOTP is not set -# CONFIG_IP_PNP_RARP is not set -# CONFIG_NET_IPIP is not set -# CONFIG_NET_IPGRE is not set -# CONFIG_ARPD is not set -# CONFIG_SYN_COOKIES is not set -# CONFIG_INET_AH is not set -# CONFIG_INET_ESP is not set -# CONFIG_INET_IPCOMP is not set -# CONFIG_INET_TUNNEL is not set -CONFIG_IP_TCPDIAG=y -# CONFIG_IP_TCPDIAG_IPV6 is not set - -# -# IP: Virtual Server Configuration -# -# CONFIG_IP_VS is not set -# CONFIG_IPV6 is not set -CONFIG_NETFILTER=y -# CONFIG_NETFILTER_DEBUG is not set -CONFIG_BRIDGE_NETFILTER=y - -# -# IP: Netfilter Configuration -# -CONFIG_IP_NF_CONNTRACK=m -CONFIG_IP_NF_CT_ACCT=y -# CONFIG_IP_NF_CONNTRACK_MARK is not set -# CONFIG_IP_NF_CT_PROTO_SCTP is not set -CONFIG_IP_NF_FTP=m -# CONFIG_IP_NF_IRC is not set -# CONFIG_IP_NF_TFTP is not set -# CONFIG_IP_NF_AMANDA is not set -# CONFIG_IP_NF_QUEUE is not set -CONFIG_IP_NF_IPTABLES=m -# CONFIG_IP_NF_MATCH_LIMIT is not set -CONFIG_IP_NF_MATCH_IPRANGE=m -# CONFIG_IP_NF_MATCH_MAC is not set -# CONFIG_IP_NF_MATCH_PKTTYPE is not set -# CONFIG_IP_NF_MATCH_MARK is not set -# CONFIG_IP_NF_MATCH_MULTIPORT is not set -# CONFIG_IP_NF_MATCH_TOS is not set -# CONFIG_IP_NF_MATCH_RECENT is not set -# CONFIG_IP_NF_MATCH_ECN is not set -# CONFIG_IP_NF_MATCH_DSCP is not set -# CONFIG_IP_NF_MATCH_AH_ESP is not set -# CONFIG_IP_NF_MATCH_LENGTH is not set -# CONFIG_IP_NF_MATCH_TTL is not set -# CONFIG_IP_NF_MATCH_TCPMSS is not set -# CONFIG_IP_NF_MATCH_HELPER is not set -# CONFIG_IP_NF_MATCH_STATE is not set -# CONFIG_IP_NF_MATCH_CONNTRACK is not set -# CONFIG_IP_NF_MATCH_OWNER is not set -CONFIG_IP_NF_MATCH_PHYSDEV=m -# CONFIG_IP_NF_MATCH_ADDRTYPE is not set -# CONFIG_IP_NF_MATCH_REALM is not set -# CONFIG_IP_NF_MATCH_SCTP is not set -# CONFIG_IP_NF_MATCH_COMMENT is not set -# CONFIG_IP_NF_MATCH_HASHLIMIT is not set -CONFIG_IP_NF_FILTER=m -CONFIG_IP_NF_TARGET_REJECT=m -# CONFIG_IP_NF_TARGET_LOG is not set -# CONFIG_IP_NF_TARGET_ULOG is not set -# CONFIG_IP_NF_TARGET_TCPMSS is not set -CONFIG_IP_NF_NAT=m -CONFIG_IP_NF_NAT_NEEDED=y -CONFIG_IP_NF_TARGET_MASQUERADE=m -# CONFIG_IP_NF_TARGET_REDIRECT is not set -# CONFIG_IP_NF_TARGET_NETMAP is not set -# CONFIG_IP_NF_TARGET_SAME is not set -# CONFIG_IP_NF_NAT_SNMP_BASIC is not set -CONFIG_IP_NF_NAT_FTP=m -# CONFIG_IP_NF_MANGLE is not set -# CONFIG_IP_NF_RAW is not set -# CONFIG_IP_NF_ARPTABLES is not set - -# -# Bridge: Netfilter Configuration -# -# CONFIG_BRIDGE_NF_EBTABLES is not set - -# -# SCTP Configuration (EXPERIMENTAL) -# -# CONFIG_IP_SCTP is not set -# CONFIG_ATM is not set -CONFIG_BRIDGE=y -# CONFIG_VLAN_8021Q is not set -# CONFIG_DECNET is not set -# CONFIG_LLC2 is not set -# CONFIG_IPX is not set -# CONFIG_ATALK is not set -# CONFIG_X25 is not set -# CONFIG_LAPB is not set -# CONFIG_NET_DIVERT is not set -# CONFIG_ECONET is not set -# CONFIG_WAN_ROUTER is not set - -# -# QoS and/or fair queueing -# -# CONFIG_NET_SCHED is not set -# CONFIG_NET_CLS_ROUTE is not set - -# -# Network testing -# -# CONFIG_NET_PKTGEN is not set -# CONFIG_NETPOLL is not set -# CONFIG_NET_POLL_CONTROLLER is not set -# CONFIG_HAMRADIO is not set -# CONFIG_IRDA is not set -# CONFIG_BT is not set -CONFIG_NETDEVICES=y -# CONFIG_DUMMY is not set -# CONFIG_BONDING is not set -# CONFIG_EQUALIZER is not set -CONFIG_TUN=y - -# -# ARCnet devices -# -# CONFIG_ARCNET is not set - -# -# Ethernet (10 or 100Mbit) -# -CONFIG_NET_ETHERNET=y -CONFIG_MII=y -# CONFIG_HAPPYMEAL is not set -# CONFIG_SUNGEM is not set -CONFIG_NET_VENDOR_3COM=y -CONFIG_VORTEX=y -# CONFIG_TYPHOON is not set - -# -# Tulip family network device support -# -CONFIG_NET_TULIP=y -# CONFIG_DE2104X is not set -CONFIG_TULIP=y -# CONFIG_TULIP_MWI is not set -# CONFIG_TULIP_MMIO is not set -# CONFIG_TULIP_NAPI is not set -# CONFIG_DE4X5 is not set -# CONFIG_WINBOND_840 is not set -# CONFIG_DM9102 is not set -# CONFIG_HP100 is not set -CONFIG_NET_PCI=y -CONFIG_PCNET32=y -# CONFIG_AMD8111_ETH is not set -# CONFIG_ADAPTEC_STARFIRE is not set -# CONFIG_B44 is not set -# CONFIG_FORCEDETH is not set -# CONFIG_DGRS is not set -# CONFIG_EEPRO100 is not set -CONFIG_E100=y -# CONFIG_FEALNX is not set -# CONFIG_NATSEMI is not set -CONFIG_NE2K_PCI=y -# CONFIG_8139CP is not set -CONFIG_8139TOO=y -CONFIG_8139TOO_PIO=y -# CONFIG_8139TOO_TUNE_TWISTER is not set -# CONFIG_8139TOO_8129 is not set -# CONFIG_8139_OLD_RX_RESET is not set -# CONFIG_SIS900 is not set -# CONFIG_EPIC100 is not set -# CONFIG_SUNDANCE is not set -CONFIG_VIA_RHINE=y -# CONFIG_VIA_RHINE_MMIO is not set - -# -# Ethernet (1000 Mbit) -# -CONFIG_ACENIC=y -# CONFIG_ACENIC_OMIT_TIGON_I is not set -# CONFIG_DL2K is not set -CONFIG_E1000=y -# CONFIG_E1000_NAPI is not set -# CONFIG_NS83820 is not set -# CONFIG_HAMACHI is not set -# CONFIG_YELLOWFIN is not set -# CONFIG_R8169 is not set -CONFIG_SK98LIN=y -# CONFIG_VIA_VELOCITY is not set -CONFIG_TIGON3=y -# CONFIG_BNX2 is not set - -# -# Ethernet (10000 Mbit) -# -# CONFIG_IXGB is not set -# CONFIG_S2IO is not set - -# -# Token Ring devices -# -# CONFIG_TR is not set - -# -# Wireless LAN (non-hamradio) -# -# CONFIG_NET_RADIO is not set - -# -# Wan interfaces -# -# CONFIG_WAN is not set -# CONFIG_FDDI is not set -# CONFIG_HIPPI is not set -# CONFIG_PPP is not set -# CONFIG_SLIP is not set -# CONFIG_NET_FC is not set -# CONFIG_SHAPER is not set -# CONFIG_NETCONSOLE is not set - -# -# ISDN subsystem -# -# CONFIG_ISDN is not set - -# -# Telephony Support -# -# CONFIG_PHONE is not set - -# -# Input device support -# -CONFIG_INPUT=y - -# -# Userland interfaces -# -CONFIG_INPUT_MOUSEDEV=y -CONFIG_INPUT_MOUSEDEV_PSAUX=y -CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024 -CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 -# CONFIG_INPUT_JOYDEV is not set -# CONFIG_INPUT_TSDEV is not set -# CONFIG_INPUT_EVDEV is not set -# CONFIG_INPUT_EVBUG is not set - -# -# Input Device Drivers -# -CONFIG_INPUT_KEYBOARD=y -CONFIG_KEYBOARD_ATKBD=y -# CONFIG_KEYBOARD_SUNKBD is not set -# CONFIG_KEYBOARD_LKKBD is not set -# CONFIG_KEYBOARD_XTKBD is not set -# CONFIG_KEYBOARD_NEWTON is not set -CONFIG_INPUT_MOUSE=y -CONFIG_MOUSE_PS2=y -# CONFIG_MOUSE_SERIAL is not set -# CONFIG_MOUSE_VSXXXAA is not set -# CONFIG_INPUT_JOYSTICK is not set -# CONFIG_INPUT_TOUCHSCREEN is not set -# CONFIG_INPUT_MISC is not set - -# -# Hardware I/O ports -# -CONFIG_SERIO=y -CONFIG_SERIO_I8042=y -CONFIG_SERIO_SERPORT=y -# CONFIG_SERIO_CT82C710 is not set -# CONFIG_SERIO_PCIPS2 is not set -CONFIG_SERIO_LIBPS2=y -# CONFIG_SERIO_RAW is not set -# CONFIG_GAMEPORT is not set - -# -# Character devices -# -CONFIG_VT=y -CONFIG_VT_CONSOLE=y -CONFIG_HW_CONSOLE=y -# CONFIG_SERIAL_NONSTANDARD is not set - -# -# Serial drivers -# -# CONFIG_SERIAL_8250 is not set - -# -# Non-8250 serial port support -# -# CONFIG_SERIAL_JSM is not set -CONFIG_UNIX98_PTYS=y -CONFIG_LEGACY_PTYS=y -CONFIG_LEGACY_PTY_COUNT=256 - -# -# IPMI -# -# CONFIG_IPMI_HANDLER is not set - -# -# Watchdog Cards -# -# CONFIG_WATCHDOG is not set -# CONFIG_HW_RANDOM is not set -# CONFIG_NVRAM is not set -CONFIG_RTC=y -# CONFIG_DTLK is not set -# CONFIG_R3964 is not set -# CONFIG_APPLICOM is not set - -# -# Ftape, the floppy tape device driver -# -# CONFIG_FTAPE is not set -CONFIG_AGP=m -CONFIG_AGP_AMD64=m -# CONFIG_AGP_INTEL is not set -CONFIG_DRM=m -CONFIG_DRM_TDFX=m -# CONFIG_DRM_GAMMA is not set -CONFIG_DRM_R128=m -CONFIG_DRM_RADEON=m -CONFIG_DRM_MGA=m -CONFIG_DRM_SIS=m -# CONFIG_MWAVE is not set -# CONFIG_RAW_DRIVER is not set -# CONFIG_HPET is not set -# CONFIG_HANGCHECK_TIMER is not set - -# -# TPM devices -# -# CONFIG_TCG_TPM is not set - -# -# I2C support -# -# CONFIG_I2C is not set - -# -# Dallas's 1-wire bus -# -# CONFIG_W1 is not set - -# -# Misc devices -# -# CONFIG_IBM_ASM is not set - -# -# Multimedia devices -# -# CONFIG_VIDEO_DEV is not set - -# -# Digital Video Broadcasting Devices -# -# CONFIG_DVB is not set - -# -# Graphics support -# -# CONFIG_FB is not set -# CONFIG_VIDEO_SELECT is not set - -# -# Console display driver support -# -CONFIG_VGA_CONSOLE=y -CONFIG_DUMMY_CONSOLE=y - -# -# Sound -# -# CONFIG_SOUND is not set - -# -# USB support -# -CONFIG_USB_ARCH_HAS_HCD=y -CONFIG_USB_ARCH_HAS_OHCI=y -CONFIG_USB=y -# CONFIG_USB_DEBUG is not set - -# -# Miscellaneous USB options -# -# CONFIG_USB_DEVICEFS is not set -# CONFIG_USB_BANDWIDTH is not set -# CONFIG_USB_DYNAMIC_MINORS is not set -# CONFIG_USB_OTG is not set - -# -# USB Host Controller Drivers -# -# CONFIG_USB_EHCI_HCD is not set -CONFIG_USB_OHCI_HCD=y -# CONFIG_USB_OHCI_BIG_ENDIAN is not set -CONFIG_USB_OHCI_LITTLE_ENDIAN=y -CONFIG_USB_UHCI_HCD=y -# CONFIG_USB_SL811_HCD is not set - -# -# USB Device Class drivers -# -# CONFIG_USB_BLUETOOTH_TTY is not set -# CONFIG_USB_ACM is not set -# CONFIG_USB_PRINTER is not set - -# -# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed; see USB_STORAGE Help for more information -# -# CONFIG_USB_STORAGE is not set - -# -# USB Input Devices -# -CONFIG_USB_HID=y -CONFIG_USB_HIDINPUT=y -# CONFIG_HID_FF is not set -# CONFIG_USB_HIDDEV is not set -# CONFIG_USB_AIPTEK is not set -# CONFIG_USB_WACOM is not set -# CONFIG_USB_KBTAB is not set -# CONFIG_USB_POWERMATE is not set -# CONFIG_USB_MTOUCH is not set -# CONFIG_USB_EGALAX is not set -# CONFIG_USB_XPAD is not set -# CONFIG_USB_ATI_REMOTE is not set - -# -# USB Imaging devices -# -# CONFIG_USB_MDC800 is not set -# CONFIG_USB_MICROTEK is not set - -# -# USB Multimedia devices -# -# CONFIG_USB_DABUSB is not set - -# -# Video4Linux support is needed for USB Multimedia device support -# - -# -# USB Network Adapters -# -# CONFIG_USB_CATC is not set -# CONFIG_USB_KAWETH is not set -# CONFIG_USB_PEGASUS is not set -# CONFIG_USB_RTL8150 is not set -# CONFIG_USB_USBNET is not set -CONFIG_USB_MON=y - -# -# USB port drivers -# - -# -# USB Serial Converter support -# -# CONFIG_USB_SERIAL is not set - -# -# USB Miscellaneous drivers -# -# CONFIG_USB_EMI62 is not set -# CONFIG_USB_EMI26 is not set -# CONFIG_USB_AUERSWALD is not set -# CONFIG_USB_RIO500 is not set -# CONFIG_USB_LEGOTOWER is not set -# CONFIG_USB_LCD is not set -# CONFIG_USB_LED is not set -# CONFIG_USB_CYTHERM is not set -# CONFIG_USB_PHIDGETKIT is not set -# CONFIG_USB_PHIDGETSERVO is not set -# CONFIG_USB_IDMOUSE is not set - -# -# USB ATM/DSL drivers -# - -# -# USB Gadget Support -# -# CONFIG_USB_GADGET is not set - -# -# MMC/SD Card support -# -# CONFIG_MMC is not set - -# -# InfiniBand support -# -CONFIG_INFINIBAND=y -CONFIG_INFINIBAND_MTHCA=y -CONFIG_INFINIBAND_MTHCA_DEBUG=y -CONFIG_INFINIBAND_IPOIB=y -CONFIG_INFINIBAND_IPOIB_DEBUG=y -CONFIG_INFINIBAND_IPOIB_DEBUG_DATA=y - -# -# Power management options -# - -# -# ACPI (Advanced Configuration and Power Interface) Support -# -CONFIG_ACPI=y -CONFIG_ACPI_BOOT=y -CONFIG_ACPI_INTERPRETER=y -CONFIG_ACPI_AC=m -CONFIG_ACPI_BATTERY=m -CONFIG_ACPI_BUTTON=m -CONFIG_ACPI_VIDEO=m -CONFIG_ACPI_FAN=m -CONFIG_ACPI_PROCESSOR=m -CONFIG_ACPI_THERMAL=m -CONFIG_ACPI_ASUS=m -CONFIG_ACPI_IBM=m -CONFIG_ACPI_TOSHIBA=m -CONFIG_ACPI_BLACKLIST_YEAR=0 -# CONFIG_ACPI_DEBUG is not set -CONFIG_ACPI_BUS=y -CONFIG_ACPI_EC=y -CONFIG_ACPI_POWER=y -CONFIG_ACPI_PCI=y -CONFIG_ACPI_SYSTEM=y -# CONFIG_ACPI_CONTAINER is not set - -# -# File systems -# -CONFIG_EXT2_FS=y -# CONFIG_EXT2_FS_XATTR is not set -CONFIG_EXT3_FS=y -CONFIG_EXT3_FS_XATTR=y -# CONFIG_EXT3_FS_POSIX_ACL is not set -# CONFIG_EXT3_FS_SECURITY is not set -CONFIG_JBD=y -# CONFIG_JBD_DEBUG is not set -CONFIG_FS_MBCACHE=y -CONFIG_REISERFS_FS=y -# CONFIG_REISERFS_CHECK is not set -# CONFIG_REISERFS_PROC_INFO is not set -# CONFIG_REISERFS_FS_XATTR is not set -# CONFIG_JFS_FS is not set - -# -# XFS support -# -# CONFIG_XFS_FS is not set -# CONFIG_MINIX_FS is not set -# CONFIG_ROMFS_FS is not set -# CONFIG_QUOTA is not set -CONFIG_DNOTIFY=y -CONFIG_AUTOFS_FS=y -CONFIG_AUTOFS4_FS=y - -# -# CD-ROM/DVD Filesystems -# -CONFIG_ISO9660_FS=y -CONFIG_JOLIET=y -CONFIG_ZISOFS=y -CONFIG_ZISOFS_FS=y -# CONFIG_UDF_FS is not set - -# -# DOS/FAT/NT Filesystems -# -CONFIG_FAT_FS=y -CONFIG_MSDOS_FS=y -CONFIG_VFAT_FS=y -CONFIG_FAT_DEFAULT_CODEPAGE=437 -CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" -# CONFIG_NTFS_FS is not set - -# -# Pseudo filesystems -# -CONFIG_PROC_FS=y -CONFIG_PROC_KCORE=y -CONFIG_SYSFS=y -# CONFIG_DEVFS_FS is not set -# CONFIG_DEVPTS_FS_XATTR is not set -CONFIG_TMPFS=y -# CONFIG_TMPFS_XATTR is not set -# CONFIG_HUGETLBFS is not set -# CONFIG_HUGETLB_PAGE is not set -CONFIG_RAMFS=y - -# -# Miscellaneous filesystems -# -# CONFIG_ADFS_FS is not set -# CONFIG_AFFS_FS is not set -# CONFIG_HFS_FS is not set -# CONFIG_HFSPLUS_FS is not set -# CONFIG_BEFS_FS is not set -# CONFIG_BFS_FS is not set -# CONFIG_EFS_FS is not set -CONFIG_CRAMFS=y -# CONFIG_VXFS_FS is not set -# CONFIG_HPFS_FS is not set -# CONFIG_QNX4FS_FS is not set -# CONFIG_SYSV_FS is not set -# CONFIG_UFS_FS is not set - -# -# Network File Systems -# -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -# CONFIG_NFS_V4 is not set -# CONFIG_NFS_DIRECTIO is not set -CONFIG_NFSD=m -CONFIG_NFSD_V3=y -# CONFIG_NFSD_V4 is not set -CONFIG_NFSD_TCP=y -CONFIG_ROOT_NFS=y -CONFIG_LOCKD=y -CONFIG_LOCKD_V4=y -CONFIG_EXPORTFS=m -CONFIG_SUNRPC=y -# CONFIG_RPCSEC_GSS_KRB5 is not set -# CONFIG_RPCSEC_GSS_SPKM3 is not set -# CONFIG_SMB_FS is not set -# CONFIG_CIFS is not set -# CONFIG_NCP_FS is not set -# CONFIG_CODA_FS is not set -# CONFIG_AFS_FS is not set - -# -# Partition Types -# -# CONFIG_PARTITION_ADVANCED is not set -CONFIG_MSDOS_PARTITION=y - -# -# Native Language Support -# -CONFIG_NLS=y -CONFIG_NLS_DEFAULT="iso8859-1" -CONFIG_NLS_CODEPAGE_437=y -# CONFIG_NLS_CODEPAGE_737 is not set -# CONFIG_NLS_CODEPAGE_775 is not set -# CONFIG_NLS_CODEPAGE_850 is not set -# CONFIG_NLS_CODEPAGE_852 is not set -# CONFIG_NLS_CODEPAGE_855 is not set -# CONFIG_NLS_CODEPAGE_857 is not set -# CONFIG_NLS_CODEPAGE_860 is not set -# CONFIG_NLS_CODEPAGE_861 is not set -# CONFIG_NLS_CODEPAGE_862 is not set -# CONFIG_NLS_CODEPAGE_863 is not set -# CONFIG_NLS_CODEPAGE_864 is not set -# CONFIG_NLS_CODEPAGE_865 is not set -# CONFIG_NLS_CODEPAGE_866 is not set -# CONFIG_NLS_CODEPAGE_869 is not set -# CONFIG_NLS_CODEPAGE_936 is not set -# CONFIG_NLS_CODEPAGE_950 is not set -# CONFIG_NLS_CODEPAGE_932 is not set -# CONFIG_NLS_CODEPAGE_949 is not set -# CONFIG_NLS_CODEPAGE_874 is not set -# CONFIG_NLS_ISO8859_8 is not set -# CONFIG_NLS_CODEPAGE_1250 is not set -# CONFIG_NLS_CODEPAGE_1251 is not set -# CONFIG_NLS_ASCII is not set -CONFIG_NLS_ISO8859_1=y -# CONFIG_NLS_ISO8859_2 is not set -# CONFIG_NLS_ISO8859_3 is not set -# CONFIG_NLS_ISO8859_4 is not set -# CONFIG_NLS_ISO8859_5 is not set -# CONFIG_NLS_ISO8859_6 is not set -# CONFIG_NLS_ISO8859_7 is not set -# CONFIG_NLS_ISO8859_9 is not set -# CONFIG_NLS_ISO8859_13 is not set -# CONFIG_NLS_ISO8859_14 is not set -# CONFIG_NLS_ISO8859_15 is not set -# CONFIG_NLS_KOI8_R is not set -# CONFIG_NLS_KOI8_U is not set -# CONFIG_NLS_UTF8 is not set - -# -# Security options -# -# CONFIG_KEYS is not set -# CONFIG_SECURITY is not set - -# -# Cryptographic options -# -CONFIG_CRYPTO=y -CONFIG_CRYPTO_HMAC=y -# CONFIG_CRYPTO_NULL is not set -# CONFIG_CRYPTO_MD4 is not set -CONFIG_CRYPTO_MD5=m -CONFIG_CRYPTO_SHA1=m -# CONFIG_CRYPTO_SHA256 is not set -# CONFIG_CRYPTO_SHA512 is not set -# CONFIG_CRYPTO_WP512 is not set -# CONFIG_CRYPTO_TGR192 is not set -CONFIG_CRYPTO_DES=m -# CONFIG_CRYPTO_BLOWFISH is not set -# CONFIG_CRYPTO_TWOFISH is not set -# CONFIG_CRYPTO_SERPENT is not set -# CONFIG_CRYPTO_AES is not set -# CONFIG_CRYPTO_CAST5 is not set -# CONFIG_CRYPTO_CAST6 is not set -# CONFIG_CRYPTO_TEA is not set -# CONFIG_CRYPTO_ARC4 is not set -# CONFIG_CRYPTO_KHAZAD is not set -# CONFIG_CRYPTO_ANUBIS is not set -# CONFIG_CRYPTO_DEFLATE is not set -# CONFIG_CRYPTO_MICHAEL_MIC is not set -CONFIG_CRYPTO_CRC32C=m -# CONFIG_CRYPTO_TEST is not set - -# -# Hardware crypto devices -# - -# -# Library routines -# -# CONFIG_CRC_CCITT is not set -CONFIG_CRC32=y -CONFIG_LIBCRC32C=m -CONFIG_ZLIB_INFLATE=y - -# -# Kernel hacking -# -# CONFIG_PRINTK_TIME is not set -CONFIG_DEBUG_KERNEL=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_LOG_BUF_SHIFT=15 -# CONFIG_SCHEDSTATS is not set -# CONFIG_DEBUG_SLAB is not set -# CONFIG_DEBUG_SPINLOCK is not set -# CONFIG_DEBUG_SPINLOCK_SLEEP is not set -# CONFIG_DEBUG_KOBJECT is not set -# CONFIG_DEBUG_INFO is not set -# CONFIG_DEBUG_FS is not set -# CONFIG_DEBUG_STACKOVERFLOW is not set -# CONFIG_KPROBES is not set -# CONFIG_DEBUG_STACK_USAGE is not set -# CONFIG_DEBUG_PAGEALLOC is not set -# CONFIG_4KSTACKS is not set -CONFIG_X86_FIND_SMP_CONFIG=y -CONFIG_X86_MPPARSE=y -# CONFIG_CHECKING is not set -# CONFIG_INIT_DEBUG is not set diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/configs/xenU_defconfig_ia64 --- a/linux-2.6-xen-sparse/arch/xen/configs/xenU_defconfig_ia64 Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,1261 +0,0 @@ -# -# Automatically generated make config: don't edit -# Linux kernel version: 2.6.12 -# Thu Sep 15 11:04:33 2005 -# - -# -# Code maturity level options -# -CONFIG_EXPERIMENTAL=y -# CONFIG_CLEAN_COMPILE is not set -CONFIG_BROKEN=y -CONFIG_BROKEN_ON_SMP=y -CONFIG_LOCK_KERNEL=y -CONFIG_INIT_ENV_ARG_LIMIT=32 - -# -# General setup -# -CONFIG_LOCALVERSION="" -CONFIG_SWAP=y -CONFIG_SYSVIPC=y -# CONFIG_POSIX_MQUEUE is not set -CONFIG_BSD_PROCESS_ACCT=y -# CONFIG_BSD_PROCESS_ACCT_V3 is not set -CONFIG_SYSCTL=y -# CONFIG_AUDIT is not set -CONFIG_HOTPLUG=y -CONFIG_KOBJECT_UEVENT=y -# CONFIG_IKCONFIG is not set -# CONFIG_CPUSETS is not set -# CONFIG_EMBEDDED is not set -CONFIG_KALLSYMS=y -# CONFIG_KALLSYMS_ALL is not set -# CONFIG_KALLSYMS_EXTRA_PASS is not set -CONFIG_PRINTK=y -CONFIG_BUG=y -CONFIG_BASE_FULL=y -CONFIG_FUTEX=y -CONFIG_EPOLL=y -CONFIG_SHMEM=y -CONFIG_CC_ALIGN_FUNCTIONS=0 -CONFIG_CC_ALIGN_LABELS=0 -CONFIG_CC_ALIGN_LOOPS=0 -CONFIG_CC_ALIGN_JUMPS=0 -# CONFIG_TINY_SHMEM is not set -CONFIG_BASE_SMALL=0 - -# -# Loadable module support -# -CONFIG_MODULES=y -# CONFIG_MODULE_UNLOAD is not set -CONFIG_OBSOLETE_MODPARM=y -# CONFIG_MODVERSIONS is not set -# CONFIG_MODULE_SRCVERSION_ALL is not set -# CONFIG_KMOD is not set - -# -# Processor type and features -# -CONFIG_IA64=y -CONFIG_64BIT=y -CONFIG_MMU=y -CONFIG_RWSEM_XCHGADD_ALGORITHM=y -CONFIG_GENERIC_CALIBRATE_DELAY=y -CONFIG_TIME_INTERPOLATION=y -CONFIG_EFI=y -CONFIG_GENERIC_IOMAP=y -CONFIG_XEN=y -CONFIG_XEN_VT=n -CONFIG_ARCH_XEN=y -CONFIG_XEN_PRIVILEGED_GUEST=y -CONFIG_XEN_PHYSDEV_ACCESS=y -CONFIG_XEN_BLKDEV_GRANT=y -CONFIG_XEN_BLKDEV_FRONTEND=y -CONFIG_VGA_CONSOLE=y -CONFIG_FRAMEBUFFER_CONSOLE=n -CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y -# CONFIG_IA64_GENERIC is not set -# CONFIG_IA64_DIG is not set -CONFIG_IA64_HP_ZX1=y -# CONFIG_IA64_HP_ZX1_SWIOTLB is not set -# CONFIG_IA64_SGI_SN2 is not set -# CONFIG_IA64_HP_SIM is not set -# CONFIG_ITANIUM is not set -CONFIG_MCKINLEY=y -# CONFIG_IA64_PAGE_SIZE_4KB is not set -# CONFIG_IA64_PAGE_SIZE_8KB is not set -CONFIG_IA64_PAGE_SIZE_16KB=y -# CONFIG_IA64_PAGE_SIZE_64KB is not set -CONFIG_IA64_L1_CACHE_SHIFT=7 -# CONFIG_NUMA is not set -CONFIG_VIRTUAL_MEM_MAP=y -CONFIG_HOLES_IN_ZONE=y -# CONFIG_IA64_CYCLONE is not set -CONFIG_IOSAPIC=y -CONFIG_FORCE_MAX_ZONEORDER=18 -CONFIG_SMP=y -CONFIG_NR_CPUS=16 -# CONFIG_HOTPLUG_CPU is not set -# CONFIG_SCHED_SMT is not set -# CONFIG_PREEMPT is not set -CONFIG_HAVE_DEC_LOCK=y -# CONFIG_IA32_SUPPORT is not set -CONFIG_IA64_MCA_RECOVERY=y -CONFIG_PERFMON=y -CONFIG_IA64_PALINFO=y -CONFIG_ACPI_DEALLOCATE_IRQ=y - -# -# Firmware Drivers -# -CONFIG_EFI_VARS=y -CONFIG_EFI_PCDP=y -CONFIG_BINFMT_ELF=y -CONFIG_BINFMT_MISC=y - -# -# Power management and ACPI -# -CONFIG_PM=y -CONFIG_ACPI=y - -# -# ACPI (Advanced Configuration and Power Interface) Support -# -CONFIG_ACPI_BOOT=y -CONFIG_ACPI_INTERPRETER=y -CONFIG_ACPI_BUTTON=y -# CONFIG_ACPI_VIDEO is not set -CONFIG_ACPI_FAN=y -CONFIG_ACPI_PROCESSOR=y -CONFIG_ACPI_THERMAL=y -CONFIG_ACPI_BLACKLIST_YEAR=0 -# CONFIG_ACPI_DEBUG is not set -CONFIG_ACPI_BUS=y -CONFIG_ACPI_POWER=y -CONFIG_ACPI_PCI=y -CONFIG_ACPI_SYSTEM=y -# CONFIG_ACPI_CONTAINER is not set - -# -# Bus options (PCI, PCMCIA) -# -CONFIG_PCI=y -CONFIG_PCI_DOMAINS=y -# CONFIG_PCI_MSI is not set -CONFIG_PCI_LEGACY_PROC=y -CONFIG_PCI_NAMES=y -# CONFIG_PCI_DEBUG is not set - -# -# PCI Hotplug Support -# -CONFIG_HOTPLUG_PCI=y -# CONFIG_HOTPLUG_PCI_FAKE is not set -CONFIG_HOTPLUG_PCI_ACPI=y -# CONFIG_HOTPLUG_PCI_ACPI_IBM is not set -# CONFIG_HOTPLUG_PCI_CPCI is not set -# CONFIG_HOTPLUG_PCI_SHPC is not set - -# -# PCCARD (PCMCIA/CardBus) support -# -# CONFIG_PCCARD is not set - -# -# Device Drivers -# - -# -# Generic Driver Options -# -CONFIG_STANDALONE=y -CONFIG_PREVENT_FIRMWARE_BUILD=y -# CONFIG_FW_LOADER is not set -# CONFIG_DEBUG_DRIVER is not set - -# -# Memory Technology Devices (MTD) -# -# CONFIG_MTD is not set - -# -# Parallel port support -# -# CONFIG_PARPORT is not set - -# -# Plug and Play support -# -# CONFIG_PNP is not set - -# -# Block devices -# -# CONFIG_BLK_CPQ_DA is not set -# CONFIG_BLK_CPQ_CISS_DA is not set -# CONFIG_BLK_DEV_DAC960 is not set -# CONFIG_BLK_DEV_UMEM is not set -# CONFIG_BLK_DEV_COW_COMMON is not set -CONFIG_BLK_DEV_LOOP=y -# CONFIG_BLK_DEV_CRYPTOLOOP is not set -# CONFIG_BLK_DEV_NBD is not set -# CONFIG_BLK_DEV_SX8 is not set -# CONFIG_BLK_DEV_UB is not set -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_COUNT=16 -CONFIG_BLK_DEV_RAM_SIZE=4096 -CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="" -# CONFIG_CDROM_PKTCDVD is not set - -# -# IO Schedulers -# -CONFIG_IOSCHED_NOOP=y -CONFIG_IOSCHED_AS=y -CONFIG_IOSCHED_DEADLINE=y -CONFIG_IOSCHED_CFQ=y -# CONFIG_ATA_OVER_ETH is not set - -# -# ATA/ATAPI/MFM/RLL support -# -# CONFIG_IDE is not set - -# -# SCSI device support -# -CONFIG_SCSI=y -CONFIG_SCSI_PROC_FS=y - -# -# SCSI support type (disk, tape, CD-ROM) -# -CONFIG_BLK_DEV_SD=y -CONFIG_CHR_DEV_ST=y -CONFIG_CHR_DEV_OSST=y -CONFIG_BLK_DEV_SR=y -CONFIG_BLK_DEV_SR_VENDOR=y -CONFIG_CHR_DEV_SG=y - -# -# Some SCSI devices (e.g. CD jukebox) support multiple LUNs -# -CONFIG_SCSI_MULTI_LUN=y -CONFIG_SCSI_CONSTANTS=y -CONFIG_SCSI_LOGGING=y - -# -# SCSI Transport Attributes -# -CONFIG_SCSI_SPI_ATTRS=y -# CONFIG_SCSI_FC_ATTRS is not set -# CONFIG_SCSI_ISCSI_ATTRS is not set - -# -# SCSI low-level drivers -# -# CONFIG_BLK_DEV_3W_XXXX_RAID is not set -# CONFIG_SCSI_3W_9XXX is not set -# CONFIG_SCSI_ACARD is not set -# CONFIG_SCSI_AACRAID is not set -# CONFIG_SCSI_AIC7XXX is not set -# CONFIG_SCSI_AIC7XXX_OLD is not set -# CONFIG_SCSI_AIC79XX is not set -# CONFIG_SCSI_ADVANSYS is not set -# CONFIG_MEGARAID_NEWGEN is not set -# CONFIG_MEGARAID_LEGACY is not set -# CONFIG_SCSI_SATA is not set -# CONFIG_SCSI_CPQFCTS is not set -# CONFIG_SCSI_DMX3191D is not set -# CONFIG_SCSI_EATA_PIO is not set -# CONFIG_SCSI_FUTURE_DOMAIN is not set -# CONFIG_SCSI_IPS is not set -# CONFIG_SCSI_INITIO is not set -# CONFIG_SCSI_INIA100 is not set -CONFIG_SCSI_SYM53C8XX_2=y -CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=1 -CONFIG_SCSI_SYM53C8XX_DEFAULT_TAGS=16 -CONFIG_SCSI_SYM53C8XX_MAX_TAGS=64 -# CONFIG_SCSI_SYM53C8XX_IOMAPPED is not set -# CONFIG_SCSI_IPR is not set -# CONFIG_SCSI_PCI2000 is not set -# CONFIG_SCSI_PCI2220I is not set -# CONFIG_SCSI_QLOGIC_ISP is not set -# CONFIG_SCSI_QLOGIC_FC is not set -CONFIG_SCSI_QLOGIC_1280=y -# CONFIG_SCSI_QLOGIC_1280_1040 is not set -CONFIG_SCSI_QLA2XXX=y -# CONFIG_SCSI_QLA21XX is not set -# CONFIG_SCSI_QLA22XX is not set -# CONFIG_SCSI_QLA2300 is not set -# CONFIG_SCSI_QLA2322 is not set -# CONFIG_SCSI_QLA6312 is not set -# CONFIG_SCSI_LPFC is not set -# CONFIG_SCSI_DC395x is not set -# CONFIG_SCSI_DC390T is not set -# CONFIG_SCSI_DEBUG is not set - -# -# Multi-device support (RAID and LVM) -# -# CONFIG_MD is not set - -# -# Fusion MPT device support -# -CONFIG_FUSION=y -CONFIG_FUSION_MAX_SGE=40 -# CONFIG_FUSION_CTL is not set - -# -# IEEE 1394 (FireWire) support -# -# CONFIG_IEEE1394 is not set - -# -# I2O device support -# -# CONFIG_I2O is not set - -# -# Networking support -# -CONFIG_NET=y - -# -# Networking options -# -CONFIG_PACKET=y -# CONFIG_PACKET_MMAP is not set -CONFIG_UNIX=y -# CONFIG_NET_KEY is not set -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -# CONFIG_IP_ADVANCED_ROUTER is not set -# CONFIG_IP_PNP is not set -# CONFIG_NET_IPIP is not set -# CONFIG_NET_IPGRE is not set -# CONFIG_IP_MROUTE is not set -# CONFIG_ARPD is not set -# CONFIG_SYN_COOKIES is not set -# CONFIG_INET_AH is not set -# CONFIG_INET_ESP is not set -# CONFIG_INET_IPCOMP is not set -# CONFIG_INET_TUNNEL is not set -# CONFIG_IP_TCPDIAG is not set -# CONFIG_IP_TCPDIAG_IPV6 is not set - -# -# IP: Virtual Server Configuration -# -# CONFIG_IP_VS is not set -# CONFIG_IPV6 is not set -CONFIG_NETFILTER=y -# CONFIG_NETFILTER_DEBUG is not set - -# -# IP: Netfilter Configuration -# -# CONFIG_IP_NF_CONNTRACK is not set -# CONFIG_IP_NF_CONNTRACK_MARK is not set -# CONFIG_IP_NF_QUEUE is not set -# CONFIG_IP_NF_IPTABLES is not set -CONFIG_IP_NF_ARPTABLES=y -# CONFIG_IP_NF_ARPFILTER is not set -# CONFIG_IP_NF_ARP_MANGLE is not set - -# -# SCTP Configuration (EXPERIMENTAL) -# -# CONFIG_IP_SCTP is not set -# CONFIG_ATM is not set -# CONFIG_BRIDGE is not set -# CONFIG_VLAN_8021Q is not set -# CONFIG_DECNET is not set -# CONFIG_LLC2 is not set -# CONFIG_IPX is not set -# CONFIG_ATALK is not set -# CONFIG_X25 is not set -# CONFIG_LAPB is not set -# CONFIG_NET_DIVERT is not set -# CONFIG_ECONET is not set -# CONFIG_WAN_ROUTER is not set - -# -# QoS and/or fair queueing -# -# CONFIG_NET_SCHED is not set -# CONFIG_NET_CLS_ROUTE is not set - -# -# Network testing -# -# CONFIG_NET_PKTGEN is not set -# CONFIG_NETPOLL is not set -# CONFIG_NET_POLL_CONTROLLER is not set -# CONFIG_HAMRADIO is not set -# CONFIG_IRDA is not set -# CONFIG_BT is not set -CONFIG_NETDEVICES=y -CONFIG_DUMMY=y -# CONFIG_BONDING is not set -# CONFIG_EQUALIZER is not set -# CONFIG_TUN is not set - -# -# ARCnet devices -# -# CONFIG_ARCNET is not set - -# -# Ethernet (10 or 100Mbit) -# -CONFIG_NET_ETHERNET=y -CONFIG_MII=y -# CONFIG_HAPPYMEAL is not set -# CONFIG_SUNGEM is not set -# CONFIG_NET_VENDOR_3COM is not set - -# -# Tulip family network device support -# -CONFIG_NET_TULIP=y -# CONFIG_DE2104X is not set -CONFIG_TULIP=y -CONFIG_TULIP_MWI=y -CONFIG_TULIP_MMIO=y -CONFIG_TULIP_NAPI=y -CONFIG_TULIP_NAPI_HW_MITIGATION=y -# CONFIG_DE4X5 is not set -# CONFIG_WINBOND_840 is not set -# CONFIG_DM9102 is not set -# CONFIG_HP100 is not set -CONFIG_NET_PCI=y -# CONFIG_PCNET32 is not set -# CONFIG_AMD8111_ETH is not set -# CONFIG_ADAPTEC_STARFIRE is not set -# CONFIG_B44 is not set -# CONFIG_FORCEDETH is not set -# CONFIG_DGRS is not set -# CONFIG_EEPRO100 is not set -CONFIG_E100=y -# CONFIG_FEALNX is not set -# CONFIG_NATSEMI is not set -# CONFIG_NE2K_PCI is not set -# CONFIG_8139CP is not set -# CONFIG_8139TOO is not set -# CONFIG_SIS900 is not set -# CONFIG_EPIC100 is not set -# CONFIG_SUNDANCE is not set -# CONFIG_VIA_RHINE is not set - -# -# Ethernet (1000 Mbit) -# -# CONFIG_ACENIC is not set -# CONFIG_DL2K is not set -CONFIG_E1000=y -# CONFIG_E1000_NAPI is not set -# CONFIG_NS83820 is not set -# CONFIG_HAMACHI is not set -# CONFIG_YELLOWFIN is not set -# CONFIG_R8169 is not set -# CONFIG_SK98LIN is not set -# CONFIG_VIA_VELOCITY is not set -CONFIG_TIGON3=y -# CONFIG_BNX2 is not set - -# -# Ethernet (10000 Mbit) -# -# CONFIG_IXGB is not set -# CONFIG_S2IO is not set - -# -# Token Ring devices -# -# CONFIG_TR is not set - -# -# Wireless LAN (non-hamradio) -# -# CONFIG_NET_RADIO is not set - -# -# Wan interfaces -# -# CONFIG_WAN is not set -# CONFIG_FDDI is not set -# CONFIG_HIPPI is not set -# CONFIG_PPP is not set -# CONFIG_SLIP is not set -# CONFIG_NET_FC is not set -# CONFIG_SHAPER is not set -# CONFIG_NETCONSOLE is not set - -# -# ISDN subsystem -# -# CONFIG_ISDN is not set - -# -# Telephony Support -# -# CONFIG_PHONE is not set - -# -# Input device support -# -CONFIG_INPUT=y - -# -# Userland interfaces -# -CONFIG_INPUT_MOUSEDEV=y -CONFIG_INPUT_MOUSEDEV_PSAUX=y -CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024 -CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 -CONFIG_INPUT_JOYDEV=y -# CONFIG_INPUT_TSDEV is not set -CONFIG_INPUT_EVDEV=y -# CONFIG_INPUT_EVBUG is not set - -# -# Input Device Drivers -# -# CONFIG_INPUT_KEYBOARD is not set -# CONFIG_INPUT_MOUSE is not set -# CONFIG_INPUT_JOYSTICK is not set -# CONFIG_INPUT_TOUCHSCREEN is not set -# CONFIG_INPUT_MISC is not set - -# -# Hardware I/O ports -# -CONFIG_SERIO=y -# CONFIG_SERIO_I8042 is not set -# CONFIG_SERIO_SERPORT is not set -# CONFIG_SERIO_PCIPS2 is not set -# CONFIG_SERIO_RAW is not set -# CONFIG_GAMEPORT is not set - -# -# Character devices -# -# CONFIG_VT is not set -# CONFIG_SERIAL_NONSTANDARD is not set - -# -# Serial drivers -# -CONFIG_SERIAL_8250=y -CONFIG_SERIAL_8250_CONSOLE=y -CONFIG_SERIAL_8250_ACPI=y -CONFIG_SERIAL_8250_NR_UARTS=8 -CONFIG_SERIAL_8250_EXTENDED=y -CONFIG_SERIAL_8250_SHARE_IRQ=y -# CONFIG_SERIAL_8250_DETECT_IRQ is not set -# CONFIG_SERIAL_8250_MULTIPORT is not set -# CONFIG_SERIAL_8250_RSA is not set - -# -# Non-8250 serial port support -# -CONFIG_SERIAL_CORE=y -CONFIG_SERIAL_CORE_CONSOLE=y -# CONFIG_SERIAL_JSM is not set -CONFIG_UNIX98_PTYS=y -CONFIG_LEGACY_PTYS=y -CONFIG_LEGACY_PTY_COUNT=256 - -# -# IPMI -# -# CONFIG_IPMI_HANDLER is not set - -# -# Watchdog Cards -# -# CONFIG_WATCHDOG is not set -# CONFIG_HW_RANDOM is not set -CONFIG_EFI_RTC=y -# CONFIG_DTLK is not set -# CONFIG_R3964 is not set -# CONFIG_APPLICOM is not set - -# -# Ftape, the floppy tape device driver -# -CONFIG_AGP=y -CONFIG_AGP_HP_ZX1=y -CONFIG_DRM=y -# CONFIG_DRM_TDFX is not set -# CONFIG_DRM_GAMMA is not set -# CONFIG_DRM_R128 is not set -CONFIG_DRM_RADEON=y -# CONFIG_DRM_MGA is not set -# CONFIG_DRM_SIS is not set -# CONFIG_RAW_DRIVER is not set -# CONFIG_HPET is not set -# CONFIG_HANGCHECK_TIMER is not set - -# -# TPM devices -# -# CONFIG_TCG_TPM is not set - -# -# I2C support -# -CONFIG_I2C=y -CONFIG_I2C_CHARDEV=y - -# -# I2C Algorithms -# -CONFIG_I2C_ALGOBIT=y -CONFIG_I2C_ALGOPCF=y -# CONFIG_I2C_ALGOPCA is not set - -# -# I2C Hardware Bus support -# -# CONFIG_I2C_ALI1535 is not set -# CONFIG_I2C_ALI1563 is not set -# CONFIG_I2C_ALI15X3 is not set -# CONFIG_I2C_AMD756 is not set -# CONFIG_I2C_AMD8111 is not set -# CONFIG_I2C_I801 is not set -# CONFIG_I2C_I810 is not set -# CONFIG_I2C_PIIX4 is not set -# CONFIG_I2C_ISA is not set -# CONFIG_I2C_NFORCE2 is not set -# CONFIG_I2C_PARPORT_LIGHT is not set -# CONFIG_I2C_PROSAVAGE is not set -# CONFIG_I2C_SAVAGE4 is not set -# CONFIG_SCx200_ACB is not set -# CONFIG_I2C_SIS5595 is not set -# CONFIG_I2C_SIS630 is not set -# CONFIG_I2C_SIS96X is not set -# CONFIG_I2C_STUB is not set -# CONFIG_I2C_VIA is not set -# CONFIG_I2C_VIAPRO is not set -# CONFIG_I2C_VOODOO3 is not set -# CONFIG_I2C_PCA_ISA is not set - -# -# Hardware Sensors Chip support -# -# CONFIG_I2C_SENSOR is not set -# CONFIG_SENSORS_ADM1021 is not set -# CONFIG_SENSORS_ADM1025 is not set -# CONFIG_SENSORS_ADM1026 is not set -# CONFIG_SENSORS_ADM1031 is not set -# CONFIG_SENSORS_ASB100 is not set -# CONFIG_SENSORS_DS1621 is not set -# CONFIG_SENSORS_FSCHER is not set -# CONFIG_SENSORS_FSCPOS is not set -# CONFIG_SENSORS_GL518SM is not set -# CONFIG_SENSORS_GL520SM is not set -# CONFIG_SENSORS_IT87 is not set -# CONFIG_SENSORS_LM63 is not set -# CONFIG_SENSORS_LM75 is not set -# CONFIG_SENSORS_LM77 is not set -# CONFIG_SENSORS_LM78 is not set -# CONFIG_SENSORS_LM80 is not set -# CONFIG_SENSORS_LM83 is not set -# CONFIG_SENSORS_LM85 is not set -# CONFIG_SENSORS_LM87 is not set -# CONFIG_SENSORS_LM90 is not set -# CONFIG_SENSORS_LM92 is not set -# CONFIG_SENSORS_MAX1619 is not set -# CONFIG_SENSORS_PC87360 is not set -# CONFIG_SENSORS_SMSC47B397 is not set -# CONFIG_SENSORS_SIS5595 is not set -# CONFIG_SENSORS_SMSC47M1 is not set -# CONFIG_SENSORS_VIA686A is not set -# CONFIG_SENSORS_W83781D is not set -# CONFIG_SENSORS_W83L785TS is not set -# CONFIG_SENSORS_W83627HF is not set - -# -# Other I2C Chip support -# -# CONFIG_SENSORS_DS1337 is not set -# CONFIG_SENSORS_EEPROM is not set -# CONFIG_SENSORS_PCF8574 is not set -# CONFIG_SENSORS_PCF8591 is not set -# CONFIG_SENSORS_RTC8564 is not set -# CONFIG_I2C_DEBUG_CORE is not set -# CONFIG_I2C_DEBUG_ALGO is not set -# CONFIG_I2C_DEBUG_BUS is not set -# CONFIG_I2C_DEBUG_CHIP is not set - -# -# Dallas's 1-wire bus -# -# CONFIG_W1 is not set - -# -# Misc devices -# - -# -# Multimedia devices -# -CONFIG_VIDEO_DEV=y - -# -# Video For Linux -# - -# -# Video Adapters -# -# CONFIG_VIDEO_BT848 is not set -# CONFIG_VIDEO_CPIA is not set -# CONFIG_VIDEO_SAA5246A is not set -# CONFIG_VIDEO_SAA5249 is not set -# CONFIG_TUNER_3036 is not set -# CONFIG_VIDEO_STRADIS is not set -# CONFIG_VIDEO_ZORAN is not set -# CONFIG_VIDEO_ZR36120 is not set -# CONFIG_VIDEO_SAA7134 is not set -# CONFIG_VIDEO_MXB is not set -# CONFIG_VIDEO_DPC is not set -# CONFIG_VIDEO_HEXIUM_ORION is not set -# CONFIG_VIDEO_HEXIUM_GEMINI is not set -# CONFIG_VIDEO_CX88 is not set -# CONFIG_VIDEO_OVCAMCHIP is not set - -# -# Radio Adapters -# -# CONFIG_RADIO_GEMTEK_PCI is not set -# CONFIG_RADIO_MAXIRADIO is not set -# CONFIG_RADIO_MAESTRO is not set - -# -# Digital Video Broadcasting Devices -# -# CONFIG_DVB is not set - -# -# Graphics support -# -CONFIG_FB=y -CONFIG_FB_CFB_FILLRECT=y -CONFIG_FB_CFB_COPYAREA=y -CONFIG_FB_CFB_IMAGEBLIT=y -CONFIG_FB_SOFT_CURSOR=y -# CONFIG_FB_MACMODES is not set -CONFIG_FB_MODE_HELPERS=y -# CONFIG_FB_TILEBLITTING is not set -# CONFIG_FB_CIRRUS is not set -# CONFIG_FB_PM2 is not set -# CONFIG_FB_CYBER2000 is not set -# CONFIG_FB_ASILIANT is not set -# CONFIG_FB_IMSTT is not set -# CONFIG_FB_NVIDIA is not set -# CONFIG_FB_RIVA is not set -# CONFIG_FB_MATROX is not set -# CONFIG_FB_RADEON_OLD is not set -CONFIG_FB_RADEON=y -CONFIG_FB_RADEON_I2C=y -CONFIG_FB_RADEON_DEBUG=y -# CONFIG_FB_ATY128 is not set -# CONFIG_FB_ATY is not set -# CONFIG_FB_SAVAGE is not set -# CONFIG_FB_SIS is not set -# CONFIG_FB_NEOMAGIC is not set -# CONFIG_FB_KYRO is not set -# CONFIG_FB_3DFX is not set -# CONFIG_FB_VOODOO1 is not set -# CONFIG_FB_TRIDENT is not set -# CONFIG_FB_PM3 is not set -# CONFIG_FB_S1D13XXX is not set -# CONFIG_FB_VIRTUAL is not set - -# -# Logo configuration -# -CONFIG_LOGO=y -# CONFIG_LOGO_LINUX_MONO is not set -# CONFIG_LOGO_LINUX_VGA16 is not set -CONFIG_LOGO_LINUX_CLUT224=y -# CONFIG_BACKLIGHT_LCD_SUPPORT is not set - -# -# Sound -# -CONFIG_SOUND=y - -# -# Advanced Linux Sound Architecture -# -CONFIG_SND=y -CONFIG_SND_TIMER=y -CONFIG_SND_PCM=y -CONFIG_SND_HWDEP=y -CONFIG_SND_RAWMIDI=y -CONFIG_SND_SEQUENCER=y -# CONFIG_SND_SEQ_DUMMY is not set -CONFIG_SND_OSSEMUL=y -CONFIG_SND_MIXER_OSS=y -CONFIG_SND_PCM_OSS=y -CONFIG_SND_SEQUENCER_OSS=y -# CONFIG_SND_VERBOSE_PRINTK is not set -# CONFIG_SND_DEBUG is not set - -# -# Generic devices -# -CONFIG_SND_MPU401_UART=y -CONFIG_SND_OPL3_LIB=y -# CONFIG_SND_DUMMY is not set -# CONFIG_SND_VIRMIDI is not set -# CONFIG_SND_MTPAV is not set -# CONFIG_SND_SERIAL_U16550 is not set -# CONFIG_SND_MPU401 is not set - -# -# PCI devices -# -CONFIG_SND_AC97_CODEC=y -# CONFIG_SND_ALI5451 is not set -# CONFIG_SND_ATIIXP is not set -# CONFIG_SND_ATIIXP_MODEM is not set -# CONFIG_SND_AU8810 is not set -# CONFIG_SND_AU8820 is not set -# CONFIG_SND_AU8830 is not set -# CONFIG_SND_AZT3328 is not set -# CONFIG_SND_BT87X is not set -# CONFIG_SND_CS46XX is not set -# CONFIG_SND_CS4281 is not set -# CONFIG_SND_EMU10K1 is not set -# CONFIG_SND_EMU10K1X is not set -# CONFIG_SND_CA0106 is not set -# CONFIG_SND_KORG1212 is not set -# CONFIG_SND_MIXART is not set -# CONFIG_SND_NM256 is not set -# CONFIG_SND_RME32 is not set -# CONFIG_SND_RME96 is not set -# CONFIG_SND_RME9652 is not set -# CONFIG_SND_HDSP is not set -# CONFIG_SND_TRIDENT is not set -# CONFIG_SND_YMFPCI is not set -# CONFIG_SND_ALS4000 is not set -# CONFIG_SND_CMIPCI is not set -# CONFIG_SND_ENS1370 is not set -# CONFIG_SND_ENS1371 is not set -# CONFIG_SND_ES1938 is not set -# CONFIG_SND_ES1968 is not set -# CONFIG_SND_MAESTRO3 is not set -CONFIG_SND_FM801=y -CONFIG_SND_FM801_TEA575X=y -# CONFIG_SND_ICE1712 is not set -# CONFIG_SND_ICE1724 is not set -# CONFIG_SND_INTEL8X0 is not set -# CONFIG_SND_INTEL8X0M is not set -# CONFIG_SND_SONICVIBES is not set -# CONFIG_SND_VIA82XX is not set -# CONFIG_SND_VIA82XX_MODEM is not set -# CONFIG_SND_VX222 is not set -# CONFIG_SND_HDA_INTEL is not set - -# -# USB devices -# -# CONFIG_SND_USB_AUDIO is not set - -# -# Open Sound System -# -# CONFIG_SOUND_PRIME is not set - -# -# USB support -# -CONFIG_USB_ARCH_HAS_HCD=y -CONFIG_USB_ARCH_HAS_OHCI=y -CONFIG_USB=y -# CONFIG_USB_DEBUG is not set - -# -# Miscellaneous USB options -# -# CONFIG_USB_DEVICEFS is not set -CONFIG_USB_BANDWIDTH=y -# CONFIG_USB_DYNAMIC_MINORS is not set -# CONFIG_USB_SUSPEND is not set -# CONFIG_USB_OTG is not set - -# -# USB Host Controller Drivers -# -CONFIG_USB_EHCI_HCD=y -# CONFIG_USB_EHCI_SPLIT_ISO is not set -# CONFIG_USB_EHCI_ROOT_HUB_TT is not set -CONFIG_USB_OHCI_HCD=y -# CONFIG_USB_OHCI_BIG_ENDIAN is not set -CONFIG_USB_OHCI_LITTLE_ENDIAN=y -CONFIG_USB_UHCI_HCD=y -# CONFIG_USB_SL811_HCD is not set - -# -# USB Device Class drivers -# -# CONFIG_USB_AUDIO is not set -# CONFIG_USB_BLUETOOTH_TTY is not set -# CONFIG_USB_MIDI is not set -# CONFIG_USB_ACM is not set -# CONFIG_USB_PRINTER is not set - -# -# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed; see USB_STORAGE Help for more information -# -CONFIG_USB_STORAGE=y -# CONFIG_USB_STORAGE_DEBUG is not set -# CONFIG_USB_STORAGE_DATAFAB is not set -# CONFIG_USB_STORAGE_FREECOM is not set -# CONFIG_USB_STORAGE_DPCM is not set -# CONFIG_USB_STORAGE_USBAT is not set -# CONFIG_USB_STORAGE_SDDR09 is not set -# CONFIG_USB_STORAGE_SDDR55 is not set -# CONFIG_USB_STORAGE_JUMPSHOT is not set - -# -# USB Input Devices -# -CONFIG_USB_HID=y -CONFIG_USB_HIDINPUT=y -# CONFIG_HID_FF is not set -CONFIG_USB_HIDDEV=y -# CONFIG_USB_AIPTEK is not set -# CONFIG_USB_WACOM is not set -# CONFIG_USB_KBTAB is not set -# CONFIG_USB_POWERMATE is not set -# CONFIG_USB_MTOUCH is not set -# CONFIG_USB_EGALAX is not set -# CONFIG_USB_XPAD is not set -# CONFIG_USB_ATI_REMOTE is not set - -# -# USB Imaging devices -# -# CONFIG_USB_MDC800 is not set -# CONFIG_USB_MICROTEK is not set - -# -# USB Multimedia devices -# -# CONFIG_USB_DABUSB is not set -# CONFIG_USB_VICAM is not set -# CONFIG_USB_DSBR is not set -# CONFIG_USB_IBMCAM is not set -# CONFIG_USB_KONICAWC is not set -# CONFIG_USB_OV511 is not set -# CONFIG_USB_SE401 is not set -# CONFIG_USB_SN9C102 is not set -# CONFIG_USB_STV680 is not set -# CONFIG_USB_PWC is not set - -# -# USB Network Adapters -# -# CONFIG_USB_CATC is not set -# CONFIG_USB_KAWETH is not set -# CONFIG_USB_PEGASUS is not set -# CONFIG_USB_RTL8150 is not set -# CONFIG_USB_USBNET is not set -CONFIG_USB_MON=y - -# -# USB port drivers -# - -# -# USB Serial Converter support -# -# CONFIG_USB_SERIAL is not set - -# -# USB Miscellaneous drivers -# -# CONFIG_USB_EMI62 is not set -# CONFIG_USB_EMI26 is not set -# CONFIG_USB_AUERSWALD is not set -# CONFIG_USB_RIO500 is not set -# CONFIG_USB_LEGOTOWER is not set -# CONFIG_USB_LCD is not set -# CONFIG_USB_LED is not set -# CONFIG_USB_CYTHERM is not set -# CONFIG_USB_PHIDGETKIT is not set -# CONFIG_USB_PHIDGETSERVO is not set -# CONFIG_USB_IDMOUSE is not set -# CONFIG_USB_SISUSBVGA is not set - -# -# USB ATM/DSL drivers -# - -# -# USB Gadget Support -# -# CONFIG_USB_GADGET is not set - -# -# MMC/SD Card support -# -# CONFIG_MMC is not set - -# -# InfiniBand support -# -# CONFIG_INFINIBAND is not set - -# -# File systems -# -CONFIG_EXT2_FS=y -CONFIG_EXT2_FS_XATTR=y -# CONFIG_EXT2_FS_POSIX_ACL is not set -# CONFIG_EXT2_FS_SECURITY is not set -CONFIG_EXT3_FS=y -CONFIG_EXT3_FS_XATTR=y -# CONFIG_EXT3_FS_POSIX_ACL is not set -# CONFIG_EXT3_FS_SECURITY is not set -CONFIG_JBD=y -# CONFIG_JBD_DEBUG is not set -CONFIG_FS_MBCACHE=y -# CONFIG_REISERFS_FS is not set -# CONFIG_JFS_FS is not set - -# -# XFS support -# -# CONFIG_XFS_FS is not set -# CONFIG_MINIX_FS is not set -# CONFIG_ROMFS_FS is not set -# CONFIG_QUOTA is not set -CONFIG_DNOTIFY=y -CONFIG_AUTOFS_FS=y -# CONFIG_AUTOFS4_FS is not set - -# -# CD-ROM/DVD Filesystems -# -CONFIG_ISO9660_FS=y -CONFIG_JOLIET=y -# CONFIG_ZISOFS is not set -CONFIG_UDF_FS=y -CONFIG_UDF_NLS=y - -# -# DOS/FAT/NT Filesystems -# -CONFIG_FAT_FS=y -CONFIG_MSDOS_FS=y -CONFIG_VFAT_FS=y -CONFIG_FAT_DEFAULT_CODEPAGE=437 -CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" -# CONFIG_NTFS_FS is not set - -# -# Pseudo filesystems -# -CONFIG_PROC_FS=y -CONFIG_PROC_KCORE=y -CONFIG_SYSFS=y -# CONFIG_DEVFS_FS is not set -# CONFIG_DEVPTS_FS_XATTR is not set -CONFIG_TMPFS=y -CONFIG_TMPFS_XATTR=y -CONFIG_TMPFS_SECURITY=y -CONFIG_HUGETLBFS=y -CONFIG_HUGETLB_PAGE=y -CONFIG_RAMFS=y - -# -# Miscellaneous filesystems -# -# CONFIG_ADFS_FS is not set -# CONFIG_AFFS_FS is not set -# CONFIG_HFS_FS is not set -# CONFIG_HFSPLUS_FS is not set -# CONFIG_BEFS_FS is not set -# CONFIG_BFS_FS is not set -# CONFIG_EFS_FS is not set -# CONFIG_CRAMFS is not set -# CONFIG_VXFS_FS is not set -# CONFIG_HPFS_FS is not set -# CONFIG_QNX4FS_FS is not set -# CONFIG_SYSV_FS is not set -# CONFIG_UFS_FS is not set - -# -# Network File Systems -# -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -CONFIG_NFS_V4=y -# CONFIG_NFS_DIRECTIO is not set -CONFIG_NFSD=y -CONFIG_NFSD_V3=y -# CONFIG_NFSD_V4 is not set -# CONFIG_NFSD_TCP is not set -CONFIG_LOCKD=y -CONFIG_LOCKD_V4=y -CONFIG_EXPORTFS=y -CONFIG_SUNRPC=y -CONFIG_SUNRPC_GSS=y -CONFIG_RPCSEC_GSS_KRB5=y -# CONFIG_RPCSEC_GSS_SPKM3 is not set -# CONFIG_SMB_FS is not set -# CONFIG_CIFS is not set -# CONFIG_NCP_FS is not set -# CONFIG_CODA_FS is not set -# CONFIG_AFS_FS is not set - -# -# Partition Types -# -CONFIG_PARTITION_ADVANCED=y -# CONFIG_ACORN_PARTITION is not set -# CONFIG_OSF_PARTITION is not set -# CONFIG_AMIGA_PARTITION is not set -# CONFIG_ATARI_PARTITION is not set -# CONFIG_MAC_PARTITION is not set -CONFIG_MSDOS_PARTITION=y -# CONFIG_BSD_DISKLABEL is not set -# CONFIG_MINIX_SUBPARTITION is not set -# CONFIG_SOLARIS_X86_PARTITION is not set -# CONFIG_UNIXWARE_DISKLABEL is not set -# CONFIG_LDM_PARTITION is not set -# CONFIG_SGI_PARTITION is not set -# CONFIG_ULTRIX_PARTITION is not set -# CONFIG_SUN_PARTITION is not set -CONFIG_EFI_PARTITION=y - -# -# Native Language Support -# -CONFIG_NLS=y -CONFIG_NLS_DEFAULT="iso8859-1" -CONFIG_NLS_CODEPAGE_437=y -CONFIG_NLS_CODEPAGE_737=y -CONFIG_NLS_CODEPAGE_775=y -CONFIG_NLS_CODEPAGE_850=y -CONFIG_NLS_CODEPAGE_852=y -CONFIG_NLS_CODEPAGE_855=y -CONFIG_NLS_CODEPAGE_857=y -CONFIG_NLS_CODEPAGE_860=y -CONFIG_NLS_CODEPAGE_861=y -CONFIG_NLS_CODEPAGE_862=y -CONFIG_NLS_CODEPAGE_863=y -CONFIG_NLS_CODEPAGE_864=y -CONFIG_NLS_CODEPAGE_865=y -CONFIG_NLS_CODEPAGE_866=y -CONFIG_NLS_CODEPAGE_869=y -CONFIG_NLS_CODEPAGE_936=y -CONFIG_NLS_CODEPAGE_950=y -CONFIG_NLS_CODEPAGE_932=y -CONFIG_NLS_CODEPAGE_949=y -CONFIG_NLS_CODEPAGE_874=y -CONFIG_NLS_ISO8859_8=y -# CONFIG_NLS_CODEPAGE_1250 is not set -CONFIG_NLS_CODEPAGE_1251=y -# CONFIG_NLS_ASCII is not set -CONFIG_NLS_ISO8859_1=y -CONFIG_NLS_ISO8859_2=y -CONFIG_NLS_ISO8859_3=y -CONFIG_NLS_ISO8859_4=y -CONFIG_NLS_ISO8859_5=y -CONFIG_NLS_ISO8859_6=y -CONFIG_NLS_ISO8859_7=y -CONFIG_NLS_ISO8859_9=y -CONFIG_NLS_ISO8859_13=y -CONFIG_NLS_ISO8859_14=y -CONFIG_NLS_ISO8859_15=y -CONFIG_NLS_KOI8_R=y -CONFIG_NLS_KOI8_U=y -CONFIG_NLS_UTF8=y - -# -# Library routines -# -# CONFIG_CRC_CCITT is not set -CONFIG_CRC32=y -# CONFIG_LIBCRC32C is not set -CONFIG_GENERIC_HARDIRQS=y -CONFIG_GENERIC_IRQ_PROBE=y - -# -# Profiling support -# -# CONFIG_PROFILING is not set - -# -# Kernel hacking -# -# CONFIG_PRINTK_TIME is not set -CONFIG_DEBUG_KERNEL=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_LOG_BUF_SHIFT=17 -# CONFIG_SCHEDSTATS is not set -# CONFIG_DEBUG_SLAB is not set -# CONFIG_DEBUG_SPINLOCK is not set -# CONFIG_DEBUG_SPINLOCK_SLEEP is not set -# CONFIG_DEBUG_KOBJECT is not set -# CONFIG_DEBUG_INFO is not set -# CONFIG_DEBUG_FS is not set -CONFIG_IA64_GRANULE_16MB=y -# CONFIG_IA64_GRANULE_64MB is not set -CONFIG_IA64_PRINT_HAZARDS=y -# CONFIG_DISABLE_VHPT is not set -# CONFIG_IA64_DEBUG_CMPXCHG is not set -# CONFIG_IA64_DEBUG_IRQ is not set - -# -# Security options -# -# CONFIG_KEYS is not set -# CONFIG_SECURITY is not set - -# -# Cryptographic options -# -CONFIG_CRYPTO=y -# CONFIG_CRYPTO_HMAC is not set -# CONFIG_CRYPTO_NULL is not set -# CONFIG_CRYPTO_MD4 is not set -CONFIG_CRYPTO_MD5=y -# CONFIG_CRYPTO_SHA1 is not set -# CONFIG_CRYPTO_SHA256 is not set -# CONFIG_CRYPTO_SHA512 is not set -# CONFIG_CRYPTO_WP512 is not set -# CONFIG_CRYPTO_TGR192 is not set -CONFIG_CRYPTO_DES=y -# CONFIG_CRYPTO_BLOWFISH is not set -# CONFIG_CRYPTO_TWOFISH is not set -# CONFIG_CRYPTO_SERPENT is not set -# CONFIG_CRYPTO_AES is not set -# CONFIG_CRYPTO_CAST5 is not set -# CONFIG_CRYPTO_CAST6 is not set -# CONFIG_CRYPTO_TEA is not set -# CONFIG_CRYPTO_ARC4 is not set -# CONFIG_CRYPTO_KHAZAD is not set -# CONFIG_CRYPTO_ANUBIS is not set -# CONFIG_CRYPTO_DEFLATE is not set -# CONFIG_CRYPTO_MICHAEL_MIC is not set -# CONFIG_CRYPTO_CRC32C is not set -# CONFIG_CRYPTO_TEST is not set - -# -# Hardware crypto devices -# diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/configs/xenU_defconfig_x86_32 --- a/linux-2.6-xen-sparse/arch/xen/configs/xenU_defconfig_x86_32 Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,562 +0,0 @@ -# -# Automatically generated make config: don't edit -# Linux kernel version: 2.6.12-xenU -# Wed Aug 3 09:57:44 2005 -# -CONFIG_XEN=y -CONFIG_ARCH_XEN=y -CONFIG_NO_IDLE_HZ=y - -# -# XEN -# -# CONFIG_XEN_PRIVILEGED_GUEST is not set -# CONFIG_XEN_PHYSDEV_ACCESS is not set -# CONFIG_XEN_TPMDEV_FRONTEND is not set -# CONFIG_XEN_TPMDEV_BACKEND is not set -CONFIG_XEN_BLKDEV_FRONTEND=y -CONFIG_XEN_NETDEV_FRONTEND=y -# CONFIG_XEN_BLKDEV_TAP is not set -# CONFIG_XEN_SHADOW_MODE is not set -CONFIG_XEN_SCRUB_PAGES=y -CONFIG_XEN_X86=y -# CONFIG_XEN_X86_64 is not set -CONFIG_HAVE_ARCH_ALLOC_SKB=y -CONFIG_HAVE_ARCH_DEV_ALLOC_SKB=y - -# -# Code maturity level options -# -CONFIG_EXPERIMENTAL=y -CONFIG_CLEAN_COMPILE=y -CONFIG_LOCK_KERNEL=y -CONFIG_INIT_ENV_ARG_LIMIT=32 - -# -# General setup -# -CONFIG_LOCALVERSION="" -CONFIG_SWAP=y -CONFIG_SYSVIPC=y -# CONFIG_POSIX_MQUEUE is not set -# CONFIG_BSD_PROCESS_ACCT is not set -CONFIG_SYSCTL=y -# CONFIG_AUDIT is not set -CONFIG_HOTPLUG=y -CONFIG_KOBJECT_UEVENT=y -# CONFIG_IKCONFIG is not set -# CONFIG_CPUSETS is not set -# CONFIG_EMBEDDED is not set -CONFIG_KALLSYMS=y -# CONFIG_KALLSYMS_ALL is not set -# CONFIG_KALLSYMS_EXTRA_PASS is not set -CONFIG_PRINTK=y -CONFIG_BUG=y -CONFIG_BASE_FULL=y -CONFIG_FUTEX=y -CONFIG_EPOLL=y -CONFIG_SHMEM=y -CONFIG_CC_ALIGN_FUNCTIONS=0 -CONFIG_CC_ALIGN_LABELS=0 -CONFIG_CC_ALIGN_LOOPS=0 -CONFIG_CC_ALIGN_JUMPS=0 -# CONFIG_TINY_SHMEM is not set -CONFIG_BASE_SMALL=0 - -# -# Loadable module support -# -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_MODULE_FORCE_UNLOAD is not set -CONFIG_OBSOLETE_MODPARM=y -# CONFIG_MODVERSIONS is not set -# CONFIG_MODULE_SRCVERSION_ALL is not set -CONFIG_KMOD=y -CONFIG_STOP_MACHINE=y - -# -# X86 Processor Configuration -# -CONFIG_XENARCH="i386" -CONFIG_X86=y -CONFIG_MMU=y -CONFIG_UID16=y -CONFIG_GENERIC_ISA_DMA=y -CONFIG_GENERIC_IOMAP=y -# CONFIG_M386 is not set -# CONFIG_M486 is not set -# CONFIG_M586 is not set -# CONFIG_M586TSC is not set -# CONFIG_M586MMX is not set -CONFIG_M686=y -# CONFIG_MPENTIUMII is not set -# CONFIG_MPENTIUMIII is not set -# CONFIG_MPENTIUMM is not set -# CONFIG_MPENTIUM4 is not set -# CONFIG_MK6 is not set -# CONFIG_MK7 is not set -# CONFIG_MK8 is not set -# CONFIG_MCRUSOE is not set -# CONFIG_MEFFICEON is not set -# CONFIG_MWINCHIPC6 is not set -# CONFIG_MWINCHIP2 is not set -# CONFIG_MWINCHIP3D is not set -# CONFIG_MGEODEGX1 is not set -# CONFIG_MCYRIXIII is not set -# CONFIG_MVIAC3_2 is not set -# CONFIG_X86_GENERIC is not set -CONFIG_X86_CMPXCHG=y -CONFIG_X86_XADD=y -CONFIG_X86_L1_CACHE_SHIFT=5 -CONFIG_RWSEM_XCHGADD_ALGORITHM=y -CONFIG_GENERIC_CALIBRATE_DELAY=y -CONFIG_X86_PPRO_FENCE=y -CONFIG_X86_WP_WORKS_OK=y -CONFIG_X86_INVLPG=y -CONFIG_X86_BSWAP=y -CONFIG_X86_POPAD_OK=y -CONFIG_X86_GOOD_APIC=y -CONFIG_X86_USE_PPRO_CHECKSUM=y -# CONFIG_HPET_TIMER is not set -# CONFIG_HPET_EMULATE_RTC is not set -CONFIG_SMP=y -CONFIG_SMP_ALTERNATIVES=y -CONFIG_NR_CPUS=8 -# CONFIG_SCHED_SMT is not set -# CONFIG_X86_REBOOTFIXUPS is not set -CONFIG_X86_CPUID=y - -# -# Firmware Drivers -# -# CONFIG_EDD is not set -# CONFIG_NOHIGHMEM is not set -CONFIG_HIGHMEM4G=y -# CONFIG_HIGHMEM64G is not set -CONFIG_HIGHMEM=y -CONFIG_HAVE_DEC_LOCK=y -# CONFIG_REGPARM is not set -CONFIG_HOTPLUG_CPU=y -CONFIG_GENERIC_HARDIRQS=y -CONFIG_GENERIC_IRQ_PROBE=y -CONFIG_X86_SMP=y -CONFIG_X86_BIOS_REBOOT=y -CONFIG_X86_TRAMPOLINE=y -CONFIG_PC=y -CONFIG_SECCOMP=y -CONFIG_EARLY_PRINTK=y - -# -# Executable file formats -# -CONFIG_BINFMT_ELF=y -# CONFIG_BINFMT_AOUT is not set -# CONFIG_BINFMT_MISC is not set - -# -# Device Drivers -# - -# -# Generic Driver Options -# -CONFIG_STANDALONE=y -CONFIG_PREVENT_FIRMWARE_BUILD=y -# CONFIG_FW_LOADER is not set -# CONFIG_DEBUG_DRIVER is not set - -# -# Block devices -# -# CONFIG_BLK_DEV_FD is not set -# CONFIG_BLK_DEV_COW_COMMON is not set -CONFIG_BLK_DEV_LOOP=m -# CONFIG_BLK_DEV_CRYPTOLOOP is not set -CONFIG_BLK_DEV_NBD=m -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_COUNT=16 -CONFIG_BLK_DEV_RAM_SIZE=4096 -CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="" -# CONFIG_LBD is not set -# CONFIG_CDROM_PKTCDVD is not set - -# -# IO Schedulers -# -CONFIG_IOSCHED_NOOP=y -CONFIG_IOSCHED_AS=y -CONFIG_IOSCHED_DEADLINE=y -CONFIG_IOSCHED_CFQ=y -# CONFIG_ATA_OVER_ETH is not set - -# -# SCSI device support -# -CONFIG_SCSI=m -CONFIG_SCSI_PROC_FS=y - -# -# SCSI support type (disk, tape, CD-ROM) -# -CONFIG_BLK_DEV_SD=m -# CONFIG_CHR_DEV_ST is not set -# CONFIG_CHR_DEV_OSST is not set -# CONFIG_BLK_DEV_SR is not set -# CONFIG_CHR_DEV_SG is not set - -# -# Some SCSI devices (e.g. CD jukebox) support multiple LUNs -# -# CONFIG_SCSI_MULTI_LUN is not set -# CONFIG_SCSI_CONSTANTS is not set -# CONFIG_SCSI_LOGGING is not set - -# -# SCSI Transport Attributes -# -# CONFIG_SCSI_SPI_ATTRS is not set -# CONFIG_SCSI_FC_ATTRS is not set -# CONFIG_SCSI_ISCSI_ATTRS is not set - -# -# SCSI low-level drivers -# -# CONFIG_SCSI_SATA is not set -# CONFIG_SCSI_DEBUG is not set - -# -# Multi-device support (RAID and LVM) -# -# CONFIG_MD is not set - -# -# Networking support -# -CONFIG_NET=y - -# -# Networking options -# -CONFIG_PACKET=y -# CONFIG_PACKET_MMAP is not set -CONFIG_UNIX=y -# CONFIG_NET_KEY is not set -CONFIG_INET=y -# CONFIG_IP_MULTICAST is not set -# CONFIG_IP_ADVANCED_ROUTER is not set -CONFIG_IP_PNP=y -# CONFIG_IP_PNP_DHCP is not set -# CONFIG_IP_PNP_BOOTP is not set -# CONFIG_IP_PNP_RARP is not set -# CONFIG_NET_IPIP is not set -# CONFIG_NET_IPGRE is not set -# CONFIG_ARPD is not set -# CONFIG_SYN_COOKIES is not set -# CONFIG_INET_AH is not set -# CONFIG_INET_ESP is not set -# CONFIG_INET_IPCOMP is not set -# CONFIG_INET_TUNNEL is not set -CONFIG_IP_TCPDIAG=y -# CONFIG_IP_TCPDIAG_IPV6 is not set -# CONFIG_IPV6 is not set -# CONFIG_NETFILTER is not set - -# -# SCTP Configuration (EXPERIMENTAL) -# -# CONFIG_IP_SCTP is not set -# CONFIG_ATM is not set -# CONFIG_BRIDGE is not set -# CONFIG_VLAN_8021Q is not set -# CONFIG_DECNET is not set -# CONFIG_LLC2 is not set -# CONFIG_IPX is not set -# CONFIG_ATALK is not set -# CONFIG_X25 is not set -# CONFIG_LAPB is not set -# CONFIG_NET_DIVERT is not set -# CONFIG_ECONET is not set -# CONFIG_WAN_ROUTER is not set - -# -# QoS and/or fair queueing -# -# CONFIG_NET_SCHED is not set -# CONFIG_NET_CLS_ROUTE is not set - -# -# Network testing -# -# CONFIG_NET_PKTGEN is not set -# CONFIG_NETPOLL is not set -# CONFIG_NET_POLL_CONTROLLER is not set -# CONFIG_HAMRADIO is not set -# CONFIG_IRDA is not set -# CONFIG_BT is not set -CONFIG_NETDEVICES=y -# CONFIG_DUMMY is not set -# CONFIG_BONDING is not set -# CONFIG_EQUALIZER is not set -# CONFIG_TUN is not set - -# -# Ethernet (10 or 100Mbit) -# -# CONFIG_NET_ETHERNET is not set - -# -# Ethernet (1000 Mbit) -# - -# -# Ethernet (10000 Mbit) -# - -# -# Token Ring devices -# - -# -# Wireless LAN (non-hamradio) -# -# CONFIG_NET_RADIO is not set - -# -# Wan interfaces -# -# CONFIG_WAN is not set -# CONFIG_PPP is not set -# CONFIG_SLIP is not set -# CONFIG_SHAPER is not set -# CONFIG_NETCONSOLE is not set -CONFIG_UNIX98_PTYS=y -CONFIG_LEGACY_PTYS=y -CONFIG_LEGACY_PTY_COUNT=256 -# CONFIG_TCG_TPM is not set - -# -# Character devices -# - -# -# File systems -# -CONFIG_EXT2_FS=y -# CONFIG_EXT2_FS_XATTR is not set -CONFIG_EXT3_FS=y -CONFIG_EXT3_FS_XATTR=y -# CONFIG_EXT3_FS_POSIX_ACL is not set -# CONFIG_EXT3_FS_SECURITY is not set -CONFIG_JBD=y -# CONFIG_JBD_DEBUG is not set -CONFIG_FS_MBCACHE=y -CONFIG_REISERFS_FS=y -# CONFIG_REISERFS_CHECK is not set -# CONFIG_REISERFS_PROC_INFO is not set -# CONFIG_REISERFS_FS_XATTR is not set -# CONFIG_JFS_FS is not set - -# -# XFS support -# -# CONFIG_XFS_FS is not set -# CONFIG_MINIX_FS is not set -# CONFIG_ROMFS_FS is not set -# CONFIG_QUOTA is not set -CONFIG_DNOTIFY=y -CONFIG_AUTOFS_FS=y -CONFIG_AUTOFS4_FS=y - -# -# CD-ROM/DVD Filesystems -# -CONFIG_ISO9660_FS=y -CONFIG_JOLIET=y -CONFIG_ZISOFS=y -CONFIG_ZISOFS_FS=y -# CONFIG_UDF_FS is not set - -# -# DOS/FAT/NT Filesystems -# -CONFIG_FAT_FS=m -CONFIG_MSDOS_FS=m -CONFIG_VFAT_FS=m -CONFIG_FAT_DEFAULT_CODEPAGE=437 -CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" -# CONFIG_NTFS_FS is not set - -# -# Pseudo filesystems -# -CONFIG_PROC_FS=y -CONFIG_PROC_KCORE=y -CONFIG_SYSFS=y -# CONFIG_DEVFS_FS is not set -CONFIG_DEVPTS_FS_XATTR=y -# CONFIG_DEVPTS_FS_SECURITY is not set -CONFIG_TMPFS=y -# CONFIG_TMPFS_XATTR is not set -# CONFIG_HUGETLBFS is not set -# CONFIG_HUGETLB_PAGE is not set -CONFIG_RAMFS=y - -# -# Miscellaneous filesystems -# -# CONFIG_ADFS_FS is not set -# CONFIG_AFFS_FS is not set -# CONFIG_HFS_FS is not set -# CONFIG_HFSPLUS_FS is not set -# CONFIG_BEFS_FS is not set -# CONFIG_BFS_FS is not set -# CONFIG_EFS_FS is not set -CONFIG_CRAMFS=y -# CONFIG_VXFS_FS is not set -# CONFIG_HPFS_FS is not set -# CONFIG_QNX4FS_FS is not set -# CONFIG_SYSV_FS is not set -# CONFIG_UFS_FS is not set - -# -# Network File Systems -# -CONFIG_NFS_FS=y -CONFIG_NFS_V3=y -# CONFIG_NFS_V4 is not set -# CONFIG_NFS_DIRECTIO is not set -# CONFIG_NFSD is not set -CONFIG_ROOT_NFS=y -CONFIG_LOCKD=y -CONFIG_LOCKD_V4=y -CONFIG_SUNRPC=y -# CONFIG_RPCSEC_GSS_KRB5 is not set -# CONFIG_RPCSEC_GSS_SPKM3 is not set -# CONFIG_SMB_FS is not set -# CONFIG_CIFS is not set -# CONFIG_NCP_FS is not set -# CONFIG_CODA_FS is not set -# CONFIG_AFS_FS is not set - -# -# Partition Types -# -# CONFIG_PARTITION_ADVANCED is not set -CONFIG_MSDOS_PARTITION=y - -# -# Native Language Support -# -CONFIG_NLS=y -CONFIG_NLS_DEFAULT="iso8859-1" -CONFIG_NLS_CODEPAGE_437=y -# CONFIG_NLS_CODEPAGE_737 is not set -# CONFIG_NLS_CODEPAGE_775 is not set -# CONFIG_NLS_CODEPAGE_850 is not set -# CONFIG_NLS_CODEPAGE_852 is not set -# CONFIG_NLS_CODEPAGE_855 is not set -# CONFIG_NLS_CODEPAGE_857 is not set -# CONFIG_NLS_CODEPAGE_860 is not set -# CONFIG_NLS_CODEPAGE_861 is not set -# CONFIG_NLS_CODEPAGE_862 is not set -# CONFIG_NLS_CODEPAGE_863 is not set -# CONFIG_NLS_CODEPAGE_864 is not set -# CONFIG_NLS_CODEPAGE_865 is not set -# CONFIG_NLS_CODEPAGE_866 is not set -# CONFIG_NLS_CODEPAGE_869 is not set -# CONFIG_NLS_CODEPAGE_936 is not set -# CONFIG_NLS_CODEPAGE_950 is not set -# CONFIG_NLS_CODEPAGE_932 is not set -# CONFIG_NLS_CODEPAGE_949 is not set -# CONFIG_NLS_CODEPAGE_874 is not set -# CONFIG_NLS_ISO8859_8 is not set -# CONFIG_NLS_CODEPAGE_1250 is not set -# CONFIG_NLS_CODEPAGE_1251 is not set -# CONFIG_NLS_ASCII is not set -CONFIG_NLS_ISO8859_1=y -# CONFIG_NLS_ISO8859_2 is not set -# CONFIG_NLS_ISO8859_3 is not set -# CONFIG_NLS_ISO8859_4 is not set -# CONFIG_NLS_ISO8859_5 is not set -# CONFIG_NLS_ISO8859_6 is not set -# CONFIG_NLS_ISO8859_7 is not set -# CONFIG_NLS_ISO8859_9 is not set -# CONFIG_NLS_ISO8859_13 is not set -# CONFIG_NLS_ISO8859_14 is not set -# CONFIG_NLS_ISO8859_15 is not set -# CONFIG_NLS_KOI8_R is not set -# CONFIG_NLS_KOI8_U is not set -# CONFIG_NLS_UTF8 is not set - -# -# Security options -# -# CONFIG_KEYS is not set -# CONFIG_SECURITY is not set - -# -# Cryptographic options -# -CONFIG_CRYPTO=y -# CONFIG_CRYPTO_HMAC is not set -# CONFIG_CRYPTO_NULL is not set -# CONFIG_CRYPTO_MD4 is not set -CONFIG_CRYPTO_MD5=m -# CONFIG_CRYPTO_SHA1 is not set -# CONFIG_CRYPTO_SHA256 is not set -# CONFIG_CRYPTO_SHA512 is not set -# CONFIG_CRYPTO_WP512 is not set -# CONFIG_CRYPTO_TGR192 is not set -# CONFIG_CRYPTO_DES is not set -# CONFIG_CRYPTO_BLOWFISH is not set -# CONFIG_CRYPTO_TWOFISH is not set -# CONFIG_CRYPTO_SERPENT is not set -# CONFIG_CRYPTO_AES_586 is not set -# CONFIG_CRYPTO_CAST5 is not set -# CONFIG_CRYPTO_CAST6 is not set -# CONFIG_CRYPTO_TEA is not set -# CONFIG_CRYPTO_ARC4 is not set -# CONFIG_CRYPTO_KHAZAD is not set -# CONFIG_CRYPTO_ANUBIS is not set -# CONFIG_CRYPTO_DEFLATE is not set -# CONFIG_CRYPTO_MICHAEL_MIC is not set -CONFIG_CRYPTO_CRC32C=m -# CONFIG_CRYPTO_TEST is not set - -# -# Hardware crypto devices -# -# CONFIG_CRYPTO_DEV_PADLOCK is not set - -# -# Library routines -# -# CONFIG_CRC_CCITT is not set -# CONFIG_CRC32 is not set -CONFIG_LIBCRC32C=m -CONFIG_ZLIB_INFLATE=y - -# -# Kernel hacking -# -# CONFIG_PRINTK_TIME is not set -CONFIG_DEBUG_KERNEL=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_SCHEDSTATS is not set -# CONFIG_DEBUG_SLAB is not set -# CONFIG_DEBUG_SPINLOCK is not set -# CONFIG_DEBUG_SPINLOCK_SLEEP is not set -# CONFIG_DEBUG_KOBJECT is not set -# CONFIG_DEBUG_HIGHMEM is not set -CONFIG_DEBUG_BUGVERBOSE=y -# CONFIG_DEBUG_INFO is not set -# CONFIG_DEBUG_FS is not set -# CONFIG_FRAME_POINTER is not set -# CONFIG_DEBUG_STACKOVERFLOW is not set -# CONFIG_KPROBES is not set -# CONFIG_DEBUG_STACK_USAGE is not set -# CONFIG_DEBUG_PAGEALLOC is not set -# CONFIG_4KSTACKS is not set diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/configs/xenU_defconfig_x86_64 --- a/linux-2.6-xen-sparse/arch/xen/configs/xenU_defconfig_x86_64 Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,939 +0,0 @@ -# -# Automatically generated make config: don't edit -# Linux kernel version: 2.6.12-xenU -# Thu Aug 18 11:15:14 2005 -# -CONFIG_XEN=y -CONFIG_ARCH_XEN=y -CONFIG_NO_IDLE_HZ=y - -# -# XEN -# -# CONFIG_XEN_PRIVILEGED_GUEST is not set -# CONFIG_XEN_PHYSDEV_ACCESS is not set -# CONFIG_XEN_TPMDEV_FRONTEND is not set -# CONFIG_XEN_TPMDEV_BACKEND is not set -CONFIG_XEN_BLKDEV_FRONTEND=y -CONFIG_XEN_NETDEV_FRONTEND=y -# CONFIG_XEN_BLKDEV_TAP is not set -# CONFIG_XEN_SHADOW_MODE is not set -CONFIG_XEN_SCRUB_PAGES=y -# CONFIG_XEN_X86 is not set -CONFIG_XEN_X86_64=y -CONFIG_HAVE_ARCH_ALLOC_SKB=y -CONFIG_HAVE_ARCH_DEV_ALLOC_SKB=y - -# -# Code maturity level options -# -CONFIG_EXPERIMENTAL=y -CONFIG_CLEAN_COMPILE=y -CONFIG_LOCK_KERNEL=y -CONFIG_INIT_ENV_ARG_LIMIT=32 - -# -# General setup -# -CONFIG_LOCALVERSION="" -CONFIG_SWAP=y -CONFIG_SYSVIPC=y -CONFIG_POSIX_MQUEUE=y -CONFIG_BSD_PROCESS_ACCT=y -# CONFIG_BSD_PROCESS_ACCT_V3 is not set -CONFIG_SYSCTL=y -CONFIG_AUDIT=y -CONFIG_AUDITSYSCALL=y -CONFIG_HOTPLUG=y -CONFIG_KOBJECT_UEVENT=y -# CONFIG_IKCONFIG is not set -# CONFIG_CPUSETS is not set -# CONFIG_EMBEDDED is not set -CONFIG_KALLSYMS=y -# CONFIG_KALLSYMS_ALL is not set -CONFIG_KALLSYMS_EXTRA_PASS=y -CONFIG_PRINTK=y -CONFIG_BUG=y -CONFIG_BASE_FULL=y -CONFIG_FUTEX=y -CONFIG_EPOLL=y -CONFIG_SHMEM=y -CONFIG_CC_ALIGN_FUNCTIONS=0 -CONFIG_CC_ALIGN_LABELS=0 -CONFIG_CC_ALIGN_LOOPS=0 -CONFIG_CC_ALIGN_JUMPS=0 -# CONFIG_TINY_SHMEM is not set -CONFIG_BASE_SMALL=0 - -# -# Loadable module support -# -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_MODULE_FORCE_UNLOAD is not set -CONFIG_OBSOLETE_MODPARM=y -CONFIG_MODVERSIONS=y -# CONFIG_MODULE_SRCVERSION_ALL is not set -CONFIG_KMOD=y -CONFIG_STOP_MACHINE=y -CONFIG_XENARCH="x86_64" -CONFIG_X86=y -CONFIG_MMU=y -CONFIG_UID16=y -CONFIG_GENERIC_ISA_DMA=y -CONFIG_GENERIC_IOMAP=y -CONFIG_X86_CMPXCHG=y -CONFIG_X86_L1_CACHE_SHIFT=7 -CONFIG_RWSEM_GENERIC_SPINLOCK=y -CONFIG_GENERIC_CALIBRATE_DELAY=y -CONFIG_X86_GOOD_APIC=y -# CONFIG_HPET_TIMER is not set -CONFIG_SMP=y -CONFIG_NR_CPUS=8 -# CONFIG_SCHED_SMT is not set -# CONFIG_MICROCODE is not set -CONFIG_X86_CPUID=y -# CONFIG_NUMA is not set -# CONFIG_MTRR is not set -CONFIG_HAVE_DEC_LOCK=y -# CONFIG_X86_LOCAL_APIC is not set -# CONFIG_X86_IO_APIC is not set -# CONFIG_PCI is not set -CONFIG_ISA_DMA_API=y -CONFIG_GENERIC_HARDIRQS=y -CONFIG_GENERIC_IRQ_PROBE=y -CONFIG_SECCOMP=y - -# -# X86_64 processor configuration -# -CONFIG_X86_64=y -CONFIG_64BIT=y -CONFIG_EARLY_PRINTK=y - -# -# Processor type and features -# -CONFIG_MPSC=y -# CONFIG_GENERIC_CPU is not set -CONFIG_X86_L1_CACHE_BYTES=128 -# CONFIG_X86_TSC is not set -CONFIG_X86_XEN_GENAPIC=y -# CONFIG_X86_MSR is not set -CONFIG_X86_HT=y -# CONFIG_K8_NUMA is not set -# CONFIG_NUMA_EMU is not set -CONFIG_DUMMY_IOMMU=y -# CONFIG_X86_MCE is not set - -# -# Power management options -# -# CONFIG_PM is not set - -# -# CPU Frequency scaling -# -# CONFIG_CPU_FREQ is not set - -# -# Bus options (PCI etc.) -# -# CONFIG_UNORDERED_IO is not set - -# -# Executable file formats / Emulations -# -CONFIG_IA32_EMULATION=y -# CONFIG_IA32_AOUT is not set -CONFIG_COMPAT=y -CONFIG_SYSVIPC_COMPAT=y - -# -# Executable file formats -# -CONFIG_BINFMT_ELF=y -CONFIG_BINFMT_MISC=y - -# -# Device Drivers -# - -# -# Generic Driver Options -# -CONFIG_STANDALONE=y -CONFIG_PREVENT_FIRMWARE_BUILD=y -CONFIG_FW_LOADER=y -# CONFIG_DEBUG_DRIVER is not set - -# -# Block devices -# -CONFIG_BLK_DEV_FD=m -# CONFIG_BLK_DEV_COW_COMMON is not set -CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_CRYPTOLOOP=m -CONFIG_BLK_DEV_NBD=m -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_COUNT=16 -CONFIG_BLK_DEV_RAM_SIZE=16384 -CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="" -CONFIG_LBD=y -# CONFIG_CDROM_PKTCDVD is not set - -# -# IO Schedulers -# -CONFIG_IOSCHED_NOOP=y -CONFIG_IOSCHED_AS=y -CONFIG_IOSCHED_DEADLINE=y -CONFIG_IOSCHED_CFQ=y -# CONFIG_ATA_OVER_ETH is not set - -# -# SCSI device support -# -CONFIG_SCSI=m -CONFIG_SCSI_PROC_FS=y - -# -# SCSI support type (disk, tape, CD-ROM) -# -CONFIG_BLK_DEV_SD=m -CONFIG_CHR_DEV_ST=m -CONFIG_CHR_DEV_OSST=m -CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y -CONFIG_CHR_DEV_SG=m - -# -# Some SCSI devices (e.g. CD jukebox) support multiple LUNs -# -# CONFIG_SCSI_MULTI_LUN is not set -CONFIG_SCSI_CONSTANTS=y -CONFIG_SCSI_LOGGING=y - -# -# SCSI Transport Attributes -# -CONFIG_SCSI_SPI_ATTRS=m -CONFIG_SCSI_FC_ATTRS=m -# CONFIG_SCSI_ISCSI_ATTRS is not set - -# -# SCSI low-level drivers -# -CONFIG_SCSI_SATA=y -# CONFIG_SCSI_DEBUG is not set - -# -# Multi-device support (RAID and LVM) -# -CONFIG_MD=y -CONFIG_BLK_DEV_MD=y -CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m -CONFIG_MD_RAID1=m -CONFIG_MD_RAID10=m -CONFIG_MD_RAID5=m -CONFIG_MD_RAID6=m -CONFIG_MD_MULTIPATH=m -# CONFIG_MD_FAULTY is not set -CONFIG_BLK_DEV_DM=m -CONFIG_DM_CRYPT=m -CONFIG_DM_SNAPSHOT=m -CONFIG_DM_MIRROR=m -CONFIG_DM_ZERO=m -# CONFIG_DM_MULTIPATH is not set - -# -# Networking support -# -CONFIG_NET=y - -# -# Networking options -# -CONFIG_PACKET=y -CONFIG_PACKET_MMAP=y -CONFIG_UNIX=y -CONFIG_NET_KEY=m -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_ADVANCED_ROUTER=y -CONFIG_IP_MULTIPLE_TABLES=y -CONFIG_IP_ROUTE_FWMARK=y -CONFIG_IP_ROUTE_MULTIPATH=y -# CONFIG_IP_ROUTE_MULTIPATH_CACHED is not set -CONFIG_IP_ROUTE_VERBOSE=y -CONFIG_IP_PNP=y -CONFIG_IP_PNP_DHCP=y -CONFIG_IP_PNP_BOOTP=y -CONFIG_IP_PNP_RARP=y -CONFIG_NET_IPIP=m -CONFIG_NET_IPGRE=m -CONFIG_NET_IPGRE_BROADCAST=y -CONFIG_IP_MROUTE=y -CONFIG_IP_PIMSM_V1=y -CONFIG_IP_PIMSM_V2=y -# CONFIG_ARPD is not set -CONFIG_SYN_COOKIES=y -CONFIG_INET_AH=m -CONFIG_INET_ESP=m -CONFIG_INET_IPCOMP=m -CONFIG_INET_TUNNEL=m -CONFIG_IP_TCPDIAG=y -# CONFIG_IP_TCPDIAG_IPV6 is not set - -# -# IP: Virtual Server Configuration -# -CONFIG_IP_VS=m -# CONFIG_IP_VS_DEBUG is not set -CONFIG_IP_VS_TAB_BITS=12 - -# -# IPVS transport protocol load balancing support -# -CONFIG_IP_VS_PROTO_TCP=y -CONFIG_IP_VS_PROTO_UDP=y -CONFIG_IP_VS_PROTO_ESP=y -CONFIG_IP_VS_PROTO_AH=y - -# -# IPVS scheduler -# -CONFIG_IP_VS_RR=m -CONFIG_IP_VS_WRR=m -CONFIG_IP_VS_LC=m -CONFIG_IP_VS_WLC=m -CONFIG_IP_VS_LBLC=m -CONFIG_IP_VS_LBLCR=m -CONFIG_IP_VS_DH=m -CONFIG_IP_VS_SH=m -CONFIG_IP_VS_SED=m -CONFIG_IP_VS_NQ=m - -# -# IPVS application helper -# -CONFIG_IP_VS_FTP=m -CONFIG_IPV6=m -CONFIG_IPV6_PRIVACY=y -CONFIG_INET6_AH=m -CONFIG_INET6_ESP=m -CONFIG_INET6_IPCOMP=m -CONFIG_INET6_TUNNEL=m -CONFIG_IPV6_TUNNEL=m -CONFIG_NETFILTER=y -# CONFIG_NETFILTER_DEBUG is not set -CONFIG_BRIDGE_NETFILTER=y - -# -# IP: Netfilter Configuration -# -CONFIG_IP_NF_CONNTRACK=m -CONFIG_IP_NF_CT_ACCT=y -# CONFIG_IP_NF_CONNTRACK_MARK is not set -CONFIG_IP_NF_CT_PROTO_SCTP=m -CONFIG_IP_NF_FTP=m -CONFIG_IP_NF_IRC=m -CONFIG_IP_NF_TFTP=m -CONFIG_IP_NF_AMANDA=m -CONFIG_IP_NF_QUEUE=m -CONFIG_IP_NF_IPTABLES=m -CONFIG_IP_NF_MATCH_LIMIT=m -CONFIG_IP_NF_MATCH_IPRANGE=m -CONFIG_IP_NF_MATCH_MAC=m -CONFIG_IP_NF_MATCH_PKTTYPE=m -CONFIG_IP_NF_MATCH_MARK=m -CONFIG_IP_NF_MATCH_MULTIPORT=m -CONFIG_IP_NF_MATCH_TOS=m -CONFIG_IP_NF_MATCH_RECENT=m -CONFIG_IP_NF_MATCH_ECN=m -CONFIG_IP_NF_MATCH_DSCP=m -CONFIG_IP_NF_MATCH_AH_ESP=m -CONFIG_IP_NF_MATCH_LENGTH=m -CONFIG_IP_NF_MATCH_TTL=m -CONFIG_IP_NF_MATCH_TCPMSS=m -CONFIG_IP_NF_MATCH_HELPER=m -CONFIG_IP_NF_MATCH_STATE=m -CONFIG_IP_NF_MATCH_CONNTRACK=m -CONFIG_IP_NF_MATCH_OWNER=m -CONFIG_IP_NF_MATCH_PHYSDEV=m -CONFIG_IP_NF_MATCH_ADDRTYPE=m -CONFIG_IP_NF_MATCH_REALM=m -CONFIG_IP_NF_MATCH_SCTP=m -CONFIG_IP_NF_MATCH_COMMENT=m -# CONFIG_IP_NF_MATCH_HASHLIMIT is not set -CONFIG_IP_NF_FILTER=m -CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m -CONFIG_IP_NF_TARGET_TCPMSS=m -CONFIG_IP_NF_NAT=m -CONFIG_IP_NF_NAT_NEEDED=y -CONFIG_IP_NF_TARGET_MASQUERADE=m -CONFIG_IP_NF_TARGET_REDIRECT=m -CONFIG_IP_NF_TARGET_NETMAP=m -CONFIG_IP_NF_TARGET_SAME=m -CONFIG_IP_NF_NAT_SNMP_BASIC=m -CONFIG_IP_NF_NAT_IRC=m -CONFIG_IP_NF_NAT_FTP=m -CONFIG_IP_NF_NAT_TFTP=m -CONFIG_IP_NF_NAT_AMANDA=m -CONFIG_IP_NF_MANGLE=m -CONFIG_IP_NF_TARGET_TOS=m -CONFIG_IP_NF_TARGET_ECN=m -CONFIG_IP_NF_TARGET_DSCP=m -CONFIG_IP_NF_TARGET_MARK=m -CONFIG_IP_NF_TARGET_CLASSIFY=m -CONFIG_IP_NF_RAW=m -CONFIG_IP_NF_TARGET_NOTRACK=m -CONFIG_IP_NF_ARPTABLES=m -CONFIG_IP_NF_ARPFILTER=m -CONFIG_IP_NF_ARP_MANGLE=m - -# -# IPv6: Netfilter Configuration (EXPERIMENTAL) -# -# CONFIG_IP6_NF_QUEUE is not set -CONFIG_IP6_NF_IPTABLES=m -CONFIG_IP6_NF_MATCH_LIMIT=m -CONFIG_IP6_NF_MATCH_MAC=m -CONFIG_IP6_NF_MATCH_RT=m -CONFIG_IP6_NF_MATCH_OPTS=m -CONFIG_IP6_NF_MATCH_FRAG=m -CONFIG_IP6_NF_MATCH_HL=m -CONFIG_IP6_NF_MATCH_MULTIPORT=m -CONFIG_IP6_NF_MATCH_OWNER=m -CONFIG_IP6_NF_MATCH_MARK=m -CONFIG_IP6_NF_MATCH_IPV6HEADER=m -CONFIG_IP6_NF_MATCH_AHESP=m -CONFIG_IP6_NF_MATCH_LENGTH=m -CONFIG_IP6_NF_MATCH_EUI64=m -CONFIG_IP6_NF_MATCH_PHYSDEV=m -CONFIG_IP6_NF_FILTER=m -CONFIG_IP6_NF_TARGET_LOG=m -CONFIG_IP6_NF_MANGLE=m -CONFIG_IP6_NF_TARGET_MARK=m -CONFIG_IP6_NF_RAW=m - -# -# Bridge: Netfilter Configuration -# -CONFIG_BRIDGE_NF_EBTABLES=m -CONFIG_BRIDGE_EBT_BROUTE=m -CONFIG_BRIDGE_EBT_T_FILTER=m -CONFIG_BRIDGE_EBT_T_NAT=m -CONFIG_BRIDGE_EBT_802_3=m -CONFIG_BRIDGE_EBT_AMONG=m -CONFIG_BRIDGE_EBT_ARP=m -CONFIG_BRIDGE_EBT_IP=m -CONFIG_BRIDGE_EBT_LIMIT=m -CONFIG_BRIDGE_EBT_MARK=m -CONFIG_BRIDGE_EBT_PKTTYPE=m -CONFIG_BRIDGE_EBT_STP=m -CONFIG_BRIDGE_EBT_VLAN=m -CONFIG_BRIDGE_EBT_ARPREPLY=m -CONFIG_BRIDGE_EBT_DNAT=m -CONFIG_BRIDGE_EBT_MARK_T=m -CONFIG_BRIDGE_EBT_REDIRECT=m -CONFIG_BRIDGE_EBT_SNAT=m -CONFIG_BRIDGE_EBT_LOG=m -# CONFIG_BRIDGE_EBT_ULOG is not set -CONFIG_XFRM=y -CONFIG_XFRM_USER=y - -# -# SCTP Configuration (EXPERIMENTAL) -# -CONFIG_IP_SCTP=m -# CONFIG_SCTP_DBG_MSG is not set -# CONFIG_SCTP_DBG_OBJCNT is not set -# CONFIG_SCTP_HMAC_NONE is not set -# CONFIG_SCTP_HMAC_SHA1 is not set -CONFIG_SCTP_HMAC_MD5=y -CONFIG_ATM=m -CONFIG_ATM_CLIP=m -# CONFIG_ATM_CLIP_NO_ICMP is not set -CONFIG_ATM_LANE=m -# CONFIG_ATM_MPOA is not set -CONFIG_ATM_BR2684=m -# CONFIG_ATM_BR2684_IPFILTER is not set -CONFIG_BRIDGE=m -CONFIG_VLAN_8021Q=m -# CONFIG_DECNET is not set -CONFIG_LLC=m -# CONFIG_LLC2 is not set -CONFIG_IPX=m -# CONFIG_IPX_INTERN is not set -CONFIG_ATALK=m -CONFIG_DEV_APPLETALK=y -CONFIG_IPDDP=m -CONFIG_IPDDP_ENCAP=y -CONFIG_IPDDP_DECAP=y -# CONFIG_X25 is not set -# CONFIG_LAPB is not set -CONFIG_NET_DIVERT=y -# CONFIG_ECONET is not set -CONFIG_WAN_ROUTER=m - -# -# QoS and/or fair queueing -# -CONFIG_NET_SCHED=y -CONFIG_NET_SCH_CLK_JIFFIES=y -# CONFIG_NET_SCH_CLK_GETTIMEOFDAY is not set -# CONFIG_NET_SCH_CLK_CPU is not set -CONFIG_NET_SCH_CBQ=m -CONFIG_NET_SCH_HTB=m -CONFIG_NET_SCH_HFSC=m -CONFIG_NET_SCH_ATM=m -CONFIG_NET_SCH_PRIO=m -CONFIG_NET_SCH_RED=m -CONFIG_NET_SCH_SFQ=m -CONFIG_NET_SCH_TEQL=m -CONFIG_NET_SCH_TBF=m -CONFIG_NET_SCH_GRED=m -CONFIG_NET_SCH_DSMARK=m -CONFIG_NET_SCH_NETEM=m -CONFIG_NET_SCH_INGRESS=m -CONFIG_NET_QOS=y -CONFIG_NET_ESTIMATOR=y -CONFIG_NET_CLS=y -# CONFIG_NET_CLS_BASIC is not set -CONFIG_NET_CLS_TCINDEX=m -CONFIG_NET_CLS_ROUTE4=m -CONFIG_NET_CLS_ROUTE=y -CONFIG_NET_CLS_FW=m -CONFIG_NET_CLS_U32=m -CONFIG_CLS_U32_PERF=y -CONFIG_NET_CLS_IND=y -# CONFIG_CLS_U32_MARK is not set -CONFIG_NET_CLS_RSVP=m -CONFIG_NET_CLS_RSVP6=m -# CONFIG_NET_EMATCH is not set -# CONFIG_NET_CLS_ACT is not set -CONFIG_NET_CLS_POLICE=y - -# -# Network testing -# -# CONFIG_NET_PKTGEN is not set -CONFIG_NETPOLL=y -# CONFIG_NETPOLL_RX is not set -CONFIG_NETPOLL_TRAP=y -CONFIG_NET_POLL_CONTROLLER=y -# CONFIG_HAMRADIO is not set -CONFIG_IRDA=m - -# -# IrDA protocols -# -CONFIG_IRLAN=m -CONFIG_IRNET=m -CONFIG_IRCOMM=m -# CONFIG_IRDA_ULTRA is not set - -# -# IrDA options -# -CONFIG_IRDA_CACHE_LAST_LSAP=y -CONFIG_IRDA_FAST_RR=y -# CONFIG_IRDA_DEBUG is not set - -# -# Infrared-port device drivers -# - -# -# SIR device drivers -# -CONFIG_IRTTY_SIR=m - -# -# Dongle support -# -CONFIG_DONGLE=y -CONFIG_ESI_DONGLE=m -CONFIG_ACTISYS_DONGLE=m -CONFIG_TEKRAM_DONGLE=m -CONFIG_LITELINK_DONGLE=m -CONFIG_MA600_DONGLE=m -CONFIG_GIRBIL_DONGLE=m -CONFIG_MCP2120_DONGLE=m -CONFIG_OLD_BELKIN_DONGLE=m -CONFIG_ACT200L_DONGLE=m - -# -# Old SIR device drivers -# - -# -# Old Serial dongle support -# - -# -# FIR device drivers -# -# CONFIG_NSC_FIR is not set -# CONFIG_WINBOND_FIR is not set -# CONFIG_SMC_IRCC_FIR is not set -# CONFIG_ALI_FIR is not set -# CONFIG_VIA_FIR is not set -CONFIG_BT=m -CONFIG_BT_L2CAP=m -CONFIG_BT_SCO=m -CONFIG_BT_RFCOMM=m -CONFIG_BT_RFCOMM_TTY=y -CONFIG_BT_BNEP=m -CONFIG_BT_BNEP_MC_FILTER=y -CONFIG_BT_BNEP_PROTO_FILTER=y -CONFIG_BT_HIDP=m - -# -# Bluetooth device drivers -# -CONFIG_BT_HCIUART=m -CONFIG_BT_HCIUART_H4=y -CONFIG_BT_HCIUART_BCSP=y -CONFIG_BT_HCIUART_BCSP_TXCRC=y -CONFIG_BT_HCIVHCI=m -CONFIG_NETDEVICES=y -CONFIG_DUMMY=m -CONFIG_BONDING=m -CONFIG_EQUALIZER=m -CONFIG_TUN=m - -# -# Ethernet (10 or 100Mbit) -# -CONFIG_NET_ETHERNET=y -CONFIG_MII=m - -# -# Ethernet (1000 Mbit) -# - -# -# Ethernet (10000 Mbit) -# - -# -# Token Ring devices -# - -# -# Wireless LAN (non-hamradio) -# -CONFIG_NET_RADIO=y - -# -# Obsolete Wireless cards support (pre-802.11) -# -# CONFIG_STRIP is not set -CONFIG_ATMEL=m - -# -# Wan interfaces -# -# CONFIG_WAN is not set - -# -# ATM drivers -# -CONFIG_ATM_TCP=m -CONFIG_PPP=m -CONFIG_PPP_MULTILINK=y -CONFIG_PPP_FILTER=y -CONFIG_PPP_ASYNC=m -CONFIG_PPP_SYNC_TTY=m -CONFIG_PPP_DEFLATE=m -# CONFIG_PPP_BSDCOMP is not set -CONFIG_PPPOE=m -CONFIG_PPPOATM=m -# CONFIG_SLIP is not set -# CONFIG_SHAPER is not set -CONFIG_NETCONSOLE=m -CONFIG_INPUT=m -CONFIG_UNIX98_PTYS=y -# CONFIG_LEGACY_PTYS is not set -# CONFIG_TCG_TPM is not set - -# -# Character devices -# - -# -# File systems -# -CONFIG_EXT2_FS=y -CONFIG_EXT2_FS_XATTR=y -CONFIG_EXT2_FS_POSIX_ACL=y -CONFIG_EXT2_FS_SECURITY=y -CONFIG_EXT3_FS=y -CONFIG_EXT3_FS_XATTR=y -# CONFIG_EXT3_FS_POSIX_ACL is not set -# CONFIG_EXT3_FS_SECURITY is not set -CONFIG_JBD=m -# CONFIG_JBD_DEBUG is not set -CONFIG_FS_MBCACHE=y -CONFIG_REISERFS_FS=y -# CONFIG_REISERFS_CHECK is not set -CONFIG_REISERFS_PROC_INFO=y -CONFIG_REISERFS_FS_XATTR=y -CONFIG_REISERFS_FS_POSIX_ACL=y -CONFIG_REISERFS_FS_SECURITY=y -CONFIG_JFS_FS=m -CONFIG_JFS_POSIX_ACL=y -# CONFIG_JFS_SECURITY is not set -# CONFIG_JFS_DEBUG is not set -# CONFIG_JFS_STATISTICS is not set -CONFIG_FS_POSIX_ACL=y - -# -# XFS support -# -CONFIG_XFS_FS=m -CONFIG_XFS_EXPORT=y -# CONFIG_XFS_RT is not set -CONFIG_XFS_QUOTA=y -CONFIG_XFS_SECURITY=y -CONFIG_XFS_POSIX_ACL=y -CONFIG_MINIX_FS=m -CONFIG_ROMFS_FS=m -CONFIG_QUOTA=y -# CONFIG_QFMT_V1 is not set -CONFIG_QFMT_V2=y -CONFIG_QUOTACTL=y -CONFIG_DNOTIFY=y -CONFIG_AUTOFS_FS=m -CONFIG_AUTOFS4_FS=m - -# -# CD-ROM/DVD Filesystems -# -CONFIG_ISO9660_FS=y -CONFIG_JOLIET=y -CONFIG_ZISOFS=y -CONFIG_ZISOFS_FS=y -CONFIG_UDF_FS=m -CONFIG_UDF_NLS=y - -# -# DOS/FAT/NT Filesystems -# -CONFIG_FAT_FS=m -CONFIG_MSDOS_FS=m -CONFIG_VFAT_FS=m -CONFIG_FAT_DEFAULT_CODEPAGE=437 -CONFIG_FAT_DEFAULT_IOCHARSET="ascii" -# CONFIG_NTFS_FS is not set - -# -# Pseudo filesystems -# -CONFIG_PROC_FS=y -CONFIG_PROC_KCORE=y -CONFIG_SYSFS=y -# CONFIG_DEVFS_FS is not set -CONFIG_DEVPTS_FS_XATTR=y -CONFIG_DEVPTS_FS_SECURITY=y -CONFIG_TMPFS=y -CONFIG_TMPFS_XATTR=y -CONFIG_TMPFS_SECURITY=y -# CONFIG_HUGETLBFS is not set -# CONFIG_HUGETLB_PAGE is not set -CONFIG_RAMFS=y - -# -# Miscellaneous filesystems -# -# CONFIG_ADFS_FS is not set -CONFIG_AFFS_FS=m -CONFIG_HFS_FS=m -CONFIG_HFSPLUS_FS=m -CONFIG_BEFS_FS=m -# CONFIG_BEFS_DEBUG is not set -CONFIG_BFS_FS=m -CONFIG_EFS_FS=m -CONFIG_CRAMFS=y -CONFIG_VXFS_FS=m -# CONFIG_HPFS_FS is not set -CONFIG_QNX4FS_FS=m -CONFIG_SYSV_FS=m -CONFIG_UFS_FS=m -# CONFIG_UFS_FS_WRITE is not set - -# -# Network File Systems -# -CONFIG_NFS_FS=m -CONFIG_NFS_V3=y -CONFIG_NFS_V4=y -CONFIG_NFS_DIRECTIO=y -CONFIG_NFSD=m -CONFIG_NFSD_V3=y -CONFIG_NFSD_V4=y -CONFIG_NFSD_TCP=y -CONFIG_LOCKD=m -CONFIG_LOCKD_V4=y -CONFIG_EXPORTFS=m -CONFIG_SUNRPC=m -CONFIG_SUNRPC_GSS=m -CONFIG_RPCSEC_GSS_KRB5=m -CONFIG_RPCSEC_GSS_SPKM3=m -CONFIG_SMB_FS=m -# CONFIG_SMB_NLS_DEFAULT is not set -CONFIG_CIFS=m -# CONFIG_CIFS_STATS is not set -CONFIG_CIFS_XATTR=y -CONFIG_CIFS_POSIX=y -# CONFIG_CIFS_EXPERIMENTAL is not set -CONFIG_NCP_FS=m -CONFIG_NCPFS_PACKET_SIGNING=y -CONFIG_NCPFS_IOCTL_LOCKING=y -CONFIG_NCPFS_STRONG=y -CONFIG_NCPFS_NFS_NS=y -CONFIG_NCPFS_OS2_NS=y -CONFIG_NCPFS_SMALLDOS=y -CONFIG_NCPFS_NLS=y -CONFIG_NCPFS_EXTRAS=y -# CONFIG_CODA_FS is not set -# CONFIG_AFS_FS is not set - -# -# Partition Types -# -CONFIG_PARTITION_ADVANCED=y -# CONFIG_ACORN_PARTITION is not set -CONFIG_OSF_PARTITION=y -# CONFIG_AMIGA_PARTITION is not set -# CONFIG_ATARI_PARTITION is not set -CONFIG_MAC_PARTITION=y -CONFIG_MSDOS_PARTITION=y -CONFIG_BSD_DISKLABEL=y -CONFIG_MINIX_SUBPARTITION=y -CONFIG_SOLARIS_X86_PARTITION=y -CONFIG_UNIXWARE_DISKLABEL=y -# CONFIG_LDM_PARTITION is not set -CONFIG_SGI_PARTITION=y -# CONFIG_ULTRIX_PARTITION is not set -CONFIG_SUN_PARTITION=y -CONFIG_EFI_PARTITION=y - -# -# Native Language Support -# -CONFIG_NLS=y -CONFIG_NLS_DEFAULT="utf8" -CONFIG_NLS_CODEPAGE_437=y -CONFIG_NLS_CODEPAGE_737=m -CONFIG_NLS_CODEPAGE_775=m -CONFIG_NLS_CODEPAGE_850=m -CONFIG_NLS_CODEPAGE_852=m -CONFIG_NLS_CODEPAGE_855=m -CONFIG_NLS_CODEPAGE_857=m -CONFIG_NLS_CODEPAGE_860=m -CONFIG_NLS_CODEPAGE_861=m -CONFIG_NLS_CODEPAGE_862=m -CONFIG_NLS_CODEPAGE_863=m -CONFIG_NLS_CODEPAGE_864=m -CONFIG_NLS_CODEPAGE_865=m -CONFIG_NLS_CODEPAGE_866=m -CONFIG_NLS_CODEPAGE_869=m -CONFIG_NLS_CODEPAGE_936=m -CONFIG_NLS_CODEPAGE_950=m -CONFIG_NLS_CODEPAGE_932=m -CONFIG_NLS_CODEPAGE_949=m -CONFIG_NLS_CODEPAGE_874=m -CONFIG_NLS_ISO8859_8=m -CONFIG_NLS_CODEPAGE_1250=m -CONFIG_NLS_CODEPAGE_1251=m -CONFIG_NLS_ASCII=y -CONFIG_NLS_ISO8859_1=m -CONFIG_NLS_ISO8859_2=m -CONFIG_NLS_ISO8859_3=m -CONFIG_NLS_ISO8859_4=m -CONFIG_NLS_ISO8859_5=m -CONFIG_NLS_ISO8859_6=m -CONFIG_NLS_ISO8859_7=m -CONFIG_NLS_ISO8859_9=m -CONFIG_NLS_ISO8859_13=m -CONFIG_NLS_ISO8859_14=m -CONFIG_NLS_ISO8859_15=m -CONFIG_NLS_KOI8_R=m -CONFIG_NLS_KOI8_U=m -CONFIG_NLS_UTF8=m - -# -# Security options -# -# CONFIG_KEYS is not set -# CONFIG_SECURITY is not set - -# -# Cryptographic options -# -CONFIG_CRYPTO=y -CONFIG_CRYPTO_HMAC=y -CONFIG_CRYPTO_NULL=m -CONFIG_CRYPTO_MD4=m -CONFIG_CRYPTO_MD5=m -CONFIG_CRYPTO_SHA1=y -CONFIG_CRYPTO_SHA256=m -CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_WP512=m -# CONFIG_CRYPTO_TGR192 is not set -CONFIG_CRYPTO_DES=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_SERPENT=m -# CONFIG_CRYPTO_AES is not set -CONFIG_CRYPTO_CAST5=m -CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_KHAZAD=m -# CONFIG_CRYPTO_ANUBIS is not set -CONFIG_CRYPTO_DEFLATE=m -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_CRC32C=m -# CONFIG_CRYPTO_TEST is not set - -# -# Hardware crypto devices -# - -# -# Library routines -# -CONFIG_CRC_CCITT=m -CONFIG_CRC32=y -CONFIG_LIBCRC32C=m -CONFIG_ZLIB_INFLATE=y -CONFIG_ZLIB_DEFLATE=m - -# -# Kernel hacking -# -# CONFIG_PRINTK_TIME is not set -CONFIG_DEBUG_KERNEL=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_LOG_BUF_SHIFT=15 -# CONFIG_SCHEDSTATS is not set -# CONFIG_DEBUG_SLAB is not set -# CONFIG_DEBUG_SPINLOCK is not set -# CONFIG_DEBUG_SPINLOCK_SLEEP is not set -# CONFIG_DEBUG_KOBJECT is not set -# CONFIG_DEBUG_INFO is not set -# CONFIG_DEBUG_FS is not set -# CONFIG_DEBUG_STACKOVERFLOW is not set -# CONFIG_KPROBES is not set -# CONFIG_DEBUG_STACK_USAGE is not set -# CONFIG_DEBUG_PAGEALLOC is not set -# CONFIG_4KSTACKS is not set -# CONFIG_INIT_DEBUG is not set diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/configs/xen_defconfig_x86_32 --- a/linux-2.6-xen-sparse/arch/xen/configs/xen_defconfig_x86_32 Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,2965 +0,0 @@ -# -# Automatically generated make config: don't edit -# Linux kernel version: 2.6.12.6-xen -# Mon Dec 12 10:42:00 2005 -# -CONFIG_XEN=y -CONFIG_ARCH_XEN=y -CONFIG_NO_IDLE_HZ=y - -# -# XEN -# -CONFIG_XEN_PRIVILEGED_GUEST=y -CONFIG_XEN_PHYSDEV_ACCESS=y -CONFIG_XEN_BLKDEV_BACKEND=y -# CONFIG_XEN_BLKDEV_TAP_BE is not set -CONFIG_XEN_NETDEV_BACKEND=y -# CONFIG_XEN_NETDEV_PIPELINED_TRANSMITTER is not set -# CONFIG_XEN_TPMDEV_FRONTEND is not set -# CONFIG_XEN_TPMDEV_BACKEND is not set -CONFIG_XEN_BLKDEV_FRONTEND=y -CONFIG_XEN_NETDEV_FRONTEND=y -# CONFIG_XEN_BLKDEV_TAP is not set -# CONFIG_XEN_SHADOW_MODE is not set -CONFIG_XEN_SCRUB_PAGES=y -CONFIG_XEN_X86=y -# CONFIG_XEN_X86_64 is not set -CONFIG_HAVE_ARCH_ALLOC_SKB=y -CONFIG_HAVE_ARCH_DEV_ALLOC_SKB=y - -# -# Code maturity level options -# -CONFIG_EXPERIMENTAL=y -# CONFIG_CLEAN_COMPILE is not set -CONFIG_BROKEN=y -CONFIG_BROKEN_ON_SMP=y -CONFIG_LOCK_KERNEL=y -CONFIG_INIT_ENV_ARG_LIMIT=32 - -# -# General setup -# -CONFIG_LOCALVERSION="" -CONFIG_SWAP=y -CONFIG_SYSVIPC=y -CONFIG_POSIX_MQUEUE=y -CONFIG_BSD_PROCESS_ACCT=y -# CONFIG_BSD_PROCESS_ACCT_V3 is not set -CONFIG_SYSCTL=y -# CONFIG_AUDIT is not set -CONFIG_HOTPLUG=y -CONFIG_KOBJECT_UEVENT=y -# CONFIG_IKCONFIG is not set -# CONFIG_CPUSETS is not set -CONFIG_EMBEDDED=y -CONFIG_KALLSYMS=y -# CONFIG_KALLSYMS_ALL is not set -# CONFIG_KALLSYMS_EXTRA_PASS is not set -CONFIG_PRINTK=y -CONFIG_BUG=y -CONFIG_BASE_FULL=y -CONFIG_FUTEX=y -CONFIG_EPOLL=y -# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set -CONFIG_SHMEM=y -CONFIG_CC_ALIGN_FUNCTIONS=0 -CONFIG_CC_ALIGN_LABELS=0 -CONFIG_CC_ALIGN_LOOPS=0 -CONFIG_CC_ALIGN_JUMPS=0 -# CONFIG_TINY_SHMEM is not set -CONFIG_BASE_SMALL=0 - -# -# Loadable module support -# -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODULE_FORCE_UNLOAD=y -CONFIG_OBSOLETE_MODPARM=y -CONFIG_MODVERSIONS=y -# CONFIG_MODULE_SRCVERSION_ALL is not set -CONFIG_KMOD=y -CONFIG_STOP_MACHINE=y - -# -# X86 Processor Configuration -# -CONFIG_XENARCH="i386" -CONFIG_X86=y -CONFIG_MMU=y -CONFIG_UID16=y -CONFIG_GENERIC_ISA_DMA=y -CONFIG_GENERIC_IOMAP=y -# CONFIG_M386 is not set -# CONFIG_M486 is not set -# CONFIG_M586 is not set -# CONFIG_M586TSC is not set -# CONFIG_M586MMX is not set -CONFIG_M686=y -# CONFIG_MPENTIUMII is not set -# CONFIG_MPENTIUMIII is not set -# CONFIG_MPENTIUMM is not set -# CONFIG_MPENTIUM4 is not set -# CONFIG_MK6 is not set -# CONFIG_MK7 is not set -# CONFIG_MK8 is not set -# CONFIG_MCRUSOE is not set -# CONFIG_MEFFICEON is not set -# CONFIG_MWINCHIPC6 is not set -# CONFIG_MWINCHIP2 is not set -# CONFIG_MWINCHIP3D is not set -# CONFIG_MGEODEGX1 is not set -# CONFIG_MCYRIXIII is not set -# CONFIG_MVIAC3_2 is not set -# CONFIG_X86_GENERIC is not set -CONFIG_X86_CMPXCHG=y -CONFIG_X86_XADD=y -CONFIG_X86_L1_CACHE_SHIFT=5 -CONFIG_RWSEM_XCHGADD_ALGORITHM=y -CONFIG_GENERIC_CALIBRATE_DELAY=y -CONFIG_X86_PPRO_FENCE=y -CONFIG_X86_WP_WORKS_OK=y -CONFIG_X86_INVLPG=y -CONFIG_X86_BSWAP=y -CONFIG_X86_POPAD_OK=y -CONFIG_X86_GOOD_APIC=y -CONFIG_X86_USE_PPRO_CHECKSUM=y -# CONFIG_HPET_TIMER is not set -# CONFIG_HPET_EMULATE_RTC is not set -CONFIG_SMP=y -CONFIG_SMP_ALTERNATIVES=y -CONFIG_NR_CPUS=8 -# CONFIG_SCHED_SMT is not set -# CONFIG_X86_REBOOTFIXUPS is not set -CONFIG_MICROCODE=y -CONFIG_X86_CPUID=m -CONFIG_SWIOTLB=y - -# -# Firmware Drivers -# -CONFIG_EDD=m -# CONFIG_NOHIGHMEM is not set -CONFIG_HIGHMEM4G=y -# CONFIG_HIGHMEM64G is not set -CONFIG_HIGHMEM=y -CONFIG_MTRR=y -CONFIG_HAVE_DEC_LOCK=y -# CONFIG_REGPARM is not set -CONFIG_X86_LOCAL_APIC=y -CONFIG_X86_IO_APIC=y -CONFIG_HOTPLUG_CPU=y - -# -# Bus options (PCI, PCMCIA, EISA, MCA, ISA) -# -CONFIG_PCI=y -# CONFIG_PCI_GOMMCONFIG is not set -# CONFIG_PCI_GODIRECT is not set -CONFIG_PCI_GOANY=y -CONFIG_PCI_DIRECT=y -CONFIG_PCI_MMCONFIG=y -# CONFIG_PCIEPORTBUS is not set -# CONFIG_PCI_MSI is not set -# CONFIG_PCI_LEGACY_PROC is not set -CONFIG_PCI_NAMES=y -# CONFIG_PCI_DEBUG is not set -CONFIG_ISA_DMA_API=y -CONFIG_ISA=y -# CONFIG_EISA is not set -# CONFIG_MCA is not set -CONFIG_SCx200=m - -# -# PCCARD (PCMCIA/CardBus) support -# -CONFIG_PCCARD=m -# CONFIG_PCMCIA_DEBUG is not set -CONFIG_PCMCIA=m -CONFIG_CARDBUS=y - -# -# PC-card bridges -# -CONFIG_YENTA=m -CONFIG_PD6729=m -CONFIG_I82092=m -CONFIG_I82365=m -CONFIG_TCIC=m -CONFIG_PCMCIA_PROBE=y -CONFIG_PCCARD_NONSTATIC=m - -# -# PCI Hotplug Support -# -CONFIG_HOTPLUG_PCI=m -CONFIG_HOTPLUG_PCI_FAKE=m -# CONFIG_HOTPLUG_PCI_ACPI is not set -CONFIG_HOTPLUG_PCI_CPCI=y -CONFIG_HOTPLUG_PCI_CPCI_ZT5550=m -CONFIG_HOTPLUG_PCI_CPCI_GENERIC=m -CONFIG_HOTPLUG_PCI_SHPC=m -# CONFIG_HOTPLUG_PCI_SHPC_POLL_EVENT_MODE is not set -CONFIG_GENERIC_HARDIRQS=y -CONFIG_GENERIC_IRQ_PROBE=y -CONFIG_X86_SMP=y -CONFIG_X86_BIOS_REBOOT=y -CONFIG_X86_TRAMPOLINE=y -CONFIG_SECCOMP=y -# CONFIG_EARLY_PRINTK is not set - -# -# Executable file formats -# -CONFIG_BINFMT_ELF=y -CONFIG_BINFMT_AOUT=m -CONFIG_BINFMT_MISC=m - -# -# Device Drivers -# - -# -# Generic Driver Options -# -CONFIG_STANDALONE=y -CONFIG_PREVENT_FIRMWARE_BUILD=y -CONFIG_FW_LOADER=m -# CONFIG_DEBUG_DRIVER is not set - -# -# Memory Technology Devices (MTD) -# -CONFIG_MTD=m -# CONFIG_MTD_DEBUG is not set -CONFIG_MTD_CONCAT=m -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_REDBOOT_PARTS=m -CONFIG_MTD_REDBOOT_DIRECTORY_BLOCK=-1 -# CONFIG_MTD_REDBOOT_PARTS_UNALLOCATED is not set -# CONFIG_MTD_REDBOOT_PARTS_READONLY is not set -# CONFIG_MTD_CMDLINE_PARTS is not set - -# -# User Modules And Translation Layers -# -CONFIG_MTD_CHAR=m -CONFIG_MTD_BLOCK=m -CONFIG_MTD_BLOCK_RO=m -CONFIG_FTL=m -CONFIG_NFTL=m -CONFIG_NFTL_RW=y -CONFIG_INFTL=m - -# -# RAM/ROM/Flash chip drivers -# -CONFIG_MTD_CFI=m -CONFIG_MTD_JEDECPROBE=m -CONFIG_MTD_GEN_PROBE=m -# CONFIG_MTD_CFI_ADV_OPTIONS is not set -CONFIG_MTD_MAP_BANK_WIDTH_1=y -CONFIG_MTD_MAP_BANK_WIDTH_2=y -CONFIG_MTD_MAP_BANK_WIDTH_4=y -# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set -# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set -# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set -CONFIG_MTD_CFI_I1=y -CONFIG_MTD_CFI_I2=y -# CONFIG_MTD_CFI_I4 is not set -# CONFIG_MTD_CFI_I8 is not set -CONFIG_MTD_CFI_INTELEXT=m -CONFIG_MTD_CFI_AMDSTD=m -CONFIG_MTD_CFI_AMDSTD_RETRY=0 -CONFIG_MTD_CFI_STAA=m -CONFIG_MTD_CFI_UTIL=m -CONFIG_MTD_RAM=m -CONFIG_MTD_ROM=m -CONFIG_MTD_ABSENT=m -# CONFIG_MTD_OBSOLETE_CHIPS is not set - -# -# Mapping drivers for chip access -# -CONFIG_MTD_COMPLEX_MAPPINGS=y -CONFIG_MTD_PHYSMAP=m -CONFIG_MTD_PHYSMAP_START=0x8000000 -CONFIG_MTD_PHYSMAP_LEN=0x4000000 -CONFIG_MTD_PHYSMAP_BANKWIDTH=2 -CONFIG_MTD_PNC2000=m -CONFIG_MTD_SC520CDP=m -CONFIG_MTD_NETSC520=m -CONFIG_MTD_TS5500=m -CONFIG_MTD_SBC_GXX=m -CONFIG_MTD_ELAN_104NC=m -CONFIG_MTD_SCx200_DOCFLASH=m -# CONFIG_MTD_AMD76XROM is not set -# CONFIG_MTD_ICHXROM is not set -# CONFIG_MTD_SCB2_FLASH is not set -CONFIG_MTD_NETtel=m -CONFIG_MTD_DILNETPC=m -CONFIG_MTD_DILNETPC_BOOTSIZE=0x80000 -# CONFIG_MTD_L440GX is not set -CONFIG_MTD_PCI=m -CONFIG_MTD_PCMCIA=m - -# -# Self-contained MTD device drivers -# -CONFIG_MTD_PMC551=m -# CONFIG_MTD_PMC551_BUGFIX is not set -# CONFIG_MTD_PMC551_DEBUG is not set -CONFIG_MTD_SLRAM=m -CONFIG_MTD_PHRAM=m -CONFIG_MTD_MTDRAM=m -CONFIG_MTDRAM_TOTAL_SIZE=4096 -CONFIG_MTDRAM_ERASE_SIZE=128 -CONFIG_MTD_BLKMTD=m -# CONFIG_MTD_BLOCK2MTD is not set - -# -# Disk-On-Chip Device Drivers -# -CONFIG_MTD_DOC2000=m -CONFIG_MTD_DOC2001=m -CONFIG_MTD_DOC2001PLUS=m -CONFIG_MTD_DOCPROBE=m -CONFIG_MTD_DOCECC=m -# CONFIG_MTD_DOCPROBE_ADVANCED is not set -CONFIG_MTD_DOCPROBE_ADDRESS=0 - -# -# NAND Flash Device Drivers -# -CONFIG_MTD_NAND=m -# CONFIG_MTD_NAND_VERIFY_WRITE is not set -CONFIG_MTD_NAND_IDS=m -CONFIG_MTD_NAND_DISKONCHIP=m -# CONFIG_MTD_NAND_DISKONCHIP_PROBE_ADVANCED is not set -CONFIG_MTD_NAND_DISKONCHIP_PROBE_ADDRESS=0 -# CONFIG_MTD_NAND_DISKONCHIP_BBTWRITE is not set -# CONFIG_MTD_NAND_NANDSIM is not set - -# -# Parallel port support -# -CONFIG_PARPORT=m -CONFIG_PARPORT_PC=m -CONFIG_PARPORT_SERIAL=m -CONFIG_PARPORT_PC_FIFO=y -# CONFIG_PARPORT_PC_SUPERIO is not set -CONFIG_PARPORT_PC_PCMCIA=m -CONFIG_PARPORT_NOT_PC=y -# CONFIG_PARPORT_GSC is not set -CONFIG_PARPORT_1284=y - -# -# Plug and Play support -# -CONFIG_PNP=y -# CONFIG_PNP_DEBUG is not set - -# -# Protocols -# -CONFIG_ISAPNP=y -# CONFIG_PNPBIOS is not set -# CONFIG_PNPACPI is not set - -# -# Block devices -# -CONFIG_BLK_DEV_FD=m -CONFIG_BLK_DEV_XD=m -CONFIG_PARIDE=m -CONFIG_PARIDE_PARPORT=m - -# -# Parallel IDE high-level drivers -# -CONFIG_PARIDE_PD=m -CONFIG_PARIDE_PCD=m -CONFIG_PARIDE_PF=m -CONFIG_PARIDE_PT=m -CONFIG_PARIDE_PG=m - -# -# Parallel IDE protocol modules -# -CONFIG_PARIDE_ATEN=m -CONFIG_PARIDE_BPCK=m -CONFIG_PARIDE_BPCK6=m -CONFIG_PARIDE_COMM=m -CONFIG_PARIDE_DSTR=m -CONFIG_PARIDE_FIT2=m -CONFIG_PARIDE_FIT3=m -CONFIG_PARIDE_EPAT=m -# CONFIG_PARIDE_EPATC8 is not set -CONFIG_PARIDE_EPIA=m -CONFIG_PARIDE_FRIQ=m -CONFIG_PARIDE_FRPW=m -CONFIG_PARIDE_KBIC=m -CONFIG_PARIDE_KTTI=m -CONFIG_PARIDE_ON20=m -CONFIG_PARIDE_ON26=m -CONFIG_BLK_CPQ_DA=m -CONFIG_BLK_CPQ_CISS_DA=m -CONFIG_CISS_SCSI_TAPE=y -CONFIG_BLK_DEV_DAC960=m -CONFIG_BLK_DEV_UMEM=m -# CONFIG_BLK_DEV_COW_COMMON is not set -CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_CRYPTOLOOP=m -CONFIG_BLK_DEV_NBD=m -CONFIG_BLK_DEV_SX8=m -# CONFIG_BLK_DEV_UB is not set -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_COUNT=16 -CONFIG_BLK_DEV_RAM_SIZE=16384 -CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="" -CONFIG_LBD=y -CONFIG_CDROM_PKTCDVD=m -CONFIG_CDROM_PKTCDVD_BUFFERS=8 -# CONFIG_CDROM_PKTCDVD_WCACHE is not set - -# -# IO Schedulers -# -CONFIG_IOSCHED_NOOP=y -CONFIG_IOSCHED_AS=y -CONFIG_IOSCHED_DEADLINE=y -CONFIG_IOSCHED_CFQ=y -CONFIG_ATA_OVER_ETH=m - -# -# ATA/ATAPI/MFM/RLL support -# -CONFIG_IDE=y -CONFIG_BLK_DEV_IDE=y - -# -# Please see Documentation/ide.txt for help/info on IDE drives -# -# CONFIG_BLK_DEV_IDE_SATA is not set -# CONFIG_BLK_DEV_HD_IDE is not set -CONFIG_BLK_DEV_IDEDISK=y -CONFIG_IDEDISK_MULTI_MODE=y -CONFIG_BLK_DEV_IDECS=m -CONFIG_BLK_DEV_IDECD=y -CONFIG_BLK_DEV_IDETAPE=m -CONFIG_BLK_DEV_IDEFLOPPY=y -CONFIG_BLK_DEV_IDESCSI=m -# CONFIG_IDE_TASK_IOCTL is not set - -# -# IDE chipset support/bugfixes -# -CONFIG_IDE_GENERIC=y -CONFIG_BLK_DEV_CMD640=y -CONFIG_BLK_DEV_CMD640_ENHANCED=y -CONFIG_BLK_DEV_IDEPNP=y -CONFIG_BLK_DEV_IDEPCI=y -CONFIG_IDEPCI_SHARE_IRQ=y -# CONFIG_BLK_DEV_OFFBOARD is not set -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_OPTI621=m -CONFIG_BLK_DEV_RZ1000=y -CONFIG_BLK_DEV_IDEDMA_PCI=y -# CONFIG_BLK_DEV_IDEDMA_FORCED is not set -CONFIG_IDEDMA_PCI_AUTO=y -# CONFIG_IDEDMA_ONLYDISK is not set -CONFIG_BLK_DEV_AEC62XX=y -CONFIG_BLK_DEV_ALI15X3=y -# CONFIG_WDC_ALI15X3 is not set -CONFIG_BLK_DEV_AMD74XX=y -CONFIG_BLK_DEV_ATIIXP=y -CONFIG_BLK_DEV_CMD64X=y -CONFIG_BLK_DEV_TRIFLEX=y -CONFIG_BLK_DEV_CY82C693=y -CONFIG_BLK_DEV_CS5520=y -CONFIG_BLK_DEV_CS5530=y -CONFIG_BLK_DEV_HPT34X=y -# CONFIG_HPT34X_AUTODMA is not set -CONFIG_BLK_DEV_HPT366=y -CONFIG_BLK_DEV_SC1200=m -CONFIG_BLK_DEV_PIIX=y -CONFIG_BLK_DEV_NS87415=m -CONFIG_BLK_DEV_PDC202XX_OLD=y -CONFIG_PDC202XX_BURST=y -CONFIG_BLK_DEV_PDC202XX_NEW=y -CONFIG_PDC202XX_FORCE=y -CONFIG_BLK_DEV_SVWKS=y -CONFIG_BLK_DEV_SIIMAGE=y -CONFIG_BLK_DEV_SIS5513=y -CONFIG_BLK_DEV_SLC90E66=y -CONFIG_BLK_DEV_TRM290=m -CONFIG_BLK_DEV_VIA82CXXX=y -# CONFIG_IDE_ARM is not set -# CONFIG_IDE_CHIPSETS is not set -CONFIG_BLK_DEV_IDEDMA=y -# CONFIG_IDEDMA_IVB is not set -CONFIG_IDEDMA_AUTO=y -# CONFIG_BLK_DEV_HD is not set - -# -# SCSI device support -# -CONFIG_SCSI=m -CONFIG_SCSI_PROC_FS=y - -# -# SCSI support type (disk, tape, CD-ROM) -# -CONFIG_BLK_DEV_SD=m -CONFIG_CHR_DEV_ST=m -CONFIG_CHR_DEV_OSST=m -CONFIG_BLK_DEV_SR=m -# CONFIG_BLK_DEV_SR_VENDOR is not set -CONFIG_CHR_DEV_SG=m - -# -# Some SCSI devices (e.g. CD jukebox) support multiple LUNs -# -CONFIG_SCSI_MULTI_LUN=y -CONFIG_SCSI_CONSTANTS=y -CONFIG_SCSI_LOGGING=y - -# -# SCSI Transport Attributes -# -CONFIG_SCSI_SPI_ATTRS=m -CONFIG_SCSI_FC_ATTRS=m -# CONFIG_SCSI_ISCSI_ATTRS is not set - -# -# SCSI low-level drivers -# -CONFIG_BLK_DEV_3W_XXXX_RAID=m -CONFIG_SCSI_3W_9XXX=m -# CONFIG_SCSI_7000FASST is not set -CONFIG_SCSI_ACARD=m -CONFIG_SCSI_AHA152X=m -# CONFIG_SCSI_AHA1542 is not set -CONFIG_SCSI_AACRAID=m -CONFIG_SCSI_AIC7XXX=m -CONFIG_AIC7XXX_CMDS_PER_DEVICE=8 -CONFIG_AIC7XXX_RESET_DELAY_MS=15000 -CONFIG_AIC7XXX_DEBUG_ENABLE=y -CONFIG_AIC7XXX_DEBUG_MASK=0 -CONFIG_AIC7XXX_REG_PRETTY_PRINT=y -CONFIG_SCSI_AIC7XXX_OLD=m -CONFIG_SCSI_AIC79XX=m -CONFIG_AIC79XX_CMDS_PER_DEVICE=32 -CONFIG_AIC79XX_RESET_DELAY_MS=15000 -CONFIG_AIC79XX_ENABLE_RD_STRM=y -CONFIG_AIC79XX_DEBUG_ENABLE=y -CONFIG_AIC79XX_DEBUG_MASK=0 -CONFIG_AIC79XX_REG_PRETTY_PRINT=y -CONFIG_SCSI_DPT_I2O=m -CONFIG_SCSI_ADVANSYS=m -CONFIG_SCSI_IN2000=m -CONFIG_MEGARAID_NEWGEN=y -CONFIG_MEGARAID_MM=m -CONFIG_MEGARAID_MAILBOX=m -CONFIG_SCSI_SATA=y -CONFIG_SCSI_SATA_AHCI=m -CONFIG_SCSI_SATA_SVW=m -CONFIG_SCSI_ATA_PIIX=m -CONFIG_SCSI_SATA_NV=m -CONFIG_SCSI_SATA_PROMISE=m -# CONFIG_SCSI_SATA_QSTOR is not set -CONFIG_SCSI_SATA_SX4=m -CONFIG_SCSI_SATA_SIL=m -CONFIG_SCSI_SATA_SIS=m -CONFIG_SCSI_SATA_ULI=m -CONFIG_SCSI_SATA_VIA=m -CONFIG_SCSI_SATA_VITESSE=m -CONFIG_SCSI_BUSLOGIC=m -# CONFIG_SCSI_OMIT_FLASHPOINT is not set -# CONFIG_SCSI_CPQFCTS is not set -CONFIG_SCSI_DMX3191D=m -CONFIG_SCSI_DTC3280=m -CONFIG_SCSI_EATA=m -CONFIG_SCSI_EATA_TAGGED_QUEUE=y -CONFIG_SCSI_EATA_LINKED_COMMANDS=y -CONFIG_SCSI_EATA_MAX_TAGS=16 -CONFIG_SCSI_EATA_PIO=m -CONFIG_SCSI_FUTURE_DOMAIN=m -CONFIG_SCSI_GDTH=m -CONFIG_SCSI_GENERIC_NCR5380=m -CONFIG_SCSI_GENERIC_NCR5380_MMIO=m -CONFIG_SCSI_GENERIC_NCR53C400=y -CONFIG_SCSI_IPS=m -# CONFIG_SCSI_INITIO is not set -# CONFIG_SCSI_INIA100 is not set -CONFIG_SCSI_PPA=m -CONFIG_SCSI_IMM=m -# CONFIG_SCSI_IZIP_EPP16 is not set -# CONFIG_SCSI_IZIP_SLOW_CTR is not set -CONFIG_SCSI_NCR53C406A=m -CONFIG_SCSI_SYM53C8XX_2=m -CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=1 -CONFIG_SCSI_SYM53C8XX_DEFAULT_TAGS=16 -CONFIG_SCSI_SYM53C8XX_MAX_TAGS=64 -# CONFIG_SCSI_SYM53C8XX_IOMAPPED is not set -CONFIG_SCSI_IPR=m -# CONFIG_SCSI_IPR_TRACE is not set -# CONFIG_SCSI_IPR_DUMP is not set -CONFIG_SCSI_PAS16=m -# CONFIG_SCSI_PCI2000 is not set -# CONFIG_SCSI_PCI2220I is not set -CONFIG_SCSI_PSI240I=m -CONFIG_SCSI_QLOGIC_FAS=m -CONFIG_SCSI_QLOGIC_ISP=m -CONFIG_SCSI_QLOGIC_FC=m -CONFIG_SCSI_QLOGIC_FC_FIRMWARE=y -CONFIG_SCSI_QLOGIC_1280=m -CONFIG_SCSI_QLOGIC_1280_1040=y -CONFIG_SCSI_QLA2XXX=m -CONFIG_SCSI_QLA21XX=m -CONFIG_SCSI_QLA22XX=m -CONFIG_SCSI_QLA2300=m -CONFIG_SCSI_QLA2322=m -CONFIG_SCSI_QLA6312=m -CONFIG_SCSI_LPFC=m -# CONFIG_SCSI_SEAGATE is not set -CONFIG_SCSI_SYM53C416=m -CONFIG_SCSI_DC395x=m -CONFIG_SCSI_DC390T=m -CONFIG_SCSI_T128=m -CONFIG_SCSI_U14_34F=m -CONFIG_SCSI_U14_34F_TAGGED_QUEUE=y -CONFIG_SCSI_U14_34F_LINKED_COMMANDS=y -CONFIG_SCSI_U14_34F_MAX_TAGS=8 -# CONFIG_SCSI_ULTRASTOR is not set -CONFIG_SCSI_NSP32=m -CONFIG_SCSI_DEBUG=m - -# -# PCMCIA SCSI adapter support -# -CONFIG_PCMCIA_AHA152X=m -CONFIG_PCMCIA_FDOMAIN=m -CONFIG_PCMCIA_NINJA_SCSI=m -CONFIG_PCMCIA_QLOGIC=m -CONFIG_PCMCIA_SYM53C500=m - -# -# Old CD-ROM drivers (not SCSI, not IDE) -# -CONFIG_CD_NO_IDESCSI=y -CONFIG_AZTCD=m -CONFIG_GSCD=m -# CONFIG_SBPCD is not set -CONFIG_MCDX=m -CONFIG_OPTCD=m -# CONFIG_CM206 is not set -CONFIG_SJCD=m -CONFIG_ISP16_CDI=m -CONFIG_CDU31A=m -CONFIG_CDU535=m - -# -# Multi-device support (RAID and LVM) -# -CONFIG_MD=y -CONFIG_BLK_DEV_MD=m -CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m -CONFIG_MD_RAID1=m -CONFIG_MD_RAID10=m -CONFIG_MD_RAID5=m -CONFIG_MD_RAID6=m -CONFIG_MD_MULTIPATH=m -CONFIG_MD_FAULTY=m -CONFIG_BLK_DEV_DM=m -CONFIG_DM_CRYPT=m -CONFIG_DM_SNAPSHOT=m -CONFIG_DM_MIRROR=m -CONFIG_DM_ZERO=m -CONFIG_DM_MULTIPATH=m -CONFIG_DM_MULTIPATH_EMC=m - -# -# Fusion MPT device support -# -CONFIG_FUSION=m -CONFIG_FUSION_MAX_SGE=40 -CONFIG_FUSION_CTL=m -CONFIG_FUSION_LAN=m - -# -# IEEE 1394 (FireWire) support -# -CONFIG_IEEE1394=m - -# -# Subsystem Options -# -# CONFIG_IEEE1394_VERBOSEDEBUG is not set -# CONFIG_IEEE1394_OUI_DB is not set -CONFIG_IEEE1394_EXTRA_CONFIG_ROMS=y -CONFIG_IEEE1394_CONFIG_ROM_IP1394=y - -# -# Device Drivers -# -CONFIG_IEEE1394_PCILYNX=m -CONFIG_IEEE1394_OHCI1394=m - -# -# Protocol Drivers -# -CONFIG_IEEE1394_VIDEO1394=m -CONFIG_IEEE1394_SBP2=m -# CONFIG_IEEE1394_SBP2_PHYS_DMA is not set -CONFIG_IEEE1394_ETH1394=m -CONFIG_IEEE1394_DV1394=m -CONFIG_IEEE1394_RAWIO=m -CONFIG_IEEE1394_CMP=m -CONFIG_IEEE1394_AMDTP=m - -# -# I2O device support -# -CONFIG_I2O=m -CONFIG_I2O_CONFIG=m -CONFIG_I2O_BLOCK=m -CONFIG_I2O_SCSI=m -CONFIG_I2O_PROC=m - -# -# Networking support -# -CONFIG_NET=y - -# -# Networking options -# -CONFIG_PACKET=m -CONFIG_PACKET_MMAP=y -CONFIG_UNIX=m -CONFIG_NET_KEY=m -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_ADVANCED_ROUTER=y -CONFIG_IP_MULTIPLE_TABLES=y -CONFIG_IP_ROUTE_FWMARK=y -CONFIG_IP_ROUTE_MULTIPATH=y -# CONFIG_IP_ROUTE_MULTIPATH_CACHED is not set -CONFIG_IP_ROUTE_VERBOSE=y -# CONFIG_IP_PNP is not set -CONFIG_NET_IPIP=m -CONFIG_NET_IPGRE=m -CONFIG_NET_IPGRE_BROADCAST=y -CONFIG_IP_MROUTE=y -CONFIG_IP_PIMSM_V1=y -CONFIG_IP_PIMSM_V2=y -# CONFIG_ARPD is not set -CONFIG_SYN_COOKIES=y -CONFIG_INET_AH=m -CONFIG_INET_ESP=m -CONFIG_INET_IPCOMP=m -CONFIG_INET_TUNNEL=m -CONFIG_IP_TCPDIAG=m -CONFIG_IP_TCPDIAG_IPV6=y - -# -# IP: Virtual Server Configuration -# -CONFIG_IP_VS=m -# CONFIG_IP_VS_DEBUG is not set -CONFIG_IP_VS_TAB_BITS=12 - -# -# IPVS transport protocol load balancing support -# -CONFIG_IP_VS_PROTO_TCP=y -CONFIG_IP_VS_PROTO_UDP=y -CONFIG_IP_VS_PROTO_ESP=y -CONFIG_IP_VS_PROTO_AH=y - -# -# IPVS scheduler -# -CONFIG_IP_VS_RR=m -CONFIG_IP_VS_WRR=m -CONFIG_IP_VS_LC=m -CONFIG_IP_VS_WLC=m -CONFIG_IP_VS_LBLC=m -CONFIG_IP_VS_LBLCR=m -CONFIG_IP_VS_DH=m -CONFIG_IP_VS_SH=m -CONFIG_IP_VS_SED=m -CONFIG_IP_VS_NQ=m - -# -# IPVS application helper -# -CONFIG_IP_VS_FTP=m -CONFIG_IPV6=m -CONFIG_IPV6_PRIVACY=y -CONFIG_INET6_AH=m -CONFIG_INET6_ESP=m -CONFIG_INET6_IPCOMP=m -CONFIG_INET6_TUNNEL=m -CONFIG_IPV6_TUNNEL=m -CONFIG_NETFILTER=y -# CONFIG_NETFILTER_DEBUG is not set -CONFIG_BRIDGE_NETFILTER=y - -# -# IP: Netfilter Configuration -# -CONFIG_IP_NF_CONNTRACK=m -CONFIG_IP_NF_CT_ACCT=y -CONFIG_IP_NF_CONNTRACK_MARK=y -CONFIG_IP_NF_CT_PROTO_SCTP=m -CONFIG_IP_NF_FTP=m -CONFIG_IP_NF_IRC=m -CONFIG_IP_NF_TFTP=m -CONFIG_IP_NF_AMANDA=m -CONFIG_IP_NF_QUEUE=m -CONFIG_IP_NF_IPTABLES=m -CONFIG_IP_NF_MATCH_LIMIT=m -CONFIG_IP_NF_MATCH_IPRANGE=m -CONFIG_IP_NF_MATCH_MAC=m -CONFIG_IP_NF_MATCH_PKTTYPE=m -CONFIG_IP_NF_MATCH_MARK=m -CONFIG_IP_NF_MATCH_MULTIPORT=m -CONFIG_IP_NF_MATCH_TOS=m -CONFIG_IP_NF_MATCH_RECENT=m -CONFIG_IP_NF_MATCH_ECN=m -CONFIG_IP_NF_MATCH_DSCP=m -CONFIG_IP_NF_MATCH_AH_ESP=m -CONFIG_IP_NF_MATCH_LENGTH=m -CONFIG_IP_NF_MATCH_TTL=m -CONFIG_IP_NF_MATCH_TCPMSS=m -CONFIG_IP_NF_MATCH_HELPER=m -CONFIG_IP_NF_MATCH_STATE=m -CONFIG_IP_NF_MATCH_CONNTRACK=m -CONFIG_IP_NF_MATCH_OWNER=m -CONFIG_IP_NF_MATCH_PHYSDEV=m -CONFIG_IP_NF_MATCH_ADDRTYPE=m -CONFIG_IP_NF_MATCH_REALM=m -CONFIG_IP_NF_MATCH_SCTP=m -CONFIG_IP_NF_MATCH_COMMENT=m -CONFIG_IP_NF_MATCH_CONNMARK=m -CONFIG_IP_NF_MATCH_HASHLIMIT=m -CONFIG_IP_NF_FILTER=m -CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m -CONFIG_IP_NF_TARGET_TCPMSS=m -CONFIG_IP_NF_NAT=m -CONFIG_IP_NF_NAT_NEEDED=y -CONFIG_IP_NF_TARGET_MASQUERADE=m -CONFIG_IP_NF_TARGET_REDIRECT=m -CONFIG_IP_NF_TARGET_NETMAP=m -CONFIG_IP_NF_TARGET_SAME=m -CONFIG_IP_NF_NAT_SNMP_BASIC=m -CONFIG_IP_NF_NAT_IRC=m -CONFIG_IP_NF_NAT_FTP=m -CONFIG_IP_NF_NAT_TFTP=m -CONFIG_IP_NF_NAT_AMANDA=m -CONFIG_IP_NF_MANGLE=m -CONFIG_IP_NF_TARGET_TOS=m -CONFIG_IP_NF_TARGET_ECN=m -CONFIG_IP_NF_TARGET_DSCP=m -CONFIG_IP_NF_TARGET_MARK=m -CONFIG_IP_NF_TARGET_CLASSIFY=m -CONFIG_IP_NF_TARGET_CONNMARK=m -CONFIG_IP_NF_TARGET_CLUSTERIP=m -CONFIG_IP_NF_RAW=m -CONFIG_IP_NF_TARGET_NOTRACK=m -CONFIG_IP_NF_ARPTABLES=m -CONFIG_IP_NF_ARPFILTER=m -CONFIG_IP_NF_ARP_MANGLE=m - -# -# IPv6: Netfilter Configuration (EXPERIMENTAL) -# -CONFIG_IP6_NF_QUEUE=m -CONFIG_IP6_NF_IPTABLES=m -CONFIG_IP6_NF_MATCH_LIMIT=m -CONFIG_IP6_NF_MATCH_MAC=m -CONFIG_IP6_NF_MATCH_RT=m -CONFIG_IP6_NF_MATCH_OPTS=m -CONFIG_IP6_NF_MATCH_FRAG=m -CONFIG_IP6_NF_MATCH_HL=m -CONFIG_IP6_NF_MATCH_MULTIPORT=m -CONFIG_IP6_NF_MATCH_OWNER=m -CONFIG_IP6_NF_MATCH_MARK=m -CONFIG_IP6_NF_MATCH_IPV6HEADER=m -CONFIG_IP6_NF_MATCH_AHESP=m -CONFIG_IP6_NF_MATCH_LENGTH=m -CONFIG_IP6_NF_MATCH_EUI64=m -CONFIG_IP6_NF_MATCH_PHYSDEV=m -CONFIG_IP6_NF_FILTER=m -CONFIG_IP6_NF_TARGET_LOG=m -CONFIG_IP6_NF_MANGLE=m -CONFIG_IP6_NF_TARGET_MARK=m -CONFIG_IP6_NF_RAW=m - -# -# DECnet: Netfilter Configuration -# -CONFIG_DECNET_NF_GRABULATOR=m - -# -# Bridge: Netfilter Configuration -# -CONFIG_BRIDGE_NF_EBTABLES=m -CONFIG_BRIDGE_EBT_BROUTE=m -CONFIG_BRIDGE_EBT_T_FILTER=m -CONFIG_BRIDGE_EBT_T_NAT=m -CONFIG_BRIDGE_EBT_802_3=m -CONFIG_BRIDGE_EBT_AMONG=m -CONFIG_BRIDGE_EBT_ARP=m -CONFIG_BRIDGE_EBT_IP=m -CONFIG_BRIDGE_EBT_LIMIT=m -CONFIG_BRIDGE_EBT_MARK=m -CONFIG_BRIDGE_EBT_PKTTYPE=m -CONFIG_BRIDGE_EBT_STP=m -CONFIG_BRIDGE_EBT_VLAN=m -CONFIG_BRIDGE_EBT_ARPREPLY=m -CONFIG_BRIDGE_EBT_DNAT=m -CONFIG_BRIDGE_EBT_MARK_T=m -CONFIG_BRIDGE_EBT_REDIRECT=m -CONFIG_BRIDGE_EBT_SNAT=m -CONFIG_BRIDGE_EBT_LOG=m -# CONFIG_BRIDGE_EBT_ULOG is not set -CONFIG_XFRM=y -CONFIG_XFRM_USER=m - -# -# SCTP Configuration (EXPERIMENTAL) -# -CONFIG_IP_SCTP=m -# CONFIG_SCTP_DBG_MSG is not set -# CONFIG_SCTP_DBG_OBJCNT is not set -# CONFIG_SCTP_HMAC_NONE is not set -# CONFIG_SCTP_HMAC_SHA1 is not set -CONFIG_SCTP_HMAC_MD5=y -CONFIG_ATM=y -CONFIG_ATM_CLIP=y -# CONFIG_ATM_CLIP_NO_ICMP is not set -CONFIG_ATM_LANE=m -CONFIG_ATM_MPOA=m -CONFIG_ATM_BR2684=m -# CONFIG_ATM_BR2684_IPFILTER is not set -CONFIG_BRIDGE=m -CONFIG_VLAN_8021Q=m -CONFIG_DECNET=m -# CONFIG_DECNET_ROUTER is not set -CONFIG_LLC=y -CONFIG_LLC2=m -CONFIG_IPX=m -# CONFIG_IPX_INTERN is not set -CONFIG_ATALK=m -CONFIG_DEV_APPLETALK=y -CONFIG_LTPC=m -CONFIG_COPS=m -CONFIG_COPS_DAYNA=y -CONFIG_COPS_TANGENT=y -CONFIG_IPDDP=m -CONFIG_IPDDP_ENCAP=y -CONFIG_IPDDP_DECAP=y -CONFIG_X25=m -CONFIG_LAPB=m -# CONFIG_NET_DIVERT is not set -CONFIG_ECONET=m -CONFIG_ECONET_AUNUDP=y -CONFIG_ECONET_NATIVE=y -CONFIG_WAN_ROUTER=m - -# -# QoS and/or fair queueing -# -CONFIG_NET_SCHED=y -CONFIG_NET_SCH_CLK_JIFFIES=y -# CONFIG_NET_SCH_CLK_GETTIMEOFDAY is not set -# CONFIG_NET_SCH_CLK_CPU is not set -CONFIG_NET_SCH_CBQ=m -CONFIG_NET_SCH_HTB=m -CONFIG_NET_SCH_HFSC=m -CONFIG_NET_SCH_ATM=m -CONFIG_NET_SCH_PRIO=m -CONFIG_NET_SCH_RED=m -CONFIG_NET_SCH_SFQ=m -CONFIG_NET_SCH_TEQL=m -CONFIG_NET_SCH_TBF=m -CONFIG_NET_SCH_GRED=m -CONFIG_NET_SCH_DSMARK=m -CONFIG_NET_SCH_NETEM=m -CONFIG_NET_SCH_INGRESS=m -CONFIG_NET_QOS=y -CONFIG_NET_ESTIMATOR=y -CONFIG_NET_CLS=y -CONFIG_NET_CLS_BASIC=m -CONFIG_NET_CLS_TCINDEX=m -CONFIG_NET_CLS_ROUTE4=m -CONFIG_NET_CLS_ROUTE=y -CONFIG_NET_CLS_FW=m -CONFIG_NET_CLS_U32=m -# CONFIG_CLS_U32_PERF is not set -# CONFIG_NET_CLS_IND is not set -# CONFIG_CLS_U32_MARK is not set -CONFIG_NET_CLS_RSVP=m -CONFIG_NET_CLS_RSVP6=m -CONFIG_NET_EMATCH=y -CONFIG_NET_EMATCH_STACK=32 -CONFIG_NET_EMATCH_CMP=m -CONFIG_NET_EMATCH_NBYTE=m -CONFIG_NET_EMATCH_U32=m -CONFIG_NET_EMATCH_META=m -# CONFIG_NET_CLS_ACT is not set -CONFIG_NET_CLS_POLICE=y - -# -# Network testing -# -CONFIG_NET_PKTGEN=m -CONFIG_NETPOLL=y -# CONFIG_NETPOLL_RX is not set -# CONFIG_NETPOLL_TRAP is not set -CONFIG_NET_POLL_CONTROLLER=y -CONFIG_HAMRADIO=y - -# -# Packet Radio protocols -# -CONFIG_AX25=m -# CONFIG_AX25_DAMA_SLAVE is not set -CONFIG_NETROM=m -CONFIG_ROSE=m - -# -# AX.25 network device drivers -# -CONFIG_MKISS=m -CONFIG_6PACK=m -CONFIG_BPQETHER=m -# CONFIG_DMASCC is not set -CONFIG_SCC=m -# CONFIG_SCC_DELAY is not set -# CONFIG_SCC_TRXECHO is not set -CONFIG_BAYCOM_SER_FDX=m -CONFIG_BAYCOM_SER_HDX=m -CONFIG_BAYCOM_PAR=m -CONFIG_BAYCOM_EPP=m -CONFIG_YAM=m -CONFIG_IRDA=m - -# -# IrDA protocols -# -CONFIG_IRLAN=m -CONFIG_IRNET=m -CONFIG_IRCOMM=m -# CONFIG_IRDA_ULTRA is not set - -# -# IrDA options -# -CONFIG_IRDA_CACHE_LAST_LSAP=y -CONFIG_IRDA_FAST_RR=y -CONFIG_IRDA_DEBUG=y - -# -# Infrared-port device drivers -# - -# -# SIR device drivers -# -CONFIG_IRTTY_SIR=m - -# -# Dongle support -# -CONFIG_DONGLE=y -CONFIG_ESI_DONGLE=m -CONFIG_ACTISYS_DONGLE=m -CONFIG_TEKRAM_DONGLE=m -CONFIG_LITELINK_DONGLE=m -CONFIG_MA600_DONGLE=m -CONFIG_GIRBIL_DONGLE=m -CONFIG_MCP2120_DONGLE=m -CONFIG_OLD_BELKIN_DONGLE=m -CONFIG_ACT200L_DONGLE=m - -# -# Old SIR device drivers -# -CONFIG_IRPORT_SIR=m - -# -# Old Serial dongle support -# -# CONFIG_DONGLE_OLD is not set - -# -# FIR device drivers -# -CONFIG_USB_IRDA=m -CONFIG_SIGMATEL_FIR=m -CONFIG_NSC_FIR=m -CONFIG_WINBOND_FIR=m -# CONFIG_TOSHIBA_FIR is not set -CONFIG_SMC_IRCC_FIR=m -CONFIG_ALI_FIR=m -CONFIG_VLSI_FIR=m -CONFIG_VIA_FIR=m -CONFIG_BT=m -CONFIG_BT_L2CAP=m -CONFIG_BT_SCO=m -CONFIG_BT_RFCOMM=m -CONFIG_BT_RFCOMM_TTY=y -CONFIG_BT_BNEP=m -CONFIG_BT_BNEP_MC_FILTER=y -CONFIG_BT_BNEP_PROTO_FILTER=y -CONFIG_BT_CMTP=m -CONFIG_BT_HIDP=m - -# -# Bluetooth device drivers -# -CONFIG_BT_HCIUSB=m -CONFIG_BT_HCIUSB_SCO=y -CONFIG_BT_HCIUART=m -CONFIG_BT_HCIUART_H4=y -CONFIG_BT_HCIUART_BCSP=y -# CONFIG_BT_HCIUART_BCSP_TXCRC is not set -CONFIG_BT_HCIBCM203X=m -# CONFIG_BT_HCIBPA10X is not set -CONFIG_BT_HCIBFUSB=m -CONFIG_BT_HCIDTL1=m -CONFIG_BT_HCIBT3C=m -CONFIG_BT_HCIBLUECARD=m -CONFIG_BT_HCIBTUART=m -CONFIG_BT_HCIVHCI=m -CONFIG_NETDEVICES=y -CONFIG_DUMMY=m -CONFIG_BONDING=m -CONFIG_EQUALIZER=m -CONFIG_TUN=m -CONFIG_NET_SB1000=m - -# -# ARCnet devices -# -CONFIG_ARCNET=m -CONFIG_ARCNET_1201=m -CONFIG_ARCNET_1051=m -CONFIG_ARCNET_RAW=m -# CONFIG_ARCNET_CAP is not set -CONFIG_ARCNET_COM90xx=m -CONFIG_ARCNET_COM90xxIO=m -CONFIG_ARCNET_RIM_I=m -CONFIG_ARCNET_COM20020=m -CONFIG_ARCNET_COM20020_ISA=m -CONFIG_ARCNET_COM20020_PCI=m - -# -# Ethernet (10 or 100Mbit) -# -CONFIG_NET_ETHERNET=y -CONFIG_MII=m -CONFIG_HAPPYMEAL=m -CONFIG_SUNGEM=m -CONFIG_NET_VENDOR_3COM=y -CONFIG_EL1=m -CONFIG_EL2=m -# CONFIG_ELPLUS is not set -CONFIG_EL16=m -CONFIG_EL3=m -# CONFIG_3C515 is not set -CONFIG_VORTEX=m -CONFIG_TYPHOON=m -# CONFIG_LANCE is not set -CONFIG_NET_VENDOR_SMC=y -CONFIG_WD80x3=m -CONFIG_ULTRA=m -CONFIG_SMC9194=m -CONFIG_NET_VENDOR_RACAL=y -CONFIG_NI5010=m -CONFIG_NI52=m -# CONFIG_NI65 is not set - -# -# Tulip family network device support -# -CONFIG_NET_TULIP=y -CONFIG_DE2104X=m -CONFIG_TULIP=m -# CONFIG_TULIP_MWI is not set -# CONFIG_TULIP_MMIO is not set -# CONFIG_TULIP_NAPI is not set -CONFIG_DE4X5=m -CONFIG_WINBOND_840=m -CONFIG_DM9102=m -CONFIG_PCMCIA_XIRCOM=m -# CONFIG_PCMCIA_XIRTULIP is not set -CONFIG_AT1700=m -CONFIG_DEPCA=m -CONFIG_HP100=m -CONFIG_NET_ISA=y -CONFIG_E2100=m -CONFIG_EWRK3=m -CONFIG_EEXPRESS=m -CONFIG_EEXPRESS_PRO=m -CONFIG_HPLAN_PLUS=m -CONFIG_HPLAN=m -CONFIG_LP486E=m -CONFIG_ETH16I=m -CONFIG_NE2000=m -CONFIG_ZNET=m -CONFIG_SEEQ8005=m -CONFIG_NET_PCI=y -CONFIG_PCNET32=m -CONFIG_AMD8111_ETH=m -# CONFIG_AMD8111E_NAPI is not set -CONFIG_ADAPTEC_STARFIRE=m -# CONFIG_ADAPTEC_STARFIRE_NAPI is not set -CONFIG_AC3200=m -CONFIG_APRICOT=m -CONFIG_B44=m -CONFIG_FORCEDETH=m -CONFIG_CS89x0=m -# CONFIG_DGRS is not set -CONFIG_EEPRO100=m -CONFIG_E100=m -CONFIG_FEALNX=m -CONFIG_NATSEMI=m -CONFIG_NE2K_PCI=m -CONFIG_8139CP=m -CONFIG_8139TOO=m -CONFIG_8139TOO_PIO=y -CONFIG_8139TOO_TUNE_TWISTER=y -CONFIG_8139TOO_8129=y -# CONFIG_8139_OLD_RX_RESET is not set -CONFIG_SIS900=m -CONFIG_EPIC100=m -CONFIG_SUNDANCE=m -# CONFIG_SUNDANCE_MMIO is not set -CONFIG_TLAN=m -CONFIG_VIA_RHINE=m -# CONFIG_VIA_RHINE_MMIO is not set -CONFIG_NET_POCKET=y -CONFIG_ATP=m -CONFIG_DE600=m -CONFIG_DE620=m - -# -# Ethernet (1000 Mbit) -# -# CONFIG_ACENIC is not set -CONFIG_DL2K=m -CONFIG_E1000=m -# CONFIG_E1000_NAPI is not set -CONFIG_NS83820=m -CONFIG_HAMACHI=m -CONFIG_YELLOWFIN=m -CONFIG_R8169=m -# CONFIG_R8169_NAPI is not set -# CONFIG_R8169_VLAN is not set -CONFIG_SK98LIN=m -CONFIG_VIA_VELOCITY=m -CONFIG_TIGON3=m -CONFIG_BNX2=m - -# -# Ethernet (10000 Mbit) -# -CONFIG_IXGB=m -# CONFIG_IXGB_NAPI is not set -CONFIG_S2IO=m -# CONFIG_S2IO_NAPI is not set -# CONFIG_2BUFF_MODE is not set - -# -# Token Ring devices -# -CONFIG_TR=y -CONFIG_IBMTR=m -CONFIG_IBMOL=m -CONFIG_IBMLS=m -CONFIG_3C359=m -CONFIG_TMS380TR=m -CONFIG_TMSPCI=m -CONFIG_SKISA=m -CONFIG_PROTEON=m -CONFIG_ABYSS=m -# CONFIG_SMCTR is not set - -# -# Wireless LAN (non-hamradio) -# -CONFIG_NET_RADIO=y - -# -# Obsolete Wireless cards support (pre-802.11) -# -CONFIG_STRIP=m -CONFIG_ARLAN=m -CONFIG_WAVELAN=m -CONFIG_PCMCIA_WAVELAN=m -CONFIG_PCMCIA_NETWAVE=m - -# -# Wireless 802.11 Frequency Hopping cards support -# -CONFIG_PCMCIA_RAYCS=m - -# -# Wireless 802.11b ISA/PCI cards support -# -CONFIG_AIRO=m -CONFIG_HERMES=m -CONFIG_PLX_HERMES=m -CONFIG_TMD_HERMES=m -CONFIG_PCI_HERMES=m -CONFIG_ATMEL=m -CONFIG_PCI_ATMEL=m - -# -# Wireless 802.11b Pcmcia/Cardbus cards support -# -CONFIG_PCMCIA_HERMES=m -CONFIG_AIRO_CS=m -CONFIG_PCMCIA_ATMEL=m -CONFIG_PCMCIA_WL3501=m - -# -# Prism GT/Duette 802.11(a/b/g) PCI/Cardbus support -# -CONFIG_PRISM54=m -CONFIG_NET_WIRELESS=y - -# -# PCMCIA network device support -# -CONFIG_NET_PCMCIA=y -CONFIG_PCMCIA_3C589=m -CONFIG_PCMCIA_3C574=m -CONFIG_PCMCIA_FMVJ18X=m -CONFIG_PCMCIA_PCNET=m -CONFIG_PCMCIA_NMCLAN=m -CONFIG_PCMCIA_SMC91C92=m -CONFIG_PCMCIA_XIRC2PS=m -CONFIG_PCMCIA_AXNET=m -CONFIG_ARCNET_COM20020_CS=m -CONFIG_PCMCIA_IBMTR=m - -# -# Wan interfaces -# -CONFIG_WAN=y -CONFIG_HOSTESS_SV11=m -CONFIG_COSA=m -CONFIG_DSCC4=m -CONFIG_DSCC4_PCISYNC=y -CONFIG_DSCC4_PCI_RST=y -CONFIG_LANMEDIA=m -CONFIG_SEALEVEL_4021=m -CONFIG_SYNCLINK_SYNCPPP=m -CONFIG_HDLC=m -CONFIG_HDLC_RAW=y -CONFIG_HDLC_RAW_ETH=y -CONFIG_HDLC_CISCO=y -CONFIG_HDLC_FR=y -CONFIG_HDLC_PPP=y -CONFIG_HDLC_X25=y -CONFIG_PCI200SYN=m -CONFIG_WANXL=m -CONFIG_PC300=m -CONFIG_PC300_MLPPP=y -CONFIG_N2=m -CONFIG_C101=m -CONFIG_FARSYNC=m -CONFIG_DLCI=m -CONFIG_DLCI_COUNT=24 -CONFIG_DLCI_MAX=8 -CONFIG_SDLA=m -CONFIG_WAN_ROUTER_DRIVERS=y -# CONFIG_VENDOR_SANGOMA is not set -CONFIG_CYCLADES_SYNC=m -CONFIG_CYCLOMX_X25=y -CONFIG_LAPBETHER=m -CONFIG_X25_ASY=m -CONFIG_SBNI=m -# CONFIG_SBNI_MULTILINE is not set - -# -# ATM drivers -# -CONFIG_ATM_TCP=m -CONFIG_ATM_LANAI=m -CONFIG_ATM_ENI=m -# CONFIG_ATM_ENI_DEBUG is not set -# CONFIG_ATM_ENI_TUNE_BURST is not set -CONFIG_ATM_FIRESTREAM=m -CONFIG_ATM_ZATM=m -# CONFIG_ATM_ZATM_DEBUG is not set -CONFIG_ATM_NICSTAR=m -# CONFIG_ATM_NICSTAR_USE_SUNI is not set -# CONFIG_ATM_NICSTAR_USE_IDT77105 is not set -CONFIG_ATM_IDT77252=m -# CONFIG_ATM_IDT77252_DEBUG is not set -# CONFIG_ATM_IDT77252_RCV_ALL is not set -CONFIG_ATM_IDT77252_USE_SUNI=y -CONFIG_ATM_AMBASSADOR=m -# CONFIG_ATM_AMBASSADOR_DEBUG is not set -CONFIG_ATM_HORIZON=m -# CONFIG_ATM_HORIZON_DEBUG is not set -CONFIG_ATM_IA=m -# CONFIG_ATM_IA_DEBUG is not set -CONFIG_ATM_FORE200E_MAYBE=m -CONFIG_ATM_FORE200E_PCA=y -CONFIG_ATM_FORE200E_PCA_DEFAULT_FW=y -# CONFIG_ATM_FORE200E_USE_TASKLET is not set -CONFIG_ATM_FORE200E_TX_RETRY=16 -CONFIG_ATM_FORE200E_DEBUG=0 -CONFIG_ATM_FORE200E=m -CONFIG_ATM_HE=m -CONFIG_ATM_HE_USE_SUNI=y -CONFIG_FDDI=y -CONFIG_DEFXX=m -CONFIG_SKFP=m -CONFIG_HIPPI=y -CONFIG_ROADRUNNER=m -# CONFIG_ROADRUNNER_LARGE_RINGS is not set -CONFIG_PLIP=m -CONFIG_PPP=m -CONFIG_PPP_MULTILINK=y -CONFIG_PPP_FILTER=y -CONFIG_PPP_ASYNC=m -CONFIG_PPP_SYNC_TTY=m -CONFIG_PPP_DEFLATE=m -CONFIG_PPP_BSDCOMP=m -CONFIG_PPPOE=m -CONFIG_PPPOATM=m -CONFIG_SLIP=m -CONFIG_SLIP_COMPRESSED=y -CONFIG_SLIP_SMART=y -CONFIG_SLIP_MODE_SLIP6=y -CONFIG_NET_FC=y -CONFIG_SHAPER=m -CONFIG_NETCONSOLE=m - -# -# ISDN subsystem -# -CONFIG_ISDN=m - -# -# Old ISDN4Linux -# -CONFIG_ISDN_I4L=m -CONFIG_ISDN_PPP=y -CONFIG_ISDN_PPP_VJ=y -CONFIG_ISDN_MPP=y -CONFIG_IPPP_FILTER=y -CONFIG_ISDN_PPP_BSDCOMP=m -CONFIG_ISDN_AUDIO=y -CONFIG_ISDN_TTY_FAX=y -CONFIG_ISDN_X25=y - -# -# ISDN feature submodules -# -# CONFIG_ISDN_DRV_LOOP is not set -# CONFIG_ISDN_DIVERSION is not set - -# -# ISDN4Linux hardware drivers -# - -# -# Passive cards -# -CONFIG_ISDN_DRV_HISAX=m - -# -# D-channel protocol features -# -CONFIG_HISAX_EURO=y -CONFIG_DE_AOC=y -# CONFIG_HISAX_NO_SENDCOMPLETE is not set -# CONFIG_HISAX_NO_LLC is not set -# CONFIG_HISAX_NO_KEYPAD is not set -CONFIG_HISAX_1TR6=y -CONFIG_HISAX_NI1=y -CONFIG_HISAX_MAX_CARDS=8 - -# -# HiSax supported cards -# -CONFIG_HISAX_16_0=y -CONFIG_HISAX_16_3=y -CONFIG_HISAX_TELESPCI=y -CONFIG_HISAX_S0BOX=y -CONFIG_HISAX_AVM_A1=y -CONFIG_HISAX_FRITZPCI=y -CONFIG_HISAX_AVM_A1_PCMCIA=y -CONFIG_HISAX_ELSA=y -CONFIG_HISAX_IX1MICROR2=y -CONFIG_HISAX_DIEHLDIVA=y -CONFIG_HISAX_ASUSCOM=y -CONFIG_HISAX_TELEINT=y -CONFIG_HISAX_HFCS=y -CONFIG_HISAX_SEDLBAUER=y -CONFIG_HISAX_SPORTSTER=y -CONFIG_HISAX_MIC=y -CONFIG_HISAX_NETJET=y -CONFIG_HISAX_NETJET_U=y -CONFIG_HISAX_NICCY=y -CONFIG_HISAX_ISURF=y -CONFIG_HISAX_HSTSAPHIR=y -CONFIG_HISAX_BKM_A4T=y -CONFIG_HISAX_SCT_QUADRO=y -CONFIG_HISAX_GAZEL=y -CONFIG_HISAX_HFC_PCI=y -CONFIG_HISAX_W6692=y -CONFIG_HISAX_HFC_SX=y -CONFIG_HISAX_ENTERNOW_PCI=y -# CONFIG_HISAX_DEBUG is not set - -# -# HiSax PCMCIA card service modules -# -CONFIG_HISAX_SEDLBAUER_CS=m -CONFIG_HISAX_ELSA_CS=m -CONFIG_HISAX_AVM_A1_CS=m -CONFIG_HISAX_TELES_CS=m - -# -# HiSax sub driver modules -# -CONFIG_HISAX_ST5481=m -CONFIG_HISAX_HFCUSB=m -CONFIG_HISAX_HFC4S8S=m -CONFIG_HISAX_FRITZ_PCIPNP=m -CONFIG_HISAX_HDLC=y - -# -# Active cards -# -CONFIG_ISDN_DRV_ICN=m -CONFIG_ISDN_DRV_PCBIT=m -CONFIG_ISDN_DRV_SC=m -CONFIG_ISDN_DRV_ACT2000=m -# CONFIG_HYSDN is not set - -# -# CAPI subsystem -# -CONFIG_ISDN_CAPI=m -CONFIG_ISDN_DRV_AVMB1_VERBOSE_REASON=y -CONFIG_ISDN_CAPI_MIDDLEWARE=y -CONFIG_ISDN_CAPI_CAPI20=m -CONFIG_ISDN_CAPI_CAPIFS_BOOL=y -CONFIG_ISDN_CAPI_CAPIFS=m -CONFIG_ISDN_CAPI_CAPIDRV=m - -# -# CAPI hardware drivers -# - -# -# Active AVM cards -# -CONFIG_CAPI_AVM=y -CONFIG_ISDN_DRV_AVMB1_B1ISA=m -CONFIG_ISDN_DRV_AVMB1_B1PCI=m -CONFIG_ISDN_DRV_AVMB1_B1PCIV4=y -CONFIG_ISDN_DRV_AVMB1_T1ISA=m -CONFIG_ISDN_DRV_AVMB1_B1PCMCIA=m -CONFIG_ISDN_DRV_AVMB1_AVM_CS=m -CONFIG_ISDN_DRV_AVMB1_T1PCI=m -CONFIG_ISDN_DRV_AVMB1_C4=m - -# -# Active Eicon DIVA Server cards -# -CONFIG_CAPI_EICON=y -CONFIG_ISDN_DIVAS=m -CONFIG_ISDN_DIVAS_BRIPCI=y -CONFIG_ISDN_DIVAS_PRIPCI=y -CONFIG_ISDN_DIVAS_DIVACAPI=m -CONFIG_ISDN_DIVAS_USERIDI=m -CONFIG_ISDN_DIVAS_MAINT=m - -# -# Telephony Support -# -CONFIG_PHONE=m -CONFIG_PHONE_IXJ=m -CONFIG_PHONE_IXJ_PCMCIA=m - -# -# Input device support -# -CONFIG_INPUT=y - -# -# Userland interfaces -# -CONFIG_INPUT_MOUSEDEV=y -CONFIG_INPUT_MOUSEDEV_PSAUX=y -CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024 -CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 -CONFIG_INPUT_JOYDEV=m -CONFIG_INPUT_TSDEV=m -CONFIG_INPUT_TSDEV_SCREEN_X=240 -CONFIG_INPUT_TSDEV_SCREEN_Y=320 -CONFIG_INPUT_EVDEV=m -CONFIG_INPUT_EVBUG=m - -# -# Input Device Drivers -# -CONFIG_INPUT_KEYBOARD=y -CONFIG_KEYBOARD_ATKBD=y -CONFIG_KEYBOARD_SUNKBD=m -CONFIG_KEYBOARD_LKKBD=m -CONFIG_KEYBOARD_XTKBD=m -CONFIG_KEYBOARD_NEWTON=m -CONFIG_INPUT_MOUSE=y -CONFIG_MOUSE_PS2=y -CONFIG_MOUSE_SERIAL=m -CONFIG_MOUSE_INPORT=m -# CONFIG_MOUSE_ATIXL is not set -CONFIG_MOUSE_LOGIBM=m -CONFIG_MOUSE_PC110PAD=m -CONFIG_MOUSE_VSXXXAA=m -CONFIG_INPUT_JOYSTICK=y -CONFIG_JOYSTICK_ANALOG=m -CONFIG_JOYSTICK_A3D=m -CONFIG_JOYSTICK_ADI=m -CONFIG_JOYSTICK_COBRA=m -CONFIG_JOYSTICK_GF2K=m -CONFIG_JOYSTICK_GRIP=m -CONFIG_JOYSTICK_GRIP_MP=m -CONFIG_JOYSTICK_GUILLEMOT=m -CONFIG_JOYSTICK_INTERACT=m -CONFIG_JOYSTICK_SIDEWINDER=m -CONFIG_JOYSTICK_TMDC=m -CONFIG_JOYSTICK_IFORCE=m -CONFIG_JOYSTICK_IFORCE_USB=y -CONFIG_JOYSTICK_IFORCE_232=y -CONFIG_JOYSTICK_WARRIOR=m -CONFIG_JOYSTICK_MAGELLAN=m -CONFIG_JOYSTICK_SPACEORB=m -CONFIG_JOYSTICK_SPACEBALL=m -CONFIG_JOYSTICK_STINGER=m -CONFIG_JOYSTICK_TWIDJOY=m -CONFIG_JOYSTICK_DB9=m -CONFIG_JOYSTICK_GAMECON=m -CONFIG_JOYSTICK_TURBOGRAFX=m -CONFIG_JOYSTICK_JOYDUMP=m -CONFIG_INPUT_TOUCHSCREEN=y -CONFIG_TOUCHSCREEN_GUNZE=m -CONFIG_TOUCHSCREEN_ELO=m -CONFIG_TOUCHSCREEN_MTOUCH=m -CONFIG_TOUCHSCREEN_MK712=m -CONFIG_INPUT_MISC=y -CONFIG_INPUT_PCSPKR=m -CONFIG_INPUT_UINPUT=m - -# -# Hardware I/O ports -# -CONFIG_SERIO=y -CONFIG_SERIO_I8042=y -CONFIG_SERIO_SERPORT=m -CONFIG_SERIO_CT82C710=m -CONFIG_SERIO_PARKBD=m -CONFIG_SERIO_PCIPS2=m -CONFIG_SERIO_LIBPS2=y -CONFIG_SERIO_RAW=m -CONFIG_GAMEPORT=m -CONFIG_GAMEPORT_NS558=m -CONFIG_GAMEPORT_L4=m -CONFIG_GAMEPORT_EMU10K1=m -CONFIG_GAMEPORT_VORTEX=m -CONFIG_GAMEPORT_FM801=m -# CONFIG_GAMEPORT_CS461X is not set - -# -# Character devices -# -CONFIG_VT=y -CONFIG_VT_CONSOLE=y -CONFIG_HW_CONSOLE=y -# CONFIG_SERIAL_NONSTANDARD is not set - -# -# Serial drivers -# -CONFIG_SERIAL_8250=m -# CONFIG_SERIAL_8250_CS is not set -# CONFIG_SERIAL_8250_ACPI is not set -CONFIG_SERIAL_8250_NR_UARTS=4 -# CONFIG_SERIAL_8250_EXTENDED is not set - -# -# Non-8250 serial port support -# -CONFIG_SERIAL_CORE=m -CONFIG_SERIAL_JSM=m -CONFIG_UNIX98_PTYS=y -CONFIG_LEGACY_PTYS=y -CONFIG_LEGACY_PTY_COUNT=256 -CONFIG_PRINTER=m -# CONFIG_LP_CONSOLE is not set -CONFIG_PPDEV=m -CONFIG_TIPAR=m - -# -# IPMI -# -CONFIG_IPMI_HANDLER=m -# CONFIG_IPMI_PANIC_EVENT is not set -CONFIG_IPMI_DEVICE_INTERFACE=m -CONFIG_IPMI_SI=m -CONFIG_IPMI_WATCHDOG=m -CONFIG_IPMI_POWEROFF=m - -# -# Watchdog Cards -# -CONFIG_WATCHDOG=y -# CONFIG_WATCHDOG_NOWAYOUT is not set - -# -# Watchdog Device Drivers -# -CONFIG_SOFT_WATCHDOG=m -CONFIG_ACQUIRE_WDT=m -CONFIG_ADVANTECH_WDT=m -CONFIG_ALIM1535_WDT=m -CONFIG_ALIM7101_WDT=m -CONFIG_SC520_WDT=m -CONFIG_EUROTECH_WDT=m -CONFIG_IB700_WDT=m -CONFIG_WAFER_WDT=m -CONFIG_I8XX_TCO=m -CONFIG_SC1200_WDT=m -CONFIG_SCx200_WDT=m -CONFIG_60XX_WDT=m -CONFIG_CPU5_WDT=m -CONFIG_W83627HF_WDT=m -CONFIG_W83877F_WDT=m -CONFIG_MACHZ_WDT=m - -# -# ISA-based Watchdog Cards -# -CONFIG_PCWATCHDOG=m -CONFIG_MIXCOMWD=m -CONFIG_WDT=m -CONFIG_WDT_501=y - -# -# PCI-based Watchdog Cards -# -CONFIG_PCIPCWATCHDOG=m -CONFIG_WDTPCI=m -CONFIG_WDT_501_PCI=y - -# -# USB-based Watchdog Cards -# -CONFIG_USBPCWATCHDOG=m -CONFIG_HW_RANDOM=m -CONFIG_NVRAM=m -CONFIG_RTC=m -CONFIG_GEN_RTC=m -CONFIG_GEN_RTC_X=y -CONFIG_DTLK=m -CONFIG_R3964=m -CONFIG_APPLICOM=m -CONFIG_SONYPI=m - -# -# Ftape, the floppy tape device driver -# -# CONFIG_FTAPE is not set -CONFIG_AGP=m -CONFIG_AGP_ALI=m -CONFIG_AGP_ATI=m -CONFIG_AGP_AMD=m -CONFIG_AGP_AMD64=m -CONFIG_AGP_INTEL=m -CONFIG_AGP_NVIDIA=m -CONFIG_AGP_SIS=m -CONFIG_AGP_SWORKS=m -CONFIG_AGP_VIA=m -CONFIG_AGP_EFFICEON=m -CONFIG_DRM=m -CONFIG_DRM_TDFX=m -# CONFIG_DRM_GAMMA is not set -CONFIG_DRM_R128=m -CONFIG_DRM_RADEON=m -CONFIG_DRM_I810=m -CONFIG_DRM_I830=m -CONFIG_DRM_I915=m -CONFIG_DRM_MGA=m -CONFIG_DRM_SIS=m - -# -# PCMCIA character devices -# -CONFIG_SYNCLINK_CS=m -CONFIG_MWAVE=m -CONFIG_SCx200_GPIO=m -CONFIG_RAW_DRIVER=m -# CONFIG_HPET is not set -CONFIG_MAX_RAW_DEVS=256 -CONFIG_HANGCHECK_TIMER=m - -# -# TPM devices -# -# CONFIG_TCG_TPM is not set - -# -# I2C support -# -CONFIG_I2C=m -CONFIG_I2C_CHARDEV=m - -# -# I2C Algorithms -# -CONFIG_I2C_ALGOBIT=m -CONFIG_I2C_ALGOPCF=m -CONFIG_I2C_ALGOPCA=m - -# -# I2C Hardware Bus support -# -CONFIG_I2C_ALI1535=m -CONFIG_I2C_ALI1563=m -CONFIG_I2C_ALI15X3=m -CONFIG_I2C_AMD756=m -CONFIG_I2C_AMD756_S4882=m -CONFIG_I2C_AMD8111=m -CONFIG_I2C_ELEKTOR=m -CONFIG_I2C_I801=m -CONFIG_I2C_I810=m -CONFIG_I2C_PIIX4=m -CONFIG_I2C_ISA=m -CONFIG_I2C_NFORCE2=m -CONFIG_I2C_PARPORT=m -CONFIG_I2C_PARPORT_LIGHT=m -CONFIG_I2C_PROSAVAGE=m -CONFIG_I2C_SAVAGE4=m -CONFIG_SCx200_I2C=m -CONFIG_SCx200_I2C_SCL=12 -CONFIG_SCx200_I2C_SDA=13 -CONFIG_SCx200_ACB=m -CONFIG_I2C_SIS5595=m -CONFIG_I2C_SIS630=m -CONFIG_I2C_SIS96X=m -CONFIG_I2C_STUB=m -CONFIG_I2C_VIA=m -CONFIG_I2C_VIAPRO=m -CONFIG_I2C_VOODOO3=m -CONFIG_I2C_PCA_ISA=m - -# -# Hardware Sensors Chip support -# -CONFIG_I2C_SENSOR=m -CONFIG_SENSORS_ADM1021=m -CONFIG_SENSORS_ADM1025=m -CONFIG_SENSORS_ADM1026=m -CONFIG_SENSORS_ADM1031=m -CONFIG_SENSORS_ASB100=m -CONFIG_SENSORS_DS1621=m -CONFIG_SENSORS_FSCHER=m -CONFIG_SENSORS_FSCPOS=m -CONFIG_SENSORS_GL518SM=m -CONFIG_SENSORS_GL520SM=m -CONFIG_SENSORS_IT87=m -CONFIG_SENSORS_LM63=m -CONFIG_SENSORS_LM75=m -CONFIG_SENSORS_LM77=m -CONFIG_SENSORS_LM78=m -CONFIG_SENSORS_LM80=m -CONFIG_SENSORS_LM83=m -CONFIG_SENSORS_LM85=m -CONFIG_SENSORS_LM87=m -CONFIG_SENSORS_LM90=m -CONFIG_SENSORS_LM92=m -CONFIG_SENSORS_MAX1619=m -CONFIG_SENSORS_PC87360=m -# CONFIG_SENSORS_SMSC47B397 is not set -CONFIG_SENSORS_SIS5595=m -CONFIG_SENSORS_SMSC47M1=m -CONFIG_SENSORS_VIA686A=m -CONFIG_SENSORS_W83781D=m -CONFIG_SENSORS_W83L785TS=m -CONFIG_SENSORS_W83627HF=m - -# -# Other I2C Chip support -# -CONFIG_SENSORS_DS1337=m -CONFIG_SENSORS_EEPROM=m -CONFIG_SENSORS_PCF8574=m -CONFIG_SENSORS_PCF8591=m -CONFIG_SENSORS_RTC8564=m -# CONFIG_I2C_DEBUG_CORE is not set -# CONFIG_I2C_DEBUG_ALGO is not set -# CONFIG_I2C_DEBUG_BUS is not set -# CONFIG_I2C_DEBUG_CHIP is not set - -# -# Dallas's 1-wire bus -# -CONFIG_W1=m -CONFIG_W1_MATROX=m -CONFIG_W1_DS9490=m -CONFIG_W1_DS9490_BRIDGE=m -CONFIG_W1_THERM=m -CONFIG_W1_SMEM=m - -# -# Misc devices -# -CONFIG_IBM_ASM=m - -# -# Multimedia devices -# -CONFIG_VIDEO_DEV=m - -# -# Video For Linux -# - -# -# Video Adapters -# -CONFIG_VIDEO_BT848=m -CONFIG_VIDEO_PMS=m -CONFIG_VIDEO_BWQCAM=m -CONFIG_VIDEO_CQCAM=m -CONFIG_VIDEO_W9966=m -CONFIG_VIDEO_CPIA=m -CONFIG_VIDEO_CPIA_PP=m -CONFIG_VIDEO_CPIA_USB=m -CONFIG_VIDEO_SAA5246A=m -CONFIG_VIDEO_SAA5249=m -CONFIG_TUNER_3036=m -CONFIG_VIDEO_STRADIS=m -CONFIG_VIDEO_ZORAN=m -CONFIG_VIDEO_ZORAN_BUZ=m -CONFIG_VIDEO_ZORAN_DC10=m -CONFIG_VIDEO_ZORAN_DC30=m -CONFIG_VIDEO_ZORAN_LML33=m -CONFIG_VIDEO_ZORAN_LML33R10=m -# CONFIG_VIDEO_ZR36120 is not set -CONFIG_VIDEO_MEYE=m -# CONFIG_VIDEO_SAA7134 is not set -CONFIG_VIDEO_MXB=m -CONFIG_VIDEO_DPC=m -CONFIG_VIDEO_HEXIUM_ORION=m -CONFIG_VIDEO_HEXIUM_GEMINI=m -CONFIG_VIDEO_CX88=m -# CONFIG_VIDEO_CX88_DVB is not set -CONFIG_VIDEO_OVCAMCHIP=m - -# -# Radio Adapters -# -CONFIG_RADIO_CADET=m -CONFIG_RADIO_RTRACK=m -CONFIG_RADIO_RTRACK2=m -CONFIG_RADIO_AZTECH=m -CONFIG_RADIO_GEMTEK=m -CONFIG_RADIO_GEMTEK_PCI=m -CONFIG_RADIO_MAXIRADIO=m -CONFIG_RADIO_MAESTRO=m -CONFIG_RADIO_MIROPCM20=m -CONFIG_RADIO_MIROPCM20_RDS=m -CONFIG_RADIO_SF16FMI=m -CONFIG_RADIO_SF16FMR2=m -CONFIG_RADIO_TERRATEC=m -CONFIG_RADIO_TRUST=m -CONFIG_RADIO_TYPHOON=m -CONFIG_RADIO_TYPHOON_PROC_FS=y -CONFIG_RADIO_ZOLTRIX=m - -# -# Digital Video Broadcasting Devices -# -CONFIG_DVB=y -CONFIG_DVB_CORE=m - -# -# Supported SAA7146 based PCI Adapters -# -CONFIG_DVB_AV7110=m -# CONFIG_DVB_AV7110_OSD is not set -CONFIG_DVB_BUDGET=m -CONFIG_DVB_BUDGET_CI=m -CONFIG_DVB_BUDGET_AV=m -CONFIG_DVB_BUDGET_PATCH=m - -# -# Supported USB Adapters -# -CONFIG_DVB_TTUSB_BUDGET=m -CONFIG_DVB_TTUSB_DEC=m -CONFIG_DVB_DIBUSB=m -CONFIG_DVB_DIBUSB_MISDESIGNED_DEVICES=y -# CONFIG_DVB_DIBCOM_DEBUG is not set -CONFIG_DVB_CINERGYT2=m -# CONFIG_DVB_CINERGYT2_TUNING is not set - -# -# Supported FlexCopII (B2C2) Adapters -# -CONFIG_DVB_B2C2_FLEXCOP=m -CONFIG_DVB_B2C2_FLEXCOP_PCI=m -CONFIG_DVB_B2C2_FLEXCOP_USB=m -# CONFIG_DVB_B2C2_FLEXCOP_DEBUG is not set -CONFIG_DVB_B2C2_SKYSTAR=m - -# -# Supported BT878 Adapters -# -CONFIG_DVB_BT8XX=m - -# -# Supported DVB Frontends -# - -# -# Customise DVB Frontends -# - -# -# DVB-S (satellite) frontends -# -CONFIG_DVB_STV0299=m -CONFIG_DVB_CX24110=m -CONFIG_DVB_TDA8083=m -CONFIG_DVB_TDA80XX=m -CONFIG_DVB_MT312=m -CONFIG_DVB_VES1X93=m - -# -# DVB-T (terrestrial) frontends -# -CONFIG_DVB_SP8870=m -CONFIG_DVB_SP887X=m -CONFIG_DVB_CX22700=m -CONFIG_DVB_CX22702=m -CONFIG_DVB_L64781=m -CONFIG_DVB_TDA1004X=m -CONFIG_DVB_NXT6000=m -CONFIG_DVB_MT352=m -CONFIG_DVB_DIB3000MB=m -CONFIG_DVB_DIB3000MC=m - -# -# DVB-C (cable) frontends -# -CONFIG_DVB_ATMEL_AT76C651=m -CONFIG_DVB_VES1820=m -CONFIG_DVB_TDA10021=m -CONFIG_DVB_STV0297=m - -# -# ATSC (North American/Korean Terresterial DTV) frontends -# -CONFIG_DVB_NXT2002=m -CONFIG_DVB_OR51211=m -CONFIG_DVB_OR51132=m -CONFIG_VIDEO_SAA7146=m -CONFIG_VIDEO_SAA7146_VV=m -CONFIG_VIDEO_VIDEOBUF=m -CONFIG_VIDEO_TUNER=m -CONFIG_VIDEO_BUF=m -CONFIG_VIDEO_BTCX=m -CONFIG_VIDEO_IR=m -CONFIG_VIDEO_TVEEPROM=m - -# -# Graphics support -# -CONFIG_FB=y -CONFIG_FB_CFB_FILLRECT=m -CONFIG_FB_CFB_COPYAREA=m -CONFIG_FB_CFB_IMAGEBLIT=m -CONFIG_FB_SOFT_CURSOR=m -# CONFIG_FB_MACMODES is not set -CONFIG_FB_MODE_HELPERS=y -CONFIG_FB_TILEBLITTING=y -CONFIG_FB_CIRRUS=m -CONFIG_FB_PM2=m -CONFIG_FB_PM2_FIFO_DISCONNECT=y -CONFIG_FB_CYBER2000=m -# CONFIG_FB_ASILIANT is not set -# CONFIG_FB_IMSTT is not set -CONFIG_FB_VGA16=m -# CONFIG_FB_VESA is not set -CONFIG_VIDEO_SELECT=y -CONFIG_FB_HGA=m -# CONFIG_FB_HGA_ACCEL is not set -CONFIG_FB_NVIDIA=m -CONFIG_FB_NVIDIA_I2C=y -CONFIG_FB_RIVA=m -CONFIG_FB_RIVA_I2C=y -CONFIG_FB_RIVA_DEBUG=y -CONFIG_FB_I810=m -# CONFIG_FB_I810_GTF is not set -CONFIG_FB_INTEL=m -# CONFIG_FB_INTEL_DEBUG is not set -CONFIG_FB_MATROX=m -CONFIG_FB_MATROX_MILLENIUM=y -CONFIG_FB_MATROX_MYSTIQUE=y -# CONFIG_FB_MATROX_G is not set -CONFIG_FB_MATROX_I2C=m -CONFIG_FB_MATROX_MULTIHEAD=y -CONFIG_FB_RADEON_OLD=m -CONFIG_FB_RADEON=m -CONFIG_FB_RADEON_I2C=y -# CONFIG_FB_RADEON_DEBUG is not set -CONFIG_FB_ATY128=m -CONFIG_FB_ATY=m -CONFIG_FB_ATY_CT=y -CONFIG_FB_ATY_GENERIC_LCD=y -CONFIG_FB_ATY_XL_INIT=y -CONFIG_FB_ATY_GX=y -CONFIG_FB_SAVAGE=m -CONFIG_FB_SAVAGE_I2C=y -CONFIG_FB_SAVAGE_ACCEL=y -CONFIG_FB_SIS=m -CONFIG_FB_SIS_300=y -CONFIG_FB_SIS_315=y -CONFIG_FB_NEOMAGIC=m -CONFIG_FB_KYRO=m -CONFIG_FB_3DFX=m -# CONFIG_FB_3DFX_ACCEL is not set -CONFIG_FB_VOODOO1=m -CONFIG_FB_TRIDENT=m -# CONFIG_FB_TRIDENT_ACCEL is not set -# CONFIG_FB_PM3 is not set -CONFIG_FB_GEODE=y -CONFIG_FB_GEODE_GX1=m -CONFIG_FB_S1D13XXX=m -CONFIG_FB_VIRTUAL=m - -# -# Console display driver support -# -CONFIG_VGA_CONSOLE=y -CONFIG_MDA_CONSOLE=m -CONFIG_DUMMY_CONSOLE=y -CONFIG_FRAMEBUFFER_CONSOLE=m -# CONFIG_FONTS is not set -CONFIG_FONT_8x8=y -CONFIG_FONT_8x16=y - -# -# Logo configuration -# -# CONFIG_LOGO is not set -# CONFIG_BACKLIGHT_LCD_SUPPORT is not set - -# -# Sound -# -CONFIG_SOUND=m - -# -# Advanced Linux Sound Architecture -# -CONFIG_SND=m -CONFIG_SND_TIMER=m -CONFIG_SND_PCM=m -CONFIG_SND_HWDEP=m -CONFIG_SND_RAWMIDI=m -CONFIG_SND_SEQUENCER=m -CONFIG_SND_SEQ_DUMMY=m -CONFIG_SND_OSSEMUL=y -CONFIG_SND_MIXER_OSS=m -CONFIG_SND_PCM_OSS=m -CONFIG_SND_SEQUENCER_OSS=y -CONFIG_SND_RTCTIMER=m -# CONFIG_SND_VERBOSE_PRINTK is not set -# CONFIG_SND_DEBUG is not set -CONFIG_SND_GENERIC_PM=y - -# -# Generic devices -# -CONFIG_SND_MPU401_UART=m -CONFIG_SND_OPL3_LIB=m -CONFIG_SND_OPL4_LIB=m -CONFIG_SND_VX_LIB=m -CONFIG_SND_DUMMY=m -CONFIG_SND_VIRMIDI=m -CONFIG_SND_MTPAV=m -CONFIG_SND_SERIAL_U16550=m -CONFIG_SND_MPU401=m - -# -# ISA devices -# -CONFIG_SND_AD1848_LIB=m -CONFIG_SND_CS4231_LIB=m -CONFIG_SND_AD1816A=m -CONFIG_SND_AD1848=m -CONFIG_SND_CS4231=m -CONFIG_SND_CS4232=m -CONFIG_SND_CS4236=m -CONFIG_SND_ES968=m -CONFIG_SND_ES1688=m -CONFIG_SND_ES18XX=m -CONFIG_SND_GUS_SYNTH=m -CONFIG_SND_GUSCLASSIC=m -CONFIG_SND_GUSEXTREME=m -CONFIG_SND_GUSMAX=m -CONFIG_SND_INTERWAVE=m -CONFIG_SND_INTERWAVE_STB=m -CONFIG_SND_OPTI92X_AD1848=m -CONFIG_SND_OPTI92X_CS4231=m -CONFIG_SND_OPTI93X=m -CONFIG_SND_SB8=m -CONFIG_SND_SB16=m -CONFIG_SND_SBAWE=m -CONFIG_SND_SB16_CSP=y -CONFIG_SND_WAVEFRONT=m -CONFIG_SND_ALS100=m -CONFIG_SND_AZT2320=m -CONFIG_SND_CMI8330=m -CONFIG_SND_DT019X=m -CONFIG_SND_OPL3SA2=m -CONFIG_SND_SGALAXY=m -CONFIG_SND_SSCAPE=m - -# -# PCI devices -# -CONFIG_SND_AC97_CODEC=m -CONFIG_SND_ALI5451=m -CONFIG_SND_ATIIXP=m -CONFIG_SND_ATIIXP_MODEM=m -CONFIG_SND_AU8810=m -CONFIG_SND_AU8820=m -CONFIG_SND_AU8830=m -CONFIG_SND_AZT3328=m -CONFIG_SND_BT87X=m -# CONFIG_SND_BT87X_OVERCLOCK is not set -CONFIG_SND_CS46XX=m -CONFIG_SND_CS46XX_NEW_DSP=y -CONFIG_SND_CS4281=m -CONFIG_SND_EMU10K1=m -# CONFIG_SND_EMU10K1X is not set -# CONFIG_SND_CA0106 is not set -CONFIG_SND_KORG1212=m -CONFIG_SND_MIXART=m -CONFIG_SND_NM256=m -CONFIG_SND_RME32=m -CONFIG_SND_RME96=m -CONFIG_SND_RME9652=m -CONFIG_SND_HDSP=m -CONFIG_SND_TRIDENT=m -CONFIG_SND_YMFPCI=m -CONFIG_SND_ALS4000=m -CONFIG_SND_CMIPCI=m -CONFIG_SND_ENS1370=m -CONFIG_SND_ENS1371=m -CONFIG_SND_ES1938=m -CONFIG_SND_ES1968=m -CONFIG_SND_MAESTRO3=m -CONFIG_SND_FM801=m -CONFIG_SND_FM801_TEA575X=m -CONFIG_SND_ICE1712=m -CONFIG_SND_ICE1724=m -CONFIG_SND_INTEL8X0=m -CONFIG_SND_INTEL8X0M=m -CONFIG_SND_SONICVIBES=m -CONFIG_SND_VIA82XX=m -# CONFIG_SND_VIA82XX_MODEM is not set -CONFIG_SND_VX222=m -CONFIG_SND_HDA_INTEL=m - -# -# USB devices -# -CONFIG_SND_USB_AUDIO=m -CONFIG_SND_USB_USX2Y=m - -# -# PCMCIA devices -# -CONFIG_SND_VXPOCKET=m -CONFIG_SND_VXP440=m -CONFIG_SND_PDAUDIOCF=m - -# -# Open Sound System -# -CONFIG_SOUND_PRIME=m -CONFIG_SOUND_BT878=m -CONFIG_SOUND_CMPCI=m -# CONFIG_SOUND_CMPCI_FM is not set -# CONFIG_SOUND_CMPCI_MIDI is not set -CONFIG_SOUND_CMPCI_JOYSTICK=y -CONFIG_SOUND_EMU10K1=m -CONFIG_MIDI_EMU10K1=y -CONFIG_SOUND_FUSION=m -CONFIG_SOUND_CS4281=m -CONFIG_SOUND_ES1370=m -CONFIG_SOUND_ES1371=m -CONFIG_SOUND_ESSSOLO1=m -CONFIG_SOUND_MAESTRO=m -CONFIG_SOUND_MAESTRO3=m -CONFIG_SOUND_ICH=m -CONFIG_SOUND_SONICVIBES=m -CONFIG_SOUND_TRIDENT=m -# CONFIG_SOUND_MSNDCLAS is not set -# CONFIG_SOUND_MSNDPIN is not set -CONFIG_SOUND_VIA82CXXX=m -CONFIG_MIDI_VIA82CXXX=y -CONFIG_SOUND_OSS=m -# CONFIG_SOUND_TRACEINIT is not set -# CONFIG_SOUND_DMAP is not set -# CONFIG_SOUND_AD1816 is not set -CONFIG_SOUND_AD1889=m -CONFIG_SOUND_SGALAXY=m -CONFIG_SOUND_ADLIB=m -CONFIG_SOUND_ACI_MIXER=m -CONFIG_SOUND_CS4232=m -CONFIG_SOUND_SSCAPE=m -CONFIG_SOUND_GUS=m -CONFIG_SOUND_GUS16=y -CONFIG_SOUND_GUSMAX=y -CONFIG_SOUND_VMIDI=m -CONFIG_SOUND_TRIX=m -CONFIG_SOUND_MSS=m -CONFIG_SOUND_MPU401=m -CONFIG_SOUND_NM256=m -CONFIG_SOUND_MAD16=m -CONFIG_MAD16_OLDCARD=y -CONFIG_SOUND_PAS=m -CONFIG_SOUND_PSS=m -CONFIG_PSS_MIXER=y -CONFIG_SOUND_SB=m -# CONFIG_SOUND_AWE32_SYNTH is not set -CONFIG_SOUND_WAVEFRONT=m -CONFIG_SOUND_MAUI=m -CONFIG_SOUND_YM3812=m -CONFIG_SOUND_OPL3SA1=m -CONFIG_SOUND_OPL3SA2=m -CONFIG_SOUND_YMFPCI=m -# CONFIG_SOUND_YMFPCI_LEGACY is not set -CONFIG_SOUND_UART6850=m -CONFIG_SOUND_AEDSP16=m -CONFIG_SC6600=y -CONFIG_SC6600_JOY=y -CONFIG_SC6600_CDROM=4 -CONFIG_SC6600_CDROMBASE=0x0 -# CONFIG_AEDSP16_MSS is not set -# CONFIG_AEDSP16_SBPRO is not set -# CONFIG_AEDSP16_MPU401 is not set -CONFIG_SOUND_TVMIXER=m -CONFIG_SOUND_KAHLUA=m -CONFIG_SOUND_ALI5455=m -CONFIG_SOUND_FORTE=m -CONFIG_SOUND_RME96XX=m -CONFIG_SOUND_AD1980=m - -# -# USB support -# -CONFIG_USB_ARCH_HAS_HCD=y -CONFIG_USB_ARCH_HAS_OHCI=y -CONFIG_USB=y -# CONFIG_USB_DEBUG is not set - -# -# Miscellaneous USB options -# -CONFIG_USB_DEVICEFS=y -CONFIG_USB_BANDWIDTH=y -# CONFIG_USB_DYNAMIC_MINORS is not set -# CONFIG_USB_OTG is not set - -# -# USB Host Controller Drivers -# -CONFIG_USB_EHCI_HCD=y -CONFIG_USB_EHCI_SPLIT_ISO=y -CONFIG_USB_EHCI_ROOT_HUB_TT=y -CONFIG_USB_OHCI_HCD=m -# CONFIG_USB_OHCI_BIG_ENDIAN is not set -CONFIG_USB_OHCI_LITTLE_ENDIAN=y -CONFIG_USB_UHCI_HCD=m -CONFIG_USB_SL811_HCD=m -CONFIG_USB_SL811_CS=m - -# -# USB Device Class drivers -# -CONFIG_USB_AUDIO=m - -# -# USB Bluetooth TTY can only be used with disabled Bluetooth subsystem -# -CONFIG_USB_MIDI=m -CONFIG_USB_ACM=m -CONFIG_USB_PRINTER=m - -# -# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed; see USB_STORAGE Help for more information -# -CONFIG_USB_STORAGE=m -# CONFIG_USB_STORAGE_DEBUG is not set -CONFIG_USB_STORAGE_DATAFAB=y -CONFIG_USB_STORAGE_FREECOM=y -CONFIG_USB_STORAGE_ISD200=y -CONFIG_USB_STORAGE_DPCM=y -CONFIG_USB_STORAGE_USBAT=y -CONFIG_USB_STORAGE_SDDR09=y -CONFIG_USB_STORAGE_SDDR55=y -CONFIG_USB_STORAGE_JUMPSHOT=y - -# -# USB Input Devices -# -CONFIG_USB_HID=m -CONFIG_USB_HIDINPUT=y -# CONFIG_HID_FF is not set -CONFIG_USB_HIDDEV=y - -# -# USB HID Boot Protocol drivers -# -CONFIG_USB_KBD=m -CONFIG_USB_MOUSE=m -CONFIG_USB_AIPTEK=m -CONFIG_USB_WACOM=m -CONFIG_USB_KBTAB=m -CONFIG_USB_POWERMATE=m -CONFIG_USB_MTOUCH=m -CONFIG_USB_EGALAX=m -CONFIG_USB_XPAD=m -CONFIG_USB_ATI_REMOTE=m - -# -# USB Imaging devices -# -CONFIG_USB_MDC800=m -CONFIG_USB_MICROTEK=m - -# -# USB Multimedia devices -# -# CONFIG_USB_DABUSB is not set -CONFIG_USB_VICAM=m -CONFIG_USB_DSBR=m -CONFIG_USB_IBMCAM=m -CONFIG_USB_KONICAWC=m -CONFIG_USB_OV511=m -CONFIG_USB_SE401=m -CONFIG_USB_SN9C102=m -CONFIG_USB_STV680=m -CONFIG_USB_W9968CF=m -CONFIG_USB_PWC=m - -# -# USB Network Adapters -# -CONFIG_USB_CATC=m -CONFIG_USB_KAWETH=m -CONFIG_USB_PEGASUS=m -CONFIG_USB_RTL8150=m -CONFIG_USB_USBNET=m - -# -# USB Host-to-Host Cables -# -CONFIG_USB_ALI_M5632=y -CONFIG_USB_AN2720=y -CONFIG_USB_BELKIN=y -CONFIG_USB_GENESYS=y -CONFIG_USB_NET1080=y -CONFIG_USB_PL2301=y -CONFIG_USB_KC2190=y - -# -# Intelligent USB Devices/Gadgets -# -CONFIG_USB_ARMLINUX=y -CONFIG_USB_EPSON2888=y -CONFIG_USB_ZAURUS=y -CONFIG_USB_CDCETHER=y - -# -# USB Network Adapters -# -CONFIG_USB_AX8817X=y -CONFIG_USB_ZD1201=m -CONFIG_USB_MON=m - -# -# USB port drivers -# -CONFIG_USB_USS720=m - -# -# USB Serial Converter support -# -CONFIG_USB_SERIAL=m -CONFIG_USB_SERIAL_GENERIC=y -CONFIG_USB_SERIAL_AIRPRIME=m -CONFIG_USB_SERIAL_BELKIN=m -CONFIG_USB_SERIAL_WHITEHEAT=m -CONFIG_USB_SERIAL_DIGI_ACCELEPORT=m -CONFIG_USB_SERIAL_CP2101=m -CONFIG_USB_SERIAL_CYPRESS_M8=m -CONFIG_USB_SERIAL_EMPEG=m -CONFIG_USB_SERIAL_FTDI_SIO=m -CONFIG_USB_SERIAL_VISOR=m -CONFIG_USB_SERIAL_IPAQ=m -CONFIG_USB_SERIAL_IR=m -CONFIG_USB_SERIAL_EDGEPORT=m -CONFIG_USB_SERIAL_EDGEPORT_TI=m -# CONFIG_USB_SERIAL_GARMIN is not set -CONFIG_USB_SERIAL_IPW=m -CONFIG_USB_SERIAL_KEYSPAN_PDA=m -CONFIG_USB_SERIAL_KEYSPAN=m -# CONFIG_USB_SERIAL_KEYSPAN_MPR is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA28 is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA28X is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA28XA is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA28XB is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA19 is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA18X is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA19W is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA19QW is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA19QI is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA49W is not set -# CONFIG_USB_SERIAL_KEYSPAN_USA49WLC is not set -CONFIG_USB_SERIAL_KLSI=m -CONFIG_USB_SERIAL_KOBIL_SCT=m -CONFIG_USB_SERIAL_MCT_U232=m -CONFIG_USB_SERIAL_PL2303=m -CONFIG_USB_SERIAL_HP4X=m -CONFIG_USB_SERIAL_SAFE=m -# CONFIG_USB_SERIAL_SAFE_PADDED is not set -# CONFIG_USB_SERIAL_TI is not set -CONFIG_USB_SERIAL_CYBERJACK=m -CONFIG_USB_SERIAL_XIRCOM=m -CONFIG_USB_SERIAL_OPTION=m -CONFIG_USB_SERIAL_OMNINET=m -CONFIG_USB_EZUSB=y - -# -# USB Miscellaneous drivers -# -# CONFIG_USB_EMI62 is not set -# CONFIG_USB_EMI26 is not set -CONFIG_USB_AUERSWALD=m -CONFIG_USB_RIO500=m -CONFIG_USB_LEGOTOWER=m -CONFIG_USB_LCD=m -CONFIG_USB_LED=m -CONFIG_USB_CYTHERM=m -CONFIG_USB_PHIDGETKIT=m -CONFIG_USB_PHIDGETSERVO=m -# CONFIG_USB_IDMOUSE is not set -CONFIG_USB_SISUSBVGA=m -CONFIG_USB_TEST=m - -# -# USB ATM/DSL drivers -# -CONFIG_USB_ATM=m -CONFIG_USB_SPEEDTOUCH=m - -# -# USB Gadget Support -# -CONFIG_USB_GADGET=m -# CONFIG_USB_GADGET_DEBUG_FILES is not set -CONFIG_USB_GADGET_NET2280=y -CONFIG_USB_NET2280=m -# CONFIG_USB_GADGET_PXA2XX is not set -# CONFIG_USB_GADGET_GOKU is not set -# CONFIG_USB_GADGET_LH7A40X is not set -# CONFIG_USB_GADGET_OMAP is not set -# CONFIG_USB_GADGET_DUMMY_HCD is not set -CONFIG_USB_GADGET_DUALSPEED=y -CONFIG_USB_ZERO=m -CONFIG_USB_ETH=m -CONFIG_USB_ETH_RNDIS=y -CONFIG_USB_GADGETFS=m -CONFIG_USB_FILE_STORAGE=m -# CONFIG_USB_FILE_STORAGE_TEST is not set -CONFIG_USB_G_SERIAL=m - -# -# MMC/SD Card support -# -# CONFIG_MMC is not set - -# -# InfiniBand support -# -# CONFIG_INFINIBAND is not set - -# -# Power management options -# - -# -# ACPI (Advanced Configuration and Power Interface) Support -# -CONFIG_ACPI=y -CONFIG_ACPI_BOOT=y -CONFIG_ACPI_INTERPRETER=y -CONFIG_ACPI_AC=m -CONFIG_ACPI_BATTERY=m -CONFIG_ACPI_BUTTON=m -CONFIG_ACPI_VIDEO=m -CONFIG_ACPI_FAN=m -CONFIG_ACPI_PROCESSOR=m -# CONFIG_ACPI_HOTPLUG_CPU is not set -CONFIG_ACPI_THERMAL=m -CONFIG_ACPI_ASUS=m -CONFIG_ACPI_IBM=m -CONFIG_ACPI_TOSHIBA=m -CONFIG_ACPI_BLACKLIST_YEAR=0 -# CONFIG_ACPI_DEBUG is not set -CONFIG_ACPI_BUS=y -CONFIG_ACPI_EC=y -CONFIG_ACPI_POWER=y -CONFIG_ACPI_PCI=y -CONFIG_ACPI_SYSTEM=y -# CONFIG_X86_PM_TIMER is not set -# CONFIG_ACPI_CONTAINER is not set - -# -# File systems -# -CONFIG_EXT2_FS=y -CONFIG_EXT2_FS_XATTR=y -CONFIG_EXT2_FS_POSIX_ACL=y -CONFIG_EXT2_FS_SECURITY=y -CONFIG_EXT3_FS=m -CONFIG_EXT3_FS_XATTR=y -CONFIG_EXT3_FS_POSIX_ACL=y -CONFIG_EXT3_FS_SECURITY=y -CONFIG_JBD=m -# CONFIG_JBD_DEBUG is not set -CONFIG_FS_MBCACHE=y -CONFIG_REISERFS_FS=m -# CONFIG_REISERFS_CHECK is not set -# CONFIG_REISERFS_PROC_INFO is not set -# CONFIG_REISERFS_FS_XATTR is not set -CONFIG_JFS_FS=m -CONFIG_JFS_POSIX_ACL=y -# CONFIG_JFS_SECURITY is not set -# CONFIG_JFS_DEBUG is not set -CONFIG_JFS_STATISTICS=y -CONFIG_FS_POSIX_ACL=y - -# -# XFS support -# -CONFIG_XFS_FS=m -CONFIG_XFS_EXPORT=y -CONFIG_XFS_RT=y -CONFIG_XFS_QUOTA=y -CONFIG_XFS_SECURITY=y -CONFIG_XFS_POSIX_ACL=y -CONFIG_MINIX_FS=m -CONFIG_ROMFS_FS=m -CONFIG_QUOTA=y -CONFIG_QFMT_V1=m -CONFIG_QFMT_V2=m -CONFIG_QUOTACTL=y -CONFIG_DNOTIFY=y -CONFIG_AUTOFS_FS=m -CONFIG_AUTOFS4_FS=m - -# -# CD-ROM/DVD Filesystems -# -CONFIG_ISO9660_FS=m -CONFIG_JOLIET=y -CONFIG_ZISOFS=y -CONFIG_ZISOFS_FS=m -CONFIG_UDF_FS=m -CONFIG_UDF_NLS=y - -# -# DOS/FAT/NT Filesystems -# -CONFIG_FAT_FS=m -CONFIG_MSDOS_FS=m -CONFIG_VFAT_FS=m -CONFIG_FAT_DEFAULT_CODEPAGE=437 -CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1" -CONFIG_NTFS_FS=m -# CONFIG_NTFS_DEBUG is not set -# CONFIG_NTFS_RW is not set - -# -# Pseudo filesystems -# -CONFIG_PROC_FS=y -CONFIG_PROC_KCORE=y -CONFIG_SYSFS=y -# CONFIG_DEVFS_FS is not set -CONFIG_DEVPTS_FS_XATTR=y -CONFIG_DEVPTS_FS_SECURITY=y -CONFIG_TMPFS=y -CONFIG_TMPFS_XATTR=y -CONFIG_TMPFS_SECURITY=y -# CONFIG_HUGETLBFS is not set -# CONFIG_HUGETLB_PAGE is not set -CONFIG_RAMFS=y - -# -# Miscellaneous filesystems -# -CONFIG_ADFS_FS=m -# CONFIG_ADFS_FS_RW is not set -CONFIG_AFFS_FS=m -CONFIG_HFS_FS=m -CONFIG_HFSPLUS_FS=m -CONFIG_BEFS_FS=m -# CONFIG_BEFS_DEBUG is not set -CONFIG_BFS_FS=m -CONFIG_EFS_FS=m -CONFIG_JFFS_FS=m -CONFIG_JFFS_FS_VERBOSE=0 -CONFIG_JFFS_PROC_FS=y -CONFIG_JFFS2_FS=m -CONFIG_JFFS2_FS_DEBUG=0 -# CONFIG_JFFS2_FS_NAND is not set -# CONFIG_JFFS2_FS_NOR_ECC is not set -# CONFIG_JFFS2_COMPRESSION_OPTIONS is not set -CONFIG_JFFS2_ZLIB=y -CONFIG_JFFS2_RTIME=y -# CONFIG_JFFS2_RUBIN is not set -CONFIG_CRAMFS=y -CONFIG_VXFS_FS=m -CONFIG_HPFS_FS=m -CONFIG_QNX4FS_FS=m -# CONFIG_QNX4FS_RW is not set -CONFIG_SYSV_FS=m -CONFIG_UFS_FS=m -# CONFIG_UFS_FS_WRITE is not set - -# -# Network File Systems -# -CONFIG_NFS_FS=m -CONFIG_NFS_V3=y -CONFIG_NFS_V4=y -CONFIG_NFS_DIRECTIO=y -CONFIG_NFSD=m -CONFIG_NFSD_V3=y -CONFIG_NFSD_V4=y -CONFIG_NFSD_TCP=y -CONFIG_LOCKD=m -CONFIG_LOCKD_V4=y -CONFIG_EXPORTFS=m -CONFIG_SUNRPC=m -CONFIG_SUNRPC_GSS=m -CONFIG_RPCSEC_GSS_KRB5=m -CONFIG_RPCSEC_GSS_SPKM3=m -CONFIG_SMB_FS=m -# CONFIG_SMB_NLS_DEFAULT is not set -CONFIG_CIFS=m -# CONFIG_CIFS_STATS is not set -# CONFIG_CIFS_XATTR is not set -# CONFIG_CIFS_EXPERIMENTAL is not set -CONFIG_NCP_FS=m -CONFIG_NCPFS_PACKET_SIGNING=y -CONFIG_NCPFS_IOCTL_LOCKING=y -CONFIG_NCPFS_STRONG=y -CONFIG_NCPFS_NFS_NS=y -CONFIG_NCPFS_OS2_NS=y -# CONFIG_NCPFS_SMALLDOS is not set -CONFIG_NCPFS_NLS=y -CONFIG_NCPFS_EXTRAS=y -CONFIG_CODA_FS=m -# CONFIG_CODA_FS_OLD_API is not set -CONFIG_AFS_FS=m -CONFIG_RXRPC=m - -# -# Partition Types -# -CONFIG_PARTITION_ADVANCED=y -CONFIG_ACORN_PARTITION=y -CONFIG_ACORN_PARTITION_CUMANA=y -# CONFIG_ACORN_PARTITION_EESOX is not set -CONFIG_ACORN_PARTITION_ICS=y -# CONFIG_ACORN_PARTITION_ADFS is not set -# CONFIG_ACORN_PARTITION_POWERTEC is not set -CONFIG_ACORN_PARTITION_RISCIX=y -CONFIG_OSF_PARTITION=y -CONFIG_AMIGA_PARTITION=y -CONFIG_ATARI_PARTITION=y -CONFIG_MAC_PARTITION=y -CONFIG_MSDOS_PARTITION=y -CONFIG_BSD_DISKLABEL=y -CONFIG_MINIX_SUBPARTITION=y -CONFIG_SOLARIS_X86_PARTITION=y -CONFIG_UNIXWARE_DISKLABEL=y -CONFIG_LDM_PARTITION=y -# CONFIG_LDM_DEBUG is not set -CONFIG_SGI_PARTITION=y -CONFIG_ULTRIX_PARTITION=y -CONFIG_SUN_PARTITION=y -CONFIG_EFI_PARTITION=y - -# -# Native Language Support -# -CONFIG_NLS=y -CONFIG_NLS_DEFAULT="cp437" -CONFIG_NLS_CODEPAGE_437=m -CONFIG_NLS_CODEPAGE_737=m -CONFIG_NLS_CODEPAGE_775=m -CONFIG_NLS_CODEPAGE_850=m -CONFIG_NLS_CODEPAGE_852=m -CONFIG_NLS_CODEPAGE_855=m -CONFIG_NLS_CODEPAGE_857=m -CONFIG_NLS_CODEPAGE_860=m -CONFIG_NLS_CODEPAGE_861=m -CONFIG_NLS_CODEPAGE_862=m -CONFIG_NLS_CODEPAGE_863=m -CONFIG_NLS_CODEPAGE_864=m -CONFIG_NLS_CODEPAGE_865=m -CONFIG_NLS_CODEPAGE_866=m -CONFIG_NLS_CODEPAGE_869=m -CONFIG_NLS_CODEPAGE_936=m -CONFIG_NLS_CODEPAGE_950=m -CONFIG_NLS_CODEPAGE_932=m -CONFIG_NLS_CODEPAGE_949=m -CONFIG_NLS_CODEPAGE_874=m -CONFIG_NLS_ISO8859_8=m -CONFIG_NLS_CODEPAGE_1250=m -CONFIG_NLS_CODEPAGE_1251=m -CONFIG_NLS_ASCII=m -CONFIG_NLS_ISO8859_1=m -CONFIG_NLS_ISO8859_2=m -CONFIG_NLS_ISO8859_3=m -CONFIG_NLS_ISO8859_4=m -CONFIG_NLS_ISO8859_5=m -CONFIG_NLS_ISO8859_6=m -CONFIG_NLS_ISO8859_7=m -CONFIG_NLS_ISO8859_9=m -CONFIG_NLS_ISO8859_13=m -CONFIG_NLS_ISO8859_14=m -CONFIG_NLS_ISO8859_15=m -CONFIG_NLS_KOI8_R=m -CONFIG_NLS_KOI8_U=m -CONFIG_NLS_UTF8=m - -# -# Security options -# -CONFIG_KEYS=y -# CONFIG_KEYS_DEBUG_PROC_KEYS is not set -CONFIG_SECURITY=y -# CONFIG_SECURITY_NETWORK is not set -CONFIG_SECURITY_CAPABILITIES=y -CONFIG_SECURITY_ROOTPLUG=m -CONFIG_SECURITY_SECLVL=m -CONFIG_SECURITY_SELINUX=y -CONFIG_SECURITY_SELINUX_BOOTPARAM=y -CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=0 -CONFIG_SECURITY_SELINUX_DISABLE=y -CONFIG_SECURITY_SELINUX_DEVELOP=y -CONFIG_SECURITY_SELINUX_AVC_STATS=y -CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1 - -# -# Cryptographic options -# -CONFIG_CRYPTO=y -CONFIG_CRYPTO_HMAC=y -CONFIG_CRYPTO_NULL=m -CONFIG_CRYPTO_MD4=m -CONFIG_CRYPTO_MD5=y -CONFIG_CRYPTO_SHA1=m -CONFIG_CRYPTO_SHA256=m -CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_WP512=m -CONFIG_CRYPTO_TGR192=m -CONFIG_CRYPTO_DES=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_SERPENT=m -CONFIG_CRYPTO_AES_586=m -CONFIG_CRYPTO_CAST5=m -CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_ANUBIS=m -CONFIG_CRYPTO_DEFLATE=m -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_CRC32C=m -CONFIG_CRYPTO_TEST=m - -# -# Hardware crypto devices -# -# CONFIG_CRYPTO_DEV_PADLOCK is not set - -# -# Library routines -# -CONFIG_CRC_CCITT=m -CONFIG_CRC32=y -CONFIG_LIBCRC32C=m -CONFIG_ZLIB_INFLATE=y -CONFIG_ZLIB_DEFLATE=m -CONFIG_REED_SOLOMON=m -CONFIG_REED_SOLOMON_DEC16=y - -# -# Kernel hacking -# -# CONFIG_PRINTK_TIME is not set -CONFIG_DEBUG_KERNEL=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_LOG_BUF_SHIFT=14 -# CONFIG_SCHEDSTATS is not set -# CONFIG_DEBUG_SLAB is not set -# CONFIG_DEBUG_SPINLOCK is not set -# CONFIG_DEBUG_SPINLOCK_SLEEP is not set -# CONFIG_DEBUG_KOBJECT is not set -# CONFIG_DEBUG_HIGHMEM is not set -# CONFIG_DEBUG_BUGVERBOSE is not set -# CONFIG_DEBUG_INFO is not set -# CONFIG_DEBUG_FS is not set -# CONFIG_FRAME_POINTER is not set -# CONFIG_DEBUG_STACKOVERFLOW is not set -# CONFIG_KPROBES is not set -# CONFIG_DEBUG_STACK_USAGE is not set -# CONFIG_DEBUG_PAGEALLOC is not set -# CONFIG_4KSTACKS is not set -CONFIG_X86_FIND_SMP_CONFIG=y -CONFIG_X86_MPPARSE=y diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/configs/xen_defconfig_x86_64 --- a/linux-2.6-xen-sparse/arch/xen/configs/xen_defconfig_x86_64 Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,2425 +0,0 @@ -# -# Automatically generated make config: don't edit -# Linux kernel version: 2.6.12.4-xen -# Mon Aug 15 19:54:11 2005 -# -CONFIG_XEN=y -CONFIG_ARCH_XEN=y -CONFIG_NO_IDLE_HZ=y - -# -# XEN -# -CONFIG_XEN_PRIVILEGED_GUEST=y -CONFIG_XEN_PHYSDEV_ACCESS=y -CONFIG_XEN_BLKDEV_BACKEND=y -# CONFIG_XEN_BLKDEV_TAP_BE is not set -CONFIG_XEN_NETDEV_BACKEND=y -# CONFIG_XEN_NETDEV_PIPELINED_TRANSMITTER is not set -# CONFIG_XEN_TPMDEV_FRONTEND is not set -# CONFIG_XEN_TPMDEV_BACKEND is not set -CONFIG_XEN_BLKDEV_FRONTEND=y -CONFIG_XEN_NETDEV_FRONTEND=y -# CONFIG_XEN_BLKDEV_TAP is not set -# CONFIG_XEN_SHADOW_MODE is not set -CONFIG_XEN_SCRUB_PAGES=y -# CONFIG_XEN_X86 is not set -CONFIG_XEN_X86_64=y -CONFIG_HAVE_ARCH_ALLOC_SKB=y -CONFIG_HAVE_ARCH_DEV_ALLOC_SKB=y - -# -# Code maturity level options -# -CONFIG_EXPERIMENTAL=y -# CONFIG_CLEAN_COMPILE is not set -CONFIG_BROKEN=y -CONFIG_BROKEN_ON_SMP=y -CONFIG_LOCK_KERNEL=y -CONFIG_INIT_ENV_ARG_LIMIT=32 - -# -# General setup -# -CONFIG_LOCALVERSION="" -CONFIG_SWAP=y -CONFIG_SYSVIPC=y -# CONFIG_POSIX_MQUEUE is not set -# CONFIG_BSD_PROCESS_ACCT is not set -CONFIG_SYSCTL=y -# CONFIG_AUDIT is not set -CONFIG_HOTPLUG=y -CONFIG_KOBJECT_UEVENT=y -# CONFIG_IKCONFIG is not set -# CONFIG_CPUSETS is not set -# CONFIG_EMBEDDED is not set -CONFIG_KALLSYMS=y -# CONFIG_KALLSYMS_ALL is not set -CONFIG_KALLSYMS_EXTRA_PASS=y -CONFIG_PRINTK=y -CONFIG_BUG=y -CONFIG_BASE_FULL=y -CONFIG_FUTEX=y -CONFIG_EPOLL=y -CONFIG_SHMEM=y -CONFIG_CC_ALIGN_FUNCTIONS=0 -CONFIG_CC_ALIGN_LABELS=0 -CONFIG_CC_ALIGN_LOOPS=0 -CONFIG_CC_ALIGN_JUMPS=0 -# CONFIG_TINY_SHMEM is not set -CONFIG_BASE_SMALL=0 - -# -# Loadable module support -# -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -# CONFIG_MODULE_FORCE_UNLOAD is not set -CONFIG_OBSOLETE_MODPARM=y -# CONFIG_MODVERSIONS is not set -CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_KMOD=y -CONFIG_STOP_MACHINE=y -CONFIG_XENARCH="x86_64" -CONFIG_X86=y -CONFIG_MMU=y -CONFIG_UID16=y -CONFIG_GENERIC_ISA_DMA=y -CONFIG_GENERIC_IOMAP=y -CONFIG_X86_CMPXCHG=y -CONFIG_X86_L1_CACHE_SHIFT=7 -CONFIG_RWSEM_GENERIC_SPINLOCK=y -CONFIG_GENERIC_CALIBRATE_DELAY=y -CONFIG_X86_GOOD_APIC=y -# CONFIG_HPET_TIMER is not set -CONFIG_SMP=y -CONFIG_NR_CPUS=8 -# CONFIG_SCHED_SMT is not set -CONFIG_MICROCODE=y -# CONFIG_X86_CPUID is not set -# CONFIG_NUMA is not set -# CONFIG_MTRR is not set -CONFIG_HAVE_DEC_LOCK=y -CONFIG_X86_LOCAL_APIC=y -CONFIG_X86_IO_APIC=y -CONFIG_PCI=y -CONFIG_PCI_DIRECT=y -# CONFIG_PCI_MMCONFIG is not set -CONFIG_ISA_DMA_API=y -CONFIG_GENERIC_HARDIRQS=y -CONFIG_GENERIC_IRQ_PROBE=y -CONFIG_SECCOMP=y - -# -# X86_64 processor configuration -# -CONFIG_X86_64=y -CONFIG_64BIT=y -CONFIG_EARLY_PRINTK=y - -# -# Processor type and features -# -# CONFIG_MPSC is not set -CONFIG_GENERIC_CPU=y -CONFIG_X86_L1_CACHE_BYTES=128 -# CONFIG_X86_TSC is not set -CONFIG_X86_XEN_GENAPIC=y -# CONFIG_X86_MSR is not set -CONFIG_X86_HT=y -# CONFIG_K8_NUMA is not set -# CONFIG_NUMA_EMU is not set -# CONFIG_GART_IOMMU is not set -CONFIG_DUMMY_IOMMU=y -CONFIG_SWIOTLB=y -# CONFIG_X86_MCE is not set - -# -# Power management options -# -# CONFIG_PM is not set - -# -# CPU Frequency scaling -# -# CONFIG_CPU_FREQ is not set - -# -# Bus options (PCI etc.) -# -# CONFIG_UNORDERED_IO is not set - -# -# Executable file formats / Emulations -# -CONFIG_IA32_EMULATION=y -# CONFIG_IA32_AOUT is not set -CONFIG_COMPAT=y -CONFIG_SYSVIPC_COMPAT=y - -# -# Executable file formats -# -CONFIG_BINFMT_ELF=y -CONFIG_BINFMT_MISC=y - -# -# Device Drivers -# - -# -# Generic Driver Options -# -CONFIG_STANDALONE=y -CONFIG_PREVENT_FIRMWARE_BUILD=y -CONFIG_FW_LOADER=y -# CONFIG_DEBUG_DRIVER is not set - -# -# Memory Technology Devices (MTD) -# -CONFIG_MTD=m -# CONFIG_MTD_DEBUG is not set -CONFIG_MTD_CONCAT=m -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_REDBOOT_PARTS=m -CONFIG_MTD_REDBOOT_DIRECTORY_BLOCK=-1 -# CONFIG_MTD_REDBOOT_PARTS_UNALLOCATED is not set -# CONFIG_MTD_REDBOOT_PARTS_READONLY is not set -CONFIG_MTD_CMDLINE_PARTS=y - -# -# User Modules And Translation Layers -# -CONFIG_MTD_CHAR=m -CONFIG_MTD_BLOCK=m -CONFIG_MTD_BLOCK_RO=m -CONFIG_FTL=m -CONFIG_NFTL=m -CONFIG_NFTL_RW=y -CONFIG_INFTL=m - -# -# RAM/ROM/Flash chip drivers -# -CONFIG_MTD_CFI=m -CONFIG_MTD_JEDECPROBE=m -CONFIG_MTD_GEN_PROBE=m -# CONFIG_MTD_CFI_ADV_OPTIONS is not set -CONFIG_MTD_MAP_BANK_WIDTH_1=y -CONFIG_MTD_MAP_BANK_WIDTH_2=y -CONFIG_MTD_MAP_BANK_WIDTH_4=y -# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set -# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set -# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set -CONFIG_MTD_CFI_I1=y -CONFIG_MTD_CFI_I2=y -# CONFIG_MTD_CFI_I4 is not set -# CONFIG_MTD_CFI_I8 is not set -CONFIG_MTD_CFI_INTELEXT=m -CONFIG_MTD_CFI_AMDSTD=m -CONFIG_MTD_CFI_AMDSTD_RETRY=3 -CONFIG_MTD_CFI_STAA=m -CONFIG_MTD_CFI_UTIL=m -CONFIG_MTD_RAM=m -CONFIG_MTD_ROM=m -CONFIG_MTD_ABSENT=m -# CONFIG_MTD_OBSOLETE_CHIPS is not set - -# -# Mapping drivers for chip access -# -CONFIG_MTD_COMPLEX_MAPPINGS=y -# CONFIG_MTD_PHYSMAP is not set -# CONFIG_MTD_PNC2000 is not set -CONFIG_MTD_SC520CDP=m -CONFIG_MTD_NETSC520=m -CONFIG_MTD_TS5500=m -CONFIG_MTD_SBC_GXX=m -CONFIG_MTD_ELAN_104NC=m -# CONFIG_MTD_AMD76XROM is not set -# CONFIG_MTD_ICHXROM is not set -CONFIG_MTD_SCB2_FLASH=m -# CONFIG_MTD_NETtel is not set -# CONFIG_MTD_DILNETPC is not set -# CONFIG_MTD_L440GX is not set -CONFIG_MTD_PCI=m - -# -# Self-contained MTD device drivers -# -CONFIG_MTD_PMC551=m -# CONFIG_MTD_PMC551_BUGFIX is not set -# CONFIG_MTD_PMC551_DEBUG is not set -# CONFIG_MTD_SLRAM is not set -# CONFIG_MTD_PHRAM is not set -CONFIG_MTD_MTDRAM=m -CONFIG_MTDRAM_TOTAL_SIZE=4096 -CONFIG_MTDRAM_ERASE_SIZE=128 -# CONFIG_MTD_BLKMTD is not set -CONFIG_MTD_BLOCK2MTD=m - -# -# Disk-On-Chip Device Drivers -# -CONFIG_MTD_DOC2000=m -# CONFIG_MTD_DOC2001 is not set -CONFIG_MTD_DOC2001PLUS=m -CONFIG_MTD_DOCPROBE=m -CONFIG_MTD_DOCECC=m -# CONFIG_MTD_DOCPROBE_ADVANCED is not set -CONFIG_MTD_DOCPROBE_ADDRESS=0 - -# -# NAND Flash Device Drivers -# -CONFIG_MTD_NAND=m -# CONFIG_MTD_NAND_VERIFY_WRITE is not set -CONFIG_MTD_NAND_IDS=m -# CONFIG_MTD_NAND_DISKONCHIP is not set -# CONFIG_MTD_NAND_NANDSIM is not set - -# -# Parallel port support -# -CONFIG_PARPORT=m -CONFIG_PARPORT_PC=m -# CONFIG_PARPORT_PC_FIFO is not set -# CONFIG_PARPORT_PC_SUPERIO is not set -CONFIG_PARPORT_NOT_PC=y -# CONFIG_PARPORT_GSC is not set -CONFIG_PARPORT_1284=y - -# -# Plug and Play support -# -# CONFIG_PNP is not set - -# -# Block devices -# -CONFIG_BLK_DEV_FD=m -CONFIG_PARIDE=m -CONFIG_PARIDE_PARPORT=m - -# -# Parallel IDE high-level drivers -# -CONFIG_PARIDE_PD=m -CONFIG_PARIDE_PCD=m -CONFIG_PARIDE_PF=m -CONFIG_PARIDE_PT=m -CONFIG_PARIDE_PG=m - -# -# Parallel IDE protocol modules -# -CONFIG_PARIDE_ATEN=m -CONFIG_PARIDE_BPCK=m -CONFIG_PARIDE_COMM=m -CONFIG_PARIDE_DSTR=m -CONFIG_PARIDE_FIT2=m -CONFIG_PARIDE_FIT3=m -CONFIG_PARIDE_EPAT=m -CONFIG_PARIDE_EPATC8=y -CONFIG_PARIDE_EPIA=m -CONFIG_PARIDE_FRIQ=m -CONFIG_PARIDE_FRPW=m -CONFIG_PARIDE_KBIC=m -CONFIG_PARIDE_KTTI=m -CONFIG_PARIDE_ON20=m -CONFIG_PARIDE_ON26=m -CONFIG_BLK_CPQ_DA=m -CONFIG_BLK_CPQ_CISS_DA=m -CONFIG_CISS_SCSI_TAPE=y -CONFIG_BLK_DEV_DAC960=m -CONFIG_BLK_DEV_UMEM=m -# CONFIG_BLK_DEV_COW_COMMON is not set -CONFIG_BLK_DEV_LOOP=m -CONFIG_BLK_DEV_CRYPTOLOOP=m -CONFIG_BLK_DEV_NBD=m -CONFIG_BLK_DEV_SX8=m -# CONFIG_BLK_DEV_UB is not set -CONFIG_BLK_DEV_RAM=y -CONFIG_BLK_DEV_RAM_COUNT=16 -CONFIG_BLK_DEV_RAM_SIZE=16384 -CONFIG_BLK_DEV_INITRD=y -CONFIG_INITRAMFS_SOURCE="" -CONFIG_LBD=y -CONFIG_CDROM_PKTCDVD=m -CONFIG_CDROM_PKTCDVD_BUFFERS=8 -# CONFIG_CDROM_PKTCDVD_WCACHE is not set - -# -# IO Schedulers -# -CONFIG_IOSCHED_NOOP=y -CONFIG_IOSCHED_AS=y -CONFIG_IOSCHED_DEADLINE=y -CONFIG_IOSCHED_CFQ=y -CONFIG_ATA_OVER_ETH=m - -# -# ATA/ATAPI/MFM/RLL support -# -CONFIG_IDE=y -CONFIG_BLK_DEV_IDE=y - -# -# Please see Documentation/ide.txt for help/info on IDE drives -# -# CONFIG_BLK_DEV_IDE_SATA is not set -# CONFIG_BLK_DEV_HD_IDE is not set -CONFIG_BLK_DEV_IDEDISK=y -CONFIG_IDEDISK_MULTI_MODE=y -CONFIG_BLK_DEV_IDECD=y -# CONFIG_BLK_DEV_IDETAPE is not set -CONFIG_BLK_DEV_IDEFLOPPY=y -CONFIG_BLK_DEV_IDESCSI=m -# CONFIG_IDE_TASK_IOCTL is not set - -# -# IDE chipset support/bugfixes -# -CONFIG_IDE_GENERIC=y -CONFIG_BLK_DEV_CMD640=y -CONFIG_BLK_DEV_CMD640_ENHANCED=y -CONFIG_BLK_DEV_IDEPCI=y -CONFIG_IDEPCI_SHARE_IRQ=y -# CONFIG_BLK_DEV_OFFBOARD is not set -CONFIG_BLK_DEV_GENERIC=y -# CONFIG_BLK_DEV_OPTI621 is not set -CONFIG_BLK_DEV_RZ1000=y -CONFIG_BLK_DEV_IDEDMA_PCI=y -# CONFIG_BLK_DEV_IDEDMA_FORCED is not set -CONFIG_IDEDMA_PCI_AUTO=y -# CONFIG_IDEDMA_ONLYDISK is not set -CONFIG_BLK_DEV_AEC62XX=y -CONFIG_BLK_DEV_ALI15X3=y -# CONFIG_WDC_ALI15X3 is not set -CONFIG_BLK_DEV_AMD74XX=y -CONFIG_BLK_DEV_ATIIXP=y -CONFIG_BLK_DEV_CMD64X=y -CONFIG_BLK_DEV_TRIFLEX=y -CONFIG_BLK_DEV_CY82C693=y -CONFIG_BLK_DEV_CS5520=y -CONFIG_BLK_DEV_CS5530=y -CONFIG_BLK_DEV_HPT34X=y -# CONFIG_HPT34X_AUTODMA is not set -CONFIG_BLK_DEV_HPT366=y -# CONFIG_BLK_DEV_SC1200 is not set -CONFIG_BLK_DEV_PIIX=y -# CONFIG_BLK_DEV_NS87415 is not set -CONFIG_BLK_DEV_PDC202XX_OLD=y -# CONFIG_PDC202XX_BURST is not set -CONFIG_BLK_DEV_PDC202XX_NEW=y -CONFIG_PDC202XX_FORCE=y -CONFIG_BLK_DEV_SVWKS=y -CONFIG_BLK_DEV_SIIMAGE=y -CONFIG_BLK_DEV_SIS5513=y -CONFIG_BLK_DEV_SLC90E66=y -# CONFIG_BLK_DEV_TRM290 is not set -CONFIG_BLK_DEV_VIA82CXXX=y -# CONFIG_IDE_ARM is not set -CONFIG_BLK_DEV_IDEDMA=y -# CONFIG_IDEDMA_IVB is not set -CONFIG_IDEDMA_AUTO=y -# CONFIG_BLK_DEV_HD is not set - -# -# SCSI device support -# -CONFIG_SCSI=y -CONFIG_SCSI_PROC_FS=y - -# -# SCSI support type (disk, tape, CD-ROM) -# -CONFIG_BLK_DEV_SD=y -CONFIG_CHR_DEV_ST=m -CONFIG_CHR_DEV_OSST=m -CONFIG_BLK_DEV_SR=m -CONFIG_BLK_DEV_SR_VENDOR=y -CONFIG_CHR_DEV_SG=m - -# -# Some SCSI devices (e.g. CD jukebox) support multiple LUNs -# -CONFIG_SCSI_MULTI_LUN=y -CONFIG_SCSI_CONSTANTS=y -CONFIG_SCSI_LOGGING=y - -# -# SCSI Transport Attributes -# -CONFIG_SCSI_SPI_ATTRS=m -CONFIG_SCSI_FC_ATTRS=m -CONFIG_SCSI_ISCSI_ATTRS=m - -# -# SCSI low-level drivers -# -CONFIG_BLK_DEV_3W_XXXX_RAID=m -CONFIG_SCSI_3W_9XXX=m -CONFIG_SCSI_ACARD=m -CONFIG_SCSI_AACRAID=m -CONFIG_SCSI_AIC7XXX=m -CONFIG_AIC7XXX_CMDS_PER_DEVICE=4 -CONFIG_AIC7XXX_RESET_DELAY_MS=15000 -# CONFIG_AIC7XXX_DEBUG_ENABLE is not set -CONFIG_AIC7XXX_DEBUG_MASK=0 -# CONFIG_AIC7XXX_REG_PRETTY_PRINT is not set -CONFIG_SCSI_AIC7XXX_OLD=m -CONFIG_SCSI_AIC79XX=m -CONFIG_AIC79XX_CMDS_PER_DEVICE=4 -CONFIG_AIC79XX_RESET_DELAY_MS=15000 -# CONFIG_AIC79XX_ENABLE_RD_STRM is not set -# CONFIG_AIC79XX_DEBUG_ENABLE is not set -CONFIG_AIC79XX_DEBUG_MASK=0 -# CONFIG_AIC79XX_REG_PRETTY_PRINT is not set -# CONFIG_SCSI_ADVANSYS is not set -CONFIG_MEGARAID_NEWGEN=y -CONFIG_MEGARAID_MM=m -CONFIG_MEGARAID_MAILBOX=m -CONFIG_SCSI_SATA=y -CONFIG_SCSI_SATA_AHCI=m -CONFIG_SCSI_SATA_SVW=m -CONFIG_SCSI_ATA_PIIX=y -CONFIG_SCSI_SATA_NV=m -CONFIG_SCSI_SATA_PROMISE=m -CONFIG_SCSI_SATA_QSTOR=m -CONFIG_SCSI_SATA_SX4=m -CONFIG_SCSI_SATA_SIL=m -CONFIG_SCSI_SATA_SIS=m -CONFIG_SCSI_SATA_ULI=m -CONFIG_SCSI_SATA_VIA=m -CONFIG_SCSI_SATA_VITESSE=m -CONFIG_SCSI_BUSLOGIC=m -# CONFIG_SCSI_OMIT_FLASHPOINT is not set -# CONFIG_SCSI_CPQFCTS is not set -# CONFIG_SCSI_DMX3191D is not set -# CONFIG_SCSI_EATA is not set -# CONFIG_SCSI_EATA_PIO is not set -# CONFIG_SCSI_FUTURE_DOMAIN is not set -CONFIG_SCSI_GDTH=m -CONFIG_SCSI_IPS=m -CONFIG_SCSI_INITIO=m -CONFIG_SCSI_INIA100=m -CONFIG_SCSI_PPA=m -CONFIG_SCSI_IMM=m -# CONFIG_SCSI_IZIP_EPP16 is not set -# CONFIG_SCSI_IZIP_SLOW_CTR is not set -CONFIG_SCSI_SYM53C8XX_2=m -CONFIG_SCSI_SYM53C8XX_DMA_ADDRESSING_MODE=1 -CONFIG_SCSI_SYM53C8XX_DEFAULT_TAGS=16 -CONFIG_SCSI_SYM53C8XX_MAX_TAGS=64 -# CONFIG_SCSI_SYM53C8XX_IOMAPPED is not set -# CONFIG_SCSI_IPR is not set -# CONFIG_SCSI_PCI2000 is not set -# CONFIG_SCSI_PCI2220I is not set -# CONFIG_SCSI_QLOGIC_ISP is not set -# CONFIG_SCSI_QLOGIC_FC is not set -CONFIG_SCSI_QLOGIC_1280=m -CONFIG_SCSI_QLOGIC_1280_1040=y -CONFIG_SCSI_QLA2XXX=y -CONFIG_SCSI_QLA21XX=m -CONFIG_SCSI_QLA22XX=m -CONFIG_SCSI_QLA2300=m -CONFIG_SCSI_QLA2322=m -CONFIG_SCSI_QLA6312=m -CONFIG_SCSI_LPFC=m -CONFIG_SCSI_DC395x=m -CONFIG_SCSI_DC390T=m -# CONFIG_SCSI_DEBUG is not set - -# -# Multi-device support (RAID and LVM) -# -CONFIG_MD=y -CONFIG_BLK_DEV_MD=y -CONFIG_MD_LINEAR=m -CONFIG_MD_RAID0=m -CONFIG_MD_RAID1=m -CONFIG_MD_RAID10=m -CONFIG_MD_RAID5=m -CONFIG_MD_RAID6=m -CONFIG_MD_MULTIPATH=m -CONFIG_MD_FAULTY=m -CONFIG_BLK_DEV_DM=m -CONFIG_DM_CRYPT=m -CONFIG_DM_SNAPSHOT=m -CONFIG_DM_MIRROR=m -CONFIG_DM_ZERO=m -CONFIG_DM_MULTIPATH=m -CONFIG_DM_MULTIPATH_EMC=m - -# -# Fusion MPT device support -# -CONFIG_FUSION=m -CONFIG_FUSION_MAX_SGE=40 -CONFIG_FUSION_CTL=m -CONFIG_FUSION_LAN=m - -# -# IEEE 1394 (FireWire) support -# -CONFIG_IEEE1394=m - -# -# Subsystem Options -# -# CONFIG_IEEE1394_VERBOSEDEBUG is not set -CONFIG_IEEE1394_OUI_DB=y -CONFIG_IEEE1394_EXTRA_CONFIG_ROMS=y -CONFIG_IEEE1394_CONFIG_ROM_IP1394=y - -# -# Device Drivers -# -CONFIG_IEEE1394_PCILYNX=m -CONFIG_IEEE1394_OHCI1394=m - -# -# Protocol Drivers -# -CONFIG_IEEE1394_VIDEO1394=m -CONFIG_IEEE1394_SBP2=m -# CONFIG_IEEE1394_SBP2_PHYS_DMA is not set -CONFIG_IEEE1394_ETH1394=m -CONFIG_IEEE1394_DV1394=m -CONFIG_IEEE1394_RAWIO=m -CONFIG_IEEE1394_CMP=m -CONFIG_IEEE1394_AMDTP=m - -# -# I2O device support -# -CONFIG_I2O=m -CONFIG_I2O_CONFIG=m -CONFIG_I2O_BLOCK=m -CONFIG_I2O_SCSI=m -CONFIG_I2O_PROC=m - -# -# Networking support -# -CONFIG_NET=y - -# -# Networking options -# -CONFIG_PACKET=y -CONFIG_PACKET_MMAP=y -CONFIG_UNIX=y -CONFIG_NET_KEY=m -CONFIG_INET=y -CONFIG_IP_MULTICAST=y -CONFIG_IP_ADVANCED_ROUTER=y -CONFIG_IP_MULTIPLE_TABLES=y -CONFIG_IP_ROUTE_FWMARK=y -CONFIG_IP_ROUTE_MULTIPATH=y -# CONFIG_IP_ROUTE_MULTIPATH_CACHED is not set -CONFIG_IP_ROUTE_VERBOSE=y -# CONFIG_IP_PNP is not set -CONFIG_NET_IPIP=m -CONFIG_NET_IPGRE=m -CONFIG_NET_IPGRE_BROADCAST=y -CONFIG_IP_MROUTE=y -CONFIG_IP_PIMSM_V1=y -CONFIG_IP_PIMSM_V2=y -# CONFIG_ARPD is not set -CONFIG_SYN_COOKIES=y -CONFIG_INET_AH=m -CONFIG_INET_ESP=m -CONFIG_INET_IPCOMP=m -CONFIG_INET_TUNNEL=m -CONFIG_IP_TCPDIAG=m -CONFIG_IP_TCPDIAG_IPV6=y - -# -# IP: Virtual Server Configuration -# -CONFIG_IP_VS=m -# CONFIG_IP_VS_DEBUG is not set -CONFIG_IP_VS_TAB_BITS=12 - -# -# IPVS transport protocol load balancing support -# -CONFIG_IP_VS_PROTO_TCP=y -CONFIG_IP_VS_PROTO_UDP=y -CONFIG_IP_VS_PROTO_ESP=y -CONFIG_IP_VS_PROTO_AH=y - -# -# IPVS scheduler -# -CONFIG_IP_VS_RR=m -CONFIG_IP_VS_WRR=m -CONFIG_IP_VS_LC=m -CONFIG_IP_VS_WLC=m -CONFIG_IP_VS_LBLC=m -CONFIG_IP_VS_LBLCR=m -CONFIG_IP_VS_DH=m -CONFIG_IP_VS_SH=m -CONFIG_IP_VS_SED=m -CONFIG_IP_VS_NQ=m - -# -# IPVS application helper -# -CONFIG_IP_VS_FTP=m -CONFIG_IPV6=m -CONFIG_IPV6_PRIVACY=y -CONFIG_INET6_AH=m -CONFIG_INET6_ESP=m -CONFIG_INET6_IPCOMP=m -CONFIG_INET6_TUNNEL=m -CONFIG_IPV6_TUNNEL=m -CONFIG_NETFILTER=y -# CONFIG_NETFILTER_DEBUG is not set -CONFIG_BRIDGE_NETFILTER=y - -# -# IP: Netfilter Configuration -# -CONFIG_IP_NF_CONNTRACK=m -CONFIG_IP_NF_CT_ACCT=y -CONFIG_IP_NF_CONNTRACK_MARK=y -CONFIG_IP_NF_CT_PROTO_SCTP=m -CONFIG_IP_NF_FTP=m -CONFIG_IP_NF_IRC=m -CONFIG_IP_NF_TFTP=m -CONFIG_IP_NF_AMANDA=m -CONFIG_IP_NF_QUEUE=m -CONFIG_IP_NF_IPTABLES=m -CONFIG_IP_NF_MATCH_LIMIT=m -CONFIG_IP_NF_MATCH_IPRANGE=m -CONFIG_IP_NF_MATCH_MAC=m -CONFIG_IP_NF_MATCH_PKTTYPE=m -CONFIG_IP_NF_MATCH_MARK=m -CONFIG_IP_NF_MATCH_MULTIPORT=m -CONFIG_IP_NF_MATCH_TOS=m -CONFIG_IP_NF_MATCH_RECENT=m -CONFIG_IP_NF_MATCH_ECN=m -CONFIG_IP_NF_MATCH_DSCP=m -CONFIG_IP_NF_MATCH_AH_ESP=m -CONFIG_IP_NF_MATCH_LENGTH=m -CONFIG_IP_NF_MATCH_TTL=m -CONFIG_IP_NF_MATCH_TCPMSS=m -CONFIG_IP_NF_MATCH_HELPER=m -CONFIG_IP_NF_MATCH_STATE=m -CONFIG_IP_NF_MATCH_CONNTRACK=m -CONFIG_IP_NF_MATCH_OWNER=m -CONFIG_IP_NF_MATCH_PHYSDEV=m -CONFIG_IP_NF_MATCH_ADDRTYPE=m -CONFIG_IP_NF_MATCH_REALM=m -CONFIG_IP_NF_MATCH_SCTP=m -CONFIG_IP_NF_MATCH_COMMENT=m -CONFIG_IP_NF_MATCH_CONNMARK=m -CONFIG_IP_NF_MATCH_HASHLIMIT=m -CONFIG_IP_NF_FILTER=m -CONFIG_IP_NF_TARGET_REJECT=m -CONFIG_IP_NF_TARGET_LOG=m -CONFIG_IP_NF_TARGET_ULOG=m -CONFIG_IP_NF_TARGET_TCPMSS=m -CONFIG_IP_NF_NAT=m -CONFIG_IP_NF_NAT_NEEDED=y -CONFIG_IP_NF_TARGET_MASQUERADE=m -CONFIG_IP_NF_TARGET_REDIRECT=m -CONFIG_IP_NF_TARGET_NETMAP=m -CONFIG_IP_NF_TARGET_SAME=m -CONFIG_IP_NF_NAT_SNMP_BASIC=m -CONFIG_IP_NF_NAT_IRC=m -CONFIG_IP_NF_NAT_FTP=m -CONFIG_IP_NF_NAT_TFTP=m -CONFIG_IP_NF_NAT_AMANDA=m -CONFIG_IP_NF_MANGLE=m -CONFIG_IP_NF_TARGET_TOS=m -CONFIG_IP_NF_TARGET_ECN=m -CONFIG_IP_NF_TARGET_DSCP=m -CONFIG_IP_NF_TARGET_MARK=m -CONFIG_IP_NF_TARGET_CLASSIFY=m -CONFIG_IP_NF_TARGET_CONNMARK=m -CONFIG_IP_NF_TARGET_CLUSTERIP=m -CONFIG_IP_NF_RAW=m -CONFIG_IP_NF_TARGET_NOTRACK=m -CONFIG_IP_NF_ARPTABLES=m -CONFIG_IP_NF_ARPFILTER=m -CONFIG_IP_NF_ARP_MANGLE=m - -# -# IPv6: Netfilter Configuration (EXPERIMENTAL) -# -CONFIG_IP6_NF_QUEUE=m -CONFIG_IP6_NF_IPTABLES=m -CONFIG_IP6_NF_MATCH_LIMIT=m -CONFIG_IP6_NF_MATCH_MAC=m -CONFIG_IP6_NF_MATCH_RT=m -CONFIG_IP6_NF_MATCH_OPTS=m -CONFIG_IP6_NF_MATCH_FRAG=m -CONFIG_IP6_NF_MATCH_HL=m -CONFIG_IP6_NF_MATCH_MULTIPORT=m -CONFIG_IP6_NF_MATCH_OWNER=m -CONFIG_IP6_NF_MATCH_MARK=m -CONFIG_IP6_NF_MATCH_IPV6HEADER=m -CONFIG_IP6_NF_MATCH_AHESP=m -CONFIG_IP6_NF_MATCH_LENGTH=m -CONFIG_IP6_NF_MATCH_EUI64=m -CONFIG_IP6_NF_MATCH_PHYSDEV=m -CONFIG_IP6_NF_FILTER=m -CONFIG_IP6_NF_TARGET_LOG=m -CONFIG_IP6_NF_MANGLE=m -CONFIG_IP6_NF_TARGET_MARK=m -CONFIG_IP6_NF_RAW=m - -# -# Bridge: Netfilter Configuration -# -CONFIG_BRIDGE_NF_EBTABLES=m -CONFIG_BRIDGE_EBT_BROUTE=m -CONFIG_BRIDGE_EBT_T_FILTER=m -CONFIG_BRIDGE_EBT_T_NAT=m -CONFIG_BRIDGE_EBT_802_3=m -CONFIG_BRIDGE_EBT_AMONG=m -CONFIG_BRIDGE_EBT_ARP=m -CONFIG_BRIDGE_EBT_IP=m -CONFIG_BRIDGE_EBT_LIMIT=m -CONFIG_BRIDGE_EBT_MARK=m -CONFIG_BRIDGE_EBT_PKTTYPE=m -CONFIG_BRIDGE_EBT_STP=m -CONFIG_BRIDGE_EBT_VLAN=m -CONFIG_BRIDGE_EBT_ARPREPLY=m -CONFIG_BRIDGE_EBT_DNAT=m -CONFIG_BRIDGE_EBT_MARK_T=m -CONFIG_BRIDGE_EBT_REDIRECT=m -CONFIG_BRIDGE_EBT_SNAT=m -CONFIG_BRIDGE_EBT_LOG=m -CONFIG_BRIDGE_EBT_ULOG=m -CONFIG_XFRM=y -CONFIG_XFRM_USER=y - -# -# SCTP Configuration (EXPERIMENTAL) -# -CONFIG_IP_SCTP=m -# CONFIG_SCTP_DBG_MSG is not set -# CONFIG_SCTP_DBG_OBJCNT is not set -# CONFIG_SCTP_HMAC_NONE is not set -# CONFIG_SCTP_HMAC_SHA1 is not set -CONFIG_SCTP_HMAC_MD5=y -CONFIG_ATM=m -CONFIG_ATM_CLIP=m -# CONFIG_ATM_CLIP_NO_ICMP is not set -CONFIG_ATM_LANE=m -# CONFIG_ATM_MPOA is not set -CONFIG_ATM_BR2684=m -# CONFIG_ATM_BR2684_IPFILTER is not set -CONFIG_BRIDGE=m -CONFIG_VLAN_8021Q=m -# CONFIG_DECNET is not set -CONFIG_LLC=y -# CONFIG_LLC2 is not set -CONFIG_IPX=m -# CONFIG_IPX_INTERN is not set -CONFIG_ATALK=m -CONFIG_DEV_APPLETALK=y -CONFIG_IPDDP=m -CONFIG_IPDDP_ENCAP=y -CONFIG_IPDDP_DECAP=y -# CONFIG_X25 is not set -# CONFIG_LAPB is not set -CONFIG_NET_DIVERT=y -# CONFIG_ECONET is not set -CONFIG_WAN_ROUTER=m - -# -# QoS and/or fair queueing -# -CONFIG_NET_SCHED=y -CONFIG_NET_SCH_CLK_JIFFIES=y -# CONFIG_NET_SCH_CLK_GETTIMEOFDAY is not set -# CONFIG_NET_SCH_CLK_CPU is not set -CONFIG_NET_SCH_CBQ=m -CONFIG_NET_SCH_HTB=m -CONFIG_NET_SCH_HFSC=m -CONFIG_NET_SCH_ATM=m -CONFIG_NET_SCH_PRIO=m -CONFIG_NET_SCH_RED=m -CONFIG_NET_SCH_SFQ=m -CONFIG_NET_SCH_TEQL=m -CONFIG_NET_SCH_TBF=m -CONFIG_NET_SCH_GRED=m -CONFIG_NET_SCH_DSMARK=m -CONFIG_NET_SCH_NETEM=m -CONFIG_NET_SCH_INGRESS=m -CONFIG_NET_QOS=y -CONFIG_NET_ESTIMATOR=y -CONFIG_NET_CLS=y -CONFIG_NET_CLS_BASIC=m -CONFIG_NET_CLS_TCINDEX=m -CONFIG_NET_CLS_ROUTE4=m -CONFIG_NET_CLS_ROUTE=y -CONFIG_NET_CLS_FW=m -CONFIG_NET_CLS_U32=m -CONFIG_CLS_U32_PERF=y -CONFIG_NET_CLS_IND=y -CONFIG_CLS_U32_MARK=y -CONFIG_NET_CLS_RSVP=m -CONFIG_NET_CLS_RSVP6=m -CONFIG_NET_EMATCH=y -CONFIG_NET_EMATCH_STACK=32 -CONFIG_NET_EMATCH_CMP=m -CONFIG_NET_EMATCH_NBYTE=m -CONFIG_NET_EMATCH_U32=m -CONFIG_NET_EMATCH_META=m -# CONFIG_NET_CLS_ACT is not set -CONFIG_NET_CLS_POLICE=y - -# -# Network testing -# -# CONFIG_NET_PKTGEN is not set -CONFIG_NETPOLL=y -# CONFIG_NETPOLL_RX is not set -CONFIG_NETPOLL_TRAP=y -CONFIG_NET_POLL_CONTROLLER=y -# CONFIG_HAMRADIO is not set -CONFIG_IRDA=m - -# -# IrDA protocols -# -CONFIG_IRLAN=m -CONFIG_IRNET=m -CONFIG_IRCOMM=m -# CONFIG_IRDA_ULTRA is not set - -# -# IrDA options -# -CONFIG_IRDA_CACHE_LAST_LSAP=y -CONFIG_IRDA_FAST_RR=y -# CONFIG_IRDA_DEBUG is not set - -# -# Infrared-port device drivers -# - -# -# SIR device drivers -# -CONFIG_IRTTY_SIR=m - -# -# Dongle support -# -CONFIG_DONGLE=y -CONFIG_ESI_DONGLE=m -CONFIG_ACTISYS_DONGLE=m -CONFIG_TEKRAM_DONGLE=m -CONFIG_LITELINK_DONGLE=m -CONFIG_MA600_DONGLE=m -CONFIG_GIRBIL_DONGLE=m -CONFIG_MCP2120_DONGLE=m -CONFIG_OLD_BELKIN_DONGLE=m -CONFIG_ACT200L_DONGLE=m - -# -# Old SIR device drivers -# -CONFIG_IRPORT_SIR=m - -# -# Old Serial dongle support -# -# CONFIG_DONGLE_OLD is not set - -# -# FIR device drivers -# -CONFIG_USB_IRDA=m -CONFIG_SIGMATEL_FIR=m -CONFIG_NSC_FIR=m -CONFIG_WINBOND_FIR=m -CONFIG_SMC_IRCC_FIR=m -CONFIG_ALI_FIR=m -CONFIG_VLSI_FIR=m -CONFIG_VIA_FIR=m -CONFIG_BT=m -CONFIG_BT_L2CAP=m -CONFIG_BT_SCO=m -CONFIG_BT_RFCOMM=m -CONFIG_BT_RFCOMM_TTY=y -CONFIG_BT_BNEP=m -CONFIG_BT_BNEP_MC_FILTER=y -CONFIG_BT_BNEP_PROTO_FILTER=y -CONFIG_BT_CMTP=m -CONFIG_BT_HIDP=m - -# -# Bluetooth device drivers -# -CONFIG_BT_HCIUSB=m -CONFIG_BT_HCIUSB_SCO=y -CONFIG_BT_HCIUART=m -CONFIG_BT_HCIUART_H4=y -CONFIG_BT_HCIUART_BCSP=y -CONFIG_BT_HCIUART_BCSP_TXCRC=y -CONFIG_BT_HCIBCM203X=m -CONFIG_BT_HCIBPA10X=m -CONFIG_BT_HCIBFUSB=m -CONFIG_BT_HCIVHCI=m -CONFIG_NETDEVICES=y -CONFIG_DUMMY=m -CONFIG_BONDING=m -CONFIG_EQUALIZER=m -CONFIG_TUN=m - -# -# ARCnet devices -# -# CONFIG_ARCNET is not set - -# -# Ethernet (10 or 100Mbit) -# -CONFIG_NET_ETHERNET=y -CONFIG_MII=m -CONFIG_HAPPYMEAL=m -CONFIG_SUNGEM=m -CONFIG_NET_VENDOR_3COM=y -CONFIG_VORTEX=m -CONFIG_TYPHOON=m - -# -# Tulip family network device support -# -CONFIG_NET_TULIP=y -CONFIG_DE2104X=m -CONFIG_TULIP=m -# CONFIG_TULIP_MWI is not set -CONFIG_TULIP_MMIO=y -# CONFIG_TULIP_NAPI is not set -CONFIG_DE4X5=m -CONFIG_WINBOND_840=m -CONFIG_DM9102=m -# CONFIG_HP100 is not set -CONFIG_NET_PCI=y -CONFIG_PCNET32=m -CONFIG_AMD8111_ETH=m -CONFIG_AMD8111E_NAPI=y -CONFIG_ADAPTEC_STARFIRE=m -CONFIG_ADAPTEC_STARFIRE_NAPI=y -CONFIG_B44=m -CONFIG_FORCEDETH=m -CONFIG_DGRS=m -CONFIG_EEPRO100=m -CONFIG_E100=m -CONFIG_FEALNX=m -CONFIG_NATSEMI=m -CONFIG_NE2K_PCI=m -CONFIG_8139CP=m -CONFIG_8139TOO=m -CONFIG_8139TOO_PIO=y -# CONFIG_8139TOO_TUNE_TWISTER is not set -CONFIG_8139TOO_8129=y -# CONFIG_8139_OLD_RX_RESET is not set -CONFIG_SIS900=m -CONFIG_EPIC100=m -CONFIG_SUNDANCE=m -# CONFIG_SUNDANCE_MMIO is not set -CONFIG_VIA_RHINE=m -CONFIG_VIA_RHINE_MMIO=y - -# -# Ethernet (1000 Mbit) -# -CONFIG_ACENIC=m -# CONFIG_ACENIC_OMIT_TIGON_I is not set -CONFIG_DL2K=m -CONFIG_E1000=m -CONFIG_E1000_NAPI=y -CONFIG_NS83820=m -CONFIG_HAMACHI=m -CONFIG_YELLOWFIN=m -CONFIG_R8169=m -CONFIG_R8169_NAPI=y -CONFIG_R8169_VLAN=y -CONFIG_SK98LIN=m -CONFIG_VIA_VELOCITY=m -CONFIG_TIGON3=m -CONFIG_BNX2=m - -# -# Ethernet (10000 Mbit) -# -CONFIG_IXGB=m -CONFIG_IXGB_NAPI=y -CONFIG_S2IO=m -CONFIG_S2IO_NAPI=y -# CONFIG_2BUFF_MODE is not set - -# -# Token Ring devices -# -CONFIG_TR=y -CONFIG_IBMOL=m -CONFIG_3C359=m -CONFIG_TMS380TR=m -CONFIG_TMSPCI=m -CONFIG_ABYSS=m - -# -# Wireless LAN (non-hamradio) -# -CONFIG_NET_RADIO=y - -# -# Obsolete Wireless cards support (pre-802.11) -# -# CONFIG_STRIP is not set - -# -# Wireless 802.11b ISA/PCI cards support -# -CONFIG_HERMES=m -CONFIG_PLX_HERMES=m -CONFIG_TMD_HERMES=m -CONFIG_PCI_HERMES=m -CONFIG_ATMEL=m -CONFIG_PCI_ATMEL=m - -# -# Prism GT/Duette 802.11(a/b/g) PCI/Cardbus support -# -CONFIG_PRISM54=m -CONFIG_NET_WIRELESS=y - -# -# Wan interfaces -# -# CONFIG_WAN is not set - -# -# ATM drivers -# -CONFIG_ATM_TCP=m -CONFIG_ATM_LANAI=m -CONFIG_ATM_ENI=m -# CONFIG_ATM_ENI_DEBUG is not set -# CONFIG_ATM_ENI_TUNE_BURST is not set -CONFIG_ATM_FIRESTREAM=m -# CONFIG_ATM_ZATM is not set -CONFIG_ATM_IDT77252=m -# CONFIG_ATM_IDT77252_DEBUG is not set -# CONFIG_ATM_IDT77252_RCV_ALL is not set -CONFIG_ATM_IDT77252_USE_SUNI=y -CONFIG_ATM_AMBASSADOR=m -# CONFIG_ATM_AMBASSADOR_DEBUG is not set -CONFIG_ATM_HORIZON=m -# CONFIG_ATM_HORIZON_DEBUG is not set -CONFIG_ATM_FORE200E_MAYBE=m -# CONFIG_ATM_FORE200E_PCA is not set -CONFIG_ATM_HE=m -# CONFIG_ATM_HE_USE_SUNI is not set -CONFIG_FDDI=y -# CONFIG_DEFXX is not set -CONFIG_SKFP=m -# CONFIG_HIPPI is not set -CONFIG_PLIP=m -CONFIG_PPP=m -CONFIG_PPP_MULTILINK=y -CONFIG_PPP_FILTER=y -CONFIG_PPP_ASYNC=m -CONFIG_PPP_SYNC_TTY=m -CONFIG_PPP_DEFLATE=m -# CONFIG_PPP_BSDCOMP is not set -CONFIG_PPPOE=m -CONFIG_PPPOATM=m -CONFIG_SLIP=m -CONFIG_SLIP_COMPRESSED=y -CONFIG_SLIP_SMART=y -# CONFIG_SLIP_MODE_SLIP6 is not set -CONFIG_NET_FC=y -# CONFIG_SHAPER is not set -CONFIG_NETCONSOLE=m - -# -# ISDN subsystem -# -CONFIG_ISDN=m - -# -# Old ISDN4Linux -# -CONFIG_ISDN_I4L=m -CONFIG_ISDN_PPP=y -CONFIG_ISDN_PPP_VJ=y -CONFIG_ISDN_MPP=y -CONFIG_IPPP_FILTER=y -# CONFIG_ISDN_PPP_BSDCOMP is not set -CONFIG_ISDN_AUDIO=y -CONFIG_ISDN_TTY_FAX=y - -# -# ISDN feature submodules -# -CONFIG_ISDN_DRV_LOOP=m -CONFIG_ISDN_DIVERSION=m - -# -# ISDN4Linux hardware drivers -# - -# -# Passive cards -# -CONFIG_ISDN_DRV_HISAX=m - -# -# D-channel protocol features -# -CONFIG_HISAX_EURO=y -CONFIG_DE_AOC=y -CONFIG_HISAX_NO_SENDCOMPLETE=y -CONFIG_HISAX_NO_LLC=y -CONFIG_HISAX_NO_KEYPAD=y -CONFIG_HISAX_1TR6=y -CONFIG_HISAX_NI1=y -CONFIG_HISAX_MAX_CARDS=8 - -# -# HiSax supported cards -# -CONFIG_HISAX_16_3=y -CONFIG_HISAX_TELESPCI=y -CONFIG_HISAX_S0BOX=y -CONFIG_HISAX_FRITZPCI=y -CONFIG_HISAX_AVM_A1_PCMCIA=y -CONFIG_HISAX_ELSA=y -CONFIG_HISAX_DIEHLDIVA=y -CONFIG_HISAX_SEDLBAUER=y -CONFIG_HISAX_NETJET=y -CONFIG_HISAX_NETJET_U=y -CONFIG_HISAX_NICCY=y -CONFIG_HISAX_BKM_A4T=y -CONFIG_HISAX_SCT_QUADRO=y -CONFIG_HISAX_GAZEL=y -CONFIG_HISAX_HFC_PCI=y -CONFIG_HISAX_W6692=y -CONFIG_HISAX_HFC_SX=y -CONFIG_HISAX_ENTERNOW_PCI=y -# CONFIG_HISAX_DEBUG is not set - -# -# HiSax PCMCIA card service modules -# - -# -# HiSax sub driver modules -# -CONFIG_HISAX_ST5481=m -CONFIG_HISAX_HFCUSB=m -CONFIG_HISAX_HFC4S8S=m -CONFIG_HISAX_FRITZ_PCIPNP=m -CONFIG_HISAX_HDLC=y - -# -# Active cards -# -CONFIG_HYSDN=m -CONFIG_HYSDN_CAPI=y - -# -# CAPI subsystem -# -CONFIG_ISDN_CAPI=m -CONFIG_ISDN_DRV_AVMB1_VERBOSE_REASON=y -CONFIG_ISDN_CAPI_MIDDLEWARE=y -CONFIG_ISDN_CAPI_CAPI20=m -CONFIG_ISDN_CAPI_CAPIFS_BOOL=y -CONFIG_ISDN_CAPI_CAPIFS=m -CONFIG_ISDN_CAPI_CAPIDRV=m - -# -# CAPI hardware drivers -# - -# -# Active AVM cards -# -CONFIG_CAPI_AVM=y -CONFIG_ISDN_DRV_AVMB1_B1PCI=m -CONFIG_ISDN_DRV_AVMB1_B1PCIV4=y -CONFIG_ISDN_DRV_AVMB1_B1PCMCIA=m -CONFIG_ISDN_DRV_AVMB1_T1PCI=m -CONFIG_ISDN_DRV_AVMB1_C4=m - -# -# Active Eicon DIVA Server cards -# -# CONFIG_CAPI_EICON is not set - -# -# Telephony Support -# -# CONFIG_PHONE is not set - -# -# Input device support -# -CONFIG_INPUT=y - -# -# Userland interfaces -# -CONFIG_INPUT_MOUSEDEV=y -# CONFIG_INPUT_MOUSEDEV_PSAUX is not set -CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024 -CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768 -CONFIG_INPUT_JOYDEV=m -# CONFIG_INPUT_TSDEV is not set -CONFIG_INPUT_EVDEV=y -# CONFIG_INPUT_EVBUG is not set - -# -# Input Device Drivers -# -CONFIG_INPUT_KEYBOARD=y -CONFIG_KEYBOARD_ATKBD=y -# CONFIG_KEYBOARD_SUNKBD is not set -# CONFIG_KEYBOARD_LKKBD is not set -# CONFIG_KEYBOARD_XTKBD is not set -# CONFIG_KEYBOARD_NEWTON is not set -CONFIG_INPUT_MOUSE=y -CONFIG_MOUSE_PS2=y -CONFIG_MOUSE_SERIAL=m -CONFIG_MOUSE_VSXXXAA=m -CONFIG_INPUT_JOYSTICK=y -CONFIG_JOYSTICK_ANALOG=m -CONFIG_JOYSTICK_A3D=m -CONFIG_JOYSTICK_ADI=m -CONFIG_JOYSTICK_COBRA=m -CONFIG_JOYSTICK_GF2K=m -CONFIG_JOYSTICK_GRIP=m -CONFIG_JOYSTICK_GRIP_MP=m -CONFIG_JOYSTICK_GUILLEMOT=m -CONFIG_JOYSTICK_INTERACT=m -CONFIG_JOYSTICK_SIDEWINDER=m -CONFIG_JOYSTICK_TMDC=m -CONFIG_JOYSTICK_IFORCE=m -CONFIG_JOYSTICK_IFORCE_USB=y -CONFIG_JOYSTICK_IFORCE_232=y -CONFIG_JOYSTICK_WARRIOR=m -CONFIG_JOYSTICK_MAGELLAN=m -CONFIG_JOYSTICK_SPACEORB=m -CONFIG_JOYSTICK_SPACEBALL=m -CONFIG_JOYSTICK_STINGER=m -CONFIG_JOYSTICK_TWIDJOY=m -CONFIG_JOYSTICK_DB9=m -CONFIG_JOYSTICK_GAMECON=m -CONFIG_JOYSTICK_TURBOGRAFX=m -CONFIG_JOYSTICK_JOYDUMP=m -CONFIG_INPUT_TOUCHSCREEN=y -CONFIG_TOUCHSCREEN_GUNZE=m -CONFIG_TOUCHSCREEN_ELO=m -CONFIG_TOUCHSCREEN_MTOUCH=m -CONFIG_TOUCHSCREEN_MK712=m -CONFIG_INPUT_MISC=y -CONFIG_INPUT_PCSPKR=m -CONFIG_INPUT_UINPUT=m - -# -# Hardware I/O ports -# -CONFIG_SERIO=y -CONFIG_SERIO_I8042=y -CONFIG_SERIO_SERPORT=y -# CONFIG_SERIO_CT82C710 is not set -# CONFIG_SERIO_PARKBD is not set -# CONFIG_SERIO_PCIPS2 is not set -CONFIG_SERIO_LIBPS2=y -# CONFIG_SERIO_RAW is not set -CONFIG_GAMEPORT=m -CONFIG_GAMEPORT_NS558=m -CONFIG_GAMEPORT_L4=m -CONFIG_GAMEPORT_EMU10K1=m -CONFIG_GAMEPORT_VORTEX=m -CONFIG_GAMEPORT_FM801=m -CONFIG_GAMEPORT_CS461X=m - -# -# Character devices -# -CONFIG_VT=y -CONFIG_VT_CONSOLE=y -CONFIG_HW_CONSOLE=y -# CONFIG_SERIAL_NONSTANDARD is not set - -# -# Serial drivers -# -# CONFIG_SERIAL_8250 is not set - -# -# Non-8250 serial port support -# -# CONFIG_SERIAL_JSM is not set -CONFIG_UNIX98_PTYS=y -# CONFIG_LEGACY_PTYS is not set -CONFIG_PRINTER=m -CONFIG_LP_CONSOLE=y -CONFIG_PPDEV=m -CONFIG_TIPAR=m - -# -# IPMI -# -CONFIG_IPMI_HANDLER=m -# CONFIG_IPMI_PANIC_EVENT is not set -CONFIG_IPMI_DEVICE_INTERFACE=m -CONFIG_IPMI_SI=m -CONFIG_IPMI_WATCHDOG=m -CONFIG_IPMI_POWEROFF=m - -# -# Watchdog Cards -# -CONFIG_WATCHDOG=y -# CONFIG_WATCHDOG_NOWAYOUT is not set - -# -# Watchdog Device Drivers -# -CONFIG_SOFT_WATCHDOG=m -CONFIG_ACQUIRE_WDT=m -CONFIG_ADVANTECH_WDT=m -CONFIG_ALIM1535_WDT=m -CONFIG_ALIM7101_WDT=m -CONFIG_SC520_WDT=m -CONFIG_EUROTECH_WDT=m -CONFIG_IB700_WDT=m -CONFIG_WAFER_WDT=m -CONFIG_I8XX_TCO=m -CONFIG_SC1200_WDT=m -# CONFIG_60XX_WDT is not set -CONFIG_CPU5_WDT=m -CONFIG_W83627HF_WDT=m -CONFIG_W83877F_WDT=m -CONFIG_MACHZ_WDT=m - -# -# PCI-based Watchdog Cards -# -CONFIG_PCIPCWATCHDOG=m -CONFIG_WDTPCI=m -CONFIG_WDT_501_PCI=y - -# -# USB-based Watchdog Cards -# -CONFIG_USBPCWATCHDOG=m -CONFIG_HW_RANDOM=m -# CONFIG_NVRAM is not set -CONFIG_RTC=y -CONFIG_DTLK=m -CONFIG_R3964=m -# CONFIG_APPLICOM is not set - -# -# Ftape, the floppy tape device driver -# -# CONFIG_FTAPE is not set -# CONFIG_AGP is not set -CONFIG_DRM=m -CONFIG_DRM_TDFX=m -# CONFIG_DRM_GAMMA is not set -CONFIG_DRM_R128=m -CONFIG_DRM_RADEON=m -# CONFIG_MWAVE is not set -# CONFIG_RAW_DRIVER is not set -# CONFIG_HPET is not set -CONFIG_HANGCHECK_TIMER=m - -# -# TPM devices -# -# CONFIG_TCG_TPM is not set - -# -# I2C support -# -CONFIG_I2C=m -CONFIG_I2C_CHARDEV=m - -# -# I2C Algorithms -# -CONFIG_I2C_ALGOBIT=m -CONFIG_I2C_ALGOPCF=m -CONFIG_I2C_ALGOPCA=m - -# -# I2C Hardware Bus support -# -# CONFIG_I2C_ALI1535 is not set -# CONFIG_I2C_ALI1563 is not set -# CONFIG_I2C_ALI15X3 is not set -CONFIG_I2C_AMD756=m -CONFIG_I2C_AMD756_S4882=m -CONFIG_I2C_AMD8111=m -# CONFIG_I2C_I801 is not set -# CONFIG_I2C_I810 is not set -# CONFIG_I2C_PIIX4 is not set -CONFIG_I2C_ISA=m -CONFIG_I2C_NFORCE2=m -# CONFIG_I2C_PARPORT is not set -# CONFIG_I2C_PARPORT_LIGHT is not set -CONFIG_I2C_PROSAVAGE=m -CONFIG_I2C_SAVAGE4=m -# CONFIG_SCx200_ACB is not set -# CONFIG_I2C_SIS5595 is not set -# CONFIG_I2C_SIS630 is not set -CONFIG_I2C_SIS96X=m -CONFIG_I2C_STUB=m -CONFIG_I2C_VIA=m -CONFIG_I2C_VIAPRO=m -CONFIG_I2C_VOODOO3=m -CONFIG_I2C_PCA_ISA=m - -# -# Hardware Sensors Chip support -# -CONFIG_I2C_SENSOR=m -CONFIG_SENSORS_ADM1021=m -CONFIG_SENSORS_ADM1025=m -CONFIG_SENSORS_ADM1026=m -CONFIG_SENSORS_ADM1031=m -CONFIG_SENSORS_ASB100=m -CONFIG_SENSORS_DS1621=m -CONFIG_SENSORS_FSCHER=m -CONFIG_SENSORS_FSCPOS=m -CONFIG_SENSORS_GL518SM=m -CONFIG_SENSORS_GL520SM=m -CONFIG_SENSORS_IT87=m -CONFIG_SENSORS_LM63=m -CONFIG_SENSORS_LM75=m -CONFIG_SENSORS_LM77=m -CONFIG_SENSORS_LM78=m -CONFIG_SENSORS_LM80=m -CONFIG_SENSORS_LM83=m -CONFIG_SENSORS_LM85=m -CONFIG_SENSORS_LM87=m -CONFIG_SENSORS_LM90=m -CONFIG_SENSORS_LM92=m -CONFIG_SENSORS_MAX1619=m -CONFIG_SENSORS_PC87360=m -CONFIG_SENSORS_SMSC47B397=m -CONFIG_SENSORS_SIS5595=m -CONFIG_SENSORS_SMSC47M1=m -CONFIG_SENSORS_VIA686A=m -CONFIG_SENSORS_W83781D=m -CONFIG_SENSORS_W83L785TS=m -CONFIG_SENSORS_W83627HF=m - -# -# Other I2C Chip support -# -CONFIG_SENSORS_DS1337=m -CONFIG_SENSORS_EEPROM=m -CONFIG_SENSORS_PCF8574=m -CONFIG_SENSORS_PCF8591=m -CONFIG_SENSORS_RTC8564=m -# CONFIG_I2C_DEBUG_CORE is not set -# CONFIG_I2C_DEBUG_ALGO is not set -# CONFIG_I2C_DEBUG_BUS is not set -# CONFIG_I2C_DEBUG_CHIP is not set - -# -# Dallas's 1-wire bus -# -CONFIG_W1=m -CONFIG_W1_MATROX=m -CONFIG_W1_DS9490=m -CONFIG_W1_DS9490_BRIDGE=m -CONFIG_W1_THERM=m -CONFIG_W1_SMEM=m - -# -# Misc devices -# -# CONFIG_IBM_ASM is not set - -# -# Multimedia devices -# -CONFIG_VIDEO_DEV=m - -# -# Video For Linux -# - -# -# Video Adapters -# -CONFIG_VIDEO_BT848=m -CONFIG_VIDEO_BWQCAM=m -CONFIG_VIDEO_CQCAM=m -CONFIG_VIDEO_W9966=m -CONFIG_VIDEO_CPIA=m -CONFIG_VIDEO_CPIA_PP=m -CONFIG_VIDEO_CPIA_USB=m -CONFIG_VIDEO_SAA5246A=m -CONFIG_VIDEO_SAA5249=m -CONFIG_TUNER_3036=m -CONFIG_VIDEO_STRADIS=m -CONFIG_VIDEO_ZORAN=m -CONFIG_VIDEO_ZORAN_BUZ=m -CONFIG_VIDEO_ZORAN_DC10=m -CONFIG_VIDEO_ZORAN_DC30=m -CONFIG_VIDEO_ZORAN_LML33=m -CONFIG_VIDEO_ZORAN_LML33R10=m -# CONFIG_VIDEO_ZR36120 is not set -CONFIG_VIDEO_SAA7134=m -CONFIG_VIDEO_SAA7134_DVB=m -CONFIG_VIDEO_MXB=m -CONFIG_VIDEO_DPC=m -CONFIG_VIDEO_HEXIUM_ORION=m -CONFIG_VIDEO_HEXIUM_GEMINI=m -CONFIG_VIDEO_CX88=m -CONFIG_VIDEO_CX88_DVB=m -CONFIG_VIDEO_OVCAMCHIP=m - -# -# Radio Adapters -# -CONFIG_RADIO_GEMTEK_PCI=m -CONFIG_RADIO_MAXIRADIO=m -CONFIG_RADIO_MAESTRO=m - -# -# Digital Video Broadcasting Devices -# -CONFIG_DVB=y -CONFIG_DVB_CORE=m - -# -# Supported SAA7146 based PCI Adapters -# -CONFIG_DVB_AV7110=m -CONFIG_DVB_AV7110_OSD=y -CONFIG_DVB_BUDGET=m -CONFIG_DVB_BUDGET_CI=m -CONFIG_DVB_BUDGET_AV=m -CONFIG_DVB_BUDGET_PATCH=m - -# -# Supported USB Adapters -# -CONFIG_DVB_TTUSB_BUDGET=m -CONFIG_DVB_TTUSB_DEC=m -CONFIG_DVB_DIBUSB=m -CONFIG_DVB_DIBUSB_MISDESIGNED_DEVICES=y -# CONFIG_DVB_DIBCOM_DEBUG is not set -CONFIG_DVB_CINERGYT2=m -CONFIG_DVB_CINERGYT2_TUNING=y -CONFIG_DVB_CINERGYT2_STREAM_URB_COUNT=32 -CONFIG_DVB_CINERGYT2_STREAM_BUF_SIZE=512 -CONFIG_DVB_CINERGYT2_QUERY_INTERVAL=250 -CONFIG_DVB_CINERGYT2_ENABLE_RC_INPUT_DEVICE=y -CONFIG_DVB_CINERGYT2_RC_QUERY_INTERVAL=100 - -# -# Supported FlexCopII (B2C2) Adapters -# -CONFIG_DVB_B2C2_FLEXCOP=m -CONFIG_DVB_B2C2_FLEXCOP_PCI=m -CONFIG_DVB_B2C2_FLEXCOP_USB=m -# CONFIG_DVB_B2C2_FLEXCOP_DEBUG is not set -CONFIG_DVB_B2C2_SKYSTAR=m - -# -# Supported BT878 Adapters -# -CONFIG_DVB_BT8XX=m - -# -# Supported DVB Frontends -# - -# -# Customise DVB Frontends -# - -# -# DVB-S (satellite) frontends -# -CONFIG_DVB_STV0299=m -CONFIG_DVB_CX24110=m -CONFIG_DVB_TDA8083=m -CONFIG_DVB_TDA80XX=m -CONFIG_DVB_MT312=m -CONFIG_DVB_VES1X93=m - -# -# DVB-T (terrestrial) frontends -# -CONFIG_DVB_SP8870=m -CONFIG_DVB_SP887X=m -CONFIG_DVB_CX22700=m -CONFIG_DVB_CX22702=m -CONFIG_DVB_L64781=m -CONFIG_DVB_TDA1004X=m -CONFIG_DVB_NXT6000=m -CONFIG_DVB_MT352=m -CONFIG_DVB_DIB3000MB=m -CONFIG_DVB_DIB3000MC=m - -# -# DVB-C (cable) frontends -# -CONFIG_DVB_ATMEL_AT76C651=m -CONFIG_DVB_VES1820=m -CONFIG_DVB_TDA10021=m -CONFIG_DVB_STV0297=m - -# -# ATSC (North American/Korean Terresterial DTV) frontends -# -CONFIG_DVB_NXT2002=m -CONFIG_DVB_OR51211=m -CONFIG_DVB_OR51132=m -CONFIG_VIDEO_SAA7146=m -CONFIG_VIDEO_SAA7146_VV=m -CONFIG_VIDEO_VIDEOBUF=m -CONFIG_VIDEO_TUNER=m -CONFIG_VIDEO_BUF=m -CONFIG_VIDEO_BUF_DVB=m -CONFIG_VIDEO_BTCX=m -CONFIG_VIDEO_IR=m -CONFIG_VIDEO_TVEEPROM=m - -# -# Graphics support -# -CONFIG_FB=y -CONFIG_FB_CFB_FILLRECT=y -CONFIG_FB_CFB_COPYAREA=y -CONFIG_FB_CFB_IMAGEBLIT=y -CONFIG_FB_SOFT_CURSOR=y -# CONFIG_FB_MACMODES is not set -CONFIG_FB_MODE_HELPERS=y -CONFIG_FB_TILEBLITTING=y -CONFIG_FB_CIRRUS=m -# CONFIG_FB_PM2 is not set -# CONFIG_FB_CYBER2000 is not set -# CONFIG_FB_ASILIANT is not set -# CONFIG_FB_IMSTT is not set -CONFIG_FB_VGA16=m -CONFIG_FB_VESA=y -CONFIG_VIDEO_SELECT=y -# CONFIG_FB_HGA is not set -# CONFIG_FB_NVIDIA is not set -CONFIG_FB_RIVA=m -# CONFIG_FB_RIVA_I2C is not set -# CONFIG_FB_RIVA_DEBUG is not set -CONFIG_FB_MATROX=m -CONFIG_FB_MATROX_MILLENIUM=y -CONFIG_FB_MATROX_MYSTIQUE=y -CONFIG_FB_MATROX_G=y -CONFIG_FB_MATROX_I2C=m -CONFIG_FB_MATROX_MAVEN=m -CONFIG_FB_MATROX_MULTIHEAD=y -# CONFIG_FB_RADEON_OLD is not set -CONFIG_FB_RADEON=m -CONFIG_FB_RADEON_I2C=y -# CONFIG_FB_RADEON_DEBUG is not set -CONFIG_FB_ATY128=m -CONFIG_FB_ATY=m -CONFIG_FB_ATY_CT=y -CONFIG_FB_ATY_GENERIC_LCD=y -# CONFIG_FB_ATY_XL_INIT is not set -CONFIG_FB_ATY_GX=y -CONFIG_FB_SAVAGE=m -CONFIG_FB_SAVAGE_I2C=y -CONFIG_FB_SAVAGE_ACCEL=y -# CONFIG_FB_SIS is not set -CONFIG_FB_NEOMAGIC=m -CONFIG_FB_KYRO=m -CONFIG_FB_3DFX=m -CONFIG_FB_3DFX_ACCEL=y -CONFIG_FB_VOODOO1=m -CONFIG_FB_TRIDENT=m -CONFIG_FB_TRIDENT_ACCEL=y -# CONFIG_FB_PM3 is not set -# CONFIG_FB_GEODE is not set -# CONFIG_FB_S1D13XXX is not set -# CONFIG_FB_VIRTUAL is not set - -# -# Console display driver support -# -CONFIG_VGA_CONSOLE=y -CONFIG_DUMMY_CONSOLE=y -CONFIG_FRAMEBUFFER_CONSOLE=y -# CONFIG_FONTS is not set -CONFIG_FONT_8x8=y -CONFIG_FONT_8x16=y - -# -# Logo configuration -# -CONFIG_LOGO=y -# CONFIG_LOGO_LINUX_MONO is not set -# CONFIG_LOGO_LINUX_VGA16 is not set -CONFIG_LOGO_LINUX_CLUT224=y -CONFIG_BACKLIGHT_LCD_SUPPORT=y -CONFIG_BACKLIGHT_CLASS_DEVICE=m -CONFIG_BACKLIGHT_DEVICE=y -CONFIG_LCD_CLASS_DEVICE=m -CONFIG_LCD_DEVICE=y - -# -# Sound -# -CONFIG_SOUND=m - -# -# Advanced Linux Sound Architecture -# -CONFIG_SND=m -CONFIG_SND_TIMER=m -CONFIG_SND_PCM=m -CONFIG_SND_HWDEP=m -CONFIG_SND_RAWMIDI=m -CONFIG_SND_SEQUENCER=m -CONFIG_SND_SEQ_DUMMY=m -CONFIG_SND_OSSEMUL=y -CONFIG_SND_MIXER_OSS=m -CONFIG_SND_PCM_OSS=m -CONFIG_SND_SEQUENCER_OSS=y -CONFIG_SND_RTCTIMER=m -# CONFIG_SND_VERBOSE_PRINTK is not set -# CONFIG_SND_DEBUG is not set - -# -# Generic devices -# -CONFIG_SND_MPU401_UART=m -CONFIG_SND_OPL3_LIB=m -CONFIG_SND_VX_LIB=m -CONFIG_SND_DUMMY=m -CONFIG_SND_VIRMIDI=m -CONFIG_SND_MTPAV=m -# CONFIG_SND_SERIAL_U16550 is not set -CONFIG_SND_MPU401=m - -# -# PCI devices -# -CONFIG_SND_AC97_CODEC=m -CONFIG_SND_ALI5451=m -CONFIG_SND_ATIIXP=m -CONFIG_SND_ATIIXP_MODEM=m -CONFIG_SND_AU8810=m -CONFIG_SND_AU8820=m -CONFIG_SND_AU8830=m -CONFIG_SND_AZT3328=m -CONFIG_SND_BT87X=m -# CONFIG_SND_BT87X_OVERCLOCK is not set -CONFIG_SND_CS46XX=m -CONFIG_SND_CS46XX_NEW_DSP=y -CONFIG_SND_CS4281=m -CONFIG_SND_EMU10K1=m -CONFIG_SND_EMU10K1X=m -CONFIG_SND_CA0106=m -CONFIG_SND_KORG1212=m -CONFIG_SND_MIXART=m -CONFIG_SND_NM256=m -CONFIG_SND_RME32=m -CONFIG_SND_RME96=m -CONFIG_SND_RME9652=m -CONFIG_SND_HDSP=m -CONFIG_SND_TRIDENT=m -CONFIG_SND_YMFPCI=m -CONFIG_SND_ALS4000=m -CONFIG_SND_CMIPCI=m -CONFIG_SND_ENS1370=m -CONFIG_SND_ENS1371=m -CONFIG_SND_ES1938=m -CONFIG_SND_ES1968=m -CONFIG_SND_MAESTRO3=m -CONFIG_SND_FM801=m -CONFIG_SND_FM801_TEA575X=m -CONFIG_SND_ICE1712=m -CONFIG_SND_ICE1724=m -CONFIG_SND_INTEL8X0=m -CONFIG_SND_INTEL8X0M=m -CONFIG_SND_SONICVIBES=m -CONFIG_SND_VIA82XX=m -CONFIG_SND_VIA82XX_MODEM=m -CONFIG_SND_VX222=m -CONFIG_SND_HDA_INTEL=m - -# -# USB devices -# -CONFIG_SND_USB_AUDIO=m -CONFIG_SND_USB_USX2Y=m - -# -# Open Sound System -# -# CONFIG_SOUND_PRIME is not set - -# -# USB support -# -CONFIG_USB_ARCH_HAS_HCD=y -CONFIG_USB_ARCH_HAS_OHCI=y -CONFIG_USB=y -# CONFIG_USB_DEBUG is not set - -# -# Miscellaneous USB options -# -CONFIG_USB_DEVICEFS=y -# CONFIG_USB_BANDWIDTH is not set -# CONFIG_USB_DYNAMIC_MINORS is not set -# CONFIG_USB_OTG is not set - -# -# USB Host Controller Drivers -# -CONFIG_USB_EHCI_HCD=m -CONFIG_USB_EHCI_SPLIT_ISO=y -CONFIG_USB_EHCI_ROOT_HUB_TT=y -CONFIG_USB_OHCI_HCD=m -# CONFIG_USB_OHCI_BIG_ENDIAN is not set -CONFIG_USB_OHCI_LITTLE_ENDIAN=y -CONFIG_USB_UHCI_HCD=m -CONFIG_USB_SL811_HCD=m - -# -# USB Device Class drivers -# -# CONFIG_USB_AUDIO is not set - -# -# USB Bluetooth TTY can only be used with disabled Bluetooth subsystem -# -CONFIG_USB_MIDI=m -CONFIG_USB_ACM=m -CONFIG_USB_PRINTER=m - -# -# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' may also be needed; see USB_STORAGE Help for more information -# -CONFIG_USB_STORAGE=m -# CONFIG_USB_STORAGE_DEBUG is not set -CONFIG_USB_STORAGE_DATAFAB=y -CONFIG_USB_STORAGE_FREECOM=y -CONFIG_USB_STORAGE_ISD200=y -CONFIG_USB_STORAGE_DPCM=y -CONFIG_USB_STORAGE_USBAT=y -CONFIG_USB_STORAGE_SDDR09=y -CONFIG_USB_STORAGE_SDDR55=y -CONFIG_USB_STORAGE_JUMPSHOT=y - -# -# USB Input Devices -# -CONFIG_USB_HID=y -CONFIG_USB_HIDINPUT=y -CONFIG_HID_FF=y -CONFIG_HID_PID=y -CONFIG_LOGITECH_FF=y -CONFIG_THRUSTMASTER_FF=y -CONFIG_USB_HIDDEV=y -CONFIG_USB_AIPTEK=m -CONFIG_USB_WACOM=m -CONFIG_USB_KBTAB=m -CONFIG_USB_POWERMATE=m -CONFIG_USB_MTOUCH=m -CONFIG_USB_EGALAX=m -CONFIG_USB_XPAD=m -CONFIG_USB_ATI_REMOTE=m - -# -# USB Imaging devices -# -CONFIG_USB_MDC800=m -CONFIG_USB_MICROTEK=m - -# -# USB Multimedia devices -# -CONFIG_USB_DABUSB=m -CONFIG_USB_VICAM=m -CONFIG_USB_DSBR=m -CONFIG_USB_IBMCAM=m -CONFIG_USB_KONICAWC=m -CONFIG_USB_OV511=m -CONFIG_USB_SE401=m -CONFIG_USB_SN9C102=m -CONFIG_USB_STV680=m -CONFIG_USB_W9968CF=m -CONFIG_USB_PWC=m - -# -# USB Network Adapters -# -CONFIG_USB_CATC=m -CONFIG_USB_KAWETH=m -CONFIG_USB_PEGASUS=m -CONFIG_USB_RTL8150=m -CONFIG_USB_USBNET=m - -# -# USB Host-to-Host Cables -# -CONFIG_USB_ALI_M5632=y -CONFIG_USB_AN2720=y -CONFIG_USB_BELKIN=y -CONFIG_USB_GENESYS=y -CONFIG_USB_NET1080=y -CONFIG_USB_PL2301=y -CONFIG_USB_KC2190=y - -# -# Intelligent USB Devices/Gadgets -# -CONFIG_USB_ARMLINUX=y -CONFIG_USB_EPSON2888=y -CONFIG_USB_ZAURUS=y -CONFIG_USB_CDCETHER=y - -# -# USB Network Adapters -# -CONFIG_USB_AX8817X=y -CONFIG_USB_ZD1201=m -CONFIG_USB_MON=m - -# -# USB port drivers -# -CONFIG_USB_USS720=m - -# -# USB Serial Converter support -# -CONFIG_USB_SERIAL=m -CONFIG_USB_SERIAL_GENERIC=y -CONFIG_USB_SERIAL_AIRPRIME=m -CONFIG_USB_SERIAL_BELKIN=m -CONFIG_USB_SERIAL_WHITEHEAT=m -CONFIG_USB_SERIAL_DIGI_ACCELEPORT=m -CONFIG_USB_SERIAL_CP2101=m -CONFIG_USB_SERIAL_CYPRESS_M8=m -CONFIG_USB_SERIAL_EMPEG=m -CONFIG_USB_SERIAL_FTDI_SIO=m -CONFIG_USB_SERIAL_VISOR=m -CONFIG_USB_SERIAL_IPAQ=m -CONFIG_USB_SERIAL_IR=m -CONFIG_USB_SERIAL_EDGEPORT=m -CONFIG_USB_SERIAL_EDGEPORT_TI=m -CONFIG_USB_SERIAL_GARMIN=m -CONFIG_USB_SERIAL_IPW=m -CONFIG_USB_SERIAL_KEYSPAN_PDA=m -CONFIG_USB_SERIAL_KEYSPAN=m -CONFIG_USB_SERIAL_KEYSPAN_MPR=y -CONFIG_USB_SERIAL_KEYSPAN_USA28=y -CONFIG_USB_SERIAL_KEYSPAN_USA28X=y -CONFIG_USB_SERIAL_KEYSPAN_USA28XA=y -CONFIG_USB_SERIAL_KEYSPAN_USA28XB=y -CONFIG_USB_SERIAL_KEYSPAN_USA19=y -CONFIG_USB_SERIAL_KEYSPAN_USA18X=y -CONFIG_USB_SERIAL_KEYSPAN_USA19W=y -CONFIG_USB_SERIAL_KEYSPAN_USA19QW=y -CONFIG_USB_SERIAL_KEYSPAN_USA19QI=y -CONFIG_USB_SERIAL_KEYSPAN_USA49W=y -CONFIG_USB_SERIAL_KEYSPAN_USA49WLC=y -CONFIG_USB_SERIAL_KLSI=m -CONFIG_USB_SERIAL_KOBIL_SCT=m -CONFIG_USB_SERIAL_MCT_U232=m -CONFIG_USB_SERIAL_PL2303=m -CONFIG_USB_SERIAL_HP4X=m -CONFIG_USB_SERIAL_SAFE=m -CONFIG_USB_SERIAL_SAFE_PADDED=y -CONFIG_USB_SERIAL_TI=m -CONFIG_USB_SERIAL_CYBERJACK=m -CONFIG_USB_SERIAL_XIRCOM=m -CONFIG_USB_SERIAL_OMNINET=m -CONFIG_USB_EZUSB=y - -# -# USB Miscellaneous drivers -# -CONFIG_USB_EMI62=m -# CONFIG_USB_EMI26 is not set -CONFIG_USB_AUERSWALD=m -CONFIG_USB_RIO500=m -CONFIG_USB_LEGOTOWER=m -CONFIG_USB_LCD=m -CONFIG_USB_LED=m -# CONFIG_USB_CYTHERM is not set -CONFIG_USB_PHIDGETKIT=m -CONFIG_USB_PHIDGETSERVO=m -CONFIG_USB_IDMOUSE=m -CONFIG_USB_SISUSBVGA=m -CONFIG_USB_TEST=m - -# -# USB ATM/DSL drivers -# -CONFIG_USB_ATM=m -CONFIG_USB_SPEEDTOUCH=m - -# -# USB Gadget Support -# -# CONFIG_USB_GADGET is not set - -# -# MMC/SD Card support -# -CONFIG_MMC=m -# CONFIG_MMC_DEBUG is not set -CONFIG_MMC_BLOCK=m -CONFIG_MMC_WBSD=m - -# -# InfiniBand support -# -CONFIG_INFINIBAND=m -CONFIG_INFINIBAND_MTHCA=m -# CONFIG_INFINIBAND_MTHCA_DEBUG is not set -CONFIG_INFINIBAND_IPOIB=m -# CONFIG_INFINIBAND_IPOIB_DEBUG is not set - -# -# Power management options -# - -# -# ACPI (Advanced Configuration and Power Interface) Support -# -CONFIG_ACPI=y -CONFIG_ACPI_BOOT=y -CONFIG_ACPI_INTERPRETER=y -CONFIG_ACPI_AC=m -CONFIG_ACPI_BATTERY=m -CONFIG_ACPI_BUTTON=m -CONFIG_ACPI_VIDEO=m -CONFIG_ACPI_FAN=m -CONFIG_ACPI_PROCESSOR=m -CONFIG_ACPI_THERMAL=m -CONFIG_ACPI_ASUS=m -CONFIG_ACPI_IBM=m -CONFIG_ACPI_TOSHIBA=m -CONFIG_ACPI_BLACKLIST_YEAR=0 -# CONFIG_ACPI_DEBUG is not set -CONFIG_ACPI_BUS=y -CONFIG_ACPI_EC=y -CONFIG_ACPI_POWER=y -CONFIG_ACPI_PCI=y -CONFIG_ACPI_SYSTEM=y -# CONFIG_ACPI_CONTAINER is not set - -# -# File systems -# -CONFIG_EXT2_FS=y -CONFIG_EXT2_FS_XATTR=y -CONFIG_EXT2_FS_POSIX_ACL=y -CONFIG_EXT2_FS_SECURITY=y -CONFIG_EXT3_FS=m -CONFIG_EXT3_FS_XATTR=y -CONFIG_EXT3_FS_POSIX_ACL=y -CONFIG_EXT3_FS_SECURITY=y -CONFIG_JBD=m -# CONFIG_JBD_DEBUG is not set -CONFIG_FS_MBCACHE=y -CONFIG_REISERFS_FS=m -# CONFIG_REISERFS_CHECK is not set -CONFIG_REISERFS_PROC_INFO=y -CONFIG_REISERFS_FS_XATTR=y -CONFIG_REISERFS_FS_POSIX_ACL=y -CONFIG_REISERFS_FS_SECURITY=y -CONFIG_JFS_FS=m -CONFIG_JFS_POSIX_ACL=y -CONFIG_JFS_SECURITY=y -# CONFIG_JFS_DEBUG is not set -# CONFIG_JFS_STATISTICS is not set -CONFIG_FS_POSIX_ACL=y - -# -# XFS support -# -CONFIG_XFS_FS=m -CONFIG_XFS_EXPORT=y -# CONFIG_XFS_RT is not set -CONFIG_XFS_QUOTA=y -CONFIG_XFS_SECURITY=y -CONFIG_XFS_POSIX_ACL=y -CONFIG_MINIX_FS=m -CONFIG_ROMFS_FS=m -CONFIG_QUOTA=y -# CONFIG_QFMT_V1 is not set -CONFIG_QFMT_V2=y -CONFIG_QUOTACTL=y -CONFIG_DNOTIFY=y -CONFIG_AUTOFS_FS=m -CONFIG_AUTOFS4_FS=m - -# -# CD-ROM/DVD Filesystems -# -CONFIG_ISO9660_FS=y -CONFIG_JOLIET=y -CONFIG_ZISOFS=y -CONFIG_ZISOFS_FS=y -CONFIG_UDF_FS=m -CONFIG_UDF_NLS=y - -# -# DOS/FAT/NT Filesystems -# -CONFIG_FAT_FS=m -CONFIG_MSDOS_FS=m -CONFIG_VFAT_FS=m -CONFIG_FAT_DEFAULT_CODEPAGE=437 -CONFIG_FAT_DEFAULT_IOCHARSET="ascii" -# CONFIG_NTFS_FS is not set - -# -# Pseudo filesystems -# -CONFIG_PROC_FS=y -CONFIG_PROC_KCORE=y -CONFIG_SYSFS=y -# CONFIG_DEVFS_FS is not set -CONFIG_DEVPTS_FS_XATTR=y -CONFIG_DEVPTS_FS_SECURITY=y -CONFIG_TMPFS=y -CONFIG_TMPFS_XATTR=y -CONFIG_TMPFS_SECURITY=y -# CONFIG_HUGETLBFS is not set -# CONFIG_HUGETLB_PAGE is not set -CONFIG_RAMFS=y - -# -# Miscellaneous filesystems -# -# CONFIG_ADFS_FS is not set -CONFIG_AFFS_FS=m -CONFIG_HFS_FS=m -CONFIG_HFSPLUS_FS=m -CONFIG_BEFS_FS=m -# CONFIG_BEFS_DEBUG is not set -CONFIG_BFS_FS=m -CONFIG_EFS_FS=m -# CONFIG_JFFS_FS is not set -CONFIG_JFFS2_FS=m -CONFIG_JFFS2_FS_DEBUG=0 -CONFIG_JFFS2_FS_NAND=y -# CONFIG_JFFS2_FS_NOR_ECC is not set -# CONFIG_JFFS2_COMPRESSION_OPTIONS is not set -CONFIG_JFFS2_ZLIB=y -CONFIG_JFFS2_RTIME=y -# CONFIG_JFFS2_RUBIN is not set -CONFIG_CRAMFS=y -CONFIG_VXFS_FS=m -# CONFIG_HPFS_FS is not set -CONFIG_QNX4FS_FS=m -# CONFIG_QNX4FS_RW is not set -CONFIG_SYSV_FS=m -CONFIG_UFS_FS=m -# CONFIG_UFS_FS_WRITE is not set - -# -# Network File Systems -# -CONFIG_NFS_FS=m -CONFIG_NFS_V3=y -CONFIG_NFS_V4=y -CONFIG_NFS_DIRECTIO=y -CONFIG_NFSD=m -CONFIG_NFSD_V3=y -CONFIG_NFSD_V4=y -CONFIG_NFSD_TCP=y -CONFIG_LOCKD=m -CONFIG_LOCKD_V4=y -CONFIG_EXPORTFS=m -CONFIG_SUNRPC=m -CONFIG_SUNRPC_GSS=m -CONFIG_RPCSEC_GSS_KRB5=m -CONFIG_RPCSEC_GSS_SPKM3=m -CONFIG_SMB_FS=m -# CONFIG_SMB_NLS_DEFAULT is not set -CONFIG_CIFS=m -# CONFIG_CIFS_STATS is not set -CONFIG_CIFS_XATTR=y -CONFIG_CIFS_POSIX=y -# CONFIG_CIFS_EXPERIMENTAL is not set -CONFIG_NCP_FS=m -CONFIG_NCPFS_PACKET_SIGNING=y -CONFIG_NCPFS_IOCTL_LOCKING=y -CONFIG_NCPFS_STRONG=y -CONFIG_NCPFS_NFS_NS=y -CONFIG_NCPFS_OS2_NS=y -CONFIG_NCPFS_SMALLDOS=y -CONFIG_NCPFS_NLS=y -CONFIG_NCPFS_EXTRAS=y -# CONFIG_CODA_FS is not set -# CONFIG_AFS_FS is not set - -# -# Partition Types -# -CONFIG_PARTITION_ADVANCED=y -# CONFIG_ACORN_PARTITION is not set -CONFIG_OSF_PARTITION=y -CONFIG_AMIGA_PARTITION=y -# CONFIG_ATARI_PARTITION is not set -CONFIG_MAC_PARTITION=y -CONFIG_MSDOS_PARTITION=y -CONFIG_BSD_DISKLABEL=y -CONFIG_MINIX_SUBPARTITION=y -CONFIG_SOLARIS_X86_PARTITION=y -CONFIG_UNIXWARE_DISKLABEL=y -# CONFIG_LDM_PARTITION is not set -CONFIG_SGI_PARTITION=y -# CONFIG_ULTRIX_PARTITION is not set -CONFIG_SUN_PARTITION=y -CONFIG_EFI_PARTITION=y - -# -# Native Language Support -# -CONFIG_NLS=y -CONFIG_NLS_DEFAULT="utf8" -CONFIG_NLS_CODEPAGE_437=y -CONFIG_NLS_CODEPAGE_737=m -CONFIG_NLS_CODEPAGE_775=m -CONFIG_NLS_CODEPAGE_850=m -CONFIG_NLS_CODEPAGE_852=m -CONFIG_NLS_CODEPAGE_855=m -CONFIG_NLS_CODEPAGE_857=m -CONFIG_NLS_CODEPAGE_860=m -CONFIG_NLS_CODEPAGE_861=m -CONFIG_NLS_CODEPAGE_862=m -CONFIG_NLS_CODEPAGE_863=m -CONFIG_NLS_CODEPAGE_864=m -CONFIG_NLS_CODEPAGE_865=m -CONFIG_NLS_CODEPAGE_866=m -CONFIG_NLS_CODEPAGE_869=m -CONFIG_NLS_CODEPAGE_936=m -CONFIG_NLS_CODEPAGE_950=m -CONFIG_NLS_CODEPAGE_932=m -CONFIG_NLS_CODEPAGE_949=m -CONFIG_NLS_CODEPAGE_874=m -CONFIG_NLS_ISO8859_8=m -CONFIG_NLS_CODEPAGE_1250=m -CONFIG_NLS_CODEPAGE_1251=m -CONFIG_NLS_ASCII=y -CONFIG_NLS_ISO8859_1=m -CONFIG_NLS_ISO8859_2=m -CONFIG_NLS_ISO8859_3=m -CONFIG_NLS_ISO8859_4=m -CONFIG_NLS_ISO8859_5=m -CONFIG_NLS_ISO8859_6=m -CONFIG_NLS_ISO8859_7=m -CONFIG_NLS_ISO8859_9=m -CONFIG_NLS_ISO8859_13=m -CONFIG_NLS_ISO8859_14=m -CONFIG_NLS_ISO8859_15=m -CONFIG_NLS_KOI8_R=m -CONFIG_NLS_KOI8_U=m -CONFIG_NLS_UTF8=m - -# -# Security options -# -CONFIG_KEYS=y -CONFIG_KEYS_DEBUG_PROC_KEYS=y -CONFIG_SECURITY=y -CONFIG_SECURITY_NETWORK=y -CONFIG_SECURITY_CAPABILITIES=y -# CONFIG_SECURITY_ROOTPLUG is not set -# CONFIG_SECURITY_SECLVL is not set -CONFIG_SECURITY_SELINUX=y -CONFIG_SECURITY_SELINUX_BOOTPARAM=y -CONFIG_SECURITY_SELINUX_BOOTPARAM_VALUE=1 -CONFIG_SECURITY_SELINUX_DISABLE=y -CONFIG_SECURITY_SELINUX_DEVELOP=y -CONFIG_SECURITY_SELINUX_AVC_STATS=y -CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE=1 - -# -# Cryptographic options -# -CONFIG_CRYPTO=y -CONFIG_CRYPTO_HMAC=y -CONFIG_CRYPTO_NULL=m -CONFIG_CRYPTO_MD4=m -CONFIG_CRYPTO_MD5=m -CONFIG_CRYPTO_SHA1=y -CONFIG_CRYPTO_SHA256=m -CONFIG_CRYPTO_SHA512=m -CONFIG_CRYPTO_WP512=m -CONFIG_CRYPTO_TGR192=m -CONFIG_CRYPTO_DES=m -CONFIG_CRYPTO_BLOWFISH=m -CONFIG_CRYPTO_TWOFISH=m -CONFIG_CRYPTO_SERPENT=m -CONFIG_CRYPTO_AES=m -CONFIG_CRYPTO_CAST5=m -CONFIG_CRYPTO_CAST6=m -CONFIG_CRYPTO_TEA=m -CONFIG_CRYPTO_ARC4=m -CONFIG_CRYPTO_KHAZAD=m -CONFIG_CRYPTO_ANUBIS=m -CONFIG_CRYPTO_DEFLATE=m -CONFIG_CRYPTO_MICHAEL_MIC=m -CONFIG_CRYPTO_CRC32C=m -# CONFIG_CRYPTO_TEST is not set - -# -# Hardware crypto devices -# - -# -# Library routines -# -CONFIG_CRC_CCITT=m -CONFIG_CRC32=y -CONFIG_LIBCRC32C=m -CONFIG_ZLIB_INFLATE=y -CONFIG_ZLIB_DEFLATE=m - -# -# Kernel hacking -# -# CONFIG_PRINTK_TIME is not set -CONFIG_DEBUG_KERNEL=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_LOG_BUF_SHIFT=15 -# CONFIG_SCHEDSTATS is not set -# CONFIG_DEBUG_SLAB is not set -# CONFIG_DEBUG_SPINLOCK is not set -# CONFIG_DEBUG_SPINLOCK_SLEEP is not set -# CONFIG_DEBUG_KOBJECT is not set -# CONFIG_DEBUG_INFO is not set -# CONFIG_DEBUG_FS is not set -# CONFIG_DEBUG_STACKOVERFLOW is not set -# CONFIG_KPROBES is not set -# CONFIG_DEBUG_STACK_USAGE is not set -# CONFIG_DEBUG_PAGEALLOC is not set -# CONFIG_4KSTACKS is not set -CONFIG_X86_FIND_SMP_CONFIG=y -CONFIG_X86_MPPARSE=y -# CONFIG_INIT_DEBUG is not set diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/Kconfig --- a/linux-2.6-xen-sparse/arch/xen/i386/Kconfig Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,960 +0,0 @@ -# -# For a description of the syntax of this configuration file, -# see Documentation/kbuild/kconfig-language.txt. -# - -menu "X86 Processor Configuration" - -config XENARCH - string - default i386 - -config X86 - bool - default y - help - This is Linux's home port. Linux was originally native to the Intel - 386, and runs on all the later x86 processors including the Intel - 486, 586, Pentiums, and various instruction-set-compatible chips by - AMD, Cyrix, and others. - -config MMU - bool - default y - -config SBUS - bool - -config UID16 - bool - default y - -config GENERIC_ISA_DMA - bool - default y - -config GENERIC_IOMAP - bool - default y - -choice - prompt "Processor family" - default M686 - -config M386 - bool "386" - ---help--- - This is the processor type of your CPU. This information is used for - optimizing purposes. In order to compile a kernel that can run on - all x86 CPU types (albeit not optimally fast), you can specify - "386" here. - - The kernel will not necessarily run on earlier architectures than - the one you have chosen, e.g. a Pentium optimized kernel will run on - a PPro, but not necessarily on a i486. - - Here are the settings recommended for greatest speed: - - "386" for the AMD/Cyrix/Intel 386DX/DXL/SL/SLC/SX, Cyrix/TI - 486DLC/DLC2, UMC 486SX-S and NexGen Nx586. Only "386" kernels - will run on a 386 class machine. - - "486" for the AMD/Cyrix/IBM/Intel 486DX/DX2/DX4 or - SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or U5S. - - "586" for generic Pentium CPUs lacking the TSC - (time stamp counter) register. - - "Pentium-Classic" for the Intel Pentium. - - "Pentium-MMX" for the Intel Pentium MMX. - - "Pentium-Pro" for the Intel Pentium Pro. - - "Pentium-II" for the Intel Pentium II or pre-Coppermine Celeron. - - "Pentium-III" for the Intel Pentium III or Coppermine Celeron. - - "Pentium-4" for the Intel Pentium 4 or P4-based Celeron. - - "K6" for the AMD K6, K6-II and K6-III (aka K6-3D). - - "Athlon" for the AMD K7 family (Athlon/Duron/Thunderbird). - - "Crusoe" for the Transmeta Crusoe series. - - "Efficeon" for the Transmeta Efficeon series. - - "Winchip-C6" for original IDT Winchip. - - "Winchip-2" for IDT Winchip 2. - - "Winchip-2A" for IDT Winchips with 3dNow! capabilities. - - "GeodeGX1" for Geode GX1 (Cyrix MediaGX). - - "CyrixIII/VIA C3" for VIA Cyrix III or VIA C3. - - "VIA C3-2 for VIA C3-2 "Nehemiah" (model 9 and above). - - If you don't know what to do, choose "386". - -config M486 - bool "486" - help - Select this for a 486 series processor, either Intel or one of the - compatible processors from AMD, Cyrix, IBM, or Intel. Includes DX, - DX2, and DX4 variants; also SL/SLC/SLC2/SLC3/SX/SX2 and UMC U5D or - U5S. - -config M586 - bool "586/K5/5x86/6x86/6x86MX" - help - Select this for an 586 or 686 series processor such as the AMD K5, - the Cyrix 5x86, 6x86 and 6x86MX. This choice does not - assume the RDTSC (Read Time Stamp Counter) instruction. - -config M586TSC - bool "Pentium-Classic" - help - Select this for a Pentium Classic processor with the RDTSC (Read - Time Stamp Counter) instruction for benchmarking. - -config M586MMX - bool "Pentium-MMX" - help - Select this for a Pentium with the MMX graphics/multimedia - extended instructions. - -config M686 - bool "Pentium-Pro" - help - Select this for Intel Pentium Pro chips. This enables the use of - Pentium Pro extended instructions, and disables the init-time guard - against the f00f bug found in earlier Pentiums. - -config MPENTIUMII - bool "Pentium-II/Celeron(pre-Coppermine)" - help - Select this for Intel chips based on the Pentium-II and - pre-Coppermine Celeron core. This option enables an unaligned - copy optimization, compiles the kernel with optimization flags - tailored for the chip, and applies any applicable Pentium Pro - optimizations. - -config MPENTIUMIII - bool "Pentium-III/Celeron(Coppermine)/Pentium-III Xeon" - help - Select this for Intel chips based on the Pentium-III and - Celeron-Coppermine core. This option enables use of some - extended prefetch instructions in addition to the Pentium II - extensions. - -config MPENTIUMM - bool "Pentium M" - help - Select this for Intel Pentium M (not Pentium-4 M) - notebook chips. - -config MPENTIUM4 - bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/Xeon" - help - Select this for Intel Pentium 4 chips. This includes the - Pentium 4, P4-based Celeron and Xeon, and Pentium-4 M - (not Pentium M) chips. This option enables compile flags - optimized for the chip, uses the correct cache shift, and - applies any applicable Pentium III optimizations. - -config MK6 - bool "K6/K6-II/K6-III" - help - Select this for an AMD K6-family processor. Enables use of - some extended instructions, and passes appropriate optimization - flags to GCC. - -config MK7 - bool "Athlon/Duron/K7" - help - Select this for an AMD Athlon K7-family processor. Enables use of - some extended instructions, and passes appropriate optimization - flags to GCC. - -config MK8 - bool "Opteron/Athlon64/Hammer/K8" - help - Select this for an AMD Opteron or Athlon64 Hammer-family processor. Enables - use of some extended instructions, and passes appropriate optimization - flags to GCC. - -config MCRUSOE - bool "Crusoe" - help - Select this for a Transmeta Crusoe processor. Treats the processor - like a 586 with TSC, and sets some GCC optimization flags (like a - Pentium Pro with no alignment requirements). - -config MEFFICEON - bool "Efficeon" - help - Select this for a Transmeta Efficeon processor. - -config MWINCHIPC6 - bool "Winchip-C6" - help - Select this for an IDT Winchip C6 chip. Linux and GCC - treat this chip as a 586TSC with some extended instructions - and alignment requirements. - -config MWINCHIP2 - bool "Winchip-2" - help - Select this for an IDT Winchip-2. Linux and GCC - treat this chip as a 586TSC with some extended instructions - and alignment requirements. - -config MWINCHIP3D - bool "Winchip-2A/Winchip-3" - help - Select this for an IDT Winchip-2A or 3. Linux and GCC - treat this chip as a 586TSC with some extended instructions - and alignment reqirements. Also enable out of order memory - stores for this CPU, which can increase performance of some - operations. - -config MGEODEGX1 - bool "GeodeGX1" - help - Select this for a Geode GX1 (Cyrix MediaGX) chip. - -config MCYRIXIII - bool "CyrixIII/VIA-C3" - help - Select this for a Cyrix III or C3 chip. Presently Linux and GCC - treat this chip as a generic 586. Whilst the CPU is 686 class, - it lacks the cmov extension which gcc assumes is present when - generating 686 code. - Note that Nehemiah (Model 9) and above will not boot with this - kernel due to them lacking the 3DNow! instructions used in earlier - incarnations of the CPU. - -config MVIAC3_2 - bool "VIA C3-2 (Nehemiah)" - help - Select this for a VIA C3 "Nehemiah". Selecting this enables usage - of SSE and tells gcc to treat the CPU as a 686. - Note, this kernel will not boot on older (pre model 9) C3s. - -endchoice - -config X86_GENERIC - bool "Generic x86 support" - help - Instead of just including optimizations for the selected - x86 variant (e.g. PII, Crusoe or Athlon), include some more - generic optimizations as well. This will make the kernel - perform better on x86 CPUs other than that selected. - - This is really intended for distributors who need more - generic optimizations. - -# -# Define implied options from the CPU selection here -# -config X86_CMPXCHG - bool - depends on !M386 - default y - -config X86_XADD - bool - depends on !M386 - default y - -config X86_L1_CACHE_SHIFT - int - default "7" if MPENTIUM4 || X86_GENERIC - default "4" if X86_ELAN || M486 || M386 - default "5" if MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODEGX1 - default "6" if MK7 || MK8 || MPENTIUMM - -config RWSEM_GENERIC_SPINLOCK - bool - depends on M386 - default y - -config RWSEM_XCHGADD_ALGORITHM - bool - depends on !M386 - default y - -config GENERIC_CALIBRATE_DELAY - bool - default y - -config X86_PPRO_FENCE - bool - depends on M686 || M586MMX || M586TSC || M586 || M486 || M386 || MGEODEGX1 - default y - -config X86_F00F_BUG - bool - depends on M586MMX || M586TSC || M586 || M486 || M386 - default y - -config X86_WP_WORKS_OK - bool - depends on !M386 - default y - -config X86_INVLPG - bool - depends on !M386 - default y - -config X86_BSWAP - bool - depends on !M386 - default y - -config X86_POPAD_OK - bool - depends on !M386 - default y - -config X86_ALIGNMENT_16 - bool - depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII || X86_ELAN || MK6 || M586MMX || M586TSC || M586 || M486 || MVIAC3_2 || MGEODEGX1 - default y - -config X86_GOOD_APIC - bool - depends on MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || MK8 || MEFFICEON - default y - -config X86_INTEL_USERCOPY - bool - depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON - default y - -config X86_USE_PPRO_CHECKSUM - bool - depends on MWINCHIP3D || MWINCHIP2 || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MEFFICEON - default y - -config X86_USE_3DNOW - bool - depends on MCYRIXIII || MK7 - default y - -config X86_OOSTORE - bool - depends on (MWINCHIP3D || MWINCHIP2 || MWINCHIPC6) && MTRR - default y - -config HPET_TIMER - bool - default n -#config HPET_TIMER -# bool "HPET Timer Support" -# help -# This enables the use of the HPET for the kernel's internal timer. -# HPET is the next generation timer replacing legacy 8254s. -# You can safely choose Y here. However, HPET will only be -# activated if the platform and the BIOS support this feature. -# Otherwise the 8254 will be used for timing services. -# -# Choose N to continue using the legacy 8254 timer. - -config HPET_EMULATE_RTC - def_bool HPET_TIMER && RTC=y - -config SMP - bool "Symmetric multi-processing support" - ---help--- - This enables support for systems with more than one CPU. If you have - a system with only one CPU, like most personal computers, say N. If - you have a system with more than one CPU, say Y. - - If you say N here, the kernel will run on single and multiprocessor - machines, but will use only one CPU of a multiprocessor machine. If - you say Y here, the kernel will run on many, but not all, - singleprocessor machines. On a singleprocessor machine, the kernel - will run faster if you say N here. - - Note that if you say Y here and choose architecture "586" or - "Pentium" under "Processor family", the kernel will not work on 486 - architectures. Similarly, multiprocessor kernels for the "PPro" - architecture may not work on all Pentium based boards. - - People using multiprocessor machines who say Y here should also say - Y to "Enhanced Real Time Clock Support", below. The "Advanced Power - Management" code will be disabled if you say Y here. - - See also the <file:Documentation/smp.txt>, - <file:Documentation/i386/IO-APIC.txt>, - <file:Documentation/nmi_watchdog.txt> and the SMP-HOWTO available at - <http://www.tldp.org/docs.html#howto>. - - If you don't know what to do here, say N. - -config SMP_ALTERNATIVES - bool "SMP alternatives support (EXPERIMENTAL)" - depends on SMP && EXPERIMENTAL - help - Try to reduce the overhead of running an SMP kernel on a uniprocessor - host slightly by replacing certain key instruction sequences - according to whether we currently have more than one CPU available. - This should provide a noticeable boost to performance when - running SMP kernels on UP machines, and have negligible impact - when running on an true SMP host. - - If unsure, say N. - -config NR_CPUS - int "Maximum number of CPUs (2-255)" - range 2 255 - depends on SMP - default "32" if X86_NUMAQ || X86_SUMMIT || X86_BIGSMP || X86_ES7000 - default "8" - help - This allows you to specify the maximum number of CPUs which this - kernel will support. The maximum supported value is 255 and the - minimum value which makes sense is 2. - - This is purely to save memory - each supported CPU adds - approximately eight kilobytes to the kernel image. - -config SCHED_SMT - bool "SMT (Hyperthreading) scheduler support" - depends on SMP - default off - help - SMT scheduler support improves the CPU scheduler's decision making - when dealing with Intel Pentium 4 chips with HyperThreading at a - cost of slightly increased overhead in some places. If unsure say - N here. - -#config PREEMPT -# bool "Preemptible Kernel" -# help -# This option reduces the latency of the kernel when reacting to -# real-time or interactive events by allowing a low priority process to -# be preempted even if it is in kernel mode executing a system call. -# This allows applications to run more reliably even when the system is -# under load. -# -# Say Y here if you are building a kernel for a desktop, embedded -# or real-time system. Say N if you are unsure. - -config PREEMPT_BKL - bool "Preempt The Big Kernel Lock" - depends on PREEMPT - default y - help - This option reduces the latency of the kernel by making the - big kernel lock preemptible. - - Say Y here if you are building a kernel for a desktop system. - Say N if you are unsure. - -#config X86_TSC -# bool -# depends on (MWINCHIP3D || MWINCHIP2 || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MGEODEGX1) && !X86_NUMAQ -# default y - -#config X86_MCE -# bool "Machine Check Exception" -# depends on !X86_VOYAGER -# ---help--- -# Machine Check Exception support allows the processor to notify the -# kernel if it detects a problem (e.g. overheating, component failure). -# The action the kernel takes depends on the severity of the problem, -# ranging from a warning message on the console, to halting the machine. -# Your processor must be a Pentium or newer to support this - check the -# flags in /proc/cpuinfo for mce. Note that some older Pentium systems -# have a design flaw which leads to false MCE events - hence MCE is -# disabled on all P5 processors, unless explicitly enabled with "mce" -# as a boot argument. Similarly, if MCE is built in and creates a -# problem on some new non-standard machine, you can boot with "nomce" -# to disable it. MCE support simply ignores non-MCE processors like -# the 386 and 486, so nearly everyone can say Y here. - -#config X86_MCE_NONFATAL -# tristate "Check for non-fatal errors on AMD Athlon/Duron / Intel Pentium 4" -# depends on X86_MCE -# help -# Enabling this feature starts a timer that triggers every 5 seconds which -# will look at the machine check registers to see if anything happened. -# Non-fatal problems automatically get corrected (but still logged). -# Disable this if you don't want to see these messages. -# Seeing the messages this option prints out may be indicative of dying hardware, -# or out-of-spec (ie, overclocked) hardware. -# This option only does something on certain CPUs. -# (AMD Athlon/Duron and Intel Pentium 4) - -#config X86_MCE_P4THERMAL -# bool "check for P4 thermal throttling interrupt." -# depends on X86_MCE && (X86_UP_APIC || SMP) -# help -# Enabling this feature will cause a message to be printed when the P4 -# enters thermal throttling. - -config X86_REBOOTFIXUPS - bool "Enable X86 board specific fixups for reboot" - depends on X86 - default n - ---help--- - This enables chipset and/or board specific fixups to be done - in order to get reboot to work correctly. This is only needed on - some combinations of hardware and BIOS. The symptom, for which - this config is intended, is when reboot ends with a stalled/hung - system. - - Currently, the only fixup is for the Geode GX1/CS5530A/TROM2.1. - combination. - - Say Y if you want to enable the fixup. Currently, it's safe to - enable this option even if you don't need it. - Say N otherwise. - -config MICROCODE - tristate "/dev/cpu/microcode - Intel IA32 CPU microcode support" - depends on XEN_PRIVILEGED_GUEST - ---help--- - If you say Y here and also to "/dev file system support" in the - 'File systems' section, you will be able to update the microcode on - Intel processors in the IA32 family, e.g. Pentium Pro, Pentium II, - Pentium III, Pentium 4, Xeon etc. You will obviously need the - actual microcode binary data itself which is not shipped with the - Linux kernel. - - For latest news and information on obtaining all the required - ingredients for this driver, check: - <http://www.urbanmyth.org/microcode/>. - - To compile this driver as a module, choose M here: the - module will be called microcode. - -#config X86_MSR -# tristate "/dev/cpu/*/msr - Model-specific register support" -# help -# This device gives privileged processes access to the x86 -# Model-Specific Registers (MSRs). It is a character device with -# major 202 and minors 0 to 31 for /dev/cpu/0/msr to /dev/cpu/31/msr. -# MSR accesses are directed to a specific CPU on multi-processor -# systems. - -config X86_CPUID - tristate "/dev/cpu/*/cpuid - CPU information support" - help - This device gives processes access to the x86 CPUID instruction to - be executed on a specific processor. It is a character device - with major 203 and minors 0 to 31 for /dev/cpu/0/cpuid to - /dev/cpu/31/cpuid. - -config SWIOTLB - bool - depends on PCI - default y - -source "drivers/firmware/Kconfig" - -choice - prompt "High Memory Support" - default NOHIGHMEM - -config NOHIGHMEM - bool "off" - ---help--- - Linux can use up to 64 Gigabytes of physical memory on x86 systems. - However, the address space of 32-bit x86 processors is only 4 - Gigabytes large. That means that, if you have a large amount of - physical memory, not all of it can be "permanently mapped" by the - kernel. The physical memory that's not permanently mapped is called - "high memory". - - If you are compiling a kernel which will never run on a machine with - more than 1 Gigabyte total physical RAM, answer "off" here (default - choice and suitable for most users). This will result in a "3GB/1GB" - split: 3GB are mapped so that each process sees a 3GB virtual memory - space and the remaining part of the 4GB virtual memory space is used - by the kernel to permanently map as much physical memory as - possible. - - If the machine has between 1 and 4 Gigabytes physical RAM, then - answer "4GB" here. - - If more than 4 Gigabytes is used then answer "64GB" here. This - selection turns Intel PAE (Physical Address Extension) mode on. - PAE implements 3-level paging on IA32 processors. PAE is fully - supported by Linux, PAE mode is implemented on all recent Intel - processors (Pentium Pro and better). NOTE: If you say "64GB" here, - then the kernel will not boot on CPUs that don't support PAE! - - The actual amount of total physical memory will either be - auto detected or can be forced by using a kernel command line option - such as "mem=256M". (Try "man bootparam" or see the documentation of - your boot loader (lilo or loadlin) about how to pass options to the - kernel at boot time.) - - If unsure, say "off". - -config HIGHMEM4G - bool "4GB" - help - Select this if you have a 32-bit processor and between 1 and 4 - gigabytes of physical RAM. - -config HIGHMEM64G - bool "64GB" - help - Select this if you have a 32-bit processor and more than 4 - gigabytes of physical RAM. - -endchoice - -config HIGHMEM - bool - depends on HIGHMEM64G || HIGHMEM4G - default y - -config X86_PAE - bool - depends on HIGHMEM64G - default y - -# Common NUMA Features -config NUMA - bool "Numa Memory Allocation and Scheduler Support" - depends on SMP && HIGHMEM64G && (X86_NUMAQ || X86_GENERICARCH || (X86_SUMMIT && ACPI)) - default n if X86_PC - default y if (X86_NUMAQ || X86_SUMMIT) - -# Need comments to help the hapless user trying to turn on NUMA support -comment "NUMA (NUMA-Q) requires SMP, 64GB highmem support" - depends on X86_NUMAQ && (!HIGHMEM64G || !SMP) - -comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI" - depends on X86_SUMMIT && (!HIGHMEM64G || !ACPI) - -config DISCONTIGMEM - bool - depends on NUMA - default y - -config HAVE_ARCH_BOOTMEM_NODE - bool - depends on NUMA - default y - -config HAVE_MEMORY_PRESENT - bool - depends on DISCONTIGMEM - default y - -config NEED_NODE_MEMMAP_SIZE - bool - depends on DISCONTIGMEM - default y - -#config HIGHPTE -# bool "Allocate 3rd-level pagetables from highmem" -# depends on HIGHMEM4G || HIGHMEM64G -# help -# The VM uses one page table entry for each page of physical memory. -# For systems with a lot of RAM, this can be wasteful of precious -# low memory. Setting this option will put user-space page table -# entries in high memory. - -config MTRR - bool - depends on XEN_PRIVILEGED_GUEST - default y - -#config MTRR -# bool "MTRR (Memory Type Range Register) support" -# ---help--- -# On Intel P6 family processors (Pentium Pro, Pentium II and later) -# the Memory Type Range Registers (MTRRs) may be used to control -# processor access to memory ranges. This is most useful if you have -# a video (VGA) card on a PCI or AGP bus. Enabling write-combining -# allows bus write transfers to be combined into a larger transfer -# before bursting over the PCI/AGP bus. This can increase performance -# of image write operations 2.5 times or more. Saying Y here creates a -# /proc/mtrr file which may be used to manipulate your processor's -# MTRRs. Typically the X server should use this. -# -# This code has a reasonably generic interface so that similar -# control registers on other processors can be easily supported -# as well: -# -# The Cyrix 6x86, 6x86MX and M II processors have Address Range -# Registers (ARRs) which provide a similar functionality to MTRRs. For -# these, the ARRs are used to emulate the MTRRs. -# The AMD K6-2 (stepping 8 and above) and K6-3 processors have two -# MTRRs. The Centaur C6 (WinChip) has 8 MCRs, allowing -# write-combining. All of these processors are supported by this code -# and it makes sense to say Y here if you have one of them. -# -# Saying Y here also fixes a problem with buggy SMP BIOSes which only -# set the MTRRs for the boot CPU and not for the secondary CPUs. This -# can lead to all sorts of problems, so it's good to say Y here. -# -# You can safely say Y even if your machine doesn't have MTRRs, you'll -# just add about 9 KB to your kernel. -# -# See <file:Documentation/mtrr.txt> for more information. - -config IRQBALANCE - bool "Enable kernel irq balancing" - depends on SMP && X86_IO_APIC && !XEN - default y - help - The default yes will allow the kernel to do irq load balancing. - Saying no will keep the kernel from doing irq load balancing. - -config HAVE_DEC_LOCK - bool - depends on (SMP || PREEMPT) && X86_CMPXCHG - default y - -# turning this on wastes a bunch of space. -# Summit needs it only when NUMA is on -config BOOT_IOREMAP - bool - depends on (((X86_SUMMIT || X86_GENERICARCH) && NUMA) || (X86 && EFI)) - default y - -config REGPARM - bool "Use register arguments (EXPERIMENTAL)" - depends on EXPERIMENTAL - default n - help - Compile the kernel with -mregparm=3. This uses a different ABI - and passes the first three arguments of a function call in registers. - This will probably break binary only modules. - - This feature is only enabled for gcc-3.0 and later - earlier compilers - generate incorrect output with certain kernel constructs when - -mregparm=3 is used. - -config X86_LOCAL_APIC - bool - depends on XEN_PRIVILEGED_GUEST && (X86_UP_APIC || ((X86_VISWS || SMP) && !X86_VOYAGER)) - default y - -config X86_IO_APIC - bool - depends on XEN_PRIVILEGED_GUEST && (X86_UP_IOAPIC || (SMP && !(X86_VISWS || X86_VOYAGER))) - default y - -config X86_VISWS_APIC - bool - depends on X86_VISWS - default y - -config HOTPLUG_CPU - bool "Support for hot-pluggable CPUs (EXPERIMENTAL)" - depends on SMP && HOTPLUG && EXPERIMENTAL - ---help--- - Say Y here to experiment with turning CPUs off and on. CPUs - can be controlled through /sys/devices/system/cpu. - - Say N. - - -if XEN_PHYSDEV_ACCESS - -menu "Bus options (PCI, PCMCIA, EISA, MCA, ISA)" - -config X86_UP_APIC - bool "Local APIC support on uniprocessors" - depends on !SMP && !(X86_VISWS || X86_VOYAGER) - help - A local APIC (Advanced Programmable Interrupt Controller) is an - integrated interrupt controller in the CPU. If you have a single-CPU - system which has a processor with a local APIC, you can say Y here to - enable and use it. If you say Y here even though your machine doesn't - have a local APIC, then the kernel will still run with no slowdown at - all. The local APIC supports CPU-generated self-interrupts (timer, - performance counters), and the NMI watchdog which detects hard - lockups. - -config X86_UP_IOAPIC - bool "IO-APIC support on uniprocessors" - depends on X86_UP_APIC - help - An IO-APIC (I/O Advanced Programmable Interrupt Controller) is an - SMP-capable replacement for PC-style interrupt controllers. Most - SMP systems and many recent uniprocessor systems have one. - - If you have a single-CPU system with an IO-APIC, you can say Y here - to use it. If you say Y here even though your machine doesn't have - an IO-APIC, then the kernel will still run with no slowdown at all. - -config PCI - bool "PCI support" if !X86_VISWS - depends on !X86_VOYAGER - default y if X86_VISWS - help - Find out whether you have a PCI motherboard. PCI is the name of a - bus system, i.e. the way the CPU talks to the other stuff inside - your box. Other bus systems are ISA, EISA, MicroChannel (MCA) or - VESA. If you have PCI, say Y, otherwise N. - - The PCI-HOWTO, available from - <http://www.tldp.org/docs.html#howto>, contains valuable - information about which PCI hardware does work under Linux and which - doesn't. - -choice - prompt "PCI access mode" - depends on PCI && !X86_VISWS - default PCI_GOANY - ---help--- - On PCI systems, the BIOS can be used to detect the PCI devices and - determine their configuration. However, some old PCI motherboards - have BIOS bugs and may crash if this is done. Also, some embedded - PCI-based systems don't have any BIOS at all. Linux can also try to - detect the PCI hardware directly without using the BIOS. - - With this option, you can specify how Linux should detect the - PCI devices. If you choose "BIOS", the BIOS will be used, - if you choose "Direct", the BIOS won't be used, and if you - choose "MMConfig", then PCI Express MMCONFIG will be used. - If you choose "Any", the kernel will try MMCONFIG, then the - direct access method and falls back to the BIOS if that doesn't - work. If unsure, go with the default, which is "Any". - -#config PCI_GOBIOS -# bool "BIOS" - -config PCI_GOMMCONFIG - bool "MMConfig" - -config PCI_GODIRECT - bool "Direct" - -config PCI_GOANY - bool "Any" - -endchoice - -#config PCI_BIOS -# bool -# depends on !X86_VISWS && PCI && (PCI_GOBIOS || PCI_GOANY) -# default y - -config PCI_DIRECT - bool - depends on PCI && ((PCI_GODIRECT || PCI_GOANY) || X86_VISWS) - default y - -config PCI_MMCONFIG - bool - depends on PCI && ACPI && (PCI_GOMMCONFIG || PCI_GOANY) - select ACPI_BOOT - default y - -source "drivers/pci/pcie/Kconfig" - -source "drivers/pci/Kconfig" - -config ISA_DMA_API - bool - default y - -config ISA - bool "ISA support" - depends on !(X86_VOYAGER || X86_VISWS) - help - Find out whether you have ISA slots on your motherboard. ISA is the - name of a bus system, i.e. the way the CPU talks to the other stuff - inside your box. Other bus systems are PCI, EISA, MicroChannel - (MCA) or VESA. ISA is an older system, now being displaced by PCI; - newer boards don't support it. If you have ISA, say Y, otherwise N. - -config EISA - bool "EISA support" - depends on ISA - ---help--- - The Extended Industry Standard Architecture (EISA) bus was - developed as an open alternative to the IBM MicroChannel bus. - - The EISA bus provided some of the features of the IBM MicroChannel - bus while maintaining backward compatibility with cards made for - the older ISA bus. The EISA bus saw limited use between 1988 and - 1995 when it was made obsolete by the PCI bus. - - Say Y here if you are building a kernel for an EISA-based machine. - - Otherwise, say N. - -source "drivers/eisa/Kconfig" - -config MCA - bool "MCA support" if !(X86_VISWS || X86_VOYAGER) - default y if X86_VOYAGER - help - MicroChannel Architecture is found in some IBM PS/2 machines and - laptops. It is a bus system similar to PCI or ISA. See - <file:Documentation/mca.txt> (and especially the web page given - there) before attempting to build an MCA bus kernel. - -source "drivers/mca/Kconfig" - -config SCx200 - tristate "NatSemi SCx200 support" - depends on !X86_VOYAGER - help - This provides basic support for the National Semiconductor SCx200 - processor. Right now this is just a driver for the GPIO pins. - - If you don't know what to do here, say N. - - This support is also available as a module. If compiled as a - module, it will be called scx200. - -source "drivers/pcmcia/Kconfig" - -source "drivers/pci/hotplug/Kconfig" - -endmenu - -endif - -# -# Use the generic interrupt handling code in kernel/irq/: -# -config GENERIC_HARDIRQS - bool - default y - -config GENERIC_IRQ_PROBE - bool - default y - -config X86_SMP - bool - depends on SMP && !X86_VOYAGER - default y - -#config X86_HT -# bool -# depends on SMP && !(X86_VISWS || X86_VOYAGER) -# default y - -config X86_BIOS_REBOOT - bool - depends on !(X86_VISWS || X86_VOYAGER) - default y - -config X86_TRAMPOLINE - bool - depends on X86_SMP || (X86_VOYAGER && SMP) - default y - -config PC - bool - depends on X86 && !EMBEDDED - default y - -config SECCOMP - bool "Enable seccomp to safely compute untrusted bytecode" - depends on PROC_FS - default y - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via /proc/<pid>/seccomp, it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - - If unsure, say Y. Only embedded should say N here. - -endmenu diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/Makefile --- a/linux-2.6-xen-sparse/arch/xen/i386/Makefile Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,108 +0,0 @@ -# -# i386/Makefile -# -# This file is included by the global makefile so that you can add your own -# architecture-specific flags and dependencies. Remember to do have actions -# for "archclean" cleaning up for this architecture. -# -# This file is subject to the terms and conditions of the GNU General Public -# License. See the file "COPYING" in the main directory of this archive -# for more details. -# -# Copyright (C) 1994 by Linus Torvalds -# -# 19990713 Artur Skawina <skawina@xxxxxxxxxxxxx> -# Added '-march' and '-mpreferred-stack-boundary' support -# -# 20050320 Kianusch Sayah Karadji <kianusch@xxxxxxxxxxx> -# Added support for GEODE CPU - -XENARCH := $(subst ",,$(CONFIG_XENARCH)) - -LDFLAGS := -m elf_i386 -LDFLAGS_vmlinux := -CHECK := $(CHECK) -D__i386__=1 - -CFLAGS += -m32 -AFLAGS += -m32 - -CFLAGS += -pipe -msoft-float - -# prevent gcc from keeping the stack 16 byte aligned -CFLAGS += $(call cc-option,-mpreferred-stack-boundary=2,) - -align := $(cc-option-align) -cflags-$(CONFIG_M386) += -march=i386 -cflags-$(CONFIG_M486) += -march=i486 -cflags-$(CONFIG_M586) += -march=i586 -cflags-$(CONFIG_M586TSC) += -march=i586 -cflags-$(CONFIG_M586MMX) += $(call cc-option,-march=pentium-mmx,-march=i586) -cflags-$(CONFIG_M686) += -march=i686 -cflags-$(CONFIG_MPENTIUMII) += -march=i686 $(call cc-option,-mtune=pentium2) -cflags-$(CONFIG_MPENTIUMIII) += -march=i686 $(call cc-option,-mtune=pentium3) -cflags-$(CONFIG_MPENTIUMM) += -march=i686 $(call cc-option,-mtune=pentium3) -cflags-$(CONFIG_MPENTIUM4) += -march=i686 $(call cc-option,-mtune=pentium4) -cflags-$(CONFIG_MK6) += -march=k6 -# Please note, that patches that add -march=athlon-xp and friends are pointless. -# They make zero difference whatsosever to performance at this time. -cflags-$(CONFIG_MK7) += $(call cc-option,-march=athlon,-march=i686 $(align)-functions=4) -cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8,$(call cc-option,-march=athlon,-march=i686 $(align)-functions=4)) -cflags-$(CONFIG_MCRUSOE) += -march=i686 $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0 -cflags-$(CONFIG_MEFFICEON) += -march=i686 $(call cc-option,-mtune=pentium3) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0 -cflags-$(CONFIG_MWINCHIPC6) += $(call cc-option,-march=winchip-c6,-march=i586) -cflags-$(CONFIG_MWINCHIP2) += $(call cc-option,-march=winchip2,-march=i586) -cflags-$(CONFIG_MWINCHIP3D) += $(call cc-option,-march=winchip2,-march=i586) -cflags-$(CONFIG_MCYRIXIII) += $(call cc-option,-march=c3,-march=i486) $(align)-functions=0 $(align)-jumps=0 $(align)-loops=0 -cflags-$(CONFIG_MVIAC3_2) += $(call cc-option,-march=c3-2,-march=i686) - -# AMD Elan support -cflags-$(CONFIG_X86_ELAN) += -march=i486 - -# Geode GX1 support -cflags-$(CONFIG_MGEODEGX1) += $(call cc-option,-march=pentium-mmx,-march=i486) - -# -mregparm=3 works ok on gcc-3.0 and later -# -GCC_VERSION := $(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-version.sh $(CC)) -cflags-$(CONFIG_REGPARM) += $(shell if [ $(GCC_VERSION) -ge 0300 ] ; then echo "-mregparm=3"; fi ;) - -# Disable unit-at-a-time mode, it makes gcc use a lot more stack -# due to the lack of sharing of stacklots. -CFLAGS += $(call cc-option,-fno-unit-at-a-time,) - -CFLAGS += $(cflags-y) - -head-y := arch/xen/i386/kernel/head.o arch/xen/i386/kernel/init_task.o - -libs-y += arch/i386/lib/ -core-y += arch/xen/i386/kernel/ \ - arch/xen/i386/mm/ \ - arch/xen/i386/mach-default/ \ - arch/i386/crypto/ -# \ -# arch/xen/$(mcore-y)/ -drivers-$(CONFIG_MATH_EMULATION) += arch/i386/math-emu/ -drivers-$(CONFIG_PCI) += arch/xen/i386/pci/ -# must be linked after kernel/ -drivers-$(CONFIG_OPROFILE) += arch/i386/oprofile/ -drivers-$(CONFIG_PM) += arch/i386/power/ - -# for clean -obj- += kernel/ mm/ pci/ -#obj- += ../../i386/lib/ ../../i386/mm/ -#../../i386/$(mcore-y)/ -#obj- += ../../i386/pci/ ../../i386/oprofile/ ../../i386/power/ - -xenflags-y += -Iinclude/asm-xen/asm-i386/mach-xen \ - -Iinclude/asm-i386/mach-default -CFLAGS += $(xenflags-y) -AFLAGS += $(xenflags-y) - -prepare: include/asm-$(XENARCH)/asm_offsets.h -CLEAN_FILES += include/asm-$(XENARCH)/asm_offsets.h - -arch/$(XENARCH)/kernel/asm-offsets.s: include/asm include/.asm-ignore \ - include/linux/version.h include/config/MARKER - -include/asm-$(XENARCH)/asm_offsets.h: arch/$(XENARCH)/kernel/asm-offsets.s - $(call filechk,gen-asm-offsets) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/Makefile --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/Makefile Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,100 +0,0 @@ -# -# Makefile for the linux kernel. -# - -XENARCH := $(subst ",,$(CONFIG_XENARCH)) - -CFLAGS += -Iarch/$(XENARCH)/kernel -AFLAGS += -Iarch/$(XENARCH)/kernel - -extra-y := head.o init_task.o - -obj-y := process.o signal.o entry.o traps.o \ - time.o ioport.o ldt.o setup.o \ - pci-dma.o i386_ksyms.o irq.o quirks.o fixup.o - -c-obj-y := semaphore.o vm86.o \ - ptrace.o sys_i386.o \ - i387.o dmi_scan.o bootflag.o -s-obj-y := - -obj-y += cpu/ -#obj-y += timers/ -obj-$(CONFIG_ACPI_BOOT) += acpi/ -#c-obj-$(CONFIG_X86_BIOS_REBOOT) += reboot.o -c-obj-$(CONFIG_MCA) += mca.o -c-obj-$(CONFIG_X86_MSR) += msr.o -c-obj-$(CONFIG_X86_CPUID) += cpuid.o -obj-$(CONFIG_MICROCODE) += microcode.o -c-obj-$(CONFIG_APM) += apm.o -obj-$(CONFIG_X86_SMP) += smp.o -#obj-$(CONFIG_X86_TRAMPOLINE) += trampoline.o -obj-$(CONFIG_X86_MPPARSE) += mpparse.o -obj-$(CONFIG_X86_LOCAL_APIC) += apic.o -c-obj-$(CONFIG_X86_LOCAL_APIC) += nmi.o -obj-$(CONFIG_X86_IO_APIC) += io_apic.o -c-obj-$(CONFIG_X86_REBOOTFIXUPS) += reboot_fixups.o -c-obj-$(CONFIG_X86_NUMAQ) += numaq.o -c-obj-$(CONFIG_X86_SUMMIT_NUMA) += summit.o -c-obj-$(CONFIG_MODULES) += module.o -c-obj-y += sysenter.o -obj-y += vsyscall.o -c-obj-$(CONFIG_ACPI_SRAT) += srat.o -c-obj-$(CONFIG_HPET_TIMER) += time_hpet.o -c-obj-$(CONFIG_EFI) += efi.o efi_stub.o -c-obj-$(CONFIG_EARLY_PRINTK) += early_printk.o -c-obj-$(CONFIG_SMP_ALTERNATIVES)+= smpalts.o -obj-$(CONFIG_SWIOTLB) += swiotlb.o - -EXTRA_AFLAGS := -traditional - -c-obj-$(CONFIG_SCx200) += scx200.o - -# vsyscall.o contains the vsyscall DSO images as __initdata. -# We must build both images before we can assemble it. -# Note: kbuild does not track this dependency due to usage of .incbin -$(obj)/vsyscall.o: $(obj)/vsyscall-int80.so $(obj)/vsyscall-sysenter.so -targets += $(foreach F,int80 sysenter,vsyscall-$F.o vsyscall-$F.so) -targets += vsyscall-note.o vsyscall.lds - -# The DSO images are built using a special linker script. -quiet_cmd_syscall = SYSCALL $@ - cmd_syscall = $(CC) -m elf_i386 -nostdlib $(SYSCFLAGS_$(@F)) \ - -Wl,-T,$(filter-out FORCE,$^) -o $@ - -export CPPFLAGS_vsyscall.lds += -P -C -U$(ARCH) - -vsyscall-flags = -shared -s -Wl,-soname=linux-gate.so.1 -SYSCFLAGS_vsyscall-sysenter.so = $(vsyscall-flags) -SYSCFLAGS_vsyscall-int80.so = $(vsyscall-flags) - -$(obj)/vsyscall-int80.so $(obj)/vsyscall-sysenter.so: \ -$(obj)/vsyscall-%.so: $(src)/vsyscall.lds \ - $(obj)/vsyscall-%.o $(obj)/vsyscall-note.o FORCE - $(call if_changed,syscall) - -# We also create a special relocatable object that should mirror the symbol -# table and layout of the linked DSO. With ld -R we can then refer to -# these symbols in the kernel code rather than hand-coded addresses. -extra-y += vsyscall-syms.o -$(obj)/built-in.o: $(obj)/vsyscall-syms.o -$(obj)/built-in.o: ld_flags += -R $(obj)/vsyscall-syms.o - -SYSCFLAGS_vsyscall-syms.o = -r -$(obj)/vsyscall-syms.o: $(src)/vsyscall.lds \ - $(obj)/vsyscall-sysenter.o $(obj)/vsyscall-note.o FORCE - $(call if_changed,syscall) - -c-link := -s-link := vsyscall-int80.o vsyscall-sysenter.o vsyscall-sigreturn.o vsyscall.lds.o - -$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-obj-m) $(c-link)) $(patsubst %.o,$(obj)/%.S,$(s-obj-y) $(s-link)): - @ln -fsn $(srctree)/arch/i386/kernel/$(notdir $@) $@ - -$(obj)/vsyscall-int80.S: $(obj)/vsyscall-sigreturn.S - -obj-y += $(c-obj-y) $(s-obj-y) -obj-m += $(c-obj-m) - -clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-m) $(c-obj-) $(c-link)) -clean-files += $(patsubst %.o,%.S,$(s-obj-y) $(s-obj-) $(s-link)) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/acpi/Makefile --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/acpi/Makefile Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,13 +0,0 @@ -obj-$(CONFIG_ACPI_BOOT) := boot.o -c-obj-$(CONFIG_X86_IO_APIC) += earlyquirk.o -c-obj-$(CONFIG_ACPI_SLEEP) += sleep.o wakeup.o - -c-link := - -$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)): - @ln -fsn $(srctree)/arch/i386/kernel/acpi/$(notdir $@) $@ - -obj-y += $(c-obj-y) $(s-obj-y) - -clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link)) -clean-files += $(patsubst %.o,%.S,$(s-obj-y) $(s-obj-) $(s-link)) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/acpi/boot.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/acpi/boot.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,920 +0,0 @@ -/* - * boot.c - Architecture-Specific Low-Level ACPI Boot Support - * - * Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@xxxxxxxxx> - * Copyright (C) 2001 Jun Nakajima <jun.nakajima@xxxxxxxxx> - * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - */ - -#include <linux/init.h> -#include <linux/config.h> -#include <linux/acpi.h> -#include <linux/efi.h> -#include <linux/irq.h> -#include <linux/module.h> - -#include <asm/pgtable.h> -#include <asm/io_apic.h> -#include <asm/apic.h> -#include <asm/io.h> -#include <asm/irq.h> -#include <asm/mpspec.h> -#ifdef CONFIG_XEN -#include <asm/fixmap.h> -#endif - -#ifdef CONFIG_X86_64 - -static inline void acpi_madt_oem_check(char *oem_id, char *oem_table_id) { } -extern void __init clustered_apic_check(void); -static inline int ioapic_setup_disabled(void) { return 0; } -#include <asm/proto.h> - -#else /* X86 */ - -#ifdef CONFIG_X86_LOCAL_APIC -#include <mach_apic.h> -#include <mach_mpparse.h> -#endif /* CONFIG_X86_LOCAL_APIC */ - -#endif /* X86 */ - -#define BAD_MADT_ENTRY(entry, end) ( \ - (!entry) || (unsigned long)entry + sizeof(*entry) > end || \ - ((acpi_table_entry_header *)entry)->length != sizeof(*entry)) - -#define PREFIX "ACPI: " - -#ifdef CONFIG_ACPI_PCI -int acpi_noirq __initdata; /* skip ACPI IRQ initialization */ -int acpi_pci_disabled __initdata; /* skip ACPI PCI scan and IRQ initialization */ -#else -int acpi_noirq __initdata = 1; -int acpi_pci_disabled __initdata = 1; -#endif -int acpi_ht __initdata = 1; /* enable HT */ - -int acpi_lapic; -int acpi_ioapic; -int acpi_strict; -EXPORT_SYMBOL(acpi_strict); - -acpi_interrupt_flags acpi_sci_flags __initdata; -int acpi_sci_override_gsi __initdata; -int acpi_skip_timer_override __initdata; - -#ifdef CONFIG_X86_LOCAL_APIC -static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; -#endif - -#ifndef __HAVE_ARCH_CMPXCHG -#warning ACPI uses CMPXCHG, i486 and later hardware -#endif - -#define MAX_MADT_ENTRIES 256 -u8 x86_acpiid_to_apicid[MAX_MADT_ENTRIES] = - { [0 ... MAX_MADT_ENTRIES-1] = 0xff }; -EXPORT_SYMBOL(x86_acpiid_to_apicid); - -/* -------------------------------------------------------------------------- - Boot-time Configuration - -------------------------------------------------------------------------- */ - -/* - * The default interrupt routing model is PIC (8259). This gets - * overriden if IOAPICs are enumerated (below). - */ -enum acpi_irq_model_id acpi_irq_model = ACPI_IRQ_MODEL_PIC; - -#if defined(CONFIG_X86_64) && !defined(CONFIG_XEN) - -/* rely on all ACPI tables being in the direct mapping */ -char *__acpi_map_table(unsigned long phys_addr, unsigned long size) -{ - if (!phys_addr || !size) - return NULL; - - if (phys_addr < (end_pfn_map << PAGE_SHIFT)) - return __va(phys_addr); - - return NULL; -} - -#else - -/* - * Temporarily use the virtual area starting from FIX_IO_APIC_BASE_END, - * to map the target physical address. The problem is that set_fixmap() - * provides a single page, and it is possible that the page is not - * sufficient. - * By using this area, we can map up to MAX_IO_APICS pages temporarily, - * i.e. until the next __va_range() call. - * - * Important Safety Note: The fixed I/O APIC page numbers are *subtracted* - * from the fixed base. That's why we start at FIX_IO_APIC_BASE_END and - * count idx down while incrementing the phys address. - */ -char *__acpi_map_table(unsigned long phys, unsigned long size) -{ - unsigned long base, offset, mapped_size; - int idx; - -#ifndef CONFIG_XEN - if (phys + size < 8*1024*1024) - return __va(phys); -#endif - - offset = phys & (PAGE_SIZE - 1); - mapped_size = PAGE_SIZE - offset; - set_fixmap(FIX_ACPI_END, phys); - base = fix_to_virt(FIX_ACPI_END); - - /* - * Most cases can be covered by the below. - */ - idx = FIX_ACPI_END; - while (mapped_size < size) { - if (--idx < FIX_ACPI_BEGIN) - return NULL; /* cannot handle this */ - phys += PAGE_SIZE; - set_fixmap(idx, phys); - mapped_size += PAGE_SIZE; - } - - return ((unsigned char *) base + offset); -} -#endif - -#ifdef CONFIG_PCI_MMCONFIG -static int __init acpi_parse_mcfg(unsigned long phys_addr, unsigned long size) -{ - struct acpi_table_mcfg *mcfg; - - if (!phys_addr || !size) - return -EINVAL; - - mcfg = (struct acpi_table_mcfg *) __acpi_map_table(phys_addr, size); - if (!mcfg) { - printk(KERN_WARNING PREFIX "Unable to map MCFG\n"); - return -ENODEV; - } - - if (mcfg->base_reserved) { - printk(KERN_ERR PREFIX "MMCONFIG not in low 4GB of memory\n"); - return -ENODEV; - } - - pci_mmcfg_base_addr = mcfg->base_address; - - return 0; -} -#else -#define acpi_parse_mcfg NULL -#endif /* !CONFIG_PCI_MMCONFIG */ - -#ifdef CONFIG_X86_LOCAL_APIC -static int __init -acpi_parse_madt ( - unsigned long phys_addr, - unsigned long size) -{ - struct acpi_table_madt *madt = NULL; - - if (!phys_addr || !size) - return -EINVAL; - - madt = (struct acpi_table_madt *) __acpi_map_table(phys_addr, size); - if (!madt) { - printk(KERN_WARNING PREFIX "Unable to map MADT\n"); - return -ENODEV; - } - - if (madt->lapic_address) { - acpi_lapic_addr = (u64) madt->lapic_address; - - printk(KERN_DEBUG PREFIX "Local APIC address 0x%08x\n", - madt->lapic_address); - } - - acpi_madt_oem_check(madt->header.oem_id, madt->header.oem_table_id); - - return 0; -} - - -static int __init -acpi_parse_lapic ( - acpi_table_entry_header *header, const unsigned long end) -{ - struct acpi_table_lapic *processor = NULL; - - processor = (struct acpi_table_lapic*) header; - - if (BAD_MADT_ENTRY(processor, end)) - return -EINVAL; - - acpi_table_print_madt_entry(header); - - /* no utility in registering a disabled processor */ - if (processor->flags.enabled == 0) - return 0; - - x86_acpiid_to_apicid[processor->acpi_id] = processor->id; - - mp_register_lapic ( - processor->id, /* APIC ID */ - processor->flags.enabled); /* Enabled? */ - - return 0; -} - -static int __init -acpi_parse_lapic_addr_ovr ( - acpi_table_entry_header *header, const unsigned long end) -{ - struct acpi_table_lapic_addr_ovr *lapic_addr_ovr = NULL; - - lapic_addr_ovr = (struct acpi_table_lapic_addr_ovr*) header; - - if (BAD_MADT_ENTRY(lapic_addr_ovr, end)) - return -EINVAL; - - acpi_lapic_addr = lapic_addr_ovr->address; - - return 0; -} - -static int __init -acpi_parse_lapic_nmi ( - acpi_table_entry_header *header, const unsigned long end) -{ - struct acpi_table_lapic_nmi *lapic_nmi = NULL; - - lapic_nmi = (struct acpi_table_lapic_nmi*) header; - - if (BAD_MADT_ENTRY(lapic_nmi, end)) - return -EINVAL; - - acpi_table_print_madt_entry(header); - - if (lapic_nmi->lint != 1) - printk(KERN_WARNING PREFIX "NMI not connected to LINT 1!\n"); - - return 0; -} - - -#endif /*CONFIG_X86_LOCAL_APIC*/ - -#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_ACPI_INTERPRETER) - -static int __init -acpi_parse_ioapic ( - acpi_table_entry_header *header, const unsigned long end) -{ - struct acpi_table_ioapic *ioapic = NULL; - - ioapic = (struct acpi_table_ioapic*) header; - - if (BAD_MADT_ENTRY(ioapic, end)) - return -EINVAL; - - acpi_table_print_madt_entry(header); - - mp_register_ioapic ( - ioapic->id, - ioapic->address, - ioapic->global_irq_base); - - return 0; -} - -/* - * Parse Interrupt Source Override for the ACPI SCI - */ -static void -acpi_sci_ioapic_setup(u32 gsi, u16 polarity, u16 trigger) -{ - if (trigger == 0) /* compatible SCI trigger is level */ - trigger = 3; - - if (polarity == 0) /* compatible SCI polarity is low */ - polarity = 3; - - /* Command-line over-ride via acpi_sci= */ - if (acpi_sci_flags.trigger) - trigger = acpi_sci_flags.trigger; - - if (acpi_sci_flags.polarity) - polarity = acpi_sci_flags.polarity; - - /* - * mp_config_acpi_legacy_irqs() already setup IRQs < 16 - * If GSI is < 16, this will update its flags, - * else it will create a new mp_irqs[] entry. - */ - mp_override_legacy_irq(gsi, polarity, trigger, gsi); - - /* - * stash over-ride to indicate we've been here - * and for later update of acpi_fadt - */ - acpi_sci_override_gsi = gsi; - return; -} - -static int __init -acpi_parse_int_src_ovr ( - acpi_table_entry_header *header, const unsigned long end) -{ - struct acpi_table_int_src_ovr *intsrc = NULL; - - intsrc = (struct acpi_table_int_src_ovr*) header; - - if (BAD_MADT_ENTRY(intsrc, end)) - return -EINVAL; - - acpi_table_print_madt_entry(header); - - if (intsrc->bus_irq == acpi_fadt.sci_int) { - acpi_sci_ioapic_setup(intsrc->global_irq, - intsrc->flags.polarity, intsrc->flags.trigger); - return 0; - } - - if (acpi_skip_timer_override && - intsrc->bus_irq == 0 && intsrc->global_irq == 2) { - printk(PREFIX "BIOS IRQ0 pin2 override ignored.\n"); - return 0; - } - - mp_override_legacy_irq ( - intsrc->bus_irq, - intsrc->flags.polarity, - intsrc->flags.trigger, - intsrc->global_irq); - - return 0; -} - - -static int __init -acpi_parse_nmi_src ( - acpi_table_entry_header *header, const unsigned long end) -{ - struct acpi_table_nmi_src *nmi_src = NULL; - - nmi_src = (struct acpi_table_nmi_src*) header; - - if (BAD_MADT_ENTRY(nmi_src, end)) - return -EINVAL; - - acpi_table_print_madt_entry(header); - - /* TBD: Support nimsrc entries? */ - - return 0; -} - -#endif /* CONFIG_X86_IO_APIC */ - -#ifdef CONFIG_ACPI_BUS - -/* - * acpi_pic_sci_set_trigger() - * - * use ELCR to set PIC-mode trigger type for SCI - * - * If a PIC-mode SCI is not recognized or gives spurious IRQ7's - * it may require Edge Trigger -- use "acpi_sci=edge" - * - * Port 0x4d0-4d1 are ECLR1 and ECLR2, the Edge/Level Control Registers - * for the 8259 PIC. bit[n] = 1 means irq[n] is Level, otherwise Edge. - * ECLR1 is IRQ's 0-7 (IRQ 0, 1, 2 must be 0) - * ECLR2 is IRQ's 8-15 (IRQ 8, 13 must be 0) - */ - -void __init -acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger) -{ - unsigned int mask = 1 << irq; - unsigned int old, new; - - /* Real old ELCR mask */ - old = inb(0x4d0) | (inb(0x4d1) << 8); - - /* - * If we use ACPI to set PCI irq's, then we should clear ELCR - * since we will set it correctly as we enable the PCI irq - * routing. - */ - new = acpi_noirq ? old : 0; - - /* - * Update SCI information in the ELCR, it isn't in the PCI - * routing tables.. - */ - switch (trigger) { - case 1: /* Edge - clear */ - new &= ~mask; - break; - case 3: /* Level - set */ - new |= mask; - break; - } - - if (old == new) - return; - - printk(PREFIX "setting ELCR to %04x (from %04x)\n", new, old); - outb(new, 0x4d0); - outb(new >> 8, 0x4d1); -} - - -#endif /* CONFIG_ACPI_BUS */ - -int acpi_gsi_to_irq(u32 gsi, unsigned int *irq) -{ -#ifdef CONFIG_X86_IO_APIC - if (use_pci_vector() && !platform_legacy_irq(gsi)) - *irq = IO_APIC_VECTOR(gsi); - else -#endif - *irq = gsi; - return 0; -} - -unsigned int acpi_register_gsi(u32 gsi, int edge_level, int active_high_low) -{ - unsigned int irq; - unsigned int plat_gsi = gsi; - -#ifdef CONFIG_PCI - /* - * Make sure all (legacy) PCI IRQs are set as level-triggered. - */ - if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) { - extern void eisa_set_level_irq(unsigned int irq); - - if (edge_level == ACPI_LEVEL_SENSITIVE) - eisa_set_level_irq(gsi); - } -#endif - -#ifdef CONFIG_X86_IO_APIC - if (acpi_irq_model == ACPI_IRQ_MODEL_IOAPIC) { - plat_gsi = mp_register_gsi(gsi, edge_level, active_high_low); - } -#endif - acpi_gsi_to_irq(plat_gsi, &irq); - return irq; -} -EXPORT_SYMBOL(acpi_register_gsi); - -/* - * ACPI based hotplug support for CPU - */ -#ifdef CONFIG_ACPI_HOTPLUG_CPU -int -acpi_map_lsapic(acpi_handle handle, int *pcpu) -{ - /* TBD */ - return -EINVAL; -} -EXPORT_SYMBOL(acpi_map_lsapic); - - -int -acpi_unmap_lsapic(int cpu) -{ - /* TBD */ - return -EINVAL; -} -EXPORT_SYMBOL(acpi_unmap_lsapic); -#endif /* CONFIG_ACPI_HOTPLUG_CPU */ - -static unsigned long __init -acpi_scan_rsdp ( - unsigned long start, - unsigned long length) -{ - unsigned long offset = 0; - unsigned long sig_len = sizeof("RSD PTR ") - 1; - unsigned long vstart = (unsigned long)isa_bus_to_virt(start); - - /* - * Scan all 16-byte boundaries of the physical memory region for the - * RSDP signature. - */ - for (offset = 0; offset < length; offset += 16) { - if (strncmp((char *) (vstart + offset), "RSD PTR ", sig_len)) - continue; - return (start + offset); - } - - return 0; -} - -static int __init acpi_parse_sbf(unsigned long phys_addr, unsigned long size) -{ - struct acpi_table_sbf *sb; - - if (!phys_addr || !size) - return -EINVAL; - - sb = (struct acpi_table_sbf *) __acpi_map_table(phys_addr, size); - if (!sb) { - printk(KERN_WARNING PREFIX "Unable to map SBF\n"); - return -ENODEV; - } - - sbf_port = sb->sbf_cmos; /* Save CMOS port */ - - return 0; -} - - -#ifdef CONFIG_HPET_TIMER - -static int __init acpi_parse_hpet(unsigned long phys, unsigned long size) -{ - struct acpi_table_hpet *hpet_tbl; - - if (!phys || !size) - return -EINVAL; - - hpet_tbl = (struct acpi_table_hpet *) __acpi_map_table(phys, size); - if (!hpet_tbl) { - printk(KERN_WARNING PREFIX "Unable to map HPET\n"); - return -ENODEV; - } - - if (hpet_tbl->addr.space_id != ACPI_SPACE_MEM) { - printk(KERN_WARNING PREFIX "HPET timers must be located in " - "memory.\n"); - return -1; - } - -#ifdef CONFIG_X86_64 - vxtime.hpet_address = hpet_tbl->addr.addrl | - ((long) hpet_tbl->addr.addrh << 32); - - printk(KERN_INFO PREFIX "HPET id: %#x base: %#lx\n", - hpet_tbl->id, vxtime.hpet_address); -#else /* X86 */ - { - extern unsigned long hpet_address; - - hpet_address = hpet_tbl->addr.addrl; - printk(KERN_INFO PREFIX "HPET id: %#x base: %#lx\n", - hpet_tbl->id, hpet_address); - } -#endif /* X86 */ - - return 0; -} -#else -#define acpi_parse_hpet NULL -#endif - -#ifdef CONFIG_X86_PM_TIMER -extern u32 pmtmr_ioport; -#endif - -static int __init acpi_parse_fadt(unsigned long phys, unsigned long size) -{ - struct fadt_descriptor_rev2 *fadt = NULL; - - fadt = (struct fadt_descriptor_rev2*) __acpi_map_table(phys,size); - if(!fadt) { - printk(KERN_WARNING PREFIX "Unable to map FADT\n"); - return 0; - } - -#ifdef CONFIG_ACPI_INTERPRETER - /* initialize sci_int early for INT_SRC_OVR MADT parsing */ - acpi_fadt.sci_int = fadt->sci_int; -#endif - -#ifdef CONFIG_ACPI_BUS - /* initialize rev and apic_phys_dest_mode for x86_64 genapic */ - acpi_fadt.revision = fadt->revision; - acpi_fadt.force_apic_physical_destination_mode = fadt->force_apic_physical_destination_mode; -#endif - -#if defined(CONFIG_X86_PM_TIMER) && !defined(CONFIG_XEN) - /* detect the location of the ACPI PM Timer */ - if (fadt->revision >= FADT2_REVISION_ID) { - /* FADT rev. 2 */ - if (fadt->xpm_tmr_blk.address_space_id != ACPI_ADR_SPACE_SYSTEM_IO) - return 0; - - pmtmr_ioport = fadt->xpm_tmr_blk.address; - } else { - /* FADT rev. 1 */ - pmtmr_ioport = fadt->V1_pm_tmr_blk; - } - if (pmtmr_ioport) - printk(KERN_INFO PREFIX "PM-Timer IO Port: %#x\n", pmtmr_ioport); -#endif - return 0; -} - - -unsigned long __init -acpi_find_rsdp (void) -{ - unsigned long rsdp_phys = 0; - - if (efi_enabled) { - if (efi.acpi20) - return __pa(efi.acpi20); - else if (efi.acpi) - return __pa(efi.acpi); - } - /* - * Scan memory looking for the RSDP signature. First search EBDA (low - * memory) paragraphs and then search upper memory (E0000-FFFFF). - */ - rsdp_phys = acpi_scan_rsdp (0, 0x400); - if (!rsdp_phys) - rsdp_phys = acpi_scan_rsdp (0xE0000, 0x20000); - - return rsdp_phys; -} - -#ifdef CONFIG_X86_LOCAL_APIC -/* - * Parse LAPIC entries in MADT - * returns 0 on success, < 0 on error - */ -static int __init -acpi_parse_madt_lapic_entries(void) -{ - int count; - - /* - * Note that the LAPIC address is obtained from the MADT (32-bit value) - * and (optionally) overriden by a LAPIC_ADDR_OVR entry (64-bit value). - */ - - count = acpi_table_parse_madt(ACPI_MADT_LAPIC_ADDR_OVR, acpi_parse_lapic_addr_ovr, 0); - if (count < 0) { - printk(KERN_ERR PREFIX "Error parsing LAPIC address override entry\n"); - return count; - } - - mp_register_lapic_address(acpi_lapic_addr); - - count = acpi_table_parse_madt(ACPI_MADT_LAPIC, acpi_parse_lapic, - MAX_APICS); - if (!count) { - printk(KERN_ERR PREFIX "No LAPIC entries present\n"); - /* TBD: Cleanup to allow fallback to MPS */ - return -ENODEV; - } - else if (count < 0) { - printk(KERN_ERR PREFIX "Error parsing LAPIC entry\n"); - /* TBD: Cleanup to allow fallback to MPS */ - return count; - } - - count = acpi_table_parse_madt(ACPI_MADT_LAPIC_NMI, acpi_parse_lapic_nmi, 0); - if (count < 0) { - printk(KERN_ERR PREFIX "Error parsing LAPIC NMI entry\n"); - /* TBD: Cleanup to allow fallback to MPS */ - return count; - } - return 0; -} -#endif /* CONFIG_X86_LOCAL_APIC */ - -#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_ACPI_INTERPRETER) -/* - * Parse IOAPIC related entries in MADT - * returns 0 on success, < 0 on error - */ -static int __init -acpi_parse_madt_ioapic_entries(void) -{ - int count; - - /* - * ACPI interpreter is required to complete interrupt setup, - * so if it is off, don't enumerate the io-apics with ACPI. - * If MPS is present, it will handle them, - * otherwise the system will stay in PIC mode - */ - if (acpi_disabled || acpi_noirq) { - return -ENODEV; - } - - /* - * if "noapic" boot option, don't look for IO-APICs - */ - if (skip_ioapic_setup) { - printk(KERN_INFO PREFIX "Skipping IOAPIC probe " - "due to 'noapic' option.\n"); - return -ENODEV; - } - - count = acpi_table_parse_madt(ACPI_MADT_IOAPIC, acpi_parse_ioapic, MAX_IO_APICS); - if (!count) { - printk(KERN_ERR PREFIX "No IOAPIC entries present\n"); - return -ENODEV; - } - else if (count < 0) { - printk(KERN_ERR PREFIX "Error parsing IOAPIC entry\n"); - return count; - } - - count = acpi_table_parse_madt(ACPI_MADT_INT_SRC_OVR, acpi_parse_int_src_ovr, NR_IRQ_VECTORS); - if (count < 0) { - printk(KERN_ERR PREFIX "Error parsing interrupt source overrides entry\n"); - /* TBD: Cleanup to allow fallback to MPS */ - return count; - } - - /* - * If BIOS did not supply an INT_SRC_OVR for the SCI - * pretend we got one so we can set the SCI flags. - */ - if (!acpi_sci_override_gsi) - acpi_sci_ioapic_setup(acpi_fadt.sci_int, 0, 0); - - /* Fill in identity legacy mapings where no override */ - mp_config_acpi_legacy_irqs(); - - count = acpi_table_parse_madt(ACPI_MADT_NMI_SRC, acpi_parse_nmi_src, NR_IRQ_VECTORS); - if (count < 0) { - printk(KERN_ERR PREFIX "Error parsing NMI SRC entry\n"); - /* TBD: Cleanup to allow fallback to MPS */ - return count; - } - - return 0; -} -#else -static inline int acpi_parse_madt_ioapic_entries(void) -{ - return -1; -} -#endif /* !(CONFIG_X86_IO_APIC && CONFIG_ACPI_INTERPRETER) */ - - -static void __init -acpi_process_madt(void) -{ -#ifdef CONFIG_X86_LOCAL_APIC - int count, error; - - count = acpi_table_parse(ACPI_APIC, acpi_parse_madt); - if (count >= 1) { - - /* - * Parse MADT LAPIC entries - */ - error = acpi_parse_madt_lapic_entries(); - if (!error) { - acpi_lapic = 1; - - /* - * Parse MADT IO-APIC entries - */ - error = acpi_parse_madt_ioapic_entries(); - if (!error) { - acpi_irq_model = ACPI_IRQ_MODEL_IOAPIC; - acpi_irq_balance_set(NULL); - acpi_ioapic = 1; - - smp_found_config = 1; - clustered_apic_check(); - } - } - if (error == -EINVAL) { - /* - * Dell Precision Workstation 410, 610 come here. - */ - printk(KERN_ERR PREFIX "Invalid BIOS MADT, disabling ACPI\n"); - disable_acpi(); - } - } -#endif - return; -} - -/* - * acpi_boot_table_init() and acpi_boot_init() - * called from setup_arch(), always. - * 1. checksums all tables - * 2. enumerates lapics - * 3. enumerates io-apics - * - * acpi_table_init() is separate to allow reading SRAT without - * other side effects. - * - * side effects of acpi_boot_init: - * acpi_lapic = 1 if LAPIC found - * acpi_ioapic = 1 if IOAPIC found - * if (acpi_lapic && acpi_ioapic) smp_found_config = 1; - * if acpi_blacklisted() acpi_disabled = 1; - * acpi_irq_model=... - * ... - * - * return value: (currently ignored) - * 0: success - * !0: failure - */ - -int __init -acpi_boot_table_init(void) -{ - int error; - - /* - * If acpi_disabled, bail out - * One exception: acpi=ht continues far enough to enumerate LAPICs - */ - if (acpi_disabled && !acpi_ht) - return 1; - - /* - * Initialize the ACPI boot-time table parser. - */ - error = acpi_table_init(); - if (error) { - disable_acpi(); - return error; - } - -#ifdef __i386__ - check_acpi_pci(); -#endif - - acpi_table_parse(ACPI_BOOT, acpi_parse_sbf); - - /* - * blacklist may disable ACPI entirely - */ - error = acpi_blacklisted(); - if (error) { - extern int acpi_force; - - if (acpi_force) { - printk(KERN_WARNING PREFIX "acpi=force override\n"); - } else { - printk(KERN_WARNING PREFIX "Disabling ACPI support\n"); - disable_acpi(); - return error; - } - } - - return 0; -} - - -int __init acpi_boot_init(void) -{ - /* - * If acpi_disabled, bail out - * One exception: acpi=ht continues far enough to enumerate LAPICs - */ - if (acpi_disabled && !acpi_ht) - return 1; - - acpi_table_parse(ACPI_BOOT, acpi_parse_sbf); - - /* - * set sci_int and PM timer address - */ - acpi_table_parse(ACPI_FADT, acpi_parse_fadt); - - /* - * Process the Multiple APIC Description Table (MADT), if present - */ - acpi_process_madt(); - - acpi_table_parse(ACPI_HPET, acpi_parse_hpet); - acpi_table_parse(ACPI_MCFG, acpi_parse_mcfg); - - return 0; -} - diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/apic.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/apic.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,83 +0,0 @@ -/* - * Local APIC handling, local APIC timers - * - * (c) 1999, 2000 Ingo Molnar <mingo@xxxxxxxxxx> - * - * Fixes - * Maciej W. Rozycki : Bits for genuine 82489DX APICs; - * thanks to Eric Gilmore - * and Rolf G. Tews - * for testing these extensively. - * Maciej W. Rozycki : Various updates and fixes. - * Mikael Pettersson : Power Management for UP-APIC. - * Pavel Machek and - * Mikael Pettersson : PM converted to driver model. - */ - -#include <linux/config.h> -#include <linux/init.h> - -#include <linux/mm.h> -#include <linux/irq.h> -#include <linux/delay.h> -#include <linux/bootmem.h> -#include <linux/smp_lock.h> -#include <linux/interrupt.h> -#include <linux/mc146818rtc.h> -#include <linux/kernel_stat.h> -#include <linux/sysdev.h> - -#include <asm/atomic.h> -#include <asm/smp.h> -#include <asm/mtrr.h> -#include <asm/mpspec.h> -#include <asm/desc.h> -#include <asm/arch_hooks.h> -#include <asm/hpet.h> - -#include <mach_apic.h> - -#include "io_ports.h" - -/* - * Debug level - */ -int apic_verbosity; - -int get_physical_broadcast(void) -{ - return 0xff; -} - -/* - * 'what should we do if we get a hw irq event on an illegal vector'. - * each architecture has to answer this themselves. - */ -void ack_bad_irq(unsigned int irq) -{ - printk("unexpected IRQ trap at vector %02x\n", irq); - /* - * Currently unexpected vectors happen only on SMP and APIC. - * We _must_ ack these because every local APIC has only N - * irq slots per priority level, and a 'hanging, unacked' IRQ - * holds up an irq slot - in excessive cases (when multiple - * unexpected vectors occur) that might lock up the APIC - * completely. - */ - ack_APIC_irq(); -} - -/* - * This initializes the IO-APIC and APIC hardware if this is - * a UP kernel. - */ -int __init APIC_init_uniprocessor (void) -{ -#ifdef CONFIG_X86_IO_APIC - if (smp_found_config) - if (!skip_ioapic_setup && nr_ioapics) - setup_IO_APIC(); -#endif - - return 0; -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/cpu/Makefile --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/cpu/Makefile Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,31 +0,0 @@ -# -# Makefile for x86-compatible CPU details and quirks -# - -CFLAGS += -Iarch/i386/kernel/cpu - -obj-y := common.o -c-obj-y += proc.o - -c-obj-y += amd.o -c-obj-y += cyrix.o -c-obj-y += centaur.o -c-obj-y += transmeta.o -c-obj-y += intel.o intel_cacheinfo.o -c-obj-y += rise.o -c-obj-y += nexgen.o -c-obj-y += umc.o - -#obj-$(CONFIG_X86_MCE) += ../../../../i386/kernel/cpu/mcheck/ - -obj-$(CONFIG_MTRR) += mtrr/ -#obj-$(CONFIG_CPU_FREQ) += ../../../../i386/kernel/cpu/cpufreq/ - -c-link := - -$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)): - @ln -fsn $(srctree)/arch/i386/kernel/cpu/$(notdir $@) $@ - -obj-y += $(c-obj-y) - -clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link)) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/cpu/common.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/cpu/common.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,653 +0,0 @@ -#include <linux/init.h> -#include <linux/string.h> -#include <linux/delay.h> -#include <linux/smp.h> -#include <linux/module.h> -#include <linux/percpu.h> -#include <asm/semaphore.h> -#include <asm/processor.h> -#include <asm/i387.h> -#include <asm/msr.h> -#include <asm/io.h> -#include <asm/mmu_context.h> -#ifdef CONFIG_X86_LOCAL_APIC -#include <asm/mpspec.h> -#include <asm/apic.h> -#include <mach_apic.h> -#endif -#include <asm/hypervisor.h> - -#include "cpu.h" - -#ifndef CONFIG_XEN -DEFINE_PER_CPU(struct desc_struct, cpu_gdt_table[GDT_ENTRIES]); -EXPORT_PER_CPU_SYMBOL(cpu_gdt_table); - -DEFINE_PER_CPU(unsigned char, cpu_16bit_stack[CPU_16BIT_STACK_SIZE]); -EXPORT_PER_CPU_SYMBOL(cpu_16bit_stack); -#endif - -static int cachesize_override __initdata = -1; -static int disable_x86_fxsr __initdata = 0; -static int disable_x86_serial_nr __initdata = 1; - -struct cpu_dev * cpu_devs[X86_VENDOR_NUM] = {}; - -extern void mcheck_init(struct cpuinfo_x86 *c); - -extern void machine_specific_modify_cpu_capabilities(struct cpuinfo_x86 *c); - -extern int disable_pse; - -static void default_init(struct cpuinfo_x86 * c) -{ - /* Not much we can do here... */ - /* Check if at least it has cpuid */ - if (c->cpuid_level == -1) { - /* No cpuid. It must be an ancient CPU */ - if (c->x86 == 4) - strcpy(c->x86_model_id, "486"); - else if (c->x86 == 3) - strcpy(c->x86_model_id, "386"); - } -} - -static struct cpu_dev default_cpu = { - .c_init = default_init, -}; -static struct cpu_dev * this_cpu = &default_cpu; - -static int __init cachesize_setup(char *str) -{ - get_option (&str, &cachesize_override); - return 1; -} -__setup("cachesize=", cachesize_setup); - -int __init get_model_name(struct cpuinfo_x86 *c) -{ - unsigned int *v; - char *p, *q; - - if (cpuid_eax(0x80000000) < 0x80000004) - return 0; - - v = (unsigned int *) c->x86_model_id; - cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]); - cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]); - cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]); - c->x86_model_id[48] = 0; - - /* Intel chips right-justify this string for some dumb reason; - undo that brain damage */ - p = q = &c->x86_model_id[0]; - while ( *p == ' ' ) - p++; - if ( p != q ) { - while ( *p ) - *q++ = *p++; - while ( q <= &c->x86_model_id[48] ) - *q++ = '\0'; /* Zero-pad the rest */ - } - - return 1; -} - - -void __init display_cacheinfo(struct cpuinfo_x86 *c) -{ - unsigned int n, dummy, ecx, edx, l2size; - - n = cpuid_eax(0x80000000); - - if (n >= 0x80000005) { - cpuid(0x80000005, &dummy, &dummy, &ecx, &edx); - printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), D cache %dK (%d bytes/line)\n", - edx>>24, edx&0xFF, ecx>>24, ecx&0xFF); - c->x86_cache_size=(ecx>>24)+(edx>>24); - } - - if (n < 0x80000006) /* Some chips just has a large L1. */ - return; - - ecx = cpuid_ecx(0x80000006); - l2size = ecx >> 16; - - /* do processor-specific cache resizing */ - if (this_cpu->c_size_cache) - l2size = this_cpu->c_size_cache(c,l2size); - - /* Allow user to override all this if necessary. */ - if (cachesize_override != -1) - l2size = cachesize_override; - - if ( l2size == 0 ) - return; /* Again, no L2 cache is possible */ - - c->x86_cache_size = l2size; - - printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n", - l2size, ecx & 0xFF); -} - -/* Naming convention should be: <Name> [(<Codename>)] */ -/* This table only is used unless init_<vendor>() below doesn't set it; */ -/* in particular, if CPUID levels 0x80000002..4 are supported, this isn't used */ - -/* Look up CPU names by table lookup. */ -static char __init *table_lookup_model(struct cpuinfo_x86 *c) -{ - struct cpu_model_info *info; - - if ( c->x86_model >= 16 ) - return NULL; /* Range check */ - - if (!this_cpu) - return NULL; - - info = this_cpu->c_models; - - while (info && info->family) { - if (info->family == c->x86) - return info->model_names[c->x86_model]; - info++; - } - return NULL; /* Not found */ -} - - -void __init get_cpu_vendor(struct cpuinfo_x86 *c, int early) -{ - char *v = c->x86_vendor_id; - int i; - - for (i = 0; i < X86_VENDOR_NUM; i++) { - if (cpu_devs[i]) { - if (!strcmp(v,cpu_devs[i]->c_ident[0]) || - (cpu_devs[i]->c_ident[1] && - !strcmp(v,cpu_devs[i]->c_ident[1]))) { - c->x86_vendor = i; - if (!early) - this_cpu = cpu_devs[i]; - break; - } - } - } -} - - -static int __init x86_fxsr_setup(char * s) -{ - disable_x86_fxsr = 1; - return 1; -} -__setup("nofxsr", x86_fxsr_setup); - - -/* Standard macro to see if a specific flag is changeable */ -static inline int flag_is_changeable_p(u32 flag) -{ - u32 f1, f2; - - asm("pushfl\n\t" - "pushfl\n\t" - "popl %0\n\t" - "movl %0,%1\n\t" - "xorl %2,%0\n\t" - "pushl %0\n\t" - "popfl\n\t" - "pushfl\n\t" - "popl %0\n\t" - "popfl\n\t" - : "=&r" (f1), "=&r" (f2) - : "ir" (flag)); - - return ((f1^f2) & flag) != 0; -} - - -/* Probe for the CPUID instruction */ -static int __init have_cpuid_p(void) -{ - return flag_is_changeable_p(X86_EFLAGS_ID); -} - -/* Do minimum CPU detection early. - Fields really needed: vendor, cpuid_level, family, model, mask, cache alignment. - The others are not touched to avoid unwanted side effects. */ -static void __init early_cpu_detect(void) -{ - struct cpuinfo_x86 *c = &boot_cpu_data; - - c->x86_cache_alignment = 32; - - if (!have_cpuid_p()) - return; - - /* Get vendor name */ - cpuid(0x00000000, &c->cpuid_level, - (int *)&c->x86_vendor_id[0], - (int *)&c->x86_vendor_id[8], - (int *)&c->x86_vendor_id[4]); - - get_cpu_vendor(c, 1); - - c->x86 = 4; - if (c->cpuid_level >= 0x00000001) { - u32 junk, tfms, cap0, misc; - cpuid(0x00000001, &tfms, &misc, &junk, &cap0); - c->x86 = (tfms >> 8) & 15; - c->x86_model = (tfms >> 4) & 15; - if (c->x86 == 0xf) { - c->x86 += (tfms >> 20) & 0xff; - c->x86_model += ((tfms >> 16) & 0xF) << 4; - } - c->x86_mask = tfms & 15; - if (cap0 & (1<<19)) - c->x86_cache_alignment = ((misc >> 8) & 0xff) * 8; - } - - early_intel_workaround(c); - -#ifdef CONFIG_X86_HT - phys_proc_id[smp_processor_id()] = (cpuid_ebx(1) >> 24) & 0xff; -#endif -} - -void __init generic_identify(struct cpuinfo_x86 * c) -{ - u32 tfms, xlvl; - int junk; - - if (have_cpuid_p()) { - /* Get vendor name */ - cpuid(0x00000000, &c->cpuid_level, - (int *)&c->x86_vendor_id[0], - (int *)&c->x86_vendor_id[8], - (int *)&c->x86_vendor_id[4]); - - get_cpu_vendor(c, 0); - /* Initialize the standard set of capabilities */ - /* Note that the vendor-specific code below might override */ - - /* Intel-defined flags: level 0x00000001 */ - if ( c->cpuid_level >= 0x00000001 ) { - u32 capability, excap; - cpuid(0x00000001, &tfms, &junk, &excap, &capability); - c->x86_capability[0] = capability; - c->x86_capability[4] = excap; - c->x86 = (tfms >> 8) & 15; - c->x86_model = (tfms >> 4) & 15; - if (c->x86 == 0xf) { - c->x86 += (tfms >> 20) & 0xff; - c->x86_model += ((tfms >> 16) & 0xF) << 4; - } - c->x86_mask = tfms & 15; - } else { - /* Have CPUID level 0 only - unheard of */ - c->x86 = 4; - } - - /* AMD-defined flags: level 0x80000001 */ - xlvl = cpuid_eax(0x80000000); - if ( (xlvl & 0xffff0000) == 0x80000000 ) { - if ( xlvl >= 0x80000001 ) { - c->x86_capability[1] = cpuid_edx(0x80000001); - c->x86_capability[6] = cpuid_ecx(0x80000001); - } - if ( xlvl >= 0x80000004 ) - get_model_name(c); /* Default name */ - } - } -} - -static void __init squash_the_stupid_serial_number(struct cpuinfo_x86 *c) -{ - if (cpu_has(c, X86_FEATURE_PN) && disable_x86_serial_nr ) { - /* Disable processor serial number */ - unsigned long lo,hi; - rdmsr(MSR_IA32_BBL_CR_CTL,lo,hi); - lo |= 0x200000; - wrmsr(MSR_IA32_BBL_CR_CTL,lo,hi); - printk(KERN_NOTICE "CPU serial number disabled.\n"); - clear_bit(X86_FEATURE_PN, c->x86_capability); - - /* Disabling the serial number may affect the cpuid level */ - c->cpuid_level = cpuid_eax(0); - } -} - -static int __init x86_serial_nr_setup(char *s) -{ - disable_x86_serial_nr = 0; - return 1; -} -__setup("serialnumber", x86_serial_nr_setup); - - - -/* - * This does the hard work of actually picking apart the CPU stuff... - */ -void __init identify_cpu(struct cpuinfo_x86 *c) -{ - int i; - - c->loops_per_jiffy = loops_per_jiffy; - c->x86_cache_size = -1; - c->x86_vendor = X86_VENDOR_UNKNOWN; - c->cpuid_level = -1; /* CPUID not detected */ - c->x86_model = c->x86_mask = 0; /* So far unknown... */ - c->x86_vendor_id[0] = '\0'; /* Unset */ - c->x86_model_id[0] = '\0'; /* Unset */ - c->x86_num_cores = 1; - memset(&c->x86_capability, 0, sizeof c->x86_capability); - - if (!have_cpuid_p()) { - /* First of all, decide if this is a 486 or higher */ - /* It's a 486 if we can modify the AC flag */ - if ( flag_is_changeable_p(X86_EFLAGS_AC) ) - c->x86 = 4; - else - c->x86 = 3; - } - - generic_identify(c); - - printk(KERN_DEBUG "CPU: After generic identify, caps:"); - for (i = 0; i < NCAPINTS; i++) - printk(" %08lx", c->x86_capability[i]); - printk("\n"); - - if (this_cpu->c_identify) { - this_cpu->c_identify(c); - - printk(KERN_DEBUG "CPU: After vendor identify, caps:"); - for (i = 0; i < NCAPINTS; i++) - printk(" %08lx", c->x86_capability[i]); - printk("\n"); - } - - /* - * Vendor-specific initialization. In this section we - * canonicalize the feature flags, meaning if there are - * features a certain CPU supports which CPUID doesn't - * tell us, CPUID claiming incorrect flags, or other bugs, - * we handle them here. - * - * At the end of this section, c->x86_capability better - * indicate the features this CPU genuinely supports! - */ - if (this_cpu->c_init) - this_cpu->c_init(c); - - /* Disable the PN if appropriate */ - squash_the_stupid_serial_number(c); - - /* - * The vendor-specific functions might have changed features. Now - * we do "generic changes." - */ - - /* TSC disabled? */ - if ( tsc_disable ) - clear_bit(X86_FEATURE_TSC, c->x86_capability); - - /* FXSR disabled? */ - if (disable_x86_fxsr) { - clear_bit(X86_FEATURE_FXSR, c->x86_capability); - clear_bit(X86_FEATURE_XMM, c->x86_capability); - } - - if (disable_pse) - clear_bit(X86_FEATURE_PSE, c->x86_capability); - - /* If the model name is still unset, do table lookup. */ - if ( !c->x86_model_id[0] ) { - char *p; - p = table_lookup_model(c); - if ( p ) - strcpy(c->x86_model_id, p); - else - /* Last resort... */ - sprintf(c->x86_model_id, "%02x/%02x", - c->x86_vendor, c->x86_model); - } - - machine_specific_modify_cpu_capabilities(c); - - /* Now the feature flags better reflect actual CPU features! */ - - printk(KERN_DEBUG "CPU: After all inits, caps:"); - for (i = 0; i < NCAPINTS; i++) - printk(" %08lx", c->x86_capability[i]); - printk("\n"); - - /* - * On SMP, boot_cpu_data holds the common feature set between - * all CPUs; so make sure that we indicate which features are - * common between the CPUs. The first time this routine gets - * executed, c == &boot_cpu_data. - */ - if ( c != &boot_cpu_data ) { - /* AND the already accumulated flags with these */ - for ( i = 0 ; i < NCAPINTS ; i++ ) - boot_cpu_data.x86_capability[i] &= c->x86_capability[i]; - } - - /* Init Machine Check Exception if available. */ -#ifdef CONFIG_X86_MCE - mcheck_init(c); -#endif -} - -#ifdef CONFIG_X86_HT -void __init detect_ht(struct cpuinfo_x86 *c) -{ - u32 eax, ebx, ecx, edx; - int index_msb, tmp; - int cpu = smp_processor_id(); - - if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY)) - return; - - cpuid(1, &eax, &ebx, &ecx, &edx); - smp_num_siblings = (ebx & 0xff0000) >> 16; - - if (smp_num_siblings == 1) { - printk(KERN_INFO "CPU: Hyper-Threading is disabled\n"); - } else if (smp_num_siblings > 1 ) { - index_msb = 31; - - if (smp_num_siblings > NR_CPUS) { - printk(KERN_WARNING "CPU: Unsupported number of the siblings %d", smp_num_siblings); - smp_num_siblings = 1; - return; - } - tmp = smp_num_siblings; - while ((tmp & 0x80000000 ) == 0) { - tmp <<=1 ; - index_msb--; - } - if (smp_num_siblings & (smp_num_siblings - 1)) - index_msb++; - phys_proc_id[cpu] = phys_pkg_id((ebx >> 24) & 0xFF, index_msb); - - printk(KERN_INFO "CPU: Physical Processor ID: %d\n", - phys_proc_id[cpu]); - - smp_num_siblings = smp_num_siblings / c->x86_num_cores; - - tmp = smp_num_siblings; - index_msb = 31; - while ((tmp & 0x80000000) == 0) { - tmp <<=1 ; - index_msb--; - } - - if (smp_num_siblings & (smp_num_siblings - 1)) - index_msb++; - - cpu_core_id[cpu] = phys_pkg_id((ebx >> 24) & 0xFF, index_msb); - - if (c->x86_num_cores > 1) - printk(KERN_INFO "CPU: Processor Core ID: %d\n", - cpu_core_id[cpu]); - } -} -#endif - -void __init print_cpu_info(struct cpuinfo_x86 *c) -{ - char *vendor = NULL; - - if (c->x86_vendor < X86_VENDOR_NUM) - vendor = this_cpu->c_vendor; - else if (c->cpuid_level >= 0) - vendor = c->x86_vendor_id; - - if (vendor && strncmp(c->x86_model_id, vendor, strlen(vendor))) - printk("%s ", vendor); - - if (!c->x86_model_id[0]) - printk("%d86", c->x86); - else - printk("%s", c->x86_model_id); - - if (c->x86_mask || c->cpuid_level >= 0) - printk(" stepping %02x\n", c->x86_mask); - else - printk("\n"); -} - -cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE; - -/* This is hacky. :) - * We're emulating future behavior. - * In the future, the cpu-specific init functions will be called implicitly - * via the magic of initcalls. - * They will insert themselves into the cpu_devs structure. - * Then, when cpu_init() is called, we can just iterate over that array. - */ - -extern int intel_cpu_init(void); -extern int cyrix_init_cpu(void); -extern int nsc_init_cpu(void); -extern int amd_init_cpu(void); -extern int centaur_init_cpu(void); -extern int transmeta_init_cpu(void); -extern int rise_init_cpu(void); -extern int nexgen_init_cpu(void); -extern int umc_init_cpu(void); - -void __init early_cpu_init(void) -{ - intel_cpu_init(); - cyrix_init_cpu(); - nsc_init_cpu(); - amd_init_cpu(); - centaur_init_cpu(); - transmeta_init_cpu(); - rise_init_cpu(); - nexgen_init_cpu(); - umc_init_cpu(); - early_cpu_detect(); - -#ifdef CONFIG_DEBUG_PAGEALLOC - /* pse is not compatible with on-the-fly unmapping, - * disable it even if the cpus claim to support it. - */ - clear_bit(X86_FEATURE_PSE, boot_cpu_data.x86_capability); - disable_pse = 1; -#endif -} - -void __cpuinit cpu_gdt_init(struct Xgt_desc_struct *gdt_descr) -{ - unsigned long frames[16]; - unsigned long va; - int f; - - for (va = gdt_descr->address, f = 0; - va < gdt_descr->address + gdt_descr->size; - va += PAGE_SIZE, f++) { - frames[f] = virt_to_mfn(va); - make_lowmem_page_readonly( - (void *)va, XENFEAT_writable_descriptor_tables); - } - if (HYPERVISOR_set_gdt(frames, gdt_descr->size / 8)) - BUG(); - lgdt_finish(); -} - -/* - * cpu_init() initializes state that is per-CPU. Some data is already - * initialized (naturally) in the bootstrap process, such as the GDT - * and IDT. We reload them nevertheless, this function acts as a - * 'CPU state barrier', nothing should get across. - */ -void __cpuinit cpu_init (void) -{ - int cpu = smp_processor_id(); - struct tss_struct * t = &per_cpu(init_tss, cpu); - struct thread_struct *thread = &current->thread; - - if (cpu_test_and_set(cpu, cpu_initialized)) { - printk(KERN_WARNING "CPU#%d already initialized!\n", cpu); - for (;;) local_irq_enable(); - } - printk(KERN_INFO "Initializing CPU#%d\n", cpu); - - if (cpu_has_vme || cpu_has_de) - clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); - if (tsc_disable && cpu_has_tsc) { - printk(KERN_NOTICE "Disabling TSC...\n"); - /**** FIX-HPA: DOES THIS REALLY BELONG HERE? ****/ - clear_bit(X86_FEATURE_TSC, boot_cpu_data.x86_capability); - set_in_cr4(X86_CR4_TSD); - } - - /* - * Set up the per-thread TLS descriptor cache: - */ - memcpy(thread->tls_array, &get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN], - GDT_ENTRY_TLS_ENTRIES * 8); - - cpu_gdt_init(&cpu_gdt_descr[cpu]); - - /* - * Delete NT - */ - __asm__("pushfl ; andl $0xffffbfff,(%esp) ; popfl"); - - /* - * Set up and load the per-CPU TSS and LDT - */ - atomic_inc(&init_mm.mm_count); - current->active_mm = &init_mm; - if (current->mm) - BUG(); - enter_lazy_tlb(&init_mm, current); - - load_esp0(t, thread); - - load_LDT(&init_mm.context); - - /* Clear %fs and %gs. */ - asm volatile ("xorl %eax, %eax; movl %eax, %fs; movl %eax, %gs"); - - /* Clear all 6 debug registers: */ - -#define CD(register) HYPERVISOR_set_debugreg(register, 0) - - CD(0); CD(1); CD(2); CD(3); /* no db4 and db5 */; CD(6); CD(7); - -#undef CD - - /* - * Force FPU initialization: - */ - current_thread_info()->status = 0; - clear_used_math(); - mxcsr_feature_mask_init(); -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/cpu/mtrr/Makefile --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/cpu/mtrr/Makefile Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,16 +0,0 @@ -obj-y := main.o -c-obj-y := if.o - -c-link := - -$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)): $(obj)/mtrr.h - @ln -fsn $(srctree)/arch/i386/kernel/cpu/mtrr/$(notdir $@) $@ - -$(patsubst %.o,$(obj)/%.c,$(obj-y)): $(obj)/mtrr.h - -$(obj)/mtrr.h: - @ln -fsn $(srctree)/arch/i386/kernel/cpu/mtrr/mtrr.h $@ - -obj-y += $(c-obj-y) - -clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link)) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/cpu/mtrr/main.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/cpu/mtrr/main.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,172 +0,0 @@ -#include <linux/init.h> -#include <linux/proc_fs.h> -#include <linux/ctype.h> -#include <linux/module.h> -#include <linux/seq_file.h> -#include <asm/uaccess.h> - -#include <asm/mtrr.h> -#include "mtrr.h" - -void generic_get_mtrr(unsigned int reg, unsigned long *base, - unsigned int *size, mtrr_type * type) -{ - dom0_op_t op; - - op.cmd = DOM0_READ_MEMTYPE; - op.u.read_memtype.reg = reg; - (void)HYPERVISOR_dom0_op(&op); - - *size = op.u.read_memtype.nr_pfns; - *base = op.u.read_memtype.pfn; - *type = op.u.read_memtype.type; -} - -struct mtrr_ops generic_mtrr_ops = { - .use_intel_if = 1, - .get = generic_get_mtrr, -}; - -struct mtrr_ops *mtrr_if = &generic_mtrr_ops; -unsigned int num_var_ranges; -unsigned int *usage_table; - -static void __init set_num_var_ranges(void) -{ - dom0_op_t op; - - for (num_var_ranges = 0; ; num_var_ranges++) { - op.cmd = DOM0_READ_MEMTYPE; - op.u.read_memtype.reg = num_var_ranges; - if (HYPERVISOR_dom0_op(&op) != 0) - break; - } -} - -static void __init init_table(void) -{ - int i, max; - - max = num_var_ranges; - if ((usage_table = kmalloc(max * sizeof *usage_table, GFP_KERNEL)) - == NULL) { - printk(KERN_ERR "mtrr: could not allocate\n"); - return; - } - for (i = 0; i < max; i++) - usage_table[i] = 0; -} - -int mtrr_add_page(unsigned long base, unsigned long size, - unsigned int type, char increment) -{ - int error; - dom0_op_t op; - - op.cmd = DOM0_ADD_MEMTYPE; - op.u.add_memtype.pfn = base; - op.u.add_memtype.nr_pfns = size; - op.u.add_memtype.type = type; - error = HYPERVISOR_dom0_op(&op); - if (error) { - BUG_ON(error > 0); - return error; - } - - if (increment) - ++usage_table[op.u.add_memtype.reg]; - - return op.u.add_memtype.reg; -} - -int -mtrr_add(unsigned long base, unsigned long size, unsigned int type, - char increment) -{ - if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) { - printk(KERN_WARNING "mtrr: size and base must be multiples of 4 kiB\n"); - printk(KERN_DEBUG "mtrr: size: 0x%lx base: 0x%lx\n", size, base); - return -EINVAL; - } - return mtrr_add_page(base >> PAGE_SHIFT, size >> PAGE_SHIFT, type, - increment); -} - -int mtrr_del_page(int reg, unsigned long base, unsigned long size) -{ - int i, max; - mtrr_type ltype; - unsigned long lbase; - unsigned int lsize; - int error = -EINVAL; - dom0_op_t op; - - max = num_var_ranges; - if (reg < 0) { - /* Search for existing MTRR */ - for (i = 0; i < max; ++i) { - mtrr_if->get(i, &lbase, &lsize, &ltype); - if (lbase == base && lsize == size) { - reg = i; - break; - } - } - if (reg < 0) { - printk(KERN_DEBUG "mtrr: no MTRR for %lx000,%lx000 found\n", base, - size); - goto out; - } - } - if (usage_table[reg] < 1) { - printk(KERN_WARNING "mtrr: reg: %d has count=0\n", reg); - goto out; - } - if (--usage_table[reg] < 1) { - op.cmd = DOM0_DEL_MEMTYPE; - op.u.del_memtype.handle = 0; - op.u.del_memtype.reg = reg; - error = HYPERVISOR_dom0_op(&op); - if (error) { - BUG_ON(error > 0); - goto out; - } - } - error = reg; - out: - return error; -} - -int -mtrr_del(int reg, unsigned long base, unsigned long size) -{ - if ((base & (PAGE_SIZE - 1)) || (size & (PAGE_SIZE - 1))) { - printk(KERN_INFO "mtrr: size and base must be multiples of 4 kiB\n"); - printk(KERN_DEBUG "mtrr: size: 0x%lx base: 0x%lx\n", size, base); - return -EINVAL; - } - return mtrr_del_page(reg, base >> PAGE_SHIFT, size >> PAGE_SHIFT); -} - -EXPORT_SYMBOL(mtrr_add); -EXPORT_SYMBOL(mtrr_del); - -static int __init mtrr_init(void) -{ - struct cpuinfo_x86 *c = &boot_cpu_data; - - if (!(xen_start_info->flags & SIF_PRIVILEGED)) - return -ENODEV; - - if ((!cpu_has(c, X86_FEATURE_MTRR)) && - (!cpu_has(c, X86_FEATURE_K6_MTRR)) && - (!cpu_has(c, X86_FEATURE_CYRIX_ARR)) && - (!cpu_has(c, X86_FEATURE_CENTAUR_MCR))) - return -ENODEV; - - set_num_var_ranges(); - init_table(); - - return 0; -} - -subsys_initcall(mtrr_init); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/entry.S --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/entry.S Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,842 +0,0 @@ -/* - * linux/arch/i386/entry.S - * - * Copyright (C) 1991, 1992 Linus Torvalds - */ - -/* - * entry.S contains the system-call and fault low-level handling routines. - * This also contains the timer-interrupt handler, as well as all interrupts - * and faults that can result in a task-switch. - * - * NOTE: This code handles signal-recognition, which happens every time - * after a timer-interrupt and after each system call. - * - * I changed all the .align's to 4 (16 byte alignment), as that's faster - * on a 486. - * - * Stack layout in 'ret_from_system_call': - * ptrace needs to have all regs on the stack. - * if the order here is changed, it needs to be - * updated in fork.c:copy_process, signal.c:do_signal, - * ptrace.c and ptrace.h - * - * 0(%esp) - %ebx - * 4(%esp) - %ecx - * 8(%esp) - %edx - * C(%esp) - %esi - * 10(%esp) - %edi - * 14(%esp) - %ebp - * 18(%esp) - %eax - * 1C(%esp) - %ds - * 20(%esp) - %es - * 24(%esp) - orig_eax - * 28(%esp) - %eip - * 2C(%esp) - %cs - * 30(%esp) - %eflags - * 34(%esp) - %oldesp - * 38(%esp) - %oldss - * - * "current" is in register %ebx during any slow entries. - */ - -#include <linux/config.h> -#include <linux/linkage.h> -#include <asm/thread_info.h> -#include <asm/errno.h> -#include <asm/segment.h> -#include <asm/smp.h> -#include <asm/page.h> -#include <asm/desc.h> -#include "irq_vectors.h" -#include <asm-xen/xen-public/xen.h> - -#define nr_syscalls ((syscall_table_size)/4) - -EBX = 0x00 -ECX = 0x04 -EDX = 0x08 -ESI = 0x0C -EDI = 0x10 -EBP = 0x14 -EAX = 0x18 -DS = 0x1C -ES = 0x20 -ORIG_EAX = 0x24 -EIP = 0x28 -CS = 0x2C -EVENT_MASK = 0x2E -EFLAGS = 0x30 -OLDESP = 0x34 -OLDSS = 0x38 - -CF_MASK = 0x00000001 -TF_MASK = 0x00000100 -IF_MASK = 0x00000200 -DF_MASK = 0x00000400 -NT_MASK = 0x00004000 -VM_MASK = 0x00020000 -/* Pseudo-eflags. */ -NMI_MASK = 0x80000000 - -/* Offsets into shared_info_t. */ -#define evtchn_upcall_pending /* 0 */ -#define evtchn_upcall_mask 1 - -#define sizeof_vcpu_shift 6 - -#ifdef CONFIG_SMP -#define preempt_disable(reg) incl TI_preempt_count(reg) -#define preempt_enable(reg) decl TI_preempt_count(reg) -#define XEN_GET_VCPU_INFO(reg) preempt_disable(%ebp) ; \ - movl TI_cpu(%ebp),reg ; \ - shl $sizeof_vcpu_shift,reg ; \ - addl HYPERVISOR_shared_info,reg -#define XEN_PUT_VCPU_INFO(reg) preempt_enable(%ebp) -#define XEN_PUT_VCPU_INFO_fixup .byte 0xff,0xff,0xff -#else -#define XEN_GET_VCPU_INFO(reg) movl HYPERVISOR_shared_info,reg -#define XEN_PUT_VCPU_INFO(reg) -#define XEN_PUT_VCPU_INFO_fixup -#endif - -#define XEN_LOCKED_BLOCK_EVENTS(reg) movb $1,evtchn_upcall_mask(reg) -#define XEN_LOCKED_UNBLOCK_EVENTS(reg) movb $0,evtchn_upcall_mask(reg) -#define XEN_BLOCK_EVENTS(reg) XEN_GET_VCPU_INFO(reg) ; \ - XEN_LOCKED_BLOCK_EVENTS(reg) ; \ - XEN_PUT_VCPU_INFO(reg) -#define XEN_UNBLOCK_EVENTS(reg) XEN_GET_VCPU_INFO(reg) ; \ - XEN_LOCKED_UNBLOCK_EVENTS(reg) ; \ - XEN_PUT_VCPU_INFO(reg) -#define XEN_TEST_PENDING(reg) testb $0xFF,evtchn_upcall_pending(reg) - -#ifdef CONFIG_PREEMPT -#define preempt_stop GET_THREAD_INFO(%ebp) ; \ - XEN_BLOCK_EVENTS(%esi) -#else -#define preempt_stop -#define resume_kernel restore_nocheck -#endif - -#define SAVE_ALL \ - cld; \ - pushl %es; \ - pushl %ds; \ - pushl %eax; \ - pushl %ebp; \ - pushl %edi; \ - pushl %esi; \ - pushl %edx; \ - pushl %ecx; \ - pushl %ebx; \ - movl $(__USER_DS), %edx; \ - movl %edx, %ds; \ - movl %edx, %es; - -#define RESTORE_INT_REGS \ - popl %ebx; \ - popl %ecx; \ - popl %edx; \ - popl %esi; \ - popl %edi; \ - popl %ebp; \ - popl %eax - -#define RESTORE_REGS \ - RESTORE_INT_REGS; \ -1: popl %ds; \ -2: popl %es; \ -.section .fixup,"ax"; \ -3: movl $0,(%esp); \ - jmp 1b; \ -4: movl $0,(%esp); \ - jmp 2b; \ -.previous; \ -.section __ex_table,"a";\ - .align 4; \ - .long 1b,3b; \ - .long 2b,4b; \ -.previous - - -#define RESTORE_ALL \ - RESTORE_REGS \ - addl $4, %esp; \ -1: iret; \ -.section .fixup,"ax"; \ -2: pushl $0; \ - pushl $do_iret_error; \ - jmp error_code; \ -.previous; \ -.section __ex_table,"a";\ - .align 4; \ - .long 1b,2b; \ -.previous - - -ENTRY(ret_from_fork) - pushl %eax - call schedule_tail - GET_THREAD_INFO(%ebp) - popl %eax - jmp syscall_exit - -/* - * Return to user mode is not as complex as all this looks, - * but we want the default path for a system call return to - * go as quickly as possible which is why some of this is - * less clear than it otherwise should be. - */ - - # userspace resumption stub bypassing syscall exit tracing - ALIGN -ret_from_exception: - preempt_stop -ret_from_intr: - GET_THREAD_INFO(%ebp) - movl EFLAGS(%esp), %eax # mix EFLAGS and CS - movb CS(%esp), %al - testl $(VM_MASK | 2), %eax - jz resume_kernel -ENTRY(resume_userspace) - XEN_BLOCK_EVENTS(%esi) # make sure we don't miss an interrupt - # setting need_resched or sigpending - # between sampling and the iret - movl TI_flags(%ebp), %ecx - andl $_TIF_WORK_MASK, %ecx # is there any work to be done on - # int/exception return? - jne work_pending - jmp restore_all - -#ifdef CONFIG_PREEMPT -ENTRY(resume_kernel) - XEN_BLOCK_EVENTS(%esi) - cmpl $0,TI_preempt_count(%ebp) # non-zero preempt_count ? - jnz restore_nocheck -need_resched: - movl TI_flags(%ebp), %ecx # need_resched set ? - testb $_TIF_NEED_RESCHED, %cl - jz restore_all - testb $0xFF,EVENT_MASK(%esp) # interrupts off (exception path) ? - jnz restore_all - call preempt_schedule_irq - jmp need_resched -#endif - -/* SYSENTER_RETURN points to after the "sysenter" instruction in - the vsyscall page. See vsyscall-sysentry.S, which defines the symbol. */ - - # sysenter call handler stub -ENTRY(sysenter_entry) - movl TSS_sysenter_esp0(%esp),%esp -sysenter_past_esp: - sti - pushl $(__USER_DS) - pushl %ebp - pushfl - pushl $(__USER_CS) - pushl $SYSENTER_RETURN - -/* - * Load the potential sixth argument from user stack. - * Careful about security. - */ - cmpl $__PAGE_OFFSET-3,%ebp - jae syscall_fault -1: movl (%ebp),%ebp -.section __ex_table,"a" - .align 4 - .long 1b,syscall_fault -.previous - - pushl %eax - SAVE_ALL - GET_THREAD_INFO(%ebp) - - /* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */ - testw $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),TI_flags(%ebp) - jnz syscall_trace_entry - cmpl $(nr_syscalls), %eax - jae syscall_badsys - call *sys_call_table(,%eax,4) - movl %eax,EAX(%esp) - cli - movl TI_flags(%ebp), %ecx - testw $_TIF_ALLWORK_MASK, %cx - jne syscall_exit_work -/* if something modifies registers it must also disable sysexit */ - movl EIP(%esp), %edx - movl OLDESP(%esp), %ecx - xorl %ebp,%ebp - sti - sysexit - - - # system call handler stub -ENTRY(system_call) - pushl %eax # save orig_eax - SAVE_ALL - GET_THREAD_INFO(%ebp) - # system call tracing in operation - /* Note, _TIF_SECCOMP is bit number 8, and so it needs testw and not testb */ - testw $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),TI_flags(%ebp) - jnz syscall_trace_entry - cmpl $(nr_syscalls), %eax - jae syscall_badsys -syscall_call: - call *sys_call_table(,%eax,4) - movl %eax,EAX(%esp) # store the return value -syscall_exit: - XEN_BLOCK_EVENTS(%esi) # make sure we don't miss an interrupt - # setting need_resched or sigpending - # between sampling and the iret - movl TI_flags(%ebp), %ecx - testw $_TIF_ALLWORK_MASK, %cx # current->work - jne syscall_exit_work - -restore_all: -#if 0 /* XEN */ - movl EFLAGS(%esp), %eax # mix EFLAGS, SS and CS - # Warning: OLDSS(%esp) contains the wrong/random values if we - # are returning to the kernel. - # See comments in process.c:copy_thread() for details. - movb OLDSS(%esp), %ah - movb CS(%esp), %al - andl $(VM_MASK | (4 << 8) | 3), %eax - cmpl $((4 << 8) | 3), %eax - je ldt_ss # returning to user-space with LDT SS -#endif /* XEN */ -restore_nocheck: - testl $(VM_MASK|NMI_MASK), EFLAGS(%esp) - jnz hypervisor_iret - movb EVENT_MASK(%esp), %al - notb %al # %al == ~saved_mask - XEN_GET_VCPU_INFO(%esi) - andb evtchn_upcall_mask(%esi),%al - andb $1,%al # %al == mask & ~saved_mask - jnz restore_all_enable_events # != 0 => reenable event delivery - XEN_PUT_VCPU_INFO(%esi) - RESTORE_REGS - addl $4, %esp -1: iret -.section .fixup,"ax" -iret_exc: - pushl $0 # no error code - pushl $do_iret_error - jmp error_code -.previous -.section __ex_table,"a" - .align 4 - .long 1b,iret_exc -.previous - -hypervisor_iret: - andl $~NMI_MASK, EFLAGS(%esp) - RESTORE_REGS - addl $4, %esp - jmp hypercall_page + (__HYPERVISOR_iret * 32) - -#if 0 /* XEN */ -ldt_ss: - larl OLDSS(%esp), %eax - jnz restore_nocheck - testl $0x00400000, %eax # returning to 32bit stack? - jnz restore_nocheck # allright, normal return - /* If returning to userspace with 16bit stack, - * try to fix the higher word of ESP, as the CPU - * won't restore it. - * This is an "official" bug of all the x86-compatible - * CPUs, which we can try to work around to make - * dosemu and wine happy. */ - subl $8, %esp # reserve space for switch16 pointer - cli - movl %esp, %eax - /* Set up the 16bit stack frame with switch32 pointer on top, - * and a switch16 pointer on top of the current frame. */ - call setup_x86_bogus_stack - RESTORE_REGS - lss 20+4(%esp), %esp # switch to 16bit stack -1: iret -.section __ex_table,"a" - .align 4 - .long 1b,iret_exc -.previous -#endif /* XEN */ - - # perform work that needs to be done immediately before resumption - ALIGN -work_pending: - testb $_TIF_NEED_RESCHED, %cl - jz work_notifysig -work_resched: - call schedule - XEN_BLOCK_EVENTS(%esi) # make sure we don't miss an interrupt - # setting need_resched or sigpending - # between sampling and the iret - movl TI_flags(%ebp), %ecx - andl $_TIF_WORK_MASK, %ecx # is there any work to be done other - # than syscall tracing? - jz restore_all - testb $_TIF_NEED_RESCHED, %cl - jnz work_resched - -work_notifysig: # deal with pending signals and - # notify-resume requests - testl $VM_MASK, EFLAGS(%esp) - movl %esp, %eax - jne work_notifysig_v86 # returning to kernel-space or - # vm86-space - xorl %edx, %edx - call do_notify_resume - jmp restore_all - - ALIGN -work_notifysig_v86: - pushl %ecx # save ti_flags for do_notify_resume - call save_v86_state # %eax contains pt_regs pointer - popl %ecx - movl %eax, %esp - xorl %edx, %edx - call do_notify_resume - jmp restore_all - - # perform syscall exit tracing - ALIGN -syscall_trace_entry: - movl $-ENOSYS,EAX(%esp) - movl %esp, %eax - xorl %edx,%edx - call do_syscall_trace - movl ORIG_EAX(%esp), %eax - cmpl $(nr_syscalls), %eax - jnae syscall_call - jmp syscall_exit - - # perform syscall exit tracing - ALIGN -syscall_exit_work: - testb $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP), %cl - jz work_pending - XEN_UNBLOCK_EVENTS(%esi) # could let do_syscall_trace() call - # schedule() instead - movl %esp, %eax - movl $1, %edx - call do_syscall_trace - jmp resume_userspace - - ALIGN -syscall_fault: - pushl %eax # save orig_eax - SAVE_ALL - GET_THREAD_INFO(%ebp) - movl $-EFAULT,EAX(%esp) - jmp resume_userspace - - ALIGN -syscall_badsys: - movl $-ENOSYS,EAX(%esp) - jmp resume_userspace - -#if 0 /* XEN */ -#define FIXUP_ESPFIX_STACK \ - movl %esp, %eax; \ - /* switch to 32bit stack using the pointer on top of 16bit stack */ \ - lss %ss:CPU_16BIT_STACK_SIZE-8, %esp; \ - /* copy data from 16bit stack to 32bit stack */ \ - call fixup_x86_bogus_stack; \ - /* put ESP to the proper location */ \ - movl %eax, %esp; -#define UNWIND_ESPFIX_STACK \ - pushl %eax; \ - movl %ss, %eax; \ - /* see if on 16bit stack */ \ - cmpw $__ESPFIX_SS, %ax; \ - jne 28f; \ - movl $__KERNEL_DS, %edx; \ - movl %edx, %ds; \ - movl %edx, %es; \ - /* switch to 32bit stack */ \ - FIXUP_ESPFIX_STACK \ -28: popl %eax; - -/* - * Build the entry stubs and pointer table with - * some assembler magic. - */ -.data -ENTRY(interrupt) -.text - -vector=0 -ENTRY(irq_entries_start) -.rept NR_IRQS - ALIGN -1: pushl $vector-256 - jmp common_interrupt -.data - .long 1b -.text -vector=vector+1 -.endr - - ALIGN -common_interrupt: - SAVE_ALL - movl %esp,%eax - call do_IRQ - jmp ret_from_intr - -#define BUILD_INTERRUPT(name, nr) \ -ENTRY(name) \ - pushl $nr-256; \ - SAVE_ALL \ - movl %esp,%eax; \ - call smp_/**/name; \ - jmp ret_from_intr; - -/* The include is where all of the SMP etc. interrupts come from */ -#include "entry_arch.h" -#endif /* XEN */ - -ENTRY(divide_error) - pushl $0 # no error code - pushl $do_divide_error - ALIGN -error_code: - pushl %ds - pushl %eax - xorl %eax, %eax - pushl %ebp - pushl %edi - pushl %esi - pushl %edx - decl %eax # eax = -1 - pushl %ecx - pushl %ebx - cld - pushl %es -# UNWIND_ESPFIX_STACK - popl %ecx - movl ES(%esp), %edi # get the function address - movl ORIG_EAX(%esp), %edx # get the error code - movl %eax, ORIG_EAX(%esp) - movl %ecx, ES(%esp) - movl $(__USER_DS), %ecx - movl %ecx, %ds - movl %ecx, %es - movl %esp,%eax # pt_regs pointer - call *%edi - jmp ret_from_exception - -# A note on the "critical region" in our callback handler. -# We want to avoid stacking callback handlers due to events occurring -# during handling of the last event. To do this, we keep events disabled -# until we've done all processing. HOWEVER, we must enable events before -# popping the stack frame (can't be done atomically) and so it would still -# be possible to get enough handler activations to overflow the stack. -# Although unlikely, bugs of that kind are hard to track down, so we'd -# like to avoid the possibility. -# So, on entry to the handler we detect whether we interrupted an -# existing activation in its critical region -- if so, we pop the current -# activation and restart the handler using the previous one. -ENTRY(hypervisor_callback) - pushl %eax - SAVE_ALL - movl EIP(%esp),%eax - cmpl $scrit,%eax - jb 11f - cmpl $ecrit,%eax - jb critical_region_fixup -11: push %esp - call evtchn_do_upcall - add $4,%esp - jmp ret_from_intr - - ALIGN -restore_all_enable_events: - XEN_LOCKED_UNBLOCK_EVENTS(%esi) -scrit: /**** START OF CRITICAL REGION ****/ - XEN_TEST_PENDING(%esi) - jnz 14f # process more events if necessary... - XEN_PUT_VCPU_INFO(%esi) - RESTORE_ALL -14: XEN_LOCKED_BLOCK_EVENTS(%esi) - XEN_PUT_VCPU_INFO(%esi) - jmp 11b -ecrit: /**** END OF CRITICAL REGION ****/ -# [How we do the fixup]. We want to merge the current stack frame with the -# just-interrupted frame. How we do this depends on where in the critical -# region the interrupted handler was executing, and so how many saved -# registers are in each frame. We do this quickly using the lookup table -# 'critical_fixup_table'. For each byte offset in the critical region, it -# provides the number of bytes which have already been popped from the -# interrupted stack frame. -critical_region_fixup: - addl $critical_fixup_table-scrit,%eax - movzbl (%eax),%eax # %eax contains num bytes popped - cmpb $0xff,%al # 0xff => vcpu_info critical region - jne 15f - GET_THREAD_INFO(%ebp) - XEN_PUT_VCPU_INFO(%esi) # abort vcpu_info critical region - xorl %eax,%eax -15: mov %esp,%esi - add %eax,%esi # %esi points at end of src region - mov %esp,%edi - add $0x34,%edi # %edi points at end of dst region - mov %eax,%ecx - shr $2,%ecx # convert words to bytes - je 17f # skip loop if nothing to copy -16: subl $4,%esi # pre-decrementing copy loop - subl $4,%edi - movl (%esi),%eax - movl %eax,(%edi) - loop 16b -17: movl %edi,%esp # final %edi is top of merged stack - jmp 11b - -critical_fixup_table: - .byte 0xff,0xff,0xff # testb $0xff,(%esi) = XEN_TEST_PENDING - .byte 0xff,0xff # jnz 14f - XEN_PUT_VCPU_INFO_fixup - .byte 0x00 # pop %ebx - .byte 0x04 # pop %ecx - .byte 0x08 # pop %edx - .byte 0x0c # pop %esi - .byte 0x10 # pop %edi - .byte 0x14 # pop %ebp - .byte 0x18 # pop %eax - .byte 0x1c # pop %ds - .byte 0x20 # pop %es - .byte 0x24,0x24,0x24 # add $4,%esp - .byte 0x28 # iret - .byte 0xff,0xff,0xff,0xff # movb $1,1(%esi) - XEN_PUT_VCPU_INFO_fixup - .byte 0x00,0x00 # jmp 11b - -# Hypervisor uses this for application faults while it executes. -ENTRY(failsafe_callback) -1: popl %ds -2: popl %es -3: popl %fs -4: popl %gs - subl $4,%esp - SAVE_ALL - jmp ret_from_exception -.section .fixup,"ax"; \ -6: movl $0,(%esp); \ - jmp 1b; \ -7: movl $0,(%esp); \ - jmp 2b; \ -8: movl $0,(%esp); \ - jmp 3b; \ -9: movl $0,(%esp); \ - jmp 4b; \ -.previous; \ -.section __ex_table,"a";\ - .align 4; \ - .long 1b,6b; \ - .long 2b,7b; \ - .long 3b,8b; \ - .long 4b,9b; \ -.previous - -ENTRY(coprocessor_error) - pushl $0 - pushl $do_coprocessor_error - jmp error_code - -ENTRY(simd_coprocessor_error) - pushl $0 - pushl $do_simd_coprocessor_error - jmp error_code - -ENTRY(device_not_available) - pushl $-1 # mark this as an int - SAVE_ALL - #preempt_stop /* This is already an interrupt gate on Xen. */ - call math_state_restore - jmp ret_from_exception - -/* - * Debug traps and NMI can happen at the one SYSENTER instruction - * that sets up the real kernel stack. Check here, since we can't - * allow the wrong stack to be used. - * - * "TSS_sysenter_esp0+12" is because the NMI/debug handler will have - * already pushed 3 words if it hits on the sysenter instruction: - * eflags, cs and eip. - * - * We just load the right stack, and push the three (known) values - * by hand onto the new stack - while updating the return eip past - * the instruction that would have done it for sysenter. - */ -#define FIX_STACK(offset, ok, label) \ - cmpw $__KERNEL_CS,4(%esp); \ - jne ok; \ -label: \ - movl TSS_sysenter_esp0+offset(%esp),%esp; \ - pushfl; \ - pushl $__KERNEL_CS; \ - pushl $sysenter_past_esp - -ENTRY(debug) - cmpl $sysenter_entry,(%esp) - jne debug_stack_correct - FIX_STACK(12, debug_stack_correct, debug_esp_fix_insn) -debug_stack_correct: - pushl $-1 # mark this as an int - SAVE_ALL - xorl %edx,%edx # error code 0 - movl %esp,%eax # pt_regs pointer - call do_debug - jmp ret_from_exception - -ENTRY(nmi) - pushl %eax - SAVE_ALL - xorl %edx,%edx # zero error code - movl %esp,%eax # pt_regs pointer - call do_nmi - orl $NMI_MASK, EFLAGS(%esp) - jmp restore_all - -#if 0 /* XEN */ -/* - * NMI is doubly nasty. It can happen _while_ we're handling - * a debug fault, and the debug fault hasn't yet been able to - * clear up the stack. So we first check whether we got an - * NMI on the sysenter entry path, but after that we need to - * check whether we got an NMI on the debug path where the debug - * fault happened on the sysenter path. - */ -ENTRY(nmi) - pushl %eax - movl %ss, %eax - cmpw $__ESPFIX_SS, %ax - popl %eax - je nmi_16bit_stack - cmpl $sysenter_entry,(%esp) - je nmi_stack_fixup - pushl %eax - movl %esp,%eax - /* Do not access memory above the end of our stack page, - * it might not exist. - */ - andl $(THREAD_SIZE-1),%eax - cmpl $(THREAD_SIZE-20),%eax - popl %eax - jae nmi_stack_correct - cmpl $sysenter_entry,12(%esp) - je nmi_debug_stack_check -nmi_stack_correct: - pushl %eax - SAVE_ALL - xorl %edx,%edx # zero error code - movl %esp,%eax # pt_regs pointer - call do_nmi - jmp restore_all - -nmi_stack_fixup: - FIX_STACK(12,nmi_stack_correct, 1) - jmp nmi_stack_correct -nmi_debug_stack_check: - cmpw $__KERNEL_CS,16(%esp) - jne nmi_stack_correct - cmpl $debug - 1,(%esp) - jle nmi_stack_correct - cmpl $debug_esp_fix_insn,(%esp) - jle nmi_debug_stack_fixup -nmi_debug_stack_fixup: - FIX_STACK(24,nmi_stack_correct, 1) - jmp nmi_stack_correct - -nmi_16bit_stack: - /* create the pointer to lss back */ - pushl %ss - pushl %esp - movzwl %sp, %esp - addw $4, (%esp) - /* copy the iret frame of 12 bytes */ - .rept 3 - pushl 16(%esp) - .endr - pushl %eax - SAVE_ALL - FIXUP_ESPFIX_STACK # %eax == %esp - xorl %edx,%edx # zero error code - call do_nmi - RESTORE_REGS - lss 12+4(%esp), %esp # back to 16bit stack -1: iret -.section __ex_table,"a" - .align 4 - .long 1b,iret_exc -.previous -#endif /* XEN */ - -ENTRY(int3) - pushl $-1 # mark this as an int - SAVE_ALL - xorl %edx,%edx # zero error code - movl %esp,%eax # pt_regs pointer - call do_int3 - jmp ret_from_exception - -ENTRY(overflow) - pushl $0 - pushl $do_overflow - jmp error_code - -ENTRY(bounds) - pushl $0 - pushl $do_bounds - jmp error_code - -ENTRY(invalid_op) - pushl $0 - pushl $do_invalid_op - jmp error_code - -ENTRY(coprocessor_segment_overrun) - pushl $0 - pushl $do_coprocessor_segment_overrun - jmp error_code - -ENTRY(invalid_TSS) - pushl $do_invalid_TSS - jmp error_code - -ENTRY(segment_not_present) - pushl $do_segment_not_present - jmp error_code - -ENTRY(stack_segment) - pushl $do_stack_segment - jmp error_code - -ENTRY(general_protection) - pushl $do_general_protection - jmp error_code - -ENTRY(alignment_check) - pushl $do_alignment_check - jmp error_code - -ENTRY(page_fault) - pushl $do_page_fault - jmp error_code - -#ifdef CONFIG_X86_MCE -ENTRY(machine_check) - pushl $0 - pushl machine_check_vector - jmp error_code -#endif - -ENTRY(fixup_4gb_segment) - pushl $do_fixup_4gb_segment - jmp error_code - -#include "syscall_table.S" - -syscall_table_size=(.-sys_call_table) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/fixup.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/fixup.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,95 +0,0 @@ -/****************************************************************************** - * fixup.c - * - * Binary-rewriting of certain IA32 instructions, on notification by Xen. - * Used to avoid repeated slow emulation of common instructions used by the - * user-space TLS (Thread-Local Storage) libraries. - * - * **** NOTE **** - * Issues with the binary rewriting have caused it to be removed. Instead - * we rely on Xen's emulator to boot the kernel, and then print a banner - * message recommending that the user disables /lib/tls. - * - * Copyright (c) 2004, K A Fraser - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - */ - -#include <linux/config.h> -#include <linux/init.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/kernel.h> -#include <linux/delay.h> -#include <linux/version.h> - -#define DP(_f, _args...) printk(KERN_ALERT " " _f "\n" , ## _args ) - -fastcall void do_fixup_4gb_segment(struct pt_regs *regs, long error_code) -{ - static unsigned long printed = 0; - char info[100]; - int i; - - if (test_and_set_bit(0, &printed)) - return; - - HYPERVISOR_vm_assist( - VMASST_CMD_disable, VMASST_TYPE_4gb_segments_notify); - - sprintf(info, "%s (pid=%d)", current->comm, current->tgid); - - - DP(""); - DP("***************************************************************"); - DP("***************************************************************"); - DP("** WARNING: Currently emulating unsupported memory accesses **"); - DP("** in /lib/tls glibc libraries. The emulation is **"); - DP("** slow. To ensure full performance you should **"); - DP("** install a 'xen-friendly' (nosegneg) version of **"); - DP("** the library, or disable tls support by executing **"); - DP("** the following as root: **"); - DP("** mv /lib/tls /lib/tls.disabled **"); - DP("** Offending process: %-38.38s **", info); - DP("***************************************************************"); - DP("***************************************************************"); - DP(""); - - for (i = 5; i > 0; i--) { - printk("Pausing... %d", i); - mdelay(1000); - printk("\b\b\b\b\b\b\b\b\b\b\b\b"); - } - - printk("Continuing...\n\n"); -} - -static int __init fixup_init(void) -{ - HYPERVISOR_vm_assist( - VMASST_CMD_enable, VMASST_TYPE_4gb_segments_notify); - return 0; -} -__initcall(fixup_init); - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/head.S --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/head.S Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,198 +0,0 @@ - -#include <linux/config.h> - -.section __xen_guest - .ascii "GUEST_OS=linux,GUEST_VER=2.6" - .ascii ",XEN_VER=xen-3.0" - .ascii ",VIRT_BASE=0xC0000000" - .ascii ",HYPERCALL_PAGE=0x104" /* __pa(hypercall_page) >> 12 */ -#ifdef CONFIG_X86_PAE - .ascii ",PAE=yes" -#else - .ascii ",PAE=no" -#endif -#ifdef CONFIG_XEN_SHADOW_MODE - .ascii ",SHADOW=translate" -#endif - .ascii ",LOADER=generic" - .byte 0 - -.text -#include <linux/threads.h> -#include <linux/linkage.h> -#include <asm/segment.h> -#include <asm/thread_info.h> -#include <asm/asm_offsets.h> -#include <asm-xen/xen-public/arch-x86_32.h> - -/* - * References to members of the new_cpu_data structure. - */ - -#define X86 new_cpu_data+CPUINFO_x86 -#define X86_VENDOR new_cpu_data+CPUINFO_x86_vendor -#define X86_MODEL new_cpu_data+CPUINFO_x86_model -#define X86_MASK new_cpu_data+CPUINFO_x86_mask -#define X86_HARD_MATH new_cpu_data+CPUINFO_hard_math -#define X86_CPUID new_cpu_data+CPUINFO_cpuid_level -#define X86_CAPABILITY new_cpu_data+CPUINFO_x86_capability -#define X86_VENDOR_ID new_cpu_data+CPUINFO_x86_vendor_id - -ENTRY(startup_32) - movl %esi,xen_start_info - -#if 0 -ENTRY(startup_32_smp) -#endif /* CONFIG_SMP */ - - cld - - /* Set up the stack pointer */ - lss stack_start,%esp - -checkCPUtype: - - /* get vendor info */ - xorl %eax,%eax # call CPUID with 0 -> return vendor ID - cpuid - movl %eax,X86_CPUID # save CPUID level - movl %ebx,X86_VENDOR_ID # lo 4 chars - movl %edx,X86_VENDOR_ID+4 # next 4 chars - movl %ecx,X86_VENDOR_ID+8 # last 4 chars - - movl $1,%eax # Use the CPUID instruction to get CPU type - cpuid - movb %al,%cl # save reg for future use - andb $0x0f,%ah # mask processor family - movb %ah,X86 - andb $0xf0,%al # mask model - shrb $4,%al - movb %al,X86_MODEL - andb $0x0f,%cl # mask mask revision - movb %cl,X86_MASK - movl %edx,X86_CAPABILITY - - incb ready - - xorl %eax,%eax # Clear FS/GS and LDT - movl %eax,%fs - movl %eax,%gs - cld # gcc2 wants the direction flag cleared at all times - -#if 0 - movb ready, %cl - cmpb $1,%cl - je 1f # the first CPU calls start_kernel - # all other CPUs call initialize_secondary - call initialize_secondary - jmp L6 -1: -#endif /* CONFIG_SMP */ - call start_kernel -L6: - jmp L6 # main should never return here, but - # just in case, we know what happens. - -ENTRY(lgdt_finish) - movl $(__KERNEL_DS),%eax # reload all the segment registers - movw %ax,%ss # after changing gdt. - - movl $(__USER_DS),%eax # DS/ES contains default USER segment - movw %ax,%ds - movw %ax,%es - - popl %eax # reload CS by intersegment return - pushl $(__KERNEL_CS) - pushl %eax - lret - -ENTRY(stack_start) - .long init_thread_union+THREAD_SIZE - .long __BOOT_DS - -ready: .byte 0 - -.globl idt_descr -.globl cpu_gdt_descr - - ALIGN - .word 0 # 32-bit align idt_desc.address -idt_descr: - .word IDT_ENTRIES*8-1 # idt contains 256 entries - .long idt_table - -# boot GDT descriptor (later on used by CPU#0): - .word 0 # 32 bit align gdt_desc.address -cpu_gdt_descr: - .word GDT_SIZE - .long cpu_gdt_table - - .fill NR_CPUS-1,8,0 # space for the other GDT descriptors - -.org 0x1000 -ENTRY(empty_zero_page) - -.org 0x2000 -ENTRY(cpu_gdt_table) - .quad 0x0000000000000000 /* NULL descriptor */ - .quad 0x0000000000000000 /* 0x0b reserved */ - .quad 0x0000000000000000 /* 0x13 reserved */ - .quad 0x0000000000000000 /* 0x1b reserved */ - .quad 0x0000000000000000 /* 0x20 unused */ - .quad 0x0000000000000000 /* 0x28 unused */ - .quad 0x0000000000000000 /* 0x33 TLS entry 1 */ - .quad 0x0000000000000000 /* 0x3b TLS entry 2 */ - .quad 0x0000000000000000 /* 0x43 TLS entry 3 */ - .quad 0x0000000000000000 /* 0x4b reserved */ - .quad 0x0000000000000000 /* 0x53 reserved */ - .quad 0x0000000000000000 /* 0x5b reserved */ - -#ifdef CONFIG_X86_PAE - .quad 0x00cfbb00000067ff /* 0x60 kernel 4GB code at 0x00000000 */ - .quad 0x00cfb300000067ff /* 0x68 kernel 4GB data at 0x00000000 */ - .quad 0x00cffb00000067ff /* 0x73 user 4GB code at 0x00000000 */ - .quad 0x00cff300000067ff /* 0x7b user 4GB data at 0x00000000 */ -#else - .quad 0x00cfbb000000c3ff /* 0x60 kernel 4GB code at 0x00000000 */ - .quad 0x00cfb3000000c3ff /* 0x68 kernel 4GB data at 0x00000000 */ - .quad 0x00cffb000000c3ff /* 0x73 user 4GB code at 0x00000000 */ - .quad 0x00cff3000000c3ff /* 0x7b user 4GB data at 0x00000000 */ -#endif - - .quad 0x0000000000000000 /* 0x80 TSS descriptor */ - .quad 0x0000000000000000 /* 0x88 LDT descriptor */ - - /* Segments used for calling PnP BIOS */ - .quad 0x0000000000000000 /* 0x90 32-bit code */ - .quad 0x0000000000000000 /* 0x98 16-bit code */ - .quad 0x0000000000000000 /* 0xa0 16-bit data */ - .quad 0x0000000000000000 /* 0xa8 16-bit data */ - .quad 0x0000000000000000 /* 0xb0 16-bit data */ - /* - * The APM segments have byte granularity and their bases - * and limits are set at run time. - */ - .quad 0x0000000000000000 /* 0xb8 APM CS code */ - .quad 0x0000000000000000 /* 0xc0 APM CS 16 code (16 bit) */ - .quad 0x0000000000000000 /* 0xc8 APM DS data */ - - .quad 0x0000000000000000 /* 0xd0 - ESPFIX 16-bit SS */ - .quad 0x0000000000000000 /* 0xd8 - unused */ - .quad 0x0000000000000000 /* 0xe0 - unused */ - .quad 0x0000000000000000 /* 0xe8 - unused */ - .quad 0x0000000000000000 /* 0xf0 - unused */ - .quad 0x0000000000000000 /* 0xf8 - GDT entry 31: double-fault TSS */ - .fill GDT_ENTRIES-32,8,0 - -.org 0x3000 -ENTRY(default_ldt) - -.org 0x4000 -ENTRY(hypercall_page) - -.org 0x5000 -/* - * Real beginning of normal "text" segment - */ -ENTRY(stext) -ENTRY(_stext) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/i386_ksyms.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/i386_ksyms.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,185 +0,0 @@ -#include <linux/config.h> -#include <linux/module.h> -#include <linux/smp.h> -#include <linux/user.h> -#include <linux/elfcore.h> -#include <linux/mca.h> -#include <linux/sched.h> -#include <linux/in6.h> -#include <linux/interrupt.h> -#include <linux/smp_lock.h> -#include <linux/pm.h> -#include <linux/pci.h> -#include <linux/apm_bios.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/tty.h> -#include <linux/highmem.h> -#include <linux/time.h> - -#include <asm/semaphore.h> -#include <asm/processor.h> -#include <asm/i387.h> -#include <asm/uaccess.h> -#include <asm/checksum.h> -#include <asm/io.h> -#include <asm/delay.h> -#include <asm/irq.h> -#include <asm/mmx.h> -#include <asm/desc.h> -#include <asm/pgtable.h> -#include <asm/tlbflush.h> -#include <asm/nmi.h> -#include <asm/ist.h> -#include <asm/kdebug.h> - -extern void dump_thread(struct pt_regs *, struct user *); -extern spinlock_t rtc_lock; - -/* This is definitely a GPL-only symbol */ -EXPORT_SYMBOL_GPL(cpu_gdt_table); - -#if defined(CONFIG_APM_MODULE) -extern void machine_real_restart(unsigned char *, int); -EXPORT_SYMBOL(machine_real_restart); -extern void default_idle(void); -EXPORT_SYMBOL(default_idle); -#endif - -#ifdef CONFIG_SMP -extern void FASTCALL( __write_lock_failed(rwlock_t *rw)); -extern void FASTCALL( __read_lock_failed(rwlock_t *rw)); -#endif - -#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_HD) || defined(CONFIG_BLK_DEV_IDE_MODULE) || defined(CONFIG_BLK_DEV_HD_MODULE) -extern struct drive_info_struct drive_info; -EXPORT_SYMBOL(drive_info); -#endif - -extern unsigned long cpu_khz; -extern unsigned long get_cmos_time(void); - -/* platform dependent support */ -EXPORT_SYMBOL(boot_cpu_data); -#ifdef CONFIG_DISCONTIGMEM -EXPORT_SYMBOL(node_data); -EXPORT_SYMBOL(physnode_map); -#endif -#ifdef CONFIG_X86_NUMAQ -EXPORT_SYMBOL(xquad_portio); -#endif -EXPORT_SYMBOL(dump_thread); -EXPORT_SYMBOL(dump_fpu); -EXPORT_SYMBOL_GPL(kernel_fpu_begin); -EXPORT_SYMBOL(__ioremap); -EXPORT_SYMBOL(ioremap_nocache); -EXPORT_SYMBOL(iounmap); -EXPORT_SYMBOL(kernel_thread); -EXPORT_SYMBOL(pm_idle); -EXPORT_SYMBOL(pm_power_off); -EXPORT_SYMBOL(get_cmos_time); -EXPORT_SYMBOL(cpu_khz); -EXPORT_SYMBOL(apm_info); - -EXPORT_SYMBOL(__down_failed); -EXPORT_SYMBOL(__down_failed_interruptible); -EXPORT_SYMBOL(__down_failed_trylock); -EXPORT_SYMBOL(__up_wakeup); -/* Networking helper routines. */ -EXPORT_SYMBOL(csum_partial_copy_generic); -/* Delay loops */ -EXPORT_SYMBOL(__ndelay); -EXPORT_SYMBOL(__udelay); -EXPORT_SYMBOL(__delay); -EXPORT_SYMBOL(__const_udelay); - -EXPORT_SYMBOL(__get_user_1); -EXPORT_SYMBOL(__get_user_2); -EXPORT_SYMBOL(__get_user_4); - -EXPORT_SYMBOL(__put_user_1); -EXPORT_SYMBOL(__put_user_2); -EXPORT_SYMBOL(__put_user_4); -EXPORT_SYMBOL(__put_user_8); - -EXPORT_SYMBOL(strpbrk); -EXPORT_SYMBOL(strstr); - -EXPORT_SYMBOL(strncpy_from_user); -EXPORT_SYMBOL(__strncpy_from_user); -EXPORT_SYMBOL(clear_user); -EXPORT_SYMBOL(__clear_user); -EXPORT_SYMBOL(__copy_from_user_ll); -EXPORT_SYMBOL(__copy_to_user_ll); -EXPORT_SYMBOL(strnlen_user); - -#ifdef CONFIG_PCI -EXPORT_SYMBOL(pci_mem_start); -#endif - -#ifdef CONFIG_PCI_BIOS -EXPORT_SYMBOL(pcibios_set_irq_routing); -EXPORT_SYMBOL(pcibios_get_irq_routing_table); -#endif - -#ifdef CONFIG_X86_USE_3DNOW -EXPORT_SYMBOL(_mmx_memcpy); -EXPORT_SYMBOL(mmx_clear_page); -EXPORT_SYMBOL(mmx_copy_page); -#endif - -#ifdef CONFIG_X86_HT -EXPORT_SYMBOL(smp_num_siblings); -EXPORT_SYMBOL(cpu_sibling_map); -#endif - -#ifdef CONFIG_SMP -EXPORT_SYMBOL(__write_lock_failed); -EXPORT_SYMBOL(__read_lock_failed); - -/* Global SMP stuff */ -EXPORT_SYMBOL(smp_call_function); - -/* TLB flushing */ -EXPORT_SYMBOL(flush_tlb_page); -#endif - -#ifdef CONFIG_X86_IO_APIC -EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector); -#endif - -#ifdef CONFIG_MCA -EXPORT_SYMBOL(machine_id); -#endif - -#ifdef CONFIG_VT -EXPORT_SYMBOL(screen_info); -#endif - -EXPORT_SYMBOL(get_wchan); - -EXPORT_SYMBOL(rtc_lock); - -EXPORT_SYMBOL_GPL(set_nmi_callback); -EXPORT_SYMBOL_GPL(unset_nmi_callback); - -EXPORT_SYMBOL(register_die_notifier); -#ifdef CONFIG_HAVE_DEC_LOCK -EXPORT_SYMBOL(_atomic_dec_and_lock); -#endif - -EXPORT_SYMBOL(__PAGE_KERNEL); - -#ifdef CONFIG_HIGHMEM -EXPORT_SYMBOL(kmap); -EXPORT_SYMBOL(kunmap); -EXPORT_SYMBOL(kmap_atomic); -EXPORT_SYMBOL(kunmap_atomic); -EXPORT_SYMBOL(kmap_atomic_to_page); -#endif - -#if defined(CONFIG_X86_SPEEDSTEP_SMI) || defined(CONFIG_X86_SPEEDSTEP_SMI_MODULE) -EXPORT_SYMBOL(ist_info); -#endif - -EXPORT_SYMBOL(csum_partial); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/init_task.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/init_task.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,49 +0,0 @@ -#include <linux/mm.h> -#include <linux/module.h> -#include <linux/sched.h> -#include <linux/init.h> -#include <linux/init_task.h> -#include <linux/fs.h> -#include <linux/mqueue.h> - -#include <asm/uaccess.h> -#include <asm/pgtable.h> -#include <asm/desc.h> - -static struct fs_struct init_fs = INIT_FS; -static struct files_struct init_files = INIT_FILES; -static struct signal_struct init_signals = INIT_SIGNALS(init_signals); -static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); - -#define swapper_pg_dir ((pgd_t *)NULL) -struct mm_struct init_mm = INIT_MM(init_mm); -#undef swapper_pg_dir - -EXPORT_SYMBOL(init_mm); - -/* - * Initial thread structure. - * - * We need to make sure that this is THREAD_SIZE aligned due to the - * way process stacks are handled. This is done by having a special - * "init_task" linker map entry.. - */ -union thread_union init_thread_union - __attribute__((__section__(".data.init_task"))) = - { INIT_THREAD_INFO(init_task) }; - -/* - * Initial task structure. - * - * All other task structs will be allocated on slabs in fork.c - */ -struct task_struct init_task = INIT_TASK(init_task); - -EXPORT_SYMBOL(init_task); - -/* - * per-CPU TSS segments. Threads are completely 'soft' on Linux, - * no more per-task TSS's. - */ -DEFINE_PER_CPU(struct tss_struct, init_tss) ____cacheline_maxaligned_in_smp = INIT_TSS; - diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/io_apic.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/io_apic.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,2611 +0,0 @@ -/* - * Intel IO-APIC support for multi-Pentium hosts. - * - * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar, Hajnalka Szabo - * - * Many thanks to Stig Venaas for trying out countless experimental - * patches and reporting/debugging problems patiently! - * - * (c) 1999, Multiple IO-APIC support, developed by - * Ken-ichi Yaku <yaku@xxxxxxxxxxxxxxxxxxxx> and - * Hidemi Kishimoto <kisimoto@xxxxxxxxxxxxxxxxxxxx>, - * further tested and cleaned up by Zach Brown <zab@xxxxxxxxxx> - * and Ingo Molnar <mingo@xxxxxxxxxx> - * - * Fixes - * Maciej W. Rozycki : Bits for genuine 82489DX APICs; - * thanks to Eric Gilmore - * and Rolf G. Tews - * for testing these extensively - * Paul Diefenbaugh : Added full ACPI support - */ - -#include <linux/mm.h> -#include <linux/irq.h> -#include <linux/interrupt.h> -#include <linux/init.h> -#include <linux/delay.h> -#include <linux/sched.h> -#include <linux/config.h> -#include <linux/smp_lock.h> -#include <linux/mc146818rtc.h> -#include <linux/compiler.h> -#include <linux/acpi.h> - -#include <linux/sysdev.h> -#include <asm/io.h> -#include <asm/smp.h> -#include <asm/desc.h> -#include <asm/timer.h> - -#include <mach_apic.h> - -#include "io_ports.h" - -#ifdef CONFIG_XEN - -#include <asm-xen/xen-public/xen.h> -#include <asm-xen/xen-public/physdev.h> - -/* Fake i8259 */ -#define make_8259A_irq(_irq) (io_apic_irqs &= ~(1UL<<(_irq))) -#define disable_8259A_irq(_irq) ((void)0) -#define i8259A_irq_pending(_irq) (0) - -unsigned long io_apic_irqs; - -static inline unsigned int xen_io_apic_read(unsigned int apic, unsigned int reg) -{ - physdev_op_t op; - int ret; - - op.cmd = PHYSDEVOP_APIC_READ; - op.u.apic_op.apic = mp_ioapics[apic].mpc_apicid; - op.u.apic_op.offset = reg; - ret = HYPERVISOR_physdev_op(&op); - if (ret) - return ret; - return op.u.apic_op.value; -} - -static inline void xen_io_apic_write(unsigned int apic, unsigned int reg, unsigned int value) -{ - physdev_op_t op; - - op.cmd = PHYSDEVOP_APIC_WRITE; - op.u.apic_op.apic = mp_ioapics[apic].mpc_apicid; - op.u.apic_op.offset = reg; - op.u.apic_op.value = value; - HYPERVISOR_physdev_op(&op); -} - -#define io_apic_read(a,r) xen_io_apic_read(a,r) -#define io_apic_write(a,r,v) xen_io_apic_write(a,r,v) - -#endif /* CONFIG_XEN */ - -int (*ioapic_renumber_irq)(int ioapic, int irq); -atomic_t irq_mis_count; - -static DEFINE_SPINLOCK(ioapic_lock); - -/* - * Is the SiS APIC rmw bug present ? - * -1 = don't know, 0 = no, 1 = yes - */ -int sis_apic_bug = -1; - -/* - * # of IRQ routing registers - */ -int nr_ioapic_registers[MAX_IO_APICS]; - -/* - * Rough estimation of how many shared IRQs there are, can - * be changed anytime. - */ -#define MAX_PLUS_SHARED_IRQS NR_IRQS -#define PIN_MAP_SIZE (MAX_PLUS_SHARED_IRQS + NR_IRQS) - -/* - * This is performance-critical, we want to do it O(1) - * - * the indexing order of this array favors 1:1 mappings - * between pins and IRQs. - */ - -static struct irq_pin_list { - int apic, pin, next; -} irq_2_pin[PIN_MAP_SIZE]; - -int vector_irq[NR_VECTORS] = { [0 ... NR_VECTORS - 1] = -1}; -#ifdef CONFIG_PCI_MSI -#define vector_to_irq(vector) \ - (platform_legacy_irq(vector) ? vector : vector_irq[vector]) -#else -#define vector_to_irq(vector) (vector) -#endif - -/* - * The common case is 1:1 IRQ<->pin mappings. Sometimes there are - * shared ISA-space IRQs, so we have to support them. We are super - * fast in the common case, and fast for shared ISA-space IRQs. - */ -static void add_pin_to_irq(unsigned int irq, int apic, int pin) -{ - static int first_free_entry = NR_IRQS; - struct irq_pin_list *entry = irq_2_pin + irq; - - while (entry->next) - entry = irq_2_pin + entry->next; - - if (entry->pin != -1) { - entry->next = first_free_entry; - entry = irq_2_pin + entry->next; - if (++first_free_entry >= PIN_MAP_SIZE) - panic("io_apic.c: whoops"); - } - entry->apic = apic; - entry->pin = pin; -} - -#ifndef CONFIG_XEN -/* - * Reroute an IRQ to a different pin. - */ -static void __init replace_pin_at_irq(unsigned int irq, - int oldapic, int oldpin, - int newapic, int newpin) -{ - struct irq_pin_list *entry = irq_2_pin + irq; - - while (1) { - if (entry->apic == oldapic && entry->pin == oldpin) { - entry->apic = newapic; - entry->pin = newpin; - } - if (!entry->next) - break; - entry = irq_2_pin + entry->next; - } -} - -static void __modify_IO_APIC_irq (unsigned int irq, unsigned long enable, unsigned long disable) -{ - struct irq_pin_list *entry = irq_2_pin + irq; - unsigned int pin, reg; - - for (;;) { - pin = entry->pin; - if (pin == -1) - break; - reg = io_apic_read(entry->apic, 0x10 + pin*2); - reg &= ~disable; - reg |= enable; - io_apic_modify(entry->apic, 0x10 + pin*2, reg); - if (!entry->next) - break; - entry = irq_2_pin + entry->next; - } -} - -/* mask = 1 */ -static void __mask_IO_APIC_irq (unsigned int irq) -{ - __modify_IO_APIC_irq(irq, 0x00010000, 0); -} - -/* mask = 0 */ -static void __unmask_IO_APIC_irq (unsigned int irq) -{ - __modify_IO_APIC_irq(irq, 0, 0x00010000); -} - -/* mask = 1, trigger = 0 */ -static void __mask_and_edge_IO_APIC_irq (unsigned int irq) -{ - __modify_IO_APIC_irq(irq, 0x00010000, 0x00008000); -} - -/* mask = 0, trigger = 1 */ -static void __unmask_and_level_IO_APIC_irq (unsigned int irq) -{ - __modify_IO_APIC_irq(irq, 0x00008000, 0x00010000); -} - -static void mask_IO_APIC_irq (unsigned int irq) -{ - unsigned long flags; - - spin_lock_irqsave(&ioapic_lock, flags); - __mask_IO_APIC_irq(irq); - spin_unlock_irqrestore(&ioapic_lock, flags); -} - -static void unmask_IO_APIC_irq (unsigned int irq) -{ - unsigned long flags; - - spin_lock_irqsave(&ioapic_lock, flags); - __unmask_IO_APIC_irq(irq); - spin_unlock_irqrestore(&ioapic_lock, flags); -} - -static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) -{ - struct IO_APIC_route_entry entry; - unsigned long flags; - - /* Check delivery_mode to be sure we're not clearing an SMI pin */ - spin_lock_irqsave(&ioapic_lock, flags); - *(((int*)&entry) + 0) = io_apic_read(apic, 0x10 + 2 * pin); - *(((int*)&entry) + 1) = io_apic_read(apic, 0x11 + 2 * pin); - spin_unlock_irqrestore(&ioapic_lock, flags); - if (entry.delivery_mode == dest_SMI) - return; - - /* - * Disable it in the IO-APIC irq-routing table: - */ - memset(&entry, 0, sizeof(entry)); - entry.mask = 1; - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(apic, 0x10 + 2 * pin, *(((int *)&entry) + 0)); - io_apic_write(apic, 0x11 + 2 * pin, *(((int *)&entry) + 1)); - spin_unlock_irqrestore(&ioapic_lock, flags); -} - -static void clear_IO_APIC (void) -{ - int apic, pin; - - for (apic = 0; apic < nr_ioapics; apic++) - for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) - clear_IO_APIC_pin(apic, pin); -} - -static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask) -{ - unsigned long flags; - int pin; - struct irq_pin_list *entry = irq_2_pin + irq; - unsigned int apicid_value; - - apicid_value = cpu_mask_to_apicid(cpumask); - /* Prepare to do the io_apic_write */ - apicid_value = apicid_value << 24; - spin_lock_irqsave(&ioapic_lock, flags); - for (;;) { - pin = entry->pin; - if (pin == -1) - break; - io_apic_write(entry->apic, 0x10 + 1 + pin*2, apicid_value); - if (!entry->next) - break; - entry = irq_2_pin + entry->next; - } - spin_unlock_irqrestore(&ioapic_lock, flags); -} -#else -#define clear_IO_APIC() ((void)0) -#endif - -#if defined(CONFIG_IRQBALANCE) -# include <asm/processor.h> /* kernel_thread() */ -# include <linux/kernel_stat.h> /* kstat */ -# include <linux/slab.h> /* kmalloc() */ -# include <linux/timer.h> /* time_after() */ - -# ifdef CONFIG_BALANCED_IRQ_DEBUG -# define TDprintk(x...) do { printk("<%ld:%s:%d>: ", jiffies, __FILE__, __LINE__); printk(x); } while (0) -# define Dprintk(x...) do { TDprintk(x); } while (0) -# else -# define TDprintk(x...) -# define Dprintk(x...) -# endif - -cpumask_t __cacheline_aligned pending_irq_balance_cpumask[NR_IRQS]; - -#define IRQBALANCE_CHECK_ARCH -999 -static int irqbalance_disabled = IRQBALANCE_CHECK_ARCH; -static int physical_balance = 0; - -static struct irq_cpu_info { - unsigned long * last_irq; - unsigned long * irq_delta; - unsigned long irq; -} irq_cpu_data[NR_CPUS]; - -#define CPU_IRQ(cpu) (irq_cpu_data[cpu].irq) -#define LAST_CPU_IRQ(cpu,irq) (irq_cpu_data[cpu].last_irq[irq]) -#define IRQ_DELTA(cpu,irq) (irq_cpu_data[cpu].irq_delta[irq]) - -#define IDLE_ENOUGH(cpu,now) \ - (idle_cpu(cpu) && ((now) - per_cpu(irq_stat, (cpu)).idle_timestamp > 1)) - -#define IRQ_ALLOWED(cpu, allowed_mask) cpu_isset(cpu, allowed_mask) - -#define CPU_TO_PACKAGEINDEX(i) (first_cpu(cpu_sibling_map[i])) - -#define MAX_BALANCED_IRQ_INTERVAL (5*HZ) -#define MIN_BALANCED_IRQ_INTERVAL (HZ/2) -#define BALANCED_IRQ_MORE_DELTA (HZ/10) -#define BALANCED_IRQ_LESS_DELTA (HZ) - -static long balanced_irq_interval = MAX_BALANCED_IRQ_INTERVAL; - -static unsigned long move(int curr_cpu, cpumask_t allowed_mask, - unsigned long now, int direction) -{ - int search_idle = 1; - int cpu = curr_cpu; - - goto inside; - - do { - if (unlikely(cpu == curr_cpu)) - search_idle = 0; -inside: - if (direction == 1) { - cpu++; - if (cpu >= NR_CPUS) - cpu = 0; - } else { - cpu--; - if (cpu == -1) - cpu = NR_CPUS-1; - } - } while (!cpu_online(cpu) || !IRQ_ALLOWED(cpu,allowed_mask) || - (search_idle && !IDLE_ENOUGH(cpu,now))); - - return cpu; -} - -static inline void balance_irq(int cpu, int irq) -{ - unsigned long now = jiffies; - cpumask_t allowed_mask; - unsigned int new_cpu; - - if (irqbalance_disabled) - return; - - cpus_and(allowed_mask, cpu_online_map, irq_affinity[irq]); - new_cpu = move(cpu, allowed_mask, now, 1); - if (cpu != new_cpu) { - irq_desc_t *desc = irq_desc + irq; - unsigned long flags; - - spin_lock_irqsave(&desc->lock, flags); - pending_irq_balance_cpumask[irq] = cpumask_of_cpu(new_cpu); - spin_unlock_irqrestore(&desc->lock, flags); - } -} - -static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold) -{ - int i, j; - Dprintk("Rotating IRQs among CPUs.\n"); - for (i = 0; i < NR_CPUS; i++) { - for (j = 0; cpu_online(i) && (j < NR_IRQS); j++) { - if (!irq_desc[j].action) - continue; - /* Is it a significant load ? */ - if (IRQ_DELTA(CPU_TO_PACKAGEINDEX(i),j) < - useful_load_threshold) - continue; - balance_irq(i, j); - } - } - balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL, - balanced_irq_interval - BALANCED_IRQ_LESS_DELTA); - return; -} - -static void do_irq_balance(void) -{ - int i, j; - unsigned long max_cpu_irq = 0, min_cpu_irq = (~0); - unsigned long move_this_load = 0; - int max_loaded = 0, min_loaded = 0; - int load; - unsigned long useful_load_threshold = balanced_irq_interval + 10; - int selected_irq; - int tmp_loaded, first_attempt = 1; - unsigned long tmp_cpu_irq; - unsigned long imbalance = 0; - cpumask_t allowed_mask, target_cpu_mask, tmp; - - for (i = 0; i < NR_CPUS; i++) { - int package_index; - CPU_IRQ(i) = 0; - if (!cpu_online(i)) - continue; - package_index = CPU_TO_PACKAGEINDEX(i); - for (j = 0; j < NR_IRQS; j++) { - unsigned long value_now, delta; - /* Is this an active IRQ? */ - if (!irq_desc[j].action) - continue; - if ( package_index == i ) - IRQ_DELTA(package_index,j) = 0; - /* Determine the total count per processor per IRQ */ - value_now = (unsigned long) kstat_cpu(i).irqs[j]; - - /* Determine the activity per processor per IRQ */ - delta = value_now - LAST_CPU_IRQ(i,j); - - /* Update last_cpu_irq[][] for the next time */ - LAST_CPU_IRQ(i,j) = value_now; - - /* Ignore IRQs whose rate is less than the clock */ - if (delta < useful_load_threshold) - continue; - /* update the load for the processor or package total */ - IRQ_DELTA(package_index,j) += delta; - - /* Keep track of the higher numbered sibling as well */ - if (i != package_index) - CPU_IRQ(i) += delta; - /* - * We have sibling A and sibling B in the package - * - * cpu_irq[A] = load for cpu A + load for cpu B - * cpu_irq[B] = load for cpu B - */ - CPU_IRQ(package_index) += delta; - } - } - /* Find the least loaded processor package */ - for (i = 0; i < NR_CPUS; i++) { - if (!cpu_online(i)) - continue; - if (i != CPU_TO_PACKAGEINDEX(i)) - continue; - if (min_cpu_irq > CPU_IRQ(i)) { - min_cpu_irq = CPU_IRQ(i); - min_loaded = i; - } - } - max_cpu_irq = ULONG_MAX; - -tryanothercpu: - /* Look for heaviest loaded processor. - * We may come back to get the next heaviest loaded processor. - * Skip processors with trivial loads. - */ - tmp_cpu_irq = 0; - tmp_loaded = -1; - for (i = 0; i < NR_CPUS; i++) { - if (!cpu_online(i)) - continue; - if (i != CPU_TO_PACKAGEINDEX(i)) - continue; - if (max_cpu_irq <= CPU_IRQ(i)) - continue; - if (tmp_cpu_irq < CPU_IRQ(i)) { - tmp_cpu_irq = CPU_IRQ(i); - tmp_loaded = i; - } - } - - if (tmp_loaded == -1) { - /* In the case of small number of heavy interrupt sources, - * loading some of the cpus too much. We use Ingo's original - * approach to rotate them around. - */ - if (!first_attempt && imbalance >= useful_load_threshold) { - rotate_irqs_among_cpus(useful_load_threshold); - return; - } - goto not_worth_the_effort; - } - - first_attempt = 0; /* heaviest search */ - max_cpu_irq = tmp_cpu_irq; /* load */ - max_loaded = tmp_loaded; /* processor */ - imbalance = (max_cpu_irq - min_cpu_irq) / 2; - - Dprintk("max_loaded cpu = %d\n", max_loaded); - Dprintk("min_loaded cpu = %d\n", min_loaded); - Dprintk("max_cpu_irq load = %ld\n", max_cpu_irq); - Dprintk("min_cpu_irq load = %ld\n", min_cpu_irq); - Dprintk("load imbalance = %lu\n", imbalance); - - /* if imbalance is less than approx 10% of max load, then - * observe diminishing returns action. - quit - */ - if (imbalance < (max_cpu_irq >> 3)) { - Dprintk("Imbalance too trivial\n"); - goto not_worth_the_effort; - } - -tryanotherirq: - /* if we select an IRQ to move that can't go where we want, then - * see if there is another one to try. - */ - move_this_load = 0; - selected_irq = -1; - for (j = 0; j < NR_IRQS; j++) { - /* Is this an active IRQ? */ - if (!irq_desc[j].action) - continue; - if (imbalance <= IRQ_DELTA(max_loaded,j)) - continue; - /* Try to find the IRQ that is closest to the imbalance - * without going over. - */ - if (move_this_load < IRQ_DELTA(max_loaded,j)) { - move_this_load = IRQ_DELTA(max_loaded,j); - selected_irq = j; - } - } - if (selected_irq == -1) { - goto tryanothercpu; - } - - imbalance = move_this_load; - - /* For physical_balance case, we accumlated both load - * values in the one of the siblings cpu_irq[], - * to use the same code for physical and logical processors - * as much as possible. - * - * NOTE: the cpu_irq[] array holds the sum of the load for - * sibling A and sibling B in the slot for the lowest numbered - * sibling (A), _AND_ the load for sibling B in the slot for - * the higher numbered sibling. - * - * We seek the least loaded sibling by making the comparison - * (A+B)/2 vs B - */ - load = CPU_IRQ(min_loaded) >> 1; - for_each_cpu_mask(j, cpu_sibling_map[min_loaded]) { - if (load > CPU_IRQ(j)) { - /* This won't change cpu_sibling_map[min_loaded] */ - load = CPU_IRQ(j); - min_loaded = j; - } - } - - cpus_and(allowed_mask, cpu_online_map, irq_affinity[selected_irq]); - target_cpu_mask = cpumask_of_cpu(min_loaded); - cpus_and(tmp, target_cpu_mask, allowed_mask); - - if (!cpus_empty(tmp)) { - irq_desc_t *desc = irq_desc + selected_irq; - unsigned long flags; - - Dprintk("irq = %d moved to cpu = %d\n", - selected_irq, min_loaded); - /* mark for change destination */ - spin_lock_irqsave(&desc->lock, flags); - pending_irq_balance_cpumask[selected_irq] = - cpumask_of_cpu(min_loaded); - spin_unlock_irqrestore(&desc->lock, flags); - /* Since we made a change, come back sooner to - * check for more variation. - */ - balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL, - balanced_irq_interval - BALANCED_IRQ_LESS_DELTA); - return; - } - goto tryanotherirq; - -not_worth_the_effort: - /* - * if we did not find an IRQ to move, then adjust the time interval - * upward - */ - balanced_irq_interval = min((long)MAX_BALANCED_IRQ_INTERVAL, - balanced_irq_interval + BALANCED_IRQ_MORE_DELTA); - Dprintk("IRQ worth rotating not found\n"); - return; -} - -static int balanced_irq(void *unused) -{ - int i; - unsigned long prev_balance_time = jiffies; - long time_remaining = balanced_irq_interval; - - daemonize("kirqd"); - - /* push everything to CPU 0 to give us a starting point. */ - for (i = 0 ; i < NR_IRQS ; i++) { - pending_irq_balance_cpumask[i] = cpumask_of_cpu(0); - } - - for ( ; ; ) { - set_current_state(TASK_INTERRUPTIBLE); - time_remaining = schedule_timeout(time_remaining); - try_to_freeze(PF_FREEZE); - if (time_after(jiffies, - prev_balance_time+balanced_irq_interval)) { - preempt_disable(); - do_irq_balance(); - prev_balance_time = jiffies; - time_remaining = balanced_irq_interval; - preempt_enable(); - } - } - return 0; -} - -static int __init balanced_irq_init(void) -{ - int i; - struct cpuinfo_x86 *c; - cpumask_t tmp; - - cpus_shift_right(tmp, cpu_online_map, 2); - c = &boot_cpu_data; - /* When not overwritten by the command line ask subarchitecture. */ - if (irqbalance_disabled == IRQBALANCE_CHECK_ARCH) - irqbalance_disabled = NO_BALANCE_IRQ; - if (irqbalance_disabled) - return 0; - - /* disable irqbalance completely if there is only one processor online */ - if (num_online_cpus() < 2) { - irqbalance_disabled = 1; - return 0; - } - /* - * Enable physical balance only if more than 1 physical processor - * is present - */ - if (smp_num_siblings > 1 && !cpus_empty(tmp)) - physical_balance = 1; - - for (i = 0; i < NR_CPUS; i++) { - if (!cpu_online(i)) - continue; - irq_cpu_data[i].irq_delta = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL); - irq_cpu_data[i].last_irq = kmalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL); - if (irq_cpu_data[i].irq_delta == NULL || irq_cpu_data[i].last_irq == NULL) { - printk(KERN_ERR "balanced_irq_init: out of memory"); - goto failed; - } - memset(irq_cpu_data[i].irq_delta,0,sizeof(unsigned long) * NR_IRQS); - memset(irq_cpu_data[i].last_irq,0,sizeof(unsigned long) * NR_IRQS); - } - - printk(KERN_INFO "Starting balanced_irq\n"); - if (kernel_thread(balanced_irq, NULL, CLONE_KERNEL) >= 0) - return 0; - else - printk(KERN_ERR "balanced_irq_init: failed to spawn balanced_irq"); -failed: - for (i = 0; i < NR_CPUS; i++) { - if(irq_cpu_data[i].irq_delta) - kfree(irq_cpu_data[i].irq_delta); - if(irq_cpu_data[i].last_irq) - kfree(irq_cpu_data[i].last_irq); - } - return 0; -} - -int __init irqbalance_disable(char *str) -{ - irqbalance_disabled = 1; - return 0; -} - -__setup("noirqbalance", irqbalance_disable); - -static inline void move_irq(int irq) -{ - /* note - we hold the desc->lock */ - if (unlikely(!cpus_empty(pending_irq_balance_cpumask[irq]))) { - set_ioapic_affinity_irq(irq, pending_irq_balance_cpumask[irq]); - cpus_clear(pending_irq_balance_cpumask[irq]); - } -} - -late_initcall(balanced_irq_init); - -#else /* !CONFIG_IRQBALANCE */ -static inline void move_irq(int irq) { } -#endif /* CONFIG_IRQBALANCE */ - -#ifndef CONFIG_SMP -void fastcall send_IPI_self(int vector) -{ -#ifndef CONFIG_XEN - unsigned int cfg; - - /* - * Wait for idle. - */ - apic_wait_icr_idle(); - cfg = APIC_DM_FIXED | APIC_DEST_SELF | vector | APIC_DEST_LOGICAL; - /* - * Send the IPI. The write to APIC_ICR fires this off. - */ - apic_write_around(APIC_ICR, cfg); -#endif -} -#endif /* !CONFIG_SMP */ - - -/* - * support for broken MP BIOSs, enables hand-redirection of PIRQ0-7 to - * specific CPU-side IRQs. - */ - -#define MAX_PIRQS 8 -static int pirq_entries [MAX_PIRQS]; -static int pirqs_enabled; -int skip_ioapic_setup; - -static int __init ioapic_setup(char *str) -{ - skip_ioapic_setup = 1; - return 1; -} - -__setup("noapic", ioapic_setup); - -static int __init ioapic_pirq_setup(char *str) -{ - int i, max; - int ints[MAX_PIRQS+1]; - - get_options(str, ARRAY_SIZE(ints), ints); - - for (i = 0; i < MAX_PIRQS; i++) - pirq_entries[i] = -1; - - pirqs_enabled = 1; - apic_printk(APIC_VERBOSE, KERN_INFO - "PIRQ redirection, working around broken MP-BIOS.\n"); - max = MAX_PIRQS; - if (ints[0] < MAX_PIRQS) - max = ints[0]; - - for (i = 0; i < max; i++) { - apic_printk(APIC_VERBOSE, KERN_DEBUG - "... PIRQ%d -> IRQ %d\n", i, ints[i+1]); - /* - * PIRQs are mapped upside down, usually. - */ - pirq_entries[MAX_PIRQS-i-1] = ints[i+1]; - } - return 1; -} - -__setup("pirq=", ioapic_pirq_setup); - -/* - * Find the IRQ entry number of a certain pin. - */ -static int find_irq_entry(int apic, int pin, int type) -{ - int i; - - for (i = 0; i < mp_irq_entries; i++) - if (mp_irqs[i].mpc_irqtype == type && - (mp_irqs[i].mpc_dstapic == mp_ioapics[apic].mpc_apicid || - mp_irqs[i].mpc_dstapic == MP_APIC_ALL) && - mp_irqs[i].mpc_dstirq == pin) - return i; - - return -1; -} - -#ifndef CONFIG_XEN -/* - * Find the pin to which IRQ[irq] (ISA) is connected - */ -static int find_isa_irq_pin(int irq, int type) -{ - int i; - - for (i = 0; i < mp_irq_entries; i++) { - int lbus = mp_irqs[i].mpc_srcbus; - - if ((mp_bus_id_to_type[lbus] == MP_BUS_ISA || - mp_bus_id_to_type[lbus] == MP_BUS_EISA || - mp_bus_id_to_type[lbus] == MP_BUS_MCA || - mp_bus_id_to_type[lbus] == MP_BUS_NEC98 - ) && - (mp_irqs[i].mpc_irqtype == type) && - (mp_irqs[i].mpc_srcbusirq == irq)) - - return mp_irqs[i].mpc_dstirq; - } - return -1; -} -#endif - -/* - * Find a specific PCI IRQ entry. - * Not an __init, possibly needed by modules - */ -static int pin_2_irq(int idx, int apic, int pin); - -int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin) -{ - int apic, i, best_guess = -1; - - apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, " - "slot:%d, pin:%d.\n", bus, slot, pin); - if (mp_bus_id_to_pci_bus[bus] == -1) { - printk(KERN_WARNING "PCI BIOS passed nonexistent PCI bus %d!\n", bus); - return -1; - } - for (i = 0; i < mp_irq_entries; i++) { - int lbus = mp_irqs[i].mpc_srcbus; - - for (apic = 0; apic < nr_ioapics; apic++) - if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic || - mp_irqs[i].mpc_dstapic == MP_APIC_ALL) - break; - - if ((mp_bus_id_to_type[lbus] == MP_BUS_PCI) && - !mp_irqs[i].mpc_irqtype && - (bus == lbus) && - (slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) { - int irq = pin_2_irq(i,apic,mp_irqs[i].mpc_dstirq); - - if (!(apic || IO_APIC_IRQ(irq))) - continue; - - if (pin == (mp_irqs[i].mpc_srcbusirq & 3)) - return irq; - /* - * Use the first all-but-pin matching entry as a - * best-guess fuzzy result for broken mptables. - */ - if (best_guess < 0) - best_guess = irq; - } - } - return best_guess; -} - -#ifndef CONFIG_XEN -/* - * This function currently is only a helper for the i386 smp boot process where - * we need to reprogram the ioredtbls to cater for the cpus which have come online - * so mask in all cases should simply be TARGET_CPUS - */ -void __init setup_ioapic_dest(void) -{ - int pin, ioapic, irq, irq_entry; - - if (skip_ioapic_setup == 1) - return; - - for (ioapic = 0; ioapic < nr_ioapics; ioapic++) { - for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) { - irq_entry = find_irq_entry(ioapic, pin, mp_INT); - if (irq_entry == -1) - continue; - irq = pin_2_irq(irq_entry, ioapic, pin); - set_ioapic_affinity_irq(irq, TARGET_CPUS); - } - - } -} -#endif /* !CONFIG_XEN */ - -/* - * EISA Edge/Level control register, ELCR - */ -static int EISA_ELCR(unsigned int irq) -{ - if (irq < 16) { - unsigned int port = 0x4d0 + (irq >> 3); - return (inb(port) >> (irq & 7)) & 1; - } - apic_printk(APIC_VERBOSE, KERN_INFO - "Broken MPtable reports ISA irq %d\n", irq); - return 0; -} - -/* EISA interrupts are always polarity zero and can be edge or level - * trigger depending on the ELCR value. If an interrupt is listed as - * EISA conforming in the MP table, that means its trigger type must - * be read in from the ELCR */ - -#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].mpc_srcbusirq)) -#define default_EISA_polarity(idx) (0) - -/* ISA interrupts are always polarity zero edge triggered, - * when listed as conforming in the MP table. */ - -#define default_ISA_trigger(idx) (0) -#define default_ISA_polarity(idx) (0) - -/* PCI interrupts are always polarity one level triggered, - * when listed as conforming in the MP table. */ - -#define default_PCI_trigger(idx) (1) -#define default_PCI_polarity(idx) (1) - -/* MCA interrupts are always polarity zero level triggered, - * when listed as conforming in the MP table. */ - -#define default_MCA_trigger(idx) (1) -#define default_MCA_polarity(idx) (0) - -/* NEC98 interrupts are always polarity zero edge triggered, - * when listed as conforming in the MP table. */ - -#define default_NEC98_trigger(idx) (0) -#define default_NEC98_polarity(idx) (0) - -static int __init MPBIOS_polarity(int idx) -{ - int bus = mp_irqs[idx].mpc_srcbus; - int polarity; - - /* - * Determine IRQ line polarity (high active or low active): - */ - switch (mp_irqs[idx].mpc_irqflag & 3) - { - case 0: /* conforms, ie. bus-type dependent polarity */ - { - switch (mp_bus_id_to_type[bus]) - { - case MP_BUS_ISA: /* ISA pin */ - { - polarity = default_ISA_polarity(idx); - break; - } - case MP_BUS_EISA: /* EISA pin */ - { - polarity = default_EISA_polarity(idx); - break; - } - case MP_BUS_PCI: /* PCI pin */ - { - polarity = default_PCI_polarity(idx); - break; - } - case MP_BUS_MCA: /* MCA pin */ - { - polarity = default_MCA_polarity(idx); - break; - } - case MP_BUS_NEC98: /* NEC 98 pin */ - { - polarity = default_NEC98_polarity(idx); - break; - } - default: - { - printk(KERN_WARNING "broken BIOS!!\n"); - polarity = 1; - break; - } - } - break; - } - case 1: /* high active */ - { - polarity = 0; - break; - } - case 2: /* reserved */ - { - printk(KERN_WARNING "broken BIOS!!\n"); - polarity = 1; - break; - } - case 3: /* low active */ - { - polarity = 1; - break; - } - default: /* invalid */ - { - printk(KERN_WARNING "broken BIOS!!\n"); - polarity = 1; - break; - } - } - return polarity; -} - -static int MPBIOS_trigger(int idx) -{ - int bus = mp_irqs[idx].mpc_srcbus; - int trigger; - - /* - * Determine IRQ trigger mode (edge or level sensitive): - */ - switch ((mp_irqs[idx].mpc_irqflag>>2) & 3) - { - case 0: /* conforms, ie. bus-type dependent */ - { - switch (mp_bus_id_to_type[bus]) - { - case MP_BUS_ISA: /* ISA pin */ - { - trigger = default_ISA_trigger(idx); - break; - } - case MP_BUS_EISA: /* EISA pin */ - { - trigger = default_EISA_trigger(idx); - break; - } - case MP_BUS_PCI: /* PCI pin */ - { - trigger = default_PCI_trigger(idx); - break; - } - case MP_BUS_MCA: /* MCA pin */ - { - trigger = default_MCA_trigger(idx); - break; - } - case MP_BUS_NEC98: /* NEC 98 pin */ - { - trigger = default_NEC98_trigger(idx); - break; - } - default: - { - printk(KERN_WARNING "broken BIOS!!\n"); - trigger = 1; - break; - } - } - break; - } - case 1: /* edge */ - { - trigger = 0; - break; - } - case 2: /* reserved */ - { - printk(KERN_WARNING "broken BIOS!!\n"); - trigger = 1; - break; - } - case 3: /* level */ - { - trigger = 1; - break; - } - default: /* invalid */ - { - printk(KERN_WARNING "broken BIOS!!\n"); - trigger = 0; - break; - } - } - return trigger; -} - -static inline int irq_polarity(int idx) -{ - return MPBIOS_polarity(idx); -} - -static inline int irq_trigger(int idx) -{ - return MPBIOS_trigger(idx); -} - -static int pin_2_irq(int idx, int apic, int pin) -{ - int irq, i; - int bus = mp_irqs[idx].mpc_srcbus; - - /* - * Debugging check, we are in big trouble if this message pops up! - */ - if (mp_irqs[idx].mpc_dstirq != pin) - printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n"); - - switch (mp_bus_id_to_type[bus]) - { - case MP_BUS_ISA: /* ISA pin */ - case MP_BUS_EISA: - case MP_BUS_MCA: - case MP_BUS_NEC98: - { - irq = mp_irqs[idx].mpc_srcbusirq; - break; - } - case MP_BUS_PCI: /* PCI pin */ - { - /* - * PCI IRQs are mapped in order - */ - i = irq = 0; - while (i < apic) - irq += nr_ioapic_registers[i++]; - irq += pin; - - /* - * For MPS mode, so far only needed by ES7000 platform - */ - if (ioapic_renumber_irq) - irq = ioapic_renumber_irq(apic, irq); - - break; - } - default: - { - printk(KERN_ERR "unknown bus type %d.\n",bus); - irq = 0; - break; - } - } - - /* - * PCI IRQ command line redirection. Yes, limits are hardcoded. - */ - if ((pin >= 16) && (pin <= 23)) { - if (pirq_entries[pin-16] != -1) { - if (!pirq_entries[pin-16]) { - apic_printk(APIC_VERBOSE, KERN_DEBUG - "disabling PIRQ%d\n", pin-16); - } else { - irq = pirq_entries[pin-16]; - apic_printk(APIC_VERBOSE, KERN_DEBUG - "using PIRQ%d -> IRQ %d\n", - pin-16, irq); - } - } - } - return irq; -} - -static inline int IO_APIC_irq_trigger(int irq) -{ - int apic, idx, pin; - - for (apic = 0; apic < nr_ioapics; apic++) { - for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { - idx = find_irq_entry(apic,pin,mp_INT); - if ((idx != -1) && (irq == pin_2_irq(idx,apic,pin))) - return irq_trigger(idx); - } - } - /* - * nonexistent IRQs are edge default - */ - return 0; -} - -/* irq_vectors is indexed by the sum of all RTEs in all I/O APICs. */ -u8 irq_vector[NR_IRQ_VECTORS]; /* = { FIRST_DEVICE_VECTOR , 0 }; */ - -int assign_irq_vector(int irq) -{ - static int current_vector = FIRST_DEVICE_VECTOR; - physdev_op_t op; - - BUG_ON(irq >= NR_IRQ_VECTORS); - if (irq != AUTO_ASSIGN && IO_APIC_VECTOR(irq) > 0) - return IO_APIC_VECTOR(irq); - - op.cmd = PHYSDEVOP_ASSIGN_VECTOR; - op.u.irq_op.irq = irq; - if (HYPERVISOR_physdev_op(&op)) - return -ENOSPC; - current_vector = op.u.irq_op.vector; - - vector_irq[current_vector] = irq; - if (irq != AUTO_ASSIGN) - IO_APIC_VECTOR(irq) = current_vector; - - return current_vector; -} - -#ifndef CONFIG_XEN -static struct hw_interrupt_type ioapic_level_type; -static struct hw_interrupt_type ioapic_edge_type; - -#define IOAPIC_AUTO -1 -#define IOAPIC_EDGE 0 -#define IOAPIC_LEVEL 1 - -static inline void ioapic_register_intr(int irq, int vector, unsigned long trigger) -{ - if (use_pci_vector() && !platform_legacy_irq(irq)) { - if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) || - trigger == IOAPIC_LEVEL) - irq_desc[vector].handler = &ioapic_level_type; - else - irq_desc[vector].handler = &ioapic_edge_type; - set_intr_gate(vector, interrupt[vector]); - } else { - if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) || - trigger == IOAPIC_LEVEL) - irq_desc[irq].handler = &ioapic_level_type; - else - irq_desc[irq].handler = &ioapic_edge_type; - set_intr_gate(vector, interrupt[irq]); - } -} -#else -#define ioapic_register_intr(_irq,_vector,_trigger) ((void)0) -#endif - -static void __init setup_IO_APIC_irqs(void) -{ - struct IO_APIC_route_entry entry; - int apic, pin, idx, irq, first_notcon = 1, vector; - unsigned long flags; - - apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n"); - - for (apic = 0; apic < nr_ioapics; apic++) { - for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { - - /* - * add it to the IO-APIC irq-routing table: - */ - memset(&entry,0,sizeof(entry)); - - entry.delivery_mode = INT_DELIVERY_MODE; - entry.dest_mode = INT_DEST_MODE; - entry.mask = 0; /* enable IRQ */ - entry.dest.logical.logical_dest = - cpu_mask_to_apicid(TARGET_CPUS); - - idx = find_irq_entry(apic,pin,mp_INT); - if (idx == -1) { - if (first_notcon) { - apic_printk(APIC_VERBOSE, KERN_DEBUG - " IO-APIC (apicid-pin) %d-%d", - mp_ioapics[apic].mpc_apicid, - pin); - first_notcon = 0; - } else - apic_printk(APIC_VERBOSE, ", %d-%d", - mp_ioapics[apic].mpc_apicid, pin); - continue; - } - - entry.trigger = irq_trigger(idx); - entry.polarity = irq_polarity(idx); - - if (irq_trigger(idx)) { - entry.trigger = 1; - entry.mask = 1; - } - - irq = pin_2_irq(idx, apic, pin); - /* - * skip adding the timer int on secondary nodes, which causes - * a small but painful rift in the time-space continuum - */ - if (multi_timer_check(apic, irq)) - continue; - else - add_pin_to_irq(irq, apic, pin); - - if (/*!apic &&*/ !IO_APIC_IRQ(irq)) - continue; - - if (IO_APIC_IRQ(irq)) { - vector = assign_irq_vector(irq); - entry.vector = vector; - ioapic_register_intr(irq, vector, IOAPIC_AUTO); - - if (!apic && (irq < 16)) - disable_8259A_irq(irq); - } - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(apic, 0x11+2*pin, *(((int *)&entry)+1)); - io_apic_write(apic, 0x10+2*pin, *(((int *)&entry)+0)); - spin_unlock_irqrestore(&ioapic_lock, flags); - } - } - - if (!first_notcon) - apic_printk(APIC_VERBOSE, " not connected.\n"); -} - -/* - * Set up the 8259A-master output pin: - */ -#ifndef CONFIG_XEN -static void __init setup_ExtINT_IRQ0_pin(unsigned int pin, int vector) -{ - struct IO_APIC_route_entry entry; - unsigned long flags; - - memset(&entry,0,sizeof(entry)); - - disable_8259A_irq(0); - - /* mask LVT0 */ - apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); - - /* - * We use logical delivery to get the timer IRQ - * to the first CPU. - */ - entry.dest_mode = INT_DEST_MODE; - entry.mask = 0; /* unmask IRQ now */ - entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS); - entry.delivery_mode = INT_DELIVERY_MODE; - entry.polarity = 0; - entry.trigger = 0; - entry.vector = vector; - - /* - * The timer IRQ doesn't have to know that behind the - * scene we have a 8259A-master in AEOI mode ... - */ - irq_desc[0].handler = &ioapic_edge_type; - - /* - * Add it to the IO-APIC irq-routing table: - */ - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(0, 0x11+2*pin, *(((int *)&entry)+1)); - io_apic_write(0, 0x10+2*pin, *(((int *)&entry)+0)); - spin_unlock_irqrestore(&ioapic_lock, flags); - - enable_8259A_irq(0); -} - -static inline void UNEXPECTED_IO_APIC(void) -{ -} - -void __init print_IO_APIC(void) -{ - int apic, i; - union IO_APIC_reg_00 reg_00; - union IO_APIC_reg_01 reg_01; - union IO_APIC_reg_02 reg_02; - union IO_APIC_reg_03 reg_03; - unsigned long flags; - - if (apic_verbosity == APIC_QUIET) - return; - - printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries); - for (i = 0; i < nr_ioapics; i++) - printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n", - mp_ioapics[i].mpc_apicid, nr_ioapic_registers[i]); - - /* - * We are a bit conservative about what we expect. We have to - * know about every hardware change ASAP. - */ - printk(KERN_INFO "testing the IO APIC.......................\n"); - - for (apic = 0; apic < nr_ioapics; apic++) { - - spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(apic, 0); - reg_01.raw = io_apic_read(apic, 1); - if (reg_01.bits.version >= 0x10) - reg_02.raw = io_apic_read(apic, 2); - if (reg_01.bits.version >= 0x20) - reg_03.raw = io_apic_read(apic, 3); - spin_unlock_irqrestore(&ioapic_lock, flags); - - printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mpc_apicid); - printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw); - printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID); - printk(KERN_DEBUG "....... : Delivery Type: %X\n", reg_00.bits.delivery_type); - printk(KERN_DEBUG "....... : LTS : %X\n", reg_00.bits.LTS); - if (reg_00.bits.ID >= get_physical_broadcast()) - UNEXPECTED_IO_APIC(); - if (reg_00.bits.__reserved_1 || reg_00.bits.__reserved_2) - UNEXPECTED_IO_APIC(); - - printk(KERN_DEBUG ".... register #01: %08X\n", reg_01.raw); - printk(KERN_DEBUG "....... : max redirection entries: %04X\n", reg_01.bits.entries); - if ( (reg_01.bits.entries != 0x0f) && /* older (Neptune) boards */ - (reg_01.bits.entries != 0x17) && /* typical ISA+PCI boards */ - (reg_01.bits.entries != 0x1b) && /* Compaq Proliant boards */ - (reg_01.bits.entries != 0x1f) && /* dual Xeon boards */ - (reg_01.bits.entries != 0x22) && /* bigger Xeon boards */ - (reg_01.bits.entries != 0x2E) && - (reg_01.bits.entries != 0x3F) - ) - UNEXPECTED_IO_APIC(); - - printk(KERN_DEBUG "....... : PRQ implemented: %X\n", reg_01.bits.PRQ); - printk(KERN_DEBUG "....... : IO APIC version: %04X\n", reg_01.bits.version); - if ( (reg_01.bits.version != 0x01) && /* 82489DX IO-APICs */ - (reg_01.bits.version != 0x10) && /* oldest IO-APICs */ - (reg_01.bits.version != 0x11) && /* Pentium/Pro IO-APICs */ - (reg_01.bits.version != 0x13) && /* Xeon IO-APICs */ - (reg_01.bits.version != 0x20) /* Intel P64H (82806 AA) */ - ) - UNEXPECTED_IO_APIC(); - if (reg_01.bits.__reserved_1 || reg_01.bits.__reserved_2) - UNEXPECTED_IO_APIC(); - - /* - * Some Intel chipsets with IO APIC VERSION of 0x1? don't have reg_02, - * but the value of reg_02 is read as the previous read register - * value, so ignore it if reg_02 == reg_01. - */ - if (reg_01.bits.version >= 0x10 && reg_02.raw != reg_01.raw) { - printk(KERN_DEBUG ".... register #02: %08X\n", reg_02.raw); - printk(KERN_DEBUG "....... : arbitration: %02X\n", reg_02.bits.arbitration); - if (reg_02.bits.__reserved_1 || reg_02.bits.__reserved_2) - UNEXPECTED_IO_APIC(); - } - - /* - * Some Intel chipsets with IO APIC VERSION of 0x2? don't have reg_02 - * or reg_03, but the value of reg_0[23] is read as the previous read - * register value, so ignore it if reg_03 == reg_0[12]. - */ - if (reg_01.bits.version >= 0x20 && reg_03.raw != reg_02.raw && - reg_03.raw != reg_01.raw) { - printk(KERN_DEBUG ".... register #03: %08X\n", reg_03.raw); - printk(KERN_DEBUG "....... : Boot DT : %X\n", reg_03.bits.boot_DT); - if (reg_03.bits.__reserved_1) - UNEXPECTED_IO_APIC(); - } - - printk(KERN_DEBUG ".... IRQ redirection table:\n"); - - printk(KERN_DEBUG " NR Log Phy Mask Trig IRR Pol" - " Stat Dest Deli Vect: \n"); - - for (i = 0; i <= reg_01.bits.entries; i++) { - struct IO_APIC_route_entry entry; - - spin_lock_irqsave(&ioapic_lock, flags); - *(((int *)&entry)+0) = io_apic_read(apic, 0x10+i*2); - *(((int *)&entry)+1) = io_apic_read(apic, 0x11+i*2); - spin_unlock_irqrestore(&ioapic_lock, flags); - - printk(KERN_DEBUG " %02x %03X %02X ", - i, - entry.dest.logical.logical_dest, - entry.dest.physical.physical_dest - ); - - printk("%1d %1d %1d %1d %1d %1d %1d %02X\n", - entry.mask, - entry.trigger, - entry.irr, - entry.polarity, - entry.delivery_status, - entry.dest_mode, - entry.delivery_mode, - entry.vector - ); - } - } - if (use_pci_vector()) - printk(KERN_INFO "Using vector-based indexing\n"); - printk(KERN_DEBUG "IRQ to pin mappings:\n"); - for (i = 0; i < NR_IRQS; i++) { - struct irq_pin_list *entry = irq_2_pin + i; - if (entry->pin < 0) - continue; - if (use_pci_vector() && !platform_legacy_irq(i)) - printk(KERN_DEBUG "IRQ%d ", IO_APIC_VECTOR(i)); - else - printk(KERN_DEBUG "IRQ%d ", i); - for (;;) { - printk("-> %d:%d", entry->apic, entry->pin); - if (!entry->next) - break; - entry = irq_2_pin + entry->next; - } - printk("\n"); - } - - printk(KERN_INFO ".................................... done.\n"); - - return; -} - -static void print_APIC_bitfield (int base) -{ - unsigned int v; - int i, j; - - if (apic_verbosity == APIC_QUIET) - return; - - printk(KERN_DEBUG "0123456789abcdef0123456789abcdef\n" KERN_DEBUG); - for (i = 0; i < 8; i++) { - v = apic_read(base + i*0x10); - for (j = 0; j < 32; j++) { - if (v & (1<<j)) - printk("1"); - else - printk("0"); - } - printk("\n"); - } -} - -void /*__init*/ print_local_APIC(void * dummy) -{ - unsigned int v, ver, maxlvt; - - if (apic_verbosity == APIC_QUIET) - return; - - printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n", - smp_processor_id(), hard_smp_processor_id()); - v = apic_read(APIC_ID); - printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, GET_APIC_ID(v)); - v = apic_read(APIC_LVR); - printk(KERN_INFO "... APIC VERSION: %08x\n", v); - ver = GET_APIC_VERSION(v); - maxlvt = get_maxlvt(); - - v = apic_read(APIC_TASKPRI); - printk(KERN_DEBUG "... APIC TASKPRI: %08x (%02x)\n", v, v & APIC_TPRI_MASK); - - if (APIC_INTEGRATED(ver)) { /* !82489DX */ - v = apic_read(APIC_ARBPRI); - printk(KERN_DEBUG "... APIC ARBPRI: %08x (%02x)\n", v, - v & APIC_ARBPRI_MASK); - v = apic_read(APIC_PROCPRI); - printk(KERN_DEBUG "... APIC PROCPRI: %08x\n", v); - } - - v = apic_read(APIC_EOI); - printk(KERN_DEBUG "... APIC EOI: %08x\n", v); - v = apic_read(APIC_RRR); - printk(KERN_DEBUG "... APIC RRR: %08x\n", v); - v = apic_read(APIC_LDR); - printk(KERN_DEBUG "... APIC LDR: %08x\n", v); - v = apic_read(APIC_DFR); - printk(KERN_DEBUG "... APIC DFR: %08x\n", v); - v = apic_read(APIC_SPIV); - printk(KERN_DEBUG "... APIC SPIV: %08x\n", v); - - printk(KERN_DEBUG "... APIC ISR field:\n"); - print_APIC_bitfield(APIC_ISR); - printk(KERN_DEBUG "... APIC TMR field:\n"); - print_APIC_bitfield(APIC_TMR); - printk(KERN_DEBUG "... APIC IRR field:\n"); - print_APIC_bitfield(APIC_IRR); - - if (APIC_INTEGRATED(ver)) { /* !82489DX */ - if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ - apic_write(APIC_ESR, 0); - v = apic_read(APIC_ESR); - printk(KERN_DEBUG "... APIC ESR: %08x\n", v); - } - - v = apic_read(APIC_ICR); - printk(KERN_DEBUG "... APIC ICR: %08x\n", v); - v = apic_read(APIC_ICR2); - printk(KERN_DEBUG "... APIC ICR2: %08x\n", v); - - v = apic_read(APIC_LVTT); - printk(KERN_DEBUG "... APIC LVTT: %08x\n", v); - - if (maxlvt > 3) { /* PC is LVT#4. */ - v = apic_read(APIC_LVTPC); - printk(KERN_DEBUG "... APIC LVTPC: %08x\n", v); - } - v = apic_read(APIC_LVT0); - printk(KERN_DEBUG "... APIC LVT0: %08x\n", v); - v = apic_read(APIC_LVT1); - printk(KERN_DEBUG "... APIC LVT1: %08x\n", v); - - if (maxlvt > 2) { /* ERR is LVT#3. */ - v = apic_read(APIC_LVTERR); - printk(KERN_DEBUG "... APIC LVTERR: %08x\n", v); - } - - v = apic_read(APIC_TMICT); - printk(KERN_DEBUG "... APIC TMICT: %08x\n", v); - v = apic_read(APIC_TMCCT); - printk(KERN_DEBUG "... APIC TMCCT: %08x\n", v); - v = apic_read(APIC_TDCR); - printk(KERN_DEBUG "... APIC TDCR: %08x\n", v); - printk("\n"); -} - -void print_all_local_APICs (void) -{ - on_each_cpu(print_local_APIC, NULL, 1, 1); -} - -void /*__init*/ print_PIC(void) -{ - extern spinlock_t i8259A_lock; - unsigned int v; - unsigned long flags; - - if (apic_verbosity == APIC_QUIET) - return; - - printk(KERN_DEBUG "\nprinting PIC contents\n"); - - spin_lock_irqsave(&i8259A_lock, flags); - - v = inb(0xa1) << 8 | inb(0x21); - printk(KERN_DEBUG "... PIC IMR: %04x\n", v); - - v = inb(0xa0) << 8 | inb(0x20); - printk(KERN_DEBUG "... PIC IRR: %04x\n", v); - - outb(0x0b,0xa0); - outb(0x0b,0x20); - v = inb(0xa0) << 8 | inb(0x20); - outb(0x0a,0xa0); - outb(0x0a,0x20); - - spin_unlock_irqrestore(&i8259A_lock, flags); - - printk(KERN_DEBUG "... PIC ISR: %04x\n", v); - - v = inb(0x4d1) << 8 | inb(0x4d0); - printk(KERN_DEBUG "... PIC ELCR: %04x\n", v); -} -#else -void __init print_IO_APIC(void) { } -#endif /* !CONFIG_XEN */ - -static void __init enable_IO_APIC(void) -{ - union IO_APIC_reg_01 reg_01; - int i; - unsigned long flags; - - for (i = 0; i < PIN_MAP_SIZE; i++) { - irq_2_pin[i].pin = -1; - irq_2_pin[i].next = 0; - } - if (!pirqs_enabled) - for (i = 0; i < MAX_PIRQS; i++) - pirq_entries[i] = -1; - - /* - * The number of IO-APIC IRQ registers (== #pins): - */ - for (i = 0; i < nr_ioapics; i++) { - spin_lock_irqsave(&ioapic_lock, flags); - reg_01.raw = io_apic_read(i, 1); - spin_unlock_irqrestore(&ioapic_lock, flags); - nr_ioapic_registers[i] = reg_01.bits.entries+1; - } - - /* - * Do not trust the IO-APIC being empty at bootup - */ - clear_IO_APIC(); -} - -/* - * Not an __init, needed by the reboot code - */ -void disable_IO_APIC(void) -{ - /* - * Clear the IO-APIC before rebooting: - */ - clear_IO_APIC(); - -#ifndef CONFIG_XEN - disconnect_bsp_APIC(); -#endif -} - -/* - * function to set the IO-APIC physical IDs based on the - * values stored in the MPC table. - * - * by Matt Domsch <Matt_Domsch@xxxxxxxx> Tue Dec 21 12:25:05 CST 1999 - */ - -#if !defined(CONFIG_XEN) && !defined(CONFIG_X86_NUMAQ) -static void __init setup_ioapic_ids_from_mpc(void) -{ - union IO_APIC_reg_00 reg_00; - physid_mask_t phys_id_present_map; - int apic; - int i; - unsigned char old_id; - unsigned long flags; - - /* - * This is broken; anything with a real cpu count has to - * circumvent this idiocy regardless. - */ - phys_id_present_map = ioapic_phys_id_map(phys_cpu_present_map); - - /* - * Set the IOAPIC ID to the value stored in the MPC table. - */ - for (apic = 0; apic < nr_ioapics; apic++) { - - /* Read the register 0 value */ - spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(apic, 0); - spin_unlock_irqrestore(&ioapic_lock, flags); - - old_id = mp_ioapics[apic].mpc_apicid; - - if (mp_ioapics[apic].mpc_apicid >= get_physical_broadcast()) { - printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the MPC table!...\n", - apic, mp_ioapics[apic].mpc_apicid); - printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n", - reg_00.bits.ID); - mp_ioapics[apic].mpc_apicid = reg_00.bits.ID; - } - - /* Don't check I/O APIC IDs for some xAPIC systems. They have - * no meaning without the serial APIC bus. */ - if (NO_IOAPIC_CHECK) - continue; - /* - * Sanity check, is the ID really free? Every APIC in a - * system must have a unique ID or we get lots of nice - * 'stuck on smp_invalidate_needed IPI wait' messages. - */ - if (check_apicid_used(phys_id_present_map, - mp_ioapics[apic].mpc_apicid)) { - printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n", - apic, mp_ioapics[apic].mpc_apicid); - for (i = 0; i < get_physical_broadcast(); i++) - if (!physid_isset(i, phys_id_present_map)) - break; - if (i >= get_physical_broadcast()) - panic("Max APIC ID exceeded!\n"); - printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n", - i); - physid_set(i, phys_id_present_map); - mp_ioapics[apic].mpc_apicid = i; - } else { - physid_mask_t tmp; - tmp = apicid_to_cpu_present(mp_ioapics[apic].mpc_apicid); - apic_printk(APIC_VERBOSE, "Setting %d in the " - "phys_id_present_map\n", - mp_ioapics[apic].mpc_apicid); - physids_or(phys_id_present_map, phys_id_present_map, tmp); - } - - - /* - * We need to adjust the IRQ routing table - * if the ID changed. - */ - if (old_id != mp_ioapics[apic].mpc_apicid) - for (i = 0; i < mp_irq_entries; i++) - if (mp_irqs[i].mpc_dstapic == old_id) - mp_irqs[i].mpc_dstapic - = mp_ioapics[apic].mpc_apicid; - - /* - * Read the right value from the MPC table and - * write it into the ID register. - */ - apic_printk(APIC_VERBOSE, KERN_INFO - "...changing IO-APIC physical APIC ID to %d ...", - mp_ioapics[apic].mpc_apicid); - - reg_00.bits.ID = mp_ioapics[apic].mpc_apicid; - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(apic, 0, reg_00.raw); - spin_unlock_irqrestore(&ioapic_lock, flags); - - /* - * Sanity check - */ - spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(apic, 0); - spin_unlock_irqrestore(&ioapic_lock, flags); - if (reg_00.bits.ID != mp_ioapics[apic].mpc_apicid) - printk("could not set ID!\n"); - else - apic_printk(APIC_VERBOSE, " ok.\n"); - } -} -#else -static void __init setup_ioapic_ids_from_mpc(void) { } -#endif - -#ifndef CONFIG_XEN -/* - * There is a nasty bug in some older SMP boards, their mptable lies - * about the timer IRQ. We do the following to work around the situation: - * - * - timer IRQ defaults to IO-APIC IRQ - * - if this function detects that timer IRQs are defunct, then we fall - * back to ISA timer IRQs - */ -static int __init timer_irq_works(void) -{ - unsigned long t1 = jiffies; - - local_irq_enable(); - /* Let ten ticks pass... */ - mdelay((10 * 1000) / HZ); - - /* - * Expect a few ticks at least, to be sure some possible - * glue logic does not lock up after one or two first - * ticks in a non-ExtINT mode. Also the local APIC - * might have cached one ExtINT interrupt. Finally, at - * least one tick may be lost due to delays. - */ - if (jiffies - t1 > 4) - return 1; - - return 0; -} - -/* - * In the SMP+IOAPIC case it might happen that there are an unspecified - * number of pending IRQ events unhandled. These cases are very rare, - * so we 'resend' these IRQs via IPIs, to the same CPU. It's much - * better to do it this way as thus we do not have to be aware of - * 'pending' interrupts in the IRQ path, except at this point. - */ -/* - * Edge triggered needs to resend any interrupt - * that was delayed but this is now handled in the device - * independent code. - */ - -/* - * Starting up a edge-triggered IO-APIC interrupt is - * nasty - we need to make sure that we get the edge. - * If it is already asserted for some reason, we need - * return 1 to indicate that is was pending. - * - * This is not complete - we should be able to fake - * an edge even if it isn't on the 8259A... - */ -static unsigned int startup_edge_ioapic_irq(unsigned int irq) -{ - int was_pending = 0; - unsigned long flags; - - spin_lock_irqsave(&ioapic_lock, flags); - if (irq < 16) { - disable_8259A_irq(irq); - if (i8259A_irq_pending(irq)) - was_pending = 1; - } - __unmask_IO_APIC_irq(irq); - spin_unlock_irqrestore(&ioapic_lock, flags); - - return was_pending; -} - -/* - * Once we have recorded IRQ_PENDING already, we can mask the - * interrupt for real. This prevents IRQ storms from unhandled - * devices. - */ -static void ack_edge_ioapic_irq(unsigned int irq) -{ - move_irq(irq); - if ((irq_desc[irq].status & (IRQ_PENDING | IRQ_DISABLED)) - == (IRQ_PENDING | IRQ_DISABLED)) - mask_IO_APIC_irq(irq); - ack_APIC_irq(); -} - -/* - * Level triggered interrupts can just be masked, - * and shutting down and starting up the interrupt - * is the same as enabling and disabling them -- except - * with a startup need to return a "was pending" value. - * - * Level triggered interrupts are special because we - * do not touch any IO-APIC register while handling - * them. We ack the APIC in the end-IRQ handler, not - * in the start-IRQ-handler. Protection against reentrance - * from the same interrupt is still provided, both by the - * generic IRQ layer and by the fact that an unacked local - * APIC does not accept IRQs. - */ -static unsigned int startup_level_ioapic_irq (unsigned int irq) -{ - unmask_IO_APIC_irq(irq); - - return 0; /* don't check for pending */ -} - -static void end_level_ioapic_irq (unsigned int irq) -{ - unsigned long v; - int i; - - move_irq(irq); -/* - * It appears there is an erratum which affects at least version 0x11 - * of I/O APIC (that's the 82093AA and cores integrated into various - * chipsets). Under certain conditions a level-triggered interrupt is - * erroneously delivered as edge-triggered one but the respective IRR - * bit gets set nevertheless. As a result the I/O unit expects an EOI - * message but it will never arrive and further interrupts are blocked - * from the source. The exact reason is so far unknown, but the - * phenomenon was observed when two consecutive interrupt requests - * from a given source get delivered to the same CPU and the source is - * temporarily disabled in between. - * - * A workaround is to simulate an EOI message manually. We achieve it - * by setting the trigger mode to edge and then to level when the edge - * trigger mode gets detected in the TMR of a local APIC for a - * level-triggered interrupt. We mask the source for the time of the - * operation to prevent an edge-triggered interrupt escaping meanwhile. - * The idea is from Manfred Spraul. --macro - */ - i = IO_APIC_VECTOR(irq); - - v = apic_read(APIC_TMR + ((i & ~0x1f) >> 1)); - - ack_APIC_irq(); - - if (!(v & (1 << (i & 0x1f)))) { - atomic_inc(&irq_mis_count); - spin_lock(&ioapic_lock); - __mask_and_edge_IO_APIC_irq(irq); - __unmask_and_level_IO_APIC_irq(irq); - spin_unlock(&ioapic_lock); - } -} - -#ifdef CONFIG_PCI_MSI -static unsigned int startup_edge_ioapic_vector(unsigned int vector) -{ - int irq = vector_to_irq(vector); - - return startup_edge_ioapic_irq(irq); -} - -static void ack_edge_ioapic_vector(unsigned int vector) -{ - int irq = vector_to_irq(vector); - - ack_edge_ioapic_irq(irq); -} - -static unsigned int startup_level_ioapic_vector (unsigned int vector) -{ - int irq = vector_to_irq(vector); - - return startup_level_ioapic_irq (irq); -} - -static void end_level_ioapic_vector (unsigned int vector) -{ - int irq = vector_to_irq(vector); - - end_level_ioapic_irq(irq); -} - -static void mask_IO_APIC_vector (unsigned int vector) -{ - int irq = vector_to_irq(vector); - - mask_IO_APIC_irq(irq); -} - -static void unmask_IO_APIC_vector (unsigned int vector) -{ - int irq = vector_to_irq(vector); - - unmask_IO_APIC_irq(irq); -} - -static void set_ioapic_affinity_vector (unsigned int vector, - cpumask_t cpu_mask) -{ - int irq = vector_to_irq(vector); - - set_ioapic_affinity_irq(irq, cpu_mask); -} -#endif - -/* - * Level and edge triggered IO-APIC interrupts need different handling, - * so we use two separate IRQ descriptors. Edge triggered IRQs can be - * handled with the level-triggered descriptor, but that one has slightly - * more overhead. Level-triggered interrupts cannot be handled with the - * edge-triggered handler, without risking IRQ storms and other ugly - * races. - */ -static struct hw_interrupt_type ioapic_edge_type = { - .typename = "IO-APIC-edge", - .startup = startup_edge_ioapic, - .shutdown = shutdown_edge_ioapic, - .enable = enable_edge_ioapic, - .disable = disable_edge_ioapic, - .ack = ack_edge_ioapic, - .end = end_edge_ioapic, - .set_affinity = set_ioapic_affinity, -}; - -static struct hw_interrupt_type ioapic_level_type = { - .typename = "IO-APIC-level", - .startup = startup_level_ioapic, - .shutdown = shutdown_level_ioapic, - .enable = enable_level_ioapic, - .disable = disable_level_ioapic, - .ack = mask_and_ack_level_ioapic, - .end = end_level_ioapic, - .set_affinity = set_ioapic_affinity, -}; -#endif /* !CONFIG_XEN */ - -static inline void init_IO_APIC_traps(void) -{ - int irq; - - /* - * NOTE! The local APIC isn't very good at handling - * multiple interrupts at the same interrupt level. - * As the interrupt level is determined by taking the - * vector number and shifting that right by 4, we - * want to spread these out a bit so that they don't - * all fall in the same interrupt level. - * - * Also, we've got to be careful not to trash gate - * 0x80, because int 0x80 is hm, kind of importantish. ;) - */ - for (irq = 0; irq < NR_IRQS ; irq++) { - int tmp = irq; - if (use_pci_vector()) { - if (!platform_legacy_irq(tmp)) - if ((tmp = vector_to_irq(tmp)) == -1) - continue; - } - if (IO_APIC_IRQ(tmp) && !IO_APIC_VECTOR(tmp)) { - /* - * Hmm.. We don't have an entry for this, - * so default to an old-fashioned 8259 - * interrupt if we can.. - */ - if (irq < 16) - make_8259A_irq(irq); -#ifndef CONFIG_XEN - else - /* Strange. Oh, well.. */ - irq_desc[irq].handler = &no_irq_type; -#endif - } - } -} - -#ifndef CONFIG_XEN -static void enable_lapic_irq (unsigned int irq) -{ - unsigned long v; - - v = apic_read(APIC_LVT0); - apic_write_around(APIC_LVT0, v & ~APIC_LVT_MASKED); -} - -static void disable_lapic_irq (unsigned int irq) -{ - unsigned long v; - - v = apic_read(APIC_LVT0); - apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED); -} - -static void ack_lapic_irq (unsigned int irq) -{ - ack_APIC_irq(); -} - -static void end_lapic_irq (unsigned int i) { /* nothing */ } - -static struct hw_interrupt_type lapic_irq_type = { - .typename = "local-APIC-edge", - .startup = NULL, /* startup_irq() not used for IRQ0 */ - .shutdown = NULL, /* shutdown_irq() not used for IRQ0 */ - .enable = enable_lapic_irq, - .disable = disable_lapic_irq, - .ack = ack_lapic_irq, - .end = end_lapic_irq -}; - -static void setup_nmi (void) -{ - /* - * Dirty trick to enable the NMI watchdog ... - * We put the 8259A master into AEOI mode and - * unmask on all local APICs LVT0 as NMI. - * - * The idea to use the 8259A in AEOI mode ('8259A Virtual Wire') - * is from Maciej W. Rozycki - so we do not have to EOI from - * the NMI handler or the timer interrupt. - */ - apic_printk(APIC_VERBOSE, KERN_INFO "activating NMI Watchdog ..."); - - on_each_cpu(enable_NMI_through_LVT0, NULL, 1, 1); - - apic_printk(APIC_VERBOSE, " done.\n"); -} - -/* - * This looks a bit hackish but it's about the only one way of sending - * a few INTA cycles to 8259As and any associated glue logic. ICR does - * not support the ExtINT mode, unfortunately. We need to send these - * cycles as some i82489DX-based boards have glue logic that keeps the - * 8259A interrupt line asserted until INTA. --macro - */ -static inline void unlock_ExtINT_logic(void) -{ - int pin, i; - struct IO_APIC_route_entry entry0, entry1; - unsigned char save_control, save_freq_select; - unsigned long flags; - - pin = find_isa_irq_pin(8, mp_INT); - if (pin == -1) - return; - - spin_lock_irqsave(&ioapic_lock, flags); - *(((int *)&entry0) + 1) = io_apic_read(0, 0x11 + 2 * pin); - *(((int *)&entry0) + 0) = io_apic_read(0, 0x10 + 2 * pin); - spin_unlock_irqrestore(&ioapic_lock, flags); - clear_IO_APIC_pin(0, pin); - - memset(&entry1, 0, sizeof(entry1)); - - entry1.dest_mode = 0; /* physical delivery */ - entry1.mask = 0; /* unmask IRQ now */ - entry1.dest.physical.physical_dest = hard_smp_processor_id(); - entry1.delivery_mode = dest_ExtINT; - entry1.polarity = entry0.polarity; - entry1.trigger = 0; - entry1.vector = 0; - - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry1) + 1)); - io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry1) + 0)); - spin_unlock_irqrestore(&ioapic_lock, flags); - - save_control = CMOS_READ(RTC_CONTROL); - save_freq_select = CMOS_READ(RTC_FREQ_SELECT); - CMOS_WRITE((save_freq_select & ~RTC_RATE_SELECT) | 0x6, - RTC_FREQ_SELECT); - CMOS_WRITE(save_control | RTC_PIE, RTC_CONTROL); - - i = 100; - while (i-- > 0) { - mdelay(10); - if ((CMOS_READ(RTC_INTR_FLAGS) & RTC_PF) == RTC_PF) - i -= 10; - } - - CMOS_WRITE(save_control, RTC_CONTROL); - CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); - clear_IO_APIC_pin(0, pin); - - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry0) + 1)); - io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry0) + 0)); - spin_unlock_irqrestore(&ioapic_lock, flags); -} - -/* - * This code may look a bit paranoid, but it's supposed to cooperate with - * a wide range of boards and BIOS bugs. Fortunately only the timer IRQ - * is so screwy. Thanks to Brian Perkins for testing/hacking this beast - * fanatically on his truly buggy board. - */ -static inline void check_timer(void) -{ - int pin1, pin2; - int vector; - - /* - * get/set the timer IRQ vector: - */ - disable_8259A_irq(0); - vector = assign_irq_vector(0); - set_intr_gate(vector, interrupt[0]); - - /* - * Subtle, code in do_timer_interrupt() expects an AEOI - * mode for the 8259A whenever interrupts are routed - * through I/O APICs. Also IRQ0 has to be enabled in - * the 8259A which implies the virtual wire has to be - * disabled in the local APIC. - */ - apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); - init_8259A(1); - timer_ack = 1; - enable_8259A_irq(0); - - pin1 = find_isa_irq_pin(0, mp_INT); - pin2 = find_isa_irq_pin(0, mp_ExtINT); - - printk(KERN_INFO "..TIMER: vector=0x%02X pin1=%d pin2=%d\n", vector, pin1, pin2); - - if (pin1 != -1) { - /* - * Ok, does IRQ0 through the IOAPIC work? - */ - unmask_IO_APIC_irq(0); - if (timer_irq_works()) { - if (nmi_watchdog == NMI_IO_APIC) { - disable_8259A_irq(0); - setup_nmi(); - enable_8259A_irq(0); - } - return; - } - clear_IO_APIC_pin(0, pin1); - printk(KERN_ERR "..MP-BIOS bug: 8254 timer not connected to IO-APIC\n"); - } - - printk(KERN_INFO "...trying to set up timer (IRQ0) through the 8259A ... "); - if (pin2 != -1) { - printk("\n..... (found pin %d) ...", pin2); - /* - * legacy devices should be connected to IO APIC #0 - */ - setup_ExtINT_IRQ0_pin(pin2, vector); - if (timer_irq_works()) { - printk("works.\n"); - if (pin1 != -1) - replace_pin_at_irq(0, 0, pin1, 0, pin2); - else - add_pin_to_irq(0, 0, pin2); - if (nmi_watchdog == NMI_IO_APIC) { - setup_nmi(); - } - return; - } - /* - * Cleanup, just in case ... - */ - clear_IO_APIC_pin(0, pin2); - } - printk(" failed.\n"); - - if (nmi_watchdog == NMI_IO_APIC) { - printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n"); - nmi_watchdog = 0; - } - - printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ..."); - - disable_8259A_irq(0); - irq_desc[0].handler = &lapic_irq_type; - apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector); /* Fixed mode */ - enable_8259A_irq(0); - - if (timer_irq_works()) { - printk(" works.\n"); - return; - } - apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | vector); - printk(" failed.\n"); - - printk(KERN_INFO "...trying to set up timer as ExtINT IRQ..."); - - timer_ack = 0; - init_8259A(0); - make_8259A_irq(0); - apic_write_around(APIC_LVT0, APIC_DM_EXTINT); - - unlock_ExtINT_logic(); - - if (timer_irq_works()) { - printk(" works.\n"); - return; - } - printk(" failed :(.\n"); - panic("IO-APIC + timer doesn't work! Boot with apic=debug and send a " - "report. Then try booting with the 'noapic' option"); -} -#else -#define check_timer() ((void)0) -#endif - -/* - * - * IRQ's that are handled by the PIC in the MPS IOAPIC case. - * - IRQ2 is the cascade IRQ, and cannot be a io-apic IRQ. - * Linux doesn't really care, as it's not actually used - * for any interrupt handling anyway. - */ -#define PIC_IRQS (1 << PIC_CASCADE_IR) - -void __init setup_IO_APIC(void) -{ - enable_IO_APIC(); - - if (acpi_ioapic) - io_apic_irqs = ~0; /* all IRQs go through IOAPIC */ - else - io_apic_irqs = ~PIC_IRQS; - - printk("ENABLING IO-APIC IRQs\n"); - - /* - * Set up IO-APIC IRQ routing. - */ - if (!acpi_ioapic) - setup_ioapic_ids_from_mpc(); -#ifndef CONFIG_XEN - sync_Arb_IDs(); -#endif - setup_IO_APIC_irqs(); - init_IO_APIC_traps(); - check_timer(); - if (!acpi_ioapic) - print_IO_APIC(); -} - -/* - * Called after all the initialization is done. If we didnt find any - * APIC bugs then we can allow the modify fast path - */ - -static int __init io_apic_bug_finalize(void) -{ - if(sis_apic_bug == -1) - sis_apic_bug = 0; - return 0; -} - -late_initcall(io_apic_bug_finalize); - -struct sysfs_ioapic_data { - struct sys_device dev; - struct IO_APIC_route_entry entry[0]; -}; -static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS]; - -static int ioapic_suspend(struct sys_device *dev, pm_message_t state) -{ - struct IO_APIC_route_entry *entry; - struct sysfs_ioapic_data *data; - unsigned long flags; - int i; - - data = container_of(dev, struct sysfs_ioapic_data, dev); - entry = data->entry; - spin_lock_irqsave(&ioapic_lock, flags); - for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) { - *(((int *)entry) + 1) = io_apic_read(dev->id, 0x11 + 2 * i); - *(((int *)entry) + 0) = io_apic_read(dev->id, 0x10 + 2 * i); - } - spin_unlock_irqrestore(&ioapic_lock, flags); - - return 0; -} - -static int ioapic_resume(struct sys_device *dev) -{ - struct IO_APIC_route_entry *entry; - struct sysfs_ioapic_data *data; - unsigned long flags; - union IO_APIC_reg_00 reg_00; - int i; - - data = container_of(dev, struct sysfs_ioapic_data, dev); - entry = data->entry; - - spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(dev->id, 0); - if (reg_00.bits.ID != mp_ioapics[dev->id].mpc_apicid) { - reg_00.bits.ID = mp_ioapics[dev->id].mpc_apicid; - io_apic_write(dev->id, 0, reg_00.raw); - } - for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) { - io_apic_write(dev->id, 0x11+2*i, *(((int *)entry)+1)); - io_apic_write(dev->id, 0x10+2*i, *(((int *)entry)+0)); - } - spin_unlock_irqrestore(&ioapic_lock, flags); - - return 0; -} - -static struct sysdev_class ioapic_sysdev_class = { - set_kset_name("ioapic"), - .suspend = ioapic_suspend, - .resume = ioapic_resume, -}; - -static int __init ioapic_init_sysfs(void) -{ - struct sys_device * dev; - int i, size, error = 0; - - error = sysdev_class_register(&ioapic_sysdev_class); - if (error) - return error; - - for (i = 0; i < nr_ioapics; i++ ) { - size = sizeof(struct sys_device) + nr_ioapic_registers[i] - * sizeof(struct IO_APIC_route_entry); - mp_ioapic_data[i] = kmalloc(size, GFP_KERNEL); - if (!mp_ioapic_data[i]) { - printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i); - continue; - } - memset(mp_ioapic_data[i], 0, size); - dev = &mp_ioapic_data[i]->dev; - dev->id = i; - dev->cls = &ioapic_sysdev_class; - error = sysdev_register(dev); - if (error) { - kfree(mp_ioapic_data[i]); - mp_ioapic_data[i] = NULL; - printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i); - continue; - } - } - - return 0; -} - -device_initcall(ioapic_init_sysfs); - -/* -------------------------------------------------------------------------- - ACPI-based IOAPIC Configuration - -------------------------------------------------------------------------- */ - -#ifdef CONFIG_ACPI_BOOT - -int __init io_apic_get_unique_id (int ioapic, int apic_id) -{ -#ifndef CONFIG_XEN - union IO_APIC_reg_00 reg_00; - static physid_mask_t apic_id_map = PHYSID_MASK_NONE; - physid_mask_t tmp; - unsigned long flags; - int i = 0; - - /* - * The P4 platform supports up to 256 APIC IDs on two separate APIC - * buses (one for LAPICs, one for IOAPICs), where predecessors only - * supports up to 16 on one shared APIC bus. - * - * TBD: Expand LAPIC/IOAPIC support on P4-class systems to take full - * advantage of new APIC bus architecture. - */ - - if (physids_empty(apic_id_map)) - apic_id_map = ioapic_phys_id_map(phys_cpu_present_map); - - spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(ioapic, 0); - spin_unlock_irqrestore(&ioapic_lock, flags); - - if (apic_id >= get_physical_broadcast()) { - printk(KERN_WARNING "IOAPIC[%d]: Invalid apic_id %d, trying " - "%d\n", ioapic, apic_id, reg_00.bits.ID); - apic_id = reg_00.bits.ID; - } - - /* - * Every APIC in a system must have a unique ID or we get lots of nice - * 'stuck on smp_invalidate_needed IPI wait' messages. - */ - if (check_apicid_used(apic_id_map, apic_id)) { - - for (i = 0; i < get_physical_broadcast(); i++) { - if (!check_apicid_used(apic_id_map, i)) - break; - } - - if (i == get_physical_broadcast()) - panic("Max apic_id exceeded!\n"); - - printk(KERN_WARNING "IOAPIC[%d]: apic_id %d already used, " - "trying %d\n", ioapic, apic_id, i); - - apic_id = i; - } - - tmp = apicid_to_cpu_present(apic_id); - physids_or(apic_id_map, apic_id_map, tmp); - - if (reg_00.bits.ID != apic_id) { - reg_00.bits.ID = apic_id; - - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(ioapic, 0, reg_00.raw); - reg_00.raw = io_apic_read(ioapic, 0); - spin_unlock_irqrestore(&ioapic_lock, flags); - - /* Sanity check */ - if (reg_00.bits.ID != apic_id) - panic("IOAPIC[%d]: Unable change apic_id!\n", ioapic); - } - - apic_printk(APIC_VERBOSE, KERN_INFO - "IOAPIC[%d]: Assigned apic_id %d\n", ioapic, apic_id); -#endif /* !CONFIG_XEN */ - - return apic_id; -} - - -int __init io_apic_get_version (int ioapic) -{ - union IO_APIC_reg_01 reg_01; - unsigned long flags; - - spin_lock_irqsave(&ioapic_lock, flags); - reg_01.raw = io_apic_read(ioapic, 1); - spin_unlock_irqrestore(&ioapic_lock, flags); - - return reg_01.bits.version; -} - - -int __init io_apic_get_redir_entries (int ioapic) -{ - union IO_APIC_reg_01 reg_01; - unsigned long flags; - - spin_lock_irqsave(&ioapic_lock, flags); - reg_01.raw = io_apic_read(ioapic, 1); - spin_unlock_irqrestore(&ioapic_lock, flags); - - return reg_01.bits.entries; -} - - -int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int active_high_low) -{ - struct IO_APIC_route_entry entry; - unsigned long flags; - - if (!IO_APIC_IRQ(irq)) { - printk(KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n", - ioapic); - return -EINVAL; - } - - /* - * Generate a PCI IRQ routing entry and program the IOAPIC accordingly. - * Note that we mask (disable) IRQs now -- these get enabled when the - * corresponding device driver registers for this IRQ. - */ - - memset(&entry,0,sizeof(entry)); - - entry.delivery_mode = INT_DELIVERY_MODE; - entry.dest_mode = INT_DEST_MODE; - entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS); - entry.trigger = edge_level; - entry.polarity = active_high_low; - entry.mask = 1; - - /* - * IRQs < 16 are already in the irq_2_pin[] map - */ - if (irq >= 16) - add_pin_to_irq(irq, ioapic, pin); - - entry.vector = assign_irq_vector(irq); - - apic_printk(APIC_DEBUG, KERN_DEBUG "IOAPIC[%d]: Set PCI routing entry " - "(%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i)\n", ioapic, - mp_ioapics[ioapic].mpc_apicid, pin, entry.vector, irq, - edge_level, active_high_low); - - ioapic_register_intr(irq, entry.vector, edge_level); - - if (!ioapic && (irq < 16)) - disable_8259A_irq(irq); - - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(ioapic, 0x11+2*pin, *(((int *)&entry)+1)); - io_apic_write(ioapic, 0x10+2*pin, *(((int *)&entry)+0)); - spin_unlock_irqrestore(&ioapic_lock, flags); - - return 0; -} - -#endif /*CONFIG_ACPI_BOOT*/ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/ioport.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/ioport.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,125 +0,0 @@ -/* - * linux/arch/i386/kernel/ioport.c - * - * This contains the io-permission bitmap code - written by obz, with changes - * by Linus. - */ - -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/types.h> -#include <linux/ioport.h> -#include <linux/smp.h> -#include <linux/smp_lock.h> -#include <linux/stddef.h> -#include <linux/slab.h> -#include <linux/thread_info.h> -#include <asm-xen/xen-public/physdev.h> - -/* Set EXTENT bits starting at BASE in BITMAP to value TURN_ON. */ -static void set_bitmap(unsigned long *bitmap, unsigned int base, unsigned int extent, int new_value) -{ - unsigned long mask; - unsigned long *bitmap_base = bitmap + (base / BITS_PER_LONG); - unsigned int low_index = base & (BITS_PER_LONG-1); - int length = low_index + extent; - - if (low_index != 0) { - mask = (~0UL << low_index); - if (length < BITS_PER_LONG) - mask &= ~(~0UL << length); - if (new_value) - *bitmap_base++ |= mask; - else - *bitmap_base++ &= ~mask; - length -= BITS_PER_LONG; - } - - mask = (new_value ? ~0UL : 0UL); - while (length >= BITS_PER_LONG) { - *bitmap_base++ = mask; - length -= BITS_PER_LONG; - } - - if (length > 0) { - mask = ~(~0UL << length); - if (new_value) - *bitmap_base++ |= mask; - else - *bitmap_base++ &= ~mask; - } -} - - -/* - * this changes the io permissions bitmap in the current task. - */ -asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) -{ - struct thread_struct * t = &current->thread; - unsigned long *bitmap; - physdev_op_t op; - - if ((from + num <= from) || (from + num > IO_BITMAP_BITS)) - return -EINVAL; - if (turn_on && !capable(CAP_SYS_RAWIO)) - return -EPERM; - - /* - * If it's the first ioperm() call in this thread's lifetime, set the - * IO bitmap up. ioperm() is much less timing critical than clone(), - * this is why we delay this operation until now: - */ - if (!t->io_bitmap_ptr) { - bitmap = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL); - if (!bitmap) - return -ENOMEM; - - memset(bitmap, 0xff, IO_BITMAP_BYTES); - t->io_bitmap_ptr = bitmap; - - op.cmd = PHYSDEVOP_SET_IOBITMAP; - op.u.set_iobitmap.bitmap = (char *)bitmap; - op.u.set_iobitmap.nr_ports = IO_BITMAP_BITS; - HYPERVISOR_physdev_op(&op); - } - - set_bitmap(t->io_bitmap_ptr, from, num, !turn_on); - - return 0; -} - -/* - * sys_iopl has to be used when you want to access the IO ports - * beyond the 0x3ff range: to get the full 65536 ports bitmapped - * you'd need 8kB of bitmaps/process, which is a bit excessive. - * - * Here we just change the eflags value on the stack: we allow - * only the super-user to do it. This depends on the stack-layout - * on system-call entry - see also fork() and the signal handling - * code. - */ - -asmlinkage long sys_iopl(unsigned int new_io_pl) -{ - unsigned int old_io_pl = current->thread.io_pl; - physdev_op_t op; - - if (new_io_pl > 3) - return -EINVAL; - - /* Need "raw I/O" privileges for direct port access. */ - if ((new_io_pl > old_io_pl) && !capable(CAP_SYS_RAWIO)) - return -EPERM; - - /* Change our version of the privilege levels. */ - current->thread.io_pl = new_io_pl; - - /* Force the change at ring 0. */ - op.cmd = PHYSDEVOP_SET_IOPL; - op.u.set_iopl.iopl = (new_io_pl == 0) ? 1 : new_io_pl; - HYPERVISOR_physdev_op(&op); - - return 0; -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/irq.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/irq.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,300 +0,0 @@ -/* - * linux/arch/i386/kernel/irq.c - * - * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar - * - * This file contains the lowest level x86-specific interrupt - * entry, irq-stacks and irq statistics code. All the remaining - * irq logic is done by the generic kernel/irq/ code and - * by the x86-specific irq controller code. (e.g. i8259.c and - * io_apic.c.) - */ - -#include <asm/uaccess.h> -#include <linux/module.h> -#include <linux/seq_file.h> -#include <linux/interrupt.h> -#include <linux/kernel_stat.h> -#include <linux/notifier.h> -#include <linux/cpu.h> -#include <linux/delay.h> - -DEFINE_PER_CPU(irq_cpustat_t, irq_stat) ____cacheline_maxaligned_in_smp; -EXPORT_PER_CPU_SYMBOL(irq_stat); - -#ifndef CONFIG_X86_LOCAL_APIC -/* - * 'what should we do if we get a hw irq event on an illegal vector'. - * each architecture has to answer this themselves. - */ -void ack_bad_irq(unsigned int irq) -{ - printk("unexpected IRQ trap at vector %02x\n", irq); -} -#endif - -#ifdef CONFIG_4KSTACKS -/* - * per-CPU IRQ handling contexts (thread information and stack) - */ -union irq_ctx { - struct thread_info tinfo; - u32 stack[THREAD_SIZE/sizeof(u32)]; -}; - -static union irq_ctx *hardirq_ctx[NR_CPUS]; -static union irq_ctx *softirq_ctx[NR_CPUS]; -#endif - -/* - * do_IRQ handles all normal device IRQ's (the special - * SMP cross-CPU interrupts have their own specific - * handlers). - */ -fastcall unsigned int do_IRQ(struct pt_regs *regs) -{ - /* high bits used in ret_from_ code */ - int irq = regs->orig_eax & __IRQ_MASK(HARDIRQ_BITS); -#ifdef CONFIG_4KSTACKS - union irq_ctx *curctx, *irqctx; - u32 *isp; -#endif - - irq_enter(); -#ifdef CONFIG_DEBUG_STACKOVERFLOW - /* Debugging check for stack overflow: is there less than 1KB free? */ - { - long esp; - - __asm__ __volatile__("andl %%esp,%0" : - "=r" (esp) : "0" (THREAD_SIZE - 1)); - if (unlikely(esp < (sizeof(struct thread_info) + STACK_WARN))) { - printk("do_IRQ: stack overflow: %ld\n", - esp - sizeof(struct thread_info)); - dump_stack(); - } - } -#endif - -#ifdef CONFIG_4KSTACKS - - curctx = (union irq_ctx *) current_thread_info(); - irqctx = hardirq_ctx[smp_processor_id()]; - - /* - * this is where we switch to the IRQ stack. However, if we are - * already using the IRQ stack (because we interrupted a hardirq - * handler) we can't do that and just have to keep using the - * current stack (which is the irq stack already after all) - */ - if (curctx != irqctx) { - int arg1, arg2, ebx; - - /* build the stack frame on the IRQ stack */ - isp = (u32*) ((char*)irqctx + sizeof(*irqctx)); - irqctx->tinfo.task = curctx->tinfo.task; - irqctx->tinfo.previous_esp = current_stack_pointer; - - asm volatile( - " xchgl %%ebx,%%esp \n" - " call __do_IRQ \n" - " movl %%ebx,%%esp \n" - : "=a" (arg1), "=d" (arg2), "=b" (ebx) - : "0" (irq), "1" (regs), "2" (isp) - : "memory", "cc", "ecx" - ); - } else -#endif - __do_IRQ(irq, regs); - - irq_exit(); - - return 1; -} - -#ifdef CONFIG_4KSTACKS - -/* - * These should really be __section__(".bss.page_aligned") as well, but - * gcc's 3.0 and earlier don't handle that correctly. - */ -static char softirq_stack[NR_CPUS * THREAD_SIZE] - __attribute__((__aligned__(THREAD_SIZE))); - -static char hardirq_stack[NR_CPUS * THREAD_SIZE] - __attribute__((__aligned__(THREAD_SIZE))); - -/* - * allocate per-cpu stacks for hardirq and for softirq processing - */ -void irq_ctx_init(int cpu) -{ - union irq_ctx *irqctx; - - if (hardirq_ctx[cpu]) - return; - - irqctx = (union irq_ctx*) &hardirq_stack[cpu*THREAD_SIZE]; - irqctx->tinfo.task = NULL; - irqctx->tinfo.exec_domain = NULL; - irqctx->tinfo.cpu = cpu; - irqctx->tinfo.preempt_count = HARDIRQ_OFFSET; - irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); - - hardirq_ctx[cpu] = irqctx; - - irqctx = (union irq_ctx*) &softirq_stack[cpu*THREAD_SIZE]; - irqctx->tinfo.task = NULL; - irqctx->tinfo.exec_domain = NULL; - irqctx->tinfo.cpu = cpu; - irqctx->tinfo.preempt_count = SOFTIRQ_OFFSET; - irqctx->tinfo.addr_limit = MAKE_MM_SEG(0); - - softirq_ctx[cpu] = irqctx; - - printk("CPU %u irqstacks, hard=%p soft=%p\n", - cpu,hardirq_ctx[cpu],softirq_ctx[cpu]); -} - -extern asmlinkage void __do_softirq(void); - -asmlinkage void do_softirq(void) -{ - unsigned long flags; - struct thread_info *curctx; - union irq_ctx *irqctx; - u32 *isp; - - if (in_interrupt()) - return; - - local_irq_save(flags); - - if (local_softirq_pending()) { - curctx = current_thread_info(); - irqctx = softirq_ctx[smp_processor_id()]; - irqctx->tinfo.task = curctx->task; - irqctx->tinfo.previous_esp = current_stack_pointer; - - /* build the stack frame on the softirq stack */ - isp = (u32*) ((char*)irqctx + sizeof(*irqctx)); - - asm volatile( - " xchgl %%ebx,%%esp \n" - " call __do_softirq \n" - " movl %%ebx,%%esp \n" - : "=b"(isp) - : "0"(isp) - : "memory", "cc", "edx", "ecx", "eax" - ); - } - - local_irq_restore(flags); -} - -EXPORT_SYMBOL(do_softirq); -#endif - -/* - * Interrupt statistics: - */ - -atomic_t irq_err_count; - -/* - * /proc/interrupts printing: - */ - -int show_interrupts(struct seq_file *p, void *v) -{ - int i = *(loff_t *) v, j; - struct irqaction * action; - unsigned long flags; - - if (i == 0) { - seq_printf(p, " "); - for_each_cpu(j) - seq_printf(p, "CPU%d ",j); - seq_putc(p, '\n'); - } - - if (i < NR_IRQS) { - spin_lock_irqsave(&irq_desc[i].lock, flags); - action = irq_desc[i].action; - if (!action) - goto skip; - seq_printf(p, "%3d: ",i); -#ifndef CONFIG_SMP - seq_printf(p, "%10u ", kstat_irqs(i)); -#else - for_each_cpu(j) - seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]); -#endif - seq_printf(p, " %14s", irq_desc[i].handler->typename); - seq_printf(p, " %s", action->name); - - for (action=action->next; action; action = action->next) - seq_printf(p, ", %s", action->name); - - seq_putc(p, '\n'); -skip: - spin_unlock_irqrestore(&irq_desc[i].lock, flags); - } else if (i == NR_IRQS) { - seq_printf(p, "NMI: "); - for_each_cpu(j) - seq_printf(p, "%10u ", nmi_count(j)); - seq_putc(p, '\n'); -#ifdef CONFIG_X86_LOCAL_APIC - seq_printf(p, "LOC: "); - for_each_cpu(j) - seq_printf(p, "%10u ", per_cpu(irq_stat,j).apic_timer_irqs); - seq_putc(p, '\n'); -#endif - seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count)); -#if defined(CONFIG_X86_IO_APIC) - seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count)); -#endif - } - return 0; -} - -#ifdef CONFIG_HOTPLUG_CPU - -void fixup_irqs(cpumask_t map) -{ - unsigned int irq; - static int warned; - - for (irq = 0; irq < NR_IRQS; irq++) { - cpumask_t mask; - if (irq == 2) - continue; - - cpus_and(mask, irq_affinity[irq], map); - if (any_online_cpu(mask) == NR_CPUS) { - /*printk("Breaking affinity for irq %i\n", irq);*/ - mask = map; - } - if (irq_desc[irq].handler->set_affinity) - irq_desc[irq].handler->set_affinity(irq, mask); - else if (irq_desc[irq].action && !(warned++)) - printk("Cannot set affinity for irq %i\n", irq); - } - -#if 0 - barrier(); - /* Ingo Molnar says: "after the IO-APIC masks have been redirected - [note the nop - the interrupt-enable boundary on x86 is two - instructions from sti] - to flush out pending hardirqs and - IPIs. After this point nothing is supposed to reach this CPU." */ - __asm__ __volatile__("sti; nop; cli"); - barrier(); -#else - /* That doesn't seem sufficient. Give it 1ms. */ - local_irq_enable(); - mdelay(1); - local_irq_disable(); -#endif -} -#endif - diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/ldt.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/ldt.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,268 +0,0 @@ -/* - * linux/kernel/ldt.c - * - * Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds - * Copyright (C) 1999 Ingo Molnar <mingo@xxxxxxxxxx> - */ - -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/string.h> -#include <linux/mm.h> -#include <linux/smp.h> -#include <linux/smp_lock.h> -#include <linux/vmalloc.h> -#include <linux/slab.h> - -#include <asm/uaccess.h> -#include <asm/system.h> -#include <asm/ldt.h> -#include <asm/desc.h> - -#ifdef CONFIG_SMP /* avoids "defined but not used" warnig */ -static void flush_ldt(void *null) -{ - if (current->active_mm) - load_LDT(&current->active_mm->context); -} -#endif - -static int alloc_ldt(mm_context_t *pc, int mincount, int reload) -{ - void *oldldt; - void *newldt; - int oldsize; - - if (mincount <= pc->size) - return 0; - oldsize = pc->size; - mincount = (mincount+511)&(~511); - if (mincount*LDT_ENTRY_SIZE > PAGE_SIZE) - newldt = vmalloc(mincount*LDT_ENTRY_SIZE); - else - newldt = kmalloc(mincount*LDT_ENTRY_SIZE, GFP_KERNEL); - - if (!newldt) - return -ENOMEM; - - if (oldsize) - memcpy(newldt, pc->ldt, oldsize*LDT_ENTRY_SIZE); - oldldt = pc->ldt; - memset(newldt+oldsize*LDT_ENTRY_SIZE, 0, (mincount-oldsize)*LDT_ENTRY_SIZE); - pc->ldt = newldt; - wmb(); - pc->size = mincount; - wmb(); - - if (reload) { -#ifdef CONFIG_SMP - cpumask_t mask; - preempt_disable(); -#endif - make_pages_readonly( - pc->ldt, - (pc->size * LDT_ENTRY_SIZE) / PAGE_SIZE, - XENFEAT_writable_descriptor_tables); - load_LDT(pc); -#ifdef CONFIG_SMP - mask = cpumask_of_cpu(smp_processor_id()); - if (!cpus_equal(current->mm->cpu_vm_mask, mask)) - smp_call_function(flush_ldt, NULL, 1, 1); - preempt_enable(); -#endif - } - if (oldsize) { - make_pages_writable( - oldldt, - (oldsize * LDT_ENTRY_SIZE) / PAGE_SIZE, - XENFEAT_writable_descriptor_tables); - if (oldsize*LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(oldldt); - else - kfree(oldldt); - } - return 0; -} - -static inline int copy_ldt(mm_context_t *new, mm_context_t *old) -{ - int err = alloc_ldt(new, old->size, 0); - if (err < 0) - return err; - memcpy(new->ldt, old->ldt, old->size*LDT_ENTRY_SIZE); - make_pages_readonly( - new->ldt, - (new->size * LDT_ENTRY_SIZE) / PAGE_SIZE, - XENFEAT_writable_descriptor_tables); - return 0; -} - -/* - * we do not have to muck with descriptors here, that is - * done in switch_mm() as needed. - */ -int init_new_context(struct task_struct *tsk, struct mm_struct *mm) -{ - struct mm_struct * old_mm; - int retval = 0; - - init_MUTEX(&mm->context.sem); - mm->context.size = 0; - old_mm = current->mm; - if (old_mm && old_mm->context.size > 0) { - down(&old_mm->context.sem); - retval = copy_ldt(&mm->context, &old_mm->context); - up(&old_mm->context.sem); - } - return retval; -} - -/* - * No need to lock the MM as we are the last user - */ -void destroy_context(struct mm_struct *mm) -{ - if (mm->context.size) { - if (mm == current->active_mm) - clear_LDT(); - make_pages_writable( - mm->context.ldt, - (mm->context.size * LDT_ENTRY_SIZE) / PAGE_SIZE, - XENFEAT_writable_descriptor_tables); - if (mm->context.size*LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(mm->context.ldt); - else - kfree(mm->context.ldt); - mm->context.size = 0; - } -} - -static int read_ldt(void __user * ptr, unsigned long bytecount) -{ - int err; - unsigned long size; - struct mm_struct * mm = current->mm; - - if (!mm->context.size) - return 0; - if (bytecount > LDT_ENTRY_SIZE*LDT_ENTRIES) - bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES; - - down(&mm->context.sem); - size = mm->context.size*LDT_ENTRY_SIZE; - if (size > bytecount) - size = bytecount; - - err = 0; - if (copy_to_user(ptr, mm->context.ldt, size)) - err = -EFAULT; - up(&mm->context.sem); - if (err < 0) - goto error_return; - if (size != bytecount) { - /* zero-fill the rest */ - if (clear_user(ptr+size, bytecount-size) != 0) { - err = -EFAULT; - goto error_return; - } - } - return bytecount; -error_return: - return err; -} - -static int read_default_ldt(void __user * ptr, unsigned long bytecount) -{ - int err; - unsigned long size; - void *address; - - err = 0; - address = &default_ldt[0]; - size = 5*sizeof(struct desc_struct); - if (size > bytecount) - size = bytecount; - - err = size; - if (copy_to_user(ptr, address, size)) - err = -EFAULT; - - return err; -} - -static int write_ldt(void __user * ptr, unsigned long bytecount, int oldmode) -{ - struct mm_struct * mm = current->mm; - __u32 entry_1, entry_2; - int error; - struct user_desc ldt_info; - - error = -EINVAL; - if (bytecount != sizeof(ldt_info)) - goto out; - error = -EFAULT; - if (copy_from_user(&ldt_info, ptr, sizeof(ldt_info))) - goto out; - - error = -EINVAL; - if (ldt_info.entry_number >= LDT_ENTRIES) - goto out; - if (ldt_info.contents == 3) { - if (oldmode) - goto out; - if (ldt_info.seg_not_present == 0) - goto out; - } - - down(&mm->context.sem); - if (ldt_info.entry_number >= mm->context.size) { - error = alloc_ldt(&current->mm->context, ldt_info.entry_number+1, 1); - if (error < 0) - goto out_unlock; - } - - /* Allow LDTs to be cleared by the user. */ - if (ldt_info.base_addr == 0 && ldt_info.limit == 0) { - if (oldmode || LDT_empty(&ldt_info)) { - entry_1 = 0; - entry_2 = 0; - goto install; - } - } - - entry_1 = LDT_entry_a(&ldt_info); - entry_2 = LDT_entry_b(&ldt_info); - if (oldmode) - entry_2 &= ~(1 << 20); - - /* Install the new entry ... */ -install: - error = write_ldt_entry(mm->context.ldt, ldt_info.entry_number, - entry_1, entry_2); - -out_unlock: - up(&mm->context.sem); -out: - return error; -} - -asmlinkage int sys_modify_ldt(int func, void __user *ptr, unsigned long bytecount) -{ - int ret = -ENOSYS; - - switch (func) { - case 0: - ret = read_ldt(ptr, bytecount); - break; - case 1: - ret = write_ldt(ptr, bytecount, 1); - break; - case 2: - ret = read_default_ldt(ptr, bytecount); - break; - case 0x11: - ret = write_ldt(ptr, bytecount, 0); - break; - } - return ret; -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/microcode.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/microcode.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,163 +0,0 @@ -/* - * Intel CPU Microcode Update Driver for Linux - * - * Copyright (C) 2000-2004 Tigran Aivazian - * - * This driver allows to upgrade microcode on Intel processors - * belonging to IA-32 family - PentiumPro, Pentium II, - * Pentium III, Xeon, Pentium 4, etc. - * - * Reference: Section 8.10 of Volume III, Intel Pentium 4 Manual, - * Order Number 245472 or free download from: - * - * http://developer.intel.com/design/pentium4/manuals/245472.htm - * - * For more information, go to http://www.urbanmyth.org/microcode - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -//#define DEBUG /* pr_debug */ -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/sched.h> -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/vmalloc.h> -#include <linux/miscdevice.h> -#include <linux/spinlock.h> -#include <linux/mm.h> -#include <linux/syscalls.h> - -#include <asm/msr.h> -#include <asm/uaccess.h> -#include <asm/processor.h> - -MODULE_DESCRIPTION("Intel CPU (IA-32) Microcode Update Driver"); -MODULE_AUTHOR("Tigran Aivazian <tigran@xxxxxxxxxxx>"); -MODULE_LICENSE("GPL"); - -#define MICROCODE_VERSION "1.14-xen" - -#define DEFAULT_UCODE_DATASIZE (2000) /* 2000 bytes */ -#define MC_HEADER_SIZE (sizeof (microcode_header_t)) /* 48 bytes */ -#define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE) /* 2048 bytes */ - -/* no concurrent ->write()s are allowed on /dev/cpu/microcode */ -static DECLARE_MUTEX(microcode_sem); - -static void __user *user_buffer; /* user area microcode data buffer */ -static unsigned int user_buffer_size; /* it's size */ - -static int microcode_open (struct inode *unused1, struct file *unused2) -{ - return capable(CAP_SYS_RAWIO) ? 0 : -EPERM; -} - - -static int do_microcode_update (void) -{ - int err; - dom0_op_t op; - - err = sys_mlock((unsigned long)user_buffer, user_buffer_size); - if (err != 0) - return err; - - op.cmd = DOM0_MICROCODE; - op.u.microcode.data = user_buffer; - op.u.microcode.length = user_buffer_size; - err = HYPERVISOR_dom0_op(&op); - - (void)sys_munlock((unsigned long)user_buffer, user_buffer_size); - - return err; -} - -static ssize_t microcode_write (struct file *file, const char __user *buf, size_t len, loff_t *ppos) -{ - ssize_t ret; - - if (len < DEFAULT_UCODE_TOTALSIZE) { - printk(KERN_ERR "microcode: not enough data\n"); - return -EINVAL; - } - - if ((len >> PAGE_SHIFT) > num_physpages) { - printk(KERN_ERR "microcode: too much data (max %ld pages)\n", num_physpages); - return -EINVAL; - } - - down(&microcode_sem); - - user_buffer = (void __user *) buf; - user_buffer_size = (int) len; - - ret = do_microcode_update(); - if (!ret) - ret = (ssize_t)len; - - up(&microcode_sem); - - return ret; -} - -static int microcode_ioctl (struct inode *inode, struct file *file, - unsigned int cmd, unsigned long arg) -{ - switch (cmd) { - /* - * XXX: will be removed after microcode_ctl - * is updated to ignore failure of this ioctl() - */ - case MICROCODE_IOCFREE: - return 0; - default: - return -EINVAL; - } - return -EINVAL; -} - -static struct file_operations microcode_fops = { - .owner = THIS_MODULE, - .write = microcode_write, - .ioctl = microcode_ioctl, - .open = microcode_open, -}; - -static struct miscdevice microcode_dev = { - .minor = MICROCODE_MINOR, - .name = "microcode", - .devfs_name = "cpu/microcode", - .fops = &microcode_fops, -}; - -static int __init microcode_init (void) -{ - int error; - - error = misc_register(&microcode_dev); - if (error) { - printk(KERN_ERR - "microcode: can't misc_register on minor=%d\n", - MICROCODE_MINOR); - return error; - } - - printk(KERN_INFO - "IA-32 Microcode Update Driver: v" MICROCODE_VERSION " <tigran@xxxxxxxxxxx>\n"); - return 0; -} - -static void __exit microcode_exit (void) -{ - misc_deregister(&microcode_dev); - printk(KERN_INFO "IA-32 Microcode Update Driver v" MICROCODE_VERSION " unregistered\n"); -} - -module_init(microcode_init) -module_exit(microcode_exit) -MODULE_ALIAS_MISCDEV(MICROCODE_MINOR); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/mpparse.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/mpparse.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,1126 +0,0 @@ -/* - * Intel Multiprocessor Specification 1.1 and 1.4 - * compliant MP-table parsing routines. - * - * (c) 1995 Alan Cox, Building #3 <alan@xxxxxxxxxx> - * (c) 1998, 1999, 2000 Ingo Molnar <mingo@xxxxxxxxxx> - * - * Fixes - * Erich Boleyn : MP v1.4 and additional changes. - * Alan Cox : Added EBDA scanning - * Ingo Molnar : various cleanups and rewrites - * Maciej W. Rozycki: Bits for default MP configurations - * Paul Diefenbaugh: Added full ACPI support - */ - -#include <linux/mm.h> -#include <linux/irq.h> -#include <linux/init.h> -#include <linux/acpi.h> -#include <linux/delay.h> -#include <linux/config.h> -#include <linux/bootmem.h> -#include <linux/smp_lock.h> -#include <linux/kernel_stat.h> -#include <linux/mc146818rtc.h> -#include <linux/bitops.h> - -#include <asm/smp.h> -#include <asm/acpi.h> -#include <asm/mtrr.h> -#include <asm/mpspec.h> -#include <asm/io_apic.h> - -#include <mach_apic.h> -#include <mach_mpparse.h> -#include <bios_ebda.h> - -/* Have we found an MP table */ -int smp_found_config; -unsigned int __initdata maxcpus = NR_CPUS; - -/* - * Various Linux-internal data structures created from the - * MP-table. - */ -int apic_version [MAX_APICS]; -int mp_bus_id_to_type [MAX_MP_BUSSES]; -int mp_bus_id_to_node [MAX_MP_BUSSES]; -int mp_bus_id_to_local [MAX_MP_BUSSES]; -int quad_local_to_mp_bus_id [NR_CPUS/4][4]; -int mp_bus_id_to_pci_bus [MAX_MP_BUSSES] = { [0 ... MAX_MP_BUSSES-1] = -1 }; -static int mp_current_pci_id; - -/* I/O APIC entries */ -struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS]; - -/* # of MP IRQ source entries */ -struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES]; - -/* MP IRQ source entries */ -int mp_irq_entries; - -int nr_ioapics; - -int pic_mode; -unsigned long mp_lapic_addr; - -/* Processor that is doing the boot up */ -unsigned int boot_cpu_physical_apicid = -1U; -unsigned int boot_cpu_logical_apicid = -1U; -/* Internal processor count */ -static unsigned int __initdata num_processors; - -/* Bitmask of physically existing CPUs */ -physid_mask_t phys_cpu_present_map; - -u8 bios_cpu_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; - -/* - * Intel MP BIOS table parsing routines: - */ - - -/* - * Checksum an MP configuration block. - */ - -static int __init mpf_checksum(unsigned char *mp, int len) -{ - int sum = 0; - - while (len--) - sum += *mp++; - - return sum & 0xFF; -} - -/* - * Have to match translation table entries to main table entries by counter - * hence the mpc_record variable .... can't see a less disgusting way of - * doing this .... - */ - -static int mpc_record; -static struct mpc_config_translation *translation_table[MAX_MPC_ENTRY] __initdata; - -#ifdef CONFIG_X86_NUMAQ -static int MP_valid_apicid(int apicid, int version) -{ - return hweight_long(apicid & 0xf) == 1 && (apicid >> 4) != 0xf; -} -#elif !defined(CONFIG_XEN) -static int MP_valid_apicid(int apicid, int version) -{ - if (version >= 0x14) - return apicid < 0xff; - else - return apicid < 0xf; -} -#endif - -#ifndef CONFIG_XEN -static void __init MP_processor_info (struct mpc_config_processor *m) -{ - int ver, apicid; - physid_mask_t tmp; - - if (!(m->mpc_cpuflag & CPU_ENABLED)) - return; - - apicid = mpc_apic_id(m, translation_table[mpc_record]); - - if (m->mpc_featureflag&(1<<0)) - Dprintk(" Floating point unit present.\n"); - if (m->mpc_featureflag&(1<<7)) - Dprintk(" Machine Exception supported.\n"); - if (m->mpc_featureflag&(1<<8)) - Dprintk(" 64 bit compare & exchange supported.\n"); - if (m->mpc_featureflag&(1<<9)) - Dprintk(" Internal APIC present.\n"); - if (m->mpc_featureflag&(1<<11)) - Dprintk(" SEP present.\n"); - if (m->mpc_featureflag&(1<<12)) - Dprintk(" MTRR present.\n"); - if (m->mpc_featureflag&(1<<13)) - Dprintk(" PGE present.\n"); - if (m->mpc_featureflag&(1<<14)) - Dprintk(" MCA present.\n"); - if (m->mpc_featureflag&(1<<15)) - Dprintk(" CMOV present.\n"); - if (m->mpc_featureflag&(1<<16)) - Dprintk(" PAT present.\n"); - if (m->mpc_featureflag&(1<<17)) - Dprintk(" PSE present.\n"); - if (m->mpc_featureflag&(1<<18)) - Dprintk(" PSN present.\n"); - if (m->mpc_featureflag&(1<<19)) - Dprintk(" Cache Line Flush Instruction present.\n"); - /* 20 Reserved */ - if (m->mpc_featureflag&(1<<21)) - Dprintk(" Debug Trace and EMON Store present.\n"); - if (m->mpc_featureflag&(1<<22)) - Dprintk(" ACPI Thermal Throttle Registers present.\n"); - if (m->mpc_featureflag&(1<<23)) - Dprintk(" MMX present.\n"); - if (m->mpc_featureflag&(1<<24)) - Dprintk(" FXSR present.\n"); - if (m->mpc_featureflag&(1<<25)) - Dprintk(" XMM present.\n"); - if (m->mpc_featureflag&(1<<26)) - Dprintk(" Willamette New Instructions present.\n"); - if (m->mpc_featureflag&(1<<27)) - Dprintk(" Self Snoop present.\n"); - if (m->mpc_featureflag&(1<<28)) - Dprintk(" HT present.\n"); - if (m->mpc_featureflag&(1<<29)) - Dprintk(" Thermal Monitor present.\n"); - /* 30, 31 Reserved */ - - - if (m->mpc_cpuflag & CPU_BOOTPROCESSOR) { - Dprintk(" Bootup CPU\n"); - boot_cpu_physical_apicid = m->mpc_apicid; - boot_cpu_logical_apicid = apicid; - } - - if (num_processors >= NR_CPUS) { - printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached." - " Processor ignored.\n", NR_CPUS); - return; - } - - if (num_processors >= maxcpus) { - printk(KERN_WARNING "WARNING: maxcpus limit of %i reached." - " Processor ignored.\n", maxcpus); - return; - } - num_processors++; - ver = m->mpc_apicver; - - if (!MP_valid_apicid(apicid, ver)) { - printk(KERN_WARNING "Processor #%d INVALID. (Max ID: %d).\n", - m->mpc_apicid, MAX_APICS); - --num_processors; - return; - } - - tmp = apicid_to_cpu_present(apicid); - physids_or(phys_cpu_present_map, phys_cpu_present_map, tmp); - - /* - * Validate version - */ - if (ver == 0x0) { - printk(KERN_WARNING "BIOS bug, APIC version is 0 for CPU#%d! fixing up to 0x10. (tell your hw vendor)\n", m->mpc_apicid); - ver = 0x10; - } - apic_version[m->mpc_apicid] = ver; - bios_cpu_apicid[num_processors - 1] = m->mpc_apicid; -} -#else -void __init MP_processor_info (struct mpc_config_processor *m) -{ - num_processors++; -} -#endif /* CONFIG_XEN */ - -static void __init MP_bus_info (struct mpc_config_bus *m) -{ - char str[7]; - - memcpy(str, m->mpc_bustype, 6); - str[6] = 0; - - mpc_oem_bus_info(m, str, translation_table[mpc_record]); - - if (strncmp(str, BUSTYPE_ISA, sizeof(BUSTYPE_ISA)-1) == 0) { - mp_bus_id_to_type[m->mpc_busid] = MP_BUS_ISA; - } else if (strncmp(str, BUSTYPE_EISA, sizeof(BUSTYPE_EISA)-1) == 0) { - mp_bus_id_to_type[m->mpc_busid] = MP_BUS_EISA; - } else if (strncmp(str, BUSTYPE_PCI, sizeof(BUSTYPE_PCI)-1) == 0) { - mpc_oem_pci_bus(m, translation_table[mpc_record]); - mp_bus_id_to_type[m->mpc_busid] = MP_BUS_PCI; - mp_bus_id_to_pci_bus[m->mpc_busid] = mp_current_pci_id; - mp_current_pci_id++; - } else if (strncmp(str, BUSTYPE_MCA, sizeof(BUSTYPE_MCA)-1) == 0) { - mp_bus_id_to_type[m->mpc_busid] = MP_BUS_MCA; - } else if (strncmp(str, BUSTYPE_NEC98, sizeof(BUSTYPE_NEC98)-1) == 0) { - mp_bus_id_to_type[m->mpc_busid] = MP_BUS_NEC98; - } else { - printk(KERN_WARNING "Unknown bustype %s - ignoring\n", str); - } -} - -static void __init MP_ioapic_info (struct mpc_config_ioapic *m) -{ - if (!(m->mpc_flags & MPC_APIC_USABLE)) - return; - - printk(KERN_INFO "I/O APIC #%d Version %d at 0x%lX.\n", - m->mpc_apicid, m->mpc_apicver, m->mpc_apicaddr); - if (nr_ioapics >= MAX_IO_APICS) { - printk(KERN_CRIT "Max # of I/O APICs (%d) exceeded (found %d).\n", - MAX_IO_APICS, nr_ioapics); - panic("Recompile kernel with bigger MAX_IO_APICS!.\n"); - } - if (!m->mpc_apicaddr) { - printk(KERN_ERR "WARNING: bogus zero I/O APIC address" - " found in MP table, skipping!\n"); - return; - } - mp_ioapics[nr_ioapics] = *m; - nr_ioapics++; -} - -static void __init MP_intsrc_info (struct mpc_config_intsrc *m) -{ - mp_irqs [mp_irq_entries] = *m; - Dprintk("Int: type %d, pol %d, trig %d, bus %d," - " IRQ %02x, APIC ID %x, APIC INT %02x\n", - m->mpc_irqtype, m->mpc_irqflag & 3, - (m->mpc_irqflag >> 2) & 3, m->mpc_srcbus, - m->mpc_srcbusirq, m->mpc_dstapic, m->mpc_dstirq); - if (++mp_irq_entries == MAX_IRQ_SOURCES) - panic("Max # of irq sources exceeded!!\n"); -} - -static void __init MP_lintsrc_info (struct mpc_config_lintsrc *m) -{ - Dprintk("Lint: type %d, pol %d, trig %d, bus %d," - " IRQ %02x, APIC ID %x, APIC LINT %02x\n", - m->mpc_irqtype, m->mpc_irqflag & 3, - (m->mpc_irqflag >> 2) &3, m->mpc_srcbusid, - m->mpc_srcbusirq, m->mpc_destapic, m->mpc_destapiclint); - /* - * Well it seems all SMP boards in existence - * use ExtINT/LVT1 == LINT0 and - * NMI/LVT2 == LINT1 - the following check - * will show us if this assumptions is false. - * Until then we do not have to add baggage. - */ - if ((m->mpc_irqtype == mp_ExtINT) && - (m->mpc_destapiclint != 0)) - BUG(); - if ((m->mpc_irqtype == mp_NMI) && - (m->mpc_destapiclint != 1)) - BUG(); -} - -#ifdef CONFIG_X86_NUMAQ -static void __init MP_translation_info (struct mpc_config_translation *m) -{ - printk(KERN_INFO "Translation: record %d, type %d, quad %d, global %d, local %d\n", mpc_record, m->trans_type, m->trans_quad, m->trans_global, m->trans_local); - - if (mpc_record >= MAX_MPC_ENTRY) - printk(KERN_ERR "MAX_MPC_ENTRY exceeded!\n"); - else - translation_table[mpc_record] = m; /* stash this for later */ - if (m->trans_quad < MAX_NUMNODES && !node_online(m->trans_quad)) - node_set_online(m->trans_quad); -} - -/* - * Read/parse the MPC oem tables - */ - -static void __init smp_read_mpc_oem(struct mp_config_oemtable *oemtable, \ - unsigned short oemsize) -{ - int count = sizeof (*oemtable); /* the header size */ - unsigned char *oemptr = ((unsigned char *)oemtable)+count; - - mpc_record = 0; - printk(KERN_INFO "Found an OEM MPC table at %8p - parsing it ... \n", oemtable); - if (memcmp(oemtable->oem_signature,MPC_OEM_SIGNATURE,4)) - { - printk(KERN_WARNING "SMP mpc oemtable: bad signature [%c%c%c%c]!\n", - oemtable->oem_signature[0], - oemtable->oem_signature[1], - oemtable->oem_signature[2], - oemtable->oem_signature[3]); - return; - } - if (mpf_checksum((unsigned char *)oemtable,oemtable->oem_length)) - { - printk(KERN_WARNING "SMP oem mptable: checksum error!\n"); - return; - } - while (count < oemtable->oem_length) { - switch (*oemptr) { - case MP_TRANSLATION: - { - struct mpc_config_translation *m= - (struct mpc_config_translation *)oemptr; - MP_translation_info(m); - oemptr += sizeof(*m); - count += sizeof(*m); - ++mpc_record; - break; - } - default: - { - printk(KERN_WARNING "Unrecognised OEM table entry type! - %d\n", (int) *oemptr); - return; - } - } - } -} - -static inline void mps_oem_check(struct mp_config_table *mpc, char *oem, - char *productid) -{ - if (strncmp(oem, "IBM NUMA", 8)) - printk("Warning! May not be a NUMA-Q system!\n"); - if (mpc->mpc_oemptr) - smp_read_mpc_oem((struct mp_config_oemtable *) mpc->mpc_oemptr, - mpc->mpc_oemsize); -} -#endif /* CONFIG_X86_NUMAQ */ - -/* - * Read/parse the MPC - */ - -static int __init smp_read_mpc(struct mp_config_table *mpc) -{ - char str[16]; - char oem[10]; - int count=sizeof(*mpc); - unsigned char *mpt=((unsigned char *)mpc)+count; - - if (memcmp(mpc->mpc_signature,MPC_SIGNATURE,4)) { - printk(KERN_ERR "SMP mptable: bad signature [0x%x]!\n", - *(u32 *)mpc->mpc_signature); - return 0; - } - if (mpf_checksum((unsigned char *)mpc,mpc->mpc_length)) { - printk(KERN_ERR "SMP mptable: checksum error!\n"); - return 0; - } - if (mpc->mpc_spec!=0x01 && mpc->mpc_spec!=0x04) { - printk(KERN_ERR "SMP mptable: bad table version (%d)!!\n", - mpc->mpc_spec); - return 0; - } - if (!mpc->mpc_lapic) { - printk(KERN_ERR "SMP mptable: null local APIC address!\n"); - return 0; - } - memcpy(oem,mpc->mpc_oem,8); - oem[8]=0; - printk(KERN_INFO "OEM ID: %s ",oem); - - memcpy(str,mpc->mpc_productid,12); - str[12]=0; - printk("Product ID: %s ",str); - - mps_oem_check(mpc, oem, str); - - printk("APIC at: 0x%lX\n",mpc->mpc_lapic); - - /* - * Save the local APIC address (it might be non-default) -- but only - * if we're not using ACPI. - */ - if (!acpi_lapic) - mp_lapic_addr = mpc->mpc_lapic; - - /* - * Now process the configuration blocks. - */ - mpc_record = 0; - while (count < mpc->mpc_length) { - switch(*mpt) { - case MP_PROCESSOR: - { - struct mpc_config_processor *m= - (struct mpc_config_processor *)mpt; - /* ACPI may have already provided this data */ - if (!acpi_lapic) - MP_processor_info(m); - mpt += sizeof(*m); - count += sizeof(*m); - break; - } - case MP_BUS: - { - struct mpc_config_bus *m= - (struct mpc_config_bus *)mpt; - MP_bus_info(m); - mpt += sizeof(*m); - count += sizeof(*m); - break; - } - case MP_IOAPIC: - { - struct mpc_config_ioapic *m= - (struct mpc_config_ioapic *)mpt; - MP_ioapic_info(m); - mpt+=sizeof(*m); - count+=sizeof(*m); - break; - } - case MP_INTSRC: - { - struct mpc_config_intsrc *m= - (struct mpc_config_intsrc *)mpt; - - MP_intsrc_info(m); - mpt+=sizeof(*m); - count+=sizeof(*m); - break; - } - case MP_LINTSRC: - { - struct mpc_config_lintsrc *m= - (struct mpc_config_lintsrc *)mpt; - MP_lintsrc_info(m); - mpt+=sizeof(*m); - count+=sizeof(*m); - break; - } - default: - { - count = mpc->mpc_length; - break; - } - } - ++mpc_record; - } - clustered_apic_check(); - if (!num_processors) - printk(KERN_ERR "SMP mptable: no processors registered!\n"); - return num_processors; -} - -static int __init ELCR_trigger(unsigned int irq) -{ - unsigned int port; - - port = 0x4d0 + (irq >> 3); - return (inb(port) >> (irq & 7)) & 1; -} - -static void __init construct_default_ioirq_mptable(int mpc_default_type) -{ - struct mpc_config_intsrc intsrc; - int i; - int ELCR_fallback = 0; - - intsrc.mpc_type = MP_INTSRC; - intsrc.mpc_irqflag = 0; /* conforming */ - intsrc.mpc_srcbus = 0; - intsrc.mpc_dstapic = mp_ioapics[0].mpc_apicid; - - intsrc.mpc_irqtype = mp_INT; - - /* - * If true, we have an ISA/PCI system with no IRQ entries - * in the MP table. To prevent the PCI interrupts from being set up - * incorrectly, we try to use the ELCR. The sanity check to see if - * there is good ELCR data is very simple - IRQ0, 1, 2 and 13 can - * never be level sensitive, so we simply see if the ELCR agrees. - * If it does, we assume it's valid. - */ - if (mpc_default_type == 5) { - printk(KERN_INFO "ISA/PCI bus type with no IRQ information... falling back to ELCR\n"); - - if (ELCR_trigger(0) || ELCR_trigger(1) || ELCR_trigger(2) || ELCR_trigger(13)) - printk(KERN_WARNING "ELCR contains invalid data... not using ELCR\n"); - else { - printk(KERN_INFO "Using ELCR to identify PCI interrupts\n"); - ELCR_fallback = 1; - } - } - - for (i = 0; i < 16; i++) { - switch (mpc_default_type) { - case 2: - if (i == 0 || i == 13) - continue; /* IRQ0 & IRQ13 not connected */ - /* fall through */ - default: - if (i == 2) - continue; /* IRQ2 is never connected */ - } - - if (ELCR_fallback) { - /* - * If the ELCR indicates a level-sensitive interrupt, we - * copy that information over to the MP table in the - * irqflag field (level sensitive, active high polarity). - */ - if (ELCR_trigger(i)) - intsrc.mpc_irqflag = 13; - else - intsrc.mpc_irqflag = 0; - } - - intsrc.mpc_srcbusirq = i; - intsrc.mpc_dstirq = i ? i : 2; /* IRQ0 to INTIN2 */ - MP_intsrc_info(&intsrc); - } - - intsrc.mpc_irqtype = mp_ExtINT; - intsrc.mpc_srcbusirq = 0; - intsrc.mpc_dstirq = 0; /* 8259A to INTIN0 */ - MP_intsrc_info(&intsrc); -} - -static inline void __init construct_default_ISA_mptable(int mpc_default_type) -{ - struct mpc_config_processor processor; - struct mpc_config_bus bus; - struct mpc_config_ioapic ioapic; - struct mpc_config_lintsrc lintsrc; - int linttypes[2] = { mp_ExtINT, mp_NMI }; - int i; - - /* - * local APIC has default address - */ - mp_lapic_addr = APIC_DEFAULT_PHYS_BASE; - - /* - * 2 CPUs, numbered 0 & 1. - */ - processor.mpc_type = MP_PROCESSOR; - /* Either an integrated APIC or a discrete 82489DX. */ - processor.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01; - processor.mpc_cpuflag = CPU_ENABLED; - processor.mpc_cpufeature = (boot_cpu_data.x86 << 8) | - (boot_cpu_data.x86_model << 4) | - boot_cpu_data.x86_mask; - processor.mpc_featureflag = boot_cpu_data.x86_capability[0]; - processor.mpc_reserved[0] = 0; - processor.mpc_reserved[1] = 0; - for (i = 0; i < 2; i++) { - processor.mpc_apicid = i; - MP_processor_info(&processor); - } - - bus.mpc_type = MP_BUS; - bus.mpc_busid = 0; - switch (mpc_default_type) { - default: - printk("???\n"); - printk(KERN_ERR "Unknown standard configuration %d\n", - mpc_default_type); - /* fall through */ - case 1: - case 5: - memcpy(bus.mpc_bustype, "ISA ", 6); - break; - case 2: - case 6: - case 3: - memcpy(bus.mpc_bustype, "EISA ", 6); - break; - case 4: - case 7: - memcpy(bus.mpc_bustype, "MCA ", 6); - } - MP_bus_info(&bus); - if (mpc_default_type > 4) { - bus.mpc_busid = 1; - memcpy(bus.mpc_bustype, "PCI ", 6); - MP_bus_info(&bus); - } - - ioapic.mpc_type = MP_IOAPIC; - ioapic.mpc_apicid = 2; - ioapic.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01; - ioapic.mpc_flags = MPC_APIC_USABLE; - ioapic.mpc_apicaddr = 0xFEC00000; - MP_ioapic_info(&ioapic); - - /* - * We set up most of the low 16 IO-APIC pins according to MPS rules. - */ - construct_default_ioirq_mptable(mpc_default_type); - - lintsrc.mpc_type = MP_LINTSRC; - lintsrc.mpc_irqflag = 0; /* conforming */ - lintsrc.mpc_srcbusid = 0; - lintsrc.mpc_srcbusirq = 0; - lintsrc.mpc_destapic = MP_APIC_ALL; - for (i = 0; i < 2; i++) { - lintsrc.mpc_irqtype = linttypes[i]; - lintsrc.mpc_destapiclint = i; - MP_lintsrc_info(&lintsrc); - } -} - -static struct intel_mp_floating *mpf_found; - -/* - * Scan the memory blocks for an SMP configuration block. - */ -void __init get_smp_config (void) -{ - struct intel_mp_floating *mpf = mpf_found; - - /* - * ACPI may be used to obtain the entire SMP configuration or just to - * enumerate/configure processors (CONFIG_ACPI_BOOT). Note that - * ACPI supports both logical (e.g. Hyper-Threading) and physical - * processors, where MPS only supports physical. - */ - if (acpi_lapic && acpi_ioapic) { - printk(KERN_INFO "Using ACPI (MADT) for SMP configuration information\n"); - return; - } - else if (acpi_lapic) - printk(KERN_INFO "Using ACPI for processor (LAPIC) configuration information\n"); - - printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n", mpf->mpf_specification); - if (mpf->mpf_feature2 & (1<<7)) { - printk(KERN_INFO " IMCR and PIC compatibility mode.\n"); - pic_mode = 1; - } else { - printk(KERN_INFO " Virtual Wire compatibility mode.\n"); - pic_mode = 0; - } - - /* - * Now see if we need to read further. - */ - if (mpf->mpf_feature1 != 0) { - - printk(KERN_INFO "Default MP configuration #%d\n", mpf->mpf_feature1); - construct_default_ISA_mptable(mpf->mpf_feature1); - - } else if (mpf->mpf_physptr) { - - /* - * Read the physical hardware table. Anything here will - * override the defaults. - */ - if (!smp_read_mpc(isa_bus_to_virt(mpf->mpf_physptr))) { - smp_found_config = 0; - printk(KERN_ERR "BIOS bug, MP table errors detected!...\n"); - printk(KERN_ERR "... disabling SMP support. (tell your hw vendor)\n"); - return; - } - /* - * If there are no explicit MP IRQ entries, then we are - * broken. We set up most of the low 16 IO-APIC pins to - * ISA defaults and hope it will work. - */ - if (!mp_irq_entries) { - struct mpc_config_bus bus; - - printk(KERN_ERR "BIOS bug, no explicit IRQ entries, using default mptable. (tell your hw vendor)\n"); - - bus.mpc_type = MP_BUS; - bus.mpc_busid = 0; - memcpy(bus.mpc_bustype, "ISA ", 6); - MP_bus_info(&bus); - - construct_default_ioirq_mptable(0); - } - - } else - BUG(); - - printk(KERN_INFO "Processors: %d\n", num_processors); - /* - * Only use the first configuration found. - */ -} - -static int __init smp_scan_config (unsigned long base, unsigned long length) -{ - unsigned long *bp = isa_bus_to_virt(base); - struct intel_mp_floating *mpf; - - Dprintk("Scan SMP from %p for %ld bytes.\n", bp,length); - if (sizeof(*mpf) != 16) - printk("Error: MPF size\n"); - - while (length > 0) { - mpf = (struct intel_mp_floating *)bp; - if ((*bp == SMP_MAGIC_IDENT) && - (mpf->mpf_length == 1) && - !mpf_checksum((unsigned char *)bp, 16) && - ((mpf->mpf_specification == 1) - || (mpf->mpf_specification == 4)) ) { - - smp_found_config = 1; -#ifndef CONFIG_XEN - printk(KERN_INFO "found SMP MP-table at %08lx\n", - virt_to_phys(mpf)); - reserve_bootmem(virt_to_phys(mpf), PAGE_SIZE); - if (mpf->mpf_physptr) { - /* - * We cannot access to MPC table to compute - * table size yet, as only few megabytes from - * the bottom is mapped now. - * PC-9800's MPC table places on the very last - * of physical memory; so that simply reserving - * PAGE_SIZE from mpg->mpf_physptr yields BUG() - * in reserve_bootmem. - */ - unsigned long size = PAGE_SIZE; - unsigned long end = max_low_pfn * PAGE_SIZE; - if (mpf->mpf_physptr + size > end) - size = end - mpf->mpf_physptr; - reserve_bootmem(mpf->mpf_physptr, size); - } -#else - printk(KERN_INFO "found SMP MP-table at %08lx\n", - ((unsigned long)bp - (unsigned long)isa_bus_to_virt(base)) + base); -#endif - - mpf_found = mpf; - return 1; - } - bp += 4; - length -= 16; - } - return 0; -} - -void __init find_smp_config (void) -{ -#ifndef CONFIG_XEN - unsigned int address; -#endif - - /* - * FIXME: Linux assumes you have 640K of base ram.. - * this continues the error... - * - * 1) Scan the bottom 1K for a signature - * 2) Scan the top 1K of base RAM - * 3) Scan the 64K of bios - */ - if (smp_scan_config(0x0,0x400) || - smp_scan_config(639*0x400,0x400) || - smp_scan_config(0xF0000,0x10000)) - return; - /* - * If it is an SMP machine we should know now, unless the - * configuration is in an EISA/MCA bus machine with an - * extended bios data area. - * - * there is a real-mode segmented pointer pointing to the - * 4K EBDA area at 0x40E, calculate and scan it here. - * - * NOTE! There are Linux loaders that will corrupt the EBDA - * area, and as such this kind of SMP config may be less - * trustworthy, simply because the SMP table may have been - * stomped on during early boot. These loaders are buggy and - * should be fixed. - * - * MP1.4 SPEC states to only scan first 1K of 4K EBDA. - */ - -#ifndef CONFIG_XEN - address = get_bios_ebda(); - if (address) - smp_scan_config(address, 0x400); -#endif -} - -/* -------------------------------------------------------------------------- - ACPI-based MP Configuration - -------------------------------------------------------------------------- */ - -#ifdef CONFIG_ACPI_BOOT - -void __init mp_register_lapic_address ( - u64 address) -{ -#ifndef CONFIG_XEN - mp_lapic_addr = (unsigned long) address; - - if (boot_cpu_physical_apicid == -1U) - boot_cpu_physical_apicid = GET_APIC_ID(apic_read(APIC_ID)); - - Dprintk("Boot CPU = %d\n", boot_cpu_physical_apicid); -#endif -} - - -void __init mp_register_lapic ( - u8 id, - u8 enabled) -{ - struct mpc_config_processor processor; - int boot_cpu = 0; - - if (MAX_APICS - id <= 0) { - printk(KERN_WARNING "Processor #%d invalid (max %d)\n", - id, MAX_APICS); - return; - } - - if (id == boot_cpu_physical_apicid) - boot_cpu = 1; - -#ifndef CONFIG_XEN - processor.mpc_type = MP_PROCESSOR; - processor.mpc_apicid = id; - processor.mpc_apicver = GET_APIC_VERSION(apic_read(APIC_LVR)); - processor.mpc_cpuflag = (enabled ? CPU_ENABLED : 0); - processor.mpc_cpuflag |= (boot_cpu ? CPU_BOOTPROCESSOR : 0); - processor.mpc_cpufeature = (boot_cpu_data.x86 << 8) | - (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask; - processor.mpc_featureflag = boot_cpu_data.x86_capability[0]; - processor.mpc_reserved[0] = 0; - processor.mpc_reserved[1] = 0; -#endif - - MP_processor_info(&processor); -} - -#if defined(CONFIG_X86_IO_APIC) && (defined(CONFIG_ACPI_INTERPRETER) || defined(CONFIG_ACPI_BOOT)) - -#define MP_ISA_BUS 0 -#define MP_MAX_IOAPIC_PIN 127 - -static struct mp_ioapic_routing { - int apic_id; - int gsi_base; - int gsi_end; - u32 pin_programmed[4]; -} mp_ioapic_routing[MAX_IO_APICS]; - - -static int mp_find_ioapic ( - int gsi) -{ - int i = 0; - - /* Find the IOAPIC that manages this GSI. */ - for (i = 0; i < nr_ioapics; i++) { - if ((gsi >= mp_ioapic_routing[i].gsi_base) - && (gsi <= mp_ioapic_routing[i].gsi_end)) - return i; - } - - printk(KERN_ERR "ERROR: Unable to locate IOAPIC for GSI %d\n", gsi); - - return -1; -} - - -void __init mp_register_ioapic ( - u8 id, - u32 address, - u32 gsi_base) -{ - int idx = 0; - - if (nr_ioapics >= MAX_IO_APICS) { - printk(KERN_ERR "ERROR: Max # of I/O APICs (%d) exceeded " - "(found %d)\n", MAX_IO_APICS, nr_ioapics); - panic("Recompile kernel with bigger MAX_IO_APICS!\n"); - } - if (!address) { - printk(KERN_ERR "WARNING: Bogus (zero) I/O APIC address" - " found in MADT table, skipping!\n"); - return; - } - - idx = nr_ioapics++; - - mp_ioapics[idx].mpc_type = MP_IOAPIC; - mp_ioapics[idx].mpc_flags = MPC_APIC_USABLE; - mp_ioapics[idx].mpc_apicaddr = address; - - mp_ioapics[idx].mpc_apicid = io_apic_get_unique_id(idx, id); - mp_ioapics[idx].mpc_apicver = io_apic_get_version(idx); - - /* - * Build basic GSI lookup table to facilitate gsi->io_apic lookups - * and to prevent reprogramming of IOAPIC pins (PCI GSIs). - */ - mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].mpc_apicid; - mp_ioapic_routing[idx].gsi_base = gsi_base; - mp_ioapic_routing[idx].gsi_end = gsi_base + - io_apic_get_redir_entries(idx); - - printk("IOAPIC[%d]: apic_id %d, version %d, address 0x%lx, " - "GSI %d-%d\n", idx, mp_ioapics[idx].mpc_apicid, - mp_ioapics[idx].mpc_apicver, mp_ioapics[idx].mpc_apicaddr, - mp_ioapic_routing[idx].gsi_base, - mp_ioapic_routing[idx].gsi_end); - - return; -} - - -void __init mp_override_legacy_irq ( - u8 bus_irq, - u8 polarity, - u8 trigger, - u32 gsi) -{ - struct mpc_config_intsrc intsrc; - int ioapic = -1; - int pin = -1; - - /* - * Convert 'gsi' to 'ioapic.pin'. - */ - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) - return; - pin = gsi - mp_ioapic_routing[ioapic].gsi_base; - - /* - * TBD: This check is for faulty timer entries, where the override - * erroneously sets the trigger to level, resulting in a HUGE - * increase of timer interrupts! - */ - if ((bus_irq == 0) && (trigger == 3)) - trigger = 1; - - intsrc.mpc_type = MP_INTSRC; - intsrc.mpc_irqtype = mp_INT; - intsrc.mpc_irqflag = (trigger << 2) | polarity; - intsrc.mpc_srcbus = MP_ISA_BUS; - intsrc.mpc_srcbusirq = bus_irq; /* IRQ */ - intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid; /* APIC ID */ - intsrc.mpc_dstirq = pin; /* INTIN# */ - - Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, %d-%d\n", - intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3, - (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus, - intsrc.mpc_srcbusirq, intsrc.mpc_dstapic, intsrc.mpc_dstirq); - - mp_irqs[mp_irq_entries] = intsrc; - if (++mp_irq_entries == MAX_IRQ_SOURCES) - panic("Max # of irq sources exceeded!\n"); - - return; -} - -int es7000_plat; - -void __init mp_config_acpi_legacy_irqs (void) -{ - struct mpc_config_intsrc intsrc; - int i = 0; - int ioapic = -1; - - /* - * Fabricate the legacy ISA bus (bus #31). - */ - mp_bus_id_to_type[MP_ISA_BUS] = MP_BUS_ISA; - Dprintk("Bus #%d is ISA\n", MP_ISA_BUS); - - /* - * Older generations of ES7000 have no legacy identity mappings - */ - if (es7000_plat == 1) - return; - - /* - * Locate the IOAPIC that manages the ISA IRQs (0-15). - */ - ioapic = mp_find_ioapic(0); - if (ioapic < 0) - return; - - intsrc.mpc_type = MP_INTSRC; - intsrc.mpc_irqflag = 0; /* Conforming */ - intsrc.mpc_srcbus = MP_ISA_BUS; - intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid; - - /* - * Use the default configuration for the IRQs 0-15. Unless - * overriden by (MADT) interrupt source override entries. - */ - for (i = 0; i < 16; i++) { - int idx; - - for (idx = 0; idx < mp_irq_entries; idx++) { - struct mpc_config_intsrc *irq = mp_irqs + idx; - - /* Do we already have a mapping for this ISA IRQ? */ - if (irq->mpc_srcbus == MP_ISA_BUS && irq->mpc_srcbusirq == i) - break; - - /* Do we already have a mapping for this IOAPIC pin */ - if ((irq->mpc_dstapic == intsrc.mpc_dstapic) && - (irq->mpc_dstirq == i)) - break; - } - - if (idx != mp_irq_entries) { - printk(KERN_DEBUG "ACPI: IRQ%d used by override.\n", i); - continue; /* IRQ already used */ - } - - intsrc.mpc_irqtype = mp_INT; - intsrc.mpc_srcbusirq = i; /* Identity mapped */ - intsrc.mpc_dstirq = i; - - Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, " - "%d-%d\n", intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3, - (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus, - intsrc.mpc_srcbusirq, intsrc.mpc_dstapic, - intsrc.mpc_dstirq); - - mp_irqs[mp_irq_entries] = intsrc; - if (++mp_irq_entries == MAX_IRQ_SOURCES) - panic("Max # of irq sources exceeded!\n"); - } -} - -int mp_register_gsi (u32 gsi, int edge_level, int active_high_low) -{ - int ioapic = -1; - int ioapic_pin = 0; - int idx, bit = 0; - -#ifdef CONFIG_ACPI_BUS - /* Don't set up the ACPI SCI because it's already set up */ - if (acpi_fadt.sci_int == gsi) - return gsi; -#endif - - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) { - printk(KERN_WARNING "No IOAPIC for GSI %u\n", gsi); - return gsi; - } - - ioapic_pin = gsi - mp_ioapic_routing[ioapic].gsi_base; - - if (ioapic_renumber_irq) - gsi = ioapic_renumber_irq(ioapic, gsi); - - /* - * Avoid pin reprogramming. PRTs typically include entries - * with redundant pin->gsi mappings (but unique PCI devices); - * we only program the IOAPIC on the first. - */ - bit = ioapic_pin % 32; - idx = (ioapic_pin < 32) ? 0 : (ioapic_pin / 32); - if (idx > 3) { - printk(KERN_ERR "Invalid reference to IOAPIC pin " - "%d-%d\n", mp_ioapic_routing[ioapic].apic_id, - ioapic_pin); - return gsi; - } - if ((1<<bit) & mp_ioapic_routing[ioapic].pin_programmed[idx]) { - Dprintk(KERN_DEBUG "Pin %d-%d already programmed\n", - mp_ioapic_routing[ioapic].apic_id, ioapic_pin); - return gsi; - } - - mp_ioapic_routing[ioapic].pin_programmed[idx] |= (1<<bit); - - io_apic_set_pci_routing(ioapic, ioapic_pin, gsi, - edge_level == ACPI_EDGE_SENSITIVE ? 0 : 1, - active_high_low == ACPI_ACTIVE_HIGH ? 0 : 1); - return gsi; -} - -#endif /*CONFIG_X86_IO_APIC && (CONFIG_ACPI_INTERPRETER || CONFIG_ACPI_BOOT)*/ -#endif /*CONFIG_ACPI_BOOT*/ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/pci-dma.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/pci-dma.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,319 +0,0 @@ -/* - * Dynamic DMA mapping support. - * - * On i386 there is no hardware dynamic DMA address translation, - * so consistent alloc/free are merely page allocation/freeing. - * The rest of the dynamic DMA mapping interface is implemented - * in asm/pci.h. - */ - -#include <linux/types.h> -#include <linux/mm.h> -#include <linux/string.h> -#include <linux/pci.h> -#include <linux/version.h> -#include <asm/io.h> -#include <asm-xen/balloon.h> -#include <asm/tlbflush.h> -#include <asm/swiotlb.h> - -struct dma_coherent_mem { - void *virt_base; - u32 device_base; - int size; - int flags; - unsigned long *bitmap; -}; - -#define IOMMU_BUG_ON(test) \ -do { \ - if (unlikely(test)) { \ - printk(KERN_ALERT "Fatal DMA error! " \ - "Please use 'swiotlb=force'\n"); \ - BUG(); \ - } \ -} while (0) - -int -dma_map_sg(struct device *hwdev, struct scatterlist *sg, int nents, - enum dma_data_direction direction) -{ - int i, rc; - - BUG_ON(direction == DMA_NONE); - - if (swiotlb) { - rc = swiotlb_map_sg(hwdev, sg, nents, direction); - } else { - for (i = 0; i < nents; i++ ) { - sg[i].dma_address = - page_to_phys(sg[i].page) + sg[i].offset; - sg[i].dma_length = sg[i].length; - BUG_ON(!sg[i].page); - IOMMU_BUG_ON(address_needs_mapping( - hwdev, sg[i].dma_address)); - } - rc = nents; - } - - flush_write_buffers(); - return rc; -} -EXPORT_SYMBOL(dma_map_sg); - -void -dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents, - enum dma_data_direction direction) -{ - BUG_ON(direction == DMA_NONE); - if (swiotlb) - swiotlb_unmap_sg(hwdev, sg, nents, direction); -} -EXPORT_SYMBOL(dma_unmap_sg); - -dma_addr_t -dma_map_page(struct device *dev, struct page *page, unsigned long offset, - size_t size, enum dma_data_direction direction) -{ - dma_addr_t dma_addr; - - BUG_ON(direction == DMA_NONE); - - if (swiotlb) { - dma_addr = swiotlb_map_page( - dev, page, offset, size, direction); - } else { - dma_addr = page_to_phys(page) + offset; - IOMMU_BUG_ON(address_needs_mapping(dev, dma_addr)); - } - - return dma_addr; -} -EXPORT_SYMBOL(dma_map_page); - -void -dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, - enum dma_data_direction direction) -{ - BUG_ON(direction == DMA_NONE); - if (swiotlb) - swiotlb_unmap_page(dev, dma_address, size, direction); -} -EXPORT_SYMBOL(dma_unmap_page); - -int -dma_mapping_error(dma_addr_t dma_addr) -{ - if (swiotlb) - return swiotlb_dma_mapping_error(dma_addr); - return 0; -} -EXPORT_SYMBOL(dma_mapping_error); - -int -dma_supported(struct device *dev, u64 mask) -{ - if (swiotlb) - return swiotlb_dma_supported(dev, mask); - /* - * By default we'll BUG when an infeasible DMA is requested, and - * request swiotlb=force (see IOMMU_BUG_ON). - */ - return 1; -} -EXPORT_SYMBOL(dma_supported); - -void *dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, unsigned int __nocast gfp) -{ - void *ret; - struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL; - unsigned int order = get_order(size); - unsigned long vstart; - /* ignore region specifiers */ - gfp &= ~(__GFP_DMA | __GFP_HIGHMEM); - - if (mem) { - int page = bitmap_find_free_region(mem->bitmap, mem->size, - order); - if (page >= 0) { - *dma_handle = mem->device_base + (page << PAGE_SHIFT); - ret = mem->virt_base + (page << PAGE_SHIFT); - memset(ret, 0, size); - return ret; - } - if (mem->flags & DMA_MEMORY_EXCLUSIVE) - return NULL; - } - - if (dev == NULL || (dev->coherent_dma_mask < 0xffffffff)) - gfp |= GFP_DMA; - - vstart = __get_free_pages(gfp, order); - ret = (void *)vstart; - - if (ret != NULL) { - /* NB. Hardcode 31 address bits for now: aacraid limitation. */ - if (xen_create_contiguous_region(vstart, order, 31) != 0) { - free_pages(vstart, order); - return NULL; - } - memset(ret, 0, size); - *dma_handle = virt_to_bus(ret); - } - return ret; -} -EXPORT_SYMBOL(dma_alloc_coherent); - -void dma_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle) -{ - struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL; - int order = get_order(size); - - if (mem && vaddr >= mem->virt_base && vaddr < (mem->virt_base + (mem->size << PAGE_SHIFT))) { - int page = (vaddr - mem->virt_base) >> PAGE_SHIFT; - - bitmap_release_region(mem->bitmap, page, order); - } else { - xen_destroy_contiguous_region((unsigned long)vaddr, order); - free_pages((unsigned long)vaddr, order); - } -} -EXPORT_SYMBOL(dma_free_coherent); - -int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, - dma_addr_t device_addr, size_t size, int flags) -{ - void __iomem *mem_base; - int pages = size >> PAGE_SHIFT; - int bitmap_size = (pages + 31)/32; - - if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0) - goto out; - if (!size) - goto out; - if (dev->dma_mem) - goto out; - - /* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */ - - mem_base = ioremap(bus_addr, size); - if (!mem_base) - goto out; - - dev->dma_mem = kmalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL); - if (!dev->dma_mem) - goto out; - memset(dev->dma_mem, 0, sizeof(struct dma_coherent_mem)); - dev->dma_mem->bitmap = kmalloc(bitmap_size, GFP_KERNEL); - if (!dev->dma_mem->bitmap) - goto free1_out; - memset(dev->dma_mem->bitmap, 0, bitmap_size); - - dev->dma_mem->virt_base = mem_base; - dev->dma_mem->device_base = device_addr; - dev->dma_mem->size = pages; - dev->dma_mem->flags = flags; - - if (flags & DMA_MEMORY_MAP) - return DMA_MEMORY_MAP; - - return DMA_MEMORY_IO; - - free1_out: - kfree(dev->dma_mem->bitmap); - out: - return 0; -} -EXPORT_SYMBOL(dma_declare_coherent_memory); - -void dma_release_declared_memory(struct device *dev) -{ - struct dma_coherent_mem *mem = dev->dma_mem; - - if(!mem) - return; - dev->dma_mem = NULL; - iounmap(mem->virt_base); - kfree(mem->bitmap); - kfree(mem); -} -EXPORT_SYMBOL(dma_release_declared_memory); - -void *dma_mark_declared_memory_occupied(struct device *dev, - dma_addr_t device_addr, size_t size) -{ - struct dma_coherent_mem *mem = dev->dma_mem; - int pages = (size + (device_addr & ~PAGE_MASK) + PAGE_SIZE - 1) >> PAGE_SHIFT; - int pos, err; - - if (!mem) - return ERR_PTR(-EINVAL); - - pos = (device_addr - mem->device_base) >> PAGE_SHIFT; - err = bitmap_allocate_region(mem->bitmap, pos, get_order(pages)); - if (err != 0) - return ERR_PTR(err); - return mem->virt_base + (pos << PAGE_SHIFT); -} -EXPORT_SYMBOL(dma_mark_declared_memory_occupied); - -dma_addr_t -dma_map_single(struct device *dev, void *ptr, size_t size, - enum dma_data_direction direction) -{ - dma_addr_t dma; - - BUG_ON(direction == DMA_NONE); - - if (swiotlb) { - dma = swiotlb_map_single(dev, ptr, size, direction); - } else { - dma = virt_to_bus(ptr); - IOMMU_BUG_ON(range_straddles_page_boundary(ptr, size)); - IOMMU_BUG_ON(address_needs_mapping(dev, dma)); - } - - flush_write_buffers(); - return dma; -} -EXPORT_SYMBOL(dma_map_single); - -void -dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size, - enum dma_data_direction direction) -{ - BUG_ON(direction == DMA_NONE); - if (swiotlb) - swiotlb_unmap_single(dev, dma_addr, size, direction); -} -EXPORT_SYMBOL(dma_unmap_single); - -void -dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, - enum dma_data_direction direction) -{ - if (swiotlb) - swiotlb_sync_single_for_cpu(dev, dma_handle, size, direction); -} -EXPORT_SYMBOL(dma_sync_single_for_cpu); - -void -dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size, - enum dma_data_direction direction) -{ - if (swiotlb) - swiotlb_sync_single_for_device(dev, dma_handle, size, direction); -} -EXPORT_SYMBOL(dma_sync_single_for_device); - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/process.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/process.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,770 +0,0 @@ -/* - * linux/arch/i386/kernel/process.c - * - * Copyright (C) 1995 Linus Torvalds - * - * Pentium III FXSR, SSE support - * Gareth Hughes <gareth@xxxxxxxxxxx>, May 2000 - */ - -/* - * This file handles the architecture-dependent parts of process handling.. - */ - -#include <stdarg.h> - -#include <linux/cpu.h> -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/fs.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/elfcore.h> -#include <linux/smp.h> -#include <linux/smp_lock.h> -#include <linux/stddef.h> -#include <linux/slab.h> -#include <linux/vmalloc.h> -#include <linux/user.h> -#include <linux/a.out.h> -#include <linux/interrupt.h> -#include <linux/config.h> -#include <linux/utsname.h> -#include <linux/delay.h> -#include <linux/reboot.h> -#include <linux/init.h> -#include <linux/mc146818rtc.h> -#include <linux/module.h> -#include <linux/kallsyms.h> -#include <linux/ptrace.h> -#include <linux/random.h> - -#include <asm/uaccess.h> -#include <asm/pgtable.h> -#include <asm/system.h> -#include <asm/io.h> -#include <asm/ldt.h> -#include <asm/processor.h> -#include <asm/i387.h> -#include <asm/irq.h> -#include <asm/desc.h> -#include <asm-xen/xen-public/physdev.h> -#include <asm-xen/xen-public/vcpu.h> -#ifdef CONFIG_MATH_EMULATION -#include <asm/math_emu.h> -#endif - -#include <linux/irq.h> -#include <linux/err.h> - -#include <asm/tlbflush.h> -#include <asm/cpu.h> - -asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); - -static int hlt_counter; - -unsigned long boot_option_idle_override = 0; -EXPORT_SYMBOL(boot_option_idle_override); - -/* - * Return saved PC of a blocked thread. - */ -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - return ((unsigned long *)tsk->thread.esp)[3]; -} - -/* - * Powermanagement idle function, if any.. - */ -void (*pm_idle)(void); -static DEFINE_PER_CPU(unsigned int, cpu_idle_state); - -void disable_hlt(void) -{ - hlt_counter++; -} - -EXPORT_SYMBOL(disable_hlt); - -void enable_hlt(void) -{ - hlt_counter--; -} - -EXPORT_SYMBOL(enable_hlt); - -/* XXX XEN doesn't use default_idle(), poll_idle(). Use xen_idle() instead. */ -extern void stop_hz_timer(void); -extern void start_hz_timer(void); -void xen_idle(void) -{ - local_irq_disable(); - - if (need_resched()) { - local_irq_enable(); - } else { - stop_hz_timer(); - /* Blocking includes an implicit local_irq_enable(). */ - HYPERVISOR_sched_op(SCHEDOP_block, 0); - start_hz_timer(); - } -} - -/* - * The idle thread. There's no useful work to be - * done, so just try to conserve power and have a - * low exit latency (ie sit in a loop waiting for - * somebody to say that they'd like to reschedule) - */ -void cpu_idle (void) -{ -#if defined(CONFIG_HOTPLUG_CPU) - int cpu = _smp_processor_id(); -#endif - - /* endless idle loop with no priority at all */ - while (1) { - while (!need_resched()) { - - if (__get_cpu_var(cpu_idle_state)) - __get_cpu_var(cpu_idle_state) = 0; - rmb(); - -#if defined(CONFIG_HOTPLUG_CPU) - if (cpu_is_offline(cpu)) { - HYPERVISOR_vcpu_op(VCPUOP_down, cpu, NULL); - local_irq_enable(); - } -#endif - - __get_cpu_var(irq_stat).idle_timestamp = jiffies; - xen_idle(); - } - schedule(); - } -} - -void cpu_idle_wait(void) -{ - unsigned int cpu, this_cpu = get_cpu(); - cpumask_t map; - - set_cpus_allowed(current, cpumask_of_cpu(this_cpu)); - put_cpu(); - - cpus_clear(map); - for_each_online_cpu(cpu) { - per_cpu(cpu_idle_state, cpu) = 1; - cpu_set(cpu, map); - } - - __get_cpu_var(cpu_idle_state) = 0; - - wmb(); - do { - ssleep(1); - for_each_online_cpu(cpu) { - if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu)) - cpu_clear(cpu, map); - } - cpus_and(map, map, cpu_online_map); - } while (!cpus_empty(map)); -} -EXPORT_SYMBOL_GPL(cpu_idle_wait); - -/* XXX XEN doesn't use mwait_idle(), select_idle_routine(), idle_setup(). */ -/* Always use xen_idle() instead. */ -void __init select_idle_routine(const struct cpuinfo_x86 *c) {} - -void show_regs(struct pt_regs * regs) -{ - printk("\n"); - printk("Pid: %d, comm: %20s\n", current->pid, current->comm); - printk("EIP: %04x:[<%08lx>] CPU: %d\n",0xffff & regs->xcs,regs->eip, smp_processor_id()); - print_symbol("EIP is at %s\n", regs->eip); - - if (regs->xcs & 2) - printk(" ESP: %04x:%08lx",0xffff & regs->xss,regs->esp); - printk(" EFLAGS: %08lx %s (%s)\n", - regs->eflags, print_tainted(), system_utsname.release); - printk("EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n", - regs->eax,regs->ebx,regs->ecx,regs->edx); - printk("ESI: %08lx EDI: %08lx EBP: %08lx", - regs->esi, regs->edi, regs->ebp); - printk(" DS: %04x ES: %04x\n", - 0xffff & regs->xds,0xffff & regs->xes); - - show_trace(NULL, &regs->esp); -} - -/* - * This gets run with %ebx containing the - * function to call, and %edx containing - * the "args". - */ -extern void kernel_thread_helper(void); -__asm__(".section .text\n" - ".align 4\n" - "kernel_thread_helper:\n\t" - "movl %edx,%eax\n\t" - "pushl %edx\n\t" - "call *%ebx\n\t" - "pushl %eax\n\t" - "call do_exit\n" - ".previous"); - -/* - * Create a kernel thread - */ -int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) -{ - struct pt_regs regs; - - memset(&regs, 0, sizeof(regs)); - - regs.ebx = (unsigned long) fn; - regs.edx = (unsigned long) arg; - - regs.xds = __USER_DS; - regs.xes = __USER_DS; - regs.orig_eax = -1; - regs.eip = (unsigned long) kernel_thread_helper; - regs.xcs = __KERNEL_CS; - regs.eflags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2; - - /* Ok, create the new process.. */ - return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs, 0, NULL, NULL); -} - -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ - struct task_struct *tsk = current; - struct thread_struct *t = &tsk->thread; - - /* The process may have allocated an io port bitmap... nuke it. */ - if (unlikely(NULL != t->io_bitmap_ptr)) { - physdev_op_t op = { 0 }; - op.cmd = PHYSDEVOP_SET_IOBITMAP; - HYPERVISOR_physdev_op(&op); - kfree(t->io_bitmap_ptr); - t->io_bitmap_ptr = NULL; - } -} - -void flush_thread(void) -{ - struct task_struct *tsk = current; - - memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8); - memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - /* - * Forget coprocessor state.. - */ - clear_fpu(tsk); - clear_used_math(); -} - -void release_thread(struct task_struct *dead_task) -{ - if (dead_task->mm) { - // temporary debugging check - if (dead_task->mm->context.size) { - printk("WARNING: dead process %8s still has LDT? <%p/%d>\n", - dead_task->comm, - dead_task->mm->context.ldt, - dead_task->mm->context.size); - BUG(); - } - } - - release_vm86_irqs(dead_task); -} - -/* - * This gets called before we allocate a new thread and copy - * the current task into it. - */ -void prepare_to_copy(struct task_struct *tsk) -{ - unlazy_fpu(tsk); -} - -int copy_thread(int nr, unsigned long clone_flags, unsigned long esp, - unsigned long unused, - struct task_struct * p, struct pt_regs * regs) -{ - struct pt_regs * childregs; - struct task_struct *tsk; - int err; - - childregs = ((struct pt_regs *) (THREAD_SIZE + (unsigned long) p->thread_info)) - 1; - /* - * The below -8 is to reserve 8 bytes on top of the ring0 stack. - * This is necessary to guarantee that the entire "struct pt_regs" - * is accessable even if the CPU haven't stored the SS/ESP registers - * on the stack (interrupt gate does not save these registers - * when switching to the same priv ring). - * Therefore beware: accessing the xss/esp fields of the - * "struct pt_regs" is possible, but they may contain the - * completely wrong values. - */ - childregs = (struct pt_regs *) ((unsigned long) childregs - 8); - *childregs = *regs; - childregs->eax = 0; - childregs->esp = esp; - - p->thread.esp = (unsigned long) childregs; - p->thread.esp0 = (unsigned long) (childregs+1); - - p->thread.eip = (unsigned long) ret_from_fork; - - savesegment(fs,p->thread.fs); - savesegment(gs,p->thread.gs); - - tsk = current; - if (unlikely(NULL != tsk->thread.io_bitmap_ptr)) { - p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL); - if (!p->thread.io_bitmap_ptr) { - p->thread.io_bitmap_max = 0; - return -ENOMEM; - } - memcpy(p->thread.io_bitmap_ptr, tsk->thread.io_bitmap_ptr, - IO_BITMAP_BYTES); - } - - /* - * Set a new TLS for the child thread? - */ - if (clone_flags & CLONE_SETTLS) { - struct desc_struct *desc; - struct user_desc info; - int idx; - - err = -EFAULT; - if (copy_from_user(&info, (void __user *)childregs->esi, sizeof(info))) - goto out; - err = -EINVAL; - if (LDT_empty(&info)) - goto out; - - idx = info.entry_number; - if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX) - goto out; - - desc = p->thread.tls_array + idx - GDT_ENTRY_TLS_MIN; - desc->a = LDT_entry_a(&info); - desc->b = LDT_entry_b(&info); - } - - p->thread.io_pl = current->thread.io_pl; - - err = 0; - out: - if (err && p->thread.io_bitmap_ptr) { - kfree(p->thread.io_bitmap_ptr); - p->thread.io_bitmap_max = 0; - } - return err; -} - -/* - * fill in the user structure for a core dump.. - */ -void dump_thread(struct pt_regs * regs, struct user * dump) -{ - int i; - -/* changed the size calculations - should hopefully work better. lbt */ - dump->magic = CMAGIC; - dump->start_code = 0; - dump->start_stack = regs->esp & ~(PAGE_SIZE - 1); - dump->u_tsize = ((unsigned long) current->mm->end_code) >> PAGE_SHIFT; - dump->u_dsize = ((unsigned long) (current->mm->brk + (PAGE_SIZE-1))) >> PAGE_SHIFT; - dump->u_dsize -= dump->u_tsize; - dump->u_ssize = 0; - for (i = 0; i < 8; i++) - dump->u_debugreg[i] = current->thread.debugreg[i]; - - if (dump->start_stack < TASK_SIZE) - dump->u_ssize = ((unsigned long) (TASK_SIZE - dump->start_stack)) >> PAGE_SHIFT; - - dump->regs.ebx = regs->ebx; - dump->regs.ecx = regs->ecx; - dump->regs.edx = regs->edx; - dump->regs.esi = regs->esi; - dump->regs.edi = regs->edi; - dump->regs.ebp = regs->ebp; - dump->regs.eax = regs->eax; - dump->regs.ds = regs->xds; - dump->regs.es = regs->xes; - savesegment(fs,dump->regs.fs); - savesegment(gs,dump->regs.gs); - dump->regs.orig_eax = regs->orig_eax; - dump->regs.eip = regs->eip; - dump->regs.cs = regs->xcs; - dump->regs.eflags = regs->eflags; - dump->regs.esp = regs->esp; - dump->regs.ss = regs->xss; - - dump->u_fpvalid = dump_fpu (regs, &dump->i387); -} - -/* - * Capture the user space registers if the task is not running (in user space) - */ -int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs) -{ - struct pt_regs ptregs; - - ptregs = *(struct pt_regs *) - ((unsigned long)tsk->thread_info+THREAD_SIZE - sizeof(ptregs)); - ptregs.xcs &= 0xffff; - ptregs.xds &= 0xffff; - ptregs.xes &= 0xffff; - ptregs.xss &= 0xffff; - - elf_core_copy_regs(regs, &ptregs); - - boot_option_idle_override = 1; - return 1; -} - -/* - * switch_to(x,yn) should switch tasks from x to y. - * - * We fsave/fwait so that an exception goes off at the right time - * (as a call from the fsave or fwait in effect) rather than to - * the wrong process. Lazy FP saving no longer makes any sense - * with modern CPU's, and this simplifies a lot of things (SMP - * and UP become the same). - * - * NOTE! We used to use the x86 hardware context switching. The - * reason for not using it any more becomes apparent when you - * try to recover gracefully from saved state that is no longer - * valid (stale segment register values in particular). With the - * hardware task-switch, there is no way to fix up bad state in - * a reasonable manner. - * - * The fact that Intel documents the hardware task-switching to - * be slow is a fairly red herring - this code is not noticeably - * faster. However, there _is_ some room for improvement here, - * so the performance issues may eventually be a valid point. - * More important, however, is the fact that this allows us much - * more flexibility. - * - * The return value (in %eax) will be the "prev" task after - * the task-switch, and shows up in ret_from_fork in entry.S, - * for example. - */ -struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct task_struct *next_p) -{ - struct thread_struct *prev = &prev_p->thread, - *next = &next_p->thread; - int cpu = smp_processor_id(); - struct tss_struct *tss = &per_cpu(init_tss, cpu); - physdev_op_t iopl_op, iobmp_op; - multicall_entry_t _mcl[8], *mcl = _mcl; - - /* XEN NOTE: FS/GS saved in switch_mm(), not here. */ - - /* - * This is basically '__unlazy_fpu', except that we queue a - * multicall to indicate FPU task switch, rather than - * synchronously trapping to Xen. - */ - if (prev_p->thread_info->status & TS_USEDFPU) { - __save_init_fpu(prev_p); /* _not_ save_init_fpu() */ - mcl->op = __HYPERVISOR_fpu_taskswitch; - mcl->args[0] = 1; - mcl++; - } -#if 0 /* lazy fpu sanity check */ - else BUG_ON(!(read_cr0() & 8)); -#endif - - /* - * Reload esp0, LDT and the page table pointer: - * This is load_esp0(tss, next) with a multicall. - */ - tss->esp0 = next->esp0; - mcl->op = __HYPERVISOR_stack_switch; - mcl->args[0] = tss->ss0; - mcl->args[1] = tss->esp0; - mcl++; - - /* - * Load the per-thread Thread-Local Storage descriptor. - * This is load_TLS(next, cpu) with multicalls. - */ -#define C(i) do { \ - if (unlikely(next->tls_array[i].a != prev->tls_array[i].a || \ - next->tls_array[i].b != prev->tls_array[i].b)) { \ - mcl->op = __HYPERVISOR_update_descriptor; \ - *(u64 *)&mcl->args[0] = virt_to_machine( \ - &get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN + i]);\ - *(u64 *)&mcl->args[2] = *(u64 *)&next->tls_array[i]; \ - mcl++; \ - } \ -} while (0) - C(0); C(1); C(2); -#undef C - - if (unlikely(prev->io_pl != next->io_pl)) { - iopl_op.cmd = PHYSDEVOP_SET_IOPL; - iopl_op.u.set_iopl.iopl = (next->io_pl == 0) ? 1 : next->io_pl; - mcl->op = __HYPERVISOR_physdev_op; - mcl->args[0] = (unsigned long)&iopl_op; - mcl++; - } - - if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr)) { - iobmp_op.cmd = - PHYSDEVOP_SET_IOBITMAP; - iobmp_op.u.set_iobitmap.bitmap = - (char *)next->io_bitmap_ptr; - iobmp_op.u.set_iobitmap.nr_ports = - next->io_bitmap_ptr ? IO_BITMAP_BITS : 0; - mcl->op = __HYPERVISOR_physdev_op; - mcl->args[0] = (unsigned long)&iobmp_op; - mcl++; - } - - (void)HYPERVISOR_multicall(_mcl, mcl - _mcl); - - /* - * Restore %fs and %gs if needed. - */ - if (unlikely(next->fs | next->gs)) { - loadsegment(fs, next->fs); - loadsegment(gs, next->gs); - } - - /* - * Now maybe reload the debug registers - */ - if (unlikely(next->debugreg[7])) { - loaddebug(next, 0); - loaddebug(next, 1); - loaddebug(next, 2); - loaddebug(next, 3); - /* no 4 and 5 */ - loaddebug(next, 6); - loaddebug(next, 7); - } - - return prev_p; -} - -asmlinkage int sys_fork(struct pt_regs regs) -{ - return do_fork(SIGCHLD, regs.esp, &regs, 0, NULL, NULL); -} - -asmlinkage int sys_clone(struct pt_regs regs) -{ - unsigned long clone_flags; - unsigned long newsp; - int __user *parent_tidptr, *child_tidptr; - - clone_flags = regs.ebx; - newsp = regs.ecx; - parent_tidptr = (int __user *)regs.edx; - child_tidptr = (int __user *)regs.edi; - if (!newsp) - newsp = regs.esp; - return do_fork(clone_flags, newsp, &regs, 0, parent_tidptr, child_tidptr); -} - -/* - * This is trivial, and on the face of it looks like it - * could equally well be done in user mode. - * - * Not so, for quite unobvious reasons - register pressure. - * In user mode vfork() cannot have a stack frame, and if - * done by calling the "clone()" system call directly, you - * do not have enough call-clobbered registers to hold all - * the information you need. - */ -asmlinkage int sys_vfork(struct pt_regs regs) -{ - return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs.esp, &regs, 0, NULL, NULL); -} - -/* - * sys_execve() executes a new program. - */ -asmlinkage int sys_execve(struct pt_regs regs) -{ - int error; - char * filename; - - filename = getname((char __user *) regs.ebx); - error = PTR_ERR(filename); - if (IS_ERR(filename)) - goto out; - error = do_execve(filename, - (char __user * __user *) regs.ecx, - (char __user * __user *) regs.edx, - &regs); - if (error == 0) { - task_lock(current); - current->ptrace &= ~PT_DTRACE; - task_unlock(current); - /* Make sure we don't return using sysenter.. */ - set_thread_flag(TIF_IRET); - } - putname(filename); -out: - return error; -} - -#define top_esp (THREAD_SIZE - sizeof(unsigned long)) -#define top_ebp (THREAD_SIZE - 2*sizeof(unsigned long)) - -unsigned long get_wchan(struct task_struct *p) -{ - unsigned long ebp, esp, eip; - unsigned long stack_page; - int count = 0; - if (!p || p == current || p->state == TASK_RUNNING) - return 0; - stack_page = (unsigned long)p->thread_info; - esp = p->thread.esp; - if (!stack_page || esp < stack_page || esp > top_esp+stack_page) - return 0; - /* include/asm-i386/system.h:switch_to() pushes ebp last. */ - ebp = *(unsigned long *) esp; - do { - if (ebp < stack_page || ebp > top_ebp+stack_page) - return 0; - eip = *(unsigned long *) (ebp+4); - if (!in_sched_functions(eip)) - return eip; - ebp = *(unsigned long *) ebp; - } while (count++ < 16); - return 0; -} - -/* - * sys_alloc_thread_area: get a yet unused TLS descriptor index. - */ -static int get_free_idx(void) -{ - struct thread_struct *t = &current->thread; - int idx; - - for (idx = 0; idx < GDT_ENTRY_TLS_ENTRIES; idx++) - if (desc_empty(t->tls_array + idx)) - return idx + GDT_ENTRY_TLS_MIN; - return -ESRCH; -} - -/* - * Set a given TLS descriptor: - */ -asmlinkage int sys_set_thread_area(struct user_desc __user *u_info) -{ - struct thread_struct *t = &current->thread; - struct user_desc info; - struct desc_struct *desc; - int cpu, idx; - - if (copy_from_user(&info, u_info, sizeof(info))) - return -EFAULT; - idx = info.entry_number; - - /* - * index -1 means the kernel should try to find and - * allocate an empty descriptor: - */ - if (idx == -1) { - idx = get_free_idx(); - if (idx < 0) - return idx; - if (put_user(idx, &u_info->entry_number)) - return -EFAULT; - } - - if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX) - return -EINVAL; - - desc = t->tls_array + idx - GDT_ENTRY_TLS_MIN; - - /* - * We must not get preempted while modifying the TLS. - */ - cpu = get_cpu(); - - if (LDT_empty(&info)) { - desc->a = 0; - desc->b = 0; - } else { - desc->a = LDT_entry_a(&info); - desc->b = LDT_entry_b(&info); - } - load_TLS(t, cpu); - - put_cpu(); - - return 0; -} - -/* - * Get the current Thread-Local Storage area: - */ - -#define GET_BASE(desc) ( \ - (((desc)->a >> 16) & 0x0000ffff) | \ - (((desc)->b << 16) & 0x00ff0000) | \ - ( (desc)->b & 0xff000000) ) - -#define GET_LIMIT(desc) ( \ - ((desc)->a & 0x0ffff) | \ - ((desc)->b & 0xf0000) ) - -#define GET_32BIT(desc) (((desc)->b >> 22) & 1) -#define GET_CONTENTS(desc) (((desc)->b >> 10) & 3) -#define GET_WRITABLE(desc) (((desc)->b >> 9) & 1) -#define GET_LIMIT_PAGES(desc) (((desc)->b >> 23) & 1) -#define GET_PRESENT(desc) (((desc)->b >> 15) & 1) -#define GET_USEABLE(desc) (((desc)->b >> 20) & 1) - -asmlinkage int sys_get_thread_area(struct user_desc __user *u_info) -{ - struct user_desc info; - struct desc_struct *desc; - int idx; - - if (get_user(idx, &u_info->entry_number)) - return -EFAULT; - if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX) - return -EINVAL; - - desc = current->thread.tls_array + idx - GDT_ENTRY_TLS_MIN; - - info.entry_number = idx; - info.base_addr = GET_BASE(desc); - info.limit = GET_LIMIT(desc); - info.seg_32bit = GET_32BIT(desc); - info.contents = GET_CONTENTS(desc); - info.read_exec_only = !GET_WRITABLE(desc); - info.limit_in_pages = GET_LIMIT_PAGES(desc); - info.seg_not_present = !GET_PRESENT(desc); - info.useable = GET_USEABLE(desc); - - if (copy_to_user(u_info, &info, sizeof(info))) - return -EFAULT; - return 0; -} - -unsigned long arch_align_stack(unsigned long sp) -{ - if (randomize_va_space) - sp -= get_random_int() % 8192; - return sp & ~0xf; -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/quirks.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/quirks.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,49 +0,0 @@ -/* - * This file contains work-arounds for x86 and x86_64 platform bugs. - */ -#include <linux/config.h> -#include <linux/pci.h> -#include <linux/irq.h> - -#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_SMP) && defined(CONFIG_PCI) - -static void __devinit quirk_intel_irqbalance(struct pci_dev *dev) -{ - u8 config, rev; - u32 word; - - /* BIOS may enable hardware IRQ balancing for - * E7520/E7320/E7525(revision ID 0x9 and below) - * based platforms. - * Disable SW irqbalance/affinity on those platforms. - */ - pci_read_config_byte(dev, PCI_CLASS_REVISION, &rev); - if (rev > 0x9) - return; - - printk(KERN_INFO "Intel E7520/7320/7525 detected."); - - /* enable access to config space*/ - pci_read_config_byte(dev, 0xf4, &config); - config |= 0x2; - pci_write_config_byte(dev, 0xf4, config); - - /* read xTPR register */ - raw_pci_ops->read(0, 0, 0x40, 0x4c, 2, &word); - - if (!(word & (1 << 13))) { - dom0_op_t op; - printk(KERN_INFO "Disabling irq balancing and affinity\n"); - op.cmd = DOM0_PLATFORM_QUIRK; - op.u.platform_quirk.quirk_id = QUIRK_NOIRQBALANCING; - (void)HYPERVISOR_dom0_op(&op); - } - - config &= ~0x2; - /* disable access to config space*/ - pci_write_config_byte(dev, 0xf4, config); -} -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7320_MCH, quirk_intel_irqbalance); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7525_MCH, quirk_intel_irqbalance); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E7520_MCH, quirk_intel_irqbalance); -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/setup.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/setup.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,1790 +0,0 @@ -/* - * linux/arch/i386/kernel/setup.c - * - * Copyright (C) 1995 Linus Torvalds - * - * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 - * - * Memory region support - * David Parsons <orc@xxxxxxxxxxxxxx>, July-August 1999 - * - * Added E820 sanitization routine (removes overlapping memory regions); - * Brian Moyle <bmoyle@xxxxxxxxxx>, February 2001 - * - * Moved CPU detection code to cpu/${cpu}.c - * Patrick Mochel <mochel@xxxxxxxx>, March 2002 - * - * Provisions for empty E820 memory regions (reported by certain BIOSes). - * Alex Achenbach <xela@xxxxxxx>, December 2002. - * - */ - -/* - * This file handles the architecture-dependent parts of initialization - */ - -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/tty.h> -#include <linux/ioport.h> -#include <linux/acpi.h> -#include <linux/apm_bios.h> -#include <linux/initrd.h> -#include <linux/bootmem.h> -#include <linux/seq_file.h> -#include <linux/console.h> -#include <linux/mca.h> -#include <linux/root_dev.h> -#include <linux/highmem.h> -#include <linux/module.h> -#include <linux/efi.h> -#include <linux/init.h> -#include <linux/edd.h> -#include <linux/nodemask.h> -#include <linux/kernel.h> -#include <linux/percpu.h> -#include <linux/notifier.h> -#include <video/edid.h> -#include <asm/e820.h> -#include <asm/mpspec.h> -#include <asm/setup.h> -#include <asm/arch_hooks.h> -#include <asm/sections.h> -#include <asm/io_apic.h> -#include <asm/ist.h> -#include <asm/io.h> -#include <asm/hypervisor.h> -#include <asm-xen/xen-public/physdev.h> -#include <asm-xen/xen-public/memory.h> -#include <asm-xen/features.h> -#include "setup_arch_pre.h" -#include <bios_ebda.h> - -/* Allows setting of maximum possible memory size */ -static unsigned long xen_override_max_pfn; - -static int xen_panic_event(struct notifier_block *, unsigned long, void *); -static struct notifier_block xen_panic_block = { - xen_panic_event, NULL, 0 /* try to go last */ -}; - -extern char hypercall_page[PAGE_SIZE]; -EXPORT_SYMBOL(hypercall_page); - -int disable_pse __initdata = 0; - -/* - * Machine setup.. - */ - -#ifdef CONFIG_EFI -int efi_enabled = 0; -EXPORT_SYMBOL(efi_enabled); -#endif - -/* cpu data as detected by the assembly code in head.S */ -struct cpuinfo_x86 new_cpu_data __initdata = { 0, 0, 0, 0, -1, 0, 1, 0, -1 }; -/* common cpu data for all cpus */ -struct cpuinfo_x86 boot_cpu_data = { 0, 0, 0, 0, -1, 0, 1, 0, -1 }; - -unsigned long mmu_cr4_features; - -#ifdef CONFIG_ACPI_INTERPRETER - int acpi_disabled = 0; -#else - int acpi_disabled = 1; -#endif -EXPORT_SYMBOL(acpi_disabled); - -#ifdef CONFIG_ACPI_BOOT -int __initdata acpi_force = 0; -extern acpi_interrupt_flags acpi_sci_flags; -#endif - -/* for MCA, but anyone else can use it if they want */ -unsigned int machine_id; -unsigned int machine_submodel_id; -unsigned int BIOS_revision; -unsigned int mca_pentium_flag; - -/* For PCI or other memory-mapped resources */ -unsigned long pci_mem_start = 0x10000000; - -/* Boot loader ID as an integer, for the benefit of proc_dointvec */ -int bootloader_type; - -/* user-defined highmem size */ -static unsigned int highmem_pages = -1; - -/* - * Setup options - */ -struct drive_info_struct { char dummy[32]; } drive_info; -struct screen_info screen_info; -struct apm_info apm_info; -struct sys_desc_table_struct { - unsigned short length; - unsigned char table[0]; -}; -struct edid_info edid_info; -struct ist_info ist_info; -struct e820map e820; - -extern void early_cpu_init(void); -extern void dmi_scan_machine(void); -extern void generic_apic_probe(char *); -extern int root_mountflags; - -unsigned long saved_videomode; - -#define RAMDISK_IMAGE_START_MASK 0x07FF -#define RAMDISK_PROMPT_FLAG 0x8000 -#define RAMDISK_LOAD_FLAG 0x4000 - -static char command_line[COMMAND_LINE_SIZE]; - -unsigned char __initdata boot_params[PARAM_SIZE]; - -static struct resource data_resource = { - .name = "Kernel data", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM -}; - -static struct resource code_resource = { - .name = "Kernel code", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM -}; - -#ifdef CONFIG_XEN_PRIVILEGED_GUEST -static struct resource system_rom_resource = { - .name = "System ROM", - .start = 0xf0000, - .end = 0xfffff, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -}; - -static struct resource extension_rom_resource = { - .name = "Extension ROM", - .start = 0xe0000, - .end = 0xeffff, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -}; - -static struct resource adapter_rom_resources[] = { { - .name = "Adapter ROM", - .start = 0xc8000, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -}, { - .name = "Adapter ROM", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -}, { - .name = "Adapter ROM", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -}, { - .name = "Adapter ROM", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -}, { - .name = "Adapter ROM", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -}, { - .name = "Adapter ROM", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -} }; - -#define ADAPTER_ROM_RESOURCES \ - (sizeof adapter_rom_resources / sizeof adapter_rom_resources[0]) - -static struct resource video_rom_resource = { - .name = "Video ROM", - .start = 0xc0000, - .end = 0xc7fff, - .flags = IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM -}; -#endif - -static struct resource video_ram_resource = { - .name = "Video RAM area", - .start = 0xa0000, - .end = 0xbffff, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM -}; - -static struct resource standard_io_resources[] = { { - .name = "dma1", - .start = 0x0000, - .end = 0x001f, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -}, { - .name = "pic1", - .start = 0x0020, - .end = 0x0021, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -}, { - .name = "timer0", - .start = 0x0040, - .end = 0x0043, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -}, { - .name = "timer1", - .start = 0x0050, - .end = 0x0053, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -}, { - .name = "keyboard", - .start = 0x0060, - .end = 0x006f, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -}, { - .name = "dma page reg", - .start = 0x0080, - .end = 0x008f, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -}, { - .name = "pic2", - .start = 0x00a0, - .end = 0x00a1, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -}, { - .name = "dma2", - .start = 0x00c0, - .end = 0x00df, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -}, { - .name = "fpu", - .start = 0x00f0, - .end = 0x00ff, - .flags = IORESOURCE_BUSY | IORESOURCE_IO -} }; - -#define STANDARD_IO_RESOURCES \ - (sizeof standard_io_resources / sizeof standard_io_resources[0]) - -#ifdef CONFIG_XEN_PRIVILEGED_GUEST -#define romsignature(x) (*(unsigned short *)(x) == 0xaa55) - -static int __init romchecksum(unsigned char *rom, unsigned long length) -{ - unsigned char *p, sum = 0; - - for (p = rom; p < rom + length; p++) - sum += *p; - return sum == 0; -} - -static void __init probe_roms(void) -{ - unsigned long start, length, upper; - unsigned char *rom; - int i; - - /* Nothing to do if not running in dom0. */ - if (!(xen_start_info->flags & SIF_INITDOMAIN)) - return; - - /* video rom */ - upper = adapter_rom_resources[0].start; - for (start = video_rom_resource.start; start < upper; start += 2048) { - rom = isa_bus_to_virt(start); - if (!romsignature(rom)) - continue; - - video_rom_resource.start = start; - - /* 0 < length <= 0x7f * 512, historically */ - length = rom[2] * 512; - - /* if checksum okay, trust length byte */ - if (length && romchecksum(rom, length)) - video_rom_resource.end = start + length - 1; - - request_resource(&iomem_resource, &video_rom_resource); - break; - } - - start = (video_rom_resource.end + 1 + 2047) & ~2047UL; - if (start < upper) - start = upper; - - /* system rom */ - request_resource(&iomem_resource, &system_rom_resource); - upper = system_rom_resource.start; - - /* check for extension rom (ignore length byte!) */ - rom = isa_bus_to_virt(extension_rom_resource.start); - if (romsignature(rom)) { - length = extension_rom_resource.end - extension_rom_resource.start + 1; - if (romchecksum(rom, length)) { - request_resource(&iomem_resource, &extension_rom_resource); - upper = extension_rom_resource.start; - } - } - - /* check for adapter roms on 2k boundaries */ - for (i = 0; i < ADAPTER_ROM_RESOURCES && start < upper; start += 2048) { - rom = isa_bus_to_virt(start); - if (!romsignature(rom)) - continue; - - /* 0 < length <= 0x7f * 512, historically */ - length = rom[2] * 512; - - /* but accept any length that fits if checksum okay */ - if (!length || start + length > upper || !romchecksum(rom, length)) - continue; - - adapter_rom_resources[i].start = start; - adapter_rom_resources[i].end = start + length - 1; - request_resource(&iomem_resource, &adapter_rom_resources[i]); - - start = adapter_rom_resources[i++].end & ~2047UL; - } -} -#endif - -/* - * Point at the empty zero page to start with. We map the real shared_info - * page as soon as fixmap is up and running. - */ -shared_info_t *HYPERVISOR_shared_info = (shared_info_t *)empty_zero_page; -EXPORT_SYMBOL(HYPERVISOR_shared_info); - -unsigned long *phys_to_machine_mapping; -unsigned long *pfn_to_mfn_frame_list_list, *pfn_to_mfn_frame_list[16]; -EXPORT_SYMBOL(phys_to_machine_mapping); - -/* Raw start-of-day parameters from the hypervisor. */ -start_info_t *xen_start_info; -EXPORT_SYMBOL(xen_start_info); - -static void __init limit_regions(unsigned long long size) -{ - unsigned long long current_addr = 0; - int i; - - if (efi_enabled) { - for (i = 0; i < memmap.nr_map; i++) { - current_addr = memmap.map[i].phys_addr + - (memmap.map[i].num_pages << 12); - if (memmap.map[i].type == EFI_CONVENTIONAL_MEMORY) { - if (current_addr >= size) { - memmap.map[i].num_pages -= - (((current_addr-size) + PAGE_SIZE-1) >> PAGE_SHIFT); - memmap.nr_map = i + 1; - return; - } - } - } - } - for (i = 0; i < e820.nr_map; i++) { - if (e820.map[i].type == E820_RAM) { - current_addr = e820.map[i].addr + e820.map[i].size; - if (current_addr >= size) { - e820.map[i].size -= current_addr-size; - e820.nr_map = i + 1; - return; - } - } - } -} - -static void __init add_memory_region(unsigned long long start, - unsigned long long size, int type) -{ - int x; - - if (!efi_enabled) { - x = e820.nr_map; - - if (x == E820MAX) { - printk(KERN_ERR "Ooops! Too many entries in the memory map!\n"); - return; - } - - e820.map[x].addr = start; - e820.map[x].size = size; - e820.map[x].type = type; - e820.nr_map++; - } -} /* add_memory_region */ - -#define E820_DEBUG 1 - -static void __init print_memory_map(char *who) -{ - int i; - - for (i = 0; i < e820.nr_map; i++) { - printk(" %s: %016Lx - %016Lx ", who, - e820.map[i].addr, - e820.map[i].addr + e820.map[i].size); - switch (e820.map[i].type) { - case E820_RAM: printk("(usable)\n"); - break; - case E820_RESERVED: - printk("(reserved)\n"); - break; - case E820_ACPI: - printk("(ACPI data)\n"); - break; - case E820_NVS: - printk("(ACPI NVS)\n"); - break; - default: printk("type %lu\n", e820.map[i].type); - break; - } - } -} - -#if 0 -/* - * Sanitize the BIOS e820 map. - * - * Some e820 responses include overlapping entries. The following - * replaces the original e820 map with a new one, removing overlaps. - * - */ -struct change_member { - struct e820entry *pbios; /* pointer to original bios entry */ - unsigned long long addr; /* address for this change point */ -}; -static struct change_member change_point_list[2*E820MAX] __initdata; -static struct change_member *change_point[2*E820MAX] __initdata; -static struct e820entry *overlap_list[E820MAX] __initdata; -static struct e820entry new_bios[E820MAX] __initdata; - -static int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map) -{ - struct change_member *change_tmp; - unsigned long current_type, last_type; - unsigned long long last_addr; - int chgidx, still_changing; - int overlap_entries; - int new_bios_entry; - int old_nr, new_nr, chg_nr; - int i; - - /* - Visually we're performing the following (1,2,3,4 = memory types)... - - Sample memory map (w/overlaps): - ____22__________________ - ______________________4_ - ____1111________________ - _44_____________________ - 11111111________________ - ____________________33__ - ___________44___________ - __________33333_________ - ______________22________ - ___________________2222_ - _________111111111______ - _____________________11_ - _________________4______ - - Sanitized equivalent (no overlap): - 1_______________________ - _44_____________________ - ___1____________________ - ____22__________________ - ______11________________ - _________1______________ - __________3_____________ - ___________44___________ - _____________33_________ - _______________2________ - ________________1_______ - _________________4______ - ___________________2____ - ____________________33__ - ______________________4_ - */ - - /* if there's only one memory region, don't bother */ - if (*pnr_map < 2) - return -1; - - old_nr = *pnr_map; - - /* bail out if we find any unreasonable addresses in bios map */ - for (i=0; i<old_nr; i++) - if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr) - return -1; - - /* create pointers for initial change-point information (for sorting) */ - for (i=0; i < 2*old_nr; i++) - change_point[i] = &change_point_list[i]; - - /* record all known change-points (starting and ending addresses), - omitting those that are for empty memory regions */ - chgidx = 0; - for (i=0; i < old_nr; i++) { - if (biosmap[i].size != 0) { - change_point[chgidx]->addr = biosmap[i].addr; - change_point[chgidx++]->pbios = &biosmap[i]; - change_point[chgidx]->addr = biosmap[i].addr + biosmap[i].size; - change_point[chgidx++]->pbios = &biosmap[i]; - } - } - chg_nr = chgidx; /* true number of change-points */ - - /* sort change-point list by memory addresses (low -> high) */ - still_changing = 1; - while (still_changing) { - still_changing = 0; - for (i=1; i < chg_nr; i++) { - /* if <current_addr> > <last_addr>, swap */ - /* or, if current=<start_addr> & last=<end_addr>, swap */ - if ((change_point[i]->addr < change_point[i-1]->addr) || - ((change_point[i]->addr == change_point[i-1]->addr) && - (change_point[i]->addr == change_point[i]->pbios->addr) && - (change_point[i-1]->addr != change_point[i-1]->pbios->addr)) - ) - { - change_tmp = change_point[i]; - change_point[i] = change_point[i-1]; - change_point[i-1] = change_tmp; - still_changing=1; - } - } - } - - /* create a new bios memory map, removing overlaps */ - overlap_entries=0; /* number of entries in the overlap table */ - new_bios_entry=0; /* index for creating new bios map entries */ - last_type = 0; /* start with undefined memory type */ - last_addr = 0; /* start with 0 as last starting address */ - /* loop through change-points, determining affect on the new bios map */ - for (chgidx=0; chgidx < chg_nr; chgidx++) - { - /* keep track of all overlapping bios entries */ - if (change_point[chgidx]->addr == change_point[chgidx]->pbios->addr) - { - /* add map entry to overlap list (> 1 entry implies an overlap) */ - overlap_list[overlap_entries++]=change_point[chgidx]->pbios; - } - else - { - /* remove entry from list (order independent, so swap with last) */ - for (i=0; i<overlap_entries; i++) - { - if (overlap_list[i] == change_point[chgidx]->pbios) - overlap_list[i] = overlap_list[overlap_entries-1]; - } - overlap_entries--; - } - /* if there are overlapping entries, decide which "type" to use */ - /* (larger value takes precedence -- 1=usable, 2,3,4,4+=unusable) */ - current_type = 0; - for (i=0; i<overlap_entries; i++) - if (overlap_list[i]->type > current_type) - current_type = overlap_list[i]->type; - /* continue building up new bios map based on this information */ - if (current_type != last_type) { - if (last_type != 0) { - new_bios[new_bios_entry].size = - change_point[chgidx]->addr - last_addr; - /* move forward only if the new size was non-zero */ - if (new_bios[new_bios_entry].size != 0) - if (++new_bios_entry >= E820MAX) - break; /* no more space left for new bios entries */ - } - if (current_type != 0) { - new_bios[new_bios_entry].addr = change_point[chgidx]->addr; - new_bios[new_bios_entry].type = current_type; - last_addr=change_point[chgidx]->addr; - } - last_type = current_type; - } - } - new_nr = new_bios_entry; /* retain count for new bios entries */ - - /* copy new bios mapping into original location */ - memcpy(biosmap, new_bios, new_nr*sizeof(struct e820entry)); - *pnr_map = new_nr; - - return 0; -} - -/* - * Copy the BIOS e820 map into a safe place. - * - * Sanity-check it while we're at it.. - * - * If we're lucky and live on a modern system, the setup code - * will have given us a memory map that we can use to properly - * set up memory. If we aren't, we'll fake a memory map. - * - * We check to see that the memory map contains at least 2 elements - * before we'll use it, because the detection code in setup.S may - * not be perfect and most every PC known to man has two memory - * regions: one from 0 to 640k, and one from 1mb up. (The IBM - * thinkpad 560x, for example, does not cooperate with the memory - * detection code.) - */ -static int __init copy_e820_map(struct e820entry * biosmap, int nr_map) -{ - /* Only one memory region (or negative)? Ignore it */ - if (nr_map < 2) - return -1; - - do { - unsigned long long start = biosmap->addr; - unsigned long long size = biosmap->size; - unsigned long long end = start + size; - unsigned long type = biosmap->type; - - /* Overflow in 64 bits? Ignore the memory map. */ - if (start > end) - return -1; - - /* - * Some BIOSes claim RAM in the 640k - 1M region. - * Not right. Fix it up. - */ - if (type == E820_RAM) { - if (start < 0x100000ULL && end > 0xA0000ULL) { - if (start < 0xA0000ULL) - add_memory_region(start, 0xA0000ULL-start, type); - if (end <= 0x100000ULL) - continue; - start = 0x100000ULL; - size = end - start; - } - } - add_memory_region(start, size, type); - } while (biosmap++,--nr_map); - return 0; -} -#endif - -#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE) -struct edd edd; -#ifdef CONFIG_EDD_MODULE -EXPORT_SYMBOL(edd); -#endif -/** - * copy_edd() - Copy the BIOS EDD information - * from boot_params into a safe place. - * - */ -static inline void copy_edd(void) -{ - memcpy(edd.mbr_signature, EDD_MBR_SIGNATURE, sizeof(edd.mbr_signature)); - memcpy(edd.edd_info, EDD_BUF, sizeof(edd.edd_info)); - edd.mbr_signature_nr = EDD_MBR_SIG_NR; - edd.edd_info_nr = EDD_NR; -} -#else -static inline void copy_edd(void) -{ -} -#endif - -/* - * Do NOT EVER look at the BIOS memory size location. - * It does not work on many machines. - */ -#define LOWMEMSIZE() (0x9f000) - -static void __init parse_cmdline_early (char ** cmdline_p) -{ - char c = ' ', *to = command_line, *from = saved_command_line; - int len = 0, max_cmdline; - int userdef = 0; - - if ((max_cmdline = MAX_GUEST_CMDLINE) > COMMAND_LINE_SIZE) - max_cmdline = COMMAND_LINE_SIZE; - memcpy(saved_command_line, xen_start_info->cmd_line, max_cmdline); - /* Save unparsed command line copy for /proc/cmdline */ - saved_command_line[max_cmdline-1] = '\0'; - - for (;;) { - if (c != ' ') - goto next_char; - /* - * "mem=nopentium" disables the 4MB page tables. - * "mem=XXX[kKmM]" defines a memory region from HIGH_MEM - * to <mem>, overriding the bios size. - * "memmap=XXX[KkmM]@XXX[KkmM]" defines a memory region from - * <start> to <start>+<mem>, overriding the bios size. - * - * HPA tells me bootloaders need to parse mem=, so no new - * option should be mem= [also see Documentation/i386/boot.txt] - */ - if (!memcmp(from, "mem=", 4)) { - if (to != command_line) - to--; - if (!memcmp(from+4, "nopentium", 9)) { - from += 9+4; - clear_bit(X86_FEATURE_PSE, boot_cpu_data.x86_capability); - disable_pse = 1; - } else { - /* If the user specifies memory size, we - * limit the BIOS-provided memory map to - * that size. exactmap can be used to specify - * the exact map. mem=number can be used to - * trim the existing memory map. - */ - unsigned long long mem_size; - - mem_size = memparse(from+4, &from); -#if 0 - limit_regions(mem_size); - userdef=1; -#else - xen_override_max_pfn = - (unsigned long)(mem_size>>PAGE_SHIFT); -#endif - } - } - - else if (!memcmp(from, "memmap=", 7)) { - if (to != command_line) - to--; - if (!memcmp(from+7, "exactmap", 8)) { - from += 8+7; - e820.nr_map = 0; - userdef = 1; - } else { - /* If the user specifies memory size, we - * limit the BIOS-provided memory map to - * that size. exactmap can be used to specify - * the exact map. mem=number can be used to - * trim the existing memory map. - */ - unsigned long long start_at, mem_size; - - mem_size = memparse(from+7, &from); - if (*from == '@') { - start_at = memparse(from+1, &from); - add_memory_region(start_at, mem_size, E820_RAM); - } else if (*from == '#') { - start_at = memparse(from+1, &from); - add_memory_region(start_at, mem_size, E820_ACPI); - } else if (*from == '$') { - start_at = memparse(from+1, &from); - add_memory_region(start_at, mem_size, E820_RESERVED); - } else { - limit_regions(mem_size); - userdef=1; - } - } - } - - else if (!memcmp(from, "noexec=", 7)) - noexec_setup(from + 7); - - -#ifdef CONFIG_X86_MPPARSE - /* - * If the BIOS enumerates physical processors before logical, - * maxcpus=N at enumeration-time can be used to disable HT. - */ - else if (!memcmp(from, "maxcpus=", 8)) { - extern unsigned int maxcpus; - - maxcpus = simple_strtoul(from + 8, NULL, 0); - } -#endif - -#ifdef CONFIG_ACPI_BOOT - /* "acpi=off" disables both ACPI table parsing and interpreter */ - else if (!memcmp(from, "acpi=off", 8)) { - disable_acpi(); - } - - /* acpi=force to over-ride black-list */ - else if (!memcmp(from, "acpi=force", 10)) { - acpi_force = 1; - acpi_ht = 1; - acpi_disabled = 0; - } - - /* acpi=strict disables out-of-spec workarounds */ - else if (!memcmp(from, "acpi=strict", 11)) { - acpi_strict = 1; - } - - /* Limit ACPI just to boot-time to enable HT */ - else if (!memcmp(from, "acpi=ht", 7)) { - if (!acpi_force) - disable_acpi(); - acpi_ht = 1; - } - - /* "pci=noacpi" disable ACPI IRQ routing and PCI scan */ - else if (!memcmp(from, "pci=noacpi", 10)) { - acpi_disable_pci(); - } - /* "acpi=noirq" disables ACPI interrupt routing */ - else if (!memcmp(from, "acpi=noirq", 10)) { - acpi_noirq_set(); - } - - else if (!memcmp(from, "acpi_sci=edge", 13)) - acpi_sci_flags.trigger = 1; - - else if (!memcmp(from, "acpi_sci=level", 14)) - acpi_sci_flags.trigger = 3; - - else if (!memcmp(from, "acpi_sci=high", 13)) - acpi_sci_flags.polarity = 1; - - else if (!memcmp(from, "acpi_sci=low", 12)) - acpi_sci_flags.polarity = 3; - -#ifdef CONFIG_X86_IO_APIC - else if (!memcmp(from, "acpi_skip_timer_override", 24)) - acpi_skip_timer_override = 1; -#endif - -#ifdef CONFIG_X86_LOCAL_APIC - /* disable IO-APIC */ - else if (!memcmp(from, "noapic", 6)) - disable_ioapic_setup(); -#endif /* CONFIG_X86_LOCAL_APIC */ -#endif /* CONFIG_ACPI_BOOT */ - - /* - * highmem=size forces highmem to be exactly 'size' bytes. - * This works even on boxes that have no highmem otherwise. - * This also works to reduce highmem size on bigger boxes. - */ - else if (!memcmp(from, "highmem=", 8)) - highmem_pages = memparse(from+8, &from) >> PAGE_SHIFT; - - /* - * vmalloc=size forces the vmalloc area to be exactly 'size' - * bytes. This can be used to increase (or decrease) the - * vmalloc area - the default is 128m. - */ - else if (!memcmp(from, "vmalloc=", 8)) - __VMALLOC_RESERVE = memparse(from+8, &from); - - next_char: - c = *(from++); - if (!c) - break; - if (COMMAND_LINE_SIZE <= ++len) - break; - *(to++) = c; - } - *to = '\0'; - *cmdline_p = command_line; - if (userdef) { - printk(KERN_INFO "user-defined physical RAM map:\n"); - print_memory_map("user"); - } -} - -#if 0 /* !XEN */ -/* - * Callback for efi_memory_walk. - */ -static int __init -efi_find_max_pfn(unsigned long start, unsigned long end, void *arg) -{ - unsigned long *max_pfn = arg, pfn; - - if (start < end) { - pfn = PFN_UP(end -1); - if (pfn > *max_pfn) - *max_pfn = pfn; - } - return 0; -} - - -/* - * Find the highest page frame number we have available - */ -void __init find_max_pfn(void) -{ - int i; - - max_pfn = 0; - if (efi_enabled) { - efi_memmap_walk(efi_find_max_pfn, &max_pfn); - return; - } - - for (i = 0; i < e820.nr_map; i++) { - unsigned long start, end; - /* RAM? */ - if (e820.map[i].type != E820_RAM) - continue; - start = PFN_UP(e820.map[i].addr); - end = PFN_DOWN(e820.map[i].addr + e820.map[i].size); - if (start >= end) - continue; - if (end > max_pfn) - max_pfn = end; - } -} -#else -/* We don't use the fake e820 because we need to respond to user override. */ -void __init find_max_pfn(void) -{ - if (xen_override_max_pfn == 0) { - max_pfn = xen_start_info->nr_pages; - /* Default 8MB slack (to balance backend allocations). */ - max_pfn += 8 << (20 - PAGE_SHIFT); - } else if (xen_override_max_pfn > xen_start_info->nr_pages) { - max_pfn = xen_override_max_pfn; - } else { - max_pfn = xen_start_info->nr_pages; - } -} -#endif /* XEN */ - -/* - * Determine low and high memory ranges: - */ -unsigned long __init find_max_low_pfn(void) -{ - unsigned long max_low_pfn; - - max_low_pfn = max_pfn; - if (max_low_pfn > MAXMEM_PFN) { - if (highmem_pages == -1) - highmem_pages = max_pfn - MAXMEM_PFN; - if (highmem_pages + MAXMEM_PFN < max_pfn) - max_pfn = MAXMEM_PFN + highmem_pages; - if (highmem_pages + MAXMEM_PFN > max_pfn) { - printk("only %luMB highmem pages available, ignoring highmem size of %uMB.\n", pages_to_mb(max_pfn - MAXMEM_PFN), pages_to_mb(highmem_pages)); - highmem_pages = 0; - } - max_low_pfn = MAXMEM_PFN; -#ifndef CONFIG_HIGHMEM - /* Maximum memory usable is what is directly addressable */ - printk(KERN_WARNING "Warning only %ldMB will be used.\n", - MAXMEM>>20); - if (max_pfn > MAX_NONPAE_PFN) - printk(KERN_WARNING "Use a PAE enabled kernel.\n"); - else - printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n"); - max_pfn = MAXMEM_PFN; -#else /* !CONFIG_HIGHMEM */ -#ifndef CONFIG_X86_PAE - if (max_pfn > MAX_NONPAE_PFN) { - max_pfn = MAX_NONPAE_PFN; - printk(KERN_WARNING "Warning only 4GB will be used.\n"); - printk(KERN_WARNING "Use a PAE enabled kernel.\n"); - } -#endif /* !CONFIG_X86_PAE */ -#endif /* !CONFIG_HIGHMEM */ - } else { - if (highmem_pages == -1) - highmem_pages = 0; -#ifdef CONFIG_HIGHMEM - if (highmem_pages >= max_pfn) { - printk(KERN_ERR "highmem size specified (%uMB) is bigger than pages available (%luMB)!.\n", pages_to_mb(highmem_pages), pages_to_mb(max_pfn)); - highmem_pages = 0; - } - if (highmem_pages) { - if (max_low_pfn-highmem_pages < 64*1024*1024/PAGE_SIZE){ - printk(KERN_ERR "highmem size %uMB results in smaller than 64MB lowmem, ignoring it.\n", pages_to_mb(highmem_pages)); - highmem_pages = 0; - } - max_low_pfn -= highmem_pages; - } -#else - if (highmem_pages) - printk(KERN_ERR "ignoring highmem size on non-highmem kernel!\n"); -#endif - } - return max_low_pfn; -} - -/* - * Free all available memory for boot time allocation. Used - * as a callback function by efi_memory_walk() - */ - -static int __init -free_available_memory(unsigned long start, unsigned long end, void *arg) -{ - /* check max_low_pfn */ - if (start >= ((max_low_pfn + 1) << PAGE_SHIFT)) - return 0; - if (end >= ((max_low_pfn + 1) << PAGE_SHIFT)) - end = (max_low_pfn + 1) << PAGE_SHIFT; - if (start < end) - free_bootmem(start, end - start); - - return 0; -} -/* - * Register fully available low RAM pages with the bootmem allocator. - */ -static void __init register_bootmem_low_pages(unsigned long max_low_pfn) -{ - int i; - - if (efi_enabled) { - efi_memmap_walk(free_available_memory, NULL); - return; - } - for (i = 0; i < e820.nr_map; i++) { - unsigned long curr_pfn, last_pfn, size; - /* - * Reserve usable low memory - */ - if (e820.map[i].type != E820_RAM) - continue; - /* - * We are rounding up the start address of usable memory: - */ - curr_pfn = PFN_UP(e820.map[i].addr); - if (curr_pfn >= max_low_pfn) - continue; - /* - * ... and at the end of the usable range downwards: - */ - last_pfn = PFN_DOWN(e820.map[i].addr + e820.map[i].size); - - if (last_pfn > max_low_pfn) - last_pfn = max_low_pfn; - - /* - * .. finally, did all the rounding and playing - * around just make the area go away? - */ - if (last_pfn <= curr_pfn) - continue; - - size = last_pfn - curr_pfn; - free_bootmem(PFN_PHYS(curr_pfn), PFN_PHYS(size)); - } -} - -#ifndef CONFIG_XEN -/* - * workaround for Dell systems that neglect to reserve EBDA - */ -static void __init reserve_ebda_region(void) -{ - unsigned int addr; - addr = get_bios_ebda(); - if (addr) - reserve_bootmem(addr, PAGE_SIZE); -} -#endif - -#ifndef CONFIG_DISCONTIGMEM -void __init setup_bootmem_allocator(void); -static unsigned long __init setup_memory(void) -{ - /* - * partially used pages are not usable - thus - * we are rounding upwards: - */ - min_low_pfn = PFN_UP(__pa(xen_start_info->pt_base)) + - xen_start_info->nr_pt_frames; - - find_max_pfn(); - - max_low_pfn = find_max_low_pfn(); - -#ifdef CONFIG_HIGHMEM - highstart_pfn = highend_pfn = max_pfn; - if (max_pfn > max_low_pfn) { - highstart_pfn = max_low_pfn; - } - printk(KERN_NOTICE "%ldMB HIGHMEM available.\n", - pages_to_mb(highend_pfn - highstart_pfn)); -#endif - printk(KERN_NOTICE "%ldMB LOWMEM available.\n", - pages_to_mb(max_low_pfn)); - - setup_bootmem_allocator(); - - return max_low_pfn; -} - -void __init zone_sizes_init(void) -{ - unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0}; - unsigned int max_dma, low; - - /* - * XEN: Our notion of "DMA memory" is fake when running over Xen. - * We simply put all RAM in the DMA zone so that those drivers which - * needlessly specify GFP_DMA do not get starved of RAM unnecessarily. - * Those drivers that *do* require lowmem are screwed anyway when - * running over Xen! - */ - max_dma = max_low_pfn; - low = max_low_pfn; - - if (low < max_dma) - zones_size[ZONE_DMA] = low; - else { - zones_size[ZONE_DMA] = max_dma; - zones_size[ZONE_NORMAL] = low - max_dma; -#ifdef CONFIG_HIGHMEM - zones_size[ZONE_HIGHMEM] = highend_pfn - low; -#endif - } - free_area_init(zones_size); -} -#else -extern unsigned long setup_memory(void); -extern void zone_sizes_init(void); -#endif /* !CONFIG_DISCONTIGMEM */ - -void __init setup_bootmem_allocator(void) -{ - unsigned long bootmap_size; - /* - * Initialize the boot-time allocator (with low memory only): - */ - bootmap_size = init_bootmem(min_low_pfn, max_low_pfn); - - register_bootmem_low_pages(max_low_pfn); - - /* - * Reserve the bootmem bitmap itself as well. We do this in two - * steps (first step was init_bootmem()) because this catches - * the (very unlikely) case of us accidentally initializing the - * bootmem allocator with an invalid RAM area. - */ - reserve_bootmem(HIGH_MEMORY, (PFN_PHYS(min_low_pfn) + - bootmap_size + PAGE_SIZE-1) - (HIGH_MEMORY)); - -#ifndef CONFIG_XEN - /* - * reserve physical page 0 - it's a special BIOS page on many boxes, - * enabling clean reboots, SMP operation, laptop functions. - */ - reserve_bootmem(0, PAGE_SIZE); - - /* reserve EBDA region, it's a 4K region */ - reserve_ebda_region(); - - /* could be an AMD 768MPX chipset. Reserve a page before VGA to prevent - PCI prefetch into it (errata #56). Usually the page is reserved anyways, - unless you have no PS/2 mouse plugged in. */ - if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD && - boot_cpu_data.x86 == 6) - reserve_bootmem(0xa0000 - 4096, 4096); - -#ifdef CONFIG_SMP - /* - * But first pinch a few for the stack/trampoline stuff - * FIXME: Don't need the extra page at 4K, but need to fix - * trampoline before removing it. (see the GDT stuff) - */ - reserve_bootmem(PAGE_SIZE, PAGE_SIZE); -#endif -#ifdef CONFIG_ACPI_SLEEP - /* - * Reserve low memory region for sleep support. - */ - acpi_reserve_bootmem(); -#endif -#endif /* !CONFIG_XEN */ - -#ifdef CONFIG_BLK_DEV_INITRD - if (xen_start_info->mod_start) { - if (INITRD_START + INITRD_SIZE <= (max_low_pfn << PAGE_SHIFT)) { - /*reserve_bootmem(INITRD_START, INITRD_SIZE);*/ - initrd_start = INITRD_START + PAGE_OFFSET; - initrd_end = initrd_start+INITRD_SIZE; - initrd_below_start_ok = 1; - } - else { - printk(KERN_ERR "initrd extends beyond end of memory " - "(0x%08lx > 0x%08lx)\ndisabling initrd\n", - INITRD_START + INITRD_SIZE, - max_low_pfn << PAGE_SHIFT); - initrd_start = 0; - } - } -#endif - - phys_to_machine_mapping = (unsigned long *)xen_start_info->mfn_list; -} - -/* - * The node 0 pgdat is initialized before all of these because - * it's needed for bootmem. node>0 pgdats have their virtual - * space allocated before the pagetables are in place to access - * them, so they can't be cleared then. - * - * This should all compile down to nothing when NUMA is off. - */ -void __init remapped_pgdat_init(void) -{ - int nid; - - for_each_online_node(nid) { - if (nid != 0) - memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); - } -} - -/* - * Request address space for all standard RAM and ROM resources - * and also for regions reported as reserved by the e820. - */ -static void __init -legacy_init_iomem_resources(struct resource *code_resource, struct resource *data_resource) -{ - int i; -#ifdef CONFIG_XEN - dom0_op_t op; - struct dom0_memory_map_entry *map; - unsigned long gapstart, gapsize; - unsigned long long last; -#endif - -#ifdef CONFIG_XEN_PRIVILEGED_GUEST - probe_roms(); -#endif - -#ifdef CONFIG_XEN - map = alloc_bootmem_low_pages(PAGE_SIZE); - op.cmd = DOM0_PHYSICAL_MEMORY_MAP; - op.u.physical_memory_map.memory_map = map; - op.u.physical_memory_map.max_map_entries = - PAGE_SIZE / sizeof(struct dom0_memory_map_entry); - BUG_ON(HYPERVISOR_dom0_op(&op)); - - last = 0x100000000ULL; - gapstart = 0x10000000; - gapsize = 0x400000; - - for (i = op.u.physical_memory_map.nr_map_entries - 1; i >= 0; i--) { - struct resource *res; - - if ((last > map[i].end) && ((last - map[i].end) > gapsize)) { - gapsize = last - map[i].end; - gapstart = map[i].end; - } - if (map[i].start < last) - last = map[i].start; - - if (map[i].end > 0x100000000ULL) - continue; - res = alloc_bootmem_low(sizeof(struct resource)); - res->name = map[i].is_ram ? "System RAM" : "reserved"; - res->start = map[i].start; - res->end = map[i].end - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; - request_resource(&iomem_resource, res); - } - - free_bootmem(__pa(map), PAGE_SIZE); - - /* - * Start allocating dynamic PCI memory a bit into the gap, - * aligned up to the nearest megabyte. - * - * Question: should we try to pad it up a bit (do something - * like " + (gapsize >> 3)" in there too?). We now have the - * technology. - */ - pci_mem_start = (gapstart + 0xfffff) & ~0xfffff; - - printk("Allocating PCI resources starting at %08lx (gap: %08lx:%08lx)\n", - pci_mem_start, gapstart, gapsize); -#else - for (i = 0; i < e820.nr_map; i++) { - struct resource *res; - if (e820.map[i].addr + e820.map[i].size > 0x100000000ULL) - continue; - res = alloc_bootmem_low(sizeof(struct resource)); - switch (e820.map[i].type) { - case E820_RAM: res->name = "System RAM"; break; - case E820_ACPI: res->name = "ACPI Tables"; break; - case E820_NVS: res->name = "ACPI Non-volatile Storage"; break; - default: res->name = "reserved"; - } - res->start = e820.map[i].addr; - res->end = res->start + e820.map[i].size - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; - request_resource(&iomem_resource, res); - if (e820.map[i].type == E820_RAM) { - /* - * We don't know which RAM region contains kernel data, - * so we try it repeatedly and let the resource manager - * test it. - */ - request_resource(res, code_resource); - request_resource(res, data_resource); - } - } -#endif -} - -/* - * Request address space for all standard resources - */ -static void __init register_memory(void) -{ -#ifndef CONFIG_XEN - unsigned long gapstart, gapsize; - unsigned long long last; -#endif - int i; - - /* Nothing to do if not running in dom0. */ - if (!(xen_start_info->flags & SIF_INITDOMAIN)) - return; - - if (efi_enabled) - efi_initialize_iomem_resources(&code_resource, &data_resource); - else - legacy_init_iomem_resources(&code_resource, &data_resource); - - /* EFI systems may still have VGA */ - request_resource(&iomem_resource, &video_ram_resource); - - /* request I/O space for devices used on all i[345]86 PCs */ - for (i = 0; i < STANDARD_IO_RESOURCES; i++) - request_resource(&ioport_resource, &standard_io_resources[i]); - -#ifndef CONFIG_XEN - /* - * Search for the bigest gap in the low 32 bits of the e820 - * memory space. - */ - last = 0x100000000ull; - gapstart = 0x10000000; - gapsize = 0x400000; - i = e820.nr_map; - while (--i >= 0) { - unsigned long long start = e820.map[i].addr; - unsigned long long end = start + e820.map[i].size; - - /* - * Since "last" is at most 4GB, we know we'll - * fit in 32 bits if this condition is true - */ - if (last > end) { - unsigned long gap = last - end; - - if (gap > gapsize) { - gapsize = gap; - gapstart = end; - } - } - if (start < last) - last = start; - } - - /* - * Start allocating dynamic PCI memory a bit into the gap, - * aligned up to the nearest megabyte. - * - * Question: should we try to pad it up a bit (do something - * like " + (gapsize >> 3)" in there too?). We now have the - * technology. - */ - pci_mem_start = (gapstart + 0xfffff) & ~0xfffff; - - printk("Allocating PCI resources starting at %08lx (gap: %08lx:%08lx)\n", - pci_mem_start, gapstart, gapsize); -#endif -} - -/* Use inline assembly to define this because the nops are defined - as inline assembly strings in the include files and we cannot - get them easily into strings. */ -asm("\t.data\nintelnops: " - GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6 - GENERIC_NOP7 GENERIC_NOP8); -asm("\t.data\nk8nops: " - K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6 - K8_NOP7 K8_NOP8); -asm("\t.data\nk7nops: " - K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6 - K7_NOP7 K7_NOP8); - -extern unsigned char intelnops[], k8nops[], k7nops[]; -static unsigned char *intel_nops[ASM_NOP_MAX+1] = { - NULL, - intelnops, - intelnops + 1, - intelnops + 1 + 2, - intelnops + 1 + 2 + 3, - intelnops + 1 + 2 + 3 + 4, - intelnops + 1 + 2 + 3 + 4 + 5, - intelnops + 1 + 2 + 3 + 4 + 5 + 6, - intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7, -}; -static unsigned char *k8_nops[ASM_NOP_MAX+1] = { - NULL, - k8nops, - k8nops + 1, - k8nops + 1 + 2, - k8nops + 1 + 2 + 3, - k8nops + 1 + 2 + 3 + 4, - k8nops + 1 + 2 + 3 + 4 + 5, - k8nops + 1 + 2 + 3 + 4 + 5 + 6, - k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7, -}; -static unsigned char *k7_nops[ASM_NOP_MAX+1] = { - NULL, - k7nops, - k7nops + 1, - k7nops + 1 + 2, - k7nops + 1 + 2 + 3, - k7nops + 1 + 2 + 3 + 4, - k7nops + 1 + 2 + 3 + 4 + 5, - k7nops + 1 + 2 + 3 + 4 + 5 + 6, - k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7, -}; -static struct nop { - int cpuid; - unsigned char **noptable; -} noptypes[] = { - { X86_FEATURE_K8, k8_nops }, - { X86_FEATURE_K7, k7_nops }, - { -1, NULL } -}; - -/* Replace instructions with better alternatives for this CPU type. - - This runs before SMP is initialized to avoid SMP problems with - self modifying code. This implies that assymetric systems where - APs have less capabilities than the boot processor are not handled. - In this case boot with "noreplacement". */ -void apply_alternatives(void *start, void *end) -{ - struct alt_instr *a; - int diff, i, k; - unsigned char **noptable = intel_nops; - for (i = 0; noptypes[i].cpuid >= 0; i++) { - if (boot_cpu_has(noptypes[i].cpuid)) { - noptable = noptypes[i].noptable; - break; - } - } - for (a = start; (void *)a < end; a++) { - if (!boot_cpu_has(a->cpuid)) - continue; - BUG_ON(a->replacementlen > a->instrlen); - memcpy(a->instr, a->replacement, a->replacementlen); - diff = a->instrlen - a->replacementlen; - /* Pad the rest with nops */ - for (i = a->replacementlen; diff > 0; diff -= k, i += k) { - k = diff; - if (k > ASM_NOP_MAX) - k = ASM_NOP_MAX; - memcpy(a->instr + i, noptable[k], k); - } - } -} - -static int no_replacement __initdata = 0; - -void __init alternative_instructions(void) -{ - extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; - if (no_replacement) - return; - apply_alternatives(__alt_instructions, __alt_instructions_end); -} - -static int __init noreplacement_setup(char *s) -{ - no_replacement = 1; - return 0; -} - -__setup("noreplacement", noreplacement_setup); - -static char * __init machine_specific_memory_setup(void); - -#ifdef CONFIG_MCA -static void set_mca_bus(int x) -{ - MCA_bus = x; -} -#else -static void set_mca_bus(int x) { } -#endif - -/* - * Determine if we were loaded by an EFI loader. If so, then we have also been - * passed the efi memmap, systab, etc., so we should use these data structures - * for initialization. Note, the efi init code path is determined by the - * global efi_enabled. This allows the same kernel image to be used on existing - * systems (with a traditional BIOS) as well as on EFI systems. - */ -void __init setup_arch(char **cmdline_p) -{ - int i, j, k, fpp; - physdev_op_t op; - unsigned long max_low_pfn; - - /* Force a quick death if the kernel panics. */ - extern int panic_timeout; - if (panic_timeout == 0) - panic_timeout = 1; - - /* Register a call for panic conditions. */ - notifier_chain_register(&panic_notifier_list, &xen_panic_block); - - HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments); - HYPERVISOR_vm_assist(VMASST_CMD_enable, - VMASST_TYPE_writable_pagetables); - - memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); - early_cpu_init(); - - /* - * FIXME: This isn't an official loader_type right - * now but does currently work with elilo. - * If we were configured as an EFI kernel, check to make - * sure that we were loaded correctly from elilo and that - * the system table is valid. If not, then initialize normally. - */ -#ifdef CONFIG_EFI - if ((LOADER_TYPE == 0x50) && EFI_SYSTAB) - efi_enabled = 1; -#endif - - /* This must be initialized to UNNAMED_MAJOR for ipconfig to work - properly. Setting ROOT_DEV to default to /dev/ram0 breaks initrd. - */ - ROOT_DEV = MKDEV(UNNAMED_MAJOR,0); - drive_info = DRIVE_INFO; - screen_info = SCREEN_INFO; - edid_info = EDID_INFO; - apm_info.bios = APM_BIOS_INFO; - ist_info = IST_INFO; - saved_videomode = VIDEO_MODE; - if( SYS_DESC_TABLE.length != 0 ) { - set_mca_bus(SYS_DESC_TABLE.table[3] & 0x2); - machine_id = SYS_DESC_TABLE.table[0]; - machine_submodel_id = SYS_DESC_TABLE.table[1]; - BIOS_revision = SYS_DESC_TABLE.table[2]; - } - bootloader_type = LOADER_TYPE; - -#ifdef CONFIG_XEN_PHYSDEV_ACCESS - /* This is drawn from a dump from vgacon:startup in standard Linux. */ - screen_info.orig_video_mode = 3; - screen_info.orig_video_isVGA = 1; - screen_info.orig_video_lines = 25; - screen_info.orig_video_cols = 80; - screen_info.orig_video_ega_bx = 3; - screen_info.orig_video_points = 16; -#endif - -#ifdef CONFIG_BLK_DEV_RAM - rd_image_start = RAMDISK_FLAGS & RAMDISK_IMAGE_START_MASK; - rd_prompt = ((RAMDISK_FLAGS & RAMDISK_PROMPT_FLAG) != 0); - rd_doload = ((RAMDISK_FLAGS & RAMDISK_LOAD_FLAG) != 0); -#endif - - setup_xen_features(); - - ARCH_SETUP - if (efi_enabled) - efi_init(); - else { - printk(KERN_INFO "BIOS-provided physical RAM map:\n"); - print_memory_map(machine_specific_memory_setup()); - } - - copy_edd(); - - if (!MOUNT_ROOT_RDONLY) - root_mountflags &= ~MS_RDONLY; - init_mm.start_code = (unsigned long) _text; - init_mm.end_code = (unsigned long) _etext; - init_mm.end_data = (unsigned long) _edata; - init_mm.brk = (PFN_UP(__pa(xen_start_info->pt_base)) + - xen_start_info->nr_pt_frames) << PAGE_SHIFT; - - /* XEN: This is nonsense: kernel may not even be contiguous in RAM. */ - /*code_resource.start = virt_to_phys(_text);*/ - /*code_resource.end = virt_to_phys(_etext)-1;*/ - /*data_resource.start = virt_to_phys(_etext);*/ - /*data_resource.end = virt_to_phys(_edata)-1;*/ - - parse_cmdline_early(cmdline_p); - - max_low_pfn = setup_memory(); - - /* - * NOTE: before this point _nobody_ is allowed to allocate - * any memory using the bootmem allocator. Although the - * alloctor is now initialised only the first 8Mb of the kernel - * virtual address space has been mapped. All allocations before - * paging_init() has completed must use the alloc_bootmem_low_pages() - * variant (which allocates DMA'able memory) and care must be taken - * not to exceed the 8Mb limit. - */ - -#ifdef CONFIG_SMP - smp_alloc_memory(); /* AP processor realmode stacks in low memory*/ -#endif - paging_init(); - remapped_pgdat_init(); - zone_sizes_init(); - -#ifdef CONFIG_X86_FIND_SMP_CONFIG - /* - * Find and reserve possible boot-time SMP configuration: - */ - find_smp_config(); -#endif - - /* Make sure we have a correctly sized P->M table. */ - phys_to_machine_mapping = alloc_bootmem_low_pages( - max_pfn * sizeof(unsigned long)); - memset(phys_to_machine_mapping, ~0, - max_pfn * sizeof(unsigned long)); - memcpy(phys_to_machine_mapping, - (unsigned long *)xen_start_info->mfn_list, - xen_start_info->nr_pages * sizeof(unsigned long)); - free_bootmem( - __pa(xen_start_info->mfn_list), - PFN_PHYS(PFN_UP(xen_start_info->nr_pages * - sizeof(unsigned long)))); - - /* - * Initialise the list of the frames that specify the list of - * frames that make up the p2m table. Used by save/restore - */ - pfn_to_mfn_frame_list_list = alloc_bootmem_low_pages(PAGE_SIZE); - HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = - virt_to_mfn(pfn_to_mfn_frame_list_list); - - fpp = PAGE_SIZE/sizeof(unsigned long); - for ( i=0, j=0, k=-1; i< max_pfn; i+=fpp, j++ ) - { - if ( (j % fpp) == 0 ) - { - k++; - BUG_ON(k>=16); - pfn_to_mfn_frame_list[k] = alloc_bootmem_low_pages(PAGE_SIZE); - pfn_to_mfn_frame_list_list[k] = - virt_to_mfn(pfn_to_mfn_frame_list[k]); - j=0; - } - pfn_to_mfn_frame_list[k][j] = - virt_to_mfn(&phys_to_machine_mapping[i]); - } - HYPERVISOR_shared_info->arch.max_pfn = max_pfn; - - /* - * NOTE: at this point the bootmem allocator is fully available. - */ - -#ifdef CONFIG_EARLY_PRINTK - { - char *s = strstr(*cmdline_p, "earlyprintk="); - if (s) { - extern void setup_early_printk(char *); - - setup_early_printk(s); - printk("early console enabled\n"); - } - } -#endif - - if (xen_start_info->flags & SIF_INITDOMAIN) - dmi_scan_machine(); - -#ifdef CONFIG_X86_GENERICARCH - generic_apic_probe(*cmdline_p); -#endif - if (efi_enabled) - efi_map_memmap(); - - op.cmd = PHYSDEVOP_SET_IOPL; - op.u.set_iopl.iopl = 1; - HYPERVISOR_physdev_op(&op); - -#ifdef CONFIG_ACPI_BOOT - if (!(xen_start_info->flags & SIF_INITDOMAIN)) { - printk(KERN_INFO "ACPI in unprivileged domain disabled\n"); - acpi_disabled = 1; - acpi_ht = 0; - } -#endif - -#ifdef CONFIG_ACPI_BOOT - /* - * Parse the ACPI tables for possible boot-time SMP configuration. - */ - acpi_boot_table_init(); - acpi_boot_init(); -#endif - -#ifdef CONFIG_X86_LOCAL_APIC - if (smp_found_config) - get_smp_config(); -#endif - - /* XXX Disable irqdebug until we have a way to avoid interrupt - * conflicts. */ - noirqdebug_setup(""); - - register_memory(); - - if (xen_start_info->flags & SIF_INITDOMAIN) { - if (!(xen_start_info->flags & SIF_PRIVILEGED)) - panic("Xen granted us console access " - "but not privileged status"); - -#ifdef CONFIG_VT -#if defined(CONFIG_VGA_CONSOLE) - if (!efi_enabled || - (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY)) - conswitchp = &vga_con; -#elif defined(CONFIG_DUMMY_CONSOLE) - conswitchp = &dummy_con; -#endif -#endif - } else { -#ifdef CONFIG_XEN_PHYSDEV_ACCESS - extern const struct consw xennull_con; - extern int console_use_vt; -#if defined(CONFIG_VGA_CONSOLE) - /* disable VGA driver */ - ORIG_VIDEO_ISVGA = VIDEO_TYPE_VLFB; -#endif - conswitchp = &xennull_con; - console_use_vt = 0; -#endif - } -} - -static int -xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr) -{ - HYPERVISOR_sched_op(SCHEDOP_shutdown, SHUTDOWN_crash); - /* we're never actually going to get here... */ - return NOTIFY_DONE; -} - -#include "setup_arch_post.h" -/* - * Local Variables: - * mode:c - * c-file-style:"k&r" - * c-basic-offset:8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/signal.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/signal.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,665 +0,0 @@ -/* - * linux/arch/i386/kernel/signal.c - * - * Copyright (C) 1991, 1992 Linus Torvalds - * - * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson - * 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes - */ - -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/smp.h> -#include <linux/smp_lock.h> -#include <linux/kernel.h> -#include <linux/signal.h> -#include <linux/errno.h> -#include <linux/wait.h> -#include <linux/unistd.h> -#include <linux/stddef.h> -#include <linux/personality.h> -#include <linux/suspend.h> -#include <linux/ptrace.h> -#include <linux/elf.h> -#include <asm/processor.h> -#include <asm/ucontext.h> -#include <asm/uaccess.h> -#include <asm/i387.h> -#include "sigframe.h" - -#define DEBUG_SIG 0 - -#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) - -/* - * Atomically swap in the new signal mask, and wait for a signal. - */ -asmlinkage int -sys_sigsuspend(int history0, int history1, old_sigset_t mask) -{ - struct pt_regs * regs = (struct pt_regs *) &history0; - sigset_t saveset; - - mask &= _BLOCKABLE; - spin_lock_irq(&current->sighand->siglock); - saveset = current->blocked; - siginitset(&current->blocked, mask); - recalc_sigpending(); - spin_unlock_irq(&current->sighand->siglock); - - regs->eax = -EINTR; - while (1) { - current->state = TASK_INTERRUPTIBLE; - schedule(); - if (do_signal(regs, &saveset)) - return -EINTR; - } -} - -asmlinkage int -sys_rt_sigsuspend(struct pt_regs regs) -{ - sigset_t saveset, newset; - - /* XXX: Don't preclude handling different sized sigset_t's. */ - if (regs.ecx != sizeof(sigset_t)) - return -EINVAL; - - if (copy_from_user(&newset, (sigset_t __user *)regs.ebx, sizeof(newset))) - return -EFAULT; - sigdelsetmask(&newset, ~_BLOCKABLE); - - spin_lock_irq(&current->sighand->siglock); - saveset = current->blocked; - current->blocked = newset; - recalc_sigpending(); - spin_unlock_irq(&current->sighand->siglock); - - regs.eax = -EINTR; - while (1) { - current->state = TASK_INTERRUPTIBLE; - schedule(); - if (do_signal(&regs, &saveset)) - return -EINTR; - } -} - -asmlinkage int -sys_sigaction(int sig, const struct old_sigaction __user *act, - struct old_sigaction __user *oact) -{ - struct k_sigaction new_ka, old_ka; - int ret; - - if (act) { - old_sigset_t mask; - if (!access_ok(VERIFY_READ, act, sizeof(*act)) || - __get_user(new_ka.sa.sa_handler, &act->sa_handler) || - __get_user(new_ka.sa.sa_restorer, &act->sa_restorer)) - return -EFAULT; - __get_user(new_ka.sa.sa_flags, &act->sa_flags); - __get_user(mask, &act->sa_mask); - siginitset(&new_ka.sa.sa_mask, mask); - } - - ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL); - - if (!ret && oact) { - if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) || - __put_user(old_ka.sa.sa_handler, &oact->sa_handler) || - __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer)) - return -EFAULT; - __put_user(old_ka.sa.sa_flags, &oact->sa_flags); - __put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask); - } - - return ret; -} - -asmlinkage int -sys_sigaltstack(unsigned long ebx) -{ - /* This is needed to make gcc realize it doesn't own the "struct pt_regs" */ - struct pt_regs *regs = (struct pt_regs *)&ebx; - const stack_t __user *uss = (const stack_t __user *)ebx; - stack_t __user *uoss = (stack_t __user *)regs->ecx; - - return do_sigaltstack(uss, uoss, regs->esp); -} - - -/* - * Do a signal return; undo the signal stack. - */ - -static int -restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *peax) -{ - unsigned int err = 0; - - /* Always make any pending restarted system calls return -EINTR */ - current_thread_info()->restart_block.fn = do_no_restart_syscall; - -#define COPY(x) err |= __get_user(regs->x, &sc->x) - -#define COPY_SEG(seg) \ - { unsigned short tmp; \ - err |= __get_user(tmp, &sc->seg); \ - regs->x##seg = tmp; } - -#define COPY_SEG_STRICT(seg) \ - { unsigned short tmp; \ - err |= __get_user(tmp, &sc->seg); \ - regs->x##seg = tmp|3; } - -#define GET_SEG(seg) \ - { unsigned short tmp; \ - err |= __get_user(tmp, &sc->seg); \ - loadsegment(seg,tmp); } - -#define FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | X86_EFLAGS_DF | \ - X86_EFLAGS_TF | X86_EFLAGS_SF | X86_EFLAGS_ZF | \ - X86_EFLAGS_AF | X86_EFLAGS_PF | X86_EFLAGS_CF) - - GET_SEG(gs); - GET_SEG(fs); - COPY_SEG(es); - COPY_SEG(ds); - COPY(edi); - COPY(esi); - COPY(ebp); - COPY(esp); - COPY(ebx); - COPY(edx); - COPY(ecx); - COPY(eip); - COPY_SEG_STRICT(cs); - COPY_SEG_STRICT(ss); - - { - unsigned int tmpflags; - err |= __get_user(tmpflags, &sc->eflags); - regs->eflags = (regs->eflags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS); - regs->orig_eax = -1; /* disable syscall checks */ - } - - { - struct _fpstate __user * buf; - err |= __get_user(buf, &sc->fpstate); - if (buf) { - if (!access_ok(VERIFY_READ, buf, sizeof(*buf))) - goto badframe; - err |= restore_i387(buf); - } else { - struct task_struct *me = current; - if (used_math()) { - clear_fpu(me); - clear_used_math(); - } - } - } - - err |= __get_user(*peax, &sc->eax); - return err; - -badframe: - return 1; -} - -asmlinkage int sys_sigreturn(unsigned long __unused) -{ - struct pt_regs *regs = (struct pt_regs *) &__unused; - struct sigframe __user *frame = (struct sigframe __user *)(regs->esp - 8); - sigset_t set; - int eax; - - if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) - goto badframe; - if (__get_user(set.sig[0], &frame->sc.oldmask) - || (_NSIG_WORDS > 1 - && __copy_from_user(&set.sig[1], &frame->extramask, - sizeof(frame->extramask)))) - goto badframe; - - sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(&current->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(&current->sighand->siglock); - - if (restore_sigcontext(regs, &frame->sc, &eax)) - goto badframe; - return eax; - -badframe: - force_sig(SIGSEGV, current); - return 0; -} - -asmlinkage int sys_rt_sigreturn(unsigned long __unused) -{ - struct pt_regs *regs = (struct pt_regs *) &__unused; - struct rt_sigframe __user *frame = (struct rt_sigframe __user *)(regs->esp - 4); - sigset_t set; - int eax; - - if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) - goto badframe; - if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) - goto badframe; - - sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(&current->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(&current->sighand->siglock); - - if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &eax)) - goto badframe; - - if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->esp) == -EFAULT) - goto badframe; - - return eax; - -badframe: - force_sig(SIGSEGV, current); - return 0; -} - -/* - * Set up a signal frame. - */ - -static int -setup_sigcontext(struct sigcontext __user *sc, struct _fpstate __user *fpstate, - struct pt_regs *regs, unsigned long mask) -{ - int tmp, err = 0; - - tmp = 0; - __asm__("movl %%gs,%0" : "=r"(tmp): "0"(tmp)); - err |= __put_user(tmp, (unsigned int __user *)&sc->gs); - __asm__("movl %%fs,%0" : "=r"(tmp): "0"(tmp)); - err |= __put_user(tmp, (unsigned int __user *)&sc->fs); - - err |= __put_user(regs->xes, (unsigned int __user *)&sc->es); - err |= __put_user(regs->xds, (unsigned int __user *)&sc->ds); - err |= __put_user(regs->edi, &sc->edi); - err |= __put_user(regs->esi, &sc->esi); - err |= __put_user(regs->ebp, &sc->ebp); - err |= __put_user(regs->esp, &sc->esp); - err |= __put_user(regs->ebx, &sc->ebx); - err |= __put_user(regs->edx, &sc->edx); - err |= __put_user(regs->ecx, &sc->ecx); - err |= __put_user(regs->eax, &sc->eax); - err |= __put_user(current->thread.trap_no, &sc->trapno); - err |= __put_user(current->thread.error_code, &sc->err); - err |= __put_user(regs->eip, &sc->eip); - err |= __put_user(regs->xcs, (unsigned int __user *)&sc->cs); - err |= __put_user(regs->eflags, &sc->eflags); - err |= __put_user(regs->esp, &sc->esp_at_signal); - err |= __put_user(regs->xss, (unsigned int __user *)&sc->ss); - - tmp = save_i387(fpstate); - if (tmp < 0) - err = 1; - else - err |= __put_user(tmp ? fpstate : NULL, &sc->fpstate); - - /* non-iBCS2 extensions.. */ - err |= __put_user(mask, &sc->oldmask); - err |= __put_user(current->thread.cr2, &sc->cr2); - - return err; -} - -/* - * Determine which stack to use.. - */ -static inline void __user * -get_sigframe(struct k_sigaction *ka, struct pt_regs * regs, size_t frame_size) -{ - unsigned long esp; - - /* Default to using normal stack */ - esp = regs->esp; - - /* This is the X/Open sanctioned signal stack switching. */ - if (ka->sa.sa_flags & SA_ONSTACK) { - if (sas_ss_flags(esp) == 0) - esp = current->sas_ss_sp + current->sas_ss_size; - } - - /* This is the legacy signal stack switching. */ - else if ((regs->xss & 0xffff) != __USER_DS && - !(ka->sa.sa_flags & SA_RESTORER) && - ka->sa.sa_restorer) { - esp = (unsigned long) ka->sa.sa_restorer; - } - - return (void __user *)((esp - frame_size) & -8ul); -} - -/* These symbols are defined with the addresses in the vsyscall page. - See vsyscall-sigreturn.S. */ -extern void __user __kernel_sigreturn; -extern void __user __kernel_rt_sigreturn; - -static void setup_frame(int sig, struct k_sigaction *ka, - sigset_t *set, struct pt_regs * regs) -{ - void __user *restorer; - struct sigframe __user *frame; - int err = 0; - int usig; - - frame = get_sigframe(ka, regs, sizeof(*frame)); - - if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) - goto give_sigsegv; - - usig = current_thread_info()->exec_domain - && current_thread_info()->exec_domain->signal_invmap - && sig < 32 - ? current_thread_info()->exec_domain->signal_invmap[sig] - : sig; - - err = __put_user(usig, &frame->sig); - if (err) - goto give_sigsegv; - - err = setup_sigcontext(&frame->sc, &frame->fpstate, regs, set->sig[0]); - if (err) - goto give_sigsegv; - - if (_NSIG_WORDS > 1) { - err = __copy_to_user(&frame->extramask, &set->sig[1], - sizeof(frame->extramask)); - if (err) - goto give_sigsegv; - } - - restorer = &__kernel_sigreturn; - if (ka->sa.sa_flags & SA_RESTORER) - restorer = ka->sa.sa_restorer; - - /* Set up to return from userspace. */ - err |= __put_user(restorer, &frame->pretcode); - - /* - * This is popl %eax ; movl $,%eax ; int $0x80 - * - * WE DO NOT USE IT ANY MORE! It's only left here for historical - * reasons and because gdb uses it as a signature to notice - * signal handler stack frames. - */ - err |= __put_user(0xb858, (short __user *)(frame->retcode+0)); - err |= __put_user(__NR_sigreturn, (int __user *)(frame->retcode+2)); - err |= __put_user(0x80cd, (short __user *)(frame->retcode+6)); - - if (err) - goto give_sigsegv; - - /* Set up registers for signal handler */ - regs->esp = (unsigned long) frame; - regs->eip = (unsigned long) ka->sa.sa_handler; - regs->eax = (unsigned long) sig; - regs->edx = (unsigned long) 0; - regs->ecx = (unsigned long) 0; - - set_fs(USER_DS); - regs->xds = __USER_DS; - regs->xes = __USER_DS; - regs->xss = __USER_DS; - regs->xcs = __USER_CS; - - /* - * Clear TF when entering the signal handler, but - * notify any tracer that was single-stepping it. - * The tracer may want to single-step inside the - * handler too. - */ - regs->eflags &= ~TF_MASK; - if (test_thread_flag(TIF_SINGLESTEP)) - ptrace_notify(SIGTRAP); - -#if DEBUG_SIG - printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n", - current->comm, current->pid, frame, regs->eip, frame->pretcode); -#endif - - return; - -give_sigsegv: - force_sigsegv(sig, current); -} - -static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, - sigset_t *set, struct pt_regs * regs) -{ - void __user *restorer; - struct rt_sigframe __user *frame; - int err = 0; - int usig; - - frame = get_sigframe(ka, regs, sizeof(*frame)); - - if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) - goto give_sigsegv; - - usig = current_thread_info()->exec_domain - && current_thread_info()->exec_domain->signal_invmap - && sig < 32 - ? current_thread_info()->exec_domain->signal_invmap[sig] - : sig; - - err |= __put_user(usig, &frame->sig); - err |= __put_user(&frame->info, &frame->pinfo); - err |= __put_user(&frame->uc, &frame->puc); - err |= copy_siginfo_to_user(&frame->info, info); - if (err) - goto give_sigsegv; - - /* Create the ucontext. */ - err |= __put_user(0, &frame->uc.uc_flags); - err |= __put_user(0, &frame->uc.uc_link); - err |= __put_user(current->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - err |= __put_user(sas_ss_flags(regs->esp), - &frame->uc.uc_stack.ss_flags); - err |= __put_user(current->sas_ss_size, &frame->uc.uc_stack.ss_size); - err |= setup_sigcontext(&frame->uc.uc_mcontext, &frame->fpstate, - regs, set->sig[0]); - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); - if (err) - goto give_sigsegv; - - /* Set up to return from userspace. */ - restorer = &__kernel_rt_sigreturn; - if (ka->sa.sa_flags & SA_RESTORER) - restorer = ka->sa.sa_restorer; - err |= __put_user(restorer, &frame->pretcode); - - /* - * This is movl $,%eax ; int $0x80 - * - * WE DO NOT USE IT ANY MORE! It's only left here for historical - * reasons and because gdb uses it as a signature to notice - * signal handler stack frames. - */ - err |= __put_user(0xb8, (char __user *)(frame->retcode+0)); - err |= __put_user(__NR_rt_sigreturn, (int __user *)(frame->retcode+1)); - err |= __put_user(0x80cd, (short __user *)(frame->retcode+5)); - - if (err) - goto give_sigsegv; - - /* Set up registers for signal handler */ - regs->esp = (unsigned long) frame; - regs->eip = (unsigned long) ka->sa.sa_handler; - regs->eax = (unsigned long) usig; - regs->edx = (unsigned long) &frame->info; - regs->ecx = (unsigned long) &frame->uc; - - set_fs(USER_DS); - regs->xds = __USER_DS; - regs->xes = __USER_DS; - regs->xss = __USER_DS; - regs->xcs = __USER_CS; - - /* - * Clear TF when entering the signal handler, but - * notify any tracer that was single-stepping it. - * The tracer may want to single-step inside the - * handler too. - */ - regs->eflags &= ~TF_MASK; - if (test_thread_flag(TIF_SINGLESTEP)) - ptrace_notify(SIGTRAP); - -#if DEBUG_SIG - printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n", - current->comm, current->pid, frame, regs->eip, frame->pretcode); -#endif - - return; - -give_sigsegv: - force_sigsegv(sig, current); -} - -/* - * OK, we're invoking a handler - */ - -static void -handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, - sigset_t *oldset, struct pt_regs * regs) -{ - /* Are we from a system call? */ - if (regs->orig_eax >= 0) { - /* If so, check system call restarting.. */ - switch (regs->eax) { - case -ERESTART_RESTARTBLOCK: - case -ERESTARTNOHAND: - regs->eax = -EINTR; - break; - - case -ERESTARTSYS: - if (!(ka->sa.sa_flags & SA_RESTART)) { - regs->eax = -EINTR; - break; - } - /* fallthrough */ - case -ERESTARTNOINTR: - regs->eax = regs->orig_eax; - regs->eip -= 2; - } - } - - /* - * If TF is set due to a debugger (PT_DTRACE), clear the TF flag so - * that register information in the sigcontext is correct. - */ - if (unlikely(regs->eflags & TF_MASK) - && likely(current->ptrace & PT_DTRACE)) { - current->ptrace &= ~PT_DTRACE; - regs->eflags &= ~TF_MASK; - } - - /* Set up the stack frame */ - if (ka->sa.sa_flags & SA_SIGINFO) - setup_rt_frame(sig, ka, info, oldset, regs); - else - setup_frame(sig, ka, oldset, regs); - - if (!(ka->sa.sa_flags & SA_NODEFER)) { - spin_lock_irq(&current->sighand->siglock); - sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask); - sigaddset(&current->blocked,sig); - recalc_sigpending(); - spin_unlock_irq(&current->sighand->siglock); - } -} - -/* - * Note that 'init' is a special process: it doesn't get signals it doesn't - * want to handle. Thus you cannot kill init even with a SIGKILL even by - * mistake. - */ -int fastcall do_signal(struct pt_regs *regs, sigset_t *oldset) -{ - siginfo_t info; - int signr; - struct k_sigaction ka; - - /* - * We want the common case to go fast, which - * is why we may in certain cases get here from - * kernel mode. Just return without doing anything - * if so. - */ - if ((regs->xcs & 2) != 2) - return 1; - - if (current->flags & PF_FREEZE) { - refrigerator(0); - goto no_signal; - } - - if (!oldset) - oldset = &current->blocked; - - signr = get_signal_to_deliver(&info, &ka, regs, NULL); - if (signr > 0) { - /* Reenable any watchpoints before delivering the - * signal to user space. The processor register will - * have been cleared if the watchpoint triggered - * inside the kernel. - */ - if (unlikely(current->thread.debugreg[7])) { - loaddebug(&current->thread, 7); - } - - /* Whee! Actually deliver the signal. */ - handle_signal(signr, &info, &ka, oldset, regs); - return 1; - } - - no_signal: - /* Did we come from a system call? */ - if (regs->orig_eax >= 0) { - /* Restart the system call - no handlers present */ - if (regs->eax == -ERESTARTNOHAND || - regs->eax == -ERESTARTSYS || - regs->eax == -ERESTARTNOINTR) { - regs->eax = regs->orig_eax; - regs->eip -= 2; - } - if (regs->eax == -ERESTART_RESTARTBLOCK){ - regs->eax = __NR_restart_syscall; - regs->eip -= 2; - } - } - return 0; -} - -/* - * notification of userspace execution resumption - * - triggered by current->work.notify_resume - */ -__attribute__((regparm(3))) -void do_notify_resume(struct pt_regs *regs, sigset_t *oldset, - __u32 thread_info_flags) -{ - /* Pending single-step? */ - if (thread_info_flags & _TIF_SINGLESTEP) { - regs->eflags |= TF_MASK; - clear_thread_flag(TIF_SINGLESTEP); - } - /* deal with pending signal delivery */ - if (thread_info_flags & _TIF_SIGPENDING) - do_signal(regs,oldset); - - clear_thread_flag(TIF_IRET); -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/smp.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/smp.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,606 +0,0 @@ -/* - * Intel SMP support routines. - * - * (c) 1995 Alan Cox, Building #3 <alan@xxxxxxxxxx> - * (c) 1998-99, 2000 Ingo Molnar <mingo@xxxxxxxxxx> - * - * This code is released under the GNU General Public License version 2 or - * later. - */ - -#include <linux/init.h> - -#include <linux/mm.h> -#include <linux/irq.h> -#include <linux/delay.h> -#include <linux/spinlock.h> -#include <linux/smp_lock.h> -#include <linux/kernel_stat.h> -#include <linux/mc146818rtc.h> -#include <linux/cache.h> -#include <linux/interrupt.h> -#include <linux/cpu.h> - -#include <asm/mtrr.h> -#include <asm/tlbflush.h> -#if 0 -#include <mach_apic.h> -#endif -#include <asm-xen/evtchn.h> - -/* - * Some notes on x86 processor bugs affecting SMP operation: - * - * Pentium, Pentium Pro, II, III (and all CPUs) have bugs. - * The Linux implications for SMP are handled as follows: - * - * Pentium III / [Xeon] - * None of the E1AP-E3AP errata are visible to the user. - * - * E1AP. see PII A1AP - * E2AP. see PII A2AP - * E3AP. see PII A3AP - * - * Pentium II / [Xeon] - * None of the A1AP-A3AP errata are visible to the user. - * - * A1AP. see PPro 1AP - * A2AP. see PPro 2AP - * A3AP. see PPro 7AP - * - * Pentium Pro - * None of 1AP-9AP errata are visible to the normal user, - * except occasional delivery of 'spurious interrupt' as trap #15. - * This is very rare and a non-problem. - * - * 1AP. Linux maps APIC as non-cacheable - * 2AP. worked around in hardware - * 3AP. fixed in C0 and above steppings microcode update. - * Linux does not use excessive STARTUP_IPIs. - * 4AP. worked around in hardware - * 5AP. symmetric IO mode (normal Linux operation) not affected. - * 'noapic' mode has vector 0xf filled out properly. - * 6AP. 'noapic' mode might be affected - fixed in later steppings - * 7AP. We do not assume writes to the LVT deassering IRQs - * 8AP. We do not enable low power mode (deep sleep) during MP bootup - * 9AP. We do not use mixed mode - * - * Pentium - * There is a marginal case where REP MOVS on 100MHz SMP - * machines with B stepping processors can fail. XXX should provide - * an L1cache=Writethrough or L1cache=off option. - * - * B stepping CPUs may hang. There are hardware work arounds - * for this. We warn about it in case your board doesn't have the work - * arounds. Basically thats so I can tell anyone with a B stepping - * CPU and SMP problems "tough". - * - * Specific items [From Pentium Processor Specification Update] - * - * 1AP. Linux doesn't use remote read - * 2AP. Linux doesn't trust APIC errors - * 3AP. We work around this - * 4AP. Linux never generated 3 interrupts of the same priority - * to cause a lost local interrupt. - * 5AP. Remote read is never used - * 6AP. not affected - worked around in hardware - * 7AP. not affected - worked around in hardware - * 8AP. worked around in hardware - we get explicit CS errors if not - * 9AP. only 'noapic' mode affected. Might generate spurious - * interrupts, we log only the first one and count the - * rest silently. - * 10AP. not affected - worked around in hardware - * 11AP. Linux reads the APIC between writes to avoid this, as per - * the documentation. Make sure you preserve this as it affects - * the C stepping chips too. - * 12AP. not affected - worked around in hardware - * 13AP. not affected - worked around in hardware - * 14AP. we always deassert INIT during bootup - * 15AP. not affected - worked around in hardware - * 16AP. not affected - worked around in hardware - * 17AP. not affected - worked around in hardware - * 18AP. not affected - worked around in hardware - * 19AP. not affected - worked around in BIOS - * - * If this sounds worrying believe me these bugs are either ___RARE___, - * or are signal timing bugs worked around in hardware and there's - * about nothing of note with C stepping upwards. - */ - -DEFINE_PER_CPU(struct tlb_state, cpu_tlbstate) ____cacheline_aligned = { &init_mm, 0, }; - -/* - * the following functions deal with sending IPIs between CPUs. - * - * We use 'broadcast', CPU->CPU IPIs and self-IPIs too. - */ - -static inline int __prepare_ICR (unsigned int shortcut, int vector) -{ - return APIC_DM_FIXED | shortcut | vector | APIC_DEST_LOGICAL; -} - -static inline int __prepare_ICR2 (unsigned int mask) -{ - return SET_APIC_DEST_FIELD(mask); -} - -DECLARE_PER_CPU(int, ipi_to_irq[NR_IPIS]); - -static inline void __send_IPI_one(unsigned int cpu, int vector) -{ - int irq = per_cpu(ipi_to_irq, cpu)[vector]; - BUG_ON(irq < 0); - notify_remote_via_irq(irq); -} - -void __send_IPI_shortcut(unsigned int shortcut, int vector) -{ - int cpu; - - switch (shortcut) { - case APIC_DEST_SELF: - __send_IPI_one(smp_processor_id(), vector); - break; - case APIC_DEST_ALLBUT: - for (cpu = 0; cpu < NR_CPUS; ++cpu) { - if (cpu == smp_processor_id()) - continue; - if (cpu_isset(cpu, cpu_online_map)) { - __send_IPI_one(cpu, vector); - } - } - break; - default: - printk("XXXXXX __send_IPI_shortcut %08x vector %d\n", shortcut, - vector); - break; - } -} - -void fastcall send_IPI_self(int vector) -{ - __send_IPI_shortcut(APIC_DEST_SELF, vector); -} - -/* - * This is only used on smaller machines. - */ -void send_IPI_mask_bitmask(cpumask_t mask, int vector) -{ - unsigned long flags; - unsigned int cpu; - - local_irq_save(flags); - WARN_ON(cpus_addr(mask)[0] & ~cpus_addr(cpu_online_map)[0]); - - for (cpu = 0; cpu < NR_CPUS; ++cpu) { - if (cpu_isset(cpu, mask)) { - __send_IPI_one(cpu, vector); - } - } - - local_irq_restore(flags); -} - -void send_IPI_mask_sequence(cpumask_t mask, int vector) -{ - - send_IPI_mask_bitmask(mask, vector); -} - -#include <mach_ipi.h> /* must come after the send_IPI functions above for inlining */ - -#if 0 /* XEN */ -/* - * Smarter SMP flushing macros. - * c/o Linus Torvalds. - * - * These mean you can really definitely utterly forget about - * writing to user space from interrupts. (Its not allowed anyway). - * - * Optimizations Manfred Spraul <manfred@xxxxxxxxxxxxxxxx> - */ - -static cpumask_t flush_cpumask; -static struct mm_struct * flush_mm; -static unsigned long flush_va; -static DEFINE_SPINLOCK(tlbstate_lock); -#define FLUSH_ALL 0xffffffff - -/* - * We cannot call mmdrop() because we are in interrupt context, - * instead update mm->cpu_vm_mask. - * - * We need to reload %cr3 since the page tables may be going - * away from under us.. - */ -static inline void leave_mm (unsigned long cpu) -{ - if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK) - BUG(); - cpu_clear(cpu, per_cpu(cpu_tlbstate, cpu).active_mm->cpu_vm_mask); - load_cr3(swapper_pg_dir); -} - -/* - * - * The flush IPI assumes that a thread switch happens in this order: - * [cpu0: the cpu that switches] - * 1) switch_mm() either 1a) or 1b) - * 1a) thread switch to a different mm - * 1a1) cpu_clear(cpu, old_mm->cpu_vm_mask); - * Stop ipi delivery for the old mm. This is not synchronized with - * the other cpus, but smp_invalidate_interrupt ignore flush ipis - * for the wrong mm, and in the worst case we perform a superflous - * tlb flush. - * 1a2) set cpu_tlbstate to TLBSTATE_OK - * Now the smp_invalidate_interrupt won't call leave_mm if cpu0 - * was in lazy tlb mode. - * 1a3) update cpu_tlbstate[].active_mm - * Now cpu0 accepts tlb flushes for the new mm. - * 1a4) cpu_set(cpu, new_mm->cpu_vm_mask); - * Now the other cpus will send tlb flush ipis. - * 1a4) change cr3. - * 1b) thread switch without mm change - * cpu_tlbstate[].active_mm is correct, cpu0 already handles - * flush ipis. - * 1b1) set cpu_tlbstate to TLBSTATE_OK - * 1b2) test_and_set the cpu bit in cpu_vm_mask. - * Atomically set the bit [other cpus will start sending flush ipis], - * and test the bit. - * 1b3) if the bit was 0: leave_mm was called, flush the tlb. - * 2) switch %%esp, ie current - * - * The interrupt must handle 2 special cases: - * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm. - * - the cpu performs speculative tlb reads, i.e. even if the cpu only - * runs in kernel space, the cpu could load tlb entries for user space - * pages. - * - * The good news is that cpu_tlbstate is local to each cpu, no - * write/read ordering problems. - */ - -/* - * TLB flush IPI: - * - * 1) Flush the tlb entries if the cpu uses the mm that's being flushed. - * 2) Leave the mm if we are in the lazy tlb mode. - */ - -irqreturn_t smp_invalidate_interrupt(int irq, void *dev_id, - struct pt_regs *regs) -{ - unsigned long cpu; - - cpu = get_cpu(); - - if (!cpu_isset(cpu, flush_cpumask)) - goto out; - /* - * This was a BUG() but until someone can quote me the - * line from the intel manual that guarantees an IPI to - * multiple CPUs is retried _only_ on the erroring CPUs - * its staying as a return - * - * BUG(); - */ - - if (flush_mm == per_cpu(cpu_tlbstate, cpu).active_mm) { - if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK) { - if (flush_va == FLUSH_ALL) - local_flush_tlb(); - else - __flush_tlb_one(flush_va); - } else - leave_mm(cpu); - } - smp_mb__before_clear_bit(); - cpu_clear(cpu, flush_cpumask); - smp_mb__after_clear_bit(); -out: - put_cpu_no_resched(); - - return IRQ_HANDLED; -} - -static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm, - unsigned long va) -{ - /* - * A couple of (to be removed) sanity checks: - * - * - current CPU must not be in mask - * - mask must exist :) - */ - BUG_ON(cpus_empty(cpumask)); - BUG_ON(cpu_isset(smp_processor_id(), cpumask)); - BUG_ON(!mm); - - /* If a CPU which we ran on has gone down, OK. */ - cpus_and(cpumask, cpumask, cpu_online_map); - if (cpus_empty(cpumask)) - return; - - /* - * i'm not happy about this global shared spinlock in the - * MM hot path, but we'll see how contended it is. - * Temporarily this turns IRQs off, so that lockups are - * detected by the NMI watchdog. - */ - spin_lock(&tlbstate_lock); - - flush_mm = mm; - flush_va = va; -#if NR_CPUS <= BITS_PER_LONG - atomic_set_mask(cpumask, &flush_cpumask); -#else - { - int k; - unsigned long *flush_mask = (unsigned long *)&flush_cpumask; - unsigned long *cpu_mask = (unsigned long *)&cpumask; - for (k = 0; k < BITS_TO_LONGS(NR_CPUS); ++k) - atomic_set_mask(cpu_mask[k], &flush_mask[k]); - } -#endif - /* - * We have to send the IPI only to - * CPUs affected. - */ - send_IPI_mask(cpumask, INVALIDATE_TLB_VECTOR); - - while (!cpus_empty(flush_cpumask)) - /* nothing. lockup detection does not belong here */ - mb(); - - flush_mm = NULL; - flush_va = 0; - spin_unlock(&tlbstate_lock); -} - -void flush_tlb_current_task(void) -{ - struct mm_struct *mm = current->mm; - cpumask_t cpu_mask; - - preempt_disable(); - cpu_mask = mm->cpu_vm_mask; - cpu_clear(smp_processor_id(), cpu_mask); - - local_flush_tlb(); - if (!cpus_empty(cpu_mask)) - flush_tlb_others(cpu_mask, mm, FLUSH_ALL); - preempt_enable(); -} - -void flush_tlb_mm (struct mm_struct * mm) -{ - cpumask_t cpu_mask; - - preempt_disable(); - cpu_mask = mm->cpu_vm_mask; - cpu_clear(smp_processor_id(), cpu_mask); - - if (current->active_mm == mm) { - if (current->mm) - local_flush_tlb(); - else - leave_mm(smp_processor_id()); - } - if (!cpus_empty(cpu_mask)) - flush_tlb_others(cpu_mask, mm, FLUSH_ALL); - - preempt_enable(); -} - -void flush_tlb_page(struct vm_area_struct * vma, unsigned long va) -{ - struct mm_struct *mm = vma->vm_mm; - cpumask_t cpu_mask; - - preempt_disable(); - cpu_mask = mm->cpu_vm_mask; - cpu_clear(smp_processor_id(), cpu_mask); - - if (current->active_mm == mm) { - if(current->mm) - __flush_tlb_one(va); - else - leave_mm(smp_processor_id()); - } - - if (!cpus_empty(cpu_mask)) - flush_tlb_others(cpu_mask, mm, va); - - preempt_enable(); -} - -static void do_flush_tlb_all(void* info) -{ - unsigned long cpu = smp_processor_id(); - - __flush_tlb_all(); - if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_LAZY) - leave_mm(cpu); -} - -void flush_tlb_all(void) -{ - on_each_cpu(do_flush_tlb_all, NULL, 1, 1); -} - -#else - -irqreturn_t smp_invalidate_interrupt(int irq, void *dev_id, - struct pt_regs *regs) -{ return 0; } -void flush_tlb_current_task(void) -{ xen_tlb_flush_mask(&current->mm->cpu_vm_mask); } -void flush_tlb_mm(struct mm_struct * mm) -{ xen_tlb_flush_mask(&mm->cpu_vm_mask); } -void flush_tlb_page(struct vm_area_struct *vma, unsigned long va) -{ xen_invlpg_mask(&vma->vm_mm->cpu_vm_mask, va); } -void flush_tlb_all(void) -{ xen_tlb_flush_all(); } - -#endif /* XEN */ - -/* - * this function sends a 'reschedule' IPI to another CPU. - * it goes straight through and wastes no time serializing - * anything. Worst case is that we lose a reschedule ... - */ -void smp_send_reschedule(int cpu) -{ - WARN_ON(cpu_is_offline(cpu)); - send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR); -} - -/* - * Structure and data for smp_call_function(). This is designed to minimise - * static memory requirements. It also looks cleaner. - */ -static DEFINE_SPINLOCK(call_lock); - -struct call_data_struct { - void (*func) (void *info); - void *info; - atomic_t started; - atomic_t finished; - int wait; -}; - -static struct call_data_struct * call_data; - -/* - * this function sends a 'generic call function' IPI to all other CPUs - * in the system. - */ - -int smp_call_function (void (*func) (void *info), void *info, int nonatomic, - int wait) -/* - * [SUMMARY] Run a function on all other CPUs. - * <func> The function to run. This must be fast and non-blocking. - * <info> An arbitrary pointer to pass to the function. - * <nonatomic> currently unused. - * <wait> If true, wait (atomically) until function has completed on other CPUs. - * [RETURNS] 0 on success, else a negative status code. Does not return until - * remote CPUs are nearly ready to execute <<func>> or are or have executed. - * - * You must not call this function with disabled interrupts or from a - * hardware interrupt handler or from a bottom half handler. - */ -{ - struct call_data_struct data; - int cpus; - - /* Holding any lock stops cpus from going down. */ - spin_lock(&call_lock); - cpus = num_online_cpus()-1; - - if (!cpus) { - spin_unlock(&call_lock); - return 0; - } - - /* Can deadlock when called with interrupts disabled */ - WARN_ON(irqs_disabled()); - - data.func = func; - data.info = info; - atomic_set(&data.started, 0); - data.wait = wait; - if (wait) - atomic_set(&data.finished, 0); - - call_data = &data; - mb(); - - /* Send a message to all other CPUs and wait for them to respond */ - send_IPI_allbutself(CALL_FUNCTION_VECTOR); - - /* Wait for response */ - while (atomic_read(&data.started) != cpus) - barrier(); - - if (wait) - while (atomic_read(&data.finished) != cpus) - barrier(); - spin_unlock(&call_lock); - - return 0; -} - -static void stop_this_cpu (void * dummy) -{ - /* - * Remove this CPU: - */ - cpu_clear(smp_processor_id(), cpu_online_map); - local_irq_disable(); -#if 0 - disable_local_APIC(); -#endif - if (cpu_data[smp_processor_id()].hlt_works_ok) - for(;;) __asm__("hlt"); - for (;;); -} - -/* - * this function calls the 'stop' function on all other CPUs in the system. - */ - -void smp_send_stop(void) -{ - smp_call_function(stop_this_cpu, NULL, 1, 0); - - local_irq_disable(); -#if 0 - disable_local_APIC(); -#endif - local_irq_enable(); -} - -/* - * Reschedule call back. Nothing to do, - * all the work is done automatically when - * we return from the interrupt. - */ -irqreturn_t smp_reschedule_interrupt(int irq, void *dev_id, - struct pt_regs *regs) -{ - - return IRQ_HANDLED; -} - -#include <linux/kallsyms.h> -irqreturn_t smp_call_function_interrupt(int irq, void *dev_id, - struct pt_regs *regs) -{ - void (*func) (void *info) = call_data->func; - void *info = call_data->info; - int wait = call_data->wait; - - /* - * Notify initiating CPU that I've grabbed the data and am - * about to execute the function - */ - mb(); - atomic_inc(&call_data->started); - /* - * At this point the info structure may be out of scope unless wait==1 - */ - irq_enter(); - (*func)(info); - irq_exit(); - - if (wait) { - mb(); - atomic_inc(&call_data->finished); - } - - return IRQ_HANDLED; -} - diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/swiotlb.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/swiotlb.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,671 +0,0 @@ -/* - * Dynamic DMA mapping support. - * - * This implementation is a fallback for platforms that do not support - * I/O TLBs (aka DMA address translation hardware). - * Copyright (C) 2000 Asit Mallick <Asit.K.Mallick@xxxxxxxxx> - * Copyright (C) 2000 Goutham Rao <goutham.rao@xxxxxxxxx> - * Copyright (C) 2000, 2003 Hewlett-Packard Co - * David Mosberger-Tang <davidm@xxxxxxxxxx> - * Copyright (C) 2005 Keir Fraser <keir@xxxxxxxxxxxxx> - */ - -#include <linux/cache.h> -#include <linux/mm.h> -#include <linux/module.h> -#include <linux/pci.h> -#include <linux/spinlock.h> -#include <linux/string.h> -#include <linux/types.h> -#include <linux/ctype.h> -#include <linux/init.h> -#include <linux/bootmem.h> -#include <linux/highmem.h> -#include <asm/io.h> -#include <asm/pci.h> -#include <asm/dma.h> -#include <asm/uaccess.h> -#include <asm-xen/xen-public/memory.h> - -#define OFFSET(val,align) ((unsigned long)((val) & ( (align) - 1))) - -#define SG_ENT_PHYS_ADDRESS(sg) (page_to_phys((sg)->page) + (sg)->offset) - -/* - * Maximum allowable number of contiguous slabs to map, - * must be a power of 2. What is the appropriate value ? - * The complexity of {map,unmap}_single is linearly dependent on this value. - */ -#define IO_TLB_SEGSIZE 128 - -/* - * log of the size of each IO TLB slab. The number of slabs is command line - * controllable. - */ -#define IO_TLB_SHIFT 11 - -static int swiotlb_force; -static char *iotlb_virt_start; -static unsigned long iotlb_nslabs; - -/* - * Used to do a quick range check in swiotlb_unmap_single and - * swiotlb_sync_single_*, to see if the memory was in fact allocated by this - * API. - */ -static dma_addr_t iotlb_bus_start, iotlb_bus_end, iotlb_bus_mask; - -/* Does the given dma address reside within the swiotlb aperture? */ -#define in_swiotlb_aperture(a) (!(((a) ^ iotlb_bus_start) & iotlb_bus_mask)) - -/* - * When the IOMMU overflows we return a fallback buffer. This sets the size. - */ -static unsigned long io_tlb_overflow = 32*1024; - -void *io_tlb_overflow_buffer; - -/* - * This is a free list describing the number of free entries available from - * each index - */ -static unsigned int *io_tlb_list; -static unsigned int io_tlb_index; - -/* - * We need to save away the original address corresponding to a mapped entry - * for the sync operations. - */ -static struct phys_addr { - struct page *page; - unsigned int offset; -} *io_tlb_orig_addr; - -/* - * Protect the above data structures in the map and unmap calls - */ -static DEFINE_SPINLOCK(io_tlb_lock); - -static int __init -setup_io_tlb_npages(char *str) -{ - /* Unlike ia64, the size is aperture in megabytes, not 'slabs'! */ - if (isdigit(*str)) { - iotlb_nslabs = simple_strtoul(str, &str, 0) << - (20 - IO_TLB_SHIFT); - iotlb_nslabs = ALIGN(iotlb_nslabs, IO_TLB_SEGSIZE); - /* Round up to power of two (xen_create_contiguous_region). */ - while (iotlb_nslabs & (iotlb_nslabs-1)) - iotlb_nslabs += iotlb_nslabs & ~(iotlb_nslabs-1); - } - if (*str == ',') - ++str; - /* - * NB. 'force' enables the swiotlb, but doesn't force its use for - * every DMA like it does on native Linux. 'off' forcibly disables - * use of the swiotlb. - */ - if (!strcmp(str, "force")) - swiotlb_force = 1; - else if (!strcmp(str, "off")) - swiotlb_force = -1; - return 1; -} -__setup("swiotlb=", setup_io_tlb_npages); -/* make io_tlb_overflow tunable too? */ - -/* - * Statically reserve bounce buffer space and initialize bounce buffer data - * structures for the software IO TLB used to implement the PCI DMA API. - */ -void -swiotlb_init_with_default_size (size_t default_size) -{ - unsigned long i, bytes; - int rc; - - if (!iotlb_nslabs) { - iotlb_nslabs = (default_size >> IO_TLB_SHIFT); - iotlb_nslabs = ALIGN(iotlb_nslabs, IO_TLB_SEGSIZE); - /* Round up to power of two (xen_create_contiguous_region). */ - while (iotlb_nslabs & (iotlb_nslabs-1)) - iotlb_nslabs += iotlb_nslabs & ~(iotlb_nslabs-1); - } - - bytes = iotlb_nslabs * (1UL << IO_TLB_SHIFT); - - /* - * Get IO TLB memory from the low pages - */ - iotlb_virt_start = alloc_bootmem_low_pages(bytes); - if (!iotlb_virt_start) - panic("Cannot allocate SWIOTLB buffer!\n" - "Use dom0_mem Xen boot parameter to reserve\n" - "some DMA memory (e.g., dom0_mem=-128M).\n"); - - /* Hardcode 31 address bits for now: aacraid limitation. */ - rc = xen_create_contiguous_region( - (unsigned long)iotlb_virt_start, get_order(bytes), 31); - BUG_ON(rc); - - /* - * Allocate and initialize the free list array. This array is used - * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE. - */ - io_tlb_list = alloc_bootmem(iotlb_nslabs * sizeof(int)); - for (i = 0; i < iotlb_nslabs; i++) - io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE); - io_tlb_index = 0; - io_tlb_orig_addr = alloc_bootmem( - iotlb_nslabs * sizeof(*io_tlb_orig_addr)); - - /* - * Get the overflow emergency buffer - */ - io_tlb_overflow_buffer = alloc_bootmem_low(io_tlb_overflow); - - iotlb_bus_start = virt_to_bus(iotlb_virt_start); - iotlb_bus_end = iotlb_bus_start + bytes; - iotlb_bus_mask = ~(dma_addr_t)(bytes - 1); - - printk(KERN_INFO "Software IO TLB enabled: \n" - " Aperture: %lu megabytes\n" - " Bus range: 0x%016lx - 0x%016lx\n" - " Kernel range: 0x%016lx - 0x%016lx\n", - bytes >> 20, - (unsigned long)iotlb_bus_start, - (unsigned long)iotlb_bus_end, - (unsigned long)iotlb_virt_start, - (unsigned long)iotlb_virt_start + bytes); -} - -void -swiotlb_init(void) -{ - long ram_end; - size_t defsz = 64 * (1 << 20); /* 64MB default size */ - - if (swiotlb_force == 1) { - swiotlb = 1; - } else if ((swiotlb_force != -1) && - (xen_start_info->flags & SIF_INITDOMAIN)) { - /* Domain 0 always has a swiotlb. */ - ram_end = HYPERVISOR_memory_op(XENMEM_maximum_ram_page, NULL); - if (ram_end <= 0x7ffff) - defsz = 2 * (1 << 20); /* 2MB on <2GB on systems. */ - swiotlb = 1; - } - - if (swiotlb) - swiotlb_init_with_default_size(defsz); - else - printk(KERN_INFO "Software IO TLB disabled\n"); -} - -/* - * We use __copy_to_user to transfer to the host buffer because the buffer - * may be mapped read-only (e.g, in blkback driver) but lower-level - * drivers map the buffer for DMA_BIDIRECTIONAL access. This causes an - * unnecessary copy from the aperture to the host buffer, and a page fault. - */ -static void -__sync_single(struct phys_addr buffer, char *dma_addr, size_t size, int dir) -{ - if (PageHighMem(buffer.page)) { - size_t len, bytes; - char *dev, *host, *kmp; - len = size; - while (len != 0) { - if (((bytes = len) + buffer.offset) > PAGE_SIZE) - bytes = PAGE_SIZE - buffer.offset; - kmp = kmap_atomic(buffer.page, KM_SWIOTLB); - dev = dma_addr + size - len; - host = kmp + buffer.offset; - if (dir == DMA_FROM_DEVICE) { - if (__copy_to_user(host, dev, bytes)) - /* inaccessible */; - } else - memcpy(dev, host, bytes); - kunmap_atomic(kmp, KM_SWIOTLB); - len -= bytes; - buffer.page++; - buffer.offset = 0; - } - } else { - char *host = (char *)phys_to_virt( - page_to_pseudophys(buffer.page)) + buffer.offset; - if (dir == DMA_FROM_DEVICE) { - if (__copy_to_user(host, dma_addr, size)) - /* inaccessible */; - } else if (dir == DMA_TO_DEVICE) - memcpy(dma_addr, host, size); - } -} - -/* - * Allocates bounce buffer and returns its kernel virtual address. - */ -static void * -map_single(struct device *hwdev, struct phys_addr buffer, size_t size, int dir) -{ - unsigned long flags; - char *dma_addr; - unsigned int nslots, stride, index, wrap; - int i; - - /* - * For mappings greater than a page, we limit the stride (and - * hence alignment) to a page size. - */ - nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; - if (size > PAGE_SIZE) - stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT)); - else - stride = 1; - - BUG_ON(!nslots); - - /* - * Find suitable number of IO TLB entries size that will fit this - * request and allocate a buffer from that IO TLB pool. - */ - spin_lock_irqsave(&io_tlb_lock, flags); - { - wrap = index = ALIGN(io_tlb_index, stride); - - if (index >= iotlb_nslabs) - wrap = index = 0; - - do { - /* - * If we find a slot that indicates we have 'nslots' - * number of contiguous buffers, we allocate the - * buffers from that slot and mark the entries as '0' - * indicating unavailable. - */ - if (io_tlb_list[index] >= nslots) { - int count = 0; - - for (i = index; i < (int)(index + nslots); i++) - io_tlb_list[i] = 0; - for (i = index - 1; - (OFFSET(i, IO_TLB_SEGSIZE) != - IO_TLB_SEGSIZE -1) && io_tlb_list[i]; - i--) - io_tlb_list[i] = ++count; - dma_addr = iotlb_virt_start + - (index << IO_TLB_SHIFT); - - /* - * Update the indices to avoid searching in - * the next round. - */ - io_tlb_index = - ((index + nslots) < iotlb_nslabs - ? (index + nslots) : 0); - - goto found; - } - index += stride; - if (index >= iotlb_nslabs) - index = 0; - } while (index != wrap); - - spin_unlock_irqrestore(&io_tlb_lock, flags); - return NULL; - } - found: - spin_unlock_irqrestore(&io_tlb_lock, flags); - - /* - * Save away the mapping from the original address to the DMA address. - * This is needed when we sync the memory. Then we sync the buffer if - * needed. - */ - io_tlb_orig_addr[index] = buffer; - if ((dir == DMA_TO_DEVICE) || (dir == DMA_BIDIRECTIONAL)) - __sync_single(buffer, dma_addr, size, DMA_TO_DEVICE); - - return dma_addr; -} - -/* - * dma_addr is the kernel virtual address of the bounce buffer to unmap. - */ -static void -unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir) -{ - unsigned long flags; - int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT; - int index = (dma_addr - iotlb_virt_start) >> IO_TLB_SHIFT; - struct phys_addr buffer = io_tlb_orig_addr[index]; - - /* - * First, sync the memory before unmapping the entry - */ - if ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)) - __sync_single(buffer, dma_addr, size, DMA_FROM_DEVICE); - - /* - * Return the buffer to the free list by setting the corresponding - * entries to indicate the number of contigous entries available. - * While returning the entries to the free list, we merge the entries - * with slots below and above the pool being returned. - */ - spin_lock_irqsave(&io_tlb_lock, flags); - { - count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ? - io_tlb_list[index + nslots] : 0); - /* - * Step 1: return the slots to the free list, merging the - * slots with superceeding slots - */ - for (i = index + nslots - 1; i >= index; i--) - io_tlb_list[i] = ++count; - /* - * Step 2: merge the returned slots with the preceding slots, - * if available (non zero) - */ - for (i = index - 1; - (OFFSET(i, IO_TLB_SEGSIZE) != - IO_TLB_SEGSIZE -1) && io_tlb_list[i]; - i--) - io_tlb_list[i] = ++count; - } - spin_unlock_irqrestore(&io_tlb_lock, flags); -} - -static void -sync_single(struct device *hwdev, char *dma_addr, size_t size, int dir) -{ - int index = (dma_addr - iotlb_virt_start) >> IO_TLB_SHIFT; - struct phys_addr buffer = io_tlb_orig_addr[index]; - BUG_ON((dir != DMA_FROM_DEVICE) && (dir != DMA_TO_DEVICE)); - __sync_single(buffer, dma_addr, size, dir); -} - -static void -swiotlb_full(struct device *dev, size_t size, int dir, int do_panic) -{ - /* - * Ran out of IOMMU space for this operation. This is very bad. - * Unfortunately the drivers cannot handle this operation properly. - * unless they check for pci_dma_mapping_error (most don't) - * When the mapping is small enough return a static buffer to limit - * the damage, or panic when the transfer is too big. - */ - printk(KERN_ERR "PCI-DMA: Out of SW-IOMMU space for %lu bytes at " - "device %s\n", (unsigned long)size, dev ? dev->bus_id : "?"); - - if (size > io_tlb_overflow && do_panic) { - if (dir == PCI_DMA_FROMDEVICE || dir == PCI_DMA_BIDIRECTIONAL) - panic("PCI-DMA: Memory would be corrupted\n"); - if (dir == PCI_DMA_TODEVICE || dir == PCI_DMA_BIDIRECTIONAL) - panic("PCI-DMA: Random memory would be DMAed\n"); - } -} - -/* - * Map a single buffer of the indicated size for DMA in streaming mode. The - * PCI address to use is returned. - * - * Once the device is given the dma address, the device owns this memory until - * either swiotlb_unmap_single or swiotlb_dma_sync_single is performed. - */ -dma_addr_t -swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir) -{ - dma_addr_t dev_addr = virt_to_bus(ptr); - void *map; - struct phys_addr buffer; - - BUG_ON(dir == DMA_NONE); - - /* - * If the pointer passed in happens to be in the device's DMA window, - * we can safely return the device addr and not worry about bounce - * buffering it. - */ - if (!range_straddles_page_boundary(ptr, size) && - !address_needs_mapping(hwdev, dev_addr)) - return dev_addr; - - /* - * Oh well, have to allocate and map a bounce buffer. - */ - buffer.page = virt_to_page(ptr); - buffer.offset = (unsigned long)ptr & ~PAGE_MASK; - map = map_single(hwdev, buffer, size, dir); - if (!map) { - swiotlb_full(hwdev, size, dir, 1); - map = io_tlb_overflow_buffer; - } - - dev_addr = virt_to_bus(map); - return dev_addr; -} - -/* - * Unmap a single streaming mode DMA translation. The dma_addr and size must - * match what was provided for in a previous swiotlb_map_single call. All - * other usages are undefined. - * - * After this call, reads by the cpu to the buffer are guaranteed to see - * whatever the device wrote there. - */ -void -swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size, - int dir) -{ - BUG_ON(dir == DMA_NONE); - if (in_swiotlb_aperture(dev_addr)) - unmap_single(hwdev, bus_to_virt(dev_addr), size, dir); -} - -/* - * Make physical memory consistent for a single streaming mode DMA translation - * after a transfer. - * - * If you perform a swiotlb_map_single() but wish to interrogate the buffer - * using the cpu, yet do not wish to teardown the PCI dma mapping, you must - * call this function before doing so. At the next point you give the PCI dma - * address back to the card, you must first perform a - * swiotlb_dma_sync_for_device, and then the device again owns the buffer - */ -void -swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir) -{ - BUG_ON(dir == DMA_NONE); - if (in_swiotlb_aperture(dev_addr)) - sync_single(hwdev, bus_to_virt(dev_addr), size, dir); -} - -void -swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir) -{ - BUG_ON(dir == DMA_NONE); - if (in_swiotlb_aperture(dev_addr)) - sync_single(hwdev, bus_to_virt(dev_addr), size, dir); -} - -/* - * Map a set of buffers described by scatterlist in streaming mode for DMA. - * This is the scatter-gather version of the above swiotlb_map_single - * interface. Here the scatter gather list elements are each tagged with the - * appropriate dma address and length. They are obtained via - * sg_dma_{address,length}(SG). - * - * NOTE: An implementation may be able to use a smaller number of - * DMA address/length pairs than there are SG table elements. - * (for example via virtual mapping capabilities) - * The routine returns the number of addr/length pairs actually - * used, at most nents. - * - * Device ownership issues as mentioned above for swiotlb_map_single are the - * same here. - */ -int -swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nelems, - int dir) -{ - struct phys_addr buffer; - dma_addr_t dev_addr; - char *map; - int i; - - BUG_ON(dir == DMA_NONE); - - for (i = 0; i < nelems; i++, sg++) { - dev_addr = SG_ENT_PHYS_ADDRESS(sg); - if (address_needs_mapping(hwdev, dev_addr)) { - buffer.page = sg->page; - buffer.offset = sg->offset; - map = map_single(hwdev, buffer, sg->length, dir); - if (!map) { - /* Don't panic here, we expect map_sg users - to do proper error handling. */ - swiotlb_full(hwdev, sg->length, dir, 0); - swiotlb_unmap_sg(hwdev, sg - i, i, dir); - sg[0].dma_length = 0; - return 0; - } - sg->dma_address = (dma_addr_t)virt_to_bus(map); - } else - sg->dma_address = dev_addr; - sg->dma_length = sg->length; - } - return nelems; -} - -/* - * Unmap a set of streaming mode DMA translations. Again, cpu read rules - * concerning calls here are the same as for swiotlb_unmap_single() above. - */ -void -swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nelems, - int dir) -{ - int i; - - BUG_ON(dir == DMA_NONE); - - for (i = 0; i < nelems; i++, sg++) - if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) - unmap_single(hwdev, - (void *)bus_to_virt(sg->dma_address), - sg->dma_length, dir); -} - -/* - * Make physical memory consistent for a set of streaming mode DMA translations - * after a transfer. - * - * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules - * and usage. - */ -void -swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg, - int nelems, int dir) -{ - int i; - - BUG_ON(dir == DMA_NONE); - - for (i = 0; i < nelems; i++, sg++) - if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) - sync_single(hwdev, - (void *)bus_to_virt(sg->dma_address), - sg->dma_length, dir); -} - -void -swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg, - int nelems, int dir) -{ - int i; - - BUG_ON(dir == DMA_NONE); - - for (i = 0; i < nelems; i++, sg++) - if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg)) - sync_single(hwdev, - (void *)bus_to_virt(sg->dma_address), - sg->dma_length, dir); -} - -dma_addr_t -swiotlb_map_page(struct device *hwdev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction direction) -{ - struct phys_addr buffer; - dma_addr_t dev_addr; - char *map; - - dev_addr = page_to_phys(page) + offset; - if (address_needs_mapping(hwdev, dev_addr)) { - buffer.page = page; - buffer.offset = offset; - map = map_single(hwdev, buffer, size, direction); - if (!map) { - swiotlb_full(hwdev, size, direction, 1); - map = io_tlb_overflow_buffer; - } - dev_addr = (dma_addr_t)virt_to_bus(map); - } - - return dev_addr; -} - -void -swiotlb_unmap_page(struct device *hwdev, dma_addr_t dma_address, - size_t size, enum dma_data_direction direction) -{ - BUG_ON(direction == DMA_NONE); - if (in_swiotlb_aperture(dma_address)) - unmap_single(hwdev, bus_to_virt(dma_address), size, direction); -} - -int -swiotlb_dma_mapping_error(dma_addr_t dma_addr) -{ - return (dma_addr == virt_to_bus(io_tlb_overflow_buffer)); -} - -/* - * Return whether the given PCI device DMA address mask can be supported - * properly. For example, if your device can only drive the low 24-bits - * during PCI bus mastering, then you would pass 0x00ffffff as the mask to - * this function. - */ -int -swiotlb_dma_supported (struct device *hwdev, u64 mask) -{ - return (mask >= (iotlb_bus_end - 1)); -} - -EXPORT_SYMBOL(swiotlb_init); -EXPORT_SYMBOL(swiotlb_map_single); -EXPORT_SYMBOL(swiotlb_unmap_single); -EXPORT_SYMBOL(swiotlb_map_sg); -EXPORT_SYMBOL(swiotlb_unmap_sg); -EXPORT_SYMBOL(swiotlb_sync_single_for_cpu); -EXPORT_SYMBOL(swiotlb_sync_single_for_device); -EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu); -EXPORT_SYMBOL(swiotlb_sync_sg_for_device); -EXPORT_SYMBOL(swiotlb_map_page); -EXPORT_SYMBOL(swiotlb_unmap_page); -EXPORT_SYMBOL(swiotlb_dma_mapping_error); -EXPORT_SYMBOL(swiotlb_dma_supported); - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/time.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/time.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,927 +0,0 @@ -/* - * linux/arch/i386/kernel/time.c - * - * Copyright (C) 1991, 1992, 1995 Linus Torvalds - * - * This file contains the PC-specific time handling details: - * reading the RTC at bootup, etc.. - * 1994-07-02 Alan Modra - * fixed set_rtc_mmss, fixed time.year for >= 2000, new mktime - * 1995-03-26 Markus Kuhn - * fixed 500 ms bug at call to set_rtc_mmss, fixed DS12887 - * precision CMOS clock update - * 1996-05-03 Ingo Molnar - * fixed time warps in do_[slow|fast]_gettimeoffset() - * 1997-09-10 Updated NTP code according to technical memorandum Jan '96 - * "A Kernel Model for Precision Timekeeping" by Dave Mills - * 1998-09-05 (Various) - * More robust do_fast_gettimeoffset() algorithm implemented - * (works with APM, Cyrix 6x86MX and Centaur C6), - * monotonic gettimeofday() with fast_get_timeoffset(), - * drift-proof precision TSC calibration on boot - * (C. Scott Ananian <cananian@xxxxxxxxxxxxxxxxxxxx>, Andrew D. - * Balsa <andrebalsa@xxxxxxxxxx>, Philip Gladstone <philip@xxxxxxxxxx>; - * ported from 2.0.35 Jumbo-9 by Michael Krause <m.krause@xxxxxxxxxxxxx>). - * 1998-12-16 Andrea Arcangeli - * Fixed Jumbo-9 code in 2.1.131: do_gettimeofday was missing 1 jiffy - * because was not accounting lost_ticks. - * 1998-12-24 Copyright (C) 1998 Andrea Arcangeli - * Fixed a xtime SMP race (we need the xtime_lock rw spinlock to - * serialize accesses to xtime/lost_ticks). - */ - -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/param.h> -#include <linux/string.h> -#include <linux/mm.h> -#include <linux/interrupt.h> -#include <linux/time.h> -#include <linux/delay.h> -#include <linux/init.h> -#include <linux/smp.h> -#include <linux/module.h> -#include <linux/sysdev.h> -#include <linux/bcd.h> -#include <linux/efi.h> -#include <linux/mca.h> -#include <linux/sysctl.h> -#include <linux/percpu.h> - -#include <asm/io.h> -#include <asm/smp.h> -#include <asm/irq.h> -#include <asm/msr.h> -#include <asm/delay.h> -#include <asm/mpspec.h> -#include <asm/uaccess.h> -#include <asm/processor.h> -#include <asm/timer.h> - -#include "mach_time.h" - -#include <linux/timex.h> -#include <linux/config.h> - -#include <asm/hpet.h> - -#include <asm/arch_hooks.h> - -#include "io_ports.h" - -#include <asm-xen/evtchn.h> - -extern spinlock_t i8259A_lock; -int pit_latch_buggy; /* extern */ - -u64 jiffies_64 = INITIAL_JIFFIES; - -EXPORT_SYMBOL(jiffies_64); - -#if defined(__x86_64__) -unsigned long vxtime_hz = PIT_TICK_RATE; -struct vxtime_data __vxtime __section_vxtime; /* for vsyscalls */ -volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES; -unsigned long __wall_jiffies __section_wall_jiffies = INITIAL_JIFFIES; -struct timespec __xtime __section_xtime; -struct timezone __sys_tz __section_sys_tz; -#endif - -#if defined(__x86_64__) -unsigned int cpu_khz; /* Detected as we calibrate the TSC */ -#else -unsigned long cpu_khz; /* Detected as we calibrate the TSC */ -#endif - -extern unsigned long wall_jiffies; - -DEFINE_SPINLOCK(rtc_lock); - -DEFINE_SPINLOCK(i8253_lock); -EXPORT_SYMBOL(i8253_lock); - -extern struct init_timer_opts timer_tsc_init; -extern struct timer_opts timer_tsc; -struct timer_opts *cur_timer = &timer_tsc; - -/* These are peridically updated in shared_info, and then copied here. */ -struct shadow_time_info { - u64 tsc_timestamp; /* TSC at last update of time vals. */ - u64 system_timestamp; /* Time, in nanosecs, since boot. */ - u32 tsc_to_nsec_mul; - u32 tsc_to_usec_mul; - int tsc_shift; - u32 version; -}; -static DEFINE_PER_CPU(struct shadow_time_info, shadow_time); -static struct timespec shadow_tv; -static u32 shadow_tv_version; - -/* Keep track of last time we did processing/updating of jiffies and xtime. */ -static u64 processed_system_time; /* System time (ns) at last processing. */ -static DEFINE_PER_CPU(u64, processed_system_time); - -/* Must be signed, as it's compared with s64 quantities which can be -ve. */ -#define NS_PER_TICK (1000000000LL/HZ) - -static inline void __normalize_time(time_t *sec, s64 *nsec) -{ - while (*nsec >= NSEC_PER_SEC) { - (*nsec) -= NSEC_PER_SEC; - (*sec)++; - } - while (*nsec < 0) { - (*nsec) += NSEC_PER_SEC; - (*sec)--; - } -} - -/* Does this guest OS track Xen time, or set its wall clock independently? */ -static int independent_wallclock = 0; -static int __init __independent_wallclock(char *str) -{ - independent_wallclock = 1; - return 1; -} -__setup("independent_wallclock", __independent_wallclock); - -int tsc_disable __initdata = 0; - -static void delay_tsc(unsigned long loops) -{ - unsigned long bclock, now; - - rdtscl(bclock); - do - { - rep_nop(); - rdtscl(now); - } while ((now-bclock) < loops); -} - -struct timer_opts timer_tsc = { - .name = "tsc", - .delay = delay_tsc, -}; - -/* - * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction, - * yielding a 64-bit result. - */ -static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift) -{ - u64 product; -#ifdef __i386__ - u32 tmp1, tmp2; -#endif - - if ( shift < 0 ) - delta >>= -shift; - else - delta <<= shift; - -#ifdef __i386__ - __asm__ ( - "mul %5 ; " - "mov %4,%%eax ; " - "mov %%edx,%4 ; " - "mul %5 ; " - "xor %5,%5 ; " - "add %4,%%eax ; " - "adc %5,%%edx ; " - : "=A" (product), "=r" (tmp1), "=r" (tmp2) - : "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) ); -#else - __asm__ ( - "mul %%rdx ; shrd $32,%%rdx,%%rax" - : "=a" (product) : "0" (delta), "d" ((u64)mul_frac) ); -#endif - - return product; -} - -void init_cpu_khz(void) -{ - u64 __cpu_khz = 1000000ULL << 32; - struct vcpu_time_info *info; - info = &HYPERVISOR_shared_info->vcpu_info[0].time; - do_div(__cpu_khz, info->tsc_to_system_mul); - if ( info->tsc_shift < 0 ) - cpu_khz = __cpu_khz << -info->tsc_shift; - else - cpu_khz = __cpu_khz >> info->tsc_shift; -} - -static u64 get_nsec_offset(struct shadow_time_info *shadow) -{ - u64 now, delta; - rdtscll(now); - delta = now - shadow->tsc_timestamp; - return scale_delta(delta, shadow->tsc_to_nsec_mul, shadow->tsc_shift); -} - -static unsigned long get_usec_offset(struct shadow_time_info *shadow) -{ - u64 now, delta; - rdtscll(now); - delta = now - shadow->tsc_timestamp; - return scale_delta(delta, shadow->tsc_to_usec_mul, shadow->tsc_shift); -} - -static void __update_wallclock(time_t sec, long nsec) -{ - long wtm_nsec, xtime_nsec; - time_t wtm_sec, xtime_sec; - u64 tmp, wc_nsec; - - /* Adjust wall-clock time base based on wall_jiffies ticks. */ - wc_nsec = processed_system_time; - wc_nsec += sec * (u64)NSEC_PER_SEC; - wc_nsec += nsec; - wc_nsec -= (jiffies - wall_jiffies) * (u64)NS_PER_TICK; - - /* Split wallclock base into seconds and nanoseconds. */ - tmp = wc_nsec; - xtime_nsec = do_div(tmp, 1000000000); - xtime_sec = (time_t)tmp; - - wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - xtime_sec); - wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - xtime_nsec); - - set_normalized_timespec(&xtime, xtime_sec, xtime_nsec); - set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); - - time_adjust = 0; /* stop active adjtime() */ - time_status |= STA_UNSYNC; - time_maxerror = NTP_PHASE_LIMIT; - time_esterror = NTP_PHASE_LIMIT; -} - -static void update_wallclock(void) -{ - shared_info_t *s = HYPERVISOR_shared_info; - - do { - shadow_tv_version = s->wc_version; - rmb(); - shadow_tv.tv_sec = s->wc_sec; - shadow_tv.tv_nsec = s->wc_nsec; - rmb(); - } - while ((s->wc_version & 1) | (shadow_tv_version ^ s->wc_version)); - - if (!independent_wallclock) - __update_wallclock(shadow_tv.tv_sec, shadow_tv.tv_nsec); -} - -/* - * Reads a consistent set of time-base values from Xen, into a shadow data - * area. - */ -static void get_time_values_from_xen(void) -{ - shared_info_t *s = HYPERVISOR_shared_info; - struct vcpu_time_info *src; - struct shadow_time_info *dst; - - src = &s->vcpu_info[smp_processor_id()].time; - dst = &per_cpu(shadow_time, smp_processor_id()); - - do { - dst->version = src->version; - rmb(); - dst->tsc_timestamp = src->tsc_timestamp; - dst->system_timestamp = src->system_time; - dst->tsc_to_nsec_mul = src->tsc_to_system_mul; - dst->tsc_shift = src->tsc_shift; - rmb(); - } - while ((src->version & 1) | (dst->version ^ src->version)); - - dst->tsc_to_usec_mul = dst->tsc_to_nsec_mul / 1000; -} - -static inline int time_values_up_to_date(int cpu) -{ - struct vcpu_time_info *src; - struct shadow_time_info *dst; - - src = &HYPERVISOR_shared_info->vcpu_info[cpu].time; - dst = &per_cpu(shadow_time, cpu); - - return (dst->version == src->version); -} - -/* - * This is a special lock that is owned by the CPU and holds the index - * register we are working with. It is required for NMI access to the - * CMOS/RTC registers. See include/asm-i386/mc146818rtc.h for details. - */ -volatile unsigned long cmos_lock = 0; -EXPORT_SYMBOL(cmos_lock); - -/* Routines for accessing the CMOS RAM/RTC. */ -unsigned char rtc_cmos_read(unsigned char addr) -{ - unsigned char val; - lock_cmos_prefix(addr); - outb_p(addr, RTC_PORT(0)); - val = inb_p(RTC_PORT(1)); - lock_cmos_suffix(addr); - return val; -} -EXPORT_SYMBOL(rtc_cmos_read); - -void rtc_cmos_write(unsigned char val, unsigned char addr) -{ - lock_cmos_prefix(addr); - outb_p(addr, RTC_PORT(0)); - outb_p(val, RTC_PORT(1)); - lock_cmos_suffix(addr); -} -EXPORT_SYMBOL(rtc_cmos_write); - -/* - * This version of gettimeofday has microsecond resolution - * and better than microsecond precision on fast x86 machines with TSC. - */ -void do_gettimeofday(struct timeval *tv) -{ - unsigned long seq; - unsigned long usec, sec; - unsigned long max_ntp_tick; - s64 nsec; - unsigned int cpu; - struct shadow_time_info *shadow; - u32 local_time_version; - - cpu = get_cpu(); - shadow = &per_cpu(shadow_time, cpu); - - do { - unsigned long lost; - - local_time_version = shadow->version; - seq = read_seqbegin(&xtime_lock); - - usec = get_usec_offset(shadow); - lost = jiffies - wall_jiffies; - - /* - * If time_adjust is negative then NTP is slowing the clock - * so make sure not to go into next possible interval. - * Better to lose some accuracy than have time go backwards.. - */ - if (unlikely(time_adjust < 0)) { - max_ntp_tick = (USEC_PER_SEC / HZ) - tickadj; - usec = min(usec, max_ntp_tick); - - if (lost) - usec += lost * max_ntp_tick; - } - else if (unlikely(lost)) - usec += lost * (USEC_PER_SEC / HZ); - - sec = xtime.tv_sec; - usec += (xtime.tv_nsec / NSEC_PER_USEC); - - nsec = shadow->system_timestamp - processed_system_time; - __normalize_time(&sec, &nsec); - usec += (long)nsec / NSEC_PER_USEC; - - if (unlikely(!time_values_up_to_date(cpu))) { - /* - * We may have blocked for a long time, - * rendering our calculations invalid - * (e.g. the time delta may have - * overflowed). Detect that and recalculate - * with fresh values. - */ - get_time_values_from_xen(); - continue; - } - } while (read_seqretry(&xtime_lock, seq) || - (local_time_version != shadow->version)); - - put_cpu(); - - while (usec >= USEC_PER_SEC) { - usec -= USEC_PER_SEC; - sec++; - } - - tv->tv_sec = sec; - tv->tv_usec = usec; -} - -EXPORT_SYMBOL(do_gettimeofday); - -int do_settimeofday(struct timespec *tv) -{ - time_t sec; - s64 nsec; - unsigned int cpu; - struct shadow_time_info *shadow; - dom0_op_t op; - - if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) - return -EINVAL; - - cpu = get_cpu(); - shadow = &per_cpu(shadow_time, cpu); - - write_seqlock_irq(&xtime_lock); - - /* - * Ensure we don't get blocked for a long time so that our time delta - * overflows. If that were to happen then our shadow time values would - * be stale, so we can retry with fresh ones. - */ - for ( ; ; ) { - nsec = tv->tv_nsec - get_nsec_offset(shadow); - if (time_values_up_to_date(cpu)) - break; - get_time_values_from_xen(); - } - sec = tv->tv_sec; - __normalize_time(&sec, &nsec); - - if ((xen_start_info->flags & SIF_INITDOMAIN) && - !independent_wallclock) { - op.cmd = DOM0_SETTIME; - op.u.settime.secs = sec; - op.u.settime.nsecs = nsec; - op.u.settime.system_time = shadow->system_timestamp; - HYPERVISOR_dom0_op(&op); - update_wallclock(); - } else if (independent_wallclock) { - nsec -= shadow->system_timestamp; - __normalize_time(&sec, &nsec); - __update_wallclock(sec, nsec); - } - - write_sequnlock_irq(&xtime_lock); - - put_cpu(); - - clock_was_set(); - return 0; -} - -EXPORT_SYMBOL(do_settimeofday); - -#ifdef CONFIG_XEN_PRIVILEGED_GUEST -static int set_rtc_mmss(unsigned long nowtime) -{ - int retval; - - WARN_ON(irqs_disabled()); - - if (!(xen_start_info->flags & SIF_INITDOMAIN)) - return 0; - - /* gets recalled with irq locally disabled */ - spin_lock_irq(&rtc_lock); - if (efi_enabled) - retval = efi_set_rtc_mmss(nowtime); - else - retval = mach_set_rtc_mmss(nowtime); - spin_unlock_irq(&rtc_lock); - - return retval; -} -#else -static int set_rtc_mmss(unsigned long nowtime) -{ - return 0; -} -#endif - -/* monotonic_clock(): returns # of nanoseconds passed since time_init() - * Note: This function is required to return accurate - * time even in the absence of multiple timer ticks. - */ -unsigned long long monotonic_clock(void) -{ - int cpu = get_cpu(); - struct shadow_time_info *shadow = &per_cpu(shadow_time, cpu); - u64 time; - u32 local_time_version; - - do { - local_time_version = shadow->version; - smp_rmb(); - time = shadow->system_timestamp + get_nsec_offset(shadow); - if (!time_values_up_to_date(cpu)) - get_time_values_from_xen(); - smp_rmb(); - } while (local_time_version != shadow->version); - - put_cpu(); - - return time; -} -EXPORT_SYMBOL(monotonic_clock); - -unsigned long long sched_clock(void) -{ - return monotonic_clock(); -} - -#if defined(CONFIG_SMP) && defined(CONFIG_FRAME_POINTER) -unsigned long profile_pc(struct pt_regs *regs) -{ - unsigned long pc = instruction_pointer(regs); - - if (in_lock_functions(pc)) - return *(unsigned long *)(regs->ebp + 4); - - return pc; -} -EXPORT_SYMBOL(profile_pc); -#endif - -irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs) -{ - s64 delta, delta_cpu; - int i, cpu = smp_processor_id(); - struct shadow_time_info *shadow = &per_cpu(shadow_time, cpu); - - write_seqlock(&xtime_lock); - - do { - get_time_values_from_xen(); - - delta = delta_cpu = - shadow->system_timestamp + get_nsec_offset(shadow); - delta -= processed_system_time; - delta_cpu -= per_cpu(processed_system_time, cpu); - } - while (!time_values_up_to_date(cpu)); - - if ((unlikely(delta < -1000000LL) || unlikely(delta_cpu < 0)) - && printk_ratelimit()) { - printk("Timer ISR/%d: Time went backwards: " - "delta=%lld cpu_delta=%lld shadow=%lld " - "off=%lld processed=%lld cpu_processed=%lld\n", - cpu, delta, delta_cpu, shadow->system_timestamp, - (s64)get_nsec_offset(shadow), - processed_system_time, - per_cpu(processed_system_time, cpu)); - for (i = 0; i < num_online_cpus(); i++) - printk(" %d: %lld\n", i, - per_cpu(processed_system_time, i)); - } - - /* System-wide jiffy work. */ - while (delta >= NS_PER_TICK) { - delta -= NS_PER_TICK; - processed_system_time += NS_PER_TICK; - do_timer(regs); - } - - if (shadow_tv_version != HYPERVISOR_shared_info->wc_version) { - update_wallclock(); - clock_was_set(); - } - - write_sequnlock(&xtime_lock); - - /* - * Local CPU jiffy work. No need to hold xtime_lock, and I'm not sure - * if there is risk of deadlock if we do (since update_process_times - * may do scheduler rebalancing work and thus acquire runqueue locks). - */ - while (delta_cpu >= NS_PER_TICK) { - delta_cpu -= NS_PER_TICK; - per_cpu(processed_system_time, cpu) += NS_PER_TICK; - update_process_times(user_mode(regs)); - profile_tick(CPU_PROFILING, regs); - } - - return IRQ_HANDLED; -} - -/* not static: needed by APM */ -unsigned long get_cmos_time(void) -{ - unsigned long retval; - - spin_lock(&rtc_lock); - - if (efi_enabled) - retval = efi_get_time(); - else - retval = mach_get_cmos_time(); - - spin_unlock(&rtc_lock); - - return retval; -} -static void sync_cmos_clock(unsigned long dummy); - -static struct timer_list sync_cmos_timer = - TIMER_INITIALIZER(sync_cmos_clock, 0, 0); - -static void sync_cmos_clock(unsigned long dummy) -{ - struct timeval now, next; - int fail = 1; - - /* - * If we have an externally synchronized Linux clock, then update - * CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be - * called as close as possible to 500 ms before the new second starts. - * This code is run on a timer. If the clock is set, that timer - * may not expire at the correct time. Thus, we adjust... - */ - if ((time_status & STA_UNSYNC) != 0) - /* - * Not synced, exit, do not restart a timer (if one is - * running, let it run out). - */ - return; - - do_gettimeofday(&now); - if (now.tv_usec >= USEC_AFTER - ((unsigned) TICK_SIZE) / 2 && - now.tv_usec <= USEC_BEFORE + ((unsigned) TICK_SIZE) / 2) - fail = set_rtc_mmss(now.tv_sec); - - next.tv_usec = USEC_AFTER - now.tv_usec; - if (next.tv_usec <= 0) - next.tv_usec += USEC_PER_SEC; - - if (!fail) - next.tv_sec = 659; - else - next.tv_sec = 0; - - if (next.tv_usec >= USEC_PER_SEC) { - next.tv_sec++; - next.tv_usec -= USEC_PER_SEC; - } - mod_timer(&sync_cmos_timer, jiffies + timeval_to_jiffies(&next)); -} - -void notify_arch_cmos_timer(void) -{ - mod_timer(&sync_cmos_timer, jiffies + 1); -} - -static long clock_cmos_diff, sleep_start; - -static int timer_suspend(struct sys_device *dev, pm_message_t state) -{ - /* - * Estimate time zone so that set_time can update the clock - */ - clock_cmos_diff = -get_cmos_time(); - clock_cmos_diff += get_seconds(); - sleep_start = get_cmos_time(); - return 0; -} - -static int timer_resume(struct sys_device *dev) -{ - unsigned long flags; - unsigned long sec; - unsigned long sleep_length; - -#ifdef CONFIG_HPET_TIMER - if (is_hpet_enabled()) - hpet_reenable(); -#endif - sec = get_cmos_time() + clock_cmos_diff; - sleep_length = (get_cmos_time() - sleep_start) * HZ; - write_seqlock_irqsave(&xtime_lock, flags); - xtime.tv_sec = sec; - xtime.tv_nsec = 0; - write_sequnlock_irqrestore(&xtime_lock, flags); - jiffies += sleep_length; - wall_jiffies += sleep_length; - return 0; -} - -static struct sysdev_class timer_sysclass = { - .resume = timer_resume, - .suspend = timer_suspend, - set_kset_name("timer"), -}; - - -/* XXX this driverfs stuff should probably go elsewhere later -john */ -static struct sys_device device_timer = { - .id = 0, - .cls = &timer_sysclass, -}; - -static int time_init_device(void) -{ - int error = sysdev_class_register(&timer_sysclass); - if (!error) - error = sysdev_register(&device_timer); - return error; -} - -device_initcall(time_init_device); - -#ifdef CONFIG_HPET_TIMER -extern void (*late_time_init)(void); -/* Duplicate of time_init() below, with hpet_enable part added */ -static void __init hpet_time_init(void) -{ - xtime.tv_sec = get_cmos_time(); - xtime.tv_nsec = (INITIAL_JIFFIES % HZ) * (NSEC_PER_SEC / HZ); - set_normalized_timespec(&wall_to_monotonic, - -xtime.tv_sec, -xtime.tv_nsec); - - if ((hpet_enable() >= 0) && hpet_use_timer) { - printk("Using HPET for base-timer\n"); - } - - cur_timer = select_timer(); - printk(KERN_INFO "Using %s for high-res timesource\n",cur_timer->name); - - time_init_hook(); -} -#endif - -/* Dynamically-mapped IRQ. */ -DEFINE_PER_CPU(int, timer_irq); - -extern void (*late_time_init)(void); -static void setup_cpu0_timer_irq(void) -{ - per_cpu(timer_irq, 0) = - bind_virq_to_irqhandler( - VIRQ_TIMER, - 0, - timer_interrupt, - SA_INTERRUPT, - "timer0", - NULL); - BUG_ON(per_cpu(timer_irq, 0) < 0); -} - -void __init time_init(void) -{ -#ifdef CONFIG_HPET_TIMER - if (is_hpet_capable()) { - /* - * HPET initialization needs to do memory-mapped io. So, let - * us do a late initialization after mem_init(). - */ - late_time_init = hpet_time_init; - return; - } -#endif - get_time_values_from_xen(); - - processed_system_time = per_cpu(shadow_time, 0).system_timestamp; - per_cpu(processed_system_time, 0) = processed_system_time; - - update_wallclock(); - - init_cpu_khz(); - printk(KERN_INFO "Xen reported: %lu.%03lu MHz processor.\n", - cpu_khz / 1000, cpu_khz % 1000); - -#if defined(__x86_64__) - vxtime.mode = VXTIME_TSC; - vxtime.quot = (1000000L << 32) / vxtime_hz; - vxtime.tsc_quot = (1000L << 32) / cpu_khz; - vxtime.hz = vxtime_hz; - sync_core(); - rdtscll(vxtime.last_tsc); -#endif - - /* Cannot request_irq() until kmem is initialised. */ - late_time_init = setup_cpu0_timer_irq; -} - -/* Convert jiffies to system time. */ -static inline u64 jiffies_to_st(unsigned long j) -{ - unsigned long seq; - long delta; - u64 st; - - do { - seq = read_seqbegin(&xtime_lock); - delta = j - jiffies; - /* NB. The next check can trigger in some wrap-around cases, - * but that's ok: we'll just end up with a shorter timeout. */ - if (delta < 1) - delta = 1; - st = processed_system_time + (delta * (u64)NS_PER_TICK); - } while (read_seqretry(&xtime_lock, seq)); - - return st; -} - -/* - * stop_hz_timer / start_hz_timer - enter/exit 'tickless mode' on an idle cpu - * These functions are based on implementations from arch/s390/kernel/time.c - */ -void stop_hz_timer(void) -{ - unsigned int cpu = smp_processor_id(); - unsigned long j; - - /* s390 does this /before/ checking rcu_pending(). We copy them. */ - cpu_set(cpu, nohz_cpu_mask); - - /* Leave ourselves in 'tick mode' if rcu or softirq pending. */ - if (rcu_pending(cpu) || local_softirq_pending()) { - cpu_clear(cpu, nohz_cpu_mask); - j = jiffies + 1; - } else { - j = next_timer_interrupt(); - } - - BUG_ON(HYPERVISOR_set_timer_op(jiffies_to_st(j)) != 0); -} - -void start_hz_timer(void) -{ - cpu_clear(smp_processor_id(), nohz_cpu_mask); -} - -/* No locking required. We are only CPU running, and interrupts are off. */ -void time_resume(void) -{ - init_cpu_khz(); - - get_time_values_from_xen(); - - processed_system_time = per_cpu(shadow_time, 0).system_timestamp; - per_cpu(processed_system_time, 0) = processed_system_time; - - update_wallclock(); -} - -#ifdef CONFIG_SMP -static char timer_name[NR_CPUS][15]; - -void local_setup_timer(unsigned int cpu) -{ - int seq; - - BUG_ON(cpu == 0); - - do { - seq = read_seqbegin(&xtime_lock); - /* Use cpu0 timestamp: cpu's shadow is not initialised yet. */ - per_cpu(processed_system_time, cpu) = - per_cpu(shadow_time, 0).system_timestamp; - } while (read_seqretry(&xtime_lock, seq)); - - sprintf(timer_name[cpu], "timer%d", cpu); - per_cpu(timer_irq, cpu) = - bind_virq_to_irqhandler( - VIRQ_TIMER, - cpu, - timer_interrupt, - SA_INTERRUPT, - timer_name[cpu], - NULL); - BUG_ON(per_cpu(timer_irq, cpu) < 0); -} - -void local_teardown_timer(unsigned int cpu) -{ - BUG_ON(cpu == 0); - unbind_from_irqhandler(per_cpu(timer_irq, cpu), NULL); -} -#endif - -/* - * /proc/sys/xen: This really belongs in another file. It can stay here for - * now however. - */ -static ctl_table xen_subtable[] = { - {1, "independent_wallclock", &independent_wallclock, - sizeof(independent_wallclock), 0644, NULL, proc_dointvec}, - {0} -}; -static ctl_table xen_table[] = { - {123, "xen", NULL, 0, 0555, xen_subtable}, - {0} -}; -static int __init xen_sysctl_init(void) -{ - (void)register_sysctl_table(xen_table, 0); - return 0; -} -__initcall(xen_sysctl_init); - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/traps.c --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/traps.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,1029 +0,0 @@ -/* - * linux/arch/i386/traps.c - * - * Copyright (C) 1991, 1992 Linus Torvalds - * - * Pentium III FXSR, SSE support - * Gareth Hughes <gareth@xxxxxxxxxxx>, May 2000 - */ - -/* - * 'Traps.c' handles hardware traps and faults after we have saved some - * state in 'asm.s'. - */ -#include <linux/config.h> -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/timer.h> -#include <linux/mm.h> -#include <linux/init.h> -#include <linux/delay.h> -#include <linux/spinlock.h> -#include <linux/interrupt.h> -#include <linux/highmem.h> -#include <linux/kallsyms.h> -#include <linux/ptrace.h> -#include <linux/utsname.h> -#include <linux/kprobes.h> - -#ifdef CONFIG_EISA -#include <linux/ioport.h> -#include <linux/eisa.h> -#endif - -#ifdef CONFIG_MCA -#include <linux/mca.h> -#endif - -#include <asm/processor.h> -#include <asm/system.h> -#include <asm/uaccess.h> -#include <asm/io.h> -#include <asm/atomic.h> -#include <asm/debugreg.h> -#include <asm/desc.h> -#include <asm/i387.h> -#include <asm/nmi.h> - -#include <asm/smp.h> -#include <asm/arch_hooks.h> -#include <asm/kdebug.h> - -#include <linux/irq.h> -#include <linux/module.h> - -#include "mach_traps.h" - -asmlinkage int system_call(void); - -/* Do we ignore FPU interrupts ? */ -char ignore_fpu_irq = 0; - -/* - * The IDT has to be page-aligned to simplify the Pentium - * F0 0F bug workaround.. We have a special link segment - * for this. - */ -struct desc_struct idt_table[256] __attribute__((__section__(".data.idt"))) = { {0, 0}, }; - -asmlinkage void divide_error(void); -asmlinkage void debug(void); -asmlinkage void nmi(void); -asmlinkage void int3(void); -asmlinkage void overflow(void); -asmlinkage void bounds(void); -asmlinkage void invalid_op(void); -asmlinkage void device_not_available(void); -asmlinkage void coprocessor_segment_overrun(void); -asmlinkage void invalid_TSS(void); -asmlinkage void segment_not_present(void); -asmlinkage void stack_segment(void); -asmlinkage void general_protection(void); -asmlinkage void page_fault(void); -asmlinkage void coprocessor_error(void); -asmlinkage void simd_coprocessor_error(void); -asmlinkage void alignment_check(void); -asmlinkage void fixup_4gb_segment(void); -asmlinkage void machine_check(void); - -static int kstack_depth_to_print = 24; -struct notifier_block *i386die_chain; -static DEFINE_SPINLOCK(die_notifier_lock); - -int register_die_notifier(struct notifier_block *nb) -{ - int err = 0; - unsigned long flags; - spin_lock_irqsave(&die_notifier_lock, flags); - err = notifier_chain_register(&i386die_chain, nb); - spin_unlock_irqrestore(&die_notifier_lock, flags); - return err; -} - -static inline int valid_stack_ptr(struct thread_info *tinfo, void *p) -{ - return p > (void *)tinfo && - p < (void *)tinfo + THREAD_SIZE - 3; -} - -static inline unsigned long print_context_stack(struct thread_info *tinfo, - unsigned long *stack, unsigned long ebp) -{ - unsigned long addr; - -#ifdef CONFIG_FRAME_POINTER - while (valid_stack_ptr(tinfo, (void *)ebp)) { - addr = *(unsigned long *)(ebp + 4); - printk(" [<%08lx>] ", addr); - print_symbol("%s", addr); - printk("\n"); - ebp = *(unsigned long *)ebp; - } -#else - while (valid_stack_ptr(tinfo, stack)) { - addr = *stack++; - if (__kernel_text_address(addr)) { - printk(" [<%08lx>]", addr); - print_symbol(" %s", addr); - printk("\n"); - } - } -#endif - return ebp; -} - -void show_trace(struct task_struct *task, unsigned long * stack) -{ - unsigned long ebp; - - if (!task) - task = current; - - if (task == current) { - /* Grab ebp right from our regs */ - asm ("movl %%ebp, %0" : "=r" (ebp) : ); - } else { - /* ebp is the last reg pushed by switch_to */ - ebp = *(unsigned long *) task->thread.esp; - } - - while (1) { - struct thread_info *context; - context = (struct thread_info *) - ((unsigned long)stack & (~(THREAD_SIZE - 1))); - ebp = print_context_stack(context, stack, ebp); - stack = (unsigned long*)context->previous_esp; - if (!stack) - break; - printk(" =======================\n"); - } -} - -void show_stack(struct task_struct *task, unsigned long *esp) -{ - unsigned long *stack; - int i; - - if (esp == NULL) { - if (task) - esp = (unsigned long*)task->thread.esp; - else - esp = (unsigned long *)&esp; - } - - stack = esp; - for(i = 0; i < kstack_depth_to_print; i++) { - if (kstack_end(stack)) - break; - if (i && ((i % 8) == 0)) - printk("\n "); - printk("%08lx ", *stack++); - } - printk("\nCall Trace:\n"); - show_trace(task, esp); -} - -/* - * The architecture-independent dump_stack generator - */ -void dump_stack(void) -{ - unsigned long stack; - - show_trace(current, &stack); -} - -EXPORT_SYMBOL(dump_stack); - -void show_registers(struct pt_regs *regs) -{ - int i; - int in_kernel = 1; - unsigned long esp; - unsigned short ss; - - esp = (unsigned long) (&regs->esp); - ss = __KERNEL_DS; - if (regs->xcs & 2) { - in_kernel = 0; - esp = regs->esp; - ss = regs->xss & 0xffff; - } - print_modules(); - printk("CPU: %d\nEIP: %04x:[<%08lx>] %s VLI\nEFLAGS: %08lx" - " (%s) \n", - smp_processor_id(), 0xffff & regs->xcs, regs->eip, - print_tainted(), regs->eflags, system_utsname.release); - print_symbol("EIP is at %s\n", regs->eip); - printk("eax: %08lx ebx: %08lx ecx: %08lx edx: %08lx\n", - regs->eax, regs->ebx, regs->ecx, regs->edx); - printk("esi: %08lx edi: %08lx ebp: %08lx esp: %08lx\n", - regs->esi, regs->edi, regs->ebp, esp); - printk("ds: %04x es: %04x ss: %04x\n", - regs->xds & 0xffff, regs->xes & 0xffff, ss); - printk("Process %s (pid: %d, threadinfo=%p task=%p)", - current->comm, current->pid, current_thread_info(), current); - /* - * When in-kernel, we also print out the stack and code at the - * time of the fault.. - */ - if (in_kernel) { - u8 *eip; - - printk("\nStack: "); - show_stack(NULL, (unsigned long*)esp); - - printk("Code: "); - - eip = (u8 *)regs->eip - 43; - for (i = 0; i < 64; i++, eip++) { - unsigned char c; - - if (eip < (u8 *)PAGE_OFFSET || __get_user(c, eip)) { - printk(" Bad EIP value."); - break; - } - if (eip == (u8 *)regs->eip) - printk("<%02x> ", c); - else - printk("%02x ", c); - } - } - printk("\n"); -} - -static void handle_BUG(struct pt_regs *regs) -{ - unsigned short ud2; - unsigned short line; - char *file; - char c; - unsigned long eip; - - if (regs->xcs & 2) - goto no_bug; /* Not in kernel */ - - eip = regs->eip; - - if (eip < PAGE_OFFSET) - goto no_bug; - if (__get_user(ud2, (unsigned short *)eip)) - goto no_bug; - if (ud2 != 0x0b0f) - goto no_bug; - if (__get_user(line, (unsigned short *)(eip + 2))) - goto bug; - if (__get_user(file, (char **)(eip + 4)) || - (unsigned long)file < PAGE_OFFSET || __get_user(c, file)) - file = "<bad filename>"; - - printk("------------[ cut here ]------------\n"); - printk(KERN_ALERT "kernel BUG at %s:%d!\n", file, line); - -no_bug: - return; - - /* Here we know it was a BUG but file-n-line is unavailable */ -bug: - printk("Kernel BUG\n"); -} - -void die(const char * str, struct pt_regs * regs, long err) -{ - static struct { - spinlock_t lock; - u32 lock_owner; - int lock_owner_depth; - } die = { - .lock = SPIN_LOCK_UNLOCKED, - .lock_owner = -1, - .lock_owner_depth = 0 - }; - static int die_counter; - - if (die.lock_owner != _smp_processor_id()) { - console_verbose(); - spin_lock_irq(&die.lock); - die.lock_owner = smp_processor_id(); - die.lock_owner_depth = 0; - bust_spinlocks(1); - } - - if (++die.lock_owner_depth < 3) { - int nl = 0; - handle_BUG(regs); - printk(KERN_ALERT "%s: %04lx [#%d]\n", str, err & 0xffff, ++die_counter); -#ifdef CONFIG_PREEMPT - printk("PREEMPT "); - nl = 1; -#endif -#ifdef CONFIG_SMP - printk("SMP "); - nl = 1; -#endif -#ifdef CONFIG_DEBUG_PAGEALLOC - printk("DEBUG_PAGEALLOC"); - nl = 1; -#endif - if (nl) - printk("\n"); - notify_die(DIE_OOPS, (char *)str, regs, err, 255, SIGSEGV); - show_registers(regs); - } else - printk(KERN_ERR "Recursive die() failure, output suppressed\n"); - - bust_spinlocks(0); - die.lock_owner = -1; - spin_unlock_irq(&die.lock); - if (in_interrupt()) - panic("Fatal exception in interrupt"); - - if (panic_on_oops) { - printk(KERN_EMERG "Fatal exception: panic in 5 seconds\n"); - ssleep(5); - panic("Fatal exception"); - } - do_exit(SIGSEGV); -} - -static inline void die_if_kernel(const char * str, struct pt_regs * regs, long err) -{ - if (!(regs->eflags & VM_MASK) && !(2 & regs->xcs)) - die(str, regs, err); -} - -static void do_trap(int trapnr, int signr, char *str, int vm86, - struct pt_regs * regs, long error_code, siginfo_t *info) -{ - if (regs->eflags & VM_MASK) { - if (vm86) - goto vm86_trap; - goto trap_signal; - } - - if (!(regs->xcs & 2)) - goto kernel_trap; - - trap_signal: { - struct task_struct *tsk = current; - tsk->thread.error_code = error_code; - tsk->thread.trap_no = trapnr; - if (info) - force_sig_info(signr, info, tsk); - else - force_sig(signr, tsk); - return; - } - - kernel_trap: { - if (!fixup_exception(regs)) - die(str, regs, error_code); - return; - } - - vm86_trap: { - int ret = handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, trapnr); - if (ret) goto trap_signal; - return; - } -} - -#define DO_ERROR(trapnr, signr, str, name) \ -fastcall void do_##name(struct pt_regs * regs, long error_code) \ -{ \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ - return; \ - do_trap(trapnr, signr, str, 0, regs, error_code, NULL); \ -} - -#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ -fastcall void do_##name(struct pt_regs * regs, long error_code) \ -{ \ - siginfo_t info; \ - info.si_signo = signr; \ - info.si_errno = 0; \ - info.si_code = sicode; \ - info.si_addr = (void __user *)siaddr; \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ - return; \ - do_trap(trapnr, signr, str, 0, regs, error_code, &info); \ -} - -#define DO_VM86_ERROR(trapnr, signr, str, name) \ -fastcall void do_##name(struct pt_regs * regs, long error_code) \ -{ \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ - return; \ - do_trap(trapnr, signr, str, 1, regs, error_code, NULL); \ -} - -#define DO_VM86_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ -fastcall void do_##name(struct pt_regs * regs, long error_code) \ -{ \ - siginfo_t info; \ - info.si_signo = signr; \ - info.si_errno = 0; \ - info.si_code = sicode; \ - info.si_addr = (void __user *)siaddr; \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ - return; \ - do_trap(trapnr, signr, str, 1, regs, error_code, &info); \ -} - -DO_VM86_ERROR_INFO( 0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->eip) -#ifndef CONFIG_KPROBES -DO_VM86_ERROR( 3, SIGTRAP, "int3", int3) -#endif -DO_VM86_ERROR( 4, SIGSEGV, "overflow", overflow) -DO_VM86_ERROR( 5, SIGSEGV, "bounds", bounds) -DO_ERROR_INFO( 6, SIGILL, "invalid operand", invalid_op, ILL_ILLOPN, regs->eip) -DO_VM86_ERROR( 7, SIGSEGV, "device not available", device_not_available) -DO_ERROR( 9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun) -DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS) -DO_ERROR(11, SIGBUS, "segment not present", segment_not_present) -DO_ERROR(12, SIGBUS, "stack segment", stack_segment) -DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0) -#ifdef CONFIG_X86_MCE -DO_ERROR(18, SIGBUS, "machine check", machine_check) -#endif -DO_ERROR_INFO(32, SIGSEGV, "iret exception", iret_error, ILL_BADSTK, 0) - -fastcall void do_general_protection(struct pt_regs * regs, long error_code) -{ - /* - * If we trapped on an LDT access then ensure that the default_ldt is - * loaded, if nothing else. We load default_ldt lazily because LDT - * switching costs time and many applications don't need it. - */ - if (unlikely((error_code & 6) == 4)) { - unsigned long ldt; - __asm__ __volatile__ ("sldt %0" : "=r" (ldt)); - if (ldt == 0) { - xen_set_ldt((unsigned long)&default_ldt[0], 5); - return; - } - } - - if (regs->eflags & VM_MASK) - goto gp_in_vm86; - - if (!(regs->xcs & 2)) - goto gp_in_kernel; - - current->thread.error_code = error_code; - current->thread.trap_no = 13; - force_sig(SIGSEGV, current); - return; - -gp_in_vm86: - local_irq_enable(); - handle_vm86_fault((struct kernel_vm86_regs *) regs, error_code); - return; - -gp_in_kernel: - if (!fixup_exception(regs)) { - if (notify_die(DIE_GPF, "general protection fault", regs, - error_code, 13, SIGSEGV) == NOTIFY_STOP) - return; - die("general protection fault", regs, error_code); - } -} - -static void mem_parity_error(unsigned char reason, struct pt_regs * regs) -{ - printk("Uhhuh. NMI received. Dazed and confused, but trying to continue\n"); - printk("You probably have a hardware problem with your RAM chips\n"); - - /* Clear and disable the memory parity error line. */ - clear_mem_error(reason); -} - -static void io_check_error(unsigned char reason, struct pt_regs * regs) -{ - printk("NMI: IOCK error (debug interrupt?)\n"); - show_registers(regs); - - /* Re-enable the IOCK line, wait for a few seconds */ - clear_io_check_error(reason); -} - -static void unknown_nmi_error(unsigned char reason, struct pt_regs * regs) -{ -#ifdef CONFIG_MCA - /* Might actually be able to figure out what the guilty party - * is. */ - if( MCA_bus ) { - mca_handle_nmi(); - return; - } -#endif - printk("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n", - reason, smp_processor_id()); - printk("Dazed and confused, but trying to continue\n"); - printk("Do you have a strange power saving mode enabled?\n"); -} - -static DEFINE_SPINLOCK(nmi_print_lock); - -void die_nmi (struct pt_regs *regs, const char *msg) -{ - spin_lock(&nmi_print_lock); - /* - * We are in trouble anyway, lets at least try - * to get a message out. - */ - bust_spinlocks(1); - printk(msg); - printk(" on CPU%d, eip %08lx, registers:\n", - smp_processor_id(), regs->eip); - show_registers(regs); - printk("console shuts up ...\n"); - console_silent(); - spin_unlock(&nmi_print_lock); - bust_spinlocks(0); - do_exit(SIGSEGV); -} - -static void default_do_nmi(struct pt_regs * regs) -{ - unsigned char reason = 0; - - /* Only the BSP gets external NMIs from the system. */ - if (!smp_processor_id()) - reason = get_nmi_reason(); - - if (!(reason & 0xc0)) { - if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 0, SIGINT) - == NOTIFY_STOP) - return; -#ifdef CONFIG_X86_LOCAL_APIC - /* - * Ok, so this is none of the documented NMI sources, - * so it must be the NMI watchdog. - */ - if (nmi_watchdog) { - nmi_watchdog_tick(regs); - return; - } -#endif - unknown_nmi_error(reason, regs); - return; - } - if (notify_die(DIE_NMI, "nmi", regs, reason, 0, SIGINT) == NOTIFY_STOP) - return; - if (reason & 0x80) - mem_parity_error(reason, regs); - if (reason & 0x40) - io_check_error(reason, regs); - /* - * Reassert NMI in case it became active meanwhile - * as it's edge-triggered. - */ - reassert_nmi(); -} - -static int dummy_nmi_callback(struct pt_regs * regs, int cpu) -{ - return 0; -} - -static nmi_callback_t nmi_callback = dummy_nmi_callback; - -fastcall void do_nmi(struct pt_regs * regs, long error_code) -{ - int cpu; - - nmi_enter(); - - cpu = smp_processor_id(); - -#ifdef CONFIG_HOTPLUG_CPU - if (!cpu_online(cpu)) { - nmi_exit(); - return; - } -#endif - - ++nmi_count(cpu); - - if (!nmi_callback(regs, cpu)) - default_do_nmi(regs); - - nmi_exit(); -} - -void set_nmi_callback(nmi_callback_t callback) -{ - nmi_callback = callback; -} - -void unset_nmi_callback(void) -{ - nmi_callback = dummy_nmi_callback; -} - -#ifdef CONFIG_KPROBES -fastcall void do_int3(struct pt_regs *regs, long error_code) -{ - if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) - == NOTIFY_STOP) - return; - /* This is an interrupt gate, because kprobes wants interrupts - disabled. Normal trap handlers don't. */ - restore_interrupts(regs); - do_trap(3, SIGTRAP, "int3", 1, regs, error_code, NULL); -} -#endif - -/* - * Our handling of the processor debug registers is non-trivial. - * We do not clear them on entry and exit from the kernel. Therefore - * it is possible to get a watchpoint trap here from inside the kernel. - * However, the code in ./ptrace.c has ensured that the user can - * only set watchpoints on userspace addresses. Therefore the in-kernel - * watchpoint trap can only occur in code which is reading/writing - * from user space. Such code must not hold kernel locks (since it - * can equally take a page fault), therefore it is safe to call - * force_sig_info even though that claims and releases locks. - * - * Code in ./signal.c ensures that the debug control register - * is restored before we deliver any signal, and therefore that - * user code runs with the correct debug control register even though - * we clear it here. - * - * Being careful here means that we don't have to be as careful in a - * lot of more complicated places (task switching can be a bit lazy - * about restoring all the debug state, and ptrace doesn't have to - * find every occurrence of the TF bit that could be saved away even - * by user code) - */ -fastcall void do_debug(struct pt_regs * regs, long error_code) -{ - unsigned int condition; - struct task_struct *tsk = current; - - condition = HYPERVISOR_get_debugreg(6); - - if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code, - SIGTRAP) == NOTIFY_STOP) - return; - /* It's safe to allow irq's after DR6 has been saved */ - if (regs->eflags & X86_EFLAGS_IF) - local_irq_enable(); - - /* Mask out spurious debug traps due to lazy DR7 setting */ - if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) { - if (!tsk->thread.debugreg[7]) - goto clear_dr7; - } - - if (regs->eflags & VM_MASK) - goto debug_vm86; - - /* Save debug status register where ptrace can see it */ - tsk->thread.debugreg[6] = condition; - - /* - * Single-stepping through TF: make sure we ignore any events in - * kernel space (but re-enable TF when returning to user mode). - */ - if (condition & DR_STEP) { - /* - * We already checked v86 mode above, so we can - * check for kernel mode by just checking the CPL - * of CS. - */ - if ((regs->xcs & 2) == 0) - goto clear_TF_reenable; - } - - /* Ok, finally something we can handle */ - send_sigtrap(tsk, regs, error_code); - - /* Disable additional traps. They'll be re-enabled when - * the signal is delivered. - */ -clear_dr7: - HYPERVISOR_set_debugreg(7, 0); - return; - -debug_vm86: - handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1); - return; - -clear_TF_reenable: - set_tsk_thread_flag(tsk, TIF_SINGLESTEP); - regs->eflags &= ~TF_MASK; - return; -} - -/* - * Note that we play around with the 'TS' bit in an attempt to get - * the correct behaviour even in the presence of the asynchronous - * IRQ13 behaviour - */ -void math_error(void __user *eip) -{ - struct task_struct * task; - siginfo_t info; - unsigned short cwd, swd; - - /* - * Save the info for the exception handler and clear the error. - */ - task = current; - save_init_fpu(task); - task->thread.trap_no = 16; - task->thread.error_code = 0; - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_code = __SI_FAULT; - info.si_addr = eip; - /* - * (~cwd & swd) will mask out exceptions that are not set to unmasked - * status. 0x3f is the exception bits in these regs, 0x200 is the - * C1 reg you need in case of a stack fault, 0x040 is the stack - * fault bit. We should only be taking one exception at a time, - * so if this combination doesn't produce any single exception, - * then we have a bad program that isn't syncronizing its FPU usage - * and it will suffer the consequences since we won't be able to - * fully reproduce the context of the exception - */ - cwd = get_fpu_cwd(task); - swd = get_fpu_swd(task); - switch (((~cwd) & swd & 0x3f) | (swd & 0x240)) { - case 0x000: - default: - break; - case 0x001: /* Invalid Op */ - case 0x041: /* Stack Fault */ - case 0x241: /* Stack Fault | Direction */ - info.si_code = FPE_FLTINV; - /* Should we clear the SF or let user space do it ???? */ - break; - case 0x002: /* Denormalize */ - case 0x010: /* Underflow */ - info.si_code = FPE_FLTUND; - break; - case 0x004: /* Zero Divide */ - info.si_code = FPE_FLTDIV; - break; - case 0x008: /* Overflow */ - info.si_code = FPE_FLTOVF; - break; - case 0x020: /* Precision */ - info.si_code = FPE_FLTRES; - break; - } - force_sig_info(SIGFPE, &info, task); -} - -fastcall void do_coprocessor_error(struct pt_regs * regs, long error_code) -{ - ignore_fpu_irq = 1; - math_error((void __user *)regs->eip); -} - -static void simd_math_error(void __user *eip) -{ - struct task_struct * task; - siginfo_t info; - unsigned short mxcsr; - - /* - * Save the info for the exception handler and clear the error. - */ - task = current; - save_init_fpu(task); - task->thread.trap_no = 19; - task->thread.error_code = 0; - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_code = __SI_FAULT; - info.si_addr = eip; - /* - * The SIMD FPU exceptions are handled a little differently, as there - * is only a single status/control register. Thus, to determine which - * unmasked exception was caught we must mask the exception mask bits - * at 0x1f80, and then use these to mask the exception bits at 0x3f. - */ - mxcsr = get_fpu_mxcsr(task); - switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) { - case 0x000: - default: - break; - case 0x001: /* Invalid Op */ - info.si_code = FPE_FLTINV; - break; - case 0x002: /* Denormalize */ - case 0x010: /* Underflow */ - info.si_code = FPE_FLTUND; - break; - case 0x004: /* Zero Divide */ - info.si_code = FPE_FLTDIV; - break; - case 0x008: /* Overflow */ - info.si_code = FPE_FLTOVF; - break; - case 0x020: /* Precision */ - info.si_code = FPE_FLTRES; - break; - } - force_sig_info(SIGFPE, &info, task); -} - -fastcall void do_simd_coprocessor_error(struct pt_regs * regs, - long error_code) -{ - if (cpu_has_xmm) { - /* Handle SIMD FPU exceptions on PIII+ processors. */ - ignore_fpu_irq = 1; - simd_math_error((void __user *)regs->eip); - } else { - /* - * Handle strange cache flush from user space exception - * in all other cases. This is undocumented behaviour. - */ - if (regs->eflags & VM_MASK) { - handle_vm86_fault((struct kernel_vm86_regs *)regs, - error_code); - return; - } - die_if_kernel("cache flush denied", regs, error_code); - current->thread.trap_no = 19; - current->thread.error_code = error_code; - force_sig(SIGSEGV, current); - } -} - -#ifndef CONFIG_XEN -fastcall void setup_x86_bogus_stack(unsigned char * stk) -{ - unsigned long *switch16_ptr, *switch32_ptr; - struct pt_regs *regs; - unsigned long stack_top, stack_bot; - unsigned short iret_frame16_off; - int cpu = smp_processor_id(); - /* reserve the space on 32bit stack for the magic switch16 pointer */ - memmove(stk, stk + 8, sizeof(struct pt_regs)); - switch16_ptr = (unsigned long *)(stk + sizeof(struct pt_regs)); - regs = (struct pt_regs *)stk; - /* now the switch32 on 16bit stack */ - stack_bot = (unsigned long)&per_cpu(cpu_16bit_stack, cpu); - stack_top = stack_bot + CPU_16BIT_STACK_SIZE; - switch32_ptr = (unsigned long *)(stack_top - 8); - iret_frame16_off = CPU_16BIT_STACK_SIZE - 8 - 20; - /* copy iret frame on 16bit stack */ - memcpy((void *)(stack_bot + iret_frame16_off), &regs->eip, 20); - /* fill in the switch pointers */ - switch16_ptr[0] = (regs->esp & 0xffff0000) | iret_frame16_off; - switch16_ptr[1] = __ESPFIX_SS; - switch32_ptr[0] = (unsigned long)stk + sizeof(struct pt_regs) + - 8 - CPU_16BIT_STACK_SIZE; - switch32_ptr[1] = __KERNEL_DS; -} - -fastcall unsigned char * fixup_x86_bogus_stack(unsigned short sp) -{ - unsigned long *switch32_ptr; - unsigned char *stack16, *stack32; - unsigned long stack_top, stack_bot; - int len; - int cpu = smp_processor_id(); - stack_bot = (unsigned long)&per_cpu(cpu_16bit_stack, cpu); - stack_top = stack_bot + CPU_16BIT_STACK_SIZE; - switch32_ptr = (unsigned long *)(stack_top - 8); - /* copy the data from 16bit stack to 32bit stack */ - len = CPU_16BIT_STACK_SIZE - 8 - sp; - stack16 = (unsigned char *)(stack_bot + sp); - stack32 = (unsigned char *) - (switch32_ptr[0] + CPU_16BIT_STACK_SIZE - 8 - len); - memcpy(stack32, stack16, len); - return stack32; -} -#endif - -/* - * 'math_state_restore()' saves the current math information in the - * old math state array, and gets the new ones from the current task - * - * Careful.. There are problems with IBM-designed IRQ13 behaviour. - * Don't touch unless you *really* know how it works. - * - * Must be called with kernel preemption disabled (in this case, - * local interrupts are disabled at the call-site in entry.S). - */ -asmlinkage void math_state_restore(struct pt_regs regs) -{ - struct thread_info *thread = current_thread_info(); - struct task_struct *tsk = thread->task; - - /* NB. 'clts' is done for us by Xen during virtual trap. */ - if (!tsk_used_math(tsk)) - init_fpu(tsk); - restore_fpu(tsk); - thread->status |= TS_USEDFPU; /* So we fnsave on switch_to() */ -} - -#ifndef CONFIG_MATH_EMULATION - -asmlinkage void math_emulate(long arg) -{ - printk("math-emulation not enabled and no coprocessor found.\n"); - printk("killing %s.\n",current->comm); - force_sig(SIGFPE,current); - schedule(); -} - -#endif /* CONFIG_MATH_EMULATION */ - -#ifdef CONFIG_X86_F00F_BUG -void __init trap_init_f00f_bug(void) -{ - __set_fixmap(FIX_F00F_IDT, __pa(&idt_table), PAGE_KERNEL_RO); - - /* - * Update the IDT descriptor and reload the IDT so that - * it uses the read-only mapped virtual address. - */ - idt_descr.address = fix_to_virt(FIX_F00F_IDT); - __asm__ __volatile__("lidt %0" : : "m" (idt_descr)); -} -#endif - - -/* - * NB. All these are "trap gates" (i.e. events_mask isn't set) except - * for those that specify <dpl>|4 in the second field. - */ -static trap_info_t trap_table[] = { - { 0, 0, __KERNEL_CS, (unsigned long)divide_error }, - { 1, 0|4, __KERNEL_CS, (unsigned long)debug }, - { 3, 3|4, __KERNEL_CS, (unsigned long)int3 }, - { 4, 3, __KERNEL_CS, (unsigned long)overflow }, - { 5, 3, __KERNEL_CS, (unsigned long)bounds }, - { 6, 0, __KERNEL_CS, (unsigned long)invalid_op }, - { 7, 0|4, __KERNEL_CS, (unsigned long)device_not_available }, - { 9, 0, __KERNEL_CS, (unsigned long)coprocessor_segment_overrun }, - { 10, 0, __KERNEL_CS, (unsigned long)invalid_TSS }, - { 11, 0, __KERNEL_CS, (unsigned long)segment_not_present }, - { 12, 0, __KERNEL_CS, (unsigned long)stack_segment }, - { 13, 0, __KERNEL_CS, (unsigned long)general_protection }, - { 14, 0|4, __KERNEL_CS, (unsigned long)page_fault }, - { 15, 0, __KERNEL_CS, (unsigned long)fixup_4gb_segment }, - { 16, 0, __KERNEL_CS, (unsigned long)coprocessor_error }, - { 17, 0, __KERNEL_CS, (unsigned long)alignment_check }, -#ifdef CONFIG_X86_MCE - { 18, 0, __KERNEL_CS, (unsigned long)machine_check }, -#endif - { 19, 0, __KERNEL_CS, (unsigned long)simd_coprocessor_error }, - { SYSCALL_VECTOR, 3, __KERNEL_CS, (unsigned long)system_call }, - { 0, 0, 0, 0 } -}; - -void __init trap_init(void) -{ - HYPERVISOR_set_trap_table(trap_table); - - /* - * default LDT is a single-entry callgate to lcall7 for iBCS - * and a callgate to lcall27 for Solaris/x86 binaries - */ - make_lowmem_page_readonly( - &default_ldt[0], XENFEAT_writable_descriptor_tables); - - /* - * Should be a barrier for any external CPU state. - */ - cpu_init(); -} - -void smp_trap_init(trap_info_t *trap_ctxt) -{ - trap_info_t *t = trap_table; - int i; - - for (i = 0; i < 256; i++) { - trap_ctxt[i].vector = i; - trap_ctxt[i].cs = FLAT_KERNEL_CS; - } - - for (t = trap_table; t->address; t++) { - trap_ctxt[t->vector].flags = t->flags; - trap_ctxt[t->vector].cs = t->cs; - trap_ctxt[t->vector].address = t->address; - } -} - -static int __init kstack_setup(char *s) -{ - kstack_depth_to_print = simple_strtoul(s, NULL, 0); - return 0; -} -__setup("kstack=", kstack_setup); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/vsyscall-note.S --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/vsyscall-note.S Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,32 +0,0 @@ -/* - * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. - * Here we can supply some information useful to userland. - * First we get the vanilla i386 note that supplies the kernel version info. - */ - -#include "../../../i386/kernel/vsyscall-note.S" - -/* - * Now we add a special note telling glibc's dynamic linker a fake hardware - * flavor that it will use to choose the search path for libraries in the - * same way it uses real hardware capabilities like "mmx". - * We supply "nosegneg" as the fake capability, to indicate that we - * do not like negative offsets in instructions using segment overrides, - * since we implement those inefficiently. This makes it possible to - * install libraries optimized to avoid those access patterns in someplace - * like /lib/i686/tls/nosegneg. Note that an /etc/ld.so.conf.d/file - * corresponding to the bits here is needed to make ldconfig work right. - * It should contain: - * hwcap 0 nosegneg - * to match the mapping of bit to name that we give here. - */ -#define NOTE_KERNELCAP_BEGIN(ncaps, mask) \ - ASM_ELF_NOTE_BEGIN(".note.kernelcap", "a", "GNU", 2) \ - .long ncaps, mask -#define NOTE_KERNELCAP(bit, name) \ - .byte bit; .asciz name -#define NOTE_KERNELCAP_END ASM_ELF_NOTE_END - -NOTE_KERNELCAP_BEGIN(1, 1) -NOTE_KERNELCAP(1, "nosegneg") /* Change 1 back to 0 when glibc is fixed! */ -NOTE_KERNELCAP_END diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/kernel/vsyscall.S --- a/linux-2.6-xen-sparse/arch/xen/i386/kernel/vsyscall.S Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,15 +0,0 @@ -#include <linux/init.h> - -__INITDATA - - .globl vsyscall_int80_start, vsyscall_int80_end -vsyscall_int80_start: - .incbin "arch/xen/i386/kernel/vsyscall-int80.so" -vsyscall_int80_end: - - .globl vsyscall_sysenter_start, vsyscall_sysenter_end -vsyscall_sysenter_start: - .incbin "arch/xen/i386/kernel/vsyscall-sysenter.so" -vsyscall_sysenter_end: - -__FINIT diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/mach-default/Makefile --- a/linux-2.6-xen-sparse/arch/xen/i386/mach-default/Makefile Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,12 +0,0 @@ -# -# Makefile for the linux kernel. -# - -c-obj-y := topology.o - -$(patsubst %.o,$(obj)/%.c,$(c-obj-y)): - @ln -fsn $(srctree)/arch/i386/mach-default/$(notdir $@) $@ - -obj-y += $(c-obj-y) - -clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-)) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/mm/Makefile --- a/linux-2.6-xen-sparse/arch/xen/i386/mm/Makefile Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,24 +0,0 @@ -# -# Makefile for the linux i386-specific parts of the memory manager. -# - -XENARCH := $(subst ",,$(CONFIG_XENARCH)) - -CFLAGS += -Iarch/$(XENARCH)/mm - -obj-y := init.o pgtable.o fault.o ioremap.o hypervisor.o -c-obj-y := extable.o mmap.o pageattr.o - -c-obj-$(CONFIG_DISCONTIGMEM) += discontig.o -c-obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_HIGHMEM) += highmem.o -c-obj-$(CONFIG_BOOT_IOREMAP) += boot_ioremap.o - -c-link := - -$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)): - @ln -fsn $(srctree)/arch/i386/mm/$(notdir $@) $@ - -obj-y += $(c-obj-y) - -clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link)) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/mm/fault.c --- a/linux-2.6-xen-sparse/arch/xen/i386/mm/fault.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,620 +0,0 @@ -/* - * linux/arch/i386/mm/fault.c - * - * Copyright (C) 1995 Linus Torvalds - */ - -#include <linux/signal.h> -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/string.h> -#include <linux/types.h> -#include <linux/ptrace.h> -#include <linux/mman.h> -#include <linux/mm.h> -#include <linux/smp.h> -#include <linux/smp_lock.h> -#include <linux/interrupt.h> -#include <linux/init.h> -#include <linux/tty.h> -#include <linux/vt_kern.h> /* For unblank_screen() */ -#include <linux/highmem.h> -#include <linux/module.h> -#include <linux/percpu.h> - -#include <asm/system.h> -#include <asm/uaccess.h> -#include <asm/desc.h> -#include <asm/kdebug.h> - -extern void die(const char *,struct pt_regs *,long); - -DEFINE_PER_CPU(pgd_t *, cur_pgd); - -/* - * Unlock any spinlocks which will prevent us from getting the - * message out - */ -void bust_spinlocks(int yes) -{ - int loglevel_save = console_loglevel; - - if (yes) { - oops_in_progress = 1; - return; - } -#ifdef CONFIG_VT - unblank_screen(); -#endif - oops_in_progress = 0; - /* - * OK, the message is on the console. Now we call printk() - * without oops_in_progress set so that printk will give klogd - * a poke. Hold onto your hats... - */ - console_loglevel = 15; /* NMI oopser may have shut the console up */ - printk(" "); - console_loglevel = loglevel_save; -} - -/* - * Return EIP plus the CS segment base. The segment limit is also - * adjusted, clamped to the kernel/user address space (whichever is - * appropriate), and returned in *eip_limit. - * - * The segment is checked, because it might have been changed by another - * task between the original faulting instruction and here. - * - * If CS is no longer a valid code segment, or if EIP is beyond the - * limit, or if it is a kernel address when CS is not a kernel segment, - * then the returned value will be greater than *eip_limit. - * - * This is slow, but is very rarely executed. - */ -static inline unsigned long get_segment_eip(struct pt_regs *regs, - unsigned long *eip_limit) -{ - unsigned long eip = regs->eip; - unsigned seg = regs->xcs & 0xffff; - u32 seg_ar, seg_limit, base, *desc; - - /* The standard kernel/user address space limit. */ - *eip_limit = (seg & 2) ? USER_DS.seg : KERNEL_DS.seg; - - /* Unlikely, but must come before segment checks. */ - if (unlikely((regs->eflags & VM_MASK) != 0)) - return eip + (seg << 4); - - /* By far the most common cases. */ - if (likely(seg == __USER_CS || seg == __KERNEL_CS)) - return eip; - - /* Check the segment exists, is within the current LDT/GDT size, - that kernel/user (ring 0..3) has the appropriate privilege, - that it's a code segment, and get the limit. */ - __asm__ ("larl %3,%0; lsll %3,%1" - : "=&r" (seg_ar), "=r" (seg_limit) : "0" (0), "rm" (seg)); - if ((~seg_ar & 0x9800) || eip > seg_limit) { - *eip_limit = 0; - return 1; /* So that returned eip > *eip_limit. */ - } - - /* Get the GDT/LDT descriptor base. - When you look for races in this code remember that - LDT and other horrors are only used in user space. */ - if (seg & (1<<2)) { - /* Must lock the LDT while reading it. */ - down(&current->mm->context.sem); - desc = current->mm->context.ldt; - desc = (void *)desc + (seg & ~7); - } else { - /* Must disable preemption while reading the GDT. */ - desc = (u32 *)get_cpu_gdt_table(get_cpu()); - desc = (void *)desc + (seg & ~7); - } - - /* Decode the code segment base from the descriptor */ - base = get_desc_base((unsigned long *)desc); - - if (seg & (1<<2)) { - up(&current->mm->context.sem); - } else - put_cpu(); - - /* Adjust EIP and segment limit, and clamp at the kernel limit. - It's legitimate for segments to wrap at 0xffffffff. */ - seg_limit += base; - if (seg_limit < *eip_limit && seg_limit >= base) - *eip_limit = seg_limit; - return eip + base; -} - -/* - * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch. - * Check that here and ignore it. - */ -static int __is_prefetch(struct pt_regs *regs, unsigned long addr) -{ - unsigned long limit; - unsigned long instr = get_segment_eip (regs, &limit); - int scan_more = 1; - int prefetch = 0; - int i; - - for (i = 0; scan_more && i < 15; i++) { - unsigned char opcode; - unsigned char instr_hi; - unsigned char instr_lo; - - if (instr > limit) - break; - if (__get_user(opcode, (unsigned char *) instr)) - break; - - instr_hi = opcode & 0xf0; - instr_lo = opcode & 0x0f; - instr++; - - switch (instr_hi) { - case 0x20: - case 0x30: - /* Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes. */ - scan_more = ((instr_lo & 7) == 0x6); - break; - - case 0x60: - /* 0x64 thru 0x67 are valid prefixes in all modes. */ - scan_more = (instr_lo & 0xC) == 0x4; - break; - case 0xF0: - /* 0xF0, 0xF2, and 0xF3 are valid prefixes */ - scan_more = !instr_lo || (instr_lo>>1) == 1; - break; - case 0x00: - /* Prefetch instruction is 0x0F0D or 0x0F18 */ - scan_more = 0; - if (instr > limit) - break; - if (__get_user(opcode, (unsigned char *) instr)) - break; - prefetch = (instr_lo == 0xF) && - (opcode == 0x0D || opcode == 0x18); - break; - default: - scan_more = 0; - break; - } - } - return prefetch; -} - -static inline int is_prefetch(struct pt_regs *regs, unsigned long addr, - unsigned long error_code) -{ - if (unlikely(boot_cpu_data.x86_vendor == X86_VENDOR_AMD && - boot_cpu_data.x86 >= 6)) { - /* Catch an obscure case of prefetch inside an NX page. */ - if (nx_enabled && (error_code & 16)) - return 0; - return __is_prefetch(regs, addr); - } - return 0; -} - -fastcall void do_invalid_op(struct pt_regs *, unsigned long); - -#ifdef CONFIG_X86_PAE -static void dump_fault_path(unsigned long address) -{ - unsigned long *p, page; - unsigned long mfn; - - preempt_disable(); - page = __pa(per_cpu(cur_pgd, smp_processor_id())); - preempt_enable(); - - p = (unsigned long *)__va(page); - p += (address >> 30) * 2; - printk(KERN_ALERT "%08lx -> *pde = %08lx:%08lx\n", page, p[1], p[0]); - if (p[0] & 1) { - mfn = (p[0] >> PAGE_SHIFT) | ((p[1] & 0x7) << 20); - page = mfn_to_pfn(mfn) << PAGE_SHIFT; - p = (unsigned long *)__va(page); - address &= 0x3fffffff; - p += (address >> 21) * 2; - printk(KERN_ALERT "%08lx -> *pme = %08lx:%08lx\n", - page, p[1], p[0]); -#ifndef CONFIG_HIGHPTE - if (p[0] & 1) { - mfn = (p[0] >> PAGE_SHIFT) | ((p[1] & 0x7) << 20); - page = mfn_to_pfn(mfn) << PAGE_SHIFT; - p = (unsigned long *) __va(page); - address &= 0x001fffff; - p += (address >> 12) * 2; - printk(KERN_ALERT "%08lx -> *pte = %08lx:%08lx\n", - page, p[1], p[0]); - } -#endif - } -} -#else -static void dump_fault_path(unsigned long address) -{ - unsigned long page; - - preempt_disable(); - page = ((unsigned long *) per_cpu(cur_pgd, smp_processor_id())) - [address >> 22]; - preempt_enable(); - - page = ((unsigned long *) per_cpu(cur_pgd, get_cpu())) - [address >> 22]; - printk(KERN_ALERT "*pde = ma %08lx pa %08lx\n", page, - machine_to_phys(page)); - /* - * We must not directly access the pte in the highpte - * case, the page table might be allocated in highmem. - * And lets rather not kmap-atomic the pte, just in case - * it's allocated already. - */ -#ifndef CONFIG_HIGHPTE - if (page & 1) { - page &= PAGE_MASK; - address &= 0x003ff000; - page = machine_to_phys(page); - page = ((unsigned long *) __va(page))[address >> PAGE_SHIFT]; - printk(KERN_ALERT "*pte = ma %08lx pa %08lx\n", page, - machine_to_phys(page)); - } -#endif -} -#endif - - -/* - * This routine handles page faults. It determines the address, - * and the problem, and then passes it off to one of the appropriate - * routines. - * - * error_code: - * bit 0 == 0 means no page found, 1 means protection fault - * bit 1 == 0 means read, 1 means write - * bit 2 == 0 means kernel, 1 means user-mode - */ -fastcall void do_page_fault(struct pt_regs *regs, unsigned long error_code) -{ - struct task_struct *tsk; - struct mm_struct *mm; - struct vm_area_struct * vma; - unsigned long address; - int write; - siginfo_t info; - - address = HYPERVISOR_shared_info->vcpu_info[ - smp_processor_id()].arch.cr2; - - /* Set the "privileged fault" bit to something sane. */ - error_code &= ~4; - error_code |= (regs->xcs & 2) << 1; - if (regs->eflags & X86_EFLAGS_VM) - error_code |= 4; - - if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14, - SIGSEGV) == NOTIFY_STOP) - return; - /* It's safe to allow irq's after cr2 has been saved */ - if (regs->eflags & (X86_EFLAGS_IF|VM_MASK)) - local_irq_enable(); - - tsk = current; - - info.si_code = SEGV_MAPERR; - - /* - * We fault-in kernel-space virtual memory on-demand. The - * 'reference' page table is init_mm.pgd. - * - * NOTE! We MUST NOT take any locks for this case. We may - * be in an interrupt or a critical region, and should - * only copy the information from the master page table, - * nothing more. - * - * This verifies that the fault happens in kernel space - * (error_code & 4) == 0, and that the fault was not a - * protection error (error_code & 1) == 0. - */ - if (unlikely(address >= TASK_SIZE)) { - if (!(error_code & 5)) - goto vmalloc_fault; - /* - * Don't take the mm semaphore here. If we fixup a prefetch - * fault we could otherwise deadlock. - */ - goto bad_area_nosemaphore; - } - - mm = tsk->mm; - - /* - * If we're in an interrupt, have no user context or are running in an - * atomic region then we must not take the fault.. - */ - if (in_atomic() || !mm) - goto bad_area_nosemaphore; - - /* When running in the kernel we expect faults to occur only to - * addresses in user space. All other faults represent errors in the - * kernel and should generate an OOPS. Unfortunatly, in the case of an - * erroneous fault occuring in a code path which already holds mmap_sem - * we will deadlock attempting to validate the fault against the - * address space. Luckily the kernel only validly references user - * space from well defined areas of code, which are listed in the - * exceptions table. - * - * As the vast majority of faults will be valid we will only perform - * the source reference check when there is a possibilty of a deadlock. - * Attempt to lock the address space, if we cannot we then validate the - * source. If this is invalid we can skip the address space check, - * thus avoiding the deadlock. - */ - if (!down_read_trylock(&mm->mmap_sem)) { - if ((error_code & 4) == 0 && - !search_exception_tables(regs->eip)) - goto bad_area_nosemaphore; - down_read(&mm->mmap_sem); - } - - vma = find_vma(mm, address); - if (!vma) - goto bad_area; - if (vma->vm_start <= address) - goto good_area; - if (!(vma->vm_flags & VM_GROWSDOWN)) - goto bad_area; - if (error_code & 4) { - /* - * accessing the stack below %esp is always a bug. - * The "+ 32" is there due to some instructions (like - * pusha) doing post-decrement on the stack and that - * doesn't show up until later.. - */ - if (address + 32 < regs->esp) - goto bad_area; - } - if (expand_stack(vma, address)) - goto bad_area; -/* - * Ok, we have a good vm_area for this memory access, so - * we can handle it.. - */ -good_area: - info.si_code = SEGV_ACCERR; - write = 0; - switch (error_code & 3) { - default: /* 3: write, present */ -#ifdef TEST_VERIFY_AREA - if (regs->cs == KERNEL_CS) - printk("WP fault at %08lx\n", regs->eip); -#endif - /* fall through */ - case 2: /* write, not present */ - if (!(vma->vm_flags & VM_WRITE)) - goto bad_area; - write++; - break; - case 1: /* read, present */ - goto bad_area; - case 0: /* read, not present */ - if (!(vma->vm_flags & (VM_READ | VM_EXEC))) - goto bad_area; - } - - survive: - /* - * If for any reason at all we couldn't handle the fault, - * make sure we exit gracefully rather than endlessly redo - * the fault. - */ - switch (handle_mm_fault(mm, vma, address, write)) { - case VM_FAULT_MINOR: - tsk->min_flt++; - break; - case VM_FAULT_MAJOR: - tsk->maj_flt++; - break; - case VM_FAULT_SIGBUS: - goto do_sigbus; - case VM_FAULT_OOM: - goto out_of_memory; - default: - BUG(); - } - - /* - * Did it hit the DOS screen memory VA from vm86 mode? - */ - if (regs->eflags & VM_MASK) { - unsigned long bit = (address - 0xA0000) >> PAGE_SHIFT; - if (bit < 32) - tsk->thread.screen_bitmap |= 1 << bit; - } - up_read(&mm->mmap_sem); - return; - -/* - * Something tried to access memory that isn't in our memory map.. - * Fix it, but check if it's kernel or user first.. - */ -bad_area: - up_read(&mm->mmap_sem); - -bad_area_nosemaphore: - /* User mode accesses just cause a SIGSEGV */ - if (error_code & 4) { - /* - * Valid to do another page fault here because this one came - * from user space. - */ - if (is_prefetch(regs, address, error_code)) - return; - - tsk->thread.cr2 = address; - /* Kernel addresses are always protection faults */ - tsk->thread.error_code = error_code | (address >= TASK_SIZE); - tsk->thread.trap_no = 14; - info.si_signo = SIGSEGV; - info.si_errno = 0; - /* info.si_code has been set above */ - info.si_addr = (void __user *)address; - force_sig_info(SIGSEGV, &info, tsk); - return; - } - -#ifdef CONFIG_X86_F00F_BUG - /* - * Pentium F0 0F C7 C8 bug workaround. - */ - if (boot_cpu_data.f00f_bug) { - unsigned long nr; - - nr = (address - idt_descr.address) >> 3; - - if (nr == 6) { - do_invalid_op(regs, 0); - return; - } - } -#endif - -no_context: - /* Are we prepared to handle this kernel fault? */ - if (fixup_exception(regs)) - return; - - /* - * Valid to do another page fault here, because if this fault - * had been triggered by is_prefetch fixup_exception would have - * handled it. - */ - if (is_prefetch(regs, address, error_code)) - return; - -/* - * Oops. The kernel tried to access some bad page. We'll have to - * terminate things with extreme prejudice. - */ - - bust_spinlocks(1); - -#ifdef CONFIG_X86_PAE - if (error_code & 16) { - pte_t *pte = lookup_address(address); - - if (pte && pte_present(*pte) && !pte_exec_kernel(*pte)) - printk(KERN_CRIT "kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n", current->uid); - } -#endif - if (address < PAGE_SIZE) - printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference"); - else - printk(KERN_ALERT "Unable to handle kernel paging request"); - printk(" at virtual address %08lx\n",address); - printk(KERN_ALERT " printing eip:\n"); - printk("%08lx\n", regs->eip); - dump_fault_path(address); - die("Oops", regs, error_code); - bust_spinlocks(0); - do_exit(SIGKILL); - -/* - * We ran out of memory, or some other thing happened to us that made - * us unable to handle the page fault gracefully. - */ -out_of_memory: - up_read(&mm->mmap_sem); - if (tsk->pid == 1) { - yield(); - down_read(&mm->mmap_sem); - goto survive; - } - printk("VM: killing process %s\n", tsk->comm); - if (error_code & 4) - do_exit(SIGKILL); - goto no_context; - -do_sigbus: - up_read(&mm->mmap_sem); - - /* Kernel mode? Handle exceptions or die */ - if (!(error_code & 4)) - goto no_context; - - /* User space => ok to do another page fault */ - if (is_prefetch(regs, address, error_code)) - return; - - tsk->thread.cr2 = address; - tsk->thread.error_code = error_code; - tsk->thread.trap_no = 14; - info.si_signo = SIGBUS; - info.si_errno = 0; - info.si_code = BUS_ADRERR; - info.si_addr = (void __user *)address; - force_sig_info(SIGBUS, &info, tsk); - return; - -vmalloc_fault: - { - /* - * Synchronize this task's top level page-table - * with the 'reference' page table. - * - * Do _not_ use "tsk" here. We might be inside - * an interrupt in the middle of a task switch.. - */ - int index = pgd_index(address); - pgd_t *pgd, *pgd_k; - pud_t *pud, *pud_k; - pmd_t *pmd, *pmd_k; - pte_t *pte_k; - - preempt_disable(); - pgd = index + per_cpu(cur_pgd, smp_processor_id()); - preempt_enable(); - pgd_k = init_mm.pgd + index; - - if (!pgd_present(*pgd_k)) - goto no_context; - - /* - * set_pgd(pgd, *pgd_k); here would be useless on PAE - * and redundant with the set_pmd() on non-PAE. As would - * set_pud. - */ - - pud = pud_offset(pgd, address); - pud_k = pud_offset(pgd_k, address); - if (!pud_present(*pud_k)) - goto no_context; - - pmd = pmd_offset(pud, address); - pmd_k = pmd_offset(pud_k, address); - if (!pmd_present(*pmd_k)) - goto no_context; -#ifndef CONFIG_XEN - set_pmd(pmd, *pmd_k); -#else - /* - * When running on Xen we must launder *pmd_k through - * pmd_val() to ensure that _PAGE_PRESENT is correctly set. - */ - set_pmd(pmd, __pmd(pmd_val(*pmd_k))); -#endif - - pte_k = pte_offset_kernel(pmd_k, address); - if (!pte_present(*pte_k)) - goto no_context; - return; - } -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/mm/highmem.c --- a/linux-2.6-xen-sparse/arch/xen/i386/mm/highmem.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,99 +0,0 @@ -#include <linux/highmem.h> - -void *kmap(struct page *page) -{ - might_sleep(); - if (!PageHighMem(page)) - return page_address(page); - return kmap_high(page); -} - -void kunmap(struct page *page) -{ - if (in_interrupt()) - BUG(); - if (!PageHighMem(page)) - return; - kunmap_high(page); -} - -/* - * kmap_atomic/kunmap_atomic is significantly faster than kmap/kunmap because - * no global lock is needed and because the kmap code must perform a global TLB - * invalidation when the kmap pool wraps. - * - * However when holding an atomic kmap is is not legal to sleep, so atomic - * kmaps are appropriate for short, tight code paths only. - */ -static void *__kmap_atomic(struct page *page, enum km_type type, pgprot_t prot) -{ - enum fixed_addresses idx; - unsigned long vaddr; - - /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */ - inc_preempt_count(); - if (!PageHighMem(page)) - return page_address(page); - - idx = type + KM_TYPE_NR*smp_processor_id(); - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); -#ifdef CONFIG_DEBUG_HIGHMEM - if (!pte_none(*(kmap_pte-idx))) - BUG(); -#endif - set_pte_at_sync(&init_mm, vaddr, kmap_pte-idx, mk_pte(page, prot)); - - return (void*) vaddr; -} - -void *kmap_atomic(struct page *page, enum km_type type) -{ - return __kmap_atomic(page, type, kmap_prot); -} - -/* Same as kmap_atomic but with PAGE_KERNEL_RO page protection. */ -void *kmap_atomic_pte(struct page *page, enum km_type type) -{ - return __kmap_atomic(page, type, PAGE_KERNEL_RO); -} - -void kunmap_atomic(void *kvaddr, enum km_type type) -{ -#ifdef CONFIG_DEBUG_HIGHMEM - unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK; - enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id(); - - if (vaddr < FIXADDR_START) { // FIXME - dec_preempt_count(); - preempt_check_resched(); - return; - } - - if (vaddr != __fix_to_virt(FIX_KMAP_BEGIN+idx)) - BUG(); - - /* - * force other mappings to Oops if they'll try to access - * this pte without first remap it - */ - pte_clear(&init_mm, vaddr, kmap_pte-idx); - __flush_tlb_one(vaddr); -#endif - - dec_preempt_count(); - preempt_check_resched(); -} - -struct page *kmap_atomic_to_page(void *ptr) -{ - unsigned long idx, vaddr = (unsigned long)ptr; - pte_t *pte; - - if (vaddr < FIXADDR_START) - return virt_to_page(ptr); - - idx = virt_to_fix(vaddr); - pte = kmap_pte - (idx - FIX_KMAP_BEGIN); - return pte_page(*pte); -} - diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/mm/hypervisor.c --- a/linux-2.6-xen-sparse/arch/xen/i386/mm/hypervisor.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,459 +0,0 @@ -/****************************************************************************** - * mm/hypervisor.c - * - * Update page tables via the hypervisor. - * - * Copyright (c) 2002-2004, K A Fraser - * - * This file may be distributed separately from the Linux kernel, or - * incorporated into other software packages, subject to the following license: - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this source file (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, copy, modify, - * merge, publish, distribute, sublicense, and/or sell copies of the Software, - * and to permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - */ - -#include <linux/config.h> -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/vmalloc.h> -#include <asm/page.h> -#include <asm/pgtable.h> -#include <asm/hypervisor.h> -#include <asm-xen/balloon.h> -#include <asm-xen/xen-public/memory.h> -#include <linux/module.h> -#include <linux/percpu.h> -#include <asm/tlbflush.h> - -#ifdef CONFIG_X86_64 -#define pmd_val_ma(v) (v).pmd -#else -#ifdef CONFIG_X86_PAE -# define pmd_val_ma(v) ((v).pmd) -# define pud_val_ma(v) ((v).pgd.pgd) -#else -# define pmd_val_ma(v) ((v).pud.pgd.pgd) -#endif -#endif - -#ifndef CONFIG_XEN_SHADOW_MODE -void xen_l1_entry_update(pte_t *ptr, pte_t val) -{ - mmu_update_t u; - u.ptr = virt_to_machine(ptr); - u.val = pte_val_ma(val); - BUG_ON(HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF) < 0); -} - -void xen_l2_entry_update(pmd_t *ptr, pmd_t val) -{ - mmu_update_t u; - u.ptr = virt_to_machine(ptr); - u.val = pmd_val_ma(val); - BUG_ON(HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF) < 0); -} - -#ifdef CONFIG_X86_PAE -void xen_l3_entry_update(pud_t *ptr, pud_t val) -{ - mmu_update_t u; - u.ptr = virt_to_machine(ptr); - u.val = pud_val_ma(val); - BUG_ON(HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF) < 0); -} -#endif - -#ifdef CONFIG_X86_64 -void xen_l3_entry_update(pud_t *ptr, pud_t val) -{ - mmu_update_t u; - u.ptr = virt_to_machine(ptr); - u.val = val.pud; - BUG_ON(HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF) < 0); -} - -void xen_l4_entry_update(pgd_t *ptr, pgd_t val) -{ - mmu_update_t u; - u.ptr = virt_to_machine(ptr); - u.val = val.pgd; - BUG_ON(HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF) < 0); -} -#endif /* CONFIG_X86_64 */ -#endif /* CONFIG_XEN_SHADOW_MODE */ - -void xen_machphys_update(unsigned long mfn, unsigned long pfn) -{ - mmu_update_t u; - u.ptr = ((unsigned long long)mfn << PAGE_SHIFT) | MMU_MACHPHYS_UPDATE; - u.val = pfn; - BUG_ON(HYPERVISOR_mmu_update(&u, 1, NULL, DOMID_SELF) < 0); -} - -void xen_pt_switch(unsigned long ptr) -{ - struct mmuext_op op; - op.cmd = MMUEXT_NEW_BASEPTR; - op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); - BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); -} - -void xen_new_user_pt(unsigned long ptr) -{ - struct mmuext_op op; - op.cmd = MMUEXT_NEW_USER_BASEPTR; - op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); - BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); -} - -void xen_tlb_flush(void) -{ - struct mmuext_op op; - op.cmd = MMUEXT_TLB_FLUSH_LOCAL; - BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); -} - -void xen_invlpg(unsigned long ptr) -{ - struct mmuext_op op; - op.cmd = MMUEXT_INVLPG_LOCAL; - op.arg1.linear_addr = ptr & PAGE_MASK; - BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); -} - -#ifdef CONFIG_SMP - -void xen_tlb_flush_all(void) -{ - struct mmuext_op op; - op.cmd = MMUEXT_TLB_FLUSH_ALL; - BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); -} - -void xen_tlb_flush_mask(cpumask_t *mask) -{ - struct mmuext_op op; - if ( cpus_empty(*mask) ) - return; - op.cmd = MMUEXT_TLB_FLUSH_MULTI; - op.arg2.vcpumask = mask->bits; - BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); -} - -void xen_invlpg_all(unsigned long ptr) -{ - struct mmuext_op op; - op.cmd = MMUEXT_INVLPG_ALL; - op.arg1.linear_addr = ptr & PAGE_MASK; - BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); -} - -void xen_invlpg_mask(cpumask_t *mask, unsigned long ptr) -{ - struct mmuext_op op; - if ( cpus_empty(*mask) ) - return; - op.cmd = MMUEXT_INVLPG_MULTI; - op.arg1.linear_addr = ptr & PAGE_MASK; - op.arg2.vcpumask = mask->bits; - BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); -} - -#endif /* CONFIG_SMP */ - -#ifndef CONFIG_XEN_SHADOW_MODE -void xen_pgd_pin(unsigned long ptr) -{ - struct mmuext_op op; -#ifdef CONFIG_X86_64 - op.cmd = MMUEXT_PIN_L4_TABLE; -#elif defined(CONFIG_X86_PAE) - op.cmd = MMUEXT_PIN_L3_TABLE; -#else - op.cmd = MMUEXT_PIN_L2_TABLE; -#endif - op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); - BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); -} - -void xen_pgd_unpin(unsigned long ptr) -{ - struct mmuext_op op; - op.cmd = MMUEXT_UNPIN_TABLE; - op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); - BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); -} - -void xen_pte_pin(unsigned long ptr) -{ - struct mmuext_op op; - op.cmd = MMUEXT_PIN_L1_TABLE; - op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); - BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); -} - -void xen_pte_unpin(unsigned long ptr) -{ - struct mmuext_op op; - op.cmd = MMUEXT_UNPIN_TABLE; - op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); - BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); -} - -#ifdef CONFIG_X86_64 -void xen_pud_pin(unsigned long ptr) -{ - struct mmuext_op op; - op.cmd = MMUEXT_PIN_L3_TABLE; - op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); - BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); -} - -void xen_pud_unpin(unsigned long ptr) -{ - struct mmuext_op op; - op.cmd = MMUEXT_UNPIN_TABLE; - op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); - BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); -} - -void xen_pmd_pin(unsigned long ptr) -{ - struct mmuext_op op; - op.cmd = MMUEXT_PIN_L2_TABLE; - op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); - BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); -} - -void xen_pmd_unpin(unsigned long ptr) -{ - struct mmuext_op op; - op.cmd = MMUEXT_UNPIN_TABLE; - op.arg1.mfn = pfn_to_mfn(ptr >> PAGE_SHIFT); - BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); -} -#endif /* CONFIG_X86_64 */ -#endif /* CONFIG_XEN_SHADOW_MODE */ - -void xen_set_ldt(unsigned long ptr, unsigned long len) -{ - struct mmuext_op op; - op.cmd = MMUEXT_SET_LDT; - op.arg1.linear_addr = ptr; - op.arg2.nr_ents = len; - BUG_ON(HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF) < 0); -} - -/* - * Bitmap is indexed by page number. If bit is set, the page is part of a - * xen_create_contiguous_region() area of memory. - */ -unsigned long *contiguous_bitmap; - -static void contiguous_bitmap_set( - unsigned long first_page, unsigned long nr_pages) -{ - unsigned long start_off, end_off, curr_idx, end_idx; - - curr_idx = first_page / BITS_PER_LONG; - start_off = first_page & (BITS_PER_LONG-1); - end_idx = (first_page + nr_pages) / BITS_PER_LONG; - end_off = (first_page + nr_pages) & (BITS_PER_LONG-1); - - if (curr_idx == end_idx) { - contiguous_bitmap[curr_idx] |= - ((1UL<<end_off)-1) & -(1UL<<start_off); - } else { - contiguous_bitmap[curr_idx] |= -(1UL<<start_off); - while ( ++curr_idx < end_idx ) - contiguous_bitmap[curr_idx] = ~0UL; - contiguous_bitmap[curr_idx] |= (1UL<<end_off)-1; - } -} - -static void contiguous_bitmap_clear( - unsigned long first_page, unsigned long nr_pages) -{ - unsigned long start_off, end_off, curr_idx, end_idx; - - curr_idx = first_page / BITS_PER_LONG; - start_off = first_page & (BITS_PER_LONG-1); - end_idx = (first_page + nr_pages) / BITS_PER_LONG; - end_off = (first_page + nr_pages) & (BITS_PER_LONG-1); - - if (curr_idx == end_idx) { - contiguous_bitmap[curr_idx] &= - -(1UL<<end_off) | ((1UL<<start_off)-1); - } else { - contiguous_bitmap[curr_idx] &= (1UL<<start_off)-1; - while ( ++curr_idx != end_idx ) - contiguous_bitmap[curr_idx] = 0; - contiguous_bitmap[curr_idx] &= -(1UL<<end_off); - } -} - -/* Ensure multi-page extents are contiguous in machine memory. */ -int xen_create_contiguous_region( - unsigned long vstart, unsigned int order, unsigned int address_bits) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - unsigned long frame, i, flags; - struct xen_memory_reservation reservation = { - .extent_start = &frame, - .nr_extents = 1, - .extent_order = 0, - .domid = DOMID_SELF - }; - - scrub_pages(vstart, 1 << order); - - balloon_lock(flags); - - /* 1. Zap current PTEs, giving away the underlying pages. */ - for (i = 0; i < (1<<order); i++) { - pgd = pgd_offset_k(vstart + (i*PAGE_SIZE)); - pud = pud_offset(pgd, (vstart + (i*PAGE_SIZE))); - pmd = pmd_offset(pud, (vstart + (i*PAGE_SIZE))); - pte = pte_offset_kernel(pmd, (vstart + (i*PAGE_SIZE))); - frame = pte_mfn(*pte); - BUG_ON(HYPERVISOR_update_va_mapping( - vstart + (i*PAGE_SIZE), __pte_ma(0), 0)); - set_phys_to_machine((__pa(vstart)>>PAGE_SHIFT)+i, - INVALID_P2M_ENTRY); - BUG_ON(HYPERVISOR_memory_op( - XENMEM_decrease_reservation, &reservation) != 1); - } - - /* 2. Get a new contiguous memory extent. */ - reservation.extent_order = order; - reservation.address_bits = address_bits; - frame = __pa(vstart) >> PAGE_SHIFT; - if (HYPERVISOR_memory_op(XENMEM_populate_physmap, - &reservation) != 1) - goto fail; - - /* 3. Map the new extent in place of old pages. */ - for (i = 0; i < (1<<order); i++) { - BUG_ON(HYPERVISOR_update_va_mapping( - vstart + (i*PAGE_SIZE), - pfn_pte_ma(frame+i, PAGE_KERNEL), 0)); - set_phys_to_machine((__pa(vstart)>>PAGE_SHIFT)+i, frame+i); - } - - flush_tlb_all(); - - contiguous_bitmap_set(__pa(vstart) >> PAGE_SHIFT, 1UL << order); - - balloon_unlock(flags); - - return 0; - - fail: - reservation.extent_order = 0; - reservation.address_bits = 0; - - for (i = 0; i < (1<<order); i++) { - frame = (__pa(vstart) >> PAGE_SHIFT) + i; - BUG_ON(HYPERVISOR_memory_op( - XENMEM_populate_physmap, &reservation) != 1); - BUG_ON(HYPERVISOR_update_va_mapping( - vstart + (i*PAGE_SIZE), - pfn_pte_ma(frame, PAGE_KERNEL), 0)); - set_phys_to_machine((__pa(vstart)>>PAGE_SHIFT)+i, frame); - } - - flush_tlb_all(); - - balloon_unlock(flags); - - return -ENOMEM; -} - -void xen_destroy_contiguous_region(unsigned long vstart, unsigned int order) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - unsigned long frame, i, flags; - struct xen_memory_reservation reservation = { - .extent_start = &frame, - .nr_extents = 1, - .extent_order = 0, - .domid = DOMID_SELF - }; - - scrub_pages(vstart, 1 << order); - - balloon_lock(flags); - - contiguous_bitmap_clear(__pa(vstart) >> PAGE_SHIFT, 1UL << order); - - /* 1. Zap current PTEs, giving away the underlying pages. */ - for (i = 0; i < (1<<order); i++) { - pgd = pgd_offset_k(vstart + (i*PAGE_SIZE)); - pud = pud_offset(pgd, (vstart + (i*PAGE_SIZE))); - pmd = pmd_offset(pud, (vstart + (i*PAGE_SIZE))); - pte = pte_offset_kernel(pmd, (vstart + (i*PAGE_SIZE))); - frame = pte_mfn(*pte); - BUG_ON(HYPERVISOR_update_va_mapping( - vstart + (i*PAGE_SIZE), __pte_ma(0), 0)); - set_phys_to_machine((__pa(vstart)>>PAGE_SHIFT)+i, - INVALID_P2M_ENTRY); - BUG_ON(HYPERVISOR_memory_op( - XENMEM_decrease_reservation, &reservation) != 1); - } - - /* 2. Map new pages in place of old pages. */ - for (i = 0; i < (1<<order); i++) { - frame = (__pa(vstart) >> PAGE_SHIFT) + i; - BUG_ON(HYPERVISOR_memory_op( - XENMEM_populate_physmap, &reservation) != 1); - BUG_ON(HYPERVISOR_update_va_mapping( - vstart + (i*PAGE_SIZE), - pfn_pte_ma(frame, PAGE_KERNEL), 0)); - set_phys_to_machine((__pa(vstart)>>PAGE_SHIFT)+i, frame); - } - - flush_tlb_all(); - - balloon_unlock(flags); -} - -#ifdef __i386__ -int write_ldt_entry(void *ldt, int entry, __u32 entry_a, __u32 entry_b) -{ - __u32 *lp = (__u32 *)((char *)ldt + entry * 8); - maddr_t mach_lp = arbitrary_virt_to_machine(lp); - return HYPERVISOR_update_descriptor( - mach_lp, (u64)entry_a | ((u64)entry_b<<32)); -} -#endif - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/mm/init.c --- a/linux-2.6-xen-sparse/arch/xen/i386/mm/init.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,780 +0,0 @@ -/* - * linux/arch/i386/mm/init.c - * - * Copyright (C) 1995 Linus Torvalds - * - * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 - */ - -#include <linux/config.h> -#include <linux/module.h> -#include <linux/signal.h> -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/string.h> -#include <linux/types.h> -#include <linux/ptrace.h> -#include <linux/mman.h> -#include <linux/mm.h> -#include <linux/hugetlb.h> -#include <linux/swap.h> -#include <linux/smp.h> -#include <linux/init.h> -#include <linux/highmem.h> -#include <linux/pagemap.h> -#include <linux/bootmem.h> -#include <linux/slab.h> -#include <linux/proc_fs.h> -#include <linux/efi.h> - -#include <asm/processor.h> -#include <asm/system.h> -#include <asm/uaccess.h> -#include <asm/pgtable.h> -#include <asm/dma.h> -#include <asm/fixmap.h> -#include <asm/e820.h> -#include <asm/apic.h> -#include <asm/tlb.h> -#include <asm/tlbflush.h> -#include <asm/sections.h> -#include <asm/hypervisor.h> - -extern unsigned long *contiguous_bitmap; - -#if defined(CONFIG_SWIOTLB) -extern void swiotlb_init(void); -int swiotlb; -EXPORT_SYMBOL(swiotlb); -#endif - -unsigned int __VMALLOC_RESERVE = 128 << 20; - -DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); -unsigned long highstart_pfn, highend_pfn; - -static int noinline do_test_wp_bit(void); - -/* - * Creates a middle page table and puts a pointer to it in the - * given global directory entry. This only returns the gd entry - * in non-PAE compilation mode, since the middle layer is folded. - */ -static pmd_t * __init one_md_table_init(pgd_t *pgd) -{ - pud_t *pud; - pmd_t *pmd_table; - -#ifdef CONFIG_X86_PAE - pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE); - make_lowmem_page_readonly(pmd_table, XENFEAT_writable_page_tables); - set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT)); - pud = pud_offset(pgd, 0); - if (pmd_table != pmd_offset(pud, 0)) - BUG(); -#else - pud = pud_offset(pgd, 0); - pmd_table = pmd_offset(pud, 0); -#endif - - return pmd_table; -} - -/* - * Create a page table and place a pointer to it in a middle page - * directory entry. - */ -static pte_t * __init one_page_table_init(pmd_t *pmd) -{ - if (pmd_none(*pmd)) { - pte_t *page_table = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE); - make_lowmem_page_readonly(page_table, - XENFEAT_writable_page_tables); - set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE)); - if (page_table != pte_offset_kernel(pmd, 0)) - BUG(); - - return page_table; - } - - return pte_offset_kernel(pmd, 0); -} - -/* - * This function initializes a certain range of kernel virtual memory - * with new bootmem page tables, everywhere page tables are missing in - * the given range. - */ - -/* - * NOTE: The pagetables are allocated contiguous on the physical space - * so we can cache the place of the first one and move around without - * checking the pgd every time. - */ -static void __init page_table_range_init (unsigned long start, unsigned long end, pgd_t *pgd_base) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - int pgd_idx, pmd_idx; - unsigned long vaddr; - - vaddr = start; - pgd_idx = pgd_index(vaddr); - pmd_idx = pmd_index(vaddr); - pgd = pgd_base + pgd_idx; - - for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd++, pgd_idx++) { - if (pgd_none(*pgd)) - one_md_table_init(pgd); - pud = pud_offset(pgd, vaddr); - pmd = pmd_offset(pud, vaddr); - for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end); pmd++, pmd_idx++) { - if (vaddr < HYPERVISOR_VIRT_START && pmd_none(*pmd)) - one_page_table_init(pmd); - - vaddr += PMD_SIZE; - } - pmd_idx = 0; - } -} - -static inline int is_kernel_text(unsigned long addr) -{ - if (addr >= PAGE_OFFSET && addr <= (unsigned long)__init_end) - return 1; - return 0; -} - -/* - * This maps the physical memory to kernel virtual address space, a total - * of max_low_pfn pages, by creating page tables starting from address - * PAGE_OFFSET. - */ -static void __init kernel_physical_mapping_init(pgd_t *pgd_base) -{ - unsigned long pfn; - pgd_t *pgd; - pmd_t *pmd; - pte_t *pte; - int pgd_idx, pmd_idx, pte_ofs; - - unsigned long max_ram_pfn = xen_start_info->nr_pages; - if (max_ram_pfn > max_low_pfn) - max_ram_pfn = max_low_pfn; - - pgd_idx = pgd_index(PAGE_OFFSET); - pgd = pgd_base + pgd_idx; - pfn = 0; - pmd_idx = pmd_index(PAGE_OFFSET); - pte_ofs = pte_index(PAGE_OFFSET); - - for (; pgd_idx < PTRS_PER_PGD; pgd++, pgd_idx++) { -#ifdef CONFIG_XEN - /* - * Native linux hasn't PAE-paging enabled yet at this - * point. When running as xen domain we are in PAE - * mode already, thus we can't simply hook a empty - * pmd. That would kill the mappings we are currently - * using ... - */ - pmd = pmd_offset(pud_offset(pgd, PAGE_OFFSET), PAGE_OFFSET); -#else - pmd = one_md_table_init(pgd); -#endif - if (pfn >= max_low_pfn) - continue; - pmd += pmd_idx; - for (; pmd_idx < PTRS_PER_PMD && pfn < max_low_pfn; pmd++, pmd_idx++) { - unsigned int address = pfn * PAGE_SIZE + PAGE_OFFSET; - if (address >= HYPERVISOR_VIRT_START) - continue; - - /* Map with big pages if possible, otherwise create normal page tables. */ - if (cpu_has_pse) { - unsigned int address2 = (pfn + PTRS_PER_PTE - 1) * PAGE_SIZE + PAGE_OFFSET + PAGE_SIZE-1; - - if (is_kernel_text(address) || is_kernel_text(address2)) - set_pmd(pmd, pfn_pmd(pfn, PAGE_KERNEL_LARGE_EXEC)); - else - set_pmd(pmd, pfn_pmd(pfn, PAGE_KERNEL_LARGE)); - pfn += PTRS_PER_PTE; - } else { - pte = one_page_table_init(pmd); - - pte += pte_ofs; - for (; pte_ofs < PTRS_PER_PTE && pfn < max_low_pfn; pte++, pfn++, pte_ofs++) { - /* XEN: Only map initial RAM allocation. */ - if ((pfn >= max_ram_pfn) || pte_present(*pte)) - continue; - if (is_kernel_text(address)) - set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC)); - else - set_pte(pte, pfn_pte(pfn, PAGE_KERNEL)); - } - pte_ofs = 0; - } - } - pmd_idx = 0; - } -} - -#ifndef CONFIG_XEN - -static inline int page_kills_ppro(unsigned long pagenr) -{ - if (pagenr >= 0x70000 && pagenr <= 0x7003F) - return 1; - return 0; -} - -extern int is_available_memory(efi_memory_desc_t *); - -static inline int page_is_ram(unsigned long pagenr) -{ - int i; - unsigned long addr, end; - - if (efi_enabled) { - efi_memory_desc_t *md; - - for (i = 0; i < memmap.nr_map; i++) { - md = &memmap.map[i]; - if (!is_available_memory(md)) - continue; - addr = (md->phys_addr+PAGE_SIZE-1) >> PAGE_SHIFT; - end = (md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT)) >> PAGE_SHIFT; - - if ((pagenr >= addr) && (pagenr < end)) - return 1; - } - return 0; - } - - for (i = 0; i < e820.nr_map; i++) { - - if (e820.map[i].type != E820_RAM) /* not usable memory */ - continue; - /* - * !!!FIXME!!! Some BIOSen report areas as RAM that - * are not. Notably the 640->1Mb area. We need a sanity - * check here. - */ - addr = (e820.map[i].addr+PAGE_SIZE-1) >> PAGE_SHIFT; - end = (e820.map[i].addr+e820.map[i].size) >> PAGE_SHIFT; - if ((pagenr >= addr) && (pagenr < end)) - return 1; - } - return 0; -} - -#else /* CONFIG_XEN */ - -#define page_kills_ppro(p) 0 -#define page_is_ram(p) 1 - -#endif - -#ifdef CONFIG_HIGHMEM -pte_t *kmap_pte; -pgprot_t kmap_prot; - -#define kmap_get_fixmap_pte(vaddr) \ - pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr), vaddr), (vaddr)), (vaddr)) - -static void __init kmap_init(void) -{ - unsigned long kmap_vstart; - - /* cache the first kmap pte */ - kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN); - kmap_pte = kmap_get_fixmap_pte(kmap_vstart); - - kmap_prot = PAGE_KERNEL; -} - -static void __init permanent_kmaps_init(pgd_t *pgd_base) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - unsigned long vaddr; - - vaddr = PKMAP_BASE; - page_table_range_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base); - - pgd = swapper_pg_dir + pgd_index(vaddr); - pud = pud_offset(pgd, vaddr); - pmd = pmd_offset(pud, vaddr); - pte = pte_offset_kernel(pmd, vaddr); - pkmap_page_table = pte; -} - -void __init one_highpage_init(struct page *page, int pfn, int bad_ppro) -{ - if (page_is_ram(pfn) && !(bad_ppro && page_kills_ppro(pfn))) { - ClearPageReserved(page); - set_bit(PG_highmem, &page->flags); - set_page_count(page, 1); - if (pfn < xen_start_info->nr_pages) - __free_page(page); - totalhigh_pages++; - } else - SetPageReserved(page); -} - -#ifndef CONFIG_DISCONTIGMEM -static void __init set_highmem_pages_init(int bad_ppro) -{ - int pfn; - for (pfn = highstart_pfn; pfn < highend_pfn; pfn++) - one_highpage_init(pfn_to_page(pfn), pfn, bad_ppro); - totalram_pages += totalhigh_pages; -} -#else -extern void set_highmem_pages_init(int); -#endif /* !CONFIG_DISCONTIGMEM */ - -#else -#define kmap_init() do { } while (0) -#define permanent_kmaps_init(pgd_base) do { } while (0) -#define set_highmem_pages_init(bad_ppro) do { } while (0) -#endif /* CONFIG_HIGHMEM */ - -unsigned long long __PAGE_KERNEL = _PAGE_KERNEL; -unsigned long long __PAGE_KERNEL_EXEC = _PAGE_KERNEL_EXEC; - -#ifndef CONFIG_DISCONTIGMEM -#define remap_numa_kva() do {} while (0) -#else -extern void __init remap_numa_kva(void); -#endif - -pgd_t *swapper_pg_dir; - -static void __init pagetable_init (void) -{ - unsigned long vaddr; - pgd_t *pgd_base = (pgd_t *)xen_start_info->pt_base; - int i; - - swapper_pg_dir = pgd_base; - init_mm.pgd = pgd_base; - for (i = 0; i < NR_CPUS; i++) - per_cpu(cur_pgd, i) = pgd_base; - - /* Enable PSE if available */ - if (cpu_has_pse) { - set_in_cr4(X86_CR4_PSE); - } - - /* Enable PGE if available */ - if (cpu_has_pge) { - set_in_cr4(X86_CR4_PGE); - __PAGE_KERNEL |= _PAGE_GLOBAL; - __PAGE_KERNEL_EXEC |= _PAGE_GLOBAL; - } - - kernel_physical_mapping_init(pgd_base); - remap_numa_kva(); - - /* - * Fixed mappings, only the page table structure has to be - * created - mappings will be set by set_fixmap(): - */ - vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK; - page_table_range_init(vaddr, 0, pgd_base); - - permanent_kmaps_init(pgd_base); -} - -#if defined(CONFIG_PM_DISK) || defined(CONFIG_SOFTWARE_SUSPEND) -/* - * Swap suspend & friends need this for resume because things like the intel-agp - * driver might have split up a kernel 4MB mapping. - */ -char __nosavedata swsusp_pg_dir[PAGE_SIZE] - __attribute__ ((aligned (PAGE_SIZE))); - -static inline void save_pg_dir(void) -{ - memcpy(swsusp_pg_dir, swapper_pg_dir, PAGE_SIZE); -} -#else -static inline void save_pg_dir(void) -{ -} -#endif - -void zap_low_mappings (void) -{ - int i; - - save_pg_dir(); - - /* - * Zap initial low-memory mappings. - * - * Note that "pgd_clear()" doesn't do it for - * us, because pgd_clear() is a no-op on i386. - */ - for (i = 0; i < USER_PTRS_PER_PGD; i++) -#if defined(CONFIG_X86_PAE) && !defined(CONFIG_XEN) - set_pgd(swapper_pg_dir+i, __pgd(1 + __pa(empty_zero_page))); -#else - set_pgd(swapper_pg_dir+i, __pgd(0)); -#endif - flush_tlb_all(); -} - -static int disable_nx __initdata = 0; -u64 __supported_pte_mask = ~_PAGE_NX; - -/* - * noexec = on|off - * - * Control non executable mappings. - * - * on Enable - * off Disable - */ -void __init noexec_setup(const char *str) -{ - if (!strncmp(str, "on",2) && cpu_has_nx) { - __supported_pte_mask |= _PAGE_NX; - disable_nx = 0; - } else if (!strncmp(str,"off",3)) { - disable_nx = 1; - __supported_pte_mask &= ~_PAGE_NX; - } -} - -int nx_enabled = 0; -#ifdef CONFIG_X86_PAE - -static void __init set_nx(void) -{ - unsigned int v[4], l, h; - - if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) { - cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]); - if ((v[3] & (1 << 20)) && !disable_nx) { - rdmsr(MSR_EFER, l, h); - l |= EFER_NX; - wrmsr(MSR_EFER, l, h); - nx_enabled = 1; - __supported_pte_mask |= _PAGE_NX; - } - } -} - -/* - * Enables/disables executability of a given kernel page and - * returns the previous setting. - */ -int __init set_kernel_exec(unsigned long vaddr, int enable) -{ - pte_t *pte; - int ret = 1; - - if (!nx_enabled) - goto out; - - pte = lookup_address(vaddr); - BUG_ON(!pte); - - if (!pte_exec_kernel(*pte)) - ret = 0; - - if (enable) - pte->pte_high &= ~(1 << (_PAGE_BIT_NX - 32)); - else - pte->pte_high |= 1 << (_PAGE_BIT_NX - 32); - __flush_tlb_all(); -out: - return ret; -} - -#endif - -/* - * paging_init() sets up the page tables - note that the first 8MB are - * already mapped by head.S. - * - * This routines also unmaps the page at virtual kernel address 0, so - * that we can trap those pesky NULL-reference errors in the kernel. - */ -void __init paging_init(void) -{ -#ifdef CONFIG_XEN_PHYSDEV_ACCESS - int i; -#endif - -#ifdef CONFIG_X86_PAE - set_nx(); - if (nx_enabled) - printk("NX (Execute Disable) protection: active\n"); -#endif - - pagetable_init(); - -#if defined(CONFIG_X86_PAE) && !defined(CONFIG_XEN) - /* - * We will bail out later - printk doesn't work right now so - * the user would just see a hanging kernel. - * when running as xen domain we are already in PAE mode at - * this point. - */ - if (cpu_has_pae) - set_in_cr4(X86_CR4_PAE); -#endif - __flush_tlb_all(); - - kmap_init(); - - /* Switch to the real shared_info page, and clear the dummy page. */ - set_fixmap(FIX_SHARED_INFO, xen_start_info->shared_info); - HYPERVISOR_shared_info = (shared_info_t *)fix_to_virt(FIX_SHARED_INFO); - memset(empty_zero_page, 0, sizeof(empty_zero_page)); - -#ifdef CONFIG_XEN_PHYSDEV_ACCESS - /* Setup mapping of lower 1st MB */ - for (i = 0; i < NR_FIX_ISAMAPS; i++) - if (xen_start_info->flags & SIF_PRIVILEGED) - set_fixmap(FIX_ISAMAP_BEGIN - i, i * PAGE_SIZE); - else - __set_fixmap(FIX_ISAMAP_BEGIN - i, - virt_to_machine(empty_zero_page), - PAGE_KERNEL_RO); -#endif -} - -/* - * Test if the WP bit works in supervisor mode. It isn't supported on 386's - * and also on some strange 486's (NexGen etc.). All 586+'s are OK. This - * used to involve black magic jumps to work around some nasty CPU bugs, - * but fortunately the switch to using exceptions got rid of all that. - */ - -static void __init test_wp_bit(void) -{ - printk("Checking if this processor honours the WP bit even in supervisor mode... "); - - /* Any page-aligned address will do, the test is non-destructive */ - __set_fixmap(FIX_WP_TEST, __pa(&swapper_pg_dir), PAGE_READONLY); - boot_cpu_data.wp_works_ok = do_test_wp_bit(); - clear_fixmap(FIX_WP_TEST); - - if (!boot_cpu_data.wp_works_ok) { - printk("No.\n"); -#ifdef CONFIG_X86_WP_WORKS_OK - panic("This kernel doesn't support CPU's with broken WP. Recompile it for a 386!"); -#endif - } else { - printk("Ok.\n"); - } -} - -static void __init set_max_mapnr_init(void) -{ -#ifdef CONFIG_HIGHMEM - num_physpages = highend_pfn; -#else - num_physpages = max_low_pfn; -#endif -#ifndef CONFIG_DISCONTIGMEM - max_mapnr = num_physpages; -#endif -} - -static struct kcore_list kcore_mem, kcore_vmalloc; - -void __init mem_init(void) -{ - extern int ppro_with_ram_bug(void); - int codesize, reservedpages, datasize, initsize; - int tmp; - int bad_ppro; - unsigned long pfn; - - contiguous_bitmap = alloc_bootmem_low_pages( - (max_low_pfn + 2*BITS_PER_LONG) >> 3); - BUG_ON(!contiguous_bitmap); - memset(contiguous_bitmap, 0, (max_low_pfn + 2*BITS_PER_LONG) >> 3); - -#if defined(CONFIG_SWIOTLB) - swiotlb_init(); -#endif - -#ifndef CONFIG_DISCONTIGMEM - if (!mem_map) - BUG(); -#endif - - bad_ppro = ppro_with_ram_bug(); - -#ifdef CONFIG_HIGHMEM - /* check that fixmap and pkmap do not overlap */ - if (PKMAP_BASE+LAST_PKMAP*PAGE_SIZE >= FIXADDR_START) { - printk(KERN_ERR "fixmap and kmap areas overlap - this will crash\n"); - printk(KERN_ERR "pkstart: %lxh pkend: %lxh fixstart %lxh\n", - PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE, FIXADDR_START); - BUG(); - } -#endif - - set_max_mapnr_init(); - -#ifdef CONFIG_HIGHMEM - high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1; -#else - high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1; -#endif - printk("vmalloc area: %lx-%lx, maxmem %lx\n", - VMALLOC_START,VMALLOC_END,MAXMEM); - BUG_ON(VMALLOC_START > VMALLOC_END); - - /* this will put all low memory onto the freelists */ - totalram_pages += free_all_bootmem(); - /* XEN: init and count low-mem pages outside initial allocation. */ - for (pfn = xen_start_info->nr_pages; pfn < max_low_pfn; pfn++) { - ClearPageReserved(&mem_map[pfn]); - set_page_count(&mem_map[pfn], 1); - totalram_pages++; - } - - reservedpages = 0; - for (tmp = 0; tmp < max_low_pfn; tmp++) - /* - * Only count reserved RAM pages - */ - if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp))) - reservedpages++; - - set_highmem_pages_init(bad_ppro); - - codesize = (unsigned long) &_etext - (unsigned long) &_text; - datasize = (unsigned long) &_edata - (unsigned long) &_etext; - initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; - - kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT); - kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, - VMALLOC_END-VMALLOC_START); - - printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, %dk reserved, %dk data, %dk init, %ldk highmem)\n", - (unsigned long) nr_free_pages() << (PAGE_SHIFT-10), - num_physpages << (PAGE_SHIFT-10), - codesize >> 10, - reservedpages << (PAGE_SHIFT-10), - datasize >> 10, - initsize >> 10, - (unsigned long) (totalhigh_pages << (PAGE_SHIFT-10)) - ); - -#ifdef CONFIG_X86_PAE - if (!cpu_has_pae) - panic("cannot execute a PAE-enabled kernel on a PAE-less CPU!"); -#endif - if (boot_cpu_data.wp_works_ok < 0) - test_wp_bit(); - - /* - * Subtle. SMP is doing it's boot stuff late (because it has to - * fork idle threads) - but it also needs low mappings for the - * protected-mode entry to work. We zap these entries only after - * the WP-bit has been tested. - */ -#ifndef CONFIG_SMP - zap_low_mappings(); -#endif - - set_bit(PG_pinned, &virt_to_page(init_mm.pgd)->flags); -} - -kmem_cache_t *pgd_cache; -kmem_cache_t *pmd_cache; - -void __init pgtable_cache_init(void) -{ - if (PTRS_PER_PMD > 1) { - pmd_cache = kmem_cache_create("pmd", - PTRS_PER_PMD*sizeof(pmd_t), - PTRS_PER_PMD*sizeof(pmd_t), - 0, - pmd_ctor, - NULL); - if (!pmd_cache) - panic("pgtable_cache_init(): cannot create pmd cache"); - } - pgd_cache = kmem_cache_create("pgd", -#ifndef CONFIG_XEN - PTRS_PER_PGD*sizeof(pgd_t), - PTRS_PER_PGD*sizeof(pgd_t), -#else - PAGE_SIZE, - PAGE_SIZE, -#endif - 0, - pgd_ctor, - PTRS_PER_PMD == 1 ? pgd_dtor : NULL); - if (!pgd_cache) - panic("pgtable_cache_init(): Cannot create pgd cache"); -} - -/* - * This function cannot be __init, since exceptions don't work in that - * section. Put this after the callers, so that it cannot be inlined. - */ -static int noinline do_test_wp_bit(void) -{ - char tmp_reg; - int flag; - - __asm__ __volatile__( - " movb %0,%1 \n" - "1: movb %1,%0 \n" - " xorl %2,%2 \n" - "2: \n" - ".section __ex_table,\"a\"\n" - " .align 4 \n" - " .long 1b,2b \n" - ".previous \n" - :"=m" (*(char *)fix_to_virt(FIX_WP_TEST)), - "=q" (tmp_reg), - "=r" (flag) - :"2" (1) - :"memory"); - - return flag; -} - -void free_initmem(void) -{ - unsigned long addr; - - addr = (unsigned long)(&__init_begin); - for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - set_page_count(virt_to_page(addr), 1); - memset((void *)addr, 0xcc, PAGE_SIZE); - free_page(addr); - totalram_pages++; - } - printk (KERN_INFO "Freeing unused kernel memory: %dk freed\n", (__init_end - __init_begin) >> 10); -} - -#ifdef CONFIG_BLK_DEV_INITRD -void free_initrd_mem(unsigned long start, unsigned long end) -{ - if (start < end) - printk (KERN_INFO "Freeing initrd memory: %ldk freed\n", (end - start) >> 10); - for (; start < end; start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(start)); - set_page_count(virt_to_page(start), 1); - free_page(start); - totalram_pages++; - } -} -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/mm/ioremap.c --- a/linux-2.6-xen-sparse/arch/xen/i386/mm/ioremap.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,470 +0,0 @@ -/* - * arch/i386/mm/ioremap.c - * - * Re-map IO memory to kernel address space so that we can access it. - * This is needed for high PCI addresses that aren't mapped in the - * 640k-1MB IO memory area on PC's - * - * (C) Copyright 1995 1996 Linus Torvalds - */ - -#include <linux/vmalloc.h> -#include <linux/init.h> -#include <linux/slab.h> -#include <linux/module.h> -#include <asm/io.h> -#include <asm/fixmap.h> -#include <asm/cacheflush.h> -#include <asm/tlbflush.h> -#include <asm/pgtable.h> -#include <asm/pgalloc.h> - -#define ISA_START_ADDRESS 0x0 -#define ISA_END_ADDRESS 0x100000 - -#if 0 /* not PAE safe */ -/* These hacky macros avoid phys->machine translations. */ -#define __direct_pte(x) ((pte_t) { (x) } ) -#define __direct_mk_pte(page_nr,pgprot) \ - __direct_pte(((page_nr) << PAGE_SHIFT) | pgprot_val(pgprot)) -#define direct_mk_pte_phys(physpage, pgprot) \ - __direct_mk_pte((physpage) >> PAGE_SHIFT, pgprot) -#endif - -static int direct_remap_area_pte_fn(pte_t *pte, - struct page *pte_page, - unsigned long address, - void *data) -{ - mmu_update_t **v = (mmu_update_t **)data; - - (*v)->ptr = ((u64)pfn_to_mfn(page_to_pfn(pte_page)) << - PAGE_SHIFT) | ((unsigned long)pte & ~PAGE_MASK); - (*v)++; - - return 0; -} - -static int __direct_remap_pfn_range(struct mm_struct *mm, - unsigned long address, - unsigned long mfn, - unsigned long size, - pgprot_t prot, - domid_t domid) -{ - int rc; - unsigned long i, start_address; - mmu_update_t *u, *v, *w; - - u = v = w = (mmu_update_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT); - if (u == NULL) - return -ENOMEM; - - start_address = address; - - flush_cache_all(); - - for (i = 0; i < size; i += PAGE_SIZE) { - if ((v - u) == (PAGE_SIZE / sizeof(mmu_update_t))) { - /* Fill in the PTE pointers. */ - rc = generic_page_range(mm, start_address, - address - start_address, - direct_remap_area_pte_fn, &w); - if (rc) - goto out; - w = u; - rc = -EFAULT; - if (HYPERVISOR_mmu_update(u, v - u, NULL, domid) < 0) - goto out; - v = u; - start_address = address; - } - - /* - * Fill in the machine address: PTE ptr is done later by - * __direct_remap_area_pages(). - */ - v->val = pte_val_ma(pfn_pte_ma(mfn, prot)); - - mfn++; - address += PAGE_SIZE; - v++; - } - - if (v != u) { - /* get the ptep's filled in */ - rc = generic_page_range(mm, start_address, address - start_address, - direct_remap_area_pte_fn, &w); - if (rc) - goto out; - rc = -EFAULT; - if (unlikely(HYPERVISOR_mmu_update(u, v - u, NULL, domid) < 0)) - goto out; - } - - rc = 0; - - out: - flush_tlb_all(); - - free_page((unsigned long)u); - - return rc; -} - -int direct_remap_pfn_range(struct vm_area_struct *vma, - unsigned long address, - unsigned long mfn, - unsigned long size, - pgprot_t prot, - domid_t domid) -{ - /* Same as remap_pfn_range(). */ - vma->vm_flags |= VM_IO | VM_RESERVED; - - return __direct_remap_pfn_range( - vma->vm_mm, address, mfn, size, prot, domid); -} -EXPORT_SYMBOL(direct_remap_pfn_range); - -int direct_kernel_remap_pfn_range(unsigned long address, - unsigned long mfn, - unsigned long size, - pgprot_t prot, - domid_t domid) -{ - return __direct_remap_pfn_range( - &init_mm, address, mfn, size, prot, domid); -} -EXPORT_SYMBOL(direct_kernel_remap_pfn_range); - -static int lookup_pte_fn( - pte_t *pte, struct page *pte_page, unsigned long addr, void *data) -{ - uint64_t *ptep = (uint64_t *)data; - if (ptep) - *ptep = ((uint64_t)pfn_to_mfn(page_to_pfn(pte_page)) << - PAGE_SHIFT) | ((unsigned long)pte & ~PAGE_MASK); - return 0; -} - -int create_lookup_pte_addr(struct mm_struct *mm, - unsigned long address, - uint64_t *ptep) -{ - return generic_page_range(mm, address, PAGE_SIZE, lookup_pte_fn, ptep); -} - -EXPORT_SYMBOL(create_lookup_pte_addr); - -static int noop_fn( - pte_t *pte, struct page *pte_page, unsigned long addr, void *data) -{ - return 0; -} - -int touch_pte_range(struct mm_struct *mm, - unsigned long address, - unsigned long size) -{ - return generic_page_range(mm, address, size, noop_fn, NULL); -} - -EXPORT_SYMBOL(touch_pte_range); - -#ifdef CONFIG_XEN_PHYSDEV_ACCESS - -/* - * Does @address reside within a non-highmem page that is local to this virtual - * machine (i.e., not an I/O page, nor a memory page belonging to another VM). - * See the comment that accompanies pte_pfn() in pgtable-2level.h to understand - * why this works. - */ -static inline int is_local_lowmem(unsigned long address) -{ - extern unsigned long max_low_pfn; - unsigned long mfn = address >> PAGE_SHIFT; - unsigned long pfn = mfn_to_pfn(mfn); - return ((pfn < max_low_pfn) && (phys_to_machine_mapping[pfn] == mfn)); -} - -/* - * Generic mapping function (not visible outside): - */ - -/* - * Remap an arbitrary physical address space into the kernel virtual - * address space. Needed when the kernel wants to access high addresses - * directly. - * - * NOTE! We need to allow non-page-aligned mappings too: we will obviously - * have to convert them into an offset in a page-aligned mapping, but the - * caller shouldn't need to know that small detail. - */ -void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned long flags) -{ - void __iomem * addr; - struct vm_struct * area; - unsigned long offset, last_addr; - domid_t domid = DOMID_IO; - - /* Don't allow wraparound or zero size */ - last_addr = phys_addr + size - 1; - if (!size || last_addr < phys_addr) - return NULL; - - /* - * Don't remap the low PCI/ISA area, it's always mapped.. - */ - if (xen_start_info->flags & SIF_PRIVILEGED && - phys_addr >= ISA_START_ADDRESS && last_addr < ISA_END_ADDRESS) - return (void __iomem *) isa_bus_to_virt(phys_addr); - - /* - * Don't allow anybody to remap normal RAM that we're using.. - */ - if (is_local_lowmem(phys_addr)) { - char *t_addr, *t_end; - struct page *page; - - t_addr = bus_to_virt(phys_addr); - t_end = t_addr + (size - 1); - - for(page = virt_to_page(t_addr); page <= virt_to_page(t_end); page++) - if(!PageReserved(page)) - return NULL; - - domid = DOMID_SELF; - } - - /* - * Mappings have to be page-aligned - */ - offset = phys_addr & ~PAGE_MASK; - phys_addr &= PAGE_MASK; - size = PAGE_ALIGN(last_addr+1) - phys_addr; - - /* - * Ok, go for it.. - */ - area = get_vm_area(size, VM_IOREMAP | (flags << 20)); - if (!area) - return NULL; - area->phys_addr = phys_addr; - addr = (void __iomem *) area->addr; - flags |= _PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED; -#ifdef __x86_64__ - flags |= _PAGE_USER; -#endif - if (__direct_remap_pfn_range(&init_mm, (unsigned long)addr, - phys_addr>>PAGE_SHIFT, - size, __pgprot(flags), domid)) { - vunmap((void __force *) addr); - return NULL; - } - return (void __iomem *) (offset + (char __iomem *)addr); -} - - -/** - * ioremap_nocache - map bus memory into CPU space - * @offset: bus address of the memory - * @size: size of the resource to map - * - * ioremap_nocache performs a platform specific sequence of operations to - * make bus memory CPU accessible via the readb/readw/readl/writeb/ - * writew/writel functions and the other mmio helpers. The returned - * address is not guaranteed to be usable directly as a virtual - * address. - * - * This version of ioremap ensures that the memory is marked uncachable - * on the CPU as well as honouring existing caching rules from things like - * the PCI bus. Note that there are other caches and buffers on many - * busses. In particular driver authors should read up on PCI writes - * - * It's useful if some control registers are in such an area and - * write combining or read caching is not desirable: - * - * Must be freed with iounmap. - */ - -void __iomem *ioremap_nocache (unsigned long phys_addr, unsigned long size) -{ - unsigned long last_addr; - void __iomem *p = __ioremap(phys_addr, size, _PAGE_PCD); - if (!p) - return p; - - /* Guaranteed to be > phys_addr, as per __ioremap() */ - last_addr = phys_addr + size - 1; - - if (is_local_lowmem(last_addr)) { - struct page *ppage = virt_to_page(bus_to_virt(phys_addr)); - unsigned long npages; - - phys_addr &= PAGE_MASK; - - /* This might overflow and become zero.. */ - last_addr = PAGE_ALIGN(last_addr); - - /* .. but that's ok, because modulo-2**n arithmetic will make - * the page-aligned "last - first" come out right. - */ - npages = (last_addr - phys_addr) >> PAGE_SHIFT; - - if (change_page_attr(ppage, npages, PAGE_KERNEL_NOCACHE) < 0) { - iounmap(p); - p = NULL; - } - global_flush_tlb(); - } - - return p; -} - -void iounmap(volatile void __iomem *addr) -{ - struct vm_struct *p; - if ((void __force *) addr <= high_memory) - return; - - /* - * __ioremap special-cases the PCI/ISA range by not instantiating a - * vm_area and by simply returning an address into the kernel mapping - * of ISA space. So handle that here. - */ - if ((unsigned long) addr >= fix_to_virt(FIX_ISAMAP_BEGIN)) - return; - - write_lock(&vmlist_lock); - p = __remove_vm_area((void *) (PAGE_MASK & (unsigned long __force) addr)); - if (!p) { - printk("iounmap: bad address %p\n", addr); - goto out_unlock; - } - - if ((p->flags >> 20) && is_local_lowmem(p->phys_addr)) { - /* p->size includes the guard page, but cpa doesn't like that */ - change_page_attr(virt_to_page(bus_to_virt(p->phys_addr)), - (p->size - PAGE_SIZE) >> PAGE_SHIFT, - PAGE_KERNEL); - global_flush_tlb(); - } -out_unlock: - write_unlock(&vmlist_lock); - kfree(p); -} - -#ifdef __i386__ - -void __init *bt_ioremap(unsigned long phys_addr, unsigned long size) -{ - unsigned long offset, last_addr; - unsigned int nrpages; - enum fixed_addresses idx; - - /* Don't allow wraparound or zero size */ - last_addr = phys_addr + size - 1; - if (!size || last_addr < phys_addr) - return NULL; - - /* - * Don't remap the low PCI/ISA area, it's always mapped.. - */ - if (xen_start_info->flags & SIF_PRIVILEGED && - phys_addr >= ISA_START_ADDRESS && last_addr < ISA_END_ADDRESS) - return isa_bus_to_virt(phys_addr); - - /* - * Mappings have to be page-aligned - */ - offset = phys_addr & ~PAGE_MASK; - phys_addr &= PAGE_MASK; - size = PAGE_ALIGN(last_addr) - phys_addr; - - /* - * Mappings have to fit in the FIX_BTMAP area. - */ - nrpages = size >> PAGE_SHIFT; - if (nrpages > NR_FIX_BTMAPS) - return NULL; - - /* - * Ok, go for it.. - */ - idx = FIX_BTMAP_BEGIN; - while (nrpages > 0) { - set_fixmap(idx, phys_addr); - phys_addr += PAGE_SIZE; - --idx; - --nrpages; - } - return (void*) (offset + fix_to_virt(FIX_BTMAP_BEGIN)); -} - -void __init bt_iounmap(void *addr, unsigned long size) -{ - unsigned long virt_addr; - unsigned long offset; - unsigned int nrpages; - enum fixed_addresses idx; - - virt_addr = (unsigned long)addr; - if (virt_addr < fix_to_virt(FIX_BTMAP_BEGIN)) - return; - if (virt_addr >= fix_to_virt(FIX_ISAMAP_BEGIN)) - return; - offset = virt_addr & ~PAGE_MASK; - nrpages = PAGE_ALIGN(offset + size - 1) >> PAGE_SHIFT; - - idx = FIX_BTMAP_BEGIN; - while (nrpages > 0) { - clear_fixmap(idx); - --idx; - --nrpages; - } -} - -#endif /* __i386__ */ - -#else /* CONFIG_XEN_PHYSDEV_ACCESS */ - -void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, - unsigned long flags) -{ - return NULL; -} - -void __iomem *ioremap_nocache (unsigned long phys_addr, unsigned long size) -{ - return NULL; -} - -void iounmap(volatile void __iomem *addr) -{ -} - -#ifdef __i386__ - -void __init *bt_ioremap(unsigned long phys_addr, unsigned long size) -{ - return NULL; -} - -void __init bt_iounmap(void *addr, unsigned long size) -{ -} - -#endif /* __i386__ */ - -#endif /* CONFIG_XEN_PHYSDEV_ACCESS */ - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/mm/pgtable.c --- a/linux-2.6-xen-sparse/arch/xen/i386/mm/pgtable.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,619 +0,0 @@ -/* - * linux/arch/i386/mm/pgtable.c - */ - -#include <linux/config.h> -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/mm.h> -#include <linux/swap.h> -#include <linux/smp.h> -#include <linux/highmem.h> -#include <linux/slab.h> -#include <linux/pagemap.h> -#include <linux/spinlock.h> - -#include <asm/system.h> -#include <asm/pgtable.h> -#include <asm/pgalloc.h> -#include <asm/fixmap.h> -#include <asm/e820.h> -#include <asm/tlb.h> -#include <asm/tlbflush.h> -#include <asm/io.h> -#include <asm/mmu_context.h> - -#include <asm-xen/features.h> -#include <asm-xen/foreign_page.h> -#include <asm/hypervisor.h> - -static void pgd_test_and_unpin(pgd_t *pgd); - -void show_mem(void) -{ - int total = 0, reserved = 0; - int shared = 0, cached = 0; - int highmem = 0; - struct page *page; - pg_data_t *pgdat; - unsigned long i; - - printk("Mem-info:\n"); - show_free_areas(); - printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10)); - for_each_pgdat(pgdat) { - for (i = 0; i < pgdat->node_spanned_pages; ++i) { - page = pgdat->node_mem_map + i; - total++; - if (PageHighMem(page)) - highmem++; - if (PageReserved(page)) - reserved++; - else if (PageSwapCache(page)) - cached++; - else if (page_count(page)) - shared += page_count(page) - 1; - } - } - printk("%d pages of RAM\n", total); - printk("%d pages of HIGHMEM\n",highmem); - printk("%d reserved pages\n",reserved); - printk("%d pages shared\n",shared); - printk("%d pages swap cached\n",cached); -} - -/* - * Associate a virtual page frame with a given physical page frame - * and protection flags for that frame. - */ -static void set_pte_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - pgd = swapper_pg_dir + pgd_index(vaddr); - if (pgd_none(*pgd)) { - BUG(); - return; - } - pud = pud_offset(pgd, vaddr); - if (pud_none(*pud)) { - BUG(); - return; - } - pmd = pmd_offset(pud, vaddr); - if (pmd_none(*pmd)) { - BUG(); - return; - } - pte = pte_offset_kernel(pmd, vaddr); - /* <pfn,flags> stored as-is, to permit clearing entries */ - set_pte(pte, pfn_pte(pfn, flags)); - - /* - * It's enough to flush this one mapping. - * (PGE mappings get flushed as well) - */ - __flush_tlb_one(vaddr); -} - -/* - * Associate a virtual page frame with a given physical page frame - * and protection flags for that frame. - */ -static void set_pte_pfn_ma(unsigned long vaddr, unsigned long pfn, - pgprot_t flags) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - pgd = swapper_pg_dir + pgd_index(vaddr); - if (pgd_none(*pgd)) { - BUG(); - return; - } - pud = pud_offset(pgd, vaddr); - if (pud_none(*pud)) { - BUG(); - return; - } - pmd = pmd_offset(pud, vaddr); - if (pmd_none(*pmd)) { - BUG(); - return; - } - pte = pte_offset_kernel(pmd, vaddr); - /* <pfn,flags> stored as-is, to permit clearing entries */ - set_pte(pte, pfn_pte_ma(pfn, flags)); - - /* - * It's enough to flush this one mapping. - * (PGE mappings get flushed as well) - */ - __flush_tlb_one(vaddr); -} - -/* - * Associate a large virtual page frame with a given physical page frame - * and protection flags for that frame. pfn is for the base of the page, - * vaddr is what the page gets mapped to - both must be properly aligned. - * The pmd must already be instantiated. Assumes PAE mode. - */ -void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - - if (vaddr & (PMD_SIZE-1)) { /* vaddr is misaligned */ - printk ("set_pmd_pfn: vaddr misaligned\n"); - return; /* BUG(); */ - } - if (pfn & (PTRS_PER_PTE-1)) { /* pfn is misaligned */ - printk ("set_pmd_pfn: pfn misaligned\n"); - return; /* BUG(); */ - } - pgd = swapper_pg_dir + pgd_index(vaddr); - if (pgd_none(*pgd)) { - printk ("set_pmd_pfn: pgd_none\n"); - return; /* BUG(); */ - } - pud = pud_offset(pgd, vaddr); - pmd = pmd_offset(pud, vaddr); - set_pmd(pmd, pfn_pmd(pfn, flags)); - /* - * It's enough to flush this one mapping. - * (PGE mappings get flushed as well) - */ - __flush_tlb_one(vaddr); -} - -void __set_fixmap (enum fixed_addresses idx, maddr_t phys, pgprot_t flags) -{ - unsigned long address = __fix_to_virt(idx); - - if (idx >= __end_of_fixed_addresses) { - BUG(); - return; - } - switch (idx) { - case FIX_WP_TEST: - case FIX_VSYSCALL: -#ifdef CONFIG_X86_F00F_BUG - case FIX_F00F_IDT: -#endif - set_pte_pfn(address, phys >> PAGE_SHIFT, flags); - break; - default: - set_pte_pfn_ma(address, phys >> PAGE_SHIFT, flags); - break; - } -} - -pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) -{ - pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO); - if (pte) - make_lowmem_page_readonly(pte, XENFEAT_writable_page_tables); - return pte; -} - -struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address) -{ - struct page *pte; - -#ifdef CONFIG_HIGHPTE - pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT|__GFP_ZERO, 0); -#else - pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0); - if (pte) { - SetPageForeign(pte, pte_free); - set_page_count(pte, 1); - } -#endif - - return pte; -} - -void pte_free(struct page *pte) -{ - unsigned long va = (unsigned long)__va(page_to_pfn(pte)<<PAGE_SHIFT); - - if (!pte_write(*virt_to_ptep(va))) - BUG_ON(HYPERVISOR_update_va_mapping( - va, pfn_pte(page_to_pfn(pte), PAGE_KERNEL), 0)); - - ClearPageForeign(pte); - set_page_count(pte, 1); - - __free_page(pte); -} - -void pmd_ctor(void *pmd, kmem_cache_t *cache, unsigned long flags) -{ - memset(pmd, 0, PTRS_PER_PMD*sizeof(pmd_t)); -} - -/* - * List of all pgd's needed for non-PAE so it can invalidate entries - * in both cached and uncached pgd's; not needed for PAE since the - * kernel pmd is shared. If PAE were not to share the pmd a similar - * tactic would be needed. This is essentially codepath-based locking - * against pageattr.c; it is the unique case in which a valid change - * of kernel pagetables can't be lazily synchronized by vmalloc faults. - * vmalloc faults work because attached pagetables are never freed. - * The locking scheme was chosen on the basis of manfred's - * recommendations and having no core impact whatsoever. - * -- wli - */ -DEFINE_SPINLOCK(pgd_lock); -struct page *pgd_list; - -static inline void pgd_list_add(pgd_t *pgd) -{ - struct page *page = virt_to_page(pgd); - page->index = (unsigned long)pgd_list; - if (pgd_list) - pgd_list->private = (unsigned long)&page->index; - pgd_list = page; - page->private = (unsigned long)&pgd_list; -} - -static inline void pgd_list_del(pgd_t *pgd) -{ - struct page *next, **pprev, *page = virt_to_page(pgd); - next = (struct page *)page->index; - pprev = (struct page **)page->private; - *pprev = next; - if (next) - next->private = (unsigned long)pprev; -} - -void pgd_ctor(void *pgd, kmem_cache_t *cache, unsigned long unused) -{ - unsigned long flags; - - if (PTRS_PER_PMD > 1) { - /* Ensure pgd resides below 4GB. */ - int rc = xen_create_contiguous_region( - (unsigned long)pgd, 0, 32); - BUG_ON(rc); - if (HAVE_SHARED_KERNEL_PMD) - memcpy((pgd_t *)pgd + USER_PTRS_PER_PGD, - swapper_pg_dir + USER_PTRS_PER_PGD, - (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t)); - } else { - spin_lock_irqsave(&pgd_lock, flags); - memcpy((pgd_t *)pgd + USER_PTRS_PER_PGD, - swapper_pg_dir + USER_PTRS_PER_PGD, - (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t)); - memset(pgd, 0, USER_PTRS_PER_PGD*sizeof(pgd_t)); - pgd_list_add(pgd); - spin_unlock_irqrestore(&pgd_lock, flags); - } -} - -/* never called when PTRS_PER_PMD > 1 */ -void pgd_dtor(void *pgd, kmem_cache_t *cache, unsigned long unused) -{ - unsigned long flags; /* can be called from interrupt context */ - - spin_lock_irqsave(&pgd_lock, flags); - pgd_list_del(pgd); - spin_unlock_irqrestore(&pgd_lock, flags); - - pgd_test_and_unpin(pgd); -} - -pgd_t *pgd_alloc(struct mm_struct *mm) -{ - int i; - pgd_t *pgd = kmem_cache_alloc(pgd_cache, GFP_KERNEL); - - pgd_test_and_unpin(pgd); - - if (PTRS_PER_PMD == 1 || !pgd) - return pgd; - - for (i = 0; i < USER_PTRS_PER_PGD; ++i) { - pmd_t *pmd = kmem_cache_alloc(pmd_cache, GFP_KERNEL); - if (!pmd) - goto out_oom; - set_pgd(&pgd[i], __pgd(1 + __pa(pmd))); - } - - if (!HAVE_SHARED_KERNEL_PMD) { - unsigned long flags; - - for (i = USER_PTRS_PER_PGD; i < PTRS_PER_PGD; i++) { - pmd_t *pmd = kmem_cache_alloc(pmd_cache, GFP_KERNEL); - if (!pmd) - goto out_oom; - set_pgd(&pgd[USER_PTRS_PER_PGD], __pgd(1 + __pa(pmd))); - } - - spin_lock_irqsave(&pgd_lock, flags); - for (i = USER_PTRS_PER_PGD; i < PTRS_PER_PGD; i++) { - unsigned long v = (unsigned long)i << PGDIR_SHIFT; - pgd_t *kpgd = pgd_offset_k(v); - pud_t *kpud = pud_offset(kpgd, v); - pmd_t *kpmd = pmd_offset(kpud, v); - pmd_t *pmd = (void *)__va(pgd_val(pgd[i])-1); - memcpy(pmd, kpmd, PAGE_SIZE); - make_lowmem_page_readonly( - pmd, XENFEAT_writable_page_tables); - } - pgd_list_add(pgd); - spin_unlock_irqrestore(&pgd_lock, flags); - } - - return pgd; - -out_oom: - for (i--; i >= 0; i--) - kmem_cache_free(pmd_cache, (void *)__va(pgd_val(pgd[i])-1)); - kmem_cache_free(pgd_cache, pgd); - return NULL; -} - -void pgd_free(pgd_t *pgd) -{ - int i; - - pgd_test_and_unpin(pgd); - - /* in the PAE case user pgd entries are overwritten before usage */ - if (PTRS_PER_PMD > 1) { - for (i = 0; i < USER_PTRS_PER_PGD; ++i) { - pmd_t *pmd = (void *)__va(pgd_val(pgd[i])-1); - kmem_cache_free(pmd_cache, pmd); - } - if (!HAVE_SHARED_KERNEL_PMD) { - unsigned long flags; - spin_lock_irqsave(&pgd_lock, flags); - pgd_list_del(pgd); - spin_unlock_irqrestore(&pgd_lock, flags); - for (i = USER_PTRS_PER_PGD; i < PTRS_PER_PGD; i++) { - pmd_t *pmd = (void *)__va(pgd_val(pgd[i])-1); - make_lowmem_page_writable( - pmd, XENFEAT_writable_page_tables); - memset(pmd, 0, PTRS_PER_PMD*sizeof(pmd_t)); - kmem_cache_free(pmd_cache, pmd); - } - } - } - /* in the non-PAE case, free_pgtables() clears user pgd entries */ - kmem_cache_free(pgd_cache, pgd); -} - -#ifndef CONFIG_XEN_SHADOW_MODE -void make_lowmem_page_readonly(void *va, unsigned int feature) -{ - pte_t *pte; - int rc; - - if (xen_feature(feature)) - return; - - pte = virt_to_ptep(va); - rc = HYPERVISOR_update_va_mapping( - (unsigned long)va, pte_wrprotect(*pte), 0); - BUG_ON(rc); -} - -void make_lowmem_page_writable(void *va, unsigned int feature) -{ - pte_t *pte; - int rc; - - if (xen_feature(feature)) - return; - - pte = virt_to_ptep(va); - rc = HYPERVISOR_update_va_mapping( - (unsigned long)va, pte_mkwrite(*pte), 0); - BUG_ON(rc); -} - -void make_page_readonly(void *va, unsigned int feature) -{ - pte_t *pte; - int rc; - - if (xen_feature(feature)) - return; - - pte = virt_to_ptep(va); - rc = HYPERVISOR_update_va_mapping( - (unsigned long)va, pte_wrprotect(*pte), 0); - if (rc) /* fallback? */ - xen_l1_entry_update(pte, pte_wrprotect(*pte)); - if ((unsigned long)va >= (unsigned long)high_memory) { - unsigned long pfn = pte_pfn(*pte); -#ifdef CONFIG_HIGHMEM - if (pfn >= highstart_pfn) - kmap_flush_unused(); /* flush stale writable kmaps */ - else -#endif - make_lowmem_page_readonly( - phys_to_virt(pfn << PAGE_SHIFT), feature); - } -} - -void make_page_writable(void *va, unsigned int feature) -{ - pte_t *pte; - int rc; - - if (xen_feature(feature)) - return; - - pte = virt_to_ptep(va); - rc = HYPERVISOR_update_va_mapping( - (unsigned long)va, pte_mkwrite(*pte), 0); - if (rc) /* fallback? */ - xen_l1_entry_update(pte, pte_mkwrite(*pte)); - if ((unsigned long)va >= (unsigned long)high_memory) { - unsigned long pfn = pte_pfn(*pte); -#ifdef CONFIG_HIGHMEM - if (pfn < highstart_pfn) -#endif - make_lowmem_page_writable( - phys_to_virt(pfn << PAGE_SHIFT), feature); - } -} - -void make_pages_readonly(void *va, unsigned int nr, unsigned int feature) -{ - if (xen_feature(feature)) - return; - - while (nr-- != 0) { - make_page_readonly(va, feature); - va = (void *)((unsigned long)va + PAGE_SIZE); - } -} - -void make_pages_writable(void *va, unsigned int nr, unsigned int feature) -{ - if (xen_feature(feature)) - return; - - while (nr-- != 0) { - make_page_writable(va, feature); - va = (void *)((unsigned long)va + PAGE_SIZE); - } -} -#endif /* CONFIG_XEN_SHADOW_MODE */ - -static inline void pgd_walk_set_prot(void *pt, pgprot_t flags) -{ - struct page *page = virt_to_page(pt); - unsigned long pfn = page_to_pfn(page); - - if (PageHighMem(page)) - return; - BUG_ON(HYPERVISOR_update_va_mapping( - (unsigned long)__va(pfn << PAGE_SHIFT), - pfn_pte(pfn, flags), 0)); -} - -static void pgd_walk(pgd_t *pgd_base, pgprot_t flags) -{ - pgd_t *pgd = pgd_base; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - int g, u, m; - - for (g = 0; g < USER_PTRS_PER_PGD; g++, pgd++) { - if (pgd_none(*pgd)) - continue; - pud = pud_offset(pgd, 0); - if (PTRS_PER_PUD > 1) /* not folded */ - pgd_walk_set_prot(pud,flags); - for (u = 0; u < PTRS_PER_PUD; u++, pud++) { - if (pud_none(*pud)) - continue; - pmd = pmd_offset(pud, 0); - if (PTRS_PER_PMD > 1) /* not folded */ - pgd_walk_set_prot(pmd,flags); - for (m = 0; m < PTRS_PER_PMD; m++, pmd++) { - if (pmd_none(*pmd)) - continue; - pte = pte_offset_kernel(pmd,0); - pgd_walk_set_prot(pte,flags); - } - } - } - - BUG_ON(HYPERVISOR_update_va_mapping( - (unsigned long)pgd_base, - pfn_pte(virt_to_phys(pgd_base)>>PAGE_SHIFT, flags), - UVMF_TLB_FLUSH)); -} - -static void __pgd_pin(pgd_t *pgd) -{ - pgd_walk(pgd, PAGE_KERNEL_RO); - xen_pgd_pin(__pa(pgd)); - set_bit(PG_pinned, &virt_to_page(pgd)->flags); -} - -static void __pgd_unpin(pgd_t *pgd) -{ - xen_pgd_unpin(__pa(pgd)); - pgd_walk(pgd, PAGE_KERNEL); - clear_bit(PG_pinned, &virt_to_page(pgd)->flags); -} - -static void pgd_test_and_unpin(pgd_t *pgd) -{ - if (test_bit(PG_pinned, &virt_to_page(pgd)->flags)) - __pgd_unpin(pgd); -} - -void mm_pin(struct mm_struct *mm) -{ - spin_lock(&mm->page_table_lock); - __pgd_pin(mm->pgd); - spin_unlock(&mm->page_table_lock); -} - -void mm_unpin(struct mm_struct *mm) -{ - spin_lock(&mm->page_table_lock); - __pgd_unpin(mm->pgd); - spin_unlock(&mm->page_table_lock); -} - -void mm_pin_all(void) -{ - struct page *page; - for (page = pgd_list; page; page = (struct page *)page->index) { - if (!test_bit(PG_pinned, &page->flags)) - __pgd_pin((pgd_t *)page_address(page)); - } -} - -void _arch_exit_mmap(struct mm_struct *mm) -{ - struct task_struct *tsk = current; - - task_lock(tsk); - - /* - * We aggressively remove defunct pgd from cr3. We execute unmap_vmas() - * *much* faster this way, as no tlb flushes means bigger wrpt batches. - */ - if (tsk->active_mm == mm) { - tsk->active_mm = &init_mm; - atomic_inc(&init_mm.mm_count); - - switch_mm(mm, &init_mm, tsk); - - atomic_dec(&mm->mm_count); - BUG_ON(atomic_read(&mm->mm_count) == 0); - } - - task_unlock(tsk); - - if (test_bit(PG_pinned, &virt_to_page(mm->pgd)->flags) && - (atomic_read(&mm->mm_count) == 1)) - mm_unpin(mm); -} - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/pci/Makefile --- a/linux-2.6-xen-sparse/arch/xen/i386/pci/Makefile Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,33 +0,0 @@ -XENARCH := $(subst ",,$(CONFIG_XENARCH)) - -CFLAGS += -Iarch/$(XENARCH)/pci - -obj-y := i386.o - -#c-obj-$(CONFIG_PCI_BIOS) += pcbios.o -c-obj-$(CONFIG_PCI_MMCONFIG) += mmconfig.o -c-obj-$(CONFIG_PCI_DIRECT) += direct.o - -c-pci-y := fixup.o -c-pci-$(CONFIG_ACPI_PCI) += acpi.o -c-pci-y += legacy.o -# Make sure irq.o gets linked in after legacy.o -l-pci-y += irq.o - -c-pci-$(CONFIG_X86_VISWS) := visws.o fixup.o -pci-$(CONFIG_X86_VISWS) := -c-pci-$(CONFIG_X86_NUMAQ) := numa.o -l-pci-$(CONFIG_X86_NUMAQ) := irq.o - -obj-y += $(pci-y) -c-obj-y += $(c-pci-y) common.o - -c-link := - -$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)): - @ln -fsn $(srctree)/arch/i386/pci/$(notdir $@) $@ - -# Make sure irq.o gets linked in before common.o -obj-y += $(patsubst common.o,$(l-pci-y) common.o,$(c-obj-y)) - -clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link)) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/pci/i386.c --- a/linux-2.6-xen-sparse/arch/xen/i386/pci/i386.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,304 +0,0 @@ -/* - * Low-Level PCI Access for i386 machines - * - * Copyright 1993, 1994 Drew Eckhardt - * Visionary Computing - * (Unix and Linux consulting and custom programming) - * Drew@xxxxxxxxxxxx - * +1 (303) 786-7975 - * - * Drew's work was sponsored by: - * iX Multiuser Multitasking Magazine - * Hannover, Germany - * hm@xxxxx - * - * Copyright 1997--2000 Martin Mares <mj@xxxxxx> - * - * For more information, please consult the following manuals (look at - * http://www.pcisig.com/ for how to get them): - * - * PCI BIOS Specification - * PCI Local Bus Specification - * PCI to PCI Bridge Specification - * PCI System Design Guide - * - */ - -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/init.h> -#include <linux/ioport.h> -#include <linux/errno.h> - -#include "pci.h" - -/* - * We need to avoid collisions with `mirrored' VGA ports - * and other strange ISA hardware, so we always want the - * addresses to be allocated in the 0x000-0x0ff region - * modulo 0x400. - * - * Why? Because some silly external IO cards only decode - * the low 10 bits of the IO address. The 0x00-0xff region - * is reserved for motherboard devices that decode all 16 - * bits, so it's ok to allocate at, say, 0x2800-0x28ff, - * but we want to try to avoid allocating at 0x2900-0x2bff - * which might have be mirrored at 0x0100-0x03ff.. - */ -void -pcibios_align_resource(void *data, struct resource *res, - unsigned long size, unsigned long align) -{ - if (res->flags & IORESOURCE_IO) { - unsigned long start = res->start; - - if (start & 0x300) { - start = (start + 0x3ff) & ~0x3ff; - res->start = start; - } - } -} - - -/* - * Handle resources of PCI devices. If the world were perfect, we could - * just allocate all the resource regions and do nothing more. It isn't. - * On the other hand, we cannot just re-allocate all devices, as it would - * require us to know lots of host bridge internals. So we attempt to - * keep as much of the original configuration as possible, but tweak it - * when it's found to be wrong. - * - * Known BIOS problems we have to work around: - * - I/O or memory regions not configured - * - regions configured, but not enabled in the command register - * - bogus I/O addresses above 64K used - * - expansion ROMs left enabled (this may sound harmless, but given - * the fact the PCI specs explicitly allow address decoders to be - * shared between expansion ROMs and other resource regions, it's - * at least dangerous) - * - * Our solution: - * (1) Allocate resources for all buses behind PCI-to-PCI bridges. - * This gives us fixed barriers on where we can allocate. - * (2) Allocate resources for all enabled devices. If there is - * a collision, just mark the resource as unallocated. Also - * disable expansion ROMs during this step. - * (3) Try to allocate resources for disabled devices. If the - * resources were assigned correctly, everything goes well, - * if they weren't, they won't disturb allocation of other - * resources. - * (4) Assign new addresses to resources which were either - * not configured at all or misconfigured. If explicitly - * requested by the user, configure expansion ROM address - * as well. - */ - -static void __init pcibios_allocate_bus_resources(struct list_head *bus_list) -{ - struct pci_bus *bus; - struct pci_dev *dev; - int idx; - struct resource *r, *pr; - - /* Depth-First Search on bus tree */ - list_for_each_entry(bus, bus_list, node) { - if ((dev = bus->self)) { - for (idx = PCI_BRIDGE_RESOURCES; idx < PCI_NUM_RESOURCES; idx++) { - r = &dev->resource[idx]; - if (!r->start) - continue; - pr = pci_find_parent_resource(dev, r); - if (!pr || request_resource(pr, r) < 0) - printk(KERN_ERR "PCI: Cannot allocate resource region %d of bridge %s\n", idx, pci_name(dev)); - } - } - pcibios_allocate_bus_resources(&bus->children); - } -} - -static void __init pcibios_allocate_resources(int pass) -{ - struct pci_dev *dev = NULL; - int idx, disabled; - u16 command; - struct resource *r, *pr; - - for_each_pci_dev(dev) { - pci_read_config_word(dev, PCI_COMMAND, &command); - for(idx = 0; idx < 6; idx++) { - r = &dev->resource[idx]; - if (r->parent) /* Already allocated */ - continue; - if (!r->start) /* Address not assigned at all */ - continue; - if (r->flags & IORESOURCE_IO) - disabled = !(command & PCI_COMMAND_IO); - else - disabled = !(command & PCI_COMMAND_MEMORY); - if (pass == disabled) { - DBG("PCI: Resource %08lx-%08lx (f=%lx, d=%d, p=%d)\n", - r->start, r->end, r->flags, disabled, pass); - pr = pci_find_parent_resource(dev, r); - if (!pr || request_resource(pr, r) < 0) { - printk(KERN_ERR "PCI: Cannot allocate resource region %d of device %s\n", idx, pci_name(dev)); - /* We'll assign a new address later */ - r->end -= r->start; - r->start = 0; - } - } - } - if (!pass) { - r = &dev->resource[PCI_ROM_RESOURCE]; - if (r->flags & IORESOURCE_ROM_ENABLE) { - /* Turn the ROM off, leave the resource region, but keep it unregistered. */ - u32 reg; - DBG("PCI: Switching off ROM of %s\n", pci_name(dev)); - r->flags &= ~IORESOURCE_ROM_ENABLE; - pci_read_config_dword(dev, dev->rom_base_reg, &reg); - pci_write_config_dword(dev, dev->rom_base_reg, reg & ~PCI_ROM_ADDRESS_ENABLE); - } - } - } -} - -static int __init pcibios_assign_resources(void) -{ - struct pci_dev *dev = NULL; - int idx; - struct resource *r; - - for_each_pci_dev(dev) { - int class = dev->class >> 8; - - /* Don't touch classless devices and host bridges */ - if (!class || class == PCI_CLASS_BRIDGE_HOST) - continue; - - for(idx=0; idx<6; idx++) { - r = &dev->resource[idx]; - - /* - * Don't touch IDE controllers and I/O ports of video cards! - */ - if ((class == PCI_CLASS_STORAGE_IDE && idx < 4) || - (class == PCI_CLASS_DISPLAY_VGA && (r->flags & IORESOURCE_IO))) - continue; - - /* - * We shall assign a new address to this resource, either because - * the BIOS forgot to do so or because we have decided the old - * address was unusable for some reason. - */ - if (!r->start && r->end) - pci_assign_resource(dev, idx); - } - - if (pci_probe & PCI_ASSIGN_ROMS) { - r = &dev->resource[PCI_ROM_RESOURCE]; - r->end -= r->start; - r->start = 0; - if (r->end) - pci_assign_resource(dev, PCI_ROM_RESOURCE); - } - } - return 0; -} - -void __init pcibios_resource_survey(void) -{ - DBG("PCI: Allocating resources\n"); - pcibios_allocate_bus_resources(&pci_root_buses); - pcibios_allocate_resources(0); - pcibios_allocate_resources(1); -} - -/** - * called in fs_initcall (one below subsys_initcall), - * give a chance for motherboard reserve resources - */ -fs_initcall(pcibios_assign_resources); - -int pcibios_enable_resources(struct pci_dev *dev, int mask) -{ - u16 cmd, old_cmd; - int idx; - struct resource *r; - - pci_read_config_word(dev, PCI_COMMAND, &cmd); - old_cmd = cmd; - for(idx=0; idx<6; idx++) { - /* Only set up the requested stuff */ - if (!(mask & (1<<idx))) - continue; - - r = &dev->resource[idx]; - if (!r->start && r->end) { - printk(KERN_ERR "PCI: Device %s not available because of resource collisions\n", pci_name(dev)); - return -EINVAL; - } - if (r->flags & IORESOURCE_IO) - cmd |= PCI_COMMAND_IO; - if (r->flags & IORESOURCE_MEM) - cmd |= PCI_COMMAND_MEMORY; - } - if (dev->resource[PCI_ROM_RESOURCE].start) - cmd |= PCI_COMMAND_MEMORY; - if (cmd != old_cmd) { - printk("PCI: Enabling device %s (%04x -> %04x)\n", pci_name(dev), old_cmd, cmd); - pci_write_config_word(dev, PCI_COMMAND, cmd); - } - return 0; -} - -/* - * If we set up a device for bus mastering, we need to check the latency - * timer as certain crappy BIOSes forget to set it properly. - */ -unsigned int pcibios_max_latency = 255; - -void pcibios_set_master(struct pci_dev *dev) -{ - u8 lat; - pci_read_config_byte(dev, PCI_LATENCY_TIMER, &lat); - if (lat < 16) - lat = (64 <= pcibios_max_latency) ? 64 : pcibios_max_latency; - else if (lat > pcibios_max_latency) - lat = pcibios_max_latency; - else - return; - printk(KERN_DEBUG "PCI: Setting latency timer of device %s to %d\n", pci_name(dev), lat); - pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat); -} - -int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, - enum pci_mmap_state mmap_state, int write_combine) -{ - unsigned long prot; - - /* I/O space cannot be accessed via normal processor loads and - * stores on this platform. - */ - if (mmap_state == pci_mmap_io) - return -EINVAL; - - /* Leave vm_pgoff as-is, the PCI space address is the physical - * address on this platform. - */ - vma->vm_flags |= (VM_SHM | VM_LOCKED | VM_IO); - - prot = pgprot_val(vma->vm_page_prot); - if (boot_cpu_data.x86 > 3) - prot |= _PAGE_PCD | _PAGE_PWT; - vma->vm_page_prot = __pgprot(prot); - - /* Write-combine setting is ignored, it is changed via the mtrr - * interfaces on this platform. - */ - if (direct_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, - vma->vm_end - vma->vm_start, - vma->vm_page_prot, DOMID_IO)) - return -EAGAIN; - - return 0; -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/i386/pci/irq.c --- a/linux-2.6-xen-sparse/arch/xen/i386/pci/irq.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,1120 +0,0 @@ -/* - * Low-Level PCI Support for PC -- Routing of Interrupts - * - * (c) 1999--2000 Martin Mares <mj@xxxxxx> - */ - -#include <linux/config.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/init.h> -#include <linux/slab.h> -#include <linux/interrupt.h> -#include <linux/irq.h> -#include <linux/dmi.h> -#include <asm/io.h> -#include <asm/smp.h> -#include <asm/io_apic.h> -#include <asm/hw_irq.h> -#include <linux/acpi.h> - -#include "pci.h" - -#define PIRQ_SIGNATURE (('$' << 0) + ('P' << 8) + ('I' << 16) + ('R' << 24)) -#define PIRQ_VERSION 0x0100 - -static int broken_hp_bios_irq9; -static int acer_tm360_irqrouting; - -static struct irq_routing_table *pirq_table; - -static int pirq_enable_irq(struct pci_dev *dev); - -/* - * Never use: 0, 1, 2 (timer, keyboard, and cascade) - * Avoid using: 13, 14 and 15 (FP error and IDE). - * Penalize: 3, 4, 6, 7, 12 (known ISA uses: serial, floppy, parallel and mouse) - */ -unsigned int pcibios_irq_mask = 0xfff8; - -static int pirq_penalty[16] = { - 1000000, 1000000, 1000000, 1000, 1000, 0, 1000, 1000, - 0, 0, 0, 0, 1000, 100000, 100000, 100000 -}; - -struct irq_router { - char *name; - u16 vendor, device; - int (*get)(struct pci_dev *router, struct pci_dev *dev, int pirq); - int (*set)(struct pci_dev *router, struct pci_dev *dev, int pirq, int new); -}; - -struct irq_router_handler { - u16 vendor; - int (*probe)(struct irq_router *r, struct pci_dev *router, u16 device); -}; - -int (*pcibios_enable_irq)(struct pci_dev *dev) = NULL; - -/* - * Search 0xf0000 -- 0xfffff for the PCI IRQ Routing Table. - */ - -static struct irq_routing_table * __init pirq_find_routing_table(void) -{ - u8 *addr; - struct irq_routing_table *rt; - int i; - u8 sum; - -#ifdef CONFIG_XEN_PRIVILEGED_GUEST - for(addr = (u8 *) isa_bus_to_virt(0xf0000); addr < (u8 *) isa_bus_to_virt(0x100000); addr += 16) { - rt = (struct irq_routing_table *) addr; - if (rt->signature != PIRQ_SIGNATURE || - rt->version != PIRQ_VERSION || - rt->size % 16 || - rt->size < sizeof(struct irq_routing_table)) - continue; - sum = 0; - for(i=0; i<rt->size; i++) - sum += addr[i]; - if (!sum) { - DBG("PCI: Interrupt Routing Table found at 0x%p\n", rt); - return rt; - } - } -#endif - - return NULL; -} - -/* - * If we have a IRQ routing table, use it to search for peer host - * bridges. It's a gross hack, but since there are no other known - * ways how to get a list of buses, we have to go this way. - */ - -static void __init pirq_peer_trick(void) -{ - struct irq_routing_table *rt = pirq_table; - u8 busmap[256]; - int i; - struct irq_info *e; - - memset(busmap, 0, sizeof(busmap)); - for(i=0; i < (rt->size - sizeof(struct irq_routing_table)) / sizeof(struct irq_info); i++) { - e = &rt->slots[i]; -#ifdef DEBUG - { - int j; - DBG("%02x:%02x slot=%02x", e->bus, e->devfn/8, e->slot); - for(j=0; j<4; j++) - DBG(" %d:%02x/%04x", j, e->irq[j].link, e->irq[j].bitmap); - DBG("\n"); - } -#endif - busmap[e->bus] = 1; - } - for(i = 1; i < 256; i++) { - if (!busmap[i] || pci_find_bus(0, i)) - continue; - if (pci_scan_bus(i, &pci_root_ops, NULL)) - printk(KERN_INFO "PCI: Discovered primary peer bus %02x [IRQ]\n", i); - } - pcibios_last_bus = -1; -} - -/* - * Code for querying and setting of IRQ routes on various interrupt routers. - */ - -void eisa_set_level_irq(unsigned int irq) -{ - unsigned char mask = 1 << (irq & 7); - unsigned int port = 0x4d0 + (irq >> 3); - unsigned char val; - static u16 eisa_irq_mask; - - if (irq >= 16 || (1 << irq) & eisa_irq_mask) - return; - - eisa_irq_mask |= (1 << irq); - printk("PCI: setting IRQ %u as level-triggered\n", irq); - val = inb(port); - if (!(val & mask)) { - DBG(" -> edge"); - outb(val | mask, port); - } -} - -/* - * Common IRQ routing practice: nybbles in config space, - * offset by some magic constant. - */ -static unsigned int read_config_nybble(struct pci_dev *router, unsigned offset, unsigned nr) -{ - u8 x; - unsigned reg = offset + (nr >> 1); - - pci_read_config_byte(router, reg, &x); - return (nr & 1) ? (x >> 4) : (x & 0xf); -} - -static void write_config_nybble(struct pci_dev *router, unsigned offset, unsigned nr, unsigned int val) -{ - u8 x; - unsigned reg = offset + (nr >> 1); - - pci_read_config_byte(router, reg, &x); - x = (nr & 1) ? ((x & 0x0f) | (val << 4)) : ((x & 0xf0) | val); - pci_write_config_byte(router, reg, x); -} - -/* - * ALI pirq entries are damn ugly, and completely undocumented. - * This has been figured out from pirq tables, and it's not a pretty - * picture. - */ -static int pirq_ali_get(struct pci_dev *router, struct pci_dev *dev, int pirq) -{ - static unsigned char irqmap[16] = { 0, 9, 3, 10, 4, 5, 7, 6, 1, 11, 0, 12, 0, 14, 0, 15 }; - - return irqmap[read_config_nybble(router, 0x48, pirq-1)]; -} - -static int pirq_ali_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) -{ - static unsigned char irqmap[16] = { 0, 8, 0, 2, 4, 5, 7, 6, 0, 1, 3, 9, 11, 0, 13, 15 }; - unsigned int val = irqmap[irq]; - - if (val) { - write_config_nybble(router, 0x48, pirq-1, val); - return 1; - } - return 0; -} - -/* - * The Intel PIIX4 pirq rules are fairly simple: "pirq" is - * just a pointer to the config space. - */ -static int pirq_piix_get(struct pci_dev *router, struct pci_dev *dev, int pirq) -{ - u8 x; - - pci_read_config_byte(router, pirq, &x); - return (x < 16) ? x : 0; -} - -static int pirq_piix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) -{ - pci_write_config_byte(router, pirq, irq); - return 1; -} - -/* - * The VIA pirq rules are nibble-based, like ALI, - * but without the ugly irq number munging. - * However, PIRQD is in the upper instead of lower 4 bits. - */ -static int pirq_via_get(struct pci_dev *router, struct pci_dev *dev, int pirq) -{ - return read_config_nybble(router, 0x55, pirq == 4 ? 5 : pirq); -} - -static int pirq_via_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) -{ - write_config_nybble(router, 0x55, pirq == 4 ? 5 : pirq, irq); - return 1; -} - -/* - * ITE 8330G pirq rules are nibble-based - * FIXME: pirqmap may be { 1, 0, 3, 2 }, - * 2+3 are both mapped to irq 9 on my system - */ -static int pirq_ite_get(struct pci_dev *router, struct pci_dev *dev, int pirq) -{ - static unsigned char pirqmap[4] = { 1, 0, 2, 3 }; - return read_config_nybble(router,0x43, pirqmap[pirq-1]); -} - -static int pirq_ite_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) -{ - static unsigned char pirqmap[4] = { 1, 0, 2, 3 }; - write_config_nybble(router, 0x43, pirqmap[pirq-1], irq); - return 1; -} - -/* - * OPTI: high four bits are nibble pointer.. - * I wonder what the low bits do? - */ -static int pirq_opti_get(struct pci_dev *router, struct pci_dev *dev, int pirq) -{ - return read_config_nybble(router, 0xb8, pirq >> 4); -} - -static int pirq_opti_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) -{ - write_config_nybble(router, 0xb8, pirq >> 4, irq); - return 1; -} - -/* - * Cyrix: nibble offset 0x5C - * 0x5C bits 7:4 is INTB bits 3:0 is INTA - * 0x5D bits 7:4 is INTD bits 3:0 is INTC - */ -static int pirq_cyrix_get(struct pci_dev *router, struct pci_dev *dev, int pirq) -{ - return read_config_nybble(router, 0x5C, (pirq-1)^1); -} - -static int pirq_cyrix_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) -{ - write_config_nybble(router, 0x5C, (pirq-1)^1, irq); - return 1; -} - -/* - * PIRQ routing for SiS 85C503 router used in several SiS chipsets. - * We have to deal with the following issues here: - * - vendors have different ideas about the meaning of link values - * - some onboard devices (integrated in the chipset) have special - * links and are thus routed differently (i.e. not via PCI INTA-INTD) - * - different revision of the router have a different layout for - * the routing registers, particularly for the onchip devices - * - * For all routing registers the common thing is we have one byte - * per routeable link which is defined as: - * bit 7 IRQ mapping enabled (0) or disabled (1) - * bits [6:4] reserved (sometimes used for onchip devices) - * bits [3:0] IRQ to map to - * allowed: 3-7, 9-12, 14-15 - * reserved: 0, 1, 2, 8, 13 - * - * The config-space registers located at 0x41/0x42/0x43/0x44 are - * always used to route the normal PCI INT A/B/C/D respectively. - * Apparently there are systems implementing PCI routing table using - * link values 0x01-0x04 and others using 0x41-0x44 for PCI INTA..D. - * We try our best to handle both link mappings. - * - * Currently (2003-05-21) it appears most SiS chipsets follow the - * definition of routing registers from the SiS-5595 southbridge. - * According to the SiS 5595 datasheets the revision id's of the - * router (ISA-bridge) should be 0x01 or 0xb0. - * - * Furthermore we've also seen lspci dumps with revision 0x00 and 0xb1. - * Looks like these are used in a number of SiS 5xx/6xx/7xx chipsets. - * They seem to work with the current routing code. However there is - * some concern because of the two USB-OHCI HCs (original SiS 5595 - * had only one). YMMV. - * - * Onchip routing for router rev-id 0x01/0xb0 and probably 0x00/0xb1: - * - * 0x61: IDEIRQ: - * bits [6:5] must be written 01 - * bit 4 channel-select primary (0), secondary (1) - * - * 0x62: USBIRQ: - * bit 6 OHCI function disabled (0), enabled (1) - * - * 0x6a: ACPI/SCI IRQ: bits 4-6 reserved - * - * 0x7e: Data Acq. Module IRQ - bits 4-6 reserved - * - * We support USBIRQ (in addition to INTA-INTD) and keep the - * IDE, ACPI and DAQ routing untouched as set by the BIOS. - * - * Currently the only reported exception is the new SiS 65x chipset - * which includes the SiS 69x southbridge. Here we have the 85C503 - * router revision 0x04 and there are changes in the register layout - * mostly related to the different USB HCs with USB 2.0 support. - * - * Onchip routing for router rev-id 0x04 (try-and-error observation) - * - * 0x60/0x61/0x62/0x63: 1xEHCI and 3xOHCI (companion) USB-HCs - * bit 6-4 are probably unused, not like 5595 - */ - -#define PIRQ_SIS_IRQ_MASK 0x0f -#define PIRQ_SIS_IRQ_DISABLE 0x80 -#define PIRQ_SIS_USB_ENABLE 0x40 - -static int pirq_sis_get(struct pci_dev *router, struct pci_dev *dev, int pirq) -{ - u8 x; - int reg; - - reg = pirq; - if (reg >= 0x01 && reg <= 0x04) - reg += 0x40; - pci_read_config_byte(router, reg, &x); - return (x & PIRQ_SIS_IRQ_DISABLE) ? 0 : (x & PIRQ_SIS_IRQ_MASK); -} - -static int pirq_sis_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) -{ - u8 x; - int reg; - - reg = pirq; - if (reg >= 0x01 && reg <= 0x04) - reg += 0x40; - pci_read_config_byte(router, reg, &x); - x &= ~(PIRQ_SIS_IRQ_MASK | PIRQ_SIS_IRQ_DISABLE); - x |= irq ? irq: PIRQ_SIS_IRQ_DISABLE; - pci_write_config_byte(router, reg, x); - return 1; -} - - -/* - * VLSI: nibble offset 0x74 - educated guess due to routing table and - * config space of VLSI 82C534 PCI-bridge/router (1004:0102) - * Tested on HP OmniBook 800 covering PIRQ 1, 2, 4, 8 for onboard - * devices, PIRQ 3 for non-pci(!) soundchip and (untested) PIRQ 6 - * for the busbridge to the docking station. - */ - -static int pirq_vlsi_get(struct pci_dev *router, struct pci_dev *dev, int pirq) -{ - if (pirq > 8) { - printk(KERN_INFO "VLSI router pirq escape (%d)\n", pirq); - return 0; - } - return read_config_nybble(router, 0x74, pirq-1); -} - -static int pirq_vlsi_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) -{ - if (pirq > 8) { - printk(KERN_INFO "VLSI router pirq escape (%d)\n", pirq); - return 0; - } - write_config_nybble(router, 0x74, pirq-1, irq); - return 1; -} - -/* - * ServerWorks: PCI interrupts mapped to system IRQ lines through Index - * and Redirect I/O registers (0x0c00 and 0x0c01). The Index register - * format is (PCIIRQ## | 0x10), e.g.: PCIIRQ10=0x1a. The Redirect - * register is a straight binary coding of desired PIC IRQ (low nibble). - * - * The 'link' value in the PIRQ table is already in the correct format - * for the Index register. There are some special index values: - * 0x00 for ACPI (SCI), 0x01 for USB, 0x02 for IDE0, 0x04 for IDE1, - * and 0x03 for SMBus. - */ -static int pirq_serverworks_get(struct pci_dev *router, struct pci_dev *dev, int pirq) -{ - outb_p(pirq, 0xc00); - return inb(0xc01) & 0xf; -} - -static int pirq_serverworks_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) -{ - outb_p(pirq, 0xc00); - outb_p(irq, 0xc01); - return 1; -} - -/* Support for AMD756 PCI IRQ Routing - * Jhon H. Caicedo <jhcaiced@xxxxxxxxxxx> - * Jun/21/2001 0.2.0 Release, fixed to use "nybble" functions... (jhcaiced) - * Jun/19/2001 Alpha Release 0.1.0 (jhcaiced) - * The AMD756 pirq rules are nibble-based - * offset 0x56 0-3 PIRQA 4-7 PIRQB - * offset 0x57 0-3 PIRQC 4-7 PIRQD - */ -static int pirq_amd756_get(struct pci_dev *router, struct pci_dev *dev, int pirq) -{ - u8 irq; - irq = 0; - if (pirq <= 4) - { - irq = read_config_nybble(router, 0x56, pirq - 1); - } - printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d get irq : %2d\n", - dev->vendor, dev->device, pirq, irq); - return irq; -} - -static int pirq_amd756_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) -{ - printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d SET irq : %2d\n", - dev->vendor, dev->device, pirq, irq); - if (pirq <= 4) - { - write_config_nybble(router, 0x56, pirq - 1, irq); - } - return 1; -} - -#ifdef CONFIG_PCI_BIOS - -static int pirq_bios_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq) -{ - struct pci_dev *bridge; - int pin = pci_get_interrupt_pin(dev, &bridge); - return pcibios_set_irq_routing(bridge, pin, irq); -} - -#endif - -static __init int intel_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) -{ - static struct pci_device_id pirq_440gx[] = { - { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443GX_0) }, - { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82443GX_2) }, - { }, - }; - - /* 440GX has a proprietary PIRQ router -- don't use it */ - if (pci_dev_present(pirq_440gx)) - return 0; - - switch(device) - { - case PCI_DEVICE_ID_INTEL_82371FB_0: - case PCI_DEVICE_ID_INTEL_82371SB_0: - case PCI_DEVICE_ID_INTEL_82371AB_0: - case PCI_DEVICE_ID_INTEL_82371MX: - case PCI_DEVICE_ID_INTEL_82443MX_0: - case PCI_DEVICE_ID_INTEL_82801AA_0: - case PCI_DEVICE_ID_INTEL_82801AB_0: - case PCI_DEVICE_ID_INTEL_82801BA_0: - case PCI_DEVICE_ID_INTEL_82801BA_10: - case PCI_DEVICE_ID_INTEL_82801CA_0: - case PCI_DEVICE_ID_INTEL_82801CA_12: - case PCI_DEVICE_ID_INTEL_82801DB_0: - case PCI_DEVICE_ID_INTEL_82801E_0: - case PCI_DEVICE_ID_INTEL_82801EB_0: - case PCI_DEVICE_ID_INTEL_ESB_1: - case PCI_DEVICE_ID_INTEL_ICH6_0: - case PCI_DEVICE_ID_INTEL_ICH6_1: - case PCI_DEVICE_ID_INTEL_ICH7_0: - case PCI_DEVICE_ID_INTEL_ICH7_1: - case PCI_DEVICE_ID_INTEL_ICH7_30: - case PCI_DEVICE_ID_INTEL_ICH7_31: - case PCI_DEVICE_ID_INTEL_ESB2_0: - r->name = "PIIX/ICH"; - r->get = pirq_piix_get; - r->set = pirq_piix_set; - return 1; - } - return 0; -} - -static __init int via_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) -{ - /* FIXME: We should move some of the quirk fixup stuff here */ - switch(device) - { - case PCI_DEVICE_ID_VIA_82C586_0: - case PCI_DEVICE_ID_VIA_82C596: - case PCI_DEVICE_ID_VIA_82C686: - case PCI_DEVICE_ID_VIA_8231: - /* FIXME: add new ones for 8233/5 */ - r->name = "VIA"; - r->get = pirq_via_get; - r->set = pirq_via_set; - return 1; - } - return 0; -} - -static __init int vlsi_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) -{ - switch(device) - { - case PCI_DEVICE_ID_VLSI_82C534: - r->name = "VLSI 82C534"; - r->get = pirq_vlsi_get; - r->set = pirq_vlsi_set; - return 1; - } - return 0; -} - - -static __init int serverworks_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) -{ - switch(device) - { - case PCI_DEVICE_ID_SERVERWORKS_OSB4: - case PCI_DEVICE_ID_SERVERWORKS_CSB5: - r->name = "ServerWorks"; - r->get = pirq_serverworks_get; - r->set = pirq_serverworks_set; - return 1; - } - return 0; -} - -static __init int sis_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) -{ - if (device != PCI_DEVICE_ID_SI_503) - return 0; - - r->name = "SIS"; - r->get = pirq_sis_get; - r->set = pirq_sis_set; - return 1; -} - -static __init int cyrix_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) -{ - switch(device) - { - case PCI_DEVICE_ID_CYRIX_5520: - r->name = "NatSemi"; - r->get = pirq_cyrix_get; - r->set = pirq_cyrix_set; - return 1; - } - return 0; -} - -static __init int opti_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) -{ - switch(device) - { - case PCI_DEVICE_ID_OPTI_82C700: - r->name = "OPTI"; - r->get = pirq_opti_get; - r->set = pirq_opti_set; - return 1; - } - return 0; -} - -static __init int ite_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) -{ - switch(device) - { - case PCI_DEVICE_ID_ITE_IT8330G_0: - r->name = "ITE"; - r->get = pirq_ite_get; - r->set = pirq_ite_set; - return 1; - } - return 0; -} - -static __init int ali_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) -{ - switch(device) - { - case PCI_DEVICE_ID_AL_M1533: - case PCI_DEVICE_ID_AL_M1563: - printk("PCI: Using ALI IRQ Router\n"); - r->name = "ALI"; - r->get = pirq_ali_get; - r->set = pirq_ali_set; - return 1; - } - return 0; -} - -static __init int amd_router_probe(struct irq_router *r, struct pci_dev *router, u16 device) -{ - switch(device) - { - case PCI_DEVICE_ID_AMD_VIPER_740B: - r->name = "AMD756"; - break; - case PCI_DEVICE_ID_AMD_VIPER_7413: - r->name = "AMD766"; - break; - case PCI_DEVICE_ID_AMD_VIPER_7443: - r->name = "AMD768"; - break; - default: - return 0; - } - r->get = pirq_amd756_get; - r->set = pirq_amd756_set; - return 1; -} - -static __initdata struct irq_router_handler pirq_routers[] = { - { PCI_VENDOR_ID_INTEL, intel_router_probe }, - { PCI_VENDOR_ID_AL, ali_router_probe }, - { PCI_VENDOR_ID_ITE, ite_router_probe }, - { PCI_VENDOR_ID_VIA, via_router_probe }, - { PCI_VENDOR_ID_OPTI, opti_router_probe }, - { PCI_VENDOR_ID_SI, sis_router_probe }, - { PCI_VENDOR_ID_CYRIX, cyrix_router_probe }, - { PCI_VENDOR_ID_VLSI, vlsi_router_probe }, - { PCI_VENDOR_ID_SERVERWORKS, serverworks_router_probe }, - { PCI_VENDOR_ID_AMD, amd_router_probe }, - /* Someone with docs needs to add the ATI Radeon IGP */ - { 0, NULL } -}; -static struct irq_router pirq_router; -static struct pci_dev *pirq_router_dev; - - -/* - * FIXME: should we have an option to say "generic for - * chipset" ? - */ - -static void __init pirq_find_router(struct irq_router *r) -{ - struct irq_routing_table *rt = pirq_table; - struct irq_router_handler *h; - -#ifdef CONFIG_PCI_BIOS - if (!rt->signature) { - printk(KERN_INFO "PCI: Using BIOS for IRQ routing\n"); - r->set = pirq_bios_set; - r->name = "BIOS"; - return; - } -#endif - - /* Default unless a driver reloads it */ - r->name = "default"; - r->get = NULL; - r->set = NULL; - - DBG("PCI: Attempting to find IRQ router for %04x:%04x\n", - rt->rtr_vendor, rt->rtr_device); - - pirq_router_dev = pci_find_slot(rt->rtr_bus, rt->rtr_devfn); - if (!pirq_router_dev) { - DBG("PCI: Interrupt router not found at %02x:%02x\n", rt->rtr_bus, rt->rtr_devfn); - return; - } - - for( h = pirq_routers; h->vendor; h++) { - /* First look for a router match */ - if (rt->rtr_vendor == h->vendor && h->probe(r, pirq_router_dev, rt->rtr_device)) - break; - /* Fall back to a device match */ - if (pirq_router_dev->vendor == h->vendor && h->probe(r, pirq_router_dev, pirq_router_dev->device)) - break; - } - printk(KERN_INFO "PCI: Using IRQ router %s [%04x/%04x] at %s\n", - pirq_router.name, - pirq_router_dev->vendor, - pirq_router_dev->device, - pci_name(pirq_router_dev)); -} - -static struct irq_info *pirq_get_info(struct pci_dev *dev) -{ - struct irq_routing_table *rt = pirq_table; - int entries = (rt->size - sizeof(struct irq_routing_table)) / sizeof(struct irq_info); - struct irq_info *info; - - for (info = rt->slots; entries--; info++) - if (info->bus == dev->bus->number && PCI_SLOT(info->devfn) == PCI_SLOT(dev->devfn)) - return info; - return NULL; -} - -static int pcibios_lookup_irq(struct pci_dev *dev, int assign) -{ - u8 pin; - struct irq_info *info; - int i, pirq, newirq; - int irq = 0; - u32 mask; - struct irq_router *r = &pirq_router; - struct pci_dev *dev2 = NULL; - char *msg = NULL; - - /* Find IRQ pin */ - pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); - if (!pin) { - DBG(" -> no interrupt pin\n"); - return 0; - } - pin = pin - 1; - - /* Find IRQ routing entry */ - - if (!pirq_table) - return 0; - - DBG("IRQ for %s[%c]", pci_name(dev), 'A' + pin); - info = pirq_get_info(dev); - if (!info) { - DBG(" -> not found in routing table\n"); - return 0; - } - pirq = info->irq[pin].link; - mask = info->irq[pin].bitmap; - if (!pirq) { - DBG(" -> not routed\n"); - return 0; - } - DBG(" -> PIRQ %02x, mask %04x, excl %04x", pirq, mask, pirq_table->exclusive_irqs); - mask &= pcibios_irq_mask; - - /* Work around broken HP Pavilion Notebooks which assign USB to - IRQ 9 even though it is actually wired to IRQ 11 */ - - if (broken_hp_bios_irq9 && pirq == 0x59 && dev->irq == 9) { - dev->irq = 11; - pci_write_config_byte(dev, PCI_INTERRUPT_LINE, 11); - r->set(pirq_router_dev, dev, pirq, 11); - } - - /* same for Acer Travelmate 360, but with CB and irq 11 -> 10 */ - if (acer_tm360_irqrouting && dev->irq == 11 && dev->vendor == PCI_VENDOR_ID_O2) { - pirq = 0x68; - mask = 0x400; - dev->irq = r->get(pirq_router_dev, dev, pirq); - pci_write_config_byte(dev, PCI_INTERRUPT_LINE, dev->irq); - } - - /* - * Find the best IRQ to assign: use the one - * reported by the device if possible. - */ - newirq = dev->irq; - if (!((1 << newirq) & mask)) { - if ( pci_probe & PCI_USE_PIRQ_MASK) newirq = 0; - else printk(KERN_WARNING "PCI: IRQ %i for device %s doesn't match PIRQ mask - try pci=usepirqmask\n", newirq, pci_name(dev)); - } - if (!newirq && assign) { - for (i = 0; i < 16; i++) { - if (!(mask & (1 << i))) - continue; - if (pirq_penalty[i] < pirq_penalty[newirq] && can_request_irq(i, SA_SHIRQ)) - newirq = i; - } - } - DBG(" -> newirq=%d", newirq); - - /* Check if it is hardcoded */ - if ((pirq & 0xf0) == 0xf0) { - irq = pirq & 0xf; - DBG(" -> hardcoded IRQ %d\n", irq); - msg = "Hardcoded"; - } else if ( r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \ - ((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask)) ) { - DBG(" -> got IRQ %d\n", irq); - msg = "Found"; - } else if (newirq && r->set && (dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) { - DBG(" -> assigning IRQ %d", newirq); - if (r->set(pirq_router_dev, dev, pirq, newirq)) { - eisa_set_level_irq(newirq); - DBG(" ... OK\n"); - msg = "Assigned"; - irq = newirq; - } - } - - if (!irq) { - DBG(" ... failed\n"); - if (newirq && mask == (1 << newirq)) { - msg = "Guessed"; - irq = newirq; - } else - return 0; - } - printk(KERN_INFO "PCI: %s IRQ %d for device %s\n", msg, irq, pci_name(dev)); - - /* Update IRQ for all devices with the same pirq value */ - while ((dev2 = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev2)) != NULL) { - pci_read_config_byte(dev2, PCI_INTERRUPT_PIN, &pin); - if (!pin) - continue; - pin--; - info = pirq_get_info(dev2); - if (!info) - continue; - if (info->irq[pin].link == pirq) { - /* We refuse to override the dev->irq information. Give a warning! */ - if ( dev2->irq && dev2->irq != irq && \ - (!(pci_probe & PCI_USE_PIRQ_MASK) || \ - ((1 << dev2->irq) & mask)) ) { -#ifndef CONFIG_PCI_MSI - printk(KERN_INFO "IRQ routing conflict for %s, have irq %d, want irq %d\n", - pci_name(dev2), dev2->irq, irq); -#endif - continue; - } - dev2->irq = irq; - pirq_penalty[irq]++; - if (dev != dev2) - printk(KERN_INFO "PCI: Sharing IRQ %d with %s\n", irq, pci_name(dev2)); - } - } - return 1; -} - -static void __init pcibios_fixup_irqs(void) -{ - struct pci_dev *dev = NULL; - u8 pin; - - DBG("PCI: IRQ fixup\n"); - while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { - /* - * If the BIOS has set an out of range IRQ number, just ignore it. - * Also keep track of which IRQ's are already in use. - */ - if (dev->irq >= 16) { - DBG("%s: ignoring bogus IRQ %d\n", pci_name(dev), dev->irq); - dev->irq = 0; - } - /* If the IRQ is already assigned to a PCI device, ignore its ISA use penalty */ - if (pirq_penalty[dev->irq] >= 100 && pirq_penalty[dev->irq] < 100000) - pirq_penalty[dev->irq] = 0; - pirq_penalty[dev->irq]++; - } - - dev = NULL; - while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { - pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); -#ifdef CONFIG_X86_IO_APIC - /* - * Recalculate IRQ numbers if we use the I/O APIC. - */ - if (io_apic_assign_pci_irqs) - { - int irq; - - if (pin) { - pin--; /* interrupt pins are numbered starting from 1 */ - irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, PCI_SLOT(dev->devfn), pin); - /* - * Busses behind bridges are typically not listed in the MP-table. - * In this case we have to look up the IRQ based on the parent bus, - * parent slot, and pin number. The SMP code detects such bridged - * busses itself so we should get into this branch reliably. - */ - if (irq < 0 && dev->bus->parent) { /* go back to the bridge */ - struct pci_dev * bridge = dev->bus->self; - - pin = (pin + PCI_SLOT(dev->devfn)) % 4; - irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, - PCI_SLOT(bridge->devfn), pin); - if (irq >= 0) - printk(KERN_WARNING "PCI: using PPB %s[%c] to get irq %d\n", - pci_name(bridge), 'A' + pin, irq); - } - if (irq >= 0) { - if (use_pci_vector() && - !platform_legacy_irq(irq)) - irq = IO_APIC_VECTOR(irq); - - printk(KERN_INFO "PCI->APIC IRQ transform: %s[%c] -> IRQ %d\n", - pci_name(dev), 'A' + pin, irq); - dev->irq = irq; - } - } - } -#endif - /* - * Still no IRQ? Try to lookup one... - */ - if (pin && !dev->irq) - pcibios_lookup_irq(dev, 0); - } -} - -/* - * Work around broken HP Pavilion Notebooks which assign USB to - * IRQ 9 even though it is actually wired to IRQ 11 - */ -static int __init fix_broken_hp_bios_irq9(struct dmi_system_id *d) -{ - if (!broken_hp_bios_irq9) { - broken_hp_bios_irq9 = 1; - printk(KERN_INFO "%s detected - fixing broken IRQ routing\n", d->ident); - } - return 0; -} - -/* - * Work around broken Acer TravelMate 360 Notebooks which assign - * Cardbus to IRQ 11 even though it is actually wired to IRQ 10 - */ -static int __init fix_acer_tm360_irqrouting(struct dmi_system_id *d) -{ - if (!acer_tm360_irqrouting) { - acer_tm360_irqrouting = 1; - printk(KERN_INFO "%s detected - fixing broken IRQ routing\n", d->ident); - } - return 0; -} - -static struct dmi_system_id __initdata pciirq_dmi_table[] = { - { - .callback = fix_broken_hp_bios_irq9, - .ident = "HP Pavilion N5400 Series Laptop", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), - DMI_MATCH(DMI_BIOS_VERSION, "GE.M1.03"), - DMI_MATCH(DMI_PRODUCT_VERSION, "HP Pavilion Notebook Model GE"), - DMI_MATCH(DMI_BOARD_VERSION, "OmniBook N32N-736"), - }, - }, - { - .callback = fix_acer_tm360_irqrouting, - .ident = "Acer TravelMate 36x Laptop", - .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "Acer"), - DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 360"), - }, - }, - { } -}; - -static int __init pcibios_irq_init(void) -{ - DBG("PCI: IRQ init\n"); - - if (pcibios_enable_irq || raw_pci_ops == NULL) - return 0; - - dmi_check_system(pciirq_dmi_table); - - pirq_table = pirq_find_routing_table(); - -#ifdef CONFIG_PCI_BIOS - if (!pirq_table && (pci_probe & PCI_BIOS_IRQ_SCAN)) - pirq_table = pcibios_get_irq_routing_table(); -#endif - if (pirq_table) { - pirq_peer_trick(); - pirq_find_router(&pirq_router); - if (pirq_table->exclusive_irqs) { - int i; - for (i=0; i<16; i++) - if (!(pirq_table->exclusive_irqs & (1 << i))) - pirq_penalty[i] += 100; - } - /* If we're using the I/O APIC, avoid using the PCI IRQ routing table */ - if (io_apic_assign_pci_irqs) - pirq_table = NULL; - } - - pcibios_enable_irq = pirq_enable_irq; - - pcibios_fixup_irqs(); - return 0; -} - -subsys_initcall(pcibios_irq_init); - - -static void pirq_penalize_isa_irq(int irq) -{ - /* - * If any ISAPnP device reports an IRQ in its list of possible - * IRQ's, we try to avoid assigning it to PCI devices. - */ - if (irq < 16) - pirq_penalty[irq] += 100; -} - -void pcibios_penalize_isa_irq(int irq) -{ -#ifdef CONFIG_ACPI_PCI - if (!acpi_noirq) - acpi_penalize_isa_irq(irq); - else -#endif - pirq_penalize_isa_irq(irq); -} - -static int pirq_enable_irq(struct pci_dev *dev) -{ - u8 pin; - struct pci_dev *temp_dev; - - pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); - if (pin && !pcibios_lookup_irq(dev, 1) && !dev->irq) { - char *msg = ""; - - pin--; /* interrupt pins are numbered starting from 1 */ - - if (io_apic_assign_pci_irqs) { - int irq; - - irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, PCI_SLOT(dev->devfn), pin); - /* - * Busses behind bridges are typically not listed in the MP-table. - * In this case we have to look up the IRQ based on the parent bus, - * parent slot, and pin number. The SMP code detects such bridged - * busses itself so we should get into this branch reliably. - */ - temp_dev = dev; - while (irq < 0 && dev->bus->parent) { /* go back to the bridge */ - struct pci_dev * bridge = dev->bus->self; - - pin = (pin + PCI_SLOT(dev->devfn)) % 4; - irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number, - PCI_SLOT(bridge->devfn), pin); - if (irq >= 0) - printk(KERN_WARNING "PCI: using PPB %s[%c] to get irq %d\n", - pci_name(bridge), 'A' + pin, irq); - dev = bridge; - } - dev = temp_dev; - if (irq >= 0) { -#ifdef CONFIG_PCI_MSI - if (!platform_legacy_irq(irq)) - irq = IO_APIC_VECTOR(irq); -#endif - printk(KERN_INFO "PCI->APIC IRQ transform: %s[%c] -> IRQ %d\n", - pci_name(dev), 'A' + pin, irq); - dev->irq = irq; - return 0; - } else - msg = " Probably buggy MP table."; - } else if (pci_probe & PCI_BIOS_IRQ_SCAN) - msg = ""; - else - msg = " Please try using pci=biosirq."; - - /* With IDE legacy devices the IRQ lookup failure is not a problem.. */ - if (dev->class >> 8 == PCI_CLASS_STORAGE_IDE && !(dev->class & 0x5)) - return 0; - - printk(KERN_WARNING "PCI: No IRQ known for interrupt pin %c of device %s.%s\n", - 'A' + pin, pci_name(dev), msg); - } - return 0; -} - -int pci_vector_resources(int last, int nr_released) -{ - int count = nr_released; - - int next = last; - int offset = (last % 8); - - while (next < FIRST_SYSTEM_VECTOR) { - next += 8; -#ifdef CONFIG_X86_64 - if (next == IA32_SYSCALL_VECTOR) - continue; -#else - if (next == SYSCALL_VECTOR) - continue; -#endif - count++; - if (next >= FIRST_SYSTEM_VECTOR) { - if (offset%8) { - next = FIRST_DEVICE_VECTOR + offset; - offset++; - continue; - } - count--; - } - } - - return count; -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/kernel/Makefile --- a/linux-2.6-xen-sparse/arch/xen/kernel/Makefile Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,18 +0,0 @@ -# -# Makefile for the linux kernel. -# - -XENARCH := $(subst ",,$(CONFIG_XENARCH)) - -CPPFLAGS_vmlinux.lds += -U$(XENARCH) - -$(obj)/vmlinux.lds.S: - @ln -fsn $(srctree)/arch/$(XENARCH)/kernel/vmlinux.lds.S $@ - -extra-y += vmlinux.lds - -obj-y := evtchn.o reboot.o gnttab.o features.o - -obj-$(CONFIG_PROC_FS) += xen_proc.o -obj-$(CONFIG_NET) += skbuff.o -obj-$(CONFIG_SMP) += smpboot.o diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/kernel/evtchn.c --- a/linux-2.6-xen-sparse/arch/xen/kernel/evtchn.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,820 +0,0 @@ -/****************************************************************************** - * evtchn.c - * - * Communication via Xen event channels. - * - * Copyright (c) 2002-2005, K A Fraser - * - * This file may be distributed separately from the Linux kernel, or - * incorporated into other software packages, subject to the following license: - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this source file (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, copy, modify, - * merge, publish, distribute, sublicense, and/or sell copies of the Software, - * and to permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - */ - -#include <linux/config.h> -#include <linux/module.h> -#include <linux/irq.h> -#include <linux/interrupt.h> -#include <linux/sched.h> -#include <linux/kernel_stat.h> -#include <linux/version.h> -#include <asm/atomic.h> -#include <asm/system.h> -#include <asm/ptrace.h> -#include <asm/synch_bitops.h> -#include <asm-xen/xen-public/event_channel.h> -#include <asm-xen/xen-public/physdev.h> -#include <asm/hypervisor.h> -#include <asm-xen/evtchn.h> -#include <linux/mc146818rtc.h> /* RTC_IRQ */ - -/* - * This lock protects updates to the following mapping and reference-count - * arrays. The lock does not need to be acquired to read the mapping tables. - */ -static spinlock_t irq_mapping_update_lock; - -/* IRQ <-> event-channel mappings. */ -static int evtchn_to_irq[NR_EVENT_CHANNELS]; - -/* Packed IRQ information: binding type, sub-type index, and event channel. */ -static u32 irq_info[NR_IRQS]; -/* Binding types. */ -enum { IRQT_UNBOUND, IRQT_PIRQ, IRQT_VIRQ, IRQT_IPI, IRQT_EVTCHN }; -/* Constructor for packed IRQ information. */ -#define mk_irq_info(type, index, evtchn) \ - (((u32)(type) << 24) | ((u32)(index) << 16) | (u32)(evtchn)) -/* Convenient shorthand for packed representation of an unbound IRQ. */ -#define IRQ_UNBOUND mk_irq_info(IRQT_UNBOUND, 0, 0) -/* Accessor macros for packed IRQ information. */ -#define evtchn_from_irq(irq) ((u16)(irq_info[irq])) -#define index_from_irq(irq) ((u8)(irq_info[irq] >> 16)) -#define type_from_irq(irq) ((u8)(irq_info[irq] >> 24)) - -/* IRQ <-> VIRQ mapping. */ -DEFINE_PER_CPU(int, virq_to_irq[NR_VIRQS]); - -/* IRQ <-> IPI mapping. */ -#ifndef NR_IPIS -#define NR_IPIS 1 -#endif -DEFINE_PER_CPU(int, ipi_to_irq[NR_IPIS]); - -/* Reference counts for bindings to IRQs. */ -static int irq_bindcount[NR_IRQS]; - -/* Bitmap indicating which PIRQs require Xen to be notified on unmask. */ -static unsigned long pirq_needs_unmask_notify[NR_PIRQS/sizeof(unsigned long)]; - -#ifdef CONFIG_SMP - -static u8 cpu_evtchn[NR_EVENT_CHANNELS]; -static unsigned long cpu_evtchn_mask[NR_CPUS][NR_EVENT_CHANNELS/BITS_PER_LONG]; - -#define active_evtchns(cpu,sh,idx) \ - ((sh)->evtchn_pending[idx] & \ - cpu_evtchn_mask[cpu][idx] & \ - ~(sh)->evtchn_mask[idx]) - -static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu) -{ - clear_bit(chn, (unsigned long *)cpu_evtchn_mask[cpu_evtchn[chn]]); - set_bit(chn, (unsigned long *)cpu_evtchn_mask[cpu]); - cpu_evtchn[chn] = cpu; -} - -static void init_evtchn_cpu_bindings(void) -{ - /* By default all event channels notify CPU#0. */ - memset(cpu_evtchn, 0, sizeof(cpu_evtchn)); - memset(cpu_evtchn_mask[0], ~0, sizeof(cpu_evtchn_mask[0])); -} - -#define cpu_from_evtchn(evtchn) (cpu_evtchn[evtchn]) - -#else - -#define active_evtchns(cpu,sh,idx) \ - ((sh)->evtchn_pending[idx] & \ - ~(sh)->evtchn_mask[idx]) -#define bind_evtchn_to_cpu(chn,cpu) ((void)0) -#define init_evtchn_cpu_bindings() ((void)0) -#define cpu_from_evtchn(evtchn) (0) - -#endif - -/* Upcall to generic IRQ layer. */ -#ifdef CONFIG_X86 -extern fastcall unsigned int do_IRQ(struct pt_regs *regs); -#if defined (__i386__) -#define IRQ_REG orig_eax -#elif defined (__x86_64__) -#define IRQ_REG orig_rax -#endif -#define do_IRQ(irq, regs) do { \ - (regs)->IRQ_REG = (irq); \ - do_IRQ((regs)); \ -} while (0) -#endif - -/* Xen will never allocate port zero for any purpose. */ -#define VALID_EVTCHN(chn) ((chn) != 0) - -/* - * Force a proper event-channel callback from Xen after clearing the - * callback mask. We do this in a very simple manner, by making a call - * down into Xen. The pending flag will be checked by Xen on return. - */ -void force_evtchn_callback(void) -{ - (void)HYPERVISOR_xen_version(0, NULL); -} -EXPORT_SYMBOL(force_evtchn_callback); - -/* NB. Interrupts are disabled on entry. */ -asmlinkage void evtchn_do_upcall(struct pt_regs *regs) -{ - unsigned long l1, l2; - unsigned int l1i, l2i, port; - int irq, cpu = smp_processor_id(); - shared_info_t *s = HYPERVISOR_shared_info; - vcpu_info_t *vcpu_info = &s->vcpu_info[cpu]; - - vcpu_info->evtchn_upcall_pending = 0; - - /* NB. No need for a barrier here -- XCHG is a barrier on x86. */ - l1 = xchg(&vcpu_info->evtchn_pending_sel, 0); - while (l1 != 0) { - l1i = __ffs(l1); - l1 &= ~(1UL << l1i); - - while ((l2 = active_evtchns(cpu, s, l1i)) != 0) { - l2i = __ffs(l2); - - port = (l1i * BITS_PER_LONG) + l2i; - if ((irq = evtchn_to_irq[port]) != -1) - do_IRQ(irq, regs); - else - evtchn_device_upcall(port); - } - } -} -EXPORT_SYMBOL(evtchn_do_upcall); - -static int find_unbound_irq(void) -{ - int irq; - - for (irq = 0; irq < NR_IRQS; irq++) - if (irq_bindcount[irq] == 0) - break; - - if (irq == NR_IRQS) - panic("No available IRQ to bind to: increase NR_IRQS!\n"); - - return irq; -} - -static int bind_evtchn_to_irq(unsigned int evtchn) -{ - int irq; - - spin_lock(&irq_mapping_update_lock); - - if ((irq = evtchn_to_irq[evtchn]) == -1) { - irq = find_unbound_irq(); - evtchn_to_irq[evtchn] = irq; - irq_info[irq] = mk_irq_info(IRQT_EVTCHN, 0, evtchn); - } - - irq_bindcount[irq]++; - - spin_unlock(&irq_mapping_update_lock); - - return irq; -} - -static int bind_virq_to_irq(unsigned int virq, unsigned int cpu) -{ - evtchn_op_t op = { .cmd = EVTCHNOP_bind_virq }; - int evtchn, irq; - - spin_lock(&irq_mapping_update_lock); - - if ((irq = per_cpu(virq_to_irq, cpu)[virq]) == -1) { - op.u.bind_virq.virq = virq; - op.u.bind_virq.vcpu = cpu; - BUG_ON(HYPERVISOR_event_channel_op(&op) != 0); - evtchn = op.u.bind_virq.port; - - irq = find_unbound_irq(); - evtchn_to_irq[evtchn] = irq; - irq_info[irq] = mk_irq_info(IRQT_VIRQ, virq, evtchn); - - per_cpu(virq_to_irq, cpu)[virq] = irq; - - bind_evtchn_to_cpu(evtchn, cpu); - } - - irq_bindcount[irq]++; - - spin_unlock(&irq_mapping_update_lock); - - return irq; -} - -static int bind_ipi_to_irq(unsigned int ipi, unsigned int cpu) -{ - evtchn_op_t op = { .cmd = EVTCHNOP_bind_ipi }; - int evtchn, irq; - - spin_lock(&irq_mapping_update_lock); - - if ((irq = per_cpu(ipi_to_irq, cpu)[ipi]) == -1) { - op.u.bind_ipi.vcpu = cpu; - BUG_ON(HYPERVISOR_event_channel_op(&op) != 0); - evtchn = op.u.bind_ipi.port; - - irq = find_unbound_irq(); - evtchn_to_irq[evtchn] = irq; - irq_info[irq] = mk_irq_info(IRQT_IPI, ipi, evtchn); - - per_cpu(ipi_to_irq, cpu)[ipi] = irq; - - bind_evtchn_to_cpu(evtchn, cpu); - } - - irq_bindcount[irq]++; - - spin_unlock(&irq_mapping_update_lock); - - return irq; -} - -static void unbind_from_irq(unsigned int irq) -{ - evtchn_op_t op = { .cmd = EVTCHNOP_close }; - int evtchn = evtchn_from_irq(irq); - - spin_lock(&irq_mapping_update_lock); - - if ((--irq_bindcount[irq] == 0) && VALID_EVTCHN(evtchn)) { - op.u.close.port = evtchn; - BUG_ON(HYPERVISOR_event_channel_op(&op) != 0); - - switch (type_from_irq(irq)) { - case IRQT_VIRQ: - per_cpu(virq_to_irq, cpu_from_evtchn(evtchn)) - [index_from_irq(irq)] = -1; - break; - case IRQT_IPI: - per_cpu(ipi_to_irq, cpu_from_evtchn(evtchn)) - [index_from_irq(irq)] = -1; - break; - default: - break; - } - - /* Closed ports are implicitly re-bound to VCPU0. */ - bind_evtchn_to_cpu(evtchn, 0); - - evtchn_to_irq[evtchn] = -1; - irq_info[irq] = IRQ_UNBOUND; - } - - spin_unlock(&irq_mapping_update_lock); -} - -int bind_evtchn_to_irqhandler( - unsigned int evtchn, - irqreturn_t (*handler)(int, void *, struct pt_regs *), - unsigned long irqflags, - const char *devname, - void *dev_id) -{ - unsigned int irq; - int retval; - - irq = bind_evtchn_to_irq(evtchn); - retval = request_irq(irq, handler, irqflags, devname, dev_id); - if (retval != 0) { - unbind_from_irq(irq); - return retval; - } - - return irq; -} -EXPORT_SYMBOL(bind_evtchn_to_irqhandler); - -int bind_virq_to_irqhandler( - unsigned int virq, - unsigned int cpu, - irqreturn_t (*handler)(int, void *, struct pt_regs *), - unsigned long irqflags, - const char *devname, - void *dev_id) -{ - unsigned int irq; - int retval; - - irq = bind_virq_to_irq(virq, cpu); - retval = request_irq(irq, handler, irqflags, devname, dev_id); - if (retval != 0) { - unbind_from_irq(irq); - return retval; - } - - return irq; -} -EXPORT_SYMBOL(bind_virq_to_irqhandler); - -int bind_ipi_to_irqhandler( - unsigned int ipi, - unsigned int cpu, - irqreturn_t (*handler)(int, void *, struct pt_regs *), - unsigned long irqflags, - const char *devname, - void *dev_id) -{ - unsigned int irq; - int retval; - - irq = bind_ipi_to_irq(ipi, cpu); - retval = request_irq(irq, handler, irqflags, devname, dev_id); - if (retval != 0) { - unbind_from_irq(irq); - return retval; - } - - return irq; -} -EXPORT_SYMBOL(bind_ipi_to_irqhandler); - -void unbind_from_irqhandler(unsigned int irq, void *dev_id) -{ - free_irq(irq, dev_id); - unbind_from_irq(irq); -} -EXPORT_SYMBOL(unbind_from_irqhandler); - -#ifdef CONFIG_SMP -static void do_nothing_function(void *ign) -{ -} -#endif - -/* Rebind an evtchn so that it gets delivered to a specific cpu */ -static void rebind_irq_to_cpu(unsigned irq, unsigned tcpu) -{ - evtchn_op_t op = { .cmd = EVTCHNOP_bind_vcpu }; - int evtchn; - - spin_lock(&irq_mapping_update_lock); - - evtchn = evtchn_from_irq(irq); - if (!VALID_EVTCHN(evtchn)) { - spin_unlock(&irq_mapping_update_lock); - return; - } - - /* Send future instances of this interrupt to other vcpu. */ - op.u.bind_vcpu.port = evtchn; - op.u.bind_vcpu.vcpu = tcpu; - - /* - * If this fails, it usually just indicates that we're dealing with a - * virq or IPI channel, which don't actually need to be rebound. Ignore - * it, but don't do the xenlinux-level rebind in that case. - */ - if (HYPERVISOR_event_channel_op(&op) >= 0) - bind_evtchn_to_cpu(evtchn, tcpu); - - spin_unlock(&irq_mapping_update_lock); - - /* - * Now send the new target processor a NOP IPI. When this returns, it - * will check for any pending interrupts, and so service any that got - * delivered to the wrong processor by mistake. - * - * XXX: The only time this is called with interrupts disabled is from - * the hotplug/hotunplug path. In that case, all cpus are stopped with - * interrupts disabled, and the missed interrupts will be picked up - * when they start again. This is kind of a hack. - */ - if (!irqs_disabled()) - smp_call_function(do_nothing_function, NULL, 0, 0); -} - - -static void set_affinity_irq(unsigned irq, cpumask_t dest) -{ - unsigned tcpu = first_cpu(dest); - rebind_irq_to_cpu(irq, tcpu); -} - -/* - * Interface to generic handling in irq.c - */ - -static unsigned int startup_dynirq(unsigned int irq) -{ - int evtchn = evtchn_from_irq(irq); - - if (VALID_EVTCHN(evtchn)) - unmask_evtchn(evtchn); - return 0; -} - -static void shutdown_dynirq(unsigned int irq) -{ - int evtchn = evtchn_from_irq(irq); - - if (VALID_EVTCHN(evtchn)) - mask_evtchn(evtchn); -} - -static void enable_dynirq(unsigned int irq) -{ - int evtchn = evtchn_from_irq(irq); - - if (VALID_EVTCHN(evtchn)) - unmask_evtchn(evtchn); -} - -static void disable_dynirq(unsigned int irq) -{ - int evtchn = evtchn_from_irq(irq); - - if (VALID_EVTCHN(evtchn)) - mask_evtchn(evtchn); -} - -static void ack_dynirq(unsigned int irq) -{ - int evtchn = evtchn_from_irq(irq); - - if (VALID_EVTCHN(evtchn)) { - mask_evtchn(evtchn); - clear_evtchn(evtchn); - } -} - -static void end_dynirq(unsigned int irq) -{ - int evtchn = evtchn_from_irq(irq); - - if (VALID_EVTCHN(evtchn) && !(irq_desc[irq].status & IRQ_DISABLED)) - unmask_evtchn(evtchn); -} - -static struct hw_interrupt_type dynirq_type = { - "Dynamic-irq", - startup_dynirq, - shutdown_dynirq, - enable_dynirq, - disable_dynirq, - ack_dynirq, - end_dynirq, - set_affinity_irq -}; - -static inline void pirq_unmask_notify(int pirq) -{ - physdev_op_t op; - if (unlikely(test_bit(pirq, &pirq_needs_unmask_notify[0]))) { - op.cmd = PHYSDEVOP_IRQ_UNMASK_NOTIFY; - (void)HYPERVISOR_physdev_op(&op); - } -} - -static inline void pirq_query_unmask(int pirq) -{ - physdev_op_t op; - op.cmd = PHYSDEVOP_IRQ_STATUS_QUERY; - op.u.irq_status_query.irq = pirq; - (void)HYPERVISOR_physdev_op(&op); - clear_bit(pirq, &pirq_needs_unmask_notify[0]); - if (op.u.irq_status_query.flags & PHYSDEVOP_IRQ_NEEDS_UNMASK_NOTIFY) - set_bit(pirq, &pirq_needs_unmask_notify[0]); -} - -/* - * On startup, if there is no action associated with the IRQ then we are - * probing. In this case we should not share with others as it will confuse us. - */ -#define probing_irq(_irq) (irq_desc[(_irq)].action == NULL) - -static unsigned int startup_pirq(unsigned int irq) -{ - evtchn_op_t op = { .cmd = EVTCHNOP_bind_pirq }; - int evtchn = evtchn_from_irq(irq); - - if (VALID_EVTCHN(evtchn)) - goto out; - - op.u.bind_pirq.pirq = irq; - /* NB. We are happy to share unless we are probing. */ - op.u.bind_pirq.flags = probing_irq(irq) ? 0 : BIND_PIRQ__WILL_SHARE; - if (HYPERVISOR_event_channel_op(&op) != 0) { - if ( !probing_irq(irq) ) - printk(KERN_INFO "Failed to obtain physical " - "IRQ %d\n", irq); - return 0; - } - evtchn = op.u.bind_pirq.port; - - pirq_query_unmask(irq_to_pirq(irq)); - - bind_evtchn_to_cpu(evtchn, 0); - evtchn_to_irq[evtchn] = irq; - irq_info[irq] = mk_irq_info(IRQT_PIRQ, irq, evtchn); - - out: - unmask_evtchn(evtchn); - pirq_unmask_notify(irq_to_pirq(irq)); - - return 0; -} - -static void shutdown_pirq(unsigned int irq) -{ - evtchn_op_t op = { .cmd = EVTCHNOP_close }; - int evtchn = evtchn_from_irq(irq); - - if (!VALID_EVTCHN(evtchn)) - return; - - mask_evtchn(evtchn); - - op.u.close.port = evtchn; - BUG_ON(HYPERVISOR_event_channel_op(&op) != 0); - - bind_evtchn_to_cpu(evtchn, 0); - evtchn_to_irq[evtchn] = -1; - irq_info[irq] = IRQ_UNBOUND; -} - -static void enable_pirq(unsigned int irq) -{ - int evtchn = evtchn_from_irq(irq); - - if (VALID_EVTCHN(evtchn)) { - unmask_evtchn(evtchn); - pirq_unmask_notify(irq_to_pirq(irq)); - } -} - -static void disable_pirq(unsigned int irq) -{ - int evtchn = evtchn_from_irq(irq); - - if (VALID_EVTCHN(evtchn)) - mask_evtchn(evtchn); -} - -static void ack_pirq(unsigned int irq) -{ - int evtchn = evtchn_from_irq(irq); - - if (VALID_EVTCHN(evtchn)) { - mask_evtchn(evtchn); - clear_evtchn(evtchn); - } -} - -static void end_pirq(unsigned int irq) -{ - int evtchn = evtchn_from_irq(irq); - - if (VALID_EVTCHN(evtchn) && !(irq_desc[irq].status & IRQ_DISABLED)) { - unmask_evtchn(evtchn); - pirq_unmask_notify(irq_to_pirq(irq)); - } -} - -static struct hw_interrupt_type pirq_type = { - "Phys-irq", - startup_pirq, - shutdown_pirq, - enable_pirq, - disable_pirq, - ack_pirq, - end_pirq, - set_affinity_irq -}; - -void hw_resend_irq(struct hw_interrupt_type *h, unsigned int i) -{ - int evtchn = evtchn_from_irq(i); - shared_info_t *s = HYPERVISOR_shared_info; - if (!VALID_EVTCHN(evtchn)) - return; - BUG_ON(!synch_test_bit(evtchn, &s->evtchn_mask[0])); - synch_set_bit(evtchn, &s->evtchn_pending[0]); -} - -void notify_remote_via_irq(int irq) -{ - int evtchn = evtchn_from_irq(irq); - - if (VALID_EVTCHN(evtchn)) - notify_remote_via_evtchn(evtchn); -} -EXPORT_SYMBOL(notify_remote_via_irq); - -void mask_evtchn(int port) -{ - shared_info_t *s = HYPERVISOR_shared_info; - synch_set_bit(port, &s->evtchn_mask[0]); -} -EXPORT_SYMBOL(mask_evtchn); - -void unmask_evtchn(int port) -{ - shared_info_t *s = HYPERVISOR_shared_info; - unsigned int cpu = smp_processor_id(); - vcpu_info_t *vcpu_info = &s->vcpu_info[cpu]; - - /* Slow path (hypercall) if this is a non-local port. */ - if (unlikely(cpu != cpu_from_evtchn(port))) { - evtchn_op_t op = { .cmd = EVTCHNOP_unmask, - .u.unmask.port = port }; - (void)HYPERVISOR_event_channel_op(&op); - return; - } - - synch_clear_bit(port, &s->evtchn_mask[0]); - - /* - * The following is basically the equivalent of 'hw_resend_irq'. Just - * like a real IO-APIC we 'lose the interrupt edge' if the channel is - * masked. - */ - if (synch_test_bit(port, &s->evtchn_pending[0]) && - !synch_test_and_set_bit(port / BITS_PER_LONG, - &vcpu_info->evtchn_pending_sel)) { - vcpu_info->evtchn_upcall_pending = 1; - if (!vcpu_info->evtchn_upcall_mask) - force_evtchn_callback(); - } -} -EXPORT_SYMBOL(unmask_evtchn); - -void irq_resume(void) -{ - evtchn_op_t op; - int cpu, pirq, virq, ipi, irq, evtchn; - - init_evtchn_cpu_bindings(); - - /* New event-channel space is not 'live' yet. */ - for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++) - mask_evtchn(evtchn); - - /* Check that no PIRQs are still bound. */ - for (pirq = 0; pirq < NR_PIRQS; pirq++) - BUG_ON(irq_info[pirq_to_irq(pirq)] != IRQ_UNBOUND); - - /* Secondary CPUs must have no VIRQ or IPI bindings. */ - for (cpu = 1; cpu < NR_CPUS; cpu++) { - for (virq = 0; virq < NR_VIRQS; virq++) - BUG_ON(per_cpu(virq_to_irq, cpu)[virq] != -1); - for (ipi = 0; ipi < NR_IPIS; ipi++) - BUG_ON(per_cpu(ipi_to_irq, cpu)[ipi] != -1); - } - - /* No IRQ <-> event-channel mappings. */ - for (irq = 0; irq < NR_IRQS; irq++) - irq_info[irq] &= ~0xFFFF; /* zap event-channel binding */ - for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++) - evtchn_to_irq[evtchn] = -1; - - /* Primary CPU: rebind VIRQs automatically. */ - for (virq = 0; virq < NR_VIRQS; virq++) { - if ((irq = per_cpu(virq_to_irq, 0)[virq]) == -1) - continue; - - BUG_ON(irq_info[irq] != mk_irq_info(IRQT_VIRQ, virq, 0)); - - /* Get a new binding from Xen. */ - memset(&op, 0, sizeof(op)); - op.cmd = EVTCHNOP_bind_virq; - op.u.bind_virq.virq = virq; - op.u.bind_virq.vcpu = 0; - BUG_ON(HYPERVISOR_event_channel_op(&op) != 0); - evtchn = op.u.bind_virq.port; - - /* Record the new mapping. */ - evtchn_to_irq[evtchn] = irq; - irq_info[irq] = mk_irq_info(IRQT_VIRQ, virq, evtchn); - - /* Ready for use. */ - unmask_evtchn(evtchn); - } - - /* Primary CPU: rebind IPIs automatically. */ - for (ipi = 0; ipi < NR_IPIS; ipi++) { - if ((irq = per_cpu(ipi_to_irq, 0)[ipi]) == -1) - continue; - - BUG_ON(irq_info[irq] != mk_irq_info(IRQT_IPI, ipi, 0)); - - /* Get a new binding from Xen. */ - memset(&op, 0, sizeof(op)); - op.cmd = EVTCHNOP_bind_ipi; - op.u.bind_ipi.vcpu = 0; - BUG_ON(HYPERVISOR_event_channel_op(&op) != 0); - evtchn = op.u.bind_ipi.port; - - /* Record the new mapping. */ - evtchn_to_irq[evtchn] = irq; - irq_info[irq] = mk_irq_info(IRQT_IPI, ipi, evtchn); - - /* Ready for use. */ - unmask_evtchn(evtchn); - } -} - -void __init init_IRQ(void) -{ - int i; - int cpu; - - irq_ctx_init(0); - - spin_lock_init(&irq_mapping_update_lock); - - init_evtchn_cpu_bindings(); - - /* No VIRQ or IPI bindings. */ - for (cpu = 0; cpu < NR_CPUS; cpu++) { - for (i = 0; i < NR_VIRQS; i++) - per_cpu(virq_to_irq, cpu)[i] = -1; - for (i = 0; i < NR_IPIS; i++) - per_cpu(ipi_to_irq, cpu)[i] = -1; - } - - /* No event-channel -> IRQ mappings. */ - for (i = 0; i < NR_EVENT_CHANNELS; i++) { - evtchn_to_irq[i] = -1; - mask_evtchn(i); /* No event channels are 'live' right now. */ - } - - /* No IRQ -> event-channel mappings. */ - for (i = 0; i < NR_IRQS; i++) - irq_info[i] = IRQ_UNBOUND; - - /* Dynamic IRQ space is currently unbound. Zero the refcnts. */ - for (i = 0; i < NR_DYNIRQS; i++) { - irq_bindcount[dynirq_to_irq(i)] = 0; - - irq_desc[dynirq_to_irq(i)].status = IRQ_DISABLED; - irq_desc[dynirq_to_irq(i)].action = NULL; - irq_desc[dynirq_to_irq(i)].depth = 1; - irq_desc[dynirq_to_irq(i)].handler = &dynirq_type; - } - - /* Phys IRQ space is statically bound (1:1 mapping). Nail refcnts. */ - for (i = 0; i < NR_PIRQS; i++) - { - irq_bindcount[pirq_to_irq(i)] = 1; - -#ifdef RTC_IRQ - /* If not domain 0, force our RTC driver to fail its probe. */ - if ((i == RTC_IRQ) && - !(xen_start_info->flags & SIF_INITDOMAIN)) - continue; -#endif - - irq_desc[pirq_to_irq(i)].status = IRQ_DISABLED; - irq_desc[pirq_to_irq(i)].action = NULL; - irq_desc[pirq_to_irq(i)].depth = 1; - irq_desc[pirq_to_irq(i)].handler = &pirq_type; - } -} - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/kernel/features.c --- a/linux-2.6-xen-sparse/arch/xen/kernel/features.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,38 +0,0 @@ -/****************************************************************************** - * features.c - * - * Xen feature flags. - * - * Copyright (c) 2006, Ian Campbell, XenSource Inc. - */ -#include <linux/types.h> -#include <linux/cache.h> -#include <asm/hypervisor.h> -#include <asm-xen/features.h> - -/* When we rebase to a more recent Linux we can use __read_mostly here. */ -unsigned long xen_features[XENFEAT_NR_SUBMAPS] __cacheline_aligned; - -void setup_xen_features(void) -{ - uint32_t *flags = (uint32_t *)&xen_features[0]; - xen_feature_info_t fi; - int i; - - for (i=0; i<XENFEAT_NR_SUBMAPS; i++) { - fi.submap_idx = i; - if (HYPERVISOR_xen_version(XENVER_get_features, &fi) < 0) - break; - flags[i] = fi.submap; - } -} - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/kernel/gnttab.c --- a/linux-2.6-xen-sparse/arch/xen/kernel/gnttab.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,411 +0,0 @@ -/****************************************************************************** - * gnttab.c - * - * Granting foreign access to our memory reservation. - * - * Copyright (c) 2005, Christopher Clark - * Copyright (c) 2004-2005, K A Fraser - */ - -#include <linux/config.h> -#include <linux/module.h> -#include <linux/sched.h> -#include <asm/pgtable.h> -#include <asm-xen/xen-public/xen.h> -#include <asm/fixmap.h> -#include <asm/uaccess.h> -#include <asm-xen/linux-public/privcmd.h> -#include <asm-xen/gnttab.h> -#include <asm/synch_bitops.h> - -#if 1 -#define ASSERT(_p) \ - if ( !(_p) ) { printk(KERN_ALERT"Assertion '%s': line %d, file %s\n", \ - #_p , __LINE__, __FILE__); *(int*)0=0; } -#else -#define ASSERT(_p) ((void)0) -#endif - -#define WPRINTK(fmt, args...) \ - printk(KERN_WARNING "xen_grant: " fmt, ##args) - - -EXPORT_SYMBOL(gnttab_grant_foreign_access); -EXPORT_SYMBOL(gnttab_end_foreign_access_ref); -EXPORT_SYMBOL(gnttab_end_foreign_access); -EXPORT_SYMBOL(gnttab_query_foreign_access); -EXPORT_SYMBOL(gnttab_grant_foreign_transfer); -EXPORT_SYMBOL(gnttab_end_foreign_transfer_ref); -EXPORT_SYMBOL(gnttab_end_foreign_transfer); -EXPORT_SYMBOL(gnttab_alloc_grant_references); -EXPORT_SYMBOL(gnttab_free_grant_references); -EXPORT_SYMBOL(gnttab_free_grant_reference); -EXPORT_SYMBOL(gnttab_claim_grant_reference); -EXPORT_SYMBOL(gnttab_release_grant_reference); -EXPORT_SYMBOL(gnttab_request_free_callback); -EXPORT_SYMBOL(gnttab_grant_foreign_access_ref); -EXPORT_SYMBOL(gnttab_grant_foreign_transfer_ref); - -/* External tools reserve first few grant table entries. */ -#define NR_RESERVED_ENTRIES 8 - -#define NR_GRANT_ENTRIES (NR_GRANT_FRAMES * PAGE_SIZE / sizeof(grant_entry_t)) -#define GNTTAB_LIST_END (NR_GRANT_ENTRIES + 1) - -static grant_ref_t gnttab_list[NR_GRANT_ENTRIES]; -static int gnttab_free_count; -static grant_ref_t gnttab_free_head; -static spinlock_t gnttab_list_lock = SPIN_LOCK_UNLOCKED; - -static grant_entry_t *shared; - -static struct gnttab_free_callback *gnttab_free_callback_list = NULL; - -static int -get_free_entries(int count) -{ - unsigned long flags; - int ref; - grant_ref_t head; - spin_lock_irqsave(&gnttab_list_lock, flags); - if (gnttab_free_count < count) { - spin_unlock_irqrestore(&gnttab_list_lock, flags); - return -1; - } - ref = head = gnttab_free_head; - gnttab_free_count -= count; - while (count-- > 1) - head = gnttab_list[head]; - gnttab_free_head = gnttab_list[head]; - gnttab_list[head] = GNTTAB_LIST_END; - spin_unlock_irqrestore(&gnttab_list_lock, flags); - return ref; -} - -#define get_free_entry() get_free_entries(1) - -static void -do_free_callbacks(void) -{ - struct gnttab_free_callback *callback, *next; - - callback = gnttab_free_callback_list; - gnttab_free_callback_list = NULL; - - while (callback != NULL) { - next = callback->next; - if (gnttab_free_count >= callback->count) { - callback->next = NULL; - callback->fn(callback->arg); - } else { - callback->next = gnttab_free_callback_list; - gnttab_free_callback_list = callback; - } - callback = next; - } -} - -static inline void -check_free_callbacks(void) -{ - if (unlikely(gnttab_free_callback_list)) - do_free_callbacks(); -} - -static void -put_free_entry(grant_ref_t ref) -{ - unsigned long flags; - spin_lock_irqsave(&gnttab_list_lock, flags); - gnttab_list[ref] = gnttab_free_head; - gnttab_free_head = ref; - gnttab_free_count++; - check_free_callbacks(); - spin_unlock_irqrestore(&gnttab_list_lock, flags); -} - -/* - * Public grant-issuing interface functions - */ - -int -gnttab_grant_foreign_access(domid_t domid, unsigned long frame, int readonly) -{ - int ref; - - if (unlikely((ref = get_free_entry()) == -1)) - return -ENOSPC; - - shared[ref].frame = frame; - shared[ref].domid = domid; - wmb(); - shared[ref].flags = GTF_permit_access | (readonly ? GTF_readonly : 0); - - return ref; -} - -void -gnttab_grant_foreign_access_ref(grant_ref_t ref, domid_t domid, - unsigned long frame, int readonly) -{ - shared[ref].frame = frame; - shared[ref].domid = domid; - wmb(); - shared[ref].flags = GTF_permit_access | (readonly ? GTF_readonly : 0); -} - - -int -gnttab_query_foreign_access(grant_ref_t ref) -{ - u16 nflags; - - nflags = shared[ref].flags; - - return (nflags & (GTF_reading|GTF_writing)); -} - -int -gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly) -{ - u16 flags, nflags; - - nflags = shared[ref].flags; - do { - if ( (flags = nflags) & (GTF_reading|GTF_writing) ) { - printk(KERN_ALERT "WARNING: g.e. still in use!\n"); - return 0; - } - } - while ((nflags = synch_cmpxchg(&shared[ref].flags, flags, 0)) != - flags); - - return 1; -} - -void -gnttab_end_foreign_access(grant_ref_t ref, int readonly, unsigned long page) -{ - if (gnttab_end_foreign_access_ref(ref, readonly)) { - put_free_entry(ref); - if (page != 0) { - free_page(page); - } - } - else { - /* XXX This needs to be fixed so that the ref and page are - placed on a list to be freed up later. */ - printk(KERN_WARNING - "WARNING: leaking g.e. and page still in use!\n"); - } -} - -int -gnttab_grant_foreign_transfer(domid_t domid) -{ - int ref; - - if (unlikely((ref = get_free_entry()) == -1)) - return -ENOSPC; - - shared[ref].frame = 0; - shared[ref].domid = domid; - wmb(); - shared[ref].flags = GTF_accept_transfer; - - return ref; -} - -void -gnttab_grant_foreign_transfer_ref(grant_ref_t ref, domid_t domid) -{ - shared[ref].frame = 0; - shared[ref].domid = domid; - wmb(); - shared[ref].flags = GTF_accept_transfer; -} - -unsigned long -gnttab_end_foreign_transfer_ref(grant_ref_t ref) -{ - unsigned long frame; - u16 flags; - - /* - * If a transfer is not even yet started, try to reclaim the grant - * reference and return failure (== 0). - */ - while (!((flags = shared[ref].flags) & GTF_transfer_committed)) { - if ( synch_cmpxchg(&shared[ref].flags, flags, 0) == flags ) - return 0; - cpu_relax(); - } - - /* If a transfer is in progress then wait until it is completed. */ - while (!(flags & GTF_transfer_completed)) { - flags = shared[ref].flags; - cpu_relax(); - } - - /* Read the frame number /after/ reading completion status. */ - rmb(); - frame = shared[ref].frame; - BUG_ON(frame == 0); - - return frame; -} - -unsigned long -gnttab_end_foreign_transfer(grant_ref_t ref) -{ - unsigned long frame = gnttab_end_foreign_transfer_ref(ref); - put_free_entry(ref); - return frame; -} - -void -gnttab_free_grant_reference(grant_ref_t ref) -{ - - put_free_entry(ref); -} - -void -gnttab_free_grant_references(grant_ref_t head) -{ - grant_ref_t ref; - unsigned long flags; - int count = 1; - if (head == GNTTAB_LIST_END) - return; - spin_lock_irqsave(&gnttab_list_lock, flags); - ref = head; - while (gnttab_list[ref] != GNTTAB_LIST_END) { - ref = gnttab_list[ref]; - count++; - } - gnttab_list[ref] = gnttab_free_head; - gnttab_free_head = head; - gnttab_free_count += count; - check_free_callbacks(); - spin_unlock_irqrestore(&gnttab_list_lock, flags); -} - -int -gnttab_alloc_grant_references(u16 count, grant_ref_t *head) -{ - int h = get_free_entries(count); - - if (h == -1) - return -ENOSPC; - - *head = h; - - return 0; -} - -int -gnttab_claim_grant_reference(grant_ref_t *private_head) -{ - grant_ref_t g = *private_head; - if (unlikely(g == GNTTAB_LIST_END)) - return -ENOSPC; - *private_head = gnttab_list[g]; - return g; -} - -void -gnttab_release_grant_reference(grant_ref_t *private_head, grant_ref_t release) -{ - gnttab_list[release] = *private_head; - *private_head = release; -} - -void -gnttab_request_free_callback(struct gnttab_free_callback *callback, - void (*fn)(void *), void *arg, u16 count) -{ - unsigned long flags; - spin_lock_irqsave(&gnttab_list_lock, flags); - if (callback->next) - goto out; - callback->fn = fn; - callback->arg = arg; - callback->count = count; - callback->next = gnttab_free_callback_list; - gnttab_free_callback_list = callback; - check_free_callbacks(); - out: - spin_unlock_irqrestore(&gnttab_list_lock, flags); -} - -int -gnttab_resume(void) -{ - gnttab_setup_table_t setup; - unsigned long frames[NR_GRANT_FRAMES]; - int i; - - setup.dom = DOMID_SELF; - setup.nr_frames = NR_GRANT_FRAMES; - setup.frame_list = frames; - - BUG_ON(HYPERVISOR_grant_table_op(GNTTABOP_setup_table, &setup, 1)); - BUG_ON(setup.status != 0); - -#ifdef __ia64__ - shared = __va(frames[0] << PAGE_SHIFT); - printk("grant table at %p\n", shared); -#else - for (i = 0; i < NR_GRANT_FRAMES; i++) - set_fixmap(FIX_GNTTAB_END - i, frames[i] << PAGE_SHIFT); -#endif - - return 0; -} - -int -gnttab_suspend(void) -{ - int i; - - for (i = 0; i < NR_GRANT_FRAMES; i++) - clear_fixmap(FIX_GNTTAB_END - i); - - return 0; -} - -static int __init -gnttab_init(void) -{ - int i; - - if (xen_init() < 0) - return -ENODEV; - - BUG_ON(gnttab_resume()); - -#ifndef __ia64__ - shared = (grant_entry_t *)fix_to_virt(FIX_GNTTAB_END); -#endif - - for (i = NR_RESERVED_ENTRIES; i < NR_GRANT_ENTRIES; i++) - gnttab_list[i] = i + 1; - gnttab_free_count = NR_GRANT_ENTRIES - NR_RESERVED_ENTRIES; - gnttab_free_head = NR_RESERVED_ENTRIES; - - printk("Grant table initialized\n"); - return 0; -} - -core_initcall(gnttab_init); - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/kernel/reboot.c --- a/linux-2.6-xen-sparse/arch/xen/kernel/reboot.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,430 +0,0 @@ -#define __KERNEL_SYSCALLS__ -#include <linux/version.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/unistd.h> -#include <linux/module.h> -#include <linux/reboot.h> -#include <linux/sysrq.h> -#include <linux/stringify.h> -#include <asm/irq.h> -#include <asm/mmu_context.h> -#include <asm-xen/evtchn.h> -#include <asm/hypervisor.h> -#include <asm-xen/xen-public/dom0_ops.h> -#include <asm-xen/xenbus.h> -#include <linux/cpu.h> -#include <linux/kthread.h> -#include <asm-xen/xencons.h> - -#if defined(__i386__) || defined(__x86_64__) -/* - * Power off function, if any - */ -void (*pm_power_off)(void); -#endif - -#define SHUTDOWN_INVALID -1 -#define SHUTDOWN_POWEROFF 0 -#define SHUTDOWN_REBOOT 1 -#define SHUTDOWN_SUSPEND 2 -// Code 3 is SHUTDOWN_CRASH, which we don't use because the domain can only -// report a crash, not be instructed to crash! -// HALT is the same as POWEROFF, as far as we're concerned. The tools use -// the distinction when we return the reason code to them. -#define SHUTDOWN_HALT 4 - -void machine_restart(char * __unused) -{ - /* We really want to get pending console data out before we die. */ - xencons_force_flush(); - HYPERVISOR_sched_op(SCHEDOP_shutdown, SHUTDOWN_reboot); -} - -void machine_halt(void) -{ - machine_power_off(); -} - -void machine_power_off(void) -{ - /* We really want to get pending console data out before we die. */ - xencons_force_flush(); - HYPERVISOR_sched_op(SCHEDOP_shutdown, SHUTDOWN_poweroff); -} - -int reboot_thru_bios = 0; /* for dmi_scan.c */ -EXPORT_SYMBOL(machine_restart); -EXPORT_SYMBOL(machine_halt); -EXPORT_SYMBOL(machine_power_off); - - -/****************************************************************************** - * Stop/pickle callback handling. - */ - -/* Ignore multiple shutdown requests. */ -static int shutting_down = SHUTDOWN_INVALID; -static void __shutdown_handler(void *unused); -static DECLARE_WORK(shutdown_work, __shutdown_handler, NULL); - -#ifndef CONFIG_HOTPLUG_CPU -#define cpu_down(x) (-EOPNOTSUPP) -#define cpu_up(x) (-EOPNOTSUPP) -#endif - - -static int __do_suspend(void *ignore) -{ - int i, j, k, fpp; - - extern int gnttab_suspend(void); - extern int gnttab_resume(void); - - extern void time_resume(void); - extern unsigned long max_pfn; - extern unsigned long *pfn_to_mfn_frame_list_list; - extern unsigned long *pfn_to_mfn_frame_list[]; - -#ifdef CONFIG_SMP - cpumask_t prev_online_cpus; - int vcpu_prepare(int vcpu); -#endif - - int err = 0; - - BUG_ON(smp_processor_id() != 0); - BUG_ON(in_interrupt()); - -#if defined(CONFIG_SMP) && !defined(CONFIG_HOTPLUG_CPU) - if (num_online_cpus() > 1) { - printk(KERN_WARNING "Can't suspend SMP guests " - "without CONFIG_HOTPLUG_CPU\n"); - return -EOPNOTSUPP; - } -#endif - - xenbus_suspend(); - - lock_cpu_hotplug(); -#ifdef CONFIG_SMP - /* - * Take all other CPUs offline. We hold the hotplug semaphore to - * avoid other processes bringing up CPUs under our feet. - */ - cpus_clear(prev_online_cpus); - while (num_online_cpus() > 1) { - for_each_online_cpu(i) { - if (i == 0) - continue; - unlock_cpu_hotplug(); - err = cpu_down(i); - lock_cpu_hotplug(); - if (err != 0) { - printk(KERN_CRIT "Failed to take all CPUs " - "down: %d.\n", err); - goto out_reenable_cpus; - } - cpu_set(i, prev_online_cpus); - } - } -#endif - - preempt_disable(); - -#ifdef __i386__ - kmem_cache_shrink(pgd_cache); - mm_pin_all(); -#endif - - __cli(); - preempt_enable(); - unlock_cpu_hotplug(); - - gnttab_suspend(); - - HYPERVISOR_shared_info = (shared_info_t *)empty_zero_page; - clear_fixmap(FIX_SHARED_INFO); - - xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn); - xen_start_info->console_mfn = mfn_to_pfn(xen_start_info->console_mfn); - - /* - * We'll stop somewhere inside this hypercall. When it returns, - * we'll start resuming after the restore. - */ - HYPERVISOR_suspend(virt_to_mfn(xen_start_info)); - - shutting_down = SHUTDOWN_INVALID; - - set_fixmap(FIX_SHARED_INFO, xen_start_info->shared_info); - - HYPERVISOR_shared_info = (shared_info_t *)fix_to_virt(FIX_SHARED_INFO); - - memset(empty_zero_page, 0, PAGE_SIZE); - - HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = - virt_to_mfn(pfn_to_mfn_frame_list_list); - - fpp = PAGE_SIZE/sizeof(unsigned long); - for (i = 0, j = 0, k = -1; i < max_pfn; i += fpp, j++) { - if ((j % fpp) == 0) { - k++; - pfn_to_mfn_frame_list_list[k] = - virt_to_mfn(pfn_to_mfn_frame_list[k]); - j = 0; - } - pfn_to_mfn_frame_list[k][j] = - virt_to_mfn(&phys_to_machine_mapping[i]); - } - HYPERVISOR_shared_info->arch.max_pfn = max_pfn; - - gnttab_resume(); - - irq_resume(); - - time_resume(); - - __sti(); - - xencons_resume(); - -#ifdef CONFIG_SMP - for_each_cpu(i) - vcpu_prepare(i); - -#endif - - /* - * Only resume xenbus /after/ we've prepared our VCPUs; otherwise - * the VCPU hotplug callback can race with our vcpu_prepare - */ - xenbus_resume(); - -#ifdef CONFIG_SMP - out_reenable_cpus: - for_each_cpu_mask(i, prev_online_cpus) { - j = cpu_up(i); - if ((j != 0) && !cpu_online(i)) { - printk(KERN_CRIT "Failed to bring cpu " - "%d back up (%d).\n", - i, j); - err = j; - } - } -#endif - - return err; -} - -static int shutdown_process(void *__unused) -{ - static char *envp[] = { "HOME=/", "TERM=linux", - "PATH=/sbin:/usr/sbin:/bin:/usr/bin", NULL }; - static char *restart_argv[] = { "/sbin/reboot", NULL }; - static char *poweroff_argv[] = { "/sbin/poweroff", NULL }; - - extern asmlinkage long sys_reboot(int magic1, int magic2, - unsigned int cmd, void *arg); - - daemonize("shutdown"); - - switch (shutting_down) { - case SHUTDOWN_POWEROFF: - case SHUTDOWN_HALT: - if (execve("/sbin/poweroff", poweroff_argv, envp) < 0) { - sys_reboot(LINUX_REBOOT_MAGIC1, - LINUX_REBOOT_MAGIC2, - LINUX_REBOOT_CMD_POWER_OFF, - NULL); - } - break; - - case SHUTDOWN_REBOOT: - if (execve("/sbin/reboot", restart_argv, envp) < 0) { - sys_reboot(LINUX_REBOOT_MAGIC1, - LINUX_REBOOT_MAGIC2, - LINUX_REBOOT_CMD_RESTART, - NULL); - } - break; - } - - shutting_down = SHUTDOWN_INVALID; /* could try again */ - - return 0; -} - -static int kthread_create_on_cpu(int (*f)(void *arg), - void *arg, - const char *name, - int cpu) -{ - struct task_struct *p; - p = kthread_create(f, arg, name); - if (IS_ERR(p)) - return PTR_ERR(p); - kthread_bind(p, cpu); - wake_up_process(p); - return 0; -} - -static void __shutdown_handler(void *unused) -{ - int err; - - if (shutting_down != SHUTDOWN_SUSPEND) - err = kernel_thread(shutdown_process, NULL, - CLONE_FS | CLONE_FILES); - else - err = kthread_create_on_cpu(__do_suspend, NULL, "suspend", 0); - - if ( err < 0 ) { - printk(KERN_WARNING "Error creating shutdown process (%d): " - "retrying...\n", -err); - schedule_delayed_work(&shutdown_work, HZ/2); - } -} - -static void shutdown_handler(struct xenbus_watch *watch, - const char **vec, unsigned int len) -{ - char *str; - xenbus_transaction_t xbt; - int err; - - if (shutting_down != SHUTDOWN_INVALID) - return; - - again: - err = xenbus_transaction_start(&xbt); - if (err) - return; - str = (char *)xenbus_read(xbt, "control", "shutdown", NULL); - /* Ignore read errors and empty reads. */ - if (XENBUS_IS_ERR_READ(str)) { - xenbus_transaction_end(xbt, 1); - return; - } - - xenbus_write(xbt, "control", "shutdown", ""); - - err = xenbus_transaction_end(xbt, 0); - if (err == -EAGAIN) { - kfree(str); - goto again; - } - - if (strcmp(str, "poweroff") == 0) - shutting_down = SHUTDOWN_POWEROFF; - else if (strcmp(str, "reboot") == 0) - shutting_down = SHUTDOWN_REBOOT; - else if (strcmp(str, "suspend") == 0) - shutting_down = SHUTDOWN_SUSPEND; - else if (strcmp(str, "halt") == 0) - shutting_down = SHUTDOWN_HALT; - else { - printk("Ignoring shutdown request: %s\n", str); - shutting_down = SHUTDOWN_INVALID; - } - - if (shutting_down != SHUTDOWN_INVALID) - schedule_work(&shutdown_work); - - kfree(str); -} - -#ifdef CONFIG_MAGIC_SYSRQ -static void sysrq_handler(struct xenbus_watch *watch, const char **vec, - unsigned int len) -{ - char sysrq_key = '\0'; - xenbus_transaction_t xbt; - int err; - - again: - err = xenbus_transaction_start(&xbt); - if (err) - return; - if (!xenbus_scanf(xbt, "control", "sysrq", "%c", &sysrq_key)) { - printk(KERN_ERR "Unable to read sysrq code in " - "control/sysrq\n"); - xenbus_transaction_end(xbt, 1); - return; - } - - if (sysrq_key != '\0') - xenbus_printf(xbt, "control", "sysrq", "%c", '\0'); - - err = xenbus_transaction_end(xbt, 0); - if (err == -EAGAIN) - goto again; - - if (sysrq_key != '\0') { - handle_sysrq(sysrq_key, NULL, NULL); - } -} -#endif - -static struct xenbus_watch shutdown_watch = { - .node = "control/shutdown", - .callback = shutdown_handler -}; - -#ifdef CONFIG_MAGIC_SYSRQ -static struct xenbus_watch sysrq_watch = { - .node ="control/sysrq", - .callback = sysrq_handler -}; -#endif - -static struct notifier_block xenstore_notifier; - -static int setup_shutdown_watcher(struct notifier_block *notifier, - unsigned long event, - void *data) -{ - int err1 = 0; -#ifdef CONFIG_MAGIC_SYSRQ - int err2 = 0; -#endif - - err1 = register_xenbus_watch(&shutdown_watch); -#ifdef CONFIG_MAGIC_SYSRQ - err2 = register_xenbus_watch(&sysrq_watch); -#endif - - if (err1) { - printk(KERN_ERR "Failed to set shutdown watcher\n"); - } - -#ifdef CONFIG_MAGIC_SYSRQ - if (err2) { - printk(KERN_ERR "Failed to set sysrq watcher\n"); - } -#endif - - return NOTIFY_DONE; -} - -static int __init setup_shutdown_event(void) -{ - - xenstore_notifier.notifier_call = setup_shutdown_watcher; - - register_xenstore_notifier(&xenstore_notifier); - - return 0; -} - -subsys_initcall(setup_shutdown_event); - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/kernel/skbuff.c --- a/linux-2.6-xen-sparse/arch/xen/kernel/skbuff.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,142 +0,0 @@ - -#include <linux/config.h> -#include <linux/module.h> -#include <linux/version.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/netdevice.h> -#include <linux/inetdevice.h> -#include <linux/etherdevice.h> -#include <linux/skbuff.h> -#include <linux/init.h> -#include <asm/io.h> -#include <asm/page.h> -#include <asm/hypervisor.h> - -/* Referenced in netback.c. */ -/*static*/ kmem_cache_t *skbuff_cachep; - -#define MAX_SKBUFF_ORDER 4 -static kmem_cache_t *skbuff_order_cachep[MAX_SKBUFF_ORDER + 1]; - -static struct { - int size; - kmem_cache_t *cachep; -} skbuff_small[] = { { 512, NULL }, { 2048, NULL } }; - -struct sk_buff *alloc_skb(unsigned int length, int gfp_mask) -{ - int order, i; - kmem_cache_t *cachep; - - length = SKB_DATA_ALIGN(length) + sizeof(struct skb_shared_info); - - if (length <= skbuff_small[ARRAY_SIZE(skbuff_small)-1].size) { - for (i = 0; skbuff_small[i].size < length; i++) - continue; - cachep = skbuff_small[i].cachep; - } else { - order = get_order(length); - if (order > MAX_SKBUFF_ORDER) { - printk(KERN_ALERT "Attempt to allocate order %d " - "skbuff. Increase MAX_SKBUFF_ORDER.\n", order); - return NULL; - } - cachep = skbuff_order_cachep[order]; - } - - length -= sizeof(struct skb_shared_info); - - return alloc_skb_from_cache(cachep, length, gfp_mask); -} - -struct sk_buff *__dev_alloc_skb(unsigned int length, int gfp_mask) -{ - struct sk_buff *skb; - int order; - - length = SKB_DATA_ALIGN(length + 16); - order = get_order(length + sizeof(struct skb_shared_info)); - if (order > MAX_SKBUFF_ORDER) { - printk(KERN_ALERT "Attempt to allocate order %d skbuff. " - "Increase MAX_SKBUFF_ORDER.\n", order); - return NULL; - } - - skb = alloc_skb_from_cache( - skbuff_order_cachep[order], length, gfp_mask); - if (skb != NULL) - skb_reserve(skb, 16); - - return skb; -} - -static void skbuff_ctor(void *buf, kmem_cache_t *cachep, unsigned long unused) -{ - int order = 0; - - while (skbuff_order_cachep[order] != cachep) - order++; - - /* Do our best to allocate contiguous memory but fall back to IOMMU. */ - if (order != 0) - (void)xen_create_contiguous_region( - (unsigned long)buf, order, 0); - - scrub_pages(buf, 1 << order); -} - -static void skbuff_dtor(void *buf, kmem_cache_t *cachep, unsigned long unused) -{ - int order = 0; - - while (skbuff_order_cachep[order] != cachep) - order++; - - if (order != 0) - xen_destroy_contiguous_region((unsigned long)buf, order); -} - -static int __init skbuff_init(void) -{ - static char name[MAX_SKBUFF_ORDER + 1][20]; - static char small_name[ARRAY_SIZE(skbuff_small)][20]; - unsigned long size; - int i, order; - - for (i = 0; i < ARRAY_SIZE(skbuff_small); i++) { - size = skbuff_small[i].size; - sprintf(small_name[i], "xen-skb-%lu", size); - /* - * No ctor/dtor: objects do not span page boundaries, and they - * are only used on transmit path so no need for scrubbing. - */ - skbuff_small[i].cachep = kmem_cache_create( - small_name[i], size, size, 0, NULL, NULL); - } - - for (order = 0; order <= MAX_SKBUFF_ORDER; order++) { - size = PAGE_SIZE << order; - sprintf(name[order], "xen-skb-%lu", size); - skbuff_order_cachep[order] = kmem_cache_create( - name[order], size, size, 0, skbuff_ctor, skbuff_dtor); - } - - skbuff_cachep = skbuff_order_cachep[0]; - - return 0; -} -core_initcall(skbuff_init); - -EXPORT_SYMBOL(__dev_alloc_skb); - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/kernel/smpboot.c --- a/linux-2.6-xen-sparse/arch/xen/kernel/smpboot.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,439 +0,0 @@ -/* - * Xen SMP booting functions - * - * See arch/i386/kernel/smpboot.c for copyright and credits for derived - * portions of this file. - */ - -#include <linux/module.h> -#include <linux/config.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/sched.h> -#include <linux/kernel_stat.h> -#include <linux/smp_lock.h> -#include <linux/irq.h> -#include <linux/bootmem.h> -#include <linux/notifier.h> -#include <linux/cpu.h> -#include <linux/percpu.h> -#include <asm/desc.h> -#include <asm/arch_hooks.h> -#include <asm/pgalloc.h> -#include <asm-xen/evtchn.h> -#include <asm-xen/xen-public/vcpu.h> -#include <asm-xen/xenbus.h> - -#ifdef CONFIG_SMP_ALTERNATIVES -#include <asm/smp_alt.h> -#endif - -extern irqreturn_t smp_reschedule_interrupt(int, void *, struct pt_regs *); -extern irqreturn_t smp_call_function_interrupt(int, void *, struct pt_regs *); - -extern void local_setup_timer(unsigned int cpu); -extern void local_teardown_timer(unsigned int cpu); - -extern void hypervisor_callback(void); -extern void failsafe_callback(void); -extern void system_call(void); -extern void smp_trap_init(trap_info_t *); - -extern cpumask_t cpu_initialized; - -/* Number of siblings per CPU package */ -int smp_num_siblings = 1; -int phys_proc_id[NR_CPUS]; /* Package ID of each logical CPU */ -EXPORT_SYMBOL(phys_proc_id); -int cpu_core_id[NR_CPUS]; /* Core ID of each logical CPU */ -EXPORT_SYMBOL(cpu_core_id); - -cpumask_t cpu_online_map; -EXPORT_SYMBOL(cpu_online_map); -cpumask_t cpu_possible_map; -EXPORT_SYMBOL(cpu_possible_map); - -struct cpuinfo_x86 cpu_data[NR_CPUS] __cacheline_aligned; -EXPORT_SYMBOL(cpu_data); - -#ifdef CONFIG_HOTPLUG_CPU -DEFINE_PER_CPU(int, cpu_state) = { 0 }; -#endif - -static DEFINE_PER_CPU(int, resched_irq); -static DEFINE_PER_CPU(int, callfunc_irq); -static char resched_name[NR_CPUS][15]; -static char callfunc_name[NR_CPUS][15]; - -u8 cpu_2_logical_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; - -void *xquad_portio; - -cpumask_t cpu_sibling_map[NR_CPUS] __cacheline_aligned; -cpumask_t cpu_core_map[NR_CPUS] __cacheline_aligned; -EXPORT_SYMBOL(cpu_core_map); - -#if defined(__i386__) -u8 x86_cpu_to_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = 0xff }; -EXPORT_SYMBOL(x86_cpu_to_apicid); -#elif !defined(CONFIG_X86_IO_APIC) -unsigned int maxcpus = NR_CPUS; -#endif - -void __init smp_alloc_memory(void) -{ -} - -static void xen_smp_intr_init(unsigned int cpu) -{ - sprintf(resched_name[cpu], "resched%d", cpu); - per_cpu(resched_irq, cpu) = - bind_ipi_to_irqhandler( - RESCHEDULE_VECTOR, - cpu, - smp_reschedule_interrupt, - SA_INTERRUPT, - resched_name[cpu], - NULL); - BUG_ON(per_cpu(resched_irq, cpu) < 0); - - sprintf(callfunc_name[cpu], "callfunc%d", cpu); - per_cpu(callfunc_irq, cpu) = - bind_ipi_to_irqhandler( - CALL_FUNCTION_VECTOR, - cpu, - smp_call_function_interrupt, - SA_INTERRUPT, - callfunc_name[cpu], - NULL); - BUG_ON(per_cpu(callfunc_irq, cpu) < 0); - - if (cpu != 0) - local_setup_timer(cpu); -} - -#ifdef CONFIG_HOTPLUG_CPU -static void xen_smp_intr_exit(unsigned int cpu) -{ - if (cpu != 0) - local_teardown_timer(cpu); - - unbind_from_irqhandler(per_cpu(resched_irq, cpu), NULL); - unbind_from_irqhandler(per_cpu(callfunc_irq, cpu), NULL); -} -#endif - -static void cpu_bringup(void) -{ - if (!cpu_isset(smp_processor_id(), cpu_initialized)) - cpu_init(); - local_irq_enable(); - cpu_idle(); -} - -void vcpu_prepare(int vcpu) -{ - vcpu_guest_context_t ctxt; - struct task_struct *idle = idle_task(vcpu); - - if (vcpu == 0) - return; - - memset(&ctxt, 0, sizeof(ctxt)); - - ctxt.flags = VGCF_IN_KERNEL; - ctxt.user_regs.ds = __USER_DS; - ctxt.user_regs.es = __USER_DS; - ctxt.user_regs.fs = 0; - ctxt.user_regs.gs = 0; - ctxt.user_regs.ss = __KERNEL_DS; - ctxt.user_regs.eip = (unsigned long)cpu_bringup; - ctxt.user_regs.eflags = X86_EFLAGS_IF | 0x1000; /* IOPL_RING1 */ - - memset(&ctxt.fpu_ctxt, 0, sizeof(ctxt.fpu_ctxt)); - - smp_trap_init(ctxt.trap_ctxt); - - ctxt.ldt_ents = 0; - - ctxt.gdt_frames[0] = virt_to_mfn(cpu_gdt_descr[vcpu].address); - ctxt.gdt_ents = cpu_gdt_descr[vcpu].size / 8; - -#ifdef __i386__ - ctxt.user_regs.cs = __KERNEL_CS; - ctxt.user_regs.esp = idle->thread.esp; - - ctxt.kernel_ss = __KERNEL_DS; - ctxt.kernel_sp = idle->thread.esp0; - - ctxt.event_callback_cs = __KERNEL_CS; - ctxt.event_callback_eip = (unsigned long)hypervisor_callback; - ctxt.failsafe_callback_cs = __KERNEL_CS; - ctxt.failsafe_callback_eip = (unsigned long)failsafe_callback; - - ctxt.ctrlreg[3] = virt_to_mfn(swapper_pg_dir) << PAGE_SHIFT; -#else - ctxt.user_regs.cs = __KERNEL_CS | 3; - ctxt.user_regs.esp = idle->thread.rsp; - - ctxt.kernel_ss = __KERNEL_DS; - ctxt.kernel_sp = idle->thread.rsp0; - - ctxt.event_callback_eip = (unsigned long)hypervisor_callback; - ctxt.failsafe_callback_eip = (unsigned long)failsafe_callback; - ctxt.syscall_callback_eip = (unsigned long)system_call; - - ctxt.ctrlreg[3] = virt_to_mfn(init_level4_pgt) << PAGE_SHIFT; - - ctxt.gs_base_kernel = (unsigned long)(cpu_pda + vcpu); -#endif - - BUG_ON(HYPERVISOR_vcpu_op(VCPUOP_initialise, vcpu, &ctxt)); -} - -void __init smp_prepare_cpus(unsigned int max_cpus) -{ - int cpu, rc; - struct task_struct *idle; - - cpu_data[0] = boot_cpu_data; - - cpu_2_logical_apicid[0] = 0; - x86_cpu_to_apicid[0] = 0; - - current_thread_info()->cpu = 0; - cpu_sibling_map[0] = cpumask_of_cpu(0); - cpu_core_map[0] = cpumask_of_cpu(0); - - if (max_cpus != 0) - xen_smp_intr_init(0); - - for (cpu = 1; cpu < max_cpus; cpu++) { - rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL); - if (rc == -ENOENT) - break; - BUG_ON(rc != 0); - - cpu_data[cpu] = boot_cpu_data; - cpu_2_logical_apicid[cpu] = cpu; - x86_cpu_to_apicid[cpu] = cpu; - - idle = fork_idle(cpu); - if (IS_ERR(idle)) - panic("failed fork for CPU %d", cpu); - -#ifdef __x86_64__ - cpu_pda[cpu].pcurrent = idle; - cpu_pda[cpu].cpunumber = cpu; - per_cpu(init_tss,cpu).rsp0 = idle->thread.rsp; - clear_ti_thread_flag(idle->thread_info, TIF_FORK); -#endif - - irq_ctx_init(cpu); - - cpu_gdt_descr[cpu].address = - __get_free_page(GFP_KERNEL|__GFP_ZERO); - BUG_ON(cpu_gdt_descr[0].size > PAGE_SIZE); - cpu_gdt_descr[cpu].size = cpu_gdt_descr[0].size; - memcpy((void *)cpu_gdt_descr[cpu].address, - (void *)cpu_gdt_descr[0].address, - cpu_gdt_descr[0].size); - make_page_readonly( - (void *)cpu_gdt_descr[cpu].address, - XENFEAT_writable_descriptor_tables); - - cpu_set(cpu, cpu_possible_map); -#ifdef CONFIG_HOTPLUG_CPU - if (xen_start_info->flags & SIF_INITDOMAIN) - cpu_set(cpu, cpu_present_map); -#else - cpu_set(cpu, cpu_present_map); -#endif - - vcpu_prepare(cpu); - } - - /* Currently, Xen gives no dynamic NUMA/HT info. */ - for (cpu = 1; cpu < NR_CPUS; cpu++) { - cpu_sibling_map[cpu] = cpumask_of_cpu(cpu); - cpu_core_map[cpu] = cpumask_of_cpu(cpu); - } - -#ifdef CONFIG_X86_IO_APIC - /* - * Here we can be sure that there is an IO-APIC in the system. Let's - * go and set it up: - */ - if (!skip_ioapic_setup && nr_ioapics) - setup_IO_APIC(); -#endif -} - -void __devinit smp_prepare_boot_cpu(void) -{ - cpu_possible_map = cpumask_of_cpu(0); - cpu_present_map = cpumask_of_cpu(0); - cpu_online_map = cpumask_of_cpu(0); -} - -#ifdef CONFIG_HOTPLUG_CPU - -/* - * Initialize cpu_present_map late to skip SMP boot code in init/main.c. - * But do it early enough to catch critical for_each_present_cpu() loops - * in i386-specific code. - */ -static int __init initialize_cpu_present_map(void) -{ - cpu_present_map = cpu_possible_map; - return 0; -} -core_initcall(initialize_cpu_present_map); - -static void vcpu_hotplug(unsigned int cpu) -{ - int err; - char dir[32], state[32]; - - if ((cpu >= NR_CPUS) || !cpu_possible(cpu)) - return; - - sprintf(dir, "cpu/%d", cpu); - err = xenbus_scanf(XBT_NULL, dir, "availability", "%s", state); - if (err != 1) { - printk(KERN_ERR "XENBUS: Unable to read cpu state\n"); - return; - } - - if (strcmp(state, "online") == 0) { - (void)cpu_up(cpu); - } else if (strcmp(state, "offline") == 0) { - (void)cpu_down(cpu); - } else { - printk(KERN_ERR "XENBUS: unknown state(%s) on CPU%d\n", - state, cpu); - } -} - -static void handle_vcpu_hotplug_event( - struct xenbus_watch *watch, const char **vec, unsigned int len) -{ - int cpu; - char *cpustr; - const char *node = vec[XS_WATCH_PATH]; - - if ((cpustr = strstr(node, "cpu/")) != NULL) { - sscanf(cpustr, "cpu/%d", &cpu); - vcpu_hotplug(cpu); - } -} - -static int setup_cpu_watcher(struct notifier_block *notifier, - unsigned long event, void *data) -{ - int i; - - static struct xenbus_watch cpu_watch = { - .node = "cpu", - .callback = handle_vcpu_hotplug_event }; - (void)register_xenbus_watch(&cpu_watch); - - if (!(xen_start_info->flags & SIF_INITDOMAIN)) { - for_each_cpu(i) - vcpu_hotplug(i); - printk(KERN_INFO "Brought up %ld CPUs\n", - (long)num_online_cpus()); - } - - return NOTIFY_DONE; -} - -static int __init setup_vcpu_hotplug_event(void) -{ - static struct notifier_block xsn_cpu = { - .notifier_call = setup_cpu_watcher }; - register_xenstore_notifier(&xsn_cpu); - return 0; -} - -arch_initcall(setup_vcpu_hotplug_event); - -int __cpu_disable(void) -{ - cpumask_t map = cpu_online_map; - int cpu = smp_processor_id(); - - if (cpu == 0) - return -EBUSY; - - cpu_clear(cpu, map); - fixup_irqs(map); - cpu_clear(cpu, cpu_online_map); - - return 0; -} - -void __cpu_die(unsigned int cpu) -{ - while (HYPERVISOR_vcpu_op(VCPUOP_is_up, cpu, NULL)) { - current->state = TASK_UNINTERRUPTIBLE; - schedule_timeout(HZ/10); - } - - xen_smp_intr_exit(cpu); - -#ifdef CONFIG_SMP_ALTERNATIVES - if (num_online_cpus() == 1) - unprepare_for_smp(); -#endif -} - -#else /* !CONFIG_HOTPLUG_CPU */ - -int __cpu_disable(void) -{ - return -ENOSYS; -} - -void __cpu_die(unsigned int cpu) -{ - BUG(); -} - -#endif /* CONFIG_HOTPLUG_CPU */ - -int __devinit __cpu_up(unsigned int cpu) -{ -#ifdef CONFIG_SMP_ALTERNATIVES - if (num_online_cpus() == 1) - prepare_for_smp(); -#endif - - xen_smp_intr_init(cpu); - cpu_set(cpu, cpu_online_map); - if (HYPERVISOR_vcpu_op(VCPUOP_up, cpu, NULL) != 0) - BUG(); - - return 0; -} - -void __init smp_cpus_done(unsigned int max_cpus) -{ -} - -int setup_profiling_timer(unsigned int multiplier) -{ - /* Dummy function. */ - return 0; -} - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/kernel/xen_proc.c --- a/linux-2.6-xen-sparse/arch/xen/kernel/xen_proc.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,29 +0,0 @@ - -#include <linux/config.h> -#include <linux/proc_fs.h> -#include <asm-xen/xen_proc.h> - -static struct proc_dir_entry *xen_base; - -struct proc_dir_entry *create_xen_proc_entry(const char *name, mode_t mode) -{ - if ( xen_base == NULL ) - if ( (xen_base = proc_mkdir("xen", &proc_root)) == NULL ) - panic("Couldn't create /proc/xen"); - return create_proc_entry(name, mode, xen_base); -} - -void remove_xen_proc_entry(const char *name) -{ - remove_proc_entry(name, xen_base); -} - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/Kconfig --- a/linux-2.6-xen-sparse/arch/xen/x86_64/Kconfig Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,480 +0,0 @@ -# -# For a description of the syntax of this configuration file, -# see Documentation/kbuild/kconfig-language.txt. -# -# Note: ISA is disabled and will hopefully never be enabled. -# If you managed to buy an ISA x86-64 box you'll have to fix all the -# ISA drivers you need yourself. -# - -menu "X86_64 processor configuration" - -config XENARCH - string - default x86_64 - -config X86_64 - bool - default y - help - Port to the x86-64 architecture. x86-64 is a 64-bit extension to the - classical 32-bit x86 architecture. For details see - <http://www.x86-64.org/>. - -config 64BIT - def_bool y - -config X86 - bool - default y - -config MMU - bool - default y - -config ISA - bool - -config SBUS - bool - -config RWSEM_GENERIC_SPINLOCK - bool - default y - -config RWSEM_XCHGADD_ALGORITHM - bool - -config GENERIC_CALIBRATE_DELAY - bool - default y - -config X86_CMPXCHG - bool - default y - -config EARLY_PRINTK - bool "Early Printk" - default n - help - Write kernel log output directly into the VGA buffer or to a serial - port. - - This is useful for kernel debugging when your machine crashes very - early before the console code is initialized. For normal operation - it is not recommended because it looks ugly and doesn't cooperate - with klogd/syslogd or the X server. You should normally N here, - unless you want to debug such a crash. - -config GENERIC_ISA_DMA - bool - default y - -config GENERIC_IOMAP - bool - default y - -#source "init/Kconfig" - - -menu "Processor type and features" - -choice - prompt "Processor family" - default MK8 - -#config MK8 -# bool "AMD-Opteron/Athlon64" -# help -# Optimize for AMD Opteron/Athlon64/Hammer/K8 CPUs. - -config MPSC - bool "Intel EM64T" - help - Optimize for Intel Pentium 4 and Xeon CPUs with Intel - Extended Memory 64 Technology(EM64T). For details see - <http://www.intel.com/technology/64bitextensions/>. - -config GENERIC_CPU - bool "Generic-x86-64" - help - Generic x86-64 CPU. - -endchoice - -# -# Define implied options from the CPU selection here -# -config X86_L1_CACHE_BYTES - int - default "128" if GENERIC_CPU || MPSC - default "64" if MK8 - -config X86_L1_CACHE_SHIFT - int - default "7" if GENERIC_CPU || MPSC - default "6" if MK8 - -config X86_TSC - bool - default n - -config X86_GOOD_APIC - bool - default y - -config X86_IO_APIC - bool - default XEN_PRIVILEGED_GUEST - -config X86_XEN_GENAPIC - bool - default XEN_PRIVILEGED_GUEST || SMP - -config X86_LOCAL_APIC - bool - default XEN_PRIVILEGED_GUEST - -config MICROCODE - tristate "/dev/cpu/microcode - Intel CPU microcode support" - ---help--- - If you say Y here the 'File systems' section, you will be - able to update the microcode on Intel processors. You will - obviously need the actual microcode binary data itself which is - not shipped with the Linux kernel. - - For latest news and information on obtaining all the required - ingredients for this driver, check: - <http://www.urbanmyth.org/microcode/>. - - To compile this driver as a module, choose M here: the - module will be called microcode. - If you use modprobe or kmod you may also want to add the line - 'alias char-major-10-184 microcode' to your /etc/modules.conf file. - -config X86_MSR - tristate "/dev/cpu/*/msr - Model-specific register support" - help - This device gives privileged processes access to the x86 - Model-Specific Registers (MSRs). It is a character device with - major 202 and minors 0 to 31 for /dev/cpu/0/msr to /dev/cpu/31/msr. - MSR accesses are directed to a specific CPU on multi-processor - systems. - -config X86_CPUID - tristate "/dev/cpu/*/cpuid - CPU information support" - help - This device gives processes access to the x86 CPUID instruction to - be executed on a specific processor. It is a character device - with major 203 and minors 0 to 31 for /dev/cpu/0/cpuid to - /dev/cpu/31/cpuid. - -# disable it for opteron optimized builds because it pulls in ACPI_BOOT -config X86_HT - bool - depends on SMP && !MK8 - default y - -config MATH_EMULATION - bool - -config MCA - bool - -config EISA - bool - -config MTRR - bool "MTRR (Memory Type Range Register) support" - ---help--- - On Intel P6 family processors (Pentium Pro, Pentium II and later) - the Memory Type Range Registers (MTRRs) may be used to control - processor access to memory ranges. This is most useful if you have - a video (VGA) card on a PCI or AGP bus. Enabling write-combining - allows bus write transfers to be combined into a larger transfer - before bursting over the PCI/AGP bus. This can increase performance - of image write operations 2.5 times or more. Saying Y here creates a - /proc/mtrr file which may be used to manipulate your processor's - MTRRs. Typically the X server should use this. - - This code has a reasonably generic interface so that similar - control registers on other processors can be easily supported - as well. - - Saying Y here also fixes a problem with buggy SMP BIOSes which only - set the MTRRs for the boot CPU and not for the secondary CPUs. This - can lead to all sorts of problems, so it's good to say Y here. - - Just say Y here, all x86-64 machines support MTRRs. - - See <file:Documentation/mtrr.txt> for more information. - -config SMP - bool "Symmetric multi-processing support" - ---help--- - This enables support for systems with more than one CPU. If you have - a system with only one CPU, like most personal computers, say N. If - you have a system with more than one CPU, say Y. - - If you say N here, the kernel will run on single and multiprocessor - machines, but will use only one CPU of a multiprocessor machine. If - you say Y here, the kernel will run on many, but not all, - singleprocessor machines. On a singleprocessor machine, the kernel - will run faster if you say N here. - - If you don't know what to do here, say N. - -#config PREEMPT -# bool "Preemptible Kernel" -# ---help--- -# This option reduces the latency of the kernel when reacting to -# real-time or interactive events by allowing a low priority process to -# be preempted even if it is in kernel mode executing a system call. -# This allows applications to run more reliably even when the system is -# under load. On contrary it may also break your drivers and add -# priority inheritance problems to your system. Don't select it if -# you rely on a stable system or have slightly obscure hardware. -# It's also not very well tested on x86-64 currently. -# You have been warned. -# -# Say Y here if you are feeling brave and building a kernel for a -# desktop, embedded or real-time system. Say N if you are unsure. - -config SCHED_SMT - bool "SMT (Hyperthreading) scheduler support" - depends on SMP - default n - help - SMT scheduler support improves the CPU scheduler's decision making - when dealing with Intel Pentium 4 chips with HyperThreading at a - cost of slightly increased overhead in some places. If unsure say - N here. - -config K8_NUMA - bool "K8 NUMA support" - select NUMA - depends on SMP - help - Enable NUMA (Non Unified Memory Architecture) support for - AMD Opteron Multiprocessor systems. The kernel will try to allocate - memory used by a CPU on the local memory controller of the CPU - and add some more NUMA awareness to the kernel. - This code is recommended on all multiprocessor Opteron systems - and normally doesn't hurt on others. - -config NUMA_EMU - bool "NUMA emulation support" - select NUMA - depends on SMP - help - Enable NUMA emulation. A flat machine will be split - into virtual nodes when booted with "numa=fake=N", where N is the - number of nodes. This is only useful for debugging. - -config DISCONTIGMEM - bool - depends on NUMA - default y - -config NUMA - bool - default n - -config HAVE_DEC_LOCK - bool - depends on SMP - default y - -# actually 64 maximum, but you need to fix the APIC code first -# to use clustered mode or whatever your big iron needs -config NR_CPUS - int "Maximum number of CPUs (2-255)" - range 2 255 - depends on SMP - default "16" - help - This allows you to specify the maximum number of CPUs which this - kernel will support. The maximum supported value is 32 and the - minimum value which makes sense is 2. - - This is purely to save memory - each supported CPU requires - memory in the static kernel configuration. - -config HPET_TIMER - bool - default n - help - Use the IA-PC HPET (High Precision Event Timer) to manage - time in preference to the PIT and RTC, if a HPET is - present. The HPET provides a stable time base on SMP - systems, unlike the RTC, but it is more expensive to access, - as it is off-chip. You can find the HPET spec at - <http://www.intel.com/labs/platcomp/hpet/hpetspec.htm>. - - If unsure, say Y. - -config HPET_EMULATE_RTC - bool "Provide RTC interrupt" - depends on HPET_TIMER && RTC=y - -config GART_IOMMU - bool "IOMMU support" - depends on PCI - help - Support the K8 IOMMU. Needed to run systems with more than 4GB of memory - properly with 32-bit PCI devices that do not support DAC (Double Address - Cycle). The IOMMU can be turned off at runtime with the iommu=off parameter. - Normally the kernel will take the right choice by itself. - If unsure, say Y. - -# need this always enabled with GART_IOMMU for the VIA workaround -config SWIOTLB - bool - depends on PCI - default y - -config DUMMY_IOMMU - bool - depends on !GART_IOMMU - default y - help - Don't use IOMMU code. This will cause problems when you have more than 4GB - of memory and any 32-bit devices. Don't turn on unless you know what you - are doing. - -config X86_MCE - bool "Machine check support" if EMBEDDED - default n - help - Include a machine check error handler to report hardware errors. - This version will require the mcelog utility to decode some - machine check error logs. See - ftp://ftp.x86-64.org/pub/linux/tools/mcelog - -config SECCOMP - bool "Enable seccomp to safely compute untrusted bytecode" - depends on PROC_FS - default y - help - This kernel feature is useful for number crunching applications - that may need to compute untrusted bytecode during their - execution. By using pipes or other transports made available to - the process as file descriptors supporting the read/write - syscalls, it's possible to isolate those applications in - their own address space using seccomp. Once seccomp is - enabled via /proc/<pid>/seccomp, it cannot be disabled - and the task is only allowed to execute a few safe syscalls - defined by each seccomp mode. - - If unsure, say Y. Only embedded should say N here. - -endmenu - -# -# Use the generic interrupt handling code in kernel/irq/: -# -config GENERIC_HARDIRQS - bool - default y - -config GENERIC_IRQ_PROBE - bool - default y - -# we have no ISA slots, but we do have ISA-style DMA. -config ISA_DMA_API - bool - default y - -menu "Power management options" - -source kernel/power/Kconfig - -source "arch/x86_64/kernel/cpufreq/Kconfig" - -endmenu - -menu "Bus options (PCI etc.)" - -config PCI - bool "PCI support" - -# x86-64 doesn't support PCI BIOS access from long mode so always go direct. -config PCI_DIRECT - bool - depends on PCI - default y - -config PCI_MMCONFIG - bool "Support mmconfig PCI config space access" - depends on PCI && ACPI - select ACPI_BOOT - -config UNORDERED_IO - bool "Unordered IO mapping access" - depends on EXPERIMENTAL - help - Use unordered stores to access IO memory mappings in device drivers. - Still very experimental. When a driver works on IA64/ppc64/pa-risc it should - work with this option, but it makes the drivers behave differently - from i386. Requires that the driver writer used memory barriers - properly. - -#source "drivers/pci/pcie/Kconfig" - -#source "drivers/pci/Kconfig" - -#source "drivers/pcmcia/Kconfig" - -#source "drivers/pci/hotplug/Kconfig" - -endmenu - - -menu "Executable file formats / Emulations" - -# source "fs/Kconfig.binfmt" - -config IA32_EMULATION - bool "IA32 Emulation" - help - Include code to run 32-bit programs under a 64-bit kernel. You should likely - turn this on, unless you're 100% sure that you don't have any 32-bit programs - left. - -config IA32_AOUT - bool "IA32 a.out support" - depends on IA32_EMULATION - help - Support old a.out binaries in the 32bit emulation. - -config COMPAT - bool - depends on IA32_EMULATION - default y - -config SYSVIPC_COMPAT - bool - depends on COMPAT && SYSVIPC - default y - -config UID16 - bool - depends on IA32_EMULATION - default y - -endmenu - -# source drivers/Kconfig - -# source "drivers/firmware/Kconfig" - -# source fs/Kconfig - -#source "arch/x86_64/oprofile/Kconfig" - -# source "security/Kconfig" - -# source "crypto/Kconfig" - -endmenu diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/Makefile --- a/linux-2.6-xen-sparse/arch/xen/x86_64/Makefile Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,93 +0,0 @@ -# -# x86_64/Makefile -# -# This file is included by the global makefile so that you can add your own -# architecture-specific flags and dependencies. Remember to do have actions -# for "archclean" and "archdep" for cleaning up and making dependencies for -# this architecture -# -# This file is subject to the terms and conditions of the GNU General Public -# License. See the file "COPYING" in the main directory of this archive -# for more details. -# -# Copyright (C) 1994 by Linus Torvalds -# -# 19990713 Artur Skawina <skawina@xxxxxxxxxxxxx> -# Added '-march' and '-mpreferred-stack-boundary' support -# 20000913 Pavel Machek <pavel@xxxxxxx> -# Converted for x86_64 architecture -# 20010105 Andi Kleen, add IA32 compiler. -# ....and later removed it again.... -# 20050205 Jun Nakajima <jun.nakajima@xxxxxxxxx> -# Modified for Xen -# -# $Id: Makefile,v 1.31 2002/03/22 15:56:07 ak Exp $ - -# -# early bootup linking needs 32bit. You can either use real 32bit tools -# here or 64bit tools in 32bit mode. -# -XENARCH := $(subst ",,$(CONFIG_XENARCH)) - -IA32_CC := $(CC) $(CPPFLAGS) -m32 -O2 -fomit-frame-pointer -IA32_LD := $(LD) -m elf_i386 -IA32_AS := $(CC) $(AFLAGS) -m32 -Wa,--32 -traditional -c -IA32_OBJCOPY := $(CROSS_COMPILE)objcopy -IA32_CPP := $(CROSS_COMPILE)gcc -m32 -E -export IA32_CC IA32_LD IA32_AS IA32_OBJCOPY IA32_CPP - - -LDFLAGS := -m elf_x86_64 -#LDFLAGS_vmlinux := -e stext - -CHECKFLAGS += -D__x86_64__ -m64 - -cflags-$(CONFIG_MK8) += $(call cc-option,-march=k8) -cflags-$(CONFIG_MPSC) += $(call cc-option,-march=nocona) -CFLAGS += $(cflags-y) - -CFLAGS += -mno-red-zone -CFLAGS += -mcmodel=kernel -CFLAGS += -pipe -# this makes reading assembly source easier, but produces worse code -# actually it makes the kernel smaller too. -CFLAGS += -fno-reorder-blocks -CFLAGS += -Wno-sign-compare -ifneq ($(CONFIG_DEBUG_INFO),y) -CFLAGS += -fno-asynchronous-unwind-tables -# -fweb shrinks the kernel a bit, but the difference is very small -# it also messes up debugging, so don't use it for now. -#CFLAGS += $(call cc-option,-fweb) -endif -# -funit-at-a-time shrinks the kernel .text considerably -# unfortunately it makes reading oopses harder. -CFLAGS += $(call cc-option,-funit-at-a-time,) - -head-y := arch/xen/x86_64/kernel/head.o arch/xen/x86_64/kernel/head64.o arch/xen/x86_64/kernel/init_task.o - -libs-y += arch/x86_64/lib/ -core-y += arch/xen/x86_64/kernel/ arch/xen/x86_64/mm/ -core-$(CONFIG_IA32_EMULATION) += arch/xen/x86_64/ia32/ -drivers-$(CONFIG_PCI) += arch/xen/x86_64/pci/ -drivers-$(CONFIG_OPROFILE) += arch/x86_64/oprofile/ - -# for clean -obj- += kernel/ mm/ pci/ - -xenflags-y += -Iinclude/asm-xen/asm-x86_64/mach-xen - -CFLAGS += $(xenflags-y) -AFLAGS += $(xenflags-y) - -prepare: include/asm-$(XENARCH)/asm_offsets.h -CLEAN_FILES += include/asm-$(XENARCH)/asm_offsets.h - -arch/$(XENARCH)/kernel/asm-offsets.s: include/asm include/.asm-ignore \ - include/linux/version.h include/config/MARKER - -include/asm-$(XENARCH)/offset.h: arch/$(XENARCH)/kernel/asm-offsets.s - $(call filechk,gen-asm-offsets) - -include/asm-$(XENARCH)/asm_offsets.h: include/asm-$(XENARCH)/offset.h - ln -fsn offset.h include/asm-$(XENARCH)/asm_offsets.h - ln -fsn offset.h include/asm-$(XENARCH)/asm_offset.h diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/ia32/Makefile --- a/linux-2.6-xen-sparse/arch/xen/x86_64/ia32/Makefile Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,66 +0,0 @@ -# -# Makefile for the ia32 kernel emulation subsystem. -# -XENARCH := $(subst ",,$(CONFIG_XENARCH)) - -CFLAGS += -Iarch/$(XENARCH)/kernel - -obj-$(CONFIG_IA32_EMULATION) := ia32entry.o syscall32.o - -c-obj-$(CONFIG_IA32_EMULATION) := sys_ia32.o ia32_ioctl.o \ - ia32_signal.o tls32.o \ - ia32_binfmt.o fpu32.o ptrace32.o - -s-obj-y := - -sysv-$(CONFIG_SYSVIPC) := ipc32.o -c-obj-$(CONFIG_IA32_EMULATION) += $(sysv-y) - -c-obj-$(CONFIG_IA32_AOUT) += ia32_aout.o - -$(obj)/syscall32.o: $(src)/syscall32.c \ - $(foreach F,int80 sysenter syscall,$(obj)/vsyscall-$F.so) - -# syscall32.c currently contains inline asm which has .incbin directives. -# This defeats ccache's signature checks, and also breaks distcc. -# Make sure neither ccache nor distcc compiles this file. -# -$(obj)/syscall32.o: override CC := env CCACHE_DISABLE=1 DISTCC_HOSTS=localhost $(CC) - -# Teach kbuild about targets -targets := $(foreach F,int80 sysenter syscall,vsyscall-$F.o vsyscall-$F.so) - -# The DSO images are built using a special linker script -quiet_cmd_syscall = SYSCALL $@ - cmd_syscall = $(CC) -m32 -nostdlib -shared -s \ - -Wl,-soname=linux-gate.so.1 -o $@ \ - -Wl,-T,$(filter-out FORCE,$^) - - -$(obj)/vsyscall-int80.so $(obj)/vsyscall-sysenter.so $(obj)/vsyscall-syscall.so: \ -$(obj)/vsyscall-%.so: $(obj)/vsyscall.lds $(obj)/vsyscall-%.o FORCE - $(call if_changed,syscall) - -AFLAGS_vsyscall-int80.o = -m32 -I$(obj) -AFLAGS_vsyscall-sysenter.o = -m32 -I$(obj) -AFLAGS_vsyscall-syscall.o = -m32 -I$(obj) -CFLAGS_ia32_ioctl.o += -Ifs/ - -s-link := vsyscall-syscall.o vsyscall-sysenter.o vsyscall-sigreturn.o - -$(obj)/vsyscall.lds: - @ln -fsn $(srctree)/arch/x86_64/ia32/$(notdir $@) $@ - -$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)) $(patsubst %.o,$(obj)/%.S,$(s-obj-y) $(s-link)): - @ln -fsn $(srctree)/arch/x86_64/ia32/$(notdir $@) $@ - -$(obj)/vsyscall-int80.o $(obj)/vsyscall-sysenter.o $(obj)/vsyscall-syscall.o: \ - $(obj)/vsyscall-sigreturn.S $(obj)/../../i386/kernel/vsyscall-note.S - -$(obj)/../../i386/kernel/vsyscall-note.S: - @ln -fsn $(srctree)/arch/i386/kernel/$(notdir $@) $@ - -obj-y += $(c-obj-y) $(s-obj-y) - -clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link)) -clean-files += $(patsubst %.o,%.S,$(s-obj-y) $(s-obj-) $(s-link)) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/ia32/ia32entry.S --- a/linux-2.6-xen-sparse/arch/xen/x86_64/ia32/ia32entry.S Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,629 +0,0 @@ -/* - * Compatibility mode system call entry point for x86-64. - * - * Copyright 2000-2002 Andi Kleen, SuSE Labs. - */ - -#include <asm/dwarf2.h> -#include <asm/calling.h> -#include <asm/offset.h> -#include <asm/current.h> -#include <asm/errno.h> -#include <asm/ia32_unistd.h> -#include <asm/thread_info.h> -#include <asm/segment.h> -#include <asm/vsyscall32.h> -#include <linux/linkage.h> - -#define __XEN_X86_64 1 - - .macro IA32_ARG_FIXUP noebp=0 - movl %edi,%r8d - .if \noebp - .else - movl %ebp,%r9d - .endif - xchg %ecx,%esi - movl %ebx,%edi - movl %edx,%edx /* zero extension */ - .endm - - /* clobbers %eax */ - .macro CLEAR_RREGS - xorl %eax,%eax - movq %rax,R11(%rsp) - movq %rax,R10(%rsp) - movq %rax,R9(%rsp) - movq %rax,R8(%rsp) - .endm - -#if defined (__XEN_X86_64) -#include "../kernel/xen_entry.S" - -#define __swapgs -#define __cli -#define __sti -#else -/* - * Use the native instructions - */ -#define __swapgs swapgs -#define __cli cli -#define __sti sti -#endif - -/* - * 32bit SYSENTER instruction entry. - * - * Arguments: - * %eax System call number. - * %ebx Arg1 - * %ecx Arg2 - * %edx Arg3 - * %esi Arg4 - * %edi Arg5 - * %ebp user stack - * 0(%ebp) Arg6 - * - * Interrupts off. - * - * This is purely a fast path. For anything complicated we use the int 0x80 - * path below. Set up a complete hardware stack frame to share code - * with the int 0x80 path. - */ -ENTRY(ia32_sysenter_target) - CFI_STARTPROC - __swapgs - movq %gs:pda_kernelstack, %rsp - addq $(PDA_STACKOFFSET),%rsp - XEN_UNBLOCK_EVENTS(%r11) - __sti - movl %ebp,%ebp /* zero extension */ - pushq $__USER32_DS - pushq %rbp - pushfq - movl $VSYSCALL32_SYSEXIT, %r10d - pushq $__USER32_CS - movl %eax, %eax - pushq %r10 - pushq %rax - cld - SAVE_ARGS 0,0,1 - /* no need to do an access_ok check here because rbp has been - 32bit zero extended */ -1: movl (%rbp),%r9d - .section __ex_table,"a" - .quad 1b,ia32_badarg - .previous - GET_THREAD_INFO(%r10) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10) - jnz sysenter_tracesys -sysenter_do_call: - cmpl $(IA32_NR_syscalls),%eax - jae ia32_badsys - IA32_ARG_FIXUP 1 - call *ia32_sys_call_table(,%rax,8) - movq %rax,RAX-ARGOFFSET(%rsp) - GET_THREAD_INFO(%r10) - XEN_BLOCK_EVENTS(%r11) - __cli - testl $_TIF_ALLWORK_MASK,threadinfo_flags(%r10) - jnz int_ret_from_sys_call - /* clear IF, that popfq doesn't enable interrupts early */ - andl $~0x200,EFLAGS-R11(%rsp) - RESTORE_ARGS 1,24,1,1,1,1 - popfq - popq %rcx /* User %esp */ - movl $VSYSCALL32_SYSEXIT,%edx /* User %eip */ - __swapgs - XEN_UNBLOCK_EVENTS(%r11) - __sti /* sti only takes effect after the next instruction */ - /* sysexit */ - .byte 0xf, 0x35 /* TBD */ - -sysenter_tracesys: - SAVE_REST - CLEAR_RREGS - movq $-ENOSYS,RAX(%rsp) /* really needed? */ - movq %rsp,%rdi /* &pt_regs -> arg1 */ - call syscall_trace_enter - LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed it */ - RESTORE_REST - movl %ebp, %ebp - /* no need to do an access_ok check here because rbp has been - 32bit zero extended */ -1: movl (%rbp),%r9d - .section __ex_table,"a" - .quad 1b,ia32_badarg - .previous - jmp sysenter_do_call - CFI_ENDPROC - -/* - * 32bit SYSCALL instruction entry. - * - * Arguments: - * %eax System call number. - * %ebx Arg1 - * %ecx return EIP - * %edx Arg3 - * %esi Arg4 - * %edi Arg5 - * %ebp Arg2 [note: not saved in the stack frame, should not be touched] - * %esp user stack - * 0(%esp) Arg6 - * - * Interrupts off. - * - * This is purely a fast path. For anything complicated we use the int 0x80 - * path below. Set up a complete hardware stack frame to share code - * with the int 0x80 path. - */ -ENTRY(ia32_cstar_target) - CFI_STARTPROC - __swapgs - movl %esp,%r8d - movq %gs:pda_kernelstack,%rsp - XEN_UNBLOCK_EVENTS(%r11) - __sti - SAVE_ARGS 8,1,1 - movl %eax,%eax /* zero extension */ - movq %rax,ORIG_RAX-ARGOFFSET(%rsp) - movq %rcx,RIP-ARGOFFSET(%rsp) - movq %rbp,RCX-ARGOFFSET(%rsp) /* this lies slightly to ptrace */ - movl %ebp,%ecx - movq $__USER32_CS,CS-ARGOFFSET(%rsp) - movq $__USER32_DS,SS-ARGOFFSET(%rsp) - movq %r11,EFLAGS-ARGOFFSET(%rsp) - movq %r8,RSP-ARGOFFSET(%rsp) - /* no need to do an access_ok check here because r8 has been - 32bit zero extended */ - /* hardware stack frame is complete now */ -1: movl (%r8),%r9d - .section __ex_table,"a" - .quad 1b,ia32_badarg - .previous - GET_THREAD_INFO(%r10) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10) - jnz cstar_tracesys -cstar_do_call: - cmpl $IA32_NR_syscalls,%eax - jae ia32_badsys - IA32_ARG_FIXUP 1 - call *ia32_sys_call_table(,%rax,8) - movq %rax,RAX-ARGOFFSET(%rsp) - GET_THREAD_INFO(%r10) - XEN_BLOCK_EVENTS(%r11) - __cli - testl $_TIF_ALLWORK_MASK,threadinfo_flags(%r10) - jnz int_ret_from_sys_call - RESTORE_ARGS 1,-ARG_SKIP,1,1,1 - movl RIP-ARGOFFSET(%rsp),%ecx - movl EFLAGS-ARGOFFSET(%rsp),%r11d - movl RSP-ARGOFFSET(%rsp),%esp - __swapgs - sysretl /* TBD */ - -cstar_tracesys: - SAVE_REST - CLEAR_RREGS - movq $-ENOSYS,RAX(%rsp) /* really needed? */ - movq %rsp,%rdi /* &pt_regs -> arg1 */ - call syscall_trace_enter - LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed it */ - RESTORE_REST - movl RSP-ARGOFFSET(%rsp), %r8d - /* no need to do an access_ok check here because r8 has been - 32bit zero extended */ -1: movl (%r8),%r9d - .section __ex_table,"a" - .quad 1b,ia32_badarg - .previous - jmp cstar_do_call - -ia32_badarg: - movq $-EFAULT,%rax - jmp ia32_sysret - CFI_ENDPROC - -/* - * Emulated IA32 system calls via int 0x80. - * - * Arguments: - * %eax System call number. - * %ebx Arg1 - * %ecx Arg2 - * %edx Arg3 - * %esi Arg4 - * %edi Arg5 - * %ebp Arg6 [note: not saved in the stack frame, should not be touched] - * - * Notes: - * Uses the same stack frame as the x86-64 version. - * All registers except %eax must be saved (but ptrace may violate that) - * Arguments are zero extended. For system calls that want sign extension and - * take long arguments a wrapper is needed. Most calls can just be called - * directly. - * Assumes it is only called from user space and entered with interrupts off. - */ - -ENTRY(ia32_syscall) - CFI_STARTPROC - __swapgs - XEN_UNBLOCK_EVENTS(%r11) - __sti - movq (%rsp),%rcx - movq 8(%rsp),%r11 - addq $0x10,%rsp /* skip rcx and r11 */ - movl %eax,%eax - pushq %rax - cld -/* 1: jmp 1b */ - /* note the registers are not zero extended to the sf. - this could be a problem. */ - SAVE_ARGS 0,0,1 - GET_THREAD_INFO(%r10) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10) - jnz ia32_tracesys -ia32_do_syscall: - cmpl $(IA32_NR_syscalls),%eax - jae ia32_badsys - IA32_ARG_FIXUP - call *ia32_sys_call_table(,%rax,8) # xxx: rip relative -ia32_sysret: - movq %rax,RAX-ARGOFFSET(%rsp) - jmp int_ret_from_sys_call - -ia32_tracesys: - SAVE_REST - movq $-ENOSYS,RAX(%rsp) /* really needed? */ - movq %rsp,%rdi /* &pt_regs -> arg1 */ - call syscall_trace_enter - LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed it */ - RESTORE_REST - jmp ia32_do_syscall - -ia32_badsys: - movq $0,ORIG_RAX-ARGOFFSET(%rsp) - movq $-ENOSYS,RAX-ARGOFFSET(%rsp) - jmp int_ret_from_sys_call - -ni_syscall: - movq %rax,%rdi - jmp sys32_ni_syscall - -quiet_ni_syscall: - movq $-ENOSYS,%rax - ret - CFI_ENDPROC - - .macro PTREGSCALL label, func, arg - .globl \label -\label: - leaq \func(%rip),%rax - leaq -ARGOFFSET+8(%rsp),\arg /* 8 for return address */ - jmp ia32_ptregs_common - .endm - - PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn, %rdi - PTREGSCALL stub32_sigreturn, sys32_sigreturn, %rdi - PTREGSCALL stub32_sigaltstack, sys32_sigaltstack, %rdx - PTREGSCALL stub32_sigsuspend, sys32_sigsuspend, %rcx - PTREGSCALL stub32_execve, sys32_execve, %rcx - PTREGSCALL stub32_fork, sys_fork, %rdi - PTREGSCALL stub32_clone, sys32_clone, %rdx - PTREGSCALL stub32_vfork, sys_vfork, %rdi - PTREGSCALL stub32_iopl, sys_iopl, %rsi - PTREGSCALL stub32_rt_sigsuspend, sys_rt_sigsuspend, %rdx - -ENTRY(ia32_ptregs_common) - CFI_STARTPROC - popq %r11 - SAVE_REST - call *%rax - RESTORE_REST - jmp ia32_sysret /* misbalances the return cache */ - CFI_ENDPROC - - .data - .align 8 - .globl ia32_sys_call_table -ia32_sys_call_table: - .quad sys_restart_syscall - .quad sys_exit - .quad stub32_fork - .quad sys_read - .quad sys_write - .quad sys32_open /* 5 */ - .quad sys_close - .quad sys32_waitpid - .quad sys_creat - .quad sys_link - .quad sys_unlink /* 10 */ - .quad stub32_execve - .quad sys_chdir - .quad compat_sys_time - .quad sys_mknod - .quad sys_chmod /* 15 */ - .quad sys_lchown16 - .quad quiet_ni_syscall /* old break syscall holder */ - .quad sys_stat - .quad sys32_lseek - .quad sys_getpid /* 20 */ - .quad compat_sys_mount /* mount */ - .quad sys_oldumount /* old_umount */ - .quad sys_setuid16 - .quad sys_getuid16 - .quad compat_sys_stime /* stime */ /* 25 */ - .quad sys32_ptrace /* ptrace */ - .quad sys_alarm - .quad sys_fstat /* (old)fstat */ - .quad sys_pause - .quad compat_sys_utime /* 30 */ - .quad quiet_ni_syscall /* old stty syscall holder */ - .quad quiet_ni_syscall /* old gtty syscall holder */ - .quad sys_access - .quad sys_nice - .quad quiet_ni_syscall /* 35 */ /* old ftime syscall holder */ - .quad sys_sync - .quad sys32_kill - .quad sys_rename - .quad sys_mkdir - .quad sys_rmdir /* 40 */ - .quad sys_dup - .quad sys32_pipe - .quad compat_sys_times - .quad quiet_ni_syscall /* old prof syscall holder */ - .quad sys_brk /* 45 */ - .quad sys_setgid16 - .quad sys_getgid16 - .quad sys_signal - .quad sys_geteuid16 - .quad sys_getegid16 /* 50 */ - .quad sys_acct - .quad sys_umount /* new_umount */ - .quad quiet_ni_syscall /* old lock syscall holder */ - .quad compat_sys_ioctl - .quad compat_sys_fcntl64 /* 55 */ - .quad quiet_ni_syscall /* old mpx syscall holder */ - .quad sys_setpgid - .quad quiet_ni_syscall /* old ulimit syscall holder */ - .quad sys32_olduname - .quad sys_umask /* 60 */ - .quad sys_chroot - .quad sys32_ustat - .quad sys_dup2 - .quad sys_getppid - .quad sys_getpgrp /* 65 */ - .quad sys_setsid - .quad sys32_sigaction - .quad sys_sgetmask - .quad sys_ssetmask - .quad sys_setreuid16 /* 70 */ - .quad sys_setregid16 - .quad stub32_sigsuspend - .quad compat_sys_sigpending - .quad sys_sethostname - .quad compat_sys_setrlimit /* 75 */ - .quad compat_sys_old_getrlimit /* old_getrlimit */ - .quad compat_sys_getrusage - .quad sys32_gettimeofday - .quad sys32_settimeofday - .quad sys_getgroups16 /* 80 */ - .quad sys_setgroups16 - .quad sys32_old_select - .quad sys_symlink - .quad sys_lstat - .quad sys_readlink /* 85 */ -#ifdef CONFIG_IA32_AOUT - .quad sys_uselib -#else - .quad quiet_ni_syscall -#endif - .quad sys_swapon - .quad sys_reboot - .quad compat_sys_old_readdir - .quad sys32_mmap /* 90 */ - .quad sys_munmap - .quad sys_truncate - .quad sys_ftruncate - .quad sys_fchmod - .quad sys_fchown16 /* 95 */ - .quad sys_getpriority - .quad sys_setpriority - .quad quiet_ni_syscall /* old profil syscall holder */ - .quad compat_sys_statfs - .quad compat_sys_fstatfs /* 100 */ - .quad sys_ioperm - .quad compat_sys_socketcall - .quad sys_syslog - .quad compat_sys_setitimer - .quad compat_sys_getitimer /* 105 */ - .quad compat_sys_newstat - .quad compat_sys_newlstat - .quad compat_sys_newfstat - .quad sys32_uname - .quad stub32_iopl /* 110 */ - .quad sys_vhangup - .quad quiet_ni_syscall /* old "idle" system call */ - .quad sys32_vm86_warning /* vm86old */ - .quad compat_sys_wait4 - .quad sys_swapoff /* 115 */ - .quad sys32_sysinfo - .quad sys32_ipc - .quad sys_fsync - .quad stub32_sigreturn - .quad stub32_clone /* 120 */ - .quad sys_setdomainname - .quad sys_uname - .quad sys_modify_ldt - .quad sys32_adjtimex - .quad sys32_mprotect /* 125 */ - .quad compat_sys_sigprocmask - .quad quiet_ni_syscall /* create_module */ - .quad sys_init_module - .quad sys_delete_module - .quad quiet_ni_syscall /* 130 get_kernel_syms */ - .quad sys_quotactl - .quad sys_getpgid - .quad sys_fchdir - .quad quiet_ni_syscall /* bdflush */ - .quad sys_sysfs /* 135 */ - .quad sys_personality - .quad quiet_ni_syscall /* for afs_syscall */ - .quad sys_setfsuid16 - .quad sys_setfsgid16 - .quad sys_llseek /* 140 */ - .quad compat_sys_getdents - .quad compat_sys_select - .quad sys_flock - .quad sys_msync - .quad compat_sys_readv /* 145 */ - .quad compat_sys_writev - .quad sys_getsid - .quad sys_fdatasync - .quad sys32_sysctl /* sysctl */ - .quad sys_mlock /* 150 */ - .quad sys_munlock - .quad sys_mlockall - .quad sys_munlockall - .quad sys_sched_setparam - .quad sys_sched_getparam /* 155 */ - .quad sys_sched_setscheduler - .quad sys_sched_getscheduler - .quad sys_sched_yield - .quad sys_sched_get_priority_max - .quad sys_sched_get_priority_min /* 160 */ - .quad sys_sched_rr_get_interval - .quad compat_sys_nanosleep - .quad sys_mremap - .quad sys_setresuid16 - .quad sys_getresuid16 /* 165 */ - .quad sys32_vm86_warning /* vm86 */ - .quad quiet_ni_syscall /* query_module */ - .quad sys_poll - .quad compat_sys_nfsservctl - .quad sys_setresgid16 /* 170 */ - .quad sys_getresgid16 - .quad sys_prctl - .quad stub32_rt_sigreturn - .quad sys32_rt_sigaction - .quad sys32_rt_sigprocmask /* 175 */ - .quad sys32_rt_sigpending - .quad compat_sys_rt_sigtimedwait - .quad sys32_rt_sigqueueinfo - .quad stub32_rt_sigsuspend - .quad sys32_pread /* 180 */ - .quad sys32_pwrite - .quad sys_chown16 - .quad sys_getcwd - .quad sys_capget - .quad sys_capset - .quad stub32_sigaltstack - .quad sys32_sendfile - .quad quiet_ni_syscall /* streams1 */ - .quad quiet_ni_syscall /* streams2 */ - .quad stub32_vfork /* 190 */ - .quad compat_sys_getrlimit - .quad sys32_mmap2 - .quad sys32_truncate64 - .quad sys32_ftruncate64 - .quad sys32_stat64 /* 195 */ - .quad sys32_lstat64 - .quad sys32_fstat64 - .quad sys_lchown - .quad sys_getuid - .quad sys_getgid /* 200 */ - .quad sys_geteuid - .quad sys_getegid - .quad sys_setreuid - .quad sys_setregid - .quad sys_getgroups /* 205 */ - .quad sys_setgroups - .quad sys_fchown - .quad sys_setresuid - .quad sys_getresuid - .quad sys_setresgid /* 210 */ - .quad sys_getresgid - .quad sys_chown - .quad sys_setuid - .quad sys_setgid - .quad sys_setfsuid /* 215 */ - .quad sys_setfsgid - .quad sys_pivot_root - .quad sys_mincore - .quad sys_madvise - .quad compat_sys_getdents64 /* 220 getdents64 */ - .quad compat_sys_fcntl64 - .quad quiet_ni_syscall /* tux */ - .quad quiet_ni_syscall /* security */ - .quad sys_gettid - .quad sys_readahead /* 225 */ - .quad sys_setxattr - .quad sys_lsetxattr - .quad sys_fsetxattr - .quad sys_getxattr - .quad sys_lgetxattr /* 230 */ - .quad sys_fgetxattr - .quad sys_listxattr - .quad sys_llistxattr - .quad sys_flistxattr - .quad sys_removexattr /* 235 */ - .quad sys_lremovexattr - .quad sys_fremovexattr - .quad sys_tkill - .quad sys_sendfile64 - .quad compat_sys_futex /* 240 */ - .quad compat_sys_sched_setaffinity - .quad compat_sys_sched_getaffinity - .quad sys32_set_thread_area - .quad sys32_get_thread_area - .quad compat_sys_io_setup /* 245 */ - .quad sys_io_destroy - .quad compat_sys_io_getevents - .quad compat_sys_io_submit - .quad sys_io_cancel - .quad sys_fadvise64 /* 250 */ - .quad quiet_ni_syscall /* free_huge_pages */ - .quad sys_exit_group - .quad sys32_lookup_dcookie - .quad sys_epoll_create - .quad sys_epoll_ctl /* 255 */ - .quad sys_epoll_wait - .quad sys_remap_file_pages - .quad sys_set_tid_address - .quad sys32_timer_create - .quad compat_sys_timer_settime /* 260 */ - .quad compat_sys_timer_gettime - .quad sys_timer_getoverrun - .quad sys_timer_delete - .quad compat_sys_clock_settime - .quad compat_sys_clock_gettime /* 265 */ - .quad compat_sys_clock_getres - .quad compat_sys_clock_nanosleep - .quad compat_sys_statfs64 - .quad compat_sys_fstatfs64 - .quad sys_tgkill /* 270 */ - .quad compat_sys_utimes - .quad sys32_fadvise64_64 - .quad quiet_ni_syscall /* sys_vserver */ - .quad sys_mbind - .quad compat_sys_get_mempolicy /* 275 */ - .quad sys_set_mempolicy - .quad compat_sys_mq_open - .quad sys_mq_unlink - .quad compat_sys_mq_timedsend - .quad compat_sys_mq_timedreceive /* 280 */ - .quad compat_sys_mq_notify - .quad compat_sys_mq_getsetattr - .quad quiet_ni_syscall /* reserved for kexec */ - .quad compat_sys_waitid - .quad quiet_ni_syscall /* sys_altroot */ - .quad sys_add_key - .quad sys_request_key - .quad sys_keyctl - /* don't forget to change IA32_NR_syscalls */ -ia32_syscall_end: - .rept IA32_NR_syscalls-(ia32_syscall_end-ia32_sys_call_table)/8 - .quad ni_syscall - .endr diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/ia32/syscall32.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/ia32/syscall32.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,153 +0,0 @@ -/* Copyright 2002,2003 Andi Kleen, SuSE Labs */ - -/* vsyscall handling for 32bit processes. Map a stub page into it - on demand because 32bit cannot reach the kernel's fixmaps */ - -#include <linux/mm.h> -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/gfp.h> -#include <linux/init.h> -#include <linux/stringify.h> -#include <linux/security.h> -#include <asm/proto.h> -#include <asm/tlbflush.h> -#include <asm/ia32_unistd.h> - -#define USE_INT80 - -#ifdef USE_INT80 -/* 32bit VDSOs mapped into user space. */ -asm(".section \".init.data\",\"aw\"\n" - "syscall32_int80:\n" - ".incbin \"arch/xen/x86_64/ia32/vsyscall-int80.so\"\n" - "syscall32_int80_end:\n" - "syscall32_syscall:\n" - ".incbin \"arch/xen/x86_64/ia32/vsyscall-syscall.so\"\n" - "syscall32_syscall_end:\n" - "syscall32_sysenter:\n" - ".incbin \"arch/xen/x86_64/ia32/vsyscall-sysenter.so\"\n" - "syscall32_sysenter_end:\n" - ".previous"); - -extern unsigned char syscall32_int80[], syscall32_int80_end[]; -#else -/* 32bit VDSOs mapped into user space. */ -asm(".section \".init.data\",\"aw\"\n" - "syscall32_syscall:\n" - ".incbin \"arch/xen/x86_64/ia32/vsyscall-syscall.so\"\n" - "syscall32_syscall_end:\n" - "syscall32_sysenter:\n" - ".incbin \"arch/xen/x86_64/ia32/vsyscall-sysenter.so\"\n" - "syscall32_sysenter_end:\n" - ".previous"); - -static int use_sysenter = -1; -#endif - -extern unsigned char syscall32_syscall[], syscall32_syscall_end[]; -extern unsigned char syscall32_sysenter[], syscall32_sysenter_end[]; -extern int sysctl_vsyscall32; - -char *syscall32_page; - -static struct page * -syscall32_nopage(struct vm_area_struct *vma, unsigned long adr, int *type) -{ - struct page *p = virt_to_page(adr - vma->vm_start + syscall32_page); - get_page(p); - return p; -} - -/* Prevent VMA merging */ -static void syscall32_vma_close(struct vm_area_struct *vma) -{ -} - -static struct vm_operations_struct syscall32_vm_ops = { - .close = syscall32_vma_close, - .nopage = syscall32_nopage, -}; - -struct linux_binprm; - -/* Setup a VMA at program startup for the vsyscall page */ -int syscall32_setup_pages(struct linux_binprm *bprm, int exstack) -{ - int npages = (VSYSCALL32_END - VSYSCALL32_BASE) >> PAGE_SHIFT; - struct vm_area_struct *vma; - struct mm_struct *mm = current->mm; - - vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL); - if (!vma) - return -ENOMEM; - if (security_vm_enough_memory(npages)) { - kmem_cache_free(vm_area_cachep, vma); - return -ENOMEM; - } - - memset(vma, 0, sizeof(struct vm_area_struct)); - /* Could randomize here */ - vma->vm_start = VSYSCALL32_BASE; - vma->vm_end = VSYSCALL32_END; - /* MAYWRITE to allow gdb to COW and set breakpoints */ - vma->vm_flags = VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYEXEC|VM_MAYEXEC|VM_MAYWRITE; - vma->vm_flags |= mm->def_flags; - vma->vm_page_prot = protection_map[vma->vm_flags & 7]; - vma->vm_ops = &syscall32_vm_ops; - vma->vm_mm = mm; - - down_write(&mm->mmap_sem); - insert_vm_struct(mm, vma); - mm->total_vm += npages; - up_write(&mm->mmap_sem); - return 0; -} - -static int __init init_syscall32(void) -{ - syscall32_page = (void *)get_zeroed_page(GFP_KERNEL); - if (!syscall32_page) - panic("Cannot allocate syscall32 page"); - -#ifdef USE_INT80 - /* - * At this point we use int 0x80. - */ - memcpy(syscall32_page, syscall32_int80, - syscall32_int80_end - syscall32_int80); -#else - - if (use_sysenter > 0) { - memcpy(syscall32_page, syscall32_sysenter, - syscall32_sysenter_end - syscall32_sysenter); - } else { - memcpy(syscall32_page, syscall32_syscall, - syscall32_syscall_end - syscall32_syscall); - } -#endif - return 0; -} - -/* - * This must be done early in case we have an initrd containing 32-bit - * binaries (e.g., hotplug). This could be pushed upstream to arch/x86_64. - */ -core_initcall(init_syscall32); - -/* May not be __init: called during resume */ -void syscall32_cpu_init(void) -{ -#ifndef USE_INT80 - if (use_sysenter < 0) - use_sysenter = (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL); - - /* Load these always in case some future AMD CPU supports - SYSENTER from compat mode too. */ - checking_wrmsrl(MSR_IA32_SYSENTER_CS, (u64)(__KERNEL_CS | 3)); - checking_wrmsrl(MSR_IA32_SYSENTER_ESP, 0ULL); - checking_wrmsrl(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); - - wrmsrl(MSR_CSTAR, ia32_cstar_target); -#endif -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/ia32/vsyscall-int80.S --- a/linux-2.6-xen-sparse/arch/xen/x86_64/ia32/vsyscall-int80.S Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,57 +0,0 @@ -/* - * Code for the vsyscall page. This version uses the old int $0x80 method. - * - * NOTE: - * 1) __kernel_vsyscall _must_ be first in this page. - * 2) there are alignment constraints on this stub, see vsyscall-sigreturn.S - * for details. - */ -#include <asm/ia32_unistd.h> -#include <asm/offset.h> - - .text - .section .text.vsyscall,"ax" - .globl __kernel_vsyscall - .type __kernel_vsyscall,@function -__kernel_vsyscall: -.LSTART_vsyscall: - int $0x80 - ret -.LEND_vsyscall: - .size __kernel_vsyscall,.-.LSTART_vsyscall - .previous - - .section .eh_frame,"a",@progbits -.LSTARTFRAME: - .long .LENDCIE-.LSTARTCIE -.LSTARTCIE: - .long 0 /* CIE ID */ - .byte 1 /* Version number */ - .string "zR" /* NUL-terminated augmentation string */ - .uleb128 1 /* Code alignment factor */ - .sleb128 -4 /* Data alignment factor */ - .byte 8 /* Return address register column */ - .uleb128 1 /* Augmentation value length */ - .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */ - .byte 0x0c /* DW_CFA_def_cfa */ - .uleb128 4 - .uleb128 4 - .byte 0x88 /* DW_CFA_offset, column 0x8 */ - .uleb128 1 - .align 4 -.LENDCIE: - - .long .LENDFDE1-.LSTARTFDE1 /* Length FDE */ -.LSTARTFDE1: - .long .LSTARTFDE1-.LSTARTFRAME /* CIE pointer */ - .long .LSTART_vsyscall-. /* PC-relative start address */ - .long .LEND_vsyscall-.LSTART_vsyscall - .uleb128 0 /* Augmentation length */ - .align 4 -.LENDFDE1: - -/* - * Get the common code for the sigreturn entry points. - */ -#define SYSCALL_ENTER_KERNEL int $0x80 -#include "vsyscall-sigreturn.S" diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/Makefile --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/Makefile Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,71 +0,0 @@ -# -# Makefile for the linux kernel. -# -XENARCH := $(subst ",,$(CONFIG_XENARCH)) - -CFLAGS += -Iarch/$(XENARCH)/kernel - -extra-y := head.o head64.o init_task.o - -obj-y := process.o signal.o entry.o traps.o \ - ioport.o ldt.o setup.o \ - x8664_ksyms.o vsyscall.o \ - setup64.o e820.o irq.o early_printk.o -c-obj-y := semaphore.o i387.o sys_x86_64.o \ - ptrace.o quirks.o syscall.o bootflag.o - -i386-obj-y := time.o -#obj-y += ../../i386/kernel/timers/ - -s-obj-y := - -#obj-$(CONFIG_X86_MCE) += mce.o -#obj-$(CONFIG_MTRR) += ../../i386/kernel/cpu/mtrr/ -obj-$(CONFIG_ACPI_BOOT) += acpi/ -c-obj-$(CONFIG_X86_MSR) += msr.o -obj-$(CONFIG_MICROCODE) += microcode.o -obj-$(CONFIG_X86_CPUID) += cpuid.o -obj-$(CONFIG_SMP) += smp.o -obj-$(CONFIG_X86_LOCAL_APIC) += apic.o -c-obj-$(CONFIG_X86_LOCAL_APIC) += nmi.o -obj-$(CONFIG_X86_IO_APIC) += io_apic.o mpparse.o -obj-$(CONFIG_X86_XEN_GENAPIC) += genapic.o genapic_xen.o -c-obj-$(CONFIG_X86_IO_APIC) += genapic_cluster.o genapic_flat.o -#obj-$(CONFIG_PM) += suspend.o -#obj-$(CONFIG_SOFTWARE_SUSPEND) += suspend_asm.o -#obj-$(CONFIG_CPU_FREQ) += cpufreq/ -#obj-$(CONFIG_EARLY_PRINTK) += early_printk.o -#obj-$(CONFIG_GART_IOMMU) += pci-gart.o aperture.o -obj-$(CONFIG_DUMMY_IOMMU) += pci-nommu.o -i386-obj-$(CONFIG_DUMMY_IOMMU) += pci-dma.o -i386-obj-$(CONFIG_SWIOTLB) += swiotlb.o -obj-$(CONFIG_KPROBES) += kprobes.o -#obj-$(CONFIG_X86_PM_TIMER) += pmtimer.o - -c-obj-$(CONFIG_MODULES) += module.o - -obj-y += topology.o -c-obj-y += intel_cacheinfo.o - -bootflag-y += ../../../i386/kernel/bootflag.o -cpuid-$(subst m,y,$(CONFIG_X86_CPUID)) += ../../../i386/kernel/cpuid.o -topology-y += ../../../i386/mach-default/topology.o -#swiotlb-$(CONFIG_SWIOTLB) += ../../../ia64/lib/swiotlb.o -microcode-$(subst m,y,$(CONFIG_MICROCODE)) += ../../i386/kernel/microcode.o -intel_cacheinfo-y += ../../../i386/kernel/cpu/intel_cacheinfo.o -quirks-y += ../../i386/kernel/quirks.o - -c-link := init_task.o -s-link := vsyscall.o - -$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-obj-m) $(c-link)) $(patsubst %.o,$(obj)/%.S,$(s-obj-y) $(s-link)): - @ln -fsn $(srctree)/arch/x86_64/kernel/$(notdir $@) $@ - -$(patsubst %.o,$(obj)/%.c,$(i386-obj-y)): - @ln -fsn $(srctree)/arch/xen/i386/kernel/$(notdir $@) $@ - -obj-y += $(c-obj-y) $(s-obj-y) $(i386-obj-y) -obj-m += $(c-obj-m) - -clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-m) $(c-obj-) $(c-link) $(i386-obj-y)) -clean-files += $(patsubst %.o,%.S,$(s-obj-y) $(s-obj-) $(s-link)) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/acpi/Makefile --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/acpi/Makefile Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,20 +0,0 @@ -i386-obj-$(CONFIG_ACPI_BOOT) := boot.o -c-obj-$(CONFIG_X86_IO_APIC) := earlyquirk.o -c-obj-$(CONFIG_ACPI_SLEEP) += sleep.o -s-obj-$(CONFIG_ACPI_SLEEP) += wakeup.o - -c-link := - -$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)): - @ln -fsn $(srctree)/arch/i386/kernel/acpi/$(notdir $@) $@ - -$(patsubst %.o,$(obj)/%.S,$(s-obj-y) $(s-link)): - @ln -fsn $(srctree)/arch/x86_64/kernel/acpi/$(notdir $@) $@ - -$(patsubst %.o,$(obj)/%.c,$(i386-obj-y)): - @ln -fsn $(srctree)/arch/xen/i386/kernel/acpi/$(notdir $@) $@ - -obj-y += $(c-obj-y) $(s-obj-y) $(i386-obj-y) - -clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link)) -clean-files += $(patsubst %.o,%.S,$(s-obj-y) $(s-obj-) $(s-link)) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/apic.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/apic.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,201 +0,0 @@ -/* - * Local APIC handling, local APIC timers - * - * (c) 1999, 2000 Ingo Molnar <mingo@xxxxxxxxxx> - * - * Fixes - * Maciej W. Rozycki : Bits for genuine 82489DX APICs; - * thanks to Eric Gilmore - * and Rolf G. Tews - * for testing these extensively. - * Maciej W. Rozycki : Various updates and fixes. - * Mikael Pettersson : Power Management for UP-APIC. - * Pavel Machek and - * Mikael Pettersson : PM converted to driver model. - */ - -#include <linux/config.h> -#include <linux/init.h> - -#include <linux/mm.h> -#include <linux/irq.h> -#include <linux/delay.h> -#include <linux/bootmem.h> -#include <linux/smp_lock.h> -#include <linux/interrupt.h> -#include <linux/mc146818rtc.h> -#include <linux/kernel_stat.h> -#include <linux/sysdev.h> - -#include <asm/atomic.h> -#include <asm/smp.h> -#include <asm/mtrr.h> -#include <asm/mpspec.h> -#include <asm/desc.h> -#include <asm/arch_hooks.h> -#include <asm/hpet.h> - -#include "io_ports.h" - -/* - * Debug level - */ -int apic_verbosity; -int disable_apic; - -void smp_local_timer_interrupt(struct pt_regs *regs) -{ - - profile_tick(CPU_PROFILING, regs); -#ifndef CONFIG_XEN - int cpu = smp_processor_id(); - - if (--per_cpu(prof_counter, cpu) <= 0) { - /* - * The multiplier may have changed since the last time we got - * to this point as a result of the user writing to - * /proc/profile. In this case we need to adjust the APIC - * timer accordingly. - * - * Interrupts are already masked off at this point. - */ - per_cpu(prof_counter, cpu) = per_cpu(prof_multiplier, cpu); - if (per_cpu(prof_counter, cpu) != - per_cpu(prof_old_multiplier, cpu)) { - __setup_APIC_LVTT(calibration_result/ - per_cpu(prof_counter, cpu)); - per_cpu(prof_old_multiplier, cpu) = - per_cpu(prof_counter, cpu); - } - -#ifdef CONFIG_SMP - update_process_times(user_mode(regs)); -#endif - } -#endif - - /* - * We take the 'long' return path, and there every subsystem - * grabs the appropriate locks (kernel lock/ irq lock). - * - * we might want to decouple profiling from the 'long path', - * and do the profiling totally in assembly. - * - * Currently this isn't too much of an issue (performance wise), - * we can take more than 100K local irqs per second on a 100 MHz P5. - */ -} - -/* - * Local APIC timer interrupt. This is the most natural way for doing - * local interrupts, but local timer interrupts can be emulated by - * broadcast interrupts too. [in case the hw doesn't support APIC timers] - * - * [ if a single-CPU system runs an SMP kernel then we call the local - * interrupt as well. Thus we cannot inline the local irq ... ] - */ -void smp_apic_timer_interrupt(struct pt_regs *regs) -{ - /* - * the NMI deadlock-detector uses this. - */ - add_pda(apic_timer_irqs, 1); - - /* - * NOTE! We'd better ACK the irq immediately, - * because timer handling can be slow. - */ - ack_APIC_irq(); - /* - * update_process_times() expects us to have done irq_enter(). - * Besides, if we don't timer interrupts ignore the global - * interrupt lock, which is the WrongThing (tm) to do. - */ - irq_enter(); - smp_local_timer_interrupt(regs); - irq_exit(); -} - -/* - * This interrupt should _never_ happen with our APIC/SMP architecture - */ -asmlinkage void smp_spurious_interrupt(void) -{ - unsigned int v; - irq_enter(); - /* - * Check if this really is a spurious interrupt and ACK it - * if it is a vectored one. Just in case... - * Spurious interrupts should not be ACKed. - */ - v = apic_read(APIC_ISR + ((SPURIOUS_APIC_VECTOR & ~0x1f) >> 1)); - if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f))) - ack_APIC_irq(); - -#if 0 - static unsigned long last_warning; - static unsigned long skipped; - - /* see sw-dev-man vol 3, chapter 7.4.13.5 */ - if (time_before(last_warning+30*HZ,jiffies)) { - printk(KERN_INFO "spurious APIC interrupt on CPU#%d, %ld skipped.\n", - smp_processor_id(), skipped); - last_warning = jiffies; - skipped = 0; - } else { - skipped++; - } -#endif - irq_exit(); -} - -/* - * This interrupt should never happen with our APIC/SMP architecture - */ - -asmlinkage void smp_error_interrupt(void) -{ - unsigned int v, v1; - - irq_enter(); - /* First tickle the hardware, only then report what went on. -- REW */ - v = apic_read(APIC_ESR); - apic_write(APIC_ESR, 0); - v1 = apic_read(APIC_ESR); - ack_APIC_irq(); - atomic_inc(&irq_err_count); - - /* Here is what the APIC error bits mean: - 0: Send CS error - 1: Receive CS error - 2: Send accept error - 3: Receive accept error - 4: Reserved - 5: Send illegal vector - 6: Received illegal vector - 7: Illegal register address - */ - printk (KERN_DEBUG "APIC error on CPU%d: %02x(%02x)\n", - smp_processor_id(), v , v1); - irq_exit(); -} - -int get_physical_broadcast(void) -{ - return 0xff; -} - -/* - * This initializes the IO-APIC and APIC hardware if this is - * a UP kernel. - */ -int __init APIC_init_uniprocessor (void) -{ -#ifdef CONFIG_X86_IO_APIC - if (smp_found_config) - if (!skip_ioapic_setup && nr_ioapics) - setup_IO_APIC(); -#endif - - return 0; -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/e820.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/e820.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,676 +0,0 @@ -/* - * Handle the memory map. - * The functions here do the job until bootmem takes over. - * $Id: e820.c,v 1.4 2002/09/19 19:25:32 ak Exp $ - * - * Getting sanitize_e820_map() in sync with i386 version by applying change: - * - Provisions for empty E820 memory regions (reported by certain BIOSes). - * Alex Achenbach <xela@xxxxxxx>, December 2002. - * Venkatesh Pallipadi <venkatesh.pallipadi@xxxxxxxxx> - * - */ -#include <linux/config.h> -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/init.h> -#include <linux/bootmem.h> -#include <linux/ioport.h> -#include <linux/string.h> -#include <asm/page.h> -#include <asm/e820.h> -#include <asm/proto.h> -#include <asm/bootsetup.h> -#include <asm-xen/xen-public/memory.h> - -unsigned long pci_mem_start = 0xaeedbabe; - -/* - * PFN of last memory page. - */ -unsigned long end_pfn; -unsigned long end_user_pfn = MAXMEM>>PAGE_SHIFT; -unsigned long end_pfn_map; - -/* - * Add a memory region to the kernel e820 map. - */ -void __init add_memory_region(unsigned long start, unsigned long size, int type) -{ - int x = e820.nr_map; - - if (x == E820MAX) { - printk(KERN_ERR "Ooops! Too many entries in the memory map!\n"); - return; - } - - e820.map[x].addr = start; - e820.map[x].size = size; - e820.map[x].type = type; - e820.nr_map++; -} - -#ifndef CONFIG_XEN -extern char _end[]; - -/* - * end_pfn only includes RAM, while end_pfn_map includes all e820 entries. - * The direct mapping extends to end_pfn_map, so that we can directly access - * apertures, ACPI and other tables without having to play with fixmaps. - */ - -/* - * Last pfn which the user wants to use. - */ - -extern struct resource code_resource, data_resource; - -/* Check for some hardcoded bad areas that early boot is not allowed to touch */ -static inline int bad_addr(unsigned long *addrp, unsigned long size) -{ - unsigned long addr = *addrp, last = addr + size; - - /* various gunk below that needed for SMP startup */ - if (addr < 0x8000) { - *addrp = 0x8000; - return 1; - } - - /* direct mapping tables of the kernel */ - if (last >= table_start<<PAGE_SHIFT && addr < table_end<<PAGE_SHIFT) { - *addrp = table_end << PAGE_SHIFT; - return 1; - } - - /* initrd */ -#ifdef CONFIG_BLK_DEV_INITRD - if (LOADER_TYPE && INITRD_START && last >= INITRD_START && - addr < INITRD_START+INITRD_SIZE) { - *addrp = INITRD_START + INITRD_SIZE; - return 1; - } -#endif - /* kernel code + 640k memory hole (later should not be needed, but - be paranoid for now) */ - if (last >= 640*1024 && addr < __pa_symbol(&_end)) { - *addrp = __pa_symbol(&_end); - return 1; - } - /* XXX ramdisk image here? */ - return 0; -} - -int __init e820_mapped(unsigned long start, unsigned long end, unsigned type) -{ - int i; - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - if (type && ei->type != type) - continue; - if (ei->addr >= end || ei->addr + ei->size < start) - continue; - return 1; - } - return 0; -} - -/* - * Find a free area in a specific range. - */ -unsigned long __init find_e820_area(unsigned long start, unsigned long end, unsigned size) -{ - int i; - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - unsigned long addr = ei->addr, last; - if (ei->type != E820_RAM) - continue; - if (addr < start) - addr = start; - if (addr > ei->addr + ei->size) - continue; - while (bad_addr(&addr, size) && addr+size < ei->addr + ei->size) - ; - last = addr + size; - if (last > ei->addr + ei->size) - continue; - if (last > end) - continue; - return addr; - } - return -1UL; -} - -/* - * Free bootmem based on the e820 table for a node. - */ -void __init e820_bootmem_free(pg_data_t *pgdat, unsigned long start,unsigned long end) -{ - int i; - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - unsigned long last, addr; - - if (ei->type != E820_RAM || - ei->addr+ei->size <= start || - ei->addr > end) - continue; - - addr = round_up(ei->addr, PAGE_SIZE); - if (addr < start) - addr = start; - - last = round_down(ei->addr + ei->size, PAGE_SIZE); - if (last >= end) - last = end; - - if (last > addr && last-addr >= PAGE_SIZE) - free_bootmem_node(pgdat, addr, last-addr); - } -} - -/* - * Find the highest page frame number we have available - */ -unsigned long __init e820_end_of_ram(void) -{ - int i; - unsigned long end_pfn = 0; - - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - unsigned long start, end; - - start = round_up(ei->addr, PAGE_SIZE); - end = round_down(ei->addr + ei->size, PAGE_SIZE); - if (start >= end) - continue; - if (ei->type == E820_RAM) { - if (end > end_pfn<<PAGE_SHIFT) - end_pfn = end>>PAGE_SHIFT; - } else { - if (end > end_pfn_map<<PAGE_SHIFT) - end_pfn_map = end>>PAGE_SHIFT; - } - } - - if (end_pfn > end_pfn_map) - end_pfn_map = end_pfn; - if (end_pfn_map > MAXMEM>>PAGE_SHIFT) - end_pfn_map = MAXMEM>>PAGE_SHIFT; - if (end_pfn > end_user_pfn) - end_pfn = end_user_pfn; - if (end_pfn > end_pfn_map) - end_pfn = end_pfn_map; - - return end_pfn; -} - -/* - * Mark e820 reserved areas as busy for the resource manager. - */ -void __init e820_reserve_resources(void) -{ - int i; - for (i = 0; i < e820.nr_map; i++) { - struct resource *res; - if (e820.map[i].addr + e820.map[i].size > 0x100000000ULL) - continue; - res = alloc_bootmem_low(sizeof(struct resource)); - switch (e820.map[i].type) { - case E820_RAM: res->name = "System RAM"; break; - case E820_ACPI: res->name = "ACPI Tables"; break; - case E820_NVS: res->name = "ACPI Non-volatile Storage"; break; - default: res->name = "reserved"; - } - res->start = e820.map[i].addr; - res->end = res->start + e820.map[i].size - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; - request_resource(&iomem_resource, res); - if (e820.map[i].type == E820_RAM) { - /* - * We don't know which RAM region contains kernel data, - * so we try it repeatedly and let the resource manager - * test it. - */ - request_resource(res, &code_resource); - request_resource(res, &data_resource); - } - } -} - -void __init e820_print_map(char *who) -{ - int i; - - for (i = 0; i < e820.nr_map; i++) { - printk(" %s: %016Lx - %016Lx ", who, - (unsigned long long) e820.map[i].addr, - (unsigned long long) (e820.map[i].addr + e820.map[i].size)); - switch (e820.map[i].type) { - case E820_RAM: printk("(usable)\n"); - break; - case E820_RESERVED: - printk("(reserved)\n"); - break; - case E820_ACPI: - printk("(ACPI data)\n"); - break; - case E820_NVS: - printk("(ACPI NVS)\n"); - break; - default: printk("type %u\n", e820.map[i].type); - break; - } - } -} - -/* - * Sanitize the BIOS e820 map. - * - * Some e820 responses include overlapping entries. The following - * replaces the original e820 map with a new one, removing overlaps. - * - */ -static int __init sanitize_e820_map(struct e820entry * biosmap, char * pnr_map) -{ - struct change_member { - struct e820entry *pbios; /* pointer to original bios entry */ - unsigned long long addr; /* address for this change point */ - }; - static struct change_member change_point_list[2*E820MAX] __initdata; - static struct change_member *change_point[2*E820MAX] __initdata; - static struct e820entry *overlap_list[E820MAX] __initdata; - static struct e820entry new_bios[E820MAX] __initdata; - struct change_member *change_tmp; - unsigned long current_type, last_type; - unsigned long long last_addr; - int chgidx, still_changing; - int overlap_entries; - int new_bios_entry; - int old_nr, new_nr, chg_nr; - int i; - - /* - Visually we're performing the following (1,2,3,4 = memory types)... - - Sample memory map (w/overlaps): - ____22__________________ - ______________________4_ - ____1111________________ - _44_____________________ - 11111111________________ - ____________________33__ - ___________44___________ - __________33333_________ - ______________22________ - ___________________2222_ - _________111111111______ - _____________________11_ - _________________4______ - - Sanitized equivalent (no overlap): - 1_______________________ - _44_____________________ - ___1____________________ - ____22__________________ - ______11________________ - _________1______________ - __________3_____________ - ___________44___________ - _____________33_________ - _______________2________ - ________________1_______ - _________________4______ - ___________________2____ - ____________________33__ - ______________________4_ - */ - - /* if there's only one memory region, don't bother */ - if (*pnr_map < 2) - return -1; - - old_nr = *pnr_map; - - /* bail out if we find any unreasonable addresses in bios map */ - for (i=0; i<old_nr; i++) - if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr) - return -1; - - /* create pointers for initial change-point information (for sorting) */ - for (i=0; i < 2*old_nr; i++) - change_point[i] = &change_point_list[i]; - - /* record all known change-points (starting and ending addresses), - omitting those that are for empty memory regions */ - chgidx = 0; - for (i=0; i < old_nr; i++) { - if (biosmap[i].size != 0) { - change_point[chgidx]->addr = biosmap[i].addr; - change_point[chgidx++]->pbios = &biosmap[i]; - change_point[chgidx]->addr = biosmap[i].addr + biosmap[i].size; - change_point[chgidx++]->pbios = &biosmap[i]; - } - } - chg_nr = chgidx; - - /* sort change-point list by memory addresses (low -> high) */ - still_changing = 1; - while (still_changing) { - still_changing = 0; - for (i=1; i < chg_nr; i++) { - /* if <current_addr> > <last_addr>, swap */ - /* or, if current=<start_addr> & last=<end_addr>, swap */ - if ((change_point[i]->addr < change_point[i-1]->addr) || - ((change_point[i]->addr == change_point[i-1]->addr) && - (change_point[i]->addr == change_point[i]->pbios->addr) && - (change_point[i-1]->addr != change_point[i-1]->pbios->addr)) - ) - { - change_tmp = change_point[i]; - change_point[i] = change_point[i-1]; - change_point[i-1] = change_tmp; - still_changing=1; - } - } - } - - /* create a new bios memory map, removing overlaps */ - overlap_entries=0; /* number of entries in the overlap table */ - new_bios_entry=0; /* index for creating new bios map entries */ - last_type = 0; /* start with undefined memory type */ - last_addr = 0; /* start with 0 as last starting address */ - /* loop through change-points, determining affect on the new bios map */ - for (chgidx=0; chgidx < chg_nr; chgidx++) - { - /* keep track of all overlapping bios entries */ - if (change_point[chgidx]->addr == change_point[chgidx]->pbios->addr) - { - /* add map entry to overlap list (> 1 entry implies an overlap) */ - overlap_list[overlap_entries++]=change_point[chgidx]->pbios; - } - else - { - /* remove entry from list (order independent, so swap with last) */ - for (i=0; i<overlap_entries; i++) - { - if (overlap_list[i] == change_point[chgidx]->pbios) - overlap_list[i] = overlap_list[overlap_entries-1]; - } - overlap_entries--; - } - /* if there are overlapping entries, decide which "type" to use */ - /* (larger value takes precedence -- 1=usable, 2,3,4,4+=unusable) */ - current_type = 0; - for (i=0; i<overlap_entries; i++) - if (overlap_list[i]->type > current_type) - current_type = overlap_list[i]->type; - /* continue building up new bios map based on this information */ - if (current_type != last_type) { - if (last_type != 0) { - new_bios[new_bios_entry].size = - change_point[chgidx]->addr - last_addr; - /* move forward only if the new size was non-zero */ - if (new_bios[new_bios_entry].size != 0) - if (++new_bios_entry >= E820MAX) - break; /* no more space left for new bios entries */ - } - if (current_type != 0) { - new_bios[new_bios_entry].addr = change_point[chgidx]->addr; - new_bios[new_bios_entry].type = current_type; - last_addr=change_point[chgidx]->addr; - } - last_type = current_type; - } - } - new_nr = new_bios_entry; /* retain count for new bios entries */ - - /* copy new bios mapping into original location */ - memcpy(biosmap, new_bios, new_nr*sizeof(struct e820entry)); - *pnr_map = new_nr; - - return 0; -} - -/* - * Copy the BIOS e820 map into a safe place. - * - * Sanity-check it while we're at it.. - * - * If we're lucky and live on a modern system, the setup code - * will have given us a memory map that we can use to properly - * set up memory. If we aren't, we'll fake a memory map. - * - * We check to see that the memory map contains at least 2 elements - * before we'll use it, because the detection code in setup.S may - * not be perfect and most every PC known to man has two memory - * regions: one from 0 to 640k, and one from 1mb up. (The IBM - * thinkpad 560x, for example, does not cooperate with the memory - * detection code.) - */ -static int __init copy_e820_map(struct e820entry * biosmap, int nr_map) -{ - /* Only one memory region (or negative)? Ignore it */ - if (nr_map < 2) - return -1; - - do { - unsigned long start = biosmap->addr; - unsigned long size = biosmap->size; - unsigned long end = start + size; - unsigned long type = biosmap->type; - - /* Overflow in 64 bits? Ignore the memory map. */ - if (start > end) - return -1; - - /* - * Some BIOSes claim RAM in the 640k - 1M region. - * Not right. Fix it up. - * - * This should be removed on Hammer which is supposed to not - * have non e820 covered ISA mappings there, but I had some strange - * problems so it stays for now. -AK - */ - if (type == E820_RAM) { - if (start < 0x100000ULL && end > 0xA0000ULL) { - if (start < 0xA0000ULL) - add_memory_region(start, 0xA0000ULL-start, type); - if (end <= 0x100000ULL) - continue; - start = 0x100000ULL; - size = end - start; - } - } - - add_memory_region(start, size, type); - } while (biosmap++,--nr_map); - return 0; -} - -void __init setup_memory_region(void) -{ - char *who = "BIOS-e820"; - - /* - * Try to copy the BIOS-supplied E820-map. - * - * Otherwise fake a memory map; one section from 0k->640k, - * the next section from 1mb->appropriate_mem_k - */ - sanitize_e820_map(E820_MAP, &E820_MAP_NR); - if (copy_e820_map(E820_MAP, E820_MAP_NR) < 0) { - unsigned long mem_size; - - /* compare results from other methods and take the greater */ - if (ALT_MEM_K < EXT_MEM_K) { - mem_size = EXT_MEM_K; - who = "BIOS-88"; - } else { - mem_size = ALT_MEM_K; - who = "BIOS-e801"; - } - - e820.nr_map = 0; - add_memory_region(0, LOWMEMSIZE(), E820_RAM); - add_memory_region(HIGH_MEMORY, mem_size << 10, E820_RAM); - } - printk(KERN_INFO "BIOS-provided physical RAM map:\n"); - e820_print_map(who); -} - -#else /* CONFIG_XEN */ - -extern unsigned long xen_override_max_pfn; -extern union xen_start_info_union xen_start_info_union; - -unsigned long __init e820_end_of_ram(void) -{ - unsigned long max_end_pfn; - - if (xen_override_max_pfn == 0) { - max_end_pfn = xen_start_info->nr_pages; - /* Default 8MB slack (to balance backend allocations). */ - max_end_pfn += 8 << (20 - PAGE_SHIFT); - } else if (xen_override_max_pfn > xen_start_info->nr_pages) { - max_end_pfn = xen_override_max_pfn; - } else { - max_end_pfn = xen_start_info->nr_pages; - } - - return max_end_pfn; -} - -void __init e820_reserve_resources(void) -{ - dom0_op_t op; - struct dom0_memory_map_entry *map; - unsigned long gapstart, gapsize, last; - int i, found = 0; - - if (!(xen_start_info->flags & SIF_INITDOMAIN)) - return; - - map = alloc_bootmem_low_pages(PAGE_SIZE); - op.cmd = DOM0_PHYSICAL_MEMORY_MAP; - op.u.physical_memory_map.memory_map = map; - op.u.physical_memory_map.max_map_entries = - PAGE_SIZE / sizeof(struct dom0_memory_map_entry); - BUG_ON(HYPERVISOR_dom0_op(&op)); - - last = 0x100000000ULL; - gapstart = 0x10000000; - gapsize = 0x400000; - - for (i = op.u.physical_memory_map.nr_map_entries - 1; i >= 0; i--) { - struct resource *res; - - if ((last > map[i].end) && ((last - map[i].end) > gapsize)) { - gapsize = last - map[i].end; - gapstart = map[i].end; - found = 1; - } - if (map[i].start < last) - last = map[i].start; - - if (map[i].end > 0x100000000ULL) - continue; - res = alloc_bootmem_low(sizeof(struct resource)); - res->name = map[i].is_ram ? "System RAM" : "reserved"; - res->start = map[i].start; - res->end = map[i].end - 1; - res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; - request_resource(&iomem_resource, res); - } - - free_bootmem(__pa(map), PAGE_SIZE); - - if (!found) { - gapstart = HYPERVISOR_memory_op(XENMEM_maximum_ram_page, NULL); - gapstart = (gapstart << PAGE_SHIFT) + 1024*1024; - printk(KERN_ERR "PCI: Warning: Cannot find a gap in the 32bit address range\n" - KERN_ERR "PCI: Unassigned devices with 32bit resource registers may break!\n"); - } - - /* - * Start allocating dynamic PCI memory a bit into the gap, - * aligned up to the nearest megabyte. - * - * Question: should we try to pad it up a bit (do something - * like " + (gapsize >> 3)" in there too?). We now have the - * technology. - */ - pci_mem_start = (gapstart + 0xfffff) & ~0xfffff; - - printk(KERN_INFO "Allocating PCI resources starting at %lx (gap: %lx:%lx)\n", - pci_mem_start, gapstart, gapsize); -} - -#endif - -void __init parse_memopt(char *p, char **from) -{ - end_user_pfn = memparse(p, from); - end_user_pfn >>= PAGE_SHIFT; - xen_override_max_pfn = (unsigned long) end_user_pfn; -} - -/* - * Search for the biggest gap in the low 32 bits of the e820 - * memory space. We pass this space to PCI to assign MMIO resources - * for hotplug or unconfigured devices in. - * Hopefully the BIOS let enough space left. - */ -__init void e820_setup_gap(void) -{ -#ifndef CONFIG_XEN - unsigned long gapstart, gapsize; - unsigned long last; - int i; - int found = 0; - - last = 0x100000000ull; - gapstart = 0x10000000; - gapsize = 0x400000; - i = e820.nr_map; - while (--i >= 0) { - unsigned long long start = e820.map[i].addr; - unsigned long long end = start + e820.map[i].size; - - /* - * Since "last" is at most 4GB, we know we'll - * fit in 32 bits if this condition is true - */ - if (last > end) { - unsigned long gap = last - end; - - if (gap > gapsize) { - gapsize = gap; - gapstart = end; - found = 1; - } - } - if (start < last) - last = start; - } - - if (!found) { - gapstart = (end_pfn << PAGE_SHIFT) + 1024*1024; - printk(KERN_ERR "PCI: Warning: Cannot find a gap in the 32bit address range\n" - KERN_ERR "PCI: Unassigned devices with 32bit resource registers may break!\n"); - } - - /* - * Start allocating dynamic PCI memory a bit into the gap, - * aligned up to the nearest megabyte. - * - * Question: should we try to pad it up a bit (do something - * like " + (gapsize >> 3)" in there too?). We now have the - * technology. - */ - pci_mem_start = (gapstart + 0xfffff) & ~0xfffff; - - printk(KERN_INFO "Allocating PCI resources starting at %lx (gap: %lx:%lx)\n", - pci_mem_start, gapstart, gapsize); -#endif -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/early_printk.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/early_printk.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,251 +0,0 @@ -#include <linux/config.h> -#include <linux/console.h> -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/string.h> -#include <asm/io.h> -#include <asm/processor.h> - -#ifndef CONFIG_XEN - -/* Simple VGA output */ - -#ifdef __i386__ -#define VGABASE (__ISA_IO_base + 0xb8000) -#else -#define VGABASE ((void __iomem *)0xffffffff800b8000UL) -#endif - -#define MAX_YPOS 25 -#define MAX_XPOS 80 - -static int current_ypos = 1, current_xpos = 0; - -static void early_vga_write(struct console *con, const char *str, unsigned n) -{ - char c; - int i, k, j; - - while ((c = *str++) != '\0' && n-- > 0) { - if (current_ypos >= MAX_YPOS) { - /* scroll 1 line up */ - for (k = 1, j = 0; k < MAX_YPOS; k++, j++) { - for (i = 0; i < MAX_XPOS; i++) { - writew(readw(VGABASE + 2*(MAX_XPOS*k + i)), - VGABASE + 2*(MAX_XPOS*j + i)); - } - } - for (i = 0; i < MAX_XPOS; i++) - writew(0x720, VGABASE + 2*(MAX_XPOS*j + i)); - current_ypos = MAX_YPOS-1; - } - if (c == '\n') { - current_xpos = 0; - current_ypos++; - } else if (c != '\r') { - writew(((0x7 << 8) | (unsigned short) c), - VGABASE + 2*(MAX_XPOS*current_ypos + - current_xpos++)); - if (current_xpos >= MAX_XPOS) { - current_xpos = 0; - current_ypos++; - } - } - } -} - -static struct console early_vga_console = { - .name = "earlyvga", - .write = early_vga_write, - .flags = CON_PRINTBUFFER, - .index = -1, -}; - -/* Serial functions loosely based on a similar package from Klaus P. Gerlicher */ - -static int early_serial_base = 0x3f8; /* ttyS0 */ - -#define XMTRDY 0x20 - -#define DLAB 0x80 - -#define TXR 0 /* Transmit register (WRITE) */ -#define RXR 0 /* Receive register (READ) */ -#define IER 1 /* Interrupt Enable */ -#define IIR 2 /* Interrupt ID */ -#define FCR 2 /* FIFO control */ -#define LCR 3 /* Line control */ -#define MCR 4 /* Modem control */ -#define LSR 5 /* Line Status */ -#define MSR 6 /* Modem Status */ -#define DLL 0 /* Divisor Latch Low */ -#define DLH 1 /* Divisor latch High */ - -static int early_serial_putc(unsigned char ch) -{ - unsigned timeout = 0xffff; - while ((inb(early_serial_base + LSR) & XMTRDY) == 0 && --timeout) - cpu_relax(); - outb(ch, early_serial_base + TXR); - return timeout ? 0 : -1; -} - -static void early_serial_write(struct console *con, const char *s, unsigned n) -{ - while (*s && n-- > 0) { - early_serial_putc(*s); - if (*s == '\n') - early_serial_putc('\r'); - s++; - } -} - -#define DEFAULT_BAUD 9600 - -static __init void early_serial_init(char *s) -{ - unsigned char c; - unsigned divisor; - unsigned baud = DEFAULT_BAUD; - char *e; - - if (*s == ',') - ++s; - - if (*s) { - unsigned port; - if (!strncmp(s,"0x",2)) { - early_serial_base = simple_strtoul(s, &e, 16); - } else { - static int bases[] = { 0x3f8, 0x2f8 }; - - if (!strncmp(s,"ttyS",4)) - s += 4; - port = simple_strtoul(s, &e, 10); - if (port > 1 || s == e) - port = 0; - early_serial_base = bases[port]; - } - s += strcspn(s, ","); - if (*s == ',') - s++; - } - - outb(0x3, early_serial_base + LCR); /* 8n1 */ - outb(0, early_serial_base + IER); /* no interrupt */ - outb(0, early_serial_base + FCR); /* no fifo */ - outb(0x3, early_serial_base + MCR); /* DTR + RTS */ - - if (*s) { - baud = simple_strtoul(s, &e, 0); - if (baud == 0 || s == e) - baud = DEFAULT_BAUD; - } - - divisor = 115200 / baud; - c = inb(early_serial_base + LCR); - outb(c | DLAB, early_serial_base + LCR); - outb(divisor & 0xff, early_serial_base + DLL); - outb((divisor >> 8) & 0xff, early_serial_base + DLH); - outb(c & ~DLAB, early_serial_base + LCR); -} - -#else /* CONFIG_XEN */ - -static void -early_serial_write(struct console *con, const char *s, unsigned count) -{ - int n; - - while (count > 0) { - n = HYPERVISOR_console_io(CONSOLEIO_write, count, (char *)s); - if (n <= 0) - break; - count -= n; - s += n; - } -} - -static __init void early_serial_init(char *s) -{ -} - -/* - * No early VGA console on Xen, as we do not have convenient ISA-space - * mappings. Someone should fix this for domain 0. For now, use fake serial. - */ -#define early_vga_console early_serial_console - -#endif - -static struct console early_serial_console = { - .name = "earlyser", - .write = early_serial_write, - .flags = CON_PRINTBUFFER, - .index = -1, -}; - -/* Direct interface for emergencies */ -struct console *early_console = &early_vga_console; -static int early_console_initialized = 0; - -void early_printk(const char *fmt, ...) -{ - char buf[512]; - int n; - va_list ap; - - va_start(ap,fmt); - n = vscnprintf(buf,512,fmt,ap); - early_console->write(early_console,buf,n); - va_end(ap); -} - -static int keep_early; - -int __init setup_early_printk(char *opt) -{ - char *space; - char buf[256]; - - if (early_console_initialized) - return -1; - - opt = strchr(opt, '=') + 1; - - strlcpy(buf,opt,sizeof(buf)); - space = strchr(buf, ' '); - if (space) - *space = 0; - - if (strstr(buf,"keep")) - keep_early = 1; - - if (!strncmp(buf, "serial", 6)) { - early_serial_init(buf + 6); - early_console = &early_serial_console; - } else if (!strncmp(buf, "ttyS", 4)) { - early_serial_init(buf); - early_console = &early_serial_console; - } else if (!strncmp(buf, "vga", 3)) { - early_console = &early_vga_console; - } - early_console_initialized = 1; - register_console(early_console); - return 0; -} - -void __init disable_early_printk(void) -{ - if (!early_console_initialized || !early_console) - return; - if (!keep_early) { - printk("disabling early console\n"); - unregister_console(early_console); - early_console_initialized = 0; - } else { - printk("keeping early console\n"); - } -} - -__setup("earlyprintk=", setup_early_printk); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/entry.S --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/entry.S Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,1019 +0,0 @@ -/* - * linux/arch/x86_64/entry.S - * - * Copyright (C) 1991, 1992 Linus Torvalds - * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs - * Copyright (C) 2000 Pavel Machek <pavel@xxxxxxx> - * - * $Id$ - * - * Jun Nakajima <jun.nakajima@xxxxxxxxx> - * Asit Mallick <asit.k.mallick@xxxxxxxxx> - * Modified for Xen - */ - -/* - * entry.S contains the system-call and fault low-level handling routines. - * - * NOTE: This code handles signal-recognition, which happens every time - * after an interrupt and after each system call. - * - * Normal syscalls and interrupts don't save a full stack frame, this is - * only done for syscall tracing, signals or fork/exec et.al. - * - * A note on terminology: - * - top of stack: Architecture defined interrupt frame from SS to RIP - * at the top of the kernel process stack. - * - partial stack frame: partially saved registers upto R11. - * - full stack frame: Like partial stack frame, but all register saved. - * - * TODO: - * - schedule it carefully for the final hardware. - */ - -#define ASSEMBLY 1 -#include <linux/config.h> -#include <linux/linkage.h> -#include <asm/segment.h> -#include <asm/smp.h> -#include <asm/cache.h> -#include <asm/errno.h> -#include <asm/dwarf2.h> -#include <asm/calling.h> -#include <asm/asm_offset.h> -#include <asm/msr.h> -#include <asm/unistd.h> -#include <asm/thread_info.h> -#include <asm/hw_irq.h> -#include <asm/errno.h> -#include <asm-xen/xen-public/arch-x86_64.h> - -#include "irq_vectors.h" - -#include "xen_entry.S" - - .code64 - -#ifndef CONFIG_PREEMPT -#define retint_kernel retint_restore_args -#endif - -/* - * C code is not supposed to know about undefined top of stack. Every time - * a C function with an pt_regs argument is called from the SYSCALL based - * fast path FIXUP_TOP_OF_STACK is needed. - * RESTORE_TOP_OF_STACK syncs the syscall state after any possible ptregs - * manipulation. - */ - - /* %rsp:at FRAMEEND */ - .macro FIXUP_TOP_OF_STACK tmp - movq $__USER_CS,CS(%rsp) - movq $-1,RCX(%rsp) - .endm - - .macro RESTORE_TOP_OF_STACK tmp,offset=0 - .endm - - .macro FAKE_STACK_FRAME child_rip - /* push in order ss, rsp, eflags, cs, rip */ - xorq %rax, %rax - pushq %rax /* ss */ - CFI_ADJUST_CFA_OFFSET 8 - pushq %rax /* rsp */ - CFI_ADJUST_CFA_OFFSET 8 - CFI_OFFSET rip,0 - pushq $(1<<9) /* eflags - interrupts on */ - CFI_ADJUST_CFA_OFFSET 8 - pushq $__KERNEL_CS /* cs */ - CFI_ADJUST_CFA_OFFSET 8 - pushq \child_rip /* rip */ - CFI_ADJUST_CFA_OFFSET 8 - CFI_OFFSET rip,0 - pushq %rax /* orig rax */ - CFI_ADJUST_CFA_OFFSET 8 - .endm - - .macro UNFAKE_STACK_FRAME - addq $8*6, %rsp - CFI_ADJUST_CFA_OFFSET -(6*8) - .endm - - .macro CFI_DEFAULT_STACK - CFI_ADJUST_CFA_OFFSET (SS) - CFI_OFFSET r15,R15-SS - CFI_OFFSET r14,R14-SS - CFI_OFFSET r13,R13-SS - CFI_OFFSET r12,R12-SS - CFI_OFFSET rbp,RBP-SS - CFI_OFFSET rbx,RBX-SS - CFI_OFFSET r11,R11-SS - CFI_OFFSET r10,R10-SS - CFI_OFFSET r9,R9-SS - CFI_OFFSET r8,R8-SS - CFI_OFFSET rax,RAX-SS - CFI_OFFSET rcx,RCX-SS - CFI_OFFSET rdx,RDX-SS - CFI_OFFSET rsi,RSI-SS - CFI_OFFSET rdi,RDI-SS - CFI_OFFSET rsp,RSP-SS - CFI_OFFSET rip,RIP-SS - .endm - - /* - * Must be consistent with the definition in arch-x86_64.h: - * struct iret_context { - * u64 rax, r11, rcx, flags, rip, cs, rflags, rsp, ss; - * }; - * #define VGCF_IN_SYSCALL (1<<8) - */ - .macro HYPERVISOR_IRET flag - pushq $\flag - jmp hypercall_page + (__HYPERVISOR_iret * 32) - .endm - - .macro SWITCH_TO_KERNEL ssoff,adjust=0 - jc 1f - orb $1,\ssoff-\adjust+4(%rsp) -1: - .endm - -/* - * A newly forked process directly context switches into this. - */ -/* rdi: prev */ -ENTRY(ret_from_fork) - CFI_STARTPROC - CFI_DEFAULT_STACK - call schedule_tail - GET_THREAD_INFO(%rcx) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%rcx) - jnz rff_trace -rff_action: - RESTORE_REST - testl $3,CS-ARGOFFSET(%rsp) # from kernel_thread? - je int_ret_from_sys_call - testl $_TIF_IA32,threadinfo_flags(%rcx) - jnz int_ret_from_sys_call - RESTORE_TOP_OF_STACK %rdi,ARGOFFSET - jmp ret_from_sys_call -rff_trace: - movq %rsp,%rdi - call syscall_trace_leave - GET_THREAD_INFO(%rcx) - jmp rff_action - CFI_ENDPROC - -/* - * System call entry. Upto 6 arguments in registers are supported. - * - * SYSCALL does not save anything on the stack and does not change the - * stack pointer. - */ - -/* - * Register setup: - * rax system call number - * rdi arg0 - * rcx return address for syscall/sysret, C arg3 - * rsi arg1 - * rdx arg2 - * r10 arg3 (--> moved to rcx for C) - * r8 arg4 - * r9 arg5 - * r11 eflags for syscall/sysret, temporary for C - * r12-r15,rbp,rbx saved by C code, not touched. - * - * Interrupts are off on entry. - * Only called from user space. - * - * XXX if we had a free scratch register we could save the RSP into the stack frame - * and report it properly in ps. Unfortunately we haven't. - */ - -ENTRY(system_call) - CFI_STARTPROC - SAVE_ARGS -8,0 - movq %rax,ORIG_RAX-ARGOFFSET(%rsp) - XEN_UNBLOCK_EVENTS(%r11) - GET_THREAD_INFO(%rcx) - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%rcx) - jnz tracesys - cmpq $__NR_syscall_max,%rax - ja badsys - movq %r10,%rcx - call *sys_call_table(,%rax,8) # XXX: rip relative - movq %rax,RAX-ARGOFFSET(%rsp) -/* - * Syscall return path ending with SYSRET (fast path) - * Has incomplete stack frame and undefined top of stack. - */ - .globl ret_from_sys_call -ret_from_sys_call: - movl $_TIF_ALLWORK_MASK,%edi - /* edi: flagmask */ -sysret_check: - GET_THREAD_INFO(%rcx) - XEN_BLOCK_EVENTS(%rsi) - movl threadinfo_flags(%rcx),%edx - andl %edi,%edx - jnz sysret_careful - XEN_UNBLOCK_EVENTS(%rsi) - RESTORE_ARGS 0,8,0 - HYPERVISOR_IRET VGCF_IN_SYSCALL - - /* Handle reschedules */ - /* edx: work, edi: workmask */ -sysret_careful: - bt $TIF_NEED_RESCHED,%edx - jnc sysret_signal - XEN_BLOCK_EVENTS(%rsi) - pushq %rdi - call schedule - popq %rdi - jmp sysret_check - - /* Handle a signal */ -sysret_signal: -/* sti */ - XEN_UNBLOCK_EVENTS(%rsi) - testl $(_TIF_SIGPENDING|_TIF_NOTIFY_RESUME|_TIF_SINGLESTEP),%edx - jz 1f - - /* Really a signal */ - /* edx: work flags (arg3) */ - leaq do_notify_resume(%rip),%rax - leaq -ARGOFFSET(%rsp),%rdi # &pt_regs -> arg1 - xorl %esi,%esi # oldset -> arg2 - call ptregscall_common -1: movl $_TIF_NEED_RESCHED,%edi - jmp sysret_check - - /* Do syscall tracing */ -tracesys: - SAVE_REST - movq $-ENOSYS,RAX(%rsp) - FIXUP_TOP_OF_STACK %rdi - movq %rsp,%rdi - call syscall_trace_enter - LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed it */ - RESTORE_REST - cmpq $__NR_syscall_max,%rax - ja 1f - movq %r10,%rcx /* fixup for C */ - call *sys_call_table(,%rax,8) - movq %rax,RAX-ARGOFFSET(%rsp) -1: SAVE_REST - movq %rsp,%rdi - call syscall_trace_leave - RESTORE_TOP_OF_STACK %rbx - RESTORE_REST - jmp ret_from_sys_call - -badsys: - movq $-ENOSYS,RAX-ARGOFFSET(%rsp) - jmp ret_from_sys_call - -/* - * Syscall return path ending with IRET. - * Has correct top of stack, but partial stack frame. - */ -ENTRY(int_ret_from_sys_call) - XEN_BLOCK_EVENTS(%rsi) - testb $3,CS-ARGOFFSET(%rsp) - jnz 1f - /* Need to set the proper %ss (not NULL) for ring 3 iretq */ - movl $__KERNEL_DS,SS-ARGOFFSET(%rsp) - jmp retint_restore_args # retrun from ring3 kernel -1: - movl $_TIF_ALLWORK_MASK,%edi - /* edi: mask to check */ -int_with_check: - GET_THREAD_INFO(%rcx) - movl threadinfo_flags(%rcx),%edx - andl %edi,%edx - jnz int_careful - jmp retint_restore_args - - /* Either reschedule or signal or syscall exit tracking needed. */ - /* First do a reschedule test. */ - /* edx: work, edi: workmask */ -int_careful: - bt $TIF_NEED_RESCHED,%edx - jnc int_very_careful -/* sti */ - XEN_UNBLOCK_EVENTS(%rsi) - pushq %rdi - call schedule - popq %rdi - cli - jmp int_with_check - - /* handle signals and tracing -- both require a full stack frame */ -int_very_careful: -/* sti */ - XEN_UNBLOCK_EVENTS(%rsi) - SAVE_REST - /* Check for syscall exit trace */ - testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP),%edx - jz int_signal - pushq %rdi - leaq 8(%rsp),%rdi # &ptregs -> arg1 - call syscall_trace_leave - popq %rdi - andl $~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP),%edi - cli - jmp int_restore_rest - -int_signal: - testl $(_TIF_NOTIFY_RESUME|_TIF_SIGPENDING|_TIF_SINGLESTEP),%edx - jz 1f - movq %rsp,%rdi # &ptregs -> arg1 - xorl %esi,%esi # oldset -> arg2 - call do_notify_resume -1: movl $_TIF_NEED_RESCHED,%edi -int_restore_rest: - RESTORE_REST - cli - jmp int_with_check - CFI_ENDPROC - -/* - * Certain special system calls that need to save a complete full stack frame. - */ - - .macro PTREGSCALL label,func,arg - .globl \label -\label: - leaq \func(%rip),%rax - leaq -ARGOFFSET+8(%rsp),\arg /* 8 for return address */ - jmp ptregscall_common - .endm - - PTREGSCALL stub_clone, sys_clone, %r8 - PTREGSCALL stub_fork, sys_fork, %rdi - PTREGSCALL stub_vfork, sys_vfork, %rdi - PTREGSCALL stub_rt_sigsuspend, sys_rt_sigsuspend, %rdx - PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx - PTREGSCALL stub_iopl, sys_iopl, %rsi - -ENTRY(ptregscall_common) - CFI_STARTPROC - popq %r11 - CFI_ADJUST_CFA_OFFSET -8 - SAVE_REST - movq %r11, %r15 - FIXUP_TOP_OF_STACK %r11 - call *%rax - RESTORE_TOP_OF_STACK %r11 - movq %r15, %r11 - RESTORE_REST - pushq %r11 - CFI_ADJUST_CFA_OFFSET 8 - ret - CFI_ENDPROC - -ENTRY(stub_execve) - CFI_STARTPROC - popq %r11 - CFI_ADJUST_CFA_OFFSET -8 - SAVE_REST - movq %r11, %r15 - FIXUP_TOP_OF_STACK %r11 - call sys_execve - GET_THREAD_INFO(%rcx) - bt $TIF_IA32,threadinfo_flags(%rcx) - jc exec_32bit - RESTORE_TOP_OF_STACK %r11 - movq %r15, %r11 - RESTORE_REST - push %r11 - ret - -exec_32bit: - CFI_ADJUST_CFA_OFFSET REST_SKIP - movq %rax,RAX(%rsp) - RESTORE_REST - jmp int_ret_from_sys_call - CFI_ENDPROC - -/* - * sigreturn is special because it needs to restore all registers on return. - * This cannot be done with SYSRET, so use the IRET return path instead. - */ -ENTRY(stub_rt_sigreturn) - CFI_STARTPROC - addq $8, %rsp - SAVE_REST - movq %rsp,%rdi - FIXUP_TOP_OF_STACK %r11 - call sys_rt_sigreturn - movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer - RESTORE_REST - jmp int_ret_from_sys_call - CFI_ENDPROC - -/* - * Interrupt entry/exit. - * - * Interrupt entry points save only callee clobbered registers in fast path. - * - * Entry runs with interrupts off. - */ - -/* 0(%rsp): interrupt number */ - .macro interrupt func - CFI_STARTPROC simple - CFI_DEF_CFA rsp,(SS-RDI) - CFI_REL_OFFSET rsp,(RSP-ORIG_RAX) - CFI_REL_OFFSET rip,(RIP-ORIG_RAX) - cld -#ifdef CONFIG_DEBUG_INFO - SAVE_ALL - movq %rsp,%rdi - /* - * Setup a stack frame pointer. This allows gdb to trace - * back to the original stack. - */ - movq %rsp,%rbp - CFI_DEF_CFA_REGISTER rbp -#else - SAVE_ARGS - leaq -ARGOFFSET(%rsp),%rdi # arg1 for handler -#endif -#if 0 /* For Xen we don't need to do this */ - testl $3,CS(%rdi) - je 1f - swapgs -#endif -1: addl $1,%gs:pda_irqcount # RED-PEN should check preempt count - movq %gs:pda_irqstackptr,%rax - cmoveq %rax,%rsp - pushq %rdi # save old stack - call \func - .endm - -retint_check: - movl threadinfo_flags(%rcx),%edx - andl %edi,%edx - jnz retint_careful -retint_restore_args: - movb EVENT_MASK-REST_SKIP(%rsp), %al - notb %al # %al == ~saved_mask - XEN_GET_VCPU_INFO(%rsi) - andb evtchn_upcall_mask(%rsi),%al - andb $1,%al # %al == mask & ~saved_mask - jnz restore_all_enable_events # != 0 => reenable event delivery - XEN_PUT_VCPU_INFO(%rsi) - - RESTORE_ARGS 0,8,0 - testb $3,8(%rsp) # check CS - jnz user_mode -kernel_mode: - orb $3,1*8(%rsp) - iretq -user_mode: - HYPERVISOR_IRET 0 - - /* edi: workmask, edx: work */ -retint_careful: - bt $TIF_NEED_RESCHED,%edx - jnc retint_signal - XEN_UNBLOCK_EVENTS(%rsi) -/* sti */ - pushq %rdi - call schedule - popq %rdi - XEN_BLOCK_EVENTS(%rsi) - GET_THREAD_INFO(%rcx) -/* cli */ - jmp retint_check - -retint_signal: - testl $(_TIF_SIGPENDING|_TIF_NOTIFY_RESUME|_TIF_SINGLESTEP),%edx - jz retint_restore_args - XEN_UNBLOCK_EVENTS(%rsi) - SAVE_REST - movq $-1,ORIG_RAX(%rsp) - xorq %rsi,%rsi # oldset - movq %rsp,%rdi # &pt_regs - call do_notify_resume - RESTORE_REST - XEN_BLOCK_EVENTS(%rsi) - movl $_TIF_NEED_RESCHED,%edi - GET_THREAD_INFO(%rcx) - jmp retint_check - -#ifdef CONFIG_PREEMPT - /* Returning to kernel space. Check if we need preemption */ - /* rcx: threadinfo. interrupts off. */ - .p2align -retint_kernel: - cmpl $0,threadinfo_preempt_count(%rcx) - jnz retint_restore_args - bt $TIF_NEED_RESCHED,threadinfo_flags(%rcx) - jnc retint_restore_args - bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */ - jnc retint_restore_args - call preempt_schedule_irq - jmp retint_kernel /* check again */ -#endif - CFI_ENDPROC - -/* - * APIC interrupts. - */ - .macro apicinterrupt num,func - pushq $\num-256 - interrupt \func - jmp error_entry - CFI_ENDPROC - .endm - -#if 0 -ENTRY(reschedule_interrupt) - apicinterrupt RESCHEDULE_VECTOR,smp_reschedule_interrupt - -ENTRY(invalidate_interrupt) - apicinterrupt INVALIDATE_TLB_VECTOR,smp_invalidate_interrupt - -ENTRY(call_function_interrupt) - apicinterrupt CALL_FUNCTION_VECTOR,smp_call_function_interrupt -#endif - -#ifdef CONFIG_X86_LOCAL_APIC -ENTRY(apic_timer_interrupt) - apicinterrupt LOCAL_TIMER_VECTOR,smp_apic_timer_interrupt - -ENTRY(error_interrupt) - apicinterrupt ERROR_APIC_VECTOR,smp_error_interrupt - -ENTRY(spurious_interrupt) - apicinterrupt SPURIOUS_APIC_VECTOR,smp_spurious_interrupt -#endif - -/* - * Exception entry points. - */ - .macro zeroentry sym - movq (%rsp),%rcx - movq 8(%rsp),%r11 - addq $0x10,%rsp /* skip rcx and r11 */ - pushq $0 /* push error code/oldrax */ - pushq %rax /* push real oldrax to the rdi slot */ - leaq \sym(%rip),%rax - jmp error_entry - .endm - - .macro errorentry sym - movq (%rsp),%rcx - movq 8(%rsp),%r11 - addq $0x10,%rsp /* rsp points to the error code */ - pushq %rax - leaq \sym(%rip),%rax - jmp error_entry - .endm - -#if 0 - /* error code is on the stack already */ - /* handle NMI like exceptions that can happen everywhere */ - .macro paranoidentry sym - movq (%rsp),%rcx - movq 8(%rsp),%r11 - addq $0x10,%rsp /* skip rcx and r11 */ - SAVE_ALL - cld - movl $1,%ebx - movl $MSR_GS_BASE,%ecx - rdmsr - testl %edx,%edx - js 1f -/* swapgs */ - xorl %ebx,%ebx -1: movq %rsp,%rdi - movq ORIG_RAX(%rsp),%rsi - movq $-1,ORIG_RAX(%rsp) - call \sym - cli - .endm -#endif - -/* - * Exception entry point. This expects an error code/orig_rax on the stack - * and the exception handler in %rax. - */ -ENTRY(error_entry) - CFI_STARTPROC simple - CFI_DEF_CFA rsp,(SS-RDI) - CFI_REL_OFFSET rsp,(RSP-RDI) - CFI_REL_OFFSET rip,(RIP-RDI) - /* rdi slot contains rax, oldrax contains error code */ - cld - subq $14*8,%rsp - CFI_ADJUST_CFA_OFFSET (14*8) - movq %rsi,13*8(%rsp) - CFI_REL_OFFSET rsi,RSI - movq 14*8(%rsp),%rsi /* load rax from rdi slot */ - movq %rdx,12*8(%rsp) - CFI_REL_OFFSET rdx,RDX - movq %rcx,11*8(%rsp) - CFI_REL_OFFSET rcx,RCX - movq %rsi,10*8(%rsp) /* store rax */ - CFI_REL_OFFSET rax,RAX - movq %r8, 9*8(%rsp) - CFI_REL_OFFSET r8,R8 - movq %r9, 8*8(%rsp) - CFI_REL_OFFSET r9,R9 - movq %r10,7*8(%rsp) - CFI_REL_OFFSET r10,R10 - movq %r11,6*8(%rsp) - CFI_REL_OFFSET r11,R11 - movq %rbx,5*8(%rsp) - CFI_REL_OFFSET rbx,RBX - movq %rbp,4*8(%rsp) - CFI_REL_OFFSET rbp,RBP - movq %r12,3*8(%rsp) - CFI_REL_OFFSET r12,R12 - movq %r13,2*8(%rsp) - CFI_REL_OFFSET r13,R13 - movq %r14,1*8(%rsp) - CFI_REL_OFFSET r14,R14 - movq %r15,(%rsp) - CFI_REL_OFFSET r15,R15 -#if 0 - cmpl $__KERNEL_CS,CS(%rsp) - je error_kernelspace -#endif -error_call_handler: - movq %rdi, RDI(%rsp) - movq %rsp,%rdi - movq ORIG_RAX(%rsp),%rsi # get error code - movq $-1,ORIG_RAX(%rsp) - call *%rax -error_exit: - RESTORE_REST -/* cli */ - XEN_BLOCK_EVENTS(%rsi) - GET_THREAD_INFO(%rcx) - testb $3,CS-ARGOFFSET(%rsp) - jz retint_kernel - movl threadinfo_flags(%rcx),%edx - movl $_TIF_WORK_MASK,%edi - andl %edi,%edx - jnz retint_careful - jmp retint_restore_args - -error_kernelspace: - /* - * We need to re-write the logic here because we don't do iretq to - * to return to user mode. It's still possible that we get trap/fault - * in the kernel (when accessing buffers pointed to by system calls, - * for example). - * - */ -#if 0 - incl %ebx - /* There are two places in the kernel that can potentially fault with - usergs. Handle them here. The exception handlers after - iret run with kernel gs again, so don't set the user space flag. - B stepping K8s sometimes report an truncated RIP for IRET - exceptions returning to compat mode. Check for these here too. */ - leaq iret_label(%rip),%rbp - cmpq %rbp,RIP(%rsp) - je error_swapgs - movl %ebp,%ebp /* zero extend */ - cmpq %rbp,RIP(%rsp) - je error_swapgs - cmpq $gs_change,RIP(%rsp) - je error_swapgs - jmp error_sti -#endif - -ENTRY(hypervisor_callback) - zeroentry do_hypervisor_callback - -/* - * Copied from arch/xen/i386/kernel/entry.S - */ -# A note on the "critical region" in our callback handler. -# We want to avoid stacking callback handlers due to events occurring -# during handling of the last event. To do this, we keep events disabled -# until we've done all processing. HOWEVER, we must enable events before -# popping the stack frame (can't be done atomically) and so it would still -# be possible to get enough handler activations to overflow the stack. -# Although unlikely, bugs of that kind are hard to track down, so we'd -# like to avoid the possibility. -# So, on entry to the handler we detect whether we interrupted an -# existing activation in its critical region -- if so, we pop the current -# activation and restart the handler using the previous one. -ENTRY(do_hypervisor_callback) # do_hyperviosr_callback(struct *pt_regs) -# Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will -# see the correct pointer to the pt_regs - addq $8, %rsp # we don't return, adjust the stack frame -11: movb $0, EVENT_MASK(%rsp) - call evtchn_do_upcall - jmp error_exit - -#ifdef CONFIG_X86_LOCAL_APIC -ENTRY(nmi) - zeroentry do_nmi_callback -ENTRY(do_nmi_callback) - addq $8, %rsp - call do_nmi - RESTORE_REST - XEN_BLOCK_EVENTS(%rsi) - GET_THREAD_INFO(%rcx) - jmp retint_restore_args -#endif - - ALIGN -restore_all_enable_events: - XEN_UNBLOCK_EVENTS(%rsi) # %rsi is already set up... - -scrit: /**** START OF CRITICAL REGION ****/ - XEN_TEST_PENDING(%rsi) - jnz 14f # process more events if necessary... - XEN_PUT_VCPU_INFO(%rsi) - RESTORE_ARGS 0,8,0 - testb $3,8(%rsp) # check CS - jnz crit_user_mode - orb $3,1*8(%rsp) - iretq -crit_user_mode: - HYPERVISOR_IRET 0 - -14: XEN_LOCKED_BLOCK_EVENTS(%rsi) - XEN_PUT_VCPU_INFO(%rsi) - SAVE_REST - movq %rsp,%rdi # set the argument again - jmp 11b -ecrit: /**** END OF CRITICAL REGION ****/ -# At this point, unlike on x86-32, we don't do the fixup to simplify the -# code and the stack frame is more complex on x86-64. -# When the kernel is interrupted in the critical section, the kernel -# will do IRET in that case, and everything will be restored at that point, -# i.e. it just resumes from the next instruction interrupted with the same context. - -# Hypervisor uses this for application faults while it executes. -ENTRY(failsafe_callback) - addq $0x10,%rsp /* skip rcx and r11 */ -1: mov (%rsp),%ds -2: mov 8(%rsp),%es -3: mov 16(%rsp),%fs -4: mov 24(%rsp),%gs - addq $0x20,%rsp /* skip the above selectors */ - SAVE_ALL - jmp error_exit -.section .fixup,"ax"; \ -6: movq $0,(%rsp); \ - jmp 1b; \ -7: movq $0,8(%rsp); \ - jmp 2b; \ -8: movq $0,16(%rsp); \ - jmp 3b; \ -9: movq $0,24(%rsp); \ - jmp 4b; \ -.previous; \ -.section __ex_table,"a";\ - .align 16; \ - .quad 1b,6b; \ - .quad 2b,7b; \ - .quad 3b,8b; \ - .quad 4b,9b; \ -.previous - -#if 0 - .section __ex_table,"a" - .align 8 - .quad gs_change,bad_gs - .previous - .section .fixup,"ax" - /* running with kernelgs */ -bad_gs: -/* swapgs */ /* switch back to user gs */ - xorl %eax,%eax - movl %eax,%gs - jmp 2b - .previous -#endif - -/* - * Create a kernel thread. - * - * C extern interface: - * extern long kernel_thread(int (*fn)(void *), void * arg, unsigned long flags) - * - * asm input arguments: - * rdi: fn, rsi: arg, rdx: flags - */ -ENTRY(kernel_thread) - CFI_STARTPROC - FAKE_STACK_FRAME $child_rip - SAVE_ALL - - # rdi: flags, rsi: usp, rdx: will be &pt_regs - movq %rdx,%rdi - orq kernel_thread_flags(%rip),%rdi - movq $-1, %rsi - movq %rsp, %rdx - - xorl %r8d,%r8d - xorl %r9d,%r9d - - # clone now - call do_fork - movq %rax,RAX(%rsp) - xorl %edi,%edi - - /* - * It isn't worth to check for reschedule here, - * so internally to the x86_64 port you can rely on kernel_thread() - * not to reschedule the child before returning, this avoids the need - * of hacks for example to fork off the per-CPU idle tasks. - * [Hopefully no generic code relies on the reschedule -AK] - */ - RESTORE_ALL - UNFAKE_STACK_FRAME - ret - CFI_ENDPROC - - -child_rip: - /* - * Here we are in the child and the registers are set as they were - * at kernel_thread() invocation in the parent. - */ - movq %rdi, %rax - movq %rsi, %rdi - call *%rax - # exit - xorq %rdi, %rdi - call do_exit - -/* - * execve(). This function needs to use IRET, not SYSRET, to set up all state properly. - * - * C extern interface: - * extern long execve(char *name, char **argv, char **envp) - * - * asm input arguments: - * rdi: name, rsi: argv, rdx: envp - * - * We want to fallback into: - * extern long sys_execve(char *name, char **argv,char **envp, struct pt_regs regs) - * - * do_sys_execve asm fallback arguments: - * rdi: name, rsi: argv, rdx: envp, fake frame on the stack - */ -ENTRY(execve) - CFI_STARTPROC - FAKE_STACK_FRAME $0 - SAVE_ALL - call sys_execve - movq %rax, RAX(%rsp) - RESTORE_REST - testq %rax,%rax - jne 1f - jmp int_ret_from_sys_call -1: RESTORE_ARGS - UNFAKE_STACK_FRAME - ret - CFI_ENDPROC - -ENTRY(page_fault) - errorentry do_page_fault - -ENTRY(coprocessor_error) - zeroentry do_coprocessor_error - -ENTRY(simd_coprocessor_error) - zeroentry do_simd_coprocessor_error - -ENTRY(device_not_available) - zeroentry math_state_restore - - /* runs on exception stack */ -ENTRY(debug) - CFI_STARTPROC -/* pushq $0 - CFI_ADJUST_CFA_OFFSET 8 */ - zeroentry do_debug -/* jmp paranoid_exit */ - CFI_ENDPROC - -#if 0 - /* runs on exception stack */ -ENTRY(nmi) - CFI_STARTPROC - pushq $-1 - CFI_ADJUST_CFA_OFFSET 8 - paranoidentry do_nmi - /* - * "Paranoid" exit path from exception stack. - * Paranoid because this is used by NMIs and cannot take - * any kernel state for granted. - * We don't do kernel preemption checks here, because only - * NMI should be common and it does not enable IRQs and - * cannot get reschedule ticks. - */ - /* ebx: no swapgs flag */ -paranoid_exit: - testl %ebx,%ebx /* swapgs needed? */ - jnz paranoid_restore - testl $3,CS(%rsp) - jnz paranoid_userspace -paranoid_swapgs: - swapgs -paranoid_restore: - RESTORE_ALL 8 - iretq -paranoid_userspace: - GET_THREAD_INFO(%rcx) - movl threadinfo_flags(%rcx),%ebx - andl $_TIF_WORK_MASK,%ebx - jz paranoid_swapgs - movq %rsp,%rdi /* &pt_regs */ - call sync_regs - movq %rax,%rsp /* switch stack for scheduling */ - testl $_TIF_NEED_RESCHED,%ebx - jnz paranoid_schedule - movl %ebx,%edx /* arg3: thread flags */ - sti - xorl %esi,%esi /* arg2: oldset */ - movq %rsp,%rdi /* arg1: &pt_regs */ - call do_notify_resume - cli - jmp paranoid_userspace -paranoid_schedule: - sti - call schedule - cli - jmp paranoid_userspace - CFI_ENDPROC -#endif - -ENTRY(int3) - zeroentry do_int3 - -ENTRY(overflow) - zeroentry do_overflow - -ENTRY(bounds) - zeroentry do_bounds - -ENTRY(invalid_op) - zeroentry do_invalid_op - -ENTRY(coprocessor_segment_overrun) - zeroentry do_coprocessor_segment_overrun - -ENTRY(reserved) - zeroentry do_reserved - -#if 0 - /* runs on exception stack */ -ENTRY(double_fault) - CFI_STARTPROC - paranoidentry do_double_fault - jmp paranoid_exit - CFI_ENDPROC -#endif - -ENTRY(invalid_TSS) - errorentry do_invalid_TSS - -ENTRY(segment_not_present) - errorentry do_segment_not_present - - /* runs on exception stack */ -ENTRY(stack_segment) - CFI_STARTPROC - errorentry do_stack_segment - CFI_ENDPROC - -ENTRY(general_protection) - errorentry do_general_protection - -ENTRY(alignment_check) - errorentry do_alignment_check - -ENTRY(divide_error) - zeroentry do_divide_error - -ENTRY(spurious_interrupt_bug) - zeroentry do_spurious_interrupt_bug - -#ifdef CONFIG_X86_MCE - /* runs on exception stack */ -ENTRY(machine_check) - CFI_STARTPROC - pushq $0 - CFI_ADJUST_CFA_OFFSET 8 - paranoidentry do_machine_check - jmp paranoid_exit - CFI_ENDPROC -#endif - -ENTRY(call_debug) - zeroentry do_call_debug - diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/genapic.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/genapic.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,123 +0,0 @@ -/* - * Copyright 2004 James Cleverdon, IBM. - * Subject to the GNU Public License, v.2 - * - * Generic APIC sub-arch probe layer. - * - * Hacked for x86-64 by James Cleverdon from i386 architecture code by - * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and - * James Cleverdon. - */ -#include <linux/config.h> -#include <linux/threads.h> -#include <linux/cpumask.h> -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/ctype.h> -#include <linux/init.h> -#include <linux/module.h> - -#include <asm/smp.h> -#include <asm/ipi.h> - -#if defined(CONFIG_ACPI_BUS) -#include <acpi/acpi_bus.h> -#endif - -/* which logical CPU number maps to which CPU (physical APIC ID) */ -u8 x86_cpu_to_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; -EXPORT_SYMBOL(x86_cpu_to_apicid); -u8 x86_cpu_to_log_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; - -extern struct genapic apic_cluster; -extern struct genapic apic_flat; - -#ifndef CONFIG_XEN -struct genapic *genapic = &apic_flat; -#else -extern struct genapic apic_xen; -struct genapic *genapic = &apic_xen; -#endif - - -/* - * Check the APIC IDs in bios_cpu_apicid and choose the APIC mode. - */ -void __init clustered_apic_check(void) -{ -#ifndef CONFIG_XEN - long i; - u8 clusters, max_cluster; - u8 id; - u8 cluster_cnt[NUM_APIC_CLUSTERS]; - - if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { - /* AMD always uses flat mode right now */ - genapic = &apic_flat; - goto print; - } - -#if defined(CONFIG_ACPI_BUS) - /* - * Some x86_64 machines use physical APIC mode regardless of how many - * procs/clusters are present (x86_64 ES7000 is an example). - */ - if (acpi_fadt.revision > FADT2_REVISION_ID) - if (acpi_fadt.force_apic_physical_destination_mode) { - genapic = &apic_cluster; - goto print; - } -#endif - - memset(cluster_cnt, 0, sizeof(cluster_cnt)); - - for (i = 0; i < NR_CPUS; i++) { - id = bios_cpu_apicid[i]; - if (id != BAD_APICID) - cluster_cnt[APIC_CLUSTERID(id)]++; - } - - clusters = 0; - max_cluster = 0; - for (i = 0; i < NUM_APIC_CLUSTERS; i++) { - if (cluster_cnt[i] > 0) { - ++clusters; - if (cluster_cnt[i] > max_cluster) - max_cluster = cluster_cnt[i]; - } - } - - /* - * If we have clusters <= 1 and CPUs <= 8 in cluster 0, then flat mode, - * else if max_cluster <= 4 and cluster_cnt[15] == 0, clustered logical - * else physical mode. - * (We don't use lowest priority delivery + HW APIC IRQ steering, so - * can ignore the clustered logical case and go straight to physical.) - */ - if (clusters <= 1 && max_cluster <= 8 && cluster_cnt[0] == max_cluster) - genapic = &apic_flat; - else - genapic = &apic_cluster; - -print: -#else - /* hardcode to xen apic functions */ - genapic = &apic_xen; -#endif - printk(KERN_INFO "Setting APIC routing to %s\n", genapic->name); -} - -/* Same for both flat and clustered. */ - -#ifdef CONFIG_XEN -extern void xen_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest); -#endif - -void send_IPI_self(int vector) -{ -#ifndef CONFIG_XEN - __send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL); -#else - xen_send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL); -#endif -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/genapic_xen.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/genapic_xen.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,162 +0,0 @@ -/* - * Copyright 2004 James Cleverdon, IBM. - * Subject to the GNU Public License, v.2 - * - * Xen APIC subarch code. Maximum 8 CPUs, logical delivery. - * - * Hacked for x86-64 by James Cleverdon from i386 architecture code by - * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and - * James Cleverdon. - * - * Hacked to pieces for Xen by Chris Wright. - */ -#include <linux/config.h> -#include <linux/threads.h> -#include <linux/cpumask.h> -#include <linux/string.h> -#include <linux/kernel.h> -#include <linux/ctype.h> -#include <linux/init.h> -#ifdef CONFIG_XEN_PRIVILEGED_GUEST -#include <asm/smp.h> -#include <asm/ipi.h> -#else -#include <asm/apic.h> -#include <asm/apicdef.h> -#include <asm/genapic.h> -#endif -#include <asm-xen/evtchn.h> - -DECLARE_PER_CPU(int, ipi_to_irq[NR_IPIS]); - -static inline void __send_IPI_one(unsigned int cpu, int vector) -{ - int irq = per_cpu(ipi_to_irq, cpu)[vector]; - BUG_ON(irq < 0); - notify_remote_via_irq(irq); -} - -void xen_send_IPI_shortcut(unsigned int shortcut, int vector, unsigned int dest) -{ - int cpu; - - switch (shortcut) { - case APIC_DEST_SELF: - __send_IPI_one(smp_processor_id(), vector); - break; - case APIC_DEST_ALLBUT: - for (cpu = 0; cpu < NR_CPUS; ++cpu) { - if (cpu == smp_processor_id()) - continue; - if (cpu_isset(cpu, cpu_online_map)) { - __send_IPI_one(cpu, vector); - } - } - break; - case APIC_DEST_ALLINC: - for (cpu = 0; cpu < NR_CPUS; ++cpu) { - if (cpu_isset(cpu, cpu_online_map)) { - __send_IPI_one(cpu, vector); - } - } - break; - default: - printk("XXXXXX __send_IPI_shortcut %08x vector %d\n", shortcut, - vector); - break; - } -} - -static cpumask_t xen_target_cpus(void) -{ - return cpu_online_map; -} - -/* - * Set up the logical destination ID. - * Do nothing, not called now. - */ -static void xen_init_apic_ldr(void) -{ - Dprintk("%s\n", __FUNCTION__); - return; -} - -static void xen_send_IPI_allbutself(int vector) -{ - /* - * if there are no other CPUs in the system then - * we get an APIC send error if we try to broadcast. - * thus we have to avoid sending IPIs in this case. - */ - Dprintk("%s\n", __FUNCTION__); - if (num_online_cpus() > 1) - xen_send_IPI_shortcut(APIC_DEST_ALLBUT, vector, APIC_DEST_LOGICAL); -} - -static void xen_send_IPI_all(int vector) -{ - Dprintk("%s\n", __FUNCTION__); - xen_send_IPI_shortcut(APIC_DEST_ALLINC, vector, APIC_DEST_LOGICAL); -} - -static void xen_send_IPI_mask(cpumask_t cpumask, int vector) -{ - unsigned long mask = cpus_addr(cpumask)[0]; - unsigned int cpu; - unsigned long flags; - - Dprintk("%s\n", __FUNCTION__); - local_irq_save(flags); - WARN_ON(mask & ~cpus_addr(cpu_online_map)[0]); - - for (cpu = 0; cpu < NR_CPUS; ++cpu) { - if (cpu_isset(cpu, cpumask)) { - __send_IPI_one(cpu, vector); - } - } - local_irq_restore(flags); -} - -#ifdef CONFIG_XEN_PRIVILEGED_GUEST -static int xen_apic_id_registered(void) -{ - /* better be set */ - Dprintk("%s\n", __FUNCTION__); - return physid_isset(smp_processor_id(), phys_cpu_present_map); -} -#endif - -static unsigned int xen_cpu_mask_to_apicid(cpumask_t cpumask) -{ - Dprintk("%s\n", __FUNCTION__); - return cpus_addr(cpumask)[0] & APIC_ALL_CPUS; -} - -static unsigned int phys_pkg_id(int index_msb) -{ - u32 ebx; - - Dprintk("%s\n", __FUNCTION__); - ebx = cpuid_ebx(1); - return ((ebx >> 24) & 0xFF) >> index_msb; -} - -struct genapic apic_xen = { - .name = "xen", -#ifdef CONFIG_XEN_PRIVILEGED_GUEST - .int_delivery_mode = dest_LowestPrio, -#endif - .int_dest_mode = (APIC_DEST_LOGICAL != 0), - .int_delivery_dest = APIC_DEST_LOGICAL | APIC_DM_LOWEST, - .target_cpus = xen_target_cpus, -#ifdef CONFIG_XEN_PRIVILEGED_GUEST - .apic_id_registered = xen_apic_id_registered, -#endif - .init_apic_ldr = xen_init_apic_ldr, - .send_IPI_all = xen_send_IPI_all, - .send_IPI_allbutself = xen_send_IPI_allbutself, - .send_IPI_mask = xen_send_IPI_mask, - .cpu_mask_to_apicid = xen_cpu_mask_to_apicid, - .phys_pkg_id = phys_pkg_id, -}; diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/head.S --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/head.S Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,275 +0,0 @@ -/* - * linux/arch/x86_64/kernel/head.S -- start in 32bit and switch to 64bit - * - * Copyright (C) 2000 Andrea Arcangeli <andrea@xxxxxxx> SuSE - * Copyright (C) 2000 Pavel Machek <pavel@xxxxxxx> - * Copyright (C) 2000 Karsten Keil <kkeil@xxxxxxx> - * Copyright (C) 2001,2002 Andi Kleen <ak@xxxxxxx> - * - * $Id: head.S,v 1.49 2002/03/19 17:39:25 ak Exp $ - * - * Jun Nakajima <jun.nakajima@xxxxxxxxx> - * Modified for Xen - */ - - -#include <linux/linkage.h> - -.section __xen_guest - .ascii "GUEST_OS=linux,GUEST_VER=2.6" - .ascii ",XEN_VER=xen-3.0" - .ascii ",VIRT_BASE=0xffffffff80000000" - .ascii ",HYPERCALL_PAGE=0x10d" /* __pa(hypercall_page) >> 12 */ - .ascii ",LOADER=generic" - .byte 0 - - -#include <linux/threads.h> -#include <asm/desc.h> -#include <asm/segment.h> -#include <asm/page.h> -#include <asm/msr.h> -#include <asm/cache.h> - -/* we are not able to switch in one step to the final KERNEL ADRESS SPACE - * because we need identity-mapped pages on setup so define __START_KERNEL to - * 0x100000 for this stage - * - */ - - .text - .code64 - .globl startup_64 -startup_64: -ENTRY(_start) - movq %rsi,xen_start_info(%rip) - -#ifdef CONFIG_SMP -ENTRY(startup_64_smp) -#endif /* CONFIG_SMP */ - - cld - - movq init_rsp(%rip),%rsp - /* zero EFLAGS after setting rsp */ - pushq $0 - popfq - movq initial_code(%rip),%rax - jmp *%rax - - /* SMP bootup changes these two */ - .globl initial_code -initial_code: - .quad x86_64_start_kernel - .globl init_rsp -init_rsp: - .quad init_thread_union+THREAD_SIZE-8 - -ENTRY(early_idt_handler) - xorl %eax,%eax - movq 8(%rsp),%rsi # get rip - movq (%rsp),%rdx - leaq early_idt_msg(%rip),%rdi -1: hlt # generate #GP - jmp 1b - -early_idt_msg: - .asciz "PANIC: early exception rip %lx error %lx cr2 %lx\n" - -#if 0 -ENTRY(lgdt_finish) - movl $(__USER_DS),%eax # DS/ES contains default USER segment - movw %ax,%ds - movw %ax,%es - movl $(__KERNEL_DS),%eax - movw %ax,%ss # after changing gdt. - popq %rax # get the retrun address - pushq $(__KERNEL_CS) - pushq %rax - lretq -#endif - -ENTRY(stext) -ENTRY(_stext) - - /* - * This default setting generates an ident mapping at address 0x100000 - * and a mapping for the kernel that precisely maps virtual address - * 0xffffffff80000000 to physical address 0x000000. (always using - * 2Mbyte large pages provided by PAE mode) - */ -.org 0x1000 -ENTRY(init_level4_pgt) - .fill 512,8,0 - - /* - * We update two pgd entries to make kernel and user pgd consistent - * at pgd_populate(). It can be used for kernel modules. So we place - * this page here for those cases to avoid memory corruption. - * We also use this page to establish the initiali mapping for - * vsyscall area. - */ -.org 0x2000 -ENTRY(init_level4_user_pgt) - .fill 512,8,0 - - /* - * In Xen the following pre-initialized pgt entries are re-initialized. - */ -.org 0x3000 -ENTRY(level3_kernel_pgt) - .fill 510,8,0 - /* (2^48-(2*1024*1024*1024)-((2^39)*511))/(2^30) = 510 */ - .quad 0x0000000000105007 /* -> level2_kernel_pgt */ - .fill 1,8,0 - -.org 0x4000 -ENTRY(level2_ident_pgt) - /* 40MB for bootup. */ - .quad 0x0000000000000283 - .quad 0x0000000000200183 - .quad 0x0000000000400183 - .quad 0x0000000000600183 - .quad 0x0000000000800183 - .quad 0x0000000000A00183 - .quad 0x0000000000C00183 - .quad 0x0000000000E00183 - .quad 0x0000000001000183 - .quad 0x0000000001200183 - .quad 0x0000000001400183 - .quad 0x0000000001600183 - .quad 0x0000000001800183 - .quad 0x0000000001A00183 - .quad 0x0000000001C00183 - .quad 0x0000000001E00183 - .quad 0x0000000002000183 - .quad 0x0000000002200183 - .quad 0x0000000002400183 - .quad 0x0000000002600183 - /* Temporary mappings for the super early allocator in arch/x86_64/mm/init.c */ - .globl temp_boot_pmds -temp_boot_pmds: - .fill 492,8,0 - -.org 0x5000 -ENTRY(level2_kernel_pgt) - /* 40MB kernel mapping. The kernel code cannot be bigger than that. - When you change this change KERNEL_TEXT_SIZE in page.h too. */ - /* (2^48-(2*1024*1024*1024)-((2^39)*511)-((2^30)*510)) = 0 */ - .quad 0x0000000000000183 - .quad 0x0000000000200183 - .quad 0x0000000000400183 - .quad 0x0000000000600183 - .quad 0x0000000000800183 - .quad 0x0000000000A00183 - .quad 0x0000000000C00183 - .quad 0x0000000000E00183 - .quad 0x0000000001000183 - .quad 0x0000000001200183 - .quad 0x0000000001400183 - .quad 0x0000000001600183 - .quad 0x0000000001800183 - .quad 0x0000000001A00183 - .quad 0x0000000001C00183 - .quad 0x0000000001E00183 - .quad 0x0000000002000183 - .quad 0x0000000002200183 - .quad 0x0000000002400183 - .quad 0x0000000002600183 - /* Module mapping starts here */ - .fill 492,8,0 - - /* - * This is used for vsyscall area mapping as we have a different - * level4 page table for user. - */ -.org 0x6000 -ENTRY(level3_user_pgt) - .fill 512,8,0 - -.org 0x7000 -ENTRY(cpu_gdt_table) -/* The TLS descriptors are currently at a different place compared to i386. - Hopefully nobody expects them at a fixed place (Wine?) */ - .quad 0x0000000000000000 /* NULL descriptor */ - .quad 0x008ffa000000ffff /* __KERNEL_COMPAT32_CS */ - .quad 0x00affa000000ffff /* __KERNEL_CS */ - .quad 0x00cff2000000ffff /* __KERNEL_DS */ - - .quad 0x00cffa000000ffff /* __USER32_CS */ - .quad 0x00cff2000000ffff /* __USER_DS, __USER32_DS */ - .quad 0x00affa000000ffff /* __USER_CS */ - .quad 0x00cffa000000ffff /* __KERNEL32_CS */ - .quad 0,0 /* TSS */ - .quad 0,0 /* LDT */ - .quad 0,0,0 /* three TLS descriptors */ - .quad 0 /* unused now? __KERNEL16_CS - 16bit PM for S3 wakeup. */ - -gdt_end: -#if 0 - /* asm/segment.h:GDT_ENTRIES must match this */ - /* This should be a multiple of the cache line size */ - /* GDTs of other CPUs: */ - .fill (GDT_SIZE * NR_CPUS) - (gdt_end - cpu_gdt_table) -#endif - -.org 0x8000 -ENTRY(empty_zero_page) - -.org 0x9000 -ENTRY(empty_bad_page) - -.org 0xa000 -ENTRY(empty_bad_pte_table) - -.org 0xb000 -ENTRY(empty_bad_pmd_table) - -.org 0xc000 -ENTRY(level3_physmem_pgt) - .quad 0x0000000000105007 /* -> level2_kernel_pgt (so that __va works even before pagetable_init) */ - -.org 0xd000 -ENTRY(hypercall_page) - -.org 0xe000 -#ifdef CONFIG_ACPI_SLEEP -ENTRY(wakeup_level4_pgt) - .quad 0x0000000000102007 /* -> level3_ident_pgt */ - .fill 255,8,0 - .quad 0x000000000010a007 - .fill 254,8,0 - /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ - .quad 0x0000000000103007 /* -> level3_kernel_pgt */ -#endif - - .data - - .align 16 - .globl cpu_gdt_descr -cpu_gdt_descr: - .word gdt_end-cpu_gdt_table -gdt: - .quad cpu_gdt_table -#ifdef CONFIG_SMP - .rept NR_CPUS-1 - .word 0 - .quad 0 - .endr -#endif - -/* We need valid kernel segments for data and code in long mode too - * IRET will check the segment types kkeil 2000/10/28 - * Also sysret mandates a special GDT layout - */ - -#if 0 -.align L1_CACHE_BYTES -#endif - .align L1_CACHE_BYTES -ENTRY(idt_table) - .rept 256 - .quad 0 - .quad 0 - .endr - diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/head64.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/head64.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,127 +0,0 @@ -/* - * linux/arch/x86_64/kernel/head64.c -- prepare to run common code - * - * Copyright (C) 2000 Andrea Arcangeli <andrea@xxxxxxx> SuSE - * - * $Id: head64.c,v 1.22 2001/07/06 14:28:20 ak Exp $ - * - * Jun Nakajima <jun.nakajima@xxxxxxxxx> - * Modified for Xen. - */ - -#include <linux/init.h> -#include <linux/linkage.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/percpu.h> - -#include <asm/processor.h> -#include <asm/proto.h> -#include <asm/smp.h> -#include <asm/bootsetup.h> -#include <asm/setup.h> -#include <asm/desc.h> - -unsigned long start_pfn; - -/* Don't add a printk in there. printk relies on the PDA which is not initialized - yet. */ -#if 0 -static void __init clear_bss(void) -{ - extern char __bss_start[], __bss_end[]; - memset(__bss_start, 0, - (unsigned long) __bss_end - (unsigned long) __bss_start); -} -#endif - -#define NEW_CL_POINTER 0x228 /* Relative to real mode data */ -#define OLD_CL_MAGIC_ADDR 0x90020 -#define OLD_CL_MAGIC 0xA33F -#define OLD_CL_BASE_ADDR 0x90000 -#define OLD_CL_OFFSET 0x90022 - -extern char saved_command_line[]; - -#if 0 -static void __init copy_bootdata(char *real_mode_data) -{ - int new_data; - char * command_line; - - memcpy(x86_boot_params, real_mode_data, BOOT_PARAM_SIZE); - new_data = *(int *) (x86_boot_params + NEW_CL_POINTER); - if (!new_data) { - if (OLD_CL_MAGIC != * (u16 *) OLD_CL_MAGIC_ADDR) { - printk("so old bootloader that it does not support commandline?!\n"); - return; - } - new_data = OLD_CL_BASE_ADDR + * (u16 *) OLD_CL_OFFSET; - printk("old bootloader convention, maybe loadlin?\n"); - } - command_line = (char *) ((u64)(new_data)); - memcpy(saved_command_line, command_line, COMMAND_LINE_SIZE); - printk("Bootdata ok (command line is %s)\n", saved_command_line); -} -#endif - -static void __init setup_boot_cpu_data(void) -{ - unsigned int dummy, eax; - - /* get vendor info */ - cpuid(0, (unsigned int *)&boot_cpu_data.cpuid_level, - (unsigned int *)&boot_cpu_data.x86_vendor_id[0], - (unsigned int *)&boot_cpu_data.x86_vendor_id[8], - (unsigned int *)&boot_cpu_data.x86_vendor_id[4]); - - /* get cpu type */ - cpuid(1, &eax, &dummy, &dummy, - (unsigned int *) &boot_cpu_data.x86_capability); - boot_cpu_data.x86 = (eax >> 8) & 0xf; - boot_cpu_data.x86_model = (eax >> 4) & 0xf; - boot_cpu_data.x86_mask = eax & 0xf; -} - -extern char _end[]; - -void __init x86_64_start_kernel(char * real_mode_data) -{ - int i; - - phys_to_machine_mapping = (unsigned long *)xen_start_info->mfn_list; - start_pfn = (__pa(xen_start_info->pt_base) >> PAGE_SHIFT) + - xen_start_info->nr_pt_frames; - - for (i = 0; i < 256; i++) - set_intr_gate(i, early_idt_handler); -#if 0 - asm volatile("lidt %0" :: "m" (idt_descr)); -#endif - pda_init(0); - /* copy_bootdata(real_mode_data); */ -#ifdef CONFIG_SMP - cpu_set(0, cpu_online_map); -#endif -#if 0 - s = strstr(saved_command_line, "earlyprintk="); - if (s != NULL) - setup_early_printk(s); -#endif -#ifdef CONFIG_DISCONTIGMEM - s = strstr(saved_command_line, "numa="); - if (s != NULL) - numa_setup(s+5); -#endif -#ifdef CONFIG_X86_IO_APIC - if (strstr(saved_command_line, "disableapic")) - disable_apic = 1; -#endif - /* You need early console to see that */ - if (__pa_symbol(&_end) >= KERNEL_TEXT_SIZE) - panic("Kernel too big for kernel mapping\n"); - - setup_boot_cpu_data(); - start_kernel(); -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/io_apic.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/io_apic.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,1992 +0,0 @@ -/* - * Intel IO-APIC support for multi-Pentium hosts. - * - * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar, Hajnalka Szabo - * - * Many thanks to Stig Venaas for trying out countless experimental - * patches and reporting/debugging problems patiently! - * - * (c) 1999, Multiple IO-APIC support, developed by - * Ken-ichi Yaku <yaku@xxxxxxxxxxxxxxxxxxxx> and - * Hidemi Kishimoto <kisimoto@xxxxxxxxxxxxxxxxxxxx>, - * further tested and cleaned up by Zach Brown <zab@xxxxxxxxxx> - * and Ingo Molnar <mingo@xxxxxxxxxx> - * - * Fixes - * Maciej W. Rozycki : Bits for genuine 82489DX APICs; - * thanks to Eric Gilmore - * and Rolf G. Tews - * for testing these extensively - * Paul Diefenbaugh : Added full ACPI support - */ - -#include <linux/mm.h> -#include <linux/irq.h> -#include <linux/interrupt.h> -#include <linux/init.h> -#include <linux/delay.h> -#include <linux/sched.h> -#include <linux/config.h> -#include <linux/smp_lock.h> -#include <linux/mc146818rtc.h> -#include <linux/acpi.h> -#include <linux/sysdev.h> - -#include <asm/io.h> -#include <asm/smp.h> -#include <asm/desc.h> -#include <asm/proto.h> -#include <asm/mach_apic.h> -#include <asm/acpi.h> - -#define __apicdebuginit __init - -int sis_apic_bug; /* not actually supported, dummy for compile */ - -static int no_timer_check; - -static DEFINE_SPINLOCK(ioapic_lock); - -/* - * # of IRQ routing registers - */ -int nr_ioapic_registers[MAX_IO_APICS]; - -/* - * Rough estimation of how many shared IRQs there are, can - * be changed anytime. - */ -#define MAX_PLUS_SHARED_IRQS NR_IRQS -#define PIN_MAP_SIZE (MAX_PLUS_SHARED_IRQS + NR_IRQS) - -/* - * This is performance-critical, we want to do it O(1) - * - * the indexing order of this array favors 1:1 mappings - * between pins and IRQs. - */ - -static struct irq_pin_list { - short apic, pin, next; -} irq_2_pin[PIN_MAP_SIZE]; - -int vector_irq[NR_VECTORS] = { [0 ... NR_VECTORS - 1] = -1}; -#ifdef CONFIG_PCI_MSI -#define vector_to_irq(vector) \ - (platform_legacy_irq(vector) ? vector : vector_irq[vector]) -#else -#define vector_to_irq(vector) (vector) -#endif - -#ifdef CONFIG_XEN - -#include <asm-xen/xen-public/xen.h> -#include <asm-xen/xen-public/physdev.h> - -/* Fake i8259 */ -#define make_8259A_irq(_irq) (io_apic_irqs &= ~(1UL<<(_irq))) -#define disable_8259A_irq(_irq) ((void)0) -#define i8259A_irq_pending(_irq) (0) - -unsigned long io_apic_irqs; - -static inline unsigned int xen_io_apic_read(unsigned int apic, unsigned int reg) -{ - physdev_op_t op; - int ret; - - op.cmd = PHYSDEVOP_APIC_READ; - op.u.apic_op.apic = mp_ioapics[apic].mpc_apicid; - op.u.apic_op.offset = reg; - ret = HYPERVISOR_physdev_op(&op); - if (ret) - return ret; - return op.u.apic_op.value; -} - -static inline void xen_io_apic_write(unsigned int apic, unsigned int reg, unsigned int value) -{ - physdev_op_t op; - - op.cmd = PHYSDEVOP_APIC_WRITE; - op.u.apic_op.apic = mp_ioapics[apic].mpc_apicid; - op.u.apic_op.offset = reg; - op.u.apic_op.value = value; - HYPERVISOR_physdev_op(&op); -} - -#define io_apic_read(a,r) xen_io_apic_read(a,r) -#define io_apic_write(a,r,v) xen_io_apic_write(a,r,v) - -#define clear_IO_APIC() ((void)0) - -#endif /* !CONFIG_XEN */ - -/* - * The common case is 1:1 IRQ<->pin mappings. Sometimes there are - * shared ISA-space IRQs, so we have to support them. We are super - * fast in the common case, and fast for shared ISA-space IRQs. - */ -static void add_pin_to_irq(unsigned int irq, int apic, int pin) -{ - static int first_free_entry = NR_IRQS; - struct irq_pin_list *entry = irq_2_pin + irq; - - while (entry->next) - entry = irq_2_pin + entry->next; - - if (entry->pin != -1) { - entry->next = first_free_entry; - entry = irq_2_pin + entry->next; - if (++first_free_entry >= PIN_MAP_SIZE) - panic("io_apic.c: whoops"); - } - entry->apic = apic; - entry->pin = pin; -} - -#ifndef CONFIG_XEN -#define __DO_ACTION(R, ACTION, FINAL) \ - \ -{ \ - int pin; \ - struct irq_pin_list *entry = irq_2_pin + irq; \ - \ - for (;;) { \ - unsigned int reg; \ - pin = entry->pin; \ - if (pin == -1) \ - break; \ - reg = io_apic_read(entry->apic, 0x10 + R + pin*2); \ - reg ACTION; \ - io_apic_modify(entry->apic, reg); \ - if (!entry->next) \ - break; \ - entry = irq_2_pin + entry->next; \ - } \ - FINAL; \ -} - -#define DO_ACTION(name,R,ACTION, FINAL) \ - \ - static void name##_IO_APIC_irq (unsigned int irq) \ - __DO_ACTION(R, ACTION, FINAL) - -DO_ACTION( __mask, 0, |= 0x00010000, io_apic_sync(entry->apic) ) - /* mask = 1 */ -DO_ACTION( __unmask, 0, &= 0xfffeffff, ) - /* mask = 0 */ - -static void mask_IO_APIC_irq (unsigned int irq) -{ - unsigned long flags; - - spin_lock_irqsave(&ioapic_lock, flags); - __mask_IO_APIC_irq(irq); - spin_unlock_irqrestore(&ioapic_lock, flags); -} - -static void unmask_IO_APIC_irq (unsigned int irq) -{ - unsigned long flags; - - spin_lock_irqsave(&ioapic_lock, flags); - __unmask_IO_APIC_irq(irq); - spin_unlock_irqrestore(&ioapic_lock, flags); -} - -static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin) -{ - struct IO_APIC_route_entry entry; - unsigned long flags; - - /* Check delivery_mode to be sure we're not clearing an SMI pin */ - spin_lock_irqsave(&ioapic_lock, flags); - *(((int*)&entry) + 0) = io_apic_read(apic, 0x10 + 2 * pin); - *(((int*)&entry) + 1) = io_apic_read(apic, 0x11 + 2 * pin); - spin_unlock_irqrestore(&ioapic_lock, flags); - if (entry.delivery_mode == dest_SMI) - return; - /* - * Disable it in the IO-APIC irq-routing table: - */ - memset(&entry, 0, sizeof(entry)); - entry.mask = 1; - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(apic, 0x10 + 2 * pin, *(((int *)&entry) + 0)); - io_apic_write(apic, 0x11 + 2 * pin, *(((int *)&entry) + 1)); - spin_unlock_irqrestore(&ioapic_lock, flags); -} - -static void clear_IO_APIC (void) -{ - int apic, pin; - - for (apic = 0; apic < nr_ioapics; apic++) - for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) - clear_IO_APIC_pin(apic, pin); -} - -#endif /* !CONFIG_XEN */ - -/* - * support for broken MP BIOSs, enables hand-redirection of PIRQ0-7 to - * specific CPU-side IRQs. - */ - -#define MAX_PIRQS 8 -static int pirq_entries [MAX_PIRQS]; -static int pirqs_enabled; -int skip_ioapic_setup; -int ioapic_force; - -/* dummy parsing: see setup.c */ - -static int __init disable_ioapic_setup(char *str) -{ - skip_ioapic_setup = 1; - return 1; -} - -static int __init enable_ioapic_setup(char *str) -{ - ioapic_force = 1; - skip_ioapic_setup = 0; - return 1; -} - -__setup("noapic", disable_ioapic_setup); -__setup("apic", enable_ioapic_setup); - -#include <asm/pci-direct.h> -#include <linux/pci_ids.h> -#include <linux/pci.h> - -/* Temporary Hack. Nvidia and VIA boards currently only work with IO-APIC - off. Check for an Nvidia or VIA PCI bridge and turn it off. - Use pci direct infrastructure because this runs before the PCI subsystem. - - Can be overwritten with "apic" - - And another hack to disable the IOMMU on VIA chipsets. - - Kludge-O-Rama. */ -void __init check_ioapic(void) -{ - int num,slot,func; - if (ioapic_force) - return; - - /* Poor man's PCI discovery */ - for (num = 0; num < 32; num++) { - for (slot = 0; slot < 32; slot++) { - for (func = 0; func < 8; func++) { - u32 class; - u32 vendor; - u8 type; - class = read_pci_config(num,slot,func, - PCI_CLASS_REVISION); - if (class == 0xffffffff) - break; - - if ((class >> 16) != PCI_CLASS_BRIDGE_PCI) - continue; - - vendor = read_pci_config(num, slot, func, - PCI_VENDOR_ID); - vendor &= 0xffff; - switch (vendor) { - case PCI_VENDOR_ID_VIA: -#ifdef CONFIG_GART_IOMMU - if ((end_pfn >= (0xffffffff>>PAGE_SHIFT) || - force_iommu) && - !iommu_aperture_allowed) { - printk(KERN_INFO - "Looks like a VIA chipset. Disabling IOMMU. Overwrite with \"iommu=allowed\"\n"); - iommu_aperture_disabled = 1; - } -#endif - return; - case PCI_VENDOR_ID_NVIDIA: -#ifdef CONFIG_ACPI - /* All timer overrides on Nvidia - seem to be wrong. Skip them. */ - acpi_skip_timer_override = 1; - printk(KERN_INFO - "Nvidia board detected. Ignoring ACPI timer override.\n"); -#endif - /* RED-PEN skip them on mptables too? */ - return; - } - - /* No multi-function device? */ - type = read_pci_config_byte(num,slot,func, - PCI_HEADER_TYPE); - if (!(type & 0x80)) - break; - } - } - } -} - -static int __init ioapic_pirq_setup(char *str) -{ - int i, max; - int ints[MAX_PIRQS+1]; - - get_options(str, ARRAY_SIZE(ints), ints); - - for (i = 0; i < MAX_PIRQS; i++) - pirq_entries[i] = -1; - - pirqs_enabled = 1; - apic_printk(APIC_VERBOSE, "PIRQ redirection, working around broken MP-BIOS.\n"); - max = MAX_PIRQS; - if (ints[0] < MAX_PIRQS) - max = ints[0]; - - for (i = 0; i < max; i++) { - apic_printk(APIC_VERBOSE, "... PIRQ%d -> IRQ %d\n", i, ints[i+1]); - /* - * PIRQs are mapped upside down, usually. - */ - pirq_entries[MAX_PIRQS-i-1] = ints[i+1]; - } - return 1; -} - -__setup("pirq=", ioapic_pirq_setup); - -/* - * Find the IRQ entry number of a certain pin. - */ -static int find_irq_entry(int apic, int pin, int type) -{ - int i; - - for (i = 0; i < mp_irq_entries; i++) - if (mp_irqs[i].mpc_irqtype == type && - (mp_irqs[i].mpc_dstapic == mp_ioapics[apic].mpc_apicid || - mp_irqs[i].mpc_dstapic == MP_APIC_ALL) && - mp_irqs[i].mpc_dstirq == pin) - return i; - - return -1; -} - -#ifndef CONFIG_XEN -/* - * Find the pin to which IRQ[irq] (ISA) is connected - */ -static int __init find_isa_irq_pin(int irq, int type) -{ - int i; - - for (i = 0; i < mp_irq_entries; i++) { - int lbus = mp_irqs[i].mpc_srcbus; - - if ((mp_bus_id_to_type[lbus] == MP_BUS_ISA || - mp_bus_id_to_type[lbus] == MP_BUS_EISA || - mp_bus_id_to_type[lbus] == MP_BUS_MCA) && - (mp_irqs[i].mpc_irqtype == type) && - (mp_irqs[i].mpc_srcbusirq == irq)) - - return mp_irqs[i].mpc_dstirq; - } - return -1; -} -#endif - -/* - * Find a specific PCI IRQ entry. - * Not an __init, possibly needed by modules - */ -static int pin_2_irq(int idx, int apic, int pin); - -int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin) -{ - int apic, i, best_guess = -1; - - apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n", - bus, slot, pin); - if (mp_bus_id_to_pci_bus[bus] == -1) { - apic_printk(APIC_VERBOSE, "PCI BIOS passed nonexistent PCI bus %d!\n", bus); - return -1; - } - for (i = 0; i < mp_irq_entries; i++) { - int lbus = mp_irqs[i].mpc_srcbus; - - for (apic = 0; apic < nr_ioapics; apic++) - if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic || - mp_irqs[i].mpc_dstapic == MP_APIC_ALL) - break; - - if ((mp_bus_id_to_type[lbus] == MP_BUS_PCI) && - !mp_irqs[i].mpc_irqtype && - (bus == lbus) && - (slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) { - int irq = pin_2_irq(i,apic,mp_irqs[i].mpc_dstirq); - - if (!(apic || IO_APIC_IRQ(irq))) - continue; - - if (pin == (mp_irqs[i].mpc_srcbusirq & 3)) - return irq; - /* - * Use the first all-but-pin matching entry as a - * best-guess fuzzy result for broken mptables. - */ - if (best_guess < 0) - best_guess = irq; - } - } - return best_guess; -} - -/* - * EISA Edge/Level control register, ELCR - */ -static int EISA_ELCR(unsigned int irq) -{ - if (irq < 16) { - unsigned int port = 0x4d0 + (irq >> 3); - return (inb(port) >> (irq & 7)) & 1; - } - apic_printk(APIC_VERBOSE, "Broken MPtable reports ISA irq %d\n", irq); - return 0; -} - -/* EISA interrupts are always polarity zero and can be edge or level - * trigger depending on the ELCR value. If an interrupt is listed as - * EISA conforming in the MP table, that means its trigger type must - * be read in from the ELCR */ - -#define default_EISA_trigger(idx) (EISA_ELCR(mp_irqs[idx].mpc_srcbusirq)) -#define default_EISA_polarity(idx) (0) - -/* ISA interrupts are always polarity zero edge triggered, - * when listed as conforming in the MP table. */ - -#define default_ISA_trigger(idx) (0) -#define default_ISA_polarity(idx) (0) - -/* PCI interrupts are always polarity one level triggered, - * when listed as conforming in the MP table. */ - -#define default_PCI_trigger(idx) (1) -#define default_PCI_polarity(idx) (1) - -/* MCA interrupts are always polarity zero level triggered, - * when listed as conforming in the MP table. */ - -#define default_MCA_trigger(idx) (1) -#define default_MCA_polarity(idx) (0) - -static int __init MPBIOS_polarity(int idx) -{ - int bus = mp_irqs[idx].mpc_srcbus; - int polarity; - - /* - * Determine IRQ line polarity (high active or low active): - */ - switch (mp_irqs[idx].mpc_irqflag & 3) - { - case 0: /* conforms, ie. bus-type dependent polarity */ - { - switch (mp_bus_id_to_type[bus]) - { - case MP_BUS_ISA: /* ISA pin */ - { - polarity = default_ISA_polarity(idx); - break; - } - case MP_BUS_EISA: /* EISA pin */ - { - polarity = default_EISA_polarity(idx); - break; - } - case MP_BUS_PCI: /* PCI pin */ - { - polarity = default_PCI_polarity(idx); - break; - } - case MP_BUS_MCA: /* MCA pin */ - { - polarity = default_MCA_polarity(idx); - break; - } - default: - { - printk(KERN_WARNING "broken BIOS!!\n"); - polarity = 1; - break; - } - } - break; - } - case 1: /* high active */ - { - polarity = 0; - break; - } - case 2: /* reserved */ - { - printk(KERN_WARNING "broken BIOS!!\n"); - polarity = 1; - break; - } - case 3: /* low active */ - { - polarity = 1; - break; - } - default: /* invalid */ - { - printk(KERN_WARNING "broken BIOS!!\n"); - polarity = 1; - break; - } - } - return polarity; -} - -static int MPBIOS_trigger(int idx) -{ - int bus = mp_irqs[idx].mpc_srcbus; - int trigger; - - /* - * Determine IRQ trigger mode (edge or level sensitive): - */ - switch ((mp_irqs[idx].mpc_irqflag>>2) & 3) - { - case 0: /* conforms, ie. bus-type dependent */ - { - switch (mp_bus_id_to_type[bus]) - { - case MP_BUS_ISA: /* ISA pin */ - { - trigger = default_ISA_trigger(idx); - break; - } - case MP_BUS_EISA: /* EISA pin */ - { - trigger = default_EISA_trigger(idx); - break; - } - case MP_BUS_PCI: /* PCI pin */ - { - trigger = default_PCI_trigger(idx); - break; - } - case MP_BUS_MCA: /* MCA pin */ - { - trigger = default_MCA_trigger(idx); - break; - } - default: - { - printk(KERN_WARNING "broken BIOS!!\n"); - trigger = 1; - break; - } - } - break; - } - case 1: /* edge */ - { - trigger = 0; - break; - } - case 2: /* reserved */ - { - printk(KERN_WARNING "broken BIOS!!\n"); - trigger = 1; - break; - } - case 3: /* level */ - { - trigger = 1; - break; - } - default: /* invalid */ - { - printk(KERN_WARNING "broken BIOS!!\n"); - trigger = 0; - break; - } - } - return trigger; -} - -static inline int irq_polarity(int idx) -{ - return MPBIOS_polarity(idx); -} - -static inline int irq_trigger(int idx) -{ - return MPBIOS_trigger(idx); -} - -static int pin_2_irq(int idx, int apic, int pin) -{ - int irq, i; - int bus = mp_irqs[idx].mpc_srcbus; - - /* - * Debugging check, we are in big trouble if this message pops up! - */ - if (mp_irqs[idx].mpc_dstirq != pin) - printk(KERN_ERR "broken BIOS or MPTABLE parser, ayiee!!\n"); - - switch (mp_bus_id_to_type[bus]) - { - case MP_BUS_ISA: /* ISA pin */ - case MP_BUS_EISA: - case MP_BUS_MCA: - { - irq = mp_irqs[idx].mpc_srcbusirq; - break; - } - case MP_BUS_PCI: /* PCI pin */ - { - /* - * PCI IRQs are mapped in order - */ - i = irq = 0; - while (i < apic) - irq += nr_ioapic_registers[i++]; - irq += pin; - break; - } - default: - { - printk(KERN_ERR "unknown bus type %d.\n",bus); - irq = 0; - break; - } - } - - /* - * PCI IRQ command line redirection. Yes, limits are hardcoded. - */ - if ((pin >= 16) && (pin <= 23)) { - if (pirq_entries[pin-16] != -1) { - if (!pirq_entries[pin-16]) { - apic_printk(APIC_VERBOSE, "disabling PIRQ%d\n", pin-16); - } else { - irq = pirq_entries[pin-16]; - apic_printk(APIC_VERBOSE, "using PIRQ%d -> IRQ %d\n", - pin-16, irq); - } - } - } - return irq; -} - -static inline int IO_APIC_irq_trigger(int irq) -{ - int apic, idx, pin; - - for (apic = 0; apic < nr_ioapics; apic++) { - for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { - idx = find_irq_entry(apic,pin,mp_INT); - if ((idx != -1) && (irq == pin_2_irq(idx,apic,pin))) - return irq_trigger(idx); - } - } - /* - * nonexistent IRQs are edge default - */ - return 0; -} - -/* irq_vectors is indexed by the sum of all RTEs in all I/O APICs. */ -u8 irq_vector[NR_IRQ_VECTORS]; - -int assign_irq_vector(int irq) -{ - static int current_vector = FIRST_DEVICE_VECTOR; - physdev_op_t op; - - BUG_ON(irq >= NR_IRQ_VECTORS); - if (irq != AUTO_ASSIGN && IO_APIC_VECTOR(irq) > 0) - return IO_APIC_VECTOR(irq); - - op.cmd = PHYSDEVOP_ASSIGN_VECTOR; - op.u.irq_op.irq = irq; - if (HYPERVISOR_physdev_op(&op)) - return -ENOSPC; - current_vector = op.u.irq_op.vector; - - vector_irq[current_vector] = irq; - if (irq != AUTO_ASSIGN) - IO_APIC_VECTOR(irq) = current_vector; - - return current_vector; -} - -extern void (*interrupt[NR_IRQS])(void); -#ifndef CONFIG_XEN -static struct hw_interrupt_type ioapic_level_type; -static struct hw_interrupt_type ioapic_edge_type; - -#define IOAPIC_AUTO -1 -#define IOAPIC_EDGE 0 -#define IOAPIC_LEVEL 1 - -static inline void ioapic_register_intr(int irq, int vector, unsigned long trigger) -{ - if (use_pci_vector() && !platform_legacy_irq(irq)) { - if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) || - trigger == IOAPIC_LEVEL) - irq_desc[vector].handler = &ioapic_level_type; - else - irq_desc[vector].handler = &ioapic_edge_type; - set_intr_gate(vector, interrupt[vector]); - } else { - if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) || - trigger == IOAPIC_LEVEL) - irq_desc[irq].handler = &ioapic_level_type; - else - irq_desc[irq].handler = &ioapic_edge_type; - set_intr_gate(vector, interrupt[irq]); - } -} -#else -#define ioapic_register_intr(_irq,_vector,_trigger) ((void)0) -#endif /* !CONFIG_XEN */ - -static void __init setup_IO_APIC_irqs(void) -{ - struct IO_APIC_route_entry entry; - int apic, pin, idx, irq, first_notcon = 1, vector; - unsigned long flags; - - apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n"); - - for (apic = 0; apic < nr_ioapics; apic++) { - for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) { - - /* - * add it to the IO-APIC irq-routing table: - */ - memset(&entry,0,sizeof(entry)); - - entry.delivery_mode = INT_DELIVERY_MODE; - entry.dest_mode = INT_DEST_MODE; - entry.mask = 0; /* enable IRQ */ - entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS); - - idx = find_irq_entry(apic,pin,mp_INT); - if (idx == -1) { - if (first_notcon) { - apic_printk(APIC_VERBOSE, KERN_DEBUG " IO-APIC (apicid-pin) %d-%d", mp_ioapics[apic].mpc_apicid, pin); - first_notcon = 0; - } else - apic_printk(APIC_VERBOSE, ", %d-%d", mp_ioapics[apic].mpc_apicid, pin); - continue; - } - - entry.trigger = irq_trigger(idx); - entry.polarity = irq_polarity(idx); - - if (irq_trigger(idx)) { - entry.trigger = 1; - entry.mask = 1; - entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS); - } - - irq = pin_2_irq(idx, apic, pin); - add_pin_to_irq(irq, apic, pin); - - if (/* !apic && */ !IO_APIC_IRQ(irq)) - continue; - - if (IO_APIC_IRQ(irq)) { - vector = assign_irq_vector(irq); - entry.vector = vector; - - ioapic_register_intr(irq, vector, IOAPIC_AUTO); - if (!apic && (irq < 16)) - disable_8259A_irq(irq); - } - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(apic, 0x11+2*pin, *(((int *)&entry)+1)); - io_apic_write(apic, 0x10+2*pin, *(((int *)&entry)+0)); - spin_unlock_irqrestore(&ioapic_lock, flags); - } - } - - if (!first_notcon) - apic_printk(APIC_VERBOSE," not connected.\n"); -} - -#ifndef CONFIG_XEN -/* - * Set up the 8259A-master output pin as broadcast to all - * CPUs. - */ -static void __init setup_ExtINT_IRQ0_pin(unsigned int pin, int vector) -{ - struct IO_APIC_route_entry entry; - unsigned long flags; - - memset(&entry,0,sizeof(entry)); - - disable_8259A_irq(0); - - /* mask LVT0 */ - apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); - - /* - * We use logical delivery to get the timer IRQ - * to the first CPU. - */ - entry.dest_mode = INT_DEST_MODE; - entry.mask = 0; /* unmask IRQ now */ - entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS); - entry.delivery_mode = INT_DELIVERY_MODE; - entry.polarity = 0; - entry.trigger = 0; - entry.vector = vector; - - /* - * The timer IRQ doesn't have to know that behind the - * scene we have a 8259A-master in AEOI mode ... - */ - irq_desc[0].handler = &ioapic_edge_type; - - /* - * Add it to the IO-APIC irq-routing table: - */ - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(0, 0x11+2*pin, *(((int *)&entry)+1)); - io_apic_write(0, 0x10+2*pin, *(((int *)&entry)+0)); - spin_unlock_irqrestore(&ioapic_lock, flags); - - enable_8259A_irq(0); -} - -void __init UNEXPECTED_IO_APIC(void) -{ -} - -void __apicdebuginit print_IO_APIC(void) -{ - int apic, i; - union IO_APIC_reg_00 reg_00; - union IO_APIC_reg_01 reg_01; - union IO_APIC_reg_02 reg_02; - unsigned long flags; - - if (apic_verbosity == APIC_QUIET) - return; - - printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries); - for (i = 0; i < nr_ioapics; i++) - printk(KERN_DEBUG "number of IO-APIC #%d registers: %d.\n", - mp_ioapics[i].mpc_apicid, nr_ioapic_registers[i]); - - /* - * We are a bit conservative about what we expect. We have to - * know about every hardware change ASAP. - */ - printk(KERN_INFO "testing the IO APIC.......................\n"); - - for (apic = 0; apic < nr_ioapics; apic++) { - - spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(apic, 0); - reg_01.raw = io_apic_read(apic, 1); - if (reg_01.bits.version >= 0x10) - reg_02.raw = io_apic_read(apic, 2); - spin_unlock_irqrestore(&ioapic_lock, flags); - - printk("\n"); - printk(KERN_DEBUG "IO APIC #%d......\n", mp_ioapics[apic].mpc_apicid); - printk(KERN_DEBUG ".... register #00: %08X\n", reg_00.raw); - printk(KERN_DEBUG "....... : physical APIC id: %02X\n", reg_00.bits.ID); - if (reg_00.bits.__reserved_1 || reg_00.bits.__reserved_2) - UNEXPECTED_IO_APIC(); - - printk(KERN_DEBUG ".... register #01: %08X\n", *(int *)&reg_01); - printk(KERN_DEBUG "....... : max redirection entries: %04X\n", reg_01.bits.entries); - if ( (reg_01.bits.entries != 0x0f) && /* older (Neptune) boards */ - (reg_01.bits.entries != 0x17) && /* typical ISA+PCI boards */ - (reg_01.bits.entries != 0x1b) && /* Compaq Proliant boards */ - (reg_01.bits.entries != 0x1f) && /* dual Xeon boards */ - (reg_01.bits.entries != 0x22) && /* bigger Xeon boards */ - (reg_01.bits.entries != 0x2E) && - (reg_01.bits.entries != 0x3F) && - (reg_01.bits.entries != 0x03) - ) - UNEXPECTED_IO_APIC(); - - printk(KERN_DEBUG "....... : PRQ implemented: %X\n", reg_01.bits.PRQ); - printk(KERN_DEBUG "....... : IO APIC version: %04X\n", reg_01.bits.version); - if ( (reg_01.bits.version != 0x01) && /* 82489DX IO-APICs */ - (reg_01.bits.version != 0x02) && /* 82801BA IO-APICs (ICH2) */ - (reg_01.bits.version != 0x10) && /* oldest IO-APICs */ - (reg_01.bits.version != 0x11) && /* Pentium/Pro IO-APICs */ - (reg_01.bits.version != 0x13) && /* Xeon IO-APICs */ - (reg_01.bits.version != 0x20) /* Intel P64H (82806 AA) */ - ) - UNEXPECTED_IO_APIC(); - if (reg_01.bits.__reserved_1 || reg_01.bits.__reserved_2) - UNEXPECTED_IO_APIC(); - - if (reg_01.bits.version >= 0x10) { - printk(KERN_DEBUG ".... register #02: %08X\n", reg_02.raw); - printk(KERN_DEBUG "....... : arbitration: %02X\n", reg_02.bits.arbitration); - if (reg_02.bits.__reserved_1 || reg_02.bits.__reserved_2) - UNEXPECTED_IO_APIC(); - } - - printk(KERN_DEBUG ".... IRQ redirection table:\n"); - - printk(KERN_DEBUG " NR Log Phy Mask Trig IRR Pol" - " Stat Dest Deli Vect: \n"); - - for (i = 0; i <= reg_01.bits.entries; i++) { - struct IO_APIC_route_entry entry; - - spin_lock_irqsave(&ioapic_lock, flags); - *(((int *)&entry)+0) = io_apic_read(apic, 0x10+i*2); - *(((int *)&entry)+1) = io_apic_read(apic, 0x11+i*2); - spin_unlock_irqrestore(&ioapic_lock, flags); - - printk(KERN_DEBUG " %02x %03X %02X ", - i, - entry.dest.logical.logical_dest, - entry.dest.physical.physical_dest - ); - - printk("%1d %1d %1d %1d %1d %1d %1d %02X\n", - entry.mask, - entry.trigger, - entry.irr, - entry.polarity, - entry.delivery_status, - entry.dest_mode, - entry.delivery_mode, - entry.vector - ); - } - } - if (use_pci_vector()) - printk(KERN_INFO "Using vector-based indexing\n"); - printk(KERN_DEBUG "IRQ to pin mappings:\n"); - for (i = 0; i < NR_IRQS; i++) { - struct irq_pin_list *entry = irq_2_pin + i; - if (entry->pin < 0) - continue; - if (use_pci_vector() && !platform_legacy_irq(i)) - printk(KERN_DEBUG "IRQ%d ", IO_APIC_VECTOR(i)); - else - printk(KERN_DEBUG "IRQ%d ", i); - for (;;) { - printk("-> %d:%d", entry->apic, entry->pin); - if (!entry->next) - break; - entry = irq_2_pin + entry->next; - } - printk("\n"); - } - - printk(KERN_INFO ".................................... done.\n"); - - return; -} - -#if 0 - -static __apicdebuginit void print_APIC_bitfield (int base) -{ - unsigned int v; - int i, j; - - if (apic_verbosity == APIC_QUIET) - return; - - printk(KERN_DEBUG "0123456789abcdef0123456789abcdef\n" KERN_DEBUG); - for (i = 0; i < 8; i++) { - v = apic_read(base + i*0x10); - for (j = 0; j < 32; j++) { - if (v & (1<<j)) - printk("1"); - else - printk("0"); - } - printk("\n"); - } -} - -void __apicdebuginit print_local_APIC(void * dummy) -{ - unsigned int v, ver, maxlvt; - - if (apic_verbosity == APIC_QUIET) - return; - - printk("\n" KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n", - smp_processor_id(), hard_smp_processor_id()); - v = apic_read(APIC_ID); - printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, GET_APIC_ID(v)); - v = apic_read(APIC_LVR); - printk(KERN_INFO "... APIC VERSION: %08x\n", v); - ver = GET_APIC_VERSION(v); - maxlvt = get_maxlvt(); - - v = apic_read(APIC_TASKPRI); - printk(KERN_DEBUG "... APIC TASKPRI: %08x (%02x)\n", v, v & APIC_TPRI_MASK); - - if (APIC_INTEGRATED(ver)) { /* !82489DX */ - v = apic_read(APIC_ARBPRI); - printk(KERN_DEBUG "... APIC ARBPRI: %08x (%02x)\n", v, - v & APIC_ARBPRI_MASK); - v = apic_read(APIC_PROCPRI); - printk(KERN_DEBUG "... APIC PROCPRI: %08x\n", v); - } - - v = apic_read(APIC_EOI); - printk(KERN_DEBUG "... APIC EOI: %08x\n", v); - v = apic_read(APIC_RRR); - printk(KERN_DEBUG "... APIC RRR: %08x\n", v); - v = apic_read(APIC_LDR); - printk(KERN_DEBUG "... APIC LDR: %08x\n", v); - v = apic_read(APIC_DFR); - printk(KERN_DEBUG "... APIC DFR: %08x\n", v); - v = apic_read(APIC_SPIV); - printk(KERN_DEBUG "... APIC SPIV: %08x\n", v); - - printk(KERN_DEBUG "... APIC ISR field:\n"); - print_APIC_bitfield(APIC_ISR); - printk(KERN_DEBUG "... APIC TMR field:\n"); - print_APIC_bitfield(APIC_TMR); - printk(KERN_DEBUG "... APIC IRR field:\n"); - print_APIC_bitfield(APIC_IRR); - - if (APIC_INTEGRATED(ver)) { /* !82489DX */ - if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */ - apic_write(APIC_ESR, 0); - v = apic_read(APIC_ESR); - printk(KERN_DEBUG "... APIC ESR: %08x\n", v); - } - - v = apic_read(APIC_ICR); - printk(KERN_DEBUG "... APIC ICR: %08x\n", v); - v = apic_read(APIC_ICR2); - printk(KERN_DEBUG "... APIC ICR2: %08x\n", v); - - v = apic_read(APIC_LVTT); - printk(KERN_DEBUG "... APIC LVTT: %08x\n", v); - - if (maxlvt > 3) { /* PC is LVT#4. */ - v = apic_read(APIC_LVTPC); - printk(KERN_DEBUG "... APIC LVTPC: %08x\n", v); - } - v = apic_read(APIC_LVT0); - printk(KERN_DEBUG "... APIC LVT0: %08x\n", v); - v = apic_read(APIC_LVT1); - printk(KERN_DEBUG "... APIC LVT1: %08x\n", v); - - if (maxlvt > 2) { /* ERR is LVT#3. */ - v = apic_read(APIC_LVTERR); - printk(KERN_DEBUG "... APIC LVTERR: %08x\n", v); - } - - v = apic_read(APIC_TMICT); - printk(KERN_DEBUG "... APIC TMICT: %08x\n", v); - v = apic_read(APIC_TMCCT); - printk(KERN_DEBUG "... APIC TMCCT: %08x\n", v); - v = apic_read(APIC_TDCR); - printk(KERN_DEBUG "... APIC TDCR: %08x\n", v); - printk("\n"); -} - -void print_all_local_APICs (void) -{ - on_each_cpu(print_local_APIC, NULL, 1, 1); -} - -void __apicdebuginit print_PIC(void) -{ - extern spinlock_t i8259A_lock; - unsigned int v; - unsigned long flags; - - if (apic_verbosity == APIC_QUIET) - return; - - printk(KERN_DEBUG "\nprinting PIC contents\n"); - - spin_lock_irqsave(&i8259A_lock, flags); - - v = inb(0xa1) << 8 | inb(0x21); - printk(KERN_DEBUG "... PIC IMR: %04x\n", v); - - v = inb(0xa0) << 8 | inb(0x20); - printk(KERN_DEBUG "... PIC IRR: %04x\n", v); - - outb(0x0b,0xa0); - outb(0x0b,0x20); - v = inb(0xa0) << 8 | inb(0x20); - outb(0x0a,0xa0); - outb(0x0a,0x20); - - spin_unlock_irqrestore(&i8259A_lock, flags); - - printk(KERN_DEBUG "... PIC ISR: %04x\n", v); - - v = inb(0x4d1) << 8 | inb(0x4d0); - printk(KERN_DEBUG "... PIC ELCR: %04x\n", v); -} - -#endif /* 0 */ - -#else -void __init print_IO_APIC(void) { } -#endif /* !CONFIG_XEN */ - -static void __init enable_IO_APIC(void) -{ - union IO_APIC_reg_01 reg_01; - int i; - unsigned long flags; - - for (i = 0; i < PIN_MAP_SIZE; i++) { - irq_2_pin[i].pin = -1; - irq_2_pin[i].next = 0; - } - if (!pirqs_enabled) - for (i = 0; i < MAX_PIRQS; i++) - pirq_entries[i] = -1; - - /* - * The number of IO-APIC IRQ registers (== #pins): - */ - for (i = 0; i < nr_ioapics; i++) { - spin_lock_irqsave(&ioapic_lock, flags); - reg_01.raw = io_apic_read(i, 1); - spin_unlock_irqrestore(&ioapic_lock, flags); - nr_ioapic_registers[i] = reg_01.bits.entries+1; - } - - /* - * Do not trust the IO-APIC being empty at bootup - */ - clear_IO_APIC(); -} - -/* - * Not an __init, needed by the reboot code - */ -void disable_IO_APIC(void) -{ - /* - * Clear the IO-APIC before rebooting: - */ - clear_IO_APIC(); - -#ifndef CONFIG_XEN - disconnect_bsp_APIC(); -#endif -} - -/* - * function to set the IO-APIC physical IDs based on the - * values stored in the MPC table. - * - * by Matt Domsch <Matt_Domsch@xxxxxxxx> Tue Dec 21 12:25:05 CST 1999 - */ - -#ifndef CONFIG_XEN -static void __init setup_ioapic_ids_from_mpc (void) -{ - union IO_APIC_reg_00 reg_00; - int apic; - int i; - unsigned char old_id; - unsigned long flags; - - /* - * Set the IOAPIC ID to the value stored in the MPC table. - */ - for (apic = 0; apic < nr_ioapics; apic++) { - - /* Read the register 0 value */ - spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(apic, 0); - spin_unlock_irqrestore(&ioapic_lock, flags); - - old_id = mp_ioapics[apic].mpc_apicid; - - - printk(KERN_INFO "Using IO-APIC %d\n", mp_ioapics[apic].mpc_apicid); - - - /* - * We need to adjust the IRQ routing table - * if the ID changed. - */ - if (old_id != mp_ioapics[apic].mpc_apicid) - for (i = 0; i < mp_irq_entries; i++) - if (mp_irqs[i].mpc_dstapic == old_id) - mp_irqs[i].mpc_dstapic - = mp_ioapics[apic].mpc_apicid; - - /* - * Read the right value from the MPC table and - * write it into the ID register. - */ - apic_printk(APIC_VERBOSE,KERN_INFO "...changing IO-APIC physical APIC ID to %d ...", - mp_ioapics[apic].mpc_apicid); - - reg_00.bits.ID = mp_ioapics[apic].mpc_apicid; - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(apic, 0, reg_00.raw); - spin_unlock_irqrestore(&ioapic_lock, flags); - - /* - * Sanity check - */ - spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(apic, 0); - spin_unlock_irqrestore(&ioapic_lock, flags); - if (reg_00.bits.ID != mp_ioapics[apic].mpc_apicid) - printk("could not set ID!\n"); - else - apic_printk(APIC_VERBOSE," ok.\n"); - } -} -#else -static void __init setup_ioapic_ids_from_mpc(void) { } -#endif - -/* - * There is a nasty bug in some older SMP boards, their mptable lies - * about the timer IRQ. We do the following to work around the situation: - * - * - timer IRQ defaults to IO-APIC IRQ - * - if this function detects that timer IRQs are defunct, then we fall - * back to ISA timer IRQs - */ -#ifndef CONFIG_XEN -static int __init timer_irq_works(void) -{ - unsigned long t1 = jiffies; - - local_irq_enable(); - /* Let ten ticks pass... */ - mdelay((10 * 1000) / HZ); - - /* - * Expect a few ticks at least, to be sure some possible - * glue logic does not lock up after one or two first - * ticks in a non-ExtINT mode. Also the local APIC - * might have cached one ExtINT interrupt. Finally, at - * least one tick may be lost due to delays. - */ - - /* jiffies wrap? */ - if (jiffies - t1 > 4) - return 1; - return 0; -} - -/* - * In the SMP+IOAPIC case it might happen that there are an unspecified - * number of pending IRQ events unhandled. These cases are very rare, - * so we 'resend' these IRQs via IPIs, to the same CPU. It's much - * better to do it this way as thus we do not have to be aware of - * 'pending' interrupts in the IRQ path, except at this point. - */ -/* - * Edge triggered needs to resend any interrupt - * that was delayed but this is now handled in the device - * independent code. - */ - -/* - * Starting up a edge-triggered IO-APIC interrupt is - * nasty - we need to make sure that we get the edge. - * If it is already asserted for some reason, we need - * return 1 to indicate that is was pending. - * - * This is not complete - we should be able to fake - * an edge even if it isn't on the 8259A... - */ - -static unsigned int startup_edge_ioapic_irq(unsigned int irq) -{ - int was_pending = 0; - unsigned long flags; - - spin_lock_irqsave(&ioapic_lock, flags); - if (irq < 16) { - disable_8259A_irq(irq); - if (i8259A_irq_pending(irq)) - was_pending = 1; - } - __unmask_IO_APIC_irq(irq); - spin_unlock_irqrestore(&ioapic_lock, flags); - - return was_pending; -} - -/* - * Once we have recorded IRQ_PENDING already, we can mask the - * interrupt for real. This prevents IRQ storms from unhandled - * devices. - */ -static void ack_edge_ioapic_irq(unsigned int irq) -{ - if ((irq_desc[irq].status & (IRQ_PENDING | IRQ_DISABLED)) - == (IRQ_PENDING | IRQ_DISABLED)) - mask_IO_APIC_irq(irq); - ack_APIC_irq(); -} - -/* - * Level triggered interrupts can just be masked, - * and shutting down and starting up the interrupt - * is the same as enabling and disabling them -- except - * with a startup need to return a "was pending" value. - * - * Level triggered interrupts are special because we - * do not touch any IO-APIC register while handling - * them. We ack the APIC in the end-IRQ handler, not - * in the start-IRQ-handler. Protection against reentrance - * from the same interrupt is still provided, both by the - * generic IRQ layer and by the fact that an unacked local - * APIC does not accept IRQs. - */ -static unsigned int startup_level_ioapic_irq (unsigned int irq) -{ - unmask_IO_APIC_irq(irq); - - return 0; /* don't check for pending */ -} - -static void end_level_ioapic_irq (unsigned int irq) -{ - ack_APIC_irq(); -} - -static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask) -{ - unsigned long flags; - unsigned int dest; - - dest = cpu_mask_to_apicid(mask); - - /* - * Only the high 8 bits are valid. - */ - dest = SET_APIC_LOGICAL_ID(dest); - - spin_lock_irqsave(&ioapic_lock, flags); - __DO_ACTION(1, = dest, ) - spin_unlock_irqrestore(&ioapic_lock, flags); -} - -#ifdef CONFIG_PCI_MSI -static unsigned int startup_edge_ioapic_vector(unsigned int vector) -{ - int irq = vector_to_irq(vector); - - return startup_edge_ioapic_irq(irq); -} - -static void ack_edge_ioapic_vector(unsigned int vector) -{ - int irq = vector_to_irq(vector); - - ack_edge_ioapic_irq(irq); -} - -static unsigned int startup_level_ioapic_vector (unsigned int vector) -{ - int irq = vector_to_irq(vector); - - return startup_level_ioapic_irq (irq); -} - -static void end_level_ioapic_vector (unsigned int vector) -{ - int irq = vector_to_irq(vector); - - end_level_ioapic_irq(irq); -} - -static void mask_IO_APIC_vector (unsigned int vector) -{ - int irq = vector_to_irq(vector); - - mask_IO_APIC_irq(irq); -} - -static void unmask_IO_APIC_vector (unsigned int vector) -{ - int irq = vector_to_irq(vector); - - unmask_IO_APIC_irq(irq); -} - -static void set_ioapic_affinity_vector (unsigned int vector, - cpumask_t cpu_mask) -{ - int irq = vector_to_irq(vector); - - set_ioapic_affinity_irq(irq, cpu_mask); -} -#endif - -/* - * Level and edge triggered IO-APIC interrupts need different handling, - * so we use two separate IRQ descriptors. Edge triggered IRQs can be - * handled with the level-triggered descriptor, but that one has slightly - * more overhead. Level-triggered interrupts cannot be handled with the - * edge-triggered handler, without risking IRQ storms and other ugly - * races. - */ - -static struct hw_interrupt_type ioapic_edge_type = { - .typename = "IO-APIC-edge", - .startup = startup_edge_ioapic, - .shutdown = shutdown_edge_ioapic, - .enable = enable_edge_ioapic, - .disable = disable_edge_ioapic, - .ack = ack_edge_ioapic, - .end = end_edge_ioapic, - .set_affinity = set_ioapic_affinity, -}; - -static struct hw_interrupt_type ioapic_level_type = { - .typename = "IO-APIC-level", - .startup = startup_level_ioapic, - .shutdown = shutdown_level_ioapic, - .enable = enable_level_ioapic, - .disable = disable_level_ioapic, - .ack = mask_and_ack_level_ioapic, - .end = end_level_ioapic, - .set_affinity = set_ioapic_affinity, -}; -#endif /* !CONFIG_XEN */ - -static inline void init_IO_APIC_traps(void) -{ - int irq; - - /* - * NOTE! The local APIC isn't very good at handling - * multiple interrupts at the same interrupt level. - * As the interrupt level is determined by taking the - * vector number and shifting that right by 4, we - * want to spread these out a bit so that they don't - * all fall in the same interrupt level. - * - * Also, we've got to be careful not to trash gate - * 0x80, because int 0x80 is hm, kind of importantish. ;) - */ - for (irq = 0; irq < NR_IRQS ; irq++) { - int tmp = irq; - if (use_pci_vector()) { - if (!platform_legacy_irq(tmp)) - if ((tmp = vector_to_irq(tmp)) == -1) - continue; - } - if (IO_APIC_IRQ(tmp) && !IO_APIC_VECTOR(tmp)) { - /* - * Hmm.. We don't have an entry for this, - * so default to an old-fashioned 8259 - * interrupt if we can.. - */ - if (irq < 16) - make_8259A_irq(irq); -#ifndef CONFIG_XEN - else - /* Strange. Oh, well.. */ - irq_desc[irq].handler = &no_irq_type; -#endif - } - } -} - -#ifndef CONFIG_XEN -static void enable_lapic_irq (unsigned int irq) -{ - unsigned long v; - - v = apic_read(APIC_LVT0); - apic_write_around(APIC_LVT0, v & ~APIC_LVT_MASKED); -} - -static void disable_lapic_irq (unsigned int irq) -{ - unsigned long v; - - v = apic_read(APIC_LVT0); - apic_write_around(APIC_LVT0, v | APIC_LVT_MASKED); -} - -static void ack_lapic_irq (unsigned int irq) -{ - ack_APIC_irq(); -} - -static void end_lapic_irq (unsigned int i) { /* nothing */ } - -static struct hw_interrupt_type lapic_irq_type = { - .typename = "local-APIC-edge", - .startup = NULL, /* startup_irq() not used for IRQ0 */ - .shutdown = NULL, /* shutdown_irq() not used for IRQ0 */ - .enable = enable_lapic_irq, - .disable = disable_lapic_irq, - .ack = ack_lapic_irq, - .end = end_lapic_irq, -}; - -static void setup_nmi (void) -{ - /* - * Dirty trick to enable the NMI watchdog ... - * We put the 8259A master into AEOI mode and - * unmask on all local APICs LVT0 as NMI. - * - * The idea to use the 8259A in AEOI mode ('8259A Virtual Wire') - * is from Maciej W. Rozycki - so we do not have to EOI from - * the NMI handler or the timer interrupt. - */ - printk(KERN_INFO "activating NMI Watchdog ..."); - - enable_NMI_through_LVT0(NULL); - - printk(" done.\n"); -} - -/* - * This looks a bit hackish but it's about the only one way of sending - * a few INTA cycles to 8259As and any associated glue logic. ICR does - * not support the ExtINT mode, unfortunately. We need to send these - * cycles as some i82489DX-based boards have glue logic that keeps the - * 8259A interrupt line asserted until INTA. --macro - */ -static inline void unlock_ExtINT_logic(void) -{ - int pin, i; - struct IO_APIC_route_entry entry0, entry1; - unsigned char save_control, save_freq_select; - unsigned long flags; - - pin = find_isa_irq_pin(8, mp_INT); - if (pin == -1) - return; - - spin_lock_irqsave(&ioapic_lock, flags); - *(((int *)&entry0) + 1) = io_apic_read(0, 0x11 + 2 * pin); - *(((int *)&entry0) + 0) = io_apic_read(0, 0x10 + 2 * pin); - spin_unlock_irqrestore(&ioapic_lock, flags); - clear_IO_APIC_pin(0, pin); - - memset(&entry1, 0, sizeof(entry1)); - - entry1.dest_mode = 0; /* physical delivery */ - entry1.mask = 0; /* unmask IRQ now */ - entry1.dest.physical.physical_dest = hard_smp_processor_id(); - entry1.delivery_mode = dest_ExtINT; - entry1.polarity = entry0.polarity; - entry1.trigger = 0; - entry1.vector = 0; - - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry1) + 1)); - io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry1) + 0)); - spin_unlock_irqrestore(&ioapic_lock, flags); - - save_control = CMOS_READ(RTC_CONTROL); - save_freq_select = CMOS_READ(RTC_FREQ_SELECT); - CMOS_WRITE((save_freq_select & ~RTC_RATE_SELECT) | 0x6, - RTC_FREQ_SELECT); - CMOS_WRITE(save_control | RTC_PIE, RTC_CONTROL); - - i = 100; - while (i-- > 0) { - mdelay(10); - if ((CMOS_READ(RTC_INTR_FLAGS) & RTC_PF) == RTC_PF) - i -= 10; - } - - CMOS_WRITE(save_control, RTC_CONTROL); - CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); - clear_IO_APIC_pin(0, pin); - - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(0, 0x11 + 2 * pin, *(((int *)&entry0) + 1)); - io_apic_write(0, 0x10 + 2 * pin, *(((int *)&entry0) + 0)); - spin_unlock_irqrestore(&ioapic_lock, flags); -} - -/* - * This code may look a bit paranoid, but it's supposed to cooperate with - * a wide range of boards and BIOS bugs. Fortunately only the timer IRQ - * is so screwy. Thanks to Brian Perkins for testing/hacking this beast - * fanatically on his truly buggy board. - */ -static inline void check_timer(void) -{ - int pin1, pin2; - int vector; - - /* - * get/set the timer IRQ vector: - */ - disable_8259A_irq(0); - vector = assign_irq_vector(0); - set_intr_gate(vector, interrupt[0]); - - /* - * Subtle, code in do_timer_interrupt() expects an AEOI - * mode for the 8259A whenever interrupts are routed - * through I/O APICs. Also IRQ0 has to be enabled in - * the 8259A which implies the virtual wire has to be - * disabled in the local APIC. - */ - apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT); - init_8259A(1); - enable_8259A_irq(0); - - pin1 = find_isa_irq_pin(0, mp_INT); - pin2 = find_isa_irq_pin(0, mp_ExtINT); - - apic_printk(APIC_VERBOSE,KERN_INFO "..TIMER: vector=0x%02X pin1=%d pin2=%d\n", vector, pin1, pin2); - - if (pin1 != -1) { - /* - * Ok, does IRQ0 through the IOAPIC work? - */ - unmask_IO_APIC_irq(0); - if (!no_timer_check && timer_irq_works()) { - nmi_watchdog_default(); - if (nmi_watchdog == NMI_IO_APIC) { - disable_8259A_irq(0); - setup_nmi(); - enable_8259A_irq(0); - } - return; - } - clear_IO_APIC_pin(0, pin1); - apic_printk(APIC_QUIET,KERN_ERR "..MP-BIOS bug: 8254 timer not connected to IO-APIC\n"); - } - - apic_printk(APIC_VERBOSE,KERN_INFO "...trying to set up timer (IRQ0) through the 8259A ... "); - if (pin2 != -1) { - apic_printk(APIC_VERBOSE,"\n..... (found pin %d) ...", pin2); - /* - * legacy devices should be connected to IO APIC #0 - */ - setup_ExtINT_IRQ0_pin(pin2, vector); - if (timer_irq_works()) { - printk("works.\n"); - nmi_watchdog_default(); - if (nmi_watchdog == NMI_IO_APIC) { - setup_nmi(); - } - return; - } - /* - * Cleanup, just in case ... - */ - clear_IO_APIC_pin(0, pin2); - } - printk(" failed.\n"); - - if (nmi_watchdog) { - printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n"); - nmi_watchdog = 0; - } - - apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as Virtual Wire IRQ..."); - - disable_8259A_irq(0); - irq_desc[0].handler = &lapic_irq_type; - apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector); /* Fixed mode */ - enable_8259A_irq(0); - - if (timer_irq_works()) { - apic_printk(APIC_QUIET, " works.\n"); - return; - } - apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | vector); - apic_printk(APIC_VERBOSE," failed.\n"); - - apic_printk(APIC_VERBOSE, KERN_INFO "...trying to set up timer as ExtINT IRQ..."); - - init_8259A(0); - make_8259A_irq(0); - apic_write_around(APIC_LVT0, APIC_DM_EXTINT); - - unlock_ExtINT_logic(); - - if (timer_irq_works()) { - apic_printk(APIC_VERBOSE," works.\n"); - return; - } - apic_printk(APIC_VERBOSE," failed :(.\n"); - panic("IO-APIC + timer doesn't work! Try using the 'noapic' kernel parameter\n"); -} -#else -#define check_timer() ((void)0) -#endif /* !CONFIG_XEN */ - -static int __init notimercheck(char *s) -{ - no_timer_check = 1; - return 1; -} -__setup("no_timer_check", notimercheck); - -/* - * - * IRQ's that are handled by the PIC in the MPS IOAPIC case. - * - IRQ2 is the cascade IRQ, and cannot be a io-apic IRQ. - * Linux doesn't really care, as it's not actually used - * for any interrupt handling anyway. - */ -#define PIC_IRQS (1<<2) - -void __init setup_IO_APIC(void) -{ - enable_IO_APIC(); - - if (acpi_ioapic) - io_apic_irqs = ~0; /* all IRQs go through IOAPIC */ - else - io_apic_irqs = ~PIC_IRQS; - - apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n"); - - /* - * Set up the IO-APIC IRQ routing table. - */ - if (!acpi_ioapic) - setup_ioapic_ids_from_mpc(); -#ifndef CONFIG_XEN - sync_Arb_IDs(); -#endif /* !CONFIG_XEN */ - setup_IO_APIC_irqs(); - init_IO_APIC_traps(); - check_timer(); - if (!acpi_ioapic) - print_IO_APIC(); -} - -struct sysfs_ioapic_data { - struct sys_device dev; - struct IO_APIC_route_entry entry[0]; -}; -static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS]; - -static int ioapic_suspend(struct sys_device *dev, pm_message_t state) -{ - struct IO_APIC_route_entry *entry; - struct sysfs_ioapic_data *data; - unsigned long flags; - int i; - - data = container_of(dev, struct sysfs_ioapic_data, dev); - entry = data->entry; - spin_lock_irqsave(&ioapic_lock, flags); - for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) { - *(((int *)entry) + 1) = io_apic_read(dev->id, 0x11 + 2 * i); - *(((int *)entry) + 0) = io_apic_read(dev->id, 0x10 + 2 * i); - } - spin_unlock_irqrestore(&ioapic_lock, flags); - - return 0; -} - -static int ioapic_resume(struct sys_device *dev) -{ - struct IO_APIC_route_entry *entry; - struct sysfs_ioapic_data *data; - unsigned long flags; - union IO_APIC_reg_00 reg_00; - int i; - - data = container_of(dev, struct sysfs_ioapic_data, dev); - entry = data->entry; - - spin_lock_irqsave(&ioapic_lock, flags); - reg_00.raw = io_apic_read(dev->id, 0); - if (reg_00.bits.ID != mp_ioapics[dev->id].mpc_apicid) { - reg_00.bits.ID = mp_ioapics[dev->id].mpc_apicid; - io_apic_write(dev->id, 0, reg_00.raw); - } - for (i = 0; i < nr_ioapic_registers[dev->id]; i ++, entry ++ ) { - io_apic_write(dev->id, 0x11+2*i, *(((int *)entry)+1)); - io_apic_write(dev->id, 0x10+2*i, *(((int *)entry)+0)); - } - spin_unlock_irqrestore(&ioapic_lock, flags); - - return 0; -} - -static struct sysdev_class ioapic_sysdev_class = { - set_kset_name("ioapic"), - .suspend = ioapic_suspend, - .resume = ioapic_resume, -}; - -static int __init ioapic_init_sysfs(void) -{ - struct sys_device * dev; - int i, size, error = 0; - - error = sysdev_class_register(&ioapic_sysdev_class); - if (error) - return error; - - for (i = 0; i < nr_ioapics; i++ ) { - size = sizeof(struct sys_device) + nr_ioapic_registers[i] - * sizeof(struct IO_APIC_route_entry); - mp_ioapic_data[i] = kmalloc(size, GFP_KERNEL); - if (!mp_ioapic_data[i]) { - printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i); - continue; - } - memset(mp_ioapic_data[i], 0, size); - dev = &mp_ioapic_data[i]->dev; - dev->id = i; - dev->cls = &ioapic_sysdev_class; - error = sysdev_register(dev); - if (error) { - kfree(mp_ioapic_data[i]); - mp_ioapic_data[i] = NULL; - printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i); - continue; - } - } - - return 0; -} - -device_initcall(ioapic_init_sysfs); - -/* -------------------------------------------------------------------------- - ACPI-based IOAPIC Configuration - -------------------------------------------------------------------------- */ - -#ifdef CONFIG_ACPI_BOOT - -#define IO_APIC_MAX_ID 0xFE - -int __init io_apic_get_version (int ioapic) -{ - union IO_APIC_reg_01 reg_01; - unsigned long flags; - - spin_lock_irqsave(&ioapic_lock, flags); - reg_01.raw = io_apic_read(ioapic, 1); - spin_unlock_irqrestore(&ioapic_lock, flags); - - return reg_01.bits.version; -} - - -int __init io_apic_get_redir_entries (int ioapic) -{ - union IO_APIC_reg_01 reg_01; - unsigned long flags; - - spin_lock_irqsave(&ioapic_lock, flags); - reg_01.raw = io_apic_read(ioapic, 1); - spin_unlock_irqrestore(&ioapic_lock, flags); - - return reg_01.bits.entries; -} - - -int io_apic_set_pci_routing (int ioapic, int pin, int irq, int edge_level, int active_high_low) -{ - struct IO_APIC_route_entry entry; - unsigned long flags; - - if (!IO_APIC_IRQ(irq)) { - apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n", - ioapic); - return -EINVAL; - } - - /* - * Generate a PCI IRQ routing entry and program the IOAPIC accordingly. - * Note that we mask (disable) IRQs now -- these get enabled when the - * corresponding device driver registers for this IRQ. - */ - - memset(&entry,0,sizeof(entry)); - - entry.delivery_mode = INT_DELIVERY_MODE; - entry.dest_mode = INT_DEST_MODE; - entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS); - entry.trigger = edge_level; - entry.polarity = active_high_low; - entry.mask = 1; /* Disabled (masked) */ - - /* - * IRQs < 16 are already in the irq_2_pin[] map - */ - if (irq >= 16) - add_pin_to_irq(irq, ioapic, pin); - - entry.vector = assign_irq_vector(irq); - - apic_printk(APIC_VERBOSE,KERN_DEBUG "IOAPIC[%d]: Set PCI routing entry (%d-%d -> 0x%x -> " - "IRQ %d Mode:%i Active:%i)\n", ioapic, - mp_ioapics[ioapic].mpc_apicid, pin, entry.vector, irq, - edge_level, active_high_low); - - ioapic_register_intr(irq, entry.vector, edge_level); - - if (!ioapic && (irq < 16)) - disable_8259A_irq(irq); - - spin_lock_irqsave(&ioapic_lock, flags); - io_apic_write(ioapic, 0x11+2*pin, *(((int *)&entry)+1)); - io_apic_write(ioapic, 0x10+2*pin, *(((int *)&entry)+0)); - spin_unlock_irqrestore(&ioapic_lock, flags); - - return 0; -} - -#endif /*CONFIG_ACPI_BOOT*/ - - -#ifndef CONFIG_XEN -/* - * This function currently is only a helper for the i386 smp boot process where - * we need to reprogram the ioredtbls to cater for the cpus which have come online - * so mask in all cases should simply be TARGET_CPUS - */ -void __init setup_ioapic_dest(void) -{ - int pin, ioapic, irq, irq_entry; - - if (skip_ioapic_setup == 1) - return; - - for (ioapic = 0; ioapic < nr_ioapics; ioapic++) { - for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) { - irq_entry = find_irq_entry(ioapic, pin, mp_INT); - if (irq_entry == -1) - continue; - irq = pin_2_irq(irq_entry, ioapic, pin); - set_ioapic_affinity_irq(irq, TARGET_CPUS); - } - - } -} -#endif /* !CONFIG_XEN */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/ioport.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/ioport.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,57 +0,0 @@ -/* - * linux/arch/x86_64/kernel/ioport.c - * - * This contains the io-permission bitmap code - written by obz, with changes - * by Linus. - */ - -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/types.h> -#include <linux/ioport.h> -#include <linux/mm.h> -#include <linux/smp.h> -#include <linux/smp_lock.h> -#include <linux/stddef.h> -#include <linux/slab.h> -#include <linux/thread_info.h> -#include <asm-xen/xen-public/physdev.h> - -/* - * sys_iopl has to be used when you want to access the IO ports - * beyond the 0x3ff range: to get the full 65536 ports bitmapped - * you'd need 8kB of bitmaps/process, which is a bit excessive. - * - */ - -asmlinkage long sys_iopl(unsigned int new_io_pl, struct pt_regs *regs) -{ - unsigned int old_io_pl = current->thread.io_pl; - physdev_op_t op; - - if (new_io_pl > 3) - return -EINVAL; - - /* Need "raw I/O" privileges for direct port access. */ - if ((new_io_pl > old_io_pl) && !capable(CAP_SYS_RAWIO)) - return -EPERM; - - /* Change our version of the privilege levels. */ - current->thread.io_pl = new_io_pl; - - /* Force the change at ring 0. */ - op.cmd = PHYSDEVOP_SET_IOPL; - op.u.set_iopl.iopl = (new_io_pl == 0) ? 1 : new_io_pl; - HYPERVISOR_physdev_op(&op); - - return 0; -} - -/* - * this changes the io permissions bitmap in the current task. - */ -asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) -{ - return turn_on ? sys_iopl(3, NULL) : 0; -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/irq.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/irq.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,107 +0,0 @@ -/* - * linux/arch/x86_64/kernel/irq.c - * - * Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar - * - * This file contains the lowest level x86_64-specific interrupt - * entry and irq statistics code. All the remaining irq logic is - * done by the generic kernel/irq/ code and in the - * x86_64-specific irq controller code. (e.g. i8259.c and - * io_apic.c.) - */ - -#include <linux/kernel_stat.h> -#include <linux/interrupt.h> -#include <linux/seq_file.h> -#include <linux/module.h> -#include <asm/uaccess.h> -#include <asm/io_apic.h> - -atomic_t irq_err_count; -#ifdef CONFIG_X86_IO_APIC -#ifdef APIC_MISMATCH_DEBUG -atomic_t irq_mis_count; -#endif -#endif - -/* - * Generic, controller-independent functions: - */ - -int show_interrupts(struct seq_file *p, void *v) -{ - int i = *(loff_t *) v, j; - struct irqaction * action; - unsigned long flags; - - if (i == 0) { - seq_printf(p, " "); - for (j=0; j<NR_CPUS; j++) - if (cpu_online(j)) - seq_printf(p, "CPU%d ",j); - seq_putc(p, '\n'); - } - - if (i < NR_IRQS) { - spin_lock_irqsave(&irq_desc[i].lock, flags); - action = irq_desc[i].action; - if (!action) - goto skip; - seq_printf(p, "%3d: ",i); -#ifndef CONFIG_SMP - seq_printf(p, "%10u ", kstat_irqs(i)); -#else - for (j=0; j<NR_CPUS; j++) - if (cpu_online(j)) - seq_printf(p, "%10u ", - kstat_cpu(j).irqs[i]); -#endif - seq_printf(p, " %14s", irq_desc[i].handler->typename); - - seq_printf(p, " %s", action->name); - for (action=action->next; action; action = action->next) - seq_printf(p, ", %s", action->name); - seq_putc(p, '\n'); -skip: - spin_unlock_irqrestore(&irq_desc[i].lock, flags); - } else if (i == NR_IRQS) { - seq_printf(p, "NMI: "); - for (j = 0; j < NR_CPUS; j++) - if (cpu_online(j)) - seq_printf(p, "%10u ", cpu_pda[j].__nmi_count); - seq_putc(p, '\n'); -#ifdef CONFIG_X86_LOCAL_APIC - seq_printf(p, "LOC: "); - for (j = 0; j < NR_CPUS; j++) - if (cpu_online(j)) - seq_printf(p, "%10u ", cpu_pda[j].apic_timer_irqs); - seq_putc(p, '\n'); -#endif - seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count)); -#ifdef CONFIG_X86_IO_APIC -#ifdef APIC_MISMATCH_DEBUG - seq_printf(p, "MIS: %10u\n", atomic_read(&irq_mis_count)); -#endif -#endif - } - return 0; -} - -/* - * do_IRQ handles all normal device IRQ's (the special - * SMP cross-CPU interrupts have their own specific - * handlers). - */ -asmlinkage unsigned int do_IRQ(struct pt_regs *regs) -{ - /* high bits used in ret_from_ code */ - int irq = regs->orig_rax & __IRQ_MASK(HARDIRQ_BITS); - - irq_enter(); - - __do_IRQ(irq, regs); - irq_exit(); - - return 1; -} - diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/ldt.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/ldt.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,282 +0,0 @@ -/* - * linux/arch/x86_64/kernel/ldt.c - * - * Copyright (C) 1992 Krishna Balasubramanian and Linus Torvalds - * Copyright (C) 1999 Ingo Molnar <mingo@xxxxxxxxxx> - * Copyright (C) 2002 Andi Kleen - * - * This handles calls from both 32bit and 64bit mode. - */ - -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/string.h> -#include <linux/mm.h> -#include <linux/smp.h> -#include <linux/smp_lock.h> -#include <linux/vmalloc.h> -#include <linux/slab.h> - -#include <asm/uaccess.h> -#include <asm/system.h> -#include <asm/ldt.h> -#include <asm/desc.h> -#include <asm/proto.h> -#include <asm/pgalloc.h> - -#ifdef CONFIG_SMP /* avoids "defined but not used" warnig */ -static void flush_ldt(void *null) -{ - if (current->active_mm) - load_LDT(&current->active_mm->context); -} -#endif - -static int alloc_ldt(mm_context_t *pc, unsigned mincount, int reload) -{ - void *oldldt; - void *newldt; - unsigned oldsize; - - if (mincount <= (unsigned)pc->size) - return 0; - oldsize = pc->size; - mincount = (mincount+511)&(~511); - if (mincount*LDT_ENTRY_SIZE > PAGE_SIZE) - newldt = vmalloc(mincount*LDT_ENTRY_SIZE); - else - newldt = kmalloc(mincount*LDT_ENTRY_SIZE, GFP_KERNEL); - - if (!newldt) - return -ENOMEM; - - if (oldsize) - memcpy(newldt, pc->ldt, oldsize*LDT_ENTRY_SIZE); - oldldt = pc->ldt; - memset(newldt+oldsize*LDT_ENTRY_SIZE, 0, (mincount-oldsize)*LDT_ENTRY_SIZE); - wmb(); - pc->ldt = newldt; - wmb(); - pc->size = mincount; - wmb(); - if (reload) { -#ifdef CONFIG_SMP - cpumask_t mask; - - preempt_disable(); -#endif - make_pages_readonly( - pc->ldt, - (pc->size * LDT_ENTRY_SIZE) / PAGE_SIZE, - XENFEAT_writable_descriptor_tables); - load_LDT(pc); -#ifdef CONFIG_SMP - mask = cpumask_of_cpu(smp_processor_id()); - if (!cpus_equal(current->mm->cpu_vm_mask, mask)) - smp_call_function(flush_ldt, NULL, 1, 1); - preempt_enable(); -#endif - } - if (oldsize) { - make_pages_writable( - oldldt, - (oldsize * LDT_ENTRY_SIZE) / PAGE_SIZE, - XENFEAT_writable_descriptor_tables); - if (oldsize*LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(oldldt); - else - kfree(oldldt); - } - return 0; -} - -static inline int copy_ldt(mm_context_t *new, mm_context_t *old) -{ - int err = alloc_ldt(new, old->size, 0); - if (err < 0) - return err; - memcpy(new->ldt, old->ldt, old->size*LDT_ENTRY_SIZE); - make_pages_readonly( - new->ldt, - (new->size * LDT_ENTRY_SIZE) / PAGE_SIZE, - XENFEAT_writable_descriptor_tables); - return 0; -} - -/* - * we do not have to muck with descriptors here, that is - * done in switch_mm() as needed. - */ -int init_new_context(struct task_struct *tsk, struct mm_struct *mm) -{ - struct mm_struct * old_mm; - int retval = 0; - - memset(&mm->context, 0, sizeof(mm->context)); - init_MUTEX(&mm->context.sem); - old_mm = current->mm; - if (old_mm && old_mm->context.size > 0) { - down(&old_mm->context.sem); - retval = copy_ldt(&mm->context, &old_mm->context); - up(&old_mm->context.sem); - } - if (retval == 0) { - spin_lock(&mm_unpinned_lock); - list_add(&mm->context.unpinned, &mm_unpinned); - spin_unlock(&mm_unpinned_lock); - } - return retval; -} - -/* - * - * Don't touch the LDT register - we're already in the next thread. - */ -void destroy_context(struct mm_struct *mm) -{ - if (mm->context.size) { - if (mm == current->active_mm) - clear_LDT(); - make_pages_writable( - mm->context.ldt, - (mm->context.size * LDT_ENTRY_SIZE) / PAGE_SIZE, - XENFEAT_writable_descriptor_tables); - if (mm->context.size*LDT_ENTRY_SIZE > PAGE_SIZE) - vfree(mm->context.ldt); - else - kfree(mm->context.ldt); - mm->context.size = 0; - } - if (!mm->context.pinned) { - spin_lock(&mm_unpinned_lock); - list_del(&mm->context.unpinned); - spin_unlock(&mm_unpinned_lock); - } -} - -static int read_ldt(void __user * ptr, unsigned long bytecount) -{ - int err; - unsigned long size; - struct mm_struct * mm = current->mm; - - if (!mm->context.size) - return 0; - if (bytecount > LDT_ENTRY_SIZE*LDT_ENTRIES) - bytecount = LDT_ENTRY_SIZE*LDT_ENTRIES; - - down(&mm->context.sem); - size = mm->context.size*LDT_ENTRY_SIZE; - if (size > bytecount) - size = bytecount; - - err = 0; - if (copy_to_user(ptr, mm->context.ldt, size)) - err = -EFAULT; - up(&mm->context.sem); - if (err < 0) - goto error_return; - if (size != bytecount) { - /* zero-fill the rest */ - if (clear_user(ptr+size, bytecount-size) != 0) { - err = -EFAULT; - goto error_return; - } - } - return bytecount; -error_return: - return err; -} - -static int read_default_ldt(void __user * ptr, unsigned long bytecount) -{ - /* Arbitrary number */ - /* x86-64 default LDT is all zeros */ - if (bytecount > 128) - bytecount = 128; - if (clear_user(ptr, bytecount)) - return -EFAULT; - return bytecount; -} - -static int write_ldt(void __user * ptr, unsigned long bytecount, int oldmode) -{ - struct task_struct *me = current; - struct mm_struct * mm = me->mm; - __u32 entry_1, entry_2, *lp; - unsigned long mach_lp; - int error; - struct user_desc ldt_info; - - error = -EINVAL; - - if (bytecount != sizeof(ldt_info)) - goto out; - error = -EFAULT; - if (copy_from_user(&ldt_info, ptr, bytecount)) - goto out; - - error = -EINVAL; - if (ldt_info.entry_number >= LDT_ENTRIES) - goto out; - if (ldt_info.contents == 3) { - if (oldmode) - goto out; - if (ldt_info.seg_not_present == 0) - goto out; - } - - down(&mm->context.sem); - if (ldt_info.entry_number >= (unsigned)mm->context.size) { - error = alloc_ldt(&current->mm->context, ldt_info.entry_number+1, 1); - if (error < 0) - goto out_unlock; - } - - lp = (__u32 *) ((ldt_info.entry_number << 3) + (char *) mm->context.ldt); - mach_lp = arbitrary_virt_to_machine(lp); - - /* Allow LDTs to be cleared by the user. */ - if (ldt_info.base_addr == 0 && ldt_info.limit == 0) { - if (oldmode || LDT_empty(&ldt_info)) { - entry_1 = 0; - entry_2 = 0; - goto install; - } - } - - entry_1 = LDT_entry_a(&ldt_info); - entry_2 = LDT_entry_b(&ldt_info); - if (oldmode) - entry_2 &= ~(1 << 20); - - /* Install the new entry ... */ -install: - error = HYPERVISOR_update_descriptor(mach_lp, (unsigned long)((entry_1 | (unsigned long) entry_2 << 32))); - -out_unlock: - up(&mm->context.sem); -out: - return error; -} - -asmlinkage int sys_modify_ldt(int func, void __user *ptr, unsigned long bytecount) -{ - int ret = -ENOSYS; - - switch (func) { - case 0: - ret = read_ldt(ptr, bytecount); - break; - case 1: - ret = write_ldt(ptr, bytecount, 1); - break; - case 2: - ret = read_default_ldt(ptr, bytecount); - break; - case 0x11: - ret = write_ldt(ptr, bytecount, 0); - break; - } - return ret; -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/mpparse.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/mpparse.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,963 +0,0 @@ -/* - * Intel Multiprocessor Specification 1.1 and 1.4 - * compliant MP-table parsing routines. - * - * (c) 1995 Alan Cox, Building #3 <alan@xxxxxxxxxx> - * (c) 1998, 1999, 2000 Ingo Molnar <mingo@xxxxxxxxxx> - * - * Fixes - * Erich Boleyn : MP v1.4 and additional changes. - * Alan Cox : Added EBDA scanning - * Ingo Molnar : various cleanups and rewrites - * Maciej W. Rozycki: Bits for default MP configurations - * Paul Diefenbaugh: Added full ACPI support - */ - -#include <linux/mm.h> -#include <linux/irq.h> -#include <linux/init.h> -#include <linux/delay.h> -#include <linux/config.h> -#include <linux/bootmem.h> -#include <linux/smp_lock.h> -#include <linux/kernel_stat.h> -#include <linux/mc146818rtc.h> -#include <linux/acpi.h> - -#include <asm/smp.h> -#include <asm/mtrr.h> -#include <asm/mpspec.h> -#include <asm/pgalloc.h> -#include <asm/io_apic.h> -#include <asm/proto.h> -#include <asm/acpi.h> - -/* Have we found an MP table */ -int smp_found_config; -unsigned int __initdata maxcpus = NR_CPUS; - -int acpi_found_madt; - -/* - * Various Linux-internal data structures created from the - * MP-table. - */ -int apic_version [MAX_APICS]; -unsigned char mp_bus_id_to_type [MAX_MP_BUSSES] = { [0 ... MAX_MP_BUSSES-1] = -1 }; -int mp_bus_id_to_pci_bus [MAX_MP_BUSSES] = { [0 ... MAX_MP_BUSSES-1] = -1 }; -cpumask_t pci_bus_to_cpumask [256] = { [0 ... 255] = CPU_MASK_ALL }; - -static int mp_current_pci_id = 0; -/* I/O APIC entries */ -struct mpc_config_ioapic mp_ioapics[MAX_IO_APICS]; - -/* # of MP IRQ source entries */ -struct mpc_config_intsrc mp_irqs[MAX_IRQ_SOURCES]; - -/* MP IRQ source entries */ -int mp_irq_entries; - -int nr_ioapics; -int pic_mode; -unsigned long mp_lapic_addr = 0; - - - -/* Processor that is doing the boot up */ -unsigned int boot_cpu_id = -1U; -/* Internal processor count */ -static unsigned int num_processors = 0; - -/* Bitmask of physically existing CPUs */ -physid_mask_t phys_cpu_present_map = PHYSID_MASK_NONE; - -/* ACPI MADT entry parsing functions */ -#ifdef CONFIG_ACPI_BOOT -extern struct acpi_boot_flags acpi_boot; -#ifdef CONFIG_X86_LOCAL_APIC -extern int acpi_parse_lapic (acpi_table_entry_header *header); -extern int acpi_parse_lapic_addr_ovr (acpi_table_entry_header *header); -extern int acpi_parse_lapic_nmi (acpi_table_entry_header *header); -#endif /*CONFIG_X86_LOCAL_APIC*/ -#ifdef CONFIG_X86_IO_APIC -extern int acpi_parse_ioapic (acpi_table_entry_header *header); -#endif /*CONFIG_X86_IO_APIC*/ -#endif /*CONFIG_ACPI_BOOT*/ - -u8 bios_cpu_apicid[NR_CPUS] = { [0 ... NR_CPUS-1] = BAD_APICID }; - - -/* - * Intel MP BIOS table parsing routines: - */ - -/* - * Checksum an MP configuration block. - */ - -static int __init mpf_checksum(unsigned char *mp, int len) -{ - int sum = 0; - - while (len--) - sum += *mp++; - - return sum & 0xFF; -} - -#ifndef CONFIG_XEN -static void __init MP_processor_info (struct mpc_config_processor *m) -{ - int ver; - static int found_bsp=0; - - if (!(m->mpc_cpuflag & CPU_ENABLED)) - return; - - printk(KERN_INFO "Processor #%d %d:%d APIC version %d\n", - m->mpc_apicid, - (m->mpc_cpufeature & CPU_FAMILY_MASK)>>8, - (m->mpc_cpufeature & CPU_MODEL_MASK)>>4, - m->mpc_apicver); - - if (m->mpc_cpuflag & CPU_BOOTPROCESSOR) { - Dprintk(" Bootup CPU\n"); - boot_cpu_id = m->mpc_apicid; - } - if (num_processors >= NR_CPUS) { - printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached." - " Processor ignored.\n", NR_CPUS); - return; - } - - num_processors++; - - if (m->mpc_apicid > MAX_APICS) { - printk(KERN_ERR "Processor #%d INVALID. (Max ID: %d).\n", - m->mpc_apicid, MAX_APICS); - return; - } - ver = m->mpc_apicver; - - physid_set(m->mpc_apicid, phys_cpu_present_map); - /* - * Validate version - */ - if (ver == 0x0) { - printk(KERN_ERR "BIOS bug, APIC version is 0 for CPU#%d! fixing up to 0x10. (tell your hw vendor)\n", m->mpc_apicid); - ver = 0x10; - } - apic_version[m->mpc_apicid] = ver; - if (m->mpc_cpuflag & CPU_BOOTPROCESSOR) { - /* - * bios_cpu_apicid is required to have processors listed - * in same order as logical cpu numbers. Hence the first - * entry is BSP, and so on. - */ - bios_cpu_apicid[0] = m->mpc_apicid; - x86_cpu_to_apicid[0] = m->mpc_apicid; - found_bsp = 1; - } else { - bios_cpu_apicid[num_processors - found_bsp] = m->mpc_apicid; - x86_cpu_to_apicid[num_processors - found_bsp] = m->mpc_apicid; - } -} -#else -void __init MP_processor_info (struct mpc_config_processor *m) -{ - num_processors++; -} -#endif /* CONFIG_XEN */ - -static void __init MP_bus_info (struct mpc_config_bus *m) -{ - char str[7]; - - memcpy(str, m->mpc_bustype, 6); - str[6] = 0; - Dprintk("Bus #%d is %s\n", m->mpc_busid, str); - - if (strncmp(str, "ISA", 3) == 0) { - mp_bus_id_to_type[m->mpc_busid] = MP_BUS_ISA; - } else if (strncmp(str, "EISA", 4) == 0) { - mp_bus_id_to_type[m->mpc_busid] = MP_BUS_EISA; - } else if (strncmp(str, "PCI", 3) == 0) { - mp_bus_id_to_type[m->mpc_busid] = MP_BUS_PCI; - mp_bus_id_to_pci_bus[m->mpc_busid] = mp_current_pci_id; - mp_current_pci_id++; - } else if (strncmp(str, "MCA", 3) == 0) { - mp_bus_id_to_type[m->mpc_busid] = MP_BUS_MCA; - } else { - printk(KERN_ERR "Unknown bustype %s\n", str); - } -} - -static void __init MP_ioapic_info (struct mpc_config_ioapic *m) -{ - if (!(m->mpc_flags & MPC_APIC_USABLE)) - return; - - printk("I/O APIC #%d Version %d at 0x%X.\n", - m->mpc_apicid, m->mpc_apicver, m->mpc_apicaddr); - if (nr_ioapics >= MAX_IO_APICS) { - printk(KERN_ERR "Max # of I/O APICs (%d) exceeded (found %d).\n", - MAX_IO_APICS, nr_ioapics); - panic("Recompile kernel with bigger MAX_IO_APICS!.\n"); - } - if (!m->mpc_apicaddr) { - printk(KERN_ERR "WARNING: bogus zero I/O APIC address" - " found in MP table, skipping!\n"); - return; - } - mp_ioapics[nr_ioapics] = *m; - nr_ioapics++; -} - -static void __init MP_intsrc_info (struct mpc_config_intsrc *m) -{ - mp_irqs [mp_irq_entries] = *m; - Dprintk("Int: type %d, pol %d, trig %d, bus %d," - " IRQ %02x, APIC ID %x, APIC INT %02x\n", - m->mpc_irqtype, m->mpc_irqflag & 3, - (m->mpc_irqflag >> 2) & 3, m->mpc_srcbus, - m->mpc_srcbusirq, m->mpc_dstapic, m->mpc_dstirq); - if (++mp_irq_entries == MAX_IRQ_SOURCES) - panic("Max # of irq sources exceeded!!\n"); -} - -static void __init MP_lintsrc_info (struct mpc_config_lintsrc *m) -{ - Dprintk("Lint: type %d, pol %d, trig %d, bus %d," - " IRQ %02x, APIC ID %x, APIC LINT %02x\n", - m->mpc_irqtype, m->mpc_irqflag & 3, - (m->mpc_irqflag >> 2) &3, m->mpc_srcbusid, - m->mpc_srcbusirq, m->mpc_destapic, m->mpc_destapiclint); - /* - * Well it seems all SMP boards in existence - * use ExtINT/LVT1 == LINT0 and - * NMI/LVT2 == LINT1 - the following check - * will show us if this assumptions is false. - * Until then we do not have to add baggage. - */ - if ((m->mpc_irqtype == mp_ExtINT) && - (m->mpc_destapiclint != 0)) - BUG(); - if ((m->mpc_irqtype == mp_NMI) && - (m->mpc_destapiclint != 1)) - BUG(); -} - -/* - * Read/parse the MPC - */ - -static int __init smp_read_mpc(struct mp_config_table *mpc) -{ - char str[16]; - int count=sizeof(*mpc); - unsigned char *mpt=((unsigned char *)mpc)+count; - - if (memcmp(mpc->mpc_signature,MPC_SIGNATURE,4)) { - printk("SMP mptable: bad signature [%c%c%c%c]!\n", - mpc->mpc_signature[0], - mpc->mpc_signature[1], - mpc->mpc_signature[2], - mpc->mpc_signature[3]); - return 0; - } - if (mpf_checksum((unsigned char *)mpc,mpc->mpc_length)) { - printk("SMP mptable: checksum error!\n"); - return 0; - } - if (mpc->mpc_spec!=0x01 && mpc->mpc_spec!=0x04) { - printk(KERN_ERR "SMP mptable: bad table version (%d)!!\n", - mpc->mpc_spec); - return 0; - } - if (!mpc->mpc_lapic) { - printk(KERN_ERR "SMP mptable: null local APIC address!\n"); - return 0; - } - memcpy(str,mpc->mpc_oem,8); - str[8]=0; - printk(KERN_INFO "OEM ID: %s ",str); - - memcpy(str,mpc->mpc_productid,12); - str[12]=0; - printk(KERN_INFO "Product ID: %s ",str); - - printk(KERN_INFO "APIC at: 0x%X\n",mpc->mpc_lapic); - - /* save the local APIC address, it might be non-default */ - if (!acpi_lapic) - mp_lapic_addr = mpc->mpc_lapic; - - /* - * Now process the configuration blocks. - */ - while (count < mpc->mpc_length) { - switch(*mpt) { - case MP_PROCESSOR: - { - struct mpc_config_processor *m= - (struct mpc_config_processor *)mpt; - if (!acpi_lapic) - MP_processor_info(m); - mpt += sizeof(*m); - count += sizeof(*m); - break; - } - case MP_BUS: - { - struct mpc_config_bus *m= - (struct mpc_config_bus *)mpt; - MP_bus_info(m); - mpt += sizeof(*m); - count += sizeof(*m); - break; - } - case MP_IOAPIC: - { - struct mpc_config_ioapic *m= - (struct mpc_config_ioapic *)mpt; - MP_ioapic_info(m); - mpt+=sizeof(*m); - count+=sizeof(*m); - break; - } - case MP_INTSRC: - { - struct mpc_config_intsrc *m= - (struct mpc_config_intsrc *)mpt; - - MP_intsrc_info(m); - mpt+=sizeof(*m); - count+=sizeof(*m); - break; - } - case MP_LINTSRC: - { - struct mpc_config_lintsrc *m= - (struct mpc_config_lintsrc *)mpt; - MP_lintsrc_info(m); - mpt+=sizeof(*m); - count+=sizeof(*m); - break; - } - } - } - clustered_apic_check(); - if (!num_processors) - printk(KERN_ERR "SMP mptable: no processors registered!\n"); - return num_processors; -} - -static int __init ELCR_trigger(unsigned int irq) -{ - unsigned int port; - - port = 0x4d0 + (irq >> 3); - return (inb(port) >> (irq & 7)) & 1; -} - -static void __init construct_default_ioirq_mptable(int mpc_default_type) -{ - struct mpc_config_intsrc intsrc; - int i; - int ELCR_fallback = 0; - - intsrc.mpc_type = MP_INTSRC; - intsrc.mpc_irqflag = 0; /* conforming */ - intsrc.mpc_srcbus = 0; - intsrc.mpc_dstapic = mp_ioapics[0].mpc_apicid; - - intsrc.mpc_irqtype = mp_INT; - - /* - * If true, we have an ISA/PCI system with no IRQ entries - * in the MP table. To prevent the PCI interrupts from being set up - * incorrectly, we try to use the ELCR. The sanity check to see if - * there is good ELCR data is very simple - IRQ0, 1, 2 and 13 can - * never be level sensitive, so we simply see if the ELCR agrees. - * If it does, we assume it's valid. - */ - if (mpc_default_type == 5) { - printk(KERN_INFO "ISA/PCI bus type with no IRQ information... falling back to ELCR\n"); - - if (ELCR_trigger(0) || ELCR_trigger(1) || ELCR_trigger(2) || ELCR_trigger(13)) - printk(KERN_ERR "ELCR contains invalid data... not using ELCR\n"); - else { - printk(KERN_INFO "Using ELCR to identify PCI interrupts\n"); - ELCR_fallback = 1; - } - } - - for (i = 0; i < 16; i++) { - switch (mpc_default_type) { - case 2: - if (i == 0 || i == 13) - continue; /* IRQ0 & IRQ13 not connected */ - /* fall through */ - default: - if (i == 2) - continue; /* IRQ2 is never connected */ - } - - if (ELCR_fallback) { - /* - * If the ELCR indicates a level-sensitive interrupt, we - * copy that information over to the MP table in the - * irqflag field (level sensitive, active high polarity). - */ - if (ELCR_trigger(i)) - intsrc.mpc_irqflag = 13; - else - intsrc.mpc_irqflag = 0; - } - - intsrc.mpc_srcbusirq = i; - intsrc.mpc_dstirq = i ? i : 2; /* IRQ0 to INTIN2 */ - MP_intsrc_info(&intsrc); - } - - intsrc.mpc_irqtype = mp_ExtINT; - intsrc.mpc_srcbusirq = 0; - intsrc.mpc_dstirq = 0; /* 8259A to INTIN0 */ - MP_intsrc_info(&intsrc); -} - -static inline void __init construct_default_ISA_mptable(int mpc_default_type) -{ - struct mpc_config_processor processor; - struct mpc_config_bus bus; - struct mpc_config_ioapic ioapic; - struct mpc_config_lintsrc lintsrc; - int linttypes[2] = { mp_ExtINT, mp_NMI }; - int i; - - /* - * local APIC has default address - */ - mp_lapic_addr = APIC_DEFAULT_PHYS_BASE; - - /* - * 2 CPUs, numbered 0 & 1. - */ - processor.mpc_type = MP_PROCESSOR; - /* Either an integrated APIC or a discrete 82489DX. */ - processor.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01; - processor.mpc_cpuflag = CPU_ENABLED; - processor.mpc_cpufeature = (boot_cpu_data.x86 << 8) | - (boot_cpu_data.x86_model << 4) | - boot_cpu_data.x86_mask; - processor.mpc_featureflag = boot_cpu_data.x86_capability[0]; - processor.mpc_reserved[0] = 0; - processor.mpc_reserved[1] = 0; - for (i = 0; i < 2; i++) { - processor.mpc_apicid = i; - MP_processor_info(&processor); - } - - bus.mpc_type = MP_BUS; - bus.mpc_busid = 0; - switch (mpc_default_type) { - default: - printk(KERN_ERR "???\nUnknown standard configuration %d\n", - mpc_default_type); - /* fall through */ - case 1: - case 5: - memcpy(bus.mpc_bustype, "ISA ", 6); - break; - case 2: - case 6: - case 3: - memcpy(bus.mpc_bustype, "EISA ", 6); - break; - case 4: - case 7: - memcpy(bus.mpc_bustype, "MCA ", 6); - } - MP_bus_info(&bus); - if (mpc_default_type > 4) { - bus.mpc_busid = 1; - memcpy(bus.mpc_bustype, "PCI ", 6); - MP_bus_info(&bus); - } - - ioapic.mpc_type = MP_IOAPIC; - ioapic.mpc_apicid = 2; - ioapic.mpc_apicver = mpc_default_type > 4 ? 0x10 : 0x01; - ioapic.mpc_flags = MPC_APIC_USABLE; - ioapic.mpc_apicaddr = 0xFEC00000; - MP_ioapic_info(&ioapic); - - /* - * We set up most of the low 16 IO-APIC pins according to MPS rules. - */ - construct_default_ioirq_mptable(mpc_default_type); - - lintsrc.mpc_type = MP_LINTSRC; - lintsrc.mpc_irqflag = 0; /* conforming */ - lintsrc.mpc_srcbusid = 0; - lintsrc.mpc_srcbusirq = 0; - lintsrc.mpc_destapic = MP_APIC_ALL; - for (i = 0; i < 2; i++) { - lintsrc.mpc_irqtype = linttypes[i]; - lintsrc.mpc_destapiclint = i; - MP_lintsrc_info(&lintsrc); - } -} - -static struct intel_mp_floating *mpf_found; - -/* - * Scan the memory blocks for an SMP configuration block. - */ -void __init get_smp_config (void) -{ - struct intel_mp_floating *mpf = mpf_found; - - /* - * ACPI may be used to obtain the entire SMP configuration or just to - * enumerate/configure processors (CONFIG_ACPI_BOOT). Note that - * ACPI supports both logical (e.g. Hyper-Threading) and physical - * processors, where MPS only supports physical. - */ - if (acpi_lapic && acpi_ioapic) { - printk(KERN_INFO "Using ACPI (MADT) for SMP configuration information\n"); - return; - } - else if (acpi_lapic) - printk(KERN_INFO "Using ACPI for processor (LAPIC) configuration information\n"); - - printk("Intel MultiProcessor Specification v1.%d\n", mpf->mpf_specification); - if (mpf->mpf_feature2 & (1<<7)) { - printk(KERN_INFO " IMCR and PIC compatibility mode.\n"); - pic_mode = 1; - } else { - printk(KERN_INFO " Virtual Wire compatibility mode.\n"); - pic_mode = 0; - } - - /* - * Now see if we need to read further. - */ - if (mpf->mpf_feature1 != 0) { - - printk(KERN_INFO "Default MP configuration #%d\n", mpf->mpf_feature1); - construct_default_ISA_mptable(mpf->mpf_feature1); - - } else if (mpf->mpf_physptr) { - - /* - * Read the physical hardware table. Anything here will - * override the defaults. - */ - if (!smp_read_mpc(isa_bus_to_virt(mpf->mpf_physptr))) { - smp_found_config = 0; - printk(KERN_ERR "BIOS bug, MP table errors detected!...\n"); - printk(KERN_ERR "... disabling SMP support. (tell your hw vendor)\n"); - return; - } - /* - * If there are no explicit MP IRQ entries, then we are - * broken. We set up most of the low 16 IO-APIC pins to - * ISA defaults and hope it will work. - */ - if (!mp_irq_entries) { - struct mpc_config_bus bus; - - printk(KERN_ERR "BIOS bug, no explicit IRQ entries, using default mptable. (tell your hw vendor)\n"); - - bus.mpc_type = MP_BUS; - bus.mpc_busid = 0; - memcpy(bus.mpc_bustype, "ISA ", 6); - MP_bus_info(&bus); - - construct_default_ioirq_mptable(0); - } - - } else - BUG(); - - printk(KERN_INFO "Processors: %d\n", num_processors); - /* - * Only use the first configuration found. - */ -} - -static int __init smp_scan_config (unsigned long base, unsigned long length) -{ - extern void __bad_mpf_size(void); - unsigned int *bp = isa_bus_to_virt(base); - struct intel_mp_floating *mpf; - - Dprintk("Scan SMP from %p for %ld bytes.\n", bp,length); - if (sizeof(*mpf) != 16) - __bad_mpf_size(); - - while (length > 0) { - mpf = (struct intel_mp_floating *)bp; - if ((*bp == SMP_MAGIC_IDENT) && - (mpf->mpf_length == 1) && - !mpf_checksum((unsigned char *)bp, 16) && - ((mpf->mpf_specification == 1) - || (mpf->mpf_specification == 4)) ) { - - smp_found_config = 1; - mpf_found = mpf; - return 1; - } - bp += 4; - length -= 16; - } - return 0; -} - -void __init find_intel_smp (void) -{ - unsigned int address; - - /* - * FIXME: Linux assumes you have 640K of base ram.. - * this continues the error... - * - * 1) Scan the bottom 1K for a signature - * 2) Scan the top 1K of base RAM - * 3) Scan the 64K of bios - */ - if (smp_scan_config(0x0,0x400) || - smp_scan_config(639*0x400,0x400) || - smp_scan_config(0xF0000,0x10000)) - return; - /* - * If it is an SMP machine we should know now, unless the - * configuration is in an EISA/MCA bus machine with an - * extended bios data area. - * - * there is a real-mode segmented pointer pointing to the - * 4K EBDA area at 0x40E, calculate and scan it here. - * - * NOTE! There are Linux loaders that will corrupt the EBDA - * area, and as such this kind of SMP config may be less - * trustworthy, simply because the SMP table may have been - * stomped on during early boot. These loaders are buggy and - * should be fixed. - */ - - address = *(unsigned short *)phys_to_virt(0x40E); - address <<= 4; - if (smp_scan_config(address, 0x1000)) - return; - - /* If we have come this far, we did not find an MP table */ - printk(KERN_INFO "No mptable found.\n"); -} - -/* - * - Intel MP Configuration Table - */ -void __init find_smp_config (void) -{ -#ifdef CONFIG_X86_LOCAL_APIC - find_intel_smp(); -#endif -} - - -/* -------------------------------------------------------------------------- - ACPI-based MP Configuration - -------------------------------------------------------------------------- */ - -#ifdef CONFIG_ACPI_BOOT - -void __init mp_register_lapic_address ( - u64 address) -{ -#ifndef CONFIG_XEN - mp_lapic_addr = (unsigned long) address; - - if (boot_cpu_id == -1U) - boot_cpu_id = GET_APIC_ID(apic_read(APIC_ID)); - - Dprintk("Boot CPU = %d\n", boot_cpu_physical_apicid); -#endif -} - - -void __init mp_register_lapic ( - u8 id, - u8 enabled) -{ - struct mpc_config_processor processor; - int boot_cpu = 0; - - if (id >= MAX_APICS) { - printk(KERN_WARNING "Processor #%d invalid (max %d)\n", - id, MAX_APICS); - return; - } - - if (id == boot_cpu_physical_apicid) - boot_cpu = 1; - -#ifndef CONFIG_XEN - processor.mpc_type = MP_PROCESSOR; - processor.mpc_apicid = id; - processor.mpc_apicver = 0x10; /* TBD: lapic version */ - processor.mpc_cpuflag = (enabled ? CPU_ENABLED : 0); - processor.mpc_cpuflag |= (boot_cpu ? CPU_BOOTPROCESSOR : 0); - processor.mpc_cpufeature = (boot_cpu_data.x86 << 8) | - (boot_cpu_data.x86_model << 4) | boot_cpu_data.x86_mask; - processor.mpc_featureflag = boot_cpu_data.x86_capability[0]; - processor.mpc_reserved[0] = 0; - processor.mpc_reserved[1] = 0; -#endif - - MP_processor_info(&processor); -} - -#ifdef CONFIG_X86_IO_APIC - -#define MP_ISA_BUS 0 -#define MP_MAX_IOAPIC_PIN 127 - -static struct mp_ioapic_routing { - int apic_id; - int gsi_start; - int gsi_end; - u32 pin_programmed[4]; -} mp_ioapic_routing[MAX_IO_APICS]; - - -static int mp_find_ioapic ( - int gsi) -{ - int i = 0; - - /* Find the IOAPIC that manages this GSI. */ - for (i = 0; i < nr_ioapics; i++) { - if ((gsi >= mp_ioapic_routing[i].gsi_start) - && (gsi <= mp_ioapic_routing[i].gsi_end)) - return i; - } - - printk(KERN_ERR "ERROR: Unable to locate IOAPIC for GSI %d\n", gsi); - - return -1; -} - - -void __init mp_register_ioapic ( - u8 id, - u32 address, - u32 gsi_base) -{ - int idx = 0; - - if (nr_ioapics >= MAX_IO_APICS) { - printk(KERN_ERR "ERROR: Max # of I/O APICs (%d) exceeded " - "(found %d)\n", MAX_IO_APICS, nr_ioapics); - panic("Recompile kernel with bigger MAX_IO_APICS!\n"); - } - if (!address) { - printk(KERN_ERR "WARNING: Bogus (zero) I/O APIC address" - " found in MADT table, skipping!\n"); - return; - } - - idx = nr_ioapics++; - - mp_ioapics[idx].mpc_type = MP_IOAPIC; - mp_ioapics[idx].mpc_flags = MPC_APIC_USABLE; - mp_ioapics[idx].mpc_apicaddr = address; - - mp_ioapics[idx].mpc_apicid = id; - mp_ioapics[idx].mpc_apicver = io_apic_get_version(idx); - - /* - * Build basic IRQ lookup table to facilitate gsi->io_apic lookups - * and to prevent reprogramming of IOAPIC pins (PCI IRQs). - */ - mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].mpc_apicid; - mp_ioapic_routing[idx].gsi_start = gsi_base; - mp_ioapic_routing[idx].gsi_end = gsi_base + - io_apic_get_redir_entries(idx); - - printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, " - "GSI %d-%d\n", idx, mp_ioapics[idx].mpc_apicid, - mp_ioapics[idx].mpc_apicver, mp_ioapics[idx].mpc_apicaddr, - mp_ioapic_routing[idx].gsi_start, - mp_ioapic_routing[idx].gsi_end); - - return; -} - - -void __init mp_override_legacy_irq ( - u8 bus_irq, - u8 polarity, - u8 trigger, - u32 gsi) -{ - struct mpc_config_intsrc intsrc; - int ioapic = -1; - int pin = -1; - - /* - * Convert 'gsi' to 'ioapic.pin'. - */ - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) - return; - pin = gsi - mp_ioapic_routing[ioapic].gsi_start; - - /* - * TBD: This check is for faulty timer entries, where the override - * erroneously sets the trigger to level, resulting in a HUGE - * increase of timer interrupts! - */ - if ((bus_irq == 0) && (trigger == 3)) - trigger = 1; - - intsrc.mpc_type = MP_INTSRC; - intsrc.mpc_irqtype = mp_INT; - intsrc.mpc_irqflag = (trigger << 2) | polarity; - intsrc.mpc_srcbus = MP_ISA_BUS; - intsrc.mpc_srcbusirq = bus_irq; /* IRQ */ - intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid; /* APIC ID */ - intsrc.mpc_dstirq = pin; /* INTIN# */ - - Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, %d-%d\n", - intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3, - (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus, - intsrc.mpc_srcbusirq, intsrc.mpc_dstapic, intsrc.mpc_dstirq); - - mp_irqs[mp_irq_entries] = intsrc; - if (++mp_irq_entries == MAX_IRQ_SOURCES) - panic("Max # of irq sources exceeded!\n"); - - return; -} - - -void __init mp_config_acpi_legacy_irqs (void) -{ - struct mpc_config_intsrc intsrc; - int i = 0; - int ioapic = -1; - - /* - * Fabricate the legacy ISA bus (bus #31). - */ - mp_bus_id_to_type[MP_ISA_BUS] = MP_BUS_ISA; - Dprintk("Bus #%d is ISA\n", MP_ISA_BUS); - - /* - * Locate the IOAPIC that manages the ISA IRQs (0-15). - */ - ioapic = mp_find_ioapic(0); - if (ioapic < 0) - return; - - intsrc.mpc_type = MP_INTSRC; - intsrc.mpc_irqflag = 0; /* Conforming */ - intsrc.mpc_srcbus = MP_ISA_BUS; - intsrc.mpc_dstapic = mp_ioapics[ioapic].mpc_apicid; - - /* - * Use the default configuration for the IRQs 0-15. Unless - * overridden by (MADT) interrupt source override entries. - */ - for (i = 0; i < 16; i++) { - int idx; - - for (idx = 0; idx < mp_irq_entries; idx++) { - struct mpc_config_intsrc *irq = mp_irqs + idx; - - /* Do we already have a mapping for this ISA IRQ? */ - if (irq->mpc_srcbus == MP_ISA_BUS && irq->mpc_srcbusirq == i) - break; - - /* Do we already have a mapping for this IOAPIC pin */ - if ((irq->mpc_dstapic == intsrc.mpc_dstapic) && - (irq->mpc_dstirq == i)) - break; - } - - if (idx != mp_irq_entries) { - printk(KERN_DEBUG "ACPI: IRQ%d used by override.\n", i); - continue; /* IRQ already used */ - } - - intsrc.mpc_irqtype = mp_INT; - intsrc.mpc_srcbusirq = i; /* Identity mapped */ - intsrc.mpc_dstirq = i; - - Dprintk("Int: type %d, pol %d, trig %d, bus %d, irq %d, " - "%d-%d\n", intsrc.mpc_irqtype, intsrc.mpc_irqflag & 3, - (intsrc.mpc_irqflag >> 2) & 3, intsrc.mpc_srcbus, - intsrc.mpc_srcbusirq, intsrc.mpc_dstapic, - intsrc.mpc_dstirq); - - mp_irqs[mp_irq_entries] = intsrc; - if (++mp_irq_entries == MAX_IRQ_SOURCES) - panic("Max # of irq sources exceeded!\n"); - } - - return; -} - -int mp_register_gsi(u32 gsi, int edge_level, int active_high_low) -{ - int ioapic = -1; - int ioapic_pin = 0; - int idx, bit = 0; - - if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) - return gsi; - -#ifdef CONFIG_ACPI_BUS - /* Don't set up the ACPI SCI because it's already set up */ - if (acpi_fadt.sci_int == gsi) - return gsi; -#endif - - ioapic = mp_find_ioapic(gsi); - if (ioapic < 0) { - printk(KERN_WARNING "No IOAPIC for GSI %u\n", gsi); - return gsi; - } - - ioapic_pin = gsi - mp_ioapic_routing[ioapic].gsi_start; - - /* - * Avoid pin reprogramming. PRTs typically include entries - * with redundant pin->gsi mappings (but unique PCI devices); - * we only program the IOAPIC on the first. - */ - bit = ioapic_pin % 32; - idx = (ioapic_pin < 32) ? 0 : (ioapic_pin / 32); - if (idx > 3) { - printk(KERN_ERR "Invalid reference to IOAPIC pin " - "%d-%d\n", mp_ioapic_routing[ioapic].apic_id, - ioapic_pin); - return gsi; - } - if ((1<<bit) & mp_ioapic_routing[ioapic].pin_programmed[idx]) { - Dprintk(KERN_DEBUG "Pin %d-%d already programmed\n", - mp_ioapic_routing[ioapic].apic_id, ioapic_pin); - return gsi; - } - - mp_ioapic_routing[ioapic].pin_programmed[idx] |= (1<<bit); - - io_apic_set_pci_routing(ioapic, ioapic_pin, gsi, - edge_level == ACPI_EDGE_SENSITIVE ? 0 : 1, - active_high_low == ACPI_ACTIVE_HIGH ? 0 : 1); - return gsi; -} - -#endif /*CONFIG_X86_IO_APIC*/ -#endif /*CONFIG_ACPI_BOOT*/ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/pci-nommu.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/pci-nommu.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,98 +0,0 @@ -/* Fallback functions when the main IOMMU code is not compiled in. This - code is roughly equivalent to i386. */ -#include <linux/mm.h> -#include <linux/init.h> -#include <linux/pci.h> -#include <linux/string.h> -#include <asm/proto.h> -#include <asm/processor.h> - -int iommu_merge = 0; -EXPORT_SYMBOL(iommu_merge); - -dma_addr_t bad_dma_address; -EXPORT_SYMBOL(bad_dma_address); - -int iommu_bio_merge = 0; -EXPORT_SYMBOL(iommu_bio_merge); - -int iommu_sac_force = 0; -EXPORT_SYMBOL(iommu_sac_force); - -#if 0 -/* - * Dummy IO MMU functions - */ - -void *dma_alloc_coherent(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, unsigned gfp) -{ - void *ret; - u64 mask; - int order = get_order(size); - - if (hwdev) - mask = hwdev->coherent_dma_mask & *hwdev->dma_mask; - else - mask = 0xffffffff; - for (;;) { - ret = (void *)__get_free_pages(gfp, order); - if (ret == NULL) - return NULL; - *dma_handle = virt_to_bus(ret); - if ((*dma_handle & ~mask) == 0) - break; - free_pages((unsigned long)ret, order); - if (gfp & GFP_DMA) - return NULL; - gfp |= GFP_DMA; - } - - memset(ret, 0, size); - return ret; -} -EXPORT_SYMBOL(dma_alloc_coherent); - -void dma_free_coherent(struct device *hwdev, size_t size, - void *vaddr, dma_addr_t dma_handle) -{ - free_pages((unsigned long)vaddr, get_order(size)); -} -EXPORT_SYMBOL(dma_free_coherent); -#endif - -#if 0 -int dma_supported(struct device *hwdev, u64 mask) -{ - /* - * we fall back to GFP_DMA when the mask isn't all 1s, - * so we can't guarantee allocations that must be - * within a tighter range than GFP_DMA.. - * RED-PEN this won't work for pci_map_single. Caller has to - * use GFP_DMA in the first place. - */ - if (mask < 0x00ffffff) - return 0; - - return 1; -} -EXPORT_SYMBOL(dma_supported); -#endif - -int dma_get_cache_alignment(void) -{ - return boot_cpu_data.x86_clflush_size; -} -EXPORT_SYMBOL(dma_get_cache_alignment); - -static int __init check_ram(void) -{ - if (end_pfn >= 0xffffffff>>PAGE_SHIFT) { - printk( - KERN_ERR "WARNING more than 4GB of memory but IOMMU not compiled in.\n" - KERN_ERR "WARNING 32bit PCI may malfunction.\n"); - } - return 0; -} -__initcall(check_ram); - diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/process.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/process.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,752 +0,0 @@ -/* - * linux/arch/x86-64/kernel/process.c - * - * Copyright (C) 1995 Linus Torvalds - * - * Pentium III FXSR, SSE support - * Gareth Hughes <gareth@xxxxxxxxxxx>, May 2000 - * - * X86-64 port - * Andi Kleen. - * - * $Id: process.c,v 1.38 2002/01/15 10:08:03 ak Exp $ - * - * Jun Nakajima <jun.nakajima@xxxxxxxxx> - * Modified for Xen - */ - -/* - * This file handles the architecture-dependent parts of process handling.. - */ - -#include <stdarg.h> - -#include <linux/cpu.h> -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/elfcore.h> -#include <linux/smp.h> -#include <linux/slab.h> -#include <linux/user.h> -#include <linux/module.h> -#include <linux/a.out.h> -#include <linux/interrupt.h> -#include <linux/delay.h> -#include <linux/irq.h> -#include <linux/ptrace.h> -#include <linux/utsname.h> -#include <linux/random.h> - -#include <asm/uaccess.h> -#include <asm/pgtable.h> -#include <asm/system.h> -#include <asm/io.h> -#include <asm/processor.h> -#include <asm/i387.h> -#include <asm/mmu_context.h> -#include <asm/pda.h> -#include <asm/prctl.h> -#include <asm/kdebug.h> -#include <asm-xen/xen-public/dom0_ops.h> -#include <asm-xen/xen-public/physdev.h> -#include <asm/desc.h> -#include <asm/proto.h> -#include <asm/hardirq.h> -#include <asm/ia32.h> - -asmlinkage extern void ret_from_fork(void); - -unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED; - -static atomic_t hlt_counter = ATOMIC_INIT(0); - -unsigned long boot_option_idle_override = 0; -EXPORT_SYMBOL(boot_option_idle_override); - -/* - * Powermanagement idle function, if any.. - */ -void (*pm_idle)(void); -static DEFINE_PER_CPU(unsigned int, cpu_idle_state); - -void disable_hlt(void) -{ - atomic_inc(&hlt_counter); -} - -EXPORT_SYMBOL(disable_hlt); - -void enable_hlt(void) -{ - atomic_dec(&hlt_counter); -} - -EXPORT_SYMBOL(enable_hlt); - -/* XXX XEN doesn't use default_idle(), poll_idle(). Use xen_idle() instead. */ -extern void stop_hz_timer(void); -extern void start_hz_timer(void); -void xen_idle(void) -{ - local_irq_disable(); - - if (need_resched()) { - local_irq_enable(); - } else { - stop_hz_timer(); - /* Blocking includes an implicit local_irq_enable(). */ - HYPERVISOR_sched_op(SCHEDOP_block, 0); - start_hz_timer(); - } -} - -#ifdef CONFIG_HOTPLUG_CPU -#include <asm/nmi.h> -/* We don't actually take CPU down, just spin without interrupts. */ -static inline void play_dead(void) -{ - /* Ack it */ - __get_cpu_var(cpu_state) = CPU_DEAD; - - /* We shouldn't have to disable interrupts while dead, but - * some interrupts just don't seem to go away, and this makes - * it "work" for testing purposes. */ - /* Death loop */ - while (__get_cpu_var(cpu_state) != CPU_UP_PREPARE) - HYPERVISOR_sched_op(SCHEDOP_yield, 0); - - local_irq_disable(); - __flush_tlb_all(); - cpu_set(smp_processor_id(), cpu_online_map); - local_irq_enable(); -} -#else -static inline void play_dead(void) -{ - BUG(); -} -#endif /* CONFIG_HOTPLUG_CPU */ - -/* - * The idle thread. There's no useful work to be - * done, so just try to conserve power and have a - * low exit latency (ie sit in a loop waiting for - * somebody to say that they'd like to reschedule) - */ -void cpu_idle (void) -{ - int cpu = smp_processor_id(); - - /* endless idle loop with no priority at all */ - while (1) { - while (!need_resched()) { - if (__get_cpu_var(cpu_idle_state)) - __get_cpu_var(cpu_idle_state) = 0; - rmb(); - - if (cpu_is_offline(cpu)) - play_dead(); - - xen_idle(); - } - - schedule(); - } -} - -void cpu_idle_wait(void) -{ - unsigned int cpu, this_cpu = get_cpu(); - cpumask_t map; - - set_cpus_allowed(current, cpumask_of_cpu(this_cpu)); - put_cpu(); - - cpus_clear(map); - for_each_online_cpu(cpu) { - per_cpu(cpu_idle_state, cpu) = 1; - cpu_set(cpu, map); - } - - __get_cpu_var(cpu_idle_state) = 0; - - wmb(); - do { - ssleep(1); - for_each_online_cpu(cpu) { - if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu)) - cpu_clear(cpu, map); - } - cpus_and(map, map, cpu_online_map); - } while (!cpus_empty(map)); -} -EXPORT_SYMBOL_GPL(cpu_idle_wait); - -/* XXX XEN doesn't use mwait_idle(), select_idle_routine(), idle_setup(). */ -/* Always use xen_idle() instead. */ -void __init select_idle_routine(const struct cpuinfo_x86 *c) {} - -/* Prints also some state that isn't saved in the pt_regs */ -void __show_regs(struct pt_regs * regs) -{ - unsigned long fs, gs, shadowgs; - unsigned int fsindex,gsindex; - unsigned int ds,cs,es; - - printk("\n"); - print_modules(); - printk("Pid: %d, comm: %.20s %s %s\n", - current->pid, current->comm, print_tainted(), system_utsname.release); - printk("RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->rip); - printk_address(regs->rip); - printk("\nRSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, regs->rsp, regs->eflags); - printk("RAX: %016lx RBX: %016lx RCX: %016lx\n", - regs->rax, regs->rbx, regs->rcx); - printk("RDX: %016lx RSI: %016lx RDI: %016lx\n", - regs->rdx, regs->rsi, regs->rdi); - printk("RBP: %016lx R08: %016lx R09: %016lx\n", - regs->rbp, regs->r8, regs->r9); - printk("R10: %016lx R11: %016lx R12: %016lx\n", - regs->r10, regs->r11, regs->r12); - printk("R13: %016lx R14: %016lx R15: %016lx\n", - regs->r13, regs->r14, regs->r15); - - asm("mov %%ds,%0" : "=r" (ds)); - asm("mov %%cs,%0" : "=r" (cs)); - asm("mov %%es,%0" : "=r" (es)); - asm("mov %%fs,%0" : "=r" (fsindex)); - asm("mov %%gs,%0" : "=r" (gsindex)); - - rdmsrl(MSR_FS_BASE, fs); - rdmsrl(MSR_GS_BASE, gs); - rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); - - printk("FS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", - fs,fsindex,gs,gsindex,shadowgs); - printk("CS: %04x DS: %04x ES: %04x\n", cs, ds, es); - -} - -void show_regs(struct pt_regs *regs) -{ - __show_regs(regs); - show_trace(&regs->rsp); -} - -/* - * Free current thread data structures etc.. - */ -void exit_thread(void) -{ - struct task_struct *me = current; - struct thread_struct *t = &me->thread; - if (me->thread.io_bitmap_ptr) { - struct tss_struct *tss = &per_cpu(init_tss, get_cpu()); - - kfree(t->io_bitmap_ptr); - t->io_bitmap_ptr = NULL; - /* - * Careful, clear this in the TSS too: - */ - memset(tss->io_bitmap, 0xff, t->io_bitmap_max); - t->io_bitmap_max = 0; - put_cpu(); - } -} - -void load_gs_index(unsigned gs) -{ - HYPERVISOR_set_segment_base(SEGBASE_GS_USER_SEL, gs); -} - -void flush_thread(void) -{ - struct task_struct *tsk = current; - struct thread_info *t = current_thread_info(); - - if (t->flags & _TIF_ABI_PENDING) - t->flags ^= (_TIF_ABI_PENDING | _TIF_IA32); - - tsk->thread.debugreg0 = 0; - tsk->thread.debugreg1 = 0; - tsk->thread.debugreg2 = 0; - tsk->thread.debugreg3 = 0; - tsk->thread.debugreg6 = 0; - tsk->thread.debugreg7 = 0; - memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array)); - /* - * Forget coprocessor state.. - */ - clear_fpu(tsk); - clear_used_math(); -} - -void release_thread(struct task_struct *dead_task) -{ - if (dead_task->mm) { - if (dead_task->mm->context.size) { - printk("WARNING: dead process %8s still has LDT? <%p/%d>\n", - dead_task->comm, - dead_task->mm->context.ldt, - dead_task->mm->context.size); - BUG(); - } - } -} - -static inline void set_32bit_tls(struct task_struct *t, int tls, u32 addr) -{ - struct user_desc ud = { - .base_addr = addr, - .limit = 0xfffff, - .contents = (3 << 3), /* user */ - .seg_32bit = 1, - .limit_in_pages = 1, - .useable = 1, - }; - struct n_desc_struct *desc = (void *)t->thread.tls_array; - desc += tls; - desc->a = LDT_entry_a(&ud); - desc->b = LDT_entry_b(&ud); -} - -static inline u32 read_32bit_tls(struct task_struct *t, int tls) -{ - struct desc_struct *desc = (void *)t->thread.tls_array; - desc += tls; - return desc->base0 | - (((u32)desc->base1) << 16) | - (((u32)desc->base2) << 24); -} - -/* - * This gets called before we allocate a new thread and copy - * the current task into it. - */ -void prepare_to_copy(struct task_struct *tsk) -{ - unlazy_fpu(tsk); -} - -int copy_thread(int nr, unsigned long clone_flags, unsigned long rsp, - unsigned long unused, - struct task_struct * p, struct pt_regs * regs) -{ - int err; - struct pt_regs * childregs; - struct task_struct *me = current; - - childregs = ((struct pt_regs *) (THREAD_SIZE + (unsigned long) p->thread_info)) - 1; - - *childregs = *regs; - - childregs->rax = 0; - childregs->rsp = rsp; - if (rsp == ~0UL) { - childregs->rsp = (unsigned long)childregs; - } - - p->thread.rsp = (unsigned long) childregs; - p->thread.rsp0 = (unsigned long) (childregs+1); - p->thread.userrsp = me->thread.userrsp; - - set_ti_thread_flag(p->thread_info, TIF_FORK); - - p->thread.fs = me->thread.fs; - p->thread.gs = me->thread.gs; - - asm("mov %%gs,%0" : "=m" (p->thread.gsindex)); - asm("mov %%fs,%0" : "=m" (p->thread.fsindex)); - asm("mov %%es,%0" : "=m" (p->thread.es)); - asm("mov %%ds,%0" : "=m" (p->thread.ds)); - - if (unlikely(me->thread.io_bitmap_ptr != NULL)) { - p->thread.io_bitmap_ptr = kmalloc(IO_BITMAP_BYTES, GFP_KERNEL); - if (!p->thread.io_bitmap_ptr) { - p->thread.io_bitmap_max = 0; - return -ENOMEM; - } - memcpy(p->thread.io_bitmap_ptr, me->thread.io_bitmap_ptr, IO_BITMAP_BYTES); - } - - /* - * Set a new TLS for the child thread? - */ - if (clone_flags & CLONE_SETTLS) { -#ifdef CONFIG_IA32_EMULATION - if (test_thread_flag(TIF_IA32)) - err = ia32_child_tls(p, childregs); - else -#endif - err = do_arch_prctl(p, ARCH_SET_FS, childregs->r8); - if (err) - goto out; - } - p->thread.io_pl = current->thread.io_pl; - - err = 0; -out: - if (err && p->thread.io_bitmap_ptr) { - kfree(p->thread.io_bitmap_ptr); - p->thread.io_bitmap_max = 0; - } - return err; -} - -/* - * This special macro can be used to load a debugging register - */ -#define loaddebug(thread,register) \ - HYPERVISOR_set_debugreg((register), \ - (thread->debugreg ## register)) - - -static inline void __save_init_fpu( struct task_struct *tsk ) -{ - asm volatile( "rex64 ; fxsave %0 ; fnclex" - : "=m" (tsk->thread.i387.fxsave)); - tsk->thread_info->status &= ~TS_USEDFPU; -} - -/* - * switch_to(x,y) should switch tasks from x to y. - * - * This could still be optimized: - * - fold all the options into a flag word and test it with a single test. - * - could test fs/gs bitsliced - */ -struct task_struct *__switch_to(struct task_struct *prev_p, struct task_struct *next_p) -{ - struct thread_struct *prev = &prev_p->thread, - *next = &next_p->thread; - int cpu = smp_processor_id(); - struct tss_struct *tss = &per_cpu(init_tss, cpu); - physdev_op_t iopl_op, iobmp_op; - multicall_entry_t _mcl[8], *mcl = _mcl; - - /* - * This is basically '__unlazy_fpu', except that we queue a - * multicall to indicate FPU task switch, rather than - * synchronously trapping to Xen. - */ - if (prev_p->thread_info->status & TS_USEDFPU) { - __save_init_fpu(prev_p); /* _not_ save_init_fpu() */ - mcl->op = __HYPERVISOR_fpu_taskswitch; - mcl->args[0] = 1; - mcl++; - } - - /* - * Reload esp0, LDT and the page table pointer: - */ - tss->rsp0 = next->rsp0; - mcl->op = __HYPERVISOR_stack_switch; - mcl->args[0] = __KERNEL_DS; - mcl->args[1] = tss->rsp0; - mcl++; - - /* - * Load the per-thread Thread-Local Storage descriptor. - * This is load_TLS(next, cpu) with multicalls. - */ -#define C(i) do { \ - if (unlikely(next->tls_array[i] != prev->tls_array[i])) { \ - mcl->op = __HYPERVISOR_update_descriptor; \ - mcl->args[0] = virt_to_machine( \ - &get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN + i]);\ - mcl->args[1] = next->tls_array[i]; \ - mcl++; \ - } \ -} while (0) - C(0); C(1); C(2); -#undef C - - if (unlikely(prev->io_pl != next->io_pl)) { - iopl_op.cmd = PHYSDEVOP_SET_IOPL; - iopl_op.u.set_iopl.iopl = (next->io_pl == 0) ? 1 : next->io_pl; - mcl->op = __HYPERVISOR_physdev_op; - mcl->args[0] = (unsigned long)&iopl_op; - mcl++; - } - - if (unlikely(prev->io_bitmap_ptr || next->io_bitmap_ptr)) { - iobmp_op.cmd = - PHYSDEVOP_SET_IOBITMAP; - iobmp_op.u.set_iobitmap.bitmap = - (char *)next->io_bitmap_ptr; - iobmp_op.u.set_iobitmap.nr_ports = - next->io_bitmap_ptr ? IO_BITMAP_BITS : 0; - mcl->op = __HYPERVISOR_physdev_op; - mcl->args[0] = (unsigned long)&iobmp_op; - mcl++; - } - - (void)HYPERVISOR_multicall(_mcl, mcl - _mcl); - /* - * Switch DS and ES. - * This won't pick up thread selector changes, but I guess that is ok. - */ - if (unlikely(next->es)) - loadsegment(es, next->es); - - if (unlikely(next->ds)) - loadsegment(ds, next->ds); - - /* - * Switch FS and GS. - */ - if (unlikely(next->fsindex)) - loadsegment(fs, next->fsindex); - - if (next->fs) - HYPERVISOR_set_segment_base(SEGBASE_FS, next->fs); - - if (unlikely(next->gsindex)) - load_gs_index(next->gsindex); - - if (next->gs) - HYPERVISOR_set_segment_base(SEGBASE_GS_USER, next->gs); - - /* - * Switch the PDA context. - */ - prev->userrsp = read_pda(oldrsp); - write_pda(oldrsp, next->userrsp); - write_pda(pcurrent, next_p); - write_pda(kernelstack, (unsigned long)next_p->thread_info + THREAD_SIZE - PDA_STACKOFFSET); - - /* - * Now maybe reload the debug registers - */ - if (unlikely(next->debugreg7)) { - loaddebug(next, 0); - loaddebug(next, 1); - loaddebug(next, 2); - loaddebug(next, 3); - /* no 4 and 5 */ - loaddebug(next, 6); - loaddebug(next, 7); - } - - return prev_p; -} - -/* - * sys_execve() executes a new program. - */ -asmlinkage -long sys_execve(char __user *name, char __user * __user *argv, - char __user * __user *envp, struct pt_regs regs) -{ - long error; - char * filename; - - filename = getname(name); - error = PTR_ERR(filename); - if (IS_ERR(filename)) - return error; - error = do_execve(filename, argv, envp, &regs); - if (error == 0) { - task_lock(current); - current->ptrace &= ~PT_DTRACE; - task_unlock(current); - } - putname(filename); - return error; -} - -void set_personality_64bit(void) -{ - /* inherit personality from parent */ - - /* Make sure to be in 64bit mode */ - clear_thread_flag(TIF_IA32); - - /* TBD: overwrites user setup. Should have two bits. - But 64bit processes have always behaved this way, - so it's not too bad. The main problem is just that - 32bit childs are affected again. */ - current->personality &= ~READ_IMPLIES_EXEC; -} - -asmlinkage long sys_fork(struct pt_regs *regs) -{ - return do_fork(SIGCHLD, regs->rsp, regs, 0, NULL, NULL); -} - -asmlinkage long sys_clone(unsigned long clone_flags, unsigned long newsp, void __user *parent_tid, void __user *child_tid, struct pt_regs *regs) -{ - if (!newsp) - newsp = regs->rsp; - return do_fork(clone_flags, newsp, regs, 0, parent_tid, child_tid); -} - -/* - * This is trivial, and on the face of it looks like it - * could equally well be done in user mode. - * - * Not so, for quite unobvious reasons - register pressure. - * In user mode vfork() cannot have a stack frame, and if - * done by calling the "clone()" system call directly, you - * do not have enough call-clobbered registers to hold all - * the information you need. - */ -asmlinkage long sys_vfork(struct pt_regs *regs) -{ - return do_fork(CLONE_VFORK | CLONE_VM | SIGCHLD, regs->rsp, regs, 0, - NULL, NULL); -} - -unsigned long get_wchan(struct task_struct *p) -{ - unsigned long stack; - u64 fp,rip; - int count = 0; - - if (!p || p == current || p->state==TASK_RUNNING) - return 0; - stack = (unsigned long)p->thread_info; - if (p->thread.rsp < stack || p->thread.rsp > stack+THREAD_SIZE) - return 0; - fp = *(u64 *)(p->thread.rsp); - do { - if (fp < (unsigned long)stack || fp > (unsigned long)stack+THREAD_SIZE) - return 0; - rip = *(u64 *)(fp+8); - if (!in_sched_functions(rip)) - return rip; - fp = *(u64 *)fp; - } while (count++ < 16); - return 0; -} - -long do_arch_prctl(struct task_struct *task, int code, unsigned long addr) -{ - int ret = 0; - int doit = task == current; - int cpu; - - switch (code) { - case ARCH_SET_GS: - if (addr >= TASK_SIZE) - return -EPERM; - cpu = get_cpu(); - /* handle small bases via the GDT because that's faster to - switch. */ - if (addr <= 0xffffffff) { - set_32bit_tls(task, GS_TLS, addr); - if (doit) { - load_TLS(&task->thread, cpu); - load_gs_index(GS_TLS_SEL); - } - task->thread.gsindex = GS_TLS_SEL; - task->thread.gs = 0; - } else { - task->thread.gsindex = 0; - task->thread.gs = addr; - if (doit) { - load_gs_index(0); - ret = HYPERVISOR_set_segment_base(SEGBASE_GS_USER, addr); - } - } - put_cpu(); - break; - case ARCH_SET_FS: - /* Not strictly needed for fs, but do it for symmetry - with gs */ - if (addr >= TASK_SIZE) - return -EPERM; - cpu = get_cpu(); - /* handle small bases via the GDT because that's faster to - switch. */ - if (addr <= 0xffffffff) { - set_32bit_tls(task, FS_TLS, addr); - if (doit) { - load_TLS(&task->thread, cpu); - asm volatile("mov %0,%%fs" :: "r" (FS_TLS_SEL)); - } - task->thread.fsindex = FS_TLS_SEL; - task->thread.fs = 0; - } else { - task->thread.fsindex = 0; - task->thread.fs = addr; - if (doit) { - /* set the selector to 0 to not confuse - __switch_to */ - asm volatile("mov %0,%%fs" :: "r" (0)); - ret = HYPERVISOR_set_segment_base(SEGBASE_FS, addr); - - } - } - put_cpu(); - break; - case ARCH_GET_FS: { - unsigned long base; - if (task->thread.fsindex == FS_TLS_SEL) - base = read_32bit_tls(task, FS_TLS); - else if (doit) { - rdmsrl(MSR_FS_BASE, base); - } else - base = task->thread.fs; - ret = put_user(base, (unsigned long __user *)addr); - break; - } - case ARCH_GET_GS: { - unsigned long base; - if (task->thread.gsindex == GS_TLS_SEL) - base = read_32bit_tls(task, GS_TLS); - else if (doit) { - rdmsrl(MSR_KERNEL_GS_BASE, base); - } else - base = task->thread.gs; - ret = put_user(base, (unsigned long __user *)addr); - break; - } - - default: - ret = -EINVAL; - break; - } - - return ret; -} - -long sys_arch_prctl(int code, unsigned long addr) -{ - return do_arch_prctl(current, code, addr); -} - -/* - * Capture the user space registers if the task is not running (in user space) - */ -int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs) -{ - struct pt_regs *pp, ptregs; - - pp = (struct pt_regs *)(tsk->thread.rsp0); - --pp; - - ptregs = *pp; - ptregs.cs &= 0xffff; - ptregs.ss &= 0xffff; - - elf_core_copy_regs(regs, &ptregs); - - boot_option_idle_override = 1; - return 1; -} - -unsigned long arch_align_stack(unsigned long sp) -{ - if (randomize_va_space) - sp -= get_random_int() % 8192; - return sp & ~0xf; -} - -#ifndef CONFIG_SMP -void _restore_vcpu(void) -{ -} -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/setup.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/setup.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,1472 +0,0 @@ -/* - * linux/arch/x86-64/kernel/setup.c - * - * Copyright (C) 1995 Linus Torvalds - * - * Nov 2001 Dave Jones <davej@xxxxxxx> - * Forked from i386 setup code. - * - * $Id$ - */ - -/* - * This file handles the architecture-dependent parts of initialization - */ - -#include <linux/errno.h> -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/stddef.h> -#include <linux/unistd.h> -#include <linux/ptrace.h> -#include <linux/slab.h> -#include <linux/user.h> -#include <linux/a.out.h> -#include <linux/tty.h> -#include <linux/ioport.h> -#include <linux/delay.h> -#include <linux/config.h> -#include <linux/init.h> -#include <linux/initrd.h> -#include <linux/highmem.h> -#include <linux/bootmem.h> -#include <linux/module.h> -#include <asm/processor.h> -#include <linux/console.h> -#include <linux/seq_file.h> -#include <linux/root_dev.h> -#include <linux/pci.h> -#include <linux/acpi.h> -#include <linux/kallsyms.h> -#include <linux/edd.h> -#include <asm/mtrr.h> -#include <asm/uaccess.h> -#include <asm/system.h> -#include <asm/io.h> -#include <asm/smp.h> -#include <asm/msr.h> -#include <asm/desc.h> -#include <video/edid.h> -#include <asm/e820.h> -#include <asm/dma.h> -#include <asm/mpspec.h> -#include <asm/mmu_context.h> -#include <asm/bootsetup.h> -#include <asm/proto.h> -#include <asm/setup.h> -#include <asm/mach_apic.h> -#include <asm/numa.h> -#ifdef CONFIG_XEN -#include <linux/percpu.h> -#include <asm-xen/xen-public/physdev.h> -#include "setup_arch_pre.h" -#include <asm/hypervisor.h> -#include <asm-xen/xen-public/nmi.h> -#include <asm-xen/features.h> -#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) -#define PFN_PHYS(x) ((x) << PAGE_SHIFT) -#define end_pfn_map end_pfn -#include <asm/mach-xen/setup_arch_post.h> - -extern unsigned long start_pfn; -extern struct edid_info edid_info; - -shared_info_t *HYPERVISOR_shared_info = (shared_info_t *)empty_zero_page; -EXPORT_SYMBOL(HYPERVISOR_shared_info); - -extern char hypercall_page[PAGE_SIZE]; -EXPORT_SYMBOL(hypercall_page); - -/* Allows setting of maximum possible memory size */ -unsigned long xen_override_max_pfn; - -unsigned long *phys_to_machine_mapping; -unsigned long *pfn_to_mfn_frame_list_list, *pfn_to_mfn_frame_list[512]; - -EXPORT_SYMBOL(phys_to_machine_mapping); - -DEFINE_PER_CPU(multicall_entry_t, multicall_list[8]); -DEFINE_PER_CPU(int, nr_multicall_ents); - -/* Raw start-of-day parameters from the hypervisor. */ -start_info_t *xen_start_info; -EXPORT_SYMBOL(xen_start_info); -#endif - -/* - * Machine setup.. - */ - -struct cpuinfo_x86 boot_cpu_data; - -unsigned long mmu_cr4_features; - -int acpi_disabled; -EXPORT_SYMBOL(acpi_disabled); -#ifdef CONFIG_ACPI_BOOT -extern int __initdata acpi_ht; -extern acpi_interrupt_flags acpi_sci_flags; -int __initdata acpi_force = 0; -#endif - -int acpi_numa __initdata; - -/* Boot loader ID as an integer, for the benefit of proc_dointvec */ -int bootloader_type; - -unsigned long saved_video_mode; - -#ifdef CONFIG_SWIOTLB -int swiotlb; -EXPORT_SYMBOL(swiotlb); -#endif - -/* - * Setup options - */ -struct drive_info_struct { char dummy[32]; } drive_info; -struct screen_info screen_info; -struct sys_desc_table_struct { - unsigned short length; - unsigned char table[0]; -}; - -struct edid_info edid_info; -struct e820map e820; - -extern int root_mountflags; -extern char _text, _etext, _edata, _end; - -char command_line[COMMAND_LINE_SIZE]; - -struct resource standard_io_resources[] = { - { .name = "dma1", .start = 0x00, .end = 0x1f, - .flags = IORESOURCE_BUSY | IORESOURCE_IO }, - { .name = "pic1", .start = 0x20, .end = 0x21, - .flags = IORESOURCE_BUSY | IORESOURCE_IO }, - { .name = "timer0", .start = 0x40, .end = 0x43, - .flags = IORESOURCE_BUSY | IORESOURCE_IO }, - { .name = "timer1", .start = 0x50, .end = 0x53, - .flags = IORESOURCE_BUSY | IORESOURCE_IO }, - { .name = "keyboard", .start = 0x60, .end = 0x6f, - .flags = IORESOURCE_BUSY | IORESOURCE_IO }, - { .name = "dma page reg", .start = 0x80, .end = 0x8f, - .flags = IORESOURCE_BUSY | IORESOURCE_IO }, - { .name = "pic2", .start = 0xa0, .end = 0xa1, - .flags = IORESOURCE_BUSY | IORESOURCE_IO }, - { .name = "dma2", .start = 0xc0, .end = 0xdf, - .flags = IORESOURCE_BUSY | IORESOURCE_IO }, - { .name = "fpu", .start = 0xf0, .end = 0xff, - .flags = IORESOURCE_BUSY | IORESOURCE_IO } -}; - -#define STANDARD_IO_RESOURCES \ - (sizeof standard_io_resources / sizeof standard_io_resources[0]) - -#define IORESOURCE_RAM (IORESOURCE_BUSY | IORESOURCE_MEM) - -struct resource data_resource = { - .name = "Kernel data", - .start = 0, - .end = 0, - .flags = IORESOURCE_RAM, -}; -struct resource code_resource = { - .name = "Kernel code", - .start = 0, - .end = 0, - .flags = IORESOURCE_RAM, -}; - -#define IORESOURCE_ROM (IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM) - -#if defined(CONFIG_XEN_PRIVILEGED_GUEST) || !defined(CONFIG_XEN) -static struct resource system_rom_resource = { - .name = "System ROM", - .start = 0xf0000, - .end = 0xfffff, - .flags = IORESOURCE_ROM, -}; - -static struct resource extension_rom_resource = { - .name = "Extension ROM", - .start = 0xe0000, - .end = 0xeffff, - .flags = IORESOURCE_ROM, -}; - -static struct resource adapter_rom_resources[] = { - { .name = "Adapter ROM", .start = 0xc8000, .end = 0, - .flags = IORESOURCE_ROM }, - { .name = "Adapter ROM", .start = 0, .end = 0, - .flags = IORESOURCE_ROM }, - { .name = "Adapter ROM", .start = 0, .end = 0, - .flags = IORESOURCE_ROM }, - { .name = "Adapter ROM", .start = 0, .end = 0, - .flags = IORESOURCE_ROM }, - { .name = "Adapter ROM", .start = 0, .end = 0, - .flags = IORESOURCE_ROM }, - { .name = "Adapter ROM", .start = 0, .end = 0, - .flags = IORESOURCE_ROM } -}; -#endif - -#define ADAPTER_ROM_RESOURCES \ - (sizeof adapter_rom_resources / sizeof adapter_rom_resources[0]) - -#if defined(CONFIG_XEN_PRIVILEGED_GUEST) || !defined(CONFIG_XEN) -static struct resource video_rom_resource = { - .name = "Video ROM", - .start = 0xc0000, - .end = 0xc7fff, - .flags = IORESOURCE_ROM, -}; -#endif - -static struct resource video_ram_resource = { - .name = "Video RAM area", - .start = 0xa0000, - .end = 0xbffff, - .flags = IORESOURCE_RAM, -}; - -#if defined(CONFIG_XEN_PRIVILEGED_GUEST) || !defined(CONFIG_XEN) -#define romsignature(x) (*(unsigned short *)(x) == 0xaa55) - -static int __init romchecksum(unsigned char *rom, unsigned long length) -{ - unsigned char *p, sum = 0; - - for (p = rom; p < rom + length; p++) - sum += *p; - return sum == 0; -} - -static void __init probe_roms(void) -{ - unsigned long start, length, upper; - unsigned char *rom; - int i; - - /* video rom */ - upper = adapter_rom_resources[0].start; - for (start = video_rom_resource.start; start < upper; start += 2048) { - rom = isa_bus_to_virt(start); - if (!romsignature(rom)) - continue; - - video_rom_resource.start = start; - - /* 0 < length <= 0x7f * 512, historically */ - length = rom[2] * 512; - - /* if checksum okay, trust length byte */ - if (length && romchecksum(rom, length)) - video_rom_resource.end = start + length - 1; - - request_resource(&iomem_resource, &video_rom_resource); - break; - } - - start = (video_rom_resource.end + 1 + 2047) & ~2047UL; - if (start < upper) - start = upper; - - /* system rom */ - request_resource(&iomem_resource, &system_rom_resource); - upper = system_rom_resource.start; - - /* check for extension rom (ignore length byte!) */ - rom = isa_bus_to_virt(extension_rom_resource.start); - if (romsignature(rom)) { - length = extension_rom_resource.end - extension_rom_resource.start + 1; - if (romchecksum(rom, length)) { - request_resource(&iomem_resource, &extension_rom_resource); - upper = extension_rom_resource.start; - } - } - - /* check for adapter roms on 2k boundaries */ - for (i = 0; i < ADAPTER_ROM_RESOURCES && start < upper; start += 2048) { - rom = isa_bus_to_virt(start); - if (!romsignature(rom)) - continue; - - /* 0 < length <= 0x7f * 512, historically */ - length = rom[2] * 512; - - /* but accept any length that fits if checksum okay */ - if (!length || start + length > upper || !romchecksum(rom, length)) - continue; - - adapter_rom_resources[i].start = start; - adapter_rom_resources[i].end = start + length - 1; - request_resource(&iomem_resource, &adapter_rom_resources[i]); - - start = adapter_rom_resources[i++].end & ~2047UL; - } -} -#endif - -static __init void parse_cmdline_early (char ** cmdline_p) -{ - char c = ' ', *to = command_line, *from = COMMAND_LINE; - int len = 0; - - /* Save unparsed command line copy for /proc/cmdline */ -#ifdef CONFIG_XEN - int max_cmdline; - - if ((max_cmdline = MAX_GUEST_CMDLINE) > COMMAND_LINE_SIZE) - max_cmdline = COMMAND_LINE_SIZE; - memcpy(saved_command_line, xen_start_info->cmd_line, max_cmdline); - saved_command_line[max_cmdline-1] = '\0'; -#else - memcpy(saved_command_line, COMMAND_LINE, COMMAND_LINE_SIZE); - saved_command_line[COMMAND_LINE_SIZE-1] = '\0'; -#endif - - for (;;) { - if (c != ' ') - goto next_char; - -#ifdef CONFIG_SMP - /* - * If the BIOS enumerates physical processors before logical, - * maxcpus=N at enumeration-time can be used to disable HT. - */ - else if (!memcmp(from, "maxcpus=", 8)) { - extern unsigned int maxcpus; - - maxcpus = simple_strtoul(from + 8, NULL, 0); - } -#endif -#ifdef CONFIG_ACPI_BOOT - /* "acpi=off" disables both ACPI table parsing and interpreter init */ - if (!memcmp(from, "acpi=off", 8)) - disable_acpi(); - - if (!memcmp(from, "acpi=force", 10)) { - /* add later when we do DMI horrors: */ - acpi_force = 1; - acpi_disabled = 0; - } - - /* acpi=ht just means: do ACPI MADT parsing - at bootup, but don't enable the full ACPI interpreter */ - if (!memcmp(from, "acpi=ht", 7)) { - if (!acpi_force) - disable_acpi(); - acpi_ht = 1; - } - else if (!memcmp(from, "pci=noacpi", 10)) - acpi_disable_pci(); - else if (!memcmp(from, "acpi=noirq", 10)) - acpi_noirq_set(); - - else if (!memcmp(from, "acpi_sci=edge", 13)) - acpi_sci_flags.trigger = 1; - else if (!memcmp(from, "acpi_sci=level", 14)) - acpi_sci_flags.trigger = 3; - else if (!memcmp(from, "acpi_sci=high", 13)) - acpi_sci_flags.polarity = 1; - else if (!memcmp(from, "acpi_sci=low", 12)) - acpi_sci_flags.polarity = 3; - - /* acpi=strict disables out-of-spec workarounds */ - else if (!memcmp(from, "acpi=strict", 11)) { - acpi_strict = 1; - } -#ifdef CONFIG_X86_IO_APIC - else if (!memcmp(from, "acpi_skip_timer_override", 24)) - acpi_skip_timer_override = 1; -#endif -#endif - -#ifndef CONFIG_XEN - if (!memcmp(from, "nolapic", 7) || - !memcmp(from, "disableapic", 11)) - disable_apic = 1; - - if (!memcmp(from, "noapic", 6)) - skip_ioapic_setup = 1; - - if (!memcmp(from, "apic", 4)) { - skip_ioapic_setup = 0; - ioapic_force = 1; - } -#endif - - if (!memcmp(from, "mem=", 4)) - parse_memopt(from+4, &from); - -#ifdef CONFIG_DISCONTIGMEM - if (!memcmp(from, "numa=", 5)) - numa_setup(from+5); -#endif - -#ifdef CONFIG_GART_IOMMU - if (!memcmp(from,"iommu=",6)) { - iommu_setup(from+6); - } -#endif - - if (!memcmp(from,"oops=panic", 10)) - panic_on_oops = 1; - - if (!memcmp(from, "noexec=", 7)) - nonx_setup(from + 7); - - next_char: - c = *(from++); - if (!c) - break; - if (COMMAND_LINE_SIZE <= ++len) - break; - *(to++) = c; - } - *to = '\0'; - *cmdline_p = command_line; -} - -#ifndef CONFIG_DISCONTIGMEM -#ifdef CONFIG_XEN -static void __init contig_initmem_init(void) -{ - unsigned long bootmap_size = init_bootmem(start_pfn, end_pfn); - free_bootmem(0, xen_start_info->nr_pages << PAGE_SHIFT); - reserve_bootmem(HIGH_MEMORY, - (PFN_PHYS(start_pfn) + bootmap_size + PAGE_SIZE-1) - - HIGH_MEMORY); -} -#else -static void __init contig_initmem_init(void) -{ - unsigned long bootmap_size, bootmap; - bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT; - bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size); - if (bootmap == -1L) - panic("Cannot find bootmem map of size %ld\n",bootmap_size); - bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn); - e820_bootmem_free(&contig_page_data, 0, end_pfn << PAGE_SHIFT); - reserve_bootmem(bootmap, bootmap_size); -} -#endif /* !CONFIG_XEN */ -#endif - -/* Use inline assembly to define this because the nops are defined - as inline assembly strings in the include files and we cannot - get them easily into strings. */ -asm("\t.data\nk8nops: " - K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6 - K8_NOP7 K8_NOP8); - -extern unsigned char k8nops[]; -static unsigned char *k8_nops[ASM_NOP_MAX+1] = { - NULL, - k8nops, - k8nops + 1, - k8nops + 1 + 2, - k8nops + 1 + 2 + 3, - k8nops + 1 + 2 + 3 + 4, - k8nops + 1 + 2 + 3 + 4 + 5, - k8nops + 1 + 2 + 3 + 4 + 5 + 6, - k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7, -}; - -/* Replace instructions with better alternatives for this CPU type. - - This runs before SMP is initialized to avoid SMP problems with - self modifying code. This implies that assymetric systems where - APs have less capabilities than the boot processor are not handled. - In this case boot with "noreplacement". */ -void apply_alternatives(void *start, void *end) -{ - struct alt_instr *a; - int diff, i, k; - for (a = start; (void *)a < end; a++) { - if (!boot_cpu_has(a->cpuid)) - continue; - - BUG_ON(a->replacementlen > a->instrlen); - __inline_memcpy(a->instr, a->replacement, a->replacementlen); - diff = a->instrlen - a->replacementlen; - - /* Pad the rest with nops */ - for (i = a->replacementlen; diff > 0; diff -= k, i += k) { - k = diff; - if (k > ASM_NOP_MAX) - k = ASM_NOP_MAX; - __inline_memcpy(a->instr + i, k8_nops[k], k); - } - } -} - -static int no_replacement __initdata = 0; - -void __init alternative_instructions(void) -{ - extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; - if (no_replacement) - return; - apply_alternatives(__alt_instructions, __alt_instructions_end); -} - -static int __init noreplacement_setup(char *s) -{ - no_replacement = 1; - return 0; -} - -__setup("noreplacement", noreplacement_setup); - -#if defined(CONFIG_EDD) || defined(CONFIG_EDD_MODULE) -struct edd edd; -#ifdef CONFIG_EDD_MODULE -EXPORT_SYMBOL(edd); -#endif -/** - * copy_edd() - Copy the BIOS EDD information - * from boot_params into a safe place. - * - */ -static inline void copy_edd(void) -{ - memcpy(edd.mbr_signature, EDD_MBR_SIGNATURE, sizeof(edd.mbr_signature)); - memcpy(edd.edd_info, EDD_BUF, sizeof(edd.edd_info)); - edd.mbr_signature_nr = EDD_MBR_SIG_NR; - edd.edd_info_nr = EDD_NR; -} -#else -static inline void copy_edd(void) -{ -} -#endif - -#ifndef CONFIG_XEN -#define EBDA_ADDR_POINTER 0x40E -static void __init reserve_ebda_region(void) -{ - unsigned int addr; - /** - * there is a real-mode segmented pointer pointing to the - * 4K EBDA area at 0x40E - */ - addr = *(unsigned short *)phys_to_virt(EBDA_ADDR_POINTER); - addr <<= 4; - if (addr) - reserve_bootmem_generic(addr, PAGE_SIZE); -} -#endif - -void __init setup_arch(char **cmdline_p) -{ - unsigned long kernel_end; - -#ifdef CONFIG_XEN - ROOT_DEV = MKDEV(RAMDISK_MAJOR,0); - drive_info = DRIVE_INFO; - kernel_end = 0; /* dummy */ -#ifdef CONFIG_XEN_PHYSDEV_ACCESS - screen_info = SCREEN_INFO; - - /* This is drawn from a dump from vgacon:startup in standard Linux. */ - screen_info.orig_video_mode = 3; - screen_info.orig_video_isVGA = 1; - screen_info.orig_video_lines = 25; - screen_info.orig_video_cols = 80; - screen_info.orig_video_ega_bx = 3; - screen_info.orig_video_points = 16; -#endif - edid_info = EDID_INFO; - saved_video_mode = SAVED_VIDEO_MODE; - bootloader_type = LOADER_TYPE; - -#ifdef CONFIG_BLK_DEV_RAM - rd_image_start = RAMDISK_FLAGS & RAMDISK_IMAGE_START_MASK; - rd_prompt = ((RAMDISK_FLAGS & RAMDISK_PROMPT_FLAG) != 0); - rd_doload = ((RAMDISK_FLAGS & RAMDISK_LOAD_FLAG) != 0); - - -#endif - - setup_xen_features(); - - HYPERVISOR_vm_assist(VMASST_CMD_enable, - VMASST_TYPE_writable_pagetables); - - ARCH_SETUP -#else - ROOT_DEV = old_decode_dev(ORIG_ROOT_DEV); - drive_info = DRIVE_INFO; - screen_info = SCREEN_INFO; - edid_info = EDID_INFO; - saved_video_mode = SAVED_VIDEO_MODE; - bootloader_type = LOADER_TYPE; - -#ifdef CONFIG_BLK_DEV_RAM - rd_image_start = RAMDISK_FLAGS & RAMDISK_IMAGE_START_MASK; - rd_prompt = ((RAMDISK_FLAGS & RAMDISK_PROMPT_FLAG) != 0); - rd_doload = ((RAMDISK_FLAGS & RAMDISK_LOAD_FLAG) != 0); -#endif - setup_memory_region(); - copy_edd(); -#endif /* !CONFIG_XEN */ - - if (!MOUNT_ROOT_RDONLY) - root_mountflags &= ~MS_RDONLY; - init_mm.start_code = (unsigned long) &_text; - init_mm.end_code = (unsigned long) &_etext; - init_mm.end_data = (unsigned long) &_edata; -#ifdef CONFIG_XEN - init_mm.brk = start_pfn << PAGE_SHIFT; -#else - init_mm.brk = (unsigned long) &_end; - - code_resource.start = virt_to_phys(&_text); - code_resource.end = virt_to_phys(&_etext)-1; - data_resource.start = virt_to_phys(&_etext); - data_resource.end = virt_to_phys(&_edata)-1; -#endif - - parse_cmdline_early(cmdline_p); - - early_identify_cpu(&boot_cpu_data); - - /* - * partially used pages are not usable - thus - * we are rounding upwards: - */ - end_pfn = e820_end_of_ram(); - - check_efer(); - - init_memory_mapping(0, (end_pfn_map << PAGE_SHIFT)); - -#ifdef CONFIG_ACPI_NUMA - /* - * Parse SRAT to discover nodes. - */ - acpi_numa_init(); -#endif - -#ifdef CONFIG_DISCONTIGMEM - numa_initmem_init(0, end_pfn); -#else - contig_initmem_init(); -#endif - -#ifndef CONFIG_XEN - /* Reserve direct mapping */ - reserve_bootmem_generic(table_start << PAGE_SHIFT, - (table_end - table_start) << PAGE_SHIFT); - - /* reserve kernel */ - kernel_end = round_up(__pa_symbol(&_end),PAGE_SIZE); - reserve_bootmem_generic(HIGH_MEMORY, kernel_end - HIGH_MEMORY); - - /* - * reserve physical page 0 - it's a special BIOS page on many boxes, - * enabling clean reboots, SMP operation, laptop functions. - */ - reserve_bootmem_generic(0, PAGE_SIZE); - - /* reserve ebda region */ - reserve_ebda_region(); -#endif - -#ifdef CONFIG_SMP - /* - * But first pinch a few for the stack/trampoline stuff - * FIXME: Don't need the extra page at 4K, but need to fix - * trampoline before removing it. (see the GDT stuff) - */ - reserve_bootmem_generic(PAGE_SIZE, PAGE_SIZE); - - /* Reserve SMP trampoline */ - reserve_bootmem_generic(SMP_TRAMPOLINE_BASE, PAGE_SIZE); -#endif - -#ifdef CONFIG_ACPI_SLEEP - /* - * Reserve low memory region for sleep support. - */ - acpi_reserve_bootmem(); -#endif -#ifdef CONFIG_XEN -#ifdef CONFIG_BLK_DEV_INITRD - if (xen_start_info->mod_start) { - if (INITRD_START + INITRD_SIZE <= (end_pfn << PAGE_SHIFT)) { - /*reserve_bootmem_generic(INITRD_START, INITRD_SIZE);*/ - initrd_start = INITRD_START + PAGE_OFFSET; - initrd_end = initrd_start+INITRD_SIZE; - initrd_below_start_ok = 1; - } else { - printk(KERN_ERR "initrd extends beyond end of memory " - "(0x%08lx > 0x%08lx)\ndisabling initrd\n", - (unsigned long)(INITRD_START + INITRD_SIZE), - (unsigned long)(end_pfn << PAGE_SHIFT)); - initrd_start = 0; - } - } -#endif -#else /* CONFIG_XEN */ -#ifdef CONFIG_BLK_DEV_INITRD - if (LOADER_TYPE && INITRD_START) { - if (INITRD_START + INITRD_SIZE <= (end_pfn << PAGE_SHIFT)) { - reserve_bootmem_generic(INITRD_START, INITRD_SIZE); - initrd_start = - INITRD_START ? INITRD_START + PAGE_OFFSET : 0; - initrd_end = initrd_start+INITRD_SIZE; - } - else { - printk(KERN_ERR "initrd extends beyond end of memory " - "(0x%08lx > 0x%08lx)\ndisabling initrd\n", - (unsigned long)(INITRD_START + INITRD_SIZE), - (unsigned long)(end_pfn << PAGE_SHIFT)); - initrd_start = 0; - } - } -#endif -#endif /* !CONFIG_XEN */ - paging_init(); -#ifdef CONFIG_X86_LOCAL_APIC - /* - * Find and reserve possible boot-time SMP configuration: - */ - find_smp_config(); -#endif -#ifdef CONFIG_XEN - { - int i, j, k, fpp; - unsigned long va; - - /* Make sure we have a large enough P->M table. */ - phys_to_machine_mapping = alloc_bootmem( - end_pfn * sizeof(unsigned long)); - memset(phys_to_machine_mapping, ~0, - end_pfn * sizeof(unsigned long)); - memcpy(phys_to_machine_mapping, - (unsigned long *)xen_start_info->mfn_list, - xen_start_info->nr_pages * sizeof(unsigned long)); - free_bootmem( - __pa(xen_start_info->mfn_list), - PFN_PHYS(PFN_UP(xen_start_info->nr_pages * - sizeof(unsigned long)))); - - /* 'Initial mapping' of old p2m table must be destroyed. */ - for (va = xen_start_info->mfn_list; - va < (xen_start_info->mfn_list + - (xen_start_info->nr_pages*sizeof(unsigned long))); - va += PAGE_SIZE) { - HYPERVISOR_update_va_mapping(va, __pte_ma(0), 0); - } - - /* 'Initial mapping' of initrd must be destroyed. */ - for (va = xen_start_info->mod_start; - va < (xen_start_info->mod_start+xen_start_info->mod_len); - va += PAGE_SIZE) { - HYPERVISOR_update_va_mapping(va, __pte_ma(0), 0); - } - - /* - * Initialise the list of the frames that specify the list of - * frames that make up the p2m table. Used by save/restore - */ - pfn_to_mfn_frame_list_list = alloc_bootmem(PAGE_SIZE); - HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list = - virt_to_mfn(pfn_to_mfn_frame_list_list); - - fpp = PAGE_SIZE/sizeof(unsigned long); - for ( i=0, j=0, k=-1; i< end_pfn; i+=fpp, j++ ) - { - if ( (j % fpp) == 0 ) - { - k++; - BUG_ON(k>=fpp); - pfn_to_mfn_frame_list[k] = alloc_bootmem(PAGE_SIZE); - pfn_to_mfn_frame_list_list[k] = - virt_to_mfn(pfn_to_mfn_frame_list[k]); - j=0; - } - pfn_to_mfn_frame_list[k][j] = - virt_to_mfn(&phys_to_machine_mapping[i]); - } - HYPERVISOR_shared_info->arch.max_pfn = end_pfn; - - } - - if ( ! (xen_start_info->flags & SIF_INITDOMAIN)) - { - acpi_disabled = 1; -#ifdef CONFIG_ACPI_BOOT - acpi_ht = 0; -#endif - } -#endif - -#ifndef CONFIG_XEN - check_ioapic(); -#endif - -#ifdef CONFIG_ACPI_BOOT - /* - * Initialize the ACPI boot-time table parser (gets the RSDP and SDT). - * Call this early for SRAT node setup. - */ - acpi_boot_table_init(); - - /* - * Read APIC and some other early information from ACPI tables. - */ - acpi_boot_init(); -#endif - -#ifdef CONFIG_X86_LOCAL_APIC - /* - * get boot-time SMP configuration: - */ - if (smp_found_config) - get_smp_config(); -#ifndef CONFIG_XEN - init_apic_mappings(); -#endif -#endif - -#if defined(CONFIG_XEN_PRIVILEGED_GUEST) || !defined(CONFIG_XEN) - /* - * Request address space for all standard RAM and ROM resources - * and also for regions reported as reserved by the e820. - */ - probe_roms(); - e820_reserve_resources(); -#endif - - request_resource(&iomem_resource, &video_ram_resource); - - { - unsigned i; - /* request I/O space for devices used on all i[345]86 PCs */ - for (i = 0; i < STANDARD_IO_RESOURCES; i++) - request_resource(&ioport_resource, &standard_io_resources[i]); - } - - e820_setup_gap(); - -#ifdef CONFIG_GART_IOMMU - iommu_hole_init(); -#endif - -#ifdef CONFIG_XEN - { - physdev_op_t op; - - op.cmd = PHYSDEVOP_SET_IOPL; - op.u.set_iopl.iopl = 1; - HYPERVISOR_physdev_op(&op); - - if (xen_start_info->flags & SIF_INITDOMAIN) { - if (!(xen_start_info->flags & SIF_PRIVILEGED)) - panic("Xen granted us console access " - "but not privileged status"); - -#ifdef CONFIG_VT -#if defined(CONFIG_VGA_CONSOLE) - conswitchp = &vga_con; -#elif defined(CONFIG_DUMMY_CONSOLE) - conswitchp = &dummy_con; -#endif -#endif - } else { -#ifdef CONFIG_XEN_PRIVILEGED_GUEST - extern const struct consw xennull_con; - extern int console_use_vt; -#if defined(CONFIG_VGA_CONSOLE) - /* disable VGA driver */ - ORIG_VIDEO_ISVGA = VIDEO_TYPE_VLFB; -#endif - conswitchp = &xennull_con; - console_use_vt = 0; -#endif - } - } -#else /* CONFIG_XEN */ - -#ifdef CONFIG_VT -#if defined(CONFIG_VGA_CONSOLE) - conswitchp = &vga_con; -#elif defined(CONFIG_DUMMY_CONSOLE) - conswitchp = &dummy_con; -#endif -#endif - -#endif /* !CONFIG_XEN */ -} - -static int __init get_model_name(struct cpuinfo_x86 *c) -{ - unsigned int *v; - - if (c->extended_cpuid_level < 0x80000004) - return 0; - - v = (unsigned int *) c->x86_model_id; - cpuid(0x80000002, &v[0], &v[1], &v[2], &v[3]); - cpuid(0x80000003, &v[4], &v[5], &v[6], &v[7]); - cpuid(0x80000004, &v[8], &v[9], &v[10], &v[11]); - c->x86_model_id[48] = 0; - return 1; -} - - -static void __init display_cacheinfo(struct cpuinfo_x86 *c) -{ - unsigned int n, dummy, eax, ebx, ecx, edx; - - n = c->extended_cpuid_level; - - if (n >= 0x80000005) { - cpuid(0x80000005, &dummy, &ebx, &ecx, &edx); - printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), D cache %dK (%d bytes/line)\n", - edx>>24, edx&0xFF, ecx>>24, ecx&0xFF); - c->x86_cache_size=(ecx>>24)+(edx>>24); - /* On K8 L1 TLB is inclusive, so don't count it */ - c->x86_tlbsize = 0; - } - - if (n >= 0x80000006) { - cpuid(0x80000006, &dummy, &ebx, &ecx, &edx); - ecx = cpuid_ecx(0x80000006); - c->x86_cache_size = ecx >> 16; - c->x86_tlbsize += ((ebx >> 16) & 0xfff) + (ebx & 0xfff); - - printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n", - c->x86_cache_size, ecx & 0xFF); - } - - if (n >= 0x80000007) - cpuid(0x80000007, &dummy, &dummy, &dummy, &c->x86_power); - if (n >= 0x80000008) { - cpuid(0x80000008, &eax, &dummy, &dummy, &dummy); - c->x86_virt_bits = (eax >> 8) & 0xff; - c->x86_phys_bits = eax & 0xff; - } -} - -/* - * On a AMD dual core setup the lower bits of the APIC id distingush the cores. - * Assumes number of cores is a power of two. - */ -static void __init amd_detect_cmp(struct cpuinfo_x86 *c) -{ -#ifdef CONFIG_SMP - int cpu = smp_processor_id(); - int node = 0; - unsigned bits; - if (c->x86_num_cores == 1) - return; - - bits = 0; - while ((1 << bits) < c->x86_num_cores) - bits++; - - /* Low order bits define the core id (index of core in socket) */ - cpu_core_id[cpu] = phys_proc_id[cpu] & ((1 << bits)-1); - /* Convert the APIC ID into the socket ID */ - phys_proc_id[cpu] >>= bits; - -#ifdef CONFIG_NUMA - /* When an ACPI SRAT table is available use the mappings from SRAT - instead. */ - if (acpi_numa <= 0) { - node = phys_proc_id[cpu]; - if (!node_online(node)) - node = first_node(node_online_map); - cpu_to_node[cpu] = node; - } else { - node = cpu_to_node[cpu]; - } -#endif - - printk(KERN_INFO "CPU %d(%d) -> Node %d -> Core %d\n", - cpu, c->x86_num_cores, node, cpu_core_id[cpu]); -#endif -} - -static int __init init_amd(struct cpuinfo_x86 *c) -{ - int r; - int level; - - /* Bit 31 in normal CPUID used for nonstandard 3DNow ID; - 3DNow is IDd by bit 31 in extended CPUID (1*32+31) anyway */ - clear_bit(0*32+31, &c->x86_capability); - - /* C-stepping K8? */ - level = cpuid_eax(1); - if ((level >= 0x0f48 && level < 0x0f50) || level >= 0x0f58) - set_bit(X86_FEATURE_K8_C, &c->x86_capability); - - r = get_model_name(c); - if (!r) { - switch (c->x86) { - case 15: - /* Should distinguish Models here, but this is only - a fallback anyways. */ - strcpy(c->x86_model_id, "Hammer"); - break; - } - } - display_cacheinfo(c); - - if (c->extended_cpuid_level >= 0x80000008) { - c->x86_num_cores = (cpuid_ecx(0x80000008) & 0xff) + 1; - if (c->x86_num_cores & (c->x86_num_cores - 1)) - c->x86_num_cores = 1; - - amd_detect_cmp(c); - } - - return r; -} - -static void __init detect_ht(struct cpuinfo_x86 *c) -{ -#ifdef CONFIG_SMP - u32 eax, ebx, ecx, edx; - int index_msb, tmp; - int cpu = smp_processor_id(); - - if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY)) - return; - - cpuid(1, &eax, &ebx, &ecx, &edx); - smp_num_siblings = (ebx & 0xff0000) >> 16; - - if (smp_num_siblings == 1) { - printk(KERN_INFO "CPU: Hyper-Threading is disabled\n"); - } else if (smp_num_siblings > 1) { - index_msb = 31; - /* - * At this point we only support two siblings per - * processor package. - */ - if (smp_num_siblings > NR_CPUS) { - printk(KERN_WARNING "CPU: Unsupported number of the siblings %d", smp_num_siblings); - smp_num_siblings = 1; - return; - } - tmp = smp_num_siblings; - while ((tmp & 0x80000000 ) == 0) { - tmp <<=1 ; - index_msb--; - } - if (smp_num_siblings & (smp_num_siblings - 1)) - index_msb++; - phys_proc_id[cpu] = phys_pkg_id(index_msb); - - printk(KERN_INFO "CPU: Physical Processor ID: %d\n", - phys_proc_id[cpu]); - - smp_num_siblings = smp_num_siblings / c->x86_num_cores; - - tmp = smp_num_siblings; - index_msb = 31; - while ((tmp & 0x80000000) == 0) { - tmp <<=1 ; - index_msb--; - } - if (smp_num_siblings & (smp_num_siblings - 1)) - index_msb++; - - cpu_core_id[cpu] = phys_pkg_id(index_msb); - - if (c->x86_num_cores > 1) - printk(KERN_INFO "CPU: Processor Core ID: %d\n", - cpu_core_id[cpu]); - } -#endif -} - -/* - * find out the number of processor cores on the die - */ -static int __init intel_num_cpu_cores(struct cpuinfo_x86 *c) -{ - unsigned int eax; - - if (c->cpuid_level < 4) - return 1; - - __asm__("cpuid" - : "=a" (eax) - : "0" (4), "c" (0) - : "bx", "dx"); - - if (eax & 0x1f) - return ((eax >> 26) + 1); - else - return 1; -} - -static void __init init_intel(struct cpuinfo_x86 *c) -{ - /* Cache sizes */ - unsigned n; - - init_intel_cacheinfo(c); - n = c->extended_cpuid_level; - if (n >= 0x80000008) { - unsigned eax = cpuid_eax(0x80000008); - c->x86_virt_bits = (eax >> 8) & 0xff; - c->x86_phys_bits = eax & 0xff; - } - - if (c->x86 == 15) - c->x86_cache_alignment = c->x86_clflush_size * 2; - if (c->x86 >= 15) - set_bit(X86_FEATURE_CONSTANT_TSC, &c->x86_capability); - c->x86_num_cores = intel_num_cpu_cores(c); -} - -void __init get_cpu_vendor(struct cpuinfo_x86 *c) -{ - char *v = c->x86_vendor_id; - - if (!strcmp(v, "AuthenticAMD")) - c->x86_vendor = X86_VENDOR_AMD; - else if (!strcmp(v, "GenuineIntel")) - c->x86_vendor = X86_VENDOR_INTEL; - else - c->x86_vendor = X86_VENDOR_UNKNOWN; -} - -struct cpu_model_info { - int vendor; - int family; - char *model_names[16]; -}; - -/* Do some early cpuid on the boot CPU to get some parameter that are - needed before check_bugs. Everything advanced is in identify_cpu - below. */ -void __init early_identify_cpu(struct cpuinfo_x86 *c) -{ - u32 tfms; - - c->loops_per_jiffy = loops_per_jiffy; - c->x86_cache_size = -1; - c->x86_vendor = X86_VENDOR_UNKNOWN; - c->x86_model = c->x86_mask = 0; /* So far unknown... */ - c->x86_vendor_id[0] = '\0'; /* Unset */ - c->x86_model_id[0] = '\0'; /* Unset */ - c->x86_clflush_size = 64; - c->x86_cache_alignment = c->x86_clflush_size; - c->x86_num_cores = 1; - c->extended_cpuid_level = 0; - memset(&c->x86_capability, 0, sizeof c->x86_capability); - - /* Get vendor name */ - cpuid(0x00000000, (unsigned int *)&c->cpuid_level, - (unsigned int *)&c->x86_vendor_id[0], - (unsigned int *)&c->x86_vendor_id[8], - (unsigned int *)&c->x86_vendor_id[4]); - - get_cpu_vendor(c); - - /* Initialize the standard set of capabilities */ - /* Note that the vendor-specific code below might override */ - - /* Intel-defined flags: level 0x00000001 */ - if (c->cpuid_level >= 0x00000001) { - __u32 misc; - cpuid(0x00000001, &tfms, &misc, &c->x86_capability[4], - &c->x86_capability[0]); - c->x86 = (tfms >> 8) & 0xf; - c->x86_model = (tfms >> 4) & 0xf; - c->x86_mask = tfms & 0xf; - if (c->x86 == 0xf) { - c->x86 += (tfms >> 20) & 0xff; - c->x86_model += ((tfms >> 16) & 0xF) << 4; - } - if (c->x86_capability[0] & (1<<19)) - c->x86_clflush_size = ((misc >> 8) & 0xff) * 8; - } else { - /* Have CPUID level 0 only - unheard of */ - c->x86 = 4; - } - -#ifdef CONFIG_SMP - phys_proc_id[smp_processor_id()] = (cpuid_ebx(1) >> 24) & 0xff; -#endif -} - -/* - * This does the hard work of actually picking apart the CPU stuff... - */ -void __init identify_cpu(struct cpuinfo_x86 *c) -{ - int i; - u32 xlvl; - - early_identify_cpu(c); - - /* AMD-defined flags: level 0x80000001 */ - xlvl = cpuid_eax(0x80000000); - c->extended_cpuid_level = xlvl; - if ((xlvl & 0xffff0000) == 0x80000000) { - if (xlvl >= 0x80000001) { - c->x86_capability[1] = cpuid_edx(0x80000001); - c->x86_capability[6] = cpuid_ecx(0x80000001); - } - if (xlvl >= 0x80000004) - get_model_name(c); /* Default name */ - } - - /* Transmeta-defined flags: level 0x80860001 */ - xlvl = cpuid_eax(0x80860000); - if ((xlvl & 0xffff0000) == 0x80860000) { - /* Don't set x86_cpuid_level here for now to not confuse. */ - if (xlvl >= 0x80860001) - c->x86_capability[2] = cpuid_edx(0x80860001); - } - - /* - * Vendor-specific initialization. In this section we - * canonicalize the feature flags, meaning if there are - * features a certain CPU supports which CPUID doesn't - * tell us, CPUID claiming incorrect flags, or other bugs, - * we handle them here. - * - * At the end of this section, c->x86_capability better - * indicate the features this CPU genuinely supports! - */ - switch (c->x86_vendor) { - case X86_VENDOR_AMD: - init_amd(c); - break; - - case X86_VENDOR_INTEL: - init_intel(c); - break; - - case X86_VENDOR_UNKNOWN: - default: - display_cacheinfo(c); - break; - } - - select_idle_routine(c); - detect_ht(c); - - /* - * On SMP, boot_cpu_data holds the common feature set between - * all CPUs; so make sure that we indicate which features are - * common between the CPUs. The first time this routine gets - * executed, c == &boot_cpu_data. - */ - if (c != &boot_cpu_data) { - /* AND the already accumulated flags with these */ - for (i = 0 ; i < NCAPINTS ; i++) - boot_cpu_data.x86_capability[i] &= c->x86_capability[i]; - } - -#ifdef CONFIG_X86_MCE - mcheck_init(c); -#endif -#ifdef CONFIG_NUMA - if (c != &boot_cpu_data) - numa_add_cpu(c - cpu_data); -#endif -} - - -void __init print_cpu_info(struct cpuinfo_x86 *c) -{ - if (c->x86_model_id[0]) - printk("%s", c->x86_model_id); - - if (c->x86_mask || c->cpuid_level >= 0) - printk(" stepping %02x\n", c->x86_mask); - else - printk("\n"); -} - -/* - * Get CPU information for use by the procfs. - */ - -static int show_cpuinfo(struct seq_file *m, void *v) -{ - struct cpuinfo_x86 *c = v; - - /* - * These flag bits must match the definitions in <asm/cpufeature.h>. - * NULL means this bit is undefined or reserved; either way it doesn't - * have meaning as far as Linux is concerned. Note that it's important - * to realize there is a difference between this table and CPUID -- if - * applications want to get the raw CPUID data, they should access - * /dev/cpu/<cpu_nr>/cpuid instead. - */ - static char *x86_cap_flags[] = { - /* Intel-defined */ - "fpu", "vme", "de", "pse", "tsc", "msr", "pae", "mce", - "cx8", "apic", NULL, "sep", "mtrr", "pge", "mca", "cmov", - "pat", "pse36", "pn", "clflush", NULL, "dts", "acpi", "mmx", - "fxsr", "sse", "sse2", "ss", "ht", "tm", "ia64", NULL, - - /* AMD-defined */ - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, "nx", NULL, "mmxext", NULL, - NULL, "fxsr_opt", NULL, NULL, NULL, "lm", "3dnowext", "3dnow", - - /* Transmeta-defined */ - "recovery", "longrun", NULL, "lrti", NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - - /* Other (Linux-defined) */ - "cxmmx", NULL, "cyrix_arr", "centaur_mcr", NULL, - "constant_tsc", NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - - /* Intel-defined (#2) */ - "pni", NULL, NULL, "monitor", "ds_cpl", NULL, NULL, "est", - "tm2", NULL, "cid", NULL, NULL, "cx16", "xtpr", NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - - /* VIA/Cyrix/Centaur-defined */ - NULL, NULL, "rng", "rng_en", NULL, NULL, "ace", "ace_en", - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - - /* AMD-defined (#2) */ - "lahf_lm", "cmp_legacy", NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, - }; - static char *x86_power_flags[] = { - "ts", /* temperature sensor */ - "fid", /* frequency id control */ - "vid", /* voltage id control */ - "ttp", /* thermal trip */ - "tm", - "stc" - }; - - -#ifdef CONFIG_SMP - if (!cpu_online(c-cpu_data)) - return 0; -#endif - - seq_printf(m,"processor\t: %u\n" - "vendor_id\t: %s\n" - "cpu family\t: %d\n" - "model\t\t: %d\n" - "model name\t: %s\n", - (unsigned)(c-cpu_data), - c->x86_vendor_id[0] ? c->x86_vendor_id : "unknown", - c->x86, - (int)c->x86_model, - c->x86_model_id[0] ? c->x86_model_id : "unknown"); - - if (c->x86_mask || c->cpuid_level >= 0) - seq_printf(m, "stepping\t: %d\n", c->x86_mask); - else - seq_printf(m, "stepping\t: unknown\n"); - - if (cpu_has(c,X86_FEATURE_TSC)) { - seq_printf(m, "cpu MHz\t\t: %u.%03u\n", - cpu_khz / 1000, (cpu_khz % 1000)); - } - - /* Cache size */ - if (c->x86_cache_size >= 0) - seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size); - -#ifdef CONFIG_SMP - if (smp_num_siblings * c->x86_num_cores > 1) { - int cpu = c - cpu_data; - seq_printf(m, "physical id\t: %d\n", phys_proc_id[cpu]); - seq_printf(m, "siblings\t: %d\n", - c->x86_num_cores * smp_num_siblings); - seq_printf(m, "core id\t\t: %d\n", cpu_core_id[cpu]); - seq_printf(m, "cpu cores\t: %d\n", c->x86_num_cores); - } -#endif - - seq_printf(m, - "fpu\t\t: yes\n" - "fpu_exception\t: yes\n" - "cpuid level\t: %d\n" - "wp\t\t: yes\n" - "flags\t\t:", - c->cpuid_level); - - { - int i; - for ( i = 0 ; i < 32*NCAPINTS ; i++ ) - if ( test_bit(i, &c->x86_capability) && - x86_cap_flags[i] != NULL ) - seq_printf(m, " %s", x86_cap_flags[i]); - } - - seq_printf(m, "\nbogomips\t: %lu.%02lu\n", - c->loops_per_jiffy/(500000/HZ), - (c->loops_per_jiffy/(5000/HZ)) % 100); - - if (c->x86_tlbsize > 0) - seq_printf(m, "TLB size\t: %d 4K pages\n", c->x86_tlbsize); - seq_printf(m, "clflush size\t: %d\n", c->x86_clflush_size); - seq_printf(m, "cache_alignment\t: %d\n", c->x86_cache_alignment); - - seq_printf(m, "address sizes\t: %u bits physical, %u bits virtual\n", - c->x86_phys_bits, c->x86_virt_bits); - - seq_printf(m, "power management:"); - { - unsigned i; - for (i = 0; i < 32; i++) - if (c->x86_power & (1 << i)) { - if (i < ARRAY_SIZE(x86_power_flags)) - seq_printf(m, " %s", x86_power_flags[i]); - else - seq_printf(m, " [%d]", i); - } - } - - seq_printf(m, "\n\n"); - - return 0; -} - -static void *c_start(struct seq_file *m, loff_t *pos) -{ - return *pos < NR_CPUS ? cpu_data + *pos : NULL; -} - -static void *c_next(struct seq_file *m, void *v, loff_t *pos) -{ - ++*pos; - return c_start(m, pos); -} - -static void c_stop(struct seq_file *m, void *v) -{ -} - -struct seq_operations cpuinfo_op = { - .start =c_start, - .next = c_next, - .stop = c_stop, - .show = show_cpuinfo, -}; diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/setup64.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/setup64.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,359 +0,0 @@ -/* - * X86-64 specific CPU setup. - * Copyright (C) 1995 Linus Torvalds - * Copyright 2001, 2002, 2003 SuSE Labs / Andi Kleen. - * See setup.c for older changelog. - * $Id: setup64.c,v 1.12 2002/03/21 10:09:17 ak Exp $ - * - * Jun Nakajima <jun.nakajima@xxxxxxxxx> - * Modified for Xen - * - */ -#include <linux/config.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/sched.h> -#include <linux/string.h> -#include <linux/bootmem.h> -#include <linux/bitops.h> -#include <asm/bootsetup.h> -#include <asm/pda.h> -#include <asm/pgtable.h> -#include <asm/processor.h> -#include <asm/desc.h> -#include <asm/atomic.h> -#include <asm/mmu_context.h> -#include <asm/smp.h> -#include <asm/i387.h> -#include <asm/percpu.h> -#include <asm/mtrr.h> -#include <asm/proto.h> -#include <asm/mman.h> -#include <asm/numa.h> -#ifdef CONFIG_XEN -#include <asm/hypervisor.h> -#endif - -char x86_boot_params[BOOT_PARAM_SIZE] __initdata = {0,}; - -cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE; - -struct x8664_pda cpu_pda[NR_CPUS] __cacheline_aligned; - -extern struct task_struct init_task; - -extern unsigned char __per_cpu_start[], __per_cpu_end[]; - -extern struct desc_ptr cpu_gdt_descr[]; -struct desc_ptr idt_descr = { 256 * 16, (unsigned long) idt_table }; - -char boot_cpu_stack[IRQSTACKSIZE] __attribute__((section(".bss.page_aligned"))); - -unsigned long __supported_pte_mask = ~0UL; -static int do_not_nx __initdata = 0; - -/* noexec=on|off -Control non executable mappings for 64bit processes. - -on Enable(default) -off Disable -*/ -int __init nonx_setup(char *str) -{ - if (!strncmp(str, "on", 2)) { - __supported_pte_mask |= _PAGE_NX; - do_not_nx = 0; - } else if (!strncmp(str, "off", 3)) { - do_not_nx = 1; - __supported_pte_mask &= ~_PAGE_NX; - } - return 0; -} -__setup("noexec=", nonx_setup); /* parsed early actually */ - -int force_personality32 = READ_IMPLIES_EXEC; - -/* noexec32=on|off -Control non executable heap for 32bit processes. -To control the stack too use noexec=off - -on PROT_READ does not imply PROT_EXEC for 32bit processes -off PROT_READ implies PROT_EXEC (default) -*/ -static int __init nonx32_setup(char *str) -{ - if (!strcmp(str, "on")) - force_personality32 &= ~READ_IMPLIES_EXEC; - else if (!strcmp(str, "off")) - force_personality32 |= READ_IMPLIES_EXEC; - return 0; -} -__setup("noexec32=", nonx32_setup); - -/* - * Great future plan: - * Declare PDA itself and support (irqstack,tss,pgd) as per cpu data. - * Always point %gs to its beginning - */ -void __init setup_per_cpu_areas(void) -{ - int i; - unsigned long size; - - /* Copy section for each CPU (we discard the original) */ - size = ALIGN(__per_cpu_end - __per_cpu_start, SMP_CACHE_BYTES); -#ifdef CONFIG_MODULES - if (size < PERCPU_ENOUGH_ROOM) - size = PERCPU_ENOUGH_ROOM; -#endif - - for (i = 0; i < NR_CPUS; i++) { - unsigned char *ptr; - - if (!NODE_DATA(cpu_to_node(i))) { - printk("cpu with no node %d, num_online_nodes %d\n", - i, num_online_nodes()); - ptr = alloc_bootmem(size); - } else { - ptr = alloc_bootmem_node(NODE_DATA(cpu_to_node(i)), size); - } - if (!ptr) - panic("Cannot allocate cpu data for CPU %d\n", i); - cpu_pda[i].data_offset = ptr - __per_cpu_start; - memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start); - } -} - -#ifdef CONFIG_XEN -static void switch_pt(void) -{ - xen_pt_switch(__pa(init_level4_pgt)); - xen_new_user_pt(__pa(init_level4_user_pgt)); -} - -void __cpuinit cpu_gdt_init(struct desc_ptr *gdt_descr) -{ - unsigned long frames[16]; - unsigned long va; - int f; - - for (va = gdt_descr->address, f = 0; - va < gdt_descr->address + gdt_descr->size; - va += PAGE_SIZE, f++) { - frames[f] = virt_to_mfn(va); - make_page_readonly( - (void *)va, XENFEAT_writable_descriptor_tables); - } - if (HYPERVISOR_set_gdt(frames, gdt_descr->size / - sizeof (struct desc_struct))) - BUG(); -} -#else -static void switch_pt(void) -{ - asm volatile("movq %0,%%cr3" :: "r" (__pa_symbol(&init_level4_pgt))); -} - -void __init cpu_gdt_init(struct desc_ptr *gdt_descr) -{ -#ifdef CONFIG_SMP - int cpu = stack_smp_processor_id(); -#else - int cpu = smp_processor_id(); -#endif - - asm volatile("lgdt %0" :: "m" (cpu_gdt_descr[cpu])); - asm volatile("lidt %0" :: "m" (idt_descr)); -} -#endif - -void pda_init(int cpu) -{ - struct x8664_pda *pda = &cpu_pda[cpu]; - - /* Setup up data that may be needed in __get_free_pages early */ - asm volatile("movl %0,%%fs ; movl %0,%%gs" :: "r" (0)); -#ifndef CONFIG_XEN - wrmsrl(MSR_GS_BASE, cpu_pda + cpu); -#else - HYPERVISOR_set_segment_base(SEGBASE_GS_KERNEL, - (unsigned long)(cpu_pda + cpu)); -#endif - - pda->me = pda; - pda->cpunumber = cpu; - pda->irqcount = -1; - pda->kernelstack = - (unsigned long)stack_thread_info() - PDA_STACKOFFSET + THREAD_SIZE; - pda->active_mm = &init_mm; - pda->mmu_state = 0; - - if (cpu == 0) { -#ifdef CONFIG_XEN - xen_init_pt(); -#endif - /* others are initialized in smpboot.c */ - pda->pcurrent = &init_task; - pda->irqstackptr = boot_cpu_stack; - } else { - pda->irqstackptr = (char *) - __get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER); - if (!pda->irqstackptr) - panic("cannot allocate irqstack for cpu %d", cpu); - } - - switch_pt(); - - pda->irqstackptr += IRQSTACKSIZE-64; -} - -char boot_exception_stacks[N_EXCEPTION_STACKS * EXCEPTION_STKSZ] -__attribute__((section(".bss.page_aligned"))); - -/* May not be marked __init: used by software suspend */ -void syscall_init(void) -{ -#ifndef CONFIG_XEN - /* - * LSTAR and STAR live in a bit strange symbiosis. - * They both write to the same internal register. STAR allows to set CS/DS - * but only a 32bit target. LSTAR sets the 64bit rip. - */ - wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 | ((u64)__KERNEL_CS)<<32); - wrmsrl(MSR_LSTAR, system_call); - - /* Flags to clear on syscall */ - wrmsrl(MSR_SYSCALL_MASK, EF_TF|EF_DF|EF_IE|0x3000); -#endif -#ifdef CONFIG_IA32_EMULATION - syscall32_cpu_init (); -#endif -} - -void __cpuinit check_efer(void) -{ - unsigned long efer; - - rdmsrl(MSR_EFER, efer); - if (!(efer & EFER_NX) || do_not_nx) { - __supported_pte_mask &= ~_PAGE_NX; - } -} - -/* - * cpu_init() initializes state that is per-CPU. Some data is already - * initialized (naturally) in the bootstrap process, such as the GDT - * and IDT. We reload them nevertheless, this function acts as a - * 'CPU state barrier', nothing should get across. - * A lot of state is already set up in PDA init. - */ -void __cpuinit cpu_init (void) -{ -#ifdef CONFIG_SMP - int cpu = stack_smp_processor_id(); -#else - int cpu = smp_processor_id(); -#endif - struct tss_struct *t = &per_cpu(init_tss, cpu); - unsigned long v; - char *estacks = NULL; - struct task_struct *me; - int i; - - /* CPU 0 is initialised in head64.c */ - if (cpu != 0) { - pda_init(cpu); - } else - estacks = boot_exception_stacks; - - me = current; - - if (cpu_test_and_set(cpu, cpu_initialized)) - panic("CPU#%d already initialized!\n", cpu); - - printk("Initializing CPU#%d\n", cpu); - - clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); - - /* - * Initialize the per-CPU GDT with the boot GDT, - * and set up the GDT descriptor: - */ -#ifndef CONFIG_XEN - if (cpu) { - memcpy(cpu_gdt_table[cpu], cpu_gdt_table[0], GDT_SIZE); - } - - cpu_gdt_descr[cpu].size = GDT_SIZE; - cpu_gdt_descr[cpu].address = (unsigned long)cpu_gdt_table[cpu]; - - memcpy(me->thread.tls_array, cpu_gdt_table[cpu], GDT_ENTRY_TLS_ENTRIES * 8); -#else - memcpy(me->thread.tls_array, &get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN], - GDT_ENTRY_TLS_ENTRIES * 8); - - cpu_gdt_init(&cpu_gdt_descr[cpu]); -#endif - - /* - * Delete NT - */ - - asm volatile("pushfq ; popq %%rax ; btr $14,%%rax ; pushq %%rax ; popfq" ::: "eax"); - - syscall_init(); - - wrmsrl(MSR_FS_BASE, 0); - wrmsrl(MSR_KERNEL_GS_BASE, 0); - barrier(); - - check_efer(); - - /* - * set up and load the per-CPU TSS - */ - for (v = 0; v < N_EXCEPTION_STACKS; v++) { - if (cpu) { - estacks = (char *)__get_free_pages(GFP_ATOMIC, - EXCEPTION_STACK_ORDER); - if (!estacks) - panic("Cannot allocate exception stack %ld %d\n", - v, cpu); - } - estacks += EXCEPTION_STKSZ; - t->ist[v] = (unsigned long)estacks; - } - - t->io_bitmap_base = offsetof(struct tss_struct, io_bitmap); - /* - * <= is required because the CPU will access up to - * 8 bits beyond the end of the IO permission bitmap. - */ - for (i = 0; i <= IO_BITMAP_LONGS; i++) - t->io_bitmap[i] = ~0UL; - - atomic_inc(&init_mm.mm_count); - me->active_mm = &init_mm; - if (me->mm) - BUG(); - enter_lazy_tlb(&init_mm, me); - -#ifndef CONFIG_XEN - set_tss_desc(cpu, t); - load_TR_desc(); -#endif - load_LDT(&init_mm.context); - - /* - * Clear all 6 debug registers: - */ - - set_debug(0UL, 0); - set_debug(0UL, 1); - set_debug(0UL, 2); - set_debug(0UL, 3); - set_debug(0UL, 6); - set_debug(0UL, 7); - - fpu_init(); -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/signal.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/signal.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,493 +0,0 @@ -/* - * linux/arch/x86_64/kernel/signal.c - * - * Copyright (C) 1991, 1992 Linus Torvalds - * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs - * - * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson - * 2000-06-20 Pentium III FXSR, SSE support by Gareth Hughes - * 2000-2002 x86-64 support by Andi Kleen - * - * $Id: signal.c,v 1.18 2001/10/17 22:30:37 ak Exp $ - */ - -#include <linux/sched.h> -#include <linux/mm.h> -#include <linux/smp.h> -#include <linux/smp_lock.h> -#include <linux/kernel.h> -#include <linux/signal.h> -#include <linux/errno.h> -#include <linux/wait.h> -#include <linux/ptrace.h> -#include <linux/unistd.h> -#include <linux/stddef.h> -#include <linux/personality.h> -#include <linux/compiler.h> -#include <asm/ucontext.h> -#include <asm/uaccess.h> -#include <asm/i387.h> -#include <asm/proto.h> -#include <asm/ia32_unistd.h> - -/* #define DEBUG_SIG 1 */ - -#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP))) - -void ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, - sigset_t *set, struct pt_regs * regs); -void ia32_setup_frame(int sig, struct k_sigaction *ka, - sigset_t *set, struct pt_regs * regs); - -asmlinkage long -sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize, struct pt_regs *regs) -{ - sigset_t saveset, newset; - - /* XXX: Don't preclude handling different sized sigset_t's. */ - if (sigsetsize != sizeof(sigset_t)) - return -EINVAL; - - if (copy_from_user(&newset, unewset, sizeof(newset))) - return -EFAULT; - sigdelsetmask(&newset, ~_BLOCKABLE); - - spin_lock_irq(&current->sighand->siglock); - saveset = current->blocked; - current->blocked = newset; - recalc_sigpending(); - spin_unlock_irq(&current->sighand->siglock); -#ifdef DEBUG_SIG - printk("rt_sigsuspend savset(%lx) newset(%lx) regs(%p) rip(%lx)\n", - saveset, newset, regs, regs->rip); -#endif - regs->rax = -EINTR; - while (1) { - current->state = TASK_INTERRUPTIBLE; - schedule(); - if (do_signal(regs, &saveset)) - return -EINTR; - } -} - -asmlinkage long -sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss, - struct pt_regs *regs) -{ - return do_sigaltstack(uss, uoss, regs->rsp); -} - - -/* - * Do a signal return; undo the signal stack. - */ - -struct rt_sigframe -{ - char __user *pretcode; - struct ucontext uc; - struct siginfo info; -}; - -static int -restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, unsigned long *prax) -{ - unsigned int err = 0; - - /* Always make any pending restarted system calls return -EINTR */ - current_thread_info()->restart_block.fn = do_no_restart_syscall; - -#define COPY(x) err |= __get_user(regs->x, &sc->x) - - COPY(rdi); COPY(rsi); COPY(rbp); COPY(rsp); COPY(rbx); - COPY(rdx); COPY(rcx); COPY(rip); - COPY(r8); - COPY(r9); - COPY(r10); - COPY(r11); - COPY(r12); - COPY(r13); - COPY(r14); - COPY(r15); - - { - unsigned int tmpflags; - err |= __get_user(tmpflags, &sc->eflags); - regs->eflags = (regs->eflags & ~0x40DD5) | (tmpflags & 0x40DD5); - regs->orig_rax = -1; /* disable syscall checks */ - } - - { - struct _fpstate __user * buf; - err |= __get_user(buf, &sc->fpstate); - - if (buf) { - if (!access_ok(VERIFY_READ, buf, sizeof(*buf))) - goto badframe; - err |= restore_i387(buf); - } else { - struct task_struct *me = current; - if (used_math()) { - clear_fpu(me); - clear_used_math(); - } - } - } - - err |= __get_user(*prax, &sc->rax); - return err; - -badframe: - return 1; -} - -asmlinkage long sys_rt_sigreturn(struct pt_regs *regs) -{ - struct rt_sigframe __user *frame; - sigset_t set; - unsigned long eax; - - frame = (struct rt_sigframe __user *)(regs->rsp - 8); - if (!access_ok(VERIFY_READ, frame, sizeof(*frame))) { - goto badframe; - } - if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) { - goto badframe; - } - - sigdelsetmask(&set, ~_BLOCKABLE); - spin_lock_irq(&current->sighand->siglock); - current->blocked = set; - recalc_sigpending(); - spin_unlock_irq(&current->sighand->siglock); - - if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &eax)) - goto badframe; - -#ifdef DEBUG_SIG - printk("%d sigreturn rip:%lx rsp:%lx frame:%p rax:%lx\n",current->pid,regs.rip,regs.rsp,frame,eax); -#endif - - if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->rsp) == -EFAULT) - goto badframe; - - return eax; - -badframe: - signal_fault(regs,frame,"sigreturn"); - return 0; -} - -/* - * Set up a signal frame. - */ - -static inline int -setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs, unsigned long mask, struct task_struct *me) -{ - int err = 0; - - err |= __put_user(0, &sc->gs); - err |= __put_user(0, &sc->fs); - - err |= __put_user(regs->rdi, &sc->rdi); - err |= __put_user(regs->rsi, &sc->rsi); - err |= __put_user(regs->rbp, &sc->rbp); - err |= __put_user(regs->rsp, &sc->rsp); - err |= __put_user(regs->rbx, &sc->rbx); - err |= __put_user(regs->rdx, &sc->rdx); - err |= __put_user(regs->rcx, &sc->rcx); - err |= __put_user(regs->rax, &sc->rax); - err |= __put_user(regs->r8, &sc->r8); - err |= __put_user(regs->r9, &sc->r9); - err |= __put_user(regs->r10, &sc->r10); - err |= __put_user(regs->r11, &sc->r11); - err |= __put_user(regs->r12, &sc->r12); - err |= __put_user(regs->r13, &sc->r13); - err |= __put_user(regs->r14, &sc->r14); - err |= __put_user(regs->r15, &sc->r15); - err |= __put_user(me->thread.trap_no, &sc->trapno); - err |= __put_user(me->thread.error_code, &sc->err); - err |= __put_user(regs->rip, &sc->rip); - err |= __put_user(regs->eflags, &sc->eflags); - err |= __put_user(mask, &sc->oldmask); - err |= __put_user(me->thread.cr2, &sc->cr2); - - return err; -} - -/* - * Determine which stack to use.. - */ - -static void __user * -get_stack(struct k_sigaction *ka, struct pt_regs *regs, unsigned long size) -{ - unsigned long rsp; - - /* Default to using normal stack - redzone*/ - rsp = regs->rsp - 128; - - /* This is the X/Open sanctioned signal stack switching. */ - /* RED-PEN: redzone on that stack? */ - if (ka->sa.sa_flags & SA_ONSTACK) { - if (sas_ss_flags(rsp) == 0) - rsp = current->sas_ss_sp + current->sas_ss_size; - } - - return (void __user *)round_down(rsp - size, 16); -} - -static void setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info, - sigset_t *set, struct pt_regs * regs) -{ - struct rt_sigframe __user *frame; - struct _fpstate __user *fp = NULL; - int err = 0; - struct task_struct *me = current; - - if (used_math()) { - fp = get_stack(ka, regs, sizeof(struct _fpstate)); - frame = (void __user *)round_down( - (unsigned long)fp - sizeof(struct rt_sigframe), 16) - 8; - - if (!access_ok(VERIFY_WRITE, fp, sizeof(struct _fpstate))) - goto give_sigsegv; - - if (save_i387(fp) < 0) - err |= -1; - } else - frame = get_stack(ka, regs, sizeof(struct rt_sigframe)) - 8; - - if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame))) - goto give_sigsegv; - - if (ka->sa.sa_flags & SA_SIGINFO) { - err |= copy_siginfo_to_user(&frame->info, info); - if (err) - goto give_sigsegv; - } - - /* Create the ucontext. */ - err |= __put_user(0, &frame->uc.uc_flags); - err |= __put_user(0, &frame->uc.uc_link); - err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - err |= __put_user(sas_ss_flags(regs->rsp), - &frame->uc.uc_stack.ss_flags); - err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size); - err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, set->sig[0], me); - err |= __put_user(fp, &frame->uc.uc_mcontext.fpstate); - if (sizeof(*set) == 16) { - __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]); - __put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]); - } else - err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); - - /* Set up to return from userspace. If provided, use a stub - already in userspace. */ - /* x86-64 should always use SA_RESTORER. */ - if (ka->sa.sa_flags & SA_RESTORER) { - err |= __put_user(ka->sa.sa_restorer, &frame->pretcode); - } else { - /* could use a vstub here */ - goto give_sigsegv; - } - - if (err) - goto give_sigsegv; - -#ifdef DEBUG_SIG - printk("%d old rip %lx old rsp %lx old rax %lx\n", current->pid,regs->rip,regs->rsp,regs->rax); -#endif - - /* Set up registers for signal handler */ - { - struct exec_domain *ed = current_thread_info()->exec_domain; - if (unlikely(ed && ed->signal_invmap && sig < 32)) - sig = ed->signal_invmap[sig]; - } - regs->rdi = sig; - /* In case the signal handler was declared without prototypes */ - regs->rax = 0; - - /* This also works for non SA_SIGINFO handlers because they expect the - next argument after the signal number on the stack. */ - regs->rsi = (unsigned long)&frame->info; - regs->rdx = (unsigned long)&frame->uc; - regs->rip = (unsigned long) ka->sa.sa_handler; - - regs->rsp = (unsigned long)frame; - - set_fs(USER_DS); - regs->eflags &= ~TF_MASK; - if (test_thread_flag(TIF_SINGLESTEP)) - ptrace_notify(SIGTRAP); -#ifdef DEBUG_SIG - printk("SIG deliver (%s:%d): sp=%p pc=%p ra=%p\n", - current->comm, current->pid, frame, regs->rip, frame->pretcode); -#endif - - return; - -give_sigsegv: - force_sigsegv(sig, current); -} - -/* - * OK, we're invoking a handler - */ - -static void -handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka, - sigset_t *oldset, struct pt_regs *regs) -{ -#ifdef DEBUG_SIG - printk("handle_signal pid:%d sig:%lu rip:%lx rsp:%lx regs=%p\n", - current->pid, sig, - regs->rip, regs->rsp, regs); -#endif - - /* Are we from a system call? */ - if ((long)regs->orig_rax >= 0) { - /* If so, check system call restarting.. */ - switch (regs->rax) { - case -ERESTART_RESTARTBLOCK: - case -ERESTARTNOHAND: - regs->rax = -EINTR; - break; - - case -ERESTARTSYS: - if (!(ka->sa.sa_flags & SA_RESTART)) { - regs->rax = -EINTR; - break; - } - /* fallthrough */ - case -ERESTARTNOINTR: - regs->rax = regs->orig_rax; - regs->rip -= 2; - break; - } - } - - /* - * If TF is set due to a debugger (PT_DTRACE), clear the TF - * flag so that register information in the sigcontext is - * correct. - */ - if (unlikely(regs->eflags & TF_MASK)) { - if (likely(current->ptrace & PT_DTRACE)) { - current->ptrace &= ~PT_DTRACE; - regs->eflags &= ~TF_MASK; - } - } - -#ifdef CONFIG_IA32_EMULATION - if (test_thread_flag(TIF_IA32)) { - if (ka->sa.sa_flags & SA_SIGINFO) - ia32_setup_rt_frame(sig, ka, info, oldset, regs); - else - ia32_setup_frame(sig, ka, oldset, regs); - } else -#endif - setup_rt_frame(sig, ka, info, oldset, regs); - - if (!(ka->sa.sa_flags & SA_NODEFER)) { - spin_lock_irq(&current->sighand->siglock); - sigorsets(&current->blocked,&current->blocked,&ka->sa.sa_mask); - sigaddset(&current->blocked,sig); - recalc_sigpending(); - spin_unlock_irq(&current->sighand->siglock); - } -} - -/* - * Note that 'init' is a special process: it doesn't get signals it doesn't - * want to handle. Thus you cannot kill init even with a SIGKILL even by - * mistake. - */ -int do_signal(struct pt_regs *regs, sigset_t *oldset) -{ - struct k_sigaction ka; - siginfo_t info; - int signr; - - /* - * We want the common case to go fast, which - * is why we may in certain cases get here from - * kernel mode. Just return without doing anything - * if so. - */ - if ((regs->cs & 2) != 2) - return 1; - - if (try_to_freeze(0)) - goto no_signal; - - if (!oldset) - oldset = &current->blocked; - - signr = get_signal_to_deliver(&info, &ka, regs, NULL); - if (signr > 0) { - /* Reenable any watchpoints before delivering the - * signal to user space. The processor register will - * have been cleared if the watchpoint triggered - * inside the kernel. - */ - if (current->thread.debugreg7) { - HYPERVISOR_set_debugreg(7, - current->thread.debugreg7); - } - - /* Whee! Actually deliver the signal. */ - handle_signal(signr, &info, &ka, oldset, regs); - return 1; - } - - no_signal: - /* Did we come from a system call? */ - if ((long)regs->orig_rax >= 0) { - /* Restart the system call - no handlers present */ - long res = regs->rax; - if (res == -ERESTARTNOHAND || - res == -ERESTARTSYS || - res == -ERESTARTNOINTR) { - regs->rax = regs->orig_rax; - regs->rip -= 2; - } - if (regs->rax == (unsigned long)-ERESTART_RESTARTBLOCK) { - regs->rax = test_thread_flag(TIF_IA32) ? - __NR_ia32_restart_syscall : - __NR_restart_syscall; - regs->rip -= 2; - } - } - return 0; -} - -void do_notify_resume(struct pt_regs *regs, sigset_t *oldset, __u32 thread_info_flags) -{ -#ifdef DEBUG_SIG - printk("do_notify_resume flags:%x rip:%lx rsp:%lx caller:%lx pending:%lx\n", - thread_info_flags, regs->rip, regs->rsp, __builtin_return_address(0),signal_pending(current)); -#endif - - /* Pending single-step? */ - if (thread_info_flags & _TIF_SINGLESTEP) { - regs->eflags |= TF_MASK; - clear_thread_flag(TIF_SINGLESTEP); - } - - /* deal with pending signal delivery */ - if (thread_info_flags & _TIF_SIGPENDING) - do_signal(regs,oldset); -} - -void signal_fault(struct pt_regs *regs, void __user *frame, char *where) -{ - struct task_struct *me = current; - if (exception_trace) - printk("%s[%d] bad frame in %s frame:%p rip:%lx rsp:%lx orax:%lx\n", - me->comm,me->pid,where,frame,regs->rip,regs->rsp,regs->orig_rax); - - force_sig(SIGSEGV, me); -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/smp.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/smp.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,493 +0,0 @@ -/* - * Intel SMP support routines. - * - * (c) 1995 Alan Cox, Building #3 <alan@xxxxxxxxxx> - * (c) 1998-99, 2000 Ingo Molnar <mingo@xxxxxxxxxx> - * (c) 2002,2003 Andi Kleen, SuSE Labs. - * - * This code is released under the GNU General Public License version 2 or - * later. - */ - -#include <linux/init.h> - -#include <linux/mm.h> -#include <linux/irq.h> -#include <linux/delay.h> -#include <linux/spinlock.h> -#include <linux/smp_lock.h> -#include <linux/smp.h> -#include <linux/kernel_stat.h> -#include <linux/mc146818rtc.h> -#include <linux/interrupt.h> - -#include <asm/mtrr.h> -#include <asm/pgalloc.h> -#include <asm/tlbflush.h> -#include <asm/mach_apic.h> -#include <asm/mmu_context.h> -#include <asm/proto.h> -#include <asm/apicdef.h> -#ifdef CONFIG_XEN -#include <asm-xen/evtchn.h> -#endif - -#ifndef CONFIG_XEN -/* - * Smarter SMP flushing macros. - * c/o Linus Torvalds. - * - * These mean you can really definitely utterly forget about - * writing to user space from interrupts. (Its not allowed anyway). - * - * Optimizations Manfred Spraul <manfred@xxxxxxxxxxxxxxxx> - */ - -static cpumask_t flush_cpumask; -static struct mm_struct * flush_mm; -static unsigned long flush_va; -static DEFINE_SPINLOCK(tlbstate_lock); -#define FLUSH_ALL -1ULL -#endif - -/* - * We cannot call mmdrop() because we are in interrupt context, - * instead update mm->cpu_vm_mask. - */ -static inline void leave_mm (unsigned long cpu) -{ - if (read_pda(mmu_state) == TLBSTATE_OK) - BUG(); - clear_bit(cpu, &read_pda(active_mm)->cpu_vm_mask); - load_cr3(swapper_pg_dir); -} - -#ifndef CONFIG_XEN -/* - * - * The flush IPI assumes that a thread switch happens in this order: - * [cpu0: the cpu that switches] - * 1) switch_mm() either 1a) or 1b) - * 1a) thread switch to a different mm - * 1a1) clear_bit(cpu, &old_mm->cpu_vm_mask); - * Stop ipi delivery for the old mm. This is not synchronized with - * the other cpus, but smp_invalidate_interrupt ignore flush ipis - * for the wrong mm, and in the worst case we perform a superfluous - * tlb flush. - * 1a2) set cpu mmu_state to TLBSTATE_OK - * Now the smp_invalidate_interrupt won't call leave_mm if cpu0 - * was in lazy tlb mode. - * 1a3) update cpu active_mm - * Now cpu0 accepts tlb flushes for the new mm. - * 1a4) set_bit(cpu, &new_mm->cpu_vm_mask); - * Now the other cpus will send tlb flush ipis. - * 1a4) change cr3. - * 1b) thread switch without mm change - * cpu active_mm is correct, cpu0 already handles - * flush ipis. - * 1b1) set cpu mmu_state to TLBSTATE_OK - * 1b2) test_and_set the cpu bit in cpu_vm_mask. - * Atomically set the bit [other cpus will start sending flush ipis], - * and test the bit. - * 1b3) if the bit was 0: leave_mm was called, flush the tlb. - * 2) switch %%esp, ie current - * - * The interrupt must handle 2 special cases: - * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm. - * - the cpu performs speculative tlb reads, i.e. even if the cpu only - * runs in kernel space, the cpu could load tlb entries for user space - * pages. - * - * The good news is that cpu mmu_state is local to each cpu, no - * write/read ordering problems. - */ - -/* - * TLB flush IPI: - * - * 1) Flush the tlb entries if the cpu uses the mm that's being flushed. - * 2) Leave the mm if we are in the lazy tlb mode. - */ - -asmlinkage void smp_invalidate_interrupt (void) -{ - unsigned long cpu; - - cpu = get_cpu(); - - if (!cpu_isset(cpu, flush_cpumask)) - goto out; - /* - * This was a BUG() but until someone can quote me the - * line from the intel manual that guarantees an IPI to - * multiple CPUs is retried _only_ on the erroring CPUs - * its staying as a return - * - * BUG(); - */ - - if (flush_mm == read_pda(active_mm)) { - if (read_pda(mmu_state) == TLBSTATE_OK) { - if (flush_va == FLUSH_ALL) - local_flush_tlb(); - else - __flush_tlb_one(flush_va); - } else - leave_mm(cpu); - } - ack_APIC_irq(); - cpu_clear(cpu, flush_cpumask); - -out: - put_cpu_no_resched(); -} - -static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm, - unsigned long va) -{ - cpumask_t tmp; - /* - * A couple of (to be removed) sanity checks: - * - * - we do not send IPIs to not-yet booted CPUs. - * - current CPU must not be in mask - * - mask must exist :) - */ - BUG_ON(cpus_empty(cpumask)); - cpus_and(tmp, cpumask, cpu_online_map); - BUG_ON(!cpus_equal(tmp, cpumask)); - BUG_ON(cpu_isset(smp_processor_id(), cpumask)); - if (!mm) - BUG(); - - /* - * I'm not happy about this global shared spinlock in the - * MM hot path, but we'll see how contended it is. - * Temporarily this turns IRQs off, so that lockups are - * detected by the NMI watchdog. - */ - spin_lock(&tlbstate_lock); - - flush_mm = mm; - flush_va = va; - cpus_or(flush_cpumask, cpumask, flush_cpumask); - - /* - * We have to send the IPI only to - * CPUs affected. - */ - send_IPI_mask(cpumask, INVALIDATE_TLB_VECTOR); - - while (!cpus_empty(flush_cpumask)) - mb(); /* nothing. lockup detection does not belong here */; - - flush_mm = NULL; - flush_va = 0; - spin_unlock(&tlbstate_lock); -} - -void flush_tlb_current_task(void) -{ - struct mm_struct *mm = current->mm; - cpumask_t cpu_mask; - - preempt_disable(); - cpu_mask = mm->cpu_vm_mask; - cpu_clear(smp_processor_id(), cpu_mask); - - local_flush_tlb(); - if (!cpus_empty(cpu_mask)) - flush_tlb_others(cpu_mask, mm, FLUSH_ALL); - preempt_enable(); -} - -void flush_tlb_mm (struct mm_struct * mm) -{ - cpumask_t cpu_mask; - - preempt_disable(); - cpu_mask = mm->cpu_vm_mask; - cpu_clear(smp_processor_id(), cpu_mask); - - if (current->active_mm == mm) { - if (current->mm) - local_flush_tlb(); - else - leave_mm(smp_processor_id()); - } - if (!cpus_empty(cpu_mask)) - flush_tlb_others(cpu_mask, mm, FLUSH_ALL); - - preempt_enable(); -} - -void flush_tlb_page(struct vm_area_struct * vma, unsigned long va) -{ - struct mm_struct *mm = vma->vm_mm; - cpumask_t cpu_mask; - - preempt_disable(); - cpu_mask = mm->cpu_vm_mask; - cpu_clear(smp_processor_id(), cpu_mask); - - if (current->active_mm == mm) { - if(current->mm) - __flush_tlb_one(va); - else - leave_mm(smp_processor_id()); - } - - if (!cpus_empty(cpu_mask)) - flush_tlb_others(cpu_mask, mm, va); - - preempt_enable(); -} - -static void do_flush_tlb_all(void* info) -{ - unsigned long cpu = smp_processor_id(); - - __flush_tlb_all(); - if (read_pda(mmu_state) == TLBSTATE_LAZY) - leave_mm(cpu); -} - -void flush_tlb_all(void) -{ - on_each_cpu(do_flush_tlb_all, NULL, 1, 1); -} -#else -asmlinkage void smp_invalidate_interrupt (void) -{ return; } -void flush_tlb_current_task(void) -{ xen_tlb_flush_mask(&current->mm->cpu_vm_mask); } -void flush_tlb_mm (struct mm_struct * mm) -{ xen_tlb_flush_mask(&mm->cpu_vm_mask); } -void flush_tlb_page(struct vm_area_struct * vma, unsigned long va) -{ xen_invlpg_mask(&vma->vm_mm->cpu_vm_mask, va); } -void flush_tlb_all(void) -{ xen_tlb_flush_all(); } -#endif /* Xen */ - -void smp_kdb_stop(void) -{ - send_IPI_allbutself(KDB_VECTOR); -} - -/* - * this function sends a 'reschedule' IPI to another CPU. - * it goes straight through and wastes no time serializing - * anything. Worst case is that we lose a reschedule ... - */ - -void smp_send_reschedule(int cpu) -{ - send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR); -} - -/* - * Structure and data for smp_call_function(). This is designed to minimise - * static memory requirements. It also looks cleaner. - */ -static DEFINE_SPINLOCK(call_lock); - -struct call_data_struct { - void (*func) (void *info); - void *info; - atomic_t started; - atomic_t finished; - int wait; -}; - -static struct call_data_struct * call_data; - -/* - * this function sends a 'generic call function' IPI to all other CPUs - * in the system. - */ -static void __smp_call_function (void (*func) (void *info), void *info, - int nonatomic, int wait) -{ - struct call_data_struct data; - int cpus = num_online_cpus()-1; - - if (!cpus) - return; - - data.func = func; - data.info = info; - atomic_set(&data.started, 0); - data.wait = wait; - if (wait) - atomic_set(&data.finished, 0); - - call_data = &data; - wmb(); - /* Send a message to all other CPUs and wait for them to respond */ - send_IPI_allbutself(CALL_FUNCTION_VECTOR); - - /* Wait for response */ - while (atomic_read(&data.started) != cpus) -#ifndef CONFIG_XEN - cpu_relax(); -#else - barrier(); -#endif - - if (!wait) - return; - - while (atomic_read(&data.finished) != cpus) -#ifndef CONFIG_XEN - cpu_relax(); -#else - barrier(); -#endif -} - -/* - * smp_call_function - run a function on all other CPUs. - * @func: The function to run. This must be fast and non-blocking. - * @info: An arbitrary pointer to pass to the function. - * @nonatomic: currently unused. - * @wait: If true, wait (atomically) until function has completed on other - * CPUs. - * - * Returns 0 on success, else a negative status code. Does not return until - * remote CPUs are nearly ready to execute func or are or have executed. - * - * You must not call this function with disabled interrupts or from a - * hardware interrupt handler or from a bottom half handler. - * Actually there are a few legal cases, like panic. - */ -int smp_call_function (void (*func) (void *info), void *info, int nonatomic, - int wait) -{ - spin_lock(&call_lock); - __smp_call_function(func,info,nonatomic,wait); - spin_unlock(&call_lock); - return 0; -} - -void smp_stop_cpu(void) -{ - /* - * Remove this CPU: - */ - cpu_clear(smp_processor_id(), cpu_online_map); - local_irq_disable(); -#ifndef CONFIG_XEN - disable_local_APIC(); -#endif - local_irq_enable(); -} - -static void smp_really_stop_cpu(void *dummy) -{ - smp_stop_cpu(); - for (;;) - asm("hlt"); -} - -void smp_send_stop(void) -{ - int nolock = 0; -#ifndef CONFIG_XEN - if (reboot_force) - return; -#endif - /* Don't deadlock on the call lock in panic */ - if (!spin_trylock(&call_lock)) { - /* ignore locking because we have paniced anyways */ - nolock = 1; - } - __smp_call_function(smp_really_stop_cpu, NULL, 0, 0); - if (!nolock) - spin_unlock(&call_lock); - - local_irq_disable(); -#ifndef CONFIG_XEN - disable_local_APIC(); -#endif - local_irq_enable(); -} - -/* - * Reschedule call back. Nothing to do, - * all the work is done automatically when - * we return from the interrupt. - */ -#ifndef CONFIG_XEN -asmlinkage void smp_reschedule_interrupt(void) -#else -asmlinkage irqreturn_t smp_reschedule_interrupt(void) -#endif -{ -#ifndef CONFIG_XEN - ack_APIC_irq(); -#else - return IRQ_HANDLED; -#endif -} - -#ifndef CONFIG_XEN -asmlinkage void smp_call_function_interrupt(void) -#else -asmlinkage irqreturn_t smp_call_function_interrupt(void) -#endif -{ - void (*func) (void *info) = call_data->func; - void *info = call_data->info; - int wait = call_data->wait; - -#ifndef CONFIG_XEN - ack_APIC_irq(); -#endif - /* - * Notify initiating CPU that I've grabbed the data and am - * about to execute the function - */ - mb(); - atomic_inc(&call_data->started); - /* - * At this point the info structure may be out of scope unless wait==1 - */ - irq_enter(); - (*func)(info); - irq_exit(); - if (wait) { - mb(); - atomic_inc(&call_data->finished); - } -#ifdef CONFIG_XEN - return IRQ_HANDLED; -#endif -} - -int safe_smp_processor_id(void) -{ -#ifdef CONFIG_XEN - return smp_processor_id(); -#else - int apicid, i; - - if (disable_apic) - return 0; - - apicid = hard_smp_processor_id(); - if (x86_cpu_to_apicid[apicid] == apicid) - return apicid; - - for (i = 0; i < NR_CPUS; ++i) { - if (x86_cpu_to_apicid[i] == apicid) - return i; - } - - /* No entries in x86_cpu_to_apicid? Either no MPS|ACPI, - * or called too early. Either way, we must be CPU 0. */ - if (x86_cpu_to_apicid[0] == BAD_APICID) - return 0; - - return 0; /* Should not happen */ -#endif -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/traps.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/traps.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,994 +0,0 @@ -/* - * linux/arch/x86-64/traps.c - * - * Copyright (C) 1991, 1992 Linus Torvalds - * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs - * - * Pentium III FXSR, SSE support - * Gareth Hughes <gareth@xxxxxxxxxxx>, May 2000 - * - * $Id: traps.c,v 1.36 2002/03/24 11:09:10 ak Exp $ - */ - -/* - * 'Traps.c' handles hardware traps and faults after we have saved some - * state in 'entry.S'. - */ -#include <linux/config.h> -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/ptrace.h> -#include <linux/timer.h> -#include <linux/mm.h> -#include <linux/init.h> -#include <linux/delay.h> -#include <linux/spinlock.h> -#include <linux/interrupt.h> -#include <linux/module.h> -#include <linux/moduleparam.h> -#include <linux/nmi.h> - -#include <asm/system.h> -#include <asm/uaccess.h> -#include <asm/io.h> -#include <asm/atomic.h> -#include <asm/debugreg.h> -#include <asm/desc.h> -#include <asm/i387.h> -#include <asm/kdebug.h> -#include <asm/processor.h> - -#include <asm/smp.h> -#include <asm/pgalloc.h> -#include <asm/pda.h> -#include <asm/proto.h> -#include <asm/nmi.h> - -#include <linux/irq.h> - - -extern struct gate_struct idt_table[256]; - -asmlinkage void divide_error(void); -asmlinkage void debug(void); -asmlinkage void nmi(void); -asmlinkage void int3(void); -asmlinkage void overflow(void); -asmlinkage void bounds(void); -asmlinkage void invalid_op(void); -asmlinkage void device_not_available(void); -asmlinkage void double_fault(void); -asmlinkage void coprocessor_segment_overrun(void); -asmlinkage void invalid_TSS(void); -asmlinkage void segment_not_present(void); -asmlinkage void stack_segment(void); -asmlinkage void general_protection(void); -asmlinkage void page_fault(void); -asmlinkage void coprocessor_error(void); -asmlinkage void simd_coprocessor_error(void); -asmlinkage void reserved(void); -asmlinkage void alignment_check(void); -asmlinkage void machine_check(void); -asmlinkage void spurious_interrupt_bug(void); -asmlinkage void call_debug(void); - -struct notifier_block *die_chain; -static DEFINE_SPINLOCK(die_notifier_lock); - -int register_die_notifier(struct notifier_block *nb) -{ - int err = 0; - unsigned long flags; - spin_lock_irqsave(&die_notifier_lock, flags); - err = notifier_chain_register(&die_chain, nb); - spin_unlock_irqrestore(&die_notifier_lock, flags); - return err; -} - -static inline void conditional_sti(struct pt_regs *regs) -{ - if (regs->eflags & X86_EFLAGS_IF) - local_irq_enable(); -} - -static int kstack_depth_to_print = 10; - -#ifdef CONFIG_KALLSYMS -#include <linux/kallsyms.h> -int printk_address(unsigned long address) -{ - unsigned long offset = 0, symsize; - const char *symname; - char *modname; - char *delim = ":"; - char namebuf[128]; - - symname = kallsyms_lookup(address, &symsize, &offset, &modname, namebuf); - if (!symname) - return printk("[<%016lx>]", address); - if (!modname) - modname = delim = ""; - return printk("<%016lx>{%s%s%s%s%+ld}", - address,delim,modname,delim,symname,offset); -} -#else -int printk_address(unsigned long address) -{ - return printk("[<%016lx>]", address); -} -#endif - -static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, - unsigned *usedp, const char **idp) -{ - static const char ids[N_EXCEPTION_STACKS][8] = { - [DEBUG_STACK - 1] = "#DB", - [NMI_STACK - 1] = "NMI", - [DOUBLEFAULT_STACK - 1] = "#DF", - [STACKFAULT_STACK - 1] = "#SS", - [MCE_STACK - 1] = "#MC", - }; - unsigned k; - - for (k = 0; k < N_EXCEPTION_STACKS; k++) { - unsigned long end; - - end = per_cpu(init_tss, cpu).ist[k]; - if (stack >= end) - continue; - if (stack >= end - EXCEPTION_STKSZ) { - if (*usedp & (1U << k)) - break; - *usedp |= 1U << k; - *idp = ids[k]; - return (unsigned long *)end; - } - } - return NULL; -} - -/* - * x86-64 can have upto three kernel stacks: - * process stack - * interrupt stack - * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack - */ - -void show_trace(unsigned long *stack) -{ - unsigned long addr; - const unsigned cpu = safe_smp_processor_id(); - unsigned long *irqstack_end = (unsigned long *)cpu_pda[cpu].irqstackptr; - int i; - unsigned used = 0; - - printk("\nCall Trace:"); - -#define HANDLE_STACK(cond) \ - do while (cond) { \ - addr = *stack++; \ - if (kernel_text_address(addr)) { \ - /* \ - * If the address is either in the text segment of the \ - * kernel, or in the region which contains vmalloc'ed \ - * memory, it *may* be the address of a calling \ - * routine; if so, print it so that someone tracing \ - * down the cause of the crash will be able to figure \ - * out the call path that was taken. \ - */ \ - i += printk_address(addr); \ - if (i > 50) { \ - printk("\n "); \ - i = 0; \ - } \ - else \ - i += printk(" "); \ - } \ - } while (0) - - for(i = 0; ; ) { - const char *id; - unsigned long *estack_end; - estack_end = in_exception_stack(cpu, (unsigned long)stack, - &used, &id); - - if (estack_end) { - i += printk(" <%s> ", id); - HANDLE_STACK (stack < estack_end); - i += printk(" <EOE> "); - stack = (unsigned long *) estack_end[-2]; - continue; - } - if (irqstack_end) { - unsigned long *irqstack; - irqstack = irqstack_end - - (IRQSTACKSIZE - 64) / sizeof(*irqstack); - - if (stack >= irqstack && stack < irqstack_end) { - i += printk(" <IRQ> "); - HANDLE_STACK (stack < irqstack_end); - stack = (unsigned long *) (irqstack_end[-1]); - irqstack_end = NULL; - i += printk(" <EOI> "); - continue; - } - } - break; - } - - HANDLE_STACK (((long) stack & (THREAD_SIZE-1)) != 0); -#undef HANDLE_STACK - printk("\n"); -} - -void show_stack(struct task_struct *tsk, unsigned long * rsp) -{ - unsigned long *stack; - int i; - const int cpu = safe_smp_processor_id(); - unsigned long *irqstack_end = (unsigned long *) (cpu_pda[cpu].irqstackptr); - unsigned long *irqstack = (unsigned long *) (cpu_pda[cpu].irqstackptr - IRQSTACKSIZE); - - // debugging aid: "show_stack(NULL, NULL);" prints the - // back trace for this cpu. - - if (rsp == NULL) { - if (tsk) - rsp = (unsigned long *)tsk->thread.rsp; - else - rsp = (unsigned long *)&rsp; - } - - stack = rsp; - for(i=0; i < kstack_depth_to_print; i++) { - if (stack >= irqstack && stack <= irqstack_end) { - if (stack == irqstack_end) { - stack = (unsigned long *) (irqstack_end[-1]); - printk(" <EOI> "); - } - } else { - if (((long) stack & (THREAD_SIZE-1)) == 0) - break; - } - if (i && ((i % 4) == 0)) - printk("\n "); - printk("%016lx ", *stack++); - touch_nmi_watchdog(); - } - show_trace((unsigned long *)rsp); -} - -/* - * The architecture-independent dump_stack generator - */ -void dump_stack(void) -{ - unsigned long dummy; - show_trace(&dummy); -} - -EXPORT_SYMBOL(dump_stack); - -void show_registers(struct pt_regs *regs) -{ - int i; - int in_kernel = (regs->cs & 3) == 0; - unsigned long rsp; - const int cpu = safe_smp_processor_id(); - struct task_struct *cur = cpu_pda[cpu].pcurrent; - - rsp = regs->rsp; - - printk("CPU %d ", cpu); - __show_regs(regs); - printk("Process %s (pid: %d, threadinfo %p, task %p)\n", - cur->comm, cur->pid, cur->thread_info, cur); - - /* - * When in-kernel, we also print out the stack and code at the - * time of the fault.. - */ - if (in_kernel) { - - printk("Stack: "); - show_stack(NULL, (unsigned long*)rsp); - - printk("\nCode: "); - if(regs->rip < PAGE_OFFSET) - goto bad; - - for(i=0;i<20;i++) - { - unsigned char c; - if(__get_user(c, &((unsigned char*)regs->rip)[i])) { -bad: - printk(" Bad RIP value."); - break; - } - printk("%02x ", c); - } - } - printk("\n"); -} - -void handle_BUG(struct pt_regs *regs) -{ - struct bug_frame f; - char tmp; - - if (regs->cs & 3) - return; - if (__copy_from_user(&f, (struct bug_frame *) regs->rip, - sizeof(struct bug_frame))) - return; - if ((unsigned long)f.filename < __PAGE_OFFSET || - f.ud2[0] != 0x0f || f.ud2[1] != 0x0b) - return; - if (__get_user(tmp, f.filename)) - f.filename = "unmapped filename"; - printk("----------- [cut here ] --------- [please bite here ] ---------\n"); - printk(KERN_ALERT "Kernel BUG at %.50s:%d\n", f.filename, f.line); -} - -#ifdef CONFIG_BUG -void out_of_line_bug(void) -{ - BUG(); -} -#endif - -static DEFINE_SPINLOCK(die_lock); -static int die_owner = -1; - -void oops_begin(void) -{ - int cpu = safe_smp_processor_id(); - /* racy, but better than risking deadlock. */ - local_irq_disable(); - if (!spin_trylock(&die_lock)) { - if (cpu == die_owner) - /* nested oops. should stop eventually */; - else - spin_lock(&die_lock); - } - die_owner = cpu; - console_verbose(); - bust_spinlocks(1); -} - -void oops_end(void) -{ - die_owner = -1; - bust_spinlocks(0); - spin_unlock(&die_lock); - if (panic_on_oops) - panic("Oops"); -} - -void __die(const char * str, struct pt_regs * regs, long err) -{ - static int die_counter; - printk(KERN_EMERG "%s: %04lx [%u] ", str, err & 0xffff,++die_counter); -#ifdef CONFIG_PREEMPT - printk("PREEMPT "); -#endif -#ifdef CONFIG_SMP - printk("SMP "); -#endif -#ifdef CONFIG_DEBUG_PAGEALLOC - printk("DEBUG_PAGEALLOC"); -#endif - printk("\n"); - notify_die(DIE_OOPS, (char *)str, regs, err, 255, SIGSEGV); - show_registers(regs); - /* Executive summary in case the oops scrolled away */ - printk(KERN_ALERT "RIP "); - printk_address(regs->rip); - printk(" RSP <%016lx>\n", regs->rsp); -} - -void die(const char * str, struct pt_regs * regs, long err) -{ - oops_begin(); - handle_BUG(regs); - __die(str, regs, err); - oops_end(); - do_exit(SIGSEGV); -} -static inline void die_if_kernel(const char * str, struct pt_regs * regs, long err) -{ - if (!(regs->eflags & VM_MASK) && (regs->cs == __KERNEL_CS)) - die(str, regs, err); -} - -#ifdef CONFIG_X86_LOCAL_APIC -void die_nmi(char *str, struct pt_regs *regs) -{ - oops_begin(); - /* - * We are in trouble anyway, lets at least try - * to get a message out. - */ - printk(str, safe_smp_processor_id()); - show_registers(regs); - if (panic_on_timeout || panic_on_oops) - panic("nmi watchdog"); - printk("console shuts up ...\n"); - oops_end(); - do_exit(SIGSEGV); -} -#endif - -static void do_trap(int trapnr, int signr, char *str, - struct pt_regs * regs, long error_code, siginfo_t *info) -{ - conditional_sti(regs); - -#ifdef CONFIG_CHECKING - { - unsigned long gs; - struct x8664_pda *pda = cpu_pda + safe_smp_processor_id(); - rdmsrl(MSR_GS_BASE, gs); - if (gs != (unsigned long)pda) { - wrmsrl(MSR_GS_BASE, pda); - printk("%s: wrong gs %lx expected %p rip %lx\n", str, gs, pda, - regs->rip); - } - } -#endif - - if ((regs->cs & 3) != 0) { - struct task_struct *tsk = current; - - if (exception_trace && unhandled_signal(tsk, signr)) - printk(KERN_INFO - "%s[%d] trap %s rip:%lx rsp:%lx error:%lx\n", - tsk->comm, tsk->pid, str, - regs->rip,regs->rsp,error_code); - - tsk->thread.error_code = error_code; - tsk->thread.trap_no = trapnr; - if (info) - force_sig_info(signr, info, tsk); - else - force_sig(signr, tsk); - return; - } - - - /* kernel trap */ - { - const struct exception_table_entry *fixup; - fixup = search_exception_tables(regs->rip); - if (fixup) { - regs->rip = fixup->fixup; - } else - die(str, regs, error_code); - return; - } -} - -#define DO_ERROR(trapnr, signr, str, name) \ -asmlinkage void do_##name(struct pt_regs * regs, long error_code) \ -{ \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ - return; \ - do_trap(trapnr, signr, str, regs, error_code, NULL); \ -} - -#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ -asmlinkage void do_##name(struct pt_regs * regs, long error_code) \ -{ \ - siginfo_t info; \ - info.si_signo = signr; \ - info.si_errno = 0; \ - info.si_code = sicode; \ - info.si_addr = (void __user *)siaddr; \ - if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) \ - == NOTIFY_STOP) \ - return; \ - do_trap(trapnr, signr, str, regs, error_code, &info); \ -} - -DO_ERROR_INFO( 0, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->rip) -DO_ERROR( 4, SIGSEGV, "overflow", overflow) -DO_ERROR( 5, SIGSEGV, "bounds", bounds) -DO_ERROR_INFO( 6, SIGILL, "invalid operand", invalid_op, ILL_ILLOPN, regs->rip) -DO_ERROR( 7, SIGSEGV, "device not available", device_not_available) -DO_ERROR( 9, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun) -DO_ERROR(10, SIGSEGV, "invalid TSS", invalid_TSS) -DO_ERROR(11, SIGBUS, "segment not present", segment_not_present) -DO_ERROR_INFO(17, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0) -DO_ERROR(18, SIGSEGV, "reserved", reserved) -DO_ERROR(12, SIGBUS, "stack segment", stack_segment) -DO_ERROR( 8, SIGSEGV, "double fault", double_fault) - -asmlinkage void do_general_protection(struct pt_regs * regs, long error_code) -{ - conditional_sti(regs); - -#ifdef CONFIG_CHECKING - { - unsigned long gs; - struct x8664_pda *pda = cpu_pda + safe_smp_processor_id(); - rdmsrl(MSR_GS_BASE, gs); - if (gs != (unsigned long)pda) { - wrmsrl(MSR_GS_BASE, pda); - oops_in_progress++; - printk("general protection handler: wrong gs %lx expected %p\n", gs, pda); - oops_in_progress--; - } - } -#endif - - if ((regs->cs & 3)!=0) { - struct task_struct *tsk = current; - - if (exception_trace && unhandled_signal(tsk, SIGSEGV)) - printk(KERN_INFO - "%s[%d] general protection rip:%lx rsp:%lx error:%lx\n", - tsk->comm, tsk->pid, - regs->rip,regs->rsp,error_code); - - tsk->thread.error_code = error_code; - tsk->thread.trap_no = 13; - force_sig(SIGSEGV, tsk); - return; - } - - /* kernel gp */ - { - const struct exception_table_entry *fixup; - fixup = search_exception_tables(regs->rip); - if (fixup) { - regs->rip = fixup->fixup; - return; - } - if (notify_die(DIE_GPF, "general protection fault", regs, - error_code, 13, SIGSEGV) == NOTIFY_STOP) - return; - die("general protection fault", regs, error_code); - } -} - -static void mem_parity_error(unsigned char reason, struct pt_regs * regs) -{ - printk("Uhhuh. NMI received. Dazed and confused, but trying to continue\n"); - printk("You probably have a hardware problem with your RAM chips\n"); - -#if 0 /* XEN */ - /* Clear and disable the memory parity error line. */ - reason = (reason & 0xf) | 4; - outb(reason, 0x61); -#endif /* XEN */ -} - -static void io_check_error(unsigned char reason, struct pt_regs * regs) -{ - printk("NMI: IOCK error (debug interrupt?)\n"); - show_registers(regs); - -#if 0 /* XEN */ - /* Re-enable the IOCK line, wait for a few seconds */ - reason = (reason & 0xf) | 8; - outb(reason, 0x61); - mdelay(2000); - reason &= ~8; - outb(reason, 0x61); -#endif /* XEN */ -} - -static void unknown_nmi_error(unsigned char reason, struct pt_regs * regs) -{ printk("Uhhuh. NMI received for unknown reason %02x.\n", reason); - printk("Dazed and confused, but trying to continue\n"); - printk("Do you have a strange power saving mode enabled?\n"); -} - -/* Runs on IST stack. This code must keep interrupts off all the time. - Nested NMIs are prevented by the CPU. */ -asmlinkage void default_do_nmi(struct pt_regs *regs) -{ - unsigned char reason = 0; - - /* Only the BSP gets external NMIs from the system. */ - if (!smp_processor_id()) - reason = get_nmi_reason(); - - if (!(reason & 0xc0)) { - if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 0, SIGINT) - == NOTIFY_STOP) - return; -#ifdef CONFIG_X86_LOCAL_APIC - /* - * Ok, so this is none of the documented NMI sources, - * so it must be the NMI watchdog. - */ - if (nmi_watchdog > 0) { - nmi_watchdog_tick(regs,reason); - return; - } -#endif - unknown_nmi_error(reason, regs); - return; - } - if (notify_die(DIE_NMI, "nmi", regs, reason, 0, SIGINT) == NOTIFY_STOP) - return; - - /* AK: following checks seem to be broken on modern chipsets. FIXME */ - - if (reason & 0x80) - mem_parity_error(reason, regs); - if (reason & 0x40) - io_check_error(reason, regs); -} - -asmlinkage void do_int3(struct pt_regs * regs, long error_code) -{ - if (notify_die(DIE_INT3, "int3", regs, error_code, 3, SIGTRAP) == NOTIFY_STOP) { - return; - } - do_trap(3, SIGTRAP, "int3", regs, error_code, NULL); - return; -} - -/* Help handler running on IST stack to switch back to user stack - for scheduling or signal handling. The actual stack switch is done in - entry.S */ -asmlinkage struct pt_regs *sync_regs(struct pt_regs *eregs) -{ - struct pt_regs *regs = eregs; - /* Did already sync */ - if (eregs == (struct pt_regs *)eregs->rsp) - ; - /* Exception from user space */ - else if (eregs->cs & 3) - regs = ((struct pt_regs *)current->thread.rsp0) - 1; - /* Exception from kernel and interrupts are enabled. Move to - kernel process stack. */ - else if (eregs->eflags & X86_EFLAGS_IF) - regs = (struct pt_regs *)(eregs->rsp -= sizeof(struct pt_regs)); - if (eregs != regs) - *regs = *eregs; - return regs; -} - -/* runs on IST stack. */ -asmlinkage void do_debug(struct pt_regs * regs, unsigned long error_code) -{ - unsigned long condition; - struct task_struct *tsk = current; - siginfo_t info; - -#ifdef CONFIG_CHECKING - { - /* RED-PEN interaction with debugger - could destroy gs */ - unsigned long gs; - struct x8664_pda *pda = cpu_pda + safe_smp_processor_id(); - rdmsrl(MSR_GS_BASE, gs); - if (gs != (unsigned long)pda) { - wrmsrl(MSR_GS_BASE, pda); - printk("debug handler: wrong gs %lx expected %p\n", gs, pda); - } - } -#endif - - asm("movq %%db6,%0" : "=r" (condition)); - - if (notify_die(DIE_DEBUG, "debug", regs, condition, error_code, - SIGTRAP) == NOTIFY_STOP) - return; - - conditional_sti(regs); - - /* Mask out spurious debug traps due to lazy DR7 setting */ - if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) { - if (!tsk->thread.debugreg7) { - goto clear_dr7; - } - } - - tsk->thread.debugreg6 = condition; - - /* Mask out spurious TF errors due to lazy TF clearing */ - if (condition & DR_STEP) { - /* - * The TF error should be masked out only if the current - * process is not traced and if the TRAP flag has been set - * previously by a tracing process (condition detected by - * the PT_DTRACE flag); remember that the i386 TRAP flag - * can be modified by the process itself in user mode, - * allowing programs to debug themselves without the ptrace() - * interface. - */ - if ((regs->cs & 3) == 0) - goto clear_TF_reenable; - /* - * Was the TF flag set by a debugger? If so, clear it now, - * so that register information is correct. - */ - if (tsk->ptrace & PT_DTRACE) { - regs->eflags &= ~TF_MASK; - tsk->ptrace &= ~PT_DTRACE; - } - } - - /* Ok, finally something we can handle */ - tsk->thread.trap_no = 1; - tsk->thread.error_code = error_code; - info.si_signo = SIGTRAP; - info.si_errno = 0; - info.si_code = TRAP_BRKPT; - if ((regs->cs & 3) == 0) - goto clear_dr7; - - info.si_addr = (void __user *)regs->rip; - force_sig_info(SIGTRAP, &info, tsk); -clear_dr7: - asm volatile("movq %0,%%db7"::"r"(0UL)); - return; - -clear_TF_reenable: - set_tsk_thread_flag(tsk, TIF_SINGLESTEP); - regs->eflags &= ~TF_MASK; -} - -static int kernel_math_error(struct pt_regs *regs, char *str) -{ - const struct exception_table_entry *fixup; - fixup = search_exception_tables(regs->rip); - if (fixup) { - regs->rip = fixup->fixup; - return 1; - } - notify_die(DIE_GPF, str, regs, 0, 16, SIGFPE); - /* Illegal floating point operation in the kernel */ - die(str, regs, 0); - return 0; -} - -/* - * Note that we play around with the 'TS' bit in an attempt to get - * the correct behaviour even in the presence of the asynchronous - * IRQ13 behaviour - */ -asmlinkage void do_coprocessor_error(struct pt_regs *regs) -{ - void __user *rip = (void __user *)(regs->rip); - struct task_struct * task; - siginfo_t info; - unsigned short cwd, swd; - - conditional_sti(regs); - if ((regs->cs & 3) == 0 && - kernel_math_error(regs, "kernel x87 math error")) - return; - - /* - * Save the info for the exception handler and clear the error. - */ - task = current; - save_init_fpu(task); - task->thread.trap_no = 16; - task->thread.error_code = 0; - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_code = __SI_FAULT; - info.si_addr = rip; - /* - * (~cwd & swd) will mask out exceptions that are not set to unmasked - * status. 0x3f is the exception bits in these regs, 0x200 is the - * C1 reg you need in case of a stack fault, 0x040 is the stack - * fault bit. We should only be taking one exception at a time, - * so if this combination doesn't produce any single exception, - * then we have a bad program that isn't synchronizing its FPU usage - * and it will suffer the consequences since we won't be able to - * fully reproduce the context of the exception - */ - cwd = get_fpu_cwd(task); - swd = get_fpu_swd(task); - switch (((~cwd) & swd & 0x3f) | (swd & 0x240)) { - case 0x000: - default: - break; - case 0x001: /* Invalid Op */ - case 0x041: /* Stack Fault */ - case 0x241: /* Stack Fault | Direction */ - info.si_code = FPE_FLTINV; - break; - case 0x002: /* Denormalize */ - case 0x010: /* Underflow */ - info.si_code = FPE_FLTUND; - break; - case 0x004: /* Zero Divide */ - info.si_code = FPE_FLTDIV; - break; - case 0x008: /* Overflow */ - info.si_code = FPE_FLTOVF; - break; - case 0x020: /* Precision */ - info.si_code = FPE_FLTRES; - break; - } - force_sig_info(SIGFPE, &info, task); -} - -asmlinkage void bad_intr(void) -{ - printk("bad interrupt"); -} - -asmlinkage void do_simd_coprocessor_error(struct pt_regs *regs) -{ - void __user *rip = (void __user *)(regs->rip); - struct task_struct * task; - siginfo_t info; - unsigned short mxcsr; - - conditional_sti(regs); - if ((regs->cs & 3) == 0 && - kernel_math_error(regs, "kernel simd math error")) - return; - - /* - * Save the info for the exception handler and clear the error. - */ - task = current; - save_init_fpu(task); - task->thread.trap_no = 19; - task->thread.error_code = 0; - info.si_signo = SIGFPE; - info.si_errno = 0; - info.si_code = __SI_FAULT; - info.si_addr = rip; - /* - * The SIMD FPU exceptions are handled a little differently, as there - * is only a single status/control register. Thus, to determine which - * unmasked exception was caught we must mask the exception mask bits - * at 0x1f80, and then use these to mask the exception bits at 0x3f. - */ - mxcsr = get_fpu_mxcsr(task); - switch (~((mxcsr & 0x1f80) >> 7) & (mxcsr & 0x3f)) { - case 0x000: - default: - break; - case 0x001: /* Invalid Op */ - info.si_code = FPE_FLTINV; - break; - case 0x002: /* Denormalize */ - case 0x010: /* Underflow */ - info.si_code = FPE_FLTUND; - break; - case 0x004: /* Zero Divide */ - info.si_code = FPE_FLTDIV; - break; - case 0x008: /* Overflow */ - info.si_code = FPE_FLTOVF; - break; - case 0x020: /* Precision */ - info.si_code = FPE_FLTRES; - break; - } - force_sig_info(SIGFPE, &info, task); -} - -asmlinkage void do_spurious_interrupt_bug(struct pt_regs * regs) -{ -} - -#if 0 -asmlinkage void __attribute__((weak)) smp_thermal_interrupt(void) -{ -} -#endif - -/* - * 'math_state_restore()' saves the current math information in the - * old math state array, and gets the new ones from the current task - * - * Careful.. There are problems with IBM-designed IRQ13 behaviour. - * Don't touch unless you *really* know how it works. - */ -asmlinkage void math_state_restore(void) -{ - struct task_struct *me = current; - /* clts(); */ /* 'clts' is done for us by Xen during virtual trap. */ - - if (!used_math()) - init_fpu(me); - restore_fpu_checking(&me->thread.i387.fxsave); - me->thread_info->status |= TS_USEDFPU; -} - -void do_call_debug(struct pt_regs *regs) -{ - notify_die(DIE_CALL, "debug call", regs, 0, 255, SIGINT); -} - - -/* - * NB. All these are "interrupt gates" (i.e. events_mask is set) because we - * specify <dpl>|4 in the second field. - */ -static trap_info_t trap_table[] = { - { 0, 0|4, (__KERNEL_CS|0x3), (unsigned long)divide_error }, - { 1, 0|4, (__KERNEL_CS|0x3), (unsigned long)debug }, - { 3, 3|4, (__KERNEL_CS|0x3), (unsigned long)int3 }, - { 4, 3|4, (__KERNEL_CS|0x3), (unsigned long)overflow }, - { 5, 3|4, (__KERNEL_CS|0x3), (unsigned long)bounds }, - { 6, 0|4, (__KERNEL_CS|0x3), (unsigned long)invalid_op }, - { 7, 0|4, (__KERNEL_CS|0x3), (unsigned long)device_not_available }, - { 9, 0|4, (__KERNEL_CS|0x3), (unsigned long)coprocessor_segment_overrun}, - { 10, 0|4, (__KERNEL_CS|0x3), (unsigned long)invalid_TSS }, - { 11, 0|4, (__KERNEL_CS|0x3), (unsigned long)segment_not_present }, - { 12, 0|4, (__KERNEL_CS|0x3), (unsigned long)stack_segment }, - { 13, 0|4, (__KERNEL_CS|0x3), (unsigned long)general_protection }, - { 14, 0|4, (__KERNEL_CS|0x3), (unsigned long)page_fault }, - { 15, 0|4, (__KERNEL_CS|0x3), (unsigned long)spurious_interrupt_bug }, - { 16, 0|4, (__KERNEL_CS|0x3), (unsigned long)coprocessor_error }, - { 17, 0|4, (__KERNEL_CS|0x3), (unsigned long)alignment_check }, -#ifdef CONFIG_X86_MCE - { 18, 0|4, (__KERNEL_CS|0x3), (unsigned long)machine_check }, -#endif - { 19, 0|4, (__KERNEL_CS|0x3), (unsigned long)simd_coprocessor_error }, -#ifdef CONFIG_IA32_EMULATION - { IA32_SYSCALL_VECTOR, 3|4, (__KERNEL_CS|0x3), (unsigned long)ia32_syscall}, -#endif - { 0, 0, 0, 0 } -}; - -void __init trap_init(void) -{ - int ret; - - ret = HYPERVISOR_set_trap_table(trap_table); - - if (ret) - printk("HYPERVISOR_set_trap_table faild: error %d\n", - ret); - -#ifdef CONFIG_IA32_EMULATION - set_system_gate(IA32_SYSCALL_VECTOR, ia32_syscall); -#endif - - /* - * Should be a barrier for any external CPU state. - */ - cpu_init(); -} - -void smp_trap_init(trap_info_t *trap_ctxt) -{ - trap_info_t *t = trap_table; - int i; - - for (i = 0; i < 256; i++) { - trap_ctxt[i].vector = i; - trap_ctxt[i].cs = FLAT_KERNEL_CS; - } - - for (t = trap_table; t->address; t++) { - trap_ctxt[t->vector].flags = t->flags; - trap_ctxt[t->vector].cs = t->cs; - trap_ctxt[t->vector].address = t->address; - } -} - - -/* Actual parsing is done early in setup.c. */ -static int __init oops_dummy(char *s) -{ - panic_on_oops = 1; - return -1; -} -__setup("oops=", oops_dummy); - -static int __init kstack_setup(char *s) -{ - kstack_depth_to_print = simple_strtoul(s,NULL,0); - return 0; -} -__setup("kstack=", kstack_setup); - diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/vsyscall.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/vsyscall.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,241 +0,0 @@ -/* - * linux/arch/x86_64/kernel/vsyscall.c - * - * Copyright (C) 2001 Andrea Arcangeli <andrea@xxxxxxx> SuSE - * Copyright 2003 Andi Kleen, SuSE Labs. - * - * Thanks to hpa@xxxxxxxxxxxxx for some useful hint. - * Special thanks to Ingo Molnar for his early experience with - * a different vsyscall implementation for Linux/IA32 and for the name. - * - * vsyscall 1 is located at -10Mbyte, vsyscall 2 is located - * at virtual address -10Mbyte+1024bytes etc... There are at max 4 - * vsyscalls. One vsyscall can reserve more than 1 slot to avoid - * jumping out of line if necessary. We cannot add more with this - * mechanism because older kernels won't return -ENOSYS. - * If we want more than four we need a vDSO. - * - * Note: the concept clashes with user mode linux. If you use UML and - * want per guest time just set the kernel.vsyscall64 sysctl to 0. - */ - -#include <linux/time.h> -#include <linux/init.h> -#include <linux/kernel.h> -#include <linux/timer.h> -#include <linux/seqlock.h> -#include <linux/jiffies.h> -#include <linux/sysctl.h> - -#include <asm/vsyscall.h> -#include <asm/pgtable.h> -#include <asm/page.h> -#include <asm/fixmap.h> -#include <asm/errno.h> -#include <asm/io.h> - -#define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr))) -#define force_inline __attribute__((always_inline)) inline - -int __sysctl_vsyscall __section_sysctl_vsyscall = 1; -seqlock_t __xtime_lock __section_xtime_lock = SEQLOCK_UNLOCKED; - -#include <asm/unistd.h> - -static force_inline void timeval_normalize(struct timeval * tv) -{ - time_t __sec; - - __sec = tv->tv_usec / 1000000; - if (__sec) { - tv->tv_usec %= 1000000; - tv->tv_sec += __sec; - } -} - -static force_inline void do_vgettimeofday(struct timeval * tv) -{ - long sequence, t; - unsigned long sec, usec; - - do { - sequence = read_seqbegin(&__xtime_lock); - - sec = __xtime.tv_sec; - usec = (__xtime.tv_nsec / 1000) + - (__jiffies - __wall_jiffies) * (1000000 / HZ); - - if (__vxtime.mode != VXTIME_HPET) { - sync_core(); - rdtscll(t); - if (t < __vxtime.last_tsc) - t = __vxtime.last_tsc; - usec += ((t - __vxtime.last_tsc) * - __vxtime.tsc_quot) >> 32; - /* See comment in x86_64 do_gettimeofday. */ - } else { - usec += ((readl((void *)fix_to_virt(VSYSCALL_HPET) + 0xf0) - - __vxtime.last) * __vxtime.quot) >> 32; - } - } while (read_seqretry(&__xtime_lock, sequence)); - - tv->tv_sec = sec + usec / 1000000; - tv->tv_usec = usec % 1000000; -} - -/* RED-PEN may want to readd seq locking, but then the variable should be write-once. */ -static force_inline void do_get_tz(struct timezone * tz) -{ - *tz = __sys_tz; -} - -static force_inline int gettimeofday(struct timeval *tv, struct timezone *tz) -{ - int ret; - asm volatile("vsysc2: syscall" - : "=a" (ret) - : "0" (__NR_gettimeofday),"D" (tv),"S" (tz) : __syscall_clobber ); - return ret; -} - -static force_inline long time_syscall(long *t) -{ - long secs; - asm volatile("vsysc1: syscall" - : "=a" (secs) - : "0" (__NR_time),"D" (t) : __syscall_clobber); - return secs; -} - -static int __vsyscall(0) vgettimeofday(struct timeval * tv, struct timezone * tz) -{ - if (unlikely(!__sysctl_vsyscall)) - return gettimeofday(tv,tz); - if (tv) - do_vgettimeofday(tv); - if (tz) - do_get_tz(tz); - return 0; -} - -/* This will break when the xtime seconds get inaccurate, but that is - * unlikely */ -static time_t __vsyscall(1) vtime(time_t *t) -{ - if (unlikely(!__sysctl_vsyscall)) - return time_syscall(t); - else if (t) - *t = __xtime.tv_sec; - return __xtime.tv_sec; -} - -static long __vsyscall(2) venosys_0(void) -{ - return -ENOSYS; -} - -static long __vsyscall(3) venosys_1(void) -{ - return -ENOSYS; -} - -#ifdef CONFIG_SYSCTL - -#define SYSCALL 0x050f -#define NOP2 0x9090 - -/* - * NOP out syscall in vsyscall page when not needed. - */ -static int vsyscall_sysctl_change(ctl_table *ctl, int write, struct file * filp, - void __user *buffer, size_t *lenp, loff_t *ppos) -{ - extern u16 vsysc1, vsysc2; - u16 *map1, *map2; - int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); - if (!write) - return ret; - /* gcc has some trouble with __va(__pa()), so just do it this - way. */ - map1 = ioremap(__pa_symbol(&vsysc1), 2); - if (!map1) - return -ENOMEM; - map2 = ioremap(__pa_symbol(&vsysc2), 2); - if (!map2) { - ret = -ENOMEM; - goto out; - } - if (!sysctl_vsyscall) { - *map1 = SYSCALL; - *map2 = SYSCALL; - } else { - *map1 = NOP2; - *map2 = NOP2; - } - iounmap(map2); -out: - iounmap(map1); - return ret; -} - -static int vsyscall_sysctl_nostrat(ctl_table *t, int __user *name, int nlen, - void __user *oldval, size_t __user *oldlenp, - void __user *newval, size_t newlen, - void **context) -{ - return -ENOSYS; -} - -static ctl_table kernel_table2[] = { - { .ctl_name = 99, .procname = "vsyscall64", - .data = &sysctl_vsyscall, .maxlen = sizeof(int), .mode = 0644, - .strategy = vsyscall_sysctl_nostrat, - .proc_handler = vsyscall_sysctl_change }, - { 0, } -}; - -static ctl_table kernel_root_table2[] = { - { .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, - .child = kernel_table2 }, - { 0 }, -}; - -#endif - -static void __init map_vsyscall(void) -{ - extern char __vsyscall_0; - unsigned long physaddr_page0 = __pa_symbol(&__vsyscall_0); - - __set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_page0, PAGE_KERNEL_VSYSCALL); -} - -#ifdef CONFIG_XEN -static void __init map_vsyscall_user(void) -{ - extern void __set_fixmap_user(enum fixed_addresses, unsigned long, pgprot_t); - extern char __vsyscall_0; - unsigned long physaddr_page0 = __pa_symbol(&__vsyscall_0); - - __set_fixmap_user(VSYSCALL_FIRST_PAGE, physaddr_page0, PAGE_KERNEL_VSYSCALL); -} -#endif - -static int __init vsyscall_init(void) -{ - BUG_ON(((unsigned long) &vgettimeofday != - VSYSCALL_ADDR(__NR_vgettimeofday))); - BUG_ON((unsigned long) &vtime != VSYSCALL_ADDR(__NR_vtime)); - BUG_ON((VSYSCALL_ADDR(0) != __fix_to_virt(VSYSCALL_FIRST_PAGE))); - map_vsyscall(); -#ifdef CONFIG_XEN - map_vsyscall_user(); - sysctl_vsyscall = 0; /* disable vgettimeofay() */ -#endif -#ifdef CONFIG_SYSCTL - register_sysctl_table(kernel_root_table2, 0); -#endif - return 0; -} - -__initcall(vsyscall_init); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/x8664_ksyms.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/x8664_ksyms.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,208 +0,0 @@ -#include <linux/config.h> -#include <linux/module.h> -#include <linux/smp.h> -#include <linux/user.h> -#include <linux/sched.h> -#include <linux/in6.h> -#include <linux/interrupt.h> -#include <linux/smp_lock.h> -#include <linux/pm.h> -#include <linux/pci.h> -#include <linux/apm_bios.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/syscalls.h> -#include <linux/tty.h> -#include <linux/ioctl32.h> - -#include <asm/semaphore.h> -#include <asm/processor.h> -#include <asm/i387.h> -#include <asm/uaccess.h> -#include <asm/checksum.h> -#include <asm/io.h> -#include <asm/delay.h> -#include <asm/irq.h> -#include <asm/mmx.h> -#include <asm/desc.h> -#include <asm/pgtable.h> -#include <asm/pgalloc.h> -#include <asm/nmi.h> -#include <asm/kdebug.h> -#include <asm/unistd.h> -#include <asm/tlbflush.h> -#include <asm/kdebug.h> - -extern spinlock_t rtc_lock; - -#ifdef CONFIG_SMP -extern void __write_lock_failed(rwlock_t *rw); -extern void __read_lock_failed(rwlock_t *rw); -#endif - -#if defined(CONFIG_BLK_DEV_IDE) || defined(CONFIG_BLK_DEV_HD) || defined(CONFIG_BLK_DEV_IDE_MODULE) || defined(CONFIG_BLK_DEV_HD_MODULE) -extern struct drive_info_struct drive_info; -EXPORT_SYMBOL(drive_info); -#endif - -extern unsigned long get_cmos_time(void); - -/* platform dependent support */ -EXPORT_SYMBOL(boot_cpu_data); -//EXPORT_SYMBOL(dump_fpu); -EXPORT_SYMBOL(__ioremap); -EXPORT_SYMBOL(ioremap_nocache); -EXPORT_SYMBOL(iounmap); -EXPORT_SYMBOL(enable_irq); -EXPORT_SYMBOL(disable_irq); -EXPORT_SYMBOL(disable_irq_nosync); -EXPORT_SYMBOL(probe_irq_mask); -EXPORT_SYMBOL(kernel_thread); -EXPORT_SYMBOL(pm_idle); -EXPORT_SYMBOL(pm_power_off); -EXPORT_SYMBOL(get_cmos_time); - -EXPORT_SYMBOL(__down_failed); -EXPORT_SYMBOL(__down_failed_interruptible); -EXPORT_SYMBOL(__down_failed_trylock); -EXPORT_SYMBOL(__up_wakeup); -/* Networking helper routines. */ -EXPORT_SYMBOL(csum_partial_copy_nocheck); -EXPORT_SYMBOL(ip_compute_csum); -/* Delay loops */ -EXPORT_SYMBOL(__udelay); -EXPORT_SYMBOL(__ndelay); -EXPORT_SYMBOL(__delay); -EXPORT_SYMBOL(__const_udelay); - -EXPORT_SYMBOL(__get_user_1); -EXPORT_SYMBOL(__get_user_2); -EXPORT_SYMBOL(__get_user_4); -EXPORT_SYMBOL(__get_user_8); -EXPORT_SYMBOL(__put_user_1); -EXPORT_SYMBOL(__put_user_2); -EXPORT_SYMBOL(__put_user_4); -EXPORT_SYMBOL(__put_user_8); - -EXPORT_SYMBOL(strpbrk); -EXPORT_SYMBOL(strstr); - -EXPORT_SYMBOL(strncpy_from_user); -EXPORT_SYMBOL(__strncpy_from_user); -EXPORT_SYMBOL(clear_user); -EXPORT_SYMBOL(__clear_user); -EXPORT_SYMBOL(copy_user_generic); -EXPORT_SYMBOL(copy_from_user); -EXPORT_SYMBOL(copy_to_user); -EXPORT_SYMBOL(copy_in_user); -EXPORT_SYMBOL(strnlen_user); - -#ifdef CONFIG_PCI -EXPORT_SYMBOL(pci_alloc_consistent); -EXPORT_SYMBOL(pci_free_consistent); -#endif - -#ifdef CONFIG_PCI -EXPORT_SYMBOL(pci_mem_start); -#endif - -EXPORT_SYMBOL(copy_page); -EXPORT_SYMBOL(clear_page); - -EXPORT_SYMBOL(cpu_pda); -#ifdef CONFIG_SMP -EXPORT_SYMBOL(__write_lock_failed); -EXPORT_SYMBOL(__read_lock_failed); - -EXPORT_SYMBOL(synchronize_irq); -EXPORT_SYMBOL(smp_call_function); -#endif - -#ifdef CONFIG_VT -EXPORT_SYMBOL(screen_info); -#endif - -EXPORT_SYMBOL(get_wchan); - -EXPORT_SYMBOL(rtc_lock); - -#ifdef CONFIG_X86_LOCAL_APIC -EXPORT_SYMBOL_GPL(set_nmi_callback); -EXPORT_SYMBOL_GPL(unset_nmi_callback); -#endif - -/* Export string functions. We normally rely on gcc builtin for most of these, - but gcc sometimes decides not to inline them. */ -#undef memcpy -#undef memset -#undef memmove -#undef memchr -#undef strlen -#undef strncmp -#undef strncpy -#undef strchr - -extern void * memset(void *,int,__kernel_size_t); -extern size_t strlen(const char *); -extern void * memmove(void * dest,const void *src,size_t count); -extern void *memchr(const void *s, int c, size_t n); -extern void * memcpy(void *,const void *,__kernel_size_t); -extern void * __memcpy(void *,const void *,__kernel_size_t); - -EXPORT_SYMBOL(memset); -EXPORT_SYMBOL(strlen); -EXPORT_SYMBOL(memmove); -EXPORT_SYMBOL(strncmp); -EXPORT_SYMBOL(strncpy); -EXPORT_SYMBOL(strchr); -EXPORT_SYMBOL(strncat); -EXPORT_SYMBOL(memchr); -EXPORT_SYMBOL(strrchr); -EXPORT_SYMBOL(strnlen); -EXPORT_SYMBOL(memscan); -EXPORT_SYMBOL(memcpy); -EXPORT_SYMBOL(__memcpy); - -#ifdef CONFIG_RWSEM_XCHGADD_ALGORITHM -/* prototypes are wrong, these are assembly with custom calling functions */ -extern void rwsem_down_read_failed_thunk(void); -extern void rwsem_wake_thunk(void); -extern void rwsem_downgrade_thunk(void); -extern void rwsem_down_write_failed_thunk(void); -EXPORT_SYMBOL(rwsem_down_read_failed_thunk); -EXPORT_SYMBOL(rwsem_wake_thunk); -EXPORT_SYMBOL(rwsem_downgrade_thunk); -EXPORT_SYMBOL(rwsem_down_write_failed_thunk); -#endif - -EXPORT_SYMBOL(empty_zero_page); - -#ifdef CONFIG_HAVE_DEC_LOCK -EXPORT_SYMBOL(_atomic_dec_and_lock); -#endif - -EXPORT_SYMBOL(die_chain); -EXPORT_SYMBOL(register_die_notifier); - -#ifdef CONFIG_SMP -EXPORT_SYMBOL(cpu_sibling_map); -EXPORT_SYMBOL(smp_num_siblings); -#endif - -extern void do_softirq_thunk(void); -EXPORT_SYMBOL(do_softirq_thunk); - -#ifdef CONFIG_BUG -EXPORT_SYMBOL(out_of_line_bug); -#endif - -EXPORT_SYMBOL(init_level4_pgt); - -extern unsigned long __supported_pte_mask; -EXPORT_SYMBOL(__supported_pte_mask); - -#ifdef CONFIG_SMP -EXPORT_SYMBOL(flush_tlb_page); -#endif - -EXPORT_SYMBOL(cpu_khz); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/kernel/xen_entry.S --- a/linux-2.6-xen-sparse/arch/xen/x86_64/kernel/xen_entry.S Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,41 +0,0 @@ -/* - * Copied from arch/xen/i386/kernel/entry.S - */ -/* Offsets into shared_info_t. */ -#define evtchn_upcall_pending 0 -#define evtchn_upcall_mask 1 - -#define sizeof_vcpu_shift 6 - -#ifdef CONFIG_SMP -//#define preempt_disable(reg) incl threadinfo_preempt_count(reg) -//#define preempt_enable(reg) decl threadinfo_preempt_count(reg) -#define preempt_disable(reg) -#define preempt_enable(reg) -#define XEN_GET_VCPU_INFO(reg) preempt_disable(%rbp) ; \ - movq %gs:pda_cpunumber,reg ; \ - shl $32, reg ; \ - shr $32-sizeof_vcpu_shift,reg ; \ - addq HYPERVISOR_shared_info,reg -#define XEN_PUT_VCPU_INFO(reg) preempt_enable(%rbp) ; \ -#define XEN_PUT_VCPU_INFO_fixup .byte 0xff,0xff,0xff -#else -#define XEN_GET_VCPU_INFO(reg) movq HYPERVISOR_shared_info,reg -#define XEN_PUT_VCPU_INFO(reg) -#define XEN_PUT_VCPU_INFO_fixup -#endif - -#define XEN_LOCKED_BLOCK_EVENTS(reg) movb $1,evtchn_upcall_mask(reg) -#define XEN_LOCKED_UNBLOCK_EVENTS(reg) movb $0,evtchn_upcall_mask(reg) -#define XEN_BLOCK_EVENTS(reg) XEN_GET_VCPU_INFO(reg) ; \ - XEN_LOCKED_BLOCK_EVENTS(reg) ; \ - XEN_PUT_VCPU_INFO(reg) -#define XEN_UNBLOCK_EVENTS(reg) XEN_GET_VCPU_INFO(reg) ; \ - XEN_LOCKED_UNBLOCK_EVENTS(reg) ; \ - XEN_PUT_VCPU_INFO(reg) -#define XEN_TEST_PENDING(reg) testb $0xFF,evtchn_upcall_pending(reg) - -EVENT_MASK = (CS+4) -VGCF_IN_SYSCALL = (1<<8) - - diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/mm/Makefile --- a/linux-2.6-xen-sparse/arch/xen/x86_64/mm/Makefile Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,31 +0,0 @@ -# -# Makefile for the linux x86_64-specific parts of the memory manager. -# - -XENARCH := $(subst ",,$(CONFIG_XENARCH)) - -CFLAGS += -Iarch/$(XENARCH)/mm - -obj-y := init.o fault.o pageattr.o -c-obj-y := extable.o - -i386-obj-y := hypervisor.o ioremap.o - -#obj-y := init.o fault.o ioremap.o extable.o pageattr.o -#c-obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -c-obj-$(CONFIG_DISCONTIGMEM) += numa.o -c-obj-$(CONFIG_K8_NUMA) += k8topology.o - -hugetlbpage-y = ../../../i386/mm/hugetlbpage.o - -c-link := - -$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)): - @ln -fsn $(srctree)/arch/x86_64/mm/$(notdir $@) $@ - -$(patsubst %.o,$(obj)/%.c,$(i386-obj-y)): - ln -fsn $(srctree)/arch/xen/i386/mm/$(notdir $@) $@ - -obj-y += $(c-obj-y) $(i386-obj-y) - -clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link) $(i386-obj-y)) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/mm/fault.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/mm/fault.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,596 +0,0 @@ -/* - * linux/arch/x86-64/mm/fault.c - * - * Copyright (C) 1995 Linus Torvalds - * Copyright (C) 2001,2002 Andi Kleen, SuSE Labs. - */ - -#include <linux/config.h> -#include <linux/signal.h> -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/string.h> -#include <linux/types.h> -#include <linux/ptrace.h> -#include <linux/mman.h> -#include <linux/mm.h> -#include <linux/smp.h> -#include <linux/smp_lock.h> -#include <linux/interrupt.h> -#include <linux/init.h> -#include <linux/tty.h> -#include <linux/vt_kern.h> /* For unblank_screen() */ -#include <linux/compiler.h> -#include <linux/module.h> -#include <linux/percpu.h> -#include <linux/kprobes.h> - -#include <asm/system.h> -#include <asm/uaccess.h> -#include <asm/pgalloc.h> -#include <asm/smp.h> -#include <asm/tlbflush.h> -#include <asm/proto.h> -#include <asm/kdebug.h> -#include <asm-generic/sections.h> -#include <asm/kdebug.h> - -DEFINE_PER_CPU(pgd_t *, cur_pgd); - -void bust_spinlocks(int yes) -{ - int loglevel_save = console_loglevel; - if (yes) { - oops_in_progress = 1; - } else { -#ifdef CONFIG_VT - unblank_screen(); -#endif - oops_in_progress = 0; - /* - * OK, the message is on the console. Now we call printk() - * without oops_in_progress set so that printk will give klogd - * a poke. Hold onto your hats... - */ - console_loglevel = 15; /* NMI oopser may have shut the console up */ - printk(" "); - console_loglevel = loglevel_save; - } -} - -/* Sometimes the CPU reports invalid exceptions on prefetch. - Check that here and ignore. - Opcode checker based on code by Richard Brunner */ -static noinline int is_prefetch(struct pt_regs *regs, unsigned long addr, - unsigned long error_code) -{ - unsigned char *instr; - int scan_more = 1; - int prefetch = 0; - unsigned char *max_instr; - - /* If it was a exec fault ignore */ - if (error_code & (1<<4)) - return 0; - - instr = (unsigned char *)convert_rip_to_linear(current, regs); - max_instr = instr + 15; - - if ((regs->cs & 3) != 0 && instr >= (unsigned char *)TASK_SIZE) - return 0; - - while (scan_more && instr < max_instr) { - unsigned char opcode; - unsigned char instr_hi; - unsigned char instr_lo; - - if (__get_user(opcode, instr)) - break; - - instr_hi = opcode & 0xf0; - instr_lo = opcode & 0x0f; - instr++; - - switch (instr_hi) { - case 0x20: - case 0x30: - /* Values 0x26,0x2E,0x36,0x3E are valid x86 - prefixes. In long mode, the CPU will signal - invalid opcode if some of these prefixes are - present so we will never get here anyway */ - scan_more = ((instr_lo & 7) == 0x6); - break; - - case 0x40: - /* In AMD64 long mode, 0x40 to 0x4F are valid REX prefixes - Need to figure out under what instruction mode the - instruction was issued ... */ - /* Could check the LDT for lm, but for now it's good - enough to assume that long mode only uses well known - segments or kernel. */ - scan_more = ((regs->cs & 3) == 0) || (regs->cs == __USER_CS); - break; - - case 0x60: - /* 0x64 thru 0x67 are valid prefixes in all modes. */ - scan_more = (instr_lo & 0xC) == 0x4; - break; - case 0xF0: - /* 0xF0, 0xF2, and 0xF3 are valid prefixes in all modes. */ - scan_more = !instr_lo || (instr_lo>>1) == 1; - break; - case 0x00: - /* Prefetch instruction is 0x0F0D or 0x0F18 */ - scan_more = 0; - if (__get_user(opcode, instr)) - break; - prefetch = (instr_lo == 0xF) && - (opcode == 0x0D || opcode == 0x18); - break; - default: - scan_more = 0; - break; - } - } - return prefetch; -} - -static int bad_address(void *p) -{ - unsigned long dummy; - return __get_user(dummy, (unsigned long *)p); -} - -void dump_pagetable(unsigned long address) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - preempt_disable(); - pgd = (pgd_t *)per_cpu(cur_pgd, smp_processor_id()); - preempt_enable(); - pgd += pgd_index(address); - printk("PGD %lx ", pgd_val(*pgd)); - if (bad_address(pgd)) goto bad; - if (!pgd_present(*pgd)) goto ret; - - pud = __pud_offset_k((pud_t *)pgd_page(*pgd), address); - if (bad_address(pud)) goto bad; - printk("PUD %lx ", pud_val(*pud)); - if (!pud_present(*pud)) goto ret; - - pmd = pmd_offset(pud, address); - if (bad_address(pmd)) goto bad; - printk("PMD %lx ", pmd_val(*pmd)); - if (!pmd_present(*pmd)) goto ret; - - pte = pte_offset_kernel(pmd, address); - if (bad_address(pte)) goto bad; - printk("PTE %lx", pte_val(*pte)); -ret: - printk("\n"); - return; -bad: - printk("BAD\n"); -} - -static const char errata93_warning[] = -KERN_ERR "******* Your BIOS seems to not contain a fix for K8 errata #93\n" -KERN_ERR "******* Working around it, but it may cause SEGVs or burn power.\n" -KERN_ERR "******* Please consider a BIOS update.\n" -KERN_ERR "******* Disabling USB legacy in the BIOS may also help.\n"; - -/* Workaround for K8 erratum #93 & buggy BIOS. - BIOS SMM functions are required to use a specific workaround - to avoid corruption of the 64bit RIP register on C stepping K8. - A lot of BIOS that didn't get tested properly miss this. - The OS sees this as a page fault with the upper 32bits of RIP cleared. - Try to work around it here. - Note we only handle faults in kernel here. */ - -static int is_errata93(struct pt_regs *regs, unsigned long address) -{ - static int warned; - if (address != regs->rip) - return 0; - if ((address >> 32) != 0) - return 0; - address |= 0xffffffffUL << 32; - if ((address >= (u64)_stext && address <= (u64)_etext) || - (address >= MODULES_VADDR && address <= MODULES_END)) { - if (!warned) { - printk(errata93_warning); - warned = 1; - } - regs->rip = address; - return 1; - } - return 0; -} - -int unhandled_signal(struct task_struct *tsk, int sig) -{ - if (tsk->pid == 1) - return 1; - /* Warn for strace, but not for gdb */ - if (!test_ti_thread_flag(tsk->thread_info, TIF_SYSCALL_TRACE) && - (tsk->ptrace & PT_PTRACED)) - return 0; - return (tsk->sighand->action[sig-1].sa.sa_handler == SIG_IGN) || - (tsk->sighand->action[sig-1].sa.sa_handler == SIG_DFL); -} - -static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs, - unsigned long error_code) -{ - oops_begin(); - printk(KERN_ALERT "%s: Corrupted page table at address %lx\n", - current->comm, address); - dump_pagetable(address); - __die("Bad pagetable", regs, error_code); - oops_end(); - do_exit(SIGKILL); -} - -/* - * Handle a fault on the vmalloc or module mapping area - * - * This assumes no large pages in there. - */ -static int vmalloc_fault(unsigned long address) -{ - pgd_t *pgd, *pgd_ref; - pud_t *pud, *pud_ref; - pmd_t *pmd, *pmd_ref; - pte_t *pte, *pte_ref; - - /* Copy kernel mappings over when needed. This can also - happen within a race in page table update. In the later - case just flush. */ - - /* On Xen the line below does not always work. Needs investigating! */ - /*pgd = pgd_offset(current->mm ?: &init_mm, address);*/ - preempt_disable(); - pgd = (pgd_t *)per_cpu(cur_pgd, smp_processor_id()); - preempt_enable(); - pgd += pgd_index(address); - pgd_ref = pgd_offset_k(address); - if (pgd_none(*pgd_ref)) - return -1; - if (pgd_none(*pgd)) - set_pgd(pgd, *pgd_ref); - - /* Below here mismatches are bugs because these lower tables - are shared */ - - pud = pud_offset(pgd, address); - pud_ref = pud_offset(pgd_ref, address); - if (pud_none(*pud_ref)) - return -1; - if (pud_none(*pud) || pud_page(*pud) != pud_page(*pud_ref)) - BUG(); - pmd = pmd_offset(pud, address); - pmd_ref = pmd_offset(pud_ref, address); - if (pmd_none(*pmd_ref)) - return -1; - if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref)) - BUG(); - pte_ref = pte_offset_kernel(pmd_ref, address); - if (!pte_present(*pte_ref)) - return -1; - pte = pte_offset_kernel(pmd, address); - /* Don't use pte_page here, because the mappings can point - outside mem_map, and the NUMA hash lookup cannot handle - that. */ - if (!pte_present(*pte) || pte_pfn(*pte) != pte_pfn(*pte_ref)) - BUG(); - __flush_tlb_all(); - return 0; -} - -int page_fault_trace = 0; -int exception_trace = 1; - - -#define MEM_VERBOSE 1 - -#ifdef MEM_VERBOSE -#define MEM_LOG(_f, _a...) \ - printk("fault.c:[%d]-> " _f "\n", \ - __LINE__ , ## _a ) -#else -#define MEM_LOG(_f, _a...) ((void)0) -#endif - -/* - * This routine handles page faults. It determines the address, - * and the problem, and then passes it off to one of the appropriate - * routines. - * - * error_code: - * bit 0 == 0 means no page found, 1 means protection fault - * bit 1 == 0 means read, 1 means write - * bit 2 == 0 means kernel, 1 means user-mode - * bit 3 == 1 means fault was an instruction fetch - */ -asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code) -{ - struct task_struct *tsk; - struct mm_struct *mm; - struct vm_area_struct * vma; - unsigned long address; - const struct exception_table_entry *fixup; - int write; - siginfo_t info; - - if (!user_mode(regs)) - error_code &= ~4; /* means kernel */ - -#ifdef CONFIG_CHECKING - { - unsigned long gs; - struct x8664_pda *pda = cpu_pda + stack_smp_processor_id(); - rdmsrl(MSR_GS_BASE, gs); - if (gs != (unsigned long)pda) { - wrmsrl(MSR_GS_BASE, pda); - printk("page_fault: wrong gs %lx expected %p\n", gs, pda); - } - } -#endif - - /* get the address */ - address = HYPERVISOR_shared_info->vcpu_info[ - smp_processor_id()].arch.cr2; - - if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14, - SIGSEGV) == NOTIFY_STOP) - return; - - if (likely(regs->eflags & X86_EFLAGS_IF)) - local_irq_enable(); - - if (unlikely(page_fault_trace)) - printk("pagefault rip:%lx rsp:%lx cs:%lu ss:%lu address %lx error %lx\n", - regs->rip,regs->rsp,regs->cs,regs->ss,address,error_code); - - tsk = current; - mm = tsk->mm; - info.si_code = SEGV_MAPERR; - - - /* - * We fault-in kernel-space virtual memory on-demand. The - * 'reference' page table is init_mm.pgd. - * - * NOTE! We MUST NOT take any locks for this case. We may - * be in an interrupt or a critical region, and should - * only copy the information from the master page table, - * nothing more. - * - * This verifies that the fault happens in kernel space - * (error_code & 4) == 0, and that the fault was not a - * protection error (error_code & 1) == 0. - */ - if (unlikely(address >= TASK_SIZE)) { - if (!(error_code & 5) && - ((address >= VMALLOC_START && address < VMALLOC_END) || - (address >= MODULES_VADDR && address < MODULES_END))) { - if (vmalloc_fault(address) < 0) - goto bad_area_nosemaphore; - return; - } - /* - * Don't take the mm semaphore here. If we fixup a prefetch - * fault we could otherwise deadlock. - */ - goto bad_area_nosemaphore; - } - - if (unlikely(error_code & (1 << 3))) - pgtable_bad(address, regs, error_code); - - /* - * If we're in an interrupt or have no user - * context, we must not take the fault.. - */ - if (unlikely(in_atomic() || !mm)) - goto bad_area_nosemaphore; - - again: - /* When running in the kernel we expect faults to occur only to - * addresses in user space. All other faults represent errors in the - * kernel and should generate an OOPS. Unfortunatly, in the case of an - * erroneous fault occuring in a code path which already holds mmap_sem - * we will deadlock attempting to validate the fault against the - * address space. Luckily the kernel only validly references user - * space from well defined areas of code, which are listed in the - * exceptions table. - * - * As the vast majority of faults will be valid we will only perform - * the source reference check when there is a possibilty of a deadlock. - * Attempt to lock the address space, if we cannot we then validate the - * source. If this is invalid we can skip the address space check, - * thus avoiding the deadlock. - */ - if (!down_read_trylock(&mm->mmap_sem)) { - if ((error_code & 4) == 0 && - !search_exception_tables(regs->rip)) - goto bad_area_nosemaphore; - down_read(&mm->mmap_sem); - } - - vma = find_vma(mm, address); - if (!vma) - goto bad_area; - if (likely(vma->vm_start <= address)) - goto good_area; - if (!(vma->vm_flags & VM_GROWSDOWN)) - goto bad_area; - if (error_code & 4) { - // XXX: align red zone size with ABI - if (address + 128 < regs->rsp) - goto bad_area; - } - if (expand_stack(vma, address)) - goto bad_area; -/* - * Ok, we have a good vm_area for this memory access, so - * we can handle it.. - */ -good_area: - info.si_code = SEGV_ACCERR; - write = 0; - switch (error_code & 3) { - default: /* 3: write, present */ - /* fall through */ - case 2: /* write, not present */ - if (!(vma->vm_flags & VM_WRITE)) - goto bad_area; - write++; - break; - case 1: /* read, present */ - goto bad_area; - case 0: /* read, not present */ - if (!(vma->vm_flags & (VM_READ | VM_EXEC))) - goto bad_area; - } - - /* - * If for any reason at all we couldn't handle the fault, - * make sure we exit gracefully rather than endlessly redo - * the fault. - */ - switch (handle_mm_fault(mm, vma, address, write)) { - case 1: - tsk->min_flt++; - break; - case 2: - tsk->maj_flt++; - break; - case 0: - goto do_sigbus; - default: - goto out_of_memory; - } - - up_read(&mm->mmap_sem); - return; - -/* - * Something tried to access memory that isn't in our memory map.. - * Fix it, but check if it's kernel or user first.. - */ -bad_area: - up_read(&mm->mmap_sem); - -bad_area_nosemaphore: - /* User mode accesses just cause a SIGSEGV */ - if (error_code & 4) { - if (is_prefetch(regs, address, error_code)) - return; - - /* Work around K8 erratum #100 K8 in compat mode - occasionally jumps to illegal addresses >4GB. We - catch this here in the page fault handler because - these addresses are not reachable. Just detect this - case and return. Any code segment in LDT is - compatibility mode. */ - if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) && - (address >> 32)) - return; - - if (exception_trace && unhandled_signal(tsk, SIGSEGV)) { - printk( - "%s%s[%d]: segfault at %016lx rip %016lx rsp %016lx error %lx\n", - tsk->pid > 1 ? KERN_INFO : KERN_EMERG, - tsk->comm, tsk->pid, address, regs->rip, - regs->rsp, error_code); - } - - tsk->thread.cr2 = address; - /* Kernel addresses are always protection faults */ - tsk->thread.error_code = error_code | (address >= TASK_SIZE); - tsk->thread.trap_no = 14; - info.si_signo = SIGSEGV; - info.si_errno = 0; - /* info.si_code has been set above */ - info.si_addr = (void __user *)address; - force_sig_info(SIGSEGV, &info, tsk); - return; - } - -no_context: - - /* Are we prepared to handle this kernel fault? */ - fixup = search_exception_tables(regs->rip); - if (fixup) { - regs->rip = fixup->fixup; - return; - } - - /* - * Hall of shame of CPU/BIOS bugs. - */ - - if (is_prefetch(regs, address, error_code)) - return; - - if (is_errata93(regs, address)) - return; - -/* - * Oops. The kernel tried to access some bad page. We'll have to - * terminate things with extreme prejudice. - */ - - oops_begin(); - - if (address < PAGE_SIZE) - printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference"); - else - printk(KERN_ALERT "Unable to handle kernel paging request"); - printk(" at %016lx RIP: \n" KERN_ALERT,address); - printk_address(regs->rip); - printk("\n"); - dump_pagetable(address); - __die("Oops", regs, error_code); - /* Executive summary in case the body of the oops scrolled away */ - printk(KERN_EMERG "CR2: %016lx\n", address); - oops_end(); - do_exit(SIGKILL); - -/* - * We ran out of memory, or some other thing happened to us that made - * us unable to handle the page fault gracefully. - */ -out_of_memory: - up_read(&mm->mmap_sem); - if (current->pid == 1) { - yield(); - goto again; - } - printk("VM: killing process %s\n", tsk->comm); - if (error_code & 4) - do_exit(SIGKILL); - goto no_context; - -do_sigbus: - up_read(&mm->mmap_sem); - - /* Kernel mode? Handle exceptions or die */ - if (!(error_code & 4)) - goto no_context; - - tsk->thread.cr2 = address; - tsk->thread.error_code = error_code; - tsk->thread.trap_no = 14; - info.si_signo = SIGBUS; - info.si_errno = 0; - info.si_code = BUS_ADRERR; - info.si_addr = (void __user *)address; - force_sig_info(SIGBUS, &info, tsk); - return; -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/mm/init.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/mm/init.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,964 +0,0 @@ -/* - * linux/arch/x86_64/mm/init.c - * - * Copyright (C) 1995 Linus Torvalds - * Copyright (C) 2000 Pavel Machek <pavel@xxxxxxx> - * Copyright (C) 2002,2003 Andi Kleen <ak@xxxxxxx> - * - * Jun Nakajima <jun.nakajima@xxxxxxxxx> - * Modified for Xen. - */ - -#include <linux/config.h> -#include <linux/signal.h> -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/string.h> -#include <linux/types.h> -#include <linux/ptrace.h> -#include <linux/mman.h> -#include <linux/mm.h> -#include <linux/swap.h> -#include <linux/smp.h> -#include <linux/init.h> -#include <linux/pagemap.h> -#include <linux/bootmem.h> -#include <linux/proc_fs.h> - -#include <asm/processor.h> -#include <asm/system.h> -#include <asm/uaccess.h> -#include <asm/pgtable.h> -#include <asm/pgalloc.h> -#include <asm/dma.h> -#include <asm/fixmap.h> -#include <asm/e820.h> -#include <asm/apic.h> -#include <asm/tlb.h> -#include <asm/mmu_context.h> -#include <asm/proto.h> -#include <asm/smp.h> - -#include <asm-xen/features.h> - -#ifndef Dprintk -#define Dprintk(x...) -#endif - -extern unsigned long *contiguous_bitmap; - -#if defined(CONFIG_SWIOTLB) -extern void swiotlb_init(void); -#endif - -extern char _stext[]; - -DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); -extern unsigned long start_pfn; - -/* - * Use this until direct mapping is established, i.e. before __va() is - * available in init_memory_mapping(). - */ - -#define addr_to_page(addr, page) \ - (addr) &= PHYSICAL_PAGE_MASK; \ - (page) = ((unsigned long *) ((unsigned long) \ - (((mfn_to_pfn((addr) >> PAGE_SHIFT)) << PAGE_SHIFT) + \ - __START_KERNEL_map))) - -static void early_make_page_readonly(void *va, unsigned int feature) -{ - unsigned long addr, _va = (unsigned long)va; - pte_t pte, *ptep; - unsigned long *page = (unsigned long *) init_level4_pgt; - - if (xen_feature(feature)) - return; - - addr = (unsigned long) page[pgd_index(_va)]; - addr_to_page(addr, page); - - addr = page[pud_index(_va)]; - addr_to_page(addr, page); - - addr = page[pmd_index(_va)]; - addr_to_page(addr, page); - - ptep = (pte_t *) &page[pte_index(_va)]; - - pte.pte = ptep->pte & ~_PAGE_RW; - if (HYPERVISOR_update_va_mapping(_va, pte, 0)) - BUG(); -} - -void make_page_readonly(void *va, unsigned int feature) -{ - pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t pte, *ptep; - unsigned long addr = (unsigned long) va; - - if (xen_feature(feature)) - return; - - pgd = pgd_offset_k(addr); - pud = pud_offset(pgd, addr); - pmd = pmd_offset(pud, addr); - ptep = pte_offset_kernel(pmd, addr); - - pte.pte = ptep->pte & ~_PAGE_RW; - if (HYPERVISOR_update_va_mapping(addr, pte, 0)) - xen_l1_entry_update(ptep, pte); /* fallback */ - - if ((addr >= VMALLOC_START) && (addr < VMALLOC_END)) - make_page_readonly(__va(pte_pfn(pte) << PAGE_SHIFT), feature); -} - -void make_page_writable(void *va, unsigned int feature) -{ - pgd_t *pgd; pud_t *pud; pmd_t *pmd; pte_t pte, *ptep; - unsigned long addr = (unsigned long) va; - - if (xen_feature(feature)) - return; - - pgd = pgd_offset_k(addr); - pud = pud_offset(pgd, addr); - pmd = pmd_offset(pud, addr); - ptep = pte_offset_kernel(pmd, addr); - - pte.pte = ptep->pte | _PAGE_RW; - if (HYPERVISOR_update_va_mapping(addr, pte, 0)) - xen_l1_entry_update(ptep, pte); /* fallback */ - - if ((addr >= VMALLOC_START) && (addr < VMALLOC_END)) - make_page_writable(__va(pte_pfn(pte) << PAGE_SHIFT), feature); -} - -void make_pages_readonly(void *va, unsigned nr, unsigned int feature) -{ - if (xen_feature(feature)) - return; - - while (nr-- != 0) { - make_page_readonly(va, feature); - va = (void*)((unsigned long)va + PAGE_SIZE); - } -} - -void make_pages_writable(void *va, unsigned nr, unsigned int feature) -{ - if (xen_feature(feature)) - return; - - while (nr-- != 0) { - make_page_writable(va, feature); - va = (void*)((unsigned long)va + PAGE_SIZE); - } -} - -/* - * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the - * physical space so we can cache the place of the first one and move - * around without checking the pgd every time. - */ - -void show_mem(void) -{ - int i, total = 0, reserved = 0; - int shared = 0, cached = 0; - pg_data_t *pgdat; - struct page *page; - - printk("Mem-info:\n"); - show_free_areas(); - printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10)); - - for_each_pgdat(pgdat) { - for (i = 0; i < pgdat->node_spanned_pages; ++i) { - page = pfn_to_page(pgdat->node_start_pfn + i); - total++; - if (PageReserved(page)) - reserved++; - else if (PageSwapCache(page)) - cached++; - else if (page_count(page)) - shared += page_count(page) - 1; - } - } - printk("%d pages of RAM\n", total); - printk("%d reserved pages\n",reserved); - printk("%d pages shared\n",shared); - printk("%d pages swap cached\n",cached); -} - -/* References to section boundaries */ - -extern char _text, _etext, _edata, __bss_start, _end[]; -extern char __init_begin, __init_end; - -int after_bootmem; - -static void *spp_getpage(void) -{ - void *ptr; - if (after_bootmem) - ptr = (void *) get_zeroed_page(GFP_ATOMIC); - else - ptr = alloc_bootmem_pages(PAGE_SIZE); - if (!ptr || ((unsigned long)ptr & ~PAGE_MASK)) - panic("set_pte_phys: cannot allocate page data %s\n", after_bootmem?"after bootmem":""); - - Dprintk("spp_getpage %p\n", ptr); - return ptr; -} - -#define pgd_offset_u(address) (pgd_t *)(init_level4_user_pgt + pgd_index(address)) - -static inline pud_t *pud_offset_u(unsigned long address) -{ - pud_t *pud = level3_user_pgt; - - return pud + pud_index(address); -} - -static void set_pte_phys(unsigned long vaddr, - unsigned long phys, pgprot_t prot, int user_mode) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte, new_pte; - - Dprintk("set_pte_phys %lx to %lx\n", vaddr, phys); - - pgd = (user_mode ? pgd_offset_u(vaddr) : pgd_offset_k(vaddr)); - if (pgd_none(*pgd)) { - printk("PGD FIXMAP MISSING, it should be setup in head.S!\n"); - return; - } - pud = (user_mode ? pud_offset_u(vaddr) : pud_offset(pgd, vaddr)); - if (pud_none(*pud)) { - pmd = (pmd_t *) spp_getpage(); - make_page_readonly(pmd, XENFEAT_writable_page_tables); - xen_pmd_pin(__pa(pmd)); - set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | _PAGE_USER)); - if (pmd != pmd_offset(pud, 0)) { - printk("PAGETABLE BUG #01! %p <-> %p\n", pmd, pmd_offset(pud,0)); - return; - } - } - pmd = pmd_offset(pud, vaddr); - if (pmd_none(*pmd)) { - pte = (pte_t *) spp_getpage(); - make_page_readonly(pte, XENFEAT_writable_page_tables); - xen_pte_pin(__pa(pte)); - set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE | _PAGE_USER)); - if (pte != pte_offset_kernel(pmd, 0)) { - printk("PAGETABLE BUG #02!\n"); - return; - } - } - new_pte = pfn_pte(phys >> PAGE_SHIFT, prot); - - pte = pte_offset_kernel(pmd, vaddr); - if (!pte_none(*pte) && - pte_val(*pte) != (pte_val(new_pte) & __supported_pte_mask)) - pte_ERROR(*pte); - set_pte(pte, new_pte); - - /* - * It's enough to flush this one mapping. - * (PGE mappings get flushed as well) - */ - __flush_tlb_one(vaddr); -} - -static void set_pte_phys_ma(unsigned long vaddr, - unsigned long phys, pgprot_t prot) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte, new_pte; - - Dprintk("set_pte_phys %lx to %lx\n", vaddr, phys); - - pgd = pgd_offset_k(vaddr); - if (pgd_none(*pgd)) { - printk("PGD FIXMAP MISSING, it should be setup in head.S!\n"); - return; - } - pud = pud_offset(pgd, vaddr); - if (pud_none(*pud)) { - - pmd = (pmd_t *) spp_getpage(); - make_page_readonly(pmd, XENFEAT_writable_page_tables); - xen_pmd_pin(__pa(pmd)); - - set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | _PAGE_USER)); - - if (pmd != pmd_offset(pud, 0)) { - printk("PAGETABLE BUG #01! %p <-> %p\n", pmd, pmd_offset(pud,0)); - return; - } - } - pmd = pmd_offset(pud, vaddr); - - if (pmd_none(*pmd)) { - pte = (pte_t *) spp_getpage(); - make_page_readonly(pte, XENFEAT_writable_page_tables); - xen_pte_pin(__pa(pte)); - - set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE | _PAGE_USER)); - if (pte != pte_offset_kernel(pmd, 0)) { - printk("PAGETABLE BUG #02!\n"); - return; - } - } - - new_pte = pfn_pte_ma(phys >> PAGE_SHIFT, prot); - pte = pte_offset_kernel(pmd, vaddr); - - /* - * Note that the pte page is already RO, thus we want to use - * xen_l1_entry_update(), not set_pte(). - */ - xen_l1_entry_update(pte, - pfn_pte_ma(phys >> PAGE_SHIFT, prot)); - - /* - * It's enough to flush this one mapping. - * (PGE mappings get flushed as well) - */ - __flush_tlb_one(vaddr); -} - -#define SET_FIXMAP_KERNEL 0 -#define SET_FIXMAP_USER 1 - -/* NOTE: this is meant to be run only at boot */ -void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t prot) -{ - unsigned long address = __fix_to_virt(idx); - - if (idx >= __end_of_fixed_addresses) { - printk("Invalid __set_fixmap\n"); - return; - } - switch (idx) { - case VSYSCALL_FIRST_PAGE: - set_pte_phys(address, phys, prot, SET_FIXMAP_KERNEL); - break; - default: - set_pte_phys_ma(address, phys, prot); - break; - } -} - -/* - * At this point it only supports vsyscall area. - */ -void __set_fixmap_user (enum fixed_addresses idx, unsigned long phys, pgprot_t prot) -{ - unsigned long address = __fix_to_virt(idx); - - if (idx >= __end_of_fixed_addresses) { - printk("Invalid __set_fixmap\n"); - return; - } - - set_pte_phys(address, phys, prot, SET_FIXMAP_USER); -} - -unsigned long __initdata table_start, tables_space; - -unsigned long get_machine_pfn(unsigned long addr) -{ - pud_t* pud = pud_offset_k(addr); - pmd_t* pmd = pmd_offset(pud, addr); - pte_t *pte = pte_offset_kernel(pmd, addr); - - return pte_mfn(*pte); -} - -static __init void *alloc_static_page(unsigned long *phys) -{ - unsigned long va = (start_pfn << PAGE_SHIFT) + __START_KERNEL_map; - *phys = start_pfn << PAGE_SHIFT; - start_pfn++; - memset((void *)va, 0, PAGE_SIZE); - return (void *)va; -} - -#define PTE_SIZE PAGE_SIZE - -static inline void __set_pte(pte_t *dst, pte_t val) -{ - *dst = val; -} - -static inline int make_readonly(unsigned long paddr) -{ - int readonly = 0; - - /* Make old and new page tables read-only. */ - if (!xen_feature(XENFEAT_writable_page_tables) - && (paddr >= (xen_start_info->pt_base - __START_KERNEL_map)) - && (paddr < ((table_start << PAGE_SHIFT) + tables_space))) - readonly = 1; - /* - * No need for writable mapping of kernel image. This also ensures that - * page and descriptor tables embedded inside don't have writable - * mappings. - */ - if ((paddr >= __pa_symbol(&_text)) && (paddr < __pa_symbol(&_end))) - readonly = 1; - - return readonly; -} - -static void __init phys_pud_init(pud_t *pud, unsigned long address, unsigned long end) -{ - long i, j, k; - unsigned long paddr; - - i = pud_index(address); - pud = pud + i; - for (; i < PTRS_PER_PUD; pud++, i++) { - unsigned long pmd_phys; - pmd_t *pmd; - - paddr = address + i*PUD_SIZE; - if (paddr >= end) { - for (; i < PTRS_PER_PUD; i++, pud++) - set_pud(pud, __pud(0)); - break; - } - - pmd = alloc_static_page(&pmd_phys); - early_make_page_readonly(pmd, XENFEAT_writable_page_tables); - xen_pmd_pin(pmd_phys); - set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE)); - for (j = 0; j < PTRS_PER_PMD; pmd++, j++) { - unsigned long pte_phys; - pte_t *pte, *pte_save; - - if (paddr >= end) { - for (; j < PTRS_PER_PMD; j++, pmd++) - set_pmd(pmd, __pmd(0)); - break; - } - pte = alloc_static_page(&pte_phys); - pte_save = pte; - for (k = 0; k < PTRS_PER_PTE; pte++, k++, paddr += PTE_SIZE) { - if ((paddr >= end) || - ((paddr >> PAGE_SHIFT) >= - xen_start_info->nr_pages)) { - __set_pte(pte, __pte(0)); - continue; - } - if (make_readonly(paddr)) { - __set_pte(pte, - __pte(paddr | (_KERNPG_TABLE & ~_PAGE_RW))); - continue; - } - __set_pte(pte, __pte(paddr | _KERNPG_TABLE)); - } - pte = pte_save; - early_make_page_readonly( - pte, XENFEAT_writable_page_tables); - xen_pte_pin(pte_phys); - set_pmd(pmd, __pmd(pte_phys | _KERNPG_TABLE)); - } - } - __flush_tlb(); -} - -static void __init find_early_table_space(unsigned long end) -{ - unsigned long puds, pmds, ptes; - - puds = (end + PUD_SIZE - 1) >> PUD_SHIFT; - pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT; - ptes = (end + PTE_SIZE - 1) >> PAGE_SHIFT; - - tables_space = - round_up(puds * 8, PAGE_SIZE) + - round_up(pmds * 8, PAGE_SIZE) + - round_up(ptes * 8, PAGE_SIZE); -} - -void __init xen_init_pt(void) -{ - unsigned long addr, *page; - int i; - - for (i = 0; i < NR_CPUS; i++) - per_cpu(cur_pgd, i) = init_mm.pgd; - - memset((void *)init_level4_pgt, 0, PAGE_SIZE); - memset((void *)level3_kernel_pgt, 0, PAGE_SIZE); - memset((void *)level2_kernel_pgt, 0, PAGE_SIZE); - - /* Find the initial pte page that was built for us. */ - page = (unsigned long *)xen_start_info->pt_base; - addr = page[pgd_index(__START_KERNEL_map)]; - addr_to_page(addr, page); - addr = page[pud_index(__START_KERNEL_map)]; - addr_to_page(addr, page); - - /* Construct mapping of initial pte page in our own directories. */ - init_level4_pgt[pgd_index(__START_KERNEL_map)] = - mk_kernel_pgd(__pa_symbol(level3_kernel_pgt)); - level3_kernel_pgt[pud_index(__START_KERNEL_map)] = - __pud(__pa_symbol(level2_kernel_pgt) | - _KERNPG_TABLE | _PAGE_USER); - memcpy((void *)level2_kernel_pgt, page, PAGE_SIZE); - - early_make_page_readonly(init_level4_pgt, - XENFEAT_writable_page_tables); - early_make_page_readonly(init_level4_user_pgt, - XENFEAT_writable_page_tables); - early_make_page_readonly(level3_kernel_pgt, - XENFEAT_writable_page_tables); - early_make_page_readonly(level3_user_pgt, - XENFEAT_writable_page_tables); - early_make_page_readonly(level2_kernel_pgt, - XENFEAT_writable_page_tables); - - xen_pgd_pin(__pa_symbol(init_level4_pgt)); - xen_pgd_pin(__pa_symbol(init_level4_user_pgt)); - xen_pud_pin(__pa_symbol(level3_kernel_pgt)); - xen_pud_pin(__pa_symbol(level3_user_pgt)); - xen_pmd_pin(__pa_symbol(level2_kernel_pgt)); - - set_pgd((pgd_t *)(init_level4_user_pgt + 511), - mk_kernel_pgd(__pa_symbol(level3_user_pgt))); -} - -void __init extend_init_mapping(void) -{ - unsigned long va = __START_KERNEL_map; - unsigned long phys, addr, *pte_page; - pmd_t *pmd; - pte_t *pte, new_pte; - unsigned long *page = (unsigned long *)init_level4_pgt; - - addr = page[pgd_index(va)]; - addr_to_page(addr, page); - addr = page[pud_index(va)]; - addr_to_page(addr, page); - - /* Kill mapping of low 1MB. */ - while (va < (unsigned long)&_text) { - HYPERVISOR_update_va_mapping(va, __pte_ma(0), 0); - va += PAGE_SIZE; - } - - /* Ensure init mappings cover kernel text/data and initial tables. */ - while (va < (__START_KERNEL_map - + (start_pfn << PAGE_SHIFT) - + tables_space)) { - pmd = (pmd_t *)&page[pmd_index(va)]; - if (pmd_none(*pmd)) { - pte_page = alloc_static_page(&phys); - early_make_page_readonly( - pte_page, XENFEAT_writable_page_tables); - xen_pte_pin(phys); - set_pmd(pmd, __pmd(phys | _KERNPG_TABLE | _PAGE_USER)); - } else { - addr = page[pmd_index(va)]; - addr_to_page(addr, pte_page); - } - pte = (pte_t *)&pte_page[pte_index(va)]; - if (pte_none(*pte)) { - new_pte = pfn_pte( - (va - __START_KERNEL_map) >> PAGE_SHIFT, - __pgprot(_KERNPG_TABLE | _PAGE_USER)); - xen_l1_entry_update(pte, new_pte); - } - va += PAGE_SIZE; - } - - /* Finally, blow away any spurious initial mappings. */ - while (1) { - pmd = (pmd_t *)&page[pmd_index(va)]; - if (pmd_none(*pmd)) - break; - HYPERVISOR_update_va_mapping(va, __pte_ma(0), 0); - va += PAGE_SIZE; - } -} - -/* Setup the direct mapping of the physical memory at PAGE_OFFSET. - This runs before bootmem is initialized and gets pages directly from the - physical memory. To access them they are temporarily mapped. */ -void __init init_memory_mapping(unsigned long start, unsigned long end) -{ - unsigned long next; - - Dprintk("init_memory_mapping\n"); - - find_early_table_space(end); - extend_init_mapping(); - - table_start = start_pfn; - - start = (unsigned long)__va(start); - end = (unsigned long)__va(end); - - for (; start < end; start = next) { - unsigned long pud_phys; - pud_t *pud = alloc_static_page(&pud_phys); - early_make_page_readonly(pud, XENFEAT_writable_page_tables); - xen_pud_pin(pud_phys); - next = start + PGDIR_SIZE; - if (next > end) - next = end; - phys_pud_init(pud, __pa(start), __pa(next)); - set_pgd(pgd_offset_k(start), mk_kernel_pgd(pud_phys)); - } - - printk("kernel direct mapping tables upto %lx @ %lx-%lx\n", - __pa(end), table_start<<PAGE_SHIFT, start_pfn<<PAGE_SHIFT); - - BUG_ON(start_pfn != (table_start + (tables_space >> PAGE_SHIFT))); - - __flush_tlb_all(); -} - -extern struct x8664_pda cpu_pda[NR_CPUS]; - -void zap_low_mappings(void) -{ - /* this is not required for Xen */ -#if 0 - swap_low_mappings(); -#endif -} - -#ifndef CONFIG_DISCONTIGMEM -void __init paging_init(void) -{ - { - unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0}; - /* unsigned int max_dma; */ - /* max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; */ - /* if (end_pfn < max_dma) */ - zones_size[ZONE_DMA] = end_pfn; -#if 0 - else { - zones_size[ZONE_DMA] = max_dma; - zones_size[ZONE_NORMAL] = end_pfn - max_dma; - } -#endif - free_area_init(zones_size); - } - - set_fixmap(FIX_SHARED_INFO, xen_start_info->shared_info); - HYPERVISOR_shared_info = (shared_info_t *)fix_to_virt(FIX_SHARED_INFO); - - memset(empty_zero_page, 0, sizeof(empty_zero_page)); - init_mm.context.pinned = 1; - -#ifdef CONFIG_XEN_PHYSDEV_ACCESS - { - int i; - /* Setup mapping of lower 1st MB */ - for (i = 0; i < NR_FIX_ISAMAPS; i++) - if (xen_start_info->flags & SIF_PRIVILEGED) - set_fixmap(FIX_ISAMAP_BEGIN - i, i * PAGE_SIZE); - else - __set_fixmap(FIX_ISAMAP_BEGIN - i, - virt_to_mfn(empty_zero_page) << PAGE_SHIFT, - PAGE_KERNEL_RO); - } -#endif - -} -#endif - -/* Unmap a kernel mapping if it exists. This is useful to avoid prefetches - from the CPU leading to inconsistent cache lines. address and size - must be aligned to 2MB boundaries. - Does nothing when the mapping doesn't exist. */ -void __init clear_kernel_mapping(unsigned long address, unsigned long size) -{ - unsigned long end = address + size; - - BUG_ON(address & ~LARGE_PAGE_MASK); - BUG_ON(size & ~LARGE_PAGE_MASK); - - for (; address < end; address += LARGE_PAGE_SIZE) { - pgd_t *pgd = pgd_offset_k(address); - pud_t *pud; - pmd_t *pmd; - if (pgd_none(*pgd)) - continue; - pud = pud_offset(pgd, address); - if (pud_none(*pud)) - continue; - pmd = pmd_offset(pud, address); - if (!pmd || pmd_none(*pmd)) - continue; - if (0 == (pmd_val(*pmd) & _PAGE_PSE)) { - /* Could handle this, but it should not happen currently. */ - printk(KERN_ERR - "clear_kernel_mapping: mapping has been split. will leak memory\n"); - pmd_ERROR(*pmd); - } - set_pmd(pmd, __pmd(0)); - } - __flush_tlb_all(); -} - -static inline int page_is_ram (unsigned long pagenr) -{ - return 1; -} - -static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel, kcore_modules, - kcore_vsyscall; - -void __init mem_init(void) -{ - int codesize, reservedpages, datasize, initsize; - int tmp; - - contiguous_bitmap = alloc_bootmem_low_pages( - (end_pfn + 2*BITS_PER_LONG) >> 3); - BUG_ON(!contiguous_bitmap); - memset(contiguous_bitmap, 0, (end_pfn + 2*BITS_PER_LONG) >> 3); - -#if defined(CONFIG_SWIOTLB) - swiotlb_init(); -#endif - - /* How many end-of-memory variables you have, grandma! */ - max_low_pfn = end_pfn; - max_pfn = end_pfn; - num_physpages = end_pfn; - high_memory = (void *) __va(end_pfn * PAGE_SIZE); - - /* clear the zero-page */ - memset(empty_zero_page, 0, PAGE_SIZE); - - reservedpages = 0; - - /* this will put all low memory onto the freelists */ -#ifdef CONFIG_DISCONTIGMEM - totalram_pages += numa_free_all_bootmem(); - tmp = 0; - /* should count reserved pages here for all nodes */ -#else - max_mapnr = end_pfn; - if (!mem_map) BUG(); - - totalram_pages += free_all_bootmem(); - - for (tmp = 0; tmp < end_pfn; tmp++) - /* - * Only count reserved RAM pages - */ - if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp))) - reservedpages++; -#endif - - after_bootmem = 1; - - codesize = (unsigned long) &_etext - (unsigned long) &_text; - datasize = (unsigned long) &_edata - (unsigned long) &_etext; - initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin; - - /* Register memory areas for /proc/kcore */ - kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT); - kclist_add(&kcore_vmalloc, (void *)VMALLOC_START, - VMALLOC_END-VMALLOC_START); - kclist_add(&kcore_kernel, &_stext, _end - _stext); - kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_LEN); - kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START, - VSYSCALL_END - VSYSCALL_START); - - printk("Memory: %luk/%luk available (%dk kernel code, %dk reserved, %dk data, %dk init)\n", - (unsigned long) nr_free_pages() << (PAGE_SHIFT-10), - end_pfn << (PAGE_SHIFT-10), - codesize >> 10, - reservedpages << (PAGE_SHIFT-10), - datasize >> 10, - initsize >> 10); - - /* - * Subtle. SMP is doing its boot stuff late (because it has to - * fork idle threads) - but it also needs low mappings for the - * protected-mode entry to work. We zap these entries only after - * the WP-bit has been tested. - */ -#ifndef CONFIG_SMP - zap_low_mappings(); -#endif -} - -extern char __initdata_begin[], __initdata_end[]; - -void free_initmem(void) -{ -#ifdef __DO_LATER__ - /* - * Some pages can be pinned, but some are not. Unpinning such pages - * triggers BUG(). - */ - unsigned long addr; - - addr = (unsigned long)(&__init_begin); - for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) { - ClearPageReserved(virt_to_page(addr)); - set_page_count(virt_to_page(addr), 1); - memset((void *)(addr & ~(PAGE_SIZE-1)), 0xcc, PAGE_SIZE); - xen_pte_unpin(__pa(addr)); - make_page_writable( - __va(__pa(addr)), XENFEAT_writable_page_tables); - /* - * Make pages from __PAGE_OFFSET address as well - */ - make_page_writable( - (void *)addr, XENFEAT_writable_page_tables); - free_page(addr); - totalram_pages++; - } - memset(__initdata_begin, 0xba, __initdata_end - __initdata_begin); - printk ("Freeing unused kernel memory: %luk freed\n", (&__init_end - &__init_begin) >> 10); -#endif -} - -#ifdef CONFIG_BLK_DEV_INITRD -void free_initrd_mem(unsigned long start, unsigned long end) -{ - if (start < (unsigned long)&_end) - return; - printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10); - for (; start < end; start += PAGE_SIZE) { - ClearPageReserved(virt_to_page(start)); - set_page_count(virt_to_page(start), 1); - free_page(start); - totalram_pages++; - } -} -#endif - -void __init reserve_bootmem_generic(unsigned long phys, unsigned len) -{ - /* Should check here against the e820 map to avoid double free */ -#ifdef CONFIG_DISCONTIGMEM - int nid = phys_to_nid(phys); - reserve_bootmem_node(NODE_DATA(nid), phys, len); -#else - reserve_bootmem(phys, len); -#endif -} - -int kern_addr_valid(unsigned long addr) -{ - unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT; - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - if (above != 0 && above != -1UL) - return 0; - - pgd = pgd_offset_k(addr); - if (pgd_none(*pgd)) - return 0; - - pud = pud_offset_k(addr); - if (pud_none(*pud)) - return 0; - - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) - return 0; - if (pmd_large(*pmd)) - return pfn_valid(pmd_pfn(*pmd)); - - pte = pte_offset_kernel(pmd, addr); - if (pte_none(*pte)) - return 0; - return pfn_valid(pte_pfn(*pte)); -} - -#ifdef CONFIG_SYSCTL -#include <linux/sysctl.h> - -extern int exception_trace, page_fault_trace; - -static ctl_table debug_table2[] = { - { 99, "exception-trace", &exception_trace, sizeof(int), 0644, NULL, - proc_dointvec }, -#ifdef CONFIG_CHECKING - { 100, "page-fault-trace", &page_fault_trace, sizeof(int), 0644, NULL, - proc_dointvec }, -#endif - { 0, } -}; - -static ctl_table debug_root_table2[] = { - { .ctl_name = CTL_DEBUG, .procname = "debug", .mode = 0555, - .child = debug_table2 }, - { 0 }, -}; - -static __init int x8664_sysctl_init(void) -{ - register_sysctl_table(debug_root_table2, 1); - return 0; -} -__initcall(x8664_sysctl_init); -#endif - -/* A pseudo VMAs to allow ptrace access for the vsyscall page. This only - covers the 64bit vsyscall page now. 32bit has a real VMA now and does - not need special handling anymore. */ - -static struct vm_area_struct gate_vma = { - .vm_start = VSYSCALL_START, - .vm_end = VSYSCALL_END, - .vm_page_prot = PAGE_READONLY -}; - -struct vm_area_struct *get_gate_vma(struct task_struct *tsk) -{ -#ifdef CONFIG_IA32_EMULATION - if (test_tsk_thread_flag(tsk, TIF_IA32)) - return NULL; -#endif - return &gate_vma; -} - -int in_gate_area(struct task_struct *task, unsigned long addr) -{ - struct vm_area_struct *vma = get_gate_vma(task); - if (!vma) - return 0; - return (addr >= vma->vm_start) && (addr < vma->vm_end); -} - -/* Use this when you have no reliable task/vma, typically from interrupt - * context. It is less reliable than using the task's vma and may give - * false positives. - */ -int in_gate_area_no_task(unsigned long addr) -{ - return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END); -} - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/mm/pageattr.c --- a/linux-2.6-xen-sparse/arch/xen/x86_64/mm/pageattr.c Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,382 +0,0 @@ -/* - * Copyright 2002 Andi Kleen, SuSE Labs. - * Thanks to Ben LaHaise for precious feedback. - */ - -#include <linux/config.h> -#include <linux/mm.h> -#include <linux/sched.h> -#include <linux/highmem.h> -#include <linux/module.h> -#include <linux/slab.h> -#include <asm/uaccess.h> -#include <asm/processor.h> -#include <asm/tlbflush.h> -#include <asm/io.h> - -#ifdef CONFIG_XEN -#include <asm/pgalloc.h> -#include <asm/mmu_context.h> - -LIST_HEAD(mm_unpinned); -DEFINE_SPINLOCK(mm_unpinned_lock); - -static inline void mm_walk_set_prot(void *pt, pgprot_t flags) -{ - struct page *page = virt_to_page(pt); - unsigned long pfn = page_to_pfn(page); - - BUG_ON(HYPERVISOR_update_va_mapping( - (unsigned long)__va(pfn << PAGE_SHIFT), - pfn_pte(pfn, flags), 0)); -} - -static void mm_walk(struct mm_struct *mm, pgprot_t flags) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - int g,u,m; - - pgd = mm->pgd; - for (g = 0; g <= USER_PTRS_PER_PGD; g++, pgd++) { - if (pgd_none(*pgd)) - continue; - pud = pud_offset(pgd, 0); - if (PTRS_PER_PUD > 1) /* not folded */ - mm_walk_set_prot(pud,flags); - for (u = 0; u < PTRS_PER_PUD; u++, pud++) { - if (pud_none(*pud)) - continue; - pmd = pmd_offset(pud, 0); - if (PTRS_PER_PMD > 1) /* not folded */ - mm_walk_set_prot(pmd,flags); - for (m = 0; m < PTRS_PER_PMD; m++, pmd++) { - if (pmd_none(*pmd)) - continue; - pte = pte_offset_kernel(pmd,0); - mm_walk_set_prot(pte,flags); - } - } - } -} - -void mm_pin(struct mm_struct *mm) -{ - spin_lock(&mm->page_table_lock); - - mm_walk(mm, PAGE_KERNEL_RO); - BUG_ON(HYPERVISOR_update_va_mapping( - (unsigned long)mm->pgd, - pfn_pte(virt_to_phys(mm->pgd)>>PAGE_SHIFT, PAGE_KERNEL_RO), - UVMF_TLB_FLUSH)); - BUG_ON(HYPERVISOR_update_va_mapping( - (unsigned long)__user_pgd(mm->pgd), - pfn_pte(virt_to_phys(__user_pgd(mm->pgd))>>PAGE_SHIFT, PAGE_KERNEL_RO), - UVMF_TLB_FLUSH)); - xen_pgd_pin(__pa(mm->pgd)); /* kernel */ - xen_pgd_pin(__pa(__user_pgd(mm->pgd))); /* user */ - mm->context.pinned = 1; - spin_lock(&mm_unpinned_lock); - list_del(&mm->context.unpinned); - spin_unlock(&mm_unpinned_lock); - - spin_unlock(&mm->page_table_lock); -} - -void mm_unpin(struct mm_struct *mm) -{ - spin_lock(&mm->page_table_lock); - - xen_pgd_unpin(__pa(mm->pgd)); - xen_pgd_unpin(__pa(__user_pgd(mm->pgd))); - BUG_ON(HYPERVISOR_update_va_mapping( - (unsigned long)mm->pgd, - pfn_pte(virt_to_phys(mm->pgd)>>PAGE_SHIFT, PAGE_KERNEL), 0)); - BUG_ON(HYPERVISOR_update_va_mapping( - (unsigned long)__user_pgd(mm->pgd), - pfn_pte(virt_to_phys(__user_pgd(mm->pgd))>>PAGE_SHIFT, PAGE_KERNEL), 0)); - mm_walk(mm, PAGE_KERNEL); - xen_tlb_flush(); - mm->context.pinned = 0; - spin_lock(&mm_unpinned_lock); - list_add(&mm->context.unpinned, &mm_unpinned); - spin_unlock(&mm_unpinned_lock); - - spin_unlock(&mm->page_table_lock); -} - -void mm_pin_all(void) -{ - while (!list_empty(&mm_unpinned)) - mm_pin(list_entry(mm_unpinned.next, struct mm_struct, - context.unpinned)); -} - -void _arch_exit_mmap(struct mm_struct *mm) -{ - struct task_struct *tsk = current; - - task_lock(tsk); - - /* - * We aggressively remove defunct pgd from cr3. We execute unmap_vmas() - * *much* faster this way, as no tlb flushes means bigger wrpt batches. - */ - if ( tsk->active_mm == mm ) - { - tsk->active_mm = &init_mm; - atomic_inc(&init_mm.mm_count); - - switch_mm(mm, &init_mm, tsk); - - atomic_dec(&mm->mm_count); - BUG_ON(atomic_read(&mm->mm_count) == 0); - } - - task_unlock(tsk); - - if ( mm->context.pinned && (atomic_read(&mm->mm_count) == 1) ) - mm_unpin(mm); -} - -void pte_free(struct page *pte) -{ - unsigned long va = (unsigned long)__va(page_to_pfn(pte)<<PAGE_SHIFT); - - if (!pte_write(*virt_to_ptep(va))) - BUG_ON(HYPERVISOR_update_va_mapping( - va, pfn_pte(page_to_pfn(pte), PAGE_KERNEL), 0)); - __free_page(pte); -} -#endif /* CONFIG_XEN */ - -static inline pte_t *lookup_address(unsigned long address) -{ - pgd_t *pgd = pgd_offset_k(address); - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - if (pgd_none(*pgd)) - return NULL; - pud = pud_offset(pgd, address); - if (!pud_present(*pud)) - return NULL; - pmd = pmd_offset(pud, address); - if (!pmd_present(*pmd)) - return NULL; - if (pmd_large(*pmd)) - return (pte_t *)pmd; - pte = pte_offset_kernel(pmd, address); - if (pte && !pte_present(*pte)) - pte = NULL; - return pte; -} - -static struct page *split_large_page(unsigned long address, pgprot_t prot, - pgprot_t ref_prot) -{ - int i; - unsigned long addr; - struct page *base = alloc_pages(GFP_KERNEL, 0); - pte_t *pbase; - if (!base) - return NULL; - address = __pa(address); - addr = address & LARGE_PAGE_MASK; - pbase = (pte_t *)page_address(base); - for (i = 0; i < PTRS_PER_PTE; i++, addr += PAGE_SIZE) { - pbase[i] = pfn_pte(addr >> PAGE_SHIFT, - addr == address ? prot : ref_prot); - } - return base; -} - - -static void flush_kernel_map(void *address) -{ - if (0 && address && cpu_has_clflush) { - /* is this worth it? */ - int i; - for (i = 0; i < PAGE_SIZE; i += boot_cpu_data.x86_clflush_size) - asm volatile("clflush (%0)" :: "r" (address + i)); - } else - asm volatile("wbinvd":::"memory"); - if (address) - __flush_tlb_one(address); - else - __flush_tlb_all(); -} - - -static inline void flush_map(unsigned long address) -{ - on_each_cpu(flush_kernel_map, (void *)address, 1, 1); -} - -struct deferred_page { - struct deferred_page *next; - struct page *fpage; - unsigned long address; -}; -static struct deferred_page *df_list; /* protected by init_mm.mmap_sem */ - -static inline void save_page(unsigned long address, struct page *fpage) -{ - struct deferred_page *df; - df = kmalloc(sizeof(struct deferred_page), GFP_KERNEL); - if (!df) { - flush_map(address); - __free_page(fpage); - } else { - df->next = df_list; - df->fpage = fpage; - df->address = address; - df_list = df; - } -} - -/* - * No more special protections in this 2/4MB area - revert to a - * large page again. - */ -static void revert_page(unsigned long address, pgprot_t ref_prot) -{ - pgd_t *pgd; - pud_t *pud; - pmd_t *pmd; - pte_t large_pte; - - pgd = pgd_offset_k(address); - BUG_ON(pgd_none(*pgd)); - pud = pud_offset(pgd,address); - BUG_ON(pud_none(*pud)); - pmd = pmd_offset(pud, address); - BUG_ON(pmd_val(*pmd) & _PAGE_PSE); - pgprot_val(ref_prot) |= _PAGE_PSE; - large_pte = mk_pte_phys(__pa(address) & LARGE_PAGE_MASK, ref_prot); - set_pte((pte_t *)pmd, large_pte); -} - -static int -__change_page_attr(unsigned long address, unsigned long pfn, pgprot_t prot, - pgprot_t ref_prot) -{ - pte_t *kpte; - struct page *kpte_page; - unsigned kpte_flags; - kpte = lookup_address(address); - if (!kpte) return 0; - kpte_page = virt_to_page(((unsigned long)kpte) & PAGE_MASK); - kpte_flags = pte_val(*kpte); - if (pgprot_val(prot) != pgprot_val(ref_prot)) { - if ((kpte_flags & _PAGE_PSE) == 0) { - set_pte(kpte, pfn_pte(pfn, prot)); - } else { - /* - * split_large_page will take the reference for this change_page_attr - * on the split page. - */ - struct page *split = split_large_page(address, prot, ref_prot); - if (!split) - return -ENOMEM; - set_pte(kpte,mk_pte(split, ref_prot)); - kpte_page = split; - } - get_page(kpte_page); - } else if ((kpte_flags & _PAGE_PSE) == 0) { - set_pte(kpte, pfn_pte(pfn, ref_prot)); - __put_page(kpte_page); - } else - BUG(); - - /* on x86-64 the direct mapping set at boot is not using 4k pages */ - /* - * ..., but the XEN guest kernels (currently) do: - * If the pte was reserved, it means it was created at boot - * time (not via split_large_page) and in turn we must not - * replace it with a large page. - */ -#ifndef CONFIG_XEN - BUG_ON(PageReserved(kpte_page)); -#else - if (!PageReserved(kpte_page)) -#endif - switch (page_count(kpte_page)) { - case 1: - save_page(address, kpte_page); - revert_page(address, ref_prot); - break; - case 0: - BUG(); /* memleak and failed 2M page regeneration */ - } - return 0; -} - -/* - * Change the page attributes of an page in the linear mapping. - * - * This should be used when a page is mapped with a different caching policy - * than write-back somewhere - some CPUs do not like it when mappings with - * different caching policies exist. This changes the page attributes of the - * in kernel linear mapping too. - * - * The caller needs to ensure that there are no conflicting mappings elsewhere. - * This function only deals with the kernel linear map. - * - * Caller must call global_flush_tlb() after this. - */ -int change_page_attr_addr(unsigned long address, int numpages, pgprot_t prot) -{ - int err = 0; - int i; - - down_write(&init_mm.mmap_sem); - for (i = 0; i < numpages; i++, address += PAGE_SIZE) { - unsigned long pfn = __pa(address) >> PAGE_SHIFT; - - err = __change_page_attr(address, pfn, prot, PAGE_KERNEL); - if (err) - break; - /* Handle kernel mapping too which aliases part of the - * lowmem */ - if (__pa(address) < KERNEL_TEXT_SIZE) { - unsigned long addr2; - pgprot_t prot2 = prot; - addr2 = __START_KERNEL_map + __pa(address); - pgprot_val(prot2) &= ~_PAGE_NX; - err = __change_page_attr(addr2, pfn, prot2, PAGE_KERNEL_EXEC); - } - } - up_write(&init_mm.mmap_sem); - return err; -} - -/* Don't call this for MMIO areas that may not have a mem_map entry */ -int change_page_attr(struct page *page, int numpages, pgprot_t prot) -{ - unsigned long addr = (unsigned long)page_address(page); - return change_page_attr_addr(addr, numpages, prot); -} - -void global_flush_tlb(void) -{ - struct deferred_page *df, *next_df; - - down_read(&init_mm.mmap_sem); - df = xchg(&df_list, NULL); - up_read(&init_mm.mmap_sem); - if (!df) - return; - flush_map((df && !df->next) ? df->address : 0); - for (; df; df = next_df) { - next_df = df->next; - if (df->fpage) - __free_page(df->fpage); - kfree(df); - } -} - -EXPORT_SYMBOL(change_page_attr); -EXPORT_SYMBOL(global_flush_tlb); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/pci/Makefile --- a/linux-2.6-xen-sparse/arch/xen/x86_64/pci/Makefile Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,39 +0,0 @@ -# -# Makefile for X86_64 specific PCI routines -# -# Reuse the i386 PCI subsystem -# -XENARCH := $(subst ",,$(CONFIG_XENARCH)) -CFLAGS += -Iarch/$(XENARCH)/pci - -CFLAGS += -Iarch/i386/pci - -c-xen-obj-y := i386.o -c-i386-obj-y += fixup.o -c-i386-obj-$(CONFIG_ACPI_PCI) += acpi.o -c-i386-obj-y += legacy.o common.o -c-i386-obj-$(CONFIG_PCI_DIRECT)+= direct.o -c-xen-obj-y += irq.o -# mmconfig has a 64bit special -c-obj-$(CONFIG_PCI_MMCONFIG) += mmconfig.o - -c-obj-$(CONFIG_NUMA) += k8-bus.o - -c-link := - -$(patsubst %.o,$(obj)/%.c,$(c-xen-obj-y)): - @ln -fsn $(srctree)/arch/xen/i386/pci/$(notdir $@) $@ - -$(patsubst %.o,$(obj)/%.c,$(c-obj-y) $(c-link)): - @ln -fsn $(srctree)/arch/x86_64/pci/$(notdir $@) $@ - -$(patsubst %.o,$(obj)/%.c,$(c-i386-obj-y)): - @ln -fsn $(srctree)/arch/i386/pci/$(notdir $@) $@ - -# Make sure irq.o gets linked in before common.o -obj-y += $(patsubst common.o,$(c-xen-obj-y) common.o,$(c-i386-obj-y)) -obj-y += $(c-obj-y) - -clean-files += $(patsubst %.o,%.c,$(c-obj-y) $(c-obj-) $(c-link)) -clean-files += $(patsubst %.o,%.c,$(c-i386-obj-y) $(c-i386-obj-)) -clean-files += $(patsubst %.o,%.c,$(c-xen-obj-y) $(c-xen-obj-)) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/arch/xen/x86_64/pci/Makefile-BUS --- a/linux-2.6-xen-sparse/arch/xen/x86_64/pci/Makefile-BUS Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,22 +0,0 @@ -# -# Makefile for X86_64 specific PCI routines -# -# Reuse the i386 PCI subsystem -# -CFLAGS += -I arch/i386/pci - -obj-y := i386.o -obj-$(CONFIG_PCI_DIRECT)+= direct.o -obj-y += fixup.o -obj-$(CONFIG_ACPI_PCI) += acpi.o -obj-y += legacy.o irq.o common.o -# mmconfig has a 64bit special -obj-$(CONFIG_PCI_MMCONFIG) += mmconfig.o - -direct-y += ../../i386/pci/direct.o -acpi-y += ../../i386/pci/acpi.o -legacy-y += ../../i386/pci/legacy.o -irq-y += ../../i386/pci/irq.o -common-y += ../../i386/pci/common.o -fixup-y += ../../i386/pci/fixup.o -i386-y += ../../i386/pci/i386.o diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/drivers/char/tpm/Kconfig.domU --- a/linux-2.6-xen-sparse/drivers/char/tpm/Kconfig.domU Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,30 +0,0 @@ -# -# TPM device configuration -# - -menu "TPM devices" - -config TCG_TPM - tristate "TPM Support for XEN" - depends on ARCH_XEN && !XEN_PHYSDEV_ACCESS - ---help--- - If you want to make TPM security available in your system, - say Yes and it will be accessible from within a user domain. For - more information see <http://www.trustedcomputinggroup.org>. - An implementation of the Trusted Software Stack (TSS), the - userspace enablement piece of the specification, can be - obtained at: <http://sourceforge.net/projects/trousers>. To - compile this driver as a module, choose M here; the module - will be called tpm. If unsure, say N. - -config TCG_XEN - tristate "XEN TPM Interface" - depends on TCG_TPM && ARCH_XEN && XEN_TPMDEV_FRONTEND - ---help--- - If you want to make TPM support available to a Xen - user domain, say Yes and it will - be accessible from within Linux. To compile this driver - as a module, choose M here; the module will be called - tpm_xen. - -endmenu diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/agp.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/agp.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,37 +0,0 @@ -#ifndef AGP_H -#define AGP_H 1 - -#include <asm/pgtable.h> -#include <asm/cacheflush.h> -#include <asm/system.h> - -/* - * Functions to keep the agpgart mappings coherent with the MMU. - * The GART gives the CPU a physical alias of pages in memory. The alias region is - * mapped uncacheable. Make sure there are no conflicting mappings - * with different cachability attributes for the same page. This avoids - * data corruption on some CPUs. - */ - -int map_page_into_agp(struct page *page); -int unmap_page_from_agp(struct page *page); -#define flush_agp_mappings() global_flush_tlb() - -/* Could use CLFLUSH here if the cpu supports it. But then it would - need to be called for each cacheline of the whole page so it may not be - worth it. Would need a page for it. */ -#define flush_agp_cache() wbinvd() - -/* Convert a physical address to an address suitable for the GART. */ -#define phys_to_gart(x) phys_to_machine(x) -#define gart_to_phys(x) machine_to_phys(x) - -/* GATT allocation. Returns/accepts GATT kernel virtual address. */ -#define alloc_gatt_pages(order) ({ \ - char *_t; dma_addr_t _d; \ - _t = dma_alloc_coherent(NULL,PAGE_SIZE<<(order),&_d,GFP_KERNEL); \ - _t; }) -#define free_gatt_pages(table, order) \ - dma_free_coherent(NULL,PAGE_SIZE<<(order),(table),virt_to_bus(table)) - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/desc.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/desc.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,148 +0,0 @@ -#ifndef __ARCH_DESC_H -#define __ARCH_DESC_H - -#include <asm/ldt.h> -#include <asm/segment.h> - -#define CPU_16BIT_STACK_SIZE 1024 - -#ifndef __ASSEMBLY__ - -#include <linux/preempt.h> -#include <linux/smp.h> - -#include <asm/mmu.h> - -extern struct desc_struct cpu_gdt_table[NR_CPUS][GDT_ENTRIES]; - -DECLARE_PER_CPU(unsigned char, cpu_16bit_stack[CPU_16BIT_STACK_SIZE]); - -struct Xgt_desc_struct { - unsigned short size; - unsigned long address __attribute__((packed)); - unsigned short pad; -} __attribute__ ((packed)); - -extern struct Xgt_desc_struct idt_descr, cpu_gdt_descr[NR_CPUS]; - -#define load_TR_desc() __asm__ __volatile__("ltr %%ax"::"a" (GDT_ENTRY_TSS*8)) -#define load_LDT_desc() __asm__ __volatile__("lldt %%ax"::"a" (GDT_ENTRY_LDT*8)) - -#define get_cpu_gdt_table(_cpu) ((struct desc_struct *)cpu_gdt_descr[(_cpu)].address) - -/* - * This is the ldt that every process will get unless we need - * something other than this. - */ -extern struct desc_struct default_ldt[]; -extern void set_intr_gate(unsigned int irq, void * addr); - -#define _set_tssldt_desc(n,addr,limit,type) \ -__asm__ __volatile__ ("movw %w3,0(%2)\n\t" \ - "movw %%ax,2(%2)\n\t" \ - "rorl $16,%%eax\n\t" \ - "movb %%al,4(%2)\n\t" \ - "movb %4,5(%2)\n\t" \ - "movb $0,6(%2)\n\t" \ - "movb %%ah,7(%2)\n\t" \ - "rorl $16,%%eax" \ - : "=m"(*(n)) : "a" (addr), "r"(n), "ir"(limit), "i"(type)) - -static inline void __set_tss_desc(unsigned int cpu, unsigned int entry, void *addr) -{ - _set_tssldt_desc(&get_cpu_gdt_table(cpu)[entry], (int)addr, - offsetof(struct tss_struct, __cacheline_filler) - 1, 0x89); -} - -#define set_tss_desc(cpu,addr) __set_tss_desc(cpu, GDT_ENTRY_TSS, addr) - -static inline void set_ldt_desc(unsigned int cpu, void *addr, unsigned int size) -{ - _set_tssldt_desc(&get_cpu_gdt_table(cpu)[GDT_ENTRY_LDT], - (int)addr, ((size << 3)-1), 0x82); -} - -#define LDT_entry_a(info) \ - ((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff)) - -#define LDT_entry_b(info) \ - (((info)->base_addr & 0xff000000) | \ - (((info)->base_addr & 0x00ff0000) >> 16) | \ - ((info)->limit & 0xf0000) | \ - (((info)->read_exec_only ^ 1) << 9) | \ - ((info)->contents << 10) | \ - (((info)->seg_not_present ^ 1) << 15) | \ - ((info)->seg_32bit << 22) | \ - ((info)->limit_in_pages << 23) | \ - ((info)->useable << 20) | \ - 0x7000) - -#define LDT_empty(info) (\ - (info)->base_addr == 0 && \ - (info)->limit == 0 && \ - (info)->contents == 0 && \ - (info)->read_exec_only == 1 && \ - (info)->seg_32bit == 0 && \ - (info)->limit_in_pages == 0 && \ - (info)->seg_not_present == 1 && \ - (info)->useable == 0 ) - -extern int write_ldt_entry(void *ldt, int entry, __u32 entry_a, __u32 entry_b); - -#if TLS_SIZE != 24 -# error update this code. -#endif - -static inline void load_TLS(struct thread_struct *t, unsigned int cpu) -{ -#define C(i) HYPERVISOR_update_descriptor(virt_to_machine(&get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN + i]), *(u64 *)&t->tls_array[i]) - C(0); C(1); C(2); -#undef C -} - -static inline void clear_LDT(void) -{ - int cpu = get_cpu(); - - /* - * NB. We load the default_ldt for lcall7/27 handling on demand, as - * it slows down context switching. Noone uses it anyway. - */ - cpu = cpu; /* XXX avoid compiler warning */ - xen_set_ldt(0UL, 0); - put_cpu(); -} - -/* - * load one particular LDT into the current CPU - */ -static inline void load_LDT_nolock(mm_context_t *pc, int cpu) -{ - void *segments = pc->ldt; - int count = pc->size; - - if (likely(!count)) - segments = NULL; - - xen_set_ldt((unsigned long)segments, count); -} - -static inline void load_LDT(mm_context_t *pc) -{ - int cpu = get_cpu(); - load_LDT_nolock(pc, cpu); - put_cpu(); -} - -static inline unsigned long get_desc_base(unsigned long *desc) -{ - unsigned long base; - base = ((desc[0] >> 16) & 0x0000ffff) | - ((desc[1] << 16) & 0x00ff0000) | - (desc[1] & 0xff000000); - return base; -} - -#endif /* !__ASSEMBLY__ */ - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/dma-mapping.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/dma-mapping.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,156 +0,0 @@ -#ifndef _ASM_I386_DMA_MAPPING_H -#define _ASM_I386_DMA_MAPPING_H - -/* - * IOMMU interface. See Documentation/DMA-mapping.txt and DMA-API.txt for - * documentation. - */ - -#include <linux/config.h> -#include <linux/mm.h> -#include <asm/cache.h> -#include <asm/io.h> -#include <asm/scatterlist.h> -#include <asm-i386/swiotlb.h> - -static inline int -address_needs_mapping(struct device *hwdev, dma_addr_t addr) -{ - dma_addr_t mask = 0xffffffff; - /* If the device has a mask, use it, otherwise default to 32 bits */ - if (hwdev && hwdev->dma_mask) - mask = *hwdev->dma_mask; - return (addr & ~mask) != 0; -} - -static inline int -range_straddles_page_boundary(void *p, size_t size) -{ - extern unsigned long *contiguous_bitmap; - return (((((unsigned long)p & ~PAGE_MASK) + size) > PAGE_SIZE) && - !test_bit(__pa(p) >> PAGE_SHIFT, contiguous_bitmap)); -} - -#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) -#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h) - -void *dma_alloc_coherent(struct device *dev, size_t size, - dma_addr_t *dma_handle, unsigned int __nocast flag); - -void dma_free_coherent(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle); - -extern dma_addr_t -dma_map_single(struct device *dev, void *ptr, size_t size, - enum dma_data_direction direction); - -extern void -dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size, - enum dma_data_direction direction); - -extern int dma_map_sg(struct device *hwdev, struct scatterlist *sg, - int nents, enum dma_data_direction direction); -extern void dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, - int nents, enum dma_data_direction direction); - -extern dma_addr_t -dma_map_page(struct device *dev, struct page *page, unsigned long offset, - size_t size, enum dma_data_direction direction); - -extern void -dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size, - enum dma_data_direction direction); - -extern void -dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, - enum dma_data_direction direction); - -extern void -dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size, - enum dma_data_direction direction); - -static inline void -dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle, - unsigned long offset, size_t size, - enum dma_data_direction direction) -{ - dma_sync_single_for_cpu(dev, dma_handle+offset, size, direction); -} - -static inline void -dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle, - unsigned long offset, size_t size, - enum dma_data_direction direction) -{ - dma_sync_single_for_device(dev, dma_handle+offset, size, direction); -} - -static inline void -dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems, - enum dma_data_direction direction) -{ - if (swiotlb) - swiotlb_sync_sg_for_cpu(dev,sg,nelems,direction); - flush_write_buffers(); -} - -static inline void -dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, - enum dma_data_direction direction) -{ - if (swiotlb) - swiotlb_sync_sg_for_device(dev,sg,nelems,direction); - flush_write_buffers(); -} - -extern int -dma_mapping_error(dma_addr_t dma_addr); - -extern int -dma_supported(struct device *dev, u64 mask); - -static inline int -dma_set_mask(struct device *dev, u64 mask) -{ - if(!dev->dma_mask || !dma_supported(dev, mask)) - return -EIO; - - *dev->dma_mask = mask; - - return 0; -} - -#ifdef __i386__ -static inline int -dma_get_cache_alignment(void) -{ - /* no easy way to get cache size on all x86, so return the - * maximum possible, to be safe */ - return (1 << L1_CACHE_SHIFT_MAX); -} -#else -extern int dma_get_cache_alignment(void); -#endif - -#define dma_is_consistent(d) (1) - -static inline void -dma_cache_sync(void *vaddr, size_t size, - enum dma_data_direction direction) -{ - flush_write_buffers(); -} - -#define ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY -extern int -dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, - dma_addr_t device_addr, size_t size, int flags); - -extern void -dma_release_declared_memory(struct device *dev); - -extern void * -dma_mark_declared_memory_occupied(struct device *dev, - dma_addr_t device_addr, size_t size); - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/fixmap.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/fixmap.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,167 +0,0 @@ -/* - * fixmap.h: compile-time virtual memory allocation - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 1998 Ingo Molnar - * - * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 - */ - -#ifndef _ASM_FIXMAP_H -#define _ASM_FIXMAP_H - -#include <linux/config.h> - -/* used by vmalloc.c, vsyscall.lds.S. - * - * Leave one empty page between vmalloc'ed areas and - * the start of the fixmap. - */ -#define __FIXADDR_TOP (HYPERVISOR_VIRT_START - 2 * PAGE_SIZE) - -#ifndef __ASSEMBLY__ -#include <linux/kernel.h> -#include <asm/acpi.h> -#include <asm/apicdef.h> -#include <asm/page.h> -#include <asm-xen/gnttab.h> -#ifdef CONFIG_HIGHMEM -#include <linux/threads.h> -#include <asm/kmap_types.h> -#endif - -/* - * Here we define all the compile-time 'special' virtual - * addresses. The point is to have a constant address at - * compile time, but to set the physical address only - * in the boot process. We allocate these special addresses - * from the end of virtual memory (0xfffff000) backwards. - * Also this lets us do fail-safe vmalloc(), we - * can guarantee that these special addresses and - * vmalloc()-ed addresses never overlap. - * - * these 'compile-time allocated' memory buffers are - * fixed-size 4k pages. (or larger if used with an increment - * highger than 1) use fixmap_set(idx,phys) to associate - * physical memory with fixmap indices. - * - * TLB entries of such buffers will not be flushed across - * task switches. - */ -enum fixed_addresses { - FIX_HOLE, - FIX_VSYSCALL, -#ifdef CONFIG_X86_LOCAL_APIC - FIX_APIC_BASE, /* local (CPU) APIC) -- required for SMP or not */ -#endif -#ifdef CONFIG_X86_IO_APIC - FIX_IO_APIC_BASE_0, - FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS-1, -#endif -#ifdef CONFIG_X86_VISWS_APIC - FIX_CO_CPU, /* Cobalt timer */ - FIX_CO_APIC, /* Cobalt APIC Redirection Table */ - FIX_LI_PCIA, /* Lithium PCI Bridge A */ - FIX_LI_PCIB, /* Lithium PCI Bridge B */ -#endif -#ifdef CONFIG_X86_F00F_BUG - FIX_F00F_IDT, /* Virtual mapping for IDT */ -#endif -#ifdef CONFIG_X86_CYCLONE_TIMER - FIX_CYCLONE_TIMER, /*cyclone timer register*/ -#endif -#ifdef CONFIG_HIGHMEM - FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ - FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, -#endif -#ifdef CONFIG_ACPI_BOOT - FIX_ACPI_BEGIN, - FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1, -#endif -#ifdef CONFIG_PCI_MMCONFIG - FIX_PCIE_MCFG, -#endif - FIX_SHARED_INFO, - FIX_GNTTAB_BEGIN, - FIX_GNTTAB_END = FIX_GNTTAB_BEGIN + NR_GRANT_FRAMES - 1, -#ifdef CONFIG_XEN_PHYSDEV_ACCESS -#define NR_FIX_ISAMAPS 256 - FIX_ISAMAP_END, - FIX_ISAMAP_BEGIN = FIX_ISAMAP_END + NR_FIX_ISAMAPS - 1, -#endif - __end_of_permanent_fixed_addresses, - /* temporary boot-time mappings, used before ioremap() is functional */ -#define NR_FIX_BTMAPS 16 - FIX_BTMAP_END = __end_of_permanent_fixed_addresses, - FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS - 1, - FIX_WP_TEST, - __end_of_fixed_addresses -}; - -extern void __set_fixmap( - enum fixed_addresses idx, maddr_t phys, pgprot_t flags); - -#define set_fixmap(idx, phys) \ - __set_fixmap(idx, phys, PAGE_KERNEL) -/* - * Some hardware wants to get fixmapped without caching. - */ -#define set_fixmap_nocache(idx, phys) \ - __set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE) - -#define clear_fixmap(idx) \ - __set_fixmap(idx, 0, __pgprot(0)) - -#define FIXADDR_TOP ((unsigned long)__FIXADDR_TOP) - -#define __FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) -#define __FIXADDR_BOOT_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) -#define FIXADDR_START (FIXADDR_TOP - __FIXADDR_SIZE) -#define FIXADDR_BOOT_START (FIXADDR_TOP - __FIXADDR_BOOT_SIZE) - -#define __fix_to_virt(x) (FIXADDR_TOP - ((x) << PAGE_SHIFT)) -#define __virt_to_fix(x) ((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT) - -/* - * This is the range that is readable by user mode, and things - * acting like user mode such as get_user_pages. - */ -#define FIXADDR_USER_START (__fix_to_virt(FIX_VSYSCALL)) -#define FIXADDR_USER_END (FIXADDR_USER_START + PAGE_SIZE) - - -extern void __this_fixmap_does_not_exist(void); - -/* - * 'index to address' translation. If anyone tries to use the idx - * directly without tranlation, we catch the bug with a NULL-deference - * kernel oops. Illegal ranges of incoming indices are caught too. - */ -static __always_inline unsigned long fix_to_virt(const unsigned int idx) -{ - /* - * this branch gets completely eliminated after inlining, - * except when someone tries to use fixaddr indices in an - * illegal way. (such as mixing up address types or using - * out-of-range indices). - * - * If it doesn't get removed, the linker will complain - * loudly with a reasonably clear error message.. - */ - if (idx >= __end_of_fixed_addresses) - __this_fixmap_does_not_exist(); - - return __fix_to_virt(idx); -} - -static inline unsigned long virt_to_fix(const unsigned long vaddr) -{ - BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START); - return __virt_to_fix(vaddr); -} - -#endif /* !__ASSEMBLY__ */ -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/floppy.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/floppy.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,147 +0,0 @@ -/* - * Architecture specific parts of the Floppy driver - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 1995 - * - * Modifications for Xen are Copyright (c) 2004, Keir Fraser. - */ -#ifndef __ASM_XEN_I386_FLOPPY_H -#define __ASM_XEN_I386_FLOPPY_H - -#include <linux/vmalloc.h> - -/* XEN: Hit DMA paths on the head. This trick from asm-m68k/floppy.h. */ -#include <asm/dma.h> -#undef MAX_DMA_ADDRESS -#define MAX_DMA_ADDRESS 0 -#define CROSS_64KB(a,s) (0) - -#define fd_inb(port) inb_p(port) -#define fd_outb(value,port) outb_p(value,port) - -#define fd_request_dma() (0) -#define fd_free_dma() ((void)0) -#define fd_enable_irq() enable_irq(FLOPPY_IRQ) -#define fd_disable_irq() disable_irq(FLOPPY_IRQ) -#define fd_free_irq() free_irq(FLOPPY_IRQ, NULL) -#define fd_get_dma_residue() (virtual_dma_count + virtual_dma_residue) -#define fd_dma_setup(addr, size, mode, io) vdma_dma_setup(addr, size, mode, io) -/* - * Do not use vmalloc/vfree: floppy_release_irq_and_dma() gets called from - * softirq context via motor_off_callback. A generic bug we happen to trigger. - */ -#define fd_dma_mem_alloc(size) __get_free_pages(GFP_KERNEL, get_order(size)) -#define fd_dma_mem_free(addr, size) free_pages(addr, get_order(size)) - -static int virtual_dma_count; -static int virtual_dma_residue; -static char *virtual_dma_addr; -static int virtual_dma_mode; -static int doing_pdma; - -static irqreturn_t floppy_hardint(int irq, void *dev_id, struct pt_regs * regs) -{ - register unsigned char st; - register int lcount; - register char *lptr; - - if (!doing_pdma) - return floppy_interrupt(irq, dev_id, regs); - - st = 1; - for(lcount=virtual_dma_count, lptr=virtual_dma_addr; - lcount; lcount--, lptr++) { - st=inb(virtual_dma_port+4) & 0xa0 ; - if(st != 0xa0) - break; - if(virtual_dma_mode) - outb_p(*lptr, virtual_dma_port+5); - else - *lptr = inb_p(virtual_dma_port+5); - } - virtual_dma_count = lcount; - virtual_dma_addr = lptr; - st = inb(virtual_dma_port+4); - - if(st == 0x20) - return IRQ_HANDLED; - if(!(st & 0x20)) { - virtual_dma_residue += virtual_dma_count; - virtual_dma_count=0; - doing_pdma = 0; - floppy_interrupt(irq, dev_id, regs); - return IRQ_HANDLED; - } - return IRQ_HANDLED; -} - -static void fd_disable_dma(void) -{ - doing_pdma = 0; - virtual_dma_residue += virtual_dma_count; - virtual_dma_count=0; -} - -static int fd_request_irq(void) -{ - return request_irq(FLOPPY_IRQ, floppy_hardint,SA_INTERRUPT, - "floppy", NULL); -} - -static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io) -{ - doing_pdma = 1; - virtual_dma_port = io; - virtual_dma_mode = (mode == DMA_MODE_WRITE); - virtual_dma_addr = addr; - virtual_dma_count = size; - virtual_dma_residue = 0; - return 0; -} - -/* XEN: This trick to force 'virtual DMA' is from include/asm-m68k/floppy.h. */ -#define FDC1 xen_floppy_init() -static int FDC2 = -1; - -static int xen_floppy_init(void) -{ - use_virtual_dma = 1; - can_use_virtual_dma = 1; - return 0x3f0; -} - -/* - * Floppy types are stored in the rtc's CMOS RAM and so rtc_lock - * is needed to prevent corrupted CMOS RAM in case "insmod floppy" - * coincides with another rtc CMOS user. Paul G. - */ -#define FLOPPY0_TYPE ({ \ - unsigned long flags; \ - unsigned char val; \ - spin_lock_irqsave(&rtc_lock, flags); \ - val = (CMOS_READ(0x10) >> 4) & 15; \ - spin_unlock_irqrestore(&rtc_lock, flags); \ - val; \ -}) - -#define FLOPPY1_TYPE ({ \ - unsigned long flags; \ - unsigned char val; \ - spin_lock_irqsave(&rtc_lock, flags); \ - val = CMOS_READ(0x10) & 15; \ - spin_unlock_irqrestore(&rtc_lock, flags); \ - val; \ -}) - -#define N_FDC 2 -#define N_DRIVE 8 - -#define FLOPPY_MOTOR_MASK 0xf0 - -#define EXTRA_FLOPPY_PARAMS - -#endif /* __ASM_XEN_I386_FLOPPY_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/highmem.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/highmem.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,80 +0,0 @@ -/* - * highmem.h: virtual kernel memory mappings for high memory - * - * Used in CONFIG_HIGHMEM systems for memory pages which - * are not addressable by direct kernel virtual addresses. - * - * Copyright (C) 1999 Gerhard Wichert, Siemens AG - * Gerhard.Wichert@xxxxxxxxxxxxxx - * - * - * Redesigned the x86 32-bit VM architecture to deal with - * up to 16 Terabyte physical memory. With current x86 CPUs - * we now support up to 64 Gigabytes physical RAM. - * - * Copyright (C) 1999 Ingo Molnar <mingo@xxxxxxxxxx> - */ - -#ifndef _ASM_HIGHMEM_H -#define _ASM_HIGHMEM_H - -#ifdef __KERNEL__ - -#include <linux/config.h> -#include <linux/interrupt.h> -#include <linux/threads.h> -#include <asm/kmap_types.h> -#include <asm/tlbflush.h> - -/* declarations for highmem.c */ -extern unsigned long highstart_pfn, highend_pfn; - -extern pte_t *kmap_pte; -extern pgprot_t kmap_prot; -extern pte_t *pkmap_page_table; - -/* - * Right now we initialize only a single pte table. It can be extended - * easily, subsequent pte tables have to be allocated in one physical - * chunk of RAM. - */ -#ifdef CONFIG_X86_PAE -#define LAST_PKMAP 512 -#else -#define LAST_PKMAP 1024 -#endif -/* - * Ordering is: - * - * FIXADDR_TOP - * fixed_addresses - * FIXADDR_START - * temp fixed addresses - * FIXADDR_BOOT_START - * Persistent kmap area - * PKMAP_BASE - * VMALLOC_END - * Vmalloc area - * VMALLOC_START - * high_memory - */ -#define PKMAP_BASE ( (FIXADDR_BOOT_START - PAGE_SIZE*(LAST_PKMAP + 1)) & PMD_MASK ) -#define LAST_PKMAP_MASK (LAST_PKMAP-1) -#define PKMAP_NR(virt) ((virt-PKMAP_BASE) >> PAGE_SHIFT) -#define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT)) - -extern void * FASTCALL(kmap_high(struct page *page)); -extern void FASTCALL(kunmap_high(struct page *page)); - -void *kmap(struct page *page); -void kunmap(struct page *page); -void *kmap_atomic(struct page *page, enum km_type type); -void *kmap_atomic_pte(struct page *page, enum km_type type); -void kunmap_atomic(void *kvaddr, enum km_type type); -struct page *kmap_atomic_to_page(void *ptr); - -#define flush_cache_kmaps() do { } while (0) - -#endif /* __KERNEL__ */ - -#endif /* _ASM_HIGHMEM_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/hw_irq.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/hw_irq.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,71 +0,0 @@ -#ifndef _ASM_HW_IRQ_H -#define _ASM_HW_IRQ_H - -/* - * linux/include/asm/hw_irq.h - * - * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar - * - * moved some of the old arch/i386/kernel/irq.h to here. VY - * - * IRQ/IPI changes taken from work by Thomas Radke - * <tomsoft@xxxxxxxxxxxxxxxxxxxxxxxxx> - */ - -#include <linux/config.h> -#include <linux/profile.h> -#include <asm/atomic.h> -#include <asm/irq.h> -#include <asm/sections.h> - -/* - * Various low-level irq details needed by irq.c, process.c, - * time.c, io_apic.c and smp.c - * - * Interrupt entry/exit code at both C and assembly level - */ - -extern u8 irq_vector[NR_IRQ_VECTORS]; -#define IO_APIC_VECTOR(irq) (irq_vector[irq]) -#define AUTO_ASSIGN -1 - -extern void (*interrupt[NR_IRQS])(void); - -#ifdef CONFIG_SMP -fastcall void reschedule_interrupt(void); -fastcall void invalidate_interrupt(void); -fastcall void call_function_interrupt(void); -#endif - -#ifdef CONFIG_X86_LOCAL_APIC -fastcall void apic_timer_interrupt(void); -fastcall void error_interrupt(void); -fastcall void spurious_interrupt(void); -fastcall void thermal_interrupt(struct pt_regs *); -#define platform_legacy_irq(irq) ((irq) < 16) -#endif - -void disable_8259A_irq(unsigned int irq); -void enable_8259A_irq(unsigned int irq); -int i8259A_irq_pending(unsigned int irq); -void make_8259A_irq(unsigned int irq); -void init_8259A(int aeoi); -void FASTCALL(send_IPI_self(int vector)); -void init_VISWS_APIC_irqs(void); -void setup_IO_APIC(void); -void disable_IO_APIC(void); -void print_IO_APIC(void); -int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn); -void send_IPI(int dest, int vector); -void setup_ioapic_dest(void); - -extern unsigned long io_apic_irqs; - -extern atomic_t irq_err_count; -extern atomic_t irq_mis_count; - -#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs)) - -extern void hw_resend_irq(struct hw_interrupt_type *h, unsigned int i); - -#endif /* _ASM_HW_IRQ_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/hypercall.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/hypercall.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,323 +0,0 @@ -/****************************************************************************** - * hypercall.h - * - * Linux-specific hypervisor handling. - * - * Copyright (c) 2002-2004, K A Fraser - * - * This file may be distributed separately from the Linux kernel, or - * incorporated into other software packages, subject to the following license: - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this source file (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, copy, modify, - * merge, publish, distribute, sublicense, and/or sell copies of the Software, - * and to permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - */ - -#ifndef __HYPERCALL_H__ -#define __HYPERCALL_H__ - -#include <asm-xen/xen-public/xen.h> -#include <asm-xen/xen-public/sched.h> -#include <asm-xen/xen-public/nmi.h> - -#define __STR(x) #x -#define STR(x) __STR(x) - -#define _hypercall0(type, name) \ -({ \ - long __res; \ - asm volatile ( \ - "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ - : "=a" (__res) \ - : \ - : "memory" ); \ - (type)__res; \ -}) - -#define _hypercall1(type, name, a1) \ -({ \ - long __res, __ign1; \ - asm volatile ( \ - "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ - : "=a" (__res), "=b" (__ign1) \ - : "1" ((long)(a1)) \ - : "memory" ); \ - (type)__res; \ -}) - -#define _hypercall2(type, name, a1, a2) \ -({ \ - long __res, __ign1, __ign2; \ - asm volatile ( \ - "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ - : "=a" (__res), "=b" (__ign1), "=c" (__ign2) \ - : "1" ((long)(a1)), "2" ((long)(a2)) \ - : "memory" ); \ - (type)__res; \ -}) - -#define _hypercall3(type, name, a1, a2, a3) \ -({ \ - long __res, __ign1, __ign2, __ign3; \ - asm volatile ( \ - "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ - : "=a" (__res), "=b" (__ign1), "=c" (__ign2), \ - "=d" (__ign3) \ - : "1" ((long)(a1)), "2" ((long)(a2)), \ - "3" ((long)(a3)) \ - : "memory" ); \ - (type)__res; \ -}) - -#define _hypercall4(type, name, a1, a2, a3, a4) \ -({ \ - long __res, __ign1, __ign2, __ign3, __ign4; \ - asm volatile ( \ - "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ - : "=a" (__res), "=b" (__ign1), "=c" (__ign2), \ - "=d" (__ign3), "=S" (__ign4) \ - : "1" ((long)(a1)), "2" ((long)(a2)), \ - "3" ((long)(a3)), "4" ((long)(a4)) \ - : "memory" ); \ - (type)__res; \ -}) - -#define _hypercall5(type, name, a1, a2, a3, a4, a5) \ -({ \ - long __res, __ign1, __ign2, __ign3, __ign4, __ign5; \ - asm volatile ( \ - "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ - : "=a" (__res), "=b" (__ign1), "=c" (__ign2), \ - "=d" (__ign3), "=S" (__ign4), "=D" (__ign5) \ - : "1" ((long)(a1)), "2" ((long)(a2)), \ - "3" ((long)(a3)), "4" ((long)(a4)), \ - "5" ((long)(a5)) \ - : "memory" ); \ - (type)__res; \ -}) - -static inline int -HYPERVISOR_set_trap_table( - trap_info_t *table) -{ - return _hypercall1(int, set_trap_table, table); -} - -static inline int -HYPERVISOR_mmu_update( - mmu_update_t *req, int count, int *success_count, domid_t domid) -{ - return _hypercall4(int, mmu_update, req, count, success_count, domid); -} - -static inline int -HYPERVISOR_mmuext_op( - struct mmuext_op *op, int count, int *success_count, domid_t domid) -{ - return _hypercall4(int, mmuext_op, op, count, success_count, domid); -} - -static inline int -HYPERVISOR_set_gdt( - unsigned long *frame_list, int entries) -{ - return _hypercall2(int, set_gdt, frame_list, entries); -} - -static inline int -HYPERVISOR_stack_switch( - unsigned long ss, unsigned long esp) -{ - return _hypercall2(int, stack_switch, ss, esp); -} - -static inline int -HYPERVISOR_set_callbacks( - unsigned long event_selector, unsigned long event_address, - unsigned long failsafe_selector, unsigned long failsafe_address) -{ - return _hypercall4(int, set_callbacks, - event_selector, event_address, - failsafe_selector, failsafe_address); -} - -static inline int -HYPERVISOR_fpu_taskswitch( - int set) -{ - return _hypercall1(int, fpu_taskswitch, set); -} - -static inline int -HYPERVISOR_sched_op( - int cmd, unsigned long arg) -{ - return _hypercall2(int, sched_op, cmd, arg); -} - -static inline long -HYPERVISOR_set_timer_op( - u64 timeout) -{ - unsigned long timeout_hi = (unsigned long)(timeout>>32); - unsigned long timeout_lo = (unsigned long)timeout; - return _hypercall2(long, set_timer_op, timeout_lo, timeout_hi); -} - -static inline int -HYPERVISOR_dom0_op( - dom0_op_t *dom0_op) -{ - dom0_op->interface_version = DOM0_INTERFACE_VERSION; - return _hypercall1(int, dom0_op, dom0_op); -} - -static inline int -HYPERVISOR_set_debugreg( - int reg, unsigned long value) -{ - return _hypercall2(int, set_debugreg, reg, value); -} - -static inline unsigned long -HYPERVISOR_get_debugreg( - int reg) -{ - return _hypercall1(unsigned long, get_debugreg, reg); -} - -static inline int -HYPERVISOR_update_descriptor( - u64 ma, u64 desc) -{ - return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32); -} - -static inline int -HYPERVISOR_memory_op( - unsigned int cmd, void *arg) -{ - return _hypercall2(int, memory_op, cmd, arg); -} - -static inline int -HYPERVISOR_multicall( - void *call_list, int nr_calls) -{ - return _hypercall2(int, multicall, call_list, nr_calls); -} - -static inline int -HYPERVISOR_update_va_mapping( - unsigned long va, pte_t new_val, unsigned long flags) -{ - unsigned long pte_hi = 0; -#ifdef CONFIG_X86_PAE - pte_hi = new_val.pte_high; -#endif - return _hypercall4(int, update_va_mapping, va, - new_val.pte_low, pte_hi, flags); -} - -static inline int -HYPERVISOR_event_channel_op( - void *op) -{ - return _hypercall1(int, event_channel_op, op); -} - -static inline int -HYPERVISOR_xen_version( - int cmd, void *arg) -{ - return _hypercall2(int, xen_version, cmd, arg); -} - -static inline int -HYPERVISOR_console_io( - int cmd, int count, char *str) -{ - return _hypercall3(int, console_io, cmd, count, str); -} - -static inline int -HYPERVISOR_physdev_op( - void *physdev_op) -{ - return _hypercall1(int, physdev_op, physdev_op); -} - -static inline int -HYPERVISOR_grant_table_op( - unsigned int cmd, void *uop, unsigned int count) -{ - return _hypercall3(int, grant_table_op, cmd, uop, count); -} - -static inline int -HYPERVISOR_update_va_mapping_otherdomain( - unsigned long va, pte_t new_val, unsigned long flags, domid_t domid) -{ - unsigned long pte_hi = 0; -#ifdef CONFIG_X86_PAE - pte_hi = new_val.pte_high; -#endif - return _hypercall5(int, update_va_mapping_otherdomain, va, - new_val.pte_low, pte_hi, flags, domid); -} - -static inline int -HYPERVISOR_vm_assist( - unsigned int cmd, unsigned int type) -{ - return _hypercall2(int, vm_assist, cmd, type); -} - -static inline int -HYPERVISOR_vcpu_op( - int cmd, int vcpuid, void *extra_args) -{ - return _hypercall3(int, vcpu_op, cmd, vcpuid, extra_args); -} - -static inline int -HYPERVISOR_suspend( - unsigned long srec) -{ - return _hypercall3(int, sched_op, SCHEDOP_shutdown, - SHUTDOWN_suspend, srec); -} - -static inline int -HYPERVISOR_nmi_op( - unsigned long op, - unsigned long arg) -{ - return _hypercall2(int, nmi_op, op, arg); -} - -#endif /* __HYPERCALL_H__ */ - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/hypervisor.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/hypervisor.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,175 +0,0 @@ -/****************************************************************************** - * hypervisor.h - * - * Linux-specific hypervisor handling. - * - * Copyright (c) 2002-2004, K A Fraser - * - * This file may be distributed separately from the Linux kernel, or - * incorporated into other software packages, subject to the following license: - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this source file (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, copy, modify, - * merge, publish, distribute, sublicense, and/or sell copies of the Software, - * and to permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - */ - -#ifndef __HYPERVISOR_H__ -#define __HYPERVISOR_H__ - -#include <linux/config.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/version.h> -#include <asm-xen/xen-public/xen.h> -#include <asm-xen/xen-public/dom0_ops.h> -#include <asm/ptrace.h> -#include <asm/page.h> -#if defined(__i386__) -# ifdef CONFIG_X86_PAE -# include <asm-generic/pgtable-nopud.h> -# else -# include <asm-generic/pgtable-nopmd.h> -# endif -#endif - -extern shared_info_t *HYPERVISOR_shared_info; - -/* arch/xen/i386/kernel/setup.c */ -extern start_info_t *xen_start_info; - -/* arch/xen/kernel/evtchn.c */ -/* Force a proper event-channel callback from Xen. */ -void force_evtchn_callback(void); - -/* arch/xen/kernel/process.c */ -void xen_cpu_idle (void); - -/* arch/xen/i386/kernel/hypervisor.c */ -void do_hypervisor_callback(struct pt_regs *regs); - -/* arch/xen/i386/kernel/head.S */ -void lgdt_finish(void); - -/* arch/xen/i386/mm/hypervisor.c */ -/* - * NB. ptr values should be PHYSICAL, not MACHINE. 'vals' should be already - * be MACHINE addresses. - */ - -void xen_pt_switch(unsigned long ptr); -void xen_new_user_pt(unsigned long ptr); /* x86_64 only */ -void xen_load_gs(unsigned int selector); /* x86_64 only */ -void xen_tlb_flush(void); -void xen_invlpg(unsigned long ptr); - -#ifndef CONFIG_XEN_SHADOW_MODE -void xen_l1_entry_update(pte_t *ptr, pte_t val); -void xen_l2_entry_update(pmd_t *ptr, pmd_t val); -void xen_l3_entry_update(pud_t *ptr, pud_t val); /* x86_64/PAE */ -void xen_l4_entry_update(pgd_t *ptr, pgd_t val); /* x86_64 only */ -void xen_pgd_pin(unsigned long ptr); -void xen_pgd_unpin(unsigned long ptr); -void xen_pud_pin(unsigned long ptr); /* x86_64 only */ -void xen_pud_unpin(unsigned long ptr); /* x86_64 only */ -void xen_pmd_pin(unsigned long ptr); /* x86_64 only */ -void xen_pmd_unpin(unsigned long ptr); /* x86_64 only */ -void xen_pte_pin(unsigned long ptr); -void xen_pte_unpin(unsigned long ptr); -#else -#define xen_l1_entry_update(_p, _v) set_pte((_p), (_v)) -#define xen_l2_entry_update(_p, _v) set_pgd((_p), (_v)) -#define xen_pgd_pin(_p) ((void)0) -#define xen_pgd_unpin(_p) ((void)0) -#define xen_pte_pin(_p) ((void)0) -#define xen_pte_unpin(_p) ((void)0) -#endif - -void xen_set_ldt(unsigned long ptr, unsigned long bytes); -void xen_machphys_update(unsigned long mfn, unsigned long pfn); - -#ifdef CONFIG_SMP -#include <linux/cpumask.h> -void xen_tlb_flush_all(void); -void xen_invlpg_all(unsigned long ptr); -void xen_tlb_flush_mask(cpumask_t *mask); -void xen_invlpg_mask(cpumask_t *mask, unsigned long ptr); -#endif - -/* Returns zero on success else negative errno. */ -int xen_create_contiguous_region( - unsigned long vstart, unsigned int order, unsigned int address_bits); -void xen_destroy_contiguous_region( - unsigned long vstart, unsigned int order); - -#include <asm/hypercall.h> - -#if defined(CONFIG_X86_64) -#define MULTI_UVMFLAGS_INDEX 2 -#define MULTI_UVMDOMID_INDEX 3 -#else -#define MULTI_UVMFLAGS_INDEX 3 -#define MULTI_UVMDOMID_INDEX 4 -#endif - -#define xen_init() (0) - -static inline void -MULTI_update_va_mapping( - multicall_entry_t *mcl, unsigned long va, - pte_t new_val, unsigned long flags) -{ - mcl->op = __HYPERVISOR_update_va_mapping; - mcl->args[0] = va; -#if defined(CONFIG_X86_64) - mcl->args[1] = new_val.pte; - mcl->args[2] = flags; -#elif defined(CONFIG_X86_PAE) - mcl->args[1] = new_val.pte_low; - mcl->args[2] = new_val.pte_high; - mcl->args[3] = flags; -#else - mcl->args[1] = new_val.pte_low; - mcl->args[2] = 0; - mcl->args[3] = flags; -#endif -} - -static inline void -MULTI_update_va_mapping_otherdomain( - multicall_entry_t *mcl, unsigned long va, - pte_t new_val, unsigned long flags, domid_t domid) -{ - mcl->op = __HYPERVISOR_update_va_mapping_otherdomain; - mcl->args[0] = va; -#if defined(CONFIG_X86_64) - mcl->args[1] = new_val.pte; - mcl->args[2] = flags; - mcl->args[3] = domid; -#elif defined(CONFIG_X86_PAE) - mcl->args[1] = new_val.pte_low; - mcl->args[2] = new_val.pte_high; - mcl->args[3] = flags; - mcl->args[4] = domid; -#else - mcl->args[1] = new_val.pte_low; - mcl->args[2] = 0; - mcl->args[3] = flags; - mcl->args[4] = domid; -#endif -} - -#endif /* __HYPERVISOR_H__ */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/io.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/io.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,400 +0,0 @@ -#ifndef _ASM_IO_H -#define _ASM_IO_H - -#include <linux/config.h> -#include <linux/string.h> -#include <linux/compiler.h> - -/* - * This file contains the definitions for the x86 IO instructions - * inb/inw/inl/outb/outw/outl and the "string versions" of the same - * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing" - * versions of the single-IO instructions (inb_p/inw_p/..). - * - * This file is not meant to be obfuscating: it's just complicated - * to (a) handle it all in a way that makes gcc able to optimize it - * as well as possible and (b) trying to avoid writing the same thing - * over and over again with slight variations and possibly making a - * mistake somewhere. - */ - -/* - * Thanks to James van Artsdalen for a better timing-fix than - * the two short jumps: using outb's to a nonexistent port seems - * to guarantee better timings even on fast machines. - * - * On the other hand, I'd like to be sure of a non-existent port: - * I feel a bit unsafe about using 0x80 (should be safe, though) - * - * Linus - */ - - /* - * Bit simplified and optimized by Jan Hubicka - * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999. - * - * isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added, - * isa_read[wl] and isa_write[wl] fixed - * - Arnaldo Carvalho de Melo <acme@xxxxxxxxxxxxxxxx> - */ - -#define IO_SPACE_LIMIT 0xffff - -#define XQUAD_PORTIO_BASE 0xfe400000 -#define XQUAD_PORTIO_QUAD 0x40000 /* 256k per quad. */ - -#ifdef __KERNEL__ - -#include <asm-generic/iomap.h> - -#include <linux/vmalloc.h> -#include <asm/fixmap.h> - -/* - * Convert a physical pointer to a virtual kernel pointer for /dev/mem - * access - */ -#define xlate_dev_mem_ptr(p) __va(p) - -/* - * Convert a virtual cached pointer to an uncached pointer - */ -#define xlate_dev_kmem_ptr(p) p - -/** - * virt_to_phys - map virtual addresses to physical - * @address: address to remap - * - * The returned physical address is the physical (CPU) mapping for - * the memory address given. It is only valid to use this function on - * addresses directly mapped or allocated via kmalloc. - * - * This function does not give bus mappings for DMA transfers. In - * almost all conceivable cases a device driver should not be using - * this function - */ - -static inline unsigned long virt_to_phys(volatile void * address) -{ - return __pa(address); -} - -/** - * phys_to_virt - map physical address to virtual - * @address: address to remap - * - * The returned virtual address is a current CPU mapping for - * the memory address given. It is only valid to use this function on - * addresses that have a kernel mapping - * - * This function does not handle bus mappings for DMA transfers. In - * almost all conceivable cases a device driver should not be using - * this function - */ - -static inline void * phys_to_virt(unsigned long address) -{ - return __va(address); -} - -/* - * Change "struct page" to physical address. - */ -#define page_to_pseudophys(page) ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT) -#define page_to_phys(page) (phys_to_machine(page_to_pseudophys(page))) - -#define bio_to_pseudophys(bio) (page_to_pseudophys(bio_page((bio))) + \ - (unsigned long) bio_offset((bio))) -#define bvec_to_pseudophys(bv) (page_to_pseudophys((bv)->bv_page) + \ - (unsigned long) (bv)->bv_offset) - -#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ - (((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2))) && \ - ((bvec_to_pseudophys((vec1)) + (vec1)->bv_len) == \ - bvec_to_pseudophys((vec2)))) - -extern void __iomem * __ioremap(unsigned long offset, unsigned long size, unsigned long flags); - -/** - * ioremap - map bus memory into CPU space - * @offset: bus address of the memory - * @size: size of the resource to map - * - * ioremap performs a platform specific sequence of operations to - * make bus memory CPU accessible via the readb/readw/readl/writeb/ - * writew/writel functions and the other mmio helpers. The returned - * address is not guaranteed to be usable directly as a virtual - * address. - */ - -static inline void __iomem * ioremap(unsigned long offset, unsigned long size) -{ - return __ioremap(offset, size, 0); -} - -extern void __iomem * ioremap_nocache(unsigned long offset, unsigned long size); -extern void iounmap(volatile void __iomem *addr); - -/* - * bt_ioremap() and bt_iounmap() are for temporary early boot-time - * mappings, before the real ioremap() is functional. - * A boot-time mapping is currently limited to at most 16 pages. - */ -extern void *bt_ioremap(unsigned long offset, unsigned long size); -extern void bt_iounmap(void *addr, unsigned long size); - -/* - * ISA I/O bus memory addresses are 1:1 with the physical address. - */ -#define isa_virt_to_bus(_x) isa_virt_to_bus_is_UNSUPPORTED->x -#define isa_page_to_bus(_x) isa_page_to_bus_is_UNSUPPORTED->x -#ifdef CONFIG_XEN_PHYSDEV_ACCESS -#define isa_bus_to_virt(_x) (void *)(__fix_to_virt(FIX_ISAMAP_BEGIN) + (_x)) -#else -#define isa_bus_to_virt(_x) isa_bus_to_virt_needs_PRIVILEGED_BUILD -#endif - -/* - * However PCI ones are not necessarily 1:1 and therefore these interfaces - * are forbidden in portable PCI drivers. - * - * Allow them on x86 for legacy drivers, though. - */ -#define virt_to_bus(_x) phys_to_machine(__pa(_x)) -#define bus_to_virt(_x) __va(machine_to_phys(_x)) - -/* - * readX/writeX() are used to access memory mapped devices. On some - * architectures the memory mapped IO stuff needs to be accessed - * differently. On the x86 architecture, we just read/write the - * memory location directly. - */ - -static inline unsigned char readb(const volatile void __iomem *addr) -{ - return *(volatile unsigned char __force *) addr; -} -static inline unsigned short readw(const volatile void __iomem *addr) -{ - return *(volatile unsigned short __force *) addr; -} -static inline unsigned int readl(const volatile void __iomem *addr) -{ - return *(volatile unsigned int __force *) addr; -} -#define readb_relaxed(addr) readb(addr) -#define readw_relaxed(addr) readw(addr) -#define readl_relaxed(addr) readl(addr) -#define __raw_readb readb -#define __raw_readw readw -#define __raw_readl readl - -static inline void writeb(unsigned char b, volatile void __iomem *addr) -{ - *(volatile unsigned char __force *) addr = b; -} -static inline void writew(unsigned short b, volatile void __iomem *addr) -{ - *(volatile unsigned short __force *) addr = b; -} -static inline void writel(unsigned int b, volatile void __iomem *addr) -{ - *(volatile unsigned int __force *) addr = b; -} -#define __raw_writeb writeb -#define __raw_writew writew -#define __raw_writel writel - -#define mmiowb() - -static inline void memset_io(volatile void __iomem *addr, unsigned char val, int count) -{ - memset((void __force *) addr, val, count); -} -static inline void memcpy_fromio(void *dst, const volatile void __iomem *src, int count) -{ - __memcpy(dst, (void __force *) src, count); -} -static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int count) -{ - __memcpy((void __force *) dst, src, count); -} - -/* - * ISA space is 'always mapped' on a typical x86 system, no need to - * explicitly ioremap() it. The fact that the ISA IO space is mapped - * to PAGE_OFFSET is pure coincidence - it does not mean ISA values - * are physical addresses. The following constant pointer can be - * used as the IO-area pointer (it can be iounmapped as well, so the - * analogy with PCI is quite large): - */ -#define __ISA_IO_base ((char __iomem *)(fix_to_virt(FIX_ISAMAP_BEGIN))) - -#define isa_readb(a) readb(__ISA_IO_base + (a)) -#define isa_readw(a) readw(__ISA_IO_base + (a)) -#define isa_readl(a) readl(__ISA_IO_base + (a)) -#define isa_writeb(b,a) writeb(b,__ISA_IO_base + (a)) -#define isa_writew(w,a) writew(w,__ISA_IO_base + (a)) -#define isa_writel(l,a) writel(l,__ISA_IO_base + (a)) -#define isa_memset_io(a,b,c) memset_io(__ISA_IO_base + (a),(b),(c)) -#define isa_memcpy_fromio(a,b,c) memcpy_fromio((a),__ISA_IO_base + (b),(c)) -#define isa_memcpy_toio(a,b,c) memcpy_toio(__ISA_IO_base + (a),(b),(c)) - - -/* - * Again, i386 does not require mem IO specific function. - */ - -#define eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void __force *)(b),(c),(d)) -#define isa_eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void __force *)(__ISA_IO_base + (b)),(c),(d)) - -/** - * check_signature - find BIOS signatures - * @io_addr: mmio address to check - * @signature: signature block - * @length: length of signature - * - * Perform a signature comparison with the mmio address io_addr. This - * address should have been obtained by ioremap. - * Returns 1 on a match. - */ - -static inline int check_signature(volatile void __iomem * io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - -/* - * Cache management - * - * This needed for two cases - * 1. Out of order aware processors - * 2. Accidentally out of order processors (PPro errata #51) - */ - -#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE) - -static inline void flush_write_buffers(void) -{ - __asm__ __volatile__ ("lock; addl $0,0(%%esp)": : :"memory"); -} - -#define dma_cache_inv(_start,_size) flush_write_buffers() -#define dma_cache_wback(_start,_size) flush_write_buffers() -#define dma_cache_wback_inv(_start,_size) flush_write_buffers() - -#else - -/* Nothing to do */ - -#define dma_cache_inv(_start,_size) do { } while (0) -#define dma_cache_wback(_start,_size) do { } while (0) -#define dma_cache_wback_inv(_start,_size) do { } while (0) -#define flush_write_buffers() - -#endif - -#endif /* __KERNEL__ */ - -#ifdef SLOW_IO_BY_JUMPING -#define __SLOW_DOWN_IO "jmp 1f; 1: jmp 1f; 1:" -#else -#define __SLOW_DOWN_IO "outb %%al,$0x80;" -#endif - -static inline void slow_down_io(void) { - __asm__ __volatile__( - __SLOW_DOWN_IO -#ifdef REALLY_SLOW_IO - __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO -#endif - : : ); -} - -#ifdef CONFIG_X86_NUMAQ -extern void *xquad_portio; /* Where the IO area was mapped */ -#define XQUAD_PORT_ADDR(port, quad) (xquad_portio + (XQUAD_PORTIO_QUAD*quad) + port) -#define __BUILDIO(bwl,bw,type) \ -static inline void out##bwl##_quad(unsigned type value, int port, int quad) { \ - if (xquad_portio) \ - write##bwl(value, XQUAD_PORT_ADDR(port, quad)); \ - else \ - out##bwl##_local(value, port); \ -} \ -static inline void out##bwl(unsigned type value, int port) { \ - out##bwl##_quad(value, port, 0); \ -} \ -static inline unsigned type in##bwl##_quad(int port, int quad) { \ - if (xquad_portio) \ - return read##bwl(XQUAD_PORT_ADDR(port, quad)); \ - else \ - return in##bwl##_local(port); \ -} \ -static inline unsigned type in##bwl(int port) { \ - return in##bwl##_quad(port, 0); \ -} -#else -#define __BUILDIO(bwl,bw,type) \ -static inline void out##bwl(unsigned type value, int port) { \ - out##bwl##_local(value, port); \ -} \ -static inline unsigned type in##bwl(int port) { \ - return in##bwl##_local(port); \ -} -#endif - - -#define BUILDIO(bwl,bw,type) \ -static inline void out##bwl##_local(unsigned type value, int port) { \ - __asm__ __volatile__("out" #bwl " %" #bw "0, %w1" : : "a"(value), "Nd"(port)); \ -} \ -static inline unsigned type in##bwl##_local(int port) { \ - unsigned type value; \ - __asm__ __volatile__("in" #bwl " %w1, %" #bw "0" : "=a"(value) : "Nd"(port)); \ - return value; \ -} \ -static inline void out##bwl##_local_p(unsigned type value, int port) { \ - out##bwl##_local(value, port); \ - slow_down_io(); \ -} \ -static inline unsigned type in##bwl##_local_p(int port) { \ - unsigned type value = in##bwl##_local(port); \ - slow_down_io(); \ - return value; \ -} \ -__BUILDIO(bwl,bw,type) \ -static inline void out##bwl##_p(unsigned type value, int port) { \ - out##bwl(value, port); \ - slow_down_io(); \ -} \ -static inline unsigned type in##bwl##_p(int port) { \ - unsigned type value = in##bwl(port); \ - slow_down_io(); \ - return value; \ -} \ -static inline void outs##bwl(int port, const void *addr, unsigned long count) { \ - __asm__ __volatile__("rep; outs" #bwl : "+S"(addr), "+c"(count) : "d"(port)); \ -} \ -static inline void ins##bwl(int port, void *addr, unsigned long count) { \ - __asm__ __volatile__("rep; ins" #bwl : "+D"(addr), "+c"(count) : "d"(port)); \ -} - -BUILDIO(b,b,char) -BUILDIO(w,w,short) -BUILDIO(l,,int) - -/* We will be supplying our own /dev/mem implementation */ -#define ARCH_HAS_DEV_MEM - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/kmap_types.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/kmap_types.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,32 +0,0 @@ -#ifndef _ASM_KMAP_TYPES_H -#define _ASM_KMAP_TYPES_H - -#include <linux/config.h> - -#ifdef CONFIG_DEBUG_HIGHMEM -# define D(n) __KM_FENCE_##n , -#else -# define D(n) -#endif - -enum km_type { -D(0) KM_BOUNCE_READ, -D(1) KM_SKB_SUNRPC_DATA, -D(2) KM_SKB_DATA_SOFTIRQ, -D(3) KM_USER0, -D(4) KM_USER1, -D(5) KM_BIO_SRC_IRQ, -D(6) KM_BIO_DST_IRQ, -D(7) KM_PTE0, -D(8) KM_PTE1, -D(9) KM_IRQ0, -D(10) KM_IRQ1, -D(11) KM_SOFTIRQ0, -D(12) KM_SOFTIRQ1, -D(13) KM_SWIOTLB, -D(14) KM_TYPE_NR -}; - -#undef D - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/mach-xen/irq_vectors.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/mach-xen/irq_vectors.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,125 +0,0 @@ -/* - * This file should contain #defines for all of the interrupt vector - * numbers used by this architecture. - * - * In addition, there are some standard defines: - * - * FIRST_EXTERNAL_VECTOR: - * The first free place for external interrupts - * - * SYSCALL_VECTOR: - * The IRQ vector a syscall makes the user to kernel transition - * under. - * - * TIMER_IRQ: - * The IRQ number the timer interrupt comes in at. - * - * NR_IRQS: - * The total number of interrupt vectors (including all the - * architecture specific interrupts) needed. - * - */ -#ifndef _ASM_IRQ_VECTORS_H -#define _ASM_IRQ_VECTORS_H - -/* - * IDT vectors usable for external interrupt sources start - * at 0x20: - */ -#define FIRST_EXTERNAL_VECTOR 0x20 - -#define SYSCALL_VECTOR 0x80 - -/* - * Vectors 0x20-0x2f are used for ISA interrupts. - */ - -#if 0 -/* - * Special IRQ vectors used by the SMP architecture, 0xf0-0xff - * - * some of the following vectors are 'rare', they are merged - * into a single vector (CALL_FUNCTION_VECTOR) to save vector space. - * TLB, reschedule and local APIC vectors are performance-critical. - * - * Vectors 0xf0-0xfa are free (reserved for future Linux use). - */ -#define SPURIOUS_APIC_VECTOR 0xff -#define ERROR_APIC_VECTOR 0xfe -#define INVALIDATE_TLB_VECTOR 0xfd -#define RESCHEDULE_VECTOR 0xfc -#define CALL_FUNCTION_VECTOR 0xfb - -#define THERMAL_APIC_VECTOR 0xf0 -/* - * Local APIC timer IRQ vector is on a different priority level, - * to work around the 'lost local interrupt if more than 2 IRQ - * sources per level' errata. - */ -#define LOCAL_TIMER_VECTOR 0xef -#endif - -#define SPURIOUS_APIC_VECTOR 0xff -#define ERROR_APIC_VECTOR 0xfe - -/* - * First APIC vector available to drivers: (vectors 0x30-0xee) - * we start at 0x31 to spread out vectors evenly between priority - * levels. (0x80 is the syscall vector) - */ -#define FIRST_DEVICE_VECTOR 0x31 -#define FIRST_SYSTEM_VECTOR 0xef - -/* - * 16 8259A IRQ's, 208 potential APIC interrupt sources. - * Right now the APIC is mostly only used for SMP. - * 256 vectors is an architectural limit. (we can have - * more than 256 devices theoretically, but they will - * have to use shared interrupts) - * Since vectors 0x00-0x1f are used/reserved for the CPU, - * the usable vector space is 0x20-0xff (224 vectors) - */ - -#define RESCHEDULE_VECTOR 0 -#define CALL_FUNCTION_VECTOR 1 -#define NR_IPIS 2 - -/* - * The maximum number of vectors supported by i386 processors - * is limited to 256. For processors other than i386, NR_VECTORS - * should be changed accordingly. - */ -#define NR_VECTORS 256 - -#define FPU_IRQ 13 - -#define FIRST_VM86_IRQ 3 -#define LAST_VM86_IRQ 15 -#define invalid_vm86_irq(irq) ((irq) < 3 || (irq) > 15) - -/* - * The flat IRQ space is divided into two regions: - * 1. A one-to-one mapping of real physical IRQs. This space is only used - * if we have physical device-access privilege. This region is at the - * start of the IRQ space so that existing device drivers do not need - * to be modified to translate physical IRQ numbers into our IRQ space. - * 3. A dynamic mapping of inter-domain and Xen-sourced virtual IRQs. These - * are bound using the provided bind/unbind functions. - */ - -#define PIRQ_BASE 0 -#define NR_PIRQS 256 - -#define DYNIRQ_BASE (PIRQ_BASE + NR_PIRQS) -#define NR_DYNIRQS 256 - -#define NR_IRQS (NR_PIRQS + NR_DYNIRQS) -#define NR_IRQ_VECTORS NR_IRQS - -#define pirq_to_irq(_x) ((_x) + PIRQ_BASE) -#define irq_to_pirq(_x) ((_x) - PIRQ_BASE) - -#define dynirq_to_irq(_x) ((_x) + DYNIRQ_BASE) -#define irq_to_dynirq(_x) ((_x) - DYNIRQ_BASE) - -#endif /* _ASM_IRQ_VECTORS_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/mach-xen/mach_traps.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/mach-xen/mach_traps.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,33 +0,0 @@ -/* - * include/asm-xen/asm-i386/mach-xen/mach_traps.h - * - * Machine specific NMI handling for Xen - */ -#ifndef _MACH_TRAPS_H -#define _MACH_TRAPS_H - -#include <linux/bitops.h> -#include <asm-xen/xen-public/nmi.h> - -static inline void clear_mem_error(unsigned char reason) {} -static inline void clear_io_check_error(unsigned char reason) {} - -static inline unsigned char get_nmi_reason(void) -{ - shared_info_t *s = HYPERVISOR_shared_info; - unsigned char reason = 0; - - /* construct a value which looks like it came from - * port 0x61. - */ - if (test_bit(_XEN_NMIREASON_io_error, &s->arch.nmi_reason)) - reason |= 0x40; - if (test_bit(_XEN_NMIREASON_parity_error, &s->arch.nmi_reason)) - reason |= 0x80; - - return reason; -} - -static inline void reassert_nmi(void) {} - -#endif /* !_MACH_TRAPS_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/mach-xen/setup_arch_post.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/mach-xen/setup_arch_post.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,43 +0,0 @@ -/** - * machine_specific_memory_setup - Hook for machine specific memory setup. - * - * Description: - * This is included late in kernel/setup.c so that it can make - * use of all of the static functions. - **/ - -static char * __init machine_specific_memory_setup(void) -{ - unsigned long max_pfn = xen_start_info->nr_pages; - - e820.nr_map = 0; - add_memory_region(0, PFN_PHYS(max_pfn), E820_RAM); - - return "Xen"; -} - -void __init machine_specific_modify_cpu_capabilities(struct cpuinfo_x86 *c) -{ - clear_bit(X86_FEATURE_VME, c->x86_capability); - clear_bit(X86_FEATURE_DE, c->x86_capability); - clear_bit(X86_FEATURE_PSE, c->x86_capability); - clear_bit(X86_FEATURE_PGE, c->x86_capability); - clear_bit(X86_FEATURE_SEP, c->x86_capability); - if (!(xen_start_info->flags & SIF_PRIVILEGED)) - clear_bit(X86_FEATURE_MTRR, c->x86_capability); -} - -extern void hypervisor_callback(void); -extern void failsafe_callback(void); -extern void nmi(void); - -static void __init machine_specific_arch_setup(void) -{ - HYPERVISOR_set_callbacks( - __KERNEL_CS, (unsigned long)hypervisor_callback, - __KERNEL_CS, (unsigned long)failsafe_callback); - - HYPERVISOR_nmi_op(XENNMI_register_callback, (unsigned long)&nmi); - - machine_specific_modify_cpu_capabilities(&boot_cpu_data); -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/mach-xen/setup_arch_pre.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/mach-xen/setup_arch_pre.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,5 +0,0 @@ -/* Hook to call BIOS initialisation function */ - -#define ARCH_SETUP machine_specific_arch_setup(); - -static void __init machine_specific_arch_setup(void); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/mmu.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/mmu.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,21 +0,0 @@ -#ifndef __i386_MMU_H -#define __i386_MMU_H - -#include <asm/semaphore.h> -/* - * The i386 doesn't have a mmu context, but - * we put the segment information here. - * - * cpu_vm_mask is used to optimize ldt flushing. - */ -typedef struct { - int size; - struct semaphore sem; - void *ldt; -} mm_context_t; - -/* mm/memory.c:exit_mmap hook */ -extern void _arch_exit_mmap(struct mm_struct *mm); -#define arch_exit_mmap(_mm) _arch_exit_mmap(_mm) - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/mmu_context.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/mmu_context.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,108 +0,0 @@ -#ifndef __I386_SCHED_H -#define __I386_SCHED_H - -#include <linux/config.h> -#include <asm/desc.h> -#include <asm/atomic.h> -#include <asm/pgalloc.h> -#include <asm/tlbflush.h> - -/* - * Used for LDT copy/destruction. - */ -int init_new_context(struct task_struct *tsk, struct mm_struct *mm); -void destroy_context(struct mm_struct *mm); - - -static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) -{ -#if 0 /* XEN: no lazy tlb */ - unsigned cpu = smp_processor_id(); - if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK) - per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_LAZY; -#endif -} - -#define prepare_arch_switch(rq,next) __prepare_arch_switch() -#define finish_arch_switch(rq, next) spin_unlock_irq(&(rq)->lock) -#define task_running(rq, p) ((rq)->curr == (p)) - -static inline void __prepare_arch_switch(void) -{ - /* - * Save away %fs and %gs. No need to save %es and %ds, as those - * are always kernel segments while inside the kernel. Must - * happen before reload of cr3/ldt (i.e., not in __switch_to). - */ - asm volatile ( "mov %%fs,%0 ; mov %%gs,%1" - : "=m" (current->thread.fs), - "=m" (current->thread.gs)); - asm volatile ( "movl %0,%%fs ; movl %0,%%gs" - : : "r" (0) ); -} - -extern void mm_pin(struct mm_struct *mm); -extern void mm_unpin(struct mm_struct *mm); -void mm_pin_all(void); - -static inline void switch_mm(struct mm_struct *prev, - struct mm_struct *next, - struct task_struct *tsk) -{ - int cpu = smp_processor_id(); - struct mmuext_op _op[2], *op = _op; - - if (likely(prev != next)) { - if (!test_bit(PG_pinned, &virt_to_page(next->pgd)->flags)) - mm_pin(next); - - /* stop flush ipis for the previous mm */ - cpu_clear(cpu, prev->cpu_vm_mask); -#if 0 /* XEN: no lazy tlb */ - per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK; - per_cpu(cpu_tlbstate, cpu).active_mm = next; -#endif - cpu_set(cpu, next->cpu_vm_mask); - - /* Re-load page tables: load_cr3(next->pgd) */ - per_cpu(cur_pgd, cpu) = next->pgd; - op->cmd = MMUEXT_NEW_BASEPTR; - op->arg1.mfn = pfn_to_mfn(__pa(next->pgd) >> PAGE_SHIFT); - op++; - - /* - * load the LDT, if the LDT is different: - */ - if (unlikely(prev->context.ldt != next->context.ldt)) { - /* load_LDT_nolock(&next->context, cpu) */ - op->cmd = MMUEXT_SET_LDT; - op->arg1.linear_addr = (unsigned long)next->context.ldt; - op->arg2.nr_ents = next->context.size; - op++; - } - - BUG_ON(HYPERVISOR_mmuext_op(_op, op-_op, NULL, DOMID_SELF)); - } -#if 0 /* XEN: no lazy tlb */ - else { - per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK; - BUG_ON(per_cpu(cpu_tlbstate, cpu).active_mm != next); - - if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) { - /* We were in lazy tlb mode and leave_mm disabled - * tlb flush IPI delivery. We must reload %cr3. - */ - load_cr3(next->pgd); - load_LDT_nolock(&next->context, cpu); - } - } -#endif -} - -#define deactivate_mm(tsk, mm) \ - asm("movl %0,%%fs ; movl %0,%%gs": :"r" (0)) - -#define activate_mm(prev, next) \ - switch_mm((prev),(next),NULL) - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/page.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/page.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,276 +0,0 @@ -#ifndef _I386_PAGE_H -#define _I386_PAGE_H - -/* PAGE_SHIFT determines the page size */ -#define PAGE_SHIFT 12 -#define PAGE_SIZE (1UL << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE-1)) - -#define LARGE_PAGE_MASK (~(LARGE_PAGE_SIZE-1)) -#define LARGE_PAGE_SIZE (1UL << PMD_SHIFT) - -#ifdef __KERNEL__ -#ifndef __ASSEMBLY__ - -#include <linux/config.h> -#include <linux/string.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <asm/bug.h> -#include <asm-xen/xen-public/xen.h> -#include <asm-xen/foreign_page.h> - -#define arch_free_page(_page,_order) \ -({ int foreign = PageForeign(_page); \ - if (foreign) \ - (PageForeignDestructor(_page))(_page); \ - foreign; \ -}) -#define HAVE_ARCH_FREE_PAGE - -#ifdef CONFIG_XEN_SCRUB_PAGES -#define scrub_pages(_p,_n) memset((void *)(_p), 0, (_n) << PAGE_SHIFT) -#else -#define scrub_pages(_p,_n) ((void)0) -#endif - -#ifdef CONFIG_X86_USE_3DNOW - -#include <asm/mmx.h> - -#define clear_page(page) mmx_clear_page((void *)(page)) -#define copy_page(to,from) mmx_copy_page(to,from) - -#else - -#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr) -#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE - -/* - * On older X86 processors it's not a win to use MMX here it seems. - * Maybe the K6-III ? - */ - -#define clear_page(page) memset((void *)(page), 0, PAGE_SIZE) -#define copy_page(to,from) memcpy((void *)(to), (void *)(from), PAGE_SIZE) - -#endif - -#define clear_user_page(page, vaddr, pg) clear_page(page) -#define copy_user_page(to, from, vaddr, pg) copy_page(to, from) - -/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/ -#define INVALID_P2M_ENTRY (~0UL) -#define FOREIGN_FRAME(m) ((m) | (1UL<<31)) -extern unsigned long *phys_to_machine_mapping; -#define pfn_to_mfn(pfn) \ -(phys_to_machine_mapping[(unsigned int)(pfn)] & ~(1UL<<31)) -#define phys_to_machine_mapping_valid(pfn) \ - (phys_to_machine_mapping[pfn] != INVALID_P2M_ENTRY) -static inline unsigned long mfn_to_pfn(unsigned long mfn) -{ - unsigned long pfn; - - /* - * The array access can fail (e.g., device space beyond end of RAM). - * In such cases it doesn't matter what we return (we return garbage), - * but we must handle the fault without crashing! - */ - asm ( - "1: movl %1,%0\n" - "2:\n" - ".section __ex_table,\"a\"\n" - " .align 4\n" - " .long 1b,2b\n" - ".previous" - : "=r" (pfn) : "m" (machine_to_phys_mapping[mfn]) ); - - return pfn; -} - -static inline void set_phys_to_machine(unsigned long pfn, unsigned long mfn) -{ - phys_to_machine_mapping[pfn] = mfn; -} - -/* Definitions for machine and pseudophysical addresses. */ -#ifdef CONFIG_X86_PAE -typedef unsigned long long paddr_t; -typedef unsigned long long maddr_t; -#else -typedef unsigned long paddr_t; -typedef unsigned long maddr_t; -#endif - -static inline maddr_t phys_to_machine(paddr_t phys) -{ - maddr_t machine = pfn_to_mfn(phys >> PAGE_SHIFT); - machine = (machine << PAGE_SHIFT) | (phys & ~PAGE_MASK); - return machine; -} -static inline paddr_t machine_to_phys(maddr_t machine) -{ - paddr_t phys = mfn_to_pfn(machine >> PAGE_SHIFT); - phys = (phys << PAGE_SHIFT) | (machine & ~PAGE_MASK); - return phys; -} - -/* - * These are used to make use of C type-checking.. - */ -extern int nx_enabled; -#ifdef CONFIG_X86_PAE -extern unsigned long long __supported_pte_mask; -typedef struct { unsigned long pte_low, pte_high; } pte_t; -typedef struct { unsigned long long pmd; } pmd_t; -typedef struct { unsigned long long pgd; } pgd_t; -typedef struct { unsigned long long pgprot; } pgprot_t; -#define __pte(x) ({ unsigned long long _x = (x); \ - if (_x & 1) _x = phys_to_machine(_x); \ - ((pte_t) {(unsigned long)(_x), (unsigned long)(_x>>32)}); }) -#define __pgd(x) ({ unsigned long long _x = (x); \ - (((_x)&1) ? ((pgd_t) {phys_to_machine(_x)}) : ((pgd_t) {(_x)})); }) -#define __pmd(x) ({ unsigned long long _x = (x); \ - (((_x)&1) ? ((pmd_t) {phys_to_machine(_x)}) : ((pmd_t) {(_x)})); }) -static inline unsigned long long pte_val(pte_t x) -{ - unsigned long long ret; - - if (x.pte_low) { - ret = x.pte_low | (unsigned long long)x.pte_high << 32; - ret = machine_to_phys(ret) | 1; - } else { - ret = 0; - } - return ret; -} -static inline unsigned long long pmd_val(pmd_t x) -{ - unsigned long long ret = x.pmd; - if (ret) ret = machine_to_phys(ret) | 1; - return ret; -} -static inline unsigned long long pgd_val(pgd_t x) -{ - unsigned long long ret = x.pgd; - if (ret) ret = machine_to_phys(ret) | 1; - return ret; -} -static inline unsigned long long pte_val_ma(pte_t x) -{ - return (unsigned long long)x.pte_high << 32 | x.pte_low; -} -#define HPAGE_SHIFT 21 -#else -typedef struct { unsigned long pte_low; } pte_t; -typedef struct { unsigned long pgd; } pgd_t; -typedef struct { unsigned long pgprot; } pgprot_t; -#define boot_pte_t pte_t /* or would you rather have a typedef */ -#define pte_val(x) (((x).pte_low & 1) ? machine_to_phys((x).pte_low) : \ - (x).pte_low) -#define pte_val_ma(x) ((x).pte_low) -#define __pte(x) ({ unsigned long _x = (x); \ - (((_x)&1) ? ((pte_t) {phys_to_machine(_x)}) : ((pte_t) {(_x)})); }) -#define __pgd(x) ({ unsigned long _x = (x); \ - (((_x)&1) ? ((pgd_t) {phys_to_machine(_x)}) : ((pgd_t) {(_x)})); }) -static inline unsigned long pgd_val(pgd_t x) -{ - unsigned long ret = x.pgd; - if (ret) ret = machine_to_phys(ret) | 1; - return ret; -} -#define HPAGE_SHIFT 22 -#endif -#define PTE_MASK PAGE_MASK - -#ifdef CONFIG_HUGETLB_PAGE -#define HPAGE_SIZE ((1UL) << HPAGE_SHIFT) -#define HPAGE_MASK (~(HPAGE_SIZE - 1)) -#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) -#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA -#endif - -#define pgprot_val(x) ((x).pgprot) - -#define __pte_ma(x) ((pte_t) { (x) } ) -#define __pgprot(x) ((pgprot_t) { (x) } ) - -#endif /* !__ASSEMBLY__ */ - -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) - -/* - * This handles the memory map.. We could make this a config - * option, but too many people screw it up, and too few need - * it. - * - * A __PAGE_OFFSET of 0xC0000000 means that the kernel has - * a virtual address space of one gigabyte, which limits the - * amount of physical memory you can use to about 950MB. - * - * If you want more physical memory than this then see the CONFIG_HIGHMEM4G - * and CONFIG_HIGHMEM64G options in the kernel configuration. - */ - -#ifndef __ASSEMBLY__ - -/* - * This much address space is reserved for vmalloc() and iomap() - * as well as fixmap mappings. - */ -extern unsigned int __VMALLOC_RESERVE; - -/* Pure 2^n version of get_order */ -static __inline__ int get_order(unsigned long size) -{ - int order; - - size = (size-1) >> (PAGE_SHIFT-1); - order = -1; - do { - size >>= 1; - order++; - } while (size); - return order; -} - -extern int sysctl_legacy_va_layout; - -#endif /* __ASSEMBLY__ */ - -#ifdef __ASSEMBLY__ -#define __PAGE_OFFSET (0xC0000000) -#else -#define __PAGE_OFFSET (0xC0000000UL) -#endif - - -#define PAGE_OFFSET ((unsigned long)__PAGE_OFFSET) -#define VMALLOC_RESERVE ((unsigned long)__VMALLOC_RESERVE) -#define MAXMEM (HYPERVISOR_VIRT_START-__PAGE_OFFSET-__VMALLOC_RESERVE) -#define __pa(x) ((unsigned long)(x)-PAGE_OFFSET) -#define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET)) -#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) -#ifndef CONFIG_DISCONTIGMEM -#define pfn_to_page(pfn) (mem_map + (pfn)) -#define page_to_pfn(page) ((unsigned long)((page) - mem_map)) -#define pfn_valid(pfn) ((pfn) < max_mapnr) -#endif /* !CONFIG_DISCONTIGMEM */ -#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) - -#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) - -#define VM_DATA_DEFAULT_FLAGS \ - (VM_READ | VM_WRITE | \ - ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \ - VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) - -/* VIRT <-> MACHINE conversion */ -#define virt_to_machine(v) (phys_to_machine(__pa(v))) -#define virt_to_mfn(v) (pfn_to_mfn(__pa(v) >> PAGE_SHIFT)) -#define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) - -#endif /* __KERNEL__ */ - -#endif /* _I386_PAGE_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/param.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/param.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,23 +0,0 @@ -#ifndef _ASMi386_PARAM_H -#define _ASMi386_PARAM_H - -#ifdef __KERNEL__ -# define HZ 100 /* Internal kernel timer frequency */ -# define USER_HZ 100 /* .. some user interfaces are in "ticks" */ -# define CLOCKS_PER_SEC (USER_HZ) /* like times() */ -#endif - -#ifndef HZ -#define HZ 100 -#endif - -#define EXEC_PAGESIZE 4096 - -#ifndef NOGROUP -#define NOGROUP (-1) -#endif - -#define MAXHOSTNAMELEN 64 /* max length of hostname */ -#define COMMAND_LINE_SIZE 256 - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/pci.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/pci.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,140 +0,0 @@ -#ifndef __i386_PCI_H -#define __i386_PCI_H - -#include <linux/config.h> - -#ifdef __KERNEL__ -#include <linux/mm.h> /* for struct page */ - -/* Can be used to override the logic in pci_scan_bus for skipping - already-configured bus numbers - to be used for buggy BIOSes - or architectures with incomplete PCI setup by the loader */ - -#ifdef CONFIG_PCI -extern unsigned int pcibios_assign_all_busses(void); -#else -#define pcibios_assign_all_busses() 0 -#endif -#define pcibios_scan_all_fns(a, b) 0 - -extern unsigned long pci_mem_start; -#define PCIBIOS_MIN_IO 0x1000 -#define PCIBIOS_MIN_MEM (pci_mem_start) - -#define PCIBIOS_MIN_CARDBUS_IO 0x4000 - -void pcibios_config_init(void); -struct pci_bus * pcibios_scan_root(int bus); - -void pcibios_set_master(struct pci_dev *dev); -void pcibios_penalize_isa_irq(int irq); -struct irq_routing_table *pcibios_get_irq_routing_table(void); -int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq); - -/* Dynamic DMA mapping stuff. - * i386 has everything mapped statically. - */ - -#include <linux/types.h> -#include <linux/slab.h> -#include <asm/scatterlist.h> -#include <linux/string.h> -#include <asm/io.h> - -struct pci_dev; - -#ifdef CONFIG_SWIOTLB - - -/* On Xen we use SWIOTLB instead of blk-specific bounce buffers. */ -#define PCI_DMA_BUS_IS_PHYS (0) - -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ - dma_addr_t ADDR_NAME; -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \ - __u32 LEN_NAME; -#define pci_unmap_addr(PTR, ADDR_NAME) \ - ((PTR)->ADDR_NAME) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ - (((PTR)->ADDR_NAME) = (VAL)) -#define pci_unmap_len(PTR, LEN_NAME) \ - ((PTR)->LEN_NAME) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ - (((PTR)->LEN_NAME) = (VAL)) - -#else - -/* The PCI address space does equal the physical memory - * address space. The networking and block device layers use - * this boolean for bounce buffer decisions. - */ -#define PCI_DMA_BUS_IS_PHYS (1) - -/* pci_unmap_{page,single} is a nop so... */ -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) -#define pci_unmap_addr(PTR, ADDR_NAME) (0) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) do { } while (0) -#define pci_unmap_len(PTR, LEN_NAME) (0) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) do { } while (0) - -#endif - -/* This is always fine. */ -#define pci_dac_dma_supported(pci_dev, mask) (1) - -static inline dma64_addr_t -pci_dac_page_to_dma(struct pci_dev *pdev, struct page *page, unsigned long offset, int direction) -{ - return ((dma64_addr_t) page_to_phys(page) + - (dma64_addr_t) offset); -} - -static inline struct page * -pci_dac_dma_to_page(struct pci_dev *pdev, dma64_addr_t dma_addr) -{ - return pfn_to_page(dma_addr >> PAGE_SHIFT); -} - -static inline unsigned long -pci_dac_dma_to_offset(struct pci_dev *pdev, dma64_addr_t dma_addr) -{ - return (dma_addr & ~PAGE_MASK); -} - -static inline void -pci_dac_dma_sync_single_for_cpu(struct pci_dev *pdev, dma64_addr_t dma_addr, size_t len, int direction) -{ -} - -static inline void -pci_dac_dma_sync_single_for_device(struct pci_dev *pdev, dma64_addr_t dma_addr, size_t len, int direction) -{ - flush_write_buffers(); -} - -#define HAVE_PCI_MMAP -extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, - enum pci_mmap_state mmap_state, int write_combine); - - -static inline void pcibios_add_platform_entries(struct pci_dev *dev) -{ -} - -#endif /* __KERNEL__ */ - -/* implement the pci_ DMA API in terms of the generic device dma_ one */ -#include <asm-generic/pci-dma-compat.h> - -/* generic pci stuff */ -#include <asm-generic/pci.h> - -/* On Xen we have to scan all functions since Xen hides bridges from - * us. If a bridge is at fn=0 and that slot has a multifunction - * device, we won't find the additional devices without scanning all - * functions. */ -#undef pcibios_scan_all_fns -#define pcibios_scan_all_fns(a, b) 1 - -#endif /* __i386_PCI_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/pgalloc.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/pgalloc.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,64 +0,0 @@ -#ifndef _I386_PGALLOC_H -#define _I386_PGALLOC_H - -#include <linux/config.h> -#include <asm/fixmap.h> -#include <linux/threads.h> -#include <linux/mm.h> /* for struct page */ -#include <asm/io.h> /* for phys_to_virt and page_to_pseudophys */ - -/* Is this pagetable pinned? */ -#define PG_pinned PG_arch_1 - -#define pmd_populate_kernel(mm, pmd, pte) \ - set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(pte))) - -#define pmd_populate(mm, pmd, pte) \ -do { \ - if (test_bit(PG_pinned, &virt_to_page((mm)->pgd)->flags)) { \ - if (!PageHighMem(pte)) \ - BUG_ON(HYPERVISOR_update_va_mapping( \ - (unsigned long)__va(page_to_pfn(pte)<<PAGE_SHIFT),\ - pfn_pte(page_to_pfn(pte), PAGE_KERNEL_RO), 0));\ - set_pmd(pmd, __pmd(_PAGE_TABLE + \ - ((unsigned long long)page_to_pfn(pte) << \ - (unsigned long long) PAGE_SHIFT))); \ - } else { \ - *(pmd) = __pmd(_PAGE_TABLE + \ - ((unsigned long long)page_to_pfn(pte) << \ - (unsigned long long) PAGE_SHIFT)); \ - } \ -} while (0) - -/* - * Allocate and free page tables. - */ -extern pgd_t *pgd_alloc(struct mm_struct *); -extern void pgd_free(pgd_t *pgd); - -extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long); -extern struct page *pte_alloc_one(struct mm_struct *, unsigned long); - -static inline void pte_free_kernel(pte_t *pte) -{ - free_page((unsigned long)pte); - make_page_writable(pte, XENFEAT_writable_page_tables); -} - -extern void pte_free(struct page *pte); - -#define __pte_free_tlb(tlb,pte) tlb_remove_page((tlb),(pte)) - -#ifdef CONFIG_X86_PAE -/* - * In the PAE case we free the pmds as part of the pgd. - */ -#define pmd_alloc_one(mm, addr) ({ BUG(); ((pmd_t *)2); }) -#define pmd_free(x) do { } while (0) -#define __pmd_free_tlb(tlb,x) do { } while (0) -#define pud_populate(mm, pmd, pte) BUG() -#endif - -#define check_pgt_cache() do { } while (0) - -#endif /* _I386_PGALLOC_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/pgtable-2level-defs.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/pgtable-2level-defs.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,21 +0,0 @@ -#ifndef _I386_PGTABLE_2LEVEL_DEFS_H -#define _I386_PGTABLE_2LEVEL_DEFS_H - -#define HAVE_SHARED_KERNEL_PMD 0 - -/* - * traditional i386 two-level paging structure: - */ - -#define PGDIR_SHIFT 22 -#define PTRS_PER_PGD 1024 -#define PTRS_PER_PGD_NO_HV (HYPERVISOR_VIRT_START >> PGDIR_SHIFT) - -/* - * the i386 is two-level, so we don't really have any - * PMD directory physically. - */ - -#define PTRS_PER_PTE 1024 - -#endif /* _I386_PGTABLE_2LEVEL_DEFS_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/pgtable-2level.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/pgtable-2level.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,119 +0,0 @@ -#ifndef _I386_PGTABLE_2LEVEL_H -#define _I386_PGTABLE_2LEVEL_H - -#include <asm-generic/pgtable-nopmd.h> - -#define pte_ERROR(e) \ - printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low) -#define pgd_ERROR(e) \ - printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e)) - -/* - * Certain architectures need to do special things when PTEs - * within a page table are directly modified. Thus, the following - * hook is made available. - */ -#define set_pte(pteptr, pteval) (*(pteptr) = pteval) - -#define set_pte_at(_mm,addr,ptep,pteval) do { \ - if (((_mm) != current->mm && (_mm) != &init_mm) || \ - HYPERVISOR_update_va_mapping((addr), (pteval), 0)) \ - set_pte((ptep), (pteval)); \ -} while (0) - -#define set_pte_at_sync(_mm,addr,ptep,pteval) do { \ - if (((_mm) != current->mm && (_mm) != &init_mm) || \ - HYPERVISOR_update_va_mapping((addr), (pteval), UVMF_INVLPG)) { \ - set_pte((ptep), (pteval)); \ - xen_invlpg((addr)); \ - } \ -} while (0) - -#define set_pte_atomic(pteptr, pteval) set_pte(pteptr,pteval) - -#ifndef CONFIG_XEN_SHADOW_MODE -#define set_pmd(pmdptr, pmdval) xen_l2_entry_update((pmdptr), (pmdval)) -#else -#define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval)) -#endif - -#define ptep_get_and_clear(mm,addr,xp) __pte_ma(xchg(&(xp)->pte_low, 0)) -#define pte_same(a, b) ((a).pte_low == (b).pte_low) -/* - * We detect special mappings in one of two ways: - * 1. If the MFN is an I/O page then Xen will set the m2p entry - * to be outside our maximum possible pseudophys range. - * 2. If the MFN belongs to a different domain then we will certainly - * not have MFN in our p2m table. Conversely, if the page is ours, - * then we'll have p2m(m2p(MFN))==MFN. - * If we detect a special mapping then it doesn't have a 'struct page'. - * We force !pfn_valid() by returning an out-of-range pointer. - * - * NB. These checks require that, for any MFN that is not in our reservation, - * there is no PFN such that p2m(PFN) == MFN. Otherwise we can get confused if - * we are foreign-mapping the MFN, and the other domain as m2p(MFN) == PFN. - * Yikes! Various places must poke in INVALID_P2M_ENTRY for safety. - * - * NB2. When deliberately mapping foreign pages into the p2m table, you *must* - * use FOREIGN_FRAME(). This will cause pte_pfn() to choke on it, as we - * require. In all the cases we care about, the FOREIGN_FRAME bit is - * masked (e.g., pfn_to_mfn()) so behaviour there is correct. - */ -#define pte_mfn(_pte) ((_pte).pte_low >> PAGE_SHIFT) -#define pte_pfn(_pte) \ -({ \ - unsigned long mfn = pte_mfn(_pte); \ - unsigned long pfn = mfn_to_pfn(mfn); \ - if ((pfn >= max_mapnr) || (phys_to_machine_mapping[pfn] != mfn))\ - pfn = max_mapnr; /* special: force !pfn_valid() */ \ - pfn; \ -}) - -#define pte_page(_pte) pfn_to_page(pte_pfn(_pte)) - -#define pte_none(x) (!(x).pte_low) -#define pfn_pte(pfn, prot) __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) -#define pfn_pte_ma(pfn, prot) __pte_ma(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) -#define pfn_pmd(pfn, prot) __pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) - -#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)) - -#define pmd_page_kernel(pmd) \ -((unsigned long) __va(pmd_val(pmd) & PAGE_MASK)) - -/* - * All present user pages are user-executable: - */ -static inline int pte_exec(pte_t pte) -{ - return pte_user(pte); -} - -/* - * All present pages are kernel-executable: - */ -static inline int pte_exec_kernel(pte_t pte) -{ - return 1; -} - -/* - * Bits 0, 6 and 7 are taken, split up the 29 bits of offset - * into this range: - */ -#define PTE_FILE_MAX_BITS 29 - -#define pte_to_pgoff(pte) \ - ((((pte).pte_low >> 1) & 0x1f ) + (((pte).pte_low >> 8) << 5 )) - -#define pgoff_to_pte(off) \ - ((pte_t) { (((off) & 0x1f) << 1) + (((off) >> 5) << 8) + _PAGE_FILE }) - -/* Encode and de-code a swap entry */ -#define __swp_type(x) (((x).val >> 1) & 0x1f) -#define __swp_offset(x) ((x).val >> 8) -#define __swp_entry(type, offset) ((swp_entry_t) { ((type) << 1) | ((offset) << 8) }) -#define __pte_to_swp_entry(pte) ((swp_entry_t) { (pte).pte_low }) -#define __swp_entry_to_pte(x) ((pte_t) { (x).val }) - -#endif /* _I386_PGTABLE_2LEVEL_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/pgtable-3level-defs.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/pgtable-3level-defs.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,25 +0,0 @@ -#ifndef _I386_PGTABLE_3LEVEL_DEFS_H -#define _I386_PGTABLE_3LEVEL_DEFS_H - -#define HAVE_SHARED_KERNEL_PMD 0 - -/* - * PGDIR_SHIFT determines what a top-level page table entry can map - */ -#define PGDIR_SHIFT 30 -#define PTRS_PER_PGD 4 -#define PTRS_PER_PGD_NO_HV 4 - -/* - * PMD_SHIFT determines the size of the area a middle-level - * page table can map - */ -#define PMD_SHIFT 21 -#define PTRS_PER_PMD 512 - -/* - * entries per page directory level - */ -#define PTRS_PER_PTE 512 - -#endif /* _I386_PGTABLE_3LEVEL_DEFS_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/pgtable-3level.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/pgtable-3level.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,200 +0,0 @@ -#ifndef _I386_PGTABLE_3LEVEL_H -#define _I386_PGTABLE_3LEVEL_H - -#include <asm-generic/pgtable-nopud.h> - -/* - * Intel Physical Address Extension (PAE) Mode - three-level page - * tables on PPro+ CPUs. - * - * Copyright (C) 1999 Ingo Molnar <mingo@xxxxxxxxxx> - */ - -#define pte_ERROR(e) \ - printk("%s:%d: bad pte %p(%08lx%08lx).\n", __FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low) -#define pmd_ERROR(e) \ - printk("%s:%d: bad pmd %p(%016Lx).\n", __FILE__, __LINE__, &(e), pmd_val(e)) -#define pgd_ERROR(e) \ - printk("%s:%d: bad pgd %p(%016Lx).\n", __FILE__, __LINE__, &(e), pgd_val(e)) - -#define pud_none(pud) 0 -#define pud_bad(pud) 0 -#define pud_present(pud) 1 - -/* - * Is the pte executable? - */ -static inline int pte_x(pte_t pte) -{ - return !(pte_val(pte) & _PAGE_NX); -} - -/* - * All present user-pages with !NX bit are user-executable: - */ -static inline int pte_exec(pte_t pte) -{ - return pte_user(pte) && pte_x(pte); -} -/* - * All present pages with !NX bit are kernel-executable: - */ -static inline int pte_exec_kernel(pte_t pte) -{ - return pte_x(pte); -} - -/* Rules for using set_pte: the pte being assigned *must* be - * either not present or in a state where the hardware will - * not attempt to update the pte. In places where this is - * not possible, use pte_get_and_clear to obtain the old pte - * value and then use set_pte to update it. -ben - */ -#define __HAVE_ARCH_SET_PTE_ATOMIC - -#if 1 -/* use writable pagetables */ -static inline void set_pte(pte_t *ptep, pte_t pte) -{ - ptep->pte_high = pte.pte_high; - smp_wmb(); - ptep->pte_low = pte.pte_low; -} -# define set_pte_atomic(pteptr,pteval) \ - set_64bit((unsigned long long *)(pteptr),pte_val_ma(pteval)) -#else -/* no writable pagetables */ -# define set_pte(pteptr,pteval) \ - xen_l1_entry_update((pteptr), (pteval)) -# define set_pte_atomic(pteptr,pteval) set_pte(pteptr,pteval) -#endif - -#define set_pte_at(_mm,addr,ptep,pteval) do { \ - if (((_mm) != current->mm && (_mm) != &init_mm) || \ - HYPERVISOR_update_va_mapping((addr), (pteval), 0)) \ - set_pte((ptep), (pteval)); \ -} while (0) - -#define set_pte_at_sync(_mm,addr,ptep,pteval) do { \ - if (((_mm) != current->mm && (_mm) != &init_mm) || \ - HYPERVISOR_update_va_mapping((addr), (pteval), UVMF_INVLPG)) { \ - set_pte((ptep), (pteval)); \ - xen_invlpg((addr)); \ - } \ -} while (0) - -#ifdef CONFIG_XEN_SHADOW_MODE -# define set_pmd(pmdptr,pmdval) \ - set_64bit((unsigned long long *)(pmdptr),pmd_val(pmdval)) -# define set_pud(pudptr,pudval) \ - set_64bit((unsigned long long *)(pudptr),pud_val(pudval)) -#else -# define set_pmd(pmdptr,pmdval) \ - xen_l2_entry_update((pmdptr), (pmdval)) -# define set_pud(pudptr,pudval) \ - xen_l3_entry_update((pudptr), (pudval)) -#endif - -/* - * Pentium-II erratum A13: in PAE mode we explicitly have to flush - * the TLB via cr3 if the top-level pgd is changed... - * We do not let the generic code free and clear pgd entries due to - * this erratum. - */ -static inline void pud_clear (pud_t * pud) { } - -#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)) - -#define pmd_page_kernel(pmd) \ -((unsigned long) __va(pmd_val(pmd) & PAGE_MASK)) - -#define pud_page(pud) \ -((struct page *) __va(pud_val(pud) & PAGE_MASK)) - -#define pud_page_kernel(pud) \ -((unsigned long) __va(pud_val(pud) & PAGE_MASK)) - - -/* Find an entry in the second-level page table.. */ -#define pmd_offset(pud, address) ((pmd_t *) pud_page(*(pud)) + \ - pmd_index(address)) - -static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) -{ - pte_t res; - - /* xchg acts as a barrier before the setting of the high bits */ - res.pte_low = xchg(&ptep->pte_low, 0); - res.pte_high = ptep->pte_high; - ptep->pte_high = 0; - - return res; -} - -static inline int pte_same(pte_t a, pte_t b) -{ - return a.pte_low == b.pte_low && a.pte_high == b.pte_high; -} - -#define pte_page(x) pfn_to_page(pte_pfn(x)) - -static inline int pte_none(pte_t pte) -{ - return !pte.pte_low && !pte.pte_high; -} - -#define pte_mfn(_pte) ( ((_pte).pte_low >> PAGE_SHIFT) |\ - (((_pte).pte_high & 0xfff) << (32-PAGE_SHIFT)) ) -#define pte_pfn(_pte) \ -({ \ - unsigned long mfn = pte_mfn(_pte); \ - unsigned long pfn = mfn_to_pfn(mfn); \ - if ((pfn >= max_mapnr) || (phys_to_machine_mapping[pfn] != mfn))\ - pfn = max_mapnr; /* special: force !pfn_valid() */ \ - pfn; \ -}) - -extern unsigned long long __supported_pte_mask; - -static inline pte_t pfn_pte_ma(unsigned long page_nr, pgprot_t pgprot) -{ - pte_t pte; - - pte.pte_high = (page_nr >> (32 - PAGE_SHIFT)) | \ - (pgprot_val(pgprot) >> 32); - pte.pte_high &= (__supported_pte_mask >> 32); - pte.pte_low = ((page_nr << PAGE_SHIFT) | pgprot_val(pgprot)) & \ - __supported_pte_mask; - return pte; -} - -static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) -{ - return pfn_pte_ma(pfn_to_mfn(page_nr), pgprot); -} - -static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) -{ - BUG(); panic("needs review"); - return __pmd((((unsigned long long)page_nr << PAGE_SHIFT) | \ - pgprot_val(pgprot)) & __supported_pte_mask); -} - -/* - * Bits 0, 6 and 7 are taken in the low part of the pte, - * put the 32 bits of offset into the high part. - */ -#define pte_to_pgoff(pte) ((pte).pte_high) -#define pgoff_to_pte(off) ((pte_t) { _PAGE_FILE, (off) }) -#define PTE_FILE_MAX_BITS 32 - -/* Encode and de-code a swap entry */ -#define __swp_type(x) (((x).val) & 0x1f) -#define __swp_offset(x) ((x).val >> 5) -#define __swp_entry(type, offset) ((swp_entry_t){(type) | (offset) << 5}) -#define __pte_to_swp_entry(pte) ((swp_entry_t){ (pte).pte_high }) -#define __swp_entry_to_pte(x) ((pte_t){ 0, (x).val }) - -#define __pmd_free_tlb(tlb, x) do { } while (0) - -#endif /* _I386_PGTABLE_3LEVEL_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/pgtable.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/pgtable.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,478 +0,0 @@ -#ifndef _I386_PGTABLE_H -#define _I386_PGTABLE_H - -#include <linux/config.h> -#include <asm/hypervisor.h> - -/* - * The Linux memory management assumes a three-level page table setup. On - * the i386, we use that, but "fold" the mid level into the top-level page - * table, so that we physically have the same two-level page table as the - * i386 mmu expects. - * - * This file contains the functions and defines necessary to modify and use - * the i386 page table tree. - */ -#ifndef __ASSEMBLY__ -#include <asm/processor.h> -#include <asm/fixmap.h> -#include <linux/threads.h> - -#ifndef _I386_BITOPS_H -#include <asm/bitops.h> -#endif - -#include <linux/slab.h> -#include <linux/list.h> -#include <linux/spinlock.h> - -/* - * ZERO_PAGE is a global shared page that is always zero: used - * for zero-mapped memory areas etc.. - */ -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) -extern unsigned long empty_zero_page[1024]; -extern pgd_t *swapper_pg_dir; -extern kmem_cache_t *pgd_cache; -extern kmem_cache_t *pmd_cache; -extern spinlock_t pgd_lock; -extern struct page *pgd_list; - -void pmd_ctor(void *, kmem_cache_t *, unsigned long); -void pgd_ctor(void *, kmem_cache_t *, unsigned long); -void pgd_dtor(void *, kmem_cache_t *, unsigned long); -void pgtable_cache_init(void); -void paging_init(void); - -/* - * The Linux x86 paging architecture is 'compile-time dual-mode', it - * implements both the traditional 2-level x86 page tables and the - * newer 3-level PAE-mode page tables. - */ -#ifdef CONFIG_X86_PAE -# include <asm/pgtable-3level-defs.h> -# define PMD_SIZE (1UL << PMD_SHIFT) -# define PMD_MASK (~(PMD_SIZE-1)) -#else -# include <asm/pgtable-2level-defs.h> -#endif - -#define PGDIR_SIZE (1UL << PGDIR_SHIFT) -#define PGDIR_MASK (~(PGDIR_SIZE-1)) - -#define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE) -#define FIRST_USER_ADDRESS 0 - -#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT) -#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS) - -#define TWOLEVEL_PGDIR_SHIFT 22 -#define BOOT_USER_PGD_PTRS (__PAGE_OFFSET >> TWOLEVEL_PGDIR_SHIFT) -#define BOOT_KERNEL_PGD_PTRS (1024-BOOT_USER_PGD_PTRS) - -/* Just any arbitrary offset to the start of the vmalloc VM area: the - * current 8MB value just means that there will be a 8MB "hole" after the - * physical memory until the kernel virtual memory starts. That means that - * any out-of-bounds memory accesses will hopefully be caught. - * The vmalloc() routines leaves a hole of 4kB between each vmalloced - * area for the same reason. ;) - */ -#define VMALLOC_OFFSET (8*1024*1024) -#define VMALLOC_START (((unsigned long) high_memory + vmalloc_earlyreserve + \ - 2*VMALLOC_OFFSET-1) & ~(VMALLOC_OFFSET-1)) -#ifdef CONFIG_HIGHMEM -# define VMALLOC_END (PKMAP_BASE-2*PAGE_SIZE) -#else -# define VMALLOC_END (FIXADDR_START-2*PAGE_SIZE) -#endif - -/* - * The 4MB page is guessing.. Detailed in the infamous "Chapter H" - * of the Pentium details, but assuming intel did the straightforward - * thing, this bit set in the page directory entry just means that - * the page directory entry points directly to a 4MB-aligned block of - * memory. - */ -#define _PAGE_BIT_PRESENT 0 -#define _PAGE_BIT_RW 1 -#define _PAGE_BIT_USER 2 -#define _PAGE_BIT_PWT 3 -#define _PAGE_BIT_PCD 4 -#define _PAGE_BIT_ACCESSED 5 -#define _PAGE_BIT_DIRTY 6 -#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page, Pentium+, if present.. */ -#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */ -#define _PAGE_BIT_UNUSED1 9 /* available for programmer */ -#define _PAGE_BIT_UNUSED2 10 -#define _PAGE_BIT_UNUSED3 11 -#define _PAGE_BIT_NX 63 - -#define _PAGE_PRESENT 0x001 -#define _PAGE_RW 0x002 -#define _PAGE_USER 0x004 -#define _PAGE_PWT 0x008 -#define _PAGE_PCD 0x010 -#define _PAGE_ACCESSED 0x020 -#define _PAGE_DIRTY 0x040 -#define _PAGE_PSE 0x080 /* 4 MB (or 2MB) page, Pentium+, if present.. */ -#define _PAGE_GLOBAL 0x100 /* Global TLB entry PPro+ */ -#define _PAGE_UNUSED1 0x200 /* available for programmer */ -#define _PAGE_UNUSED2 0x400 -#define _PAGE_UNUSED3 0x800 - -#define _PAGE_FILE 0x040 /* set:pagecache unset:swap */ -#define _PAGE_PROTNONE 0x080 /* If not present */ -#ifdef CONFIG_X86_PAE -#define _PAGE_NX (1ULL<<_PAGE_BIT_NX) -#else -#define _PAGE_NX 0 -#endif - -#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY) -#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY) -#define _PAGE_CHG_MASK (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY) - -#define PAGE_NONE \ - __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED) -#define PAGE_SHARED \ - __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED) - -#define PAGE_SHARED_EXEC \ - __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED) -#define PAGE_COPY_NOEXEC \ - __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX) -#define PAGE_COPY_EXEC \ - __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED) -#define PAGE_COPY \ - PAGE_COPY_NOEXEC -#define PAGE_READONLY \ - __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX) -#define PAGE_READONLY_EXEC \ - __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED) - -#define _PAGE_KERNEL \ - (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX) -#define _PAGE_KERNEL_EXEC \ - (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED) - -extern unsigned long long __PAGE_KERNEL, __PAGE_KERNEL_EXEC; -#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW) -#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_PCD) -#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE) -#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE) - -#define PAGE_KERNEL __pgprot(__PAGE_KERNEL) -#define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO) -#define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC) -#define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE) -#define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE) -#define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC) - -/* - * The i386 can't do page protection for execute, and considers that - * the same are read. Also, write permissions imply read permissions. - * This is the closest we can get.. - */ -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY -#define __P010 PAGE_COPY -#define __P011 PAGE_COPY -#define __P100 PAGE_READONLY_EXEC -#define __P101 PAGE_READONLY_EXEC -#define __P110 PAGE_COPY_EXEC -#define __P111 PAGE_COPY_EXEC - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED -#define __S100 PAGE_READONLY_EXEC -#define __S101 PAGE_READONLY_EXEC -#define __S110 PAGE_SHARED_EXEC -#define __S111 PAGE_SHARED_EXEC - -/* - * Define this if things work differently on an i386 and an i486: - * it will (on an i486) warn about kernel memory accesses that are - * done without a 'access_ok(VERIFY_WRITE,..)' - */ -#undef TEST_ACCESS_OK - -/* The boot page tables (all created as a single array) */ -extern unsigned long pg0[]; - -#define pte_present(x) ((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE)) -#define pte_clear(mm,addr,xp) do { set_pte_at(mm, addr, xp, __pte(0)); } while (0) - -#define pmd_none(x) (!pmd_val(x)) -/* pmd_present doesn't just test the _PAGE_PRESENT bit since wr.p.t. - can temporarily clear it. */ -#define pmd_present(x) (pmd_val(x)) -#define pmd_clear(xp) do { set_pmd(xp, __pmd(0)); } while (0) -#define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER & ~_PAGE_PRESENT)) != (_KERNPG_TABLE & ~_PAGE_PRESENT)) - - -#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT)) - -/* - * The following only work if pte_present() is true. - * Undefined behaviour if not.. - */ -static inline int pte_user(pte_t pte) { return (pte).pte_low & _PAGE_USER; } -static inline int pte_read(pte_t pte) { return (pte).pte_low & _PAGE_USER; } -static inline int pte_dirty(pte_t pte) { return (pte).pte_low & _PAGE_DIRTY; } -static inline int pte_young(pte_t pte) { return (pte).pte_low & _PAGE_ACCESSED; } -static inline int pte_write(pte_t pte) { return (pte).pte_low & _PAGE_RW; } - -/* - * The following only works if pte_present() is not true. - */ -static inline int pte_file(pte_t pte) { return (pte).pte_low & _PAGE_FILE; } - -static inline pte_t pte_rdprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER; return pte; } -static inline pte_t pte_exprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER; return pte; } -static inline pte_t pte_mkclean(pte_t pte) { (pte).pte_low &= ~_PAGE_DIRTY; return pte; } -static inline pte_t pte_mkold(pte_t pte) { (pte).pte_low &= ~_PAGE_ACCESSED; return pte; } -static inline pte_t pte_wrprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_RW; return pte; } -static inline pte_t pte_mkread(pte_t pte) { (pte).pte_low |= _PAGE_USER; return pte; } -static inline pte_t pte_mkexec(pte_t pte) { (pte).pte_low |= _PAGE_USER; return pte; } -static inline pte_t pte_mkdirty(pte_t pte) { (pte).pte_low |= _PAGE_DIRTY; return pte; } -static inline pte_t pte_mkyoung(pte_t pte) { (pte).pte_low |= _PAGE_ACCESSED; return pte; } -static inline pte_t pte_mkwrite(pte_t pte) { (pte).pte_low |= _PAGE_RW; return pte; } - -#ifdef CONFIG_X86_PAE -# include <asm/pgtable-3level.h> -#else -# include <asm/pgtable-2level.h> -#endif - -static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) -{ - if (!pte_dirty(*ptep)) - return 0; - return test_and_clear_bit(_PAGE_BIT_DIRTY, &ptep->pte_low); -} - -static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) -{ - if (!pte_young(*ptep)) - return 0; - return test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte_low); -} - -static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) -{ - if (pte_write(*ptep)) - clear_bit(_PAGE_BIT_RW, &ptep->pte_low); -} - -/* - * Macro to mark a page protection value as "uncacheable". On processors which do not support - * it, this is a no-op. - */ -#define pgprot_noncached(prot) ((boot_cpu_data.x86 > 3) \ - ? (__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT)) : (prot)) - -/* - * Conversion functions: convert a page and protection to a page entry, - * and a page entry and page directory to the page they refer to. - */ - -#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot)) -#define mk_pte_huge(entry) ((entry).pte_low |= _PAGE_PRESENT | _PAGE_PSE) - -static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) -{ - pte.pte_low &= _PAGE_CHG_MASK; - pte.pte_low |= pgprot_val(newprot); -#ifdef CONFIG_X86_PAE - /* - * Chop off the NX bit (if present), and add the NX portion of - * the newprot (if present): - */ - pte.pte_high &= ~(1 << (_PAGE_BIT_NX - 32)); - pte.pte_high |= (pgprot_val(newprot) >> 32) & \ - (__supported_pte_mask >> 32); -#endif - return pte; -} - -#define page_pte(page) page_pte_prot(page, __pgprot(0)) - -#define pmd_large(pmd) \ -((pmd_val(pmd) & (_PAGE_PSE|_PAGE_PRESENT)) == (_PAGE_PSE|_PAGE_PRESENT)) - -/* - * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD] - * - * this macro returns the index of the entry in the pgd page which would - * control the given virtual address - */ -#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1)) -#define pgd_index_k(addr) pgd_index(addr) - -/* - * pgd_offset() returns a (pgd_t *) - * pgd_index() is used get the offset into the pgd page's array of pgd_t's; - */ -#define pgd_offset(mm, address) ((mm)->pgd+pgd_index(address)) - -/* - * a shortcut which implies the use of the kernel's pgd, instead - * of a process's - */ -#define pgd_offset_k(address) pgd_offset(&init_mm, address) - -/* - * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD] - * - * this macro returns the index of the entry in the pmd page which would - * control the given virtual address - */ -#define pmd_index(address) \ - (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1)) - -/* - * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE] - * - * this macro returns the index of the entry in the pte page which would - * control the given virtual address - */ -#define pte_index(address) \ - (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) -#define pte_offset_kernel(dir, address) \ - ((pte_t *) pmd_page_kernel(*(dir)) + pte_index(address)) - -/* - * Helper function that returns the kernel pagetable entry controlling - * the virtual address 'address'. NULL means no pagetable entry present. - * NOTE: the return type is pte_t but if the pmd is PSE then we return it - * as a pte too. - */ -extern pte_t *lookup_address(unsigned long address); - -/* - * Make a given kernel text page executable/non-executable. - * Returns the previous executability setting of that page (which - * is used to restore the previous state). Used by the SMP bootup code. - * NOTE: this is an __init function for security reasons. - */ -#ifdef CONFIG_X86_PAE - extern int set_kernel_exec(unsigned long vaddr, int enable); -#else - static inline int set_kernel_exec(unsigned long vaddr, int enable) { return 0;} -#endif - -extern void noexec_setup(const char *str); - -#if defined(CONFIG_HIGHPTE) -#define pte_offset_map(dir, address) \ - ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)),KM_PTE0) + \ - pte_index(address)) -#define pte_offset_map_nested(dir, address) \ - ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)),KM_PTE1) + \ - pte_index(address)) -#define pte_unmap(pte) kunmap_atomic(pte, KM_PTE0) -#define pte_unmap_nested(pte) kunmap_atomic(pte, KM_PTE1) -#else -#define pte_offset_map(dir, address) \ - ((pte_t *)page_address(pmd_page(*(dir))) + pte_index(address)) -#define pte_offset_map_nested(dir, address) pte_offset_map(dir, address) -#define pte_unmap(pte) do { } while (0) -#define pte_unmap_nested(pte) do { } while (0) -#endif - -/* - * The i386 doesn't have any external MMU info: the kernel page - * tables contain all the necessary information. - * - * Also, we only update the dirty/accessed state if we set - * the dirty bit by hand in the kernel, since the hardware - * will do the accessed bit for us, and we don't want to - * race with other CPU's that might be updating the dirty - * bit at the same time. - */ -#define update_mmu_cache(vma,address,pte) do { } while (0) -#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS -#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \ - do { \ - if (__dirty) { \ - if ( likely((__vma)->vm_mm == current->mm) ) { \ - BUG_ON(HYPERVISOR_update_va_mapping((__address), (__entry), UVMF_INVLPG|UVMF_MULTI|(unsigned long)((__vma)->vm_mm->cpu_vm_mask.bits))); \ - } else { \ - xen_l1_entry_update((__ptep), (__entry)); \ - flush_tlb_page((__vma), (__address)); \ - } \ - } \ - } while (0) - -#define __HAVE_ARCH_PTEP_ESTABLISH -#define ptep_establish(__vma, __address, __ptep, __entry) \ -do { \ - ptep_set_access_flags(__vma, __address, __ptep, __entry, 1); \ -} while (0) - -#include <asm-xen/features.h> -void make_lowmem_page_readonly(void *va, unsigned int feature); -void make_lowmem_page_writable(void *va, unsigned int feature); -void make_page_readonly(void *va, unsigned int feature); -void make_page_writable(void *va, unsigned int feature); -void make_pages_readonly(void *va, unsigned int nr, unsigned int feature); -void make_pages_writable(void *va, unsigned int nr, unsigned int feature); - -#define virt_to_ptep(__va) \ -({ \ - pgd_t *__pgd = pgd_offset_k((unsigned long)(__va)); \ - pud_t *__pud = pud_offset(__pgd, (unsigned long)(__va)); \ - pmd_t *__pmd = pmd_offset(__pud, (unsigned long)(__va)); \ - pte_offset_kernel(__pmd, (unsigned long)(__va)); \ -}) - -#define arbitrary_virt_to_machine(__va) \ -({ \ - maddr_t m = (maddr_t)pte_mfn(*virt_to_ptep(__va)) << PAGE_SHIFT;\ - m | ((unsigned long)(__va) & (PAGE_SIZE-1)); \ -}) - -#endif /* !__ASSEMBLY__ */ - -#ifndef CONFIG_DISCONTIGMEM -#define kern_addr_valid(addr) (1) -#endif /* !CONFIG_DISCONTIGMEM */ - -int direct_remap_pfn_range(struct vm_area_struct *vma, - unsigned long address, - unsigned long mfn, - unsigned long size, - pgprot_t prot, - domid_t domid); -int direct_kernel_remap_pfn_range(unsigned long address, - unsigned long mfn, - unsigned long size, - pgprot_t prot, - domid_t domid); -int create_lookup_pte_addr(struct mm_struct *mm, - unsigned long address, - uint64_t *ptep); -int touch_pte_range(struct mm_struct *mm, - unsigned long address, - unsigned long size); - -#define io_remap_page_range(vma,from,phys,size,prot) \ -direct_remap_pfn_range(vma,from,(phys)>>PAGE_SHIFT,size,prot,DOMID_IO) - -#define io_remap_pfn_range(vma,from,pfn,size,prot) \ -direct_remap_pfn_range(vma,from,pfn,size,prot,DOMID_IO) - -#define MK_IOSPACE_PFN(space, pfn) (pfn) -#define GET_IOSPACE(pfn) 0 -#define GET_PFN(pfn) (pfn) - -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY -#define __HAVE_ARCH_PTEP_GET_AND_CLEAR -#define __HAVE_ARCH_PTEP_SET_WRPROTECT -#define __HAVE_ARCH_PTE_SAME -#include <asm-generic/pgtable.h> - -#endif /* _I386_PGTABLE_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/processor.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/processor.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,703 +0,0 @@ -/* - * include/asm-i386/processor.h - * - * Copyright (C) 1994 Linus Torvalds - */ - -#ifndef __ASM_I386_PROCESSOR_H -#define __ASM_I386_PROCESSOR_H - -#include <asm/vm86.h> -#include <asm/math_emu.h> -#include <asm/segment.h> -#include <asm/page.h> -#include <asm/types.h> -#include <asm/sigcontext.h> -#include <asm/cpufeature.h> -#include <asm/msr.h> -#include <asm/system.h> -#include <linux/cache.h> -#include <linux/config.h> -#include <linux/threads.h> -#include <asm/percpu.h> - -/* flag for disabling the tsc */ -extern int tsc_disable; - -struct desc_struct { - unsigned long a,b; -}; - -#define desc_empty(desc) \ - (!((desc)->a + (desc)->b)) - -#define desc_equal(desc1, desc2) \ - (((desc1)->a == (desc2)->a) && ((desc1)->b == (desc2)->b)) -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ void *pc; __asm__("movl $1f,%0\n1:":"=g" (pc)); pc; }) - -/* - * CPU type and hardware bug flags. Kept separately for each CPU. - * Members of this structure are referenced in head.S, so think twice - * before touching them. [mj] - */ - -struct cpuinfo_x86 { - __u8 x86; /* CPU family */ - __u8 x86_vendor; /* CPU vendor */ - __u8 x86_model; - __u8 x86_mask; - char wp_works_ok; /* It doesn't on 386's */ - char hlt_works_ok; /* Problems on some 486Dx4's and old 386's */ - char hard_math; - char rfu; - int cpuid_level; /* Maximum supported CPUID level, -1=no CPUID */ - unsigned long x86_capability[NCAPINTS]; - char x86_vendor_id[16]; - char x86_model_id[64]; - int x86_cache_size; /* in KB - valid for CPUS which support this - call */ - int x86_cache_alignment; /* In bytes */ - int fdiv_bug; - int f00f_bug; - int coma_bug; - unsigned long loops_per_jiffy; - unsigned char x86_num_cores; -} __attribute__((__aligned__(SMP_CACHE_BYTES))); - -#define X86_VENDOR_INTEL 0 -#define X86_VENDOR_CYRIX 1 -#define X86_VENDOR_AMD 2 -#define X86_VENDOR_UMC 3 -#define X86_VENDOR_NEXGEN 4 -#define X86_VENDOR_CENTAUR 5 -#define X86_VENDOR_RISE 6 -#define X86_VENDOR_TRANSMETA 7 -#define X86_VENDOR_NSC 8 -#define X86_VENDOR_NUM 9 -#define X86_VENDOR_UNKNOWN 0xff - -/* - * capabilities of CPUs - */ - -extern struct cpuinfo_x86 boot_cpu_data; -extern struct cpuinfo_x86 new_cpu_data; -extern struct tss_struct doublefault_tss; -DECLARE_PER_CPU(struct tss_struct, init_tss); -DECLARE_PER_CPU(pgd_t *, cur_pgd); - -#ifdef CONFIG_SMP -extern struct cpuinfo_x86 cpu_data[]; -#define current_cpu_data cpu_data[smp_processor_id()] -#else -#define cpu_data (&boot_cpu_data) -#define current_cpu_data boot_cpu_data -#endif - -extern int phys_proc_id[NR_CPUS]; -extern int cpu_core_id[NR_CPUS]; -extern char ignore_fpu_irq; - -extern void identify_cpu(struct cpuinfo_x86 *); -extern void print_cpu_info(struct cpuinfo_x86 *); -extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c); - -#ifdef CONFIG_X86_HT -extern void detect_ht(struct cpuinfo_x86 *c); -#else -static inline void detect_ht(struct cpuinfo_x86 *c) {} -#endif - -/* - * EFLAGS bits - */ -#define X86_EFLAGS_CF 0x00000001 /* Carry Flag */ -#define X86_EFLAGS_PF 0x00000004 /* Parity Flag */ -#define X86_EFLAGS_AF 0x00000010 /* Auxillary carry Flag */ -#define X86_EFLAGS_ZF 0x00000040 /* Zero Flag */ -#define X86_EFLAGS_SF 0x00000080 /* Sign Flag */ -#define X86_EFLAGS_TF 0x00000100 /* Trap Flag */ -#define X86_EFLAGS_IF 0x00000200 /* Interrupt Flag */ -#define X86_EFLAGS_DF 0x00000400 /* Direction Flag */ -#define X86_EFLAGS_OF 0x00000800 /* Overflow Flag */ -#define X86_EFLAGS_IOPL 0x00003000 /* IOPL mask */ -#define X86_EFLAGS_NT 0x00004000 /* Nested Task */ -#define X86_EFLAGS_RF 0x00010000 /* Resume Flag */ -#define X86_EFLAGS_VM 0x00020000 /* Virtual Mode */ -#define X86_EFLAGS_AC 0x00040000 /* Alignment Check */ -#define X86_EFLAGS_VIF 0x00080000 /* Virtual Interrupt Flag */ -#define X86_EFLAGS_VIP 0x00100000 /* Virtual Interrupt Pending */ -#define X86_EFLAGS_ID 0x00200000 /* CPUID detection flag */ - -/* - * Generic CPUID function - * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx - * resulting in stale register contents being returned. - */ -static inline void cpuid(unsigned int op, unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx) -{ - __asm__("cpuid" - : "=a" (*eax), - "=b" (*ebx), - "=c" (*ecx), - "=d" (*edx) - : "0" (op), "c"(0)); -} - -/* Some CPUID calls want 'count' to be placed in ecx */ -static inline void cpuid_count(int op, int count, int *eax, int *ebx, int *ecx, - int *edx) -{ - __asm__("cpuid" - : "=a" (*eax), - "=b" (*ebx), - "=c" (*ecx), - "=d" (*edx) - : "0" (op), "c" (count)); -} - -/* - * CPUID functions returning a single datum - */ -static inline unsigned int cpuid_eax(unsigned int op) -{ - unsigned int eax; - - __asm__("cpuid" - : "=a" (eax) - : "0" (op) - : "bx", "cx", "dx"); - return eax; -} -static inline unsigned int cpuid_ebx(unsigned int op) -{ - unsigned int eax, ebx; - - __asm__("cpuid" - : "=a" (eax), "=b" (ebx) - : "0" (op) - : "cx", "dx" ); - return ebx; -} -static inline unsigned int cpuid_ecx(unsigned int op) -{ - unsigned int eax, ecx; - - __asm__("cpuid" - : "=a" (eax), "=c" (ecx) - : "0" (op) - : "bx", "dx" ); - return ecx; -} -static inline unsigned int cpuid_edx(unsigned int op) -{ - unsigned int eax, edx; - - __asm__("cpuid" - : "=a" (eax), "=d" (edx) - : "0" (op) - : "bx", "cx"); - return edx; -} - -#define load_cr3(pgdir) do { \ - xen_pt_switch(__pa(pgdir)); \ - per_cpu(cur_pgd, smp_processor_id()) = pgdir; \ -} while (/* CONSTCOND */0) - - -/* - * Intel CPU features in CR4 - */ -#define X86_CR4_VME 0x0001 /* enable vm86 extensions */ -#define X86_CR4_PVI 0x0002 /* virtual interrupts flag enable */ -#define X86_CR4_TSD 0x0004 /* disable time stamp at ipl 3 */ -#define X86_CR4_DE 0x0008 /* enable debugging extensions */ -#define X86_CR4_PSE 0x0010 /* enable page size extensions */ -#define X86_CR4_PAE 0x0020 /* enable physical address extensions */ -#define X86_CR4_MCE 0x0040 /* Machine check enable */ -#define X86_CR4_PGE 0x0080 /* enable global pages */ -#define X86_CR4_PCE 0x0100 /* enable performance counters at ipl 3 */ -#define X86_CR4_OSFXSR 0x0200 /* enable fast FPU save and restore */ -#define X86_CR4_OSXMMEXCPT 0x0400 /* enable unmasked SSE exceptions */ - -/* - * Save the cr4 feature set we're using (ie - * Pentium 4MB enable and PPro Global page - * enable), so that any CPU's that boot up - * after us can get the correct flags. - */ -extern unsigned long mmu_cr4_features; - -static inline void set_in_cr4 (unsigned long mask) -{ - mmu_cr4_features |= mask; - switch (mask) { - case X86_CR4_OSFXSR: - case X86_CR4_OSXMMEXCPT: - break; - default: - do { - const char *msg = "Xen unsupported cr4 update\n"; - (void)HYPERVISOR_console_io( - CONSOLEIO_write, __builtin_strlen(msg), - (char *)msg); - BUG(); - } while (0); - } -} - -static inline void clear_in_cr4 (unsigned long mask) -{ - mmu_cr4_features &= ~mask; - __asm__("movl %%cr4,%%eax\n\t" - "andl %0,%%eax\n\t" - "movl %%eax,%%cr4\n" - : : "irg" (~mask) - :"ax"); -} - -/* - * NSC/Cyrix CPU configuration register indexes - */ - -#define CX86_PCR0 0x20 -#define CX86_GCR 0xb8 -#define CX86_CCR0 0xc0 -#define CX86_CCR1 0xc1 -#define CX86_CCR2 0xc2 -#define CX86_CCR3 0xc3 -#define CX86_CCR4 0xe8 -#define CX86_CCR5 0xe9 -#define CX86_CCR6 0xea -#define CX86_CCR7 0xeb -#define CX86_PCR1 0xf0 -#define CX86_DIR0 0xfe -#define CX86_DIR1 0xff -#define CX86_ARR_BASE 0xc4 -#define CX86_RCR_BASE 0xdc - -/* - * NSC/Cyrix CPU indexed register access macros - */ - -#define getCx86(reg) ({ outb((reg), 0x22); inb(0x23); }) - -#define setCx86(reg, data) do { \ - outb((reg), 0x22); \ - outb((data), 0x23); \ -} while (0) - -static inline void __monitor(const void *eax, unsigned long ecx, - unsigned long edx) -{ - /* "monitor %eax,%ecx,%edx;" */ - asm volatile( - ".byte 0x0f,0x01,0xc8;" - : :"a" (eax), "c" (ecx), "d"(edx)); -} - -static inline void __mwait(unsigned long eax, unsigned long ecx) -{ - /* "mwait %eax,%ecx;" */ - asm volatile( - ".byte 0x0f,0x01,0xc9;" - : :"a" (eax), "c" (ecx)); -} - -/* from system description table in BIOS. Mostly for MCA use, but -others may find it useful. */ -extern unsigned int machine_id; -extern unsigned int machine_submodel_id; -extern unsigned int BIOS_revision; -extern unsigned int mca_pentium_flag; - -/* Boot loader type from the setup header */ -extern int bootloader_type; - -/* - * User space process size: 3GB (default). - */ -#define TASK_SIZE (PAGE_OFFSET) - -/* This decides where the kernel will search for a free chunk of vm - * space during mmap's. - */ -#define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 3)) - -#define HAVE_ARCH_PICK_MMAP_LAYOUT - -/* - * Size of io_bitmap. - */ -#define IO_BITMAP_BITS 65536 -#define IO_BITMAP_BYTES (IO_BITMAP_BITS/8) -#define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long)) -#define IO_BITMAP_OFFSET offsetof(struct tss_struct,io_bitmap) -#define INVALID_IO_BITMAP_OFFSET 0x8000 -#define INVALID_IO_BITMAP_OFFSET_LAZY 0x9000 - -struct i387_fsave_struct { - long cwd; - long swd; - long twd; - long fip; - long fcs; - long foo; - long fos; - long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */ - long status; /* software status information */ -}; - -struct i387_fxsave_struct { - unsigned short cwd; - unsigned short swd; - unsigned short twd; - unsigned short fop; - long fip; - long fcs; - long foo; - long fos; - long mxcsr; - long mxcsr_mask; - long st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */ - long xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */ - long padding[56]; -} __attribute__ ((aligned (16))); - -struct i387_soft_struct { - long cwd; - long swd; - long twd; - long fip; - long fcs; - long foo; - long fos; - long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */ - unsigned char ftop, changed, lookahead, no_update, rm, alimit; - struct info *info; - unsigned long entry_eip; -}; - -union i387_union { - struct i387_fsave_struct fsave; - struct i387_fxsave_struct fxsave; - struct i387_soft_struct soft; -}; - -typedef struct { - unsigned long seg; -} mm_segment_t; - -struct thread_struct; - -struct tss_struct { - unsigned short back_link,__blh; - unsigned long esp0; - unsigned short ss0,__ss0h; - unsigned long esp1; - unsigned short ss1,__ss1h; /* ss1 is used to cache MSR_IA32_SYSENTER_CS */ - unsigned long esp2; - unsigned short ss2,__ss2h; - unsigned long __cr3; - unsigned long eip; - unsigned long eflags; - unsigned long eax,ecx,edx,ebx; - unsigned long esp; - unsigned long ebp; - unsigned long esi; - unsigned long edi; - unsigned short es, __esh; - unsigned short cs, __csh; - unsigned short ss, __ssh; - unsigned short ds, __dsh; - unsigned short fs, __fsh; - unsigned short gs, __gsh; - unsigned short ldt, __ldth; - unsigned short trace, io_bitmap_base; - /* - * The extra 1 is there because the CPU will access an - * additional byte beyond the end of the IO permission - * bitmap. The extra byte must be all 1 bits, and must - * be within the limit. - */ - unsigned long io_bitmap[IO_BITMAP_LONGS + 1]; - /* - * Cache the current maximum and the last task that used the bitmap: - */ - unsigned long io_bitmap_max; - struct thread_struct *io_bitmap_owner; - /* - * pads the TSS to be cacheline-aligned (size is 0x100) - */ - unsigned long __cacheline_filler[35]; - /* - * .. and then another 0x100 bytes for emergency kernel stack - */ - unsigned long stack[64]; -} __attribute__((packed)); - -#define ARCH_MIN_TASKALIGN 16 - -struct thread_struct { -/* cached TLS descriptors. */ - struct desc_struct tls_array[GDT_ENTRY_TLS_ENTRIES]; - unsigned long esp0; - unsigned long sysenter_cs; - unsigned long eip; - unsigned long esp; - unsigned long fs; - unsigned long gs; - unsigned int io_pl; -/* Hardware debugging registers */ - unsigned long debugreg[8]; /* %%db0-7 debug registers */ -/* fault info */ - unsigned long cr2, trap_no, error_code; -/* floating point info */ - union i387_union i387; -/* virtual 86 mode info */ - struct vm86_struct __user * vm86_info; - unsigned long screen_bitmap; - unsigned long v86flags, v86mask, saved_esp0; - unsigned int saved_fs, saved_gs; -/* IO permissions */ - unsigned long *io_bitmap_ptr; -/* max allowed port in the bitmap, in bytes: */ - unsigned long io_bitmap_max; -}; - -#define INIT_THREAD { \ - .vm86_info = NULL, \ - .sysenter_cs = __KERNEL_CS, \ - .io_bitmap_ptr = NULL, \ -} - -/* - * Note that the .io_bitmap member must be extra-big. This is because - * the CPU will access an additional byte beyond the end of the IO - * permission bitmap. The extra byte must be all 1 bits, and must - * be within the limit. - */ -#define INIT_TSS { \ - .esp0 = sizeof(init_stack) + (long)&init_stack, \ - .ss0 = __KERNEL_DS, \ - .ss1 = __KERNEL_CS, \ - .ldt = GDT_ENTRY_LDT, \ - .io_bitmap_base = INVALID_IO_BITMAP_OFFSET, \ - .io_bitmap = { [ 0 ... IO_BITMAP_LONGS] = ~0 }, \ -} - -static inline void load_esp0(struct tss_struct *tss, struct thread_struct *thread) -{ - tss->esp0 = thread->esp0; - /* This can only happen when SEP is enabled, no need to test "SEP"arately */ - if (unlikely(tss->ss1 != thread->sysenter_cs)) { - tss->ss1 = thread->sysenter_cs; - wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0); - } - HYPERVISOR_stack_switch(tss->ss0, tss->esp0); -} - -#define start_thread(regs, new_eip, new_esp) do { \ - __asm__("movl %0,%%fs ; movl %0,%%gs": :"r" (0)); \ - set_fs(USER_DS); \ - regs->xds = __USER_DS; \ - regs->xes = __USER_DS; \ - regs->xss = __USER_DS; \ - regs->xcs = __USER_CS; \ - regs->eip = new_eip; \ - regs->esp = new_esp; \ -} while (0) - -/* - * This special macro can be used to load a debugging register - */ -#define loaddebug(thread,register) \ - HYPERVISOR_set_debugreg((register), \ - ((thread)->debugreg[register])) - -/* Forward declaration, a strange C thing */ -struct task_struct; -struct mm_struct; - -/* Free all resources held by a thread. */ -extern void release_thread(struct task_struct *); - -/* Prepare to copy thread state - unlazy all lazy status */ -extern void prepare_to_copy(struct task_struct *tsk); - -/* - * create a kernel thread without removing it from tasklists - */ -extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); - -extern unsigned long thread_saved_pc(struct task_struct *tsk); -void show_trace(struct task_struct *task, unsigned long *stack); - -unsigned long get_wchan(struct task_struct *p); - -#define THREAD_SIZE_LONGS (THREAD_SIZE/sizeof(unsigned long)) -#define KSTK_TOP(info) \ -({ \ - unsigned long *__ptr = (unsigned long *)(info); \ - (unsigned long)(&__ptr[THREAD_SIZE_LONGS]); \ -}) - -#define task_pt_regs(task) \ -({ \ - struct pt_regs *__regs__; \ - __regs__ = (struct pt_regs *)KSTK_TOP((task)->thread_info); \ - __regs__ - 1; \ -}) - -#define KSTK_EIP(task) (task_pt_regs(task)->eip) -#define KSTK_ESP(task) (task_pt_regs(task)->esp) - - -struct microcode_header { - unsigned int hdrver; - unsigned int rev; - unsigned int date; - unsigned int sig; - unsigned int cksum; - unsigned int ldrver; - unsigned int pf; - unsigned int datasize; - unsigned int totalsize; - unsigned int reserved[3]; -}; - -struct microcode { - struct microcode_header hdr; - unsigned int bits[0]; -}; - -typedef struct microcode microcode_t; -typedef struct microcode_header microcode_header_t; - -/* microcode format is extended from prescott processors */ -struct extended_signature { - unsigned int sig; - unsigned int pf; - unsigned int cksum; -}; - -struct extended_sigtable { - unsigned int count; - unsigned int cksum; - unsigned int reserved[3]; - struct extended_signature sigs[0]; -}; -/* '6' because it used to be for P6 only (but now covers Pentium 4 as well) */ -#define MICROCODE_IOCFREE _IO('6',0) - -/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ -static inline void rep_nop(void) -{ - __asm__ __volatile__("rep;nop": : :"memory"); -} - -#define cpu_relax() rep_nop() - -/* generic versions from gas */ -#define GENERIC_NOP1 ".byte 0x90\n" -#define GENERIC_NOP2 ".byte 0x89,0xf6\n" -#define GENERIC_NOP3 ".byte 0x8d,0x76,0x00\n" -#define GENERIC_NOP4 ".byte 0x8d,0x74,0x26,0x00\n" -#define GENERIC_NOP5 GENERIC_NOP1 GENERIC_NOP4 -#define GENERIC_NOP6 ".byte 0x8d,0xb6,0x00,0x00,0x00,0x00\n" -#define GENERIC_NOP7 ".byte 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00\n" -#define GENERIC_NOP8 GENERIC_NOP1 GENERIC_NOP7 - -/* Opteron nops */ -#define K8_NOP1 GENERIC_NOP1 -#define K8_NOP2 ".byte 0x66,0x90\n" -#define K8_NOP3 ".byte 0x66,0x66,0x90\n" -#define K8_NOP4 ".byte 0x66,0x66,0x66,0x90\n" -#define K8_NOP5 K8_NOP3 K8_NOP2 -#define K8_NOP6 K8_NOP3 K8_NOP3 -#define K8_NOP7 K8_NOP4 K8_NOP3 -#define K8_NOP8 K8_NOP4 K8_NOP4 - -/* K7 nops */ -/* uses eax dependencies (arbitary choice) */ -#define K7_NOP1 GENERIC_NOP1 -#define K7_NOP2 ".byte 0x8b,0xc0\n" -#define K7_NOP3 ".byte 0x8d,0x04,0x20\n" -#define K7_NOP4 ".byte 0x8d,0x44,0x20,0x00\n" -#define K7_NOP5 K7_NOP4 ASM_NOP1 -#define K7_NOP6 ".byte 0x8d,0x80,0,0,0,0\n" -#define K7_NOP7 ".byte 0x8D,0x04,0x05,0,0,0,0\n" -#define K7_NOP8 K7_NOP7 ASM_NOP1 - -#ifdef CONFIG_MK8 -#define ASM_NOP1 K8_NOP1 -#define ASM_NOP2 K8_NOP2 -#define ASM_NOP3 K8_NOP3 -#define ASM_NOP4 K8_NOP4 -#define ASM_NOP5 K8_NOP5 -#define ASM_NOP6 K8_NOP6 -#define ASM_NOP7 K8_NOP7 -#define ASM_NOP8 K8_NOP8 -#elif defined(CONFIG_MK7) -#define ASM_NOP1 K7_NOP1 -#define ASM_NOP2 K7_NOP2 -#define ASM_NOP3 K7_NOP3 -#define ASM_NOP4 K7_NOP4 -#define ASM_NOP5 K7_NOP5 -#define ASM_NOP6 K7_NOP6 -#define ASM_NOP7 K7_NOP7 -#define ASM_NOP8 K7_NOP8 -#else -#define ASM_NOP1 GENERIC_NOP1 -#define ASM_NOP2 GENERIC_NOP2 -#define ASM_NOP3 GENERIC_NOP3 -#define ASM_NOP4 GENERIC_NOP4 -#define ASM_NOP5 GENERIC_NOP5 -#define ASM_NOP6 GENERIC_NOP6 -#define ASM_NOP7 GENERIC_NOP7 -#define ASM_NOP8 GENERIC_NOP8 -#endif - -#define ASM_NOP_MAX 8 - -/* Prefetch instructions for Pentium III and AMD Athlon */ -/* It's not worth to care about 3dnow! prefetches for the K6 - because they are microcoded there and very slow. - However we don't do prefetches for pre XP Athlons currently - That should be fixed. */ -#define ARCH_HAS_PREFETCH -extern inline void prefetch(const void *x) -{ - alternative_input(ASM_NOP4, - "prefetchnta (%1)", - X86_FEATURE_XMM, - "r" (x)); -} - -#define ARCH_HAS_PREFETCH -#define ARCH_HAS_PREFETCHW -#define ARCH_HAS_SPINLOCK_PREFETCH - -/* 3dnow! prefetch to get an exclusive cache line. Useful for - spinlocks to avoid one state transition in the cache coherency protocol. */ -extern inline void prefetchw(const void *x) -{ - alternative_input(ASM_NOP4, - "prefetchw (%1)", - X86_FEATURE_3DNOW, - "r" (x)); -} -#define spin_lock_prefetch(x) prefetchw(x) - -extern void select_idle_routine(const struct cpuinfo_x86 *c); - -#define cache_line_size() (boot_cpu_data.x86_cache_alignment) - -extern unsigned long boot_option_idle_override; - -#endif /* __ASM_I386_PROCESSOR_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/ptrace.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/ptrace.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,69 +0,0 @@ -#ifndef _I386_PTRACE_H -#define _I386_PTRACE_H - -#define EBX 0 -#define ECX 1 -#define EDX 2 -#define ESI 3 -#define EDI 4 -#define EBP 5 -#define EAX 6 -#define DS 7 -#define ES 8 -#define FS 9 -#define GS 10 -#define ORIG_EAX 11 -#define EIP 12 -#define CS 13 -#define EFL 14 -#define UESP 15 -#define SS 16 -#define FRAME_SIZE 17 - -/* this struct defines the way the registers are stored on the - stack during a system call. */ - -struct pt_regs { - long ebx; - long ecx; - long edx; - long esi; - long edi; - long ebp; - long eax; - int xds; - int xes; - long orig_eax; - long eip; - int xcs; - long eflags; - long esp; - int xss; -}; - -/* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */ -#define PTRACE_GETREGS 12 -#define PTRACE_SETREGS 13 -#define PTRACE_GETFPREGS 14 -#define PTRACE_SETFPREGS 15 -#define PTRACE_GETFPXREGS 18 -#define PTRACE_SETFPXREGS 19 - -#define PTRACE_OLDSETOPTIONS 21 - -#define PTRACE_GET_THREAD_AREA 25 -#define PTRACE_SET_THREAD_AREA 26 - -#ifdef __KERNEL__ -struct task_struct; -extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code); -#define user_mode(regs) ((VM_MASK & (regs)->eflags) || (2 & (regs)->xcs)) -#define instruction_pointer(regs) ((regs)->eip) -#if defined(CONFIG_SMP) && defined(CONFIG_FRAME_POINTER) -extern unsigned long profile_pc(struct pt_regs *regs); -#else -#define profile_pc(regs) instruction_pointer(regs) -#endif -#endif - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/scatterlist.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/scatterlist.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,22 +0,0 @@ -#ifndef _I386_SCATTERLIST_H -#define _I386_SCATTERLIST_H - -struct scatterlist { - struct page *page; - unsigned int offset; - unsigned int length; - dma_addr_t dma_address; - unsigned int dma_length; -}; - -/* These macros should be used after a pci_map_sg call has been done - * to get bus addresses of each of the SG entries and their lengths. - * You should only work with the number of sg entries pci_map_sg - * returns. - */ -#define sg_dma_address(sg) ((sg)->dma_address) -#define sg_dma_len(sg) ((sg)->dma_length) - -#define ISA_DMA_THRESHOLD (0x00ffffff) - -#endif /* !(_I386_SCATTERLIST_H) */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/segment.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/segment.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,99 +0,0 @@ -#ifndef _ASM_SEGMENT_H -#define _ASM_SEGMENT_H - -/* - * The layout of the per-CPU GDT under Linux: - * - * 0 - null - * 1 - reserved - * 2 - reserved - * 3 - reserved - * - * 4 - unused <==== new cacheline - * 5 - unused - * - * ------- start of TLS (Thread-Local Storage) segments: - * - * 6 - TLS segment #1 [ glibc's TLS segment ] - * 7 - TLS segment #2 [ Wine's %fs Win32 segment ] - * 8 - TLS segment #3 - * 9 - reserved - * 10 - reserved - * 11 - reserved - * - * ------- start of kernel segments: - * - * 12 - kernel code segment <==== new cacheline - * 13 - kernel data segment - * 14 - default user CS - * 15 - default user DS - * 16 - TSS - * 17 - LDT - * 18 - PNPBIOS support (16->32 gate) - * 19 - PNPBIOS support - * 20 - PNPBIOS support - * 21 - PNPBIOS support - * 22 - PNPBIOS support - * 23 - APM BIOS support - * 24 - APM BIOS support - * 25 - APM BIOS support - * - * 26 - ESPFIX small SS - * 27 - unused - * 28 - unused - * 29 - unused - * 30 - unused - * 31 - TSS for double fault handler - */ -#define GDT_ENTRY_TLS_ENTRIES 3 -#define GDT_ENTRY_TLS_MIN 6 -#define GDT_ENTRY_TLS_MAX (GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1) - -#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8) - -#define GDT_ENTRY_DEFAULT_USER_CS 14 -#define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS * 8 + 3) - -#define GDT_ENTRY_DEFAULT_USER_DS 15 -#define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS * 8 + 3) - -#define GDT_ENTRY_KERNEL_BASE 12 - -#define GDT_ENTRY_KERNEL_CS (GDT_ENTRY_KERNEL_BASE + 0) -#define __KERNEL_CS (GDT_ENTRY_KERNEL_CS * 8 + 1) - -#define GDT_ENTRY_KERNEL_DS (GDT_ENTRY_KERNEL_BASE + 1) -#define __KERNEL_DS (GDT_ENTRY_KERNEL_DS * 8 + 1) - -#define GDT_ENTRY_TSS (GDT_ENTRY_KERNEL_BASE + 4) -#define GDT_ENTRY_LDT (GDT_ENTRY_KERNEL_BASE + 5) - -#define GDT_ENTRY_PNPBIOS_BASE (GDT_ENTRY_KERNEL_BASE + 6) -#define GDT_ENTRY_APMBIOS_BASE (GDT_ENTRY_KERNEL_BASE + 11) - -#define GDT_ENTRY_ESPFIX_SS (GDT_ENTRY_KERNEL_BASE + 14) -#define __ESPFIX_SS (GDT_ENTRY_ESPFIX_SS * 8) - -#define GDT_ENTRY_DOUBLEFAULT_TSS 31 - -/* - * The GDT has 32 entries - */ -#define GDT_ENTRIES 32 - -#define GDT_SIZE (GDT_ENTRIES * 8) - -/* Simple and small GDT entries for booting only */ - -#define __BOOT_CS FLAT_KERNEL_CS - -#define __BOOT_DS FLAT_KERNEL_DS - -/* - * The interrupt descriptor table has room for 256 idt's, - * the global descriptor table is dependent on the number - * of tasks we can have.. - */ -#define IDT_ENTRIES 256 - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/setup.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/setup.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,66 +0,0 @@ -/* - * Just a place holder. We don't want to have to test x86 before - * we include stuff - */ - -#ifndef _i386_SETUP_H -#define _i386_SETUP_H - -#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) -#define PFN_DOWN(x) ((x) >> PAGE_SHIFT) -#define PFN_PHYS(x) ((unsigned long long)(x) << PAGE_SHIFT) - -/* - * Reserved space for vmalloc and iomap - defined in asm/page.h - */ -#define MAXMEM_PFN PFN_DOWN(MAXMEM) -#define MAX_NONPAE_PFN (1 << 20) - -#define PARAM_SIZE 4096 -#define COMMAND_LINE_SIZE 256 - -#define OLD_CL_MAGIC_ADDR 0x90020 -#define OLD_CL_MAGIC 0xA33F -#define OLD_CL_BASE_ADDR 0x90000 -#define OLD_CL_OFFSET 0x90022 -#define NEW_CL_POINTER 0x228 /* Relative to real mode data */ - -#ifndef __ASSEMBLY__ -/* - * This is set up by the setup-routine at boot-time - */ -extern unsigned char boot_params[PARAM_SIZE]; - -#define PARAM (boot_params) -#define SCREEN_INFO (*(struct screen_info *) (PARAM+0)) -#define EXT_MEM_K (*(unsigned short *) (PARAM+2)) -#define ALT_MEM_K (*(unsigned long *) (PARAM+0x1e0)) -#define E820_MAP_NR (*(char*) (PARAM+E820NR)) -#define E820_MAP ((struct e820entry *) (PARAM+E820MAP)) -#define APM_BIOS_INFO (*(struct apm_bios_info *) (PARAM+0x40)) -#define IST_INFO (*(struct ist_info *) (PARAM+0x60)) -#define DRIVE_INFO (*(struct drive_info_struct *) (PARAM+0x80)) -#define SYS_DESC_TABLE (*(struct sys_desc_table_struct*)(PARAM+0xa0)) -#define EFI_SYSTAB ((efi_system_table_t *) *((unsigned long *)(PARAM+0x1c4))) -#define EFI_MEMDESC_SIZE (*((unsigned long *) (PARAM+0x1c8))) -#define EFI_MEMDESC_VERSION (*((unsigned long *) (PARAM+0x1cc))) -#define EFI_MEMMAP ((efi_memory_desc_t *) *((unsigned long *)(PARAM+0x1d0))) -#define EFI_MEMMAP_SIZE (*((unsigned long *) (PARAM+0x1d4))) -#define MOUNT_ROOT_RDONLY (*(unsigned short *) (PARAM+0x1F2)) -#define RAMDISK_FLAGS (*(unsigned short *) (PARAM+0x1F8)) -#define VIDEO_MODE (*(unsigned short *) (PARAM+0x1FA)) -#define ORIG_ROOT_DEV (*(unsigned short *) (PARAM+0x1FC)) -#define AUX_DEVICE_INFO (*(unsigned char *) (PARAM+0x1FF)) -#define LOADER_TYPE (*(unsigned char *) (PARAM+0x210)) -#define KERNEL_START (*(unsigned long *) (PARAM+0x214)) -#define INITRD_START (__pa(xen_start_info->mod_start)) -#define INITRD_SIZE (xen_start_info->mod_len) -#define EDID_INFO (*(struct edid_info *) (PARAM+0x440)) -#define EDD_NR (*(unsigned char *) (PARAM+EDDNR)) -#define EDD_MBR_SIG_NR (*(unsigned char *) (PARAM+EDD_MBR_SIG_NR_BUF)) -#define EDD_MBR_SIGNATURE ((unsigned int *) (PARAM+EDD_MBR_SIG_BUF)) -#define EDD_BUF ((struct edd_info *) (PARAM+EDDBUF)) - -#endif /* __ASSEMBLY__ */ - -#endif /* _i386_SETUP_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/smp.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/smp.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,93 +0,0 @@ -#ifndef __ASM_SMP_H -#define __ASM_SMP_H - -/* - * We need the APIC definitions automatically as part of 'smp.h' - */ -#ifndef __ASSEMBLY__ -#include <linux/config.h> -#include <linux/kernel.h> -#include <linux/threads.h> -#include <linux/cpumask.h> -#endif - -#ifdef CONFIG_X86_LOCAL_APIC -#ifndef __ASSEMBLY__ -#include <asm/fixmap.h> -#include <asm/bitops.h> -#include <asm/mpspec.h> -#ifdef CONFIG_X86_IO_APIC -#include <asm/io_apic.h> -#endif -#include <asm/apic.h> -#endif -#endif - -#define BAD_APICID 0xFFu -#ifdef CONFIG_SMP -#ifndef __ASSEMBLY__ - -/* - * Private routines/data - */ - -extern void smp_alloc_memory(void); -extern int pic_mode; -extern int smp_num_siblings; -extern cpumask_t cpu_sibling_map[]; -extern cpumask_t cpu_core_map[]; - -extern void smp_flush_tlb(void); -extern void smp_message_irq(int cpl, void *dev_id, struct pt_regs *regs); -extern void smp_invalidate_rcv(void); /* Process an NMI */ -extern void (*mtrr_hook) (void); -extern void zap_low_mappings (void); - -#define MAX_APICID 256 -extern u8 x86_cpu_to_apicid[]; - -/* - * This function is needed by all SMP systems. It must _always_ be valid - * from the initial startup. We map APIC_BASE very early in page_setup(), - * so this is correct in the x86 case. - */ -#define __smp_processor_id() (current_thread_info()->cpu) - -extern cpumask_t cpu_possible_map; -#define cpu_callin_map cpu_possible_map - -/* We don't mark CPUs online until __cpu_up(), so we need another measure */ -static inline int num_booting_cpus(void) -{ - return cpus_weight(cpu_possible_map); -} - -#ifdef CONFIG_X86_LOCAL_APIC - -#ifdef APIC_DEFINITION -extern int hard_smp_processor_id(void); -#else -#include <mach_apicdef.h> -static inline int hard_smp_processor_id(void) -{ - /* we don't want to mark this access volatile - bad code generation */ - return GET_APIC_ID(*(unsigned long *)(APIC_BASE+APIC_ID)); -} -#endif - -static __inline int logical_smp_processor_id(void) -{ - /* we don't want to mark this access volatile - bad code generation */ - return GET_APIC_LOGICAL_ID(*(unsigned long *)(APIC_BASE+APIC_LDR)); -} - -#endif - -extern int __cpu_disable(void); -extern void __cpu_die(unsigned int cpu); -#endif /* !__ASSEMBLY__ */ - -#define NO_PROC_ID 0xFF /* No processor magic marker */ - -#endif -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/spinlock.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/spinlock.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,277 +0,0 @@ -#ifndef __ASM_SPINLOCK_H -#define __ASM_SPINLOCK_H - -#include <asm/atomic.h> -#include <asm/rwlock.h> -#include <asm/page.h> -#include <linux/config.h> -#include <linux/compiler.h> -#include <asm/smp_alt.h> - -asmlinkage int printk(const char * fmt, ...) - __attribute__ ((format (printf, 1, 2))); - -/* - * Your basic SMP spinlocks, allowing only a single CPU anywhere - */ - -typedef struct { - volatile unsigned int slock; -#ifdef CONFIG_DEBUG_SPINLOCK - unsigned magic; -#endif -#ifdef CONFIG_PREEMPT - unsigned int break_lock; -#endif -} spinlock_t; - -#define SPINLOCK_MAGIC 0xdead4ead - -#ifdef CONFIG_DEBUG_SPINLOCK -#define SPINLOCK_MAGIC_INIT , SPINLOCK_MAGIC -#else -#define SPINLOCK_MAGIC_INIT /* */ -#endif - -#define SPIN_LOCK_UNLOCKED (spinlock_t) { 1 SPINLOCK_MAGIC_INIT } - -#define spin_lock_init(x) do { *(x) = SPIN_LOCK_UNLOCKED; } while(0) - -/* - * Simple spin lock operations. There are two variants, one clears IRQ's - * on the local processor, one does not. - * - * We make no fairness assumptions. They have a cost. - */ - -#define spin_is_locked(x) (*(volatile signed char *)(&(x)->slock) <= 0) -#define spin_unlock_wait(x) do { barrier(); } while(spin_is_locked(x)) - -#define spin_lock_string \ - "1:\n" \ - LOCK \ - "decb %0\n\t" \ - "jns 3f\n" \ - "2:\t" \ - "rep;nop\n\t" \ - "cmpb $0,%0\n\t" \ - "jle 2b\n\t" \ - "jmp 1b\n" \ - "3:\n\t" - -#define spin_lock_string_flags \ - "1:\n" \ - LOCK \ - "decb %0\n\t" \ - "jns 4f\n\t" \ - "2:\t" \ - "testl $0x200, %1\n\t" \ - "jz 3f\n\t" \ - "#sti\n\t" \ - "3:\t" \ - "rep;nop\n\t" \ - "cmpb $0, %0\n\t" \ - "jle 3b\n\t" \ - "#cli\n\t" \ - "jmp 1b\n" \ - "4:\n\t" - -/* - * This works. Despite all the confusion. - * (except on PPro SMP or if we are using OOSTORE) - * (PPro errata 66, 92) - */ - -#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE) - -#define spin_unlock_string \ - "movb $1,%0" \ - :"=m" (lock->slock) : : "memory" - - -static inline void _raw_spin_unlock(spinlock_t *lock) -{ -#ifdef CONFIG_DEBUG_SPINLOCK - BUG_ON(lock->magic != SPINLOCK_MAGIC); - BUG_ON(!spin_is_locked(lock)); -#endif - __asm__ __volatile__( - spin_unlock_string - ); -} - -#else - -#define spin_unlock_string \ - "xchgb %b0, %1" \ - :"=q" (oldval), "=m" (lock->slock) \ - :"0" (oldval) : "memory" - -static inline void _raw_spin_unlock(spinlock_t *lock) -{ - char oldval = 1; -#ifdef CONFIG_DEBUG_SPINLOCK - BUG_ON(lock->magic != SPINLOCK_MAGIC); - BUG_ON(!spin_is_locked(lock)); -#endif - __asm__ __volatile__( - spin_unlock_string - ); -} - -#endif - -static inline int _raw_spin_trylock(spinlock_t *lock) -{ - char oldval; -#ifdef CONFIG_SMP_ALTERNATIVES - __asm__ __volatile__( - "1:movb %1,%b0\n" - "movb $0,%1\n" - "2:" - ".section __smp_alternatives,\"a\"\n" - ".long 1b\n" - ".long 3f\n" - ".previous\n" - ".section __smp_replacements,\"a\"\n" - "3: .byte 2b - 1b\n" - ".byte 5f-4f\n" - ".byte 0\n" - ".byte 6f-5f\n" - ".byte -1\n" - "4: xchgb %b0,%1\n" - "5: movb %1,%b0\n" - "movb $0,%1\n" - "6:\n" - ".previous\n" - :"=q" (oldval), "=m" (lock->slock) - :"0" (0) : "memory"); -#else - __asm__ __volatile__( - "xchgb %b0,%1\n" - :"=q" (oldval), "=m" (lock->slock) - :"0" (0) : "memory"); -#endif - return oldval > 0; -} - -static inline void _raw_spin_lock(spinlock_t *lock) -{ -#ifdef CONFIG_DEBUG_SPINLOCK - if (unlikely(lock->magic != SPINLOCK_MAGIC)) { - printk("eip: %p\n", __builtin_return_address(0)); - BUG(); - } -#endif - __asm__ __volatile__( - spin_lock_string - :"=m" (lock->slock) : : "memory"); -} - -static inline void _raw_spin_lock_flags (spinlock_t *lock, unsigned long flags) -{ -#ifdef CONFIG_DEBUG_SPINLOCK - if (unlikely(lock->magic != SPINLOCK_MAGIC)) { - printk("eip: %p\n", __builtin_return_address(0)); - BUG(); - } -#endif - __asm__ __volatile__( - spin_lock_string_flags - :"=m" (lock->slock) : "r" (flags) : "memory"); -} - -/* - * Read-write spinlocks, allowing multiple readers - * but only one writer. - * - * NOTE! it is quite common to have readers in interrupts - * but no interrupt writers. For those circumstances we - * can "mix" irq-safe locks - any writer needs to get a - * irq-safe write-lock, but readers can get non-irqsafe - * read-locks. - */ -typedef struct { - volatile unsigned int lock; -#ifdef CONFIG_DEBUG_SPINLOCK - unsigned magic; -#endif -#ifdef CONFIG_PREEMPT - unsigned int break_lock; -#endif -} rwlock_t; - -#define RWLOCK_MAGIC 0xdeaf1eed - -#ifdef CONFIG_DEBUG_SPINLOCK -#define RWLOCK_MAGIC_INIT , RWLOCK_MAGIC -#else -#define RWLOCK_MAGIC_INIT /* */ -#endif - -#define RW_LOCK_UNLOCKED (rwlock_t) { RW_LOCK_BIAS RWLOCK_MAGIC_INIT } - -#define rwlock_init(x) do { *(x) = RW_LOCK_UNLOCKED; } while(0) - -/** - * read_can_lock - would read_trylock() succeed? - * @lock: the rwlock in question. - */ -#define read_can_lock(x) ((int)(x)->lock > 0) - -/** - * write_can_lock - would write_trylock() succeed? - * @lock: the rwlock in question. - */ -#define write_can_lock(x) ((x)->lock == RW_LOCK_BIAS) - -/* - * On x86, we implement read-write locks as a 32-bit counter - * with the high bit (sign) being the "contended" bit. - * - * The inline assembly is non-obvious. Think about it. - * - * Changed to use the same technique as rw semaphores. See - * semaphore.h for details. -ben - */ -/* the spinlock helpers are in arch/i386/kernel/semaphore.c */ - -static inline void _raw_read_lock(rwlock_t *rw) -{ -#ifdef CONFIG_DEBUG_SPINLOCK - BUG_ON(rw->magic != RWLOCK_MAGIC); -#endif - __build_read_lock(rw, "__read_lock_failed"); -} - -static inline void _raw_write_lock(rwlock_t *rw) -{ -#ifdef CONFIG_DEBUG_SPINLOCK - BUG_ON(rw->magic != RWLOCK_MAGIC); -#endif - __build_write_lock(rw, "__write_lock_failed"); -} - -#define _raw_read_unlock(rw) asm volatile(LOCK "incl %0" :"=m" ((rw)->lock) : : "memory") -#define _raw_write_unlock(rw) asm volatile(LOCK "addl $" RW_LOCK_BIAS_STR ",%0":"=m" ((rw)->lock) : : "memory") - -static inline int _raw_read_trylock(rwlock_t *lock) -{ - atomic_t *count = (atomic_t *)lock; - atomic_dec(count); - if (atomic_read(count) >= 0) - return 1; - atomic_inc(count); - return 0; -} - -static inline int _raw_write_trylock(rwlock_t *lock) -{ - atomic_t *count = (atomic_t *)lock; - if (atomic_sub_and_test(RW_LOCK_BIAS, count)) - return 1; - atomic_add(RW_LOCK_BIAS, count); - return 0; -} - -#endif /* __ASM_SPINLOCK_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/swiotlb.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/swiotlb.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,42 +0,0 @@ -#ifndef _ASM_SWIOTLB_H -#define _ASM_SWIOTLB_H 1 - -#include <linux/config.h> - -/* SWIOTLB interface */ - -extern dma_addr_t swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, - int dir); -extern void swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, - size_t size, int dir); -extern void swiotlb_sync_single_for_cpu(struct device *hwdev, - dma_addr_t dev_addr, - size_t size, int dir); -extern void swiotlb_sync_single_for_device(struct device *hwdev, - dma_addr_t dev_addr, - size_t size, int dir); -extern void swiotlb_sync_sg_for_cpu(struct device *hwdev, - struct scatterlist *sg, int nelems, - int dir); -extern void swiotlb_sync_sg_for_device(struct device *hwdev, - struct scatterlist *sg, int nelems, - int dir); -extern int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, - int nents, int direction); -extern void swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, - int nents, int direction); -extern int swiotlb_dma_mapping_error(dma_addr_t dma_addr); -extern dma_addr_t swiotlb_map_page(struct device *hwdev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction direction); -extern void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dma_address, - size_t size, enum dma_data_direction direction); -extern int swiotlb_dma_supported(struct device *hwdev, u64 mask); - -#ifdef CONFIG_SWIOTLB -extern int swiotlb; -#else -#define swiotlb 0 -#endif - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/synch_bitops.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/synch_bitops.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,140 +0,0 @@ -#ifndef __XEN_SYNCH_BITOPS_H__ -#define __XEN_SYNCH_BITOPS_H__ - -/* - * Copyright 1992, Linus Torvalds. - * Heavily modified to provide guaranteed strong synchronisation - * when communicating with Xen or other guest OSes running on other CPUs. - */ - -#include <linux/config.h> - -#define ADDR (*(volatile long *) addr) - -static __inline__ void synch_set_bit(int nr, volatile void * addr) -{ - __asm__ __volatile__ ( - "lock btsl %1,%0" - : "=m" (ADDR) : "Ir" (nr) : "memory" ); -} - -static __inline__ void synch_clear_bit(int nr, volatile void * addr) -{ - __asm__ __volatile__ ( - "lock btrl %1,%0" - : "=m" (ADDR) : "Ir" (nr) : "memory" ); -} - -static __inline__ void synch_change_bit(int nr, volatile void * addr) -{ - __asm__ __volatile__ ( - "lock btcl %1,%0" - : "=m" (ADDR) : "Ir" (nr) : "memory" ); -} - -static __inline__ int synch_test_and_set_bit(int nr, volatile void * addr) -{ - int oldbit; - __asm__ __volatile__ ( - "lock btsl %2,%1\n\tsbbl %0,%0" - : "=r" (oldbit), "=m" (ADDR) : "Ir" (nr) : "memory"); - return oldbit; -} - -static __inline__ int synch_test_and_clear_bit(int nr, volatile void * addr) -{ - int oldbit; - __asm__ __volatile__ ( - "lock btrl %2,%1\n\tsbbl %0,%0" - : "=r" (oldbit), "=m" (ADDR) : "Ir" (nr) : "memory"); - return oldbit; -} - -static __inline__ int synch_test_and_change_bit(int nr, volatile void * addr) -{ - int oldbit; - - __asm__ __volatile__ ( - "lock btcl %2,%1\n\tsbbl %0,%0" - : "=r" (oldbit), "=m" (ADDR) : "Ir" (nr) : "memory"); - return oldbit; -} - -struct __synch_xchg_dummy { unsigned long a[100]; }; -#define __synch_xg(x) ((struct __synch_xchg_dummy *)(x)) - -#define synch_cmpxchg(ptr, old, new) \ -((__typeof__(*(ptr)))__synch_cmpxchg((ptr),\ - (unsigned long)(old), \ - (unsigned long)(new), \ - sizeof(*(ptr)))) - -static inline unsigned long __synch_cmpxchg(volatile void *ptr, - unsigned long old, - unsigned long new, int size) -{ - unsigned long prev; - switch (size) { - case 1: - __asm__ __volatile__("lock; cmpxchgb %b1,%2" - : "=a"(prev) - : "q"(new), "m"(*__synch_xg(ptr)), - "0"(old) - : "memory"); - return prev; - case 2: - __asm__ __volatile__("lock; cmpxchgw %w1,%2" - : "=a"(prev) - : "q"(new), "m"(*__synch_xg(ptr)), - "0"(old) - : "memory"); - return prev; -#ifdef CONFIG_X86_64 - case 4: - __asm__ __volatile__("lock; cmpxchgl %k1,%2" - : "=a"(prev) - : "q"(new), "m"(*__synch_xg(ptr)), - "0"(old) - : "memory"); - return prev; - case 8: - __asm__ __volatile__("lock; cmpxchgq %1,%2" - : "=a"(prev) - : "q"(new), "m"(*__synch_xg(ptr)), - "0"(old) - : "memory"); - return prev; -#else - case 4: - __asm__ __volatile__("lock; cmpxchgl %1,%2" - : "=a"(prev) - : "q"(new), "m"(*__synch_xg(ptr)), - "0"(old) - : "memory"); - return prev; -#endif - } - return old; -} - -static __inline__ int synch_const_test_bit(int nr, const volatile void * addr) -{ - return ((1UL << (nr & 31)) & - (((const volatile unsigned int *) addr)[nr >> 5])) != 0; -} - -static __inline__ int synch_var_test_bit(int nr, volatile void * addr) -{ - int oldbit; - __asm__ __volatile__ ( - "btl %2,%1\n\tsbbl %0,%0" - : "=r" (oldbit) : "m" (ADDR), "Ir" (nr) ); - return oldbit; -} - -#define synch_test_bit(nr,addr) \ -(__builtin_constant_p(nr) ? \ - synch_const_test_bit((nr),(addr)) : \ - synch_var_test_bit((nr),(addr))) - -#endif /* __XEN_SYNCH_BITOPS_H__ */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/system.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/system.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,588 +0,0 @@ -#ifndef __ASM_SYSTEM_H -#define __ASM_SYSTEM_H - -#include <linux/config.h> -#include <linux/kernel.h> -#include <linux/bitops.h> -#include <asm/synch_bitops.h> -#include <asm/segment.h> -#include <asm/cpufeature.h> -#include <asm/hypervisor.h> -#include <asm/smp_alt.h> - -#ifdef __KERNEL__ - -struct task_struct; /* one of the stranger aspects of C forward declarations.. */ -extern struct task_struct * FASTCALL(__switch_to(struct task_struct *prev, struct task_struct *next)); - -#define switch_to(prev,next,last) do { \ - unsigned long esi,edi; \ - asm volatile("pushfl\n\t" \ - "pushl %%ebp\n\t" \ - "movl %%esp,%0\n\t" /* save ESP */ \ - "movl %5,%%esp\n\t" /* restore ESP */ \ - "movl $1f,%1\n\t" /* save EIP */ \ - "pushl %6\n\t" /* restore EIP */ \ - "jmp __switch_to\n" \ - "1:\t" \ - "popl %%ebp\n\t" \ - "popfl" \ - :"=m" (prev->thread.esp),"=m" (prev->thread.eip), \ - "=a" (last),"=S" (esi),"=D" (edi) \ - :"m" (next->thread.esp),"m" (next->thread.eip), \ - "2" (prev), "d" (next)); \ -} while (0) - -#define _set_base(addr,base) do { unsigned long __pr; \ -__asm__ __volatile__ ("movw %%dx,%1\n\t" \ - "rorl $16,%%edx\n\t" \ - "movb %%dl,%2\n\t" \ - "movb %%dh,%3" \ - :"=&d" (__pr) \ - :"m" (*((addr)+2)), \ - "m" (*((addr)+4)), \ - "m" (*((addr)+7)), \ - "0" (base) \ - ); } while(0) - -#define _set_limit(addr,limit) do { unsigned long __lr; \ -__asm__ __volatile__ ("movw %%dx,%1\n\t" \ - "rorl $16,%%edx\n\t" \ - "movb %2,%%dh\n\t" \ - "andb $0xf0,%%dh\n\t" \ - "orb %%dh,%%dl\n\t" \ - "movb %%dl,%2" \ - :"=&d" (__lr) \ - :"m" (*(addr)), \ - "m" (*((addr)+6)), \ - "0" (limit) \ - ); } while(0) - -#define set_base(ldt,base) _set_base( ((char *)&(ldt)) , (base) ) -#define set_limit(ldt,limit) _set_limit( ((char *)&(ldt)) , ((limit)-1)>>12 ) - -static inline unsigned long _get_base(char * addr) -{ - unsigned long __base; - __asm__("movb %3,%%dh\n\t" - "movb %2,%%dl\n\t" - "shll $16,%%edx\n\t" - "movw %1,%%dx" - :"=&d" (__base) - :"m" (*((addr)+2)), - "m" (*((addr)+4)), - "m" (*((addr)+7))); - return __base; -} - -#define get_base(ldt) _get_base( ((char *)&(ldt)) ) - -/* - * Load a segment. Fall back on loading the zero - * segment if something goes wrong.. - */ -#define loadsegment(seg,value) \ - asm volatile("\n" \ - "1:\t" \ - "mov %0,%%" #seg "\n" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3:\t" \ - "pushl $0\n\t" \ - "popl %%" #seg "\n\t" \ - "jmp 2b\n" \ - ".previous\n" \ - ".section __ex_table,\"a\"\n\t" \ - ".align 4\n\t" \ - ".long 1b,3b\n" \ - ".previous" \ - : :"m" (value)) - -/* - * Save a segment register away - */ -#define savesegment(seg, value) \ - asm volatile("mov %%" #seg ",%0":"=m" (value)) - -/* - * Clear and set 'TS' bit respectively - */ -#define clts() (HYPERVISOR_fpu_taskswitch(0)) -#define read_cr0() ({ \ - unsigned int __dummy; \ - __asm__( \ - "movl %%cr0,%0\n\t" \ - :"=r" (__dummy)); \ - __dummy; \ -}) -#define write_cr0(x) \ - __asm__("movl %0,%%cr0": :"r" (x)); - -#define read_cr4() ({ \ - unsigned int __dummy; \ - __asm__( \ - "movl %%cr4,%0\n\t" \ - :"=r" (__dummy)); \ - __dummy; \ -}) -#define write_cr4(x) \ - __asm__("movl %0,%%cr4": :"r" (x)); -#define stts() (HYPERVISOR_fpu_taskswitch(1)) - -#endif /* __KERNEL__ */ - -#define wbinvd() \ - __asm__ __volatile__ ("wbinvd": : :"memory"); - -static inline unsigned long get_limit(unsigned long segment) -{ - unsigned long __limit; - __asm__("lsll %1,%0" - :"=r" (__limit):"r" (segment)); - return __limit+1; -} - -#define nop() __asm__ __volatile__ ("nop") - -#define xchg(ptr,v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v),(ptr),sizeof(*(ptr)))) - -#define tas(ptr) (xchg((ptr),1)) - -struct __xchg_dummy { unsigned long a[100]; }; -#define __xg(x) ((struct __xchg_dummy *)(x)) - - -/* - * The semantics of XCHGCMP8B are a bit strange, this is why - * there is a loop and the loading of %%eax and %%edx has to - * be inside. This inlines well in most cases, the cached - * cost is around ~38 cycles. (in the future we might want - * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that - * might have an implicit FPU-save as a cost, so it's not - * clear which path to go.) - * - * cmpxchg8b must be used with the lock prefix here to allow - * the instruction to be executed atomically, see page 3-102 - * of the instruction set reference 24319102.pdf. We need - * the reader side to see the coherent 64bit value. - */ -static inline void __set_64bit (unsigned long long * ptr, - unsigned int low, unsigned int high) -{ - __asm__ __volatile__ ( - "\n1:\t" - "movl (%0), %%eax\n\t" - "movl 4(%0), %%edx\n\t" - "lock cmpxchg8b (%0)\n\t" - "jnz 1b" - : /* no outputs */ - : "D"(ptr), - "b"(low), - "c"(high) - : "ax","dx","memory"); -} - -static inline void __set_64bit_constant (unsigned long long *ptr, - unsigned long long value) -{ - __set_64bit(ptr,(unsigned int)(value), (unsigned int)((value)>>32ULL)); -} -#define ll_low(x) *(((unsigned int*)&(x))+0) -#define ll_high(x) *(((unsigned int*)&(x))+1) - -static inline void __set_64bit_var (unsigned long long *ptr, - unsigned long long value) -{ - __set_64bit(ptr,ll_low(value), ll_high(value)); -} - -#define set_64bit(ptr,value) \ -(__builtin_constant_p(value) ? \ - __set_64bit_constant(ptr, value) : \ - __set_64bit_var(ptr, value) ) - -#define _set_64bit(ptr,value) \ -(__builtin_constant_p(value) ? \ - __set_64bit(ptr, (unsigned int)(value), (unsigned int)((value)>>32ULL) ) : \ - __set_64bit(ptr, ll_low(value), ll_high(value)) ) - -/* - * Note: no "lock" prefix even on SMP: xchg always implies lock anyway - * Note 2: xchg has side effect, so that attribute volatile is necessary, - * but generally the primitive is invalid, *ptr is output argument. --ANK - */ -static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size) -{ - switch (size) { - case 1: - __asm__ __volatile__("xchgb %b0,%1" - :"=q" (x) - :"m" (*__xg(ptr)), "0" (x) - :"memory"); - break; - case 2: - __asm__ __volatile__("xchgw %w0,%1" - :"=r" (x) - :"m" (*__xg(ptr)), "0" (x) - :"memory"); - break; - case 4: - __asm__ __volatile__("xchgl %0,%1" - :"=r" (x) - :"m" (*__xg(ptr)), "0" (x) - :"memory"); - break; - } - return x; -} - -/* - * Atomic compare and exchange. Compare OLD with MEM, if identical, - * store NEW in MEM. Return the initial value in MEM. Success is - * indicated by comparing RETURN with OLD. - */ - -#ifdef CONFIG_X86_CMPXCHG -#define __HAVE_ARCH_CMPXCHG 1 -#endif - -static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, - unsigned long new, int size) -{ - unsigned long prev; - switch (size) { - case 1: - __asm__ __volatile__(LOCK "cmpxchgb %b1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 2: - __asm__ __volatile__(LOCK "cmpxchgw %w1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 4: - __asm__ __volatile__(LOCK "cmpxchgl %1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - } - return old; -} - -#define cmpxchg(ptr,o,n)\ - ((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\ - (unsigned long)(n),sizeof(*(ptr)))) - -#ifdef __KERNEL__ -struct alt_instr { - __u8 *instr; /* original instruction */ - __u8 *replacement; - __u8 cpuid; /* cpuid bit set for replacement */ - __u8 instrlen; /* length of original instruction */ - __u8 replacementlen; /* length of new instruction, <= instrlen */ - __u8 pad; -}; -#endif - -/* - * Alternative instructions for different CPU types or capabilities. - * - * This allows to use optimized instructions even on generic binary - * kernels. - * - * length of oldinstr must be longer or equal the length of newinstr - * It can be padded with nops as needed. - * - * For non barrier like inlines please define new variants - * without volatile and memory clobber. - */ -#define alternative(oldinstr, newinstr, feature) \ - asm volatile ("661:\n\t" oldinstr "\n662:\n" \ - ".section .altinstructions,\"a\"\n" \ - " .align 4\n" \ - " .long 661b\n" /* label */ \ - " .long 663f\n" /* new instruction */ \ - " .byte %c0\n" /* feature bit */ \ - " .byte 662b-661b\n" /* sourcelen */ \ - " .byte 664f-663f\n" /* replacementlen */ \ - ".previous\n" \ - ".section .altinstr_replacement,\"ax\"\n" \ - "663:\n\t" newinstr "\n664:\n" /* replacement */ \ - ".previous" :: "i" (feature) : "memory") - -/* - * Alternative inline assembly with input. - * - * Pecularities: - * No memory clobber here. - * Argument numbers start with 1. - * Best is to use constraints that are fixed size (like (%1) ... "r") - * If you use variable sized constraints like "m" or "g" in the - * replacement maake sure to pad to the worst case length. - */ -#define alternative_input(oldinstr, newinstr, feature, input...) \ - asm volatile ("661:\n\t" oldinstr "\n662:\n" \ - ".section .altinstructions,\"a\"\n" \ - " .align 4\n" \ - " .long 661b\n" /* label */ \ - " .long 663f\n" /* new instruction */ \ - " .byte %c0\n" /* feature bit */ \ - " .byte 662b-661b\n" /* sourcelen */ \ - " .byte 664f-663f\n" /* replacementlen */ \ - ".previous\n" \ - ".section .altinstr_replacement,\"ax\"\n" \ - "663:\n\t" newinstr "\n664:\n" /* replacement */ \ - ".previous" :: "i" (feature), ##input) - -/* - * Force strict CPU ordering. - * And yes, this is required on UP too when we're talking - * to devices. - * - * For now, "wmb()" doesn't actually do anything, as all - * Intel CPU's follow what Intel calls a *Processor Order*, - * in which all writes are seen in the program order even - * outside the CPU. - * - * I expect future Intel CPU's to have a weaker ordering, - * but I'd also expect them to finally get their act together - * and add some real memory barriers if so. - * - * Some non intel clones support out of order store. wmb() ceases to be a - * nop for these. - */ - - -/* - * Actually only lfence would be needed for mb() because all stores done - * by the kernel should be already ordered. But keep a full barrier for now. - */ - -#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2) -#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2) - -/** - * read_barrier_depends - Flush all pending reads that subsequents reads - * depend on. - * - * No data-dependent reads from memory-like regions are ever reordered - * over this barrier. All reads preceding this primitive are guaranteed - * to access memory (but not necessarily other CPUs' caches) before any - * reads following this primitive that depend on the data return by - * any of the preceding reads. This primitive is much lighter weight than - * rmb() on most CPUs, and is never heavier weight than is - * rmb(). - * - * These ordering constraints are respected by both the local CPU - * and the compiler. - * - * Ordering is not guaranteed by anything other than these primitives, - * not even by data dependencies. See the documentation for - * memory_barrier() for examples and URLs to more information. - * - * For example, the following code would force ordering (the initial - * value of "a" is zero, "b" is one, and "p" is "&a"): - * - * <programlisting> - * CPU 0 CPU 1 - * - * b = 2; - * memory_barrier(); - * p = &b; q = p; - * read_barrier_depends(); - * d = *q; - * </programlisting> - * - * because the read of "*q" depends on the read of "p" and these - * two reads are separated by a read_barrier_depends(). However, - * the following code, with the same initial values for "a" and "b": - * - * <programlisting> - * CPU 0 CPU 1 - * - * a = 2; - * memory_barrier(); - * b = 3; y = b; - * read_barrier_depends(); - * x = a; - * </programlisting> - * - * does not enforce ordering, since there is no data dependency between - * the read of "a" and the read of "b". Therefore, on some CPUs, such - * as Alpha, "y" could be set to 3 and "x" to 0. Use rmb() - * in cases like thiswhere there are no data dependencies. - **/ - -#define read_barrier_depends() do { } while(0) - -#ifdef CONFIG_X86_OOSTORE -/* Actually there are no OOO store capable CPUs for now that do SSE, - but make it already an possibility. */ -#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM) -#else -#define wmb() __asm__ __volatile__ ("": : :"memory") -#endif - -#ifdef CONFIG_SMP -#define smp_wmb() wmb() -#if defined(CONFIG_SMP_ALTERNATIVES) && !defined(MODULE) -#define smp_alt_mb(instr) \ -__asm__ __volatile__("6667:\nnop\nnop\nnop\nnop\nnop\nnop\n6668:\n" \ - ".section __smp_alternatives,\"a\"\n" \ - ".long 6667b\n" \ - ".long 6673f\n" \ - ".previous\n" \ - ".section __smp_replacements,\"a\"\n" \ - "6673:.byte 6668b-6667b\n" \ - ".byte 6670f-6669f\n" \ - ".byte 6671f-6670f\n" \ - ".byte 0\n" \ - ".byte %c0\n" \ - "6669:lock;addl $0,0(%%esp)\n" \ - "6670:" instr "\n" \ - "6671:\n" \ - ".previous\n" \ - : \ - : "i" (X86_FEATURE_XMM2) \ - : "memory") -#define smp_rmb() smp_alt_mb("lfence") -#define smp_mb() smp_alt_mb("mfence") -#define set_mb(var, value) do { \ -unsigned long __set_mb_temp; \ -__asm__ __volatile__("6667:movl %1, %0\n6668:\n" \ - ".section __smp_alternatives,\"a\"\n" \ - ".long 6667b\n" \ - ".long 6673f\n" \ - ".previous\n" \ - ".section __smp_replacements,\"a\"\n" \ - "6673: .byte 6668b-6667b\n" \ - ".byte 6670f-6669f\n" \ - ".byte 0\n" \ - ".byte 6671f-6670f\n" \ - ".byte -1\n" \ - "6669: xchg %1, %0\n" \ - "6670:movl %1, %0\n" \ - "6671:\n" \ - ".previous\n" \ - : "=m" (var), "=r" (__set_mb_temp) \ - : "1" (value) \ - : "memory"); } while (0) -#else -#define smp_rmb() rmb() -#define smp_mb() mb() -#define set_mb(var, value) do { xchg(&var, value); } while (0) -#endif -#define smp_read_barrier_depends() read_barrier_depends() -#else -#define smp_mb() barrier() -#define smp_rmb() barrier() -#define smp_wmb() barrier() -#define smp_read_barrier_depends() do { } while(0) -#define set_mb(var, value) do { var = value; barrier(); } while (0) -#endif - -#define set_wmb(var, value) do { var = value; wmb(); } while (0) - -/* interrupt control.. */ - -/* - * The use of 'barrier' in the following reflects their use as local-lock - * operations. Reentrancy must be prevented (e.g., __cli()) /before/ following - * critical operations are executed. All critical operations must complete - * /before/ reentrancy is permitted (e.g., __sti()). Alpha architecture also - * includes these barriers, for example. - */ - -#define __cli() \ -do { \ - vcpu_info_t *_vcpu; \ - preempt_disable(); \ - _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ - _vcpu->evtchn_upcall_mask = 1; \ - preempt_enable_no_resched(); \ - barrier(); \ -} while (0) - -#define __sti() \ -do { \ - vcpu_info_t *_vcpu; \ - barrier(); \ - preempt_disable(); \ - _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ - _vcpu->evtchn_upcall_mask = 0; \ - barrier(); /* unmask then check (avoid races) */ \ - if ( unlikely(_vcpu->evtchn_upcall_pending) ) \ - force_evtchn_callback(); \ - preempt_enable(); \ -} while (0) - -#define __save_flags(x) \ -do { \ - vcpu_info_t *_vcpu; \ - preempt_disable(); \ - _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ - (x) = _vcpu->evtchn_upcall_mask; \ - preempt_enable(); \ -} while (0) - -#define __restore_flags(x) \ -do { \ - vcpu_info_t *_vcpu; \ - barrier(); \ - preempt_disable(); \ - _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ - if ((_vcpu->evtchn_upcall_mask = (x)) == 0) { \ - barrier(); /* unmask then check (avoid races) */ \ - if ( unlikely(_vcpu->evtchn_upcall_pending) ) \ - force_evtchn_callback(); \ - preempt_enable(); \ - } else \ - preempt_enable_no_resched(); \ -} while (0) - -#define safe_halt() ((void)0) - -#define __save_and_cli(x) \ -do { \ - vcpu_info_t *_vcpu; \ - preempt_disable(); \ - _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ - (x) = _vcpu->evtchn_upcall_mask; \ - _vcpu->evtchn_upcall_mask = 1; \ - preempt_enable_no_resched(); \ - barrier(); \ -} while (0) - -#define local_irq_save(x) __save_and_cli(x) -#define local_irq_restore(x) __restore_flags(x) -#define local_save_flags(x) __save_flags(x) -#define local_irq_disable() __cli() -#define local_irq_enable() __sti() - -/* Cannot use preempt_enable() here as we would recurse in preempt_sched(). */ -#define irqs_disabled() \ -({ int ___x; \ - vcpu_info_t *_vcpu; \ - preempt_disable(); \ - _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ - ___x = (_vcpu->evtchn_upcall_mask != 0); \ - preempt_enable_no_resched(); \ - ___x; }) - -/* - * disable hlt during certain critical i/o operations - */ -#define HAVE_DISABLE_HLT -void disable_hlt(void); -void enable_hlt(void); - -extern int es7000_plat; -void cpu_idle_wait(void); - -extern unsigned long arch_align_stack(unsigned long sp); - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/tlbflush.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/tlbflush.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,102 +0,0 @@ -#ifndef _I386_TLBFLUSH_H -#define _I386_TLBFLUSH_H - -#include <linux/config.h> -#include <linux/mm.h> -#include <asm/processor.h> - -#define __flush_tlb() xen_tlb_flush() -#define __flush_tlb_global() xen_tlb_flush() -#define __flush_tlb_all() xen_tlb_flush() - -extern unsigned long pgkern_mask; - -#define cpu_has_invlpg (boot_cpu_data.x86 > 3) - -#define __flush_tlb_single(addr) xen_invlpg(addr) - -#define __flush_tlb_one(addr) __flush_tlb_single(addr) - -/* - * TLB flushing: - * - * - flush_tlb() flushes the current mm struct TLBs - * - flush_tlb_all() flushes all processes TLBs - * - flush_tlb_mm(mm) flushes the specified mm context TLB's - * - flush_tlb_page(vma, vmaddr) flushes one page - * - flush_tlb_range(vma, start, end) flushes a range of pages - * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages - * - flush_tlb_pgtables(mm, start, end) flushes a range of page tables - * - * ..but the i386 has somewhat limited tlb flushing capabilities, - * and page-granular flushes are available only on i486 and up. - */ - -#ifndef CONFIG_SMP - -#define flush_tlb() __flush_tlb() -#define flush_tlb_all() __flush_tlb_all() -#define local_flush_tlb() __flush_tlb() - -static inline void flush_tlb_mm(struct mm_struct *mm) -{ - if (mm == current->active_mm) - __flush_tlb(); -} - -static inline void flush_tlb_page(struct vm_area_struct *vma, - unsigned long addr) -{ - if (vma->vm_mm == current->active_mm) - __flush_tlb_one(addr); -} - -static inline void flush_tlb_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) -{ - if (vma->vm_mm == current->active_mm) - __flush_tlb(); -} - -#else - -#include <asm/smp.h> - -#define local_flush_tlb() \ - __flush_tlb() - -extern void flush_tlb_all(void); -extern void flush_tlb_current_task(void); -extern void flush_tlb_mm(struct mm_struct *); -extern void flush_tlb_page(struct vm_area_struct *, unsigned long); - -#define flush_tlb() flush_tlb_current_task() - -static inline void flush_tlb_range(struct vm_area_struct * vma, unsigned long start, unsigned long end) -{ - flush_tlb_mm(vma->vm_mm); -} - -#define TLBSTATE_OK 1 -#define TLBSTATE_LAZY 2 - -struct tlb_state -{ - struct mm_struct *active_mm; - int state; - char __cacheline_padding[L1_CACHE_BYTES-8]; -}; -DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate); - - -#endif - -#define flush_tlb_kernel_range(start, end) flush_tlb_all() - -static inline void flush_tlb_pgtables(struct mm_struct *mm, - unsigned long start, unsigned long end) -{ - /* i386 does not keep any page table caches in TLB */ -} - -#endif /* _I386_TLBFLUSH_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-i386/vga.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-i386/vga.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,20 +0,0 @@ -/* - * Access to VGA videoram - * - * (c) 1998 Martin Mares <mj@xxxxxx> - */ - -#ifndef _LINUX_ASM_VGA_H_ -#define _LINUX_ASM_VGA_H_ - -/* - * On the PC, we can just recalculate addresses and then - * access the videoram directly without any black magic. - */ - -#define VGA_MAP_MEM(x) (unsigned long)isa_bus_to_virt(x) - -#define vga_readb(x) (*(x)) -#define vga_writeb(x,y) (*(y) = (x)) - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-ia64/fixmap.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-ia64/fixmap.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,2 +0,0 @@ -#define clear_fixmap(x) do {} while (0) -#define set_fixmap(x,y) do {} while (0) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-ia64/hypercall.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-ia64/hypercall.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,500 +0,0 @@ -/****************************************************************************** - * hypercall.h - * - * Linux-specific hypervisor handling. - * - * Copyright (c) 2002-2004, K A Fraser - * - * This file may be distributed separately from the Linux kernel, or - * incorporated into other software packages, subject to the following license: - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this source file (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, copy, modify, - * merge, publish, distribute, sublicense, and/or sell copies of the Software, - * and to permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - */ - -#ifndef __HYPERCALL_H__ -#define __HYPERCALL_H__ - -#include <asm-xen/xen-public/xen.h> -#include <asm-xen/xen-public/sched.h> - -/* FIXME: temp place to hold these page related macros */ -#include <asm/page.h> -#define virt_to_machine(v) __pa(v) -#define machine_to_virt(m) __va(m) -//#define virt_to_mfn(v) (__pa(v) >> 14) -//#define mfn_to_virt(m) (__va(m << 14)) -#define virt_to_mfn(v) ((__pa(v)) >> PAGE_SHIFT) -#define mfn_to_virt(m) (__va((m) << PAGE_SHIFT)) - -/* - * Assembler stubs for hyper-calls. - */ - -#if 0 -static inline int -HYPERVISOR_set_trap_table( - trap_info_t *table) -{ -#if 0 - int ret; - unsigned long ignore; - - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ignore) - : "0" (__HYPERVISOR_set_trap_table), "1" (table) - : "memory" ); - - return ret; -#endif - return 1; -} - -static inline int -HYPERVISOR_mmu_update( - mmu_update_t *req, int count, int *success_count, domid_t domid) -{ -#if 0 - int ret; - unsigned long ign1, ign2, ign3, ign4; - - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3), "=S" (ign4) - : "0" (__HYPERVISOR_mmu_update), "1" (req), "2" (count), - "3" (success_count), "4" (domid) - : "memory" ); - - return ret; -#endif - return 1; -} - -static inline int -HYPERVISOR_mmuext_op( - struct mmuext_op *op, int count, int *success_count, domid_t domid) -{ -#if 0 - int ret; - unsigned long ign1, ign2, ign3, ign4; - - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3), "=S" (ign4) - : "0" (__HYPERVISOR_mmuext_op), "1" (op), "2" (count), - "3" (success_count), "4" (domid) - : "memory" ); - - return ret; -#endif - return 1; -} - -static inline int -HYPERVISOR_set_gdt( - unsigned long *frame_list, int entries) -{ -#if 0 - int ret; - unsigned long ign1, ign2; - - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ign1), "=c" (ign2) - : "0" (__HYPERVISOR_set_gdt), "1" (frame_list), "2" (entries) - : "memory" ); - - - return ret; -#endif - return 1; -} - -static inline int -HYPERVISOR_stack_switch( - unsigned long ss, unsigned long esp) -{ -#if 0 - int ret; - unsigned long ign1, ign2; - - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ign1), "=c" (ign2) - : "0" (__HYPERVISOR_stack_switch), "1" (ss), "2" (esp) - : "memory" ); - - return ret; -#endif - return 1; -} - -static inline int -HYPERVISOR_set_callbacks( - unsigned long event_selector, unsigned long event_address, - unsigned long failsafe_selector, unsigned long failsafe_address) -{ -#if 0 - int ret; - unsigned long ign1, ign2, ign3, ign4; - - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3), "=S" (ign4) - : "0" (__HYPERVISOR_set_callbacks), "1" (event_selector), - "2" (event_address), "3" (failsafe_selector), "4" (failsafe_address) - : "memory" ); - - return ret; -#endif - return 1; -} - -static inline int -HYPERVISOR_fpu_taskswitch( - int set) -{ -#if 0 - int ret; - unsigned long ign; - - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ign) - : "0" (__HYPERVISOR_fpu_taskswitch), "1" (set) - : "memory" ); - - return ret; -#endif - return 1; -} - -static inline int -HYPERVISOR_sched_op( - int cmd, unsigned long arg) -{ - return 1; -} - -static inline int -HYPERVISOR_suspend( - unsigned long srec) -{ - return 1; -} - -static inline long -HYPERVISOR_set_timer_op( - u64 timeout) -{ -#if 0 - int ret; - unsigned long timeout_hi = (unsigned long)(timeout>>32); - unsigned long timeout_lo = (unsigned long)timeout; - unsigned long ign1, ign2; - - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ign1), "=c" (ign2) - : "0" (__HYPERVISOR_set_timer_op), "b" (timeout_lo), "c" (timeout_hi) - : "memory"); - - return ret; -#endif - return 1; -} - -static inline int -HYPERVISOR_dom0_op( - dom0_op_t *dom0_op) -{ -#if 0 - int ret; - unsigned long ign1; - - dom0_op->interface_version = DOM0_INTERFACE_VERSION; - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ign1) - : "0" (__HYPERVISOR_dom0_op), "1" (dom0_op) - : "memory"); - - return ret; -#endif - return 1; -} - -static inline int -HYPERVISOR_set_debugreg( - int reg, unsigned long value) -{ -#if 0 - int ret; - unsigned long ign1, ign2; - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ign1), "=c" (ign2) - : "0" (__HYPERVISOR_set_debugreg), "1" (reg), "2" (value) - : "memory" ); - - return ret; -#endif - return 1; -} - -static inline unsigned long -HYPERVISOR_get_debugreg( - int reg) -{ -#if 0 - unsigned long ret; - unsigned long ign; - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ign) - : "0" (__HYPERVISOR_get_debugreg), "1" (reg) - : "memory" ); - - return ret; -#endif - return 1; -} - -static inline int -HYPERVISOR_update_descriptor( - unsigned long ma, unsigned long word1, unsigned long word2) -{ -#if 0 - int ret; - unsigned long ign1, ign2, ign3; - - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3) - : "0" (__HYPERVISOR_update_descriptor), "1" (ma), "2" (word1), - "3" (word2) - : "memory" ); - - return ret; -#endif - return 1; -} - -static inline int -HYPERVISOR_set_fast_trap( - int idx) -{ -#if 0 - int ret; - unsigned long ign; - - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ign) - : "0" (__HYPERVISOR_set_fast_trap), "1" (idx) - : "memory" ); - - return ret; -#endif - return 1; -} - -static inline int -HYPERVISOR_dom_mem_op( - unsigned int op, unsigned long *extent_list, - unsigned long nr_extents, unsigned int extent_order) -{ -#if 0 - int ret; - unsigned long ign1, ign2, ign3, ign4, ign5; - - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3), "=S" (ign4), - "=D" (ign5) - : "0" (__HYPERVISOR_dom_mem_op), "1" (op), "2" (extent_list), - "3" (nr_extents), "4" (extent_order), "5" (DOMID_SELF) - : "memory" ); - - return ret; -#endif - return 1; -} - -static inline int -HYPERVISOR_multicall( - void *call_list, int nr_calls) -{ -#if 0 - int ret; - unsigned long ign1, ign2; - - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ign1), "=c" (ign2) - : "0" (__HYPERVISOR_multicall), "1" (call_list), "2" (nr_calls) - : "memory" ); - - return ret; -#endif - return 1; -} -#endif - -static inline int -HYPERVISOR_update_va_mapping( - unsigned long va, pte_t new_val, unsigned long flags) -{ - /* no-op */ - return 1; -} - -static inline int -HYPERVISOR_memory_op( - unsigned int cmd, void *arg) -{ - int ret; - __asm__ __volatile__ ( ";; mov r14=%2 ; mov r15=%3 ; mov r2=%1 ; break 0x1000 ;; mov %0=r8 ;;" - : "=r" (ret) - : "i" (__HYPERVISOR_memory_op), "r"(cmd), "r"(arg) - : "r14","r15","r2","r8","memory" ); - return ret; -} - -static inline int -HYPERVISOR_event_channel_op( - void *op) -{ - int ret; - __asm__ __volatile__ ( ";; mov r14=%2 ; mov r2=%1 ; break 0x1000 ;; mov %0=r8 ;;" - : "=r" (ret) - : "i" (__HYPERVISOR_event_channel_op), "r"(op) - : "r14","r2","r8","memory" ); - return ret; -} - -#if 0 -static inline int -HYPERVISOR_xen_version( - int cmd) -{ -#if 0 - int ret; - unsigned long ignore; - - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ignore) - : "0" (__HYPERVISOR_xen_version), "1" (cmd) - : "memory" ); - - return ret; -#endif - return 1; -} -#endif - -static inline int -HYPERVISOR_console_io( - int cmd, int count, char *str) -{ - int ret; - __asm__ __volatile__ ( ";; mov r14=%2 ; mov r15=%3 ; mov r16=%4 ; mov r2=%1 ; break 0x1000 ;; mov %0=r8 ;;" - : "=r" (ret) - : "i" (__HYPERVISOR_console_io), "r"(cmd), "r"(count), "r"(str) - : "r14","r15","r16","r2","r8","memory" ); - return ret; -} - -#if 0 -static inline int -HYPERVISOR_physdev_op( - void *physdev_op) -{ -#if 0 - int ret; - unsigned long ign; - - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ign) - : "0" (__HYPERVISOR_physdev_op), "1" (physdev_op) - : "memory" ); - - return ret; -#endif - return 1; -} -#endif - -static inline int -HYPERVISOR_grant_table_op( - unsigned int cmd, void *uop, unsigned int count) -{ - int ret; - __asm__ __volatile__ ( ";; mov r14=%2 ; mov r15=%3 ; mov r16=%4 ; mov r2=%1 ; break 0x1000 ;; mov %0=r8 ;;" - : "=r" (ret) - : "i" (__HYPERVISOR_grant_table_op), "r"(cmd), "r"(uop), "r"(count) - : "r14","r15","r16","r2","r8","memory" ); - return ret; -} - -#if 0 -static inline int -HYPERVISOR_update_va_mapping_otherdomain( - unsigned long va, pte_t new_val, unsigned long flags, domid_t domid) -{ -#if 0 - int ret; - unsigned long ign1, ign2, ign3, ign4; - - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ign1), "=c" (ign2), "=d" (ign3), "=S" (ign4) - : "0" (__HYPERVISOR_update_va_mapping_otherdomain), - "1" (va), "2" ((new_val).pte_low), "3" (flags), "4" (domid) : - "memory" ); - - return ret; -#endif - return 1; -} - -static inline int -HYPERVISOR_vm_assist( - unsigned int cmd, unsigned int type) -{ -#if 0 - int ret; - unsigned long ign1, ign2; - - __asm__ __volatile__ ( - TRAP_INSTR - : "=a" (ret), "=b" (ign1), "=c" (ign2) - : "0" (__HYPERVISOR_vm_assist), "1" (cmd), "2" (type) - : "memory" ); - - return ret; -#endif - return 1; -} - -#endif - -#endif /* __HYPERCALL_H__ */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-ia64/hypervisor.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-ia64/hypervisor.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,70 +0,0 @@ -/****************************************************************************** - * hypervisor.h - * - * Linux-specific hypervisor handling. - * - * Copyright (c) 2002-2004, K A Fraser - * - * This file may be distributed separately from the Linux kernel, or - * incorporated into other software packages, subject to the following license: - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this source file (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, copy, modify, - * merge, publish, distribute, sublicense, and/or sell copies of the Software, - * and to permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - */ - -#ifndef __HYPERVISOR_H__ -#define __HYPERVISOR_H__ - -#include <linux/config.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/version.h> -#include <asm-xen/xen-public/xen.h> -#include <asm-xen/xen-public/dom0_ops.h> -#include <asm/ptrace.h> -#include <asm/page.h> - -extern shared_info_t *HYPERVISOR_shared_info; -extern start_info_t *xen_start_info; - -void force_evtchn_callback(void); - -#include <asm/hypercall.h> - -// for drivers/xen/privcmd/privcmd.c -#define direct_remap_pfn_range(a,b,c,d,e,f) remap_pfn_range(a,b,c,d,e) -#define pfn_to_mfn(x) (x) -#define mfn_to_pfn(x) (x) -#define machine_to_phys_mapping 0 - -// for drivers/xen/balloon/balloon.c -#ifdef CONFIG_XEN_SCRUB_PAGES -#define scrub_pages(_p,_n) memset((void *)(_p), 0, (_n) << PAGE_SHIFT) -#else -#define scrub_pages(_p,_n) ((void)0) -#endif -#define pte_mfn(_x) pte_pfn(_x) -#define INVALID_P2M_ENTRY (~0UL) -#define __pte_ma(_x) ((pte_t) {(_x)}) -#define phys_to_machine_mapping_valid(_x) (1) -#define kmap_flush_unused() do {} while (0) -#define set_phys_to_machine(_x,_y) do {} while (0) -#define xen_machphys_update(_x,_y) do {} while (0) -#define pfn_pte_ma(_x,_y) __pte_ma(0) - -#endif /* __HYPERVISOR_H__ */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-ia64/synch_bitops.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-ia64/synch_bitops.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,61 +0,0 @@ -#ifndef __XEN_SYNCH_BITOPS_H__ -#define __XEN_SYNCH_BITOPS_H__ - -/* - * Copyright 1992, Linus Torvalds. - * Heavily modified to provide guaranteed strong synchronisation - * when communicating with Xen or other guest OSes running on other CPUs. - */ - -#include <linux/config.h> - -#define ADDR (*(volatile long *) addr) - -static __inline__ void synch_set_bit(int nr, volatile void * addr) -{ - set_bit(nr, addr); -} - -static __inline__ void synch_clear_bit(int nr, volatile void * addr) -{ - clear_bit(nr, addr); -} - -static __inline__ void synch_change_bit(int nr, volatile void * addr) -{ - change_bit(nr, addr); -} - -static __inline__ int synch_test_and_set_bit(int nr, volatile void * addr) -{ - return test_and_set_bit(nr, addr); -} - -static __inline__ int synch_test_and_clear_bit(int nr, volatile void * addr) -{ - return test_and_clear_bit(nr, addr); -} - -static __inline__ int synch_test_and_change_bit(int nr, volatile void * addr) -{ - return test_and_change_bit(nr, addr); -} - -static __inline__ int synch_const_test_bit(int nr, const volatile void * addr) -{ - return test_bit(nr, addr); -} - -static __inline__ int synch_var_test_bit(int nr, volatile void * addr) -{ - return test_bit(nr, addr); -} - -#define synch_cmpxchg ia64_cmpxchg4_acq - -#define synch_test_bit(nr,addr) \ -(__builtin_constant_p(nr) ? \ - synch_const_test_bit((nr),(addr)) : \ - synch_var_test_bit((nr),(addr))) - -#endif /* __XEN_SYNCH_BITOPS_H__ */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/arch_hooks.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/arch_hooks.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,27 +0,0 @@ -#ifndef _ASM_ARCH_HOOKS_H -#define _ASM_ARCH_HOOKS_H - -#include <linux/interrupt.h> - -/* - * linux/include/asm/arch_hooks.h - * - * define the architecture specific hooks - */ - -/* these aren't arch hooks, they are generic routines - * that can be used by the hooks */ -extern void init_ISA_irqs(void); -extern void apic_intr_init(void); -extern void smp_intr_init(void); -extern irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs); - -/* these are the defined hooks */ -extern void intr_init_hook(void); -extern void pre_intr_init_hook(void); -extern void pre_setup_arch_hook(void); -extern void trap_init_hook(void); -extern void time_init_hook(void); -extern void mca_nmi_hook(void); - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/bootsetup.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/bootsetup.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,42 +0,0 @@ - -#ifndef _X86_64_BOOTSETUP_H -#define _X86_64_BOOTSETUP_H 1 - -#define BOOT_PARAM_SIZE 4096 -extern char x86_boot_params[BOOT_PARAM_SIZE]; - -/* - * This is set up by the setup-routine at boot-time - */ -#define PARAM ((unsigned char *)x86_boot_params) -#define SCREEN_INFO (*(struct screen_info *) (PARAM+0)) -#define EXT_MEM_K (*(unsigned short *) (PARAM+2)) -#define ALT_MEM_K (*(unsigned int *) (PARAM+0x1e0)) -#define E820_MAP_NR (*(char*) (PARAM+E820NR)) -#define E820_MAP ((struct e820entry *) (PARAM+E820MAP)) -#define APM_BIOS_INFO (*(struct apm_bios_info *) (PARAM+0x40)) -#define DRIVE_INFO (*(struct drive_info_struct *) (PARAM+0x80)) -#define SYS_DESC_TABLE (*(struct sys_desc_table_struct*)(PARAM+0xa0)) -#define MOUNT_ROOT_RDONLY (*(unsigned short *) (PARAM+0x1F2)) -#define RAMDISK_FLAGS (*(unsigned short *) (PARAM+0x1F8)) -#define SAVED_VIDEO_MODE (*(unsigned short *) (PARAM+0x1FA)) -#define ORIG_ROOT_DEV (*(unsigned short *) (PARAM+0x1FC)) -#define AUX_DEVICE_INFO (*(unsigned char *) (PARAM+0x1FF)) -#define LOADER_TYPE (*(unsigned char *) (PARAM+0x210)) -#define KERNEL_START (*(unsigned int *) (PARAM+0x214)) - -#define INITRD_START (__pa(xen_start_info->mod_start)) -#define INITRD_SIZE (xen_start_info->mod_len) -#define EDID_INFO (*(struct edid_info *) (PARAM+0x440)) - -#define EDD_NR (*(unsigned char *) (PARAM+EDDNR)) -#define EDD_MBR_SIG_NR (*(unsigned char *) (PARAM+EDD_MBR_SIG_NR_BUF)) -#define EDD_MBR_SIGNATURE ((unsigned int *) (PARAM+EDD_MBR_SIG_BUF)) -#define EDD_BUF ((struct edd_info *) (PARAM+EDDBUF)) -#define COMMAND_LINE saved_command_line - -#define RAMDISK_IMAGE_START_MASK 0x07FF -#define RAMDISK_PROMPT_FLAG 0x8000 -#define RAMDISK_LOAD_FLAG 0x4000 - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/desc.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/desc.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,240 +0,0 @@ -/* Written 2000 by Andi Kleen */ -#ifndef __ARCH_DESC_H -#define __ARCH_DESC_H - -#include <linux/threads.h> -#include <asm/ldt.h> - -#ifndef __ASSEMBLY__ - -#include <linux/string.h> -#include <asm/segment.h> -#include <asm/mmu.h> - -// 8 byte segment descriptor -struct desc_struct { - u16 limit0; - u16 base0; - unsigned base1 : 8, type : 4, s : 1, dpl : 2, p : 1; - unsigned limit : 4, avl : 1, l : 1, d : 1, g : 1, base2 : 8; -} __attribute__((packed)); - -struct n_desc_struct { - unsigned int a,b; -}; - -enum { - GATE_INTERRUPT = 0xE, - GATE_TRAP = 0xF, - GATE_CALL = 0xC, -}; - -// 16byte gate -struct gate_struct { - u16 offset_low; - u16 segment; - unsigned ist : 3, zero0 : 5, type : 5, dpl : 2, p : 1; - u16 offset_middle; - u32 offset_high; - u32 zero1; -} __attribute__((packed)); - -#define PTR_LOW(x) ((unsigned long)(x) & 0xFFFF) -#define PTR_MIDDLE(x) (((unsigned long)(x) >> 16) & 0xFFFF) -#define PTR_HIGH(x) ((unsigned long)(x) >> 32) - -enum { - DESC_TSS = 0x9, - DESC_LDT = 0x2, -}; - -// LDT or TSS descriptor in the GDT. 16 bytes. -struct ldttss_desc { - u16 limit0; - u16 base0; - unsigned base1 : 8, type : 5, dpl : 2, p : 1; - unsigned limit1 : 4, zero0 : 3, g : 1, base2 : 8; - u32 base3; - u32 zero1; -} __attribute__((packed)); - -struct desc_ptr { - unsigned short size; - unsigned long address; -} __attribute__((packed)) ; - -extern struct desc_ptr idt_descr, cpu_gdt_descr[NR_CPUS]; - -extern struct desc_struct cpu_gdt_table[NR_CPUS][GDT_ENTRIES]; - -#define get_cpu_gdt_table(_cpu) ((struct desc_struct *)(cpu_gdt_descr[(_cpu)].address)) - -#define load_TR_desc() asm volatile("ltr %w0"::"r" (GDT_ENTRY_TSS*8)) -#define load_LDT_desc() asm volatile("lldt %w0"::"r" (GDT_ENTRY_LDT*8)) - -static inline void clear_LDT(void) -{ - int cpu = get_cpu(); - - /* - * NB. We load the default_ldt for lcall7/27 handling on demand, as - * it slows down context switching. Noone uses it anyway. - */ - cpu = cpu; /* XXX avoid compiler warning */ - xen_set_ldt(0UL, 0); - put_cpu(); -} - -/* - * This is the ldt that every process will get unless we need - * something other than this. - */ -extern struct desc_struct default_ldt[]; -extern struct gate_struct idt_table[]; - -static inline void _set_gate(void *adr, unsigned type, unsigned long func, unsigned dpl, unsigned ist) -{ - struct gate_struct s; - s.offset_low = PTR_LOW(func); - s.segment = __KERNEL_CS; - s.ist = ist; - s.p = 1; - s.dpl = dpl; - s.zero0 = 0; - s.zero1 = 0; - s.type = type; - s.offset_middle = PTR_MIDDLE(func); - s.offset_high = PTR_HIGH(func); - /* does not need to be atomic because it is only done once at setup time */ - memcpy(adr, &s, 16); -} - -static inline void set_intr_gate(int nr, void *func) -{ - _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 0, 0); -} - -static inline void set_intr_gate_ist(int nr, void *func, unsigned ist) -{ - _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 0, ist); -} - -static inline void set_system_gate(int nr, void *func) -{ - _set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 3, 0); -} - -static inline void set_tssldt_descriptor(void *ptr, unsigned long tss, unsigned type, - unsigned size) -{ - struct ldttss_desc d; - memset(&d,0,sizeof(d)); - d.limit0 = size & 0xFFFF; - d.base0 = PTR_LOW(tss); - d.base1 = PTR_MIDDLE(tss) & 0xFF; - d.type = type; - d.p = 1; - d.limit1 = (size >> 16) & 0xF; - d.base2 = (PTR_MIDDLE(tss) >> 8) & 0xFF; - d.base3 = PTR_HIGH(tss); - memcpy(ptr, &d, 16); -} - -static inline void set_tss_desc(unsigned cpu, void *addr) -{ - set_tssldt_descriptor((struct ldttss_desc *)&get_cpu_gdt_table(cpu)[GDT_ENTRY_TSS], - (unsigned long)addr, - DESC_TSS, - sizeof(struct tss_struct) - 1); -} - -static inline void set_ldt_desc(unsigned cpu, void *addr, int size) -{ - set_tssldt_descriptor((struct ldttss_desc *)&get_cpu_gdt_table(cpu)[GDT_ENTRY_LDT], - (unsigned long)addr, - DESC_LDT, size * 8 - 1); -} - -static inline void set_seg_base(unsigned cpu, int entry, void *base) -{ - struct desc_struct *d = (struct desc_struct *)&get_cpu_gdt_table(cpu)[entry]; - u32 addr = (u32)(u64)base; - BUG_ON((u64)base >> 32); - d->base0 = addr & 0xffff; - d->base1 = (addr >> 16) & 0xff; - d->base2 = (addr >> 24) & 0xff; -} - -#define LDT_entry_a(info) \ - ((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff)) -/* Don't allow setting of the lm bit. It is useless anyways because - 64bit system calls require __USER_CS. */ -#define LDT_entry_b(info) \ - (((info)->base_addr & 0xff000000) | \ - (((info)->base_addr & 0x00ff0000) >> 16) | \ - ((info)->limit & 0xf0000) | \ - (((info)->read_exec_only ^ 1) << 9) | \ - ((info)->contents << 10) | \ - (((info)->seg_not_present ^ 1) << 15) | \ - ((info)->seg_32bit << 22) | \ - ((info)->limit_in_pages << 23) | \ - ((info)->useable << 20) | \ - /* ((info)->lm << 21) | */ \ - 0x7000) - -#define LDT_empty(info) (\ - (info)->base_addr == 0 && \ - (info)->limit == 0 && \ - (info)->contents == 0 && \ - (info)->read_exec_only == 1 && \ - (info)->seg_32bit == 0 && \ - (info)->limit_in_pages == 0 && \ - (info)->seg_not_present == 1 && \ - (info)->useable == 0 && \ - (info)->lm == 0) - -#if TLS_SIZE != 24 -# error update this code. -#endif - -static inline void load_TLS(struct thread_struct *t, unsigned int cpu) -{ -#if 0 - u64 *gdt = (u64 *)(cpu_gdt_table[cpu] + GDT_ENTRY_TLS_MIN); - gdt[0] = t->tls_array[0]; - gdt[1] = t->tls_array[1]; - gdt[2] = t->tls_array[2]; -#endif -#define C(i) \ - HYPERVISOR_update_descriptor(virt_to_machine(&get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN + i]), t->tls_array[i]) - - C(0); C(1); C(2); -#undef C -} - -/* - * load one particular LDT into the current CPU - */ -extern inline void load_LDT_nolock (mm_context_t *pc, int cpu) -{ - void *segments = pc->ldt; - int count = pc->size; - - if (likely(!count)) - segments = NULL; - - xen_set_ldt((unsigned long)segments, count); -} - -static inline void load_LDT(mm_context_t *pc) -{ - int cpu = get_cpu(); - load_LDT_nolock(pc, cpu); - put_cpu(); -} - -extern struct desc_ptr idt_descr; - -#endif /* !__ASSEMBLY__ */ - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/dma-mapping.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/dma-mapping.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,1 +0,0 @@ -#include <asm-i386/dma-mapping.h> diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/fixmap.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/fixmap.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,113 +0,0 @@ -/* - * fixmap.h: compile-time virtual memory allocation - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 1998 Ingo Molnar - */ - -#ifndef _ASM_FIXMAP_H -#define _ASM_FIXMAP_H - -#include <linux/config.h> -#include <linux/kernel.h> -#include <asm/apicdef.h> -#include <asm-xen/gnttab.h> -#include <asm/page.h> -#include <asm/vsyscall.h> -#include <asm/vsyscall32.h> -#include <asm/acpi.h> - -/* - * Here we define all the compile-time 'special' virtual - * addresses. The point is to have a constant address at - * compile time, but to set the physical address only - * in the boot process. - * - * these 'compile-time allocated' memory buffers are - * fixed-size 4k pages. (or larger if used with an increment - * highger than 1) use fixmap_set(idx,phys) to associate - * physical memory with fixmap indices. - * - * TLB entries of such buffers will not be flushed across - * task switches. - */ - -enum fixed_addresses { - VSYSCALL_LAST_PAGE, - VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1, - VSYSCALL_HPET, - FIX_HPET_BASE, -#ifdef CONFIG_X86_LOCAL_APIC - FIX_APIC_BASE, /* local (CPU) APIC) -- required for SMP or not */ -#endif -#ifdef CONFIG_X86_IO_APIC - FIX_IO_APIC_BASE_0, - FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS-1, -#endif -#ifdef CONFIG_ACPI_BOOT - FIX_ACPI_BEGIN, - FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1, -#endif - FIX_SHARED_INFO, - FIX_GNTTAB_BEGIN, - FIX_GNTTAB_END = FIX_GNTTAB_BEGIN + NR_GRANT_FRAMES - 1, -#ifdef CONFIG_XEN_PHYSDEV_ACCESS -#define NR_FIX_ISAMAPS 256 - FIX_ISAMAP_END, - FIX_ISAMAP_BEGIN = FIX_ISAMAP_END + NR_FIX_ISAMAPS - 1, -#endif - __end_of_fixed_addresses -}; - -extern void __set_fixmap (enum fixed_addresses idx, - unsigned long phys, pgprot_t flags); - -#define set_fixmap(idx, phys) \ - __set_fixmap(idx, phys, PAGE_KERNEL) -/* - * Some hardware wants to get fixmapped without caching. - */ -#define set_fixmap_nocache(idx, phys) \ - __set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE) - -#define clear_fixmap(idx) \ - __set_fixmap(idx, 0, __pgprot(0)) - -#define FIXADDR_TOP (VSYSCALL_END-PAGE_SIZE) -#define FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) -#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) - -/* Only covers 32bit vsyscalls currently. Need another set for 64bit. */ -#define FIXADDR_USER_START ((unsigned long)VSYSCALL32_VSYSCALL) -#define FIXADDR_USER_END (FIXADDR_USER_START + PAGE_SIZE) - -#define __fix_to_virt(x) (FIXADDR_TOP - ((x) << PAGE_SHIFT)) - -extern void __this_fixmap_does_not_exist(void); - -/* - * 'index to address' translation. If anyone tries to use the idx - * directly without translation, we catch the bug with a NULL-deference - * kernel oops. Illegal ranges of incoming indices are caught too. - */ -extern inline unsigned long fix_to_virt(const unsigned int idx) -{ - /* - * this branch gets completely eliminated after inlining, - * except when someone tries to use fixaddr indices in an - * illegal way. (such as mixing up address types or using - * out-of-range indices). - * - * If it doesn't get removed, the linker will complain - * loudly with a reasonably clear error message.. - */ - if (idx >= __end_of_fixed_addresses) - __this_fixmap_does_not_exist(); - - return __fix_to_virt(idx); -} - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/floppy.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/floppy.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,204 +0,0 @@ -/* - * Architecture specific parts of the Floppy driver - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 1995 - * - * Modifications for Xen are Copyright (c) 2004, Keir Fraser. - */ -#ifndef __ASM_XEN_X86_64_FLOPPY_H -#define __ASM_XEN_X86_64_FLOPPY_H - -#include <linux/vmalloc.h> - - -/* - * The DMA channel used by the floppy controller cannot access data at - * addresses >= 16MB - * - * Went back to the 1MB limit, as some people had problems with the floppy - * driver otherwise. It doesn't matter much for performance anyway, as most - * floppy accesses go through the track buffer. - */ -#define _CROSS_64KB(a,s,vdma) \ -(!(vdma) && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64)) - -#include <linux/vmalloc.h> - -/* XEN: Hit DMA paths on the head. This trick from asm-m68k/floppy.h. */ -#include <asm/dma.h> -#undef MAX_DMA_ADDRESS -#define MAX_DMA_ADDRESS 0 -#define CROSS_64KB(a,s) (0) - -#define fd_inb(port) inb_p(port) -#define fd_outb(value,port) outb_p(value,port) - -#define fd_request_dma() (0) -#define fd_free_dma() ((void)0) -#define fd_enable_irq() enable_irq(FLOPPY_IRQ) -#define fd_disable_irq() disable_irq(FLOPPY_IRQ) -#define fd_free_irq() free_irq(FLOPPY_IRQ, NULL) -#define fd_get_dma_residue() vdma_get_dma_residue(FLOPPY_DMA) -#define fd_dma_mem_alloc(size) vdma_mem_alloc(size) -#define fd_dma_mem_free(addr, size) vdma_mem_free(addr, size) -#define fd_dma_setup(addr, size, mode, io) vdma_dma_setup(addr, size, mode, io) - -static int virtual_dma_count; -static int virtual_dma_residue; -static char *virtual_dma_addr; -static int virtual_dma_mode; -static int doing_pdma; - -static irqreturn_t floppy_hardint(int irq, void *dev_id, struct pt_regs * regs) -{ - register unsigned char st; - -#undef TRACE_FLPY_INT - -#ifdef TRACE_FLPY_INT - static int calls=0; - static int bytes=0; - static int dma_wait=0; -#endif - if (!doing_pdma) - return floppy_interrupt(irq, dev_id, regs); - -#ifdef TRACE_FLPY_INT - if(!calls) - bytes = virtual_dma_count; -#endif - - { - register int lcount; - register char *lptr; - - st = 1; - for(lcount=virtual_dma_count, lptr=virtual_dma_addr; - lcount; lcount--, lptr++) { - st=inb(virtual_dma_port+4) & 0xa0 ; - if(st != 0xa0) - break; - if(virtual_dma_mode) - outb_p(*lptr, virtual_dma_port+5); - else - *lptr = inb_p(virtual_dma_port+5); - } - virtual_dma_count = lcount; - virtual_dma_addr = lptr; - st = inb(virtual_dma_port+4); - } - -#ifdef TRACE_FLPY_INT - calls++; -#endif - if(st == 0x20) - return IRQ_HANDLED; - if(!(st & 0x20)) { - virtual_dma_residue += virtual_dma_count; - virtual_dma_count=0; -#ifdef TRACE_FLPY_INT - printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n", - virtual_dma_count, virtual_dma_residue, calls, bytes, - dma_wait); - calls = 0; - dma_wait=0; -#endif - doing_pdma = 0; - floppy_interrupt(irq, dev_id, regs); - return IRQ_HANDLED; - } -#ifdef TRACE_FLPY_INT - if(!virtual_dma_count) - dma_wait++; -#endif - return IRQ_HANDLED; -} - -static void fd_disable_dma(void) -{ - doing_pdma = 0; - virtual_dma_residue += virtual_dma_count; - virtual_dma_count=0; -} - -static int vdma_get_dma_residue(unsigned int dummy) -{ - return virtual_dma_count + virtual_dma_residue; -} - - -static int fd_request_irq(void) -{ - return request_irq(FLOPPY_IRQ, floppy_hardint,SA_INTERRUPT, - "floppy", NULL); -} - - -static unsigned long vdma_mem_alloc(unsigned long size) -{ - return (unsigned long) vmalloc(size); - -} - -static void vdma_mem_free(unsigned long addr, unsigned long size) -{ - vfree((void *)addr); -} - -static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io) -{ - doing_pdma = 1; - virtual_dma_port = io; - virtual_dma_mode = (mode == DMA_MODE_WRITE); - virtual_dma_addr = addr; - virtual_dma_count = size; - virtual_dma_residue = 0; - return 0; -} - -/* XEN: This trick to force 'virtual DMA' is from include/asm-m68k/floppy.h. */ -#define FDC1 xen_floppy_init() -static int FDC2 = -1; - -static int xen_floppy_init(void) -{ - use_virtual_dma = 1; - can_use_virtual_dma = 1; - return 0x340; -} - -/* - * Floppy types are stored in the rtc's CMOS RAM and so rtc_lock - * is needed to prevent corrupted CMOS RAM in case "insmod floppy" - * coincides with another rtc CMOS user. Paul G. - */ -#define FLOPPY0_TYPE ({ \ - unsigned long flags; \ - unsigned char val; \ - spin_lock_irqsave(&rtc_lock, flags); \ - val = (CMOS_READ(0x10) >> 4) & 15; \ - spin_unlock_irqrestore(&rtc_lock, flags); \ - val; \ -}) - -#define FLOPPY1_TYPE ({ \ - unsigned long flags; \ - unsigned char val; \ - spin_lock_irqsave(&rtc_lock, flags); \ - val = CMOS_READ(0x10) & 15; \ - spin_unlock_irqrestore(&rtc_lock, flags); \ - val; \ -}) - -#define N_FDC 2 -#define N_DRIVE 8 - -#define FLOPPY_MOTOR_MASK 0xf0 - -#define EXTRA_FLOPPY_PARAMS - -#endif /* __ASM_XEN_X86_64_FLOPPY_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/hw_irq.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/hw_irq.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,138 +0,0 @@ -#ifndef _ASM_HW_IRQ_H -#define _ASM_HW_IRQ_H - -/* - * linux/include/asm/hw_irq.h - * - * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar - * - * moved some of the old arch/i386/kernel/irq.h to here. VY - * - * IRQ/IPI changes taken from work by Thomas Radke - * <tomsoft@xxxxxxxxxxxxxxxxxxxxxxxxx> - * - * hacked by Andi Kleen for x86-64. - * - * $Id: hw_irq.h,v 1.24 2001/09/14 20:55:03 vojtech Exp $ - */ - -#ifndef __ASSEMBLY__ -#include <linux/config.h> -#include <asm/atomic.h> -#include <asm/irq.h> -#include <linux/profile.h> -#include <linux/smp.h> - -struct hw_interrupt_type; -#endif - -/* - * IDT vectors usable for external interrupt sources start - * at 0x20: - */ -#define FIRST_EXTERNAL_VECTOR 0x20 - -#define IA32_SYSCALL_VECTOR 0x80 - - -/* - * Vectors 0x20-0x2f are used for ISA interrupts. - */ - -/* - * Special IRQ vectors used by the SMP architecture, 0xf0-0xff - * - * some of the following vectors are 'rare', they are merged - * into a single vector (CALL_FUNCTION_VECTOR) to save vector space. - * TLB, reschedule and local APIC vectors are performance-critical. - * - * Vectors 0xf0-0xf9 are free (reserved for future Linux use). - */ -#ifndef CONFIG_XEN -#define SPURIOUS_APIC_VECTOR 0xff -#define ERROR_APIC_VECTOR 0xfe -#define INVALIDATE_TLB_VECTOR 0xfd -#define RESCHEDULE_VECTOR 0xfc -#define TASK_MIGRATION_VECTOR 0xfb -#define CALL_FUNCTION_VECTOR 0xfa -#define KDB_VECTOR 0xf9 - -#define THERMAL_APIC_VECTOR 0xf0 -#endif - -/* - * Local APIC timer IRQ vector is on a different priority level, - * to work around the 'lost local interrupt if more than 2 IRQ - * sources per level' errata. - */ -#define LOCAL_TIMER_VECTOR 0xef - -/* - * First APIC vector available to drivers: (vectors 0x30-0xee) - * we start at 0x31 to spread out vectors evenly between priority - * levels. (0x80 is the syscall vector) - */ -#define FIRST_DEVICE_VECTOR 0x31 -#define FIRST_SYSTEM_VECTOR 0xef /* duplicated in irq.h */ - - -#ifndef __ASSEMBLY__ -extern u8 irq_vector[NR_IRQ_VECTORS]; -#define IO_APIC_VECTOR(irq) (irq_vector[irq]) -#define AUTO_ASSIGN -1 - -/* - * Various low-level irq details needed by irq.c, process.c, - * time.c, io_apic.c and smp.c - * - * Interrupt entry/exit code at both C and assembly level - */ - -extern void disable_8259A_irq(unsigned int irq); -extern void enable_8259A_irq(unsigned int irq); -extern int i8259A_irq_pending(unsigned int irq); -extern void make_8259A_irq(unsigned int irq); -extern void init_8259A(int aeoi); -extern void FASTCALL(send_IPI_self(int vector)); -extern void init_VISWS_APIC_irqs(void); -extern void setup_IO_APIC(void); -extern void disable_IO_APIC(void); -extern void print_IO_APIC(void); -extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn); -extern void send_IPI(int dest, int vector); -extern void setup_ioapic_dest(void); - -extern unsigned long io_apic_irqs; - -extern atomic_t irq_err_count; -extern atomic_t irq_mis_count; - -#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs)) - -#define __STR(x) #x -#define STR(x) __STR(x) - -#include <asm/ptrace.h> - -#define IRQ_NAME2(nr) nr##_interrupt(void) -#define IRQ_NAME(nr) IRQ_NAME2(IRQ##nr) - -/* - * SMP has a few special interrupts for IPI messages - */ - -#define BUILD_IRQ(nr) \ -asmlinkage void IRQ_NAME(nr); \ -__asm__( \ -"\n.p2align\n" \ -"IRQ" #nr "_interrupt:\n\t" \ - "push $" #nr "-256 ; " \ - "jmp common_interrupt"); - -extern void hw_resend_irq(struct hw_interrupt_type *h, unsigned int i); - -#define platform_legacy_irq(irq) ((irq) < 16) - -#endif - -#endif /* _ASM_HW_IRQ_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/hypercall.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/hypercall.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,323 +0,0 @@ -/****************************************************************************** - * hypercall.h - * - * Linux-specific hypervisor handling. - * - * Copyright (c) 2002-2004, K A Fraser - * - * 64-bit updates: - * Benjamin Liu <benjamin.liu@xxxxxxxxx> - * Jun Nakajima <jun.nakajima@xxxxxxxxx> - * - * This file may be distributed separately from the Linux kernel, or - * incorporated into other software packages, subject to the following license: - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this source file (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, copy, modify, - * merge, publish, distribute, sublicense, and/or sell copies of the Software, - * and to permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - */ - -#ifndef __HYPERCALL_H__ -#define __HYPERCALL_H__ - -#include <asm-xen/xen-public/xen.h> -#include <asm-xen/xen-public/sched.h> - -#define __STR(x) #x -#define STR(x) __STR(x) - -#define _hypercall0(type, name) \ -({ \ - long __res; \ - asm volatile ( \ - "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ - : "=a" (__res) \ - : \ - : "memory" ); \ - (type)__res; \ -}) - -#define _hypercall1(type, name, a1) \ -({ \ - long __res, __ign1; \ - asm volatile ( \ - "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ - : "=a" (__res), "=D" (__ign1) \ - : "1" ((long)(a1)) \ - : "memory" ); \ - (type)__res; \ -}) - -#define _hypercall2(type, name, a1, a2) \ -({ \ - long __res, __ign1, __ign2; \ - asm volatile ( \ - "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ - : "=a" (__res), "=D" (__ign1), "=S" (__ign2) \ - : "1" ((long)(a1)), "2" ((long)(a2)) \ - : "memory" ); \ - (type)__res; \ -}) - -#define _hypercall3(type, name, a1, a2, a3) \ -({ \ - long __res, __ign1, __ign2, __ign3; \ - asm volatile ( \ - "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ - : "=a" (__res), "=D" (__ign1), "=S" (__ign2), \ - "=d" (__ign3) \ - : "1" ((long)(a1)), "2" ((long)(a2)), \ - "3" ((long)(a3)) \ - : "memory" ); \ - (type)__res; \ -}) - -#define _hypercall4(type, name, a1, a2, a3, a4) \ -({ \ - long __res, __ign1, __ign2, __ign3; \ - asm volatile ( \ - "movq %7,%%r10; " \ - "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ - : "=a" (__res), "=D" (__ign1), "=S" (__ign2), \ - "=d" (__ign3) \ - : "1" ((long)(a1)), "2" ((long)(a2)), \ - "3" ((long)(a3)), "g" ((long)(a4)) \ - : "memory", "r10" ); \ - (type)__res; \ -}) - -#define _hypercall5(type, name, a1, a2, a3, a4, a5) \ -({ \ - long __res, __ign1, __ign2, __ign3; \ - asm volatile ( \ - "movq %7,%%r10; movq %8,%%r8; " \ - "call hypercall_page + ("STR(__HYPERVISOR_##name)" * 32)"\ - : "=a" (__res), "=D" (__ign1), "=S" (__ign2), \ - "=d" (__ign3) \ - : "1" ((long)(a1)), "2" ((long)(a2)), \ - "3" ((long)(a3)), "g" ((long)(a4)), \ - "g" ((long)(a5)) \ - : "memory", "r10", "r8" ); \ - (type)__res; \ -}) - -static inline int -HYPERVISOR_set_trap_table( - trap_info_t *table) -{ - return _hypercall1(int, set_trap_table, table); -} - -static inline int -HYPERVISOR_mmu_update( - mmu_update_t *req, int count, int *success_count, domid_t domid) -{ - return _hypercall4(int, mmu_update, req, count, success_count, domid); -} - -static inline int -HYPERVISOR_mmuext_op( - struct mmuext_op *op, int count, int *success_count, domid_t domid) -{ - return _hypercall4(int, mmuext_op, op, count, success_count, domid); -} - -static inline int -HYPERVISOR_set_gdt( - unsigned long *frame_list, int entries) -{ - return _hypercall2(int, set_gdt, frame_list, entries); -} - -static inline int -HYPERVISOR_stack_switch( - unsigned long ss, unsigned long esp) -{ - return _hypercall2(int, stack_switch, ss, esp); -} - -static inline int -HYPERVISOR_set_callbacks( - unsigned long event_address, unsigned long failsafe_address, - unsigned long syscall_address) -{ - return _hypercall3(int, set_callbacks, - event_address, failsafe_address, syscall_address); -} - -static inline int -HYPERVISOR_fpu_taskswitch( - int set) -{ - return _hypercall1(int, fpu_taskswitch, set); -} - -static inline int -HYPERVISOR_sched_op( - int cmd, unsigned long arg) -{ - return _hypercall2(int, sched_op, cmd, arg); -} - -static inline long -HYPERVISOR_set_timer_op( - u64 timeout) -{ - return _hypercall1(long, set_timer_op, timeout); -} - -static inline int -HYPERVISOR_dom0_op( - dom0_op_t *dom0_op) -{ - dom0_op->interface_version = DOM0_INTERFACE_VERSION; - return _hypercall1(int, dom0_op, dom0_op); -} - -static inline int -HYPERVISOR_set_debugreg( - int reg, unsigned long value) -{ - return _hypercall2(int, set_debugreg, reg, value); -} - -static inline unsigned long -HYPERVISOR_get_debugreg( - int reg) -{ - return _hypercall1(unsigned long, get_debugreg, reg); -} - -static inline int -HYPERVISOR_update_descriptor( - unsigned long ma, unsigned long word) -{ - return _hypercall2(int, update_descriptor, ma, word); -} - -static inline int -HYPERVISOR_memory_op( - unsigned int cmd, void *arg) -{ - return _hypercall2(int, memory_op, cmd, arg); -} - -static inline int -HYPERVISOR_multicall( - void *call_list, int nr_calls) -{ - return _hypercall2(int, multicall, call_list, nr_calls); -} - -static inline int -HYPERVISOR_update_va_mapping( - unsigned long va, pte_t new_val, unsigned long flags) -{ - return _hypercall3(int, update_va_mapping, va, new_val.pte, flags); -} - -static inline int -HYPERVISOR_event_channel_op( - void *op) -{ - return _hypercall1(int, event_channel_op, op); -} - -static inline int -HYPERVISOR_xen_version( - int cmd, void *arg) -{ - return _hypercall2(int, xen_version, cmd, arg); -} - -static inline int -HYPERVISOR_console_io( - int cmd, int count, char *str) -{ - return _hypercall3(int, console_io, cmd, count, str); -} - -static inline int -HYPERVISOR_physdev_op( - void *physdev_op) -{ - return _hypercall1(int, physdev_op, physdev_op); -} - -static inline int -HYPERVISOR_grant_table_op( - unsigned int cmd, void *uop, unsigned int count) -{ - return _hypercall3(int, grant_table_op, cmd, uop, count); -} - -static inline int -HYPERVISOR_update_va_mapping_otherdomain( - unsigned long va, pte_t new_val, unsigned long flags, domid_t domid) -{ - return _hypercall4(int, update_va_mapping_otherdomain, va, - new_val.pte, flags, domid); -} - -static inline int -HYPERVISOR_vm_assist( - unsigned int cmd, unsigned int type) -{ - return _hypercall2(int, vm_assist, cmd, type); -} - -static inline int -HYPERVISOR_vcpu_op( - int cmd, int vcpuid, void *extra_args) -{ - return _hypercall3(int, vcpu_op, cmd, vcpuid, extra_args); -} - -static inline int -HYPERVISOR_set_segment_base( - int reg, unsigned long value) -{ - return _hypercall2(int, set_segment_base, reg, value); -} - -static inline int -HYPERVISOR_suspend( - unsigned long srec) -{ - return _hypercall3(int, sched_op, SCHEDOP_shutdown, - SHUTDOWN_suspend, srec); -} - -static inline int -HYPERVISOR_nmi_op( - unsigned long op, - unsigned long arg) -{ - return _hypercall2(int, nmi_op, op, arg); -} - -#endif /* __HYPERCALL_H__ */ - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/hypervisor.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/hypervisor.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,2 +0,0 @@ - -#include <asm-i386/hypervisor.h> diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/io.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/io.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,374 +0,0 @@ -#ifndef _ASM_IO_H -#define _ASM_IO_H - -#include <linux/config.h> -#include <asm/fixmap.h> -/* - * This file contains the definitions for the x86 IO instructions - * inb/inw/inl/outb/outw/outl and the "string versions" of the same - * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing" - * versions of the single-IO instructions (inb_p/inw_p/..). - * - * This file is not meant to be obfuscating: it's just complicated - * to (a) handle it all in a way that makes gcc able to optimize it - * as well as possible and (b) trying to avoid writing the same thing - * over and over again with slight variations and possibly making a - * mistake somewhere. - */ - -/* - * Thanks to James van Artsdalen for a better timing-fix than - * the two short jumps: using outb's to a nonexistent port seems - * to guarantee better timings even on fast machines. - * - * On the other hand, I'd like to be sure of a non-existent port: - * I feel a bit unsafe about using 0x80 (should be safe, though) - * - * Linus - */ - - /* - * Bit simplified and optimized by Jan Hubicka - * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999. - * - * isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added, - * isa_read[wl] and isa_write[wl] fixed - * - Arnaldo Carvalho de Melo <acme@xxxxxxxxxxxxxxxx> - */ - -#define __SLOW_DOWN_IO "\noutb %%al,$0x80" - -#ifdef REALLY_SLOW_IO -#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO -#else -#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO -#endif - -/* - * Talk about misusing macros.. - */ -#define __OUT1(s,x) \ -extern inline void out##s(unsigned x value, unsigned short port) { - -#define __OUT2(s,s1,s2) \ -__asm__ __volatile__ ("out" #s " %" s1 "0,%" s2 "1" - -#define __OUT(s,s1,x) \ -__OUT1(s,x) __OUT2(s,s1,"w") : : "a" (value), "Nd" (port)); } \ -__OUT1(s##_p,x) __OUT2(s,s1,"w") __FULL_SLOW_DOWN_IO : : "a" (value), "Nd" (port));} \ - -#define __IN1(s) \ -extern inline RETURN_TYPE in##s(unsigned short port) { RETURN_TYPE _v; - -#define __IN2(s,s1,s2) \ -__asm__ __volatile__ ("in" #s " %" s2 "1,%" s1 "0" - -#define __IN(s,s1,i...) \ -__IN1(s) __IN2(s,s1,"w") : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \ -__IN1(s##_p) __IN2(s,s1,"w") __FULL_SLOW_DOWN_IO : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \ - -#define __INS(s) \ -extern inline void ins##s(unsigned short port, void * addr, unsigned long count) \ -{ __asm__ __volatile__ ("rep ; ins" #s \ -: "=D" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); } - -#define __OUTS(s) \ -extern inline void outs##s(unsigned short port, const void * addr, unsigned long count) \ -{ __asm__ __volatile__ ("rep ; outs" #s \ -: "=S" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); } - -#define RETURN_TYPE unsigned char -__IN(b,"") -#undef RETURN_TYPE -#define RETURN_TYPE unsigned short -__IN(w,"") -#undef RETURN_TYPE -#define RETURN_TYPE unsigned int -__IN(l,"") -#undef RETURN_TYPE - -__OUT(b,"b",char) -__OUT(w,"w",short) -__OUT(l,,int) - -__INS(b) -__INS(w) -__INS(l) - -__OUTS(b) -__OUTS(w) -__OUTS(l) - -#define IO_SPACE_LIMIT 0xffff - -#if defined(__KERNEL__) && __x86_64__ - -#include <linux/vmalloc.h> - -#ifndef __i386__ -/* - * Change virtual addresses to physical addresses and vv. - * These are pretty trivial - */ -extern inline unsigned long virt_to_phys(volatile void * address) -{ - return __pa(address); -} - -extern inline void * phys_to_virt(unsigned long address) -{ - return __va(address); -} - - -#define virt_to_bus(_x) phys_to_machine(__pa(_x)) -#define bus_to_virt(_x) __va(machine_to_phys(_x)) -#endif - -/* - * Change "struct page" to physical address. - */ -#ifdef CONFIG_DISCONTIGMEM -#include <asm/mmzone.h> -#define page_to_pseudophys(page) ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT) -#define page_to_phys(page) (phys_to_machine(page_to_pseudophys(page))) - -#define bio_to_pseudophys(bio) (page_to_pseudophys(bio_page((bio))) + \ - (unsigned long) bio_offset((bio))) -#define bvec_to_pseudophys(bv) (page_to_pseudophys((bv)->bv_page) + \ - (unsigned long) (bv)->bv_offset) - -#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ - (((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2))) && \ - ((bvec_to_pseudophys((vec1)) + (vec1)->bv_len) == \ - bvec_to_pseudophys((vec2)))) -#else -// #define page_to_phys(page) ((page - mem_map) << PAGE_SHIFT) -#define page_to_pseudophys(page) ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT) -#define page_to_phys(page) (phys_to_machine(page_to_pseudophys(page))) - -#define bio_to_pseudophys(bio) (page_to_pseudophys(bio_page((bio))) + \ - (unsigned long) bio_offset((bio))) -#define bvec_to_pseudophys(bv) (page_to_pseudophys((bv)->bv_page) + \ - (unsigned long) (bv)->bv_offset) - -#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ - (((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2))) && \ - ((bvec_to_pseudophys((vec1)) + (vec1)->bv_len) == \ - bvec_to_pseudophys((vec2)))) -#endif - -#include <asm-generic/iomap.h> - -extern void __iomem *__ioremap(unsigned long offset, unsigned long size, unsigned long flags); - -extern inline void __iomem * ioremap (unsigned long offset, unsigned long size) -{ - return __ioremap(offset, size, 0); -} - -/* - * This one maps high address device memory and turns off caching for that area. - * it's useful if some control registers are in such an area and write combining - * or read caching is not desirable: - */ -extern void __iomem * ioremap_nocache (unsigned long offset, unsigned long size); -extern void iounmap(volatile void __iomem *addr); - -/* - * ISA I/O bus memory addresses are 1:1 with the physical address. - */ - -#define isa_virt_to_bus(_x) isa_virt_to_bus_is_UNSUPPORTED->x -#define isa_page_to_bus(_x) isa_page_to_bus_is_UNSUPPORTED->x -#ifdef CONFIG_XEN_PHYSDEV_ACCESS -#define isa_bus_to_virt(_x) (void *)(__fix_to_virt(FIX_ISAMAP_BEGIN) + (_x)) -#else -#define isa_bus_to_virt(_x) isa_bus_to_virt_needs_PRIVILEGED_BUILD -#endif -/* - * However PCI ones are not necessarily 1:1 and therefore these interfaces - * are forbidden in portable PCI drivers. - * - * Allow them on x86 for legacy drivers, though. - */ -#define virt_to_bus(_x) phys_to_machine(__pa(_x)) -#define bus_to_virt(_x) __va(machine_to_phys(_x)) - -/* - * readX/writeX() are used to access memory mapped devices. On some - * architectures the memory mapped IO stuff needs to be accessed - * differently. On the x86 architecture, we just read/write the - * memory location directly. - */ - -static inline __u8 __readb(const volatile void __iomem *addr) -{ - return *(__force volatile __u8 *)addr; -} -static inline __u16 __readw(const volatile void __iomem *addr) -{ - return *(__force volatile __u16 *)addr; -} -static inline __u32 __readl(const volatile void __iomem *addr) -{ - return *(__force volatile __u32 *)addr; -} -static inline __u64 __readq(const volatile void __iomem *addr) -{ - return *(__force volatile __u64 *)addr; -} -#define readb(x) __readb(x) -#define readw(x) __readw(x) -#define readl(x) __readl(x) -#define readq(x) __readq(x) -#define readb_relaxed(a) readb(a) -#define readw_relaxed(a) readw(a) -#define readl_relaxed(a) readl(a) -#define readq_relaxed(a) readq(a) -#define __raw_readb readb -#define __raw_readw readw -#define __raw_readl readl -#define __raw_readq readq - -#define mmiowb() - -#ifdef CONFIG_UNORDERED_IO -static inline void __writel(__u32 val, volatile void __iomem *addr) -{ - volatile __u32 __iomem *target = addr; - asm volatile("movnti %1,%0" - : "=m" (*target) - : "r" (val) : "memory"); -} - -static inline void __writeq(__u64 val, volatile void __iomem *addr) -{ - volatile __u64 __iomem *target = addr; - asm volatile("movnti %1,%0" - : "=m" (*target) - : "r" (val) : "memory"); -} -#else -static inline void __writel(__u32 b, volatile void __iomem *addr) -{ - *(__force volatile __u32 *)addr = b; -} -static inline void __writeq(__u64 b, volatile void __iomem *addr) -{ - *(__force volatile __u64 *)addr = b; -} -#endif -static inline void __writeb(__u8 b, volatile void __iomem *addr) -{ - *(__force volatile __u8 *)addr = b; -} -static inline void __writew(__u16 b, volatile void __iomem *addr) -{ - *(__force volatile __u16 *)addr = b; -} -#define writeq(val,addr) __writeq((val),(addr)) -#define writel(val,addr) __writel((val),(addr)) -#define writew(val,addr) __writew((val),(addr)) -#define writeb(val,addr) __writeb((val),(addr)) -#define __raw_writeb writeb -#define __raw_writew writew -#define __raw_writel writel -#define __raw_writeq writeq - -void __memcpy_fromio(void*,unsigned long,unsigned); -void __memcpy_toio(unsigned long,const void*,unsigned); - -static inline void memcpy_fromio(void *to, const volatile void __iomem *from, unsigned len) -{ - __memcpy_fromio(to,(unsigned long)from,len); -} -static inline void memcpy_toio(volatile void __iomem *to, const void *from, unsigned len) -{ - __memcpy_toio((unsigned long)to,from,len); -} - -void memset_io(volatile void __iomem *a, int b, size_t c); - -/* - * ISA space is 'always mapped' on a typical x86 system, no need to - * explicitly ioremap() it. The fact that the ISA IO space is mapped - * to PAGE_OFFSET is pure coincidence - it does not mean ISA values - * are physical addresses. The following constant pointer can be - * used as the IO-area pointer (it can be iounmapped as well, so the - * analogy with PCI is quite large): - */ -#define __ISA_IO_base ((char __iomem *)(fix_to_virt(FIX_ISAMAP_BEGIN))) - -#define isa_readb(a) readb(__ISA_IO_base + (a)) -#define isa_readw(a) readw(__ISA_IO_base + (a)) -#define isa_readl(a) readl(__ISA_IO_base + (a)) -#define isa_writeb(b,a) writeb(b,__ISA_IO_base + (a)) -#define isa_writew(w,a) writew(w,__ISA_IO_base + (a)) -#define isa_writel(l,a) writel(l,__ISA_IO_base + (a)) -#define isa_memset_io(a,b,c) memset_io(__ISA_IO_base + (a),(b),(c)) -#define isa_memcpy_fromio(a,b,c) memcpy_fromio((a),__ISA_IO_base + (b),(c)) -#define isa_memcpy_toio(a,b,c) memcpy_toio(__ISA_IO_base + (a),(b),(c)) - - -/* - * Again, x86-64 does not require mem IO specific function. - */ - -#define eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void *)(b),(c),(d)) -#define isa_eth_io_copy_and_sum(a,b,c,d) eth_copy_and_sum((a),(void *)(__ISA_IO_base + (b)),(c),(d)) - -/** - * check_signature - find BIOS signatures - * @io_addr: mmio address to check - * @signature: signature block - * @length: length of signature - * - * Perform a signature comparison with the mmio address io_addr. This - * address should have been obtained by ioremap. - * Returns 1 on a match. - */ - -static inline int check_signature(void __iomem *io_addr, - const unsigned char *signature, int length) -{ - int retval = 0; - do { - if (readb(io_addr) != *signature) - goto out; - io_addr++; - signature++; - length--; - } while (length); - retval = 1; -out: - return retval; -} - -/* Nothing to do */ - -#define dma_cache_inv(_start,_size) do { } while (0) -#define dma_cache_wback(_start,_size) do { } while (0) -#define dma_cache_wback_inv(_start,_size) do { } while (0) - -#define flush_write_buffers() - -extern int iommu_bio_merge; -#define BIO_VMERGE_BOUNDARY iommu_bio_merge - -/* - * Convert a physical pointer to a virtual kernel pointer for /dev/mem - * access - */ -#define xlate_dev_mem_ptr(p) __va(p) - -/* - * Convert a virtual cached pointer to an uncached pointer - */ -#define xlate_dev_kmem_ptr(p) p - -#endif /* __KERNEL__ */ - -#define ARCH_HAS_DEV_MEM - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/irq.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/irq.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,36 +0,0 @@ -#ifndef _ASM_IRQ_H -#define _ASM_IRQ_H - -/* - * linux/include/asm/irq.h - * - * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar - * - * IRQ/IPI changes taken from work by Thomas Radke - * <tomsoft@xxxxxxxxxxxxxxxxxxxxxxxxx> - */ - -#include <linux/config.h> -#include <linux/sched.h> -/* include comes from machine specific directory */ -#include "irq_vectors.h" -#include <asm/thread_info.h> - -static __inline__ int irq_canonicalize(int irq) -{ - return ((irq == 2) ? 9 : irq); -} - -#ifdef CONFIG_X86_LOCAL_APIC -#define ARCH_HAS_NMI_WATCHDOG /* See include/linux/nmi.h */ -#endif - -#define KDB_VECTOR 0xf9 - -# define irq_ctx_init(cpu) do { } while (0) - -struct irqaction; -struct pt_regs; -int handle_IRQ_event(unsigned int, struct pt_regs *, struct irqaction *); - -#endif /* _ASM_IRQ_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/io_ports.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/io_ports.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,30 +0,0 @@ -/* - * arch/i386/mach-generic/io_ports.h - * - * Machine specific IO port address definition for generic. - * Written by Osamu Tomita <tomita@xxxxxxxxxxx> - */ -#ifndef _MACH_IO_PORTS_H -#define _MACH_IO_PORTS_H - -/* i8253A PIT registers */ -#define PIT_MODE 0x43 -#define PIT_CH0 0x40 -#define PIT_CH2 0x42 - -/* i8259A PIC registers */ -#define PIC_MASTER_CMD 0x20 -#define PIC_MASTER_IMR 0x21 -#define PIC_MASTER_ISR PIC_MASTER_CMD -#define PIC_MASTER_POLL PIC_MASTER_ISR -#define PIC_MASTER_OCW3 PIC_MASTER_ISR -#define PIC_SLAVE_CMD 0xa0 -#define PIC_SLAVE_IMR 0xa1 - -/* i8259A PIC related value */ -#define PIC_CASCADE_IR 2 -#define MASTER_ICW4_DEFAULT 0x01 -#define SLAVE_ICW4_DEFAULT 0x01 -#define PIC_ICW4_AEOI 2 - -#endif /* !_MACH_IO_PORTS_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/irq_vectors.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/irq_vectors.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,123 +0,0 @@ -/* - * This file should contain #defines for all of the interrupt vector - * numbers used by this architecture. - * - * In addition, there are some standard defines: - * - * FIRST_EXTERNAL_VECTOR: - * The first free place for external interrupts - * - * SYSCALL_VECTOR: - * The IRQ vector a syscall makes the user to kernel transition - * under. - * - * TIMER_IRQ: - * The IRQ number the timer interrupt comes in at. - * - * NR_IRQS: - * The total number of interrupt vectors (including all the - * architecture specific interrupts) needed. - * - */ -#ifndef _ASM_IRQ_VECTORS_H -#define _ASM_IRQ_VECTORS_H - -/* - * IDT vectors usable for external interrupt sources start - * at 0x20: - */ -#define FIRST_EXTERNAL_VECTOR 0x20 - -#define SYSCALL_VECTOR 0x80 - -/* - * Vectors 0x20-0x2f are used for ISA interrupts. - */ - -#if 0 -/* - * Special IRQ vectors used by the SMP architecture, 0xf0-0xff - * - * some of the following vectors are 'rare', they are merged - * into a single vector (CALL_FUNCTION_VECTOR) to save vector space. - * TLB, reschedule and local APIC vectors are performance-critical. - * - * Vectors 0xf0-0xfa are free (reserved for future Linux use). - */ -#define INVALIDATE_TLB_VECTOR 0xfd -#define RESCHEDULE_VECTOR 0xfc -#define CALL_FUNCTION_VECTOR 0xfb - -#define THERMAL_APIC_VECTOR 0xf0 -/* - * Local APIC timer IRQ vector is on a different priority level, - * to work around the 'lost local interrupt if more than 2 IRQ - * sources per level' errata. - */ -#define LOCAL_TIMER_VECTOR 0xef -#endif - -#define SPURIOUS_APIC_VECTOR 0xff -#define ERROR_APIC_VECTOR 0xfe - -/* - * First APIC vector available to drivers: (vectors 0x30-0xee) - * we start at 0x31 to spread out vectors evenly between priority - * levels. (0x80 is the syscall vector) - */ -#define FIRST_DEVICE_VECTOR 0x31 -#define FIRST_SYSTEM_VECTOR 0xef - -/* - * 16 8259A IRQ's, 208 potential APIC interrupt sources. - * Right now the APIC is mostly only used for SMP. - * 256 vectors is an architectural limit. (we can have - * more than 256 devices theoretically, but they will - * have to use shared interrupts) - * Since vectors 0x00-0x1f are used/reserved for the CPU, - * the usable vector space is 0x20-0xff (224 vectors) - */ - -#define RESCHEDULE_VECTOR 0 -#define CALL_FUNCTION_VECTOR 1 -#define NR_IPIS 2 - -/* - * The maximum number of vectors supported by i386 processors - * is limited to 256. For processors other than i386, NR_VECTORS - * should be changed accordingly. - */ -#define NR_VECTORS 256 - -#define FPU_IRQ 13 - -#define FIRST_VM86_IRQ 3 -#define LAST_VM86_IRQ 15 -#define invalid_vm86_irq(irq) ((irq) < 3 || (irq) > 15) - -/* - * The flat IRQ space is divided into two regions: - * 1. A one-to-one mapping of real physical IRQs. This space is only used - * if we have physical device-access privilege. This region is at the - * start of the IRQ space so that existing device drivers do not need - * to be modified to translate physical IRQ numbers into our IRQ space. - * 3. A dynamic mapping of inter-domain and Xen-sourced virtual IRQs. These - * are bound using the provided bind/unbind functions. - */ - -#define PIRQ_BASE 0 -#define NR_PIRQS 256 - -#define DYNIRQ_BASE (PIRQ_BASE + NR_PIRQS) -#define NR_DYNIRQS 256 - -#define NR_IRQS (NR_PIRQS + NR_DYNIRQS) -#define NR_IRQ_VECTORS NR_IRQS - -#define pirq_to_irq(_x) ((_x) + PIRQ_BASE) -#define irq_to_pirq(_x) ((_x) - PIRQ_BASE) - -#define dynirq_to_irq(_x) ((_x) + DYNIRQ_BASE) -#define irq_to_dynirq(_x) ((_x) - DYNIRQ_BASE) - -#endif /* _ASM_IRQ_VECTORS_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/mach_time.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/mach_time.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,122 +0,0 @@ -/* - * include/asm-i386/mach-default/mach_time.h - * - * Machine specific set RTC function for generic. - * Split out from time.c by Osamu Tomita <tomita@xxxxxxxxxxx> - */ -#ifndef _MACH_TIME_H -#define _MACH_TIME_H - -#include <asm-i386/mc146818rtc.h> - -/* for check timing call set_rtc_mmss() 500ms */ -/* used in arch/i386/time.c::do_timer_interrupt() */ -#define USEC_AFTER 500000 -#define USEC_BEFORE 500000 - -/* - * In order to set the CMOS clock precisely, set_rtc_mmss has to be - * called 500 ms after the second nowtime has started, because when - * nowtime is written into the registers of the CMOS clock, it will - * jump to the next second precisely 500 ms later. Check the Motorola - * MC146818A or Dallas DS12887 data sheet for details. - * - * BUG: This routine does not handle hour overflow properly; it just - * sets the minutes. Usually you'll only notice that after reboot! - */ -static inline int mach_set_rtc_mmss(unsigned long nowtime) -{ - int retval = 0; - int real_seconds, real_minutes, cmos_minutes; - unsigned char save_control, save_freq_select; - - save_control = CMOS_READ(RTC_CONTROL); /* tell the clock it's being set */ - CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL); - - save_freq_select = CMOS_READ(RTC_FREQ_SELECT); /* stop and reset prescaler */ - CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT); - - cmos_minutes = CMOS_READ(RTC_MINUTES); - if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) - BCD_TO_BIN(cmos_minutes); - - /* - * since we're only adjusting minutes and seconds, - * don't interfere with hour overflow. This avoids - * messing with unknown time zones but requires your - * RTC not to be off by more than 15 minutes - */ - real_seconds = nowtime % 60; - real_minutes = nowtime / 60; - if (((abs(real_minutes - cmos_minutes) + 15)/30) & 1) - real_minutes += 30; /* correct for half hour time zone */ - real_minutes %= 60; - - if (abs(real_minutes - cmos_minutes) < 30) { - if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { - BIN_TO_BCD(real_seconds); - BIN_TO_BCD(real_minutes); - } - CMOS_WRITE(real_seconds,RTC_SECONDS); - CMOS_WRITE(real_minutes,RTC_MINUTES); - } else { - printk(KERN_WARNING - "set_rtc_mmss: can't update from %d to %d\n", - cmos_minutes, real_minutes); - retval = -1; - } - - /* The following flags have to be released exactly in this order, - * otherwise the DS12887 (popular MC146818A clone with integrated - * battery and quartz) will not reset the oscillator and will not - * update precisely 500 ms later. You won't find this mentioned in - * the Dallas Semiconductor data sheets, but who believes data - * sheets anyway ... -- Markus Kuhn - */ - CMOS_WRITE(save_control, RTC_CONTROL); - CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); - - return retval; -} - -static inline unsigned long mach_get_cmos_time(void) -{ - unsigned int year, mon, day, hour, min, sec; - int i; - - /* The Linux interpretation of the CMOS clock register contents: - * When the Update-In-Progress (UIP) flag goes from 1 to 0, the - * RTC registers show the second which has precisely just started. - * Let's hope other operating systems interpret the RTC the same way. - */ - /* read RTC exactly on falling edge of update flag */ - for (i = 0 ; i < 1000000 ; i++) /* may take up to 1 second... */ - if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) - break; - for (i = 0 ; i < 1000000 ; i++) /* must try at least 2.228 ms */ - if (!(CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP)) - break; - do { /* Isn't this overkill ? UIP above should guarantee consistency */ - sec = CMOS_READ(RTC_SECONDS); - min = CMOS_READ(RTC_MINUTES); - hour = CMOS_READ(RTC_HOURS); - day = CMOS_READ(RTC_DAY_OF_MONTH); - mon = CMOS_READ(RTC_MONTH); - year = CMOS_READ(RTC_YEAR); - } while (sec != CMOS_READ(RTC_SECONDS)); - if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) || RTC_ALWAYS_BCD) - { - BCD_TO_BIN(sec); - BCD_TO_BIN(min); - BCD_TO_BIN(hour); - BCD_TO_BIN(day); - BCD_TO_BIN(mon); - BCD_TO_BIN(year); - } - if ((year += 1900) < 1970) - year += 100; - - return mktime(year, mon, day, hour, min, sec); -} - -#endif /* !_MACH_TIME_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/mach_timer.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/mach_timer.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,48 +0,0 @@ -/* - * include/asm-i386/mach-default/mach_timer.h - * - * Machine specific calibrate_tsc() for generic. - * Split out from timer_tsc.c by Osamu Tomita <tomita@xxxxxxxxxxx> - */ -/* ------ Calibrate the TSC ------- - * Return 2^32 * (1 / (TSC clocks per usec)) for do_fast_gettimeoffset(). - * Too much 64-bit arithmetic here to do this cleanly in C, and for - * accuracy's sake we want to keep the overhead on the CTC speaker (channel 2) - * output busy loop as low as possible. We avoid reading the CTC registers - * directly because of the awkward 8-bit access mechanism of the 82C54 - * device. - */ -#ifndef _MACH_TIMER_H -#define _MACH_TIMER_H - -#define CALIBRATE_LATCH (5 * LATCH) - -static inline void mach_prepare_counter(void) -{ - /* Set the Gate high, disable speaker */ - outb((inb(0x61) & ~0x02) | 0x01, 0x61); - - /* - * Now let's take care of CTC channel 2 - * - * Set the Gate high, program CTC channel 2 for mode 0, - * (interrupt on terminal count mode), binary count, - * load 5 * LATCH count, (LSB and MSB) to begin countdown. - * - * Some devices need a delay here. - */ - outb(0xb0, 0x43); /* binary, mode 0, LSB/MSB, Ch 2 */ - outb_p(CALIBRATE_LATCH & 0xff, 0x42); /* LSB of count */ - outb_p(CALIBRATE_LATCH >> 8, 0x42); /* MSB of count */ -} - -static inline void mach_countup(unsigned long *count_p) -{ - unsigned long count = 0; - do { - count++; - } while ((inb_p(0x61) & 0x20) == 0); - *count_p = count; -} - -#endif /* !_MACH_TIMER_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/setup_arch_post.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/setup_arch_post.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,52 +0,0 @@ -/** - * machine_specific_memory_setup - Hook for machine specific memory setup. - * - * Description: - * This is included late in kernel/setup.c so that it can make - * use of all of the static functions. - **/ - -static char * __init machine_specific_memory_setup(void) -{ - char *who; - unsigned long start_pfn, max_pfn; - - who = "Xen"; - - start_pfn = 0; - max_pfn = xen_start_info->nr_pages; - - e820.nr_map = 0; - add_memory_region(PFN_PHYS(start_pfn), PFN_PHYS(max_pfn) - PFN_PHYS(start_pfn), E820_RAM); - - return who; -} - -void __init machine_specific_modify_cpu_capabilities(struct cpuinfo_x86 *c) -{ - clear_bit(X86_FEATURE_VME, c->x86_capability); - clear_bit(X86_FEATURE_DE, c->x86_capability); - clear_bit(X86_FEATURE_PSE, c->x86_capability); - clear_bit(X86_FEATURE_PGE, c->x86_capability); - clear_bit(X86_FEATURE_SEP, c->x86_capability); - if (!(xen_start_info->flags & SIF_PRIVILEGED)) - clear_bit(X86_FEATURE_MTRR, c->x86_capability); -} - -extern void hypervisor_callback(void); -extern void failsafe_callback(void); -extern void nmi(void); - -static void __init machine_specific_arch_setup(void) -{ - HYPERVISOR_set_callbacks( - (unsigned long) hypervisor_callback, - (unsigned long) failsafe_callback, - (unsigned long) system_call); - -#ifdef CONFIG_X86_LOCAL_APIC - HYPERVISOR_nmi_op(XENNMI_register_callback, (unsigned long)&nmi); -#endif - - machine_specific_modify_cpu_capabilities(&boot_cpu_data); -} diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/setup_arch_pre.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/mach-xen/setup_arch_pre.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,5 +0,0 @@ -/* Hook to call BIOS initialisation function */ - -#define ARCH_SETUP machine_specific_arch_setup(); - -static void __init machine_specific_arch_setup(void); diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/mmu.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/mmu.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,33 +0,0 @@ -#ifndef __x86_64_MMU_H -#define __x86_64_MMU_H - -#include <linux/spinlock.h> -#include <asm/semaphore.h> - -/* - * The x86_64 doesn't have a mmu context, but - * we put the segment information here. - * - * cpu_vm_mask is used to optimize ldt flushing. - */ -typedef struct { - void *ldt; - rwlock_t ldtlock; - int size; - struct semaphore sem; -#ifdef CONFIG_XEN - unsigned pinned:1; - struct list_head unpinned; -#endif -} mm_context_t; - -#ifdef CONFIG_XEN -extern struct list_head mm_unpinned; -extern spinlock_t mm_unpinned_lock; - -/* mm/memory.c:exit_mmap hook */ -extern void _arch_exit_mmap(struct mm_struct *mm); -#define arch_exit_mmap(_mm) _arch_exit_mmap(_mm) -#endif - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/mmu_context.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/mmu_context.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,132 +0,0 @@ -#ifndef __X86_64_MMU_CONTEXT_H -#define __X86_64_MMU_CONTEXT_H - -#include <linux/config.h> -#include <asm/desc.h> -#include <asm/atomic.h> -#include <asm/pgalloc.h> -#include <asm/page.h> -#include <asm/pda.h> -#include <asm/pgtable.h> -#include <asm/tlbflush.h> - -/* - * possibly do the LDT unload here? - */ -int init_new_context(struct task_struct *tsk, struct mm_struct *mm); -void destroy_context(struct mm_struct *mm); - -static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) -{ -#if 0 /* XEN: no lazy tlb */ - if (read_pda(mmu_state) == TLBSTATE_OK) - write_pda(mmu_state, TLBSTATE_LAZY); -#endif -} - -#define prepare_arch_switch(rq,next) __prepare_arch_switch() -#define finish_arch_switch(rq, next) spin_unlock_irq(&(rq)->lock) -#define task_running(rq, p) ((rq)->curr == (p)) - -static inline void __prepare_arch_switch(void) -{ - /* - * Save away %es, %ds, %fs and %gs. Must happen before reload - * of cr3/ldt (i.e., not in __switch_to). - */ - __asm__ __volatile__ ( - "mov %%es,%0 ; mov %%ds,%1 ; mov %%fs,%2 ; mov %%gs,%3" - : "=m" (current->thread.es), - "=m" (current->thread.ds), - "=m" (current->thread.fsindex), - "=m" (current->thread.gsindex) ); - - if (current->thread.ds) - __asm__ __volatile__ ( "movl %0,%%ds" : : "r" (0) ); - - if (current->thread.es) - __asm__ __volatile__ ( "movl %0,%%es" : : "r" (0) ); - - if (current->thread.fsindex) { - __asm__ __volatile__ ( "movl %0,%%fs" : : "r" (0) ); - current->thread.fs = 0; - } - - if (current->thread.gsindex) { - load_gs_index(0); - current->thread.gs = 0; - } -} - -extern void mm_pin(struct mm_struct *mm); -extern void mm_unpin(struct mm_struct *mm); -void mm_pin_all(void); - -static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, - struct task_struct *tsk) -{ - unsigned cpu = smp_processor_id(); - struct mmuext_op _op[3], *op = _op; - - if (likely(prev != next)) { - if (!next->context.pinned) - mm_pin(next); - - /* stop flush ipis for the previous mm */ - clear_bit(cpu, &prev->cpu_vm_mask); -#if 0 /* XEN: no lazy tlb */ - write_pda(mmu_state, TLBSTATE_OK); - write_pda(active_mm, next); -#endif - set_bit(cpu, &next->cpu_vm_mask); - - /* load_cr3(next->pgd) */ - per_cpu(cur_pgd, smp_processor_id()) = next->pgd; - op->cmd = MMUEXT_NEW_BASEPTR; - op->arg1.mfn = pfn_to_mfn(__pa(next->pgd) >> PAGE_SHIFT); - op++; - - /* xen_new_user_pt(__pa(__user_pgd(next->pgd))) */ - op->cmd = MMUEXT_NEW_USER_BASEPTR; - op->arg1.mfn = pfn_to_mfn(__pa(__user_pgd(next->pgd)) >> PAGE_SHIFT); - op++; - - if (unlikely(next->context.ldt != prev->context.ldt)) { - /* load_LDT_nolock(&next->context, cpu) */ - op->cmd = MMUEXT_SET_LDT; - op->arg1.linear_addr = (unsigned long)next->context.ldt; - op->arg2.nr_ents = next->context.size; - op++; - } - - BUG_ON(HYPERVISOR_mmuext_op(_op, op-_op, NULL, DOMID_SELF)); - } - -#if 0 /* XEN: no lazy tlb */ - else { - write_pda(mmu_state, TLBSTATE_OK); - if (read_pda(active_mm) != next) - out_of_line_bug(); - if(!test_and_set_bit(cpu, &next->cpu_vm_mask)) { - /* We were in lazy tlb mode and leave_mm disabled - * tlb flush IPI delivery. We must reload CR3 - * to make sure to use no freed page tables. - */ - load_cr3(next->pgd); - xen_new_user_pt(__pa(__user_pgd(next->pgd))); - load_LDT_nolock(&next->context, cpu); - } - } -#endif -} - -#define deactivate_mm(tsk,mm) do { \ - load_gs_index(0); \ - asm volatile("movl %0,%%fs"::"r"(0)); \ -} while(0) - -#define activate_mm(prev, next) do { \ - switch_mm((prev),(next),NULL); \ -} while (0) - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/nmi.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/nmi.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,75 +0,0 @@ -/* - * linux/include/asm-i386/nmi.h - */ -#ifndef ASM_NMI_H -#define ASM_NMI_H - -#include <linux/pm.h> - -#include <asm-xen/xen-public/nmi.h> - -struct pt_regs; - -typedef int (*nmi_callback_t)(struct pt_regs * regs, int cpu); - -/** - * set_nmi_callback - * - * Set a handler for an NMI. Only one handler may be - * set. Return 1 if the NMI was handled. - */ -void set_nmi_callback(nmi_callback_t callback); - -/** - * unset_nmi_callback - * - * Remove the handler previously set. - */ -void unset_nmi_callback(void); - -#ifdef CONFIG_PM - -/** Replace the PM callback routine for NMI. */ -struct pm_dev * set_nmi_pm_callback(pm_callback callback); - -/** Unset the PM callback routine back to the default. */ -void unset_nmi_pm_callback(struct pm_dev * dev); - -#else - -static inline struct pm_dev * set_nmi_pm_callback(pm_callback callback) -{ - return 0; -} - -static inline void unset_nmi_pm_callback(struct pm_dev * dev) -{ -} - -#endif /* CONFIG_PM */ - -extern void default_do_nmi(struct pt_regs *); -extern void die_nmi(char *str, struct pt_regs *regs); - -static inline unsigned char get_nmi_reason(void) -{ - shared_info_t *s = HYPERVISOR_shared_info; - unsigned char reason = 0; - - /* construct a value which looks like it came from - * port 0x61. - */ - if (test_bit(_XEN_NMIREASON_io_error, &s->arch.nmi_reason)) - reason |= 0x40; - if (test_bit(_XEN_NMIREASON_parity_error, &s->arch.nmi_reason)) - reason |= 0x80; - - return reason; -} - -extern int panic_on_timeout; -extern int unknown_nmi_panic; - -extern int check_nmi_watchdog(void); - -#endif /* ASM_NMI_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/page.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/page.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,260 +0,0 @@ -#ifndef _X86_64_PAGE_H -#define _X86_64_PAGE_H - -#include <linux/config.h> -/* #include <linux/string.h> */ -#ifndef __ASSEMBLY__ -#include <linux/types.h> -#endif -#include <asm-xen/xen-public/xen.h> -#include <asm-xen/foreign_page.h> - -#define arch_free_page(_page,_order) \ -({ int foreign = PageForeign(_page); \ - if (foreign) \ - (PageForeignDestructor(_page))(_page); \ - foreign; \ -}) -#define HAVE_ARCH_FREE_PAGE - -#ifdef CONFIG_XEN_SCRUB_PAGES -#define scrub_pages(_p,_n) memset((void *)(_p), 0, (_n) << PAGE_SHIFT) -#else -#define scrub_pages(_p,_n) ((void)0) -#endif - -/* PAGE_SHIFT determines the page size */ -#define PAGE_SHIFT 12 -#ifdef __ASSEMBLY__ -#define PAGE_SIZE (0x1 << PAGE_SHIFT) -#else -#define PAGE_SIZE (1UL << PAGE_SHIFT) -#endif -#define PAGE_MASK (~(PAGE_SIZE-1)) -#define PHYSICAL_PAGE_MASK (~(PAGE_SIZE-1) & (__PHYSICAL_MASK << PAGE_SHIFT)) - -#define THREAD_ORDER 1 -#ifdef __ASSEMBLY__ -#define THREAD_SIZE (1 << (PAGE_SHIFT + THREAD_ORDER)) -#else -#define THREAD_SIZE (1UL << (PAGE_SHIFT + THREAD_ORDER)) -#endif -#define CURRENT_MASK (~(THREAD_SIZE-1)) - -#define LARGE_PAGE_MASK (~(LARGE_PAGE_SIZE-1)) -#define LARGE_PAGE_SIZE (1UL << PMD_SHIFT) - -#define HPAGE_SHIFT PMD_SHIFT -#define HPAGE_SIZE ((1UL) << HPAGE_SHIFT) -#define HPAGE_MASK (~(HPAGE_SIZE - 1)) -#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) - -#ifdef __KERNEL__ -#ifndef __ASSEMBLY__ - -void clear_page(void *); -void copy_page(void *, void *); - -#define clear_user_page(page, vaddr, pg) clear_page(page) -#define copy_user_page(to, from, vaddr, pg) copy_page(to, from) - -#define alloc_zeroed_user_highpage(vma, vaddr) alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vma, vaddr) -#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE - -/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/ -#define INVALID_P2M_ENTRY (~0UL) -#define FOREIGN_FRAME(m) ((m) | (1UL<<63)) -extern unsigned long *phys_to_machine_mapping; -#define pfn_to_mfn(pfn) \ -(phys_to_machine_mapping[(unsigned int)(pfn)] & ~(1UL << 63)) -#define phys_to_machine_mapping_valid(pfn) \ - (phys_to_machine_mapping[pfn] != INVALID_P2M_ENTRY) -static inline unsigned long mfn_to_pfn(unsigned long mfn) -{ - unsigned long pfn; - - /* - * The array access can fail (e.g., device space beyond end of RAM). - * In such cases it doesn't matter what we return (we return garbage), - * but we must handle the fault without crashing! - */ - asm ( - "1: movq %1,%0\n" - "2:\n" - ".section __ex_table,\"a\"\n" - " .align 8\n" - " .quad 1b,2b\n" - ".previous" - : "=r" (pfn) : "m" (machine_to_phys_mapping[mfn]) ); - - return pfn; -} - -static inline void set_phys_to_machine(unsigned long pfn, unsigned long mfn) -{ - phys_to_machine_mapping[pfn] = mfn; -} - -/* Definitions for machine and pseudophysical addresses. */ -typedef unsigned long paddr_t; -typedef unsigned long maddr_t; - -static inline maddr_t phys_to_machine(paddr_t phys) -{ - maddr_t machine = pfn_to_mfn(phys >> PAGE_SHIFT); - machine = (machine << PAGE_SHIFT) | (phys & ~PAGE_MASK); - return machine; -} - -static inline paddr_t machine_to_phys(maddr_t machine) -{ - paddr_t phys = mfn_to_pfn(machine >> PAGE_SHIFT); - phys = (phys << PAGE_SHIFT) | (machine & ~PAGE_MASK); - return phys; -} - -/* - * These are used to make use of C type-checking.. - */ -typedef struct { unsigned long pte; } pte_t; -typedef struct { unsigned long pmd; } pmd_t; -typedef struct { unsigned long pud; } pud_t; -typedef struct { unsigned long pgd; } pgd_t; -#define PTE_MASK PHYSICAL_PAGE_MASK - -typedef struct { unsigned long pgprot; } pgprot_t; - -#define pte_val(x) (((x).pte & 1) ? machine_to_phys((x).pte) : \ - (x).pte) -#define pte_val_ma(x) ((x).pte) - -static inline unsigned long pmd_val(pmd_t x) -{ - unsigned long ret = x.pmd; - if (ret) ret = machine_to_phys(ret); - return ret; -} - -static inline unsigned long pud_val(pud_t x) -{ - unsigned long ret = x.pud; - if (ret) ret = machine_to_phys(ret); - return ret; -} - -static inline unsigned long pgd_val(pgd_t x) -{ - unsigned long ret = x.pgd; - if (ret) ret = machine_to_phys(ret); - return ret; -} - -#define pgprot_val(x) ((x).pgprot) - -#define __pte_ma(x) ((pte_t) { (x) } ) - -static inline pte_t __pte(unsigned long x) -{ - if (x & 1) x = phys_to_machine(x); - return ((pte_t) { (x) }); -} - -static inline pmd_t __pmd(unsigned long x) -{ - if ((x & 1)) x = phys_to_machine(x); - return ((pmd_t) { (x) }); -} - -static inline pud_t __pud(unsigned long x) -{ - if ((x & 1)) x = phys_to_machine(x); - return ((pud_t) { (x) }); -} - -static inline pgd_t __pgd(unsigned long x) -{ - if ((x & 1)) x = phys_to_machine(x); - return ((pgd_t) { (x) }); -} - -#define __pgprot(x) ((pgprot_t) { (x) } ) - -#define __START_KERNEL 0xffffffff80100000UL -#define __START_KERNEL_map 0xffffffff80000000UL -#define __PAGE_OFFSET 0xffff880000000000UL - -#else -#define __START_KERNEL 0xffffffff80100000 -#define __START_KERNEL_map 0xffffffff80000000 -#define __PAGE_OFFSET 0xffff880000000000 -#endif /* !__ASSEMBLY__ */ - -/* to align the pointer to the (next) page boundary */ -#define PAGE_ALIGN(addr) (((addr)+PAGE_SIZE-1)&PAGE_MASK) - -/* See Documentation/x86_64/mm.txt for a description of the memory map. */ -#define __PHYSICAL_MASK_SHIFT 46 -#define __PHYSICAL_MASK ((1UL << __PHYSICAL_MASK_SHIFT) - 1) -#define __VIRTUAL_MASK_SHIFT 48 -#define __VIRTUAL_MASK ((1UL << __VIRTUAL_MASK_SHIFT) - 1) - -#define KERNEL_TEXT_SIZE (40UL*1024*1024) -#define KERNEL_TEXT_START 0xffffffff80000000UL - -#ifndef __ASSEMBLY__ - -#include <asm/bug.h> - -/* Pure 2^n version of get_order */ -extern __inline__ int get_order(unsigned long size) -{ - int order; - - size = (size-1) >> (PAGE_SHIFT-1); - order = -1; - do { - size >>= 1; - order++; - } while (size); - return order; -} - -#endif /* __ASSEMBLY__ */ - -#define PAGE_OFFSET ((unsigned long)__PAGE_OFFSET) - -/* Note: __pa(&symbol_visible_to_c) should be always replaced with __pa_symbol. - Otherwise you risk miscompilation. */ -#define __pa(x) (((unsigned long)(x)>=__START_KERNEL_map)?(unsigned long)(x) - (unsigned long)__START_KERNEL_map:(unsigned long)(x) - PAGE_OFFSET) -/* __pa_symbol should be used for C visible symbols. - This seems to be the official gcc blessed way to do such arithmetic. */ -#define __pa_symbol(x) \ - ({unsigned long v; \ - asm("" : "=r" (v) : "0" (x)); \ - __pa(v); }) - -#define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET)) -#ifndef CONFIG_DISCONTIGMEM -#define pfn_to_page(pfn) (mem_map + (pfn)) -#define page_to_pfn(page) ((unsigned long)((page) - mem_map)) -#define pfn_valid(pfn) ((pfn) < max_mapnr) -#endif - -#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) -#define virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT) -#define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) - -/* VIRT <-> MACHINE conversion */ -#define virt_to_machine(v) (phys_to_machine(__pa(v))) -#define virt_to_mfn(v) (pfn_to_mfn(__pa(v) >> PAGE_SHIFT)) -#define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) - -#define VM_DATA_DEFAULT_FLAGS \ - (((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \ - VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) - -#define __HAVE_ARCH_GATE_AREA 1 - -#endif /* __KERNEL__ */ - -#endif /* _X86_64_PAGE_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/param.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/param.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,22 +0,0 @@ -#ifndef _ASMx86_64_PARAM_H -#define _ASMx86_64_PARAM_H - -#ifdef __KERNEL__ -# define HZ 100 /* Internal kernel timer frequency */ -# define USER_HZ 100 /* .. some user interfaces are in "ticks" */ -# define CLOCKS_PER_SEC (USER_HZ) /* like times() */ -#endif - -#ifndef HZ -#define HZ 100 -#endif - -#define EXEC_PAGESIZE 4096 - -#ifndef NOGROUP -#define NOGROUP (-1) -#endif - -#define MAXHOSTNAMELEN 64 /* max length of hostname */ - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/pci.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/pci.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,167 +0,0 @@ -#ifndef __x8664_PCI_H -#define __x8664_PCI_H - -#include <linux/config.h> -#include <asm/io.h> - -#ifdef __KERNEL__ - -#include <linux/mm.h> /* for struct page */ - -/* Can be used to override the logic in pci_scan_bus for skipping - already-configured bus numbers - to be used for buggy BIOSes - or architectures with incomplete PCI setup by the loader */ - -#ifdef CONFIG_PCI -extern unsigned int pcibios_assign_all_busses(void); -#else -#define pcibios_assign_all_busses() 0 -#endif -#define pcibios_scan_all_fns(a, b) 0 - -extern int no_iommu, force_iommu; - -extern unsigned long pci_mem_start; -#define PCIBIOS_MIN_IO 0x1000 -#define PCIBIOS_MIN_MEM (pci_mem_start) - -#define PCIBIOS_MIN_CARDBUS_IO 0x4000 - -void pcibios_config_init(void); -struct pci_bus * pcibios_scan_root(int bus); -extern int (*pci_config_read)(int seg, int bus, int dev, int fn, int reg, int len, u32 *value); -extern int (*pci_config_write)(int seg, int bus, int dev, int fn, int reg, int len, u32 value); - -void pcibios_set_master(struct pci_dev *dev); -void pcibios_penalize_isa_irq(int irq); -struct irq_routing_table *pcibios_get_irq_routing_table(void); -int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq); - -#include <linux/types.h> -#include <linux/slab.h> -#include <asm/scatterlist.h> -#include <linux/string.h> -#include <asm/page.h> - -extern int iommu_setup(char *opt); - -#ifdef CONFIG_GART_IOMMU -/* The PCI address space does equal the physical memory - * address space. The networking and block device layers use - * this boolean for bounce buffer decisions - * - * On AMD64 it mostly equals, but we set it to zero to tell some subsystems - * that an IOMMU is available. - */ -#define PCI_DMA_BUS_IS_PHYS (no_iommu ? 1 : 0) - -/* - * x86-64 always supports DAC, but sometimes it is useful to force - * devices through the IOMMU to get automatic sg list merging. - * Optional right now. - */ -extern int iommu_sac_force; -#define pci_dac_dma_supported(pci_dev, mask) (!iommu_sac_force) - -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ - dma_addr_t ADDR_NAME; -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \ - __u32 LEN_NAME; -#define pci_unmap_addr(PTR, ADDR_NAME) \ - ((PTR)->ADDR_NAME) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ - (((PTR)->ADDR_NAME) = (VAL)) -#define pci_unmap_len(PTR, LEN_NAME) \ - ((PTR)->LEN_NAME) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ - (((PTR)->LEN_NAME) = (VAL)) - -#elif defined(CONFIG_SWIOTLB) - -#define PCI_DMA_BUS_IS_PHYS 0 - -#define pci_dac_dma_supported(pci_dev, mask) 1 - -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) \ - dma_addr_t ADDR_NAME; -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) \ - __u32 LEN_NAME; -#define pci_unmap_addr(PTR, ADDR_NAME) \ - ((PTR)->ADDR_NAME) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \ - (((PTR)->ADDR_NAME) = (VAL)) -#define pci_unmap_len(PTR, LEN_NAME) \ - ((PTR)->LEN_NAME) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \ - (((PTR)->LEN_NAME) = (VAL)) - -#else -/* No IOMMU */ - -#define PCI_DMA_BUS_IS_PHYS 1 -#define pci_dac_dma_supported(pci_dev, mask) 1 - -#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME) -#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) -#define pci_unmap_addr(PTR, ADDR_NAME) (0) -#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) do { } while (0) -#define pci_unmap_len(PTR, LEN_NAME) (0) -#define pci_unmap_len_set(PTR, LEN_NAME, VAL) do { } while (0) - -#endif - -#include <asm-generic/pci-dma-compat.h> - -static inline dma64_addr_t -pci_dac_page_to_dma(struct pci_dev *pdev, struct page *page, unsigned long offset, int direction) -{ - return ((dma64_addr_t) page_to_phys(page) + - (dma64_addr_t) offset); -} - -static inline struct page * -pci_dac_dma_to_page(struct pci_dev *pdev, dma64_addr_t dma_addr) -{ - return virt_to_page(__va(dma_addr)); -} - -static inline unsigned long -pci_dac_dma_to_offset(struct pci_dev *pdev, dma64_addr_t dma_addr) -{ - return (dma_addr & ~PAGE_MASK); -} - -static inline void -pci_dac_dma_sync_single_for_cpu(struct pci_dev *pdev, dma64_addr_t dma_addr, size_t len, int direction) -{ -} - -static inline void -pci_dac_dma_sync_single_for_device(struct pci_dev *pdev, dma64_addr_t dma_addr, size_t len, int direction) -{ - flush_write_buffers(); -} - -#define HAVE_PCI_MMAP -extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, - enum pci_mmap_state mmap_state, int write_combine); - -static inline void pcibios_add_platform_entries(struct pci_dev *dev) -{ -} - -#endif /* __KERNEL__ */ - -/* generic pci stuff */ -#ifdef CONFIG_PCI -#include <asm-generic/pci.h> -#endif - -/* On Xen we have to scan all functions since Xen hides bridges from - * us. If a bridge is at fn=0 and that slot has a multifunction - * device, we won't find the additional devices without scanning all - * functions. */ -#undef pcibios_scan_all_fns -#define pcibios_scan_all_fns(a, b) 1 - -#endif /* __x8664_PCI_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/pgalloc.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/pgalloc.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,199 +0,0 @@ -#ifndef _X86_64_PGALLOC_H -#define _X86_64_PGALLOC_H - -#include <asm/fixmap.h> -#include <asm/pda.h> -#include <linux/threads.h> -#include <linux/mm.h> -#include <asm/io.h> /* for phys_to_virt and page_to_pseudophys */ - -#include <asm-xen/features.h> -void make_page_readonly(void *va, unsigned int feature); -void make_page_writable(void *va, unsigned int feature); -void make_pages_readonly(void *va, unsigned int nr, unsigned int feature); -void make_pages_writable(void *va, unsigned int nr, unsigned int feature); - -#define __user_pgd(pgd) ((pgd) + PTRS_PER_PGD) - -static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte) -{ - set_pmd(pmd, __pmd(_PAGE_TABLE | __pa(pte))); -} - -static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte) -{ - if (unlikely((mm)->context.pinned)) { - BUG_ON(HYPERVISOR_update_va_mapping( - (unsigned long)__va(page_to_pfn(pte) << PAGE_SHIFT), - pfn_pte(page_to_pfn(pte), PAGE_KERNEL_RO), 0)); - set_pmd(pmd, __pmd(_PAGE_TABLE | (page_to_pfn(pte) << PAGE_SHIFT))); - } else { - *(pmd) = __pmd(_PAGE_TABLE | (page_to_pfn(pte) << PAGE_SHIFT)); - } -} - -static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) -{ - if (unlikely((mm)->context.pinned)) { - BUG_ON(HYPERVISOR_update_va_mapping( - (unsigned long)pmd, - pfn_pte(virt_to_phys(pmd)>>PAGE_SHIFT, - PAGE_KERNEL_RO), 0)); - set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd))); - } else { - *(pud) = __pud(_PAGE_TABLE | __pa(pmd)); - } -} - -/* - * We need to use the batch mode here, but pgd_pupulate() won't be - * be called frequently. - */ -static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud) -{ - if (unlikely((mm)->context.pinned)) { - BUG_ON(HYPERVISOR_update_va_mapping( - (unsigned long)pud, - pfn_pte(virt_to_phys(pud)>>PAGE_SHIFT, - PAGE_KERNEL_RO), 0)); - set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(pud))); - set_pgd(__user_pgd(pgd), __pgd(_PAGE_TABLE | __pa(pud))); - } else { - *(pgd) = __pgd(_PAGE_TABLE | __pa(pud)); - *(__user_pgd(pgd)) = *(pgd); - } -} - -extern __inline__ void pmd_free(pmd_t *pmd) -{ - pte_t *ptep = virt_to_ptep(pmd); - - if (!pte_write(*ptep)) { - BUG_ON(HYPERVISOR_update_va_mapping( - (unsigned long)pmd, - pfn_pte(virt_to_phys(pmd)>>PAGE_SHIFT, PAGE_KERNEL), - 0)); - } - free_page((unsigned long)pmd); -} - -static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - pmd_t *pmd = (pmd_t *) get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); - return pmd; -} - -static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) -{ - pud_t *pud = (pud_t *) get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); - return pud; -} - -static inline void pud_free(pud_t *pud) -{ - pte_t *ptep = virt_to_ptep(pud); - - if (!pte_write(*ptep)) { - BUG_ON(HYPERVISOR_update_va_mapping( - (unsigned long)pud, - pfn_pte(virt_to_phys(pud)>>PAGE_SHIFT, PAGE_KERNEL), - 0)); - } - free_page((unsigned long)pud); -} - -static inline pgd_t *pgd_alloc(struct mm_struct *mm) -{ - /* - * We allocate two contiguous pages for kernel and user. - */ - unsigned boundary; - pgd_t *pgd = (pgd_t *)__get_free_pages(GFP_KERNEL|__GFP_REPEAT, 1); - - if (!pgd) - return NULL; - /* - * Copy kernel pointers in from init. - * Could keep a freelist or slab cache of those because the kernel - * part never changes. - */ - boundary = pgd_index(__PAGE_OFFSET); - memset(pgd, 0, boundary * sizeof(pgd_t)); - memcpy(pgd + boundary, - init_level4_pgt + boundary, - (PTRS_PER_PGD - boundary) * sizeof(pgd_t)); - - memset(__user_pgd(pgd), 0, PAGE_SIZE); /* clean up user pgd */ - /* - * Set level3_user_pgt for vsyscall area - */ - set_pgd(__user_pgd(pgd) + pgd_index(VSYSCALL_START), - mk_kernel_pgd(__pa_symbol(level3_user_pgt))); - return pgd; -} - -static inline void pgd_free(pgd_t *pgd) -{ - pte_t *ptep = virt_to_ptep(pgd); - - if (!pte_write(*ptep)) { - xen_pgd_unpin(__pa(pgd)); - BUG_ON(HYPERVISOR_update_va_mapping( - (unsigned long)pgd, - pfn_pte(virt_to_phys(pgd)>>PAGE_SHIFT, PAGE_KERNEL), - 0)); - } - - ptep = virt_to_ptep(__user_pgd(pgd)); - - if (!pte_write(*ptep)) { - xen_pgd_unpin(__pa(__user_pgd(pgd))); - BUG_ON(HYPERVISOR_update_va_mapping( - (unsigned long)__user_pgd(pgd), - pfn_pte(virt_to_phys(__user_pgd(pgd))>>PAGE_SHIFT, - PAGE_KERNEL), - 0)); - } - - free_pages((unsigned long)pgd, 1); -} - -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) -{ - pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT); - if (pte) - make_page_readonly(pte, XENFEAT_writable_page_tables); - - return pte; -} - -static inline struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address) -{ - struct page *pte; - - pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO, 0); - return pte; -} - -/* Should really implement gc for free page table pages. This could be - done with a reference count in struct page. */ - -extern __inline__ void pte_free_kernel(pte_t *pte) -{ - BUG_ON((unsigned long)pte & (PAGE_SIZE-1)); - xen_pte_unpin(__pa(pte)); - make_page_writable(pte, XENFEAT_writable_page_tables); - free_page((unsigned long)pte); -} - -extern void pte_free(struct page *pte); - -//#define __pte_free_tlb(tlb,pte) tlb_remove_page((tlb),(pte)) -//#define __pmd_free_tlb(tlb,x) tlb_remove_page((tlb),virt_to_page(x)) -//#define __pud_free_tlb(tlb,x) tlb_remove_page((tlb),virt_to_page(x)) - -#define __pte_free_tlb(tlb,x) pte_free((x)) -#define __pmd_free_tlb(tlb,x) pmd_free((x)) -#define __pud_free_tlb(tlb,x) pud_free((x)) - -#endif /* _X86_64_PGALLOC_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/pgtable.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/pgtable.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,570 +0,0 @@ -#ifndef _X86_64_PGTABLE_H -#define _X86_64_PGTABLE_H - -/* - * This file contains the functions and defines necessary to modify and use - * the x86-64 page table tree. - */ -#include <asm/processor.h> -#include <asm/fixmap.h> -#include <asm/bitops.h> -#include <linux/threads.h> -#include <linux/sched.h> -#include <asm/pda.h> -#ifdef CONFIG_XEN -#include <asm/hypervisor.h> - -extern pud_t level3_user_pgt[512]; -extern pud_t init_level4_user_pgt[]; - -extern void xen_init_pt(void); - -#define virt_to_ptep(__va) \ -({ \ - pgd_t *__pgd = pgd_offset_k((unsigned long)(__va)); \ - pud_t *__pud = pud_offset(__pgd, (unsigned long)(__va)); \ - pmd_t *__pmd = pmd_offset(__pud, (unsigned long)(__va)); \ - pte_offset_kernel(__pmd, (unsigned long)(__va)); \ -}) - -#define arbitrary_virt_to_machine(__va) \ -({ \ - maddr_t m = (maddr_t)pte_mfn(*virt_to_ptep(__va)) << PAGE_SHIFT;\ - m | ((unsigned long)(__va) & (PAGE_SIZE-1)); \ -}) -#endif - -extern pud_t level3_kernel_pgt[512]; -extern pud_t level3_physmem_pgt[512]; -extern pud_t level3_ident_pgt[512]; -extern pmd_t level2_kernel_pgt[512]; -extern pgd_t init_level4_pgt[]; -extern unsigned long __supported_pte_mask; - -#define swapper_pg_dir init_level4_pgt - -extern int nonx_setup(char *str); -extern void paging_init(void); -extern void clear_kernel_mapping(unsigned long addr, unsigned long size); - -extern unsigned long pgkern_mask; - -/* - * ZERO_PAGE is a global shared page that is always zero: used - * for zero-mapped memory areas etc.. - */ -extern unsigned long empty_zero_page[PAGE_SIZE/sizeof(unsigned long)]; -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) - -/* - * PGDIR_SHIFT determines what a top-level page table entry can map - */ -#define PGDIR_SHIFT 39 -#define PTRS_PER_PGD 512 - -/* - * 3rd level page - */ -#define PUD_SHIFT 30 -#define PTRS_PER_PUD 512 - -/* - * PMD_SHIFT determines the size of the area a middle-level - * page table can map - */ -#define PMD_SHIFT 21 -#define PTRS_PER_PMD 512 - -/* - * entries per page directory level - */ -#define PTRS_PER_PTE 512 - -#define pte_ERROR(e) \ - printk("%s:%d: bad pte %p(%016lx).\n", __FILE__, __LINE__, &(e), pte_val(e)) -#define pmd_ERROR(e) \ - printk("%s:%d: bad pmd %p(%016lx).\n", __FILE__, __LINE__, &(e), pmd_val(e)) -#define pud_ERROR(e) \ - printk("%s:%d: bad pud %p(%016lx).\n", __FILE__, __LINE__, &(e), pud_val(e)) -#define pgd_ERROR(e) \ - printk("%s:%d: bad pgd %p(%016lx).\n", __FILE__, __LINE__, &(e), pgd_val(e)) - -#define pgd_none(x) (!pgd_val(x)) -#define pud_none(x) (!pud_val(x)) - -#define set_pte_batched(pteptr, pteval) \ - queue_l1_entry_update(pteptr, (pteval)) - -extern inline int pud_present(pud_t pud) { return !pud_none(pud); } - -static inline void set_pte(pte_t *dst, pte_t val) -{ - *dst = val; -} - -#define set_pmd(pmdptr, pmdval) xen_l2_entry_update(pmdptr, (pmdval)) -#define set_pud(pudptr, pudval) xen_l3_entry_update(pudptr, (pudval)) -#define set_pgd(pgdptr, pgdval) xen_l4_entry_update(pgdptr, (pgdval)) - -extern inline void pud_clear (pud_t * pud) -{ - set_pud(pud, __pud(0)); -} - -#define __user_pgd(pgd) ((pgd) + PTRS_PER_PGD) - -extern inline void pgd_clear (pgd_t * pgd) -{ - set_pgd(pgd, __pgd(0)); - set_pgd(__user_pgd(pgd), __pgd(0)); -} - -#define pud_page(pud) \ - ((unsigned long) __va(pud_val(pud) & PHYSICAL_PAGE_MASK)) - -/* - * A note on implementation of this atomic 'get-and-clear' operation. - * This is actually very simple because Xen Linux can only run on a single - * processor. Therefore, we cannot race other processors setting the 'accessed' - * or 'dirty' bits on a page-table entry. - * Even if pages are shared between domains, that is not a problem because - * each domain will have separate page tables, with their own versions of - * accessed & dirty state. - */ -#define ptep_get_and_clear(mm,addr,xp) __pte_ma(xchg(&(xp)->pte, 0)) - -#if 0 -static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *xp) -{ - pte_t pte = *xp; - if (pte.pte) - set_pte(xp, __pte_ma(0)); - return pte; -} -#endif - -#define pte_same(a, b) ((a).pte == (b).pte) - -#define PMD_SIZE (1UL << PMD_SHIFT) -#define PMD_MASK (~(PMD_SIZE-1)) -#define PUD_SIZE (1UL << PUD_SHIFT) -#define PUD_MASK (~(PUD_SIZE-1)) -#define PGDIR_SIZE (1UL << PGDIR_SHIFT) -#define PGDIR_MASK (~(PGDIR_SIZE-1)) - -#define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE) -#define FIRST_USER_ADDRESS 0 - -#ifndef __ASSEMBLY__ -#define MAXMEM 0x3fffffffffffUL -#define VMALLOC_START 0xffffc20000000000UL -#define VMALLOC_END 0xffffe1ffffffffffUL -#define MODULES_VADDR 0xffffffff88000000UL -#define MODULES_END 0xfffffffffff00000UL -#define MODULES_LEN (MODULES_END - MODULES_VADDR) - -#define _PAGE_BIT_PRESENT 0 -#define _PAGE_BIT_RW 1 -#define _PAGE_BIT_USER 2 -#define _PAGE_BIT_PWT 3 -#define _PAGE_BIT_PCD 4 -#define _PAGE_BIT_ACCESSED 5 -#define _PAGE_BIT_DIRTY 6 -#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */ -#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */ -#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ - -#define _PAGE_PRESENT 0x001 -#define _PAGE_RW 0x002 -#define _PAGE_USER 0x004 -#define _PAGE_PWT 0x008 -#define _PAGE_PCD 0x010 -#define _PAGE_ACCESSED 0x020 -#define _PAGE_DIRTY 0x040 -#define _PAGE_PSE 0x080 /* 2MB page */ -#define _PAGE_FILE 0x040 /* set:pagecache, unset:swap */ -#define _PAGE_GLOBAL 0x100 /* Global TLB entry */ - -#define _PAGE_PROTNONE 0x080 /* If not present */ -#define _PAGE_NX (1UL<<_PAGE_BIT_NX) - -#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY) -#define _KERNPG_TABLE _PAGE_TABLE - -#define _PAGE_CHG_MASK (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY) - -#define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED) -#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX) -#define PAGE_SHARED_EXEC __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED) -#define PAGE_COPY_NOEXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX) -#define PAGE_COPY PAGE_COPY_NOEXEC -#define PAGE_COPY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED) -#define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX) -#define PAGE_READONLY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED) -#define __PAGE_KERNEL \ - (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX | _PAGE_USER ) -#define __PAGE_KERNEL_EXEC \ - (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_USER ) -#define __PAGE_KERNEL_NOCACHE \ - (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_PCD | _PAGE_ACCESSED | _PAGE_NX | _PAGE_USER ) -#define __PAGE_KERNEL_RO \ - (_PAGE_PRESENT | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX | _PAGE_USER ) -#define __PAGE_KERNEL_VSYSCALL \ - (_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_USER ) -#define __PAGE_KERNEL_VSYSCALL_NOCACHE \ - (_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_PCD | _PAGE_USER ) -#define __PAGE_KERNEL_LARGE \ - (__PAGE_KERNEL | _PAGE_PSE | _PAGE_USER ) - - -/* - * We don't support GLOBAL page in xenolinux64 - */ -#define MAKE_GLOBAL(x) __pgprot((x)) - -#define PAGE_KERNEL MAKE_GLOBAL(__PAGE_KERNEL) -#define PAGE_KERNEL_EXEC MAKE_GLOBAL(__PAGE_KERNEL_EXEC) -#define PAGE_KERNEL_RO MAKE_GLOBAL(__PAGE_KERNEL_RO) -#define PAGE_KERNEL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE) -#define PAGE_KERNEL_VSYSCALL32 __pgprot(__PAGE_KERNEL_VSYSCALL) -#define PAGE_KERNEL_VSYSCALL MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL) -#define PAGE_KERNEL_LARGE MAKE_GLOBAL(__PAGE_KERNEL_LARGE) -#define PAGE_KERNEL_VSYSCALL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL_NOCACHE) - -/* xwr */ -#define __P000 PAGE_NONE -#define __P001 PAGE_READONLY -#define __P010 PAGE_COPY -#define __P011 PAGE_COPY -#define __P100 PAGE_READONLY_EXEC -#define __P101 PAGE_READONLY_EXEC -#define __P110 PAGE_COPY_EXEC -#define __P111 PAGE_COPY_EXEC - -#define __S000 PAGE_NONE -#define __S001 PAGE_READONLY -#define __S010 PAGE_SHARED -#define __S011 PAGE_SHARED -#define __S100 PAGE_READONLY_EXEC -#define __S101 PAGE_READONLY_EXEC -#define __S110 PAGE_SHARED_EXEC -#define __S111 PAGE_SHARED_EXEC - -static inline unsigned long pgd_bad(pgd_t pgd) -{ - unsigned long val = pgd_val(pgd); - val &= ~PTE_MASK; - val &= ~(_PAGE_USER | _PAGE_DIRTY); - return val & ~(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED); -} - -static inline unsigned long pud_bad(pud_t pud) -{ - unsigned long val = pud_val(pud); - val &= ~PTE_MASK; - val &= ~(_PAGE_USER | _PAGE_DIRTY); - return val & ~(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED); -} - -#define set_pte_at(_mm,addr,ptep,pteval) do { \ - if (((_mm) != current->mm && (_mm) != &init_mm) || \ - HYPERVISOR_update_va_mapping((addr), (pteval), 0)) \ - set_pte((ptep), (pteval)); \ -} while (0) - -#define pte_none(x) (!(x).pte) -#define pte_present(x) ((x).pte & (_PAGE_PRESENT | _PAGE_PROTNONE)) -#define pte_clear(mm,addr,xp) do { set_pte_at(mm, addr, xp, __pte(0)); } while (0) - -#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT)) - -/* - * We detect special mappings in one of two ways: - * 1. If the MFN is an I/O page then Xen will set the m2p entry - * to be outside our maximum possible pseudophys range. - * 2. If the MFN belongs to a different domain then we will certainly - * not have MFN in our p2m table. Conversely, if the page is ours, - * then we'll have p2m(m2p(MFN))==MFN. - * If we detect a special mapping then it doesn't have a 'struct page'. - * We force !pfn_valid() by returning an out-of-range pointer. - * - * NB. These checks require that, for any MFN that is not in our reservation, - * there is no PFN such that p2m(PFN) == MFN. Otherwise we can get confused if - * we are foreign-mapping the MFN, and the other domain as m2p(MFN) == PFN. - * Yikes! Various places must poke in INVALID_P2M_ENTRY for safety. - * - * NB2. When deliberately mapping foreign pages into the p2m table, you *must* - * use FOREIGN_FRAME(). This will cause pte_pfn() to choke on it, as we - * require. In all the cases we care about, the FOREIGN_FRAME bit is - * masked (e.g., pfn_to_mfn()) so behaviour there is correct. - */ -#define pte_mfn(_pte) (((_pte).pte & PTE_MASK) >> PAGE_SHIFT) -#define pte_pfn(_pte) \ -({ \ - unsigned long mfn = pte_mfn(_pte); \ - unsigned long pfn = mfn_to_pfn(mfn); \ - if ((pfn >= max_mapnr) || (phys_to_machine_mapping[pfn] != mfn))\ - pfn = max_mapnr; /* special: force !pfn_valid() */ \ - pfn; \ -}) - -#define pte_page(x) pfn_to_page(pte_pfn(x)) - -static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) -{ - pte_t pte; - - (pte).pte = (pfn_to_mfn(page_nr) << PAGE_SHIFT); - (pte).pte |= pgprot_val(pgprot); - (pte).pte &= __supported_pte_mask; - return pte; -} - -#define pfn_pte_ma(pfn, prot) __pte_ma((((pfn) << PAGE_SHIFT) | pgprot_val(prot)) & __supported_pte_mask) -/* - * The following only work if pte_present() is true. - * Undefined behaviour if not.. - */ -#define __pte_val(x) ((x).pte) - -static inline int pte_user(pte_t pte) { return __pte_val(pte) & _PAGE_USER; } -extern inline int pte_read(pte_t pte) { return __pte_val(pte) & _PAGE_USER; } -extern inline int pte_exec(pte_t pte) { return __pte_val(pte) & _PAGE_USER; } -extern inline int pte_dirty(pte_t pte) { return __pte_val(pte) & _PAGE_DIRTY; } -extern inline int pte_young(pte_t pte) { return __pte_val(pte) & _PAGE_ACCESSED; } -extern inline int pte_write(pte_t pte) { return __pte_val(pte) & _PAGE_RW; } -static inline int pte_file(pte_t pte) { return __pte_val(pte) & _PAGE_FILE; } - -extern inline pte_t pte_rdprotect(pte_t pte) { __pte_val(pte) &= ~_PAGE_USER; return pte; } -extern inline pte_t pte_exprotect(pte_t pte) { __pte_val(pte) &= ~_PAGE_USER; return pte; } -extern inline pte_t pte_mkclean(pte_t pte) { __pte_val(pte) &= ~_PAGE_DIRTY; return pte; } -extern inline pte_t pte_mkold(pte_t pte) { __pte_val(pte) &= ~_PAGE_ACCESSED; return pte; } -extern inline pte_t pte_wrprotect(pte_t pte) { __pte_val(pte) &= ~_PAGE_RW; return pte; } -extern inline pte_t pte_mkread(pte_t pte) { __pte_val(pte) |= _PAGE_USER; return pte; } -extern inline pte_t pte_mkexec(pte_t pte) { __pte_val(pte) |= _PAGE_USER; return pte; } -extern inline pte_t pte_mkdirty(pte_t pte) { __pte_val(pte) |= _PAGE_DIRTY; return pte; } -extern inline pte_t pte_mkyoung(pte_t pte) { __pte_val(pte) |= _PAGE_ACCESSED; return pte; } -extern inline pte_t pte_mkwrite(pte_t pte) { __pte_val(pte) |= _PAGE_RW; return pte; } - -struct vm_area_struct; - -static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) -{ - pte_t pte = *ptep; - int ret = pte_dirty(pte); - if (ret) - set_pte(ptep, pte_mkclean(pte)); - return ret; -} - -static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) -{ - pte_t pte = *ptep; - int ret = pte_young(pte); - if (ret) - set_pte(ptep, pte_mkold(pte)); - return ret; -} - -static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) -{ - pte_t pte = *ptep; - if (pte_write(pte)) - set_pte(ptep, pte_wrprotect(pte)); -} - -/* - * Macro to mark a page protection value as "uncacheable". - */ -#define pgprot_noncached(prot) (__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT)) - -#define __LARGE_PTE (_PAGE_PSE|_PAGE_PRESENT) -static inline int pmd_large(pmd_t pte) { - return (pmd_val(pte) & __LARGE_PTE) == __LARGE_PTE; -} - - -/* - * Conversion functions: convert a page and protection to a page entry, - * and a page entry and page directory to the page they refer to. - */ - -#define page_pte(page) page_pte_prot(page, __pgprot(0)) - -/* - * Level 4 access. - * Never use these in the common code. - */ -#define pgd_page(pgd) ((unsigned long) __va(pgd_val(pgd) & PTE_MASK)) -#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1)) -#define pgd_offset(mm, addr) ((mm)->pgd + pgd_index(addr)) -#define pgd_offset_k(address) (pgd_t *)(init_level4_pgt + pgd_index(address)) -#define pgd_present(pgd) (pgd_val(pgd) & _PAGE_PRESENT) -#define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE) - -/* PUD - Level3 access */ -/* to find an entry in a page-table-directory. */ -#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) -#define pud_offset(pgd, address) ((pud_t *) pgd_page(*(pgd)) + pud_index(address)) -static inline pud_t *__pud_offset_k(pud_t *pud, unsigned long address) -{ - return pud + pud_index(address); -} - -/* Find correct pud via the hidden fourth level page level: */ - -/* This accesses the reference page table of the boot cpu. - Other CPUs get synced lazily via the page fault handler. */ -static inline pud_t *pud_offset_k(unsigned long address) -{ - return pud_offset(pgd_offset_k(address), address); -} - -/* PMD - Level 2 access */ -#define pmd_page_kernel(pmd) ((unsigned long) __va(pmd_val(pmd) & PTE_MASK)) -#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)) - -#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1)) -#define pmd_offset(dir, address) ((pmd_t *) pud_page(*(dir)) + \ - pmd_index(address)) -#define pmd_none(x) (!pmd_val(x)) -/* pmd_present doesn't just test the _PAGE_PRESENT bit since wr.p.t. - can temporarily clear it. */ -#define pmd_present(x) (pmd_val(x)) -#define pmd_clear(xp) do { set_pmd(xp, __pmd(0)); } while (0) -#define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_PRESENT)) != (_KERNPG_TABLE & ~_PAGE_PRESENT)) -#define pfn_pmd(nr,prot) (__pmd(((nr) << PAGE_SHIFT) | pgprot_val(prot))) -#define pmd_pfn(x) ((pmd_val(x) >> PAGE_SHIFT) & __PHYSICAL_MASK) - -#define pte_to_pgoff(pte) ((pte_val(pte) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT) -#define pgoff_to_pte(off) ((pte_t) { ((off) << PAGE_SHIFT) | _PAGE_FILE }) -#define PTE_FILE_MAX_BITS __PHYSICAL_MASK_SHIFT - -/* PTE - Level 1 access. */ - -/* page, protection -> pte */ -#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot)) -#define mk_pte_huge(entry) (pte_val(entry) |= _PAGE_PRESENT | _PAGE_PSE) - -/* physical address -> PTE */ -static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot) -{ - pte_t pte; - (pte).pte = physpage | pgprot_val(pgprot); - return pte; -} - -/* Change flags of a PTE */ -extern inline pte_t pte_modify(pte_t pte, pgprot_t newprot) -{ - (pte).pte &= _PAGE_CHG_MASK; - (pte).pte |= pgprot_val(newprot); - (pte).pte &= __supported_pte_mask; - return pte; -} - -#define pte_index(address) \ - ((address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)) -#define pte_offset_kernel(dir, address) ((pte_t *) pmd_page_kernel(*(dir)) + \ - pte_index(address)) - -/* x86-64 always has all page tables mapped. */ -#define pte_offset_map(dir,address) pte_offset_kernel(dir,address) -#define pte_offset_map_nested(dir,address) pte_offset_kernel(dir,address) -#define pte_unmap(pte) /* NOP */ -#define pte_unmap_nested(pte) /* NOP */ - -#define update_mmu_cache(vma,address,pte) do { } while (0) - -/* We only update the dirty/accessed state if we set - * the dirty bit by hand in the kernel, since the hardware - * will do the accessed bit for us, and we don't want to - * race with other CPU's that might be updating the dirty - * bit at the same time. */ -#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS -#if 0 -#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \ - do { \ - if (__dirty) { \ - set_pte(__ptep, __entry); \ - flush_tlb_page(__vma, __address); \ - } \ - } while (0) -#endif -#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \ - do { \ - if (__dirty) { \ - if ( likely((__vma)->vm_mm == current->mm) ) { \ - BUG_ON(HYPERVISOR_update_va_mapping((__address), (__entry), UVMF_INVLPG|UVMF_MULTI|(unsigned long)((__vma)->vm_mm->cpu_vm_mask.bits))); \ - } else { \ - xen_l1_entry_update((__ptep), (__entry)); \ - flush_tlb_page((__vma), (__address)); \ - } \ - } \ - } while (0) - -/* Encode and de-code a swap entry */ -#define __swp_type(x) (((x).val >> 1) & 0x3f) -#define __swp_offset(x) ((x).val >> 8) -#define __swp_entry(type, offset) ((swp_entry_t) { ((type) << 1) | ((offset) << 8) }) -#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) -#define __swp_entry_to_pte(x) ((pte_t) { (x).val }) - -#endif /* !__ASSEMBLY__ */ - -extern int kern_addr_valid(unsigned long addr); - -#define DOMID_LOCAL (0xFFFFU) - -int direct_remap_pfn_range(struct vm_area_struct *vma, - unsigned long address, - unsigned long mfn, - unsigned long size, - pgprot_t prot, - domid_t domid); - -int direct_kernel_remap_pfn_range(unsigned long address, - unsigned long mfn, - unsigned long size, - pgprot_t prot, - domid_t domid); - -int create_lookup_pte_addr(struct mm_struct *mm, - unsigned long address, - uint64_t *ptep); - -int touch_pte_range(struct mm_struct *mm, - unsigned long address, - unsigned long size); - -#define io_remap_page_range(vma, vaddr, paddr, size, prot) \ - direct_remap_pfn_range(vma,vaddr,(paddr)>>PAGE_SHIFT,size,prot,DOMID_IO) - -#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \ - direct_remap_pfn_range(vma,vaddr,pfn,size,prot,DOMID_IO) - -#define MK_IOSPACE_PFN(space, pfn) (pfn) -#define GET_IOSPACE(pfn) 0 -#define GET_PFN(pfn) (pfn) - -#define HAVE_ARCH_UNMAPPED_AREA - -#define pgtable_cache_init() do { } while (0) -#define check_pgt_cache() do { } while (0) - -#define PAGE_AGP PAGE_KERNEL_NOCACHE -#define HAVE_PAGE_AGP 1 - -/* fs/proc/kcore.c */ -#define kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK) -#define kc_offset_to_vaddr(o) \ - (((o) & (1UL << (__VIRTUAL_MASK_SHIFT-1))) ? ((o) | (~__VIRTUAL_MASK)) : (o)) - -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG -#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY -#define __HAVE_ARCH_PTEP_GET_AND_CLEAR -#define __HAVE_ARCH_PTEP_SET_WRPROTECT -#define __HAVE_ARCH_PTE_SAME -#include <asm-generic/pgtable.h> - -#endif /* _X86_64_PGTABLE_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/processor.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/processor.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,486 +0,0 @@ -/* - * include/asm-x86_64/processor.h - * - * Copyright (C) 1994 Linus Torvalds - */ - -#ifndef __ASM_X86_64_PROCESSOR_H -#define __ASM_X86_64_PROCESSOR_H - -#include <asm/segment.h> -#include <asm/page.h> -#include <asm/types.h> -#include <asm/sigcontext.h> -#include <asm/cpufeature.h> -#include <linux/config.h> -#include <linux/threads.h> -#include <asm/msr.h> -#include <asm/current.h> -#include <asm/system.h> -#include <asm/mmsegment.h> -#include <asm/percpu.h> -#include <linux/personality.h> - -#define TF_MASK 0x00000100 -#define IF_MASK 0x00000200 -#define IOPL_MASK 0x00003000 -#define NT_MASK 0x00004000 -#define VM_MASK 0x00020000 -#define AC_MASK 0x00040000 -#define VIF_MASK 0x00080000 /* virtual interrupt flag */ -#define VIP_MASK 0x00100000 /* virtual interrupt pending */ -#define ID_MASK 0x00200000 - -#define desc_empty(desc) \ - (!((desc)->a + (desc)->b)) - -#define desc_equal(desc1, desc2) \ - (((desc1)->a == (desc2)->a) && ((desc1)->b == (desc2)->b)) - -/* - * Default implementation of macro that returns current - * instruction pointer ("program counter"). - */ -#define current_text_addr() ({ void *pc; asm volatile("leaq 1f(%%rip),%0\n1:":"=r"(pc)); pc; }) - -/* - * CPU type and hardware bug flags. Kept separately for each CPU. - */ - -struct cpuinfo_x86 { - __u8 x86; /* CPU family */ - __u8 x86_vendor; /* CPU vendor */ - __u8 x86_model; - __u8 x86_mask; - int cpuid_level; /* Maximum supported CPUID level, -1=no CPUID */ - __u32 x86_capability[NCAPINTS]; - char x86_vendor_id[16]; - char x86_model_id[64]; - int x86_cache_size; /* in KB */ - int x86_clflush_size; - int x86_cache_alignment; - int x86_tlbsize; /* number of 4K pages in DTLB/ITLB combined(in pages)*/ - __u8 x86_virt_bits, x86_phys_bits; - __u8 x86_num_cores; - __u32 x86_power; - __u32 extended_cpuid_level; /* Max extended CPUID function supported */ - unsigned long loops_per_jiffy; -} ____cacheline_aligned; - -#define X86_VENDOR_INTEL 0 -#define X86_VENDOR_CYRIX 1 -#define X86_VENDOR_AMD 2 -#define X86_VENDOR_UMC 3 -#define X86_VENDOR_NEXGEN 4 -#define X86_VENDOR_CENTAUR 5 -#define X86_VENDOR_RISE 6 -#define X86_VENDOR_TRANSMETA 7 -#define X86_VENDOR_NUM 8 -#define X86_VENDOR_UNKNOWN 0xff - -#ifdef CONFIG_SMP -extern struct cpuinfo_x86 cpu_data[]; -#define current_cpu_data cpu_data[smp_processor_id()] -#else -#define cpu_data (&boot_cpu_data) -#define current_cpu_data boot_cpu_data -#endif - -extern char ignore_irq13; - -extern void identify_cpu(struct cpuinfo_x86 *); -extern void print_cpu_info(struct cpuinfo_x86 *); -extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c); - -/* - * EFLAGS bits - */ -#define X86_EFLAGS_CF 0x00000001 /* Carry Flag */ -#define X86_EFLAGS_PF 0x00000004 /* Parity Flag */ -#define X86_EFLAGS_AF 0x00000010 /* Auxillary carry Flag */ -#define X86_EFLAGS_ZF 0x00000040 /* Zero Flag */ -#define X86_EFLAGS_SF 0x00000080 /* Sign Flag */ -#define X86_EFLAGS_TF 0x00000100 /* Trap Flag */ -#define X86_EFLAGS_IF 0x00000200 /* Interrupt Flag */ -#define X86_EFLAGS_DF 0x00000400 /* Direction Flag */ -#define X86_EFLAGS_OF 0x00000800 /* Overflow Flag */ -#define X86_EFLAGS_IOPL 0x00003000 /* IOPL mask */ -#define X86_EFLAGS_NT 0x00004000 /* Nested Task */ -#define X86_EFLAGS_RF 0x00010000 /* Resume Flag */ -#define X86_EFLAGS_VM 0x00020000 /* Virtual Mode */ -#define X86_EFLAGS_AC 0x00040000 /* Alignment Check */ -#define X86_EFLAGS_VIF 0x00080000 /* Virtual Interrupt Flag */ -#define X86_EFLAGS_VIP 0x00100000 /* Virtual Interrupt Pending */ -#define X86_EFLAGS_ID 0x00200000 /* CPUID detection flag */ - -/* - * Intel CPU features in CR4 - */ -#define X86_CR4_VME 0x0001 /* enable vm86 extensions */ -#define X86_CR4_PVI 0x0002 /* virtual interrupts flag enable */ -#define X86_CR4_TSD 0x0004 /* disable time stamp at ipl 3 */ -#define X86_CR4_DE 0x0008 /* enable debugging extensions */ -#define X86_CR4_PSE 0x0010 /* enable page size extensions */ -#define X86_CR4_PAE 0x0020 /* enable physical address extensions */ -#define X86_CR4_MCE 0x0040 /* Machine check enable */ -#define X86_CR4_PGE 0x0080 /* enable global pages */ -#define X86_CR4_PCE 0x0100 /* enable performance counters at ipl 3 */ -#define X86_CR4_OSFXSR 0x0200 /* enable fast FPU save and restore */ -#define X86_CR4_OSXMMEXCPT 0x0400 /* enable unmasked SSE exceptions */ - -/* - * Save the cr4 feature set we're using (ie - * Pentium 4MB enable and PPro Global page - * enable), so that any CPU's that boot up - * after us can get the correct flags. - */ -extern unsigned long mmu_cr4_features; - -static inline void set_in_cr4 (unsigned long mask) -{ - mmu_cr4_features |= mask; - switch (mask) { - case X86_CR4_OSFXSR: - case X86_CR4_OSXMMEXCPT: - break; - default: - do { - const char *msg = "Xen unsupported cr4 update\n"; - (void)HYPERVISOR_console_io( - CONSOLEIO_write, __builtin_strlen(msg), - (char *)msg); - BUG(); - } while (0); - } -} - - -static inline void clear_in_cr4 (unsigned long mask) -{ -#ifndef CONFIG_XEN - mmu_cr4_features &= ~mask; - __asm__("movq %%cr4,%%rax\n\t" - "andq %0,%%rax\n\t" - "movq %%rax,%%cr4\n" - : : "irg" (~mask) - :"ax"); -#endif -} - - -#define load_cr3(pgdir) do { \ - xen_pt_switch(__pa(pgdir)); \ - per_cpu(cur_pgd, smp_processor_id()) = pgdir; \ -} while (/* CONSTCOND */0) - -/* - * Bus types - */ -#define MCA_bus 0 -#define MCA_bus__is_a_macro - - -/* - * User space process size. 47bits minus one guard page. - */ -#define TASK_SIZE (0x800000000000UL - 4096) - -/* This decides where the kernel will search for a free chunk of vm - * space during mmap's. - */ -#define IA32_PAGE_OFFSET ((current->personality & ADDR_LIMIT_3GB) ? 0xc0000000 : 0xFFFFe000) -#define TASK_UNMAPPED_32 PAGE_ALIGN(IA32_PAGE_OFFSET/3) -#define TASK_UNMAPPED_64 PAGE_ALIGN(TASK_SIZE/3) -#define TASK_UNMAPPED_BASE \ - (test_thread_flag(TIF_IA32) ? TASK_UNMAPPED_32 : TASK_UNMAPPED_64) - -/* - * Size of io_bitmap. - */ -#define IO_BITMAP_BITS 65536 -#define IO_BITMAP_BYTES (IO_BITMAP_BITS/8) -#define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long)) -#define IO_BITMAP_OFFSET offsetof(struct tss_struct,io_bitmap) -#define INVALID_IO_BITMAP_OFFSET 0x8000 - -struct i387_fxsave_struct { - u16 cwd; - u16 swd; - u16 twd; - u16 fop; - u64 rip; - u64 rdp; - u32 mxcsr; - u32 mxcsr_mask; - u32 st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */ - u32 xmm_space[64]; /* 16*16 bytes for each XMM-reg = 128 bytes */ - u32 padding[24]; -} __attribute__ ((aligned (16))); - -union i387_union { - struct i387_fxsave_struct fxsave; -}; - -struct tss_struct { - u32 reserved1; - u64 rsp0; - u64 rsp1; - u64 rsp2; - u64 reserved2; - u64 ist[7]; - u32 reserved3; - u32 reserved4; - u16 reserved5; - u16 io_bitmap_base; - /* - * The extra 1 is there because the CPU will access an - * additional byte beyond the end of the IO permission - * bitmap. The extra byte must be all 1 bits, and must - * be within the limit. Thus we have: - * - * 128 bytes, the bitmap itself, for ports 0..0x3ff - * 8 bytes, for an extra "long" of ~0UL - */ - unsigned long io_bitmap[IO_BITMAP_LONGS + 1]; -} __attribute__((packed)) ____cacheline_aligned; - -extern struct cpuinfo_x86 boot_cpu_data; -DECLARE_PER_CPU(struct tss_struct,init_tss); -DECLARE_PER_CPU(pgd_t *, cur_pgd); - -#define ARCH_MIN_TASKALIGN 16 - -struct thread_struct { - unsigned long rsp0; - unsigned long rsp; - unsigned long userrsp; /* Copy from PDA */ - unsigned long fs; - unsigned long gs; - unsigned int io_pl; - unsigned short es, ds, fsindex, gsindex; -/* Hardware debugging registers */ - unsigned long debugreg0; - unsigned long debugreg1; - unsigned long debugreg2; - unsigned long debugreg3; - unsigned long debugreg6; - unsigned long debugreg7; -/* fault info */ - unsigned long cr2, trap_no, error_code; -/* floating point info */ - union i387_union i387 __attribute__((aligned(16))); -/* IO permissions. the bitmap could be moved into the GDT, that would make - switch faster for a limited number of ioperm using tasks. -AK */ - int ioperm; - unsigned long *io_bitmap_ptr; - unsigned io_bitmap_max; -/* cached TLS descriptors. */ - u64 tls_array[GDT_ENTRY_TLS_ENTRIES]; -} __attribute__((aligned(16))); - -#define INIT_THREAD {} - -#define INIT_MMAP \ -{ &init_mm, 0, 0, NULL, PAGE_SHARED, VM_READ | VM_WRITE | VM_EXEC, 1, NULL, NULL } - -#define STACKFAULT_STACK 1 -#define DOUBLEFAULT_STACK 2 -#define NMI_STACK 3 -#define DEBUG_STACK 4 -#define MCE_STACK 5 -#define N_EXCEPTION_STACKS 5 /* hw limit: 7 */ -#define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER) -#define EXCEPTION_STACK_ORDER 0 - -#define start_thread(regs,new_rip,new_rsp) do { \ - asm volatile("movl %0,%%fs; movl %0,%%es; movl %0,%%ds": :"r" (0)); \ - load_gs_index(0); \ - (regs)->rip = (new_rip); \ - (regs)->rsp = (new_rsp); \ - write_pda(oldrsp, (new_rsp)); \ - (regs)->cs = __USER_CS; \ - (regs)->ss = __USER_DS; \ - (regs)->eflags = 0x200; \ - set_fs(USER_DS); \ -} while(0) - -struct task_struct; -struct mm_struct; - -/* Free all resources held by a thread. */ -extern void release_thread(struct task_struct *); - -/* Prepare to copy thread state - unlazy all lazy status */ -extern void prepare_to_copy(struct task_struct *tsk); - -/* - * create a kernel thread without removing it from tasklists - */ -extern long kernel_thread(int (*fn)(void *), void * arg, unsigned long flags); - -/* - * Return saved PC of a blocked thread. - * What is this good for? it will be always the scheduler or ret_from_fork. - */ -#define thread_saved_pc(t) (*(unsigned long *)((t)->thread.rsp - 8)) - -extern unsigned long get_wchan(struct task_struct *p); -#define KSTK_EIP(tsk) \ - (((struct pt_regs *)(tsk->thread.rsp0 - sizeof(struct pt_regs)))->rip) -#define KSTK_ESP(tsk) -1 /* sorry. doesn't work for syscall. */ - - -struct microcode_header { - unsigned int hdrver; - unsigned int rev; - unsigned int date; - unsigned int sig; - unsigned int cksum; - unsigned int ldrver; - unsigned int pf; - unsigned int datasize; - unsigned int totalsize; - unsigned int reserved[3]; -}; - -struct microcode { - struct microcode_header hdr; - unsigned int bits[0]; -}; - -typedef struct microcode microcode_t; -typedef struct microcode_header microcode_header_t; - -/* microcode format is extended from prescott processors */ -struct extended_signature { - unsigned int sig; - unsigned int pf; - unsigned int cksum; -}; - -struct extended_sigtable { - unsigned int count; - unsigned int cksum; - unsigned int reserved[3]; - struct extended_signature sigs[0]; -}; - -/* '6' because it used to be for P6 only (but now covers Pentium 4 as well) */ -#define MICROCODE_IOCFREE _IO('6',0) - - -#define ASM_NOP1 K8_NOP1 -#define ASM_NOP2 K8_NOP2 -#define ASM_NOP3 K8_NOP3 -#define ASM_NOP4 K8_NOP4 -#define ASM_NOP5 K8_NOP5 -#define ASM_NOP6 K8_NOP6 -#define ASM_NOP7 K8_NOP7 -#define ASM_NOP8 K8_NOP8 - -/* Opteron nops */ -#define K8_NOP1 ".byte 0x90\n" -#define K8_NOP2 ".byte 0x66,0x90\n" -#define K8_NOP3 ".byte 0x66,0x66,0x90\n" -#define K8_NOP4 ".byte 0x66,0x66,0x66,0x90\n" -#define K8_NOP5 K8_NOP3 K8_NOP2 -#define K8_NOP6 K8_NOP3 K8_NOP3 -#define K8_NOP7 K8_NOP4 K8_NOP3 -#define K8_NOP8 K8_NOP4 K8_NOP4 - -#define ASM_NOP_MAX 8 - -/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */ -extern inline void rep_nop(void) -{ - __asm__ __volatile__("rep;nop": : :"memory"); -} - -/* Stop speculative execution */ -extern inline void sync_core(void) -{ - int tmp; - asm volatile("cpuid" : "=a" (tmp) : "0" (1) : "ebx","ecx","edx","memory"); -} - -#define cpu_has_fpu 1 - -#define ARCH_HAS_PREFETCH -static inline void prefetch(void *x) -{ - asm volatile("prefetcht0 %0" :: "m" (*(unsigned long *)x)); -} - -#define ARCH_HAS_PREFETCHW 1 -static inline void prefetchw(void *x) -{ - alternative_input(ASM_NOP5, - "prefetchw (%1)", - X86_FEATURE_3DNOW, - "r" (x)); -} - -#define ARCH_HAS_SPINLOCK_PREFETCH 1 - -#define spin_lock_prefetch(x) prefetchw(x) - -#define cpu_relax() rep_nop() - -/* - * NSC/Cyrix CPU configuration register indexes - */ -#define CX86_CCR0 0xc0 -#define CX86_CCR1 0xc1 -#define CX86_CCR2 0xc2 -#define CX86_CCR3 0xc3 -#define CX86_CCR4 0xe8 -#define CX86_CCR5 0xe9 -#define CX86_CCR6 0xea -#define CX86_CCR7 0xeb -#define CX86_DIR0 0xfe -#define CX86_DIR1 0xff -#define CX86_ARR_BASE 0xc4 -#define CX86_RCR_BASE 0xdc - -/* - * NSC/Cyrix CPU indexed register access macros - */ - -#define getCx86(reg) ({ outb((reg), 0x22); inb(0x23); }) - -#define setCx86(reg, data) do { \ - outb((reg), 0x22); \ - outb((data), 0x23); \ -} while (0) - -static inline void __monitor(const void *eax, unsigned long ecx, - unsigned long edx) -{ - /* "monitor %eax,%ecx,%edx;" */ - asm volatile( - ".byte 0x0f,0x01,0xc8;" - : :"a" (eax), "c" (ecx), "d"(edx)); -} - -static inline void __mwait(unsigned long eax, unsigned long ecx) -{ - /* "mwait %eax,%ecx;" */ - asm volatile( - ".byte 0x0f,0x01,0xc9;" - : :"a" (eax), "c" (ecx)); -} - -#define stack_current() \ -({ \ - struct thread_info *ti; \ - asm("andq %%rsp,%0; ":"=r" (ti) : "0" (CURRENT_MASK)); \ - ti->task; \ -}) - -#define cache_line_size() (boot_cpu_data.x86_cache_alignment) - -extern unsigned long boot_option_idle_override; -/* Boot loader type from the setup header */ -extern int bootloader_type; - -#endif /* __ASM_X86_64_PROCESSOR_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/ptrace.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/ptrace.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,124 +0,0 @@ -#ifndef _X86_64_PTRACE_H -#define _X86_64_PTRACE_H - -#if defined(__ASSEMBLY__) || defined(__FRAME_OFFSETS) -#define R15 0 -#define R14 8 -#define R13 16 -#define R12 24 -#define RBP 32 -#define RBX 40 -/* arguments: interrupts/non tracing syscalls only save upto here*/ -#define R11 48 -#define R10 56 -#define R9 64 -#define R8 72 -#define RAX 80 -#define RCX 88 -#define RDX 96 -#define RSI 104 -#define RDI 112 -#define ORIG_RAX 120 /* = ERROR */ -/* end of arguments */ -/* cpu exception frame or undefined in case of fast syscall. */ -#define RIP 128 -#define CS 136 -#define EFLAGS 144 -#define RSP 152 -#define SS 160 -#define ARGOFFSET R11 -#endif /* __ASSEMBLY__ */ - -/* top of stack page */ -#define FRAME_SIZE 168 - -#define PTRACE_OLDSETOPTIONS 21 - -#ifndef __ASSEMBLY__ - -struct pt_regs { - unsigned long r15; - unsigned long r14; - unsigned long r13; - unsigned long r12; - unsigned long rbp; - unsigned long rbx; -/* arguments: non interrupts/non tracing syscalls only save upto here*/ - unsigned long r11; - unsigned long r10; - unsigned long r9; - unsigned long r8; - unsigned long rax; - unsigned long rcx; - unsigned long rdx; - unsigned long rsi; - unsigned long rdi; - unsigned long orig_rax; -/* end of arguments */ -/* cpu exception frame or undefined */ - unsigned long rip; - unsigned long cs; - unsigned long eflags; - unsigned long rsp; - unsigned long ss; -/* top of stack page */ -}; - -#endif - -/* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */ -#define PTRACE_GETREGS 12 -#define PTRACE_SETREGS 13 -#define PTRACE_GETFPREGS 14 -#define PTRACE_SETFPREGS 15 -#define PTRACE_GETFPXREGS 18 -#define PTRACE_SETFPXREGS 19 - -/* only useful for access 32bit programs */ -#define PTRACE_GET_THREAD_AREA 25 -#define PTRACE_SET_THREAD_AREA 26 - -#define PTRACE_ARCH_PRCTL 30 /* arch_prctl for child */ - -#if defined(__KERNEL__) && !defined(__ASSEMBLY__) -#define user_mode(regs) (!!((regs)->cs & 3)) -#define instruction_pointer(regs) ((regs)->rip) -#if defined(CONFIG_SMP) && defined(CONFIG_FRAME_POINTER) -extern unsigned long profile_pc(struct pt_regs *regs); -#else -#define profile_pc(regs) instruction_pointer(regs) -#endif - -void signal_fault(struct pt_regs *regs, void __user *frame, char *where); - -struct task_struct; - -extern unsigned long -convert_rip_to_linear(struct task_struct *child, struct pt_regs *regs); - -enum { - EF_CF = 0x00000001, - EF_PF = 0x00000004, - EF_AF = 0x00000010, - EF_ZF = 0x00000040, - EF_SF = 0x00000080, - EF_TF = 0x00000100, - EF_IE = 0x00000200, - EF_DF = 0x00000400, - EF_OF = 0x00000800, - EF_IOPL = 0x00003000, - EF_IOPL_RING0 = 0x00000000, - EF_IOPL_RING1 = 0x00001000, - EF_IOPL_RING2 = 0x00002000, - EF_NT = 0x00004000, /* nested task */ - EF_RF = 0x00010000, /* resume */ - EF_VM = 0x00020000, /* virtual mode */ - EF_AC = 0x00040000, /* alignment */ - EF_VIF = 0x00080000, /* virtual interrupt */ - EF_VIP = 0x00100000, /* virtual interrupt pending */ - EF_ID = 0x00200000, /* id */ -}; - -#endif - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/segment.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/segment.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,46 +0,0 @@ -#ifndef _ASM_SEGMENT_H -#define _ASM_SEGMENT_H - -#include <asm/cache.h> - -#define __KERNEL_CS 0x10 -#define __KERNEL_DS 0x1b - -#define __KERNEL32_CS 0x3b - -/* - * we cannot use the same code segment descriptor for user and kernel - * -- not even in the long flat mode, because of different DPL /kkeil - * The segment offset needs to contain a RPL. Grr. -AK - * GDT layout to get 64bit syscall right (sysret hardcodes gdt offsets) - */ - -#define __USER32_CS 0x23 /* 4*8+3 */ -#define __USER_DS 0x2b /* 5*8+3 */ -#define __USER_CS 0x33 /* 6*8+3 */ -#define __USER32_DS __USER_DS -#define __KERNEL16_CS (GDT_ENTRY_KERNELCS16 * 8) -#define __KERNEL_COMPAT32_CS 0x8 - -#define GDT_ENTRY_TLS 1 -#define GDT_ENTRY_TSS 8 /* needs two entries */ -#define GDT_ENTRY_LDT 10 /* needs two entries */ -#define GDT_ENTRY_TLS_MIN 12 -#define GDT_ENTRY_TLS_MAX 14 -#define GDT_ENTRY_KERNELCS16 15 - -#define GDT_ENTRY_TLS_ENTRIES 3 - -/* TLS indexes for 64bit - hardcoded in arch_prctl */ -#define FS_TLS 0 -#define GS_TLS 1 - -#define GS_TLS_SEL ((GDT_ENTRY_TLS_MIN+GS_TLS)*8 + 3) -#define FS_TLS_SEL ((GDT_ENTRY_TLS_MIN+FS_TLS)*8 + 3) - -#define IDT_ENTRIES 256 -#define GDT_ENTRIES 16 -#define GDT_SIZE (GDT_ENTRIES * 8) -#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8) - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/smp.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/smp.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,138 +0,0 @@ -#ifndef __ASM_SMP_H -#define __ASM_SMP_H - -/* - * We need the APIC definitions automatically as part of 'smp.h' - */ -#ifndef __ASSEMBLY__ -#include <linux/config.h> -#include <linux/threads.h> -#include <linux/cpumask.h> -#include <linux/bitops.h> -extern int disable_apic; -#endif - -#ifdef CONFIG_X86_LOCAL_APIC -#ifndef __ASSEMBLY__ -#include <asm/fixmap.h> -#include <asm/mpspec.h> -#ifdef CONFIG_X86_IO_APIC -#include <asm/io_apic.h> -#endif -#include <asm/apic.h> -#include <asm/thread_info.h> -#endif -#endif - -#ifdef CONFIG_SMP -#ifndef ASSEMBLY - -#include <asm/pda.h> - -struct pt_regs; - -extern cpumask_t cpu_present_mask; -extern cpumask_t cpu_possible_map; -extern cpumask_t cpu_online_map; - -/* - * Private routines/data - */ - -extern void smp_alloc_memory(void); -extern volatile unsigned long smp_invalidate_needed; -extern int pic_mode; -extern int smp_num_siblings; -extern void smp_flush_tlb(void); -extern void smp_message_irq(int cpl, void *dev_id, struct pt_regs *regs); -extern void smp_send_reschedule(int cpu); -extern void smp_invalidate_rcv(void); /* Process an NMI */ -extern void zap_low_mappings(void); -void smp_stop_cpu(void); -extern cpumask_t cpu_sibling_map[NR_CPUS]; -extern cpumask_t cpu_core_map[NR_CPUS]; -extern int phys_proc_id[NR_CPUS]; -extern int cpu_core_id[NR_CPUS]; - -#define SMP_TRAMPOLINE_BASE 0x6000 - -/* - * On x86 all CPUs are mapped 1:1 to the APIC space. - * This simplifies scheduling and IPI sending and - * compresses data structures. - */ - -static inline int num_booting_cpus(void) -{ - return cpus_weight(cpu_possible_map); -} - -#define __smp_processor_id() read_pda(cpunumber) - -#ifdef CONFIG_X86_LOCAL_APIC -extern __inline int hard_smp_processor_id(void) -{ - /* we don't want to mark this access volatile - bad code generation */ - return GET_APIC_ID(*(unsigned int *)(APIC_BASE+APIC_ID)); -} -#endif - -extern int safe_smp_processor_id(void); - -#endif /* !ASSEMBLY */ - -#define NO_PROC_ID 0xFF /* No processor magic marker */ - -#endif - -#ifndef ASSEMBLY -/* - * Some lowlevel functions might want to know about - * the real APIC ID <-> CPU # mapping. - */ -extern u8 x86_cpu_to_apicid[NR_CPUS]; /* physical ID */ -extern u8 x86_cpu_to_log_apicid[NR_CPUS]; -extern u8 bios_cpu_apicid[]; -#ifdef CONFIG_X86_LOCAL_APIC -static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask) -{ - return cpus_addr(cpumask)[0]; -} - -static inline int cpu_present_to_apicid(int mps_cpu) -{ - if (mps_cpu < NR_CPUS) - return (int)bios_cpu_apicid[mps_cpu]; - else - return BAD_APICID; -} -#endif - -#endif /* !ASSEMBLY */ - -#ifndef CONFIG_SMP -#define stack_smp_processor_id() 0 -#define safe_smp_processor_id() 0 -#define cpu_logical_map(x) (x) -#else -#include <asm/thread_info.h> -#define stack_smp_processor_id() \ -({ \ - struct thread_info *ti; \ - __asm__("andq %%rsp,%0; ":"=r" (ti) : "0" (CURRENT_MASK)); \ - ti->cpu; \ -}) -#endif - -#ifndef __ASSEMBLY__ -#ifdef CONFIG_X86_LOCAL_APIC -static __inline int logical_smp_processor_id(void) -{ - /* we don't want to mark this access volatile - bad code generation */ - return GET_APIC_LOGICAL_ID(*(unsigned long *)(APIC_BASE+APIC_LDR)); -} -#endif -#endif - -#endif - diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/synch_bitops.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/synch_bitops.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,2 +0,0 @@ - -#include <asm-i386/synch_bitops.h> diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/system.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/system.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,414 +0,0 @@ -#ifndef __ASM_SYSTEM_H -#define __ASM_SYSTEM_H - -#include <linux/config.h> -#include <linux/kernel.h> -#include <asm/segment.h> -#include <asm/synch_bitops.h> -#include <asm/hypervisor.h> -#include <asm-xen/xen-public/arch-x86_64.h> - -#ifdef __KERNEL__ - -#ifdef CONFIG_SMP -#define LOCK_PREFIX "lock ; " -#else -#define LOCK_PREFIX "" -#endif - -#define __STR(x) #x -#define STR(x) __STR(x) - -#define __SAVE(reg,offset) "movq %%" #reg ",(14-" #offset ")*8(%%rsp)\n\t" -#define __RESTORE(reg,offset) "movq (14-" #offset ")*8(%%rsp),%%" #reg "\n\t" - -/* frame pointer must be last for get_wchan */ -#define SAVE_CONTEXT "pushfq ; pushq %%rbp ; movq %%rsi,%%rbp\n\t" -#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popfq\n\t" - -#define __EXTRA_CLOBBER \ - ,"rcx","rbx","rdx","r8","r9","r10","r11","r12","r13","r14","r15" - -#define switch_to(prev,next,last) \ - asm volatile(SAVE_CONTEXT \ - "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \ - "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \ - "call __switch_to\n\t" \ - ".globl thread_return\n" \ - "thread_return:\n\t" \ - "movq %%gs:%P[pda_pcurrent],%%rsi\n\t" \ - "movq %P[thread_info](%%rsi),%%r8\n\t" \ - LOCK "btr %[tif_fork],%P[ti_flags](%%r8)\n\t" \ - "movq %%rax,%%rdi\n\t" \ - "jc ret_from_fork\n\t" \ - RESTORE_CONTEXT \ - : "=a" (last) \ - : [next] "S" (next), [prev] "D" (prev), \ - [threadrsp] "i" (offsetof(struct task_struct, thread.rsp)), \ - [ti_flags] "i" (offsetof(struct thread_info, flags)),\ - [tif_fork] "i" (TIF_FORK), \ - [thread_info] "i" (offsetof(struct task_struct, thread_info)), \ - [pda_pcurrent] "i" (offsetof(struct x8664_pda, pcurrent)) \ - : "memory", "cc" __EXTRA_CLOBBER) - - -extern void load_gs_index(unsigned); - -/* - * Load a segment. Fall back on loading the zero - * segment if something goes wrong.. - */ -#define loadsegment(seg,value) \ - asm volatile("\n" \ - "1:\t" \ - "movl %k0,%%" #seg "\n" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3:\t" \ - "movl %1,%%" #seg "\n\t" \ - "jmp 2b\n" \ - ".previous\n" \ - ".section __ex_table,\"a\"\n\t" \ - ".align 8\n\t" \ - ".quad 1b,3b\n" \ - ".previous" \ - : :"r" (value), "r" (0)) - -#define set_debug(value,register) \ - __asm__("movq %0,%%db" #register \ - : /* no output */ \ - :"r" ((unsigned long) value)) - - -#ifdef __KERNEL__ -struct alt_instr { - __u8 *instr; /* original instruction */ - __u8 *replacement; - __u8 cpuid; /* cpuid bit set for replacement */ - __u8 instrlen; /* length of original instruction */ - __u8 replacementlen; /* length of new instruction, <= instrlen */ - __u8 pad[5]; -}; -#endif - -/* - * Alternative instructions for different CPU types or capabilities. - * - * This allows to use optimized instructions even on generic binary - * kernels. - * - * length of oldinstr must be longer or equal the length of newinstr - * It can be padded with nops as needed. - * - * For non barrier like inlines please define new variants - * without volatile and memory clobber. - */ -#define alternative(oldinstr, newinstr, feature) \ - asm volatile ("661:\n\t" oldinstr "\n662:\n" \ - ".section .altinstructions,\"a\"\n" \ - " .align 8\n" \ - " .quad 661b\n" /* label */ \ - " .quad 663f\n" /* new instruction */ \ - " .byte %c0\n" /* feature bit */ \ - " .byte 662b-661b\n" /* sourcelen */ \ - " .byte 664f-663f\n" /* replacementlen */ \ - ".previous\n" \ - ".section .altinstr_replacement,\"ax\"\n" \ - "663:\n\t" newinstr "\n664:\n" /* replacement */ \ - ".previous" :: "i" (feature) : "memory") - -/* - * Alternative inline assembly with input. - * - * Pecularities: - * No memory clobber here. - * Argument numbers start with 1. - * Best is to use constraints that are fixed size (like (%1) ... "r") - * If you use variable sized constraints like "m" or "g" in the - * replacement maake sure to pad to the worst case length. - */ -#define alternative_input(oldinstr, newinstr, feature, input...) \ - asm volatile ("661:\n\t" oldinstr "\n662:\n" \ - ".section .altinstructions,\"a\"\n" \ - " .align 8\n" \ - " .quad 661b\n" /* label */ \ - " .quad 663f\n" /* new instruction */ \ - " .byte %c0\n" /* feature bit */ \ - " .byte 662b-661b\n" /* sourcelen */ \ - " .byte 664f-663f\n" /* replacementlen */ \ - ".previous\n" \ - ".section .altinstr_replacement,\"ax\"\n" \ - "663:\n\t" newinstr "\n664:\n" /* replacement */ \ - ".previous" :: "i" (feature), ##input) - -/* - * Clear and set 'TS' bit respectively - */ -#define clts() (HYPERVISOR_fpu_taskswitch(0)) - -static inline unsigned long read_cr0(void) -{ - unsigned long cr0; - asm volatile("movq %%cr0,%0" : "=r" (cr0)); - return cr0; -} - -static inline void write_cr0(unsigned long val) -{ - asm volatile("movq %0,%%cr0" :: "r" (val)); -} - -static inline unsigned long read_cr3(void) -{ - unsigned long cr3; - asm("movq %%cr3,%0" : "=r" (cr3)); - return cr3; -} - -static inline unsigned long read_cr4(void) -{ - unsigned long cr4; - asm("movq %%cr4,%0" : "=r" (cr4)); - return cr4; -} - -static inline void write_cr4(unsigned long val) -{ - asm volatile("movq %0,%%cr4" :: "r" (val)); -} - -#define stts() (HYPERVISOR_fpu_taskswitch(1)) - -#define wbinvd() \ - __asm__ __volatile__ ("wbinvd": : :"memory"); - -#endif /* __KERNEL__ */ - -#define nop() __asm__ __volatile__ ("nop") - -#define xchg(ptr,v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v),(ptr),sizeof(*(ptr)))) - -#define tas(ptr) (xchg((ptr),1)) - -#define __xg(x) ((volatile long *)(x)) - -extern inline void set_64bit(volatile unsigned long *ptr, unsigned long val) -{ - *ptr = val; -} - -#define _set_64bit set_64bit - -/* - * Note: no "lock" prefix even on SMP: xchg always implies lock anyway - * Note 2: xchg has side effect, so that attribute volatile is necessary, - * but generally the primitive is invalid, *ptr is output argument. --ANK - */ -static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size) -{ - switch (size) { - case 1: - __asm__ __volatile__("xchgb %b0,%1" - :"=q" (x) - :"m" (*__xg(ptr)), "0" (x) - :"memory"); - break; - case 2: - __asm__ __volatile__("xchgw %w0,%1" - :"=r" (x) - :"m" (*__xg(ptr)), "0" (x) - :"memory"); - break; - case 4: - __asm__ __volatile__("xchgl %k0,%1" - :"=r" (x) - :"m" (*__xg(ptr)), "0" (x) - :"memory"); - break; - case 8: - __asm__ __volatile__("xchgq %0,%1" - :"=r" (x) - :"m" (*__xg(ptr)), "0" (x) - :"memory"); - break; - } - return x; -} - -/* - * Atomic compare and exchange. Compare OLD with MEM, if identical, - * store NEW in MEM. Return the initial value in MEM. Success is - * indicated by comparing RETURN with OLD. - */ - -#define __HAVE_ARCH_CMPXCHG 1 - -static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old, - unsigned long new, int size) -{ - unsigned long prev; - switch (size) { - case 1: - __asm__ __volatile__(LOCK_PREFIX "cmpxchgb %b1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 2: - __asm__ __volatile__(LOCK_PREFIX "cmpxchgw %w1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 4: - __asm__ __volatile__(LOCK_PREFIX "cmpxchgl %k1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - case 8: - __asm__ __volatile__(LOCK_PREFIX "cmpxchgq %1,%2" - : "=a"(prev) - : "q"(new), "m"(*__xg(ptr)), "0"(old) - : "memory"); - return prev; - } - return old; -} - -#define cmpxchg(ptr,o,n)\ - ((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\ - (unsigned long)(n),sizeof(*(ptr)))) - -#ifdef CONFIG_SMP -#define smp_mb() mb() -#define smp_rmb() rmb() -#define smp_wmb() wmb() -#define smp_read_barrier_depends() do {} while(0) -#else -#define smp_mb() barrier() -#define smp_rmb() barrier() -#define smp_wmb() barrier() -#define smp_read_barrier_depends() do {} while(0) -#endif - - -/* - * Force strict CPU ordering. - * And yes, this is required on UP too when we're talking - * to devices. - */ -#define mb() asm volatile("mfence":::"memory") -#define rmb() asm volatile("lfence":::"memory") - -#ifdef CONFIG_UNORDERED_IO -#define wmb() asm volatile("sfence" ::: "memory") -#else -#define wmb() asm volatile("" ::: "memory") -#endif -#define read_barrier_depends() do {} while(0) -#define set_mb(var, value) do { xchg(&var, value); } while (0) -#define set_wmb(var, value) do { var = value; wmb(); } while (0) - -#define warn_if_not_ulong(x) do { unsigned long foo; (void) (&(x) == &foo); } while (0) - - -/* - * The use of 'barrier' in the following reflects their use as local-lock - * operations. Reentrancy must be prevented (e.g., __cli()) /before/ following - * critical operations are executed. All critical operations must complete - * /before/ reentrancy is permitted (e.g., __sti()). Alpha architecture also - * includes these barriers, for example. - */ - -#define __cli() \ -do { \ - vcpu_info_t *_vcpu; \ - preempt_disable(); \ - _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ - _vcpu->evtchn_upcall_mask = 1; \ - preempt_enable_no_resched(); \ - barrier(); \ -} while (0) - -#define __sti() \ -do { \ - vcpu_info_t *_vcpu; \ - barrier(); \ - preempt_disable(); \ - _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ - _vcpu->evtchn_upcall_mask = 0; \ - barrier(); /* unmask then check (avoid races) */ \ - if ( unlikely(_vcpu->evtchn_upcall_pending) ) \ - force_evtchn_callback(); \ - preempt_enable(); \ -} while (0) - -#define __save_flags(x) \ -do { \ - vcpu_info_t *_vcpu; \ - preempt_disable(); \ - _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ - (x) = _vcpu->evtchn_upcall_mask; \ - preempt_enable(); \ -} while (0) - -#define __restore_flags(x) \ -do { \ - vcpu_info_t *_vcpu; \ - barrier(); \ - preempt_disable(); \ - _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ - if ((_vcpu->evtchn_upcall_mask = (x)) == 0) { \ - barrier(); /* unmask then check (avoid races) */ \ - if ( unlikely(_vcpu->evtchn_upcall_pending) ) \ - force_evtchn_callback(); \ - preempt_enable(); \ - } else \ - preempt_enable_no_resched(); \ -} while (0) - -#define safe_halt() ((void)0) - -#define __save_and_cli(x) \ -do { \ - vcpu_info_t *_vcpu; \ - preempt_disable(); \ - _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ - (x) = _vcpu->evtchn_upcall_mask; \ - _vcpu->evtchn_upcall_mask = 1; \ - preempt_enable_no_resched(); \ - barrier(); \ -} while (0) - -void cpu_idle_wait(void); - -#define local_irq_save(x) __save_and_cli(x) -#define local_irq_restore(x) __restore_flags(x) -#define local_save_flags(x) __save_flags(x) -#define local_irq_disable() __cli() -#define local_irq_enable() __sti() - -/* Cannot use preempt_enable() here as we would recurse in preempt_sched(). */ -#define irqs_disabled() \ -({ int ___x; \ - vcpu_info_t *_vcpu; \ - preempt_disable(); \ - _vcpu = &HYPERVISOR_shared_info->vcpu_info[smp_processor_id()]; \ - ___x = (_vcpu->evtchn_upcall_mask != 0); \ - preempt_enable_no_resched(); \ - ___x; }) - -/* - * disable hlt during certain critical i/o operations - */ -#define HAVE_DISABLE_HLT -void disable_hlt(void); -void enable_hlt(void); - -#define HAVE_EAT_KEY -void eat_key(void); - -extern unsigned long arch_align_stack(unsigned long sp); - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/timer.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/timer.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,64 +0,0 @@ -#ifndef _ASMi386_TIMER_H -#define _ASMi386_TIMER_H -#include <linux/init.h> - -/** - * struct timer_ops - used to define a timer source - * - * @name: name of the timer. - * @init: Probes and initializes the timer. Takes clock= override - * string as an argument. Returns 0 on success, anything else - * on failure. - * @mark_offset: called by the timer interrupt. - * @get_offset: called by gettimeofday(). Returns the number of microseconds - * since the last timer interupt. - * @monotonic_clock: returns the number of nanoseconds since the init of the - * timer. - * @delay: delays this many clock cycles. - */ -struct timer_opts { - char* name; - void (*mark_offset)(void); - unsigned long (*get_offset)(void); - unsigned long long (*monotonic_clock)(void); - void (*delay)(unsigned long); -}; - -struct init_timer_opts { - int (*init)(char *override); - struct timer_opts *opts; -}; - -#define TICK_SIZE (tick_nsec / 1000) - -extern struct timer_opts* __init select_timer(void); -extern void clock_fallback(void); -void setup_pit_timer(void); - -/* Modifiers for buggy PIT handling */ - -extern int pit_latch_buggy; - -extern struct timer_opts *cur_timer; -extern int timer_ack; - -/* list of externed timers */ -extern struct timer_opts timer_none; -extern struct timer_opts timer_pit; -extern struct init_timer_opts timer_pit_init; -extern struct init_timer_opts timer_tsc_init; -#ifdef CONFIG_X86_CYCLONE_TIMER -extern struct init_timer_opts timer_cyclone_init; -#endif - -extern unsigned long calibrate_tsc(void); -extern void init_cpu_khz(void); -#ifdef CONFIG_HPET_TIMER -extern struct init_timer_opts timer_hpet_init; -extern unsigned long calibrate_tsc_hpet(unsigned long *tsc_hpet_quotient_ptr); -#endif - -#ifdef CONFIG_X86_PM_TIMER -extern struct init_timer_opts timer_pmtmr_init; -#endif -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/tlbflush.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/tlbflush.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,97 +0,0 @@ -#ifndef _X8664_TLBFLUSH_H -#define _X8664_TLBFLUSH_H - -#include <linux/config.h> -#include <linux/mm.h> -#include <asm/processor.h> - -#define __flush_tlb() xen_tlb_flush() - -/* - * Global pages have to be flushed a bit differently. Not a real - * performance problem because this does not happen often. - */ -#define __flush_tlb_global() xen_tlb_flush() - - -extern unsigned long pgkern_mask; - -#define __flush_tlb_all() __flush_tlb_global() - -#define __flush_tlb_one(addr) xen_invlpg((unsigned long)addr) - - -/* - * TLB flushing: - * - * - flush_tlb() flushes the current mm struct TLBs - * - flush_tlb_all() flushes all processes TLBs - * - flush_tlb_mm(mm) flushes the specified mm context TLB's - * - flush_tlb_page(vma, vmaddr) flushes one page - * - flush_tlb_range(vma, start, end) flushes a range of pages - * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages - * - flush_tlb_pgtables(mm, start, end) flushes a range of page tables - * - * ..but the x86_64 has somewhat limited tlb flushing capabilities, - * and page-granular flushes are available only on i486 and up. - */ - -#ifndef CONFIG_SMP - -#define flush_tlb() __flush_tlb() -#define flush_tlb_all() __flush_tlb_all() -#define local_flush_tlb() __flush_tlb() - -static inline void flush_tlb_mm(struct mm_struct *mm) -{ - if (mm == current->active_mm) - __flush_tlb(); -} - -static inline void flush_tlb_page(struct vm_area_struct *vma, - unsigned long addr) -{ - if (vma->vm_mm == current->active_mm) - __flush_tlb_one(addr); -} - -static inline void flush_tlb_range(struct vm_area_struct *vma, - unsigned long start, unsigned long end) -{ - if (vma->vm_mm == current->active_mm) - __flush_tlb(); -} - -#else - -#include <asm/smp.h> - -#define local_flush_tlb() \ - __flush_tlb() - -extern void flush_tlb_all(void); -extern void flush_tlb_current_task(void); -extern void flush_tlb_mm(struct mm_struct *); -extern void flush_tlb_page(struct vm_area_struct *, unsigned long); - -#define flush_tlb() flush_tlb_current_task() - -static inline void flush_tlb_range(struct vm_area_struct * vma, unsigned long start, unsigned long end) -{ - flush_tlb_mm(vma->vm_mm); -} - -#define TLBSTATE_OK 1 -#define TLBSTATE_LAZY 2 - -#endif - -#define flush_tlb_kernel_range(start, end) flush_tlb_all() - -static inline void flush_tlb_pgtables(struct mm_struct *mm, - unsigned long start, unsigned long end) -{ - /* x86_64 does not keep any page table caches in TLB */ -} - -#endif /* _X8664_TLBFLUSH_H */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/vga.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/vga.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,20 +0,0 @@ -/* - * Access to VGA videoram - * - * (c) 1998 Martin Mares <mj@xxxxxx> - */ - -#ifndef _LINUX_ASM_VGA_H_ -#define _LINUX_ASM_VGA_H_ - -/* - * On the PC, we can just recalculate addresses and then - * access the videoram directly without any black magic. - */ - -#define VGA_MAP_MEM(x) (unsigned long)isa_bus_to_virt(x) - -#define vga_readb(x) (*(x)) -#define vga_writeb(x,y) (*(y) = (x)) - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/xor.h --- a/linux-2.6-xen-sparse/include/asm-xen/asm-x86_64/xor.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,328 +0,0 @@ -/* - * x86-64 changes / gcc fixes from Andi Kleen. - * Copyright 2002 Andi Kleen, SuSE Labs. - * - * This hasn't been optimized for the hammer yet, but there are likely - * no advantages to be gotten from x86-64 here anyways. - */ - -typedef struct { unsigned long a,b; } __attribute__((aligned(16))) xmm_store_t; - -/* Doesn't use gcc to save the XMM registers, because there is no easy way to - tell it to do a clts before the register saving. */ -#define XMMS_SAVE do { \ - preempt_disable(); \ - if (!(current_thread_info()->status & TS_USEDFPU)) \ - clts(); \ - __asm__ __volatile__ ( \ - "movups %%xmm0,(%1) ;\n\t" \ - "movups %%xmm1,0x10(%1) ;\n\t" \ - "movups %%xmm2,0x20(%1) ;\n\t" \ - "movups %%xmm3,0x30(%1) ;\n\t" \ - : "=&r" (cr0) \ - : "r" (xmm_save) \ - : "memory"); \ -} while(0) - -#define XMMS_RESTORE do { \ - asm volatile ( \ - "sfence ;\n\t" \ - "movups (%1),%%xmm0 ;\n\t" \ - "movups 0x10(%1),%%xmm1 ;\n\t" \ - "movups 0x20(%1),%%xmm2 ;\n\t" \ - "movups 0x30(%1),%%xmm3 ;\n\t" \ - : \ - : "r" (cr0), "r" (xmm_save) \ - : "memory"); \ - if (!(current_thread_info()->status & TS_USEDFPU)) \ - stts(); \ - preempt_enable(); \ -} while(0) - -#define OFFS(x) "16*("#x")" -#define PF_OFFS(x) "256+16*("#x")" -#define PF0(x) " prefetchnta "PF_OFFS(x)"(%[p1]) ;\n" -#define LD(x,y) " movaps "OFFS(x)"(%[p1]), %%xmm"#y" ;\n" -#define ST(x,y) " movaps %%xmm"#y", "OFFS(x)"(%[p1]) ;\n" -#define PF1(x) " prefetchnta "PF_OFFS(x)"(%[p2]) ;\n" -#define PF2(x) " prefetchnta "PF_OFFS(x)"(%[p3]) ;\n" -#define PF3(x) " prefetchnta "PF_OFFS(x)"(%[p4]) ;\n" -#define PF4(x) " prefetchnta "PF_OFFS(x)"(%[p5]) ;\n" -#define PF5(x) " prefetchnta "PF_OFFS(x)"(%[p6]) ;\n" -#define XO1(x,y) " xorps "OFFS(x)"(%[p2]), %%xmm"#y" ;\n" -#define XO2(x,y) " xorps "OFFS(x)"(%[p3]), %%xmm"#y" ;\n" -#define XO3(x,y) " xorps "OFFS(x)"(%[p4]), %%xmm"#y" ;\n" -#define XO4(x,y) " xorps "OFFS(x)"(%[p5]), %%xmm"#y" ;\n" -#define XO5(x,y) " xorps "OFFS(x)"(%[p6]), %%xmm"#y" ;\n" - - -static void -xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) -{ - unsigned int lines = bytes >> 8; - unsigned long cr0; - xmm_store_t xmm_save[4]; - - XMMS_SAVE; - - asm volatile ( -#undef BLOCK -#define BLOCK(i) \ - LD(i,0) \ - LD(i+1,1) \ - PF1(i) \ - PF1(i+2) \ - LD(i+2,2) \ - LD(i+3,3) \ - PF0(i+4) \ - PF0(i+6) \ - XO1(i,0) \ - XO1(i+1,1) \ - XO1(i+2,2) \ - XO1(i+3,3) \ - ST(i,0) \ - ST(i+1,1) \ - ST(i+2,2) \ - ST(i+3,3) \ - - - PF0(0) - PF0(2) - - " .align 32 ;\n" - " 1: ;\n" - - BLOCK(0) - BLOCK(4) - BLOCK(8) - BLOCK(12) - - " addq %[inc], %[p1] ;\n" - " addq %[inc], %[p2] ;\n" - " decl %[cnt] ; jnz 1b" - : [p1] "+r" (p1), [p2] "+r" (p2), [cnt] "+r" (lines) - : [inc] "r" (256UL) - : "memory"); - - XMMS_RESTORE; -} - -static void -xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3) -{ - unsigned int lines = bytes >> 8; - xmm_store_t xmm_save[4]; - unsigned long cr0; - - XMMS_SAVE; - - __asm__ __volatile__ ( -#undef BLOCK -#define BLOCK(i) \ - PF1(i) \ - PF1(i+2) \ - LD(i,0) \ - LD(i+1,1) \ - LD(i+2,2) \ - LD(i+3,3) \ - PF2(i) \ - PF2(i+2) \ - PF0(i+4) \ - PF0(i+6) \ - XO1(i,0) \ - XO1(i+1,1) \ - XO1(i+2,2) \ - XO1(i+3,3) \ - XO2(i,0) \ - XO2(i+1,1) \ - XO2(i+2,2) \ - XO2(i+3,3) \ - ST(i,0) \ - ST(i+1,1) \ - ST(i+2,2) \ - ST(i+3,3) \ - - - PF0(0) - PF0(2) - - " .align 32 ;\n" - " 1: ;\n" - - BLOCK(0) - BLOCK(4) - BLOCK(8) - BLOCK(12) - - " addq %[inc], %[p1] ;\n" - " addq %[inc], %[p2] ;\n" - " addq %[inc], %[p3] ;\n" - " decl %[cnt] ; jnz 1b" - : [cnt] "+r" (lines), - [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3) - : [inc] "r" (256UL) - : "memory"); - XMMS_RESTORE; -} - -static void -xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4) -{ - unsigned int lines = bytes >> 8; - xmm_store_t xmm_save[4]; - unsigned long cr0; - - XMMS_SAVE; - - __asm__ __volatile__ ( -#undef BLOCK -#define BLOCK(i) \ - PF1(i) \ - PF1(i+2) \ - LD(i,0) \ - LD(i+1,1) \ - LD(i+2,2) \ - LD(i+3,3) \ - PF2(i) \ - PF2(i+2) \ - XO1(i,0) \ - XO1(i+1,1) \ - XO1(i+2,2) \ - XO1(i+3,3) \ - PF3(i) \ - PF3(i+2) \ - PF0(i+4) \ - PF0(i+6) \ - XO2(i,0) \ - XO2(i+1,1) \ - XO2(i+2,2) \ - XO2(i+3,3) \ - XO3(i,0) \ - XO3(i+1,1) \ - XO3(i+2,2) \ - XO3(i+3,3) \ - ST(i,0) \ - ST(i+1,1) \ - ST(i+2,2) \ - ST(i+3,3) \ - - - PF0(0) - PF0(2) - - " .align 32 ;\n" - " 1: ;\n" - - BLOCK(0) - BLOCK(4) - BLOCK(8) - BLOCK(12) - - " addq %[inc], %[p1] ;\n" - " addq %[inc], %[p2] ;\n" - " addq %[inc], %[p3] ;\n" - " addq %[inc], %[p4] ;\n" - " decl %[cnt] ; jnz 1b" - : [cnt] "+c" (lines), - [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4) - : [inc] "r" (256UL) - : "memory" ); - - XMMS_RESTORE; -} - -static void -xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4, unsigned long *p5) -{ - unsigned int lines = bytes >> 8; - xmm_store_t xmm_save[4]; - unsigned long cr0; - - XMMS_SAVE; - - __asm__ __volatile__ ( -#undef BLOCK -#define BLOCK(i) \ - PF1(i) \ - PF1(i+2) \ - LD(i,0) \ - LD(i+1,1) \ - LD(i+2,2) \ - LD(i+3,3) \ - PF2(i) \ - PF2(i+2) \ - XO1(i,0) \ - XO1(i+1,1) \ - XO1(i+2,2) \ - XO1(i+3,3) \ - PF3(i) \ - PF3(i+2) \ - XO2(i,0) \ - XO2(i+1,1) \ - XO2(i+2,2) \ - XO2(i+3,3) \ - PF4(i) \ - PF4(i+2) \ - PF0(i+4) \ - PF0(i+6) \ - XO3(i,0) \ - XO3(i+1,1) \ - XO3(i+2,2) \ - XO3(i+3,3) \ - XO4(i,0) \ - XO4(i+1,1) \ - XO4(i+2,2) \ - XO4(i+3,3) \ - ST(i,0) \ - ST(i+1,1) \ - ST(i+2,2) \ - ST(i+3,3) \ - - - PF0(0) - PF0(2) - - " .align 32 ;\n" - " 1: ;\n" - - BLOCK(0) - BLOCK(4) - BLOCK(8) - BLOCK(12) - - " addq %[inc], %[p1] ;\n" - " addq %[inc], %[p2] ;\n" - " addq %[inc], %[p3] ;\n" - " addq %[inc], %[p4] ;\n" - " addq %[inc], %[p5] ;\n" - " decl %[cnt] ; jnz 1b" - : [cnt] "+c" (lines), - [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4), - [p5] "+r" (p5) - : [inc] "r" (256UL) - : "memory"); - - XMMS_RESTORE; -} - -static struct xor_block_template xor_block_sse = { - .name = "generic_sse", - .do_2 = xor_sse_2, - .do_3 = xor_sse_3, - .do_4 = xor_sse_4, - .do_5 = xor_sse_5, -}; - -#undef XOR_TRY_TEMPLATES -#define XOR_TRY_TEMPLATES \ - do { \ - xor_speed(&xor_block_sse); \ - } while (0) - -/* We force the use of the SSE xor block because it can write around L2. - We may also be able to load into the L1 only depending on how the cpu - deals with a load to a line that is being prefetched. */ -#define XOR_SELECT_TEMPLATE(FASTEST) (&xor_block_sse) diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/balloon.h --- a/linux-2.6-xen-sparse/include/asm-xen/balloon.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,70 +0,0 @@ -/****************************************************************************** - * balloon.h - * - * Xen balloon driver - enables returning/claiming memory to/from Xen. - * - * Copyright (c) 2003, B Dragovic - * Copyright (c) 2003-2004, M Williamson, K Fraser - * - * This file may be distributed separately from the Linux kernel, or - * incorporated into other software packages, subject to the following license: - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this source file (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, copy, modify, - * merge, publish, distribute, sublicense, and/or sell copies of the Software, - * and to permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - */ - -#ifndef __ASM_BALLOON_H__ -#define __ASM_BALLOON_H__ - -/* - * Inform the balloon driver that it should allow some slop for device-driver - * memory activities. - */ -extern void -balloon_update_driver_allowance( - long delta); - -/* Allocate an empty low-memory page range. */ -extern struct page * -balloon_alloc_empty_page_range( - unsigned long nr_pages); - -/* Deallocate an empty page range, adding to the balloon. */ -extern void -balloon_dealloc_empty_page_range( - struct page *page, unsigned long nr_pages); - -/* - * Prevent the balloon driver from changing the memory reservation during - * a driver critical region. - */ -extern spinlock_t balloon_lock; -#define balloon_lock(__flags) spin_lock_irqsave(&balloon_lock, __flags) -#define balloon_unlock(__flags) spin_unlock_irqrestore(&balloon_lock, __flags) - -#endif /* __ASM_BALLOON_H__ */ - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/driver_util.h --- a/linux-2.6-xen-sparse/include/asm-xen/driver_util.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,26 +0,0 @@ - -#ifndef __ASM_XEN_DRIVER_UTIL_H__ -#define __ASM_XEN_DRIVER_UTIL_H__ - -#include <linux/config.h> -#include <linux/vmalloc.h> - -/* Allocate/destroy a 'vmalloc' VM area. */ -extern struct vm_struct *alloc_vm_area(unsigned long size); -extern void free_vm_area(struct vm_struct *area); - -/* Lock an area so that PTEs are accessible in the current address space. */ -extern void lock_vm_area(struct vm_struct *area); -extern void unlock_vm_area(struct vm_struct *area); - -#endif /* __ASM_XEN_DRIVER_UTIL_H__ */ - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/evtchn.h --- a/linux-2.6-xen-sparse/include/asm-xen/evtchn.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,123 +0,0 @@ -/****************************************************************************** - * evtchn.h - * - * Communication via Xen event channels. - * Also definitions for the device that demuxes notifications to userspace. - * - * Copyright (c) 2004-2005, K A Fraser - * - * This file may be distributed separately from the Linux kernel, or - * incorporated into other software packages, subject to the following license: - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this source file (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, copy, modify, - * merge, publish, distribute, sublicense, and/or sell copies of the Software, - * and to permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - */ - -#ifndef __ASM_EVTCHN_H__ -#define __ASM_EVTCHN_H__ - -#include <linux/config.h> -#include <linux/interrupt.h> -#include <asm/hypervisor.h> -#include <asm/ptrace.h> -#include <asm/synch_bitops.h> -#include <asm-xen/xen-public/event_channel.h> -#include <linux/smp.h> - -/* - * LOW-LEVEL DEFINITIONS - */ - -/* - * Dynamically bind an event source to an IRQ-like callback handler. - * On some platforms this may not be implemented via the Linux IRQ subsystem. - * The IRQ argument passed to the callback handler is the same as returned - * from the bind call. It may not correspond to a Linux IRQ number. - * Returns IRQ or negative errno. - * UNBIND: Takes IRQ to unbind from; automatically closes the event channel. - */ -extern int bind_evtchn_to_irqhandler( - unsigned int evtchn, - irqreturn_t (*handler)(int, void *, struct pt_regs *), - unsigned long irqflags, - const char *devname, - void *dev_id); -extern int bind_virq_to_irqhandler( - unsigned int virq, - unsigned int cpu, - irqreturn_t (*handler)(int, void *, struct pt_regs *), - unsigned long irqflags, - const char *devname, - void *dev_id); -extern int bind_ipi_to_irqhandler( - unsigned int ipi, - unsigned int cpu, - irqreturn_t (*handler)(int, void *, struct pt_regs *), - unsigned long irqflags, - const char *devname, - void *dev_id); - -/* - * Common unbind function for all event sources. Takes IRQ to unbind from. - * Automatically closes the underlying event channel (even for bindings - * made with bind_evtchn_to_irqhandler()). - */ -extern void unbind_from_irqhandler(unsigned int irq, void *dev_id); - -extern void irq_resume(void); - -/* Entry point for notifications into Linux subsystems. */ -asmlinkage void evtchn_do_upcall(struct pt_regs *regs); - -/* Entry point for notifications into the userland character device. */ -extern void evtchn_device_upcall(int port); - -extern void mask_evtchn(int port); -extern void unmask_evtchn(int port); - -static inline void clear_evtchn(int port) -{ - shared_info_t *s = HYPERVISOR_shared_info; - synch_clear_bit(port, &s->evtchn_pending[0]); -} - -static inline void notify_remote_via_evtchn(int port) -{ - evtchn_op_t op; - op.cmd = EVTCHNOP_send, - op.u.send.port = port; - (void)HYPERVISOR_event_channel_op(&op); -} - -/* - * Unlike notify_remote_via_evtchn(), this is safe to use across - * save/restore. Notifications on a broken connection are silently dropped. - */ -extern void notify_remote_via_irq(int irq); - -#endif /* __ASM_EVTCHN_H__ */ - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/features.h --- a/linux-2.6-xen-sparse/include/asm-xen/features.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,20 +0,0 @@ -/****************************************************************************** - * features.h - * - * Query the features reported by Xen. - * - * Copyright (c) 2006, Ian Campbell - */ - -#ifndef __ASM_XEN_FEATURES_H__ -#define __ASM_XEN_FEATURES_H__ - -#include <asm-xen/xen-public/version.h> - -extern void setup_xen_features(void); - -extern unsigned long xen_features[XENFEAT_NR_SUBMAPS]; - -#define xen_feature(flag) (test_bit(flag, xen_features)) - -#endif /* __ASM_XEN_FEATURES_H__ */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/foreign_page.h --- a/linux-2.6-xen-sparse/include/asm-xen/foreign_page.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,40 +0,0 @@ -/****************************************************************************** - * foreign_page.h - * - * Provide a "foreign" page type, that is owned by a foreign allocator and - * not the normal buddy allocator in page_alloc.c - * - * Copyright (c) 2004, K A Fraser - */ - -#ifndef __ASM_XEN_FOREIGN_PAGE_H__ -#define __ASM_XEN_FOREIGN_PAGE_H__ - -#define PG_foreign PG_arch_1 - -#define PageForeign(page) test_bit(PG_foreign, &(page)->flags) - -#define SetPageForeign(page, dtor) do { \ - set_bit(PG_foreign, &(page)->flags); \ - (page)->mapping = (void *)dtor; \ -} while (0) - -#define ClearPageForeign(page) do { \ - clear_bit(PG_foreign, &(page)->flags); \ - (page)->mapping = NULL; \ -} while (0) - -#define PageForeignDestructor(page) \ - ( (void (*) (struct page *)) (page)->mapping ) - -#endif /* __ASM_XEN_FOREIGN_PAGE_H__ */ - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/gnttab.h --- a/linux-2.6-xen-sparse/include/asm-xen/gnttab.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,98 +0,0 @@ -/****************************************************************************** - * gnttab.h - * - * Two sets of functionality: - * 1. Granting foreign access to our memory reservation. - * 2. Accessing others' memory reservations via grant references. - * (i.e., mechanisms for both sender and recipient of grant references) - * - * Copyright (c) 2004-2005, K A Fraser - * Copyright (c) 2005, Christopher Clark - */ - -#ifndef __ASM_GNTTAB_H__ -#define __ASM_GNTTAB_H__ - -#include <linux/config.h> -#include <asm/hypervisor.h> -#include <asm-xen/xen-public/grant_table.h> - -/* NR_GRANT_FRAMES must be less than or equal to that configured in Xen */ -#ifdef __ia64__ -#define NR_GRANT_FRAMES 1 -#else -#define NR_GRANT_FRAMES 4 -#endif - -struct gnttab_free_callback { - struct gnttab_free_callback *next; - void (*fn)(void *); - void *arg; - u16 count; -}; - -int gnttab_grant_foreign_access(domid_t domid, unsigned long frame, - int readonly); - -/* - * End access through the given grant reference, iff the grant entry is no - * longer in use. Return 1 if the grant entry was freed, 0 if it is still in - * use. - */ -int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly); - -/* - * Eventually end access through the given grant reference, and once that - * access has been ended, free the given page too. Access will be ended - * immediately iff the grant entry is not in use, otherwise it will happen - * some time later. page may be 0, in which case no freeing will occur. - */ -void gnttab_end_foreign_access(grant_ref_t ref, int readonly, - unsigned long page); - -int gnttab_grant_foreign_transfer(domid_t domid); - -unsigned long gnttab_end_foreign_transfer_ref(grant_ref_t ref); -unsigned long gnttab_end_foreign_transfer(grant_ref_t ref); - -int gnttab_query_foreign_access(grant_ref_t ref); - -/* - * operations on reserved batches of grant references - */ -int gnttab_alloc_grant_references(u16 count, grant_ref_t *pprivate_head); - -void gnttab_free_grant_reference(grant_ref_t ref); - -void gnttab_free_grant_references(grant_ref_t head); - -int gnttab_claim_grant_reference(grant_ref_t *pprivate_head); - -void gnttab_release_grant_reference(grant_ref_t *private_head, - grant_ref_t release); - -void gnttab_request_free_callback(struct gnttab_free_callback *callback, - void (*fn)(void *), void *arg, u16 count); - -void gnttab_grant_foreign_access_ref(grant_ref_t ref, domid_t domid, - unsigned long frame, int readonly); - -void gnttab_grant_foreign_transfer_ref(grant_ref_t, domid_t domid); - -#ifdef __ia64__ -#define gnttab_map_vaddr(map) __va(map.dev_bus_addr) -#else -#define gnttab_map_vaddr(map) ((void *)(map.host_virt_addr)) -#endif - -#endif /* __ASM_GNTTAB_H__ */ - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/linux-public/evtchn.h --- a/linux-2.6-xen-sparse/include/asm-xen/linux-public/evtchn.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,98 +0,0 @@ -/****************************************************************************** - * evtchn.h - * - * Interface to /dev/xen/evtchn. - * - * Copyright (c) 2003-2005, K A Fraser - * - * This file may be distributed separately from the Linux kernel, or - * incorporated into other software packages, subject to the following license: - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this source file (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, copy, modify, - * merge, publish, distribute, sublicense, and/or sell copies of the Software, - * and to permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - */ - -#ifndef __LINUX_PUBLIC_EVTCHN_H__ -#define __LINUX_PUBLIC_EVTCHN_H__ - -/* /dev/xen/evtchn resides at device number major=10, minor=201 */ -#define EVTCHN_MINOR 201 - -/* - * Bind a fresh port to VIRQ @virq. - * Return allocated port. - */ -#define IOCTL_EVTCHN_BIND_VIRQ \ - _IOC(_IOC_NONE, 'E', 0, sizeof(struct ioctl_evtchn_bind_virq)) -struct ioctl_evtchn_bind_virq { - unsigned int virq; -}; - -/* - * Bind a fresh port to remote <@remote_domain, @remote_port>. - * Return allocated port. - */ -#define IOCTL_EVTCHN_BIND_INTERDOMAIN \ - _IOC(_IOC_NONE, 'E', 1, sizeof(struct ioctl_evtchn_bind_interdomain)) -struct ioctl_evtchn_bind_interdomain { - unsigned int remote_domain, remote_port; -}; - -/* - * Allocate a fresh port for binding to @remote_domain. - * Return allocated port. - */ -#define IOCTL_EVTCHN_BIND_UNBOUND_PORT \ - _IOC(_IOC_NONE, 'E', 2, sizeof(struct ioctl_evtchn_bind_unbound_port)) -struct ioctl_evtchn_bind_unbound_port { - unsigned int remote_domain; -}; - -/* - * Unbind previously allocated @port. - */ -#define IOCTL_EVTCHN_UNBIND \ - _IOC(_IOC_NONE, 'E', 3, sizeof(struct ioctl_evtchn_unbind)) -struct ioctl_evtchn_unbind { - unsigned int port; -}; - -/* - * Unbind previously allocated @port. - */ -#define IOCTL_EVTCHN_NOTIFY \ - _IOC(_IOC_NONE, 'E', 4, sizeof(struct ioctl_evtchn_notify)) -struct ioctl_evtchn_notify { - unsigned int port; -}; - -/* Clear and reinitialise the event buffer. Clear error condition. */ -#define IOCTL_EVTCHN_RESET \ - _IOC(_IOC_NONE, 'E', 5, 0) - -#endif /* __LINUX_PUBLIC_EVTCHN_H__ */ - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/linux-public/privcmd.h --- a/linux-2.6-xen-sparse/include/asm-xen/linux-public/privcmd.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,91 +0,0 @@ -/****************************************************************************** - * privcmd.h - * - * Interface to /proc/xen/privcmd. - * - * Copyright (c) 2003-2005, K A Fraser - * - * This file may be distributed separately from the Linux kernel, or - * incorporated into other software packages, subject to the following license: - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this source file (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, copy, modify, - * merge, publish, distribute, sublicense, and/or sell copies of the Software, - * and to permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - */ - -#ifndef __LINUX_PUBLIC_PRIVCMD_H__ -#define __LINUX_PUBLIC_PRIVCMD_H__ - -#ifndef __user -#define __user -#endif - -typedef struct privcmd_hypercall -{ - unsigned long op; - unsigned long arg[5]; -} privcmd_hypercall_t; - -typedef struct privcmd_mmap_entry { - unsigned long va; - unsigned long mfn; - unsigned long npages; -} privcmd_mmap_entry_t; - -typedef struct privcmd_mmap { - int num; - domid_t dom; /* target domain */ - privcmd_mmap_entry_t __user *entry; -} privcmd_mmap_t; - -typedef struct privcmd_mmapbatch { - int num; /* number of pages to populate */ - domid_t dom; /* target domain */ - unsigned long addr; /* virtual address */ - unsigned long __user *arr; /* array of mfns - top nibble set on err */ -} privcmd_mmapbatch_t; - -typedef struct privcmd_blkmsg -{ - unsigned long op; - void *buf; - int buf_size; -} privcmd_blkmsg_t; - -/* - * @cmd: IOCTL_PRIVCMD_HYPERCALL - * @arg: &privcmd_hypercall_t - * Return: Value returned from execution of the specified hypercall. - */ -#define IOCTL_PRIVCMD_HYPERCALL \ - _IOC(_IOC_NONE, 'P', 0, sizeof(privcmd_hypercall_t)) -#define IOCTL_PRIVCMD_MMAP \ - _IOC(_IOC_NONE, 'P', 2, sizeof(privcmd_mmap_t)) -#define IOCTL_PRIVCMD_MMAPBATCH \ - _IOC(_IOC_NONE, 'P', 3, sizeof(privcmd_mmapbatch_t)) - -#endif /* __LINUX_PUBLIC_PRIVCMD_H__ */ - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/net_driver_util.h --- a/linux-2.6-xen-sparse/include/asm-xen/net_driver_util.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,56 +0,0 @@ -/***************************************************************************** - * - * Utility functions for Xen network devices. - * - * Copyright (c) 2005 XenSource Ltd. - * - * This file may be distributed separately from the Linux kernel, or - * incorporated into other software packages, subject to the following - * license: - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this source file (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, copy, modify, - * merge, publish, distribute, sublicense, and/or sell copies of the Software, - * and to permit persons to whom the Software is furnished to do so, subject - * to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - */ - -#ifndef _ASM_XEN_NET_DRIVER_UTIL_H -#define _ASM_XEN_NET_DRIVER_UTIL_H - - -#include <asm-xen/xenbus.h> - - -/** - * Read the 'mac' node at the given device's node in the store, and parse that - * as colon-separated octets, placing result the given mac array. mac must be - * a preallocated array of length ETH_ALEN (as declared in linux/if_ether.h). - * Return 0 on success, or -errno on error. - */ -int xen_net_read_mac(struct xenbus_device *dev, u8 mac[]); - - -#endif /* _ASM_XEN_NET_DRIVER_UTIL_H */ - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/tpmfe.h --- a/linux-2.6-xen-sparse/include/asm-xen/tpmfe.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,33 +0,0 @@ -#ifndef TPM_FE_H -#define TPM_FE_H - -struct tpmfe_device { - /* - * Let upper layer receive data from front-end - */ - int (*receive)(const u8 *buffer, size_t count, const void *ptr); - /* - * Indicate the status of the front-end to the upper - * layer. - */ - void (*status)(unsigned int flags); - - /* - * This field indicates the maximum size the driver can - * transfer in one chunk. It is filled out by the front-end - * driver and should be propagated to the generic tpm driver - * for allocation of buffers. - */ - unsigned int max_tx_size; -}; - -enum { - TPMFE_STATUS_DISCONNECTED = 0x0, - TPMFE_STATUS_CONNECTED = 0x1 -}; - -int tpm_fe_send(const u8 * buf, size_t count, void *ptr); -int tpm_fe_register_receiver(struct tpmfe_device *); -void tpm_fe_unregister_receiver(void); - -#endif diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/xen_proc.h --- a/linux-2.6-xen-sparse/include/asm-xen/xen_proc.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,23 +0,0 @@ - -#ifndef __ASM_XEN_PROC_H__ -#define __ASM_XEN_PROC_H__ - -#include <linux/config.h> -#include <linux/proc_fs.h> - -extern struct proc_dir_entry *create_xen_proc_entry( - const char *name, mode_t mode); -extern void remove_xen_proc_entry( - const char *name); - -#endif /* __ASM_XEN_PROC_H__ */ - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/xenbus.h --- a/linux-2.6-xen-sparse/include/asm-xen/xenbus.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,254 +0,0 @@ -/****************************************************************************** - * xenbus.h - * - * Talks to Xen Store to figure out what devices we have. - * - * Copyright (C) 2005 Rusty Russell, IBM Corporation - * Copyright (C) 2005 XenSource Ltd. - * - * This file may be distributed separately from the Linux kernel, or - * incorporated into other software packages, subject to the following license: - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this source file (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, copy, modify, - * merge, publish, distribute, sublicense, and/or sell copies of the Software, - * and to permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - */ - -#ifndef _ASM_XEN_XENBUS_H -#define _ASM_XEN_XENBUS_H - -#include <linux/device.h> -#include <linux/notifier.h> -#include <asm/semaphore.h> -#include <asm-xen/xen-public/io/xenbus.h> -#include <asm-xen/xen-public/io/xs_wire.h> - -#define XBT_NULL 0 - -/* Register callback to watch this node. */ -struct xenbus_watch -{ - struct list_head list; - - /* Path being watched. */ - const char *node; - - /* Callback (executed in a process context with no locks held). */ - void (*callback)(struct xenbus_watch *, - const char **vec, unsigned int len); -}; - - -/* A xenbus device. */ -struct xenbus_device { - const char *devicetype; - const char *nodename; - const char *otherend; - int otherend_id; - struct xenbus_watch otherend_watch; - struct device dev; - int has_error; - void *data; -}; - -static inline struct xenbus_device *to_xenbus_device(struct device *dev) -{ - return container_of(dev, struct xenbus_device, dev); -} - -struct xenbus_device_id -{ - /* .../device/<device_type>/<identifier> */ - char devicetype[32]; /* General class of device. */ -}; - -/* A xenbus driver. */ -struct xenbus_driver { - char *name; - struct module *owner; - const struct xenbus_device_id *ids; - int (*probe)(struct xenbus_device *dev, - const struct xenbus_device_id *id); - void (*otherend_changed)(struct xenbus_device *dev, - XenbusState backend_state); - int (*remove)(struct xenbus_device *dev); - int (*suspend)(struct xenbus_device *dev); - int (*resume)(struct xenbus_device *dev); - int (*hotplug)(struct xenbus_device *, char **, int, char *, int); - struct device_driver driver; - int (*read_otherend_details)(struct xenbus_device *dev); -}; - -static inline struct xenbus_driver *to_xenbus_driver(struct device_driver *drv) -{ - return container_of(drv, struct xenbus_driver, driver); -} - -int xenbus_register_frontend(struct xenbus_driver *drv); -int xenbus_register_backend(struct xenbus_driver *drv); -void xenbus_unregister_driver(struct xenbus_driver *drv); - -typedef u32 xenbus_transaction_t; - -char **xenbus_directory(xenbus_transaction_t t, - const char *dir, const char *node, unsigned int *num); -void *xenbus_read(xenbus_transaction_t t, - const char *dir, const char *node, unsigned int *len); -int xenbus_write(xenbus_transaction_t t, - const char *dir, const char *node, const char *string); -int xenbus_mkdir(xenbus_transaction_t t, - const char *dir, const char *node); -int xenbus_exists(xenbus_transaction_t t, - const char *dir, const char *node); -int xenbus_rm(xenbus_transaction_t t, const char *dir, const char *node); -int xenbus_transaction_start(xenbus_transaction_t *t); -int xenbus_transaction_end(xenbus_transaction_t t, int abort); - -/* Single read and scanf: returns -errno or num scanned if > 0. */ -int xenbus_scanf(xenbus_transaction_t t, - const char *dir, const char *node, const char *fmt, ...) - __attribute__((format(scanf, 4, 5))); - -/* Single printf and write: returns -errno or 0. */ -int xenbus_printf(xenbus_transaction_t t, - const char *dir, const char *node, const char *fmt, ...) - __attribute__((format(printf, 4, 5))); - -/* Generic read function: NULL-terminated triples of name, - * sprintf-style type string, and pointer. Returns 0 or errno.*/ -int xenbus_gather(xenbus_transaction_t t, const char *dir, ...); - -/* notifer routines for when the xenstore comes up */ -int register_xenstore_notifier(struct notifier_block *nb); -void unregister_xenstore_notifier(struct notifier_block *nb); - -int register_xenbus_watch(struct xenbus_watch *watch); -void unregister_xenbus_watch(struct xenbus_watch *watch); -void xs_suspend(void); -void xs_resume(void); - -/* Used by xenbus_dev to borrow kernel's store connection. */ -void *xenbus_dev_request_and_reply(struct xsd_sockmsg *msg); - -/* Called from xen core code. */ -void xenbus_suspend(void); -void xenbus_resume(void); - -#define XENBUS_IS_ERR_READ(str) ({ \ - if (!IS_ERR(str) && strlen(str) == 0) { \ - kfree(str); \ - str = ERR_PTR(-ERANGE); \ - } \ - IS_ERR(str); \ -}) - -#define XENBUS_EXIST_ERR(err) ((err) == -ENOENT || (err) == -ERANGE) - - -/** - * Register a watch on the given path, using the given xenbus_watch structure - * for storage, and the given callback function as the callback. Return 0 on - * success, or -errno on error. On success, the given path will be saved as - * watch->node, and remains the caller's to free. On error, watch->node will - * be NULL, the device will switch to XenbusStateClosing, and the error will - * be saved in the store. - */ -int xenbus_watch_path(struct xenbus_device *dev, const char *path, - struct xenbus_watch *watch, - void (*callback)(struct xenbus_watch *, - const char **, unsigned int)); - - -/** - * Register a watch on the given path/path2, using the given xenbus_watch - * structure for storage, and the given callback function as the callback. - * Return 0 on success, or -errno on error. On success, the watched path - * (path/path2) will be saved as watch->node, and becomes the caller's to - * kfree(). On error, watch->node will be NULL, so the caller has nothing to - * free, the device will switch to XenbusStateClosing, and the error will be - * saved in the store. - */ -int xenbus_watch_path2(struct xenbus_device *dev, const char *path, - const char *path2, struct xenbus_watch *watch, - void (*callback)(struct xenbus_watch *, - const char **, unsigned int)); - - -/** - * Advertise in the store a change of the given driver to the given new_state. - * Perform the change inside the given transaction xbt. xbt may be NULL, in - * which case this is performed inside its own transaction. Return 0 on - * success, or -errno on error. On error, the device will switch to - * XenbusStateClosing, and the error will be saved in the store. - */ -int xenbus_switch_state(struct xenbus_device *dev, - xenbus_transaction_t xbt, - XenbusState new_state); - - -/** - * Grant access to the given ring_mfn to the peer of the given device. Return - * 0 on success, or -errno on error. On error, the device will switch to - * XenbusStateClosing, and the error will be saved in the store. - */ -int xenbus_grant_ring(struct xenbus_device *dev, unsigned long ring_mfn); - - -/** - * Allocate an event channel for the given xenbus_device, assigning the newly - * created local port to *port. Return 0 on success, or -errno on error. On - * error, the device will switch to XenbusStateClosing, and the error will be - * saved in the store. - */ -int xenbus_alloc_evtchn(struct xenbus_device *dev, int *port); - - -/** - * Return the state of the driver rooted at the given store path, or - * XenbusStateClosed if no state can be read. - */ -XenbusState xenbus_read_driver_state(const char *path); - - -/*** - * Report the given negative errno into the store, along with the given - * formatted message. - */ -void xenbus_dev_error(struct xenbus_device *dev, int err, const char *fmt, - ...); - - -/*** - * Equivalent to xenbus_dev_error(dev, err, fmt, args), followed by - * xenbus_switch_state(dev, NULL, XenbusStateClosing) to schedule an orderly - * closedown of this driver and its peer. - */ -void xenbus_dev_fatal(struct xenbus_device *dev, int err, const char *fmt, - ...); - - -#endif /* _ASM_XEN_XENBUS_H */ - -/* - * Local variables: - * c-file-style: "linux" - * indent-tabs-mode: t - * c-indent-level: 8 - * c-basic-offset: 8 - * tab-width: 8 - * End: - */ diff -r 690fc13948db -r fd9b2c1bb577 linux-2.6-xen-sparse/include/asm-xen/xencons.h --- a/linux-2.6-xen-sparse/include/asm-xen/xencons.h Mon Jan 30 12:35:43 2006 +++ /dev/null Mon Jan 30 17:18:27 2006 @@ -1,14 +0,0 @@ -#ifndef __ASM_XENCONS_H__ -#define __ASM_XENCONS_H__ - -void xencons_force_flush(void); -void xencons_resume(void); - -/* Interrupt work hooks. Receive data, or kick data out. */ -void xencons_rx(char *buf, unsigned len, struct pt_regs *regs); -void xencons_tx(void); - -int xencons_ring_init(void); -int xencons_ring_send(const char *data, unsigned len); - -#endif /* __ASM_XENCONS_H__ */ _______________________________________________ Xen-changelog mailing list Xen-changelog@xxxxxxxxxxxxxxxxxxx http://lists.xensource.com/xen-changelog

©2013 Xen Project, A Linux Foundation Collaborative Project. All Rights Reserved.
Linux Foundation is a registered trademark of The Linux Foundation.
Xen Project is a trademark of The Linux Foundation.