[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-devel] [PATCH, fixed] linux/x86: use sysenter/syscall for 32-bit apps on 64-bit Xen



.. for both 32-bit apps on 64-bit kernels and 32bit kernels.

Andi Kleen pointed out a problem with the original version, which is
being fixed here.

Also removing the needless re-enabling of events on x86-64's 64-bit
syscall path as well as it's 32-bit int80 path (the latter accompanied
by telling Xen not to disable them in the first place).

This was tested on 2.6.22.1, and only made apply to 2.6.18 without
further testing.

Signed-off-by: Jan Beulich <jbeulich@xxxxxxxxxx>

Index: head-2007-08-07/arch/i386/kernel/entry-xen.S
===================================================================
--- head-2007-08-07.orig/arch/i386/kernel/entry-xen.S   2007-08-08 
12:33:23.000000000 +0200
+++ head-2007-08-07/arch/i386/kernel/entry-xen.S        2007-07-03 
14:01:17.000000000 +0200
@@ -382,6 +382,26 @@ sysenter_past_esp:
        CFI_ENDPROC
 
 
+       # pv sysenter call handler stub
+ENTRY(sysenter_entry_pv)
+       RING0_INT_FRAME
+       movl $__USER_DS,16(%esp)
+       movl %ebp,12(%esp)
+/*
+ * 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
+       /* fall through */
+       CFI_ENDPROC
+ENDPROC(sysenter_entry_pv)
+
        # system call handler stub
 ENTRY(system_call)
        RING0_INT_FRAME                 # can't unwind into user space anyway
Index: head-2007-08-07/arch/i386/kernel/process-xen.c
===================================================================
--- head-2007-08-07.orig/arch/i386/kernel/process-xen.c 2007-08-08 
12:33:23.000000000 +0200
+++ head-2007-08-07/arch/i386/kernel/process-xen.c      2007-07-04 
10:02:51.000000000 +0200
@@ -51,6 +51,7 @@
 #include <asm/math_emu.h>
 #endif
 
+#include <xen/interface/callback.h>
 #include <xen/interface/physdev.h>
 #include <xen/interface/vcpu.h>
 #include <xen/cpu_hotplug.h>
@@ -554,6 +555,13 @@ struct task_struct fastcall * __switch_t
        struct physdev_set_iopl iopl_op;
        struct physdev_set_iobitmap iobmp_op;
        multicall_entry_t _mcl[8], *mcl = _mcl;
+       struct callback_register sysexit = {
+               .type = CALLBACKTYPE_sysexit,
+               .address = {
+                       __USER_CS,
+                       (unsigned long)task_thread_info(next_p)->sysenter_return
+               }
+       };
 
        /* XEN NOTE: FS/GS saved in switch_mm(), not here. */
 
@@ -581,6 +589,14 @@ struct task_struct fastcall * __switch_t
        mcl->args[1] = next->esp0;
        mcl++;
 
+       if (boot_cpu_has(X86_FEATURE_SEP) && next_p->mm) {
+               /* Specify sysexit address. */
+               mcl->op      = __HYPERVISOR_callback_op;
+               mcl->args[0] = CALLBACKOP_register;
+               mcl->args[1] = (unsigned long)&sysexit;
+               mcl++;
+       }
+
        /*
         * Load the per-thread Thread-Local Storage descriptor.
         * This is load_TLS(next, cpu) with multicalls.
@@ -616,7 +633,9 @@ struct task_struct fastcall * __switch_t
                mcl++;
        }
 
-       (void)HYPERVISOR_multicall(_mcl, mcl - _mcl);
+       BUG_ON(mcl > _mcl + ARRAY_SIZE(_mcl));
+       if (unlikely(HYPERVISOR_multicall_check(_mcl, mcl - _mcl, NULL)))
+               BUG();
 
        /*
         * Restore %fs and %gs if needed.
Index: head-2007-08-07/arch/i386/kernel/sysenter.c
===================================================================
--- head-2007-08-07.orig/arch/i386/kernel/sysenter.c    2007-08-08 
12:33:23.000000000 +0200
+++ head-2007-08-07/arch/i386/kernel/sysenter.c 2007-08-07 16:55:04.000000000 
+0200
@@ -48,7 +48,7 @@ extern asmlinkage void sysenter_entry(vo
 
 void enable_sep_cpu(void)
 {
-#ifndef CONFIG_X86_NO_TSS
+#ifndef CONFIG_XEN
        int cpu = get_cpu();
        struct tss_struct *tss = &per_cpu(init_tss, cpu);
 
@@ -62,8 +62,36 @@ void enable_sep_cpu(void)
        wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0);
        wrmsr(MSR_IA32_SYSENTER_ESP, tss->esp1, 0);
        wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long) sysenter_entry, 0);
-       put_cpu();      
+#else
+       extern asmlinkage void sysenter_entry_pv(void);
+       static struct callback_register sysenter = {
+               .type = CALLBACKTYPE_sysenter,
+               .address = { __KERNEL_CS, (unsigned long)sysenter_entry_pv },
+       };
+
+       if (!boot_cpu_has(X86_FEATURE_SEP))
+               return;
+
+       get_cpu();
+
+       if (xen_feature(XENFEAT_supervisor_mode_kernel))
+               sysenter.address.eip = (unsigned long)sysenter_entry;
+
+       switch (HYPERVISOR_callback_op(CALLBACKOP_register, &sysenter)) {
+       case 0:
+               break;
+#if CONFIG_XEN_COMPAT < 0x030200
+       case -ENOSYS:
+               sysenter.type = CALLBACKTYPE_sysenter_deprecated;
+               if (HYPERVISOR_callback_op(CALLBACKOP_register, &sysenter) == 0)
+                       break;
 #endif
+       default:
+               clear_bit(X86_FEATURE_SEP, boot_cpu_data.x86_capability);
+               break;
+       }
+#endif
+       put_cpu();
 }
 
 /*
@@ -78,18 +89,6 @@ int __init sysenter_setup(void)
 {
        syscall_page = (void *)get_zeroed_page(GFP_ATOMIC);
 
-#ifdef CONFIG_XEN
-       if (boot_cpu_has(X86_FEATURE_SEP)) {
-               static struct callback_register __initdata sysenter = {
-                       .type = CALLBACKTYPE_sysenter,
-                       .address = { __KERNEL_CS, (unsigned long)sysenter_entry 
},
-               };
-
-               if (HYPERVISOR_callback_op(CALLBACKOP_register, &sysenter) < 0)
-                       clear_bit(X86_FEATURE_SEP, 
boot_cpu_data.x86_capability);
-       }
-#endif
-
 #ifdef CONFIG_COMPAT_VDSO
        __set_fixmap(FIX_VDSO, __pa(syscall_page), PAGE_READONLY);
        printk("Compat vDSO mapped to %08lx.\n", __fix_to_virt(FIX_VDSO));
@@ -174,6 +173,19 @@ int arch_setup_additional_pages(struct l
        current->mm->context.vdso = (void *)addr;
        current_thread_info()->sysenter_return =
                                    (void *)VDSO_SYM(&SYSENTER_RETURN);
+#ifdef CONFIG_XEN
+       if (boot_cpu_has(X86_FEATURE_SEP)) {
+               /* Specify sysexit address. */
+               struct callback_register sysexit = {
+                       .type = CALLBACKTYPE_sysexit,
+                       .address = { __USER_CS, VDSO_SYM(&SYSENTER_RETURN) }
+               };
+
+               if (HYPERVISOR_callback_op(CALLBACKOP_register,
+                                          &sysexit) < 0)
+                       BUG();
+       }
+#endif
        mm->total_vm++;
 up_fail:
        up_write(&mm->mmap_sem);
Index: head-2007-08-07/arch/x86_64/ia32/Makefile
===================================================================
--- head-2007-08-07.orig/arch/x86_64/ia32/Makefile      2007-08-08 
12:33:23.000000000 +0200
+++ head-2007-08-07/arch/x86_64/ia32/Makefile   2007-07-09 17:16:44.000000000 
+0200
@@ -14,11 +14,14 @@ obj-$(CONFIG_IA32_AOUT) += ia32_aout.o
 audit-class-$(CONFIG_AUDIT) := audit.o
 obj-$(CONFIG_IA32_EMULATION) += $(audit-class-y)
 
+syscall32-types-y := sysenter syscall
+syscall32-types-$(subst 1,$(CONFIG_XEN),$(shell expr $(CONFIG_XEN_COMPAT)0 '<' 
0x0302000)) += int80
+
 $(obj)/syscall32_syscall.o: \
-       $(foreach F,sysenter syscall,$(obj)/vsyscall-$F.so)
+       $(foreach F,$(syscall32-types-y),$(obj)/vsyscall-$F.so)
 
 # Teach kbuild about targets
-targets := $(foreach F,sysenter syscall,vsyscall-$F.o vsyscall-$F.so)
+targets := $(foreach F,$(syscall32-types-y),vsyscall-$F.o vsyscall-$F.so)
 
 # The DSO images are built using a special linker script
 quiet_cmd_syscall = SYSCALL $@
@@ -27,18 +30,10 @@ quiet_cmd_syscall = SYSCALL $@
                           -Wl,-soname=linux-gate.so.1 -o $@ \
                           -Wl,-T,$(filter-out FORCE,$^)
 
-$(obj)/vsyscall-int80.so \
-$(obj)/vsyscall-sysenter.so $(obj)/vsyscall-syscall.so: \
+$(foreach F,$(syscall32-types-y),$(obj)/vsyscall-$F.so): \
 $(obj)/vsyscall-%.so: $(src)/vsyscall.lds $(obj)/vsyscall-%.o FORCE
        $(call if_changed,syscall)
 
 AFLAGS_vsyscall-sysenter.o = -m32 -Wa,-32 -Iarch/i386/kernel
 AFLAGS_vsyscall-syscall.o = -m32 -Wa,-32 -Iarch/i386/kernel
-
-ifdef CONFIG_XEN
 AFLAGS_vsyscall-int80.o = -m32 -Wa,-32 -Iarch/i386/kernel
-CFLAGS_syscall32.o += -DUSE_INT80
-AFLAGS_syscall32_syscall.o += -DUSE_INT80
-
-$(obj)/syscall32_syscall.o: $(obj)/vsyscall-int80.so
-endif
Index: head-2007-08-07/arch/x86_64/ia32/ia32entry-xen.S
===================================================================
--- head-2007-08-07.orig/arch/x86_64/ia32/ia32entry-xen.S       2007-08-08 
12:33:23.000000000 +0200
+++ head-2007-08-07/arch/x86_64/ia32/ia32entry-xen.S    2007-07-03 
15:12:20.000000000 +0200
@@ -80,7 +80,7 @@
  * %ebp user stack
  * 0(%ebp) Arg6        
  *     
- * Interrupts off.
+ * Interrupts on.
  *     
  * 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
@@ -89,38 +89,25 @@
  */    
 ENTRY(ia32_sysenter_target)
        CFI_STARTPROC32 simple
-       CFI_DEF_CFA     rsp,0
-       CFI_REGISTER    rsp,rbp
-       __swapgs 
-       movq    %gs:pda_kernelstack, %rsp
-       addq    $(PDA_STACKOFFSET),%rsp
-       /*
-        * No need to follow this irqs on/off section: the syscall
-        * disabled irqs, here we enable it straight after entry:
-        */
-       XEN_UNBLOCK_EVENTS(%r11)        
-       __sti
+       CFI_DEF_CFA     rsp,SS+8-RIP+16
+       /*CFI_REL_OFFSET        ss,SS-RIP+16*/
+       CFI_REL_OFFSET  rsp,RSP-RIP+16
+       /*CFI_REL_OFFSET        rflags,EFLAGS-RIP+16*/
+       /*CFI_REL_OFFSET        cs,CS-RIP+16*/
+       CFI_REL_OFFSET  rip,RIP-RIP+16
+       CFI_REL_OFFSET  r11,8
+       CFI_REL_OFFSET  rcx,0
+       movq    8(%rsp),%r11
+       CFI_RESTORE     r11
+       popq    %rcx
+       CFI_ADJUST_CFA_OFFSET -8
+       CFI_RESTORE     rcx
        movl    %ebp,%ebp               /* zero extension */
-       pushq   $__USER32_DS
-       CFI_ADJUST_CFA_OFFSET 8
-       /*CFI_REL_OFFSET ss,0*/
-       pushq   %rbp
-       CFI_ADJUST_CFA_OFFSET 8
-       CFI_REL_OFFSET rsp,0
-       pushfq
-       CFI_ADJUST_CFA_OFFSET 8
-       /*CFI_REL_OFFSET rflags,0*/
-       movl    $VSYSCALL32_SYSEXIT, %r10d
-       CFI_REGISTER rip,r10
-       pushq   $__USER32_CS
-       CFI_ADJUST_CFA_OFFSET 8
-       /*CFI_REL_OFFSET cs,0*/
-       movl    %eax, %eax
-       pushq   %r10
-       CFI_ADJUST_CFA_OFFSET 8
-       CFI_REL_OFFSET rip,0
-       pushq   %rax
-       CFI_ADJUST_CFA_OFFSET 8
+       movl    %eax,%eax
+       movl    $__USER32_DS,40(%rsp)
+       movq    %rbp,32(%rsp)
+       movl    $__USER32_CS,16(%rsp)
+       movq    %rax,(%rsp)
        cld
        SAVE_ARGS 0,0,0
        /* no need to do an access_ok check here because rbp has been
@@ -132,7 +119,6 @@ ENTRY(ia32_sysenter_target)
        GET_THREAD_INFO(%r10)
        orl    $TS_COMPAT,threadinfo_status(%r10)
        testl  
$(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10)
-       CFI_REMEMBER_STATE
        jnz  sysenter_tracesys
 sysenter_do_call:      
        cmpl    $(IA32_NR_syscalls-1),%eax
@@ -140,33 +126,9 @@ sysenter_do_call:  
        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
-       TRACE_IRQS_OFF
-       testl   $_TIF_ALLWORK_MASK,threadinfo_flags(%r10)
-       jnz     int_ret_from_sys_call
-       andl    $~TS_COMPAT,threadinfo_status(%r10)
-       /* clear IF, that popfq doesn't enable interrupts early */
-       andl  $~0x200,EFLAGS-R11(%rsp) 
-       RESTORE_ARGS 1,24,1,1,1,1
-       popfq
-       CFI_ADJUST_CFA_OFFSET -8
-       /*CFI_RESTORE rflags*/
-       popq    %rcx                            /* User %esp */
-       CFI_ADJUST_CFA_OFFSET -8
-       CFI_REGISTER rsp,rcx
-       movl    $VSYSCALL32_SYSEXIT,%edx        /* User %eip */
-       CFI_REGISTER rip,rdx
-       TRACE_IRQS_ON
-       __swapgs
-       XEN_UNBLOCK_EVENTS(%r11)                
-       __sti           /* sti only takes effect after the next instruction */
-       /* sysexit */
-       .byte   0xf, 0x35  /* TBD */
+       jmp int_ret_from_sys_call
 
 sysenter_tracesys:
-       CFI_RESTORE_STATE
        SAVE_REST
        CLEAR_RREGS
        movq    $-ENOSYS,RAX(%rsp)      /* really needed? */
@@ -199,7 +161,7 @@ ENDPROC(ia32_sysenter_target)
  * %esp user stack 
  * 0(%esp) Arg6
  *     
- * Interrupts off.
+ * Interrupts on.
  *     
  * 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
@@ -208,32 +170,20 @@ ENDPROC(ia32_sysenter_target)
  */    
 ENTRY(ia32_cstar_target)
        CFI_STARTPROC32 simple
-       CFI_DEF_CFA     rsp,PDA_STACKOFFSET
-       CFI_REGISTER    rip,rcx
-       /*CFI_REGISTER  rflags,r11*/
-       __swapgs
-       movl    %esp,%r8d
-       CFI_REGISTER    rsp,r8
-       movq    %gs:pda_kernelstack,%rsp
-       /*
-        * No need to follow this irqs on/off section: the syscall
-        * disabled irqs and here we enable it straight after entry:
-        */
-       XEN_UNBLOCK_EVENTS(%r11)        
-       __sti
-       SAVE_ARGS 8,1,1
+       CFI_DEF_CFA     rsp,SS+8-RIP+16
+       /*CFI_REL_OFFSET        ss,SS-RIP+16*/
+       CFI_REL_OFFSET  rsp,RSP-RIP+16
+       /*CFI_REL_OFFSET        rflags,EFLAGS-RIP+16*/
+       /*CFI_REL_OFFSET        cs,CS-RIP+16*/
+       CFI_REL_OFFSET  rip,RIP-RIP+16
        movl    %eax,%eax       /* zero extension */
+       movl    RSP-RIP+16(%rsp),%r8d
+       SAVE_ARGS -8,1,1
        movq    %rax,ORIG_RAX-ARGOFFSET(%rsp)
-       movq    %rcx,RIP-ARGOFFSET(%rsp)
-       CFI_REL_OFFSET rip,RIP-ARGOFFSET
        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)
-       /*CFI_REL_OFFSET rflags,EFLAGS-ARGOFFSET*/
-       movq    %r8,RSP-ARGOFFSET(%rsp) 
-       CFI_REL_OFFSET rsp,RSP-ARGOFFSET
+       movl    $__USER32_CS,CS-ARGOFFSET(%rsp)
+       movl    $__USER32_DS,SS-ARGOFFSET(%rsp)
        /* no need to do an access_ok check here because r8 has been
           32bit zero extended */ 
        /* hardware stack frame is complete now */      
@@ -244,7 +194,6 @@ ENTRY(ia32_cstar_target)
        GET_THREAD_INFO(%r10)
        orl   $TS_COMPAT,threadinfo_status(%r10)
        testl 
$(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%r10)
-       CFI_REMEMBER_STATE
        jnz   cstar_tracesys
 cstar_do_call: 
        cmpl $IA32_NR_syscalls-1,%eax
@@ -252,26 +201,9 @@ cstar_do_call:     
        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
-       TRACE_IRQS_OFF
-       testl $_TIF_ALLWORK_MASK,threadinfo_flags(%r10)
-       jnz  int_ret_from_sys_call
-       andl $~TS_COMPAT,threadinfo_status(%r10)
-       RESTORE_ARGS 1,-ARG_SKIP,1,1,1
-       movl RIP-ARGOFFSET(%rsp),%ecx
-       CFI_REGISTER rip,rcx
-       movl EFLAGS-ARGOFFSET(%rsp),%r11d       
-       /*CFI_REGISTER rflags,r11*/
-       TRACE_IRQS_ON
-       movl RSP-ARGOFFSET(%rsp),%esp
-       CFI_RESTORE rsp
-       __swapgs
-       sysretl  /* TBD */
+       jmp int_ret_from_sys_call
        
 cstar_tracesys:        
-       CFI_RESTORE_STATE
        SAVE_REST
        CLEAR_RREGS
        movq $-ENOSYS,RAX(%rsp) /* really needed? */
@@ -312,32 +244,27 @@ ia32_badarg:
  * 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.  
+ * Assumes it is only called from user space and entered with interrupts on.
  */                            
 
 ENTRY(ia32_syscall)
        CFI_STARTPROC   simple
-       CFI_DEF_CFA     rsp,SS+8-RIP
-       /*CFI_REL_OFFSET        ss,SS-RIP*/
-       CFI_REL_OFFSET  rsp,RSP-RIP
-       /*CFI_REL_OFFSET        rflags,EFLAGS-RIP*/
-       /*CFI_REL_OFFSET        cs,CS-RIP*/
-       CFI_REL_OFFSET  rip,RIP-RIP
-       __swapgs
-       /*
-        * No need to follow this irqs on/off section: the syscall
-        * disabled irqs and here we enable it straight after entry:
-        */
-       XEN_UNBLOCK_EVENTS(%r11)
-       __sti
-       movq (%rsp),%rcx
+       CFI_DEF_CFA     rsp,SS+8-RIP+16
+       /*CFI_REL_OFFSET        ss,SS-RIP+16*/
+       CFI_REL_OFFSET  rsp,RSP-RIP+16
+       /*CFI_REL_OFFSET        rflags,EFLAGS-RIP+16*/
+       /*CFI_REL_OFFSET        cs,CS-RIP+16*/
+       CFI_REL_OFFSET  rip,RIP-RIP+16
+       CFI_REL_OFFSET  r11,8
+       CFI_REL_OFFSET  rcx,0
        movq 8(%rsp),%r11
-        addq $0x10,%rsp /* skip rcx and r11 */
+       CFI_RESTORE     r11
+       popq %rcx
+       CFI_ADJUST_CFA_OFFSET -8
+       CFI_RESTORE     rcx
        movl %eax,%eax
-       pushq %rax
-       CFI_ADJUST_CFA_OFFSET 8
+       movq %rax,(%rsp)
        cld
-/* 1:  jmp 1b   */
        /* note the registers are not zero extended to the sf.
           this could be a problem. */
        SAVE_ARGS 0,0,1
Index: head-2007-08-07/arch/x86_64/ia32/syscall32_syscall-xen.S
===================================================================
--- head-2007-08-07.orig/arch/x86_64/ia32/syscall32_syscall-xen.S       
2007-08-08 12:33:23.000000000 +0200
+++ head-2007-08-07/arch/x86_64/ia32/syscall32_syscall-xen.S    2007-07-03 
14:01:17.000000000 +0200
@@ -2,7 +2,7 @@
 
        .section ".init.data","aw"
 
-#ifdef USE_INT80
+#if CONFIG_XEN_COMPAT < 0x030200
 
        .globl syscall32_int80
        .globl syscall32_int80_end
Index: head-2007-08-07/arch/x86_64/ia32/syscall32-xen.c
===================================================================
--- head-2007-08-07.orig/arch/x86_64/ia32/syscall32-xen.c       2007-08-08 
12:33:23.000000000 +0200
+++ head-2007-08-07/arch/x86_64/ia32/syscall32-xen.c    2007-08-08 
12:34:10.000000000 +0200
@@ -14,17 +14,18 @@
 #include <asm/proto.h>
 #include <asm/tlbflush.h>
 #include <asm/ia32_unistd.h>
+#include <xen/interface/callback.h>
 
-#ifdef USE_INT80
-extern unsigned char syscall32_int80[], syscall32_int80_end[];
-#endif
 extern unsigned char syscall32_syscall[], syscall32_syscall_end[];
 extern unsigned char syscall32_sysenter[], syscall32_sysenter_end[];
 extern int sysctl_vsyscall32;
 
 char *syscall32_page; 
-#ifndef USE_INT80
 static int use_sysenter = -1;
+
+#if CONFIG_XEN_COMPAT < 0x030200
+extern unsigned char syscall32_int80[], syscall32_int80_end[];
+static int use_int80 = 1;
 #endif
 
 static struct page *
@@ -69,13 +70,12 @@ static int __init init_syscall32(void)
        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 CONFIG_XEN_COMPAT < 0x030200
+       if (use_int80) {
+               memcpy(syscall32_page, syscall32_int80,
+                      syscall32_int80_end - syscall32_int80);
+       } else
+#endif
        if (use_sysenter > 0) {
                memcpy(syscall32_page, syscall32_sysenter,
                       syscall32_sysenter_end - syscall32_sysenter);
@@ -83,7 +83,6 @@ static int __init init_syscall32(void)
                memcpy(syscall32_page, syscall32_syscall,
                       syscall32_syscall_end - syscall32_syscall);
        }       
-#endif
        return 0;
 } 
 
@@ -96,16 +95,35 @@ core_initcall(init_syscall32); 
 /* May not be __init: called during resume */
 void syscall32_cpu_init(void)
 {
-#ifndef USE_INT80
+       static struct callback_register cstar = {
+               .type = CALLBACKTYPE_syscall32,
+               .address = (unsigned long)ia32_cstar_target
+       };
+       static struct callback_register sysenter = {
+               .type = CALLBACKTYPE_sysenter,
+               .address = (unsigned long)ia32_sysenter_target
+       };
+       static struct callback_register sysexit = {
+               .type = CALLBACKTYPE_sysexit,
+               .address = (unsigned long)VSYSCALL32_SYSEXIT
+       };
+
+       if (HYPERVISOR_callback_op(CALLBACKOP_register, &sysexit) < 0)
+#if CONFIG_XEN_COMPAT < 0x030200
+               return;
+       use_int80 = 0;
+#else
+               BUG();
+#endif
+
        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);
-       checking_wrmsrl(MSR_IA32_SYSENTER_ESP, 0ULL);
-       checking_wrmsrl(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target);
+       if (HYPERVISOR_callback_op(CALLBACKOP_register, &sysenter) < 0)
+               BUG();
 
-       wrmsrl(MSR_CSTAR, ia32_cstar_target);
-#endif
+       if (HYPERVISOR_callback_op(CALLBACKOP_register, &cstar) < 0)
+               BUG();
 }
Index: head-2007-08-07/arch/x86_64/kernel/entry-xen.S
===================================================================
--- head-2007-08-07.orig/arch/x86_64/kernel/entry-xen.S 2007-08-08 
12:33:23.000000000 +0200
+++ head-2007-08-07/arch/x86_64/kernel/entry-xen.S      2007-08-07 
16:21:38.000000000 +0200
@@ -244,7 +244,7 @@ END(ret_from_fork)
  * r11  eflags for syscall/sysret, temporary for C
  * r12-r15,rbp,rbx saved by C code, not touched.               
  * 
- * Interrupts are off on entry.
+ * Interrupts are enabled on entry.
  * Only called from user space.
  *
  * XXX if we had a free scratch register we could save the RSP into the stack 
frame
@@ -259,11 +259,6 @@ ENTRY(system_call)
        _frame (RIP-0x10)
        SAVE_ARGS -8,0
        movq  %rax,ORIG_RAX-ARGOFFSET(%rsp) 
-       /*
-        * No need to follow this irqs off/on section - it's straight
-        * and short:
-        */
-        XEN_UNBLOCK_EVENTS(%r11)        
        GET_THREAD_INFO(%rcx)
        testl 
$(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%rcx)
        CFI_REMEMBER_STATE
Index: head-2007-08-07/arch/x86_64/kernel/process-xen.c
===================================================================
--- head-2007-08-07.orig/arch/x86_64/kernel/process-xen.c       2007-08-08 
12:33:23.000000000 +0200
+++ head-2007-08-07/arch/x86_64/kernel/process-xen.c    2007-07-04 
10:03:04.000000000 +0200
@@ -584,7 +584,10 @@ __switch_to(struct task_struct *prev_p, 
                mcl++;
        }
 
-       (void)HYPERVISOR_multicall(_mcl, mcl - _mcl);
+       BUG_ON(mcl > _mcl + ARRAY_SIZE(_mcl));
+       if (unlikely(HYPERVISOR_multicall_check(_mcl, mcl - _mcl, NULL)))
+               BUG();
+
        /* 
         * Switch DS and ES.
         * This won't pick up thread selector changes, but I guess that is ok.
Index: head-2007-08-07/arch/x86_64/kernel/setup64-xen.c
===================================================================
--- head-2007-08-07.orig/arch/x86_64/kernel/setup64-xen.c       2007-08-08 
12:33:23.000000000 +0200
+++ head-2007-08-07/arch/x86_64/kernel/setup64-xen.c    2007-08-07 
17:06:30.000000000 +0200
@@ -29,6 +29,7 @@
 #include <asm/sections.h>
 #ifdef CONFIG_XEN
 #include <asm/hypervisor.h>
+#include <xen/interface/callback.h>
 #endif
 
 char x86_boot_params[BOOT_PARAM_SIZE] __initdata = {0,};
@@ -211,21 +212,33 @@
 /* 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); 
+       static struct callback_register lstar = {
+               .type = CALLBACKTYPE_syscall,
+               .address = (unsigned long)system_call
+       };
+       static struct callback_register sfmask = {
+               .type = CALLBACKTYPE_sfmask,
+               .address = EF_TF|EF_DF
+       };
 
-       /* Flags to clear on syscall */
-       wrmsrl(MSR_SYSCALL_MASK, EF_TF|EF_DF|EF_IE|0x3000); 
+#if CONFIG_XEN_COMPAT < 0x030200
+       /*
+        * Can't check SYSCALL flag here, as it is always on; SEP indicates
+        * availability of the new callback types.
+        */
+       if (!boot_cpu_has(X86_FEATURE_SEP))
+               return;
 #endif
+       if (HYPERVISOR_callback_op(CALLBACKOP_register, &lstar) < 0)
+               BUG();
+
 #ifdef CONFIG_IA32_EMULATION                   
        syscall32_cpu_init ();
 #endif
+
+       /* Flags to clear on syscall */
+       if (HYPERVISOR_callback_op(CALLBACKOP_register, &sfmask) < 0)
+               BUG();
 }
 
 void __cpuinit check_efer(void)
Index: head-2007-08-07/arch/x86_64/kernel/traps-xen.c
===================================================================
--- head-2007-08-07.orig/arch/x86_64/kernel/traps-xen.c 2007-08-08 
12:33:23.000000000 +0200
+++ head-2007-08-07/arch/x86_64/kernel/traps-xen.c      2007-07-03 
14:01:17.000000000 +0200
@@ -1107,7 +1107,7 @@ static trap_info_t trap_table[] = {
 #endif
         { 19, 0|4, __KERNEL_CS, (unsigned long)simd_coprocessor_error     },
 #ifdef CONFIG_IA32_EMULATION
-       { IA32_SYSCALL_VECTOR, 3|4, __KERNEL_CS, (unsigned long)ia32_syscall},
+       { IA32_SYSCALL_VECTOR, 3, __KERNEL_CS, (unsigned long)ia32_syscall},
 #endif
         {  0, 0,           0, 0                                              }
 };
Index: head-2007-08-07/drivers/xen/Kconfig
===================================================================
--- head-2007-08-07.orig/drivers/xen/Kconfig    2007-08-08 12:33:23.000000000 
+0200
+++ head-2007-08-07/drivers/xen/Kconfig 2007-07-03 14:01:17.000000000 +0200
@@ -13,7 +13,7 @@ config XEN
 if XEN
 config XEN_INTERFACE_VERSION
        hex
-       default 0x00030205
+       default 0x00030206
 
 menu "XEN"
 
@@ -237,6 +237,9 @@ choice
        config XEN_COMPAT_030004_AND_LATER
                bool "3.0.4 and later"
 
+       config XEN_COMPAT_030100_AND_LATER
+               bool "3.1.0 and later"
+
        config XEN_COMPAT_LATEST_ONLY
                bool "no compatibility code"
 
@@ -245,6 +248,7 @@ endchoice
 config XEN_COMPAT
        hex
        default 0xffffff if XEN_COMPAT_LATEST_ONLY
+       default 0x030100 if XEN_COMPAT_030100_AND_LATER
        default 0x030004 if XEN_COMPAT_030004_AND_LATER
        default 0x030002 if XEN_COMPAT_030002_AND_LATER
        default 0
Index: head-2007-08-07/drivers/xen/core/smpboot.c
===================================================================
--- head-2007-08-07.orig/drivers/xen/core/smpboot.c     2007-08-08 
12:33:23.000000000 +0200
+++ head-2007-08-07/drivers/xen/core/smpboot.c  2007-07-03 14:46:21.000000000 
+0200
@@ -172,6 +172,7 @@ static void xen_smp_intr_exit(unsigned i
 void cpu_bringup(void)
 {
        cpu_init();
+       identify_cpu(cpu_data + smp_processor_id());
        touch_softlockup_watchdog();
        preempt_disable();
        local_irq_enable();
Index: head-2007-08-07/include/asm-x86_64/mach-xen/setup_arch_post.h
===================================================================
--- head-2007-08-07.orig/include/asm-x86_64/mach-xen/setup_arch_post.h  
2007-08-08 12:33:23.000000000 +0200
+++ head-2007-08-07/include/asm-x86_64/mach-xen/setup_arch_post.h       
2007-07-05 15:12:30.000000000 +0200
@@ -23,10 +23,12 @@ static void __init machine_specific_arch
                .type = CALLBACKTYPE_failsafe,
                .address = (unsigned long)failsafe_callback,
        };
+#if CONFIG_XEN_COMPAT < 0x030200
        static struct callback_register __initdata syscall = {
                .type = CALLBACKTYPE_syscall,
                .address = (unsigned long)system_call,
        };
+#endif
 #ifdef CONFIG_X86_LOCAL_APIC
        static struct callback_register __initdata nmi_cb = {
                .type = CALLBACKTYPE_nmi,
@@ -35,8 +37,10 @@ static void __init machine_specific_arch
        ret = HYPERVISOR_callback_op(CALLBACKOP_register, &event);
        if (ret == 0)
                ret = HYPERVISOR_callback_op(CALLBACKOP_register, &failsafe);
+#if CONFIG_XEN_COMPAT < 0x030200
        if (ret == 0)
                ret = HYPERVISOR_callback_op(CALLBACKOP_register, &syscall);
+#endif
 #if CONFIG_XEN_COMPAT <= 0x030002
        if (ret == -ENOSYS)
                ret = HYPERVISOR_set_callbacks(
Index: head-2007-08-07/include/xen/interface/callback.h
===================================================================
--- head-2007-08-07.orig/include/xen/interface/callback.h       2007-08-08 
12:33:23.000000000 +0200
+++ head-2007-08-07/include/xen/interface/callback.h    2007-07-03 
10:39:14.000000000 +0200
@@ -38,13 +38,34 @@
 
 #define CALLBACKTYPE_event                 0
 #define CALLBACKTYPE_failsafe              1
-#define CALLBACKTYPE_syscall               2 /* x86_64 only */
+#define CALLBACKTYPE_syscall               2 /* x86_64 hv only */
 /*
- * sysenter is only available on x86_32 with the
- * supervisor_mode_kernel option enabled.
+ * sysenter_deprecated is only available on x86_32 with the
+ * supervisor_mode_kernel option enabled, and should not be used in new code.
  */
-#define CALLBACKTYPE_sysenter              3
+#define CALLBACKTYPE_sysenter_deprecated   3
 #define CALLBACKTYPE_nmi                   4
+#if __XEN_INTERFACE_VERSION__ < 0x00030206
+#define CALLBACKTYPE_sysenter              CALLBACKTYPE_sysenter_deprecated
+#else
+/*
+ * sysenter is only available
+ * - on x86_32 with the supervisor_mode_kernel option enabled,
+ * - on x86_64 hv for x86_32 pv or 32-bit guest support in x86_64 pv.
+ */
+#define CALLBACKTYPE_sysenter              5
+/*
+ * sysexit is only available on x86_64 hv, and is only used to fill a
+ * sysenter frame's return address (if the guest desires to have a non-NULL
+ * value there). Additionally, since CALLBACKF_mask_events is meaningless
+ * here, it is being (mis-)used for 64-bits guests to distinguish sysenter
+ * callers expected to be in 64-bit mode (flag set) from 32-bit ones (flag
+ * clear).
+ */
+#define CALLBACKTYPE_sysexit               6
+#define CALLBACKTYPE_syscall32             7 /* x86_64 only */
+#define CALLBACKTYPE_sfmask                8 /* x86_64 only */
+#endif
 
 /*
  * Disable event deliver during callback? This flag is ignored for event and
Index: head-2007-08-07/include/xen/interface/xen-compat.h
===================================================================
--- head-2007-08-07.orig/include/xen/interface/xen-compat.h     2007-08-08 
12:33:23.000000000 +0200
+++ head-2007-08-07/include/xen/interface/xen-compat.h  2007-07-03 
10:39:14.000000000 +0200
@@ -27,7 +27,7 @@
 #ifndef __XEN_PUBLIC_XEN_COMPAT_H__
 #define __XEN_PUBLIC_XEN_COMPAT_H__
 
-#define __XEN_LATEST_INTERFACE_VERSION__ 0x00030205
+#define __XEN_LATEST_INTERFACE_VERSION__ 0x00030206
 
 #if defined(__XEN__) || defined(__XEN_TOOLS__)
 /* Xen is built with matching headers and implements the latest interface. */



_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.