|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [xen master] x86: introduce ioremap_wc()
commit 81d195c6c0e2ee1b706d19dbbb57f73bbf6b81b4
Author: Jan Beulich <jbeulich@xxxxxxxx>
AuthorDate: Fri Feb 18 14:42:39 2022 +0100
Commit: Jan Beulich <jbeulich@xxxxxxxx>
CommitDate: Fri Feb 18 14:42:39 2022 +0100
x86: introduce ioremap_wc()
In order for a to-be-introduced ERMS form of memcpy() to not regress
boot performance on certain systems when video output is active, we
first need to arrange for avoiding further dependency on firmware
setting up MTRRs in a way we can actually further modify. On many
systems, due to the continuously growing amounts of installed memory,
MTRRs get configured with at least one huge WB range, and with MMIO
ranges below 4Gb then forced to UC via overlapping MTRRs. mtrr_add(), as
it is today, can't deal with such a setup. Hence on such systems we
presently leave the frame buffer mapped UC, leading to significantly
reduced performance when using REP STOSB / REP MOVSB.
On post-PentiumII hardware (i.e. any that's capable of running 64-bit
code), an effective memory type of WC can be achieved without MTRRs, by
simply referencing the respective PAT entry from the PTEs. While this
will leave the switch to ERMS forms of memset() and memcpy() with
largely unchanged performance, the change here on its own improves
performance on affected systems quite significantly: Measuring just the
individual affected memcpy() invocations yielded a speedup by a factor
of over 250 on my initial (Skylake) test system. memset() isn't getting
improved by as much there, but still by a factor of about 20.
While adding {__,}PAGE_HYPERVISOR_WC, also add {__,}PAGE_HYPERVISOR_WT
to, at the very least, make clear what PTE flags this memory type uses.
Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
Reviewed-by: Roger Pau Monné <roger.pau@xxxxxxxxxx>
---
xen/arch/x86/include/asm/mm.h | 2 ++
xen/arch/x86/include/asm/page.h | 2 ++
xen/arch/x86/include/asm/x86_64/page.h | 4 ++++
xen/arch/x86/mm.c | 14 ++++++++++++++
xen/drivers/video/vesa.c | 7 +++----
xen/drivers/video/vga.c | 6 +++++-
6 files changed, 30 insertions(+), 5 deletions(-)
diff --git a/xen/arch/x86/include/asm/mm.h b/xen/arch/x86/include/asm/mm.h
index 9b9de4c6be..bdde24d2ce 100644
--- a/xen/arch/x86/include/asm/mm.h
+++ b/xen/arch/x86/include/asm/mm.h
@@ -602,6 +602,8 @@ void destroy_perdomain_mapping(struct domain *, unsigned
long va,
unsigned int nr);
void free_perdomain_mappings(struct domain *);
+void __iomem *ioremap_wc(paddr_t, size_t);
+
extern int memory_add(unsigned long spfn, unsigned long epfn, unsigned int
pxm);
void domain_set_alloc_bitsize(struct domain *d);
diff --git a/xen/arch/x86/include/asm/page.h b/xen/arch/x86/include/asm/page.h
index 1d080cffbe..447491cd09 100644
--- a/xen/arch/x86/include/asm/page.h
+++ b/xen/arch/x86/include/asm/page.h
@@ -349,8 +349,10 @@ void efi_update_l4_pgtable(unsigned int l4idx,
l4_pgentry_t);
#define __PAGE_HYPERVISOR_RX (_PAGE_PRESENT | _PAGE_ACCESSED)
#define __PAGE_HYPERVISOR (__PAGE_HYPERVISOR_RX | \
_PAGE_DIRTY | _PAGE_RW)
+#define __PAGE_HYPERVISOR_WT (__PAGE_HYPERVISOR | _PAGE_PWT)
#define __PAGE_HYPERVISOR_UCMINUS (__PAGE_HYPERVISOR | _PAGE_PCD)
#define __PAGE_HYPERVISOR_UC (__PAGE_HYPERVISOR | _PAGE_PCD | _PAGE_PWT)
+#define __PAGE_HYPERVISOR_WC (__PAGE_HYPERVISOR | _PAGE_PAT)
#define __PAGE_HYPERVISOR_SHSTK (__PAGE_HYPERVISOR_RO | _PAGE_DIRTY)
#define MAP_SMALL_PAGES _PAGE_AVAIL0 /* don't use superpages mappings */
diff --git a/xen/arch/x86/include/asm/x86_64/page.h
b/xen/arch/x86/include/asm/x86_64/page.h
index cb1db107c4..26bdb4b19b 100644
--- a/xen/arch/x86/include/asm/x86_64/page.h
+++ b/xen/arch/x86/include/asm/x86_64/page.h
@@ -152,6 +152,10 @@ static inline intpte_t put_pte_flags(unsigned int x)
_PAGE_GLOBAL | _PAGE_NX)
#define PAGE_HYPERVISOR_UC (__PAGE_HYPERVISOR_UC | \
_PAGE_GLOBAL | _PAGE_NX)
+#define PAGE_HYPERVISOR_WC (__PAGE_HYPERVISOR_WC | \
+ _PAGE_GLOBAL | _PAGE_NX)
+#define PAGE_HYPERVISOR_WT (__PAGE_HYPERVISOR_WT | \
+ _PAGE_GLOBAL | _PAGE_NX)
#endif /* __X86_64_PAGE_H__ */
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index b80e4ab9c5..9c7c616253 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -5895,6 +5895,20 @@ void __iomem *ioremap(paddr_t pa, size_t len)
return (void __force __iomem *)va;
}
+void __iomem *__init ioremap_wc(paddr_t pa, size_t len)
+{
+ mfn_t mfn = _mfn(PFN_DOWN(pa));
+ unsigned int offs = pa & (PAGE_SIZE - 1);
+ unsigned int nr = PFN_UP(offs + len);
+ void *va;
+
+ WARN_ON(page_is_ram_type(mfn_x(mfn), RAM_TYPE_CONVENTIONAL));
+
+ va = __vmap(&mfn, nr, 1, 1, PAGE_HYPERVISOR_WC, VMAP_DEFAULT);
+
+ return (void __force __iomem *)(va + offs);
+}
+
int create_perdomain_mapping(struct domain *d, unsigned long va,
unsigned int nr, l1_pgentry_t **pl1tab,
struct page_info **ppg)
diff --git a/xen/drivers/video/vesa.c b/xen/drivers/video/vesa.c
index 2c1bbd9278..f9169f701f 100644
--- a/xen/drivers/video/vesa.c
+++ b/xen/drivers/video/vesa.c
@@ -9,9 +9,9 @@
#include <xen/param.h>
#include <xen/xmalloc.h>
#include <xen/kernel.h>
+#include <xen/mm.h>
#include <xen/vga.h>
#include <asm/io.h>
-#include <asm/page.h>
#include "font.h"
#include "lfb.h"
@@ -103,7 +103,7 @@ void __init vesa_init(void)
lfbp.text_columns = vlfb_info.width / font->width;
lfbp.text_rows = vlfb_info.height / font->height;
- lfbp.lfb = lfb = ioremap(lfb_base(), vram_remap);
+ lfbp.lfb = lfb = ioremap_wc(lfb_base(), vram_remap);
if ( !lfb )
return;
@@ -179,8 +179,7 @@ void __init vesa_mtrr_init(void)
static void lfb_flush(void)
{
- if ( vesa_mtrr == 3 )
- __asm__ __volatile__ ("sfence" : : : "memory");
+ __asm__ __volatile__ ("sfence" : : : "memory");
}
void __init vesa_endboot(bool_t keep)
diff --git a/xen/drivers/video/vga.c b/xen/drivers/video/vga.c
index b7f04d0d97..5e58f83c97 100644
--- a/xen/drivers/video/vga.c
+++ b/xen/drivers/video/vga.c
@@ -79,7 +79,7 @@ void __init video_init(void)
{
case XEN_VGATYPE_TEXT_MODE_3:
if ( page_is_ram_type(paddr_to_pfn(0xB8000), RAM_TYPE_CONVENTIONAL) ||
- ((video = ioremap(0xB8000, 0x8000)) == NULL) )
+ ((video = ioremap_wc(0xB8000, 0x8000)) == NULL) )
return;
outw(0x200a, 0x3d4); /* disable cursor */
columns = vga_console_info.u.text_mode_3.columns;
@@ -164,7 +164,11 @@ void __init video_endboot(void)
{
case XEN_VGATYPE_TEXT_MODE_3:
if ( !vgacon_keep )
+ {
memset(video, 0, columns * lines * 2);
+ iounmap(video);
+ video = ZERO_BLOCK_PTR;
+ }
break;
case XEN_VGATYPE_VESA_LFB:
case XEN_VGATYPE_EFI_LFB:
--
generated by git-patchbot for /home/xen/git/xen.git#master
|
 |
Lists.xenproject.org is hosted with RackSpace, monitoring our |