Christopher Lameter <c...@linux.com> writes:
> On Mon, 7 Aug 2017, Huang, Ying wrote:
>
>> --- a/mm/memory.c
>> +++ b/mm/memory.c
>> @@ -4374,9 +4374,31 @@ void clear_huge_page(struct page *page,
>> }
>>
>> might_sleep();
>> - for (i = 0; i < pages_per_huge_page; i++) {
>> + VM_BUG_ON(clamp(addr_hint, addr, addr +
>> + (pages_per_huge_page << PAGE_SHIFT)) != addr_hint);
>> + n = (addr_hint - addr) / PAGE_SIZE;
>> + if (2 * n <= pages_per_huge_page) {
>> + base = 0;
>> + l = n;
>> + for (i = pages_per_huge_page - 1; i >= 2 * n; i--) {
>> + cond_resched();
>> + clear_user_highpage(page + i, addr + i * PAGE_SIZE);
>> + }
>
> I really like the idea behind the patch but this is not clearing from last
> to first byte of the huge page.
>
> What seems to be happening here is clearing from the last page to the
> first page and I would think that within each page the clearing is from
> first byte to last byte. Maybe more gains can be had by really clearing
> from last to first byte of the huge page instead of this jumping over 4k
> addresses?
I changed the code to use clear_page_orig() and make it clear pages from
last to first. The patch is as below.
With that, there is no visible changes in benchmark result. But the
cache miss rate dropped a little from 27.64% to 26.70%. The cache miss
rate is different with before because the clear_page() implementation
used is different.
I think this is because the size of page is relative small compared with
the cache size, so that the effect is almost invisible.
Best Regards,
Huang, Ying
--------------->8----------------
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index b4a0d43248cf..01d201afde92 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -42,8 +42,8 @@ void clear_page_erms(void *page);
static inline void clear_page(void *page)
{
alternative_call_2(clear_page_orig,
- clear_page_rep, X86_FEATURE_REP_GOOD,
- clear_page_erms, X86_FEATURE_ERMS,
+ clear_page_orig, X86_FEATURE_REP_GOOD,
+ clear_page_orig, X86_FEATURE_ERMS,
"=D" (page),
"0" (page)
: "memory", "rax", "rcx");
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index 81b1635d67de..23e6238e625d 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -25,19 +25,20 @@ EXPORT_SYMBOL_GPL(clear_page_rep)
ENTRY(clear_page_orig)
xorl %eax,%eax
movl $4096/64,%ecx
+ addq $4096-64,%rdi
.p2align 4
.Lloop:
decl %ecx
#define PUT(x) movq %rax,x*8(%rdi)
- movq %rax,(%rdi)
- PUT(1)
- PUT(2)
- PUT(3)
- PUT(4)
- PUT(5)
- PUT(6)
PUT(7)
- leaq 64(%rdi),%rdi
+ PUT(6)
+ PUT(5)
+ PUT(4)
+ PUT(3)
+ PUT(2)
+ PUT(1)
+ movq %rax,(%rdi)
+ leaq -64(%rdi),%rdi
jnz .Lloop
nop
ret
