linux-stable/include/linux/huge_mm.h
Andrea Arcangeli 37a1c49a91 thp: mremap support and TLB optimization
This adds THP support to mremap (decreases the number of split_huge_page()
calls).

Here are also some benchmarks with a proggy like this:

===
#define _GNU_SOURCE
#include <sys/mman.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <sys/time.h>

#define SIZE (5UL*1024*1024*1024)

int main()
{
        static struct timeval oldstamp, newstamp;
	long diffsec;
	char *p, *p2, *p3, *p4;
	if (posix_memalign((void **)&p, 2*1024*1024, SIZE))
		perror("memalign"), exit(1);
	if (posix_memalign((void **)&p2, 2*1024*1024, SIZE))
		perror("memalign"), exit(1);
	if (posix_memalign((void **)&p3, 2*1024*1024, 4096))
		perror("memalign"), exit(1);

	memset(p, 0xff, SIZE);
	memset(p2, 0xff, SIZE);
	memset(p3, 0x77, 4096);
	gettimeofday(&oldstamp, NULL);
	p4 = mremap(p, SIZE, SIZE, MREMAP_FIXED|MREMAP_MAYMOVE, p3);
	gettimeofday(&newstamp, NULL);
	diffsec = newstamp.tv_sec - oldstamp.tv_sec;
	diffsec = newstamp.tv_usec - oldstamp.tv_usec + 1000000 * diffsec;
	printf("usec %ld\n", diffsec);
	if (p == MAP_FAILED || p4 != p3)
	//if (p == MAP_FAILED)
		perror("mremap"), exit(1);
	if (memcmp(p4, p2, SIZE))
		printf("mremap bug\n"), exit(1);
	printf("ok\n");

	return 0;
}
===

THP on

 Performance counter stats for './largepage13' (3 runs):

          69195836 dTLB-loads                 ( +-   3.546% )  (scaled from 50.30%)
             60708 dTLB-load-misses           ( +-  11.776% )  (scaled from 52.62%)
         676266476 dTLB-stores                ( +-   5.654% )  (scaled from 69.54%)
             29856 dTLB-store-misses          ( +-   4.081% )  (scaled from 89.22%)
        1055848782 iTLB-loads                 ( +-   4.526% )  (scaled from 80.18%)
              8689 iTLB-load-misses           ( +-   2.987% )  (scaled from 58.20%)

        7.314454164  seconds time elapsed   ( +-   0.023% )

THP off

 Performance counter stats for './largepage13' (3 runs):

        1967379311 dTLB-loads                 ( +-   0.506% )  (scaled from 60.59%)
           9238687 dTLB-load-misses           ( +-  22.547% )  (scaled from 61.87%)
        2014239444 dTLB-stores                ( +-   0.692% )  (scaled from 60.40%)
           3312335 dTLB-store-misses          ( +-   7.304% )  (scaled from 67.60%)
        6764372065 iTLB-loads                 ( +-   0.925% )  (scaled from 79.00%)
              8202 iTLB-load-misses           ( +-   0.475% )  (scaled from 70.55%)

        9.693655243  seconds time elapsed   ( +-   0.069% )

grep thp /proc/vmstat
thp_fault_alloc 35849
thp_fault_fallback 0
thp_collapse_alloc 3
thp_collapse_alloc_failed 0
thp_split 0

thp_split 0 confirms no thp split despite plenty of hugepages allocated.

The measurement of only the mremap time (so excluding the 3 long
memset and final long 10GB memory accessing memcmp):

THP on

usec 14824
usec 14862
usec 14859

THP off

usec 256416
usec 255981
usec 255847

With an older kernel without the mremap optimizations (the below patch
optimizes the non THP version too).

THP on

usec 392107
usec 390237
usec 404124

THP off

usec 444294
usec 445237
usec 445820

I guess with a threaded program that sends more IPI on large SMP it'd
create an even larger difference.

All debug options are off except DEBUG_VM to avoid skewing the
results.

The only problem for native 2M mremap like it happens above both the
source and destination address must be 2M aligned or the hugepmd can't be
moved without a split but that is an hardware limitation.

[akpm@linux-foundation.org: coding-style nitpicking]
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Johannes Weiner <jweiner@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-10-31 17:30:48 -07:00

181 lines
5.9 KiB
C

#ifndef _LINUX_HUGE_MM_H
#define _LINUX_HUGE_MM_H
extern int do_huge_pmd_anonymous_page(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd,
unsigned int flags);
extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
struct vm_area_struct *vma);
extern int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd,
pmd_t orig_pmd);
extern pgtable_t get_pmd_huge_pte(struct mm_struct *mm);
extern struct page *follow_trans_huge_pmd(struct mm_struct *mm,
unsigned long addr,
pmd_t *pmd,
unsigned int flags);
extern int zap_huge_pmd(struct mmu_gather *tlb,
struct vm_area_struct *vma,
pmd_t *pmd);
extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
unsigned char *vec);
extern int move_huge_pmd(struct vm_area_struct *vma,
struct vm_area_struct *new_vma,
unsigned long old_addr,
unsigned long new_addr, unsigned long old_end,
pmd_t *old_pmd, pmd_t *new_pmd);
extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, pgprot_t newprot);
enum transparent_hugepage_flag {
TRANSPARENT_HUGEPAGE_FLAG,
TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
TRANSPARENT_HUGEPAGE_DEFRAG_FLAG,
TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG,
#ifdef CONFIG_DEBUG_VM
TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG,
#endif
};
enum page_check_address_pmd_flag {
PAGE_CHECK_ADDRESS_PMD_FLAG,
PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG,
PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG,
};
extern pmd_t *page_check_address_pmd(struct page *page,
struct mm_struct *mm,
unsigned long address,
enum page_check_address_pmd_flag flag);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define HPAGE_PMD_SHIFT HPAGE_SHIFT
#define HPAGE_PMD_MASK HPAGE_MASK
#define HPAGE_PMD_SIZE HPAGE_SIZE
#define transparent_hugepage_enabled(__vma) \
((transparent_hugepage_flags & \
(1<<TRANSPARENT_HUGEPAGE_FLAG) || \
(transparent_hugepage_flags & \
(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG) && \
((__vma)->vm_flags & VM_HUGEPAGE))) && \
!((__vma)->vm_flags & VM_NOHUGEPAGE) && \
!is_vma_temporary_stack(__vma))
#define transparent_hugepage_defrag(__vma) \
((transparent_hugepage_flags & \
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_FLAG)) || \
(transparent_hugepage_flags & \
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG) && \
(__vma)->vm_flags & VM_HUGEPAGE))
#ifdef CONFIG_DEBUG_VM
#define transparent_hugepage_debug_cow() \
(transparent_hugepage_flags & \
(1<<TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG))
#else /* CONFIG_DEBUG_VM */
#define transparent_hugepage_debug_cow() 0
#endif /* CONFIG_DEBUG_VM */
extern unsigned long transparent_hugepage_flags;
extern int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pmd_t *dst_pmd, pmd_t *src_pmd,
struct vm_area_struct *vma,
unsigned long addr, unsigned long end);
extern int handle_pte_fault(struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long address,
pte_t *pte, pmd_t *pmd, unsigned int flags);
extern int split_huge_page(struct page *page);
extern void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd);
#define split_huge_page_pmd(__mm, __pmd) \
do { \
pmd_t *____pmd = (__pmd); \
if (unlikely(pmd_trans_huge(*____pmd))) \
__split_huge_page_pmd(__mm, ____pmd); \
} while (0)
#define wait_split_huge_page(__anon_vma, __pmd) \
do { \
pmd_t *____pmd = (__pmd); \
anon_vma_lock(__anon_vma); \
anon_vma_unlock(__anon_vma); \
BUG_ON(pmd_trans_splitting(*____pmd) || \
pmd_trans_huge(*____pmd)); \
} while (0)
#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
#if HPAGE_PMD_ORDER > MAX_ORDER
#error "hugepages can't be allocated by the buddy allocator"
#endif
extern int hugepage_madvise(struct vm_area_struct *vma,
unsigned long *vm_flags, int advice);
extern void __vma_adjust_trans_huge(struct vm_area_struct *vma,
unsigned long start,
unsigned long end,
long adjust_next);
static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
unsigned long start,
unsigned long end,
long adjust_next)
{
if (!vma->anon_vma || vma->vm_ops)
return;
__vma_adjust_trans_huge(vma, start, end, adjust_next);
}
static inline int hpage_nr_pages(struct page *page)
{
if (unlikely(PageTransHuge(page)))
return HPAGE_PMD_NR;
return 1;
}
static inline struct page *compound_trans_head(struct page *page)
{
if (PageTail(page)) {
struct page *head;
head = page->first_page;
smp_rmb();
/*
* head may be a dangling pointer.
* __split_huge_page_refcount clears PageTail before
* overwriting first_page, so if PageTail is still
* there it means the head pointer isn't dangling.
*/
if (PageTail(page))
return head;
}
return page;
}
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
#define HPAGE_PMD_SHIFT ({ BUG(); 0; })
#define HPAGE_PMD_MASK ({ BUG(); 0; })
#define HPAGE_PMD_SIZE ({ BUG(); 0; })
#define hpage_nr_pages(x) 1
#define transparent_hugepage_enabled(__vma) 0
#define transparent_hugepage_flags 0UL
static inline int split_huge_page(struct page *page)
{
return 0;
}
#define split_huge_page_pmd(__mm, __pmd) \
do { } while (0)
#define wait_split_huge_page(__anon_vma, __pmd) \
do { } while (0)
#define compound_trans_head(page) compound_head(page)
static inline int hugepage_madvise(struct vm_area_struct *vma,
unsigned long *vm_flags, int advice)
{
BUG();
return 0;
}
static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
unsigned long start,
unsigned long end,
long adjust_next)
{
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif /* _LINUX_HUGE_MM_H */