thp: optimize away unnecessary page table locking
Currently when we check if we can handle thp as it is or we need to split
it into regular sized pages, we hold page table lock prior to check
whether a given pmd is mapping thp or not. Because of this, when it's not
"huge pmd" we suffer from unnecessary lock/unlock overhead. To remove it,
this patch introduces a optimized check function and replace several
similar logics with it.
[akpm@linux-foundation.org: checkpatch fixes]
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 95264c0..328843d 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -394,20 +394,11 @@
pte_t *pte;
spinlock_t *ptl;
- spin_lock(&walk->mm->page_table_lock);
- if (pmd_trans_huge(*pmd)) {
- if (pmd_trans_splitting(*pmd)) {
- spin_unlock(&walk->mm->page_table_lock);
- wait_split_huge_page(vma->anon_vma, pmd);
- } else {
- smaps_pte_entry(*(pte_t *)pmd, addr,
- HPAGE_PMD_SIZE, walk);
- spin_unlock(&walk->mm->page_table_lock);
- mss->anonymous_thp += HPAGE_PMD_SIZE;
- return 0;
- }
- } else {
+ if (pmd_trans_huge_lock(pmd, vma) == 1) {
+ smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
spin_unlock(&walk->mm->page_table_lock);
+ mss->anonymous_thp += HPAGE_PMD_SIZE;
+ return 0;
}
if (pmd_trans_unstable(pmd))
@@ -705,26 +696,19 @@
/* find the first VMA at or above 'addr' */
vma = find_vma(walk->mm, addr);
spin_lock(&walk->mm->page_table_lock);
- if (pmd_trans_huge(*pmd)) {
- if (pmd_trans_splitting(*pmd)) {
- spin_unlock(&walk->mm->page_table_lock);
- wait_split_huge_page(vma->anon_vma, pmd);
- } else {
- for (; addr != end; addr += PAGE_SIZE) {
- unsigned long offset;
+ if (pmd_trans_huge_lock(pmd, vma) == 1) {
+ for (; addr != end; addr += PAGE_SIZE) {
+ unsigned long offset;
- offset = (addr & ~PAGEMAP_WALK_MASK) >>
- PAGE_SHIFT;
- pfn = thp_pmd_to_pagemap_entry(*pmd, offset);
- err = add_to_pagemap(addr, pfn, pm);
- if (err)
- break;
- }
- spin_unlock(&walk->mm->page_table_lock);
- return err;
+ offset = (addr & ~PAGEMAP_WALK_MASK) >>
+ PAGE_SHIFT;
+ pfn = thp_pmd_to_pagemap_entry(*pmd, offset);
+ err = add_to_pagemap(addr, pfn, pm);
+ if (err)
+ break;
}
- } else {
spin_unlock(&walk->mm->page_table_lock);
+ return err;
}
for (; addr != end; addr += PAGE_SIZE) {
@@ -992,24 +976,17 @@
pte_t *pte;
md = walk->private;
- spin_lock(&walk->mm->page_table_lock);
- if (pmd_trans_huge(*pmd)) {
- if (pmd_trans_splitting(*pmd)) {
- spin_unlock(&walk->mm->page_table_lock);
- wait_split_huge_page(md->vma->anon_vma, pmd);
- } else {
- pte_t huge_pte = *(pte_t *)pmd;
- struct page *page;
- page = can_gather_numa_stats(huge_pte, md->vma, addr);
- if (page)
- gather_stats(page, md, pte_dirty(huge_pte),
- HPAGE_PMD_SIZE/PAGE_SIZE);
- spin_unlock(&walk->mm->page_table_lock);
- return 0;
- }
- } else {
+ if (pmd_trans_huge_lock(pmd, md->vma) == 1) {
+ pte_t huge_pte = *(pte_t *)pmd;
+ struct page *page;
+
+ page = can_gather_numa_stats(huge_pte, md->vma, addr);
+ if (page)
+ gather_stats(page, md, pte_dirty(huge_pte),
+ HPAGE_PMD_SIZE/PAGE_SIZE);
spin_unlock(&walk->mm->page_table_lock);
+ return 0;
}
if (pmd_trans_unstable(pmd))