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>

3 files changed, 101 insertions, 114 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 95264c0ef308..328843de6e9f 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -394,20 +394,11 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	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 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	/* 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;
-
-				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;
+	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;
 		}
-	} else {
 		spin_unlock(&walk->mm->page_table_lock);
+		return err;
 	}
 
 	for (; addr != end; addr += PAGE_SIZE) {
@@ -992,24 +976,17 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 	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))
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 1b921299abc4..f56cacb4fec3 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -113,6 +113,18 @@ extern void __vma_adjust_trans_huge(struct vm_area_struct *vma,
 				    unsigned long start,
 				    unsigned long end,
 				    long adjust_next);
+extern int __pmd_trans_huge_lock(pmd_t *pmd,
+				 struct vm_area_struct *vma);
+/* mmap_sem must be held on entry */
+static inline int pmd_trans_huge_lock(pmd_t *pmd,
+				      struct vm_area_struct *vma)
+{
+	VM_BUG_ON(!rwsem_is_locked(&vma->vm_mm->mmap_sem));
+	if (pmd_trans_huge(*pmd))
+		return __pmd_trans_huge_lock(pmd, vma);
+	else
+		return 0;
+}
 static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
 					 unsigned long start,
 					 unsigned long end,
@@ -176,6 +188,11 @@ static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
 					 long adjust_next)
 {
 }
+static inline int pmd_trans_huge_lock(pmd_t *pmd,
+				      struct vm_area_struct *vma)
+{
+	return 0;
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #endif /* _LINUX_HUGE_MM_H */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8f7fc394f636..f0e5306eeb55 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1031,32 +1031,23 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 {
 	int ret = 0;
 
-	spin_lock(&tlb->mm->page_table_lock);
-	if (likely(pmd_trans_huge(*pmd))) {
-		if (unlikely(pmd_trans_splitting(*pmd))) {
-			spin_unlock(&tlb->mm->page_table_lock);
-			wait_split_huge_page(vma->anon_vma,
-					     pmd);
-		} else {
-			struct page *page;
-			pgtable_t pgtable;
-			pgtable = get_pmd_huge_pte(tlb->mm);
-			page = pmd_page(*pmd);
-			pmd_clear(pmd);
-			tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
-			page_remove_rmap(page);
-			VM_BUG_ON(page_mapcount(page) < 0);
-			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
-			VM_BUG_ON(!PageHead(page));
-			tlb->mm->nr_ptes--;
-			spin_unlock(&tlb->mm->page_table_lock);
-			tlb_remove_page(tlb, page);
-			pte_free(tlb->mm, pgtable);
-			ret = 1;
-		}
-	} else
+	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
+		struct page *page;
+		pgtable_t pgtable;
+		pgtable = get_pmd_huge_pte(tlb->mm);
+		page = pmd_page(*pmd);
+		pmd_clear(pmd);
+		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
+		page_remove_rmap(page);
+		VM_BUG_ON(page_mapcount(page) < 0);
+		add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
+		VM_BUG_ON(!PageHead(page));
+		tlb->mm->nr_ptes--;
 		spin_unlock(&tlb->mm->page_table_lock);
-
+		tlb_remove_page(tlb, page);
+		pte_free(tlb->mm, pgtable);
+		ret = 1;
+	}
 	return ret;
 }
 
@@ -1066,21 +1057,15 @@ int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 {
 	int ret = 0;
 
-	spin_lock(&vma->vm_mm->page_table_lock);
-	if (likely(pmd_trans_huge(*pmd))) {
-		ret = !pmd_trans_splitting(*pmd);
-		spin_unlock(&vma->vm_mm->page_table_lock);
-		if (unlikely(!ret))
-			wait_split_huge_page(vma->anon_vma, pmd);
-		else {
-			/*
-			 * All logical pages in the range are present
-			 * if backed by a huge page.
-			 */
-			memset(vec, 1, (end - addr) >> PAGE_SHIFT);
-		}
-	} else
+	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
+		/*
+		 * All logical pages in the range are present
+		 * if backed by a huge page.
+		 */
 		spin_unlock(&vma->vm_mm->page_table_lock);
+		memset(vec, 1, (end - addr) >> PAGE_SHIFT);
+		ret = 1;
+	}
 
 	return ret;
 }
@@ -1110,20 +1095,11 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		goto out;
 	}
 
-	spin_lock(&mm->page_table_lock);
-	if (likely(pmd_trans_huge(*old_pmd))) {
-		if (pmd_trans_splitting(*old_pmd)) {
-			spin_unlock(&mm->page_table_lock);
-			wait_split_huge_page(vma->anon_vma, old_pmd);
-			ret = -1;
-		} else {
-			pmd = pmdp_get_and_clear(mm, old_addr, old_pmd);
-			VM_BUG_ON(!pmd_none(*new_pmd));
-			set_pmd_at(mm, new_addr, new_pmd, pmd);
-			spin_unlock(&mm->page_table_lock);
-			ret = 1;
-		}
-	} else {
+	ret = __pmd_trans_huge_lock(old_pmd, vma);
+	if (ret == 1) {
+		pmd = pmdp_get_and_clear(mm, old_addr, old_pmd);
+		VM_BUG_ON(!pmd_none(*new_pmd));
+		set_pmd_at(mm, new_addr, new_pmd, pmd);
 		spin_unlock(&mm->page_table_lock);
 	}
 out:
@@ -1136,24 +1112,41 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 	struct mm_struct *mm = vma->vm_mm;
 	int ret = 0;
 
-	spin_lock(&mm->page_table_lock);
+	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
+		pmd_t entry;
+		entry = pmdp_get_and_clear(mm, addr, pmd);
+		entry = pmd_modify(entry, newprot);
+		set_pmd_at(mm, addr, pmd, entry);
+		spin_unlock(&vma->vm_mm->page_table_lock);
+		ret = 1;
+	}
+
+	return ret;
+}
+
+/*
+ * Returns 1 if a given pmd maps a stable (not under splitting) thp.
+ * Returns -1 if it maps a thp under splitting. Returns 0 otherwise.
+ *
+ * Note that if it returns 1, this routine returns without unlocking page
+ * table locks. So callers must unlock them.
+ */
+int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma)
+{
+	spin_lock(&vma->vm_mm->page_table_lock);
 	if (likely(pmd_trans_huge(*pmd))) {
 		if (unlikely(pmd_trans_splitting(*pmd))) {
-			spin_unlock(&mm->page_table_lock);
+			spin_unlock(&vma->vm_mm->page_table_lock);
 			wait_split_huge_page(vma->anon_vma, pmd);
+			return -1;
 		} else {
-			pmd_t entry;
-
-			entry = pmdp_get_and_clear(mm, addr, pmd);
-			entry = pmd_modify(entry, newprot);
-			set_pmd_at(mm, addr, pmd, entry);
-			spin_unlock(&vma->vm_mm->page_table_lock);
-			ret = 1;
+			/* Thp mapped by 'pmd' is stable, so we can
+			 * handle it as it is. */
+			return 1;
 		}
-	} else
-		spin_unlock(&vma->vm_mm->page_table_lock);
-
-	return ret;
+	}
+	spin_unlock(&vma->vm_mm->page_table_lock);
+	return 0;
 }
 
 pmd_t *page_check_address_pmd(struct page *page,