1 files changed, 82 insertions, 45 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b49579c7f2a5..7d57af21f49e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -653,6 +653,7 @@ static void free_huge_page(struct page *page)
 	BUG_ON(page_count(page));
 	BUG_ON(page_mapcount(page));
 	restore_reserve = PagePrivate(page);
+	ClearPagePrivate(page);
 
 	spin_lock(&hugetlb_lock);
 	hugetlb_cgroup_uncharge_page(hstate_index(h),
@@ -695,8 +696,22 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order)
 	/* we rely on prep_new_huge_page to set the destructor */
 	set_compound_order(page, order);
 	__SetPageHead(page);
+	__ClearPageReserved(page);
 	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
 		__SetPageTail(p);
+		/*
+		 * For gigantic hugepages allocated through bootmem at
+		 * boot, it's safer to be consistent with the not-gigantic
+		 * hugepages and clear the PG_reserved bit from all tail pages
+		 * too.  Otherwse drivers using get_user_pages() to access tail
+		 * pages may get the reference counting wrong if they see
+		 * PG_reserved set on a tail page (despite the head page not
+		 * having PG_reserved set).  Enforcing this consistency between
+		 * head and tail pages allows drivers to optimize away a check
+		 * on the head page when they need know if put_page() is needed
+		 * after get_user_pages().
+		 */
+		__ClearPageReserved(p);
 		set_page_count(p, 0);
 		p->first_page = page;
 	}
@@ -1329,9 +1344,9 @@ static void __init gather_bootmem_prealloc(void)
 #else
 		page = virt_to_page(m);
 #endif
-		__ClearPageReserved(page);
 		WARN_ON(page_count(page) != 1);
 		prep_compound_huge_page(page, h->order);
+		WARN_ON(PageReserved(page));
 		prep_new_huge_page(h, page, page_to_nid(page));
 		/*
 		 * If we had gigantic hugepages allocated at boot time, we need
@@ -2361,6 +2376,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 
 	for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
+		spinlock_t *src_ptl, *dst_ptl;
 		src_pte = huge_pte_offset(src, addr);
 		if (!src_pte)
 			continue;
@@ -2372,8 +2388,9 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		if (dst_pte == src_pte)
 			continue;
 
-		spin_lock(&dst->page_table_lock);
-		spin_lock_nested(&src->page_table_lock, SINGLE_DEPTH_NESTING);
+		dst_ptl = huge_pte_lock(h, dst, dst_pte);
+		src_ptl = huge_pte_lockptr(h, src, src_pte);
+		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 		if (!huge_pte_none(huge_ptep_get(src_pte))) {
 			if (cow)
 				huge_ptep_set_wrprotect(src, addr, src_pte);
@@ -2383,8 +2400,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			page_dup_rmap(ptepage);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
 		}
-		spin_unlock(&src->page_table_lock);
-		spin_unlock(&dst->page_table_lock);
+		spin_unlock(src_ptl);
+		spin_unlock(dst_ptl);
 	}
 	return 0;
 
@@ -2427,6 +2444,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	unsigned long address;
 	pte_t *ptep;
 	pte_t pte;
+	spinlock_t *ptl;
 	struct page *page;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
@@ -2440,25 +2458,25 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	tlb_start_vma(tlb, vma);
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 again:
-	spin_lock(&mm->page_table_lock);
 	for (address = start; address < end; address += sz) {
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;
 
+		ptl = huge_pte_lock(h, mm, ptep);
 		if (huge_pmd_unshare(mm, &address, ptep))
-			continue;
+			goto unlock;
 
 		pte = huge_ptep_get(ptep);
 		if (huge_pte_none(pte))
-			continue;
+			goto unlock;
 
 		/*
 		 * HWPoisoned hugepage is already unmapped and dropped reference
 		 */
 		if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) {
 			huge_pte_clear(mm, address, ptep);
-			continue;
+			goto unlock;
 		}
 
 		page = pte_page(pte);
@@ -2469,7 +2487,7 @@ again:
 		 */
 		if (ref_page) {
 			if (page != ref_page)
-				continue;
+				goto unlock;
 
 			/*
 			 * Mark the VMA as having unmapped its page so that
@@ -2486,13 +2504,18 @@ again:
 
 		page_remove_rmap(page);
 		force_flush = !__tlb_remove_page(tlb, page);
-		if (force_flush)
+		if (force_flush) {
+			spin_unlock(ptl);
 			break;
+		}
 		/* Bail out after unmapping reference page if supplied */
-		if (ref_page)
+		if (ref_page) {
+			spin_unlock(ptl);
 			break;
+		}
+unlock:
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 	/*
 	 * mmu_gather ran out of room to batch pages, we break out of
 	 * the PTE lock to avoid doing the potential expensive TLB invalidate
@@ -2598,7 +2621,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
  */
 static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pte_t *ptep, pte_t pte,
-			struct page *pagecache_page)
+			struct page *pagecache_page, spinlock_t *ptl)
 {
 	struct hstate *h = hstate_vma(vma);
 	struct page *old_page, *new_page;
@@ -2632,8 +2655,8 @@ retry_avoidcopy:
 
 	page_cache_get(old_page);
 
-	/* Drop page_table_lock as buddy allocator may be called */
-	spin_unlock(&mm->page_table_lock);
+	/* Drop page table lock as buddy allocator may be called */
+	spin_unlock(ptl);
 	new_page = alloc_huge_page(vma, address, outside_reserve);
 
 	if (IS_ERR(new_page)) {
@@ -2651,13 +2674,13 @@ retry_avoidcopy:
 			BUG_ON(huge_pte_none(pte));
 			if (unmap_ref_private(mm, vma, old_page, address)) {
 				BUG_ON(huge_pte_none(pte));
-				spin_lock(&mm->page_table_lock);
+				spin_lock(ptl);
 				ptep = huge_pte_offset(mm, address & huge_page_mask(h));
 				if (likely(pte_same(huge_ptep_get(ptep), pte)))
 					goto retry_avoidcopy;
 				/*
-				 * race occurs while re-acquiring page_table_lock, and
-				 * our job is done.
+				 * race occurs while re-acquiring page table
+				 * lock, and our job is done.
 				 */
 				return 0;
 			}
@@ -2665,7 +2688,7 @@ retry_avoidcopy:
 		}
 
 		/* Caller expects lock to be held */
-		spin_lock(&mm->page_table_lock);
+		spin_lock(ptl);
 		if (err == -ENOMEM)
 			return VM_FAULT_OOM;
 		else
@@ -2680,7 +2703,7 @@ retry_avoidcopy:
 		page_cache_release(new_page);
 		page_cache_release(old_page);
 		/* Caller expects lock to be held */
-		spin_lock(&mm->page_table_lock);
+		spin_lock(ptl);
 		return VM_FAULT_OOM;
 	}
 
@@ -2692,10 +2715,10 @@ retry_avoidcopy:
 	mmun_end = mmun_start + huge_page_size(h);
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	/*
-	 * Retake the page_table_lock to check for racing updates
+	 * Retake the page table lock to check for racing updates
 	 * before the page tables are altered
 	 */
-	spin_lock(&mm->page_table_lock);
+	spin_lock(ptl);
 	ptep = huge_pte_offset(mm, address & huge_page_mask(h));
 	if (likely(pte_same(huge_ptep_get(ptep), pte))) {
 		ClearPagePrivate(new_page);
@@ -2709,13 +2732,13 @@ retry_avoidcopy:
 		/* Make the old page be freed below */
 		new_page = old_page;
 	}
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 	page_cache_release(new_page);
 	page_cache_release(old_page);
 
 	/* Caller expects lock to be held */
-	spin_lock(&mm->page_table_lock);
+	spin_lock(ptl);
 	return 0;
 }
 
@@ -2763,6 +2786,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page;
 	struct address_space *mapping;
 	pte_t new_pte;
+	spinlock_t *ptl;
 
 	/*
 	 * Currently, we are forced to kill the process in the event the
@@ -2849,7 +2873,8 @@ retry:
 			goto backout_unlocked;
 		}
 
-	spin_lock(&mm->page_table_lock);
+	ptl = huge_pte_lockptr(h, mm, ptep);
+	spin_lock(ptl);
 	size = i_size_read(mapping->host) >> huge_page_shift(h);
 	if (idx >= size)
 		goto backout;
@@ -2870,16 +2895,16 @@ retry:
 
 	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
 		/* Optimization, do the COW without a second fault */
-		ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page);
+		ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page, ptl);
 	}
 
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 	unlock_page(page);
 out:
 	return ret;
 
 backout:
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 backout_unlocked:
 	unlock_page(page);
 	put_page(page);
@@ -2891,6 +2916,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	pte_t *ptep;
 	pte_t entry;
+	spinlock_t *ptl;
 	int ret;
 	struct page *page = NULL;
 	struct page *pagecache_page = NULL;
@@ -2903,7 +2929,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (ptep) {
 		entry = huge_ptep_get(ptep);
 		if (unlikely(is_hugetlb_entry_migration(entry))) {
-			migration_entry_wait_huge(mm, ptep);
+			migration_entry_wait_huge(vma, mm, ptep);
 			return 0;
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
 			return VM_FAULT_HWPOISON_LARGE |
@@ -2959,17 +2985,18 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (page != pagecache_page)
 		lock_page(page);
 
-	spin_lock(&mm->page_table_lock);
+	ptl = huge_pte_lockptr(h, mm, ptep);
+	spin_lock(ptl);
 	/* Check for a racing update before calling hugetlb_cow */
 	if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
-		goto out_page_table_lock;
+		goto out_ptl;
 
 
 	if (flags & FAULT_FLAG_WRITE) {
 		if (!huge_pte_write(entry)) {
 			ret = hugetlb_cow(mm, vma, address, ptep, entry,
-							pagecache_page);
-			goto out_page_table_lock;
+					pagecache_page, ptl);
+			goto out_ptl;
 		}
 		entry = huge_pte_mkdirty(entry);
 	}
@@ -2978,8 +3005,8 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 						flags & FAULT_FLAG_WRITE))
 		update_mmu_cache(vma, address, ptep);
 
-out_page_table_lock:
-	spin_unlock(&mm->page_table_lock);
+out_ptl:
+	spin_unlock(ptl);
 
 	if (pagecache_page) {
 		unlock_page(pagecache_page);
@@ -3005,9 +3032,9 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	unsigned long remainder = *nr_pages;
 	struct hstate *h = hstate_vma(vma);
 
-	spin_lock(&mm->page_table_lock);
 	while (vaddr < vma->vm_end && remainder) {
 		pte_t *pte;
+		spinlock_t *ptl = NULL;
 		int absent;
 		struct page *page;
 
@@ -3015,8 +3042,12 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 * Some archs (sparc64, sh*) have multiple pte_ts to
 		 * each hugepage.  We have to make sure we get the
 		 * first, for the page indexing below to work.
+		 *
+		 * Note that page table lock is not held when pte is null.
 		 */
 		pte = huge_pte_offset(mm, vaddr & huge_page_mask(h));
+		if (pte)
+			ptl = huge_pte_lock(h, mm, pte);
 		absent = !pte || huge_pte_none(huge_ptep_get(pte));
 
 		/*
@@ -3028,6 +3059,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		if (absent && (flags & FOLL_DUMP) &&
 		    !hugetlbfs_pagecache_present(h, vma, vaddr)) {
+			if (pte)
+				spin_unlock(ptl);
 			remainder = 0;
 			break;
 		}
@@ -3047,10 +3080,10 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		      !huge_pte_write(huge_ptep_get(pte)))) {
 			int ret;
 
-			spin_unlock(&mm->page_table_lock);
+			if (pte)
+				spin_unlock(ptl);
 			ret = hugetlb_fault(mm, vma, vaddr,
 				(flags & FOLL_WRITE) ? FAULT_FLAG_WRITE : 0);
-			spin_lock(&mm->page_table_lock);
 			if (!(ret & VM_FAULT_ERROR))
 				continue;
 
@@ -3081,8 +3114,8 @@ same_page:
 			 */
 			goto same_page;
 		}
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 	*nr_pages = remainder;
 	*position = vaddr;
 
@@ -3103,13 +3136,15 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	flush_cache_range(vma, address, end);
 
 	mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
-	spin_lock(&mm->page_table_lock);
 	for (; address < end; address += huge_page_size(h)) {
+		spinlock_t *ptl;
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;
+		ptl = huge_pte_lock(h, mm, ptep);
 		if (huge_pmd_unshare(mm, &address, ptep)) {
 			pages++;
+			spin_unlock(ptl);
 			continue;
 		}
 		if (!huge_pte_none(huge_ptep_get(ptep))) {
@@ -3119,8 +3154,8 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 			set_huge_pte_at(mm, address, ptep, pte);
 			pages++;
 		}
+		spin_unlock(ptl);
 	}
-	spin_unlock(&mm->page_table_lock);
 	/*
 	 * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare
 	 * may have cleared our pud entry and done put_page on the page table:
@@ -3283,6 +3318,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	unsigned long saddr;
 	pte_t *spte = NULL;
 	pte_t *pte;
+	spinlock_t *ptl;
 
 	if (!vma_shareable(vma, addr))
 		return (pte_t *)pmd_alloc(mm, pud, addr);
@@ -3305,13 +3341,14 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	if (!spte)
 		goto out;
 
-	spin_lock(&mm->page_table_lock);
+	ptl = huge_pte_lockptr(hstate_vma(vma), mm, spte);
+	spin_lock(ptl);
 	if (pud_none(*pud))
 		pud_populate(mm, pud,
 				(pmd_t *)((unsigned long)spte & PAGE_MASK));
 	else
 		put_page(virt_to_page(spte));
-	spin_unlock(&mm->page_table_lock);
+	spin_unlock(ptl);
 out:
 	pte = (pte_t *)pmd_alloc(mm, pud, addr);
 	mutex_unlock(&mapping->i_mmap_mutex);
@@ -3325,7 +3362,7 @@ out:
  * indicated by page_count > 1, unmap is achieved by clearing pud and
  * decrementing the ref count. If count == 1, the pte page is not shared.
  *
- * called with vma->vm_mm->page_table_lock held.
+ * called with page table lock held.
  *
  * returns: 1 successfully unmapped a shared pte page
  *	    0 the underlying pte page is not shared, or it is the last user