[PATCH 5 of 9] The conversion to a rwsem allows callbacks during rmap traversal

[Andrea Arcangeli <andrea@qumranet.com>]

# HG changeset patch
# User Andrea Arcangeli <andrea@qumranet.com>
# Date 1207666463 -7200
# Node ID 20e829e35dfeceeb55a816ef495afda10cd50b98
# Parent  2c2ed514f294dbbfc66157f771bc900789ac6005
The conversion to a rwsem allows callbacks during rmap traversal
for files in a non atomic context. A rw style lock also allows concurrent
walking of the reverse map. This is fairly straightforward if one removes
pieces of the resched checking.

[Restarting unmapping is an issue to be discussed].

This slightly increases Aim9 performance results on an 8p.

Signed-off-by: Andrea Arcangeli <andrea@qumranet.com>
Signed-off-by: Christoph Lameter <clameter@sgi.com>

diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -69,7 +69,7 @@
 	if (!vma_shareable(vma, addr))
 		return;
 
-	spin_lock(&mapping->i_mmap_lock);
+	down_read(&mapping->i_mmap_sem);
 	vma_prio_tree_foreach(svma, &iter, &mapping->i_mmap, idx, idx) {
 		if (svma == vma)
 			continue;
@@ -94,7 +94,7 @@
 		put_page(virt_to_page(spte));
 	spin_unlock(&mm->page_table_lock);
 out:
-	spin_unlock(&mapping->i_mmap_lock);
+	up_read(&mapping->i_mmap_sem);
 }
 
 /*
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -454,10 +454,10 @@
 	pgoff = offset >> PAGE_SHIFT;
 
 	i_size_write(inode, offset);
-	spin_lock(&mapping->i_mmap_lock);
+	down_read(&mapping->i_mmap_sem);
 	if (!prio_tree_empty(&mapping->i_mmap))
 		hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff);
-	spin_unlock(&mapping->i_mmap_lock);
+	up_read(&mapping->i_mmap_sem);
 	truncate_hugepages(inode, offset);
 	return 0;
 }
diff --git a/fs/inode.c b/fs/inode.c
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -210,7 +210,7 @@
 	INIT_LIST_HEAD(&inode->i_devices);
 	INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC);
 	rwlock_init(&inode->i_data.tree_lock);
-	spin_lock_init(&inode->i_data.i_mmap_lock);
+	init_rwsem(&inode->i_data.i_mmap_sem);
 	INIT_LIST_HEAD(&inode->i_data.private_list);
 	spin_lock_init(&inode->i_data.private_lock);
 	INIT_RAW_PRIO_TREE_ROOT(&inode->i_data.i_mmap);
diff --git a/include/linux/fs.h b/include/linux/fs.h
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -503,7 +503,7 @@
 	unsigned int		i_mmap_writable;/* count VM_SHARED mappings */
 	struct prio_tree_root	i_mmap;		/* tree of private and shared mappings */
 	struct list_head	i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
-	spinlock_t		i_mmap_lock;	/* protect tree, count, list */
+	struct rw_semaphore	i_mmap_sem;	/* protect tree, count, list */
 	unsigned int		truncate_count;	/* Cover race condition with truncate */
 	unsigned long		nrpages;	/* number of total pages */
 	pgoff_t			writeback_index;/* writeback starts here */
diff --git a/include/linux/mm.h b/include/linux/mm.h
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -716,7 +716,7 @@
 	struct address_space *check_mapping;	/* Check page->mapping if set */
 	pgoff_t	first_index;			/* Lowest page->index to unmap */
 	pgoff_t last_index;			/* Highest page->index to unmap */
-	spinlock_t *i_mmap_lock;		/* For unmap_mapping_range: */
+	struct rw_semaphore *i_mmap_sem;	/* For unmap_mapping_range: */
 	unsigned long truncate_count;		/* Compare vm_truncate_count */
 };
 
@@ -1051,9 +1051,9 @@
 				   unsigned long flags, struct page **pages);
 
 struct mm_lock_data {
-	spinlock_t **i_mmap_locks;
+	struct rw_semaphore **i_mmap_sems;
 	spinlock_t **anon_vma_locks;
-	unsigned long nr_i_mmap_locks;
+	unsigned long nr_i_mmap_sems;
 	unsigned long nr_anon_vma_locks;
 };
 extern struct mm_lock_data *mm_lock(struct mm_struct * mm);
diff --git a/kernel/fork.c b/kernel/fork.c
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -274,12 +274,12 @@
 				atomic_dec(&inode->i_writecount);
 
 			/* insert tmp into the share list, just after mpnt */
-			spin_lock(&file->f_mapping->i_mmap_lock);
+			down_write(&file->f_mapping->i_mmap_sem);
 			tmp->vm_truncate_count = mpnt->vm_truncate_count;
 			flush_dcache_mmap_lock(file->f_mapping);
 			vma_prio_tree_add(tmp, mpnt);
 			flush_dcache_mmap_unlock(file->f_mapping);
-			spin_unlock(&file->f_mapping->i_mmap_lock);
+			up_write(&file->f_mapping->i_mmap_sem);
 		}
 
 		/*
diff --git a/mm/filemap.c b/mm/filemap.c
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -61,16 +61,16 @@
 /*
  * Lock ordering:
  *
- *  ->i_mmap_lock		(vmtruncate)
+ *  ->i_mmap_sem		(vmtruncate)
  *    ->private_lock		(__free_pte->__set_page_dirty_buffers)
  *      ->swap_lock		(exclusive_swap_page, others)
  *        ->mapping->tree_lock
  *
  *  ->i_mutex
- *    ->i_mmap_lock		(truncate->unmap_mapping_range)
+ *    ->i_mmap_sem		(truncate->unmap_mapping_range)
  *
  *  ->mmap_sem
- *    ->i_mmap_lock
+ *    ->i_mmap_sem
  *      ->page_table_lock or pte_lock	(various, mainly in memory.c)
  *        ->mapping->tree_lock	(arch-dependent flush_dcache_mmap_lock)
  *
@@ -87,7 +87,7 @@
  *    ->sb_lock			(fs/fs-writeback.c)
  *    ->mapping->tree_lock	(__sync_single_inode)
  *
- *  ->i_mmap_lock
+ *  ->i_mmap_sem
  *    ->anon_vma.lock		(vma_adjust)
  *
  *  ->anon_vma.lock
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -184,7 +184,7 @@
 	if (!page)
 		return;
 
-	spin_lock(&mapping->i_mmap_lock);
+	down_read(&mapping->i_mmap_sem);
 	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
 		mm = vma->vm_mm;
 		address = vma->vm_start +
@@ -204,7 +204,7 @@
 			page_cache_release(page);
 		}
 	}
-	spin_unlock(&mapping->i_mmap_lock);
+	up_read(&mapping->i_mmap_sem);
 }
 
 /*
diff --git a/mm/fremap.c b/mm/fremap.c
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -206,13 +206,13 @@
 			}
 			goto out;
 		}
-		spin_lock(&mapping->i_mmap_lock);
+		down_write(&mapping->i_mmap_sem);
 		flush_dcache_mmap_lock(mapping);
 		vma->vm_flags |= VM_NONLINEAR;
 		vma_prio_tree_remove(vma, &mapping->i_mmap);
 		vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
 		flush_dcache_mmap_unlock(mapping);
-		spin_unlock(&mapping->i_mmap_lock);
+		up_write(&mapping->i_mmap_sem);
 	}
 
 	mmu_notifier_invalidate_range_start(mm, start, start + size);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -790,7 +790,7 @@
 	struct page *page;
 	struct page *tmp;
 	/*
-	 * A page gathering list, protected by per file i_mmap_lock. The
+	 * A page gathering list, protected by per file i_mmap_sem. The
 	 * lock is used to avoid list corruption from multiple unmapping
 	 * of the same page since we are using page->lru.
 	 */
@@ -840,9 +840,9 @@
 	 * do nothing in this case.
 	 */
 	if (vma->vm_file) {
-		spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
+		down_write(&vma->vm_file->f_mapping->i_mmap_sem);
 		__unmap_hugepage_range(vma, start, end);
-		spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
+		up_write(&vma->vm_file->f_mapping->i_mmap_sem);
 	}
 }
 
@@ -1085,7 +1085,7 @@
 	BUG_ON(address >= end);
 	flush_cache_range(vma, address, end);
 
-	spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
+	down_write(&vma->vm_file->f_mapping->i_mmap_sem);
 	spin_lock(&mm->page_table_lock);
 	for (; address < end; address += HPAGE_SIZE) {
 		ptep = huge_pte_offset(mm, address);
@@ -1100,7 +1100,7 @@
 		}
 	}
 	spin_unlock(&mm->page_table_lock);
-	spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
+	up_write(&vma->vm_file->f_mapping->i_mmap_sem);
 
 	flush_tlb_range(vma, start, end);
 }
diff --git a/mm/memory.c b/mm/memory.c
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -838,7 +838,6 @@
 	unsigned long tlb_start = 0;	/* For tlb_finish_mmu */
 	int tlb_start_valid = 0;
 	unsigned long start = start_addr;
-	spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
 	int fullmm = (*tlbp)->fullmm;
 
 	for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) {
@@ -875,22 +874,12 @@
 			}
 
 			tlb_finish_mmu(*tlbp, tlb_start, start);
-
-			if (need_resched() ||
-				(i_mmap_lock && spin_needbreak(i_mmap_lock))) {
-				if (i_mmap_lock) {
-					*tlbp = NULL;
-					goto out;
-				}
-				cond_resched();
-			}
-
+			cond_resched();
 			*tlbp = tlb_gather_mmu(vma->vm_mm, fullmm);
 			tlb_start_valid = 0;
 			zap_work = ZAP_BLOCK_SIZE;
 		}
 	}
-out:
 	return start;	/* which is now the end (or restart) address */
 }
 
@@ -1752,7 +1741,7 @@
 /*
  * Helper functions for unmap_mapping_range().
  *
- * __ Notes on dropping i_mmap_lock to reduce latency while unmapping __
+ * __ Notes on dropping i_mmap_sem to reduce latency while unmapping __
  *
  * We have to restart searching the prio_tree whenever we drop the lock,
  * since the iterator is only valid while the lock is held, and anyway
@@ -1771,7 +1760,7 @@
  * can't efficiently keep all vmas in step with mapping->truncate_count:
  * so instead reset them all whenever it wraps back to 0 (then go to 1).
  * mapping->truncate_count and vma->vm_truncate_count are protected by
- * i_mmap_lock.
+ * i_mmap_sem.
  *
  * In order to make forward progress despite repeatedly restarting some
  * large vma, note the restart_addr from unmap_vmas when it breaks out:
@@ -1821,7 +1810,7 @@
 
 	restart_addr = zap_page_range(vma, start_addr,
 					end_addr - start_addr, details);
-	need_break = need_resched() || spin_needbreak(details->i_mmap_lock);
+	need_break = need_resched();
 
 	if (restart_addr >= end_addr) {
 		/* We have now completed this vma: mark it so */
@@ -1835,9 +1824,9 @@
 			goto again;
 	}
 
-	spin_unlock(details->i_mmap_lock);
+	up_write(details->i_mmap_sem);
 	cond_resched();
-	spin_lock(details->i_mmap_lock);
+	down_write(details->i_mmap_sem);
 	return -EINTR;
 }
 
@@ -1931,9 +1920,9 @@
 	details.last_index = hba + hlen - 1;
 	if (details.last_index < details.first_index)
 		details.last_index = ULONG_MAX;
-	details.i_mmap_lock = &mapping->i_mmap_lock;
+	details.i_mmap_sem = &mapping->i_mmap_sem;
 
-	spin_lock(&mapping->i_mmap_lock);
+	down_write(&mapping->i_mmap_sem);
 
 	/* Protect against endless unmapping loops */
 	mapping->truncate_count++;
@@ -1948,7 +1937,7 @@
 		unmap_mapping_range_tree(&mapping->i_mmap, &details);
 	if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
 		unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
-	spin_unlock(&mapping->i_mmap_lock);
+	up_write(&mapping->i_mmap_sem);
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 
diff --git a/mm/migrate.c b/mm/migrate.c
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -211,12 +211,12 @@
 	if (!mapping)
 		return;
 
-	spin_lock(&mapping->i_mmap_lock);
+	down_read(&mapping->i_mmap_sem);
 
 	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff)
 		remove_migration_pte(vma, old, new);
 
-	spin_unlock(&mapping->i_mmap_lock);
+	up_read(&mapping->i_mmap_sem);
 }
 
 /*
diff --git a/mm/mmap.c b/mm/mmap.c
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -188,7 +188,7 @@
 }
 
 /*
- * Requires inode->i_mapping->i_mmap_lock
+ * Requires inode->i_mapping->i_mmap_sem
  */
 static void __remove_shared_vm_struct(struct vm_area_struct *vma,
 		struct file *file, struct address_space *mapping)
@@ -216,9 +216,9 @@
 
 	if (file) {
 		struct address_space *mapping = file->f_mapping;
-		spin_lock(&mapping->i_mmap_lock);
+		down_write(&mapping->i_mmap_sem);
 		__remove_shared_vm_struct(vma, file, mapping);
-		spin_unlock(&mapping->i_mmap_lock);
+		up_write(&mapping->i_mmap_sem);
 	}
 }
 
@@ -441,7 +441,7 @@
 		mapping = vma->vm_file->f_mapping;
 
 	if (mapping) {
-		spin_lock(&mapping->i_mmap_lock);
+		down_write(&mapping->i_mmap_sem);
 		vma->vm_truncate_count = mapping->truncate_count;
 	}
 	anon_vma_lock(vma);
@@ -451,7 +451,7 @@
 
 	anon_vma_unlock(vma);
 	if (mapping)
-		spin_unlock(&mapping->i_mmap_lock);
+		up_write(&mapping->i_mmap_sem);
 
 	mm->map_count++;
 	validate_mm(mm);
@@ -538,7 +538,7 @@
 		mapping = file->f_mapping;
 		if (!(vma->vm_flags & VM_NONLINEAR))
 			root = &mapping->i_mmap;
-		spin_lock(&mapping->i_mmap_lock);
+		down_write(&mapping->i_mmap_sem);
 		if (importer &&
 		    vma->vm_truncate_count != next->vm_truncate_count) {
 			/*
@@ -622,7 +622,7 @@
 	if (anon_vma)
 		spin_unlock(&anon_vma->lock);
 	if (mapping)
-		spin_unlock(&mapping->i_mmap_lock);
+		up_write(&mapping->i_mmap_sem);
 
 	if (remove_next) {
 		if (file)
@@ -2066,7 +2066,7 @@
 
 /* Insert vm structure into process list sorted by address
  * and into the inode's i_mmap tree.  If vm_file is non-NULL
- * then i_mmap_lock is taken here.
+ * then i_mmap_sem is taken here.
  */
 int insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma)
 {
@@ -2258,22 +2258,23 @@
 struct mm_lock_data *mm_lock(struct mm_struct * mm)
 {
 	struct vm_area_struct *vma;
-	spinlock_t *i_mmap_lock_last, *anon_vma_lock_last;
-	unsigned long nr_i_mmap_locks, nr_anon_vma_locks, i;
+	struct rw_semaphore *i_mmap_sem_last;
+	spinlock_t *anon_vma_lock_last;
+	unsigned long nr_i_mmap_sems, nr_anon_vma_locks, i;
 	struct mm_lock_data *data;
 	int err;
 
 	down_write(&mm->mmap_sem);
 
 	err = -EINTR;
-	nr_i_mmap_locks = nr_anon_vma_locks = 0;
+	nr_i_mmap_sems = nr_anon_vma_locks = 0;
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {
 		cond_resched();
 		if (unlikely(signal_pending(current)))
 			goto out;
 
 		if (vma->vm_file && vma->vm_file->f_mapping)
-			nr_i_mmap_locks++;
+			nr_i_mmap_sems++;
 		if (vma->anon_vma)
 			nr_anon_vma_locks++;
 	}
@@ -2283,13 +2284,13 @@
 	if (!data)
 		goto out;
 
-	if (nr_i_mmap_locks) {
-		data->i_mmap_locks = vmalloc(nr_i_mmap_locks *
-					     sizeof(spinlock_t));
-		if (!data->i_mmap_locks)
+	if (nr_i_mmap_sems) {
+		data->i_mmap_sems = vmalloc(nr_i_mmap_sems *
+					    sizeof(struct rw_semaphore));
+		if (!data->i_mmap_sems)
 			goto out_kfree;
 	} else
-		data->i_mmap_locks = NULL;
+		data->i_mmap_sems = NULL;
 
 	if (nr_anon_vma_locks) {
 		data->anon_vma_locks = vmalloc(nr_anon_vma_locks *
@@ -2300,10 +2301,11 @@
 		data->anon_vma_locks = NULL;
 
 	err = -EINTR;
-	i_mmap_lock_last = NULL;
-	nr_i_mmap_locks = 0;
+	i_mmap_sem_last = NULL;
+	nr_i_mmap_sems = 0;
 	for (;;) {
-		spinlock_t *i_mmap_lock = (spinlock_t *) -1UL;
+		struct rw_semaphore *i_mmap_sem;
+		i_mmap_sem = (struct rw_semaphore *) -1UL;
 		for (vma = mm->mmap; vma; vma = vma->vm_next) {
 			cond_resched();
 			if (unlikely(signal_pending(current)))
@@ -2311,21 +2313,21 @@
 
 			if (!vma->vm_file || !vma->vm_file->f_mapping)
 				continue;
-			if ((unsigned long) i_mmap_lock >
+			if ((unsigned long) i_mmap_sem >
 			    (unsigned long)
-			    &vma->vm_file->f_mapping->i_mmap_lock &&
+			    &vma->vm_file->f_mapping->i_mmap_sem &&
 			    (unsigned long)
-			    &vma->vm_file->f_mapping->i_mmap_lock >
-			    (unsigned long) i_mmap_lock_last)
-				i_mmap_lock =
-					&vma->vm_file->f_mapping->i_mmap_lock;
+			    &vma->vm_file->f_mapping->i_mmap_sem >
+			    (unsigned long) i_mmap_sem_last)
+				i_mmap_sem =
+					&vma->vm_file->f_mapping->i_mmap_sem;
 		}
-		if (i_mmap_lock == (spinlock_t *) -1UL)
+		if (i_mmap_sem == (struct rw_semaphore *) -1UL)
 			break;
-		i_mmap_lock_last = i_mmap_lock;
-		data->i_mmap_locks[nr_i_mmap_locks++] = i_mmap_lock;
+		i_mmap_sem_last = i_mmap_sem;
+		data->i_mmap_sems[nr_i_mmap_sems++] = i_mmap_sem;
 	}
-	data->nr_i_mmap_locks = nr_i_mmap_locks;
+	data->nr_i_mmap_sems = nr_i_mmap_sems;
 
 	anon_vma_lock_last = NULL;
 	nr_anon_vma_locks = 0;
@@ -2351,8 +2353,8 @@
 	}
 	data->nr_anon_vma_locks = nr_anon_vma_locks;
 
-	for (i = 0; i < nr_i_mmap_locks; i++)
-		spin_lock(data->i_mmap_locks[i]);
+	for (i = 0; i < nr_i_mmap_sems; i++)
+		down_write(data->i_mmap_sems[i]);
 	for (i = 0; i < nr_anon_vma_locks; i++)
 		spin_lock(data->anon_vma_locks[i]);
 
@@ -2361,7 +2363,7 @@
 out_vfree_both:
 	vfree(data->anon_vma_locks);
 out_vfree:
-	vfree(data->i_mmap_locks);
+	vfree(data->i_mmap_sems);
 out_kfree:
 	kfree(data);
 out:
@@ -2373,14 +2375,14 @@
 {
 	unsigned long i;
 
-	for (i = 0; i < data->nr_i_mmap_locks; i++)
-		spin_unlock(data->i_mmap_locks[i]);
+	for (i = 0; i < data->nr_i_mmap_sems; i++)
+		up_write(data->i_mmap_sems[i]);
 	for (i = 0; i < data->nr_anon_vma_locks; i++)
 		spin_unlock(data->anon_vma_locks[i]);
 
 	up_write(&mm->mmap_sem);
 	
-	vfree(data->i_mmap_locks);
+	vfree(data->i_mmap_sems);
 	vfree(data->anon_vma_locks);
 	kfree(data);
 }
diff --git a/mm/mremap.c b/mm/mremap.c
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -88,7 +88,7 @@
 		 * and we propagate stale pages into the dst afterward.
 		 */
 		mapping = vma->vm_file->f_mapping;
-		spin_lock(&mapping->i_mmap_lock);
+		down_write(&mapping->i_mmap_sem);
 		if (new_vma->vm_truncate_count &&
 		    new_vma->vm_truncate_count != vma->vm_truncate_count)
 			new_vma->vm_truncate_count = 0;
@@ -120,7 +120,7 @@
 	pte_unmap_nested(new_pte - 1);
 	pte_unmap_unlock(old_pte - 1, old_ptl);
 	if (mapping)
-		spin_unlock(&mapping->i_mmap_lock);
+		up_write(&mapping->i_mmap_sem);
 	mmu_notifier_invalidate_range_end(vma->vm_mm, old_start, old_end);
 }
 
diff --git a/mm/rmap.c b/mm/rmap.c
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -24,7 +24,7 @@
  *   inode->i_alloc_sem (vmtruncate_range)
  *   mm->mmap_sem
  *     page->flags PG_locked (lock_page)
- *       mapping->i_mmap_lock
+ *       mapping->i_mmap_sem
  *         anon_vma->lock
  *           mm->page_table_lock or pte_lock
  *             zone->lru_lock (in mark_page_accessed, isolate_lru_page)
@@ -373,14 +373,14 @@
 	 * The page lock not only makes sure that page->mapping cannot
 	 * suddenly be NULLified by truncation, it makes sure that the
 	 * structure at mapping cannot be freed and reused yet,
-	 * so we can safely take mapping->i_mmap_lock.
+	 * so we can safely take mapping->i_mmap_sem.
 	 */
 	BUG_ON(!PageLocked(page));
 
-	spin_lock(&mapping->i_mmap_lock);
+	down_read(&mapping->i_mmap_sem);
 
 	/*
-	 * i_mmap_lock does not stabilize mapcount at all, but mapcount
+	 * i_mmap_sem does not stabilize mapcount at all, but mapcount
 	 * is more likely to be accurate if we note it after spinning.
 	 */
 	mapcount = page_mapcount(page);
@@ -403,7 +403,7 @@
 			break;
 	}
 
-	spin_unlock(&mapping->i_mmap_lock);
+	up_read(&mapping->i_mmap_sem);
 	return referenced;
 }
 
@@ -489,12 +489,12 @@
 
 	BUG_ON(PageAnon(page));
 
-	spin_lock(&mapping->i_mmap_lock);
+	down_read(&mapping->i_mmap_sem);
 	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
 		if (vma->vm_flags & VM_SHARED)
 			ret += page_mkclean_one(page, vma);
 	}
-	spin_unlock(&mapping->i_mmap_lock);
+	up_read(&mapping->i_mmap_sem);
 	return ret;
 }
 
@@ -930,7 +930,7 @@
 	unsigned long max_nl_size = 0;
 	unsigned int mapcount;
 
-	spin_lock(&mapping->i_mmap_lock);
+	down_read(&mapping->i_mmap_sem);
 	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
 		ret = try_to_unmap_one(page, vma, migration);
 		if (ret == SWAP_FAIL || !page_mapped(page))
@@ -967,7 +967,6 @@
 	mapcount = page_mapcount(page);
 	if (!mapcount)
 		goto out;
-	cond_resched_lock(&mapping->i_mmap_lock);
 
 	max_nl_size = (max_nl_size + CLUSTER_SIZE - 1) & CLUSTER_MASK;
 	if (max_nl_cursor == 0)
@@ -989,7 +988,6 @@
 			}
 			vma->vm_private_data = (void *) max_nl_cursor;
 		}
-		cond_resched_lock(&mapping->i_mmap_lock);
 		max_nl_cursor += CLUSTER_SIZE;
 	} while (max_nl_cursor <= max_nl_size);
 
@@ -1001,7 +999,7 @@
 	list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
 		vma->vm_private_data = NULL;
 out:
-	spin_unlock(&mapping->i_mmap_lock);
+	up_write(&mapping->i_mmap_sem);
 	return ret;
 }