Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull VFS update from Al Viro:
 "fscache fixes, ESTALE patchset, vmtruncate removal series, assorted
  misc stuff."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (79 commits)
  vfs: make lremovexattr retry once on ESTALE error
  vfs: make removexattr retry once on ESTALE
  vfs: make llistxattr retry once on ESTALE error
  vfs: make listxattr retry once on ESTALE error
  vfs: make lgetxattr retry once on ESTALE
  vfs: make getxattr retry once on an ESTALE error
  vfs: allow lsetxattr() to retry once on ESTALE errors
  vfs: allow setxattr to retry once on ESTALE errors
  vfs: allow utimensat() calls to retry once on an ESTALE error
  vfs: fix user_statfs to retry once on ESTALE errors
  vfs: make fchownat retry once on ESTALE errors
  vfs: make fchmodat retry once on ESTALE errors
  vfs: have chroot retry once on ESTALE error
  vfs: have chdir retry lookup and call once on ESTALE error
  vfs: have faccessat retry once on an ESTALE error
  vfs: have do_sys_truncate retry once on an ESTALE error
  vfs: fix renameat to retry on ESTALE errors
  vfs: make do_unlinkat retry once on ESTALE errors
  vfs: make do_rmdir retry once on ESTALE errors
  vfs: add a flags argument to user_path_parent
  ...

64 files changed, 1096 insertions, 435 deletions

diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index e9bad50..5f95d1e 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -45,6 +45,14 @@ static int adfs_readpage(struct file *file, struct page *page)
 	return block_read_full_page(page, adfs_get_block);
 }
 
+static void adfs_write_failed(struct address_space *mapping, loff_t to)
+{
+	struct inode *inode = mapping->host;
+
+	if (to > inode->i_size)
+		truncate_pagecache(inode, to, inode->i_size);
+}
+
 static int adfs_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata)
@@ -55,11 +63,8 @@ static int adfs_write_begin(struct file *file, struct address_space *mapping,
 	ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
 				adfs_get_block,
 				&ADFS_I(mapping->host)->mmu_private);
-	if (unlikely(ret)) {
-		loff_t isize = mapping->host->i_size;
-		if (pos + len > isize)
-			vmtruncate(mapping->host, isize);
-	}
+	if (unlikely(ret))
+		adfs_write_failed(mapping, pos + len);
 
 	return ret;
 }
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 2f4c935..af3261b 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -39,7 +39,6 @@ const struct file_operations affs_file_operations = {
 };
 
 const struct inode_operations affs_file_inode_operations = {
-	.truncate	= affs_truncate,
 	.setattr	= affs_notify_change,
 };
 
@@ -402,6 +401,16 @@ static int affs_readpage(struct file *file, struct page *page)
 	return block_read_full_page(page, affs_get_block);
 }
 
+static void affs_write_failed(struct address_space *mapping, loff_t to)
+{
+	struct inode *inode = mapping->host;
+
+	if (to > inode->i_size) {
+		truncate_pagecache(inode, to, inode->i_size);
+		affs_truncate(inode);
+	}
+}
+
 static int affs_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata)
@@ -412,11 +421,8 @@ static int affs_write_begin(struct file *file, struct address_space *mapping,
 	ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
 				affs_get_block,
 				&AFFS_I(mapping->host)->mmu_private);
-	if (unlikely(ret)) {
-		loff_t isize = mapping->host->i_size;
-		if (pos + len > isize)
-			vmtruncate(mapping->host, isize);
-	}
+	if (unlikely(ret))
+		affs_write_failed(mapping, pos + len);
 
 	return ret;
 }
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index 15c4842..0e092d0 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -237,9 +237,12 @@ affs_notify_change(struct dentry *dentry, struct iattr *attr)
 
 	if ((attr->ia_valid & ATTR_SIZE) &&
 	    attr->ia_size != i_size_read(inode)) {
-		error = vmtruncate(inode, attr->ia_size);
+		error = inode_newsize_ok(inode, attr->ia_size);
 		if (error)
 			return error;
+
+		truncate_setsize(inode, attr->ia_size);
+		affs_truncate(inode);
 	}
 
 	setattr_copy(inode, attr);
diff --git a/fs/bfs/file.c b/fs/bfs/file.c
index f20e8a7..ad3ea14 100644
--- a/fs/bfs/file.c
+++ b/fs/bfs/file.c
@@ -161,6 +161,14 @@ static int bfs_readpage(struct file *file, struct page *page)
 	return block_read_full_page(page, bfs_get_block);
 }
 
+static void bfs_write_failed(struct address_space *mapping, loff_t to)
+{
+	struct inode *inode = mapping->host;
+
+	if (to > inode->i_size)
+		truncate_pagecache(inode, to, inode->i_size);
+}
+
 static int bfs_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata)
@@ -169,11 +177,8 @@ static int bfs_write_begin(struct file *file, struct address_space *mapping,
 
 	ret = block_write_begin(mapping, pos, len, flags, pagep,
 				bfs_get_block);
-	if (unlikely(ret)) {
-		loff_t isize = mapping->host->i_size;
-		if (pos + len > isize)
-			vmtruncate(mapping->host, isize);
-	}
+	if (unlikely(ret))
+		bfs_write_failed(mapping, pos + len);
 
 	return ret;
 }
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 67ed24a..16d9e8e 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4262,16 +4262,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 	if (dentry->d_name.len > BTRFS_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
-	if (unlikely(d_need_lookup(dentry))) {
-		memcpy(&location, dentry->d_fsdata, sizeof(struct btrfs_key));
-		kfree(dentry->d_fsdata);
-		dentry->d_fsdata = NULL;
-		/* This thing is hashed, drop it for now */
-		d_drop(dentry);
-	} else {
-		ret = btrfs_inode_by_name(dir, dentry, &location);
-	}
-
+	ret = btrfs_inode_by_name(dir, dentry, &location);
 	if (ret < 0)
 		return ERR_PTR(ret);
 
@@ -4341,11 +4332,6 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
 	struct dentry *ret;
 
 	ret = d_splice_alias(btrfs_lookup_dentry(dir, dentry), dentry);
-	if (unlikely(d_need_lookup(dentry))) {
-		spin_lock(&dentry->d_lock);
-		dentry->d_flags &= ~DCACHE_NEED_LOOKUP;
-		spin_unlock(&dentry->d_lock);
-	}
 	return ret;
 }
 
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index 67bef6d..746ce53 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -41,12 +41,12 @@ static struct fscache_object *cachefiles_alloc_object(
 
 	_enter("{%s},%p,", cache->cache.identifier, cookie);
 
-	lookup_data = kmalloc(sizeof(*lookup_data), GFP_KERNEL);
+	lookup_data = kmalloc(sizeof(*lookup_data), cachefiles_gfp);
 	if (!lookup_data)
 		goto nomem_lookup_data;
 
 	/* create a new object record and a temporary leaf image */
-	object = kmem_cache_alloc(cachefiles_object_jar, GFP_KERNEL);
+	object = kmem_cache_alloc(cachefiles_object_jar, cachefiles_gfp);
 	if (!object)
 		goto nomem_object;
 
@@ -63,7 +63,7 @@ static struct fscache_object *cachefiles_alloc_object(
 	 * - stick the length on the front and leave space on the back for the
 	 *   encoder
 	 */
-	buffer = kmalloc((2 + 512) + 3, GFP_KERNEL);
+	buffer = kmalloc((2 + 512) + 3, cachefiles_gfp);
 	if (!buffer)
 		goto nomem_buffer;
 
@@ -219,7 +219,7 @@ static void cachefiles_update_object(struct fscache_object *_object)
 		return;
 	}
 
-	auxdata = kmalloc(2 + 512 + 3, GFP_KERNEL);
+	auxdata = kmalloc(2 + 512 + 3, cachefiles_gfp);
 	if (!auxdata) {
 		_leave(" [nomem]");
 		return;
@@ -441,6 +441,54 @@ truncate_failed:
 }
 
 /*
+ * Invalidate an object
+ */
+static void cachefiles_invalidate_object(struct fscache_operation *op)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	const struct cred *saved_cred;
+	struct path path;
+	uint64_t ni_size;
+	int ret;
+
+	object = container_of(op->object, struct cachefiles_object, fscache);
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	op->object->cookie->def->get_attr(op->object->cookie->netfs_data,
+					  &ni_size);
+
+	_enter("{OBJ%x},[%llu]",
+	       op->object->debug_id, (unsigned long long)ni_size);
+
+	if (object->backer) {
+		ASSERT(S_ISREG(object->backer->d_inode->i_mode));
+
+		fscache_set_store_limit(&object->fscache, ni_size);
+
+		path.dentry = object->backer;
+		path.mnt = cache->mnt;
+
+		cachefiles_begin_secure(cache, &saved_cred);
+		ret = vfs_truncate(&path, 0);
+		if (ret == 0)
+			ret = vfs_truncate(&path, ni_size);
+		cachefiles_end_secure(cache, saved_cred);
+
+		if (ret != 0) {
+			fscache_set_store_limit(&object->fscache, 0);
+			if (ret == -EIO)
+				cachefiles_io_error_obj(object,
+							"Invalidate failed");
+		}
+	}
+
+	fscache_op_complete(op, true);
+	_leave("");
+}
+
+/*
  * dissociate a cache from all the pages it was backing
  */
 static void cachefiles_dissociate_pages(struct fscache_cache *cache)
@@ -455,6 +503,7 @@ const struct fscache_cache_ops cachefiles_cache_ops = {
 	.lookup_complete	= cachefiles_lookup_complete,
 	.grab_object		= cachefiles_grab_object,
 	.update_object		= cachefiles_update_object,
+	.invalidate_object	= cachefiles_invalidate_object,
 	.drop_object		= cachefiles_drop_object,
 	.put_object		= cachefiles_put_object,
 	.sync_cache		= cachefiles_sync_cache,
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index bd6bc1b..4938251 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -23,6 +23,8 @@ extern unsigned cachefiles_debug;
 #define CACHEFILES_DEBUG_KLEAVE	2
 #define CACHEFILES_DEBUG_KDEBUG	4
 
+#define cachefiles_gfp (__GFP_WAIT | __GFP_NORETRY | __GFP_NOMEMALLOC)
+
 /*
  * node records
  */
diff --git a/fs/cachefiles/key.c b/fs/cachefiles/key.c
index 81b8b2b..33b58c6 100644
--- a/fs/cachefiles/key.c
+++ b/fs/cachefiles/key.c
@@ -78,7 +78,7 @@ char *cachefiles_cook_key(const u8 *raw, int keylen, uint8_t type)
 
 	_debug("max: %d", max);
 
-	key = kmalloc(max, GFP_KERNEL);
+	key = kmalloc(max, cachefiles_gfp);
 	if (!key)
 		return NULL;
 
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index b0b5f7c..8c01c5fc 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -40,8 +40,7 @@ void __cachefiles_printk_object(struct cachefiles_object *object,
 	printk(KERN_ERR "%sobjstate=%s fl=%lx wbusy=%x ev=%lx[%lx]\n",
 	       prefix, fscache_object_states[object->fscache.state],
 	       object->fscache.flags, work_busy(&object->fscache.work),
-	       object->fscache.events,
-	       object->fscache.event_mask & FSCACHE_OBJECT_EVENTS_MASK);
+	       object->fscache.events, object->fscache.event_mask);
 	printk(KERN_ERR "%sops=%u inp=%u exc=%u\n",
 	       prefix, object->fscache.n_ops, object->fscache.n_in_progress,
 	       object->fscache.n_exclusive);
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index c994691..4809922 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -77,25 +77,25 @@ static int cachefiles_read_reissue(struct cachefiles_object *object,
 	struct page *backpage = monitor->back_page, *backpage2;
 	int ret;
 
-	kenter("{ino=%lx},{%lx,%lx}",
+	_enter("{ino=%lx},{%lx,%lx}",
 	       object->backer->d_inode->i_ino,
 	       backpage->index, backpage->flags);
 
 	/* skip if the page was truncated away completely */
 	if (backpage->mapping != bmapping) {
-		kleave(" = -ENODATA [mapping]");
+		_leave(" = -ENODATA [mapping]");
 		return -ENODATA;
 	}
 
 	backpage2 = find_get_page(bmapping, backpage->index);
 	if (!backpage2) {
-		kleave(" = -ENODATA [gone]");
+		_leave(" = -ENODATA [gone]");
 		return -ENODATA;
 	}
 
 	if (backpage != backpage2) {
 		put_page(backpage2);
-		kleave(" = -ENODATA [different]");
+		_leave(" = -ENODATA [different]");
 		return -ENODATA;
 	}
 
@@ -114,7 +114,7 @@ static int cachefiles_read_reissue(struct cachefiles_object *object,
 		if (PageUptodate(backpage))
 			goto unlock_discard;
 
-		kdebug("reissue read");
+		_debug("reissue read");
 		ret = bmapping->a_ops->readpage(NULL, backpage);
 		if (ret < 0)
 			goto unlock_discard;
@@ -129,7 +129,7 @@ static int cachefiles_read_reissue(struct cachefiles_object *object,
 	}
 
 	/* it'll reappear on the todo list */
-	kleave(" = -EINPROGRESS");
+	_leave(" = -EINPROGRESS");
 	return -EINPROGRESS;
 
 unlock_discard:
@@ -137,7 +137,7 @@ unlock_discard:
 	spin_lock_irq(&object->work_lock);
 	list_del(&monitor->op_link);
 	spin_unlock_irq(&object->work_lock);
-	kleave(" = %d", ret);
+	_leave(" = %d", ret);
 	return ret;
 }
 
@@ -174,11 +174,13 @@ static void cachefiles_read_copier(struct fscache_operation *_op)
 		_debug("- copy {%lu}", monitor->back_page->index);
 
 	recheck:
-		if (PageUptodate(monitor->back_page)) {
+		if (test_bit(FSCACHE_COOKIE_INVALIDATING,
+			     &object->fscache.cookie->flags)) {
+			error = -ESTALE;
+		} else if (PageUptodate(monitor->back_page)) {
 			copy_highpage(monitor->netfs_page, monitor->back_page);
-
-			pagevec_add(&pagevec, monitor->netfs_page);
-			fscache_mark_pages_cached(monitor->op, &pagevec);
+			fscache_mark_page_cached(monitor->op,
+						 monitor->netfs_page);
 			error = 0;
 		} else if (!PageError(monitor->back_page)) {
 			/* the page has probably been truncated */
@@ -198,6 +200,7 @@ static void cachefiles_read_copier(struct fscache_operation *_op)
 
 		fscache_end_io(op, monitor->netfs_page, error);
 		page_cache_release(monitor->netfs_page);
+		fscache_retrieval_complete(op, 1);
 		fscache_put_retrieval(op);
 		kfree(monitor);
 
@@ -239,7 +242,7 @@ static int cachefiles_read_backing_file_one(struct cachefiles_object *object,
 	_debug("read back %p{%lu,%d}",
 	       netpage, netpage->index, page_count(netpage));
 
-	monitor = kzalloc(sizeof(*monitor), GFP_KERNEL);
+	monitor = kzalloc(sizeof(*monitor), cachefiles_gfp);
 	if (!monitor)
 		goto nomem;
 
@@ -258,13 +261,14 @@ static int cachefiles_read_backing_file_one(struct cachefiles_object *object,
 			goto backing_page_already_present;
 
 		if (!newpage) {
-			newpage = page_cache_alloc_cold(bmapping);
+			newpage = __page_cache_alloc(cachefiles_gfp |
+						     __GFP_COLD);
 			if (!newpage)
 				goto nomem_monitor;
 		}
 
 		ret = add_to_page_cache(newpage, bmapping,
-					netpage->index, GFP_KERNEL);
+					netpage->index, cachefiles_gfp);
 		if (ret == 0)
 			goto installed_new_backing_page;
 		if (ret != -EEXIST)
@@ -335,11 +339,11 @@ backing_page_already_present:
 backing_page_already_uptodate:
 	_debug("- uptodate");
 
-	pagevec_add(pagevec, netpage);
-	fscache_mark_pages_cached(op, pagevec);
+	fscache_mark_page_cached(op, netpage);
 
 	copy_highpage(netpage, backpage);
 	fscache_end_io(op, netpage, 0);
+	fscache_retrieval_complete(op, 1);
 
 success:
 	_debug("success");
@@ -357,10 +361,13 @@ out:
 
 read_error:
 	_debug("read error %d", ret);
-	if (ret == -ENOMEM)
+	if (ret == -ENOMEM) {
+		fscache_retrieval_complete(op, 1);
 		goto out;
+	}
 io_error:
 	cachefiles_io_error_obj(object, "Page read error on backing file");
+	fscache_retrieval_complete(op, 1);
 	ret = -ENOBUFS;
 	goto out;
 
@@ -370,6 +377,7 @@ nomem_monitor:
 	fscache_put_retrieval(monitor->op);
 	kfree(monitor);
 nomem:
+	fscache_retrieval_complete(op, 1);
 	_leave(" = -ENOMEM");
 	return -ENOMEM;
 }
@@ -408,7 +416,7 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
 	_enter("{%p},{%lx},,,", object, page->index);
 
 	if (!object->backer)
-		return -ENOBUFS;
+		goto enobufs;
 
 	inode = object->backer->d_inode;
 	ASSERT(S_ISREG(inode->i_mode));
@@ -417,7 +425,7 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
 
 	/* calculate the shift required to use bmap */
 	if (inode->i_sb->s_blocksize > PAGE_SIZE)
-		return -ENOBUFS;
+		goto enobufs;
 
 	shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
 
@@ -448,15 +456,20 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
 						       &pagevec);
 	} else if (cachefiles_has_space(cache, 0, 1) == 0) {
 		/* there's space in the cache we can use */
-		pagevec_add(&pagevec, page);
-		fscache_mark_pages_cached(op, &pagevec);
+		fscache_mark_page_cached(op, page);
+		fscache_retrieval_complete(op, 1);
 		ret = -ENODATA;
 	} else {
-		ret = -ENOBUFS;
+		goto enobufs;
 	}
 
 	_leave(" = %d", ret);
 	return ret;
+
+enobufs:
+	fscache_retrieval_complete(op, 1);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
 }
 
 /*
@@ -465,8 +478,7 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
  */
 static int cachefiles_read_backing_file(struct cachefiles_object *object,
 					struct fscache_retrieval *op,
-					struct list_head *list,
-					struct pagevec *mark_pvec)
+					struct list_head *list)
 {
 	struct cachefiles_one_read *monitor = NULL;
 	struct address_space *bmapping = object->backer->d_inode->i_mapping;
@@ -485,7 +497,7 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 		       netpage, netpage->index, page_count(netpage));
 
 		if (!monitor) {
-			monitor = kzalloc(sizeof(*monitor), GFP_KERNEL);
+			monitor = kzalloc(sizeof(*monitor), cachefiles_gfp);
 			if (!monitor)
 				goto nomem;
 
@@ -500,13 +512,14 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 				goto backing_page_already_present;
 
 			if (!newpage) {
-				newpage = page_cache_alloc_cold(bmapping);
+				newpage = __page_cache_alloc(cachefiles_gfp |
+							     __GFP_COLD);
 				if (!newpage)
 					goto nomem;
 			}
 
 			ret = add_to_page_cache(newpage, bmapping,
-						netpage->index, GFP_KERNEL);
+						netpage->index, cachefiles_gfp);
 			if (ret == 0)
 				goto installed_new_backing_page;
 			if (ret != -EEXIST)
@@ -536,10 +549,11 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 		_debug("- monitor add");
 
 		ret = add_to_page_cache(netpage, op->mapping, netpage->index,
-					GFP_KERNEL);
+					cachefiles_gfp);
 		if (ret < 0) {
 			if (ret == -EEXIST) {
 				page_cache_release(netpage);
+				fscache_retrieval_complete(op, 1);
 				continue;
 			}
 			goto nomem;
@@ -612,10 +626,11 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 		_debug("- uptodate");
 
 		ret = add_to_page_cache(netpage, op->mapping, netpage->index,
-					GFP_KERNEL);
+					cachefiles_gfp);
 		if (ret < 0) {
 			if (ret == -EEXIST) {
 				page_cache_release(netpage);
+				fscache_retrieval_complete(op, 1);
 				continue;
 			}
 			goto nomem;
@@ -626,16 +641,17 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
 		page_cache_release(backpage);
 		backpage = NULL;
 
-		if (!pagevec_add(mark_pvec, netpage))
-			fscache_mark_pages_cached(op, mark_pvec);
+		fscache_mark_page_cached(op, netpage);
 
 		page_cache_get(netpage);
 		if (!pagevec_add(&lru_pvec, netpage))
 			__pagevec_lru_add_file(&lru_pvec);
 
+		/* the netpage is unlocked and marked up to date here */
 		fscache_end_io(op, netpage, 0);
 		page_cache_release(netpage);
 		netpage = NULL;
+		fscache_retrieval_complete(op, 1);
 		continue;
 	}
 
@@ -661,6 +677,7 @@ out:
 	list_for_each_entry_safe(netpage, _n, list, lru) {
 		list_del(&netpage->lru);
 		page_cache_release(netpage);
+		fscache_retrieval_complete(op, 1);
 	}
 
 	_leave(" = %d", ret);
@@ -669,15 +686,17 @@ out:
 nomem:
 	_debug("nomem");
 	ret = -ENOMEM;
-	goto out;
+	goto record_page_complete;
 
 read_error:
 	_debug("read error %d", ret);
 	if (ret == -ENOMEM)
-		goto out;
+		goto record_page_complete;
 io_error:
 	cachefiles_io_error_obj(object, "Page read error on backing file");
 	ret = -ENOBUFS;
+record_page_complete:
+	fscache_retrieval_complete(op, 1);
 	goto out;
 }
 
@@ -709,7 +728,7 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
 	       *nr_pages);
 
 	if (!object->backer)
-		return -ENOBUFS;
+		goto all_enobufs;
 
 	space = 1;
 	if (cachefiles_has_space(cache, 0, *nr_pages) < 0)
@@ -722,7 +741,7 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
 
 	/* calculate the shift required to use bmap */
 	if (inode->i_sb->s_blocksize > PAGE_SIZE)
-		return -ENOBUFS;
+		goto all_enobufs;
 
 	shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
 
@@ -762,7 +781,10 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
 			nrbackpages++;
 		} else if (space && pagevec_add(&pagevec, page) == 0) {
 			fscache_mark_pages_cached(op, &pagevec);
+			fscache_retrieval_complete(op, 1);
 			ret = -ENODATA;
+		} else {
+			fscache_retrieval_complete(op, 1);
 		}
 	}
 
@@ -775,18 +797,18 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
 	/* submit the apparently valid pages to the backing fs to be read from
 	 * disk */
 	if (nrbackpages > 0) {
-		ret2 = cachefiles_read_backing_file(object, op, &backpages,
-						    &pagevec);
+		ret2 = cachefiles_read_backing_file(object, op, &backpages);
 		if (ret2 == -ENOMEM || ret2 == -EINTR)
 			ret = ret2;
 	}
 
-	if (pagevec_count(&pagevec) > 0)
-		fscache_mark_pages_cached(op, &pagevec);
-
 	_leave(" = %d [nr=%u%s]",
 	       ret, *nr_pages, list_empty(pages) ? " empty" : "");
 	return ret;
+
+all_enobufs:
+	fscache_retrieval_complete(op, *nr_pages);
+	return -ENOBUFS;
 }
 
 /*
@@ -806,7 +828,6 @@ int cachefiles_allocate_page(struct fscache_retrieval *op,
 {
 	struct cachefiles_object *object;
 	struct cachefiles_cache *cache;
-	struct pagevec pagevec;
 	int ret;
 
 	object = container_of(op->op.object,
@@ -817,14 +838,12 @@ int cachefiles_allocate_page(struct fscache_retrieval *op,
 	_enter("%p,{%lx},", object, page->index);
 
 	ret = cachefiles_has_space(cache, 0, 1);
-	if (ret == 0) {
-		pagevec_init(&pagevec, 0);
-		pagevec_add(&pagevec, page);
-		fscache_mark_pages_cached(op, &pagevec);
-	} else {
+	if (ret == 0)
+		fscache_mark_page_cached(op, page);
+	else
 		ret = -ENOBUFS;
-	}
 
+	fscache_retrieval_complete(op, 1);
 	_leave(" = %d", ret);
 	return ret;
 }
@@ -874,6 +893,7 @@ int cachefiles_allocate_pages(struct fscache_retrieval *op,
 		ret = -ENOBUFS;
 	}
 
+	fscache_retrieval_complete(op, *nr_pages);
 	_leave(" = %d", ret);
 	return ret;
 }
diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c
index e18b183..73b4628 100644
--- a/fs/cachefiles/xattr.c
+++ b/fs/cachefiles/xattr.c
@@ -174,7 +174,7 @@ int cachefiles_check_object_xattr(struct cachefiles_object *object,
 	ASSERT(dentry);
 	ASSERT(dentry->d_inode);
 
-	auxbuf = kmalloc(sizeof(struct cachefiles_xattr) + 512, GFP_KERNEL);
+	auxbuf = kmalloc(sizeof(struct cachefiles_xattr) + 512, cachefiles_gfp);
 	if (!auxbuf) {
 		_leave(" = -ENOMEM");
 		return -ENOMEM;
diff --git a/fs/dcache.c b/fs/dcache.c
index 3a463d0..19153a0 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -455,24 +455,6 @@ void d_drop(struct dentry *dentry)
 EXPORT_SYMBOL(d_drop);
 
 /*
- * d_clear_need_lookup - drop a dentry from cache and clear the need lookup flag
- * @dentry: dentry to drop
- *
- * This is called when we do a lookup on a placeholder dentry that needed to be
- * looked up.  The dentry should have been hashed in order for it to be found by
- * the lookup code, but now needs to be unhashed while we do the actual lookup
- * and clear the DCACHE_NEED_LOOKUP flag.
- */
-void d_clear_need_lookup(struct dentry *dentry)
-{
-	spin_lock(&dentry->d_lock);
-	__d_drop(dentry);
-	dentry->d_flags &= ~DCACHE_NEED_LOOKUP;
-	spin_unlock(&dentry->d_lock);
-}
-EXPORT_SYMBOL(d_clear_need_lookup);
-
-/*
  * Finish off a dentry we've decided to kill.
  * dentry->d_lock must be held, returns with it unlocked.
  * If ref is non-zero, then decrement the refcount too.
@@ -565,13 +547,7 @@ repeat:
  	if (d_unhashed(dentry))
 		goto kill_it;
 
-	/*
-	 * If this dentry needs lookup, don't set the referenced flag so that it
-	 * is more likely to be cleaned up by the dcache shrinker in case of
-	 * memory pressure.
-	 */
-	if (!d_need_lookup(dentry))
-		dentry->d_flags |= DCACHE_REFERENCED;
+	dentry->d_flags |= DCACHE_REFERENCED;
 	dentry_lru_add(dentry);
 
 	dentry->d_count--;
@@ -1583,7 +1559,7 @@ EXPORT_SYMBOL(d_find_any_alias);
  */
 struct dentry *d_obtain_alias(struct inode *inode)
 {
-	static const struct qstr anonstring = { .name = "" };
+	static const struct qstr anonstring = QSTR_INIT("/", 1);
 	struct dentry *tmp;
 	struct dentry *res;
 
@@ -1737,13 +1713,6 @@ struct dentry *d_add_ci(struct dentry *dentry, struct inode *inode,
 	}
 
 	/*
-	 * We are going to instantiate this dentry, unhash it and clear the
-	 * lookup flag so we can do that.
-	 */
-	if (unlikely(d_need_lookup(found)))
-		d_clear_need_lookup(found);
-
-	/*
 	 * Negative dentry: instantiate it unless the inode is a directory and
 	 * already has a dentry.
 	 */
diff --git a/fs/file_table.c b/fs/file_table.c
index a72bf9d..de9e965 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -458,8 +458,8 @@ void mark_files_ro(struct super_block *sb)
 		spin_unlock(&f->f_lock);
 		if (file_check_writeable(f) != 0)
 			continue;
+		__mnt_drop_write(f->f_path.mnt);
 		file_release_write(f);
-		mnt_drop_write_file(f);
 	} while_file_list_for_each_entry;
 	lg_global_unlock(&files_lglock);
 }
diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c
index 6a3c48a..b52aed1 100644
--- a/fs/fscache/cache.c
+++ b/fs/fscache/cache.c
@@ -314,10 +314,10 @@ EXPORT_SYMBOL(fscache_add_cache);
  */
 void fscache_io_error(struct fscache_cache *cache)
 {
-	set_bit(FSCACHE_IOERROR, &cache->flags);
-
-	printk(KERN_ERR "FS-Cache: Cache %s stopped due to I/O error\n",
-	       cache->ops->name);
+	if (!test_and_set_bit(FSCACHE_IOERROR, &cache->flags))
+		printk(KERN_ERR "FS-Cache:"
+		       " Cache '%s' stopped due to I/O error\n",
+		       cache->ops->name);
 }
 EXPORT_SYMBOL(fscache_io_error);
 
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 9905350..8dcb114 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -370,6 +370,66 @@ cant_attach_object:
 }
 
 /*
+ * Invalidate an object.  Callable with spinlocks held.
+ */
+void __fscache_invalidate(struct fscache_cookie *cookie)
+{
+	struct fscache_object *object;
+
+	_enter("{%s}", cookie->def->name);
+
+	fscache_stat(&fscache_n_invalidates);
+
+	/* Only permit invalidation of data files.  Invalidating an index will
+	 * require the caller to release all its attachments to the tree rooted
+	 * there, and if it's doing that, it may as well just retire the
+	 * cookie.
+	 */
+	ASSERTCMP(cookie->def->type, ==, FSCACHE_COOKIE_TYPE_DATAFILE);
+
+	/* We will be updating the cookie too. */
+	BUG_ON(!cookie->def->get_aux);
+
+	/* If there's an object, we tell the object state machine to handle the
+	 * invalidation on our behalf, otherwise there's nothing to do.
+	 */
+	if (!hlist_empty(&cookie->backing_objects)) {
+		spin_lock(&cookie->lock);
+
+		if (!hlist_empty(&cookie->backing_objects) &&
+		    !test_and_set_bit(FSCACHE_COOKIE_INVALIDATING,
+				      &cookie->flags)) {
+			object = hlist_entry(cookie->backing_objects.first,
+					     struct fscache_object,
+					     cookie_link);
+			if (object->state < FSCACHE_OBJECT_DYING)
+				fscache_raise_event(
+					object, FSCACHE_OBJECT_EV_INVALIDATE);
+		}
+
+		spin_unlock(&cookie->lock);
+	}
+
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_invalidate);
+
+/*
+ * Wait for object invalidation to complete.
+ */
+void __fscache_wait_on_invalidate(struct fscache_cookie *cookie)
+{
+	_enter("%p", cookie);
+
+	wait_on_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING,
+		    fscache_wait_bit_interruptible,
+		    TASK_UNINTERRUPTIBLE);
+
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_wait_on_invalidate);
+
+/*
  * update the index entries backing a cookie
  */
 void __fscache_update_cookie(struct fscache_cookie *cookie)
@@ -442,16 +502,34 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
 
 	event = retire ? FSCACHE_OBJECT_EV_RETIRE : FSCACHE_OBJECT_EV_RELEASE;
 
+try_again:
 	spin_lock(&cookie->lock);
 
 	/* break links with all the active objects */
 	while (!hlist_empty(&cookie->backing_objects)) {
+		int n_reads;
 		object = hlist_entry(cookie->backing_objects.first,
 				     struct fscache_object,
 				     cookie_link);
 
 		_debug("RELEASE OBJ%x", object->debug_id);
 
+		set_bit(FSCACHE_COOKIE_WAITING_ON_READS, &cookie->flags);
+		n_reads = atomic_read(&object->n_reads);
+		if (n_reads) {
+			int n_ops = object->n_ops;
+			int n_in_progress = object->n_in_progress;
+			spin_unlock(&cookie->lock);
+			printk(KERN_ERR "FS-Cache:"
+			       " Cookie '%s' still has %d outstanding reads (%d,%d)\n",
+			       cookie->def->name,
+			       n_reads, n_ops, n_in_progress);
+			wait_on_bit(&cookie->flags, FSCACHE_COOKIE_WAITING_ON_READS,
+				    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+			printk("Wait finished\n");
+			goto try_again;
+		}
+
 		/* detach each cache object from the object cookie */
 		spin_lock(&object->lock);
 		hlist_del_init(&object->cookie_link);
diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
index f6aad48..ee38fef 100644
--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -121,12 +121,19 @@ extern int fscache_submit_exclusive_op(struct fscache_object *,
 				       struct fscache_operation *);
 extern int fscache_submit_op(struct fscache_object *,
 			     struct fscache_operation *);
-extern int fscache_cancel_op(struct fscache_operation *);
+extern int fscache_cancel_op(struct fscache_operation *,
+			     void (*)(struct fscache_operation *));
+extern void fscache_cancel_all_ops(struct fscache_object *);
 extern void fscache_abort_object(struct fscache_object *);
 extern void fscache_start_operations(struct fscache_object *);
 extern void fscache_operation_gc(struct work_struct *);
 
 /*
+ * page.c
+ */
+extern void fscache_invalidate_writes(struct fscache_cookie *);
+
+/*
  * proc.c
  */
 #ifdef CONFIG_PROC_FS
@@ -194,6 +201,7 @@ extern atomic_t fscache_n_store_vmscan_not_storing;
 extern atomic_t fscache_n_store_vmscan_gone;
 extern atomic_t fscache_n_store_vmscan_busy;
 extern atomic_t fscache_n_store_vmscan_cancelled;
+extern atomic_t fscache_n_store_vmscan_wait;
 
 extern atomic_t fscache_n_marks;
 extern atomic_t fscache_n_uncaches;
@@ -205,6 +213,9 @@ extern atomic_t fscache_n_acquires_ok;
 extern atomic_t fscache_n_acquires_nobufs;
 extern atomic_t fscache_n_acquires_oom;
 
+extern atomic_t fscache_n_invalidates;
+extern atomic_t fscache_n_invalidates_run;
+
 extern atomic_t fscache_n_updates;
 extern atomic_t fscache_n_updates_null;
 extern atomic_t fscache_n_updates_run;
@@ -237,6 +248,7 @@ extern atomic_t fscache_n_cop_alloc_object;
 extern atomic_t fscache_n_cop_lookup_object;
 extern atomic_t fscache_n_cop_lookup_complete;
 extern atomic_t fscache_n_cop_grab_object;
+extern atomic_t fscache_n_cop_invalidate_object;
 extern atomic_t fscache_n_cop_update_object;
 extern atomic_t fscache_n_cop_drop_object;
 extern atomic_t fscache_n_cop_put_object;
@@ -278,6 +290,7 @@ extern const struct file_operations fscache_stats_fops;
 static inline void fscache_raise_event(struct fscache_object *object,
 				       unsigned event)
 {
+	BUG_ON(event >= NR_FSCACHE_OBJECT_EVENTS);
 	if (!test_and_set_bit(event, &object->events) &&
 	    test_bit(event, &object->event_mask))
 		fscache_enqueue_object(object);
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
index ebe29c5..f27c89d 100644
--- a/fs/fscache/object-list.c
+++ b/fs/fscache/object-list.c
@@ -245,7 +245,7 @@ static int fscache_objlist_show(struct seq_file *m, void *v)
 		   obj->n_in_progress,
 		   obj->n_exclusive,
 		   atomic_read(&obj->n_reads),
-		   obj->event_mask & FSCACHE_OBJECT_EVENTS_MASK,
+		   obj->event_mask,
 		   obj->events,
 		   obj->flags,
 		   work_busy(&obj->work));
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index b6b897c..50d41c1 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -14,6 +14,7 @@
 
 #define FSCACHE_DEBUG_LEVEL COOKIE
 #include <linux/module.h>
+#include <linux/slab.h>
 #include "internal.h"
 
 const char *fscache_object_states[FSCACHE_OBJECT__NSTATES] = {
@@ -22,6 +23,7 @@ const char *fscache_object_states[FSCACHE_OBJECT__NSTATES] = {
 	[FSCACHE_OBJECT_CREATING]	= "OBJECT_CREATING",
 	[FSCACHE_OBJECT_AVAILABLE]	= "OBJECT_AVAILABLE",
 	[FSCACHE_OBJECT_ACTIVE]		= "OBJECT_ACTIVE",
+	[FSCACHE_OBJECT_INVALIDATING]	= "OBJECT_INVALIDATING",
 	[FSCACHE_OBJECT_UPDATING]	= "OBJECT_UPDATING",
 	[FSCACHE_OBJECT_DYING]		= "OBJECT_DYING",
 	[FSCACHE_OBJECT_LC_DYING]	= "OBJECT_LC_DYING",
@@ -39,6 +41,7 @@ const char fscache_object_states_short[FSCACHE_OBJECT__NSTATES][5] = {
 	[FSCACHE_OBJECT_CREATING]	= "CRTN",
 	[FSCACHE_OBJECT_AVAILABLE]	= "AVBL",
 	[FSCACHE_OBJECT_ACTIVE]		= "ACTV",
+	[FSCACHE_OBJECT_INVALIDATING]	= "INVL",
 	[FSCACHE_OBJECT_UPDATING]	= "UPDT",
 	[FSCACHE_OBJECT_DYING]		= "DYNG",
 	[FSCACHE_OBJECT_LC_DYING]	= "LCDY",
@@ -54,6 +57,7 @@ static void fscache_put_object(struct fscache_object *);
 static void fscache_initialise_object(struct fscache_object *);
 static void fscache_lookup_object(struct fscache_object *);
 static void fscache_object_available(struct fscache_object *);
+static void fscache_invalidate_object(struct fscache_object *);
 static void fscache_release_object(struct fscache_object *);
 static void fscache_withdraw_object(struct fscache_object *);
 static void fscache_enqueue_dependents(struct fscache_object *);
@@ -79,6 +83,15 @@ static inline void fscache_done_parent_op(struct fscache_object *object)
 }
 
 /*
+ * Notify netfs of invalidation completion.
+ */
+static inline void fscache_invalidation_complete(struct fscache_cookie *cookie)
+{
+	if (test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags))
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING);
+}
+
+/*
  * process events that have been sent to an object's state machine
  * - initiates parent lookup
  * - does object lookup
@@ -90,6 +103,7 @@ static void fscache_object_state_machine(struct fscache_object *object)
 {
 	enum fscache_object_state new_state;
 	struct fscache_cookie *cookie;
+	int event;
 
 	ASSERT(object != NULL);
 
@@ -101,7 +115,8 @@ static void fscache_object_state_machine(struct fscache_object *object)
 		/* wait for the parent object to become ready */
 	case FSCACHE_OBJECT_INIT:
 		object->event_mask =
-			ULONG_MAX & ~(1 << FSCACHE_OBJECT_EV_CLEARED);
+			FSCACHE_OBJECT_EVENTS_MASK &
+			~(1 << FSCACHE_OBJECT_EV_CLEARED);
 		fscache_initialise_object(object);
 		goto done;
 
@@ -125,6 +140,16 @@ static void fscache_object_state_machine(struct fscache_object *object)
 	case FSCACHE_OBJECT_ACTIVE:
 		goto active_transit;
 
+		/* Invalidate an object on disk */
+	case FSCACHE_OBJECT_INVALIDATING:
+		clear_bit(FSCACHE_OBJECT_EV_INVALIDATE, &object->events);
+		fscache_stat(&fscache_n_invalidates_run);
+		fscache_stat(&fscache_n_cop_invalidate_object);
+		fscache_invalidate_object(object);
+		fscache_stat_d(&fscache_n_cop_invalidate_object);
+		fscache_raise_event(object, FSCACHE_OBJECT_EV_UPDATE);
+		goto active_transit;
+
 		/* update the object metadata on disk */
 	case FSCACHE_OBJECT_UPDATING:
 		clear_bit(FSCACHE_OBJECT_EV_UPDATE, &object->events);
@@ -251,13 +276,17 @@ static void fscache_object_state_machine(struct fscache_object *object)
 
 	/* determine the transition from a lookup state */
 lookup_transit:
-	switch (fls(object->events & object->event_mask) - 1) {
+	event = fls(object->events & object->event_mask) - 1;
+	switch (event) {
 	case FSCACHE_OBJECT_EV_WITHDRAW:
 	case FSCACHE_OBJECT_EV_RETIRE:
 	case FSCACHE_OBJECT_EV_RELEASE:
 	case FSCACHE_OBJECT_EV_ERROR:
 		new_state = FSCACHE_OBJECT_LC_DYING;
 		goto change_state;
+	case FSCACHE_OBJECT_EV_INVALIDATE:
+		new_state = FSCACHE_OBJECT_INVALIDATING;
+		goto change_state;
 	case FSCACHE_OBJECT_EV_REQUEUE:
 		goto done;
 	case -1:
@@ -268,13 +297,17 @@ lookup_transit:
 
 	/* determine the transition from an active state */
 active_transit:
-	switch (fls(object->events & object->event_mask) - 1) {
+	event = fls(object->events & object->event_mask) - 1;
+	switch (event) {
 	case FSCACHE_OBJECT_EV_WITHDRAW:
 	case FSCACHE_OBJECT_EV_RETIRE:
 	case FSCACHE_OBJECT_EV_RELEASE:
 	case FSCACHE_OBJECT_EV_ERROR:
 		new_state = FSCACHE_OBJECT_DYING;
 		goto change_state;
+	case FSCACHE_OBJECT_EV_INVALIDATE:
+		new_state = FSCACHE_OBJECT_INVALIDATING;
+		goto change_state;
 	case FSCACHE_OBJECT_EV_UPDATE:
 		new_state = FSCACHE_OBJECT_UPDATING;
 		goto change_state;
@@ -287,7 +320,8 @@ active_transit:
 
 	/* determine the transition from a terminal state */
 terminal_transit:
-	switch (fls(object->events & object->event_mask) - 1) {
+	event = fls(object->events & object->event_mask) - 1;
+	switch (event) {
 	case FSCACHE_OBJECT_EV_WITHDRAW:
 		new_state = FSCACHE_OBJECT_WITHDRAWING;
 		goto change_state;
@@ -320,8 +354,8 @@ done:
 
 unsupported_event:
 	printk(KERN_ERR "FS-Cache:"
-	       " Unsupported event %lx [mask %lx] in state %s\n",
-	       object->events, object->event_mask,
+	       " Unsupported event %d [%lx/%lx] in state %s\n",
+	       event, object->events, object->event_mask,
 	       fscache_object_states[object->state]);
 	BUG();
 }
@@ -587,8 +621,6 @@ static void fscache_object_available(struct fscache_object *object)
 	if (object->n_in_progress == 0) {
 		if (object->n_ops > 0) {
 			ASSERTCMP(object->n_ops, >=, object->n_obj_ops);
-			ASSERTIF(object->n_ops > object->n_obj_ops,
-				 !list_empty(&object->pending_ops));
 			fscache_start_operations(object);
 		} else {
 			ASSERT(list_empty(&object->pending_ops));
@@ -681,6 +713,7 @@ static void fscache_withdraw_object(struct fscache_object *object)
 		if (object->cookie == cookie) {
 			hlist_del_init(&object->cookie_link);
 			object->cookie = NULL;
+			fscache_invalidation_complete(cookie);
 			detached = true;
 		}
 		spin_unlock(&cookie->lock);
@@ -890,3 +923,55 @@ enum fscache_checkaux fscache_check_aux(struct fscache_object *object,
 	return result;
 }
 EXPORT_SYMBOL(fscache_check_aux);
+
+/*
+ * Asynchronously invalidate an object.
+ */
+static void fscache_invalidate_object(struct fscache_object *object)
+{
+	struct fscache_operation *op;
+	struct fscache_cookie *cookie = object->cookie;
+
+	_enter("{OBJ%x}", object->debug_id);
+
+	/* Reject any new read/write ops and abort any that are pending. */
+	fscache_invalidate_writes(cookie);
+	clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+	fscache_cancel_all_ops(object);
+
+	/* Now we have to wait for in-progress reads and writes */
+	op = kzalloc(sizeof(*op), GFP_KERNEL);
+	if (!op) {
+		fscache_raise_event(object, FSCACHE_OBJECT_EV_ERROR);
+		_leave(" [ENOMEM]");
+		return;
+	}
+
+	fscache_operation_init(op, object->cache->ops->invalidate_object, NULL);
+	op->flags = FSCACHE_OP_ASYNC | (1 << FSCACHE_OP_EXCLUSIVE);
+
+	spin_lock(&cookie->lock);
+	if (fscache_submit_exclusive_op(object, op) < 0)
+		goto submit_op_failed;
+	spin_unlock(&cookie->lock);
+	fscache_put_operation(op);
+
+	/* Once we've completed the invalidation, we know there will be no data
+	 * stored in the cache and thus we can reinstate the data-check-skip
+	 * optimisation.
+	 */
+	set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+
+	/* We can allow read and write requests to come in once again.  They'll
+	 * queue up behind our exclusive invalidation operation.
+	 */
+	fscache_invalidation_complete(cookie);
+	_leave("");
+	return;
+
+submit_op_failed:
+	spin_unlock(&cookie->lock);
+	kfree(op);
+	fscache_raise_event(object, FSCACHE_OBJECT_EV_ERROR);
+	_leave(" [EIO]");
+}
diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c
index 30afdfa..762a9ec 100644
--- a/fs/fscache/operation.c
+++ b/fs/fscache/operation.c
@@ -37,6 +37,7 @@ void fscache_enqueue_operation(struct fscache_operation *op)
 	ASSERT(op->processor != NULL);
 	ASSERTCMP(op->object->state, >=, FSCACHE_OBJECT_AVAILABLE);
 	ASSERTCMP(atomic_read(&op->usage), >, 0);
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS);
 
 	fscache_stat(&fscache_n_op_enqueue);
 	switch (op->flags & FSCACHE_OP_TYPE) {
@@ -64,6 +65,9 @@ EXPORT_SYMBOL(fscache_enqueue_operation);
 static void fscache_run_op(struct fscache_object *object,
 			   struct fscache_operation *op)
 {
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_PENDING);
+
+	op->state = FSCACHE_OP_ST_IN_PROGRESS;
 	object->n_in_progress++;
 	if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
 		wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
@@ -84,18 +88,21 @@ int fscache_submit_exclusive_op(struct fscache_object *object,
 
 	_enter("{OBJ%x OP%x},", object->debug_id, op->debug_id);
 
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_INITIALISED);
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
 	spin_lock(&object->lock);
 	ASSERTCMP(object->n_ops, >=, object->n_in_progress);
 	ASSERTCMP(object->n_ops, >=, object->n_exclusive);
 	ASSERT(list_empty(&op->pend_link));
 
-	ret = -ENOBUFS;
+	op->state = FSCACHE_OP_ST_PENDING;
 	if (fscache_object_is_active(object)) {
 		op->object = object;
 		object->n_ops++;
 		object->n_exclusive++;	/* reads and writes must wait */
 
-		if (object->n_ops > 1) {
+		if (object->n_in_progress > 0) {
 			atomic_inc(&op->usage);
 			list_add_tail(&op->pend_link, &object->pending_ops);
 			fscache_stat(&fscache_n_op_pend);
@@ -121,8 +128,11 @@ int fscache_submit_exclusive_op(struct fscache_object *object,
 		fscache_stat(&fscache_n_op_pend);
 		ret = 0;
 	} else {
-		/* not allowed to submit ops in any other state */
-		BUG();
+		/* If we're in any other state, there must have been an I/O
+		 * error of some nature.
+		 */
+		ASSERT(test_bit(FSCACHE_IOERROR, &object->cache->flags));
+		ret = -EIO;
 	}
 
 	spin_unlock(&object->lock);
@@ -186,6 +196,7 @@ int fscache_submit_op(struct fscache_object *object,
 	_enter("{OBJ%x OP%x},{%u}",
 	       object->debug_id, op->debug_id, atomic_read(&op->usage));
 
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_INITIALISED);
 	ASSERTCMP(atomic_read(&op->usage), >, 0);
 
 	spin_lock(&object->lock);
@@ -196,6 +207,7 @@ int fscache_submit_op(struct fscache_object *object,
 	ostate = object->state;
 	smp_rmb();
 
+	op->state = FSCACHE_OP_ST_PENDING;
 	if (fscache_object_is_active(object)) {
 		op->object = object;
 		object->n_ops++;
@@ -225,12 +237,15 @@ int fscache_submit_op(struct fscache_object *object,
 		   object->state == FSCACHE_OBJECT_LC_DYING ||
 		   object->state == FSCACHE_OBJECT_WITHDRAWING) {
 		fscache_stat(&fscache_n_op_rejected);
+		op->state = FSCACHE_OP_ST_CANCELLED;
 		ret = -ENOBUFS;
 	} else if (!test_bit(FSCACHE_IOERROR, &object->cache->flags)) {
 		fscache_report_unexpected_submission(object, op, ostate);
 		ASSERT(!fscache_object_is_active(object));
+		op->state = FSCACHE_OP_ST_CANCELLED;
 		ret = -ENOBUFS;
 	} else {
+		op->state = FSCACHE_OP_ST_CANCELLED;
 		ret = -ENOBUFS;
 	}
 
@@ -283,20 +298,28 @@ void fscache_start_operations(struct fscache_object *object)
 /*
  * cancel an operation that's pending on an object
  */
-int fscache_cancel_op(struct fscache_operation *op)
+int fscache_cancel_op(struct fscache_operation *op,
+		      void (*do_cancel)(struct fscache_operation *))
 {
 	struct fscache_object *object = op->object;
 	int ret;
 
 	_enter("OBJ%x OP%x}", op->object->debug_id, op->debug_id);
 
+	ASSERTCMP(op->state, >=, FSCACHE_OP_ST_PENDING);
+	ASSERTCMP(op->state, !=, FSCACHE_OP_ST_CANCELLED);
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
 	spin_lock(&object->lock);
 
 	ret = -EBUSY;
-	if (!list_empty(&op->pend_link)) {
+	if (op->state == FSCACHE_OP_ST_PENDING) {
+		ASSERT(!list_empty(&op->pend_link));
 		fscache_stat(&fscache_n_op_cancelled);
 		list_del_init(&op->pend_link);
-		object->n_ops--;
+		if (do_cancel)
+			do_cancel(op);
+		op->state = FSCACHE_OP_ST_CANCELLED;
 		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
 			object->n_exclusive--;
 		if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
@@ -311,6 +334,70 @@ int fscache_cancel_op(struct fscache_operation *op)
 }
 
 /*
+ * Cancel all pending operations on an object
+ */
+void fscache_cancel_all_ops(struct fscache_object *object)
+{
+	struct fscache_operation *op;
+
+	_enter("OBJ%x", object->debug_id);
+
+	spin_lock(&object->lock);
+
+	while (!list_empty(&object->pending_ops)) {
+		op = list_entry(object->pending_ops.next,
+				struct fscache_operation, pend_link);
+		fscache_stat(&fscache_n_op_cancelled);
+		list_del_init(&op->pend_link);
+
+		ASSERTCMP(op->state, ==, FSCACHE_OP_ST_PENDING);
+		op->state = FSCACHE_OP_ST_CANCELLED;
+
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
+			object->n_exclusive--;
+		if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
+			wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
+		fscache_put_operation(op);
+		cond_resched_lock(&object->lock);
+	}
+
+	spin_unlock(&object->lock);
+	_leave("");
+}
+
+/*
+ * Record the completion or cancellation of an in-progress operation.
+ */
+void fscache_op_complete(struct fscache_operation *op, bool cancelled)
+{
+	struct fscache_object *object = op->object;
+
+	_enter("OBJ%x", object->debug_id);
+
+	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS);
+	ASSERTCMP(object->n_in_progress, >, 0);
+	ASSERTIFCMP(test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags),
+		    object->n_exclusive, >, 0);
+	ASSERTIFCMP(test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags),
+		    object->n_in_progress, ==, 1);
+
+	spin_lock(&object->lock);
+
+	op->state = cancelled ?
+		FSCACHE_OP_ST_CANCELLED : FSCACHE_OP_ST_COMPLETE;
+
+	if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
+		object->n_exclusive--;
+	object->n_in_progress--;
+	if (object->n_in_progress == 0)
+		fscache_start_operations(object);
+
+	spin_unlock(&object->lock);
+	_leave("");
+}
+EXPORT_SYMBOL(fscache_op_complete);
+
+/*
  * release an operation
  * - queues pending ops if this is the last in-progress op
  */
@@ -328,8 +415,9 @@ void fscache_put_operation(struct fscache_operation *op)
 		return;
 
 	_debug("PUT OP");
-	if (test_and_set_bit(FSCACHE_OP_DEAD, &op->flags))
-		BUG();
+	ASSERTIFCMP(op->state != FSCACHE_OP_ST_COMPLETE,
+		    op->state, ==, FSCACHE_OP_ST_CANCELLED);
+	op->state = FSCACHE_OP_ST_DEAD;
 
 	fscache_stat(&fscache_n_op_release);
 
@@ -340,8 +428,14 @@ void fscache_put_operation(struct fscache_operation *op)
 
 	object = op->object;
 
-	if (test_bit(FSCACHE_OP_DEC_READ_CNT, &op->flags))
-		atomic_dec(&object->n_reads);
+	if (test_bit(FSCACHE_OP_DEC_READ_CNT, &op->flags)) {
+		if (atomic_dec_and_test(&object->n_reads)) {
+			clear_bit(FSCACHE_COOKIE_WAITING_ON_READS,
+				  &object->cookie->flags);
+			wake_up_bit(&object->cookie->flags,
+				    FSCACHE_COOKIE_WAITING_ON_READS);
+		}
+	}
 
 	/* now... we may get called with the object spinlock held, so we
 	 * complete the cleanup here only if we can immediately acquire the
@@ -359,16 +453,6 @@ void fscache_put_operation(struct fscache_operation *op)
 		return;
 	}
 
-	if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) {
-		ASSERTCMP(object->n_exclusive, >, 0);
-		object->n_exclusive--;
-	}
-
-	ASSERTCMP(object->n_in_progress, >, 0);
-	object->n_in_progress--;
-	if (object->n_in_progress == 0)
-		fscache_start_operations(object);
-
 	ASSERTCMP(object->n_ops, >, 0);
 	object->n_ops--;
 	if (object->n_ops == 0)
@@ -407,23 +491,14 @@ void fscache_operation_gc(struct work_struct *work)
 		spin_unlock(&cache->op_gc_list_lock);
 
 		object = op->object;
+		spin_lock(&object->lock);
 
 		_debug("GC DEFERRED REL OBJ%x OP%x",
 		       object->debug_id, op->debug_id);
 		fscache_stat(&fscache_n_op_gc);
 
 		ASSERTCMP(atomic_read(&op->usage), ==, 0);
-
-		spin_lock(&object->lock);
-		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) {
-			ASSERTCMP(object->n_exclusive, >, 0);
-			object->n_exclusive--;
-		}
-
-		ASSERTCMP(object->n_in_progress, >, 0);
-		object->n_in_progress--;
-		if (object->n_in_progress == 0)
-			fscache_start_operations(object);
+		ASSERTCMP(op->state, ==, FSCACHE_OP_ST_DEAD);
 
 		ASSERTCMP(object->n_ops, >, 0);
 		object->n_ops--;
@@ -431,6 +506,7 @@ void fscache_operation_gc(struct work_struct *work)
 			fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED);
 
 		spin_unlock(&object->lock);
+		kfree(op);
 
 	} while (count++ < 20);
 
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 3f7a59b..ff000e5 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -56,6 +56,7 @@ bool __fscache_maybe_release_page(struct fscache_cookie *cookie,
 
 	_enter("%p,%p,%x", cookie, page, gfp);
 
+try_again:
 	rcu_read_lock();
 	val = radix_tree_lookup(&cookie->stores, page->index);
 	if (!val) {
@@ -104,11 +105,19 @@ bool __fscache_maybe_release_page(struct fscache_cookie *cookie,
 	return true;
 
 page_busy:
-	/* we might want to wait here, but that could deadlock the allocator as
-	 * the work threads writing to the cache may all end up sleeping
-	 * on memory allocation */
-	fscache_stat(&fscache_n_store_vmscan_busy);
-	return false;
+	/* We will wait here if we're allowed to, but that could deadlock the
+	 * allocator as the work threads writing to the cache may all end up
+	 * sleeping on memory allocation, so we may need to impose a timeout
+	 * too. */
+	if (!(gfp & __GFP_WAIT)) {
+		fscache_stat(&fscache_n_store_vmscan_busy);
+		return false;
+	}
+
+	fscache_stat(&fscache_n_store_vmscan_wait);
+	__fscache_wait_on_page_write(cookie, page);
+	gfp &= ~__GFP_WAIT;
+	goto try_again;
 }
 EXPORT_SYMBOL(__fscache_maybe_release_page);
 
@@ -162,6 +171,7 @@ static void fscache_attr_changed_op(struct fscache_operation *op)
 			fscache_abort_object(object);
 	}
 
+	fscache_op_complete(op, true);
 	_leave("");
 }
 
@@ -223,6 +233,8 @@ static void fscache_release_retrieval_op(struct fscache_operation *_op)
 
 	_enter("{OP%x}", op->op.debug_id);
 
+	ASSERTCMP(op->n_pages, ==, 0);
+
 	fscache_hist(fscache_retrieval_histogram, op->start_time);
 	if (op->context)
 		fscache_put_context(op->op.object->cookie, op->context);
@@ -291,6 +303,17 @@ static int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie)
 }
 
 /*
+ * Handle cancellation of a pending retrieval op
+ */
+static void fscache_do_cancel_retrieval(struct fscache_operation *_op)
+{
+	struct fscache_retrieval *op =
+		container_of(_op, struct fscache_retrieval, op);
+
+	op->n_pages = 0;
+}
+
+/*
  * wait for an object to become active (or dead)
  */
 static int fscache_wait_for_retrieval_activation(struct fscache_object *object,
@@ -307,8 +330,8 @@ static int fscache_wait_for_retrieval_activation(struct fscache_object *object,
 	fscache_stat(stat_op_waits);
 	if (wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
 			fscache_wait_bit_interruptible,
-			TASK_INTERRUPTIBLE) < 0) {
-		ret = fscache_cancel_op(&op->op);
+			TASK_INTERRUPTIBLE) != 0) {
+		ret = fscache_cancel_op(&op->op, fscache_do_cancel_retrieval);
 		if (ret == 0)
 			return -ERESTARTSYS;
 
@@ -320,7 +343,14 @@ static int fscache_wait_for_retrieval_activation(struct fscache_object *object,
 	_debug("<<< GO");
 
 check_if_dead:
+	if (op->op.state == FSCACHE_OP_ST_CANCELLED) {
+		fscache_stat(stat_object_dead);
+		_leave(" = -ENOBUFS [cancelled]");
+		return -ENOBUFS;
+	}
 	if (unlikely(fscache_object_is_dead(object))) {
+		pr_err("%s() = -ENOBUFS [obj dead %d]\n", __func__, op->op.state);
+		fscache_cancel_op(&op->op, fscache_do_cancel_retrieval);
 		fscache_stat(stat_object_dead);
 		return -ENOBUFS;
 	}
@@ -353,6 +383,11 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 	if (hlist_empty(&cookie->backing_objects))
 		goto nobufs;
 
+	if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) {
+		_leave(" = -ENOBUFS [invalidating]");
+		return -ENOBUFS;
+	}
+
 	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
 	ASSERTCMP(page, !=, NULL);
 
@@ -364,6 +399,7 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 		_leave(" = -ENOMEM");
 		return -ENOMEM;
 	}
+	op->n_pages = 1;
 
 	spin_lock(&cookie->lock);
 
@@ -375,10 +411,10 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 	ASSERTCMP(object->state, >, FSCACHE_OBJECT_LOOKING_UP);
 
 	atomic_inc(&object->n_reads);
-	set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
+	__set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
 
 	if (fscache_submit_op(object, &op->op) < 0)
-		goto nobufs_unlock;
+		goto nobufs_unlock_dec;
 	spin_unlock(&cookie->lock);
 
 	fscache_stat(&fscache_n_retrieval_ops);
@@ -425,6 +461,8 @@ error:
 	_leave(" = %d", ret);
 	return ret;
 
+nobufs_unlock_dec:
+	atomic_dec(&object->n_reads);
 nobufs_unlock:
 	spin_unlock(&cookie->lock);
 	kfree(op);
@@ -472,6 +510,11 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 	if (hlist_empty(&cookie->backing_objects))
 		goto nobufs;
 
+	if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) {
+		_leave(" = -ENOBUFS [invalidating]");
+		return -ENOBUFS;
+	}
+
 	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
 	ASSERTCMP(*nr_pages, >, 0);
 	ASSERT(!list_empty(pages));
@@ -482,6 +525,7 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 	op = fscache_alloc_retrieval(mapping, end_io_func, context);
 	if (!op)
 		return -ENOMEM;
+	op->n_pages = *nr_pages;
 
 	spin_lock(&cookie->lock);
 
@@ -491,10 +535,10 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 			     struct fscache_object, cookie_link);
 
 	atomic_inc(&object->n_reads);
-	set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
+	__set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags);
 
 	if (fscache_submit_op(object, &op->op) < 0)
-		goto nobufs_unlock;
+		goto nobufs_unlock_dec;
 	spin_unlock(&cookie->lock);
 
 	fscache_stat(&fscache_n_retrieval_ops);
@@ -541,6 +585,8 @@ error:
 	_leave(" = %d", ret);
 	return ret;
 
+nobufs_unlock_dec:
+	atomic_dec(&object->n_reads);
 nobufs_unlock:
 	spin_unlock(&cookie->lock);
 	kfree(op);
@@ -577,12 +623,18 @@ int __fscache_alloc_page(struct fscache_cookie *cookie,
 	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
 	ASSERTCMP(page, !=, NULL);
 
+	if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) {
+		_leave(" = -ENOBUFS [invalidating]");
+		return -ENOBUFS;
+	}
+
 	if (fscache_wait_for_deferred_lookup(cookie) < 0)
 		return -ERESTARTSYS;
 
 	op = fscache_alloc_retrieval(page->mapping, NULL, NULL);
 	if (!op)
 		return -ENOMEM;
+	op->n_pages = 1;
 
 	spin_lock(&cookie->lock);
 
@@ -658,9 +710,27 @@ static void fscache_write_op(struct fscache_operation *_op)
 	spin_lock(&object->lock);
 	cookie = object->cookie;
 
-	if (!fscache_object_is_active(object) || !cookie) {
+	if (!fscache_object_is_active(object)) {
+		/* If we get here, then the on-disk cache object likely longer
+		 * exists, so we should just cancel this write operation.
+		 */
+		spin_unlock(&object->lock);
+		fscache_op_complete(&op->op, false);
+		_leave(" [inactive]");
+		return;
+	}
+
+	if (!cookie) {
+		/* If we get here, then the cookie belonging to the object was
+		 * detached, probably by the cookie being withdrawn due to
+		 * memory pressure, which means that the pages we might write
+		 * to the cache from no longer exist - therefore, we can just
+		 * cancel this write operation.
+		 */
 		spin_unlock(&object->lock);
-		_leave("");
+		fscache_op_complete(&op->op, false);
+		_leave(" [cancel] op{f=%lx s=%u} obj{s=%u f=%lx}",
+		       _op->flags, _op->state, object->state, object->flags);
 		return;
 	}
 
@@ -696,6 +766,7 @@ static void fscache_write_op(struct fscache_operation *_op)
 	fscache_end_page_write(object, page);
 	if (ret < 0) {
 		fscache_abort_object(object);
+		fscache_op_complete(&op->op, true);
 	} else {
 		fscache_enqueue_operation(&op->op);
 	}
@@ -710,6 +781,38 @@ superseded:
 	spin_unlock(&cookie->stores_lock);
 	clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
 	spin_unlock(&object->lock);
+	fscache_op_complete(&op->op, true);
+	_leave("");
+}
+
+/*
+ * Clear the pages pending writing for invalidation
+ */
+void fscache_invalidate_writes(struct fscache_cookie *cookie)
+{
+	struct page *page;
+	void *results[16];
+	int n, i;
+
+	_enter("");
+
+	while (spin_lock(&cookie->stores_lock),
+	       n = radix_tree_gang_lookup_tag(&cookie->stores, results, 0,
+					      ARRAY_SIZE(results),
+					      FSCACHE_COOKIE_PENDING_TAG),
+	       n > 0) {
+		for (i = n - 1; i >= 0; i--) {
+			page = results[i];
+			radix_tree_delete(&cookie->stores, page->index);
+		}
+
+		spin_unlock(&cookie->stores_lock);
+
+		for (i = n - 1; i >= 0; i--)
+			page_cache_release(results[i]);
+	}
+
+	spin_unlock(&cookie->stores_lock);
 	_leave("");
 }
 
@@ -759,7 +862,12 @@ int __fscache_write_page(struct fscache_cookie *cookie,
 
 	fscache_stat(&fscache_n_stores);
 
-	op = kzalloc(sizeof(*op), GFP_NOIO);
+	if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) {
+		_leave(" = -ENOBUFS [invalidating]");
+		return -ENOBUFS;
+	}
+
+	op = kzalloc(sizeof(*op), GFP_NOIO | __GFP_NOMEMALLOC | __GFP_NORETRY);
 	if (!op)
 		goto nomem;
 
@@ -915,6 +1023,40 @@ done:
 EXPORT_SYMBOL(__fscache_uncache_page);
 
 /**
+ * fscache_mark_page_cached - Mark a page as being cached
+ * @op: The retrieval op pages are being marked for
+ * @page: The page to be marked
+ *
+ * Mark a netfs page as being cached.  After this is called, the netfs
+ * must call fscache_uncache_page() to remove the mark.
+ */
+void fscache_mark_page_cached(struct fscache_retrieval *op, struct page *page)
+{
+	struct fscache_cookie *cookie = op->op.object->cookie;
+
+#ifdef CONFIG_FSCACHE_STATS
+	atomic_inc(&fscache_n_marks);
+#endif
+
+	_debug("- mark %p{%lx}", page, page->index);
+	if (TestSetPageFsCache(page)) {
+		static bool once_only;
+		if (!once_only) {
+			once_only = true;
+			printk(KERN_WARNING "FS-Cache:"
+			       " Cookie type %s marked page %lx"
+			       " multiple times\n",
+			       cookie->def->name, page->index);
+		}
+	}
+
+	if (cookie->def->mark_page_cached)
+		cookie->def->mark_page_cached(cookie->netfs_data,
+					      op->mapping, page);
+}
+EXPORT_SYMBOL(fscache_mark_page_cached);
+
+/**
  * fscache_mark_pages_cached - Mark pages as being cached
  * @op: The retrieval op pages are being marked for
  * @pagevec: The pages to be marked
@@ -925,32 +1067,11 @@ EXPORT_SYMBOL(__fscache_uncache_page);
 void fscache_mark_pages_cached(struct fscache_retrieval *op,
 			       struct pagevec *pagevec)
 {
-	struct fscache_cookie *cookie = op->op.object->cookie;
 	unsigned long loop;
 
-#ifdef CONFIG_FSCACHE_STATS
-	atomic_add(pagevec->nr, &fscache_n_marks);
-#endif
-
-	for (loop = 0; loop < pagevec->nr; loop++) {
-		struct page *page = pagevec->pages[loop];
-
-		_debug("- mark %p{%lx}", page, page->index);
-		if (TestSetPageFsCache(page)) {
-			static bool once_only;
-			if (!once_only) {
-				once_only = true;
-				printk(KERN_WARNING "FS-Cache:"
-				       " Cookie type %s marked page %lx"
-				       " multiple times\n",
-				       cookie->def->name, page->index);
-			}
-		}
-	}
+	for (loop = 0; loop < pagevec->nr; loop++)
+		fscache_mark_page_cached(op, pagevec->pages[loop]);
 
-	if (cookie->def->mark_pages_cached)
-		cookie->def->mark_pages_cached(cookie->netfs_data,
-					       op->mapping, pagevec);
 	pagevec_reinit(pagevec);
 }
 EXPORT_SYMBOL(fscache_mark_pages_cached);
diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
index 4765190..8179e8b 100644
--- a/fs/fscache/stats.c
+++ b/fs/fscache/stats.c
@@ -69,6 +69,7 @@ atomic_t fscache_n_store_vmscan_not_storing;
 atomic_t fscache_n_store_vmscan_gone;
 atomic_t fscache_n_store_vmscan_busy;
 atomic_t fscache_n_store_vmscan_cancelled;
+atomic_t fscache_n_store_vmscan_wait;
 
 atomic_t fscache_n_marks;
 atomic_t fscache_n_uncaches;
@@ -80,6 +81,9 @@ atomic_t fscache_n_acquires_ok;
 atomic_t fscache_n_acquires_nobufs;
 atomic_t fscache_n_acquires_oom;
 
+atomic_t fscache_n_invalidates;
+atomic_t fscache_n_invalidates_run;
+
 atomic_t fscache_n_updates;
 atomic_t fscache_n_updates_null;
 atomic_t fscache_n_updates_run;
@@ -112,6 +116,7 @@ atomic_t fscache_n_cop_alloc_object;
 atomic_t fscache_n_cop_lookup_object;
 atomic_t fscache_n_cop_lookup_complete;
 atomic_t fscache_n_cop_grab_object;
+atomic_t fscache_n_cop_invalidate_object;
 atomic_t fscache_n_cop_update_object;
 atomic_t fscache_n_cop_drop_object;
 atomic_t fscache_n_cop_put_object;
@@ -168,6 +173,10 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&fscache_n_object_created),
 		   atomic_read(&fscache_n_object_lookups_timed_out));
 
+	seq_printf(m, "Invals : n=%u run=%u\n",
+		   atomic_read(&fscache_n_invalidates),
+		   atomic_read(&fscache_n_invalidates_run));
+
 	seq_printf(m, "Updates: n=%u nul=%u run=%u\n",
 		   atomic_read(&fscache_n_updates),
 		   atomic_read(&fscache_n_updates_null),
@@ -224,11 +233,12 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&fscache_n_store_radix_deletes),
 		   atomic_read(&fscache_n_store_pages_over_limit));
 
-	seq_printf(m, "VmScan : nos=%u gon=%u bsy=%u can=%u\n",
+	seq_printf(m, "VmScan : nos=%u gon=%u bsy=%u can=%u wt=%u\n",
 		   atomic_read(&fscache_n_store_vmscan_not_storing),
 		   atomic_read(&fscache_n_store_vmscan_gone),
 		   atomic_read(&fscache_n_store_vmscan_busy),
-		   atomic_read(&fscache_n_store_vmscan_cancelled));
+		   atomic_read(&fscache_n_store_vmscan_cancelled),
+		   atomic_read(&fscache_n_store_vmscan_wait));
 
 	seq_printf(m, "Ops    : pend=%u run=%u enq=%u can=%u rej=%u\n",
 		   atomic_read(&fscache_n_op_pend),
@@ -246,7 +256,8 @@ static int fscache_stats_show(struct seq_file *m, void *v)
 		   atomic_read(&fscache_n_cop_lookup_object),
 		   atomic_read(&fscache_n_cop_lookup_complete),
 		   atomic_read(&fscache_n_cop_grab_object));
-	seq_printf(m, "CacheOp: upo=%d dro=%d pto=%d atc=%d syn=%d\n",
+	seq_printf(m, "CacheOp: inv=%d upo=%d dro=%d pto=%d atc=%d syn=%d\n",
+		   atomic_read(&fscache_n_cop_invalidate_object),
 		   atomic_read(&fscache_n_cop_update_object),
 		   atomic_read(&fscache_n_cop_drop_object),
 		   atomic_read(&fscache_n_cop_put_object),
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 0b35903..d47f116 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -35,6 +35,16 @@ static int hfs_readpage(struct file *file, struct page *page)
 	return block_read_full_page(page, hfs_get_block);
 }
 
+static void hfs_write_failed(struct address_space *mapping, loff_t to)
+{
+	struct inode *inode = mapping->host;
+
+	if (to > inode->i_size) {
+		truncate_pagecache(inode, to, inode->i_size);
+		hfs_file_truncate(inode);
+	}
+}
+
 static int hfs_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata)
@@ -45,11 +55,8 @@ static int hfs_write_begin(struct file *file, struct address_space *mapping,
 	ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
 				hfs_get_block,
 				&HFS_I(mapping->host)->phys_size);
-	if (unlikely(ret)) {
-		loff_t isize = mapping->host->i_size;
-		if (pos + len > isize)
-			vmtruncate(mapping->host, isize);
-	}
+	if (unlikely(ret))
+		hfs_write_failed(mapping, pos + len);
 
 	return ret;
 }
@@ -120,6 +127,7 @@ static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb,
 		const struct iovec *iov, loff_t offset, unsigned long nr_segs)
 {
 	struct file *file = iocb->ki_filp;
+	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = file->f_path.dentry->d_inode->i_mapping->host;
 	ssize_t ret;
 
@@ -135,7 +143,7 @@ static ssize_t hfs_direct_IO(int rw, struct kiocb *iocb,
 		loff_t end = offset + iov_length(iov, nr_segs);
 
 		if (end > isize)
-			vmtruncate(inode, isize);
+			hfs_write_failed(mapping, end);
 	}
 
 	return ret;
@@ -617,9 +625,12 @@ int hfs_inode_setattr(struct dentry *dentry, struct iattr * attr)
 	    attr->ia_size != i_size_read(inode)) {
 		inode_dio_wait(inode);
 
-		error = vmtruncate(inode, attr->ia_size);
+		error = inode_newsize_ok(inode, attr->ia_size);
 		if (error)
 			return error;
+
+		truncate_setsize(inode, attr->ia_size);
+		hfs_file_truncate(inode);
 	}
 
 	setattr_copy(inode, attr);
@@ -668,7 +679,6 @@ static const struct file_operations hfs_file_operations = {
 
 static const struct inode_operations hfs_file_inode_operations = {
 	.lookup		= hfs_file_lookup,
-	.truncate	= hfs_file_truncate,
 	.setattr	= hfs_inode_setattr,
 	.setxattr	= hfs_setxattr,
 	.getxattr	= hfs_getxattr,
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 2172aa5..799b336 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -28,6 +28,16 @@ static int hfsplus_writepage(struct page *page, struct writeback_control *wbc)
 	return block_write_full_page(page, hfsplus_get_block, wbc);
 }
 
+static void hfsplus_write_failed(struct address_space *mapping, loff_t to)
+{
+	struct inode *inode = mapping->host;
+
+	if (to > inode->i_size) {
+		truncate_pagecache(inode, to, inode->i_size);
+		hfsplus_file_truncate(inode);
+	}
+}
+
 static int hfsplus_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata)
@@ -38,11 +48,8 @@ static int hfsplus_write_begin(struct file *file, struct address_space *mapping,
 	ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
 				hfsplus_get_block,
 				&HFSPLUS_I(mapping->host)->phys_size);
-	if (unlikely(ret)) {
-		loff_t isize = mapping->host->i_size;
-		if (pos + len > isize)
-			vmtruncate(mapping->host, isize);
-	}
+	if (unlikely(ret))
+		hfsplus_write_failed(mapping, pos + len);
 
 	return ret;
 }
@@ -116,6 +123,7 @@ static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb,
 		const struct iovec *iov, loff_t offset, unsigned long nr_segs)
 {
 	struct file *file = iocb->ki_filp;
+	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = file->f_path.dentry->d_inode->i_mapping->host;
 	ssize_t ret;
 
@@ -131,7 +139,7 @@ static ssize_t hfsplus_direct_IO(int rw, struct kiocb *iocb,
 		loff_t end = offset + iov_length(iov, nr_segs);
 
 		if (end > isize)
-			vmtruncate(inode, isize);
+			hfsplus_write_failed(mapping, end);
 	}
 
 	return ret;
@@ -300,10 +308,8 @@ static int hfsplus_setattr(struct dentry *dentry, struct iattr *attr)
 	if ((attr->ia_valid & ATTR_SIZE) &&
 	    attr->ia_size != i_size_read(inode)) {
 		inode_dio_wait(inode);
-
-		error = vmtruncate(inode, attr->ia_size);
-		if (error)
-			return error;
+		truncate_setsize(inode, attr->ia_size);
+		hfsplus_file_truncate(inode);
 	}
 
 	setattr_copy(inode, attr);
@@ -358,7 +364,6 @@ int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end,
 
 static const struct inode_operations hfsplus_file_inode_operations = {
 	.lookup		= hfsplus_file_lookup,
-	.truncate	= hfsplus_file_truncate,
 	.setattr	= hfsplus_setattr,
 	.setxattr	= hfsplus_setxattr,
 	.getxattr	= hfsplus_getxattr,
diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c
index 89d2a58..fbfe2df 100644
--- a/fs/hpfs/file.c
+++ b/fs/hpfs/file.c
@@ -50,7 +50,7 @@ static secno hpfs_bmap(struct inode *inode, unsigned file_secno)
 	return disk_secno;
 }
 
-static void hpfs_truncate(struct inode *i)
+void hpfs_truncate(struct inode *i)
 {
 	if (IS_IMMUTABLE(i)) return /*-EPERM*/;
 	hpfs_lock_assert(i->i_sb);
@@ -105,6 +105,16 @@ static int hpfs_readpage(struct file *file, struct page *page)
 	return block_read_full_page(page,hpfs_get_block);
 }
 
+static void hpfs_write_failed(struct address_space *mapping, loff_t to)
+{
+	struct inode *inode = mapping->host;
+
+	if (to > inode->i_size) {
+		truncate_pagecache(inode, to, inode->i_size);
+		hpfs_truncate(inode);
+	}
+}
+
 static int hpfs_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata)
@@ -115,11 +125,8 @@ static int hpfs_write_begin(struct file *file, struct address_space *mapping,
 	ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
 				hpfs_get_block,
 				&hpfs_i(mapping->host)->mmu_private);
-	if (unlikely(ret)) {
-		loff_t isize = mapping->host->i_size;
-		if (pos + len > isize)
-			vmtruncate(mapping->host, isize);
-	}
+	if (unlikely(ret))
+		hpfs_write_failed(mapping, pos + len);
 
 	return ret;
 }
@@ -166,6 +173,5 @@ const struct file_operations hpfs_file_ops =
 
 const struct inode_operations hpfs_file_iops =
 {
-	.truncate	= hpfs_truncate,
 	.setattr	= hpfs_setattr,
 };
diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h
index 7102aae..b7ae286 100644
--- a/fs/hpfs/hpfs_fn.h
+++ b/fs/hpfs/hpfs_fn.h
@@ -252,6 +252,7 @@ void hpfs_set_ea(struct inode *, struct fnode *, const char *,
 /* file.c */
 
 int hpfs_file_fsync(struct file *, loff_t, loff_t, int);
+void hpfs_truncate(struct inode *);
 extern const struct file_operations hpfs_file_ops;
 extern const struct inode_operations hpfs_file_iops;
 extern const struct address_space_operations hpfs_aops;
diff --git a/fs/hpfs/inode.c b/fs/hpfs/inode.c
index 804a9a8..5dc06c8 100644
--- a/fs/hpfs/inode.c
+++ b/fs/hpfs/inode.c
@@ -277,9 +277,12 @@ int hpfs_setattr(struct dentry *dentry, struct iattr *attr)
 
 	if ((attr->ia_valid & ATTR_SIZE) &&
 	    attr->ia_size != i_size_read(inode)) {
-		error = vmtruncate(inode, attr->ia_size);
+		error = inode_newsize_ok(inode, attr->ia_size);
 		if (error)
 			goto out_unlock;
+
+		truncate_setsize(inode, attr->ia_size);
+		hpfs_truncate(inode);
 	}
 
 	setattr_copy(inode, attr);
diff --git a/fs/jfs/file.c b/fs/jfs/file.c
index 9d3afd1..dd7442c 100644
--- a/fs/jfs/file.c
+++ b/fs/jfs/file.c
@@ -119,9 +119,12 @@ int jfs_setattr(struct dentry *dentry, struct iattr *iattr)
 	    iattr->ia_size != i_size_read(inode)) {
 		inode_dio_wait(inode);
 
-		rc = vmtruncate(inode, iattr->ia_size);
+		rc = inode_newsize_ok(inode, iattr->ia_size);
 		if (rc)
 			return rc;
+
+		truncate_setsize(inode, iattr->ia_size);
+		jfs_truncate(inode);
 	}
 
 	setattr_copy(inode, iattr);
@@ -133,7 +136,6 @@ int jfs_setattr(struct dentry *dentry, struct iattr *iattr)
 }
 
 const struct inode_operations jfs_file_inode_operations = {
-	.truncate	= jfs_truncate,
 	.setxattr	= jfs_setxattr,
 	.getxattr	= jfs_getxattr,
 	.listxattr	= jfs_listxattr,
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 4692bf3..b7dc47b 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -300,6 +300,16 @@ static int jfs_readpages(struct file *file, struct address_space *mapping,
 	return mpage_readpages(mapping, pages, nr_pages, jfs_get_block);
 }
 
+static void jfs_write_failed(struct address_space *mapping, loff_t to)
+{
+	struct inode *inode = mapping->host;
+
+	if (to > inode->i_size) {
+		truncate_pagecache(inode, to, inode->i_size);
+		jfs_truncate(inode);
+	}
+}
+
 static int jfs_write_begin(struct file *file, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned flags,
 				struct page **pagep, void **fsdata)
@@ -308,11 +318,8 @@ static int jfs_write_begin(struct file *file, struct address_space *mapping,
 
 	ret = nobh_write_begin(mapping, pos, len, flags, pagep, fsdata,
 				jfs_get_block);
-	if (unlikely(ret)) {
-		loff_t isize = mapping->host->i_size;
-		if (pos + len > isize)
-			vmtruncate(mapping->host, isize);
-	}
+	if (unlikely(ret))
+		jfs_write_failed(mapping, pos + len);
 
 	return ret;
 }
@@ -326,6 +333,7 @@ static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb,
 	const struct iovec *iov, loff_t offset, unsigned long nr_segs)
 {
 	struct file *file = iocb->ki_filp;
+	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = file->f_mapping->host;
 	ssize_t ret;
 
@@ -341,7 +349,7 @@ static ssize_t jfs_direct_IO(int rw, struct kiocb *iocb,
 		loff_t end = offset + iov_length(iov, nr_segs);
 
 		if (end > isize)
-			vmtruncate(inode, isize);
+			jfs_write_failed(mapping, end);
 	}
 
 	return ret;
diff --git a/fs/libfs.c b/fs/libfs.c
index 35fc6e7..916da8c 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -369,8 +369,6 @@ int simple_setattr(struct dentry *dentry, struct iattr *iattr)
 	struct inode *inode = dentry->d_inode;
 	int error;
 
-	WARN_ON_ONCE(inode->i_op->truncate);
-
 	error = inode_change_ok(inode, iattr);
 	if (error)
 		return error;
diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c
index e1a3b6b..9a59cba 100644
--- a/fs/logfs/readwrite.c
+++ b/fs/logfs/readwrite.c
@@ -1887,9 +1887,15 @@ int logfs_truncate(struct inode *inode, u64 target)
 		logfs_put_wblocks(sb, NULL, 1);
 	}
 
-	if (!err)
-		err = vmtruncate(inode, target);
+	if (!err) {
+		err = inode_newsize_ok(inode, target);
+		if (err)
+			goto out;
+
+		truncate_setsize(inode, target);
+	}
 
+ out:
 	/* I don't trust error recovery yet. */
 	WARN_ON(err);
 	return err;
diff --git a/fs/minix/file.c b/fs/minix/file.c
index 4493ce6..adc6f54 100644
--- a/fs/minix/file.c
+++ b/fs/minix/file.c
@@ -34,9 +34,12 @@ static int minix_setattr(struct dentry *dentry, struct iattr *attr)
 
 	if ((attr->ia_valid & ATTR_SIZE) &&
 	    attr->ia_size != i_size_read(inode)) {
-		error = vmtruncate(inode, attr->ia_size);
+		error = inode_newsize_ok(inode, attr->ia_size);
 		if (error)
 			return error;
+
+		truncate_setsize(inode, attr->ia_size);
+		minix_truncate(inode);
 	}
 
 	setattr_copy(inode, attr);
@@ -45,7 +48,6 @@ static int minix_setattr(struct dentry *dentry, struct iattr *attr)
 }
 
 const struct inode_operations minix_file_inode_operations = {
-	.truncate	= minix_truncate,
 	.setattr	= minix_setattr,
 	.getattr	= minix_getattr,
 };
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 4fc5f8a..99541cc 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -395,6 +395,16 @@ int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len)
 	return __block_write_begin(page, pos, len, minix_get_block);
 }
 
+static void minix_write_failed(struct address_space *mapping, loff_t to)
+{
+	struct inode *inode = mapping->host;
+
+	if (to > inode->i_size) {
+		truncate_pagecache(inode, to, inode->i_size);
+		minix_truncate(inode);
+	}
+}
+
 static int minix_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata)
@@ -403,11 +413,8 @@ static int minix_write_begin(struct file *file, struct address_space *mapping,
 
 	ret = block_write_begin(mapping, pos, len, flags, pagep,
 				minix_get_block);
-	if (unlikely(ret)) {
-		loff_t isize = mapping->host->i_size;
-		if (pos + len > isize)
-			vmtruncate(mapping->host, isize);
-	}
+	if (unlikely(ret))
+		minix_write_failed(mapping, pos + len);
 
 	return ret;
 }
diff --git a/fs/namei.c b/fs/namei.c
index 5f4cdf3..43a97ee 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1275,9 +1275,7 @@ static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir,
 	*need_lookup = false;
 	dentry = d_lookup(dir, name);
 	if (dentry) {
-		if (d_need_lookup(dentry)) {
-			*need_lookup = true;
-		} else if (dentry->d_flags & DCACHE_OP_REVALIDATE) {
+		if (dentry->d_flags & DCACHE_OP_REVALIDATE) {
 			error = d_revalidate(dentry, flags);
 			if (unlikely(error <= 0)) {
 				if (error < 0) {
@@ -1383,8 +1381,6 @@ static int lookup_fast(struct nameidata *nd, struct qstr *name,
 			return -ECHILD;
 		nd->seq = seq;
 
-		if (unlikely(d_need_lookup(dentry)))
-			goto unlazy;
 		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
 			status = d_revalidate(dentry, nd->flags);
 			if (unlikely(status <= 0)) {
@@ -1410,11 +1406,6 @@ unlazy:
 	if (unlikely(!dentry))
 		goto need_lookup;
 
-	if (unlikely(d_need_lookup(dentry))) {
-		dput(dentry);
-		goto need_lookup;
-	}
-
 	if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval)
 		status = d_revalidate(dentry, nd->flags);
 	if (unlikely(status <= 0)) {
@@ -1859,7 +1850,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 	if (flags & LOOKUP_ROOT) {
 		struct inode *inode = nd->root.dentry->d_inode;
 		if (*name) {
-			if (!inode->i_op->lookup)
+			if (!can_lookup(inode))
 				return -ENOTDIR;
 			retval = inode_permission(inode, MAY_EXEC);
 			if (retval)
@@ -1903,6 +1894,7 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 			get_fs_pwd(current->fs, &nd->path);
 		}
 	} else {
+		/* Caller must check execute permissions on the starting path component */
 		struct fd f = fdget_raw(dfd);
 		struct dentry *dentry;
 
@@ -1912,16 +1904,10 @@ static int path_init(int dfd, const char *name, unsigned int flags,
 		dentry = f.file->f_path.dentry;
 
 		if (*name) {
-			if (!S_ISDIR(dentry->d_inode->i_mode)) {
+			if (!can_lookup(dentry->d_inode)) {
 				fdput(f);
 				return -ENOTDIR;
 			}
-
-			retval = inode_permission(dentry->d_inode, MAY_EXEC);
-			if (retval) {
-				fdput(f);
-				return retval;
-			}
 		}
 
 		nd->path = f.file->f_path;
@@ -2189,15 +2175,19 @@ int user_path_at(int dfd, const char __user *name, unsigned flags,
  *     path-walking is complete.
  */
 static struct filename *
-user_path_parent(int dfd, const char __user *path, struct nameidata *nd)
+user_path_parent(int dfd, const char __user *path, struct nameidata *nd,
+		 unsigned int flags)
 {
 	struct filename *s = getname(path);
 	int error;
 
+	/* only LOOKUP_REVAL is allowed in extra flags */
+	flags &= LOOKUP_REVAL;
+
 	if (IS_ERR(s))
 		return s;
 
-	error = filename_lookup(dfd, s, LOOKUP_PARENT, nd);
+	error = filename_lookup(dfd, s, flags | LOOKUP_PARENT, nd);
 	if (error) {
 		putname(s);
 		return ERR_PTR(error);
@@ -3044,12 +3034,22 @@ struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt,
 	return file;
 }
 
-struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path, int is_dir)
+struct dentry *kern_path_create(int dfd, const char *pathname,
+				struct path *path, unsigned int lookup_flags)
 {
 	struct dentry *dentry = ERR_PTR(-EEXIST);
 	struct nameidata nd;
 	int err2;
-	int error = do_path_lookup(dfd, pathname, LOOKUP_PARENT, &nd);
+	int error;
+	bool is_dir = (lookup_flags & LOOKUP_DIRECTORY);
+
+	/*
+	 * Note that only LOOKUP_REVAL and LOOKUP_DIRECTORY matter here. Any
+	 * other flags passed in are ignored!
+	 */
+	lookup_flags &= LOOKUP_REVAL;
+
+	error = do_path_lookup(dfd, pathname, LOOKUP_PARENT|lookup_flags, &nd);
 	if (error)
 		return ERR_PTR(error);
 
@@ -3113,13 +3113,14 @@ void done_path_create(struct path *path, struct dentry *dentry)
 }
 EXPORT_SYMBOL(done_path_create);
 
-struct dentry *user_path_create(int dfd, const char __user *pathname, struct path *path, int is_dir)
+struct dentry *user_path_create(int dfd, const char __user *pathname,
+				struct path *path, unsigned int lookup_flags)
 {
 	struct filename *tmp = getname(pathname);
 	struct dentry *res;
 	if (IS_ERR(tmp))
 		return ERR_CAST(tmp);
-	res = kern_path_create(dfd, tmp->name, path, is_dir);
+	res = kern_path_create(dfd, tmp->name, path, lookup_flags);
 	putname(tmp);
 	return res;
 }
@@ -3175,12 +3176,13 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode,
 	struct dentry *dentry;
 	struct path path;
 	int error;
+	unsigned int lookup_flags = 0;
 
 	error = may_mknod(mode);
 	if (error)
 		return error;
-
-	dentry = user_path_create(dfd, filename, &path, 0);
+retry:
+	dentry = user_path_create(dfd, filename, &path, lookup_flags);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
@@ -3203,6 +3205,10 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode,
 	}
 out:
 	done_path_create(&path, dentry);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 	return error;
 }
 
@@ -3241,8 +3247,10 @@ SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode)
 	struct dentry *dentry;
 	struct path path;
 	int error;
+	unsigned int lookup_flags = LOOKUP_DIRECTORY;
 
-	dentry = user_path_create(dfd, pathname, &path, 1);
+retry:
+	dentry = user_path_create(dfd, pathname, &path, lookup_flags);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
@@ -3252,6 +3260,10 @@ SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode)
 	if (!error)
 		error = vfs_mkdir(path.dentry->d_inode, dentry, mode);
 	done_path_create(&path, dentry);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 	return error;
 }
 
@@ -3327,8 +3339,9 @@ static long do_rmdir(int dfd, const char __user *pathname)
 	struct filename *name;
 	struct dentry *dentry;
 	struct nameidata nd;
-
-	name = user_path_parent(dfd, pathname, &nd);
+	unsigned int lookup_flags = 0;
+retry:
+	name = user_path_parent(dfd, pathname, &nd, lookup_flags);
 	if (IS_ERR(name))
 		return PTR_ERR(name);
 
@@ -3370,6 +3383,10 @@ exit2:
 exit1:
 	path_put(&nd.path);
 	putname(name);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 	return error;
 }
 
@@ -3423,8 +3440,9 @@ static long do_unlinkat(int dfd, const char __user *pathname)
 	struct dentry *dentry;
 	struct nameidata nd;
 	struct inode *inode = NULL;
-
-	name = user_path_parent(dfd, pathname, &nd);
+	unsigned int lookup_flags = 0;
+retry:
+	name = user_path_parent(dfd, pathname, &nd, lookup_flags);
 	if (IS_ERR(name))
 		return PTR_ERR(name);
 
@@ -3462,6 +3480,11 @@ exit2:
 exit1:
 	path_put(&nd.path);
 	putname(name);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		inode = NULL;
+		goto retry;
+	}
 	return error;
 
 slashes:
@@ -3513,12 +3536,13 @@ SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
 	struct filename *from;
 	struct dentry *dentry;
 	struct path path;
+	unsigned int lookup_flags = 0;
 
 	from = getname(oldname);
 	if (IS_ERR(from))
 		return PTR_ERR(from);
-
-	dentry = user_path_create(newdfd, newname, &path, 0);
+retry:
+	dentry = user_path_create(newdfd, newname, &path, lookup_flags);
 	error = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
 		goto out_putname;
@@ -3527,6 +3551,10 @@ SYSCALL_DEFINE3(symlinkat, const char __user *, oldname,
 	if (!error)
 		error = vfs_symlink(path.dentry->d_inode, dentry, from->name);
 	done_path_create(&path, dentry);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 out_putname:
 	putname(from);
 	return error;
@@ -3613,12 +3641,13 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
 
 	if (flags & AT_SYMLINK_FOLLOW)
 		how |= LOOKUP_FOLLOW;
-
+retry:
 	error = user_path_at(olddfd, oldname, how, &old_path);
 	if (error)
 		return error;
 
-	new_dentry = user_path_create(newdfd, newname, &new_path, 0);
+	new_dentry = user_path_create(newdfd, newname, &new_path,
+					(how & LOOKUP_REVAL));
 	error = PTR_ERR(new_dentry);
 	if (IS_ERR(new_dentry))
 		goto out;
@@ -3635,6 +3664,10 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
 	error = vfs_link(old_path.dentry, new_path.dentry->d_inode, new_dentry);
 out_dput:
 	done_path_create(&new_path, new_dentry);
+	if (retry_estale(error, how)) {
+		how |= LOOKUP_REVAL;
+		goto retry;
+	}
 out:
 	path_put(&old_path);
 
@@ -3807,15 +3840,17 @@ SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname,
 	struct nameidata oldnd, newnd;
 	struct filename *from;
 	struct filename *to;
+	unsigned int lookup_flags = 0;
+	bool should_retry = false;
 	int error;
-
-	from = user_path_parent(olddfd, oldname, &oldnd);
+retry:
+	from = user_path_parent(olddfd, oldname, &oldnd, lookup_flags);
 	if (IS_ERR(from)) {
 		error = PTR_ERR(from);
 		goto exit;
 	}
 
-	to = user_path_parent(newdfd, newname, &newnd);
+	to = user_path_parent(newdfd, newname, &newnd, lookup_flags);
 	if (IS_ERR(to)) {
 		error = PTR_ERR(to);
 		goto exit1;
@@ -3887,11 +3922,18 @@ exit3:
 	unlock_rename(new_dir, old_dir);
 	mnt_drop_write(oldnd.path.mnt);
 exit2:
+	if (retry_estale(error, lookup_flags))
+		should_retry = true;
 	path_put(&newnd.path);
 	putname(to);
 exit1:
 	path_put(&oldnd.path);
 	putname(from);
+	if (should_retry) {
+		should_retry = false;
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 exit:
 	return error;
 }
diff --git a/fs/namespace.c b/fs/namespace.c
index 398a50f..55605c5 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -313,7 +313,7 @@ int __mnt_want_write(struct vfsmount *m)
 	 * incremented count after it has set MNT_WRITE_HOLD.
 	 */
 	smp_mb();
-	while (mnt->mnt.mnt_flags & MNT_WRITE_HOLD)
+	while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD)
 		cpu_relax();
 	/*
 	 * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index d7e9fe7..1acdad7 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -976,9 +976,7 @@ int ncp_notify_change(struct dentry *dentry, struct iattr *attr)
 			goto out;
 
 		if (attr->ia_size != i_size_read(inode)) {
-			result = vmtruncate(inode, attr->ia_size);
-			if (result)
-				goto out;
+			truncate_setsize(inode, attr->ia_size);
 			mark_inode_dirty(inode);
 		}
 	}
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index c817787..24d1d1c 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -307,6 +307,7 @@ void nfs_fscache_set_inode_cookie(struct inode *inode, struct file *filp)
 		nfs_fscache_inode_unlock(inode);
 	}
 }
+EXPORT_SYMBOL_GPL(nfs_fscache_set_inode_cookie);
 
 /*
  * Replace a per-inode cookie due to revalidation detecting a file having
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index c5b11b5..277b027 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -153,6 +153,22 @@ static inline void nfs_readpage_to_fscache(struct inode *inode,
 }
 
 /*
+ * Invalidate the contents of fscache for this inode.  This will not sleep.
+ */
+static inline void nfs_fscache_invalidate(struct inode *inode)
+{
+	fscache_invalidate(NFS_I(inode)->fscache);
+}
+
+/*
+ * Wait for an object to finish being invalidated.
+ */
+static inline void nfs_fscache_wait_on_invalidate(struct inode *inode)
+{
+	fscache_wait_on_invalidate(NFS_I(inode)->fscache);
+}
+
+/*
  * indicate the client caching state as readable text
  */
 static inline const char *nfs_server_fscache_state(struct nfs_server *server)
@@ -162,7 +178,6 @@ static inline const char *nfs_server_fscache_state(struct nfs_server *server)
 	return "no ";
 }
 
-
 #else /* CONFIG_NFS_FSCACHE */
 static inline int nfs_fscache_register(void) { return 0; }
 static inline void nfs_fscache_unregister(void) {}
@@ -205,6 +220,9 @@ static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx,
 static inline void nfs_readpage_to_fscache(struct inode *inode,
 					   struct page *page, int sync) {}
 
+
+static inline void nfs_fscache_invalidate(struct inode *inode) {}
+
 static inline const char *nfs_server_fscache_state(struct nfs_server *server)
 {
 	return "no ";
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 2faae14..ebeb94c 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -161,10 +161,12 @@ static void nfs_zap_caches_locked(struct inode *inode)
 	nfsi->attrtimeo_timestamp = jiffies;
 
 	memset(NFS_I(inode)->cookieverf, 0, sizeof(NFS_I(inode)->cookieverf));
-	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))
+	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
 		nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE;
-	else
+		nfs_fscache_invalidate(inode);
+	} else {
 		nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE;
+	}
 }
 
 void nfs_zap_caches(struct inode *inode)
@@ -179,6 +181,7 @@ void nfs_zap_mapping(struct inode *inode, struct address_space *mapping)
 	if (mapping->nrpages != 0) {
 		spin_lock(&inode->i_lock);
 		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA;
+		nfs_fscache_invalidate(inode);
 		spin_unlock(&inode->i_lock);
 	}
 }
@@ -881,7 +884,7 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
 		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
 	spin_unlock(&inode->i_lock);
 	nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
-	nfs_fscache_reset_inode_cookie(inode);
+	nfs_fscache_wait_on_invalidate(inode);
 	dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n",
 			inode->i_sb->s_id, (long long)NFS_FILEID(inode));
 	return 0;
@@ -957,6 +960,10 @@ static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr
 		i_size_write(inode, nfs_size_to_loff_t(fattr->size));
 		ret |= NFS_INO_INVALID_ATTR;
 	}
+
+	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
+		nfs_fscache_invalidate(inode);
+
 	return ret;
 }
 
@@ -1205,8 +1212,10 @@ static int nfs_post_op_update_inode_locked(struct inode *inode, struct nfs_fattr
 	struct nfs_inode *nfsi = NFS_I(inode);
 
 	nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
-	if (S_ISDIR(inode->i_mode))
+	if (S_ISDIR(inode->i_mode)) {
 		nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+		nfs_fscache_invalidate(inode);
+	}
 	if ((fattr->valid & NFS_ATTR_FATTR) == 0)
 		return 0;
 	return nfs_refresh_inode_locked(inode, fattr);
@@ -1494,6 +1503,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			(save_cache_validity & NFS_INO_REVAL_FORCED))
 		nfsi->cache_validity |= invalid;
 
+	if (invalid & NFS_INO_INVALID_DATA)
+		nfs_fscache_invalidate(inode);
+
 	return 0;
  out_err:
 	/*
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index e769930..08ddccc 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -5,6 +5,7 @@
  */
 #include <linux/nfs_fs.h>
 #include "internal.h"
+#include "fscache.h"
 #include "pnfs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_FILE
@@ -74,6 +75,7 @@ nfs4_file_open(struct inode *inode, struct file *filp)
 
 	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 	nfs_file_set_open_context(filp, ctx);
+	nfs_fscache_set_inode_cookie(inode, filp);
 	err = 0;
 
 out_put_ctx:
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 493f0f4..5d864fb 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -64,7 +64,7 @@
 #include "pnfs.h"
 #include "netns.h"
 #include "nfs4session.h"
-
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PROC
 
@@ -734,6 +734,7 @@ static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo)
 	if (!cinfo->atomic || cinfo->before != dir->i_version)
 		nfs_force_lookup_revalidate(dir);
 	dir->i_version = cinfo->after;
+	nfs_fscache_invalidate(dir);
 	spin_unlock(&dir->i_lock);
 }
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 5209916..b673be3 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1794,7 +1794,8 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
 	if (PagePrivate(page))
 		return -EBUSY;
 
-	nfs_fscache_release_page(page, GFP_KERNEL);
+	if (!nfs_fscache_release_page(page, GFP_KERNEL))
+		return -EBUSY;
 
 	return migrate_page(mapping, newpage, page, mode);
 }
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 16f35f7..6194688 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -167,7 +167,6 @@ const struct file_operations nilfs_file_operations = {
 };
 
 const struct inode_operations nilfs_file_inode_operations = {
-	.truncate	= nilfs_truncate,
 	.setattr	= nilfs_setattr,
 	.permission     = nilfs_permission,
 	.fiemap		= nilfs_fiemap,
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 4d31d2c..6b49f14 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -213,6 +213,16 @@ static int nilfs_set_page_dirty(struct page *page)
 	return ret;
 }
 
+void nilfs_write_failed(struct address_space *mapping, loff_t to)
+{
+	struct inode *inode = mapping->host;
+
+	if (to > inode->i_size) {
+		truncate_pagecache(inode, to, inode->i_size);
+		nilfs_truncate(inode);
+	}
+}
+
 static int nilfs_write_begin(struct file *file, struct address_space *mapping,
 			     loff_t pos, unsigned len, unsigned flags,
 			     struct page **pagep, void **fsdata)
@@ -227,10 +237,7 @@ static int nilfs_write_begin(struct file *file, struct address_space *mapping,
 	err = block_write_begin(mapping, pos, len, flags, pagep,
 				nilfs_get_block);
 	if (unlikely(err)) {
-		loff_t isize = mapping->host->i_size;
-		if (pos + len > isize)
-			vmtruncate(mapping->host, isize);
-
+		nilfs_write_failed(mapping, pos + len);
 		nilfs_transaction_abort(inode->i_sb);
 	}
 	return err;
@@ -259,6 +266,7 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 		loff_t offset, unsigned long nr_segs)
 {
 	struct file *file = iocb->ki_filp;
+	struct address_space *mapping = file->f_mapping;
 	struct inode *inode = file->f_mapping->host;
 	ssize_t size;
 
@@ -278,7 +286,7 @@ nilfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
 		loff_t end = offset + iov_length(iov, nr_segs);
 
 		if (end > isize)
-			vmtruncate(inode, isize);
+			nilfs_write_failed(mapping, end);
 	}
 
 	return size;
@@ -786,10 +794,8 @@ int nilfs_setattr(struct dentry *dentry, struct iattr *iattr)
 	if ((iattr->ia_valid & ATTR_SIZE) &&
 	    iattr->ia_size != i_size_read(inode)) {
 		inode_dio_wait(inode);
-
-		err = vmtruncate(inode, iattr->ia_size);
-		if (unlikely(err))
-			goto out_err;
+		truncate_setsize(inode, iattr->ia_size);
+		nilfs_truncate(inode);
 	}
 
 	setattr_copy(inode, iattr);
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 74cece8..9bc72de 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -277,6 +277,7 @@ extern void nilfs_update_inode(struct inode *, struct buffer_head *);
 extern void nilfs_truncate(struct inode *);
 extern void nilfs_evict_inode(struct inode *);
 extern int nilfs_setattr(struct dentry *, struct iattr *);
+extern void nilfs_write_failed(struct address_space *mapping, loff_t to);
 int nilfs_permission(struct inode *inode, int mask);
 int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh);
 extern int nilfs_inode_dirty(struct inode *);
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index f1626f5..ff00a0b 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -527,7 +527,8 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
 		if (unlikely(err)) {
 			loff_t isize = inode->i_size;
 			if (pos + blocksize > isize)
-				vmtruncate(inode, isize);
+				nilfs_write_failed(inode->i_mapping,
+							pos + blocksize);
 			goto failed_inode;
 		}
 
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 1ecf464..5b2d4f0 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -1762,6 +1762,16 @@ err_out:
 	return err;
 }
 
+static void ntfs_write_failed(struct address_space *mapping, loff_t to)
+{
+	struct inode *inode = mapping->host;
+
+	if (to > inode->i_size) {
+		truncate_pagecache(inode, to, inode->i_size);
+		ntfs_truncate_vfs(inode);
+	}
+}
+
 /**
  * ntfs_file_buffered_write -
  *
@@ -2022,8 +2032,9 @@ static ssize_t ntfs_file_buffered_write(struct kiocb *iocb,
 				 * allocated space, which is not a disaster.
 				 */
 				i_size = i_size_read(vi);
-				if (pos + bytes > i_size)
-					vmtruncate(vi, i_size);
+				if (pos + bytes > i_size) {
+					ntfs_write_failed(mapping, pos + bytes);
+				}
 				break;
 			}
 		}
@@ -2227,7 +2238,6 @@ const struct file_operations ntfs_file_ops = {
 
 const struct inode_operations ntfs_file_inode_ops = {
 #ifdef NTFS_RW
-	.truncate	= ntfs_truncate_vfs,
 	.setattr	= ntfs_setattr,
 #endif /* NTFS_RW */
 };
diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index 1d27331..d3e118c 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -2866,9 +2866,11 @@ conv_err_out:
  *
  * See ntfs_truncate() description above for details.
  */
+#ifdef NTFS_RW
 void ntfs_truncate_vfs(struct inode *vi) {
 	ntfs_truncate(vi);
 }
+#endif
 
 /**
  * ntfs_setattr - called from notify_change() when an attribute is being changed
@@ -2914,8 +2916,10 @@ int ntfs_setattr(struct dentry *dentry, struct iattr *attr)
 						NInoCompressed(ni) ?
 						"compressed" : "encrypted");
 				err = -EOPNOTSUPP;
-			} else
-				err = vmtruncate(vi, attr->ia_size);
+			} else {
+				truncate_setsize(vi, attr->ia_size);
+				ntfs_truncate_vfs(vi);
+			}
 			if (err || ia_valid == ATTR_SIZE)
 				goto out;
 		} else {
diff --git a/fs/ntfs/inode.h b/fs/ntfs/inode.h
index db29695..76b6cfb 100644
--- a/fs/ntfs/inode.h
+++ b/fs/ntfs/inode.h
@@ -316,6 +316,10 @@ static inline void ntfs_commit_inode(struct inode *vi)
 	return;
 }
 
+#else
+
+static inline void ntfs_truncate_vfs(struct inode *vi) {}
+
 #endif /* NTFS_RW */
 
 #endif /* _LINUX_NTFS_INODE_H */
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index fe492e1..37d313e 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1218,24 +1218,6 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 		}
 	}
 
-	/*
-	 * This will intentionally not wind up calling truncate_setsize(),
-	 * since all the work for a size change has been done above.
-	 * Otherwise, we could get into problems with truncate as
-	 * ip_alloc_sem is used there to protect against i_size
-	 * changes.
-	 *
-	 * XXX: this means the conditional below can probably be removed.
-	 */
-	if ((attr->ia_valid & ATTR_SIZE) &&
-	    attr->ia_size != i_size_read(inode)) {
-		status = vmtruncate(inode, attr->ia_size);
-		if (status) {
-			mlog_errno(status);
-			goto bail_commit;
-		}
-	}
-
 	setattr_copy(inode, attr);
 	mark_inode_dirty(inode);
 
diff --git a/fs/omfs/file.c b/fs/omfs/file.c
index 77e3cb2..e0d9b3e 100644
--- a/fs/omfs/file.c
+++ b/fs/omfs/file.c
@@ -306,6 +306,16 @@ omfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 	return mpage_writepages(mapping, wbc, omfs_get_block);
 }
 
+static void omfs_write_failed(struct address_space *mapping, loff_t to)
+{
+	struct inode *inode = mapping->host;
+
+	if (to > inode->i_size) {
+		truncate_pagecache(inode, to, inode->i_size);
+		omfs_truncate(inode);
+	}
+}
+
 static int omfs_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata)
@@ -314,11 +324,8 @@ static int omfs_write_begin(struct file *file, struct address_space *mapping,
 
 	ret = block_write_begin(mapping, pos, len, flags, pagep,
 				omfs_get_block);
-	if (unlikely(ret)) {
-		loff_t isize = mapping->host->i_size;
-		if (pos + len > isize)
-			vmtruncate(mapping->host, isize);
-	}
+	if (unlikely(ret))
+		omfs_write_failed(mapping, pos + len);
 
 	return ret;
 }
@@ -350,9 +357,11 @@ static int omfs_setattr(struct dentry *dentry, struct iattr *attr)
 
 	if ((attr->ia_valid & ATTR_SIZE) &&
 	    attr->ia_size != i_size_read(inode)) {
-		error = vmtruncate(inode, attr->ia_size);
+		error = inode_newsize_ok(inode, attr->ia_size);
 		if (error)
 			return error;
+		truncate_setsize(inode, attr->ia_size);
+		omfs_truncate(inode);
 	}
 
 	setattr_copy(inode, attr);
@@ -362,7 +371,6 @@ static int omfs_setattr(struct dentry *dentry, struct iattr *attr)
 
 const struct inode_operations omfs_file_inops = {
 	.setattr = omfs_setattr,
-	.truncate = omfs_truncate
 };
 
 const struct address_space_operations omfs_aops = {
diff --git a/fs/open.c b/fs/open.c
index 182d866..9b33c0cb 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -61,33 +61,22 @@ int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
 	return ret;
 }
 
-static long do_sys_truncate(const char __user *pathname, loff_t length)
+long vfs_truncate(struct path *path, loff_t length)
 {
-	struct path path;
 	struct inode *inode;
-	int error;
-
-	error = -EINVAL;
-	if (length < 0)	/* sorry, but loff_t says... */
-		goto out;
+	long error;
 
-	error = user_path(pathname, &path);
-	if (error)
-		goto out;
-	inode = path.dentry->d_inode;
+	inode = path->dentry->d_inode;
 
 	/* For directories it's -EISDIR, for other non-regulars - -EINVAL */
-	error = -EISDIR;
 	if (S_ISDIR(inode->i_mode))
-		goto dput_and_out;
-
-	error = -EINVAL;
+		return -EISDIR;
 	if (!S_ISREG(inode->i_mode))
-		goto dput_and_out;
+		return -EINVAL;
 
-	error = mnt_want_write(path.mnt);
+	error = mnt_want_write(path->mnt);
 	if (error)
-		goto dput_and_out;
+		goto out;
 
 	error = inode_permission(inode, MAY_WRITE);
 	if (error)
@@ -111,19 +100,40 @@ static long do_sys_truncate(const char __user *pathname, loff_t length)
 
 	error = locks_verify_truncate(inode, NULL, length);
 	if (!error)
-		error = security_path_truncate(&path);
+		error = security_path_truncate(path);
 	if (!error)
-		error = do_truncate(path.dentry, length, 0, NULL);
+		error = do_truncate(path->dentry, length, 0, NULL);
 
 put_write_and_out:
 	put_write_access(inode);
 mnt_drop_write_and_out:
-	mnt_drop_write(path.mnt);
-dput_and_out:
-	path_put(&path);
+	mnt_drop_write(path->mnt);
 out:
 	return error;
 }
+EXPORT_SYMBOL_GPL(vfs_truncate);
+
+static long do_sys_truncate(const char __user *pathname, loff_t length)
+{
+	unsigned int lookup_flags = LOOKUP_FOLLOW;
+	struct path path;
+	int error;
+
+	if (length < 0)	/* sorry, but loff_t says... */
+		return -EINVAL;
+
+retry:
+	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
+	if (!error) {
+		error = vfs_truncate(&path, length);
+		path_put(&path);
+	}
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
+	return error;
+}
 
 SYSCALL_DEFINE2(truncate, const char __user *, path, long, length)
 {
@@ -306,6 +316,7 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
 	struct path path;
 	struct inode *inode;
 	int res;
+	unsigned int lookup_flags = LOOKUP_FOLLOW;
 
 	if (mode & ~S_IRWXO)	/* where's F_OK, X_OK, W_OK, R_OK? */
 		return -EINVAL;
@@ -328,8 +339,8 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
 	}
 
 	old_cred = override_creds(override_cred);
-
-	res = user_path_at(dfd, filename, LOOKUP_FOLLOW, &path);
+retry:
+	res = user_path_at(dfd, filename, lookup_flags, &path);
 	if (res)
 		goto out;
 
@@ -364,6 +375,10 @@ SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
 
 out_path_release:
 	path_put(&path);
+	if (retry_estale(res, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 out:
 	revert_creds(old_cred);
 	put_cred(override_cred);
@@ -379,8 +394,9 @@ SYSCALL_DEFINE1(chdir, const char __user *, filename)
 {
 	struct path path;
 	int error;
-
-	error = user_path_dir(filename, &path);
+	unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
+retry:
+	error = user_path_at(AT_FDCWD, filename, lookup_flags, &path);
 	if (error)
 		goto out;
 
@@ -392,6 +408,10 @@ SYSCALL_DEFINE1(chdir, const char __user *, filename)
 
 dput_and_out:
 	path_put(&path);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 out:
 	return error;
 }
@@ -425,8 +445,9 @@ SYSCALL_DEFINE1(chroot, const char __user *, filename)
 {
 	struct path path;
 	int error;
-
-	error = user_path_dir(filename, &path);
+	unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
+retry:
+	error = user_path_at(AT_FDCWD, filename, lookup_flags, &path);
 	if (error)
 		goto out;
 
@@ -445,6 +466,10 @@ SYSCALL_DEFINE1(chroot, const char __user *, filename)
 	error = 0;
 dput_and_out:
 	path_put(&path);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 out:
 	return error;
 }
@@ -489,11 +514,16 @@ SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, umode_t, mode
 {
 	struct path path;
 	int error;
-
-	error = user_path_at(dfd, filename, LOOKUP_FOLLOW, &path);
+	unsigned int lookup_flags = LOOKUP_FOLLOW;
+retry:
+	error = user_path_at(dfd, filename, lookup_flags, &path);
 	if (!error) {
 		error = chmod_common(&path, mode);
 		path_put(&path);
+		if (retry_estale(error, lookup_flags)) {
+			lookup_flags |= LOOKUP_REVAL;
+			goto retry;
+		}
 	}
 	return error;
 }
@@ -552,6 +582,7 @@ SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user,
 	lookup_flags = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
 	if (flag & AT_EMPTY_PATH)
 		lookup_flags |= LOOKUP_EMPTY;
+retry:
 	error = user_path_at(dfd, filename, lookup_flags, &path);
 	if (error)
 		goto out;
@@ -562,6 +593,10 @@ SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user,
 	mnt_drop_write(path.mnt);
 out_release:
 	path_put(&path);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 out:
 	return error;
 }
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 5a5a0be..9b43ff77 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -542,13 +542,6 @@ int proc_setattr(struct dentry *dentry, struct iattr *attr)
 	if (error)
 		return error;
 
-	if ((attr->ia_valid & ATTR_SIZE) &&
-	    attr->ia_size != i_size_read(inode)) {
-		error = vmtruncate(inode, attr->ia_size);
-		if (error)
-			return error;
-	}
-
 	setattr_copy(inode, attr);
 	mark_inode_dirty(inode);
 	return 0;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 7b3ae3c..2e4ed13 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -261,16 +261,9 @@ static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
 	if (error)
 		return error;
 
-	if ((iattr->ia_valid & ATTR_SIZE) &&
-	    iattr->ia_size != i_size_read(inode)) {
-		error = vmtruncate(inode, iattr->ia_size);
-		if (error)
-			return error;
-	}
-
 	setattr_copy(inode, iattr);
 	mark_inode_dirty(inode);
-	
+
 	de->uid = inode->i_uid;
 	de->gid = inode->i_gid;
 	de->mode = inode->i_mode;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 701580d..1827d88 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -736,13 +736,6 @@ static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
 	if (error)
 		return error;
 
-	if ((attr->ia_valid & ATTR_SIZE) &&
-	    attr->ia_size != i_size_read(inode)) {
-		error = vmtruncate(inode, attr->ia_size);
-		if (error)
-			return error;
-	}
-
 	setattr_copy(inode, attr);
 	mark_inode_dirty(inode);
 	return 0;
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 8375c92..50302d6 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -126,7 +126,7 @@ static int reiserfs_file_open(struct inode *inode, struct file *file)
 	return err;
 }
 
-static void reiserfs_vfs_truncate_file(struct inode *inode)
+void reiserfs_vfs_truncate_file(struct inode *inode)
 {
 	mutex_lock(&(REISERFS_I(inode)->tailpack));
 	reiserfs_truncate_file(inode, 1);
@@ -312,7 +312,6 @@ const struct file_operations reiserfs_file_operations = {
 };
 
 const struct inode_operations reiserfs_file_inode_operations = {
-	.truncate = reiserfs_vfs_truncate_file,
 	.setattr = reiserfs_setattr,
 	.setxattr = reiserfs_setxattr,
 	.getxattr = reiserfs_getxattr,
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index d83736f..95d7680 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -3085,8 +3085,10 @@ static ssize_t reiserfs_direct_IO(int rw, struct kiocb *iocb,
 		loff_t isize = i_size_read(inode);
 		loff_t end = offset + iov_length(iov, nr_segs);
 
-		if (end > isize)
-			vmtruncate(inode, isize);
+		if ((end > isize) && inode_newsize_ok(inode, isize) == 0) {
+			truncate_setsize(inode, isize);
+			reiserfs_vfs_truncate_file(inode);
+		}
 	}
 
 	return ret;
@@ -3200,8 +3202,13 @@ int reiserfs_setattr(struct dentry *dentry, struct iattr *attr)
 	 */
 	reiserfs_write_unlock_once(inode->i_sb, depth);
 	if ((attr->ia_valid & ATTR_SIZE) &&
-	    attr->ia_size != i_size_read(inode))
-		error = vmtruncate(inode, attr->ia_size);
+	    attr->ia_size != i_size_read(inode)) {
+		error = inode_newsize_ok(inode, attr->ia_size);
+		if (!error) {
+			truncate_setsize(inode, attr->ia_size);
+			reiserfs_vfs_truncate_file(inode);
+		}
+	}
 
 	if (!error) {
 		setattr_copy(inode, attr);
diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h
index 33215f5..157e474 100644
--- a/fs/reiserfs/reiserfs.h
+++ b/fs/reiserfs/reiserfs.h
@@ -2455,6 +2455,7 @@ struct reiserfs_transaction_handle *reiserfs_persistent_transaction(struct
 								    *,
 								    int count);
 int reiserfs_end_persistent_transaction(struct reiserfs_transaction_handle *);
+void reiserfs_vfs_truncate_file(struct inode *inode);
 int reiserfs_commit_page(struct inode *inode, struct page *page,
 			 unsigned from, unsigned to);
 void reiserfs_flush_old_commits(struct super_block *);
diff --git a/fs/stat.c b/fs/stat.c
index eae4946..14f4545 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -74,7 +74,7 @@ int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
 {
 	struct path path;
 	int error = -EINVAL;
-	int lookup_flags = 0;
+	unsigned int lookup_flags = 0;
 
 	if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
 		      AT_EMPTY_PATH)) != 0)
@@ -84,13 +84,17 @@ int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
 		lookup_flags |= LOOKUP_FOLLOW;
 	if (flag & AT_EMPTY_PATH)
 		lookup_flags |= LOOKUP_EMPTY;
-
+retry:
 	error = user_path_at(dfd, filename, lookup_flags, &path);
 	if (error)
 		goto out;
 
 	error = vfs_getattr(path.mnt, path.dentry, stat);
 	path_put(&path);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 out:
 	return error;
 }
@@ -296,11 +300,13 @@ SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname,
 	struct path path;
 	int error;
 	int empty = 0;
+	unsigned int lookup_flags = LOOKUP_EMPTY;
 
 	if (bufsiz <= 0)
 		return -EINVAL;
 
-	error = user_path_at_empty(dfd, pathname, LOOKUP_EMPTY, &path, &empty);
+retry:
+	error = user_path_at_empty(dfd, pathname, lookup_flags, &path, &empty);
 	if (!error) {
 		struct inode *inode = path.dentry->d_inode;
 
@@ -314,6 +320,10 @@ SYSCALL_DEFINE4(readlinkat, int, dfd, const char __user *, pathname,
 			}
 		}
 		path_put(&path);
+		if (retry_estale(error, lookup_flags)) {
+			lookup_flags |= LOOKUP_REVAL;
+			goto retry;
+		}
 	}
 	return error;
 }
diff --git a/fs/statfs.c b/fs/statfs.c
index f8e832e..c219e733 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -77,10 +77,17 @@ EXPORT_SYMBOL(vfs_statfs);
 int user_statfs(const char __user *pathname, struct kstatfs *st)
 {
 	struct path path;
-	int error = user_path_at(AT_FDCWD, pathname, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
+	int error;
+	unsigned int lookup_flags = LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT;
+retry:
+	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (!error) {
 		error = vfs_statfs(&path, st);
 		path_put(&path);
+		if (retry_estale(error, lookup_flags)) {
+			lookup_flags |= LOOKUP_REVAL;
+			goto retry;
+		}
 	}
 	return error;
 }
diff --git a/fs/sysv/file.c b/fs/sysv/file.c
index 0a65939..9d4dc683 100644
--- a/fs/sysv/file.c
+++ b/fs/sysv/file.c
@@ -41,9 +41,11 @@ static int sysv_setattr(struct dentry *dentry, struct iattr *attr)
 
 	if ((attr->ia_valid & ATTR_SIZE) &&
 	    attr->ia_size != i_size_read(inode)) {
-		error = vmtruncate(inode, attr->ia_size);
+		error = inode_newsize_ok(inode, attr->ia_size);
 		if (error)
 			return error;
+		truncate_setsize(inode, attr->ia_size);
+		sysv_truncate(inode);
 	}
 
 	setattr_copy(inode, attr);
@@ -52,7 +54,6 @@ static int sysv_setattr(struct dentry *dentry, struct iattr *attr)
 }
 
 const struct inode_operations sysv_file_inode_operations = {
-	.truncate	= sysv_truncate,
 	.setattr	= sysv_setattr,
 	.getattr	= sysv_getattr,
 };
diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c
index 90b54b4..c1a591a 100644
--- a/fs/sysv/itree.c
+++ b/fs/sysv/itree.c
@@ -464,6 +464,16 @@ int sysv_prepare_chunk(struct page *page, loff_t pos, unsigned len)
 	return __block_write_begin(page, pos, len, get_block);
 }
 
+static void sysv_write_failed(struct address_space *mapping, loff_t to)
+{
+	struct inode *inode = mapping->host;
+
+	if (to > inode->i_size) {
+		truncate_pagecache(inode, to, inode->i_size);
+		sysv_truncate(inode);
+	}
+}
+
 static int sysv_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata)
@@ -471,11 +481,8 @@ static int sysv_write_begin(struct file *file, struct address_space *mapping,
 	int ret;
 
 	ret = block_write_begin(mapping, pos, len, flags, pagep, get_block);
-	if (unlikely(ret)) {
-		loff_t isize = mapping->host->i_size;
-		if (pos + len > isize)
-			vmtruncate(mapping->host, isize);
-	}
+	if (unlikely(ret))
+		sysv_write_failed(mapping, pos + len);
 
 	return ret;
 }
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index eb6d0b7..ff24e44 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -526,6 +526,14 @@ int ufs_prepare_chunk(struct page *page, loff_t pos, unsigned len)
 	return __block_write_begin(page, pos, len, ufs_getfrag_block);
 }
 
+static void ufs_write_failed(struct address_space *mapping, loff_t to)
+{
+	struct inode *inode = mapping->host;
+
+	if (to > inode->i_size)
+		truncate_pagecache(inode, to, inode->i_size);
+}
+
 static int ufs_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata)
@@ -534,11 +542,8 @@ static int ufs_write_begin(struct file *file, struct address_space *mapping,
 
 	ret = block_write_begin(mapping, pos, len, flags, pagep,
 				ufs_getfrag_block);
-	if (unlikely(ret)) {
-		loff_t isize = mapping->host->i_size;
-		if (pos + len > isize)
-			vmtruncate(mapping->host, isize);
-	}
+	if (unlikely(ret))
+		ufs_write_failed(mapping, pos + len);
 
 	return ret;
 }
diff --git a/fs/utimes.c b/fs/utimes.c
index bb0696a..f4fb7ec 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -158,13 +158,17 @@ long do_utimes(int dfd, const char __user *filename, struct timespec *times,
 
 		if (!(flags & AT_SYMLINK_NOFOLLOW))
 			lookup_flags |= LOOKUP_FOLLOW;
-
+retry:
 		error = user_path_at(dfd, filename, lookup_flags, &path);
 		if (error)
 			goto out;
 
 		error = utimes_common(&path, times);
 		path_put(&path);
+		if (retry_estale(error, lookup_flags)) {
+			lookup_flags |= LOOKUP_REVAL;
+			goto retry;
+		}
 	}
 
 out:
diff --git a/fs/xattr.c b/fs/xattr.c
index e21c119..3377dff 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -370,8 +370,9 @@ SYSCALL_DEFINE5(setxattr, const char __user *, pathname,
 {
 	struct path path;
 	int error;
-
-	error = user_path(pathname, &path);
+	unsigned int lookup_flags = LOOKUP_FOLLOW;
+retry:
+	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
 		return error;
 	error = mnt_want_write(path.mnt);
@@ -380,6 +381,10 @@ SYSCALL_DEFINE5(setxattr, const char __user *, pathname,
 		mnt_drop_write(path.mnt);
 	}
 	path_put(&path);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 	return error;
 }
 
@@ -389,8 +394,9 @@ SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname,
 {
 	struct path path;
 	int error;
-
-	error = user_lpath(pathname, &path);
+	unsigned int lookup_flags = 0;
+retry:
+	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
 		return error;
 	error = mnt_want_write(path.mnt);
@@ -399,6 +405,10 @@ SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname,
 		mnt_drop_write(path.mnt);
 	}
 	path_put(&path);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 	return error;
 }
 
@@ -476,12 +486,17 @@ SYSCALL_DEFINE4(getxattr, const char __user *, pathname,
 {
 	struct path path;
 	ssize_t error;
-
-	error = user_path(pathname, &path);
+	unsigned int lookup_flags = LOOKUP_FOLLOW;
+retry:
+	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
 		return error;
 	error = getxattr(path.dentry, name, value, size);
 	path_put(&path);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 	return error;
 }
 
@@ -490,12 +505,17 @@ SYSCALL_DEFINE4(lgetxattr, const char __user *, pathname,
 {
 	struct path path;
 	ssize_t error;
-
-	error = user_lpath(pathname, &path);
+	unsigned int lookup_flags = 0;
+retry:
+	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
 		return error;
 	error = getxattr(path.dentry, name, value, size);
 	path_put(&path);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 	return error;
 }
 
@@ -556,12 +576,17 @@ SYSCALL_DEFINE3(listxattr, const char __user *, pathname, char __user *, list,
 {
 	struct path path;
 	ssize_t error;
-
-	error = user_path(pathname, &path);
+	unsigned int lookup_flags = LOOKUP_FOLLOW;
+retry:
+	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
 		return error;
 	error = listxattr(path.dentry, list, size);
 	path_put(&path);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 	return error;
 }
 
@@ -570,12 +595,17 @@ SYSCALL_DEFINE3(llistxattr, const char __user *, pathname, char __user *, list,
 {
 	struct path path;
 	ssize_t error;
-
-	error = user_lpath(pathname, &path);
+	unsigned int lookup_flags = 0;
+retry:
+	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
 		return error;
 	error = listxattr(path.dentry, list, size);
 	path_put(&path);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 	return error;
 }
 
@@ -615,8 +645,9 @@ SYSCALL_DEFINE2(removexattr, const char __user *, pathname,
 {
 	struct path path;
 	int error;
-
-	error = user_path(pathname, &path);
+	unsigned int lookup_flags = LOOKUP_FOLLOW;
+retry:
+	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
 		return error;
 	error = mnt_want_write(path.mnt);
@@ -625,6 +656,10 @@ SYSCALL_DEFINE2(removexattr, const char __user *, pathname,
 		mnt_drop_write(path.mnt);
 	}
 	path_put(&path);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 	return error;
 }
 
@@ -633,8 +668,9 @@ SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname,
 {
 	struct path path;
 	int error;
-
-	error = user_lpath(pathname, &path);
+	unsigned int lookup_flags = 0;
+retry:
+	error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
 	if (error)
 		return error;
 	error = mnt_want_write(path.mnt);
@@ -643,6 +679,10 @@ SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname,
 		mnt_drop_write(path.mnt);
 	}
 	path_put(&path);
+	if (retry_estale(error, lookup_flags)) {
+		lookup_flags |= LOOKUP_REVAL;
+		goto retry;
+	}
 	return error;
 }