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
  ...

Documentation/filesystems/Locking

@@ -80,7 +80,6 @@ rename:		yes (all)	(see below)
 readlink:	no
 follow_link:	no
 put_link:	no
-truncate:	yes		(see below)
 setattr:	yes
 permission:	no (may not block if called in rcu-walk mode)
 get_acl:	no
@@ -96,11 +95,6 @@ atomic_open:	yes
 	Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
 victim.
 	cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
-	->truncate() is never called directly - it's a callback, not a
-method. It's called by vmtruncate() - deprecated library function used by
-->setattr(). Locking information above applies to that call (i.e. is
-inherited from ->setattr() - vmtruncate() is used when ATTR_SIZE had been
-passed).
 
 See Documentation/filesystems/directory-locking for more detailed discussion
 of the locking scheme for directory operations.

Documentation/filesystems/caching/backend-api.txt

@@ -308,6 +308,18 @@ performed on the denizens of the cache.  These are held in a structure of type:
      obtained by calling object->cookie->def->get_aux()/get_attr().
 
 
+ (*) Invalidate data object [mandatory]:
+
+	int (*invalidate_object)(struct fscache_operation *op)
+
+     This is called to invalidate a data object (as pointed to by op->object).
+     All the data stored for this object should be discarded and an
+     attr_changed operation should be performed.  The caller will follow up
+     with an object update operation.
+
+     fscache_op_complete() must be called on op before returning.
+
+
  (*) Discard object [mandatory]:
 
 	void (*drop_object)(struct fscache_object *object)
@@ -419,7 +431,10 @@ performed on the denizens of the cache.  These are held in a structure of type:
 
      If an I/O error occurs, fscache_io_error() should be called and -ENOBUFS
      returned if possible or fscache_end_io() called with a suitable error
-     code..
+     code.
+
+     fscache_put_retrieval() should be called after a page or pages are dealt
+     with.  This will complete the operation when all pages are dealt with.
 
 
  (*) Request pages be read from cache [mandatory]:
@@ -526,6 +541,27 @@ FS-Cache provides some utilities that a cache backend may make use of:
      error value should be 0 if successful and an error otherwise.
 
 
+ (*) Record that one or more pages being retrieved or allocated have been dealt
+     with:
+
+	void fscache_retrieval_complete(struct fscache_retrieval *op,
+					int n_pages);
+
+     This is called to record the fact that one or more pages have been dealt
+     with and are no longer the concern of this operation.  When the number of
+     pages remaining in the operation reaches 0, the operation will be
+     completed.
+
+
+ (*) Record operation completion:
+
+	void fscache_op_complete(struct fscache_operation *op);
+
+     This is called to record the completion of an operation.  This deducts
+     this operation from the parent object's run state, potentially permitting
+     one or more pending operations to start running.
+
+
  (*) Set highest store limit:
 
 	void fscache_set_store_limit(struct fscache_object *object,

Documentation/filesystems/caching/netfs-api.txt

@@ -35,8 +35,9 @@ This document contains the following sections:
 	(12) Index and data file update
 	(13) Miscellaneous cookie operations
 	(14) Cookie unregistration
-	(15) Index and data file invalidation
-	(16) FS-Cache specific page flags.
+	(15) Index invalidation
+	(16) Data file invalidation
+	(17) FS-Cache specific page flags.
 
 
 =============================
@@ -767,13 +768,42 @@ the cookies for "child" indices, objects and pages have been relinquished
 first.
 
 
-================================
-INDEX AND DATA FILE INVALIDATION
-================================
+==================
+INDEX INVALIDATION
+==================
 
-There is no direct way to invalidate an index subtree or a data file.  To do
-this, the caller should relinquish and retire the cookie they have, and then
-acquire a new one.
+There is no direct way to invalidate an index subtree.  To do this, the caller
+should relinquish and retire the cookie they have, and then acquire a new one.
+
+
+======================
+DATA FILE INVALIDATION
+======================
+
+Sometimes it will be necessary to invalidate an object that contains data.
+Typically this will be necessary when the server tells the netfs of a foreign
+change - at which point the netfs has to throw away all the state it had for an
+inode and reload from the server.
+
+To indicate that a cache object should be invalidated, the following function
+can be called:
+
+	void fscache_invalidate(struct fscache_cookie *cookie);
+
+This can be called with spinlocks held as it defers the work to a thread pool.
+All extant storage, retrieval and attribute change ops at this point are
+cancelled and discarded.  Some future operations will be rejected until the
+cache has had a chance to insert a barrier in the operations queue.  After
+that, operations will be queued again behind the invalidation operation.
+
+The invalidation operation will perform an attribute change operation and an
+auxiliary data update operation as it is very likely these will have changed.
+
+Using the following function, the netfs can wait for the invalidation operation
+to have reached a point at which it can start submitting ordinary operations
+once again:
+
+	void fscache_wait_on_invalidate(struct fscache_cookie *cookie);
 
 
 ===========================

Documentation/filesystems/caching/object.txt

@@ -216,7 +216,14 @@ servicing netfs requests:
      The normal running state.  In this state, requests the netfs makes will be
      passed on to the cache.
 
- (6) State FSCACHE_OBJECT_UPDATING.
+ (6) State FSCACHE_OBJECT_INVALIDATING.
+
+     The object is undergoing invalidation.  When the state comes here, it
+     discards all pending read, write and attribute change operations as it is
+     going to clear out the cache entirely and reinitialise it.  It will then
+     continue to the FSCACHE_OBJECT_UPDATING state.
+
+ (7) State FSCACHE_OBJECT_UPDATING.
 
      The state machine comes here to update the object in the cache from the
      netfs's records.  This involves updating the auxiliary data that is used
@@ -225,13 +232,13 @@ servicing netfs requests:
 And there are terminal states in which an object cleans itself up, deallocates
 memory and potentially deletes stuff from disk:
 
- (7) State FSCACHE_OBJECT_LC_DYING.
+ (8) State FSCACHE_OBJECT_LC_DYING.
 
      The object comes here if it is dying because of a lookup or creation
      error.  This would be due to a disk error or system error of some sort.
      Temporary data is cleaned up, and the parent is released.
 
- (8) State FSCACHE_OBJECT_DYING.
+ (9) State FSCACHE_OBJECT_DYING.
 
      The object comes here if it is dying due to an error, because its parent
      cookie has been relinquished by the netfs or because the cache is being
@@ -241,27 +248,27 @@ memory and potentially deletes stuff from disk:
      can destroy themselves.  This object waits for all its children to go away
      before advancing to the next state.
 
- (9) State FSCACHE_OBJECT_ABORT_INIT.
+(10) State FSCACHE_OBJECT_ABORT_INIT.
 
      The object comes to this state if it was waiting on its parent in
      FSCACHE_OBJECT_INIT, but its parent died.  The object will destroy itself
      so that the parent may proceed from the FSCACHE_OBJECT_DYING state.
 
-(10) State FSCACHE_OBJECT_RELEASING.
-(11) State FSCACHE_OBJECT_RECYCLING.
+(11) State FSCACHE_OBJECT_RELEASING.
+(12) State FSCACHE_OBJECT_RECYCLING.
 
      The object comes to one of these two states when dying once it is rid of
      all its children, if it is dying because the netfs relinquished its
      cookie.  In the first state, the cached data is expected to persist, and
      in the second it will be deleted.
 
-(12) State FSCACHE_OBJECT_WITHDRAWING.
+(13) State FSCACHE_OBJECT_WITHDRAWING.
 
      The object transits to this state if the cache decides it wants to
      withdraw the object from service, perhaps to make space, but also due to
      error or just because the whole cache is being withdrawn.
 
-(13) State FSCACHE_OBJECT_DEAD.
+(14) State FSCACHE_OBJECT_DEAD.
 
      The object transits to this state when the in-memory object record is
      ready to be deleted.  The object processor shouldn't ever see an object in

Documentation/filesystems/caching/operations.txt

@@ -174,7 +174,7 @@ Operations are used through the following procedure:
      necessary (the object might have died whilst the thread was waiting).
 
      When it has finished doing its processing, it should call
-     fscache_put_operation() on it.
+     fscache_op_complete() and fscache_put_operation() on it.
 
  (4) The operation holds an effective lock upon the object, preventing other
      exclusive ops conflicting until it is released.  The operation can be

Documentation/filesystems/porting

@@ -281,7 +281,7 @@ ext2_write_failed and callers for an example.
 
 [mandatory]
 
-	->truncate is going away.  The whole truncate sequence needs to be
+	->truncate is gone.  The whole truncate sequence needs to be
 implemented in ->setattr, which is now mandatory for filesystems
 implementing on-disk size changes.  Start with a copy of the old inode_setattr
 and vmtruncate, and the reorder the vmtruncate + foofs_vmtruncate sequence to

Documentation/filesystems/vfs.txt

@@ -350,7 +350,6 @@ struct inode_operations {
 	int (*readlink) (struct dentry *, char __user *,int);
         void * (*follow_link) (struct dentry *, struct nameidata *);
         void (*put_link) (struct dentry *, struct nameidata *, void *);
-	void (*truncate) (struct inode *);
 	int (*permission) (struct inode *, int);
 	int (*get_acl)(struct inode *, int);
 	int (*setattr) (struct dentry *, struct iattr *);
@@ -431,16 +430,6 @@ otherwise noted.
   	started might not be in the page cache at the end of the
   	walk).
 
-  truncate: Deprecated. This will not be called if ->setsize is defined.
-	Called by the VFS to change the size of a file.  The
- 	i_size field of the inode is set to the desired size by the
- 	VFS before this method is called.  This method is called by
- 	the truncate(2) system call and related functionality.
-
-	Note: ->truncate and vmtruncate are deprecated. Do not add new
-	instances/calls of these. Filesystems should be converted to do their
-	truncate sequence via ->setattr().
-
   permission: called by the VFS to check for access rights on a POSIX-like
   	filesystem.
 

arch/powerpc/platforms/cell/spufs/syscalls.c

@@ -66,7 +66,7 @@ static long do_spu_create(const char __user *pathname, unsigned int flags,
 	struct dentry *dentry;
 	int ret;
 
-	dentry = user_path_create(AT_FDCWD, pathname, &path, 1);
+	dentry = user_path_create(AT_FDCWD, pathname, &path, LOOKUP_DIRECTORY);
 	ret = PTR_ERR(dentry);
 	if (!IS_ERR(dentry)) {
 		ret = spufs_create(&path, dentry, flags, mode, neighbor);

drivers/base/devtmpfs.c

@@ -148,7 +148,7 @@ static int dev_mkdir(const char *name, umode_t mode)
 	struct path path;
 	int err;
 
-	dentry = kern_path_create(AT_FDCWD, name, &path, 1);
+	dentry = kern_path_create(AT_FDCWD, name, &path, LOOKUP_DIRECTORY);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 

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;
 }

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;
 }

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);

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;
 }

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;
 }
 

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;
@@ -440,6 +440,54 @@ truncate_failed:
 	return ret;
 }
 
+/*
+ * 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
  */
@@ -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,

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
  */

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;
 

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);

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;
 }

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;