Merge tag 'fscache-fixes-for-ceph' into wip-fscache

Patches for Ceph FS-Cache support

28 files changed, 357 insertions, 129 deletions

diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 5e376bb9341..8defc6b3f9a 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -40,7 +40,7 @@ struct inode *bfs_iget(struct super_block *sb, unsigned long ino)
 	int block, off;
 
 	inode = iget_locked(sb, ino);
-	if (IS_ERR(inode))
+	if (!inode)
 		return ERR_PTR(-ENOMEM);
 	if (!(inode->i_state & I_NEW))
 		return inode;
diff --git a/fs/bio.c b/fs/bio.c
index 94bbc04dba7..c5eae725149 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1045,12 +1045,22 @@ static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs,
 int bio_uncopy_user(struct bio *bio)
 {
 	struct bio_map_data *bmd = bio->bi_private;
-	int ret = 0;
+	struct bio_vec *bvec;
+	int ret = 0, i;
 
-	if (!bio_flagged(bio, BIO_NULL_MAPPED))
-		ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs,
-				     bmd->nr_sgvecs, bio_data_dir(bio) == READ,
-				     0, bmd->is_our_pages);
+	if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
+		/*
+		 * if we're in a workqueue, the request is orphaned, so
+		 * don't copy into a random user address space, just free.
+		 */
+		if (current->mm)
+			ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs,
+					     bmd->nr_sgvecs, bio_data_dir(bio) == READ,
+					     0, bmd->is_our_pages);
+		else if (bmd->is_our_pages)
+			bio_for_each_segment_all(bvec, bio, i)
+				__free_page(bvec->bv_page);
+	}
 	bio_free_map_data(bmd);
 	bio_put(bio);
 	return ret;
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
index d4c1206af9f..43eb5592cde 100644
--- a/fs/cachefiles/interface.c
+++ b/fs/cachefiles/interface.c
@@ -378,6 +378,31 @@ static void cachefiles_sync_cache(struct fscache_cache *_cache)
 }
 
 /*
+ * check if the backing cache is updated to FS-Cache
+ * - called by FS-Cache when evaluates if need to invalidate the cache
+ */
+static bool cachefiles_check_consistency(struct fscache_operation *op)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	const struct cred *saved_cred;
+	int ret;
+
+	_enter("{OBJ%x}", op->object->debug_id);
+
+	object = container_of(op->object, struct cachefiles_object, fscache);
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	cachefiles_begin_secure(cache, &saved_cred);
+	ret = cachefiles_check_auxdata(object);
+	cachefiles_end_secure(cache, saved_cred);
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
  * notification the attributes on an object have changed
  * - called with reads/writes excluded by FS-Cache
  */
@@ -522,4 +547,5 @@ const struct fscache_cache_ops cachefiles_cache_ops = {
 	.write_page		= cachefiles_write_page,
 	.uncache_page		= cachefiles_uncache_page,
 	.dissociate_pages	= cachefiles_dissociate_pages,
+	.check_consistency	= cachefiles_check_consistency,
 };
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index 49382519907..5349473df1b 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -235,6 +235,7 @@ extern int cachefiles_set_object_xattr(struct cachefiles_object *object,
 				       struct cachefiles_xattr *auxdata);
 extern int cachefiles_update_object_xattr(struct cachefiles_object *object,
 					  struct cachefiles_xattr *auxdata);
+extern int cachefiles_check_auxdata(struct cachefiles_object *object);
 extern int cachefiles_check_object_xattr(struct cachefiles_object *object,
 					 struct cachefiles_xattr *auxdata);
 extern int cachefiles_remove_object_xattr(struct cachefiles_cache *cache,
diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c
index 2476e516260..34c88b83e39 100644
--- a/fs/cachefiles/xattr.c
+++ b/fs/cachefiles/xattr.c
@@ -157,6 +157,42 @@ int cachefiles_update_object_xattr(struct cachefiles_object *object,
 }
 
 /*
+ * check the consistency between the backing cache and the FS-Cache cookie
+ */
+int cachefiles_check_auxdata(struct cachefiles_object *object)
+{
+	struct cachefiles_xattr *auxbuf;
+	struct dentry *dentry = object->dentry;
+	unsigned int dlen;
+	int ret;
+
+	ASSERT(dentry);
+	ASSERT(dentry->d_inode);
+	ASSERT(object->fscache.cookie->def->check_aux);
+
+	auxbuf = kmalloc(sizeof(struct cachefiles_xattr) + 512, GFP_KERNEL);
+	if (!auxbuf)
+		return -ENOMEM;
+
+	auxbuf->len = vfs_getxattr(dentry, cachefiles_xattr_cache,
+				   &auxbuf->type, 512 + 1);
+	if (auxbuf->len < 1)
+		return -ESTALE;
+
+	if (auxbuf->type != object->fscache.cookie->def->type)
+		return -ESTALE;
+
+	dlen = auxbuf->len - 1;
+	ret = fscache_check_aux(&object->fscache, &auxbuf->data, dlen);
+
+	kfree(auxbuf);
+	if (ret != FSCACHE_CHECKAUX_OKAY)
+		return -ESTALE;
+
+	return 0;
+}
+
+/*
  * check the state xattr on a cache file
  * - return -ESTALE if the object should be deleted
  */
diff --git a/fs/dcache.c b/fs/dcache.c
index 87bdb5329c3..b949af850cd 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -229,7 +229,7 @@ static void __d_free(struct rcu_head *head)
  */
 static void d_free(struct dentry *dentry)
 {
-	BUG_ON(dentry->d_count);
+	BUG_ON(dentry->d_lockref.count);
 	this_cpu_dec(nr_dentry);
 	if (dentry->d_op && dentry->d_op->d_release)
 		dentry->d_op->d_release(dentry);
@@ -467,7 +467,7 @@ relock:
 	}
 
 	if (ref)
-		dentry->d_count--;
+		dentry->d_lockref.count--;
 	/*
 	 * inform the fs via d_prune that this dentry is about to be
 	 * unhashed and destroyed.
@@ -513,15 +513,10 @@ void dput(struct dentry *dentry)
 		return;
 
 repeat:
-	if (dentry->d_count == 1)
+	if (dentry->d_lockref.count == 1)
 		might_sleep();
-	spin_lock(&dentry->d_lock);
-	BUG_ON(!dentry->d_count);
-	if (dentry->d_count > 1) {
-		dentry->d_count--;
-		spin_unlock(&dentry->d_lock);
+	if (lockref_put_or_lock(&dentry->d_lockref))
 		return;
-	}
 
 	if (dentry->d_flags & DCACHE_OP_DELETE) {
 		if (dentry->d_op->d_delete(dentry))
@@ -535,7 +530,7 @@ repeat:
 	dentry->d_flags |= DCACHE_REFERENCED;
 	dentry_lru_add(dentry);
 
-	dentry->d_count--;
+	dentry->d_lockref.count--;
 	spin_unlock(&dentry->d_lock);
 	return;
 
@@ -590,7 +585,7 @@ int d_invalidate(struct dentry * dentry)
 	 * We also need to leave mountpoints alone,
 	 * directory or not.
 	 */
-	if (dentry->d_count > 1 && dentry->d_inode) {
+	if (dentry->d_lockref.count > 1 && dentry->d_inode) {
 		if (S_ISDIR(dentry->d_inode->i_mode) || d_mountpoint(dentry)) {
 			spin_unlock(&dentry->d_lock);
 			return -EBUSY;
@@ -606,14 +601,12 @@ EXPORT_SYMBOL(d_invalidate);
 /* This must be called with d_lock held */
 static inline void __dget_dlock(struct dentry *dentry)
 {
-	dentry->d_count++;
+	dentry->d_lockref.count++;
 }
 
 static inline void __dget(struct dentry *dentry)
 {
-	spin_lock(&dentry->d_lock);
-	__dget_dlock(dentry);
-	spin_unlock(&dentry->d_lock);
+	lockref_get(&dentry->d_lockref);
 }
 
 struct dentry *dget_parent(struct dentry *dentry)
@@ -634,8 +627,8 @@ repeat:
 		goto repeat;
 	}
 	rcu_read_unlock();
-	BUG_ON(!ret->d_count);
-	ret->d_count++;
+	BUG_ON(!ret->d_lockref.count);
+	ret->d_lockref.count++;
 	spin_unlock(&ret->d_lock);
 	return ret;
 }
@@ -718,7 +711,7 @@ restart:
 	spin_lock(&inode->i_lock);
 	hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
 		spin_lock(&dentry->d_lock);
-		if (!dentry->d_count) {
+		if (!dentry->d_lockref.count) {
 			__dget_dlock(dentry);
 			__d_drop(dentry);
 			spin_unlock(&dentry->d_lock);
@@ -763,12 +756,8 @@ static void try_prune_one_dentry(struct dentry *dentry)
 	/* Prune ancestors. */
 	dentry = parent;
 	while (dentry) {
-		spin_lock(&dentry->d_lock);
-		if (dentry->d_count > 1) {
-			dentry->d_count--;
-			spin_unlock(&dentry->d_lock);
+		if (lockref_put_or_lock(&dentry->d_lockref))
 			return;
-		}
 		dentry = dentry_kill(dentry, 1);
 	}
 }
@@ -793,7 +782,7 @@ static void shrink_dentry_list(struct list_head *list)
 		 * the LRU because of laziness during lookup.  Do not free
 		 * it - just keep it off the LRU list.
 		 */
-		if (dentry->d_count) {
+		if (dentry->d_lockref.count) {
 			dentry_lru_del(dentry);
 			spin_unlock(&dentry->d_lock);
 			continue;
@@ -913,7 +902,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
 			dentry_lru_del(dentry);
 			__d_shrink(dentry);
 
-			if (dentry->d_count != 0) {
+			if (dentry->d_lockref.count != 0) {
 				printk(KERN_ERR
 				       "BUG: Dentry %p{i=%lx,n=%s}"
 				       " still in use (%d)"
@@ -922,7 +911,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
 				       dentry->d_inode ?
 				       dentry->d_inode->i_ino : 0UL,
 				       dentry->d_name.name,
-				       dentry->d_count,
+				       dentry->d_lockref.count,
 				       dentry->d_sb->s_type->name,
 				       dentry->d_sb->s_id);
 				BUG();
@@ -933,7 +922,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
 				list_del(&dentry->d_u.d_child);
 			} else {
 				parent = dentry->d_parent;
-				parent->d_count--;
+				parent->d_lockref.count--;
 				list_del(&dentry->d_u.d_child);
 			}
 
@@ -981,7 +970,7 @@ void shrink_dcache_for_umount(struct super_block *sb)
 
 	dentry = sb->s_root;
 	sb->s_root = NULL;
-	dentry->d_count--;
+	dentry->d_lockref.count--;
 	shrink_dcache_for_umount_subtree(dentry);
 
 	while (!hlist_bl_empty(&sb->s_anon)) {
@@ -1147,7 +1136,7 @@ resume:
 		 * loop in shrink_dcache_parent() might not make any progress
 		 * and loop forever.
 		 */
-		if (dentry->d_count) {
+		if (dentry->d_lockref.count) {
 			dentry_lru_del(dentry);
 		} else if (!(dentry->d_flags & DCACHE_SHRINK_LIST)) {
 			dentry_lru_move_list(dentry, dispose);
@@ -1269,7 +1258,7 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	smp_wmb();
 	dentry->d_name.name = dname;
 
-	dentry->d_count = 1;
+	dentry->d_lockref.count = 1;
 	dentry->d_flags = 0;
 	spin_lock_init(&dentry->d_lock);
 	seqcount_init(&dentry->d_seq);
@@ -1970,7 +1959,7 @@ struct dentry *__d_lookup(const struct dentry *parent, const struct qstr *name)
 				goto next;
 		}
 
-		dentry->d_count++;
+		dentry->d_lockref.count++;
 		found = dentry;
 		spin_unlock(&dentry->d_lock);
 		break;
@@ -2069,7 +2058,7 @@ again:
 	spin_lock(&dentry->d_lock);
 	inode = dentry->d_inode;
 	isdir = S_ISDIR(inode->i_mode);
-	if (dentry->d_count == 1) {
+	if (dentry->d_lockref.count == 1) {
 		if (!spin_trylock(&inode->i_lock)) {
 			spin_unlock(&dentry->d_lock);
 			cpu_relax();
@@ -2724,6 +2713,17 @@ char *dynamic_dname(struct dentry *dentry, char *buffer, int buflen,
 	return memcpy(buffer, temp, sz);
 }
 
+char *simple_dname(struct dentry *dentry, char *buffer, int buflen)
+{
+	char *end = buffer + buflen;
+	/* these dentries are never renamed, so d_lock is not needed */
+	if (prepend(&end, &buflen, " (deleted)", 11) ||
+	    prepend_name(&end, &buflen, &dentry->d_name) ||
+	    prepend(&end, &buflen, "/", 1))  
+		end = ERR_PTR(-ENAMETOOLONG);
+	return end;  
+}
+
 /*
  * Write full pathname from the root of the filesystem into the buffer.
  */
@@ -2937,7 +2937,7 @@ resume:
 		}
 		if (!(dentry->d_flags & DCACHE_GENOCIDE)) {
 			dentry->d_flags |= DCACHE_GENOCIDE;
-			dentry->d_count--;
+			dentry->d_lockref.count--;
 		}
 		spin_unlock(&dentry->d_lock);
 	}
@@ -2945,7 +2945,7 @@ resume:
 		struct dentry *child = this_parent;
 		if (!(this_parent->d_flags & DCACHE_GENOCIDE)) {
 			this_parent->d_flags |= DCACHE_GENOCIDE;
-			this_parent->d_count--;
+			this_parent->d_lockref.count--;
 		}
 		this_parent = try_to_ascend(this_parent, locked, seq);
 		if (!this_parent)
diff --git a/fs/efs/inode.c b/fs/efs/inode.c
index f3913eb2c47..d15ccf20f1b 100644
--- a/fs/efs/inode.c
+++ b/fs/efs/inode.c
@@ -57,7 +57,7 @@ struct inode *efs_iget(struct super_block *super, unsigned long ino)
 	struct inode *inode;
 
 	inode = iget_locked(super, ino);
-	if (IS_ERR(inode))
+	if (!inode)
 		return ERR_PTR(-ENOMEM);
 	if (!(inode->i_state & I_NEW))
 		return inode;
diff --git a/fs/exec.c b/fs/exec.c
index 9c73def8764..fd774c7cb48 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -608,7 +608,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
 		return -ENOMEM;
 
 	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm, 0);
+	tlb_gather_mmu(&tlb, mm, old_start, old_end);
 	if (new_end > old_start) {
 		/*
 		 * when the old and new regions overlap clear from new_end.
@@ -625,7 +625,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
 		free_pgd_range(&tlb, old_start, old_end, new_end,
 			vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING);
 	}
-	tlb_finish_mmu(&tlb, new_end, old_end);
+	tlb_finish_mmu(&tlb, old_start, old_end);
 
 	/*
 	 * Shrink the vma to just the new range.  Always succeeds.
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index b577e45425b..0ab26fbf338 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2086,6 +2086,7 @@ extern int  ext4_sync_inode(handle_t *, struct inode *);
 extern void ext4_dirty_inode(struct inode *, int);
 extern int ext4_change_inode_journal_flag(struct inode *, int);
 extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
+extern int ext4_inode_attach_jinode(struct inode *inode);
 extern int ext4_can_truncate(struct inode *inode);
 extern void ext4_truncate(struct inode *);
 extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 72a3600aedb..17ac112ab10 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -255,10 +255,10 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 	set_buffer_prio(bh);
 	if (ext4_handle_valid(handle)) {
 		err = jbd2_journal_dirty_metadata(handle, bh);
-		if (err) {
-			/* Errors can only happen if there is a bug */
-			handle->h_err = err;
-			__ext4_journal_stop(where, line, handle);
+		/* Errors can only happen if there is a bug */
+		if (WARN_ON_ONCE(err)) {
+			ext4_journal_abort_handle(where, line, __func__, bh,
+						  handle, err);
 		}
 	} else {
 		if (inode)
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 6f4cc567c38..319c9d26279 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -219,7 +219,6 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 {
 	struct super_block *sb = inode->i_sb;
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
-	struct ext4_inode_info *ei = EXT4_I(inode);
 	struct vfsmount *mnt = filp->f_path.mnt;
 	struct path path;
 	char buf[64], *cp;
@@ -259,22 +258,10 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 	 * Set up the jbd2_inode if we are opening the inode for
 	 * writing and the journal is present
 	 */
-	if (sbi->s_journal && !ei->jinode && (filp->f_mode & FMODE_WRITE)) {
-		struct jbd2_inode *jinode = jbd2_alloc_inode(GFP_KERNEL);
-
-		spin_lock(&inode->i_lock);
-		if (!ei->jinode) {
-			if (!jinode) {
-				spin_unlock(&inode->i_lock);
-				return -ENOMEM;
-			}
-			ei->jinode = jinode;
-			jbd2_journal_init_jbd_inode(ei->jinode, inode);
-			jinode = NULL;
-		}
-		spin_unlock(&inode->i_lock);
-		if (unlikely(jinode != NULL))
-			jbd2_free_inode(jinode);
+	if (filp->f_mode & FMODE_WRITE) {
+		int ret = ext4_inode_attach_jinode(inode);
+		if (ret < 0)
+			return ret;
 	}
 	return dquot_file_open(inode, filp);
 }
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index dd32a2eacd0..c2ca04e67a4 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3533,6 +3533,18 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 		   offset;
 	}
 
+	if (offset & (sb->s_blocksize - 1) ||
+	    (offset + length) & (sb->s_blocksize - 1)) {
+		/*
+		 * Attach jinode to inode for jbd2 if we do any zeroing of
+		 * partial block
+		 */
+		ret = ext4_inode_attach_jinode(inode);
+		if (ret < 0)
+			goto out_mutex;
+
+	}
+
 	first_block_offset = round_up(offset, sb->s_blocksize);
 	last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
 
@@ -3601,6 +3613,31 @@ out_mutex:
 	return ret;
 }
 
+int ext4_inode_attach_jinode(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct jbd2_inode *jinode;
+
+	if (ei->jinode || !EXT4_SB(inode->i_sb)->s_journal)
+		return 0;
+
+	jinode = jbd2_alloc_inode(GFP_KERNEL);
+	spin_lock(&inode->i_lock);
+	if (!ei->jinode) {
+		if (!jinode) {
+			spin_unlock(&inode->i_lock);
+			return -ENOMEM;
+		}
+		ei->jinode = jinode;
+		jbd2_journal_init_jbd_inode(ei->jinode, inode);
+		jinode = NULL;
+	}
+	spin_unlock(&inode->i_lock);
+	if (unlikely(jinode != NULL))
+		jbd2_free_inode(jinode);
+	return 0;
+}
+
 /*
  * ext4_truncate()
  *
@@ -3661,6 +3698,12 @@ void ext4_truncate(struct inode *inode)
 			return;
 	}
 
+	/* If we zero-out tail of the page, we have to create jinode for jbd2 */
+	if (inode->i_size & (inode->i_sb->s_blocksize - 1)) {
+		if (ext4_inode_attach_jinode(inode) < 0)
+			return;
+	}
+
 	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 		credits = ext4_writepage_trans_blocks(inode);
 	else
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 0e91a3c9fdb..318e8433527 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -558,3 +558,74 @@ void __fscache_cookie_put(struct fscache_cookie *cookie)
 
 	_leave("");
 }
+
+/*
+ * check the consistency between the netfs inode and the backing cache
+ *
+ * NOTE: it only serves no-index type
+ */
+int __fscache_check_consistency(struct fscache_cookie *cookie)
+{
+	struct fscache_operation *op;
+	struct fscache_object *object;
+	int ret;
+
+	_enter("%p,", cookie);
+
+	ASSERTCMP(cookie->def->type, ==, FSCACHE_COOKIE_TYPE_DATAFILE);
+
+	if (fscache_wait_for_deferred_lookup(cookie) < 0)
+		return -ERESTARTSYS;
+
+	if (hlist_empty(&cookie->backing_objects))
+		return 0;
+
+	op = kzalloc(sizeof(*op), GFP_NOIO | __GFP_NOMEMALLOC | __GFP_NORETRY);
+	if (!op)
+		return -ENOMEM;
+
+	fscache_operation_init(op, NULL, NULL);
+	op->flags = FSCACHE_OP_MYTHREAD |
+		(1 << FSCACHE_OP_WAITING);
+
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto inconsistent;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+	if (test_bit(FSCACHE_IOERROR, &object->cache->flags))
+		goto inconsistent;
+
+	op->debug_id = atomic_inc_return(&fscache_op_debug_id);
+
+	atomic_inc(&cookie->n_active);
+	if (fscache_submit_op(object, op) < 0)
+		goto submit_failed;
+
+	/* the work queue now carries its own ref on the object */
+	spin_unlock(&cookie->lock);
+
+	ret = fscache_wait_for_operation_activation(object, op,
+						    NULL, NULL, NULL);
+	if (ret == 0) {
+		/* ask the cache to honour the operation */
+		ret = object->cache->ops->check_consistency(op);
+		fscache_op_complete(op, false);
+	} else if (ret == -ENOBUFS) {
+		ret = 0;
+	}
+
+	fscache_put_operation(op);
+	_leave(" = %d", ret);
+	return ret;
+
+submit_failed:
+	atomic_dec(&cookie->n_active);
+inconsistent:
+	spin_unlock(&cookie->lock);
+	kfree(op);
+	_leave(" = -ESTALE");
+	return -ESTALE;
+}
+EXPORT_SYMBOL(__fscache_check_consistency);
diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
index 12d505bedb5..4226f6680b0 100644
--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -130,6 +130,12 @@ extern void fscache_operation_gc(struct work_struct *);
 /*
  * page.c
  */
+extern int fscache_wait_for_deferred_lookup(struct fscache_cookie *);
+extern int fscache_wait_for_operation_activation(struct fscache_object *,
+						 struct fscache_operation *,
+						 atomic_t *,
+						 atomic_t *,
+						 void (*)(struct fscache_operation *));
 extern void fscache_invalidate_writes(struct fscache_cookie *);
 
 /*
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index d479ab3c63e..8702b732109 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -278,7 +278,7 @@ static struct fscache_retrieval *fscache_alloc_retrieval(
 /*
  * wait for a deferred lookup to complete
  */
-static int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie)
+int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie)
 {
 	unsigned long jif;
 
@@ -322,42 +322,46 @@ static void fscache_do_cancel_retrieval(struct fscache_operation *_op)
 /*
  * wait for an object to become active (or dead)
  */
-static int fscache_wait_for_retrieval_activation(struct fscache_object *object,
-						 struct fscache_retrieval *op,
-						 atomic_t *stat_op_waits,
-						 atomic_t *stat_object_dead)
+int fscache_wait_for_operation_activation(struct fscache_object *object,
+					  struct fscache_operation *op,
+					  atomic_t *stat_op_waits,
+					  atomic_t *stat_object_dead,
+					  void (*do_cancel)(struct fscache_operation *))
 {
 	int ret;
 
-	if (!test_bit(FSCACHE_OP_WAITING, &op->op.flags))
+	if (!test_bit(FSCACHE_OP_WAITING, &op->flags))
 		goto check_if_dead;
 
 	_debug(">>> WT");
-	fscache_stat(stat_op_waits);
-	if (wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+	if (stat_op_waits)
+		fscache_stat(stat_op_waits);
+	if (wait_on_bit(&op->flags, FSCACHE_OP_WAITING,
 			fscache_wait_bit_interruptible,
 			TASK_INTERRUPTIBLE) != 0) {
-		ret = fscache_cancel_op(&op->op, fscache_do_cancel_retrieval);
+		ret = fscache_cancel_op(op, do_cancel);
 		if (ret == 0)
 			return -ERESTARTSYS;
 
 		/* it's been removed from the pending queue by another party,
 		 * so we should get to run shortly */
-		wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+		wait_on_bit(&op->flags, FSCACHE_OP_WAITING,
 			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
 	}
 	_debug("<<< GO");
 
 check_if_dead:
-	if (op->op.state == FSCACHE_OP_ST_CANCELLED) {
-		fscache_stat(stat_object_dead);
+	if (op->state == FSCACHE_OP_ST_CANCELLED) {
+		if (stat_object_dead)
+			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);
+		pr_err("%s() = -ENOBUFS [obj dead %d]\n", __func__, op->state);
+		fscache_cancel_op(op, do_cancel);
+		if (stat_object_dead)
+			fscache_stat(stat_object_dead);
 		return -ENOBUFS;
 	}
 	return 0;
@@ -432,10 +436,11 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
 
 	/* we wait for the operation to become active, and then process it
 	 * *here*, in this thread, and not in the thread pool */
-	ret = fscache_wait_for_retrieval_activation(
-		object, op,
+	ret = fscache_wait_for_operation_activation(
+		object, &op->op,
 		__fscache_stat(&fscache_n_retrieval_op_waits),
-		__fscache_stat(&fscache_n_retrievals_object_dead));
+		__fscache_stat(&fscache_n_retrievals_object_dead),
+		fscache_do_cancel_retrieval);
 	if (ret < 0)
 		goto error;
 
@@ -557,10 +562,11 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
 
 	/* we wait for the operation to become active, and then process it
 	 * *here*, in this thread, and not in the thread pool */
-	ret = fscache_wait_for_retrieval_activation(
-		object, op,
+	ret = fscache_wait_for_operation_activation(
+		object, &op->op,
 		__fscache_stat(&fscache_n_retrieval_op_waits),
-		__fscache_stat(&fscache_n_retrievals_object_dead));
+		__fscache_stat(&fscache_n_retrievals_object_dead),
+		fscache_do_cancel_retrieval);
 	if (ret < 0)
 		goto error;
 
@@ -658,10 +664,11 @@ int __fscache_alloc_page(struct fscache_cookie *cookie,
 
 	fscache_stat(&fscache_n_alloc_ops);
 
-	ret = fscache_wait_for_retrieval_activation(
-		object, op,
+	ret = fscache_wait_for_operation_activation(
+		object, &op->op,
 		__fscache_stat(&fscache_n_alloc_op_waits),
-		__fscache_stat(&fscache_n_allocs_object_dead));
+		__fscache_stat(&fscache_n_allocs_object_dead),
+		fscache_do_cancel_retrieval);
 	if (ret < 0)
 		goto error;
 
@@ -694,6 +701,22 @@ nobufs:
 EXPORT_SYMBOL(__fscache_alloc_page);
 
 /*
+ * Unmark pages allocate in the readahead code path (via:
+ * fscache_readpages_or_alloc) after delegating to the base filesystem
+ */
+void __fscache_readpages_cancel(struct fscache_cookie *cookie,
+				struct list_head *pages)
+{
+	struct page *page;
+
+	list_for_each_entry(page, pages, lru) {
+		if (PageFsCache(page))
+			__fscache_uncache_page(cookie, page);
+	}
+}
+EXPORT_SYMBOL(__fscache_readpages_cancel);
+
+/*
  * release a write op reference
  */
 static void fscache_release_write_op(struct fscache_operation *_op)
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 9435384562a..544a809819c 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1838,14 +1838,14 @@ int __init gfs2_glock_init(void)
 
 	glock_workqueue = alloc_workqueue("glock_workqueue", WQ_MEM_RECLAIM |
 					  WQ_HIGHPRI | WQ_FREEZABLE, 0);
-	if (IS_ERR(glock_workqueue))
-		return PTR_ERR(glock_workqueue);
+	if (!glock_workqueue)
+		return -ENOMEM;
 	gfs2_delete_workqueue = alloc_workqueue("delete_workqueue",
 						WQ_MEM_RECLAIM | WQ_FREEZABLE,
 						0);
-	if (IS_ERR(gfs2_delete_workqueue)) {
+	if (!gfs2_delete_workqueue) {
 		destroy_workqueue(glock_workqueue);
-		return PTR_ERR(gfs2_delete_workqueue);
+		return -ENOMEM;
 	}
 
 	register_shrinker(&glock_shrinker);
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 5f2e5224c51..e2e0a90396e 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -47,7 +47,8 @@ static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh)
  * None of the buffers should be dirty, locked, or pinned.
  */
 
-static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
+static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync,
+			     unsigned int nr_revokes)
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
 	struct list_head *head = &gl->gl_ail_list;
@@ -57,7 +58,9 @@ static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
 
 	gfs2_log_lock(sdp);
 	spin_lock(&sdp->sd_ail_lock);
-	list_for_each_entry_safe(bd, tmp, head, bd_ail_gl_list) {
+	list_for_each_entry_safe_reverse(bd, tmp, head, bd_ail_gl_list) {
+		if (nr_revokes == 0)
+			break;
 		bh = bd->bd_bh;
 		if (bh->b_state & b_state) {
 			if (fsync)
@@ -65,6 +68,7 @@ static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
 			gfs2_ail_error(gl, bh);
 		}
 		gfs2_trans_add_revoke(sdp, bd);
+		nr_revokes--;
 	}
 	GLOCK_BUG_ON(gl, !fsync && atomic_read(&gl->gl_ail_count));
 	spin_unlock(&sdp->sd_ail_lock);
@@ -91,7 +95,7 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 	WARN_ON_ONCE(current->journal_info);
 	current->journal_info = &tr;
 
-	__gfs2_ail_flush(gl, 0);
+	__gfs2_ail_flush(gl, 0, tr.tr_revokes);
 
 	gfs2_trans_end(sdp);
 	gfs2_log_flush(sdp, NULL);
@@ -101,15 +105,19 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
 	unsigned int revokes = atomic_read(&gl->gl_ail_count);
+	unsigned int max_revokes = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / sizeof(u64);
 	int ret;
 
 	if (!revokes)
 		return;
 
-	ret = gfs2_trans_begin(sdp, 0, revokes);
+	while (revokes > max_revokes)
+		max_revokes += (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header)) / sizeof(u64);
+
+	ret = gfs2_trans_begin(sdp, 0, max_revokes);
 	if (ret)
 		return;
-	__gfs2_ail_flush(gl, fsync);
+	__gfs2_ail_flush(gl, fsync, max_revokes);
 	gfs2_trans_end(sdp);
 	gfs2_log_flush(sdp, NULL);
 }
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index bbb2715171c..64915eeae5a 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -594,7 +594,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 		}
 		gfs2_glock_dq_uninit(ghs);
 		if (IS_ERR(d))
-			return PTR_RET(d);
+			return PTR_ERR(d);
 		return error;
 	} else if (error != -ENOENT) {
 		goto fail_gunlock;
@@ -1750,6 +1750,10 @@ static ssize_t gfs2_getxattr(struct dentry *dentry, const char *name,
 	struct gfs2_holder gh;
 	int ret;
 
+	/* For selinux during lookup */
+	if (gfs2_glock_is_locked_by_me(ip->i_gl))
+		return generic_getxattr(dentry, name, data, size);
+
 	gfs2_holder_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
 	ret = gfs2_glock_nq(&gh);
 	if (ret == 0) {
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index e04d0e09ee7..7b0f5043cf2 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -155,7 +155,7 @@ static int __init init_gfs2_fs(void)
 		goto fail_wq;
 
 	gfs2_control_wq = alloc_workqueue("gfs2_control",
-			       WQ_NON_REENTRANT | WQ_UNBOUND | WQ_FREEZABLE, 0);
+					  WQ_UNBOUND | WQ_FREEZABLE, 0);
 	if (!gfs2_control_wq)
 		goto fail_recovery;
 
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 34423978b17..d19b30ababf 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -926,14 +926,8 @@ static int get_hstate_idx(int page_size_log)
 	return h - hstates;
 }
 
-static char *hugetlb_dname(struct dentry *dentry, char *buffer, int buflen)
-{
-	return dynamic_dname(dentry, buffer, buflen, "/%s (deleted)",
-				dentry->d_name.name);
-}
-
 static struct dentry_operations anon_ops = {
-	.d_dname = hugetlb_dname
+	.d_dname = simple_dname
 };
 
 /*
diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c
index 8743ba9c674..984c2bbf4f6 100644
--- a/fs/jfs/jfs_dtree.c
+++ b/fs/jfs/jfs_dtree.c
@@ -3047,6 +3047,14 @@ int jfs_readdir(struct file *file, struct dir_context *ctx)
 
 		dir_index = (u32) ctx->pos;
 
+		/*
+		 * NFSv4 reserves cookies 1 and 2 for . and .. so the value
+		 * we return to the vfs is one greater than the one we use
+		 * internally.
+		 */
+		if (dir_index)
+			dir_index--;
+
 		if (dir_index > 1) {
 			struct dir_table_slot dirtab_slot;
 
@@ -3086,7 +3094,7 @@ int jfs_readdir(struct file *file, struct dir_context *ctx)
 			if (p->header.flag & BT_INTERNAL) {
 				jfs_err("jfs_readdir: bad index table");
 				DT_PUTPAGE(mp);
-				ctx->pos = -1;
+				ctx->pos = DIREND;
 				return 0;
 			}
 		} else {
@@ -3094,14 +3102,14 @@ int jfs_readdir(struct file *file, struct dir_context *ctx)
 				/*
 				 * self "."
 				 */
-				ctx->pos = 0;
+				ctx->pos = 1;
 				if (!dir_emit(ctx, ".", 1, ip->i_ino, DT_DIR))
 					return 0;
 			}
 			/*
 			 * parent ".."
 			 */
-			ctx->pos = 1;
+			ctx->pos = 2;
 			if (!dir_emit(ctx, "..", 2, PARENT(ip), DT_DIR))
 				return 0;
 
@@ -3122,22 +3130,23 @@ int jfs_readdir(struct file *file, struct dir_context *ctx)
 		/*
 		 * Legacy filesystem - OS/2 & Linux JFS < 0.3.6
 		 *
-		 * pn = index = 0:	First entry "."
-		 * pn = 0; index = 1:	Second entry ".."
+		 * pn = 0; index = 1:	First entry "."
+		 * pn = 0; index = 2:	Second entry ".."
 		 * pn > 0:		Real entries, pn=1 -> leftmost page
 		 * pn = index = -1:	No more entries
 		 */
 		dtpos = ctx->pos;
-		if (dtpos == 0) {
+		if (dtpos < 2) {
 			/* build "." entry */
+			ctx->pos = 1;
 			if (!dir_emit(ctx, ".", 1, ip->i_ino, DT_DIR))
 				return 0;
-			dtoffset->index = 1;
+			dtoffset->index = 2;
 			ctx->pos = dtpos;
 		}
 
 		if (dtoffset->pn == 0) {
-			if (dtoffset->index == 1) {
+			if (dtoffset->index == 2) {
 				/* build ".." entry */
 				if (!dir_emit(ctx, "..", 2, PARENT(ip), DT_DIR))
 					return 0;
@@ -3228,6 +3237,12 @@ int jfs_readdir(struct file *file, struct dir_context *ctx)
 					}
 					jfs_dirent->position = unique_pos++;
 				}
+				/*
+				 * We add 1 to the index because we may
+				 * use a value of 2 internally, and NFSv4
+				 * doesn't like that.
+				 */
+				jfs_dirent->position++;
 			} else {
 				jfs_dirent->position = dtpos;
 				len = min(d_namleft, DTLHDRDATALEN_LEGACY);
diff --git a/fs/namei.c b/fs/namei.c
index 89a612e392e..7720fbd5277 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -536,8 +536,8 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
 		 * a reference at this point.
 		 */
 		BUG_ON(!IS_ROOT(dentry) && dentry->d_parent != parent);
-		BUG_ON(!parent->d_count);
-		parent->d_count++;
+		BUG_ON(!parent->d_lockref.count);
+		parent->d_lockref.count++;
 		spin_unlock(&dentry->d_lock);
 	}
 	spin_unlock(&parent->d_lock);
@@ -3327,7 +3327,7 @@ void dentry_unhash(struct dentry *dentry)
 {
 	shrink_dcache_parent(dentry);
 	spin_lock(&dentry->d_lock);
-	if (dentry->d_count == 1)
+	if (dentry->d_lockref.count == 1)
 		__d_drop(dentry);
 	spin_unlock(&dentry->d_lock);
 }
@@ -3671,11 +3671,15 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
 	if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
 		return -EINVAL;
 	/*
-	 * Using empty names is equivalent to using AT_SYMLINK_FOLLOW
-	 * on /proc/self/fd/<fd>.
+	 * To use null names we require CAP_DAC_READ_SEARCH
+	 * This ensures that not everyone will be able to create
+	 * handlink using the passed filedescriptor.
 	 */
-	if (flags & AT_EMPTY_PATH)
+	if (flags & AT_EMPTY_PATH) {
+		if (!capable(CAP_DAC_READ_SEARCH))
+			return -ENOENT;
 		how = LOOKUP_EMPTY;
+	}
 
 	if (flags & AT_SYMLINK_FOLLOW)
 		how |= LOOKUP_FOLLOW;
diff --git a/fs/namespace.c b/fs/namespace.c
index 7b1ca9ba0b0..a45ba4f267f 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1429,7 +1429,7 @@ struct vfsmount *collect_mounts(struct path *path)
 			 CL_COPY_ALL | CL_PRIVATE);
 	namespace_unlock();
 	if (IS_ERR(tree))
-		return NULL;
+		return ERR_CAST(tree);
 	return &tree->mnt;
 }
 
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index dc9a913784a..2d8be51f90d 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -345,8 +345,7 @@ static void nilfs_end_bio_write(struct bio *bio, int err)
 
 	if (err == -EOPNOTSUPP) {
 		set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
-		bio_put(bio);
-		/* to be detected by submit_seg_bio() */
+		/* to be detected by nilfs_segbuf_submit_bio() */
 	}
 
 	if (!uptodate)
@@ -377,12 +376,12 @@ static int nilfs_segbuf_submit_bio(struct nilfs_segment_buffer *segbuf,
 	bio->bi_private = segbuf;
 	bio_get(bio);
 	submit_bio(mode, bio);
+	segbuf->sb_nbio++;
 	if (bio_flagged(bio, BIO_EOPNOTSUPP)) {
 		bio_put(bio);
 		err = -EOPNOTSUPP;
 		goto failed;
 	}
-	segbuf->sb_nbio++;
 	bio_put(bio);
 
 	wi->bio = NULL;
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 854d80955bf..121da2dc3be 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1022,7 +1022,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 	struct inode *inode = NULL;
 	struct ocfs2_super *osb = NULL;
 	struct buffer_head *bh = NULL;
-	char nodestr[8];
+	char nodestr[12];
 	struct ocfs2_blockcheck_stats stats;
 
 	trace_ocfs2_fill_super(sb, data, silent);
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 75f2890abbd..0ff80f9b930 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -230,8 +230,6 @@ static int proc_readfd_common(struct file *file, struct dir_context *ctx,
 
 	if (!dir_emit_dots(file, ctx))
 		goto out;
-	if (!dir_emit_dots(file, ctx))
-		goto out;
 	files = get_files_struct(p);
 	if (!files)
 		goto out;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 94441a40733..737e15615b0 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -271,7 +271,7 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
 		de = next;
 	} while (de);
 	spin_unlock(&proc_subdir_lock);
-	return 0;
+	return 1;
 }
 
 int proc_readdir(struct file *file, struct dir_context *ctx)
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 229e366598d..e0a790da726 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -205,7 +205,9 @@ static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentr
 static int proc_root_readdir(struct file *file, struct dir_context *ctx)
 {
 	if (ctx->pos < FIRST_PROCESS_ENTRY) {
-		proc_readdir(file, ctx);
+		int error = proc_readdir(file, ctx);
+		if (unlikely(error <= 0))
+			return error;
 		ctx->pos = FIRST_PROCESS_ENTRY;
 	}