Merge branch 'for-linus' of...

Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs into for-linus

Documentation/filesystems/btrfs.txt

@@ -63,8 +63,8 @@ IRC network.
 Userspace tools for creating and manipulating Btrfs file systems are
 available from the git repository at the following location:
 
- http://git.kernel.org/?p=linux/kernel/git/mason/btrfs-progs-unstable.git
- git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-progs-unstable.git
+ http://git.kernel.org/?p=linux/kernel/git/mason/btrfs-progs.git
+ git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-progs.git
 
 These include the following tools:
 

fs/btrfs/Makefile

@@ -7,6 +7,7 @@ btrfs-y += super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \
 	   extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
 	   export.o tree-log.o free-space-cache.o zlib.o lzo.o \
-	   compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o
+	   compression.o delayed-ref.o relocation.o delayed-inode.o scrub.o \
+	   reada.o backref.o
 
 btrfs-$(CONFIG_BTRFS_FS_POSIX_ACL) += acl.o

fs/btrfs/acl.c

@@ -59,22 +59,19 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
 		if (!value)
 			return ERR_PTR(-ENOMEM);
 		size = __btrfs_getxattr(inode, name, value, size);
-		if (size > 0) {
-			acl = posix_acl_from_xattr(value, size);
-			if (IS_ERR(acl)) {
-				kfree(value);
-				return acl;
-			}
-			set_cached_acl(inode, type, acl);
-		}
-		kfree(value);
+	}
+	if (size > 0) {
+		acl = posix_acl_from_xattr(value, size);
 	} else if (size == -ENOENT || size == -ENODATA || size == 0) {
 		/* FIXME, who returns -ENOENT?  I think nobody */
 		acl = NULL;
-		set_cached_acl(inode, type, acl);
 	} else {
 		acl = ERR_PTR(-EIO);
 	}
+	kfree(value);
+
+	if (!IS_ERR(acl))
+		set_cached_acl(inode, type, acl);
 
 	return acl;
 }

fs/btrfs/async-thread.c

@@ -64,6 +64,8 @@ struct btrfs_worker_thread {
 	int idle;
 };
 
+static int __btrfs_start_workers(struct btrfs_workers *workers);
+
 /*
  * btrfs_start_workers uses kthread_run, which can block waiting for memory
  * for a very long time.  It will actually throttle on page writeback,
@@ -88,27 +90,10 @@ static void start_new_worker_func(struct btrfs_work *work)
 {
 	struct worker_start *start;
 	start = container_of(work, struct worker_start, work);
-	btrfs_start_workers(start->queue, 1);
+	__btrfs_start_workers(start->queue);
 	kfree(start);
 }
 
-static int start_new_worker(struct btrfs_workers *queue)
-{
-	struct worker_start *start;
-	int ret;
-
-	start = kzalloc(sizeof(*start), GFP_NOFS);
-	if (!start)
-		return -ENOMEM;
-
-	start->work.func = start_new_worker_func;
-	start->queue = queue;
-	ret = btrfs_queue_worker(queue->atomic_worker_start, &start->work);
-	if (ret)
-		kfree(start);
-	return ret;
-}
-
 /*
  * helper function to move a thread onto the idle list after it
  * has finished some requests.
@@ -153,12 +138,20 @@ static void check_busy_worker(struct btrfs_worker_thread *worker)
 static void check_pending_worker_creates(struct btrfs_worker_thread *worker)
 {
 	struct btrfs_workers *workers = worker->workers;
+	struct worker_start *start;
 	unsigned long flags;
 
 	rmb();
 	if (!workers->atomic_start_pending)
 		return;
 
+	start = kzalloc(sizeof(*start), GFP_NOFS);
+	if (!start)
+		return;
+
+	start->work.func = start_new_worker_func;
+	start->queue = workers;
+
 	spin_lock_irqsave(&workers->lock, flags);
 	if (!workers->atomic_start_pending)
 		goto out;
@@ -170,10 +163,11 @@ static void check_pending_worker_creates(struct btrfs_worker_thread *worker)
 
 	workers->num_workers_starting += 1;
 	spin_unlock_irqrestore(&workers->lock, flags);
-	start_new_worker(workers);
+	btrfs_queue_worker(workers->atomic_worker_start, &start->work);
 	return;
 
 out:
+	kfree(start);
 	spin_unlock_irqrestore(&workers->lock, flags);
 }
 
@@ -331,7 +325,7 @@ static int worker_loop(void *arg)
 			run_ordered_completions(worker->workers, work);
 
 			check_pending_worker_creates(worker);
-
+			cond_resched();
 		}
 
 		spin_lock_irq(&worker->lock);
@@ -462,56 +456,55 @@ void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
  * starts new worker threads.  This does not enforce the max worker
  * count in case you need to temporarily go past it.
  */
-static int __btrfs_start_workers(struct btrfs_workers *workers,
-				 int num_workers)
+static int __btrfs_start_workers(struct btrfs_workers *workers)
 {
 	struct btrfs_worker_thread *worker;
 	int ret = 0;
-	int i;
 
-	for (i = 0; i < num_workers; i++) {
-		worker = kzalloc(sizeof(*worker), GFP_NOFS);
-		if (!worker) {
-			ret = -ENOMEM;
-			goto fail;
-		}
+	worker = kzalloc(sizeof(*worker), GFP_NOFS);
+	if (!worker) {
+		ret = -ENOMEM;
+		goto fail;
+	}
 
-		INIT_LIST_HEAD(&worker->pending);
-		INIT_LIST_HEAD(&worker->prio_pending);
-		INIT_LIST_HEAD(&worker->worker_list);
-		spin_lock_init(&worker->lock);
-
-		atomic_set(&worker->num_pending, 0);
-		atomic_set(&worker->refs, 1);
-		worker->workers = workers;
-		worker->task = kthread_run(worker_loop, worker,
-					   "btrfs-%s-%d", workers->name,
-					   workers->num_workers + i);
-		if (IS_ERR(worker->task)) {
-			ret = PTR_ERR(worker->task);
-			kfree(worker);
-			goto fail;
-		}
-		spin_lock_irq(&workers->lock);
-		list_add_tail(&worker->worker_list, &workers->idle_list);
-		worker->idle = 1;
-		workers->num_workers++;
-		workers->num_workers_starting--;
-		WARN_ON(workers->num_workers_starting < 0);
-		spin_unlock_irq(&workers->lock);
+	INIT_LIST_HEAD(&worker->pending);
+	INIT_LIST_HEAD(&worker->prio_pending);
+	INIT_LIST_HEAD(&worker->worker_list);
+	spin_lock_init(&worker->lock);
+
+	atomic_set(&worker->num_pending, 0);
+	atomic_set(&worker->refs, 1);
+	worker->workers = workers;
+	worker->task = kthread_run(worker_loop, worker,
+				   "btrfs-%s-%d", workers->name,
+				   workers->num_workers + 1);
+	if (IS_ERR(worker->task)) {
+		ret = PTR_ERR(worker->task);
+		kfree(worker);
+		goto fail;
 	}
+	spin_lock_irq(&workers->lock);
+	list_add_tail(&worker->worker_list, &workers->idle_list);
+	worker->idle = 1;
+	workers->num_workers++;
+	workers->num_workers_starting--;
+	WARN_ON(workers->num_workers_starting < 0);
+	spin_unlock_irq(&workers->lock);
+
 	return 0;
 fail:
-	btrfs_stop_workers(workers);
+	spin_lock_irq(&workers->lock);
+	workers->num_workers_starting--;
+	spin_unlock_irq(&workers->lock);
 	return ret;
 }
 
-int btrfs_start_workers(struct btrfs_workers *workers, int num_workers)
+int btrfs_start_workers(struct btrfs_workers *workers)
 {
 	spin_lock_irq(&workers->lock);
-	workers->num_workers_starting += num_workers;
+	workers->num_workers_starting++;
 	spin_unlock_irq(&workers->lock);
-	return __btrfs_start_workers(workers, num_workers);
+	return __btrfs_start_workers(workers);
 }
 
 /*
@@ -568,9 +561,10 @@ static struct btrfs_worker_thread *find_worker(struct btrfs_workers *workers)
 	struct btrfs_worker_thread *worker;
 	unsigned long flags;
 	struct list_head *fallback;
+	int ret;
 
-again:
 	spin_lock_irqsave(&workers->lock, flags);
+again:
 	worker = next_worker(workers);
 
 	if (!worker) {
@@ -584,7 +578,10 @@ static struct btrfs_worker_thread *find_worker(struct btrfs_workers *workers)
 			workers->num_workers_starting++;
 			spin_unlock_irqrestore(&workers->lock, flags);
 			/* we're below the limit, start another worker */
-			__btrfs_start_workers(workers, 1);
+			ret = __btrfs_start_workers(workers);
+			spin_lock_irqsave(&workers->lock, flags);
+			if (ret)
+				goto fallback;
 			goto again;
 		}
 	}
@@ -665,7 +662,7 @@ void btrfs_set_work_high_prio(struct btrfs_work *work)
 /*
  * places a struct btrfs_work into the pending queue of one of the kthreads
  */
-int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
+void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
 {
 	struct btrfs_worker_thread *worker;
 	unsigned long flags;
@@ -673,7 +670,7 @@ int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
 
 	/* don't requeue something already on a list */
 	if (test_and_set_bit(WORK_QUEUED_BIT, &work->flags))
-		goto out;
+		return;
 
 	worker = find_worker(workers);
 	if (workers->ordered) {
@@ -712,7 +709,4 @@ int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work)
 	if (wake)
 		wake_up_process(worker->task);
 	spin_unlock_irqrestore(&worker->lock, flags);
-
-out:
-	return 0;
 }

fs/btrfs/async-thread.h

@@ -109,8 +109,8 @@ struct btrfs_workers {
 	char *name;
 };
 
-int btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
-int btrfs_start_workers(struct btrfs_workers *workers, int num_workers);
+void btrfs_queue_worker(struct btrfs_workers *workers, struct btrfs_work *work);
+int btrfs_start_workers(struct btrfs_workers *workers);
 int btrfs_stop_workers(struct btrfs_workers *workers);
 void btrfs_init_workers(struct btrfs_workers *workers, char *name, int max,
 			struct btrfs_workers *async_starter);

fs/btrfs/backref.h

+/*
+ * Copyright (C) 2011 STRATO.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#ifndef __BTRFS_BACKREF__
+#define __BTRFS_BACKREF__
+
+#include "ioctl.h"
+
+struct inode_fs_paths {
+	struct btrfs_path		*btrfs_path;
+	struct btrfs_root		*fs_root;
+	struct btrfs_data_container	*fspath;
+};
+
+typedef int (iterate_extent_inodes_t)(u64 inum, u64 offset, u64 root,
+		void *ctx);
+typedef int (iterate_irefs_t)(u64 parent, struct btrfs_inode_ref *iref,
+				struct extent_buffer *eb, void *ctx);
+
+int inode_item_info(u64 inum, u64 ioff, struct btrfs_root *fs_root,
+			struct btrfs_path *path);
+
+int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical,
+			struct btrfs_path *path, struct btrfs_key *found_key);
+
+int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
+				struct btrfs_extent_item *ei, u32 item_size,
+				u64 *out_root, u8 *out_level);
+
+int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
+				struct btrfs_path *path,
+				u64 extent_item_objectid,
+				u64 extent_offset,
+				iterate_extent_inodes_t *iterate, void *ctx);
+
+int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info,
+				struct btrfs_path *path,
+				iterate_extent_inodes_t *iterate, void *ctx);
+
+int paths_from_inode(u64 inum, struct inode_fs_paths *ipath);
+
+struct btrfs_data_container *init_data_container(u32 total_bytes);
+struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root,
+					struct btrfs_path *path);
+void free_ipath(struct inode_fs_paths *ipath);
+
+#endif

fs/btrfs/btrfs_inode.h

@@ -103,11 +103,6 @@ struct btrfs_inode {
 	 */
 	u64 delalloc_bytes;
 
-	/* total number of bytes that may be used for this inode for
-	 * delalloc
-	 */
-	u64 reserved_bytes;
-
 	/*
 	 * the size of the file stored in the metadata on disk.  data=ordered
 	 * means the in-memory i_size might be larger than the size on disk
@@ -115,9 +110,6 @@ struct btrfs_inode {
 	 */
 	u64 disk_i_size;
 
-	/* flags field from the on disk inode */
-	u32 flags;
-
 	/*
 	 * if this is a directory then index_cnt is the counter for the index
 	 * number for new files that are created
@@ -131,6 +123,15 @@ struct btrfs_inode {
 	 */
 	u64 last_unlink_trans;
 
+	/*
+	 * Number of bytes outstanding that are going to need csums.  This is
+	 * used in ENOSPC accounting.
+	 */
+	u64 csum_bytes;
+
+	/* flags field from the on disk inode */
+	u32 flags;
+
 	/*
 	 * Counters to keep track of the number of extent item's we may use due
 	 * to delalloc and such.  outstanding_extents is the number of extent
@@ -146,14 +147,12 @@ struct btrfs_inode {
 	 * the btrfs file release call will add this inode to the
 	 * ordered operations list so that we make sure to flush out any
 	 * new data the application may have written before commit.
-	 *
-	 * yes, its silly to have a single bitflag, but we might grow more
-	 * of these.
 	 */
 	unsigned ordered_data_close:1;
 	unsigned orphan_meta_reserved:1;
 	unsigned dummy_inode:1;
 	unsigned in_defrag:1;
+	unsigned delalloc_meta_reserved:1;
 
 	/*
 	 * always compress this one file

fs/btrfs/compression.c

@@ -85,7 +85,8 @@ struct compressed_bio {
 static inline int compressed_bio_size(struct btrfs_root *root,
 				      unsigned long disk_size)
 {
-	u16 csum_size = btrfs_super_csum_size(&root->fs_info->super_copy);
+	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
+
 	return sizeof(struct compressed_bio) +
 		((disk_size + root->sectorsize - 1) / root->sectorsize) *
 		csum_size;

fs/btrfs/ctree.c

@@ -514,10 +514,25 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans,
 				   struct btrfs_root *root,
 				   struct extent_buffer *buf)
 {
+	/* ensure we can see the force_cow */
+	smp_rmb();
+
+	/*
+	 * We do not need to cow a block if
+	 * 1) this block is not created or changed in this transaction;
+	 * 2) this block does not belong to TREE_RELOC tree;
+	 * 3) the root is not forced COW.
+	 *
+	 * What is forced COW:
+	 *    when we create snapshot during commiting the transaction,
+	 *    after we've finished coping src root, we must COW the shared
+	 *    block to ensure the metadata consistency.
+	 */
 	if (btrfs_header_generation(buf) == trans->transid &&
 	    !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN) &&
 	    !(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID &&
-	      btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)))
+	      btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)) &&
+	    !root->force_cow)
 		return 0;
 	return 1;
 }
@@ -902,9 +917,10 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 
 	orig_ptr = btrfs_node_blockptr(mid, orig_slot);
 
-	if (level < BTRFS_MAX_LEVEL - 1)
+	if (level < BTRFS_MAX_LEVEL - 1) {
 		parent = path->nodes[level + 1];
-	pslot = path->slots[level + 1];
+		pslot = path->slots[level + 1];
+	}
 
 	/*
 	 * deal with the case where there is only one pointer in the root
@@ -1107,9 +1123,10 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans,
 	mid = path->nodes[level];
 	WARN_ON(btrfs_header_generation(mid) != trans->transid);
 
-	if (level < BTRFS_MAX_LEVEL - 1)
+	if (level < BTRFS_MAX_LEVEL - 1) {
 		parent = path->nodes[level + 1];
-	pslot = path->slots[level + 1];
+		pslot = path->slots[level + 1];
+	}
 
 	if (!parent)
 		return 1;

fs/btrfs/delayed-inode.c

@@ -591,7 +591,7 @@ static int btrfs_delayed_item_reserve_metadata(struct btrfs_trans_handle *trans,
 		return 0;
 
 	src_rsv = trans->block_rsv;
-	dst_rsv = &root->fs_info->global_block_rsv;
+	dst_rsv = &root->fs_info->delayed_block_rsv;
 
 	num_bytes = btrfs_calc_trans_metadata_size(root, 1);
 	ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes);
@@ -609,7 +609,7 @@ static void btrfs_delayed_item_release_metadata(struct btrfs_root *root,
 	if (!item->bytes_reserved)
 		return;
 
-	rsv = &root->fs_info->global_block_rsv;
+	rsv = &root->fs_info->delayed_block_rsv;
 	btrfs_block_rsv_release(root, rsv,
 				item->bytes_reserved);
 }
@@ -617,24 +617,102 @@ static void btrfs_delayed_item_release_metadata(struct btrfs_root *root,
 static int btrfs_delayed_inode_reserve_metadata(
 					struct btrfs_trans_handle *trans,
 					struct btrfs_root *root,
+					struct inode *inode,
 					struct btrfs_delayed_node *node)
 {
 	struct btrfs_block_rsv *src_rsv;
 	struct btrfs_block_rsv *dst_rsv;
 	u64 num_bytes;
 	int ret;
-
-	if (!trans->bytes_reserved)
-		return 0;
+	int release = false;
 
 	src_rsv = trans->block_rsv;
-	dst_rsv = &root->fs_info->global_block_rsv;
+	dst_rsv = &root->fs_info->delayed_block_rsv;
 
 	num_bytes = btrfs_calc_trans_metadata_size(root, 1);
+
+	/*
+	 * btrfs_dirty_inode will update the inode under btrfs_join_transaction
+	 * which doesn't reserve space for speed.  This is a problem since we
+	 * still need to reserve space for this update, so try to reserve the
+	 * space.
+	 *
+	 * Now if src_rsv == delalloc_block_rsv we'll let it just steal since
+	 * we're accounted for.
+	 */
+	if (!src_rsv || (!trans->bytes_reserved &&
+	    src_rsv != &root->fs_info->delalloc_block_rsv)) {
+		ret = btrfs_block_rsv_add_noflush(root, dst_rsv, num_bytes);
+		/*
+		 * Since we're under a transaction reserve_metadata_bytes could
+		 * try to commit the transaction which will make it return
+		 * EAGAIN to make us stop the transaction we have, so return
+		 * ENOSPC instead so that btrfs_dirty_inode knows what to do.
+		 */
+		if (ret == -EAGAIN)
+			ret = -ENOSPC;
+		if (!ret)
+			node->bytes_reserved = num_bytes;
+		return ret;
+	} else if (src_rsv == &root->fs_info->delalloc_block_rsv) {
+		spin_lock(&BTRFS_I(inode)->lock);
+		if (BTRFS_I(inode)->delalloc_meta_reserved) {
+			BTRFS_I(inode)->delalloc_meta_reserved = 0;
+			spin_unlock(&BTRFS_I(inode)->lock);
+			release = true;
+			goto migrate;
+		}
+		spin_unlock(&BTRFS_I(inode)->lock);
+
+		/* Ok we didn't have space pre-reserved.  This shouldn't happen
+		 * too often but it can happen if we do delalloc to an existing
+		 * inode which gets dirtied because of the time update, and then
+		 * isn't touched again until after the transaction commits and
+		 * then we try to write out the data.  First try to be nice and
+		 * reserve something strictly for us.  If not be a pain and try
+		 * to steal from the delalloc block rsv.
+		 */
+		ret = btrfs_block_rsv_add_noflush(root, dst_rsv, num_bytes);
+		if (!ret)
+			goto out;
+
+		ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes);
+		if (!ret)
+			goto out;
+
+		/*
+		 * Ok this is a problem, let's just steal from the global rsv
+		 * since this really shouldn't happen that often.
+		 */
+		WARN_ON(1);
+		ret = btrfs_block_rsv_migrate(&root->fs_info->global_block_rsv,
+					      dst_rsv, num_bytes);
+		goto out;
+	}
+
+migrate:
 	ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes);
+
+out:
+	/*
+	 * Migrate only takes a reservation, it doesn't touch the size of the
+	 * block_rsv.  This is to simplify people who don't normally have things
+	 * migrated from their block rsv.  If they go to release their
+	 * reservation, that will decrease the size as well, so if migrate
+	 * reduced size we'd end up with a negative size.  But for the
+	 * delalloc_meta_reserved stuff we will only know to drop 1 reservation,
+	 * but we could in fact do this reserve/migrate dance several times
+	 * between the time we did the original reservation and we'd clean it
+	 * up.  So to take care of this, release the space for the meta
+	 * reservation here.  I think it may be time for a documentation page on
+	 * how block rsvs. work.
+	 */
 	if (!ret)
 		node->bytes_reserved = num_bytes;
 
+	if (release)
+		btrfs_block_rsv_release(root, src_rsv, num_bytes);
+
 	return ret;
 }
 
@@ -646,7 +724,7 @@ static void btrfs_delayed_inode_release_metadata(struct btrfs_root *root,
 	if (!node->bytes_reserved)
 		return;
 
-	rsv = &root->fs_info->global_block_rsv;
+	rsv = &root->fs_info->delayed_block_rsv;
 	btrfs_block_rsv_release(root, rsv,
 				node->bytes_reserved);
 	node->bytes_reserved = 0;
@@ -1026,7 +1104,7 @@ int btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
 	path->leave_spinning = 1;
 
 	block_rsv = trans->block_rsv;
-	trans->block_rsv = &root->fs_info->global_block_rsv;
+	trans->block_rsv = &root->fs_info->delayed_block_rsv;
 
 	delayed_root = btrfs_get_delayed_root(root);
 
@@ -1069,7 +1147,7 @@ static int __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
 	path->leave_spinning = 1;
 
 	block_rsv = trans->block_rsv;
-	trans->block_rsv = &node->root->fs_info->global_block_rsv;
+	trans->block_rsv = &node->root->fs_info->delayed_block_rsv;
 
 	ret = btrfs_insert_delayed_items(trans, path, node->root, node);
 	if (!ret)
@@ -1149,7 +1227,7 @@ static void btrfs_async_run_delayed_node_done(struct btrfs_work *work)
 		goto free_path;
 
 	block_rsv = trans->block_rsv;
-	trans->block_rsv = &root->fs_info->global_block_rsv;
+	trans->block_rsv = &root->fs_info->delayed_block_rsv;
 
 	ret = btrfs_insert_delayed_items(trans, path, root, delayed_node);
 	if (!ret)
@@ -1685,12 +1763,10 @@ int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
 		goto release_node;
 	}
 
-	ret = btrfs_delayed_inode_reserve_metadata(trans, root, delayed_node);
-	/*
-	 * we must reserve enough space when we start a new transaction,
-	 * so reserving metadata failure is impossible
-	 */
-	BUG_ON(ret);
+	ret = btrfs_delayed_inode_reserve_metadata(trans, root, inode,
+						   delayed_node);
+	if (ret)
+		goto release_node;
 
 	fill_stack_inode_item(trans, &delayed_node->inode_item, inode);
 	delayed_node->inode_dirty = 1;

fs/btrfs/disk-io.h

@@ -40,6 +40,8 @@ struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
 				      u32 blocksize, u64 parent_transid);
 int readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize,
 			 u64 parent_transid);
+int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize,
+			 int mirror_num, struct extent_buffer **eb);
 struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
 						   u64 bytenr, u32 blocksize);
 int clean_tree_block(struct btrfs_trans_handle *trans,
@@ -83,8 +85,6 @@ int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
 			     struct btrfs_fs_info *fs_info);
 int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
 		       struct btrfs_root *root);
-int btree_lock_page_hook(struct page *page);
-
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 void btrfs_init_lockdep(void);

fs/btrfs/extent_io.h

@@ -17,6 +17,8 @@
 #define EXTENT_NODATASUM (1 << 10)
 #define EXTENT_DO_ACCOUNTING (1 << 11)
 #define EXTENT_FIRST_DELALLOC (1 << 12)
+#define EXTENT_NEED_WAIT (1 << 13)
+#define EXTENT_DAMAGED (1 << 14)
 #define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK)
 #define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC)
 
@@ -32,6 +34,7 @@
 #define EXTENT_BUFFER_BLOCKING 1
 #define EXTENT_BUFFER_DIRTY 2
 #define EXTENT_BUFFER_CORRUPT 3
+#define EXTENT_BUFFER_READAHEAD 4	/* this got triggered by readahead */
 
 /* these are flags for extent_clear_unlock_delalloc */
 #define EXTENT_CLEAR_UNLOCK_PAGE 0x1
@@ -67,7 +70,7 @@ struct extent_io_ops {
 			      unsigned long bio_flags);
 	int (*readpage_io_hook)(struct page *page, u64 start, u64 end);
 	int (*readpage_io_failed_hook)(struct bio *bio, struct page *page,
-				       u64 start, u64 end,
+				       u64 start, u64 end, int failed_mirror,
 				       struct extent_state *state);
 	int (*writepage_io_failed_hook)(struct bio *bio, struct page *page,
 					u64 start, u64 end,
@@ -85,7 +88,8 @@ struct extent_io_ops {
 				  struct extent_state *other);
 	void (*split_extent_hook)(struct inode *inode,
 				  struct extent_state *orig, u64 split);
-	int (*write_cache_pages_lock_hook)(struct page *page);
+	int (*write_cache_pages_lock_hook)(struct page *page, void *data,
+					   void (*flush_fn)(void *));
 };
 
 struct extent_io_tree {
@@ -185,7 +189,7 @@ int unlock_extent_cached(struct extent_io_tree *tree, u64 start, u64 end,
 int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end,
 		    gfp_t mask);
 int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
-			  get_extent_t *get_extent);
+			  get_extent_t *get_extent, int mirror_num);
 int __init extent_io_init(void);
 void extent_io_exit(void);
 
@@ -214,6 +218,8 @@ int set_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
 		     gfp_t mask);
 int clear_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
 		       gfp_t mask);
+int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
+		       int bits, int clear_bits, gfp_t mask);
 int set_extent_delalloc(struct extent_io_tree *tree, u64 start, u64 end,
 			struct extent_state **cached_state, gfp_t mask);
 int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
@@ -248,9 +254,14 @@ struct extent_buffer *alloc_extent_buffer(struct extent_io_tree *tree,
 struct extent_buffer *find_extent_buffer(struct extent_io_tree *tree,
 					 u64 start, unsigned long len);
 void free_extent_buffer(struct extent_buffer *eb);
+#define WAIT_NONE	0
+#define WAIT_COMPLETE	1
+#define WAIT_PAGE_LOCK	2
 int read_extent_buffer_pages(struct extent_io_tree *tree,
 			     struct extent_buffer *eb, u64 start, int wait,
 			     get_extent_t *get_extent, int mirror_num);
+unsigned long num_extent_pages(u64 start, u64 len);
+struct page *extent_buffer_page(struct extent_buffer *eb, unsigned long i);
 
 static inline void extent_buffer_get(struct extent_buffer *eb)
 {
@@ -300,4 +311,10 @@ int extent_clear_unlock_delalloc(struct inode *inode,
 struct bio *
 btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs,
 		gfp_t gfp_flags);
+
+struct btrfs_mapping_tree;
+
+int repair_io_failure(struct btrfs_mapping_tree *map_tree, u64 start,
+			u64 length, u64 logical, struct page *page,
+			int mirror_num);
 #endif

fs/btrfs/file-item.c

@@ -91,8 +91,7 @@ struct btrfs_csum_item *btrfs_lookup_csum(struct btrfs_trans_handle *trans,
 	struct btrfs_csum_item *item;
 	struct extent_buffer *leaf;
 	u64 csum_offset = 0;
-	u16 csum_size =
-		btrfs_super_csum_size(&root->fs_info->super_copy);
+	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
 	int csums_in_item;
 
 	file_key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
@@ -162,8 +161,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 	u64 item_last_offset = 0;
 	u64 disk_bytenr;
 	u32 diff;
-	u16 csum_size =
-		btrfs_super_csum_size(&root->fs_info->super_copy);
+	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
 	int ret;
 	struct btrfs_path *path;
 	struct btrfs_csum_item *item = NULL;
@@ -290,7 +288,7 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 	int ret;
 	size_t size;
 	u64 csum_end;
-	u16 csum_size = btrfs_super_csum_size(&root->fs_info->super_copy);
+	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -492,8 +490,7 @@ static noinline int truncate_one_csum(struct btrfs_trans_handle *trans,
 				      u64 bytenr, u64 len)
 {
 	struct extent_buffer *leaf;
-	u16 csum_size =
-		btrfs_super_csum_size(&root->fs_info->super_copy);
+	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
 	u64 csum_end;
 	u64 end_byte = bytenr + len;
 	u32 blocksize_bits = root->fs_info->sb->s_blocksize_bits;
@@ -549,8 +546,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 	u64 csum_end;
 	struct extent_buffer *leaf;
 	int ret;
-	u16 csum_size =
-		btrfs_super_csum_size(&root->fs_info->super_copy);
+	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
 	int blocksize_bits = root->fs_info->sb->s_blocksize_bits;
 
 	root = root->fs_info->csum_root;
@@ -676,8 +672,7 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 	struct btrfs_sector_sum *sector_sum;
 	u32 nritems;
 	u32 ins_size;
-	u16 csum_size =
-		btrfs_super_csum_size(&root->fs_info->super_copy);
+	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
 
 	path = btrfs_alloc_path();
 	if (!path)

fs/btrfs/file.c

@@ -1069,6 +1069,7 @@ static noinline int prepare_pages(struct btrfs_root *root, struct file *file,
 	int i;
 	unsigned long index = pos >> PAGE_CACHE_SHIFT;
 	struct inode *inode = fdentry(file)->d_inode;
+	gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
 	int err = 0;
 	int faili = 0;
 	u64 start_pos;
@@ -1080,7 +1081,7 @@ static noinline int prepare_pages(struct btrfs_root *root, struct file *file,
 again:
 	for (i = 0; i < num_pages; i++) {
 		pages[i] = find_or_create_page(inode->i_mapping, index + i,
-					       GFP_NOFS);
+					       mask);
 		if (!pages[i]) {
 			faili = i - 1;
 			err = -ENOMEM;
@@ -1386,7 +1387,11 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb,
 		goto out;
 	}
 
-	file_update_time(file);
+	err = btrfs_update_time(file);
+	if (err) {
+		mutex_unlock(&inode->i_mutex);
+		goto out;
+	}
 	BTRFS_I(inode)->sequence++;
 
 	start_pos = round_down(pos, root->sectorsize);
@@ -1615,10 +1620,6 @@ static long btrfs_fallocate(struct file *file, int mode,
 			goto out;
 	}
 
-	ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start);
-	if (ret)
-		goto out;
-
 	locked_end = alloc_end - 1;
 	while (1) {
 		struct btrfs_ordered_extent *ordered;
@@ -1664,11 +1665,27 @@ static long btrfs_fallocate(struct file *file, int mode,
 		if (em->block_start == EXTENT_MAP_HOLE ||
 		    (cur_offset >= inode->i_size &&
 		     !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
+
+			/*
+			 * Make sure we have enough space before we do the
+			 * allocation.
+			 */
+			ret = btrfs_check_data_free_space(inode, last_byte -
+							  cur_offset);
+			if (ret) {
+				free_extent_map(em);
+				break;
+			}
+
 			ret = btrfs_prealloc_file_range(inode, mode, cur_offset,
 							last_byte - cur_offset,
 							1 << inode->i_blkbits,
 							offset + len,
 							&alloc_hint);
+
+			/* Let go of our reservation. */
+			btrfs_free_reserved_data_space(inode, last_byte -
+						       cur_offset);
 			if (ret < 0) {
 				free_extent_map(em);
 				break;
@@ -1694,8 +1711,6 @@ static long btrfs_fallocate(struct file *file, int mode,
 	}
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
 			     &cached_state, GFP_NOFS);
-
-	btrfs_free_reserved_data_space(inode, alloc_end - alloc_start);
 out:
 	mutex_unlock(&inode->i_mutex);
 	return ret;

fs/btrfs/inode-map.c

@@ -398,6 +398,8 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
 	struct btrfs_path *path;
 	struct inode *inode;
+	struct btrfs_block_rsv *rsv;
+	u64 num_bytes;
 	u64 alloc_hint = 0;
 	int ret;
 	int prealloc;
@@ -421,11 +423,26 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 	if (!path)
 		return -ENOMEM;
 
+	rsv = trans->block_rsv;
+	trans->block_rsv = &root->fs_info->trans_block_rsv;
+
+	num_bytes = trans->bytes_reserved;
+	/*
+	 * 1 item for inode item insertion if need
+	 * 3 items for inode item update (in the worst case)
+	 * 1 item for free space object
+	 * 3 items for pre-allocation
+	 */
+	trans->bytes_reserved = btrfs_calc_trans_metadata_size(root, 8);
+	ret = btrfs_block_rsv_add_noflush(root, trans->block_rsv,
+					  trans->bytes_reserved);
+	if (ret)
+		goto out;
 again:
 	inode = lookup_free_ino_inode(root, path);
 	if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) {
 		ret = PTR_ERR(inode);
-		goto out;
+		goto out_release;
 	}
 
 	if (IS_ERR(inode)) {
@@ -434,7 +451,7 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 
 		ret = create_free_ino_inode(root, trans, path);
 		if (ret)
-			goto out;
+			goto out_release;
 		goto again;
 	}
 
@@ -465,21 +482,26 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 	/* Just to make sure we have enough space */
 	prealloc += 8 * PAGE_CACHE_SIZE;
 
-	ret = btrfs_check_data_free_space(inode, prealloc);
+	ret = btrfs_delalloc_reserve_space(inode, prealloc);
 	if (ret)
 		goto out_put;
 
 	ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc,
 					      prealloc, prealloc, &alloc_hint);
-	if (ret)
+	if (ret) {
+		btrfs_delalloc_release_space(inode, prealloc);
 		goto out_put;
+	}
 	btrfs_free_reserved_data_space(inode, prealloc);
 
+	ret = btrfs_write_out_ino_cache(root, trans, path);
 out_put:
 	iput(inode);
+out_release:
+	btrfs_block_rsv_release(root, trans->block_rsv, trans->bytes_reserved);
 out:
-	if (ret == 0)
-		ret = btrfs_write_out_ino_cache(root, trans, path);
+	trans->block_rsv = rsv;
+	trans->bytes_reserved = num_bytes;
 
 	btrfs_free_path(path);
 	return ret;

fs/btrfs/ioctl.h

@@ -193,6 +193,30 @@ struct btrfs_ioctl_space_args {
 	struct btrfs_ioctl_space_info spaces[0];
 };
 
+struct btrfs_data_container {
+	__u32	bytes_left;	/* out -- bytes not needed to deliver output */
+	__u32	bytes_missing;	/* out -- additional bytes needed for result */
+	__u32	elem_cnt;	/* out */
+	__u32	elem_missed;	/* out */
+	__u64	val[0];		/* out */
+};
+
+struct btrfs_ioctl_ino_path_args {
+	__u64				inum;		/* in */
+	__u32				size;		/* in */
+	__u64				reserved[4];
+	/* struct btrfs_data_container	*fspath;	   out */
+	__u64				fspath;		/* out */
+};
+
+struct btrfs_ioctl_logical_ino_args {
+	__u64				logical;	/* in */
+	__u32				size;		/* in */
+	__u64				reserved[4];
+	/* struct btrfs_data_container	*inodes;	out   */
+	__u64				inodes;
+};
+
 #define BTRFS_IOC_SNAP_CREATE _IOW(BTRFS_IOCTL_MAGIC, 1, \
 				   struct btrfs_ioctl_vol_args)
 #define BTRFS_IOC_DEFRAG _IOW(BTRFS_IOCTL_MAGIC, 2, \
@@ -248,4 +272,9 @@ struct btrfs_ioctl_space_args {
 				 struct btrfs_ioctl_dev_info_args)
 #define BTRFS_IOC_FS_INFO _IOR(BTRFS_IOCTL_MAGIC, 31, \
 			       struct btrfs_ioctl_fs_info_args)
+#define BTRFS_IOC_INO_PATHS _IOWR(BTRFS_IOCTL_MAGIC, 35, \
+					struct btrfs_ioctl_ino_path_args)
+#define BTRFS_IOC_LOGICAL_INO _IOWR(BTRFS_IOCTL_MAGIC, 36, \
+					struct btrfs_ioctl_ino_path_args)
+
 #endif

fs/btrfs/print-tree.c

@@ -158,8 +158,7 @@ static void print_extent_ref_v0(struct extent_buffer *eb, int slot)
 void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
 {
 	int i;
-	u32 type;
-	u32 nr = btrfs_header_nritems(l);
+	u32 type, nr;
 	struct btrfs_item *item;
 	struct btrfs_root_item *ri;
 	struct btrfs_dir_item *di;
@@ -172,6 +171,11 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
 	struct btrfs_key key;
 	struct btrfs_key found_key;
 
+	if (!l)
+		return;
+
+	nr = btrfs_header_nritems(l);
+
 	printk(KERN_INFO "leaf %llu total ptrs %d free space %d\n",
 		(unsigned long long)btrfs_header_bytenr(l), nr,
 		btrfs_leaf_free_space(root, l));

fs/btrfs/relocation.c

@@ -1174,6 +1174,8 @@ static int clone_backref_node(struct btrfs_trans_handle *trans,
 			list_add_tail(&new_edge->list[UPPER],
 				      &new_node->lower);
 		}
+	} else {
+		list_add_tail(&new_node->lower, &cache->leaves);
 	}
 
 	rb_node = tree_insert(&cache->rb_root, new_node->bytenr,
@@ -2041,8 +2043,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
 		BUG_ON(IS_ERR(trans));
 		trans->block_rsv = rc->block_rsv;
 
-		ret = btrfs_block_rsv_check(trans, root, rc->block_rsv,
-					    min_reserved, 0);
+		ret = btrfs_block_rsv_refill(root, rc->block_rsv, min_reserved);
 		if (ret) {
 			BUG_ON(ret != -EAGAIN);
 			ret = btrfs_commit_transaction(trans, root);
@@ -2152,8 +2153,7 @@ int prepare_to_merge(struct reloc_control *rc, int err)
 again:
 	if (!err) {
 		num_bytes = rc->merging_rsv_size;
-		ret = btrfs_block_rsv_add(NULL, root, rc->block_rsv,
-					  num_bytes);
+		ret = btrfs_block_rsv_add(root, rc->block_rsv, num_bytes);
 		if (ret)
 			err = ret;
 	}
@@ -2427,7 +2427,7 @@ static int reserve_metadata_space(struct btrfs_trans_handle *trans,
 	num_bytes = calcu_metadata_size(rc, node, 1) * 2;
 
 	trans->block_rsv = rc->block_rsv;
-	ret = btrfs_block_rsv_add(trans, root, rc->block_rsv, num_bytes);
+	ret = btrfs_block_rsv_add(root, rc->block_rsv, num_bytes);
 	if (ret) {
 		if (ret == -EAGAIN)
 			rc->commit_transaction = 1;
@@ -2922,6 +2922,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 	unsigned long last_index;
 	struct page *page;
 	struct file_ra_state *ra;
+	gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
 	int nr = 0;
 	int ret = 0;
 
@@ -2946,7 +2947,9 @@ static int relocate_file_extent_cluster(struct inode *inode,
 	index = (cluster->start - offset) >> PAGE_CACHE_SHIFT;
 	last_index = (cluster->end - offset) >> PAGE_CACHE_SHIFT;
 	while (index <= last_index) {
+		mutex_lock(&inode->i_mutex);
 		ret = btrfs_delalloc_reserve_metadata(inode, PAGE_CACHE_SIZE);
+		mutex_unlock(&inode->i_mutex);
 		if (ret)
 			goto out;
 
@@ -2956,7 +2959,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 						  ra, NULL, index,
 						  last_index + 1 - index);
 			page = find_or_create_page(inode->i_mapping, index,
-						   GFP_NOFS);
+						   mask);
 			if (!page) {
 				btrfs_delalloc_release_metadata(inode,
 							PAGE_CACHE_SIZE);
@@ -3323,8 +3326,11 @@ static int find_data_references(struct reloc_control *rc,
 	}
 
 	key.objectid = ref_objectid;
-	key.offset = ref_offset;
 	key.type = BTRFS_EXTENT_DATA_KEY;
+	if (ref_offset > ((u64)-1 << 32))
+		key.offset = 0;
+	else
+		key.offset = ref_offset;
 
 	path->search_commit_root = 1;
 	path->skip_locking = 1;
@@ -3645,14 +3651,11 @@ int prepare_to_relocate(struct reloc_control *rc)
 	 * btrfs_init_reloc_root will use them when there
 	 * is no reservation in transaction handle.
 	 */
-	ret = btrfs_block_rsv_add(NULL, rc->extent_root, rc->block_rsv,
+	ret = btrfs_block_rsv_add(rc->extent_root, rc->block_rsv,
 				  rc->extent_root->nodesize * 256);
 	if (ret)
 		return ret;
 
-	rc->block_rsv->refill_used = 1;
-	btrfs_add_durable_block_rsv(rc->extent_root->fs_info, rc->block_rsv);
-
 	memset(&rc->cluster, 0, sizeof(rc->cluster));
 	rc->search_start = rc->block_group->key.objectid;
 	rc->extents_found = 0;
@@ -3777,8 +3780,7 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
 			}
 		}
 
-		ret = btrfs_block_rsv_check(trans, rc->extent_root,
-					    rc->block_rsv, 0, 5);
+		ret = btrfs_block_rsv_check(rc->extent_root, rc->block_rsv, 5);
 		if (ret < 0) {
 			if (ret != -EAGAIN) {
 				err = ret;