Merge tag 'v4.18.19' into dev-4.18

This is the 4.18.19 stable release

Signed-off-by: Joel Stanley <joel@jms.id.au>

12 files changed, 297 insertions, 114 deletions

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 4bc326df472e..4a7ae216977d 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1054,9 +1054,26 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 	if ((root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && parent)
 		parent_start = parent->start;
 
+	/*
+	 * If we are COWing a node/leaf from the extent, chunk or device trees,
+	 * make sure that we do not finish block group creation of pending block
+	 * groups. We do this to avoid a deadlock.
+	 * COWing can result in allocation of a new chunk, and flushing pending
+	 * block groups (btrfs_create_pending_block_groups()) can be triggered
+	 * when finishing allocation of a new chunk. Creation of a pending block
+	 * group modifies the extent, chunk and device trees, therefore we could
+	 * deadlock with ourselves since we are holding a lock on an extent
+	 * buffer that btrfs_create_pending_block_groups() may try to COW later.
+	 */
+	if (root == fs_info->extent_root ||
+	    root == fs_info->chunk_root ||
+	    root == fs_info->dev_root)
+		trans->can_flush_pending_bgs = false;
+
 	cow = btrfs_alloc_tree_block(trans, root, parent_start,
 			root->root_key.objectid, &disk_key, level,
 			search_start, empty_size);
+	trans->can_flush_pending_bgs = true;
 	if (IS_ERR(cow))
 		return PTR_ERR(cow);
 
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index d20b244623f2..e129a595f811 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -445,6 +445,7 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 		break;
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
+		ASSERT(0);
 		ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED;
 		goto leave;
 	}
@@ -487,6 +488,10 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
 		btrfs_dev_replace_write_lock(dev_replace);
+		dev_replace->replace_state =
+			BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED;
+		dev_replace->srcdev = NULL;
+		dev_replace->tgtdev = NULL;
 		goto leave;
 	}
 
@@ -508,8 +513,6 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 	return ret;
 
 leave:
-	dev_replace->srcdev = NULL;
-	dev_replace->tgtdev = NULL;
 	btrfs_dev_replace_write_unlock(dev_replace);
 	btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
 	return ret;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 4ab0bccfa281..e67de6a9805b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2490,6 +2490,9 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
 					   insert_reserved);
 	else
 		BUG();
+	if (ret && insert_reserved)
+		btrfs_pin_extent(trans->fs_info, node->bytenr,
+				 node->num_bytes, 1);
 	return ret;
 }
 
@@ -3034,7 +3037,6 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 	struct btrfs_delayed_ref_head *head;
 	int ret;
 	int run_all = count == (unsigned long)-1;
-	bool can_flush_pending_bgs = trans->can_flush_pending_bgs;
 
 	/* We'll clean this up in btrfs_cleanup_transaction */
 	if (trans->aborted)
@@ -3051,7 +3053,6 @@ again:
 #ifdef SCRAMBLE_DELAYED_REFS
 	delayed_refs->run_delayed_start = find_middle(&delayed_refs->root);
 #endif
-	trans->can_flush_pending_bgs = false;
 	ret = __btrfs_run_delayed_refs(trans, count);
 	if (ret < 0) {
 		btrfs_abort_transaction(trans, ret);
@@ -3082,7 +3083,6 @@ again:
 		goto again;
 	}
 out:
-	trans->can_flush_pending_bgs = can_flush_pending_bgs;
 	return 0;
 }
 
@@ -4664,6 +4664,7 @@ again:
 			goto out;
 	} else {
 		ret = 1;
+		space_info->max_extent_size = 0;
 	}
 
 	space_info->force_alloc = CHUNK_ALLOC_NO_FORCE;
@@ -4685,11 +4686,9 @@ out:
 	 * the block groups that were made dirty during the lifetime of the
 	 * transaction.
 	 */
-	if (trans->can_flush_pending_bgs &&
-	    trans->chunk_bytes_reserved >= (u64)SZ_2M) {
+	if (trans->chunk_bytes_reserved >= (u64)SZ_2M)
 		btrfs_create_pending_block_groups(trans);
-		btrfs_trans_release_chunk_metadata(trans);
-	}
+
 	return ret;
 }
 
@@ -6581,6 +6580,7 @@ static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
 		space_info->bytes_readonly += num_bytes;
 	cache->reserved -= num_bytes;
 	space_info->bytes_reserved -= num_bytes;
+	space_info->max_extent_size = 0;
 
 	if (delalloc)
 		cache->delalloc_bytes -= num_bytes;
@@ -7412,6 +7412,7 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
 	struct btrfs_block_group_cache *block_group = NULL;
 	u64 search_start = 0;
 	u64 max_extent_size = 0;
+	u64 max_free_space = 0;
 	u64 empty_cluster = 0;
 	struct btrfs_space_info *space_info;
 	int loop = 0;
@@ -7707,8 +7708,8 @@ unclustered_alloc:
 			spin_lock(&ctl->tree_lock);
 			if (ctl->free_space <
 			    num_bytes + empty_cluster + empty_size) {
-				if (ctl->free_space > max_extent_size)
-					max_extent_size = ctl->free_space;
+				max_free_space = max(max_free_space,
+						     ctl->free_space);
 				spin_unlock(&ctl->tree_lock);
 				goto loop;
 			}
@@ -7877,6 +7878,8 @@ loop:
 	}
 out:
 	if (ret == -ENOSPC) {
+		if (!max_extent_size)
+			max_extent_size = max_free_space;
 		spin_lock(&space_info->lock);
 		space_info->max_extent_size = max_extent_size;
 		spin_unlock(&space_info->lock);
@@ -8158,21 +8161,14 @@ static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 	}
 
 	path = btrfs_alloc_path();
-	if (!path) {
-		btrfs_free_and_pin_reserved_extent(fs_info,
-						   extent_key.objectid,
-						   fs_info->nodesize);
+	if (!path)
 		return -ENOMEM;
-	}
 
 	path->leave_spinning = 1;
 	ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path,
 				      &extent_key, size);
 	if (ret) {
 		btrfs_free_path(path);
-		btrfs_free_and_pin_reserved_extent(fs_info,
-						   extent_key.objectid,
-						   fs_info->nodesize);
 		return ret;
 	}
 
@@ -8301,6 +8297,19 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	if (IS_ERR(buf))
 		return buf;
 
+	/*
+	 * Extra safety check in case the extent tree is corrupted and extent
+	 * allocator chooses to use a tree block which is already used and
+	 * locked.
+	 */
+	if (buf->lock_owner == current->pid) {
+		btrfs_err_rl(fs_info,
+"tree block %llu owner %llu already locked by pid=%d, extent tree corruption detected",
+			buf->start, btrfs_header_owner(buf), current->pid);
+		free_extent_buffer(buf);
+		return ERR_PTR(-EUCLEAN);
+	}
+
 	btrfs_set_header_generation(buf, trans->transid);
 	btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
 	btrfs_tree_lock(buf);
@@ -8938,15 +8947,14 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 	if (eb == root->node) {
 		if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF)
 			parent = eb->start;
-		else
-			BUG_ON(root->root_key.objectid !=
-			       btrfs_header_owner(eb));
+		else if (root->root_key.objectid != btrfs_header_owner(eb))
+			goto owner_mismatch;
 	} else {
 		if (wc->flags[level + 1] & BTRFS_BLOCK_FLAG_FULL_BACKREF)
 			parent = path->nodes[level + 1]->start;
-		else
-			BUG_ON(root->root_key.objectid !=
-			       btrfs_header_owner(path->nodes[level + 1]));
+		else if (root->root_key.objectid !=
+			 btrfs_header_owner(path->nodes[level + 1]))
+			goto owner_mismatch;
 	}
 
 	btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1);
@@ -8954,6 +8962,11 @@ out:
 	wc->refs[level] = 0;
 	wc->flags[level] = 0;
 	return 0;
+
+owner_mismatch:
+	btrfs_err_rl(fs_info, "unexpected tree owner, have %llu expect %llu",
+		     btrfs_header_owner(eb), root->root_key.objectid);
+	return -EUCLEAN;
 }
 
 static noinline int walk_down_tree(struct btrfs_trans_handle *trans,
@@ -9007,6 +9020,8 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans,
 			ret = walk_up_proc(trans, root, path, wc);
 			if (ret > 0)
 				return 0;
+			if (ret < 0)
+				return ret;
 
 			if (path->locks[level]) {
 				btrfs_tree_unlock_rw(path->nodes[level],
@@ -9772,6 +9787,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
 
 		block_group = btrfs_lookup_first_block_group(info, last);
 		while (block_group) {
+			wait_block_group_cache_done(block_group);
 			spin_lock(&block_group->lock);
 			if (block_group->iref)
 				break;
@@ -10184,15 +10200,19 @@ error:
 void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_block_group_cache *block_group, *tmp;
+	struct btrfs_block_group_cache *block_group;
 	struct btrfs_root *extent_root = fs_info->extent_root;
 	struct btrfs_block_group_item item;
 	struct btrfs_key key;
 	int ret = 0;
-	bool can_flush_pending_bgs = trans->can_flush_pending_bgs;
 
-	trans->can_flush_pending_bgs = false;
-	list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) {
+	if (!trans->can_flush_pending_bgs)
+		return;
+
+	while (!list_empty(&trans->new_bgs)) {
+		block_group = list_first_entry(&trans->new_bgs,
+					       struct btrfs_block_group_cache,
+					       bg_list);
 		if (ret)
 			goto next;
 
@@ -10214,7 +10234,7 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
 next:
 		list_del_init(&block_group->bg_list);
 	}
-	trans->can_flush_pending_bgs = can_flush_pending_bgs;
+	btrfs_trans_release_chunk_metadata(trans);
 }
 
 int btrfs_make_block_group(struct btrfs_trans_handle *trans,
@@ -10869,14 +10889,16 @@ int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info,
  * We don't want a transaction for this since the discard may take a
  * substantial amount of time.  We don't require that a transaction be
  * running, but we do need to take a running transaction into account
- * to ensure that we're not discarding chunks that were released in
- * the current transaction.
+ * to ensure that we're not discarding chunks that were released or
+ * allocated in the current transaction.
  *
  * Holding the chunks lock will prevent other threads from allocating
  * or releasing chunks, but it won't prevent a running transaction
  * from committing and releasing the memory that the pending chunks
  * list head uses.  For that, we need to take a reference to the
- * transaction.
+ * transaction and hold the commit root sem.  We only need to hold
+ * it while performing the free space search since we have already
+ * held back allocations.
  */
 static int btrfs_trim_free_extents(struct btrfs_device *device,
 				   u64 minlen, u64 *trimmed)
@@ -10886,6 +10908,10 @@ static int btrfs_trim_free_extents(struct btrfs_device *device,
 
 	*trimmed = 0;
 
+	/* Discard not supported = nothing to do. */
+	if (!blk_queue_discard(bdev_get_queue(device->bdev)))
+		return 0;
+
 	/* Not writeable = nothing to do. */
 	if (!test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state))
 		return 0;
@@ -10903,9 +10929,13 @@ static int btrfs_trim_free_extents(struct btrfs_device *device,
 
 		ret = mutex_lock_interruptible(&fs_info->chunk_mutex);
 		if (ret)
-			return ret;
+			break;
 
-		down_read(&fs_info->commit_root_sem);
+		ret = down_read_killable(&fs_info->commit_root_sem);
+		if (ret) {
+			mutex_unlock(&fs_info->chunk_mutex);
+			break;
+		}
 
 		spin_lock(&fs_info->trans_lock);
 		trans = fs_info->running_transaction;
@@ -10913,13 +10943,17 @@ static int btrfs_trim_free_extents(struct btrfs_device *device,
 			refcount_inc(&trans->use_count);
 		spin_unlock(&fs_info->trans_lock);
 
+		if (!trans)
+			up_read(&fs_info->commit_root_sem);
+
 		ret = find_free_dev_extent_start(trans, device, minlen, start,
 						 &start, &len);
-		if (trans)
+		if (trans) {
+			up_read(&fs_info->commit_root_sem);
 			btrfs_put_transaction(trans);
+		}
 
 		if (ret) {
-			up_read(&fs_info->commit_root_sem);
 			mutex_unlock(&fs_info->chunk_mutex);
 			if (ret == -ENOSPC)
 				ret = 0;
@@ -10927,7 +10961,6 @@ static int btrfs_trim_free_extents(struct btrfs_device *device,
 		}
 
 		ret = btrfs_issue_discard(device->bdev, start, len, &bytes);
-		up_read(&fs_info->commit_root_sem);
 		mutex_unlock(&fs_info->chunk_mutex);
 
 		if (ret)
@@ -10947,6 +10980,15 @@ static int btrfs_trim_free_extents(struct btrfs_device *device,
 	return ret;
 }
 
+/*
+ * Trim the whole filesystem by:
+ * 1) trimming the free space in each block group
+ * 2) trimming the unallocated space on each device
+ *
+ * This will also continue trimming even if a block group or device encounters
+ * an error.  The return value will be the last error, or 0 if nothing bad
+ * happens.
+ */
 int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
 {
 	struct btrfs_block_group_cache *cache = NULL;
@@ -10956,18 +10998,14 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
 	u64 start;
 	u64 end;
 	u64 trimmed = 0;
-	u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
+	u64 bg_failed = 0;
+	u64 dev_failed = 0;
+	int bg_ret = 0;
+	int dev_ret = 0;
 	int ret = 0;
 
-	/*
-	 * try to trim all FS space, our block group may start from non-zero.
-	 */
-	if (range->len == total_bytes)
-		cache = btrfs_lookup_first_block_group(fs_info, range->start);
-	else
-		cache = btrfs_lookup_block_group(fs_info, range->start);
-
-	while (cache) {
+	cache = btrfs_lookup_first_block_group(fs_info, range->start);
+	for (; cache; cache = next_block_group(fs_info, cache)) {
 		if (cache->key.objectid >= (range->start + range->len)) {
 			btrfs_put_block_group(cache);
 			break;
@@ -10981,13 +11019,15 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
 			if (!block_group_cache_done(cache)) {
 				ret = cache_block_group(cache, 0);
 				if (ret) {
-					btrfs_put_block_group(cache);
-					break;
+					bg_failed++;
+					bg_ret = ret;
+					continue;
 				}
 				ret = wait_block_group_cache_done(cache);
 				if (ret) {
-					btrfs_put_block_group(cache);
-					break;
+					bg_failed++;
+					bg_ret = ret;
+					continue;
 				}
 			}
 			ret = btrfs_trim_block_group(cache,
@@ -10998,28 +11038,40 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
 
 			trimmed += group_trimmed;
 			if (ret) {
-				btrfs_put_block_group(cache);
-				break;
+				bg_failed++;
+				bg_ret = ret;
+				continue;
 			}
 		}
-
-		cache = next_block_group(fs_info, cache);
 	}
 
+	if (bg_failed)
+		btrfs_warn(fs_info,
+			"failed to trim %llu block group(s), last error %d",
+			bg_failed, bg_ret);
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
-	devices = &fs_info->fs_devices->alloc_list;
-	list_for_each_entry(device, devices, dev_alloc_list) {
+	devices = &fs_info->fs_devices->devices;
+	list_for_each_entry(device, devices, dev_list) {
 		ret = btrfs_trim_free_extents(device, range->minlen,
 					      &group_trimmed);
-		if (ret)
+		if (ret) {
+			dev_failed++;
+			dev_ret = ret;
 			break;
+		}
 
 		trimmed += group_trimmed;
 	}
 	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 
+	if (dev_failed)
+		btrfs_warn(fs_info,
+			"failed to trim %llu device(s), last error %d",
+			dev_failed, dev_ret);
 	range->len = trimmed;
-	return ret;
+	if (bg_ret)
+		return bg_ret;
+	return dev_ret;
 }
 
 /*
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 51e77d72068a..22c2f38cd9b3 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -534,6 +534,14 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages,
 
 	end_of_last_block = start_pos + num_bytes - 1;
 
+	/*
+	 * The pages may have already been dirty, clear out old accounting so
+	 * we can set things up properly
+	 */
+	clear_extent_bit(&BTRFS_I(inode)->io_tree, start_pos, end_of_last_block,
+			 EXTENT_DIRTY | EXTENT_DELALLOC |
+			 EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, cached);
+
 	if (!btrfs_is_free_space_inode(BTRFS_I(inode))) {
 		if (start_pos >= isize &&
 		    !(BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC)) {
@@ -1504,18 +1512,27 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
 		}
 		if (ordered)
 			btrfs_put_ordered_extent(ordered);
-		clear_extent_bit(&inode->io_tree, start_pos, last_pos,
-				 EXTENT_DIRTY | EXTENT_DELALLOC |
-				 EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
-				 0, 0, cached_state);
+
 		*lockstart = start_pos;
 		*lockend = last_pos;
 		ret = 1;
 	}
 
+	/*
+	 * It's possible the pages are dirty right now, but we don't want
+	 * to clean them yet because copy_from_user may catch a page fault
+	 * and we might have to fall back to one page at a time.  If that
+	 * happens, we'll unlock these pages and we'd have a window where
+	 * reclaim could sneak in and drop the once-dirty page on the floor
+	 * without writing it.
+	 *
+	 * We have the pages locked and the extent range locked, so there's
+	 * no way someone can start IO on any dirty pages in this range.
+	 *
+	 * We'll call btrfs_dirty_pages() later on, and that will flip around
+	 * delalloc bits and dirty the pages as required.
+	 */
 	for (i = 0; i < num_pages; i++) {
-		if (clear_page_dirty_for_io(pages[i]))
-			account_page_redirty(pages[i]);
 		set_page_extent_mapped(pages[i]);
 		WARN_ON(!PageLocked(pages[i]));
 	}
@@ -2065,6 +2082,14 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		goto out;
 
 	inode_lock(inode);
+
+	/*
+	 * We take the dio_sem here because the tree log stuff can race with
+	 * lockless dio writes and get an extent map logged for an extent we
+	 * never waited on.  We need it this high up for lockdep reasons.
+	 */
+	down_write(&BTRFS_I(inode)->dio_sem);
+
 	atomic_inc(&root->log_batch);
 	full_sync = test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
 			     &BTRFS_I(inode)->runtime_flags);
@@ -2116,6 +2141,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		ret = start_ordered_ops(inode, start, end);
 	}
 	if (ret) {
+		up_write(&BTRFS_I(inode)->dio_sem);
 		inode_unlock(inode);
 		goto out;
 	}
@@ -2171,6 +2197,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		 * checked called fsync.
 		 */
 		ret = filemap_check_wb_err(inode->i_mapping, file->f_wb_err);
+		up_write(&BTRFS_I(inode)->dio_sem);
 		inode_unlock(inode);
 		goto out;
 	}
@@ -2189,6 +2216,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
+		up_write(&BTRFS_I(inode)->dio_sem);
 		inode_unlock(inode);
 		goto out;
 	}
@@ -2210,6 +2238,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	 * file again, but that will end up using the synchronization
 	 * inside btrfs_sync_log to keep things safe.
 	 */
+	up_write(&BTRFS_I(inode)->dio_sem);
 	inode_unlock(inode);
 
 	/*
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index d5f80cb300be..a5f18333aa8c 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -10,6 +10,7 @@
 #include <linux/math64.h>
 #include <linux/ratelimit.h>
 #include <linux/error-injection.h>
+#include <linux/sched/mm.h>
 #include "ctree.h"
 #include "free-space-cache.h"
 #include "transaction.h"
@@ -47,6 +48,7 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
 	struct btrfs_free_space_header *header;
 	struct extent_buffer *leaf;
 	struct inode *inode = NULL;
+	unsigned nofs_flag;
 	int ret;
 
 	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
@@ -68,7 +70,13 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
 	btrfs_disk_key_to_cpu(&location, &disk_key);
 	btrfs_release_path(path);
 
+	/*
+	 * We are often under a trans handle at this point, so we need to make
+	 * sure NOFS is set to keep us from deadlocking.
+	 */
+	nofs_flag = memalloc_nofs_save();
 	inode = btrfs_iget(fs_info->sb, &location, root, NULL);
+	memalloc_nofs_restore(nofs_flag);
 	if (IS_ERR(inode))
 		return inode;
 	if (is_bad_inode(inode)) {
@@ -1686,6 +1694,8 @@ static inline void __bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
 	bitmap_clear(info->bitmap, start, count);
 
 	info->bytes -= bytes;
+	if (info->max_extent_size > ctl->unit)
+		info->max_extent_size = 0;
 }
 
 static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl,
@@ -1769,6 +1779,13 @@ static int search_bitmap(struct btrfs_free_space_ctl *ctl,
 	return -1;
 }
 
+static inline u64 get_max_extent_size(struct btrfs_free_space *entry)
+{
+	if (entry->bitmap)
+		return entry->max_extent_size;
+	return entry->bytes;
+}
+
 /* Cache the size of the max extent in bytes */
 static struct btrfs_free_space *
 find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes,
@@ -1790,8 +1807,8 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes,
 	for (node = &entry->offset_index; node; node = rb_next(node)) {
 		entry = rb_entry(node, struct btrfs_free_space, offset_index);
 		if (entry->bytes < *bytes) {
-			if (entry->bytes > *max_extent_size)
-				*max_extent_size = entry->bytes;
+			*max_extent_size = max(get_max_extent_size(entry),
+					       *max_extent_size);
 			continue;
 		}
 
@@ -1809,8 +1826,8 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes,
 		}
 
 		if (entry->bytes < *bytes + align_off) {
-			if (entry->bytes > *max_extent_size)
-				*max_extent_size = entry->bytes;
+			*max_extent_size = max(get_max_extent_size(entry),
+					       *max_extent_size);
 			continue;
 		}
 
@@ -1822,8 +1839,10 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes,
 				*offset = tmp;
 				*bytes = size;
 				return entry;
-			} else if (size > *max_extent_size) {
-				*max_extent_size = size;
+			} else {
+				*max_extent_size =
+					max(get_max_extent_size(entry),
+					    *max_extent_size);
 			}
 			continue;
 		}
@@ -2447,6 +2466,7 @@ void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
 	struct rb_node *n;
 	int count = 0;
 
+	spin_lock(&ctl->tree_lock);
 	for (n = rb_first(&ctl->free_space_offset); n; n = rb_next(n)) {
 		info = rb_entry(n, struct btrfs_free_space, offset_index);
 		if (info->bytes >= bytes && !block_group->ro)
@@ -2455,6 +2475,7 @@ void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
 			   info->offset, info->bytes,
 		       (info->bitmap) ? "yes" : "no");
 	}
+	spin_unlock(&ctl->tree_lock);
 	btrfs_info(fs_info, "block group has cluster?: %s",
 	       list_empty(&block_group->cluster_list) ? "no" : "yes");
 	btrfs_info(fs_info,
@@ -2683,8 +2704,8 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
 
 	err = search_bitmap(ctl, entry, &search_start, &search_bytes, true);
 	if (err) {
-		if (search_bytes > *max_extent_size)
-			*max_extent_size = search_bytes;
+		*max_extent_size = max(get_max_extent_size(entry),
+				       *max_extent_size);
 		return 0;
 	}
 
@@ -2721,8 +2742,9 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
 
 	entry = rb_entry(node, struct btrfs_free_space, offset_index);
 	while (1) {
-		if (entry->bytes < bytes && entry->bytes > *max_extent_size)
-			*max_extent_size = entry->bytes;
+		if (entry->bytes < bytes)
+			*max_extent_size = max(get_max_extent_size(entry),
+					       *max_extent_size);
 
 		if (entry->bytes < bytes ||
 		    (!entry->bitmap && entry->offset < min_start)) {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d3736fbf6774..dc0f9d089b19 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -507,6 +507,7 @@ again:
 		pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
 		if (!pages) {
 			/* just bail out to the uncompressed code */
+			nr_pages = 0;
 			goto cont;
 		}
 
@@ -2950,6 +2951,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 	bool truncated = false;
 	bool range_locked = false;
 	bool clear_new_delalloc_bytes = false;
+	bool clear_reserved_extent = true;
 
 	if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
 	    !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags) &&
@@ -3053,10 +3055,12 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 						logical_len, logical_len,
 						compress_type, 0, 0,
 						BTRFS_FILE_EXTENT_REG);
-		if (!ret)
+		if (!ret) {
+			clear_reserved_extent = false;
 			btrfs_release_delalloc_bytes(fs_info,
 						     ordered_extent->start,
 						     ordered_extent->disk_len);
+		}
 	}
 	unpin_extent_cache(&BTRFS_I(inode)->extent_tree,
 			   ordered_extent->file_offset, ordered_extent->len,
@@ -3117,8 +3121,13 @@ out:
 		 * wrong we need to return the space for this ordered extent
 		 * back to the allocator.  We only free the extent in the
 		 * truncated case if we didn't write out the extent at all.
+		 *
+		 * If we made it past insert_reserved_file_extent before we
+		 * errored out then we don't need to do this as the accounting
+		 * has already been done.
 		 */
 		if ((ret || !logical_len) &&
+		    clear_reserved_extent &&
 		    !test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
 		    !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags))
 			btrfs_free_reserved_extent(fs_info,
@@ -5293,11 +5302,13 @@ static void evict_inode_truncate_pages(struct inode *inode)
 		struct extent_state *cached_state = NULL;
 		u64 start;
 		u64 end;
+		unsigned state_flags;
 
 		node = rb_first(&io_tree->state);
 		state = rb_entry(node, struct extent_state, rb_node);
 		start = state->start;
 		end = state->end;
+		state_flags = state->state;
 		spin_unlock(&io_tree->lock);
 
 		lock_extent_bits(io_tree, start, end, &cached_state);
@@ -5310,7 +5321,7 @@ static void evict_inode_truncate_pages(struct inode *inode)
 		 *
 		 * Note, end is the bytenr of last byte, so we need + 1 here.
 		 */
-		if (state->state & EXTENT_DELALLOC)
+		if (state_flags & EXTENT_DELALLOC)
 			btrfs_qgroup_free_data(inode, NULL, start, end - start + 1);
 
 		clear_extent_bit(io_tree, start, end,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index ef7159646615..c972920701a3 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -496,7 +496,6 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
 	struct fstrim_range range;
 	u64 minlen = ULLONG_MAX;
 	u64 num_devices = 0;
-	u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
 	int ret;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -520,11 +519,15 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
 		return -EOPNOTSUPP;
 	if (copy_from_user(&range, arg, sizeof(range)))
 		return -EFAULT;
-	if (range.start > total_bytes ||
-	    range.len < fs_info->sb->s_blocksize)
+
+	/*
+	 * NOTE: Don't truncate the range using super->total_bytes.  Bytenr of
+	 * block group is in the logical address space, which can be any
+	 * sectorsize aligned bytenr in  the range [0, U64_MAX].
+	 */
+	if (range.len < fs_info->sb->s_blocksize)
 		return -EINVAL;
 
-	range.len = min(range.len, total_bytes - range.start);
 	range.minlen = max(range.minlen, minlen);
 	ret = btrfs_trim_fs(fs_info, &range);
 	if (ret < 0)
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index c25dc47210a3..7407f5a5d682 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2856,6 +2856,7 @@ qgroup_rescan_zero_tracking(struct btrfs_fs_info *fs_info)
 		qgroup->rfer_cmpr = 0;
 		qgroup->excl = 0;
 		qgroup->excl_cmpr = 0;
+		qgroup_dirty(fs_info, qgroup);
 	}
 	spin_unlock(&fs_info->qgroup_lock);
 }
@@ -3065,6 +3066,10 @@ static int __btrfs_qgroup_release_data(struct inode *inode,
 	int trace_op = QGROUP_RELEASE;
 	int ret;
 
+	if (!test_bit(BTRFS_FS_QUOTA_ENABLED,
+		      &BTRFS_I(inode)->root->fs_info->flags))
+		return 0;
+
 	/* In release case, we shouldn't have @reserved */
 	WARN_ON(!free && reserved);
 	if (free && reserved)
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index d60dd06445ce..cad73ed7aebc 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -261,6 +261,8 @@ void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
 static inline void btrfs_qgroup_free_delayed_ref(struct btrfs_fs_info *fs_info,
 						 u64 ref_root, u64 num_bytes)
 {
+	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+		return;
 	trace_btrfs_qgroup_free_delayed_ref(fs_info, ref_root, num_bytes);
 	btrfs_qgroup_free_refroot(fs_info, ref_root, num_bytes,
 				  BTRFS_QGROUP_RSV_DATA);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index be94c65bb4d2..5ee49b796815 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1321,7 +1321,7 @@ static void __del_reloc_root(struct btrfs_root *root)
 	struct mapping_node *node = NULL;
 	struct reloc_control *rc = fs_info->reloc_ctl;
 
-	if (rc) {
+	if (rc && root->node) {
 		spin_lock(&rc->reloc_root_tree.lock);
 		rb_node = tree_search(&rc->reloc_root_tree.rb_root,
 				      root->node->start);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index ff5f6c719976..9ee0aca134fc 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1930,6 +1930,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 		return ret;
 	}
 
+	btrfs_trans_release_metadata(trans);
+	trans->block_rsv = NULL;
+
 	/* make a pass through all the delayed refs we have so far
 	 * any runnings procs may add more while we are here
 	 */
@@ -1939,9 +1942,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 		return ret;
 	}
 
-	btrfs_trans_release_metadata(trans);
-	trans->block_rsv = NULL;
-
 	cur_trans = trans->transaction;
 
 	/*
@@ -2281,15 +2281,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 
 	kmem_cache_free(btrfs_trans_handle_cachep, trans);
 
-	/*
-	 * If fs has been frozen, we can not handle delayed iputs, otherwise
-	 * it'll result in deadlock about SB_FREEZE_FS.
-	 */
-	if (current != fs_info->transaction_kthread &&
-	    current != fs_info->cleaner_kthread &&
-	    !test_bit(BTRFS_FS_FROZEN, &fs_info->flags))
-		btrfs_run_delayed_iputs(fs_info);
-
 	return ret;
 
 scrub_continue:
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 84b00a29d531..8b3f14a1adf0 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -258,6 +258,13 @@ struct walk_control {
 	/* what stage of the replay code we're currently in */
 	int stage;
 
+	/*
+	 * Ignore any items from the inode currently being processed. Needs
+	 * to be set every time we find a BTRFS_INODE_ITEM_KEY and we are in
+	 * the LOG_WALK_REPLAY_INODES stage.
+	 */
+	bool ignore_cur_inode;
+
 	/* the root we are currently replaying */
 	struct btrfs_root *replay_dest;
 
@@ -2492,6 +2499,20 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
 
 			inode_item = btrfs_item_ptr(eb, i,
 					    struct btrfs_inode_item);
+			/*
+			 * If we have a tmpfile (O_TMPFILE) that got fsync'ed
+			 * and never got linked before the fsync, skip it, as
+			 * replaying it is pointless since it would be deleted
+			 * later. We skip logging tmpfiles, but it's always
+			 * possible we are replaying a log created with a kernel
+			 * that used to log tmpfiles.
+			 */
+			if (btrfs_inode_nlink(eb, inode_item) == 0) {
+				wc->ignore_cur_inode = true;
+				continue;
+			} else {
+				wc->ignore_cur_inode = false;
+			}
 			ret = replay_xattr_deletes(wc->trans, root, log,
 						   path, key.objectid);
 			if (ret)
@@ -2529,16 +2550,8 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
 					     root->fs_info->sectorsize);
 				ret = btrfs_drop_extents(wc->trans, root, inode,
 							 from, (u64)-1, 1);
-				/*
-				 * If the nlink count is zero here, the iput
-				 * will free the inode.  We bump it to make
-				 * sure it doesn't get freed until the link
-				 * count fixup is done.
-				 */
 				if (!ret) {
-					if (inode->i_nlink == 0)
-						inc_nlink(inode);
-					/* Update link count and nbytes. */
+					/* Update the inode's nbytes. */
 					ret = btrfs_update_inode(wc->trans,
 								 root, inode);
 				}
@@ -2553,6 +2566,9 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
 				break;
 		}
 
+		if (wc->ignore_cur_inode)
+			continue;
+
 		if (key.type == BTRFS_DIR_INDEX_KEY &&
 		    wc->stage == LOG_WALK_REPLAY_DIR_INDEX) {
 			ret = replay_one_dir_item(wc->trans, root, path,
@@ -3209,9 +3225,12 @@ static void free_log_tree(struct btrfs_trans_handle *trans,
 	};
 
 	ret = walk_log_tree(trans, log, &wc);
-	/* I don't think this can happen but just in case */
-	if (ret)
-		btrfs_abort_transaction(trans, ret);
+	if (ret) {
+		if (trans)
+			btrfs_abort_transaction(trans, ret);
+		else
+			btrfs_handle_fs_error(log->fs_info, ret, NULL);
+	}
 
 	while (1) {
 		ret = find_first_extent_bit(&log->dirty_log_pages,
@@ -4505,7 +4524,6 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 
 	INIT_LIST_HEAD(&extents);
 
-	down_write(&inode->dio_sem);
 	write_lock(&tree->lock);
 	test_gen = root->fs_info->last_trans_committed;
 	logged_start = start;
@@ -4586,7 +4604,6 @@ process:
 	}
 	WARN_ON(!list_empty(&extents));
 	write_unlock(&tree->lock);
-	up_write(&inode->dio_sem);
 
 	btrfs_release_path(path);
 	if (!ret)
@@ -4784,7 +4801,8 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
 			ASSERT(len == i_size ||
 			       (len == fs_info->sectorsize &&
 				btrfs_file_extent_compression(leaf, extent) !=
-				BTRFS_COMPRESS_NONE));
+				BTRFS_COMPRESS_NONE) ||
+			       (len < i_size && i_size < fs_info->sectorsize));
 			return 0;
 		}
 
@@ -5718,9 +5736,33 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
 
 			dir_inode = btrfs_iget(fs_info->sb, &inode_key,
 					       root, NULL);
-			/* If parent inode was deleted, skip it. */
-			if (IS_ERR(dir_inode))
-				continue;
+			/*
+			 * If the parent inode was deleted, return an error to
+			 * fallback to a transaction commit. This is to prevent
+			 * getting an inode that was moved from one parent A to
+			 * a parent B, got its former parent A deleted and then
+			 * it got fsync'ed, from existing at both parents after
+			 * a log replay (and the old parent still existing).
+			 * Example:
+			 *
+			 * mkdir /mnt/A
+			 * mkdir /mnt/B
+			 * touch /mnt/B/bar
+			 * sync
+			 * mv /mnt/B/bar /mnt/A/bar
+			 * mv -T /mnt/A /mnt/B
+			 * fsync /mnt/B/bar
+			 * <power fail>
+			 *
+			 * If we ignore the old parent B which got deleted,
+			 * after a log replay we would have file bar linked
+			 * at both parents and the old parent B would still
+			 * exist.
+			 */
+			if (IS_ERR(dir_inode)) {
+				ret = PTR_ERR(dir_inode);
+				goto out;
+			}
 
 			if (ctx)
 				ctx->log_new_dentries = false;
@@ -5794,7 +5836,13 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto end_no_trans;
 
-	if (btrfs_inode_in_log(inode, trans->transid)) {
+	/*
+	 * Skip already logged inodes or inodes corresponding to tmpfiles
+	 * (since logging them is pointless, a link count of 0 means they
+	 * will never be accessible).
+	 */
+	if (btrfs_inode_in_log(inode, trans->transid) ||
+	    inode->vfs_inode.i_nlink == 0) {
 		ret = BTRFS_NO_LOG_SYNC;
 		goto end_no_trans;
 	}