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

…/git/mason/linux-btrfs

Pull btrfs fixes from Chris Mason:
 "This has our collection of bug fixes.  I missed the last rc because I
  thought our patches were making NFS crash during my xfs test runs.
  Turns out it was an NFS client bug fixed by someone else while I tried
  to bisect it.

  All of these fixes are small, but some are fairly high impact.  The
  biggest are fixes for our mount -o remount handling, a deadlock due to
  GFP_KERNEL allocations in readdir, and a RAID10 error handling bug.

  This was tested against both 3.3 and Linus' master as of this morning."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (26 commits)
  Btrfs: reduce lock contention during extent insertion
  Btrfs: avoid deadlocks from GFP_KERNEL allocations during btrfs_real_readdir
  Btrfs: Fix space checking during fs resize
  Btrfs: fix block_rsv and space_info lock ordering
  Btrfs: Prevent root_list corruption
  Btrfs: fix repair code for RAID10
  Btrfs: do not start delalloc inodes during sync
  Btrfs: fix that check_int_data mount option was ignored
  Btrfs: don't count CRC or header errors twice while scrubbing
  Btrfs: fix btrfs_ioctl_dev_info() crash on missing device
  btrfs: don't return EINTR
  Btrfs: double unlock bug in error handling
  Btrfs: always store the mirror we read the eb from
  fs/btrfs/volumes.c: add missing free_fs_devices
  btrfs: fix early abort in 'remount'
  Btrfs: fix max chunk size check in chunk allocator
  Btrfs: add missing read locks in backref.c
  Btrfs: don't call free_extent_buffer twice in iterate_irefs
  Btrfs: Make free_ipath() deal gracefully with NULL pointers
  Btrfs: avoid possible use-after-free in clear_extent_bit()
  ...

fs/btrfs/backref.c

@@ -22,6 +22,7 @@
 #include "ulist.h"
 #include "transaction.h"
 #include "delayed-ref.h"
+#include "locking.h"
 
 /*
  * this structure records all encountered refs on the way up to the root
@@ -893,18 +894,22 @@ static char *iref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 	s64 bytes_left = size - 1;
 	struct extent_buffer *eb = eb_in;
 	struct btrfs_key found_key;
+	int leave_spinning = path->leave_spinning;
 
 	if (bytes_left >= 0)
 		dest[bytes_left] = '\0';
 
+	path->leave_spinning = 1;
 	while (1) {
 		len = btrfs_inode_ref_name_len(eb, iref);
 		bytes_left -= len;
 		if (bytes_left >= 0)
 			read_extent_buffer(eb, dest + bytes_left,
 						(unsigned long)(iref + 1), len);
-		if (eb != eb_in)
+		if (eb != eb_in) {
+			btrfs_tree_read_unlock_blocking(eb);
 			free_extent_buffer(eb);
+		}
 		ret = inode_ref_info(parent, 0, fs_root, path, &found_key);
 		if (ret > 0)
 			ret = -ENOENT;
@@ -919,8 +924,11 @@ static char *iref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 		slot = path->slots[0];
 		eb = path->nodes[0];
 		/* make sure we can use eb after releasing the path */
-		if (eb != eb_in)
+		if (eb != eb_in) {
 			atomic_inc(&eb->refs);
+			btrfs_tree_read_lock(eb);
+			btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+		}
 		btrfs_release_path(path);
 
 		iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref);
@@ -931,6 +939,7 @@ static char *iref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
 	}
 
 	btrfs_release_path(path);
+	path->leave_spinning = leave_spinning;
 
 	if (ret)
 		return ERR_PTR(ret);
@@ -1247,7 +1256,7 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root,
 				struct btrfs_path *path,
 				iterate_irefs_t *iterate, void *ctx)
 {
-	int ret;
+	int ret = 0;
 	int slot;
 	u32 cur;
 	u32 len;
@@ -1259,7 +1268,8 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root,
 	struct btrfs_inode_ref *iref;
 	struct btrfs_key found_key;
 
-	while (1) {
+	while (!ret) {
+		path->leave_spinning = 1;
 		ret = inode_ref_info(inum, parent ? parent+1 : 0, fs_root, path,
 					&found_key);
 		if (ret < 0)
@@ -1275,6 +1285,8 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root,
 		eb = path->nodes[0];
 		/* make sure we can use eb after releasing the path */
 		atomic_inc(&eb->refs);
+		btrfs_tree_read_lock(eb);
+		btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
 		btrfs_release_path(path);
 
 		item = btrfs_item_nr(eb, slot);
@@ -1288,13 +1300,12 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root,
 				 (unsigned long long)found_key.objectid,
 				 (unsigned long long)fs_root->objectid);
 			ret = iterate(parent, iref, eb, ctx);
-			if (ret) {
-				free_extent_buffer(eb);
+			if (ret)
 				break;
-			}
 			len = sizeof(*iref) + name_len;
 			iref = (struct btrfs_inode_ref *)((char *)iref + len);
 		}
+		btrfs_tree_read_unlock_blocking(eb);
 		free_extent_buffer(eb);
 	}
 
@@ -1414,6 +1425,8 @@ struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root,
 
 void free_ipath(struct inode_fs_paths *ipath)
 {
+	if (!ipath)
+		return;
 	kfree(ipath->fspath);
 	kfree(ipath);
 }

fs/btrfs/ctree.h

@@ -1078,7 +1078,7 @@ struct btrfs_fs_info {
 	 * is required instead of the faster short fsync log commits
 	 */
 	u64 last_trans_log_full_commit;
-	unsigned long mount_opt:21;
+	unsigned long mount_opt;
 	unsigned long compress_type:4;
 	u64 max_inline;
 	u64 alloc_start;

fs/btrfs/disk-io.c

@@ -383,17 +383,16 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root,
 		if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags))
 			break;
 
-		if (!failed_mirror) {
-			failed = 1;
-			printk(KERN_ERR "failed mirror was %d\n", eb->failed_mirror);
-			failed_mirror = eb->failed_mirror;
-		}
-
 		num_copies = btrfs_num_copies(&root->fs_info->mapping_tree,
 					      eb->start, eb->len);
 		if (num_copies == 1)
 			break;
 
+		if (!failed_mirror) {
+			failed = 1;
+			failed_mirror = eb->read_mirror;
+		}
+
 		mirror_num++;
 		if (mirror_num == failed_mirror)
 			mirror_num++;
@@ -564,7 +563,7 @@ struct extent_buffer *find_eb_for_page(struct extent_io_tree *tree,
 }
 
 static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
-			       struct extent_state *state)
+			       struct extent_state *state, int mirror)
 {
 	struct extent_io_tree *tree;
 	u64 found_start;
@@ -589,6 +588,7 @@ static int btree_readpage_end_io_hook(struct page *page, u64 start, u64 end,
 	if (!reads_done)
 		goto err;
 
+	eb->read_mirror = mirror;
 	if (test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
 		ret = -EIO;
 		goto err;
@@ -652,7 +652,7 @@ static int btree_io_failed_hook(struct page *page, int failed_mirror)
 
 	eb = (struct extent_buffer *)page->private;
 	set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
-	eb->failed_mirror = failed_mirror;
+	eb->read_mirror = failed_mirror;
 	if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
 		btree_readahead_hook(root, eb, eb->start, -EIO);
 	return -EIO;	/* we fixed nothing */
@@ -2254,9 +2254,9 @@ int open_ctree(struct super_block *sb,
 		goto fail_sb_buffer;
 	}
 
-	if (sectorsize < PAGE_SIZE) {
-		printk(KERN_WARNING "btrfs: Incompatible sector size "
-		       "found on %s\n", sb->s_id);
+	if (sectorsize != PAGE_SIZE) {
+		printk(KERN_WARNING "btrfs: Incompatible sector size(%lu) "
+		       "found on %s\n", (unsigned long)sectorsize, sb->s_id);
 		goto fail_sb_buffer;
 	}
 

fs/btrfs/extent-tree.c

@@ -2301,6 +2301,7 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
 
 				if (ret) {
 					printk(KERN_DEBUG "btrfs: run_delayed_extent_op returned %d\n", ret);
+					spin_lock(&delayed_refs->lock);
 					return ret;
 				}
 
@@ -2331,6 +2332,7 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans,
 
 		if (ret) {
 			printk(KERN_DEBUG "btrfs: run_one_delayed_ref returned %d\n", ret);
+			spin_lock(&delayed_refs->lock);
 			return ret;
 		}
 
@@ -3769,13 +3771,10 @@ static int reserve_metadata_bytes(struct btrfs_root *root,
 		 */
 		if (current->journal_info)
 			return -EAGAIN;
-		ret = wait_event_interruptible(space_info->wait,
-					       !space_info->flush);
-		/* Must have been interrupted, return */
-		if (ret) {
-			printk(KERN_DEBUG "btrfs: %s returning -EINTR\n", __func__);
+		ret = wait_event_killable(space_info->wait, !space_info->flush);
+		/* Must have been killed, return */
+		if (ret)
 			return -EINTR;
-		}
 
 		spin_lock(&space_info->lock);
 	}
@@ -4215,8 +4214,8 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
 
 	num_bytes = calc_global_metadata_size(fs_info);
 
-	spin_lock(&block_rsv->lock);
 	spin_lock(&sinfo->lock);
+	spin_lock(&block_rsv->lock);
 
 	block_rsv->size = num_bytes;
 
@@ -4242,8 +4241,8 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
 		block_rsv->full = 1;
 	}
 
-	spin_unlock(&sinfo->lock);
 	spin_unlock(&block_rsv->lock);
+	spin_unlock(&sinfo->lock);
 }
 
 static void init_global_block_rsv(struct btrfs_fs_info *fs_info)

fs/btrfs/extent_io.c

@@ -402,20 +402,28 @@ static int split_state(struct extent_io_tree *tree, struct extent_state *orig,
 	return 0;
 }
 
+static struct extent_state *next_state(struct extent_state *state)
+{
+	struct rb_node *next = rb_next(&state->rb_node);
+	if (next)
+		return rb_entry(next, struct extent_state, rb_node);
+	else
+		return NULL;
+}
+
 /*
  * utility function to clear some bits in an extent state struct.
- * it will optionally wake up any one waiting on this state (wake == 1), or
- * forcibly remove the state from the tree (delete == 1).
+ * it will optionally wake up any one waiting on this state (wake == 1)
  *
  * If no bits are set on the state struct after clearing things, the
  * struct is freed and removed from the tree
  */
-static int clear_state_bit(struct extent_io_tree *tree,
-			    struct extent_state *state,
-			    int *bits, int wake)
+static struct extent_state *clear_state_bit(struct extent_io_tree *tree,
+					    struct extent_state *state,
+					    int *bits, int wake)
 {
+	struct extent_state *next;
 	int bits_to_clear = *bits & ~EXTENT_CTLBITS;
-	int ret = state->state & bits_to_clear;
 
 	if ((bits_to_clear & EXTENT_DIRTY) && (state->state & EXTENT_DIRTY)) {
 		u64 range = state->end - state->start + 1;
@@ -427,6 +435,7 @@ static int clear_state_bit(struct extent_io_tree *tree,
 	if (wake)
 		wake_up(&state->wq);
 	if (state->state == 0) {
+		next = next_state(state);
 		if (state->tree) {
 			rb_erase(&state->rb_node, &tree->state);
 			state->tree = NULL;
@@ -436,8 +445,9 @@ static int clear_state_bit(struct extent_io_tree *tree,
 		}
 	} else {
 		merge_state(tree, state);
+		next = next_state(state);
 	}
-	return ret;
+	return next;
 }
 
 static struct extent_state *
@@ -476,7 +486,6 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	struct extent_state *state;
 	struct extent_state *cached;
 	struct extent_state *prealloc = NULL;
-	struct rb_node *next_node;
 	struct rb_node *node;
 	u64 last_end;
 	int err;
@@ -528,14 +537,11 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	WARN_ON(state->end < start);
 	last_end = state->end;
 
-	if (state->end < end && !need_resched())
-		next_node = rb_next(&state->rb_node);
-	else
-		next_node = NULL;
-
 	/* the state doesn't have the wanted bits, go ahead */
-	if (!(state->state & bits))
+	if (!(state->state & bits)) {
+		state = next_state(state);
 		goto next;
+	}
 
 	/*
 	 *     | ---- desired range ---- |
@@ -593,16 +599,13 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		goto out;
 	}
 
-	clear_state_bit(tree, state, &bits, wake);
+	state = clear_state_bit(tree, state, &bits, wake);
 next:
 	if (last_end == (u64)-1)
 		goto out;
 	start = last_end + 1;
-	if (start <= end && next_node) {
-		state = rb_entry(next_node, struct extent_state,
-				 rb_node);
+	if (start <= end && state && !need_resched())
 		goto hit_next;
-	}
 	goto search_again;
 
 out:
@@ -2301,7 +2304,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 	u64 start;
 	u64 end;
 	int whole_page;
-	int failed_mirror;
+	int mirror;
 	int ret;
 
 	if (err)
@@ -2340,20 +2343,18 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 		}
 		spin_unlock(&tree->lock);
 
+		mirror = (int)(unsigned long)bio->bi_bdev;
 		if (uptodate && tree->ops && tree->ops->readpage_end_io_hook) {
 			ret = tree->ops->readpage_end_io_hook(page, start, end,
-							      state);
+							      state, mirror);
 			if (ret)
 				uptodate = 0;
 			else
 				clean_io_failure(start, page);
 		}
 
-		if (!uptodate)
-			failed_mirror = (int)(unsigned long)bio->bi_bdev;
-
 		if (!uptodate && tree->ops && tree->ops->readpage_io_failed_hook) {
-			ret = tree->ops->readpage_io_failed_hook(page, failed_mirror);
+			ret = tree->ops->readpage_io_failed_hook(page, mirror);
 			if (!ret && !err &&
 			    test_bit(BIO_UPTODATE, &bio->bi_flags))
 				uptodate = 1;
@@ -2368,8 +2369,7 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 			 * can't handle the error it will return -EIO and we
 			 * remain responsible for that page.
 			 */
-			ret = bio_readpage_error(bio, page, start, end,
-							failed_mirror, NULL);
+			ret = bio_readpage_error(bio, page, start, end, mirror, NULL);
 			if (ret == 0) {
 				uptodate =
 					test_bit(BIO_UPTODATE, &bio->bi_flags);
@@ -4462,7 +4462,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 	}
 
 	clear_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
-	eb->failed_mirror = 0;
+	eb->read_mirror = 0;
 	atomic_set(&eb->io_pages, num_reads);
 	for (i = start_i; i < num_pages; i++) {
 		page = extent_buffer_page(eb, i);

fs/btrfs/extent_io.h

@@ -79,7 +79,7 @@ struct extent_io_ops {
 					u64 start, u64 end,
 				       struct extent_state *state);
 	int (*readpage_end_io_hook)(struct page *page, u64 start, u64 end,
-				    struct extent_state *state);
+				    struct extent_state *state, int mirror);
 	int (*writepage_end_io_hook)(struct page *page, u64 start, u64 end,
 				      struct extent_state *state, int uptodate);
 	void (*set_bit_hook)(struct inode *inode, struct extent_state *state,
@@ -135,7 +135,7 @@ struct extent_buffer {
 	spinlock_t refs_lock;
 	atomic_t refs;
 	atomic_t io_pages;
-	int failed_mirror;
+	int read_mirror;
 	struct list_head leak_list;
 	struct rcu_head rcu_head;
 	pid_t lock_owner;