summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-01-14 05:55:51 +1200
committerLinus Torvalds <torvalds@linux-foundation.org>2019-01-14 05:55:51 +1200
commit6b529fb0a3eabf9c4cc3e94c11477250379ce6d8 (patch)
tree132133ceb3eef791ea98d288041616d5eb9fdcf8
parent72d657dd2115804b93bde4b77e426cc2de70eebf (diff)
parent1b3922a8bc74231f9a767d1be6d9a061a4d4eeab (diff)
downloadlinux-6b529fb0a3eabf9c4cc3e94c11477250379ce6d8.tar.bz2
Merge tag 'for-5.0-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fixes from David Sterba: - two regression fixes in clone/dedupe ioctls, the generic check callback needs to lock extents properly and wait for io to avoid problems with writeback and relocation - fix deadlock when using free space tree due to block group creation - a recently added check refuses a valid fileystem with seeding device, make that work again with a quickfix, proper solution needs more intrusive changes * tag 'for-5.0-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: btrfs: Use real device structure to verify dev extent Btrfs: fix deadlock when using free space tree due to block group creation Btrfs: fix race between reflink/dedupe and relocation Btrfs: fix race between cloning range ending at eof and writeback
-rw-r--r--fs/btrfs/ctree.c16
-rw-r--r--fs/btrfs/ioctl.c49
-rw-r--r--fs/btrfs/volumes.c12
3 files changed, 64 insertions, 13 deletions
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index d92462fe66c8..f64aad613727 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1016,19 +1016,21 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
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.
+ * If we are COWing a node/leaf from the extent, chunk, device or free
+ * space 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.
+ * group modifies the extent, chunk, device and free space 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)
+ root == fs_info->dev_root ||
+ root == fs_info->free_space_root)
trans->can_flush_pending_bgs = false;
cow = btrfs_alloc_tree_block(trans, root, parent_start,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index fab9443f6a42..9c8e1734429c 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3221,6 +3221,26 @@ static void btrfs_double_inode_lock(struct inode *inode1, struct inode *inode2)
inode_lock_nested(inode2, I_MUTEX_CHILD);
}
+static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
+ struct inode *inode2, u64 loff2, u64 len)
+{
+ unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
+ unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
+}
+
+static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
+ struct inode *inode2, u64 loff2, u64 len)
+{
+ if (inode1 < inode2) {
+ swap(inode1, inode2);
+ swap(loff1, loff2);
+ } else if (inode1 == inode2 && loff2 < loff1) {
+ swap(loff1, loff2);
+ }
+ lock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
+ lock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
+}
+
static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen,
struct inode *dst, u64 dst_loff)
{
@@ -3242,11 +3262,12 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen,
return -EINVAL;
/*
- * Lock destination range to serialize with concurrent readpages().
+ * Lock destination range to serialize with concurrent readpages() and
+ * source range to serialize with relocation.
*/
- lock_extent(&BTRFS_I(dst)->io_tree, dst_loff, dst_loff + len - 1);
+ btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
ret = btrfs_clone(src, dst, loff, olen, len, dst_loff, 1);
- unlock_extent(&BTRFS_I(dst)->io_tree, dst_loff, dst_loff + len - 1);
+ btrfs_double_extent_unlock(src, loff, dst, dst_loff, len);
return ret;
}
@@ -3905,17 +3926,33 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src,
len = ALIGN(src->i_size, bs) - off;
if (destoff > inode->i_size) {
+ const u64 wb_start = ALIGN_DOWN(inode->i_size, bs);
+
ret = btrfs_cont_expand(inode, inode->i_size, destoff);
if (ret)
return ret;
+ /*
+ * We may have truncated the last block if the inode's size is
+ * not sector size aligned, so we need to wait for writeback to
+ * complete before proceeding further, otherwise we can race
+ * with cloning and attempt to increment a reference to an
+ * extent that no longer exists (writeback completed right after
+ * we found the previous extent covering eof and before we
+ * attempted to increment its reference count).
+ */
+ ret = btrfs_wait_ordered_range(inode, wb_start,
+ destoff - wb_start);
+ if (ret)
+ return ret;
}
/*
- * Lock destination range to serialize with concurrent readpages().
+ * Lock destination range to serialize with concurrent readpages() and
+ * source range to serialize with relocation.
*/
- lock_extent(&BTRFS_I(inode)->io_tree, destoff, destoff + len - 1);
+ btrfs_double_extent_lock(src, off, inode, destoff, len);
ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
- unlock_extent(&BTRFS_I(inode)->io_tree, destoff, destoff + len - 1);
+ btrfs_double_extent_unlock(src, off, inode, destoff, len);
/*
* Truncate page cache pages so that future reads will see the cloned
* data immediately and not the previous data.
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 2576b1a379c9..3e4f8f88353e 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -7825,6 +7825,18 @@ static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
ret = -EUCLEAN;
goto out;
}
+
+ /* It's possible this device is a dummy for seed device */
+ if (dev->disk_total_bytes == 0) {
+ dev = find_device(fs_info->fs_devices->seed, devid, NULL);
+ if (!dev) {
+ btrfs_err(fs_info, "failed to find seed devid %llu",
+ devid);
+ ret = -EUCLEAN;
+ goto out;
+ }
+ }
+
if (physical_offset + physical_len > dev->disk_total_bytes) {
btrfs_err(fs_info,
"dev extent devid %llu physical offset %llu len %llu is beyond device boundary %llu",