summaryrefslogtreecommitdiff
path: root/fs/btrfs/extent_io.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-02-21 08:45:07 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2024-02-21 08:45:07 -0800
commit8da8d88455ebbb4e05423cf60cff985e92d43754 (patch)
treea24dd9b83769e9b3cae9fe44b4c377d9288ca325 /fs/btrfs/extent_io.c
parentd8be5a55b8e3f7eab8f36ceed2512f457f914318 (diff)
parentb0ad381fa7690244802aed119b478b4bdafc31dd (diff)
Merge tag 'for-6.8-rc5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fixes from David Sterba: - Fix a deadlock in fiemap. There was a big lock around the whole operation that can interfere with a page fault and mkwrite. Reducing the lock scope can also speed up fiemap - Fix range condition for extent defragmentation which could lead to worse layout in some cases * tag 'for-6.8-rc5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: btrfs: fix deadlock with fiemap and extent locking btrfs: defrag: avoid unnecessary defrag caused by incorrect extent size
Diffstat (limited to 'fs/btrfs/extent_io.c')
-rw-r--r--fs/btrfs/extent_io.c62
1 files changed, 45 insertions, 17 deletions
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index cfd2967f04a2..3e19a2475ab3 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2689,16 +2689,34 @@ static int fiemap_process_hole(struct btrfs_inode *inode,
* it beyond i_size.
*/
while (cur_offset < end && cur_offset < i_size) {
+ struct extent_state *cached_state = NULL;
u64 delalloc_start;
u64 delalloc_end;
u64 prealloc_start;
+ u64 lockstart;
+ u64 lockend;
u64 prealloc_len = 0;
bool delalloc;
+ lockstart = round_down(cur_offset, inode->root->fs_info->sectorsize);
+ lockend = round_up(end, inode->root->fs_info->sectorsize);
+
+ /*
+ * We are only locking for the delalloc range because that's the
+ * only thing that can change here. With fiemap we have a lock
+ * on the inode, so no buffered or direct writes can happen.
+ *
+ * However mmaps and normal page writeback will cause this to
+ * change arbitrarily. We have to lock the extent lock here to
+ * make sure that nobody messes with the tree while we're doing
+ * btrfs_find_delalloc_in_range.
+ */
+ lock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
delalloc = btrfs_find_delalloc_in_range(inode, cur_offset, end,
delalloc_cached_state,
&delalloc_start,
&delalloc_end);
+ unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
if (!delalloc)
break;
@@ -2866,15 +2884,15 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
u64 start, u64 len)
{
const u64 ino = btrfs_ino(inode);
- struct extent_state *cached_state = NULL;
struct extent_state *delalloc_cached_state = NULL;
struct btrfs_path *path;
struct fiemap_cache cache = { 0 };
struct btrfs_backref_share_check_ctx *backref_ctx;
u64 last_extent_end;
u64 prev_extent_end;
- u64 lockstart;
- u64 lockend;
+ u64 range_start;
+ u64 range_end;
+ const u64 sectorsize = inode->root->fs_info->sectorsize;
bool stopped = false;
int ret;
@@ -2885,12 +2903,11 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
goto out;
}
- lockstart = round_down(start, inode->root->fs_info->sectorsize);
- lockend = round_up(start + len, inode->root->fs_info->sectorsize);
- prev_extent_end = lockstart;
+ range_start = round_down(start, sectorsize);
+ range_end = round_up(start + len, sectorsize);
+ prev_extent_end = range_start;
btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED);
- lock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
ret = fiemap_find_last_extent_offset(inode, path, &last_extent_end);
if (ret < 0)
@@ -2898,7 +2915,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
btrfs_release_path(path);
path->reada = READA_FORWARD;
- ret = fiemap_search_slot(inode, path, lockstart);
+ ret = fiemap_search_slot(inode, path, range_start);
if (ret < 0) {
goto out_unlock;
} else if (ret > 0) {
@@ -2910,7 +2927,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
goto check_eof_delalloc;
}
- while (prev_extent_end < lockend) {
+ while (prev_extent_end < range_end) {
struct extent_buffer *leaf = path->nodes[0];
struct btrfs_file_extent_item *ei;
struct btrfs_key key;
@@ -2933,19 +2950,19 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
* The first iteration can leave us at an extent item that ends
* before our range's start. Move to the next item.
*/
- if (extent_end <= lockstart)
+ if (extent_end <= range_start)
goto next_item;
backref_ctx->curr_leaf_bytenr = leaf->start;
/* We have in implicit hole (NO_HOLES feature enabled). */
if (prev_extent_end < key.offset) {
- const u64 range_end = min(key.offset, lockend) - 1;
+ const u64 hole_end = min(key.offset, range_end) - 1;
ret = fiemap_process_hole(inode, fieinfo, &cache,
&delalloc_cached_state,
backref_ctx, 0, 0, 0,
- prev_extent_end, range_end);
+ prev_extent_end, hole_end);
if (ret < 0) {
goto out_unlock;
} else if (ret > 0) {
@@ -2955,7 +2972,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
}
/* We've reached the end of the fiemap range, stop. */
- if (key.offset >= lockend) {
+ if (key.offset >= range_end) {
stopped = true;
break;
}
@@ -3049,29 +3066,41 @@ check_eof_delalloc:
btrfs_free_path(path);
path = NULL;
- if (!stopped && prev_extent_end < lockend) {
+ if (!stopped && prev_extent_end < range_end) {
ret = fiemap_process_hole(inode, fieinfo, &cache,
&delalloc_cached_state, backref_ctx,
- 0, 0, 0, prev_extent_end, lockend - 1);
+ 0, 0, 0, prev_extent_end, range_end - 1);
if (ret < 0)
goto out_unlock;
- prev_extent_end = lockend;
+ prev_extent_end = range_end;
}
if (cache.cached && cache.offset + cache.len >= last_extent_end) {
const u64 i_size = i_size_read(&inode->vfs_inode);
if (prev_extent_end < i_size) {
+ struct extent_state *cached_state = NULL;
u64 delalloc_start;
u64 delalloc_end;
+ u64 lockstart;
+ u64 lockend;
bool delalloc;
+ lockstart = round_down(prev_extent_end, sectorsize);
+ lockend = round_up(i_size, sectorsize);
+
+ /*
+ * See the comment in fiemap_process_hole as to why
+ * we're doing the locking here.
+ */
+ lock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
delalloc = btrfs_find_delalloc_in_range(inode,
prev_extent_end,
i_size - 1,
&delalloc_cached_state,
&delalloc_start,
&delalloc_end);
+ unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
if (!delalloc)
cache.flags |= FIEMAP_EXTENT_LAST;
} else {
@@ -3082,7 +3111,6 @@ check_eof_delalloc:
ret = emit_last_fiemap_cache(fieinfo, &cache);
out_unlock:
- unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
out:
free_extent_state(delalloc_cached_state);