summaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/ctree.c2
-rw-r--r--fs/btrfs/extent_io.c29
-rw-r--r--fs/btrfs/extent_map.c83
-rw-r--r--fs/btrfs/file.c13
-rw-r--r--fs/btrfs/inode.c17
-rw-r--r--fs/btrfs/ordered-data.c12
-rw-r--r--fs/btrfs/qgroup.c11
-rw-r--r--fs/btrfs/sysfs.c4
-rw-r--r--fs/btrfs/tests/delayed-refs-tests.c1
-rw-r--r--fs/btrfs/transaction.c4
-rw-r--r--fs/btrfs/volumes.c7
11 files changed, 130 insertions, 53 deletions
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 92071ca0655f..3dc5a35dd19b 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1496,6 +1496,7 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
if (!p->skip_locking) {
btrfs_unlock_up_safe(p, parent_level + 1);
+ btrfs_maybe_reset_lockdep_class(root, tmp);
tmp_locked = true;
btrfs_tree_read_lock(tmp);
btrfs_release_path(p);
@@ -1539,6 +1540,7 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
if (!p->skip_locking) {
ASSERT(ret == -EAGAIN);
+ btrfs_maybe_reset_lockdep_class(root, tmp);
tmp_locked = true;
btrfs_tree_read_lock(tmp);
btrfs_release_path(p);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index a2cac9d0a1a9..b2fae67f8fa3 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -523,8 +523,6 @@ static void end_bbio_data_read(struct btrfs_bio *bbio)
u64 end;
u32 len;
- /* For now only order 0 folios are supported for data. */
- ASSERT(folio_order(folio) == 0);
btrfs_debug(fs_info,
"%s: bi_sector=%llu, err=%d, mirror=%u",
__func__, bio->bi_iter.bi_sector, bio->bi_status,
@@ -552,7 +550,6 @@ static void end_bbio_data_read(struct btrfs_bio *bbio)
if (likely(uptodate)) {
loff_t i_size = i_size_read(inode);
- pgoff_t end_index = i_size >> folio_shift(folio);
/*
* Zero out the remaining part if this range straddles
@@ -561,9 +558,11 @@ static void end_bbio_data_read(struct btrfs_bio *bbio)
* Here we should only zero the range inside the folio,
* not touch anything else.
*
- * NOTE: i_size is exclusive while end is inclusive.
+ * NOTE: i_size is exclusive while end is inclusive and
+ * folio_contains() takes PAGE_SIZE units.
*/
- if (folio_index(folio) == end_index && i_size <= end) {
+ if (folio_contains(folio, i_size >> PAGE_SHIFT) &&
+ i_size <= end) {
u32 zero_start = max(offset_in_folio(folio, i_size),
offset_in_folio(folio, start));
u32 zero_len = offset_in_folio(folio, end) + 1 -
@@ -899,7 +898,6 @@ static struct extent_map *get_extent_map(struct btrfs_inode *inode,
u64 len, struct extent_map **em_cached)
{
struct extent_map *em;
- struct extent_state *cached_state = NULL;
ASSERT(em_cached);
@@ -915,14 +913,12 @@ static struct extent_map *get_extent_map(struct btrfs_inode *inode,
*em_cached = NULL;
}
- btrfs_lock_and_flush_ordered_range(inode, start, start + len - 1, &cached_state);
em = btrfs_get_extent(inode, folio, start, len);
if (!IS_ERR(em)) {
BUG_ON(*em_cached);
refcount_inc(&em->refs);
*em_cached = em;
}
- unlock_extent(&inode->io_tree, start, start + len - 1, &cached_state);
return em;
}
@@ -956,7 +952,7 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
return ret;
}
- if (folio->index == last_byte >> folio_shift(folio)) {
+ if (folio_contains(folio, last_byte >> PAGE_SHIFT)) {
size_t zero_offset = offset_in_folio(folio, last_byte);
if (zero_offset) {
@@ -1079,11 +1075,18 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached,
int btrfs_read_folio(struct file *file, struct folio *folio)
{
+ struct btrfs_inode *inode = folio_to_inode(folio);
+ const u64 start = folio_pos(folio);
+ const u64 end = start + folio_size(folio) - 1;
+ struct extent_state *cached_state = NULL;
struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ };
struct extent_map *em_cached = NULL;
int ret;
+ btrfs_lock_and_flush_ordered_range(inode, start, end, &cached_state);
ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl, NULL);
+ unlock_extent(&inode->io_tree, start, end, &cached_state);
+
free_extent_map(em_cached);
/*
@@ -2380,12 +2383,20 @@ void btrfs_readahead(struct readahead_control *rac)
{
struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ | REQ_RAHEAD };
struct folio *folio;
+ struct btrfs_inode *inode = BTRFS_I(rac->mapping->host);
+ const u64 start = readahead_pos(rac);
+ const u64 end = start + readahead_length(rac) - 1;
+ struct extent_state *cached_state = NULL;
struct extent_map *em_cached = NULL;
u64 prev_em_start = (u64)-1;
+ btrfs_lock_and_flush_ordered_range(inode, start, end, &cached_state);
+
while ((folio = readahead_folio(rac)) != NULL)
btrfs_do_readpage(folio, &em_cached, &bio_ctrl, &prev_em_start);
+ unlock_extent(&inode->io_tree, start, end, &cached_state);
+
if (em_cached)
free_extent_map(em_cached);
submit_one_bio(&bio_ctrl);
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 67ce85ff0ae2..7f46abbd6311 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -1128,6 +1128,8 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c
long nr_dropped = 0;
struct rb_node *node;
+ lockdep_assert_held_write(&tree->lock);
+
/*
* Take the mmap lock so that we serialize with the inode logging phase
* of fsync because we may need to set the full sync flag on the inode,
@@ -1139,28 +1141,12 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c
* to find new extents, which may not be there yet because ordered
* extents haven't completed yet.
*
- * We also do a try lock because otherwise we could deadlock. This is
- * because the shrinker for this filesystem may be invoked while we are
- * in a path that is holding the mmap lock in write mode. For example in
- * a reflink operation while COWing an extent buffer, when allocating
- * pages for a new extent buffer and under memory pressure, the shrinker
- * may be invoked, and therefore we would deadlock by attempting to read
- * lock the mmap lock while we are holding already a write lock on it.
+ * We also do a try lock because we don't want to block for too long and
+ * we are holding the extent map tree's lock in write mode.
*/
if (!down_read_trylock(&inode->i_mmap_lock))
return 0;
- /*
- * We want to be fast so if the lock is busy we don't want to spend time
- * waiting for it - either some task is about to do IO for the inode or
- * we may have another task shrinking extent maps, here in this code, so
- * skip this inode.
- */
- if (!write_trylock(&tree->lock)) {
- up_read(&inode->i_mmap_lock);
- return 0;
- }
-
node = rb_first(&tree->root);
while (node) {
struct rb_node *next = rb_next(node);
@@ -1201,12 +1187,61 @@ next:
break;
node = next;
}
- write_unlock(&tree->lock);
up_read(&inode->i_mmap_lock);
return nr_dropped;
}
+static struct btrfs_inode *find_first_inode_to_shrink(struct btrfs_root *root,
+ u64 min_ino)
+{
+ struct btrfs_inode *inode;
+ unsigned long from = min_ino;
+
+ xa_lock(&root->inodes);
+ while (true) {
+ struct extent_map_tree *tree;
+
+ inode = xa_find(&root->inodes, &from, ULONG_MAX, XA_PRESENT);
+ if (!inode)
+ break;
+
+ tree = &inode->extent_tree;
+
+ /*
+ * We want to be fast so if the lock is busy we don't want to
+ * spend time waiting for it (some task is about to do IO for
+ * the inode).
+ */
+ if (!write_trylock(&tree->lock))
+ goto next;
+
+ /*
+ * Skip inode if it doesn't have loaded extent maps, so we avoid
+ * getting a reference and doing an iput later. This includes
+ * cases like files that were opened for things like stat(2), or
+ * files with all extent maps previously released through the
+ * release folio callback (btrfs_release_folio()) or released in
+ * a previous run, or directories which never have extent maps.
+ */
+ if (RB_EMPTY_ROOT(&tree->root)) {
+ write_unlock(&tree->lock);
+ goto next;
+ }
+
+ if (igrab(&inode->vfs_inode))
+ break;
+
+ write_unlock(&tree->lock);
+next:
+ from = btrfs_ino(inode) + 1;
+ cond_resched_lock(&root->inodes.xa_lock);
+ }
+ xa_unlock(&root->inodes);
+
+ return inode;
+}
+
static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx *ctx)
{
struct btrfs_fs_info *fs_info = root->fs_info;
@@ -1214,21 +1249,21 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx
long nr_dropped = 0;
u64 min_ino = fs_info->em_shrinker_last_ino + 1;
- inode = btrfs_find_first_inode(root, min_ino);
+ inode = find_first_inode_to_shrink(root, min_ino);
while (inode) {
nr_dropped += btrfs_scan_inode(inode, ctx);
+ write_unlock(&inode->extent_tree.lock);
min_ino = btrfs_ino(inode) + 1;
fs_info->em_shrinker_last_ino = btrfs_ino(inode);
- btrfs_add_delayed_iput(inode);
+ iput(&inode->vfs_inode);
- if (ctx->scanned >= ctx->nr_to_scan ||
- btrfs_fs_closing(inode->root->fs_info))
+ if (ctx->scanned >= ctx->nr_to_scan || btrfs_fs_closing(fs_info))
break;
cond_resched();
- inode = btrfs_find_first_inode(root, min_ino);
+ inode = find_first_inode_to_shrink(root, min_ino);
}
if (inode) {
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 36f51c311bb1..0b568c8d24cb 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1039,7 +1039,6 @@ int btrfs_write_check(struct kiocb *iocb, size_t count)
loff_t pos = iocb->ki_pos;
int ret;
loff_t oldsize;
- loff_t start_pos;
/*
* Quickly bail out on NOWAIT writes if we don't have the nodatacow or
@@ -1066,9 +1065,8 @@ int btrfs_write_check(struct kiocb *iocb, size_t count)
inode_inc_iversion(inode);
}
- start_pos = round_down(pos, fs_info->sectorsize);
oldsize = i_size_read(inode);
- if (start_pos > oldsize) {
+ if (pos > oldsize) {
/* Expand hole size to cover write data, preventing empty gap */
loff_t end_pos = round_up(pos + count, fs_info->sectorsize);
@@ -1092,7 +1090,7 @@ ssize_t btrfs_buffered_write(struct kiocb *iocb, struct iov_iter *i)
u64 lockend;
size_t num_written = 0;
ssize_t ret;
- loff_t old_isize = i_size_read(inode);
+ loff_t old_isize;
unsigned int ilock_flags = 0;
const bool nowait = (iocb->ki_flags & IOCB_NOWAIT);
unsigned int bdp_flags = (nowait ? BDP_ASYNC : 0);
@@ -1105,6 +1103,13 @@ ssize_t btrfs_buffered_write(struct kiocb *iocb, struct iov_iter *i)
if (ret < 0)
return ret;
+ /*
+ * We can only trust the isize with inode lock held, or it can race with
+ * other buffered writes and cause incorrect call of
+ * pagecache_isize_extended() to overwrite existing data.
+ */
+ old_isize = i_size_read(inode);
+
ret = generic_write_checks(iocb, i);
if (ret <= 0)
goto out;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a9322601ab5c..a9e56c994e9e 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1382,8 +1382,13 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
continue;
}
if (done_offset) {
- *done_offset = start - 1;
- return 0;
+ /*
+ * Move @end to the end of the processed range,
+ * and exit the loop to unlock the processed extents.
+ */
+ end = start - 1;
+ ret = 0;
+ break;
}
ret = -ENOSPC;
}
@@ -6739,18 +6744,18 @@ fail:
return err;
}
-static int btrfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
- struct dentry *dentry, umode_t mode)
+static struct dentry *btrfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
+ struct dentry *dentry, umode_t mode)
{
struct inode *inode;
inode = new_inode(dir->i_sb);
if (!inode)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
inode_init_owner(idmap, inode, dir, S_IFDIR | mode);
inode->i_op = &btrfs_dir_inode_operations;
inode->i_fop = &btrfs_dir_file_operations;
- return btrfs_create_common(dir, dentry, inode);
+ return ERR_PTR(btrfs_create_common(dir, dentry, inode));
}
static noinline int uncompress_inline(struct btrfs_path *path,
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 30eceaf829a7..4aca7475fd82 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -1229,6 +1229,18 @@ struct btrfs_ordered_extent *btrfs_split_ordered_extent(
*/
if (WARN_ON_ONCE(len >= ordered->num_bytes))
return ERR_PTR(-EINVAL);
+ /*
+ * If our ordered extent had an error there's no point in continuing.
+ * The error may have come from a transaction abort done either by this
+ * task or some other concurrent task, and the transaction abort path
+ * iterates over all existing ordered extents and sets the flag
+ * BTRFS_ORDERED_IOERR on them.
+ */
+ if (unlikely(flags & (1U << BTRFS_ORDERED_IOERR))) {
+ const int fs_error = BTRFS_FS_ERROR(fs_info);
+
+ return fs_error ? ERR_PTR(fs_error) : ERR_PTR(-EIO);
+ }
/* We cannot split partially completed ordered extents. */
if (ordered->bytes_left) {
ASSERT(!(flags & ~BTRFS_ORDERED_TYPE_FLAGS));
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index b90fabe302e6..f9d3766c809b 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1880,11 +1880,7 @@ int btrfs_qgroup_cleanup_dropped_subvolume(struct btrfs_fs_info *fs_info, u64 su
* Commit current transaction to make sure all the rfer/excl numbers
* get updated.
*/
- trans = btrfs_start_transaction(fs_info->quota_root, 0);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
-
- ret = btrfs_commit_transaction(trans);
+ ret = btrfs_commit_current_transaction(fs_info->quota_root);
if (ret < 0)
return ret;
@@ -1897,8 +1893,11 @@ int btrfs_qgroup_cleanup_dropped_subvolume(struct btrfs_fs_info *fs_info, u64 su
/*
* It's squota and the subvolume still has numbers needed for future
* accounting, in this case we can not delete it. Just skip it.
+ *
+ * Or the qgroup is already removed by a qgroup rescan. For both cases we're
+ * safe to ignore them.
*/
- if (ret == -EBUSY)
+ if (ret == -EBUSY || ret == -ENOENT)
ret = 0;
return ret;
}
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 53b846d99ece..14f53f757555 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -1330,13 +1330,13 @@ MODULE_PARM_DESC(read_policy,
int btrfs_read_policy_to_enum(const char *str, s64 *value_ret)
{
- char param[32] = { 0 };
+ char param[32];
char __maybe_unused *value_str;
if (!str || strlen(str) == 0)
return 0;
- strncpy(param, str, sizeof(param) - 1);
+ strscpy(param, str);
#ifdef CONFIG_BTRFS_EXPERIMENTAL
/* Separate value from input in policy:value format. */
diff --git a/fs/btrfs/tests/delayed-refs-tests.c b/fs/btrfs/tests/delayed-refs-tests.c
index 6558508c2ddf..265370e79a54 100644
--- a/fs/btrfs/tests/delayed-refs-tests.c
+++ b/fs/btrfs/tests/delayed-refs-tests.c
@@ -1009,6 +1009,7 @@ int btrfs_test_delayed_refs(u32 sectorsize, u32 nodesize)
if (!ret)
ret = select_delayed_refs_test(&trans);
+ kfree(transaction);
out_free_fs_info:
btrfs_free_dummy_fs_info(fs_info);
return ret;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 15312013f2a3..aca83a98b75a 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -274,8 +274,10 @@ loop:
cur_trans = fs_info->running_transaction;
if (cur_trans) {
if (TRANS_ABORTED(cur_trans)) {
+ const int abort_error = cur_trans->aborted;
+
spin_unlock(&fs_info->trans_lock);
- return cur_trans->aborted;
+ return abort_error;
}
if (btrfs_blocked_trans_types[cur_trans->state] & type) {
spin_unlock(&fs_info->trans_lock);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 0a0776489055..3f8afbd1ebb5 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -7155,6 +7155,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
btrfs_err(fs_info,
"failed to add chunk map, start=%llu len=%llu: %d",
map->start, map->chunk_len, ret);
+ btrfs_free_chunk_map(map);
}
return ret;
@@ -7200,8 +7201,12 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info,
fs_devices = find_fsid(fsid, NULL);
if (!fs_devices) {
- if (!btrfs_test_opt(fs_info, DEGRADED))
+ if (!btrfs_test_opt(fs_info, DEGRADED)) {
+ btrfs_err(fs_info,
+ "failed to find fsid %pU when attempting to open seed devices",
+ fsid);
return ERR_PTR(-ENOENT);
+ }
fs_devices = alloc_fs_devices(fsid);
if (IS_ERR(fs_devices))
generated by cgit v1.2.3 (git 2.46.0) at 2025-07-02 21:01:22 +0000