summaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/bio.c33
-rw-r--r--fs/btrfs/ctree.c17
-rw-r--r--fs/btrfs/ctree.h19
-rw-r--r--fs/btrfs/disk-io.c9
-rw-r--r--fs/btrfs/extent-tree.c8
-rw-r--r--fs/btrfs/file.c1
-rw-r--r--fs/btrfs/inode.c171
-rw-r--r--fs/btrfs/ioctl.c132
-rw-r--r--fs/btrfs/locking.h10
-rw-r--r--fs/btrfs/qgroup.c3
-rw-r--r--fs/btrfs/ref-verify.c1
-rw-r--r--fs/btrfs/relocation.c6
-rw-r--r--fs/btrfs/scrub.c4
-rw-r--r--fs/btrfs/send.c6
-rw-r--r--fs/btrfs/super.c66
-rw-r--r--fs/btrfs/sysfs.c10
-rw-r--r--fs/btrfs/tree-checker.c27
-rw-r--r--fs/btrfs/volumes.c4
-rw-r--r--fs/btrfs/zlib.c4
-rw-r--r--fs/btrfs/zoned.c5
20 files changed, 362 insertions, 174 deletions
diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index 1f216d07eff6..7ea6f0b43b95 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -81,6 +81,9 @@ static struct btrfs_bio *btrfs_split_bio(struct btrfs_fs_info *fs_info,
bio = bio_split(&orig_bbio->bio, map_length >> SECTOR_SHIFT, GFP_NOFS,
&btrfs_clone_bioset);
+ if (IS_ERR(bio))
+ return ERR_CAST(bio);
+
bbio = btrfs_bio(bio);
btrfs_bio_init(bbio, fs_info, NULL, orig_bbio);
bbio->inode = orig_bbio->inode;
@@ -355,7 +358,7 @@ static void btrfs_simple_end_io(struct bio *bio)
INIT_WORK(&bbio->end_io_work, btrfs_end_bio_work);
queue_work(btrfs_end_io_wq(fs_info, bio), &bbio->end_io_work);
} else {
- if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status)
+ if (bio_is_zone_append(bio) && !bio->bi_status)
btrfs_record_physical_zoned(bbio);
btrfs_bio_end_io(bbio, bbio->bio.bi_status);
}
@@ -398,7 +401,7 @@ static void btrfs_orig_write_end_io(struct bio *bio)
else
bio->bi_status = BLK_STS_OK;
- if (bio_op(bio) == REQ_OP_ZONE_APPEND && !bio->bi_status)
+ if (bio_is_zone_append(bio) && !bio->bi_status)
stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
btrfs_bio_end_io(bbio, bbio->bio.bi_status);
@@ -412,7 +415,7 @@ static void btrfs_clone_write_end_io(struct bio *bio)
if (bio->bi_status) {
atomic_inc(&stripe->bioc->error);
btrfs_log_dev_io_error(bio, stripe->dev);
- } else if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
+ } else if (bio_is_zone_append(bio)) {
stripe->physical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
}
@@ -649,8 +652,14 @@ static u64 btrfs_append_map_length(struct btrfs_bio *bbio, u64 map_length)
map_length = min(map_length, bbio->fs_info->max_zone_append_size);
sector_offset = bio_split_rw_at(&bbio->bio, &bbio->fs_info->limits,
&nr_segs, map_length);
- if (sector_offset)
- return sector_offset << SECTOR_SHIFT;
+ if (sector_offset) {
+ /*
+ * bio_split_rw_at() could split at a size smaller than our
+ * sectorsize and thus cause unaligned I/Os. Fix that by
+ * always rounding down to the nearest boundary.
+ */
+ return ALIGN_DOWN(sector_offset << SECTOR_SHIFT, bbio->fs_info->sectorsize);
+ }
return map_length;
}
@@ -678,7 +687,8 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
&bioc, &smap, &mirror_num);
if (error) {
ret = errno_to_blk_status(error);
- goto fail;
+ btrfs_bio_counter_dec(fs_info);
+ goto end_bbio;
}
map_length = min(map_length, length);
@@ -686,7 +696,15 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
map_length = btrfs_append_map_length(bbio, map_length);
if (map_length < length) {
- bbio = btrfs_split_bio(fs_info, bbio, map_length);
+ struct btrfs_bio *split;
+
+ split = btrfs_split_bio(fs_info, bbio, map_length);
+ if (IS_ERR(split)) {
+ ret = errno_to_blk_status(PTR_ERR(split));
+ btrfs_bio_counter_dec(fs_info);
+ goto end_bbio;
+ }
+ bbio = split;
bio = &bbio->bio;
}
@@ -760,6 +778,7 @@ fail:
btrfs_bio_end_io(remaining, ret);
}
+end_bbio:
btrfs_bio_end_io(bbio, ret);
/* Do not submit another chunk */
return true;
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 148648ea1c8b..185985a337b3 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -654,6 +654,8 @@ int btrfs_force_cow_block(struct btrfs_trans_handle *trans,
goto error_unlock_cow;
}
}
+
+ trace_btrfs_cow_block(root, buf, cow);
if (unlock_orig)
btrfs_tree_unlock(buf);
free_extent_buffer_stale(buf);
@@ -710,7 +712,6 @@ int btrfs_cow_block(struct btrfs_trans_handle *trans,
{
struct btrfs_fs_info *fs_info = root->fs_info;
u64 search_start;
- int ret;
if (unlikely(test_bit(BTRFS_ROOT_DELETING, &root->state))) {
btrfs_abort_transaction(trans, -EUCLEAN);
@@ -751,12 +752,8 @@ int btrfs_cow_block(struct btrfs_trans_handle *trans,
* Also We don't care about the error, as it's handled internally.
*/
btrfs_qgroup_trace_subtree_after_cow(trans, root, buf);
- ret = btrfs_force_cow_block(trans, root, buf, parent, parent_slot,
- cow_ret, search_start, 0, nest);
-
- trace_btrfs_cow_block(root, buf, *cow_ret);
-
- return ret;
+ return btrfs_force_cow_block(trans, root, buf, parent, parent_slot,
+ cow_ret, search_start, 0, nest);
}
ALLOW_ERROR_INJECTION(btrfs_cow_block, ERRNO);
@@ -2046,7 +2043,7 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
const struct btrfs_key *key, struct btrfs_path *p,
int ins_len, int cow)
{
- struct btrfs_fs_info *fs_info = root->fs_info;
+ struct btrfs_fs_info *fs_info;
struct extent_buffer *b;
int slot;
int ret;
@@ -2059,6 +2056,10 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
int min_write_lock_level;
int prev_cmp;
+ if (!root)
+ return -EINVAL;
+
+ fs_info = root->fs_info;
might_sleep();
lowest_level = p->lowest_level;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 307dedf95c70..2c341956a01c 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -371,6 +371,25 @@ static inline void btrfs_set_root_last_trans(struct btrfs_root *root, u64 transi
}
/*
+ * Return the generation this root started with.
+ *
+ * Every normal root that is created with root->root_key.offset set to it's
+ * originating generation. If it is a snapshot it is the generation when the
+ * snapshot was created.
+ *
+ * However for TREE_RELOC roots root_key.offset is the objectid of the owning
+ * tree root. Thankfully we copy the root item of the owning tree root, which
+ * has it's last_snapshot set to what we would have root_key.offset set to, so
+ * return that if this is a TREE_RELOC root.
+ */
+static inline u64 btrfs_root_origin_generation(const struct btrfs_root *root)
+{
+ if (btrfs_root_id(root) == BTRFS_TREE_RELOC_OBJECTID)
+ return btrfs_root_last_snapshot(&root->root_item);
+ return root->root_key.offset;
+}
+
+/*
* Structure that conveys information about an extent that is going to replace
* all the extents in a file range.
*/
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 814320948645..eff0dd1ae62f 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4262,6 +4262,15 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
* already the cleaner, but below we run all pending delayed iputs.
*/
btrfs_flush_workqueue(fs_info->fixup_workers);
+ /*
+ * Similar case here, we have to wait for delalloc workers before we
+ * proceed below and stop the cleaner kthread, otherwise we trigger a
+ * use-after-tree on the cleaner kthread task_struct when a delalloc
+ * worker running submit_compressed_extents() adds a delayed iput, which
+ * does a wake up on the cleaner kthread, which was already freed below
+ * when we call kthread_stop().
+ */
+ btrfs_flush_workqueue(fs_info->delalloc_workers);
/*
* After we parked the cleaner kthread, ordered extents may have
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 412e318e4a22..3c6f7fecbb9a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2422,7 +2422,7 @@ int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset,
goto out;
ret = check_delayed_ref(root, path, objectid, offset, bytenr);
- } while (ret == -EAGAIN);
+ } while (ret == -EAGAIN && !path->nowait);
out:
btrfs_release_path(path);
@@ -5285,7 +5285,7 @@ static bool visit_node_for_delete(struct btrfs_root *root, struct walk_control *
* reference to it.
*/
generation = btrfs_node_ptr_generation(eb, slot);
- if (!wc->update_ref || generation <= root->root_key.offset)
+ if (!wc->update_ref || generation <= btrfs_root_origin_generation(root))
return false;
/*
@@ -5340,7 +5340,7 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans,
goto reada;
if (wc->stage == UPDATE_BACKREF &&
- generation <= root->root_key.offset)
+ generation <= btrfs_root_origin_generation(root))
continue;
/* We don't lock the tree block, it's OK to be racy here */
@@ -5683,7 +5683,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
* for the subtree
*/
if (wc->stage == UPDATE_BACKREF &&
- generation <= root->root_key.offset) {
+ generation <= btrfs_root_origin_generation(root)) {
wc->lookup_info = 1;
return 1;
}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 588c353d2969..14e27473c5bc 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -911,6 +911,7 @@ again:
ret = PTR_ERR(folio);
return ret;
}
+ folio_wait_writeback(folio);
/* Only support page sized folio yet. */
ASSERT(folio_order(folio) == 0);
ret = set_folio_extent_mapped(folio);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 03fe0de2cd0d..27b2fe7f735d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3063,6 +3063,19 @@ int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent)
goto out;
}
+ /*
+ * If it's a COW write we need to lock the extent range as we will be
+ * inserting/replacing file extent items and unpinning an extent map.
+ * This must be taken before joining a transaction, as it's a higher
+ * level lock (like the inode's VFS lock), otherwise we can run into an
+ * ABBA deadlock with other tasks (transactions work like a lock,
+ * depending on their current state).
+ */
+ if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) {
+ clear_bits |= EXTENT_LOCKED;
+ lock_extent(io_tree, start, end, &cached_state);
+ }
+
if (freespace_inode)
trans = btrfs_join_transaction_spacecache(root);
else
@@ -3099,9 +3112,6 @@ int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent)
goto out;
}
- clear_bits |= EXTENT_LOCKED;
- lock_extent(io_tree, start, end, &cached_state);
-
if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered_extent->flags))
compress_type = ordered_extent->compress_type;
if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) {
@@ -9068,9 +9078,9 @@ out:
}
struct btrfs_encoded_read_private {
- wait_queue_head_t wait;
+ struct completion done;
void *uring_ctx;
- atomic_t pending;
+ refcount_t pending_refs;
blk_status_t status;
};
@@ -9089,14 +9099,14 @@ static void btrfs_encoded_read_endio(struct btrfs_bio *bbio)
*/
WRITE_ONCE(priv->status, bbio->bio.bi_status);
}
- if (atomic_dec_return(&priv->pending) == 0) {
+ if (refcount_dec_and_test(&priv->pending_refs)) {
int err = blk_status_to_errno(READ_ONCE(priv->status));
if (priv->uring_ctx) {
btrfs_uring_read_extent_endio(priv->uring_ctx, err);
kfree(priv);
} else {
- wake_up(&priv->wait);
+ complete(&priv->done);
}
}
bio_put(&bbio->bio);
@@ -9116,8 +9126,8 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode,
if (!priv)
return -ENOMEM;
- init_waitqueue_head(&priv->wait);
- atomic_set(&priv->pending, 1);
+ init_completion(&priv->done);
+ refcount_set(&priv->pending_refs, 1);
priv->status = 0;
priv->uring_ctx = uring_ctx;
@@ -9130,7 +9140,7 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode,
size_t bytes = min_t(u64, disk_io_size, PAGE_SIZE);
if (bio_add_page(&bbio->bio, pages[i], bytes, 0) < bytes) {
- atomic_inc(&priv->pending);
+ refcount_inc(&priv->pending_refs);
btrfs_submit_bbio(bbio, 0);
bbio = btrfs_bio_alloc(BIO_MAX_VECS, REQ_OP_READ, fs_info,
@@ -9145,11 +9155,11 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode,
disk_io_size -= bytes;
} while (disk_io_size);
- atomic_inc(&priv->pending);
+ refcount_inc(&priv->pending_refs);
btrfs_submit_bbio(bbio, 0);
if (uring_ctx) {
- if (atomic_dec_return(&priv->pending) == 0) {
+ if (refcount_dec_and_test(&priv->pending_refs)) {
ret = blk_status_to_errno(READ_ONCE(priv->status));
btrfs_uring_read_extent_endio(uring_ctx, ret);
kfree(priv);
@@ -9158,8 +9168,8 @@ int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode,
return -EIOCBQUEUED;
} else {
- if (atomic_dec_return(&priv->pending) != 0)
- io_wait_event(priv->wait, !atomic_read(&priv->pending));
+ if (!refcount_dec_and_test(&priv->pending_refs))
+ wait_for_completion_io(&priv->done);
/* See btrfs_encoded_read_endio() for ordering. */
ret = blk_status_to_errno(READ_ONCE(priv->status));
kfree(priv);
@@ -9789,15 +9799,25 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
struct btrfs_fs_info *fs_info = root->fs_info;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct extent_state *cached_state = NULL;
- struct extent_map *em = NULL;
struct btrfs_chunk_map *map = NULL;
struct btrfs_device *device = NULL;
struct btrfs_swap_info bsi = {
.lowest_ppage = (sector_t)-1ULL,
};
+ struct btrfs_backref_share_check_ctx *backref_ctx = NULL;
+ struct btrfs_path *path = NULL;
int ret = 0;
u64 isize;
- u64 start;
+ u64 prev_extent_end = 0;
+
+ /*
+ * Acquire the inode's mmap lock to prevent races with memory mapped
+ * writes, as they could happen after we flush delalloc below and before
+ * we lock the extent range further below. The inode was already locked
+ * up in the call chain.
+ */
+ btrfs_assert_inode_locked(BTRFS_I(inode));
+ down_write(&BTRFS_I(inode)->i_mmap_lock);
/*
* If the swap file was just created, make sure delalloc is done. If the
@@ -9806,22 +9826,32 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
*/
ret = btrfs_wait_ordered_range(BTRFS_I(inode), 0, (u64)-1);
if (ret)
- return ret;
+ goto out_unlock_mmap;
/*
* The inode is locked, so these flags won't change after we check them.
*/
if (BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS) {
btrfs_warn(fs_info, "swapfile must not be compressed");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out_unlock_mmap;
}
if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW)) {
btrfs_warn(fs_info, "swapfile must not be copy-on-write");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out_unlock_mmap;
}
if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
btrfs_warn(fs_info, "swapfile must not be checksummed");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out_unlock_mmap;
+ }
+
+ path = btrfs_alloc_path();
+ backref_ctx = btrfs_alloc_backref_share_check_ctx();
+ if (!path || !backref_ctx) {
+ ret = -ENOMEM;
+ goto out_unlock_mmap;
}
/*
@@ -9836,7 +9866,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_SWAP_ACTIVATE)) {
btrfs_warn(fs_info,
"cannot activate swapfile while exclusive operation is running");
- return -EBUSY;
+ ret = -EBUSY;
+ goto out_unlock_mmap;
}
/*
@@ -9850,7 +9881,8 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
btrfs_exclop_finish(fs_info);
btrfs_warn(fs_info,
"cannot activate swapfile because snapshot creation is in progress");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out_unlock_mmap;
}
/*
* Snapshots can create extents which require COW even if NODATACOW is
@@ -9866,11 +9898,13 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
if (btrfs_root_dead(root)) {
spin_unlock(&root->root_item_lock);
+ btrfs_drew_write_unlock(&root->snapshot_lock);
btrfs_exclop_finish(fs_info);
btrfs_warn(fs_info,
"cannot activate swapfile because subvolume %llu is being deleted",
btrfs_root_id(root));
- return -EPERM;
+ ret = -EPERM;
+ goto out_unlock_mmap;
}
atomic_inc(&root->nr_swapfiles);
spin_unlock(&root->root_item_lock);
@@ -9878,24 +9912,39 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize);
lock_extent(io_tree, 0, isize - 1, &cached_state);
- start = 0;
- while (start < isize) {
- u64 logical_block_start, physical_block_start;
+ while (prev_extent_end < isize) {
+ struct btrfs_key key;
+ struct extent_buffer *leaf;
+ struct btrfs_file_extent_item *ei;
struct btrfs_block_group *bg;
- u64 len = isize - start;
+ u64 logical_block_start;
+ u64 physical_block_start;
+ u64 extent_gen;
+ u64 disk_bytenr;
+ u64 len;
- em = btrfs_get_extent(BTRFS_I(inode), NULL, start, len);
- if (IS_ERR(em)) {
- ret = PTR_ERR(em);
+ key.objectid = btrfs_ino(BTRFS_I(inode));
+ key.type = BTRFS_EXTENT_DATA_KEY;
+ key.offset = prev_extent_end;
+
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0)
goto out;
- }
- if (em->disk_bytenr == EXTENT_MAP_HOLE) {
+ /*
+ * If key not found it means we have an implicit hole (NO_HOLES
+ * is enabled).
+ */
+ if (ret > 0) {
btrfs_warn(fs_info, "swapfile must not have holes");
ret = -EINVAL;
goto out;
}
- if (em->disk_bytenr == EXTENT_MAP_INLINE) {
+
+ leaf = path->nodes[0];
+ ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item);
+
+ if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_INLINE) {
/*
* It's unlikely we'll ever actually find ourselves
* here, as a file small enough to fit inline won't be
@@ -9907,23 +9956,45 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
ret = -EINVAL;
goto out;
}
- if (extent_map_is_compressed(em)) {
+
+ if (btrfs_file_extent_compression(leaf, ei) != BTRFS_COMPRESS_NONE) {
btrfs_warn(fs_info, "swapfile must not be compressed");
ret = -EINVAL;
goto out;
}
- logical_block_start = extent_map_block_start(em) + (start - em->start);
- len = min(len, em->len - (start - em->start));
- free_extent_map(em);
- em = NULL;
+ disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, ei);
+ if (disk_bytenr == 0) {
+ btrfs_warn(fs_info, "swapfile must not have holes");
+ ret = -EINVAL;
+ goto out;
+ }
- ret = can_nocow_extent(inode, start, &len, NULL, false, true);
+ logical_block_start = disk_bytenr + btrfs_file_extent_offset(leaf, ei);
+ extent_gen = btrfs_file_extent_generation(leaf, ei);
+ prev_extent_end = btrfs_file_extent_end(path);
+
+ if (prev_extent_end > isize)
+ len = isize - key.offset;
+ else
+ len = btrfs_file_extent_num_bytes(leaf, ei);
+
+ backref_ctx->curr_leaf_bytenr = leaf->start;
+
+ /*
+ * Don't need the path anymore, release to avoid deadlocks when
+ * calling btrfs_is_data_extent_shared() because when joining a
+ * transaction it can block waiting for the current one's commit
+ * which in turn may be trying to lock the same leaf to flush
+ * delayed items for example.
+ */
+ btrfs_release_path(path);
+
+ ret = btrfs_is_data_extent_shared(BTRFS_I(inode), disk_bytenr,
+ extent_gen, backref_ctx);
if (ret < 0) {
goto out;
- } else if (ret) {
- ret = 0;
- } else {
+ } else if (ret > 0) {
btrfs_warn(fs_info,
"swapfile must not be copy-on-write");
ret = -EINVAL;
@@ -9958,7 +10029,6 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
physical_block_start = (map->stripes[0].physical +
(logical_block_start - map->start));
- len = min(len, map->chunk_len - (logical_block_start - map->start));
btrfs_free_chunk_map(map);
map = NULL;
@@ -9999,20 +10069,23 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
if (ret)
goto out;
}
- bsi.start = start;
+ bsi.start = key.offset;
bsi.block_start = physical_block_start;
bsi.block_len = len;
}
- start += len;
+ if (fatal_signal_pending(current)) {
+ ret = -EINTR;
+ goto out;
+ }
+
+ cond_resched();
}
if (bsi.block_len)
ret = btrfs_add_swap_extent(sis, &bsi);
out:
- if (!IS_ERR_OR_NULL(em))
- free_extent_map(em);
if (!IS_ERR_OR_NULL(map))
btrfs_free_chunk_map(map);
@@ -10025,6 +10098,10 @@ out:
btrfs_exclop_finish(fs_info);
+out_unlock_mmap:
+ up_write(&BTRFS_I(inode)->i_mmap_lock);
+ btrfs_free_backref_share_ctx(backref_ctx);
+ btrfs_free_path(path);
if (ret)
return ret;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index c9302d193187..4d9305fa37a8 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -4751,6 +4751,9 @@ static void btrfs_uring_read_finished(struct io_uring_cmd *cmd, unsigned int iss
size_t page_offset;
ssize_t ret;
+ /* The inode lock has already been acquired in btrfs_uring_read_extent. */
+ btrfs_lockdep_inode_acquire(inode, i_rwsem);
+
if (priv->err) {
ret = priv->err;
goto out;
@@ -4859,6 +4862,13 @@ static int btrfs_uring_read_extent(struct kiocb *iocb, struct iov_iter *iter,
* and inode and freeing the allocations.
*/
+ /*
+ * We're returning to userspace with the inode lock held, and that's
+ * okay - it'll get unlocked in a worker thread. Call
+ * btrfs_lockdep_inode_release() to avoid confusing lockdep.
+ */
+ btrfs_lockdep_inode_release(inode, i_rwsem);
+
return -EIOCBQUEUED;
out_fail:
@@ -4868,25 +4878,29 @@ out_fail:
return ret;
}
+struct btrfs_uring_encoded_data {
+ struct btrfs_ioctl_encoded_io_args args;
+ struct iovec iovstack[UIO_FASTIOV];
+ struct iovec *iov;
+ struct iov_iter iter;
+};
+
static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue_flags)
{
size_t copy_end_kernel = offsetofend(struct btrfs_ioctl_encoded_io_args, flags);
size_t copy_end;
- struct btrfs_ioctl_encoded_io_args args = { 0 };
int ret;
u64 disk_bytenr, disk_io_size;
struct file *file;
struct btrfs_inode *inode;
struct btrfs_fs_info *fs_info;
struct extent_io_tree *io_tree;
- struct iovec iovstack[UIO_FASTIOV];
- struct iovec *iov = iovstack;
- struct iov_iter iter;
loff_t pos;
struct kiocb kiocb;
struct extent_state *cached_state = NULL;
u64 start, lockend;
void __user *sqe_addr;
+ struct btrfs_uring_encoded_data *data = io_uring_cmd_get_async_data(cmd)->op_data;
if (!capable(CAP_SYS_ADMIN)) {
ret = -EPERM;
@@ -4900,43 +4914,64 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue
if (issue_flags & IO_URING_F_COMPAT) {
#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT)
- struct btrfs_ioctl_encoded_io_args_32 args32;
-
copy_end = offsetofend(struct btrfs_ioctl_encoded_io_args_32, flags);
- if (copy_from_user(&args32, sqe_addr, copy_end)) {
- ret = -EFAULT;
- goto out_acct;
- }
- args.iov = compat_ptr(args32.iov);
- args.iovcnt = args32.iovcnt;
- args.offset = args32.offset;
- args.flags = args32.flags;
#else
return -ENOTTY;
#endif
} else {
copy_end = copy_end_kernel;
- if (copy_from_user(&args, sqe_addr, copy_end)) {
- ret = -EFAULT;
+ }
+
+ if (!data) {
+ data = kzalloc(sizeof(*data), GFP_NOFS);
+ if (!data) {
+ ret = -ENOMEM;
goto out_acct;
}
- }
- if (args.flags != 0)
- return -EINVAL;
+ io_uring_cmd_get_async_data(cmd)->op_data = data;
- ret = import_iovec(ITER_DEST, args.iov, args.iovcnt, ARRAY_SIZE(iovstack),
- &iov, &iter);
- if (ret < 0)
- goto out_acct;
+ if (issue_flags & IO_URING_F_COMPAT) {
+#if defined(CONFIG_64BIT) && defined(CONFIG_COMPAT)
+ struct btrfs_ioctl_encoded_io_args_32 args32;
- if (iov_iter_count(&iter) == 0) {
- ret = 0;
- goto out_free;
+ if (copy_from_user(&args32, sqe_addr, copy_end)) {
+ ret = -EFAULT;
+ goto out_acct;
+ }
+
+ data->args.iov = compat_ptr(args32.iov);
+ data->args.iovcnt = args32.iovcnt;
+ data->args.offset = args32.offset;
+ data->args.flags = args32.flags;
+#endif
+ } else {
+ if (copy_from_user(&data->args, sqe_addr, copy_end)) {
+ ret = -EFAULT;
+ goto out_acct;
+ }
+ }
+
+ if (data->args.flags != 0) {
+ ret = -EINVAL;
+ goto out_acct;
+ }
+
+ data->iov = data->iovstack;
+ ret = import_iovec(ITER_DEST, data->args.iov, data->args.iovcnt,
+ ARRAY_SIZE(data->iovstack), &data->iov,
+ &data->iter);
+ if (ret < 0)
+ goto out_acct;
+
+ if (iov_iter_count(&data->iter) == 0) {
+ ret = 0;
+ goto out_free;
+ }
}
- pos = args.offset;
- ret = rw_verify_area(READ, file, &pos, args.len);
+ pos = data->args.offset;
+ ret = rw_verify_area(READ, file, &pos, data->args.len);
if (ret < 0)
goto out_free;
@@ -4949,15 +4984,16 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue
start = ALIGN_DOWN(pos, fs_info->sectorsize);
lockend = start + BTRFS_MAX_UNCOMPRESSED - 1;
- ret = btrfs_encoded_read(&kiocb, &iter, &args, &cached_state,
+ ret = btrfs_encoded_read(&kiocb, &data->iter, &data->args, &cached_state,
&disk_bytenr, &disk_io_size);
if (ret < 0 && ret != -EIOCBQUEUED)
goto out_free;
file_accessed(file);
- if (copy_to_user(sqe_addr + copy_end, (const char *)&args + copy_end_kernel,
- sizeof(args) - copy_end_kernel)) {
+ if (copy_to_user(sqe_addr + copy_end,
+ (const char *)&data->args + copy_end_kernel,
+ sizeof(data->args) - copy_end_kernel)) {
if (ret == -EIOCBQUEUED) {
unlock_extent(io_tree, start, lockend, &cached_state);
btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
@@ -4967,40 +5003,22 @@ static int btrfs_uring_encoded_read(struct io_uring_cmd *cmd, unsigned int issue
}
if (ret == -EIOCBQUEUED) {
- u64 count;
-
- /*
- * If we've optimized things by storing the iovecs on the stack,
- * undo this.
- */
- if (!iov) {
- iov = kmalloc(sizeof(struct iovec) * args.iovcnt, GFP_NOFS);
- if (!iov) {
- unlock_extent(io_tree, start, lockend, &cached_state);
- btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
- ret = -ENOMEM;
- goto out_acct;
- }
-
- memcpy(iov, iovstack, sizeof(struct iovec) * args.iovcnt);
- }
-
- count = min_t(u64, iov_iter_count(&iter), disk_io_size);
+ u64 count = min_t(u64, iov_iter_count(&data->iter), disk_io_size);
/* Match ioctl by not returning past EOF if uncompressed. */
- if (!args.compression)
- count = min_t(u64, count, args.len);
+ if (!data->args.compression)
+ count = min_t(u64, count, data->args.len);
- ret = btrfs_uring_read_extent(&kiocb, &iter, start, lockend,
- cached_state, disk_bytenr,
- disk_io_size, count,
- args.compression, iov, cmd);
+ ret = btrfs_uring_read_extent(&kiocb, &data->iter, start, lockend,
+ cached_state, disk_bytenr, disk_io_size,
+ count, data->args.compression,
+ data->iov, cmd);
goto out_acct;
}
out_free:
- kfree(iov);
+ kfree(data->iov);
out_acct:
if (ret > 0)
diff --git a/fs/btrfs/locking.h b/fs/btrfs/locking.h
index 46c8be2afab1..35036b151bf5 100644
--- a/fs/btrfs/locking.h
+++ b/fs/btrfs/locking.h
@@ -129,6 +129,16 @@ enum btrfs_lockdep_trans_states {
rwsem_release(&owner->lock##_map, _THIS_IP_)
/*
+ * Used to account for the fact that when doing io_uring encoded I/O, we can
+ * return to userspace with the inode lock still held.
+ */
+#define btrfs_lockdep_inode_acquire(owner, lock) \
+ rwsem_acquire_read(&owner->vfs_inode.lock.dep_map, 0, 0, _THIS_IP_)
+
+#define btrfs_lockdep_inode_release(owner, lock) \
+ rwsem_release(&owner->vfs_inode.lock.dep_map, _THIS_IP_)
+
+/*
* Macros for the transaction states wait events, similar to the generic wait
* event macros.
*/
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index a6f92836c9b1..f9b214992212 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1121,6 +1121,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info,
fs_info->qgroup_flags = BTRFS_QGROUP_STATUS_FLAG_ON;
if (simple) {
fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE;
+ btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA);
btrfs_set_qgroup_status_enable_gen(leaf, ptr, trans->transid);
} else {
fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
@@ -1254,8 +1255,6 @@ out_add_root:
spin_lock(&fs_info->qgroup_lock);
fs_info->quota_root = quota_root;
set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
- if (simple)
- btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA);
spin_unlock(&fs_info->qgroup_lock);
/* Skip rescan for simple qgroups. */
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index 9522a8b79d22..2928abf7eb82 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -857,6 +857,7 @@ int btrfs_ref_tree_mod(struct btrfs_fs_info *fs_info,
"dropping a ref for a root that doesn't have a ref on the block");
dump_block_entry(fs_info, be);
dump_ref_action(fs_info, ra);
+ rb_erase(&ref->node, &be->refs);
kfree(ref);
kfree(ra);
goto out_unlock;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index bf267bdfa8f8..db8b42f674b7 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2902,6 +2902,7 @@ static int relocate_one_folio(struct reloc_control *rc,
const bool use_rst = btrfs_need_stripe_tree_update(fs_info, rc->block_group->flags);
ASSERT(index <= last_index);
+again:
folio = filemap_lock_folio(inode->i_mapping, index);
if (IS_ERR(folio)) {
@@ -2937,6 +2938,11 @@ static int relocate_one_folio(struct reloc_control *rc,
ret = -EIO;
goto release_folio;
}
+ if (folio->mapping != inode->i_mapping) {
+ folio_unlock(folio);
+ folio_put(folio);
+ goto again;
+ }
}
/*
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 204c928beaf9..531312efee8d 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1541,6 +1541,10 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg,
u64 extent_gen;
int ret;
+ if (unlikely(!extent_root)) {
+ btrfs_err(fs_info, "no valid extent root for scrub");
+ return -EUCLEAN;
+ }
memset(stripe->sectors, 0, sizeof(struct scrub_sector_verification) *
stripe->nr_sectors);
scrub_stripe_reset_bitmaps(stripe);
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 7254279c3cc9..498c84323253 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -5280,6 +5280,7 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len)
unsigned cur_len = min_t(unsigned, len,
PAGE_SIZE - pg_offset);
+again:
folio = filemap_lock_folio(mapping, index);
if (IS_ERR(folio)) {
page_cache_sync_readahead(mapping,
@@ -5312,6 +5313,11 @@ static int put_file_data(struct send_ctx *sctx, u64 offset, u32 len)
ret = -EIO;
break;
}
+ if (folio->mapping != mapping) {
+ folio_unlock(folio);
+ folio_put(folio);
+ goto again;
+ }
}
memcpy_from_folio(sctx->send_buf + sctx->send_size, folio,
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 97a85d180b61..7dfe5005129a 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1885,18 +1885,21 @@ static int btrfs_get_tree_super(struct fs_context *fc)
if (sb->s_root) {
btrfs_close_devices(fs_devices);
- if ((fc->sb_flags ^ sb->s_flags) & SB_RDONLY)
- ret = -EBUSY;
+ /*
+ * At this stage we may have RO flag mismatch between
+ * fc->sb_flags and sb->s_flags. Caller should detect such
+ * mismatch and reconfigure with sb->s_umount rwsem held if
+ * needed.
+ */
} else {
snprintf(sb->s_id, sizeof(sb->s_id), "%pg", bdev);
shrinker_debugfs_rename(sb->s_shrink, "sb-btrfs:%s", sb->s_id);
btrfs_sb(sb)->bdev_holder = &btrfs_fs_type;
ret = btrfs_fill_super(sb, fs_devices);
- }
-
- if (ret) {
- deactivate_locked_super(sb);
- return ret;
+ if (ret) {
+ deactivate_locked_super(sb);
+ return ret;
+ }
}
btrfs_clear_oneshot_options(fs_info);
@@ -1982,39 +1985,18 @@ error:
* btrfs or not, setting the whole super block RO. To make per-subvolume mounting
* work with different options work we need to keep backward compatibility.
*/
-static struct vfsmount *btrfs_reconfigure_for_mount(struct fs_context *fc)
+static int btrfs_reconfigure_for_mount(struct fs_context *fc, struct vfsmount *mnt)
{
- struct vfsmount *mnt;
- int ret;
- const bool ro2rw = !(fc->sb_flags & SB_RDONLY);
-
- /*
- * We got an EBUSY because our SB_RDONLY flag didn't match the existing
- * super block, so invert our setting here and retry the mount so we
- * can get our vfsmount.
- */
- if (ro2rw)
- fc->sb_flags |= SB_RDONLY;
- else
- fc->sb_flags &= ~SB_RDONLY;
-
- mnt = fc_mount(fc);
- if (IS_ERR(mnt))
- return mnt;
+ int ret = 0;
- if (!ro2rw)
- return mnt;
+ if (fc->sb_flags & SB_RDONLY)
+ return ret;
- /* We need to convert to rw, call reconfigure. */
- fc->sb_flags &= ~SB_RDONLY;
down_write(&mnt->mnt_sb->s_umount);
- ret = btrfs_reconfigure(fc);
+ if (!(fc->sb_flags & SB_RDONLY) && (mnt->mnt_sb->s_flags & SB_RDONLY))
+ ret = btrfs_reconfigure(fc);
up_write(&mnt->mnt_sb->s_umount);
- if (ret) {
- mntput(mnt);
- return ERR_PTR(ret);
- }
- return mnt;
+ return ret;
}
static int btrfs_get_tree_subvol(struct fs_context *fc)
@@ -2024,6 +2006,7 @@ static int btrfs_get_tree_subvol(struct fs_context *fc)
struct fs_context *dup_fc;
struct dentry *dentry;
struct vfsmount *mnt;
+ int ret = 0;
/*
* Setup a dummy root and fs_info for test/set super. This is because
@@ -2066,11 +2049,16 @@ static int btrfs_get_tree_subvol(struct fs_context *fc)
fc->security = NULL;
mnt = fc_mount(dup_fc);
- if (PTR_ERR_OR_ZERO(mnt) == -EBUSY)
- mnt = btrfs_reconfigure_for_mount(dup_fc);
- put_fs_context(dup_fc);
- if (IS_ERR(mnt))
+ if (IS_ERR(mnt)) {
+ put_fs_context(dup_fc);
return PTR_ERR(mnt);
+ }
+ ret = btrfs_reconfigure_for_mount(dup_fc, mnt);
+ put_fs_context(dup_fc);
+ if (ret) {
+ mntput(mnt);
+ return ret;
+ }
/*
* This free's ->subvol_name, because if it isn't set we have to
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index b843308e2bc6..7f09b6c9cc2d 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -295,7 +295,7 @@ BTRFS_FEAT_ATTR_INCOMPAT(simple_quota, SIMPLE_QUOTA);
#ifdef CONFIG_BLK_DEV_ZONED
BTRFS_FEAT_ATTR_INCOMPAT(zoned, ZONED);
#endif
-#ifdef CONFIG_BTRFS_DEBUG
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
/* Remove once support for extent tree v2 is feature complete */
BTRFS_FEAT_ATTR_INCOMPAT(extent_tree_v2, EXTENT_TREE_V2);
/* Remove once support for raid stripe tree is feature complete. */
@@ -329,7 +329,7 @@ static struct attribute *btrfs_supported_feature_attrs[] = {
#ifdef CONFIG_BLK_DEV_ZONED
BTRFS_FEAT_ATTR_PTR(zoned),
#endif
-#ifdef CONFIG_BTRFS_DEBUG
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
BTRFS_FEAT_ATTR_PTR(extent_tree_v2),
BTRFS_FEAT_ATTR_PTR(raid_stripe_tree),
#endif
@@ -1118,7 +1118,7 @@ static ssize_t btrfs_nodesize_show(struct kobject *kobj,
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
- return sysfs_emit(buf, "%u\n", fs_info->super_copy->nodesize);
+ return sysfs_emit(buf, "%u\n", fs_info->nodesize);
}
BTRFS_ATTR(, nodesize, btrfs_nodesize_show);
@@ -1128,7 +1128,7 @@ static ssize_t btrfs_sectorsize_show(struct kobject *kobj,
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
- return sysfs_emit(buf, "%u\n", fs_info->super_copy->sectorsize);
+ return sysfs_emit(buf, "%u\n", fs_info->sectorsize);
}
BTRFS_ATTR(, sectorsize, btrfs_sectorsize_show);
@@ -1180,7 +1180,7 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj,
{
struct btrfs_fs_info *fs_info = to_fs_info(kobj);
- return sysfs_emit(buf, "%u\n", fs_info->super_copy->sectorsize);
+ return sysfs_emit(buf, "%u\n", fs_info->sectorsize);
}
BTRFS_ATTR(, clone_alignment, btrfs_clone_alignment_show);
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 148d8cefa40e..dfeee033f31f 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1527,6 +1527,11 @@ static int check_extent_item(struct extent_buffer *leaf,
dref_offset, fs_info->sectorsize);
return -EUCLEAN;
}
+ if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) {
+ extent_err(leaf, slot,
+ "invalid data ref count, should have non-zero value");
+ return -EUCLEAN;
+ }
inline_refs += btrfs_extent_data_ref_count(leaf, dref);
break;
/* Contains parent bytenr and ref count */
@@ -1539,6 +1544,11 @@ static int check_extent_item(struct extent_buffer *leaf,
inline_offset, fs_info->sectorsize);
return -EUCLEAN;
}
+ if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) {
+ extent_err(leaf, slot,
+ "invalid shared data ref count, should have non-zero value");
+ return -EUCLEAN;
+ }
inline_refs += btrfs_shared_data_ref_count(leaf, sref);
break;
case BTRFS_EXTENT_OWNER_REF_KEY:
@@ -1611,8 +1621,18 @@ static int check_simple_keyed_refs(struct extent_buffer *leaf,
{
u32 expect_item_size = 0;
- if (key->type == BTRFS_SHARED_DATA_REF_KEY)
+ if (key->type == BTRFS_SHARED_DATA_REF_KEY) {
+ struct btrfs_shared_data_ref *sref;
+
+ sref = btrfs_item_ptr(leaf, slot, struct btrfs_shared_data_ref);
+ if (unlikely(btrfs_shared_data_ref_count(leaf, sref) == 0)) {
+ extent_err(leaf, slot,
+ "invalid shared data backref count, should have non-zero value");
+ return -EUCLEAN;
+ }
+
expect_item_size = sizeof(struct btrfs_shared_data_ref);
+ }
if (unlikely(btrfs_item_size(leaf, slot) != expect_item_size)) {
generic_err(leaf, slot,
@@ -1689,6 +1709,11 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
offset, leaf->fs_info->sectorsize);
return -EUCLEAN;
}
+ if (unlikely(btrfs_extent_data_ref_count(leaf, dref) == 0)) {
+ extent_err(leaf, slot,
+ "invalid extent data backref count, should have non-zero value");
+ return -EUCLEAN;
+ }
}
return 0;
}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 1cccaf9c2b0d..3d0ac8bdb21f 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -797,6 +797,10 @@ static int get_canonical_dev_path(const char *dev_path, char *canonical)
if (ret)
goto out;
resolved_path = d_path(&path, path_buf, PATH_MAX);
+ if (IS_ERR(resolved_path)) {
+ ret = PTR_ERR(resolved_path);
+ goto out;
+ }
ret = strscpy(canonical, resolved_path, PATH_MAX);
out:
kfree(path_buf);
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index ddf0d5a448a7..c9e92c6941ec 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -174,10 +174,10 @@ int zlib_compress_folios(struct list_head *ws, struct address_space *mapping,
copy_page(workspace->buf + i * PAGE_SIZE,
data_in);
start += PAGE_SIZE;
- workspace->strm.avail_in =
- (in_buf_folios << PAGE_SHIFT);
}
workspace->strm.next_in = workspace->buf;
+ workspace->strm.avail_in = min(bytes_left,
+ in_buf_folios << PAGE_SHIFT);
} else {
unsigned int pg_off;
unsigned int cur_len;
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 11ed523e528e..df905ae82929 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -748,8 +748,9 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
(u64)lim->max_segments << PAGE_SHIFT),
fs_info->sectorsize);
fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED;
- if (fs_info->max_zone_append_size < fs_info->max_extent_size)
- fs_info->max_extent_size = fs_info->max_zone_append_size;
+
+ fs_info->max_extent_size = min_not_zero(fs_info->max_extent_size,
+ fs_info->max_zone_append_size);
/*
* Check mount options here, because we might change fs_info->zoned
generated by cgit v1.2.3 (git 2.39.0) at 2025-07-31 02:52:30 +0300