diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 498442d0c2163dd2570db2b64c9175b4daf61c0e..2e49d978f504edd1d1d8e54b2c995d885dac23ef 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1223,8 +1223,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
block_group->space_info->total_bytes -= block_group->length;
block_group->space_info->bytes_readonly -=
(block_group->length - block_group->zone_unusable);
- block_group->space_info->bytes_zone_unusable -=
- block_group->zone_unusable;
+ btrfs_space_info_update_bytes_zone_unusable(fs_info, block_group->space_info,
+ -block_group->zone_unusable);
block_group->space_info->disk_total -= block_group->length * factor;
spin_unlock(&block_group->space_info->lock);
@@ -1396,7 +1396,8 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
if (btrfs_is_zoned(cache->fs_info)) {
/* Migrate zone_unusable bytes to readonly */
sinfo->bytes_readonly += cache->zone_unusable;
- sinfo->bytes_zone_unusable -= cache->zone_unusable;
+ btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo,
+ -cache->zone_unusable);
cache->zone_unusable = 0;
}
cache->ro++;
@@ -3056,9 +3057,11 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache)
if (btrfs_is_zoned(cache->fs_info)) {
/* Migrate zone_unusable bytes back */
cache->zone_unusable =
- (cache->alloc_offset - cache->used) +
+ (cache->alloc_offset - cache->used - cache->pinned -
+ cache->reserved) +
(cache->length - cache->zone_capacity);
- sinfo->bytes_zone_unusable += cache->zone_unusable;
+ btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo,
+ cache->zone_unusable);
sinfo->bytes_readonly -= cache->zone_unusable;
}
num_bytes = cache->length - cache->reserved -
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index c8568b1a61c4322317d7e8a66a641a1fdcb6da2d..75fa563e4cacb8b3df391fda8015140748e67ef5 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -459,6 +459,7 @@ struct btrfs_file_private {
void *filldir_buf;
u64 last_index;
struct extent_state *llseek_cached_state;
+ bool fsync_skip_inode_lock;
};
static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info)
diff --git a/fs/btrfs/direct-io.c b/fs/btrfs/direct-io.c
index f9fb2db6a1e4ad29125ae78d09cfa67f9890e2bb..67adbe9d294aecabce353c00cb5cb06bae7b7cba 100644
--- a/fs/btrfs/direct-io.c
+++ b/fs/btrfs/direct-io.c
@@ -856,21 +856,37 @@ ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
* So here we disable page faults in the iov_iter and then retry if we
* got -EFAULT, faulting in the pages before the retry.
*/
+again:
from->nofault = true;
dio = btrfs_dio_write(iocb, from, written);
from->nofault = false;
- /*
- * iomap_dio_complete() will call btrfs_sync_file() if we have a dsync
- * iocb, and that needs to lock the inode. So unlock it before calling
- * iomap_dio_complete() to avoid a deadlock.
- */
- btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
-
- if (IS_ERR_OR_NULL(dio))
+ if (IS_ERR_OR_NULL(dio)) {
ret = PTR_ERR_OR_ZERO(dio);
- else
+ } else {
+ struct btrfs_file_private stack_private = { 0 };
+ struct btrfs_file_private *private;
+ const bool have_private = (file->private_data != NULL);
+
+ if (!have_private)
+ file->private_data = &stack_private;
+
+ /*
+ * If we have a synchronous write, we must make sure the fsync
+ * triggered by the iomap_dio_complete() call below doesn't
+ * deadlock on the inode lock - we are already holding it and we
+ * can't call it after unlocking because we may need to complete
+ * partial writes due to the input buffer (or parts of it) not
+ * being already faulted in.
+ */
+ private = file->private_data;
+ private->fsync_skip_inode_lock = true;
ret = iomap_dio_complete(dio);
+ private->fsync_skip_inode_lock = false;
+
+ if (!have_private)
+ file->private_data = NULL;
+ }
/* No increment (+=) because iomap returns a cumulative value. */
if (ret > 0)
@@ -897,10 +913,12 @@ ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
} else {
fault_in_iov_iter_readable(from, left);
prev_left = left;
- goto relock;
+ goto again;
}
}
+ btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
+
/*
* If 'ret' is -ENOTBLK or we have not written all data, then it means
* we must fallback to buffered IO.
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index d77498e7671c724e7aae5907c41453dab04aa6a0..ff9f0d41987ec09f27a0e7acad6414e678bd1d9b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2793,7 +2793,8 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
readonly = true;
} else if (btrfs_is_zoned(fs_info)) {
/* Need reset before reusing in a zoned block group */
- space_info->bytes_zone_unusable += len;
+ btrfs_space_info_update_bytes_zone_unusable(fs_info, space_info,
+ len);
readonly = true;
}
spin_unlock(&cache->lock);
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 81558f90ee80fa5c05d5811ab5e79017e6bdb0ec..23b65dc73c0048c7425685a3f85eb5b84d1643c8 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -664,7 +664,7 @@ static noinline int merge_extent_mapping(struct btrfs_inode *inode,
start_diff = start - em->start;
em->start = start;
em->len = end - start;
- if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE && !extent_map_is_compressed(em))
+ if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE)
em->offset += start_diff;
return add_extent_mapping(inode, em, 0);
}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 21381de906f6073e32a9f360e456da900dbe4d47..9f10a9f23fcc8b91e9cd929f3365a9bc0b0f4a99 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1603,6 +1603,7 @@ static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx)
*/
int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
+ struct btrfs_file_private *private = file->private_data;
struct dentry *dentry = file_dentry(file);
struct btrfs_inode *inode = BTRFS_I(d_inode(dentry));
struct btrfs_root *root = inode->root;
@@ -1612,6 +1613,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
int ret = 0, err;
u64 len;
bool full_sync;
+ const bool skip_ilock = (private ? private->fsync_skip_inode_lock : false);
trace_btrfs_sync_file(file, datasync);
@@ -1639,7 +1641,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
if (ret)
goto out;
- btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP);
+ if (skip_ilock)
+ down_write(&inode->i_mmap_lock);
+ else
+ btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP);
atomic_inc(&root->log_batch);
@@ -1663,7 +1668,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
*/
ret = start_ordered_ops(inode, start, end);
if (ret) {
- btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
+ if (skip_ilock)
+ up_write(&inode->i_mmap_lock);
+ else
+ btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
goto out;
}
@@ -1788,7 +1796,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
* file again, but that will end up using the synchronization
* inside btrfs_sync_log to keep things safe.
*/
- btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
+ if (skip_ilock)
+ up_write(&inode->i_mmap_lock);
+ else
+ btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
if (ret == BTRFS_NO_LOG_SYNC) {
ret = btrfs_end_transaction(trans);
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 3f9b7507543ad4b0cd7cb7e6e4e16bc1dacf6f22..f5996a43db241484da43328cd62418e7af771af4 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -2723,8 +2723,10 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
* If the block group is read-only, we should account freed space into
* bytes_readonly.
*/
- if (!block_group->ro)
+ if (!block_group->ro) {
block_group->zone_unusable += to_unusable;
+ WARN_ON(block_group->zone_unusable > block_group->length);
+ }
spin_unlock(&ctl->tree_lock);
if (!used) {
spin_lock(&block_group->lock);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 01eab695564727be83101c4b9eecd1a43c1fc908..19d05a4c5c334789a41f13c96c2230b297418530 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -714,8 +714,9 @@ static noinline int __cow_file_range_inline(struct btrfs_inode *inode, u64 offse
return ret;
}
-static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 offset,
- u64 end,
+static noinline int cow_file_range_inline(struct btrfs_inode *inode,
+ struct page *locked_page,
+ u64 offset, u64 end,
size_t compressed_size,
int compress_type,
struct folio *compressed_folio,
@@ -739,7 +740,10 @@ static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 offset,
return ret;
}
- extent_clear_unlock_delalloc(inode, offset, end, NULL, &cached,
+ if (ret == 0)
+ locked_page = NULL;
+
+ extent_clear_unlock_delalloc(inode, offset, end, locked_page, &cached,
clear_flags,
PAGE_UNLOCK | PAGE_START_WRITEBACK |
PAGE_END_WRITEBACK);
@@ -1043,10 +1047,10 @@ static void compress_file_range(struct btrfs_work *work)
* extent for the subpage case.
*/
if (total_in < actual_end)
- ret = cow_file_range_inline(inode, start, end, 0,
+ ret = cow_file_range_inline(inode, NULL, start, end, 0,
BTRFS_COMPRESS_NONE, NULL, false);
else
- ret = cow_file_range_inline(inode, start, end, total_compressed,
+ ret = cow_file_range_inline(inode, NULL, start, end, total_compressed,
compress_type, folios[0], false);
if (ret <= 0) {
if (ret < 0)
@@ -1359,7 +1363,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
if (!no_inline) {
/* lets try to make an inline extent */
- ret = cow_file_range_inline(inode, start, end, 0,
+ ret = cow_file_range_inline(inode, locked_page, start, end, 0,
BTRFS_COMPRESS_NONE, NULL, false);
if (ret <= 0) {
/*
@@ -5660,7 +5664,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
struct inode *inode;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct btrfs_root *sub_root = root;
- struct btrfs_key location;
+ struct btrfs_key location = { 0 };
u8 di_type = 0;
int ret = 0;
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 9ac94d3119e8ddd5fea47652a6114955c2ec9142..68e14fd486384e3d47236f4c40d28501fcc8ccd6 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -316,7 +316,7 @@ void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info,
found->bytes_used += block_group->used;
found->disk_used += block_group->used * factor;
found->bytes_readonly += block_group->bytes_super;
- found->bytes_zone_unusable += block_group->zone_unusable;
+ btrfs_space_info_update_bytes_zone_unusable(info, found, block_group->zone_unusable);
if (block_group->length > 0)
found->full = 0;
btrfs_try_granting_tickets(info, found);
@@ -583,8 +583,7 @@ void btrfs_dump_space_info(struct btrfs_fs_info *fs_info,
spin_lock(&cache->lock);
avail = cache->length - cache->used - cache->pinned -
- cache->reserved - cache->delalloc_bytes -
- cache->bytes_super - cache->zone_unusable;
+ cache->reserved - cache->bytes_super - cache->zone_unusable;
btrfs_info(fs_info,
"block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %llu delalloc %llu super %llu zone_unusable (%llu bytes available) %s",
cache->start, cache->length, cache->used, cache->pinned,
diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h
index 4db8a0267c1606fe7b671ff349962ef18eb4317b..88b44221ce9782304fc4c7ead17c49fd593e451b 100644
--- a/fs/btrfs/space-info.h
+++ b/fs/btrfs/space-info.h
@@ -249,6 +249,7 @@ btrfs_space_info_update_##name(struct btrfs_fs_info *fs_info, \
DECLARE_SPACE_INFO_UPDATE(bytes_may_use, "space_info");
DECLARE_SPACE_INFO_UPDATE(bytes_pinned, "pinned");
+DECLARE_SPACE_INFO_UPDATE(bytes_zone_unusable, "zone_unusable");
int btrfs_init_space_info(struct btrfs_fs_info *fs_info);
void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info,
diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c
index ebec4ab361b82ac58e57414a3ec323034202d4f4..56e61ac1cc64c87d4dde3e6ddf92a4daaef650d3 100644
--- a/fs/btrfs/tests/extent-map-tests.c
+++ b/fs/btrfs/tests/extent-map-tests.c
@@ -900,6 +900,102 @@ static int test_case_7(struct btrfs_fs_info *fs_info, struct btrfs_inode *inode)
return ret;
}
+/*
+ * Test a regression for compressed extent map adjustment when we attempt to
+ * add an extent map that is partially overlapped by another existing extent
+ * map. The resulting extent map offset was left unchanged despite having
+ * incremented its start offset.
+ */
+static int test_case_8(struct btrfs_fs_info *fs_info, struct btrfs_inode *inode)
+{
+ struct extent_map_tree *em_tree = &inode->extent_tree;
+ struct extent_map *em;
+ int ret;
+ int ret2;
+
+ em = alloc_extent_map();
+ if (!em) {
+ test_std_err(TEST_ALLOC_EXTENT_MAP);
+ return -ENOMEM;
+ }
+
+ /* Compressed extent for the file range [120K, 128K). */
+ em->start = SZ_1K * 120;
+ em->len = SZ_8K;
+ em->disk_num_bytes = SZ_4K;
+ em->ram_bytes = SZ_8K;
+ em->flags |= EXTENT_FLAG_COMPRESS_ZLIB;
+ write_lock(&em_tree->lock);
+ ret = btrfs_add_extent_mapping(inode, &em, em->start, em->len);
+ write_unlock(&em_tree->lock);
+ free_extent_map(em);
+ if (ret < 0) {
+ test_err("couldn't add extent map for range [120K, 128K)");
+ goto out;
+ }
+
+ em = alloc_extent_map();
+ if (!em) {
+ test_std_err(TEST_ALLOC_EXTENT_MAP);
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ /*
+ * Compressed extent for the file range [108K, 144K), which overlaps
+ * with the [120K, 128K) we previously inserted.
+ */
+ em->start = SZ_1K * 108;
+ em->len = SZ_1K * 36;
+ em->disk_num_bytes = SZ_4K;
+ em->ram_bytes = SZ_1K * 36;
+ em->flags |= EXTENT_FLAG_COMPRESS_ZLIB;
+
+ /*
+ * Try to add the extent map but with a search range of [140K, 144K),
+ * this should succeed and adjust the extent map to the range
+ * [128K, 144K), with a length of 16K and an offset of 20K.
+ *
+ * This simulates a scenario where in the subvolume tree of an inode we
+ * have a compressed file extent item for the range [108K, 144K) and we
+ * have an overlapping compressed extent map for the range [120K, 128K),
+ * which was created by an encoded write, but its ordered extent was not
+ * yet completed, so the subvolume tree doesn't have yet the file extent
+ * item for that range - we only have the extent map in the inode's
+ * extent map tree.
+ */
+ write_lock(&em_tree->lock);
+ ret = btrfs_add_extent_mapping(inode, &em, SZ_1K * 140, SZ_4K);
+ write_unlock(&em_tree->lock);
+ free_extent_map(em);
+ if (ret < 0) {
+ test_err("couldn't add extent map for range [108K, 144K)");
+ goto out;
+ }
+
+ if (em->start != SZ_128K) {
+ test_err("unexpected extent map start %llu (should be 128K)", em->start);
+ ret = -EINVAL;
+ goto out;
+ }
+ if (em->len != SZ_16K) {
+ test_err("unexpected extent map length %llu (should be 16K)", em->len);
+ ret = -EINVAL;
+ goto out;
+ }
+ if (em->offset != SZ_1K * 20) {
+ test_err("unexpected extent map offset %llu (should be 20K)", em->offset);
+ ret = -EINVAL;
+ goto out;
+ }
+out:
+ ret2 = free_extent_map_tree(inode);
+ if (ret == 0)
+ ret = ret2;
+
+ return ret;
+}
+
struct rmap_test_vector {
u64 raid_type;
u64 physical_start;
@@ -1076,6 +1172,9 @@ int btrfs_test_extent_map(void)
if (ret)
goto out;
ret = test_case_7(fs_info, BTRFS_I(inode));
+ if (ret)
+ goto out;
+ ret = test_case_8(fs_info, BTRFS_I(inode));
if (ret)
goto out;
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 89e009a4c3a30c03abeccc0cdc645db87d129b25..a825fa598e3c2a87bf159d6008da0dbe7a2c978e 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1289,6 +1289,19 @@ static void extent_err(const struct extent_buffer *eb, int slot,
va_end(args);
}
+static bool is_valid_dref_root(u64 rootid)
+{
+ /*
+ * The following tree root objectids are allowed to have a data backref:
+ * - subvolume trees
+ * - data reloc tree
+ * - tree root
+ * For v1 space cache
+ */
+ return is_fstree(rootid) || rootid == BTRFS_DATA_RELOC_TREE_OBJECTID ||
+ rootid == BTRFS_ROOT_TREE_OBJECTID;
+}
+
static int check_extent_item(struct extent_buffer *leaf,
struct btrfs_key *key, int slot,
struct btrfs_key *prev_key)
@@ -1441,6 +1454,8 @@ static int check_extent_item(struct extent_buffer *leaf,
struct btrfs_extent_data_ref *dref;
struct btrfs_shared_data_ref *sref;
u64 seq;
+ u64 dref_root;
+ u64 dref_objectid;
u64 dref_offset;
u64 inline_offset;
u8 inline_type;
@@ -1484,11 +1499,26 @@ static int check_extent_item(struct extent_buffer *leaf,
*/
case BTRFS_EXTENT_DATA_REF_KEY:
dref = (struct btrfs_extent_data_ref *)(&iref->offset);
+ dref_root = btrfs_extent_data_ref_root(leaf, dref);
+ dref_objectid = btrfs_extent_data_ref_objectid(leaf, dref);
dref_offset = btrfs_extent_data_ref_offset(leaf, dref);
seq = hash_extent_data_ref(
btrfs_extent_data_ref_root(leaf, dref),
btrfs_extent_data_ref_objectid(leaf, dref),
btrfs_extent_data_ref_offset(leaf, dref));
+ if (unlikely(!is_valid_dref_root(dref_root))) {
+ extent_err(leaf, slot,
+ "invalid data ref root value %llu",
+ dref_root);
+ return -EUCLEAN;
+ }
+ if (unlikely(dref_objectid < BTRFS_FIRST_FREE_OBJECTID ||
+ dref_objectid > BTRFS_LAST_FREE_OBJECTID)) {
+ extent_err(leaf, slot,
+ "invalid data ref objectid value %llu",
+ dref_root);
+ return -EUCLEAN;
+ }
if (unlikely(!IS_ALIGNED(dref_offset,
fs_info->sectorsize))) {
extent_err(leaf, slot,
@@ -1627,6 +1657,8 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
return -EUCLEAN;
}
for (; ptr < end; ptr += sizeof(*dref)) {
+ u64 root;
+ u64 objectid;
u64 offset;
/*
@@ -1634,7 +1666,22 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
* overflow from the leaf due to hash collisions.
*/
dref = (struct btrfs_extent_data_ref *)ptr;
+ root = btrfs_extent_data_ref_root(leaf, dref);
+ objectid = btrfs_extent_data_ref_objectid(leaf, dref);
offset = btrfs_extent_data_ref_offset(leaf, dref);
+ if (unlikely(!is_valid_dref_root(root))) {
+ extent_err(leaf, slot,
+ "invalid extent data backref root value %llu",
+ root);
+ return -EUCLEAN;
+ }
+ if (unlikely(objectid < BTRFS_FIRST_FREE_OBJECTID ||
+ objectid > BTRFS_LAST_FREE_OBJECTID)) {
+ extent_err(leaf, slot,
+ "invalid extent data backref objectid value %llu",
+ root);
+ return -EUCLEAN;
+ }
if (unlikely(!IS_ALIGNED(offset, leaf->fs_info->sectorsize))) {
extent_err(leaf, slot,
"invalid extent data backref offset, have %llu expect aligned to %u",
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 246c0fbd582ee308bf35caaff97b796631ff86a3..0a523023bdcc38e3c20a0d28a58a836381cb34b0 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -2383,6 +2383,14 @@ DEFINE_EVENT(btrfs__space_info_update, update_bytes_pinned,
TP_ARGS(fs_info, sinfo, old, diff)
);
+DEFINE_EVENT(btrfs__space_info_update, update_bytes_zone_unusable,
+
+ TP_PROTO(const struct btrfs_fs_info *fs_info,
+ const struct btrfs_space_info *sinfo, u64 old, s64 diff),
+
+ TP_ARGS(fs_info, sinfo, old, diff)
+);
+
DECLARE_EVENT_CLASS(btrfs_raid56_bio,
TP_PROTO(const struct btrfs_raid_bio *rbio,