summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-11-30 01:26:50 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2017-11-30 01:26:50 +0300
commit26cd94744e142dd5d5a21e2c1e31bacc120b2d74 (patch)
tree011899c07353efd6ff8736332848afa42c66041c /fs
parent198e0c0c61b604ab919e34989afe3505b80cd0eb (diff)
parentea37d5998b50a72b9045ba60a132eeb20e1c4230 (diff)
downloadlinux-26cd94744e142dd5d5a21e2c1e31bacc120b2d74.tar.xz
Merge tag 'for-4.15-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs fixes from David Sterba: "We've collected some fixes in since the pre-merge window freeze. There's technically only one regression fix for 4.15, but the rest seems important and candidates for stable. - fix missing flush bio puts in error cases (is serious, but rarely happens) - fix reporting stat::st_blocks for buffered append writes - fix space cache invalidation - fix out of bound memory access when setting zlib level - fix potential memory corruption when fsync fails in the middle - fix crash in integrity checker - incremetnal send fix, path mixup for certain unlink/rename combination - pass flags to writeback so compressed writes can be throttled properly - error handling fixes" * tag 'for-4.15-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: Btrfs: incremental send, fix wrong unlink path after renaming file btrfs: tree-checker: Fix false panic for sanity test Btrfs: fix list_add corruption and soft lockups in fsync btrfs: Fix wild memory access in compression level parser btrfs: fix deadlock when writing out space cache btrfs: clear space cache inode generation always Btrfs: fix reported number of inode blocks after buffered append writes Btrfs: move definition of the function btrfs_find_new_delalloc_bytes Btrfs: bail out gracefully rather than BUG_ON btrfs: dev_alloc_list is not protected by RCU, use normal list_del btrfs: add missing device::flush_bio puts btrfs: Fix transaction abort during failure in btrfs_rm_dev_item Btrfs: add write_flags for compression bio
Diffstat (limited to 'fs')
-rw-r--r--fs/btrfs/compression.c9
-rw-r--r--fs/btrfs/compression.h5
-rw-r--r--fs/btrfs/ctree.h1
-rw-r--r--fs/btrfs/disk-io.c10
-rw-r--r--fs/btrfs/extent-tree.c14
-rw-r--r--fs/btrfs/extent_io.c2
-rw-r--r--fs/btrfs/extent_io.h8
-rw-r--r--fs/btrfs/file.c130
-rw-r--r--fs/btrfs/free-space-cache.c3
-rw-r--r--fs/btrfs/inode.c34
-rw-r--r--fs/btrfs/relocation.c3
-rw-r--r--fs/btrfs/send.c124
-rw-r--r--fs/btrfs/super.c13
-rw-r--r--fs/btrfs/tests/extent-io-tests.c6
-rw-r--r--fs/btrfs/tests/inode-tests.c12
-rw-r--r--fs/btrfs/tree-checker.c27
-rw-r--r--fs/btrfs/tree-checker.h14
-rw-r--r--fs/btrfs/tree-log.c2
-rw-r--r--fs/btrfs/volumes.c32
19 files changed, 314 insertions, 135 deletions
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index b35ce16b3df3..5982c8a71f02 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -295,7 +295,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
unsigned long len, u64 disk_start,
unsigned long compressed_len,
struct page **compressed_pages,
- unsigned long nr_pages)
+ unsigned long nr_pages,
+ unsigned int write_flags)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct bio *bio = NULL;
@@ -327,7 +328,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
bdev = fs_info->fs_devices->latest_bdev;
bio = btrfs_bio_alloc(bdev, first_byte);
- bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+ bio->bi_opf = REQ_OP_WRITE | write_flags;
bio->bi_private = cb;
bio->bi_end_io = end_compressed_bio_write;
refcount_set(&cb->pending_bios, 1);
@@ -374,7 +375,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
bio_put(bio);
bio = btrfs_bio_alloc(bdev, first_byte);
- bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+ bio->bi_opf = REQ_OP_WRITE | write_flags;
bio->bi_private = cb;
bio->bi_end_io = end_compressed_bio_write;
bio_add_page(bio, page, PAGE_SIZE, 0);
@@ -1528,5 +1529,5 @@ unsigned int btrfs_compress_str2level(const char *str)
if (str[4] == ':' && '1' <= str[5] && str[5] <= '9' && str[6] == 0)
return str[5] - '0';
- return 0;
+ return BTRFS_ZLIB_DEFAULT_LEVEL;
}
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index da20755ebf21..0868cc554f14 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -34,6 +34,8 @@
/* Maximum size of data before compression */
#define BTRFS_MAX_UNCOMPRESSED (SZ_128K)
+#define BTRFS_ZLIB_DEFAULT_LEVEL 3
+
struct compressed_bio {
/* number of bios pending for this compressed extent */
refcount_t pending_bios;
@@ -91,7 +93,8 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
unsigned long len, u64 disk_start,
unsigned long compressed_len,
struct page **compressed_pages,
- unsigned long nr_pages);
+ unsigned long nr_pages,
+ unsigned int write_flags);
blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
int mirror_num, unsigned long bio_flags);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 51477a537c83..13c260b525a1 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3180,6 +3180,7 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput);
int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput,
int nr);
int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
+ unsigned int extra_bits,
struct extent_state **cached_state, int dedupe);
int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
struct btrfs_root *new_root,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index efce9a2fa9be..10a2a579cc7f 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -610,7 +610,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
* that we don't try and read the other copies of this block, just
* return -EIO.
*/
- if (found_level == 0 && btrfs_check_leaf(root, eb)) {
+ if (found_level == 0 && btrfs_check_leaf_full(root, eb)) {
set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
ret = -EIO;
}
@@ -3848,7 +3848,13 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
buf->len,
fs_info->dirty_metadata_batch);
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
- if (btrfs_header_level(buf) == 0 && btrfs_check_leaf(root, buf)) {
+ /*
+ * Since btrfs_mark_buffer_dirty() can be called with item pointer set
+ * but item data not updated.
+ * So here we should only check item pointers, not item data.
+ */
+ if (btrfs_header_level(buf) == 0 &&
+ btrfs_check_leaf_relaxed(root, buf)) {
btrfs_print_leaf(buf);
ASSERT(0);
}
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 7208ecef7088..4497f937e8fb 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3502,13 +3502,6 @@ again:
goto again;
}
- /* We've already setup this transaction, go ahead and exit */
- if (block_group->cache_generation == trans->transid &&
- i_size_read(inode)) {
- dcs = BTRFS_DC_SETUP;
- goto out_put;
- }
-
/*
* We want to set the generation to 0, that way if anything goes wrong
* from here on out we know not to trust this cache when we load up next
@@ -3532,6 +3525,13 @@ again:
}
WARN_ON(ret);
+ /* We've already setup this transaction, go ahead and exit */
+ if (block_group->cache_generation == trans->transid &&
+ i_size_read(inode)) {
+ dcs = BTRFS_DC_SETUP;
+ goto out_put;
+ }
+
if (i_size_read(inode) > 0) {
ret = btrfs_check_trunc_cache_free_space(fs_info,
&fs_info->global_block_rsv);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index f9e9f721efe2..012d63870b99 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3253,7 +3253,7 @@ static noinline_for_stack int writepage_delalloc(struct inode *inode,
delalloc_start,
delalloc_end,
&page_started,
- nr_written);
+ nr_written, wbc);
/* File system has been set read-only */
if (ret) {
SetPageError(page);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 4a8861379d3e..93dcae0c3183 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -116,7 +116,8 @@ struct extent_io_ops {
*/
int (*fill_delalloc)(void *private_data, struct page *locked_page,
u64 start, u64 end, int *page_started,
- unsigned long *nr_written);
+ unsigned long *nr_written,
+ struct writeback_control *wbc);
int (*writepage_start_hook)(struct page *page, u64 start, u64 end);
void (*writepage_end_io_hook)(struct page *page, u64 start, u64 end,
@@ -365,10 +366,11 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
struct extent_state **cached_state);
static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
- u64 end, struct extent_state **cached_state)
+ u64 end, unsigned int extra_bits,
+ struct extent_state **cached_state)
{
return set_extent_bit(tree, start, end,
- EXTENT_DELALLOC | EXTENT_UPTODATE,
+ EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits,
NULL, cached_state, GFP_NOFS);
}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index f80254d82f40..eb1bac7c8553 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -477,6 +477,47 @@ static void btrfs_drop_pages(struct page **pages, size_t num_pages)
}
}
+static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode,
+ const u64 start,
+ const u64 len,
+ struct extent_state **cached_state)
+{
+ u64 search_start = start;
+ const u64 end = start + len - 1;
+
+ while (search_start < end) {
+ const u64 search_len = end - search_start + 1;
+ struct extent_map *em;
+ u64 em_len;
+ int ret = 0;
+
+ em = btrfs_get_extent(inode, NULL, 0, search_start,
+ search_len, 0);
+ if (IS_ERR(em))
+ return PTR_ERR(em);
+
+ if (em->block_start != EXTENT_MAP_HOLE)
+ goto next;
+
+ em_len = em->len;
+ if (em->start < search_start)
+ em_len -= search_start - em->start;
+ if (em_len > search_len)
+ em_len = search_len;
+
+ ret = set_extent_bit(&inode->io_tree, search_start,
+ search_start + em_len - 1,
+ EXTENT_DELALLOC_NEW,
+ NULL, cached_state, GFP_NOFS);
+next:
+ search_start = extent_map_end(em);
+ free_extent_map(em);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
/*
* after copy_from_user, pages need to be dirtied and we need to make
* sure holes are created between the current EOF and the start of
@@ -497,14 +538,34 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages,
u64 end_of_last_block;
u64 end_pos = pos + write_bytes;
loff_t isize = i_size_read(inode);
+ unsigned int extra_bits = 0;
start_pos = pos & ~((u64) fs_info->sectorsize - 1);
num_bytes = round_up(write_bytes + pos - start_pos,
fs_info->sectorsize);
end_of_last_block = start_pos + num_bytes - 1;
+
+ if (!btrfs_is_free_space_inode(BTRFS_I(inode))) {
+ if (start_pos >= isize &&
+ !(BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC)) {
+ /*
+ * There can't be any extents following eof in this case
+ * so just set the delalloc new bit for the range
+ * directly.
+ */
+ extra_bits |= EXTENT_DELALLOC_NEW;
+ } else {
+ err = btrfs_find_new_delalloc_bytes(BTRFS_I(inode),
+ start_pos,
+ num_bytes, cached);
+ if (err)
+ return err;
+ }
+ }
+
err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
- cached, 0);
+ extra_bits, cached, 0);
if (err)
return err;
@@ -1404,47 +1465,6 @@ fail:
}
-static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode,
- const u64 start,
- const u64 len,
- struct extent_state **cached_state)
-{
- u64 search_start = start;
- const u64 end = start + len - 1;
-
- while (search_start < end) {
- const u64 search_len = end - search_start + 1;
- struct extent_map *em;
- u64 em_len;
- int ret = 0;
-
- em = btrfs_get_extent(inode, NULL, 0, search_start,
- search_len, 0);
- if (IS_ERR(em))
- return PTR_ERR(em);
-
- if (em->block_start != EXTENT_MAP_HOLE)
- goto next;
-
- em_len = em->len;
- if (em->start < search_start)
- em_len -= search_start - em->start;
- if (em_len > search_len)
- em_len = search_len;
-
- ret = set_extent_bit(&inode->io_tree, search_start,
- search_start + em_len - 1,
- EXTENT_DELALLOC_NEW,
- NULL, cached_state, GFP_NOFS);
-next:
- search_start = extent_map_end(em);
- free_extent_map(em);
- if (ret)
- return ret;
- }
- return 0;
-}
-
/*
* This function locks the extent and properly waits for data=ordered extents
* to finish before allowing the pages to be modified if need.
@@ -1473,10 +1493,8 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
+ round_up(pos + write_bytes - start_pos,
fs_info->sectorsize) - 1;
- if (start_pos < inode->vfs_inode.i_size ||
- (inode->flags & BTRFS_INODE_PREALLOC)) {
+ if (start_pos < inode->vfs_inode.i_size) {
struct btrfs_ordered_extent *ordered;
- unsigned int clear_bits;
lock_extent_bits(&inode->io_tree, start_pos, last_pos,
cached_state);
@@ -1498,19 +1516,10 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
}
if (ordered)
btrfs_put_ordered_extent(ordered);
- ret = btrfs_find_new_delalloc_bytes(inode, start_pos,
- last_pos - start_pos + 1,
- cached_state);
- clear_bits = EXTENT_DIRTY | EXTENT_DELALLOC |
- EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG;
- if (ret)
- clear_bits |= EXTENT_DELALLOC_NEW | EXTENT_LOCKED;
- clear_extent_bit(&inode->io_tree, start_pos,
- last_pos, clear_bits,
- (clear_bits & EXTENT_LOCKED) ? 1 : 0,
- 0, cached_state, GFP_NOFS);
- if (ret)
- return ret;
+ clear_extent_bit(&inode->io_tree, start_pos, last_pos,
+ EXTENT_DIRTY | EXTENT_DELALLOC |
+ EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
+ 0, 0, cached_state, GFP_NOFS);
*lockstart = start_pos;
*lockend = last_pos;
ret = 1;
@@ -2048,6 +2057,8 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
len = (u64)end - (u64)start + 1;
trace_btrfs_sync_file(file, datasync);
+ btrfs_init_log_ctx(&ctx, inode);
+
/*
* We write the dirty pages in the range and wait until they complete
* out of the ->i_mutex. If so, we can flush the dirty pages by
@@ -2194,8 +2205,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
}
trans->sync = true;
- btrfs_init_log_ctx(&ctx, inode);
-
ret = btrfs_log_dentry_safe(trans, root, dentry, start, end, &ctx);
if (ret < 0) {
/* Fallthrough and commit/free transaction. */
@@ -2253,6 +2262,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
ret = btrfs_end_transaction(trans);
}
out:
+ ASSERT(list_empty(&ctx.list));
err = file_check_and_advance_wb_err(file);
if (!ret)
ret = err;
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index cdc9f4015ec3..4426d1c73e50 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -1264,7 +1264,7 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
/* Lock all pages first so we can lock the extent safely. */
ret = io_ctl_prepare_pages(io_ctl, inode, 0);
if (ret)
- goto out;
+ goto out_unlock;
lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1,
&cached_state);
@@ -1358,6 +1358,7 @@ out_nospc_locked:
out_nospc:
cleanup_write_cache_enospc(inode, io_ctl, &cached_state);
+out_unlock:
if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA))
up_write(&block_group->data_rwsem);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b93fe05a39c7..993061f83067 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -378,6 +378,7 @@ struct async_cow {
struct page *locked_page;
u64 start;
u64 end;
+ unsigned int write_flags;
struct list_head extents;
struct btrfs_work work;
};
@@ -857,7 +858,8 @@ retry:
async_extent->ram_size,
ins.objectid,
ins.offset, async_extent->pages,
- async_extent->nr_pages)) {
+ async_extent->nr_pages,
+ async_cow->write_flags)) {
struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
struct page *p = async_extent->pages[0];
const u64 start = async_extent->start;
@@ -1191,7 +1193,8 @@ static noinline void async_cow_free(struct btrfs_work *work)
static int cow_file_range_async(struct inode *inode, struct page *locked_page,
u64 start, u64 end, int *page_started,
- unsigned long *nr_written)
+ unsigned long *nr_written,
+ unsigned int write_flags)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct async_cow *async_cow;
@@ -1208,6 +1211,7 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
async_cow->root = root;
async_cow->locked_page = locked_page;
async_cow->start = start;
+ async_cow->write_flags = write_flags;
if (BTRFS_I(inode)->flags & BTRFS_INODE_NOCOMPRESS &&
!btrfs_test_opt(fs_info, FORCE_COMPRESS))
@@ -1577,11 +1581,13 @@ static inline int need_force_cow(struct inode *inode, u64 start, u64 end)
*/
static int run_delalloc_range(void *private_data, struct page *locked_page,
u64 start, u64 end, int *page_started,
- unsigned long *nr_written)
+ unsigned long *nr_written,
+ struct writeback_control *wbc)
{
struct inode *inode = private_data;
int ret;
int force_cow = need_force_cow(inode, start, end);
+ unsigned int write_flags = wbc_to_write_flags(wbc);
if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW && !force_cow) {
ret = run_delalloc_nocow(inode, locked_page, start, end,
@@ -1596,7 +1602,8 @@ static int run_delalloc_range(void *private_data, struct page *locked_page,
set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
&BTRFS_I(inode)->runtime_flags);
ret = cow_file_range_async(inode, locked_page, start, end,
- page_started, nr_written);
+ page_started, nr_written,
+ write_flags);
}
if (ret)
btrfs_cleanup_ordered_extents(inode, start, end - start + 1);
@@ -2025,11 +2032,12 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans,
}
int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
+ unsigned int extra_bits,
struct extent_state **cached_state, int dedupe)
{
WARN_ON((end & (PAGE_SIZE - 1)) == 0);
return set_extent_delalloc(&BTRFS_I(inode)->io_tree, start, end,
- cached_state);
+ extra_bits, cached_state);
}
/* see btrfs_writepage_start_hook for details on why this is required */
@@ -2090,7 +2098,7 @@ again:
goto out;
}
- btrfs_set_extent_delalloc(inode, page_start, page_end, &cached_state,
+ btrfs_set_extent_delalloc(inode, page_start, page_end, 0, &cached_state,
0);
ClearPageChecked(page);
set_page_dirty(page);
@@ -4790,7 +4798,7 @@ again:
EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
0, 0, &cached_state, GFP_NOFS);
- ret = btrfs_set_extent_delalloc(inode, block_start, block_end,
+ ret = btrfs_set_extent_delalloc(inode, block_start, block_end, 0,
&cached_state, 0);
if (ret) {
unlock_extent_cached(io_tree, block_start, block_end,
@@ -5438,6 +5446,14 @@ static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry,
goto out_err;
btrfs_dir_item_key_to_cpu(path->nodes[0], di, location);
+ if (location->type != BTRFS_INODE_ITEM_KEY &&
+ location->type != BTRFS_ROOT_ITEM_KEY) {
+ btrfs_warn(root->fs_info,
+"%s gets something invalid in DIR_ITEM (name %s, directory ino %llu, location(%llu %u %llu))",
+ __func__, name, btrfs_ino(BTRFS_I(dir)),
+ location->objectid, location->type, location->offset);
+ goto out_err;
+ }
out:
btrfs_free_path(path);
return ret;
@@ -5754,8 +5770,6 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
return inode;
}
- BUG_ON(location.type != BTRFS_ROOT_ITEM_KEY);
-
index = srcu_read_lock(&fs_info->subvol_srcu);
ret = fixup_tree_root_location(fs_info, dir, dentry,
&location, &sub_root);
@@ -9150,7 +9164,7 @@ again:
EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
0, 0, &cached_state, GFP_NOFS);
- ret = btrfs_set_extent_delalloc(inode, page_start, end,
+ ret = btrfs_set_extent_delalloc(inode, page_start, end, 0,
&cached_state, 0);
if (ret) {
unlock_extent_cached(io_tree, page_start, page_end,
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 4cf2eb67eba6..f0c3f00e97cb 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3268,7 +3268,8 @@ static int relocate_file_extent_cluster(struct inode *inode,
nr++;
}
- btrfs_set_extent_delalloc(inode, page_start, page_end, NULL, 0);
+ btrfs_set_extent_delalloc(inode, page_start, page_end, 0, NULL,
+ 0);
set_page_dirty(page);
unlock_extent(&BTRFS_I(inode)->io_tree,
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index c10e4c70f02d..20d3300bd268 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -3521,7 +3521,40 @@ out:
}
/*
- * Check if ino ino1 is an ancestor of inode ino2 in the given root.
+ * Check if inode ino2, or any of its ancestors, is inode ino1.
+ * Return 1 if true, 0 if false and < 0 on error.
+ */
+static int check_ino_in_path(struct btrfs_root *root,
+ const u64 ino1,
+ const u64 ino1_gen,
+ const u64 ino2,
+ const u64 ino2_gen,
+ struct fs_path *fs_path)
+{
+ u64 ino = ino2;
+
+ if (ino1 == ino2)
+ return ino1_gen == ino2_gen;
+
+ while (ino > BTRFS_FIRST_FREE_OBJECTID) {
+ u64 parent;
+ u64 parent_gen;
+ int ret;
+
+ fs_path_reset(fs_path);
+ ret = get_first_ref(root, ino, &parent, &parent_gen, fs_path);
+ if (ret < 0)
+ return ret;
+ if (parent == ino1)
+ return parent_gen == ino1_gen;
+ ino = parent;
+ }
+ return 0;
+}
+
+/*
+ * Check if ino ino1 is an ancestor of inode ino2 in the given root for any
+ * possible path (in case ino2 is not a directory and has multiple hard links).
* Return 1 if true, 0 if false and < 0 on error.
*/
static int is_ancestor(struct btrfs_root *root,
@@ -3530,36 +3563,91 @@ static int is_ancestor(struct btrfs_root *root,
const u64 ino2,
struct fs_path *fs_path)
{
- u64 ino = ino2;
- bool free_path = false;
+ bool free_fs_path = false;
int ret = 0;
+ struct btrfs_path *path = NULL;
+ struct btrfs_key key;
if (!fs_path) {
fs_path = fs_path_alloc();
if (!fs_path)
return -ENOMEM;
- free_path = true;
+ free_fs_path = true;
}
- while (ino > BTRFS_FIRST_FREE_OBJECTID) {
- u64 parent;
- u64 parent_gen;
+ path = alloc_path_for_send();
+ if (!path) {
+ ret = -ENOMEM;
+ goto out;
+ }
- fs_path_reset(fs_path);
- ret = get_first_ref(root, ino, &parent, &parent_gen, fs_path);
- if (ret < 0) {
- if (ret == -ENOENT && ino == ino2)
- ret = 0;
- goto out;
+ key.objectid = ino2;
+ key.type = BTRFS_INODE_REF_KEY;
+ key.offset = 0;
+
+ ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+ if (ret < 0)
+ goto out;
+
+ while (true) {
+ struct extent_buffer *leaf = path->nodes[0];
+ int slot = path->slots[0];
+ u32 cur_offset = 0;
+ u32 item_size;
+
+ if (slot >= btrfs_header_nritems(leaf)) {
+ ret = btrfs_next_leaf(root, path);
+ if (ret < 0)
+ goto out;
+ if (ret > 0)
+ break;
+ continue;
}
- if (parent == ino1) {
- ret = parent_gen == ino1_gen ? 1 : 0;
- goto out;
+
+ btrfs_item_key_to_cpu(leaf, &key, slot);
+ if (key.objectid != ino2)
+ break;
+ if (key.type != BTRFS_INODE_REF_KEY &&
+ key.type != BTRFS_INODE_EXTREF_KEY)
+ break;
+
+ item_size = btrfs_item_size_nr(leaf, slot);
+ while (cur_offset < item_size) {
+ u64 parent;
+ u64 parent_gen;
+
+ if (key.type == BTRFS_INODE_EXTREF_KEY) {
+ unsigned long ptr;
+ struct btrfs_inode_extref *extref;
+
+ ptr = btrfs_item_ptr_offset(leaf, slot);
+ extref = (struct btrfs_inode_extref *)
+ (ptr + cur_offset);
+ parent = btrfs_inode_extref_parent(leaf,
+ extref);
+ cur_offset += sizeof(*extref);
+ cur_offset += btrfs_inode_extref_name_len(leaf,
+ extref);
+ } else {
+ parent = key.offset;
+ cur_offset = item_size;
+ }
+
+ ret = get_inode_info(root, parent, NULL, &parent_gen,
+ NULL, NULL, NULL, NULL);
+ if (ret < 0)
+ goto out;
+ ret = check_ino_in_path(root, ino1, ino1_gen,
+ parent, parent_gen, fs_path);
+ if (ret)
+ goto out;
}
- ino = parent;
+ path->slots[0]++;
}
+ ret = 0;
out:
- if (free_path)
+ btrfs_free_path(path);
+ if (free_fs_path)
fs_path_free(fs_path);
return ret;
}
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 305cae7444a0..3a4dce153645 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -507,9 +507,18 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
token == Opt_compress_force ||
strncmp(args[0].from, "zlib", 4) == 0) {
compress_type = "zlib";
+
info->compress_type = BTRFS_COMPRESS_ZLIB;
- info->compress_level =
- btrfs_compress_str2level(args[0].from);
+ info->compress_level = BTRFS_ZLIB_DEFAULT_LEVEL;
+ /*
+ * args[0] contains uninitialized data since
+ * for these tokens we don't expect any
+ * parameter.
+ */
+ if (token != Opt_compress &&
+ token != Opt_compress_force)
+ info->compress_level =
+ btrfs_compress_str2level(args[0].from);
btrfs_set_opt(info->mount_opt, COMPRESS);
btrfs_clear_opt(info->mount_opt, NODATACOW);
btrfs_clear_opt(info->mount_opt, NODATASUM);
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index d06b1c931d05..2e7f64a3b22b 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -114,7 +114,7 @@ static int test_find_delalloc(u32 sectorsize)
* |--- delalloc ---|
* |--- search ---|
*/
- set_extent_delalloc(&tmp, 0, sectorsize - 1, NULL);
+ set_extent_delalloc(&tmp, 0, sectorsize - 1, 0, NULL);
start = 0;
end = 0;
found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -145,7 +145,7 @@ static int test_find_delalloc(u32 sectorsize)
test_msg("Couldn't find the locked page\n");
goto out_bits;
}
- set_extent_delalloc(&tmp, sectorsize, max_bytes - 1, NULL);
+ set_extent_delalloc(&tmp, sectorsize, max_bytes - 1, 0, NULL);
start = test_start;
end = 0;
found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
@@ -200,7 +200,7 @@ static int test_find_delalloc(u32 sectorsize)
*
* We are re-using our test_start from above since it works out well.
*/
- set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, NULL);
+ set_extent_delalloc(&tmp, max_bytes, total_dirty - 1, 0, NULL);
start = test_start;
end = 0;
found = find_lock_delalloc_range(inode, &tmp, locked_page, &start,
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index f797642c013d..30affb60da51 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -968,7 +968,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
btrfs_test_inode_set_ops(inode);
/* [BTRFS_MAX_EXTENT_SIZE] */
- ret = btrfs_set_extent_delalloc(inode, 0, BTRFS_MAX_EXTENT_SIZE - 1,
+ ret = btrfs_set_extent_delalloc(inode, 0, BTRFS_MAX_EXTENT_SIZE - 1, 0,
NULL, 0);
if (ret) {
test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
@@ -984,7 +984,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
/* [BTRFS_MAX_EXTENT_SIZE][sectorsize] */
ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE,
BTRFS_MAX_EXTENT_SIZE + sectorsize - 1,
- NULL, 0);
+ 0, NULL, 0);
if (ret) {
test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
goto out;
@@ -1018,7 +1018,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
ret = btrfs_set_extent_delalloc(inode, BTRFS_MAX_EXTENT_SIZE >> 1,
(BTRFS_MAX_EXTENT_SIZE >> 1)
+ sectorsize - 1,
- NULL, 0);
+ 0, NULL, 0);
if (ret) {
test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
goto out;
@@ -1036,7 +1036,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
ret = btrfs_set_extent_delalloc(inode,
BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize,
(BTRFS_MAX_EXTENT_SIZE << 1) + 3 * sectorsize - 1,
- NULL, 0);
+ 0, NULL, 0);
if (ret) {
test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
goto out;
@@ -1053,7 +1053,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
*/
ret = btrfs_set_extent_delalloc(inode,
BTRFS_MAX_EXTENT_SIZE + sectorsize,
- BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, NULL, 0);
+ BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, 0, NULL, 0);
if (ret) {
test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
goto out;
@@ -1089,7 +1089,7 @@ static int test_extent_accounting(u32 sectorsize, u32 nodesize)
*/
ret = btrfs_set_extent_delalloc(inode,
BTRFS_MAX_EXTENT_SIZE + sectorsize,
- BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, NULL, 0);
+ BTRFS_MAX_EXTENT_SIZE + 2 * sectorsize - 1, 0, NULL, 0);
if (ret) {
test_msg("btrfs_set_extent_delalloc returned %d\n", ret);
goto out;
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 114fc5f0ecc5..ce4ed6ec8f39 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -242,7 +242,8 @@ static int check_leaf_item(struct btrfs_root *root,
return ret;
}
-int btrfs_check_leaf(struct btrfs_root *root, struct extent_buffer *leaf)
+static int check_leaf(struct btrfs_root *root, struct extent_buffer *leaf,
+ bool check_item_data)
{
struct btrfs_fs_info *fs_info = root->fs_info;
/* No valid key type is 0, so all key should be larger than this key */
@@ -361,10 +362,15 @@ int btrfs_check_leaf(struct btrfs_root *root, struct extent_buffer *leaf)
return -EUCLEAN;
}
- /* Check if the item size and content meet other criteria */
- ret = check_leaf_item(root, leaf, &key, slot);
- if (ret < 0)
- return ret;
+ if (check_item_data) {
+ /*
+ * Check if the item size and content meet other
+ * criteria
+ */
+ ret = check_leaf_item(root, leaf, &key, slot);
+ if (ret < 0)
+ return ret;
+ }
prev_key.objectid = key.objectid;
prev_key.type = key.type;
@@ -374,6 +380,17 @@ int btrfs_check_leaf(struct btrfs_root *root, struct extent_buffer *leaf)
return 0;
}
+int btrfs_check_leaf_full(struct btrfs_root *root, struct extent_buffer *leaf)
+{
+ return check_leaf(root, leaf, true);
+}
+
+int btrfs_check_leaf_relaxed(struct btrfs_root *root,
+ struct extent_buffer *leaf)
+{
+ return check_leaf(root, leaf, false);
+}
+
int btrfs_check_node(struct btrfs_root *root, struct extent_buffer *node)
{
unsigned long nr = btrfs_header_nritems(node);
diff --git a/fs/btrfs/tree-checker.h b/fs/btrfs/tree-checker.h
index 96c486e95d70..3d53e8d6fda0 100644
--- a/fs/btrfs/tree-checker.h
+++ b/fs/btrfs/tree-checker.h
@@ -20,7 +20,19 @@
#include "ctree.h"
#include "extent_io.h"
-int btrfs_check_leaf(struct btrfs_root *root, struct extent_buffer *leaf);
+/*
+ * Comprehensive leaf checker.
+ * Will check not only the item pointers, but also every possible member
+ * in item data.
+ */
+int btrfs_check_leaf_full(struct btrfs_root *root, struct extent_buffer *leaf);
+
+/*
+ * Less strict leaf checker.
+ * Will only check item pointers, not reading item data.
+ */
+int btrfs_check_leaf_relaxed(struct btrfs_root *root,
+ struct extent_buffer *leaf);
int btrfs_check_node(struct btrfs_root *root, struct extent_buffer *node);
#endif
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index aa7c71cff575..7bf9b31561db 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4102,7 +4102,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
if (ordered_io_err) {
ctx->io_err = -EIO;
- return 0;
+ return ctx->io_err;
}
btrfs_init_map_token(&token);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 925070b9ce03..49810b70afd3 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -189,6 +189,7 @@ static void free_fs_devices(struct btrfs_fs_devices *fs_devices)
struct btrfs_device, dev_list);
list_del(&device->dev_list);
rcu_string_free(device->name);
+ bio_put(device->flush_bio);
kfree(device);
}
kfree(fs_devices);
@@ -578,6 +579,7 @@ static void btrfs_free_stale_device(struct btrfs_device *cur_dev)
fs_devs->num_devices--;
list_del(&dev->dev_list);
rcu_string_free(dev->name);
+ bio_put(dev->flush_bio);
kfree(dev);
}
break;
@@ -630,6 +632,7 @@ static noinline int device_list_add(const char *path,
name = rcu_string_strdup(path, GFP_NOFS);
if (!name) {
+ bio_put(device->flush_bio);
kfree(device);
return -ENOMEM;
}
@@ -742,6 +745,7 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
name = rcu_string_strdup(orig_dev->name->str,
GFP_KERNEL);
if (!name) {
+ bio_put(device->flush_bio);
kfree(device);
goto error;
}
@@ -807,6 +811,7 @@ again:
list_del_init(&device->dev_list);
fs_devices->num_devices--;
rcu_string_free(device->name);
+ bio_put(device->flush_bio);
kfree(device);
}
@@ -1750,20 +1755,24 @@ static int btrfs_rm_dev_item(struct btrfs_fs_info *fs_info,
key.offset = device->devid;
ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
- if (ret < 0)
- goto out;
-
- if (ret > 0) {
- ret = -ENOENT;
+ if (ret) {
+ if (ret > 0)
+ ret = -ENOENT;
+ btrfs_abort_transaction(trans, ret);
+ btrfs_end_transaction(trans);
goto out;
}
ret = btrfs_del_item(trans, root, path);
- if (ret)
- goto out;
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ btrfs_end_transaction(trans);
+ }
+
out:
btrfs_free_path(path);
- btrfs_commit_transaction(trans);
+ if (!ret)
+ ret = btrfs_commit_transaction(trans);
return ret;
}
@@ -1993,7 +2002,7 @@ void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
fs_devices = srcdev->fs_devices;
list_del_rcu(&srcdev->dev_list);
- list_del_rcu(&srcdev->dev_alloc_list);
+ list_del(&srcdev->dev_alloc_list);
fs_devices->num_devices--;
if (srcdev->missing)
fs_devices->missing_devices--;
@@ -2349,6 +2358,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
name = rcu_string_strdup(device_path, GFP_KERNEL);
if (!name) {
+ bio_put(device->flush_bio);
kfree(device);
ret = -ENOMEM;
goto error;
@@ -2358,6 +2368,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
rcu_string_free(device->name);
+ bio_put(device->flush_bio);
kfree(device);
ret = PTR_ERR(trans);
goto error;
@@ -2501,6 +2512,7 @@ error_trans:
if (trans)
btrfs_end_transaction(trans);
rcu_string_free(device->name);
+ bio_put(device->flush_bio);
kfree(device);
error:
blkdev_put(bdev, FMODE_EXCL);
@@ -2567,6 +2579,7 @@ int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
name = rcu_string_strdup(device_path, GFP_KERNEL);
if (!name) {
+ bio_put(device->flush_bio);
kfree(device);
ret = -ENOMEM;
goto error;
@@ -6284,6 +6297,7 @@ struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
ret = find_next_devid(fs_info, &tmp);
if (ret) {
+ bio_put(dev->flush_bio);
kfree(dev);
return ERR_PTR(ret);
}