summaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/extent-tree.c2
-rw-r--r--fs/btrfs/file-item.c15
-rw-r--r--fs/btrfs/inode.c2
-rw-r--r--fs/btrfs/ioctl.c10
-rw-r--r--fs/btrfs/ordered-data.c3
-rw-r--r--fs/btrfs/props.c8
-rw-r--r--fs/btrfs/qgroup.c4
-rw-r--r--fs/btrfs/raid56.c3
-rw-r--r--fs/btrfs/transaction.c49
-rw-r--r--fs/btrfs/tree-log.c33
-rw-r--r--fs/btrfs/volumes.c2
11 files changed, 100 insertions, 31 deletions
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 1d49694e6ae3..c5880329ae37 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -6174,7 +6174,7 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
*
* This is overestimating in most cases.
*/
- qgroup_rsv_size = outstanding_extents * fs_info->nodesize;
+ qgroup_rsv_size = (u64)outstanding_extents * fs_info->nodesize;
spin_lock(&block_rsv->lock);
block_rsv->size = reserve_size;
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 920bf3b4b0ef..cccc75d15970 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -7,6 +7,7 @@
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
+#include <linux/sched/mm.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
@@ -427,9 +428,13 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
unsigned long this_sum_bytes = 0;
int i;
u64 offset;
+ unsigned nofs_flag;
+
+ nofs_flag = memalloc_nofs_save();
+ sums = kvzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size),
+ GFP_KERNEL);
+ memalloc_nofs_restore(nofs_flag);
- sums = kzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size),
- GFP_NOFS);
if (!sums)
return BLK_STS_RESOURCE;
@@ -472,8 +477,10 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
bytes_left = bio->bi_iter.bi_size - total_bytes;
- sums = kzalloc(btrfs_ordered_sum_size(fs_info, bytes_left),
- GFP_NOFS);
+ nofs_flag = memalloc_nofs_save();
+ sums = kvzalloc(btrfs_ordered_sum_size(fs_info,
+ bytes_left), GFP_KERNEL);
+ memalloc_nofs_restore(nofs_flag);
BUG_ON(!sums); /* -ENOMEM */
sums->len = bytes_left;
ordered = btrfs_lookup_ordered_extent(inode,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 82fdda8ff5ab..2973608824ec 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6783,7 +6783,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
u64 extent_start = 0;
u64 extent_end = 0;
u64 objectid = btrfs_ino(inode);
- u8 extent_type;
+ int extent_type = -1;
struct btrfs_path *path = NULL;
struct btrfs_root *root = inode->root;
struct btrfs_file_extent_item *item;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index ec2d8919e7fb..cd4e693406a0 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -501,6 +501,16 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
+ /*
+ * If the fs is mounted with nologreplay, which requires it to be
+ * mounted in RO mode as well, we can not allow discard on free space
+ * inside block groups, because log trees refer to extents that are not
+ * pinned in a block group's free space cache (pinning the extents is
+ * precisely the first phase of replaying a log tree).
+ */
+ if (btrfs_test_opt(fs_info, NOLOGREPLAY))
+ return -EROFS;
+
rcu_read_lock();
list_for_each_entry_rcu(device, &fs_info->fs_devices->devices,
dev_list) {
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 6fde2b2741ef..45e3cfd1198b 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -6,6 +6,7 @@
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/writeback.h>
+#include <linux/sched/mm.h>
#include "ctree.h"
#include "transaction.h"
#include "btrfs_inode.h"
@@ -442,7 +443,7 @@ void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry)
cur = entry->list.next;
sum = list_entry(cur, struct btrfs_ordered_sum, list);
list_del(&sum->list);
- kfree(sum);
+ kvfree(sum);
}
kmem_cache_free(btrfs_ordered_extent_cache, entry);
}
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index dc6140013ae8..61d22a56c0ba 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -366,11 +366,11 @@ int btrfs_subvol_inherit_props(struct btrfs_trans_handle *trans,
static int prop_compression_validate(const char *value, size_t len)
{
- if (!strncmp("lzo", value, len))
+ if (!strncmp("lzo", value, 3))
return 0;
- else if (!strncmp("zlib", value, len))
+ else if (!strncmp("zlib", value, 4))
return 0;
- else if (!strncmp("zstd", value, len))
+ else if (!strncmp("zstd", value, 4))
return 0;
return -EINVAL;
@@ -396,7 +396,7 @@ static int prop_compression_apply(struct inode *inode,
btrfs_set_fs_incompat(fs_info, COMPRESS_LZO);
} else if (!strncmp("zlib", value, 4)) {
type = BTRFS_COMPRESS_ZLIB;
- } else if (!strncmp("zstd", value, len)) {
+ } else if (!strncmp("zstd", value, 4)) {
type = BTRFS_COMPRESS_ZSTD;
btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD);
} else {
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index eb680b715dd6..e659d9d61107 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1922,8 +1922,8 @@ static int qgroup_trace_new_subtree_blocks(struct btrfs_trans_handle* trans,
int i;
/* Level sanity check */
- if (cur_level < 0 || cur_level >= BTRFS_MAX_LEVEL ||
- root_level < 0 || root_level >= BTRFS_MAX_LEVEL ||
+ if (cur_level < 0 || cur_level >= BTRFS_MAX_LEVEL - 1 ||
+ root_level < 0 || root_level >= BTRFS_MAX_LEVEL - 1 ||
root_level < cur_level) {
btrfs_err_rl(fs_info,
"%s: bad levels, cur_level=%d root_level=%d",
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 1869ba8e5981..67a6f7d47402 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -2430,8 +2430,9 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
bitmap_clear(rbio->dbitmap, pagenr, 1);
kunmap(p);
- for (stripe = 0; stripe < rbio->real_stripes; stripe++)
+ for (stripe = 0; stripe < nr_data; stripe++)
kunmap(page_in_rbio(rbio, stripe, pagenr, 0));
+ kunmap(p_page);
}
__free_page(p_page);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index acdad6d658f5..e4e665f422fc 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1886,8 +1886,10 @@ static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans)
}
}
-static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
+static inline int btrfs_start_delalloc_flush(struct btrfs_trans_handle *trans)
{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
+
/*
* We use writeback_inodes_sb here because if we used
* btrfs_start_delalloc_roots we would deadlock with fs freeze.
@@ -1897,15 +1899,50 @@ static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
* from already being in a transaction and our join_transaction doesn't
* have to re-take the fs freeze lock.
*/
- if (btrfs_test_opt(fs_info, FLUSHONCOMMIT))
+ if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) {
writeback_inodes_sb(fs_info->sb, WB_REASON_SYNC);
+ } else {
+ struct btrfs_pending_snapshot *pending;
+ struct list_head *head = &trans->transaction->pending_snapshots;
+
+ /*
+ * Flush dellaloc for any root that is going to be snapshotted.
+ * This is done to avoid a corrupted version of files, in the
+ * snapshots, that had both buffered and direct IO writes (even
+ * if they were done sequentially) due to an unordered update of
+ * the inode's size on disk.
+ */
+ list_for_each_entry(pending, head, list) {
+ int ret;
+
+ ret = btrfs_start_delalloc_snapshot(pending->root);
+ if (ret)
+ return ret;
+ }
+ }
return 0;
}
-static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info)
+static inline void btrfs_wait_delalloc_flush(struct btrfs_trans_handle *trans)
{
- if (btrfs_test_opt(fs_info, FLUSHONCOMMIT))
+ struct btrfs_fs_info *fs_info = trans->fs_info;
+
+ if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) {
btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
+ } else {
+ struct btrfs_pending_snapshot *pending;
+ struct list_head *head = &trans->transaction->pending_snapshots;
+
+ /*
+ * Wait for any dellaloc that we started previously for the roots
+ * that are going to be snapshotted. This is to avoid a corrupted
+ * version of files in the snapshots that had both buffered and
+ * direct IO writes (even if they were done sequentially).
+ */
+ list_for_each_entry(pending, head, list)
+ btrfs_wait_ordered_extents(pending->root,
+ U64_MAX, 0, U64_MAX);
+ }
}
int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
@@ -2023,7 +2060,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
extwriter_counter_dec(cur_trans, trans->type);
- ret = btrfs_start_delalloc_flush(fs_info);
+ ret = btrfs_start_delalloc_flush(trans);
if (ret)
goto cleanup_transaction;
@@ -2039,7 +2076,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
if (ret)
goto cleanup_transaction;
- btrfs_wait_delalloc_flush(fs_info);
+ btrfs_wait_delalloc_flush(trans);
btrfs_scrub_pause(fs_info);
/*
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index f06454a55e00..561884f60d35 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3578,9 +3578,16 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
}
btrfs_release_path(path);
- /* find the first key from this transaction again */
+ /*
+ * Find the first key from this transaction again. See the note for
+ * log_new_dir_dentries, if we're logging a directory recursively we
+ * won't be holding its i_mutex, which means we can modify the directory
+ * while we're logging it. If we remove an entry between our first
+ * search and this search we'll not find the key again and can just
+ * bail.
+ */
ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0);
- if (WARN_ON(ret != 0))
+ if (ret != 0)
goto done;
/*
@@ -4544,6 +4551,19 @@ static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode,
item = btrfs_item_ptr(path->nodes[0], path->slots[0],
struct btrfs_inode_item);
*size_ret = btrfs_inode_size(path->nodes[0], item);
+ /*
+ * If the in-memory inode's i_size is smaller then the inode
+ * size stored in the btree, return the inode's i_size, so
+ * that we get a correct inode size after replaying the log
+ * when before a power failure we had a shrinking truncate
+ * followed by addition of a new name (rename / new hard link).
+ * Otherwise return the inode size from the btree, to avoid
+ * data loss when replaying a log due to previously doing a
+ * write that expands the inode's size and logging a new name
+ * immediately after.
+ */
+ if (*size_ret > inode->vfs_inode.i_size)
+ *size_ret = inode->vfs_inode.i_size;
}
btrfs_release_path(path);
@@ -4705,15 +4725,8 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
struct btrfs_file_extent_item);
if (btrfs_file_extent_type(leaf, extent) ==
- BTRFS_FILE_EXTENT_INLINE) {
- len = btrfs_file_extent_ram_bytes(leaf, extent);
- ASSERT(len == i_size ||
- (len == fs_info->sectorsize &&
- btrfs_file_extent_compression(leaf, extent) !=
- BTRFS_COMPRESS_NONE) ||
- (len < i_size && i_size < fs_info->sectorsize));
+ BTRFS_FILE_EXTENT_INLINE)
return 0;
- }
len = btrfs_file_extent_num_bytes(leaf, extent);
/* Last extent goes beyond i_size, no need to log a hole. */
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 9024eee889b9..db934ceae9c1 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6407,7 +6407,7 @@ static void btrfs_end_bio(struct bio *bio)
if (bio_op(bio) == REQ_OP_WRITE)
btrfs_dev_stat_inc_and_print(dev,
BTRFS_DEV_STAT_WRITE_ERRS);
- else
+ else if (!(bio->bi_opf & REQ_RAHEAD))
btrfs_dev_stat_inc_and_print(dev,
BTRFS_DEV_STAT_READ_ERRS);
if (bio->bi_opf & REQ_PREFLUSH)
generated by cgit (git 2.34.1) at 2024-05-22 13:02:58 +0000