summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-10-06 17:45:53 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-10-06 17:45:53 -0700
commitbc32a6330fb0e90d1ce813c720d50098a41ec2e6 (patch)
tree8bb6d032d9f17b2bd63f446b371ba4e9be566e31
parent7f198ba7ae9874c64ffe8cd3aa60cf5dab78ce3a (diff)
parent1b45cc5c7b920fd8bf72e5a888ec7abeadf41e09 (diff)
downloadlinux-bc32a6330fb0e90d1ce813c720d50098a41ec2e6.tar.gz
linux-bc32a6330fb0e90d1ce813c720d50098a41ec2e6.tar.bz2
linux-bc32a6330fb0e90d1ce813c720d50098a41ec2e6.zip
Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
Pull ext4 updates from Ted Ts'o: "The first two changes involve files outside of fs/ext4: - submit_bh() can never return an error, so change it to return void, and remove the unused checks from its callers - fix I_DIRTY_TIME handling so it will be set even if the inode already has I_DIRTY_INODE Performance: - Always enable i_version counter (as btrfs and xfs already do). Remove some uneeded i_version bumps to avoid unnecessary nfs cache invalidations - Wake up journal waiters in FIFO order, to avoid some journal users from not getting a journal handle for an unfairly long time - In ext4_write_begin() allocate any necessary buffer heads before starting the journal handle - Don't try to prefetch the block allocation bitmaps for a read-only file system Bug Fixes: - Fix a number of fast commit bugs, including resources leaks and out of bound references in various error handling paths and/or if the fast commit log is corrupted - Avoid stopping the online resize early when expanding a file system which is less than 16TiB to a size greater than 16TiB - Fix apparent metadata corruption caused by a race with a metadata buffer head getting migrated while it was trying to be read - Mark the lazy initialization thread freezable to prevent suspend failures - Other miscellaneous bug fixes Cleanups: - Break up the incredibly long ext4_full_super() function by refactoring to move code into more understandable, smaller functions - Remove the deprecated (and ignored) noacl and nouser_attr mount option - Factor out some common code in fast commit handling - Other miscellaneous cleanups" * tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (53 commits) ext4: fix potential out of bound read in ext4_fc_replay_scan() ext4: factor out ext4_fc_get_tl() ext4: introduce EXT4_FC_TAG_BASE_LEN helper ext4: factor out ext4_free_ext_path() ext4: remove unnecessary drop path references in mext_check_coverage() ext4: update 'state->fc_regions_size' after successful memory allocation ext4: fix potential memory leak in ext4_fc_record_regions() ext4: fix potential memory leak in ext4_fc_record_modified_inode() ext4: remove redundant checking in ext4_ioctl_checkpoint jbd2: add miss release buffer head in fc_do_one_pass() ext4: move DIOREAD_NOLOCK setting to ext4_set_def_opts() ext4: remove useless local variable 'blocksize' ext4: unify the ext4 super block loading operation ext4: factor out ext4_journal_data_mode_check() ext4: factor out ext4_load_and_init_journal() ext4: factor out ext4_group_desc_init() and ext4_group_desc_free() ext4: factor out ext4_geometry_check() ext4: factor out ext4_check_feature_compatibility() ext4: factor out ext4_init_metadata_csum() ext4: factor out ext4_encoding_init() ...
-rw-r--r--Documentation/filesystems/vfs.rst3
-rw-r--r--fs/buffer.c23
-rw-r--r--fs/ext4/ext4.h5
-rw-r--r--fs/ext4/extents.c107
-rw-r--r--fs/ext4/extents_status.c3
-rw-r--r--fs/ext4/fast_commit.c210
-rw-r--r--fs/ext4/fast_commit.h3
-rw-r--r--fs/ext4/file.c6
-rw-r--r--fs/ext4/inode.c17
-rw-r--r--fs/ext4/ioctl.c7
-rw-r--r--fs/ext4/migrate.c3
-rw-r--r--fs/ext4/move_extent.c26
-rw-r--r--fs/ext4/namei.c17
-rw-r--r--fs/ext4/resize.c2
-rw-r--r--fs/ext4/super.c1233
-rw-r--r--fs/ext4/verity.c6
-rw-r--r--fs/ext4/xattr.c1
-rw-r--r--fs/fs-writeback.c37
-rw-r--r--fs/jbd2/commit.c12
-rw-r--r--fs/jbd2/journal.c19
-rw-r--r--fs/jbd2/recovery.c1
-rw-r--r--fs/jbd2/transaction.c6
-rw-r--r--fs/mbcache.c17
-rw-r--r--fs/ntfs/file.c4
-rw-r--r--fs/xfs/xfs_super.c10
-rw-r--r--include/linux/buffer_head.h2
-rw-r--r--include/linux/fs.h9
27 files changed, 988 insertions, 801 deletions
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index 6cd6953e175b..b2ef2449aed9 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -274,6 +274,9 @@ or bottom half).
This is specifically for the inode itself being marked dirty,
not its data. If the update needs to be persisted by fdatasync(),
then I_DIRTY_DATASYNC will be set in the flags argument.
+ I_DIRTY_TIME will be set in the flags in case lazytime is enabled
+ and struct inode has times updated since the last ->dirty_inode
+ call.
``write_inode``
this method is called when the VFS needs to write an inode to
diff --git a/fs/buffer.c b/fs/buffer.c
index 55e762a58eb6..0a7ba84c1905 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -52,8 +52,8 @@
#include "internal.h"
static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
-static int submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
- struct writeback_control *wbc);
+static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
+ struct writeback_control *wbc);
#define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)
@@ -2673,8 +2673,8 @@ static void end_bio_bh_io_sync(struct bio *bio)
bio_put(bio);
}
-static int submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
- struct writeback_control *wbc)
+static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
+ struct writeback_control *wbc)
{
const enum req_op op = opf & REQ_OP_MASK;
struct bio *bio;
@@ -2717,12 +2717,11 @@ static int submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh,
}
submit_bio(bio);
- return 0;
}
-int submit_bh(blk_opf_t opf, struct buffer_head *bh)
+void submit_bh(blk_opf_t opf, struct buffer_head *bh)
{
- return submit_bh_wbc(opf, bh, NULL);
+ submit_bh_wbc(opf, bh, NULL);
}
EXPORT_SYMBOL(submit_bh);
@@ -2801,8 +2800,6 @@ EXPORT_SYMBOL(write_dirty_buffer);
*/
int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags)
{
- int ret = 0;
-
WARN_ON(atomic_read(&bh->b_count) < 1);
lock_buffer(bh);
if (test_clear_buffer_dirty(bh)) {
@@ -2817,14 +2814,14 @@ int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags)
get_bh(bh);
bh->b_end_io = end_buffer_write_sync;
- ret = submit_bh(REQ_OP_WRITE | op_flags, bh);
+ submit_bh(REQ_OP_WRITE | op_flags, bh);
wait_on_buffer(bh);
- if (!ret && !buffer_uptodate(bh))
- ret = -EIO;
+ if (!buffer_uptodate(bh))
+ return -EIO;
} else {
unlock_buffer(bh);
}
- return ret;
+ return 0;
}
EXPORT_SYMBOL(__sync_dirty_buffer);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index e5f2f5ca5120..8d5453852f98 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3592,9 +3592,6 @@ extern bool empty_inline_dir(struct inode *dir, int *has_inline_data);
extern struct buffer_head *ext4_get_first_inline_block(struct inode *inode,
struct ext4_dir_entry_2 **parent_de,
int *retval);
-extern int ext4_inline_data_fiemap(struct inode *inode,
- struct fiemap_extent_info *fieinfo,
- int *has_inline, __u64 start, __u64 len);
extern void *ext4_read_inline_link(struct inode *inode);
struct iomap;
@@ -3713,7 +3710,7 @@ extern int ext4_ext_insert_extent(handle_t *, struct inode *,
extern struct ext4_ext_path *ext4_find_extent(struct inode *, ext4_lblk_t,
struct ext4_ext_path **,
int flags);
-extern void ext4_ext_drop_refs(struct ext4_ext_path *);
+extern void ext4_free_ext_path(struct ext4_ext_path *);
extern int ext4_ext_check_inode(struct inode *inode);
extern ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path);
extern int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 5235974126bd..f1956288307f 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -106,6 +106,25 @@ static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped)
return 0;
}
+static void ext4_ext_drop_refs(struct ext4_ext_path *path)
+{
+ int depth, i;
+
+ if (!path)
+ return;
+ depth = path->p_depth;
+ for (i = 0; i <= depth; i++, path++) {
+ brelse(path->p_bh);
+ path->p_bh = NULL;
+ }
+}
+
+void ext4_free_ext_path(struct ext4_ext_path *path)
+{
+ ext4_ext_drop_refs(path);
+ kfree(path);
+}
+
/*
* Make sure 'handle' has at least 'check_cred' credits. If not, restart
* transaction with 'restart_cred' credits. The function drops i_data_sem
@@ -636,8 +655,7 @@ int ext4_ext_precache(struct inode *inode)
ext4_set_inode_state(inode, EXT4_STATE_EXT_PRECACHED);
out:
up_read(&ei->i_data_sem);
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
return ret;
}
@@ -724,19 +742,6 @@ static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path,
#define ext4_ext_show_move(inode, path, newblock, level)
#endif
-void ext4_ext_drop_refs(struct ext4_ext_path *path)
-{
- int depth, i;
-
- if (!path)
- return;
- depth = path->p_depth;
- for (i = 0; i <= depth; i++, path++) {
- brelse(path->p_bh);
- path->p_bh = NULL;
- }
-}
-
/*
* ext4_ext_binsearch_idx:
* binary search for the closest index of the given block
@@ -955,8 +960,7 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block,
return path;
err:
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
if (orig_path)
*orig_path = NULL;
return ERR_PTR(ret);
@@ -2174,8 +2178,7 @@ merge:
err = ext4_ext_dirty(handle, inode, path + path->p_depth);
cleanup:
- ext4_ext_drop_refs(npath);
- kfree(npath);
+ ext4_free_ext_path(npath);
return err;
}
@@ -3061,8 +3064,7 @@ again:
}
}
out:
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
path = NULL;
if (err == -EAGAIN)
goto again;
@@ -4375,8 +4377,7 @@ got_allocated_blocks:
allocated = map->m_len;
ext4_ext_show_leaf(inode, path);
out:
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
trace_ext4_ext_map_blocks_exit(inode, flags, map,
err ? err : allocated);
@@ -5245,8 +5246,7 @@ again:
break;
}
out:
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
return ret;
}
@@ -5538,15 +5538,13 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len)
EXT4_GET_BLOCKS_METADATA_NOFAIL);
}
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
if (ret < 0) {
up_write(&EXT4_I(inode)->i_data_sem);
goto out_stop;
}
} else {
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
}
ret = ext4_es_remove_extent(inode, offset_lblk,
@@ -5766,10 +5764,8 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1,
count -= len;
repeat:
- ext4_ext_drop_refs(path1);
- kfree(path1);
- ext4_ext_drop_refs(path2);
- kfree(path2);
+ ext4_free_ext_path(path1);
+ ext4_free_ext_path(path2);
path1 = path2 = NULL;
}
return replaced_count;
@@ -5848,8 +5844,7 @@ int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu)
}
out:
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
return err ? err : mapped;
}
@@ -5916,8 +5911,7 @@ int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start,
ret = ext4_ext_dirty(NULL, inode, &path[path->p_depth]);
up_write(&EXT4_I(inode)->i_data_sem);
out:
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
ext4_mark_inode_dirty(NULL, inode);
return ret;
}
@@ -5935,8 +5929,7 @@ void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end)
return;
ex = path[path->p_depth].p_ext;
if (!ex) {
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
ext4_mark_inode_dirty(NULL, inode);
return;
}
@@ -5949,8 +5942,7 @@ void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end)
ext4_ext_dirty(NULL, inode, &path[path->p_depth]);
up_write(&EXT4_I(inode)->i_data_sem);
ext4_mark_inode_dirty(NULL, inode);
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
}
}
@@ -5989,13 +5981,11 @@ int ext4_ext_replay_set_iblocks(struct inode *inode)
return PTR_ERR(path);
ex = path[path->p_depth].p_ext;
if (!ex) {
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
goto out;
}
end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex);
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
/* Count the number of data blocks */
cur = 0;
@@ -6025,30 +6015,26 @@ int ext4_ext_replay_set_iblocks(struct inode *inode)
if (IS_ERR(path))
goto out;
numblks += path->p_depth;
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
while (cur < end) {
path = ext4_find_extent(inode, cur, NULL, 0);
if (IS_ERR(path))
break;
ex = path[path->p_depth].p_ext;
if (!ex) {
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
return 0;
}
cur = max(cur + 1, le32_to_cpu(ex->ee_block) +
ext4_ext_get_actual_len(ex));
ret = skip_hole(inode, &cur);
if (ret < 0) {
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
break;
}
path2 = ext4_find_extent(inode, cur, NULL, 0);
if (IS_ERR(path2)) {
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
break;
}
for (i = 0; i <= max(path->p_depth, path2->p_depth); i++) {
@@ -6062,10 +6048,8 @@ int ext4_ext_replay_set_iblocks(struct inode *inode)
if (cmp1 != cmp2 && cmp2 != 0)
numblks++;
}
- ext4_ext_drop_refs(path);
- ext4_ext_drop_refs(path2);
- kfree(path);
- kfree(path2);
+ ext4_free_ext_path(path);
+ ext4_free_ext_path(path2);
}
out:
@@ -6092,13 +6076,11 @@ int ext4_ext_clear_bb(struct inode *inode)
return PTR_ERR(path);
ex = path[path->p_depth].p_ext;
if (!ex) {
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
return 0;
}
end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex);
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
cur = 0;
while (cur < end) {
@@ -6117,8 +6099,7 @@ int ext4_ext_clear_bb(struct inode *inode)
ext4_fc_record_regions(inode->i_sb, inode->i_ino,
0, path[j].p_block, 1, 1);
}
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
}
ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, 0);
ext4_fc_record_regions(inode->i_sb, inode->i_ino,
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 23167efda95e..cd0a861853e3 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -667,8 +667,7 @@ static void ext4_es_insert_extent_ext_check(struct inode *inode,
}
}
out:
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
}
static void ext4_es_insert_extent_ind_check(struct inode *inode,
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 2af962cbb835..ef05bfa87798 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -229,6 +229,12 @@ __releases(&EXT4_SB(inode->i_sb)->s_fc_lock)
finish_wait(wq, &wait.wq_entry);
}
+static bool ext4_fc_disabled(struct super_block *sb)
+{
+ return (!test_opt2(sb, JOURNAL_FAST_COMMIT) ||
+ (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY));
+}
+
/*
* Inform Ext4's fast about start of an inode update
*
@@ -240,8 +246,7 @@ void ext4_fc_start_update(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
- if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
- (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
+ if (ext4_fc_disabled(inode->i_sb))
return;
restart:
@@ -265,8 +270,7 @@ void ext4_fc_stop_update(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
- if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
- (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
+ if (ext4_fc_disabled(inode->i_sb))
return;
if (atomic_dec_and_test(&ei->i_fc_updates))
@@ -283,8 +287,7 @@ void ext4_fc_del(struct inode *inode)
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_fc_dentry_update *fc_dentry;
- if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
- (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
+ if (ext4_fc_disabled(inode->i_sb))
return;
restart:
@@ -337,8 +340,7 @@ void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handl
struct ext4_sb_info *sbi = EXT4_SB(sb);
tid_t tid;
- if (!test_opt2(sb, JOURNAL_FAST_COMMIT) ||
- (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))
+ if (ext4_fc_disabled(sb))
return;
ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
@@ -493,10 +495,8 @@ void __ext4_fc_track_unlink(handle_t *handle,
void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
- (sbi->s_mount_state & EXT4_FC_REPLAY))
+ if (ext4_fc_disabled(inode->i_sb))
return;
if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
@@ -522,10 +522,8 @@ void __ext4_fc_track_link(handle_t *handle,
void ext4_fc_track_link(handle_t *handle, struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
- (sbi->s_mount_state & EXT4_FC_REPLAY))
+ if (ext4_fc_disabled(inode->i_sb))
return;
if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
@@ -551,10 +549,8 @@ void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
- (sbi->s_mount_state & EXT4_FC_REPLAY))
+ if (ext4_fc_disabled(inode->i_sb))
return;
if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
@@ -576,22 +572,20 @@ static int __track_inode(struct inode *inode, void *arg, bool update)
void ext4_fc_track_inode(handle_t *handle, struct inode *inode)
{
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
int ret;
if (S_ISDIR(inode->i_mode))
return;
+ if (ext4_fc_disabled(inode->i_sb))
+ return;
+
if (ext4_should_journal_data(inode)) {
ext4_fc_mark_ineligible(inode->i_sb,
EXT4_FC_REASON_INODE_JOURNAL_DATA, handle);
return;
}
- if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
- (sbi->s_mount_state & EXT4_FC_REPLAY))
- return;
-
if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
return;
@@ -634,15 +628,13 @@ static int __track_range(struct inode *inode, void *arg, bool update)
void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t start,
ext4_lblk_t end)
{
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct __track_range_args args;
int ret;
if (S_ISDIR(inode->i_mode))
return;
- if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
- (sbi->s_mount_state & EXT4_FC_REPLAY))
+ if (ext4_fc_disabled(inode->i_sb))
return;
if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
@@ -710,10 +702,10 @@ static u8 *ext4_fc_reserve_space(struct super_block *sb, int len, u32 *crc)
* After allocating len, we should have space at least for a 0 byte
* padding.
*/
- if (len + sizeof(struct ext4_fc_tl) > bsize)
+ if (len + EXT4_FC_TAG_BASE_LEN > bsize)
return NULL;
- if (bsize - off - 1 > len + sizeof(struct ext4_fc_tl)) {
+ if (bsize - off - 1 > len + EXT4_FC_TAG_BASE_LEN) {
/*
* Only allocate from current buffer if we have enough space for
* this request AND we have space to add a zero byte padding.
@@ -730,10 +722,10 @@ static u8 *ext4_fc_reserve_space(struct super_block *sb, int len, u32 *crc)
/* Need to add PAD tag */
tl = (struct ext4_fc_tl *)(sbi->s_fc_bh->b_data + off);
tl->fc_tag = cpu_to_le16(EXT4_FC_TAG_PAD);
- pad_len = bsize - off - 1 - sizeof(struct ext4_fc_tl);
+ pad_len = bsize - off - 1 - EXT4_FC_TAG_BASE_LEN;
tl->fc_len = cpu_to_le16(pad_len);
if (crc)
- *crc = ext4_chksum(sbi, *crc, tl, sizeof(*tl));
+ *crc = ext4_chksum(sbi, *crc, tl, EXT4_FC_TAG_BASE_LEN);
if (pad_len > 0)
ext4_fc_memzero(sb, tl + 1, pad_len, crc);
ext4_fc_submit_bh(sb, false);
@@ -775,7 +767,7 @@ static int ext4_fc_write_tail(struct super_block *sb, u32 crc)
* ext4_fc_reserve_space takes care of allocating an extra block if
* there's no enough space on this block for accommodating this tail.
*/
- dst = ext4_fc_reserve_space(sb, sizeof(tl) + sizeof(tail), &crc);
+ dst = ext4_fc_reserve_space(sb, EXT4_FC_TAG_BASE_LEN + sizeof(tail), &crc);
if (!dst)
return -ENOSPC;
@@ -785,8 +777,8 @@ static int ext4_fc_write_tail(struct super_block *sb, u32 crc)
tl.fc_len = cpu_to_le16(bsize - off - 1 + sizeof(struct ext4_fc_tail));
sbi->s_fc_bytes = round_up(sbi->s_fc_bytes, bsize);
- ext4_fc_memcpy(sb, dst, &tl, sizeof(tl), &crc);
- dst += sizeof(tl);
+ ext4_fc_memcpy(sb, dst, &tl, EXT4_FC_TAG_BASE_LEN, &crc);
+ dst += EXT4_FC_TAG_BASE_LEN;
tail.fc_tid = cpu_to_le32(sbi->s_journal->j_running_transaction->t_tid);
ext4_fc_memcpy(sb, dst, &tail.fc_tid, sizeof(tail.fc_tid), &crc);
dst += sizeof(tail.fc_tid);
@@ -808,15 +800,15 @@ static bool ext4_fc_add_tlv(struct super_block *sb, u16 tag, u16 len, u8 *val,
struct ext4_fc_tl tl;
u8 *dst;
- dst = ext4_fc_reserve_space(sb, sizeof(tl) + len, crc);
+ dst = ext4_fc_reserve_space(sb, EXT4_FC_TAG_BASE_LEN + len, crc);
if (!dst)
return false;
tl.fc_tag = cpu_to_le16(tag);
tl.fc_len = cpu_to_le16(len);
- ext4_fc_memcpy(sb, dst, &tl, sizeof(tl), crc);
- ext4_fc_memcpy(sb, dst + sizeof(tl), val, len, crc);
+ ext4_fc_memcpy(sb, dst, &tl, EXT4_FC_TAG_BASE_LEN, crc);
+ ext4_fc_memcpy(sb, dst + EXT4_FC_TAG_BASE_LEN, val, len, crc);
return true;
}
@@ -828,8 +820,8 @@ static bool ext4_fc_add_dentry_tlv(struct super_block *sb, u32 *crc,
struct ext4_fc_dentry_info fcd;
struct ext4_fc_tl tl;
int dlen = fc_dentry->fcd_name.len;
- u8 *dst = ext4_fc_reserve_space(sb, sizeof(tl) + sizeof(fcd) + dlen,
- crc);
+ u8 *dst = ext4_fc_reserve_space(sb,
+ EXT4_FC_TAG_BASE_LEN + sizeof(fcd) + dlen, crc);
if (!dst)
return false;
@@ -838,8 +830,8 @@ static bool ext4_fc_add_dentry_tlv(struct super_block *sb, u32 *crc,
fcd.fc_ino = cpu_to_le32(fc_dentry->fcd_ino);
tl.fc_tag = cpu_to_le16(fc_dentry->fcd_op);
tl.fc_len = cpu_to_le16(sizeof(fcd) + dlen);
- ext4_fc_memcpy(sb, dst, &tl, sizeof(tl), crc);
- dst += sizeof(tl);
+ ext4_fc_memcpy(sb, dst, &tl, EXT4_FC_TAG_BASE_LEN, crc);
+ dst += EXT4_FC_TAG_BASE_LEN;
ext4_fc_memcpy(sb, dst, &fcd, sizeof(fcd), crc);
dst += sizeof(fcd);
ext4_fc_memcpy(sb, dst, fc_dentry->fcd_name.name, dlen, crc);
@@ -874,22 +866,25 @@ static int ext4_fc_write_inode(struct inode *inode, u32 *crc)
tl.fc_tag = cpu_to_le16(EXT4_FC_TAG_INODE);
tl.fc_len = cpu_to_le16(inode_len + sizeof(fc_inode.fc_ino));
+ ret = -ECANCELED;
dst = ext4_fc_reserve_space(inode->i_sb,
- sizeof(tl) + inode_len + sizeof(fc_inode.fc_ino), crc);
+ EXT4_FC_TAG_BASE_LEN + inode_len + sizeof(fc_inode.fc_ino), crc);
if (!dst)
- return -ECANCELED;
+ goto err;
- if (!ext4_fc_memcpy(inode->i_sb, dst, &tl, sizeof(tl), crc))
- return -ECANCELED;
- dst += sizeof(tl);
+ if (!ext4_fc_memcpy(inode->i_sb, dst, &tl, EXT4_FC_TAG_BASE_LEN, crc))
+ goto err;
+ dst += EXT4_FC_TAG_BASE_LEN;
if (!ext4_fc_memcpy(inode->i_sb, dst, &fc_inode, sizeof(fc_inode), crc))
- return -ECANCELED;
+ goto err;
dst += sizeof(fc_inode);
if (!ext4_fc_memcpy(inode->i_sb, dst, (u8 *)ext4_raw_inode(&iloc),
inode_len, crc))
- return -ECANCELED;
-
- return 0;
+ goto err;
+ ret = 0;
+err:
+ brelse(iloc.bh);
+ return ret;
}
/*
@@ -1343,7 +1338,7 @@ struct dentry_info_args {
};
static inline void tl_to_darg(struct dentry_info_args *darg,
- struct ext4_fc_tl *tl, u8 *val)
+ struct ext4_fc_tl *tl, u8 *val)
{
struct ext4_fc_dentry_info fcd;
@@ -1352,8 +1347,14 @@ static inline void tl_to_darg(struct dentry_info_args *darg,
darg->parent_ino = le32_to_cpu(fcd.fc_parent_ino);
darg->ino = le32_to_cpu(fcd.fc_ino);
darg->dname = val + offsetof(struct ext4_fc_dentry_info, fc_dname);
- darg->dname_len = le16_to_cpu(tl->fc_len) -
- sizeof(struct ext4_fc_dentry_info);
+ darg->dname_len = tl->fc_len - sizeof(struct ext4_fc_dentry_info);
+}
+
+static inline void ext4_fc_get_tl(struct ext4_fc_tl *tl, u8 *val)
+{
+ memcpy(tl, val, EXT4_FC_TAG_BASE_LEN);
+ tl->fc_len = le16_to_cpu(tl->fc_len);
+ tl->fc_tag = le16_to_cpu(tl->fc_tag);
}
/* Unlink replay function */
@@ -1491,13 +1492,15 @@ static int ext4_fc_record_modified_inode(struct super_block *sb, int ino)
if (state->fc_modified_inodes[i] == ino)
return 0;
if (state->fc_modified_inodes_used == state->fc_modified_inodes_size) {
- state->fc_modified_inodes = krealloc(
- state->fc_modified_inodes,
+ int *fc_modified_inodes;
+
+ fc_modified_inodes = krealloc(state->fc_modified_inodes,
sizeof(int) * (state->fc_modified_inodes_size +
EXT4_FC_REPLAY_REALLOC_INCREMENT),
GFP_KERNEL);
- if (!state->fc_modified_inodes)
+ if (!fc_modified_inodes)
return -ENOMEM;
+ state->fc_modified_inodes = fc_modified_inodes;
state->fc_modified_inodes_size +=
EXT4_FC_REPLAY_REALLOC_INCREMENT;
}
@@ -1516,7 +1519,7 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl,
struct ext4_inode *raw_fc_inode;
struct inode *inode = NULL;
struct ext4_iloc iloc;
- int inode_len, ino, ret, tag = le16_to_cpu(tl->fc_tag);
+ int inode_len, ino, ret, tag = tl->fc_tag;
struct ext4_extent_header *eh;
memcpy(&fc_inode, val, sizeof(fc_inode));
@@ -1541,7 +1544,7 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl,
if (ret)
goto out;
- inode_len = le16_to_cpu(tl->fc_len) - sizeof(struct ext4_fc_inode);
+ inode_len = tl->fc_len - sizeof(struct ext4_fc_inode);
raw_inode = ext4_raw_inode(&iloc);
memcpy(raw_inode, raw_fc_inode, offsetof(struct ext4_inode, i_block));
@@ -1682,15 +1685,18 @@ int ext4_fc_record_regions(struct super_block *sb, int ino,
if (replay && state->fc_regions_used != state->fc_regions_valid)
state->fc_regions_used = state->fc_regions_valid;
if (state->fc_regions_used == state->fc_regions_size) {
+ struct ext4_fc_alloc_region *fc_regions;
+
+ fc_regions = krealloc(state->fc_regions,
+ sizeof(struct ext4_fc_alloc_region) *
+ (state->fc_regions_size +
+ EXT4_FC_REPLAY_REALLOC_INCREMENT),
+ GFP_KERNEL);
+ if (!fc_regions)
+ return -ENOMEM;
state->fc_regions_size +=
EXT4_FC_REPLAY_REALLOC_INCREMENT;
- state->fc_regions = krealloc(
- state->fc_regions,
- state->fc_regions_size *
- sizeof(struct ext4_fc_alloc_region),
- GFP_KERNEL);
- if (!state->fc_regions)
- return -ENOMEM;
+ state->fc_regions = fc_regions;
}
region = &state->fc_regions[state->fc_regions_used++];
region->ino = ino;
@@ -1770,8 +1776,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
ret = ext4_ext_insert_extent(
NULL, inode, &path, &newex, 0);
up_write((&EXT4_I(inode)->i_data_sem));
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
if (ret)
goto out;
goto next;
@@ -1926,8 +1931,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
for (j = 0; j < path->p_depth; j++)
ext4_mb_mark_bb(inode->i_sb,
path[j].p_block, 1, 1);
- ext4_ext_drop_refs(path);
- kfree(path);
+ ext4_free_ext_path(path);
}
cur += ret;
ext4_mb_mark_bb(inode->i_sb, map.m_pblk,
@@ -1972,6 +1976,34 @@ void ext4_fc_replay_cleanup(struct super_block *sb)
kfree(sbi->s_fc_replay_state.fc_modified_inodes);
}
+static inline bool ext4_fc_tag_len_isvalid(struct ext4_fc_tl *tl,
+ u8 *val, u8 *end)
+{
+ if (val + tl->fc_len > end)
+ return false;
+
+ /* Here only check ADD_RANGE/TAIL/HEAD which will read data when do
+ * journal rescan before do CRC check. Other tags length check will
+ * rely on CRC check.
+ */
+ switch (tl->fc_tag) {
+ case EXT4_FC_TAG_ADD_RANGE:
+ return (sizeof(struct ext4_fc_add_range) == tl->fc_len);
+ case EXT4_FC_TAG_TAIL:
+ return (sizeof(struct ext4_fc_tail) <= tl->fc_len);
+ case EXT4_FC_TAG_HEAD:
+ return (sizeof(struct ext4_fc_head) == tl->fc_len);
+ case EXT4_FC_TAG_DEL_RANGE:
+ case EXT4_FC_TAG_LINK:
+ case EXT4_FC_TAG_UNLINK:
+ case EXT4_FC_TAG_CREAT:
+ case EXT4_FC_TAG_INODE:
+ case EXT4_FC_TAG_PAD:
+ default:
+ return true;
+ }
+}
+
/*
* Recovery Scan phase handler
*
@@ -2028,12 +2060,18 @@ static int ext4_fc_replay_scan(journal_t *journal,
}
state->fc_replay_expected_off++;
- for (cur = start; cur < end; cur = cur + sizeof(tl) + le16_to_cpu(tl.fc_len)) {
- memcpy(&tl, cur, sizeof(tl));
- val = cur + sizeof(tl);
+ for (cur = start; cur < end - EXT4_FC_TAG_BASE_LEN;
+ cur = cur + EXT4_FC_TAG_BASE_LEN + tl.fc_len) {
+ ext4_fc_get_tl(&tl, cur);
+ val =