summaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/balloc.c2
-rw-r--r--fs/ext4/block_validity.c16
-rw-r--r--fs/ext4/dir.c7
-rw-r--r--fs/ext4/ext4.h81
-rw-r--r--fs/ext4/ext4_jbd2.c21
-rw-r--r--fs/ext4/ext4_jbd2.h14
-rw-r--r--fs/ext4/extents.c5
-rw-r--r--fs/ext4/fast_commit.c134
-rw-r--r--fs/ext4/fast_commit.h78
-rw-r--r--fs/ext4/file.c7
-rw-r--r--fs/ext4/fsync.c2
-rw-r--r--fs/ext4/indirect.c4
-rw-r--r--fs/ext4/inode-test.c320
-rw-r--r--fs/ext4/inode.c41
-rw-r--r--fs/ext4/ioctl.c5
-rw-r--r--fs/ext4/mballoc.c39
-rw-r--r--fs/ext4/namei.c40
-rw-r--r--fs/ext4/page-io.c5
-rw-r--r--fs/ext4/resize.c20
-rw-r--r--fs/ext4/super.c569
-rw-r--r--fs/ext4/sysfs.c10
-rw-r--r--fs/ext4/xattr.c6
22 files changed, 768 insertions, 658 deletions
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 1d640b145637..f45f9feebe59 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -185,7 +185,7 @@ static int ext4_init_block_bitmap(struct super_block *sb,
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_fsblk_t start, tmp;
- J_ASSERT_BH(bh, buffer_locked(bh));
+ ASSERT(buffer_locked(bh));
/* If checksum is bad mark all blocks used to prevent allocation
* essentially implementing a per-group read-only flag. */
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 8e6ca23ed172..4666b55b736e 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -176,12 +176,10 @@ static int ext4_protect_reserved_inode(struct super_block *sb,
err = add_system_zone(system_blks, map.m_pblk, n, ino);
if (err < 0) {
if (err == -EFSCORRUPTED) {
- __ext4_error(sb, __func__, __LINE__,
- -err, map.m_pblk,
- "blocks %llu-%llu from inode %u overlap system zone",
- map.m_pblk,
- map.m_pblk + map.m_len - 1,
- ino);
+ EXT4_ERROR_INODE_ERR(inode, -err,
+ "blocks %llu-%llu from inode overlap system zone",
+ map.m_pblk,
+ map.m_pblk + map.m_len - 1);
}
break;
}
@@ -206,7 +204,7 @@ static void ext4_destroy_system_zone(struct rcu_head *rcu)
*
* The update of system_blks pointer in this function is protected by
* sb->s_umount semaphore. However we have to be careful as we can be
- * racing with ext4_data_block_valid() calls reading system_blks rbtree
+ * racing with ext4_inode_block_valid() calls reading system_blks rbtree
* protected only by RCU. That's why we first build the rbtree and then
* swap it in place.
*/
@@ -258,7 +256,7 @@ int ext4_setup_system_zone(struct super_block *sb)
/*
* System blks rbtree complete, announce it once to prevent racing
- * with ext4_data_block_valid() accessing the rbtree at the same
+ * with ext4_inode_block_valid() accessing the rbtree at the same
* time.
*/
rcu_assign_pointer(sbi->s_system_blks, system_blks);
@@ -278,7 +276,7 @@ err:
*
* The update of system_blks pointer in this function is protected by
* sb->s_umount semaphore. However we have to be careful as we can be
- * racing with ext4_data_block_valid() calls reading system_blks rbtree
+ * racing with ext4_inode_block_valid() calls reading system_blks rbtree
* protected only by RCU. So we first clear the system_blks pointer and
* then free the rbtree only after RCU grace period expires.
*/
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index c6d16353326a..5ed870614c8d 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -657,10 +657,3 @@ const struct file_operations ext4_dir_operations = {
.fsync = ext4_sync_file,
.release = ext4_release_dir,
};
-
-#ifdef CONFIG_UNICODE
-const struct dentry_operations ext4_dentry_ops = {
- .d_hash = generic_ci_d_hash,
- .d_compare = generic_ci_d_compare,
-};
-#endif
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 65ecaf96d0a4..2866d249f3d2 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -98,6 +98,16 @@
#define ext_debug(ino, fmt, ...) no_printk(fmt, ##__VA_ARGS__)
#endif
+#define ASSERT(assert) \
+do { \
+ if (unlikely(!(assert))) { \
+ printk(KERN_EMERG \
+ "Assertion failure in %s() at %s:%d: '%s'\n", \
+ __func__, __FILE__, __LINE__, #assert); \
+ BUG(); \
+ } \
+} while (0)
+
/* data type for block offset of block group */
typedef int ext4_grpblk_t;
@@ -1619,6 +1629,27 @@ struct ext4_sb_info {
errseq_t s_bdev_wb_err;
spinlock_t s_bdev_wb_lock;
+ /* Information about errors that happened during this mount */
+ spinlock_t s_error_lock;
+ int s_add_error_count;
+ int s_first_error_code;
+ __u32 s_first_error_line;
+ __u32 s_first_error_ino;
+ __u64 s_first_error_block;
+ const char *s_first_error_func;
+ time64_t s_first_error_time;
+ int s_last_error_code;
+ __u32 s_last_error_line;
+ __u32 s_last_error_ino;
+ __u64 s_last_error_block;
+ const char *s_last_error_func;
+ time64_t s_last_error_time;
+ /*
+ * If we are in a context where we cannot update error information in
+ * the on-disk superblock, we queue this work to do it.
+ */
+ struct work_struct s_error_work;
+
/* Ext4 fast commit stuff */
atomic_t s_fc_subtid;
atomic_t s_fc_ineligible_updates;
@@ -1858,7 +1889,6 @@ static inline bool ext4_verity_in_progress(struct inode *inode)
#define EXT4_GOOD_OLD_REV 0 /* The good old (original) format */
#define EXT4_DYNAMIC_REV 1 /* V2 format w/ dynamic inode sizes */
-#define EXT4_CURRENT_REV EXT4_GOOD_OLD_REV
#define EXT4_MAX_SUPP_REV EXT4_DYNAMIC_REV
#define EXT4_GOOD_OLD_INODE_SIZE 128
@@ -2952,9 +2982,9 @@ extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
ext4_group_t block_group,
unsigned int flags);
-extern __printf(6, 7)
-void __ext4_error(struct super_block *, const char *, unsigned int, int, __u64,
- const char *, ...);
+extern __printf(7, 8)
+void __ext4_error(struct super_block *, const char *, unsigned int, bool,
+ int, __u64, const char *, ...);
extern __printf(6, 7)
void __ext4_error_inode(struct inode *, const char *, unsigned int,
ext4_fsblk_t, int, const char *, ...);
@@ -2963,9 +2993,6 @@ void __ext4_error_file(struct file *, const char *, unsigned int, ext4_fsblk_t,
const char *, ...);
extern void __ext4_std_error(struct super_block *, const char *,
unsigned int, int);
-extern __printf(5, 6)
-void __ext4_abort(struct super_block *, const char *, unsigned int, int,
- const char *, ...);
extern __printf(4, 5)
void __ext4_warning(struct super_block *, const char *, unsigned int,
const char *, ...);
@@ -2995,6 +3022,9 @@ void __ext4_grp_locked_error(const char *, unsigned int,
#define EXT4_ERROR_FILE(file, block, fmt, a...) \
ext4_error_file((file), __func__, __LINE__, (block), (fmt), ## a)
+#define ext4_abort(sb, err, fmt, a...) \
+ __ext4_error((sb), __func__, __LINE__, true, (err), 0, (fmt), ## a)
+
#ifdef CONFIG_PRINTK
#define ext4_error_inode(inode, func, line, block, fmt, ...) \
@@ -3005,11 +3035,11 @@ void __ext4_grp_locked_error(const char *, unsigned int,
#define ext4_error_file(file, func, line, block, fmt, ...) \
__ext4_error_file(file, func, line, block, fmt, ##__VA_ARGS__)
#define ext4_error(sb, fmt, ...) \
- __ext4_error((sb), __func__, __LINE__, 0, 0, (fmt), ##__VA_ARGS__)
+ __ext4_error((sb), __func__, __LINE__, false, 0, 0, (fmt), \
+ ##__VA_ARGS__)
#define ext4_error_err(sb, err, fmt, ...) \
- __ext4_error((sb), __func__, __LINE__, (err), 0, (fmt), ##__VA_ARGS__)
-#define ext4_abort(sb, err, fmt, ...) \
- __ext4_abort((sb), __func__, __LINE__, (err), (fmt), ##__VA_ARGS__)
+ __ext4_error((sb), __func__, __LINE__, false, (err), 0, (fmt), \
+ ##__VA_ARGS__)
#define ext4_warning(sb, fmt, ...) \
__ext4_warning(sb, __func__, __LINE__, fmt, ##__VA_ARGS__)
#define ext4_warning_inode(inode, fmt, ...) \
@@ -3042,17 +3072,12 @@ do { \
#define ext4_error(sb, fmt, ...) \
do { \
no_printk(fmt, ##__VA_ARGS__); \
- __ext4_error(sb, "", 0, 0, 0, " "); \
+ __ext4_error(sb, "", 0, false, 0, 0, " "); \
} while (0)
#define ext4_error_err(sb, err, fmt, ...) \
do { \
no_printk(fmt, ##__VA_ARGS__); \
- __ext4_error(sb, "", 0, err, 0, " "); \
-} while (0)
-#define ext4_abort(sb, err, fmt, ...) \
-do { \
- no_printk(fmt, ##__VA_ARGS__); \
- __ext4_abort(sb, "", 0, err, " "); \
+ __ext4_error(sb, "", 0, false, err, 0, " "); \
} while (0)
#define ext4_warning(sb, fmt, ...) \
do { \
@@ -3361,6 +3386,21 @@ static inline void ext4_unlock_group(struct super_block *sb,
spin_unlock(ext4_group_lock_ptr(sb, group));
}
+#ifdef CONFIG_QUOTA
+static inline bool ext4_quota_capable(struct super_block *sb)
+{
+ return (test_opt(sb, QUOTA) || ext4_has_feature_quota(sb));
+}
+
+static inline bool ext4_is_quota_journalled(struct super_block *sb)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ return (ext4_has_feature_quota(sb) ||
+ sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]);
+}
+#endif
+
/*
* Block validity checking
*/
@@ -3381,10 +3421,6 @@ static inline void ext4_unlock_group(struct super_block *sb,
/* dir.c */
extern const struct file_operations ext4_dir_operations;
-#ifdef CONFIG_UNICODE
-extern const struct dentry_operations ext4_dentry_ops;
-#endif
-
/* file.c */
extern const struct inode_operations ext4_file_inode_operations;
extern const struct file_operations ext4_file_operations;
@@ -3613,7 +3649,6 @@ extern void ext4_io_submit(struct ext4_io_submit *io);
extern int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
- struct writeback_control *wbc,
bool keep_towrite);
extern struct ext4_io_end_vec *ext4_alloc_io_end_vec(ext4_io_end_t *io_end);
extern struct ext4_io_end_vec *ext4_last_io_end_vec(ext4_io_end_t *io_end);
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 0fd0c42a4f7d..be799040a415 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -296,8 +296,8 @@ int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
if (err) {
ext4_journal_abort_handle(where, line, __func__,
bh, handle, err);
- __ext4_abort(inode->i_sb, where, line, -err,
- "error %d when attempting revoke", err);
+ __ext4_error(inode->i_sb, where, line, true, -err, 0,
+ "error %d when attempting revoke", err);
}
BUFFER_TRACE(bh, "exit");
return err;
@@ -372,20 +372,3 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
}
return err;
}
-
-int __ext4_handle_dirty_super(const char *where, unsigned int line,
- handle_t *handle, struct super_block *sb)
-{
- struct buffer_head *bh = EXT4_SB(sb)->s_sbh;
- int err = 0;
-
- ext4_superblock_csum_set(sb);
- if (ext4_handle_valid(handle)) {
- err = jbd2_journal_dirty_metadata(handle, bh);
- if (err)
- ext4_journal_abort_handle(where, line, __func__,
- bh, handle, err);
- } else
- mark_buffer_dirty(bh);
- return err;
-}
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 00dc668e052b..0d2fa423b7ad 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -86,17 +86,14 @@
#ifdef CONFIG_QUOTA
/* Amount of blocks needed for quota update - we know that the structure was
* allocated so we need to update only data block */
-#define EXT4_QUOTA_TRANS_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
- ext4_has_feature_quota(sb)) ? 1 : 0)
+#define EXT4_QUOTA_TRANS_BLOCKS(sb) ((ext4_quota_capable(sb)) ? 1 : 0)
/* Amount of blocks needed for quota insert/delete - we do some block writes
* but inode, sb and group updates are done only once */
-#define EXT4_QUOTA_INIT_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
- ext4_has_feature_quota(sb)) ?\
+#define EXT4_QUOTA_INIT_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\
(DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\
+3+DQUOT_INIT_REWRITE) : 0)
-#define EXT4_QUOTA_DEL_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
- ext4_has_feature_quota(sb)) ?\
+#define EXT4_QUOTA_DEL_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\
(DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\
+3+DQUOT_DEL_REWRITE) : 0)
#else
@@ -247,9 +244,6 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
handle_t *handle, struct inode *inode,
struct buffer_head *bh);
-int __ext4_handle_dirty_super(const char *where, unsigned int line,
- handle_t *handle, struct super_block *sb);
-
#define ext4_journal_get_write_access(handle, bh) \
__ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh))
#define ext4_forget(handle, is_metadata, inode, bh, block_nr) \
@@ -260,8 +254,6 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line,
#define ext4_handle_dirty_metadata(handle, inode, bh) \
__ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \
(bh))
-#define ext4_handle_dirty_super(handle, sb) \
- __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb))
handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
int type, int blocks, int rsv_blocks,
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 17d7096b3212..3960b7ec3ab7 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -5815,8 +5815,8 @@ int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start,
int ret;
path = ext4_find_extent(inode, start, NULL, 0);
- if (!path)
- return -EINVAL;
+ if (IS_ERR(path))
+ return PTR_ERR(path);
ex = path[path->p_depth].p_ext;
if (!ex) {
ret = -EFSCORRUPTED;
@@ -5988,7 +5988,6 @@ int ext4_ext_replay_set_iblocks(struct inode *inode)
kfree(path);
break;
}
- ex = path2[path2->p_depth].p_ext;
for (i = 0; i <= max(path->p_depth, path2->p_depth); i++) {
cmp1 = cmp2 = 0;
if (i <= path->p_depth)
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index f2033e13a273..0a14a7c87bf8 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -103,8 +103,69 @@
*
* Replay code should thus check for all the valid tails in the FC area.
*
+ * Fast Commit Replay Idempotence
+ * ------------------------------
+ *
+ * Fast commits tags are idempotent in nature provided the recovery code follows
+ * certain rules. The guiding principle that the commit path follows while
+ * committing is that it stores the result of a particular operation instead of
+ * storing the procedure.
+ *
+ * Let's consider this rename operation: 'mv /a /b'. Let's assume dirent '/a'
+ * was associated with inode 10. During fast commit, instead of storing this
+ * operation as a procedure "rename a to b", we store the resulting file system
+ * state as a "series" of outcomes:
+ *
+ * - Link dirent b to inode 10
+ * - Unlink dirent a
+ * - Inode <10> with valid refcount
+ *
+ * Now when recovery code runs, it needs "enforce" this state on the file
+ * system. This is what guarantees idempotence of fast commit replay.
+ *
+ * Let's take an example of a procedure that is not idempotent and see how fast
+ * commits make it idempotent. Consider following sequence of operations:
+ *
+ * rm A; mv B A; read A
+ * (x) (y) (z)
+ *
+ * (x), (y) and (z) are the points at which we can crash. If we store this
+ * sequence of operations as is then the replay is not idempotent. Let's say
+ * while in replay, we crash at (z). During the second replay, file A (which was
+ * actually created as a result of "mv B A" operation) would get deleted. Thus,
+ * file named A would be absent when we try to read A. So, this sequence of
+ * operations is not idempotent. However, as mentioned above, instead of storing
+ * the procedure fast commits store the outcome of each procedure. Thus the fast
+ * commit log for above procedure would be as follows:
+ *
+ * (Let's assume dirent A was linked to inode 10 and dirent B was linked to
+ * inode 11 before the replay)
+ *
+ * [Unlink A] [Link A to inode 11] [Unlink B] [Inode 11]
+ * (w) (x) (y) (z)
+ *
+ * If we crash at (z), we will have file A linked to inode 11. During the second
+ * replay, we will remove file A (inode 11). But we will create it back and make
+ * it point to inode 11. We won't find B, so we'll just skip that step. At this
+ * point, the refcount for inode 11 is not reliable, but that gets fixed by the
+ * replay of last inode 11 tag. Crashes at points (w), (x) and (y) get handled
+ * similarly. Thus, by converting a non-idempotent procedure into a series of
+ * idempotent outcomes, fast commits ensured idempotence during the replay.
+ *
* TODOs
* -----
+ *
+ * 0) Fast commit replay path hardening: Fast commit replay code should use
+ * journal handles to make sure all the updates it does during the replay
+ * path are atomic. With that if we crash during fast commit replay, after
+ * trying to do recovery again, we will find a file system where fast commit
+ * area is invalid (because new full commit would be found). In order to deal
+ * with that, fast commit replay code should ensure that the "FC_REPLAY"
+ * superblock state is persisted before starting the replay, so that after
+ * the crash, fast commit recovery code can look at that flag and perform
+ * fast commit recovery even if that area is invalidated by later full
+ * commits.
+ *
* 1) Make fast commit atomic updates more fine grained. Today, a fast commit
* eligible update must be protected within ext4_fc_start_update() and
* ext4_fc_stop_update(). These routines are called at much higher
@@ -543,13 +604,13 @@ void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t star
trace_ext4_fc_track_range(inode, start, end, ret);
}
-static void ext4_fc_submit_bh(struct super_block *sb)
+static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail)
{
int write_flags = REQ_SYNC;
struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh;
- /* TODO: REQ_FUA | REQ_PREFLUSH is unnecessarily expensive. */
- if (test_opt(sb, BARRIER))
+ /* Add REQ_FUA | REQ_PREFLUSH only its tail */
+ if (test_opt(sb, BARRIER) && is_tail)
write_flags |= REQ_FUA | REQ_PREFLUSH;
lock_buffer(bh);
set_buffer_dirty(bh);
@@ -623,7 +684,7 @@ static u8 *ext4_fc_reserve_space(struct super_block *sb, int len, u32 *crc)
*crc = ext4_chksum(sbi, *crc, tl, sizeof(*tl));
if (pad_len > 0)
ext4_fc_memzero(sb, tl + 1, pad_len, crc);
- ext4_fc_submit_bh(sb);
+ ext4_fc_submit_bh(sb, false);
ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh);
if (ret)
@@ -680,7 +741,7 @@ static int ext4_fc_write_tail(struct super_block *sb, u32 crc)
tail.fc_crc = cpu_to_le32(crc);
ext4_fc_memcpy(sb, dst, &tail.fc_crc, sizeof(tail.fc_crc), NULL);
- ext4_fc_submit_bh(sb);
+ ext4_fc_submit_bh(sb, true);
return 0;
}
@@ -1207,7 +1268,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
list_splice_init(&sbi->s_fc_dentry_q[FC_Q_STAGING],
&sbi->s_fc_dentry_q[FC_Q_MAIN]);
list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
- &sbi->s_fc_q[FC_Q_STAGING]);
+ &sbi->s_fc_q[FC_Q_MAIN]);
ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
@@ -1220,18 +1281,6 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
/* Ext4 Replay Path Routines */
-/* Get length of a particular tlv */
-static inline int ext4_fc_tag_len(struct ext4_fc_tl *tl)
-{
- return le16_to_cpu(tl->fc_len);
-}
-
-/* Get a pointer to "value" of a tlv */
-static inline u8 *ext4_fc_tag_val(struct ext4_fc_tl *tl)
-{
- return (u8 *)tl + sizeof(*tl);
-}
-
/* Helper struct for dentry replay routines */
struct dentry_info_args {
int parent_ino, dname_len, ino, inode_len;
@@ -1269,14 +1318,14 @@ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl)
entry.len = darg.dname_len;
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode %d not found", darg.ino);
return 0;
}
old_parent = ext4_iget(sb, darg.parent_ino,
EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(old_parent)) {
+ if (IS_ERR(old_parent)) {
jbd_debug(1, "Dir with inode %d not found", darg.parent_ino);
iput(inode);
return 0;
@@ -1361,7 +1410,7 @@ static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl)
darg.parent_ino, darg.dname_len);
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode not found.");
return 0;
}
@@ -1417,10 +1466,11 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
trace_ext4_fc_replay(sb, tag, ino, 0, 0);
inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
- if (!IS_ERR_OR_NULL(inode)) {
+ if (!IS_ERR(inode)) {
ext4_ext_clear_bb(inode);
iput(inode);
}
+ inode = NULL;
ext4_fc_record_modified_inode(sb, ino);
@@ -1463,7 +1513,7 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
/* Given that we just wrote the inode on disk, this SHOULD succeed. */
inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode not found.");
return -EFSCORRUPTED;
}
@@ -1515,7 +1565,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl)
goto out;
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "inode %d not found.", darg.ino);
inode = NULL;
ret = -EINVAL;
@@ -1528,7 +1578,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl)
* dot and dot dot dirents are setup properly.
*/
dir = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(dir)) {
+ if (IS_ERR(dir)) {
jbd_debug(1, "Dir %d not found.", darg.ino);
goto out;
}
@@ -1604,7 +1654,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
inode = ext4_iget(sb, le32_to_cpu(fc_add_ex->fc_ino),
EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode not found.");
return 0;
}
@@ -1728,7 +1778,7 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl)
le32_to_cpu(lrange->fc_ino), cur, remaining);
inode = ext4_iget(sb, le32_to_cpu(lrange->fc_ino), EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange->fc_ino));
return 0;
}
@@ -1770,32 +1820,6 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl)
return 0;
}
-static inline const char *tag2str(u16 tag)
-{
- switch (tag) {
- case EXT4_FC_TAG_LINK:
- return "TAG_ADD_ENTRY";
- case EXT4_FC_TAG_UNLINK:
- return "TAG_DEL_ENTRY";
- case EXT4_FC_TAG_ADD_RANGE:
- return "TAG_ADD_RANGE";
- case EXT4_FC_TAG_CREAT:
- return "TAG_CREAT_DENTRY";
- case EXT4_FC_TAG_DEL_RANGE:
- return "TAG_DEL_RANGE";
- case EXT4_FC_TAG_INODE:
- return "TAG_INODE";
- case EXT4_FC_TAG_PAD:
- return "TAG_PAD";
- case EXT4_FC_TAG_TAIL:
- return "TAG_TAIL";
- case EXT4_FC_TAG_HEAD:
- return "TAG_HEAD";
- default:
- return "TAG_ERROR";
- }
-}
-
static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
{
struct ext4_fc_replay_state *state;
@@ -1809,7 +1833,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
for (i = 0; i < state->fc_modified_inodes_used; i++) {
inode = ext4_iget(sb, state->fc_modified_inodes[i],
EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode %d not found.",
state->fc_modified_inodes[i]);
continue;
@@ -1826,7 +1850,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
if (ret > 0) {
path = ext4_find_extent(inode, map.m_lblk, NULL, 0);
- if (!IS_ERR_OR_NULL(path)) {
+ if (!IS_ERR(path)) {
for (j = 0; j < path->p_depth; j++)
ext4_mb_mark_bb(inode->i_sb,
path[j].p_block, 1, 1);
diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h
index 3a6e5a1fa1b8..b77f70f55a62 100644
--- a/fs/ext4/fast_commit.h
+++ b/fs/ext4/fast_commit.h
@@ -3,6 +3,11 @@
#ifndef __FAST_COMMIT_H__
#define __FAST_COMMIT_H__
+/*
+ * Note this file is present in e2fsprogs/lib/ext2fs/fast_commit.h and
+ * linux/fs/ext4/fast_commit.h. These file should always be byte identical.
+ */
+
/* Fast commit tags */
#define EXT4_FC_TAG_ADD_RANGE 0x0001
#define EXT4_FC_TAG_DEL_RANGE 0x0002
@@ -50,7 +55,7 @@ struct ext4_fc_del_range {
struct ext4_fc_dentry_info {
__le32 fc_parent_ino;
__le32 fc_ino;
- u8 fc_dname[0];
+ __u8 fc_dname[0];
};
/* Value structure for EXT4_FC_TAG_INODE and EXT4_FC_TAG_INODE_PARTIAL. */
@@ -66,19 +71,6 @@ struct ext4_fc_tail {
};
/*
- * In memory list of dentry updates that are performed on the file
- * system used by fast commit code.
- */
-struct ext4_fc_dentry_update {
- int fcd_op; /* Type of update create / unlink / link */
- int fcd_parent; /* Parent inode number */
- int fcd_ino; /* Inode number */
- struct qstr fcd_name; /* Dirent name */
- unsigned char fcd_iname[DNAME_INLINE_LEN]; /* Dirent name string */
- struct list_head fcd_list;
-};
-
-/*
* Fast commit reason codes
*/
enum {
@@ -107,6 +99,20 @@ enum {
EXT4_FC_REASON_MAX
};
+#ifdef __KERNEL__
+/*
+ * In memory list of dentry updates that are performed on the file
+ * system used by fast commit code.
+ */
+struct ext4_fc_dentry_update {
+ int fcd_op; /* Type of update create / unlink / link */
+ int fcd_parent; /* Parent inode number */
+ int fcd_ino; /* Inode number */
+ struct qstr fcd_name; /* Dirent name */
+ unsigned char fcd_iname[DNAME_INLINE_LEN]; /* Dirent name string */
+ struct list_head fcd_list;
+};
+
struct ext4_fc_stats {
unsigned int fc_ineligible_reason_count[EXT4_FC_REASON_MAX];
unsigned long fc_num_commits;
@@ -145,13 +151,51 @@ struct ext4_fc_replay_state {
};
#define region_last(__region) (((__region)->lblk) + ((__region)->len) - 1)
+#endif
#define fc_for_each_tl(__start, __end, __tl) \
- for (tl = (struct ext4_fc_tl *)start; \
- (u8 *)tl < (u8 *)end; \
- tl = (struct ext4_fc_tl *)((u8 *)tl + \
+ for (tl = (struct ext4_fc_tl *)(__start); \
+ (__u8 *)tl < (__u8 *)(__end); \
+ tl = (struct ext4_fc_tl *)((__u8 *)tl + \
sizeof(struct ext4_fc_tl) + \
+ le16_to_cpu(tl->fc_len)))
+static inline const char *tag2str(__u16 tag)
+{
+ switch (tag) {
+ case EXT4_FC_TAG_LINK:
+ return "ADD_ENTRY";
+ case EXT4_FC_TAG_UNLINK:
+ return "DEL_ENTRY";
+ case EXT4_FC_TAG_ADD_RANGE:
+ return "ADD_RANGE";
+ case EXT4_FC_TAG_CREAT:
+ return "CREAT_DENTRY";
+ case EXT4_FC_TAG_DEL_RANGE:
+ return "DEL_RANGE";
+ case EXT4_FC_TAG_INODE:
+ return "INODE";
+ case EXT4_FC_TAG_PAD:
+ return "PAD";
+ case EXT4_FC_TAG_TAIL:
+ return "TAIL";
+ case EXT4_FC_TAG_HEAD:
+ return "HEAD";
+ default:
+ return "ERROR";
+ }
+}
+
+/* Get length of a particular tlv */
+static inline int ext4_fc_tag_len(struct ext4_fc_tl *tl)
+{
+ return le16_to_cpu(tl->fc_len);
+}
+
+/* Get a pointer to "value" of a tlv */
+static inline __u8 *ext4_fc_tag_val(struct ext4_fc_tl *tl)
+{
+ return (__u8 *)tl + sizeof(*tl);
+}
#endif /* __FAST_COMMIT_H__ */
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 3ed8c048fb12..349b27f0dda0 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -809,9 +809,12 @@ static int ext4_sample_last_mounted(struct super_block *sb,
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto out_journal;
- strlcpy(sbi->s_es->s_last_mounted, cp,
+ lock_buffer(sbi->s_sbh);
+ strncpy(sbi->s_es->s_last_mounted, cp,
sizeof(sbi->s_es->s_last_mounted));
- ext4_handle_dirty_super(handle, sb);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
out_journal:
ext4_journal_stop(handle);
out:
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index a42ca95840f2..113bfb023a4a 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -136,7 +136,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
if (unlikely(ext4_forced_shutdown(sbi)))
return -EIO;
- J_ASSERT(ext4_journal_current_handle() == NULL);
+ ASSERT(ext4_journal_current_handle() == NULL);
trace_ext4_sync_file_enter(file, datasync);
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 05efa682bc2f..1223a18c3ff9 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -534,8 +534,8 @@ int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
ext4_fsblk_t first_block = 0;
trace_ext4_ind_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
- J_ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)));
- J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
+ ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)));
+ ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
depth = ext4_block_to_path(inode, map->m_lblk, offsets,
&blocks_to_boundary);
diff --git a/fs/ext4/inode-test.c b/fs/ext4/inode-test.c
index d62d802c9c12..7935ea6cf92c 100644
--- a/fs/ext4/inode-test.c
+++ b/fs/ext4/inode-test.c
@@ -80,6 +80,145 @@ struct timestamp_expectation {
bool lower_bound;
};
+static const struct timestamp_expectation test_data[] = {
+ {
+ .test_case_name = LOWER_BOUND_NEG_NO_EXTRA_BITS_CASE,
+ .msb_set = true,
+ .lower_bound = true,
+ .extra_bits = 0,
+ .expected = {.tv_sec = -0x80000000LL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = UPPER_BOUND_NEG_NO_EXTRA_BITS_CASE,
+ .msb_set = true,
+ .lower_bound = false,
+ .extra_bits = 0,
+ .expected = {.tv_sec = -1LL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = LOWER_BOUND_NONNEG_NO_EXTRA_BITS_CASE,
+ .msb_set = false,
+ .lower_bound = true,
+ .extra_bits = 0,
+ .expected = {0LL, 0L},
+ },
+
+ {
+ .test_case_name = UPPER_BOUND_NONNEG_NO_EXTRA_BITS_CASE,
+ .msb_set = false,
+ .lower_bound = false,
+ .extra_bits = 0,
+ .expected = {.tv_sec = 0x7fffffffLL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = LOWER_BOUND_NEG_LO_1_CASE,
+ .msb_set = true,
+ .lower_bound = true,
+ .extra_bits = 1,
+ .expected = {.tv_sec = 0x80000000LL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = UPPER_BOUND_NEG_LO_1_CASE,
+ .msb_set = true,
+ .lower_bound = false,
+ .extra_bits = 1,
+ .expected = {.tv_sec = 0xffffffffLL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = LOWER_BOUND_NONNEG_LO_1_CASE,
+ .msb_set = false,
+ .lower_bound = true,
+ .extra_bits = 1,
+ .expected = {.tv_sec = 0x100000000LL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = UPPER_BOUND_NONNEG_LO_1_CASE,
+ .msb_set = false,
+ .lower_bound = false,
+ .extra_bits = 1,
+ .expected = {.tv_sec = 0x17fffffffLL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = LOWER_BOUND_NEG_HI_1_CASE,
+ .msb_set = true,
+ .lower_bound = true,
+ .extra_bits = 2,
+ .expected = {.tv_sec = 0x180000000LL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = UPPER_BOUND_NEG_HI_1_CASE,
+ .msb_set = true,
+ .lower_bound = false,
+ .extra_bits = 2,
+ .expected = {.tv_sec = 0x1ffffffffLL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = LOWER_BOUND_NONNEG_HI_1_CASE,
+ .msb_set = false,
+ .lower_bound = true,
+ .extra_bits = 2,
+ .expected = {.tv_sec = 0x200000000LL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = UPPER_BOUND_NONNEG_HI_1_CASE,
+ .msb_set = false,
+ .lower_bound = false,
+ .extra_bits = 2,
+ .expected = {.tv_sec = 0x27fffffffLL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = UPPER_BOUND_NONNEG_HI_1_NS_1_CASE,
+ .msb_set = false,
+ .lower_bound = false,
+ .extra_bits = 6,
+ .expected = {.tv_sec = 0x27fffffffLL, .tv_nsec = 1L},
+ },
+
+ {
+ .test_case_name = LOWER_BOUND_NONNEG_HI_1_NS_MAX_CASE,
+ .msb_set = false,
+ .lower_bound = true,
+ .extra_bits = 0xFFFFFFFF,
+ .expected = {.tv_sec = 0x300000000LL,
+ .tv_nsec = MAX_NANOSECONDS},
+ },
+
+ {
+ .test_case_name = LOWER_BOUND_NONNEG_EXTRA_BITS_1_CASE,
+ .msb_set = false,
+ .lower_bound = true,
+ .extra_bits = 3,
+ .expected = {.tv_sec = 0x300000000LL, .tv_nsec = 0L},
+ },
+
+ {
+ .test_case_name = UPPER_BOUND_NONNEG_EXTRA_BITS_1_CASE,
+ .msb_set = false,
+ .lower_bound = false,
+ .extra_bits = 3,
+ .expected = {.tv_sec = 0x37fffffffLL, .tv_nsec = 0L},
+ }
+};
+
+static void timestamp_expectation_to_desc(const struct timestamp_expectation *t,
+ char *desc)
+{
+ strscpy(desc, t->test_case_name, KUNIT_PARAM_DESC_SIZE);
+}
+
+KUNIT_ARRAY_PARAM(ext4_inode, test_data, timestamp_expectation_to_desc);
+
static time64_t get_32bit_time(const struct timestamp_expectation * const test)
{
if (test->msb_set) {
@@ -101,166 +240,35 @@ static time64_t get_32bit_time(const struct timestamp_expectation * const test)
*/
static void inode_test_xtimestamp_decoding(struct kunit *test)
{
- const struct timestamp_expectation test_data[] = {
- {
- .test_case_name = LOWER_BOUND_NEG_NO_EXTRA_BITS_CASE,
- .msb_set = true,
- .lower_bound = true,
- .extra_bits = 0,
- .expected = {.tv_sec = -0x80000000LL, .tv_nsec = 0L},
- },
-
- {
- .test_case_name = UPPER_BOUND_NEG_NO_EXTRA_BITS_CASE,
- .msb_set = true,
- .lower_bound = false,
- .extra_bits = 0,
- .expected = {.tv_sec = -1LL, .tv_nsec = 0L},
- },
-
- {
- .test_case_name = LOWER_BOUND_NONNEG_NO_EXTRA_BITS_CASE,
- .msb_set = false,
- .lower_bound = true,
- .extra_bits = 0,
- .expected = {0LL, 0L},
- },
-
- {
- .test_case_name = UPPER_BOUND_NONNEG_NO_EXTRA_BITS_CASE,
- .msb_set = false,
- .lower_bound = false,
- .extra_bits = 0,
- .expected = {.tv_sec = 0x7fffffffLL, .tv_nsec = 0L},
- },
-
- {
- .test_case_name = LOWER_BOUND_NEG_LO_1_CASE,
- .msb_set = true,
- .lower_bound = true,
- .extra_bits = 1,
- .expected = {.tv_sec = 0x80000000LL, .tv_nsec = 0L},
- },
-
- {
- .test_case_name = UPPER_BOUND_NEG_LO_1_CASE,
- .msb_set = true,
- .lower_bound = false,
- .extra_bits = 1,
- .expected = {.tv_sec = 0xffffffffLL, .tv_nsec = 0L},
- },
-
- {
- .test_case_name = LOWER_BOUND_NONNEG_LO_1_CASE,
- .msb_set = false,
- .lower_bound = true,
- .extra_bits = 1,
- .expected = {.tv_sec = 0x100000000LL, .tv_nsec = 0L},
- },
-
- {
- .test_case_name = UPPER_BOUND_NONNEG_LO_1_CASE,
- .msb_set = false,
- .lower_bound = false,
- .extra_bits = 1,
- .expected = {.tv_sec = 0x17fffffffLL, .tv_nsec = 0L},
- },
-
- {
- .test_case_name = LOWER_BOUND_NEG_HI_1_CASE,
- .msb_set = true,
- .lower_bound = true,
- .extra_bits = 2,
- .expected = {.tv_sec = 0x180000000LL, .tv_nsec = 0L},
- },
-
- {
- .test_case_name = UPPER_BOUND_NEG_HI_1_CASE,
- .msb_set = true,
- .lower_bound = false,
- .extra_bits = 2,
- .expected = {.tv_sec = 0x1ffffffffLL, .tv_nsec = 0L},
- },
-
- {
- .test_case_name = LOWER_BOUND_NONNEG_HI_1_CASE,
- .msb_set = false,
- .lower_bound = true,
- .extra_bits = 2,
- .expected = {.tv_sec = 0x200000000LL, .tv_nsec = 0L},
- },
-
- {
- .test_case_name = UPPER_BOUND_NONNEG_HI_1_CASE,
- .msb_set = false,
- .lower_bound = false,
- .extra_bits = 2,
- .expected = {.tv_sec = 0x27fffffffLL, .tv_nsec = 0L},
- },
-
- {
- .test_case_name = UPPER_BOUND_NONNEG_HI_1_NS_1_CASE,
- .msb_set = false,
- .lower_bound = false,
- .extra_bits = 6,
- .expected = {.tv_sec = 0x27fffffffLL, .tv_nsec = 1L},
- },
-
- {
- .test_case_name = LOWER_BOUND_NONNEG_HI_1_NS_MAX_CASE,
- .msb_set = false,
- .lower_bound = true,
- .extra_bits = 0xFFFFFFFF,
- .expected = {.tv_sec = 0x300000000LL,
- .tv_nsec = MAX_NANOSECONDS},
- },
-
- {
- .test_case_name = LOWER_BOUND_NONNEG_EXTRA_BITS_1_CASE,
- .msb_set = false,
- .lower_bound = true,
- .extra_bits = 3,
- .expected = {.tv_sec = 0x300000000LL, .tv_nsec = 0L},
- },
-
- {
- .test_case_name = UPPER_BOUND_NONNEG_EXTRA_BITS_1_CASE,
- .msb_set = false,
- .lower_bound = false,
- .extra_bits = 3,
- .expected = {.tv_sec = 0x37fffffffLL, .tv_nsec = 0L},
- }
- };
-
struct timespec64 timestamp;
- int i;
-
- for (i = 0; i < ARRAY_SIZE(test_data); ++i) {
- timestamp.tv_sec = get_32bit_time(&test_data[i]);
- ext4_decode_extra_time(&timestamp,
- cpu_to_le32(test_data[i].extra_bits));
-
- KUNIT_EXPECT_EQ_MSG(test,
- test_data[i].expected.tv_sec,
- timestamp.tv_sec,
- CASE_NAME_FORMAT,
- test_data[i].test_case_name,
- test_data[i].msb_set,
- test_data[i].lower_bound,
- test_data[i].extra_bits);
- KUNIT_EXPECT_EQ_MSG(test,
- test_data[i].expected.tv_nsec,
- timestamp.tv_nsec,
- CASE_NAME_FORMAT,
- test_data[i].test_case_name,
- test_data[i].msb_set,
- test_data[i].lower_bound,
- test_data[i].extra_bits);
- }
+
+ struct timestamp_expectation *test_param =
+ (struct timestamp_expectation *)(test->param_value);
+
+ timestamp.tv_sec = get_32bit_time(test_param);
+ ext4_decode_extra_time(&timestamp,
+ cpu_to_le32(test_param->extra_bits));
+
+ KUNIT_EXPECT_EQ_MSG(test,
+ test_param->expected.tv_sec,
+ timestamp.tv_sec,
+ CASE_NAME_FORMAT,
+ test_param->test_case_name,
+ test_param->msb_set,
+ test_param->lower_bound,
+ test_param->extra_bits);
+ KUNIT_EXPECT_EQ_MSG(test,
+ test_param->expected.tv_nsec,
+ timestamp.tv_nsec,
+ CASE_NAME_FORMAT,
+ test_param->test_case_name,
+ test_param->msb_set,
+ test_param->lower_bound,
+ test_param->extra_bits);
}
static struct kunit_case ext4_inode_test_cases[] = {
- KUNIT_CASE(inode_test_xtimestamp_decoding),
+ KUNIT_CASE_PARAM(inode_test_xtimestamp_decoding, ext4_inode_gen_params),
{}
};
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 0d8385aea898..c173c8405856 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -175,6 +175,7 @@ void ext4_evict_inode(struct inode *inode)
*/
int extra_credits = 6;
struct ext4_xattr_inode_array *ea_inode_array = NULL;
+ bool freeze_protected = false;
trace_ext4_evict_inode(inode);
@@ -232,9 +233,14 @@ void ext4_evict_inode(struct inode *inode)
/*
* Protect us against freezing - iput() caller didn't have to have any
- * protection against it
+ * protection against it. When we are in a running transaction though,
+ * we are already protected against freezing and we cannot grab further
+ * protection due to lock ordering constraints.
*/
- sb_start_intwrite(inode->i_sb);
+ if (!ext4_journal_current_handle()) {
+ sb_start_intwrite(inode->i_sb);
+ freeze_protected = true;
+ }
if (!IS_NOQUOTA(inode))
extra_credits += EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb);
@@ -253,7 +259,8 @@ void ext4_evict_inode(struct inode *inode)
* cleaned up.
*/
ext4_orphan_del(NULL, inode);
- sb_end_intwrite(inode->i_sb);
+ if (freeze_protected)
+ sb_end_intwrite(inode->i_sb);
goto no_delete;
}
@@ -294,7 +301,8 @@ void ext4_evict_inode(struct inode *inode)
stop_handle:
ext4_journal_stop(handle);
ext4_orphan_del(NULL, inode);
- sb_end_intwrite(inode->i_sb);
+ if (freeze_protected)
+ sb_end_intwrite(inode->i_sb);
ext4_xattr_inode_array_free(ea_inode_array);
goto no_delete;
}
@@ -323,7 +331,8 @@ stop_handle:
else
ext4_free_inode(handle, inode);
ext4_journal_stop(handle);
- sb_end_intwrite(inode->i_sb);
+ if (freeze_protected)
+ sb_end_intwrite(inode->i_sb);
ext4_xattr_inode_array_free(ea_inode_array);
return;
no_delete:
@@ -830,8 +839,8 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
int create = map_flags & EXT4_GET_BLOCKS_CREATE;
int err;
- J_ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
- || handle != NULL || create == 0);
+ ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+ || handle != NULL || create == 0);
map.m_lblk = block;
map.m_len = 1;
@@ -846,9 +855,9 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
if (unlikely(!bh))
return ERR_PTR(-ENOMEM);
if (map.m_flags & EXT4_MAP_NEW) {
- J_ASSERT(create != 0);
- J_ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
- || (handle != NULL));
+ ASSERT(create != 0);
+ ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+ || (handle != NULL));
/*
* Now that we do not always journal data, we should
@@ -2055,7 +2064,7 @@ static int ext4_writepage(struct page *page,
unlock_page(page);
return -ENOMEM;
}
- ret = ext4_bio_write_page(&io_submit, page, len, wbc, keep_towrite);
+ ret = ext4_bio_write_page(&io_submit, page, len, keep_towrite);
ext4_io_submit(&io_submit);
/* Drop io_end reference we got from init */
ext4_put_io_end_defer(io_submit.io_end);
@@ -2089,7 +2098,7 @@ static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
len = size & ~PAGE_MASK;
else
len = PAGE_SIZE;
- err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false);
+ err = ext4_bio_write_page(&mpd->io_submit, page, len, false);
if (!err)
mpd->wbc->nr_to_write--;
mpd->first_page++;
@@ -4610,7 +4619,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
(ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))) {
if (flags & EXT4_IGET_HANDLE)
return ERR_PTR(-ESTALE);
- __ext4_error(sb, function, line, EFSCORRUPTED, 0,
+ __ext4_error(sb, function, line, false, EFSCORRUPTED, 0,
"inode #%lu: comm %s: iget: illegal inode #",
ino, current->comm);
return ERR_PTR(-EFSCORRUPTED);
@@ -5141,9 +5150,13 @@ static int ext4_do_update_inode(handle_t *handle,
err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
if (err)
goto out_brelse;
+ lock_buffer(EXT4_SB(sb)->s_sbh);
ext4_set_feature_large_file(sb);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(EXT4_SB(sb)->s_sbh);
ext4_handle_sync(handle);
- err = ext4_handle_dirty_super(handle, sb);
+ err = ext4_handle_dirty_metadata(handle, NULL,
+ EXT4_SB(sb)->s_sbh);
}
ext4_update_inode_fsync_trans(handle, inode, need_datasync);
out_brelse:
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index f0381876a7e5..d9665d2f82db 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -624,7 +624,7 @@ static int ext4_shutdown(struct super_block *sb, unsigned long arg)
case EXT4_GOING_FLAGS_DEFAULT:
freeze_bdev(sb->s_bdev);
set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
- thaw_bdev(sb->s_bdev, sb);
+ thaw_bdev(sb->s_bdev);
break;
case EXT4_GOING_FLAGS_LOGFLUSH:
set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
@@ -1157,7 +1157,10 @@ resizefs_out:
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto pwsalt_err_journal;
+ lock_buffer(sbi->s_sbh);
generate_random_uuid(sbi->s_es->s_encrypt_pw_salt);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
err = ext4_handle_dirty_metadata(handle, NULL,
sbi->s_sbh);
pwsalt_err_journal:
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 24af9ed5c3e5..99bf091fee10 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -822,24 +822,6 @@ void ext4_mb_generate_buddy(struct super_block *sb,
spin_unlock(&sbi->s_bal_lock);
}
-static void mb_regenerate_buddy(struct ext4_buddy *e4b)
-{
- int count;
- int order = 1;
- void *buddy;
-
- while ((buddy = mb_find_buddy(e4b, order++, &count))) {
- ext4_set_bits(buddy, 0, count);
- }
- e4b->bd_info->bb_fragments = 0;
- memset(e4b->bd_info->bb_counters, 0,
- sizeof(*e4b->bd_info->bb_counters) *
- (e4b->bd_sb->s_blocksize_bits + 2));
-
- ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy,
- e4b->bd_bitmap, e4b->bd_group);
-}
-
/* The buddy information is attached the buddy cache inode
* for convenience. The information regarding each group
* is loaded via ext4_mb_load_buddy. The information involve
@@ -1307,22 +1289,18 @@ static void ext4_mb_unload_buddy(struct ext4_buddy *e4b)
static int mb_find_order_for_block(struct ext4_buddy *e4b, int block)
{
- int order = 1;
- int bb_incr = 1 << (e4b->bd_blkbits - 1);
+ int order = 1, max;
void *bb;
BUG_ON(e4b->bd_bitmap == e4b->bd_buddy);
BUG_ON(block >= (1 << (e4b->bd_blkbits + 3)));
- bb = e4b->bd_buddy;
while (order <= e4b->bd_blkbits + 1) {
- block = block >> 1;
- if (!mb_test_bit(block, bb)) {
+ bb = mb_find_buddy(e4b, order, &max);
+ if (!mb_test_bit(block >> order, bb)) {
/* this block is part of buddy of order 'order' */
return order;
}
- bb += bb_incr;
- bb_incr >>= 1;
order++;
}
return 0;
@@ -1512,7 +1490,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
sb, e4b->bd_group,
EXT4_GROUP_INFO_BBITMAP_CORRUPT);
}
- mb_regenerate_buddy(e4b);
goto done;
}
@@ -2395,9 +2372,9 @@ repeat:
nr = sbi->s_mb_prefetch;
if (ext4_has_feature_flex_bg(sb)) {
- nr = (group / sbi->s_mb_prefetch) *
- sbi->s_mb_prefetch;
- nr = nr + sbi->s_mb_prefetch - group;
+ nr = 1 << sbi->s_log_groups_per_flex;
+ nr -= group & (nr - 1);
+ nr = min(nr, sbi->s_mb_prefetch);
}
prefetch_grp = ext4_mb_prefetch(sb, group,
nr, &prefetch_ios);
@@ -2733,7 +2710,8 @@ static int ext4_mb_init_backend(struct super_block *sb)
if (ext4_has_feature_flex_bg(sb)) {
/* a single flex group is supposed to be read by a single IO */
- sbi->s_mb_prefetch = 1 << sbi->s_es->s_log_groups_per_flex;
+ sbi->s_mb_prefetch = min(1 << sbi->s_es->s_log_groups_per_flex,
+ BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9));
sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */
} else {
sbi->s_mb_prefetch = 32;
@@ -5126,6 +5104,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
ext4_group_first_block_no(sb, group) +
EXT4_C2B(sbi, cluster),
"Block already on to-be-freed list");
+ kmem_cache_free(ext4_free_data_cachep, new_entry);
return 0;
}
}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 5fa8436cd5fa..cf652ba3e74d 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -182,10 +182,6 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
return bh;
}
-#ifndef assert
-#define assert(test) J_ASSERT(test)
-#endif
-
#ifdef DX_DEBUG
#define dxtrace(command) command
#else
@@ -843,7 +839,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
break;
}
}
- assert (at == p - 1);
+ ASSERT(at == p - 1);
}
at = p - 1;
@@ -1259,8 +1255,8 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block)
struct dx_entry *old = frame->at, *new = old + 1;
int count = dx_get_count(entries);
- assert(count < dx_get_limit(entries));
- assert(old < entries + count);
+ ASSERT(count < dx_get_limit(entries));
+ ASSERT(old < entries + count);
memmove(new + 1, new, (char *)(entries + count) - (char *)(new));
dx_set_hash(new, hash);
dx_set_block(new, block);
@@ -1608,6 +1604,7 @@ static struct buffer_head *ext4_lookup_entry(struct inode *dir,
struct buffer_head *bh;
err = ext4_fname_prepare_lookup(dir, dentry, &fname);
+ generic_set_encrypted_ci_d_ops(dentry);
if (err == -ENOENT)
return NULL;
if (err)
@@ -2958,7 +2955,7 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
* hold i_mutex, or the inode can not be referenced from outside,
* so i_nlink should not be bumped due to race
*/
- J_ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+ ASSERT((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
S_ISLNK(inode->i_mode)) || inode->i_nlink == 0);
BUFFER_TRACE(sbi->s_sbh, "get_write_access");
@@ -2979,14 +2976,17 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
(le32_to_cpu(sbi->s_es->s_inodes_count))) {
/* Insert this inode at the head of the on-disk orphan list */
NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan);
+ lock_buffer(sbi->s_sbh);
sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
dirty = true;
}
list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan);
mutex_unlock(&sbi->s_orphan_lock);
if (dirty) {
- err = ext4_handle_dirty_super(handle, sb);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
if (!err)
err = rc;
@@ -3062,9 +3062,12 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
mutex_unlock(&sbi->s_orphan_lock);
goto out_brelse;
}
+ lock_buffer(sbi->s_sbh);
sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
+ ext4_superblock_csum_set(inode->i_sb);
+ unlock_buffer(sbi->s_sbh);
mutex_unlock(&sbi->s_orphan_lock);
- err = ext4_handle_dirty_super(handle, inode->i_sb);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
} else {
struct ext4_iloc iloc2;
struct inode *i_prev =
@@ -3596,9 +3599,6 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent,
return retval2;
}
}
- brelse(ent->bh);
- ent->bh = NULL;
-
return retval;
}
@@ -3797,6 +3797,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
}
}
+ old_file_type = old.de->file_type;
if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir))
ext4_handle_sync(handle);
@@ -3824,7 +3825,6 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
force_reread = (new.dir->i_ino == old.dir->i_ino &&
ext4_test_inode_flag(new.dir, EXT4_INODE_INLINE_DATA));
- old_file_type = old.de->file_type;
if (whiteout) {
/*
* Do this before adding a new entry, so the old entry is sure
@@ -3922,15 +3922,19 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
retval = 0;
end_rename:
- brelse(old.dir_bh);
- brelse(old.bh);
- brelse(new.bh);
if (whiteout) {
- if (retval)
+ if (retval) {
+ ext4_setent(handle, &old,
+ old.inode->i_ino, old_file_type);
drop_nlink(whiteout);
+ }
unlock_new_inode(whiteout);
iput(whiteout);
+
}
+ brelse(old.dir_bh);
+ brelse(old.bh);
+ brelse(new.bh);
if (handle)
ext4_journal_stop(handle);
return retval;
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index defd2e10dfd1..03a44a0de86a 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -111,9 +111,6 @@ static void ext4_finish_bio(struct bio *bio)
unsigned under_io = 0;
unsigned long flags;
- if (!page)
- continue;
-
if (fscrypt_is_bounce_page(page)) {
bounce_page = page;
page = fscrypt_pagecache_page(bounce_page);
@@ -438,7 +435,6 @@ submit_and_retry:
int ext4_bio_write_page(struct ext4_io_submit *io,
struct page *page,
int len,
- struct writeback_control *wbc,
bool keep_towrite)
{
struct page *bounce_page = NULL;
@@ -448,6 +444,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
int ret = 0;
int nr_submitted = 0;
int nr_to_submit = 0;
+ struct writeback_control *wbc = io->io_wbc;
BUG_ON(!PageLocked(page));
BUG_ON(PageWriteback(page));
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 928700d57eb6..bd0d185654f3 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -899,8 +899,11 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
EXT4_SB(sb)->s_gdb_count++;
ext4_kvfree_array_rcu(o_group_desc);
+ lock_buffer(EXT4_SB(sb)->s_sbh);
le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
- err = ext4_handle_dirty_super(handle, sb);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(EXT4_SB(sb)->s_sbh);
+ err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
if (err)
ext4_std_error(sb, err);
return err;
@@ -1384,6 +1387,7 @@ static void ext4_update_super(struct super_block *sb,
reserved_blocks *= blocks_count;
do_div(reserved_blocks, 100);
+ lock_buffer(sbi->s_sbh);
ext4_blocks_count_set(es, ext4_blocks_count(es) + blocks_count);
ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + free_blocks);
le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb) *
@@ -1421,6 +1425,8 @@ static void ext4_update_super(struct super_block *sb,
* active. */
ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) +
reserved_blocks);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
/* Update the free space counts */
percpu_counter_add(&sbi->s_freeclusters_counter,
@@ -1515,7 +1521,7 @@ static int ext4_flex_group_add(struct super_block *sb,
ext4_update_super(sb, flex_gd);
- err = ext4_handle_dirty_super(handle, sb);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
exit_journal:
err2 = ext4_journal_stop(handle);
@@ -1717,15 +1723,18 @@ static int ext4_group_extend_no_check(struct super_block *sb,
goto errout;
}
+ lock_buffer(EXT4_SB(sb)->s_sbh);
ext4_blocks_count_set(es, o_blocks_count + add);
ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + add);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(EXT4_SB(sb)->s_sbh);
ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
o_blocks_count + add);
/* We add the blocks to the bitmap and set the group need init bit */
err = ext4_group_add_blocks(handle, sb, o_blocks_count, add);
if (err)
goto errout;
- ext4_handle_dirty_super(handle, sb);
+ ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
ext4_debug("freed blocks %llu through %llu\n", o_blocks_count,
o_blocks_count + add);
errout:
@@ -1874,12 +1883,15 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode)
if (err)
goto errout;
+ lock_buffer(sbi->s_sbh);
ext4_clear_feature_resize_inode(sb);
ext4_set_feature_meta_bg(sb);
sbi->s_es->s_first_meta_bg =
cpu_to_le32(num_desc_blocks(sb, sbi->s_groups_count));
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
- err = ext4_handle_dirty_super(handle, sb);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
if (err) {
ext4_std_error(sb, err);
goto errout;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 94472044f4c1..9a6f9875aa34 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -65,7 +65,8 @@ static struct ratelimit_state ext4_mount_msg_ratelimit;
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
static int ext4_show_options(struct seq_file *seq, struct dentry *root);
-static int ext4_commit_super(struct super_block *sb, int sync);
+static void ext4_update_super(struct super_block *sb);
+static int ext4_commit_super(struct super_block *sb);
static int ext4_mark_recovery_complete(struct super_block *sb,
struct ext4_super_block *es);
static int ext4_clear_journal_err(struct super_block *sb,
@@ -404,10 +405,8 @@ void ext4_itable_unused_set(struct super_block *sb,
bg->bg_itable_unused_hi = cpu_to_le16(count >> 16);
}
-static void __ext4_update_tstamp(__le32 *lo, __u8 *hi)
+static void __ext4_update_tstamp(__le32 *lo, __u8 *hi, time64_t now)
{
- time64_t now = ktime_get_real_seconds();
-
now = clamp_val(now, 0, (1ull << 40) - 1);
*lo = cpu_to_le32(lower_32_bits(now));
@@ -419,108 +418,11 @@ static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi)
return ((time64_t)(*hi) << 32) + le32_to_cpu(*lo);
}
#define ext4_update_tstamp(es, tstamp) \
- __ext4_update_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi)
+ __ext4_update_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi, \
+ ktime_get_real_seconds())
#define ext4_get_tstamp(es, tstamp) \
__ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi)
-static void __save_error_info(struct super_block *sb, int error,
- __u32 ino, __u64 block,
- const char *func, unsigned int line)
-{
- struct ext4_super_block *es = EXT4_SB(sb)->s_es;
- int err;
-
- EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
- if (bdev_read_only(sb->s_bdev))
- return;
- es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
- ext4_update_tstamp(es, s_last_error_time);
- strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
- es->s_last_error_line = cpu_to_le32(line);
- es->s_last_error_ino = cpu_to_le32(ino);
- es->s_last_error_block = cpu_to_le64(block);
- switch (error) {
- case EIO:
- err = EXT4_ERR_EIO;
- break;
- case ENOMEM:
- err = EXT4_ERR_ENOMEM;
- break;
- case EFSBADCRC:
- err = EXT4_ERR_EFSBADCRC;
- break;
- case 0:
- case EFSCORRUPTED:
- err = EXT4_ERR_EFSCORRUPTED;
- break;
- case ENOSPC:
- err = EXT4_ERR_ENOSPC;
- break;
- case ENOKEY:
- err = EXT4_ERR_ENOKEY;
- break;
- case EROFS:
- err = EXT4_ERR_EROFS;
- break;
- case EFBIG:
- err = EXT4_ERR_EFBIG;
- break;
- case EEXIST:
- err = EXT4_ERR_EEXIST;
- break;
- case ERANGE:
- err = EXT4_ERR_ERANGE;
- break;
- case EOVERFLOW:
- err = EXT4_ERR_EOVERFLOW;
- break;
- case EBUSY:
- err = EXT4_ERR_EBUSY;
- break;
- case ENOTDIR:
- err = EXT4_ERR_ENOTDIR;
- break;
- case ENOTEMPTY:
- err = EXT4_ERR_ENOTEMPTY;
- break;
- case ESHUTDOWN:
- err = EXT4_ERR_ESHUTDOWN;
- break;
- case EFAULT:
- err = EXT4_ERR_EFAULT;
- break;
- default:
- err = EXT4_ERR_UNKNOWN;
- }
- es->s_last_error_errcode = err;
- if (!es->s_first_error_time) {
- es->s_first_error_time = es->s_last_error_time;
- es->s_first_error_time_hi = es->s_last_error_time_hi;
- strncpy(es->s_first_error_func, func,
- sizeof(es->s_first_error_func));
- es->s_first_error_line = cpu_to_le32(line);
- es->s_first_error_ino = es->s_last_error_ino;
- es->s_first_error_block = es->s_last_error_block;
- es->s_first_error_errcode = es->s_last_error_errcode;
- }
- /*
- * Start the daily error reporting function if it hasn't been
- * started already
- */
- if (!es->s_error_count)
- mod_timer(&EXT4_SB(sb)->s_err_report, jiffies + 24*60*60*HZ);
- le32_add_cpu(&es->s_error_count, 1);
-}
-
-static void save_error_info(struct super_block *sb, int error,
- __u32 ino, __u64 block,
- const char *func, unsigned int line)
-{
- __save_error_info(sb, error, ino, block, func, line);
- if (!bdev_read_only(sb->s_bdev))
- ext4_commit_super(sb, 1);
-}
-
/*
* The del_gendisk() function uninitializes the disk-specific data
* structures, including the bdi structure, without telling anyone
@@ -649,6 +551,71 @@ static bool system_going_down(void)
|| system_state == SYSTEM_RESTART;
}
+struct ext4_err_translation {
+ int code;
+ int errno;
+};
+
+#define EXT4_ERR_TRANSLATE(err) { .code = EXT4_ERR_##err, .errno = err }
+
+static struct ext4_err_translation err_translation[] = {
+ EXT4_ERR_TRANSLATE(EIO),
+ EXT4_ERR_TRANSLATE(ENOMEM),
+ EXT4_ERR_TRANSLATE(EFSBADCRC),
+ EXT4_ERR_TRANSLATE(EFSCORRUPTED),
+ EXT4_ERR_TRANSLATE(ENOSPC),
+ EXT4_ERR_TRANSLATE(ENOKEY),
+ EXT4_ERR_TRANSLATE(EROFS),
+ EXT4_ERR_TRANSLATE(EFBIG),
+ EXT4_ERR_TRANSLATE(EEXIST),
+ EXT4_ERR_TRANSLATE(ERANGE),
+ EXT4_ERR_TRANSLATE(EOVERFLOW),
+ EXT4_ERR_TRANSLATE(EBUSY),
+ EXT4_ERR_TRANSLATE(ENOTDIR),
+ EXT4_ERR_TRANSLATE(ENOTEMPTY),
+ EXT4_ERR_TRANSLATE(ESHUTDOWN),
+ EXT4_ERR_TRANSLATE(EFAULT),
+};
+
+static int ext4_errno_to_code(int errno)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(err_translation); i++)
+ if (err_translation[i].errno == errno)
+ return err_translation[i].code;
+ return EXT4_ERR_UNKNOWN;
+}
+
+static void save_error_info(struct super_block *sb, int error,
+ __u32 ino, __u64 block,
+ const char *func, unsigned int line)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ /* We default to EFSCORRUPTED error... */
+ if (error == 0)
+ error = EFSCORRUPTED;
+
+ spin_lock(&sbi->s_error_lock);
+ sbi->s_add_error_count++;
+ sbi->s_last_error_code = error;
+ sbi->s_last_error_line = line;
+ sbi->s_last_error_ino = ino;
+ sbi->s_last_error_block = block;
+ sbi->s_last_error_func = func;
+ sbi->s_last_error_time = ktime_get_real_seconds();
+ if (!sbi->s_first_error_time) {
+ sbi->s_first_error_code = error;
+ sbi->s_first_error_line = line;
+ sbi->s_first_error_ino = ino;
+ sbi->s_first_error_block = block;
+ sbi->s_first_error_func = func;
+ sbi->s_first_error_time = sbi->s_last_error_time;
+ }
+ spin_unlock(&sbi->s_error_lock);
+}
+
/* Deal with the reporting of failure conditions on a filesystem such as
* inconsistencies detected or read IO failures.
*
@@ -662,40 +629,102 @@ static bool system_going_down(void)
* We'll just use the jbd2_journal_abort() error code to record an error in
* the journal instead. On recovery, the journal will complain about
* that error until we've noted it down and cleared it.
+ *
+ * If force_ro is set, we unconditionally force the filesystem into an
+ * ABORT|READONLY state, unless the error response on the fs has been set to
+ * panic in which case we take the easy way out and panic immediately. This is
+ * used to deal with unrecoverable failures such as journal IO errors or ENOMEM
+ * at a critical moment in log management.
*/
-
-static void ext4_handle_error(struct super_block *sb)
+static void ext4_handle_error(struct super_block *sb, bool force_ro, int error,
+ __u32 ino, __u64 block,
+ const char *func, unsigned int line)
{
+ journal_t *journal = EXT4_SB(sb)->s_journal;
+ bool continue_fs = !force_ro && test_opt(sb, ERRORS_CONT);
+
+ EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
if (test_opt(sb, WARN_ON_ERROR))
WARN_ON_ONCE(1);
- if (sb_rdonly(sb))
- return;
-
- if (!test_opt(sb, ERRORS_CONT)) {
- journal_t *journal = EXT4_SB(sb)->s_journal;
-
+ if (!continue_fs && !sb_rdonly(sb)) {
ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
if (journal)
jbd2_journal_abort(journal, -EIO);
}
+
+ if (!bdev_read_only(sb->s_bdev)) {
+ save_error_info(sb, error, ino, block, func, line);
+ /*
+ * In case the fs should keep running, we need to writeout
+ * superblock through the journal. Due to lock ordering
+ * constraints, it may not be safe to do it right here so we
+ * defer superblock flushing to a workqueue.
+ */
+ if (continue_fs)
+ schedule_work(&EXT4_SB(sb)->s_error_work);
+ else
+ ext4_commit_super(sb);
+ }
+
+ if (sb_rdonly(sb) || continue_fs)
+ return;
+
/*
* We force ERRORS_RO behavior when system is rebooting. Otherwise we
* could panic during 'reboot -f' as the underlying device got already
* disabled.
*/
- if (test_opt(sb, ERRORS_RO) || system_going_down()) {
- ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
- /*
- * Make sure updated value of ->s_mount_flags will be visible
- * before ->s_flags update
- */
- smp_wmb();
- sb->s_flags |= SB_RDONLY;
- } else if (test_opt(sb, ERRORS_PANIC)) {
+ if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) {
panic("EXT4-fs (device %s): panic forced after error\n",
sb->s_id);
}
+ ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
+ /*
+ * Make sure updated value of ->s_mount_flags will be visible before
+ * ->s_flags update
+ */
+ smp_wmb();
+ sb->s_flags |= SB_RDONLY;
+}
+
+static void flush_stashed_error_work(struct work_struct *work)
+{
+ struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info,
+ s_error_work);
+ journal_t *journal = sbi->s_journal;
+ handle_t *handle;
+
+ /*
+ * If the journal is still running, we have to write out superblock
+ * through the journal to avoid collisions of other journalled sb
+ * updates.
+ *
+ * We use directly jbd2 functions here to avoid recursing back into
+ * ext4 error handling code during handling of previous errors.
+ */
+ if (!sb_rdonly(sbi->s_sb) && journal) {
+ handle = jbd2_journal_start(journal, 1);
+ if (IS_ERR(handle))
+ goto write_directly;
+ if (jbd2_journal_get_write_access(handle, sbi->s_sbh)) {
+ jbd2_journal_stop(handle);
+ goto write_directly;
+ }
+ ext4_update_super(sbi->s_sb);
+ if (jbd2_journal_dirty_metadata(handle, sbi->s_sbh)) {
+ jbd2_journal_stop(handle);
+ goto write_directly;
+ }
+ jbd2_journal_stop(handle);
+ return;
+ }
+write_directly:
+ /*
+ * Write through journal failed. Write sb directly to get error info
+ * out and hope for the best.
+ */
+ ext4_commit_super(sbi->s_sb);
}
#define ext4_error_ratelimit(sb) \
@@ -703,7 +732,7 @@ static void ext4_handle_error(struct super_block *sb)
"EXT4-fs error")
void __ext4_error(struct super_block *sb, const char *function,
- unsigned int line, int error, __u64 block,
+ unsigned int line, bool force_ro, int error, __u64 block,
const char *fmt, ...)
{
struct va_format vaf;
@@ -722,8 +751,7 @@ void __ext4_error(struct super_block *sb, const char *function,
sb->s_id, function, line, current->comm, &vaf);
va_end(args);
}
- save_error_info(sb, error, 0, block, function, line);
- ext4_handle_error(sb);
+ ext4_handle_error(sb, force_ro, error, 0, block, function, line);
}
void __ext4_error_inode(struct inode *inode, const char *function,
@@ -753,9 +781,8 @@ void __ext4_error_inode(struct inode *inode, const char *function,
current->comm, &vaf);
va_end(args);
}
- save_error_info(inode->i_sb, error, inode->i_ino, block,
- function, line);
- ext4_handle_error(inode->i_sb);
+ ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block,
+ function, line);
}
void __ext4_error_file(struct file *file, const char *function,
@@ -792,9 +819,8 @@ void __ext4_error_file(struct file *file, const char *function,
current->comm, path, &vaf);
va_end(args);
}
- save_error_info(inode->i_sb, EFSCORRUPTED, inode->i_ino, block,
- function, line);
- ext4_handle_error(inode->i_sb);
+ ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block,
+ function, line);
}
const char *ext4_decode_error(struct super_block *sb, int errno,
@@ -861,52 +887,7 @@ void __ext4_std_error(struct super_block *sb, const char *function,
sb->s_id, function, line, errstr);
}
- save_error_info(sb, -errno, 0, 0, function, line);
- ext4_handle_error(sb);
-}
-
-/*
- * ext4_abort is a much stronger failure handler than ext4_error. The
- * abort function may be used to deal with unrecoverable failures such
- * as journal IO errors or ENOMEM at a critical moment in log management.
- *
- * We unconditionally force the filesystem into an ABORT|READONLY state,
- * unless the error response on the fs has been set to panic in which
- * case we take the easy way out and panic immediately.
- */
-
-void __ext4_abort(struct super_block *sb, const char *function,
- unsigned int line, int error, const char *fmt, ...)
-{
- struct va_format vaf;
- va_list args;
-
- if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
- return;
-
- save_error_info(sb, error, 0, 0, function, line);
- va_start(args, fmt);
- vaf.fmt = fmt;
- vaf.va = &args;
- printk(KERN_CRIT "EXT4-fs error (device %s): %s:%d: %pV\n",
- sb->s_id, function, line, &vaf);
- va_end(args);
-
- if (sb_rdonly(sb) == 0) {
- ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
- if (EXT4_SB(sb)->s_journal)
- jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
-
- ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
- /*
- * Make sure updated value of ->s_mount_flags will be visible
- * before ->s_flags update
- */
- smp_wmb();
- sb->s_flags |= SB_RDONLY;
- }
- if (test_opt(sb, ERRORS_PANIC) && !system_going_down())
- panic("EXT4-fs panic from previous error\n");
+ ext4_handle_error(sb, false, -errno, 0, 0, function, line);
}
void __ext4_msg(struct super_block *sb,
@@ -982,8 +963,6 @@ __acquires(bitlock)
return;
trace_ext4_error(sb, function, line);
- __save_error_info(sb, EFSCORRUPTED, ino, block, function, line);
-
if (ext4_error_ratelimit(sb)) {
va_start(args, fmt);
vaf.fmt = fmt;
@@ -999,17 +978,19 @@ __acquires(bitlock)
va_end(args);
}
- if (test_opt(sb, WARN_ON_ERROR))
- WARN_ON_ONCE(1);
-
if (test_opt(sb, ERRORS_CONT)) {
- ext4_commit_super(sb, 0);
+ if (test_opt(sb, WARN_ON_ERROR))
+ WARN_ON_ONCE(1);
+ EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+ if (!bdev_read_only(sb->s_bdev)) {
+ save_error_info(sb, EFSCORRUPTED, ino, block, function,
+ line);
+ schedule_work(&EXT4_SB(sb)->s_error_work);
+ }
return;
}
-
ext4_unlock_group(sb, grp);
- ext4_commit_super(sb, 1);
- ext4_handle_error(sb);
+ ext4_handle_error(sb, false, EFSCORRUPTED, ino, block, function, line);
/*
* We only get here in the ERRORS_RO case; relocking the group
* may be dangerous, but nothing bad will happen since the
@@ -1181,6 +1162,7 @@ static void ext4_put_super(struct super_block *sb)
ext4_unregister_li_request(sb);
ext4_quota_off_umount(sb);
+ flush_work(&sbi->s_error_work);
destroy_workqueue(sbi->rsv_conversion_wq);
/*
@@ -1210,7 +1192,7 @@ static void ext4_put_super(struct super_block *sb)
es->s_state = cpu_to_le16(sbi->s_mount_state);
}
if (!sb_rdonly(sb))
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
rcu_read_lock();
group_desc = rcu_dereference(sbi->s_group_desc);
@@ -1240,7 +1222,7 @@ static void ext4_put_super(struct super_block *sb)
* in-memory list had better be clean by this point. */
if (!list_empty(&sbi->s_orphan))
dump_orphan_list(sb, sbi);
- J_ASSERT(list_empty(&sbi->s_orphan));
+ ASSERT(list_empty(&sbi->s_orphan));
sync_blockdev(sb->s_bdev);
invalidate_bdev(sb->s_bdev);
@@ -2700,7 +2682,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
if (sbi->s_journal)
ext4_set_feature_journal_needs_recovery(sb);
- err = ext4_commit_super(sb, 1);
+ err = ext4_commit_super(sb);
done:
if (test_opt(sb, DEBUG))
printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
@@ -4005,6 +3987,21 @@ static void ext4_set_resv_clusters(struct super_block *sb)
atomic64_set(&sbi->s_resv_clusters, resv_clusters);
}
+static const char *ext4_quota_mode(struct super_block *sb)
+{
+#ifdef CONFIG_QUOTA
+ if (!ext4_quota_capable(sb))
+ return "none";
+
+ if (EXT4_SB(sb)->s_journal && ext4_is_quota_journalled(sb))
+ return "journalled";
+ else
+ return "writeback";
+#else
+ return "disabled";
+#endif
+}
+
static int ext4_fill_super(struct super_block *sb, void *data, int silent)
{
struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
@@ -4044,9 +4041,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_sb = sb;
sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
sbi->s_sb_block = sb_block;
- if (sb->s_bdev->bd_part)
- sbi->s_sectors_written_start =
- part_stat_read(sb->s_bdev->bd_part, sectors[STAT_WRITE]);
+ sbi->s_sectors_written_start =
+ part_stat_read(sb->s_bdev, sectors[STAT_WRITE]);
/* Cleanup superblock name */
strreplace(sb->s_id, '/', '!');
@@ -4074,7 +4070,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
if (IS_ERR(bh)) {
ext4_msg(sb, KERN_ERR, "unable to read superblock");
ret = PTR_ERR(bh);
- bh = NULL;
goto out_fail;
}
/*
@@ -4188,19 +4183,26 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
*/
sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT;
- blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
-
- if (blocksize == PAGE_SIZE)
- set_opt(sb, DIOREAD_NOLOCK);
-
- if (blocksize < EXT4_MIN_BLOCK_SIZE ||
- blocksize > EXT4_MAX_BLOCK_SIZE) {
+ if (le32_to_cpu(es->s_log_block_size) >
+ (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
+ ext4_msg(sb, KERN_ERR,
+ "Invalid log block size: %u",
+ le32_to_cpu(es->s_log_block_size));
+ goto failed_mount;
+ }
+ if (le32_to_cpu(es->s_log_cluster_size) >
+ (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
ext4_msg(sb, KERN_ERR,
- "Unsupported filesystem blocksize %d (%d log_block_size)",
- blocksize, le32_to_cpu(es->s_log_block_size));
+ "Invalid log cluster size: %u",
+ le32_to_cpu(es->s_log_cluster_size));
goto failed_mount;
}
+ blocksize = EXT4_MIN_BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);
+
+ if (blocksize == PAGE_SIZE)
+ set_opt(sb, DIOREAD_NOLOCK);
+
if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) {
sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE;
sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO;
@@ -4418,21 +4420,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
if (!ext4_feature_set_ok(sb, (sb_rdonly(sb))))
goto failed_mount;
- if (le32_to_cpu(es->s_log_block_size) >
- (EXT4_MAX_BLOCK_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
- ext4_msg(sb, KERN_ERR,
- "Invalid log block size: %u",
- le32_to_cpu(es->s_log_block_size));
- goto failed_mount;
- }
- if (le32_to_cpu(es->s_log_cluster_size) >
- (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
- ext4_msg(sb, KERN_ERR,
- "Invalid log cluster size: %u",
- le32_to_cpu(es->s_log_cluster_size));
- goto failed_mount;
- }
-
if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) {
ext4_msg(sb, KERN_ERR,
"Number of reserved GDT blocks insanely large: %d",
@@ -4703,7 +4690,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
"can't read group descriptor %d", i);
db_count = i;
ret = PTR_ERR(bh);
- bh = NULL;
goto failed_mount2;
}
rcu_read_lock();
@@ -4718,6 +4704,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
}
timer_setup(&sbi->s_err_report, print_daily_error_info, 0);
+ spin_lock_init(&sbi->s_error_lock);
+ INIT_WORK(&sbi->s_error_work, flush_stashed_error_work);
/* Register extent status tree shrinker */
if (ext4_es_register_shrinker(sbi))
@@ -4873,6 +4861,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
"requested data journaling mode");
goto failed_mount_wq;
}
+ break;
default:
break;
}
@@ -4919,7 +4908,7 @@ no_journal:
if (DUMMY_ENCRYPTION_ENABLED(sbi) && !sb_rdonly(sb) &&
!ext4_has_feature_encrypt(sb)) {
ext4_set_feature_encrypt(sb);
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
}
/*
@@ -4964,11 +4953,6 @@ no_journal:
goto failed_mount4;
}
-#ifdef CONFIG_UNICODE
- if (sb->s_encoding)
- sb->s_d_op = &ext4_dentry_ops;
-#endif
-
sb->s_root = d_make_root(root);
if (!sb->s_root) {
ext4_msg(sb, KERN_ERR, "get root dentry failed");
@@ -5006,13 +4990,11 @@ no_journal:
block = ext4_count_free_clusters(sb);
ext4_free_blocks_count_set(sbi->s_es,
EXT4_C2B(sbi, block));
- ext4_superblock_csum_set(sb);
err = percpu_counter_init(&sbi->s_freeclusters_counter, block,
GFP_KERNEL);
if (!err) {
unsigned long freei = ext4_count_free_inodes(sb);
sbi->s_es->s_free_inodes_count = cpu_to_le32(freei);
- ext4_superblock_csum_set(sb);
err = percpu_counter_init(&sbi->s_freeinodes_counter, freei,
GFP_KERNEL);
}
@@ -5092,10 +5074,11 @@ no_journal:
if (___ratelimit(&ext4_mount_msg_ratelimit, "EXT4-fs mount"))
ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. "
- "Opts: %.*s%s%s", descr,
+ "Opts: %.*s%s%s. Quota mode: %s.", descr,
(int) sizeof(sbi->s_es->s_mount_opts),
sbi->s_es->s_mount_opts,
- *sbi->s_es->s_mount_opts ? "; " : "", orig_data);
+ *sbi->s_es->s_mount_opts ? "; " : "", orig_data,
+ ext4_quota_mode(sb));
if (es->s_error_count)
mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
@@ -5160,6 +5143,7 @@ failed_mount3a:
ext4_es_unregister_shrinker(sbi);
failed_mount3:
del_timer_sync(&sbi->s_err_report);
+ flush_work(&sbi->s_error_work);
if (sbi->s_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
failed_mount2:
@@ -5474,7 +5458,7 @@ static int ext4_load_journal(struct super_block *sb,
es->s_journal_dev = cpu_to_le32(journal_devnum);
/* Make sure we flush the recovery flag to disk. */
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
}
return 0;
@@ -5484,15 +5468,14 @@ err_out:
return err;
}
-static int ext4_commit_super(struct super_block *sb, int sync)
+/* Copy state of EXT4_SB(sb) into buffer for on-disk superblock */
+static void ext4_update_super(struct super_block *sb)
{
- struct ext4_super_block *es = EXT4_SB(sb)->s_es;
- struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
- int error = 0;
-
- if (!sbh || block_device_ejected(sb))
- return error;
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ struct ext4_super_block *es = sbi->s_es;
+ struct buffer_head *sbh = sbi->s_sbh;
+ lock_buffer(sbh);
/*
* If the file system is mounted read-only, don't update the
* superblock write time. This avoids updating the superblock
@@ -5505,27 +5488,72 @@ static int ext4_commit_super(struct super_block *sb, int sync)
*/
if (!(sb->s_flags & SB_RDONLY))
ext4_update_tstamp(es, s_wtime);
- if (sb->s_bdev->bd_part)
- es->s_kbytes_written =
- cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
- ((part_stat_read(sb->s_bdev->bd_part,
- sectors[STAT_WRITE]) -
- EXT4_SB(sb)->s_sectors_written_start) >> 1));
- else
- es->s_kbytes_written =
- cpu_to_le64(EXT4_SB(sb)->s_kbytes_written);
- if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeclusters_counter))
+ es->s_kbytes_written =
+ cpu_to_le64(sbi->s_kbytes_written +
+ ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
+ sbi->s_sectors_written_start) >> 1));
+ if (percpu_counter_initialized(&sbi->s_freeclusters_counter))
ext4_free_blocks_count_set(es,
- EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive(
- &EXT4_SB(sb)->s_freeclusters_counter)));
- if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeinodes_counter))
+ EXT4_C2B(sbi, percpu_counter_sum_positive(
+ &sbi->s_freeclusters_counter)));
+ if (percpu_counter_initialized(&sbi->s_freeinodes_counter))
es->s_free_inodes_count =
cpu_to_le32(percpu_counter_sum_positive(
- &EXT4_SB(sb)->s_freeinodes_counter));
- BUFFER_TRACE(sbh, "marking dirty");
+ &sbi->s_freeinodes_counter));
+ /* Copy error information to the on-disk superblock */
+ spin_lock(&sbi->s_error_lock);
+ if (sbi->s_add_error_count > 0) {
+ es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
+ if (!es->s_first_error_time && !es->s_first_error_time_hi) {
+ __ext4_update_tstamp(&es->s_first_error_time,
+ &es->s_first_error_time_hi,
+ sbi->s_first_error_time);
+ strncpy(es->s_first_error_func, sbi->s_first_error_func,
+ sizeof(es->s_first_error_func));
+ es->s_first_error_line =
+ cpu_to_le32(sbi->s_first_error_line);
+ es->s_first_error_ino =
+ cpu_to_le32(sbi->s_first_error_ino);
+ es->s_first_error_block =
+ cpu_to_le64(sbi->s_first_error_block);
+ es->s_first_error_errcode =
+ ext4_errno_to_code(sbi->s_first_error_code);
+ }
+ __ext4_update_tstamp(&es->s_last_error_time,
+ &es->s_last_error_time_hi,
+ sbi->s_last_error_time);
+ strncpy(es->s_last_error_func, sbi->s_last_error_func,
+ sizeof(es->s_last_error_func));
+ es->s_last_error_line = cpu_to_le32(sbi->s_last_error_line);
+ es->s_last_error_ino = cpu_to_le32(sbi->s_last_error_ino);
+ es->s_last_error_block = cpu_to_le64(sbi->s_last_error_block);
+ es->s_last_error_errcode =
+ ext4_errno_to_code(sbi->s_last_error_code);
+ /*
+ * Start the daily error reporting function if it hasn't been
+ * started already
+ */
+ if (!es->s_error_count)
+ mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ);
+ le32_add_cpu(&es->s_error_count, sbi->s_add_error_count);
+ sbi->s_add_error_count = 0;
+ }
+ spin_unlock(&sbi->s_error_lock);
+
ext4_superblock_csum_set(sb);
- if (sync)
- lock_buffer(sbh);
+ unlock_buffer(sbh);
+}
+
+static int ext4_commit_super(struct super_block *sb)
+{
+ struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
+ int error = 0;
+
+ if (!sbh || block_device_ejected(sb))
+ return error;
+
+ ext4_update_super(sb);
+
if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) {
/*
* Oh, dear. A previous attempt to write the
@@ -5540,17 +5568,15 @@ static int ext4_commit_super(struct super_block *sb, int sync)
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
+ BUFFER_TRACE(sbh, "marking dirty");
mark_buffer_dirty(sbh);
- if (sync) {
- unlock_buffer(sbh);
- error = __sync_dirty_buffer(sbh,
- REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0));
- if (buffer_write_io_error(sbh)) {
- ext4_msg(sb, KERN_ERR, "I/O error while writing "
- "superblock");
- clear_buffer_write_io_error(sbh);
- set_buffer_uptodate(sbh);
- }
+ error = __sync_dirty_buffer(sbh,
+ REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0));
+ if (buffer_write_io_error(sbh)) {
+ ext4_msg(sb, KERN_ERR, "I/O error while writing "
+ "superblock");
+ clear_buffer_write_io_error(sbh);
+ set_buffer_uptodate(sbh);
}
return error;
}
@@ -5581,7 +5607,7 @@ static int ext4_mark_recovery_complete(struct super_block *sb,
if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) {
ext4_clear_feature_journal_needs_recovery(sb);
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
}
out:
jbd2_journal_unlock_updates(journal);
@@ -5623,7 +5649,7 @@ static int ext4_clear_journal_err(struct super_block *sb,
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
jbd2_journal_clear_err(journal);
jbd2_journal_update_sb_errno(journal);
@@ -5725,7 +5751,7 @@ static int ext4_freeze(struct super_block *sb)
ext4_clear_feature_journal_needs_recovery(sb);
}
- error = ext4_commit_super(sb, 1);
+ error = ext4_commit_super(sb);
out:
if (journal)
/* we rely on upper layer to stop further updates */
@@ -5747,7 +5773,7 @@ static int ext4_unfreeze(struct super_block *sb)
ext4_set_feature_journal_needs_recovery(sb);
}
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
return 0;
}
@@ -5875,6 +5901,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
}
+ /* Flush outstanding errors before changing fs state */
+ flush_work(&sbi->s_error_work);
+
if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) {
if (ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED)) {
err = -EROFS;
@@ -6004,7 +6033,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
}
if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) {
- err = ext4_commit_super(sb, 1);
+ err = ext4_commit_super(sb);
if (err)
goto restore_opts;
}
@@ -6033,7 +6062,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
*/
*flags = (*flags & ~vfs_flags) | (sb->s_flags & vfs_flags);
- ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data);
+ ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s. Quota mode: %s.",
+ orig_data, ext4_quota_mode(sb));
kfree(orig_data);
return 0;
@@ -6212,11 +6242,8 @@ static int ext4_release_dquot(struct dquot *dquot)
static int ext4_mark_dquot_dirty(struct dquot *dquot)
{
struct super_block *sb = dquot->dq_sb;
- struct ext4_sb_info *sbi = EXT4_SB(sb);
- /* Are we journaling quotas? */
- if (ext4_has_feature_quota(sb) ||
- sbi->s_qf_names[USRQUOTA] || sbi->s_qf_names[GRPQUOTA]) {
+ if (ext4_is_quota_journalled(sb)) {
dquot_mark_dquot_dirty(dquot);
return ext4_write_dquot(dquot);
} else {
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 4e27fe6ed3ae..075aa3a19ff5 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -62,11 +62,8 @@ static ssize_t session_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
{
struct super_block *sb = sbi->s_buddy_cache->i_sb;
- if (!sb->s_bdev->bd_part)
- return snprintf(buf, PAGE_SIZE, "0\n");
return snprintf(buf, PAGE_SIZE, "%lu\n",
- (part_stat_read(sb->s_bdev->bd_part,
- sectors[STAT_WRITE]) -
+ (part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
sbi->s_sectors_written_start) >> 1);
}
@@ -74,12 +71,9 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
{
struct super_block *sb = sbi->s_buddy_cache->i_sb;
- if (!sb->s_bdev->bd_part)
- return snprintf(buf, PAGE_SIZE, "0\n");
return snprintf(buf, PAGE_SIZE, "%llu\n",
(unsigned long long)(sbi->s_kbytes_written +
- ((part_stat_read(sb->s_bdev->bd_part,
- sectors[STAT_WRITE]) -
+ ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
EXT4_SB(sb)->s_sectors_written_start) >> 1)));
}
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 6127e94ea4f5..372208500f4e 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -792,8 +792,11 @@ static void ext4_xattr_update_super_block(handle_t *handle,
BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
+ lock_buffer(EXT4_SB(sb)->s_sbh);
ext4_set_feature_xattr(sb);
- ext4_handle_dirty_super(handle, sb);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(EXT4_SB(sb)->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
}
}
@@ -1927,7 +1930,6 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
} else {
/* Allocate a buffer where we construct the new block. */
s->base = kzalloc(sb->s_blocksize, GFP_NOFS);
- /* assert(header == s->base) */
error = -ENOMEM;
if (s->base == NULL)
goto cleanup;
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-22 17:48:33 +0100