From 70fdd76b501ab6d76566f3acdaba2e76e1e60670 Mon Sep 17 00:00:00 2001 From: Ojaswin Mujoo Date: Tue, 18 Mar 2025 13:22:55 +0530 Subject: [PATCH 1/3] ext4: define ext4_journal_destroy wrapper commit 5a02a6204ca37e7c22fbb55a789c503f05e8e89a upstream Define an ext4 wrapper over jbd2_journal_destroy to make sure we have consistent behavior during journal destruction. This will also come useful in the next patch where we add some ext4 specific logic in the destroy path. Reviewed-by: Jan Kara Reviewed-by: Baokun Li Signed-off-by: Ojaswin Mujoo Link: https://patch.msgid.link/c3ba78c5c419757e6d5f2d8ebb4a8ce9d21da86a.1742279837.git.ojaswin@linux.ibm.com Signed-off-by: Theodore Ts'o Signed-off-by: Xianglai Li Change-Id: I08deb6b882360e24425c9fe660f46657a84c1871 --- fs/ext4/ext4_jbd2.h | 14 ++++++++++++++ fs/ext4/super.c | 16 ++++++---------- 2 files changed, 20 insertions(+), 10 deletions(-) diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 0c77697d5e90..930778e507cc 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -513,4 +513,18 @@ static inline int ext4_should_dioread_nolock(struct inode *inode) return 1; } +/* + * Pass journal explicitly as it may not be cached in the sbi->s_journal in some + * cases + */ +static inline int ext4_journal_destroy(struct ext4_sb_info *sbi, journal_t *journal) +{ + int err = 0; + + err = jbd2_journal_destroy(journal); + sbi->s_journal = NULL; + + return err; +} + #endif /* _EXT4_JBD2_H */ diff --git a/fs/ext4/super.c b/fs/ext4/super.c index b83b9603347d..959ac242848f 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1322,8 +1322,7 @@ static void ext4_put_super(struct super_block *sb) if (sbi->s_journal) { aborted = is_journal_aborted(sbi->s_journal); - err = jbd2_journal_destroy(sbi->s_journal); - sbi->s_journal = NULL; + err = ext4_journal_destroy(sbi, sbi->s_journal); if ((err < 0) && !aborted) { ext4_abort(sb, -err, "Couldn't clean up the journal"); } @@ -4994,8 +4993,7 @@ static int ext4_load_and_init_journal(struct super_block *sb, out: /* flush s_sb_upd_work before destroying the journal. */ flush_work(&sbi->s_sb_upd_work); - jbd2_journal_destroy(sbi->s_journal); - sbi->s_journal = NULL; + ext4_journal_destroy(sbi, sbi->s_journal); return -EINVAL; } @@ -5684,8 +5682,7 @@ failed_mount8: __maybe_unused if (sbi->s_journal) { /* flush s_sb_upd_work before journal destroy. */ flush_work(&sbi->s_sb_upd_work); - jbd2_journal_destroy(sbi->s_journal); - sbi->s_journal = NULL; + ext4_journal_destroy(sbi, sbi->s_journal); } failed_mount3a: ext4_es_unregister_shrinker(sbi); @@ -5993,7 +5990,7 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb, return journal; out_journal: - jbd2_journal_destroy(journal); + ext4_journal_destroy(EXT4_SB(sb), journal); out_bdev: blkdev_put(journal_bdev, sb); return ERR_PTR(errno); @@ -6110,8 +6107,7 @@ static int ext4_load_journal(struct super_block *sb, EXT4_SB(sb)->s_journal = journal; err = ext4_clear_journal_err(sb, es); if (err) { - EXT4_SB(sb)->s_journal = NULL; - jbd2_journal_destroy(journal); + ext4_journal_destroy(EXT4_SB(sb), journal); return err; } @@ -6129,7 +6125,7 @@ static int ext4_load_journal(struct super_block *sb, return 0; err_out: - jbd2_journal_destroy(journal); + ext4_journal_destroy(EXT4_SB(sb), journal); return err; } -- Gitee From 720925a63b6d9206db81ed91f15716669a874ae1 Mon Sep 17 00:00:00 2001 From: Ojaswin Mujoo Date: Tue, 18 Mar 2025 13:22:57 +0530 Subject: [PATCH 2/3] ext4: Make sb update interval tunable commit 896b02d0b9e7deb4a4eb365e13dd912b49916519 upstream Currently, outside error paths, we auto commit the super block after 1 hour has passed and 16MB worth of updates have been written since last commit. This is a policy decision so make this tunable while keeping the defaults same. This is useful if user wants to tweak the superblock behavior or for debugging the codepath by allowing to trigger it more frequently. We can now tweak the super block update using sb_update_sec and sb_update_kb files in /sys/fs/ext4// Reviewed-by: Jan Kara Reviewed-by: Ritesh Harjani (IBM) Reviewed-by: Baokun Li Signed-off-by: Ojaswin Mujoo Link: https://patch.msgid.link/950fb8c9b2905620e16f02a3b9eeea5a5b6cb87e.1742279837.git.ojaswin@linux.ibm.com Signed-off-by: Theodore Ts'o Signed-off-by: Xianglai Li Change-Id: I45e75285943798aa2fd61b473b28c4f9d22e8a9a --- fs/ext4/ext4.h | 9 +++++++++ fs/ext4/super.c | 15 ++++++++------- fs/ext4/sysfs.c | 4 ++++ 3 files changed, 21 insertions(+), 7 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 7fb143a3e1a1..6a5a1813858f 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1601,6 +1601,8 @@ struct ext4_sb_info { unsigned int s_mb_prefetch; unsigned int s_mb_prefetch_limit; unsigned int s_mb_best_avail_max_trim_order; + unsigned int s_sb_update_sec; + unsigned int s_sb_update_kb; /* stats for buddy allocator */ atomic_t s_bal_reqs; /* number of reqs with len > 1 */ @@ -2281,6 +2283,13 @@ static inline int ext4_forced_shutdown(struct super_block *sb) #define EXT4_DEF_MIN_BATCH_TIME 0 #define EXT4_DEF_MAX_BATCH_TIME 15000 /* 15ms */ +/* + * Default values for superblock update + */ +#define EXT4_DEF_SB_UPDATE_INTERVAL_SEC (3600) /* seconds (1 hour) */ +#define EXT4_DEF_SB_UPDATE_INTERVAL_KB (16384) /* kilobytes (16MB) */ + + /* * Minimum number of groups in a flexgroup before we separate out * directories into the first block group of a flexgroup diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 959ac242848f..4ac60119b3a4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -442,9 +442,6 @@ static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi) #define ext4_get_tstamp(es, tstamp) \ __ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi) -#define EXT4_SB_REFRESH_INTERVAL_SEC (3600) /* seconds (1 hour) */ -#define EXT4_SB_REFRESH_INTERVAL_KB (16384) /* kilobytes (16MB) */ - /* * The ext4_maybe_update_superblock() function checks and updates the * superblock if needed. @@ -452,8 +449,10 @@ static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi) * This function is designed to update the on-disk superblock only under * certain conditions to prevent excessive disk writes and unnecessary * waking of the disk from sleep. The superblock will be updated if: - * 1. More than an hour has passed since the last superblock update, and - * 2. More than 16MB have been written since the last superblock update. + * 1. More than sbi->s_sb_update_sec (def: 1 hour) has passed since the last + * superblock update + * 2. More than sbi->s_sb_update_kb (def: 16MB) kbs have been written since the + * last superblock update. * * @sb: The superblock */ @@ -474,7 +473,7 @@ static void ext4_maybe_update_superblock(struct super_block *sb) now = ktime_get_real_seconds(); last_update = ext4_get_tstamp(es, s_wtime); - if (likely(now - last_update < EXT4_SB_REFRESH_INTERVAL_SEC)) + if (likely(now - last_update < sbi->s_sb_update_sec)) return; lifetime_write_kbytes = sbi->s_kbytes_written + @@ -489,7 +488,7 @@ static void ext4_maybe_update_superblock(struct super_block *sb) */ diff_size = lifetime_write_kbytes - le64_to_cpu(es->s_kbytes_written); - if (diff_size > EXT4_SB_REFRESH_INTERVAL_KB) + if (diff_size > sbi->s_sb_update_kb) schedule_work(&EXT4_SB(sb)->s_sb_upd_work); } @@ -5280,6 +5279,8 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) sbi->s_commit_interval = JBD2_DEFAULT_MAX_COMMIT_AGE * HZ; sbi->s_min_batch_time = EXT4_DEF_MIN_BATCH_TIME; sbi->s_max_batch_time = EXT4_DEF_MAX_BATCH_TIME; + sbi->s_sb_update_kb = EXT4_DEF_SB_UPDATE_INTERVAL_KB; + sbi->s_sb_update_sec = EXT4_DEF_SB_UPDATE_INTERVAL_SEC; /* * set default s_li_wait_mult for lazyinit, for the case there is diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index d65dccb44ed5..00133f4c6d94 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -248,6 +248,8 @@ EXT4_ATTR(journal_task, 0444, journal_task); EXT4_RW_ATTR_SBI_UI(mb_prefetch, s_mb_prefetch); EXT4_RW_ATTR_SBI_UI(mb_prefetch_limit, s_mb_prefetch_limit); EXT4_RW_ATTR_SBI_UL(last_trim_minblks, s_last_trim_minblks); +EXT4_RW_ATTR_SBI_UI(sb_update_sec, s_sb_update_sec); +EXT4_RW_ATTR_SBI_UI(sb_update_kb, s_sb_update_kb); static unsigned int old_bump_val = 128; EXT4_ATTR_PTR(max_writeback_mb_bump, 0444, pointer_ui, &old_bump_val); @@ -299,6 +301,8 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(mb_prefetch), ATTR_LIST(mb_prefetch_limit), ATTR_LIST(last_trim_minblks), + ATTR_LIST(sb_update_sec), + ATTR_LIST(sb_update_kb), NULL, }; ATTRIBUTE_GROUPS(ext4); -- Gitee From 8be9de76c1648f7ecbc0e89cefb1069dd686da1d Mon Sep 17 00:00:00 2001 From: Ojaswin Mujoo Date: Tue, 18 Mar 2025 13:22:56 +0530 Subject: [PATCH 3/3] ext4: avoid journaling sb update on error if journal is destroying commit ce2f26e73783b4a7c46a86e3af5b5c8de0971790 upstream Presently we always BUG_ON if trying to start a transaction on a journal marked with JBD2_UNMOUNT, since this should never happen. However, while ltp running stress tests, it was observed that in case of some error handling paths, it is possible for update_super_work to start a transaction after the journal is destroyed eg: (umount) ext4_kill_sb kill_block_super generic_shutdown_super sync_filesystem /* commits all txns */ evict_inodes /* might start a new txn */ ext4_put_super flush_work(&sbi->s_sb_upd_work) /* flush the workqueue */ jbd2_journal_destroy journal_kill_thread journal->j_flags |= JBD2_UNMOUNT; jbd2_journal_commit_transaction jbd2_journal_get_descriptor_buffer jbd2_journal_bmap ext4_journal_bmap ext4_map_blocks ... ext4_inode_error ext4_handle_error schedule_work(&sbi->s_sb_upd_work) /* work queue kicks in */ update_super_work jbd2_journal_start start_this_handle BUG_ON(journal-> j_flags & JBD2_UNMOUNT) Hence, introduce a new mount flag to indicate journal is destroying and only do a journaled (and deferred) update of sb if this flag is not set. Otherwise, just fallback to an un-journaled commit. Further, in the journal destroy path, we have the following sequence: 1. Set mount flag indicating journal is destroying 2. force a commit and wait for it 3. flush pending sb updates This sequence is important as it ensures that, after this point, there is no sb update that might be journaled so it is safe to update the sb outside the journal. (To avoid race discussed in 2d01ddc86606) Also, we don't need a similar check in ext4_grp_locked_error since it is only called from mballoc and AFAICT it would be always valid to schedule work here. Fixes: 2d01ddc86606 ("ext4: save error info to sb through journal if available") Signed-off-by: Ojaswin Mujoo Reviewed-by: Jan Kara Link: https://patch.msgid.link/9613c465d6ff00cd315602f99283d5f24018c3f7.1742279837.git.ojaswin@linux.ibm.com Signed-off-by: Theodore Ts'o Signed-off-by: Xianglai Li Change-Id: Ie3d5a8670e765452edbfcfe87e4f332f2a0f6c53 Signed-off-by: Ming Wang --- fs/ext4/ext4.h | 3 ++- fs/ext4/ext4_jbd2.h | 15 +++++++++++++++ fs/ext4/super.c | 16 ++++++++-------- 3 files changed, 25 insertions(+), 9 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 6a5a1813858f..9fa4f9cbb801 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1817,7 +1817,8 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino) */ enum { EXT4_MF_MNTDIR_SAMPLED, - EXT4_MF_FC_INELIGIBLE /* Fast commit ineligible */ + EXT4_MF_FC_INELIGIBLE, /* Fast commit ineligible */ + EXT4_MF_JOURNAL_DESTROY /* Journal is in process of destroying */ }; static inline void ext4_set_mount_flag(struct super_block *sb, int bit) diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 930778e507cc..ada46189b086 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -521,6 +521,21 @@ static inline int ext4_journal_destroy(struct ext4_sb_info *sbi, journal_t *jour { int err = 0; + /* + * At this point only two things can be operating on the journal. + * JBD2 thread performing transaction commit and s_sb_upd_work + * issuing sb update through the journal. Once we set + * EXT4_JOURNAL_DESTROY, new ext4_handle_error() calls will not + * queue s_sb_upd_work and ext4_force_commit() makes sure any + * ext4_handle_error() calls from the running transaction commit are + * finished. Hence no new s_sb_upd_work can be queued after we + * flush it here. + */ + ext4_set_mount_flag(sbi->s_sb, EXT4_MF_JOURNAL_DESTROY); + + ext4_force_commit(sbi->s_sb); + flush_work(&sbi->s_sb_upd_work); + err = jbd2_journal_destroy(journal); sbi->s_journal = NULL; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 4ac60119b3a4..1752f1748d6d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -728,9 +728,13 @@ static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, * 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. + * defer superblock flushing to a workqueue. We just need to be + * careful when the journal is already shutting down. If we get + * here in that case, just update the sb directly as the last + * transaction won't commit anyway. */ - if (continue_fs && journal) + if (continue_fs && journal && + !ext4_test_mount_flag(sb, EXT4_MF_JOURNAL_DESTROY)) schedule_work(&EXT4_SB(sb)->s_sb_upd_work); else ext4_commit_super(sb); @@ -1315,7 +1319,6 @@ static void ext4_put_super(struct super_block *sb) ext4_unregister_li_request(sb); ext4_quotas_off(sb, EXT4_MAXQUOTAS); - flush_work(&sbi->s_sb_upd_work); destroy_workqueue(sbi->rsv_conversion_wq); ext4_release_orphan_info(sb); @@ -1325,7 +1328,8 @@ static void ext4_put_super(struct super_block *sb) if ((err < 0) && !aborted) { ext4_abort(sb, -err, "Couldn't clean up the journal"); } - } + } else + flush_work(&sbi->s_sb_upd_work); ext4_es_unregister_shrinker(sbi); timer_shutdown_sync(&sbi->s_err_report); @@ -4990,8 +4994,6 @@ static int ext4_load_and_init_journal(struct super_block *sb, return 0; out: - /* flush s_sb_upd_work before destroying the journal. */ - flush_work(&sbi->s_sb_upd_work); ext4_journal_destroy(sbi, sbi->s_journal); return -EINVAL; } @@ -5681,8 +5683,6 @@ failed_mount8: __maybe_unused sbi->s_ea_block_cache = NULL; if (sbi->s_journal) { - /* flush s_sb_upd_work before journal destroy. */ - flush_work(&sbi->s_sb_upd_work); ext4_journal_destroy(sbi, sbi->s_journal); } failed_mount3a: -- Gitee