From 55f252c9f50e998f6bc3aadc7806f049f7443d21 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Mon, 27 May 2013 23:32:35 -0400 Subject: ext4: truncate_inode_pages() in orphan cleanup path Currently we do not tell mm to zero out tail of the page before truncate in orphan_cleanup(). This is ok, because the page should not be uptodate, however this may eventually change and I might cause problems. Call truncate_inode_pages() as precautionary measure. Thanks Jan Kara for pointing this out. Signed-off-by: Lukas Czerner Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 94cc84db7c9..c468560c876 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2170,6 +2170,7 @@ static void ext4_orphan_cleanup(struct super_block *sb, jbd_debug(2, "truncating inode %lu to %lld bytes\n", inode->i_ino, inode->i_size); mutex_lock(&inode->i_mutex); + truncate_inode_pages(inode->i_mapping, inode->i_size); ext4_truncate(inode); mutex_unlock(&inode->i_mutex); nr_truncates++; -- cgit v1.2.3-18-g5258 From 566370a2e56837be98bc62d012fc2d2d11851db4 Mon Sep 17 00:00:00 2001 From: Paul Taysom Date: Tue, 28 May 2013 07:51:21 -0400 Subject: ext4: suppress ext4 orphan messages on mount Suppress the messages releating to processing the ext4 orphan list ("truncating inode" and "deleting unreferenced inode") unless the debug option is on, since otherwise they end up taking up space in the log that could be used for more useful information. Tested by opening several files, unlinking them, then crashing the system, rebooting the system and examining /var/log/messages. Addresses the problem described in http://crbug.com/220976 Signed-off-by: Paul Taysom Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c468560c876..a9c143820f7 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2164,9 +2164,10 @@ static void ext4_orphan_cleanup(struct super_block *sb, list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan); dquot_initialize(inode); if (inode->i_nlink) { - ext4_msg(sb, KERN_DEBUG, - "%s: truncating inode %lu to %lld bytes", - __func__, inode->i_ino, inode->i_size); + if (test_opt(sb, DEBUG)) + ext4_msg(sb, KERN_DEBUG, + "%s: truncating inode %lu to %lld bytes", + __func__, inode->i_ino, inode->i_size); jbd_debug(2, "truncating inode %lu to %lld bytes\n", inode->i_ino, inode->i_size); mutex_lock(&inode->i_mutex); @@ -2175,9 +2176,10 @@ static void ext4_orphan_cleanup(struct super_block *sb, mutex_unlock(&inode->i_mutex); nr_truncates++; } else { - ext4_msg(sb, KERN_DEBUG, - "%s: deleting unreferenced inode %lu", - __func__, inode->i_ino); + if (test_opt(sb, DEBUG)) + ext4_msg(sb, KERN_DEBUG, + "%s: deleting unreferenced inode %lu", + __func__, inode->i_ino); jbd_debug(2, "deleting unreferenced inode %lu\n", inode->i_ino); nr_orphans++; -- cgit v1.2.3-18-g5258 From f2d50a65c93cfe718742bc85dff55bf8f11967b6 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 4 Jun 2013 12:51:16 -0400 Subject: ext4: deprecate max_writeback_mb_bump sysfs attribute This attribute is now unused so deprecate it. We still show the old default value to keep some compatibility but we don't allow writing to that attribute anymore. Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 30 ++++++++++++++++++++++++------ 1 file changed, 24 insertions(+), 6 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a9c143820f7..eac4d3081ba 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2380,7 +2380,10 @@ struct ext4_attr { ssize_t (*show)(struct ext4_attr *, struct ext4_sb_info *, char *); ssize_t (*store)(struct ext4_attr *, struct ext4_sb_info *, const char *, size_t); - int offset; + union { + int offset; + int deprecated_val; + } u; }; static int parse_strtoull(const char *buf, @@ -2449,7 +2452,7 @@ static ssize_t inode_readahead_blks_store(struct ext4_attr *a, static ssize_t sbi_ui_show(struct ext4_attr *a, struct ext4_sb_info *sbi, char *buf) { - unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset); + unsigned int *ui = (unsigned int *) (((char *) sbi) + a->u.offset); return snprintf(buf, PAGE_SIZE, "%u\n", *ui); } @@ -2458,7 +2461,7 @@ static ssize_t sbi_ui_store(struct ext4_attr *a, struct ext4_sb_info *sbi, const char *buf, size_t count) { - unsigned int *ui = (unsigned int *) (((char *) sbi) + a->offset); + unsigned int *ui = (unsigned int *) (((char *) sbi) + a->u.offset); unsigned long t; int ret; @@ -2507,12 +2510,20 @@ static ssize_t trigger_test_error(struct ext4_attr *a, return count; } +static ssize_t sbi_deprecated_show(struct ext4_attr *a, + struct ext4_sb_info *sbi, char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%d\n", a->u.deprecated_val); +} + #define EXT4_ATTR_OFFSET(_name,_mode,_show,_store,_elname) \ static struct ext4_attr ext4_attr_##_name = { \ .attr = {.name = __stringify(_name), .mode = _mode }, \ .show = _show, \ .store = _store, \ - .offset = offsetof(struct ext4_sb_info, _elname), \ + .u = { \ + .offset = offsetof(struct ext4_sb_info, _elname),\ + }, \ } #define EXT4_ATTR(name, mode, show, store) \ static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store) @@ -2523,6 +2534,14 @@ static struct ext4_attr ext4_attr_##name = __ATTR(name, mode, show, store) #define EXT4_RW_ATTR_SBI_UI(name, elname) \ EXT4_ATTR_OFFSET(name, 0644, sbi_ui_show, sbi_ui_store, elname) #define ATTR_LIST(name) &ext4_attr_##name.attr +#define EXT4_DEPRECATED_ATTR(_name, _val) \ +static struct ext4_attr ext4_attr_##_name = { \ + .attr = {.name = __stringify(_name), .mode = 0444 }, \ + .show = sbi_deprecated_show, \ + .u = { \ + .deprecated_val = _val, \ + }, \ +} EXT4_RO_ATTR(delayed_allocation_blocks); EXT4_RO_ATTR(session_write_kbytes); @@ -2537,7 +2556,7 @@ EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan); EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs); EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request); EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc); -EXT4_RW_ATTR_SBI_UI(max_writeback_mb_bump, s_max_writeback_mb_bump); +EXT4_DEPRECATED_ATTR(max_writeback_mb_bump, 128); EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb); EXT4_ATTR(trigger_fs_error, 0200, NULL, trigger_test_error); @@ -3790,7 +3809,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } sbi->s_stripe = ext4_get_stripe_size(sbi); - sbi->s_max_writeback_mb_bump = 128; sbi->s_extent_max_zeroout_kb = 32; /* -- cgit v1.2.3-18-g5258 From 2e8fa54e3b48e4ce8c4e9ca4674ffbc973f58be5 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 4 Jun 2013 14:21:02 -0400 Subject: ext4: split extent conversion lists to reserved & unreserved parts Now that we have extent conversions with reserved transaction, we have to prevent extent conversions without reserved transaction (from DIO code) to block these (as that would effectively void any transaction reservation we did). So split lists, work items, and work queues to reserved and unreserved parts. Reviewed-by: Zheng Liu Signed-off-by: Jan Kara Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 38 +++++++++++++++++++++++++++----------- 1 file changed, 27 insertions(+), 11 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index eac4d3081ba..7c8e1713e20 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -750,8 +750,10 @@ static void ext4_put_super(struct super_block *sb) ext4_unregister_li_request(sb); dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED); - flush_workqueue(sbi->dio_unwritten_wq); - destroy_workqueue(sbi->dio_unwritten_wq); + flush_workqueue(sbi->unrsv_conversion_wq); + flush_workqueue(sbi->rsv_conversion_wq); + destroy_workqueue(sbi->unrsv_conversion_wq); + destroy_workqueue(sbi->rsv_conversion_wq); if (sbi->s_journal) { err = jbd2_journal_destroy(sbi->s_journal); @@ -859,13 +861,15 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->i_reserved_quota = 0; #endif ei->jinode = NULL; - INIT_LIST_HEAD(&ei->i_completed_io_list); + INIT_LIST_HEAD(&ei->i_rsv_conversion_list); + INIT_LIST_HEAD(&ei->i_unrsv_conversion_list); spin_lock_init(&ei->i_completed_io_lock); ei->i_sync_tid = 0; ei->i_datasync_tid = 0; atomic_set(&ei->i_ioend_count, 0); atomic_set(&ei->i_unwritten, 0); - INIT_WORK(&ei->i_unwritten_work, ext4_end_io_work); + INIT_WORK(&ei->i_rsv_conversion_work, ext4_end_io_rsv_work); + INIT_WORK(&ei->i_unrsv_conversion_work, ext4_end_io_unrsv_work); return &ei->vfs_inode; } @@ -3936,12 +3940,20 @@ no_journal: * The maximum number of concurrent works can be high and * concurrency isn't really necessary. Limit it to 1. */ - EXT4_SB(sb)->dio_unwritten_wq = - alloc_workqueue("ext4-dio-unwritten", WQ_MEM_RECLAIM | WQ_UNBOUND, 1); - if (!EXT4_SB(sb)->dio_unwritten_wq) { - printk(KERN_ERR "EXT4-fs: failed to create DIO workqueue\n"); + EXT4_SB(sb)->rsv_conversion_wq = + alloc_workqueue("ext4-rsv-conversion", WQ_MEM_RECLAIM | WQ_UNBOUND, 1); + if (!EXT4_SB(sb)->rsv_conversion_wq) { + printk(KERN_ERR "EXT4-fs: failed to create workqueue\n"); ret = -ENOMEM; - goto failed_mount_wq; + goto failed_mount4; + } + + EXT4_SB(sb)->unrsv_conversion_wq = + alloc_workqueue("ext4-unrsv-conversion", WQ_MEM_RECLAIM | WQ_UNBOUND, 1); + if (!EXT4_SB(sb)->unrsv_conversion_wq) { + printk(KERN_ERR "EXT4-fs: failed to create workqueue\n"); + ret = -ENOMEM; + goto failed_mount4; } /* @@ -4095,7 +4107,10 @@ failed_mount4a: sb->s_root = NULL; failed_mount4: ext4_msg(sb, KERN_ERR, "mount failed"); - destroy_workqueue(EXT4_SB(sb)->dio_unwritten_wq); + if (EXT4_SB(sb)->rsv_conversion_wq) + destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq); + if (EXT4_SB(sb)->unrsv_conversion_wq) + destroy_workqueue(EXT4_SB(sb)->unrsv_conversion_wq); failed_mount_wq: if (sbi->s_journal) { jbd2_journal_destroy(sbi->s_journal); @@ -4541,7 +4556,8 @@ static int ext4_sync_fs(struct super_block *sb, int wait) struct ext4_sb_info *sbi = EXT4_SB(sb); trace_ext4_sync_fs(sb, wait); - flush_workqueue(sbi->dio_unwritten_wq); + flush_workqueue(sbi->rsv_conversion_wq); + flush_workqueue(sbi->unrsv_conversion_wq); /* * Writeback quota in non-journalled quota case - journalled quota has * no dirty dquots -- cgit v1.2.3-18-g5258 From 06a407f13daf9e48f0ef7189c7e54082b53940c7 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Wed, 12 Jun 2013 22:25:07 -0400 Subject: ext4: fix data integrity for ext4_sync_fs Inode's data or non journaled quota may be written w/o jounral so we _must_ send a barrier at the end of ext4_sync_fs. But it can be skipped if journal commit will do it for us. Also fix data integrity for nojournal mode. Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 36 +++++++++++++++++++++++++++++++++++- 1 file changed, 35 insertions(+), 1 deletion(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 7c8e1713e20..0f77c2e4b88 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -69,6 +69,7 @@ static void ext4_mark_recovery_complete(struct super_block *sb, static void ext4_clear_journal_err(struct super_block *sb, struct ext4_super_block *es); static int ext4_sync_fs(struct super_block *sb, int wait); +static int ext4_sync_fs_nojournal(struct super_block *sb, int wait); static int ext4_remount(struct super_block *sb, int *flags, char *data); static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf); static int ext4_unfreeze(struct super_block *sb); @@ -1097,6 +1098,7 @@ static const struct super_operations ext4_nojournal_sops = { .dirty_inode = ext4_dirty_inode, .drop_inode = ext4_drop_inode, .evict_inode = ext4_evict_inode, + .sync_fs = ext4_sync_fs_nojournal, .put_super = ext4_put_super, .statfs = ext4_statfs, .remount_fs = ext4_remount, @@ -4553,6 +4555,7 @@ static int ext4_sync_fs(struct super_block *sb, int wait) { int ret = 0; tid_t target; + bool needs_barrier = false; struct ext4_sb_info *sbi = EXT4_SB(sb); trace_ext4_sync_fs(sb, wait); @@ -4563,10 +4566,41 @@ static int ext4_sync_fs(struct super_block *sb, int wait) * no dirty dquots */ dquot_writeback_dquots(sb, -1); + /* + * Data writeback is possible w/o journal transaction, so barrier must + * being sent at the end of the function. But we can skip it if + * transaction_commit will do it for us. + */ + target = jbd2_get_latest_transaction(sbi->s_journal); + if (wait && sbi->s_journal->j_flags & JBD2_BARRIER && + !jbd2_trans_will_send_data_barrier(sbi->s_journal, target)) + needs_barrier = true; + if (jbd2_journal_start_commit(sbi->s_journal, &target)) { if (wait) - jbd2_log_wait_commit(sbi->s_journal, target); + ret = jbd2_log_wait_commit(sbi->s_journal, target); + } + if (needs_barrier) { + int err; + err = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL); + if (!ret) + ret = err; } + + return ret; +} + +static int ext4_sync_fs_nojournal(struct super_block *sb, int wait) +{ + int ret = 0; + + trace_ext4_sync_fs(sb, wait); + flush_workqueue(EXT4_SB(sb)->rsv_conversion_wq); + flush_workqueue(EXT4_SB(sb)->unrsv_conversion_wq); + dquot_writeback_dquots(sb, -1); + if (wait && test_opt(sb, BARRIER)) + ret = blkdev_issue_flush(sb->s_bdev, GFP_KERNEL, NULL); + return ret; } -- cgit v1.2.3-18-g5258 From 4418e14112e3ca85e8492a4489a3552b0cc526a8 Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Wed, 12 Jun 2013 22:38:04 -0400 Subject: ext4: Fix fsync error handling after filesystem abort If filesystem was aborted after inode's write back is complete but before its metadata was updated we may return success results in data loss. In order to handle fs abort correctly we have to check fs state once we discover that it is in MS_RDONLY state Test case: http://patchwork.ozlabs.org/patch/244297 Reviewed-by: Jan Kara Signed-off-by: Dmitry Monakhov Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0f77c2e4b88..eb52a7be1fc 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -399,6 +399,11 @@ static void ext4_handle_error(struct super_block *sb) } if (test_opt(sb, ERRORS_RO)) { 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 |= MS_RDONLY; } if (test_opt(sb, ERRORS_PANIC)) @@ -571,8 +576,13 @@ void __ext4_abort(struct super_block *sb, const char *function, if ((sb->s_flags & MS_RDONLY) == 0) { ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only"); - sb->s_flags |= MS_RDONLY; EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED; + /* + * Make sure updated value of ->s_mount_flags will be visible + * before ->s_flags update + */ + smp_wmb(); + sb->s_flags |= MS_RDONLY; if (EXT4_SB(sb)->s_journal) jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO); save_error_info(sb, function, line); -- cgit v1.2.3-18-g5258 From 03b40e349695dc700582568e5b410a89058f707e Mon Sep 17 00:00:00 2001 From: Jon Ernst Date: Mon, 17 Jun 2013 08:56:26 -0400 Subject: ext4: delete unused variables This patch removed several unused variables. Signed-off-by: Jon Ernst Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index eb52a7be1fc..54701fca451 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1924,7 +1924,6 @@ static int ext4_fill_flex_info(struct super_block *sb) struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_group_desc *gdp = NULL; ext4_group_t flex_group; - unsigned int groups_per_flex = 0; int i, err; sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex; @@ -1932,7 +1931,6 @@ static int ext4_fill_flex_info(struct super_block *sb) sbi->s_log_groups_per_flex = 0; return 1; } - groups_per_flex = 1U << sbi->s_log_groups_per_flex; err = ext4_alloc_flex_bg_array(sb, sbi->s_groups_count); if (err) -- cgit v1.2.3-18-g5258 From d3922a777f9b4c4df898d326fa940f239af4f9b6 Mon Sep 17 00:00:00 2001 From: Zheng Liu Date: Mon, 1 Jul 2013 08:12:37 -0400 Subject: ext4: improve extent cache shrink mechanism to avoid to burn CPU time Now we maintain an proper in-order LRU list in ext4 to reclaim entries from extent status tree when we are under heavy memory pressure. For keeping this order, a spin lock is used to protect this list. But this lock burns a lot of CPU time. We can use the following steps to trigger it. % cd /dev/shm % dd if=/dev/zero of=ext4-img bs=1M count=2k % mkfs.ext4 ext4-img % mount -t ext4 -o loop ext4-img /mnt % cd /mnt % for ((i=0;i<160;i++)); do truncate -s 64g $i; done % for ((i=0;i<160;i++)); do cp $i /dev/null &; done % perf record -a -g % perf report This commit tries to fix this problem. Now a new member called i_touch_when is added into ext4_inode_info to record the last access time for an inode. Meanwhile we never need to keep a proper in-order LRU list. So this can avoid to burns some CPU time. When we try to reclaim some entries from extent status tree, we use list_sort() to get a proper in-order list. Then we traverse this list to discard some entries. In ext4_sb_info, we use s_es_last_sorted to record the last time of sorting this list. When we traverse the list, we skip the inode that is newer than this time, and move this inode to the tail of LRU list. When the head of the list is newer than s_es_last_sorted, we will sort the LRU list again. In this commit, we break the loop if s_extent_cache_cnt == 0 because that means that all extents in extent status tree have been reclaimed. Meanwhile in this commit, ext4_es_{un}register_shrinker()'s prototype is changed to save a local variable in these functions. Reported-by: Dave Hansen Signed-off-by: Zheng Liu Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 54701fca451..cc8201180b3 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -773,7 +773,7 @@ static void ext4_put_super(struct super_block *sb) ext4_abort(sb, "Couldn't clean up the journal"); } - ext4_es_unregister_shrinker(sb); + ext4_es_unregister_shrinker(sbi); del_timer(&sbi->s_err_report); ext4_release_system_zone(sb); ext4_mb_release(sb); @@ -862,6 +862,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) rwlock_init(&ei->i_es_lock); INIT_LIST_HEAD(&ei->i_es_lru); ei->i_es_lru_nr = 0; + ei->i_touch_when = 0; ei->i_reserved_data_blocks = 0; ei->i_reserved_meta_blocks = 0; ei->i_allocated_meta_blocks = 0; @@ -3799,7 +3800,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_err_report.data = (unsigned long) sb; /* Register extent status tree shrinker */ - ext4_es_register_shrinker(sb); + ext4_es_register_shrinker(sbi); err = percpu_counter_init(&sbi->s_freeclusters_counter, ext4_count_free_clusters(sb)); @@ -4127,7 +4128,7 @@ failed_mount_wq: sbi->s_journal = NULL; } failed_mount3: - ext4_es_unregister_shrinker(sb); + ext4_es_unregister_shrinker(sbi); del_timer(&sbi->s_err_report); if (sbi->s_flex_groups) ext4_kvfree(sbi->s_flex_groups); -- cgit v1.2.3-18-g5258 From e7c96e8e47baf263d93a8dbbebca7216a912ca05 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 1 Jul 2013 08:12:37 -0400 Subject: ext4: reduce object size when !CONFIG_PRINTK Reduce the object size ~10% could be useful for embedded systems. Add #ifdef CONFIG_PRINTK #else #endif blocks to hold formats and arguments, passing " " to functions when !CONFIG_PRINTK and still verifying format and arguments with no_printk. $ size fs/ext4/built-in.o* text data bss dec hex filename 239375 610 888 240873 3ace9 fs/ext4/built-in.o.new 264167 738 888 265793 40e41 fs/ext4/built-in.o.old $ grep -E "CONFIG_EXT4|CONFIG_PRINTK" .config # CONFIG_PRINTK is not set CONFIG_EXT4_FS=y CONFIG_EXT4_USE_FOR_EXT23=y CONFIG_EXT4_FS_POSIX_ACL=y # CONFIG_EXT4_FS_SECURITY is not set # CONFIG_EXT4_DEBUG is not set Signed-off-by: Joe Perches Signed-off-by: "Theodore Ts'o" --- fs/ext4/super.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index cc8201180b3..85b3dd60169 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -428,9 +428,9 @@ void __ext4_error(struct super_block *sb, const char *function, ext4_handle_error(sb); } -void ext4_error_inode(struct inode *inode, const char *function, - unsigned int line, ext4_fsblk_t block, - const char *fmt, ...) +void __ext4_error_inode(struct inode *inode, const char *function, + unsigned int line, ext4_fsblk_t block, + const char *fmt, ...) { va_list args; struct va_format vaf; @@ -457,9 +457,9 @@ void ext4_error_inode(struct inode *inode, const char *function, ext4_handle_error(inode->i_sb); } -void ext4_error_file(struct file *file, const char *function, - unsigned int line, ext4_fsblk_t block, - const char *fmt, ...) +void __ext4_error_file(struct file *file, const char *function, + unsigned int line, ext4_fsblk_t block, + const char *fmt, ...) { va_list args; struct va_format vaf; @@ -591,7 +591,8 @@ void __ext4_abort(struct super_block *sb, const char *function, panic("EXT4-fs panic from previous error\n"); } -void ext4_msg(struct super_block *sb, const char *prefix, const char *fmt, ...) +void __ext4_msg(struct super_block *sb, + const char *prefix, const char *fmt, ...) { struct va_format vaf; va_list args; -- cgit v1.2.3-18-g5258 From 960fd856fdc3b08b3638f3f9b6b4bfceb77660c7 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 5 Jul 2013 23:11:16 -0400 Subject: ext4: fix ext4_get_group_number() The function ext4_get_group_number() was introduced as an optimization in commit bd86298e60b8. Unfortunately, this commit incorrectly calculate the group number for file systems with a 1k block size (when s_first_data_block is 1 instead of zero). This could cause the following kernel BUG: [ 568.877799] ------------[ cut here ]------------ [ 568.877833] kernel BUG at fs/ext4/mballoc.c:3728! [ 568.877840] Oops: Exception in kernel mode, sig: 5 [#1] [ 568.877845] SMP NR_CPUS=32 NUMA pSeries [ 568.877852] Modules linked in: binfmt_misc [ 568.877861] CPU: 1 PID: 3516 Comm: fs_mark Not tainted 3.10.0-03216-g7c6809f-dirty #1 [ 568.877867] task: c0000001fb0b8000 ti: c0000001fa954000 task.ti: c0000001fa954000 [ 568.877873] NIP: c0000000002f42a4 LR: c0000000002f4274 CTR: c000000000317ef8 [ 568.877879] REGS: c0000001fa956ed0 TRAP: 0700 Not tainted (3.10.0-03216-g7c6809f-dirty) [ 568.877884] MSR: 8000000000029032 CR: 24000428 XER: 00000000 [ 568.877902] SOFTE: 1 [ 568.877905] CFAR: c0000000002b5464 [ 568.877908] GPR00: 0000000000000001 c0000001fa957150 c000000000c6a408 c0000001fb588000 GPR04: 0000000000003fff c0000001fa9571c0 c0000001fa9571c4 000138098c50625f GPR08: 1301200000000000 0000000000000002 0000000000000001 0000000000000000 GPR12: 0000000024000422 c00000000f33a300 0000000000008000 c0000001fa9577f0 GPR16: c0000001fb7d0100 c000000000c29190 c0000000007f46e8 c000000000a14672 GPR20: 0000000000000001 0000000000000008 ffffffffffffffff 0000000000000000 GPR24: 0000000000000100 c0000001fa957278 c0000001fdb2bc78 c0000001fa957288 GPR28: 0000000000100100 c0000001fa957288 c0000001fb588000 c0000001fdb2bd10 [ 568.877993] NIP [c0000000002f42a4] .ext4_mb_release_group_pa+0xec/0x1c0 [ 568.877999] LR [c0000000002f4274] .ext4_mb_release_group_pa+0xbc/0x1c0 [ 568.878004] Call Trace: [ 568.878008] [c0000001fa957150] [c0000000002f4274] .ext4_mb_release_group_pa+0xbc/0x1c0 (unreliable) [ 568.878017] [c0000001fa957200] [c0000000002fb070] .ext4_mb_discard_lg_preallocations+0x394/0x444 [ 568.878025] [c0000001fa957340] [c0000000002fb45c] .ext4_mb_release_context+0x33c/0x734 [ 568.878032] [c0000001fa957440] [c0000000002fbcf8] .ext4_mb_new_blocks+0x4a4/0x5f4 [ 568.878039] [c0000001fa957510] [c0000000002ef56c] .ext4_ext_map_blocks+0xc28/0x1178 [ 568.878047] [c0000001fa957640] [c0000000002c1a94] .ext4_map_blocks+0x2c8/0x490 [ 568.878054] [c0000001fa957730] [c0000000002c536c] .ext4_writepages+0x738/0xc60 [ 568.878062] [c0000001fa957950] [c000000000168a78] .do_writepages+0x5c/0x80 [ 568.878069] [c0000001fa9579d0] [c00000000015d1c4] .__filemap_fdatawrite_range+0x88/0xb0 [ 568.878078] [c0000001fa957aa0] [c00000000015d23c] .filemap_write_and_wait_range+0x50/0xfc [ 568.878085] [c0000001fa957b30] [c0000000002b8edc] .ext4_sync_file+0x220/0x3c4 [ 568.878092] [c0000001fa957be0] [c0000000001f849c] .vfs_fsync_range+0x64/0x80 [ 568.878098] [c0000001fa957c70] [c0000000001f84f0] .vfs_fsync+0x38/0x4c [ 568.878105] [c0000001fa957d00] [c0000000001f87f4] .do_fsync+0x54/0x90 [ 568.878111] [c0000001fa957db0] [c0000000001f8894] .SyS_fsync+0x28/0x3c [ 568.878120] [c0000001fa957e30] [c000000000009c88] syscall_exit+0x0/0x7c [ 568.878125] Instruction dump: [ 568.878130] 60000000 813d0034 81610070 38000000 7f8b4800 419e001c 813f007c 7d2bfe70 [ 568.878144] 7d604a78 7c005850 54000ffe 7c0007b4 <0b000000> e8a10076 e87f0090 7fa4eb78 [ 568.878160] ---[ end trace 594d911d9654770b ]--- In addition fix the STD_GROUP optimization so that it works for bigalloc file systems as well. Signed-off-by: "Theodore Ts'o" Reported-by: Li Zhong Reviewed-by: Lukas Czerner Cc: stable@vger.kernel.org # 3.10 --- fs/ext4/super.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 85b3dd60169..8862d4ddf71 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3624,10 +3624,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb)); sbi->s_desc_per_block_bits = ilog2(EXT4_DESC_PER_BLOCK(sb)); - /* Do we have standard group size of blocksize * 8 blocks ? */ - if (sbi->s_blocks_per_group == blocksize << 3) - set_opt2(sb, STD_GROUP_SIZE); - for (i = 0; i < 4; i++) sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]); sbi->s_def_hash_version = es->s_def_hash_version; @@ -3697,6 +3693,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } + /* Do we have standard group size of clustersize * 8 blocks ? */ + if (sbi->s_blocks_per_group == clustersize << 3) + set_opt2(sb, STD_GROUP_SIZE); + /* * Test whether we have more sectors than will fit in sector_t, * and whether the max offset is addressable by the page cache. -- cgit v1.2.3-18-g5258 From ad065dd01662ae22138899e6b1c8eeb3a529964f Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 11 Jul 2013 18:54:37 -0400 Subject: ext4: don't show usrquota/grpquota twice in /proc/mounts We now print mount options in a generic fashion in ext4_show_options(), so we shouldn't be explicitly printing the {usr,grp}quota options in ext4_show_quota_options(). Without this patch, /proc/mounts can look like this: /dev/vdb /vdb ext4 rw,relatime,quota,usrquota,data=ordered,usrquota 0 0 ^^^^^^^^ ^^^^^^^^ Signed-off-by: "Theodore Ts'o" Cc: stable@vger.kernel.org --- fs/ext4/super.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8862d4ddf71..bca26f34edf 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1702,12 +1702,6 @@ static inline void ext4_show_quota_options(struct seq_file *seq, if (sbi->s_qf_names[GRPQUOTA]) seq_printf(seq, ",grpjquota=%s", sbi->s_qf_names[GRPQUOTA]); - - if (test_opt(sb, USRQUOTA)) - seq_puts(seq, ",usrquota"); - - if (test_opt(sb, GRPQUOTA)) - seq_puts(seq, ",grpquota"); #endif } -- cgit v1.2.3-18-g5258 From dd12ed144e9797094c04736f97aa27d5fe401476 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Fri, 26 Jul 2013 15:21:11 -0400 Subject: ext4: destroy ext4_es_cachep on module unload Without this, module can't be reloaded. [ 500.521980] kmem_cache_sanity_check (ext4_extent_status): Cache name already exists. Signed-off-by: Eric Sandeen Signed-off-by: "Theodore Ts'o" Cc: stable@vger.kernel.org # v3.8+ --- fs/ext4/super.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index bca26f34edf..36b141e420b 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5481,6 +5481,7 @@ static void __exit ext4_exit_fs(void) kset_unregister(ext4_kset); ext4_exit_system_zone(); ext4_exit_pageio(); + ext4_exit_es(); } MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); -- cgit v1.2.3-18-g5258 From 59d9fa5c2e9086db11aa287bb4030151d0095a17 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 8 Aug 2013 23:01:24 -0400 Subject: ext4: allow the mount options nodelalloc and data=journal Commit 26092bf ("ext4: use a table-driven handler for mount options") wrongly disallows the specifying the mount options nodelalloc and data=journal simultaneously. This is incorrect; it should have only disallowed the combination of delalloc and data=journal simultaneously. Reported-by: Piotr Sarna Signed-off-by: "Theodore Ts'o" Cc: stable@vger.kernel.org --- fs/ext4/super.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 36b141e420b..75b3708b778 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1359,7 +1359,7 @@ static const struct mount_opts { {Opt_delalloc, EXT4_MOUNT_DELALLOC, MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT}, {Opt_nodelalloc, EXT4_MOUNT_DELALLOC, - MOPT_EXT4_ONLY | MOPT_CLEAR | MOPT_EXPLICIT}, + MOPT_EXT4_ONLY | MOPT_CLEAR}, {Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM, MOPT_EXT4_ONLY | MOPT_SET}, {Opt_journal_async_commit, (EXT4_MOUNT_JOURNAL_ASYNC_COMMIT | -- cgit v1.2.3-18-g5258 From 6ae6514b33f941d3386da0dfbe2942766eab1577 Mon Sep 17 00:00:00 2001 From: Piotr Sarna Date: Thu, 8 Aug 2013 23:02:24 -0400 Subject: ext4: fix mount/remount error messages for incompatible mount options Commit 5688978 ("ext4: improve handling of conflicting mount options") introduced incorrect messages shown while choosing wrong mount options. First of all, both cases of incorrect mount options, "data=journal,delalloc" and "data=journal,dioread_nolock" result in the same error message. Secondly, the problem above isn't solved for remount option: the mismatched parameter is simply ignored. Moreover, ext4_msg states that remount with options "data=journal,delalloc" succeeded, which is not true. To fix it up, I added a simple check after parse_options() call to ensure that data=journal and delalloc/dioread_nolock parameters are not present at the same time. Signed-off-by: Piotr Sarna Acked-by: Bartlomiej Zolnierkiewicz Signed-off-by: Kyungmin Park Signed-off-by: "Theodore Ts'o" Cc: stable@vger.kernel.org --- fs/ext4/super.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'fs/ext4/super.c') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 75b3708b778..b59373b625e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3483,7 +3483,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) } if (test_opt(sb, DIOREAD_NOLOCK)) { ext4_msg(sb, KERN_ERR, "can't mount with " - "both data=journal and delalloc"); + "both data=journal and dioread_nolock"); goto failed_mount; } if (test_opt(sb, DELALLOC)) @@ -4727,6 +4727,21 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) goto restore_opts; } + if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) { + if (test_opt2(sb, EXPLICIT_DELALLOC)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "both data=journal and delalloc"); + err = -EINVAL; + goto restore_opts; + } + if (test_opt(sb, DIOREAD_NOLOCK)) { + ext4_msg(sb, KERN_ERR, "can't mount with " + "both data=journal and dioread_nolock"); + err = -EINVAL; + goto restore_opts; + } + } + if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) ext4_abort(sb, "Abort forced by user"); -- cgit v1.2.3-18-g5258