From 61c219f5814277ecb71d64cb30297028d6665979 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 5 Jul 2014 16:28:35 -0400 Subject: ext4: fix unjournalled bg descriptor while initializing inode bitmap The first time that we allocate from an uninitialized inode allocation bitmap, if the block allocation bitmap is also uninitalized, we need to get write access to the block group descriptor before we start modifying the block group descriptor flags and updating the free block count, etc. Otherwise, there is the potential of a bad journal checksum (if journal checksums are enabled), and of the file system becoming inconsistent if we crash at exactly the wrong time. Signed-off-by: Theodore Ts'o Cc: stable@vger.kernel.org --- fs/ext4/ialloc.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index a87455df38bc..0840bf321cdb 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -874,6 +874,13 @@ got: goto out; } + BUFFER_TRACE(group_desc_bh, "get_write_access"); + err = ext4_journal_get_write_access(handle, group_desc_bh); + if (err) { + ext4_std_error(sb, err); + goto out; + } + /* We may have to initialize the block bitmap if it isn't already */ if (ext4_has_group_desc_csum(sb) && gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { @@ -910,13 +917,6 @@ got: } } - BUFFER_TRACE(group_desc_bh, "get_write_access"); - err = ext4_journal_get_write_access(handle, group_desc_bh); - if (err) { - ext4_std_error(sb, err); - goto out; - } - /* Update the relevant bg descriptor fields */ if (ext4_has_group_desc_csum(sb)) { int free; -- cgit v1.2.3 From ae0f78de2c43b6fadd007c231a352b13b5be8ed2 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 5 Jul 2014 18:40:52 -0400 Subject: ext4: clarify error count warning messages Make it clear that values printed are times, and that it is error since last fsck. Also add note about fsck version required. Signed-off-by: Pavel Machek Signed-off-by: Theodore Ts'o Reviewed-by: Andreas Dilger Cc: stable@vger.kernel.org --- fs/ext4/super.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index b9b9aabfb4d2..342394772b6c 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2809,10 +2809,11 @@ static void print_daily_error_info(unsigned long arg) es = sbi->s_es; if (es->s_error_count) - ext4_msg(sb, KERN_NOTICE, "error count: %u", + /* fsck newer than v1.41.13 is needed to clean this condition. */ + ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u", le32_to_cpu(es->s_error_count)); if (es->s_first_error_time) { - printk(KERN_NOTICE "EXT4-fs (%s): initial error at %u: %.*s:%d", + printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d", sb->s_id, le32_to_cpu(es->s_first_error_time), (int) sizeof(es->s_first_error_func), es->s_first_error_func, @@ -2826,7 +2827,7 @@ static void print_daily_error_info(unsigned long arg) printk("\n"); } if (es->s_last_error_time) { - printk(KERN_NOTICE "EXT4-fs (%s): last error at %u: %.*s:%d", + printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d", sb->s_id, le32_to_cpu(es->s_last_error_time), (int) sizeof(es->s_last_error_func), es->s_last_error_func, -- cgit v1.2.3 From 94d4c066a4ff170a2671b1a9b153febbf36796f6 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 5 Jul 2014 19:15:50 -0400 Subject: ext4: clarify ext4_error message in ext4_mb_generate_buddy_error() We are spending a lot of time explaining to users what this error means. Let's try to improve the message to avoid this problem. Signed-off-by: Theodore Ts'o Cc: stable@vger.kernel.org --- fs/ext4/mballoc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 7f72f50a8fa7..2dcb936be90e 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -752,8 +752,8 @@ void ext4_mb_generate_buddy(struct super_block *sb, if (free != grp->bb_free) { ext4_grp_locked_error(sb, group, 0, 0, - "%u clusters in bitmap, %u in gd; " - "block bitmap corrupt.", + "block bitmap and bg descriptor " + "inconsistent: %u vs %u free clusters", free, grp->bb_free); /* * If we intend to continue, we consider group descriptor -- cgit v1.2.3 From 5dd214248f94d430d70e9230bda72f2654ac88a8 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Sat, 5 Jul 2014 19:18:22 -0400 Subject: ext4: disable synchronous transaction batching if max_batch_time==0 The mount manpage says of the max_batch_time option, This optimization can be turned off entirely by setting max_batch_time to 0. But the code doesn't do that. So fix the code to do that. Signed-off-by: Eric Sandeen Signed-off-by: Theodore Ts'o Cc: stable@vger.kernel.org --- fs/ext4/super.c | 2 -- fs/jbd2/transaction.c | 5 ++++- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 342394772b6c..6297c07c937f 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1525,8 +1525,6 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token, arg = JBD2_DEFAULT_MAX_COMMIT_AGE; sbi->s_commit_interval = HZ * arg; } else if (token == Opt_max_batch_time) { - if (arg == 0) - arg = EXT4_DEF_MAX_BATCH_TIME; sbi->s_max_batch_time = arg; } else if (token == Opt_min_batch_time) { sbi->s_min_batch_time = arg; diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 38cfcf5f6fce..6f0f590cc5a3 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -1588,9 +1588,12 @@ int jbd2_journal_stop(handle_t *handle) * to perform a synchronous write. We do this to detect the * case where a single process is doing a stream of sync * writes. No point in waiting for joiners in that case. + * + * Setting max_batch_time to 0 disables this completely. */ pid = current->pid; - if (handle->h_sync && journal->j_last_sync_writer != pid) { + if (handle->h_sync && journal->j_last_sync_writer != pid && + journal->j_max_batch_time) { u64 commit_time, trans_time; journal->j_last_sync_writer = pid; -- cgit v1.2.3 From f9ae9cf5d72b3926ca48ea60e15bdbb840f42372 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Fri, 11 Jul 2014 13:55:40 -0400 Subject: ext4: revert commit which was causing fs corruption after journal replays Commit 007649375f6af2 ("ext4: initialize multi-block allocator before checking block descriptors") causes the block group descriptor's count of the number of free blocks to become inconsistent with the number of free blocks in the allocation bitmap. This is a harmless form of fs corruption, but it causes the kernel to potentially remount the file system read-only, or to panic, depending on the file systems's error behavior. Thanks to Eric Whitney for his tireless work to reproduce and to find the guilty commit. Fixes: 007649375f6af2 ("ext4: initialize multi-block allocator before checking block descriptors" Cc: stable@vger.kernel.org # 3.15 Reported-by: David Jander Reported-by: Matteo Croce Tested-by: Eric Whitney Suggested-by: Eric Whitney Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 51 ++++++++++++++++++++++++--------------------------- 1 file changed, 24 insertions(+), 27 deletions(-) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6297c07c937f..6df7bc611dbd 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3879,38 +3879,19 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount2; } } - - /* - * set up enough so that it can read an inode, - * and create new inode for buddy allocator - */ - sbi->s_gdb_count = db_count; - if (!test_opt(sb, NOLOAD) && - EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) - sb->s_op = &ext4_sops; - else - sb->s_op = &ext4_nojournal_sops; - - ext4_ext_init(sb); - err = ext4_mb_init(sb); - if (err) { - ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)", - err); - goto failed_mount2; - } - if (!ext4_check_descriptors(sb, &first_not_zeroed)) { ext4_msg(sb, KERN_ERR, "group descriptors corrupted!"); - goto failed_mount2a; + goto failed_mount2; } if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) if (!ext4_fill_flex_info(sb)) { ext4_msg(sb, KERN_ERR, "unable to initialize " "flex_bg meta info!"); - goto failed_mount2a; + goto failed_mount2; } + sbi->s_gdb_count = db_count; get_random_bytes(&sbi->s_next_generation, sizeof(u32)); spin_lock_init(&sbi->s_next_gen_lock); @@ -3945,6 +3926,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_stripe = ext4_get_stripe_size(sbi); sbi->s_extent_max_zeroout_kb = 32; + /* + * set up enough so that it can read an inode + */ + if (!test_opt(sb, NOLOAD) && + EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) + sb->s_op = &ext4_sops; + else + sb->s_op = &ext4_nojournal_sops; sb->s_export_op = &ext4_export_ops; sb->s_xattr = ext4_xattr_handlers; #ifdef CONFIG_QUOTA @@ -4134,13 +4123,21 @@ no_journal: if (err) { ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for " "reserved pool", ext4_calculate_resv_clusters(sb)); - goto failed_mount5; + goto failed_mount4a; } err = ext4_setup_system_zone(sb); if (err) { ext4_msg(sb, KERN_ERR, "failed to initialize system " "zone (%d)", err); + goto failed_mount4a; + } + + ext4_ext_init(sb); + err = ext4_mb_init(sb); + if (err) { + ext4_msg(sb, KERN_ERR, "failed to initialize mballoc (%d)", + err); goto failed_mount5; } @@ -4217,8 +4214,11 @@ failed_mount8: failed_mount7: ext4_unregister_li_request(sb); failed_mount6: - ext4_release_system_zone(sb); + ext4_mb_release(sb); failed_mount5: + ext4_ext_release(sb); + ext4_release_system_zone(sb); +failed_mount4a: dput(sb->s_root); sb->s_root = NULL; failed_mount4: @@ -4242,14 +4242,11 @@ failed_mount3: percpu_counter_destroy(&sbi->s_extent_cache_cnt); if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); -failed_mount2a: - ext4_mb_release(sb); failed_mount2: for (i = 0; i < db_count; i++) brelse(sbi->s_group_desc[i]); ext4_kvfree(sbi->s_group_desc); failed_mount: - ext4_ext_release(sb); if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); if (sbi->s_proc) { -- cgit v1.2.3 From 3f1f9b851311a76226140b55b1ea22111234a7c2 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 12 Jul 2014 15:32:24 -0400 Subject: ext4: fix a potential deadlock in __ext4_es_shrink() This fixes the following lockdep complaint: [ INFO: possible circular locking dependency detected ] 3.16.0-rc2-mm1+ #7 Tainted: G O ------------------------------------------------------- kworker/u24:0/4356 is trying to acquire lock: (&(&sbi->s_es_lru_lock)->rlock){+.+.-.}, at: [] __ext4_es_shrink+0x4f/0x2e0 but task is already holding lock: (&ei->i_es_lock){++++-.}, at: [] ext4_es_insert_extent+0x71/0x180 which lock already depends on the new lock. Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&ei->i_es_lock); lock(&(&sbi->s_es_lru_lock)->rlock); lock(&ei->i_es_lock); lock(&(&sbi->s_es_lru_lock)->rlock); *** DEADLOCK *** 6 locks held by kworker/u24:0/4356: #0: ("writeback"){.+.+.+}, at: [] process_one_work+0x180/0x560 #1: ((&(&wb->dwork)->work)){+.+.+.}, at: [] process_one_work+0x180/0x560 #2: (&type->s_umount_key#22){++++++}, at: [] grab_super_passive+0x44/0x90 #3: (jbd2_handle){+.+...}, at: [] start_this_handle+0x189/0x5f0 #4: (&ei->i_data_sem){++++..}, at: [] ext4_map_blocks+0x132/0x550 #5: (&ei->i_es_lock){++++-.}, at: [] ext4_es_insert_extent+0x71/0x180 stack backtrace: CPU: 0 PID: 4356 Comm: kworker/u24:0 Tainted: G O 3.16.0-rc2-mm1+ #7 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 Workqueue: writeback bdi_writeback_workfn (flush-253:0) ffffffff8213dce0 ffff880014b07538 ffffffff815df0bb 0000000000000007 ffffffff8213e040 ffff880014b07588 ffffffff815db3dd ffff880014b07568 ffff880014b07610 ffff88003b868930 ffff88003b868908 ffff88003b868930 Call Trace: [] dump_stack+0x4e/0x68 [] print_circular_bug+0x1fb/0x20c [] __lock_acquire+0x163e/0x1d00 [] ? retint_restore_args+0xe/0xe [] ? __slab_alloc+0x4a8/0x4ce [] ? __ext4_es_shrink+0x4f/0x2e0 [] lock_acquire+0x87/0x120 [] ? __ext4_es_shrink+0x4f/0x2e0 [] ? ext4_es_free_extent+0x5d/0x70 [] _raw_spin_lock+0x39/0x50 [] ? __ext4_es_shrink+0x4f/0x2e0 [] ? kmem_cache_alloc+0x18b/0x1a0 [] __ext4_es_shrink+0x4f/0x2e0 [] ext4_es_insert_extent+0xc8/0x180 [] ext4_map_blocks+0x1c4/0x550 [] ext4_writepages+0x6d4/0xd00 ... Reported-by: Minchan Kim Signed-off-by: Theodore Ts'o Reported-by: Minchan Kim Cc: stable@vger.kernel.org Cc: Zheng Liu --- fs/ext4/extents_status.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c index 3f5c188953a4..0b7e28e7eaa4 100644 --- a/fs/ext4/extents_status.c +++ b/fs/ext4/extents_status.c @@ -966,10 +966,10 @@ retry: continue; } - if (ei->i_es_lru_nr == 0 || ei == locked_ei) + if (ei->i_es_lru_nr == 0 || ei == locked_ei || + !write_trylock(&ei->i_es_lock)) continue; - write_lock(&ei->i_es_lock); shrunk = __es_try_to_reclaim_extents(ei, nr_to_scan); if (ei->i_es_lru_nr == 0) list_del_init(&ei->i_es_lru); -- cgit v1.2.3 From bf40c92635d63fcc574c52649f7cda13e0418ac1 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Sat, 12 Jul 2014 16:11:42 -0400 Subject: ext4: fix potential null pointer dereference in ext4_free_inode Fix potential null pointer dereferencing problem caused by e43bb4e612 ("ext4: decrement free clusters/inodes counters when block group declared bad") Reported-by: Dan Carpenter Signed-off-by: Namjae Jeon Signed-off-by: Ashish Sangwan Signed-off-by: Theodore Ts'o Reviewed-by: Lukas Czerner --- fs/ext4/ialloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 0840bf321cdb..5b87fc36aab8 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -338,7 +338,7 @@ out: fatal = err; } else { ext4_error(sb, "bit already cleared for inode %lu", ino); - if (!EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) { + if (gdp && !EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) { int count; count = ext4_free_inodes_count(sb, gdp); percpu_counter_sub(&sbi->s_freeinodes_counter, -- cgit v1.2.3