From 1aec30021edd410b986c156f195f3d23959a9d11 Mon Sep 17 00:00:00 2001 From: Li Chen Date: Wed, 25 Feb 2026 16:26:16 +0800 Subject: ext4: publish jinode after initialization ext4_inode_attach_jinode() publishes ei->jinode to concurrent users. It used to set ei->jinode before jbd2_journal_init_jbd_inode(), allowing a reader to observe a non-NULL jinode with i_vfs_inode still unset. The fast commit flush path can then pass this jinode to jbd2_wait_inode_data(), which dereferences i_vfs_inode->i_mapping and may crash. Below is the crash I observe: ``` BUG: unable to handle page fault for address: 000000010beb47f4 PGD 110e51067 P4D 110e51067 PUD 0 Oops: Oops: 0000 [#1] SMP NOPTI CPU: 1 UID: 0 PID: 4850 Comm: fc_fsync_bench_ Not tainted 6.18.0-00764-g795a690c06a5 #1 PREEMPT(voluntary) Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Arch Linux 1.17.0-2-2 04/01/2014 RIP: 0010:xas_find_marked+0x3d/0x2e0 Code: e0 03 48 83 f8 02 0f 84 f0 01 00 00 48 8b 47 08 48 89 c3 48 39 c6 0f 82 fd 01 00 00 48 85 c9 74 3d 48 83 f9 03 77 63 4c 8b 0f <49> 8b 71 08 48 c7 47 18 00 00 00 00 48 89 f1 83 e1 03 48 83 f9 02 RSP: 0018:ffffbbee806e7bf0 EFLAGS: 00010246 RAX: 000000000010beb4 RBX: 000000000010beb4 RCX: 0000000000000003 RDX: 0000000000000001 RSI: 0000002000300000 RDI: ffffbbee806e7c10 RBP: 0000000000000001 R08: 0000002000300000 R09: 000000010beb47ec R10: ffff9ea494590090 R11: 0000000000000000 R12: 0000002000300000 R13: ffffbbee806e7c90 R14: ffff9ea494513788 R15: ffffbbee806e7c88 FS: 00007fc2f9e3e6c0(0000) GS:ffff9ea6b1444000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000010beb47f4 CR3: 0000000119ac5000 CR4: 0000000000750ef0 PKRU: 55555554 Call Trace: filemap_get_folios_tag+0x87/0x2a0 __filemap_fdatawait_range+0x5f/0xd0 ? srso_alias_return_thunk+0x5/0xfbef5 ? __schedule+0x3e7/0x10c0 ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ? srso_alias_return_thunk+0x5/0xfbef5 ? cap_safe_nice+0x37/0x70 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ? srso_alias_return_thunk+0x5/0xfbef5 filemap_fdatawait_range_keep_errors+0x12/0x40 ext4_fc_commit+0x697/0x8b0 ? ext4_file_write_iter+0x64b/0x950 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ? srso_alias_return_thunk+0x5/0xfbef5 ? vfs_write+0x356/0x480 ? srso_alias_return_thunk+0x5/0xfbef5 ? preempt_count_sub+0x5f/0x80 ext4_sync_file+0xf7/0x370 do_fsync+0x3b/0x80 ? syscall_trace_enter+0x108/0x1d0 __x64_sys_fdatasync+0x16/0x20 do_syscall_64+0x62/0x2c0 entry_SYSCALL_64_after_hwframe+0x76/0x7e ... ``` Fix this by initializing the jbd2_inode first. Use smp_wmb() and WRITE_ONCE() to publish ei->jinode after initialization. Readers use READ_ONCE() to fetch the pointer. Fixes: a361293f5fede ("jbd2: Fix oops in jbd2_journal_file_inode()") Cc: stable@vger.kernel.org Signed-off-by: Li Chen Reviewed-by: Jan Kara Link: https://patch.msgid.link/20260225082617.147957-1-me@linux.beauty Signed-off-by: Theodore Ts'o Cc: stable@kernel.org --- fs/ext4/fast_commit.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/ext4/fast_commit.c') diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index f575751f1cae..6e949c21842d 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -975,13 +975,13 @@ static int ext4_fc_flush_data(journal_t *journal) int ret = 0; list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { - ret = jbd2_submit_inode_data(journal, ei->jinode); + ret = jbd2_submit_inode_data(journal, READ_ONCE(ei->jinode)); if (ret) return ret; } list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) { - ret = jbd2_wait_inode_data(journal, ei->jinode); + ret = jbd2_wait_inode_data(journal, READ_ONCE(ei->jinode)); if (ret) return ret; } -- cgit v1.2.3 From ec0a7500d8eace5b4f305fa0c594dd148f0e8d29 Mon Sep 17 00:00:00 2001 From: Baokun Li Date: Mon, 23 Mar 2026 14:08:36 +0800 Subject: ext4: fix iloc.bh leak in ext4_fc_replay_inode() error paths During code review, Joseph found that ext4_fc_replay_inode() calls ext4_get_fc_inode_loc() to get the inode location, which holds a reference to iloc.bh that must be released via brelse(). However, several error paths jump to the 'out' label without releasing iloc.bh: - ext4_handle_dirty_metadata() failure - sync_dirty_buffer() failure - ext4_mark_inode_used() failure - ext4_iget() failure Fix this by introducing an 'out_brelse' label placed just before the existing 'out' label to ensure iloc.bh is always released. Additionally, make ext4_fc_replay_inode() propagate errors properly instead of always returning 0. Reported-by: Joseph Qi Fixes: 8016e29f4362 ("ext4: fast commit recovery path") Signed-off-by: Baokun Li Reviewed-by: Zhang Yi Reviewed-by: Jan Kara Link: https://patch.msgid.link/20260323060836.3452660-1-libaokun@linux.alibaba.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org --- fs/ext4/fast_commit.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'fs/ext4/fast_commit.c') diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 6e949c21842d..2f0057e04934 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -1613,19 +1613,21 @@ static int ext4_fc_replay_inode(struct super_block *sb, /* Immediately update the inode on disk. */ ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh); if (ret) - goto out; + goto out_brelse; ret = sync_dirty_buffer(iloc.bh); if (ret) - goto out; + goto out_brelse; ret = ext4_mark_inode_used(sb, ino); if (ret) - goto out; + goto out_brelse; /* Given that we just wrote the inode on disk, this SHOULD succeed. */ inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); if (IS_ERR(inode)) { ext4_debug("Inode not found."); - return -EFSCORRUPTED; + inode = NULL; + ret = -EFSCORRUPTED; + goto out_brelse; } /* @@ -1642,13 +1644,14 @@ static int ext4_fc_replay_inode(struct super_block *sb, ext4_inode_csum_set(inode, ext4_raw_inode(&iloc), EXT4_I(inode)); ret = ext4_handle_dirty_metadata(NULL, NULL, iloc.bh); sync_dirty_buffer(iloc.bh); +out_brelse: brelse(iloc.bh); out: iput(inode); if (!ret) blkdev_issue_flush(sb->s_bdev); - return 0; + return ret; } /* -- cgit v1.2.3