linux-ext4 - [PATCH v2 2/2] ext4: fast commit may miss file actions

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20220110044850.2806-3-yinxin.x@bytedance.com>
Date:   Mon, 10 Jan 2022 12:48:49 +0800
From:   Xin Yin <yinxin.x@...edance.com>
To:     harshadshirwadkar@...il.com, tytso@....edu,
        adilger.kernel@...ger.ca
Cc:     linux-ext4@...r.kernel.org, linux-kernel@...r.kernel.org,
        Xin Yin <yinxin.x@...edance.com>
Subject: [PATCH v2 2/2] ext4: fast commit may miss file actions

in the follow scenario:
1. jbd start transaction n
2. task A get new handle for transaction n+1
3. task A do some actions and add inode to FC_Q_MAIN fc_q
4. jbd complete transaction n and clear FC_Q_MAIN fc_q
5. task A call fsync

fast commit will lost the file actions during a full commit.

we should also add updates to staging queue during a full commit.
and in ext4_fc_cleanup(), when reset a inode's fc track range, check
it's i_sync_tid, if it bigger than current transaction tid, do not
rest it, or we will lost the track range.

And EXT4_MF_FC_COMMITTING is not needed anymore, so drop it.

Signed-off-by: Xin Yin <yinxin.x@...edance.com>
---
v2: drop EXT4_MF_FC_COMMITTING
---
 fs/ext4/ext4.h        |  5 +----
 fs/ext4/fast_commit.c | 11 ++++++-----
 fs/ext4/super.c       |  1 -
 3 files changed, 7 insertions(+), 10 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index a060bb56e654..589b1e335ad4 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1793,10 +1793,7 @@ static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 enum {
 	EXT4_MF_MNTDIR_SAMPLED,
 	EXT4_MF_FS_ABORTED,	/* Fatal error detected */
-	EXT4_MF_FC_INELIGIBLE,	/* Fast commit ineligible */
-	EXT4_MF_FC_COMMITTING	/* File system underoing a fast
-				 * commit.
-				 */
+	EXT4_MF_FC_INELIGIBLE	/* Fast commit ineligible */
 };
 
 static inline void ext4_set_mount_flag(struct super_block *sb, int bit)
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 444c0e5be932..7966e3bdba27 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -365,7 +365,8 @@ static int ext4_fc_track_template(
 	spin_lock(&sbi->s_fc_lock);
 	if (list_empty(&EXT4_I(inode)->i_fc_list))
 		list_add_tail(&EXT4_I(inode)->i_fc_list,
-				(ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING)) ?
+				(sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
+				 sbi->s_journal->j_flags & JBD2_FAST_COMMIT_ONGOING) ?
 				&sbi->s_fc_q[FC_Q_STAGING] :
 				&sbi->s_fc_q[FC_Q_MAIN]);
 	spin_unlock(&sbi->s_fc_lock);
@@ -418,7 +419,8 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update)
 	node->fcd_name.len = dentry->d_name.len;
 
 	spin_lock(&sbi->s_fc_lock);
-	if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_COMMITTING))
+	if (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING ||
+		sbi->s_journal->j_flags & JBD2_FAST_COMMIT_ONGOING)
 		list_add_tail(&node->fcd_list,
 				&sbi->s_fc_dentry_q[FC_Q_STAGING]);
 	else
@@ -884,7 +886,6 @@ static int ext4_fc_submit_inode_data_all(journal_t *journal)
 	int ret = 0;
 
 	spin_lock(&sbi->s_fc_lock);
-	ext4_set_mount_flag(sb, EXT4_MF_FC_COMMITTING);
 	list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) {
 		ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING);
 		while (atomic_read(&ei->i_fc_updates)) {
@@ -1202,7 +1203,8 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid)
 		list_del_init(&iter->i_fc_list);
 		ext4_clear_inode_state(&iter->vfs_inode,
 				       EXT4_STATE_FC_COMMITTING);
-		ext4_fc_reset_inode(&iter->vfs_inode);
+		if (iter->i_sync_tid <= tid)
+			ext4_fc_reset_inode(&iter->vfs_inode);
 		/* Make sure EXT4_STATE_FC_COMMITTING bit is clear */
 		smp_mb();
 #if (BITS_PER_LONG < 64)
@@ -1231,7 +1233,6 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid)
 	list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
 				&sbi->s_fc_q[FC_Q_MAIN]);
 
-	ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
 	if (tid >= sbi->s_fc_ineligible_tid) {
 		sbi->s_fc_ineligible_tid = 0;
 		ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 6049547d3c0f..5404516ea7e0 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4626,7 +4626,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	INIT_LIST_HEAD(&sbi->s_fc_dentry_q[FC_Q_STAGING]);
 	sbi->s_fc_bytes = 0;
 	ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
-	ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
 	sbi->s_fc_ineligible_tid = 0;
 	spin_lock_init(&sbi->s_fc_lock);
 	memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats));
-- 
2.20.1