summaryrefslogtreecommitdiff
path: root/fs/ext4/fast_commit.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4/fast_commit.c')
-rw-r--r--fs/ext4/fast_commit.c134
1 files changed, 79 insertions, 55 deletions
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index f2033e13a273c..0a14a7c87bf82 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -103,8 +103,69 @@
*
* Replay code should thus check for all the valid tails in the FC area.
*
+ * Fast Commit Replay Idempotence
+ * ------------------------------
+ *
+ * Fast commits tags are idempotent in nature provided the recovery code follows
+ * certain rules. The guiding principle that the commit path follows while
+ * committing is that it stores the result of a particular operation instead of
+ * storing the procedure.
+ *
+ * Let's consider this rename operation: 'mv /a /b'. Let's assume dirent '/a'
+ * was associated with inode 10. During fast commit, instead of storing this
+ * operation as a procedure "rename a to b", we store the resulting file system
+ * state as a "series" of outcomes:
+ *
+ * - Link dirent b to inode 10
+ * - Unlink dirent a
+ * - Inode <10> with valid refcount
+ *
+ * Now when recovery code runs, it needs "enforce" this state on the file
+ * system. This is what guarantees idempotence of fast commit replay.
+ *
+ * Let's take an example of a procedure that is not idempotent and see how fast
+ * commits make it idempotent. Consider following sequence of operations:
+ *
+ * rm A; mv B A; read A
+ * (x) (y) (z)
+ *
+ * (x), (y) and (z) are the points at which we can crash. If we store this
+ * sequence of operations as is then the replay is not idempotent. Let's say
+ * while in replay, we crash at (z). During the second replay, file A (which was
+ * actually created as a result of "mv B A" operation) would get deleted. Thus,
+ * file named A would be absent when we try to read A. So, this sequence of
+ * operations is not idempotent. However, as mentioned above, instead of storing
+ * the procedure fast commits store the outcome of each procedure. Thus the fast
+ * commit log for above procedure would be as follows:
+ *
+ * (Let's assume dirent A was linked to inode 10 and dirent B was linked to
+ * inode 11 before the replay)
+ *
+ * [Unlink A] [Link A to inode 11] [Unlink B] [Inode 11]
+ * (w) (x) (y) (z)
+ *
+ * If we crash at (z), we will have file A linked to inode 11. During the second
+ * replay, we will remove file A (inode 11). But we will create it back and make
+ * it point to inode 11. We won't find B, so we'll just skip that step. At this
+ * point, the refcount for inode 11 is not reliable, but that gets fixed by the
+ * replay of last inode 11 tag. Crashes at points (w), (x) and (y) get handled
+ * similarly. Thus, by converting a non-idempotent procedure into a series of
+ * idempotent outcomes, fast commits ensured idempotence during the replay.
+ *
* TODOs
* -----
+ *
+ * 0) Fast commit replay path hardening: Fast commit replay code should use
+ * journal handles to make sure all the updates it does during the replay
+ * path are atomic. With that if we crash during fast commit replay, after
+ * trying to do recovery again, we will find a file system where fast commit
+ * area is invalid (because new full commit would be found). In order to deal
+ * with that, fast commit replay code should ensure that the "FC_REPLAY"
+ * superblock state is persisted before starting the replay, so that after
+ * the crash, fast commit recovery code can look at that flag and perform
+ * fast commit recovery even if that area is invalidated by later full
+ * commits.
+ *
* 1) Make fast commit atomic updates more fine grained. Today, a fast commit
* eligible update must be protected within ext4_fc_start_update() and
* ext4_fc_stop_update(). These routines are called at much higher
@@ -543,13 +604,13 @@ void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t star
trace_ext4_fc_track_range(inode, start, end, ret);
}
-static void ext4_fc_submit_bh(struct super_block *sb)
+static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail)
{
int write_flags = REQ_SYNC;
struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh;
- /* TODO: REQ_FUA | REQ_PREFLUSH is unnecessarily expensive. */
- if (test_opt(sb, BARRIER))
+ /* Add REQ_FUA | REQ_PREFLUSH only its tail */
+ if (test_opt(sb, BARRIER) && is_tail)
write_flags |= REQ_FUA | REQ_PREFLUSH;
lock_buffer(bh);
set_buffer_dirty(bh);
@@ -623,7 +684,7 @@ static u8 *ext4_fc_reserve_space(struct super_block *sb, int len, u32 *crc)
*crc = ext4_chksum(sbi, *crc, tl, sizeof(*tl));
if (pad_len > 0)
ext4_fc_memzero(sb, tl + 1, pad_len, crc);
- ext4_fc_submit_bh(sb);
+ ext4_fc_submit_bh(sb, false);
ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh);
if (ret)
@@ -680,7 +741,7 @@ static int ext4_fc_write_tail(struct super_block *sb, u32 crc)
tail.fc_crc = cpu_to_le32(crc);
ext4_fc_memcpy(sb, dst, &tail.fc_crc, sizeof(tail.fc_crc), NULL);
- ext4_fc_submit_bh(sb);
+ ext4_fc_submit_bh(sb, true);
return 0;
}
@@ -1207,7 +1268,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
list_splice_init(&sbi->s_fc_dentry_q[FC_Q_STAGING],
&sbi->s_fc_dentry_q[FC_Q_MAIN]);
list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
- &sbi->s_fc_q[FC_Q_STAGING]);
+ &sbi->s_fc_q[FC_Q_MAIN]);
ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
@@ -1220,18 +1281,6 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
/* Ext4 Replay Path Routines */
-/* Get length of a particular tlv */
-static inline int ext4_fc_tag_len(struct ext4_fc_tl *tl)
-{
- return le16_to_cpu(tl->fc_len);
-}
-
-/* Get a pointer to "value" of a tlv */
-static inline u8 *ext4_fc_tag_val(struct ext4_fc_tl *tl)
-{
- return (u8 *)tl + sizeof(*tl);
-}
-
/* Helper struct for dentry replay routines */
struct dentry_info_args {
int parent_ino, dname_len, ino, inode_len;
@@ -1269,14 +1318,14 @@ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl)
entry.len = darg.dname_len;
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode %d not found", darg.ino);
return 0;
}
old_parent = ext4_iget(sb, darg.parent_ino,
EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(old_parent)) {
+ if (IS_ERR(old_parent)) {
jbd_debug(1, "Dir with inode %d not found", darg.parent_ino);
iput(inode);
return 0;
@@ -1361,7 +1410,7 @@ static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl)
darg.parent_ino, darg.dname_len);
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode not found.");
return 0;
}
@@ -1417,10 +1466,11 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
trace_ext4_fc_replay(sb, tag, ino, 0, 0);
inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
- if (!IS_ERR_OR_NULL(inode)) {
+ if (!IS_ERR(inode)) {
ext4_ext_clear_bb(inode);
iput(inode);
}
+ inode = NULL;
ext4_fc_record_modified_inode(sb, ino);
@@ -1463,7 +1513,7 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
/* Given that we just wrote the inode on disk, this SHOULD succeed. */
inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode not found.");
return -EFSCORRUPTED;
}
@@ -1515,7 +1565,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl)
goto out;
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "inode %d not found.", darg.ino);
inode = NULL;
ret = -EINVAL;
@@ -1528,7 +1578,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl)
* dot and dot dot dirents are setup properly.
*/
dir = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(dir)) {
+ if (IS_ERR(dir)) {
jbd_debug(1, "Dir %d not found.", darg.ino);
goto out;
}
@@ -1604,7 +1654,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
inode = ext4_iget(sb, le32_to_cpu(fc_add_ex->fc_ino),
EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode not found.");
return 0;
}
@@ -1728,7 +1778,7 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl)
le32_to_cpu(lrange->fc_ino), cur, remaining);
inode = ext4_iget(sb, le32_to_cpu(lrange->fc_ino), EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange->fc_ino));
return 0;
}
@@ -1770,32 +1820,6 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl)
return 0;
}
-static inline const char *tag2str(u16 tag)
-{
- switch (tag) {
- case EXT4_FC_TAG_LINK:
- return "TAG_ADD_ENTRY";
- case EXT4_FC_TAG_UNLINK:
- return "TAG_DEL_ENTRY";
- case EXT4_FC_TAG_ADD_RANGE:
- return "TAG_ADD_RANGE";
- case EXT4_FC_TAG_CREAT:
- return "TAG_CREAT_DENTRY";
- case EXT4_FC_TAG_DEL_RANGE:
- return "TAG_DEL_RANGE";
- case EXT4_FC_TAG_INODE:
- return "TAG_INODE";
- case EXT4_FC_TAG_PAD:
- return "TAG_PAD";
- case EXT4_FC_TAG_TAIL:
- return "TAG_TAIL";
- case EXT4_FC_TAG_HEAD:
- return "TAG_HEAD";
- default:
- return "TAG_ERROR";
- }
-}
-
static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
{
struct ext4_fc_replay_state *state;
@@ -1809,7 +1833,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
for (i = 0; i < state->fc_modified_inodes_used; i++) {
inode = ext4_iget(sb, state->fc_modified_inodes[i],
EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode %d not found.",
state->fc_modified_inodes[i]);
continue;
@@ -1826,7 +1850,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
if (ret > 0) {
path = ext4_find_extent(inode, map.m_lblk, NULL, 0);
- if (!IS_ERR_OR_NULL(path)) {
+ if (!IS_ERR(path)) {
for (j = 0; j < path->p_depth; j++)
ext4_mb_mark_bb(inode->i_sb,
path[j].p_block, 1, 1);
generated by cgit v1.2.3 (git 2.39.1) at 2025-08-08 00:55:50 +0000