Hi,
On 28 March, I posted a v3 patch for this problem, but that had problems too,
which Andreas found using xfstests/034 test.
This v4 version fixes those problems and, as Steve Whitehouse suggested,
uses the faster iomap interface to map blocks from other journals, rather
than the now obsolete gfs2_extent_map().
Regards,
Bob Peterson
---
This patch fixes regressions in 588bff95c94efc05f9e1a0b19015c9408ed7c0ef.
Due to that patch, function clean_journal was setting the value of
sd_log_flush_head, but that's only valid if it is replaying the node's
own journal. If it's replaying another node's journal, that's completely
wrong and will lead to multiple problems. This patch tries to clean up
the mess by passing the value of the logical journal block number into
gfs2_write_log_header so the function can treat non-owned journals
generically. For the local journal, the journal extent map is used for
best performance. For other nodes from other journals, new function
gfs2_lblk_to_dblk is called to figure it out using gfs2_iomap_get.
This patch also tries to establish more consistency when passing journal
block parameters by changing several unsigned int types to a consistent
u32.
Fixes: 588bff95c94e ("GFS2: Reduce code redundancy writing log headers")
Signed-off-by: Bob Peterson <rpete...@redhat.com>
---
fs/gfs2/bmap.c | 27 +++++++++++++++++++++++++++
fs/gfs2/bmap.h | 1 +
fs/gfs2/incore.h | 2 +-
fs/gfs2/log.c | 24 ++++++++++++++++--------
fs/gfs2/log.h | 3 ++-
fs/gfs2/lops.c | 6 +++---
fs/gfs2/lops.h | 2 +-
fs/gfs2/recovery.c | 10 ++++++----
fs/gfs2/recovery.h | 2 +-
9 files changed, 58 insertions(+), 19 deletions(-)
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 02b2646d84b3..d914a745787e 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -925,6 +925,33 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos,
loff_t length,
goto out;
}
+/**
+ * gfs2_lblk_to_dblk - convert logical block to disk block
+ * @inode: the inode of the file we're mapping
+ * @lblock: the block relative to the start of the file
+ *
+ * This function maps a single block from a file logical block (relative to
+ * the start of the file) to a file system absolute block using iomap.
+ *
+ * Returns: the absolute file system block, or an error
+ */
+u64 gfs2_lblk_to_dblk(struct inode *inode, u32 lblock)
+{
+ struct iomap iomap = { };
+ struct metapath mp = { .mp_aheight = 1, };
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
+ loff_t pos = (loff_t)lblock << inode->i_blkbits;
+ int ret;
+
+ ret = gfs2_iomap_get(inode, pos, sdp->sd_sb.sb_bsize, 0, &iomap, &mp);
+ release_metapath(&mp);
+
+ if (gfs2_assert_withdraw(sdp, ret == 0))
+ return (u64)ret;
+
+ return iomap.addr >> inode->i_blkbits;
+}
+
static int gfs2_write_lock(struct inode *inode)
{
struct gfs2_inode *ip = GFS2_I(inode);
diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h
index 6b18fb323f0a..57e9e57dda86 100644
--- a/fs/gfs2/bmap.h
+++ b/fs/gfs2/bmap.h
@@ -64,5 +64,6 @@ extern int gfs2_write_alloc_required(struct gfs2_inode *ip,
u64 offset,
extern int gfs2_map_journal_extents(struct gfs2_sbd *sdp, struct gfs2_jdesc
*jd);
extern void gfs2_free_journal_extents(struct gfs2_jdesc *jd);
extern int __gfs2_punch_hole(struct file *file, loff_t offset, loff_t length);
+extern u64 gfs2_lblk_to_dblk(struct inode *inode, u32 lblock);
#endif /* __BMAP_DOT_H__ */
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index cdf07b408f54..86840a70ee1a 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -535,7 +535,7 @@ struct gfs2_jdesc {
unsigned long jd_flags;
#define JDF_RECOVERY 1
unsigned int jd_jid;
- unsigned int jd_blocks;
+ u32 jd_blocks;
int jd_recover_error;
/* Replay stuff */
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index b8830fda51e8..a80a6257cba6 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -666,11 +666,12 @@ void gfs2_write_revokes(struct gfs2_sbd *sdp)
}
/**
- * write_log_header - Write a journal log header buffer at sd_log_flush_head
+ * gfs2_write_log_header - Write a journal log header buffer at lblock
* @sdp: The GFS2 superblock
* @jd: journal descriptor of the journal to which we are writing
* @seq: sequence number
* @tail: tail of the log
+ * @lblock: value for lh_blkno (block number relative to start of journal)
* @flags: log header flags GFS2_LOG_HEAD_*
* @op_flags: flags to pass to the bio
*
@@ -678,7 +679,8 @@ void gfs2_write_revokes(struct gfs2_sbd *sdp)
*/
void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
- u64 seq, u32 tail, u32 flags, int op_flags)
+ u64 seq, u32 tail, u32 lblock, u32 flags,
+ int op_flags)
{
struct gfs2_log_header *lh;
u32 hash, crc;
@@ -686,7 +688,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct
gfs2_jdesc *jd,
struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
struct timespec64 tv;
struct super_block *sb = sdp->sd_vfs;
- u64 addr;
+ u64 dblock;
lh = page_address(page);
clear_page(lh);
@@ -699,15 +701,21 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct
gfs2_jdesc *jd,
lh->lh_sequence = cpu_to_be64(seq);
lh->lh_flags = cpu_to_be32(flags);
lh->lh_tail = cpu_to_be32(tail);
- lh->lh_blkno = cpu_to_be32(sdp->sd_log_flush_head);
+ lh->lh_blkno = cpu_to_be32(lblock);
hash = ~crc32(~0, lh, LH_V1_SIZE);
lh->lh_hash = cpu_to_be32(hash);
ktime_get_coarse_real_ts64(&tv);
lh->lh_nsec = cpu_to_be32(tv.tv_nsec);
lh->lh_sec = cpu_to_be64(tv.tv_sec);
- addr = gfs2_log_bmap(sdp);
- lh->lh_addr = cpu_to_be64(addr);
+ if (!list_empty(&jd->extent_list))
+ dblock = gfs2_log_bmap(sdp);
+ else {
+ dblock = gfs2_lblk_to_dblk(jd->jd_inode, lblock);
+ if (gfs2_assert_withdraw(sdp, dblock > 0))
+ return;
+ }
+ lh->lh_addr = cpu_to_be64(dblock);
lh->lh_jinode = cpu_to_be64(GFS2_I(jd->jd_inode)->i_no_addr);
/* We may only write local statfs, quota, etc., when writing to our
@@ -732,7 +740,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct
gfs2_jdesc *jd,
sb->s_blocksize - LH_V1_SIZE - 4);
lh->lh_crc = cpu_to_be32(crc);
- gfs2_log_write(sdp, page, sb->s_blocksize, 0, addr);
+ gfs2_log_write(sdp, page, sb->s_blocksize, 0, dblock);
gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, op_flags);
log_flush_wait(sdp);
}
@@ -761,7 +769,7 @@ static void log_write_header(struct gfs2_sbd *sdp, u32
flags)
}
sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
gfs2_write_log_header(sdp, sdp->sd_jdesc, sdp->sd_log_sequence++, tail,
- flags, op_flags);
+ sdp->sd_log_flush_head, flags, op_flags);
if (sdp->sd_log_tail != tail)
log_pull_tail(sdp, tail);
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index 1bc9bd444b28..86d07d436cdf 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -70,7 +70,8 @@ extern unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp,
unsigned int nstruct,
extern void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks);
extern int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks);
extern void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
- u64 seq, u32 tail, u32 flags, int op_flags);
+ u64 seq, u32 tail, u32 lblock, u32 flags,
+ int op_flags);
extern void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
u32 type);
extern void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 8722c60b11fe..aef21b6a608f 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -530,7 +530,7 @@ static void buf_lo_before_scan(struct gfs2_jdesc *jd,
jd->jd_replayed_blocks = 0;
}
-static int buf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+static int buf_lo_scan_elements(struct gfs2_jdesc *jd, u32 start,
struct gfs2_log_descriptor *ld, __be64 *ptr,
int pass)
{
@@ -685,7 +685,7 @@ static void revoke_lo_before_scan(struct gfs2_jdesc *jd,
jd->jd_replay_tail = head->lh_tail;
}
-static int revoke_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+static int revoke_lo_scan_elements(struct gfs2_jdesc *jd, u32 start,
struct gfs2_log_descriptor *ld, __be64 *ptr,
int pass)
{
@@ -767,7 +767,7 @@ static void databuf_lo_before_commit(struct gfs2_sbd *sdp,
struct gfs2_trans *tr
gfs2_before_commit(sdp, limit, nbuf, &tr->tr_databuf, 1);
}
-static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, u32 start,
struct gfs2_log_descriptor *ld,
__be64 *ptr, int pass)
{
diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h
index 711c4d89c063..4e81742de7a0 100644
--- a/fs/gfs2/lops.h
+++ b/fs/gfs2/lops.h
@@ -77,7 +77,7 @@ static inline void lops_before_scan(struct gfs2_jdesc *jd,
gfs2_log_ops[x]->lo_before_scan(jd, head, pass);
}
-static inline int lops_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
+static inline int lops_scan_elements(struct gfs2_jdesc *jd, u32 start,
struct gfs2_log_descriptor *ld,
__be64 *ptr,
unsigned int pass)
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index 2dac43065382..fa575d1676b9 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -316,7 +316,7 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct
gfs2_log_header_host *head)
* Returns: errno
*/
-static int foreach_descriptor(struct gfs2_jdesc *jd, unsigned int start,
+static int foreach_descriptor(struct gfs2_jdesc *jd, u32 start,
unsigned int end, int pass)
{
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
@@ -386,10 +386,12 @@ static void clean_journal(struct gfs2_jdesc *jd,
struct gfs2_log_header_host *head)
{
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
+ u32 lblock = head->lh_blkno;
- sdp->sd_log_flush_head = head->lh_blkno;
- gfs2_replay_incr_blk(jd, &sdp->sd_log_flush_head);
- gfs2_write_log_header(sdp, jd, head->lh_sequence + 1, 0,
+ gfs2_replay_incr_blk(jd, &lblock);
+ if (jd->jd_jid == sdp->sd_lockstruct.ls_jid)
+ sdp->sd_log_flush_head = lblock;
+ gfs2_write_log_header(sdp, jd, head->lh_sequence + 1, 0, lblock,
GFS2_LOG_HEAD_UNMOUNT | GFS2_LOG_HEAD_RECOVERY,
REQ_PREFLUSH | REQ_FUA | REQ_META | REQ_SYNC);
}
diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h
index 11d81248be85..5932d4b6f43e 100644
--- a/fs/gfs2/recovery.h
+++ b/fs/gfs2/recovery.h
@@ -14,7 +14,7 @@
extern struct workqueue_struct *gfs_recovery_wq;
-static inline void gfs2_replay_incr_blk(struct gfs2_jdesc *jd, unsigned int
*blk)
+static inline void gfs2_replay_incr_blk(struct gfs2_jdesc *jd, u32 *blk)
{
if (++*blk == jd->jd_blocks)
*blk = 0;
