[Cluster-devel] [GFS2 PATCH v3 00/19] gfs2: misc recovery patch collection

[Cluster-devel] [GFS2 PATCH v3 00/19] gfs2: misc recovery patch collection

[Bob Peterson]

Here is version 3 of the patch set I posted on 23 April. It is revised
based on bugs I found testing with xfstests.

This is a collection of patches I've been using to address the myriad
of recovery problems I've found. I'm still finding them, so the battle
is not won yet. I'm not convinced we need all of these but I thought
I'd send them anyway and get feedback. Previously I sent out a version
of the patch "gfs2: Force withdraw to replay journals and wait for it
to finish" that was too big and complex. So I broke it up into four
patches, starting with "move check_journal_clean to util.c for future
use". So those four need to be a set. There aren't many other dependencies
between patches, so the others could probably be taken or rejected
individually. There are more patches I still need to perfect, but maybe
a few of the safer ones can be pushed to for-next.

Bob Peterson (19):
  gfs2: kthread and remount improvements
  gfs2: eliminate tr_num_revoke_rm
  gfs2: log which portion of the journal is replayed
  gfs2: Warn when a journal replay overwrites a rgrp with buffers
  gfs2: Introduce concept of a pending withdraw
  gfs2: log error reform
  gfs2: Only complain the first time an io error occurs in quota or log
  gfs2: Stop ail1 wait loop when withdrawn
  gfs2: Ignore recovery attempts if gfs2 has io error or is withdrawn
  gfs2: move check_journal_clean to util.c for future use
  gfs2: Allow some glocks to be used during withdraw
  gfs2: Don't loop forever in gfs2_freeze if withdrawn
  gfs2: Make secondary withdrawers wait for first withdrawer
  gfs2: Don't write log headers after file system withdraw
  gfs2: Force withdraw to replay journals and wait for it to finish
  gfs2: simply gfs2_freeze by removing case
  gfs2: Add verbose option to check_journal_clean
  gfs2: Check for log write errors before telling dlm to unlock
  gfs2: Do log_flush in gfs2_ail_empty_gl even if ail list is empty

 fs/gfs2/aops.c       |   4 +-
 fs/gfs2/file.c       |   2 +-
 fs/gfs2/glock.c      |  82 +++++++++++++++--
 fs/gfs2/glock.h      |   1 +
 fs/gfs2/glops.c      | 100 +++++++++++++++++++--
 fs/gfs2/glops.h      |   3 +-
 fs/gfs2/incore.h     |  21 ++++-
 fs/gfs2/inode.c      |  14 ++-
 fs/gfs2/lock_dlm.c   |  50 +++++++++++
 fs/gfs2/log.c        |  55 +++++++-----
 fs/gfs2/log.h        |   1 +
 fs/gfs2/lops.c       |  27 +++++-
 fs/gfs2/meta_io.c    |   6 +-
 fs/gfs2/ops_fstype.c |  65 ++++----------
 fs/gfs2/quota.c      |  10 ++-
 fs/gfs2/recovery.c   |   3 +-
 fs/gfs2/super.c      |  88 +++++++++++-------
 fs/gfs2/super.h      |   1 +
 fs/gfs2/sys.c        |  14 ++-
 fs/gfs2/trans.c      |   6 +-
 fs/gfs2/util.c       | 206 ++++++++++++++++++++++++++++++++++++++++---
 fs/gfs2/util.h       |  15 ++++
 22 files changed, 617 insertions(+), 157 deletions(-)

-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 01/19] gfs2: kthread and remount improvements

[Bob Peterson]

Before this patch, gfs2 saved the pointers to the two daemon threads
(logd and quotad) in the superblock, but they were never cleared,
even if the threads were stopped (e.g. on remount -o ro). That meant
that certain error conditions (like a withdrawn file system) could
race. For example, xfstests generic/361 caused an IO error during
remount -o ro, which caused the kthreads to be stopped, then the
error flagged. Later, when the test unmounted the file system, it
would try to stop the threads a second time with kthread_stop.

This patch does two things: First, every time it stops the threads
it zeroes out the thread pointer, and also checks whether it's NULL
before trying to stop it. Second, in function gfs2_remount_fs, it
was returning if an error was logged by either of the two functions
for gfs2_make_fs_ro and _rw, which caused it to bypass the online
uevent at the bottom of the function. This removes that bypass in
favor of just running the whole function, then returning the error.
That way, unmounts and remounts won't hang forever.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/super.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index a6a325b2a78b..dc4ec1ca3d4e 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -396,6 +396,7 @@ static int init_threads(struct gfs2_sbd *sdp)
 
 fail:
 	kthread_stop(sdp->sd_logd_process);
+	sdp->sd_logd_process = NULL;
 	return error;
 }
 
@@ -453,8 +454,12 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp)
 	freeze_gh.gh_flags |= GL_NOCACHE;
 	gfs2_glock_dq_uninit(&freeze_gh);
 fail_threads:
-	kthread_stop(sdp->sd_quotad_process);
-	kthread_stop(sdp->sd_logd_process);
+	if (sdp->sd_quotad_process)
+		kthread_stop(sdp->sd_quotad_process);
+	sdp->sd_quotad_process = NULL;
+	if (sdp->sd_logd_process)
+		kthread_stop(sdp->sd_logd_process);
+	sdp->sd_logd_process = NULL;
 	return error;
 }
 
@@ -855,8 +860,12 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 		return error;
 
 	flush_workqueue(gfs2_delete_workqueue);
-	kthread_stop(sdp->sd_quotad_process);
-	kthread_stop(sdp->sd_logd_process);
+	if (sdp->sd_quotad_process)
+		kthread_stop(sdp->sd_quotad_process);
+	sdp->sd_quotad_process = NULL;
+	if (sdp->sd_logd_process)
+		kthread_stop(sdp->sd_logd_process);
+	sdp->sd_logd_process = NULL;
 
 	gfs2_quota_sync(sdp->sd_vfs, 0);
 	gfs2_statfs_sync(sdp->sd_vfs, 0);
@@ -1273,8 +1282,6 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
 			error = gfs2_make_fs_ro(sdp);
 		else
 			error = gfs2_make_fs_rw(sdp);
-		if (error)
-			return error;
 	}
 
 	sdp->sd_args = args;
@@ -1300,7 +1307,7 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
 	spin_unlock(&gt->gt_spin);
 
 	gfs2_online_uevent(sdp);
-	return 0;
+	return error;
 }
 
 /**
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 02/19] gfs2: eliminate tr_num_revoke_rm

[Bob Peterson]

For its journal processing, gfs2 kept track of the number of buffers
added and removed on a per-transaction basis. These values are used
to calculate space needed in the journal. But while these calculations
make sense for the number of buffers, they make no sense for revokes.
Revokes are managed in their own list, linked from the superblock.
So it's entirely unnecessary to keep separate per-transaction counts
for revokes added and removed. A single count will do the same job.
Therefore, this patch combines the transaction revokes into a single
count.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/incore.h | 1 -
 fs/gfs2/log.c    | 3 +--
 fs/gfs2/trans.c  | 6 +++---
 3 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 78c8e761b321..c54800385298 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -507,7 +507,6 @@ struct gfs2_trans {
 	unsigned int tr_num_buf_rm;
 	unsigned int tr_num_databuf_rm;
 	unsigned int tr_num_revoke;
-	unsigned int tr_num_revoke_rm;
 
 	struct list_head tr_list;
 	struct list_head tr_databuf;
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index a7febb4bd400..76da6f046379 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -887,7 +887,6 @@ static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new)
 	old->tr_num_buf_rm	+= new->tr_num_buf_rm;
 	old->tr_num_databuf_rm	+= new->tr_num_databuf_rm;
 	old->tr_num_revoke	+= new->tr_num_revoke;
-	old->tr_num_revoke_rm	+= new->tr_num_revoke_rm;
 
 	list_splice_tail_init(&new->tr_databuf, &old->tr_databuf);
 	list_splice_tail_init(&new->tr_buf, &old->tr_buf);
@@ -909,7 +908,7 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 		set_bit(TR_ATTACHED, &tr->tr_flags);
 	}
 
-	sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
+	sdp->sd_log_commited_revoke += tr->tr_num_revoke;
 	reserved = calc_reserved(sdp);
 	maxres = sdp->sd_log_blks_reserved + tr->tr_reserved;
 	gfs2_assert_withdraw(sdp, maxres >= reserved);
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index d328da7cde36..7ebc0f99deb1 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -80,10 +80,10 @@ static void gfs2_print_trans(struct gfs2_sbd *sdp, const struct gfs2_trans *tr)
 	fs_warn(sdp, "blocks=%u revokes=%u reserved=%u touched=%u\n",
 		tr->tr_blocks, tr->tr_revokes, tr->tr_reserved,
 		test_bit(TR_TOUCHED, &tr->tr_flags));
-	fs_warn(sdp, "Buf %u/%u Databuf %u/%u Revoke %u/%u\n",
+	fs_warn(sdp, "Buf %u/%u Databuf %u/%u Revoke %u\n",
 		tr->tr_num_buf_new, tr->tr_num_buf_rm,
 		tr->tr_num_databuf_new, tr->tr_num_databuf_rm,
-		tr->tr_num_revoke, tr->tr_num_revoke_rm);
+		tr->tr_num_revoke);
 }
 
 void gfs2_trans_end(struct gfs2_sbd *sdp)
@@ -266,7 +266,7 @@ void gfs2_trans_remove_revoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len)
 			gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke);
 			sdp->sd_log_num_revoke--;
 			kmem_cache_free(gfs2_bufdata_cachep, bd);
-			tr->tr_num_revoke_rm++;
+			tr->tr_num_revoke--;
 			if (--n == 0)
 				break;
 		}
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 03/19] gfs2: log which portion of the journal is replayed

[Bob Peterson]

When a journal is replayed, gfs2 logs a message similar to:

jid=X: Replaying journal...

This patch adds the tail and block number so that the range of the
replayed block is also printed. These values will match the values
shown if the journal is dumped with gfs2_edit -p journalX. The
resulting output looks something like this:

jid=1: Replaying journal...0x28b7 to 0x2beb

This will allow us to better debug file system corruption problems.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/recovery.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index fa575d1676b9..16422fdef2b9 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -514,7 +514,8 @@ void gfs2_recover_func(struct work_struct *work)
 		}
 
 		t_tlck = ktime_get();
-		fs_info(sdp, "jid=%u: Replaying journal...\n", jd->jd_jid);
+		fs_info(sdp, "jid=%u: Replaying journal...0x%x to 0x%x\n",
+			jd->jd_jid, head.lh_tail, head.lh_blkno);
 
 		for (pass = 0; pass < 2; pass++) {
 			lops_before_scan(jd, &head, pass);
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 04/19] gfs2: Warn when a journal replay overwrites a rgrp with buffers

[Bob Peterson]

This patch adds some instrumentation in gfs2's journal replay that
indicates when we're about to overwrite a rgrp for which we already
have a valid buffer_head.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/lops.c | 22 ++++++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 6af6a3cea967..2e8c6d02e112 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -564,9 +564,27 @@ static int buf_lo_scan_elements(struct gfs2_jdesc *jd, u32 start,
 
 		if (gfs2_meta_check(sdp, bh_ip))
 			error = -EIO;
-		else
+		else {
+			struct gfs2_meta_header *mh =
+				(struct gfs2_meta_header *)bh_ip->b_data;
+
+			if (mh->mh_type == cpu_to_be32(GFS2_METATYPE_RG)) {
+				struct gfs2_rgrpd *rgd;
+
+				rgd = gfs2_blk2rgrpd(sdp, blkno, false);
+				if (rgd && rgd->rd_addr == blkno &&
+				    rgd->rd_bits && rgd->rd_bits->bi_bh) {
+					fs_info(sdp, "Replaying 0x%llx but we "
+						"already have a bh!\n",
+						(unsigned long long)blkno);
+					fs_info(sdp, "busy:%d, pinned:%d\n",
+						buffer_busy(rgd->rd_bits->bi_bh) ? 1 : 0,
+						buffer_pinned(rgd->rd_bits->bi_bh));
+					gfs2_dump_glock(NULL, rgd->rd_gl);
+				}
+			}
 			mark_buffer_dirty(bh_ip);
-
+		}
 		brelse(bh_log);
 		brelse(bh_ip);
 
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 05/19] gfs2: Introduce concept of a pending withdraw

[Bob Peterson]

File system withdraws can be delayed when inconsistencies are
discovered when we cannot withdraw immediately, for example, when
critical spin_locks are held. But delaying the withdraw can cause
gfs2 to ignore the error and keep running for a short period of time.
For example, an rgrp glock may be dequeued and demoted while there
are still buffers that haven't been properly revoked, due to io
errors writing to the journal.

This patch introduces a new concept of a pending withdraw, which
means an inconsistency has been discovered and we need to withdraw
at the earliest possible opportunity. In these cases, we aren't
quite withdrawn yet, but we still need to not dequeue glocks and
other critical things. If we dequeue the glocks and the withdraw
results in our journal being replayed, the replay could overwrite
data that's been modified by a different node that acquired the
glock in the meantime.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/aops.c       |  4 ++--
 fs/gfs2/file.c       |  2 +-
 fs/gfs2/glock.c      |  7 +++----
 fs/gfs2/glops.c      |  2 +-
 fs/gfs2/incore.h     |  1 +
 fs/gfs2/log.c        | 20 ++++++++------------
 fs/gfs2/meta_io.c    |  6 +++---
 fs/gfs2/ops_fstype.c |  3 +--
 fs/gfs2/quota.c      |  2 +-
 fs/gfs2/super.c      |  6 +++---
 fs/gfs2/sys.c        |  2 +-
 fs/gfs2/util.h       | 12 ++++++++++++
 12 files changed, 37 insertions(+), 30 deletions(-)

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 05dd78f4b2b3..2bacce032a34 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -521,7 +521,7 @@ static int __gfs2_readpage(void *file, struct page *page)
 		error = mpage_readpage(page, gfs2_block_map);
 	}
 
-	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+	if (unlikely(gfs2_withdrawn(sdp)))
 		return -EIO;
 
 	return error;
@@ -638,7 +638,7 @@ static int gfs2_readpages(struct file *file, struct address_space *mapping,
 	gfs2_glock_dq(&gh);
 out_uninit:
 	gfs2_holder_uninit(&gh);
-	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+	if (unlikely(gfs2_withdrawn(sdp)))
 		ret = -EIO;
 	return ret;
 }
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 58a768e59712..bba39c73a43c 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1169,7 +1169,7 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
 		cmd = F_SETLK;
 		fl->fl_type = F_UNLCK;
 	}
-	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
+	if (unlikely(gfs2_withdrawn(sdp))) {
 		if (fl->fl_type == F_UNLCK)
 			locks_lock_file_wait(file, fl);
 		return -EIO;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 15c605cfcfc8..fe9f9a22426e 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -547,7 +547,7 @@ __acquires(&gl->gl_lockref.lock)
 	unsigned int lck_flags = (unsigned int)(gh ? gh->gh_flags : 0);
 	int ret;
 
-	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) &&
+	if (unlikely(gfs2_withdrawn(sdp)) &&
 	    target != LM_ST_UNLOCKED)
 		return;
 	lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
@@ -584,8 +584,7 @@ __acquires(&gl->gl_lockref.lock)
 		}
 		else if (ret) {
 			fs_err(sdp, "lm_lock ret %d\n", ret);
-			GLOCK_BUG_ON(gl, !test_bit(SDF_SHUTDOWN,
-						   &sdp->sd_flags));
+			GLOCK_BUG_ON(gl, !gfs2_withdrawn(sdp));
 		}
 	} else { /* lock_nolock */
 		finish_xmote(gl, target);
@@ -1097,7 +1096,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh)
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	int error = 0;
 
-	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+	if (unlikely(gfs2_withdrawn(sdp)))
 		return -EIO;
 
 	if (test_bit(GLF_LRU, &gl->gl_flags))
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 78510ab91835..b9f36a85a4d4 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -538,7 +538,7 @@ static int freeze_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
 			gfs2_consist(sdp);
 
 		/*  Initialize some head of the log stuff  */
-		if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) {
+		if (!gfs2_withdrawn(sdp)) {
 			sdp->sd_log_sequence = head.lh_sequence + 1;
 			gfs2_log_pointers_init(sdp, head.lh_blkno);
 		}
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index c54800385298..003d9da937b4 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -620,6 +620,7 @@ enum {
 	SDF_SKIP_DLM_UNLOCK	= 8,
 	SDF_FORCE_AIL_FLUSH     = 9,
 	SDF_AIL1_IO_ERROR	= 10,
+	SDF_WITHDRAW		= 11, /* Will withdraw eventually */
 };
 
 enum gfs2_freeze_state {
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 76da6f046379..944aaf3d1816 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -92,8 +92,7 @@ static void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
 
 static int gfs2_ail1_start_one(struct gfs2_sbd *sdp,
 			       struct writeback_control *wbc,
-			       struct gfs2_trans *tr,
-			       bool *withdraw)
+			       struct gfs2_trans *tr)
 __releases(&sdp->sd_ail_lock)
 __acquires(&sdp->sd_ail_lock)
 {
@@ -112,7 +111,7 @@ __acquires(&sdp->sd_ail_lock)
 			    !test_and_set_bit(SDF_AIL1_IO_ERROR,
 					      &sdp->sd_flags)) {
 				gfs2_io_error_bh(sdp, bh);
-				*withdraw = true;
+				set_bit(SDF_WITHDRAW, &sdp->sd_flags);
 			}
 			list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
 			continue;
@@ -153,7 +152,6 @@ void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc)
 	struct list_head *head = &sdp->sd_ail1_list;
 	struct gfs2_trans *tr;
 	struct blk_plug plug;
-	bool withdraw = false;
 
 	trace_gfs2_ail_flush(sdp, wbc, 1);
 	blk_start_plug(&plug);
@@ -162,12 +160,12 @@ void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc)
 	list_for_each_entry_reverse(tr, head, tr_list) {
 		if (wbc->nr_to_write <= 0)
 			break;
-		if (gfs2_ail1_start_one(sdp, wbc, tr, &withdraw))
+		if (gfs2_ail1_start_one(sdp, wbc, tr))
 			goto restart;
 	}
 	spin_unlock(&sdp->sd_ail_lock);
 	blk_finish_plug(&plug);
-	if (withdraw)
+	if (test_bit(SDF_WITHDRAW, &sdp->sd_flags))
 		gfs2_lm_withdraw(sdp, NULL);
 	trace_gfs2_ail_flush(sdp, wbc, 0);
 }
@@ -196,8 +194,7 @@ static void gfs2_ail1_start(struct gfs2_sbd *sdp)
  *
  */
 
-static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
-				bool *withdraw)
+static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 {
 	struct gfs2_bufdata *bd, *s;
 	struct buffer_head *bh;
@@ -211,7 +208,7 @@ static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
 		if (!buffer_uptodate(bh) &&
 		    !test_and_set_bit(SDF_AIL1_IO_ERROR, &sdp->sd_flags)) {
 			gfs2_io_error_bh(sdp, bh);
-			*withdraw = true;
+			set_bit(SDF_WITHDRAW, &sdp->sd_flags);
 		}
 		list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
 	}
@@ -229,11 +226,10 @@ static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
 	struct gfs2_trans *tr, *s;
 	int oldest_tr = 1;
 	int ret;
-	bool withdraw = false;
 
 	spin_lock(&sdp->sd_ail_lock);
 	list_for_each_entry_safe_reverse(tr, s, &sdp->sd_ail1_list, tr_list) {
-		gfs2_ail1_empty_one(sdp, tr, &withdraw);
+		gfs2_ail1_empty_one(sdp, tr);
 		if (list_empty(&tr->tr_ail1_list) && oldest_tr)
 			list_move(&tr->tr_list, &sdp->sd_ail2_list);
 		else
@@ -242,7 +238,7 @@ static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
 	ret = list_empty(&sdp->sd_ail1_list);
 	spin_unlock(&sdp->sd_ail_lock);
 
-	if (withdraw)
+	if (test_bit(SDF_WITHDRAW, &sdp->sd_flags))
 		gfs2_lm_withdraw(sdp, "fatal: I/O error(s)\n");
 
 	return ret;
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 3201342404a7..b125008f064f 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -255,7 +255,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 	struct buffer_head *bh, *bhs[2];
 	int num = 0;
 
-	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
+	if (unlikely(gfs2_withdrawn(sdp))) {
 		*bhp = NULL;
 		return -EIO;
 	}
@@ -313,7 +313,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 
 int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
 {
-	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+	if (unlikely(gfs2_withdrawn(sdp)))
 		return -EIO;
 
 	wait_on_buffer(bh);
@@ -324,7 +324,7 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
 			gfs2_io_error_bh_wd(sdp, bh);
 		return -EIO;
 	}
-	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+	if (unlikely(gfs2_withdrawn(sdp)))
 		return -EIO;
 
 	return 0;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index abfaecde0e3d..075f64075ff6 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -998,8 +998,7 @@ static int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent)
 void gfs2_lm_unmount(struct gfs2_sbd *sdp)
 {
 	const struct lm_lockops *lm = sdp->sd_lockstruct.ls_ops;
-	if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) &&
-	    lm->lm_unmount)
+	if (likely(!gfs2_withdrawn(sdp)) && lm->lm_unmount)
 		lm->lm_unmount(sdp);
 }
 
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 2ae5a109eea7..a8dfc86fd682 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1478,7 +1478,7 @@ static void quotad_error(struct gfs2_sbd *sdp, const char *msg, int error)
 {
 	if (error == 0 || error == -EROFS)
 		return;
-	if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) {
+	if (!gfs2_withdrawn(sdp)) {
 		fs_err(sdp, "gfs2_quotad: %s error %d\n", msg, error);
 		sdp->sd_log_error = error;
 		wake_up(&sdp->sd_logd_waitq);
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index dc4ec1ca3d4e..378519beb6c3 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -807,7 +807,7 @@ static void gfs2_dirty_inode(struct inode *inode, int flags)
 
 	if (!(flags & I_DIRTY_INODE))
 		return;
-	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+	if (unlikely(gfs2_withdrawn(sdp)))
 		return;
 	if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
 		ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
@@ -856,7 +856,7 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 
 	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, GL_NOCACHE,
 				   &freeze_gh);
-	if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
+	if (error && !gfs2_withdrawn(sdp))
 		return error;
 
 	flush_workqueue(gfs2_delete_workqueue);
@@ -1014,7 +1014,7 @@ static int gfs2_freeze(struct super_block *sb)
 	if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN)
 		goto out;
 
-	if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) {
+	if (gfs2_withdrawn(sdp)) {
 		error = -EINVAL;
 		goto out;
 	}
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 1787d295834e..b772ff5509bb 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -121,7 +121,7 @@ static ssize_t freeze_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
 
 static ssize_t withdraw_show(struct gfs2_sbd *sdp, char *buf)
 {
-	unsigned int b = test_bit(SDF_SHUTDOWN, &sdp->sd_flags);
+	unsigned int b = gfs2_withdrawn(sdp);
 	return snprintf(buf, PAGE_SIZE, "%u\n", b);
 }
 
diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h
index 9278fecba632..0df65555545f 100644
--- a/fs/gfs2/util.h
+++ b/fs/gfs2/util.h
@@ -167,6 +167,18 @@ static inline unsigned int gfs2_tune_get_i(struct gfs2_tune *gt,
 	return x;
 }
 
+/**
+ * gfs2_withdrawn - test whether the file system is withdrawing or withdrawn
+ * @sdp: the superblock
+ */
+static inline bool gfs2_withdrawn(struct gfs2_sbd *sdp)
+{
+	if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags) ||
+	    test_bit(SDF_WITHDRAW, &sdp->sd_flags))
+		return true;
+	return false;
+}
+
 #define gfs2_tune_get(sdp, field) \
 gfs2_tune_get_i(&(sdp)->sd_tune, &(sdp)->sd_tune.field)
 
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 06/19] gfs2: log error reform

[Bob Peterson]

Before this patch, gfs2 kept track of journal io errors in two
places sd_log_error and the SDF_AIL1_IO_ERROR flag in sd_flags.
This patch consolidates the two into sd_log_error so that it
reflects the first error encountered writing to the journal.
In future patches, we will take advantage of this by checking
this value rather than having to check both when reacting to
io errors.

In addition, this fixes a tight loop in unmount: If buffers
get on the ail1 list and an io error occurs elsewhere, the
ail1 list would never be cleared because they were always busy.
So unmount would hang, waiting for the ail1 list to empty.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/incore.h |  5 ++---
 fs/gfs2/log.c    | 20 +++++++++++++++-----
 fs/gfs2/quota.c  |  2 +-
 3 files changed, 18 insertions(+), 9 deletions(-)

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 003d9da937b4..e16ab4c98072 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -619,8 +619,7 @@ enum {
 	SDF_RORECOVERY		= 7, /* read only recovery */
 	SDF_SKIP_DLM_UNLOCK	= 8,
 	SDF_FORCE_AIL_FLUSH     = 9,
-	SDF_AIL1_IO_ERROR	= 10,
-	SDF_WITHDRAW		= 11, /* Will withdraw eventually */
+	SDF_WITHDRAW		= 10, /* Will withdraw eventually */
 };
 
 enum gfs2_freeze_state {
@@ -829,7 +828,7 @@ struct gfs2_sbd {
 	atomic_t sd_log_in_flight;
 	struct bio *sd_log_bio;
 	wait_queue_head_t sd_log_flush_wait;
-	int sd_log_error;
+	int sd_log_error; /* First log error */
 
 	atomic_t sd_reserving_log;
 	wait_queue_head_t sd_reserving_log_wait;
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 944aaf3d1816..33ef2cb570e2 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -108,8 +108,7 @@ __acquires(&sdp->sd_ail_lock)
 
 		if (!buffer_busy(bh)) {
 			if (!buffer_uptodate(bh) &&
-			    !test_and_set_bit(SDF_AIL1_IO_ERROR,
-					      &sdp->sd_flags)) {
+			    !cmpxchg(&sdp->sd_log_error, 0, -EIO)) {
 				gfs2_io_error_bh(sdp, bh);
 				set_bit(SDF_WITHDRAW, &sdp->sd_flags);
 			}
@@ -203,10 +202,21 @@ static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 					 bd_ail_st_list) {
 		bh = bd->bd_bh;
 		gfs2_assert(sdp, bd->bd_tr == tr);
-		if (buffer_busy(bh))
+		/**
+		 * If another process flagged an io error, e.g. writing to the
+		 * journal, error all other bhs and move them off the ail1 to
+		 * prevent a tight loop when unmount tries to flush ail1,
+		 * regardless of whether they're still busy. If no outside
+		 * errors were found and the buffer is busy, move to the next.
+		 * If the ail buffer is not busy and caught an error, flag it
+		 * for others.
+		 */
+		if (sdp->sd_log_error) {
+			gfs2_io_error_bh(sdp, bh);
+		} else if (buffer_busy(bh)) {
 			continue;
-		if (!buffer_uptodate(bh) &&
-		    !test_and_set_bit(SDF_AIL1_IO_ERROR, &sdp->sd_flags)) {
+		} else if (!buffer_uptodate(bh) &&
+			   !cmpxchg(&sdp->sd_log_error, 0, -EIO)) {
 			gfs2_io_error_bh(sdp, bh);
 			set_bit(SDF_WITHDRAW, &sdp->sd_flags);
 		}
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index a8dfc86fd682..8871fca9102f 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1480,7 +1480,7 @@ static void quotad_error(struct gfs2_sbd *sdp, const char *msg, int error)
 		return;
 	if (!gfs2_withdrawn(sdp)) {
 		fs_err(sdp, "gfs2_quotad: %s error %d\n", msg, error);
-		sdp->sd_log_error = error;
+		cmpxchg(&sdp->sd_log_error, 0, error);
 		wake_up(&sdp->sd_logd_waitq);
 	}
 }
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 07/19] gfs2: Only complain the first time an io error occurs in quota or log

[Bob Peterson]

Before this patch, all io errors received by the quota daemon or the
logd daemon would cause a complaint message to be issued, such as:

   gfs2: fsid=dm-13.0: Error 10 writing to journal, jid=0

This patch changes it so that the error message is only issued the
first time the error is encountered.

Also, before this patch function gfs2_end_log_write did not set the
sd_log_error value, so log errors would not cause the file system to
be withdrawn. This patch sets the error code so the file system is
properly withdrawn if an io error is encountered writing to the journal.

WARNING: This change in function breaks check xfstests generic/441
and causes it to fail: io errors writing to the log should cause a
file system to be withdrawn, and no further operations are tolerated.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/lops.c  | 5 +++--
 fs/gfs2/quota.c | 4 ++--
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 2e8c6d02e112..065867b5f7c8 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -211,8 +211,9 @@ static void gfs2_end_log_write(struct bio *bio)
 	struct bvec_iter_all iter_all;
 
 	if (bio->bi_status) {
-		fs_err(sdp, "Error %d writing to journal, jid=%u\n",
-		       bio->bi_status, sdp->sd_jdesc->jd_jid);
+		if (!cmpxchg(&sdp->sd_log_error, 0, bio->bi_status))
+			fs_err(sdp, "Error %d writing to journal, jid=%u\n",
+			       bio->bi_status, sdp->sd_jdesc->jd_jid);
 		wake_up(&sdp->sd_logd_waitq);
 	}
 
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 8871fca9102f..acb6cbdd1431 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1479,8 +1479,8 @@ static void quotad_error(struct gfs2_sbd *sdp, const char *msg, int error)
 	if (error == 0 || error == -EROFS)
 		return;
 	if (!gfs2_withdrawn(sdp)) {
-		fs_err(sdp, "gfs2_quotad: %s error %d\n", msg, error);
-		cmpxchg(&sdp->sd_log_error, 0, error);
+		if (!cmpxchg(&sdp->sd_log_error, 0, error))
+			fs_err(sdp, "gfs2_quotad: %s error %d\n", msg, error);
 		wake_up(&sdp->sd_logd_waitq);
 	}
 }
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 08/19] gfs2: Stop ail1 wait loop when withdrawn

[Bob Peterson]

Before this patch, function gfs2_log_flush could get into an infinite
loop trying to clear out its ail1 list. If the file system was
withdrawn (or pending withdraw) due to a problem with writing the ail1
list, it would never clear out the list, and therefore, would loop
infinitely. This patch changes function gfs2_log_flush so that it
does while (!gfs2_withdraw(sdp)) rather than while (;;).

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/log.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 33ef2cb570e2..6169276aa9e6 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -854,7 +854,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags)
 
 	if (!(flags & GFS2_LOG_HEAD_FLUSH_NORMAL)) {
 		if (!sdp->sd_log_idle) {
-			for (;;) {
+			while (!gfs2_withdrawn(sdp)) {
 				gfs2_ail1_start(sdp);
 				gfs2_ail1_wait(sdp);
 				if (gfs2_ail1_empty(sdp))
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 09/19] gfs2: Ignore recovery attempts if gfs2 has io error or is withdrawn

[Bob Peterson]

This patch addresses various problems with gfs2/dlm recovery.

For example, suppose a node with a bunch of gfs2 mounts suddenly
reboots due to kernel panic, and dlm determines it should perform
recovery. DLM does so from a pseudo-state machine calling various
callbacks into lock_dlm to perform a sequence of steps. It uses
generation numbers and recover bits in dlm "control" lock lvbs.

Now suppose another node tries to recover the failed node's
journal, but in so doing, encounters an IO error or withdraws
due to unforeseen circumstances, such as an hba driver failure.
In these cases, the recovery would eventually bail out, but it
would still update its generation number in the lvb. The other
nodes would all see the newer generation number and think they
don't need to do recovery because the generation number is newer
than the last one they saw, and therefore someone else has already
taken care of it.

If the file system has an io error or is withdrawn, it cannot
safely replay any journals (its own or others) but someone else
still needs to do it. Therefore we don't want it messing with
the journal recovery generation numbers: the local generation
numbers eventually get put into the lvb generation numbers to be
seen by all nodes.

This patch adds checks to many of the callbacks used by dlm
in its recovery state machine so that the functions are ignored
and skipped if an io error has occurred or if the file system
was withdraw.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/lock_dlm.c | 18 ++++++++++++++++++
 fs/gfs2/util.c     | 15 +++++++--------
 2 files changed, 25 insertions(+), 8 deletions(-)

diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 31df26ed7854..9329f86ffcbe 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -1081,6 +1081,10 @@ static void gdlm_recover_prep(void *arg)
 	struct gfs2_sbd *sdp = arg;
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
 
+	if (gfs2_withdrawn(sdp)) {
+		fs_err(sdp, "recover_prep ignored due to withdraw.\n");
+		return;
+	}
 	spin_lock(&ls->ls_recover_spin);
 	ls->ls_recover_block = ls->ls_recover_start;
 	set_bit(DFL_DLM_RECOVERY, &ls->ls_recover_flags);
@@ -1103,6 +1107,11 @@ static void gdlm_recover_slot(void *arg, struct dlm_slot *slot)
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
 	int jid = slot->slot - 1;
 
+	if (gfs2_withdrawn(sdp)) {
+		fs_err(sdp, "recover_slot jid %d ignored due to withdraw.\n",
+		       jid);
+		return;
+	}
 	spin_lock(&ls->ls_recover_spin);
 	if (ls->ls_recover_size < jid + 1) {
 		fs_err(sdp, "recover_slot jid %d gen %u short size %d\n",
@@ -1127,6 +1136,10 @@ static void gdlm_recover_done(void *arg, struct dlm_slot *slots, int num_slots,
 	struct gfs2_sbd *sdp = arg;
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
 
+	if (gfs2_withdrawn(sdp)) {
+		fs_err(sdp, "recover_done ignored due to withdraw.\n");
+		return;
+	}
 	/* ensure the ls jid arrays are large enough */
 	set_recover_size(sdp, slots, num_slots);
 
@@ -1154,6 +1167,11 @@ static void gdlm_recovery_result(struct gfs2_sbd *sdp, unsigned int jid,
 {
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
 
+	if (gfs2_withdrawn(sdp)) {
+		fs_err(sdp, "recovery_result jid %d ignored due to withdraw.\n",
+		       jid);
+		return;
+	}
 	if (test_bit(DFL_NO_DLM_OPS, &ls->ls_recover_flags))
 		return;
 
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 0a814ccac41d..7eaea6dfe1cf 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -259,14 +259,13 @@ void gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
 			const char *function, char *file, unsigned int line,
 			bool withdraw)
 {
-	if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
-		fs_err(sdp,
-		       "fatal: I/O error\n"
-		       "  block = %llu\n"
-		       "  function = %s, file = %s, line = %u\n",
-		       (unsigned long long)bh->b_blocknr,
-		       function, file, line);
+	if (gfs2_withdrawn(sdp))
+		return;
+
+	fs_err(sdp, "fatal: I/O error\n"
+	       "  block = %llu\n"
+	       "  function = %s, file = %s, line = %u\n",
+	       (unsigned long long)bh->b_blocknr, function, file, line);
 	if (withdraw)
 		gfs2_lm_withdraw(sdp, NULL);
 }
-
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 10/19] gfs2: move check_journal_clean to util.c for future use

[Bob Peterson]

Before this patch function check_journal_clean was in ops_fstype.c.
This patch moves it to util.c so we can make use of it elsewhere
in a future patch.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/ops_fstype.c | 42 -----------------------------------------
 fs/gfs2/util.c       | 45 ++++++++++++++++++++++++++++++++++++++++++++
 fs/gfs2/util.h       |  1 +
 3 files changed, 46 insertions(+), 42 deletions(-)

diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 075f64075ff6..8a09f3aa609c 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -590,48 +590,6 @@ static int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh)
 	return error;
 }
 
-/**
- * check_journal_clean - Make sure a journal is clean for a spectator mount
- * @sdp: The GFS2 superblock
- * @jd: The journal descriptor
- *
- * Returns: 0 if the journal is clean or locked, else an error
- */
-static int check_journal_clean(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd)
-{
-	int error;
-	struct gfs2_holder j_gh;
-	struct gfs2_log_header_host head;
-	struct gfs2_inode *ip;
-
-	ip = GFS2_I(jd->jd_inode);
-	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_NOEXP |
-				   GL_EXACT | GL_NOCACHE, &j_gh);
-	if (error) {
-		fs_err(sdp, "Error locking journal for spectator mount.\n");
-		return -EPERM;
-	}
-	error = gfs2_jdesc_check(jd);
-	if (error) {
-		fs_err(sdp, "Error checking journal for spectator mount.\n");
-		goto out_unlock;
-	}
-	error = gfs2_find_jhead(jd, &head);
-	if (error) {
-		fs_err(sdp, "Error parsing journal for spectator mount.\n");
-		goto out_unlock;
-	}
-	if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
-		error = -EPERM;
-		fs_err(sdp, "jid=%u: Journal is dirty, so the first mounter "
-		       "must not be a spectator.\n", jd->jd_jid);
-	}
-
-out_unlock:
-	gfs2_glock_dq_uninit(&j_gh);
-	return error;
-}
-
 static int init_journal(struct gfs2_sbd *sdp, int undo)
 {
 	struct inode *master = d_inode(sdp->sd_master_dir);
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 7eaea6dfe1cf..398d3cedb1a4 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -19,7 +19,10 @@
 #include "gfs2.h"
 #include "incore.h"
 #include "glock.h"
+#include "lops.h"
+#include "recovery.h"
 #include "rgrp.h"
+#include "super.h"
 #include "util.h"
 
 struct kmem_cache *gfs2_glock_cachep __read_mostly;
@@ -36,6 +39,48 @@ void gfs2_assert_i(struct gfs2_sbd *sdp)
 	fs_emerg(sdp, "fatal assertion failed\n");
 }
 
+/**
+ * check_journal_clean - Make sure a journal is clean for a spectator mount
+ * @sdp: The GFS2 superblock
+ * @jd: The journal descriptor
+ *
+ * Returns: 0 if the journal is clean or locked, else an error
+ */
+int check_journal_clean(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd)
+{
+	int error;
+	struct gfs2_holder j_gh;
+	struct gfs2_log_header_host head;
+	struct gfs2_inode *ip;
+
+	ip = GFS2_I(jd->jd_inode);
+	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_NOEXP |
+				   GL_EXACT | GL_NOCACHE, &j_gh);
+	if (error) {
+		fs_err(sdp, "Error locking journal for spectator mount.\n");
+		return -EPERM;
+	}
+	error = gfs2_jdesc_check(jd);
+	if (error) {
+		fs_err(sdp, "Error checking journal for spectator mount.\n");
+		goto out_unlock;
+	}
+	error = gfs2_find_jhead(jd, &head);
+	if (error) {
+		fs_err(sdp, "Error parsing journal for spectator mount.\n");
+		goto out_unlock;
+	}
+	if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
+		error = -EPERM;
+		fs_err(sdp, "jid=%u: Journal is dirty, so the first mounter "
+		       "must not be a spectator.\n", jd->jd_jid);
+	}
+
+out_unlock:
+	gfs2_glock_dq_uninit(&j_gh);
+	return error;
+}
+
 int gfs2_lm_withdraw(struct gfs2_sbd *sdp, const char *fmt, ...)
 {
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h
index 0df65555545f..49d46865dceb 100644
--- a/fs/gfs2/util.h
+++ b/fs/gfs2/util.h
@@ -131,6 +131,7 @@ static inline void gfs2_metatype_set(struct buffer_head *bh, u16 type,
 
 int gfs2_io_error_i(struct gfs2_sbd *sdp, const char *function,
 		    char *file, unsigned int line);
+int check_journal_clean(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd);
 
 #define gfs2_io_error(sdp) \
 gfs2_io_error_i((sdp), __func__, __FILE__, __LINE__);
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 11/19] gfs2: Allow some glocks to be used during withdraw

[Bob Peterson]

Before this patch, when a file system was withdrawn, all further
attempts to enqueue or promote glocks were rejected and returned
-EIO. This is only important for media-backed glocks like inode
and rgrp glocks. All other glocks may be safely used because there
is no potential for metadata corruption. This patch allows some
glocks to be used even after the file system is withdrawn. This
is accomplished with a new glops flag, GLOF_JOURNALED, which tells
us which inodes cannot be safely manipulated after withdraw. This
facilitates future patches that enhance fs withdraw.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/glock.c      |  7 +++++--
 fs/gfs2/glops.c      | 16 +++++++++++++---
 fs/gfs2/glops.h      |  3 ++-
 fs/gfs2/incore.h     |  8 ++++++++
 fs/gfs2/inode.c      | 14 ++++++++++----
 fs/gfs2/ops_fstype.c | 14 +++++++++++---
 fs/gfs2/sys.c        | 12 ++++++++++--
 7 files changed, 59 insertions(+), 15 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index fe9f9a22426e..eeb84d8d21f3 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -548,7 +548,7 @@ __acquires(&gl->gl_lockref.lock)
 	int ret;
 
 	if (unlikely(gfs2_withdrawn(sdp)) &&
-	    target != LM_ST_UNLOCKED)
+	    (glops->go_flags & GLOF_JOURNALED) && target != LM_ST_UNLOCKED)
 		return;
 	lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
 		      LM_FLAG_PRIORITY);
@@ -1096,7 +1096,8 @@ int gfs2_glock_nq(struct gfs2_holder *gh)
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	int error = 0;
 
-	if (unlikely(gfs2_withdrawn(sdp)))
+	if (unlikely(gfs2_withdrawn(sdp)) &&
+	    (gl->gl_ops->go_flags & GLOF_JOURNALED))
 		return -EIO;
 
 	if (test_bit(GLF_LRU, &gl->gl_flags))
@@ -1760,6 +1761,8 @@ static const char *gflags2str(char *buf, const struct gfs2_glock *gl)
 		*p++ = 'o';
 	if (test_bit(GLF_BLOCKING, gflags))
 		*p++ = 'b';
+	if (gl->gl_ops->go_flags & GLOF_JOURNALED)
+		*p++ = 'j';
 	*p = 0;
 	return buf;
 }
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index b9f36a85a4d4..d2b44bdca17e 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -584,7 +584,7 @@ const struct gfs2_glock_operations gfs2_meta_glops = {
 	.go_type = LM_TYPE_META,
 };
 
-const struct gfs2_glock_operations gfs2_inode_glops = {
+const struct gfs2_glock_operations gfs2_sys_inode_glops = {
 	.go_sync = inode_go_sync,
 	.go_inval = inode_go_inval,
 	.go_demote_ok = inode_go_demote_ok,
@@ -594,6 +594,16 @@ const struct gfs2_glock_operations gfs2_inode_glops = {
 	.go_flags = GLOF_ASPACE | GLOF_LRU,
 };
 
+const struct gfs2_glock_operations gfs2_user_inode_glops = {
+	.go_sync = inode_go_sync,
+	.go_inval = inode_go_inval,
+	.go_demote_ok = inode_go_demote_ok,
+	.go_lock = inode_go_lock,
+	.go_dump = inode_go_dump,
+	.go_type = LM_TYPE_INODE,
+	.go_flags = GLOF_ASPACE | GLOF_LRU | GLOF_JOURNALED,
+};
+
 const struct gfs2_glock_operations gfs2_rgrp_glops = {
 	.go_sync = rgrp_go_sync,
 	.go_inval = rgrp_go_inval,
@@ -601,7 +611,7 @@ const struct gfs2_glock_operations gfs2_rgrp_glops = {
 	.go_unlock = gfs2_rgrp_go_unlock,
 	.go_dump = gfs2_rgrp_dump,
 	.go_type = LM_TYPE_RGRP,
-	.go_flags = GLOF_LVB,
+	.go_flags = GLOF_LVB | GLOF_JOURNALED,
 };
 
 const struct gfs2_glock_operations gfs2_freeze_glops = {
@@ -637,7 +647,7 @@ const struct gfs2_glock_operations gfs2_journal_glops = {
 
 const struct gfs2_glock_operations *gfs2_glops_list[] = {
 	[LM_TYPE_META] = &gfs2_meta_glops,
-	[LM_TYPE_INODE] = &gfs2_inode_glops,
+	[LM_TYPE_INODE] = &gfs2_user_inode_glops,
 	[LM_TYPE_RGRP] = &gfs2_rgrp_glops,
 	[LM_TYPE_IOPEN] = &gfs2_iopen_glops,
 	[LM_TYPE_FLOCK] = &gfs2_flock_glops,
diff --git a/fs/gfs2/glops.h b/fs/gfs2/glops.h
index 8ed1857c1a8d..63130a5959e1 100644
--- a/fs/gfs2/glops.h
+++ b/fs/gfs2/glops.h
@@ -15,7 +15,8 @@
 extern struct workqueue_struct *gfs2_freeze_wq;
 
 extern const struct gfs2_glock_operations gfs2_meta_glops;
-extern const struct gfs2_glock_operations gfs2_inode_glops;
+extern const struct gfs2_glock_operations gfs2_user_inode_glops;
+extern const struct gfs2_glock_operations gfs2_sys_inode_glops;
 extern const struct gfs2_glock_operations gfs2_rgrp_glops;
 extern const struct gfs2_glock_operations gfs2_freeze_glops;
 extern const struct gfs2_glock_operations gfs2_iopen_glops;
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index e16ab4c98072..b16b82e5b85a 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -250,6 +250,14 @@ struct gfs2_glock_operations {
 #define GLOF_ASPACE 1
 #define GLOF_LVB    2
 #define GLOF_LRU    4
+/**
+ * The GLOF_JOURNALED flag marks objects that are journaled, which means we
+ * need to treat them specially when a file system withdraw occurs. Inodes
+ * like the journal inode itself are okay to manipulate after withdraw, but
+ * user files need to be protected from journal replay after their glock has
+ * been granted to another node.
+ */
+#define GLOF_JOURNALED 8
 };
 
 enum {
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 998051c4aea7..2fefd8581965 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -141,7 +141,8 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
 		struct gfs2_sbd *sdp = GFS2_SB(inode);
 		ip->i_no_formal_ino = no_formal_ino;
 
-		error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
+		error = gfs2_glock_get(sdp, no_addr, &gfs2_user_inode_glops,
+				       CREATE, &ip->i_gl);
 		if (unlikely(error))
 			goto fail;
 		flush_delayed_work(&ip->i_gl->gl_work);
@@ -248,6 +249,8 @@ struct inode *gfs2_lookup_simple(struct inode *dip, const char *name)
 {
 	struct qstr qstr;
 	struct inode *inode;
+	struct gfs2_inode *ip;
+
 	gfs2_str2qstr(&qstr, name);
 	inode = gfs2_lookupi(dip, &qstr, 1);
 	/* gfs2_lookupi has inconsistent callers: vfs
@@ -257,8 +260,10 @@ struct inode *gfs2_lookup_simple(struct inode *dip, const char *name)
 	 */
 	if (inode == NULL)
 		return ERR_PTR(-ENOENT);
-	else
-		return inode;
+
+	ip = GFS2_I(inode);
+	ip->i_gl->gl_ops = &gfs2_sys_inode_glops;
+	return inode;
 }
 
 
@@ -703,7 +708,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 
 	gfs2_set_inode_blocks(inode, blocks);
 
-	error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
+	error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_user_inode_glops,
+			       CREATE, &ip->i_gl);
 	if (error)
 		goto fail_free_inode;
 	flush_delayed_work(&ip->i_gl->gl_work);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 8a09f3aa609c..531c1870de8e 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -431,7 +431,7 @@ static int init_locking(struct gfs2_sbd *sdp, struct gfs2_holder *mount_gh,
 }
 
 static int gfs2_lookup_root(struct super_block *sb, struct dentry **dptr,
-			    u64 no_addr, const char *name)
+			    u64 no_addr, const char *name, int journaled)
 {
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct dentry *dentry;
@@ -443,6 +443,11 @@ static int gfs2_lookup_root(struct super_block *sb, struct dentry **dptr,
 		fs_err(sdp, "can't read in %s inode: %ld\n", name, PTR_ERR(inode));
 		return PTR_ERR(inode);
 	}
+	if (!journaled) {
+		struct gfs2_inode *ip = GFS2_I(inode);
+
+		ip->i_gl->gl_ops = &gfs2_sys_inode_glops;
+	}
 	dentry = d_make_root(inode);
 	if (!dentry) {
 		fs_err(sdp, "can't alloc %s dentry\n", name);
@@ -491,13 +496,13 @@ static int init_sb(struct gfs2_sbd *sdp, int silent)
 
 	/* Get the root inode */
 	no_addr = sdp->sd_sb.sb_root_dir.no_addr;
-	ret = gfs2_lookup_root(sb, &sdp->sd_root_dir, no_addr, "root");
+	ret = gfs2_lookup_root(sb, &sdp->sd_root_dir, no_addr, "root", 1);
 	if (ret)
 		goto out;
 
 	/* Get the master inode */
 	no_addr = sdp->sd_sb.sb_master_dir.no_addr;
-	ret = gfs2_lookup_root(sb, &sdp->sd_master_dir, no_addr, "master");
+	ret = gfs2_lookup_root(sb, &sdp->sd_master_dir, no_addr, "master", 0);
 	if (ret) {
 		dput(sdp->sd_root_dir);
 		goto out;
@@ -532,6 +537,7 @@ static void gfs2_others_may_mount(struct gfs2_sbd *sdp)
 static int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh)
 {
 	struct gfs2_inode *dip = GFS2_I(sdp->sd_jindex);
+	struct gfs2_inode *ip;
 	struct qstr name;
 	char buf[20];
 	struct gfs2_jdesc *jd;
@@ -579,6 +585,8 @@ static int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh)
 			break;
 		}
 
+		ip = GFS2_I(jd->jd_inode);
+		ip->i_gl->gl_ops = &gfs2_sys_inode_glops;
 		spin_lock(&sdp->sd_jindex_spin);
 		jd->jd_jid = sdp->sd_journals++;
 		list_add_tail(&jd->jd_list, &sdp->sd_jindex_list);
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index b772ff5509bb..dd32e266fd2e 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -264,8 +264,16 @@ static ssize_t demote_rq_store(struct gfs2_sbd *sdp, const char *buf, size_t len
 	if (!test_and_set_bit(SDF_DEMOTE, &sdp->sd_flags))
 		fs_info(sdp, "demote interface used\n");
 	rv = gfs2_glock_get(sdp, glnum, glops, 0, &gl);
-	if (rv)
-		return rv;
+	if (rv) {
+		/* If the glock is not found and it's supposed to be an inode,
+		 * check if it's one of the system inodes. */
+		if (gltype == LM_TYPE_INODE) {
+			glops = &gfs2_sys_inode_glops;
+			rv = gfs2_glock_get(sdp, glnum, glops, 0, &gl);
+			if (rv)
+				return rv;
+		}
+	}
 	gfs2_glock_cb(gl, glmode);
 	gfs2_glock_put(gl);
 	return len;
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 12/19] gfs2: Don't loop forever in gfs2_freeze if withdrawn

[Bob Peterson]

Before this patch, function gfs2_freeze would loop forever if the
file system trying to be frozen is withdrawn. That's because function
gfs2_lock_fs_check_clean tries to enqueue the glock of the journal
and the gfs2_glock returns -EIO because you can't enqueue a journaled
glock after a withdraw.

This patch moves the check for file system withdraw inside the loop
so that the loop can end when withdraw occurs.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/super.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 378519beb6c3..4ae23c338034 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1014,12 +1014,12 @@ static int gfs2_freeze(struct super_block *sb)
 	if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN)
 		goto out;
 
-	if (gfs2_withdrawn(sdp)) {
-		error = -EINVAL;
-		goto out;
-	}
-
 	for (;;) {
+		if (gfs2_withdrawn(sdp)) {
+			error = -EINVAL;
+			goto out;
+		}
+
 		error = gfs2_lock_fs_check_clean(sdp, &sdp->sd_freeze_gh);
 		if (!error)
 			break;
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 13/19] gfs2: Make secondary withdrawers wait for first withdrawer

[Bob Peterson]

Before this patch, if a process encountered an error and decided to
withdraw, if another process was already in the process of withdrawing,
the secondary withdraw would be silently ignored, which set it free
to proceed with its processing, unlock any locks, etc. That's correct
behavior if the original withdrawer encounters further errors down
the road. However, second withdrawers need to wait for the first
withdrawer to finish its withdraw before proceeding. If we don't wait
we could end up assuming everything is alright, unlock glocks and
telling other nodes they can have the glock, despite the fact that
a withdraw is still ongoing and may require a journal replay before
any locks are released. For example, if an rgrp glock is freed
by a process that didn't wait for the withdraw, a journal replay
could introduce file system corruption by replaying a rgrp block
that has already been granted to another node.

This patch makes secondary withdrawers wait until the primary
withdrawer is finished with its processing before proceeding.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/incore.h |  3 +++
 fs/gfs2/util.c   | 21 +++++++++++++++++++--
 2 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index b16b82e5b85a..0b283bbd20ea 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -628,6 +628,7 @@ enum {
 	SDF_SKIP_DLM_UNLOCK	= 8,
 	SDF_FORCE_AIL_FLUSH     = 9,
 	SDF_WITHDRAW		= 10, /* Will withdraw eventually */
+	SDF_WITHDRAW_IN_PROG	= 11, /* Withdraw is in progress */
 };
 
 enum gfs2_freeze_state {
@@ -837,6 +838,8 @@ struct gfs2_sbd {
 	struct bio *sd_log_bio;
 	wait_queue_head_t sd_log_flush_wait;
 	int sd_log_error; /* First log error */
+	atomic_t sd_withdrawer;
+	wait_queue_head_t sd_withdraw_wait;
 
 	atomic_t sd_reserving_log;
 	wait_queue_head_t sd_reserving_log_wait;
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 398d3cedb1a4..ad56f934ff0f 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -89,9 +89,23 @@ int gfs2_lm_withdraw(struct gfs2_sbd *sdp, const char *fmt, ...)
 	struct va_format vaf;
 
 	if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW &&
-	    test_and_set_bit(SDF_SHUTDOWN, &sdp->sd_flags))
-		return 0;
+	    test_and_set_bit(SDF_SHUTDOWN, &sdp->sd_flags)) {
+		if (!test_bit(SDF_WITHDRAW_IN_PROG, &sdp->sd_flags))
+			return -1;
+
+		fs_warn(sdp, "Pid %d waiting for process %d to withdraw.\n",
+			pid_nr(task_pid(current)),
+			atomic_read(&sdp->sd_withdrawer));
+		wait_on_bit(&sdp->sd_flags, SDF_WITHDRAW_IN_PROG,
+			    TASK_UNINTERRUPTIBLE);
+		fs_warn(sdp, "Pid %d done waiting for process %d.\n",
+			pid_nr(task_pid(current)),
+			atomic_read(&sdp->sd_withdrawer));
+		return -1;
+	}
 
+	set_bit(SDF_WITHDRAW_IN_PROG, &sdp->sd_flags);
+	atomic_set(&sdp->sd_withdrawer, pid_nr(task_pid(current)));
 	if (fmt) {
 		va_start(args, fmt);
 
@@ -119,6 +133,9 @@ int gfs2_lm_withdraw(struct gfs2_sbd *sdp, const char *fmt, ...)
 		set_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags);
 		fs_err(sdp, "withdrawn\n");
 		dump_stack();
+		clear_bit(SDF_WITHDRAW_IN_PROG, &sdp->sd_flags);
+		smp_mb__after_atomic();
+		wake_up_bit(&sdp->sd_flags, SDF_WITHDRAW_IN_PROG);
 	}
 
 	if (sdp->sd_args.ar_errors == GFS2_ERRORS_PANIC)
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 14/19] gfs2: Don't write log headers after file system withdraw

[Bob Peterson]

Before this patch, when a node withdrew a gfs2 file system, it
wrote a (clean) unmount log header. That's wrong. You don't want
to write anything to the journal once you're withdrawn because
that's acknowledging that the transaction is complete and the
journal is in good shape, neither of which may be a valid
assumption when the file system is withdrawn. This is especially
true if the withdraw was caused due to io errors writing to the
journal in the first place. The best course of action is to leave
the journal "as is" until it may be safely replayed during
journal recovery, regardless of whether it's done by this node or
another.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/log.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 6169276aa9e6..771589b2e225 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -693,12 +693,16 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
 {
 	struct gfs2_log_header *lh;
 	u32 hash, crc;
-	struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
+	struct page *page;
 	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
 	struct timespec64 tv;
 	struct super_block *sb = sdp->sd_vfs;
 	u64 dblock;
 
+	if (gfs2_withdrawn(sdp))
+		goto out;
+
+	page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
 	lh = page_address(page);
 	clear_page(lh);
 
@@ -751,6 +755,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
 
 	gfs2_log_write(sdp, page, sb->s_blocksize, 0, dblock);
 	gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, op_flags);
+out:
 	log_flush_wait(sdp);
 }
 
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 15/19] gfs2: Force withdraw to replay journals and wait for it to finish

[Bob Peterson]

When a node withdraws from a file system, it often leaves its journal
in an incomplete state. This is especially true when the withdraw is
caused by io errors writing to the journal. Before this patch, a
withdraw would try to write a "shutdown" record to the journal, tell
dlm it's done with the file system, and none of the other nodes
know about the problem. Later, when the problem is fixed and the
withdrawn node is rebooted, it would then discover that its own
journal was incomplete, and replay it. However, replaying it at this
point is almost guaranteed to introduce corruption because the other
nodes are likely to have used affected resource groups that appeared
in the journal since the time of the withdraw. Replaying the journal
later will overwrite any changes made, and not through any fault of
dlm, which was instructed during the withdraw to release those
resources.

This patch makes file system withdraws seen by the entire cluster.
Withdrawing nodes dequeue their journal glock to allow recovery.

The remaining nodes check all the journals to see if they are
clean or in need of replay. They try to replay dirty journals, but
only the journals of withdrawn nodes will be "not busy" and
therefore available for replay.

Until the journal replay is complete, no i/o related glocks may be
given out, to ensure that the replay does not cause the
aforementioned corruption: We cannot allow any journal replay to
overwrite blocks associated with a glock once it is held. The
glocks not affected by a withdraw are permitted to be passed
around as normal during a withdraw. A new glops flag, called
GLOF_OK_AT_WITHDRAW, indicates glocks that may be passed around
freely while a withdraw is taking place.

One such glock is the "live" glock which is now used to signal when
a withdraw occurs. When a withdraw occurs, the node signals its
withdraw by dequeueing the "live" glock and trying to enqueue it
in EX mode, thus forcing the other nodes to all see a demote
request, by way of a "1CB" (one callback) try lock. The "live"
glock is not granted in EX; the callback is only just used to
indicate a withdraw has occurred.

Note that all nodes in the cluster must wait for the recovering
node to finish replaying the withdrawing node's journal before
continuing. To this end, it checks that the journals are clean
multiple times in a retry loop.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/glock.c      |  32 ++++++++++--
 fs/gfs2/glock.h      |   1 +
 fs/gfs2/glops.c      |  56 +++++++++++++++++++++
 fs/gfs2/incore.h     |   5 ++
 fs/gfs2/lock_dlm.c   |  32 ++++++++++++
 fs/gfs2/log.c        |   1 +
 fs/gfs2/meta_io.c    |   2 +-
 fs/gfs2/ops_fstype.c |   4 +-
 fs/gfs2/quota.c      |   4 ++
 fs/gfs2/super.c      |  47 ++++++++++++------
 fs/gfs2/super.h      |   1 +
 fs/gfs2/util.c       | 116 ++++++++++++++++++++++++++++++++++++++++++-
 12 files changed, 281 insertions(+), 20 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index eeb84d8d21f3..3d1b9bdfd0de 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -247,7 +247,7 @@ static void __gfs2_glock_put(struct gfs2_glock *gl)
 	gfs2_glock_remove_from_lru(gl);
 	spin_unlock(&gl->gl_lockref.lock);
 	GLOCK_BUG_ON(gl, !list_empty(&gl->gl_holders));
-	GLOCK_BUG_ON(gl, mapping && mapping->nrpages);
+	GLOCK_BUG_ON(gl, mapping && mapping->nrpages && !gfs2_withdrawn(sdp));
 	trace_gfs2_glock_put(gl);
 	sdp->sd_lockstruct.ls_ops->lm_put_lock(gl);
 }
@@ -548,7 +548,9 @@ __acquires(&gl->gl_lockref.lock)
 	int ret;
 
 	if (unlikely(gfs2_withdrawn(sdp)) &&
-	    (glops->go_flags & GLOF_JOURNALED) && target != LM_ST_UNLOCKED)
+	    (glops->go_flags & GLOF_JOURNALED) &&
+	    (gh && !(LM_FLAG_NOEXP & gh->gh_flags)) &&
+	    target != LM_ST_UNLOCKED)
 		return;
 	lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
 		      LM_FLAG_PRIORITY);
@@ -1096,7 +1098,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh)
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	int error = 0;
 
-	if (unlikely(gfs2_withdrawn(sdp)) &&
+	if (unlikely(gfs2_withdrawn(sdp)) && !(LM_FLAG_NOEXP & gh->gh_flags) &&
 	    (gl->gl_ops->go_flags & GLOF_JOURNALED))
 		return -EIO;
 
@@ -1141,11 +1143,30 @@ int gfs2_glock_poll(struct gfs2_holder *gh)
 void gfs2_glock_dq(struct gfs2_holder *gh)
 {
 	struct gfs2_glock *gl = gh->gh_gl;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
 	unsigned delay = 0;
 	int fast_path = 0;
 
 	spin_lock(&gl->gl_lockref.lock);
+	/**
+	 * If we're in the process of file system withdraw, we cannot just
+	 * dequeue any glocks until our journal is recovered, lest we
+	 * introduce file system corruption. We need two exceptions to this
+	 * rule: We need to allow unlocking of nondisk glocks and the glock
+	 * for our own journal that needs recovery. Note that evict may also
+	 * call this for the journal inode, but without using sdp->sd_jinode_gh
+	 * so we need to check the glock, not just the holder of the glock.
+	 */
+	if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags) &&
+	    test_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags) &&
+	    (gl->gl_ops->go_flags & GLOF_JOURNALED) &&
+	    gh->gh_gl != sdp->sd_jinode_gl) {
+		sdp->sd_glock_dqs_held++;
+		might_sleep();
+		wait_on_bit(&sdp->sd_flags, SDF_WITHDRAW_RECOVERY,
+			    TASK_UNINTERRUPTIBLE);
+	}
 	if (gh->gh_flags & GL_NOCACHE)
 		handle_callback(gl, LM_ST_UNLOCKED, 0, false);
 
@@ -1625,6 +1646,11 @@ static void dump_glock_func(struct gfs2_glock *gl)
 	dump_glock(NULL, gl);
 }
 
+void gfs2_gl_flushwork(struct gfs2_sbd *sdp)
+{
+	flush_workqueue(glock_workqueue);
+}
+
 /**
  * gfs2_gl_hash_clear - Empty out the glock hash table
  * @sdp: the filesystem
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 936b3295839c..c1c40e2dbd96 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -202,6 +202,7 @@ extern int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number,
 			     struct gfs2_holder *gh);
 extern int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs);
 extern void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs);
+extern void gfs2_gl_flushwork(struct gfs2_sbd *sdp);
 extern void gfs2_dump_glock(struct seq_file *seq, struct gfs2_glock *gl);
 #define GLOCK_BUG_ON(gl,x) do { if (unlikely(x)) { gfs2_dump_glock(NULL, gl); BUG(); } } while(0)
 extern __printf(2, 3)
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index d2b44bdca17e..ff50013c6aa9 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -31,6 +31,8 @@
 
 struct workqueue_struct *gfs2_freeze_wq;
 
+extern struct workqueue_struct *gfs2_control_wq;
+
 static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh)
 {
 	fs_err(gl->gl_name.ln_sbd,
@@ -506,6 +508,10 @@ static void freeze_go_sync(struct gfs2_glock *gl)
 		error = freeze_super(sdp->sd_vfs);
 		if (error) {
 			printk(KERN_INFO "GFS2: couldn't freeze filesystem: %d\n", error);
+			if (gfs2_withdrawn(sdp)) {
+				atomic_set(&sdp->sd_freeze_state, SFS_UNFROZEN);
+				return;
+			}
 			gfs2_assert_withdraw(sdp, 0);
 		}
 		queue_work(gfs2_freeze_wq, &sdp->sd_freeze_work);
@@ -580,6 +586,55 @@ static void iopen_go_callback(struct gfs2_glock *gl, bool remote)
 	}
 }
 
+/**
+ * nondisk_go_callback - used to signal when a node did a withdraw
+ * @gl: the nondisk glock
+ * @remote: true if this came from a different cluster node
+ *
+ */
+static void nondisk_go_callback(struct gfs2_glock *gl, bool remote)
+{
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+
+	/* Ignore the callback unless it's from another node, and it's the
+	   live lock. */
+	if (!remote || gl->gl_name.ln_number != GFS2_LIVE_LOCK)
+		return;
+
+	/* First order of business is to cancel the demote request. We don't
+	 * really want to demote a nondisk glock. At best it's just to inform
+	 * us of a another node's withdraw. We'll keep it in SH mode. */
+	clear_bit(GLF_DEMOTE, &gl->gl_flags);
+	clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags);
+
+	/* Ignore the unlock if we're withdrawn, unmounting, or in recovery. */
+	if (test_bit(SDF_NORECOVERY, &sdp->sd_flags) ||
+	    test_bit(SDF_SHUTDOWN, &sdp->sd_flags) ||
+	    test_bit(SDF_REMOTE_WITHDRAW, &sdp->sd_flags))
+		return;
+
+	/* We only care when a node wants us to unlock, because that means
+	 * they want a journal recovered. */
+	if (gl->gl_demote_state != LM_ST_UNLOCKED)
+		return;
+
+	if (sdp->sd_args.ar_spectator) {
+		fs_warn(sdp, "Spectator node cannot recover journals.\n");
+		return;
+	}
+
+	fs_warn(sdp, "Some node has withdrawn; checking for recovery.\n");
+	set_bit(SDF_REMOTE_WITHDRAW, &sdp->sd_flags);
+	/**
+	 * We can't call remote_withdraw directly here or gfs2_recover_journal
+	 * because this is called from the glock unlock function and the
+	 * remote_withdraw needs to enqueue and dequeue the same "live" glock
+	 * we were called from. So we queue it to the control work queue in
+	 * lock_dlm.
+	 */
+	queue_delayed_work(gfs2_control_wq, &sdp->sd_control_work, 0);
+}
+
 const struct gfs2_glock_operations gfs2_meta_glops = {
 	.go_type = LM_TYPE_META,
 };
@@ -634,6 +689,7 @@ const struct gfs2_glock_operations gfs2_flock_glops = {
 
 const struct gfs2_glock_operations gfs2_nondisk_glops = {
 	.go_type = LM_TYPE_NONDISK,
+	.go_callback = nondisk_go_callback,
 };
 
 const struct gfs2_glock_operations gfs2_quota_glops = {
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 0b283bbd20ea..60b094bad47e 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -629,6 +629,9 @@ enum {
 	SDF_FORCE_AIL_FLUSH     = 9,
 	SDF_WITHDRAW		= 10, /* Will withdraw eventually */
 	SDF_WITHDRAW_IN_PROG	= 11, /* Withdraw is in progress */
+	SDF_REMOTE_WITHDRAW	= 12, /* Performing remote recovery */
+	SDF_WITHDRAW_RECOVERY	= 13, /* Wait for journal recovery when we are
+					 withdrawing */
 };
 
 enum gfs2_freeze_state {
@@ -777,6 +780,7 @@ struct gfs2_sbd {
 	struct gfs2_jdesc *sd_jdesc;
 	struct gfs2_holder sd_journal_gh;
 	struct gfs2_holder sd_jinode_gh;
+	struct gfs2_glock *sd_jinode_gl;
 
 	struct gfs2_holder sd_sc_gh;
 	struct gfs2_holder sd_qc_gh;
@@ -863,6 +867,7 @@ struct gfs2_sbd {
 
 	unsigned long sd_last_warning;
 	struct dentry *debugfs_dir;    /* debugfs directory */
+	unsigned long sd_glock_dqs_held;
 };
 
 static inline void gfs2_glstats_inc(struct gfs2_glock *gl, int which)
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 9329f86ffcbe..444c481f985d 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -19,6 +19,8 @@
 
 #include "incore.h"
 #include "glock.h"
+#include "glops.h"
+#include "recovery.h"
 #include "util.h"
 #include "sys.h"
 #include "trace_gfs2.h"
@@ -325,6 +327,7 @@ static void gdlm_cancel(struct gfs2_glock *gl)
 /*
  * dlm/gfs2 recovery coordination using dlm_recover callbacks
  *
+ *  0. gfs2 checks for another cluster node withdraw, needing journal replay
  *  1. dlm_controld sees lockspace members change
  *  2. dlm_controld blocks dlm-kernel locking activity
  *  3. dlm_controld within dlm-kernel notifies gfs2 (recover_prep)
@@ -573,6 +576,28 @@ static int control_lock(struct gfs2_sbd *sdp, int mode, uint32_t flags)
 			 &ls->ls_control_lksb, "control_lock");
 }
 
+/**
+ * remote_withdraw - react to a node withdrawing from the file system
+ * @sdp: The superblock
+ */
+static void remote_withdraw(struct gfs2_sbd *sdp)
+{
+	struct gfs2_jdesc *jd;
+	int ret = 0, count = 0;
+
+	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
+		if (jd->jd_jid == sdp->sd_lockstruct.ls_jid)
+			continue;
+		ret = gfs2_recover_journal(jd, true);
+		if (ret)
+			break;
+		count++;
+	}
+
+	/* Now drop the additional reference we acquired */
+	fs_err(sdp, "Journals checked: %d, ret = %d.\n", count, ret);
+}
+
 static void gfs2_control_func(struct work_struct *work)
 {
 	struct gfs2_sbd *sdp = container_of(work, struct gfs2_sbd, sd_control_work.work);
@@ -583,6 +608,13 @@ static void gfs2_control_func(struct work_struct *work)
 	int recover_size;
 	int i, error;
 
+	/* First check for other nodes that may have done a withdraw. */
+	if (test_bit(SDF_REMOTE_WITHDRAW, &sdp->sd_flags)) {
+		remote_withdraw(sdp);
+		clear_bit(SDF_REMOTE_WITHDRAW, &sdp->sd_flags);
+		return;
+	}
+
 	spin_lock(&ls->ls_recover_spin);
 	/*
 	 * No MOUNT_DONE means we're still mounting; control_mount()
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 771589b2e225..732b585f33be 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -1023,6 +1023,7 @@ int gfs2_logd(void *data)
 					 "withdrawing the file system to "
 					 "prevent further damage.\n",
 					 sdp->sd_fsname, sdp->sd_log_error);
+			break;
 		}
 
 		did_flush = false;
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index b125008f064f..49adeadd5868 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -255,7 +255,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 	struct buffer_head *bh, *bhs[2];
 	int num = 0;
 
-	if (unlikely(gfs2_withdrawn(sdp))) {
+	if (unlikely(gfs2_withdrawn(sdp)) && gl != sdp->sd_jinode_gl) {
 		*bhp = NULL;
 		return -EIO;
 	}
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 531c1870de8e..c4222c1fa735 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -650,7 +650,8 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 
 		error = gfs2_glock_nq_num(sdp, sdp->sd_lockstruct.ls_jid,
 					  &gfs2_journal_glops,
-					  LM_ST_EXCLUSIVE, LM_FLAG_NOEXP,
+					  LM_ST_EXCLUSIVE,
+					  LM_FLAG_NOEXP | GL_NOCACHE,
 					  &sdp->sd_journal_gh);
 		if (error) {
 			fs_err(sdp, "can't acquire journal glock: %d\n", error);
@@ -658,6 +659,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 		}
 
 		ip = GFS2_I(sdp->sd_jdesc->jd_inode);
+		sdp->sd_jinode_gl = ip->i_gl;
 		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
 					   LM_FLAG_NOEXP | GL_EXACT | GL_NOCACHE,
 					   &sdp->sd_jinode_gh);
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index acb6cbdd1431..6075d26c9d78 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -1575,6 +1575,10 @@ int gfs2_quotad(void *data)
 		else
 			t = 0;
 		finish_wait(&sdp->sd_quota_wait, &wait);
+
+		if (atomic_read(&sdp->sd_withdrawer) ==
+		    pid_nr(task_pid(current)))
+			break;
 	}
 
 	return 0;
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 4ae23c338034..1582cb11866e 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -845,35 +845,52 @@ static void gfs2_dirty_inode(struct inode *inode, int flags)
 /**
  * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one
  * @sdp: the filesystem
+ * @withdrawing: if 1, we're withdrawing so only do what's necessary
  *
  * Returns: errno
  */
 
-static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
+int gfs2_make_fs_ro(struct gfs2_sbd *sdp, int withdrawing)
 {
 	struct gfs2_holder freeze_gh;
+	int flags = GL_NOCACHE;
 	int error;
 
-	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, GL_NOCACHE,
+	if (withdrawing)
+		flags |= LM_FLAG_TRY;
+	gfs2_holder_mark_uninitialized(&freeze_gh);
+	error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, flags,
 				   &freeze_gh);
+	if (error == GLR_TRYFAILED)
+		error = 0;
+
 	if (error && !gfs2_withdrawn(sdp))
 		return error;
 
 	flush_workqueue(gfs2_delete_workqueue);
-	if (sdp->sd_quotad_process)
+
+	if (current == sdp->sd_quotad_process)
+		fs_warn(sdp, "The quotad daemon is withdrawing.\n");
+	else if (sdp->sd_quotad_process)
 		kthread_stop(sdp->sd_quotad_process);
 	sdp->sd_quotad_process = NULL;
-	if (sdp->sd_logd_process)
+
+	if (current == sdp->sd_logd_process)
+		fs_warn(sdp, "The logd daemon is withdrawing.\n");
+	else if (sdp->sd_logd_process)
 		kthread_stop(sdp->sd_logd_process);
 	sdp->sd_logd_process = NULL;
 
-	gfs2_quota_sync(sdp->sd_vfs, 0);
-	gfs2_statfs_sync(sdp->sd_vfs, 0);
-
-	gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_SHUTDOWN |
-		       GFS2_LFC_MAKE_FS_RO);
+	if (!withdrawing) {
+		gfs2_quota_sync(sdp->sd_vfs, 0);
+		gfs2_statfs_sync(sdp->sd_vfs, 0);
+		gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_SHUTDOWN |
+			       GFS2_LFC_MAKE_FS_RO);
+	}
 	wait_event(sdp->sd_reserving_log_wait, atomic_read(&sdp->sd_reserving_log) == 0);
-	gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks);
+	if (!withdrawing)
+		gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) ==
+				 sdp->sd_jdesc->jd_blocks);
 
 	if (gfs2_holder_initialized(&freeze_gh))
 		gfs2_glock_dq_uninit(&freeze_gh);
@@ -913,7 +930,7 @@ static void gfs2_put_super(struct super_block *sb)
 	spin_unlock(&sdp->sd_jindex_spin);
 
 	if (!sb_rdonly(sb)) {
-		error = gfs2_make_fs_ro(sdp);
+		error = gfs2_make_fs_ro(sdp, 0);
 		if (error)
 			gfs2_io_error(sdp);
 	}
@@ -930,8 +947,10 @@ static void gfs2_put_super(struct super_block *sb)
 	gfs2_glock_put(sdp->sd_freeze_gl);
 
 	if (!sdp->sd_args.ar_spectator) {
-		gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
-		gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
+		if (gfs2_holder_initialized(&sdp->sd_journal_gh))
+			gfs2_glock_dq_uninit(&sdp->sd_journal_gh);
+		if (gfs2_holder_initialized(&sdp->sd_jinode_gh))
+			gfs2_glock_dq_uninit(&sdp->sd_jinode_gh);
 		gfs2_glock_dq_uninit(&sdp->sd_sc_gh);
 		gfs2_glock_dq_uninit(&sdp->sd_qc_gh);
 		iput(sdp->sd_sc_inode);
@@ -1279,7 +1298,7 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
 
 	if ((sb->s_flags ^ *flags) & SB_RDONLY) {
 		if (*flags & SB_RDONLY)
-			error = gfs2_make_fs_ro(sdp);
+			error = gfs2_make_fs_ro(sdp, 0);
 		else
 			error = gfs2_make_fs_rw(sdp);
 	}
diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h
index 73c97dccae21..e859c6d5bb3e 100644
--- a/fs/gfs2/super.h
+++ b/fs/gfs2/super.h
@@ -45,6 +45,7 @@ extern void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc,
 extern void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh,
 			  struct buffer_head *l_bh);
 extern int gfs2_statfs_sync(struct super_block *sb, int type);
+extern int gfs2_make_fs_ro(struct gfs2_sbd *sdp, int withdrawing);
 extern void gfs2_freeze_func(struct work_struct *work);
 
 extern struct file_system_type gfs2_fs_type;
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index ad56f934ff0f..5e39859d58d8 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -14,11 +14,13 @@
 #include <linux/buffer_head.h>
 #include <linux/crc32.h>
 #include <linux/gfs2_ondisk.h>
+#include <linux/delay.h>
 #include <linux/uaccess.h>
 
 #include "gfs2.h"
 #include "incore.h"
 #include "glock.h"
+#include "log.h"
 #include "lops.h"
 #include "recovery.h"
 #include "rgrp.h"
@@ -81,6 +83,116 @@ int check_journal_clean(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd)
 	return error;
 }
 
+static void signal_our_withdraw(struct gfs2_sbd *sdp)
+{
+	struct gfs2_glock *gl = sdp->sd_live_gh.gh_gl;
+	int ret = 0;
+	int tries;
+
+	if (test_bit(SDF_NORECOVERY, &sdp->sd_flags))
+		return;
+
+	/* Prevent any glock dq until withdraw recovery is complete */
+	set_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags);
+	/**
+	 * Don't tell dlm we're bailing until we have no more buffers in the
+	 * wind. If journal had an IO error, the log code should just purge
+	 * the outstanding buffers rather than submitting new IO. Making the
+	 * file system read-only will flush the journal, etc.
+	 *
+	 * During a normal unmount, gfs2_make_fs_ro calls gfs2_log_shutdown
+	 * which clears SDF_JOURNAL_LIVE. In a withdraw, we must not write
+	 * any UNMOUNT log header, so we can't call gfs2_log_shutdown, and
+	 * therefore we need to clear SDF_JOURNAL_LIVE manually.
+	 */
+	clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
+	if (!sb_rdonly(sdp->sd_vfs)) {
+		ret = gfs2_make_fs_ro(sdp, 1);
+		sdp->sd_vfs->s_flags |= SB_RDONLY;
+	}
+
+	/* Drop the glock for our journal so another node can recover it. */
+	gfs2_glock_dq_wait(&sdp->sd_journal_gh);
+	gfs2_holder_uninit(&sdp->sd_journal_gh);
+	sdp->sd_jinode_gh.gh_flags |= GL_NOCACHE;
+	gfs2_glock_dq_wait(&sdp->sd_jinode_gh);
+	/* holder_uninit to force glock_put, to force dlm to let go */
+	gfs2_holder_uninit(&sdp->sd_jinode_gh);
+	/* Note: We need to be careful here:
+	 * Func gfs2_jindex_free calls iput on jd_inode, which will evict it.
+	 * The evict, in turn, will dequeue its glock, but the glock dq will
+	 * wait for the withdraw unless we have exception code in glock_dq. */
+	gfs2_jindex_free(sdp);
+	/* Flush the glock work so the glock is freed. This allows try locks
+	 * on other nodes to be successful, otherwise we remain the owner of
+	 * the glock until the workqueue gets around to running. */
+	gfs2_gl_flushwork(sdp);
+
+	if (sdp->sd_lockstruct.ls_ops->lm_lock == NULL) { /* lock_nolock */
+		clear_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags);
+		goto skip_recovery;
+	}
+	/**
+	 * Dequeue the "live" glock, but keep a reference so it's never freed.
+	 */
+	gfs2_glock_hold(gl);
+	gfs2_glock_dq_wait(&sdp->sd_live_gh);
+	/**
+	 * We enqueue the "live" glock in EX so that all other nodes
+	 * get a demote request and act on it. We don't really want the
+	 * lock in EX, so we send a "try" lock with 1CB to produce a callback.
+	 */
+	fs_warn(sdp, "Requesting recovery of jid %d.\n",
+		sdp->sd_lockstruct.ls_jid);
+	gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | LM_FLAG_NOEXP,
+			   &sdp->sd_live_gh);
+	msleep(GL_GLOCK_MAX_HOLD);
+	/* This will likely fail in a cluster, but succeed standalone: */
+	ret = gfs2_glock_nq(&sdp->sd_live_gh);
+	/* If we actually got the "live" lock in EX mode, there are no other
+	 * nodes available to replay our journal. So we try to replay it
+	 * ourselves. We hold the "live" glock to prevent other mounters
+	 * during recovery, then just dequeue it and reacquire it in our
+	 * normal SH mode. Just in case the problem that caused us to
+	 * withdraw prevents us from recovering our journal (e.g. io errors
+	 * and such) we still check if the journal is clean before proceeding
+	 * but we may wait forever until another mounter does the recovery. */
+	if (ret == 0) {
+		fs_warn(sdp, "No other mounters found. Trying to recover our "
+			"own journal jid %d.\n", sdp->sd_lockstruct.ls_jid);
+		if (gfs2_recover_journal(sdp->sd_jdesc, 1))
+			fs_warn(sdp, "Unable to recover our journal jid %d.\n",
+				sdp->sd_lockstruct.ls_jid);
+		gfs2_glock_dq_wait(&sdp->sd_live_gh);
+		gfs2_holder_reinit(LM_ST_SHARED, LM_FLAG_NOEXP | GL_EXACT,
+				   &sdp->sd_live_gh);
+		gfs2_glock_nq(&sdp->sd_live_gh);
+	}
+	/* Now drop the additional reference we acquired */
+	gfs2_glock_queue_put(gl);
+	clear_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags);
+
+	/* Now wait until recovery complete. */
+	for (tries = 0; tries < 10; tries++) {
+		ret = check_journal_clean(sdp, sdp->sd_jdesc);
+		if (!ret)
+			break;
+		msleep(HZ);
+		fs_warn(sdp, "Waiting for journal recovery jid %d.\n",
+			sdp->sd_lockstruct.ls_jid);
+	}
+skip_recovery:
+	if (!ret)
+		fs_warn(sdp, "Journal recovery complete for jid %d.\n",
+			sdp->sd_lockstruct.ls_jid);
+	else
+		fs_warn(sdp, "Journal recovery skipped for %d until next "
+			"mount.\n", sdp->sd_lockstruct.ls_jid);
+	fs_warn(sdp, "Glock dequeues delayed: %lu\n", sdp->sd_glock_dqs_held);
+	sdp->sd_glock_dqs_held = 0;
+	wake_up_bit(&sdp->sd_flags, SDF_WITHDRAW_RECOVERY);
+}
+
 int gfs2_lm_withdraw(struct gfs2_sbd *sdp, const char *fmt, ...)
 {
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
@@ -121,6 +233,8 @@ int gfs2_lm_withdraw(struct gfs2_sbd *sdp, const char *fmt, ...)
 		fs_err(sdp, "about to withdraw this file system\n");
 		BUG_ON(sdp->sd_args.ar_debug);
 
+		signal_our_withdraw(sdp);
+
 		kobject_uevent(&sdp->sd_kobj, KOBJ_OFFLINE);
 
 		if (!strcmp(sdp->sd_lockstruct.ls_ops->lm_proto_name, "lock_dlm"))
@@ -131,7 +245,7 @@ int gfs2_lm_withdraw(struct gfs2_sbd *sdp, const char *fmt, ...)
 			lm->lm_unmount(sdp);
 		}
 		set_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags);
-		fs_err(sdp, "withdrawn\n");
+		fs_err(sdp, "File system withdrawn\n");
 		dump_stack();
 		clear_bit(SDF_WITHDRAW_IN_PROG, &sdp->sd_flags);
 		smp_mb__after_atomic();
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 16/19] gfs2: simply gfs2_freeze by removing case

[Bob Peterson]

Function gfs2_freeze had a case statement that simply checked the
error code, but the break statements just made the logic hard to
read. This patch simplifies the logic in favor of a simple if.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/super.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 1582cb11866e..7ffeb4379222 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1043,20 +1043,14 @@ static int gfs2_freeze(struct super_block *sb)
 		if (!error)
 			break;
 
-		switch (error) {
-		case -EBUSY:
+		if (error == -EBUSY)
 			fs_err(sdp, "waiting for recovery before freeze\n");
-			break;
-
-		default:
+		else
 			fs_err(sdp, "error freezing FS: %d\n", error);
-			break;
-		}
 
 		fs_err(sdp, "retrying...\n");
 		msleep(1000);
 	}
-	error = 0;
 out:
 	mutex_unlock(&sdp->sd_freeze_mutex);
 	return error;
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 17/19] gfs2: Add verbose option to check_journal_clean

[Bob Peterson]

Before this patch, function check_journal_clean would give messages
related to journal recovery. That's fine for mount time, but when a
node withdraws and forces replay that way, we don't want all those
distracting and misleading messages. This patch adds a new parameter
to make those messages optional.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/ops_fstype.c |  2 +-
 fs/gfs2/util.c       | 23 ++++++++++++++++-------
 fs/gfs2/util.h       |  4 +++-
 3 files changed, 20 insertions(+), 9 deletions(-)

diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index c4222c1fa735..d8bca92f34a1 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -690,7 +690,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 			struct gfs2_jdesc *jd = gfs2_jdesc_find(sdp, x);
 
 			if (sdp->sd_args.ar_spectator) {
-				error = check_journal_clean(sdp, jd);
+				error = check_journal_clean(sdp, jd, true);
 				if (error)
 					goto fail_jinode_gh;
 				continue;
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 5e39859d58d8..2dd3fb8975a7 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -48,7 +48,8 @@ void gfs2_assert_i(struct gfs2_sbd *sdp)
  *
  * Returns: 0 if the journal is clean or locked, else an error
  */
-int check_journal_clean(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd)
+int check_journal_clean(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
+			bool verbose)
 {
 	int error;
 	struct gfs2_holder j_gh;
@@ -59,23 +60,31 @@ int check_journal_clean(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd)
 	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_NOEXP |
 				   GL_EXACT | GL_NOCACHE, &j_gh);
 	if (error) {
-		fs_err(sdp, "Error locking journal for spectator mount.\n");
+		if (verbose)
+			fs_err(sdp, "Error %d locking journal for spectator "
+			       "mount.\n", error);
 		return -EPERM;
 	}
 	error = gfs2_jdesc_check(jd);
 	if (error) {
-		fs_err(sdp, "Error checking journal for spectator mount.\n");
+		if (verbose)
+			fs_err(sdp, "Error checking journal for spectator "
+			       "mount.\n");
 		goto out_unlock;
 	}
 	error = gfs2_find_jhead(jd, &head);
 	if (error) {
-		fs_err(sdp, "Error parsing journal for spectator mount.\n");
+		if (verbose)
+			fs_err(sdp, "Error parsing journal for spectator "
+			       "mount.\n");
 		goto out_unlock;
 	}
 	if (!(head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) {
 		error = -EPERM;
-		fs_err(sdp, "jid=%u: Journal is dirty, so the first mounter "
-		       "must not be a spectator.\n", jd->jd_jid);
+		if (verbose)
+			fs_err(sdp, "jid=%u: Journal is dirty, so the first "
+			       "mounter must not be a spectator.\n",
+			       jd->jd_jid);
 	}
 
 out_unlock:
@@ -174,7 +183,7 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp)
 
 	/* Now wait until recovery complete. */
 	for (tries = 0; tries < 10; tries++) {
-		ret = check_journal_clean(sdp, sdp->sd_jdesc);
+		ret = check_journal_clean(sdp, sdp->sd_jdesc, false);
 		if (!ret)
 			break;
 		msleep(HZ);
diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h
index 49d46865dceb..345b906a6142 100644
--- a/fs/gfs2/util.h
+++ b/fs/gfs2/util.h
@@ -131,7 +131,9 @@ static inline void gfs2_metatype_set(struct buffer_head *bh, u16 type,
 
 int gfs2_io_error_i(struct gfs2_sbd *sdp, const char *function,
 		    char *file, unsigned int line);
-int check_journal_clean(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd);
+
+extern int check_journal_clean(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
+			       bool verbose);
 
 #define gfs2_io_error(sdp) \
 gfs2_io_error_i((sdp), __func__, __FILE__, __LINE__);
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 18/19] gfs2: Check for log write errors before telling dlm to unlock

[Bob Peterson]

Before this patch, function do_xmote just assumed all the writes
submitted to the journal were finished and successful, and it
called the go_unlock function to release the dlm lock. But if
they're not, and a revoke failed to make its way to the journal,
a journal replay on another node will cause corruption if we
let the go_inval function continue and tell dlm to release the
glock to another node. This patch adds a couple checks for errors
in do_xmote after the calls to go_sync and go_inval. If an error
is found, we cannot withdraw yet, because the withdraw itself
uses glocks to make the file system read-only. Instead, we flag
the error. Later, asserts should cause another node to replay
the journal before continuing, thus protecting rgrp and dinode
glocks and maintaining the integrity of the metadata. Note that
we only need to do this for journaled glocks. System glocks
should be able to progress even under withdrawn conditions.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/glock.c | 44 +++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 41 insertions(+), 3 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 3d1b9bdfd0de..f4129305a815 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -570,8 +570,47 @@ __acquires(&gl->gl_lockref.lock)
 	spin_unlock(&gl->gl_lockref.lock);
 	if (glops->go_sync)
 		glops->go_sync(gl);
+	/**
+	 * Check for an error encountered since we called go_sync. If so, we
+	 * can't withdraw from the glock code because the withdraw code itself
+	 * uses glocks (see function signal_our_withdraw) to change the mount
+	 * to read-only. Most importantly, we must not call dlm to unlock the
+	 * glock until the journal is in a known good state (after journal
+	 * replay) otherwise other nodes may use the object (rgrp or dinode)
+	 * and then later, journal replay will corrupt the file system. The
+	 * best we can do now is wait for the logd daemon to see sd_log_error
+	 * and withdraw, and in the meantime, requeue the work for later.
+	 */
+	if ((glops->go_flags & GLOF_JOURNALED) && sdp->sd_log_error) {
+		gfs2_glock_hold(gl);
+		finish_xmote(gl, LM_OUT_ERROR | LM_ST_UNLOCKED);
+		gfs2_glock_queue_work(gl, GL_GLOCK_DFT_HOLD);
+		goto out;
+	}
 	if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags))
 		glops->go_inval(gl, target == LM_ST_DEFERRED ? 0 : DIO_METADATA);
+	/**
+	 * If the go_inval left some items on the ail, that's a problem. We
+	 * need to withdraw, but we can't, as explained above. Warn about the
+	 * error, dump the glock, then fall through and wait for logd to do
+	 * the withdraw for us.
+	 */
+	if (atomic_read(&gl->gl_ail_count) != 0) {
+		if (!cmpxchg(&sdp->sd_log_error, 0, -EIO)) {
+			gfs2_assert_warn(sdp, !atomic_read(&gl->gl_ail_count));
+			gfs2_dump_glock(NULL, gl);
+		}
+	}
+	/**
+	 * Check for an error encountered while we were doing go_inval, and
+	 * handle it the same way we did for the go_sync case.
+	 */
+	if ((glops->go_flags & GLOF_JOURNALED) && sdp->sd_log_error) {
+		gfs2_glock_hold(gl);
+		finish_xmote(gl, LM_OUT_ERROR | LM_ST_UNLOCKED);
+		gfs2_glock_queue_work(gl, GL_GLOCK_DFT_HOLD);
+		goto out;
+	}
 	clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
 
 	gfs2_glock_hold(gl);
@@ -583,8 +622,7 @@ __acquires(&gl->gl_lockref.lock)
 		    test_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags)) {
 			finish_xmote(gl, target);
 			gfs2_glock_queue_work(gl, 0);
-		}
-		else if (ret) {
+		} else if (ret) {
 			fs_err(sdp, "lm_lock ret %d\n", ret);
 			GLOCK_BUG_ON(gl, !gfs2_withdrawn(sdp));
 		}
@@ -592,7 +630,7 @@ __acquires(&gl->gl_lockref.lock)
 		finish_xmote(gl, target);
 		gfs2_glock_queue_work(gl, 0);
 	}
-
+out:
 	spin_lock(&gl->gl_lockref.lock);
 }
 
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 19/19] gfs2: Do log_flush in gfs2_ail_empty_gl even if ail list is empty

[Bob Peterson]

Before this patch, if gfs2_ail_empty_gl saw there was nothing on
the ail list, it would return and not flush the log. The problem
is that there could still be a revoke for the rgrp sitting on the
sd_log_le_revoke list that's been recently taken off the ail list.
But that revoke still needs to be written, and the rgrp_go_inval
still needs to call log_flush_wait to ensure the revokes are all
properly written to the journal before we relinquish control of
the glock to another node. If we give the glock to another node
before we have this knowledge, the node might crash and its journal
replayed, in which case the missing revoke would allow the journal
replay to replay the rgrp over top of the rgrp we already gave to
another node, thus overwriting its changes and corrupting the
file system.

This patch makes gfs2_ail_empty_gl still call gfs2_log_flush rather
than returning.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/glops.c | 26 +++++++++++++++++++++++++-
 fs/gfs2/log.c   |  2 +-
 fs/gfs2/log.h   |  1 +
 3 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index ff50013c6aa9..1cd2a3c69d63 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -93,8 +93,31 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 	INIT_LIST_HEAD(&tr.tr_databuf);
 	tr.tr_revokes = atomic_read(&gl->gl_ail_count);
 
-	if (!tr.tr_revokes)
+	if (!tr.tr_revokes) {
+		/**
+		 * We have nothing on the ail, but there could be revokes on
+		 * the sdp revoke queue, in which case, we still want to flush
+		 * the log and wait for it to finish.
+		 *
+		 * If the sdp revoke list is empty too, we might still have an
+		 * io outstanding for writing revokes, so we should wait for
+		 * it before returning.
+		 *
+		 * If none of these conditions are true, our revokes are all
+		 * flushed and we can return.
+		 */
+		gfs2_log_lock(sdp);
+		if (test_bit(GLF_REVOKES, &gl->gl_flags)) {
+			gfs2_log_unlock(sdp);
+			goto flush;
+		} else if (atomic_read(&sdp->sd_log_in_flight)) {
+			gfs2_log_unlock(sdp);
+			log_flush_wait(sdp);
+		} else {
+			gfs2_log_unlock(sdp);
+		}
 		return;
+	}
 
 	/* A shortened, inline version of gfs2_trans_begin()
          * tr->alloced is not set since the transaction structure is
@@ -109,6 +132,7 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 	__gfs2_ail_flush(gl, 0, tr.tr_revokes);
 
 	gfs2_trans_end(sdp);
+flush:
 	gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
 		       GFS2_LFC_AIL_EMPTY_GL);
 }
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 732b585f33be..a6c83cdf4e1b 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -522,7 +522,7 @@ static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
 }
 
 
-static void log_flush_wait(struct gfs2_sbd *sdp)
+void log_flush_wait(struct gfs2_sbd *sdp)
 {
 	DEFINE_WAIT(wait);
 
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index 7a34a3234266..cd1581bff293 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -76,6 +76,7 @@ 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);
 extern void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc);
+extern void log_flush_wait(struct gfs2_sbd *sdp);
 
 extern void gfs2_log_shutdown(struct gfs2_sbd *sdp);
 extern int gfs2_logd(void *data);
-- 
2.20.1

[Cluster-devel] [GFS2 PATCH v3 09/19] gfs2: Ignore recovery attempts if gfs2 has io error or is withdrawn

[Steven Whitehouse]

Hi,

On 01/05/2019 00:03, Bob Peterson wrote:
> This patch addresses various problems with gfs2/dlm recovery.
>
> For example, suppose a node with a bunch of gfs2 mounts suddenly
> reboots due to kernel panic, and dlm determines it should perform
> recovery. DLM does so from a pseudo-state machine calling various
> callbacks into lock_dlm to perform a sequence of steps. It uses
> generation numbers and recover bits in dlm "control" lock lvbs.
>
> Now suppose another node tries to recover the failed node's
> journal, but in so doing, encounters an IO error or withdraws
> due to unforeseen circumstances, such as an hba driver failure.
> In these cases, the recovery would eventually bail out, but it
> would still update its generation number in the lvb. The other
> nodes would all see the newer generation number and think they
> don't need to do recovery because the generation number is newer
> than the last one they saw, and therefore someone else has already
> taken care of it.
>
> If the file system has an io error or is withdrawn, it cannot
> safely replay any journals (its own or others) but someone else
> still needs to do it. Therefore we don't want it messing with
> the journal recovery generation numbers: the local generation
> numbers eventually get put into the lvb generation numbers to be
> seen by all nodes.
>
> This patch adds checks to many of the callbacks used by dlm
> in its recovery state machine so that the functions are ignored
> and skipped if an io error has occurred or if the file system
> was withdraw.
>
> Signed-off-by: Bob Peterson <rpeterso@redhat.com>

These should probably propagate the error back to the caller of the 
recovery request. We do have a proper notification system for failed 
recovery via uevents,

Steve.

> ---
>   fs/gfs2/lock_dlm.c | 18 ++++++++++++++++++
>   fs/gfs2/util.c     | 15 +++++++--------
>   2 files changed, 25 insertions(+), 8 deletions(-)
>
> diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
> index 31df26ed7854..9329f86ffcbe 100644
> --- a/fs/gfs2/lock_dlm.c
> +++ b/fs/gfs2/lock_dlm.c
> @@ -1081,6 +1081,10 @@ static void gdlm_recover_prep(void *arg)
>   	struct gfs2_sbd *sdp = arg;
>   	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
>   
> +	if (gfs2_withdrawn(sdp)) {
> +		fs_err(sdp, "recover_prep ignored due to withdraw.\n");
> +		return;
> +	}
>   	spin_lock(&ls->ls_recover_spin);
>   	ls->ls_recover_block = ls->ls_recover_start;
>   	set_bit(DFL_DLM_RECOVERY, &ls->ls_recover_flags);
> @@ -1103,6 +1107,11 @@ static void gdlm_recover_slot(void *arg, struct dlm_slot *slot)
>   	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
>   	int jid = slot->slot - 1;
>   
> +	if (gfs2_withdrawn(sdp)) {
> +		fs_err(sdp, "recover_slot jid %d ignored due to withdraw.\n",
> +		       jid);
> +		return;
> +	}
>   	spin_lock(&ls->ls_recover_spin);
>   	if (ls->ls_recover_size < jid + 1) {
>   		fs_err(sdp, "recover_slot jid %d gen %u short size %d\n",
> @@ -1127,6 +1136,10 @@ static void gdlm_recover_done(void *arg, struct dlm_slot *slots, int num_slots,
>   	struct gfs2_sbd *sdp = arg;
>   	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
>   
> +	if (gfs2_withdrawn(sdp)) {
> +		fs_err(sdp, "recover_done ignored due to withdraw.\n");
> +		return;
> +	}
>   	/* ensure the ls jid arrays are large enough */
>   	set_recover_size(sdp, slots, num_slots);
>   
> @@ -1154,6 +1167,11 @@ static void gdlm_recovery_result(struct gfs2_sbd *sdp, unsigned int jid,
>   {
>   	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
>   
> +	if (gfs2_withdrawn(sdp)) {
> +		fs_err(sdp, "recovery_result jid %d ignored due to withdraw.\n",
> +		       jid);
> +		return;
> +	}
>   	if (test_bit(DFL_NO_DLM_OPS, &ls->ls_recover_flags))
>   		return;
>   
> diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
> index 0a814ccac41d..7eaea6dfe1cf 100644
> --- a/fs/gfs2/util.c
> +++ b/fs/gfs2/util.c
> @@ -259,14 +259,13 @@ void gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
>   			const char *function, char *file, unsigned int line,
>   			bool withdraw)
>   {
> -	if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
> -		fs_err(sdp,
> -		       "fatal: I/O error\n"
> -		       "  block = %llu\n"
> -		       "  function = %s, file = %s, line = %u\n",
> -		       (unsigned long long)bh->b_blocknr,
> -		       function, file, line);
> +	if (gfs2_withdrawn(sdp))
> +		return;
> +
> +	fs_err(sdp, "fatal: I/O error\n"
> +	       "  block = %llu\n"
> +	       "  function = %s, file = %s, line = %u\n",
> +	       (unsigned long long)bh->b_blocknr, function, file, line);
>   	if (withdraw)
>   		gfs2_lm_withdraw(sdp, NULL);
>   }
> -

[Cluster-devel] [GFS2 PATCH v3 00/19] gfs2: misc recovery patch collection

[Steven Whitehouse]

Hi,

On 01/05/2019 00:03, Bob Peterson wrote:
> Here is version 3 of the patch set I posted on 23 April. It is revised
> based on bugs I found testing with xfstests.
>
> This is a collection of patches I've been using to address the myriad
> of recovery problems I've found. I'm still finding them, so the battle
> is not won yet. I'm not convinced we need all of these but I thought
> I'd send them anyway and get feedback. Previously I sent out a version
> of the patch "gfs2: Force withdraw to replay journals and wait for it
> to finish" that was too big and complex. So I broke it up into four
> patches, starting with "move check_journal_clean to util.c for future
> use". So those four need to be a set. There aren't many other dependencies
> between patches, so the others could probably be taken or rejected
> individually. There are more patches I still need to perfect, but maybe
> a few of the safer ones can be pushed to for-next.

There is quite a lot of good stuff here, but it would be good to split 
it up and make it clearer what is bug fixes, and what are new features,

Steve.


> Bob Peterson (19):
>    gfs2: kthread and remount improvements
>    gfs2: eliminate tr_num_revoke_rm
>    gfs2: log which portion of the journal is replayed
>    gfs2: Warn when a journal replay overwrites a rgrp with buffers
>    gfs2: Introduce concept of a pending withdraw
>    gfs2: log error reform
>    gfs2: Only complain the first time an io error occurs in quota or log
>    gfs2: Stop ail1 wait loop when withdrawn
>    gfs2: Ignore recovery attempts if gfs2 has io error or is withdrawn
>    gfs2: move check_journal_clean to util.c for future use
>    gfs2: Allow some glocks to be used during withdraw
>    gfs2: Don't loop forever in gfs2_freeze if withdrawn
>    gfs2: Make secondary withdrawers wait for first withdrawer
>    gfs2: Don't write log headers after file system withdraw
>    gfs2: Force withdraw to replay journals and wait for it to finish
>    gfs2: simply gfs2_freeze by removing case
>    gfs2: Add verbose option to check_journal_clean
>    gfs2: Check for log write errors before telling dlm to unlock
>    gfs2: Do log_flush in gfs2_ail_empty_gl even if ail list is empty
>
>   fs/gfs2/aops.c       |   4 +-
>   fs/gfs2/file.c       |   2 +-
>   fs/gfs2/glock.c      |  82 +++++++++++++++--
>   fs/gfs2/glock.h      |   1 +
>   fs/gfs2/glops.c      | 100 +++++++++++++++++++--
>   fs/gfs2/glops.h      |   3 +-
>   fs/gfs2/incore.h     |  21 ++++-
>   fs/gfs2/inode.c      |  14 ++-
>   fs/gfs2/lock_dlm.c   |  50 +++++++++++
>   fs/gfs2/log.c        |  55 +++++++-----
>   fs/gfs2/log.h        |   1 +
>   fs/gfs2/lops.c       |  27 +++++-
>   fs/gfs2/meta_io.c    |   6 +-
>   fs/gfs2/ops_fstype.c |  65 ++++----------
>   fs/gfs2/quota.c      |  10 ++-
>   fs/gfs2/recovery.c   |   3 +-
>   fs/gfs2/super.c      |  88 +++++++++++-------
>   fs/gfs2/super.h      |   1 +
>   fs/gfs2/sys.c        |  14 ++-
>   fs/gfs2/trans.c      |   6 +-
>   fs/gfs2/util.c       | 206 ++++++++++++++++++++++++++++++++++++++++---
>   fs/gfs2/util.h       |  15 ++++
>   22 files changed, 617 insertions(+), 157 deletions(-)
>

[Cluster-devel] [GFS2 PATCH v3 04/19] gfs2: Warn when a journal replay overwrites a rgrp with buffers

[Andreas Gruenbacher]

Bob,

On Wed, 1 May 2019 at 01:03, Bob Peterson <rpeterso@redhat.com> wrote:
> This patch adds some instrumentation in gfs2's journal replay that
> indicates when we're about to overwrite a rgrp for which we already
> have a valid buffer_head.

looks okay, but can you explain in the commit message when this
problem will trigger and why that's a problem?

Thanks,
Andreas

> Signed-off-by: Bob Peterson <rpeterso@redhat.com>
> ---
>  fs/gfs2/lops.c | 22 ++++++++++++++++++++--
>  1 file changed, 20 insertions(+), 2 deletions(-)
>
> diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
> index 6af6a3cea967..2e8c6d02e112 100644
> --- a/fs/gfs2/lops.c
> +++ b/fs/gfs2/lops.c
> @@ -564,9 +564,27 @@ static int buf_lo_scan_elements(struct gfs2_jdesc *jd, u32 start,
>
>                 if (gfs2_meta_check(sdp, bh_ip))
>                         error = -EIO;
> -               else
> +               else {
> +                       struct gfs2_meta_header *mh =
> +                               (struct gfs2_meta_header *)bh_ip->b_data;
> +
> +                       if (mh->mh_type == cpu_to_be32(GFS2_METATYPE_RG)) {
> +                               struct gfs2_rgrpd *rgd;
> +
> +                               rgd = gfs2_blk2rgrpd(sdp, blkno, false);
> +                               if (rgd && rgd->rd_addr == blkno &&
> +                                   rgd->rd_bits && rgd->rd_bits->bi_bh) {
> +                                       fs_info(sdp, "Replaying 0x%llx but we "
> +                                               "already have a bh!\n",
> +                                               (unsigned long long)blkno);
> +                                       fs_info(sdp, "busy:%d, pinned:%d\n",
> +                                               buffer_busy(rgd->rd_bits->bi_bh) ? 1 : 0,
> +                                               buffer_pinned(rgd->rd_bits->bi_bh));
> +                                       gfs2_dump_glock(NULL, rgd->rd_gl);
> +                               }
> +                       }
>                         mark_buffer_dirty(bh_ip);
> -
> +               }
>                 brelse(bh_log);
>                 brelse(bh_ip);
>
> --
> 2.20.1
>

[Cluster-devel] [GFS2 PATCH v3 05/19] gfs2: Introduce concept of a pending withdraw

[Andreas Gruenbacher]

Bob,

On Wed, 1 May 2019 at 01:03, Bob Peterson <rpeterso@redhat.com> wrote:
> File system withdraws can be delayed when inconsistencies are
> discovered when we cannot withdraw immediately, for example, when
> critical spin_locks are held. But delaying the withdraw can cause
> gfs2 to ignore the error and keep running for a short period of time.
> For example, an rgrp glock may be dequeued and demoted while there
> are still buffers that haven't been properly revoked, due to io
> errors writing to the journal.
>
> This patch introduces a new concept of a pending withdraw, which
> means an inconsistency has been discovered and we need to withdraw
> at the earliest possible opportunity. In these cases, we aren't
> quite withdrawn yet, but we still need to not dequeue glocks and
> other critical things. If we dequeue the glocks and the withdraw
> results in our journal being replayed, the replay could overwrite
> data that's been modified by a different node that acquired the
> glock in the meantime.

this is looking good. Maybe we can improve our terminology a bit
though: how about SDF_FAULTY instead of SDF_WITHDRAW? Also,
SDF_SHUTDOWN really indicates that a filesystem is being or has been
withdrawn, so maybe that should really be called SDF_WITHDRAW?

Thanks,
Andreas

> Signed-off-by: Bob Peterson <rpeterso@redhat.com>
> ---
>  fs/gfs2/aops.c       |  4 ++--
>  fs/gfs2/file.c       |  2 +-
>  fs/gfs2/glock.c      |  7 +++----
>  fs/gfs2/glops.c      |  2 +-
>  fs/gfs2/incore.h     |  1 +
>  fs/gfs2/log.c        | 20 ++++++++------------
>  fs/gfs2/meta_io.c    |  6 +++---
>  fs/gfs2/ops_fstype.c |  3 +--
>  fs/gfs2/quota.c      |  2 +-
>  fs/gfs2/super.c      |  6 +++---
>  fs/gfs2/sys.c        |  2 +-
>  fs/gfs2/util.h       | 12 ++++++++++++
>  12 files changed, 37 insertions(+), 30 deletions(-)
>
> diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
> index 05dd78f4b2b3..2bacce032a34 100644
> --- a/fs/gfs2/aops.c
> +++ b/fs/gfs2/aops.c
> @@ -521,7 +521,7 @@ static int __gfs2_readpage(void *file, struct page *page)
>                 error = mpage_readpage(page, gfs2_block_map);
>         }
>
> -       if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
> +       if (unlikely(gfs2_withdrawn(sdp)))
>                 return -EIO;
>
>         return error;
> @@ -638,7 +638,7 @@ static int gfs2_readpages(struct file *file, struct address_space *mapping,
>         gfs2_glock_dq(&gh);
>  out_uninit:
>         gfs2_holder_uninit(&gh);
> -       if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
> +       if (unlikely(gfs2_withdrawn(sdp)))
>                 ret = -EIO;
>         return ret;
>  }
> diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
> index 58a768e59712..bba39c73a43c 100644
> --- a/fs/gfs2/file.c
> +++ b/fs/gfs2/file.c
> @@ -1169,7 +1169,7 @@ static int gfs2_lock(struct file *file, int cmd, struct file_lock *fl)
>                 cmd = F_SETLK;
>                 fl->fl_type = F_UNLCK;
>         }
> -       if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
> +       if (unlikely(gfs2_withdrawn(sdp))) {
>                 if (fl->fl_type == F_UNLCK)
>                         locks_lock_file_wait(file, fl);
>                 return -EIO;
> diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
> index 15c605cfcfc8..fe9f9a22426e 100644
> --- a/fs/gfs2/glock.c
> +++ b/fs/gfs2/glock.c
> @@ -547,7 +547,7 @@ __acquires(&gl->gl_lockref.lock)
>         unsigned int lck_flags = (unsigned int)(gh ? gh->gh_flags : 0);
>         int ret;
>
> -       if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) &&
> +       if (unlikely(gfs2_withdrawn(sdp)) &&
>             target != LM_ST_UNLOCKED)
>                 return;
>         lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
> @@ -584,8 +584,7 @@ __acquires(&gl->gl_lockref.lock)
>                 }
>                 else if (ret) {
>                         fs_err(sdp, "lm_lock ret %d\n", ret);
> -                       GLOCK_BUG_ON(gl, !test_bit(SDF_SHUTDOWN,
> -                                                  &sdp->sd_flags));
> +                       GLOCK_BUG_ON(gl, !gfs2_withdrawn(sdp));
>                 }
>         } else { /* lock_nolock */
>                 finish_xmote(gl, target);
> @@ -1097,7 +1096,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh)
>         struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
>         int error = 0;
>
> -       if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
> +       if (unlikely(gfs2_withdrawn(sdp)))
>                 return -EIO;
>
>         if (test_bit(GLF_LRU, &gl->gl_flags))
> diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
> index 78510ab91835..b9f36a85a4d4 100644
> --- a/fs/gfs2/glops.c
> +++ b/fs/gfs2/glops.c
> @@ -538,7 +538,7 @@ static int freeze_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
>                         gfs2_consist(sdp);
>
>                 /*  Initialize some head of the log stuff  */
> -               if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) {
> +               if (!gfs2_withdrawn(sdp)) {
>                         sdp->sd_log_sequence = head.lh_sequence + 1;
>                         gfs2_log_pointers_init(sdp, head.lh_blkno);
>                 }
> diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
> index c54800385298..003d9da937b4 100644
> --- a/fs/gfs2/incore.h
> +++ b/fs/gfs2/incore.h
> @@ -620,6 +620,7 @@ enum {
>         SDF_SKIP_DLM_UNLOCK     = 8,
>         SDF_FORCE_AIL_FLUSH     = 9,
>         SDF_AIL1_IO_ERROR       = 10,
> +       SDF_WITHDRAW            = 11, /* Will withdraw eventually */
>  };
>
>  enum gfs2_freeze_state {
> diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
> index 76da6f046379..944aaf3d1816 100644
> --- a/fs/gfs2/log.c
> +++ b/fs/gfs2/log.c
> @@ -92,8 +92,7 @@ static void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
>
>  static int gfs2_ail1_start_one(struct gfs2_sbd *sdp,
>                                struct writeback_control *wbc,
> -                              struct gfs2_trans *tr,
> -                              bool *withdraw)
> +                              struct gfs2_trans *tr)
>  __releases(&sdp->sd_ail_lock)
>  __acquires(&sdp->sd_ail_lock)
>  {
> @@ -112,7 +111,7 @@ __acquires(&sdp->sd_ail_lock)
>                             !test_and_set_bit(SDF_AIL1_IO_ERROR,
>                                               &sdp->sd_flags)) {
>                                 gfs2_io_error_bh(sdp, bh);
> -                               *withdraw = true;
> +                               set_bit(SDF_WITHDRAW, &sdp->sd_flags);
>                         }
>                         list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
>                         continue;
> @@ -153,7 +152,6 @@ void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc)
>         struct list_head *head = &sdp->sd_ail1_list;
>         struct gfs2_trans *tr;
>         struct blk_plug plug;
> -       bool withdraw = false;
>
>         trace_gfs2_ail_flush(sdp, wbc, 1);
>         blk_start_plug(&plug);
> @@ -162,12 +160,12 @@ void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc)
>         list_for_each_entry_reverse(tr, head, tr_list) {
>                 if (wbc->nr_to_write <= 0)
>                         break;
> -               if (gfs2_ail1_start_one(sdp, wbc, tr, &withdraw))
> +               if (gfs2_ail1_start_one(sdp, wbc, tr))
>                         goto restart;
>         }
>         spin_unlock(&sdp->sd_ail_lock);
>         blk_finish_plug(&plug);
> -       if (withdraw)
> +       if (test_bit(SDF_WITHDRAW, &sdp->sd_flags))
>                 gfs2_lm_withdraw(sdp, NULL);
>         trace_gfs2_ail_flush(sdp, wbc, 0);
>  }
> @@ -196,8 +194,7 @@ static void gfs2_ail1_start(struct gfs2_sbd *sdp)
>   *
>   */
>
> -static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
> -                               bool *withdraw)
> +static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
>  {
>         struct gfs2_bufdata *bd, *s;
>         struct buffer_head *bh;
> @@ -211,7 +208,7 @@ static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
>                 if (!buffer_uptodate(bh) &&
>                     !test_and_set_bit(SDF_AIL1_IO_ERROR, &sdp->sd_flags)) {
>                         gfs2_io_error_bh(sdp, bh);
> -                       *withdraw = true;
> +                       set_bit(SDF_WITHDRAW, &sdp->sd_flags);
>                 }
>                 list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
>         }
> @@ -229,11 +226,10 @@ static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
>         struct gfs2_trans *tr, *s;
>         int oldest_tr = 1;
>         int ret;
> -       bool withdraw = false;
>
>         spin_lock(&sdp->sd_ail_lock);
>         list_for_each_entry_safe_reverse(tr, s, &sdp->sd_ail1_list, tr_list) {
> -               gfs2_ail1_empty_one(sdp, tr, &withdraw);
> +               gfs2_ail1_empty_one(sdp, tr);
>                 if (list_empty(&tr->tr_ail1_list) && oldest_tr)
>                         list_move(&tr->tr_list, &sdp->sd_ail2_list);
>                 else
> @@ -242,7 +238,7 @@ static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
>         ret = list_empty(&sdp->sd_ail1_list);
>         spin_unlock(&sdp->sd_ail_lock);
>
> -       if (withdraw)
> +       if (test_bit(SDF_WITHDRAW, &sdp->sd_flags))
>                 gfs2_lm_withdraw(sdp, "fatal: I/O error(s)\n");
>
>         return ret;
> diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
> index 3201342404a7..b125008f064f 100644
> --- a/fs/gfs2/meta_io.c
> +++ b/fs/gfs2/meta_io.c
> @@ -255,7 +255,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
>         struct buffer_head *bh, *bhs[2];
>         int num = 0;
>
> -       if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
> +       if (unlikely(gfs2_withdrawn(sdp))) {
>                 *bhp = NULL;
>                 return -EIO;
>         }
> @@ -313,7 +313,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
>
>  int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
>  {
> -       if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
> +       if (unlikely(gfs2_withdrawn(sdp)))
>                 return -EIO;
>
>         wait_on_buffer(bh);
> @@ -324,7 +324,7 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
>                         gfs2_io_error_bh_wd(sdp, bh);
>                 return -EIO;
>         }
> -       if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
> +       if (unlikely(gfs2_withdrawn(sdp)))
>                 return -EIO;
>
>         return 0;
> diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
> index abfaecde0e3d..075f64075ff6 100644
> --- a/fs/gfs2/ops_fstype.c
> +++ b/fs/gfs2/ops_fstype.c
> @@ -998,8 +998,7 @@ static int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent)
>  void gfs2_lm_unmount(struct gfs2_sbd *sdp)
>  {
>         const struct lm_lockops *lm = sdp->sd_lockstruct.ls_ops;
> -       if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) &&
> -           lm->lm_unmount)
> +       if (likely(!gfs2_withdrawn(sdp)) && lm->lm_unmount)
>                 lm->lm_unmount(sdp);
>  }
>
> diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
> index 2ae5a109eea7..a8dfc86fd682 100644
> --- a/fs/gfs2/quota.c
> +++ b/fs/gfs2/quota.c
> @@ -1478,7 +1478,7 @@ static void quotad_error(struct gfs2_sbd *sdp, const char *msg, int error)
>  {
>         if (error == 0 || error == -EROFS)
>                 return;
> -       if (!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) {
> +       if (!gfs2_withdrawn(sdp)) {
>                 fs_err(sdp, "gfs2_quotad: %s error %d\n", msg, error);
>                 sdp->sd_log_error = error;
>                 wake_up(&sdp->sd_logd_waitq);
> diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
> index dc4ec1ca3d4e..378519beb6c3 100644
> --- a/fs/gfs2/super.c
> +++ b/fs/gfs2/super.c
> @@ -807,7 +807,7 @@ static void gfs2_dirty_inode(struct inode *inode, int flags)
>
>         if (!(flags & I_DIRTY_INODE))
>                 return;
> -       if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
> +       if (unlikely(gfs2_withdrawn(sdp)))
>                 return;
>         if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
>                 ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
> @@ -856,7 +856,7 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
>
>         error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, GL_NOCACHE,
>                                    &freeze_gh);
> -       if (error && !test_bit(SDF_SHUTDOWN, &sdp->sd_flags))
> +       if (error && !gfs2_withdrawn(sdp))
>                 return error;
>
>         flush_workqueue(gfs2_delete_workqueue);
> @@ -1014,7 +1014,7 @@ static int gfs2_freeze(struct super_block *sb)
>         if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN)
>                 goto out;
>
> -       if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) {
> +       if (gfs2_withdrawn(sdp)) {
>                 error = -EINVAL;
>                 goto out;
>         }
> diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
> index 1787d295834e..b772ff5509bb 100644
> --- a/fs/gfs2/sys.c
> +++ b/fs/gfs2/sys.c
> @@ -121,7 +121,7 @@ static ssize_t freeze_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
>
>  static ssize_t withdraw_show(struct gfs2_sbd *sdp, char *buf)
>  {
> -       unsigned int b = test_bit(SDF_SHUTDOWN, &sdp->sd_flags);
> +       unsigned int b = gfs2_withdrawn(sdp);
>         return snprintf(buf, PAGE_SIZE, "%u\n", b);
>  }
>
> diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h
> index 9278fecba632..0df65555545f 100644
> --- a/fs/gfs2/util.h
> +++ b/fs/gfs2/util.h
> @@ -167,6 +167,18 @@ static inline unsigned int gfs2_tune_get_i(struct gfs2_tune *gt,
>         return x;
>  }
>
> +/**
> + * gfs2_withdrawn - test whether the file system is withdrawing or withdrawn
> + * @sdp: the superblock
> + */
> +static inline bool gfs2_withdrawn(struct gfs2_sbd *sdp)
> +{
> +       if (test_bit(SDF_SHUTDOWN, &sdp->sd_flags) ||
> +           test_bit(SDF_WITHDRAW, &sdp->sd_flags))
> +               return true;
> +       return false;
> +}
> +
>  #define gfs2_tune_get(sdp, field) \
>  gfs2_tune_get_i(&(sdp)->sd_tune, &(sdp)->sd_tune.field)
>
> --
> 2.20.1
>