Merge tag 'gfs2-for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2

Pull gfs2 updates from Bob Peterson:
 "We've got a lot of patches (39) for this merge window. Most of these
  patches are related to corruption that occurs when journals are
  replayed. For example:

   1. A node fails while writing to the file system.
   2. Other nodes use the metadata that was once used by the failed
      node.
   3. When the node returns to the cluster, its journal is replayed, but
      the older metadata blocks overwrite the changes from step 2.

  Summary:

   - Fixed the recovery sequence to prevent corruption during journal
     replay.

   - Many bug fixes found during recovery testing.

   - New improved file system withdraw sequence.

   - Fixed how resource group buffers are managed.

   - Fixed how metadata revokes are tracked and written.

   - Improve processing of IO errors hit by daemons like logd and
     quotad.

   - Improved error checking in metadata writes.

   - Fixed how qadata quota data structures are managed"

* tag 'gfs2-for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2: (39 commits)
  gfs2: Fix oversight in gfs2_ail1_flush
  gfs2: change from write to read lock for sd_log_flush_lock in journal replay
  gfs2: instrumentation wrt ail1 stuck
  gfs2: don't lock sd_log_flush_lock in try_rgrp_unlink
  gfs2: Remove unnecessary gfs2_qa_{get,put} pairs
  gfs2: Split gfs2_rsqa_delete into gfs2_rs_delete and gfs2_qa_put
  gfs2: Change inode qa_data to allow multiple users
  gfs2: eliminate gfs2_rsqa_alloc in favor of gfs2_qa_alloc
  gfs2: Switch to list_{first,last}_entry
  gfs2: Clean up inode initialization and teardown
  gfs2: Additional information when gfs2_ail1_flush withdraws
  gfs2: leaf_dealloc needs to allocate one more revoke
  gfs2: allow journal replay to hold sd_log_flush_lock
  gfs2: don't allow releasepage to free bd still used for revokes
  gfs2: flesh out delayed withdraw for gfs2_log_flush
  gfs2: Do proper error checking for go_sync family of glops functions
  gfs2: Don't demote a glock until its revokes are written
  gfs2: drain the ail2 list after io errors
  gfs2: Withdraw in gfs2_ail1_flush if write_cache_pages fails
  gfs2: Do log_flush in gfs2_ail_empty_gl even if ail list is empty
  ...

1 files changed, 19 insertions, 8 deletions

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 9fd88ed18807..84a824293a78 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -234,20 +234,21 @@ struct lm_lockname {
 
 
 struct gfs2_glock_operations {
-	void (*go_sync) (struct gfs2_glock *gl);
+	int (*go_sync) (struct gfs2_glock *gl);
 	int (*go_xmote_bh) (struct gfs2_glock *gl, struct gfs2_holder *gh);
 	void (*go_inval) (struct gfs2_glock *gl, int flags);
 	int (*go_demote_ok) (const struct gfs2_glock *gl);
 	int (*go_lock) (struct gfs2_holder *gh);
-	void (*go_unlock) (struct gfs2_holder *gh);
 	void (*go_dump)(struct seq_file *seq, struct gfs2_glock *gl,
 			const char *fs_id_buf);
 	void (*go_callback)(struct gfs2_glock *gl, bool remote);
+	void (*go_free)(struct gfs2_glock *gl);
 	const int go_type;
 	const unsigned long go_flags;
-#define GLOF_ASPACE 1
-#define GLOF_LVB    2
-#define GLOF_LRU    4
+#define GLOF_ASPACE 1 /* address space attached */
+#define GLOF_LVB    2 /* Lock Value Block attached */
+#define GLOF_LRU    4 /* LRU managed */
+#define GLOF_NONDISK   8 /* not I/O related */
 };
 
 enum {
@@ -294,6 +295,7 @@ struct gfs2_qadata { /* quota allocation data */
 	struct gfs2_quota_data *qa_qd[2 * GFS2_MAXQUOTAS];
 	struct gfs2_holder qa_qd_ghs[2 * GFS2_MAXQUOTAS];
 	unsigned int qa_qd_num;
+	int qa_ref;
 };
 
 /* Resource group multi-block reservation, in order of appearance:
@@ -343,6 +345,7 @@ enum {
 	GLF_OBJECT			= 14, /* Used only for tracing */
 	GLF_BLOCKING			= 15,
 	GLF_INODE_CREATING		= 16, /* Inode creation occurring */
+	GLF_FREEING			= 18, /* Wait for glock to be freed */
 };
 
 struct gfs2_glock {
@@ -542,6 +545,7 @@ struct gfs2_jdesc {
 	struct list_head jd_revoke_list;
 	unsigned int jd_replay_tail;
 
+	u64 jd_no_addr;
 };
 
 struct gfs2_statfs_change_host {
@@ -616,8 +620,12 @@ enum {
 	SDF_RORECOVERY		= 7, /* read only recovery */
 	SDF_SKIP_DLM_UNLOCK	= 8,
 	SDF_FORCE_AIL_FLUSH     = 9,
-	SDF_AIL1_IO_ERROR	= 10,
-	SDF_FS_FROZEN           = 11,
+	SDF_FS_FROZEN           = 10,
+	SDF_WITHDRAWING		= 11, /* Will withdraw eventually */
+	SDF_WITHDRAW_IN_PROG	= 12, /* Withdraw is in progress */
+	SDF_REMOTE_WITHDRAW	= 13, /* Performing remote recovery */
+	SDF_WITHDRAW_RECOVERY	= 14, /* Wait for journal recovery when we are
+					 withdrawing */
 };
 
 enum gfs2_freeze_state {
@@ -768,6 +776,7 @@ 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;
@@ -828,7 +837,8 @@ 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 */
+	wait_queue_head_t sd_withdraw_wait;
 
 	atomic_t sd_reserving_log;
 	wait_queue_head_t sd_reserving_log_wait;
@@ -852,6 +862,7 @@ 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)