Merge tag 'xfs-5.7-merge-12' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull more xfs updates from Darrick Wong:
 "As promised last week, this batch changes how xfs interacts with
  memory reclaim; how the log batches and throttles log items; how hard
  writes near ENOSPC will try to squeeze more space out of the
  filesystem; and hopefully fix the last of the umount hangs after a
  catastrophic failure.

  Summary:

   - Validate the realtime geometry in the superblock when mounting

   - Refactor a bunch of tricky flag handling in the log code

   - Flush the CIL more judiciously so that we don't wait until there
     are millions of log items consuming a lot of memory.

   - Throttle transaction commits to prevent the xfs frontend from
     flooding the CIL with too many log items.

   - Account metadata buffers correctly for memory reclaim.

   - Mark slabs properly for memory reclaim. These should help reclaim
     run more effectively when XFS is using a lot of memory.

   - Don't write a garbage log record at unmount time if we're trying to
     trigger summary counter recalculation at next mount.

   - Don't block the AIL on locked dquot/inode buffers; instead trigger
     its backoff mechanism to give the lock holder a chance to finish
     up.

   - Ratelimit writeback flushing when buffered writes encounter ENOSPC.

   - Other minor cleanups.

   - Make reflink a synchronous operation when the fs is mounted with
     wsync or sync, which means that now we force the log to disk to
     record the changes"

* tag 'xfs-5.7-merge-12' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (26 commits)
  xfs: reflink should force the log out if mounted with wsync
  xfs: factor out a new xfs_log_force_inode helper
  xfs: fix inode number overflow in ifree cluster helper
  xfs: remove redundant variable assignment in xfs_symlink()
  xfs: ratelimit inode flush on buffered write ENOSPC
  xfs: return locked status of inode buffer on xfsaild push
  xfs: trylock underlying buffer on dquot flush
  xfs: remove unnecessary ternary from xfs_create
  xfs: don't write a corrupt unmount record to force summary counter recalc
  xfs: factor inode lookup from xfs_ifree_cluster
  xfs: tail updates only need to occur when LSN changes
  xfs: factor common AIL item deletion code
  xfs: correctly acount for reclaimable slabs
  xfs: Improve metadata buffer reclaim accountability
  xfs: don't allow log IO to be throttled
  xfs: Throttle commits on delayed background CIL push
  xfs: Lower CIL flush limit for large logs
  xfs: remove some stale comments from the log code
  xfs: refactor unmount record writing
  xfs: merge xlog_commit_record with xlog_write_done
  ...

21 files changed, 512 insertions, 451 deletions

diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 00266de58954..c526c5e5ab76 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -328,6 +328,38 @@ xfs_validate_sb_common(
 		return -EFSCORRUPTED;
 	}
 
+	/* Validate the realtime geometry; stolen from xfs_repair */
+	if (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE ||
+	    sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) {
+		xfs_notice(mp,
+			"realtime extent sanity check failed");
+		return -EFSCORRUPTED;
+	}
+
+	if (sbp->sb_rblocks == 0) {
+		if (sbp->sb_rextents != 0 || sbp->sb_rbmblocks != 0 ||
+		    sbp->sb_rextslog != 0 || sbp->sb_frextents != 0) {
+			xfs_notice(mp,
+				"realtime zeroed geometry check failed");
+			return -EFSCORRUPTED;
+		}
+	} else {
+		uint64_t	rexts;
+		uint64_t	rbmblocks;
+
+		rexts = div_u64(sbp->sb_rblocks, sbp->sb_rextsize);
+		rbmblocks = howmany_64(sbp->sb_rextents,
+				       NBBY * sbp->sb_blocksize);
+
+		if (sbp->sb_rextents != rexts ||
+		    sbp->sb_rextslog != xfs_highbit32(sbp->sb_rextents) ||
+		    sbp->sb_rbmblocks != rbmblocks) {
+			xfs_notice(mp,
+				"realtime geometry sanity check failed");
+			return -EFSCORRUPTED;
+		}
+	}
+
 	if (sbp->sb_unit) {
 		if (!xfs_sb_version_hasdalign(sbp) ||
 		    sbp->sb_unit > sbp->sb_width ||
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index f880141a2268..9ec3eaf1c618 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -327,6 +327,9 @@ xfs_buf_free(
 
 			__free_page(page);
 		}
+		if (current->reclaim_state)
+			current->reclaim_state->reclaimed_slab +=
+							bp->b_page_count;
 	} else if (bp->b_flags & _XBF_KMEM)
 		kmem_free(bp->b_addr);
 	_xfs_buf_free_pages(bp);
@@ -2114,9 +2117,11 @@ xfs_buf_delwri_pushbuf(
 int __init
 xfs_buf_init(void)
 {
-	xfs_buf_zone = kmem_cache_create("xfs_buf",
-					 sizeof(struct xfs_buf), 0,
-					 SLAB_HWCACHE_ALIGN, NULL);
+	xfs_buf_zone = kmem_cache_create("xfs_buf", sizeof(struct xfs_buf), 0,
+					 SLAB_HWCACHE_ALIGN |
+					 SLAB_RECLAIM_ACCOUNT |
+					 SLAB_MEM_SPREAD,
+					 NULL);
 	if (!xfs_buf_zone)
 		goto out;
 
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 711376ca269f..af2c8e5ceea0 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -1105,8 +1105,8 @@ xfs_qm_dqflush(
 	 * Get the buffer containing the on-disk dquot
 	 */
 	error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno,
-				   mp->m_quotainfo->qi_dqchunklen, 0, &bp,
-				   &xfs_dquot_buf_ops);
+				   mp->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK,
+				   &bp, &xfs_dquot_buf_ops);
 	if (error)
 		goto out_unlock;
 
@@ -1177,7 +1177,7 @@ xfs_qm_dqflush(
 
 out_unlock:
 	xfs_dqfunlock(dqp);
-	return -EIO;
+	return error;
 }
 
 /*
diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c
index cf65e2e43c6e..baad1748d0d1 100644
--- a/fs/xfs/xfs_dquot_item.c
+++ b/fs/xfs/xfs_dquot_item.c
@@ -189,7 +189,8 @@ xfs_qm_dquot_logitem_push(
 		if (!xfs_buf_delwri_queue(bp, buffer_list))
 			rval = XFS_ITEM_FLUSHING;
 		xfs_buf_relse(bp);
-	}
+	} else if (error == -EAGAIN)
+		rval = XFS_ITEM_LOCKED;
 
 	spin_lock(&lip->li_ailp->ail_lock);
 out_unlock:
diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index f1372f9046e3..5a4b0119143a 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -15,7 +15,6 @@
 #include "xfs_trans.h"
 #include "xfs_inode_item.h"
 #include "xfs_icache.h"
-#include "xfs_log.h"
 #include "xfs_pnfs.h"
 
 /*
@@ -221,18 +220,7 @@ STATIC int
 xfs_fs_nfs_commit_metadata(
 	struct inode		*inode)
 {
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	xfs_lsn_t		lsn = 0;
-
-	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	if (xfs_ipincount(ip))
-		lsn = ip->i_itemp->ili_last_lsn;
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-
-	if (!lsn)
-		return 0;
-	return xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, NULL);
+	return xfs_log_force_inode(XFS_I(inode));
 }
 
 const struct export_operations xfs_export_operations = {
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index b8a4a3f29b36..4b8bdecc3863 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -80,19 +80,9 @@ xfs_dir_fsync(
 	int			datasync)
 {
 	struct xfs_inode	*ip = XFS_I(file->f_mapping->host);
-	struct xfs_mount	*mp = ip->i_mount;
-	xfs_lsn_t		lsn = 0;
 
 	trace_xfs_dir_fsync(ip);
-
-	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	if (xfs_ipincount(ip))
-		lsn = ip->i_itemp->ili_last_lsn;
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-
-	if (!lsn)
-		return 0;
-	return xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, NULL);
+	return xfs_log_force_inode(ip);
 }
 
 STATIC int
@@ -1069,7 +1059,11 @@ xfs_file_remap_range(
 
 	ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize,
 			remap_flags);
+	if (ret)
+		goto out_unlock;
 
+	if (mp->m_flags & XFS_MOUNT_WSYNC)
+		xfs_log_force_inode(dest);
 out_unlock:
 	xfs_reflink_remap_unlock(file_in, file_out);
 	if (ret)
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 14b922f2a6db..d1772786af29 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1200,8 +1200,7 @@ xfs_create(
 	unlock_dp_on_error = false;
 
 	error = xfs_dir_createname(tp, dp, name, ip->i_ino,
-				   resblks ?
-					resblks - XFS_IALLOC_SPACE_RES(mp) : 0);
+					resblks - XFS_IALLOC_SPACE_RES(mp));
 	if (error) {
 		ASSERT(error != -ENOSPC);
 		goto out_trans_cancel;
@@ -2504,6 +2503,88 @@ out:
 }
 
 /*
+ * Look up the inode number specified and mark it stale if it is found. If it is
+ * dirty, return the inode so it can be attached to the cluster buffer so it can
+ * be processed appropriately when the cluster free transaction completes.
+ */
+static struct xfs_inode *
+xfs_ifree_get_one_inode(
+	struct xfs_perag	*pag,
+	struct xfs_inode	*free_ip,
+	xfs_ino_t		inum)
+{
+	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_inode	*ip;
+
+retry:
+	rcu_read_lock();
+	ip = radix_tree_lookup(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, inum));
+
+	/* Inode not in memory, nothing to do */
+	if (!ip)
+		goto out_rcu_unlock;
+
+	/*
+	 * because this is an RCU protected lookup, we could find a recently
+	 * freed or even reallocated inode during the lookup. We need to check
+	 * under the i_flags_lock for a valid inode here. Skip it if it is not
+	 * valid, the wrong inode or stale.
+	 */
+	spin_lock(&ip->i_flags_lock);
+	if (ip->i_ino != inum || __xfs_iflags_test(ip, XFS_ISTALE)) {
+		spin_unlock(&ip->i_flags_lock);
+		goto out_rcu_unlock;
+	}
+	spin_unlock(&ip->i_flags_lock);
+
+	/*
+	 * Don't try to lock/unlock the current inode, but we _cannot_ skip the
+	 * other inodes that we did not find in the list attached to the buffer
+	 * and are not already marked stale. If we can't lock it, back off and
+	 * retry.
+	 */
+	if (ip != free_ip) {
+		if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
+			rcu_read_unlock();
+			delay(1);
+			goto retry;
+		}
+
+		/*
+		 * Check the inode number again in case we're racing with
+		 * freeing in xfs_reclaim_inode().  See the comments in that
+		 * function for more information as to why the initial check is
+		 * not sufficient.
+		 */
+		if (ip->i_ino != inum) {
+			xfs_iunlock(ip, XFS_ILOCK_EXCL);
+			goto out_rcu_unlock;
+		}
+	}
+	rcu_read_unlock();
+
+	xfs_iflock(ip);
+	xfs_iflags_set(ip, XFS_ISTALE);
+
+	/*
+	 * We don't need to attach clean inodes or those only with unlogged
+	 * changes (which we throw away, anyway).
+	 */
+	if (!ip->i_itemp || xfs_inode_clean(ip)) {
+		ASSERT(ip != free_ip);
+		xfs_ifunlock(ip);
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		goto out_no_inode;
+	}
+	return ip;
+
+out_rcu_unlock:
+	rcu_read_unlock();
+out_no_inode:
+	return NULL;
+}
+
+/*
  * A big issue when freeing the inode cluster is that we _cannot_ skip any
  * inodes that are in memory - they all must be marked stale and attached to
  * the cluster buffer.
@@ -2603,77 +2684,11 @@ xfs_ifree_cluster(
 		 * even trying to lock them.
 		 */
 		for (i = 0; i < igeo->inodes_per_cluster; i++) {
-retry:
-			rcu_read_lock();
-			ip = radix_tree_lookup(&pag->pag_ici_root,
-					XFS_INO_TO_AGINO(mp, (inum + i)));
-
-			/* Inode not in memory, nothing to do */
-			if (!ip) {
-				rcu_read_unlock();
+			ip = xfs_ifree_get_one_inode(pag, free_ip, inum + i);
+			if (!ip)
 				continue;
-			}
-
-			/*
-			 * because this is an RCU protected lookup, we could
-			 * find a recently freed or even reallocated inode
-			 * during the lookup. We need to check under the
-			 * i_flags_lock for a valid inode here. Skip it if it
-			 * is not valid, the wrong inode or stale.
-			 */
-			spin_lock(&ip->i_flags_lock);
-			if (ip->i_ino != inum + i ||
-			    __xfs_iflags_test(ip, XFS_ISTALE)) {
-				spin_unlock(&ip->i_flags_lock);
-				rcu_read_unlock();
-				continue;
-			}
-			spin_unlock(&ip->i_flags_lock);
-
-			/*
-			 * Don't try to lock/unlock the current inode, but we
-			 * _cannot_ skip the other inodes that we did not find
-			 * in the list attached to the buffer and are not
-			 * already marked stale. If we can't lock it, back off
-			 * and retry.
-			 */
-			if (ip != free_ip) {
-				if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
-					rcu_read_unlock();
-					delay(1);
-					goto retry;
-				}
-
-				/*
-				 * Check the inode number again in case we're
-				 * racing with freeing in xfs_reclaim_inode().
-				 * See the comments in that function for more
-				 * information as to why the initial check is
-				 * not sufficient.
-				 */
-				if (ip->i_ino != inum + i) {
-					xfs_iunlock(ip, XFS_ILOCK_EXCL);
-					rcu_read_unlock();
-					continue;
-				}
-			}
-			rcu_read_unlock();
-
-			xfs_iflock(ip);
-			xfs_iflags_set(ip, XFS_ISTALE);
 
-			/*
-			 * we don't need to attach clean inodes or those only
-			 * with unlogged changes (which we throw away, anyway).
-			 */
 			iip = ip->i_itemp;
-			if (!iip || xfs_inode_clean(ip)) {
-				ASSERT(ip != free_ip);
-				xfs_ifunlock(ip);
-				xfs_iunlock(ip, XFS_ILOCK_EXCL);
-				continue;
-			}
-
 			iip->ili_last_fields = iip->ili_fields;
 			iip->ili_fields = 0;
 			iip->ili_fsync_fields = 0;
@@ -3930,3 +3945,22 @@ xfs_irele(
 	trace_xfs_irele(ip, _RET_IP_);
 	iput(VFS_I(ip));
 }
+
+/*
+ * Ensure all commited transactions touching the inode are written to the log.
+ */
+int
+xfs_log_force_inode(
+	struct xfs_inode	*ip)
+{
+	xfs_lsn_t		lsn = 0;
+
+	xfs_ilock(ip, XFS_ILOCK_SHARED);
+	if (xfs_ipincount(ip))
+		lsn = ip->i_itemp->ili_last_lsn;
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+
+	if (!lsn)
+		return 0;
+	return xfs_log_force_lsn(ip->i_mount, lsn, XFS_LOG_SYNC, NULL);
+}
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 492e53992fa9..c6a63f6764a6 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -426,6 +426,7 @@ int		xfs_itruncate_extents_flags(struct xfs_trans **,
 				struct xfs_inode *, int, xfs_fsize_t, int);
 void		xfs_iext_realloc(xfs_inode_t *, int, int);
 
+int		xfs_log_force_inode(struct xfs_inode *ip);
 void		xfs_iunpin_wait(xfs_inode_t *);
 #define xfs_ipincount(ip)	((unsigned int) atomic_read(&ip->i_pincount))
 
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 4a3d13d4a022..f779cca2346f 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -552,7 +552,8 @@ xfs_inode_item_push(
 		if (!xfs_buf_delwri_queue(bp, buffer_list))
 			rval = XFS_ITEM_FLUSHING;
 		xfs_buf_relse(bp);
-	}
+	} else if (error == -EAGAIN)
+		rval = XFS_ITEM_LOCKED;
 
 	spin_lock(&lip->li_ailp->ail_lock);
 out_unlock:
@@ -730,29 +731,27 @@ xfs_iflush_done(
 	 * holding the lock before removing the inode from the AIL.
 	 */
 	if (need_ail) {
-		bool			mlip_changed = false;
+		xfs_lsn_t	tail_lsn = 0;
 
 		/* this is an opencoded batch version of xfs_trans_ail_delete */
 		spin_lock(&ailp->ail_lock);
 		list_for_each_entry(blip, &tmp, li_bio_list) {
 			if (INODE_ITEM(blip)->ili_logged &&
-			    blip->li_lsn == INODE_ITEM(blip)->ili_flush_lsn)
-				mlip_changed |= xfs_ail_delete_one(ailp, blip);
-			else {
+			    blip->li_lsn == INODE_ITEM(blip)->ili_flush_lsn) {
+				/*
+				 * xfs_ail_update_finish() only cares about the
+				 * lsn of the first tail item removed, any
+				 * others will be at the same or higher lsn so
+				 * we just ignore them.
+				 */
+				xfs_lsn_t lsn = xfs_ail_delete_one(ailp, blip);
+				if (!tail_lsn && lsn)
+					tail_lsn = lsn;
+			} else {
 				xfs_clear_li_failed(blip);
 			}
 		}
-
-		if (mlip_changed) {
-			if (!XFS_FORCED_SHUTDOWN(ailp->ail_mount))
-				xlog_assign_tail_lsn_locked(ailp->ail_mount);
-			if (list_empty(&ailp->ail_head))
-				wake_up_all(&ailp->ail_empty);
-		}
-		spin_unlock(&ailp->ail_lock);
-
-		if (mlip_changed)
-			xfs_log_space_wake(ailp->ail_mount);
+		xfs_ail_update_finish(ailp, tail_lsn);
 	}
 
 	/*
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 4a53768c5397..00fda2e8e738 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -24,13 +24,6 @@
 kmem_zone_t	*xfs_log_ticket_zone;
 
 /* Local miscellaneous function prototypes */
-STATIC int
-xlog_commit_record(
-	struct xlog		*log,
-	struct xlog_ticket	*ticket,
-	struct xlog_in_core	**iclog,
-	xfs_lsn_t		*commitlsnp);
-
 STATIC struct xlog *
 xlog_alloc_log(
 	struct xfs_mount	*mp,
@@ -66,14 +59,6 @@ xlog_grant_push_ail(
 	struct xlog		*log,
 	int			need_bytes);
 STATIC void
-xlog_regrant_reserve_log_space(
-	struct xlog		*log,
-	struct xlog_ticket	*ticket);
-STATIC void
-xlog_ungrant_log_space(
-	struct xlog		*log,
-	struct xlog_ticket	*ticket);
-STATIC void
 xlog_sync(
 	struct xlog		*log,
 	struct xlog_in_core	*iclog);
@@ -478,73 +463,6 @@ out_error:
 	return error;
 }
 
-
-/*
- * NOTES:
- *
- *	1. currblock field gets updated at startup and after in-core logs
- *		marked as with WANT_SYNC.
- */
-
-/*
- * This routine is called when a user of a log manager ticket is done with
- * the reservation.  If the ticket was ever used, then a commit record for
- * the associated transaction is written out as a log operation header with
- * no data.  The flag XLOG_TIC_INITED is set when the first write occurs with
- * a given ticket.  If the ticket was one with a permanent reservation, then
- * a few operations are done differently.  Permanent reservation tickets by
- * default don't release the reservation.  They just commit the current
- * transaction with the belief that the reservation is still needed.  A flag
- * must be passed in before permanent reservations are actually released.
- * When these type of tickets are not released, they need to be set into
- * the inited state again.  By doing this, a start record will be written
- * out when the next write occurs.
- */
-xfs_lsn_t
-xfs_log_done(
-	struct xfs_mount	*mp,
-	struct xlog_ticket	*ticket,
-	struct xlog_in_core	**iclog,
-	bool			regrant)
-{
-	struct xlog		*log = mp->m_log;
-	xfs_lsn_t		lsn = 0;
-
-	if (XLOG_FORCED_SHUTDOWN(log) ||
-	    /*
-	     * If nothing was ever written, don't write out commit record.
-	     * If we get an error, just continue and give back the log ticket.
-	     */
-	    (((ticket->t_flags & XLOG_TIC_INITED) == 0) &&
-	     (xlog_commit_record(log, ticket, iclog, &lsn)))) {
-		lsn = (xfs_lsn_t) -1;
-		regrant = false;
-	}
-
-
-	if (!regrant) {
-		trace_xfs_log_done_nonperm(log, ticket);
-
-		/*
-		 * Release ticket if not permanent reservation or a specific
-		 * request has been made to release a permanent reservation.
-		 */
-		xlog_ungrant_log_space(log, ticket);
-	} else {
-		trace_xfs_log_done_perm(log, ticket);
-
-		xlog_regrant_reserve_log_space(log, ticket);
-		/* If this ticket was a permanent reservation and we aren't
-		 * trying to release it, reset the inited flags; so next time
-		 * we write, a start record will be written out.
-		 */
-		ticket->t_flags |= XLOG_TIC_INITED;
-	}
-
-	xfs_log_ticket_put(ticket);
-	return lsn;
-}
-
 static bool
 __xlog_state_release_iclog(
 	struct xlog		*log,
@@ -869,32 +787,44 @@ xlog_wait_on_iclog(
 }
 
 /*
- * Final log writes as part of unmount.
- *
- * Mark the filesystem clean as unmount happens.  Note that during relocation
- * this routine needs to be executed as part of source-bag while the
- * deallocation must not be done until source-end.
+ * Write out an unmount record using the ticket provided. We have to account for
+ * the data space used in the unmount ticket as this write is not done from a
+ * transaction context that has already done the accounting for us.
  */
-
-/* Actually write the unmount record to disk. */
-static void
-xfs_log_write_unmount_record(
-	struct xfs_mount	*mp)
+static int
+xlog_write_unmount_record(
+	struct xlog		*log,
+	struct xlog_ticket	*ticket,
+	xfs_lsn_t		*lsn,
+	uint			flags)
 {
-	/* the data section must be 32 bit size aligned */
-	struct xfs_unmount_log_format magic = {
+	struct xfs_unmount_log_format ulf = {
 		.magic = XLOG_UNMOUNT_TYPE,
 	};
 	struct xfs_log_iovec reg = {
-		.i_addr = &magic,
-		.i_len = sizeof(magic),
+		.i_addr = &ulf,
+		.i_len = sizeof(ulf),
 		.i_type = XLOG_REG_TYPE_UNMOUNT,
 	};
 	struct xfs_log_vec vec = {
 		.lv_niovecs = 1,
 		.lv_iovecp = &reg,
 	};
-	struct xlog		*log = mp->m_log;
+
+	/* account for space used by record data */
+	ticket->t_curr_res -= sizeof(ulf);
+	return xlog_write(log, &vec, ticket, lsn, NULL, flags, false);
+}
+
+/*
+ * Mark the filesystem clean by writing an unmount record to the head of the
+ * log.
+ */
+static void
+xlog_unmount_write(
+	struct xlog		*log)
+{
+	struct xfs_mount	*mp = log->l_mp;
 	struct xlog_in_core	*iclog;
 	struct xlog_ticket	*tic = NULL;
 	xfs_lsn_t		lsn;
@@ -905,23 +835,7 @@ xfs_log_write_unmount_record(
 	if (error)
 		goto out_err;
 
-	/*
-	 * If we think the summary counters are bad, clear the unmount header
-	 * flag in the unmount record so that the summary counters will be
-	 * recalculated during log recovery at next mount.  Refer to
-	 * xlog_check_unmount_rec for more details.
-	 */
-	if (XFS_TEST_ERROR(xfs_fs_has_sickness(mp, XFS_SICK_FS_COUNTERS), mp,
-			XFS_ERRTAG_FORCE_SUMMARY_RECALC)) {
-		xfs_alert(mp, "%s: will fix summary counters at next mount",
-				__func__);
-		flags &= ~XLOG_UNMOUNT_TRANS;
-	}
-
-	/* remove inited flag, and account for space used */
-	tic->t_flags = 0;
-	tic->t_curr_res -= sizeof(magic);
-	error = xlog_write(log, &vec, tic, &lsn, NULL, flags);
+	error = xlog_write_unmount_record(log, tic, &lsn, flags);
 	/*
 	 * At this point, we're umounting anyway, so there's no point in
 	 * transitioning log state to IOERROR. Just continue...
@@ -943,8 +857,7 @@ out_err:
 
 	if (tic) {
 		trace_xfs_log_umount_write(log, tic);
-		xlog_ungrant_log_space(log, tic);
-		xfs_log_ticket_put(tic);
+		xfs_log_ticket_ungrant(log, tic);
 	}
 }
 
@@ -987,8 +900,22 @@ xfs_log_unmount_write(
 
 	if (XLOG_FORCED_SHUTDOWN(log))
 		return;
+
+	/*
+	 * If we think the summary counters are bad, avoid writing the unmount
+	 * record to force log recovery at next mount, after which the summary
+	 * counters will be recalculated.  Refer to xlog_check_unmount_rec for
+	 * more details.
+	 */
+	if (XFS_TEST_ERROR(xfs_fs_has_sickness(mp, XFS_SICK_FS_COUNTERS), mp,
+			XFS_ERRTAG_FORCE_SUMMARY_RECALC)) {
+		xfs_alert(mp, "%s: will fix summary counters at next mount",
+				__func__);
+		return;
+	}
+
 	xfs_log_unmount_verify_iclog(log);
-	xfs_log_write_unmount_record(mp);
+	xlog_unmount_write(log);
 }
 
 /*
@@ -1515,20 +1442,17 @@ out:
 	return ERR_PTR(error);
 }	/* xlog_alloc_log */
 
-
 /*
  * Write out the commit record of a transaction associated with the given
- * ticket.  Return the lsn of the commit record.
+ * ticket to close off a running log write. Return the lsn of the commit record.
  */
-STATIC int
+int
 xlog_commit_record(
 	struct xlog		*log,
 	struct xlog_ticket	*ticket,
 	struct xlog_in_core	**iclog,
-	xfs_lsn_t		*commitlsnp)
+	xfs_lsn_t		*lsn)
 {
-	struct xfs_mount *mp = log->l_mp;
-	int	error;
 	struct xfs_log_iovec reg = {
 		.i_addr = NULL,
 		.i_len = 0,
@@ -1538,12 +1462,15 @@ xlog_commit_record(
 		.lv_niovecs = 1,
 		.lv_iovecp = &reg,
 	};
+	int	error;
+
+	if (XLOG_FORCED_SHUTDOWN(log))
+		return -EIO;
 
-	ASSERT_ALWAYS(iclog);
-	error = xlog_write(log, &vec, ticket, commitlsnp, iclog,
-					XLOG_COMMIT_TRANS);
+	error = xlog_write(log, &vec, ticket, lsn, iclog, XLOG_COMMIT_TRANS,
+			   false);
 	if (error)
-		xfs_force_shutdown(mp, SHUTDOWN_LOG_IO_ERROR);
+		xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR);
 	return error;
 }
 
@@ -1761,7 +1688,15 @@ xlog_write_iclog(
 	iclog->ic_bio.bi_iter.bi_sector = log->l_logBBstart + bno;
 	iclog->ic_bio.bi_end_io = xlog_bio_end_io;
 	iclog->ic_bio.bi_private = iclog;
-	iclog->ic_bio.bi_opf = REQ_OP_WRITE | REQ_META | REQ_SYNC | REQ_FUA;
+
+	/*
+	 * We use REQ_SYNC | REQ_IDLE here to tell the block layer the are more
+	 * IOs coming immediately after this one. This prevents the block layer
+	 * writeback throttle from throttling log writes behind background
+	 * metadata writeback and causing priority inversions.
+	 */
+	iclog->ic_bio.bi_opf = REQ_OP_WRITE | REQ_META | REQ_SYNC |
+				REQ_IDLE | REQ_FUA;
 	if (need_flush)
 		iclog->ic_bio.bi_opf |= REQ_PREFLUSH;
 
@@ -1981,7 +1916,7 @@ xlog_dealloc_log(
 	log->l_mp->m_log = NULL;
 	destroy_workqueue(log->l_ioend_workqueue);
 	kmem_free(log);
-}	/* xlog_dealloc_log */
+}
 
 /*
  * Update counters atomically now that memcpy is done.
@@ -2118,23 +2053,21 @@ xlog_print_trans(
 }
 
 /*
- * Calculate the potential space needed by the log vector.  Each region gets
- * its own xlog_op_header_t and may need to be double word aligned.
+ * Calculate the potential space needed by the log vector.  We may need a start
+ * record, and each region gets its own struct xlog_op_header and may need to be
+ * double word aligned.
  */
 static int
 xlog_write_calc_vec_length(
 	struct xlog_ticket	*ticket,
-	struct xfs_log_vec	*log_vector)
+	struct xfs_log_vec	*log_vector,
+	bool			need_start_rec)
 {
 	struct xfs_log_vec	*lv;
-	int			headers = 0;
+	int			headers = need_start_rec ? 1 : 0;
 	int			len = 0;
 	int			i;
 
-	/* acct for start rec of xact */
-	if (ticket->t_flags & XLOG_TIC_INITED)
-		headers++;
-
 	for (lv = log_vector; lv; lv = lv->lv_next) {
 		/* we don't write ordered log vectors */
 		if (lv->lv_buf_len == XFS_LOG_VEC_ORDERED)
@@ -2156,27 +2089,16 @@ xlog_write_calc_vec_length(
 	return len;
 }
 
-/*
- * If first write for transaction, insert start record  We can't be trying to
- * commit if we are inited.  We can't have any "partial_copy" if we are inited.
- */
-static int
+static void
 xlog_write_start_rec(
 	struct xlog_op_header	*ophdr,
 	struct xlog_ticket	*ticket)
 {
-	if (!(ticket->t_flags & XLOG_TIC_INITED))
-		return 0;
-
 	ophdr->oh_tid	= cpu_to_be32(ticket->t_tid);
 	ophdr->oh_clientid = ticket->t_clientid;
 	ophdr->oh_len = 0;
 	ophdr->oh_flags = XLOG_START_TRANS;
 	ophdr->oh_res2 = 0;
-
-	ticket->t_flags &= ~XLOG_TIC_INITED;
-
-	return sizeof(struct xlog_op_header);
 }
 
 static xlog_op_header_t *
@@ -2365,13 +2287,14 @@ xlog_write(
 	struct xlog_ticket	*ticket,
 	xfs_lsn_t		*start_lsn,
 	struct xlog_in_core	**commit_iclog,
-	uint			flags)
+	uint			flags,
+	bool			need_start_rec)
 {
 	struct xlog_in_core	*iclog = NULL;
-	struct xfs_log_iovec	*vecp;
-	struct xfs_log_vec	*lv;
+	struct xfs_log_vec	*lv = log_vector;
+	struct xfs_log_iovec	*vecp = lv->lv_iovecp;
+	int			index = 0;
 	int			len;
-	int			index;
 	int			partial_copy = 0;
 	int			partial_copy_len = 0;
 	int			contwr = 0;
@@ -2379,25 +2302,13 @@ xlog_write(
 	int			data_cnt = 0;
 	int			error = 0;
 
-	*start_lsn = 0;
-
-	len = xlog_write_calc_vec_length(ticket, log_vector);
-
 	/*
-	 * Region headers and bytes are already accounted for.
-	 * We only need to take into account start records and
-	 * split regions in this function.
+	 * If this is a commit or unmount transaction, we don't need a start
+	 * record to be written.  We do, however, have to account for the
+	 * commit or unmount header that gets written. Hence we always have
+	 * to account for an extra xlog_op_header here.
 	 */
-	if (ticket->t_flags & XLOG_TIC_INITED)
-		ticket->t_curr_res -= sizeof(xlog_op_header_t);
-
-	/*
-	 * Commit record headers need to be accounted for. These
-	 * come in as separate writes so are easy to detect.
-	 */
-	if (flags & (XLOG_COMMIT_TRANS | XLOG_UNMOUNT_TRANS))
-		ticket->t_curr_res -= sizeof(xlog_op_header_t);
-
+	ticket->t_curr_res -= sizeof(struct xlog_op_header);
 	if (ticket->t_curr_res < 0) {
 		xfs_alert_tag(log->l_mp, XFS_PTAG_LOGRES,
 		     "ctx ticket reservation ran out. Need to up reservation");
@@ -2405,9 +2316,8 @@ xlog_write(
 		xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR);
 	}
 
-	index = 0;
-	lv = log_vector;
-	vecp = lv->lv_iovecp;
+	len = xlog_write_calc_vec_length(ticket, log_vector, need_start_rec);
+	*start_lsn = 0;
 	while (lv && (!lv->lv_niovecs || index < lv->lv_niovecs)) {
 		void		*ptr;
 		int		log_offset;
@@ -2431,7 +2341,6 @@ xlog_write(
 		while (lv && (!lv->lv_niovecs || index < lv->lv_niovecs)) {
 			struct xfs_log_iovec	*reg;
 			struct xlog_op_header	*ophdr;
-			int			start_rec_copy;
 			int			copy_len;
 			int			copy_off;
 			bool			ordered = false;
@@ -2447,11 +2356,15 @@ xlog_write(
 			ASSERT(reg->i_len % sizeof(int32_t) == 0);
 			ASSERT((unsigned long)ptr % sizeof(int32_t) == 0);
 
-			start_rec_copy = xlog_write_start_rec(ptr, ticket);
-			if (start_rec_copy) {
-				record_cnt++;
+			/*
+			 * Before we start formatting log vectors, we need to
+			 * write a start record. Only do this for the first
+			 * iclog we write to.
+			 */
+			if (need_start_rec) {
+				xlog_write_start_rec(ptr, ticket);
 				xlog_write_adv_cnt(&ptr, &len, &log_offset,
-						   start_rec_copy);
+						sizeof(struct xlog_op_header));
 			}
 
 			ophdr = xlog_write_setup_ophdr(log