xfs: remove the xfssyncd mess

index 19e2380..59d76bd 100644
@@ -921,7 +921,11 @@ xfs_fs_put_super(
 	xfs_filestream_unmount(mp);
 	cancel_delayed_work_sync(&mp->m_sync_work);
 	xfs_unmountfs(mp);
-	xfs_syncd_stop(mp);
+
+	cancel_delayed_work_sync(&mp->m_sync_work);
+	cancel_delayed_work_sync(&mp->m_reclaim_work);
+	cancel_work_sync(&mp->m_flush_work);
+
 	xfs_freesb(mp);
 	xfs_icsb_destroy_counters(mp);
 	xfs_destroy_mount_workqueues(mp);

@@ -1291,9 +1295,11 @@ xfs_fs_fill_super(
 	sb->s_time_gran = 1;
 	set_posix_acl_flag(sb);
 
-	error = xfs_syncd_init(mp);
-	if (error)
-		goto out_filestream_unmount;
+	INIT_WORK(&mp->m_flush_work, xfs_flush_worker);
+	INIT_DELAYED_WORK(&mp->m_sync_work, xfs_sync_worker);
+	INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
+
+	xfs_syncd_queue_sync(mp);
 
 	error = xfs_mountfs(mp);
 	if (error)

@@ -1316,8 +1322,10 @@ xfs_fs_fill_super(
 
 	return 0;
  out_syncd_stop:
-	xfs_syncd_stop(mp);
- out_filestream_unmount:
+	cancel_delayed_work_sync(&mp->m_sync_work);
+	cancel_delayed_work_sync(&mp->m_reclaim_work);
+	cancel_work_sync(&mp->m_flush_work);
+
 	xfs_filestream_unmount(mp);
  out_free_sb:
 	xfs_freesb(mp);

@@ -1336,7 +1344,10 @@ out_destroy_workqueues:
  out_unmount:
 	xfs_filestream_unmount(mp);
 	xfs_unmountfs(mp);
-	xfs_syncd_stop(mp);
+
+	cancel_delayed_work_sync(&mp->m_sync_work);
+	cancel_delayed_work_sync(&mp->m_reclaim_work);
+	cancel_work_sync(&mp->m_flush_work);
 	goto out_free_sb;
 }
 

index 9654817..13830e4 100644
@@ -370,7 +370,7 @@ xfs_quiesce_attr(
 	xfs_buf_unlock(mp->m_sb_bp);
 }
 
-static void
+void
 xfs_syncd_queue_sync(
 	struct xfs_mount        *mp)
 {

@@ -383,7 +383,7 @@ xfs_syncd_queue_sync(
  * disk quotas.  We might need to cover the log to indicate that the
  * filesystem is idle and not frozen.
  */
-STATIC void
+void
 xfs_sync_worker(
 	struct work_struct *work)
 {

@@ -445,7 +445,7 @@ xfs_syncd_queue_reclaim(
  * goes low. It scans as quickly as possible avoiding locked inodes or those
  * already being flushed, and once done schedules a future pass.
  */
-STATIC void
+void
 xfs_reclaim_worker(
 	struct work_struct *work)
 {

@@ -478,7 +478,7 @@ xfs_flush_inodes(
 	flush_work_sync(&mp->m_flush_work);
 }
 
-STATIC void
+void
 xfs_flush_worker(
 	struct work_struct *work)
 {

@@ -489,28 +489,6 @@ xfs_flush_worker(
 	xfs_sync_data(mp, SYNC_TRYLOCK | SYNC_WAIT);
 }
 
-int
-xfs_syncd_init(
-	struct xfs_mount	*mp)
-{
-	INIT_WORK(&mp->m_flush_work, xfs_flush_worker);
-	INIT_DELAYED_WORK(&mp->m_sync_work, xfs_sync_worker);
-	INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
-
-	xfs_syncd_queue_sync(mp);
-
-	return 0;
-}
-
-void
-xfs_syncd_stop(
-	struct xfs_mount	*mp)
-{
-	cancel_delayed_work_sync(&mp->m_sync_work);
-	cancel_delayed_work_sync(&mp->m_reclaim_work);
-	cancel_work_sync(&mp->m_flush_work);
-}
-
 void
 __xfs_inode_set_reclaim_tag(
 	struct xfs_perag	*pag,

index 941202e..3f59e5b 100644
@@ -26,8 +26,10 @@ struct xfs_perag;
 
 extern struct workqueue_struct	*xfs_syncd_wq;	/* sync workqueue */
 
-int xfs_syncd_init(struct xfs_mount *mp);
-void xfs_syncd_stop(struct xfs_mount *mp);
+void xfs_syncd_queue_sync(struct xfs_mount *mp);
+void xfs_sync_worker(struct work_struct *work);
+void xfs_flush_worker(struct work_struct *work);
+void xfs_reclaim_worker(struct work_struct *work);
 
 int xfs_quiesce_data(struct xfs_mount *mp);
 void xfs_quiesce_attr(struct xfs_mount *mp);

index 29c2f83..3152924 100644
@@ -1483,9 +1483,11 @@ xfs_unmountfs(
 
 	/*
 	 * And reclaim all inodes.  At this point there should be no dirty
-	 * inode, and none should be pinned or locked, but use synchronous
-	 * reclaim just to be sure.
+	 * inodes and none should be pinned or locked, but use synchronous
+	 * reclaim just to be sure. We can stop background inode reclaim
+	 * here as well if it is still running.
 	 */
+	cancel_delayed_work_sync(&mp->m_reclaim_work);
 	xfs_reclaim_inodes(mp, SYNC_WAIT);
 
 	xfs_qm_unmount(mp);

index 59d76bd..935b2c7 100644
@@ -918,14 +918,12 @@ xfs_fs_put_super(
 {
 	struct xfs_mount	*mp = XFS_M(sb);
 
-	xfs_filestream_unmount(mp);
-	cancel_delayed_work_sync(&mp->m_sync_work);
-	xfs_unmountfs(mp);
-
 	cancel_delayed_work_sync(&mp->m_sync_work);
-	cancel_delayed_work_sync(&mp->m_reclaim_work);
 	cancel_work_sync(&mp->m_flush_work);
 
+	xfs_filestream_unmount(mp);
+	xfs_unmountfs(mp);
+
 	xfs_freesb(mp);
 	xfs_icsb_destroy_counters(mp);
 	xfs_destroy_mount_workqueues(mp);

@@ -1232,6 +1230,9 @@ xfs_fs_fill_super(
 	spin_lock_init(&mp->m_sb_lock);
 	mutex_init(&mp->m_growlock);
 	atomic_set(&mp->m_active_trans, 0);
+	INIT_WORK(&mp->m_flush_work, xfs_flush_worker);
+	INIT_DELAYED_WORK(&mp->m_sync_work, xfs_sync_worker);
+	INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
 
 	mp->m_super = sb;
 	sb->s_fs_info = mp;

@@ -1295,15 +1296,9 @@ xfs_fs_fill_super(
 	sb->s_time_gran = 1;
 	set_posix_acl_flag(sb);
 
-	INIT_WORK(&mp->m_flush_work, xfs_flush_worker);
-	INIT_DELAYED_WORK(&mp->m_sync_work, xfs_sync_worker);
-	INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
-
-	xfs_syncd_queue_sync(mp);
-
 	error = xfs_mountfs(mp);
 	if (error)
-		goto out_syncd_stop;
+		goto out_filestream_unmount;
 
 	root = igrab(VFS_I(mp->m_rootip));
 	if (!root) {

@@ -1320,12 +1315,15 @@ xfs_fs_fill_super(
 		goto out_unmount;
 	}
 
+	/*
+	 * The filesystem is successfully mounted, so we can start background
+	 * sync work now.
+	 */
+	xfs_syncd_queue_sync(mp);
+
 	return 0;
- out_syncd_stop:
-	cancel_delayed_work_sync(&mp->m_sync_work);
-	cancel_delayed_work_sync(&mp->m_reclaim_work);
-	cancel_work_sync(&mp->m_flush_work);
 
+ out_filestream_unmount:
 	xfs_filestream_unmount(mp);
  out_free_sb:
 	xfs_freesb(mp);

@@ -1344,10 +1342,6 @@ out_destroy_workqueues:
  out_unmount:
 	xfs_filestream_unmount(mp);
 	xfs_unmountfs(mp);
-
-	cancel_delayed_work_sync(&mp->m_sync_work);
-	cancel_delayed_work_sync(&mp->m_reclaim_work);
-	cancel_work_sync(&mp->m_flush_work);
 	goto out_free_sb;
 }
 

index 13830e4..509190f 100644
@@ -379,9 +379,9 @@ xfs_syncd_queue_sync(
 }
 
 /*
- * Every sync period we need to unpin all items, reclaim inodes and sync
- * disk quotas.  We might need to cover the log to indicate that the
- * filesystem is idle and not frozen.
+ * Every sync period we need to unpin all items in the AIL and push them to
+ * disk. If there is nothing dirty, then we might need to cover the log to
+ * indicate that the filesystem is idle and not frozen.
  */
 void
 xfs_sync_worker(

@@ -391,17 +391,7 @@ xfs_sync_worker(
 					struct xfs_mount, m_sync_work);
 	int		error;
 
-	/*
-	 * We shouldn't write/force the log if we are in the mount/unmount
-	 * process or on a read only filesystem. The workqueue still needs to be
-	 * active in both cases, however, because it is used for inode reclaim
-	 * during these times.  Use the MS_ACTIVE flag to avoid doing anything
-	 * during mount.  Doing work during unmount is avoided by calling
-	 * cancel_delayed_work_sync on this work queue before tearing down
-	 * the ail and the log in xfs_log_unmount.
-	 */
-	if (!(mp->m_super->s_flags & MS_ACTIVE) &&
-	    !(mp->m_flags & XFS_MOUNT_RDONLY)) {
+	if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
 		/* dgc: errors ignored here */
 		if (mp->m_super->s_writers.frozen == SB_UNFROZEN &&
 		    xfs_log_need_covered(mp))

@@ -409,8 +399,7 @@ xfs_sync_worker(
 		else
 			xfs_log_force(mp, 0);
 
-		/* start pushing all the metadata that is currently
-		 * dirty */
+		/* start pushing all the metadata that is currently dirty */
 		xfs_ail_push_all(mp->m_ail);
 	}
 

index 935b2c7..f6147ae 100644
@@ -1107,6 +1107,7 @@ xfs_fs_remount(
 		 * value if it is non-zero, otherwise go with the default.
 		 */
 		xfs_restore_resvblks(mp);
+		xfs_syncd_queue_sync(mp);
 	}
 
 	/* rw -> ro */

@@ -1152,6 +1153,7 @@ xfs_fs_unfreeze(
 	struct xfs_mount	*mp = XFS_M(sb);
 
 	xfs_restore_resvblks(mp);
+	xfs_syncd_queue_sync(mp);
 	return 0;
 }
 

index 509190f..5d69f23 100644
@@ -323,6 +323,9 @@ xfs_quiesce_data(
  * Second stage of a quiesce. The data is already synced, now we have to take
  * care of the metadata. New transactions are already blocked, so we need to
  * wait for any remaining transactions to drain out before proceeding.
+ *
+ * Note: this stops background sync work - the callers must ensure it is started
+ * again when appropriate.
  */
 void
 xfs_quiesce_attr(

@@ -341,6 +344,9 @@ xfs_quiesce_attr(
 	/* flush all pending changes from the AIL */
 	xfs_ail_push_all_sync(mp->m_ail);
 
+	/* stop background sync work */
+	cancel_delayed_work_sync(&mp->m_sync_work);
+
 	/*
 	 * Just warn here till VFS can correctly support
 	 * read-only remount without racing.

@@ -379,9 +385,8 @@ xfs_syncd_queue_sync(
 }
 
 /*
- * Every sync period we need to unpin all items in the AIL and push them to
- * disk. If there is nothing dirty, then we might need to cover the log to
- * indicate that the filesystem is idle and not frozen.
+ * Every sync period we need to push dirty metadata and try to cover the log
+ * to indicate the filesystem is idle and not frozen.
  */
 void
 xfs_sync_worker(

@@ -391,17 +396,15 @@ xfs_sync_worker(
 					struct xfs_mount, m_sync_work);
 	int		error;
 
-	if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
-		/* dgc: errors ignored here */
-		if (mp->m_super->s_writers.frozen == SB_UNFROZEN &&
-		    xfs_log_need_covered(mp))
-			error = xfs_fs_log_dummy(mp);
-		else
-			xfs_log_force(mp, 0);
+	/* dgc: errors ignored here */
+	if (mp->m_super->s_writers.frozen == SB_UNFROZEN &&
+	    xfs_log_need_covered(mp))
+		error = xfs_fs_log_dummy(mp);
+	else
+		xfs_log_force(mp, 0);
 
-		/* start pushing all the metadata that is currently dirty */
-		xfs_ail_push_all(mp->m_ail);
-	}
+	/* start pushing all the metadata that is currently dirty */
+	xfs_ail_push_all(mp->m_ail);
 
 	/* queue us up again */
 	xfs_syncd_queue_sync(mp);

index 7f4f937..a1fe7a7 100644
@@ -34,6 +34,7 @@
 #include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_trace.h"
+#include "xfs_fsops.h"
 
 kmem_zone_t	*xfs_log_ticket_zone;
 

@@ -698,6 +699,8 @@ xfs_log_mount_finish(xfs_mount_t *mp)
 		ASSERT(mp->m_flags & XFS_MOUNT_RDONLY);
 	}
 
+	xfs_log_work_queue(mp);
+
 	return error;
 }
 

@@ -858,7 +861,7 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 void
 xfs_log_unmount(xfs_mount_t *mp)
 {
-	cancel_delayed_work_sync(&mp->m_sync_work);
+	cancel_delayed_work_sync(&mp->m_log->l_work);
 	xfs_trans_ail_destroy(mp);
 	xlog_dealloc_log(mp->m_log);
 }

@@ -1161,6 +1164,40 @@ done:
 }	/* xlog_get_iclog_buffer_size */
 
 
+void
+xfs_log_work_queue(
+	struct xfs_mount        *mp)
+{
+	queue_delayed_work(xfs_syncd_wq, &mp->m_log->l_work,
+				msecs_to_jiffies(xfs_syncd_centisecs * 10));
+}
+
+/*
+ * Every sync period we need to unpin all items in the AIL and push them to
+ * disk. If there is nothing dirty, then we might need to cover the log to
+ * indicate that the filesystem is idle.
+ */
+void
+xfs_log_worker(
+	struct work_struct	*work)
+{
+	struct xlog		*log = container_of(to_delayed_work(work),
+						struct xlog, l_work);
+	struct xfs_mount	*mp = log->l_mp;
+
+	/* dgc: errors ignored - not fatal and nowhere to report them */
+	if (xfs_log_need_covered(mp))
+		xfs_fs_log_dummy(mp);
+	else
+		xfs_log_force(mp, 0);
+
+	/* start pushing all the metadata that is currently dirty */
+	xfs_ail_push_all(mp->m_ail);
+
+	/* queue us up again */
+	xfs_log_work_queue(mp);
+}
+
 /*
  * This routine initializes some of the log structure for a given mount point.
  * Its primary purpose is to fill in enough, so recovery can occur.  However,

@@ -1195,6 +1232,7 @@ xlog_alloc_log(
 	log->l_logBBsize   = num_bblks;
 	log->l_covered_state = XLOG_STATE_COVER_IDLE;
 	log->l_flags	   |= XLOG_ACTIVE_RECOVERY;
+	INIT_DELAYED_WORK(&log->l_work, xfs_log_worker);
 
 	log->l_prev_block  = -1;
 	/* log->l_tail_lsn = 0x100000000LL; cycle = 1; current block = 0 */

@@ -3700,3 +3738,4 @@ xlog_iclogs_empty(
 	} while (iclog != log->l_iclog);
 	return 1;
 }
+

index 748d312..26ed7de 100644
@@ -181,5 +181,8 @@ int	xfs_log_commit_cil(struct xfs_mount *mp, struct xfs_trans *tp,
 				xfs_lsn_t *commit_lsn, int flags);
 bool	xfs_log_item_in_current_chkpt(struct xfs_log_item *lip);
 
+void	xfs_log_work_queue(struct xfs_mount *mp);
+void	xfs_log_worker(struct work_struct *work);
+
 #endif
 #endif	/* __XFS_LOG_H__ */

index 18a801d..9a4e0e5 100644
@@ -495,6 +495,7 @@ struct xlog {
 	struct xfs_buf		*l_xbuf;        /* extra buffer for log
 						 * wrapping */
 	struct xfs_buftarg	*l_targ;        /* buftarg of log */
+	struct delayed_work	l_work;		/* background flush work */
 	uint			l_flags;
 	uint			l_quotaoffs_flag; /* XFS_DQ_*, for QUOTAOFFs */
 	struct list_head	*l_buf_cancel_table;

index deee09e..26e46ae 100644
@@ -197,7 +197,6 @@ typedef struct xfs_mount {
 	struct mutex		m_icsb_mutex;	/* balancer sync lock */
 #endif
 	struct xfs_mru_cache	*m_filestream;  /* per-mount filestream data */
-	struct delayed_work	m_sync_work;	/* background sync work */
 	struct delayed_work	m_reclaim_work;	/* background inode reclaim */
 	struct work_struct	m_flush_work;	/* background inode flush */
 	__int64_t		m_update_flags;	/* sb flags we need to update

index f6147ae..b85ca2d 100644
@@ -918,7 +918,6 @@ xfs_fs_put_super(
 {
 	struct xfs_mount	*mp = XFS_M(sb);
 
-	cancel_delayed_work_sync(&mp->m_sync_work);
 	cancel_work_sync(&mp->m_flush_work);
 
 	xfs_filestream_unmount(mp);

@@ -953,10 +952,10 @@ xfs_fs_sync_fs(
 	if (laptop_mode) {
 		/*
 		 * The disk must be active because we're syncing.
-		 * We schedule xfssyncd now (now that the disk is
+		 * We schedule log work now (now that the disk is
 		 * active) instead of later (when it might not be).
 		 */
-		flush_delayed_work_sync(&mp->m_sync_work);
+		flush_delayed_work_sync(&mp->m_log->l_work);
 	}
 
 	return 0;

@@ -1107,7 +1106,7 @@ xfs_fs_remount(
 		 * value if it is non-zero, otherwise go with the default.
 		 */
 		xfs_restore_resvblks(mp);
-		xfs_syncd_queue_sync(mp);
+		xfs_log_work_queue(mp);
 	}
 
 	/* rw -> ro */

@@ -1153,7 +1152,7 @@ xfs_fs_unfreeze(
 	struct xfs_mount	*mp = XFS_M(sb);
 
 	xfs_restore_resvblks(mp);
-	xfs_syncd_queue_sync(mp);
+	xfs_log_work_queue(mp);
 	return 0;
 }
 

@@ -1233,7 +1232,6 @@ xfs_fs_fill_super(
 	mutex_init(&mp->m_growlock);
 	atomic_set(&mp->m_active_trans, 0);
 	INIT_WORK(&mp->m_flush_work, xfs_flush_worker);
-	INIT_DELAYED_WORK(&mp->m_sync_work, xfs_sync_worker);
 	INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
 
 	mp->m_super = sb;

@@ -1317,12 +1315,6 @@ xfs_fs_fill_super(
 		goto out_unmount;
 	}
 
-	/*
-	 * The filesystem is successfully mounted, so we can start background
-	 * sync work now.
-	 */
-	xfs_syncd_queue_sync(mp);
-
 	return 0;
 
  out_filestream_unmount:

index 5d69f23..7527610 100644
@@ -19,6 +19,7 @@
 #include "xfs_fs.h"
 #include "xfs_types.h"
 #include "xfs_log.h"
+#include "xfs_log_priv.h"
 #include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_trans_priv.h"

@@ -344,8 +345,8 @@ xfs_quiesce_attr(
 	/* flush all pending changes from the AIL */
 	xfs_ail_push_all_sync(mp->m_ail);
 
-	/* stop background sync work */
-	cancel_delayed_work_sync(&mp->m_sync_work);
+	/* stop background log work */
+	cancel_delayed_work_sync(&mp->m_log->l_work);
 
 	/*
 	 * Just warn here till VFS can correctly support

@@ -376,40 +377,6 @@ xfs_quiesce_attr(
 	xfs_buf_unlock(mp->m_sb_bp);
 }
 
-void
-xfs_syncd_queue_sync(
-	struct xfs_mount        *mp)
-{
-	queue_delayed_work(xfs_syncd_wq, &mp->m_sync_work,
-				msecs_to_jiffies(xfs_syncd_centisecs * 10));
-}
-
-/*
- * Every sync period we need to push dirty metadata and try to cover the log
- * to indicate the filesystem is idle and not frozen.
- */
-void
-xfs_sync_worker(
-	struct work_struct *work)
-{
-	struct xfs_mount *mp = container_of(to_delayed_work(work),
-					struct xfs_mount, m_sync_work);
-	int		error;
-
-	/* dgc: errors ignored here */
-	if (mp->m_super->s_writers.frozen == SB_UNFROZEN &&
-	    xfs_log_need_covered(mp))
-		error = xfs_fs_log_dummy(mp);
-	else
-		xfs_log_force(mp, 0);
-
-	/* start pushing all the metadata that is currently dirty */
-	xfs_ail_push_all(mp->m_ail);
-
-	/* queue us up again */
-	xfs_syncd_queue_sync(mp);
-}
-
 /*
  * Queue a new inode reclaim pass if there are reclaimable inodes and there
  * isn't a reclaim pass already in progress. By default it runs every 5s based

index 3f59e5b..8d58fab 100644
@@ -26,8 +26,6 @@ struct xfs_perag;
 
 extern struct workqueue_struct	*xfs_syncd_wq;	/* sync workqueue */
 
-void xfs_syncd_queue_sync(struct xfs_mount *mp);
-void xfs_sync_worker(struct work_struct *work);
 void xfs_flush_worker(struct work_struct *work);
 void xfs_reclaim_worker(struct work_struct *work);
 

index a1fe7a7..a400e71 100644
@@ -853,15 +853,38 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 }	/* xfs_log_unmount_write */
 
 /*
- * Deallocate log structures for unmount/relocation.
+ * Shut down and release the AIL and Log.
  *
- * We need to stop the aild from running before we destroy
- * and deallocate the log as the aild references the log.
+ * During unmount, we need to ensure we flush all the dirty metadata objects
+ * from the AIL so that the log is empty before we write the unmount record to
+ * the log.
+ *
+ * To do this, we first need to shut down the background log work so it is not
+ * trying to cover the log as we clean up. We then need to unpin all objects in
+ * the log so we can then flush them out. Once they have completed their IO and
+ * run the callbacks removing themselves from the AIL, we can write the unmount
+ * record, tear down the AIL and finally free the log.
  */
 void
 xfs_log_unmount(xfs_mount_t *mp)
 {
 	cancel_delayed_work_sync(&mp->m_log->l_work);
+	xfs_log_force(mp, XFS_LOG_SYNC);
+
+	/*
+	 * The superblock buffer is uncached and while xfs_ail_push_all_sync()
+	 * will push it, xfs_wait_buftarg() will not wait for it. Further,
+	 * xfs_buf_iowait() cannot be used because it was pushed with the
+	 * XBF_ASYNC flag set, so we need to use a lock/unlock pair to wait for
+	 * the IO to complete.
+	 */
+	xfs_ail_push_all_sync(mp->m_ail);
+	xfs_wait_buftarg(mp->m_ddev_targp);
+	xfs_buf_lock(mp->m_sb_bp);
+	xfs_buf_unlock(mp->m_sb_bp);
+
+	xfs_log_unmount_write(mp);
+
 	xfs_trans_ail_destroy(mp);
 	xlog_dealloc_log(mp->m_log);
 }

index 3152924..149b601 100644
@@ -1493,13 +1493,6 @@ xfs_unmountfs(
 	xfs_qm_unmount(mp);
 
 	/*
-	 * Flush out the log synchronously so that we know for sure
-	 * that nothing is pinned.  This is important because bflush()
-	 * will skip pinned buffers.
-	 */
-	xfs_log_force(mp, XFS_LOG_SYNC);
-
-	/*
 	 * Unreserve any blocks we have so that when we unmount we don't account
 	 * the reserved free space as used. This is really only necessary for
 	 * lazy superblock counting because it trusts the incore superblock

@@ -1524,23 +1517,6 @@ xfs_unmountfs(
 		xfs_warn(mp, "Unable to update superblock counters. "
 				"Freespace may not be correct on next mount.");
 
-	/*
-	 * At this point we might have modified the superblock again and thus
-	 * added an item to the AIL, thus flush it again.
-	 */
-	xfs_ail_push_all_sync(mp->m_ail);
-	xfs_wait_buftarg(mp->m_ddev_targp);
-
-	/*
-	 * The superblock buffer is uncached and xfsaild_push() will lock and
-	 * set the XBF_ASYNC flag on the buffer. We cannot do xfs_buf_iowait()
-	 * here but a lock on the superblock buffer will block until iodone()
-	 * has completed.
-	 */
-	xfs_buf_lock(mp->m_sb_bp);
-	xfs_buf_unlock(mp->m_sb_bp);
-
-	xfs_log_unmount_write(mp);
 	xfs_log_unmount(mp);
 	xfs_uuid_unmount(mp);
 

index 1eaeb8b..2cadcf7 100644
@@ -728,16 +728,17 @@ xfs_file_buffered_aio_write(
 write_retry:
 	trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0);
 	ret = generic_file_buffered_write(iocb, iovp, nr_segs,
-			pos, &iocb->ki_pos, count, ret);
+			pos, &iocb->ki_pos, count, 0);
+
 	/*
-	 * if we just got an ENOSPC, flush the inode now we aren't holding any
-	 * page locks and retry *once*
+	 * If we just got an ENOSPC, try to write back all dirty inodes to
+	 * convert delalloc space to free up some of the excess reserved
+	 * metadata space.
 	 */
 	if (ret == -ENOSPC && !enospc) {
 		enospc = 1;
-		ret = -xfs_flush_pages(ip, 0, -1, 0, FI_NONE);
-		if (!ret)
-			goto write_retry;
+		xfs_flush_inodes(ip);
+		goto write_retry;
 	}
 
 	current->backing_dev_info = NULL;

index 94b32f9..a12fe18 100644
@@ -288,6 +288,16 @@ xfs_new_eof(struct xfs_inode *ip, xfs_fsize_t new_size)
 }
 
 /*
+ * Flush all dirty data to disk. Must not be called while holding an XFS_ILOCK
+ * or a page lock.
+ */
+static inline void
+xfs_flush_inodes(struct xfs_inode *ip)
+{
+	writeback_inodes_sb_if_idle(VFS_I(ip)->i_sb, WB_REASON_FS_FREE_SPACE);
+}
+
+/*
  * i_flags helper functions
  */
 static inline void

index 973dff6..f858b90 100644
@@ -373,7 +373,7 @@ xfs_iomap_write_delay(
 	xfs_extlen_t	extsz;
 	int		nimaps;
 	xfs_bmbt_irec_t imap[XFS_WRITE_IMAPS];
-	int		prealloc, flushed = 0;
+	int		prealloc;
 	int		error;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));

@@ -434,26 +434,17 @@ retry:
 	}
 
 	/*
-	 * If bmapi returned us nothing, we got either ENOSPC or EDQUOT.  For
-	 * ENOSPC, * flush all other inodes with delalloc blocks to free up
-	 * some of the excess reserved metadata space. For both cases, retry
+	 * If bmapi returned us nothing, we got either ENOSPC or EDQUOT. Retry
 	 * without EOF preallocation.
 	 */
 	if (nimaps == 0) {
 		trace_xfs_delalloc_enospc(ip, offset, count);
-		if (flushed)
-			return XFS_ERROR(error ? error : ENOSPC);
-
-		if (error == ENOSPC) {
-			xfs_iunlock(ip, XFS_ILOCK_EXCL);
-			xfs_flush_inodes(ip);
-			xfs_ilock(ip, XFS_ILOCK_EXCL);
+		if (prealloc) {
+			prealloc = 0;
+			error = 0;
+			goto retry;
 		}
-
-		flushed = 1;
-		error = 0;
-		prealloc = 0;
-		goto retry;
+		return XFS_ERROR(error ? error : ENOSPC);
 	}
 
 	if (!(imap[0].br_startblock || XFS_IS_REALTIME_INODE(ip)))

index 26e46ae..a54b5aa 100644
@@ -198,7 +198,6 @@ typedef struct xfs_mount {
 #endif
 	struct xfs_mru_cache	*m_filestream;  /* per-mount filestream data */
 	struct delayed_work	m_reclaim_work;	/* background inode reclaim */
-	struct work_struct	m_flush_work;	/* background inode flush */
 	__int64_t		m_update_flags;	/* sb flags we need to update
 						   on the next remount,rw */
 	struct shrinker		m_inode_shrink;	/* inode reclaim shrinker */

index b85ca2d..fed1eb2 100644
@@ -918,8 +918,6 @@ xfs_fs_put_super(
 {
 	struct xfs_mount	*mp = XFS_M(sb);
 
-	cancel_work_sync(&mp->m_flush_work);
-
 	xfs_filestream_unmount(mp);
 	xfs_unmountfs(mp);
 

@@ -1231,7 +1229,6 @@ xfs_fs_fill_super(
 	spin_lock_init(&mp->m_sb_lock);
 	mutex_init(&mp->m_growlock);
 	atomic_set(&mp->m_active_trans, 0);
-	INIT_WORK(&mp->m_flush_work, xfs_flush_worker);
 	INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
 
 	mp->m_super = sb;

90 lines not on this page · raw message

index 8d58fab..0018e84 100644
@@ -26,14 +26,11 @@ struct xfs_perag;
 
 extern struct workqueue_struct	*xfs_syncd_wq;	/* sync workqueue */
 
-void xfs_flush_worker(struct work_struct *work);
 void xfs_reclaim_worker(struct work_struct *work);
 
 int xfs_quiesce_data(struct xfs_mount *mp);
 void xfs_quiesce_attr(struct xfs_mount *mp);
 
-void xfs_flush_inodes(struct xfs_inode *ip);
-
 int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);
 int xfs_reclaim_inodes_count(struct xfs_mount *mp);
 void xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);

Index: xfs/fs/xfs/xfs_file.c
===================================================================
@@ -728,16 +728,17 @@ xfs_file_buffered_aio_write(
 write_retry:
 	trace_xfs_file_buffered_write(ip, count, iocb->ki_pos, 0);
 	ret = generic_file_buffered_write(iocb, iovp, nr_segs,
-			pos, &iocb->ki_pos, count, ret);
+			pos, &iocb->ki_pos, count, 0);
+
 	/*
-	 * if we just got an ENOSPC, flush the inode now we aren't holding any
-	 * page locks and retry *once*
+	 * If we just got an ENOSPC, try to write back all dirty inodes to
+	 * convert delalloc space to free up some of the excess reserved
+	 * metadata space.
 	 */
 	if (ret == -ENOSPC && !enospc) {
 		enospc = 1;
-		ret = -xfs_flush_pages(ip, 0, -1, 0, FI_NONE);
-		if (!ret)
-			goto write_retry;
+		xfs_flush_inodes(ip->i_mount);
+		goto write_retry;
 	}
 
 	current->backing_dev_info = NULL;

Index: xfs/fs/xfs/xfs_iomap.c
===================================================================
@@ -373,7 +373,7 @@ xfs_iomap_write_delay(
 	xfs_extlen_t	extsz;
 	int		nimaps;
 	xfs_bmbt_irec_t imap[XFS_WRITE_IMAPS];
-	int		prealloc, flushed = 0;
+	int		prealloc;
 	int		error;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));

@@ -434,26 +434,17 @@ retry:
 	}
 
 	/*
-	 * If bmapi returned us nothing, we got either ENOSPC or EDQUOT.  For
-	 * ENOSPC, * flush all other inodes with delalloc blocks to free up
-	 * some of the excess reserved metadata space. For both cases, retry
+	 * If bmapi returned us nothing, we got either ENOSPC or EDQUOT. Retry
 	 * without EOF preallocation.
 	 */
 	if (nimaps == 0) {
 		trace_xfs_delalloc_enospc(ip, offset, count);
-		if (flushed)
-			return XFS_ERROR(error ? error : ENOSPC);
-
-		if (error == ENOSPC) {
-			xfs_iunlock(ip, XFS_ILOCK_EXCL);
-			xfs_flush_inodes(ip);
-			xfs_ilock(ip, XFS_ILOCK_EXCL);
+		if (prealloc) {
+			prealloc = 0;
+			error = 0;
+			goto retry;
 		}
-
-		flushed = 1;
-		error = 0;
-		prealloc = 0;
-		goto retry;
+		return XFS_ERROR(error ? error : ENOSPC);
 	}
 
 	if (!(imap[0].br_startblock || XFS_IS_REALTIME_INODE(ip)))

Index: xfs/fs/xfs/xfs_mount.h
===================================================================
@@ -198,7 +198,6 @@ typedef struct xfs_mount {
 #endif
 	struct xfs_mru_cache	*m_filestream;  /* per-mount filestream data */
 	struct delayed_work	m_reclaim_work;	/* background inode reclaim */
-	struct work_struct	m_flush_work;	/* background inode flush */
 	__int64_t		m_update_flags;	/* sb flags we need to update
 						   on the next remount,rw */
 	struct shrinker		m_inode_shrink;	/* inode reclaim shrinker */

@@ -381,6 +380,16 @@ extern int	xfs_dev_is_read_only(struct x
 
 extern void	xfs_set_low_space_thresholds(struct xfs_mount *);
 
+/*
+ * Flush all dirty data to disk. Must not be called while holding an XFS_ILOCK
+ * or a page lock.
+ */
+static inline void
+xfs_flush_inodes(struct xfs_mount *mp)
+{
+	writeback_inodes_sb_if_idle(mp->m_super, WB_REASON_FS_FREE_SPACE);
+}
+
 #endif	/* __KERNEL__ */
 
 extern void	xfs_mod_sb(struct xfs_trans *, __int64_t);

Index: xfs/fs/xfs/xfs_super.c
===================================================================
@@ -918,8 +918,6 @@ xfs_fs_put_super(
 {
 	struct xfs_mount	*mp = XFS_M(sb);
 
-	cancel_work_sync(&mp->m_flush_work);
-
 	xfs_filestream_unmount(mp);
 	xfs_unmountfs(mp);
 

@@ -1235,7 +1233,6 @@ xfs_fs_fill_super(
 	spin_lock_init(&mp->m_sb_lock);
 	mutex_init(&mp->m_growlock);
 	atomic_set(&mp->m_active_trans, 0);
-	INIT_WORK(&mp->m_flush_work, xfs_flush_worker);
 	INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
 
 	mp->m_super = sb;

90 lines not on this page · raw message

Index: xfs/fs/xfs/xfs_sync.h
===================================================================
@@ -26,14 +26,11 @@ struct xfs_perag;
 
 extern struct workqueue_struct	*xfs_syncd_wq;	/* sync workqueue */
 
-void xfs_flush_worker(struct work_struct *work);
 void xfs_reclaim_worker(struct work_struct *work);
 
 int xfs_quiesce_data(struct xfs_mount *mp);
 void xfs_quiesce_attr(struct xfs_mount *mp);
 
-void xfs_flush_inodes(struct xfs_inode *ip);
-
 int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);
 int xfs_reclaim_inodes_count(struct xfs_mount *mp);
 void xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);

Index: xfs/fs/xfs/xfs_vnodeops.c
===================================================================
@@ -777,7 +777,7 @@ xfs_create(
 			XFS_TRANS_PERM_LOG_RES, log_count);
 	if (error == ENOSPC) {
 		/* flush outstanding delalloc blocks and retry */
-		xfs_flush_inodes(dp);
+		xfs_flush_inodes(dp->i_mount);
 		error = xfs_trans_reserve(tp, resblks, log_res, 0,
 				XFS_TRANS_PERM_LOG_RES, log_count);
 	}

index da69c18..0ec7a46 100644
@@ -294,7 +294,7 @@ xfs_new_eof(struct xfs_inode *ip, xfs_fsize_t new_size)
 static inline void
 xfs_flush_inodes(struct xfs_inode *ip)
 {
-	writeback_inodes_sb_if_idle(VFS_I(ip)->i_sb, WB_REASON_FS_FREE_SPACE);
+	sync_inodes_sb(VFS_I(ip)->i_sb);
 }
 
 /*

index da69c18..f11133b 100644
@@ -294,7 +294,9 @@ xfs_new_eof(struct xfs_inode *ip, xfs_fsize_t new_size)
 static inline void
 xfs_flush_inodes(struct xfs_inode *ip)
 {
-	writeback_inodes_sb_if_idle(VFS_I(ip)->i_sb, WB_REASON_FS_FREE_SPACE);
+	down_read(&VFS_I(ip)->i_sb->s_umount);
+	sync_inodes_sb(VFS_I(ip)->i_sb);
+	up_read(&VFS_I(ip)->i_sb->s_umount);
 }
 
 /*

index a400e71..96ea9ed 100644
@@ -1191,7 +1191,7 @@ void
 xfs_log_work_queue(
 	struct xfs_mount        *mp)
 {
-	queue_delayed_work(xfs_syncd_wq, &mp->m_log->l_work,
+	queue_delayed_work(mp->m_log_workqueue, &mp->m_log->l_work,
 				msecs_to_jiffies(xfs_syncd_centisecs * 10));
 }
 

index a54b5aa..7c417b6 100644
@@ -207,6 +207,8 @@ typedef struct xfs_mount {
 	struct workqueue_struct	*m_data_workqueue;
 	struct workqueue_struct	*m_unwritten_workqueue;
 	struct workqueue_struct	*m_cil_workqueue;
+	struct workqueue_struct	*m_reclaim_workqueue;
+	struct workqueue_struct	*m_log_workqueue;
 } xfs_mount_t;
 
 /*

index fed1eb2..65cf42c 100644
@@ -776,8 +776,23 @@ xfs_init_mount_workqueues(
 			WQ_MEM_RECLAIM, 0, mp->m_fsname);
 	if (!mp->m_cil_workqueue)
 		goto out_destroy_unwritten;
+
+	mp->m_reclaim_workqueue = alloc_workqueue("xfs-reclaim/%s",
+			WQ_NON_REENTRANT, 0, mp->m_fsname);
+	if (!mp->m_reclaim_workqueue)
+		goto out_destroy_cil;
+
+	mp->m_log_workqueue = alloc_workqueue("xfs-reclaim/%s",
+			WQ_NON_REENTRANT, 0, mp->m_fsname);
+	if (!mp->m_log_workqueue)
+		goto out_destroy_reclaim;
+
 	return 0;
 
+out_destroy_reclaim:
+	destroy_workqueue(mp->m_reclaim_workqueue);
+out_destroy_cil:
+	destroy_workqueue(mp->m_cil_workqueue);
 out_destroy_unwritten:
 	destroy_workqueue(mp->m_unwritten_workqueue);
 out_destroy_data_iodone_queue:

@@ -790,6 +805,8 @@ STATIC void
 xfs_destroy_mount_workqueues(
 	struct xfs_mount	*mp)
 {
+	destroy_workqueue(mp->m_log_workqueue);
+	destroy_workqueue(mp->m_reclaim_workqueue);
 	destroy_workqueue(mp->m_cil_workqueue);
 	destroy_workqueue(mp->m_data_workqueue);
 	destroy_workqueue(mp->m_unwritten_workqueue);

@@ -1280,10 +1297,6 @@ xfs_fs_fill_super(
 	/*
 	 * we must configure the block size in the superblock before we run the
 	 * full mount process as the mount process can lookup and cache inodes.
-	 * For the same reason we must also initialise the syncd and register
-	 * the inode cache shrinker so that inodes can be reclaimed during
-	 * operations like a quotacheck that iterate all inodes in the
-	 * filesystem.
 	 */
 	sb->s_magic = XFS_SB_MAGIC;
 	sb->s_blocksize = mp->m_sb.sb_blocksize;

@@ -1523,16 +1536,6 @@ STATIC int __init
 xfs_init_workqueues(void)
 {
 	/*
-	 * We never want to the same work item to run twice, reclaiming inodes
-	 * or idling the log is not going to get any faster by multiple CPUs
-	 * competing for ressources.  Use the default large max_active value
-	 * so that even lots of filesystems can perform these task in parallel.
-	 */
-	xfs_syncd_wq = alloc_workqueue("xfssyncd", WQ_NON_REENTRANT, 0);
-	if (!xfs_syncd_wq)
-		return -ENOMEM;
-
-	/*
 	 * The allocation workqueue can be used in memory reclaim situations
 	 * (writepage path), and parallelism is only limited by the number of
 	 * AGs in all the filesystems mounted. Hence use the default large

@@ -1540,20 +1543,15 @@ xfs_init_workqueues(void)
 	 */
 	xfs_alloc_wq = alloc_workqueue("xfsalloc", WQ_MEM_RECLAIM, 0);
 	if (!xfs_alloc_wq)
-		goto out_destroy_syncd;
+		return -ENOMEM;
 
 	return 0;
-
-out_destroy_syncd:
-	destroy_workqueue(xfs_syncd_wq);
-	return -ENOMEM;
 }
 
 STATIC void
 xfs_destroy_workqueues(void)
 {
 	destroy_workqueue(xfs_alloc_wq);
-	destroy_workqueue(xfs_syncd_wq);
 }
 
 STATIC int __init

index 6a2ada3..15be21f 100644
@@ -40,8 +40,6 @@
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 
-struct workqueue_struct	*xfs_syncd_wq;	/* sync workqueue */
-
 /*
  * The inode lookup is done in batches to keep the amount of lock traffic and
  * radix tree lookups to a minimum. The batch size is a trade off between

@@ -335,18 +333,18 @@ xfs_quiesce_attr(
 /*
  * Queue a new inode reclaim pass if there are reclaimable inodes and there
  * isn't a reclaim pass already in progress. By default it runs every 5s based
- * on the xfs syncd work default of 30s. Perhaps this should have it's own
+ * on the xfs periodic sync default of 30s. Perhaps this should have it's own
  * tunable, but that can be done if this method proves to be ineffective or too
  * aggressive.
  */
 static void
-xfs_syncd_queue_reclaim(
+xfs_reclaim_work_queue(
 	struct xfs_mount        *mp)
 {
 
 	rcu_read_lock();
 	if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) {
-		queue_delayed_work(xfs_syncd_wq, &mp->m_reclaim_work,
+		queue_delayed_work(mp->m_reclaim_workqueue, &mp->m_reclaim_work,
 			msecs_to_jiffies(xfs_syncd_centisecs / 6 * 10));
 	}
 	rcu_read_unlock();

@@ -367,7 +365,7 @@ xfs_reclaim_worker(
 					struct xfs_mount, m_reclaim_work);
 
 	xfs_reclaim_inodes(mp, SYNC_TRYLOCK);
-	xfs_syncd_queue_reclaim(mp);
+	xfs_reclaim_work_queue(mp);
 }
 
 void

@@ -388,7 +386,7 @@ __xfs_inode_set_reclaim_tag(
 		spin_unlock(&ip->i_mount->m_perag_lock);
 
 		/* schedule periodic background inode reclaim */
-		xfs_syncd_queue_reclaim(ip->i_mount);
+		xfs_reclaim_work_queue(ip->i_mount);
 
 		trace_xfs_perag_set_reclaim(ip->i_mount, pag->pag_agno,
 							-1, _RET_IP_);

@@ -646,9 +644,9 @@ out:
 	/*
 	 * We could return EAGAIN here to make reclaim rescan the inode tree in
 	 * a short while. However, this just burns CPU time scanning the tree
-	 * waiting for IO to complete and xfssyncd never goes back to the idle
-	 * state. Instead, return 0 to let the next scheduled background reclaim
-	 * attempt to reclaim the inode again.
+	 * waiting for IO to complete and the reclaim work never goes back to
+	 * the idle state. Instead, return 0 to let the next scheduled
+	 * background reclaim attempt to reclaim the inode again.
 	 */
 	return 0;
 }

@@ -804,7 +802,7 @@ xfs_reclaim_inodes_nr(
 	int			nr_to_scan)
 {
 	/* kick background reclaimer and push the AIL */
-	xfs_syncd_queue_reclaim(mp);
+	xfs_reclaim_work_queue(mp);
 	xfs_ail_push_all(mp->m_ail);
 
 	xfs_reclaim_inodes_ag(mp, SYNC_TRYLOCK | SYNC_WAIT, &nr_to_scan);

index 0018e84..0beabea 100644
@@ -24,8 +24,6 @@ struct xfs_perag;
 #define SYNC_WAIT		0x0001	/* wait for i/o to complete */
 #define SYNC_TRYLOCK		0x0002  /* only try to lock inodes */
 
-extern struct workqueue_struct	*xfs_syncd_wq;	/* sync workqueue */
-
 void xfs_reclaim_worker(struct work_struct *work);
 
 int xfs_quiesce_data(struct xfs_mount *mp);

index 65cf42c..1ee7b09 100644
@@ -952,7 +952,6 @@ xfs_fs_sync_fs(
 	int			wait)
 {
 	struct xfs_mount	*mp = XFS_M(sb);
-	int			error;
 
 	/*
 	 * Doing anything during the async pass would be counterproductive.

@@ -960,10 +959,7 @@ xfs_fs_sync_fs(
 	if (!wait)
 		return 0;
 
-	error = xfs_quiesce_data(mp);
-	if (error)
-		return -error;
-
+	xfs_log_force(mp, XFS_LOG_SYNC);
 	if (laptop_mode) {
 		/*
 		 * The disk must be active because we're syncing.

@@ -1127,15 +1123,12 @@ xfs_fs_remount(
 	/* rw -> ro */
 	if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & MS_RDONLY)) {
 		/*
-		 * After we have synced the data but before we sync the
-		 * metadata, we need to free up the reserve block pool so that
-		 * the used block count in the superblock on disk is correct at
-		 * the end of the remount. Stash the current reserve pool size
-		 * so that if we get remounted rw, we can return it to the same
-		 * size.
+		 * Before we sync the metadata, we need to free up the reserve
+		 * block pool so that the used block count in the superblock on
+		 * disk is correct at the end of the remount. Stash the current
+		 * reserve pool size so that if we get remounted rw, we can
+		 * return it to the same size.
 		 */
-
-		xfs_quiesce_data(mp);
 		xfs_save_resvblks(mp);
 		xfs_quiesce_attr(mp);
 		mp->m_flags |= XFS_MOUNT_RDONLY;

84 lines not on this page · raw message

index 1ee7b09..4806e46 100644
@@ -1043,6 +1043,73 @@ xfs_restore_resvblks(struct xfs_mount *mp)
 	xfs_reserve_blocks(mp, &resblks, NULL);
 }
 
+/*
+ * Trigger writeback of all the dirty metadata in the file system.
+ *
+ * This ensures that the metadata is written to their location on disk rather
+ * than just existing in transactions in the log. This means after a quiesce
+ * there is no log replay required to write the inodes to disk (this is the main
+ * difference between a sync and a quiesce).
+ *
+ * This shoul deffectively mimic the code in xfs_unmountfs() and
+ * xfs_log_umount() but without tearing down any structures.
+ * XXX: bug fixes needed!
+ *
+ * Note: this stops background log work - the callers must ensure it is started
+ * again when appropriate.
+ */
+void
+xfs_quiesce_attr(
+	struct xfs_mount	*mp)
+{
+	int	error = 0;
+
+	/* wait for all modifications to complete */
+	while (atomic_read(&mp->m_active_trans) > 0)
+		delay(100);
+
+	/* force the log to unpin objects from the now complete transactions */
+	xfs_log_force(mp, XFS_LOG_SYNC);
+
+	/* reclaim inodes to do any IO before the freeze completes */
+	xfs_reclaim_inodes(mp, 0);
+	xfs_reclaim_inodes(mp, SYNC_WAIT);
+
+	/* flush all pending changes from the AIL */
+	xfs_ail_push_all_sync(mp->m_ail);
+
+	/* stop background log work */
+	cancel_delayed_work_sync(&mp->m_log->l_work);
+
+	/*
+	 * Just warn here till VFS can correctly support
+	 * read-only remount without racing.
+	 */
+	WARN_ON(atomic_read(&mp->m_active_trans) != 0);
+
+	/* Push the superblock and write an unmount record */
+	error = xfs_log_sbcount(mp);
+	if (error)
+		xfs_warn(mp, "xfs_attr_quiesce: failed to log sb changes. "
+				"Frozen image may not be consistent.");
+	xfs_log_unmount_write(mp);
+
+	/*
+	 * At this point we might have modified the superblock again and thus
+	 * added an item to the AIL, thus flush it again.
+	 */
+	xfs_ail_push_all_sync(mp->m_ail);
+
+	/*
+	 * The superblock buffer is uncached and xfsaild_push() will lock and
+	 * set the XBF_ASYNC flag on the buffer. We cannot do xfs_buf_iowait()
+	 * here but a lock on the superblock buffer will block until iodone()
+	 * has completed.
+	 */
+	xfs_buf_lock(mp->m_sb_bp);
+	xfs_buf_unlock(mp->m_sb_bp);
+}
+
 STATIC int
 xfs_fs_remount(
 	struct super_block	*sb,

71 lines not on this page · raw message

index 0beabea..0ba9c89 100644
@@ -26,9 +26,6 @@ struct xfs_perag;
 
 void xfs_reclaim_worker(struct work_struct *work);
 
-int xfs_quiesce_data(struct xfs_mount *mp);
-void xfs_quiesce_attr(struct xfs_mount *mp);
-
 int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);
 int xfs_reclaim_inodes_count(struct xfs_mount *mp);
 void xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);

index 96ea9ed..67d63f6 100644
@@ -853,20 +853,17 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 }	/* xfs_log_unmount_write */
 
 /*
- * Shut down and release the AIL and Log.
- *
- * During unmount, we need to ensure we flush all the dirty metadata objects
- * from the AIL so that the log is empty before we write the unmount record to
- * the log.
+ * Empty the log for unmount/freeze.
  *
  * To do this, we first need to shut down the background log work so it is not
  * trying to cover the log as we clean up. We then need to unpin all objects in
  * the log so we can then flush them out. Once they have completed their IO and
  * run the callbacks removing themselves from the AIL, we can write the unmount
- * record, tear down the AIL and finally free the log.
+ * record.
  */
 void
-xfs_log_unmount(xfs_mount_t *mp)
+xfs_log_quiesce(
+	struct xfs_mount	*mp)
 {
 	cancel_delayed_work_sync(&mp->m_log->l_work);
 	xfs_log_force(mp, XFS_LOG_SYNC);

@@ -884,6 +881,20 @@ xfs_log_unmount(xfs_mount_t *mp)
 	xfs_buf_unlock(mp->m_sb_bp);
 
 	xfs_log_unmount_write(mp);
+}
+
+/*
+ * Shut down and release the AIL and Log.
+ *
+ * During unmount, we need to ensure we flush all the dirty metadata objects
+ * from the AIL so that the log is empty before we write the unmount record to
+ * the log. Once this is done, we can tear down the AIL and the log.
+ */
+void
+xfs_log_unmount(
+	struct xfs_mount	*mp)
+{
+	xfs_log_quiesce(mp);
 
 	xfs_trans_ail_destroy(mp);
 	xlog_dealloc_log(mp->m_log);

index 26ed7de..5caee96 100644
@@ -183,6 +183,7 @@ bool	xfs_log_item_in_current_chkpt(struct xfs_log_item *lip);
 
 void	xfs_log_work_queue(struct xfs_mount *mp);
 void	xfs_log_worker(struct work_struct *work);
+void	xfs_log_quiesce(struct xfs_mount *mp);
 
 #endif
 #endif	/* __XFS_LOG_H__ */

62 lines not on this page · raw message

715 lines not on this page · raw message

43 lines not on this page · raw message

index 784a803..069c5ce 100644
@@ -38,6 +38,7 @@
 #include "xfs_inode_item.h"
 #include "xfs_bmap.h"
 #include "xfs_trace.h"
+#include "xfs_icache.h"
 
 
 /*

index 149b601..7dfbf07 100644
@@ -42,6 +42,7 @@
 #include "xfs_fsops.h"
 #include "xfs_utils.h"
 #include "xfs_trace.h"
+#include "xfs_icache.h"
 
 
 #ifdef HAVE_PERCPU_SB

index 7c417b6..a631ca3 100644
@@ -51,8 +51,6 @@ typedef struct xfs_trans_reservations {
 
 #else /* __KERNEL__ */
 
-#include "xfs_sync.h"
-
 struct xlog;
 struct xfs_inode;
 struct xfs_mru_cache;

index 858a3b1..7a9071f 100644
@@ -40,6 +40,7 @@
 #include "xfs_utils.h"
 #include "xfs_qm.h"
 #include "xfs_trace.h"
+#include "xfs_icache.h"
 
 STATIC int	xfs_qm_log_quotaoff(xfs_mount_t *, xfs_qoff_logitem_t **, uint);
 STATIC int	xfs_qm_log_quotaoff_end(xfs_mount_t *, xfs_qoff_logitem_t *,

index 81de924..ce52520 100644
@@ -49,7 +49,7 @@
 #include "xfs_extfree_item.h"
 #include "xfs_mru_cache.h"
 #include "xfs_inode_item.h"
-#include "xfs_sync.h"
+#include "xfs_icache.h"
 #include "xfs_trace.h"
 
 #include <linux/namei.h>

714 lines not on this page · raw message

43 lines not on this page · raw message

index 069c5ce..ea9a5fa 100644
@@ -453,254 +453,3 @@ out_error_or_again:
 	return error;
 }
 
-/*
- * This is a wrapper routine around the xfs_ilock() routine
- * used to centralize some grungy code.  It is used in places
- * that wish to lock the inode solely for reading the extents.
- * The reason these places can't just call xfs_ilock(SHARED)
- * is that the inode lock also guards to bringing in of the
- * extents from disk for a file in b-tree format.  If the inode
- * is in b-tree format, then we need to lock the inode exclusively
- * until the extents are read in.  Locking it exclusively all
- * the time would limit our parallelism unnecessarily, though.
- * What we do instead is check to see if the extents have been
- * read in yet, and only lock the inode exclusively if they
- * have not.
- *
- * The function returns a value which should be given to the
- * corresponding xfs_iunlock_map_shared().  This value is
- * the mode in which the lock was actually taken.
- */
-uint
-xfs_ilock_map_shared(
-	xfs_inode_t	*ip)
-{
-	uint	lock_mode;
-
-	if ((ip->i_d.di_format == XFS_DINODE_FMT_BTREE) &&
-	    ((ip->i_df.if_flags & XFS_IFEXTENTS) == 0)) {
-		lock_mode = XFS_ILOCK_EXCL;
-	} else {
-		lock_mode = XFS_ILOCK_SHARED;
-	}
-
-	xfs_ilock(ip, lock_mode);
-
-	return lock_mode;
-}
-
-/*
- * This is simply the unlock routine to go with xfs_ilock_map_shared().
- * All it does is call xfs_iunlock() with the given lock_mode.
- */
-void
-xfs_iunlock_map_shared(
-	xfs_inode_t	*ip,
-	unsigned int	lock_mode)
-{
-	xfs_iunlock(ip, lock_mode);
-}
-
-/*
- * The xfs inode contains 2 locks: a multi-reader lock called the
- * i_iolock and a multi-reader lock called the i_lock.  This routine
- * allows either or both of the locks to be obtained.
- *
- * The 2 locks should always be ordered so that the IO lock is
- * obtained first in order to prevent deadlock.
- *
- * ip -- the inode being locked
- * lock_flags -- this parameter indicates the inode's locks
- *       to be locked.  It can be:
- *		XFS_IOLOCK_SHARED,
- *		XFS_IOLOCK_EXCL,
- *		XFS_ILOCK_SHARED,
- *		XFS_ILOCK_EXCL,
- *		XFS_IOLOCK_SHARED | XFS_ILOCK_SHARED,
- *		XFS_IOLOCK_SHARED | XFS_ILOCK_EXCL,
- *		XFS_IOLOCK_EXCL | XFS_ILOCK_SHARED,
- *		XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL
- */
-void
-xfs_ilock(
-	xfs_inode_t		*ip,
-	uint			lock_flags)
-{
-	/*
-	 * You can't set both SHARED and EXCL for the same lock,
-	 * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED,
-	 * and XFS_ILOCK_EXCL are valid values to set in lock_flags.
-	 */
-	ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) !=
-	       (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
-	ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
-	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
-	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0);
-
-	if (lock_flags & XFS_IOLOCK_EXCL)
-		mrupdate_nested(&ip->i_iolock, XFS_IOLOCK_DEP(lock_flags));
-	else if (lock_flags & XFS_IOLOCK_SHARED)
-		mraccess_nested(&ip->i_iolock, XFS_IOLOCK_DEP(lock_flags));
-
-	if (lock_flags & XFS_ILOCK_EXCL)
-		mrupdate_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags));
-	else if (lock_flags & XFS_ILOCK_SHARED)
-		mraccess_nested(&ip->i_lock, XFS_ILOCK_DEP(lock_flags));
-
-	trace_xfs_ilock(ip, lock_flags, _RET_IP_);
-}
-
-/*
- * This is just like xfs_ilock(), except that the caller
- * is guaranteed not to sleep.  It returns 1 if it gets
- * the requested locks and 0 otherwise.  If the IO lock is
- * obtained but the inode lock cannot be, then the IO lock
- * is dropped before returning.
- *
- * ip -- the inode being locked
- * lock_flags -- this parameter indicates the inode's locks to be
- *       to be locked.  See the comment for xfs_ilock() for a list
- *	 of valid values.
- */
-int
-xfs_ilock_nowait(
-	xfs_inode_t		*ip,
-	uint			lock_flags)
-{
-	/*
-	 * You can't set both SHARED and EXCL for the same lock,
-	 * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED,
-	 * and XFS_ILOCK_EXCL are valid values to set in lock_flags.
-	 */
-	ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) !=
-	       (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
-	ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
-	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
-	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0);
-
-	if (lock_flags & XFS_IOLOCK_EXCL) {
-		if (!mrtryupdate(&ip->i_iolock))
-			goto out;
-	} else if (lock_flags & XFS_IOLOCK_SHARED) {
-		if (!mrtryaccess(&ip->i_iolock))
-			goto out;
-	}
-	if (lock_flags & XFS_ILOCK_EXCL) {
-		if (!mrtryupdate(&ip->i_lock))
-			goto out_undo_iolock;
-	} else if (lock_flags & XFS_ILOCK_SHARED) {
-		if (!mrtryaccess(&ip->i_lock))
-			goto out_undo_iolock;
-	}
-	trace_xfs_ilock_nowait(ip, lock_flags, _RET_IP_);
-	return 1;
-
- out_undo_iolock:
-	if (lock_flags & XFS_IOLOCK_EXCL)
-		mrunlock_excl(&ip->i_iolock);
-	else if (lock_flags & XFS_IOLOCK_SHARED)
-		mrunlock_shared(&ip->i_iolock);
- out:
-	return 0;
-}
-
-/*
- * xfs_iunlock() is used to drop the inode locks acquired with
- * xfs_ilock() and xfs_ilock_nowait().  The caller must pass
- * in the flags given to xfs_ilock() or xfs_ilock_nowait() so
- * that we know which locks to drop.
- *
- * ip -- the inode being unlocked
- * lock_flags -- this parameter indicates the inode's locks to be
- *       to be unlocked.  See the comment for xfs_ilock() for a list
- *	 of valid values for this parameter.
- *
- */
-void
-xfs_iunlock(
-	xfs_inode_t		*ip,
-	uint			lock_flags)
-{
-	/*
-	 * You can't set both SHARED and EXCL for the same lock,
-	 * and only XFS_IOLOCK_SHARED, XFS_IOLOCK_EXCL, XFS_ILOCK_SHARED,
-	 * and XFS_ILOCK_EXCL are valid values to set in lock_flags.
-	 */
-	ASSERT((lock_flags & (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL)) !=
-	       (XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
-	ASSERT((lock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL)) !=
-	       (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
-	ASSERT((lock_flags & ~(XFS_LOCK_MASK | XFS_LOCK_DEP_MASK)) == 0);
-	ASSERT(lock_flags != 0);
-
-	if (lock_flags & XFS_IOLOCK_EXCL)
-		mrunlock_excl(&ip->i_iolock);
-	else if (lock_flags & XFS_IOLOCK_SHARED)
-		mrunlock_shared(&ip->i_iolock);
-
-	if (lock_flags & XFS_ILOCK_EXCL)
-		mrunlock_excl(&ip->i_lock);
-	else if (lock_flags & XFS_ILOCK_SHARED)
-		mrunlock_shared(&ip->i_lock);
-
-	trace_xfs_iunlock(ip, lock_flags, _RET_IP_);
-}
-
-/*
- * give up write locks.  the i/o lock cannot be held nested
- * if it is being demoted.
- */
-void
-xfs_ilock_demote(
-	xfs_inode_t		*ip,
-	uint			lock_flags)
-{
-	ASSERT(lock_flags & (XFS_IOLOCK_EXCL|XFS_ILOCK_EXCL));
-	ASSERT((lock_flags & ~(XFS_IOLOCK_EXCL|XFS_ILOCK_EXCL)) == 0);
-
-	if (lock_flags & XFS_ILOCK_EXCL)
-		mrdemote(&ip->i_lock);
-	if (lock_flags & XFS_IOLOCK_EXCL)
-		mrdemote(&ip->i_iolock);
-
-	trace_xfs_ilock_demote(ip, lock_flags, _RET_IP_);
-}
-
-#ifdef DEBUG
-int
-xfs_isilocked(
-	xfs_inode_t		*ip,
-	uint			lock_flags)
-{
-	if (lock_flags & (XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)) {
-		if (!(lock_flags & XFS_ILOCK_SHARED))
-			return !!ip->i_lock.mr_writer;
-		return rwsem_is_locked(&ip->i_lock.mr_lock);
-	}
-
-	if (lock_flags & (XFS_IOLOCK_EXCL|XFS_IOLOCK_SHARED)) {
-		if (!(lock_flags & XFS_IOLOCK_SHARED))
-			return !!ip->i_iolock.mr_writer;
-		return rwsem_is_locked(&ip->i_iolock.mr_lock);
-	}
-
-	ASSERT(0);
-	return 0;
-}
-#endif
-
-void
-__xfs_iflock(
-	struct xfs_inode	*ip)
-{
-	wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_IFLOCK_BIT);
-	DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IFLOCK_BIT);
-
-	do {
-		prepare_to_wait_exclusive(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
-		if (xfs_isiflocked(ip))
-			io_schedule();
-	} while (!xfs_iflock_nowait(ip));
-
-	finish_wait(wq, &wait.wait);
-}

256 lines not on this page · raw message

index 4267922..9b6e330 100644
@@ -29,6 +29,7 @@
 #include "xfs_inode.h"
 #include "xfs_inode_item.h"
 #include "xfs_trace.h"
+#include "xfs_icache.h"
 
 /*
  * Note that we only accept fileids which are long enough rather than allow

445 lines not on this page · raw message

index 0ba9c89..222e22f 100644
@@ -24,6 +24,9 @@ struct xfs_perag;
 #define SYNC_WAIT		0x0001	/* wait for i/o to complete */
 #define SYNC_TRYLOCK		0x0002  /* only try to lock inodes */
 
+int xfs_iget(struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino,
+	     uint flags, uint lock_flags, xfs_inode_t **ipp);
+
 void xfs_reclaim_worker(struct work_struct *work);
 
 int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);

@@ -31,9 +34,6 @@ int xfs_reclaim_inodes_count(struct xfs_mount *mp);
 void xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan);
 
 void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
-void __xfs_inode_set_reclaim_tag(struct xfs_perag *pag, struct xfs_inode *ip);
-void __xfs_inode_clear_reclaim_tag(struct xfs_mount *mp, struct xfs_perag *pag,
-				struct xfs_inode *ip);
 
 int xfs_sync_inode_grab(struct xfs_inode *ip);
 int xfs_inode_ag_iterator(struct xfs_mount *mp,

455 lines not on this page · raw message

index ba404e4..bba8f37 100644
@@ -45,6 +45,7 @@
 #include "xfs_filestream.h"
 #include "xfs_vnodeops.h"
 #include "xfs_trace.h"
+#include "xfs_icache.h"
 
 kmem_zone_t *xfs_ifork_zone;
 kmem_zone_t *xfs_inode_zone;

index a12fe18..da69c18 100644
@@ -506,11 +506,10 @@ static inline int xfs_isiflocked(struct xfs_inode *ip)
 	(((pip)->i_mount->m_flags & XFS_MOUNT_GRPID) || \
 	 ((pip)->i_d.di_mode & S_ISGID))
 
+
 /*
- * xfs_iget.c prototypes.
+ * xfs_inode.c prototypes.
  */
-int		xfs_iget(struct xfs_mount *, struct xfs_trans *, xfs_ino_t,
-			 uint, uint, xfs_inode_t **);
 void		xfs_ilock(xfs_inode_t *, uint);
 int		xfs_ilock_nowait(xfs_inode_t *, uint);
 void		xfs_iunlock(xfs_inode_t *, uint);

@@ -518,11 +517,6 @@ void		xfs_ilock_demote(xfs_inode_t *, uint);
 int		xfs_isilocked(xfs_inode_t *, uint);
 uint		xfs_ilock_map_shared(xfs_inode_t *);
 void		xfs_iunlock_map_shared(xfs_inode_t *, uint);
-void		xfs_inode_free(struct xfs_inode *ip);
-
-/*
- * xfs_inode.c prototypes.
- */
 int		xfs_ialloc(struct xfs_trans *, xfs_inode_t *, umode_t,
 			   xfs_nlink_t, xfs_dev_t, prid_t, int,
 			   struct xfs_buf **, xfs_inode_t **);

index 01d10a6..3998fd2 100644
@@ -34,6 +34,7 @@
 #include "xfs_error.h"
 #include "xfs_btree.h"
 #include "xfs_trace.h"
+#include "xfs_icache.h"
 
 STATIC int
 xfs_internal_inum(

index 5da3ace..651c988 100644
@@ -42,6 +42,7 @@
 #include "xfs_quota.h"
 #include "xfs_utils.h"
 #include "xfs_trace.h"
+#include "xfs_icache.h"
 
 STATIC int
 xlog_find_zeroed(

index 2e86fa0..48c750b 100644
@@ -40,6 +40,7 @@
 #include "xfs_utils.h"
 #include "xfs_qm.h"
 #include "xfs_trace.h"
+#include "xfs_icache.h"
 
 /*
  * The global quota manager. There is only one of these for the entire

index ca28a4b..a69e0b4 100644
@@ -38,6 +38,7 @@
 #include "xfs_utils.h"
 #include "xfs_trace.h"
 #include "xfs_buf.h"
+#include "xfs_icache.h"
 
 
 /*

index 2a5c6373..e9cae13 100644
@@ -47,6 +47,7 @@
 #include "xfs_filestream.h"
 #include "xfs_vnodeops.h"
 #include "xfs_trace.h"
+#include "xfs_icache.h"
 
 /*
  * The maximum pathlen is 1024 bytes. Since the minimum file system