xfs: don't run speculative preallocation gc when fs is frozen

Now that we have the infrastructure to switch background workers on and
off at will, fix the block gc worker code so that we don't actually run
the worker when the filesystem is frozen, same as we do for deferred
inactivation.
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>

fs/xfs/scrub/common.c

@@ -893,11 +893,12 @@ xchk_start_reaping(
 	struct xfs_scrub	*sc)
 {
 	/*
-	 * Readonly filesystems do not perform inactivation, so there's no
-	 * need to restart the worker.
+	 * Readonly filesystems do not perform inactivation or speculative
+	 * preallocation, so there's no need to restart the workers.
 	 */
-	if (!(sc->mp->m_flags & XFS_MOUNT_RDONLY))
+	if (!(sc->mp->m_flags & XFS_MOUNT_RDONLY)) {
 		xfs_inodegc_start(sc->mp);
 		xfs_blockgc_start(sc->mp);
+	}
 	sc->flags &= ~XCHK_REAPING_DISABLED;
 }

fs/xfs/xfs_icache.c

@@ -211,6 +211,11 @@ static inline void
 xfs_blockgc_queue(
 	struct xfs_perag	*pag)
 {
+	struct xfs_mount	*mp = pag->pag_mount;
+
+	if (!xfs_is_blockgc_enabled(mp))
+		return;
+
 	rcu_read_lock();
 	if (radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_BLOCKGC_TAG))
 		queue_delayed_work(pag->pag_mount->m_blockgc_wq,
@@ -1366,8 +1371,12 @@ xfs_blockgc_stop(
 	struct xfs_perag	*pag;
 	xfs_agnumber_t		agno;
 
-	for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG)
+	if (!xfs_clear_blockgc_enabled(mp))
+		return;
+
+	for_each_perag(mp, agno, pag)
 		cancel_delayed_work_sync(&pag->pag_blockgc_work);
+	trace_xfs_blockgc_stop(mp, __return_address);
 }
 
 /* Enable post-EOF and CoW block auto-reclamation. */
@@ -1378,6 +1387,10 @@ xfs_blockgc_start(
 	struct xfs_perag	*pag;
 	xfs_agnumber_t		agno;
 
+	if (xfs_set_blockgc_enabled(mp))
+		return;
+
+	trace_xfs_blockgc_start(mp, __return_address);
 	for_each_perag_tag(mp, agno, pag, XFS_ICI_BLOCKGC_TAG)
 		xfs_blockgc_queue(pag);
 }
@@ -1457,13 +1470,12 @@ xfs_blockgc_worker(
 	struct xfs_mount	*mp = pag->pag_mount;
 	int			error;
 
-	if (!sb_start_write_trylock(mp->m_super))
-		return;
+	trace_xfs_blockgc_worker(mp, __return_address);
+
 	error = xfs_icwalk_ag(pag, XFS_ICWALK_BLOCKGC, NULL);
 	if (error)
 		xfs_info(mp, "AG %u preallocation gc worker failed, err=%d",
 				pag->pag_agno, error);
-	sb_end_write(mp->m_super);
 	xfs_blockgc_queue(pag);
 }
 

fs/xfs/xfs_mount.c

@@ -789,6 +789,7 @@ xfs_mountfs(
 
 	/* Enable background inode inactivation workers. */
 	xfs_inodegc_start(mp);
+	xfs_blockgc_start(mp);
 
 	/*
 	 * Get and sanity-check the root inode.

fs/xfs/xfs_mount.h

@@ -281,6 +281,12 @@ typedef struct xfs_mount {
  * processed.
  */
 #define XFS_OPSTATE_INODEGC_ENABLED	0
+/*
+ * If set, background speculative prealloc gc worker threads will be scheduled
+ * to process queued blockgc work.  If not, inodes retain their preallocations
+ * until explicitly deleted.
+ */
+#define XFS_OPSTATE_BLOCKGC_ENABLED	1
 
 #define __XFS_IS_OPSTATE(name, NAME) \
 static inline bool xfs_is_ ## name (struct xfs_mount *mp) \
@@ -297,9 +303,11 @@ static inline bool xfs_set_ ## name (struct xfs_mount *mp) \
 }
 
 __XFS_IS_OPSTATE(inodegc_enabled, INODEGC_ENABLED)
+__XFS_IS_OPSTATE(blockgc_enabled, BLOCKGC_ENABLED)
 
 #define XFS_OPSTATE_STRINGS \
-	{ (1UL << XFS_OPSTATE_INODEGC_ENABLED),		"inodegc" }
+	{ (1UL << XFS_OPSTATE_INODEGC_ENABLED),		"inodegc" }, \
+	{ (1UL << XFS_OPSTATE_BLOCKGC_ENABLED),		"blockgc" }
 
 /*
  * Max and min values for mount-option defined I/O

fs/xfs/xfs_super.c

@@ -757,15 +757,18 @@ xfs_fs_sync_fs(
 	 * down inodegc because once SB_FREEZE_FS is set it's too late to
 	 * prevent inactivation races with freeze. The fs doesn't get called
 	 * again by the freezing process until after SB_FREEZE_FS has been set,
-	 * so it's now or never.
+	 * so it's now or never.  Same logic applies to speculative allocation
+	 * garbage collection.
 	 *
 	 * We don't care if this is a normal syncfs call that does this or
 	 * freeze that does this - we can run this multiple times without issue
 	 * and we won't race with a restart because a restart can only occur
 	 * when the state is either SB_FREEZE_FS or SB_FREEZE_COMPLETE.
 	 */
-	if (sb->s_writers.frozen == SB_FREEZE_PAGEFAULT)
+	if (sb->s_writers.frozen == SB_FREEZE_PAGEFAULT) {
 		xfs_inodegc_stop(mp);
+		xfs_blockgc_stop(mp);
+	}
 
 	return 0;
 }
@@ -883,7 +886,6 @@ xfs_fs_freeze(
 	 * set a GFP_NOFS context here to avoid recursion deadlocks.
 	 */
 	flags = memalloc_nofs_save();
-	xfs_blockgc_stop(mp);
 	xfs_save_resvblks(mp);
 	ret = xfs_log_quiesce(mp);
 	memalloc_nofs_restore(flags);
@@ -895,8 +897,10 @@ xfs_fs_freeze(
 	 * here, so we can restart safely without racing with a stop in
 	 * xfs_fs_sync_fs().
 	 */
-	if (ret && !(mp->m_flags & XFS_MOUNT_RDONLY))
+	if (ret && !(mp->m_flags & XFS_MOUNT_RDONLY)) {
+		xfs_blockgc_start(mp);
 		xfs_inodegc_start(mp);
+	}
 
 	return ret;
 }
@@ -909,14 +913,17 @@ xfs_fs_unfreeze(
 
 	xfs_restore_resvblks(mp);
 	xfs_log_work_queue(mp);
-	xfs_blockgc_start(mp);
 
 	/*
 	 * Don't reactivate the inodegc worker on a readonly filesystem because
-	 * inodes are sent directly to reclaim.
+	 * inodes are sent directly to reclaim.  Don't reactivate the blockgc
+	 * worker because there are no speculative preallocations on a readonly
+	 * filesystem.
 	 */
-	if (!(mp->m_flags & XFS_MOUNT_RDONLY))
+	if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
+		xfs_blockgc_start(mp);
 		xfs_inodegc_start(mp);
+	}
 
 	return 0;
 }

fs/xfs/xfs_trace.h

@@ -195,6 +195,9 @@ DEFINE_FS_EVENT(xfs_inodegc_worker);
 DEFINE_FS_EVENT(xfs_inodegc_queue);
 DEFINE_FS_EVENT(xfs_inodegc_throttle);
 DEFINE_FS_EVENT(xfs_fs_sync_fs);
+DEFINE_FS_EVENT(xfs_blockgc_start);
+DEFINE_FS_EVENT(xfs_blockgc_stop);
+DEFINE_FS_EVENT(xfs_blockgc_worker);
 
 DECLARE_EVENT_CLASS(xfs_ag_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno),