1 files changed, 373 insertions, 80 deletions

diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index f71679ce23..66a17910d0 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -26,6 +26,7 @@
 #include "xfs_da_format.h"
 #include "xfs_da_btree.h"
 #include "xfs_attr.h"
+#include "xfs_trans_priv.h"
 
 static struct kmem_cache	*xfs_defer_pending_cache;
 
@@ -181,16 +182,89 @@ static struct kmem_cache	*xfs_defer_pending_cache;
  * Note that the continuation requested between t2 and t3 is likely to
  * reoccur.
  */
+STATIC struct xfs_log_item *
+xfs_defer_barrier_create_intent(
+	struct xfs_trans		*tp,
+	struct list_head		*items,
+	unsigned int			count,
+	bool				sort)
+{
+	return NULL;
+}
 
-static const struct xfs_defer_op_type *defer_op_types[] = {
-	[XFS_DEFER_OPS_TYPE_BMAP]	= &xfs_bmap_update_defer_type,
-	[XFS_DEFER_OPS_TYPE_REFCOUNT]	= &xfs_refcount_update_defer_type,
-	[XFS_DEFER_OPS_TYPE_RMAP]	= &xfs_rmap_update_defer_type,
-	[XFS_DEFER_OPS_TYPE_FREE]	= &xfs_extent_free_defer_type,
-	[XFS_DEFER_OPS_TYPE_AGFL_FREE]	= &xfs_agfl_free_defer_type,
-	[XFS_DEFER_OPS_TYPE_ATTR]	= &xfs_attr_defer_type,
+STATIC void
+xfs_defer_barrier_abort_intent(
+	struct xfs_log_item		*intent)
+{
+	/* empty */
+}
+
+STATIC struct xfs_log_item *
+xfs_defer_barrier_create_done(
+	struct xfs_trans		*tp,
+	struct xfs_log_item		*intent,
+	unsigned int			count)
+{
+	return NULL;
+}
+
+STATIC int
+xfs_defer_barrier_finish_item(
+	struct xfs_trans		*tp,
+	struct xfs_log_item		*done,
+	struct list_head		*item,
+	struct xfs_btree_cur		**state)
+{
+	ASSERT(0);
+	return -EFSCORRUPTED;
+}
+
+STATIC void
+xfs_defer_barrier_cancel_item(
+	struct list_head		*item)
+{
+	ASSERT(0);
+}
+
+static const struct xfs_defer_op_type xfs_barrier_defer_type = {
+	.max_items	= 1,
+	.create_intent	= xfs_defer_barrier_create_intent,
+	.abort_intent	= xfs_defer_barrier_abort_intent,
+	.create_done	= xfs_defer_barrier_create_done,
+	.finish_item	= xfs_defer_barrier_finish_item,
+	.cancel_item	= xfs_defer_barrier_cancel_item,
 };
 
+/* Create a log intent done item for a log intent item. */
+static inline void
+xfs_defer_create_done(
+	struct xfs_trans		*tp,
+	struct xfs_defer_pending	*dfp)
+{
+	struct xfs_log_item		*lip;
+
+	/* If there is no log intent item, there can be no log done item. */
+	if (!dfp->dfp_intent)
+		return;
+
+	/*
+	 * Mark the transaction dirty, even on error. This ensures the
+	 * transaction is aborted, which:
+	 *
+	 * 1.) releases the log intent item and frees the log done item
+	 * 2.) shuts down the filesystem
+	 */
+	tp->t_flags |= XFS_TRANS_DIRTY;
+	lip = dfp->dfp_ops->create_done(tp, dfp->dfp_intent, dfp->dfp_count);
+	if (!lip)
+		return;
+
+	tp->t_flags |= XFS_TRANS_HAS_INTENT_DONE;
+	xfs_trans_add_item(tp, lip);
+	set_bit(XFS_LI_DIRTY, &lip->li_flags);
+	dfp->dfp_done = lip;
+}
+
 /*
  * Ensure there's a log intent item associated with this deferred work item if
  * the operation must be restarted on crash.  Returns 1 if there's a log item;
@@ -202,18 +276,21 @@ xfs_defer_create_intent(
 	struct xfs_defer_pending	*dfp,
 	bool				sort)
 {
-	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
 	struct xfs_log_item		*lip;
 
 	if (dfp->dfp_intent)
 		return 1;
 
-	lip = ops->create_intent(tp, &dfp->dfp_work, dfp->dfp_count, sort);
+	lip = dfp->dfp_ops->create_intent(tp, &dfp->dfp_work, dfp->dfp_count,
+			sort);
 	if (!lip)
 		return 0;
 	if (IS_ERR(lip))
 		return PTR_ERR(lip);
 
+	tp->t_flags |= XFS_TRANS_DIRTY;
+	xfs_trans_add_item(tp, lip);
+	set_bit(XFS_LI_DIRTY, &lip->li_flags);
 	dfp->dfp_intent = lip;
 	return 1;
 }
@@ -245,23 +322,50 @@ xfs_defer_create_intents(
 	return ret;
 }
 
-STATIC void
+static inline void
 xfs_defer_pending_abort(
 	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp)
+{
+	trace_xfs_defer_pending_abort(mp, dfp);
+
+	if (dfp->dfp_intent && !dfp->dfp_done) {
+		dfp->dfp_ops->abort_intent(dfp->dfp_intent);
+		dfp->dfp_intent = NULL;
+	}
+}
+
+static inline void
+xfs_defer_pending_cancel_work(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp)
+{
+	struct list_head		*pwi;
+	struct list_head		*n;
+
+	trace_xfs_defer_cancel_list(mp, dfp);
+
+	list_del(&dfp->dfp_list);
+	list_for_each_safe(pwi, n, &dfp->dfp_work) {
+		list_del(pwi);
+		dfp->dfp_count--;
+		trace_xfs_defer_cancel_item(mp, dfp, pwi);
+		dfp->dfp_ops->cancel_item(pwi);
+	}
+	ASSERT(dfp->dfp_count == 0);
+	kmem_cache_free(xfs_defer_pending_cache, dfp);
+}
+
+STATIC void
+xfs_defer_pending_abort_list(
+	struct xfs_mount		*mp,
 	struct list_head		*dop_list)
 {
 	struct xfs_defer_pending	*dfp;
-	const struct xfs_defer_op_type	*ops;
 
 	/* Abort intent items that don't have a done item. */
-	list_for_each_entry(dfp, dop_list, dfp_list) {
-		ops = defer_op_types[dfp->dfp_type];
-		trace_xfs_defer_pending_abort(mp, dfp);
-		if (dfp->dfp_intent && !dfp->dfp_done) {
-			ops->abort_intent(dfp->dfp_intent);
-			dfp->dfp_intent = NULL;
-		}
-	}
+	list_for_each_entry(dfp, dop_list, dfp_list)
+		xfs_defer_pending_abort(mp, dfp);
 }
 
 /* Abort all the intents that were committed. */
@@ -271,7 +375,7 @@ xfs_defer_trans_abort(
 	struct list_head		*dop_pending)
 {
 	trace_xfs_defer_trans_abort(tp, _RET_IP_);
-	xfs_defer_pending_abort(tp->t_mountp, dop_pending);
+	xfs_defer_pending_abort_list(tp->t_mountp, dop_pending);
 }
 
 /*
@@ -389,27 +493,31 @@ xfs_defer_cancel_list(
 {
 	struct xfs_defer_pending	*dfp;
 	struct xfs_defer_pending	*pli;
-	struct list_head		*pwi;
-	struct list_head		*n;
-	const struct xfs_defer_op_type	*ops;
 
 	/*
 	 * Free the pending items.  Caller should already have arranged
 	 * for the intent items to be released.
 	 */
-	list_for_each_entry_safe(dfp, pli, dop_list, dfp_list) {
-		ops = defer_op_types[dfp->dfp_type];
-		trace_xfs_defer_cancel_list(mp, dfp);
-		list_del(&dfp->dfp_list);
-		list_for_each_safe(pwi, n, &dfp->dfp_work) {
-			list_del(pwi);
-			dfp->dfp_count--;
-			trace_xfs_defer_cancel_item(mp, dfp, pwi);
-			ops->cancel_item(pwi);
-		}
-		ASSERT(dfp->dfp_count == 0);
-		kmem_cache_free(xfs_defer_pending_cache, dfp);
+	list_for_each_entry_safe(dfp, pli, dop_list, dfp_list)
+		xfs_defer_pending_cancel_work(mp, dfp);
+}
+
+static inline void
+xfs_defer_relog_intent(
+	struct xfs_trans		*tp,
+	struct xfs_defer_pending	*dfp)
+{
+	struct xfs_log_item		*lip;
+
+	xfs_defer_create_done(tp, dfp);
+
+	lip = dfp->dfp_ops->relog_intent(tp, dfp->dfp_intent, dfp->dfp_done);
+	if (lip) {
+		xfs_trans_add_item(tp, lip);
+		set_bit(XFS_LI_DIRTY, &lip->li_flags);
 	}
+	dfp->dfp_done = NULL;
+	dfp->dfp_intent = lip;
 }
 
 /*
@@ -417,7 +525,7 @@ xfs_defer_cancel_list(
  * done item to release the intent item; and then log a new intent item.
  * The caller should provide a fresh transaction and roll it after we're done.
  */
-static int
+static void
 xfs_defer_relog(
 	struct xfs_trans		**tpp,
 	struct list_head		*dfops)
@@ -456,31 +564,28 @@ xfs_defer_relog(
 
 		trace_xfs_defer_relog_intent((*tpp)->t_mountp, dfp);
 		XFS_STATS_INC((*tpp)->t_mountp, defer_relog);
-		dfp->dfp_intent = xfs_trans_item_relog(dfp->dfp_intent, *tpp);
-	}
 
-	if ((*tpp)->t_flags & XFS_TRANS_DIRTY)
-		return xfs_defer_trans_roll(tpp);
-	return 0;
+		xfs_defer_relog_intent(*tpp, dfp);
+	}
 }
 
 /*
  * Log an intent-done item for the first pending intent, and finish the work
  * items.
  */
-static int
+int
 xfs_defer_finish_one(
 	struct xfs_trans		*tp,
 	struct xfs_defer_pending	*dfp)
 {
-	const struct xfs_defer_op_type	*ops = defer_op_types[dfp->dfp_type];
+	const struct xfs_defer_op_type	*ops = dfp->dfp_ops;
 	struct xfs_btree_cur		*state = NULL;
 	struct list_head		*li, *n;
 	int				error;
 
 	trace_xfs_defer_pending_finish(tp->t_mountp, dfp);
 
-	dfp->dfp_done = ops->create_done(tp, dfp->dfp_intent, dfp->dfp_count);
+	xfs_defer_create_done(tp, dfp);
 	list_for_each_safe(li, n, &dfp->dfp_work) {
 		list_del(li);
 		dfp->dfp_count--;
@@ -517,6 +622,24 @@ out:
 	return error;
 }
 
+/* Move all paused deferred work from @tp to @paused_list. */
+static void
+xfs_defer_isolate_paused(
+	struct xfs_trans		*tp,
+	struct list_head		*paused_list)
+{
+	struct xfs_defer_pending	*dfp;
+	struct xfs_defer_pending	*pli;
+
+	list_for_each_entry_safe(dfp, pli, &tp->t_dfops, dfp_list) {
+		if (!(dfp->dfp_flags & XFS_DEFER_PAUSED))
+			continue;
+
+		list_move_tail(&dfp->dfp_list, paused_list);
+		trace_xfs_defer_isolate_paused(tp->t_mountp, dfp);
+	}
+}
+
 /*
  * Finish all the pending work.  This involves logging intent items for
  * any work items that wandered in since the last transaction roll (if
@@ -532,6 +655,7 @@ xfs_defer_finish_noroll(
 	struct xfs_defer_pending	*dfp = NULL;
 	int				error = 0;
 	LIST_HEAD(dop_pending);
+	LIST_HEAD(dop_paused);
 
 	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
 
@@ -550,6 +674,8 @@ xfs_defer_finish_noroll(
 		 */
 		int has_intents = xfs_defer_create_intents(*tp);
 
+		xfs_defer_isolate_paused(*tp, &dop_paused);
+
 		list_splice_init(&(*tp)->t_dfops, &dop_pending);
 
 		if (has_intents < 0) {
@@ -562,22 +688,33 @@ xfs_defer_finish_noroll(
 				goto out_shutdown;
 
 			/* Relog intent items to keep the log moving. */
-			error = xfs_defer_relog(tp, &dop_pending);
-			if (error)
-				goto out_shutdown;
+			xfs_defer_relog(tp, &dop_pending);
+			xfs_defer_relog(tp, &dop_paused);
+
+			if ((*tp)->t_flags & XFS_TRANS_DIRTY) {
+				error = xfs_defer_trans_roll(tp);
+				if (error)
+					goto out_shutdown;
+			}
 		}
 
-		dfp = list_first_entry(&dop_pending, struct xfs_defer_pending,
-				       dfp_list);
+		dfp = list_first_entry_or_null(&dop_pending,
+				struct xfs_defer_pending, dfp_list);
+		if (!dfp)
+			break;
 		error = xfs_defer_finish_one(*tp, dfp);
 		if (error && error != -EAGAIN)
 			goto out_shutdown;
 	}
 
+	/* Requeue the paused items in the outgoing transaction. */
+	list_splice_tail_init(&dop_paused, &(*tp)->t_dfops);
+
 	trace_xfs_defer_finish_done(*tp, _RET_IP_);
 	return 0;
 
 out_shutdown:
+	list_splice_tail_init(&dop_paused, &dop_pending);
 	xfs_defer_trans_abort(*tp, &dop_pending);
 	xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE);
 	trace_xfs_defer_finish_error(*tp, error);
@@ -590,6 +727,9 @@ int
 xfs_defer_finish(
 	struct xfs_trans	**tp)
 {
+#ifdef DEBUG
+	struct xfs_defer_pending *dfp;
+#endif
 	int			error;
 
 	/*
@@ -609,7 +749,10 @@ xfs_defer_finish(
 	}
 
 	/* Reset LOWMODE now that we've finished all the dfops. */
-	ASSERT(list_empty(&(*tp)->t_dfops));
+#ifdef DEBUG
+	list_for_each_entry(dfp, &(*tp)->t_dfops, dfp_list)
+		ASSERT(dfp->dfp_flags & XFS_DEFER_PAUSED);
+#endif
 	(*tp)->t_flags &= ~XFS_TRANS_LOWMODE;
 	return 0;
 }
@@ -621,48 +764,165 @@ xfs_defer_cancel(
 	struct xfs_mount	*mp = tp->t_mountp;
 
 	trace_xfs_defer_cancel(tp, _RET_IP_);
+	xfs_defer_trans_abort(tp, &tp->t_dfops);
 	xfs_defer_cancel_list(mp, &tp->t_dfops);
 }
 
+/*
+ * Return the last pending work item attached to this transaction if it matches
+ * the deferred op type.
+ */
+static inline struct xfs_defer_pending *
+xfs_defer_find_last(
+	struct xfs_trans		*tp,
+	const struct xfs_defer_op_type	*ops)
+{
+	struct xfs_defer_pending	*dfp = NULL;
+
+	/* No dfops at all? */
+	if (list_empty(&tp->t_dfops))
+		return NULL;
+
+	dfp = list_last_entry(&tp->t_dfops, struct xfs_defer_pending,
+			dfp_list);
+
+	/* Wrong type? */
+	if (dfp->dfp_ops != ops)
+		return NULL;
+	return dfp;
+}
+
+/*
+ * Decide if we can add a deferred work item to the last dfops item attached
+ * to the transaction.
+ */
+static inline bool
+xfs_defer_can_append(
+	struct xfs_defer_pending	*dfp,
+	const struct xfs_defer_op_type	*ops)
+{
+	/* Already logged? */
+	if (dfp->dfp_intent)
+		return false;
+
+	/* Paused items cannot absorb more work */
+	if (dfp->dfp_flags & XFS_DEFER_PAUSED)
+		return NULL;
+
+	/* Already full? */
+	if (ops->max_items && dfp->dfp_count >= ops->max_items)
+		return false;
+
+	return true;
+}
+
+/* Create a new pending item at the end of the transaction list. */
+static inline struct xfs_defer_pending *
+xfs_defer_alloc(
+	struct xfs_trans		*tp,
+	const struct xfs_defer_op_type	*ops)
+{
+	struct xfs_defer_pending	*dfp;
+
+	dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
+			GFP_NOFS | __GFP_NOFAIL);
+	dfp->dfp_ops = ops;
+	INIT_LIST_HEAD(&dfp->dfp_work);
+	list_add_tail(&dfp->dfp_list, &tp->t_dfops);
+
+	return dfp;
+}
+
 /* Add an item for later deferred processing. */
-void
+struct xfs_defer_pending *
 xfs_defer_add(
 	struct xfs_trans		*tp,
-	enum xfs_defer_ops_type		type,
-	struct list_head		*li)
+	struct list_head		*li,
+	const struct xfs_defer_op_type	*ops)
 {
 	struct xfs_defer_pending	*dfp = NULL;
-	const struct xfs_defer_op_type	*ops = defer_op_types[type];
 
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
-	BUILD_BUG_ON(ARRAY_SIZE(defer_op_types) != XFS_DEFER_OPS_TYPE_MAX);
 
-	/*
-	 * Add the item to a pending item at the end of the intake list.
-	 * If the last pending item has the same type, reuse it.  Else,
-	 * create a new pending item at the end of the intake list.
-	 */
-	if (!list_empty(&tp->t_dfops)) {
-		dfp = list_last_entry(&tp->t_dfops,
-				struct xfs_defer_pending, dfp_list);
-		if (dfp->dfp_type != type ||
-		    (ops->max_items && dfp->dfp_count >= ops->max_items))
-			dfp = NULL;
-	}
-	if (!dfp) {
-		dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
-				GFP_NOFS | __GFP_NOFAIL);
-		dfp->dfp_type = type;
-		dfp->dfp_intent = NULL;
-		dfp->dfp_done = NULL;
-		dfp->dfp_count = 0;
-		INIT_LIST_HEAD(&dfp->dfp_work);
-		list_add_tail(&dfp->dfp_list, &tp->t_dfops);
-	}
+	dfp = xfs_defer_find_last(tp, ops);
+	if (!dfp || !xfs_defer_can_append(dfp, ops))
+		dfp = xfs_defer_alloc(tp, ops);
 
-	list_add_tail(li, &dfp->dfp_work);
+	xfs_defer_add_item(dfp, li);
 	trace_xfs_defer_add_item(tp->t_mountp, dfp, li);
-	dfp->dfp_count++;
+	return dfp;
+}
+
+/*
+ * Add a defer ops barrier to force two otherwise adjacent deferred work items
+ * to be tracked separately and have separate log items.
+ */
+void
+xfs_defer_add_barrier(
+	struct xfs_trans		*tp)
+{
+	struct xfs_defer_pending	*dfp;
+
+	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
+
+	/* If the last defer op added was a barrier, we're done. */
+	dfp = xfs_defer_find_last(tp, &xfs_barrier_defer_type);
+	if (dfp)
+		return;
+
+	xfs_defer_alloc(tp, &xfs_barrier_defer_type);
+
+	trace_xfs_defer_add_item(tp->t_mountp, dfp, NULL);
+}
+
+/*
+ * Create a pending deferred work item to replay the recovered intent item
+ * and add it to the list.
+ */
+void
+xfs_defer_start_recovery(
+	struct xfs_log_item		*lip,
+	struct list_head		*r_dfops,
+	const struct xfs_defer_op_type	*ops)
+{
+	struct xfs_defer_pending	*dfp;
+
+	dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
+			GFP_NOFS | __GFP_NOFAIL);
+	dfp->dfp_ops = ops;
+	dfp->dfp_intent = lip;
+	INIT_LIST_HEAD(&dfp->dfp_work);
+	list_add_tail(&dfp->dfp_list, r_dfops);
+}
+
+/*
+ * Cancel a deferred work item created to recover a log intent item.  @dfp
+ * will be freed after this function returns.
+ */
+void
+xfs_defer_cancel_recovery(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp)
+{
+	xfs_defer_pending_abort(mp, dfp);
+	xfs_defer_pending_cancel_work(mp, dfp);
+}
+
+/* Replay the deferred work item created from a recovered log intent item. */
+int
+xfs_defer_finish_recovery(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp,
+	struct list_head		*capture_list)
+{
+	const struct xfs_defer_op_type	*ops = dfp->dfp_ops;
+	int				error;
+
+	/* dfp is freed by recover_work and must not be accessed afterwards */
+	error = ops->recover_work(dfp, capture_list);
+	if (error)
+		trace_xlog_intent_recovery_failed(mp, ops, error);
+	return error;
 }
 
 /*
@@ -769,7 +1029,7 @@ xfs_defer_ops_capture_abort(
 {
 	unsigned short			i;
 
-	xfs_defer_pending_abort(mp, &dfc->dfc_dfops);
+	xfs_defer_pending_abort_list(mp, &dfc->dfc_dfops);
 	xfs_defer_cancel_list(mp, &dfc->dfc_dfops);
 
 	for (i = 0; i < dfc->dfc_held.dr_bufs; i++)
@@ -938,3 +1198,36 @@ xfs_defer_destroy_item_caches(void)
 	xfs_rmap_intent_destroy_cache();
 	xfs_defer_destroy_cache();
 }
+
+/*
+ * Mark a deferred work item so that it will be requeued indefinitely without
+ * being finished.  Caller must ensure there are no data dependencies on this
+ * work item in the meantime.
+ */
+void
+xfs_defer_item_pause(
+	struct xfs_trans		*tp,
+	struct xfs_defer_pending	*dfp)
+{
+	ASSERT(!(dfp->dfp_flags & XFS_DEFER_PAUSED));
+
+	dfp->dfp_flags |= XFS_DEFER_PAUSED;
+
+	trace_xfs_defer_item_pause(tp->t_mountp, dfp);
+}
+
+/*
+ * Release a paused deferred work item so that it will be finished during the
+ * next transaction roll.
+ */
+void
+xfs_defer_item_unpause(
+	struct xfs_trans		*tp,
+	struct xfs_defer_pending	*dfp)
+{
+	ASSERT(dfp->dfp_flags & XFS_DEFER_PAUSED);
+
+	dfp->dfp_flags &= ~XFS_DEFER_PAUSED;
+
+	trace_xfs_defer_item_unpause(tp->t_mountp, dfp);
+}