1 files changed, 511 insertions, 287 deletions

diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c
index a86599db20a6..15f0903f6fd4 100644
--- a/fs/xfs/xfs_rmap_item.c
+++ b/fs/xfs/xfs_rmap_item.c
@@ -20,9 +20,13 @@
 #include "xfs_error.h"
 #include "xfs_log_priv.h"
 #include "xfs_log_recover.h"
+#include "xfs_ag.h"
+#include "xfs_btree.h"
+#include "xfs_trace.h"
+#include "xfs_rtgroup.h"
 
-kmem_zone_t	*xfs_rui_zone;
-kmem_zone_t	*xfs_rud_zone;
+struct kmem_cache	*xfs_rui_cache;
+struct kmem_cache	*xfs_rud_cache;
 
 static const struct xfs_item_ops xfs_rui_item_ops;
 
@@ -35,10 +39,11 @@ STATIC void
 xfs_rui_item_free(
 	struct xfs_rui_log_item	*ruip)
 {
+	kvfree(ruip->rui_item.li_lv_shadow);
 	if (ruip->rui_format.rui_nextents > XFS_RUI_MAX_FAST_EXTENTS)
-		kmem_free(ruip);
+		kfree(ruip);
 	else
-		kmem_cache_free(xfs_rui_zone, ruip);
+		kmem_cache_free(xfs_rui_cache, ruip);
 }
 
 /*
@@ -53,10 +58,11 @@ xfs_rui_release(
 	struct xfs_rui_log_item	*ruip)
 {
 	ASSERT(atomic_read(&ruip->rui_refcount) > 0);
-	if (atomic_dec_and_test(&ruip->rui_refcount)) {
-		xfs_trans_ail_delete(&ruip->rui_item, SHUTDOWN_LOG_IO_ERROR);
-		xfs_rui_item_free(ruip);
-	}
+	if (!atomic_dec_and_test(&ruip->rui_refcount))
+		return;
+
+	xfs_trans_ail_delete(&ruip->rui_item, 0);
+	xfs_rui_item_free(ruip);
 }
 
 STATIC void
@@ -71,6 +77,11 @@ xfs_rui_item_size(
 	*nbytes += xfs_rui_log_format_sizeof(ruip->rui_format.rui_nextents);
 }
 
+unsigned int xfs_rui_log_space(unsigned int nr)
+{
+	return xlog_item_space(1, xfs_rui_log_format_sizeof(nr));
+}
+
 /*
  * This is called to fill in the vector of log iovecs for the
  * given rui log item. We use only 1 iovec, and we point that
@@ -89,7 +100,9 @@ xfs_rui_item_format(
 	ASSERT(atomic_read(&ruip->rui_next_extent) ==
 			ruip->rui_format.rui_nextents);
 
-	ruip->rui_format.rui_type = XFS_LI_RUI;
+	ASSERT(lip->li_type == XFS_LI_RUI || lip->li_type == XFS_LI_RUI_RT);
+
+	ruip->rui_format.rui_type = lip->li_type;
 	ruip->rui_format.rui_size = 1;
 
 	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_RUI_FORMAT, &ruip->rui_format,
@@ -132,18 +145,23 @@ xfs_rui_item_release(
 STATIC struct xfs_rui_log_item *
 xfs_rui_init(
 	struct xfs_mount		*mp,
+	unsigned short			item_type,
 	uint				nextents)
 
 {
 	struct xfs_rui_log_item		*ruip;
 
 	ASSERT(nextents > 0);
+	ASSERT(item_type == XFS_LI_RUI || item_type == XFS_LI_RUI_RT);
+
 	if (nextents > XFS_RUI_MAX_FAST_EXTENTS)
-		ruip = kmem_zalloc(xfs_rui_log_item_sizeof(nextents), 0);
+		ruip = kzalloc(xfs_rui_log_item_sizeof(nextents),
+				GFP_KERNEL | __GFP_NOFAIL);
 	else
-		ruip = kmem_zone_zalloc(xfs_rui_zone, 0);
+		ruip = kmem_cache_zalloc(xfs_rui_cache,
+					 GFP_KERNEL | __GFP_NOFAIL);
 
-	xfs_log_item_init(mp, &ruip->rui_item, XFS_LI_RUI, &xfs_rui_item_ops);
+	xfs_log_item_init(mp, &ruip->rui_item, item_type, &xfs_rui_item_ops);
 	ruip->rui_format.rui_nextents = nextents;
 	ruip->rui_format.rui_id = (uintptr_t)(void *)ruip;
 	atomic_set(&ruip->rui_next_extent, 0);
@@ -152,31 +170,6 @@ xfs_rui_init(
 	return ruip;
 }
 
-/*
- * Copy an RUI format buffer from the given buf, and into the destination
- * RUI format structure.  The RUI/RUD items were designed not to need any
- * special alignment handling.
- */
-STATIC int
-xfs_rui_copy_format(
-	struct xfs_log_iovec		*buf,
-	struct xfs_rui_log_format	*dst_rui_fmt)
-{
-	struct xfs_rui_log_format	*src_rui_fmt;
-	uint				len;
-
-	src_rui_fmt = buf->i_addr;
-	len = xfs_rui_log_format_sizeof(src_rui_fmt->rui_nextents);
-
-	if (buf->i_len != len) {
-		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
-		return -EFSCORRUPTED;
-	}
-
-	memcpy(dst_rui_fmt, src_rui_fmt, len);
-	return 0;
-}
-
 static inline struct xfs_rud_log_item *RUD_ITEM(struct xfs_log_item *lip)
 {
 	return container_of(lip, struct xfs_rud_log_item, rud_item);
@@ -192,6 +185,11 @@ xfs_rud_item_size(
 	*nbytes += sizeof(struct xfs_rud_log_format);
 }
 
+unsigned int xfs_rud_log_space(void)
+{
+	return xlog_item_space(1, sizeof(struct xfs_rud_log_format));
+}
+
 /*
  * This is called to fill in the vector of log iovecs for the
  * given rud log item. We use only 1 iovec, and we point that
@@ -207,7 +205,9 @@ xfs_rud_item_format(
 	struct xfs_rud_log_item	*rudp = RUD_ITEM(lip);
 	struct xfs_log_iovec	*vecp = NULL;
 
-	rudp->rud_format.rud_type = XFS_LI_RUD;
+	ASSERT(lip->li_type == XFS_LI_RUD || lip->li_type == XFS_LI_RUD_RT);
+
+	rudp->rud_format.rud_type = lip->li_type;
 	rudp->rud_format.rud_size = 1;
 
 	xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_RUD_FORMAT, &rudp->rud_format,
@@ -226,127 +226,50 @@ xfs_rud_item_release(
 	struct xfs_rud_log_item	*rudp = RUD_ITEM(lip);
 
 	xfs_rui_release(rudp->rud_ruip);
-	kmem_cache_free(xfs_rud_zone, rudp);
+	kvfree(rudp->rud_item.li_lv_shadow);
+	kmem_cache_free(xfs_rud_cache, rudp);
+}
+
+static struct xfs_log_item *
+xfs_rud_item_intent(
+	struct xfs_log_item	*lip)
+{
+	return &RUD_ITEM(lip)->rud_ruip->rui_item;
 }
 
 static const struct xfs_item_ops xfs_rud_item_ops = {
-	.flags		= XFS_ITEM_RELEASE_WHEN_COMMITTED,
+	.flags		= XFS_ITEM_RELEASE_WHEN_COMMITTED |
+			  XFS_ITEM_INTENT_DONE,
 	.iop_size	= xfs_rud_item_size,
 	.iop_format	= xfs_rud_item_format,
 	.iop_release	= xfs_rud_item_release,
+	.iop_intent	= xfs_rud_item_intent,
 };
 
-static struct xfs_rud_log_item *
-xfs_trans_get_rud(
-	struct xfs_trans		*tp,
-	struct xfs_rui_log_item		*ruip)
+static inline struct xfs_rmap_intent *ri_entry(const struct list_head *e)
 {
-	struct xfs_rud_log_item		*rudp;
-
-	rudp = kmem_zone_zalloc(xfs_rud_zone, 0);
-	xfs_log_item_init(tp->t_mountp, &rudp->rud_item, XFS_LI_RUD,
-			  &xfs_rud_item_ops);
-	rudp->rud_ruip = ruip;
-	rudp->rud_format.rud_rui_id = ruip->rui_format.rui_id;
-
-	xfs_trans_add_item(tp, &rudp->rud_item);
-	return rudp;
+	return list_entry(e, struct xfs_rmap_intent, ri_list);
 }
 
-/* Set the map extent flags for this reverse mapping. */
-static void
-xfs_trans_set_rmap_flags(
-	struct xfs_map_extent		*rmap,
-	enum xfs_rmap_intent_type	type,
-	int				whichfork,
-	xfs_exntst_t			state)
+static inline bool
+xfs_rui_item_isrt(const struct xfs_log_item *lip)
 {
-	rmap->me_flags = 0;
-	if (state == XFS_EXT_UNWRITTEN)
-		rmap->me_flags |= XFS_RMAP_EXTENT_UNWRITTEN;
-	if (whichfork == XFS_ATTR_FORK)
-		rmap->me_flags |= XFS_RMAP_EXTENT_ATTR_FORK;
-	switch (type) {
-	case XFS_RMAP_MAP:
-		rmap->me_flags |= XFS_RMAP_EXTENT_MAP;
-		break;
-	case XFS_RMAP_MAP_SHARED:
-		rmap->me_flags |= XFS_RMAP_EXTENT_MAP_SHARED;
-		break;
-	case XFS_RMAP_UNMAP:
-		rmap->me_flags |= XFS_RMAP_EXTENT_UNMAP;
-		break;
-	case XFS_RMAP_UNMAP_SHARED:
-		rmap->me_flags |= XFS_RMAP_EXTENT_UNMAP_SHARED;
-		break;
-	case XFS_RMAP_CONVERT:
-		rmap->me_flags |= XFS_RMAP_EXTENT_CONVERT;
-		break;
-	case XFS_RMAP_CONVERT_SHARED:
-		rmap->me_flags |= XFS_RMAP_EXTENT_CONVERT_SHARED;
-		break;
-	case XFS_RMAP_ALLOC:
-		rmap->me_flags |= XFS_RMAP_EXTENT_ALLOC;
-		break;
-	case XFS_RMAP_FREE:
-		rmap->me_flags |= XFS_RMAP_EXTENT_FREE;
-		break;
-	default:
-		ASSERT(0);
-	}
-}
-
-/*
- * Finish an rmap update and log it to the RUD. Note that the transaction is
- * marked dirty regardless of whether the rmap update succeeds or fails to
- * support the RUI/RUD lifecycle rules.
- */
-static int
-xfs_trans_log_finish_rmap_update(
-	struct xfs_trans		*tp,
-	struct xfs_rud_log_item		*rudp,
-	enum xfs_rmap_intent_type	type,
-	uint64_t			owner,
-	int				whichfork,
-	xfs_fileoff_t			startoff,
-	xfs_fsblock_t			startblock,
-	xfs_filblks_t			blockcount,
-	xfs_exntst_t			state,
-	struct xfs_btree_cur		**pcur)
-{
-	int				error;
-
-	error = xfs_rmap_finish_one(tp, type, owner, whichfork, startoff,
-			startblock, blockcount, state, pcur);
+	ASSERT(lip->li_type == XFS_LI_RUI || lip->li_type == XFS_LI_RUI_RT);
 
-	/*
-	 * Mark the transaction dirty, even on error. This ensures the
-	 * transaction is aborted, which:
-	 *
-	 * 1.) releases the RUI and frees the RUD
-	 * 2.) shuts down the filesystem
-	 */
-	tp->t_flags |= XFS_TRANS_DIRTY;
-	set_bit(XFS_LI_DIRTY, &rudp->rud_item.li_flags);
-
-	return error;
+	return lip->li_type == XFS_LI_RUI_RT;
 }
 
 /* Sort rmap intents by AG. */
 static int
 xfs_rmap_update_diff_items(
 	void				*priv,
-	struct list_head		*a,
-	struct list_head		*b)
+	const struct list_head		*a,
+	const struct list_head		*b)
 {
-	struct xfs_mount		*mp = priv;
-	struct xfs_rmap_intent		*ra;
-	struct xfs_rmap_intent		*rb;
+	struct xfs_rmap_intent		*ra = ri_entry(a);
+	struct xfs_rmap_intent		*rb = ri_entry(b);
 
-	ra = container_of(a, struct xfs_rmap_intent, ri_list);
-	rb = container_of(b, struct xfs_rmap_intent, ri_list);
-	return  XFS_FSB_TO_AGNO(mp, ra->ri_bmap.br_startblock) -
-		XFS_FSB_TO_AGNO(mp, rb->ri_bmap.br_startblock);
+	return ra->ri_group->xg_gno - rb->ri_group->xg_gno;
 }
 
 /* Log rmap updates in the intent item. */
@@ -354,14 +277,11 @@ STATIC void
 xfs_rmap_update_log_item(
 	struct xfs_trans		*tp,
 	struct xfs_rui_log_item		*ruip,
-	struct xfs_rmap_intent		*rmap)
+	struct xfs_rmap_intent		*ri)
 {
 	uint				next_extent;
 	struct xfs_map_extent		*map;
 
-	tp->t_flags |= XFS_TRANS_DIRTY;
-	set_bit(XFS_LI_DIRTY, &ruip->rui_item.li_flags);
-
 	/*
 	 * atomic_inc_return gives us the value after the increment;
 	 * we want to use it as an array index so we need to subtract 1 from
@@ -370,35 +290,85 @@ xfs_rmap_update_log_item(
 	next_extent = atomic_inc_return(&ruip->rui_next_extent) - 1;
 	ASSERT(next_extent < ruip->rui_format.rui_nextents);
 	map = &ruip->rui_format.rui_extents[next_extent];
-	map->me_owner = rmap->ri_owner;
-	map->me_startblock = rmap->ri_bmap.br_startblock;
-	map->me_startoff = rmap->ri_bmap.br_startoff;
-	map->me_len = rmap->ri_bmap.br_blockcount;
-	xfs_trans_set_rmap_flags(map, rmap->ri_type, rmap->ri_whichfork,
-			rmap->ri_bmap.br_state);
+	map->me_owner = ri->ri_owner;
+	map->me_startblock = ri->ri_bmap.br_startblock;
+	map->me_startoff = ri->ri_bmap.br_startoff;
+	map->me_len = ri->ri_bmap.br_blockcount;
+
+	map->me_flags = 0;
+	if (ri->ri_bmap.br_state == XFS_EXT_UNWRITTEN)
+		map->me_flags |= XFS_RMAP_EXTENT_UNWRITTEN;
+	if (ri->ri_whichfork == XFS_ATTR_FORK)
+		map->me_flags |= XFS_RMAP_EXTENT_ATTR_FORK;
+	switch (ri->ri_type) {
+	case XFS_RMAP_MAP:
+		map->me_flags |= XFS_RMAP_EXTENT_MAP;
+		break;
+	case XFS_RMAP_MAP_SHARED:
+		map->me_flags |= XFS_RMAP_EXTENT_MAP_SHARED;
+		break;
+	case XFS_RMAP_UNMAP:
+		map->me_flags |= XFS_RMAP_EXTENT_UNMAP;
+		break;
+	case XFS_RMAP_UNMAP_SHARED:
+		map->me_flags |= XFS_RMAP_EXTENT_UNMAP_SHARED;
+		break;
+	case XFS_RMAP_CONVERT:
+		map->me_flags |= XFS_RMAP_EXTENT_CONVERT;
+		break;
+	case XFS_RMAP_CONVERT_SHARED:
+		map->me_flags |= XFS_RMAP_EXTENT_CONVERT_SHARED;
+		break;
+	case XFS_RMAP_ALLOC:
+		map->me_flags |= XFS_RMAP_EXTENT_ALLOC;
+		break;
+	case XFS_RMAP_FREE:
+		map->me_flags |= XFS_RMAP_EXTENT_FREE;
+		break;
+	default:
+		ASSERT(0);
+	}
 }
 
 static struct xfs_log_item *
-xfs_rmap_update_create_intent(
+__xfs_rmap_update_create_intent(
 	struct xfs_trans		*tp,
 	struct list_head		*items,
 	unsigned int			count,
-	bool				sort)
+	bool				sort,
+	unsigned short			item_type)
 {
 	struct xfs_mount		*mp = tp->t_mountp;
-	struct xfs_rui_log_item		*ruip = xfs_rui_init(mp, count);
-	struct xfs_rmap_intent		*rmap;
+	struct xfs_rui_log_item		*ruip;
+	struct xfs_rmap_intent		*ri;
 
 	ASSERT(count > 0);
 
-	xfs_trans_add_item(tp, &ruip->rui_item);
+	ruip = xfs_rui_init(mp, item_type, count);
 	if (sort)
 		list_sort(mp, items, xfs_rmap_update_diff_items);
-	list_for_each_entry(rmap, items, ri_list)
-		xfs_rmap_update_log_item(tp, ruip, rmap);
+	list_for_each_entry(ri, items, ri_list)
+		xfs_rmap_update_log_item(tp, ruip, ri);
 	return &ruip->rui_item;
 }
 
+static struct xfs_log_item *
+xfs_rmap_update_create_intent(
+	struct xfs_trans		*tp,
+	struct list_head		*items,
+	unsigned int			count,
+	bool				sort)
+{
+	return __xfs_rmap_update_create_intent(tp, items, count, sort,
+			XFS_LI_RUI);
+}
+
+static inline unsigned short
+xfs_rud_type_from_rui(const struct xfs_rui_log_item *ruip)
+{
+	return xfs_rui_item_isrt(&ruip->rui_item) ? XFS_LI_RUD_RT : XFS_LI_RUD;
+}
+
 /* Get an RUD so we can process all the deferred rmap updates. */
 static struct xfs_log_item *
 xfs_rmap_update_create_done(
@@ -406,7 +376,51 @@ xfs_rmap_update_create_done(
 	struct xfs_log_item		*intent,
 	unsigned int			count)
 {
-	return &xfs_trans_get_rud(tp, RUI_ITEM(intent))->rud_item;
+	struct xfs_rui_log_item		*ruip = RUI_ITEM(intent);
+	struct xfs_rud_log_item		*rudp;
+
+	rudp = kmem_cache_zalloc(xfs_rud_cache, GFP_KERNEL | __GFP_NOFAIL);
+	xfs_log_item_init(tp->t_mountp, &rudp->rud_item,
+			xfs_rud_type_from_rui(ruip), &xfs_rud_item_ops);
+	rudp->rud_ruip = ruip;
+	rudp->rud_format.rud_rui_id = ruip->rui_format.rui_id;
+
+	return &rudp->rud_item;
+}
+
+/* Add this deferred RUI to the transaction. */
+void
+xfs_rmap_defer_add(
+	struct xfs_trans	*tp,
+	struct xfs_rmap_intent	*ri)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+
+	/*
+	 * Deferred rmap updates for the realtime and data sections must use
+	 * separate transactions to finish deferred work because updates to
+	 * realtime metadata files can lock AGFs to allocate btree blocks and
+	 * we don't want that mixing with the AGF locks taken to finish data
+	 * section updates.
+	 */
+	ri->ri_group = xfs_group_intent_get(mp, ri->ri_bmap.br_startblock,
+			ri->ri_realtime ? XG_TYPE_RTG : XG_TYPE_AG);
+
+	trace_xfs_rmap_defer(mp, ri);
+	xfs_defer_add(tp, &ri->ri_list, ri->ri_realtime ?
+			&xfs_rtrmap_update_defer_type :
+			&xfs_rmap_update_defer_type);
+}
+
+/* Cancel a deferred rmap update. */
+STATIC void
+xfs_rmap_update_cancel_item(
+	struct list_head		*item)
+{
+	struct xfs_rmap_intent		*ri = ri_entry(item);
+
+	xfs_group_intent_put(ri->ri_group);
+	kmem_cache_free(xfs_rmap_intent_cache, ri);
 }
 
 /* Process a deferred rmap update. */
@@ -417,19 +431,32 @@ xfs_rmap_update_finish_item(
 	struct list_head		*item,
 	struct xfs_btree_cur		**state)
 {
-	struct xfs_rmap_intent		*rmap;
+	struct xfs_rmap_intent		*ri = ri_entry(item);
 	int				error;
 
-	rmap = container_of(item, struct xfs_rmap_intent, ri_list);
-	error = xfs_trans_log_finish_rmap_update(tp, RUD_ITEM(done),
-			rmap->ri_type, rmap->ri_owner, rmap->ri_whichfork,
-			rmap->ri_bmap.br_startoff, rmap->ri_bmap.br_startblock,
-			rmap->ri_bmap.br_blockcount, rmap->ri_bmap.br_state,
-			state);
-	kmem_free(rmap);
+	error = xfs_rmap_finish_one(tp, ri, state);
+
+	xfs_rmap_update_cancel_item(item);
 	return error;
 }
 
+/* Clean up after calling xfs_rmap_finish_one. */
+STATIC void
+xfs_rmap_finish_one_cleanup(
+	struct xfs_trans	*tp,
+	struct xfs_btree_cur	*rcur,
+	int			error)
+{
+	struct xfs_buf		*agbp = NULL;
+
+	if (rcur == NULL)
+		return;
+	agbp = rcur->bc_ag.agbp;
+	xfs_btree_del_cursor(rcur, error);
+	if (error && agbp)
+		xfs_trans_brelse(tp, agbp);
+}
+
 /* Abort all pending RUIs. */
 STATIC void
 xfs_rmap_update_abort_intent(
@@ -438,48 +465,118 @@ xfs_rmap_update_abort_intent(
 	xfs_rui_release(RUI_ITEM(intent));
 }
 
-/* Cancel a deferred rmap update. */
-STATIC void
-xfs_rmap_update_cancel_item(
-	struct list_head		*item)
+/* Is this recovered RUI ok? */
+static inline bool
+xfs_rui_validate_map(
+	struct xfs_mount		*mp,
+	bool				isrt,
+	struct xfs_map_extent		*map)
 {
-	struct xfs_rmap_intent		*rmap;
+	if (!xfs_has_rmapbt(mp))
+		return false;
+
+	if (map->me_flags & ~XFS_RMAP_EXTENT_FLAGS)
+		return false;
+
+	switch (map->me_flags & XFS_RMAP_EXTENT_TYPE_MASK) {
+	case XFS_RMAP_EXTENT_MAP:
+	case XFS_RMAP_EXTENT_MAP_SHARED:
+	case XFS_RMAP_EXTENT_UNMAP:
+	case XFS_RMAP_EXTENT_UNMAP_SHARED:
+	case XFS_RMAP_EXTENT_CONVERT:
+	case XFS_RMAP_EXTENT_CONVERT_SHARED:
+	case XFS_RMAP_EXTENT_ALLOC:
+	case XFS_RMAP_EXTENT_FREE:
+		break;
+	default:
+		return false;
+	}
+
+	if (!XFS_RMAP_NON_INODE_OWNER(map->me_owner) &&
+	    !xfs_verify_ino(mp, map->me_owner))
+		return false;
+
+	if (!xfs_verify_fileext(mp, map->me_startoff, map->me_len))
+		return false;
 
-	rmap = container_of(item, struct xfs_rmap_intent, ri_list);
-	kmem_free(rmap);
+	if (isrt)
+		return xfs_verify_rtbext(mp, map->me_startblock, map->me_len);
+
+	return xfs_verify_fsbext(mp, map->me_startblock, map->me_len);
 }
 
-const struct xfs_defer_op_type xfs_rmap_update_defer_type = {
-	.max_items	= XFS_RUI_MAX_FAST_EXTENTS,
-	.create_intent	= xfs_rmap_update_create_intent,
-	.abort_intent	= xfs_rmap_update_abort_intent,
-	.create_done	= xfs_rmap_update_create_done,
-	.finish_item	= xfs_rmap_update_finish_item,
-	.finish_cleanup = xfs_rmap_finish_one_cleanup,
-	.cancel_item	= xfs_rmap_update_cancel_item,
-};
+static inline void
+xfs_rui_recover_work(
+	struct xfs_mount		*mp,
+	struct xfs_defer_pending	*dfp,
+	bool				isrt,
+	const struct xfs_map_extent	*map)
+{
+	struct xfs_rmap_intent		*ri;
+
+	ri = kmem_cache_alloc(xfs_rmap_intent_cache, GFP_KERNEL | __GFP_NOFAIL);
+
+	switch (map->me_flags & XFS_RMAP_EXTENT_TYPE_MASK) {
+	case XFS_RMAP_EXTENT_MAP:
+		ri->ri_type = XFS_RMAP_MAP;
+		break;
+	case XFS_RMAP_EXTENT_MAP_SHARED:
+		ri->ri_type = XFS_RMAP_MAP_SHARED;
+		break;
+	case XFS_RMAP_EXTENT_UNMAP:
+		ri->ri_type = XFS_RMAP_UNMAP;
+		break;
+	case XFS_RMAP_EXTENT_UNMAP_SHARED:
+		ri->ri_type = XFS_RMAP_UNMAP_SHARED;
+		break;
+	case XFS_RMAP_EXTENT_CONVERT:
+		ri->ri_type = XFS_RMAP_CONVERT;
+		break;
+	case XFS_RMAP_EXTENT_CONVERT_SHARED:
+		ri->ri_type = XFS_RMAP_CONVERT_SHARED;
+		break;
+	case XFS_RMAP_EXTENT_ALLOC:
+		ri->ri_type = XFS_RMAP_ALLOC;
+		break;
+	case XFS_RMAP_EXTENT_FREE:
+		ri->ri_type = XFS_RMAP_FREE;
+		break;
+	default:
+		ASSERT(0);
+		return;
+	}
+
+	ri->ri_owner = map->me_owner;
+	ri->ri_whichfork = (map->me_flags & XFS_RMAP_EXTENT_ATTR_FORK) ?
+			XFS_ATTR_FORK : XFS_DATA_FORK;
+	ri->ri_bmap.br_startblock = map->me_startblock;
+	ri->ri_bmap.br_startoff = map->me_startoff;
+	ri->ri_bmap.br_blockcount = map->me_len;
+	ri->ri_bmap.br_state = (map->me_flags & XFS_RMAP_EXTENT_UNWRITTEN) ?
+			XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
+	ri->ri_group = xfs_group_intent_get(mp, map->me_startblock,
+			isrt ? XG_TYPE_RTG : XG_TYPE_AG);
+	ri->ri_realtime = isrt;
+
+	xfs_defer_add_item(dfp, &ri->ri_list);
+}
 
 /*
  * Process an rmap update intent item that was recovered from the log.
  * We need to update the rmapbt.
  */
 STATIC int
-xfs_rui_item_recover(
-	struct xfs_log_item		*lip,
-	struct xfs_trans		*parent_tp)
+xfs_rmap_recover_work(
+	struct xfs_defer_pending	*dfp,
+	struct list_head		*capture_list)
 {
+	struct xfs_trans_res		resv;
+	struct xfs_log_item		*lip = dfp->dfp_intent;
 	struct xfs_rui_log_item		*ruip = RUI_ITEM(lip);
-	struct xfs_map_extent		*rmap;
-	struct xfs_rud_log_item		*rudp;
 	struct xfs_trans		*tp;
-	struct xfs_btree_cur		*rcur = NULL;
-	struct xfs_mount		*mp = parent_tp->t_mountp;
-	xfs_fsblock_t			startblock_fsb;
-	enum xfs_rmap_intent_type	type;
-	xfs_exntst_t			state;
-	bool				op_ok;
+	struct xfs_mount		*mp = lip->li_log->l_mp;
+	bool				isrt = xfs_rui_item_isrt(lip);
 	int				i;
-	int				whichfork;
 	int				error = 0;
 
 	/*
@@ -488,99 +585,117 @@ xfs_rui_item_recover(
 	 * just toss the RUI.
 	 */
 	for (i = 0; i < ruip->rui_format.rui_nextents; i++) {
-		rmap = &ruip->rui_format.rui_extents[i];
-		startblock_fsb = XFS_BB_TO_FSB(mp,
-				   XFS_FSB_TO_DADDR(mp, rmap->me_startblock));
-		switch (rmap->me_flags & XFS_RMAP_EXTENT_TYPE_MASK) {
-		case XFS_RMAP_EXTENT_MAP:
-		case XFS_RMAP_EXTENT_MAP_SHARED:
-		case XFS_RMAP_EXTENT_UNMAP:
-		case XFS_RMAP_EXTENT_UNMAP_SHARED:
-		case XFS_RMAP_EXTENT_CONVERT:
-		case XFS_RMAP_EXTENT_CONVERT_SHARED:
-		case XFS_RMAP_EXTENT_ALLOC:
-		case XFS_RMAP_EXTENT_FREE:
-			op_ok = true;
-			break;
-		default:
-			op_ok = false;
-			break;
-		}
-		if (!op_ok || startblock_fsb == 0 ||
-		    rmap->me_len == 0 ||
-		    startblock_fsb >= mp->m_sb.sb_dblocks ||
-		    rmap->me_len >= mp->m_sb.sb_agblocks ||
-		    (rmap->me_flags & ~XFS_RMAP_EXTENT_FLAGS)) {
-			/*
-			 * This will pull the RUI from the AIL and
-			 * free the memory associated with it.
-			 */
-			xfs_rui_release(ruip);
+		if (!xfs_rui_validate_map(mp, isrt,
+					&ruip->rui_format.rui_extents[i])) {
+			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+					&ruip->rui_format,
+					sizeof(ruip->rui_format));
 			return -EFSCORRUPTED;
 		}
+
+		xfs_rui_recover_work(mp, dfp, isrt,
+				&ruip->rui_format.rui_extents[i]);
 	}
 
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate,
-			mp->m_rmap_maxlevels, 0, XFS_TRANS_RESERVE, &tp);
+	resv = xlog_recover_resv(&M_RES(mp)->tr_itruncate);
+	error = xfs_trans_alloc(mp, &resv, mp->m_rmap_maxlevels, 0,
+			XFS_TRANS_RESERVE, &tp);
 	if (error)
 		return error;
-	rudp = xfs_trans_get_rud(tp, ruip);
-
-	for (i = 0; i < ruip->rui_format.rui_nextents; i++) {
-		rmap = &ruip->rui_format.rui_extents[i];
-		state = (rmap->me_flags & XFS_RMAP_EXTENT_UNWRITTEN) ?
-				XFS_EXT_UNWRITTEN : XFS_EXT_NORM;
-		whichfork = (rmap->me_flags & XFS_RMAP_EXTENT_ATTR_FORK) ?
-				XFS_ATTR_FORK : XFS_DATA_FORK;
-		switch (rmap->me_flags & XFS_RMAP_EXTENT_TYPE_MASK) {
-		case XFS_RMAP_EXTENT_MAP:
-			type = XFS_RMAP_MAP;
-			break;
-		case XFS_RMAP_EXTENT_MAP_SHARED:
-			type = XFS_RMAP_MAP_SHARED;
-			break;
-		case XFS_RMAP_EXTENT_UNMAP:
-			type = XFS_RMAP_UNMAP;
-			break;
-		case XFS_RMAP_EXTENT_UNMAP_SHARED:
-			type = XFS_RMAP_UNMAP_SHARED;
-			break;
-		case XFS_RMAP_EXTENT_CONVERT:
-			type = XFS_RMAP_CONVERT;
-			break;
-		case XFS_RMAP_EXTENT_CONVERT_SHARED:
-			type = XFS_RMAP_CONVERT_SHARED;
-			break;
-		case XFS_RMAP_EXTENT_ALLOC:
-			type = XFS_RMAP_ALLOC;
-			break;
-		case XFS_RMAP_EXTENT_FREE:
-			type = XFS_RMAP_FREE;
-			break;
-		default:
-			XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
-			error = -EFSCORRUPTED;
-			goto abort_error;
-		}
-		error = xfs_trans_log_finish_rmap_update(tp, rudp, type,
-				rmap->me_owner, whichfork,
-				rmap->me_startoff, rmap->me_startblock,
-				rmap->me_len, state, &rcur);
-		if (error)
-			goto abort_error;
 
-	}
+	error = xlog_recover_finish_intent(tp, dfp);
+	if (error == -EFSCORRUPTED)
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				&ruip->rui_format,
+				sizeof(ruip->rui_format));
+	if (error)
+		goto abort_error;
 
-	xfs_rmap_finish_one_cleanup(tp, rcur, error);
-	error = xfs_trans_commit(tp);
-	return error;
+	return xfs_defer_ops_capture_and_commit(tp, capture_list);
 
 abort_error:
-	xfs_rmap_finish_one_cleanup(tp, rcur, error);
 	xfs_trans_cancel(tp);
 	return error;
 }
 
+/* Relog an intent item to push the log tail forward. */
+static struct xfs_log_item *
+xfs_rmap_relog_intent(
+	struct xfs_trans		*tp,
+	struct xfs_log_item		*intent,
+	struct xfs_log_item		*done_item)
+{
+	struct xfs_rui_log_item		*ruip;
+	struct xfs_map_extent		*map;
+	unsigned int			count;
+
+	ASSERT(intent->li_type == XFS_LI_RUI ||
+	       intent->li_type == XFS_LI_RUI_RT);
+
+	count = RUI_ITEM(intent)->rui_format.rui_nextents;
+	map = RUI_ITEM(intent)->rui_format.rui_extents;
+
+	ruip = xfs_rui_init(tp->t_mountp, intent->li_type, count);
+	memcpy(ruip->rui_format.rui_extents, map, count * sizeof(*map));
+	atomic_set(&ruip->rui_next_extent, count);
+
+	return &ruip->rui_item;
+}
+
+const struct xfs_defer_op_type xfs_rmap_update_defer_type = {
+	.name		= "rmap",
+	.max_items	= XFS_RUI_MAX_FAST_EXTENTS,
+	.create_intent	= xfs_rmap_update_create_intent,
+	.abort_intent	= xfs_rmap_update_abort_intent,
+	.create_done	= xfs_rmap_update_create_done,
+	.finish_item	= xfs_rmap_update_finish_item,
+	.finish_cleanup = xfs_rmap_finish_one_cleanup,
+	.cancel_item	= xfs_rmap_update_cancel_item,
+	.recover_work	= xfs_rmap_recover_work,
+	.relog_intent	= xfs_rmap_relog_intent,
+};
+
+#ifdef CONFIG_XFS_RT
+static struct xfs_log_item *
+xfs_rtrmap_update_create_intent(
+	struct xfs_trans		*tp,
+	struct list_head		*items,
+	unsigned int			count,
+	bool				sort)
+{
+	return __xfs_rmap_update_create_intent(tp, items, count, sort,
+			XFS_LI_RUI_RT);
+}
+
+/* Clean up after calling xfs_rmap_finish_one. */
+STATIC void
+xfs_rtrmap_finish_one_cleanup(
+	struct xfs_trans	*tp,
+	struct xfs_btree_cur	*rcur,
+	int			error)
+{
+	if (rcur)
+		xfs_btree_del_cursor(rcur, error);
+}
+
+const struct xfs_defer_op_type xfs_rtrmap_update_defer_type = {
+	.name		= "rtrmap",
+	.max_items	= XFS_RUI_MAX_FAST_EXTENTS,
+	.create_intent	= xfs_rtrmap_update_create_intent,
+	.abort_intent	= xfs_rmap_update_abort_intent,
+	.create_done	= xfs_rmap_update_create_done,
+	.finish_item	= xfs_rmap_update_finish_item,
+	.finish_cleanup = xfs_rtrmap_finish_one_cleanup,
+	.cancel_item	= xfs_rmap_update_cancel_item,
+	.recover_work	= xfs_rmap_recover_work,
+	.relog_intent	= xfs_rmap_relog_intent,
+};
+#else
+const struct xfs_defer_op_type xfs_rtrmap_update_defer_type = {
+	.name		= "rtrmap",
+};
+#endif
+
 STATIC bool
 xfs_rui_item_match(
 	struct xfs_log_item	*lip,
@@ -590,14 +705,28 @@ xfs_rui_item_match(
 }
 
 static const struct xfs_item_ops xfs_rui_item_ops = {
+	.flags		= XFS_ITEM_INTENT,
 	.iop_size	= xfs_rui_item_size,
 	.iop_format	= xfs_rui_item_format,
 	.iop_unpin	= xfs_rui_item_unpin,
 	.iop_release	= xfs_rui_item_release,
-	.iop_recover	= xfs_rui_item_recover,
 	.iop_match	= xfs_rui_item_match,
 };
 
+static inline void
+xfs_rui_copy_format(
+	struct xfs_rui_log_format	*dst,
+	const struct xfs_rui_log_format	*src)
+{
+	unsigned int			i;
+
+	memcpy(dst, src, offsetof(struct xfs_rui_log_format, rui_extents));
+
+	for (i = 0; i < src->rui_nextents; i++)
+		memcpy(&dst->rui_extents[i], &src->rui_extents[i],
+				sizeof(struct xfs_map_extent));
+}
+
 /*
  * This routine is called to create an in-core extent rmap update
  * item from the rui format structure which was logged on disk.
@@ -612,26 +741,32 @@ xlog_recover_rui_commit_pass2(
 	struct xlog_recover_item	*item,
 	xfs_lsn_t			lsn)
 {
-	int				error;
 	struct xfs_mount		*mp = log->l_mp;
 	struct xfs_rui_log_item		*ruip;
 	struct xfs_rui_log_format	*rui_formatp;
+	size_t				len;
 
-	rui_formatp = item->ri_buf[0].i_addr;
+	rui_formatp = item->ri_buf[0].iov_base;
 
-	ruip = xfs_rui_init(mp, rui_formatp->rui_nextents);
-	error = xfs_rui_copy_format(&item->ri_buf[0], &ruip->rui_format);
-	if (error) {
-		xfs_rui_item_free(ruip);
-		return error;
+	if (item->ri_buf[0].iov_len < xfs_rui_log_format_sizeof(0)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
+		return -EFSCORRUPTED;
 	}
+
+	len = xfs_rui_log_format_sizeof(rui_formatp->rui_nextents);
+	if (item->ri_buf[0].iov_len != len) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
+		return -EFSCORRUPTED;
+	}
+
+	ruip = xfs_rui_init(mp, ITEM_TYPE(item), rui_formatp->rui_nextents);
+	xfs_rui_copy_format(&ruip->rui_format, rui_formatp);
 	atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents);
-	/*
-	 * Insert the intent into the AIL directly and drop one reference so
-	 * that finishing or canceling the work will drop the other.
-	 */
-	xfs_trans_ail_insert(log->l_ailp, &ruip->rui_item, lsn);
-	xfs_rui_release(ruip);
+
+	xlog_recover_intent_item(log, &ruip->rui_item, lsn,
+			&xfs_rmap_update_defer_type);
 	return 0;
 }
 
@@ -640,6 +775,61 @@ const struct xlog_recover_item_ops xlog_rui_item_ops = {
 	.commit_pass2		= xlog_recover_rui_commit_pass2,
 };
 
+#ifdef CONFIG_XFS_RT
+STATIC int
+xlog_recover_rtrui_commit_pass2(
+	struct xlog			*log,
+	struct list_head		*buffer_list,
+	struct xlog_recover_item	*item,
+	xfs_lsn_t			lsn)
+{
+	struct xfs_mount		*mp = log->l_mp;
+	struct xfs_rui_log_item		*ruip;
+	struct xfs_rui_log_format	*rui_formatp;
+	size_t				len;
+
+	rui_formatp = item->ri_buf[0].iov_base;
+
+	if (item->ri_buf[0].iov_len < xfs_rui_log_format_sizeof(0)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
+		return -EFSCORRUPTED;
+	}
+
+	len = xfs_rui_log_format_sizeof(rui_formatp->rui_nextents);
+	if (item->ri_buf[0].iov_len != len) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+				item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
+		return -EFSCORRUPTED;
+	}
+
+	ruip = xfs_rui_init(mp, ITEM_TYPE(item), rui_formatp->rui_nextents);
+	xfs_rui_copy_format(&ruip->rui_format, rui_formatp);
+	atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents);
+
+	xlog_recover_intent_item(log, &ruip->rui_item, lsn,
+			&xfs_rtrmap_update_defer_type);
+	return 0;
+}
+#else
+STATIC int
+xlog_recover_rtrui_commit_pass2(
+	struct xlog			*log,
+	struct list_head		*buffer_list,
+	struct xlog_recover_item	*item,
+	xfs_lsn_t			lsn)
+{
+	XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+			item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
+	return -EFSCORRUPTED;
+}
+#endif
+
+const struct xlog_recover_item_ops xlog_rtrui_item_ops = {
+	.item_type		= XFS_LI_RUI_RT,
+	.commit_pass2		= xlog_recover_rtrui_commit_pass2,
+};
+
 /*
  * This routine is called when an RUD format structure is found in a committed
  * transaction in the log. Its purpose is to cancel the corresponding RUI if it
@@ -656,8 +846,12 @@ xlog_recover_rud_commit_pass2(
 {
 	struct xfs_rud_log_format	*rud_formatp;
 
-	rud_formatp = item->ri_buf[0].i_addr;
-	ASSERT(item->ri_buf[0].i_len == sizeof(struct xfs_rud_log_format));
+	rud_formatp = item->ri_buf[0].iov_base;
+	if (item->ri_buf[0].iov_len != sizeof(struct xfs_rud_log_format)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+				rud_formatp, item->ri_buf[0].iov_len);
+		return -EFSCORRUPTED;
+	}
 
 	xlog_recover_release_intent(log, XFS_LI_RUI, rud_formatp->rud_rui_id);
 	return 0;
@@ -667,3 +861,33 @@ const struct xlog_recover_item_ops xlog_rud_item_ops = {
 	.item_type		= XFS_LI_RUD,
 	.commit_pass2		= xlog_recover_rud_commit_pass2,
 };
+
+#ifdef CONFIG_XFS_RT
+STATIC int
+xlog_recover_rtrud_commit_pass2(
+	struct xlog			*log,
+	struct list_head		*buffer_list,
+	struct xlog_recover_item	*item,
+	xfs_lsn_t			lsn)
+{
+	struct xfs_rud_log_format	*rud_formatp;
+
+	rud_formatp = item->ri_buf[0].iov_base;
+	if (item->ri_buf[0].iov_len != sizeof(struct xfs_rud_log_format)) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+				rud_formatp, item->ri_buf[0].iov_len);
+		return -EFSCORRUPTED;
+	}
+
+	xlog_recover_release_intent(log, XFS_LI_RUI_RT,
+			rud_formatp->rud_rui_id);
+	return 0;
+}
+#else
+# define xlog_recover_rtrud_commit_pass2	xlog_recover_rtrui_commit_pass2
+#endif
+
+const struct xlog_recover_item_ops xlog_rtrud_item_ops = {
+	.item_type		= XFS_LI_RUD_RT,
+	.commit_pass2		= xlog_recover_rtrud_commit_pass2,
+};