1 files changed, 150 insertions, 127 deletions

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 8090e8249116..9052839305e2 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -40,6 +40,7 @@
 #include "xfs_bmap_item.h"
 #include "xfs_symlink_remote.h"
 #include "xfs_inode_util.h"
+#include "xfs_rtgroup.h"
 
 struct kmem_cache		*xfs_bmap_intent_cache;
 
@@ -1042,7 +1043,10 @@ xfs_bmap_add_attrfork(
 	int			error;		/* error return value */
 
 	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
-	ASSERT(!XFS_NOT_DQATTACHED(mp, ip));
+	if (xfs_is_metadir_inode(ip))
+		ASSERT(XFS_IS_DQDETACHED(ip));
+	else
+		ASSERT(!XFS_NOT_DQATTACHED(mp, ip));
 	ASSERT(!xfs_inode_has_attr_fork(ip));
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
@@ -1423,6 +1427,24 @@ xfs_bmap_last_offset(
  * Extent tree manipulation functions used during allocation.
  */
 
+static inline bool
+xfs_bmap_same_rtgroup(
+	struct xfs_inode	*ip,
+	int			whichfork,
+	struct xfs_bmbt_irec	*left,
+	struct xfs_bmbt_irec	*right)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+
+	if (xfs_ifork_is_realtime(ip, whichfork) && xfs_has_rtgroups(mp)) {
+		if (xfs_rtb_to_rgno(mp, left->br_startblock) !=
+		    xfs_rtb_to_rgno(mp, right->br_startblock))
+			return false;
+	}
+
+	return true;
+}
+
 /*
  * Convert a delayed allocation to a real allocation.
  */
@@ -1492,7 +1514,8 @@ xfs_bmap_add_extent_delay_real(
 	    LEFT.br_startoff + LEFT.br_blockcount == new->br_startoff &&
 	    LEFT.br_startblock + LEFT.br_blockcount == new->br_startblock &&
 	    LEFT.br_state == new->br_state &&
-	    LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
+	    LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
+	    xfs_bmap_same_rtgroup(bma->ip, whichfork, &LEFT, new))
 		state |= BMAP_LEFT_CONTIG;
 
 	/*
@@ -1516,7 +1539,8 @@ xfs_bmap_add_extent_delay_real(
 		      (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
 		       BMAP_RIGHT_FILLING) ||
 	     LEFT.br_blockcount + new->br_blockcount + RIGHT.br_blockcount
-			<= XFS_MAX_BMBT_EXTLEN))
+			<= XFS_MAX_BMBT_EXTLEN) &&
+	    xfs_bmap_same_rtgroup(bma->ip, whichfork, new, &RIGHT))
 		state |= BMAP_RIGHT_CONTIG;
 
 	error = 0;
@@ -2061,7 +2085,8 @@ xfs_bmap_add_extent_unwritten_real(
 	    LEFT.br_startoff + LEFT.br_blockcount == new->br_startoff &&
 	    LEFT.br_startblock + LEFT.br_blockcount == new->br_startblock &&
 	    LEFT.br_state == new->br_state &&
-	    LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
+	    LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
+	    xfs_bmap_same_rtgroup(ip, whichfork, &LEFT, new))
 		state |= BMAP_LEFT_CONTIG;
 
 	/*
@@ -2085,7 +2110,8 @@ xfs_bmap_add_extent_unwritten_real(
 		      (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
 		       BMAP_RIGHT_FILLING) ||
 	     LEFT.br_blockcount + new->br_blockcount + RIGHT.br_blockcount
-			<= XFS_MAX_BMBT_EXTLEN))
+			<= XFS_MAX_BMBT_EXTLEN) &&
+	    xfs_bmap_same_rtgroup(ip, whichfork, new, &RIGHT))
 		state |= BMAP_RIGHT_CONTIG;
 
 	/*
@@ -2594,7 +2620,8 @@ xfs_bmap_add_extent_hole_delay(
 	 */
 	if ((state & BMAP_LEFT_VALID) && (state & BMAP_LEFT_DELAY) &&
 	    left.br_startoff + left.br_blockcount == new->br_startoff &&
-	    left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
+	    left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
+	    xfs_bmap_same_rtgroup(ip, whichfork, &left, new))
 		state |= BMAP_LEFT_CONTIG;
 
 	if ((state & BMAP_RIGHT_VALID) && (state & BMAP_RIGHT_DELAY) &&
@@ -2602,7 +2629,8 @@ xfs_bmap_add_extent_hole_delay(
 	    new->br_blockcount + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
 	    (!(state & BMAP_LEFT_CONTIG) ||
 	     (left.br_blockcount + new->br_blockcount +
-	      right.br_blockcount <= XFS_MAX_BMBT_EXTLEN)))
+	      right.br_blockcount <= XFS_MAX_BMBT_EXTLEN)) &&
+	    xfs_bmap_same_rtgroup(ip, whichfork, new, &right))
 		state |= BMAP_RIGHT_CONTIG;
 
 	/*
@@ -2745,7 +2773,8 @@ xfs_bmap_add_extent_hole_real(
 	    left.br_startoff + left.br_blockcount == new->br_startoff &&
 	    left.br_startblock + left.br_blockcount == new->br_startblock &&
 	    left.br_state == new->br_state &&
-	    left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
+	    left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
+	    xfs_bmap_same_rtgroup(ip, whichfork, &left, new))
 		state |= BMAP_LEFT_CONTIG;
 
 	if ((state & BMAP_RIGHT_VALID) && !(state & BMAP_RIGHT_DELAY) &&
@@ -2755,7 +2784,8 @@ xfs_bmap_add_extent_hole_real(
 	    new->br_blockcount + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
 	    (!(state & BMAP_LEFT_CONTIG) ||
 	     left.br_blockcount + new->br_blockcount +
-	     right.br_blockcount <= XFS_MAX_BMBT_EXTLEN))
+	     right.br_blockcount <= XFS_MAX_BMBT_EXTLEN) &&
+	    xfs_bmap_same_rtgroup(ip, whichfork, new, &right))
 		state |= BMAP_RIGHT_CONTIG;
 
 	error = 0;
@@ -3121,8 +3151,15 @@ xfs_bmap_adjacent_valid(
 	struct xfs_mount	*mp = ap->ip->i_mount;
 
 	if (XFS_IS_REALTIME_INODE(ap->ip) &&
-	    (ap->datatype & XFS_ALLOC_USERDATA))
-		return x < mp->m_sb.sb_rblocks;
+	    (ap->datatype & XFS_ALLOC_USERDATA)) {
+		if (!xfs_has_rtgroups(mp))
+			return x < mp->m_sb.sb_rblocks;
+
+		return xfs_rtb_to_rgno(mp, x) == xfs_rtb_to_rgno(mp, y) &&
+			xfs_rtb_to_rgno(mp, x) < mp->m_sb.sb_rgcount &&
+			xfs_rtb_to_rtx(mp, x) < mp->m_sb.sb_rgextents;
+
+	}
 
 	return XFS_FSB_TO_AGNO(mp, x) == XFS_FSB_TO_AGNO(mp, y) &&
 		XFS_FSB_TO_AGNO(mp, x) < mp->m_sb.sb_agcount &&
@@ -3280,7 +3317,7 @@ xfs_bmap_longest_free_extent(
 	}
 
 	longest = xfs_alloc_longest_free_extent(pag,
-				xfs_alloc_min_freelist(pag->pag_mount, pag),
+				xfs_alloc_min_freelist(pag_mount(pag), pag),
 				xfs_ag_resv_needed(pag, XFS_AG_RESV_NONE));
 	if (*blen < longest)
 		*blen = longest;
@@ -3477,31 +3514,19 @@ xfs_bmap_process_allocated_extent(
 	xfs_bmap_alloc_account(ap);
 }
 
-#ifdef DEBUG
 static int
 xfs_bmap_exact_minlen_extent_alloc(
-	struct xfs_bmalloca	*ap)
+	struct xfs_bmalloca	*ap,
+	struct xfs_alloc_arg	*args)
 {
-	struct xfs_mount	*mp = ap->ip->i_mount;
-	struct xfs_alloc_arg	args = { .tp = ap->tp, .mp = mp };
-	xfs_fileoff_t		orig_offset;
-	xfs_extlen_t		orig_length;
-	int			error;
-
-	ASSERT(ap->length);
-
 	if (ap->minlen != 1) {
-		ap->blkno = NULLFSBLOCK;
-		ap->length = 0;
+		args->fsbno = NULLFSBLOCK;
 		return 0;
 	}
 
-	orig_offset = ap->offset;
-	orig_length = ap->length;
-
-	args.alloc_minlen_only = 1;
-
-	xfs_bmap_compute_alignments(ap, &args);
+	args->alloc_minlen_only = 1;
+	args->minlen = args->maxlen = ap->minlen;
+	args->total = ap->total;
 
 	/*
 	 * Unlike the longest extent available in an AG, we don't track
@@ -3511,39 +3536,16 @@ xfs_bmap_exact_minlen_extent_alloc(
 	 * we need not be concerned about a drop in performance in
 	 * "debug only" code paths.
 	 */
-	ap->blkno = XFS_AGB_TO_FSB(mp, 0, 0);
-
-	args.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE;
-	args.minlen = args.maxlen = ap->minlen;
-	args.total = ap->total;
-
-	args.alignment = 1;
-	args.minalignslop = 0;
-
-	args.minleft = ap->minleft;
-	args.wasdel = ap->wasdel;
-	args.resv = XFS_AG_RESV_NONE;
-	args.datatype = ap->datatype;
-
-	error = xfs_alloc_vextent_first_ag(&args, ap->blkno);
-	if (error)
-		return error;
-
-	if (args.fsbno != NULLFSBLOCK) {
-		xfs_bmap_process_allocated_extent(ap, &args, orig_offset,
-			orig_length);
-	} else {
-		ap->blkno = NULLFSBLOCK;
-		ap->length = 0;
-	}
+	ap->blkno = XFS_AGB_TO_FSB(ap->ip->i_mount, 0, 0);
 
-	return 0;
+	/*
+	 * Call xfs_bmap_btalloc_low_space here as it first does a "normal" AG
+	 * iteration and then drops args->total to args->minlen, which might be
+	 * required to find an allocation for the transaction reservation when
+	 * the file system is very full.
+	 */
+	return xfs_bmap_btalloc_low_space(ap, args);
 }
-#else
-
-#define xfs_bmap_exact_minlen_extent_alloc(bma) (-EFSCORRUPTED)
-
-#endif
 
 /*
  * If we are not low on available data blocks and we are allocating at
@@ -3801,8 +3803,11 @@ xfs_bmap_btalloc(
 	/* Trim the allocation back to the maximum an AG can fit. */
 	args.maxlen = min(ap->length, mp->m_ag_max_usable);
 
-	if ((ap->datatype & XFS_ALLOC_USERDATA) &&
-	    xfs_inode_is_filestream(ap->ip))
+	if (unlikely(XFS_TEST_ERROR(false, mp,
+			XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT)))
+		error = xfs_bmap_exact_minlen_extent_alloc(ap, &args);
+	else if ((ap->datatype & XFS_ALLOC_USERDATA) &&
+			xfs_inode_is_filestream(ap->ip))
 		error = xfs_bmap_btalloc_filestreams(ap, &args, stripe_align);
 	else
 		error = xfs_bmap_btalloc_best_length(ap, &args, stripe_align);
@@ -4123,7 +4128,7 @@ retry:
 
 	fdblocks = indlen;
 	if (XFS_IS_REALTIME_INODE(ip)) {
-		error = xfs_dec_frextents(mp, xfs_rtb_to_rtx(mp, alen));
+		error = xfs_dec_frextents(mp, xfs_blen_to_rtbxlen(mp, alen));
 		if (error)
 			goto out_unreserve_quota;
 	} else {
@@ -4158,7 +4163,7 @@ retry:
 
 out_unreserve_frextents:
 	if (XFS_IS_REALTIME_INODE(ip))
-		xfs_add_frextents(mp, xfs_rtb_to_rtx(mp, alen));
+		xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, alen));
 out_unreserve_quota:
 	if (XFS_IS_QUOTA_ON(mp))
 		xfs_quota_unreserve_blkres(ip, alen);
@@ -4177,43 +4182,6 @@ out:
 }
 
 static int
-xfs_bmap_alloc_userdata(
-	struct xfs_bmalloca	*bma)
-{
-	struct xfs_mount	*mp = bma->ip->i_mount;
-	int			whichfork = xfs_bmapi_whichfork(bma->flags);
-	int			error;
-
-	/*
-	 * Set the data type being allocated. For the data fork, the first data
-	 * in the file is treated differently to all other allocations. For the
-	 * attribute fork, we only need to ensure the allocated range is not on
-	 * the busy list.
-	 */
-	bma->datatype = XFS_ALLOC_NOBUSY;
-	if (whichfork == XFS_DATA_FORK || whichfork == XFS_COW_FORK) {
-		bma->datatype |= XFS_ALLOC_USERDATA;
-		if (bma->offset == 0)
-			bma->datatype |= XFS_ALLOC_INITIAL_USER_DATA;
-
-		if (mp->m_dalign && bma->length >= mp->m_dalign) {
-			error = xfs_bmap_isaeof(bma, whichfork);
-			if (error)
-				return error;
-		}
-
-		if (XFS_IS_REALTIME_INODE(bma->ip))
-			return xfs_bmap_rtalloc(bma);
-	}
-
-	if (unlikely(XFS_TEST_ERROR(false, mp,
-			XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT)))
-		return xfs_bmap_exact_minlen_extent_alloc(bma);
-
-	return xfs_bmap_btalloc(bma);
-}
-
-static int
 xfs_bmapi_allocate(
 	struct xfs_bmalloca	*bma)
 {
@@ -4230,15 +4198,32 @@ xfs_bmapi_allocate(
 	else
 		bma->minlen = 1;
 
-	if (bma->flags & XFS_BMAPI_METADATA) {
-		if (unlikely(XFS_TEST_ERROR(false, mp,
-				XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT)))
-			error = xfs_bmap_exact_minlen_extent_alloc(bma);
-		else
-			error = xfs_bmap_btalloc(bma);
-	} else {
-		error = xfs_bmap_alloc_userdata(bma);
+	if (!(bma->flags & XFS_BMAPI_METADATA)) {
+		/*
+		 * For the data and COW fork, the first data in the file is
+		 * treated differently to all other allocations. For the
+		 * attribute fork, we only need to ensure the allocated range
+		 * is not on the busy list.
+		 */
+		bma->datatype = XFS_ALLOC_NOBUSY;
+		if (whichfork == XFS_DATA_FORK || whichfork == XFS_COW_FORK) {
+			bma->datatype |= XFS_ALLOC_USERDATA;
+			if (bma->offset == 0)
+				bma->datatype |= XFS_ALLOC_INITIAL_USER_DATA;
+
+			if (mp->m_dalign && bma->length >= mp->m_dalign) {
+				error = xfs_bmap_isaeof(bma, whichfork);
+				if (error)
+					return error;
+			}
+		}
 	}
+
+	if ((bma->datatype & XFS_ALLOC_USERDATA) &&
+	    XFS_IS_REALTIME_INODE(bma->ip))
+		error = xfs_bmap_rtalloc(bma);
+	else
+		error = xfs_bmap_btalloc(bma);
 	if (error)
 		return error;
 	if (bma->blkno == NULLFSBLOCK)
@@ -5086,7 +5071,7 @@ xfs_bmap_del_extent_delay(
 	fdblocks = da_diff;
 
 	if (isrt)
-		xfs_add_frextents(mp, xfs_rtb_to_rtx(mp, del->br_blockcount));
+		xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, del->br_blockcount));
 	else
 		fdblocks += del->br_blockcount;
 
@@ -5165,6 +5150,34 @@ xfs_bmap_del_extent_cow(
 	ip->i_delayed_blks -= del->br_blockcount;
 }
 
+static int
+xfs_bmap_free_rtblocks(
+	struct xfs_trans	*tp,
+	struct xfs_bmbt_irec	*del)
+{
+	struct xfs_rtgroup	*rtg;
+	int			error;
+
+	rtg = xfs_rtgroup_grab(tp->t_mountp, 0);
+	if (!rtg)
+		return -EIO;
+
+	/*
+	 * Ensure the bitmap and summary inodes are locked and joined to the
+	 * transaction before modifying them.
+	 */
+	if (!(tp->t_flags & XFS_TRANS_RTBITMAP_LOCKED)) {
+		tp->t_flags |= XFS_TRANS_RTBITMAP_LOCKED;
+		xfs_rtgroup_lock(rtg, XFS_RTGLOCK_BITMAP);
+		xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_BITMAP);
+	}
+
+	error = xfs_rtfree_blocks(tp, rtg, del->br_startblock,
+			del->br_blockcount);
+	xfs_rtgroup_rele(rtg);
+	return error;
+}
+
 /*
  * Called by xfs_bmapi to update file extent records and the btree
  * after removing space.
@@ -5377,20 +5390,12 @@ xfs_bmap_del_extent_real(
 	 * If we need to, add to list of extents to delete.
 	 */
 	if (!(bflags & XFS_BMAPI_REMAP)) {
+		bool	isrt = xfs_ifork_is_realtime(ip, whichfork);
+
 		if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) {
 			xfs_refcount_decrease_extent(tp, del);
-		} else if (xfs_ifork_is_realtime(ip, whichfork)) {
-			/*
-			 * Ensure the bitmap and summary inodes are locked
-			 * and joined to the transaction before modifying them.
-			 */
-			if (!(tp->t_flags & XFS_TRANS_RTBITMAP_LOCKED)) {
-				tp->t_flags |= XFS_TRANS_RTBITMAP_LOCKED;
-				xfs_rtbitmap_lock(mp);
-				xfs_rtbitmap_trans_join(tp);
-			}
-			error = xfs_rtfree_blocks(tp, del->br_startblock,
-					del->br_blockcount);
+		} else if (isrt && !xfs_has_rtgroups(mp)) {
+			error = xfs_bmap_free_rtblocks(tp, del);
 		} else {
 			unsigned int	efi_flags = 0;
 
@@ -5398,6 +5403,19 @@ xfs_bmap_del_extent_real(
 			    del->br_state == XFS_EXT_UNWRITTEN)
 				efi_flags |= XFS_FREE_EXTENT_SKIP_DISCARD;
 
+			/*
+			 * Historically, we did not use EFIs to free realtime
+			 * extents.  However, when reverse mapping is enabled,
+			 * we must maintain the same order of operations as the
+			 * data device, which is: Remove the file mapping,
+			 * remove the reverse mapping, and then free the
+			 * blocks.  Reflink for realtime volumes requires the
+			 * same sort of ordering.  Both features rely on
+			 * rtgroups, so let's gate rt EFI usage on rtgroups.
+			 */
+			if (isrt)
+				efi_flags |= XFS_FREE_EXTENT_REALTIME;
+
 			error = xfs_free_extent_later(tp, del->br_startblock,
 					del->br_blockcount, NULL,
 					XFS_AG_RESV_NONE, efi_flags);
@@ -5746,6 +5764,8 @@ xfs_bunmapi(
  */
 STATIC bool
 xfs_bmse_can_merge(
+	struct xfs_inode	*ip,
+	int			whichfork,
 	struct xfs_bmbt_irec	*left,	/* preceding extent */
 	struct xfs_bmbt_irec	*got,	/* current extent to shift */
 	xfs_fileoff_t		shift)	/* shift fsb */
@@ -5761,7 +5781,8 @@ xfs_bmse_can_merge(
 	if ((left->br_startoff + left->br_blockcount != startoff) ||
 	    (left->br_startblock + left->br_blockcount != got->br_startblock) ||
 	    (left->br_state != got->br_state) ||
-	    (left->br_blockcount + got->br_blockcount > XFS_MAX_BMBT_EXTLEN))
+	    (left->br_blockcount + got->br_blockcount > XFS_MAX_BMBT_EXTLEN) ||
+	    !xfs_bmap_same_rtgroup(ip, whichfork, left, got))
 		return false;
 
 	return true;
@@ -5797,7 +5818,7 @@ xfs_bmse_merge(
 	blockcount = left->br_blockcount + got->br_blockcount;
 
 	xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
-	ASSERT(xfs_bmse_can_merge(left, got, shift));
+	ASSERT(xfs_bmse_can_merge(ip, whichfork, left, got, shift));
 
 	new = *left;
 	new.br_blockcount = blockcount;
@@ -5959,7 +5980,8 @@ xfs_bmap_collapse_extents(
 			goto del_cursor;
 		}
 
-		if (xfs_bmse_can_merge(&prev, &got, offset_shift_fsb)) {
+		if (xfs_bmse_can_merge(ip, whichfork, &prev, &got,
+				offset_shift_fsb)) {
 			error = xfs_bmse_merge(tp, ip, whichfork,
 					offset_shift_fsb, &icur, &got, &prev,
 					cur, &logflags);
@@ -6095,7 +6117,8 @@ xfs_bmap_insert_extents(
 		 * never find mergeable extents in this scenario.  Check anyways
 		 * and warn if we encounter two extents that could be one.
 		 */
-		if (xfs_bmse_can_merge(&got, &next, offset_shift_fsb))
+		if (xfs_bmse_can_merge(ip, whichfork, &got, &next,
+				offset_shift_fsb))
 			WARN_ON_ONCE(1);
 	}