Merge tag 'xfs-6.12-merge-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Chandan Babu:
 "New code:

   - Introduce new ioctls to exchange contents of two files.

     The first ioctl does the preparation work to exchange the contents
     of two files while the second ioctl performs the actual exchange if
     the target file has not been changed since a given sampling point.

  Fixes:

   - Fix bugs associated with calculating the maximum range of realtime
     extents to scan for free space.

   - Copy keys instead of records when resizing the incore BMBT root
     block.

   - Do not report FITRIMming more bytes than possibly exist in the
     filesystem.

   - Modify xfs_fs.h to prevent C++ compilation errors.

   - Do not over eagerly free post-EOF speculative preallocation.

   - Ensure st_blocks never goes to zero during COW writes

  Cleanups/refactors:

   - Use Xarray to hold per-AG data instead of a Radix tree.

   - Cleanups to:
      - realtime bitmap
      - inode allocator
      - quota
      - inode rooted btree code"

* tag 'xfs-6.12-merge-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (61 commits)
  xfs: ensure st_blocks never goes to zero during COW writes
  xfs: use xas_for_each_marked in xfs_reclaim_inodes_count
  xfs: convert perag lookup to xarray
  xfs: simplify tagged perag iteration
  xfs: move the tagged perag lookup helpers to xfs_icache.c
  xfs: use kfree_rcu_mightsleep to free the perag structures
  xfs: use LIST_HEAD() to simplify code
  xfs: Remove duplicate xfs_trans_priv.h header
  xfs: remove unnecessary check
  xfs: Use xfs set and clear mp state helpers
  xfs: reclaim speculative preallocations for append only files
  xfs: simplify extent lookup in xfs_can_free_eofblocks
  xfs: check XFS_EOFBLOCKS_RELEASED earlier in xfs_release_eofblocks
  xfs: only free posteof blocks on first close
  xfs: don't free post-EOF blocks on read close
  xfs: skip all of xfs_file_release when shut down
  xfs: don't bother returning errors from xfs_file_release
  xfs: refactor f_op->release handling
  xfs: remove the i_mode check in xfs_release
  xfs: standardize the btree maxrecs function parameters
  ...

1 files changed, 57 insertions, 46 deletions

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 7df74c35d9f9..8090e8249116 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -79,9 +79,9 @@ xfs_bmap_compute_maxlevels(
 	maxleafents = xfs_iext_max_nextents(xfs_has_large_extent_counts(mp),
 				whichfork);
 	if (whichfork == XFS_DATA_FORK)
-		sz = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
+		sz = xfs_bmdr_space_calc(MINDBTPTRS);
 	else
-		sz = XFS_BMDR_SPACE_CALC(MINABTPTRS);
+		sz = xfs_bmdr_space_calc(MINABTPTRS);
 
 	maxrootrecs = xfs_bmdr_maxrecs(sz, 0);
 	minleafrecs = mp->m_bmap_dmnr[0];
@@ -102,8 +102,8 @@ xfs_bmap_compute_attr_offset(
 	struct xfs_mount	*mp)
 {
 	if (mp->m_sb.sb_inodesize == 256)
-		return XFS_LITINO(mp) - XFS_BMDR_SPACE_CALC(MINABTPTRS);
-	return XFS_BMDR_SPACE_CALC(6 * MINABTPTRS);
+		return XFS_LITINO(mp) - xfs_bmdr_space_calc(MINABTPTRS);
+	return xfs_bmdr_space_calc(6 * MINABTPTRS);
 }
 
 STATIC int				/* error */
@@ -298,7 +298,7 @@ xfs_check_block(
 	prevp = NULL;
 	for( i = 1; i <= xfs_btree_get_numrecs(block); i++) {
 		dmxr = mp->m_bmap_dmxr[0];
-		keyp = XFS_BMBT_KEY_ADDR(mp, block, i);
+		keyp = xfs_bmbt_key_addr(mp, block, i);
 
 		if (prevp) {
 			ASSERT(be64_to_cpu(prevp->br_startoff) <
@@ -310,15 +310,15 @@ xfs_check_block(
 		 * Compare the block numbers to see if there are dups.
 		 */
 		if (root)
-			pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, i, sz);
+			pp = xfs_bmap_broot_ptr_addr(mp, block, i, sz);
 		else
-			pp = XFS_BMBT_PTR_ADDR(mp, block, i, dmxr);
+			pp = xfs_bmbt_ptr_addr(mp, block, i, dmxr);
 
 		for (j = i+1; j <= be16_to_cpu(block->bb_numrecs); j++) {
 			if (root)
-				thispa = XFS_BMAP_BROOT_PTR_ADDR(mp, block, j, sz);
+				thispa = xfs_bmap_broot_ptr_addr(mp, block, j, sz);
 			else
-				thispa = XFS_BMBT_PTR_ADDR(mp, block, j, dmxr);
+				thispa = xfs_bmbt_ptr_addr(mp, block, j, dmxr);
 			if (*thispa == *pp) {
 				xfs_warn(mp, "%s: thispa(%d) == pp(%d) %lld",
 					__func__, j, i,
@@ -373,7 +373,7 @@ xfs_bmap_check_leaf_extents(
 	level = be16_to_cpu(block->bb_level);
 	ASSERT(level > 0);
 	xfs_check_block(block, mp, 1, ifp->if_broot_bytes);
-	pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
+	pp = xfs_bmap_broot_ptr_addr(mp, block, 1, ifp->if_broot_bytes);
 	bno = be64_to_cpu(*pp);
 
 	ASSERT(bno != NULLFSBLOCK);
@@ -406,7 +406,7 @@ xfs_bmap_check_leaf_extents(
 		 */
 
 		xfs_check_block(block, mp, 0, 0);
-		pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
+		pp = xfs_bmbt_ptr_addr(mp, block, 1, mp->m_bmap_dmxr[1]);
 		bno = be64_to_cpu(*pp);
 		if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, bno))) {
 			xfs_btree_mark_sick(cur);
@@ -446,14 +446,14 @@ xfs_bmap_check_leaf_extents(
 		 * conform with the first entry in this one.
 		 */
 
-		ep = XFS_BMBT_REC_ADDR(mp, block, 1);
+		ep = xfs_bmbt_rec_addr(mp, block, 1);
 		if (i) {
 			ASSERT(xfs_bmbt_disk_get_startoff(&last) +
 			       xfs_bmbt_disk_get_blockcount(&last) <=
 			       xfs_bmbt_disk_get_startoff(ep));
 		}
 		for (j = 1; j < num_recs; j++) {
-			nextp = XFS_BMBT_REC_ADDR(mp, block, j + 1);
+			nextp = xfs_bmbt_rec_addr(mp, block, j + 1);
 			ASSERT(xfs_bmbt_disk_get_startoff(ep) +
 			       xfs_bmbt_disk_get_blockcount(ep) <=
 			       xfs_bmbt_disk_get_startoff(nextp));
@@ -584,9 +584,9 @@ xfs_bmap_btree_to_extents(
 	ASSERT(ifp->if_format == XFS_DINODE_FMT_BTREE);
 	ASSERT(be16_to_cpu(rblock->bb_level) == 1);
 	ASSERT(be16_to_cpu(rblock->bb_numrecs) == 1);
-	ASSERT(xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, 0) == 1);
+	ASSERT(xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, false) == 1);
 
-	pp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, ifp->if_broot_bytes);
+	pp = xfs_bmap_broot_ptr_addr(mp, rblock, 1, ifp->if_broot_bytes);
 	cbno = be64_to_cpu(*pp);
 #ifdef DEBUG
 	if (XFS_IS_CORRUPT(cur->bc_mp, !xfs_verify_fsbno(mp, cbno))) {
@@ -714,7 +714,7 @@ xfs_bmap_extents_to_btree(
 	for_each_xfs_iext(ifp, &icur, &rec) {
 		if (isnullstartblock(rec.br_startblock))
 			continue;
-		arp = XFS_BMBT_REC_ADDR(mp, ablock, 1 + cnt);
+		arp = xfs_bmbt_rec_addr(mp, ablock, 1 + cnt);
 		xfs_bmbt_disk_set_all(arp, &rec);
 		cnt++;
 	}
@@ -724,10 +724,10 @@ xfs_bmap_extents_to_btree(
 	/*
 	 * Fill in the root key and pointer.
 	 */
-	kp = XFS_BMBT_KEY_ADDR(mp, block, 1);
-	arp = XFS_BMBT_REC_ADDR(mp, ablock, 1);
+	kp = xfs_bmbt_key_addr(mp, block, 1);
+	arp = xfs_bmbt_rec_addr(mp, ablock, 1);
 	kp->br_startoff = cpu_to_be64(xfs_bmbt_disk_get_startoff(arp));
-	pp = XFS_BMBT_PTR_ADDR(mp, block, 1, xfs_bmbt_get_maxrecs(cur,
+	pp = xfs_bmbt_ptr_addr(mp, block, 1, xfs_bmbt_get_maxrecs(cur,
 						be16_to_cpu(block->bb_level)));
 	*pp = cpu_to_be64(args.fsbno);
 
@@ -896,7 +896,7 @@ xfs_bmap_add_attrfork_btree(
 
 	mp = ip->i_mount;
 
-	if (XFS_BMAP_BMDR_SPACE(block) <= xfs_inode_data_fork_size(ip))
+	if (xfs_bmap_bmdr_space(block) <= xfs_inode_data_fork_size(ip))
 		*flags |= XFS_ILOG_DBROOT;
 	else {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
@@ -1160,7 +1160,7 @@ xfs_iread_bmbt_block(
 	}
 
 	/* Copy records into the incore cache. */
-	frp = XFS_BMBT_REC_ADDR(mp, block, 1);
+	frp = xfs_bmbt_rec_addr(mp, block, 1);
 	for (j = 0; j < num_recs; j++, frp++, ir->loaded++) {
 		struct xfs_bmbt_irec	new;
 		xfs_failaddr_t		fa;
@@ -3112,6 +3112,23 @@ xfs_bmap_extsize_align(
 	return 0;
 }
 
+static inline bool
+xfs_bmap_adjacent_valid(
+	struct xfs_bmalloca	*ap,
+	xfs_fsblock_t		x,
+	xfs_fsblock_t		y)
+{
+	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;
+
+	return XFS_FSB_TO_AGNO(mp, x) == XFS_FSB_TO_AGNO(mp, y) &&
+		XFS_FSB_TO_AGNO(mp, x) < mp->m_sb.sb_agcount &&
+		XFS_FSB_TO_AGBNO(mp, x) < mp->m_sb.sb_agblocks;
+}
+
 #define XFS_ALLOC_GAP_UNITS	4
 
 /* returns true if ap->blkno was modified */
@@ -3119,36 +3136,25 @@ bool
 xfs_bmap_adjacent(
 	struct xfs_bmalloca	*ap)	/* bmap alloc argument struct */
 {
-	xfs_fsblock_t	adjust;		/* adjustment to block numbers */
-	xfs_mount_t	*mp;		/* mount point structure */
-	int		rt;		/* true if inode is realtime */
-
-#define	ISVALID(x,y)	\
-	(rt ? \
-		(x) < mp->m_sb.sb_rblocks : \
-		XFS_FSB_TO_AGNO(mp, x) == XFS_FSB_TO_AGNO(mp, y) && \
-		XFS_FSB_TO_AGNO(mp, x) < mp->m_sb.sb_agcount && \
-		XFS_FSB_TO_AGBNO(mp, x) < mp->m_sb.sb_agblocks)
-
-	mp = ap->ip->i_mount;
-	rt = XFS_IS_REALTIME_INODE(ap->ip) &&
-		(ap->datatype & XFS_ALLOC_USERDATA);
+	xfs_fsblock_t		adjust;		/* adjustment to block numbers */
+
 	/*
 	 * If allocating at eof, and there's a previous real block,
 	 * try to use its last block as our starting point.
 	 */
 	if (ap->eof && ap->prev.br_startoff != NULLFILEOFF &&
 	    !isnullstartblock(ap->prev.br_startblock) &&
-	    ISVALID(ap->prev.br_startblock + ap->prev.br_blockcount,
-		    ap->prev.br_startblock)) {
+	    xfs_bmap_adjacent_valid(ap,
+			ap->prev.br_startblock + ap->prev.br_blockcount,
+			ap->prev.br_startblock)) {
 		ap->blkno = ap->prev.br_startblock + ap->prev.br_blockcount;
 		/*
 		 * Adjust for the gap between prevp and us.
 		 */
 		adjust = ap->offset -
 			(ap->prev.br_startoff + ap->prev.br_blockcount);
-		if (adjust &&
-		    ISVALID(ap->blkno + adjust, ap->prev.br_startblock))
+		if (adjust && xfs_bmap_adjacent_valid(ap, ap->blkno + adjust,
+				ap->prev.br_startblock))
 			ap->blkno += adjust;
 		return true;
 	}
@@ -3171,7 +3177,8 @@ xfs_bmap_adjacent(
 		    !isnullstartblock(ap->prev.br_startblock) &&
 		    (prevbno = ap->prev.br_startblock +
 			       ap->prev.br_blockcount) &&
-		    ISVALID(prevbno, ap->prev.br_startblock)) {
+		    xfs_bmap_adjacent_valid(ap, prevbno,
+				ap->prev.br_startblock)) {
 			/*
 			 * Calculate gap to end of previous block.
 			 */
@@ -3187,8 +3194,8 @@ xfs_bmap_adjacent(
 			 * number, then just use the end of the previous block.
 			 */
 			if (prevdiff <= XFS_ALLOC_GAP_UNITS * ap->length &&
-			    ISVALID(prevbno + prevdiff,
-				    ap->prev.br_startblock))
+			    xfs_bmap_adjacent_valid(ap, prevbno + prevdiff,
+					ap->prev.br_startblock))
 				prevbno += adjust;
 			else
 				prevdiff += adjust;
@@ -3220,9 +3227,11 @@ xfs_bmap_adjacent(
 			 * offset by our length.
 			 */
 			if (gotdiff <= XFS_ALLOC_GAP_UNITS * ap->length &&
-			    ISVALID(gotbno - gotdiff, gotbno))
+			    xfs_bmap_adjacent_valid(ap, gotbno - gotdiff,
+					gotbno))
 				gotbno -= adjust;
-			else if (ISVALID(gotbno - ap->length, gotbno)) {
+			else if (xfs_bmap_adjacent_valid(ap, gotbno - ap->length,
+					gotbno)) {
 				gotbno -= ap->length;
 				gotdiff += adjust - ap->length;
 			} else
@@ -3250,7 +3259,7 @@ xfs_bmap_adjacent(
 			return true;
 		}
 	}
-#undef ISVALID
+
 	return false;
 }
 
@@ -4847,6 +4856,7 @@ xfs_bmapi_remap(
 	}
 
 	ip->i_nblocks += len;
+	ip->i_delayed_blks -= len; /* see xfs_bmap_defer_add */
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 	if (ifp->if_format == XFS_DINODE_FMT_BTREE)
@@ -5376,7 +5386,8 @@ xfs_bmap_del_extent_real(
 			 */
 			if (!(tp->t_flags & XFS_TRANS_RTBITMAP_LOCKED)) {
 				tp->t_flags |= XFS_TRANS_RTBITMAP_LOCKED;
-				xfs_rtbitmap_lock(tp, mp);
+				xfs_rtbitmap_lock(mp);
+				xfs_rtbitmap_trans_join(tp);
 			}
 			error = xfs_rtfree_blocks(tp, del->br_startblock,
 					del->br_blockcount);