Merge tag 'xfs-5.16-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Darrick Wong:
 "This cycle we've worked on fixing bugs and improving XFS' memory
  footprint.

  The most notable fixes include: fixing a corruption warning (and free
  space accounting skew) if copy on write fails; fixing slab cache
  misuse if SLOB is enabled, which apparently was broken for years
  without anybody noticing; and fixing a potential race with online
  shrinkfs.

  Otherwise, the bulk of the changes here involve setting up separate
  slab caches for frequently used items such as btree cursors and log
  intent items, and compacting the structures to reduce memory usage of
  those items substantially. This also sets us up to support larger
  btrees in future kernels. We also switch parts of online fsck to
  allocate scrub context information from the heap instead of using
  stack space.

  Summary:

   - Bug fixes and cleanups for kernel memory allocation usage, this
     time without touching the mm code.

   - Refactor the log recovery mechanism that preserves held resources
     across a transaction roll so that it uses the exact same mechanism
     that we use for that during regular runtime.

   - Fix bugs and tighten checking around btree heights.

   - Remove more old typedefs.

   - Fix perag reference leaks when racing with growfs.

   - Remove unused fields from xfs_btree_cur.

   - Allocate various scrub structures on the heap to reduce stack
     usage.

   - Pack xfs_btree_cur fields and rearrange to support arbitrary
     heights.

   - Compute maximum possible heights for each btree height, and use
     that to set up slab caches for each btree type.

   - Finally remove kmem_zone_t, since these have always been struct
     kmem_cache on Linux.

   - Compact the structures used to coordinate work intent items.

   - Set up slab caches for each work intent item type.

   - Rename the "bmap_add_free" function to "free_extent_later", which
     more accurately describes what it does.

   - Fix corruption warning on unmount when a CoW preallocation covers a
     data fork delalloc reservation but then the CoW fails.

   - Add some more minor code improvements"

* tag 'xfs-5.16-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (45 commits)
  xfs: use swap() to make code cleaner
  xfs: Remove duplicated include in xfs_super
  xfs: punch out data fork delalloc blocks on COW writeback failure
  xfs: remove unused parameter from refcount code
  xfs: reduce the size of struct xfs_extent_free_item
  xfs: rename xfs_bmap_add_free to xfs_free_extent_later
  xfs: create slab caches for frequently-used deferred items
  xfs: compact deferred intent item structures
  xfs: rename _zone variables to _cache
  xfs: remove kmem_zone typedef
  xfs: use separate btree cursor cache for each btree type
  xfs: compute absolute maximum nlevels for each btree type
  xfs: kill XFS_BTREE_MAXLEVELS
  xfs: compute the maximum height of the rmap btree when reflink enabled
  xfs: clean up xfs_btree_{calc_size,compute_maxlevels}
  xfs: compute maximum AG btree height for critical reservation calculation
  xfs: rename m_ag_maxlevels to m_allocbt_maxlevels
  xfs: dynamically allocate cursors based on maxlevels
  xfs: encode the max btree height in the cursor
  xfs: refactor btree cursor allocation function
  ...

1 files changed, 52 insertions, 10 deletions

diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 72444b8b38a6..453309fc85f2 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -22,6 +22,8 @@
 #include "xfs_trace.h"
 #include "xfs_rmap.h"
 
+static struct kmem_cache	*xfs_bmbt_cur_cache;
+
 /*
  * Convert on-disk form of btree root to in-memory form.
  */
@@ -286,7 +288,7 @@ xfs_bmbt_free_block(
 	struct xfs_owner_info	oinfo;
 
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork);
-	xfs_bmap_add_free(cur->bc_tp, fsbno, 1, &oinfo);
+	xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo);
 	ip->i_nblocks--;
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
@@ -552,13 +554,9 @@ xfs_bmbt_init_cursor(
 	struct xfs_btree_cur	*cur;
 	ASSERT(whichfork != XFS_COW_FORK);
 
-	cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL);
-
-	cur->bc_tp = tp;
-	cur->bc_mp = mp;
+	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_BMAP,
+			mp->m_bm_maxlevels[whichfork], xfs_bmbt_cur_cache);
 	cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
-	cur->bc_btnum = XFS_BTNUM_BMAP;
-	cur->bc_blocklog = mp->m_sb.sb_blocklog;
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2);
 
 	cur->bc_ops = &xfs_bmbt_ops;
@@ -575,6 +573,17 @@ xfs_bmbt_init_cursor(
 	return cur;
 }
 
+/* Calculate number of records in a block mapping btree block. */
+static inline unsigned int
+xfs_bmbt_block_maxrecs(
+	unsigned int		blocklen,
+	bool			leaf)
+{
+	if (leaf)
+		return blocklen / sizeof(xfs_bmbt_rec_t);
+	return blocklen / (sizeof(xfs_bmbt_key_t) + sizeof(xfs_bmbt_ptr_t));
+}
+
 /*
  * Calculate number of records in a bmap btree block.
  */
@@ -585,10 +594,24 @@ xfs_bmbt_maxrecs(
 	int			leaf)
 {
 	blocklen -= XFS_BMBT_BLOCK_LEN(mp);
+	return xfs_bmbt_block_maxrecs(blocklen, leaf);
+}
 
-	if (leaf)
-		return blocklen / sizeof(xfs_bmbt_rec_t);
-	return blocklen / (sizeof(xfs_bmbt_key_t) + sizeof(xfs_bmbt_ptr_t));
+/* Compute the max possible height for block mapping btrees. */
+unsigned int
+xfs_bmbt_maxlevels_ondisk(void)
+{
+	unsigned int		minrecs[2];
+	unsigned int		blocklen;
+
+	blocklen = min(XFS_MIN_BLOCKSIZE - XFS_BTREE_SBLOCK_LEN,
+		       XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_SBLOCK_CRC_LEN);
+
+	minrecs[0] = xfs_bmbt_block_maxrecs(blocklen, true) / 2;
+	minrecs[1] = xfs_bmbt_block_maxrecs(blocklen, false) / 2;
+
+	/* One extra level for the inode root. */
+	return xfs_btree_compute_maxlevels(minrecs, MAXEXTNUM) + 1;
 }
 
 /*
@@ -654,3 +677,22 @@ xfs_bmbt_calc_size(
 {
 	return xfs_btree_calc_size(mp->m_bmap_dmnr, len);
 }
+
+int __init
+xfs_bmbt_init_cur_cache(void)
+{
+	xfs_bmbt_cur_cache = kmem_cache_create("xfs_bmbt_cur",
+			xfs_btree_cur_sizeof(xfs_bmbt_maxlevels_ondisk()),
+			0, 0, NULL);
+
+	if (!xfs_bmbt_cur_cache)
+		return -ENOMEM;
+	return 0;
+}
+
+void
+xfs_bmbt_destroy_cur_cache(void)
+{
+	kmem_cache_destroy(xfs_bmbt_cur_cache);
+	xfs_bmbt_cur_cache = NULL;
+}