xfs: dynamically allocate cursors based on maxlevels

Replace the statically-sized btree cursor zone with dynamically sized
allocations so that we can reduce the memory overhead for per-AG bt
cursors while handling very tall btrees for rt metadata.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>

3 files changed, 33 insertions, 20 deletions

diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 536f2a9bdc73..661525996a96 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -24,11 +24,6 @@
 #include "xfs_health.h"
 
 /*
- * Cursor allocation zone.
- */
-kmem_zone_t	*xfs_btree_cur_zone;
-
-/*
  * Btree magic numbers.
  */
 static const uint32_t xfs_magics[2][XFS_BTNUM_MAX] = {
@@ -385,7 +380,7 @@ xfs_btree_del_cursor(
 	       XFS_FORCED_SHUTDOWN(cur->bc_mp));
 	if (unlikely(cur->bc_flags & XFS_BTREE_STAGING))
 		kmem_free(cur->bc_ops);
-	kmem_cache_free(xfs_btree_cur_zone, cur);
+	kmem_free(cur);
 }
 
 /*
@@ -5229,6 +5224,32 @@ xfs_btree_has_more_records(
 		return block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK);
 }
 
+/* Compute the maximum allowed height for a given btree type. */
+static unsigned int
+xfs_btree_maxlevels(
+	struct xfs_mount	*mp,
+	xfs_btnum_t		btnum)
+{
+	switch (btnum) {
+	case XFS_BTNUM_BNO:
+	case XFS_BTNUM_CNT:
+		return mp->m_ag_maxlevels;
+	case XFS_BTNUM_BMAP:
+		return max(mp->m_bm_maxlevels[XFS_DATA_FORK],
+			   mp->m_bm_maxlevels[XFS_ATTR_FORK]);
+	case XFS_BTNUM_INO:
+	case XFS_BTNUM_FINO:
+		return M_IGEO(mp)->inobt_maxlevels;
+	case XFS_BTNUM_RMAP:
+		return mp->m_rmap_maxlevels;
+	case XFS_BTNUM_REFC:
+		return mp->m_refc_maxlevels;
+	default:
+		ASSERT(0);
+		return XFS_BTREE_MAXLEVELS;
+	}
+}
+
 /* Allocate a new btree cursor of the appropriate size. */
 struct xfs_btree_cur *
 xfs_btree_alloc_cursor(
@@ -5237,13 +5258,16 @@ xfs_btree_alloc_cursor(
 	xfs_btnum_t		btnum)
 {
 	struct xfs_btree_cur	*cur;
+	unsigned int		maxlevels = xfs_btree_maxlevels(mp, btnum);
+
+	ASSERT(maxlevels <= XFS_BTREE_MAXLEVELS);
 
-	cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL);
+	cur = kmem_zalloc(xfs_btree_cur_sizeof(maxlevels), KM_NOFS);
 	cur->bc_tp = tp;
 	cur->bc_mp = mp;
 	cur->bc_btnum = btnum;
 	cur->bc_blocklog = mp->m_sb.sb_blocklog;
-	cur->bc_maxlevels = XFS_BTREE_MAXLEVELS;
+	cur->bc_maxlevels = maxlevels;
 
 	return cur;
 }
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index dc154a071ad8..2b9e6e5ba89c 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -12,8 +12,6 @@ struct xfs_mount;
 struct xfs_trans;
 struct xfs_ifork;
 
-extern kmem_zone_t	*xfs_btree_cur_zone;
-
 /*
  * Generic key, ptr and record wrapper structures.
  *
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index ca040046c16b..63aebba355c7 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -2016,17 +2016,11 @@ xfs_init_zones(void)
 	if (!xfs_bmap_free_item_zone)
 		goto out_destroy_log_ticket_zone;
 
-	xfs_btree_cur_zone = kmem_cache_create("xfs_btree_cur",
-				xfs_btree_cur_sizeof(XFS_BTREE_MAXLEVELS),
-					       0, 0, NULL);
-	if (!xfs_btree_cur_zone)
-		goto out_destroy_bmap_free_item_zone;
-
 	xfs_da_state_zone = kmem_cache_create("xfs_da_state",
 					      sizeof(struct xfs_da_state),
 					      0, 0, NULL);
 	if (!xfs_da_state_zone)
-		goto out_destroy_btree_cur_zone;
+		goto out_destroy_bmap_free_item_zone;
 
 	xfs_ifork_zone = kmem_cache_create("xfs_ifork",
 					   sizeof(struct xfs_ifork),
@@ -2172,8 +2166,6 @@ xfs_init_zones(void)
 	kmem_cache_destroy(xfs_ifork_zone);
  out_destroy_da_state_zone:
 	kmem_cache_destroy(xfs_da_state_zone);
- out_destroy_btree_cur_zone:
-	kmem_cache_destroy(xfs_btree_cur_zone);
  out_destroy_bmap_free_item_zone:
 	kmem_cache_destroy(xfs_bmap_free_item_zone);
  out_destroy_log_ticket_zone:
@@ -2205,7 +2197,6 @@ xfs_destroy_zones(void)
 	kmem_cache_destroy(xfs_trans_zone);
 	kmem_cache_destroy(xfs_ifork_zone);
 	kmem_cache_destroy(xfs_da_state_zone);
-	kmem_cache_destroy(xfs_btree_cur_zone);
 	kmem_cache_destroy(xfs_bmap_free_item_zone);
 	kmem_cache_destroy(xfs_log_ticket_zone);
 }