1 files changed, 181 insertions, 77 deletions

diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 38529dbacd55..e1f789866683 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -9,42 +9,44 @@
 #include "xfs_format.h"
 #include "xfs_log_format.h"
 #include "xfs_trans_resv.h"
-#include "xfs_sb.h"
 #include "xfs_mount.h"
 #include "xfs_btree.h"
+#include "xfs_btree_staging.h"
 #include "xfs_refcount_btree.h"
+#include "xfs_refcount.h"
 #include "xfs_alloc.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_trans.h"
 #include "xfs_bit.h"
 #include "xfs_rmap.h"
+#include "xfs_ag.h"
+
+static struct kmem_cache	*xfs_refcountbt_cur_cache;
 
 static struct xfs_btree_cur *
 xfs_refcountbt_dup_cursor(
 	struct xfs_btree_cur	*cur)
 {
 	return xfs_refcountbt_init_cursor(cur->bc_mp, cur->bc_tp,
-			cur->bc_private.a.agbp, cur->bc_private.a.agno);
+			cur->bc_ag.agbp, cur->bc_ag.pag);
 }
 
 STATIC void
 xfs_refcountbt_set_root(
-	struct xfs_btree_cur	*cur,
-	union xfs_btree_ptr	*ptr,
-	int			inc)
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*ptr,
+	int				inc)
 {
-	struct xfs_buf		*agbp = cur->bc_private.a.agbp;
-	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agbp);
-	xfs_agnumber_t		seqno = be32_to_cpu(agf->agf_seqno);
-	struct xfs_perag	*pag = xfs_perag_get(cur->bc_mp, seqno);
+	struct xfs_buf		*agbp = cur->bc_ag.agbp;
+	struct xfs_agf		*agf = agbp->b_addr;
+	struct xfs_perag	*pag = agbp->b_pag;
 
 	ASSERT(ptr->s != 0);
 
 	agf->agf_refcount_root = ptr->s;
 	be32_add_cpu(&agf->agf_refcount_level, inc);
 	pag->pagf_refcount_level += inc;
-	xfs_perag_put(pag);
 
 	xfs_alloc_log_agf(cur->bc_tp, agbp,
 			XFS_AGF_REFCOUNT_ROOT | XFS_AGF_REFCOUNT_LEVEL);
@@ -52,13 +54,13 @@ xfs_refcountbt_set_root(
 
 STATIC int
 xfs_refcountbt_alloc_block(
-	struct xfs_btree_cur	*cur,
-	union xfs_btree_ptr	*start,
-	union xfs_btree_ptr	*new,
-	int			*stat)
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*start,
+	union xfs_btree_ptr		*new,
+	int				*stat)
 {
-	struct xfs_buf		*agbp = cur->bc_private.a.agbp;
-	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agbp);
+	struct xfs_buf		*agbp = cur->bc_ag.agbp;
+	struct xfs_agf		*agf = agbp->b_addr;
 	struct xfs_alloc_arg	args;		/* block allocation args */
 	int			error;		/* error return value */
 
@@ -66,7 +68,7 @@ xfs_refcountbt_alloc_block(
 	args.tp = cur->bc_tp;
 	args.mp = cur->bc_mp;
 	args.type = XFS_ALLOCTYPE_NEAR_BNO;
-	args.fsbno = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_private.a.agno,
+	args.fsbno = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_ag.pag->pag_agno,
 			xfs_refc_block(args.mp));
 	args.oinfo = XFS_RMAP_OINFO_REFC;
 	args.minlen = args.maxlen = args.prod = 1;
@@ -75,13 +77,13 @@ xfs_refcountbt_alloc_block(
 	error = xfs_alloc_vextent(&args);
 	if (error)
 		goto out_error;
-	trace_xfs_refcountbt_alloc_block(cur->bc_mp, cur->bc_private.a.agno,
+	trace_xfs_refcountbt_alloc_block(cur->bc_mp, cur->bc_ag.pag->pag_agno,
 			args.agbno, 1);
 	if (args.fsbno == NULLFSBLOCK) {
 		*stat = 0;
 		return 0;
 	}
-	ASSERT(args.agno == cur->bc_private.a.agno);
+	ASSERT(args.agno == cur->bc_ag.pag->pag_agno);
 	ASSERT(args.len == 1);
 
 	new->s = cpu_to_be32(args.agbno);
@@ -101,12 +103,12 @@ xfs_refcountbt_free_block(
 	struct xfs_buf		*bp)
 {
 	struct xfs_mount	*mp = cur->bc_mp;
-	struct xfs_buf		*agbp = cur->bc_private.a.agbp;
-	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agbp);
-	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, XFS_BUF_ADDR(bp));
+	struct xfs_buf		*agbp = cur->bc_ag.agbp;
+	struct xfs_agf		*agf = agbp->b_addr;
+	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
 	int			error;
 
-	trace_xfs_refcountbt_free_block(cur->bc_mp, cur->bc_private.a.agno,
+	trace_xfs_refcountbt_free_block(cur->bc_mp, cur->bc_ag.pag->pag_agno,
 			XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1);
 	be32_add_cpu(&agf->agf_refcount_blocks, -1);
 	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS);
@@ -136,18 +138,18 @@ xfs_refcountbt_get_maxrecs(
 
 STATIC void
 xfs_refcountbt_init_key_from_rec(
-	union xfs_btree_key	*key,
-	union xfs_btree_rec	*rec)
+	union xfs_btree_key		*key,
+	const union xfs_btree_rec	*rec)
 {
 	key->refc.rc_startblock = rec->refc.rc_startblock;
 }
 
 STATIC void
 xfs_refcountbt_init_high_key_from_rec(
-	union xfs_btree_key	*key,
-	union xfs_btree_rec	*rec)
+	union xfs_btree_key		*key,
+	const union xfs_btree_rec	*rec)
 {
-	__u32			x;
+	__u32				x;
 
 	x = be32_to_cpu(rec->refc.rc_startblock);
 	x += be32_to_cpu(rec->refc.rc_blockcount) - 1;
@@ -159,7 +161,12 @@ xfs_refcountbt_init_rec_from_cur(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_rec	*rec)
 {
-	rec->refc.rc_startblock = cpu_to_be32(cur->bc_rec.rc.rc_startblock);
+	const struct xfs_refcount_irec *irec = &cur->bc_rec.rc;
+	uint32_t		start;
+
+	start = xfs_refcount_encode_startblock(irec->rc_startblock,
+			irec->rc_domain);
+	rec->refc.rc_startblock = cpu_to_be32(start);
 	rec->refc.rc_blockcount = cpu_to_be32(cur->bc_rec.rc.rc_blockcount);
 	rec->refc.rc_refcount = cpu_to_be32(cur->bc_rec.rc.rc_refcount);
 }
@@ -169,29 +176,32 @@ xfs_refcountbt_init_ptr_from_cur(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_ptr	*ptr)
 {
-	struct xfs_agf		*agf = XFS_BUF_TO_AGF(cur->bc_private.a.agbp);
+	struct xfs_agf		*agf = cur->bc_ag.agbp->b_addr;
 
-	ASSERT(cur->bc_private.a.agno == be32_to_cpu(agf->agf_seqno));
+	ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agf->agf_seqno));
 
 	ptr->s = agf->agf_refcount_root;
 }
 
 STATIC int64_t
 xfs_refcountbt_key_diff(
-	struct xfs_btree_cur	*cur,
-	union xfs_btree_key	*key)
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*key)
 {
-	struct xfs_refcount_irec	*rec = &cur->bc_rec.rc;
-	struct xfs_refcount_key		*kp = &key->refc;
+	const struct xfs_refcount_key	*kp = &key->refc;
+	const struct xfs_refcount_irec	*irec = &cur->bc_rec.rc;
+	uint32_t			start;
 
-	return (int64_t)be32_to_cpu(kp->rc_startblock) - rec->rc_startblock;
+	start = xfs_refcount_encode_startblock(irec->rc_startblock,
+			irec->rc_domain);
+	return (int64_t)be32_to_cpu(kp->rc_startblock) - start;
 }
 
 STATIC int64_t
 xfs_refcountbt_diff_two_keys(
-	struct xfs_btree_cur	*cur,
-	union xfs_btree_key	*k1,
-	union xfs_btree_key	*k2)
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*k1,
+	const union xfs_btree_key	*k2)
 {
 	return (int64_t)be32_to_cpu(k1->refc.rc_startblock) -
 			  be32_to_cpu(k2->refc.rc_startblock);
@@ -210,7 +220,7 @@ xfs_refcountbt_verify(
 	if (!xfs_verify_magic(bp, block->bb_magic))
 		return __this_address;
 
-	if (!xfs_sb_version_hasreflink(&mp->m_sb))
+	if (!xfs_has_reflink(mp))
 		return __this_address;
 	fa = xfs_btree_sblock_v5hdr_verify(bp);
 	if (fa)
@@ -270,9 +280,9 @@ const struct xfs_buf_ops xfs_refcountbt_buf_ops = {
 
 STATIC int
 xfs_refcountbt_keys_inorder(
-	struct xfs_btree_cur	*cur,
-	union xfs_btree_key	*k1,
-	union xfs_btree_key	*k2)
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*k1,
+	const union xfs_btree_key	*k2)
 {
 	return be32_to_cpu(k1->refc.rc_startblock) <
 	       be32_to_cpu(k2->refc.rc_startblock);
@@ -280,9 +290,9 @@ xfs_refcountbt_keys_inorder(
 
 STATIC int
 xfs_refcountbt_recs_inorder(
-	struct xfs_btree_cur	*cur,
-	union xfs_btree_rec	*r1,
-	union xfs_btree_rec	*r2)
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_rec	*r1,
+	const union xfs_btree_rec	*r2)
 {
 	return  be32_to_cpu(r1->refc.rc_startblock) +
 		be32_to_cpu(r1->refc.rc_blockcount) <=
@@ -311,42 +321,102 @@ static const struct xfs_btree_ops xfs_refcountbt_ops = {
 };
 
 /*
- * Allocate a new refcount btree cursor.
+ * Initialize a new refcount btree cursor.
  */
-struct xfs_btree_cur *
-xfs_refcountbt_init_cursor(
+static struct xfs_btree_cur *
+xfs_refcountbt_init_common(
 	struct xfs_mount	*mp,
 	struct xfs_trans	*tp,
-	struct xfs_buf		*agbp,
-	xfs_agnumber_t		agno)
+	struct xfs_perag	*pag)
 {
-	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agbp);
 	struct xfs_btree_cur	*cur;
 
-	ASSERT(agno != NULLAGNUMBER);
-	ASSERT(agno < mp->m_sb.sb_agcount);
-	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_NOFS);
+	ASSERT(pag->pag_agno < mp->m_sb.sb_agcount);
 
-	cur->bc_tp = tp;
-	cur->bc_mp = mp;
-	cur->bc_btnum = XFS_BTNUM_REFC;
-	cur->bc_blocklog = mp->m_sb.sb_blocklog;
-	cur->bc_ops = &xfs_refcountbt_ops;
+	cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_REFC,
+			mp->m_refc_maxlevels, xfs_refcountbt_cur_cache);
 	cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_refcbt_2);
 
-	cur->bc_nlevels = be32_to_cpu(agf->agf_refcount_level);
-
-	cur->bc_private.a.agbp = agbp;
-	cur->bc_private.a.agno = agno;
 	cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
 
-	cur->bc_private.a.priv.refc.nr_ops = 0;
-	cur->bc_private.a.priv.refc.shape_changes = 0;
+	/* take a reference for the cursor */
+	atomic_inc(&pag->pag_ref);
+	cur->bc_ag.pag = pag;
+
+	cur->bc_ag.refc.nr_ops = 0;
+	cur->bc_ag.refc.shape_changes = 0;
+	cur->bc_ops = &xfs_refcountbt_ops;
+	return cur;
+}
+
+/* Create a btree cursor. */
+struct xfs_btree_cur *
+xfs_refcountbt_init_cursor(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_buf		*agbp,
+	struct xfs_perag	*pag)
+{
+	struct xfs_agf		*agf = agbp->b_addr;
+	struct xfs_btree_cur	*cur;
+
+	cur = xfs_refcountbt_init_common(mp, tp, pag);
+	cur->bc_nlevels = be32_to_cpu(agf->agf_refcount_level);
+	cur->bc_ag.agbp = agbp;
+	return cur;
+}
+
+/* Create a btree cursor with a fake root for staging. */
+struct xfs_btree_cur *
+xfs_refcountbt_stage_cursor(
+	struct xfs_mount	*mp,
+	struct xbtree_afakeroot	*afake,
+	struct xfs_perag	*pag)
+{
+	struct xfs_btree_cur	*cur;
 
+	cur = xfs_refcountbt_init_common(mp, NULL, pag);
+	xfs_btree_stage_afakeroot(cur, afake);
 	return cur;
 }
 
 /*
+ * Swap in the new btree root.  Once we pass this point the newly rebuilt btree
+ * is in place and we have to kill off all the old btree blocks.
+ */
+void
+xfs_refcountbt_commit_staged_btree(
+	struct xfs_btree_cur	*cur,
+	struct xfs_trans	*tp,
+	struct xfs_buf		*agbp)
+{
+	struct xfs_agf		*agf = agbp->b_addr;
+	struct xbtree_afakeroot	*afake = cur->bc_ag.afake;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_STAGING);
+
+	agf->agf_refcount_root = cpu_to_be32(afake->af_root);
+	agf->agf_refcount_level = cpu_to_be32(afake->af_levels);
+	agf->agf_refcount_blocks = cpu_to_be32(afake->af_blocks);
+	xfs_alloc_log_agf(tp, agbp, XFS_AGF_REFCOUNT_BLOCKS |
+				    XFS_AGF_REFCOUNT_ROOT |
+				    XFS_AGF_REFCOUNT_LEVEL);
+	xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_refcountbt_ops);
+}
+
+/* Calculate number of records in a refcount btree block. */
+static inline unsigned int
+xfs_refcountbt_block_maxrecs(
+	unsigned int		blocklen,
+	bool			leaf)
+{
+	if (leaf)
+		return blocklen / sizeof(struct xfs_refcount_rec);
+	return blocklen / (sizeof(struct xfs_refcount_key) +
+			   sizeof(xfs_refcount_ptr_t));
+}
+
+/*
  * Calculate the number of records in a refcount btree block.
  */
 int
@@ -355,11 +425,22 @@ xfs_refcountbt_maxrecs(
 	bool			leaf)
 {
 	blocklen -= XFS_REFCOUNT_BLOCK_LEN;
+	return xfs_refcountbt_block_maxrecs(blocklen, leaf);
+}
 
-	if (leaf)
-		return blocklen / sizeof(struct xfs_refcount_rec);
-	return blocklen / (sizeof(struct xfs_refcount_key) +
-			   sizeof(xfs_refcount_ptr_t));
+/* Compute the max possible height of the maximally sized refcount btree. */
+unsigned int
+xfs_refcountbt_maxlevels_ondisk(void)
+{
+	unsigned int		minrecs[2];
+	unsigned int		blocklen;
+
+	blocklen = XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_SBLOCK_CRC_LEN;
+
+	minrecs[0] = xfs_refcountbt_block_maxrecs(blocklen, true) / 2;
+	minrecs[1] = xfs_refcountbt_block_maxrecs(blocklen, false) / 2;
+
+	return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_CRC_AG_BLOCKS);
 }
 
 /* Compute the maximum height of a refcount btree. */
@@ -367,8 +448,14 @@ void
 xfs_refcountbt_compute_maxlevels(
 	struct xfs_mount		*mp)
 {
+	if (!xfs_has_reflink(mp)) {
+		mp->m_refc_maxlevels = 0;
+		return;
+	}
+
 	mp->m_refc_maxlevels = xfs_btree_compute_maxlevels(
 			mp->m_refc_mnr, mp->m_sb.sb_agblocks);
+	ASSERT(mp->m_refc_maxlevels <= xfs_refcountbt_maxlevels_ondisk());
 }
 
 /* Calculate the refcount btree size for some records. */
@@ -402,7 +489,7 @@ int
 xfs_refcountbt_calc_reserves(
 	struct xfs_mount	*mp,
 	struct xfs_trans	*tp,
-	xfs_agnumber_t		agno,
+	struct xfs_perag	*pag,
 	xfs_extlen_t		*ask,
 	xfs_extlen_t		*used)
 {
@@ -412,15 +499,14 @@ xfs_refcountbt_calc_reserves(
 	xfs_extlen_t		tree_len;
 	int			error;
 
-	if (!xfs_sb_version_hasreflink(&mp->m_sb))
+	if (!xfs_has_reflink(mp))
 		return 0;
 
-
-	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
+	error = xfs_alloc_read_agf(pag, tp, 0, &agbp);
 	if (error)
 		return error;
 
-	agf = XFS_BUF_TO_AGF(agbp);
+	agf = agbp->b_addr;
 	agblocks = be32_to_cpu(agf->agf_length);
 	tree_len = be32_to_cpu(agf->agf_refcount_blocks);
 	xfs_trans_brelse(tp, agbp);
@@ -430,8 +516,7 @@ xfs_refcountbt_calc_reserves(
 	 * never be available for the kinds of things that would require btree
 	 * expansion.  We therefore can pretend the space isn't there.
 	 */
-	if (mp->m_sb.sb_logstart &&
-	    XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart) == agno)
+	if (xfs_ag_contains_log(mp, pag->pag_agno))
 		agblocks -= mp->m_sb.sb_logblocks;
 
 	*ask += xfs_refcountbt_max_size(mp, agblocks);
@@ -439,3 +524,22 @@ xfs_refcountbt_calc_reserves(
 
 	return error;
 }
+
+int __init
+xfs_refcountbt_init_cur_cache(void)
+{
+	xfs_refcountbt_cur_cache = kmem_cache_create("xfs_refcbt_cur",
+			xfs_btree_cur_sizeof(xfs_refcountbt_maxlevels_ondisk()),
+			0, 0, NULL);
+
+	if (!xfs_refcountbt_cur_cache)
+		return -ENOMEM;
+	return 0;
+}
+
+void
+xfs_refcountbt_destroy_cur_cache(void)
+{
+	kmem_cache_destroy(xfs_refcountbt_cur_cache);
+	xfs_refcountbt_cur_cache = NULL;
+}