1 files changed, 202 insertions, 102 deletions

diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 279694d73e4e..549a3cba0234 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -9,61 +9,59 @@
 #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_alloc_btree.h"
 #include "xfs_alloc.h"
 #include "xfs_extent_busy.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_trans.h"
+#include "xfs_ag.h"
 
+static struct kmem_cache	*xfs_allocbt_cur_cache;
 
 STATIC struct xfs_btree_cur *
 xfs_allocbt_dup_cursor(
 	struct xfs_btree_cur	*cur)
 {
 	return xfs_allocbt_init_cursor(cur->bc_mp, cur->bc_tp,
-			cur->bc_private.a.agbp, cur->bc_private.a.agno,
-			cur->bc_btnum);
+			cur->bc_ag.agbp, cur->bc_ag.pag, cur->bc_btnum);
 }
 
 STATIC void
 xfs_allocbt_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_buf		*agbp = cur->bc_ag.agbp;
+	struct xfs_agf		*agf = agbp->b_addr;
 	int			btnum = cur->bc_btnum;
-	struct xfs_perag	*pag = xfs_perag_get(cur->bc_mp, seqno);
 
 	ASSERT(ptr->s != 0);
 
 	agf->agf_roots[btnum] = ptr->s;
 	be32_add_cpu(&agf->agf_levels[btnum], inc);
-	pag->pagf_levels[btnum] += inc;
-	xfs_perag_put(pag);
+	cur->bc_ag.pag->pagf_levels[btnum] += inc;
 
 	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS);
 }
 
 STATIC int
 xfs_allocbt_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)
 {
 	int			error;
 	xfs_agblock_t		bno;
 
 	/* Allocate the new block from the freelist. If we can't, give up.  */
-	error = xfs_alloc_get_freelist(cur->bc_tp, cur->bc_private.a.agbp,
-				       &bno, 1);
+	error = xfs_alloc_get_freelist(cur->bc_ag.pag, cur->bc_tp,
+			cur->bc_ag.agbp, &bno, 1);
 	if (error)
 		return error;
 
@@ -72,9 +70,9 @@ xfs_allocbt_alloc_block(
 		return 0;
 	}
 
-	xfs_extent_busy_reuse(cur->bc_mp, cur->bc_private.a.agno, bno, 1, false);
+	atomic64_inc(&cur->bc_mp->m_allocbt_blks);
+	xfs_extent_busy_reuse(cur->bc_mp, cur->bc_ag.pag, bno, 1, false);
 
-	xfs_trans_agbtree_delta(cur->bc_tp, 1);
 	new->s = cpu_to_be32(bno);
 
 	*stat = 1;
@@ -86,19 +84,19 @@ xfs_allocbt_free_block(
 	struct xfs_btree_cur	*cur,
 	struct xfs_buf		*bp)
 {
-	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;
 	xfs_agblock_t		bno;
 	int			error;
 
-	bno = xfs_daddr_to_agbno(cur->bc_mp, XFS_BUF_ADDR(bp));
-	error = xfs_alloc_put_freelist(cur->bc_tp, agbp, NULL, bno, 1);
+	bno = xfs_daddr_to_agbno(cur->bc_mp, xfs_buf_daddr(bp));
+	error = xfs_alloc_put_freelist(cur->bc_ag.pag, cur->bc_tp, agbp, NULL,
+			bno, 1);
 	if (error)
 		return error;
 
-	xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1,
+	atomic64_dec(&cur->bc_mp->m_allocbt_blks);
+	xfs_extent_busy_insert(cur->bc_tp, agbp->b_pag, bno, 1,
 			      XFS_EXTENT_BUSY_SKIP_DISCARD);
-	xfs_trans_agbtree_delta(cur->bc_tp, -1);
 	return 0;
 }
 
@@ -107,14 +105,13 @@ xfs_allocbt_free_block(
  */
 STATIC void
 xfs_allocbt_update_lastrec(
-	struct xfs_btree_cur	*cur,
-	struct xfs_btree_block	*block,
-	union xfs_btree_rec	*rec,
-	int			ptr,
-	int			reason)
+	struct xfs_btree_cur		*cur,
+	const struct xfs_btree_block	*block,
+	const union xfs_btree_rec	*rec,
+	int				ptr,
+	int				reason)
 {
-	struct xfs_agf		*agf = XFS_BUF_TO_AGF(cur->bc_private.a.agbp);
-	xfs_agnumber_t		seqno = be32_to_cpu(agf->agf_seqno);
+	struct xfs_agf		*agf = cur->bc_ag.agbp->b_addr;
 	struct xfs_perag	*pag;
 	__be32			len;
 	int			numrecs;
@@ -159,10 +156,9 @@ xfs_allocbt_update_lastrec(
 	}
 
 	agf->agf_longest = len;
-	pag = xfs_perag_get(cur->bc_mp, seqno);
+	pag = cur->bc_ag.agbp->b_pag;
 	pag->pagf_longest = be32_to_cpu(len);
-	xfs_perag_put(pag);
-	xfs_alloc_log_agf(cur->bc_tp, cur->bc_private.a.agbp, XFS_AGF_LONGEST);
+	xfs_alloc_log_agf(cur->bc_tp, cur->bc_ag.agbp, XFS_AGF_LONGEST);
 }
 
 STATIC int
@@ -183,8 +179,8 @@ xfs_allocbt_get_maxrecs(
 
 STATIC void
 xfs_allocbt_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->alloc.ar_startblock = rec->alloc.ar_startblock;
 	key->alloc.ar_blockcount = rec->alloc.ar_blockcount;
@@ -192,10 +188,10 @@ xfs_allocbt_init_key_from_rec(
 
 STATIC void
 xfs_bnobt_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->alloc.ar_startblock);
 	x += be32_to_cpu(rec->alloc.ar_blockcount) - 1;
@@ -205,8 +201,8 @@ xfs_bnobt_init_high_key_from_rec(
 
 STATIC void
 xfs_cntbt_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)
 {
 	key->alloc.ar_blockcount = rec->alloc.ar_blockcount;
 	key->alloc.ar_startblock = 0;
@@ -226,32 +222,32 @@ xfs_allocbt_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_roots[cur->bc_btnum];
 }
 
 STATIC int64_t
 xfs_bnobt_key_diff(
-	struct xfs_btree_cur	*cur,
-	union xfs_btree_key	*key)
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*key)
 {
-	xfs_alloc_rec_incore_t	*rec = &cur->bc_rec.a;
-	xfs_alloc_key_t		*kp = &key->alloc;
+	struct xfs_alloc_rec_incore	*rec = &cur->bc_rec.a;
+	const struct xfs_alloc_rec	*kp = &key->alloc;
 
 	return (int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock;
 }
 
 STATIC int64_t
 xfs_cntbt_key_diff(
-	struct xfs_btree_cur	*cur,
-	union xfs_btree_key	*key)
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_key	*key)
 {
-	xfs_alloc_rec_incore_t	*rec = &cur->bc_rec.a;
-	xfs_alloc_key_t		*kp = &key->alloc;
-	int64_t			diff;
+	struct xfs_alloc_rec_incore	*rec = &cur->bc_rec.a;
+	const struct xfs_alloc_rec	*kp = &key->alloc;
+	int64_t				diff;
 
 	diff = (int64_t)be32_to_cpu(kp->ar_blockcount) - rec->ar_blockcount;
 	if (diff)
@@ -262,9 +258,9 @@ xfs_cntbt_key_diff(
 
 STATIC int64_t
 xfs_bnobt_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->alloc.ar_startblock) -
 			  be32_to_cpu(k2->alloc.ar_startblock);
@@ -272,11 +268,11 @@ xfs_bnobt_diff_two_keys(
 
 STATIC int64_t
 xfs_cntbt_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)
 {
-	int64_t			diff;
+	int64_t				diff;
 
 	diff =  be32_to_cpu(k1->alloc.ar_blockcount) -
 		be32_to_cpu(k2->alloc.ar_blockcount);
@@ -301,7 +297,7 @@ xfs_allocbt_verify(
 	if (!xfs_verify_magic(bp, block->bb_magic))
 		return __this_address;
 
-	if (xfs_sb_version_hascrc(&mp->m_sb)) {
+	if (xfs_has_crc(mp)) {
 		fa = xfs_btree_sblock_v5hdr_verify(bp);
 		if (fa)
 			return fa;
@@ -322,7 +318,7 @@ xfs_allocbt_verify(
 	if (pag && pag->pagf_init) {
 		if (level >= pag->pagf_levels[btnum])
 			return __this_address;
-	} else if (level >= mp->m_ag_maxlevels)
+	} else if (level >= mp->m_alloc_maxlevels)
 		return __this_address;
 
 	return xfs_btree_sblock_verify(bp, mp->m_alloc_mxr[level != 0]);
@@ -382,9 +378,9 @@ const struct xfs_buf_ops xfs_cntbt_buf_ops = {
 
 STATIC int
 xfs_bnobt_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->alloc.ar_startblock) <
 	       be32_to_cpu(k2->alloc.ar_startblock);
@@ -392,9 +388,9 @@ xfs_bnobt_keys_inorder(
 
 STATIC int
 xfs_bnobt_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->alloc.ar_startblock) +
 		be32_to_cpu(r1->alloc.ar_blockcount) <=
@@ -403,9 +399,9 @@ xfs_bnobt_recs_inorder(
 
 STATIC int
 xfs_cntbt_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->alloc.ar_blockcount) <
 		be32_to_cpu(k2->alloc.ar_blockcount) ||
@@ -416,9 +412,9 @@ xfs_cntbt_keys_inorder(
 
 STATIC int
 xfs_cntbt_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->alloc.ar_blockcount) <
 		be32_to_cpu(r2->alloc.ar_blockcount) ||
@@ -471,6 +467,41 @@ static const struct xfs_btree_ops xfs_cntbt_ops = {
 	.recs_inorder		= xfs_cntbt_recs_inorder,
 };
 
+/* Allocate most of a new allocation btree cursor. */
+STATIC struct xfs_btree_cur *
+xfs_allocbt_init_common(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_perag	*pag,
+	xfs_btnum_t		btnum)
+{
+	struct xfs_btree_cur	*cur;
+
+	ASSERT(btnum == XFS_BTNUM_BNO || btnum == XFS_BTNUM_CNT);
+
+	cur = xfs_btree_alloc_cursor(mp, tp, btnum, mp->m_alloc_maxlevels,
+			xfs_allocbt_cur_cache);
+	cur->bc_ag.abt.active = false;
+
+	if (btnum == XFS_BTNUM_CNT) {
+		cur->bc_ops = &xfs_cntbt_ops;
+		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtc_2);
+		cur->bc_flags = XFS_BTREE_LASTREC_UPDATE;
+	} else {
+		cur->bc_ops = &xfs_bnobt_ops;
+		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtb_2);
+	}
+
+	/* take a reference for the cursor */
+	atomic_inc(&pag->pag_ref);
+	cur->bc_ag.pag = pag;
+
+	if (xfs_has_crc(mp))
+		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
+
+	return cur;
+}
+
 /*
  * Allocate a new allocation btree cursor.
  */
@@ -479,43 +510,77 @@ xfs_allocbt_init_cursor(
 	struct xfs_mount	*mp,		/* file system mount point */
 	struct xfs_trans	*tp,		/* transaction pointer */
 	struct xfs_buf		*agbp,		/* buffer for agf structure */
-	xfs_agnumber_t		agno,		/* allocation group number */
+	struct xfs_perag	*pag,
 	xfs_btnum_t		btnum)		/* btree identifier */
 {
-	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agbp);
+	struct xfs_agf		*agf = agbp->b_addr;
 	struct xfs_btree_cur	*cur;
 
-	ASSERT(btnum == XFS_BTNUM_BNO || btnum == XFS_BTNUM_CNT);
-
-	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_NOFS);
-
-	cur->bc_tp = tp;
-	cur->bc_mp = mp;
-	cur->bc_btnum = btnum;
-	cur->bc_blocklog = mp->m_sb.sb_blocklog;
-
-	if (btnum == XFS_BTNUM_CNT) {
-		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtc_2);
-		cur->bc_ops = &xfs_cntbt_ops;
+	cur = xfs_allocbt_init_common(mp, tp, pag, btnum);
+	if (btnum == XFS_BTNUM_CNT)
 		cur->bc_nlevels = be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]);
-		cur->bc_flags = XFS_BTREE_LASTREC_UPDATE;
-	} else {
-		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtb_2);
-		cur->bc_ops = &xfs_bnobt_ops;
+	else
 		cur->bc_nlevels = be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]);
-	}
 
-	cur->bc_private.a.agbp = agbp;
-	cur->bc_private.a.agno = agno;
-	cur->bc_private.a.priv.abt.active = false;
+	cur->bc_ag.agbp = agbp;
 
-	if (xfs_sb_version_hascrc(&mp->m_sb))
-		cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
+	return cur;
+}
+
+/* Create a free space btree cursor with a fake root for staging. */
+struct xfs_btree_cur *
+xfs_allocbt_stage_cursor(
+	struct xfs_mount	*mp,
+	struct xbtree_afakeroot	*afake,
+	struct xfs_perag	*pag,
+	xfs_btnum_t		btnum)
+{
+	struct xfs_btree_cur	*cur;
 
+	cur = xfs_allocbt_init_common(mp, NULL, pag, btnum);
+	xfs_btree_stage_afakeroot(cur, afake);
 	return cur;
 }
 
 /*
+ * Install a new free space btree root.  Caller is responsible for invalidating
+ * and freeing the old btree blocks.
+ */
+void
+xfs_allocbt_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_roots[cur->bc_btnum] = cpu_to_be32(afake->af_root);
+	agf->agf_levels[cur->bc_btnum] = cpu_to_be32(afake->af_levels);
+	xfs_alloc_log_agf(tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS);
+
+	if (cur->bc_btnum == XFS_BTNUM_BNO) {
+		xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_bnobt_ops);
+	} else {
+		cur->bc_flags |= XFS_BTREE_LASTREC_UPDATE;
+		xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_cntbt_ops);
+	}
+}
+
+/* Calculate number of records in an alloc btree block. */
+static inline unsigned int
+xfs_allocbt_block_maxrecs(
+	unsigned int		blocklen,
+	bool			leaf)
+{
+	if (leaf)
+		return blocklen / sizeof(xfs_alloc_rec_t);
+	return blocklen / (sizeof(xfs_alloc_key_t) + sizeof(xfs_alloc_ptr_t));
+}
+
+/*
  * Calculate number of records in an alloc btree block.
  */
 int
@@ -525,10 +590,26 @@ xfs_allocbt_maxrecs(
 	int			leaf)
 {
 	blocklen -= XFS_ALLOC_BLOCK_LEN(mp);
+	return xfs_allocbt_block_maxrecs(blocklen, leaf);
+}
 
-	if (leaf)
-		return blocklen / sizeof(xfs_alloc_rec_t);
-	return blocklen / (sizeof(xfs_alloc_key_t) + sizeof(xfs_alloc_ptr_t));
+/* Free space btrees are at their largest when every other block is free. */
+#define XFS_MAX_FREESP_RECORDS	((XFS_MAX_AG_BLOCKS + 1) / 2)
+
+/* Compute the max possible height for free space btrees. */
+unsigned int
+xfs_allocbt_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_allocbt_block_maxrecs(blocklen, true) / 2;
+	minrecs[1] = xfs_allocbt_block_maxrecs(blocklen, false) / 2;
+
+	return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_FREESP_RECORDS);
 }
 
 /* Calculate the freespace btree size for some records. */
@@ -539,3 +620,22 @@ xfs_allocbt_calc_size(
 {
 	return xfs_btree_calc_size(mp->m_alloc_mnr, len);
 }
+
+int __init
+xfs_allocbt_init_cur_cache(void)
+{
+	xfs_allocbt_cur_cache = kmem_cache_create("xfs_bnobt_cur",
+			xfs_btree_cur_sizeof(xfs_allocbt_maxlevels_ondisk()),
+			0, 0, NULL);
+
+	if (!xfs_allocbt_cur_cache)
+		return -ENOMEM;
+	return 0;
+}
+
+void
+xfs_allocbt_destroy_cur_cache(void)
+{
+	kmem_cache_destroy(xfs_allocbt_cur_cache);
+	xfs_allocbt_cur_cache = NULL;
+}