summaryrefslogtreecommitdiff
path: root/fs/xfs/libxfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs/libxfs')
-rw-r--r--fs/xfs/libxfs/xfs_ag.c2
-rw-r--r--fs/xfs/libxfs/xfs_ag.h36
-rw-r--r--fs/xfs/libxfs/xfs_ag_resv.c3
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c120
-rw-r--r--fs/xfs/libxfs/xfs_alloc.h38
-rw-r--r--fs/xfs/libxfs/xfs_alloc_btree.c63
-rw-r--r--fs/xfs/libxfs/xfs_alloc_btree.h5
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.c2
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c101
-rw-r--r--fs/xfs/libxfs/xfs_bmap.h35
-rw-r--r--fs/xfs/libxfs/xfs_bmap_btree.c62
-rw-r--r--fs/xfs/libxfs/xfs_bmap_btree.h5
-rw-r--r--fs/xfs/libxfs/xfs_btree.c333
-rw-r--r--fs/xfs/libxfs/xfs_btree.h99
-rw-r--r--fs/xfs/libxfs/xfs_btree_staging.c8
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.c6
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.h3
-rw-r--r--fs/xfs/libxfs/xfs_defer.c241
-rw-r--r--fs/xfs/libxfs/xfs_defer.h41
-rw-r--r--fs/xfs/libxfs/xfs_dquot_buf.c4
-rw-r--r--fs/xfs/libxfs/xfs_format.h12
-rw-r--r--fs/xfs/libxfs/xfs_fs.h2
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.c5
-rw-r--r--fs/xfs/libxfs/xfs_ialloc_btree.c90
-rw-r--r--fs/xfs/libxfs/xfs_ialloc_btree.h5
-rw-r--r--fs/xfs/libxfs/xfs_inode_buf.c6
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.c24
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.h2
-rw-r--r--fs/xfs/libxfs/xfs_refcount.c46
-rw-r--r--fs/xfs/libxfs/xfs_refcount.h7
-rw-r--r--fs/xfs/libxfs/xfs_refcount_btree.c65
-rw-r--r--fs/xfs/libxfs/xfs_refcount_btree.h5
-rw-r--r--fs/xfs/libxfs/xfs_rmap.c21
-rw-r--r--fs/xfs/libxfs/xfs_rmap.h7
-rw-r--r--fs/xfs/libxfs/xfs_rmap_btree.c116
-rw-r--r--fs/xfs/libxfs/xfs_rmap_btree.h5
-rw-r--r--fs/xfs/libxfs/xfs_sb.c4
-rw-r--r--fs/xfs/libxfs/xfs_trans_resv.c18
-rw-r--r--fs/xfs/libxfs/xfs_trans_space.h9
39 files changed, 1178 insertions, 478 deletions
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 005abfd9fd34..d7d875cef07a 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -850,7 +850,7 @@ xfs_ag_shrink_space(
if (err2 != -ENOSPC)
goto resv_err;
- __xfs_bmap_add_free(*tpp, args.fsbno, delta, NULL, true);
+ __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL, true);
/*
* Roll the transaction before trying to re-init the per-ag
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 4c6f9045baca..3f597cad2c33 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -116,23 +116,29 @@ void xfs_perag_put(struct xfs_perag *pag);
/*
* Perag iteration APIs
- *
- * XXX: for_each_perag_range() usage really needs an iterator to clean up when
- * we terminate at end_agno because we may have taken a reference to the perag
- * beyond end_agno. Right now callers have to be careful to catch and clean that
- * up themselves. This is not necessary for the callers of for_each_perag() and
- * for_each_perag_from() because they terminate at sb_agcount where there are
- * no perag structures in tree beyond end_agno.
*/
-#define for_each_perag_range(mp, next_agno, end_agno, pag) \
- for ((pag) = xfs_perag_get((mp), (next_agno)); \
- (pag) != NULL && (next_agno) <= (end_agno); \
- (next_agno) = (pag)->pag_agno + 1, \
- xfs_perag_put(pag), \
- (pag) = xfs_perag_get((mp), (next_agno)))
+static inline struct xfs_perag *
+xfs_perag_next(
+ struct xfs_perag *pag,
+ xfs_agnumber_t *agno,
+ xfs_agnumber_t end_agno)
+{
+ struct xfs_mount *mp = pag->pag_mount;
+
+ *agno = pag->pag_agno + 1;
+ xfs_perag_put(pag);
+ if (*agno > end_agno)
+ return NULL;
+ return xfs_perag_get(mp, *agno);
+}
+
+#define for_each_perag_range(mp, agno, end_agno, pag) \
+ for ((pag) = xfs_perag_get((mp), (agno)); \
+ (pag) != NULL; \
+ (pag) = xfs_perag_next((pag), &(agno), (end_agno)))
-#define for_each_perag_from(mp, next_agno, pag) \
- for_each_perag_range((mp), (next_agno), (mp)->m_sb.sb_agcount, (pag))
+#define for_each_perag_from(mp, agno, pag) \
+ for_each_perag_range((mp), (agno), (mp)->m_sb.sb_agcount - 1, (pag))
#define for_each_perag(mp, agno, pag) \
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index 2aa2b3484c28..fe94058d4e9e 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -91,7 +91,8 @@ xfs_ag_resv_critical(
trace_xfs_ag_resv_critical(pag, type, avail);
/* Critically low if less than 10% or max btree height remains. */
- return XFS_TEST_ERROR(avail < orig / 10 || avail < XFS_BTREE_MAXLEVELS,
+ return XFS_TEST_ERROR(avail < orig / 10 ||
+ avail < pag->pag_mount->m_agbtree_maxlevels,
pag->pag_mount, XFS_ERRTAG_AG_RESV_CRITICAL);
}
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 95157f5a5a6c..353e53b892e6 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -27,7 +27,7 @@
#include "xfs_ag_resv.h"
#include "xfs_bmap.h"
-extern kmem_zone_t *xfs_bmap_free_item_zone;
+struct kmem_cache *xfs_extfree_item_cache;
struct workqueue_struct *xfs_alloc_wq;
@@ -426,8 +426,8 @@ xfs_alloc_fix_len(
*/
STATIC int /* error code */
xfs_alloc_fixup_trees(
- xfs_btree_cur_t *cnt_cur, /* cursor for by-size btree */
- xfs_btree_cur_t *bno_cur, /* cursor for by-block btree */
+ struct xfs_btree_cur *cnt_cur, /* cursor for by-size btree */
+ struct xfs_btree_cur *bno_cur, /* cursor for by-block btree */
xfs_agblock_t fbno, /* starting block of free extent */
xfs_extlen_t flen, /* length of free extent */
xfs_agblock_t rbno, /* starting block of returned extent */
@@ -488,8 +488,8 @@ xfs_alloc_fixup_trees(
struct xfs_btree_block *bnoblock;
struct xfs_btree_block *cntblock;
- bnoblock = XFS_BUF_TO_BLOCK(bno_cur->bc_bufs[0]);
- cntblock = XFS_BUF_TO_BLOCK(cnt_cur->bc_bufs[0]);
+ bnoblock = XFS_BUF_TO_BLOCK(bno_cur->bc_levels[0].bp);
+ cntblock = XFS_BUF_TO_BLOCK(cnt_cur->bc_levels[0].bp);
if (XFS_IS_CORRUPT(mp,
bnoblock->bb_numrecs !=
@@ -1200,8 +1200,8 @@ xfs_alloc_ag_vextent_exact(
xfs_alloc_arg_t *args) /* allocation argument structure */
{
struct xfs_agf __maybe_unused *agf = args->agbp->b_addr;
- xfs_btree_cur_t *bno_cur;/* by block-number btree cursor */
- xfs_btree_cur_t *cnt_cur;/* by count btree cursor */
+ struct xfs_btree_cur *bno_cur;/* by block-number btree cursor */
+ struct xfs_btree_cur *cnt_cur;/* by count btree cursor */
int error;
xfs_agblock_t fbno; /* start block of found extent */
xfs_extlen_t flen; /* length of found extent */
@@ -1512,7 +1512,7 @@ xfs_alloc_ag_vextent_lastblock(
* than minlen.
*/
if (*len || args->alignment > 1) {
- acur->cnt->bc_ptrs[0] = 1;
+ acur->cnt->bc_levels[0].ptr = 1;
do {
error = xfs_alloc_get_rec(acur->cnt, bno, len, &i);
if (error)
@@ -1658,8 +1658,8 @@ xfs_alloc_ag_vextent_size(
xfs_alloc_arg_t *args) /* allocation argument structure */
{
struct xfs_agf *agf = args->agbp->b_addr;
- xfs_btree_cur_t *bno_cur; /* cursor for bno btree */
- xfs_btree_cur_t *cnt_cur; /* cursor for cnt btree */
+ struct xfs_btree_cur *bno_cur; /* cursor for bno btree */
+ struct xfs_btree_cur *cnt_cur; /* cursor for cnt btree */
int error; /* error result */
xfs_agblock_t fbno; /* start of found freespace */
xfs_extlen_t flen; /* length of found freespace */
@@ -2190,14 +2190,15 @@ xfs_free_ag_extent(
*/
/*
- * Compute and fill in value of m_ag_maxlevels.
+ * Compute and fill in value of m_alloc_maxlevels.
*/
void
xfs_alloc_compute_maxlevels(
xfs_mount_t *mp) /* file system mount structure */
{
- mp->m_ag_maxlevels = xfs_btree_compute_maxlevels(mp->m_alloc_mnr,
+ mp->m_alloc_maxlevels = xfs_btree_compute_maxlevels(mp->m_alloc_mnr,
(mp->m_sb.sb_agblocks + 1) / 2);
+ ASSERT(mp->m_alloc_maxlevels <= xfs_allocbt_maxlevels_ondisk());
}
/*
@@ -2255,14 +2256,14 @@ xfs_alloc_min_freelist(
const uint8_t *levels = pag ? pag->pagf_levels : fake_levels;
unsigned int min_free;
- ASSERT(mp->m_ag_maxlevels > 0);
+ ASSERT(mp->m_alloc_maxlevels > 0);
/* space needed by-bno freespace btree */
min_free = min_t(unsigned int, levels[XFS_BTNUM_BNOi] + 1,
- mp->m_ag_maxlevels);
+ mp->m_alloc_maxlevels);
/* space needed by-size freespace btree */
min_free += min_t(unsigned int, levels[XFS_BTNUM_CNTi] + 1,
- mp->m_ag_maxlevels);
+ mp->m_alloc_maxlevels);
/* space needed reverse mapping used space btree */
if (xfs_has_rmapbt(mp))
min_free += min_t(unsigned int, levels[XFS_BTNUM_RMAPi] + 1,
@@ -2439,7 +2440,7 @@ xfs_agfl_reset(
/*
* Defer an AGFL block free. This is effectively equivalent to
- * xfs_bmap_add_free() with some special handling particular to AGFL blocks.
+ * xfs_free_extent_later() with some special handling particular to AGFL blocks.
*
* Deferring AGFL frees helps prevent log reservation overruns due to too many
* allocation operations in a transaction. AGFL frees are prone to this problem
@@ -2458,21 +2459,74 @@ xfs_defer_agfl_block(
struct xfs_mount *mp = tp->t_mountp;
struct xfs_extent_free_item *new; /* new element */
- ASSERT(xfs_bmap_free_item_zone != NULL);
+ ASSERT(xfs_extfree_item_cache != NULL);
ASSERT(oinfo != NULL);
- new = kmem_cache_alloc(xfs_bmap_free_item_zone,
+ new = kmem_cache_zalloc(xfs_extfree_item_cache,
GFP_KERNEL | __GFP_NOFAIL);
new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno);
new->xefi_blockcount = 1;
- new->xefi_oinfo = *oinfo;
- new->xefi_skip_discard = false;
+ new->xefi_owner = oinfo->oi_owner;
trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &new->xefi_list);
}
+/*
+ * Add the extent to the list of extents to be free at transaction end.
+ * The list is maintained sorted (by block number).
+ */
+void
+__xfs_free_extent_later(
+ struct xfs_trans *tp,
+ xfs_fsblock_t bno,
+ xfs_filblks_t len,
+ const struct xfs_owner_info *oinfo,
+ bool skip_discard)
+{
+ struct xfs_extent_free_item *new; /* new element */
+#ifdef DEBUG
+ struct xfs_mount *mp = tp->t_mountp;
+ xfs_agnumber_t agno;
+ xfs_agblock_t agbno;
+
+ ASSERT(bno != NULLFSBLOCK);
+ ASSERT(len > 0);
+ ASSERT(len <= MAXEXTLEN);
+ ASSERT(!isnullstartblock(bno));
+ agno = XFS_FSB_TO_AGNO(mp, bno);
+ agbno = XFS_FSB_TO_AGBNO(mp, bno);
+ ASSERT(agno < mp->m_sb.sb_agcount);
+ ASSERT(agbno < mp->m_sb.sb_agblocks);
+ ASSERT(len < mp->m_sb.sb_agblocks);
+ ASSERT(agbno + len <= mp->m_sb.sb_agblocks);
+#endif
+ ASSERT(xfs_extfree_item_cache != NULL);
+
+ new = kmem_cache_zalloc(xfs_extfree_item_cache,
+ GFP_KERNEL | __GFP_NOFAIL);
+ new->xefi_startblock = bno;
+ new->xefi_blockcount = (xfs_extlen_t)len;
+ if (skip_discard)
+ new->xefi_flags |= XFS_EFI_SKIP_DISCARD;
+ if (oinfo) {
+ ASSERT(oinfo->oi_offset == 0);
+
+ if (oinfo->oi_flags & XFS_OWNER_INFO_ATTR_FORK)
+ new->xefi_flags |= XFS_EFI_ATTR_FORK;
+ if (oinfo->oi_flags & XFS_OWNER_INFO_BMBT_BLOCK)
+ new->xefi_flags |= XFS_EFI_BMBT_BLOCK;
+ new->xefi_owner = oinfo->oi_owner;
+ } else {
+ new->xefi_owner = XFS_RMAP_OWN_NULL;
+ }
+ trace_xfs_bmap_free_defer(tp->t_mountp,
+ XFS_FSB_TO_AGNO(tp->t_mountp, bno), 0,
+ XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len);
+ xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list);
+}
+
#ifdef DEBUG
/*
* Check if an AGF has a free extent record whose length is equal to
@@ -2903,13 +2957,16 @@ xfs_agf_verify(
if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) < 1 ||
be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) < 1 ||
- be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) > mp->m_ag_maxlevels ||
- be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) > mp->m_ag_maxlevels)
+ be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) >
+ mp->m_alloc_maxlevels ||
+ be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) >
+ mp->m_alloc_maxlevels)
return __this_address;
if (xfs_has_rmapbt(mp) &&
(be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) < 1 ||
- be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) > mp->m_rmap_maxlevels))
+ be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) >
+ mp->m_rmap_maxlevels))
return __this_address;
if (xfs_has_rmapbt(mp) &&
@@ -3495,3 +3552,20 @@ xfs_agfl_walk(
return 0;
}
+
+int __init
+xfs_extfree_intent_init_cache(void)
+{
+ xfs_extfree_item_cache = kmem_cache_create("xfs_extfree_intent",
+ sizeof(struct xfs_extent_free_item),
+ 0, 0, NULL);
+
+ return xfs_extfree_item_cache != NULL ? 0 : -ENOMEM;
+}
+
+void
+xfs_extfree_intent_destroy_cache(void)
+{
+ kmem_cache_destroy(xfs_extfree_item_cache);
+ xfs_extfree_item_cache = NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index df4aefaf0046..1c14a0b1abea 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -98,7 +98,7 @@ unsigned int xfs_alloc_min_freelist(struct xfs_mount *mp,
struct xfs_perag *pag);
/*
- * Compute and fill in value of m_ag_maxlevels.
+ * Compute and fill in value of m_alloc_maxlevels.
*/
void
xfs_alloc_compute_maxlevels(
@@ -248,4 +248,40 @@ xfs_buf_to_agfl_bno(
return bp->b_addr;
}
+void __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno,
+ xfs_filblks_t len, const struct xfs_owner_info *oinfo,
+ bool skip_discard);
+
+/*
+ * List of extents to be free "later".
+ * The list is kept sorted on xbf_startblock.
+ */
+struct xfs_extent_free_item {
+ struct list_head xefi_list;
+ uint64_t xefi_owner;
+ xfs_fsblock_t xefi_startblock;/* starting fs block number */
+ xfs_extlen_t xefi_blockcount;/* number of blocks in extent */
+ unsigned int xefi_flags;
+};
+
+#define XFS_EFI_SKIP_DISCARD (1U << 0) /* don't issue discard */
+#define XFS_EFI_ATTR_FORK (1U << 1) /* freeing attr fork block */
+#define XFS_EFI_BMBT_BLOCK (1U << 2) /* freeing bmap btree block */
+
+static inline void
+xfs_free_extent_later(
+ struct xfs_trans *tp,
+ xfs_fsblock_t bno,
+ xfs_filblks_t len,
+ const struct xfs_owner_info *oinfo)
+{
+ __xfs_free_extent_later(tp, bno, len, oinfo, false);
+}
+
+
+extern struct kmem_cache *xfs_extfree_item_cache;
+
+int __init xfs_extfree_intent_init_cache(void);
+void xfs_extfree_intent_destroy_cache(void);
+
#endif /* __XFS_ALLOC_H__ */
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 6746fd735550..8c9f73cc0bee 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -20,6 +20,7 @@
#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(
@@ -316,7 +317,7 @@ 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]);
@@ -477,12 +478,8 @@ xfs_allocbt_init_common(
ASSERT(btnum == XFS_BTNUM_BNO || btnum == XFS_BTNUM_CNT);
- cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL);
-
- cur->bc_tp = tp;
- cur->bc_mp = mp;
- cur->bc_btnum = btnum;
- cur->bc_blocklog = mp->m_sb.sb_blocklog;
+ 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) {
@@ -571,6 +568,17 @@ xfs_allocbt_commit_staged_btree(
}
}
+/* 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.
*/
@@ -581,10 +589,26 @@ 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. */
@@ -595,3 +619,22 @@ 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;
+}
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.h b/fs/xfs/libxfs/xfs_alloc_btree.h
index 2f6b816aaf9f..45df893ef6bb 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.h
+++ b/fs/xfs/libxfs/xfs_alloc_btree.h
@@ -60,4 +60,9 @@ extern xfs_extlen_t xfs_allocbt_calc_size(struct xfs_mount *mp,
void xfs_allocbt_commit_staged_btree(struct xfs_btree_cur *cur,
struct xfs_trans *tp, struct xfs_buf *agbp);
+unsigned int xfs_allocbt_maxlevels_ondisk(void);
+
+int __init xfs_allocbt_init_cur_cache(void);
+void xfs_allocbt_destroy_cur_cache(void);
+
#endif /* __XFS_ALLOC_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index e1d11e314228..014daa8c542d 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -770,7 +770,7 @@ xfs_attr_fork_remove(
ASSERT(ip->i_afp->if_nextents == 0);
xfs_idestroy_fork(ip->i_afp);
- kmem_cache_free(xfs_ifork_zone, ip->i_afp);
+ kmem_cache_free(xfs_ifork_cache, ip->i_afp);
ip->i_afp = NULL;
ip->i_forkoff = 0;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index b48230f1a361..4dccd4d90622 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -37,8 +37,7 @@
#include "xfs_icache.h"
#include "xfs_iomap.h"
-
-kmem_zone_t *xfs_bmap_free_item_zone;
+struct kmem_cache *xfs_bmap_intent_cache;
/*
* Miscellaneous helper functions
@@ -93,6 +92,7 @@ xfs_bmap_compute_maxlevels(
maxblocks = (maxblocks + minnoderecs - 1) / minnoderecs;
}
mp->m_bm_maxlevels[whichfork] = level;
+ ASSERT(mp->m_bm_maxlevels[whichfork] <= xfs_bmbt_maxlevels_ondisk());
}
unsigned int
@@ -239,11 +239,11 @@ xfs_bmap_get_bp(
if (!cur)
return NULL;
- for (i = 0; i < XFS_BTREE_MAXLEVELS; i++) {
- if (!cur->bc_bufs[i])
+ for (i = 0; i < cur->bc_maxlevels; i++) {
+ if (!cur->bc_levels[i].bp)
break;
- if (xfs_buf_daddr(cur->bc_bufs[i]) == bno)
- return cur->bc_bufs[i];
+ if (xfs_buf_daddr(cur->bc_levels[i].bp) == bno)
+ return cur->bc_levels[i].bp;
}
/* Chase down all the log items to see if the bp is there */
@@ -316,7 +316,7 @@ xfs_check_block(
*/
STATIC void
xfs_bmap_check_leaf_extents(
- xfs_btree_cur_t *cur, /* btree cursor or null */
+ struct xfs_btree_cur *cur, /* btree cursor or null */
xfs_inode_t *ip, /* incore inode pointer */
int whichfork) /* data or attr fork */
{
@@ -522,56 +522,6 @@ xfs_bmap_validate_ret(
#endif /* DEBUG */
/*
- * bmap free list manipulation functions
- */
-
-/*
- * Add the extent to the list of extents to be free at transaction end.
- * The list is maintained sorted (by block number).
- */
-void
-__xfs_bmap_add_free(
- struct xfs_trans *tp,
- xfs_fsblock_t bno,
- xfs_filblks_t len,
- const struct xfs_owner_info *oinfo,
- bool skip_discard)
-{
- struct xfs_extent_free_item *new; /* new element */
-#ifdef DEBUG
- struct xfs_mount *mp = tp->t_mountp;
- xfs_agnumber_t agno;
- xfs_agblock_t agbno;
-
- ASSERT(bno != NULLFSBLOCK);
- ASSERT(len > 0);
- ASSERT(len <= MAXEXTLEN);
- ASSERT(!isnullstartblock(bno));
- agno = XFS_FSB_TO_AGNO(mp, bno);
- agbno = XFS_FSB_TO_AGBNO(mp, bno);
- ASSERT(agno < mp->m_sb.sb_agcount);
- ASSERT(agbno < mp->m_sb.sb_agblocks);
- ASSERT(len < mp->m_sb.sb_agblocks);
- ASSERT(agbno + len <= mp->m_sb.sb_agblocks);
-#endif
- ASSERT(xfs_bmap_free_item_zone != NULL);
-
- new = kmem_cache_alloc(xfs_bmap_free_item_zone,
- GFP_KERNEL | __GFP_NOFAIL);
- new->xefi_startblock = bno;
- new->xefi_blockcount = (xfs_extlen_t)len;
- if (oinfo)
- new->xefi_oinfo = *oinfo;
- else
- new->xefi_oinfo = XFS_RMAP_OINFO_SKIP_UPDATE;
- new->xefi_skip_discard = skip_discard;
- trace_xfs_bmap_free_defer(tp->t_mountp,
- XFS_FSB_TO_AGNO(tp->t_mountp, bno), 0,
- XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len);
- xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list);
-}
-
-/*
* Inode fork format manipulation functions
*/
@@ -625,12 +575,12 @@ xfs_bmap_btree_to_extents(
if ((error = xfs_btree_check_block(cur, cblock, 0, cbp)))
return error;
xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
- xfs_bmap_add_free(cur->bc_tp, cbno, 1, &oinfo);
+ xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo);
ip->i_nblocks--;
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
xfs_trans_binval(tp, cbp);
- if (cur->bc_bufs[0] == cbp)
- cur->bc_bufs[0] = NULL;
+ if (cur->bc_levels[0].bp == cbp)
+ cur->bc_levels[0].bp = NULL;
xfs_iroot_realloc(ip, -1, whichfork);
ASSERT(ifp->if_broot == NULL);
ifp->if_format = XFS_DINODE_FMT_EXTENTS;
@@ -925,7 +875,7 @@ xfs_bmap_add_attrfork_btree(
int *flags) /* inode logging flags */
{
struct xfs_btree_block *block = ip->i_df.if_broot;
- xfs_btree_cur_t *cur; /* btree cursor */
+ struct xfs_btree_cur *cur; /* btree cursor */
int error; /* error return value */
xfs_mount_t *mp; /* file system mount struct */
int stat; /* newroot status */
@@ -968,7 +918,7 @@ xfs_bmap_add_attrfork_extents(
struct xfs_inode *ip, /* incore inode pointer */
int *flags) /* inode logging flags */
{
- xfs_btree_cur_t *cur; /* bmap btree cursor */
+ struct xfs_btree_cur *cur; /* bmap btree cursor */
int error; /* error return value */
if (ip->i_df.if_nextents * sizeof(struct xfs_bmbt_rec) <=
@@ -1988,11 +1938,11 @@ xfs_bmap_add_extent_unwritten_real(
xfs_inode_t *ip, /* incore inode pointer */
int whichfork,
struct xfs_iext_cursor *icur,
- xfs_btree_cur_t **curp, /* if *curp is null, not a btree */
+ struct xfs_btree_cur **curp, /* if *curp is null, not a btree */
xfs_bmbt_irec_t *new, /* new data to add to file extents */
int *logflagsp) /* inode logging flags */
{
- xfs_btree_cur_t *cur; /* btree cursor */
+ struct xfs_btree_cur *cur; /* btree cursor */
int error; /* error return value */
int i; /* temp state */
struct xfs_ifork *ifp; /* inode fork pointer */
@@ -5045,7 +4995,7 @@ xfs_bmap_del_extent_real(
xfs_inode_t *ip, /* incore inode pointer */
xfs_trans_t *tp, /* current transaction pointer */
struct xfs_iext_cursor *icur,
- xfs_btree_cur_t *cur, /* if null, not a btree */
+ struct xfs_btree_cur *cur, /* if null, not a btree */
xfs_bmbt_irec_t *del, /* data to remove from extents */
int *logflagsp, /* inode logging flags */
int whichfork, /* data or attr fork */
@@ -5296,7 +5246,7 @@ xfs_bmap_del_extent_real(
if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) {
xfs_refcount_decrease_extent(tp, del);
} else {
- __xfs_bmap_add_free(tp, del->br_startblock,
+ __xfs_free_extent_later(tp, del->br_startblock,
del->br_blockcount, NULL,
(bflags & XFS_BMAPI_NODISCARD) ||
del->br_state == XFS_EXT_UNWRITTEN);
@@ -6189,7 +6139,7 @@ __xfs_bmap_add(
bmap->br_blockcount,
bmap->br_state);
- bi = kmem_alloc(sizeof(struct xfs_bmap_intent), KM_NOFS);
+ bi = kmem_cache_alloc(xfs_bmap_intent_cache, GFP_NOFS | __GFP_NOFAIL);
INIT_LIST_HEAD(&bi->bi_list);
bi->bi_type = type;
bi->bi_owner = ip;
@@ -6300,3 +6250,20 @@ xfs_bmap_validate_extent(
return __this_address;
return NULL;
}
+
+int __init
+xfs_bmap_intent_init_cache(void)
+{
+ xfs_bmap_intent_cache = kmem_cache_create("xfs_bmap_intent",
+ sizeof(struct xfs_bmap_intent),
+ 0, 0, NULL);
+
+ return xfs_bmap_intent_cache != NULL ? 0 : -ENOMEM;
+}
+
+void
+xfs_bmap_intent_destroy_cache(void)
+{
+ kmem_cache_destroy(xfs_bmap_intent_cache);
+ xfs_bmap_intent_cache = NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 67641f669918..03d9aaf87413 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -13,8 +13,6 @@ struct xfs_inode;
struct xfs_mount;
struct xfs_trans;
-extern kmem_zone_t *xfs_bmap_free_item_zone;
-
/*
* Argument structure for xfs_bmap_alloc.
*/
@@ -44,19 +42,6 @@ struct xfs_bmalloca {
int flags;
};
-/*
- * List of extents to be free "later".
- * The list is kept sorted on xbf_startblock.
- */
-struct xfs_extent_free_item
-{
- xfs_fsblock_t xefi_startblock;/* starting fs block number */
- xfs_extlen_t xefi_blockcount;/* number of blocks in extent */
- bool xefi_skip_discard;
- struct list_head xefi_list;
- struct xfs_owner_info xefi_oinfo; /* extent owner */
-};
-
#define XFS_BMAP_MAX_NMAP 4
/*
@@ -189,9 +174,6 @@ unsigned int xfs_bmap_compute_attr_offset(struct xfs_mount *mp);
int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
void xfs_bmap_local_to_extents_empty(struct xfs_trans *tp,
struct xfs_inode *ip, int whichfork);
-void __xfs_bmap_add_free(struct xfs_trans *tp, xfs_fsblock_t bno,
- xfs_filblks_t len, const struct xfs_owner_info *oinfo,
- bool skip_discard);
void xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork);
int xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
@@ -239,16 +221,6 @@ int xfs_bmap_add_extent_unwritten_real(struct xfs_trans *tp,
struct xfs_iext_cursor *icur, struct xfs_btree_cur **curp,
struct xfs_bmbt_irec *new, int *logflagsp);
-static inline void
-xfs_bmap_add_free(
- struct xfs_trans *tp,
- xfs_fsblock_t bno,
- xfs_filblks_t len,
- const struct xfs_owner_info *oinfo)
-{
- __xfs_bmap_add_free(tp, bno, len, oinfo, false);
-}
-
enum xfs_bmap_intent_type {
XFS_BMAP_MAP = 1,
XFS_BMAP_UNMAP,
@@ -257,8 +229,8 @@ enum xfs_bmap_intent_type {
struct xfs_bmap_intent {
struct list_head bi_list;
enum xfs_bmap_intent_type bi_type;
- struct xfs_inode *bi_owner;
int bi_whichfork;
+ struct xfs_inode *bi_owner;
struct xfs_bmbt_irec bi_bmap;
};
@@ -290,4 +262,9 @@ int xfs_bmapi_remap(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock,
int flags);
+extern struct kmem_cache *xfs_bmap_intent_cache;
+
+int __init xfs_bmap_intent_init_cache(void);
+void xfs_bmap_intent_destroy_cache(void);
+
#endif /* __XFS_BMAP_H__ */
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;
+}
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.h b/fs/xfs/libxfs/xfs_bmap_btree.h
index 729e3bc569be..3e7a40a83835 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.h
+++ b/fs/xfs/libxfs/xfs_bmap_btree.h
@@ -110,4 +110,9 @@ extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
extern unsigned long long xfs_bmbt_calc_size(struct xfs_mount *mp,
unsigned long long len);
+unsigned int xfs_bmbt_maxlevels_ondisk(void);
+
+int __init xfs_bmbt_init_cur_cache(void);
+void xfs_bmbt_destroy_cur_cache(void);
+
#endif /* __XFS_BMAP_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 298395481713..b4e19aacb9de 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -22,11 +22,11 @@
#include "xfs_log.h"
#include "xfs_btree_staging.h"
#include "xfs_ag.h"
-
-/*
- * Cursor allocation zone.
- */
-kmem_zone_t *xfs_btree_cur_zone;
+#include "xfs_alloc_btree.h"
+#include "xfs_ialloc_btree.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_refcount_btree.h"
/*
* Btree magic numbers.
@@ -367,8 +367,8 @@ xfs_btree_del_cursor(
* way we won't have initialized all the entries down to 0.
*/
for (i = 0; i < cur->bc_nlevels; i++) {
- if (cur->bc_bufs[i])
- xfs_trans_brelse(cur->bc_tp, cur->bc_bufs[i]);
+ if (cur->bc_levels[i].bp)
+ xfs_trans_brelse(cur->bc_tp, cur->bc_levels[i].bp);
else if (!error)
break;
}
@@ -379,7 +379,7 @@ xfs_btree_del_cursor(
kmem_free(cur->bc_ops);
if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) && cur->bc_ag.pag)
xfs_perag_put(cur->bc_ag.pag);
- kmem_cache_free(xfs_btree_cur_zone, cur);
+ kmem_cache_free(cur->bc_cache, cur);
}
/*
@@ -388,14 +388,14 @@ xfs_btree_del_cursor(
*/
int /* error */
xfs_btree_dup_cursor(
- xfs_btree_cur_t *cur, /* input cursor */
- xfs_btree_cur_t **ncur) /* output cursor */
+ struct xfs_btree_cur *cur, /* input cursor */
+ struct xfs_btree_cur **ncur) /* output cursor */
{
struct xfs_buf *bp; /* btree block's buffer pointer */
int error; /* error return value */
int i; /* level number of btree block */
xfs_mount_t *mp; /* mount structure for filesystem */
- xfs_btree_cur_t *new; /* new cursor value */
+ struct xfs_btree_cur *new; /* new cursor value */
xfs_trans_t *tp; /* transaction pointer, can be NULL */
tp = cur->bc_tp;
@@ -415,9 +415,9 @@ xfs_btree_dup_cursor(
* For each level current, re-get the buffer and copy the ptr value.
*/
for (i = 0; i < new->bc_nlevels; i++) {
- new->bc_ptrs[i] = cur->bc_ptrs[i];
- new->bc_ra[i] = cur->bc_ra[i];
- bp = cur->bc_bufs[i];
+ new->bc_levels[i].ptr = cur->bc_levels[i].ptr;
+ new->bc_levels[i].ra = cur->bc_levels[i].ra;
+ bp = cur->bc_levels[i].bp;
if (bp) {
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
xfs_buf_daddr(bp), mp->m_bsize,
@@ -429,7 +429,7 @@ xfs_btree_dup_cursor(
return error;
}
}
- new->bc_bufs[i] = bp;
+ new->bc_levels[i].bp = bp;
}
*ncur = new;
return 0;
@@ -681,7 +681,7 @@ xfs_btree_get_block(
return xfs_btree_get_iroot(cur);
}
- *bpp = cur->bc_bufs[level];
+ *bpp = cur->bc_levels[level].bp;
return XFS_BUF_TO_BLOCK(*bpp);
}
@@ -691,7 +691,7 @@ xfs_btree_get_block(
*/
STATIC int /* success=1, failure=0 */
xfs_btree_firstrec(
- xfs_btree_cur_t *cur, /* btree cursor */
+ struct xfs_btree_cur *cur, /* btree cursor */
int level) /* level to change */
{
struct xfs_btree_block *block; /* generic btree block pointer */
@@ -711,7 +711,7 @@ xfs_btree_firstrec(
/*
* Set the ptr value to 1, that's the first record/key.
*/
- cur->bc_ptrs[level] = 1;
+ cur->bc_levels[level].ptr = 1;
return 1;
}
@@ -721,7 +721,7 @@ xfs_btree_firstrec(
*/
STATIC int /* success=1, failure=0 */
xfs_btree_lastrec(
- xfs_btree_cur_t *cur, /* btree cursor */
+ struct xfs_btree_cur *cur, /* btree cursor */
int level) /* level to change */
{
struct xfs_btree_block *block; /* generic btree block pointer */
@@ -741,7 +741,7 @@ xfs_btree_lastrec(
/*
* Set the ptr value to numrecs, that's the last record/key.
*/
- cur->bc_ptrs[level] = be16_to_cpu(block->bb_numrecs);
+ cur->bc_levels[level].ptr = be16_to_cpu(block->bb_numrecs);
return 1;
}
@@ -922,11 +922,11 @@ xfs_btree_readahead(
(lev == cur->bc_nlevels - 1))
return 0;
- if ((cur->bc_ra[lev] | lr) == cur->bc_ra[lev])
+ if ((cur->bc_levels[lev].ra | lr) == cur->bc_levels[lev].ra)
return 0;
- cur->bc_ra[lev] |= lr;
- block = XFS_BUF_TO_BLOCK(cur->bc_bufs[lev]);
+ cur->bc_levels[lev].ra |= lr;
+ block = XFS_BUF_TO_BLOCK(cur->bc_levels[lev].bp);
if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
return xfs_btree_readahead_lblock(cur, lr, block);
@@ -985,28 +985,28 @@ xfs_btree_readahead_ptr(
*/
STATIC void
xfs_btree_setbuf(
- xfs_btree_cur_t *cur, /* btree cursor */
+ struct xfs_btree_cur *cur, /* btree cursor */
int lev, /* level in btree */
struct xfs_buf *bp) /* new buffer to set */
{
struct xfs_btree_block *b; /* btree block */
- if (cur->bc_bufs[lev])
- xfs_trans_brelse(cur->bc_tp, cur->bc_bufs[lev]);
- cur->bc_bufs[lev] = bp;
- cur->bc_ra[lev] = 0;
+ if (cur->bc_levels[lev].bp)
+ xfs_trans_brelse(cur->bc_tp, cur->bc_levels[lev].bp);
+ cur->bc_levels[lev].bp = bp;
+ cur->bc_levels[lev].ra = 0;
b = XFS_BUF_TO_BLOCK(bp);
if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
if (b->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK))
- cur->bc_ra[lev] |= XFS_BTCUR_LEFTRA;
+ cur->bc_levels[lev].ra |= XFS_BTCUR_LEFTRA;
if (b->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK))
- cur->bc_ra[lev] |= XFS_BTCUR_RIGHTRA;
+ cur->bc_levels[lev].ra |= XFS_BTCUR_RIGHTRA;
} else {
if (b->bb_u.s.bb_leftsib == cpu_to_be32(NULLAGBLOCK))
- cur->bc_ra[lev] |= XFS_BTCUR_LEFTRA;
+ cur->bc_levels[lev].ra |= XFS_BTCUR_LEFTRA;
if (b->bb_u.s.bb_rightsib == cpu_to_be32(NULLAGBLOCK))
- cur->bc_ra[lev] |= XFS_BTCUR_RIGHTRA;
+ cur->bc_levels[lev].ra |= XFS_BTCUR_RIGHTRA;
}
}
@@ -1548,7 +1548,7 @@ xfs_btree_increment(
#endif
/* We're done if we remain in the block after the increment. */
- if (++cur->bc_ptrs[level] <= xfs_btree_get_numrecs(block))
+ if (++cur->bc_levels[level].ptr <= xfs_btree_get_numrecs(block))
goto out1;
/* Fail if we just went off the right edge of the tree. */
@@ -1571,7 +1571,7 @@ xfs_btree_increment(
goto error0;
#endif
- if (++cur->bc_ptrs[lev] <= xfs_btree_get_numrecs(block))
+ if (++cur->bc_levels[lev].ptr <= xfs_btree_get_numrecs(block))
break;
/* Read-ahead the right block for the next loop. */
@@ -1598,14 +1598,14 @@ xfs_btree_increment(
for (block = xfs_btree_get_block(cur, lev, &bp); lev > level; ) {
union xfs_btree_ptr *ptrp;
- ptrp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[lev], block);
+ ptrp = xfs_btree_ptr_addr(cur, cur->bc_levels[lev].ptr, block);
--lev;
error = xfs_btree_read_buf_block(cur, ptrp, 0, &block, &bp);
if (error)
goto error0;
xfs_btree_setbuf(cur, lev, bp);
- cur->bc_ptrs[lev] = 1;
+ cur->bc_levels[lev].ptr = 1;
}
out1:
*stat = 1;
@@ -1641,7 +1641,7 @@ xfs_btree_decrement(
xfs_btree_readahead(cur, level, XFS_BTCUR_LEFTRA);
/* We're done if we remain in the block after the decrement. */
- if (--cur->bc_ptrs[level] > 0)
+ if (--cur->bc_levels[level].ptr > 0)
goto out1;
/* Get a pointer to the btree block. */
@@ -1665,7 +1665,7 @@ xfs_btree_decrement(
* Stop when we don't go off the left edge of a block.
*/
for (lev = level + 1; lev < cur->bc_nlevels; lev++) {
- if (--cur->bc_ptrs[lev] > 0)
+ if (--cur->bc_levels[lev].ptr > 0)
break;
/* Read-ahead the left block for the next loop. */
xfs_btree_readahead(cur, lev, XFS_BTCUR_LEFTRA);
@@ -1691,13 +1691,13 @@ xfs_btree_decrement(
for (block = xfs_btree_get_block(cur, lev, &bp); lev > level; ) {
union xfs_btree_ptr *ptrp;
- ptrp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[lev], block);
+ ptrp = xfs_btree_ptr_addr(cur, cur->bc_levels[lev].ptr, block);
--lev;
error = xfs_btree_read_buf_block(cur, ptrp, 0, &block, &bp);
if (error)
goto error0;
xfs_btree_setbuf(cur, lev, bp);
- cur->bc_ptrs[lev] = xfs_btree_get_numrecs(block);
+ cur->bc_levels[lev].ptr = xfs_btree_get_numrecs(block);
}
out1:
*stat = 1;
@@ -1735,7 +1735,7 @@ xfs_btree_lookup_get_block(
*
* Otherwise throw it away and get a new one.
*/
- bp = cur->bc_bufs[level];
+ bp = cur->bc_levels[level].bp;
error = xfs_btree_ptr_to_daddr(cur, pp, &daddr);
if (error)
return error;
@@ -1864,7 +1864,7 @@ xfs_btree_lookup(
return -EFSCORRUPTED;
}
- cur->bc_ptrs[0] = dir != XFS_LOOKUP_LE;
+ cur->bc_levels[0].ptr = dir != XFS_LOOKUP_LE;
*stat = 0;
return 0;
}
@@ -1916,7 +1916,7 @@ xfs_btree_lookup(
if (error)
goto error0;
- cur->bc_ptrs[level] = keyno;
+ cur->bc_levels[level].ptr = keyno;
}
}
@@ -1933,7 +1933,7 @@ xfs_btree_lookup(
!xfs_btree_ptr_is_null(cur, &ptr)) {
int i;
- cur->bc_ptrs[0] = keyno;
+ cur->bc_levels[0].ptr = keyno;
error = xfs_btree_increment(cur, 0, &i);
if (error)
goto error0;
@@ -1944,7 +1944,7 @@ xfs_btree_lookup(
}
} else if (dir == XFS_LOOKUP_LE && diff > 0)
keyno--;
- cur->bc_ptrs[0] = keyno;
+ cur->bc_levels[0].ptr = keyno;
/* Return if we succeeded or not. */
if (keyno == 0 || keyno > xfs_btree_get_numrecs(block))
@@ -2104,7 +2104,7 @@ __xfs_btree_updkeys(
if (error)
return error;
#endif
- ptr = cur->bc_ptrs[level];
+ ptr = cur->bc_levels[level].ptr;
nlkey = xfs_btree_key_addr(cur, ptr, block);
nhkey = xfs_btree_high_key_addr(cur, ptr, block);
if (!force_all &&
@@ -2171,7 +2171,7 @@ xfs_btree_update_keys(
if (error)
return error;
#endif
- ptr = cur->bc_ptrs[level];
+ ptr = cur->bc_levels[level].ptr;
kp = xfs_btree_key_addr(cur, ptr, block);
xfs_btree_copy_keys(cur, kp, &key, 1);
xfs_btree_log_keys(cur, bp, ptr, ptr);
@@ -2205,7 +2205,7 @@ xfs_btree_update(
goto error0;
#endif
/* Get the address of the rec to be updated. */
- ptr = cur->bc_ptrs[0];
+ ptr = cur->bc_levels[0].ptr;
rp = xfs_btree_rec_addr(cur, ptr, block);
/* Fill in the new contents and log them. */
@@ -2280,7 +2280,7 @@ xfs_btree_lshift(
* If the cursor entry is the one that would be moved, don't
* do it... it's too complicated.
*/
- if (cur->bc_ptrs[level] <= 1)
+ if (cur->bc_levels[level].ptr <= 1)
goto out0;
/* Set up the left neighbor as "left". */
@@ -2414,7 +2414,7 @@ xfs_btree_lshift(
goto error0;
/* Slide the cursor value left one. */
- cur->bc_ptrs[level]--;
+ cur->bc_levels[level].ptr--;
*stat = 1;
return 0;
@@ -2476,7 +2476,7 @@ xfs_btree_rshift(
* do it... it's too complicated.
*/
lrecs = xfs_btree_get_numrecs(left);
- if (cur->bc_ptrs[level] >= lrecs)
+ if (cur->bc_levels[level].ptr >= lrecs)
goto out0;
/* Set up the right neighbor as "right". */
@@ -2664,7 +2664,7 @@ __xfs_btree_split(
*/
lrecs = xfs_btree_get_numrecs(left);
rrecs = lrecs / 2;
- if ((lrecs & 1) && cur->bc_ptrs[level] <= rrecs + 1)
+ if ((lrecs & 1) && cur->bc_levels[level].ptr <= rrecs + 1)
rrecs++;
src_index = (lrecs - rrecs + 1);
@@ -2760,9 +2760,9 @@ __xfs_btree_split(
* If it's just pointing past the last entry in left, then we'll
* insert there, so don't change anything in that case.
*/
- if (cur->bc_ptrs[level] > lrecs + 1) {
+ if (cur->bc_levels[level].ptr > lrecs + 1) {
xfs_btree_setbuf(cur, level, rbp);
- cur->bc_ptrs[level] -= lrecs;
+ cur->bc_levels[level].ptr -= lrecs;
}
/*
* If there are more levels, we'll need another cursor which refers
@@ -2772,7 +2772,7 @@ __xfs_btree_split(
error = xfs_btree_dup_cursor(cur, curp);
if (error)
goto error0;
- (*curp)->bc_ptrs[level + 1]++;
+ (*curp)->bc_levels[level + 1].ptr++;
}
*ptrp = rptr;
*stat = 1;
@@ -2933,7 +2933,8 @@ xfs_btree_new_iroot(
be16_add_cpu(&block->bb_level, 1);
xfs_btree_set_numrecs(block, 1);
cur->bc_nlevels++;
- cur->bc_ptrs[level + 1] = 1;
+ ASSERT(cur->bc_nlevels <= cur->bc_maxlevels);
+ cur->bc_levels[level + 1].ptr = 1;
kp = xfs_btree_key_addr(cur, 1, block);
ckp = xfs_btree_key_addr(cur, 1, cblock);
@@ -3094,8 +3095,9 @@ xfs_btree_new_root(
/* Fix up the cursor. */
xfs_btree_setbuf(cur, cur->bc_nlevels, nbp);
- cur->bc_ptrs[cur->bc_nlevels] = nptr;
+ cur->bc_levels[cur->bc_nlevels].ptr = nptr;
cur->bc_nlevels++;
+ ASSERT(cur->bc_nlevels <= cur->bc_maxlevels);
*stat = 1;
return 0;
error0:
@@ -3152,7 +3154,7 @@ xfs_btree_make_block_unfull(
return error;
if (*stat) {
- *oindex = *index = cur->bc_ptrs[level];
+ *oindex = *index = cur->bc_levels[level].ptr;
return 0;
}
@@ -3167,7 +3169,7 @@ xfs_btree_make_block_unfull(
return error;
- *index = cur->bc_ptrs[level];
+ *index = cur->bc_levels[level].ptr;
return 0;
}
@@ -3214,7 +3216,7 @@ xfs_btree_insrec(
}
/* If we're off the left edge, return failure. */
- ptr = cur->bc_ptrs[level];
+ ptr = cur->bc_levels[level].ptr;
if (ptr == 0) {
*stat = 0;
return 0;
@@ -3557,7 +3559,7 @@ xfs_btree_kill_iroot(
if (error)
return error;
- cur->bc_bufs[level - 1] = NULL;
+ cur->bc_levels[level - 1].bp = NULL;
be16_add_cpu(&block->bb_level, -1);
xfs_trans_log_inode(cur->bc_tp, ip,
XFS_ILOG_CORE | xfs_ilog_fbroot(cur->bc_ino.whichfork));
@@ -3590,8 +3592,8 @@ xfs_btree_kill_root(
if (error)
return error;
- cur->bc_bufs[level] = NULL;
- cur->bc_ra[level] = 0;
+ cur->bc_levels[level].bp = NULL;
+ cur->bc_levels[level].ra = 0;
cur->bc_nlevels--;
return 0;
@@ -3650,7 +3652,7 @@ xfs_btree_delrec(
tcur = NULL;
/* Get the index of the entry being deleted, check for nothing there. */
- ptr = cur->bc_ptrs[level];
+ ptr = cur->bc_levels[level].ptr;
if (ptr == 0) {
*stat = 0;
return 0;
@@ -3960,7 +3962,7 @@ xfs_btree_delrec(
xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
tcur = NULL;
if (level == 0)
- cur->bc_ptrs[0]++;
+ cur->bc_levels[0].ptr++;
*stat = 1;
return 0;
@@ -4097,9 +4099,9 @@ xfs_btree_delrec(
* cursor to the left block, and fix up the index.
*/
if (bp != lbp) {
- cur->bc_bufs[level] = lbp;
- cur->bc_ptrs[level] += lrecs;
- cur->bc_ra[level] = 0;
+ cur->bc_levels[level].bp = lbp;
+ cur->bc_levels[level].ptr += lrecs;
+ cur->bc_levels[level].ra = 0;
}
/*
* If we joined with the right neighbor and there's a level above
@@ -4119,16 +4121,16 @@ xfs_btree_delrec(
* We can't use decrement because it would change the next level up.
*/
if (level > 0)
- cur->bc_ptrs[level]--;
+ cur->bc_levels[level].ptr--;
/*
* We combined blocks, so we have to update the parent keys if the
- * btree supports overlapped intervals. However, bc_ptrs[level + 1]
- * points to the old block so that the caller knows which record to
- * delete. Therefore, the caller must be savvy enough to call updkeys
- * for us if we return stat == 2. The other exit points from this
- * function don't require deletions further up the tree, so they can
- * call updkeys directly.
+ * btree supports overlapped intervals. However,
+ * bc_levels[level + 1].ptr points to the old block so that the caller
+ * knows which record to delete. Therefore, the caller must be savvy
+ * enough to call updkeys for us if we return stat == 2. The other
+ * exit points from this function don't require deletions further up
+ * the tree, so they can call updkeys directly.
*/
/* Return value means the next level up has something to do. */
@@ -4182,7 +4184,7 @@ xfs_btree_delete(
if (i == 0) {
for (level = 1; level < cur->bc_nlevels; level++) {
- if (cur->bc_ptrs[level] == 0) {
+ if (cur->bc_levels[level].ptr == 0) {
error = xfs_btree_decrement(cur, level, &i);
if (error)
goto error0;
@@ -4213,7 +4215,7 @@ xfs_btree_get_rec(
int error; /* error return value */
#endif
- ptr = cur->bc_ptrs[0];
+ ptr = cur->bc_levels[0].ptr;
block = xfs_btree_get_block(cur, 0, &bp);
#ifdef DEBUG
@@ -4512,21 +4514,76 @@ xfs_btree_sblock_verify(
}
/*
- * Calculate the number of btree levels needed to store a given number of
- * records in a short-format btree.
+ * For the given limits on leaf and keyptr records per block, calculate the
+ * height of the tree needed to index the number of leaf records.
*/
-uint
+unsigned int
xfs_btree_compute_maxlevels(
- uint *limits,
- unsigned long len)
+ const unsigned int *limits,
+ unsigned long long records)
+{
+ unsigned long long level_blocks = howmany_64(records, limits[0]);
+ unsigned int height = 1;
+
+ while (level_blocks > 1) {
+ level_blocks = howmany_64(level_blocks, limits[1]);
+ height++;
+ }
+
+ return height;
+}
+
+/*
+ * For the given limits on leaf and keyptr records per block, calculate the
+ * number of blocks needed to index the given number of leaf records.
+ */
+unsigned long long
+xfs_btree_calc_size(
+ const unsigned int *limits,
+ unsigned long long records)
+{
+ unsigned long long level_blocks = howmany_64(records, limits[0]);
+ unsigned long long blocks = level_blocks;
+
+ while (level_blocks > 1) {
+ level_blocks = howmany_64(level_blocks, limits[1]);
+ blocks += level_blocks;
+ }
+
+ return blocks;
+}
+
+/*
+ * Given a number of available blocks for the btree to consume with records and
+ * pointers, calculate the height of the tree needed to index all the records
+ * that space can hold based on the number of pointers each interior node
+ * holds.
+ *
+ * We start by assuming a single level tree consumes a single block, then track
+ * the number of blocks each node level consumes until we no longer have space
+ * to store the next node level. At this point, we are indexing all the leaf
+ * blocks in the space, and there's no more free space to split the tree any
+ * further. That's our maximum btree height.
+ */
+unsigned int
+xfs_btree_space_to_height(
+ const unsigned int *limits,
+ unsigned long long leaf_blocks)
{
- uint level;
- unsigned long maxblocks;
+ unsigned long long node_blocks = limits[1];
+ unsigned long long blocks_left = leaf_blocks - 1;
+ unsigned int height = 1;
+
+ if (leaf_blocks < 1)
+ return 0;
+
+ while (node_blocks < blocks_left) {
+ blocks_left -= node_blocks;
+ node_blocks *= limits[1];
+ height++;
+ }
- maxblocks = (len + limits[0] - 1) / limits[0];
- for (level = 1; maxblocks > 1; level++)
- maxblocks = (maxblocks + limits[1] - 1) / limits[1];
- return level;
+ return height;
}
/*
@@ -4661,23 +4718,25 @@ xfs_btree_overlapped_query_range(
if (error)
goto out;
#endif
- cur->bc_ptrs[level] = 1;
+ cur->bc_levels[level].ptr = 1;
while (level < cur->bc_nlevels) {
block = xfs_btree_get_block(cur, level, &bp);
/* End of node, pop back towards the root. */
- if (cur->bc_ptrs[level] > be16_to_cpu(block->bb_numrecs)) {
+ if (cur->bc_levels[level].ptr >
+ be16_to_cpu(block->bb_numrecs)) {
pop_up:
if (level < cur->bc_nlevels - 1)
- cur->bc_ptrs[level + 1]++;
+ cur->bc_levels[level + 1].ptr++;
level++;
continue;
}
if (level == 0) {
/* Handle a leaf node. */
- recp = xfs_btree_rec_addr(cur, cur->bc_ptrs[0], block);
+ recp = xfs_btree_rec_addr(cur, cur->bc_levels[0].ptr,
+ block);
cur->bc_ops->init_high_key_from_rec(&rec_hkey, recp);
ldiff = cur->bc_ops->diff_two_keys(cur, &rec_hkey,
@@ -4700,14 +4759,15 @@ pop_up:
/* Record is larger than high key; pop. */
goto pop_up;
}
- cur->bc_ptrs[level]++;
+ cur->bc_levels[level].ptr++;
continue;
}
/* Handle an internal node. */
- lkp = xfs_btree_key_addr(cur, cur->bc_ptrs[level], block);
- hkp = xfs_btree_high_key_addr(cur, cur->bc_ptrs[level], block);
- pp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[level], block);
+ lkp = xfs_btree_key_addr(cur, cur->bc_levels[level].ptr, block);
+ hkp = xfs_btree_high_key_addr(cur, cur->bc_levels[level].ptr,
+ block);
+ pp = xfs_btree_ptr_addr(cur, cur->bc_levels[level].ptr, block);
ldiff = cur->bc_ops->diff_two_keys(cur, hkp, low_key);
hdiff = cur->bc_ops->diff_two_keys(cur, high_key, lkp);
@@ -4730,13 +4790,13 @@ pop_up:
if (error)
goto out;
#endif
- cur->bc_ptrs[level] = 1;
+ cur->bc_levels[level].ptr = 1;
continue;
} else if (hdiff < 0) {
/* The low key is larger than the upper range; pop. */
goto pop_up;
}
- cur->bc_ptrs[level]++;
+ cur->bc_levels[level].ptr++;
}
out:
@@ -4747,13 +4807,14 @@ out:
* with a zero-results range query, so release the buffers if we
* failed to return any results.
*/
- if (cur->bc_bufs[0] == NULL) {
+ if (cur->bc_levels[0].bp == NULL) {
for (i = 0; i < cur->bc_nlevels; i++) {
- if (cur->bc_bufs[i]) {
- xfs_trans_brelse(cur->bc_tp, cur->bc_bufs[i]);
- cur->bc_bufs[i] = NULL;
- cur->bc_ptrs[i] = 0;
- cur->bc_ra[i] = 0;
+ if (cur->bc_levels[i].bp) {
+ xfs_trans_brelse(cur->bc_tp,
+ cur->bc_levels[i].bp);
+ cur->bc_levels[i].bp = NULL;
+ cur->bc_levels[i].ptr = 0;
+ cur->bc_levels[i].ra = 0;
}
}
}
@@ -4816,29 +4877,6 @@ xfs_btree_query_all(
return xfs_btree_simple_query_range(cur, &low_key, &high_key, fn, priv);
}
-/*
- * Calculate the number of blocks needed to store a given number of records
- * in a short-format (per-AG metadata) btree.
- */
-unsigned long long
-xfs_btree_calc_size(
- uint *limits,
- unsigned long long len)
-{
- int level;
- int maxrecs;
- unsigned long long rval;
-
- maxrecs = limits[0];
- for (level = 0, rval = 0; len > 1; level++) {
- len += maxrecs - 1;
- do_div(len, maxrecs);
- maxrecs = limits[1];
- rval += len;
- }
- return rval;
-}
-
static int
xfs_btree_count_blocks_helper(
struct xfs_btree_cur *cur,
@@ -4915,7 +4953,7 @@ xfs_btree_has_more_records(
block = xfs_btree_get_block(cur, 0, &bp);
/* There are still records in this block. */
- if (cur->bc_ptrs[0] < xfs_btree_get_numrecs(block))
+ if (cur->bc_levels[0].ptr < xfs_btree_get_numrecs(block))
return true;
/* There are more record blocks. */
@@ -4924,3 +4962,42 @@ xfs_btree_has_more_records(
else
return block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK);
}
+
+/* Set up all the btree cursor caches. */
+int __init
+xfs_btree_init_cur_caches(void)
+{
+ int error;
+
+ error = xfs_allocbt_init_cur_cache();
+ if (error)
+ return error;
+ error = xfs_inobt_init_cur_cache();
+ if (error)
+ goto err;
+ error = xfs_bmbt_init_cur_cache();
+ if (error)
+ goto err;
+ error = xfs_rmapbt_init_cur_cache();
+ if (error)
+ goto err;
+ error = xfs_refcountbt_init_cur_cache();
+ if (error)
+ goto err;
+
+ return 0;
+err:
+ xfs_btree_destroy_cur_caches();
+ return error;
+}
+
+/* Destroy all the btree cursor caches, if they've been allocated. */
+void
+xfs_btree_destroy_cur_caches(void)
+{
+ xfs_allocbt_destroy_cur_cache();
+ xfs_inobt_destroy_cur_cache();
+ xfs_bmbt_destroy_cur_cache();
+ xfs_rmapbt_destroy_cur_cache();
+ xfs_refcountbt_destroy_cur_cache();
+}
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 4eaf8517f850..22d9f411fde6 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -13,8 +13,6 @@ struct xfs_trans;
struct xfs_ifork;
struct xfs_perag;
-extern kmem_zone_t *xfs_btree_cur_zone;
-
/*
* Generic key, ptr and record wrapper structures.
*
@@ -92,8 +90,6 @@ uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum);
#define XFS_BTREE_STATS_ADD(cur, stat, val) \
XFS_STATS_ADD_OFF((cur)->bc_mp, (cur)->bc_statoff + __XBTS_ ## stat, val)
-#define XFS_BTREE_MAXLEVELS 9 /* max of all btrees */
-
struct xfs_btree_ops {
/* size of the key and record structures */
size_t key_len;
@@ -181,18 +177,18 @@ union xfs_btree_irec {
/* Per-AG btree information. */
struct xfs_btree_cur_ag {
- struct xfs_perag *pag;
+ struct xfs_perag *pag;
union {
struct xfs_buf *agbp;
struct xbtree_afakeroot *afake; /* for staging cursor */
};
union {
struct {
- unsigned long nr_ops; /* # record updates */
- int shape_changes; /* # of extent splits */
+ unsigned int nr_ops; /* # record updates */
+ unsigned int shape_changes; /* # of extent splits */
} refc;
struct {
- bool active; /* allocation cursor state */
+ bool active; /* allocation cursor state */
} abt;
};
};
@@ -212,26 +208,35 @@ struct xfs_btree_cur_ino {
#define XFS_BTCUR_BMBT_INVALID_OWNER (1 << 1)
};
+struct xfs_btree_level {
+ /* buffer pointer */
+ struct xfs_buf *bp;
+
+ /* key/record number */
+ uint16_t ptr;
+
+ /* readahead info */
+#define XFS_BTCUR_LEFTRA (1 << 0) /* left sibling has been read-ahead */
+#define XFS_BTCUR_RIGHTRA (1 << 1) /* right sibling has been read-ahead */
+ uint16_t ra;
+};
+
/*
* Btree cursor structure.
* This collects all information needed by the btree code in one place.
*/
-typedef struct xfs_btree_cur
+struct xfs_btree_cur
{
struct xfs_trans *bc_tp; /* transaction we're in, if any */
struct xfs_mount *bc_mp; /* file system mount struct */
const struct xfs_btree_ops *bc_ops;
- uint bc_flags; /* btree features - below */
+ struct kmem_cache *bc_cache; /* cursor cache */
+ unsigned int bc_flags; /* btree features - below */
+ xfs_btnum_t bc_btnum; /* identifies which btree type */
union xfs_btree_irec bc_rec; /* current insert/search record value */
- struct xfs_buf *bc_bufs[XFS_BTREE_MAXLEVELS]; /* buf ptr per level */
- int bc_ptrs[XFS_BTREE_MAXLEVELS]; /* key/record # */
- uint8_t bc_ra[XFS_BTREE_MAXLEVELS]; /* readahead bits */
-#define XFS_BTCUR_LEFTRA 1 /* left sibling has been read-ahead */
-#define XFS_BTCUR_RIGHTRA 2 /* right sibling has been read-ahead */
- uint8_t bc_nlevels; /* number of levels in the tree */
- uint8_t bc_blocklog; /* log2(blocksize) of btree blocks */
- xfs_btnum_t bc_btnum; /* identifies which btree type */
- int bc_statoff; /* offset of btre stats array */
+ uint8_t bc_nlevels; /* number of levels in the tree */
+ uint8_t bc_maxlevels; /* maximum levels for this btree type */
+ int bc_statoff; /* offset of btree stats array */
/*
* Short btree pointers need an agno to be able to turn the pointers
@@ -243,7 +248,21 @@ typedef struct xfs_btree_cur
struct xfs_btree_cur_ag bc_ag;
struct xfs_btree_cur_ino bc_ino;
};
-} xfs_btree_cur_t;
+
+ /* Must be at the end of the struct! */
+ struct xfs_btree_level bc_levels[];
+};
+
+/*
+ * Compute the size of a btree cursor that can handle a btree of a given
+ * height. The bc_levels array handles node and leaf blocks, so its size
+ * is exactly nlevels.
+ */
+static inline size_t
+xfs_btree_cur_sizeof(unsigned int nlevels)
+{
+ return struct_size((struct xfs_btree_cur *)NULL, bc_levels, nlevels);
+}
/* cursor flags */
#define XFS_BTREE_LONG_PTRS (1<<0) /* pointers are 64bits long */
@@ -258,7 +277,6 @@ typedef struct xfs_btree_cur
*/
#define XFS_BTREE_STAGING (1<<5)
-
#define XFS_BTREE_NOERROR 0
#define XFS_BTREE_ERROR 1
@@ -309,7 +327,7 @@ xfs_btree_check_sptr(
*/
void
xfs_btree_del_cursor(
- xfs_btree_cur_t *cur, /* btree cursor */
+ struct xfs_btree_cur *cur, /* btree cursor */
int error); /* del because of error */
/*
@@ -318,8 +336,8 @@ xfs_btree_del_cursor(
*/
int /* error */
xfs_btree_dup_cursor(
- xfs_btree_cur_t *cur, /* input cursor */
- xfs_btree_cur_t **ncur);/* output cursor */
+ struct xfs_btree_cur *cur, /* input cursor */
+ struct xfs_btree_cur **ncur);/* output cursor */
/*
* Compute first and last byte offsets for the fields given.
@@ -460,8 +478,12 @@ xfs_failaddr_t xfs_btree_lblock_v5hdr_verify(struct xfs_buf *bp,
xfs_failaddr_t xfs_btree_lblock_verify(struct xfs_buf *bp,
unsigned int max_recs);
-uint xfs_btree_compute_maxlevels(uint *limits, unsigned long len);
-unsigned long long xfs_btree_calc_size(uint *limits, unsigned long long len);
+unsigned int xfs_btree_compute_maxlevels(const unsigned int *limits,
+ unsigned long long records);
+unsigned long long xfs_btree_calc_size(const unsigned int *limits,
+ unsigned long long records);
+unsigned int xfs_btree_space_to_height(const unsigned int *limits,
+ unsigned long long blocks);
/*
* Return codes for the query range iterator function are 0 to continue
@@ -527,7 +549,7 @@ struct xfs_ifork *xfs_btree_ifork_ptr(struct xfs_btree_cur *cur);
/* Does this cursor point to the last block in the given level? */
static inline bool
xfs_btree_islastblock(
- xfs_btree_cur_t *cur,
+ struct xfs_btree_cur *cur,
int level)
{
struct xfs_btree_block *block;
@@ -558,4 +580,27 @@ void xfs_btree_copy_keys(struct xfs_btree_cur *cur,
union xfs_btree_key *dst_key,
const union xfs_btree_key *src_key, int numkeys);
+static inline struct xfs_btree_cur *
+xfs_btree_alloc_cursor(
+ struct xfs_mount *mp,
+ struct xfs_trans *tp,
+ xfs_btnum_t btnum,
+ uint8_t maxlevels,
+ struct kmem_cache *cache)
+{
+ struct xfs_btree_cur *cur;
+
+ cur = kmem_cache_zalloc(cache, GFP_NOFS | __GFP_NOFAIL);
+ cur->bc_tp = tp;
+ cur->bc_mp = mp;
+ cur->bc_btnum = btnum;
+ cur->bc_maxlevels = maxlevels;
+ cur->bc_cache = cache;
+
+ return cur;
+}
+
+int __init xfs_btree_init_cur_caches(void);
+void xfs_btree_destroy_cur_caches(void);
+
#endif /* __XFS_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c
index ac9e80152b5c..dd75e208b543 100644
--- a/fs/xfs/libxfs/xfs_btree_staging.c
+++ b/fs/xfs/libxfs/xfs_btree_staging.c
@@ -657,12 +657,12 @@ xfs_btree_bload_compute_geometry(
* checking levels 0 and 1 here, so set bc_nlevels such that the btree
* code doesn't interpret either as the root level.
*/
- cur->bc_nlevels = XFS_BTREE_MAXLEVELS - 1;
+ cur->bc_nlevels = cur->bc_maxlevels - 1;
xfs_btree_bload_ensure_slack(cur, &bbl->leaf_slack, 0);
xfs_btree_bload_ensure_slack(cur, &bbl->node_slack, 1);
bbl->nr_records = nr_this_level = nr_records;
- for (cur->bc_nlevels = 1; cur->bc_nlevels < XFS_BTREE_MAXLEVELS;) {
+ for (cur->bc_nlevels = 1; cur->bc_nlevels <= cur->bc_maxlevels;) {
uint64_t level_blocks;
uint64_t dontcare64;
unsigned int level = cur->bc_nlevels - 1;
@@ -703,6 +703,7 @@ xfs_btree_bload_compute_geometry(
* block-based btree level.
*/
cur->bc_nlevels++;
+ ASSERT(cur->bc_nlevels <= cur->bc_maxlevels);
xfs_btree_bload_level_geometry(cur, bbl, level,
nr_this_level, &avg_per_block,
&level_blocks, &dontcare64);
@@ -718,13 +719,14 @@ xfs_btree_bload_compute_geometry(
/* Otherwise, we need another level of btree. */
cur->bc_nlevels++;
+ ASSERT(cur->bc_nlevels <= cur->bc_maxlevels);
}
nr_blocks += level_blocks;
nr_this_level = level_blocks;
}
- if (cur->bc_nlevels == XFS_BTREE_MAXLEVELS)
+ if (cur->bc_nlevels > cur->bc_maxlevels)
return -EOVERFLOW;
bbl->btree_height = cur->bc_nlevels;
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index c062e2c85178..dd7a2dbce1d1 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -72,7 +72,7 @@ STATIC int xfs_da3_blk_unlink(xfs_da_state_t *state,
xfs_da_state_blk_t *save_blk);
-kmem_zone_t *xfs_da_state_zone; /* anchor for state struct zone */
+struct kmem_cache *xfs_da_state_cache; /* anchor for dir/attr state */
/*
* Allocate a dir-state structure.
@@ -84,7 +84,7 @@ xfs_da_state_alloc(
{
struct xfs_da_state *state;
- state = kmem_cache_zalloc(xfs_da_state_zone, GFP_NOFS | __GFP_NOFAIL);
+ state = kmem_cache_zalloc(xfs_da_state_cache, GFP_NOFS | __GFP_NOFAIL);
state->args = args;
state->mp = args->dp->i_mount;
return state;
@@ -113,7 +113,7 @@ xfs_da_state_free(xfs_da_state_t *state)
#ifdef DEBUG
memset((char *)state, 0, sizeof(*state));
#endif /* DEBUG */
- kmem_cache_free(xfs_da_state_zone, state);
+ kmem_cache_free(xfs_da_state_cache, state);
}
static inline int xfs_dabuf_nfsb(struct xfs_mount *mp, int whichfork)
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index ad5dd324631a..0faf7d9ac241 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -9,7 +9,6 @@
struct xfs_inode;
struct xfs_trans;
-struct zone;
/*
* Directory/attribute geometry information. There will be one of these for each
@@ -227,6 +226,6 @@ void xfs_da3_node_hdr_from_disk(struct xfs_mount *mp,
void xfs_da3_node_hdr_to_disk(struct xfs_mount *mp,
struct xfs_da_intnode *to, struct xfs_da3_icnode_hdr *from);
-extern struct kmem_zone *xfs_da_state_zone;
+extern struct kmem_cache *xfs_da_state_cache;
#endif /* __XFS_DA_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index eff4a127188e..0805ade2d300 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -18,6 +18,12 @@
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_log.h"
+#include "xfs_rmap.h"
+#include "xfs_refcount.h"
+#include "xfs_bmap.h"
+#include "xfs_alloc.h"
+
+static struct kmem_cache *xfs_defer_pending_cache;
/*
* Deferred Operations in XFS
@@ -232,23 +238,20 @@ xfs_defer_trans_abort(
}
}
-/* Roll a transaction so we can do some deferred op processing. */
-STATIC int
-xfs_defer_trans_roll(
- struct xfs_trans **tpp)
+/*
+ * Capture resources that the caller said not to release ("held") when the
+ * transaction commits. Caller is responsible for zero-initializing @dres.
+ */
+static int
+xfs_defer_save_resources(
+ struct xfs_defer_resources *dres,
+ struct xfs_trans *tp)
{
- struct xfs_trans *tp = *tpp;
struct xfs_buf_log_item *bli;
struct xfs_inode_log_item *ili;
struct xfs_log_item *lip;
- struct xfs_buf *bplist[XFS_DEFER_OPS_NR_BUFS];
- struct xfs_inode *iplist[XFS_DEFER_OPS_NR_INODES];
- unsigned int ordered = 0; /* bitmap */
- int bpcount = 0, ipcount = 0;
- int i;
- int error;
- BUILD_BUG_ON(NBBY * sizeof(ordered) < XFS_DEFER_OPS_NR_BUFS);
+ BUILD_BUG_ON(NBBY * sizeof(dres->dr_ordered) < XFS_DEFER_OPS_NR_BUFS);
list_for_each_entry(lip, &tp->t_items, li_trans) {
switch (lip->li_type) {
@@ -256,28 +259,29 @@ xfs_defer_trans_roll(
bli = container_of(lip, struct xfs_buf_log_item,
bli_item);
if (bli->bli_flags & XFS_BLI_HOLD) {
- if (bpcount >= XFS_DEFER_OPS_NR_BUFS) {
+ if (dres->dr_bufs >= XFS_DEFER_OPS_NR_BUFS) {
ASSERT(0);
return -EFSCORRUPTED;
}
if (bli->bli_flags & XFS_BLI_ORDERED)
- ordered |= (1U << bpcount);
+ dres->dr_ordered |=
+ (1U << dres->dr_bufs);
else
xfs_trans_dirty_buf(tp, bli->bli_buf);
- bplist[bpcount++] = bli->bli_buf;
+ dres->dr_bp[dres->dr_bufs++] = bli->bli_buf;
}
break;
case XFS_LI_INODE:
ili = container_of(lip, struct xfs_inode_log_item,
ili_item);
if (ili->ili_lock_flags == 0) {
- if (ipcount >= XFS_DEFER_OPS_NR_INODES) {
+ if (dres->dr_inos >= XFS_DEFER_OPS_NR_INODES) {
ASSERT(0);
return -EFSCORRUPTED;
}
xfs_trans_log_inode(tp, ili->ili_inode,
XFS_ILOG_CORE);
- iplist[ipcount++] = ili->ili_inode;
+ dres->dr_ip[dres->dr_inos++] = ili->ili_inode;
}
break;
default:
@@ -285,7 +289,43 @@ xfs_defer_trans_roll(
}
}
- trace_xfs_defer_trans_roll(tp, _RET_IP_);
+ return 0;
+}
+
+/* Attach the held resources to the transaction. */
+static void
+xfs_defer_restore_resources(
+ struct xfs_trans *tp,
+ struct xfs_defer_resources *dres)
+{
+ unsigned short i;
+
+ /* Rejoin the joined inodes. */
+ for (i = 0; i < dres->dr_inos; i++)
+ xfs_trans_ijoin(tp, dres->dr_ip[i], 0);
+
+ /* Rejoin the buffers and dirty them so the log moves forward. */
+ for (i = 0; i < dres->dr_bufs; i++) {
+ xfs_trans_bjoin(tp, dres->dr_bp[i]);
+ if (dres->dr_ordered & (1U << i))
+ xfs_trans_ordered_buf(tp, dres->dr_bp[i]);
+ xfs_trans_bhold(tp, dres->dr_bp[i]);
+ }
+}
+
+/* Roll a transaction so we can do some deferred op processing. */
+STATIC int
+xfs_defer_trans_roll(
+ struct xfs_trans **tpp)
+{
+ struct xfs_defer_resources dres = { };
+ int error;
+
+ error = xfs_defer_save_resources(&dres, *tpp);
+ if (error)
+ return error;
+
+ trace_xfs_defer_trans_roll(*tpp, _RET_IP_);
/*
* Roll the transaction. Rolling always given a new transaction (even
@@ -295,22 +335,11 @@ xfs_defer_trans_roll(
* happened.
*/
error = xfs_trans_roll(tpp);
- tp = *tpp;
- /* Rejoin the joined inodes. */
- for (i = 0; i < ipcount; i++)
- xfs_trans_ijoin(tp, iplist[i], 0);
-
- /* Rejoin the buffers and dirty them so the log moves forward. */
- for (i = 0; i < bpcount; i++) {
- xfs_trans_bjoin(tp, bplist[i]);
- if (ordered & (1U << i))
- xfs_trans_ordered_buf(tp, bplist[i]);
- xfs_trans_bhold(tp, bplist[i]);
- }
+ xfs_defer_restore_resources(*tpp, &dres);
if (error)
- trace_xfs_defer_trans_roll_error(tp, error);
+ trace_xfs_defer_trans_roll_error(*tpp, error);
return error;
}
@@ -342,7 +371,7 @@ xfs_defer_cancel_list(
ops->cancel_item(pwi);
}
ASSERT(dfp->dfp_count == 0);
- kmem_free(dfp);
+ kmem_cache_free(xfs_defer_pending_cache, dfp);
}
}
@@ -439,7 +468,7 @@ xfs_defer_finish_one(
/* Done with the dfp, free it. */
list_del(&dfp->dfp_list);
- kmem_free(dfp);
+ kmem_cache_free(xfs_defer_pending_cache, dfp);
out:
if (ops->finish_cleanup)
ops->finish_cleanup(tp, state, error);
@@ -573,8 +602,8 @@ xfs_defer_add(
dfp = NULL;
}
if (!dfp) {
- dfp = kmem_alloc(sizeof(struct xfs_defer_pending),
- KM_NOFS);
+ dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
+ GFP_NOFS | __GFP_NOFAIL);
dfp->dfp_type = type;
dfp->dfp_intent = NULL;
dfp->dfp_done = NULL;
@@ -627,10 +656,11 @@ xfs_defer_move(
*/
static struct xfs_defer_capture *
xfs_defer_ops_capture(
- struct xfs_trans *tp,
- struct xfs_inode *capture_ip)
+ struct xfs_trans *tp)
{
struct xfs_defer_capture *dfc;
+ unsigned short i;
+ int error;
if (list_empty(&tp->t_dfops))
return NULL;
@@ -654,27 +684,48 @@ xfs_defer_ops_capture(
/* Preserve the log reservation size. */
dfc->dfc_logres = tp->t_log_res;
+ error = xfs_defer_save_resources(&dfc->dfc_held, tp);
+ if (error) {
+ /*
+ * Resource capture should never fail, but if it does, we
+ * still have to shut down the log and release things
+ * properly.
+ */
+ xfs_force_shutdown(tp->t_mountp, SHUTDOWN_CORRUPT_INCORE);
+ }
+
/*
- * Grab an extra reference to this inode and attach it to the capture
- * structure.
+ * Grab extra references to the inodes and buffers because callers are
+ * expected to release their held references after we commit the
+ * transaction.
*/
- if (capture_ip) {
- ihold(VFS_I(capture_ip));
- dfc->dfc_capture_ip = capture_ip;
+ for (i = 0; i < dfc->dfc_held.dr_inos; i++) {
+ ASSERT(xfs_isilocked(dfc->dfc_held.dr_ip[i], XFS_ILOCK_EXCL));
+ ihold(VFS_I(dfc->dfc_held.dr_ip[i]));
}
+ for (i = 0; i < dfc->dfc_held.dr_bufs; i++)
+ xfs_buf_hold(dfc->dfc_held.dr_bp[i]);
+
return dfc;
}
/* Release all resources that we used to capture deferred ops. */
void
-xfs_defer_ops_release(
+xfs_defer_ops_capture_free(
struct xfs_mount *mp,
struct xfs_defer_capture *dfc)
{
+ unsigned short i;
+
xfs_defer_cancel_list(mp, &dfc->dfc_dfops);
- if (dfc->dfc_capture_ip)
- xfs_irele(dfc->dfc_capture_ip);
+
+ for (i = 0; i < dfc->dfc_held.dr_bufs; i++)
+ xfs_buf_relse(dfc->dfc_held.dr_bp[i]);
+
+ for (i = 0; i < dfc->dfc_held.dr_inos; i++)
+ xfs_irele(dfc->dfc_held.dr_ip[i]);
+
kmem_free(dfc);
}
@@ -689,24 +740,21 @@ xfs_defer_ops_release(
int
xfs_defer_ops_capture_and_commit(
struct xfs_trans *tp,
- struct xfs_inode *capture_ip,
struct list_head *capture_list)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_defer_capture *dfc;
int error;
- ASSERT(!capture_ip || xfs_isilocked(capture_ip, XFS_ILOCK_EXCL));
-
/* If we don't capture anything, commit transaction and exit. */
- dfc = xfs_defer_ops_capture(tp, capture_ip);
+ dfc = xfs_defer_ops_capture(tp);
if (!dfc)
return xfs_trans_commit(tp);
/* Commit the transaction and add the capture structure to the list. */
error = xfs_trans_commit(tp);
if (error) {
- xfs_defer_ops_release(mp, dfc);
+ xfs_defer_ops_capture_free(mp, dfc);
return error;
}
@@ -724,17 +772,19 @@ void
xfs_defer_ops_continue(
struct xfs_defer_capture *dfc,
struct xfs_trans *tp,
- struct xfs_inode **captured_ipp)
+ struct xfs_defer_resources *dres)
{
ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
ASSERT(!(tp->t_flags & XFS_TRANS_DIRTY));
/* Lock and join the captured inode to the new transaction. */
- if (dfc->dfc_capture_ip) {
- xfs_ilock(dfc->dfc_capture_ip, XFS_ILOCK_EXCL);
- xfs_trans_ijoin(tp, dfc->dfc_capture_ip, 0);
- }
- *captured_ipp = dfc->dfc_capture_ip;
+ if (dfc->dfc_held.dr_inos == 2)
+ xfs_lock_two_inodes(dfc->dfc_held.dr_ip[0], XFS_ILOCK_EXCL,
+ dfc->dfc_held.dr_ip[1], XFS_ILOCK_EXCL);
+ else if (dfc->dfc_held.dr_inos == 1)
+ xfs_ilock(dfc->dfc_held.dr_ip[0], XFS_ILOCK_EXCL);
+ xfs_defer_restore_resources(tp, &dfc->dfc_held);
+ memcpy(dres, &dfc->dfc_held, sizeof(struct xfs_defer_resources));
/* Move captured dfops chain and state to the transaction. */
list_splice_init(&dfc->dfc_dfops, &tp->t_dfops);
@@ -742,3 +792,82 @@ xfs_defer_ops_continue(
kmem_free(dfc);
}
+
+/* Release the resources captured and continued during recovery. */
+void
+xfs_defer_resources_rele(
+ struct xfs_defer_resources *dres)
+{
+ unsigned short i;
+
+ for (i = 0; i < dres->dr_inos; i++) {
+ xfs_iunlock(dres->dr_ip[i], XFS_ILOCK_EXCL);
+ xfs_irele(dres->dr_ip[i]);
+ dres->dr_ip[i] = NULL;
+ }
+
+ for (i = 0; i < dres->dr_bufs; i++) {
+ xfs_buf_relse(dres->dr_bp[i]);
+ dres->dr_bp[i] = NULL;
+ }
+
+ dres->dr_inos = 0;
+ dres->dr_bufs = 0;
+ dres->dr_ordered = 0;
+}
+
+static inline int __init
+xfs_defer_init_cache(void)
+{
+ xfs_defer_pending_cache = kmem_cache_create("xfs_defer_pending",
+ sizeof(struct xfs_defer_pending),
+ 0, 0, NULL);
+
+ return xfs_defer_pending_cache != NULL ? 0 : -ENOMEM;
+}
+
+static inline void
+xfs_defer_destroy_cache(void)
+{
+ kmem_cache_destroy(xfs_defer_pending_cache);
+ xfs_defer_pending_cache = NULL;
+}
+
+/* Set up caches for deferred work items. */
+int __init
+xfs_defer_init_item_caches(void)
+{
+ int error;
+
+ error = xfs_defer_init_cache();
+ if (error)
+ return error;
+ error = xfs_rmap_intent_init_cache();
+ if (error)
+ goto err;
+ error = xfs_refcount_intent_init_cache();
+ if (error)
+ goto err;
+ error = xfs_bmap_intent_init_cache();
+ if (error)
+ goto err;
+ error = xfs_extfree_intent_init_cache();
+ if (error)
+ goto err;
+
+ return 0;
+err:
+ xfs_defer_destroy_item_caches();
+ return error;
+}
+
+/* Destroy all the deferred work item caches, if they've been allocated. */
+void
+xfs_defer_destroy_item_caches(void)
+{
+ xfs_extfree_intent_destroy_cache();
+ xfs_bmap_intent_destroy_cache();
+ xfs_refcount_intent_destroy_cache();
+ xfs_rmap_intent_destroy_cache();
+ xfs_defer_destroy_cache();
+}
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 05472f71fffe..7bb8a31ad65b 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -65,6 +65,30 @@ extern const struct xfs_defer_op_type xfs_extent_free_defer_type;
extern const struct xfs_defer_op_type xfs_agfl_free_defer_type;
/*
+ * Deferred operation item relogging limits.
+ */
+#define XFS_DEFER_OPS_NR_INODES 2 /* join up to two inodes */
+#define XFS_DEFER_OPS_NR_BUFS 2 /* join up to two buffers */
+
+/* Resources that must be held across a transaction roll. */
+struct xfs_defer_resources {
+ /* held buffers */
+ struct xfs_buf *dr_bp[XFS_DEFER_OPS_NR_BUFS];
+
+ /* inodes with no unlock flags */
+ struct xfs_inode *dr_ip[XFS_DEFER_OPS_NR_INODES];
+
+ /* number of held buffers */
+ unsigned short dr_bufs;
+
+ /* bitmap of ordered buffers */
+ unsigned short dr_ordered;
+
+ /* number of held inodes */
+ unsigned short dr_inos;
+};
+
+/*
* This structure enables a dfops user to detach the chain of deferred
* operations from a transaction so that they can be continued later.
*/
@@ -83,11 +107,7 @@ struct xfs_defer_capture {
/* Log reservation saved from the transaction. */
unsigned int dfc_logres;
- /*
- * An inode reference that must be maintained to complete the deferred
- * work.
- */
- struct xfs_inode *dfc_capture_ip;
+ struct xfs_defer_resources dfc_held;
};
/*
@@ -95,9 +115,14 @@ struct xfs_defer_capture {
* This doesn't normally happen except log recovery.
*/
int xfs_defer_ops_capture_and_commit(struct xfs_trans *tp,
- struct xfs_inode *capture_ip, struct list_head *capture_list);
+ struct list_head *capture_list);
void xfs_defer_ops_continue(struct xfs_defer_capture *d, struct xfs_trans *tp,
- struct xfs_inode **captured_ipp);
-void xfs_defer_ops_release(struct xfs_mount *mp, struct xfs_defer_capture *d);
+ struct xfs_defer_resources *dres);
+void xfs_defer_ops_capture_free(struct xfs_mount *mp,
+ struct xfs_defer_capture *d);
+void xfs_defer_resources_rele(struct xfs_defer_resources *dres);
+
+int __init xfs_defer_init_item_caches(void);
+void xfs_defer_destroy_item_caches(void);
#endif /* __XFS_DEFER_H__ */
diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c
index deeb74becabc..15a362e2f5ea 100644
--- a/fs/xfs/libxfs/xfs_dquot_buf.c
+++ b/fs/xfs/libxfs/xfs_dquot_buf.c
@@ -22,7 +22,7 @@ xfs_calc_dquots_per_chunk(
unsigned int nbblks) /* basic block units */
{
ASSERT(nbblks > 0);
- return BBTOB(nbblks) / sizeof(xfs_dqblk_t);
+ return BBTOB(nbblks) / sizeof(struct xfs_dqblk);
}
/*
@@ -127,7 +127,7 @@ xfs_dqblk_repair(
* Typically, a repair is only requested by quotacheck.
*/
ASSERT(id != -1);
- memset(dqb, 0, sizeof(xfs_dqblk_t));
+ memset(dqb, 0, sizeof(struct xfs_dqblk));
dqb->dd_diskdq.d_magic = cpu_to_be16(XFS_DQUOT_MAGIC);
dqb->dd_diskdq.d_version = XFS_DQUOT_VERSION;
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 2d7057b7984b..d665c04e69dd 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -184,7 +184,7 @@ typedef struct xfs_sb {
* Superblock - on disk version. Must match the in core version above.
* Must be padded to 64 bit alignment.
*/
-typedef struct xfs_dsb {
+struct xfs_dsb {
__be32 sb_magicnum; /* magic number == XFS_SB_MAGIC */
__be32 sb_blocksize; /* logical block size, bytes */
__be64 sb_dblocks; /* number of data blocks */
@@ -263,7 +263,7 @@ typedef struct xfs_dsb {
uuid_t sb_meta_uuid; /* metadata file system unique id */
/* must be padded to 64 bit alignment */
-} xfs_dsb_t;
+};
/*
* Misc. Flags - warning - these will be cleared by xfs_repair unless
@@ -780,7 +780,7 @@ static inline time64_t xfs_bigtime_to_unix(uint64_t ondisk_seconds)
* padding field for v3 inodes.
*/
#define XFS_DINODE_MAGIC 0x494e /* 'IN' */
-typedef struct xfs_dinode {
+struct xfs_dinode {
__be16 di_magic; /* inode magic # = XFS_DINODE_MAGIC */
__be16 di_mode; /* mode and type of file */
__u8 di_version; /* inode version */
@@ -825,7 +825,7 @@ typedef struct xfs_dinode {
uuid_t di_uuid; /* UUID of the filesystem */
/* structure must be padded to 64 bit alignment */
-} xfs_dinode_t;
+};
#define XFS_DINODE_CRC_OFF offsetof(struct xfs_dinode, di_crc)
@@ -1215,7 +1215,7 @@ struct xfs_disk_dquot {
* This is what goes on disk. This is separated from the xfs_disk_dquot because
* carrying the unnecessary padding would be a waste of memory.
*/
-typedef struct xfs_dqblk {
+struct xfs_dqblk {
struct xfs_disk_dquot dd_diskdq; /* portion living incore as well */
char dd_fill[4];/* filling for posterity */
@@ -1225,7 +1225,7 @@ typedef struct xfs_dqblk {
__be32 dd_crc; /* checksum */
__be64 dd_lsn; /* last modification in log */
uuid_t dd_uuid; /* location information */
-} xfs_dqblk_t;
+};
#define XFS_DQUOT_CRC_OFF offsetof(struct xfs_dqblk, dd_crc)
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index bde2b4c64dbe..c43877c8a279 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -268,6 +268,8 @@ typedef struct xfs_fsop_resblks {
*/
#define XFS_MIN_AG_BYTES (1ULL << 24) /* 16 MB */
#define XFS_MAX_AG_BYTES (1ULL << 40) /* 1 TB */
+#define XFS_MAX_AG_BLOCKS (XFS_MAX_AG_BYTES / XFS_MIN_BLOCKSIZE)
+#define XFS_MAX_CRC_AG_BLOCKS (XFS_MAX_AG_BYTES / XFS_MIN_CRC_BLOCKSIZE)
/* keep the maximum size under 2^31 by a small amount */
#define XFS_MAX_LOG_BYTES \
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 994ad783d407..b418fe0c0679 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1827,7 +1827,7 @@ xfs_difree_inode_chunk(
if (!xfs_inobt_issparse(rec->ir_holemask)) {
/* not sparse, calculate extent info directly */
- xfs_bmap_add_free(tp, XFS_AGB_TO_FSB(mp, agno, sagbno),
+ xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, sagbno),
M_IGEO(mp)->ialloc_blks,
&XFS_RMAP_OINFO_INODES);
return;
@@ -1872,7 +1872,7 @@ xfs_difree_inode_chunk(
ASSERT(agbno % mp->m_sb.sb_spino_align == 0);
ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
- xfs_bmap_add_free(tp, XFS_AGB_TO_FSB(mp, agno, agbno),
+ xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, agbno),
contigblk, &XFS_RMAP_OINFO_INODES);
/* reset range to current bit and carry on... */
@@ -2793,6 +2793,7 @@ xfs_ialloc_setup_geometry(
inodes = (1LL << XFS_INO_AGINO_BITS(mp)) >> XFS_INODES_PER_CHUNK_LOG;
igeo->inobt_maxlevels = xfs_btree_compute_maxlevels(igeo->inobt_mnr,
inodes);
+ ASSERT(igeo->inobt_maxlevels <= xfs_iallocbt_maxlevels_ondisk());
/*
* Set the maximum inode count for this filesystem, being careful not
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 27190840c5d8..b2ad2fdc40f5 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -22,6 +22,8 @@
#include "xfs_rmap.h"
#include "xfs_ag.h"
+static struct kmem_cache *xfs_inobt_cur_cache;
+
STATIC int
xfs_inobt_get_minrecs(
struct xfs_btree_cur *cur,
@@ -432,10 +434,8 @@ xfs_inobt_init_common(
{
struct xfs_btree_cur *cur;
- cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL);
- cur->bc_tp = tp;
- cur->bc_mp = mp;
- cur->bc_btnum = btnum;
+ cur = xfs_btree_alloc_cursor(mp, tp, btnum,
+ M_IGEO(mp)->inobt_maxlevels, xfs_inobt_cur_cache);
if (btnum == XFS_BTNUM_INO) {
cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_ibt_2);
cur->bc_ops = &xfs_inobt_ops;
@@ -444,8 +444,6 @@ xfs_inobt_init_common(
cur->bc_ops = &xfs_finobt_ops;
}
- cur->bc_blocklog = mp->m_sb.sb_blocklog;
-
if (xfs_has_crc(mp))
cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
@@ -530,6 +528,17 @@ xfs_inobt_commit_staged_btree(
}
}
+/* Calculate number of records in an inode btree block. */
+static inline unsigned int
+xfs_inobt_block_maxrecs(
+ unsigned int blocklen,
+ bool leaf)
+{
+ if (leaf)
+ return blocklen / sizeof(xfs_inobt_rec_t);
+ return blocklen / (sizeof(xfs_inobt_key_t) + sizeof(xfs_inobt_ptr_t));
+}
+
/*
* Calculate number of records in an inobt btree block.
*/
@@ -540,10 +549,54 @@ xfs_inobt_maxrecs(
int leaf)
{
blocklen -= XFS_INOBT_BLOCK_LEN(mp);
+ return xfs_inobt_block_maxrecs(blocklen, leaf);
+}
- if (leaf)
- return blocklen / sizeof(xfs_inobt_rec_t);
- return blocklen / (sizeof(xfs_inobt_key_t) + sizeof(xfs_inobt_ptr_t));
+/*
+ * Maximum number of inode btree records per AG. Pretend that we can fill an
+ * entire AG completely full of inodes except for the AG headers.
+ */
+#define XFS_MAX_INODE_RECORDS \
+ ((XFS_MAX_AG_BYTES - (4 * BBSIZE)) / XFS_DINODE_MIN_SIZE) / \
+ XFS_INODES_PER_CHUNK
+
+/* Compute the max possible height for the inode btree. */
+static inline unsigned int
+xfs_inobt_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_inobt_block_maxrecs(blocklen, true) / 2;
+ minrecs[1] = xfs_inobt_block_maxrecs(blocklen, false) / 2;
+
+ return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_INODE_RECORDS);
+}
+
+/* Compute the max possible height for the free inode btree. */
+static inline unsigned int
+xfs_finobt_maxlevels_ondisk(void)
+{
+ unsigned int minrecs[2];
+ unsigned int blocklen;
+
+ blocklen = XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_SBLOCK_CRC_LEN;
+
+ minrecs[0] = xfs_inobt_block_maxrecs(blocklen, true) / 2;
+ minrecs[1] = xfs_inobt_block_maxrecs(blocklen, false) / 2;
+
+ return xfs_btree_compute_maxlevels(minrecs, XFS_MAX_INODE_RECORDS);
+}
+
+/* Compute the max possible height for either inode btree. */
+unsigned int
+xfs_iallocbt_maxlevels_ondisk(void)
+{
+ return max(xfs_inobt_maxlevels_ondisk(),
+ xfs_finobt_maxlevels_ondisk());
}
/*
@@ -761,3 +814,22 @@ xfs_iallocbt_calc_size(
{
return xfs_btree_calc_size(M_IGEO(mp)->inobt_mnr, len);
}
+
+int __init
+xfs_inobt_init_cur_cache(void)
+{
+ xfs_inobt_cur_cache = kmem_cache_create("xfs_inobt_cur",
+ xfs_btree_cur_sizeof(xfs_inobt_maxlevels_ondisk()),
+ 0, 0, NULL);
+
+ if (!xfs_inobt_cur_cache)
+ return -ENOMEM;
+ return 0;
+}
+
+void
+xfs_inobt_destroy_cur_cache(void)
+{
+ kmem_cache_destroy(xfs_inobt_cur_cache);
+ xfs_inobt_cur_cache = NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.h b/fs/xfs/libxfs/xfs_ialloc_btree.h
index 8a322d402e61..26451cb76b98 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.h
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.h
@@ -75,4 +75,9 @@ int xfs_inobt_cur(struct xfs_mount *mp, struct xfs_trans *tp,
void xfs_inobt_commit_staged_btree(struct xfs_btree_cur *cur,
struct xfs_trans *tp, struct xfs_buf *agbp);
+unsigned int xfs_iallocbt_maxlevels_ondisk(void);
+
+int __init xfs_inobt_init_cur_cache(void);
+void xfs_inobt_destroy_cur_cache(void);
+
#endif /* __XFS_IALLOC_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 3932b4ebf903..cae9708c8587 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -51,9 +51,9 @@ xfs_inode_buf_verify(
agno = xfs_daddr_to_agno(mp, xfs_buf_daddr(bp));
ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
for (i = 0; i < ni; i++) {
- int di_ok;
- xfs_dinode_t *dip;
- xfs_agino_t unlinked_ino;
+ struct xfs_dinode *dip;
+ xfs_agino_t unlinked_ino;
+ int di_ok;
dip = xfs_buf_offset(bp, (i << mp->m_sb.sb_inodelog));
unlinked_ino = be32_to_cpu(dip->di_next_unlinked);
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 1d174909f9bd..9149f4f796fc 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -26,7 +26,7 @@
#include "xfs_types.h"
#include "xfs_errortag.h"
-kmem_zone_t *xfs_ifork_zone;
+struct kmem_cache *xfs_ifork_cache;
void
xfs_init_local_fork(
@@ -67,10 +67,10 @@ xfs_init_local_fork(
*/
STATIC int
xfs_iformat_local(
- xfs_inode_t *ip,
- xfs_dinode_t *dip,
- int whichfork,
- int size)
+ struct xfs_inode *ip,
+ struct xfs_dinode *dip,
+ int whichfork,
+ int size)
{
/*
* If the size is unreasonable, then something
@@ -162,8 +162,8 @@ xfs_iformat_extents(
*/
STATIC int
xfs_iformat_btree(
- xfs_inode_t *ip,
- xfs_dinode_t *dip,
+ struct xfs_inode *ip,
+ struct xfs_dinode *dip,
int whichfork)
{
struct xfs_mount *mp = ip->i_mount;
@@ -284,7 +284,7 @@ xfs_ifork_alloc(
{
struct xfs_ifork *ifp;
- ifp = kmem_cache_zalloc(xfs_ifork_zone, GFP_NOFS | __GFP_NOFAIL);
+ ifp = kmem_cache_zalloc(xfs_ifork_cache, GFP_NOFS | __GFP_NOFAIL);
ifp->if_format = format;
ifp->if_nextents = nextents;
return ifp;
@@ -325,7 +325,7 @@ xfs_iformat_attr_fork(
}
if (error) {
- kmem_cache_free(xfs_ifork_zone, ip->i_afp);
+ kmem_cache_free(xfs_ifork_cache, ip->i_afp);
ip->i_afp = NULL;
}
return error;
@@ -580,8 +580,8 @@ xfs_iextents_copy(
*/
void
xfs_iflush_fork(
- xfs_inode_t *ip,
- xfs_dinode_t *dip,
+ struct xfs_inode *ip,
+ struct xfs_dinode *dip,
struct xfs_inode_log_item *iip,
int whichfork)
{
@@ -676,7 +676,7 @@ xfs_ifork_init_cow(
if (ip->i_cowfp)
return;
- ip->i_cowfp = kmem_cache_zalloc(xfs_ifork_zone,
+ ip->i_cowfp = kmem_cache_zalloc(xfs_ifork_cache,
GFP_NOFS | __GFP_NOFAIL);
ip->i_cowfp->if_format = XFS_DINODE_FMT_EXTENTS;
}
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index a6f7897b6887..3d64a3acb0ed 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -221,7 +221,7 @@ static inline bool xfs_iext_peek_prev_extent(struct xfs_ifork *ifp,
xfs_iext_get_extent((ifp), (ext), (got)); \
xfs_iext_next((ifp), (ext)))
-extern struct kmem_zone *xfs_ifork_zone;
+extern struct kmem_cache *xfs_ifork_cache;
extern void xfs_ifork_init_cow(struct xfs_inode *ip);
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index e5d767a7fc5d..327ba25e9e17 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -24,6 +24,8 @@
#include "xfs_rmap.h"
#include "xfs_ag.h"
+struct kmem_cache *xfs_refcount_intent_cache;
+
/* Allowable refcount adjustment amounts. */
enum xfs_refc_adjust_op {
XFS_REFCOUNT_ADJUST_INCREASE = 1,
@@ -916,8 +918,7 @@ xfs_refcount_adjust_extents(
struct xfs_btree_cur *cur,
xfs_agblock_t *agbno,
xfs_extlen_t *aglen,
- enum xfs_refc_adjust_op adj,
- struct xfs_owner_info *oinfo)
+ enum xfs_refc_adjust_op adj)
{
struct xfs_refcount_irec ext, tmp;
int error;
@@ -974,8 +975,8 @@ xfs_refcount_adjust_extents(
fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
cur->bc_ag.pag->pag_agno,
tmp.rc_startblock);
- xfs_bmap_add_free(cur->bc_tp, fsbno,
- tmp.rc_blockcount, oinfo);
+ xfs_free_extent_later(cur->bc_tp, fsbno,
+ tmp.rc_blockcount, NULL);
}
(*agbno) += tmp.rc_blockcount;
@@ -1019,8 +1020,8 @@ xfs_refcount_adjust_extents(
fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
cur->bc_ag.pag->pag_agno,
ext.rc_startblock);
- xfs_bmap_add_free(cur->bc_tp, fsbno, ext.rc_blockcount,
- oinfo);
+ xfs_free_extent_later(cur->bc_tp, fsbno,
+ ext.rc_blockcount, NULL);
}
skip:
@@ -1048,8 +1049,7 @@ xfs_refcount_adjust(
xfs_extlen_t aglen,
xfs_agblock_t *new_agbno,
xfs_extlen_t *new_aglen,
- enum xfs_refc_adjust_op adj,
- struct xfs_owner_info *oinfo)
+ enum xfs_refc_adjust_op adj)
{
bool shape_changed;
int shape_changes = 0;
@@ -1092,8 +1092,7 @@ xfs_refcount_adjust(
cur->bc_ag.refc.shape_changes++;
/* Now that we've taken care of the ends, adjust the middle extents */
- error = xfs_refcount_adjust_extents(cur, new_agbno, new_aglen,
- adj, oinfo);
+ error = xfs_refcount_adjust_extents(cur, new_agbno, new_aglen, adj);
if (error)
goto out_error;
@@ -1188,12 +1187,12 @@ xfs_refcount_finish_one(
switch (type) {
case XFS_REFCOUNT_INCREASE:
error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
- new_len, XFS_REFCOUNT_ADJUST_INCREASE, NULL);
+ new_len, XFS_REFCOUNT_ADJUST_INCREASE);
*new_fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
break;
case XFS_REFCOUNT_DECREASE:
error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
- new_len, XFS_REFCOUNT_ADJUST_DECREASE, NULL);
+ new_len, XFS_REFCOUNT_ADJUST_DECREASE);
*new_fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
break;
case XFS_REFCOUNT_ALLOC_COW:
@@ -1235,8 +1234,8 @@ __xfs_refcount_add(
type, XFS_FSB_TO_AGBNO(tp->t_mountp, startblock),
blockcount);
- ri = kmem_alloc(sizeof(struct xfs_refcount_intent),
- KM_NOFS);
+ ri = kmem_cache_alloc(xfs_refcount_intent_cache,
+ GFP_NOFS | __GFP_NOFAIL);
INIT_LIST_HEAD(&ri->ri_list);
ri->ri_type = type;
ri->ri_startblock = startblock;
@@ -1742,7 +1741,7 @@ xfs_refcount_recover_cow_leftovers(
rr->rr_rrec.rc_blockcount);
/* Free the block. */
- xfs_bmap_add_free(tp, fsb, rr->rr_rrec.rc_blockcount, NULL);
+ xfs_free_extent_later(tp, fsb, rr->rr_rrec.rc_blockcount, NULL);
error = xfs_trans_commit(tp);
if (error)
@@ -1782,3 +1781,20 @@ xfs_refcount_has_record(
return xfs_btree_has_record(cur, &low, &high, exists);
}
+
+int __init
+xfs_refcount_intent_init_cache(void)
+{
+ xfs_refcount_intent_cache = kmem_cache_create("xfs_refc_intent",
+ sizeof(struct xfs_refcount_intent),
+ 0, 0, NULL);
+
+ return xfs_refcount_intent_cache != NULL ? 0 : -ENOMEM;
+}
+
+void
+xfs_refcount_intent_destroy_cache(void)
+{
+ kmem_cache_destroy(xfs_refcount_intent_cache);
+ xfs_refcount_intent_cache = NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index 02cb3aa405be..9eb01edbd89d 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -32,8 +32,8 @@ enum xfs_refcount_intent_type {
struct xfs_refcount_intent {
struct list_head ri_list;
enum xfs_refcount_intent_type ri_type;
- xfs_fsblock_t ri_startblock;
xfs_extlen_t ri_blockcount;
+ xfs_fsblock_t ri_startblock;
};
void xfs_refcount_increase_extent(struct xfs_trans *tp,
@@ -83,4 +83,9 @@ extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec,
extern int xfs_refcount_insert(struct xfs_btree_cur *cur,
struct xfs_refcount_irec *irec, int *stat);
+extern struct kmem_cache *xfs_refcount_intent_cache;
+
+int __init xfs_refcount_intent_init_cache(void);
+void xfs_refcount_intent_destroy_cache(void);
+
#endif /* __XFS_REFCOUNT_H__ */
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 1ef9b99962ab..d14c1720b0fb 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -21,6 +21,8 @@
#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)
@@ -322,11 +324,8 @@ xfs_refcountbt_init_common(
ASSERT(pag->pag_agno < mp->m_sb.sb_agcount);
- cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL);
- cur->bc_tp = tp;
- cur->bc_mp = mp;
- cur->bc_btnum = XFS_BTNUM_REFC;
- cur->bc_blocklog = mp->m_sb.sb_blocklog;
+ 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_flags |= XFS_BTREE_CRC_BLOCKS;
@@ -396,6 +395,18 @@ xfs_refcountbt_commit_staged_btree(
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.
*/
@@ -405,11 +416,22 @@ 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. */
@@ -417,8 +439,14 @@ 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. */
@@ -488,3 +516,22 @@ 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;
+}
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.h b/fs/xfs/libxfs/xfs_refcount_btree.h
index bd9ed9e1e41f..d66b37259bed 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.h
+++ b/fs/xfs/libxfs/xfs_refcount_btree.h
@@ -65,4 +65,9 @@ extern int xfs_refcountbt_calc_reserves(struct xfs_mount *mp,
void xfs_refcountbt_commit_staged_btree(struct xfs_btree_cur *cur,
struct xfs_trans *tp, struct xfs_buf *agbp);
+unsigned int xfs_refcountbt_maxlevels_ondisk(void);
+
+int __init xfs_refcountbt_init_cur_cache(void);
+void xfs_refcountbt_destroy_cur_cache(void);
+
#endif /* __XFS_REFCOUNT_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index f45929b1b94a..cd322174dbff 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -24,6 +24,8 @@
#include "xfs_inode.h"
#include "xfs_ag.h"
+struct kmem_cache *xfs_rmap_intent_cache;
+
/*
* Lookup the first record less than or equal to [bno, len, owner, offset]
* in the btree given by cur.
@@ -2485,7 +2487,7 @@ __xfs_rmap_add(
bmap->br_blockcount,
bmap->br_state);
- ri = kmem_alloc(sizeof(struct xfs_rmap_intent), KM_NOFS);
+ ri = kmem_cache_alloc(xfs_rmap_intent_cache, GFP_NOFS | __GFP_NOFAIL);
INIT_LIST_HEAD(&ri->ri_list);
ri->ri_type = type;
ri->ri_owner = owner;
@@ -2779,3 +2781,20 @@ const struct xfs_owner_info XFS_RMAP_OINFO_REFC = {
const struct xfs_owner_info XFS_RMAP_OINFO_COW = {
.oi_owner = XFS_RMAP_OWN_COW,
};
+
+int __init
+xfs_rmap_intent_init_cache(void)
+{
+ xfs_rmap_intent_cache = kmem_cache_create("xfs_rmap_intent",
+ sizeof(struct xfs_rmap_intent),
+ 0, 0, NULL);
+
+ return xfs_rmap_intent_cache != NULL ? 0 : -ENOMEM;
+}
+
+void
+xfs_rmap_intent_destroy_cache(void)
+{
+ kmem_cache_destroy(xfs_rmap_intent_cache);
+ xfs_rmap_intent_cache = NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index fd67904ed446..b718ebeda372 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -159,8 +159,8 @@ enum xfs_rmap_intent_type {
struct xfs_rmap_intent {
struct list_head ri_list;
enum xfs_rmap_intent_type ri_type;
- uint64_t ri_owner;
int ri_whichfork;
+ uint64_t ri_owner;
struct xfs_bmbt_irec ri_bmap;
};
@@ -215,4 +215,9 @@ extern const struct xfs_owner_info XFS_RMAP_OINFO_INODES;
extern const struct xfs_owner_info XFS_RMAP_OINFO_REFC;
extern const struct xfs_owner_info XFS_RMAP_OINFO_COW;
+extern struct kmem_cache *xfs_rmap_intent_cache;
+
+int __init xfs_rmap_intent_init_cache(void);
+void xfs_rmap_intent_destroy_cache(void);
+
#endif /* __XFS_RMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index b7dbbfb3aeed..69e104d0277f 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -22,6 +22,8 @@
#include "xfs_ag.h"
#include "xfs_ag_resv.h"
+static struct kmem_cache *xfs_rmapbt_cur_cache;
+
/*
* Reverse map btree.
*
@@ -451,13 +453,10 @@ xfs_rmapbt_init_common(
{
struct xfs_btree_cur *cur;
- cur = kmem_cache_zalloc(xfs_btree_cur_zone, GFP_NOFS | __GFP_NOFAIL);
- cur->bc_tp = tp;
- cur->bc_mp = mp;
/* Overlapping btree; 2 keys per pointer. */
- cur->bc_btnum = XFS_BTNUM_RMAP;
+ cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RMAP,
+ mp->m_rmap_maxlevels, xfs_rmapbt_cur_cache);
cur->bc_flags = XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING;
- cur->bc_blocklog = mp->m_sb.sb_blocklog;
cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_rmap_2);
cur->bc_ops = &xfs_rmapbt_ops;
@@ -522,6 +521,18 @@ xfs_rmapbt_commit_staged_btree(
xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_rmapbt_ops);
}
+/* Calculate number of records in a reverse mapping btree block. */
+static inline unsigned int
+xfs_rmapbt_block_maxrecs(
+ unsigned int blocklen,
+ bool leaf)
+{
+ if (leaf)
+ return blocklen / sizeof(struct xfs_rmap_rec);
+ return blocklen /
+ (2 * sizeof(struct xfs_rmap_key) + sizeof(xfs_rmap_ptr_t));
+}
+
/*
* Calculate number of records in an rmap btree block.
*/
@@ -531,11 +542,33 @@ xfs_rmapbt_maxrecs(
int leaf)
{
blocklen -= XFS_RMAP_BLOCK_LEN;
+ return xfs_rmapbt_block_maxrecs(blocklen, leaf);
+}
- if (leaf)
- return blocklen / sizeof(struct xfs_rmap_rec);
- return blocklen /
- (2 * sizeof(struct xfs_rmap_key) + sizeof(xfs_rmap_ptr_t));
+/* Compute the max possible height for reverse mapping btrees. */
+unsigned int
+xfs_rmapbt_maxlevels_ondisk(void)
+{
+ unsigned int minrecs[2];
+ unsigned int blocklen;
+
+ blocklen = XFS_MIN_CRC_BLOCKSIZE - XFS_BTREE_SBLOCK_CRC_LEN;
+
+ minrecs[0] = xfs_rmapbt_block_maxrecs(blocklen, true) / 2;
+ minrecs[1] = xfs_rmapbt_block_maxrecs(blocklen, false) / 2;
+
+ /*
+ * Compute the asymptotic maxlevels for an rmapbt on any reflink fs.
+ *
+ * On a reflink filesystem, each AG block can have up to 2^32 (per the
+ * refcount record format) owners, which means that theoretically we
+ * could face up to 2^64 rmap records. However, we're likely to run
+ * out of blocks in the AG long before that happens, which means that
+ * we must compute the max height based on what the btree will look
+ * like if it consumes almost all the blocks in the AG due to maximal
+ * sharing factor.
+ */
+ return xfs_btree_space_to_height(minrecs, XFS_MAX_CRC_AG_BLOCKS);
}
/* Compute the maximum height of an rmap btree. */
@@ -543,26 +576,36 @@ void
xfs_rmapbt_compute_maxlevels(
struct xfs_mount *mp)
{
- /*
- * On a non-reflink filesystem, the maximum number of rmap
- * records is the number of blocks in the AG, hence the max
- * rmapbt height is log_$maxrecs($agblocks). However, with
- * reflink each AG block can have up to 2^32 (per the refcount
- * record format) owners, which means that theoretically we
- * could face up to 2^64 rmap records.
- *
- * That effectively means that the max rmapbt height must be
- * XFS_BTREE_MAXLEVELS. "Fortunately" we'll run out of AG
- * blocks to feed the rmapbt long before the rmapbt reaches
- * maximum height. The reflink code uses ag_resv_critical to
- * disallow reflinking when less than 10% of the per-AG metadata
- * block reservation since the fallback is a regular file copy.
- */
- if (xfs_has_reflink(mp))
- mp->m_rmap_maxlevels = XFS_BTREE_MAXLEVELS;
- else
+ if (!xfs_has_rmapbt(mp)) {
+ mp->m_rmap_maxlevels = 0;
+ return;
+ }
+
+ if (xfs_has_reflink(mp)) {
+ /*
+ * Compute the asymptotic maxlevels for an rmap btree on a
+ * filesystem that supports reflink.
+ *
+ * On a reflink filesystem, each AG block can have up to 2^32
+ * (per the refcount record format) owners, which means that
+ * theoretically we could face up to 2^64 rmap records.
+ * However, we're likely to run out of blocks in the AG long
+ * before that happens, which means that we must compute the
+ * max height based on what the btree will look like if it
+ * consumes almost all the blocks in the AG due to maximal
+ * sharing factor.
+ */
+ mp->m_rmap_maxlevels = xfs_btree_space_to_height(mp->m_rmap_mnr,
+ mp->m_sb.sb_agblocks);
+ } else {
+ /*
+ * If there's no block sharing, compute the maximum rmapbt
+ * height assuming one rmap record per AG block.
+ */
mp->m_rmap_maxlevels = xfs_btree_compute_maxlevels(
mp->m_rmap_mnr, mp->m_sb.sb_agblocks);
+ }
+ ASSERT(mp->m_rmap_maxlevels <= xfs_rmapbt_maxlevels_ondisk());
}
/* Calculate the refcount btree size for some records. */
@@ -633,3 +676,22 @@ xfs_rmapbt_calc_reserves(
return error;
}
+
+int __init
+xfs_rmapbt_init_cur_cache(void)
+{
+ xfs_rmapbt_cur_cache = kmem_cache_create("xfs_rmapbt_cur",
+ xfs_btree_cur_sizeof(xfs_rmapbt_maxlevels_ondisk()),
+ 0, 0, NULL);
+
+ if (!xfs_rmapbt_cur_cache)
+ return -ENOMEM;
+ return 0;
+}
+
+void
+xfs_rmapbt_destroy_cur_cache(void)
+{
+ kmem_cache_destroy(xfs_rmapbt_cur_cache);
+ xfs_rmapbt_cur_cache = NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.h b/fs/xfs/libxfs/xfs_rmap_btree.h
index f2eee6572af4..3244715dd111 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.h
+++ b/fs/xfs/libxfs/xfs_rmap_btree.h
@@ -59,4 +59,9 @@ extern xfs_extlen_t xfs_rmapbt_max_size(struct xfs_mount *mp,
extern int xfs_rmapbt_calc_reserves(struct xfs_mount *mp, struct xfs_trans *tp,
struct xfs_perag *pag, xfs_extlen_t *ask, xfs_extlen_t *used);
+unsigned int xfs_rmapbt_maxlevels_ondisk(void);
+
+int __init xfs_rmapbt_init_cur_cache(void);
+void xfs_rmapbt_destroy_cur_cache(void);
+
#endif /* __XFS_RMAP_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index e58349be78bd..f4e84aa1d50a 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -495,7 +495,7 @@ xfs_sb_quota_from_disk(struct xfs_sb *sbp)
static void
__xfs_sb_from_disk(
struct xfs_sb *to,
- xfs_dsb_t *from,
+ struct xfs_dsb *from,
bool convert_xquota)
{
to->sb_magicnum = be32_to_cpu(from->sb_magicnum);
@@ -571,7 +571,7 @@ __xfs_sb_from_disk(
void
xfs_sb_from_disk(
struct xfs_sb *to,
- xfs_dsb_t *from)
+ struct xfs_dsb *from)
{
__xfs_sb_from_disk(to, from, true);
}
diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c
index 5e300daa2559..6f83d9b306ee 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.c
+++ b/fs/xfs/libxfs/xfs_trans_resv.c
@@ -70,7 +70,7 @@ xfs_allocfree_log_count(
{
uint blocks;
- blocks = num_ops * 2 * (2 * mp->m_ag_maxlevels - 1);
+ blocks = num_ops * 2 * (2 * mp->m_alloc_maxlevels - 1);
if (xfs_has_rmapbt(mp))
blocks += num_ops * (2 * mp->m_rmap_maxlevels - 1);
if (xfs_has_reflink(mp))
@@ -814,6 +814,19 @@ xfs_trans_resv_calc(
struct xfs_mount *mp,
struct xfs_trans_resv *resp)
{
+ unsigned int rmap_maxlevels = mp->m_rmap_maxlevels;
+
+ /*
+ * In the early days of rmap+reflink, we always set the rmap maxlevels
+ * to 9 even if the AG was small enough that it would never grow to
+ * that height. Transaction reservation sizes influence the minimum
+ * log size calculation, which influences the size of the log that mkfs
+ * creates. Use the old value here to ensure that newly formatted
+ * small filesystems will mount on older kernels.
+ */
+ if (xfs_has_rmapbt(mp) && xfs_has_reflink(mp))
+ mp->m_rmap_maxlevels = XFS_OLD_REFLINK_RMAP_MAXLEVELS;
+
/*
* The following transactions are logged in physical format and
* require a permanent reservation on space.
@@ -916,4 +929,7 @@ xfs_trans_resv_calc(
resp->tr_clearagi.tr_logres = xfs_calc_clear_agi_bucket_reservation(mp);
resp->tr_growrtzero.tr_logres = xfs_calc_growrtzero_reservation(mp);
resp->tr_growrtfree.tr_logres = xfs_calc_growrtfree_reservation(mp);
+
+ /* Put everything back the way it was. This goes at the end. */
+ mp->m_rmap_maxlevels = rmap_maxlevels;
}
diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h
index 50332be34388..87b31c69a773 100644
--- a/fs/xfs/libxfs/xfs_trans_space.h
+++ b/fs/xfs/libxfs/xfs_trans_space.h
@@ -17,6 +17,13 @@
/* Adding one rmap could split every level up to the top of the tree. */
#define XFS_RMAPADD_SPACE_RES(mp) ((mp)->m_rmap_maxlevels)
+/*
+ * Note that we historically set m_rmap_maxlevels to 9 when reflink is enabled,
+ * so we must preserve this behavior to avoid changing the transaction space
+ * reservations and minimum log size calculations for existing filesystems.
+ */
+#define XFS_OLD_REFLINK_RMAP_MAXLEVELS 9
+
/* Blocks we might need to add "b" rmaps to a tree. */
#define XFS_NRMAPADD_SPACE_RES(mp, b)\
(((b + XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp) - 1) / \
@@ -74,7 +81,7 @@
#define XFS_DIOSTRAT_SPACE_RES(mp, v) \
(XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK) + (v))
#define XFS_GROWFS_SPACE_RES(mp) \
- (2 * (mp)->m_ag_maxlevels)
+ (2 * (mp)->m_alloc_maxlevels)
#define XFS_GROWFSRT_SPACE_RES(mp,b) \
((b) + XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK))
#define XFS_LINK_SPACE_RES(mp,nl) \