summaryrefslogtreecommitdiffstats
path: root/fs/xfs/libxfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs/libxfs')
-rw-r--r--fs/xfs/libxfs/xfs_ag.c79
-rw-r--r--fs/xfs/libxfs/xfs_ag.h18
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c258
-rw-r--r--fs/xfs/libxfs/xfs_alloc_btree.c191
-rw-r--r--fs/xfs/libxfs/xfs_alloc_btree.h10
-rw-r--r--fs/xfs/libxfs/xfs_attr.c5
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.c22
-rw-r--r--fs/xfs/libxfs/xfs_attr_remote.c37
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c365
-rw-r--r--fs/xfs/libxfs/xfs_bmap.h19
-rw-r--r--fs/xfs/libxfs/xfs_bmap_btree.c152
-rw-r--r--fs/xfs/libxfs/xfs_bmap_btree.h5
-rw-r--r--fs/xfs/libxfs/xfs_btree.c1078
-rw-r--r--fs/xfs/libxfs/xfs_btree.h274
-rw-r--r--fs/xfs/libxfs/xfs_btree_mem.c347
-rw-r--r--fs/xfs/libxfs/xfs_btree_mem.h75
-rw-r--r--fs/xfs/libxfs/xfs_btree_staging.c133
-rw-r--r--fs/xfs/libxfs/xfs_btree_staging.h10
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.c59
-rw-r--r--fs/xfs/libxfs/xfs_da_format.h11
-rw-r--r--fs/xfs/libxfs/xfs_defer.c25
-rw-r--r--fs/xfs/libxfs/xfs_dir2.c59
-rw-r--r--fs/xfs/libxfs/xfs_dir2.h13
-rw-r--r--fs/xfs/libxfs/xfs_dir2_block.c8
-rw-r--r--fs/xfs/libxfs/xfs_dir2_data.c3
-rw-r--r--fs/xfs/libxfs/xfs_dir2_leaf.c3
-rw-r--r--fs/xfs/libxfs/xfs_dir2_node.c7
-rw-r--r--fs/xfs/libxfs/xfs_dir2_sf.c16
-rw-r--r--fs/xfs/libxfs/xfs_format.h21
-rw-r--r--fs/xfs/libxfs/xfs_fs.h8
-rw-r--r--fs/xfs/libxfs/xfs_health.h95
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.c232
-rw-r--r--fs/xfs/libxfs/xfs_ialloc_btree.c155
-rw-r--r--fs/xfs/libxfs/xfs_ialloc_btree.h11
-rw-r--r--fs/xfs/libxfs/xfs_iext_tree.c26
-rw-r--r--fs/xfs/libxfs/xfs_inode_buf.c12
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.c49
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.h1
-rw-r--r--fs/xfs/libxfs/xfs_log_format.h4
-rw-r--r--fs/xfs/libxfs/xfs_refcount.c69
-rw-r--r--fs/xfs/libxfs/xfs_refcount_btree.c78
-rw-r--r--fs/xfs/libxfs/xfs_refcount_btree.h2
-rw-r--r--fs/xfs/libxfs/xfs_rmap.c284
-rw-r--r--fs/xfs/libxfs/xfs_rmap.h31
-rw-r--r--fs/xfs/libxfs/xfs_rmap_btree.c231
-rw-r--r--fs/xfs/libxfs/xfs_rmap_btree.h8
-rw-r--r--fs/xfs/libxfs/xfs_rtbitmap.c11
-rw-r--r--fs/xfs/libxfs/xfs_sb.c42
-rw-r--r--fs/xfs/libxfs/xfs_sb.h5
-rw-r--r--fs/xfs/libxfs/xfs_shared.h67
-rw-r--r--fs/xfs/libxfs/xfs_symlink_remote.c155
-rw-r--r--fs/xfs/libxfs/xfs_symlink_remote.h26
-rw-r--r--fs/xfs/libxfs/xfs_trans_inode.c6
-rw-r--r--fs/xfs/libxfs/xfs_types.h26
54 files changed, 3253 insertions, 1684 deletions
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 39d9525270..dc1873f76b 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -217,6 +217,7 @@ xfs_initialize_perag_data(
*/
if (fdblocks > sbp->sb_dblocks || ifree > ialloc) {
xfs_alert(mp, "AGF corruption. Please run xfs_repair.");
+ xfs_fs_mark_sick(mp, XFS_SICK_FS_COUNTERS);
error = -EFSCORRUPTED;
goto out;
}
@@ -241,7 +242,7 @@ __xfs_free_perag(
struct xfs_perag *pag = container_of(head, struct xfs_perag, rcu_head);
ASSERT(!delayed_work_pending(&pag->pag_blockgc_work));
- kmem_free(pag);
+ kfree(pag);
}
/*
@@ -263,7 +264,7 @@ xfs_free_perag(
xfs_defer_drain_free(&pag->pag_intents_drain);
cancel_delayed_work_sync(&pag->pag_blockgc_work);
- xfs_buf_hash_destroy(pag);
+ xfs_buf_cache_destroy(&pag->pag_bcache);
/* drop the mount's active reference */
xfs_perag_rele(pag);
@@ -351,9 +352,9 @@ xfs_free_unused_perag_range(
spin_unlock(&mp->m_perag_lock);
if (!pag)
break;
- xfs_buf_hash_destroy(pag);
+ xfs_buf_cache_destroy(&pag->pag_bcache);
xfs_defer_drain_free(&pag->pag_intents_drain);
- kmem_free(pag);
+ kfree(pag);
}
}
@@ -381,7 +382,7 @@ xfs_initialize_perag(
continue;
}
- pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL);
+ pag = kzalloc(sizeof(*pag), GFP_KERNEL | __GFP_RETRY_MAYFAIL);
if (!pag) {
error = -ENOMEM;
goto out_unwind_new_pags;
@@ -389,7 +390,7 @@ xfs_initialize_perag(
pag->pag_agno = index;
pag->pag_mount = mp;
- error = radix_tree_preload(GFP_NOFS);
+ error = radix_tree_preload(GFP_KERNEL | __GFP_RETRY_MAYFAIL);
if (error)
goto out_free_pag;
@@ -416,9 +417,10 @@ xfs_initialize_perag(
init_waitqueue_head(&pag->pag_active_wq);
pag->pagb_count = 0;
pag->pagb_tree = RB_ROOT;
+ xfs_hooks_init(&pag->pag_rmap_update_hooks);
#endif /* __KERNEL__ */
- error = xfs_buf_hash_init(pag);
+ error = xfs_buf_cache_init(&pag->pag_bcache);
if (error)
goto out_remove_pag;
@@ -453,7 +455,7 @@ out_remove_pag:
radix_tree_delete(&mp->m_perag_tree, index);
spin_unlock(&mp->m_perag_lock);
out_free_pag:
- kmem_free(pag);
+ kfree(pag);
out_unwind_new_pags:
/* unwind any prior newly initialized pags */
xfs_free_unused_perag_range(mp, first_initialised, agcount);
@@ -491,7 +493,7 @@ xfs_btroot_init(
struct xfs_buf *bp,
struct aghdr_init_data *id)
{
- xfs_btree_init_block(mp, bp, id->type, 0, 0, id->agno);
+ xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 0, id->agno);
}
/* Finish initializing a free space btree. */
@@ -549,7 +551,7 @@ xfs_freesp_init_recs(
}
/*
- * Alloc btree root block init functions
+ * bnobt/cntbt btree root block init functions
*/
static void
xfs_bnoroot_init(
@@ -557,17 +559,7 @@ xfs_bnoroot_init(
struct xfs_buf *bp,
struct aghdr_init_data *id)
{
- xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 0, id->agno);
- xfs_freesp_init_recs(mp, bp, id);
-}
-
-static void
-xfs_cntroot_init(
- struct xfs_mount *mp,
- struct xfs_buf *bp,
- struct aghdr_init_data *id)
-{
- xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 0, id->agno);
+ xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 0, id->agno);
xfs_freesp_init_recs(mp, bp, id);
}
@@ -583,7 +575,7 @@ xfs_rmaproot_init(
struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
struct xfs_rmap_rec *rrec;
- xfs_btree_init_block(mp, bp, XFS_BTNUM_RMAP, 0, 4, id->agno);
+ xfs_btree_init_buf(mp, bp, id->bc_ops, 0, 4, id->agno);
/*
* mark the AG header regions as static metadata The BNO
@@ -678,14 +670,13 @@ xfs_agfblock_init(
agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
agf->agf_seqno = cpu_to_be32(id->agno);
agf->agf_length = cpu_to_be32(id->agsize);
- agf->agf_roots[XFS_BTNUM_BNOi] = cpu_to_be32(XFS_BNO_BLOCK(mp));
- agf->agf_roots[XFS_BTNUM_CNTi] = cpu_to_be32(XFS_CNT_BLOCK(mp));
- agf->agf_levels[XFS_BTNUM_BNOi] = cpu_to_be32(1);
- agf->agf_levels[XFS_BTNUM_CNTi] = cpu_to_be32(1);
+ agf->agf_bno_root = cpu_to_be32(XFS_BNO_BLOCK(mp));
+ agf->agf_cnt_root = cpu_to_be32(XFS_CNT_BLOCK(mp));
+ agf->agf_bno_level = cpu_to_be32(1);
+ agf->agf_cnt_level = cpu_to_be32(1);
if (xfs_has_rmapbt(mp)) {
- agf->agf_roots[XFS_BTNUM_RMAPi] =
- cpu_to_be32(XFS_RMAP_BLOCK(mp));
- agf->agf_levels[XFS_BTNUM_RMAPi] = cpu_to_be32(1);
+ agf->agf_rmap_root = cpu_to_be32(XFS_RMAP_BLOCK(mp));
+ agf->agf_rmap_level = cpu_to_be32(1);
agf->agf_rmap_blocks = cpu_to_be32(1);
}
@@ -796,7 +787,7 @@ struct xfs_aghdr_grow_data {
size_t numblks;
const struct xfs_buf_ops *ops;
aghdr_init_work_f work;
- xfs_btnum_t type;
+ const struct xfs_btree_ops *bc_ops;
bool need_init;
};
@@ -850,13 +841,15 @@ xfs_ag_init_headers(
.numblks = BTOBB(mp->m_sb.sb_blocksize),
.ops = &xfs_bnobt_buf_ops,
.work = &xfs_bnoroot_init,
+ .bc_ops = &xfs_bnobt_ops,
.need_init = true
},
{ /* CNT root block */
.daddr = XFS_AGB_TO_DADDR(mp, id->agno, XFS_CNT_BLOCK(mp)),
.numblks = BTOBB(mp->m_sb.sb_blocksize),
.ops = &xfs_cntbt_buf_ops,
- .work = &xfs_cntroot_init,
+ .work = &xfs_bnoroot_init,
+ .bc_ops = &xfs_cntbt_ops,
.need_init = true
},
{ /* INO root block */
@@ -864,7 +857,7 @@ xfs_ag_init_headers(
.numblks = BTOBB(mp->m_sb.sb_blocksize),
.ops = &xfs_inobt_buf_ops,
.work = &xfs_btroot_init,
- .type = XFS_BTNUM_INO,
+ .bc_ops = &xfs_inobt_ops,
.need_init = true
},
{ /* FINO root block */
@@ -872,7 +865,7 @@ xfs_ag_init_headers(
.numblks = BTOBB(mp->m_sb.sb_blocksize),
.ops = &xfs_finobt_buf_ops,
.work = &xfs_btroot_init,
- .type = XFS_BTNUM_FINO,
+ .bc_ops = &xfs_finobt_ops,
.need_init = xfs_has_finobt(mp)
},
{ /* RMAP root block */
@@ -880,6 +873,7 @@ xfs_ag_init_headers(
.numblks = BTOBB(mp->m_sb.sb_blocksize),
.ops = &xfs_rmapbt_buf_ops,
.work = &xfs_rmaproot_init,
+ .bc_ops = &xfs_rmapbt_ops,
.need_init = xfs_has_rmapbt(mp)
},
{ /* REFC root block */
@@ -887,7 +881,7 @@ xfs_ag_init_headers(
.numblks = BTOBB(mp->m_sb.sb_blocksize),
.ops = &xfs_refcountbt_buf_ops,
.work = &xfs_btroot_init,
- .type = XFS_BTNUM_REFC,
+ .bc_ops = &xfs_refcountbt_ops,
.need_init = xfs_has_reflink(mp)
},
{ /* NULL terminating block */
@@ -905,7 +899,7 @@ xfs_ag_init_headers(
id->daddr = dp->daddr;
id->numblks = dp->numblks;
- id->type = dp->type;
+ id->bc_ops = dp->bc_ops;
error = xfs_ag_init_hdr(mp, id, dp->work, dp->ops);
if (error)
break;
@@ -950,8 +944,10 @@ xfs_ag_shrink_space(
agf = agfbp->b_addr;
aglen = be32_to_cpu(agi->agi_length);
/* some extra paranoid checks before we shrink the ag */
- if (XFS_IS_CORRUPT(mp, agf->agf_length != agi->agi_length))
+ if (XFS_IS_CORRUPT(mp, agf->agf_length != agi->agi_length)) {
+ xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF);
return -EFSCORRUPTED;
+ }
if (delta >= aglen)
return -EINVAL;
@@ -979,14 +975,23 @@ xfs_ag_shrink_space(
if (error) {
/*
- * if extent allocation fails, need to roll the transaction to
+ * If extent allocation fails, need to roll the transaction to
* ensure that the AGFL fixup has been committed anyway.
+ *
+ * We need to hold the AGF across the roll to ensure nothing can
+ * access the AG for allocation until the shrink is fully
+ * cleaned up. And due to the resetting of the AG block
+ * reservation space needing to lock the AGI, we also have to
+ * hold that so we don't get AGI/AGF lock order inversions in
+ * the error handling path.
*/
xfs_trans_bhold(*tpp, agfbp);
+ xfs_trans_bhold(*tpp, agibp);
err2 = xfs_trans_roll(tpp);
if (err2)
return err2;
xfs_trans_bjoin(*tpp, agfbp);
+ xfs_trans_bjoin(*tpp, agibp);
goto resv_init_out;
}
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 4b343c4fac..35de09a251 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -36,8 +36,9 @@ struct xfs_perag {
atomic_t pag_active_ref; /* active reference count */
wait_queue_head_t pag_active_wq;/* woken active_ref falls to zero */
unsigned long pag_opstate;
- uint8_t pagf_levels[XFS_BTNUM_AGF];
- /* # of levels in bno & cnt btree */
+ uint8_t pagf_bno_level; /* # of levels in bno btree */
+ uint8_t pagf_cnt_level; /* # of levels in cnt btree */
+ uint8_t pagf_rmap_level;/* # of levels in rmap btree */
uint32_t pagf_flcount; /* count of blocks in freelist */
xfs_extlen_t pagf_freeblks; /* total free blocks */
xfs_extlen_t pagf_longest; /* longest free space */
@@ -86,8 +87,10 @@ struct xfs_perag {
* Alternate btree heights so that online repair won't trip the write
* verifiers while rebuilding the AG btrees.
*/
- uint8_t pagf_repair_levels[XFS_BTNUM_AGF];
+ uint8_t pagf_repair_bno_level;
+ uint8_t pagf_repair_cnt_level;
uint8_t pagf_repair_refcount_level;
+ uint8_t pagf_repair_rmap_level;
#endif
spinlock_t pag_state_lock;
@@ -104,9 +107,7 @@ struct xfs_perag {
int pag_ici_reclaimable; /* reclaimable inodes */
unsigned long pag_ici_reclaim_cursor; /* reclaim restart point */
- /* buffer cache index */
- spinlock_t pag_buf_lock; /* lock for pag_buf_hash */
- struct rhashtable pag_buf_hash;
+ struct xfs_buf_cache pag_bcache;
/* background prealloc block trimming */
struct delayed_work pag_blockgc_work;
@@ -119,6 +120,9 @@ struct xfs_perag {
* inconsistencies.
*/
struct xfs_defer_drain pag_intents_drain;
+
+ /* Hook to feed rmapbt updates to an active online repair. */
+ struct xfs_hooks pag_rmap_update_hooks;
#endif /* __KERNEL__ */
};
@@ -331,7 +335,7 @@ struct aghdr_init_data {
/* per header data */
xfs_daddr_t daddr; /* header location */
size_t numblks; /* size of header */
- xfs_btnum_t type; /* type of btree root block */
+ const struct xfs_btree_ops *bc_ops; /* btree ops */
};
int xfs_ag_init_headers(struct xfs_mount *mp, struct aghdr_init_data *id);
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 3bd0a33fee..9da52e9217 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -26,6 +26,7 @@
#include "xfs_ag.h"
#include "xfs_ag_resv.h"
#include "xfs_bmap.h"
+#include "xfs_health.h"
struct kmem_cache *xfs_extfree_item_cache;
@@ -150,23 +151,38 @@ xfs_alloc_ag_max_usable(
return mp->m_sb.sb_agblocks - blocks;
}
+
+static int
+xfs_alloc_lookup(
+ struct xfs_btree_cur *cur,
+ xfs_lookup_t dir,
+ xfs_agblock_t bno,
+ xfs_extlen_t len,
+ int *stat)
+{
+ int error;
+
+ cur->bc_rec.a.ar_startblock = bno;
+ cur->bc_rec.a.ar_blockcount = len;
+ error = xfs_btree_lookup(cur, dir, stat);
+ if (*stat == 1)
+ cur->bc_flags |= XFS_BTREE_ALLOCBT_ACTIVE;
+ else
+ cur->bc_flags &= ~XFS_BTREE_ALLOCBT_ACTIVE;
+ return error;
+}
+
/*
* Lookup the record equal to [bno, len] in the btree given by cur.
*/
-STATIC int /* error */
+static inline int /* error */
xfs_alloc_lookup_eq(
struct xfs_btree_cur *cur, /* btree cursor */
xfs_agblock_t bno, /* starting block of extent */
xfs_extlen_t len, /* length of extent */
int *stat) /* success/failure */
{
- int error;
-
- cur->bc_rec.a.ar_startblock = bno;
- cur->bc_rec.a.ar_blockcount = len;
- error = xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat);
- cur->bc_ag.abt.active = (*stat == 1);
- return error;
+ return xfs_alloc_lookup(cur, XFS_LOOKUP_EQ, bno, len, stat);
}
/*
@@ -180,13 +196,7 @@ xfs_alloc_lookup_ge(
xfs_extlen_t len, /* length of extent */
int *stat) /* success/failure */
{
- int error;
-
- cur->bc_rec.a.ar_startblock = bno;
- cur->bc_rec.a.ar_blockcount = len;
- error = xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat);
- cur->bc_ag.abt.active = (*stat == 1);
- return error;
+ return xfs_alloc_lookup(cur, XFS_LOOKUP_GE, bno, len, stat);
}
/*
@@ -200,19 +210,14 @@ xfs_alloc_lookup_le(
xfs_extlen_t len, /* length of extent */
int *stat) /* success/failure */
{
- int error;
- cur->bc_rec.a.ar_startblock = bno;
- cur->bc_rec.a.ar_blockcount = len;
- error = xfs_btree_lookup(cur, XFS_LOOKUP_LE, stat);
- cur->bc_ag.abt.active = (*stat == 1);
- return error;
+ return xfs_alloc_lookup(cur, XFS_LOOKUP_LE, bno, len, stat);
}
static inline bool
xfs_alloc_cur_active(
struct xfs_btree_cur *cur)
{
- return cur && cur->bc_ag.abt.active;
+ return cur && (cur->bc_flags & XFS_BTREE_ALLOCBT_ACTIVE);
}
/*
@@ -268,12 +273,12 @@ xfs_alloc_complain_bad_rec(
struct xfs_mount *mp = cur->bc_mp;
xfs_warn(mp,
- "%s Freespace BTree record corruption in AG %d detected at %pS!",
- cur->bc_btnum == XFS_BTNUM_BNO ? "Block" : "Size",
- cur->bc_ag.pag->pag_agno, fa);
+ "%sbt record corruption in AG %d detected at %pS!",
+ cur->bc_ops->name, cur->bc_ag.pag->pag_agno, fa);
xfs_warn(mp,
"start block 0x%x block count 0x%x", irec->ar_startblock,
irec->ar_blockcount);
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
}
@@ -497,14 +502,18 @@ xfs_alloc_fixup_trees(
if (XFS_IS_CORRUPT(mp,
i != 1 ||
nfbno1 != fbno ||
- nflen1 != flen))
+ nflen1 != flen)) {
+ xfs_btree_mark_sick(cnt_cur);
return -EFSCORRUPTED;
+ }
#endif
} else {
if ((error = xfs_alloc_lookup_eq(cnt_cur, fbno, flen, &i)))
return error;
- if (XFS_IS_CORRUPT(mp, i != 1))
+ if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cnt_cur);
return -EFSCORRUPTED;
+ }
}
/*
* Look up the record in the by-block tree if necessary.
@@ -516,14 +525,18 @@ xfs_alloc_fixup_trees(
if (XFS_IS_CORRUPT(mp,
i != 1 ||
nfbno1 != fbno ||
- nflen1 != flen))
+ nflen1 != flen)) {
+ xfs_btree_mark_sick(bno_cur);
return -EFSCORRUPTED;
+ }
#endif
} else {
if ((error = xfs_alloc_lookup_eq(bno_cur, fbno, flen, &i)))
return error;
- if (XFS_IS_CORRUPT(mp, i != 1))
+ if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bno_cur);
return -EFSCORRUPTED;
+ }
}
#ifdef DEBUG
@@ -536,8 +549,10 @@ xfs_alloc_fixup_trees(
if (XFS_IS_CORRUPT(mp,
bnoblock->bb_numrecs !=
- cntblock->bb_numrecs))
+ cntblock->bb_numrecs)) {
+ xfs_btree_mark_sick(bno_cur);
return -EFSCORRUPTED;
+ }
}
#endif
@@ -567,30 +582,40 @@ xfs_alloc_fixup_trees(
*/
if ((error = xfs_btree_delete(cnt_cur, &i)))
return error;
- if (XFS_IS_CORRUPT(mp, i != 1))
+ if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cnt_cur);
return -EFSCORRUPTED;
+ }
/*
* Add new by-size btree entry(s).
*/
if (nfbno1 != NULLAGBLOCK) {
if ((error = xfs_alloc_lookup_eq(cnt_cur, nfbno1, nflen1, &i)))
return error;
- if (XFS_IS_CORRUPT(mp, i != 0))
+ if (XFS_IS_CORRUPT(mp, i != 0)) {
+ xfs_btree_mark_sick(cnt_cur);
return -EFSCORRUPTED;
+ }
if ((error = xfs_btree_insert(cnt_cur, &i)))
return error;
- if (XFS_IS_CORRUPT(mp, i != 1))
+ if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cnt_cur);
return -EFSCORRUPTED;
+ }
}
if (nfbno2 != NULLAGBLOCK) {
if ((error = xfs_alloc_lookup_eq(cnt_cur, nfbno2, nflen2, &i)))
return error;
- if (XFS_IS_CORRUPT(mp, i != 0))
+ if (XFS_IS_CORRUPT(mp, i != 0)) {
+ xfs_btree_mark_sick(cnt_cur);
return -EFSCORRUPTED;
+ }
if ((error = xfs_btree_insert(cnt_cur, &i)))
return error;
- if (XFS_IS_CORRUPT(mp, i != 1))
+ if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cnt_cur);
return -EFSCORRUPTED;
+ }
}
/*
* Fix up the by-block btree entry(s).
@@ -601,8 +626,10 @@ xfs_alloc_fixup_trees(
*/
if ((error = xfs_btree_delete(bno_cur, &i)))
return error;
- if (XFS_IS_CORRUPT(mp, i != 1))
+ if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bno_cur);
return -EFSCORRUPTED;
+ }
} else {
/*
* Update the by-block entry to start later|be shorter.
@@ -616,12 +643,16 @@ xfs_alloc_fixup_trees(
*/
if ((error = xfs_alloc_lookup_eq(bno_cur, nfbno2, nflen2, &i)))
return error;
- if (XFS_IS_CORRUPT(mp, i != 0))
+ if (XFS_IS_CORRUPT(mp, i != 0)) {
+ xfs_btree_mark_sick(bno_cur);
return -EFSCORRUPTED;
+ }
if ((error = xfs_btree_insert(bno_cur, &i)))
return error;
- if (XFS_IS_CORRUPT(mp, i != 1))
+ if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bno_cur);
return -EFSCORRUPTED;
+ }
}
return 0;
}
@@ -755,6 +786,8 @@ xfs_alloc_read_agfl(
mp, tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGFL_DADDR(mp)),
XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_agfl_buf_ops);
+ if (xfs_metadata_is_sick(error))
+ xfs_ag_mark_sick(pag, XFS_SICK_AG_AGFL);
if (error)
return error;
xfs_buf_set_ref(bp, XFS_AGFL_REF);
@@ -776,6 +809,7 @@ xfs_alloc_update_counters(
if (unlikely(be32_to_cpu(agf->agf_freeblks) >
be32_to_cpu(agf->agf_length))) {
xfs_buf_mark_corrupt(agbp);
+ xfs_ag_mark_sick(agbp->b_pag, XFS_SICK_AG_AGF);
return -EFSCORRUPTED;
}
@@ -828,8 +862,8 @@ xfs_alloc_cur_setup(
* attempt a small allocation.
*/
if (!acur->cnt)
- acur->cnt = xfs_allocbt_init_cursor(args->mp, args->tp,
- args->agbp, args->pag, XFS_BTNUM_CNT);
+ acur->cnt = xfs_cntbt_init_cursor(args->mp, args->tp,
+ args->agbp, args->pag);
error = xfs_alloc_lookup_ge(acur->cnt, 0, args->maxlen, &i);
if (error)
return error;
@@ -838,11 +872,11 @@ xfs_alloc_cur_setup(
* Allocate the bnobt left and right search cursors.
*/
if (!acur->bnolt)
- acur->bnolt = xfs_allocbt_init_cursor(args->mp, args->tp,
- args->agbp, args->pag, XFS_BTNUM_BNO);
+ acur->bnolt = xfs_bnobt_init_cursor(args->mp, args->tp,
+ args->agbp, args->pag);
if (!acur->bnogt)
- acur->bnogt = xfs_allocbt_init_cursor(args->mp, args->tp,
- args->agbp, args->pag, XFS_BTNUM_BNO);
+ acur->bnogt = xfs_bnobt_init_cursor(args->mp, args->tp,
+ args->agbp, args->pag);
return i == 1 ? 0 : -ENOSPC;
}
@@ -884,15 +918,17 @@ xfs_alloc_cur_check(
bool busy;
unsigned busy_gen = 0;
bool deactivate = false;
- bool isbnobt = cur->bc_btnum == XFS_BTNUM_BNO;
+ bool isbnobt = xfs_btree_is_bno(cur->bc_ops);
*new = 0;
error = xfs_alloc_get_rec(cur, &bno, &len, &i);
if (error)
return error;
- if (XFS_IS_CORRUPT(args->mp, i != 1))
+ if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
/*
* Check minlen and deactivate a cntbt cursor if out of acceptable size
@@ -958,9 +994,8 @@ xfs_alloc_cur_check(
deactivate = true;
out:
if (deactivate)
- cur->bc_ag.abt.active = false;
- trace_xfs_alloc_cur_check(args->mp, cur->bc_btnum, bno, len, diff,
- *new);
+ cur->bc_flags &= ~XFS_BTREE_ALLOCBT_ACTIVE;
+ trace_xfs_alloc_cur_check(cur, bno, len, diff, *new);
return 0;
}
@@ -1098,6 +1133,7 @@ xfs_alloc_ag_vextent_small(
if (error)
goto error;
if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+ xfs_btree_mark_sick(ccur);
error = -EFSCORRUPTED;
goto error;
}
@@ -1132,6 +1168,7 @@ xfs_alloc_ag_vextent_small(
*fbnop = args->agbno = fbno;
*flenp = args->len = 1;
if (XFS_IS_CORRUPT(args->mp, fbno >= be32_to_cpu(agf->agf_length))) {
+ xfs_btree_mark_sick(ccur);
error = -EFSCORRUPTED;
goto error;
}
@@ -1197,8 +1234,8 @@ xfs_alloc_ag_vextent_exact(
/*
* Allocate/initialize a cursor for the by-number freespace btree.
*/
- bno_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp,
- args->pag, XFS_BTNUM_BNO);
+ bno_cur = xfs_bnobt_init_cursor(args->mp, args->tp, args->agbp,
+ args->pag);
/*
* Lookup bno and minlen in the btree (minlen is irrelevant, really).
@@ -1218,6 +1255,7 @@ xfs_alloc_ag_vextent_exact(
if (error)
goto error0;
if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+ xfs_btree_mark_sick(bno_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1257,8 +1295,8 @@ xfs_alloc_ag_vextent_exact(
* We are allocating agbno for args->len
* Allocate/initialize a cursor for the by-size btree.
*/
- cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp,
- args->pag, XFS_BTNUM_CNT);
+ cnt_cur = xfs_cntbt_init_cursor(args->mp, args->tp, args->agbp,
+ args->pag);
ASSERT(args->agbno + args->len <= be32_to_cpu(agf->agf_length));
error = xfs_alloc_fixup_trees(cnt_cur, bno_cur, fbno, flen, args->agbno,
args->len, XFSA_FIXUP_BNO_OK);
@@ -1330,7 +1368,7 @@ xfs_alloc_walk_iter(
if (error)
return error;
if (i == 0)
- cur->bc_ag.abt.active = false;
+ cur->bc_flags &= ~XFS_BTREE_ALLOCBT_ACTIVE;
if (count > 0)
count--;
@@ -1444,7 +1482,7 @@ xfs_alloc_ag_vextent_locality(
if (error)
return error;
if (i) {
- acur->cnt->bc_ag.abt.active = true;
+ acur->cnt->bc_flags |= XFS_BTREE_ALLOCBT_ACTIVE;
fbcur = acur->cnt;
fbinc = false;
}
@@ -1497,8 +1535,10 @@ xfs_alloc_ag_vextent_lastblock(
error = xfs_alloc_get_rec(acur->cnt, bno, len, &i);
if (error)
return error;
- if (XFS_IS_CORRUPT(args->mp, i != 1))
+ if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+ xfs_btree_mark_sick(acur->cnt);
return -EFSCORRUPTED;
+ }
if (*len >= args->minlen)
break;
error = xfs_btree_increment(acur->cnt, 0, &i);
@@ -1670,8 +1710,8 @@ restart:
/*
* Allocate and initialize a cursor for the by-size btree.
*/
- cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp,
- args->pag, XFS_BTNUM_CNT);
+ cnt_cur = xfs_cntbt_init_cursor(args->mp, args->tp, args->agbp,
+ args->pag);
bno_cur = NULL;
/*
@@ -1710,6 +1750,7 @@ restart:
if (error)
goto error0;
if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+ xfs_btree_mark_sick(cnt_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1756,6 +1797,7 @@ restart:
rlen != 0 &&
(rlen > flen ||
rbno + rlen > fbno + flen))) {
+ xfs_btree_mark_sick(cnt_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1778,6 +1820,7 @@ restart:
&i)))
goto error0;
if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+ xfs_btree_mark_sick(cnt_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1790,6 +1833,7 @@ restart:
rlen != 0 &&
(rlen > flen ||
rbno + rlen > fbno + flen))) {
+ xfs_btree_mark_sick(cnt_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1806,6 +1850,7 @@ restart:
&i)))
goto error0;
if (XFS_IS_CORRUPT(args->mp, i != 1)) {
+ xfs_btree_mark_sick(cnt_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1844,14 +1889,15 @@ restart:
rlen = args->len;
if (XFS_IS_CORRUPT(args->mp, rlen > flen)) {
+ xfs_btree_mark_sick(cnt_cur);
error = -EFSCORRUPTED;
goto error0;
}
/*
* Allocate and initialize a cursor for the by-block tree.
*/
- bno_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp,
- args->pag, XFS_BTNUM_BNO);
+ bno_cur = xfs_bnobt_init_cursor(args->mp, args->tp, args->agbp,
+ args->pag);
if ((error = xfs_alloc_fixup_trees(cnt_cur, bno_cur, fbno, flen,
rbno, rlen, XFSA_FIXUP_CNT_OK)))
goto error0;
@@ -1863,6 +1909,7 @@ restart:
if (XFS_IS_CORRUPT(args->mp,
args->agbno + args->len >
be32_to_cpu(agf->agf_length))) {
+ xfs_ag_mark_sick(args->pag, XFS_SICK_AG_BNOBT);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1924,7 +1971,7 @@ xfs_free_ag_extent(
/*
* Allocate and initialize a cursor for the by-block btree.
*/
- bno_cur = xfs_allocbt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_BNO);
+ bno_cur = xfs_bnobt_init_cursor(mp, tp, agbp, pag);
/*
* Look for a neighboring block on the left (lower block numbers)
* that is contiguous with this space.
@@ -1938,6 +1985,7 @@ xfs_free_ag_extent(
if ((error = xfs_alloc_get_rec(bno_cur, &ltbno, &ltlen, &i)))
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bno_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1953,6 +2001,7 @@ xfs_free_ag_extent(
* Very bad.
*/
if (XFS_IS_CORRUPT(mp, ltbno + ltlen > bno)) {
+ xfs_btree_mark_sick(bno_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1971,6 +2020,7 @@ xfs_free_ag_extent(
if ((error = xfs_alloc_get_rec(bno_cur, &gtbno, &gtlen, &i)))
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bno_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1986,6 +2036,7 @@ xfs_free_ag_extent(
* Very bad.
*/
if (XFS_IS_CORRUPT(mp, bno + len > gtbno)) {
+ xfs_btree_mark_sick(bno_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1994,7 +2045,7 @@ xfs_free_ag_extent(
/*
* Now allocate and initialize a cursor for the by-size tree.
*/
- cnt_cur = xfs_allocbt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_CNT);
+ cnt_cur = xfs_cntbt_init_cursor(mp, tp, agbp, pag);
/*
* Have both left and right contiguous neighbors.
* Merge all three into a single free block.
@@ -2006,12 +2057,14 @@ xfs_free_ag_extent(
if ((error = xfs_alloc_lookup_eq(cnt_cur, ltbno, ltlen, &i)))
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cnt_cur);
error = -EFSCORRUPTED;
goto error0;
}
if ((error = xfs_btree_delete(cnt_cur, &i)))
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cnt_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -2021,12 +2074,14 @@ xfs_free_ag_extent(
if ((error = xfs_alloc_lookup_eq(cnt_cur, gtbno, gtlen, &i)))
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cnt_cur);
error = -EFSCORRUPTED;
goto error0;
}
if ((error = xfs_btree_delete(cnt_cur, &i)))
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cnt_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -2036,6 +2091,7 @@ xfs_free_ag_extent(
if ((error = xfs_btree_delete(bno_cur, &i)))
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bno_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -2045,6 +2101,7 @@ xfs_free_ag_extent(
if ((error = xfs_btree_decrement(bno_cur, 0, &i)))
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bno_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -2064,6 +2121,7 @@ xfs_free_ag_extent(
i != 1 ||
xxbno != ltbno ||
xxlen != ltlen)) {
+ xfs_btree_mark_sick(bno_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -2088,12 +2146,14 @@ xfs_free_ag_extent(
if ((error = xfs_alloc_lookup_eq(cnt_cur, ltbno, ltlen, &i)))
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cnt_cur);
error = -EFSCORRUPTED;
goto error0;
}
if ((error = xfs_btree_delete(cnt_cur, &i)))
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cnt_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -2104,6 +2164,7 @@ xfs_free_ag_extent(
if ((error = xfs_btree_decrement(bno_cur, 0, &i)))
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bno_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -2123,12 +2184,14 @@ xfs_free_ag_extent(
if ((error = xfs_alloc_lookup_eq(cnt_cur, gtbno, gtlen, &i)))
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cnt_cur);
error = -EFSCORRUPTED;
goto error0;
}
if ((error = xfs_btree_delete(cnt_cur, &i)))
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cnt_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -2151,6 +2214,7 @@ xfs_free_ag_extent(
if ((error = xfs_btree_insert(bno_cur, &i)))
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bno_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -2163,12 +2227,14 @@ xfs_free_ag_extent(
if ((error = xfs_alloc_lookup_eq(cnt_cur, nbno, nlen, &i)))
goto error0;
if (XFS_IS_CORRUPT(mp, i != 0)) {
+ xfs_btree_mark_sick(cnt_cur);
error = -EFSCORRUPTED;
goto error0;
}
if ((error = xfs_btree_insert(cnt_cur, &i)))
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cnt_cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -2267,8 +2333,9 @@ xfs_alloc_min_freelist(
struct xfs_perag *pag)
{
/* AG btrees have at least 1 level. */
- static const uint8_t fake_levels[XFS_BTNUM_AGF] = {1, 1, 1};
- const uint8_t *levels = pag ? pag->pagf_levels : fake_levels;
+ const unsigned int bno_level = pag ? pag->pagf_bno_level : 1;
+ const unsigned int cnt_level = pag ? pag->pagf_cnt_level : 1;
+ const unsigned int rmap_level = pag ? pag->pagf_rmap_level : 1;
unsigned int min_free;
ASSERT(mp->m_alloc_maxlevels > 0);
@@ -2295,16 +2362,12 @@ xfs_alloc_min_freelist(
*/
/* space needed by-bno freespace btree */
- min_free = min_t(unsigned int, levels[XFS_BTNUM_BNOi] + 1,
- mp->m_alloc_maxlevels) * 2 - 2;
+ min_free = min(bno_level + 1, mp->m_alloc_maxlevels) * 2 - 2;
/* space needed by-size freespace btree */
- min_free += min_t(unsigned int, levels[XFS_BTNUM_CNTi] + 1,
- mp->m_alloc_maxlevels) * 2 - 2;
+ min_free += min(cnt_level + 1, mp->m_alloc_maxlevels) * 2 - 2;
/* space needed reverse mapping used space btree */
if (xfs_has_rmapbt(mp))
- min_free += min_t(unsigned int, levels[XFS_BTNUM_RMAPi] + 1,
- mp->m_rmap_maxlevels) * 2 - 2;
-
+ min_free += min(rmap_level + 1, mp->m_rmap_maxlevels) * 2 - 2;
return min_free;
}
@@ -2691,13 +2754,14 @@ xfs_exact_minlen_extent_available(
xfs_extlen_t flen;
int error = 0;
- cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, agbp,
- args->pag, XFS_BTNUM_CNT);
+ cnt_cur = xfs_cntbt_init_cursor(args->mp, args->tp, agbp,
+ args->pag);
error = xfs_alloc_lookup_ge(cnt_cur, 0, args->minlen, stat);
if (error)
goto out;
if (*stat == 0) {
+ xfs_btree_mark_sick(cnt_cur);
error = -EFSCORRUPTED;
goto out;
}
@@ -2987,8 +3051,8 @@ xfs_alloc_log_agf(
offsetof(xfs_agf_t, agf_versionnum),
offsetof(xfs_agf_t, agf_seqno),
offsetof(xfs_agf_t, agf_length),
- offsetof(xfs_agf_t, agf_roots[0]),
- offsetof(xfs_agf_t, agf_levels[0]),
+ offsetof(xfs_agf_t, agf_bno_root), /* also cnt/rmap root */
+ offsetof(xfs_agf_t, agf_bno_level), /* also cnt/rmap levels */
offsetof(xfs_agf_t, agf_flfirst),
offsetof(xfs_agf_t, agf_fllast),
offsetof(xfs_agf_t, agf_flcount),
@@ -3167,12 +3231,10 @@ xfs_agf_verify(
be32_to_cpu(agf->agf_freeblks) > agf_length)
return __this_address;
- 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_alloc_maxlevels ||
- be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) >
- mp->m_alloc_maxlevels)
+ if (be32_to_cpu(agf->agf_bno_level) < 1 ||
+ be32_to_cpu(agf->agf_cnt_level) < 1 ||
+ be32_to_cpu(agf->agf_bno_level) > mp->m_alloc_maxlevels ||
+ be32_to_cpu(agf->agf_cnt_level) > mp->m_alloc_maxlevels)
return __this_address;
if (xfs_has_lazysbcount(mp) &&
@@ -3183,9 +3245,8 @@ xfs_agf_verify(
if (be32_to_cpu(agf->agf_rmap_blocks) > agf_length)
return __this_address;
- if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) < 1 ||
- be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) >
- mp->m_rmap_maxlevels)
+ if (be32_to_cpu(agf->agf_rmap_level) < 1 ||
+ be32_to_cpu(agf->agf_rmap_level) > mp->m_rmap_maxlevels)
return __this_address;
}
@@ -3268,6 +3329,8 @@ xfs_read_agf(
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGF_DADDR(mp)),
XFS_FSS_TO_BB(mp, 1), flags, agfbpp, &xfs_agf_buf_ops);
+ if (xfs_metadata_is_sick(error))
+ xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF);
if (error)
return error;
@@ -3309,12 +3372,9 @@ xfs_alloc_read_agf(
pag->pagf_btreeblks = be32_to_cpu(agf->agf_btreeblks);
pag->pagf_flcount = be32_to_cpu(agf->agf_flcount);
pag->pagf_longest = be32_to_cpu(agf->agf_longest);
- pag->pagf_levels[XFS_BTNUM_BNOi] =
- be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNOi]);
- pag->pagf_levels[XFS_BTNUM_CNTi] =
- be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNTi]);
- pag->pagf_levels[XFS_BTNUM_RMAPi] =
- be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAPi]);
+ pag->pagf_bno_level = be32_to_cpu(agf->agf_bno_level);
+ pag->pagf_cnt_level = be32_to_cpu(agf->agf_cnt_level);
+ pag->pagf_rmap_level = be32_to_cpu(agf->agf_rmap_level);
pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
if (xfs_agfl_needs_reset(pag->pag_mount, agf))
set_bit(XFS_AGSTATE_AGFL_NEEDS_RESET, &pag->pag_opstate);
@@ -3343,10 +3403,8 @@ xfs_alloc_read_agf(
ASSERT(pag->pagf_btreeblks == be32_to_cpu(agf->agf_btreeblks));
ASSERT(pag->pagf_flcount == be32_to_cpu(agf->agf_flcount));
ASSERT(pag->pagf_longest == be32_to_cpu(agf->agf_longest));
- ASSERT(pag->pagf_levels[XFS_BTNUM_BNOi] ==
- be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNOi]));
- ASSERT(pag->pagf_levels[XFS_BTNUM_CNTi] ==
- be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNTi]));
+ ASSERT(pag->pagf_bno_level == be32_to_cpu(agf->agf_bno_level));
+ ASSERT(pag->pagf_cnt_level == be32_to_cpu(agf->agf_cnt_level));
}
#endif
if (agfbpp)
@@ -3895,17 +3953,23 @@ __xfs_free_extent(
return -EIO;
error = xfs_free_extent_fix_freelist(tp, pag, &agbp);
- if (error)
+ if (error) {
+ if (xfs_metadata_is_sick(error))
+ xfs_ag_mark_sick(pag, XFS_SICK_AG_BNOBT);
return error;
+ }
+
agf = agbp->b_addr;
if (XFS_IS_CORRUPT(mp, agbno >= mp->m_sb.sb_agblocks)) {
+ xfs_ag_mark_sick(pag, XFS_SICK_AG_BNOBT);
error = -EFSCORRUPTED;
goto err_release;
}
/* validate the extent size is legal now we have the agf locked */
if (XFS_IS_CORRUPT(mp, agbno + len > be32_to_cpu(agf->agf_length))) {
+ xfs_ag_mark_sick(pag, XFS_SICK_AG_BNOBT);
error = -EFSCORRUPTED;
goto err_release;
}
@@ -3962,7 +4026,7 @@ xfs_alloc_query_range(
union xfs_btree_irec high_brec = { .a = *high_rec };
struct xfs_alloc_query_range_info query = { .priv = priv, .fn = fn };
- ASSERT(cur->bc_btnum == XFS_BTNUM_BNO);
+ ASSERT(xfs_btree_is_bno(cur->bc_ops));
return xfs_btree_query_range(cur, &low_brec, &high_brec,
xfs_alloc_query_range_helper, &query);
}
@@ -3976,7 +4040,7 @@ xfs_alloc_query_all(
{
struct xfs_alloc_query_range_info query;
- ASSERT(cur->bc_btnum == XFS_BTNUM_BNO);
+ ASSERT(xfs_btree_is_bno(cur->bc_ops));
query.priv = priv;
query.fn = fn;
return xfs_btree_query_all(cur, xfs_alloc_query_range_helper, &query);
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index a7032bf0cd..6ef5ddd896 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -16,6 +16,7 @@
#include "xfs_alloc.h"
#include "xfs_extent_busy.h"
#include "xfs_error.h"
+#include "xfs_health.h"
#include "xfs_trace.h"
#include "xfs_trans.h"
#include "xfs_ag.h"
@@ -23,13 +24,22 @@
static struct kmem_cache *xfs_allocbt_cur_cache;
STATIC struct xfs_btree_cur *
-xfs_allocbt_dup_cursor(
+xfs_bnobt_dup_cursor(
struct xfs_btree_cur *cur)
{
- return xfs_allocbt_init_cursor(cur->bc_mp, cur->bc_tp,
- cur->bc_ag.agbp, cur->bc_ag.pag, cur->bc_btnum);
+ return xfs_bnobt_init_cursor(cur->bc_mp, cur->bc_tp, cur->bc_ag.agbp,
+ cur->bc_ag.pag);
}
+STATIC struct xfs_btree_cur *
+xfs_cntbt_dup_cursor(
+ struct xfs_btree_cur *cur)
+{
+ return xfs_cntbt_init_cursor(cur->bc_mp, cur->bc_tp, cur->bc_ag.agbp,
+ cur->bc_ag.pag);
+}
+
+
STATIC void
xfs_allocbt_set_root(
struct xfs_btree_cur *cur,
@@ -38,13 +48,18 @@ xfs_allocbt_set_root(
{
struct xfs_buf *agbp = cur->bc_ag.agbp;
struct xfs_agf *agf = agbp->b_addr;
- int btnum = cur->bc_btnum;
ASSERT(ptr->s != 0);
- agf->agf_roots[btnum] = ptr->s;
- be32_add_cpu(&agf->agf_levels[btnum], inc);
- cur->bc_ag.pag->pagf_levels[btnum] += inc;
+ if (xfs_btree_is_bno(cur->bc_ops)) {
+ agf->agf_bno_root = ptr->s;
+ be32_add_cpu(&agf->agf_bno_level, inc);
+ cur->bc_ag.pag->pagf_bno_level += inc;
+ } else {
+ agf->agf_cnt_root = ptr->s;
+ be32_add_cpu(&agf->agf_cnt_level, inc);
+ cur->bc_ag.pag->pagf_cnt_level += inc;
+ }
xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS);
}
@@ -116,7 +131,7 @@ xfs_allocbt_update_lastrec(
__be32 len;
int numrecs;
- ASSERT(cur->bc_btnum == XFS_BTNUM_CNT);
+ ASSERT(!xfs_btree_is_bno(cur->bc_ops));
switch (reason) {
case LASTREC_UPDATE:
@@ -226,7 +241,10 @@ xfs_allocbt_init_ptr_from_cur(
ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agf->agf_seqno));
- ptr->s = agf->agf_roots[cur->bc_btnum];
+ if (xfs_btree_is_bno(cur->bc_ops))
+ ptr->s = agf->agf_bno_root;
+ else
+ ptr->s = agf->agf_cnt_root;
}
STATIC int64_t
@@ -299,13 +317,12 @@ xfs_allocbt_verify(
struct xfs_perag *pag = bp->b_pag;
xfs_failaddr_t fa;
unsigned int level;
- xfs_btnum_t btnum = XFS_BTNUM_BNOi;
if (!xfs_verify_magic(bp, block->bb_magic))
return __this_address;
if (xfs_has_crc(mp)) {
- fa = xfs_btree_sblock_v5hdr_verify(bp);
+ fa = xfs_btree_agblock_v5hdr_verify(bp);
if (fa)
return fa;
}
@@ -320,26 +337,32 @@ xfs_allocbt_verify(
* against.
*/
level = be16_to_cpu(block->bb_level);
- if (bp->b_ops->magic[0] == cpu_to_be32(XFS_ABTC_MAGIC))
- btnum = XFS_BTNUM_CNTi;
if (pag && xfs_perag_initialised_agf(pag)) {
- unsigned int maxlevel = pag->pagf_levels[btnum];
+ unsigned int maxlevel, repair_maxlevel = 0;
-#ifdef CONFIG_XFS_ONLINE_REPAIR
/*
* Online repair could be rewriting the free space btrees, so
* we'll validate against the larger of either tree while this
* is going on.
*/
- maxlevel = max_t(unsigned int, maxlevel,
- pag->pagf_repair_levels[btnum]);
+ if (bp->b_ops->magic[0] == cpu_to_be32(XFS_ABTC_MAGIC)) {
+ maxlevel = pag->pagf_cnt_level;
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+ repair_maxlevel = pag->pagf_repair_cnt_level;
+#endif
+ } else {
+ maxlevel = pag->pagf_bno_level;
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+ repair_maxlevel = pag->pagf_repair_bno_level;
#endif
- if (level >= maxlevel)
+ }
+
+ if (level >= max(maxlevel, repair_maxlevel))
return __this_address;
} else if (level >= mp->m_alloc_maxlevels)
return __this_address;
- return xfs_btree_sblock_verify(bp, mp->m_alloc_mxr[level != 0]);
+ return xfs_btree_agblock_verify(bp, mp->m_alloc_mxr[level != 0]);
}
static void
@@ -348,7 +371,7 @@ xfs_allocbt_read_verify(
{
xfs_failaddr_t fa;
- if (!xfs_btree_sblock_verify_crc(bp))
+ if (!xfs_btree_agblock_verify_crc(bp))
xfs_verifier_error(bp, -EFSBADCRC, __this_address);
else {
fa = xfs_allocbt_verify(bp);
@@ -372,7 +395,7 @@ xfs_allocbt_write_verify(
xfs_verifier_error(bp, -EFSCORRUPTED, fa);
return;
}
- xfs_btree_sblock_calc_crc(bp);
+ xfs_btree_agblock_calc_crc(bp);
}
@@ -454,11 +477,19 @@ xfs_allocbt_keys_contiguous(
be32_to_cpu(key2->alloc.ar_startblock));
}
-static const struct xfs_btree_ops xfs_bnobt_ops = {
+const struct xfs_btree_ops xfs_bnobt_ops = {
+ .name = "bno",
+ .type = XFS_BTREE_TYPE_AG,
+
.rec_len = sizeof(xfs_alloc_rec_t),
.key_len = sizeof(xfs_alloc_key_t),
+ .ptr_len = XFS_BTREE_SHORT_PTR_LEN,
- .dup_cursor = xfs_allocbt_dup_cursor,
+ .lru_refs = XFS_ALLOC_BTREE_REF,
+ .statoff = XFS_STATS_CALC_INDEX(xs_abtb_2),
+ .sick_mask = XFS_SICK_AG_BNOBT,
+
+ .dup_cursor = xfs_bnobt_dup_cursor,
.set_root = xfs_allocbt_set_root,
.alloc_block = xfs_allocbt_alloc_block,
.free_block = xfs_allocbt_free_block,
@@ -477,11 +508,20 @@ static const struct xfs_btree_ops xfs_bnobt_ops = {
.keys_contiguous = xfs_allocbt_keys_contiguous,
};
-static const struct xfs_btree_ops xfs_cntbt_ops = {
+const struct xfs_btree_ops xfs_cntbt_ops = {
+ .name = "cnt",
+ .type = XFS_BTREE_TYPE_AG,
+ .geom_flags = XFS_BTGEO_LASTREC_UPDATE,
+
.rec_len = sizeof(xfs_alloc_rec_t),
.key_len = sizeof(xfs_alloc_key_t),
+ .ptr_len = XFS_BTREE_SHORT_PTR_LEN,
+
+ .lru_refs = XFS_ALLOC_BTREE_REF,
+ .statoff = XFS_STATS_CALC_INDEX(xs_abtc_2),
+ .sick_mask = XFS_SICK_AG_CNTBT,
- .dup_cursor = xfs_allocbt_dup_cursor,
+ .dup_cursor = xfs_cntbt_dup_cursor,
.set_root = xfs_allocbt_set_root,
.alloc_block = xfs_allocbt_alloc_block,
.free_block = xfs_allocbt_free_block,
@@ -500,76 +540,55 @@ static const struct xfs_btree_ops xfs_cntbt_ops = {
.keys_contiguous = NULL, /* not needed right now */
};
-/* Allocate most of a new allocation btree cursor. */
-STATIC struct xfs_btree_cur *
-xfs_allocbt_init_common(
+/*
+ * Allocate a new bnobt cursor.
+ *
+ * For staging cursors tp and agbp are NULL.
+ */
+struct xfs_btree_cur *
+xfs_bnobt_init_cursor(
struct xfs_mount *mp,
struct xfs_trans *tp,
- struct xfs_perag *pag,
- xfs_btnum_t btnum)
+ struct xfs_buf *agbp,
+ struct xfs_perag *pag)
{
struct xfs_btree_cur *cur;
- ASSERT(btnum == XFS_BTNUM_BNO || btnum == XFS_BTNUM_CNT);
-
- cur = xfs_btree_alloc_cursor(mp, tp, btnum, mp->m_alloc_maxlevels,
- xfs_allocbt_cur_cache);
- cur->bc_ag.abt.active = false;
-
- if (btnum == XFS_BTNUM_CNT) {
- cur->bc_ops = &xfs_cntbt_ops;
- cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtc_2);
- cur->bc_flags = XFS_BTREE_LASTREC_UPDATE;
- } else {
- cur->bc_ops = &xfs_bnobt_ops;
- cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtb_2);
- }
-
+ cur = xfs_btree_alloc_cursor(mp, tp, &xfs_bnobt_ops,
+ mp->m_alloc_maxlevels, xfs_allocbt_cur_cache);
cur->bc_ag.pag = xfs_perag_hold(pag);
+ cur->bc_ag.agbp = agbp;
+ if (agbp) {
+ struct xfs_agf *agf = agbp->b_addr;
- if (xfs_has_crc(mp))
- cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
-
+ cur->bc_nlevels = be32_to_cpu(agf->agf_bno_level);
+ }
return cur;
}
/*
- * Allocate a new allocation btree cursor.
+ * Allocate a new cntbt cursor.
+ *
+ * For staging cursors tp and agbp are NULL.
*/
-struct xfs_btree_cur * /* new alloc btree cursor */
-xfs_allocbt_init_cursor(
- struct xfs_mount *mp, /* file system mount point */
- struct xfs_trans *tp, /* transaction pointer */
- struct xfs_buf *agbp, /* buffer for agf structure */
- struct xfs_perag *pag,
- xfs_btnum_t btnum) /* btree identifier */
-{
- struct xfs_agf *agf = agbp->b_addr;
- struct xfs_btree_cur *cur;
-
- cur = xfs_allocbt_init_common(mp, tp, pag, btnum);
- if (btnum == XFS_BTNUM_CNT)
- cur->bc_nlevels = be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]);
- else
- cur->bc_nlevels = be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]);
-
- cur->bc_ag.agbp = agbp;
-
- return cur;
-}
-
-/* Create a free space btree cursor with a fake root for staging. */
struct xfs_btree_cur *
-xfs_allocbt_stage_cursor(
+xfs_cntbt_init_cursor(
struct xfs_mount *mp,
- struct xbtree_afakeroot *afake,
- struct xfs_perag *pag,
- xfs_btnum_t btnum)
+ struct xfs_trans *tp,
+ struct xfs_buf *agbp,
+ struct xfs_perag *pag)
{
struct xfs_btree_cur *cur;
- cur = xfs_allocbt_init_common(mp, NULL, pag, btnum);
- xfs_btree_stage_afakeroot(cur, afake);
+ cur = xfs_btree_alloc_cursor(mp, tp, &xfs_cntbt_ops,
+ mp->m_alloc_maxlevels, xfs_allocbt_cur_cache);
+ cur->bc_ag.pag = xfs_perag_hold(pag);
+ cur->bc_ag.agbp = agbp;
+ if (agbp) {
+ struct xfs_agf *agf = agbp->b_addr;
+
+ cur->bc_nlevels = be32_to_cpu(agf->agf_cnt_level);
+ }
return cur;
}
@@ -588,16 +607,16 @@ xfs_allocbt_commit_staged_btree(
ASSERT(cur->bc_flags & XFS_BTREE_STAGING);
- agf->agf_roots[cur->bc_btnum] = cpu_to_be32(afake->af_root);
- agf->agf_levels[cur->bc_btnum] = cpu_to_be32(afake->af_levels);
- xfs_alloc_log_agf(tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS);
-
- if (cur->bc_btnum == XFS_BTNUM_BNO) {
- xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_bnobt_ops);
+ if (xfs_btree_is_bno(cur->bc_ops)) {
+ agf->agf_bno_root = cpu_to_be32(afake->af_root);
+ agf->agf_bno_level = cpu_to_be32(afake->af_levels);
} else {
- cur->bc_flags |= XFS_BTREE_LASTREC_UPDATE;
- xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_cntbt_ops);
+ agf->agf_cnt_root = cpu_to_be32(afake->af_root);
+ agf->agf_cnt_level = cpu_to_be32(afake->af_levels);
}
+ xfs_alloc_log_agf(tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS);
+
+ xfs_btree_commit_afakeroot(cur, tp, agbp);
}
/* Calculate number of records in an alloc btree block. */
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.h b/fs/xfs/libxfs/xfs_alloc_btree.h
index 45df893ef6..155b47f231 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.h
+++ b/fs/xfs/libxfs/xfs_alloc_btree.h
@@ -47,12 +47,12 @@ struct xbtree_afakeroot;
(maxrecs) * sizeof(xfs_alloc_key_t) + \
((index) - 1) * sizeof(xfs_alloc_ptr_t)))
-extern struct xfs_btree_cur *xfs_allocbt_init_cursor(struct xfs_mount *mp,
+struct xfs_btree_cur *xfs_bnobt_init_cursor(struct xfs_mount *mp,
struct xfs_trans *tp, struct xfs_buf *bp,
- struct xfs_perag *pag, xfs_btnum_t btnum);
-struct xfs_btree_cur *xfs_allocbt_stage_cursor(struct xfs_mount *mp,
- struct xbtree_afakeroot *afake, struct xfs_perag *pag,
- xfs_btnum_t btnum);
+ struct xfs_perag *pag);
+struct xfs_btree_cur *xfs_cntbt_init_cursor(struct xfs_mount *mp,
+ struct xfs_trans *tp, struct xfs_buf *bp,
+ struct xfs_perag *pag);
extern int xfs_allocbt_maxrecs(struct xfs_mount *, int, int);
extern xfs_extlen_t xfs_allocbt_calc_size(struct xfs_mount *mp,
unsigned long long len);
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index e965a48e7d..673a4b6d2e 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -224,7 +224,7 @@ int
xfs_attr_get_ilocked(
struct xfs_da_args *args)
{
- ASSERT(xfs_isilocked(args->dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
+ xfs_assert_ilocked(args->dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL);
if (!xfs_inode_hasattr(args->dp))
return -ENOATTR;
@@ -891,7 +891,8 @@ xfs_attr_defer_add(
struct xfs_attr_intent *new;
- new = kmem_cache_zalloc(xfs_attr_intent_cache, GFP_NOFS | __GFP_NOFAIL);
+ new = kmem_cache_zalloc(xfs_attr_intent_cache,
+ GFP_KERNEL | __GFP_NOFAIL);
new->xattri_op_flags = op_flags;
new->xattri_da_args = args;
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 6374bf1072..ac904cc1a9 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -29,6 +29,7 @@
#include "xfs_log.h"
#include "xfs_ag.h"
#include "xfs_errortag.h"
+#include "xfs_health.h"
/*
@@ -879,8 +880,7 @@ xfs_attr_shortform_to_leaf(
trace_xfs_attr_sf_to_leaf(args);
- tmpbuffer = kmem_alloc(size, 0);
- ASSERT(tmpbuffer != NULL);
+ tmpbuffer = kmalloc(size, GFP_KERNEL | __GFP_NOFAIL);
memcpy(tmpbuffer, ifp->if_data, size);
sf = (struct xfs_attr_sf_hdr *)tmpbuffer;
@@ -924,7 +924,7 @@ xfs_attr_shortform_to_leaf(
}
error = 0;
out:
- kmem_free(tmpbuffer);
+ kfree(tmpbuffer);
return error;
}
@@ -1059,7 +1059,7 @@ xfs_attr3_leaf_to_shortform(
trace_xfs_attr_leaf_to_sf(args);
- tmpbuffer = kmem_alloc(args->geo->blksize, 0);
+ tmpbuffer = kmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL);
if (!tmpbuffer)
return -ENOMEM;
@@ -1125,7 +1125,7 @@ xfs_attr3_leaf_to_shortform(
error = 0;
out:
- kmem_free(tmpbuffer);
+ kfree(tmpbuffer);
return error;
}
@@ -1533,7 +1533,7 @@ xfs_attr3_leaf_compact(
trace_xfs_attr_leaf_compact(args);
- tmpbuffer = kmem_alloc(args->geo->blksize, 0);
+ tmpbuffer = kmalloc(args->geo->blksize, GFP_KERNEL | __GFP_NOFAIL);
memcpy(tmpbuffer, bp->b_addr, args->geo->blksize);
memset(bp->b_addr, 0, args->geo->blksize);
leaf_src = (xfs_attr_leafblock_t *)tmpbuffer;
@@ -1571,7 +1571,7 @@ xfs_attr3_leaf_compact(
*/
xfs_trans_log_buf(trans, bp, 0, args->geo->blksize - 1);
- kmem_free(tmpbuffer);
+ kfree(tmpbuffer);
}
/*
@@ -2250,7 +2250,8 @@ xfs_attr3_leaf_unbalance(
struct xfs_attr_leafblock *tmp_leaf;
struct xfs_attr3_icleaf_hdr tmphdr;
- tmp_leaf = kmem_zalloc(state->args->geo->blksize, 0);
+ tmp_leaf = kzalloc(state->args->geo->blksize,
+ GFP_KERNEL | __GFP_NOFAIL);
/*
* Copy the header into the temp leaf so that all the stuff
@@ -2290,7 +2291,7 @@ xfs_attr3_leaf_unbalance(
}
memcpy(save_leaf, tmp_leaf, state->args->geo->blksize);
savehdr = tmphdr; /* struct copy */
- kmem_free(tmp_leaf);
+ kfree(tmp_leaf);
}
xfs_attr3_leaf_hdr_to_disk(state->args->geo, save_leaf, &savehdr);
@@ -2343,6 +2344,7 @@ xfs_attr3_leaf_lookup_int(
entries = xfs_attr3_leaf_entryp(leaf);
if (ichdr.count >= args->geo->blksize / 8) {
xfs_buf_mark_corrupt(bp);
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
}
@@ -2362,10 +2364,12 @@ xfs_attr3_leaf_lookup_int(
}
if (!(probe >= 0 && (!ichdr.count || probe < ichdr.count))) {
xfs_buf_mark_corrupt(bp);
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
}
if (!(span <= 4 || be32_to_cpu(entry->hashval) == hashval)) {
xfs_buf_mark_corrupt(bp);
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index d440393b40..ff04128287 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -22,6 +22,7 @@
#include "xfs_attr_remote.h"
#include "xfs_trace.h"
#include "xfs_error.h"
+#include "xfs_health.h"
#define ATTR_RMTVALUE_MAPSIZE 1 /* # of map entries at once */
@@ -276,17 +277,18 @@ xfs_attr3_rmt_hdr_set(
*/
STATIC int
xfs_attr_rmtval_copyout(
- struct xfs_mount *mp,
- struct xfs_buf *bp,
- xfs_ino_t ino,
- int *offset,
- int *valuelen,
- uint8_t **dst)
+ struct xfs_mount *mp,
+ struct xfs_buf *bp,
+ struct xfs_inode *dp,
+ int *offset,
+ int *valuelen,
+ uint8_t **dst)
{
- char *src = bp->b_addr;
- xfs_daddr_t bno = xfs_buf_daddr(bp);
- int len = BBTOB(bp->b_length);
- int blksize = mp->m_attr_geo->blksize;
+ char *src = bp->b_addr;
+ xfs_ino_t ino = dp->i_ino;
+ xfs_daddr_t bno = xfs_buf_daddr(bp);
+ int len = BBTOB(bp->b_length);
+ int blksize = mp->m_attr_geo->blksize;
ASSERT(len >= blksize);
@@ -302,6 +304,7 @@ xfs_attr_rmtval_copyout(
xfs_alert(mp,
"remote attribute header mismatch bno/off/len/owner (0x%llx/0x%x/Ox%x/0x%llx)",
bno, *offset, byte_cnt, ino);
+ xfs_dirattr_mark_sick(dp, XFS_ATTR_FORK);
return -EFSCORRUPTED;
}
hdr_size = sizeof(struct xfs_attr3_rmt_hdr);
@@ -418,10 +421,12 @@ xfs_attr_rmtval_get(
dblkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
error = xfs_buf_read(mp->m_ddev_targp, dblkno, dblkcnt,
0, &bp, &xfs_attr3_rmt_buf_ops);
+ if (xfs_metadata_is_sick(error))
+ xfs_dirattr_mark_sick(args->dp, XFS_ATTR_FORK);
if (error)
return error;
- error = xfs_attr_rmtval_copyout(mp, bp, args->dp->i_ino,
+ error = xfs_attr_rmtval_copyout(mp, bp, args->dp,
&offset, &valuelen,
&dst);
xfs_buf_relse(bp);
@@ -545,11 +550,13 @@ xfs_attr_rmtval_stale(
struct xfs_buf *bp;
int error;
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+ xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
if (XFS_IS_CORRUPT(mp, map->br_startblock == DELAYSTARTBLOCK) ||
- XFS_IS_CORRUPT(mp, map->br_startblock == HOLESTARTBLOCK))
+ XFS_IS_CORRUPT(mp, map->br_startblock == HOLESTARTBLOCK)) {
+ xfs_bmap_mark_sick(ip, XFS_ATTR_FORK);
return -EFSCORRUPTED;
+ }
error = xfs_buf_incore(mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, map->br_startblock),
@@ -659,8 +666,10 @@ xfs_attr_rmtval_invalidate(
blkcnt, &map, &nmap, XFS_BMAPI_ATTRFORK);
if (error)
return error;
- if (XFS_IS_CORRUPT(args->dp->i_mount, nmap != 1))
+ if (XFS_IS_CORRUPT(args->dp->i_mount, nmap != 1)) {
+ xfs_bmap_mark_sick(args->dp, XFS_ATTR_FORK);
return -EFSCORRUPTED;
+ }
error = xfs_attr_rmtval_stale(args->dp, &map, XBF_TRYLOCK);
if (error)
return error;
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index f362345467..656c95a22f 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -36,6 +36,9 @@
#include "xfs_refcount.h"
#include "xfs_icache.h"
#include "xfs_iomap.h"
+#include "xfs_health.h"
+#include "xfs_bmap_item.h"
+#include "xfs_symlink_remote.h"
struct kmem_cache *xfs_bmap_intent_cache;
@@ -225,6 +228,28 @@ xfs_bmap_forkoff_reset(
}
}
+static int
+xfs_bmap_read_buf(
+ struct xfs_mount *mp, /* file system mount point */
+ struct xfs_trans *tp, /* transaction pointer */
+ xfs_fsblock_t fsbno, /* file system block number */
+ struct xfs_buf **bpp) /* buffer for fsbno */
+{
+ struct xfs_buf *bp; /* return value */
+ int error;
+
+ if (!xfs_verify_fsbno(mp, fsbno))
+ return -EFSCORRUPTED;
+ error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
+ XFS_FSB_TO_DADDR(mp, fsbno), mp->m_bsize, 0, &bp,
+ &xfs_bmbt_buf_ops);
+ if (!error) {
+ xfs_buf_set_ref(bp, XFS_BMAP_BTREE_REF);
+ *bpp = bp;
+ }
+ return error;
+}
+
#ifdef DEBUG
STATIC struct xfs_buf *
xfs_bmap_get_bp(
@@ -364,9 +389,9 @@ xfs_bmap_check_leaf_extents(
bp = xfs_bmap_get_bp(cur, XFS_FSB_TO_DADDR(mp, bno));
if (!bp) {
bp_release = 1;
- error = xfs_btree_read_bufl(mp, NULL, bno, &bp,
- XFS_BMAP_BTREE_REF,
- &xfs_bmbt_buf_ops);
+ error = xfs_bmap_read_buf(mp, NULL, bno, &bp);
+ if (xfs_metadata_is_sick(error))
+ xfs_btree_mark_sick(cur);
if (error)
goto error_norelse;
}
@@ -383,6 +408,7 @@ xfs_bmap_check_leaf_extents(
pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
bno = be64_to_cpu(*pp);
if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, bno))) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -450,9 +476,9 @@ xfs_bmap_check_leaf_extents(
bp = xfs_bmap_get_bp(cur, XFS_FSB_TO_DADDR(mp, bno));
if (!bp) {
bp_release = 1;
- error = xfs_btree_read_bufl(mp, NULL, bno, &bp,
- XFS_BMAP_BTREE_REF,
- &xfs_bmbt_buf_ops);
+ error = xfs_bmap_read_buf(mp, NULL, bno, &bp);
+ if (xfs_metadata_is_sick(error))
+ xfs_btree_mark_sick(cur);
if (error)
goto error_norelse;
}
@@ -562,11 +588,14 @@ xfs_bmap_btree_to_extents(
pp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, ifp->if_broot_bytes);
cbno = be64_to_cpu(*pp);
#ifdef DEBUG
- if (XFS_IS_CORRUPT(cur->bc_mp, !xfs_btree_check_lptr(cur, cbno, 1)))
+ if (XFS_IS_CORRUPT(cur->bc_mp, !xfs_verify_fsbno(mp, cbno))) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
#endif
- error = xfs_btree_read_bufl(mp, tp, cbno, &cbp, XFS_BMAP_BTREE_REF,
- &xfs_bmbt_buf_ops);
+ error = xfs_bmap_read_buf(mp, tp, cbno, &cbp);
+ if (xfs_metadata_is_sick(error))
+ xfs_btree_mark_sick(cur);
if (error)
return error;
cblock = XFS_BUF_TO_BLOCK(cbp);
@@ -634,14 +663,13 @@ xfs_bmap_extents_to_btree(
* Fill in the root.
*/
block = ifp->if_broot;
- xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL,
- XFS_BTNUM_BMAP, 1, 1, ip->i_ino,
- XFS_BTREE_LONG_PTRS);
+ xfs_bmbt_init_block(ip, block, NULL, 1, 1);
/*
* Need a cursor. Can't allocate until bb_level is filled in.
*/
cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
- cur->bc_ino.flags = wasdel ? XFS_BTCUR_BMBT_WASDEL : 0;
+ if (wasdel)
+ cur->bc_flags |= XFS_BTREE_BMBT_WASDEL;
/*
* Convert to a btree with two levels, one record in root.
*/
@@ -667,7 +695,7 @@ xfs_bmap_extents_to_btree(
goto out_root_realloc;
}
- cur->bc_ino.allocated++;
+ cur->bc_bmap.allocated++;
ip->i_nblocks++;
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L);
error = xfs_trans_get_buf(tp, mp->m_ddev_targp,
@@ -679,11 +707,8 @@ xfs_bmap_extents_to_btree(
/*
* Fill in the child block.
*/
- abp->b_ops = &xfs_bmbt_buf_ops;
ablock = XFS_BUF_TO_BLOCK(abp);
- xfs_btree_init_block_int(mp, ablock, xfs_buf_daddr(abp),
- XFS_BTNUM_BMAP, 0, 0, ip->i_ino,
- XFS_BTREE_LONG_PTRS);
+ xfs_bmbt_init_block(ip, ablock, abp, 0, 0);
for_each_xfs_iext(ifp, &icur, &rec) {
if (isnullstartblock(rec.br_startblock))
@@ -878,6 +903,7 @@ xfs_bmap_add_attrfork_btree(
goto error0;
/* must be at least one entry */
if (XFS_IS_CORRUPT(mp, stat != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -887,7 +913,7 @@ xfs_bmap_add_attrfork_btree(
xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
return -ENOSPC;
}
- cur->bc_ino.allocated = 0;
+ cur->bc_bmap.allocated = 0;
xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
}
return 0;
@@ -915,7 +941,7 @@ xfs_bmap_add_attrfork_extents(
error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0, flags,
XFS_DATA_FORK);
if (cur) {
- cur->bc_ino.allocated = 0;
+ cur->bc_bmap.allocated = 0;
xfs_btree_del_cursor(cur, error);
}
return error;
@@ -960,6 +986,7 @@ xfs_bmap_add_attrfork_local(
/* should only be called for types that support local format data */
ASSERT(0);
+ xfs_bmap_mark_sick(ip, XFS_ATTR_FORK);
return -EFSCORRUPTED;
}
@@ -1143,6 +1170,7 @@ xfs_iread_bmbt_block(
(unsigned long long)ip->i_ino);
xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, block,
sizeof(*block), __this_address);
+ xfs_bmap_mark_sick(ip, whichfork);
return -EFSCORRUPTED;
}
@@ -1158,6 +1186,7 @@ xfs_iread_bmbt_block(
xfs_inode_verifier_error(ip, -EFSCORRUPTED,
"xfs_iread_extents(2)", frp,
sizeof(*frp), fa);
+ xfs_bmap_mark_sick(ip, whichfork);
return xfs_bmap_complain_bad_rec(ip, whichfork, fa,
&new);
}
@@ -1189,7 +1218,7 @@ xfs_iread_extents(
if (!xfs_need_iread_extents(ifp))
return 0;
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+ xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
ir.loaded = 0;
xfs_iext_first(ifp, &ir.icur);
@@ -1201,6 +1230,7 @@ xfs_iread_extents(
goto out;
if (XFS_IS_CORRUPT(mp, ir.loaded != ifp->if_nextents)) {
+ xfs_bmap_mark_sick(ip, whichfork);
error = -EFSCORRUPTED;
goto out;
}
@@ -1213,6 +1243,8 @@ xfs_iread_extents(
smp_store_release(&ifp->if_needextents, 0);
return 0;
out:
+ if (xfs_metadata_is_sick(error))
+ xfs_bmap_mark_sick(ip, whichfork);
xfs_iext_destroy(ifp);
return error;
}
@@ -1292,6 +1324,7 @@ xfs_bmap_last_before(
break;
default:
ASSERT(0);
+ xfs_bmap_mark_sick(ip, whichfork);
return -EFSCORRUPTED;
}
@@ -1388,8 +1421,10 @@ xfs_bmap_last_offset(
if (ifp->if_format == XFS_DINODE_FMT_LOCAL)
return 0;
- if (XFS_IS_CORRUPT(ip->i_mount, !xfs_ifork_has_extents(ifp)))
+ if (XFS_IS_CORRUPT(ip->i_mount, !xfs_ifork_has_extents(ifp))) {
+ xfs_bmap_mark_sick(ip, whichfork);
return -EFSCORRUPTED;
+ }
error = xfs_bmap_last_extent(NULL, ip, whichfork, &rec, &is_empty);
if (error || is_empty)
@@ -1429,8 +1464,7 @@ xfs_bmap_add_extent_delay_real(
ASSERT(whichfork != XFS_ATTR_FORK);
ASSERT(!isnullstartblock(new->br_startblock));
- ASSERT(!bma->cur ||
- (bma->cur->bc_ino.flags & XFS_BTCUR_BMBT_WASDEL));
+ ASSERT(!bma->cur || (bma->cur->bc_flags & XFS_BTREE_BMBT_WASDEL));
XFS_STATS_INC(mp, xs_add_exlist);
@@ -1528,6 +1562,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bma->cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1535,6 +1570,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bma->cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1542,6 +1578,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bma->cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1571,6 +1608,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bma->cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1604,6 +1642,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bma->cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1632,6 +1671,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 0)) {
+ xfs_btree_mark_sick(bma->cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1639,6 +1679,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bma->cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1673,6 +1714,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bma->cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1698,6 +1740,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 0)) {
+ xfs_btree_mark_sick(bma->cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1705,6 +1748,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bma->cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1721,7 +1765,7 @@ xfs_bmap_add_extent_delay_real(
temp = PREV.br_blockcount - new->br_blockcount;
da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(bma->ip, temp),
startblockval(PREV.br_startblock) -
- (bma->cur ? bma->cur->bc_ino.allocated : 0));
+ (bma->cur ? bma->cur->bc_bmap.allocated : 0));
PREV.br_startoff = new_endoff;
PREV.br_blockcount = temp;
@@ -1749,6 +1793,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bma->cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1785,6 +1830,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 0)) {
+ xfs_btree_mark_sick(bma->cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1792,6 +1838,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bma->cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1808,7 +1855,7 @@ xfs_bmap_add_extent_delay_real(
temp = PREV.br_blockcount - new->br_blockcount;
da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(bma->ip, temp),
startblockval(PREV.br_startblock) -
- (bma->cur ? bma->cur->bc_ino.allocated : 0));
+ (bma->cur ? bma->cur->bc_bmap.allocated : 0));
PREV.br_startblock = nullstartblock(da_new);
PREV.br_blockcount = temp;
@@ -1871,6 +1918,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 0)) {
+ xfs_btree_mark_sick(bma->cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1878,6 +1926,7 @@ xfs_bmap_add_extent_delay_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(bma->cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1929,8 +1978,8 @@ xfs_bmap_add_extent_delay_real(
xfs_mod_delalloc(mp, (int64_t)da_new - da_old);
if (bma->cur) {
- da_new += bma->cur->bc_ino.allocated;
- bma->cur->bc_ino.allocated = 0;
+ da_new += bma->cur->bc_bmap.allocated;
+ bma->cur->bc_bmap.allocated = 0;
}
/* adjust for changes in reserved delayed indirect blocks */
@@ -2074,30 +2123,35 @@ xfs_bmap_add_extent_unwritten_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
if ((error = xfs_btree_delete(cur, &i)))
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
if ((error = xfs_btree_decrement(cur, 0, &i)))
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
if ((error = xfs_btree_delete(cur, &i)))
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
if ((error = xfs_btree_decrement(cur, 0, &i)))
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2126,18 +2180,21 @@ xfs_bmap_add_extent_unwritten_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
if ((error = xfs_btree_delete(cur, &i)))
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
if ((error = xfs_btree_decrement(cur, 0, &i)))
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2169,18 +2226,21 @@ xfs_bmap_add_extent_unwritten_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
if ((error = xfs_btree_delete(cur, &i)))
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
if ((error = xfs_btree_decrement(cur, 0, &i)))
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2207,6 +2267,7 @@ xfs_bmap_add_extent_unwritten_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2240,6 +2301,7 @@ xfs_bmap_add_extent_unwritten_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2277,6 +2339,7 @@ xfs_bmap_add_extent_unwritten_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2287,6 +2350,7 @@ xfs_bmap_add_extent_unwritten_real(
if ((error = xfs_btree_insert(cur, &i)))
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2317,6 +2381,7 @@ xfs_bmap_add_extent_unwritten_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2353,6 +2418,7 @@ xfs_bmap_add_extent_unwritten_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2363,12 +2429,14 @@ xfs_bmap_add_extent_unwritten_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 0)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
if ((error = xfs_btree_insert(cur, &i)))
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2405,6 +2473,7 @@ xfs_bmap_add_extent_unwritten_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2417,6 +2486,7 @@ xfs_bmap_add_extent_unwritten_real(
if ((error = xfs_btree_insert(cur, &i)))
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2429,6 +2499,7 @@ xfs_bmap_add_extent_unwritten_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 0)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2436,6 +2507,7 @@ xfs_bmap_add_extent_unwritten_real(
if ((error = xfs_btree_insert(cur, &i)))
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2472,7 +2544,7 @@ xfs_bmap_add_extent_unwritten_real(
/* clear out the allocated field, done with it now in any case. */
if (cur) {
- cur->bc_ino.allocated = 0;
+ cur->bc_bmap.allocated = 0;
*curp = cur;
}
@@ -2651,7 +2723,7 @@ xfs_bmap_add_extent_hole_real(
struct xfs_bmbt_irec old;
ASSERT(!isnullstartblock(new->br_startblock));
- ASSERT(!cur || !(cur->bc_ino.flags & XFS_BTCUR_BMBT_WASDEL));
+ ASSERT(!cur || !(cur->bc_flags & XFS_BTREE_BMBT_WASDEL));
XFS_STATS_INC(mp, xs_add_exlist);
@@ -2721,6 +2793,7 @@ xfs_bmap_add_extent_hole_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2728,6 +2801,7 @@ xfs_bmap_add_extent_hole_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2735,6 +2809,7 @@ xfs_bmap_add_extent_hole_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2764,6 +2839,7 @@ xfs_bmap_add_extent_hole_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2794,6 +2870,7 @@ xfs_bmap_add_extent_hole_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2820,6 +2897,7 @@ xfs_bmap_add_extent_hole_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 0)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2827,6 +2905,7 @@ xfs_bmap_add_extent_hole_real(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2853,7 +2932,7 @@ xfs_bmap_add_extent_hole_real(
/* clear out the allocated field, done with it now in any case. */
if (cur)
- cur->bc_ino.allocated = 0;
+ cur->bc_bmap.allocated = 0;
xfs_bmap_check_leaf_extents(cur, ip, whichfork);
done:
@@ -3898,14 +3977,18 @@ xfs_bmapi_read(
ASSERT(*nmap >= 1);
ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK | XFS_BMAPI_ENTIRE)));
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED|XFS_ILOCK_EXCL));
+ xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL);
- if (WARN_ON_ONCE(!ifp))
+ if (WARN_ON_ONCE(!ifp)) {
+ xfs_bmap_mark_sick(ip, whichfork);
return -EFSCORRUPTED;
+ }
if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
- XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT))
+ XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+ xfs_bmap_mark_sick(ip, whichfork);
return -EFSCORRUPTED;
+ }
if (xfs_is_shutdown(mp))
return -EIO;
@@ -4160,9 +4243,8 @@ xfs_bmapi_allocate(
*/
bma->nallocs++;
- if (bma->cur)
- bma->cur->bc_ino.flags =
- bma->wasdel ? XFS_BTCUR_BMBT_WASDEL : 0;
+ if (bma->cur && bma->wasdel)
+ bma->cur->bc_flags |= XFS_BTREE_BMBT_WASDEL;
bma->got.br_startoff = bma->offset;
bma->got.br_startblock = bma->blkno;
@@ -4369,7 +4451,7 @@ xfs_bmapi_write(
ASSERT(tp != NULL);
ASSERT(len > 0);
ASSERT(ifp->if_format != XFS_DINODE_FMT_LOCAL);
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+ xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
ASSERT(!(flags & XFS_BMAPI_REMAP));
/* zeroing is for currently only for data extents, not metadata */
@@ -4386,6 +4468,7 @@ xfs_bmapi_write(
if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+ xfs_bmap_mark_sick(ip, whichfork);
return -EFSCORRUPTED;
}
@@ -4613,9 +4696,11 @@ xfs_bmapi_convert_delalloc(
error = -ENOSPC;
if (WARN_ON_ONCE(bma.blkno == NULLFSBLOCK))
goto out_finish;
- error = -EFSCORRUPTED;
- if (WARN_ON_ONCE(!xfs_valid_startblock(ip, bma.got.br_startblock)))
+ if (WARN_ON_ONCE(!xfs_valid_startblock(ip, bma.got.br_startblock))) {
+ xfs_bmap_mark_sick(ip, whichfork);
+ error = -EFSCORRUPTED;
goto out_finish;
+ }
XFS_STATS_ADD(mp, xs_xstrat_bytes, XFS_FSB_TO_B(mp, bma.length));
XFS_STATS_INC(mp, xs_xstrat_quick);
@@ -4666,7 +4751,7 @@ xfs_bmapi_remap(
ifp = xfs_ifork_ptr(ip, whichfork);
ASSERT(len > 0);
ASSERT(len <= (xfs_filblks_t)XFS_MAX_BMBT_EXTLEN);
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+ xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK | XFS_BMAPI_PREALLOC |
XFS_BMAPI_NORMAP)));
ASSERT((flags & (XFS_BMAPI_ATTRFORK | XFS_BMAPI_PREALLOC)) !=
@@ -4674,6 +4759,7 @@ xfs_bmapi_remap(
if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+ xfs_bmap_mark_sick(ip, whichfork);
return -EFSCORRUPTED;
}
@@ -4693,10 +4779,8 @@ xfs_bmapi_remap(
ip->i_nblocks += len;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
- if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
+ if (ifp->if_format == XFS_DINODE_FMT_BTREE)
cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
- cur->bc_ino.flags = 0;
- }
got.br_startoff = bno;
got.br_startblock = startblock;
@@ -4831,7 +4915,7 @@ xfs_bmap_del_extent_delay(
XFS_STATS_INC(mp, xs_del_exlist);
- isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip);
+ isrt = xfs_ifork_is_realtime(ip, whichfork);
del_endoff = del->br_startoff + del->br_blockcount;
got_endoff = got->br_startoff + got->br_blockcount;
da_old = startblockval(got->br_startblock);
@@ -5067,7 +5151,7 @@ xfs_bmap_del_extent_real(
return -ENOSPC;
*logflagsp = XFS_ILOG_CORE;
- if (whichfork == XFS_DATA_FORK && XFS_IS_REALTIME_INODE(ip)) {
+ if (xfs_ifork_is_realtime(ip, whichfork)) {
if (!(bflags & XFS_BMAPI_REMAP)) {
error = xfs_rtfree_blocks(tp, del->br_startblock,
del->br_blockcount);
@@ -5088,8 +5172,10 @@ xfs_bmap_del_extent_real(
error = xfs_bmbt_lookup_eq(cur, &got, &i);
if (error)
return error;
- if (XFS_IS_CORRUPT(mp, i != 1))
+ if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
}
if (got.br_startoff == del->br_startoff)
@@ -5113,8 +5199,10 @@ xfs_bmap_del_extent_real(
}
if ((error = xfs_btree_delete(cur, &i)))
return error;
- if (XFS_IS_CORRUPT(mp, i != 1))
+ if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
break;
case BMAP_LEFT_FILLING:
/*
@@ -5186,8 +5274,10 @@ xfs_bmap_del_extent_real(
error = xfs_bmbt_lookup_eq(cur, &got, &i);
if (error)
return error;
- if (XFS_IS_CORRUPT(mp, i != 1))
+ if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
/*
* Update the btree record back
* to the original value.
@@ -5203,8 +5293,10 @@ xfs_bmap_del_extent_real(
*logflagsp = 0;
return -ENOSPC;
}
- if (XFS_IS_CORRUPT(mp, i != 1))
+ if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
} else
*logflagsp |= xfs_ilog_fext(whichfork);
@@ -5286,12 +5378,14 @@ __xfs_bunmapi(
whichfork = xfs_bmapi_whichfork(flags);
ASSERT(whichfork != XFS_COW_FORK);
ifp = xfs_ifork_ptr(ip, whichfork);
- if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)))
+ if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp))) {
+ xfs_bmap_mark_sick(ip, whichfork);
return -EFSCORRUPTED;
+ }
if (xfs_is_shutdown(mp))
return -EIO;
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+ xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
ASSERT(len > 0);
ASSERT(nexts >= 0);
@@ -5304,7 +5398,7 @@ __xfs_bunmapi(
return 0;
}
XFS_STATS_INC(mp, xs_blk_unmap);
- isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip);
+ isrt = xfs_ifork_is_realtime(ip, whichfork);
end = start + len;
if (!xfs_iext_lookup_extent_before(ip, ifp, &end, &icur, &got)) {
@@ -5317,7 +5411,6 @@ __xfs_bunmapi(
if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
ASSERT(ifp->if_format == XFS_DINODE_FMT_BTREE);
cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
- cur->bc_ino.flags = 0;
} else
cur = NULL;
@@ -5367,7 +5460,7 @@ __xfs_bunmapi(
if (del.br_startoff + del.br_blockcount > end + 1)
del.br_blockcount = end + 1 - del.br_startoff;
- if (!isrt)
+ if (!isrt || (flags & XFS_BMAPI_REMAP))
goto delete;
mod = xfs_rtb_to_rtxoff(mp,
@@ -5385,7 +5478,7 @@ __xfs_bunmapi(
* This piece is unwritten, or we're not
* using unwritten extents. Skip over it.
*/
- ASSERT(end >= mod);
+ ASSERT((flags & XFS_BMAPI_REMAP) || end >= mod);
end -= mod > del.br_blockcount ?
del.br_blockcount : mod;
if (end < got.br_startoff &&
@@ -5555,7 +5648,7 @@ error0:
xfs_trans_log_inode(tp, ip, logflags);
if (cur) {
if (!error)
- cur->bc_ino.allocated = 0;
+ cur->bc_bmap.allocated = 0;
xfs_btree_del_cursor(cur, error);
}
return error;
@@ -5635,8 +5728,7 @@ xfs_bmse_merge(
blockcount = left->br_blockcount + got->br_blockcount;
- ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+ xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
ASSERT(xfs_bmse_can_merge(left, got, shift));
new = *left;
@@ -5657,21 +5749,27 @@ xfs_bmse_merge(
error = xfs_bmbt_lookup_eq(cur, got, &i);
if (error)
return error;
- if (XFS_IS_CORRUPT(mp, i != 1))
+ if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
error = xfs_btree_delete(cur, &i);
if (error)
return error;
- if (XFS_IS_CORRUPT(mp, i != 1))
+ if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
/* lookup and update size of the previous extent */
error = xfs_bmbt_lookup_eq(cur, left, &i);
if (error)
return error;
- if (XFS_IS_CORRUPT(mp, i != 1))
+ if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
error = xfs_bmbt_update(cur, &new);
if (error)
@@ -5719,8 +5817,10 @@ xfs_bmap_shift_update_extent(
error = xfs_bmbt_lookup_eq(cur, &prev, &i);
if (error)
return error;
- if (XFS_IS_CORRUPT(mp, i != 1))
+ if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
error = xfs_bmbt_update(cur, got);
if (error)
@@ -5758,28 +5858,28 @@ xfs_bmap_collapse_extents(
if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+ xfs_bmap_mark_sick(ip, whichfork);
return -EFSCORRUPTED;
}
if (xfs_is_shutdown(mp))
return -EIO;
- ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL));
+ xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
error = xfs_iread_extents(tp, ip, whichfork);
if (error)
return error;
- if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
+ if (ifp->if_format == XFS_DINODE_FMT_BTREE)
cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
- cur->bc_ino.flags = 0;
- }
if (!xfs_iext_lookup_extent(ip, ifp, *next_fsb, &icur, &got)) {
*done = true;
goto del_cursor;
}
if (XFS_IS_CORRUPT(mp, isnullstartblock(got.br_startblock))) {
+ xfs_bmap_mark_sick(ip, whichfork);
error = -EFSCORRUPTED;
goto del_cursor;
}
@@ -5837,7 +5937,7 @@ xfs_bmap_can_insert_extents(
int is_empty;
int error = 0;
- ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
+ xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL);
if (xfs_is_shutdown(ip->i_mount))
return -EIO;
@@ -5873,22 +5973,21 @@ xfs_bmap_insert_extents(
if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+ xfs_bmap_mark_sick(ip, whichfork);
return -EFSCORRUPTED;
}
if (xfs_is_shutdown(mp))
return -EIO;
- ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL));
+ xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
error = xfs_iread_extents(tp, ip, whichfork);
if (error)
return error;
- if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
+ if (ifp->if_format == XFS_DINODE_FMT_BTREE)
cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
- cur->bc_ino.flags = 0;
- }
if (*next_fsb == NULLFSBLOCK) {
xfs_iext_last(ifp, &icur);
@@ -5904,11 +6003,13 @@ xfs_bmap_insert_extents(
}
}
if (XFS_IS_CORRUPT(mp, isnullstartblock(got.br_startblock))) {
+ xfs_bmap_mark_sick(ip, whichfork);
error = -EFSCORRUPTED;
goto del_cursor;
}
if (XFS_IS_CORRUPT(mp, stop_fsb > got.br_startoff)) {
+ xfs_bmap_mark_sick(ip, whichfork);
error = -EFSCORRUPTED;
goto del_cursor;
}
@@ -5976,6 +6077,7 @@ xfs_bmap_split_extent(
if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)) ||
XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+ xfs_bmap_mark_sick(ip, whichfork);
return -EFSCORRUPTED;
}
@@ -6002,11 +6104,11 @@ xfs_bmap_split_extent(
if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
- cur->bc_ino.flags = 0;
error = xfs_bmbt_lookup_eq(cur, &got, &i);
if (error)
goto del_cursor;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto del_cursor;
}
@@ -6034,6 +6136,7 @@ xfs_bmap_split_extent(
if (error)
goto del_cursor;
if (XFS_IS_CORRUPT(mp, i != 0)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto del_cursor;
}
@@ -6041,6 +6144,7 @@ xfs_bmap_split_extent(
if (error)
goto del_cursor;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto del_cursor;
}
@@ -6060,7 +6164,7 @@ xfs_bmap_split_extent(
del_cursor:
if (cur) {
- cur->bc_ino.allocated = 0;
+ cur->bc_bmap.allocated = 0;
xfs_btree_del_cursor(cur, error);
}
@@ -6069,17 +6173,8 @@ del_cursor:
return error;
}
-/* Deferred mapping is only for real extents in the data fork. */
-static bool
-xfs_bmap_is_update_needed(
- struct xfs_bmbt_irec *bmap)
-{
- return bmap->br_startblock != HOLESTARTBLOCK &&
- bmap->br_startblock != DELAYSTARTBLOCK;
-}
-
/* Record a bmap intent. */
-static int
+static inline void
__xfs_bmap_add(
struct xfs_trans *tp,
enum xfs_bmap_intent_type type,
@@ -6089,25 +6184,19 @@ __xfs_bmap_add(
{
struct xfs_bmap_intent *bi;
- trace_xfs_bmap_defer(tp->t_mountp,
- XFS_FSB_TO_AGNO(tp->t_mountp, bmap->br_startblock),
- type,
- XFS_FSB_TO_AGBNO(tp->t_mountp, bmap->br_startblock),
- ip->i_ino, whichfork,
- bmap->br_startoff,
- bmap->br_blockcount,
- bmap->br_state);
+ if ((whichfork != XFS_DATA_FORK && whichfork != XFS_ATTR_FORK) ||
+ bmap->br_startblock == HOLESTARTBLOCK ||
+ bmap->br_startblock == DELAYSTARTBLOCK)
+ return;
- bi = kmem_cache_alloc(xfs_bmap_intent_cache, GFP_NOFS | __GFP_NOFAIL);
+ bi = kmem_cache_alloc(xfs_bmap_intent_cache, GFP_KERNEL | __GFP_NOFAIL);
INIT_LIST_HEAD(&bi->bi_list);
bi->bi_type = type;
bi->bi_owner = ip;
bi->bi_whichfork = whichfork;
bi->bi_bmap = *bmap;
- xfs_bmap_update_get_group(tp->t_mountp, bi);
- xfs_defer_add(tp, &bi->bi_list, &xfs_bmap_update_defer_type);
- return 0;
+ xfs_bmap_defer_add(tp, bi);
}
/* Map an extent into a file. */
@@ -6115,12 +6204,10 @@ void
xfs_bmap_map_extent(
struct xfs_trans *tp,
struct xfs_inode *ip,
+ int whichfork,
struct xfs_bmbt_irec *PREV)
{
- if (!xfs_bmap_is_update_needed(PREV))
- return;
-
- __xfs_bmap_add(tp, XFS_BMAP_MAP, ip, XFS_DATA_FORK, PREV);
+ __xfs_bmap_add(tp, XFS_BMAP_MAP, ip, whichfork, PREV);
}
/* Unmap an extent out of a file. */
@@ -6128,12 +6215,10 @@ void
xfs_bmap_unmap_extent(
struct xfs_trans *tp,
struct xfs_inode *ip,
+ int whichfork,
struct xfs_bmbt_irec *PREV)
{
- if (!xfs_bmap_is_update_needed(PREV))
- return;
-
- __xfs_bmap_add(tp, XFS_BMAP_UNMAP, ip, XFS_DATA_FORK, PREV);
+ __xfs_bmap_add(tp, XFS_BMAP_UNMAP, ip, whichfork, PREV);
}
/*
@@ -6147,36 +6232,35 @@ xfs_bmap_finish_one(
{
struct xfs_bmbt_irec *bmap = &bi->bi_bmap;
int error = 0;
+ int flags = 0;
- ASSERT(tp->t_highest_agno == NULLAGNUMBER);
+ if (bi->bi_whichfork == XFS_ATTR_FORK)
+ flags |= XFS_BMAPI_ATTRFORK;
- trace_xfs_bmap_deferred(tp->t_mountp,
- XFS_FSB_TO_AGNO(tp->t_mountp, bmap->br_startblock),
- bi->bi_type,
- XFS_FSB_TO_AGBNO(tp->t_mountp, bmap->br_startblock),
- bi->bi_owner->i_ino, bi->bi_whichfork,
- bmap->br_startoff, bmap->br_blockcount,
- bmap->br_state);
+ ASSERT(tp->t_highest_agno == NULLAGNUMBER);
- if (WARN_ON_ONCE(bi->bi_whichfork != XFS_DATA_FORK))
- return -EFSCORRUPTED;
+ trace_xfs_bmap_deferred(bi);
- if (XFS_TEST_ERROR(false, tp->t_mountp,
- XFS_ERRTAG_BMAP_FINISH_ONE))
+ if (XFS_TEST_ERROR(false, tp->t_mountp, XFS_ERRTAG_BMAP_FINISH_ONE))
return -EIO;
switch (bi->bi_type) {
case XFS_BMAP_MAP:
+ if (bi->bi_bmap.br_state == XFS_EXT_UNWRITTEN)
+ flags |= XFS_BMAPI_PREALLOC;
error = xfs_bmapi_remap(tp, bi->bi_owner, bmap->br_startoff,
- bmap->br_blockcount, bmap->br_startblock, 0);
+ bmap->br_blockcount, bmap->br_startblock,
+ flags);
bmap->br_blockcount = 0;
break;
case XFS_BMAP_UNMAP:
error = __xfs_bunmapi(tp, bi->bi_owner, bmap->br_startoff,
- &bmap->br_blockcount, XFS_BMAPI_REMAP, 1);
+ &bmap->br_blockcount, flags | XFS_BMAPI_REMAP,
+ 1);
break;
default:
ASSERT(0);
+ xfs_bmap_mark_sick(bi->bi_owner, bi->bi_whichfork);
error = -EFSCORRUPTED;
}
@@ -6257,7 +6341,7 @@ xfs_bunmapi_range(
xfs_filblks_t unmap_len = endoff - startoff + 1;
int error = 0;
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+ xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
while (unmap_len > 0) {
ASSERT((*tpp)->t_highest_agno == NULLAGNUMBER);
@@ -6274,3 +6358,46 @@ xfs_bunmapi_range(
out:
return error;
}
+
+struct xfs_bmap_query_range {
+ xfs_bmap_query_range_fn fn;
+ void *priv;
+};
+
+/* Format btree record and pass to our callback. */
+STATIC int
+xfs_bmap_query_range_helper(
+ struct xfs_btree_cur *cur,
+ const union xfs_btree_rec *rec,
+ void *priv)
+{
+ struct xfs_bmap_query_range *query = priv;
+ struct xfs_bmbt_irec irec;
+ xfs_failaddr_t fa;
+
+ xfs_bmbt_disk_get_all(&rec->bmbt, &irec);
+ fa = xfs_bmap_validate_extent(cur->bc_ino.ip, cur->bc_ino.whichfork,
+ &irec);
+ if (fa) {
+ xfs_btree_mark_sick(cur);
+ return xfs_bmap_complain_bad_rec(cur->bc_ino.ip,
+ cur->bc_ino.whichfork, fa, &irec);
+ }
+
+ return query->fn(cur, &irec, query->priv);
+}
+
+/* Find all bmaps. */
+int
+xfs_bmap_query_all(
+ struct xfs_btree_cur *cur,
+ xfs_bmap_query_range_fn fn,
+ void *priv)
+{
+ struct xfs_bmap_query_range query = {
+ .priv = priv,
+ .fn = fn,
+ };
+
+ return xfs_btree_query_all(cur, xfs_bmap_query_range_helper, &query);
+}
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index f6b73f1bad..f766259530 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -232,6 +232,10 @@ enum xfs_bmap_intent_type {
XFS_BMAP_UNMAP,
};
+#define XFS_BMAP_INTENT_STRINGS \
+ { XFS_BMAP_MAP, "map" }, \
+ { XFS_BMAP_UNMAP, "unmap" }
+
struct xfs_bmap_intent {
struct list_head bi_list;
enum xfs_bmap_intent_type bi_type;
@@ -241,14 +245,11 @@ struct xfs_bmap_intent {
struct xfs_bmbt_irec bi_bmap;
};
-void xfs_bmap_update_get_group(struct xfs_mount *mp,
- struct xfs_bmap_intent *bi);
-
int xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_bmap_intent *bi);
void xfs_bmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip,
- struct xfs_bmbt_irec *imap);
+ int whichfork, struct xfs_bmbt_irec *imap);
void xfs_bmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip,
- struct xfs_bmbt_irec *imap);
+ int whichfork, struct xfs_bmbt_irec *imap);
static inline uint32_t xfs_bmap_fork_to_state(int whichfork)
{
@@ -280,4 +281,12 @@ extern struct kmem_cache *xfs_bmap_intent_cache;
int __init xfs_bmap_intent_init_cache(void);
void xfs_bmap_intent_destroy_cache(void);
+typedef int (*xfs_bmap_query_range_fn)(
+ struct xfs_btree_cur *cur,
+ struct xfs_bmbt_irec *rec,
+ void *priv);
+
+int xfs_bmap_query_all(struct xfs_btree_cur *cur, xfs_bmap_query_range_fn fn,
+ void *priv);
+
#endif /* __XFS_BMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 71f2d50f78..f5d84dcb58 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -26,6 +26,22 @@
static struct kmem_cache *xfs_bmbt_cur_cache;
+void
+xfs_bmbt_init_block(
+ struct xfs_inode *ip,
+ struct xfs_btree_block *buf,
+ struct xfs_buf *bp,
+ __u16 level,
+ __u16 numrecs)
+{
+ if (bp)
+ xfs_btree_init_buf(ip->i_mount, bp, &xfs_bmbt_ops, level,
+ numrecs, ip->i_ino);
+ else
+ xfs_btree_init_block(ip->i_mount, buf, &xfs_bmbt_ops, level,
+ numrecs, ip->i_ino);
+}
+
/*
* Convert on-disk form of btree root to in-memory form.
*/
@@ -44,9 +60,7 @@ xfs_bmdr_to_bmbt(
xfs_bmbt_key_t *tkp;
__be64 *tpp;
- xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL,
- XFS_BTNUM_BMAP, 0, 0, ip->i_ino,
- XFS_BTREE_LONG_PTRS);
+ xfs_bmbt_init_block(ip, rblock, NULL, 0, 0);
rblock->bb_level = dblock->bb_level;
ASSERT(be16_to_cpu(rblock->bb_level) > 0);
rblock->bb_numrecs = dblock->bb_numrecs;
@@ -171,13 +185,8 @@ xfs_bmbt_dup_cursor(
new = xfs_bmbt_init_cursor(cur->bc_mp, cur->bc_tp,
cur->bc_ino.ip, cur->bc_ino.whichfork);
-
- /*
- * Copy the firstblock, dfops, and flags values,
- * since init cursor doesn't get them.
- */
- new->bc_ino.flags = cur->bc_ino.flags;
-
+ new->bc_flags |= (cur->bc_flags &
+ (XFS_BTREE_BMBT_INVALID_OWNER | XFS_BTREE_BMBT_WASDEL));
return new;
}
@@ -189,10 +198,10 @@ xfs_bmbt_update_cursor(
ASSERT((dst->bc_tp->t_highest_agno != NULLAGNUMBER) ||
(dst->bc_ino.ip->i_diflags & XFS_DIFLAG_REALTIME));
- dst->bc_ino.allocated += src->bc_ino.allocated;
+ dst->bc_bmap.allocated += src->bc_bmap.allocated;
dst->bc_tp->t_highest_agno = src->bc_tp->t_highest_agno;
- src->bc_ino.allocated = 0;
+ src->bc_bmap.allocated = 0;
}
STATIC int
@@ -211,7 +220,7 @@ xfs_bmbt_alloc_block(
xfs_rmap_ino_bmbt_owner(&args.oinfo, cur->bc_ino.ip->i_ino,
cur->bc_ino.whichfork);
args.minlen = args.maxlen = args.prod = 1;
- args.wasdel = cur->bc_ino.flags & XFS_BTCUR_BMBT_WASDEL;
+ args.wasdel = cur->bc_flags & XFS_BTREE_BMBT_WASDEL;
if (!args.wasdel && args.tp->t_blk_res == 0)
return -ENOSPC;
@@ -247,7 +256,7 @@ xfs_bmbt_alloc_block(
}
ASSERT(args.len == 1);
- cur->bc_ino.allocated++;
+ cur->bc_bmap.allocated++;
cur->bc_ino.ip->i_nblocks++;
xfs_trans_log_inode(args.tp, cur->bc_ino.ip, XFS_ILOG_CORE);
xfs_trans_mod_dquot_byino(args.tp, cur->bc_ino.ip,
@@ -360,14 +369,6 @@ xfs_bmbt_init_rec_from_cur(
xfs_bmbt_disk_set_all(&rec->bmbt, &cur->bc_rec.b);
}
-STATIC void
-xfs_bmbt_init_ptr_from_cur(
- struct xfs_btree_cur *cur,
- union xfs_btree_ptr *ptr)
-{
- ptr->l = 0;
-}
-
STATIC int64_t
xfs_bmbt_key_diff(
struct xfs_btree_cur *cur,
@@ -419,7 +420,7 @@ xfs_bmbt_verify(
* XXX: need a better way of verifying the owner here. Right now
* just make sure there has been one set.
*/
- fa = xfs_btree_lblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN);
+ fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN);
if (fa)
return fa;
}
@@ -435,7 +436,7 @@ xfs_bmbt_verify(
if (level > max(mp->m_bm_maxlevels[0], mp->m_bm_maxlevels[1]))
return __this_address;
- return xfs_btree_lblock_verify(bp, mp->m_bmap_dmxr[level != 0]);
+ return xfs_btree_fsblock_verify(bp, mp->m_bmap_dmxr[level != 0]);
}
static void
@@ -444,7 +445,7 @@ xfs_bmbt_read_verify(
{
xfs_failaddr_t fa;
- if (!xfs_btree_lblock_verify_crc(bp))
+ if (!xfs_btree_fsblock_verify_crc(bp))
xfs_verifier_error(bp, -EFSBADCRC, __this_address);
else {
fa = xfs_bmbt_verify(bp);
@@ -468,7 +469,7 @@ xfs_bmbt_write_verify(
xfs_verifier_error(bp, -EFSCORRUPTED, fa);
return;
}
- xfs_btree_lblock_calc_crc(bp);
+ xfs_btree_fsblock_calc_crc(bp);
}
const struct xfs_buf_ops xfs_bmbt_buf_ops = {
@@ -515,9 +516,16 @@ xfs_bmbt_keys_contiguous(
be64_to_cpu(key2->bmbt.br_startoff));
}
-static const struct xfs_btree_ops xfs_bmbt_ops = {
+const struct xfs_btree_ops xfs_bmbt_ops = {
+ .name = "bmap",
+ .type = XFS_BTREE_TYPE_INODE,
+
.rec_len = sizeof(xfs_bmbt_rec_t),
.key_len = sizeof(xfs_bmbt_key_t),
+ .ptr_len = XFS_BTREE_LONG_PTR_LEN,
+
+ .lru_refs = XFS_BMAP_BTREE_REF,
+ .statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2),
.dup_cursor = xfs_bmbt_dup_cursor,
.update_cursor = xfs_bmbt_update_cursor,
@@ -529,7 +537,6 @@ static const struct xfs_btree_ops xfs_bmbt_ops = {
.init_key_from_rec = xfs_bmbt_init_key_from_rec,
.init_high_key_from_rec = xfs_bmbt_init_high_key_from_rec,
.init_rec_from_cur = xfs_bmbt_init_rec_from_cur,
- .init_ptr_from_cur = xfs_bmbt_init_ptr_from_cur,
.key_diff = xfs_bmbt_key_diff,
.diff_two_keys = xfs_bmbt_diff_two_keys,
.buf_ops = &xfs_bmbt_buf_ops,
@@ -538,35 +545,10 @@ static const struct xfs_btree_ops xfs_bmbt_ops = {
.keys_contiguous = xfs_bmbt_keys_contiguous,
};
-static struct xfs_btree_cur *
-xfs_bmbt_init_common(
- struct xfs_mount *mp,
- struct xfs_trans *tp,
- struct xfs_inode *ip,
- int whichfork)
-{
- struct xfs_btree_cur *cur;
-
- ASSERT(whichfork != XFS_COW_FORK);
-
- cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_BMAP,
- mp->m_bm_maxlevels[whichfork], xfs_bmbt_cur_cache);
- cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_bmbt_2);
-
- cur->bc_ops = &xfs_bmbt_ops;
- cur->bc_flags = XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE;
- if (xfs_has_crc(mp))
- cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
-
- cur->bc_ino.ip = ip;
- cur->bc_ino.allocated = 0;
- cur->bc_ino.flags = 0;
-
- return cur;
-}
-
/*
- * Allocate a new bmap btree cursor.
+ * Create a new bmap btree cursor.
+ *
+ * For staging cursors -1 in passed in whichfork.
*/
struct xfs_btree_cur *
xfs_bmbt_init_cursor(
@@ -575,15 +557,34 @@ xfs_bmbt_init_cursor(
struct xfs_inode *ip,
int whichfork)
{
- struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_btree_cur *cur;
+ unsigned int maxlevels;
- cur = xfs_bmbt_init_common(mp, tp, ip, whichfork);
+ ASSERT(whichfork != XFS_COW_FORK);
- cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
- cur->bc_ino.forksize = xfs_inode_fork_size(ip, whichfork);
+ /*
+ * The Data fork always has larger maxlevel, so use that for staging
+ * cursors.
+ */
+ switch (whichfork) {
+ case XFS_STAGING_FORK:
+ maxlevels = mp->m_bm_maxlevels[XFS_DATA_FORK];
+ break;
+ default:
+ maxlevels = mp->m_bm_maxlevels[whichfork];
+ break;
+ }
+ cur = xfs_btree_alloc_cursor(mp, tp, &xfs_bmbt_ops, maxlevels,
+ xfs_bmbt_cur_cache);
+ cur->bc_ino.ip = ip;
cur->bc_ino.whichfork = whichfork;
+ cur->bc_bmap.allocated = 0;
+ if (whichfork != XFS_STAGING_FORK) {
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
+ cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
+ cur->bc_ino.forksize = xfs_inode_fork_size(ip, whichfork);
+ }
return cur;
}
@@ -599,33 +600,6 @@ xfs_bmbt_block_maxrecs(
}
/*
- * Allocate a new bmap btree cursor for reloading an inode block mapping data
- * structure. Note that callers can use the staged cursor to reload extents
- * format inode forks if they rebuild the iext tree and commit the staged
- * cursor immediately.
- */
-struct xfs_btree_cur *
-xfs_bmbt_stage_cursor(
- struct xfs_mount *mp,
- struct xfs_inode *ip,
- struct xbtree_ifakeroot *ifake)
-{
- struct xfs_btree_cur *cur;
- struct xfs_btree_ops *ops;
-
- /* data fork always has larger maxheight */
- cur = xfs_bmbt_init_common(mp, NULL, ip, XFS_DATA_FORK);
- cur->bc_nlevels = ifake->if_levels;
- cur->bc_ino.forksize = ifake->if_fork_size;
-
- /* Don't let anyone think we're attached to the real fork yet. */
- cur->bc_ino.whichfork = -1;
- xfs_btree_stage_ifakeroot(cur, ifake, &ops);
- ops->update_cursor = NULL;
- return cur;
-}
-
-/*
* Swap in the new inode fork root. Once we pass this point the newly rebuilt
* mappings are in place and we have to kill off any old btree blocks.
*/
@@ -665,7 +639,7 @@ xfs_bmbt_commit_staged_btree(
break;
}
xfs_trans_log_inode(tp, cur->bc_ino.ip, flags);
- xfs_btree_commit_ifakeroot(cur, tp, whichfork, &xfs_bmbt_ops);
+ xfs_btree_commit_ifakeroot(cur, tp, whichfork);
}
/*
@@ -751,7 +725,7 @@ xfs_bmbt_change_owner(
ASSERT(xfs_ifork_ptr(ip, whichfork)->if_format == XFS_DINODE_FMT_BTREE);
cur = xfs_bmbt_init_cursor(ip->i_mount, tp, ip, whichfork);
- cur->bc_ino.flags |= XFS_BTCUR_BMBT_INVALID_OWNER;
+ cur->bc_flags |= XFS_BTREE_BMBT_INVALID_OWNER;
error = xfs_btree_change_owner(cur, new_owner, buffer_list);
xfs_btree_del_cursor(cur, error);
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.h b/fs/xfs/libxfs/xfs_bmap_btree.h
index 151b8491f6..de1b73f122 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.h
+++ b/fs/xfs/libxfs/xfs_bmap_btree.h
@@ -107,8 +107,6 @@ extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip,
extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
struct xfs_trans *, struct xfs_inode *, int);
-struct xfs_btree_cur *xfs_bmbt_stage_cursor(struct xfs_mount *mp,
- struct xfs_inode *ip, struct xbtree_ifakeroot *ifake);
void xfs_bmbt_commit_staged_btree(struct xfs_btree_cur *cur,
struct xfs_trans *tp, int whichfork);
@@ -120,4 +118,7 @@ unsigned int xfs_bmbt_maxlevels_ondisk(void);
int __init xfs_bmbt_init_cur_cache(void);
void xfs_bmbt_destroy_cur_cache(void);
+void xfs_bmbt_init_block(struct xfs_inode *ip, struct xfs_btree_block *buf,
+ struct xfs_buf *bp, __u16 level, __u16 numrecs);
+
#endif /* __XFS_BMAP_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index ea8d3659df..d29547572a 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -27,28 +27,24 @@
#include "xfs_bmap_btree.h"
#include "xfs_rmap_btree.h"
#include "xfs_refcount_btree.h"
+#include "xfs_health.h"
+#include "xfs_buf_mem.h"
+#include "xfs_btree_mem.h"
/*
* Btree magic numbers.
*/
-static const uint32_t xfs_magics[2][XFS_BTNUM_MAX] = {
- { XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, 0, XFS_BMAP_MAGIC, XFS_IBT_MAGIC,
- XFS_FIBT_MAGIC, 0 },
- { XFS_ABTB_CRC_MAGIC, XFS_ABTC_CRC_MAGIC, XFS_RMAP_CRC_MAGIC,
- XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC, XFS_FIBT_CRC_MAGIC,
- XFS_REFC_CRC_MAGIC }
-};
-
uint32_t
xfs_btree_magic(
- int crc,
- xfs_btnum_t btnum)
+ struct xfs_mount *mp,
+ const struct xfs_btree_ops *ops)
{
- uint32_t magic = xfs_magics[crc][btnum];
+ int idx = xfs_has_crc(mp) ? 1 : 0;
+ __be32 magic = ops->buf_ops->magic[idx];
/* Ensure we asked for crc for crc-only magics. */
ASSERT(magic != 0);
- return magic;
+ return be32_to_cpu(magic);
}
/*
@@ -63,10 +59,8 @@ xfs_btree_magic(
* bytes.
*/
static inline xfs_failaddr_t
-xfs_btree_check_lblock_siblings(
+xfs_btree_check_fsblock_siblings(
struct xfs_mount *mp,
- struct xfs_btree_cur *cur,
- int level,
xfs_fsblock_t fsb,
__be64 dsibling)
{
@@ -78,22 +72,33 @@ xfs_btree_check_lblock_siblings(
sibling = be64_to_cpu(dsibling);
if (sibling == fsb)
return __this_address;
- if (level >= 0) {
- if (!xfs_btree_check_lptr(cur, sibling, level + 1))
- return __this_address;
- } else {
- if (!xfs_verify_fsbno(mp, sibling))
- return __this_address;
- }
+ if (!xfs_verify_fsbno(mp, sibling))
+ return __this_address;
+ return NULL;
+}
+static inline xfs_failaddr_t
+xfs_btree_check_memblock_siblings(
+ struct xfs_buftarg *btp,
+ xfbno_t bno,
+ __be64 dsibling)
+{
+ xfbno_t sibling;
+
+ if (dsibling == cpu_to_be64(NULLFSBLOCK))
+ return NULL;
+
+ sibling = be64_to_cpu(dsibling);
+ if (sibling == bno)
+ return __this_address;
+ if (!xmbuf_verify_daddr(btp, xfbno_to_daddr(sibling)))
+ return __this_address;
return NULL;
}
static inline xfs_failaddr_t
-xfs_btree_check_sblock_siblings(
+xfs_btree_check_agblock_siblings(
struct xfs_perag *pag,
- struct xfs_btree_cur *cur,
- int level,
xfs_agblock_t agbno,
__be32 dsibling)
{
@@ -105,34 +110,21 @@ xfs_btree_check_sblock_siblings(
sibling = be32_to_cpu(dsibling);
if (sibling == agbno)
return __this_address;
- if (level >= 0) {
- if (!xfs_btree_check_sptr(cur, sibling, level + 1))
- return __this_address;
- } else {
- if (!xfs_verify_agbno(pag, sibling))
- return __this_address;
- }
+ if (!xfs_verify_agbno(pag, sibling))
+ return __this_address;
return NULL;
}
-/*
- * Check a long btree block header. Return the address of the failing check,
- * or NULL if everything is ok.
- */
-xfs_failaddr_t
-__xfs_btree_check_lblock(
+static xfs_failaddr_t
+__xfs_btree_check_lblock_hdr(
struct xfs_btree_cur *cur,
struct xfs_btree_block *block,
int level,
struct xfs_buf *bp)
{
struct xfs_mount *mp = cur->bc_mp;
- xfs_btnum_t btnum = cur->bc_btnum;
- int crc = xfs_has_crc(mp);
- xfs_failaddr_t fa;
- xfs_fsblock_t fsb = NULLFSBLOCK;
- if (crc) {
+ if (xfs_has_crc(mp)) {
if (!uuid_equal(&block->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid))
return __this_address;
if (block->bb_u.l.bb_blkno !=
@@ -142,7 +134,7 @@ __xfs_btree_check_lblock(
return __this_address;
}
- if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(crc, btnum))
+ if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(mp, cur->bc_ops))
return __this_address;
if (be16_to_cpu(block->bb_level) != level)
return __this_address;
@@ -150,44 +142,83 @@ __xfs_btree_check_lblock(
cur->bc_ops->get_maxrecs(cur, level))
return __this_address;
- if (bp)
- fsb = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
+ return NULL;
+}
+
+/*
+ * Check a long btree block header. Return the address of the failing check,
+ * or NULL if everything is ok.
+ */
+static xfs_failaddr_t
+__xfs_btree_check_fsblock(
+ struct xfs_btree_cur *cur,
+ struct xfs_btree_block *block,
+ int level,
+ struct xfs_buf *bp)
+{
+ struct xfs_mount *mp = cur->bc_mp;
+ xfs_failaddr_t fa;
+ xfs_fsblock_t fsb;
+
+ fa = __xfs_btree_check_lblock_hdr(cur, block, level, bp);
+ if (fa)
+ return fa;
- fa = xfs_btree_check_lblock_siblings(mp, cur, level, fsb,
+ /*
+ * For inode-rooted btrees, the root block sits in the inode fork. In
+ * that case bp is NULL, and the block must not have any siblings.
+ */
+ if (!bp) {
+ if (block->bb_u.l.bb_leftsib != cpu_to_be64(NULLFSBLOCK))
+ return __this_address;
+ if (block->bb_u.l.bb_rightsib != cpu_to_be64(NULLFSBLOCK))
+ return __this_address;
+ return NULL;
+ }
+
+ fsb = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
+ fa = xfs_btree_check_fsblock_siblings(mp, fsb,
block->bb_u.l.bb_leftsib);
if (!fa)
- fa = xfs_btree_check_lblock_siblings(mp, cur, level, fsb,
+ fa = xfs_btree_check_fsblock_siblings(mp, fsb,
block->bb_u.l.bb_rightsib);
return fa;
}
-/* Check a long btree block header. */
-static int
-xfs_btree_check_lblock(
+/*
+ * Check an in-memory btree block header. Return the address of the failing
+ * check, or NULL if everything is ok.
+ */
+static xfs_failaddr_t
+__xfs_btree_check_memblock(
struct xfs_btree_cur *cur,
struct xfs_btree_block *block,
int level,
struct xfs_buf *bp)
{
- struct xfs_mount *mp = cur->bc_mp;
+ struct xfs_buftarg *btp = cur->bc_mem.xfbtree->target;
xfs_failaddr_t fa;
+ xfbno_t bno;
- fa = __xfs_btree_check_lblock(cur, block, level, bp);
- if (XFS_IS_CORRUPT(mp, fa != NULL) ||
- XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BTREE_CHECK_LBLOCK)) {
- if (bp)
- trace_xfs_btree_corrupt(bp, _RET_IP_);
- return -EFSCORRUPTED;
- }
- return 0;
+ fa = __xfs_btree_check_lblock_hdr(cur, block, level, bp);
+ if (fa)
+ return fa;
+
+ bno = xfs_daddr_to_xfbno(xfs_buf_daddr(bp));
+ fa = xfs_btree_check_memblock_siblings(btp, bno,
+ block->bb_u.l.bb_leftsib);
+ if (!fa)
+ fa = xfs_btree_check_memblock_siblings(btp, bno,
+ block->bb_u.l.bb_rightsib);
+ return fa;
}
/*
* Check a short btree block header. Return the address of the failing check,
* or NULL if everything is ok.
*/
-xfs_failaddr_t
-__xfs_btree_check_sblock(
+static xfs_failaddr_t
+__xfs_btree_check_agblock(
struct xfs_btree_cur *cur,
struct xfs_btree_block *block,
int level,
@@ -195,20 +226,17 @@ __xfs_btree_check_sblock(
{
struct xfs_mount *mp = cur->bc_mp;
struct xfs_perag *pag = cur->bc_ag.pag;
- xfs_btnum_t btnum = cur->bc_btnum;
- int crc = xfs_has_crc(mp);
xfs_failaddr_t fa;
- xfs_agblock_t agbno = NULLAGBLOCK;
+ xfs_agblock_t agbno;
- if (crc) {
+ if (xfs_has_crc(mp)) {
if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid))
return __this_address;
- if (block->bb_u.s.bb_blkno !=
- cpu_to_be64(bp ? xfs_buf_daddr(bp) : XFS_BUF_DADDR_NULL))
+ if (block->bb_u.s.bb_blkno != cpu_to_be64(xfs_buf_daddr(bp)))
return __this_address;
}
- if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(crc, btnum))
+ if (be32_to_cpu(block->bb_magic) != xfs_btree_magic(mp, cur->bc_ops))
return __this_address;
if (be16_to_cpu(block->bb_level) != level)
return __this_address;
@@ -216,36 +244,45 @@ __xfs_btree_check_sblock(
cur->bc_ops->get_maxrecs(cur, level))
return __this_address;
- if (bp)
- agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp));
-
- fa = xfs_btree_check_sblock_siblings(pag, cur, level, agbno,
+ agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp));
+ fa = xfs_btree_check_agblock_siblings(pag, agbno,
block->bb_u.s.bb_leftsib);
if (!fa)
- fa = xfs_btree_check_sblock_siblings(pag, cur, level, agbno,
+ fa = xfs_btree_check_agblock_siblings(pag, agbno,
block->bb_u.s.bb_rightsib);
return fa;
}
-/* Check a short btree block header. */
-STATIC int
-xfs_btree_check_sblock(
+/*
+ * Internal btree block check.
+ *
+ * Return NULL if the block is ok or the address of the failed check otherwise.
+ */
+xfs_failaddr_t
+__xfs_btree_check_block(
struct xfs_btree_cur *cur,
struct xfs_btree_block *block,
int level,
struct xfs_buf *bp)
{
- struct xfs_mount *mp = cur->bc_mp;
- xfs_failaddr_t fa;
-
- fa = __xfs_btree_check_sblock(cur, block, level, bp);
- if (XFS_IS_CORRUPT(mp, fa != NULL) ||
- XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BTREE_CHECK_SBLOCK)) {
- if (bp)
- trace_xfs_btree_corrupt(bp, _RET_IP_);
- return -EFSCORRUPTED;
+ switch (cur->bc_ops->type) {
+ case XFS_BTREE_TYPE_MEM:
+ return __xfs_btree_check_memblock(cur, block, level, bp);
+ case XFS_BTREE_TYPE_AG:
+ return __xfs_btree_check_agblock(cur, block, level, bp);
+ case XFS_BTREE_TYPE_INODE:
+ return __xfs_btree_check_fsblock(cur, block, level, bp);
+ default:
+ ASSERT(0);
+ return __this_address;
}
- return 0;
+}
+
+static inline unsigned int xfs_btree_block_errtag(struct xfs_btree_cur *cur)
+{
+ if (cur->bc_ops->ptr_len == XFS_BTREE_SHORT_PTR_LEN)
+ return XFS_ERRTAG_BTREE_CHECK_SBLOCK;
+ return XFS_ERRTAG_BTREE_CHECK_LBLOCK;
}
/*
@@ -258,34 +295,49 @@ xfs_btree_check_block(
int level, /* level of the btree block */
struct xfs_buf *bp) /* buffer containing block, if any */
{
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
- return xfs_btree_check_lblock(cur, block, level, bp);
- else
- return xfs_btree_check_sblock(cur, block, level, bp);
-}
+ struct xfs_mount *mp = cur->bc_mp;
+ xfs_failaddr_t fa;
-/* Check that this long pointer is valid and points within the fs. */
-bool
-xfs_btree_check_lptr(
- struct xfs_btree_cur *cur,
- xfs_fsblock_t fsbno,
- int level)
-{
- if (level <= 0)
- return false;
- return xfs_verify_fsbno(cur->bc_mp, fsbno);
+ fa = __xfs_btree_check_block(cur, block, level, bp);
+ if (XFS_IS_CORRUPT(mp, fa != NULL) ||
+ XFS_TEST_ERROR(false, mp, xfs_btree_block_errtag(cur))) {
+ if (bp)
+ trace_xfs_btree_corrupt(bp, _RET_IP_);
+ xfs_btree_mark_sick(cur);
+ return -EFSCORRUPTED;
+ }
+ return 0;
}
-/* Check that this short pointer is valid and points within the AG. */
-bool
-xfs_btree_check_sptr(
- struct xfs_btree_cur *cur,
- xfs_agblock_t agbno,
- int level)
+int
+__xfs_btree_check_ptr(
+ struct xfs_btree_cur *cur,
+ const union xfs_btree_ptr *ptr,
+ int index,
+ int level)
{
if (level <= 0)
- return false;
- return xfs_verify_agbno(cur->bc_ag.pag, agbno);
+ return -EFSCORRUPTED;
+
+ switch (cur->bc_ops->type) {
+ case XFS_BTREE_TYPE_MEM:
+ if (!xfbtree_verify_bno(cur->bc_mem.xfbtree,
+ be64_to_cpu((&ptr->l)[index])))
+ return -EFSCORRUPTED;
+ break;
+ case XFS_BTREE_TYPE_INODE:
+ if (!xfs_verify_fsbno(cur->bc_mp,
+ be64_to_cpu((&ptr->l)[index])))
+ return -EFSCORRUPTED;
+ break;
+ case XFS_BTREE_TYPE_AG:
+ if (!xfs_verify_agbno(cur->bc_ag.pag,
+ be32_to_cpu((&ptr->s)[index])))
+ return -EFSCORRUPTED;
+ break;
+ }
+
+ return 0;
}
/*
@@ -299,26 +351,35 @@ xfs_btree_check_ptr(
int index,
int level)
{
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
- if (xfs_btree_check_lptr(cur, be64_to_cpu((&ptr->l)[index]),
- level))
- return 0;
- xfs_err(cur->bc_mp,
-"Inode %llu fork %d: Corrupt btree %d pointer at level %d index %d.",
+ int error;
+
+ error = __xfs_btree_check_ptr(cur, ptr, index, level);
+ if (error) {
+ switch (cur->bc_ops->type) {
+ case XFS_BTREE_TYPE_MEM:
+ xfs_err(cur->bc_mp,
+"In-memory: Corrupt %sbt flags 0x%x pointer at level %d index %d fa %pS.",
+ cur->bc_ops->name, cur->bc_flags, level, index,
+ __this_address);
+ break;
+ case XFS_BTREE_TYPE_INODE:
+ xfs_err(cur->bc_mp,
+"Inode %llu fork %d: Corrupt %sbt pointer at level %d index %d.",
cur->bc_ino.ip->i_ino,
- cur->bc_ino.whichfork, cur->bc_btnum,
+ cur->bc_ino.whichfork, cur->bc_ops->name,
level, index);
- } else {
- if (xfs_btree_check_sptr(cur, be32_to_cpu((&ptr->s)[index]),
- level))
- return 0;
- xfs_err(cur->bc_mp,
-"AG %u: Corrupt btree %d pointer at level %d index %d.",
- cur->bc_ag.pag->pag_agno, cur->bc_btnum,
+ break;
+ case XFS_BTREE_TYPE_AG:
+ xfs_err(cur->bc_mp,
+"AG %u: Corrupt %sbt pointer at level %d index %d.",
+ cur->bc_ag.pag->pag_agno, cur->bc_ops->name,
level, index);
+ break;
+ }
+ xfs_btree_mark_sick(cur);
}
- return -EFSCORRUPTED;
+ return error;
}
#ifdef DEBUG
@@ -336,7 +397,7 @@ xfs_btree_check_ptr(
* it to disk.
*/
void
-xfs_btree_lblock_calc_crc(
+xfs_btree_fsblock_calc_crc(
struct xfs_buf *bp)
{
struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
@@ -350,7 +411,7 @@ xfs_btree_lblock_calc_crc(
}
bool
-xfs_btree_lblock_verify_crc(
+xfs_btree_fsblock_verify_crc(
struct xfs_buf *bp)
{
struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
@@ -374,7 +435,7 @@ xfs_btree_lblock_verify_crc(
* it to disk.
*/
void
-xfs_btree_sblock_calc_crc(
+xfs_btree_agblock_calc_crc(
struct xfs_buf *bp)
{
struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
@@ -388,7 +449,7 @@ xfs_btree_sblock_calc_crc(
}
bool
-xfs_btree_sblock_verify_crc(
+xfs_btree_agblock_verify_crc(
struct xfs_buf *bp)
{
struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
@@ -410,6 +471,17 @@ xfs_btree_free_block(
{
int error;
+ trace_xfs_btree_free_block(cur, bp);
+
+ /*
+ * Don't allow block freeing for a staging cursor, because staging
+ * cursors do not support regular btree modifications.
+ */
+ if (unlikely(cur->bc_flags & XFS_BTREE_STAGING)) {
+ ASSERT(0);
+ return -EFSCORRUPTED;
+ }
+
error = cur->bc_ops->free_block(cur, bp);
if (!error) {
xfs_trans_binval(cur->bc_tp, bp);
@@ -448,33 +520,70 @@ xfs_btree_del_cursor(
* zero, then we should be shut down or on our way to shutdown due to
* cancelling a dirty transaction on error.
*/
- ASSERT(cur->bc_btnum != XFS_BTNUM_BMAP || cur->bc_ino.allocated == 0 ||
+ ASSERT(!xfs_btree_is_bmap(cur->bc_ops) || cur->bc_bmap.allocated == 0 ||
xfs_is_shutdown(cur->bc_mp) || error != 0);
- if (unlikely(cur->bc_flags & XFS_BTREE_STAGING))
- kmem_free(cur->bc_ops);
- if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) && cur->bc_ag.pag)
- xfs_perag_put(cur->bc_ag.pag);
+
+ switch (cur->bc_ops->type) {
+ case XFS_BTREE_TYPE_AG:
+ if (cur->bc_ag.pag)
+ xfs_perag_put(cur->bc_ag.pag);
+ break;
+ case XFS_BTREE_TYPE_INODE:
+ /* nothing to do */
+ break;
+ case XFS_BTREE_TYPE_MEM:
+ if (cur->bc_mem.pag)
+ xfs_perag_put(cur->bc_mem.pag);
+ break;
+ }
+
kmem_cache_free(cur->bc_cache, cur);
}
+/* Return the buffer target for this btree's buffer. */
+static inline struct xfs_buftarg *
+xfs_btree_buftarg(
+ struct xfs_btree_cur *cur)
+{
+ if (cur->bc_ops->type == XFS_BTREE_TYPE_MEM)
+ return cur->bc_mem.xfbtree->target;
+ return cur->bc_mp->m_ddev_targp;
+}
+
+/* Return the block size (in units of 512b sectors) for this btree. */
+static inline unsigned int
+xfs_btree_bbsize(
+ struct xfs_btree_cur *cur)
+{
+ if (cur->bc_ops->type == XFS_BTREE_TYPE_MEM)
+ return XFBNO_BBSIZE;
+ return cur->bc_mp->m_bsize;
+}
+
/*
* Duplicate the btree cursor.
* Allocate a new one, copy the record, re-get the buffers.
*/
-int /* error */
+int /* error */
xfs_btree_dup_cursor(
- struct xfs_btree_cur *cur, /* input cursor */
- struct xfs_btree_cur **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 */
- struct xfs_btree_cur *new; /* new cursor value */
- xfs_trans_t *tp; /* transaction pointer, can be NULL */
+ struct xfs_mount *mp = cur->bc_mp;
+ struct xfs_trans *tp = cur->bc_tp;
+ struct xfs_buf *bp;
+ struct xfs_btree_cur *new;
+ int error;
+ int i;
- tp = cur->bc_tp;
- mp = cur->bc_mp;
+ /*
+ * Don't allow staging cursors to be duplicated because they're supposed
+ * to be kept private to a single thread.
+ */
+ if (unlikely(cur->bc_flags & XFS_BTREE_STAGING)) {
+ ASSERT(0);
+ return -EFSCORRUPTED;
+ }
/*
* Allocate a new cursor like the old one.
@@ -494,10 +603,13 @@ xfs_btree_dup_cursor(
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,
- 0, &bp,
- cur->bc_ops->buf_ops);
+ error = xfs_trans_read_buf(mp, tp,
+ xfs_btree_buftarg(cur),
+ xfs_buf_daddr(bp),
+ xfs_btree_bbsize(cur), 0, &bp,
+ cur->bc_ops->buf_ops);
+ if (xfs_metadata_is_sick(error))
+ xfs_btree_mark_sick(new);
if (error) {
xfs_btree_del_cursor(new, error);
*ncur = NULL;
@@ -539,7 +651,7 @@ xfs_btree_dup_cursor(
* record, key or pointer (xfs_btree_*_addr). Note that all addressing
* inside the btree block is done using indices starting at one, not zero!
*
- * If XFS_BTREE_OVERLAPPING is set, then this btree supports keys containing
+ * If XFS_BTGEO_OVERLAPPING is set, then this btree supports keys containing
* overlapping intervals. In such a tree, records are still sorted lowest to
* highest and indexed by the smallest key value that refers to the record.
* However, nodes are different: each pointer has two associated keys -- one
@@ -589,26 +701,17 @@ xfs_btree_dup_cursor(
*/
static inline size_t xfs_btree_block_len(struct xfs_btree_cur *cur)
{
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
- if (cur->bc_flags & XFS_BTREE_CRC_BLOCKS)
+ if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) {
+ if (xfs_has_crc(cur->bc_mp))
return XFS_BTREE_LBLOCK_CRC_LEN;
return XFS_BTREE_LBLOCK_LEN;
}
- if (cur->bc_flags & XFS_BTREE_CRC_BLOCKS)
+ if (xfs_has_crc(cur->bc_mp))
return XFS_BTREE_SBLOCK_CRC_LEN;
return XFS_BTREE_SBLOCK_LEN;
}
/*
- * Return size of btree block pointers for this btree instance.
- */
-static inline size_t xfs_btree_ptr_len(struct xfs_btree_cur *cur)
-{
- return (cur->bc_flags & XFS_BTREE_LONG_PTRS) ?
- sizeof(__be64) : sizeof(__be32);
-}
-
-/*
* Calculate offset of the n-th record in a btree block.
*/
STATIC size_t
@@ -655,7 +758,7 @@ xfs_btree_ptr_offset(
{
return xfs_btree_block_len(cur) +
cur->bc_ops->get_maxrecs(cur, level) * cur->bc_ops->key_len +
- (n - 1) * xfs_btree_ptr_len(cur);
+ (n - 1) * cur->bc_ops->ptr_len;
}
/*
@@ -718,7 +821,7 @@ struct xfs_ifork *
xfs_btree_ifork_ptr(
struct xfs_btree_cur *cur)
{
- ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE);
+ ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE);
if (cur->bc_flags & XFS_BTREE_STAGING)
return cur->bc_ino.ifake->if_fork;
@@ -750,8 +853,7 @@ xfs_btree_get_block(
int level, /* level in btree */
struct xfs_buf **bpp) /* buffer containing the block */
{
- if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
- (level == cur->bc_nlevels - 1)) {
+ if (xfs_btree_at_iroot(cur, level)) {
*bpp = NULL;
return xfs_btree_get_iroot(cur);
}
@@ -856,95 +958,52 @@ xfs_btree_offsets(
}
}
-/*
- * Get a buffer for the block, return it read in.
- * Long-form addressing.
- */
-int
-xfs_btree_read_bufl(
- struct xfs_mount *mp, /* file system mount point */
- struct xfs_trans *tp, /* transaction pointer */
- xfs_fsblock_t fsbno, /* file system block number */
- struct xfs_buf **bpp, /* buffer for fsbno */
- int refval, /* ref count value for buffer */
- const struct xfs_buf_ops *ops)
-{
- struct xfs_buf *bp; /* return value */
- xfs_daddr_t d; /* real disk block address */
- int error;
-
- if (!xfs_verify_fsbno(mp, fsbno))
- return -EFSCORRUPTED;
- d = XFS_FSB_TO_DADDR(mp, fsbno);
- error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, d,
- mp->m_bsize, 0, &bp, ops);
- if (error)
- return error;
- if (bp)
- xfs_buf_set_ref(bp, refval);
- *bpp = bp;
- return 0;
-}
-
-/*
- * Read-ahead the block, don't wait for it, don't return a buffer.
- * Long-form addressing.
- */
-/* ARGSUSED */
-void
-xfs_btree_reada_bufl(
- struct xfs_mount *mp, /* file system mount point */
- xfs_fsblock_t fsbno, /* file system block number */
- xfs_extlen_t count, /* count of filesystem blocks */
- const struct xfs_buf_ops *ops)
+STATIC int
+xfs_btree_readahead_fsblock(
+ struct xfs_btree_cur *cur,
+ int lr,
+ struct xfs_btree_block *block)
{
- xfs_daddr_t d;
+ struct xfs_mount *mp = cur->bc_mp;
+ xfs_fsblock_t left = be64_to_cpu(block->bb_u.l.bb_leftsib);
+ xfs_fsblock_t right = be64_to_cpu(block->bb_u.l.bb_rightsib);
+ int rval = 0;
- ASSERT(fsbno != NULLFSBLOCK);
- d = XFS_FSB_TO_DADDR(mp, fsbno);
- xfs_buf_readahead(mp->m_ddev_targp, d, mp->m_bsize * count, ops);
-}
+ if ((lr & XFS_BTCUR_LEFTRA) && left != NULLFSBLOCK) {
+ xfs_buf_readahead(mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, left),
+ mp->m_bsize, cur->bc_ops->buf_ops);
+ rval++;
+ }
-/*
- * Read-ahead the block, don't wait for it, don't return a buffer.
- * Short-form addressing.
- */
-/* ARGSUSED */
-void
-xfs_btree_reada_bufs(
- struct xfs_mount *mp, /* file system mount point */
- xfs_agnumber_t agno, /* allocation group number */
- xfs_agblock_t agbno, /* allocation group block number */
- xfs_extlen_t count, /* count of filesystem blocks */
- const struct xfs_buf_ops *ops)
-{
- xfs_daddr_t d;
+ if ((lr & XFS_BTCUR_RIGHTRA) && right != NULLFSBLOCK) {
+ xfs_buf_readahead(mp->m_ddev_targp, XFS_FSB_TO_DADDR(mp, right),
+ mp->m_bsize, cur->bc_ops->buf_ops);
+ rval++;
+ }
- ASSERT(agno != NULLAGNUMBER);
- ASSERT(agbno != NULLAGBLOCK);
- d = XFS_AGB_TO_DADDR(mp, agno, agbno);
- xfs_buf_readahead(mp->m_ddev_targp, d, mp->m_bsize * count, ops);
+ return rval;
}
STATIC int
-xfs_btree_readahead_lblock(
+xfs_btree_readahead_memblock(
struct xfs_btree_cur *cur,
int lr,
struct xfs_btree_block *block)
{
+ struct xfs_buftarg *btp = cur->bc_mem.xfbtree->target;
+ xfbno_t left = be64_to_cpu(block->bb_u.l.bb_leftsib);
+ xfbno_t right = be64_to_cpu(block->bb_u.l.bb_rightsib);
int rval = 0;
- xfs_fsblock_t left = be64_to_cpu(block->bb_u.l.bb_leftsib);
- xfs_fsblock_t right = be64_to_cpu(block->bb_u.l.bb_rightsib);
if ((lr & XFS_BTCUR_LEFTRA) && left != NULLFSBLOCK) {
- xfs_btree_reada_bufl(cur->bc_mp, left, 1,
- cur->bc_ops->buf_ops);
+ xfs_buf_readahead(btp, xfbno_to_daddr(left), XFBNO_BBSIZE,
+ cur->bc_ops->buf_ops);
rval++;
}
if ((lr & XFS_BTCUR_RIGHTRA) && right != NULLFSBLOCK) {
- xfs_btree_reada_bufl(cur->bc_mp, right, 1,
- cur->bc_ops->buf_ops);
+ xfs_buf_readahead(btp, xfbno_to_daddr(right), XFBNO_BBSIZE,
+ cur->bc_ops->buf_ops);
rval++;
}
@@ -952,25 +1011,28 @@ xfs_btree_readahead_lblock(
}
STATIC int
-xfs_btree_readahead_sblock(
+xfs_btree_readahead_agblock(
struct xfs_btree_cur *cur,
int lr,
- struct xfs_btree_block *block)
+ struct xfs_btree_block *block)
{
- int rval = 0;
+ struct xfs_mount *mp = cur->bc_mp;
+ xfs_agnumber_t agno = cur->bc_ag.pag->pag_agno;
xfs_agblock_t left = be32_to_cpu(block->bb_u.s.bb_leftsib);
xfs_agblock_t right = be32_to_cpu(block->bb_u.s.bb_rightsib);
-
+ int rval = 0;
if ((lr & XFS_BTCUR_LEFTRA) && left != NULLAGBLOCK) {
- xfs_btree_reada_bufs(cur->bc_mp, cur->bc_ag.pag->pag_agno,
- left, 1, cur->bc_ops->buf_ops);
+ xfs_buf_readahead(mp->m_ddev_targp,
+ XFS_AGB_TO_DADDR(mp, agno, left),
+ mp->m_bsize, cur->bc_ops->buf_ops);
rval++;
}
if ((lr & XFS_BTCUR_RIGHTRA) && right != NULLAGBLOCK) {
- xfs_btree_reada_bufs(cur->bc_mp, cur->bc_ag.pag->pag_agno,
- right, 1, cur->bc_ops->buf_ops);
+ xfs_buf_readahead(mp->m_ddev_targp,
+ XFS_AGB_TO_DADDR(mp, agno, right),
+ mp->m_bsize, cur->bc_ops->buf_ops);
rval++;
}
@@ -993,8 +1055,7 @@ xfs_btree_readahead(
* No readahead needed if we are at the root level and the
* btree root is stored in the inode.
*/
- if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
- (lev == cur->bc_nlevels - 1))
+ if (xfs_btree_at_iroot(cur, lev))
return 0;
if ((cur->bc_levels[lev].ra | lr) == cur->bc_levels[lev].ra)
@@ -1003,9 +1064,17 @@ xfs_btree_readahead(
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);
- return xfs_btree_readahead_sblock(cur, lr, block);
+ switch (cur->bc_ops->type) {
+ case XFS_BTREE_TYPE_AG:
+ return xfs_btree_readahead_agblock(cur, lr, block);
+ case XFS_BTREE_TYPE_INODE:
+ return xfs_btree_readahead_fsblock(cur, lr, block);
+ case XFS_BTREE_TYPE_MEM:
+ return xfs_btree_readahead_memblock(cur, lr, block);
+ default:
+ ASSERT(0);
+ return 0;
+ }
}
STATIC int
@@ -1014,23 +1083,24 @@ xfs_btree_ptr_to_daddr(
const union xfs_btree_ptr *ptr,
xfs_daddr_t *daddr)
{
- xfs_fsblock_t fsbno;
- xfs_agblock_t agbno;
int error;
error = xfs_btree_check_ptr(cur, ptr, 0, 1);
if (error)
return error;
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
- fsbno = be64_to_cpu(ptr->l);
- *daddr = XFS_FSB_TO_DADDR(cur->bc_mp, fsbno);
- } else {
- agbno = be32_to_cpu(ptr->s);
+ switch (cur->bc_ops->type) {
+ case XFS_BTREE_TYPE_AG:
*daddr = XFS_AGB_TO_DADDR(cur->bc_mp, cur->bc_ag.pag->pag_agno,
- agbno);
+ be32_to_cpu(ptr->s));
+ break;
+ case XFS_BTREE_TYPE_INODE:
+ *daddr = XFS_FSB_TO_DADDR(cur->bc_mp, be64_to_cpu(ptr->l));
+ break;
+ case XFS_BTREE_TYPE_MEM:
+ *daddr = xfbno_to_daddr(be64_to_cpu(ptr->l));
+ break;
}
-
return 0;
}
@@ -1050,8 +1120,9 @@ xfs_btree_readahead_ptr(
if (xfs_btree_ptr_to_daddr(cur, ptr, &daddr))
return;
- xfs_buf_readahead(cur->bc_mp->m_ddev_targp, daddr,
- cur->bc_mp->m_bsize * count, cur->bc_ops->buf_ops);
+ xfs_buf_readahead(xfs_btree_buftarg(cur), daddr,
+ xfs_btree_bbsize(cur) * count,
+ cur->bc_ops->buf_ops);
}
/*
@@ -1072,7 +1143,7 @@ xfs_btree_setbuf(
cur->bc_levels[lev].ra = 0;
b = XFS_BUF_TO_BLOCK(bp);
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+ if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) {
if (b->bb_u.l.bb_leftsib == cpu_to_be64(NULLFSBLOCK))
cur->bc_levels[lev].ra |= XFS_BTCUR_LEFTRA;
if (b->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK))
@@ -1090,7 +1161,7 @@ xfs_btree_ptr_is_null(
struct xfs_btree_cur *cur,
const union xfs_btree_ptr *ptr)
{
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+ if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN)
return ptr->l == cpu_to_be64(NULLFSBLOCK);
else
return ptr->s == cpu_to_be32(NULLAGBLOCK);
@@ -1101,12 +1172,23 @@ xfs_btree_set_ptr_null(
struct xfs_btree_cur *cur,
union xfs_btree_ptr *ptr)
{
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+ if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN)
ptr->l = cpu_to_be64(NULLFSBLOCK);
else
ptr->s = cpu_to_be32(NULLAGBLOCK);
}
+static inline bool
+xfs_btree_ptrs_equal(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *ptr1,
+ union xfs_btree_ptr *ptr2)
+{
+ if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN)
+ return ptr1->l == ptr2->l;
+ return ptr1->s == ptr2->s;
+}
+
/*
* Get/set/init sibling pointers
*/
@@ -1119,7 +1201,7 @@ xfs_btree_get_sibling(
{
ASSERT(lr == XFS_BB_LEFTSIB || lr == XFS_BB_RIGHTSIB);
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+ if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) {
if (lr == XFS_BB_RIGHTSIB)
ptr->l = block->bb_u.l.bb_rightsib;
else
@@ -1141,7 +1223,7 @@ xfs_btree_set_sibling(
{
ASSERT(lr == XFS_BB_LEFTSIB || lr == XFS_BB_RIGHTSIB);
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+ if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) {
if (lr == XFS_BB_RIGHTSIB)
block->bb_u.l.bb_rightsib = ptr->l;
else
@@ -1154,25 +1236,24 @@ xfs_btree_set_sibling(
}
}
-void
-xfs_btree_init_block_int(
+static void
+__xfs_btree_init_block(
struct xfs_mount *mp,
struct xfs_btree_block *buf,
+ const struct xfs_btree_ops *ops,
xfs_daddr_t blkno,
- xfs_btnum_t btnum,
__u16 level,
__u16 numrecs,
- __u64 owner,
- unsigned int flags)
+ __u64 owner)
{
- int crc = xfs_has_crc(mp);
- __u32 magic = xfs_btree_magic(crc, btnum);
+ bool crc = xfs_has_crc(mp);
+ __u32 magic = xfs_btree_magic(mp, ops);
buf->bb_magic = cpu_to_be32(magic);
buf->bb_level = cpu_to_be16(level);
buf->bb_numrecs = cpu_to_be16(numrecs);
- if (flags & XFS_BTREE_LONG_PTRS) {
+ if (ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) {
buf->bb_u.l.bb_leftsib = cpu_to_be64(NULLFSBLOCK);
buf->bb_u.l.bb_rightsib = cpu_to_be64(NULLFSBLOCK);
if (crc) {
@@ -1183,14 +1264,12 @@ xfs_btree_init_block_int(
buf->bb_u.l.bb_lsn = 0;
}
} else {
- /* owner is a 32 bit value on short blocks */
- __u32 __owner = (__u32)owner;
-
buf->bb_u.s.bb_leftsib = cpu_to_be32(NULLAGBLOCK);
buf->bb_u.s.bb_rightsib = cpu_to_be32(NULLAGBLOCK);
if (crc) {
buf->bb_u.s.bb_blkno = cpu_to_be64(blkno);
- buf->bb_u.s.bb_owner = cpu_to_be32(__owner);
+ /* owner is a 32 bit value on short blocks */
+ buf->bb_u.s.bb_owner = cpu_to_be32((__u32)owner);
uuid_copy(&buf->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid);
buf->bb_u.s.bb_lsn = 0;
}
@@ -1199,15 +1278,46 @@ xfs_btree_init_block_int(
void
xfs_btree_init_block(
- struct xfs_mount *mp,
- struct xfs_buf *bp,
- xfs_btnum_t btnum,
- __u16 level,
- __u16 numrecs,
- __u64 owner)
+ struct xfs_mount *mp,
+ struct xfs_btree_block *block,
+ const struct xfs_btree_ops *ops,
+ __u16 level,
+ __u16 numrecs,
+ __u64 owner)
+{
+ __xfs_btree_init_block(mp, block, ops, XFS_BUF_DADDR_NULL, level,
+ numrecs, owner);
+}
+
+void
+xfs_btree_init_buf(
+ struct xfs_mount *mp,
+ struct xfs_buf *bp,
+ const struct xfs_btree_ops *ops,
+ __u16 level,
+ __u16 numrecs,
+ __u64 owner)
+{
+ __xfs_btree_init_block(mp, XFS_BUF_TO_BLOCK(bp), ops,
+ xfs_buf_daddr(bp), level, numrecs, owner);
+ bp->b_ops = ops->buf_ops;
+}
+
+static inline __u64
+xfs_btree_owner(
+ struct xfs_btree_cur *cur)
{
- xfs_btree_init_block_int(mp, XFS_BUF_TO_BLOCK(bp), xfs_buf_daddr(bp),
- btnum, level, numrecs, owner, 0);
+ switch (cur->bc_ops->type) {
+ case XFS_BTREE_TYPE_MEM:
+ return cur->bc_mem.xfbtree->owner;
+ case XFS_BTREE_TYPE_INODE:
+ return cur->bc_ino.ip->i_ino;
+ case XFS_BTREE_TYPE_AG:
+ return cur->bc_ag.pag->pag_agno;
+ default:
+ ASSERT(0);
+ return 0;
+ }
}
void
@@ -1217,22 +1327,8 @@ xfs_btree_init_block_cur(
int level,
int numrecs)
{
- __u64 owner;
-
- /*
- * we can pull the owner from the cursor right now as the different
- * owners align directly with the pointer size of the btree. This may
- * change in future, but is safe for current users of the generic btree
- * code.
- */
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
- owner = cur->bc_ino.ip->i_ino;
- else
- owner = cur->bc_ag.pag->pag_agno;
-
- xfs_btree_init_block_int(cur->bc_mp, XFS_BUF_TO_BLOCK(bp),
- xfs_buf_daddr(bp), cur->bc_btnum, level,
- numrecs, owner, cur->bc_flags);
+ xfs_btree_init_buf(cur->bc_mp, bp, cur->bc_ops, level, numrecs,
+ xfs_btree_owner(cur));
}
/*
@@ -1250,7 +1346,7 @@ xfs_btree_is_lastrec(
if (level > 0)
return 0;
- if (!(cur->bc_flags & XFS_BTREE_LASTREC_UPDATE))
+ if (!(cur->bc_ops->geom_flags & XFS_BTGEO_LASTREC_UPDATE))
return 0;
xfs_btree_get_sibling(cur, block, &ptr, XFS_BB_RIGHTSIB);
@@ -1265,41 +1361,27 @@ xfs_btree_buf_to_ptr(
struct xfs_buf *bp,
union xfs_btree_ptr *ptr)
{
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
- ptr->l = cpu_to_be64(XFS_DADDR_TO_FSB(cur->bc_mp,
- xfs_buf_daddr(bp)));
- else {
+ switch (cur->bc_ops->type) {
+ case XFS_BTREE_TYPE_AG:
ptr->s = cpu_to_be32(xfs_daddr_to_agbno(cur->bc_mp,
xfs_buf_daddr(bp)));
+ break;
+ case XFS_BTREE_TYPE_INODE:
+ ptr->l = cpu_to_be64(XFS_DADDR_TO_FSB(cur->bc_mp,
+ xfs_buf_daddr(bp)));
+ break;
+ case XFS_BTREE_TYPE_MEM:
+ ptr->l = cpu_to_be64(xfs_daddr_to_xfbno(xfs_buf_daddr(bp)));
+ break;
}
}
-STATIC void
+static inline void
xfs_btree_set_refs(
struct xfs_btree_cur *cur,
struct xfs_buf *bp)
{
- switch (cur->bc_btnum) {
- case XFS_BTNUM_BNO:
- case XFS_BTNUM_CNT:
- xfs_buf_set_ref(bp, XFS_ALLOC_BTREE_REF);
- break;
- case XFS_BTNUM_INO:
- case XFS_BTNUM_FINO:
- xfs_buf_set_ref(bp, XFS_INO_BTREE_REF);
- break;
- case XFS_BTNUM_BMAP:
- xfs_buf_set_ref(bp, XFS_BMAP_BTREE_REF);
- break;
- case XFS_BTNUM_RMAP:
- xfs_buf_set_ref(bp, XFS_RMAP_BTREE_REF);
- break;
- case XFS_BTNUM_REFC:
- xfs_buf_set_ref(bp, XFS_REFC_BTREE_REF);
- break;
- default:
- ASSERT(0);
- }
+ xfs_buf_set_ref(bp, cur->bc_ops->lru_refs);
}
int
@@ -1309,15 +1391,14 @@ xfs_btree_get_buf_block(
struct xfs_btree_block **block,
struct xfs_buf **bpp)
{
- struct xfs_mount *mp = cur->bc_mp;
- xfs_daddr_t d;
- int error;
+ xfs_daddr_t d;
+ int error;
error = xfs_btree_ptr_to_daddr(cur, ptr, &d);
if (error)
return error;
- error = xfs_trans_get_buf(cur->bc_tp, mp->m_ddev_targp, d, mp->m_bsize,
- 0, bpp);
+ error = xfs_trans_get_buf(cur->bc_tp, xfs_btree_buftarg(cur), d,
+ xfs_btree_bbsize(cur), 0, bpp);
if (error)
return error;
@@ -1348,9 +1429,11 @@ xfs_btree_read_buf_block(
error = xfs_btree_ptr_to_daddr(cur, ptr, &d);
if (error)
return error;
- error = xfs_trans_read_buf(mp, cur->bc_tp, mp->m_ddev_targp, d,
- mp->m_bsize, flags, bpp,
- cur->bc_ops->buf_ops);
+ error = xfs_trans_read_buf(mp, cur->bc_tp, xfs_btree_buftarg(cur), d,
+ xfs_btree_bbsize(cur), flags, bpp,
+ cur->bc_ops->buf_ops);
+ if (xfs_metadata_is_sick(error))
+ xfs_btree_mark_sick(cur);
if (error)
return error;
@@ -1398,7 +1481,7 @@ xfs_btree_copy_ptrs(
int numptrs)
{
ASSERT(numptrs >= 0);
- memcpy(dst_ptr, src_ptr, numptrs * xfs_btree_ptr_len(cur));
+ memcpy(dst_ptr, src_ptr, numptrs * cur->bc_ops->ptr_len);
}
/*
@@ -1454,8 +1537,8 @@ xfs_btree_shift_ptrs(
ASSERT(numptrs >= 0);
ASSERT(dir == 1 || dir == -1);
- dst_ptr = (char *)ptr + (dir * xfs_btree_ptr_len(cur));
- memmove(dst_ptr, ptr, numptrs * xfs_btree_ptr_len(cur));
+ dst_ptr = (char *)ptr + (dir * cur->bc_ops->ptr_len);
+ memmove(dst_ptr, ptr, numptrs * cur->bc_ops->ptr_len);
}
/*
@@ -1566,7 +1649,7 @@ xfs_btree_log_block(
if (bp) {
int nbits;
- if (cur->bc_flags & XFS_BTREE_CRC_BLOCKS) {
+ if (xfs_has_crc(cur->bc_mp)) {
/*
* We don't log the CRC when updating a btree
* block but instead recreate it during log
@@ -1581,7 +1664,7 @@ xfs_btree_log_block(
nbits = XFS_BB_NUM_BITS;
}
xfs_btree_offsets(fields,
- (cur->bc_flags & XFS_BTREE_LONG_PTRS) ?
+ (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) ?
loffsets : soffsets,
nbits, &first, &last);
xfs_trans_buf_set_type(cur->bc_tp, bp, XFS_BLFT_BTREE_BUF);
@@ -1658,9 +1741,10 @@ xfs_btree_increment(
* confused or have the tree root in an inode.
*/
if (lev == cur->bc_nlevels) {
- if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
+ if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE)
goto out0;
ASSERT(0);
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1751,9 +1835,10 @@ xfs_btree_decrement(
* or the root of the tree is in an inode.
*/
if (lev == cur->bc_nlevels) {
- if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
+ if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE)
goto out0;
ASSERT(0);
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1786,6 +1871,33 @@ error0:
return error;
}
+/*
+ * Check the btree block owner now that we have the context to know who the
+ * real owner is.
+ */
+static inline xfs_failaddr_t
+xfs_btree_check_block_owner(
+ struct xfs_btree_cur *cur,
+ struct xfs_btree_block *block)
+{
+ __u64 owner;
+
+ if (!xfs_has_crc(cur->bc_mp) ||
+ (cur->bc_flags & XFS_BTREE_BMBT_INVALID_OWNER))
+ return NULL;
+
+ owner = xfs_btree_owner(cur);
+ if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) {
+ if (be64_to_cpu(block->bb_u.l.bb_owner) != owner)
+ return __this_address;
+ } else {
+ if (be32_to_cpu(block->bb_u.s.bb_owner) != owner)
+ return __this_address;
+ }
+
+ return NULL;
+}
+
int
xfs_btree_lookup_get_block(
struct xfs_btree_cur *cur, /* btree cursor */
@@ -1798,8 +1910,7 @@ xfs_btree_lookup_get_block(
int error = 0;
/* special case the root block if in an inode */
- if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
- (level == cur->bc_nlevels - 1)) {
+ if (xfs_btree_at_iroot(cur, level)) {
*blkp = xfs_btree_get_iroot(cur);
return 0;
}
@@ -1824,11 +1935,7 @@ xfs_btree_lookup_get_block(
return error;
/* Check the inode owner since the verifiers don't. */
- if (xfs_has_crc(cur->bc_mp) &&
- !(cur->bc_ino.flags & XFS_BTCUR_BMBT_INVALID_OWNER) &&
- (cur->bc_flags & XFS_BTREE_LONG_PTRS) &&
- be64_to_cpu((*blkp)->bb_u.l.bb_owner) !=
- cur->bc_ino.ip->i_ino)
+ if (xfs_btree_check_block_owner(cur, *blkp) != NULL)
goto out_bad;
/* Did we get the level we were looking for? */
@@ -1846,6 +1953,7 @@ out_bad:
*blkp = NULL;
xfs_buf_mark_corrupt(bp);
xfs_trans_brelse(cur->bc_tp, bp);
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
}
@@ -1872,6 +1980,27 @@ xfs_lookup_get_search_key(
}
/*
+ * Initialize a pointer to the root block.
+ */
+void
+xfs_btree_init_ptr_from_cur(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *ptr)
+{
+ if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) {
+ /*
+ * Inode-rooted btrees call xfs_btree_get_iroot to find the root
+ * in xfs_btree_lookup_get_block and don't need a pointer here.
+ */
+ ptr->l = 0;
+ } else if (cur->bc_flags & XFS_BTREE_STAGING) {
+ ptr->s = cpu_to_be32(cur->bc_ag.afake->af_root);
+ } else {
+ cur->bc_ops->init_ptr_from_cur(cur, ptr);
+ }
+}
+
+/*
* Lookup the record. The cursor is made to point to it, based on dir.
* stat is set to 0 if can't find any such record, 1 for success.
*/
@@ -1892,14 +2021,16 @@ xfs_btree_lookup(
XFS_BTREE_STATS_INC(cur, lookup);
/* No such thing as a zero-level tree. */
- if (XFS_IS_CORRUPT(cur->bc_mp, cur->bc_nlevels == 0))
+ if (XFS_IS_CORRUPT(cur->bc_mp, cur->bc_nlevels == 0)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
block = NULL;
keyno = 0;
/* initialise start pointer from cursor */
- cur->bc_ops->init_ptr_from_cur(cur, &ptr);
+ xfs_btree_init_ptr_from_cur(cur, &ptr);
pp = &ptr;
/*
@@ -1936,6 +2067,7 @@ xfs_btree_lookup(
XFS_ERRLEVEL_LOW,
cur->bc_mp, block,
sizeof(*block));
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
}
@@ -2012,8 +2144,10 @@ xfs_btree_lookup(
error = xfs_btree_increment(cur, 0, &i);
if (error)
goto error0;
- if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+ if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
*stat = 1;
return 0;
}
@@ -2040,7 +2174,7 @@ xfs_btree_high_key_from_key(
struct xfs_btree_cur *cur,
union xfs_btree_key *key)
{
- ASSERT(cur->bc_flags & XFS_BTREE_OVERLAPPING);
+ ASSERT(cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING);
return (union xfs_btree_key *)((char *)key +
(cur->bc_ops->key_len / 2));
}
@@ -2061,7 +2195,7 @@ xfs_btree_get_leaf_keys(
rec = xfs_btree_rec_addr(cur, 1, block);
cur->bc_ops->init_key_from_rec(key, rec);
- if (cur->bc_flags & XFS_BTREE_OVERLAPPING) {
+ if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) {
cur->bc_ops->init_high_key_from_rec(&max_hkey, rec);
for (n = 2; n <= xfs_btree_get_numrecs(block); n++) {
@@ -2088,7 +2222,7 @@ xfs_btree_get_node_keys(
union xfs_btree_key *high;
int n;
- if (cur->bc_flags & XFS_BTREE_OVERLAPPING) {
+ if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) {
memcpy(key, xfs_btree_key_addr(cur, 1, block),
cur->bc_ops->key_len / 2);
@@ -2132,7 +2266,7 @@ xfs_btree_needs_key_update(
struct xfs_btree_cur *cur,
int ptr)
{
- return (cur->bc_flags & XFS_BTREE_OVERLAPPING) || ptr == 1;
+ return (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) || ptr == 1;
}
/*
@@ -2156,7 +2290,7 @@ __xfs_btree_updkeys(
struct xfs_buf *bp;
int ptr;
- ASSERT(cur->bc_flags & XFS_BTREE_OVERLAPPING);
+ ASSERT(cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING);
/* Exit if there aren't any parent levels to update. */
if (level + 1 >= cur->bc_nlevels)
@@ -2225,7 +2359,7 @@ xfs_btree_update_keys(
ASSERT(level >= 0);
block = xfs_btree_get_block(cur, level, &bp);
- if (cur->bc_flags & XFS_BTREE_OVERLAPPING)
+ if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING)
return __xfs_btree_updkeys(cur, level, block, bp, false);
/*
@@ -2332,8 +2466,7 @@ xfs_btree_lshift(
int error; /* error return value */
int i;
- if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
- level == cur->bc_nlevels - 1)
+ if (xfs_btree_at_iroot(cur, level))
goto out0;
/* Set up variables for this block as "right". */
@@ -2460,12 +2593,13 @@ xfs_btree_lshift(
* Using a temporary cursor, update the parent key values of the
* block on the left.
*/
- if (cur->bc_flags & XFS_BTREE_OVERLAPPING) {
+ if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) {
error = xfs_btree_dup_cursor(cur, &tcur);
if (error)
goto error0;
i = xfs_btree_firstrec(tcur, level);
if (XFS_IS_CORRUPT(tcur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -2527,8 +2661,7 @@ xfs_btree_rshift(
int error; /* error return value */
int i; /* loop counter */
- if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
- (level == cur->bc_nlevels - 1))
+ if (xfs_btree_at_iroot(cur, level))
goto out0;
/* Set up variables for this block as "left". */
@@ -2636,6 +2769,7 @@ xfs_btree_rshift(
goto error0;
i = xfs_btree_lastrec(tcur, level);
if (XFS_IS_CORRUPT(tcur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -2645,7 +2779,7 @@ xfs_btree_rshift(
goto error1;
/* Update the parent high keys of the left block, if needed. */
- if (cur->bc_flags & XFS_BTREE_OVERLAPPING) {
+ if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) {
error = xfs_btree_update_keys(cur, level);
if (error)
goto error1;
@@ -2673,6 +2807,32 @@ error1:
return error;
}
+static inline int
+xfs_btree_alloc_block(
+ struct xfs_btree_cur *cur,
+ const union xfs_btree_ptr *hint_block,
+ union xfs_btree_ptr *new_block,
+ int *stat)
+{
+ int error;
+
+ /*
+ * Don't allow block allocation for a staging cursor, because staging
+ * cursors do not support regular btree modifications.
+ *
+ * Bulk loading uses a separate callback to obtain new blocks from a
+ * preallocated list, which prevents ENOSPC failures during loading.
+ */
+ if (unlikely(cur->bc_flags & XFS_BTREE_STAGING)) {
+ ASSERT(0);
+ return -EFSCORRUPTED;
+ }
+
+ error = cur->bc_ops->alloc_block(cur, hint_block, new_block, stat);
+ trace_xfs_btree_alloc_block(cur, new_block, *stat, error);
+ return error;
+}
+
/*
* Split cur/level block in half.
* Return new block number and the key to its first
@@ -2716,7 +2876,7 @@ __xfs_btree_split(
xfs_btree_buf_to_ptr(cur, lbp, &lptr);
/* Allocate the new block. If we can't do it, we're toast. Give up. */
- error = cur->bc_ops->alloc_block(cur, &lptr, &rptr, stat);
+ error = xfs_btree_alloc_block(cur, &lptr, &rptr, stat);
if (error)
goto error0;
if (*stat == 0)
@@ -2823,7 +2983,7 @@ __xfs_btree_split(
}
/* Update the parent high keys of the left block, if needed. */
- if (cur->bc_flags & XFS_BTREE_OVERLAPPING) {
+ if (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING) {
error = xfs_btree_update_keys(cur, level);
if (error)
goto error0;
@@ -2941,7 +3101,7 @@ xfs_btree_split(
struct xfs_btree_split_args args;
DECLARE_COMPLETION_ONSTACK(done);
- if (cur->bc_btnum != XFS_BTNUM_BMAP ||
+ if (!xfs_btree_is_bmap(cur->bc_ops) ||
cur->bc_tp->t_highest_agno == NULLAGNUMBER)
return __xfs_btree_split(cur, level, ptrp, key, curp, stat);
@@ -2963,7 +3123,6 @@ xfs_btree_split(
#define xfs_btree_split __xfs_btree_split
#endif /* __KERNEL__ */
-
/*
* Copy the old inode root contents into a real block and make the
* broot point to it.
@@ -2988,7 +3147,7 @@ xfs_btree_new_iroot(
XFS_BTREE_STATS_INC(cur, newroot);
- ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE);
+ ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE);
level = cur->bc_nlevels - 1;
@@ -2996,7 +3155,7 @@ xfs_btree_new_iroot(
pp = xfs_btree_ptr_addr(cur, 1, block);
/* Allocate the new block. If we can't do it, we're toast. Give up. */
- error = cur->bc_ops->alloc_block(cur, pp, &nptr, stat);
+ error = xfs_btree_alloc_block(cur, pp, &nptr, stat);
if (error)
goto error0;
if (*stat == 0)
@@ -3014,9 +3173,9 @@ xfs_btree_new_iroot(
* In that case have to also ensure the blkno remains correct
*/
memcpy(cblock, block, xfs_btree_block_len(cur));
- if (cur->bc_flags & XFS_BTREE_CRC_BLOCKS) {
+ if (xfs_has_crc(cur->bc_mp)) {
__be64 bno = cpu_to_be64(xfs_buf_daddr(cbp));
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+ if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN)
cblock->bb_u.l.bb_blkno = bno;
else
cblock->bb_u.s.bb_blkno = bno;
@@ -3069,6 +3228,21 @@ error0:
return error;
}
+static void
+xfs_btree_set_root(
+ struct xfs_btree_cur *cur,
+ const union xfs_btree_ptr *ptr,
+ int inc)
+{
+ if (cur->bc_flags & XFS_BTREE_STAGING) {
+ /* Update the btree root information for a per-AG fake root. */
+ cur->bc_ag.afake->af_root = be32_to_cpu(ptr->s);
+ cur->bc_ag.afake->af_levels += inc;
+ } else {
+ cur->bc_ops->set_root(cur, ptr, inc);
+ }
+}
+
/*
* Allocate a new root block, fill it in.
*/
@@ -3093,10 +3267,10 @@ xfs_btree_new_root(
XFS_BTREE_STATS_INC(cur, newroot);
/* initialise our start point from the cursor */
- cur->bc_ops->init_ptr_from_cur(cur, &rptr);
+ xfs_btree_init_ptr_from_cur(cur, &rptr);
/* Allocate the new block. If we can't do it, we're toast. Give up. */
- error = cur->bc_ops->alloc_block(cur, &rptr, &lptr, stat);
+ error = xfs_btree_alloc_block(cur, &rptr, &lptr, stat);
if (error)
goto error0;
if (*stat == 0)
@@ -3109,7 +3283,7 @@ xfs_btree_new_root(
goto error0;
/* Set the root in the holding structure increasing the level by 1. */
- cur->bc_ops->set_root(cur, &lptr, 1);
+ xfs_btree_set_root(cur, &lptr, 1);
/*
* At the previous root level there are now two blocks: the old root,
@@ -3213,8 +3387,7 @@ xfs_btree_make_block_unfull(
{
int error = 0;
- if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
- level == cur->bc_nlevels - 1) {
+ if (xfs_btree_at_iroot(cur, level)) {
struct xfs_inode *ip = cur->bc_ino.ip;
if (numrecs < cur->bc_ops->get_dmaxrecs(cur, level)) {
@@ -3299,8 +3472,8 @@ xfs_btree_insrec(
* If we have an external root pointer, and we've made it to the
* root level, allocate a new root block and we're done.
*/
- if (!(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
- (level >= cur->bc_nlevels)) {
+ if (cur->bc_ops->type != XFS_BTREE_TYPE_INODE &&
+ level >= cur->bc_nlevels) {
error = xfs_btree_new_root(cur, stat);
xfs_btree_set_ptr_null(cur, ptrp);
@@ -3524,6 +3697,7 @@ xfs_btree_insert(
}
if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -3537,7 +3711,8 @@ xfs_btree_insert(
if (pcur != cur &&
(ncur || xfs_btree_ptr_is_null(cur, &nptr))) {
/* Save the state from the cursor before we trash it */
- if (cur->bc_ops->update_cursor)
+ if (cur->bc_ops->update_cursor &&
+ !(cur->bc_flags & XFS_BTREE_STAGING))
cur->bc_ops->update_cursor(pcur, cur);
cur->bc_nlevels = pcur->bc_nlevels;
xfs_btree_del_cursor(pcur, XFS_BTREE_NOERROR);
@@ -3586,7 +3761,7 @@ xfs_btree_kill_iroot(
#endif
int i;
- ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE);
+ ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE);
ASSERT(cur->bc_nlevels > 1);
/*
@@ -3680,7 +3855,7 @@ xfs_btree_kill_root(
* Update the root pointer, decreasing the level by 1 and then
* free the old root.
*/
- cur->bc_ops->set_root(cur, newroot, -1);
+ xfs_btree_set_root(cur, newroot, -1);
error = xfs_btree_free_block(cur, bp);
if (error)
@@ -3822,27 +3997,25 @@ xfs_btree_delrec(
* Try to get rid of the next level down. If we can't then there's
* nothing left to do.
*/
- if (level == cur->bc_nlevels - 1) {
- if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) {
- xfs_iroot_realloc(cur->bc_ino.ip, -1,
- cur->bc_ino.whichfork);
+ if (xfs_btree_at_iroot(cur, level)) {
+ xfs_iroot_realloc(cur->bc_ino.ip, -1, cur->bc_ino.whichfork);
- error = xfs_btree_kill_iroot(cur);
- if (error)
- goto error0;
+ error = xfs_btree_kill_iroot(cur);
+ if (error)
+ goto error0;
- error = xfs_btree_dec_cursor(cur, level, stat);
- if (error)
- goto error0;
- *stat = 1;
- return 0;
- }
+ error = xfs_btree_dec_cursor(cur, level, stat);
+ if (error)
+ goto error0;
+ *stat = 1;
+ return 0;
+ }
- /*
- * If this is the root level, and there's only one entry left,
- * and it's NOT the leaf level, then we can get rid of this
- * level.
- */
+ /*
+ * If this is the root level, and there's only one entry left, and it's
+ * NOT the leaf level, then we can get rid of this level.
+ */
+ if (level == cur->bc_nlevels - 1) {
if (numrecs == 1 && level > 0) {
union xfs_btree_ptr *pp;
/*
@@ -3891,7 +4064,7 @@ xfs_btree_delrec(
xfs_btree_get_sibling(cur, block, &rptr, XFS_BB_RIGHTSIB);
xfs_btree_get_sibling(cur, block, &lptr, XFS_BB_LEFTSIB);
- if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) {
+ if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) {
/*
* One child of root, need to get a chance to copy its contents
* into the root and delete it. Can't go up to next level,
@@ -3931,6 +4104,7 @@ xfs_btree_delrec(
*/
i = xfs_btree_lastrec(tcur, level);
if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -3939,12 +4113,14 @@ xfs_btree_delrec(
if (error)
goto error0;
if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
i = xfs_btree_lastrec(tcur, level);
if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -3992,6 +4168,7 @@ xfs_btree_delrec(
if (!xfs_btree_ptr_is_null(cur, &lptr)) {
i = xfs_btree_firstrec(tcur, level);
if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -4000,6 +4177,7 @@ xfs_btree_delrec(
if (error)
goto error0;
if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -4017,6 +4195,7 @@ xfs_btree_delrec(
*/
i = xfs_btree_firstrec(tcur, level);
if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -4026,6 +4205,7 @@ xfs_btree_delrec(
goto error0;
i = xfs_btree_firstrec(tcur, level);
if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -4201,8 +4381,8 @@ xfs_btree_delrec(
* If we joined with the right neighbor and there's a level above
* us, increment the cursor at that level.
*/
- else if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) ||
- (level + 1 < cur->bc_nlevels)) {
+ else if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE ||
+ level + 1 < cur->bc_nlevels) {
error = xfs_btree_increment(cur, level + 1, &i);
if (error)
goto error0;
@@ -4270,7 +4450,7 @@ xfs_btree_delete(
* If we combined blocks as part of deleting the record, delrec won't
* have updated the parent high keys so we have to do that here.
*/
- if (joined && (cur->bc_flags & XFS_BTREE_OVERLAPPING)) {
+ if (joined && (cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING)) {
error = xfs_btree_updkeys_force(cur, 0);
if (error)
goto error0;
@@ -4344,7 +4524,7 @@ xfs_btree_visit_block(
{
struct xfs_btree_block *block;
struct xfs_buf *bp;
- union xfs_btree_ptr rptr;
+ union xfs_btree_ptr rptr, bufptr;
int error;
/* do right sibling readahead */
@@ -4367,15 +4547,12 @@ xfs_btree_visit_block(
* return the same block without checking if the right sibling points
* back to us and creates a cyclic reference in the btree.
*/
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
- if (be64_to_cpu(rptr.l) == XFS_DADDR_TO_FSB(cur->bc_mp,
- xfs_buf_daddr(bp)))
- return -EFSCORRUPTED;
- } else {
- if (be32_to_cpu(rptr.s) == xfs_daddr_to_agbno(cur->bc_mp,
- xfs_buf_daddr(bp)))
- return -EFSCORRUPTED;
+ xfs_btree_buf_to_ptr(cur, bp, &bufptr);
+ if (xfs_btree_ptrs_equal(cur, &rptr, &bufptr)) {
+ xfs_btree_mark_sick(cur);
+ return -EFSCORRUPTED;
}
+
return xfs_btree_lookup_get_block(cur, level, &rptr, &block);
}
@@ -4393,7 +4570,7 @@ xfs_btree_visit_blocks(
struct xfs_btree_block *block = NULL;
int error = 0;
- cur->bc_ops->init_ptr_from_cur(cur, &lptr);
+ xfs_btree_init_ptr_from_cur(cur, &lptr);
/* for each level */
for (level = cur->bc_nlevels - 1; level >= 0; level--) {
@@ -4471,7 +4648,7 @@ xfs_btree_block_change_owner(
/* modify the owner */
block = xfs_btree_get_block(cur, level, &bp);
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+ if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) {
if (block->bb_u.l.bb_owner == cpu_to_be64(bbcoi->new_owner))
return 0;
block->bb_u.l.bb_owner = cpu_to_be64(bbcoi->new_owner);
@@ -4489,7 +4666,7 @@ xfs_btree_block_change_owner(
* though, so everything is consistent in memory.
*/
if (!bp) {
- ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE);
+ ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE);
ASSERT(level == cur->bc_nlevels - 1);
return 0;
}
@@ -4523,7 +4700,7 @@ xfs_btree_change_owner(
/* Verify the v5 fields of a long-format btree block. */
xfs_failaddr_t
-xfs_btree_lblock_v5hdr_verify(
+xfs_btree_fsblock_v5hdr_verify(
struct xfs_buf *bp,
uint64_t owner)
{
@@ -4544,7 +4721,7 @@ xfs_btree_lblock_v5hdr_verify(
/* Verify a long-format btree block. */
xfs_failaddr_t
-xfs_btree_lblock_verify(
+xfs_btree_fsblock_verify(
struct xfs_buf *bp,
unsigned int max_recs)
{
@@ -4553,28 +4730,60 @@ xfs_btree_lblock_verify(
xfs_fsblock_t fsb;
xfs_failaddr_t fa;
+ ASSERT(!xfs_buftarg_is_mem(bp->b_target));
+
/* numrecs verification */
if (be16_to_cpu(block->bb_numrecs) > max_recs)
return __this_address;
/* sibling pointer verification */
fsb = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
- fa = xfs_btree_check_lblock_siblings(mp, NULL, -1, fsb,
+ fa = xfs_btree_check_fsblock_siblings(mp, fsb,
block->bb_u.l.bb_leftsib);
if (!fa)
- fa = xfs_btree_check_lblock_siblings(mp, NULL, -1, fsb,
+ fa = xfs_btree_check_fsblock_siblings(mp, fsb,
block->bb_u.l.bb_rightsib);
return fa;
}
+/* Verify an in-memory btree block. */
+xfs_failaddr_t
+xfs_btree_memblock_verify(
+ struct xfs_buf *bp,
+ unsigned int max_recs)
+{
+ struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
+ struct xfs_buftarg *btp = bp->b_target;
+ xfs_failaddr_t fa;
+ xfbno_t bno;
+
+ ASSERT(xfs_buftarg_is_mem(bp->b_target));
+
+ /* numrecs verification */
+ if (be16_to_cpu(block->bb_numrecs) > max_recs)
+ return __this_address;
+
+ /* sibling pointer verification */
+ bno = xfs_daddr_to_xfbno(xfs_buf_daddr(bp));
+ fa = xfs_btree_check_memblock_siblings(btp, bno,
+ block->bb_u.l.bb_leftsib);
+ if (fa)
+ return fa;
+ fa = xfs_btree_check_memblock_siblings(btp, bno,
+ block->bb_u.l.bb_rightsib);
+ if (fa)
+ return fa;
+
+ return NULL;
+}
/**
- * xfs_btree_sblock_v5hdr_verify() -- verify the v5 fields of a short-format
+ * xfs_btree_agblock_v5hdr_verify() -- verify the v5 fields of a short-format
* btree block
*
* @bp: buffer containing the btree block
*/
xfs_failaddr_t
-xfs_btree_sblock_v5hdr_verify(
+xfs_btree_agblock_v5hdr_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_mount;
@@ -4593,13 +4802,13 @@ xfs_btree_sblock_v5hdr_verify(
}
/**
- * xfs_btree_sblock_verify() -- verify a short-format btree block
+ * xfs_btree_agblock_verify() -- verify a short-format btree block
*
* @bp: buffer containing the btree block
* @max_recs: maximum records allowed in this btree node
*/
xfs_failaddr_t
-xfs_btree_sblock_verify(
+xfs_btree_agblock_verify(
struct xfs_buf *bp,
unsigned int max_recs)
{
@@ -4608,16 +4817,18 @@ xfs_btree_sblock_verify(
xfs_agblock_t agbno;
xfs_failaddr_t fa;
+ ASSERT(!xfs_buftarg_is_mem(bp->b_target));
+
/* numrecs verification */
if (be16_to_cpu(block->bb_numrecs) > max_recs)
return __this_address;
/* sibling pointer verification */
agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp));
- fa = xfs_btree_check_sblock_siblings(bp->b_pag, NULL, -1, agbno,
+ fa = xfs_btree_check_agblock_siblings(bp->b_pag, agbno,
block->bb_u.s.bb_leftsib);
if (!fa)
- fa = xfs_btree_check_sblock_siblings(bp->b_pag, NULL, -1, agbno,
+ fa = xfs_btree_check_agblock_siblings(bp->b_pag, agbno,
block->bb_u.s.bb_rightsib);
return fa;
}
@@ -4815,7 +5026,7 @@ xfs_btree_overlapped_query_range(
/* Load the root of the btree. */
level = cur->bc_nlevels - 1;
- cur->bc_ops->init_ptr_from_cur(cur, &ptr);
+ xfs_btree_init_ptr_from_cur(cur, &ptr);
error = xfs_btree_lookup_get_block(cur, level, &ptr, &block);
if (error)
return error;
@@ -4966,7 +5177,7 @@ xfs_btree_query_range(
if (!xfs_btree_keycmp_le(cur, &low_key, &high_key))
return -EINVAL;
- if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
+ if (!(cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING))
return xfs_btree_simple_query_range(cur, &low_key,
&high_key, fn, priv);
return xfs_btree_overlapped_query_range(cur, &low_key, &high_key,
@@ -5020,7 +5231,7 @@ xfs_btree_diff_two_ptrs(
const union xfs_btree_ptr *a,
const union xfs_btree_ptr *b)
{
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+ if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN)
return (int64_t)be64_to_cpu(a->l) - be64_to_cpu(b->l);
return (int64_t)be32_to_cpu(a->s) - be32_to_cpu(b->s);
}
@@ -5074,7 +5285,7 @@ xfs_btree_has_records_helper(
key_contig = cur->bc_ops->keys_contiguous(cur, &info->high_key,
&rec_key, info->key_mask);
if (key_contig == XBTREE_KEY_OVERLAP &&
- !(cur->bc_flags & XFS_BTREE_OVERLAPPING))
+ !(cur->bc_ops->geom_flags & XFS_BTGEO_OVERLAPPING))
return -EFSCORRUPTED;
if (key_contig == XBTREE_KEY_GAP)
return -ECANCELED;
@@ -5168,7 +5379,7 @@ xfs_btree_has_more_records(
return true;
/* There are more record blocks. */
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+ if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN)
return block->bb_u.l.bb_rightsib != cpu_to_be64(NULLFSBLOCK);
else
return block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK);
@@ -5233,6 +5444,7 @@ xfs_btree_goto_left_edge(
return error;
if (stat != 0) {
ASSERT(0);
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index d906324e25..f93374278a 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -55,15 +55,8 @@ union xfs_btree_rec {
#define XFS_LOOKUP_LE ((xfs_lookup_t)XFS_LOOKUP_LEi)
#define XFS_LOOKUP_GE ((xfs_lookup_t)XFS_LOOKUP_GEi)
-#define XFS_BTNUM_BNO ((xfs_btnum_t)XFS_BTNUM_BNOi)
-#define XFS_BTNUM_CNT ((xfs_btnum_t)XFS_BTNUM_CNTi)
-#define XFS_BTNUM_BMAP ((xfs_btnum_t)XFS_BTNUM_BMAPi)
-#define XFS_BTNUM_INO ((xfs_btnum_t)XFS_BTNUM_INOi)
-#define XFS_BTNUM_FINO ((xfs_btnum_t)XFS_BTNUM_FINOi)
-#define XFS_BTNUM_RMAP ((xfs_btnum_t)XFS_BTNUM_RMAPi)
-#define XFS_BTNUM_REFC ((xfs_btnum_t)XFS_BTNUM_REFCi)
-
-uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum);
+struct xfs_btree_ops;
+uint32_t xfs_btree_magic(struct xfs_mount *mp, const struct xfs_btree_ops *ops);
/*
* For logging record fields.
@@ -86,9 +79,11 @@ uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum);
* Generic stats interface
*/
#define XFS_BTREE_STATS_INC(cur, stat) \
- XFS_STATS_INC_OFF((cur)->bc_mp, (cur)->bc_statoff + __XBTS_ ## stat)
+ XFS_STATS_INC_OFF((cur)->bc_mp, \
+ (cur)->bc_ops->statoff + __XBTS_ ## stat)
#define XFS_BTREE_STATS_ADD(cur, stat, val) \
- XFS_STATS_ADD_OFF((cur)->bc_mp, (cur)->bc_statoff + __XBTS_ ## stat, val)
+ XFS_STATS_ADD_OFF((cur)->bc_mp, \
+ (cur)->bc_ops->statoff + __XBTS_ ## stat, val)
enum xbtree_key_contig {
XBTREE_KEY_GAP = 0,
@@ -111,10 +106,37 @@ static inline enum xbtree_key_contig xbtree_key_contig(uint64_t x, uint64_t y)
return XBTREE_KEY_OVERLAP;
}
+#define XFS_BTREE_LONG_PTR_LEN (sizeof(__be64))
+#define XFS_BTREE_SHORT_PTR_LEN (sizeof(__be32))
+
+enum xfs_btree_type {
+ XFS_BTREE_TYPE_AG,
+ XFS_BTREE_TYPE_INODE,
+ XFS_BTREE_TYPE_MEM,
+};
+
struct xfs_btree_ops {
- /* size of the key and record structures */
- size_t key_len;
- size_t rec_len;
+ const char *name;
+
+ /* Type of btree - AG-rooted or inode-rooted */
+ enum xfs_btree_type type;
+
+ /* XFS_BTGEO_* flags that determine the geometry of the btree */
+ unsigned int geom_flags;
+
+ /* size of the key, pointer, and record structures */
+ size_t key_len;
+ size_t ptr_len;
+ size_t rec_len;
+
+ /* LRU refcount to set on each btree buffer created */
+ unsigned int lru_refs;
+
+ /* offset of btree stats array */
+ unsigned int statoff;
+
+ /* sick mask for health reporting (only for XFS_BTREE_TYPE_AG) */
+ unsigned int sick_mask;
/* cursor operations */
struct xfs_btree_cur *(*dup_cursor)(struct xfs_btree_cur *);
@@ -199,6 +221,10 @@ struct xfs_btree_ops {
const union xfs_btree_key *mask);
};
+/* btree geometry flags */
+#define XFS_BTGEO_LASTREC_UPDATE (1U << 0) /* track last rec externally */
+#define XFS_BTGEO_OVERLAPPING (1U << 1) /* overlapping intervals */
+
/*
* Reasons for the update_lastrec method to be called.
*/
@@ -215,39 +241,6 @@ union xfs_btree_irec {
struct xfs_refcount_irec rc;
};
-/* Per-AG btree information. */
-struct xfs_btree_cur_ag {
- struct xfs_perag *pag;
- union {
- struct xfs_buf *agbp;
- struct xbtree_afakeroot *afake; /* for staging cursor */
- };
- union {
- struct {
- unsigned int nr_ops; /* # record updates */
- unsigned int shape_changes; /* # of extent splits */
- } refc;
- struct {
- bool active; /* allocation cursor state */
- } abt;
- };
-};
-
-/* Btree-in-inode cursor information */
-struct xfs_btree_cur_ino {
- struct xfs_inode *ip;
- struct xbtree_ifakeroot *ifake; /* for staging cursor */
- int allocated;
- short forksize;
- char whichfork;
- char flags;
-/* We are converting a delalloc reservation */
-#define XFS_BTCUR_BMBT_WASDEL (1 << 0)
-
-/* For extent swap, ignore owner check in verifier */
-#define XFS_BTCUR_BMBT_INVALID_OWNER (1 << 1)
-};
-
struct xfs_btree_level {
/* buffer pointer */
struct xfs_buf *bp;
@@ -272,21 +265,38 @@ struct xfs_btree_cur
const struct xfs_btree_ops *bc_ops;
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 */
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
- * into physical addresses for IO, so the btree cursor switches between
- * bc_ino and bc_ag based on whether XFS_BTREE_LONG_PTRS is set for the
- * cursor.
- */
+ /* per-type information */
union {
- struct xfs_btree_cur_ag bc_ag;
- struct xfs_btree_cur_ino bc_ino;
+ struct {
+ struct xfs_inode *ip;
+ short forksize;
+ char whichfork;
+ struct xbtree_ifakeroot *ifake; /* for staging cursor */
+ } bc_ino;
+ struct {
+ struct xfs_perag *pag;
+ struct xfs_buf *agbp;
+ struct xbtree_afakeroot *afake; /* for staging cursor */
+ } bc_ag;
+ struct {
+ struct xfbtree *xfbtree;
+ struct xfs_perag *pag;
+ } bc_mem;
+ };
+
+ /* per-format private data */
+ union {
+ struct {
+ int allocated;
+ } bc_bmap; /* bmapbt */
+ struct {
+ unsigned int nr_ops; /* # record updates */
+ unsigned int shape_changes; /* # of extent splits */
+ } bc_refc; /* refcountbt */
};
/* Must be at the end of the struct! */
@@ -304,18 +314,22 @@ xfs_btree_cur_sizeof(unsigned int nlevels)
return struct_size_t(struct xfs_btree_cur, bc_levels, nlevels);
}
-/* cursor flags */
-#define XFS_BTREE_LONG_PTRS (1<<0) /* pointers are 64bits long */
-#define XFS_BTREE_ROOT_IN_INODE (1<<1) /* root may be variable size */
-#define XFS_BTREE_LASTREC_UPDATE (1<<2) /* track last rec externally */
-#define XFS_BTREE_CRC_BLOCKS (1<<3) /* uses extended btree blocks */
-#define XFS_BTREE_OVERLAPPING (1<<4) /* overlapping intervals */
+/* cursor state flags */
/*
* The root of this btree is a fakeroot structure so that we can stage a btree
* rebuild without leaving it accessible via primary metadata. The ops struct
* is dynamically allocated and must be freed when the cursor is deleted.
*/
-#define XFS_BTREE_STAGING (1<<5)
+#define XFS_BTREE_STAGING (1U << 0)
+
+/* We are converting a delalloc reservation (only for bmbt btrees) */
+#define XFS_BTREE_BMBT_WASDEL (1U << 1)
+
+/* For extent swap, ignore owner check in verifier (only for bmbt btrees) */
+#define XFS_BTREE_BMBT_INVALID_OWNER (1U << 2)
+
+/* Cursor is active (only for allocbt btrees) */
+#define XFS_BTREE_ALLOCBT_ACTIVE (1U << 3)
#define XFS_BTREE_NOERROR 0
#define XFS_BTREE_ERROR 1
@@ -325,14 +339,10 @@ xfs_btree_cur_sizeof(unsigned int nlevels)
*/
#define XFS_BUF_TO_BLOCK(bp) ((struct xfs_btree_block *)((bp)->b_addr))
-/*
- * Internal long and short btree block checks. They return NULL if the
- * block is ok or the address of the failed check otherwise.
- */
-xfs_failaddr_t __xfs_btree_check_lblock(struct xfs_btree_cur *cur,
- struct xfs_btree_block *block, int level, struct xfs_buf *bp);
-xfs_failaddr_t __xfs_btree_check_sblock(struct xfs_btree_cur *cur,
+xfs_failaddr_t __xfs_btree_check_block(struct xfs_btree_cur *cur,
struct xfs_btree_block *block, int level, struct xfs_buf *bp);
+int __xfs_btree_check_ptr(struct xfs_btree_cur *cur,
+ const union xfs_btree_ptr *ptr, int index, int level);
/*
* Check that block header is ok.
@@ -345,24 +355,6 @@ xfs_btree_check_block(
struct xfs_buf *bp); /* buffer containing block, if any */
/*
- * Check that (long) pointer is ok.
- */
-bool /* error (0 or EFSCORRUPTED) */
-xfs_btree_check_lptr(
- struct xfs_btree_cur *cur, /* btree cursor */
- xfs_fsblock_t fsbno, /* btree block disk address */
- int level); /* btree block level */
-
-/*
- * Check that (short) pointer is ok.
- */
-bool /* error (0 or EFSCORRUPTED) */
-xfs_btree_check_sptr(
- struct xfs_btree_cur *cur, /* btree cursor */
- xfs_agblock_t agbno, /* btree block disk address */
- int level); /* btree block level */
-
-/*
* Delete the btree cursor.
*/
void
@@ -392,63 +384,14 @@ xfs_btree_offsets(
int *last); /* output: last byte offset */
/*
- * Get a buffer for the block, return it read in.
- * Long-form addressing.
- */
-int /* error */
-xfs_btree_read_bufl(
- struct xfs_mount *mp, /* file system mount point */
- struct xfs_trans *tp, /* transaction pointer */
- xfs_fsblock_t fsbno, /* file system block number */
- struct xfs_buf **bpp, /* buffer for fsbno */
- int refval, /* ref count value for buffer */
- const struct xfs_buf_ops *ops);
-
-/*
- * Read-ahead the block, don't wait for it, don't return a buffer.
- * Long-form addressing.
- */
-void /* error */
-xfs_btree_reada_bufl(
- struct xfs_mount *mp, /* file system mount point */
- xfs_fsblock_t fsbno, /* file system block number */
- xfs_extlen_t count, /* count of filesystem blocks */
- const struct xfs_buf_ops *ops);
-
-/*
- * Read-ahead the block, don't wait for it, don't return a buffer.
- * Short-form addressing.
- */
-void /* error */
-xfs_btree_reada_bufs(
- struct xfs_mount *mp, /* file system mount point */
- xfs_agnumber_t agno, /* allocation group number */
- xfs_agblock_t agbno, /* allocation group block number */
- xfs_extlen_t count, /* count of filesystem blocks */
- const struct xfs_buf_ops *ops);
-
-/*
* Initialise a new btree block header
*/
-void
-xfs_btree_init_block(
- struct xfs_mount *mp,
- struct xfs_buf *bp,
- xfs_btnum_t btnum,
- __u16 level,
- __u16 numrecs,
- __u64 owner);
-
-void
-xfs_btree_init_block_int(
- struct xfs_mount *mp,
- struct xfs_btree_block *buf,
- xfs_daddr_t blkno,
- xfs_btnum_t btnum,
- __u16 level,
- __u16 numrecs,
- __u64 owner,
- unsigned int flags);
+void xfs_btree_init_buf(struct xfs_mount *mp, struct xfs_buf *bp,
+ const struct xfs_btree_ops *ops, __u16 level, __u16 numrecs,
+ __u64 owner);
+void xfs_btree_init_block(struct xfs_mount *mp,
+ struct xfs_btree_block *buf, const struct xfs_btree_ops *ops,
+ __u16 level, __u16 numrecs, __u64 owner);
/*
* Common btree core entry points.
@@ -467,10 +410,10 @@ int xfs_btree_change_owner(struct xfs_btree_cur *cur, uint64_t new_owner,
/*
* btree block CRC helpers
*/
-void xfs_btree_lblock_calc_crc(struct xfs_buf *);
-bool xfs_btree_lblock_verify_crc(struct xfs_buf *);
-void xfs_btree_sblock_calc_crc(struct xfs_buf *);
-bool xfs_btree_sblock_verify_crc(struct xfs_buf *);
+void xfs_btree_fsblock_calc_crc(struct xfs_buf *);
+bool xfs_btree_fsblock_verify_crc(struct xfs_buf *);
+void xfs_btree_agblock_calc_crc(struct xfs_buf *);
+bool xfs_btree_agblock_verify_crc(struct xfs_buf *);
/*
* Internal btree helpers also used by xfs_bmap.c.
@@ -510,12 +453,14 @@ static inline int xfs_btree_get_level(const struct xfs_btree_block *block)
#define XFS_FILBLKS_MIN(a,b) min_t(xfs_filblks_t, (a), (b))
#define XFS_FILBLKS_MAX(a,b) max_t(xfs_filblks_t, (a), (b))
-xfs_failaddr_t xfs_btree_sblock_v5hdr_verify(struct xfs_buf *bp);
-xfs_failaddr_t xfs_btree_sblock_verify(struct xfs_buf *bp,
+xfs_failaddr_t xfs_btree_agblock_v5hdr_verify(struct xfs_buf *bp);
+xfs_failaddr_t xfs_btree_agblock_verify(struct xfs_buf *bp,
unsigned int max_recs);
-xfs_failaddr_t xfs_btree_lblock_v5hdr_verify(struct xfs_buf *bp,
+xfs_failaddr_t xfs_btree_fsblock_v5hdr_verify(struct xfs_buf *bp,
uint64_t owner);
-xfs_failaddr_t xfs_btree_lblock_verify(struct xfs_buf *bp,
+xfs_failaddr_t xfs_btree_fsblock_verify(struct xfs_buf *bp,
+ unsigned int max_recs);
+xfs_failaddr_t xfs_btree_memblock_verify(struct xfs_buf *bp,
unsigned int max_recs);
unsigned int xfs_btree_compute_maxlevels(const unsigned int *limits,
@@ -690,7 +635,7 @@ xfs_btree_islastblock(
block = xfs_btree_get_block(cur, level, &bp);
- if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+ if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN)
return block->bb_u.l.bb_rightsib == cpu_to_be64(NULLFSBLOCK);
return block->bb_u.s.bb_rightsib == cpu_to_be32(NULLAGBLOCK);
}
@@ -714,21 +659,28 @@ void xfs_btree_copy_ptrs(struct xfs_btree_cur *cur,
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);
+void xfs_btree_init_ptr_from_cur(struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *ptr);
static inline struct xfs_btree_cur *
xfs_btree_alloc_cursor(
struct xfs_mount *mp,
struct xfs_trans *tp,
- xfs_btnum_t btnum,
+ const struct xfs_btree_ops *ops,
uint8_t maxlevels,
struct kmem_cache *cache)
{
struct xfs_btree_cur *cur;
- cur = kmem_cache_zalloc(cache, GFP_NOFS | __GFP_NOFAIL);
+ ASSERT(ops->ptr_len == XFS_BTREE_LONG_PTR_LEN ||
+ ops->ptr_len == XFS_BTREE_SHORT_PTR_LEN);
+
+ /* BMBT allocations can come through from non-transactional context. */
+ cur = kmem_cache_zalloc(cache,
+ GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL);
+ cur->bc_ops = ops;
cur->bc_tp = tp;
cur->bc_mp = mp;
- cur->bc_btnum = btnum;
cur->bc_maxlevels = maxlevels;
cur->bc_cache = cache;
@@ -740,4 +692,14 @@ void xfs_btree_destroy_cur_caches(void);
int xfs_btree_goto_left_edge(struct xfs_btree_cur *cur);
+/* Does this level of the cursor point to the inode root (and not a block)? */
+static inline bool
+xfs_btree_at_iroot(
+ const struct xfs_btree_cur *cur,
+ int level)
+{
+ return cur->bc_ops->type == XFS_BTREE_TYPE_INODE &&
+ level == cur->bc_nlevels - 1;
+}
+
#endif /* __XFS_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_btree_mem.c b/fs/xfs/libxfs/xfs_btree_mem.c
new file mode 100644
index 0000000000..036061fe32
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_btree_mem.c
@@ -0,0 +1,347 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2021-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_trans.h"
+#include "xfs_btree.h"
+#include "xfs_error.h"
+#include "xfs_buf_mem.h"
+#include "xfs_btree_mem.h"
+#include "xfs_ag.h"
+#include "xfs_buf_item.h"
+#include "xfs_trace.h"
+
+/* Set the root of an in-memory btree. */
+void
+xfbtree_set_root(
+ struct xfs_btree_cur *cur,
+ const union xfs_btree_ptr *ptr,
+ int inc)
+{
+ ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_MEM);
+
+ cur->bc_mem.xfbtree->root = *ptr;
+ cur->bc_mem.xfbtree->nlevels += inc;
+}
+
+/* Initialize a pointer from the in-memory btree header. */
+void
+xfbtree_init_ptr_from_cur(
+ struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *ptr)
+{
+ ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_MEM);
+
+ *ptr = cur->bc_mem.xfbtree->root;
+}
+
+/* Duplicate an in-memory btree cursor. */
+struct xfs_btree_cur *
+xfbtree_dup_cursor(
+ struct xfs_btree_cur *cur)
+{
+ struct xfs_btree_cur *ncur;
+
+ ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_MEM);
+
+ ncur = xfs_btree_alloc_cursor(cur->bc_mp, cur->bc_tp, cur->bc_ops,
+ cur->bc_maxlevels, cur->bc_cache);
+ ncur->bc_flags = cur->bc_flags;
+ ncur->bc_nlevels = cur->bc_nlevels;
+ ncur->bc_mem.xfbtree = cur->bc_mem.xfbtree;
+
+ if (cur->bc_mem.pag)
+ ncur->bc_mem.pag = xfs_perag_hold(cur->bc_mem.pag);
+
+ return ncur;
+}
+
+/* Close the btree xfile and release all resources. */
+void
+xfbtree_destroy(
+ struct xfbtree *xfbt)
+{
+ xfs_buftarg_drain(xfbt->target);
+}
+
+/* Compute the number of bytes available for records. */
+static inline unsigned int
+xfbtree_rec_bytes(
+ struct xfs_mount *mp,
+ const struct xfs_btree_ops *ops)
+{
+ return XMBUF_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN;
+}
+
+/* Initialize an empty leaf block as the btree root. */
+STATIC int
+xfbtree_init_leaf_block(
+ struct xfs_mount *mp,
+ struct xfbtree *xfbt,
+ const struct xfs_btree_ops *ops)
+{
+ struct xfs_buf *bp;
+ xfbno_t bno = xfbt->highest_bno++;
+ int error;
+
+ error = xfs_buf_get(xfbt->target, xfbno_to_daddr(bno), XFBNO_BBSIZE,
+ &bp);
+ if (error)
+ return error;
+
+ trace_xfbtree_create_root_buf(xfbt, bp);
+
+ bp->b_ops = ops->buf_ops;
+ xfs_btree_init_buf(mp, bp, ops, 0, 0, xfbt->owner);
+ xfs_buf_relse(bp);
+
+ xfbt->root.l = cpu_to_be64(bno);
+ return 0;
+}
+
+/*
+ * Create an in-memory btree root that can be used with the given xmbuf.
+ * Callers must set xfbt->owner.
+ */
+int
+xfbtree_init(
+ struct xfs_mount *mp,
+ struct xfbtree *xfbt,
+ struct xfs_buftarg *btp,
+ const struct xfs_btree_ops *ops)
+{
+ unsigned int blocklen = xfbtree_rec_bytes(mp, ops);
+ unsigned int keyptr_len;
+ int error;
+
+ /* Requires a long-format CRC-format btree */
+ if (!xfs_has_crc(mp)) {
+ ASSERT(xfs_has_crc(mp));
+ return -EINVAL;
+ }
+ if (ops->ptr_len != XFS_BTREE_LONG_PTR_LEN) {
+ ASSERT(ops->ptr_len == XFS_BTREE_LONG_PTR_LEN);
+ return -EINVAL;
+ }
+
+ memset(xfbt, 0, sizeof(*xfbt));
+ xfbt->target = btp;
+
+ /* Set up min/maxrecs for this btree. */
+ keyptr_len = ops->key_len + sizeof(__be64);
+ xfbt->maxrecs[0] = blocklen / ops->rec_len;
+ xfbt->maxrecs[1] = blocklen / keyptr_len;
+ xfbt->minrecs[0] = xfbt->maxrecs[0] / 2;
+ xfbt->minrecs[1] = xfbt->maxrecs[1] / 2;
+ xfbt->highest_bno = 0;
+ xfbt->nlevels = 1;
+
+ /* Initialize the empty btree. */
+ error = xfbtree_init_leaf_block(mp, xfbt, ops);
+ if (error)
+ goto err_freesp;
+
+ trace_xfbtree_init(mp, xfbt, ops);
+
+ return 0;
+
+err_freesp:
+ xfs_buftarg_drain(xfbt->target);
+ return error;
+}
+
+/* Allocate a block to our in-memory btree. */
+int
+xfbtree_alloc_block(
+ struct xfs_btree_cur *cur,
+ const union xfs_btree_ptr *start,
+ union xfs_btree_ptr *new,
+ int *stat)
+{
+ struct xfbtree *xfbt = cur->bc_mem.xfbtree;
+ xfbno_t bno = xfbt->highest_bno++;
+
+ ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_MEM);
+
+ trace_xfbtree_alloc_block(xfbt, cur, bno);
+
+ /* Fail if the block address exceeds the maximum for the buftarg. */
+ if (!xfbtree_verify_bno(xfbt, bno)) {
+ ASSERT(xfbtree_verify_bno(xfbt, bno));
+ *stat = 0;
+ return 0;
+ }
+
+ new->l = cpu_to_be64(bno);
+ *stat = 1;
+ return 0;
+}
+
+/* Free a block from our in-memory btree. */
+int
+xfbtree_free_block(
+ struct xfs_btree_cur *cur,
+ struct xfs_buf *bp)
+{
+ struct xfbtree *xfbt = cur->bc_mem.xfbtree;
+ xfs_daddr_t daddr = xfs_buf_daddr(bp);
+ xfbno_t bno = xfs_daddr_to_xfbno(daddr);
+
+ ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_MEM);
+
+ trace_xfbtree_free_block(xfbt, cur, bno);
+
+ if (bno + 1 == xfbt->highest_bno)
+ xfbt->highest_bno--;
+
+ return 0;
+}
+
+/* Return the minimum number of records for a btree block. */
+int
+xfbtree_get_minrecs(
+ struct xfs_btree_cur *cur,
+ int level)
+{
+ struct xfbtree *xfbt = cur->bc_mem.xfbtree;
+
+ return xfbt->minrecs[level != 0];
+}
+
+/* Return the maximum number of records for a btree block. */
+int
+xfbtree_get_maxrecs(
+ struct xfs_btree_cur *cur,
+ int level)
+{
+ struct xfbtree *xfbt = cur->bc_mem.xfbtree;
+
+ return xfbt->maxrecs[level != 0];
+}
+
+/* If this log item is a buffer item that came from the xfbtree, return it. */
+static inline struct xfs_buf *
+xfbtree_buf_match(
+ struct xfbtree *xfbt,
+ const struct xfs_log_item *lip)
+{
+ const struct xfs_buf_log_item *bli;
+ struct xfs_buf *bp;
+
+ if (lip->li_type != XFS_LI_BUF)
+ return NULL;
+
+ bli = container_of(lip, struct xfs_buf_log_item, bli_item);
+ bp = bli->bli_buf;
+ if (bp->b_target != xfbt->target)
+ return NULL;
+
+ return bp;
+}
+
+/*
+ * Commit changes to the incore btree immediately by writing all dirty xfbtree
+ * buffers to the backing xfile. This detaches all xfbtree buffers from the
+ * transaction, even on failure. The buffer locks are dropped between the
+ * delwri queue and submit, so the caller must synchronize btree access.
+ *
+ * Normally we'd let the buffers commit with the transaction and get written to
+ * the xfile via the log, but online repair stages ephemeral btrees in memory
+ * and uses the btree_staging functions to write new btrees to disk atomically.
+ * The in-memory btree (and its backing store) are discarded at the end of the
+ * repair phase, which means that xfbtree buffers cannot commit with the rest
+ * of a transaction.
+ *
+ * In other words, online repair only needs the transaction to collect buffer
+ * pointers and to avoid buffer deadlocks, not to guarantee consistency of
+ * updates.
+ */
+int
+xfbtree_trans_commit(
+ struct xfbtree *xfbt,
+ struct xfs_trans *tp)
+{
+ struct xfs_log_item *lip, *n;
+ bool tp_dirty = false;
+ int error = 0;
+
+ /*
+ * For each xfbtree buffer attached to the transaction, write the dirty
+ * buffers to the xfile and release them.
+ */
+ list_for_each_entry_safe(lip, n, &tp->t_items, li_trans) {
+ struct xfs_buf *bp = xfbtree_buf_match(xfbt, lip);
+
+ if (!bp) {
+ if (test_bit(XFS_LI_DIRTY, &lip->li_flags))
+ tp_dirty |= true;
+ continue;
+ }
+
+ trace_xfbtree_trans_commit_buf(xfbt, bp);
+
+ xmbuf_trans_bdetach(tp, bp);
+
+ /*
+ * If the buffer fails verification, note the failure but
+ * continue walking the transaction items so that we remove all
+ * ephemeral btree buffers.
+ */
+ if (!error)
+ error = xmbuf_finalize(bp);
+
+ xfs_buf_relse(bp);
+ }
+
+ /*
+ * Reset the transaction's dirty flag to reflect the dirty state of the
+ * log items that are still attached.
+ */
+ tp->t_flags = (tp->t_flags & ~XFS_TRANS_DIRTY) |
+ (tp_dirty ? XFS_TRANS_DIRTY : 0);
+
+ return error;
+}
+
+/*
+ * Cancel changes to the incore btree by detaching all the xfbtree buffers.
+ * Changes are not undone, so callers must not access the btree ever again.
+ */
+void
+xfbtree_trans_cancel(
+ struct xfbtree *xfbt,
+ struct xfs_trans *tp)
+{
+ struct xfs_log_item *lip, *n;
+ bool tp_dirty = false;
+
+ list_for_each_entry_safe(lip, n, &tp->t_items, li_trans) {
+ struct xfs_buf *bp = xfbtree_buf_match(xfbt, lip);
+
+ if (!bp) {
+ if (test_bit(XFS_LI_DIRTY, &lip->li_flags))
+ tp_dirty |= true;
+ continue;
+ }
+
+ trace_xfbtree_trans_cancel_buf(xfbt, bp);
+
+ xmbuf_trans_bdetach(tp, bp);
+ xfs_buf_relse(bp);
+ }
+
+ /*
+ * Reset the transaction's dirty flag to reflect the dirty state of the
+ * log items that are still attached.
+ */
+ tp->t_flags = (tp->t_flags & ~XFS_TRANS_DIRTY) |
+ (tp_dirty ? XFS_TRANS_DIRTY : 0);
+}
diff --git a/fs/xfs/libxfs/xfs_btree_mem.h b/fs/xfs/libxfs/xfs_btree_mem.h
new file mode 100644
index 0000000000..1c3825786e
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_btree_mem.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2021-2024 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#ifndef __XFS_BTREE_MEM_H__
+#define __XFS_BTREE_MEM_H__
+
+typedef uint64_t xfbno_t;
+
+#define XFBNO_BLOCKSIZE (XMBUF_BLOCKSIZE)
+#define XFBNO_BBSHIFT (XMBUF_BLOCKSHIFT - BBSHIFT)
+#define XFBNO_BBSIZE (XFBNO_BLOCKSIZE >> BBSHIFT)
+
+static inline xfs_daddr_t xfbno_to_daddr(xfbno_t blkno)
+{
+ return blkno << XFBNO_BBSHIFT;
+}
+
+static inline xfbno_t xfs_daddr_to_xfbno(xfs_daddr_t daddr)
+{
+ return daddr >> XFBNO_BBSHIFT;
+}
+
+struct xfbtree {
+ /* buffer cache target for this in-memory btree */
+ struct xfs_buftarg *target;
+
+ /* Highest block number that has been written to. */
+ xfbno_t highest_bno;
+
+ /* Owner of this btree. */
+ unsigned long long owner;
+
+ /* Btree header */
+ union xfs_btree_ptr root;
+ unsigned int nlevels;
+
+ /* Minimum and maximum records per block. */
+ unsigned int maxrecs[2];
+ unsigned int minrecs[2];
+};
+
+#ifdef CONFIG_XFS_BTREE_IN_MEM
+static inline bool xfbtree_verify_bno(struct xfbtree *xfbt, xfbno_t bno)
+{
+ return xmbuf_verify_daddr(xfbt->target, xfbno_to_daddr(bno));
+}
+
+void xfbtree_set_root(struct xfs_btree_cur *cur,
+ const union xfs_btree_ptr *ptr, int inc);
+void xfbtree_init_ptr_from_cur(struct xfs_btree_cur *cur,
+ union xfs_btree_ptr *ptr);
+struct xfs_btree_cur *xfbtree_dup_cursor(struct xfs_btree_cur *cur);
+
+int xfbtree_get_minrecs(struct xfs_btree_cur *cur, int level);
+int xfbtree_get_maxrecs(struct xfs_btree_cur *cur, int level);
+
+int xfbtree_alloc_block(struct xfs_btree_cur *cur,
+ const union xfs_btree_ptr *start, union xfs_btree_ptr *ptr,
+ int *stat);
+int xfbtree_free_block(struct xfs_btree_cur *cur, struct xfs_buf *bp);
+
+/* Callers must set xfbt->target and xfbt->owner before calling this */
+int xfbtree_init(struct xfs_mount *mp, struct xfbtree *xfbt,
+ struct xfs_buftarg *btp, const struct xfs_btree_ops *ops);
+void xfbtree_destroy(struct xfbtree *xfbt);
+
+int xfbtree_trans_commit(struct xfbtree *xfbt, struct xfs_trans *tp);
+void xfbtree_trans_cancel(struct xfbtree *xfbt, struct xfs_trans *tp);
+#else
+# define xfbtree_verify_bno(...) (false)
+#endif /* CONFIG_XFS_BTREE_IN_MEM */
+
+#endif /* __XFS_BTREE_MEM_H__ */
diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c
index e276eba87c..6949297031 100644
--- a/fs/xfs/libxfs/xfs_btree_staging.c
+++ b/fs/xfs/libxfs/xfs_btree_staging.c
@@ -39,63 +39,6 @@
*/
/*
- * Don't allow staging cursors to be duplicated because they're supposed to be
- * kept private to a single thread.
- */
-STATIC struct xfs_btree_cur *
-xfs_btree_fakeroot_dup_cursor(
- struct xfs_btree_cur *cur)
-{
- ASSERT(0);
- return NULL;
-}
-
-/*
- * Don't allow block allocation for a staging cursor, because staging cursors
- * do not support regular btree modifications.
- *
- * Bulk loading uses a separate callback to obtain new blocks from a
- * preallocated list, which prevents ENOSPC failures during loading.
- */
-STATIC int
-xfs_btree_fakeroot_alloc_block(
- struct xfs_btree_cur *cur,
- const union xfs_btree_ptr *start_bno,
- union xfs_btree_ptr *new_bno,
- int *stat)
-{
- ASSERT(0);
- return -EFSCORRUPTED;
-}
-
-/*
- * Don't allow block freeing for a staging cursor, because staging cursors
- * do not support regular btree modifications.
- */
-STATIC int
-xfs_btree_fakeroot_free_block(
- struct xfs_btree_cur *cur,
- struct xfs_buf *bp)
-{
- ASSERT(0);
- return -EFSCORRUPTED;
-}
-
-/* Initialize a pointer to the root block from the fakeroot. */
-STATIC void
-xfs_btree_fakeroot_init_ptr_from_cur(
- struct xfs_btree_cur *cur,
- union xfs_btree_ptr *ptr)
-{
- struct xbtree_afakeroot *afake;
-
- ASSERT(cur->bc_flags & XFS_BTREE_STAGING);
-
- afake = cur->bc_ag.afake;
- ptr->s = cpu_to_be32(afake->af_root);
-}
-
-/*
* Bulk Loading for AG Btrees
* ==========================
*
@@ -109,47 +52,20 @@ xfs_btree_fakeroot_init_ptr_from_cur(
* cursor into a regular btree cursor.
*/
-/* Update the btree root information for a per-AG fake root. */
-STATIC void
-xfs_btree_afakeroot_set_root(
- struct xfs_btree_cur *cur,
- const union xfs_btree_ptr *ptr,
- int inc)
-{
- struct xbtree_afakeroot *afake = cur->bc_ag.afake;
-
- ASSERT(cur->bc_flags & XFS_BTREE_STAGING);
- afake->af_root = be32_to_cpu(ptr->s);
- afake->af_levels += inc;
-}
-
/*
* Initialize a AG-rooted btree cursor with the given AG btree fake root.
- * The btree cursor's bc_ops will be overridden as needed to make the staging
- * functionality work.
*/
void
xfs_btree_stage_afakeroot(
struct xfs_btree_cur *cur,
struct xbtree_afakeroot *afake)
{
- struct xfs_btree_ops *nops;
-
ASSERT(!(cur->bc_flags & XFS_BTREE_STAGING));
- ASSERT(!(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE));
+ ASSERT(cur->bc_ops->type != XFS_BTREE_TYPE_INODE);
ASSERT(cur->bc_tp == NULL);
- nops = kmem_alloc(sizeof(struct xfs_btree_ops), KM_NOFS);
- memcpy(nops, cur->bc_ops, sizeof(struct xfs_btree_ops));
- nops->alloc_block = xfs_btree_fakeroot_alloc_block;
- nops->free_block = xfs_btree_fakeroot_free_block;
- nops->init_ptr_from_cur = xfs_btree_fakeroot_init_ptr_from_cur;
- nops->set_root = xfs_btree_afakeroot_set_root;
- nops->dup_cursor = xfs_btree_fakeroot_dup_cursor;
-
cur->bc_ag.afake = afake;
cur->bc_nlevels = afake->af_levels;
- cur->bc_ops = nops;
cur->bc_flags |= XFS_BTREE_STAGING;
}
@@ -163,17 +79,15 @@ void
xfs_btree_commit_afakeroot(
struct xfs_btree_cur *cur,
struct xfs_trans *tp,
- struct xfs_buf *agbp,
- const struct xfs_btree_ops *ops)
+ struct xfs_buf *agbp)
{
ASSERT(cur->bc_flags & XFS_BTREE_STAGING);
ASSERT(cur->bc_tp == NULL);
trace_xfs_btree_commit_afakeroot(cur);
- kmem_free((void *)cur->bc_ops);
+ cur->bc_ag.afake = NULL;
cur->bc_ag.agbp = agbp;
- cur->bc_ops = ops;
cur->bc_flags &= ~XFS_BTREE_STAGING;
cur->bc_tp = tp;
}
@@ -211,29 +125,16 @@ xfs_btree_commit_afakeroot(
void
xfs_btree_stage_ifakeroot(
struct xfs_btree_cur *cur,
- struct xbtree_ifakeroot *ifake,
- struct xfs_btree_ops **new_ops)
+ struct xbtree_ifakeroot *ifake)
{
- struct xfs_btree_ops *nops;
-
ASSERT(!(cur->bc_flags & XFS_BTREE_STAGING));
- ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE);
+ ASSERT(cur->bc_ops->type == XFS_BTREE_TYPE_INODE);
ASSERT(cur->bc_tp == NULL);
- nops = kmem_alloc(sizeof(struct xfs_btree_ops), KM_NOFS);
- memcpy(nops, cur->bc_ops, sizeof(struct xfs_btree_ops));
- nops->alloc_block = xfs_btree_fakeroot_alloc_block;
- nops->free_block = xfs_btree_fakeroot_free_block;
- nops->init_ptr_from_cur = xfs_btree_fakeroot_init_ptr_from_cur;
- nops->dup_cursor = xfs_btree_fakeroot_dup_cursor;
-
cur->bc_ino.ifake = ifake;
cur->bc_nlevels = ifake->if_levels;
- cur->bc_ops = nops;
+ cur->bc_ino.forksize = ifake->if_fork_size;
cur->bc_flags |= XFS_BTREE_STAGING;
-
- if (new_ops)
- *new_ops = nops;
}
/*
@@ -246,18 +147,15 @@ void
xfs_btree_commit_ifakeroot(
struct xfs_btree_cur *cur,
struct xfs_trans *tp,
- int whichfork,
- const struct xfs_btree_ops *ops)
+ int whichfork)
{
ASSERT(cur->bc_flags & XFS_BTREE_STAGING);
ASSERT(cur->bc_tp == NULL);
trace_xfs_btree_commit_ifakeroot(cur);
- kmem_free((void *)cur->bc_ops);
cur->bc_ino.ifake = NULL;
cur->bc_ino.whichfork = whichfork;
- cur->bc_ops = ops;
cur->bc_flags &= ~XFS_BTREE_STAGING;
cur->bc_tp = tp;
}
@@ -397,8 +295,7 @@ xfs_btree_bload_prep_block(
struct xfs_btree_block *new_block;
int ret;
- if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
- level == cur->bc_nlevels - 1) {
+ if (xfs_btree_at_iroot(cur, level)) {
struct xfs_ifork *ifp = xfs_btree_ifork_ptr(cur);
size_t new_size;
@@ -406,14 +303,12 @@ xfs_btree_bload_prep_block(
/* Allocate a new incore btree root block. */
new_size = bbl->iroot_size(cur, level, nr_this_block, priv);
- ifp->if_broot = kmem_zalloc(new_size, 0);
+ ifp->if_broot = kzalloc(new_size, GFP_KERNEL | __GFP_NOFAIL);
ifp->if_broot_bytes = (int)new_size;
/* Initialize it and send it out. */
- xfs_btree_init_block_int(cur->bc_mp, ifp->if_broot,
- XFS_BUF_DADDR_NULL, cur->bc_btnum, level,
- nr_this_block, cur->bc_ino.ip->i_ino,
- cur->bc_flags);
+ xfs_btree_init_block(cur->bc_mp, ifp->if_broot, cur->bc_ops,
+ level, nr_this_block, cur->bc_ino.ip->i_ino);
*bpp = NULL;
*blockp = ifp->if_broot;
@@ -704,7 +599,7 @@ xfs_btree_bload_compute_geometry(
xfs_btree_bload_level_geometry(cur, bbl, level, nr_this_level,
&avg_per_block, &level_blocks, &dontcare64);
- if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) {
+ if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) {
/*
* If all the items we want to store at this level
* would fit in the inode root block, then we have our
@@ -763,7 +658,7 @@ xfs_btree_bload_compute_geometry(
return -EOVERFLOW;
bbl->btree_height = cur->bc_nlevels;
- if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
+ if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE)
bbl->nr_blocks = nr_blocks - 1;
else
bbl->nr_blocks = nr_blocks;
@@ -890,7 +785,7 @@ xfs_btree_bload(
}
/* Initialize the new root. */
- if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) {
+ if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) {
ASSERT(xfs_btree_ptr_is_null(cur, &ptr));
cur->bc_ino.ifake->if_levels = cur->bc_nlevels;
cur->bc_ino.ifake->if_blocks = total_blocks - 1;
diff --git a/fs/xfs/libxfs/xfs_btree_staging.h b/fs/xfs/libxfs/xfs_btree_staging.h
index 055ea43b1e..0c9c2ffb12 100644
--- a/fs/xfs/libxfs/xfs_btree_staging.h
+++ b/fs/xfs/libxfs/xfs_btree_staging.h
@@ -22,7 +22,7 @@ struct xbtree_afakeroot {
void xfs_btree_stage_afakeroot(struct xfs_btree_cur *cur,
struct xbtree_afakeroot *afake);
void xfs_btree_commit_afakeroot(struct xfs_btree_cur *cur, struct xfs_trans *tp,
- struct xfs_buf *agbp, const struct xfs_btree_ops *ops);
+ struct xfs_buf *agbp);
/* Fake root for an inode-rooted btree. */
struct xbtree_ifakeroot {
@@ -41,10 +41,9 @@ struct xbtree_ifakeroot {
/* Cursor interactions with fake roots for inode-rooted btrees. */
void xfs_btree_stage_ifakeroot(struct xfs_btree_cur *cur,
- struct xbtree_ifakeroot *ifake,
- struct xfs_btree_ops **new_ops);
+ struct xbtree_ifakeroot *ifake);
void xfs_btree_commit_ifakeroot(struct xfs_btree_cur *cur, struct xfs_trans *tp,
- int whichfork, const struct xfs_btree_ops *ops);
+ int whichfork);
/* Bulk loading of staged btrees. */
typedef int (*xfs_btree_bload_get_records_fn)(struct xfs_btree_cur *cur,
@@ -76,8 +75,7 @@ struct xfs_btree_bload {
/*
* This function should return the size of the in-core btree root
- * block. It is only necessary for XFS_BTREE_ROOT_IN_INODE btree
- * types.
+ * block. It is only necessary for XFS_BTREE_TYPE_INODE btrees.
*/
xfs_btree_bload_iroot_size_fn iroot_size;
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 5457188bb4..718d071bb2 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -23,6 +23,7 @@
#include "xfs_buf_item.h"
#include "xfs_log.h"
#include "xfs_errortag.h"
+#include "xfs_health.h"
/*
* xfs_da_btree.c
@@ -85,7 +86,8 @@ xfs_da_state_alloc(
{
struct xfs_da_state *state;
- state = kmem_cache_zalloc(xfs_da_state_cache, GFP_NOFS | __GFP_NOFAIL);
+ state = kmem_cache_zalloc(xfs_da_state_cache,
+ GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL);
state->args = args;
state->mp = args->dp->i_mount;
return state;
@@ -352,6 +354,8 @@ const struct xfs_buf_ops xfs_da3_node_buf_ops = {
static int
xfs_da3_node_set_type(
struct xfs_trans *tp,
+ struct xfs_inode *dp,
+ int whichfork,
struct xfs_buf *bp)
{
struct xfs_da_blkinfo *info = bp->b_addr;
@@ -373,6 +377,7 @@ xfs_da3_node_set_type(
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, tp->t_mountp,
info, sizeof(*info));
xfs_trans_brelse(tp, bp);
+ xfs_dirattr_mark_sick(dp, whichfork);
return -EFSCORRUPTED;
}
}
@@ -391,7 +396,7 @@ xfs_da3_node_read(
&xfs_da3_node_buf_ops);
if (error || !*bpp || !tp)
return error;
- return xfs_da3_node_set_type(tp, *bpp);
+ return xfs_da3_node_set_type(tp, dp, whichfork, *bpp);
}
int
@@ -408,6 +413,8 @@ xfs_da3_node_read_mapped(
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, mappedbno,
XFS_FSB_TO_BB(mp, xfs_dabuf_nfsb(mp, whichfork)), 0,
bpp, &xfs_da3_node_buf_ops);
+ if (xfs_metadata_is_sick(error))
+ xfs_dirattr_mark_sick(dp, whichfork);
if (error || !*bpp)
return error;
@@ -418,7 +425,7 @@ xfs_da3_node_read_mapped(
if (!tp)
return 0;
- return xfs_da3_node_set_type(tp, *bpp);
+ return xfs_da3_node_set_type(tp, dp, whichfork, *bpp);
}
/*
@@ -631,6 +638,7 @@ xfs_da3_split(
if (node->hdr.info.forw) {
if (be32_to_cpu(node->hdr.info.forw) != addblk->blkno) {
xfs_buf_mark_corrupt(oldblk->bp);
+ xfs_da_mark_sick(state->args);
error = -EFSCORRUPTED;
goto out;
}
@@ -644,6 +652,7 @@ xfs_da3_split(
if (node->hdr.info.back) {
if (be32_to_cpu(node->hdr.info.back) != addblk->blkno) {
xfs_buf_mark_corrupt(oldblk->bp);
+ xfs_da_mark_sick(state->args);
error = -EFSCORRUPTED;
goto out;
}
@@ -1635,6 +1644,7 @@ xfs_da3_node_lookup_int(
if (magic != XFS_DA_NODE_MAGIC && magic != XFS_DA3_NODE_MAGIC) {
xfs_buf_mark_corrupt(blk->bp);
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
}
@@ -1650,6 +1660,7 @@ xfs_da3_node_lookup_int(
/* Tree taller than we can handle; bail out! */
if (nodehdr.level >= XFS_DA_NODE_MAXDEPTH) {
xfs_buf_mark_corrupt(blk->bp);
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
}
@@ -1658,6 +1669,7 @@ xfs_da3_node_lookup_int(
expected_level = nodehdr.level - 1;
else if (expected_level != nodehdr.level) {
xfs_buf_mark_corrupt(blk->bp);
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
} else
expected_level--;
@@ -1709,12 +1721,16 @@ xfs_da3_node_lookup_int(
}
/* We can't point back to the root. */
- if (XFS_IS_CORRUPT(dp->i_mount, blkno == args->geo->leafblk))
+ if (XFS_IS_CORRUPT(dp->i_mount, blkno == args->geo->leafblk)) {
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
+ }
}
- if (XFS_IS_CORRUPT(dp->i_mount, expected_level != 0))
+ if (XFS_IS_CORRUPT(dp->i_mount, expected_level != 0)) {
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
+ }
/*
* A leaf block that ends in the hashval that we are interested in
@@ -1732,6 +1748,7 @@ xfs_da3_node_lookup_int(
args->blkno = blk->blkno;
} else {
ASSERT(0);
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
}
if (((retval == -ENOENT) || (retval == -ENOATTR)) &&
@@ -2182,7 +2199,8 @@ xfs_da_grow_inode_int(
* If we didn't get it and the block might work if fragmented,
* try without the CONTIG flag. Loop until we get it all.
*/
- mapp = kmem_alloc(sizeof(*mapp) * count, 0);
+ mapp = kmalloc(sizeof(*mapp) * count,
+ GFP_KERNEL | __GFP_NOFAIL);
for (b = *bno, mapi = 0; b < *bno + count; ) {
c = (int)(*bno + count - b);
nmap = min(XFS_BMAP_MAX_NMAP, c);
@@ -2219,7 +2237,7 @@ xfs_da_grow_inode_int(
out_free_map:
if (mapp != &map)
- kmem_free(mapp);
+ kfree(mapp);
return error;
}
@@ -2297,8 +2315,10 @@ xfs_da3_swap_lastblock(
error = xfs_bmap_last_before(tp, dp, &lastoff, w);
if (error)
return error;
- if (XFS_IS_CORRUPT(mp, lastoff == 0))
+ if (XFS_IS_CORRUPT(mp, lastoff == 0)) {
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
+ }
/*
* Read the last block in the btree space.
*/
@@ -2348,6 +2368,7 @@ xfs_da3_swap_lastblock(
if (XFS_IS_CORRUPT(mp,
be32_to_cpu(sib_info->forw) != last_blkno ||
sib_info->magic != dead_info->magic)) {
+ xfs_da_mark_sick(args);
error = -EFSCORRUPTED;
goto done;
}
@@ -2368,6 +2389,7 @@ xfs_da3_swap_lastblock(
if (XFS_IS_CORRUPT(mp,
be32_to_cpu(sib_info->back) != last_blkno ||
sib_info->magic != dead_info->magic)) {
+ xfs_da_mark_sick(args);
error = -EFSCORRUPTED;
goto done;
}
@@ -2390,6 +2412,7 @@ xfs_da3_swap_lastblock(
xfs_da3_node_hdr_from_disk(dp->i_mount, &par_hdr, par_node);
if (XFS_IS_CORRUPT(mp,
level >= 0 && level != par_hdr.level + 1)) {
+ xfs_da_mark_sick(args);
error = -EFSCORRUPTED;
goto done;
}
@@ -2401,6 +2424,7 @@ xfs_da3_swap_lastblock(
entno++)
continue;
if (XFS_IS_CORRUPT(mp, entno == par_hdr.count)) {
+ xfs_da_mark_sick(args);
error = -EFSCORRUPTED;
goto done;
}
@@ -2426,6 +2450,7 @@ xfs_da3_swap_lastblock(
xfs_trans_brelse(tp, par_buf);
par_buf = NULL;
if (XFS_IS_CORRUPT(mp, par_blkno == 0)) {
+ xfs_da_mark_sick(args);
error = -EFSCORRUPTED;
goto done;
}
@@ -2435,6 +2460,7 @@ xfs_da3_swap_lastblock(
par_node = par_buf->b_addr;
xfs_da3_node_hdr_from_disk(dp->i_mount, &par_hdr, par_node);
if (XFS_IS_CORRUPT(mp, par_hdr.level != level)) {
+ xfs_da_mark_sick(args);
error = -EFSCORRUPTED;
goto done;
}
@@ -2518,7 +2544,8 @@ xfs_dabuf_map(
int error = 0, nirecs, i;
if (nfsb > 1)
- irecs = kmem_zalloc(sizeof(irec) * nfsb, KM_NOFS);
+ irecs = kzalloc(sizeof(irec) * nfsb,
+ GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL);
nirecs = nfsb;
error = xfs_bmapi_read(dp, bno, nfsb, irecs, &nirecs,
@@ -2531,7 +2558,8 @@ xfs_dabuf_map(
* larger one that needs to be free by the caller.
*/
if (nirecs > 1) {
- map = kmem_zalloc(nirecs * sizeof(struct xfs_buf_map), KM_NOFS);
+ map = kzalloc(nirecs * sizeof(struct xfs_buf_map),
+ GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL);
if (!map) {
error = -ENOMEM;
goto out_free_irecs;
@@ -2557,12 +2585,13 @@ xfs_dabuf_map(
*nmaps = nirecs;
out_free_irecs:
if (irecs != &irec)
- kmem_free(irecs);
+ kfree(irecs);
return error;
invalid_mapping:
/* Caller ok with no mapping. */
if (XFS_IS_CORRUPT(mp, !(flags & XFS_DABUF_MAP_HOLE_OK))) {
+ xfs_dirattr_mark_sick(dp, whichfork);
error = -EFSCORRUPTED;
if (xfs_error_level >= XFS_ERRLEVEL_LOW) {
xfs_alert(mp, "%s: bno %u inode %llu",
@@ -2613,7 +2642,7 @@ xfs_da_get_buf(
out_free:
if (mapp != &map)
- kmem_free(mapp);
+ kfree(mapp);
return error;
}
@@ -2644,6 +2673,8 @@ xfs_da_read_buf(
error = xfs_trans_read_buf_map(mp, tp, mp->m_ddev_targp, mapp, nmap, 0,
&bp, ops);
+ if (xfs_metadata_is_sick(error))
+ xfs_dirattr_mark_sick(dp, whichfork);
if (error)
goto out_free;
@@ -2654,7 +2685,7 @@ xfs_da_read_buf(
*bpp = bp;
out_free:
if (mapp != &map)
- kmem_free(mapp);
+ kfree(mapp);
return error;
}
@@ -2685,7 +2716,7 @@ xfs_da_reada_buf(
out_free:
if (mapp != &map)
- kmem_free(mapp);
+ kfree(mapp);
return error;
}
diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h
index 24f9d1461f..060e5c96b7 100644
--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/fs/xfs/libxfs/xfs_da_format.h
@@ -159,6 +159,17 @@ struct xfs_da3_intnode {
#define XFS_DIR3_FT_MAX 9
+#define XFS_DIR3_FTYPE_STR \
+ { XFS_DIR3_FT_UNKNOWN, "unknown" }, \
+ { XFS_DIR3_FT_REG_FILE, "file" }, \
+ { XFS_DIR3_FT_DIR, "directory" }, \
+ { XFS_DIR3_FT_CHRDEV, "char" }, \
+ { XFS_DIR3_FT_BLKDEV, "block" }, \
+ { XFS_DIR3_FT_FIFO, "fifo" }, \
+ { XFS_DIR3_FT_SOCK, "sock" }, \
+ { XFS_DIR3_FT_SYMLINK, "symlink" }, \
+ { XFS_DIR3_FT_WHT, "whiteout" }
+
/*
* Byte offset in data block and shortform entry.
*/
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 66a17910d0..c13276095c 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -819,16 +819,16 @@ xfs_defer_can_append(
/* Create a new pending item at the end of the transaction list. */
static inline struct xfs_defer_pending *
xfs_defer_alloc(
- struct xfs_trans *tp,
+ struct list_head *dfops,
const struct xfs_defer_op_type *ops)
{
struct xfs_defer_pending *dfp;
dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
- GFP_NOFS | __GFP_NOFAIL);
+ GFP_KERNEL | __GFP_NOFAIL);
dfp->dfp_ops = ops;
INIT_LIST_HEAD(&dfp->dfp_work);
- list_add_tail(&dfp->dfp_list, &tp->t_dfops);
+ list_add_tail(&dfp->dfp_list, dfops);
return dfp;
}
@@ -846,7 +846,7 @@ xfs_defer_add(
dfp = xfs_defer_find_last(tp, ops);
if (!dfp || !xfs_defer_can_append(dfp, ops))
- dfp = xfs_defer_alloc(tp, ops);
+ dfp = xfs_defer_alloc(&tp->t_dfops, ops);
xfs_defer_add_item(dfp, li);
trace_xfs_defer_add_item(tp->t_mountp, dfp, li);
@@ -870,7 +870,7 @@ xfs_defer_add_barrier(
if (dfp)
return;
- xfs_defer_alloc(tp, &xfs_barrier_defer_type);
+ xfs_defer_alloc(&tp->t_dfops, &xfs_barrier_defer_type);
trace_xfs_defer_add_item(tp->t_mountp, dfp, NULL);
}
@@ -885,14 +885,9 @@ xfs_defer_start_recovery(
struct list_head *r_dfops,
const struct xfs_defer_op_type *ops)
{
- struct xfs_defer_pending *dfp;
+ struct xfs_defer_pending *dfp = xfs_defer_alloc(r_dfops, ops);
- dfp = kmem_cache_zalloc(xfs_defer_pending_cache,
- GFP_NOFS | __GFP_NOFAIL);
- dfp->dfp_ops = ops;
dfp->dfp_intent = lip;
- INIT_LIST_HEAD(&dfp->dfp_work);
- list_add_tail(&dfp->dfp_list, r_dfops);
}
/*
@@ -979,7 +974,7 @@ xfs_defer_ops_capture(
return ERR_PTR(error);
/* Create an object to capture the defer ops. */
- dfc = kmem_zalloc(sizeof(*dfc), KM_NOFS);
+ dfc = kzalloc(sizeof(*dfc), GFP_KERNEL | __GFP_NOFAIL);
INIT_LIST_HEAD(&dfc->dfc_list);
INIT_LIST_HEAD(&dfc->dfc_dfops);
@@ -1011,7 +1006,7 @@ xfs_defer_ops_capture(
* transaction.
*/
for (i = 0; i < dfc->dfc_held.dr_inos; i++) {
- ASSERT(xfs_isilocked(dfc->dfc_held.dr_ip[i], XFS_ILOCK_EXCL));
+ xfs_assert_ilocked(dfc->dfc_held.dr_ip[i], XFS_ILOCK_EXCL);
ihold(VFS_I(dfc->dfc_held.dr_ip[i]));
}
@@ -1038,7 +1033,7 @@ xfs_defer_ops_capture_abort(
for (i = 0; i < dfc->dfc_held.dr_inos; i++)
xfs_irele(dfc->dfc_held.dr_ip[i]);
- kmem_free(dfc);
+ kfree(dfc);
}
/*
@@ -1114,7 +1109,7 @@ xfs_defer_ops_continue(
list_splice_init(&dfc->dfc_dfops, &tp->t_dfops);
tp->t_flags |= dfc->dfc_tpflags;
- kmem_free(dfc);
+ kfree(dfc);
}
/* Release the resources captured and continued during recovery. */
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index a766732815..4821519efa 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -18,6 +18,7 @@
#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_trace.h"
+#include "xfs_health.h"
const struct xfs_name xfs_name_dotdot = {
.name = (const unsigned char *)"..",
@@ -25,6 +26,12 @@ const struct xfs_name xfs_name_dotdot = {
.type = XFS_DIR3_FT_DIR,
};
+const struct xfs_name xfs_name_dot = {
+ .name = (const unsigned char *)".",
+ .len = 1,
+ .type = XFS_DIR3_FT_DIR,
+};
+
/*
* Convert inode mode to directory entry filetype
*/
@@ -104,13 +111,13 @@ xfs_da_mount(
ASSERT(mp->m_sb.sb_versionnum & XFS_SB_VERSION_DIRV2BIT);
ASSERT(xfs_dir2_dirblock_bytes(&mp->m_sb) <= XFS_MAX_BLOCKSIZE);
- mp->m_dir_geo = kmem_zalloc(sizeof(struct xfs_da_geometry),
- KM_MAYFAIL);
- mp->m_attr_geo = kmem_zalloc(sizeof(struct xfs_da_geometry),
- KM_MAYFAIL);
+ mp->m_dir_geo = kzalloc(sizeof(struct xfs_da_geometry),
+ GFP_KERNEL | __GFP_RETRY_MAYFAIL);
+ mp->m_attr_geo = kzalloc(sizeof(struct xfs_da_geometry),
+ GFP_KERNEL | __GFP_RETRY_MAYFAIL);
if (!mp->m_dir_geo || !mp->m_attr_geo) {
- kmem_free(mp->m_dir_geo);
- kmem_free(mp->m_attr_geo);
+ kfree(mp->m_dir_geo);
+ kfree(mp->m_attr_geo);
return -ENOMEM;
}
@@ -178,8 +185,8 @@ void
xfs_da_unmount(
struct xfs_mount *mp)
{
- kmem_free(mp->m_dir_geo);
- kmem_free(mp->m_attr_geo);
+ kfree(mp->m_dir_geo);
+ kfree(mp->m_attr_geo);
}
/*
@@ -236,7 +243,7 @@ xfs_dir_init(
if (error)
return error;
- args = kmem_zalloc(sizeof(*args), KM_NOFS);
+ args = kzalloc(sizeof(*args), GFP_KERNEL | __GFP_NOFAIL);
if (!args)
return -ENOMEM;
@@ -244,7 +251,7 @@ xfs_dir_init(
args->dp = dp;
args->trans = tp;
error = xfs_dir2_sf_create(args, pdp->i_ino);
- kmem_free(args);
+ kfree(args);
return error;
}
@@ -273,7 +280,7 @@ xfs_dir_createname(
XFS_STATS_INC(dp->i_mount, xs_dir_create);
}
- args = kmem_zalloc(sizeof(*args), KM_NOFS);
+ args = kzalloc(sizeof(*args), GFP_KERNEL | __GFP_NOFAIL);
if (!args)
return -ENOMEM;
@@ -313,7 +320,7 @@ xfs_dir_createname(
rval = xfs_dir2_node_addname(args);
out_free:
- kmem_free(args);
+ kfree(args);
return rval;
}
@@ -333,7 +340,8 @@ xfs_dir_cilookup_result(
!(args->op_flags & XFS_DA_OP_CILOOKUP))
return -EEXIST;
- args->value = kmem_alloc(len, KM_NOFS | KM_MAYFAIL);
+ args->value = kmalloc(len,
+ GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_RETRY_MAYFAIL);
if (!args->value)
return -ENOMEM;
@@ -364,15 +372,8 @@ xfs_dir_lookup(
ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
XFS_STATS_INC(dp->i_mount, xs_dir_lookup);
- /*
- * We need to use KM_NOFS here so that lockdep will not throw false
- * positive deadlock warnings on a non-transactional lookup path. It is
- * safe to recurse into inode recalim in that case, but lockdep can't
- * easily be taught about it. Hence KM_NOFS avoids having to add more
- * lockdep Doing this avoids having to add a bunch of lockdep class
- * annotations into the reclaim path for the ilock.
- */
- args = kmem_zalloc(sizeof(*args), KM_NOFS);
+ args = kzalloc(sizeof(*args),
+ GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL);
args->geo = dp->i_mount->m_dir_geo;
args->name = name->name;
args->namelen = name->len;
@@ -419,7 +420,7 @@ out_check_rval:
}
out_free:
xfs_iunlock(dp, lock_mode);
- kmem_free(args);
+ kfree(args);
return rval;
}
@@ -441,7 +442,7 @@ xfs_dir_removename(
ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
XFS_STATS_INC(dp->i_mount, xs_dir_remove);
- args = kmem_zalloc(sizeof(*args), KM_NOFS);
+ args = kzalloc(sizeof(*args), GFP_KERNEL | __GFP_NOFAIL);
if (!args)
return -ENOMEM;
@@ -477,7 +478,7 @@ xfs_dir_removename(
else
rval = xfs_dir2_node_removename(args);
out_free:
- kmem_free(args);
+ kfree(args);
return rval;
}
@@ -502,7 +503,7 @@ xfs_dir_replace(
if (rval)
return rval;
- args = kmem_zalloc(sizeof(*args), KM_NOFS);
+ args = kzalloc(sizeof(*args), GFP_KERNEL | __GFP_NOFAIL);
if (!args)
return -ENOMEM;
@@ -538,7 +539,7 @@ xfs_dir_replace(
else
rval = xfs_dir2_node_replace(args);
out_free:
- kmem_free(args);
+ kfree(args);
return rval;
}
@@ -626,8 +627,10 @@ xfs_dir2_isblock(
return 0;
*isblock = true;
- if (XFS_IS_CORRUPT(mp, args->dp->i_disk_size != args->geo->blksize))
+ if (XFS_IS_CORRUPT(mp, args->dp->i_disk_size != args->geo->blksize)) {
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
+ }
return 0;
}
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index 19af22a16c..8497d041f3 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -22,6 +22,19 @@ struct xfs_dir3_icfree_hdr;
struct xfs_dir3_icleaf_hdr;
extern const struct xfs_name xfs_name_dotdot;
+extern const struct xfs_name xfs_name_dot;
+
+static inline bool
+xfs_dir2_samename(
+ const struct xfs_name *n1,
+ const struct xfs_name *n2)
+{
+ if (n1 == n2)
+ return true;
+ if (n1->len != n2->len)
+ return false;
+ return !memcmp(n1->name, n2->name, n1->len);
+}
/*
* Convert inode mode to directory entry filetype
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index 3c256d4cc4..a2da007adb 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -20,6 +20,7 @@
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_log.h"
+#include "xfs_health.h"
/*
* Local function prototypes.
@@ -152,6 +153,7 @@ xfs_dir3_block_read(
__xfs_buf_mark_corrupt(*bpp, fa);
xfs_trans_brelse(tp, *bpp);
*bpp = NULL;
+ xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
return -EFSCORRUPTED;
}
@@ -1108,7 +1110,7 @@ xfs_dir2_sf_to_block(
* Copy the directory into a temporary buffer.
* Then pitch the incore inode data so we can make extents.
*/
- sfp = kmem_alloc(ifp->if_bytes, 0);
+ sfp = kmalloc(ifp->if_bytes, GFP_KERNEL | __GFP_NOFAIL);
memcpy(sfp, oldsfp, ifp->if_bytes);
xfs_idata_realloc(dp, -ifp->if_bytes, XFS_DATA_FORK);
@@ -1253,7 +1255,7 @@ xfs_dir2_sf_to_block(
sfep = xfs_dir2_sf_nextentry(mp, sfp, sfep);
}
/* Done with the temporary buffer */
- kmem_free(sfp);
+ kfree(sfp);
/*
* Sort the leaf entries by hash value.
*/
@@ -1268,6 +1270,6 @@ xfs_dir2_sf_to_block(
xfs_dir3_data_check(dp, bp);
return 0;
out_free:
- kmem_free(sfp);
+ kfree(sfp);
return error;
}
diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c
index dbcf58979a..7a6d965bea 100644
--- a/fs/xfs/libxfs/xfs_dir2_data.c
+++ b/fs/xfs/libxfs/xfs_dir2_data.c
@@ -18,6 +18,7 @@
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_log.h"
+#include "xfs_health.h"
static xfs_failaddr_t xfs_dir2_data_freefind_verify(
struct xfs_dir2_data_hdr *hdr, struct xfs_dir2_data_free *bf,
@@ -433,6 +434,7 @@ xfs_dir3_data_read(
__xfs_buf_mark_corrupt(*bpp, fa);
xfs_trans_brelse(tp, *bpp);
*bpp = NULL;
+ xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
return -EFSCORRUPTED;
}
@@ -1198,6 +1200,7 @@ xfs_dir2_data_use_free(
corrupt:
xfs_corruption_error(__func__, XFS_ERRLEVEL_LOW, args->dp->i_mount,
hdr, sizeof(*hdr), __FILE__, __LINE__, fa);
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index cb9e950a91..08dda5ce9d 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -19,6 +19,7 @@
#include "xfs_trace.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
+#include "xfs_health.h"
/*
* Local function declarations.
@@ -1393,8 +1394,10 @@ xfs_dir2_leaf_removename(
bestsp = xfs_dir2_leaf_bests_p(ltp);
if (be16_to_cpu(bestsp[db]) != oldbest) {
xfs_buf_mark_corrupt(lbp);
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
}
+
/*
* Mark the former data entry unused.
*/
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index 7a03aeb9f4..be0b883402 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -20,6 +20,7 @@
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_log.h"
+#include "xfs_health.h"
/*
* Function declarations.
@@ -231,6 +232,7 @@ __xfs_dir3_free_read(
__xfs_buf_mark_corrupt(*bpp, fa);
xfs_trans_brelse(tp, *bpp);
*bpp = NULL;
+ xfs_dirattr_mark_sick(dp, XFS_DATA_FORK);
return -EFSCORRUPTED;
}
@@ -443,6 +445,7 @@ xfs_dir2_leaf_to_node(
if (be32_to_cpu(ltp->bestcount) >
(uint)dp->i_disk_size / args->geo->blksize) {
xfs_buf_mark_corrupt(lbp);
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
}
@@ -517,6 +520,7 @@ xfs_dir2_leafn_add(
*/
if (index < 0) {
xfs_buf_mark_corrupt(bp);
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
}
@@ -736,6 +740,7 @@ xfs_dir2_leafn_lookup_for_addname(
cpu_to_be16(NULLDATAOFF))) {
if (curfdb != newfdb)
xfs_trans_brelse(tp, curbp);
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
}
curfdb = newfdb;
@@ -804,6 +809,7 @@ xfs_dir2_leafn_lookup_for_entry(
xfs_dir3_leaf_check(dp, bp);
if (leafhdr.count <= 0) {
xfs_buf_mark_corrupt(bp);
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
}
@@ -1739,6 +1745,7 @@ xfs_dir2_node_add_datablk(
} else {
xfs_alert(mp, " ... fblk is NULL");
}
+ xfs_da_mark_sick(args);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c
index e1f83fc7b6..17a20384c8 100644
--- a/fs/xfs/libxfs/xfs_dir2_sf.c
+++ b/fs/xfs/libxfs/xfs_dir2_sf.c
@@ -276,7 +276,7 @@ xfs_dir2_block_to_sf(
* format the data into. Once we have formatted the data, we can free
* the block and copy the formatted data into the inode literal area.
*/
- sfp = kmem_alloc(mp->m_sb.sb_inodesize, 0);
+ sfp = kmalloc(mp->m_sb.sb_inodesize, GFP_KERNEL | __GFP_NOFAIL);
memcpy(sfp, sfhp, xfs_dir2_sf_hdr_size(sfhp->i8count));
/*
@@ -350,7 +350,7 @@ xfs_dir2_block_to_sf(
xfs_dir2_sf_check(args);
out:
xfs_trans_log_inode(args->trans, dp, logflags);
- kmem_free(sfp);
+ kfree(sfp);
return error;
}
@@ -524,7 +524,7 @@ xfs_dir2_sf_addname_hard(
* Copy the old directory to the stack buffer.
*/
old_isize = (int)dp->i_disk_size;
- buf = kmem_alloc(old_isize, 0);
+ buf = kmalloc(old_isize, GFP_KERNEL | __GFP_NOFAIL);
oldsfp = (xfs_dir2_sf_hdr_t *)buf;
memcpy(oldsfp, dp->i_df.if_data, old_isize);
/*
@@ -576,7 +576,7 @@ xfs_dir2_sf_addname_hard(
sfep = xfs_dir2_sf_nextentry(mp, sfp, sfep);
memcpy(sfep, oldsfep, old_isize - nbytes);
}
- kmem_free(buf);
+ kfree(buf);
dp->i_disk_size = new_isize;
xfs_dir2_sf_check(args);
}
@@ -1151,7 +1151,7 @@ xfs_dir2_sf_toino4(
* Don't want xfs_idata_realloc copying the data here.
*/
oldsize = dp->i_df.if_bytes;
- buf = kmem_alloc(oldsize, 0);
+ buf = kmalloc(oldsize, GFP_KERNEL | __GFP_NOFAIL);
ASSERT(oldsfp->i8count == 1);
memcpy(buf, oldsfp, oldsize);
/*
@@ -1190,7 +1190,7 @@ xfs_dir2_sf_toino4(
/*
* Clean up the inode.
*/
- kmem_free(buf);
+ kfree(buf);
dp->i_disk_size = newsize;
xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA);
}
@@ -1223,7 +1223,7 @@ xfs_dir2_sf_toino8(
* Don't want xfs_idata_realloc copying the data here.
*/
oldsize = dp->i_df.if_bytes;
- buf = kmem_alloc(oldsize, 0);
+ buf = kmalloc(oldsize, GFP_KERNEL | __GFP_NOFAIL);
ASSERT(oldsfp->i8count == 0);
memcpy(buf, oldsfp, oldsize);
/*
@@ -1262,7 +1262,7 @@ xfs_dir2_sf_toino8(
/*
* Clean up the inode.
*/
- kmem_free(buf);
+ kfree(buf);
dp->i_disk_size = newsize;
xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA);
}
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 382ab1e71c..2b2f9050fb 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -477,15 +477,9 @@ xfs_is_quota_inode(struct xfs_sb *sbp, xfs_ino_t ino)
#define XFS_AGI_GOOD_VERSION(v) ((v) == XFS_AGI_VERSION)
/*
- * Btree number 0 is bno, 1 is cnt, 2 is rmap. This value gives the size of the
- * arrays below.
- */
-#define XFS_BTNUM_AGF ((int)XFS_BTNUM_RMAPi + 1)
-
-/*
- * The second word of agf_levels in the first a.g. overlaps the EFS
- * superblock's magic number. Since the magic numbers valid for EFS
- * are > 64k, our value cannot be confused for an EFS superblock's.
+ * agf_cnt_level in the first AGF overlaps the EFS superblock's magic number.
+ * Since the magic numbers valid for EFS are > 64k, our value cannot be confused
+ * for an EFS superblock.
*/
typedef struct xfs_agf {
@@ -499,8 +493,13 @@ typedef struct xfs_agf {
/*
* Freespace and rmap information
*/
- __be32 agf_roots[XFS_BTNUM_AGF]; /* root blocks */
- __be32 agf_levels[XFS_BTNUM_AGF]; /* btree levels */
+ __be32 agf_bno_root; /* bnobt root block */
+ __be32 agf_cnt_root; /* cntbt root block */
+ __be32 agf_rmap_root; /* rmapbt root block */
+
+ __be32 agf_bno_level; /* bnobt btree levels */
+ __be32 agf_cnt_level; /* cntbt btree levels */
+ __be32 agf_rmap_level; /* rmapbt btree levels */
__be32 agf_flfirst; /* first freelist block's index */
__be32 agf_fllast; /* last freelist block's index */
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 6360073865..ca1b17d014 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -195,6 +195,8 @@ struct xfs_fsop_geom {
#define XFS_FSOP_GEOM_SICK_PQUOTA (1 << 3) /* project quota */
#define XFS_FSOP_GEOM_SICK_RT_BITMAP (1 << 4) /* realtime bitmap */
#define XFS_FSOP_GEOM_SICK_RT_SUMMARY (1 << 5) /* realtime summary */
+#define XFS_FSOP_GEOM_SICK_QUOTACHECK (1 << 6) /* quota counts */
+#define XFS_FSOP_GEOM_SICK_NLINKS (1 << 7) /* inode link counts */
/* Output for XFS_FS_COUNTS */
typedef struct xfs_fsop_counts {
@@ -292,6 +294,7 @@ struct xfs_ag_geometry {
#define XFS_AG_GEOM_SICK_FINOBT (1 << 7) /* free inode index */
#define XFS_AG_GEOM_SICK_RMAPBT (1 << 8) /* reverse mappings */
#define XFS_AG_GEOM_SICK_REFCNTBT (1 << 9) /* reference counts */
+#define XFS_AG_GEOM_SICK_INODES (1 << 10) /* bad inodes were seen */
/*
* Structures for XFS_IOC_FSGROWFSDATA, XFS_IOC_FSGROWFSLOG & XFS_IOC_FSGROWFSRT
@@ -709,9 +712,12 @@ struct xfs_scrub_metadata {
#define XFS_SCRUB_TYPE_GQUOTA 22 /* group quotas */
#define XFS_SCRUB_TYPE_PQUOTA 23 /* project quotas */
#define XFS_SCRUB_TYPE_FSCOUNTERS 24 /* fs summary counters */
+#define XFS_SCRUB_TYPE_QUOTACHECK 25 /* quota counters */
+#define XFS_SCRUB_TYPE_NLINKS 26 /* inode link counts */
+#define XFS_SCRUB_TYPE_HEALTHY 27 /* everything checked out ok */
/* Number of scrub subcommands. */
-#define XFS_SCRUB_TYPE_NR 25
+#define XFS_SCRUB_TYPE_NR 28
/* i: Repair this metadata. */
#define XFS_SCRUB_IFLAG_REPAIR (1u << 0)
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index 6296993ff8..3c64b5f9bd 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -26,21 +26,40 @@
* and the "sick" field tells us if that piece was found to need repairs.
* Therefore we can conclude that for a given sick flag value:
*
- * - checked && sick => metadata needs repair
- * - checked && !sick => metadata is ok
- * - !checked => has not been examined since mount
+ * - checked && sick => metadata needs repair
+ * - checked && !sick => metadata is ok
+ * - !checked && sick => errors have been observed during normal operation,
+ * but the metadata has not been checked thoroughly
+ * - !checked && !sick => has not been examined since mount
+ *
+ * Evidence of health problems can be sorted into three basic categories:
+ *
+ * a) Primary evidence, which signals that something is defective within the
+ * general grouping of metadata.
+ *
+ * b) Secondary evidence, which are side effects of primary problem but are
+ * not themselves problems. These can be forgotten when the primary
+ * health problems are addressed.
+ *
+ * c) Indirect evidence, which points to something being wrong in another
+ * group, but we had to release resources and this is all that's left of
+ * that state.
*/
struct xfs_mount;
struct xfs_perag;
struct xfs_inode;
struct xfs_fsop_geom;
+struct xfs_btree_cur;
+struct xfs_da_args;
/* Observable health issues for metadata spanning the entire filesystem. */
#define XFS_SICK_FS_COUNTERS (1 << 0) /* summary counters */
#define XFS_SICK_FS_UQUOTA (1 << 1) /* user quota */
#define XFS_SICK_FS_GQUOTA (1 << 2) /* group quota */
#define XFS_SICK_FS_PQUOTA (1 << 3) /* project quota */
+#define XFS_SICK_FS_QUOTACHECK (1 << 4) /* quota counts */
+#define XFS_SICK_FS_NLINKS (1 << 5) /* inode link counts */
/* Observable health issues for realtime volume metadata. */
#define XFS_SICK_RT_BITMAP (1 << 0) /* realtime bitmap */
@@ -57,6 +76,7 @@ struct xfs_fsop_geom;
#define XFS_SICK_AG_FINOBT (1 << 7) /* free inode index */
#define XFS_SICK_AG_RMAPBT (1 << 8) /* reverse mappings */
#define XFS_SICK_AG_REFCNTBT (1 << 9) /* reference counts */
+#define XFS_SICK_AG_INODES (1 << 10) /* inactivated bad inodes */
/* Observable health issues for inode metadata. */
#define XFS_SICK_INO_CORE (1 << 0) /* inode core */
@@ -73,11 +93,16 @@ struct xfs_fsop_geom;
#define XFS_SICK_INO_DIR_ZAPPED (1 << 10) /* directory erased */
#define XFS_SICK_INO_SYMLINK_ZAPPED (1 << 11) /* symlink erased */
+/* Don't propagate sick status to ag health summary during inactivation */
+#define XFS_SICK_INO_FORGET (1 << 12)
+
/* Primary evidence of health problems in a given group. */
#define XFS_SICK_FS_PRIMARY (XFS_SICK_FS_COUNTERS | \
XFS_SICK_FS_UQUOTA | \
XFS_SICK_FS_GQUOTA | \
- XFS_SICK_FS_PQUOTA)
+ XFS_SICK_FS_PQUOTA | \
+ XFS_SICK_FS_QUOTACHECK | \
+ XFS_SICK_FS_NLINKS)
#define XFS_SICK_RT_PRIMARY (XFS_SICK_RT_BITMAP | \
XFS_SICK_RT_SUMMARY)
@@ -107,29 +132,86 @@ struct xfs_fsop_geom;
XFS_SICK_INO_DIR_ZAPPED | \
XFS_SICK_INO_SYMLINK_ZAPPED)
-/* These functions must be provided by the xfs implementation. */
+/* Secondary state related to (but not primary evidence of) health problems. */
+#define XFS_SICK_FS_SECONDARY (0)
+#define XFS_SICK_RT_SECONDARY (0)
+#define XFS_SICK_AG_SECONDARY (0)
+#define XFS_SICK_INO_SECONDARY (XFS_SICK_INO_FORGET)
+
+/* Evidence of health problems elsewhere. */
+#define XFS_SICK_FS_INDIRECT (0)
+#define XFS_SICK_RT_INDIRECT (0)
+#define XFS_SICK_AG_INDIRECT (XFS_SICK_AG_INODES)
+#define XFS_SICK_INO_INDIRECT (0)
+
+/* All health masks. */
+#define XFS_SICK_FS_ALL (XFS_SICK_FS_PRIMARY | \
+ XFS_SICK_FS_SECONDARY | \
+ XFS_SICK_FS_INDIRECT)
+
+#define XFS_SICK_RT_ALL (XFS_SICK_RT_PRIMARY | \
+ XFS_SICK_RT_SECONDARY | \
+ XFS_SICK_RT_INDIRECT)
+
+#define XFS_SICK_AG_ALL (XFS_SICK_AG_PRIMARY | \
+ XFS_SICK_AG_SECONDARY | \
+ XFS_SICK_AG_INDIRECT)
+
+#define XFS_SICK_INO_ALL (XFS_SICK_INO_PRIMARY | \
+ XFS_SICK_INO_SECONDARY | \
+ XFS_SICK_INO_INDIRECT | \
+ XFS_SICK_INO_ZAPPED)
+
+/*
+ * These functions must be provided by the xfs implementation. Function
+ * behavior with respect to the first argument should be as follows:
+ *
+ * xfs_*_mark_sick: Set the sick flags and do not set checked flags.
+ * Runtime code should call this upon encountering
+ * a corruption.
+ *
+ * xfs_*_mark_corrupt: Set the sick and checked flags simultaneously.
+ * Fsck tools should call this when corruption is
+ * found.
+ *
+ * xfs_*_mark_healthy: Clear the sick flags and set the checked flags.
+ * Fsck tools should call this after correcting errors.
+ *
+ * xfs_*_measure_sickness: Return the sick and check status in the provided
+ * out parameters.
+ */
void xfs_fs_mark_sick(struct xfs_mount *mp, unsigned int mask);
+void xfs_fs_mark_corrupt(struct xfs_mount *mp, unsigned int mask);
void xfs_fs_mark_healthy(struct xfs_mount *mp, unsigned int mask);
void xfs_fs_measure_sickness(struct xfs_mount *mp, unsigned int *sick,
unsigned int *checked);
void xfs_rt_mark_sick(struct xfs_mount *mp, unsigned int mask);
+void xfs_rt_mark_corrupt(struct xfs_mount *mp, unsigned int mask);
void xfs_rt_mark_healthy(struct xfs_mount *mp, unsigned int mask);
void xfs_rt_measure_sickness(struct xfs_mount *mp, unsigned int *sick,
unsigned int *checked);
+void xfs_agno_mark_sick(struct xfs_mount *mp, xfs_agnumber_t agno,
+ unsigned int mask);
void xfs_ag_mark_sick(struct xfs_perag *pag, unsigned int mask);
+void xfs_ag_mark_corrupt(struct xfs_perag *pag, unsigned int mask);
void xfs_ag_mark_healthy(struct xfs_perag *pag, unsigned int mask);
void xfs_ag_measure_sickness(struct xfs_perag *pag, unsigned int *sick,
unsigned int *checked);
void xfs_inode_mark_sick(struct xfs_inode *ip, unsigned int mask);
+void xfs_inode_mark_corrupt(struct xfs_inode *ip, unsigned int mask);
void xfs_inode_mark_healthy(struct xfs_inode *ip, unsigned int mask);
void xfs_inode_measure_sickness(struct xfs_inode *ip, unsigned int *sick,
unsigned int *checked);
void xfs_health_unmount(struct xfs_mount *mp);
+void xfs_bmap_mark_sick(struct xfs_inode *ip, int whichfork);
+void xfs_btree_mark_sick(struct xfs_btree_cur *cur);
+void xfs_dirattr_mark_sick(struct xfs_inode *ip, int whichfork);
+void xfs_da_mark_sick(struct xfs_da_args *args);
/* Now some helpers. */
@@ -197,4 +279,7 @@ void xfs_fsop_geom_health(struct xfs_mount *mp, struct xfs_fsop_geom *geo);
void xfs_ag_geom_health(struct xfs_perag *pag, struct xfs_ag_geometry *ageo);
void xfs_bulkstat_health(struct xfs_inode *ip, struct xfs_bulkstat *bs);
+#define xfs_metadata_is_sick(error) \
+ (unlikely((error) == -EFSCORRUPTED || (error) == -EFSBADCRC))
+
#endif /* __XFS_HEALTH_H__ */
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 2361a22035..e5ac3e5430 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -27,6 +27,7 @@
#include "xfs_log.h"
#include "xfs_rmap.h"
#include "xfs_ag.h"
+#include "xfs_health.h"
/*
* Lookup a record by ino in the btree given by cur.
@@ -140,13 +141,13 @@ xfs_inobt_complain_bad_rec(
struct xfs_mount *mp = cur->bc_mp;
xfs_warn(mp,
- "%s Inode BTree record corruption in AG %d detected at %pS!",
- cur->bc_btnum == XFS_BTNUM_INO ? "Used" : "Free",
- cur->bc_ag.pag->pag_agno, fa);
+ "%sbt record corruption in AG %d detected at %pS!",
+ cur->bc_ops->name, cur->bc_ag.pag->pag_agno, fa);
xfs_warn(mp,
"start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x",
irec->ir_startino, irec->ir_count, irec->ir_freecount,
irec->ir_free, irec->ir_holemask);
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
}
@@ -205,14 +206,17 @@ xfs_inobt_insert(
struct xfs_buf *agbp,
xfs_agino_t newino,
xfs_agino_t newlen,
- xfs_btnum_t btnum)
+ bool is_finobt)
{
struct xfs_btree_cur *cur;
xfs_agino_t thisino;
int i;
int error;
- cur = xfs_inobt_init_cursor(pag, tp, agbp, btnum);
+ if (is_finobt)
+ cur = xfs_finobt_init_cursor(pag, tp, agbp);
+ else
+ cur = xfs_inobt_init_cursor(pag, tp, agbp);
for (thisino = newino;
thisino < newino + newlen;
@@ -528,16 +532,14 @@ __xfs_inobt_rec_merge(
}
/*
- * Insert a new sparse inode chunk into the associated inode btree. The inode
- * record for the sparse chunk is pre-aligned to a startino that should match
- * any pre-existing sparse inode record in the tree. This allows sparse chunks
- * to fill over time.
+ * Insert a new sparse inode chunk into the associated inode allocation btree.
+ * The inode record for the sparse chunk is pre-aligned to a startino that
+ * should match any pre-existing sparse inode record in the tree. This allows
+ * sparse chunks to fill over time.
*
- * This function supports two modes of handling preexisting records depending on
- * the merge flag. If merge is true, the provided record is merged with the
+ * If no preexisting record exists, the provided record is inserted.
+ * If there is a preexisting record, the provided record is merged with the
* existing record and updated in place. The merged record is returned in nrec.
- * If merge is false, an existing record is replaced with the provided record.
- * If no preexisting record exists, the provided record is always inserted.
*
* It is considered corruption if a merge is requested and not possible. Given
* the sparse inode alignment constraints, this should never happen.
@@ -547,9 +549,7 @@ xfs_inobt_insert_sprec(
struct xfs_perag *pag,
struct xfs_trans *tp,
struct xfs_buf *agbp,
- int btnum,
- struct xfs_inobt_rec_incore *nrec, /* in/out: new/merged rec. */
- bool merge) /* merge or replace */
+ struct xfs_inobt_rec_incore *nrec) /* in/out: new/merged rec. */
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_btree_cur *cur;
@@ -557,7 +557,7 @@ xfs_inobt_insert_sprec(
int i;
struct xfs_inobt_rec_incore rec;
- cur = xfs_inobt_init_cursor(pag, tp, agbp, btnum);
+ cur = xfs_inobt_init_cursor(pag, tp, agbp);
/* the new record is pre-aligned so we know where to look */
error = xfs_inobt_lookup(cur, nrec->ir_startino, XFS_LOOKUP_EQ, &i);
@@ -571,6 +571,7 @@ xfs_inobt_insert_sprec(
if (error)
goto error;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error;
}
@@ -579,45 +580,45 @@ xfs_inobt_insert_sprec(
}
/*
- * A record exists at this startino. Merge or replace the record
- * depending on what we've been asked to do.
+ * A record exists at this startino. Merge the records.
*/
- if (merge) {
- error = xfs_inobt_get_rec(cur, &rec, &i);
- if (error)
- goto error;
- if (XFS_IS_CORRUPT(mp, i != 1)) {
- error = -EFSCORRUPTED;
- goto error;
- }
- if (XFS_IS_CORRUPT(mp, rec.ir_startino != nrec->ir_startino)) {
- error = -EFSCORRUPTED;
- goto error;
- }
+ error = xfs_inobt_get_rec(cur, &rec, &i);
+ if (error)
+ goto error;
+ if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
+ error = -EFSCORRUPTED;
+ goto error;
+ }
+ if (XFS_IS_CORRUPT(mp, rec.ir_startino != nrec->ir_startino)) {
+ xfs_btree_mark_sick(cur);
+ error = -EFSCORRUPTED;
+ goto error;
+ }
- /*
- * This should never fail. If we have coexisting records that
- * cannot merge, something is seriously wrong.
- */
- if (XFS_IS_CORRUPT(mp, !__xfs_inobt_can_merge(nrec, &rec))) {
- error = -EFSCORRUPTED;
- goto error;
- }
+ /*
+ * This should never fail. If we have coexisting records that
+ * cannot merge, something is seriously wrong.
+ */
+ if (XFS_IS_CORRUPT(mp, !__xfs_inobt_can_merge(nrec, &rec))) {
+ xfs_btree_mark_sick(cur);
+ error = -EFSCORRUPTED;
+ goto error;
+ }
- trace_xfs_irec_merge_pre(mp, pag->pag_agno, rec.ir_startino,
- rec.ir_holemask, nrec->ir_startino,
- nrec->ir_holemask);
+ trace_xfs_irec_merge_pre(mp, pag->pag_agno, rec.ir_startino,
+ rec.ir_holemask, nrec->ir_startino,
+ nrec->ir_holemask);
- /* merge to nrec to output the updated record */
- __xfs_inobt_rec_merge(nrec, &rec);
+ /* merge to nrec to output the updated record */
+ __xfs_inobt_rec_merge(nrec, &rec);
- trace_xfs_irec_merge_post(mp, pag->pag_agno, nrec->ir_startino,
- nrec->ir_holemask);
+ trace_xfs_irec_merge_post(mp, pag->pag_agno, nrec->ir_startino,
+ nrec->ir_holemask);
- error = xfs_inobt_rec_check_count(mp, nrec);
- if (error)
- goto error;
- }
+ error = xfs_inobt_rec_check_count(mp, nrec);
+ if (error)
+ goto error;
error = xfs_inobt_update(cur, nrec);
if (error)
@@ -632,6 +633,59 @@ error:
}
/*
+ * Insert a new sparse inode chunk into the free inode btree. The inode
+ * record for the sparse chunk is pre-aligned to a startino that should match
+ * any pre-existing sparse inode record in the tree. This allows sparse chunks
+ * to fill over time.
+ *
+ * The new record is always inserted, overwriting a pre-existing record if
+ * there is one.
+ */
+STATIC int
+xfs_finobt_insert_sprec(
+ struct xfs_perag *pag,
+ struct xfs_trans *tp,
+ struct xfs_buf *agbp,
+ struct xfs_inobt_rec_incore *nrec) /* in/out: new rec. */
+{
+ struct xfs_mount *mp = pag->pag_mount;
+ struct xfs_btree_cur *cur;
+ int error;
+ int i;
+
+ cur = xfs_finobt_init_cursor(pag, tp, agbp);
+
+ /* the new record is pre-aligned so we know where to look */
+ error = xfs_inobt_lookup(cur, nrec->ir_startino, XFS_LOOKUP_EQ, &i);
+ if (error)
+ goto error;
+ /* if nothing there, insert a new record and return */
+ if (i == 0) {
+ error = xfs_inobt_insert_rec(cur, nrec->ir_holemask,
+ nrec->ir_count, nrec->ir_freecount,
+ nrec->ir_free, &i);
+ if (error)
+ goto error;
+ if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
+ error = -EFSCORRUPTED;
+ goto error;
+ }
+ } else {
+ error = xfs_inobt_update(cur, nrec);
+ if (error)
+ goto error;
+ }
+
+ xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+ return 0;
+error:
+ xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+ return error;
+}
+
+
+/*
* Allocate new inodes in the allocation group specified by agbp. Returns 0 if
* inodes were allocated in this AG; -EAGAIN if there was no space in this AG so
* the caller knows it can try another AG, a hard -ENOSPC when over the maximum
@@ -857,8 +911,7 @@ sparse_alloc:
* if necessary. If a merge does occur, rec is updated to the
* merged record.
*/
- error = xfs_inobt_insert_sprec(pag, tp, agbp,
- XFS_BTNUM_INO, &rec, true);
+ error = xfs_inobt_insert_sprec(pag, tp, agbp, &rec);
if (error == -EFSCORRUPTED) {
xfs_alert(args.mp,
"invalid sparse inode record: ino 0x%llx holemask 0x%x count %u",
@@ -882,21 +935,19 @@ sparse_alloc:
* existing record with this one.
*/
if (xfs_has_finobt(args.mp)) {
- error = xfs_inobt_insert_sprec(pag, tp, agbp,
- XFS_BTNUM_FINO, &rec, false);
+ error = xfs_finobt_insert_sprec(pag, tp, agbp, &rec);
if (error)
return error;
}
} else {
/* full chunk - insert new records to both btrees */
- error = xfs_inobt_insert(pag, tp, agbp, newino, newlen,
- XFS_BTNUM_INO);
+ error = xfs_inobt_insert(pag, tp, agbp, newino, newlen, false);
if (error)
return error;
if (xfs_has_finobt(args.mp)) {
error = xfs_inobt_insert(pag, tp, agbp, newino,
- newlen, XFS_BTNUM_FINO);
+ newlen, true);
if (error)
return error;
}
@@ -949,8 +1000,10 @@ xfs_ialloc_next_rec(
error = xfs_inobt_get_rec(cur, rec, &i);
if (error)
return error;
- if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+ if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
}
return 0;
@@ -974,8 +1027,10 @@ xfs_ialloc_get_rec(
error = xfs_inobt_get_rec(cur, rec, &i);
if (error)
return error;
- if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+ if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
}
return 0;
@@ -1030,7 +1085,7 @@ xfs_dialloc_ag_inobt(
ASSERT(pag->pagi_freecount > 0);
restart_pagno:
- cur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_INO);
+ cur = xfs_inobt_init_cursor(pag, tp, agbp);
/*
* If pagino is 0 (this is the root inode allocation) use newino.
* This must work because we've just allocated some.
@@ -1053,6 +1108,7 @@ xfs_dialloc_ag_inobt(
if (error)
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1061,6 +1117,7 @@ xfs_dialloc_ag_inobt(
if (error)
goto error0;
if (XFS_IS_CORRUPT(mp, j != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1219,6 +1276,7 @@ xfs_dialloc_ag_inobt(
if (error)
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1228,6 +1286,7 @@ xfs_dialloc_ag_inobt(
if (error)
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1237,6 +1296,7 @@ xfs_dialloc_ag_inobt(
if (error)
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1297,8 +1357,10 @@ xfs_dialloc_ag_finobt_near(
error = xfs_inobt_get_rec(lcur, rec, &i);
if (error)
return error;
- if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1))
+ if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(lcur);
return -EFSCORRUPTED;
+ }
/*
* See if we've landed in the parent inode record. The finobt
@@ -1322,12 +1384,14 @@ xfs_dialloc_ag_finobt_near(
if (error)
goto error_rcur;
if (XFS_IS_CORRUPT(lcur->bc_mp, j != 1)) {
+ xfs_btree_mark_sick(lcur);
error = -EFSCORRUPTED;
goto error_rcur;
}
}
if (XFS_IS_CORRUPT(lcur->bc_mp, i != 1 && j != 1)) {
+ xfs_btree_mark_sick(lcur);
error = -EFSCORRUPTED;
goto error_rcur;
}
@@ -1383,8 +1447,10 @@ xfs_dialloc_ag_finobt_newino(
error = xfs_inobt_get_rec(cur, rec, &i);
if (error)
return error;
- if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+ if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
return 0;
}
}
@@ -1395,14 +1461,18 @@ xfs_dialloc_ag_finobt_newino(
error = xfs_inobt_lookup(cur, 0, XFS_LOOKUP_GE, &i);
if (error)
return error;
- if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+ if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
error = xfs_inobt_get_rec(cur, rec, &i);
if (error)
return error;
- if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+ if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
return 0;
}
@@ -1424,14 +1494,18 @@ xfs_dialloc_ag_update_inobt(
error = xfs_inobt_lookup(cur, frec->ir_startino, XFS_LOOKUP_EQ, &i);
if (error)
return error;
- if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+ if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
error = xfs_inobt_get_rec(cur, &rec, &i);
if (error)
return error;
- if (XFS_IS_CORRUPT(cur->bc_mp, i != 1))
+ if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
ASSERT((XFS_AGINO_TO_OFFSET(cur->bc_mp, rec.ir_startino) %
XFS_INODES_PER_CHUNK) == 0);
@@ -1440,8 +1514,10 @@ xfs_dialloc_ag_update_inobt(
if (XFS_IS_CORRUPT(cur->bc_mp,
rec.ir_free != frec->ir_free ||
- rec.ir_freecount != frec->ir_freecount))
+ rec.ir_freecount != frec->ir_freecount)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
return xfs_inobt_update(cur, &rec);
}
@@ -1483,7 +1559,7 @@ xfs_dialloc_ag(
if (!pagino)
pagino = be32_to_cpu(agi->agi_newino);
- cur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_FINO);
+ cur = xfs_finobt_init_cursor(pag, tp, agbp);
error = xfs_check_agi_freecount(cur);
if (error)
@@ -1526,7 +1602,7 @@ xfs_dialloc_ag(
* the original freecount. If all is well, make the equivalent update to
* the inobt using the finobt record and offset information.
*/
- icur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_INO);
+ icur = xfs_inobt_init_cursor(pag, tp, agbp);
error = xfs_check_agi_freecount(icur);
if (error)
@@ -1943,7 +2019,7 @@ xfs_difree_inobt(
/*
* Initialize the cursor.
*/
- cur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_INO);
+ cur = xfs_inobt_init_cursor(pag, tp, agbp);
error = xfs_check_agi_freecount(cur);
if (error)
@@ -1958,6 +2034,7 @@ xfs_difree_inobt(
goto error0;
}
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -1968,6 +2045,7 @@ xfs_difree_inobt(
goto error0;
}
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error0;
}
@@ -2068,7 +2146,7 @@ xfs_difree_finobt(
int error;
int i;
- cur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_FINO);
+ cur = xfs_finobt_init_cursor(pag, tp, agbp);
error = xfs_inobt_lookup(cur, ibtrec->ir_startino, XFS_LOOKUP_EQ, &i);
if (error)
@@ -2080,6 +2158,7 @@ xfs_difree_finobt(
* something is out of sync.
*/
if (XFS_IS_CORRUPT(mp, ibtrec->ir_freecount != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error;
}
@@ -2106,6 +2185,7 @@ xfs_difree_finobt(
if (error)
goto error;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error;
}
@@ -2116,6 +2196,7 @@ xfs_difree_finobt(
if (XFS_IS_CORRUPT(mp,
rec.ir_free != ibtrec->ir_free ||
rec.ir_freecount != ibtrec->ir_freecount)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto error;
}
@@ -2265,7 +2346,7 @@ xfs_imap_lookup(
* we have a record, we need to ensure it contains the inode number
* we are looking up.
*/
- cur = xfs_inobt_init_cursor(pag, tp, agbp, XFS_BTNUM_INO);
+ cur = xfs_inobt_init_cursor(pag, tp, agbp);
error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &i);
if (!error) {
if (i)
@@ -2604,6 +2685,8 @@ xfs_read_agi(
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGI_DADDR(mp)),
XFS_FSS_TO_BB(mp, 1), 0, agibpp, &xfs_agi_buf_ops);
+ if (xfs_metadata_is_sick(error))
+ xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
if (error)
return error;
if (tp)
@@ -2765,7 +2848,7 @@ xfs_ialloc_count_inodes(
struct xfs_ialloc_count_inodes ci = {0};
int error;
- ASSERT(cur->bc_btnum == XFS_BTNUM_INO);
+ ASSERT(xfs_btree_is_ino(cur->bc_ops));
error = xfs_btree_query_all(cur, xfs_ialloc_count_inodes_rec, &ci);
if (error)
return error;
@@ -2982,7 +3065,7 @@ xfs_ialloc_check_shrink(
if (!xfs_has_sparseinodes(pag->pag_mount))
return 0;
- cur = xfs_inobt_init_cursor(pag, tp, agibp, XFS_BTNUM_INO);
+ cur = xfs_inobt_init_cursor(pag, tp, agibp);
/* Look up the inobt record that would correspond to the new EOFS. */
agino = XFS_AGB_TO_AGINO(pag->pag_mount, new_length);
@@ -2995,6 +3078,7 @@ xfs_ialloc_check_shrink(
goto out;
if (!has) {
+ xfs_ag_mark_sick(pag, XFS_SICK_AG_INOBT);
error = -EFSCORRUPTED;
goto out;
}
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 42a5e1f227..cc661fca6f 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -17,6 +17,7 @@
#include "xfs_ialloc_btree.h"
#include "xfs_alloc.h"
#include "xfs_error.h"
+#include "xfs_health.h"
#include "xfs_trace.h"
#include "xfs_trans.h"
#include "xfs_rmap.h"
@@ -37,7 +38,15 @@ xfs_inobt_dup_cursor(
struct xfs_btree_cur *cur)
{
return xfs_inobt_init_cursor(cur->bc_ag.pag, cur->bc_tp,
- cur->bc_ag.agbp, cur->bc_btnum);
+ cur->bc_ag.agbp);
+}
+
+STATIC struct xfs_btree_cur *
+xfs_finobt_dup_cursor(
+ struct xfs_btree_cur *cur)
+{
+ return xfs_finobt_init_cursor(cur->bc_ag.pag, cur->bc_tp,
+ cur->bc_ag.agbp);
}
STATIC void
@@ -81,9 +90,9 @@ xfs_inobt_mod_blockcount(
if (!xfs_has_inobtcounts(cur->bc_mp))
return;
- if (cur->bc_btnum == XFS_BTNUM_FINO)
+ if (xfs_btree_is_fino(cur->bc_ops))
be32_add_cpu(&agi->agi_fblocks, howmuch);
- else if (cur->bc_btnum == XFS_BTNUM_INO)
+ else
be32_add_cpu(&agi->agi_iblocks, howmuch);
xfs_ialloc_log_agi(cur->bc_tp, agbp, XFS_AGI_IBLOCKS);
}
@@ -300,7 +309,7 @@ xfs_inobt_verify(
* xfs_perag_initialised_agi(pag)) if we ever do.
*/
if (xfs_has_crc(mp)) {
- fa = xfs_btree_sblock_v5hdr_verify(bp);
+ fa = xfs_btree_agblock_v5hdr_verify(bp);
if (fa)
return fa;
}
@@ -310,7 +319,7 @@ xfs_inobt_verify(
if (level >= M_IGEO(mp)->inobt_maxlevels)
return __this_address;
- return xfs_btree_sblock_verify(bp,
+ return xfs_btree_agblock_verify(bp,
M_IGEO(mp)->inobt_mxr[level != 0]);
}
@@ -320,7 +329,7 @@ xfs_inobt_read_verify(
{
xfs_failaddr_t fa;
- if (!xfs_btree_sblock_verify_crc(bp))
+ if (!xfs_btree_agblock_verify_crc(bp))
xfs_verifier_error(bp, -EFSBADCRC, __this_address);
else {
fa = xfs_inobt_verify(bp);
@@ -344,7 +353,7 @@ xfs_inobt_write_verify(
xfs_verifier_error(bp, -EFSCORRUPTED, fa);
return;
}
- xfs_btree_sblock_calc_crc(bp);
+ xfs_btree_agblock_calc_crc(bp);
}
@@ -398,9 +407,17 @@ xfs_inobt_keys_contiguous(
be32_to_cpu(key2->inobt.ir_startino));
}
-static const struct xfs_btree_ops xfs_inobt_ops = {
+const struct xfs_btree_ops xfs_inobt_ops = {
+ .name = "ino",
+ .type = XFS_BTREE_TYPE_AG,
+
.rec_len = sizeof(xfs_inobt_rec_t),
.key_len = sizeof(xfs_inobt_key_t),
+ .ptr_len = XFS_BTREE_SHORT_PTR_LEN,
+
+ .lru_refs = XFS_INO_BTREE_REF,
+ .statoff = XFS_STATS_CALC_INDEX(xs_ibt_2),
+ .sick_mask = XFS_SICK_AG_INOBT,
.dup_cursor = xfs_inobt_dup_cursor,
.set_root = xfs_inobt_set_root,
@@ -420,11 +437,19 @@ static const struct xfs_btree_ops xfs_inobt_ops = {
.keys_contiguous = xfs_inobt_keys_contiguous,
};
-static const struct xfs_btree_ops xfs_finobt_ops = {
+const struct xfs_btree_ops xfs_finobt_ops = {
+ .name = "fino",
+ .type = XFS_BTREE_TYPE_AG,
+
.rec_len = sizeof(xfs_inobt_rec_t),
.key_len = sizeof(xfs_inobt_key_t),
+ .ptr_len = XFS_BTREE_SHORT_PTR_LEN,
- .dup_cursor = xfs_inobt_dup_cursor,
+ .lru_refs = XFS_INO_BTREE_REF,
+ .statoff = XFS_STATS_CALC_INDEX(xs_fibt_2),
+ .sick_mask = XFS_SICK_AG_FINOBT,
+
+ .dup_cursor = xfs_finobt_dup_cursor,
.set_root = xfs_finobt_set_root,
.alloc_block = xfs_finobt_alloc_block,
.free_block = xfs_finobt_free_block,
@@ -443,65 +468,54 @@ static const struct xfs_btree_ops xfs_finobt_ops = {
};
/*
- * Initialize a new inode btree cursor.
+ * Create an inode btree cursor.
+ *
+ * For staging cursors tp and agbp are NULL.
*/
-static struct xfs_btree_cur *
-xfs_inobt_init_common(
+struct xfs_btree_cur *
+xfs_inobt_init_cursor(
struct xfs_perag *pag,
- struct xfs_trans *tp, /* transaction pointer */
- xfs_btnum_t btnum) /* ialloc or free ino btree */
+ struct xfs_trans *tp,
+ struct xfs_buf *agbp)
{
struct xfs_mount *mp = pag->pag_mount;
struct xfs_btree_cur *cur;
- cur = xfs_btree_alloc_cursor(mp, tp, btnum,
+ cur = xfs_btree_alloc_cursor(mp, tp, &xfs_inobt_ops,
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;
- } else {
- cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_fibt_2);
- cur->bc_ops = &xfs_finobt_ops;
- }
-
- if (xfs_has_crc(mp))
- cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
-
cur->bc_ag.pag = xfs_perag_hold(pag);
+ cur->bc_ag.agbp = agbp;
+ if (agbp) {
+ struct xfs_agi *agi = agbp->b_addr;
+
+ cur->bc_nlevels = be32_to_cpu(agi->agi_level);
+ }
return cur;
}
-/* Create an inode btree cursor. */
+/*
+ * Create a free inode btree cursor.
+ *
+ * For staging cursors tp and agbp are NULL.
+ */
struct xfs_btree_cur *
-xfs_inobt_init_cursor(
+xfs_finobt_init_cursor(
struct xfs_perag *pag,
struct xfs_trans *tp,
- struct xfs_buf *agbp,
- xfs_btnum_t btnum)
+ struct xfs_buf *agbp)
{
+ struct xfs_mount *mp = pag->pag_mount;
struct xfs_btree_cur *cur;
- struct xfs_agi *agi = agbp->b_addr;
- cur = xfs_inobt_init_common(pag, tp, btnum);
- if (btnum == XFS_BTNUM_INO)
- cur->bc_nlevels = be32_to_cpu(agi->agi_level);
- else
- cur->bc_nlevels = be32_to_cpu(agi->agi_free_level);
+ cur = xfs_btree_alloc_cursor(mp, tp, &xfs_finobt_ops,
+ M_IGEO(mp)->inobt_maxlevels, xfs_inobt_cur_cache);
+ cur->bc_ag.pag = xfs_perag_hold(pag);
cur->bc_ag.agbp = agbp;
- return cur;
-}
+ if (agbp) {
+ struct xfs_agi *agi = agbp->b_addr;
-/* Create an inode btree cursor with a fake root for staging. */
-struct xfs_btree_cur *
-xfs_inobt_stage_cursor(
- struct xfs_perag *pag,
- struct xbtree_afakeroot *afake,
- xfs_btnum_t btnum)
-{
- struct xfs_btree_cur *cur;
-
- cur = xfs_inobt_init_common(pag, NULL, btnum);
- xfs_btree_stage_afakeroot(cur, afake);
+ cur->bc_nlevels = be32_to_cpu(agi->agi_free_level);
+ }
return cur;
}
@@ -521,7 +535,7 @@ xfs_inobt_commit_staged_btree(
ASSERT(cur->bc_flags & XFS_BTREE_STAGING);
- if (cur->bc_btnum == XFS_BTNUM_INO) {
+ if (xfs_btree_is_ino(cur->bc_ops)) {
fields = XFS_AGI_ROOT | XFS_AGI_LEVEL;
agi->agi_root = cpu_to_be32(afake->af_root);
agi->agi_level = cpu_to_be32(afake->af_levels);
@@ -530,7 +544,7 @@ xfs_inobt_commit_staged_btree(
fields |= XFS_AGI_IBLOCKS;
}
xfs_ialloc_log_agi(tp, agbp, fields);
- xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_inobt_ops);
+ xfs_btree_commit_afakeroot(cur, tp, agbp);
} else {
fields = XFS_AGI_FREE_ROOT | XFS_AGI_FREE_LEVEL;
agi->agi_free_root = cpu_to_be32(afake->af_root);
@@ -540,7 +554,7 @@ xfs_inobt_commit_staged_btree(
fields |= XFS_AGI_IBLOCKS;
}
xfs_ialloc_log_agi(tp, agbp, fields);
- xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_finobt_ops);
+ xfs_btree_commit_afakeroot(cur, tp, agbp);
}
}
@@ -721,45 +735,21 @@ xfs_inobt_max_size(
XFS_INODES_PER_CHUNK);
}
-/* Read AGI and create inobt cursor. */
-int
-xfs_inobt_cur(
- struct xfs_perag *pag,
- struct xfs_trans *tp,
- xfs_btnum_t which,
- struct xfs_btree_cur **curpp,
- struct xfs_buf **agi_bpp)
-{
- struct xfs_btree_cur *cur;
- int error;
-
- ASSERT(*agi_bpp == NULL);
- ASSERT(*curpp == NULL);
-
- error = xfs_ialloc_read_agi(pag, tp, agi_bpp);
- if (error)
- return error;
-
- cur = xfs_inobt_init_cursor(pag, tp, *agi_bpp, which);
- *curpp = cur;
- return 0;
-}
-
static int
-xfs_inobt_count_blocks(
+xfs_finobt_count_blocks(
struct xfs_perag *pag,
struct xfs_trans *tp,
- xfs_btnum_t btnum,
xfs_extlen_t *tree_blocks)
{
struct xfs_buf *agbp = NULL;
- struct xfs_btree_cur *cur = NULL;
+ struct xfs_btree_cur *cur;
int error;
- error = xfs_inobt_cur(pag, tp, btnum, &cur, &agbp);
+ error = xfs_ialloc_read_agi(pag, tp, &agbp);
if (error)
return error;
+ cur = xfs_inobt_init_cursor(pag, tp, agbp);
error = xfs_btree_count_blocks(cur, tree_blocks);
xfs_btree_del_cursor(cur, error);
xfs_trans_brelse(tp, agbp);
@@ -807,8 +797,7 @@ xfs_finobt_calc_reserves(
if (xfs_has_inobtcounts(pag->pag_mount))
error = xfs_finobt_read_blocks(pag, tp, &tree_len);
else
- error = xfs_inobt_count_blocks(pag, tp, XFS_BTNUM_FINO,
- &tree_len);
+ error = xfs_finobt_count_blocks(pag, tp, &tree_len);
if (error)
return error;
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.h b/fs/xfs/libxfs/xfs_ialloc_btree.h
index 3262c3fe5e..6472ec1ecb 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.h
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.h
@@ -46,10 +46,10 @@ struct xfs_perag;
(maxrecs) * sizeof(xfs_inobt_key_t) + \
((index) - 1) * sizeof(xfs_inobt_ptr_t)))
-extern struct xfs_btree_cur *xfs_inobt_init_cursor(struct xfs_perag *pag,
- struct xfs_trans *tp, struct xfs_buf *agbp, xfs_btnum_t btnum);
-struct xfs_btree_cur *xfs_inobt_stage_cursor(struct xfs_perag *pag,
- struct xbtree_afakeroot *afake, xfs_btnum_t btnum);
+struct xfs_btree_cur *xfs_inobt_init_cursor(struct xfs_perag *pag,
+ struct xfs_trans *tp, struct xfs_buf *agbp);
+struct xfs_btree_cur *xfs_finobt_init_cursor(struct xfs_perag *pag,
+ struct xfs_trans *tp, struct xfs_buf *agbp);
extern int xfs_inobt_maxrecs(struct xfs_mount *, int, int);
/* ir_holemask to inode allocation bitmap conversion */
@@ -66,9 +66,6 @@ int xfs_finobt_calc_reserves(struct xfs_perag *perag, struct xfs_trans *tp,
xfs_extlen_t *ask, xfs_extlen_t *used);
extern xfs_extlen_t xfs_iallocbt_calc_size(struct xfs_mount *mp,
unsigned long long len);
-int xfs_inobt_cur(struct xfs_perag *pag, struct xfs_trans *tp,
- xfs_btnum_t btnum, struct xfs_btree_cur **curpp,
- struct xfs_buf **agi_bpp);
void xfs_inobt_commit_staged_btree(struct xfs_btree_cur *cur,
struct xfs_trans *tp, struct xfs_buf *agbp);
diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c
index f4e6b200cd..8796f2b3e5 100644
--- a/fs/xfs/libxfs/xfs_iext_tree.c
+++ b/fs/xfs/libxfs/xfs_iext_tree.c
@@ -394,11 +394,18 @@ xfs_iext_leaf_key(
return leaf->recs[n].lo & XFS_IEXT_STARTOFF_MASK;
}
+static inline void *
+xfs_iext_alloc_node(
+ int size)
+{
+ return kzalloc(size, GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL);
+}
+
static void
xfs_iext_grow(
struct xfs_ifork *ifp)
{
- struct xfs_iext_node *node = kmem_zalloc(NODE_SIZE, KM_NOFS);
+ struct xfs_iext_node *node = xfs_iext_alloc_node(NODE_SIZE);
int i;
if (ifp->if_height == 1) {
@@ -454,7 +461,7 @@ xfs_iext_split_node(
int *nr_entries)
{
struct xfs_iext_node *node = *nodep;
- struct xfs_iext_node *new = kmem_zalloc(NODE_SIZE, KM_NOFS);
+ struct xfs_iext_node *new = xfs_iext_alloc_node(NODE_SIZE);
const int nr_move = KEYS_PER_NODE / 2;
int nr_keep = nr_move + (KEYS_PER_NODE & 1);
int i = 0;
@@ -542,7 +549,7 @@ xfs_iext_split_leaf(
int *nr_entries)
{
struct xfs_iext_leaf *leaf = cur->leaf;
- struct xfs_iext_leaf *new = kmem_zalloc(NODE_SIZE, KM_NOFS);
+ struct xfs_iext_leaf *new = xfs_iext_alloc_node(NODE_SIZE);
const int nr_move = RECS_PER_LEAF / 2;
int nr_keep = nr_move + (RECS_PER_LEAF & 1);
int i;
@@ -583,7 +590,7 @@ xfs_iext_alloc_root(
{
ASSERT(ifp->if_bytes == 0);
- ifp->if_data = kmem_zalloc(sizeof(struct xfs_iext_rec), KM_NOFS);
+ ifp->if_data = xfs_iext_alloc_node(sizeof(struct xfs_iext_rec));
ifp->if_height = 1;
/* now that we have a node step into it */
@@ -603,7 +610,8 @@ xfs_iext_realloc_root(
if (new_size / sizeof(struct xfs_iext_rec) == RECS_PER_LEAF)
new_size = NODE_SIZE;
- new = krealloc(ifp->if_data, new_size, GFP_NOFS | __GFP_NOFAIL);
+ new = krealloc(ifp->if_data, new_size,
+ GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL);
memset(new + ifp->if_bytes, 0, new_size - ifp->if_bytes);
ifp->if_data = new;
cur->leaf = new;
@@ -743,7 +751,7 @@ xfs_iext_remove_node(
again:
ASSERT(node->ptrs[pos]);
ASSERT(node->ptrs[pos] == victim);
- kmem_free(victim);
+ kfree(victim);
nr_entries = xfs_iext_node_nr_entries(node, pos) - 1;
offset = node->keys[0];
@@ -789,7 +797,7 @@ again:
ASSERT(node == ifp->if_data);
ifp->if_data = node->ptrs[0];
ifp->if_height--;
- kmem_free(node);
+ kfree(node);
}
}
@@ -863,7 +871,7 @@ xfs_iext_free_last_leaf(
struct xfs_ifork *ifp)
{
ifp->if_height--;
- kmem_free(ifp->if_data);
+ kfree(ifp->if_data);
ifp->if_data = NULL;
}
@@ -1044,7 +1052,7 @@ xfs_iext_destroy_node(
}
}
- kmem_free(node);
+ kfree(node);
}
void
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 137a65bda9..d0dcce462b 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -18,6 +18,7 @@
#include "xfs_trans.h"
#include "xfs_ialloc.h"
#include "xfs_dir2.h"
+#include "xfs_health.h"
#include <linux/iversion.h>
@@ -132,9 +133,14 @@ xfs_imap_to_bp(
struct xfs_imap *imap,
struct xfs_buf **bpp)
{
- return xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
- imap->im_len, XBF_UNMAPPED, bpp,
- &xfs_inode_buf_ops);
+ int error;
+
+ error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
+ imap->im_len, XBF_UNMAPPED, bpp, &xfs_inode_buf_ops);
+ if (xfs_metadata_is_sick(error))
+ xfs_agno_mark_sick(mp, xfs_daddr_to_agno(mp, imap->im_blkno),
+ XFS_SICK_AG_INODES);
+ return error;
}
static inline struct timespec64 xfs_inode_decode_bigtime(uint64_t ts)
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index f4569e18a8..7d660a9739 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -25,6 +25,8 @@
#include "xfs_attr_leaf.h"
#include "xfs_types.h"
#include "xfs_errortag.h"
+#include "xfs_health.h"
+#include "xfs_symlink_remote.h"
struct kmem_cache *xfs_ifork_cache;
@@ -50,7 +52,8 @@ xfs_init_local_fork(
mem_size++;
if (size) {
- char *new_data = kmem_alloc(mem_size, KM_NOFS);
+ char *new_data = kmalloc(mem_size,
+ GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL);
memcpy(new_data, data, size);
if (zero_terminate)
@@ -77,7 +80,7 @@ xfs_iformat_local(
/*
* If the size is unreasonable, then something
* is wrong and we just bail out rather than crash in
- * kmem_alloc() or memcpy() below.
+ * kmalloc() or memcpy() below.
*/
if (unlikely(size > XFS_DFORK_SIZE(dip, ip->i_mount, whichfork))) {
xfs_warn(ip->i_mount,
@@ -87,6 +90,7 @@ xfs_iformat_local(
xfs_inode_verifier_error(ip, -EFSCORRUPTED,
"xfs_iformat_local", dip, sizeof(*dip),
__this_address);
+ xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
return -EFSCORRUPTED;
}
@@ -116,7 +120,7 @@ xfs_iformat_extents(
/*
* If the number of extents is unreasonable, then something is wrong and
- * we just bail out rather than crash in kmem_alloc() or memcpy() below.
+ * we just bail out rather than crash in kmalloc() or memcpy() below.
*/
if (unlikely(size < 0 || size > XFS_DFORK_SIZE(dip, mp, whichfork))) {
xfs_warn(ip->i_mount, "corrupt inode %llu ((a)extents = %llu).",
@@ -124,6 +128,7 @@ xfs_iformat_extents(
xfs_inode_verifier_error(ip, -EFSCORRUPTED,
"xfs_iformat_extents(1)", dip, sizeof(*dip),
__this_address);
+ xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
return -EFSCORRUPTED;
}
@@ -143,6 +148,7 @@ xfs_iformat_extents(
xfs_inode_verifier_error(ip, -EFSCORRUPTED,
"xfs_iformat_extents(2)",
dp, sizeof(*dp), fa);
+ xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
return xfs_bmap_complain_bad_rec(ip, whichfork,
fa, &new);
}
@@ -201,11 +207,13 @@ xfs_iformat_btree(
xfs_inode_verifier_error(ip, -EFSCORRUPTED,
"xfs_iformat_btree", dfp, size,
__this_address);
+ xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
return -EFSCORRUPTED;
}
ifp->if_broot_bytes = size;
- ifp->if_broot = kmem_alloc(size, KM_NOFS);
+ ifp->if_broot = kmalloc(size,
+ GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL);
ASSERT(ifp->if_broot != NULL);
/*
* Copy and convert from the on-disk structure
@@ -265,12 +273,14 @@ xfs_iformat_data_fork(
default:
xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__,
dip, sizeof(*dip), __this_address);
+ xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
return -EFSCORRUPTED;
}
break;
default:
xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip,
sizeof(*dip), __this_address);
+ xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
return -EFSCORRUPTED;
}
}
@@ -342,6 +352,7 @@ xfs_iformat_attr_fork(
default:
xfs_inode_verifier_error(ip, error, __func__, dip,
sizeof(*dip), __this_address);
+ xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
error = -EFSCORRUPTED;
break;
}
@@ -399,7 +410,8 @@ xfs_iroot_realloc(
*/
if (ifp->if_broot_bytes == 0) {
new_size = XFS_BMAP_BROOT_SPACE_CALC(mp, rec_diff);
- ifp->if_broot = kmem_alloc(new_size, KM_NOFS);
+ ifp->if_broot = kmalloc(new_size,
+ GFP_KERNEL | __GFP_NOFAIL);
ifp->if_broot_bytes = (int)new_size;
return;
}
@@ -414,7 +426,7 @@ xfs_iroot_realloc(
new_max = cur_max + rec_diff;
new_size = XFS_BMAP_BROOT_SPACE_CALC(mp, new_max);
ifp->if_broot = krealloc(ifp->if_broot, new_size,
- GFP_NOFS | __GFP_NOFAIL);
+ GFP_KERNEL | __GFP_NOFAIL);
op = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1,
ifp->if_broot_bytes);
np = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1,
@@ -440,7 +452,7 @@ xfs_iroot_realloc(
else
new_size = 0;
if (new_size > 0) {
- new_broot = kmem_alloc(new_size, KM_NOFS);
+ new_broot = kmalloc(new_size, GFP_KERNEL | __GFP_NOFAIL);
/*
* First copy over the btree block header.
*/
@@ -470,7 +482,7 @@ xfs_iroot_realloc(
(int)new_size);
memcpy(np, op, new_max * (uint)sizeof(xfs_fsblock_t));
}
- kmem_free(ifp->if_broot);
+ kfree(ifp->if_broot);
ifp->if_broot = new_broot;
ifp->if_broot_bytes = (int)new_size;
if (ifp->if_broot)
@@ -488,7 +500,7 @@ xfs_iroot_realloc(
*
* If the amount of space needed has decreased below the size of the
* inline buffer, then switch to using the inline buffer. Otherwise,
- * use kmem_realloc() or kmem_alloc() to adjust the size of the buffer
+ * use krealloc() or kmalloc() to adjust the size of the buffer
* to what is needed.
*
* ip -- the inode whose if_data area is changing
@@ -509,7 +521,7 @@ xfs_idata_realloc(
if (byte_diff) {
ifp->if_data = krealloc(ifp->if_data, new_size,
- GFP_NOFS | __GFP_NOFAIL);
+ GFP_KERNEL | __GFP_NOFAIL);
if (new_size == 0)
ifp->if_data = NULL;
ifp->if_bytes = new_size;
@@ -524,13 +536,13 @@ xfs_idestroy_fork(
struct xfs_ifork *ifp)
{
if (ifp->if_broot != NULL) {
- kmem_free(ifp->if_broot);
+ kfree(ifp->if_broot);
ifp->if_broot = NULL;
}
switch (ifp->if_format) {
case XFS_DINODE_FMT_LOCAL:
- kmem_free(ifp->if_data);
+ kfree(ifp->if_data);
ifp->if_data = NULL;
break;
case XFS_DINODE_FMT_EXTENTS:
@@ -562,7 +574,7 @@ xfs_iextents_copy(
struct xfs_bmbt_irec rec;
int64_t copied = 0;
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED));
+ xfs_assert_ilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED);
ASSERT(ifp->if_bytes > 0);
for_each_xfs_iext(ifp, &icur, &rec) {
@@ -689,7 +701,7 @@ xfs_ifork_init_cow(
return;
ip->i_cowfp = kmem_cache_zalloc(xfs_ifork_cache,
- GFP_NOFS | __GFP_NOFAIL);
+ GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL);
ip->i_cowfp->if_format = XFS_DINODE_FMT_EXTENTS;
}
@@ -802,3 +814,12 @@ xfs_iext_count_upgrade(
return 0;
}
+
+/* Decide if a file mapping is on the realtime device or not. */
+bool
+xfs_ifork_is_realtime(
+ struct xfs_inode *ip,
+ int whichfork)
+{
+ return XFS_IS_REALTIME_INODE(ip) && whichfork != XFS_ATTR_FORK;
+}
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 96303249d2..bd53eb951b 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -260,6 +260,7 @@ int xfs_iext_count_may_overflow(struct xfs_inode *ip, int whichfork,
int nr_to_add);
int xfs_iext_count_upgrade(struct xfs_trans *tp, struct xfs_inode *ip,
uint nr_to_add);
+bool xfs_ifork_is_realtime(struct xfs_inode *ip, int whichfork);
/* returns true if the fork has extents but they are not read in yet. */
static inline bool xfs_need_iread_extents(const struct xfs_ifork *ifp)
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 269573c828..16872972e1 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -838,10 +838,12 @@ struct xfs_cud_log_format {
#define XFS_BMAP_EXTENT_ATTR_FORK (1U << 31)
#define XFS_BMAP_EXTENT_UNWRITTEN (1U << 30)
+#define XFS_BMAP_EXTENT_REALTIME (1U << 29)
#define XFS_BMAP_EXTENT_FLAGS (XFS_BMAP_EXTENT_TYPE_MASK | \
XFS_BMAP_EXTENT_ATTR_FORK | \
- XFS_BMAP_EXTENT_UNWRITTEN)
+ XFS_BMAP_EXTENT_UNWRITTEN | \
+ XFS_BMAP_EXTENT_REALTIME)
/*
* This is the structure used to lay out an bui log item in the
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 6709a7f8ba..511c912d51 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -23,6 +23,7 @@
#include "xfs_refcount.h"
#include "xfs_rmap.h"
#include "xfs_ag.h"
+#include "xfs_health.h"
struct kmem_cache *xfs_refcount_intent_cache;
@@ -156,6 +157,7 @@ xfs_refcount_complain_bad_rec(
xfs_warn(mp,
"Start block 0x%x, block count 0x%x, references 0x%x",
irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount);
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
}
@@ -238,6 +240,7 @@ xfs_refcount_insert(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, *i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -268,12 +271,14 @@ xfs_refcount_delete(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
trace_xfs_refcount_delete(cur->bc_mp, cur->bc_ag.pag->pag_agno, &irec);
error = xfs_btree_delete(cur, i);
if (XFS_IS_CORRUPT(cur->bc_mp, *i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -398,6 +403,7 @@ xfs_refcount_split_extent(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -425,6 +431,7 @@ xfs_refcount_split_extent(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -470,6 +477,7 @@ xfs_refcount_merge_center_extents(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -478,6 +486,7 @@ xfs_refcount_merge_center_extents(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -487,6 +496,7 @@ xfs_refcount_merge_center_extents(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -498,6 +508,7 @@ xfs_refcount_merge_center_extents(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -542,6 +553,7 @@ xfs_refcount_merge_left_extent(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -550,6 +562,7 @@ xfs_refcount_merge_left_extent(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -561,6 +574,7 @@ xfs_refcount_merge_left_extent(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -608,6 +622,7 @@ xfs_refcount_merge_right_extent(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -616,6 +631,7 @@ xfs_refcount_merge_right_extent(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -627,6 +643,7 @@ xfs_refcount_merge_right_extent(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -674,6 +691,7 @@ xfs_refcount_find_left_extents(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -693,6 +711,7 @@ xfs_refcount_find_left_extents(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -767,6 +786,7 @@ xfs_refcount_find_right_extents(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -786,6 +806,7 @@ xfs_refcount_find_right_extents(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -1056,7 +1077,7 @@ xfs_refcount_still_have_space(
* to handle each of the shape changes to the refcount btree.
*/
overhead = xfs_allocfree_block_count(cur->bc_mp,
- cur->bc_ag.refc.shape_changes);
+ cur->bc_refc.shape_changes);
overhead += cur->bc_mp->m_refc_maxlevels;
overhead *= cur->bc_mp->m_sb.sb_blocksize;
@@ -1064,17 +1085,17 @@ xfs_refcount_still_have_space(
* Only allow 2 refcount extent updates per transaction if the
* refcount continue update "error" has been injected.
*/
- if (cur->bc_ag.refc.nr_ops > 2 &&
+ if (cur->bc_refc.nr_ops > 2 &&
XFS_TEST_ERROR(false, cur->bc_mp,
XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE))
return false;
- if (cur->bc_ag.refc.nr_ops == 0)
+ if (cur->bc_refc.nr_ops == 0)
return true;
else if (overhead > cur->bc_tp->t_log_res)
return false;
- return cur->bc_tp->t_log_res - overhead >
- cur->bc_ag.refc.nr_ops * XFS_REFCOUNT_ITEM_OVERHEAD;
+ return cur->bc_tp->t_log_res - overhead >
+ cur->bc_refc.nr_ops * XFS_REFCOUNT_ITEM_OVERHEAD;
}
/*
@@ -1134,7 +1155,7 @@ xfs_refcount_adjust_extents(
* Either cover the hole (increment) or
* delete the range (decrement).
*/
- cur->bc_ag.refc.nr_ops++;
+ cur->bc_refc.nr_ops++;
if (tmp.rc_refcount) {
error = xfs_refcount_insert(cur, &tmp,
&found_tmp);
@@ -1142,6 +1163,7 @@ xfs_refcount_adjust_extents(
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp,
found_tmp != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -1180,6 +1202,7 @@ xfs_refcount_adjust_extents(
*/
if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount == 0) ||
XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount > *aglen)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -1193,7 +1216,7 @@ xfs_refcount_adjust_extents(
ext.rc_refcount += adj;
trace_xfs_refcount_modify_extent(cur->bc_mp,
cur->bc_ag.pag->pag_agno, &ext);
- cur->bc_ag.refc.nr_ops++;
+ cur->bc_refc.nr_ops++;
if (ext.rc_refcount > 1) {
error = xfs_refcount_update(cur, &ext);
if (error)
@@ -1203,6 +1226,7 @@ xfs_refcount_adjust_extents(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -1281,7 +1305,7 @@ xfs_refcount_adjust(
if (shape_changed)
shape_changes++;
if (shape_changes)
- cur->bc_ag.refc.shape_changes++;
+ cur->bc_refc.shape_changes++;
/* Now that we've taken care of the ends, adjust the middle extents */
error = xfs_refcount_adjust_extents(cur, agbno, aglen, adj);
@@ -1327,8 +1351,10 @@ xfs_refcount_continue_op(
struct xfs_perag *pag = cur->bc_ag.pag;
if (XFS_IS_CORRUPT(mp, !xfs_verify_agbext(pag, new_agbno,
- ri->ri_blockcount)))
+ ri->ri_blockcount))) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
ri->ri_startblock = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
@@ -1374,8 +1400,8 @@ xfs_refcount_finish_one(
*/
rcur = *pcur;
if (rcur != NULL && rcur->bc_ag.pag != ri->ri_pag) {
- nr_ops = rcur->bc_ag.refc.nr_ops;
- shape_changes = rcur->bc_ag.refc.shape_changes;
+ nr_ops = rcur->bc_refc.nr_ops;
+ shape_changes = rcur->bc_refc.shape_changes;
xfs_refcount_finish_one_cleanup(tp, rcur, 0);
rcur = NULL;
*pcur = NULL;
@@ -1387,8 +1413,8 @@ xfs_refcount_finish_one(
return error;
rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, ri->ri_pag);
- rcur->bc_ag.refc.nr_ops = nr_ops;
- rcur->bc_ag.refc.shape_changes = shape_changes;
+ rcur->bc_refc.nr_ops = nr_ops;
+ rcur->bc_refc.shape_changes = shape_changes;
}
*pcur = rcur;
@@ -1449,7 +1475,7 @@ __xfs_refcount_add(
blockcount);
ri = kmem_cache_alloc(xfs_refcount_intent_cache,
- GFP_NOFS | __GFP_NOFAIL);
+ GFP_KERNEL | __GFP_NOFAIL);
INIT_LIST_HEAD(&ri->ri_list);
ri->ri_type = type;
ri->ri_startblock = startblock;
@@ -1535,6 +1561,7 @@ xfs_refcount_find_shared(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -1552,6 +1579,7 @@ xfs_refcount_find_shared(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -1585,6 +1613,7 @@ xfs_refcount_find_shared(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -1682,6 +1711,7 @@ xfs_refcount_adjust_cow_extents(
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec &&
ext.rc_domain != XFS_REFC_DOMAIN_COW)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -1697,6 +1727,7 @@ xfs_refcount_adjust_cow_extents(
/* Adding a CoW reservation, there should be nothing here. */
if (XFS_IS_CORRUPT(cur->bc_mp,
agbno + aglen > ext.rc_startblock)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -1714,6 +1745,7 @@ xfs_refcount_adjust_cow_extents(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_tmp != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -1721,14 +1753,17 @@ xfs_refcount_adjust_cow_extents(
case XFS_REFCOUNT_ADJUST_COW_FREE:
/* Removing a CoW reservation, there should be one extent. */
if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_startblock != agbno)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount != aglen)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_refcount != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -1740,6 +1775,7 @@ xfs_refcount_adjust_cow_extents(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -1889,8 +1925,10 @@ xfs_refcount_recover_extent(
struct xfs_refcount_recovery *rr;
if (XFS_IS_CORRUPT(cur->bc_mp,
- be32_to_cpu(rec->refc.rc_refcount) != 1))
+ be32_to_cpu(rec->refc.rc_refcount) != 1)) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
rr = kmalloc(sizeof(struct xfs_refcount_recovery),
GFP_KERNEL | __GFP_NOFAIL);
@@ -1900,6 +1938,7 @@ xfs_refcount_recover_extent(
if (xfs_refcount_check_irec(cur->bc_ag.pag, &rr->rr_rrec) != NULL ||
XFS_IS_CORRUPT(cur->bc_mp,
rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) {
+ xfs_btree_mark_sick(cur);
kfree(rr);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 0d80bd9914..ca59f6c89f 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -16,6 +16,7 @@
#include "xfs_refcount.h"
#include "xfs_alloc.h"
#include "xfs_error.h"
+#include "xfs_health.h"
#include "xfs_trace.h"
#include "xfs_trans.h"
#include "xfs_bit.h"
@@ -77,8 +78,6 @@ xfs_refcountbt_alloc_block(
xfs_refc_block(args.mp)));
if (error)
goto out_error;
- trace_xfs_refcountbt_alloc_block(cur->bc_mp, cur->bc_ag.pag->pag_agno,
- args.agbno, 1);
if (args.fsbno == NULLFSBLOCK) {
*stat = 0;
return 0;
@@ -107,8 +106,6 @@ xfs_refcountbt_free_block(
struct xfs_agf *agf = agbp->b_addr;
xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
- trace_xfs_refcountbt_free_block(cur->bc_mp, cur->bc_ag.pag->pag_agno,
- XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno), 1);
be32_add_cpu(&agf->agf_refcount_blocks, -1);
xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS);
return xfs_free_extent_later(cur->bc_tp, fsbno, 1,
@@ -220,7 +217,7 @@ xfs_refcountbt_verify(
if (!xfs_has_reflink(mp))
return __this_address;
- fa = xfs_btree_sblock_v5hdr_verify(bp);
+ fa = xfs_btree_agblock_v5hdr_verify(bp);
if (fa)
return fa;
@@ -242,7 +239,7 @@ xfs_refcountbt_verify(
} else if (level >= mp->m_refc_maxlevels)
return __this_address;
- return xfs_btree_sblock_verify(bp, mp->m_refc_mxr[level != 0]);
+ return xfs_btree_agblock_verify(bp, mp->m_refc_mxr[level != 0]);
}
STATIC void
@@ -251,7 +248,7 @@ xfs_refcountbt_read_verify(
{
xfs_failaddr_t fa;
- if (!xfs_btree_sblock_verify_crc(bp))
+ if (!xfs_btree_agblock_verify_crc(bp))
xfs_verifier_error(bp, -EFSBADCRC, __this_address);
else {
fa = xfs_refcountbt_verify(bp);
@@ -275,7 +272,7 @@ xfs_refcountbt_write_verify(
xfs_verifier_error(bp, -EFSCORRUPTED, fa);
return;
}
- xfs_btree_sblock_calc_crc(bp);
+ xfs_btree_agblock_calc_crc(bp);
}
@@ -321,9 +318,17 @@ xfs_refcountbt_keys_contiguous(
be32_to_cpu(key2->refc.rc_startblock));
}
-static const struct xfs_btree_ops xfs_refcountbt_ops = {
+const struct xfs_btree_ops xfs_refcountbt_ops = {
+ .name = "refcount",
+ .type = XFS_BTREE_TYPE_AG,
+
.rec_len = sizeof(struct xfs_refcount_rec),
.key_len = sizeof(struct xfs_refcount_key),
+ .ptr_len = XFS_BTREE_SHORT_PTR_LEN,
+
+ .lru_refs = XFS_REFC_BTREE_REF,
+ .statoff = XFS_STATS_CALC_INDEX(xs_refcbt_2),
+ .sick_mask = XFS_SICK_AG_REFCNTBT,
.dup_cursor = xfs_refcountbt_dup_cursor,
.set_root = xfs_refcountbt_set_root,
@@ -344,59 +349,32 @@ static const struct xfs_btree_ops xfs_refcountbt_ops = {
};
/*
- * Initialize a new refcount btree cursor.
+ * Create a new refcount btree cursor.
+ *
+ * For staging cursors tp and agbp are NULL.
*/
-static struct xfs_btree_cur *
-xfs_refcountbt_init_common(
+struct xfs_btree_cur *
+xfs_refcountbt_init_cursor(
struct xfs_mount *mp,
struct xfs_trans *tp,
+ struct xfs_buf *agbp,
struct xfs_perag *pag)
{
struct xfs_btree_cur *cur;
ASSERT(pag->pag_agno < mp->m_sb.sb_agcount);
- cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_REFC,
+ cur = xfs_btree_alloc_cursor(mp, tp, &xfs_refcountbt_ops,
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;
-
cur->bc_ag.pag = xfs_perag_hold(pag);
- cur->bc_ag.refc.nr_ops = 0;
- cur->bc_ag.refc.shape_changes = 0;
- cur->bc_ops = &xfs_refcountbt_ops;
- return cur;
-}
-
-/* Create a btree cursor. */
-struct xfs_btree_cur *
-xfs_refcountbt_init_cursor(
- struct xfs_mount *mp,
- struct xfs_trans *tp,
- struct xfs_buf *agbp,
- struct xfs_perag *pag)
-{
- struct xfs_agf *agf = agbp->b_addr;
- struct xfs_btree_cur *cur;
-
- cur = xfs_refcountbt_init_common(mp, tp, pag);
- cur->bc_nlevels = be32_to_cpu(agf->agf_refcount_level);
+ cur->bc_refc.nr_ops = 0;
+ cur->bc_refc.shape_changes = 0;
cur->bc_ag.agbp = agbp;
- return cur;
-}
+ if (agbp) {
+ struct xfs_agf *agf = agbp->b_addr;
-/* Create a btree cursor with a fake root for staging. */
-struct xfs_btree_cur *
-xfs_refcountbt_stage_cursor(
- struct xfs_mount *mp,
- struct xbtree_afakeroot *afake,
- struct xfs_perag *pag)
-{
- struct xfs_btree_cur *cur;
-
- cur = xfs_refcountbt_init_common(mp, NULL, pag);
- xfs_btree_stage_afakeroot(cur, afake);
+ cur->bc_nlevels = be32_to_cpu(agf->agf_refcount_level);
+ }
return cur;
}
@@ -421,7 +399,7 @@ xfs_refcountbt_commit_staged_btree(
xfs_alloc_log_agf(tp, agbp, XFS_AGF_REFCOUNT_BLOCKS |
XFS_AGF_REFCOUNT_ROOT |
XFS_AGF_REFCOUNT_LEVEL);
- xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_refcountbt_ops);
+ xfs_btree_commit_afakeroot(cur, tp, agbp);
}
/* Calculate number of records in a refcount btree block. */
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.h b/fs/xfs/libxfs/xfs_refcount_btree.h
index d66b37259b..1e0ab25f6c 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.h
+++ b/fs/xfs/libxfs/xfs_refcount_btree.h
@@ -48,8 +48,6 @@ struct xbtree_afakeroot;
extern struct xfs_btree_cur *xfs_refcountbt_init_cursor(struct xfs_mount *mp,
struct xfs_trans *tp, struct xfs_buf *agbp,
struct xfs_perag *pag);
-struct xfs_btree_cur *xfs_refcountbt_stage_cursor(struct xfs_mount *mp,
- struct xbtree_afakeroot *afake, struct xfs_perag *pag);
extern int xfs_refcountbt_maxrecs(int blocklen, bool leaf);
extern void xfs_refcountbt_compute_maxlevels(struct xfs_mount *mp);
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 76bf7f48cb..ef16f6f9ce 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -23,6 +23,7 @@
#include "xfs_error.h"
#include "xfs_inode.h"
#include "xfs_ag.h"
+#include "xfs_health.h"
struct kmem_cache *xfs_rmap_intent_cache;
@@ -56,8 +57,10 @@ xfs_rmap_lookup_le(
error = xfs_rmap_get_rec(cur, irec, &get_stat);
if (error)
return error;
- if (!get_stat)
+ if (!get_stat) {
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
+ }
return 0;
}
@@ -132,6 +135,7 @@ xfs_rmap_insert(
if (error)
goto done;
if (XFS_IS_CORRUPT(rcur->bc_mp, i != 0)) {
+ xfs_btree_mark_sick(rcur);
error = -EFSCORRUPTED;
goto done;
}
@@ -145,6 +149,7 @@ xfs_rmap_insert(
if (error)
goto done;
if (XFS_IS_CORRUPT(rcur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(rcur);
error = -EFSCORRUPTED;
goto done;
}
@@ -174,6 +179,7 @@ xfs_rmap_delete(
if (error)
goto done;
if (XFS_IS_CORRUPT(rcur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(rcur);
error = -EFSCORRUPTED;
goto done;
}
@@ -182,6 +188,7 @@ xfs_rmap_delete(
if (error)
goto done;
if (XFS_IS_CORRUPT(rcur->bc_mp, i != 1)) {
+ xfs_btree_mark_sick(rcur);
error = -EFSCORRUPTED;
goto done;
}
@@ -208,10 +215,10 @@ xfs_rmap_btrec_to_irec(
/* Simple checks for rmap records. */
xfs_failaddr_t
xfs_rmap_check_irec(
- struct xfs_btree_cur *cur,
+ struct xfs_perag *pag,
const struct xfs_rmap_irec *irec)
{
- struct xfs_mount *mp = cur->bc_mp;
+ struct xfs_mount *mp = pag->pag_mount;
bool is_inode;
bool is_unwritten;
bool is_bmbt;
@@ -226,8 +233,8 @@ xfs_rmap_check_irec(
return __this_address;
} else {
/* check for valid extent range, including overflow */
- if (!xfs_verify_agbext(cur->bc_ag.pag, irec->rm_startblock,
- irec->rm_blockcount))
+ if (!xfs_verify_agbext(pag, irec->rm_startblock,
+ irec->rm_blockcount))
return __this_address;
}
@@ -262,6 +269,16 @@ xfs_rmap_check_irec(
return NULL;
}
+static inline xfs_failaddr_t
+xfs_rmap_check_btrec(
+ struct xfs_btree_cur *cur,
+ const struct xfs_rmap_irec *irec)
+{
+ if (xfs_btree_is_mem_rmap(cur->bc_ops))
+ return xfs_rmap_check_irec(cur->bc_mem.pag, irec);
+ return xfs_rmap_check_irec(cur->bc_ag.pag, irec);
+}
+
static inline int
xfs_rmap_complain_bad_rec(
struct xfs_btree_cur *cur,
@@ -270,13 +287,18 @@ xfs_rmap_complain_bad_rec(
{
struct xfs_mount *mp = cur->bc_mp;
- xfs_warn(mp,
- "Reverse Mapping BTree record corruption in AG %d detected at %pS!",
- cur->bc_ag.pag->pag_agno, fa);
+ if (xfs_btree_is_mem_rmap(cur->bc_ops))
+ xfs_warn(mp,
+ "In-Memory Reverse Mapping BTree record corruption detected at %pS!", fa);
+ else
+ xfs_warn(mp,
+ "Reverse Mapping BTree record corruption in AG %d detected at %pS!",
+ cur->bc_ag.pag->pag_agno, fa);
xfs_warn(mp,
"Owner 0x%llx, flags 0x%x, start block 0x%x block count 0x%x",
irec->rm_owner, irec->rm_flags, irec->rm_startblock,
irec->rm_blockcount);
+ xfs_btree_mark_sick(cur);
return -EFSCORRUPTED;
}
@@ -299,7 +321,7 @@ xfs_rmap_get_rec(
fa = xfs_rmap_btrec_to_irec(rec, irec);
if (!fa)
- fa = xfs_rmap_check_irec(cur, irec);
+ fa = xfs_rmap_check_btrec(cur, irec);
if (fa)
return xfs_rmap_complain_bad_rec(cur, fa, irec);
@@ -512,7 +534,7 @@ xfs_rmap_lookup_le_range(
*/
static int
xfs_rmap_free_check_owner(
- struct xfs_mount *mp,
+ struct xfs_btree_cur *cur,
uint64_t ltoff,
struct xfs_rmap_irec *rec,
xfs_filblks_t len,
@@ -520,6 +542,7 @@ xfs_rmap_free_check_owner(
uint64_t offset,
unsigned int flags)
{
+ struct xfs_mount *mp = cur->bc_mp;
int error = 0;
if (owner == XFS_RMAP_OWN_UNKNOWN)
@@ -529,12 +552,14 @@ xfs_rmap_free_check_owner(
if (XFS_IS_CORRUPT(mp,
(flags & XFS_RMAP_UNWRITTEN) !=
(rec->rm_flags & XFS_RMAP_UNWRITTEN))) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out;
}
/* Make sure the owner matches what we expect to find in the tree. */
if (XFS_IS_CORRUPT(mp, owner != rec->rm_owner)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out;
}
@@ -546,16 +571,19 @@ xfs_rmap_free_check_owner(
if (flags & XFS_RMAP_BMBT_BLOCK) {
if (XFS_IS_CORRUPT(mp,
!(rec->rm_flags & XFS_RMAP_BMBT_BLOCK))) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out;
}
} else {
if (XFS_IS_CORRUPT(mp, rec->rm_offset > offset)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out;
}
if (XFS_IS_CORRUPT(mp,
offset + len > ltoff + rec->rm_blockcount)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out;
}
@@ -618,6 +646,7 @@ xfs_rmap_unmap(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -639,6 +668,7 @@ xfs_rmap_unmap(
if (XFS_IS_CORRUPT(mp,
bno <
ltrec.rm_startblock + ltrec.rm_blockcount)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -665,6 +695,7 @@ xfs_rmap_unmap(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -677,12 +708,13 @@ xfs_rmap_unmap(
ltrec.rm_startblock > bno ||
ltrec.rm_startblock + ltrec.rm_blockcount <
bno + len)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
/* Check owner information. */
- error = xfs_rmap_free_check_owner(mp, ltoff, &ltrec, len, owner,
+ error = xfs_rmap_free_check_owner(cur, ltoff, &ltrec, len, owner,
offset, flags);
if (error)
goto out_error;
@@ -697,6 +729,7 @@ xfs_rmap_unmap(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -788,6 +821,86 @@ out_error:
return error;
}
+#ifdef CONFIG_XFS_LIVE_HOOKS
+/*
+ * Use a static key here to reduce the overhead of rmapbt live updates. If
+ * the compiler supports jump labels, the static branch will be replaced by a
+ * nop sled when there are no hook users. Online fsck is currently the only
+ * caller, so this is a reasonable tradeoff.
+ *
+ * Note: Patching the kernel code requires taking the cpu hotplug lock. Other
+ * parts of the kernel allocate memory with that lock held, which means that
+ * XFS callers cannot hold any locks that might be used by memory reclaim or
+ * writeback when calling the static_branch_{inc,dec} functions.
+ */
+DEFINE_STATIC_XFS_HOOK_SWITCH(xfs_rmap_hooks_switch);
+
+void
+xfs_rmap_hook_disable(void)
+{
+ xfs_hooks_switch_off(&xfs_rmap_hooks_switch);
+}
+
+void
+xfs_rmap_hook_enable(void)
+{
+ xfs_hooks_switch_on(&xfs_rmap_hooks_switch);
+}
+
+/* Call downstream hooks for a reverse mapping update. */
+static inline void
+xfs_rmap_update_hook(
+ struct xfs_trans *tp,
+ struct xfs_perag *pag,
+ enum xfs_rmap_intent_type op,
+ xfs_agblock_t startblock,
+ xfs_extlen_t blockcount,
+ bool unwritten,
+ const struct xfs_owner_info *oinfo)
+{
+ if (xfs_hooks_switched_on(&xfs_rmap_hooks_switch)) {
+ struct xfs_rmap_update_params p = {
+ .startblock = startblock,
+ .blockcount = blockcount,
+ .unwritten = unwritten,
+ .oinfo = *oinfo, /* struct copy */
+ };
+
+ if (pag)
+ xfs_hooks_call(&pag->pag_rmap_update_hooks, op, &p);
+ }
+}
+
+/* Call the specified function during a reverse mapping update. */
+int
+xfs_rmap_hook_add(
+ struct xfs_perag *pag,
+ struct xfs_rmap_hook *hook)
+{
+ return xfs_hooks_add(&pag->pag_rmap_update_hooks, &hook->rmap_hook);
+}
+
+/* Stop calling the specified function during a reverse mapping update. */
+void
+xfs_rmap_hook_del(
+ struct xfs_perag *pag,
+ struct xfs_rmap_hook *hook)
+{
+ xfs_hooks_del(&pag->pag_rmap_update_hooks, &hook->rmap_hook);
+}
+
+/* Configure rmap update hook functions. */
+void
+xfs_rmap_hook_setup(
+ struct xfs_rmap_hook *hook,
+ notifier_fn_t mod_fn)
+{
+ xfs_hook_setup(&hook->rmap_hook, mod_fn);
+}
+#else
+# define xfs_rmap_update_hook(t, p, o, s, b, u, oi) do { } while (0)
+#endif /* CONFIG_XFS_LIVE_HOOKS */
+
/*
* Remove a reference to an extent in the rmap btree.
*/
@@ -808,7 +921,7 @@ xfs_rmap_free(
return 0;
cur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag);
-
+ xfs_rmap_update_hook(tp, pag, XFS_RMAP_UNMAP, bno, len, false, oinfo);
error = xfs_rmap_unmap(cur, bno, len, false, oinfo);
xfs_btree_del_cursor(cur, error);
@@ -900,6 +1013,7 @@ xfs_rmap_map(
if (XFS_IS_CORRUPT(mp,
have_lt != 0 &&
ltrec.rm_startblock + ltrec.rm_blockcount > bno)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -917,10 +1031,12 @@ xfs_rmap_map(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(mp, have_gt != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
if (XFS_IS_CORRUPT(mp, bno + len > gtrec.rm_startblock)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -974,6 +1090,7 @@ xfs_rmap_map(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -1021,6 +1138,7 @@ xfs_rmap_map(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -1055,6 +1173,7 @@ xfs_rmap_alloc(
return 0;
cur = xfs_rmapbt_init_cursor(mp, tp, agbp, pag);
+ xfs_rmap_update_hook(tp, pag, XFS_RMAP_MAP, bno, len, false, oinfo);
error = xfs_rmap_map(cur, bno, len, false, oinfo);
xfs_btree_del_cursor(cur, error);
@@ -1116,6 +1235,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1153,12 +1273,14 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
if (XFS_IS_CORRUPT(mp,
LEFT.rm_startblock + LEFT.rm_blockcount >
bno)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1181,6 +1303,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1193,10 +1316,12 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
if (XFS_IS_CORRUPT(mp, bno + len > RIGHT.rm_startblock)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1227,6 +1352,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1246,6 +1372,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1257,6 +1384,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1264,6 +1392,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1275,6 +1404,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1282,6 +1412,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1305,6 +1436,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1312,6 +1444,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1331,6 +1464,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1342,6 +1476,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1349,6 +1484,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1419,6 +1555,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1461,6 +1598,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 0)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1476,6 +1614,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1509,6 +1648,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1522,6 +1662,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 0)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1534,6 +1675,7 @@ xfs_rmap_convert(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1606,6 +1748,7 @@ xfs_rmap_convert_shared(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1634,6 +1777,7 @@ xfs_rmap_convert_shared(
if (XFS_IS_CORRUPT(mp,
LEFT.rm_startblock + LEFT.rm_blockcount >
bno)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1652,10 +1796,12 @@ xfs_rmap_convert_shared(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
if (XFS_IS_CORRUPT(mp, bno + len > RIGHT.rm_startblock)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1706,6 +1852,7 @@ xfs_rmap_convert_shared(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1732,6 +1879,7 @@ xfs_rmap_convert_shared(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1758,6 +1906,7 @@ xfs_rmap_convert_shared(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1781,6 +1930,7 @@ xfs_rmap_convert_shared(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1816,6 +1966,7 @@ xfs_rmap_convert_shared(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1861,6 +2012,7 @@ xfs_rmap_convert_shared(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1896,6 +2048,7 @@ xfs_rmap_convert_shared(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -1934,6 +2087,7 @@ xfs_rmap_convert_shared(
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto done;
}
@@ -2023,6 +2177,7 @@ xfs_rmap_unmap_shared(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -2033,12 +2188,14 @@ xfs_rmap_unmap_shared(
ltrec.rm_startblock > bno ||
ltrec.rm_startblock + ltrec.rm_blockcount <
bno + len)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
/* Make sure the owner matches what we expect to find in the tree. */
if (XFS_IS_CORRUPT(mp, owner != ltrec.rm_owner)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -2047,16 +2204,19 @@ xfs_rmap_unmap_shared(
if (XFS_IS_CORRUPT(mp,
(flags & XFS_RMAP_UNWRITTEN) !=
(ltrec.rm_flags & XFS_RMAP_UNWRITTEN))) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
/* Check the offset. */
if (XFS_IS_CORRUPT(mp, ltrec.rm_offset > offset)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
if (XFS_IS_CORRUPT(mp, offset > ltoff + ltrec.rm_blockcount)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -2113,6 +2273,7 @@ xfs_rmap_unmap_shared(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -2142,6 +2303,7 @@ xfs_rmap_unmap_shared(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -2221,6 +2383,7 @@ xfs_rmap_map_shared(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(mp, have_gt != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -2273,6 +2436,7 @@ xfs_rmap_map_shared(
if (error)
goto out_error;
if (XFS_IS_CORRUPT(mp, i != 1)) {
+ xfs_btree_mark_sick(cur);
error = -EFSCORRUPTED;
goto out_error;
}
@@ -2335,15 +2499,12 @@ xfs_rmap_map_raw(
{
struct xfs_owner_info oinfo;
- oinfo.oi_owner = rmap->rm_owner;
- oinfo.oi_offset = rmap->rm_offset;
- oinfo.oi_flags = 0;
- if (rmap->rm_flags & XFS_RMAP_ATTR_FORK)
- oinfo.oi_flags |= XFS_OWNER_INFO_ATTR_FORK;
- if (rmap->rm_flags & XFS_RMAP_BMBT_BLOCK)
- oinfo.oi_flags |= XFS_OWNER_INFO_BMBT_BLOCK;
+ xfs_owner_info_pack(&oinfo, rmap->rm_owner, rmap->rm_offset,
+ rmap->rm_flags);
- if (rmap->rm_flags || XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner))
+ if ((rmap->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK |
+ XFS_RMAP_UNWRITTEN)) ||
+ XFS_RMAP_NON_INODE_OWNER(rmap->rm_owner))
return xfs_rmap_map(cur, rmap->rm_startblock,
rmap->rm_blockcount,
rmap->rm_flags & XFS_RMAP_UNWRITTEN,
@@ -2373,7 +2534,7 @@ xfs_rmap_query_range_helper(
fa = xfs_rmap_btrec_to_irec(rec, &irec);
if (!fa)
- fa = xfs_rmap_check_irec(cur, &irec);
+ fa = xfs_rmap_check_btrec(cur, &irec);
if (fa)
return xfs_rmap_complain_bad_rec(cur, fa, &irec);
@@ -2428,6 +2589,38 @@ xfs_rmap_finish_one_cleanup(
xfs_trans_brelse(tp, agbp);
}
+/* Commit an rmap operation into the ondisk tree. */
+int
+__xfs_rmap_finish_intent(
+ struct xfs_btree_cur *rcur,
+ enum xfs_rmap_intent_type op,
+ xfs_agblock_t bno,
+ xfs_extlen_t len,
+ const struct xfs_owner_info *oinfo,
+ bool unwritten)
+{
+ switch (op) {
+ case XFS_RMAP_ALLOC:
+ case XFS_RMAP_MAP:
+ return xfs_rmap_map(rcur, bno, len, unwritten, oinfo);
+ case XFS_RMAP_MAP_SHARED:
+ return xfs_rmap_map_shared(rcur, bno, len, unwritten, oinfo);
+ case XFS_RMAP_FREE:
+ case XFS_RMAP_UNMAP:
+ return xfs_rmap_unmap(rcur, bno, len, unwritten, oinfo);
+ case XFS_RMAP_UNMAP_SHARED:
+ return xfs_rmap_unmap_shared(rcur, bno, len, unwritten, oinfo);
+ case XFS_RMAP_CONVERT:
+ return xfs_rmap_convert(rcur, bno, len, !unwritten, oinfo);
+ case XFS_RMAP_CONVERT_SHARED:
+ return xfs_rmap_convert_shared(rcur, bno, len, !unwritten,
+ oinfo);
+ default:
+ ASSERT(0);
+ return -EFSCORRUPTED;
+ }
+}
+
/*
* Process one of the deferred rmap operations. We pass back the
* btree cursor to maintain our lock on the rmapbt between calls.
@@ -2476,10 +2669,14 @@ xfs_rmap_finish_one(
* allocate blocks.
*/
error = xfs_free_extent_fix_freelist(tp, ri->ri_pag, &agbp);
- if (error)
+ if (error) {
+ xfs_ag_mark_sick(ri->ri_pag, XFS_SICK_AG_AGFL);
return error;
- if (XFS_IS_CORRUPT(tp->t_mountp, !agbp))
+ }
+ if (XFS_IS_CORRUPT(tp->t_mountp, !agbp)) {
+ xfs_ag_mark_sick(ri->ri_pag, XFS_SICK_AG_AGFL);
return -EFSCORRUPTED;
+ }
rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, ri->ri_pag);
}
@@ -2490,39 +2687,14 @@ xfs_rmap_finish_one(
unwritten = ri->ri_bmap.br_state == XFS_EXT_UNWRITTEN;
bno = XFS_FSB_TO_AGBNO(rcur->bc_mp, ri->ri_bmap.br_startblock);
- switch (ri->ri_type) {
- case XFS_RMAP_ALLOC:
- case XFS_RMAP_MAP:
- error = xfs_rmap_map(rcur, bno, ri->ri_bmap.br_blockcount,
- unwritten, &oinfo);
- break;
- case XFS_RMAP_MAP_SHARED:
- error = xfs_rmap_map_shared(rcur, bno,
- ri->ri_bmap.br_blockcount, unwritten, &oinfo);
- break;
- case XFS_RMAP_FREE:
- case XFS_RMAP_UNMAP:
- error = xfs_rmap_unmap(rcur, bno, ri->ri_bmap.br_blockcount,
- unwritten, &oinfo);
- break;
- case XFS_RMAP_UNMAP_SHARED:
- error = xfs_rmap_unmap_shared(rcur, bno,
- ri->ri_bmap.br_blockcount, unwritten, &oinfo);
- break;
- case XFS_RMAP_CONVERT:
- error = xfs_rmap_convert(rcur, bno, ri->ri_bmap.br_blockcount,
- !unwritten, &oinfo);
- break;
- case XFS_RMAP_CONVERT_SHARED:
- error = xfs_rmap_convert_shared(rcur, bno,
- ri->ri_bmap.br_blockcount, !unwritten, &oinfo);
- break;
- default:
- ASSERT(0);
- error = -EFSCORRUPTED;
- }
+ error = __xfs_rmap_finish_intent(rcur, ri->ri_type, bno,
+ ri->ri_bmap.br_blockcount, &oinfo, unwritten);
+ if (error)
+ return error;
- return error;
+ xfs_rmap_update_hook(tp, ri->ri_pag, ri->ri_type, bno,
+ ri->ri_bmap.br_blockcount, unwritten, &oinfo);
+ return 0;
}
/*
@@ -2559,7 +2731,7 @@ __xfs_rmap_add(
bmap->br_blockcount,
bmap->br_state);
- ri = kmem_cache_alloc(xfs_rmap_intent_cache, GFP_NOFS | __GFP_NOFAIL);
+ ri = kmem_cache_alloc(xfs_rmap_intent_cache, GFP_KERNEL | __GFP_NOFAIL);
INIT_LIST_HEAD(&ri->ri_list);
ri->ri_type = type;
ri->ri_owner = owner;
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 3c98d9d50a..9d01fe6894 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -186,6 +186,10 @@ void xfs_rmap_finish_one_cleanup(struct xfs_trans *tp,
struct xfs_btree_cur *rcur, int error);
int xfs_rmap_finish_one(struct xfs_trans *tp, struct xfs_rmap_intent *ri,
struct xfs_btree_cur **pcur);
+int __xfs_rmap_finish_intent(struct xfs_btree_cur *rcur,
+ enum xfs_rmap_intent_type op, xfs_agblock_t bno,
+ xfs_extlen_t len, const struct xfs_owner_info *oinfo,
+ bool unwritten);
int xfs_rmap_lookup_le_range(struct xfs_btree_cur *cur, xfs_agblock_t bno,
uint64_t owner, uint64_t offset, unsigned int flags,
@@ -195,7 +199,7 @@ int xfs_rmap_compare(const struct xfs_rmap_irec *a,
union xfs_btree_rec;
xfs_failaddr_t xfs_rmap_btrec_to_irec(const union xfs_btree_rec *rec,
struct xfs_rmap_irec *irec);
-xfs_failaddr_t xfs_rmap_check_irec(struct xfs_btree_cur *cur,
+xfs_failaddr_t xfs_rmap_check_irec(struct xfs_perag *pag,
const struct xfs_rmap_irec *irec);
int xfs_rmap_has_records(struct xfs_btree_cur *cur, xfs_agblock_t bno,
@@ -235,4 +239,29 @@ extern struct kmem_cache *xfs_rmap_intent_cache;
int __init xfs_rmap_intent_init_cache(void);
void xfs_rmap_intent_destroy_cache(void);
+/*
+ * Parameters for tracking reverse mapping changes. The hook function arg
+ * parameter is enum xfs_rmap_intent_type, and the rest is below.
+ */
+struct xfs_rmap_update_params {
+ xfs_agblock_t startblock;
+ xfs_extlen_t blockcount;
+ struct xfs_owner_info oinfo;
+ bool unwritten;
+};
+
+#ifdef CONFIG_XFS_LIVE_HOOKS
+
+struct xfs_rmap_hook {
+ struct xfs_hook rmap_hook;
+};
+
+void xfs_rmap_hook_disable(void);
+void xfs_rmap_hook_enable(void);
+
+int xfs_rmap_hook_add(struct xfs_perag *pag, struct xfs_rmap_hook *hook);
+void xfs_rmap_hook_del(struct xfs_perag *pag, struct xfs_rmap_hook *hook);
+void xfs_rmap_hook_setup(struct xfs_rmap_hook *hook, notifier_fn_t mod_fn);
+#endif
+
#endif /* __XFS_RMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 6c81b20e97..9e759efa81 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -16,11 +16,14 @@
#include "xfs_btree_staging.h"
#include "xfs_rmap.h"
#include "xfs_rmap_btree.h"
+#include "xfs_health.h"
#include "xfs_trace.h"
#include "xfs_error.h"
#include "xfs_extent_busy.h"
#include "xfs_ag.h"
#include "xfs_ag_resv.h"
+#include "xfs_buf_mem.h"
+#include "xfs_btree_mem.h"
static struct kmem_cache *xfs_rmapbt_cur_cache;
@@ -65,13 +68,12 @@ xfs_rmapbt_set_root(
{
struct xfs_buf *agbp = cur->bc_ag.agbp;
struct xfs_agf *agf = agbp->b_addr;
- int btnum = cur->bc_btnum;
ASSERT(ptr->s != 0);
- agf->agf_roots[btnum] = ptr->s;
- be32_add_cpu(&agf->agf_levels[btnum], inc);
- cur->bc_ag.pag->pagf_levels[btnum] += inc;
+ agf->agf_rmap_root = ptr->s;
+ be32_add_cpu(&agf->agf_rmap_level, inc);
+ cur->bc_ag.pag->pagf_rmap_level += inc;
xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS);
}
@@ -94,8 +96,6 @@ xfs_rmapbt_alloc_block(
&bno, 1);
if (error)
return error;
-
- trace_xfs_rmapbt_alloc_block(cur->bc_mp, pag->pag_agno, bno, 1);
if (bno == NULLAGBLOCK) {
*stat = 0;
return 0;
@@ -125,8 +125,6 @@ xfs_rmapbt_free_block(
int error;
bno = xfs_daddr_to_agbno(cur->bc_mp, xfs_buf_daddr(bp));
- trace_xfs_rmapbt_free_block(cur->bc_mp, pag->pag_agno,
- bno, 1);
be32_add_cpu(&agf->agf_rmap_blocks, -1);
xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS);
error = xfs_alloc_put_freelist(pag, cur->bc_tp, agbp, NULL, bno, 1);
@@ -226,7 +224,7 @@ xfs_rmapbt_init_ptr_from_cur(
ASSERT(cur->bc_ag.pag->pag_agno == be32_to_cpu(agf->agf_seqno));
- ptr->s = agf->agf_roots[cur->bc_btnum];
+ ptr->s = agf->agf_rmap_root;
}
/*
@@ -340,18 +338,29 @@ xfs_rmapbt_verify(
if (!xfs_has_rmapbt(mp))
return __this_address;
- fa = xfs_btree_sblock_v5hdr_verify(bp);
+ fa = xfs_btree_agblock_v5hdr_verify(bp);
if (fa)
return fa;
level = be16_to_cpu(block->bb_level);
if (pag && xfs_perag_initialised_agf(pag)) {
- if (level >= pag->pagf_levels[XFS_BTNUM_RMAPi])
+ unsigned int maxlevel = pag->pagf_rmap_level;
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+ /*
+ * Online repair could be rewriting the free space btrees, so
+ * we'll validate against the larger of either tree while this
+ * is going on.
+ */
+ maxlevel = max_t(unsigned int, maxlevel,
+ pag->pagf_repair_rmap_level);
+#endif
+ if (level >= maxlevel)
return __this_address;
} else if (level >= mp->m_rmap_maxlevels)
return __this_address;
- return xfs_btree_sblock_verify(bp, mp->m_rmap_mxr[level != 0]);
+ return xfs_btree_agblock_verify(bp, mp->m_rmap_mxr[level != 0]);
}
static void
@@ -360,7 +369,7 @@ xfs_rmapbt_read_verify(
{
xfs_failaddr_t fa;
- if (!xfs_btree_sblock_verify_crc(bp))
+ if (!xfs_btree_agblock_verify_crc(bp))
xfs_verifier_error(bp, -EFSBADCRC, __this_address);
else {
fa = xfs_rmapbt_verify(bp);
@@ -384,7 +393,7 @@ xfs_rmapbt_write_verify(
xfs_verifier_error(bp, -EFSCORRUPTED, fa);
return;
}
- xfs_btree_sblock_calc_crc(bp);
+ xfs_btree_agblock_calc_crc(bp);
}
@@ -476,9 +485,19 @@ xfs_rmapbt_keys_contiguous(
be32_to_cpu(key2->rmap.rm_startblock));
}
-static const struct xfs_btree_ops xfs_rmapbt_ops = {
+const struct xfs_btree_ops xfs_rmapbt_ops = {
+ .name = "rmap",
+ .type = XFS_BTREE_TYPE_AG,
+ .geom_flags = XFS_BTGEO_OVERLAPPING,
+
.rec_len = sizeof(struct xfs_rmap_rec),
+ /* Overlapping btree; 2 keys per pointer. */
.key_len = 2 * sizeof(struct xfs_rmap_key),
+ .ptr_len = XFS_BTREE_SHORT_PTR_LEN,
+
+ .lru_refs = XFS_RMAP_BTREE_REF,
+ .statoff = XFS_STATS_CALC_INDEX(xs_rmap_2),
+ .sick_mask = XFS_SICK_AG_RMAPBT,
.dup_cursor = xfs_rmapbt_dup_cursor,
.set_root = xfs_rmapbt_set_root,
@@ -498,55 +517,176 @@ static const struct xfs_btree_ops xfs_rmapbt_ops = {
.keys_contiguous = xfs_rmapbt_keys_contiguous,
};
-static struct xfs_btree_cur *
-xfs_rmapbt_init_common(
+/*
+ * Create a new reverse mapping btree cursor.
+ *
+ * For staging cursors tp and agbp are NULL.
+ */
+struct xfs_btree_cur *
+xfs_rmapbt_init_cursor(
struct xfs_mount *mp,
struct xfs_trans *tp,
+ struct xfs_buf *agbp,
struct xfs_perag *pag)
{
struct xfs_btree_cur *cur;
- /* Overlapping btree; 2 keys per pointer. */
- cur = xfs_btree_alloc_cursor(mp, tp, XFS_BTNUM_RMAP,
+ cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rmapbt_ops,
mp->m_rmap_maxlevels, xfs_rmapbt_cur_cache);
- cur->bc_flags = XFS_BTREE_CRC_BLOCKS | XFS_BTREE_OVERLAPPING;
- cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_rmap_2);
- cur->bc_ops = &xfs_rmapbt_ops;
-
cur->bc_ag.pag = xfs_perag_hold(pag);
+ cur->bc_ag.agbp = agbp;
+ if (agbp) {
+ struct xfs_agf *agf = agbp->b_addr;
+
+ cur->bc_nlevels = be32_to_cpu(agf->agf_rmap_level);
+ }
return cur;
}
-/* Create a new reverse mapping btree cursor. */
+#ifdef CONFIG_XFS_BTREE_IN_MEM
+static inline unsigned int
+xfs_rmapbt_mem_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(__be64));
+}
+
+/*
+ * Validate an in-memory rmap btree block. Callers are allowed to generate an
+ * in-memory btree even if the ondisk feature is not enabled.
+ */
+static xfs_failaddr_t
+xfs_rmapbt_mem_verify(
+ struct xfs_buf *bp)
+{
+ struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
+ xfs_failaddr_t fa;
+ unsigned int level;
+ unsigned int maxrecs;
+
+ if (!xfs_verify_magic(bp, block->bb_magic))
+ return __this_address;
+
+ fa = xfs_btree_fsblock_v5hdr_verify(bp, XFS_RMAP_OWN_UNKNOWN);
+ if (fa)
+ return fa;
+
+ level = be16_to_cpu(block->bb_level);
+ if (level >= xfs_rmapbt_maxlevels_ondisk())
+ return __this_address;
+
+ maxrecs = xfs_rmapbt_mem_block_maxrecs(
+ XFBNO_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN, level == 0);
+ return xfs_btree_memblock_verify(bp, maxrecs);
+}
+
+static void
+xfs_rmapbt_mem_rw_verify(
+ struct xfs_buf *bp)
+{
+ xfs_failaddr_t fa = xfs_rmapbt_mem_verify(bp);
+
+ if (fa)
+ xfs_verifier_error(bp, -EFSCORRUPTED, fa);
+}
+
+/* skip crc checks on in-memory btrees to save time */
+static const struct xfs_buf_ops xfs_rmapbt_mem_buf_ops = {
+ .name = "xfs_rmapbt_mem",
+ .magic = { 0, cpu_to_be32(XFS_RMAP_CRC_MAGIC) },
+ .verify_read = xfs_rmapbt_mem_rw_verify,
+ .verify_write = xfs_rmapbt_mem_rw_verify,
+ .verify_struct = xfs_rmapbt_mem_verify,
+};
+
+const struct xfs_btree_ops xfs_rmapbt_mem_ops = {
+ .name = "mem_rmap",
+ .type = XFS_BTREE_TYPE_MEM,
+ .geom_flags = XFS_BTGEO_OVERLAPPING,
+
+ .rec_len = sizeof(struct xfs_rmap_rec),
+ /* Overlapping btree; 2 keys per pointer. */
+ .key_len = 2 * sizeof(struct xfs_rmap_key),
+ .ptr_len = XFS_BTREE_LONG_PTR_LEN,
+
+ .lru_refs = XFS_RMAP_BTREE_REF,
+ .statoff = XFS_STATS_CALC_INDEX(xs_rmap_mem_2),
+
+ .dup_cursor = xfbtree_dup_cursor,
+ .set_root = xfbtree_set_root,
+ .alloc_block = xfbtree_alloc_block,
+ .free_block = xfbtree_free_block,
+ .get_minrecs = xfbtree_get_minrecs,
+ .get_maxrecs = xfbtree_get_maxrecs,
+ .init_key_from_rec = xfs_rmapbt_init_key_from_rec,
+ .init_high_key_from_rec = xfs_rmapbt_init_high_key_from_rec,
+ .init_rec_from_cur = xfs_rmapbt_init_rec_from_cur,
+ .init_ptr_from_cur = xfbtree_init_ptr_from_cur,
+ .key_diff = xfs_rmapbt_key_diff,
+ .buf_ops = &xfs_rmapbt_mem_buf_ops,
+ .diff_two_keys = xfs_rmapbt_diff_two_keys,
+ .keys_inorder = xfs_rmapbt_keys_inorder,
+ .recs_inorder = xfs_rmapbt_recs_inorder,
+ .keys_contiguous = xfs_rmapbt_keys_contiguous,
+};
+
+/* Create a cursor for an in-memory btree. */
struct xfs_btree_cur *
-xfs_rmapbt_init_cursor(
- struct xfs_mount *mp,
+xfs_rmapbt_mem_cursor(
+ struct xfs_perag *pag,
struct xfs_trans *tp,
- struct xfs_buf *agbp,
- struct xfs_perag *pag)
+ struct xfbtree *xfbt)
{
- struct xfs_agf *agf = agbp->b_addr;
struct xfs_btree_cur *cur;
+ struct xfs_mount *mp = pag->pag_mount;
- cur = xfs_rmapbt_init_common(mp, tp, pag);
- cur->bc_nlevels = be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]);
- cur->bc_ag.agbp = agbp;
+ cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rmapbt_mem_ops,
+ xfs_rmapbt_maxlevels_ondisk(), xfs_rmapbt_cur_cache);
+ cur->bc_mem.xfbtree = xfbt;
+ cur->bc_nlevels = xfbt->nlevels;
+
+ cur->bc_mem.pag = xfs_perag_hold(pag);
return cur;
}
-/* Create a new reverse mapping btree cursor with a fake root for staging. */
-struct xfs_btree_cur *
-xfs_rmapbt_stage_cursor(
+/* Create an in-memory rmap btree. */
+int
+xfs_rmapbt_mem_init(
struct xfs_mount *mp,
- struct xbtree_afakeroot *afake,
- struct xfs_perag *pag)
+ struct xfbtree *xfbt,
+ struct xfs_buftarg *btp,
+ xfs_agnumber_t agno)
{
- struct xfs_btree_cur *cur;
+ xfbt->owner = agno;
+ return xfbtree_init(mp, xfbt, btp, &xfs_rmapbt_mem_ops);
+}
- cur = xfs_rmapbt_init_common(mp, NULL, pag);
- xfs_btree_stage_afakeroot(cur, afake);
- return cur;
+/* Compute the max possible height for reverse mapping btrees in memory. */
+static unsigned int
+xfs_rmapbt_mem_maxlevels(void)
+{
+ unsigned int minrecs[2];
+ unsigned int blocklen;
+
+ blocklen = XFBNO_BLOCKSIZE - XFS_BTREE_LBLOCK_CRC_LEN;
+
+ minrecs[0] = xfs_rmapbt_mem_block_maxrecs(blocklen, true) / 2;
+ minrecs[1] = xfs_rmapbt_mem_block_maxrecs(blocklen, false) / 2;
+
+ /*
+ * How tall can an in-memory rmap btree become if we filled the entire
+ * AG with rmap records?
+ */
+ return xfs_btree_compute_maxlevels(minrecs,
+ XFS_MAX_AG_BYTES / sizeof(struct xfs_rmap_rec));
}
+#else
+# define xfs_rmapbt_mem_maxlevels() (0)
+#endif /* CONFIG_XFS_BTREE_IN_MEM */
/*
* Install a new reverse mapping btree root. Caller is responsible for
@@ -563,12 +703,12 @@ xfs_rmapbt_commit_staged_btree(
ASSERT(cur->bc_flags & XFS_BTREE_STAGING);
- agf->agf_roots[cur->bc_btnum] = cpu_to_be32(afake->af_root);
- agf->agf_levels[cur->bc_btnum] = cpu_to_be32(afake->af_levels);
+ agf->agf_rmap_root = cpu_to_be32(afake->af_root);
+ agf->agf_rmap_level = cpu_to_be32(afake->af_levels);
agf->agf_rmap_blocks = cpu_to_be32(afake->af_blocks);
xfs_alloc_log_agf(tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS |
XFS_AGF_RMAP_BLOCKS);
- xfs_btree_commit_afakeroot(cur, tp, agbp, &xfs_rmapbt_ops);
+ xfs_btree_commit_afakeroot(cur, tp, agbp);
}
/* Calculate number of records in a reverse mapping btree block. */
@@ -618,7 +758,8 @@ xfs_rmapbt_maxlevels_ondisk(void)
* 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);
+ return max(xfs_btree_space_to_height(minrecs, XFS_MAX_CRC_AG_BLOCKS),
+ xfs_rmapbt_mem_maxlevels());
}
/* Compute the maximum height of an rmap btree. */
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.h b/fs/xfs/libxfs/xfs_rmap_btree.h
index 3244715dd1..eb90d89e80 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.h
+++ b/fs/xfs/libxfs/xfs_rmap_btree.h
@@ -10,6 +10,7 @@ struct xfs_buf;
struct xfs_btree_cur;
struct xfs_mount;
struct xbtree_afakeroot;
+struct xfbtree;
/* rmaps only exist on crc enabled filesystems */
#define XFS_RMAP_BLOCK_LEN XFS_BTREE_SBLOCK_CRC_LEN
@@ -44,8 +45,6 @@ struct xbtree_afakeroot;
struct xfs_btree_cur *xfs_rmapbt_init_cursor(struct xfs_mount *mp,
struct xfs_trans *tp, struct xfs_buf *bp,
struct xfs_perag *pag);
-struct xfs_btree_cur *xfs_rmapbt_stage_cursor(struct xfs_mount *mp,
- struct xbtree_afakeroot *afake, struct xfs_perag *pag);
void xfs_rmapbt_commit_staged_btree(struct xfs_btree_cur *cur,
struct xfs_trans *tp, struct xfs_buf *agbp);
int xfs_rmapbt_maxrecs(int blocklen, int leaf);
@@ -64,4 +63,9 @@ unsigned int xfs_rmapbt_maxlevels_ondisk(void);
int __init xfs_rmapbt_init_cur_cache(void);
void xfs_rmapbt_destroy_cur_cache(void);
+struct xfs_btree_cur *xfs_rmapbt_mem_cursor(struct xfs_perag *pag,
+ struct xfs_trans *tp, struct xfbtree *xfbtree);
+int xfs_rmapbt_mem_init(struct xfs_mount *mp, struct xfbtree *xfbtree,
+ struct xfs_buftarg *btp, xfs_agnumber_t agno);
+
#endif /* __XFS_RMAP_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index e31663cb7b..f246d6dbf4 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -17,6 +17,7 @@
#include "xfs_rtalloc.h"
#include "xfs_error.h"
#include "xfs_rtbitmap.h"
+#include "xfs_health.h"
/*
* Realtime allocator bitmap functions shared with userspace.
@@ -115,13 +116,19 @@ xfs_rtbuf_get(
if (error)
return error;
- if (XFS_IS_CORRUPT(mp, nmap == 0 || !xfs_bmap_is_written_extent(&map)))
+ if (XFS_IS_CORRUPT(mp, nmap == 0 || !xfs_bmap_is_written_extent(&map))) {
+ xfs_rt_mark_sick(mp, issum ? XFS_SICK_RT_SUMMARY :
+ XFS_SICK_RT_BITMAP);
return -EFSCORRUPTED;
+ }
ASSERT(map.br_startblock != NULLFSBLOCK);
error = xfs_trans_read_buf(mp, args->tp, mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, map.br_startblock),
mp->m_bsize, 0, &bp, &xfs_rtbuf_ops);
+ if (xfs_metadata_is_sick(error))
+ xfs_rt_mark_sick(mp, issum ? XFS_SICK_RT_SUMMARY :
+ XFS_SICK_RT_BITMAP);
if (error)
return error;
@@ -934,7 +941,7 @@ xfs_rtfree_extent(
struct timespec64 atime;
ASSERT(mp->m_rbmip->i_itemp != NULL);
- ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL));
+ xfs_assert_ilocked(mp->m_rbmip, XFS_ILOCK_EXCL);
error = xfs_rtcheck_alloc_range(&args, start, len);
if (error)
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 5bb6e2bd6d..73a4b895de 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -530,7 +530,8 @@ xfs_validate_sb_common(
}
if (!xfs_validate_stripe_geometry(mp, XFS_FSB_TO_B(mp, sbp->sb_unit),
- XFS_FSB_TO_B(mp, sbp->sb_width), 0, false))
+ XFS_FSB_TO_B(mp, sbp->sb_width), 0,
+ xfs_buf_daddr(bp) == XFS_SB_DADDR, false))
return -EFSCORRUPTED;
/*
@@ -1290,6 +1291,8 @@ xfs_sb_read_secondary(
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
XFS_AG_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_sb_buf_ops);
+ if (xfs_metadata_is_sick(error))
+ xfs_agno_mark_sick(mp, agno, XFS_SICK_AG_SB);
if (error)
return error;
xfs_buf_set_ref(bp, XFS_SSB_REF);
@@ -1321,8 +1324,10 @@ xfs_sb_get_secondary(
}
/*
- * sunit, swidth, sectorsize(optional with 0) should be all in bytes,
- * so users won't be confused by values in error messages.
+ * sunit, swidth, sectorsize(optional with 0) should be all in bytes, so users
+ * won't be confused by values in error messages. This function returns false
+ * if the stripe geometry is invalid and the caller is unable to repair the
+ * stripe configuration later in the mount process.
*/
bool
xfs_validate_stripe_geometry(
@@ -1330,20 +1335,21 @@ xfs_validate_stripe_geometry(
__s64 sunit,
__s64 swidth,
int sectorsize,
+ bool may_repair,
bool silent)
{
if (swidth > INT_MAX) {
if (!silent)
xfs_notice(mp,
"stripe width (%lld) is too large", swidth);
- return false;
+ goto check_override;
}
if (sunit > swidth) {
if (!silent)
xfs_notice(mp,
"stripe unit (%lld) is larger than the stripe width (%lld)", sunit, swidth);
- return false;
+ goto check_override;
}
if (sectorsize && (int)sunit % sectorsize) {
@@ -1351,21 +1357,21 @@ xfs_validate_stripe_geometry(
xfs_notice(mp,
"stripe unit (%lld) must be a multiple of the sector size (%d)",
sunit, sectorsize);
- return false;
+ goto check_override;
}
if (sunit && !swidth) {
if (!silent)
xfs_notice(mp,
"invalid stripe unit (%lld) and stripe width of 0", sunit);
- return false;
+ goto check_override;
}
if (!sunit && swidth) {
if (!silent)
xfs_notice(mp,
"invalid stripe width (%lld) and stripe unit of 0", swidth);
- return false;
+ goto check_override;
}
if (sunit && (int)swidth % (int)sunit) {
@@ -1373,9 +1379,27 @@ xfs_validate_stripe_geometry(
xfs_notice(mp,
"stripe width (%lld) must be a multiple of the stripe unit (%lld)",
swidth, sunit);
- return false;
+ goto check_override;
}
return true;
+
+check_override:
+ if (!may_repair)
+ return false;
+ /*
+ * During mount, mp->m_dalign will not be set unless the sunit mount
+ * option was set. If it was set, ignore the bad stripe alignment values
+ * and allow the validation and overwrite later in the mount process to
+ * attempt to overwrite the bad stripe alignment values with the values
+ * supplied by mount options.
+ */
+ if (!mp->m_dalign)
+ return false;
+ if (!silent)
+ xfs_notice(mp,
+"Will try to correct with specified mount options sunit (%d) and swidth (%d)",
+ BBTOB(mp->m_dalign), BBTOB(mp->m_swidth));
+ return true;
}
/*
diff --git a/fs/xfs/libxfs/xfs_sb.h b/fs/xfs/libxfs/xfs_sb.h
index 2e8e8d63d4..37b1ed1bc2 100644
--- a/fs/xfs/libxfs/xfs_sb.h
+++ b/fs/xfs/libxfs/xfs_sb.h
@@ -35,8 +35,9 @@ extern int xfs_sb_get_secondary(struct xfs_mount *mp,
struct xfs_trans *tp, xfs_agnumber_t agno,
struct xfs_buf **bpp);
-extern bool xfs_validate_stripe_geometry(struct xfs_mount *mp,
- __s64 sunit, __s64 swidth, int sectorsize, bool silent);
+bool xfs_validate_stripe_geometry(struct xfs_mount *mp,
+ __s64 sunit, __s64 swidth, int sectorsize, bool may_repair,
+ bool silent);
uint8_t xfs_compute_rextslog(xfs_rtbxlen_t rtextents);
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 4220d3584c..dfd61fa833 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -43,6 +43,60 @@ extern const struct xfs_buf_ops xfs_sb_buf_ops;
extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
extern const struct xfs_buf_ops xfs_symlink_buf_ops;
+/* btree ops */
+extern const struct xfs_btree_ops xfs_bnobt_ops;
+extern const struct xfs_btree_ops xfs_cntbt_ops;
+extern const struct xfs_btree_ops xfs_inobt_ops;
+extern const struct xfs_btree_ops xfs_finobt_ops;
+extern const struct xfs_btree_ops xfs_bmbt_ops;
+extern const struct xfs_btree_ops xfs_refcountbt_ops;
+extern const struct xfs_btree_ops xfs_rmapbt_ops;
+extern const struct xfs_btree_ops xfs_rmapbt_mem_ops;
+
+static inline bool xfs_btree_is_bno(const struct xfs_btree_ops *ops)
+{
+ return ops == &xfs_bnobt_ops;
+}
+
+static inline bool xfs_btree_is_cnt(const struct xfs_btree_ops *ops)
+{
+ return ops == &xfs_cntbt_ops;
+}
+
+static inline bool xfs_btree_is_bmap(const struct xfs_btree_ops *ops)
+{
+ return ops == &xfs_bmbt_ops;
+}
+
+static inline bool xfs_btree_is_ino(const struct xfs_btree_ops *ops)
+{
+ return ops == &xfs_inobt_ops;
+}
+
+static inline bool xfs_btree_is_fino(const struct xfs_btree_ops *ops)
+{
+ return ops == &xfs_finobt_ops;
+}
+
+static inline bool xfs_btree_is_refcount(const struct xfs_btree_ops *ops)
+{
+ return ops == &xfs_refcountbt_ops;
+}
+
+static inline bool xfs_btree_is_rmap(const struct xfs_btree_ops *ops)
+{
+ return ops == &xfs_rmapbt_ops;
+}
+
+#ifdef CONFIG_XFS_BTREE_IN_MEM
+static inline bool xfs_btree_is_mem_rmap(const struct xfs_btree_ops *ops)
+{
+ return ops == &xfs_rmapbt_mem_ops;
+}
+#else
+# define xfs_btree_is_mem_rmap(...) (false)
+#endif
+
/* log size calculation functions */
int xfs_log_calc_unit_res(struct xfs_mount *mp, int unit_bytes);
int xfs_log_calc_minimum_size(struct xfs_mount *);
@@ -128,19 +182,6 @@ void xfs_log_get_max_trans_res(struct xfs_mount *mp,
#define XFS_ICHGTIME_CHG 0x2 /* inode field change timestamp */
#define XFS_ICHGTIME_CREATE 0x4 /* inode create timestamp */
-
-/*
- * Symlink decoding/encoding functions
- */
-int xfs_symlink_blocks(struct xfs_mount *mp, int pathlen);
-int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
- uint32_t size, struct xfs_buf *bp);
-bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset,
- uint32_t size, struct xfs_buf *bp);
-void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
- struct xfs_inode *ip, struct xfs_ifork *ifp);
-xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size);
-
/* Computed inode geometry for the filesystem. */
struct xfs_ino_geometry {
/* Maximum inode count in this filesystem. */
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index 160aa20aa4..ffb1317a92 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -16,7 +16,10 @@
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_log.h"
-
+#include "xfs_symlink_remote.h"
+#include "xfs_bit.h"
+#include "xfs_bmap.h"
+#include "xfs_health.h"
/*
* Each contiguous block has a header, so it is not just a simple pathlen
@@ -227,3 +230,153 @@ xfs_symlink_shortform_verify(
return __this_address;
return NULL;
}
+
+/* Read a remote symlink target into the buffer. */
+int
+xfs_symlink_remote_read(
+ struct xfs_inode *ip,
+ char *link)
+{
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_bmbt_irec mval[XFS_SYMLINK_MAPS];
+ struct xfs_buf *bp;
+ xfs_daddr_t d;
+ char *cur_chunk;
+ int pathlen = ip->i_disk_size;
+ int nmaps = XFS_SYMLINK_MAPS;
+ int byte_cnt;
+ int n;
+ int error = 0;
+ int fsblocks = 0;
+ int offset;
+
+ xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL);
+
+ fsblocks = xfs_symlink_blocks(mp, pathlen);
+ error = xfs_bmapi_read(ip, 0, fsblocks, mval, &nmaps, 0);
+ if (error)
+ goto out;
+
+ offset = 0;
+ for (n = 0; n < nmaps; n++) {
+ d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
+ byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
+
+ error = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), 0,
+ &bp, &xfs_symlink_buf_ops);
+ if (xfs_metadata_is_sick(error))
+ xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK);
+ if (error)
+ return error;
+ byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt);
+ if (pathlen < byte_cnt)
+ byte_cnt = pathlen;
+
+ cur_chunk = bp->b_addr;
+ if (xfs_has_crc(mp)) {
+ if (!xfs_symlink_hdr_ok(ip->i_ino, offset,
+ byte_cnt, bp)) {
+ xfs_inode_mark_sick(ip, XFS_SICK_INO_SYMLINK);
+ error = -EFSCORRUPTED;
+ xfs_alert(mp,
+"symlink header does not match required off/len/owner (0x%x/0x%x,0x%llx)",
+ offset, byte_cnt, ip->i_ino);
+ xfs_buf_relse(bp);
+ goto out;
+
+ }
+
+ cur_chunk += sizeof(struct xfs_dsymlink_hdr);
+ }
+
+ memcpy(link + offset, cur_chunk, byte_cnt);
+
+ pathlen -= byte_cnt;
+ offset += byte_cnt;
+
+ xfs_buf_relse(bp);
+ }
+ ASSERT(pathlen == 0);
+
+ link[ip->i_disk_size] = '\0';
+ error = 0;
+
+ out:
+ return error;
+}
+
+/* Write the symlink target into the inode. */
+int
+xfs_symlink_write_target(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip,
+ const char *target_path,
+ int pathlen,
+ xfs_fsblock_t fs_blocks,
+ uint resblks)
+{
+ struct xfs_bmbt_irec mval[XFS_SYMLINK_MAPS];
+ struct xfs_mount *mp = tp->t_mountp;
+ const char *cur_chunk;
+ struct xfs_buf *bp;
+ xfs_daddr_t d;
+ int byte_cnt;
+ int nmaps;
+ int offset = 0;
+ int n;
+ int error;
+
+ /*
+ * If the symlink will fit into the inode, write it inline.
+ */
+ if (pathlen <= xfs_inode_data_fork_size(ip)) {
+ xfs_init_local_fork(ip, XFS_DATA_FORK, target_path, pathlen);
+
+ ip->i_disk_size = pathlen;
+ ip->i_df.if_format = XFS_DINODE_FMT_LOCAL;
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_DDATA | XFS_ILOG_CORE);
+ return 0;
+ }
+
+ nmaps = XFS_SYMLINK_MAPS;
+ error = xfs_bmapi_write(tp, ip, 0, fs_blocks, XFS_BMAPI_METADATA,
+ resblks, mval, &nmaps);
+ if (error)
+ return error;
+
+ ip->i_disk_size = pathlen;
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+ cur_chunk = target_path;
+ offset = 0;
+ for (n = 0; n < nmaps; n++) {
+ char *buf;
+
+ d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
+ byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
+ error = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
+ BTOBB(byte_cnt), 0, &bp);
+ if (error)
+ return error;
+ bp->b_ops = &xfs_symlink_buf_ops;
+
+ byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt);
+ byte_cnt = min(byte_cnt, pathlen);
+
+ buf = bp->b_addr;
+ buf += xfs_symlink_hdr_set(mp, ip->i_ino, offset, byte_cnt,
+ bp);
+
+ memcpy(buf, cur_chunk, byte_cnt);
+
+ cur_chunk += byte_cnt;
+ pathlen -= byte_cnt;
+ offset += byte_cnt;
+
+ xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SYMLINK_BUF);
+ xfs_trans_log_buf(tp, bp, 0, (buf + byte_cnt - 1) -
+ (char *)bp->b_addr);
+ }
+ ASSERT(pathlen == 0);
+ return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.h b/fs/xfs/libxfs/xfs_symlink_remote.h
new file mode 100644
index 0000000000..a63bd38ae4
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_symlink_remote.h
@@ -0,0 +1,26 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * Copyright (c) 2013 Red Hat, Inc.
+ * All Rights Reserved.
+ */
+#ifndef __XFS_SYMLINK_REMOTE_H
+#define __XFS_SYMLINK_REMOTE_H
+
+/*
+ * Symlink decoding/encoding functions
+ */
+int xfs_symlink_blocks(struct xfs_mount *mp, int pathlen);
+int xfs_symlink_hdr_set(struct xfs_mount *mp, xfs_ino_t ino, uint32_t offset,
+ uint32_t size, struct xfs_buf *bp);
+bool xfs_symlink_hdr_ok(xfs_ino_t ino, uint32_t offset,
+ uint32_t size, struct xfs_buf *bp);
+void xfs_symlink_local_to_remote(struct xfs_trans *tp, struct xfs_buf *bp,
+ struct xfs_inode *ip, struct xfs_ifork *ifp);
+xfs_failaddr_t xfs_symlink_shortform_verify(void *sfp, int64_t size);
+int xfs_symlink_remote_read(struct xfs_inode *ip, char *link);
+int xfs_symlink_write_target(struct xfs_trans *tp, struct xfs_inode *ip,
+ const char *target_path, int pathlen, xfs_fsblock_t fs_blocks,
+ uint resblks);
+
+#endif /* __XFS_SYMLINK_REMOTE_H */
diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c
index 70e97ea6ee..69fc5b9813 100644
--- a/fs/xfs/libxfs/xfs_trans_inode.c
+++ b/fs/xfs/libxfs/xfs_trans_inode.c
@@ -31,7 +31,7 @@ xfs_trans_ijoin(
{
struct xfs_inode_log_item *iip;
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+ xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
if (ip->i_itemp == NULL)
xfs_inode_item_init(ip, ip->i_mount);
iip = ip->i_itemp;
@@ -60,7 +60,7 @@ xfs_trans_ichgtime(
struct timespec64 tv;
ASSERT(tp);
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+ xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
tv = current_time(inode);
@@ -90,7 +90,7 @@ xfs_trans_log_inode(
struct inode *inode = VFS_I(ip);
ASSERT(iip);
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+ xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
ASSERT(!xfs_iflags_test(ip, XFS_ISTALE));
tp->t_flags |= XFS_TRANS_DIRTY;
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 62e02d5380..76eb9e3288 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -80,11 +80,13 @@ typedef void * xfs_failaddr_t;
/*
* Inode fork identifiers.
*/
-#define XFS_DATA_FORK 0
-#define XFS_ATTR_FORK 1
-#define XFS_COW_FORK 2
+#define XFS_STAGING_FORK (-1) /* fake fork for staging a btree */
+#define XFS_DATA_FORK (0)
+#define XFS_ATTR_FORK (1)
+#define XFS_COW_FORK (2)
#define XFS_WHICHFORK_STRINGS \
+ { XFS_STAGING_FORK, "staging" }, \
{ XFS_DATA_FORK, "data" }, \
{ XFS_ATTR_FORK, "attr" }, \
{ XFS_COW_FORK, "cow" }
@@ -114,24 +116,6 @@ typedef enum {
{ XFS_LOOKUP_LEi, "le" }, \
{ XFS_LOOKUP_GEi, "ge" }
-/*
- * This enum is used in string mapping in xfs_trace.h and scrub/trace.h;
- * please keep the TRACE_DEFINE_ENUMs for it up to date.
- */
-typedef enum {
- XFS_BTNUM_BNOi, XFS_BTNUM_CNTi, XFS_BTNUM_RMAPi, XFS_BTNUM_BMAPi,
- XFS_BTNUM_INOi, XFS_BTNUM_FINOi, XFS_BTNUM_REFCi, XFS_BTNUM_MAX
-} xfs_btnum_t;
-
-#define XFS_BTNUM_STRINGS \
- { XFS_BTNUM_BNOi, "bnobt" }, \
- { XFS_BTNUM_CNTi, "cntbt" }, \
- { XFS_BTNUM_RMAPi, "rmapbt" }, \
- { XFS_BTNUM_BMAPi, "bmbt" }, \
- { XFS_BTNUM_INOi, "inobt" }, \
- { XFS_BTNUM_FINOi, "finobt" }, \
- { XFS_BTNUM_REFCi, "refcbt" }
-
struct xfs_name {
const unsigned char *name;
int len;