aboutsummaryrefslogtreecommitdiffstats
path: root/fs/xfs/libxfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs/libxfs')
-rw-r--r--fs/xfs/libxfs/xfs_ag.c174
-rw-r--r--fs/xfs/libxfs/xfs_ag.h90
-rw-r--r--fs/xfs/libxfs/xfs_ag_resv.c2
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c187
-rw-r--r--fs/xfs/libxfs/xfs_alloc.h61
-rw-r--r--fs/xfs/libxfs/xfs_alloc_btree.c9
-rw-r--r--fs/xfs/libxfs/xfs_attr.c1681
-rw-r--r--fs/xfs/libxfs/xfs_attr.h190
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.c109
-rw-r--r--fs/xfs/libxfs/xfs_attr_leaf.h3
-rw-r--r--fs/xfs/libxfs/xfs_attr_remote.c52
-rw-r--r--fs/xfs/libxfs/xfs_attr_remote.h6
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c257
-rw-r--r--fs/xfs/libxfs/xfs_bmap.h58
-rw-r--r--fs/xfs/libxfs/xfs_bmap_btree.c19
-rw-r--r--fs/xfs/libxfs/xfs_btree.c190
-rw-r--r--fs/xfs/libxfs/xfs_btree.h26
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.c17
-rw-r--r--fs/xfs/libxfs/xfs_da_btree.h28
-rw-r--r--fs/xfs/libxfs/xfs_da_format.h9
-rw-r--r--fs/xfs/libxfs/xfs_defer.c97
-rw-r--r--fs/xfs/libxfs/xfs_defer.h3
-rw-r--r--fs/xfs/libxfs/xfs_dir2.c94
-rw-r--r--fs/xfs/libxfs/xfs_dir2.h12
-rw-r--r--fs/xfs/libxfs/xfs_dir2_block.c6
-rw-r--r--fs/xfs/libxfs/xfs_dir2_leaf.c9
-rw-r--r--fs/xfs/libxfs/xfs_dir2_priv.h5
-rw-r--r--fs/xfs/libxfs/xfs_dir2_sf.c12
-rw-r--r--fs/xfs/libxfs/xfs_errortag.h8
-rw-r--r--fs/xfs/libxfs/xfs_format.h213
-rw-r--r--fs/xfs/libxfs/xfs_fs.h78
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.c98
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.h27
-rw-r--r--fs/xfs/libxfs/xfs_ialloc_btree.c20
-rw-r--r--fs/xfs/libxfs/xfs_inode_buf.c129
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.c118
-rw-r--r--fs/xfs/libxfs/xfs_inode_fork.h103
-rw-r--r--fs/xfs/libxfs/xfs_log_format.h147
-rw-r--r--fs/xfs/libxfs/xfs_log_recover.h16
-rw-r--r--fs/xfs/libxfs/xfs_log_rlimit.c75
-rw-r--r--fs/xfs/libxfs/xfs_quota_defs.h50
-rw-r--r--fs/xfs/libxfs/xfs_refcount.c315
-rw-r--r--fs/xfs/libxfs/xfs_refcount.h53
-rw-r--r--fs/xfs/libxfs/xfs_refcount_btree.c20
-rw-r--r--fs/xfs/libxfs/xfs_rmap.c174
-rw-r--r--fs/xfs/libxfs/xfs_rmap.h7
-rw-r--r--fs/xfs/libxfs/xfs_rmap_btree.c9
-rw-r--r--fs/xfs/libxfs/xfs_rtbitmap.c9
-rw-r--r--fs/xfs/libxfs/xfs_sb.c80
-rw-r--r--fs/xfs/libxfs/xfs_shared.h24
-rw-r--r--fs/xfs/libxfs/xfs_symlink_remote.c4
-rw-r--r--fs/xfs/libxfs/xfs_trans_resv.c231
-rw-r--r--fs/xfs/libxfs/xfs_trans_resv.h16
-rw-r--r--fs/xfs/libxfs/xfs_types.c73
-rw-r--r--fs/xfs/libxfs/xfs_types.h50
55 files changed, 3281 insertions, 2272 deletions
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 1e4ee042d52f..bb0c700afe3c 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -120,18 +120,18 @@ xfs_initialize_perag_data(
for (index = 0; index < agcount; index++) {
/*
- * read the agf, then the agi. This gets us
- * all the information we need and populates the
- * per-ag structures for us.
+ * Read the AGF and AGI buffers to populate the per-ag
+ * structures for us.
*/
- error = xfs_alloc_pagf_init(mp, NULL, index, 0);
- if (error)
+ pag = xfs_perag_get(mp, index);
+ error = xfs_alloc_read_agf(pag, NULL, 0, NULL);
+ if (!error)
+ error = xfs_ialloc_read_agi(pag, NULL, NULL);
+ if (error) {
+ xfs_perag_put(pag);
return error;
+ }
- error = xfs_ialloc_pagi_init(mp, NULL, index);
- if (error)
- return error;
- pag = xfs_perag_get(mp, index);
ifree += pag->pagi_freecount;
ialloc += pag->pagi_count;
bfree += pag->pagf_freeblks;
@@ -173,7 +173,6 @@ __xfs_free_perag(
struct xfs_perag *pag = container_of(head, struct xfs_perag, rcu_head);
ASSERT(!delayed_work_pending(&pag->pag_blockgc_work));
- ASSERT(atomic_read(&pag->pag_ref) == 0);
kmem_free(pag);
}
@@ -192,20 +191,79 @@ xfs_free_perag(
pag = radix_tree_delete(&mp->m_perag_tree, agno);
spin_unlock(&mp->m_perag_lock);
ASSERT(pag);
- ASSERT(atomic_read(&pag->pag_ref) == 0);
+ XFS_IS_CORRUPT(pag->pag_mount, atomic_read(&pag->pag_ref) != 0);
cancel_delayed_work_sync(&pag->pag_blockgc_work);
- xfs_iunlink_destroy(pag);
xfs_buf_hash_destroy(pag);
call_rcu(&pag->rcu_head, __xfs_free_perag);
}
}
+/* Find the size of the AG, in blocks. */
+static xfs_agblock_t
+__xfs_ag_block_count(
+ struct xfs_mount *mp,
+ xfs_agnumber_t agno,
+ xfs_agnumber_t agcount,
+ xfs_rfsblock_t dblocks)
+{
+ ASSERT(agno < agcount);
+
+ if (agno < agcount - 1)
+ return mp->m_sb.sb_agblocks;
+ return dblocks - (agno * mp->m_sb.sb_agblocks);
+}
+
+xfs_agblock_t
+xfs_ag_block_count(
+ struct xfs_mount *mp,
+ xfs_agnumber_t agno)
+{
+ return __xfs_ag_block_count(mp, agno, mp->m_sb.sb_agcount,
+ mp->m_sb.sb_dblocks);
+}
+
+/* Calculate the first and last possible inode number in an AG. */
+static void
+__xfs_agino_range(
+ struct xfs_mount *mp,
+ xfs_agblock_t eoag,
+ xfs_agino_t *first,
+ xfs_agino_t *last)
+{
+ xfs_agblock_t bno;
+
+ /*
+ * Calculate the first inode, which will be in the first
+ * cluster-aligned block after the AGFL.
+ */
+ bno = round_up(XFS_AGFL_BLOCK(mp) + 1, M_IGEO(mp)->cluster_align);
+ *first = XFS_AGB_TO_AGINO(mp, bno);
+
+ /*
+ * Calculate the last inode, which will be at the end of the
+ * last (aligned) cluster that can be allocated in the AG.
+ */
+ bno = round_down(eoag, M_IGEO(mp)->cluster_align);
+ *last = XFS_AGB_TO_AGINO(mp, bno) - 1;
+}
+
+void
+xfs_agino_range(
+ struct xfs_mount *mp,
+ xfs_agnumber_t agno,
+ xfs_agino_t *first,
+ xfs_agino_t *last)
+{
+ return __xfs_agino_range(mp, xfs_ag_block_count(mp, agno), first, last);
+}
+
int
xfs_initialize_perag(
struct xfs_mount *mp,
xfs_agnumber_t agcount,
+ xfs_rfsblock_t dblocks,
xfs_agnumber_t *maxagi)
{
struct xfs_perag *pag;
@@ -264,13 +322,18 @@ xfs_initialize_perag(
if (error)
goto out_remove_pag;
- error = xfs_iunlink_init(pag);
- if (error)
- goto out_hash_destroy;
-
/* first new pag is fully initialized */
if (first_initialised == NULLAGNUMBER)
first_initialised = index;
+
+ /*
+ * Pre-calculated geometry
+ */
+ pag->block_count = __xfs_ag_block_count(mp, index, agcount,
+ dblocks);
+ pag->min_block = XFS_AGFL_BLOCK(mp);
+ __xfs_agino_range(mp, pag->block_count, &pag->agino_min,
+ &pag->agino_max);
}
index = xfs_set_inode_alloc(mp, agcount);
@@ -281,8 +344,6 @@ xfs_initialize_perag(
mp->m_ag_prealloc_blocks = xfs_prealloc_blocks(mp);
return 0;
-out_hash_destroy:
- xfs_buf_hash_destroy(pag);
out_remove_pag:
radix_tree_delete(&mp->m_perag_tree, index);
out_free_pag:
@@ -294,7 +355,6 @@ out_unwind_new_pags:
if (!pag)
break;
xfs_buf_hash_destroy(pag);
- xfs_iunlink_destroy(pag);
kmem_free(pag);
}
return error;
@@ -322,12 +382,6 @@ xfs_get_aghdr_buf(
return 0;
}
-static inline bool is_log_ag(struct xfs_mount *mp, struct aghdr_init_data *id)
-{
- return mp->m_sb.sb_logstart > 0 &&
- id->agno == XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart);
-}
-
/*
* Generic btree root block init function
*/
@@ -353,7 +407,7 @@ xfs_freesp_init_recs(
arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks);
- if (is_log_ag(mp, id)) {
+ if (xfs_ag_contains_log(mp, id->agno)) {
struct xfs_alloc_rec *nrec;
xfs_agblock_t start = XFS_FSB_TO_AGBNO(mp,
mp->m_sb.sb_logstart);
@@ -480,7 +534,7 @@ xfs_rmaproot_init(
}
/* account for the log space */
- if (is_log_ag(mp, id)) {
+ if (xfs_ag_contains_log(mp, id->agno)) {
rrec = XFS_RMAP_REC_ADDR(block,
be16_to_cpu(block->bb_numrecs) + 1);
rrec->rm_startblock = cpu_to_be32(
@@ -551,7 +605,7 @@ xfs_agfblock_init(
agf->agf_refcount_blocks = cpu_to_be32(1);
}
- if (is_log_ag(mp, id)) {
+ if (xfs_ag_contains_log(mp, id->agno)) {
int64_t logblocks = mp->m_sb.sb_logblocks;
be32_add_cpu(&agf->agf_freeblks, -logblocks);
@@ -762,11 +816,11 @@ xfs_ag_init_headers(
int
xfs_ag_shrink_space(
- struct xfs_mount *mp,
+ struct xfs_perag *pag,
struct xfs_trans **tpp,
- xfs_agnumber_t agno,
xfs_extlen_t delta)
{
+ struct xfs_mount *mp = pag->pag_mount;
struct xfs_alloc_arg args = {
.tp = *tpp,
.mp = mp,
@@ -783,14 +837,14 @@ xfs_ag_shrink_space(
xfs_agblock_t aglen;
int error, err2;
- ASSERT(agno == mp->m_sb.sb_agcount - 1);
- error = xfs_ialloc_read_agi(mp, *tpp, agno, &agibp);
+ ASSERT(pag->pag_agno == mp->m_sb.sb_agcount - 1);
+ error = xfs_ialloc_read_agi(pag, *tpp, &agibp);
if (error)
return error;
agi = agibp->b_addr;
- error = xfs_alloc_read_agf(mp, *tpp, agno, 0, &agfbp);
+ error = xfs_alloc_read_agf(pag, *tpp, 0, &agfbp);
if (error)
return error;
@@ -802,13 +856,14 @@ xfs_ag_shrink_space(
if (delta >= aglen)
return -EINVAL;
- args.fsbno = XFS_AGB_TO_FSB(mp, agno, aglen - delta);
+ args.fsbno = XFS_AGB_TO_FSB(mp, pag->pag_agno, aglen - delta);
/*
* Make sure that the last inode cluster cannot overlap with the new
* end of the AG, even if it's sparse.
*/
- error = xfs_ialloc_check_shrink(*tpp, agno, agibp, aglen - delta);
+ error = xfs_ialloc_check_shrink(*tpp, pag->pag_agno, agibp,
+ aglen - delta);
if (error)
return error;
@@ -816,7 +871,7 @@ xfs_ag_shrink_space(
* Disable perag reservations so it doesn't cause the allocation request
* to fail. We'll reestablish reservation before we return.
*/
- error = xfs_ag_resv_free(agibp->b_pag);
+ error = xfs_ag_resv_free(pag);
if (error)
return error;
@@ -845,7 +900,7 @@ xfs_ag_shrink_space(
be32_add_cpu(&agi->agi_length, -delta);
be32_add_cpu(&agf->agf_length, -delta);
- err2 = xfs_ag_resv_init(agibp->b_pag, *tpp);
+ err2 = xfs_ag_resv_init(pag, *tpp);
if (err2) {
be32_add_cpu(&agi->agi_length, delta);
be32_add_cpu(&agf->agf_length, delta);
@@ -869,8 +924,9 @@ xfs_ag_shrink_space(
xfs_ialloc_log_agi(*tpp, agibp, XFS_AGI_LENGTH);
xfs_alloc_log_agf(*tpp, agfbp, XFS_AGF_LENGTH);
return 0;
+
resv_init_out:
- err2 = xfs_ag_resv_init(agibp->b_pag, *tpp);
+ err2 = xfs_ag_resv_init(pag, *tpp);
if (!err2)
return error;
resv_err:
@@ -884,9 +940,8 @@ resv_err:
*/
int
xfs_ag_extend_space(
- struct xfs_mount *mp,
+ struct xfs_perag *pag,
struct xfs_trans *tp,
- struct aghdr_init_data *id,
xfs_extlen_t len)
{
struct xfs_buf *bp;
@@ -894,23 +949,20 @@ xfs_ag_extend_space(
struct xfs_agf *agf;
int error;
- /*
- * Change the agi length.
- */
- error = xfs_ialloc_read_agi(mp, tp, id->agno, &bp);
+ ASSERT(pag->pag_agno == pag->pag_mount->m_sb.sb_agcount - 1);
+
+ error = xfs_ialloc_read_agi(pag, tp, &bp);
if (error)
return error;
agi = bp->b_addr;
be32_add_cpu(&agi->agi_length, len);
- ASSERT(id->agno == mp->m_sb.sb_agcount - 1 ||
- be32_to_cpu(agi->agi_length) == mp->m_sb.sb_agblocks);
xfs_ialloc_log_agi(tp, bp, XFS_AGI_LENGTH);
/*
* Change agf length.
*/
- error = xfs_alloc_read_agf(mp, tp, id->agno, 0, &bp);
+ error = xfs_alloc_read_agf(pag, tp, 0, &bp);
if (error)
return error;
@@ -925,49 +977,49 @@ xfs_ag_extend_space(
* XFS_RMAP_OINFO_SKIP_UPDATE is used here to tell the rmap btree that
* this doesn't actually exist in the rmap btree.
*/
- error = xfs_rmap_free(tp, bp, bp->b_pag,
- be32_to_cpu(agf->agf_length) - len,
+ error = xfs_rmap_free(tp, bp, pag, be32_to_cpu(agf->agf_length) - len,
len, &XFS_RMAP_OINFO_SKIP_UPDATE);
if (error)
return error;
- return xfs_free_extent(tp, XFS_AGB_TO_FSB(mp, id->agno,
+ error = xfs_free_extent(tp, XFS_AGB_TO_FSB(pag->pag_mount, pag->pag_agno,
be32_to_cpu(agf->agf_length) - len),
len, &XFS_RMAP_OINFO_SKIP_UPDATE,
XFS_AG_RESV_NONE);
+ if (error)
+ return error;
+
+ /* Update perag geometry */
+ pag->block_count = be32_to_cpu(agf->agf_length);
+ __xfs_agino_range(pag->pag_mount, pag->block_count, &pag->agino_min,
+ &pag->agino_max);
+ return 0;
}
/* Retrieve AG geometry. */
int
xfs_ag_get_geometry(
- struct xfs_mount *mp,
- xfs_agnumber_t agno,
+ struct xfs_perag *pag,
struct xfs_ag_geometry *ageo)
{
struct xfs_buf *agi_bp;
struct xfs_buf *agf_bp;
struct xfs_agi *agi;
struct xfs_agf *agf;
- struct xfs_perag *pag;
unsigned int freeblks;
int error;
- if (agno >= mp->m_sb.sb_agcount)
- return -EINVAL;
-
/* Lock the AG headers. */
- error = xfs_ialloc_read_agi(mp, NULL, agno, &agi_bp);
+ error = xfs_ialloc_read_agi(pag, NULL, &agi_bp);
if (error)
return error;
- error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agf_bp);
+ error = xfs_alloc_read_agf(pag, NULL, 0, &agf_bp);
if (error)
goto out_agi;
- pag = agi_bp->b_pag;
-
/* Fill out form. */
memset(ageo, 0, sizeof(*ageo));
- ageo->ag_number = agno;
+ ageo->ag_number = pag->pag_agno;
agi = agi_bp->b_addr;
ageo->ag_icount = be32_to_cpu(agi->agi_count);
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index e411d51c2589..191b22b9a35b 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -67,6 +67,12 @@ struct xfs_perag {
/* for rcu-safe freeing */
struct rcu_head rcu_head;
+ /* Precalculated geometry info */
+ xfs_agblock_t block_count;
+ xfs_agblock_t min_block;
+ xfs_agino_t agino_min;
+ xfs_agino_t agino_max;
+
#ifdef __KERNEL__
/* -- kernel only structures below this line -- */
@@ -97,17 +103,11 @@ struct xfs_perag {
/* background prealloc block trimming */
struct delayed_work pag_blockgc_work;
- /*
- * Unlinked inode information. This incore information reflects
- * data stored in the AGI, so callers must hold the AGI buffer lock
- * or have some other means to control concurrency.
- */
- struct rhashtable pagi_unlinked_hash;
#endif /* __KERNEL__ */
};
int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t agcount,
- xfs_agnumber_t *maxagi);
+ xfs_rfsblock_t dcount, xfs_agnumber_t *maxagi);
int xfs_initialize_perag_data(struct xfs_mount *mp, xfs_agnumber_t agno);
void xfs_free_perag(struct xfs_mount *mp);
@@ -117,6 +117,71 @@ struct xfs_perag *xfs_perag_get_tag(struct xfs_mount *mp, xfs_agnumber_t agno,
void xfs_perag_put(struct xfs_perag *pag);
/*
+ * Per-ag geometry infomation and validation
+ */
+xfs_agblock_t xfs_ag_block_count(struct xfs_mount *mp, xfs_agnumber_t agno);
+void xfs_agino_range(struct xfs_mount *mp, xfs_agnumber_t agno,
+ xfs_agino_t *first, xfs_agino_t *last);
+
+static inline bool
+xfs_verify_agbno(struct xfs_perag *pag, xfs_agblock_t agbno)
+{
+ if (agbno >= pag->block_count)
+ return false;
+ if (agbno <= pag->min_block)
+ return false;
+ return true;
+}
+
+static inline bool
+xfs_verify_agbext(
+ struct xfs_perag *pag,
+ xfs_agblock_t agbno,
+ xfs_agblock_t len)
+{
+ if (agbno + len <= agbno)
+ return false;
+
+ if (!xfs_verify_agbno(pag, agbno))
+ return false;
+
+ return xfs_verify_agbno(pag, agbno + len - 1);
+}
+
+/*
+ * Verify that an AG inode number pointer neither points outside the AG
+ * nor points at static metadata.
+ */
+static inline bool
+xfs_verify_agino(struct xfs_perag *pag, xfs_agino_t agino)
+{
+ if (agino < pag->agino_min)
+ return false;
+ if (agino > pag->agino_max)
+ return false;
+ return true;
+}
+
+/*
+ * Verify that an AG inode number pointer neither points outside the AG
+ * nor points at static metadata, or is NULLAGINO.
+ */
+static inline bool
+xfs_verify_agino_or_null(struct xfs_perag *pag, xfs_agino_t agino)
+{
+ if (agino == NULLAGINO)
+ return true;
+ return xfs_verify_agino(pag, agino);
+}
+
+static inline bool
+xfs_ag_contains_log(struct xfs_mount *mp, xfs_agnumber_t agno)
+{
+ return mp->m_sb.sb_logstart > 0 &&
+ agno == XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart);
+}
+
+/*
* Perag iteration APIs
*/
static inline struct xfs_perag *
@@ -168,11 +233,10 @@ struct aghdr_init_data {
};
int xfs_ag_init_headers(struct xfs_mount *mp, struct aghdr_init_data *id);
-int xfs_ag_shrink_space(struct xfs_mount *mp, struct xfs_trans **tpp,
- xfs_agnumber_t agno, xfs_extlen_t delta);
-int xfs_ag_extend_space(struct xfs_mount *mp, struct xfs_trans *tp,
- struct aghdr_init_data *id, xfs_extlen_t len);
-int xfs_ag_get_geometry(struct xfs_mount *mp, xfs_agnumber_t agno,
- struct xfs_ag_geometry *ageo);
+int xfs_ag_shrink_space(struct xfs_perag *pag, struct xfs_trans **tpp,
+ xfs_extlen_t delta);
+int xfs_ag_extend_space(struct xfs_perag *pag, struct xfs_trans *tp,
+ xfs_extlen_t len);
+int xfs_ag_get_geometry(struct xfs_perag *pag, struct xfs_ag_geometry *ageo);
#endif /* __LIBXFS_AG_H */
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index fe94058d4e9e..5af123d13a63 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -322,7 +322,7 @@ out:
* address.
*/
if (has_resv) {
- error2 = xfs_alloc_pagf_init(mp, tp, pag->pag_agno, 0);
+ error2 = xfs_alloc_read_agf(pag, tp, 0, NULL);
if (error2)
return error2;
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 353e53b892e6..de79f5d07f65 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -82,6 +82,24 @@ xfs_prealloc_blocks(
}
/*
+ * The number of blocks per AG that we withhold from xfs_mod_fdblocks to
+ * guarantee that we can refill the AGFL prior to allocating space in a nearly
+ * full AG. Although the space described by the free space btrees, the
+ * blocks used by the freesp btrees themselves, and the blocks owned by the
+ * AGFL are counted in the ondisk fdblocks, it's a mistake to let the ondisk
+ * free space in the AG drop so low that the free space btrees cannot refill an
+ * empty AGFL up to the minimum level. Rather than grind through empty AGs
+ * until the fs goes down, we subtract this many AG blocks from the incore
+ * fdblocks to ensure user allocation does not overcommit the space the
+ * filesystem needs for the AGFLs. The rmap btree uses a per-AG reservation to
+ * withhold space from xfs_mod_fdblocks, so we do not account for that here.
+ */
+#define XFS_ALLOCBT_AGFL_RESERVE 4
+
+/*
+ * Compute the number of blocks that we set aside to guarantee the ability to
+ * refill the AGFL and handle a full bmap btree split.
+ *
* In order to avoid ENOSPC-related deadlock caused by out-of-order locking of
* AGF buffer (PV 947395), we place constraints on the relationship among
* actual allocations for data blocks, freelist blocks, and potential file data
@@ -93,14 +111,14 @@ xfs_prealloc_blocks(
* extents need to be actually allocated. To get around this, we explicitly set
* aside a few blocks which will not be reserved in delayed allocation.
*
- * We need to reserve 4 fsbs _per AG_ for the freelist and 4 more to handle a
- * potential split of the file's bmap btree.
+ * For each AG, we need to reserve enough blocks to replenish a totally empty
+ * AGFL and 4 more to handle a potential split of the file's bmap btree.
*/
unsigned int
xfs_alloc_set_aside(
struct xfs_mount *mp)
{
- return mp->m_sb.sb_agcount * (XFS_ALLOC_AGFL_RESERVE + 4);
+ return mp->m_sb.sb_agcount * (XFS_ALLOCBT_AGFL_RESERVE + 4);
}
/*
@@ -124,12 +142,12 @@ xfs_alloc_ag_max_usable(
unsigned int blocks;
blocks = XFS_BB_TO_FSB(mp, XFS_FSS_TO_BB(mp, 4)); /* ag headers */
- blocks += XFS_ALLOC_AGFL_RESERVE;
+ blocks += XFS_ALLOCBT_AGFL_RESERVE;
blocks += 3; /* AGF, AGI btree root blocks */
if (xfs_has_finobt(mp))
blocks++; /* finobt root block */
if (xfs_has_rmapbt(mp))
- blocks++; /* rmap root block */
+ blocks++; /* rmap root block */
if (xfs_has_reflink(mp))
blocks++; /* refcount root block */
@@ -230,7 +248,7 @@ xfs_alloc_get_rec(
int *stat) /* output: success/failure */
{
struct xfs_mount *mp = cur->bc_mp;
- xfs_agnumber_t agno = cur->bc_ag.pag->pag_agno;
+ struct xfs_perag *pag = cur->bc_ag.pag;
union xfs_btree_rec *rec;
int error;
@@ -245,11 +263,7 @@ xfs_alloc_get_rec(
goto out_bad_rec;
/* check for valid extent range, including overflow */
- if (!xfs_verify_agbno(mp, agno, *bno))
- goto out_bad_rec;
- if (*bno > *bno + *len)
- goto out_bad_rec;
- if (!xfs_verify_agbno(mp, agno, *bno + *len - 1))
+ if (!xfs_verify_agbext(pag, *bno, *len))
goto out_bad_rec;
return 0;
@@ -257,7 +271,8 @@ xfs_alloc_get_rec(
out_bad_rec:
xfs_warn(mp,
"%s Freespace BTree record corruption in AG %d detected!",
- cur->bc_btnum == XFS_BTNUM_BNO ? "Block" : "Size", agno);
+ cur->bc_btnum == XFS_BTNUM_BNO ? "Block" : "Size",
+ pag->pag_agno);
xfs_warn(mp,
"start block 0x%x block count 0x%x", *bno, *len);
return -EFSCORRUPTED;
@@ -685,20 +700,19 @@ const struct xfs_buf_ops xfs_agfl_buf_ops = {
/*
* Read in the allocation group free block array.
*/
-int /* error */
+int
xfs_alloc_read_agfl(
- xfs_mount_t *mp, /* mount point structure */
- xfs_trans_t *tp, /* transaction pointer */
- xfs_agnumber_t agno, /* allocation group number */
- struct xfs_buf **bpp) /* buffer for the ag free block array */
+ struct xfs_perag *pag,
+ struct xfs_trans *tp,
+ struct xfs_buf **bpp)
{
- struct xfs_buf *bp; /* return value */
- int error;
+ struct xfs_mount *mp = pag->pag_mount;
+ struct xfs_buf *bp;
+ int error;
- ASSERT(agno != NULLAGNUMBER);
error = xfs_trans_read_buf(
mp, tp, mp->m_ddev_targp,
- XFS_AG_DADDR(mp, agno, XFS_AGFL_DADDR(mp)),
+ XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGFL_DADDR(mp)),
XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_agfl_buf_ops);
if (error)
return error;
@@ -1057,7 +1071,8 @@ xfs_alloc_ag_vextent_small(
be32_to_cpu(agf->agf_flcount) <= args->minleft)
goto out;
- error = xfs_alloc_get_freelist(args->tp, args->agbp, &fbno, 0);
+ error = xfs_alloc_get_freelist(args->pag, args->tp, args->agbp,
+ &fbno, 0);
if (error)
goto error;
if (fbno == NULLAGBLOCK)
@@ -1501,7 +1516,7 @@ xfs_alloc_ag_vextent_lastblock(
#ifdef DEBUG
/* Randomly don't execute the first algorithm. */
- if (prandom_u32() & 1)
+ if (prandom_u32_max(2))
return 0;
#endif
@@ -2493,7 +2508,7 @@ __xfs_free_extent_later(
ASSERT(bno != NULLFSBLOCK);
ASSERT(len > 0);
- ASSERT(len <= MAXEXTLEN);
+ ASSERT(len <= XFS_MAX_BMBT_EXTLEN);
ASSERT(!isnullstartblock(bno));
agno = XFS_FSB_TO_AGNO(mp, bno);
agbno = XFS_FSB_TO_AGBNO(mp, bno);
@@ -2591,7 +2606,7 @@ xfs_alloc_fix_freelist(
ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
if (!pag->pagf_init) {
- error = xfs_alloc_read_agf(mp, tp, args->agno, flags, &agbp);
+ error = xfs_alloc_read_agf(pag, tp, flags, &agbp);
if (error) {
/* Couldn't lock the AGF so skip this AG. */
if (error == -EAGAIN)
@@ -2621,7 +2636,7 @@ xfs_alloc_fix_freelist(
* Can fail if we're not blocking on locks, and it's held.
*/
if (!agbp) {
- error = xfs_alloc_read_agf(mp, tp, args->agno, flags, &agbp);
+ error = xfs_alloc_read_agf(pag, tp, flags, &agbp);
if (error) {
/* Couldn't lock the AGF so skip this AG. */
if (error == -EAGAIN)
@@ -2679,7 +2694,7 @@ xfs_alloc_fix_freelist(
else
targs.oinfo = XFS_RMAP_OINFO_AG;
while (!(flags & XFS_ALLOC_FLAG_NOSHRINK) && pag->pagf_flcount > need) {
- error = xfs_alloc_get_freelist(tp, agbp, &bno, 0);
+ error = xfs_alloc_get_freelist(pag, tp, agbp, &bno, 0);
if (error)
goto out_agbp_relse;
@@ -2694,7 +2709,7 @@ xfs_alloc_fix_freelist(
targs.alignment = targs.minlen = targs.prod = 1;
targs.type = XFS_ALLOCTYPE_THIS_AG;
targs.pag = pag;
- error = xfs_alloc_read_agfl(mp, tp, targs.agno, &agflbp);
+ error = xfs_alloc_read_agfl(pag, tp, &agflbp);
if (error)
goto out_agbp_relse;
@@ -2723,7 +2738,7 @@ xfs_alloc_fix_freelist(
* Put each allocated block on the list.
*/
for (bno = targs.agbno; bno < targs.agbno + targs.len; bno++) {
- error = xfs_alloc_put_freelist(tp, agbp,
+ error = xfs_alloc_put_freelist(pag, tp, agbp,
agflbp, bno, 0);
if (error)
goto out_agflbp_relse;
@@ -2749,6 +2764,7 @@ out_no_agbp:
*/
int
xfs_alloc_get_freelist(
+ struct xfs_perag *pag,
struct xfs_trans *tp,
struct xfs_buf *agbp,
xfs_agblock_t *bnop,
@@ -2759,9 +2775,8 @@ xfs_alloc_get_freelist(
xfs_agblock_t bno;
__be32 *agfl_bno;
int error;
- int logflags;
+ uint32_t logflags;
struct xfs_mount *mp = tp->t_mountp;
- struct xfs_perag *pag;
/*
* Freelist is empty, give up.
@@ -2773,8 +2788,7 @@ xfs_alloc_get_freelist(
/*
* Read the array of free blocks.
*/
- error = xfs_alloc_read_agfl(mp, tp, be32_to_cpu(agf->agf_seqno),
- &agflbp);
+ error = xfs_alloc_read_agfl(pag, tp, &agflbp);
if (error)
return error;
@@ -2789,7 +2803,6 @@ xfs_alloc_get_freelist(
if (be32_to_cpu(agf->agf_flfirst) == xfs_agfl_size(mp))
agf->agf_flfirst = 0;
- pag = agbp->b_pag;
ASSERT(!pag->pagf_agflreset);
be32_add_cpu(&agf->agf_flcount, -1);
pag->pagf_flcount--;
@@ -2812,9 +2825,9 @@ xfs_alloc_get_freelist(
*/
void
xfs_alloc_log_agf(
- xfs_trans_t *tp, /* transaction pointer */
- struct xfs_buf *bp, /* buffer for a.g. freelist header */
- int fields) /* mask of fields to be logged (XFS_AGF_...) */
+ struct xfs_trans *tp,
+ struct xfs_buf *bp,
+ uint32_t fields)
{
int first; /* first byte offset */
int last; /* last byte offset */
@@ -2850,29 +2863,11 @@ xfs_alloc_log_agf(
}
/*
- * Interface for inode allocation to force the pag data to be initialized.
- */
-int /* error */
-xfs_alloc_pagf_init(
- xfs_mount_t *mp, /* file system mount structure */
- xfs_trans_t *tp, /* transaction pointer */
- xfs_agnumber_t agno, /* allocation group number */
- int flags) /* XFS_ALLOC_FLAGS_... */
-{
- struct xfs_buf *bp;
- int error;
-
- error = xfs_alloc_read_agf(mp, tp, agno, flags, &bp);
- if (!error)
- xfs_trans_brelse(tp, bp);
- return error;
-}
-
-/*
* Put the block on the freelist for the allocation group.
*/
int
xfs_alloc_put_freelist(
+ struct xfs_perag *pag,
struct xfs_trans *tp,
struct xfs_buf *agbp,
struct xfs_buf *agflbp,
@@ -2881,21 +2876,22 @@ xfs_alloc_put_freelist(
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_agf *agf = agbp->b_addr;
- struct xfs_perag *pag;
__be32 *blockp;
int error;
- int logflags;
+ uint32_t logflags;
__be32 *agfl_bno;
int startoff;
- if (!agflbp && (error = xfs_alloc_read_agfl(mp, tp,
- be32_to_cpu(agf->agf_seqno), &agflbp)))
- return error;
+ if (!agflbp) {
+ error = xfs_alloc_read_agfl(pag, tp, &agflbp);
+ if (error)
+ return error;
+ }
+
be32_add_cpu(&agf->agf_fllast, 1);
if (be32_to_cpu(agf->agf_fllast) == xfs_agfl_size(mp))
agf->agf_fllast = 0;
- pag = agbp->b_pag;
ASSERT(!pag->pagf_agflreset);
be32_add_cpu(&agf->agf_flcount, 1);
pag->pagf_flcount++;
@@ -3052,61 +3048,57 @@ const struct xfs_buf_ops xfs_agf_buf_ops = {
/*
* Read in the allocation group header (free/alloc section).
*/
-int /* error */
+int
xfs_read_agf(
- struct xfs_mount *mp, /* mount point structure */
- struct xfs_trans *tp, /* transaction pointer */
- xfs_agnumber_t agno, /* allocation group number */
- int flags, /* XFS_BUF_ */
- struct xfs_buf **bpp) /* buffer for the ag freelist header */
+ struct xfs_perag *pag,
+ struct xfs_trans *tp,
+ int flags,
+ struct xfs_buf **agfbpp)
{
- int error;
+ struct xfs_mount *mp = pag->pag_mount;
+ int error;
- trace_xfs_read_agf(mp, agno);
+ trace_xfs_read_agf(pag->pag_mount, pag->pag_agno);
- ASSERT(agno != NULLAGNUMBER);
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
- XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)),
- XFS_FSS_TO_BB(mp, 1), flags, bpp, &xfs_agf_buf_ops);
+ XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGF_DADDR(mp)),
+ XFS_FSS_TO_BB(mp, 1), flags, agfbpp, &xfs_agf_buf_ops);
if (error)
return error;
- ASSERT(!(*bpp)->b_error);
- xfs_buf_set_ref(*bpp, XFS_AGF_REF);
+ xfs_buf_set_ref(*agfbpp, XFS_AGF_REF);
return 0;
}
/*
- * Read in the allocation group header (free/alloc section).
+ * Read in the allocation group header (free/alloc section) and initialise the
+ * perag structure if necessary. If the caller provides @agfbpp, then return the
+ * locked buffer to the caller, otherwise free it.
*/
-int /* error */
+int
xfs_alloc_read_agf(
- struct xfs_mount *mp, /* mount point structure */
- struct xfs_trans *tp, /* transaction pointer */
- xfs_agnumber_t agno, /* allocation group number */
- int flags, /* XFS_ALLOC_FLAG_... */
- struct xfs_buf **bpp) /* buffer for the ag freelist header */
+ struct xfs_perag *pag,
+ struct xfs_trans *tp,
+ int flags,
+ struct xfs_buf **agfbpp)
{
- struct xfs_agf *agf; /* ag freelist header */
- struct xfs_perag *pag; /* per allocation group data */
+ struct xfs_buf *agfbp;
+ struct xfs_agf *agf;
int error;
int allocbt_blks;
- trace_xfs_alloc_read_agf(mp, agno);
+ trace_xfs_alloc_read_agf(pag->pag_mount, pag->pag_agno);
/* We don't support trylock when freeing. */
ASSERT((flags & (XFS_ALLOC_FLAG_FREEING | XFS_ALLOC_FLAG_TRYLOCK)) !=
(XFS_ALLOC_FLAG_FREEING | XFS_ALLOC_FLAG_TRYLOCK));
- ASSERT(agno != NULLAGNUMBER);
- error = xfs_read_agf(mp, tp, agno,
+ error = xfs_read_agf(pag, tp,
(flags & XFS_ALLOC_FLAG_TRYLOCK) ? XBF_TRYLOCK : 0,
- bpp);
+ &agfbp);
if (error)
return error;
- ASSERT(!(*bpp)->b_error);
- agf = (*bpp)->b_addr;
- pag = (*bpp)->b_pag;
+ agf = agfbp->b_addr;
if (!pag->pagf_init) {
pag->pagf_freeblks = be32_to_cpu(agf->agf_freeblks);
pag->pagf_btreeblks = be32_to_cpu(agf->agf_btreeblks);
@@ -3120,7 +3112,7 @@ xfs_alloc_read_agf(
be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAPi]);
pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
pag->pagf_init = 1;
- pag->pagf_agflreset = xfs_agfl_needs_reset(mp, agf);
+ pag->pagf_agflreset = xfs_agfl_needs_reset(pag->pag_mount, agf);
/*
* Update the in-core allocbt counter. Filter out the rmapbt
@@ -3130,13 +3122,14 @@ xfs_alloc_read_agf(
* counter only tracks non-root blocks.
*/
allocbt_blks = pag->pagf_btreeblks;
- if (xfs_has_rmapbt(mp))
+ if (xfs_has_rmapbt(pag->pag_mount))
allocbt_blks -= be32_to_cpu(agf->agf_rmap_blocks) - 1;
if (allocbt_blks > 0)
- atomic64_add(allocbt_blks, &mp->m_allocbt_blks);
+ atomic64_add(allocbt_blks,
+ &pag->pag_mount->m_allocbt_blks);
}
#ifdef DEBUG
- else if (!xfs_is_shutdown(mp)) {
+ else if (!xfs_is_shutdown(pag->pag_mount)) {
ASSERT(pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks));
ASSERT(pag->pagf_btreeblks == be32_to_cpu(agf->agf_btreeblks));
ASSERT(pag->pagf_flcount == be32_to_cpu(agf->agf_flcount));
@@ -3147,6 +3140,10 @@ xfs_alloc_read_agf(
be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNTi]));
}
#endif
+ if (agfbpp)
+ *agfbpp = agfbp;
+ else
+ xfs_trans_brelse(tp, agfbp);
return 0;
}
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 1c14a0b1abea..2c3f762dfb58 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -88,7 +88,6 @@ typedef struct xfs_alloc_arg {
#define XFS_ALLOC_NOBUSY (1 << 2)/* Busy extents not allowed */
/* freespace limit calculations */
-#define XFS_ALLOC_AGFL_RESERVE 4
unsigned int xfs_alloc_set_aside(struct xfs_mount *mp);
unsigned int xfs_alloc_ag_max_usable(struct xfs_mount *mp);
@@ -96,6 +95,11 @@ xfs_extlen_t xfs_alloc_longest_free_extent(struct xfs_perag *pag,
xfs_extlen_t need, xfs_extlen_t reserved);
unsigned int xfs_alloc_min_freelist(struct xfs_mount *mp,
struct xfs_perag *pag);
+int xfs_alloc_get_freelist(struct xfs_perag *pag, struct xfs_trans *tp,
+ struct xfs_buf *agfbp, xfs_agblock_t *bnop, int btreeblk);
+int xfs_alloc_put_freelist(struct xfs_perag *pag, struct xfs_trans *tp,
+ struct xfs_buf *agfbp, struct xfs_buf *agflbp,
+ xfs_agblock_t bno, int btreeblk);
/*
* Compute and fill in value of m_alloc_maxlevels.
@@ -105,56 +109,13 @@ xfs_alloc_compute_maxlevels(
struct xfs_mount *mp); /* file system mount structure */
/*
- * Get a block from the freelist.
- * Returns with the buffer for the block gotten.
- */
-int /* error */
-xfs_alloc_get_freelist(
- struct xfs_trans *tp, /* transaction pointer */
- struct xfs_buf *agbp, /* buffer containing the agf structure */
- xfs_agblock_t *bnop, /* block address retrieved from freelist */
- int btreeblk); /* destination is a AGF btree */
-
-/*
* Log the given fields from the agf structure.
*/
void
xfs_alloc_log_agf(
struct xfs_trans *tp, /* transaction pointer */
struct xfs_buf *bp, /* buffer for a.g. freelist header */
- int fields);/* mask of fields to be logged (XFS_AGF_...) */
-
-/*
- * Interface for inode allocation to force the pag data to be initialized.
- */
-int /* error */
-xfs_alloc_pagf_init(
- struct xfs_mount *mp, /* file system mount structure */
- struct xfs_trans *tp, /* transaction pointer */
- xfs_agnumber_t agno, /* allocation group number */
- int flags); /* XFS_ALLOC_FLAGS_... */
-
-/*
- * Put the block on the freelist for the allocation group.
- */
-int /* error */
-xfs_alloc_put_freelist(
- struct xfs_trans *tp, /* transaction pointer */
- struct xfs_buf *agbp, /* buffer for a.g. freelist header */
- struct xfs_buf *agflbp,/* buffer for a.g. free block array */
- xfs_agblock_t bno, /* block being freed */
- int btreeblk); /* owner was a AGF btree */
-
-/*
- * Read in the allocation group header (free/alloc section).
- */
-int /* error */
-xfs_alloc_read_agf(
- struct xfs_mount *mp, /* mount point structure */
- struct xfs_trans *tp, /* transaction pointer */
- xfs_agnumber_t agno, /* allocation group number */
- int flags, /* XFS_ALLOC_FLAG_... */
- struct xfs_buf **bpp); /* buffer for the ag freelist header */
+ uint32_t fields);/* mask of fields to be logged (XFS_AGF_...) */
/*
* Allocate an extent (variable-size).
@@ -207,10 +168,12 @@ xfs_alloc_get_rec(
xfs_extlen_t *len, /* output: length of extent */
int *stat); /* output: success/failure */
-int xfs_read_agf(struct xfs_mount *mp, struct xfs_trans *tp,
- xfs_agnumber_t agno, int flags, struct xfs_buf **bpp);
-int xfs_alloc_read_agfl(struct xfs_mount *mp, struct xfs_trans *tp,
- xfs_agnumber_t agno, struct xfs_buf **bpp);
+int xfs_read_agf(struct xfs_perag *pag, struct xfs_trans *tp, int flags,
+ struct xfs_buf **agfbpp);
+int xfs_alloc_read_agf(struct xfs_perag *pag, struct xfs_trans *tp, int flags,
+ struct xfs_buf **agfbpp);
+int xfs_alloc_read_agfl(struct xfs_perag *pag, struct xfs_trans *tp,
+ struct xfs_buf **bpp);
int xfs_free_agfl_block(struct xfs_trans *, xfs_agnumber_t, xfs_agblock_t,
struct xfs_buf *, struct xfs_owner_info *);
int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, int flags);
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 8c9f73cc0bee..549a3cba0234 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -60,8 +60,8 @@ xfs_allocbt_alloc_block(
xfs_agblock_t bno;
/* Allocate the new block from the freelist. If we can't, give up. */
- error = xfs_alloc_get_freelist(cur->bc_tp, cur->bc_ag.agbp,
- &bno, 1);
+ error = xfs_alloc_get_freelist(cur->bc_ag.pag, cur->bc_tp,
+ cur->bc_ag.agbp, &bno, 1);
if (error)
return error;
@@ -71,7 +71,7 @@ xfs_allocbt_alloc_block(
}
atomic64_inc(&cur->bc_mp->m_allocbt_blks);
- xfs_extent_busy_reuse(cur->bc_mp, cur->bc_ag.agbp->b_pag, bno, 1, false);
+ xfs_extent_busy_reuse(cur->bc_mp, cur->bc_ag.pag, bno, 1, false);
new->s = cpu_to_be32(bno);
@@ -89,7 +89,8 @@ xfs_allocbt_free_block(
int error;
bno = xfs_daddr_to_agbno(cur->bc_mp, xfs_buf_daddr(bp));
- error = xfs_alloc_put_freelist(cur->bc_tp, agbp, NULL, bno, 1);
+ error = xfs_alloc_put_freelist(cur->bc_ag.pag, cur->bc_tp, agbp, NULL,
+ bno, 1);
if (error)
return error;
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 23523b802539..e28d93d232de 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -24,6 +24,10 @@
#include "xfs_quota.h"
#include "xfs_trans_space.h"
#include "xfs_trace.h"
+#include "xfs_attr_item.h"
+#include "xfs_xattr.h"
+
+struct kmem_cache *xfs_attr_intent_cache;
/*
* xfs_attr.c
@@ -46,33 +50,27 @@ STATIC int xfs_attr_shortform_addname(xfs_da_args_t *args);
STATIC int xfs_attr_leaf_get(xfs_da_args_t *args);
STATIC int xfs_attr_leaf_removename(xfs_da_args_t *args);
STATIC int xfs_attr_leaf_hasname(struct xfs_da_args *args, struct xfs_buf **bp);
-STATIC int xfs_attr_leaf_try_add(struct xfs_da_args *args, struct xfs_buf *bp);
+STATIC int xfs_attr_leaf_try_add(struct xfs_da_args *args);
/*
* Internal routines when attribute list is more than one block.
*/
STATIC int xfs_attr_node_get(xfs_da_args_t *args);
STATIC void xfs_attr_restore_rmt_blk(struct xfs_da_args *args);
-STATIC int xfs_attr_node_addname(struct xfs_delattr_context *dac);
-STATIC int xfs_attr_node_addname_find_attr(struct xfs_delattr_context *dac);
-STATIC int xfs_attr_node_addname_clear_incomplete(
- struct xfs_delattr_context *dac);
-STATIC int xfs_attr_node_hasname(xfs_da_args_t *args,
- struct xfs_da_state **state);
-STATIC int xfs_attr_fillstate(xfs_da_state_t *state);
-STATIC int xfs_attr_refillstate(xfs_da_state_t *state);
-STATIC int xfs_attr_set_iter(struct xfs_delattr_context *dac,
- struct xfs_buf **leaf_bp);
-STATIC int xfs_attr_node_removename(struct xfs_da_args *args,
- struct xfs_da_state *state);
+static int xfs_attr_node_try_addname(struct xfs_attr_intent *attr);
+STATIC int xfs_attr_node_addname_find_attr(struct xfs_attr_intent *attr);
+STATIC int xfs_attr_node_remove_attr(struct xfs_attr_intent *attr);
+STATIC int xfs_attr_node_lookup(struct xfs_da_args *args,
+ struct xfs_da_state *state);
int
xfs_inode_hasattr(
struct xfs_inode *ip)
{
- if (!XFS_IFORK_Q(ip) ||
- (ip->i_afp->if_format == XFS_DINODE_FMT_EXTENTS &&
- ip->i_afp->if_nextents == 0))
+ if (!xfs_inode_has_attr_fork(ip))
+ return 0;
+ if (ip->i_af.if_format == XFS_DINODE_FMT_EXTENTS &&
+ ip->i_af.if_nextents == 0)
return 0;
return 1;
}
@@ -85,7 +83,7 @@ bool
xfs_attr_is_leaf(
struct xfs_inode *ip)
{
- struct xfs_ifork *ifp = ip->i_afp;
+ struct xfs_ifork *ifp = &ip->i_af;
struct xfs_iext_cursor icur;
struct xfs_bmbt_irec imap;
@@ -97,6 +95,123 @@ xfs_attr_is_leaf(
return imap.br_startoff == 0 && imap.br_blockcount == 1;
}
+/*
+ * XXX (dchinner): name path state saving and refilling is an optimisation to
+ * avoid needing to look up name entries after rolling transactions removing
+ * remote xattr blocks between the name entry lookup and name entry removal.
+ * This optimisation got sidelined when combining the set and remove state
+ * machines, but the code has been left in place because it is worthwhile to
+ * restore the optimisation once the combined state machine paths have settled.
+ *
+ * This comment is a public service announcement to remind Future Dave that he
+ * still needs to restore this code to working order.
+ */
+#if 0
+/*
+ * Fill in the disk block numbers in the state structure for the buffers
+ * that are attached to the state structure.
+ * This is done so that we can quickly reattach ourselves to those buffers
+ * after some set of transaction commits have released these buffers.
+ */
+static int
+xfs_attr_fillstate(xfs_da_state_t *state)
+{
+ xfs_da_state_path_t *path;
+ xfs_da_state_blk_t *blk;
+ int level;
+
+ trace_xfs_attr_fillstate(state->args);
+
+ /*
+ * Roll down the "path" in the state structure, storing the on-disk
+ * block number for those buffers in the "path".
+ */
+ path = &state->path;
+ ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
+ for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
+ if (blk->bp) {
+ blk->disk_blkno = xfs_buf_daddr(blk->bp);
+ blk->bp = NULL;
+ } else {
+ blk->disk_blkno = 0;
+ }
+ }
+
+ /*
+ * Roll down the "altpath" in the state structure, storing the on-disk
+ * block number for those buffers in the "altpath".
+ */
+ path = &state->altpath;
+ ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
+ for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
+ if (blk->bp) {
+ blk->disk_blkno = xfs_buf_daddr(blk->bp);
+ blk->bp = NULL;
+ } else {
+ blk->disk_blkno = 0;
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * Reattach the buffers to the state structure based on the disk block
+ * numbers stored in the state structure.
+ * This is done after some set of transaction commits have released those
+ * buffers from our grip.
+ */
+static int
+xfs_attr_refillstate(xfs_da_state_t *state)
+{
+ xfs_da_state_path_t *path;
+ xfs_da_state_blk_t *blk;
+ int level, error;
+
+ trace_xfs_attr_refillstate(state->args);
+
+ /*
+ * Roll down the "path" in the state structure, storing the on-disk
+ * block number for those buffers in the "path".
+ */
+ path = &state->path;
+ ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
+ for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
+ if (blk->disk_blkno) {
+ error = xfs_da3_node_read_mapped(state->args->trans,
+ state->args->dp, blk->disk_blkno,
+ &blk->bp, XFS_ATTR_FORK);
+ if (error)
+ return error;
+ } else {
+ blk->bp = NULL;
+ }
+ }
+
+ /*
+ * Roll down the "altpath" in the state structure, storing the on-disk
+ * block number for those buffers in the "altpath".
+ */
+ path = &state->altpath;
+ ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
+ for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
+ if (blk->disk_blkno) {
+ error = xfs_da3_node_read_mapped(state->args->trans,
+ state->args->dp, blk->disk_blkno,
+ &blk->bp, XFS_ATTR_FORK);
+ if (error)
+ return error;
+ } else {
+ blk->bp = NULL;
+ }
+ }
+
+ return 0;
+}
+#else
+static int xfs_attr_fillstate(xfs_da_state_t *state) { return 0; }
+#endif
+
/*========================================================================
* Overall external interface routines.
*========================================================================*/
@@ -114,7 +229,7 @@ xfs_attr_get_ilocked(
if (!xfs_inode_hasattr(args->dp))
return -ENOATTR;
- if (args->dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL)
+ if (args->dp->i_af.if_format == XFS_DINODE_FMT_LOCAL)
return xfs_attr_shortform_getvalue(args);
if (xfs_attr_is_leaf(args->dp))
return xfs_attr_leaf_get(args);
@@ -166,7 +281,7 @@ xfs_attr_get(
/*
* Calculate how many blocks we need for the new attribute,
*/
-STATIC int
+int
xfs_attr_calc_size(
struct xfs_da_args *args,
int *local)
@@ -199,6 +314,33 @@ xfs_attr_calc_size(
return nblks;
}
+/* Initialize transaction reservation for attr operations */
+void
+xfs_init_attr_trans(
+ struct xfs_da_args *args,
+ struct xfs_trans_res *tres,
+ unsigned int *total)
+{
+ struct xfs_mount *mp = args->dp->i_mount;
+
+ if (args->value) {
+ tres->tr_logres = M_RES(mp)->tr_attrsetm.tr_logres +
+ M_RES(mp)->tr_attrsetrt.tr_logres *
+ args->total;
+ tres->tr_logcount = XFS_ATTRSET_LOG_COUNT;
+ tres->tr_logflags = XFS_TRANS_PERM_LOG_RES;
+ *total = args->total;
+ } else {
+ *tres = M_RES(mp)->tr_attrrm;
+ *total = XFS_ATTRRM_SPACE_RES(mp);
+ }
+}
+
+/*
+ * Add an attr to a shortform fork. If there is no space,
+ * xfs_attr_shortform_addname() will convert to leaf format and return -ENOSPC.
+ * to use.
+ */
STATIC int
xfs_attr_try_sf_addname(
struct xfs_inode *dp,
@@ -210,7 +352,7 @@ xfs_attr_try_sf_addname(
/*
* Build initial attribute list (if required).
*/
- if (dp->i_afp->if_format == XFS_DINODE_FMT_EXTENTS)
+ if (dp->i_af.if_format == XFS_DINODE_FMT_EXTENTS)
xfs_attr_shortform_create(args);
error = xfs_attr_shortform_addname(args);
@@ -230,411 +372,477 @@ xfs_attr_try_sf_addname(
return error;
}
-/*
- * Check to see if the attr should be upgraded from non-existent or shortform to
- * single-leaf-block attribute list.
- */
-static inline bool
-xfs_attr_is_shortform(
- struct xfs_inode *ip)
+static int
+xfs_attr_sf_addname(
+ struct xfs_attr_intent *attr)
{
- return ip->i_afp->if_format == XFS_DINODE_FMT_LOCAL ||
- (ip->i_afp->if_format == XFS_DINODE_FMT_EXTENTS &&
- ip->i_afp->if_nextents == 0);
+ struct xfs_da_args *args = attr->xattri_da_args;
+ struct xfs_inode *dp = args->dp;
+ int error = 0;
+
+ error = xfs_attr_try_sf_addname(dp, args);
+ if (error != -ENOSPC) {
+ ASSERT(!error || error == -EEXIST);
+ attr->xattri_dela_state = XFS_DAS_DONE;
+ goto out;
+ }
+
+ /*
+ * It won't fit in the shortform, transform to a leaf block. GROT:
+ * another possible req'mt for a double-split btree op.
+ */
+ error = xfs_attr_shortform_to_leaf(args);
+ if (error)
+ return error;
+
+ attr->xattri_dela_state = XFS_DAS_LEAF_ADD;
+out:
+ trace_xfs_attr_sf_addname_return(attr->xattri_dela_state, args->dp);
+ return error;
}
/*
- * Checks to see if a delayed attribute transaction should be rolled. If so,
- * transaction is finished or rolled as needed.
+ * Handle the state change on completion of a multi-state attr operation.
+ *
+ * If the XFS_DA_OP_REPLACE flag is set, this means the operation was the first
+ * modification in a attr replace operation and we still have to do the second
+ * state, indicated by @replace_state.
+ *
+ * We consume the XFS_DA_OP_REPLACE flag so that when we are called again on
+ * completion of the second half of the attr replace operation we correctly
+ * signal that it is done.
*/
-STATIC int
-xfs_attr_trans_roll(
- struct xfs_delattr_context *dac)
+static enum xfs_delattr_state
+xfs_attr_complete_op(
+ struct xfs_attr_intent *attr,
+ enum xfs_delattr_state replace_state)
{
- struct xfs_da_args *args = dac->da_args;
- int error;
+ struct xfs_da_args *args = attr->xattri_da_args;
+ bool do_replace = args->op_flags & XFS_DA_OP_REPLACE;
+
+ args->op_flags &= ~XFS_DA_OP_REPLACE;
+ if (do_replace) {
+ args->attr_filter &= ~XFS_ATTR_INCOMPLETE;
+ return replace_state;
+ }
+ return XFS_DAS_DONE;
+}
+
+static int
+xfs_attr_leaf_addname(
+ struct xfs_attr_intent *attr)
+{
+ struct xfs_da_args *args = attr->xattri_da_args;
+ int error;
+
+ ASSERT(xfs_attr_is_leaf(args->dp));
+
+ /*
+ * Use the leaf buffer we may already hold locked as a result of
+ * a sf-to-leaf conversion.
+ */
+ error = xfs_attr_leaf_try_add(args);
+
+ if (error == -ENOSPC) {
+ error = xfs_attr3_leaf_to_node(args);
+ if (error)
+ return error;
- if (dac->flags & XFS_DAC_DEFER_FINISH) {
/*
- * The caller wants us to finish all the deferred ops so that we
- * avoid pinning the log tail with a large number of deferred
- * ops.
+ * We're not in leaf format anymore, so roll the transaction and
+ * retry the add to the newly allocated node block.
*/
- dac->flags &= ~XFS_DAC_DEFER_FINISH;
- error = xfs_defer_finish(&args->trans);
- } else
- error = xfs_trans_roll_inode(&args->trans, args->dp);
+ attr->xattri_dela_state = XFS_DAS_NODE_ADD;
+ goto out;
+ }
+ if (error)
+ return error;
+ /*
+ * We need to commit and roll if we need to allocate remote xattr blocks
+ * or perform more xattr manipulations. Otherwise there is nothing more
+ * to do and we can return success.
+ */
+ if (args->rmtblkno)
+ attr->xattri_dela_state = XFS_DAS_LEAF_SET_RMT;
+ else
+ attr->xattri_dela_state = xfs_attr_complete_op(attr,
+ XFS_DAS_LEAF_REPLACE);
+out:
+ trace_xfs_attr_leaf_addname_return(attr->xattri_dela_state, args->dp);
return error;
}
/*
- * Set the attribute specified in @args.
+ * Add an entry to a node format attr tree.
+ *
+ * Note that we might still have a leaf here - xfs_attr_is_leaf() cannot tell
+ * the difference between leaf + remote attr blocks and a node format tree,
+ * so we may still end up having to convert from leaf to node format here.
*/
-int
-xfs_attr_set_args(
- struct xfs_da_args *args)
+static int
+xfs_attr_node_addname(
+ struct xfs_attr_intent *attr)
{
- struct xfs_buf *leaf_bp = NULL;
- int error = 0;
- struct xfs_delattr_context dac = {
- .da_args = args,
- };
+ struct xfs_da_args *args = attr->xattri_da_args;
+ int error;
- do {
- error = xfs_attr_set_iter(&dac, &leaf_bp);
- if (error != -EAGAIN)
- break;
+ error = xfs_attr_node_addname_find_attr(attr);
+ if (error)
+ return error;
- error = xfs_attr_trans_roll(&dac);
- if (error) {
- if (leaf_bp)
- xfs_trans_brelse(args->trans, leaf_bp);
+ error = xfs_attr_node_try_addname(attr);
+ if (error == -ENOSPC) {
+ error = xfs_attr3_leaf_to_node(args);
+ if (error)
return error;
- }
- } while (true);
+ /*
+ * No state change, we really are in node form now
+ * but we need the transaction rolled to continue.
+ */
+ goto out;
+ }
+ if (error)
+ return error;
+ if (args->rmtblkno)
+ attr->xattri_dela_state = XFS_DAS_NODE_SET_RMT;
+ else
+ attr->xattri_dela_state = xfs_attr_complete_op(attr,
+ XFS_DAS_NODE_REPLACE);
+out:
+ trace_xfs_attr_node_addname_return(attr->xattri_dela_state, args->dp);
return error;
}
-STATIC int
-xfs_attr_sf_addname(
- struct xfs_delattr_context *dac,
- struct xfs_buf **leaf_bp)
+static int
+xfs_attr_rmtval_alloc(
+ struct xfs_attr_intent *attr)
{
- struct xfs_da_args *args = dac->da_args;
- struct xfs_inode *dp = args->dp;
+ struct xfs_da_args *args = attr->xattri_da_args;
int error = 0;
/*
- * Try to add the attr to the attribute list in the inode.
+ * If there was an out-of-line value, allocate the blocks we
+ * identified for its storage and copy the value. This is done
+ * after we create the attribute so that we don't overflow the
+ * maximum size of a transaction and/or hit a deadlock.
*/
- error = xfs_attr_try_sf_addname(dp, args);
+ if (attr->xattri_blkcnt > 0) {
+ error = xfs_attr_rmtval_set_blk(attr);
+ if (error)
+ return error;
+ /* Roll the transaction only if there is more to allocate. */
+ if (attr->xattri_blkcnt > 0)
+ goto out;
+ }
- /* Should only be 0, -EEXIST or -ENOSPC */
- if (error != -ENOSPC)
+ error = xfs_attr_rmtval_set_value(args);
+ if (error)
return error;
+ attr->xattri_dela_state = xfs_attr_complete_op(attr,
+ ++attr->xattri_dela_state);
/*
- * It won't fit in the shortform, transform to a leaf block. GROT:
- * another possible req'mt for a double-split btree op.
+ * If we are not doing a rename, we've finished the operation but still
+ * have to clear the incomplete flag protecting the new attr from
+ * exposing partially initialised state if we crash during creation.
*/
- error = xfs_attr_shortform_to_leaf(args, leaf_bp);
- if (error)
- return error;
+ if (attr->xattri_dela_state == XFS_DAS_DONE)
+ error = xfs_attr3_leaf_clearflag(args);
+out:
+ trace_xfs_attr_rmtval_alloc(attr->xattri_dela_state, args->dp);
+ return error;
+}
+
+/*
+ * Mark an attribute entry INCOMPLETE and save pointers to the relevant buffers
+ * for later deletion of the entry.
+ */
+static int
+xfs_attr_leaf_mark_incomplete(
+ struct xfs_da_args *args,
+ struct xfs_da_state *state)
+{
+ int error;
/*
- * Prevent the leaf buffer from being unlocked so that a concurrent AIL
- * push cannot grab the half-baked leaf buffer and run into problems
- * with the write verifier.
+ * Fill in disk block numbers in the state structure
+ * so that we can get the buffers back after we commit
+ * several transactions in the following calls.
*/
- xfs_trans_bhold(args->trans, *leaf_bp);
+ error = xfs_attr_fillstate(state);
+ if (error)
+ return error;
/*
- * We're still in XFS_DAS_UNINIT state here. We've converted
- * the attr fork to leaf format and will restart with the leaf
- * add.
+ * Mark the attribute as INCOMPLETE
*/
- trace_xfs_attr_sf_addname_return(XFS_DAS_UNINIT, args->dp);
- dac->flags |= XFS_DAC_DEFER_FINISH;
- return -EAGAIN;
+ return xfs_attr3_leaf_setflag(args);
+}
+
+/* Ensure the da state of an xattr deferred work item is ready to go. */
+static inline void
+xfs_attr_item_init_da_state(
+ struct xfs_attr_intent *attr)
+{
+ struct xfs_da_args *args = attr->xattri_da_args;
+
+ if (!attr->xattri_da_state)
+ attr->xattri_da_state = xfs_da_state_alloc(args);
+ else
+ xfs_da_state_reset(attr->xattri_da_state, args);
}
/*
- * Set the attribute specified in @args.
- * This routine is meant to function as a delayed operation, and may return
- * -EAGAIN when the transaction needs to be rolled. Calling functions will need
- * to handle this, and recall the function until a successful error code is
- * returned.
+ * Initial setup for xfs_attr_node_removename. Make sure the attr is there and
+ * the blocks are valid. Attr keys with remote blocks will be marked
+ * incomplete.
*/
-int
-xfs_attr_set_iter(
- struct xfs_delattr_context *dac,
- struct xfs_buf **leaf_bp)
+static
+int xfs_attr_node_removename_setup(
+ struct xfs_attr_intent *attr)
{
- struct xfs_da_args *args = dac->da_args;
- struct xfs_inode *dp = args->dp;
- struct xfs_buf *bp = NULL;
- int forkoff, error = 0;
-
- /* State machine switch */
- switch (dac->dela_state) {
- case XFS_DAS_UNINIT:
- /*
- * If the fork is shortform, attempt to add the attr. If there
- * is no space, this converts to leaf format and returns
- * -EAGAIN with the leaf buffer held across the roll. The caller
- * will deal with a transaction roll error, but otherwise
- * release the hold once we return with a clean transaction.
- */
- if (xfs_attr_is_shortform(dp))
- return xfs_attr_sf_addname(dac, leaf_bp);
- if (*leaf_bp != NULL) {
- xfs_trans_bhold_release(args->trans, *leaf_bp);
- *leaf_bp = NULL;
- }
+ struct xfs_da_args *args = attr->xattri_da_args;
+ struct xfs_da_state *state;
+ int error;
- if (xfs_attr_is_leaf(dp)) {
- error = xfs_attr_leaf_try_add(args, *leaf_bp);
- if (error == -ENOSPC) {
- error = xfs_attr3_leaf_to_node(args);
- if (error)
- return error;
-
- /*
- * Finish any deferred work items and roll the
- * transaction once more. The goal here is to
- * call node_addname with the inode and
- * transaction in the same state (inode locked
- * and joined, transaction clean) no matter how
- * we got to this step.
- *
- * At this point, we are still in
- * XFS_DAS_UNINIT, but when we come back, we'll
- * be a node, so we'll fall down into the node
- * handling code below
- */
- dac->flags |= XFS_DAC_DEFER_FINISH;
- trace_xfs_attr_set_iter_return(
- dac->dela_state, args->dp);
- return -EAGAIN;
- } else if (error) {
- return error;
- }
+ xfs_attr_item_init_da_state(attr);
+ error = xfs_attr_node_lookup(args, attr->xattri_da_state);
+ if (error != -EEXIST)
+ goto out;
+ error = 0;
- dac->dela_state = XFS_DAS_FOUND_LBLK;
- } else {
- error = xfs_attr_node_addname_find_attr(dac);
- if (error)
- return error;
+ state = attr->xattri_da_state;
+ ASSERT(state->path.blk[state->path.active - 1].bp != NULL);
+ ASSERT(state->path.blk[state->path.active - 1].magic ==
+ XFS_ATTR_LEAF_MAGIC);
- error = xfs_attr_node_addname(dac);
- if (error)
- return error;
+ error = xfs_attr_leaf_mark_incomplete(args, state);
+ if (error)
+ goto out;
+ if (args->rmtblkno > 0)
+ error = xfs_attr_rmtval_invalidate(args);
+out:
+ if (error) {
+ xfs_da_state_free(attr->xattri_da_state);
+ attr->xattri_da_state = NULL;
+ }
- dac->dela_state = XFS_DAS_FOUND_NBLK;
- }
- trace_xfs_attr_set_iter_return(dac->dela_state, args->dp);
- return -EAGAIN;
- case XFS_DAS_FOUND_LBLK:
- /*
- * If there was an out-of-line value, allocate the blocks we
- * identified for its storage and copy the value. This is done
- * after we create the attribute so that we don't overflow the
- * maximum size of a transaction and/or hit a deadlock.
- */
+ return error;
+}
- /* Open coded xfs_attr_rmtval_set without trans handling */
- if ((dac->flags & XFS_DAC_LEAF_ADDNAME_INIT) == 0) {
- dac->flags |= XFS_DAC_LEAF_ADDNAME_INIT;
- if (args->rmtblkno > 0) {
- error = xfs_attr_rmtval_find_space(dac);
- if (error)
- return error;
- }
- }
+/*
+ * Remove the original attr we have just replaced. This is dependent on the
+ * original lookup and insert placing the old attr in args->blkno/args->index
+ * and the new attr in args->blkno2/args->index2.
+ */
+static int
+xfs_attr_leaf_remove_attr(
+ struct xfs_attr_intent *attr)
+{
+ struct xfs_da_args *args = attr->xattri_da_args;
+ struct xfs_inode *dp = args->dp;
+ struct xfs_buf *bp = NULL;
+ int forkoff;
+ int error;
- /*
- * Repeat allocating remote blocks for the attr value until
- * blkcnt drops to zero.
- */
- if (dac->blkcnt > 0) {
- error = xfs_attr_rmtval_set_blk(dac);
- if (error)
- return error;
- trace_xfs_attr_set_iter_return(dac->dela_state,
- args->dp);
- return -EAGAIN;
- }
+ error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno,
+ &bp);
+ if (error)
+ return error;
- error = xfs_attr_rmtval_set_value(args);
- if (error)
- return error;
+ xfs_attr3_leaf_remove(bp, args);
- /*
- * If this is not a rename, clear the incomplete flag and we're
- * done.
- */
- if (!(args->op_flags & XFS_DA_OP_RENAME)) {
- if (args->rmtblkno > 0)
- error = xfs_attr3_leaf_clearflag(args);
- return error;
- }
+ forkoff = xfs_attr_shortform_allfit(bp, dp);
+ if (forkoff)
+ error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
+ /* bp is gone due to xfs_da_shrink_inode */
- /*
- * If this is an atomic rename operation, we must "flip" the
- * incomplete flags on the "new" and "old" attribute/value pairs
- * so that one disappears and one appears atomically. Then we
- * must remove the "old" attribute/value pair.
- *
- * In a separate transaction, set the incomplete flag on the
- * "old" attr and clear the incomplete flag on the "new" attr.
- */
- error = xfs_attr3_leaf_flipflags(args);
- if (error)
- return error;
- /*
- * Commit the flag value change and start the next trans in
- * series.
- */
- dac->dela_state = XFS_DAS_FLIP_LFLAG;
- trace_xfs_attr_set_iter_return(dac->dela_state, args->dp);
- return -EAGAIN;
- case XFS_DAS_FLIP_LFLAG:
- /*
- * Dismantle the "old" attribute/value pair by removing a
- * "remote" value (if it exists).
- */
- xfs_attr_restore_rmt_blk(args);
- error = xfs_attr_rmtval_invalidate(args);
- if (error)
- return error;
+ return error;
+}
- fallthrough;
- case XFS_DAS_RM_LBLK:
- /* Set state in case xfs_attr_rmtval_remove returns -EAGAIN */
- dac->dela_state = XFS_DAS_RM_LBLK;
- if (args->rmtblkno) {
- error = xfs_attr_rmtval_remove(dac);
- if (error == -EAGAIN)
- trace_xfs_attr_set_iter_return(
- dac->dela_state, args->dp);
- if (error)
- return error;
+/*
+ * Shrink an attribute from leaf to shortform. Used by the node format remove
+ * path when the node format collapses to a single block and so we have to check
+ * if it can be collapsed further.
+ */
+static int
+xfs_attr_leaf_shrink(
+ struct xfs_da_args *args)
+{
+ struct xfs_inode *dp = args->dp;
+ struct xfs_buf *bp;
+ int forkoff;
+ int error;
- dac->dela_state = XFS_DAS_RD_LEAF;
- trace_xfs_attr_set_iter_return(dac->dela_state, args->dp);
- return -EAGAIN;
- }
+ if (!xfs_attr_is_leaf(dp))
+ return 0;
- fallthrough;
- case XFS_DAS_RD_LEAF:
- /*
- * This is the last step for leaf format. Read the block with
- * the old attr, remove the old attr, check for shortform
- * conversion and return.
- */
- error = xfs_attr3_leaf_read(args->trans, args->dp, args->blkno,
- &bp);
- if (error)
- return error;
+ error = xfs_attr3_leaf_read(args->trans, args->dp, 0, &bp);
+ if (error)
+ return error;
- xfs_attr3_leaf_remove(bp, args);
+ forkoff = xfs_attr_shortform_allfit(bp, dp);
+ if (forkoff) {
+ error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
+ /* bp is gone due to xfs_da_shrink_inode */
+ } else {
+ xfs_trans_brelse(args->trans, bp);
+ }
- forkoff = xfs_attr_shortform_allfit(bp, dp);
- if (forkoff)
- error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
- /* bp is gone due to xfs_da_shrink_inode */
+ return error;
+}
- return error;
+/*
+ * Run the attribute operation specified in @attr.
+ *
+ * This routine is meant to function as a delayed operation and will set the
+ * state to XFS_DAS_DONE when the operation is complete. Calling functions will
+ * need to handle this, and recall the function until either an error or
+ * XFS_DAS_DONE is detected.
+ */
+int
+xfs_attr_set_iter(
+ struct xfs_attr_intent *attr)
+{
+ struct xfs_da_args *args = attr->xattri_da_args;
+ int error = 0;
- case XFS_DAS_FOUND_NBLK:
- /*
- * Find space for remote blocks and fall into the allocation
- * state.
- */
- if (args->rmtblkno > 0) {
- error = xfs_attr_rmtval_find_space(dac);
- if (error)
- return error;
+ /* State machine switch */
+next_state:
+ switch (attr->xattri_dela_state) {
+ case XFS_DAS_UNINIT:
+ ASSERT(0);
+ return -EFSCORRUPTED;
+ case XFS_DAS_SF_ADD:
+ return xfs_attr_sf_addname(attr);
+ case XFS_DAS_LEAF_ADD:
+ return xfs_attr_leaf_addname(attr);
+ case XFS_DAS_NODE_ADD:
+ return xfs_attr_node_addname(attr);
+
+ case XFS_DAS_SF_REMOVE:
+ error = xfs_attr_sf_removename(args);
+ attr->xattri_dela_state = xfs_attr_complete_op(attr,
+ xfs_attr_init_add_state(args));
+ break;
+ case XFS_DAS_LEAF_REMOVE:
+ error = xfs_attr_leaf_removename(args);
+ attr->xattri_dela_state = xfs_attr_complete_op(attr,
+ xfs_attr_init_add_state(args));
+ break;
+ case XFS_DAS_NODE_REMOVE:
+ error = xfs_attr_node_removename_setup(attr);
+ if (error == -ENOATTR &&
+ (args->op_flags & XFS_DA_OP_RECOVERY)) {
+ attr->xattri_dela_state = xfs_attr_complete_op(attr,
+ xfs_attr_init_add_state(args));
+ error = 0;
+ break;
}
+ if (error)
+ return error;
+ attr->xattri_dela_state = XFS_DAS_NODE_REMOVE_RMT;
+ if (args->rmtblkno == 0)
+ attr->xattri_dela_state++;
+ break;
+ case XFS_DAS_LEAF_SET_RMT:
+ case XFS_DAS_NODE_SET_RMT:
+ error = xfs_attr_rmtval_find_space(attr);
+ if (error)
+ return error;
+ attr->xattri_dela_state++;
fallthrough;
- case XFS_DAS_ALLOC_NODE:
- /*
- * If there was an out-of-line value, allocate the blocks we
- * identified for its storage and copy the value. This is done
- * after we create the attribute so that we don't overflow the
- * maximum size of a transaction and/or hit a deadlock.
- */
- dac->dela_state = XFS_DAS_ALLOC_NODE;
- if (args->rmtblkno > 0) {
- if (dac->blkcnt > 0) {
- error = xfs_attr_rmtval_set_blk(dac);
- if (error)
- return error;
- trace_xfs_attr_set_iter_return(
- dac->dela_state, args->dp);
- return -EAGAIN;
- }
-
- error = xfs_attr_rmtval_set_value(args);
- if (error)
- return error;
- }
- /*
- * If this was not a rename, clear the incomplete flag and we're
- * done.
- */
- if (!(args->op_flags & XFS_DA_OP_RENAME)) {
- if (args->rmtblkno > 0)
- error = xfs_attr3_leaf_clearflag(args);
- goto out;
- }
+ case XFS_DAS_LEAF_ALLOC_RMT:
+ case XFS_DAS_NODE_ALLOC_RMT:
+ error = xfs_attr_rmtval_alloc(attr);
+ if (error)
+ return error;
+ if (attr->xattri_dela_state == XFS_DAS_DONE)
+ break;
+ goto next_state;
+ case XFS_DAS_LEAF_REPLACE:
+ case XFS_DAS_NODE_REPLACE:
/*
- * If this is an atomic rename operation, we must "flip" the
- * incomplete flags on the "new" and "old" attribute/value pairs
- * so that one disappears and one appears atomically. Then we
- * must remove the "old" attribute/value pair.
- *
- * In a separate transaction, set the incomplete flag on the
- * "old" attr and clear the incomplete flag on the "new" attr.
+ * We must "flip" the incomplete flags on the "new" and "old"
+ * attribute/value pairs so that one disappears and one appears
+ * atomically.
*/
error = xfs_attr3_leaf_flipflags(args);
if (error)
- goto out;
+ return error;
/*
- * Commit the flag value change and start the next trans in
- * series
+ * We must commit the flag value change now to make it atomic
+ * and then we can start the next trans in series at REMOVE_OLD.
*/
- dac->dela_state = XFS_DAS_FLIP_NFLAG;
- trace_xfs_attr_set_iter_return(dac->dela_state, args->dp);
- return -EAGAIN;
+ attr->xattri_dela_state++;
+ break;
- case XFS_DAS_FLIP_NFLAG:
+ case XFS_DAS_LEAF_REMOVE_OLD:
+ case XFS_DAS_NODE_REMOVE_OLD:
/*
- * Dismantle the "old" attribute/value pair by removing a
- * "remote" value (if it exists).
+ * If we have a remote attr, start the process of removing it
+ * by invalidating any cached buffers.
+ *
+ * If we don't have a remote attr, we skip the remote block
+ * removal state altogether with a second state increment.
*/
xfs_attr_restore_rmt_blk(args);
-
- error = xfs_attr_rmtval_invalidate(args);
- if (error)
- return error;
-
- fallthrough;
- case XFS_DAS_RM_NBLK:
- /* Set state in case xfs_attr_rmtval_remove returns -EAGAIN */
- dac->dela_state = XFS_DAS_RM_NBLK;
if (args->rmtblkno) {
- error = xfs_attr_rmtval_remove(dac);
- if (error == -EAGAIN)
- trace_xfs_attr_set_iter_return(
- dac->dela_state, args->dp);
-
+ error = xfs_attr_rmtval_invalidate(args);
if (error)
return error;
+ } else {
+ attr->xattri_dela_state++;
+ }
- dac->dela_state = XFS_DAS_CLR_FLAG;
- trace_xfs_attr_set_iter_return(dac->dela_state, args->dp);
- return -EAGAIN;
+ attr->xattri_dela_state++;
+ goto next_state;
+
+ case XFS_DAS_LEAF_REMOVE_RMT:
+ case XFS_DAS_NODE_REMOVE_RMT:
+ error = xfs_attr_rmtval_remove(attr);
+ if (error == -EAGAIN) {
+ error = 0;
+ break;
}
+ if (error)
+ return error;
- fallthrough;
- case XFS_DAS_CLR_FLAG:
/*
- * The last state for node format. Look up the old attr and
- * remove it.
+ * We've finished removing the remote attr blocks, so commit the
+ * transaction and move on to removing the attr name from the
+ * leaf/node block. Removing the attr might require a full
+ * transaction reservation for btree block freeing, so we
+ * can't do that in the same transaction where we removed the
+ * remote attr blocks.
*/
- error = xfs_attr_node_addname_clear_incomplete(dac);
+ attr->xattri_dela_state++;
+ break;
+
+ case XFS_DAS_LEAF_REMOVE_ATTR:
+ error = xfs_attr_leaf_remove_attr(attr);
+ attr->xattri_dela_state = xfs_attr_complete_op(attr,
+ xfs_attr_init_add_state(args));
+ break;
+
+ case XFS_DAS_NODE_REMOVE_ATTR:
+ error = xfs_attr_node_remove_attr(attr);
+ if (!error)
+ error = xfs_attr_leaf_shrink(args);
+ attr->xattri_dela_state = xfs_attr_complete_op(attr,
+ xfs_attr_init_add_state(args));
break;
default:
ASSERT(0);
break;
}
-out:
+
+ trace_xfs_attr_set_iter_return(attr->xattri_dela_state, args->dp);
return error;
}
@@ -648,12 +856,13 @@ xfs_attr_lookup(
{
struct xfs_inode *dp = args->dp;
struct xfs_buf *bp = NULL;
+ struct xfs_da_state *state;
int error;
if (!xfs_inode_hasattr(dp))
return -ENOATTR;
- if (dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL)
+ if (dp->i_af.if_format == XFS_DINODE_FMT_LOCAL)
return xfs_attr_sf_findname(args, NULL, NULL);
if (xfs_attr_is_leaf(dp)) {
@@ -665,33 +874,85 @@ xfs_attr_lookup(
return error;
}
- return xfs_attr_node_hasname(args, NULL);
+ state = xfs_da_state_alloc(args);
+ error = xfs_attr_node_lookup(args, state);
+ xfs_da_state_free(state);
+ return error;
}
-/*
- * Remove the attribute specified in @args.
- */
-int
-xfs_attr_remove_args(
+static int
+xfs_attr_intent_init(
+ struct xfs_da_args *args,
+ unsigned int op_flags, /* op flag (set or remove) */
+ struct xfs_attr_intent **attr) /* new xfs_attr_intent */
+{
+
+ struct xfs_attr_intent *new;
+
+ new = kmem_cache_zalloc(xfs_attr_intent_cache, GFP_NOFS | __GFP_NOFAIL);
+ new->xattri_op_flags = op_flags;
+ new->xattri_da_args = args;
+
+ *attr = new;
+ return 0;
+}
+
+/* Sets an attribute for an inode as a deferred operation */
+static int
+xfs_attr_defer_add(
struct xfs_da_args *args)
{
- int error;
- struct xfs_delattr_context dac = {
- .da_args = args,
- };
+ struct xfs_attr_intent *new;
+ int error = 0;
- do {
- error = xfs_attr_remove_iter(&dac);
- if (error != -EAGAIN)
- break;
+ error = xfs_attr_intent_init(args, XFS_ATTRI_OP_FLAGS_SET, &new);
+ if (error)
+ return error;
- error = xfs_attr_trans_roll(&dac);
- if (error)
- return error;
+ new->xattri_dela_state = xfs_attr_init_add_state(args);
+ xfs_defer_add(args->trans, XFS_DEFER_OPS_TYPE_ATTR, &new->xattri_list);
+ trace_xfs_attr_defer_add(new->xattri_dela_state, args->dp);
- } while (true);
+ return 0;
+}
- return error;
+/* Sets an attribute for an inode as a deferred operation */
+static int
+xfs_attr_defer_replace(
+ struct xfs_da_args *args)
+{
+ struct xfs_attr_intent *new;
+ int error = 0;
+
+ error = xfs_attr_intent_init(args, XFS_ATTRI_OP_FLAGS_REPLACE, &new);
+ if (error)
+ return error;
+
+ new->xattri_dela_state = xfs_attr_init_replace_state(args);
+ xfs_defer_add(args->trans, XFS_DEFER_OPS_TYPE_ATTR, &new->xattri_list);
+ trace_xfs_attr_defer_replace(new->xattri_dela_state, args->dp);
+
+ return 0;
+}
+
+/* Removes an attribute for an inode as a deferred operation */
+static int
+xfs_attr_defer_remove(
+ struct xfs_da_args *args)
+{
+
+ struct xfs_attr_intent *new;
+ int error;
+
+ error = xfs_attr_intent_init(args, XFS_ATTRI_OP_FLAGS_REMOVE, &new);
+ if (error)
+ return error;
+
+ new->xattri_dela_state = xfs_attr_init_remove_state(args);
+ xfs_defer_add(args->trans, XFS_DEFER_OPS_TYPE_ATTR, &new->xattri_list);
+ trace_xfs_attr_defer_remove(new->xattri_dela_state, args->dp);
+
+ return 0;
}
/*
@@ -724,21 +985,21 @@ xfs_attr_set(
/*
* We have no control over the attribute names that userspace passes us
* to remove, so we have to allow the name lookup prior to attribute
- * removal to fail as well.
+ * removal to fail as well. Preserve the logged flag, since we need
+ * to pass that through to the logging code.
*/
- args->op_flags = XFS_DA_OP_OKNOENT;
+ args->op_flags = XFS_DA_OP_OKNOENT |
+ (args->op_flags & XFS_DA_OP_LOGGED);
if (args->value) {
XFS_STATS_INC(mp, xs_attr_set);
-
- args->op_flags |= XFS_DA_OP_ADDNAME;
args->total = xfs_attr_calc_size(args, &local);
/*
* If the inode doesn't have an attribute fork, add one.
* (inode must not be locked when we call this routine)
*/
- if (XFS_IFORK_Q(dp) == 0) {
+ if (xfs_inode_has_attr_fork(dp) == 0) {
int sf_size = sizeof(struct xfs_attr_sf_hdr) +
xfs_attr_sf_entsize_byname(args->namelen,
args->valuelen);
@@ -748,20 +1009,10 @@ xfs_attr_set(
return error;
}
- tres.tr_logres = M_RES(mp)->tr_attrsetm.tr_logres +
- M_RES(mp)->tr_attrsetrt.tr_logres *
- args->total;
- tres.tr_logcount = XFS_ATTRSET_LOG_COUNT;
- tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
- total = args->total;
-
if (!local)
rmt_blks = xfs_attr3_rmt_blocks(mp, args->valuelen);
} else {
XFS_STATS_INC(mp, xs_attr_remove);
-
- tres = M_RES(mp)->tr_attrrm;
- total = XFS_ATTRRM_SPACE_RES(mp);
rmt_blks = xfs_attr3_rmt_blocks(mp, XFS_XATTR_SIZE_MAX);
}
@@ -769,6 +1020,7 @@ xfs_attr_set(
* Root fork attributes can use reserved data blocks for this
* operation if necessary
*/
+ xfs_init_attr_trans(args, &tres, &total);
error = xfs_trans_alloc_inode(dp, &tres, total, 0, rsvd, &args->trans);
if (error)
return error;
@@ -776,33 +1028,43 @@ xfs_attr_set(
if (args->value || xfs_inode_hasattr(dp)) {
error = xfs_iext_count_may_overflow(dp, XFS_ATTR_FORK,
XFS_IEXT_ATTR_MANIP_CNT(rmt_blks));
+ if (error == -EFBIG)
+ error = xfs_iext_count_upgrade(args->trans, dp,
+ XFS_IEXT_ATTR_MANIP_CNT(rmt_blks));
if (error)
goto out_trans_cancel;
}
error = xfs_attr_lookup(args);
- if (args->value) {
- if (error == -EEXIST && (args->attr_flags & XATTR_CREATE))
- goto out_trans_cancel;
- if (error == -ENOATTR && (args->attr_flags & XATTR_REPLACE))
- goto out_trans_cancel;
- if (error != -ENOATTR && error != -EEXIST)
+ switch (error) {
+ case -EEXIST:
+ /* if no value, we are performing a remove operation */
+ if (!args->value) {
+ error = xfs_attr_defer_remove(args);
+ break;
+ }
+ /* Pure create fails if the attr already exists */
+ if (args->attr_flags & XATTR_CREATE)
goto out_trans_cancel;
- error = xfs_attr_set_args(args);
- if (error)
- goto out_trans_cancel;
- /* shortform attribute has already been committed */
- if (!args->trans)
- goto out_unlock;
- } else {
- if (error != -EEXIST)
+ error = xfs_attr_defer_replace(args);
+ break;
+ case -ENOATTR:
+ /* Can't remove what isn't there. */
+ if (!args->value)
goto out_trans_cancel;
- error = xfs_attr_remove_args(args);
- if (error)
+ /* Pure replace fails if no existing attr to replace. */
+ if (args->attr_flags & XATTR_REPLACE)
goto out_trans_cancel;
+
+ error = xfs_attr_defer_add(args);
+ break;
+ default:
+ goto out_trans_cancel;
}
+ if (error)
+ goto out_trans_cancel;
/*
* If this is a synchronous mount, make sure that the
@@ -837,7 +1099,7 @@ static inline int xfs_attr_sf_totsize(struct xfs_inode *dp)
{
struct xfs_attr_shortform *sf;
- sf = (struct xfs_attr_shortform *)dp->i_afp->if_u1.if_data;
+ sf = (struct xfs_attr_shortform *)dp->i_af.if_u1.if_data;
return be16_to_cpu(sf->hdr.totsize);
}
@@ -845,28 +1107,41 @@ static inline int xfs_attr_sf_totsize(struct xfs_inode *dp)
* Add a name to the shortform attribute list structure
* This is the external routine.
*/
-STATIC int
-xfs_attr_shortform_addname(xfs_da_args_t *args)
+static int
+xfs_attr_shortform_addname(
+ struct xfs_da_args *args)
{
- int newsize, forkoff, retval;
+ int newsize, forkoff;
+ int error;
trace_xfs_attr_sf_addname(args);
- retval = xfs_attr_shortform_lookup(args);
- if (retval == -ENOATTR && (args->attr_flags & XATTR_REPLACE))
- return retval;
- if (retval == -EEXIST) {
- if (args->attr_flags & XATTR_CREATE)
- return retval;
- retval = xfs_attr_sf_removename(args);
- if (retval)
- return retval;
+ error = xfs_attr_shortform_lookup(args);
+ switch (error) {
+ case -ENOATTR:
+ if (args->op_flags & XFS_DA_OP_REPLACE)
+ return error;
+ break;
+ case -EEXIST:
+ if (!(args->op_flags & XFS_DA_OP_REPLACE))
+ return error;
+
+ error = xfs_attr_sf_removename(args);
+ if (error)
+ return error;
+
/*
- * Since we have removed the old attr, clear ATTR_REPLACE so
- * that the leaf format add routine won't trip over the attr
- * not being around.
+ * Since we have removed the old attr, clear XFS_DA_OP_REPLACE
+ * so that the new attr doesn't fit in shortform format, the
+ * leaf format add routine won't trip over the attr not being
+ * around.
*/
- args->attr_flags &= ~XATTR_REPLACE;
+ args->op_flags &= ~XFS_DA_OP_REPLACE;
+ break;
+ case 0:
+ break;
+ default:
+ return error;
}
if (args->namelen >= XFS_ATTR_SF_ENTSIZE_MAX ||
@@ -889,8 +1164,8 @@ xfs_attr_shortform_addname(xfs_da_args_t *args)
* External routines when attribute list is one block
*========================================================================*/
-/* Store info about a remote block */
-STATIC void
+/* Save the current remote block info and clear the current pointers. */
+static void
xfs_attr_save_rmt_blk(
struct xfs_da_args *args)
{
@@ -899,10 +1174,13 @@ xfs_attr_save_rmt_blk(
args->rmtblkno2 = args->rmtblkno;
args->rmtblkcnt2 = args->rmtblkcnt;
args->rmtvaluelen2 = args->rmtvaluelen;
+ args->rmtblkno = 0;
+ args->rmtblkcnt = 0;
+ args->rmtvaluelen = 0;
}
/* Set stored info about a remote block */
-STATIC void
+static void
xfs_attr_restore_rmt_blk(
struct xfs_da_args *args)
{
@@ -925,48 +1203,47 @@ xfs_attr_restore_rmt_blk(
*/
STATIC int
xfs_attr_leaf_try_add(
- struct xfs_da_args *args,
- struct xfs_buf *bp)
+ struct xfs_da_args *args)
{
- int retval;
+ struct xfs_buf *bp;
+ int error;
+
+ error = xfs_attr3_leaf_read(args->trans, args->dp, 0, &bp);
+ if (error)
+ return error;
/*
- * Look up the given attribute in the leaf block. Figure out if
- * the given flags produce an error or call for an atomic rename.
+ * Look up the xattr name to set the insertion point for the new xattr.
*/
- retval = xfs_attr_leaf_hasname(args, &bp);
- if (retval != -ENOATTR && retval != -EEXIST)
- return retval;
- if (retval == -ENOATTR && (args->attr_flags & XATTR_REPLACE))
- goto out_brelse;
- if (retval == -EEXIST) {
- if (args->attr_flags & XATTR_CREATE)
+ error = xfs_attr3_leaf_lookup_int(bp, args);
+ switch (error) {
+ case -ENOATTR:
+ if (args->op_flags & XFS_DA_OP_REPLACE)
+ goto out_brelse;
+ break;
+ case -EEXIST:
+ if (!(args->op_flags & XFS_DA_OP_REPLACE))
goto out_brelse;
trace_xfs_attr_leaf_replace(args);
-
- /* save the attribute state for later removal*/
- args->op_flags |= XFS_DA_OP_RENAME; /* an atomic rename */
- xfs_attr_save_rmt_blk(args);
-
/*
- * clear the remote attr state now that it is saved so that the
- * values reflect the state of the attribute we are about to
+ * Save the existing remote attr state so that the current
+ * values reflect the state of the new attribute we are about to
* add, not the attribute we just found and will remove later.
*/
- args->rmtblkno = 0;
- args->rmtblkcnt = 0;
- args->rmtvaluelen = 0;
+ xfs_attr_save_rmt_blk(args);
+ break;
+ case 0:
+ break;
+ default:
+ goto out_brelse;
}
- /*
- * Add the attribute to the leaf block
- */
return xfs_attr3_leaf_add(bp, args);
out_brelse:
xfs_trans_brelse(args->trans, bp);
- return retval;
+ return error;
}
/*
@@ -1012,9 +1289,10 @@ xfs_attr_leaf_removename(
dp = args->dp;
error = xfs_attr_leaf_hasname(args, &bp);
-
if (error == -ENOATTR) {
xfs_trans_brelse(args->trans, bp);
+ if (args->op_flags & XFS_DA_OP_RECOVERY)
+ return 0;
return error;
} else if (error != -EEXIST)
return error;
@@ -1062,32 +1340,20 @@ xfs_attr_leaf_get(xfs_da_args_t *args)
return error;
}
-/*
- * Return EEXIST if attr is found, or ENOATTR if not
- * statep: If not null is set to point at the found state. Caller will
- * be responsible for freeing the state in this case.
- */
+/* Return EEXIST if attr is found, or ENOATTR if not. */
STATIC int
-xfs_attr_node_hasname(
+xfs_attr_node_lookup(
struct xfs_da_args *args,
- struct xfs_da_state **statep)
+ struct xfs_da_state *state)
{
- struct xfs_da_state *state;
int retval, error;
- state = xfs_da_state_alloc(args);
- if (statep != NULL)
- *statep = state;
-
/*
* Search to see if name exists, and get back a pointer to it.
*/
error = xfs_da3_node_lookup_int(state, &retval);
if (error)
- retval = error;
-
- if (!statep)
- xfs_da_state_free(state);
+ return error;
return retval;
}
@@ -1098,46 +1364,48 @@ xfs_attr_node_hasname(
STATIC int
xfs_attr_node_addname_find_attr(
- struct xfs_delattr_context *dac)
+ struct xfs_attr_intent *attr)
{
- struct xfs_da_args *args = dac->da_args;
- int retval;
+ struct xfs_da_args *args = attr->xattri_da_args;
+ int error;
/*
* Search to see if name already exists, and get back a pointer
* to where it should go.
*/
- retval = xfs_attr_node_hasname(args, &dac->da_state);
- if (retval != -ENOATTR && retval != -EEXIST)
- goto error;
-
- if (retval == -ENOATTR && (args->attr_flags & XATTR_REPLACE))
- goto error;
- if (retval == -EEXIST) {
- if (args->attr_flags & XATTR_CREATE)
+ xfs_attr_item_init_da_state(attr);
+ error = xfs_attr_node_lookup(args, attr->xattri_da_state);
+ switch (error) {
+ case -ENOATTR:
+ if (args->op_flags & XFS_DA_OP_REPLACE)
+ goto error;
+ break;
+ case -EEXIST:
+ if (!(args->op_flags & XFS_DA_OP_REPLACE))
goto error;
- trace_xfs_attr_node_replace(args);
-
- /* save the attribute state for later removal*/
- args->op_flags |= XFS_DA_OP_RENAME; /* atomic rename op */
- xfs_attr_save_rmt_blk(args);
+ trace_xfs_attr_node_replace(args);
/*
- * clear the remote attr state now that it is saved so that the
- * values reflect the state of the attribute we are about to
+ * Save the existing remote attr state so that the current
+ * values reflect the state of the new attribute we are about to
* add, not the attribute we just found and will remove later.
*/
- args->rmtblkno = 0;
- args->rmtblkcnt = 0;
- args->rmtvaluelen = 0;
+ xfs_attr_save_rmt_blk(args);
+ break;
+ case 0:
+ break;
+ default:
+ goto error;
}
return 0;
error:
- if (dac->da_state)
- xfs_da_state_free(dac->da_state);
- return retval;
+ if (attr->xattri_da_state) {
+ xfs_da_state_free(attr->xattri_da_state);
+ attr->xattri_da_state = NULL;
+ }
+ return error;
}
/*
@@ -1146,25 +1414,16 @@ error:
* This will involve walking down the Btree, and may involve splitting
* leaf nodes and even splitting intermediate nodes up to and including
* the root node (a special case of an intermediate node).
- *
- * "Remote" attribute values confuse the issue and atomic rename operations
- * add a whole extra layer of confusion on top of that.
- *
- * This routine is meant to function as a delayed operation, and may return
- * -EAGAIN when the transaction needs to be rolled. Calling functions will need
- * to handle this, and recall the function until a successful error code is
- *returned.
*/
-STATIC int
-xfs_attr_node_addname(
- struct xfs_delattr_context *dac)
+static int
+xfs_attr_node_try_addname(
+ struct xfs_attr_intent *attr)
{
- struct xfs_da_args *args = dac->da_args;
- struct xfs_da_state *state = dac->da_state;
+ struct xfs_da_state *state = attr->xattri_da_state;
struct xfs_da_state_blk *blk;
int error;
- trace_xfs_attr_node_addname(args);
+ trace_xfs_attr_node_addname(state->args);
blk = &state->path.blk[state->path.active-1];
ASSERT(blk->magic == XFS_ATTR_LEAF_MAGIC);
@@ -1175,25 +1434,9 @@ xfs_attr_node_addname(
/*
* Its really a single leaf node, but it had
* out-of-line values so it looked like it *might*
- * have been a b-tree.
+ * have been a b-tree. Let the caller deal with this.
*/
- xfs_da_state_free(state);
- state = NULL;
- error = xfs_attr3_leaf_to_node(args);
- if (error)
- goto out;
-
- /*
- * Now that we have converted the leaf to a node, we can
- * roll the transaction, and try xfs_attr3_leaf_add
- * again on re-entry. No need to set dela_state to do
- * this. dela_state is still unset by this function at
- * this point.
- */
- dac->flags |= XFS_DAC_DEFER_FINISH;
- trace_xfs_attr_node_addname_return(
- dac->dela_state, args->dp);
- return -EAGAIN;
+ goto out;
}
/*
@@ -1205,7 +1448,6 @@ xfs_attr_node_addname(
error = xfs_da3_split(state);
if (error)
goto out;
- dac->flags |= XFS_DAC_DEFER_FINISH;
} else {
/*
* Addition succeeded, update Btree hashvals.
@@ -1214,148 +1456,12 @@ xfs_attr_node_addname(
}
out:
- if (state)
- xfs_da_state_free(state);
- return error;
-}
-
-
-STATIC int
-xfs_attr_node_addname_clear_incomplete(
- struct xfs_delattr_context *dac)
-{
- struct xfs_da_args *args = dac->da_args;
- struct xfs_da_state *state = NULL;
- int retval = 0;
- int error = 0;
-
- /*
- * Re-find the "old" attribute entry after any split ops. The INCOMPLETE
- * flag means that we will find the "old" attr, not the "new" one.
- */
- args->attr_filter |= XFS_ATTR_INCOMPLETE;
- state = xfs_da_state_alloc(args);
- state->inleaf = 0;
- error = xfs_da3_node_lookup_int(state, &retval);
- if (error)
- goto out;
-
- error = xfs_attr_node_removename(args, state);
-
- /*
- * Check to see if the tree needs to be collapsed.
- */
- if (retval && (state->path.active > 1)) {
- error = xfs_da3_join(state);
- if (error)
- goto out;
- }
- retval = error = 0;
-
-out:
- if (state)
- xfs_da_state_free(state);
- if (error)
- return error;
- return retval;
-}
-
-/*
- * Shrink an attribute from leaf to shortform
- */
-STATIC int
-xfs_attr_node_shrink(
- struct xfs_da_args *args,
- struct xfs_da_state *state)
-{
- struct xfs_inode *dp = args->dp;
- int error, forkoff;
- struct xfs_buf *bp;
-
- /*
- * Have to get rid of the copy of this dabuf in the state.
- */
- ASSERT(state->path.active == 1);
- ASSERT(state->path.blk[0].bp);
- state->path.blk[0].bp = NULL;
-
- error = xfs_attr3_leaf_read(args->trans, args->dp, 0, &bp);
- if (error)
- return error;
-
- forkoff = xfs_attr_shortform_allfit(bp, dp);
- if (forkoff) {
- error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
- /* bp is gone due to xfs_da_shrink_inode */
- } else
- xfs_trans_brelse(args->trans, bp);
-
- return error;
-}
-
-/*
- * Mark an attribute entry INCOMPLETE and save pointers to the relevant buffers
- * for later deletion of the entry.
- */
-STATIC int
-xfs_attr_leaf_mark_incomplete(
- struct xfs_da_args *args,
- struct xfs_da_state *state)
-{
- int error;
-
- /*
- * Fill in disk block numbers in the state structure
- * so that we can get the buffers back after we commit
- * several transactions in the following calls.
- */
- error = xfs_attr_fillstate(state);
- if (error)
- return error;
-
- /*
- * Mark the attribute as INCOMPLETE
- */
- return xfs_attr3_leaf_setflag(args);
-}
-
-/*
- * Initial setup for xfs_attr_node_removename. Make sure the attr is there and
- * the blocks are valid. Attr keys with remote blocks will be marked
- * incomplete.
- */
-STATIC
-int xfs_attr_node_removename_setup(
- struct xfs_delattr_context *dac)
-{
- struct xfs_da_args *args = dac->da_args;
- struct xfs_da_state **state = &dac->da_state;
- int error;
-
- error = xfs_attr_node_hasname(args, state);
- if (error != -EEXIST)
- goto out;
- error = 0;
-
- ASSERT((*state)->path.blk[(*state)->path.active - 1].bp != NULL);
- ASSERT((*state)->path.blk[(*state)->path.active - 1].magic ==
- XFS_ATTR_LEAF_MAGIC);
-
- if (args->rmtblkno > 0) {
- error = xfs_attr_leaf_mark_incomplete(args, *state);
- if (error)
- goto out;
-
- error = xfs_attr_rmtval_invalidate(args);
- }
-out:
- if (error)
- xfs_da_state_free(*state);
-
+ xfs_da_state_free(state);
+ attr->xattri_da_state = NULL;
return error;
}
-STATIC int
+static int
xfs_attr_node_removename(
struct xfs_da_args *args,
struct xfs_da_state *state)
@@ -1374,246 +1480,42 @@ xfs_attr_node_removename(
return retval;
}
-/*
- * Remove the attribute specified in @args.
- *
- * This will involve walking down the Btree, and may involve joining
- * leaf nodes and even joining intermediate nodes up to and including
- * the root node (a special case of an intermediate node).
- *
- * This routine is meant to function as either an in-line or delayed operation,
- * and may return -EAGAIN when the transaction needs to be rolled. Calling
- * functions will need to handle this, and call the function until a
- * successful error code is returned.
- */
-int
-xfs_attr_remove_iter(
- struct xfs_delattr_context *dac)
-{
- struct xfs_da_args *args = dac->da_args;
- struct xfs_da_state *state = dac->da_state;
- int retval, error = 0;
- struct xfs_inode *dp = args->dp;
-
- trace_xfs_attr_node_removename(args);
-
- switch (dac->dela_state) {
- case XFS_DAS_UNINIT:
- if (!xfs_inode_hasattr(dp))
- return -ENOATTR;
-
- /*
- * Shortform or leaf formats don't require transaction rolls and
- * thus state transitions. Call the right helper and return.
- */
- if (dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL)
- return xfs_attr_sf_removename(args);
-
- if (xfs_attr_is_leaf(dp))
- return xfs_attr_leaf_removename(args);
-
- /*
- * Node format may require transaction rolls. Set up the
- * state context and fall into the state machine.
- */
- if (!dac->da_state) {
- error = xfs_attr_node_removename_setup(dac);
- if (error)
- return error;
- state = dac->da_state;
- }
-
- fallthrough;
- case XFS_DAS_RMTBLK:
- dac->dela_state = XFS_DAS_RMTBLK;
-
- /*
- * If there is an out-of-line value, de-allocate the blocks.
- * This is done before we remove the attribute so that we don't
- * overflow the maximum size of a transaction and/or hit a
- * deadlock.
- */
- if (args->rmtblkno > 0) {
- /*
- * May return -EAGAIN. Roll and repeat until all remote
- * blocks are removed.
- */
- error = xfs_attr_rmtval_remove(dac);
- if (error == -EAGAIN) {
- trace_xfs_attr_remove_iter_return(
- dac->dela_state, args->dp);
- return error;
- } else if (error) {
- goto out;
- }
-
- /*
- * Refill the state structure with buffers (the prior
- * calls released our buffers) and close out this
- * transaction before proceeding.
- */
- ASSERT(args->rmtblkno == 0);
- error = xfs_attr_refillstate(state);
- if (error)
- goto out;
- dac->dela_state = XFS_DAS_RM_NAME;
- dac->flags |= XFS_DAC_DEFER_FINISH;
- trace_xfs_attr_remove_iter_return(dac->dela_state, args->dp);
- return -EAGAIN;
- }
-
- fallthrough;
- case XFS_DAS_RM_NAME:
- /*
- * If we came here fresh from a transaction roll, reattach all
- * the buffers to the current transaction.
- */
- if (dac->dela_state == XFS_DAS_RM_NAME) {
- error = xfs_attr_refillstate(state);
- if (error)
- goto out;
- }
-
- retval = xfs_attr_node_removename(args, state);
-
- /*
- * Check to see if the tree needs to be collapsed. If so, roll
- * the transacton and fall into the shrink state.
- */
- if (retval && (state->path.active > 1)) {
- error = xfs_da3_join(state);
- if (error)
- goto out;
-
- dac->flags |= XFS_DAC_DEFER_FINISH;
- dac->dela_state = XFS_DAS_RM_SHRINK;
- trace_xfs_attr_remove_iter_return(
- dac->dela_state, args->dp);
- return -EAGAIN;
- }
-
- fallthrough;
- case XFS_DAS_RM_SHRINK:
- /*
- * If the result is small enough, push it all into the inode.
- * This is our final state so it's safe to return a dirty
- * transaction.
- */
- if (xfs_attr_is_leaf(dp))
- error = xfs_attr_node_shrink(args, state);
- ASSERT(error != -EAGAIN);
- break;
- default:
- ASSERT(0);
- error = -EINVAL;
- goto out;
- }
-out:
- if (state)
- xfs_da_state_free(state);
- return error;
-}
-
-/*
- * Fill in the disk block numbers in the state structure for the buffers
- * that are attached to the state structure.
- * This is done so that we can quickly reattach ourselves to those buffers
- * after some set of transaction commits have released these buffers.
- */
-STATIC int
-xfs_attr_fillstate(xfs_da_state_t *state)
+static int
+xfs_attr_node_remove_attr(
+ struct xfs_attr_intent *attr)
{
- xfs_da_state_path_t *path;
- xfs_da_state_blk_t *blk;
- int level;
-
- trace_xfs_attr_fillstate(state->args);
-
- /*
- * Roll down the "path" in the state structure, storing the on-disk
- * block number for those buffers in the "path".
- */
- path = &state->path;
- ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
- for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
- if (blk->bp) {
- blk->disk_blkno = xfs_buf_daddr(blk->bp);
- blk->bp = NULL;
- } else {
- blk->disk_blkno = 0;
- }
- }
+ struct xfs_da_args *args = attr->xattri_da_args;
+ struct xfs_da_state *state = xfs_da_state_alloc(args);
+ int retval = 0;
+ int error = 0;
/*
- * Roll down the "altpath" in the state structure, storing the on-disk
- * block number for those buffers in the "altpath".
+ * The attr we are removing has already been marked incomplete, so
+ * we need to set the filter appropriately to re-find the "old"
+ * attribute entry after any split ops.
*/
- path = &state->altpath;
- ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
- for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
- if (blk->bp) {
- blk->disk_blkno = xfs_buf_daddr(blk->bp);
- blk->bp = NULL;
- } else {
- blk->disk_blkno = 0;
- }
- }
-
- return 0;
-}
-
-/*
- * Reattach the buffers to the state structure based on the disk block
- * numbers stored in the state structure.
- * This is done after some set of transaction commits have released those
- * buffers from our grip.
- */
-STATIC int
-xfs_attr_refillstate(xfs_da_state_t *state)
-{
- xfs_da_state_path_t *path;
- xfs_da_state_blk_t *blk;
- int level, error;
-
- trace_xfs_attr_refillstate(state->args);
+ args->attr_filter |= XFS_ATTR_INCOMPLETE;
+ error = xfs_da3_node_lookup_int(state, &retval);
+ if (error)
+ goto out;
- /*
- * Roll down the "path" in the state structure, storing the on-disk
- * block number for those buffers in the "path".
- */
- path = &state->path;
- ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
- for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
- if (blk->disk_blkno) {
- error = xfs_da3_node_read_mapped(state->args->trans,
- state->args->dp, blk->disk_blkno,
- &blk->bp, XFS_ATTR_FORK);
- if (error)
- return error;
- } else {
- blk->bp = NULL;
- }
- }
+ error = xfs_attr_node_removename(args, state);
/*
- * Roll down the "altpath" in the state structure, storing the on-disk
- * block number for those buffers in the "altpath".
+ * Check to see if the tree needs to be collapsed.
*/
- path = &state->altpath;
- ASSERT((path->active >= 0) && (path->active < XFS_DA_NODE_MAXDEPTH));
- for (blk = path->blk, level = 0; level < path->active; blk++, level++) {
- if (blk->disk_blkno) {
- error = xfs_da3_node_read_mapped(state->args->trans,
- state->args->dp, blk->disk_blkno,
- &blk->bp, XFS_ATTR_FORK);
- if (error)
- return error;
- } else {
- blk->bp = NULL;
- }
+ if (retval && (state->path.active > 1)) {
+ error = xfs_da3_join(state);
+ if (error)
+ goto out;
}
+ retval = error = 0;
- return 0;
+out:
+ xfs_da_state_free(state);
+ if (error)
+ return error;
+ return retval;
}
/*
@@ -1639,7 +1541,8 @@ xfs_attr_node_get(
/*
* Search to see if name exists, and get back a pointer to it.
*/
- error = xfs_attr_node_hasname(args, &state);
+ state = xfs_da_state_alloc(args);
+ error = xfs_attr_node_lookup(args, state);
if (error != -EEXIST)
goto out_release;
@@ -1653,13 +1556,12 @@ xfs_attr_node_get(
* If not in a transaction, we have to release all the buffers.
*/
out_release:
- for (i = 0; state != NULL && i < state->path.active; i++) {
+ for (i = 0; i < state->path.active; i++) {
xfs_trans_brelse(args->trans, state->path.blk[i].bp);
state->path.blk[i].bp = NULL;
}
- if (state)
- xfs_da_state_free(state);
+ xfs_da_state_free(state);
return error;
}
@@ -1679,3 +1581,20 @@ xfs_attr_namecheck(
/* There shouldn't be any nulls here */
return !memchr(name, 0, length);
}
+
+int __init
+xfs_attr_intent_init_cache(void)
+{
+ xfs_attr_intent_cache = kmem_cache_create("xfs_attr_intent",
+ sizeof(struct xfs_attr_intent),
+ 0, 0, NULL);
+
+ return xfs_attr_intent_cache != NULL ? 0 : -ENOMEM;
+}
+
+void
+xfs_attr_intent_destroy_cache(void)
+{
+ kmem_cache_destroy(xfs_attr_intent_cache);
+ xfs_attr_intent_cache = NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h
index 5e71f719bdd5..81be9b3e4004 100644
--- a/fs/xfs/libxfs/xfs_attr.h
+++ b/fs/xfs/libxfs/xfs_attr.h
@@ -425,7 +425,7 @@ struct xfs_attr_list_context {
*/
/*
- * Enum values for xfs_delattr_context.da_state
+ * Enum values for xfs_attr_intent.xattri_da_state
*
* These values are used by delayed attribute operations to keep track of where
* they were before they returned -EAGAIN. A return code of -EAGAIN signals the
@@ -434,46 +434,102 @@ struct xfs_attr_list_context {
* to where it was and resume executing where it left off.
*/
enum xfs_delattr_state {
- XFS_DAS_UNINIT = 0, /* No state has been set yet */
- XFS_DAS_RMTBLK, /* Removing remote blks */
- XFS_DAS_RM_NAME, /* Remove attr name */
- XFS_DAS_RM_SHRINK, /* We are shrinking the tree */
- XFS_DAS_FOUND_LBLK, /* We found leaf blk for attr */
- XFS_DAS_FOUND_NBLK, /* We found node blk for attr */
- XFS_DAS_FLIP_LFLAG, /* Flipped leaf INCOMPLETE attr flag */
- XFS_DAS_RM_LBLK, /* A rename is removing leaf blocks */
- XFS_DAS_RD_LEAF, /* Read in the new leaf */
- XFS_DAS_ALLOC_NODE, /* We are allocating node blocks */
- XFS_DAS_FLIP_NFLAG, /* Flipped node INCOMPLETE attr flag */
- XFS_DAS_RM_NBLK, /* A rename is removing node blocks */
- XFS_DAS_CLR_FLAG, /* Clear incomplete flag */
+ XFS_DAS_UNINIT = 0, /* No state has been set yet */
+
+ /*
+ * Initial sequence states. The replace setup code relies on the
+ * ADD and REMOVE states for a specific format to be sequential so
+ * that we can transform the initial operation to be performed
+ * according to the xfs_has_larp() state easily.
+ */
+ XFS_DAS_SF_ADD, /* Initial sf add state */
+ XFS_DAS_SF_REMOVE, /* Initial sf replace/remove state */
+
+ XFS_DAS_LEAF_ADD, /* Initial leaf add state */
+ XFS_DAS_LEAF_REMOVE, /* Initial leaf replace/remove state */
+
+ XFS_DAS_NODE_ADD, /* Initial node add state */
+ XFS_DAS_NODE_REMOVE, /* Initial node replace/remove state */
+
+ /* Leaf state set/replace/remove sequence */
+ XFS_DAS_LEAF_SET_RMT, /* set a remote xattr from a leaf */
+ XFS_DAS_LEAF_ALLOC_RMT, /* We are allocating remote blocks */
+ XFS_DAS_LEAF_REPLACE, /* Perform replace ops on a leaf */
+ XFS_DAS_LEAF_REMOVE_OLD, /* Start removing old attr from leaf */
+ XFS_DAS_LEAF_REMOVE_RMT, /* A rename is removing remote blocks */
+ XFS_DAS_LEAF_REMOVE_ATTR, /* Remove the old attr from a leaf */
+
+ /* Node state sequence, must match leaf state above */
+ XFS_DAS_NODE_SET_RMT, /* set a remote xattr from a node */
+ XFS_DAS_NODE_ALLOC_RMT, /* We are allocating remote blocks */
+ XFS_DAS_NODE_REPLACE, /* Perform replace ops on a node */
+ XFS_DAS_NODE_REMOVE_OLD, /* Start removing old attr from node */
+ XFS_DAS_NODE_REMOVE_RMT, /* A rename is removing remote blocks */
+ XFS_DAS_NODE_REMOVE_ATTR, /* Remove the old attr from a node */
+
+ XFS_DAS_DONE, /* finished operation */
};
-/*
- * Defines for xfs_delattr_context.flags
- */
-#define XFS_DAC_DEFER_FINISH 0x01 /* finish the transaction */
-#define XFS_DAC_LEAF_ADDNAME_INIT 0x02 /* xfs_attr_leaf_addname init*/
+#define XFS_DAS_STRINGS \
+ { XFS_DAS_UNINIT, "XFS_DAS_UNINIT" }, \
+ { XFS_DAS_SF_ADD, "XFS_DAS_SF_ADD" }, \
+ { XFS_DAS_SF_REMOVE, "XFS_DAS_SF_REMOVE" }, \
+ { XFS_DAS_LEAF_ADD, "XFS_DAS_LEAF_ADD" }, \
+ { XFS_DAS_LEAF_REMOVE, "XFS_DAS_LEAF_REMOVE" }, \
+ { XFS_DAS_NODE_ADD, "XFS_DAS_NODE_ADD" }, \
+ { XFS_DAS_NODE_REMOVE, "XFS_DAS_NODE_REMOVE" }, \
+ { XFS_DAS_LEAF_SET_RMT, "XFS_DAS_LEAF_SET_RMT" }, \
+ { XFS_DAS_LEAF_ALLOC_RMT, "XFS_DAS_LEAF_ALLOC_RMT" }, \
+ { XFS_DAS_LEAF_REPLACE, "XFS_DAS_LEAF_REPLACE" }, \
+ { XFS_DAS_LEAF_REMOVE_OLD, "XFS_DAS_LEAF_REMOVE_OLD" }, \
+ { XFS_DAS_LEAF_REMOVE_RMT, "XFS_DAS_LEAF_REMOVE_RMT" }, \
+ { XFS_DAS_LEAF_REMOVE_ATTR, "XFS_DAS_LEAF_REMOVE_ATTR" }, \
+ { XFS_DAS_NODE_SET_RMT, "XFS_DAS_NODE_SET_RMT" }, \
+ { XFS_DAS_NODE_ALLOC_RMT, "XFS_DAS_NODE_ALLOC_RMT" }, \
+ { XFS_DAS_NODE_REPLACE, "XFS_DAS_NODE_REPLACE" }, \
+ { XFS_DAS_NODE_REMOVE_OLD, "XFS_DAS_NODE_REMOVE_OLD" }, \
+ { XFS_DAS_NODE_REMOVE_RMT, "XFS_DAS_NODE_REMOVE_RMT" }, \
+ { XFS_DAS_NODE_REMOVE_ATTR, "XFS_DAS_NODE_REMOVE_ATTR" }, \
+ { XFS_DAS_DONE, "XFS_DAS_DONE" }
+
+struct xfs_attri_log_nameval;
/*
* Context used for keeping track of delayed attribute operations
*/
-struct xfs_delattr_context {
- struct xfs_da_args *da_args;
-
- /* Used in xfs_attr_rmtval_set_blk to roll through allocating blocks */
- struct xfs_bmbt_irec map;
- xfs_dablk_t lblkno;
- int blkcnt;
+struct xfs_attr_intent {
+ /*
+ * used to log this item to an intent containing a list of attrs to
+ * commit later
+ */
+ struct list_head xattri_list;
/* Used in xfs_attr_node_removename to roll through removing blocks */
- struct xfs_da_state *da_state;
+ struct xfs_da_state *xattri_da_state;
+
+ struct xfs_da_args *xattri_da_args;
+
+ /*
+ * Shared buffer containing the attr name and value so that the logging
+ * code can share large memory buffers between log items.
+ */
+ struct xfs_attri_log_nameval *xattri_nameval;
/* Used to keep track of current state of delayed operation */
- unsigned int flags;
- enum xfs_delattr_state dela_state;
+ enum xfs_delattr_state xattri_dela_state;
+
+ /*
+ * Attr operation being performed - XFS_ATTRI_OP_FLAGS_*
+ */
+ unsigned int xattri_op_flags;
+
+ /* Used in xfs_attr_rmtval_set_blk to roll through allocating blocks */
+ xfs_dablk_t xattri_lblkno;
+ int xattri_blkcnt;
+ struct xfs_bmbt_irec xattri_map;
};
+
/*========================================================================
* Function prototypes for the kernel.
*========================================================================*/
@@ -489,11 +545,77 @@ bool xfs_attr_is_leaf(struct xfs_inode *ip);
int xfs_attr_get_ilocked(struct xfs_da_args *args);
int xfs_attr_get(struct xfs_da_args *args);
int xfs_attr_set(struct xfs_da_args *args);
-int xfs_attr_set_args(struct xfs_da_args *args);
-int xfs_attr_remove_args(struct xfs_da_args *args);
-int xfs_attr_remove_iter(struct xfs_delattr_context *dac);
+int xfs_attr_set_iter(struct xfs_attr_intent *attr);
+int xfs_attr_remove_iter(struct xfs_attr_intent *attr);
bool xfs_attr_namecheck(const void *name, size_t length);
-void xfs_delattr_context_init(struct xfs_delattr_context *dac,
- struct xfs_da_args *args);
+int xfs_attr_calc_size(struct xfs_da_args *args, int *local);
+void xfs_init_attr_trans(struct xfs_da_args *args, struct xfs_trans_res *tres,
+ unsigned int *total);
+
+/*
+ * Check to see if the attr should be upgraded from non-existent or shortform to
+ * single-leaf-block attribute list.
+ */
+static inline bool
+xfs_attr_is_shortform(
+ struct xfs_inode *ip)
+{
+ return ip->i_af.if_format == XFS_DINODE_FMT_LOCAL ||
+ (ip->i_af.if_format == XFS_DINODE_FMT_EXTENTS &&
+ ip->i_af.if_nextents == 0);
+}
+
+static inline enum xfs_delattr_state
+xfs_attr_init_add_state(struct xfs_da_args *args)
+{
+ /*
+ * When called from the completion of a attr remove to determine the
+ * next state, the attribute fork may be null. This can occur only occur
+ * on a pure remove, but we grab the next state before we check if a
+ * replace operation is being performed. If we are called from any other
+ * context, i_af is guaranteed to exist. Hence if the attr fork is
+ * null, we were called from a pure remove operation and so we are done.
+ */
+ if (!xfs_inode_has_attr_fork(args->dp))
+ return XFS_DAS_DONE;
+
+ args->op_flags |= XFS_DA_OP_ADDNAME;
+ if (xfs_attr_is_shortform(args->dp))
+ return XFS_DAS_SF_ADD;
+ if (xfs_attr_is_leaf(args->dp))
+ return XFS_DAS_LEAF_ADD;
+ return XFS_DAS_NODE_ADD;
+}
+
+static inline enum xfs_delattr_state
+xfs_attr_init_remove_state(struct xfs_da_args *args)
+{
+ args->op_flags |= XFS_DA_OP_REMOVE;
+ if (xfs_attr_is_shortform(args->dp))
+ return XFS_DAS_SF_REMOVE;
+ if (xfs_attr_is_leaf(args->dp))
+ return XFS_DAS_LEAF_REMOVE;
+ return XFS_DAS_NODE_REMOVE;
+}
+
+/*
+ * If we are logging the attributes, then we have to start with removal of the
+ * old attribute so that there is always consistent state that we can recover
+ * from if the system goes down part way through. We always log the new attr
+ * value, so even when we remove the attr first we still have the information in
+ * the log to finish the replace operation atomically.
+ */
+static inline enum xfs_delattr_state
+xfs_attr_init_replace_state(struct xfs_da_args *args)
+{
+ args->op_flags |= XFS_DA_OP_ADDNAME | XFS_DA_OP_REPLACE;
+ if (args->op_flags & XFS_DA_OP_LOGGED)
+ return xfs_attr_init_remove_state(args);
+ return xfs_attr_init_add_state(args);
+}
+
+extern struct kmem_cache *xfs_attr_intent_cache;
+int __init xfs_attr_intent_init_cache(void);
+void xfs_attr_intent_destroy_cache(void);
#endif /* __XFS_ATTR_H__ */
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 014daa8c542d..beee51ad75ce 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -28,6 +28,7 @@
#include "xfs_dir2.h"
#include "xfs_log.h"
#include "xfs_ag.h"
+#include "xfs_errortag.h"
/*
@@ -288,6 +289,23 @@ xfs_attr3_leaf_verify_entry(
return NULL;
}
+/*
+ * Validate an attribute leaf block.
+ *
+ * Empty leaf blocks can occur under the following circumstances:
+ *
+ * 1. setxattr adds a new extended attribute to a file;
+ * 2. The file has zero existing attributes;
+ * 3. The attribute is too large to fit in the attribute fork;
+ * 4. The attribute is small enough to fit in a leaf block;
+ * 5. A log flush occurs after committing the transaction that creates
+ * the (empty) leaf block; and
+ * 6. The filesystem goes down after the log flush but before the new
+ * attribute can be committed to the leaf block.
+ *
+ * Hence we need to ensure that we don't fail the validation purely
+ * because the leaf is empty.
+ */
static xfs_failaddr_t
xfs_attr3_leaf_verify(
struct xfs_buf *bp)
@@ -445,6 +463,14 @@ xfs_attr3_leaf_read(
* Namespace helper routines
*========================================================================*/
+/*
+ * If we are in log recovery, then we want the lookup to ignore the INCOMPLETE
+ * flag on disk - if there's an incomplete attr then recovery needs to tear it
+ * down. If there's no incomplete attr, then recovery needs to tear that attr
+ * down to replace it with the attr that has been logged. In this case, the
+ * INCOMPLETE flag will not be set in attr->attr_filter, but rather
+ * XFS_DA_OP_RECOVERY will be set in args->op_flags.
+ */
static bool
xfs_attr_match(
struct xfs_da_args *args,
@@ -452,14 +478,18 @@ xfs_attr_match(
unsigned char *name,
int flags)
{
+
if (args->namelen != namelen)
return false;
if (memcmp(args->name, name, namelen) != 0)
return false;
- /*
- * If we are looking for incomplete entries, show only those, else only
- * show complete entries.
- */
+
+ /* Recovery ignores the INCOMPLETE flag. */
+ if ((args->op_flags & XFS_DA_OP_RECOVERY) &&
+ args->attr_filter == (flags & XFS_ATTR_NSP_ONDISK_MASK))
+ return true;
+
+ /* All remaining matches need to be filtered by INCOMPLETE state. */
if (args->attr_filter !=
(flags & (XFS_ATTR_NSP_ONDISK_MASK | XFS_ATTR_INCOMPLETE)))
return false;
@@ -560,7 +590,7 @@ xfs_attr_shortform_bytesfit(
* to real extents, or the delalloc conversion will take care of the
* literal area rebalancing.
*/
- if (bytes <= XFS_IFORK_ASIZE(dp))
+ if (bytes <= xfs_inode_attr_fork_size(dp))
return dp->i_forkoff;
/*
@@ -652,7 +682,7 @@ xfs_attr_shortform_create(
struct xfs_da_args *args)
{
struct xfs_inode *dp = args->dp;
- struct xfs_ifork *ifp = dp->i_afp;
+ struct xfs_ifork *ifp = &dp->i_af;
struct xfs_attr_sf_hdr *hdr;
trace_xfs_attr_sf_create(args);
@@ -689,7 +719,7 @@ xfs_attr_sf_findname(
int end;
int i;
- sf = (struct xfs_attr_shortform *)args->dp->i_afp->if_u1.if_data;
+ sf = (struct xfs_attr_shortform *)args->dp->i_af.if_u1.if_data;
sfe = &sf->list[0];
end = sf->hdr.count;
for (i = 0; i < end; sfe = xfs_attr_sf_nextentry(sfe),
@@ -734,7 +764,7 @@ xfs_attr_shortform_add(
mp = dp->i_mount;
dp->i_forkoff = forkoff;
- ifp = dp->i_afp;
+ ifp = &dp->i_af;
ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
if (xfs_attr_sf_findname(args, &sfe, NULL) == -EEXIST)
@@ -767,11 +797,9 @@ xfs_attr_fork_remove(
struct xfs_inode *ip,
struct xfs_trans *tp)
{
- ASSERT(ip->i_afp->if_nextents == 0);
+ ASSERT(ip->i_af.if_nextents == 0);
- xfs_idestroy_fork(ip->i_afp);
- kmem_cache_free(xfs_ifork_cache, ip->i_afp);
- ip->i_afp = NULL;
+ xfs_ifork_zap_attr(ip);
ip->i_forkoff = 0;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
}
@@ -795,9 +823,17 @@ xfs_attr_sf_removename(
dp = args->dp;
mp = dp->i_mount;
- sf = (struct xfs_attr_shortform *)dp->i_afp->if_u1.if_data;
+ sf = (struct xfs_attr_shortform *)dp->i_af.if_u1.if_data;
error = xfs_attr_sf_findname(args, &sfe, &base);
+
+ /*
+ * If we are recovering an operation, finding nothing to
+ * remove is not an error - it just means there was nothing
+ * to clean up.
+ */
+ if (error == -ENOATTR && (args->op_flags & XFS_DA_OP_RECOVERY))
+ return 0;
if (error != -EEXIST)
return error;
size = xfs_attr_sf_entsize(sfe);
@@ -818,7 +854,7 @@ xfs_attr_sf_removename(
totsize -= size;
if (totsize == sizeof(xfs_attr_sf_hdr_t) && xfs_has_attr2(mp) &&
(dp->i_df.if_format != XFS_DINODE_FMT_BTREE) &&
- !(args->op_flags & XFS_DA_OP_ADDNAME)) {
+ !(args->op_flags & (XFS_DA_OP_ADDNAME | XFS_DA_OP_REPLACE))) {
xfs_attr_fork_remove(dp, args->trans);
} else {
xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
@@ -851,7 +887,7 @@ xfs_attr_shortform_lookup(xfs_da_args_t *args)
trace_xfs_attr_sf_lookup(args);
- ifp = args->dp->i_afp;
+ ifp = &args->dp->i_af;
ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
sfe = &sf->list[0];
@@ -879,8 +915,8 @@ xfs_attr_shortform_getvalue(
struct xfs_attr_sf_entry *sfe;
int i;
- ASSERT(args->dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL);
- sf = (struct xfs_attr_shortform *)args->dp->i_afp->if_u1.if_data;
+ ASSERT(args->dp->i_af.if_format == XFS_DINODE_FMT_LOCAL);
+ sf = (struct xfs_attr_shortform *)args->dp->i_af.if_u1.if_data;
sfe = &sf->list[0];
for (i = 0; i < sf->hdr.count;
sfe = xfs_attr_sf_nextentry(sfe), i++) {
@@ -892,14 +928,10 @@ xfs_attr_shortform_getvalue(
return -ENOATTR;
}
-/*
- * Convert from using the shortform to the leaf. On success, return the
- * buffer so that we can keep it locked until we're totally done with it.
- */
+/* Convert from using the shortform to the leaf format. */
int
xfs_attr_shortform_to_leaf(
- struct xfs_da_args *args,
- struct xfs_buf **leaf_bp)
+ struct xfs_da_args *args)
{
struct xfs_inode *dp;
struct xfs_attr_shortform *sf;
@@ -914,7 +946,7 @@ xfs_attr_shortform_to_leaf(
trace_xfs_attr_sf_to_leaf(args);
dp = args->dp;
- ifp = dp->i_afp;
+ ifp = &dp->i_af;
sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
size = be16_to_cpu(sf->hdr.totsize);
tmpbuffer = kmem_alloc(size, 0);
@@ -961,7 +993,6 @@ xfs_attr_shortform_to_leaf(
sfe = xfs_attr_sf_nextentry(sfe);
}
error = 0;
- *leaf_bp = bp;
out:
kmem_free(tmpbuffer);
return error;
@@ -1022,8 +1053,8 @@ xfs_attr_shortform_verify(
int i;
int64_t size;
- ASSERT(ip->i_afp->if_format == XFS_DINODE_FMT_LOCAL);
- ifp = XFS_IFORK_PTR(ip, XFS_ATTR_FORK);
+ ASSERT(ip->i_af.if_format == XFS_DINODE_FMT_LOCAL);
+ ifp = xfs_ifork_ptr(ip, XFS_ATTR_FORK);
sfp = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
size = ifp->if_bytes;
@@ -1127,9 +1158,17 @@ xfs_attr3_leaf_to_shortform(
goto out;
if (forkoff == -1) {
- ASSERT(xfs_has_attr2(dp->i_mount));
- ASSERT(dp->i_df.if_format != XFS_DINODE_FMT_BTREE);
- xfs_attr_fork_remove(dp, args->trans);
+ /*
+ * Don't remove the attr fork if this operation is the first
+ * part of a attr replace operations. We're going to add a new
+ * attr immediately, so we need to keep the attr fork around in
+ * this case.
+ */
+ if (!(args->op_flags & XFS_DA_OP_REPLACE)) {
+ ASSERT(xfs_has_attr2(dp->i_mount));
+ ASSERT(dp->i_df.if_format != XFS_DINODE_FMT_BTREE);
+ xfs_attr_fork_remove(dp, args->trans);
+ }
goto out;
}
@@ -1189,6 +1228,11 @@ xfs_attr3_leaf_to_node(
trace_xfs_attr_leaf_to_node(args);
+ if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_ATTR_LEAF_TO_NODE)) {
+ error = -EIO;
+ goto out;
+ }
+
error = xfs_da_grow_inode(args, &blkno);
if (error)
goto out;
@@ -1486,8 +1530,9 @@ xfs_attr3_leaf_add_work(
entry->flags = args->attr_filter;
if (tmp)
entry->flags |= XFS_ATTR_LOCAL;
- if (args->op_flags & XFS_DA_OP_RENAME) {
- entry->flags |= XFS_ATTR_INCOMPLETE;
+ if (args->op_flags & XFS_DA_OP_REPLACE) {
+ if (!(args->op_flags & XFS_DA_OP_LOGGED))
+ entry->flags |= XFS_ATTR_INCOMPLETE;
if ((args->blkno2 == args->blkno) &&
(args->index2 <= args->index)) {
args->index2++;
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h
index efa757f1e912..368f4d9fa1d5 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.h
+++ b/fs/xfs/libxfs/xfs_attr_leaf.h
@@ -49,8 +49,7 @@ void xfs_attr_shortform_create(struct xfs_da_args *args);
void xfs_attr_shortform_add(struct xfs_da_args *args, int forkoff);
int xfs_attr_shortform_lookup(struct xfs_da_args *args);
int xfs_attr_shortform_getvalue(struct xfs_da_args *args);
-int xfs_attr_shortform_to_leaf(struct xfs_da_args *args,
- struct xfs_buf **leaf_bp);
+int xfs_attr_shortform_to_leaf(struct xfs_da_args *args);
int xfs_attr_sf_removename(struct xfs_da_args *args);
int xfs_attr_sf_findname(struct xfs_da_args *args,
struct xfs_attr_sf_entry **sfep,
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 83b95be9ded8..d440393b40eb 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -543,6 +543,7 @@ xfs_attr_rmtval_stale(
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_buf *bp;
+ int error;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
@@ -550,14 +551,18 @@ xfs_attr_rmtval_stale(
XFS_IS_CORRUPT(mp, map->br_startblock == HOLESTARTBLOCK))
return -EFSCORRUPTED;
- bp = xfs_buf_incore(mp->m_ddev_targp,
+ error = xfs_buf_incore(mp->m_ddev_targp,
XFS_FSB_TO_DADDR(mp, map->br_startblock),
- XFS_FSB_TO_BB(mp, map->br_blockcount), incore_flags);
- if (bp) {
- xfs_buf_stale(bp);
- xfs_buf_relse(bp);
+ XFS_FSB_TO_BB(mp, map->br_blockcount),
+ incore_flags, &bp);
+ if (error) {
+ if (error == -ENOENT)
+ return 0;
+ return error;
}
+ xfs_buf_stale(bp);
+ xfs_buf_relse(bp);
return 0;
}
@@ -568,14 +573,14 @@ xfs_attr_rmtval_stale(
*/
int
xfs_attr_rmtval_find_space(
- struct xfs_delattr_context *dac)
+ struct xfs_attr_intent *attr)
{
- struct xfs_da_args *args = dac->da_args;
- struct xfs_bmbt_irec *map = &dac->map;
+ struct xfs_da_args *args = attr->xattri_da_args;
+ struct xfs_bmbt_irec *map = &attr->xattri_map;
int error;
- dac->lblkno = 0;
- dac->blkcnt = 0;
+ attr->xattri_lblkno = 0;
+ attr->xattri_blkcnt = 0;
args->rmtblkcnt = 0;
args->rmtblkno = 0;
memset(map, 0, sizeof(struct xfs_bmbt_irec));
@@ -584,8 +589,8 @@ xfs_attr_rmtval_find_space(
if (error)
return error;
- dac->blkcnt = args->rmtblkcnt;
- dac->lblkno = args->rmtblkno;
+ attr->xattri_blkcnt = args->rmtblkcnt;
+ attr->xattri_lblkno = args->rmtblkno;
return 0;
}
@@ -598,17 +603,18 @@ xfs_attr_rmtval_find_space(
*/
int
xfs_attr_rmtval_set_blk(
- struct xfs_delattr_context *dac)
+ struct xfs_attr_intent *attr)
{
- struct xfs_da_args *args = dac->da_args;
+ struct xfs_da_args *args = attr->xattri_da_args;
struct xfs_inode *dp = args->dp;
- struct xfs_bmbt_irec *map = &dac->map;
+ struct xfs_bmbt_irec *map = &attr->xattri_map;
int nmap;
int error;
nmap = 1;
- error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)dac->lblkno,
- dac->blkcnt, XFS_BMAPI_ATTRFORK, args->total,
+ error = xfs_bmapi_write(args->trans, dp,
+ (xfs_fileoff_t)attr->xattri_lblkno,
+ attr->xattri_blkcnt, XFS_BMAPI_ATTRFORK, args->total,
map, &nmap);
if (error)
return error;
@@ -618,8 +624,8 @@ xfs_attr_rmtval_set_blk(
(map->br_startblock != HOLESTARTBLOCK));
/* roll attribute extent map forwards */
- dac->lblkno += map->br_blockcount;
- dac->blkcnt -= map->br_blockcount;
+ attr->xattri_lblkno += map->br_blockcount;
+ attr->xattri_blkcnt -= map->br_blockcount;
return 0;
}
@@ -673,9 +679,9 @@ xfs_attr_rmtval_invalidate(
*/
int
xfs_attr_rmtval_remove(
- struct xfs_delattr_context *dac)
+ struct xfs_attr_intent *attr)
{
- struct xfs_da_args *args = dac->da_args;
+ struct xfs_da_args *args = attr->xattri_da_args;
int error, done;
/*
@@ -695,8 +701,8 @@ xfs_attr_rmtval_remove(
* the parent
*/
if (!done) {
- dac->flags |= XFS_DAC_DEFER_FINISH;
- trace_xfs_attr_rmtval_remove_return(dac->dela_state, args->dp);
+ trace_xfs_attr_rmtval_remove_return(attr->xattri_dela_state,
+ args->dp);
return -EAGAIN;
}
diff --git a/fs/xfs/libxfs/xfs_attr_remote.h b/fs/xfs/libxfs/xfs_attr_remote.h
index d72eff30ca18..d097ec6c4dc3 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.h
+++ b/fs/xfs/libxfs/xfs_attr_remote.h
@@ -12,9 +12,9 @@ int xfs_attr_rmtval_get(struct xfs_da_args *args);
int xfs_attr_rmtval_stale(struct xfs_inode *ip, struct xfs_bmbt_irec *map,
xfs_buf_flags_t incore_flags);
int xfs_attr_rmtval_invalidate(struct xfs_da_args *args);
-int xfs_attr_rmtval_remove(struct xfs_delattr_context *dac);
+int xfs_attr_rmtval_remove(struct xfs_attr_intent *attr);
int xfs_attr_rmt_find_hole(struct xfs_da_args *args);
int xfs_attr_rmtval_set_value(struct xfs_da_args *args);
-int xfs_attr_rmtval_set_blk(struct xfs_delattr_context *dac);
-int xfs_attr_rmtval_find_space(struct xfs_delattr_context *dac);
+int xfs_attr_rmtval_set_blk(struct xfs_attr_intent *attr);
+int xfs_attr_rmtval_find_space(struct xfs_attr_intent *attr);
#endif /* __XFS_ATTR_REMOTE_H__ */
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 4dccd4d90622..49d0d4ea63fc 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -52,19 +52,17 @@ xfs_bmap_compute_maxlevels(
xfs_mount_t *mp, /* file system mount structure */
int whichfork) /* data or attr fork */
{
+ uint64_t maxblocks; /* max blocks at this level */
+ xfs_extnum_t maxleafents; /* max leaf entries possible */
int level; /* btree level */
- uint maxblocks; /* max blocks at this level */
- uint maxleafents; /* max leaf entries possible */
int maxrootrecs; /* max records in root block */
int minleafrecs; /* min records in leaf block */
int minnoderecs; /* min records in node block */
int sz; /* root block size */
/*
- * The maximum number of extents in a file, hence the maximum number of
- * leaf entries, is controlled by the size of the on-disk extent count,
- * either a signed 32-bit number for the data fork, or a signed 16-bit
- * number for the attr fork.
+ * The maximum number of extents in a fork, hence the maximum number of
+ * leaf entries, is controlled by the size of the on-disk extent count.
*
* Note that we can no longer assume that if we are in ATTR1 that the
* fork offset of all the inodes will be
@@ -74,22 +72,22 @@ xfs_bmap_compute_maxlevels(
* ATTR2 we have to assume the worst case scenario of a minimum size
* available.
*/
- if (whichfork == XFS_DATA_FORK) {
- maxleafents = MAXEXTNUM;
+ maxleafents = xfs_iext_max_nextents(xfs_has_large_extent_counts(mp),
+ whichfork);
+ if (whichfork == XFS_DATA_FORK)
sz = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
- } else {
- maxleafents = MAXAEXTNUM;
+ else
sz = XFS_BMDR_SPACE_CALC(MINABTPTRS);
- }
+
maxrootrecs = xfs_bmdr_maxrecs(sz, 0);
minleafrecs = mp->m_bmap_dmnr[0];
minnoderecs = mp->m_bmap_dmnr[1];
- maxblocks = (maxleafents + minleafrecs - 1) / minleafrecs;
+ maxblocks = howmany_64(maxleafents, minleafrecs);
for (level = 1; maxblocks > 1; level++) {
if (maxblocks <= maxrootrecs)
maxblocks = 1;
else
- maxblocks = (maxblocks + minnoderecs - 1) / minnoderecs;
+ maxblocks = howmany_64(maxblocks, minnoderecs);
}
mp->m_bm_maxlevels[whichfork] = level;
ASSERT(mp->m_bm_maxlevels[whichfork] <= xfs_bmbt_maxlevels_ondisk());
@@ -130,7 +128,7 @@ xfs_bmbt_lookup_first(
*/
static inline bool xfs_bmap_needs_btree(struct xfs_inode *ip, int whichfork)
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
return whichfork != XFS_COW_FORK &&
ifp->if_format == XFS_DINODE_FMT_EXTENTS &&
@@ -142,7 +140,7 @@ static inline bool xfs_bmap_needs_btree(struct xfs_inode *ip, int whichfork)
*/
static inline bool xfs_bmap_wants_extents(struct xfs_inode *ip, int whichfork)
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
return whichfork != XFS_COW_FORK &&
ifp->if_format == XFS_DINODE_FMT_BTREE &&
@@ -296,7 +294,7 @@ xfs_check_block(
else
thispa = XFS_BMBT_PTR_ADDR(mp, block, j, dmxr);
if (*thispa == *pp) {
- xfs_warn(mp, "%s: thispa(%d) == pp(%d) %Ld",
+ xfs_warn(mp, "%s: thispa(%d) == pp(%d) %lld",
__func__, j, i,
(unsigned long long)be64_to_cpu(*thispa));
xfs_err(mp, "%s: ptrs are equal in node\n",
@@ -321,7 +319,7 @@ xfs_bmap_check_leaf_extents(
int whichfork) /* data or attr fork */
{
struct xfs_mount *mp = ip->i_mount;
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_btree_block *block; /* current btree block */
xfs_fsblock_t bno; /* block # of "block" */
struct xfs_buf *bp; /* buffer for "block" */
@@ -468,7 +466,7 @@ error0:
if (bp_release)
xfs_trans_brelse(NULL, bp);
error_norelse:
- xfs_warn(mp, "%s: BAD after btree leaves for %d extents",
+ xfs_warn(mp, "%s: BAD after btree leaves for %llu extents",
__func__, i);
xfs_err(mp, "%s: CORRUPTED BTREE OR SOMETHING", __func__);
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
@@ -485,7 +483,7 @@ STATIC void
xfs_bmap_validate_ret(
xfs_fileoff_t bno,
xfs_filblks_t len,
- int flags,
+ uint32_t flags,
xfs_bmbt_irec_t *mval,
int nmap,
int ret_nmap)
@@ -540,7 +538,7 @@ xfs_bmap_btree_to_extents(
int *logflagsp, /* inode logging flags */
int whichfork) /* data or attr fork */
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_mount *mp = ip->i_mount;
struct xfs_btree_block *rblock = ifp->if_broot;
struct xfs_btree_block *cblock;/* child btree block */
@@ -618,7 +616,7 @@ xfs_bmap_extents_to_btree(
mp = ip->i_mount;
ASSERT(whichfork != XFS_COW_FORK);
- ifp = XFS_IFORK_PTR(ip, whichfork);
+ ifp = xfs_ifork_ptr(ip, whichfork);
ASSERT(ifp->if_format == XFS_DINODE_FMT_EXTENTS);
/*
@@ -747,7 +745,7 @@ xfs_bmap_local_to_extents_empty(
struct xfs_inode *ip,
int whichfork)
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
ASSERT(whichfork != XFS_COW_FORK);
ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
@@ -787,7 +785,7 @@ xfs_bmap_local_to_extents(
* So sending the data fork of a regular inode is invalid.
*/
ASSERT(!(S_ISREG(VFS_I(ip)->i_mode) && whichfork == XFS_DATA_FORK));
- ifp = XFS_IFORK_PTR(ip, whichfork);
+ ifp = xfs_ifork_ptr(ip, whichfork);
ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
if (!ifp->if_bytes) {
@@ -882,7 +880,7 @@ xfs_bmap_add_attrfork_btree(
mp = ip->i_mount;
- if (XFS_BMAP_BMDR_SPACE(block) <= XFS_IFORK_DSIZE(ip))
+ if (XFS_BMAP_BMDR_SPACE(block) <= xfs_inode_data_fork_size(ip))
*flags |= XFS_ILOG_DBROOT;
else {
cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
@@ -922,7 +920,7 @@ xfs_bmap_add_attrfork_extents(
int error; /* error return value */
if (ip->i_df.if_nextents * sizeof(struct xfs_bmbt_rec) <=
- XFS_IFORK_DSIZE(ip))
+ xfs_inode_data_fork_size(ip))
return 0;
cur = NULL;
error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0, flags,
@@ -953,7 +951,7 @@ xfs_bmap_add_attrfork_local(
{
struct xfs_da_args dargs; /* args for dir/attr code */
- if (ip->i_df.if_bytes <= XFS_IFORK_DSIZE(ip))
+ if (ip->i_df.if_bytes <= xfs_inode_data_fork_size(ip))
return 0;
if (S_ISDIR(VFS_I(ip)->i_mode)) {
@@ -1025,7 +1023,7 @@ xfs_bmap_add_attrfork(
int logflags; /* logging flags */
int error; /* error return value */
- ASSERT(XFS_IFORK_Q(ip) == 0);
+ ASSERT(xfs_inode_has_attr_fork(ip) == 0);
mp = ip->i_mount;
ASSERT(!XFS_NOT_DQATTACHED(mp, ip));
@@ -1036,16 +1034,15 @@ xfs_bmap_add_attrfork(
rsvd, &tp);
if (error)
return error;
- if (XFS_IFORK_Q(ip))
+ if (xfs_inode_has_attr_fork(ip))
goto trans_cancel;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
error = xfs_bmap_set_attrforkoff(ip, size, &version);
if (error)
goto trans_cancel;
- ASSERT(ip->i_afp == NULL);
- ip->i_afp = xfs_ifork_alloc(XFS_DINODE_FMT_EXTENTS, 0);
+ xfs_ifork_init_attr(ip, XFS_DINODE_FMT_EXTENTS, 0);
logflags = 0;
switch (ip->i_df.if_format) {
case XFS_DINODE_FMT_LOCAL:
@@ -1118,7 +1115,7 @@ xfs_iread_bmbt_block(
xfs_extnum_t num_recs;
xfs_extnum_t j;
int whichfork = cur->bc_ino.whichfork;
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
block = xfs_btree_get_block(cur, level, &bp);
@@ -1166,7 +1163,7 @@ xfs_iread_extents(
int whichfork)
{
struct xfs_iread_state ir;
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_mount *mp = ip->i_mount;
struct xfs_btree_cur *cur;
int error;
@@ -1210,7 +1207,7 @@ xfs_bmap_first_unused(
xfs_fileoff_t *first_unused, /* unused block */
int whichfork) /* data or attr fork */
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_bmbt_irec got;
struct xfs_iext_cursor icur;
xfs_fileoff_t lastaddr = 0;
@@ -1257,7 +1254,7 @@ xfs_bmap_last_before(
xfs_fileoff_t *last_block, /* last block */
int whichfork) /* data or attr fork */
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_bmbt_irec got;
struct xfs_iext_cursor icur;
int error;
@@ -1291,7 +1288,7 @@ xfs_bmap_last_extent(
struct xfs_bmbt_irec *rec,
int *is_empty)
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_iext_cursor icur;
int error;
@@ -1357,7 +1354,7 @@ xfs_bmap_last_offset(
xfs_fileoff_t *last_block,
int whichfork)
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_bmbt_irec rec;
int is_empty;
int error;
@@ -1391,7 +1388,7 @@ xfs_bmap_add_extent_delay_real(
int whichfork)
{
struct xfs_mount *mp = bma->ip->i_mount;
- struct xfs_ifork *ifp = XFS_IFORK_PTR(bma->ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(bma->ip, whichfork);
struct xfs_bmbt_irec *new = &bma->got;
int error; /* error return value */
int i; /* temp state */
@@ -1399,7 +1396,7 @@ xfs_bmap_add_extent_delay_real(
xfs_bmbt_irec_t r[3]; /* neighbor extent entries */
/* left is 0, right is 1, prev is 2 */
int rval=0; /* return value (logging flags) */
- int state = xfs_bmap_fork_to_state(whichfork);
+ uint32_t state = xfs_bmap_fork_to_state(whichfork);
xfs_filblks_t da_new; /* new count del alloc blocks used */
xfs_filblks_t da_old; /* old count del alloc blocks used */
xfs_filblks_t temp=0; /* value for da_new calculations */
@@ -1452,7 +1449,7 @@ xfs_bmap_add_extent_delay_real(
LEFT.br_startoff + LEFT.br_blockcount == new->br_startoff &&
LEFT.br_startblock + LEFT.br_blockcount == new->br_startblock &&
LEFT.br_state == new->br_state &&
- LEFT.br_blockcount + new->br_blockcount <= MAXEXTLEN)
+ LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
state |= BMAP_LEFT_CONTIG;
/*
@@ -1470,13 +1467,13 @@ xfs_bmap_add_extent_delay_real(
new_endoff == RIGHT.br_startoff &&
new->br_startblock + new->br_blockcount == RIGHT.br_startblock &&
new->br_state == RIGHT.br_state &&
- new->br_blockcount + RIGHT.br_blockcount <= MAXEXTLEN &&
+ new->br_blockcount + RIGHT.br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
((state & (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
BMAP_RIGHT_FILLING)) !=
(BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
BMAP_RIGHT_FILLING) ||
LEFT.br_blockcount + new->br_blockcount + RIGHT.br_blockcount
- <= MAXEXTLEN))
+ <= XFS_MAX_BMBT_EXTLEN))
state |= BMAP_RIGHT_CONTIG;
error = 0;
@@ -1950,14 +1947,14 @@ xfs_bmap_add_extent_unwritten_real(
xfs_bmbt_irec_t r[3]; /* neighbor extent entries */
/* left is 0, right is 1, prev is 2 */
int rval=0; /* return value (logging flags) */
- int state = xfs_bmap_fork_to_state(whichfork);
+ uint32_t state = xfs_bmap_fork_to_state(whichfork);
struct xfs_mount *mp = ip->i_mount;
struct xfs_bmbt_irec old;
*logflagsp = 0;
cur = *curp;
- ifp = XFS_IFORK_PTR(ip, whichfork);
+ ifp = xfs_ifork_ptr(ip, whichfork);
ASSERT(!isnullstartblock(new->br_startblock));
@@ -2000,7 +1997,7 @@ xfs_bmap_add_extent_unwritten_real(
LEFT.br_startoff + LEFT.br_blockcount == new->br_startoff &&
LEFT.br_startblock + LEFT.br_blockcount == new->br_startblock &&
LEFT.br_state == new->br_state &&
- LEFT.br_blockcount + new->br_blockcount <= MAXEXTLEN)
+ LEFT.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
state |= BMAP_LEFT_CONTIG;
/*
@@ -2018,13 +2015,13 @@ xfs_bmap_add_extent_unwritten_real(
new_endoff == RIGHT.br_startoff &&
new->br_startblock + new->br_blockcount == RIGHT.br_startblock &&
new->br_state == RIGHT.br_state &&
- new->br_blockcount + RIGHT.br_blockcount <= MAXEXTLEN &&
+ new->br_blockcount + RIGHT.br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
((state & (BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
BMAP_RIGHT_FILLING)) !=
(BMAP_LEFT_CONTIG | BMAP_LEFT_FILLING |
BMAP_RIGHT_FILLING) ||
LEFT.br_blockcount + new->br_blockcount + RIGHT.br_blockcount
- <= MAXEXTLEN))
+ <= XFS_MAX_BMBT_EXTLEN))
state |= BMAP_RIGHT_CONTIG;
/*
@@ -2479,10 +2476,10 @@ xfs_bmap_add_extent_hole_delay(
xfs_filblks_t newlen=0; /* new indirect size */
xfs_filblks_t oldlen=0; /* old indirect size */
xfs_bmbt_irec_t right; /* right neighbor extent entry */
- int state = xfs_bmap_fork_to_state(whichfork);
+ uint32_t state = xfs_bmap_fork_to_state(whichfork);
xfs_filblks_t temp; /* temp for indirect calculations */
- ifp = XFS_IFORK_PTR(ip, whichfork);
+ ifp = xfs_ifork_ptr(ip, whichfork);
ASSERT(isnullstartblock(new->br_startblock));
/*
@@ -2510,15 +2507,15 @@ xfs_bmap_add_extent_hole_delay(
*/
if ((state & BMAP_LEFT_VALID) && (state & BMAP_LEFT_DELAY) &&
left.br_startoff + left.br_blockcount == new->br_startoff &&
- left.br_blockcount + new->br_blockcount <= MAXEXTLEN)
+ left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
state |= BMAP_LEFT_CONTIG;
if ((state & BMAP_RIGHT_VALID) && (state & BMAP_RIGHT_DELAY) &&
new->br_startoff + new->br_blockcount == right.br_startoff &&
- new->br_blockcount + right.br_blockcount <= MAXEXTLEN &&
+ new->br_blockcount + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
(!(state & BMAP_LEFT_CONTIG) ||
(left.br_blockcount + new->br_blockcount +
- right.br_blockcount <= MAXEXTLEN)))
+ right.br_blockcount <= XFS_MAX_BMBT_EXTLEN)))
state |= BMAP_RIGHT_CONTIG;
/*
@@ -2616,9 +2613,9 @@ xfs_bmap_add_extent_hole_real(
struct xfs_btree_cur **curp,
struct xfs_bmbt_irec *new,
int *logflagsp,
- int flags)
+ uint32_t flags)
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_mount *mp = ip->i_mount;
struct xfs_btree_cur *cur = *curp;
int error; /* error return value */
@@ -2626,7 +2623,7 @@ xfs_bmap_add_extent_hole_real(
xfs_bmbt_irec_t left; /* left neighbor extent entry */
xfs_bmbt_irec_t right; /* right neighbor extent entry */
int rval=0; /* return value (logging flags) */
- int state = xfs_bmap_fork_to_state(whichfork);
+ uint32_t state = xfs_bmap_fork_to_state(whichfork);
struct xfs_bmbt_irec old;
ASSERT(!isnullstartblock(new->br_startblock));
@@ -2661,17 +2658,17 @@ xfs_bmap_add_extent_hole_real(
left.br_startoff + left.br_blockcount == new->br_startoff &&
left.br_startblock + left.br_blockcount == new->br_startblock &&
left.br_state == new->br_state &&
- left.br_blockcount + new->br_blockcount <= MAXEXTLEN)
+ left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
state |= BMAP_LEFT_CONTIG;
if ((state & BMAP_RIGHT_VALID) && !(state & BMAP_RIGHT_DELAY) &&
new->br_startoff + new->br_blockcount == right.br_startoff &&
new->br_startblock + new->br_blockcount == right.br_startblock &&
new->br_state == right.br_state &&
- new->br_blockcount + right.br_blockcount <= MAXEXTLEN &&
+ new->br_blockcount + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
(!(state & BMAP_LEFT_CONTIG) ||
left.br_blockcount + new->br_blockcount +
- right.br_blockcount <= MAXEXTLEN))
+ right.br_blockcount <= XFS_MAX_BMBT_EXTLEN))
state |= BMAP_RIGHT_CONTIG;
error = 0;
@@ -2906,15 +2903,15 @@ xfs_bmap_extsize_align(
/*
* For large extent hint sizes, the aligned extent might be larger than
- * MAXEXTLEN. In that case, reduce the size by an extsz so that it pulls
- * the length back under MAXEXTLEN. The outer allocation loops handle
- * short allocation just fine, so it is safe to do this. We only want to
- * do it when we are forced to, though, because it means more allocation
- * operations are required.
+ * XFS_BMBT_MAX_EXTLEN. In that case, reduce the size by an extsz so
+ * that it pulls the length back under XFS_BMBT_MAX_EXTLEN. The outer
+ * allocation loops handle short allocation just fine, so it is safe to
+ * do this. We only want to do it when we are forced to, though, because
+ * it means more allocation operations are required.
*/
- while (align_alen > MAXEXTLEN)
+ while (align_alen > XFS_MAX_BMBT_EXTLEN)
align_alen -= extsz;
- ASSERT(align_alen <= MAXEXTLEN);
+ ASSERT(align_alen <= XFS_MAX_BMBT_EXTLEN);
/*
* If the previous block overlaps with this proposed allocation
@@ -3004,9 +3001,9 @@ xfs_bmap_extsize_align(
return -EINVAL;
} else {
ASSERT(orig_off >= align_off);
- /* see MAXEXTLEN handling above */
+ /* see XFS_BMBT_MAX_EXTLEN handling above */
ASSERT(orig_end <= align_off + align_alen ||
- align_alen + extsz > MAXEXTLEN);
+ align_alen + extsz > XFS_MAX_BMBT_EXTLEN);
}
#ifdef DEBUG
@@ -3187,7 +3184,8 @@ xfs_bmap_longest_free_extent(
pag = xfs_perag_get(mp, ag);
if (!pag->pagf_init) {
- error = xfs_alloc_pagf_init(mp, tp, ag, XFS_ALLOC_FLAG_TRYLOCK);
+ error = xfs_alloc_read_agf(pag, tp, XFS_ALLOC_FLAG_TRYLOCK,
+ NULL);
if (error) {
/* Couldn't lock the AGF, so skip this AG. */
if (error == -EAGAIN) {
@@ -3766,7 +3764,7 @@ xfs_bmapi_trim_map(
xfs_fileoff_t obno,
xfs_fileoff_t end,
int n,
- int flags)
+ uint32_t flags)
{
if ((flags & XFS_BMAPI_ENTIRE) ||
got->br_startoff + got->br_blockcount <= obno) {
@@ -3811,7 +3809,7 @@ xfs_bmapi_update_map(
xfs_fileoff_t obno,
xfs_fileoff_t end,
int *n,
- int flags)
+ uint32_t flags)
{
xfs_bmbt_irec_t *mval = *map;
@@ -3864,11 +3862,11 @@ xfs_bmapi_read(
xfs_filblks_t len,
struct xfs_bmbt_irec *mval,
int *nmap,
- int flags)
+ uint32_t flags)
{
struct xfs_mount *mp = ip->i_mount;
int whichfork = xfs_bmapi_whichfork(flags);
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_bmbt_irec got;
xfs_fileoff_t obno;
xfs_fileoff_t end;
@@ -3961,7 +3959,7 @@ xfs_bmapi_reserve_delalloc(
int eof)
{
struct xfs_mount *mp = ip->i_mount;
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
xfs_extlen_t alen;
xfs_extlen_t indlen;
int error;
@@ -3971,7 +3969,7 @@ xfs_bmapi_reserve_delalloc(
* Cap the alloc length. Keep track of prealloc so we know whether to
* tag the inode before we return.
*/
- alen = XFS_FILBLKS_MIN(len + prealloc, MAXEXTLEN);
+ alen = XFS_FILBLKS_MIN(len + prealloc, XFS_MAX_BMBT_EXTLEN);
if (!eof)
alen = XFS_FILBLKS_MIN(alen, got->br_startoff - aoff);
if (prealloc && alen >= len)
@@ -4088,7 +4086,7 @@ xfs_bmapi_allocate(
{
struct xfs_mount *mp = bma->ip->i_mount;
int whichfork = xfs_bmapi_whichfork(bma->flags);
- struct xfs_ifork *ifp = XFS_IFORK_PTR(bma->ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(bma->ip, whichfork);
int tmp_logflags = 0;
int error;
@@ -4104,7 +4102,7 @@ xfs_bmapi_allocate(
if (!xfs_iext_peek_prev_extent(ifp, &bma->icur, &bma->prev))
bma->prev.br_startoff = NULLFILEOFF;
} else {
- bma->length = XFS_FILBLKS_MIN(bma->length, MAXEXTLEN);
+ bma->length = XFS_FILBLKS_MIN(bma->length, XFS_MAX_BMBT_EXTLEN);
if (!bma->eof)
bma->length = XFS_FILBLKS_MIN(bma->length,
bma->got.br_startoff - bma->offset);
@@ -4184,10 +4182,10 @@ xfs_bmapi_convert_unwritten(
struct xfs_bmalloca *bma,
struct xfs_bmbt_irec *mval,
xfs_filblks_t len,
- int flags)
+ uint32_t flags)
{
int whichfork = xfs_bmapi_whichfork(flags);
- struct xfs_ifork *ifp = XFS_IFORK_PTR(bma->ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(bma->ip, whichfork);
int tmp_logflags = 0;
int error;
@@ -4264,7 +4262,7 @@ xfs_bmapi_minleft(
struct xfs_inode *ip,
int fork)
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, fork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, fork);
if (tp && tp->t_firstblock != NULLFSBLOCK)
return 0;
@@ -4285,7 +4283,7 @@ xfs_bmapi_finish(
int whichfork,
int error)
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(bma->ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(bma->ip, whichfork);
if ((bma->logflags & xfs_ilog_fext(whichfork)) &&
ifp->if_format != XFS_DINODE_FMT_EXTENTS)
@@ -4312,7 +4310,7 @@ xfs_bmapi_write(
struct xfs_inode *ip, /* incore inode */
xfs_fileoff_t bno, /* starting file offs. mapped */
xfs_filblks_t len, /* length to map in file */
- int flags, /* XFS_BMAPI_... */
+ uint32_t flags, /* XFS_BMAPI_... */
xfs_extlen_t total, /* total blocks needed */
struct xfs_bmbt_irec *mval, /* output: map values */
int *nmap) /* i/o: mval size/count */
@@ -4324,7 +4322,7 @@ xfs_bmapi_write(
};
struct xfs_mount *mp = ip->i_mount;
int whichfork = xfs_bmapi_whichfork(flags);
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
xfs_fileoff_t end; /* end of mapped file region */
bool eof = false; /* after the end of extents */
int error; /* error return */
@@ -4424,8 +4422,8 @@ xfs_bmapi_write(
* xfs_extlen_t and therefore 32 bits. Hence we have to
* check for 32-bit overflows and handle them here.
*/
- if (len > (xfs_filblks_t)MAXEXTLEN)
- bma.length = MAXEXTLEN;
+ if (len > (xfs_filblks_t)XFS_MAX_BMBT_EXTLEN)
+ bma.length = XFS_MAX_BMBT_EXTLEN;
else
bma.length = len;
@@ -4505,7 +4503,7 @@ xfs_bmapi_convert_delalloc(
struct iomap *iomap,
unsigned int *seq)
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
struct xfs_bmalloca bma = { NULL };
@@ -4526,14 +4524,16 @@ xfs_bmapi_convert_delalloc(
return error;
xfs_ilock(ip, XFS_ILOCK_EXCL);
+ xfs_trans_ijoin(tp, ip, 0);
error = xfs_iext_count_may_overflow(ip, whichfork,
XFS_IEXT_ADD_NOSPLIT_CNT);
+ if (error == -EFBIG)
+ error = xfs_iext_count_upgrade(tp, ip,
+ XFS_IEXT_ADD_NOSPLIT_CNT);
if (error)
goto out_trans_cancel;
- xfs_trans_ijoin(tp, ip, 0);
-
if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &bma.icur, &bma.got) ||
bma.got.br_startoff > offset_fsb) {
/*
@@ -4551,7 +4551,7 @@ xfs_bmapi_convert_delalloc(
* the extent. Just return the real extent at this offset.
*/
if (!isnullstartblock(bma.got.br_startblock)) {
- xfs_bmbt_to_iomap(ip, iomap, &bma.got, flags);
+ xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags);
*seq = READ_ONCE(ifp->if_seq);
goto out_trans_cancel;
}
@@ -4560,7 +4560,8 @@ xfs_bmapi_convert_delalloc(
bma.ip = ip;
bma.wasdel = true;
bma.offset = bma.got.br_startoff;
- bma.length = max_t(xfs_filblks_t, bma.got.br_blockcount, MAXEXTLEN);
+ bma.length = max_t(xfs_filblks_t, bma.got.br_blockcount,
+ XFS_MAX_BMBT_EXTLEN);
bma.minleft = xfs_bmapi_minleft(tp, ip, whichfork);
/*
@@ -4598,7 +4599,7 @@ xfs_bmapi_convert_delalloc(
XFS_STATS_INC(mp, xs_xstrat_quick);
ASSERT(!isnullstartblock(bma.got.br_startblock));
- xfs_bmbt_to_iomap(ip, iomap, &bma.got, flags);
+ xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags);
*seq = READ_ONCE(ifp->if_seq);
if (whichfork == XFS_COW_FORK)
@@ -4629,7 +4630,7 @@ xfs_bmapi_remap(
xfs_fileoff_t bno,
xfs_filblks_t len,
xfs_fsblock_t startblock,
- int flags)
+ uint32_t flags)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_ifork *ifp;
@@ -4639,9 +4640,9 @@ xfs_bmapi_remap(
int whichfork = xfs_bmapi_whichfork(flags);
int logflags = 0, error;
- ifp = XFS_IFORK_PTR(ip, whichfork);
+ ifp = xfs_ifork_ptr(ip, whichfork);
ASSERT(len > 0);
- ASSERT(len <= (xfs_filblks_t)MAXEXTLEN);
+ ASSERT(len <= (xfs_filblks_t)XFS_MAX_BMBT_EXTLEN);
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK | XFS_BMAPI_PREALLOC |
XFS_BMAPI_NORMAP)));
@@ -4796,12 +4797,12 @@ xfs_bmap_del_extent_delay(
struct xfs_bmbt_irec *del)
{
struct xfs_mount *mp = ip->i_mount;
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_bmbt_irec new;
int64_t da_old, da_new, da_diff = 0;
xfs_fileoff_t del_endoff, got_endoff;
xfs_filblks_t got_indlen, new_indlen, stolen;
- int state = xfs_bmap_fork_to_state(whichfork);
+ uint32_t state = xfs_bmap_fork_to_state(whichfork);
int error = 0;
bool isrt;
@@ -4923,10 +4924,10 @@ xfs_bmap_del_extent_cow(
struct xfs_bmbt_irec *del)
{
struct xfs_mount *mp = ip->i_mount;
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_COW_FORK);
struct xfs_bmbt_irec new;
xfs_fileoff_t del_endoff, got_endoff;
- int state = BMAP_COWFORK;
+ uint32_t state = BMAP_COWFORK;
XFS_STATS_INC(mp, xs_del_exlist);
@@ -4999,7 +5000,7 @@ xfs_bmap_del_extent_real(
xfs_bmbt_irec_t *del, /* data to remove from extents */
int *logflagsp, /* inode logging flags */
int whichfork, /* data or attr fork */
- int bflags) /* bmapi flags */
+ uint32_t bflags) /* bmapi flags */
{
xfs_fsblock_t del_endblock=0; /* first block past del */
xfs_fileoff_t del_endoff; /* first offset past del */
@@ -5015,13 +5016,13 @@ xfs_bmap_del_extent_real(
xfs_bmbt_irec_t new; /* new record to be inserted */
/* REFERENCED */
uint qfield; /* quota field to update */
- int state = xfs_bmap_fork_to_state(whichfork);
+ uint32_t state = xfs_bmap_fork_to_state(whichfork);
struct xfs_bmbt_irec old;
mp = ip->i_mount;
XFS_STATS_INC(mp, xs_del_exlist);
- ifp = XFS_IFORK_PTR(ip, whichfork);
+ ifp = xfs_ifork_ptr(ip, whichfork);
ASSERT(del->br_blockcount > 0);
xfs_iext_get_extent(ifp, icur, &got);
ASSERT(got.br_startoff <= del->br_startoff);
@@ -5148,26 +5149,6 @@ xfs_bmap_del_extent_real(
* Deleting the middle of the extent.
*/
- /*
- * For directories, -ENOSPC is returned since a directory entry
- * remove operation must not fail due to low extent count
- * availability. -ENOSPC will be handled by higher layers of XFS
- * by letting the corresponding empty Data/Free blocks to linger
- * until a future remove operation. Dabtree blocks would be
- * swapped with the last block in the leaf space and then the
- * new last block will be unmapped.
- *
- * The above logic also applies to the source directory entry of
- * a rename operation.
- */
- error = xfs_iext_count_may_overflow(ip, whichfork, 1);
- if (error) {
- ASSERT(S_ISDIR(VFS_I(ip)->i_mode) &&
- whichfork == XFS_DATA_FORK);
- error = -ENOSPC;
- goto done;
- }
-
old = got;
got.br_blockcount = del->br_startoff - got.br_startoff;
@@ -5281,7 +5262,7 @@ __xfs_bunmapi(
struct xfs_inode *ip, /* incore inode */
xfs_fileoff_t start, /* first file offset deleted */
xfs_filblks_t *rlen, /* i/o: amount remaining */
- int flags, /* misc flags */
+ uint32_t flags, /* misc flags */
xfs_extnum_t nexts) /* number of extents max */
{
struct xfs_btree_cur *cur; /* bmap btree cursor */
@@ -5299,7 +5280,6 @@ __xfs_bunmapi(
int whichfork; /* data or attribute fork */
xfs_fsblock_t sum;
xfs_filblks_t len = *rlen; /* length to unmap in file */
- xfs_fileoff_t max_len;
xfs_fileoff_t end;
struct xfs_iext_cursor icur;
bool done = false;
@@ -5308,7 +5288,7 @@ __xfs_bunmapi(
whichfork = xfs_bmapi_whichfork(flags);
ASSERT(whichfork != XFS_COW_FORK);
- ifp = XFS_IFORK_PTR(ip, whichfork);
+ ifp = xfs_ifork_ptr(ip, whichfork);
if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(ifp)))
return -EFSCORRUPTED;
if (xfs_is_shutdown(mp))
@@ -5318,16 +5298,6 @@ __xfs_bunmapi(
ASSERT(len > 0);
ASSERT(nexts >= 0);
- /*
- * Guesstimate how many blocks we can unmap without running the risk of
- * blowing out the transaction with a mix of EFIs and reflink
- * adjustments.
- */
- if (tp && xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK)
- max_len = min(len, xfs_refcount_max_unmap(tp->t_log_res));
- else
- max_len = len;
-
error = xfs_iread_extents(tp, ip, whichfork);
if (error)
return error;
@@ -5366,7 +5336,7 @@ __xfs_bunmapi(
extno = 0;
while (end != (xfs_fileoff_t)-1 && end >= start &&
- (nexts == 0 || extno < nexts) && max_len > 0) {
+ (nexts == 0 || extno < nexts)) {
/*
* Is the found extent after a hole in which end lives?
* Just back up to the previous extent, if so.
@@ -5400,14 +5370,6 @@ __xfs_bunmapi(
if (del.br_startoff + del.br_blockcount > end + 1)
del.br_blockcount = end + 1 - del.br_startoff;
- /* How much can we safely unmap? */
- if (max_len < del.br_blockcount) {
- del.br_startoff += del.br_blockcount - max_len;
- if (!wasdel)
- del.br_startblock += del.br_blockcount - max_len;
- del.br_blockcount = max_len;
- }
-
if (!isrt)
goto delete;
@@ -5543,7 +5505,6 @@ delete:
if (error)
goto error0;
- max_len -= del.br_blockcount;
end = del.br_startoff - 1;
nodelete:
/*
@@ -5609,7 +5570,7 @@ xfs_bunmapi(
struct xfs_inode *ip,
xfs_fileoff_t bno,
xfs_filblks_t len,
- int flags,
+ uint32_t flags,
xfs_extnum_t nexts,
int *done)
{
@@ -5641,7 +5602,7 @@ xfs_bmse_can_merge(
if ((left->br_startoff + left->br_blockcount != startoff) ||
(left->br_startblock + left->br_blockcount != got->br_startblock) ||
(left->br_state != got->br_state) ||
- (left->br_blockcount + got->br_blockcount > MAXEXTLEN))
+ (left->br_blockcount + got->br_blockcount > XFS_MAX_BMBT_EXTLEN))
return false;
return true;
@@ -5668,7 +5629,7 @@ xfs_bmse_merge(
struct xfs_btree_cur *cur,
int *logflags) /* output */
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_bmbt_irec new;
xfs_filblks_t blockcount;
int error, i;
@@ -5789,7 +5750,7 @@ xfs_bmap_collapse_extents(
{
int whichfork = XFS_DATA_FORK;
struct xfs_mount *mp = ip->i_mount;
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_btree_cur *cur = NULL;
struct xfs_bmbt_irec got, prev;
struct xfs_iext_cursor icur;
@@ -5904,7 +5865,7 @@ xfs_bmap_insert_extents(
{
int whichfork = XFS_DATA_FORK;
struct xfs_mount *mp = ip->i_mount;
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_btree_cur *cur = NULL;
struct xfs_bmbt_irec got, next;
struct xfs_iext_cursor icur;
@@ -6004,7 +5965,7 @@ xfs_bmap_split_extent(
xfs_fileoff_t split_fsb)
{
int whichfork = XFS_DATA_FORK;
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_btree_cur *cur = NULL;
struct xfs_bmbt_irec got;
struct xfs_bmbt_irec new; /* split extent */
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 03d9aaf87413..16db95b11589 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -39,7 +39,7 @@ struct xfs_bmalloca {
bool aeof; /* allocated space at eof */
bool conv; /* overwriting unwritten extents */
int datatype;/* data type being allocated */
- int flags;
+ uint32_t flags;
};
#define XFS_BMAP_MAX_NMAP 4
@@ -47,17 +47,17 @@ struct xfs_bmalloca {
/*
* Flags for xfs_bmapi_*
*/
-#define XFS_BMAPI_ENTIRE 0x001 /* return entire extent, not trimmed */
-#define XFS_BMAPI_METADATA 0x002 /* mapping metadata not user data */
-#define XFS_BMAPI_ATTRFORK 0x004 /* use attribute fork not data */
-#define XFS_BMAPI_PREALLOC 0x008 /* preallocation op: unwritten space */
-#define XFS_BMAPI_CONTIG 0x020 /* must allocate only one extent */
+#define XFS_BMAPI_ENTIRE (1u << 0) /* return entire extent untrimmed */
+#define XFS_BMAPI_METADATA (1u << 1) /* mapping metadata not user data */
+#define XFS_BMAPI_ATTRFORK (1u << 2) /* use attribute fork not data */
+#define XFS_BMAPI_PREALLOC (1u << 3) /* preallocating unwritten space */
+#define XFS_BMAPI_CONTIG (1u << 4) /* must allocate only one extent */
/*
* unwritten extent conversion - this needs write cache flushing and no additional
* allocation alignments. When specified with XFS_BMAPI_PREALLOC it converts
* from written to unwritten, otherwise convert from unwritten to written.
*/
-#define XFS_BMAPI_CONVERT 0x040
+#define XFS_BMAPI_CONVERT (1u << 5)
/*
* allocate zeroed extents - this requires all newly allocated user data extents
@@ -65,7 +65,7 @@ struct xfs_bmalloca {
* Use in conjunction with XFS_BMAPI_CONVERT to convert unwritten extents found
* during the allocation range to zeroed written extents.
*/
-#define XFS_BMAPI_ZERO 0x080
+#define XFS_BMAPI_ZERO (1u << 6)
/*
* Map the inode offset to the block given in ap->firstblock. Primarily
@@ -75,16 +75,16 @@ struct xfs_bmalloca {
* For bunmapi, this flag unmaps the range without adjusting quota, reducing
* refcount, or freeing the blocks.
*/
-#define XFS_BMAPI_REMAP 0x100
+#define XFS_BMAPI_REMAP (1u << 7)
/* Map something in the CoW fork. */
-#define XFS_BMAPI_COWFORK 0x200
+#define XFS_BMAPI_COWFORK (1u << 8)
/* Skip online discard of freed extents */
-#define XFS_BMAPI_NODISCARD 0x1000
+#define XFS_BMAPI_NODISCARD (1u << 9)
/* Do not update the rmap btree. Used for reconstructing bmbt from rmapbt. */
-#define XFS_BMAPI_NORMAP 0x2000
+#define XFS_BMAPI_NORMAP (1u << 10)
#define XFS_BMAPI_FLAGS \
{ XFS_BMAPI_ENTIRE, "ENTIRE" }, \
@@ -106,7 +106,7 @@ static inline int xfs_bmapi_aflag(int w)
(w == XFS_COW_FORK ? XFS_BMAPI_COWFORK : 0));
}
-static inline int xfs_bmapi_whichfork(int bmapi_flags)
+static inline int xfs_bmapi_whichfork(uint32_t bmapi_flags)
{
if (bmapi_flags & XFS_BMAPI_COWFORK)
return XFS_COW_FORK;
@@ -124,16 +124,16 @@ static inline int xfs_bmapi_whichfork(int bmapi_flags)
/*
* Flags for xfs_bmap_add_extent*.
*/
-#define BMAP_LEFT_CONTIG (1 << 0)
-#define BMAP_RIGHT_CONTIG (1 << 1)
-#define BMAP_LEFT_FILLING (1 << 2)
-#define BMAP_RIGHT_FILLING (1 << 3)
-#define BMAP_LEFT_DELAY (1 << 4)
-#define BMAP_RIGHT_DELAY (1 << 5)
-#define BMAP_LEFT_VALID (1 << 6)
-#define BMAP_RIGHT_VALID (1 << 7)
-#define BMAP_ATTRFORK (1 << 8)
-#define BMAP_COWFORK (1 << 9)
+#define BMAP_LEFT_CONTIG (1u << 0)
+#define BMAP_RIGHT_CONTIG (1u << 1)
+#define BMAP_LEFT_FILLING (1u << 2)
+#define BMAP_RIGHT_FILLING (1u << 3)
+#define BMAP_LEFT_DELAY (1u << 4)
+#define BMAP_RIGHT_DELAY (1u << 5)
+#define BMAP_LEFT_VALID (1u << 6)
+#define BMAP_RIGHT_VALID (1u << 7)
+#define BMAP_ATTRFORK (1u << 8)
+#define BMAP_COWFORK (1u << 9)
#define XFS_BMAP_EXT_FLAGS \
{ BMAP_LEFT_CONTIG, "LC" }, \
@@ -183,15 +183,15 @@ int xfs_bmap_last_offset(struct xfs_inode *ip, xfs_fileoff_t *unused,
int whichfork);
int xfs_bmapi_read(struct xfs_inode *ip, xfs_fileoff_t bno,
xfs_filblks_t len, struct xfs_bmbt_irec *mval,
- int *nmap, int flags);
+ int *nmap, uint32_t flags);
int xfs_bmapi_write(struct xfs_trans *tp, struct xfs_inode *ip,
- xfs_fileoff_t bno, xfs_filblks_t len, int flags,
+ xfs_fileoff_t bno, xfs_filblks_t len, uint32_t flags,
xfs_extlen_t total, struct xfs_bmbt_irec *mval, int *nmap);
int __xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
- xfs_fileoff_t bno, xfs_filblks_t *rlen, int flags,
+ xfs_fileoff_t bno, xfs_filblks_t *rlen, uint32_t flags,
xfs_extnum_t nexts);
int xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
- xfs_fileoff_t bno, xfs_filblks_t len, int flags,
+ xfs_fileoff_t bno, xfs_filblks_t len, uint32_t flags,
xfs_extnum_t nexts, int *done);
int xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got,
@@ -243,7 +243,7 @@ void xfs_bmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip,
void xfs_bmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip,
struct xfs_bmbt_irec *imap);
-static inline int xfs_bmap_fork_to_state(int whichfork)
+static inline uint32_t xfs_bmap_fork_to_state(int whichfork)
{
switch (whichfork) {
case XFS_ATTR_FORK:
@@ -260,7 +260,7 @@ xfs_failaddr_t xfs_bmap_validate_extent(struct xfs_inode *ip, int whichfork,
int xfs_bmapi_remap(struct xfs_trans *tp, struct xfs_inode *ip,
xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock,
- int flags);
+ uint32_t flags);
extern struct kmem_cache *xfs_bmap_intent_cache;
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 453309fc85f2..cfa052d40105 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -304,7 +304,7 @@ xfs_bmbt_get_minrecs(
if (level == cur->bc_nlevels - 1) {
struct xfs_ifork *ifp;
- ifp = XFS_IFORK_PTR(cur->bc_ino.ip,
+ ifp = xfs_ifork_ptr(cur->bc_ino.ip,
cur->bc_ino.whichfork);
return xfs_bmbt_maxrecs(cur->bc_mp,
@@ -322,7 +322,7 @@ xfs_bmbt_get_maxrecs(
if (level == cur->bc_nlevels - 1) {
struct xfs_ifork *ifp;
- ifp = XFS_IFORK_PTR(cur->bc_ino.ip,
+ ifp = xfs_ifork_ptr(cur->bc_ino.ip,
cur->bc_ino.whichfork);
return xfs_bmbt_maxrecs(cur->bc_mp,
@@ -550,7 +550,7 @@ xfs_bmbt_init_cursor(
struct xfs_inode *ip, /* inode owning the btree */
int whichfork) /* data or attr fork */
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_btree_cur *cur;
ASSERT(whichfork != XFS_COW_FORK);
@@ -564,7 +564,7 @@ xfs_bmbt_init_cursor(
if (xfs_has_crc(mp))
cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
- cur->bc_ino.forksize = XFS_IFORK_SIZE(ip, whichfork);
+ cur->bc_ino.forksize = xfs_inode_fork_size(ip, whichfork);
cur->bc_ino.ip = ip;
cur->bc_ino.allocated = 0;
cur->bc_ino.flags = 0;
@@ -597,7 +597,11 @@ xfs_bmbt_maxrecs(
return xfs_bmbt_block_maxrecs(blocklen, leaf);
}
-/* Compute the max possible height for block mapping btrees. */
+/*
+ * Calculate the maximum possible height of the btree that the on-disk format
+ * supports. This is used for sizing structures large enough to support every
+ * possible configuration of a filesystem that might get mounted.
+ */
unsigned int
xfs_bmbt_maxlevels_ondisk(void)
{
@@ -611,7 +615,8 @@ xfs_bmbt_maxlevels_ondisk(void)
minrecs[1] = xfs_bmbt_block_maxrecs(blocklen, false) / 2;
/* One extra level for the inode root. */
- return xfs_btree_compute_maxlevels(minrecs, MAXEXTNUM) + 1;
+ return xfs_btree_compute_maxlevels(minrecs,
+ XFS_MAX_EXTCNT_DATA_FORK_LARGE) + 1;
}
/*
@@ -659,7 +664,7 @@ xfs_bmbt_change_owner(
ASSERT(tp || buffer_list);
ASSERT(!(tp && buffer_list));
- ASSERT(XFS_IFORK_PTR(ip, whichfork)->if_format == XFS_DINODE_FMT_BTREE);
+ 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;
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index f18a875f51c6..4c16c8c31fcb 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -52,6 +52,70 @@ xfs_btree_magic(
}
/*
+ * These sibling pointer checks are optimised for null sibling pointers. This
+ * happens a lot, and we don't need to byte swap at runtime if the sibling
+ * pointer is NULL.
+ *
+ * These are explicitly marked at inline because the cost of calling them as
+ * functions instead of inlining them is about 36 bytes extra code per call site
+ * on x86-64. Yes, gcc-11 fails to inline them, and explicit inlining of these
+ * two sibling check functions reduces the compiled code size by over 300
+ * bytes.
+ */
+static inline xfs_failaddr_t
+xfs_btree_check_lblock_siblings(
+ struct xfs_mount *mp,
+ struct xfs_btree_cur *cur,
+ int level,
+ xfs_fsblock_t fsb,
+ __be64 dsibling)
+{
+ xfs_fsblock_t sibling;
+
+ if (dsibling == cpu_to_be64(NULLFSBLOCK))
+ return NULL;
+
+ 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;
+ }
+
+ return NULL;
+}
+
+static inline xfs_failaddr_t
+xfs_btree_check_sblock_siblings(
+ struct xfs_perag *pag,
+ struct xfs_btree_cur *cur,
+ int level,
+ xfs_agblock_t agbno,
+ __be32 dsibling)
+{
+ xfs_agblock_t sibling;
+
+ if (dsibling == cpu_to_be32(NULLAGBLOCK))
+ return NULL;
+
+ 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;
+ }
+ return NULL;
+}
+
+/*
* Check a long btree block header. Return the address of the failing check,
* or NULL if everything is ok.
*/
@@ -65,6 +129,8 @@ __xfs_btree_check_lblock(
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 (!uuid_equal(&block->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid))
@@ -83,16 +149,16 @@ __xfs_btree_check_lblock(
if (be16_to_cpu(block->bb_numrecs) >
cur->bc_ops->get_maxrecs(cur, level))
return __this_address;
- if (block->bb_u.l.bb_leftsib != cpu_to_be64(NULLFSBLOCK) &&
- !xfs_btree_check_lptr(cur, be64_to_cpu(block->bb_u.l.bb_leftsib),
- level + 1))
- return __this_address;
- if (block->bb_u.l.bb_rightsib != cpu_to_be64(NULLFSBLOCK) &&
- !xfs_btree_check_lptr(cur, be64_to_cpu(block->bb_u.l.bb_rightsib),
- level + 1))
- return __this_address;
- return NULL;
+ if (bp)
+ fsb = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
+
+ fa = xfs_btree_check_lblock_siblings(mp, cur, level, fsb,
+ block->bb_u.l.bb_leftsib);
+ if (!fa)
+ fa = xfs_btree_check_lblock_siblings(mp, cur, level, fsb,
+ block->bb_u.l.bb_rightsib);
+ return fa;
}
/* Check a long btree block header. */
@@ -128,8 +194,11 @@ __xfs_btree_check_sblock(
struct xfs_buf *bp)
{
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;
if (crc) {
if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid))
@@ -146,16 +215,16 @@ __xfs_btree_check_sblock(
if (be16_to_cpu(block->bb_numrecs) >
cur->bc_ops->get_maxrecs(cur, level))
return __this_address;
- if (block->bb_u.s.bb_leftsib != cpu_to_be32(NULLAGBLOCK) &&
- !xfs_btree_check_sptr(cur, be32_to_cpu(block->bb_u.s.bb_leftsib),
- level + 1))
- return __this_address;
- if (block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK) &&
- !xfs_btree_check_sptr(cur, be32_to_cpu(block->bb_u.s.bb_rightsib),
- level + 1))
- return __this_address;
- return NULL;
+ if (bp)
+ agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp));
+
+ fa = xfs_btree_check_sblock_siblings(pag, cur, level, agbno,
+ block->bb_u.s.bb_leftsib);
+ if (!fa)
+ fa = xfs_btree_check_sblock_siblings(pag, cur, level, agbno,
+ block->bb_u.s.bb_rightsib);
+ return fa;
}
/* Check a short btree block header. */
@@ -216,7 +285,7 @@ xfs_btree_check_sptr(
{
if (level <= 0)
return false;
- return xfs_verify_agbno(cur->bc_mp, cur->bc_ag.pag->pag_agno, agbno);
+ return xfs_verify_agbno(cur->bc_ag.pag, agbno);
}
/*
@@ -373,8 +442,14 @@ xfs_btree_del_cursor(
break;
}
+ /*
+ * If we are doing a BMBT update, the number of unaccounted blocks
+ * allocated during this cursor life time should be zero. If it's not
+ * 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 ||
- xfs_is_shutdown(cur->bc_mp));
+ 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)
@@ -647,7 +722,7 @@ xfs_btree_ifork_ptr(
if (cur->bc_flags & XFS_BTREE_STAGING)
return cur->bc_ino.ifake->if_fork;
- return XFS_IFORK_PTR(cur->bc_ino.ip, cur->bc_ino.whichfork);
+ return xfs_ifork_ptr(cur->bc_ino.ip, cur->bc_ino.whichfork);
}
/*
@@ -751,20 +826,20 @@ xfs_btree_lastrec(
*/
void
xfs_btree_offsets(
- int64_t fields, /* bitmask of fields */
+ uint32_t fields, /* bitmask of fields */
const short *offsets, /* table of field offsets */
int nbits, /* number of bits to inspect */
int *first, /* output: first byte offset */
int *last) /* output: last byte offset */
{
int i; /* current bit number */
- int64_t imask; /* mask for current bit number */
+ uint32_t imask; /* mask for current bit number */
ASSERT(fields != 0);
/*
* Find the lowest bit, so the first byte offset.
*/
- for (i = 0, imask = 1LL; ; i++, imask <<= 1) {
+ for (i = 0, imask = 1u; ; i++, imask <<= 1) {
if (imask & fields) {
*first = offsets[i];
break;
@@ -773,7 +848,7 @@ xfs_btree_offsets(
/*
* Find the highest bit, so the last byte offset.
*/
- for (i = nbits - 1, imask = 1LL << i; ; i--, imask >>= 1) {
+ for (i = nbits - 1, imask = 1u << i; ; i--, imask >>= 1) {
if (imask & fields) {
*last = offsets[i + 1] - 1;
break;
@@ -1456,7 +1531,7 @@ void
xfs_btree_log_block(
struct xfs_btree_cur *cur, /* btree cursor */
struct xfs_buf *bp, /* buffer containing btree block */
- int fields) /* mask of fields: XFS_BB_... */
+ uint32_t fields) /* mask of fields: XFS_BB_... */
{
int first; /* first byte offset logged */
int last; /* last byte offset logged */
@@ -2818,7 +2893,7 @@ xfs_btree_split_worker(
* in any way.
*/
if (args->kswapd)
- new_pflags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
+ new_pflags |= PF_MEMALLOC | PF_KSWAPD;
current_set_flags_nested(&pflags, new_pflags);
xfs_trans_set_context(args->cur->bc_tp);
@@ -3194,7 +3269,7 @@ xfs_btree_insrec(
struct xfs_btree_block *block; /* btree block */
struct xfs_buf *bp; /* buffer for block */
union xfs_btree_ptr nptr; /* new block ptr */
- struct xfs_btree_cur *ncur; /* new btree cursor */
+ struct xfs_btree_cur *ncur = NULL; /* new btree cursor */
union xfs_btree_key nkey; /* new block key */
union xfs_btree_key *lkey;
int optr; /* old key/record index */
@@ -3274,7 +3349,7 @@ xfs_btree_insrec(
#ifdef DEBUG
error = xfs_btree_check_block(cur, block, level, bp);
if (error)
- return error;
+ goto error0;
#endif
/*
@@ -3294,7 +3369,7 @@ xfs_btree_insrec(
for (i = numrecs - ptr; i >= 0; i--) {
error = xfs_btree_debug_check_ptr(cur, pp, i, level);
if (error)
- return error;
+ goto error0;
}
xfs_btree_shift_keys(cur, kp, 1, numrecs - ptr + 1);
@@ -3379,6 +3454,8 @@ xfs_btree_insrec(
return 0;
error0:
+ if (ncur)
+ xfs_btree_del_cursor(ncur, error);
return error;
}
@@ -3479,7 +3556,7 @@ xfs_btree_kill_iroot(
{
int whichfork = cur->bc_ino.whichfork;
struct xfs_inode *ip = cur->bc_ino.ip;
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_btree_block *block;
struct xfs_btree_block *cblock;
union xfs_btree_key *kp;
@@ -4271,6 +4348,21 @@ xfs_btree_visit_block(
if (xfs_btree_ptr_is_null(cur, &rptr))
return -ENOENT;
+ /*
+ * We only visit blocks once in this walk, so we have to avoid the
+ * internal xfs_btree_lookup_get_block() optimisation where it will
+ * 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;
+ }
return xfs_btree_lookup_get_block(cur, level, &rptr, &block);
}
@@ -4445,20 +4537,21 @@ xfs_btree_lblock_verify(
{
struct xfs_mount *mp = bp->b_mount;
struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
+ xfs_fsblock_t fsb;
+ xfs_failaddr_t fa;
/* numrecs verification */
if (be16_to_cpu(block->bb_numrecs) > max_recs)
return __this_address;
/* sibling pointer verification */
- if (block->bb_u.l.bb_leftsib != cpu_to_be64(NULLFSBLOCK) &&
- !xfs_verify_fsbno(mp, be64_to_cpu(block->bb_u.l.bb_leftsib)))
- return __this_address;
- if (block->bb_u.l.bb_rightsib != cpu_to_be64(NULLFSBLOCK) &&
- !xfs_verify_fsbno(mp, be64_to_cpu(block->bb_u.l.bb_rightsib)))
- return __this_address;
-
- return NULL;
+ fsb = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
+ fa = xfs_btree_check_lblock_siblings(mp, NULL, -1, fsb,
+ block->bb_u.l.bb_leftsib);
+ if (!fa)
+ fa = xfs_btree_check_lblock_siblings(mp, NULL, -1, fsb,
+ block->bb_u.l.bb_rightsib);
+ return fa;
}
/**
@@ -4499,22 +4592,21 @@ xfs_btree_sblock_verify(
{
struct xfs_mount *mp = bp->b_mount;
struct xfs_btree_block *block = XFS_BUF_TO_BLOCK(bp);
- xfs_agblock_t agno;
+ xfs_agblock_t agbno;
+ xfs_failaddr_t fa;
/* numrecs verification */
if (be16_to_cpu(block->bb_numrecs) > max_recs)
return __this_address;
/* sibling pointer verification */
- agno = xfs_daddr_to_agno(mp, xfs_buf_daddr(bp));
- if (block->bb_u.s.bb_leftsib != cpu_to_be32(NULLAGBLOCK) &&
- !xfs_verify_agbno(mp, agno, be32_to_cpu(block->bb_u.s.bb_leftsib)))
- return __this_address;
- if (block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK) &&
- !xfs_verify_agbno(mp, agno, be32_to_cpu(block->bb_u.s.bb_rightsib)))
- return __this_address;
-
- return NULL;
+ agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp));
+ fa = xfs_btree_check_sblock_siblings(bp->b_pag, NULL, -1, agbno,
+ block->bb_u.s.bb_leftsib);
+ if (!fa)
+ fa = xfs_btree_check_sblock_siblings(bp->b_pag, NULL, -1, agbno,
+ block->bb_u.s.bb_rightsib);
+ return fa;
}
/*
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 22d9f411fde6..eef27858a013 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -68,19 +68,19 @@ uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum);
/*
* For logging record fields.
*/
-#define XFS_BB_MAGIC (1 << 0)
-#define XFS_BB_LEVEL (1 << 1)
-#define XFS_BB_NUMRECS (1 << 2)
-#define XFS_BB_LEFTSIB (1 << 3)
-#define XFS_BB_RIGHTSIB (1 << 4)
-#define XFS_BB_BLKNO (1 << 5)
-#define XFS_BB_LSN (1 << 6)
-#define XFS_BB_UUID (1 << 7)
-#define XFS_BB_OWNER (1 << 8)
+#define XFS_BB_MAGIC (1u << 0)
+#define XFS_BB_LEVEL (1u << 1)
+#define XFS_BB_NUMRECS (1u << 2)
+#define XFS_BB_LEFTSIB (1u << 3)
+#define XFS_BB_RIGHTSIB (1u << 4)
+#define XFS_BB_BLKNO (1u << 5)
+#define XFS_BB_LSN (1u << 6)
+#define XFS_BB_UUID (1u << 7)
+#define XFS_BB_OWNER (1u << 8)
#define XFS_BB_NUM_BITS 5
-#define XFS_BB_ALL_BITS ((1 << XFS_BB_NUM_BITS) - 1)
+#define XFS_BB_ALL_BITS ((1u << XFS_BB_NUM_BITS) - 1)
#define XFS_BB_NUM_BITS_CRC 9
-#define XFS_BB_ALL_BITS_CRC ((1 << XFS_BB_NUM_BITS_CRC) - 1)
+#define XFS_BB_ALL_BITS_CRC ((1u << XFS_BB_NUM_BITS_CRC) - 1)
/*
* Generic stats interface
@@ -345,7 +345,7 @@ xfs_btree_dup_cursor(
*/
void
xfs_btree_offsets(
- int64_t fields, /* bitmask of fields */
+ uint32_t fields, /* bitmask of fields */
const short *offsets,/* table of field offsets */
int nbits, /* number of bits to inspect */
int *first, /* output: first byte offset */
@@ -435,7 +435,7 @@ bool xfs_btree_sblock_verify_crc(struct xfs_buf *);
/*
* Internal btree helpers also used by xfs_bmap.c.
*/
-void xfs_btree_log_block(struct xfs_btree_cur *, struct xfs_buf *, int);
+void xfs_btree_log_block(struct xfs_btree_cur *, struct xfs_buf *, uint32_t);
void xfs_btree_log_recs(struct xfs_btree_cur *, struct xfs_buf *, int, int);
/*
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 9dc1ecb9713d..e576560b46e9 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -22,6 +22,7 @@
#include "xfs_trace.h"
#include "xfs_buf_item.h"
#include "xfs_log.h"
+#include "xfs_errortag.h"
/*
* xfs_da_btree.c
@@ -116,6 +117,17 @@ xfs_da_state_free(xfs_da_state_t *state)
kmem_cache_free(xfs_da_state_cache, state);
}
+void
+xfs_da_state_reset(
+ struct xfs_da_state *state,
+ struct xfs_da_args *args)
+{
+ xfs_da_state_kill_altpath(state);
+ memset(state, 0, sizeof(struct xfs_da_state));
+ state->args = args;
+ state->mp = state->args->dp->i_mount;
+}
+
static inline int xfs_dabuf_nfsb(struct xfs_mount *mp, int whichfork)
{
if (whichfork == XFS_DATA_FORK)
@@ -482,6 +494,9 @@ xfs_da3_split(
trace_xfs_da_split(state->args);
+ if (XFS_TEST_ERROR(false, state->mp, XFS_ERRTAG_DA_LEAF_SPLIT))
+ return -EIO;
+
/*
* Walk back up the tree splitting/inserting/adjusting as necessary.
* If we need to insert and there isn't room, split the node, then
@@ -2177,8 +2192,8 @@ xfs_da_grow_inode_int(
*/
mapp = kmem_alloc(sizeof(*mapp) * count, 0);
for (b = *bno, mapi = 0; b < *bno + count; ) {
- nmap = min(XFS_BMAP_MAX_NMAP, count);
c = (int)(*bno + count - b);
+ nmap = min(XFS_BMAP_MAX_NMAP, c);
error = xfs_bmapi_write(tp, dp, b, c,
xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA,
args->total, &mapp[mapi], &nmap);
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index 0faf7d9ac241..ffa3df5b2893 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -30,6 +30,7 @@ struct xfs_da_geometry {
unsigned int free_hdr_size; /* dir2 free header size */
unsigned int free_max_bests; /* # of bests entries in dir2 free */
xfs_dablk_t freeblk; /* blockno of free data v2 */
+ xfs_extnum_t max_extents; /* Max. extents in corresponding fork */
xfs_dir2_data_aoff_t data_first_offset;
size_t data_entry_offset;
@@ -76,27 +77,33 @@ typedef struct xfs_da_args {
xfs_dablk_t rmtblkno2; /* remote attr value starting blkno */
int rmtblkcnt2; /* remote attr value block count */
int rmtvaluelen2; /* remote attr value length in bytes */
- int op_flags; /* operation flags */
+ uint32_t op_flags; /* operation flags */
enum xfs_dacmp cmpresult; /* name compare result for lookups */
} xfs_da_args_t;
/*
* Operation flags:
*/
-#define XFS_DA_OP_JUSTCHECK 0x0001 /* check for ok with no space */
-#define XFS_DA_OP_RENAME 0x0002 /* this is an atomic rename op */
-#define XFS_DA_OP_ADDNAME 0x0004 /* this is an add operation */
-#define XFS_DA_OP_OKNOENT 0x0008 /* lookup/add op, ENOENT ok, else die */
-#define XFS_DA_OP_CILOOKUP 0x0010 /* lookup to return CI name if found */
-#define XFS_DA_OP_NOTIME 0x0020 /* don't update inode timestamps */
+#define XFS_DA_OP_JUSTCHECK (1u << 0) /* check for ok with no space */
+#define XFS_DA_OP_REPLACE (1u << 1) /* this is an atomic replace op */
+#define XFS_DA_OP_ADDNAME (1u << 2) /* this is an add operation */
+#define XFS_DA_OP_OKNOENT (1u << 3) /* lookup op, ENOENT ok, else die */
+#define XFS_DA_OP_CILOOKUP (1u << 4) /* lookup returns CI name if found */
+#define XFS_DA_OP_NOTIME (1u << 5) /* don't update inode timestamps */
+#define XFS_DA_OP_REMOVE (1u << 6) /* this is a remove operation */
+#define XFS_DA_OP_RECOVERY (1u << 7) /* Log recovery operation */
+#define XFS_DA_OP_LOGGED (1u << 8) /* Use intent items to track op */
#define XFS_DA_OP_FLAGS \
{ XFS_DA_OP_JUSTCHECK, "JUSTCHECK" }, \
- { XFS_DA_OP_RENAME, "RENAME" }, \
+ { XFS_DA_OP_REPLACE, "REPLACE" }, \
{ XFS_DA_OP_ADDNAME, "ADDNAME" }, \
{ XFS_DA_OP_OKNOENT, "OKNOENT" }, \
{ XFS_DA_OP_CILOOKUP, "CILOOKUP" }, \
- { XFS_DA_OP_NOTIME, "NOTIME" }
+ { XFS_DA_OP_NOTIME, "NOTIME" }, \
+ { XFS_DA_OP_REMOVE, "REMOVE" }, \
+ { XFS_DA_OP_RECOVERY, "RECOVERY" }, \
+ { XFS_DA_OP_LOGGED, "LOGGED" }
/*
* Storage for holding state during Btree searches and split/join ops.
@@ -197,7 +204,7 @@ int xfs_da3_node_read_mapped(struct xfs_trans *tp, struct xfs_inode *dp,
* Utility routines.
*/
-#define XFS_DABUF_MAP_HOLE_OK (1 << 0)
+#define XFS_DABUF_MAP_HOLE_OK (1u << 0)
int xfs_da_grow_inode(xfs_da_args_t *args, xfs_dablk_t *new_blkno);
int xfs_da_grow_inode_int(struct xfs_da_args *args, xfs_fileoff_t *bno,
@@ -220,6 +227,7 @@ enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args,
struct xfs_da_state *xfs_da_state_alloc(struct xfs_da_args *args);
void xfs_da_state_free(xfs_da_state_t *state);
+void xfs_da_state_reset(struct xfs_da_state *state, struct xfs_da_args *args);
void xfs_da3_node_hdr_from_disk(struct xfs_mount *mp,
struct xfs_da3_icnode_hdr *to, struct xfs_da_intnode *from);
diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h
index 5a49caa5c9df..25e2841084e1 100644
--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/fs/xfs/libxfs/xfs_da_format.h
@@ -277,6 +277,7 @@ xfs_dir2_sf_firstentry(struct xfs_dir2_sf_hdr *hdr)
* Directory address space divided into sections,
* spaces separated by 32GB.
*/
+#define XFS_DIR2_MAX_SPACES 3
#define XFS_DIR2_SPACE_SIZE (1ULL << (32 + XFS_DIR2_DATA_ALIGN_LOG))
#define XFS_DIR2_DATA_SPACE 0
#define XFS_DIR2_DATA_OFFSET (XFS_DIR2_DATA_SPACE * XFS_DIR2_SPACE_SIZE)
@@ -688,10 +689,10 @@ struct xfs_attr3_leafblock {
#define XFS_ATTR_ROOT_BIT 1 /* limit access to trusted attrs */
#define XFS_ATTR_SECURE_BIT 2 /* limit access to secure attrs */
#define XFS_ATTR_INCOMPLETE_BIT 7 /* attr in middle of create/delete */
-#define XFS_ATTR_LOCAL (1 << XFS_ATTR_LOCAL_BIT)
-#define XFS_ATTR_ROOT (1 << XFS_ATTR_ROOT_BIT)
-#define XFS_ATTR_SECURE (1 << XFS_ATTR_SECURE_BIT)
-#define XFS_ATTR_INCOMPLETE (1 << XFS_ATTR_INCOMPLETE_BIT)
+#define XFS_ATTR_LOCAL (1u << XFS_ATTR_LOCAL_BIT)
+#define XFS_ATTR_ROOT (1u << XFS_ATTR_ROOT_BIT)
+#define XFS_ATTR_SECURE (1u << XFS_ATTR_SECURE_BIT)
+#define XFS_ATTR_INCOMPLETE (1u << XFS_ATTR_INCOMPLETE_BIT)
#define XFS_ATTR_NSP_ONDISK_MASK (XFS_ATTR_ROOT | XFS_ATTR_SECURE)
/*
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 0805ade2d300..5a321b783398 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -22,6 +22,10 @@
#include "xfs_refcount.h"
#include "xfs_bmap.h"
#include "xfs_alloc.h"
+#include "xfs_buf.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_attr.h"
static struct kmem_cache *xfs_defer_pending_cache;
@@ -184,36 +188,61 @@ static const struct xfs_defer_op_type *defer_op_types[] = {
[XFS_DEFER_OPS_TYPE_RMAP] = &xfs_rmap_update_defer_type,
[XFS_DEFER_OPS_TYPE_FREE] = &xfs_extent_free_defer_type,
[XFS_DEFER_OPS_TYPE_AGFL_FREE] = &xfs_agfl_free_defer_type,
+ [XFS_DEFER_OPS_TYPE_ATTR] = &xfs_attr_defer_type,
};
-static void
+/*
+ * Ensure there's a log intent item associated with this deferred work item if
+ * the operation must be restarted on crash. Returns 1 if there's a log item;
+ * 0 if there isn't; or a negative errno.
+ */
+static int
xfs_defer_create_intent(
struct xfs_trans *tp,
struct xfs_defer_pending *dfp,
bool sort)
{
const struct xfs_defer_op_type *ops = defer_op_types[dfp->dfp_type];
+ struct xfs_log_item *lip;
- if (!dfp->dfp_intent)
- dfp->dfp_intent = ops->create_intent(tp, &dfp->dfp_work,
- dfp->dfp_count, sort);
+ if (dfp->dfp_intent)
+ return 1;
+
+ lip = ops->create_intent(tp, &dfp->dfp_work, dfp->dfp_count, sort);
+ if (!lip)
+ return 0;
+ if (IS_ERR(lip))
+ return PTR_ERR(lip);
+
+ dfp->dfp_intent = lip;
+ return 1;
}
/*
* For each pending item in the intake list, log its intent item and the
* associated extents, then add the entire intake list to the end of
* the pending list.
+ *
+ * Returns 1 if at least one log item was associated with the deferred work;
+ * 0 if there are no log items; or a negative errno.
*/
-STATIC void
+static int
xfs_defer_create_intents(
struct xfs_trans *tp)
{
struct xfs_defer_pending *dfp;
+ int ret = 0;
list_for_each_entry(dfp, &tp->t_dfops, dfp_list) {
+ int ret2;
+
trace_xfs_defer_create_intent(tp->t_mountp, dfp);
- xfs_defer_create_intent(tp, dfp, true);
+ ret2 = xfs_defer_create_intent(tp, dfp, true);
+ if (ret2 < 0)
+ return ret2;
+ ret |= ret2;
}
+ return ret;
}
/* Abort all the intents that were committed. */
@@ -449,6 +478,8 @@ xfs_defer_finish_one(
dfp->dfp_count--;
error = ops->finish_item(tp, dfp->dfp_done, li, &state);
if (error == -EAGAIN) {
+ int ret;
+
/*
* Caller wants a fresh transaction; put the work item
* back on the list and log a new log intent item to
@@ -459,7 +490,9 @@ xfs_defer_finish_one(
dfp->dfp_count++;
dfp->dfp_done = NULL;
dfp->dfp_intent = NULL;
- xfs_defer_create_intent(tp, dfp, false);
+ ret = xfs_defer_create_intent(tp, dfp, false);
+ if (ret < 0)
+ error = ret;
}
if (error)
@@ -487,7 +520,7 @@ int
xfs_defer_finish_noroll(
struct xfs_trans **tp)
{
- struct xfs_defer_pending *dfp;
+ struct xfs_defer_pending *dfp = NULL;
int error = 0;
LIST_HEAD(dop_pending);
@@ -506,17 +539,24 @@ xfs_defer_finish_noroll(
* of time that any one intent item can stick around in memory,
* pinning the log tail.
*/
- xfs_defer_create_intents(*tp);
- list_splice_init(&(*tp)->t_dfops, &dop_pending);
+ int has_intents = xfs_defer_create_intents(*tp);
- error = xfs_defer_trans_roll(tp);
- if (error)
- goto out_shutdown;
+ list_splice_init(&(*tp)->t_dfops, &dop_pending);
- /* Possibly relog intent items to keep the log moving. */
- error = xfs_defer_relog(tp, &dop_pending);
- if (error)
+ if (has_intents < 0) {
+ error = has_intents;
goto out_shutdown;
+ }
+ if (has_intents || dfp) {
+ error = xfs_defer_trans_roll(tp);
+ if (error)
+ goto out_shutdown;
+
+ /* Relog intent items to keep the log moving. */
+ error = xfs_defer_relog(tp, &dop_pending);
+ if (error)
+ goto out_shutdown;
+ }
dfp = list_first_entry(&dop_pending, struct xfs_defer_pending,
dfp_list);
@@ -665,13 +705,15 @@ xfs_defer_ops_capture(
if (list_empty(&tp->t_dfops))
return NULL;
+ error = xfs_defer_create_intents(tp);
+ if (error < 0)
+ return ERR_PTR(error);
+
/* Create an object to capture the defer ops. */
dfc = kmem_zalloc(sizeof(*dfc), KM_NOFS);
INIT_LIST_HEAD(&dfc->dfc_list);
INIT_LIST_HEAD(&dfc->dfc_dfops);
- xfs_defer_create_intents(tp);
-
/* Move the dfops chain and transaction state to the capture struct. */
list_splice_init(&tp->t_dfops, &dfc->dfc_dfops);
dfc->dfc_tpflags = tp->t_flags & XFS_TRANS_LOWMODE;
@@ -748,6 +790,10 @@ xfs_defer_ops_capture_and_commit(
/* If we don't capture anything, commit transaction and exit. */
dfc = xfs_defer_ops_capture(tp);
+ if (IS_ERR(dfc)) {
+ xfs_trans_cancel(tp);
+ return PTR_ERR(dfc);
+ }
if (!dfc)
return xfs_trans_commit(tp);
@@ -774,17 +820,25 @@ xfs_defer_ops_continue(
struct xfs_trans *tp,
struct xfs_defer_resources *dres)
{
+ unsigned int i;
+
ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
ASSERT(!(tp->t_flags & XFS_TRANS_DIRTY));
- /* Lock and join the captured inode to the new transaction. */
+ /* Lock the captured resources to the new transaction. */
if (dfc->dfc_held.dr_inos == 2)
xfs_lock_two_inodes(dfc->dfc_held.dr_ip[0], XFS_ILOCK_EXCL,
dfc->dfc_held.dr_ip[1], XFS_ILOCK_EXCL);
else if (dfc->dfc_held.dr_inos == 1)
xfs_ilock(dfc->dfc_held.dr_ip[0], XFS_ILOCK_EXCL);
+
+ for (i = 0; i < dfc->dfc_held.dr_bufs; i++)
+ xfs_buf_lock(dfc->dfc_held.dr_bp[i]);
+
+ /* Join the captured resources to the new transaction. */
xfs_defer_restore_resources(tp, &dfc->dfc_held);
memcpy(dres, &dfc->dfc_held, sizeof(struct xfs_defer_resources));
+ dres->dr_bufs = 0;
/* Move captured dfops chain and state to the transaction. */
list_splice_init(&dfc->dfc_dfops, &tp->t_dfops);
@@ -854,7 +908,9 @@ xfs_defer_init_item_caches(void)
error = xfs_extfree_intent_init_cache();
if (error)
goto err;
-
+ error = xfs_attr_intent_init_cache();
+ if (error)
+ goto err;
return 0;
err:
xfs_defer_destroy_item_caches();
@@ -865,6 +921,7 @@ err:
void
xfs_defer_destroy_item_caches(void)
{
+ xfs_attr_intent_destroy_cache();
xfs_extfree_intent_destroy_cache();
xfs_bmap_intent_destroy_cache();
xfs_refcount_intent_destroy_cache();
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 7bb8a31ad65b..114a3a4930a3 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -19,6 +19,7 @@ enum xfs_defer_ops_type {
XFS_DEFER_OPS_TYPE_RMAP,
XFS_DEFER_OPS_TYPE_FREE,
XFS_DEFER_OPS_TYPE_AGFL_FREE,
+ XFS_DEFER_OPS_TYPE_ATTR,
XFS_DEFER_OPS_TYPE_MAX,
};
@@ -63,6 +64,8 @@ extern const struct xfs_defer_op_type xfs_refcount_update_defer_type;
extern const struct xfs_defer_op_type xfs_rmap_update_defer_type;
extern const struct xfs_defer_op_type xfs_extent_free_defer_type;
extern const struct xfs_defer_op_type xfs_agfl_free_defer_type;
+extern const struct xfs_defer_op_type xfs_attr_defer_type;
+
/*
* Deferred operation item relogging limits.
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 50546eadaae2..92bac3373f1f 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -19,7 +19,11 @@
#include "xfs_error.h"
#include "xfs_trace.h"
-struct xfs_name xfs_name_dotdot = { (unsigned char *)"..", 2, XFS_DIR3_FT_DIR };
+const struct xfs_name xfs_name_dotdot = {
+ .name = (const unsigned char *)"..",
+ .len = 2,
+ .type = XFS_DIR3_FT_DIR,
+};
/*
* Convert inode mode to directory entry filetype
@@ -54,10 +58,10 @@ xfs_mode_to_ftype(
*/
xfs_dahash_t
xfs_ascii_ci_hashname(
- struct xfs_name *name)
+ const struct xfs_name *name)
{
- xfs_dahash_t hash;
- int i;
+ xfs_dahash_t hash;
+ int i;
for (i = 0, hash = 0; i < name->len; i++)
hash = tolower(name->name[i]) ^ rol32(hash, 7);
@@ -146,6 +150,8 @@ xfs_da_mount(
dageo->freeblk = xfs_dir2_byte_to_da(dageo, XFS_DIR2_FREE_OFFSET);
dageo->node_ents = (dageo->blksize - dageo->node_hdr_size) /
(uint)sizeof(xfs_da_node_entry_t);
+ dageo->max_extents = (XFS_DIR2_MAX_SPACES * XFS_DIR2_SPACE_SIZE) >>
+ mp->m_sb.sb_blocklog;
dageo->magicpct = (dageo->blksize * 37) / 100;
/* set up attribute geometry - single fsb only */
@@ -157,6 +163,12 @@ xfs_da_mount(
dageo->node_hdr_size = mp->m_dir_geo->node_hdr_size;
dageo->node_ents = (dageo->blksize - dageo->node_hdr_size) /
(uint)sizeof(xfs_da_node_entry_t);
+
+ if (xfs_has_large_extent_counts(mp))
+ dageo->max_extents = XFS_MAX_EXTCNT_ATTR_FORK_LARGE;
+ else
+ dageo->max_extents = XFS_MAX_EXTCNT_ATTR_FORK_SMALL;
+
dageo->magicpct = (dageo->blksize * 37) / 100;
return 0;
}
@@ -181,7 +193,7 @@ xfs_dir_isempty(
ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
if (dp->i_disk_size == 0) /* might happen during shutdown. */
return 1;
- if (dp->i_disk_size > XFS_IFORK_DSIZE(dp))
+ if (dp->i_disk_size > xfs_inode_data_fork_size(dp))
return 0;
sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
return !sfp->count;
@@ -243,13 +255,13 @@ int
xfs_dir_createname(
struct xfs_trans *tp,
struct xfs_inode *dp,
- struct xfs_name *name,
+ const struct xfs_name *name,
xfs_ino_t inum, /* new entry inode number */
xfs_extlen_t total) /* bmap's total block count */
{
struct xfs_da_args *args;
int rval;
- int v; /* type-checking value */
+ bool v;
ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
@@ -337,16 +349,16 @@ xfs_dir_cilookup_result(
int
xfs_dir_lookup(
- xfs_trans_t *tp,
- xfs_inode_t *dp,
- struct xfs_name *name,
- xfs_ino_t *inum, /* out: inode number */
- struct xfs_name *ci_name) /* out: actual name if CI match */
+ struct xfs_trans *tp,
+ struct xfs_inode *dp,
+ const struct xfs_name *name,
+ xfs_ino_t *inum, /* out: inode number */
+ struct xfs_name *ci_name) /* out: actual name if CI match */
{
- struct xfs_da_args *args;
- int rval;
- int v; /* type-checking value */
- int lock_mode;
+ struct xfs_da_args *args;
+ int rval;
+ bool v;
+ int lock_mode;
ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
XFS_STATS_INC(dp->i_mount, xs_dir_lookup);
@@ -423,7 +435,7 @@ xfs_dir_removename(
{
struct xfs_da_args *args;
int rval;
- int v; /* type-checking value */
+ bool v;
ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
XFS_STATS_INC(dp->i_mount, xs_dir_remove);
@@ -475,13 +487,13 @@ int
xfs_dir_replace(
struct xfs_trans *tp,
struct xfs_inode *dp,
- struct xfs_name *name, /* name of entry to replace */
+ const struct xfs_name *name, /* name of entry to replace */
xfs_ino_t inum, /* new inode number */
xfs_extlen_t total) /* bmap's total block count */
{
struct xfs_da_args *args;
int rval;
- int v; /* type-checking value */
+ bool v;
ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
@@ -598,19 +610,23 @@ xfs_dir2_grow_inode(
int
xfs_dir2_isblock(
struct xfs_da_args *args,
- int *vp) /* out: 1 is block, 0 is not block */
+ bool *isblock)
{
- xfs_fileoff_t last; /* last file offset */
- int rval;
+ struct xfs_mount *mp = args->dp->i_mount;
+ xfs_fileoff_t eof;
+ int error;
- if ((rval = xfs_bmap_last_offset(args->dp, &last, XFS_DATA_FORK)))
- return rval;
- rval = XFS_FSB_TO_B(args->dp->i_mount, last) == args->geo->blksize;
- if (XFS_IS_CORRUPT(args->dp->i_mount,
- rval != 0 &&
- args->dp->i_disk_size != args->geo->blksize))
+ error = xfs_bmap_last_offset(args->dp, &eof, XFS_DATA_FORK);
+ if (error)
+ return error;
+
+ *isblock = false;
+ if (XFS_FSB_TO_B(mp, eof) != args->geo->blksize)
+ return 0;
+
+ *isblock = true;
+ if (XFS_IS_CORRUPT(mp, args->dp->i_disk_size != args->geo->blksize))
return -EFSCORRUPTED;
- *vp = rval;
return 0;
}
@@ -620,14 +636,20 @@ xfs_dir2_isblock(
int
xfs_dir2_isleaf(
struct xfs_da_args *args,
- int *vp) /* out: 1 is block, 0 is not block */
+ bool *isleaf)
{
- xfs_fileoff_t last; /* last file offset */
- int rval;
+ xfs_fileoff_t eof;
+ int error;
- if ((rval = xfs_bmap_last_offset(args->dp, &last, XFS_DATA_FORK)))
- return rval;
- *vp = last == args->geo->leafblk + args->geo->fsbcount;
+ error = xfs_bmap_last_offset(args->dp, &eof, XFS_DATA_FORK);
+ if (error)
+ return error;
+
+ *isleaf = false;
+ if (eof != args->geo->leafblk + args->geo->fsbcount)
+ return 0;
+
+ *isleaf = true;
return 0;
}
@@ -728,7 +750,7 @@ xfs_dir2_namecheck(
xfs_dahash_t
xfs_dir2_hashname(
struct xfs_mount *mp,
- struct xfs_name *name)
+ const struct xfs_name *name)
{
if (unlikely(xfs_has_asciici(mp)))
return xfs_ascii_ci_hashname(name);
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index d03e6098ded9..dd39f17dd9a9 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -21,7 +21,7 @@ struct xfs_dir2_data_unused;
struct xfs_dir3_icfree_hdr;
struct xfs_dir3_icleaf_hdr;
-extern struct xfs_name xfs_name_dotdot;
+extern const struct xfs_name xfs_name_dotdot;
/*
* Convert inode mode to directory entry filetype
@@ -39,16 +39,16 @@ extern int xfs_dir_isempty(struct xfs_inode *dp);
extern int xfs_dir_init(struct xfs_trans *tp, struct xfs_inode *dp,
struct xfs_inode *pdp);
extern int xfs_dir_createname(struct xfs_trans *tp, struct xfs_inode *dp,
- struct xfs_name *name, xfs_ino_t inum,
+ const struct xfs_name *name, xfs_ino_t inum,
xfs_extlen_t tot);
extern int xfs_dir_lookup(struct xfs_trans *tp, struct xfs_inode *dp,
- struct xfs_name *name, xfs_ino_t *inum,
+ const struct xfs_name *name, xfs_ino_t *inum,
struct xfs_name *ci_name);
extern int xfs_dir_removename(struct xfs_trans *tp, struct xfs_inode *dp,
struct xfs_name *name, xfs_ino_t ino,
xfs_extlen_t tot);
extern int xfs_dir_replace(struct xfs_trans *tp, struct xfs_inode *dp,
- struct xfs_name *name, xfs_ino_t inum,
+ const struct xfs_name *name, xfs_ino_t inum,
xfs_extlen_t tot);
extern int xfs_dir_canenter(struct xfs_trans *tp, struct xfs_inode *dp,
struct xfs_name *name);
@@ -61,8 +61,8 @@ extern int xfs_dir2_sf_to_block(struct xfs_da_args *args);
/*
* Interface routines used by userspace utilities
*/
-extern int xfs_dir2_isblock(struct xfs_da_args *args, int *r);
-extern int xfs_dir2_isleaf(struct xfs_da_args *args, int *r);
+extern int xfs_dir2_isblock(struct xfs_da_args *args, bool *isblock);
+extern int xfs_dir2_isleaf(struct xfs_da_args *args, bool *isleaf);
extern int xfs_dir2_shrink_inode(struct xfs_da_args *args, xfs_dir2_db_t db,
struct xfs_buf *bp);
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index df0869bba275..00f960a703b2 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -842,7 +842,7 @@ xfs_dir2_block_removename(
* See if the size as a shortform is good enough.
*/
size = xfs_dir2_block_sfsize(dp, hdr, &sfh);
- if (size > XFS_IFORK_DSIZE(dp))
+ if (size > xfs_inode_data_fork_size(dp))
return 0;
/*
@@ -1055,7 +1055,7 @@ xfs_dir2_leaf_to_block(
* Now see if the resulting block can be shrunken to shortform.
*/
size = xfs_dir2_block_sfsize(dp, hdr, &sfh);
- if (size > XFS_IFORK_DSIZE(dp))
+ if (size > xfs_inode_data_fork_size(dp))
return 0;
return xfs_dir2_block_to_sf(args, dbp, size, &sfh);
@@ -1071,7 +1071,7 @@ xfs_dir2_sf_to_block(
struct xfs_trans *tp = args->trans;
struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
- struct xfs_ifork *ifp = XFS_IFORK_PTR(dp, XFS_DATA_FORK);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(dp, XFS_DATA_FORK);
struct xfs_da_geometry *geo = args->geo;
xfs_dir2_db_t blkno; /* dir-relative block # (0) */
xfs_dir2_data_hdr_t *hdr; /* block header */
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index d9b66306a9a7..cb9e950a911d 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -146,6 +146,8 @@ xfs_dir3_leaf_check_int(
xfs_dir2_leaf_tail_t *ltp;
int stale;
int i;
+ bool isleaf1 = (hdr->magic == XFS_DIR2_LEAF1_MAGIC ||
+ hdr->magic == XFS_DIR3_LEAF1_MAGIC);
ltp = xfs_dir2_leaf_tail_p(geo, leaf);
@@ -158,8 +160,7 @@ xfs_dir3_leaf_check_int(
return __this_address;
/* Leaves and bests don't overlap in leaf format. */
- if ((hdr->magic == XFS_DIR2_LEAF1_MAGIC ||
- hdr->magic == XFS_DIR3_LEAF1_MAGIC) &&
+ if (isleaf1 &&
(char *)&hdr->ents[hdr->count] > (char *)xfs_dir2_leaf_bests_p(ltp))
return __this_address;
@@ -175,6 +176,10 @@ xfs_dir3_leaf_check_int(
}
if (hdr->ents[i].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
stale++;
+ if (isleaf1 && xfs_dir2_dataptr_to_db(geo,
+ be32_to_cpu(hdr->ents[i].address)) >=
+ be32_to_cpu(ltp->bestcount))
+ return __this_address;
}
if (hdr->stale != stale)
return __this_address;
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index 711709a2aa53..7404a9ff1a92 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -40,7 +40,7 @@ struct xfs_dir3_icfree_hdr {
};
/* xfs_dir2.c */
-xfs_dahash_t xfs_ascii_ci_hashname(struct xfs_name *name);
+xfs_dahash_t xfs_ascii_ci_hashname(const struct xfs_name *name);
enum xfs_dacmp xfs_ascii_ci_compname(struct xfs_da_args *args,
const unsigned char *name, int len);
extern int xfs_dir2_grow_inode(struct xfs_da_args *args, int space,
@@ -201,7 +201,8 @@ xfs_dir2_data_entsize(
return round_up(len, XFS_DIR2_DATA_ALIGN);
}
-xfs_dahash_t xfs_dir2_hashname(struct xfs_mount *mp, struct xfs_name *name);
+xfs_dahash_t xfs_dir2_hashname(struct xfs_mount *mp,
+ const struct xfs_name *name);
enum xfs_dacmp xfs_dir2_compname(struct xfs_da_args *args,
const unsigned char *name, int len);
diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c
index 5a97a87eaa20..8cd37e6e9d38 100644
--- a/fs/xfs/libxfs/xfs_dir2_sf.c
+++ b/fs/xfs/libxfs/xfs_dir2_sf.c
@@ -237,7 +237,7 @@ xfs_dir2_block_sfsize(
(i8count ? /* inumber */
count * XFS_INO64_SIZE :
count * XFS_INO32_SIZE);
- if (size > XFS_IFORK_DSIZE(dp))
+ if (size > xfs_inode_data_fork_size(dp))
return size; /* size value is a failure */
}
/*
@@ -406,7 +406,7 @@ xfs_dir2_sf_addname(
* Won't fit as shortform any more (due to size),
* or the pick routine says it won't (due to offset values).
*/
- if (new_isize > XFS_IFORK_DSIZE(dp) ||
+ if (new_isize > xfs_inode_data_fork_size(dp) ||
(pick =
xfs_dir2_sf_addname_pick(args, objchange, &sfep, &offset)) == 0) {
/*
@@ -710,7 +710,7 @@ xfs_dir2_sf_verify(
struct xfs_inode *ip)
{
struct xfs_mount *mp = ip->i_mount;
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
struct xfs_dir2_sf_hdr *sfp;
struct xfs_dir2_sf_entry *sfep;
struct xfs_dir2_sf_entry *next_sfep;
@@ -865,7 +865,6 @@ xfs_dir2_sf_lookup(
struct xfs_inode *dp = args->dp;
struct xfs_mount *mp = dp->i_mount;
int i; /* entry index */
- int error;
xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */
xfs_dir2_sf_hdr_t *sfp; /* shortform structure */
enum xfs_dacmp cmp; /* comparison result */
@@ -929,8 +928,7 @@ xfs_dir2_sf_lookup(
if (!ci_sfep)
return -ENOENT;
/* otherwise process the CI match as required by the caller */
- error = xfs_dir_cilookup_result(args, ci_sfep->name, ci_sfep->namelen);
- return error;
+ return xfs_dir_cilookup_result(args, ci_sfep->name, ci_sfep->namelen);
}
/*
@@ -1031,7 +1029,7 @@ xfs_dir2_sf_replace_needblock(
newsize = dp->i_df.if_bytes + (sfp->count + 1) * XFS_INO64_DIFF;
return inum > XFS_DIR2_MAX_SHORT_INUM &&
- sfp->i8count == 0 && newsize > XFS_IFORK_DSIZE(dp);
+ sfp->i8count == 0 && newsize > xfs_inode_data_fork_size(dp);
}
/*
diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h
index a23a52e643ad..5362908164b0 100644
--- a/fs/xfs/libxfs/xfs_errortag.h
+++ b/fs/xfs/libxfs/xfs_errortag.h
@@ -59,7 +59,10 @@
#define XFS_ERRTAG_REDUCE_MAX_IEXTENTS 36
#define XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT 37
#define XFS_ERRTAG_AG_RESV_FAIL 38
-#define XFS_ERRTAG_MAX 39
+#define XFS_ERRTAG_LARP 39
+#define XFS_ERRTAG_DA_LEAF_SPLIT 40
+#define XFS_ERRTAG_ATTR_LEAF_TO_NODE 41
+#define XFS_ERRTAG_MAX 42
/*
* Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -103,5 +106,8 @@
#define XFS_RANDOM_REDUCE_MAX_IEXTENTS 1
#define XFS_RANDOM_BMAP_ALLOC_MINLEN_EXTENT 1
#define XFS_RANDOM_AG_RESV_FAIL 1
+#define XFS_RANDOM_LARP 1
+#define XFS_RANDOM_DA_LEAF_SPLIT 1
+#define XFS_RANDOM_ATTR_LEAF_TO_NODE 1
#endif /* __XFS_ERRORTAG_H_ */
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index d665c04e69dd..371dc07233e0 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -372,12 +372,14 @@ xfs_sb_has_ro_compat_feature(
#define XFS_SB_FEAT_INCOMPAT_META_UUID (1 << 2) /* metadata UUID */
#define XFS_SB_FEAT_INCOMPAT_BIGTIME (1 << 3) /* large timestamps */
#define XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR (1 << 4) /* needs xfs_repair */
+#define XFS_SB_FEAT_INCOMPAT_NREXT64 (1 << 5) /* large extent counters */
#define XFS_SB_FEAT_INCOMPAT_ALL \
(XFS_SB_FEAT_INCOMPAT_FTYPE| \
XFS_SB_FEAT_INCOMPAT_SPINODES| \
XFS_SB_FEAT_INCOMPAT_META_UUID| \
XFS_SB_FEAT_INCOMPAT_BIGTIME| \
- XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR)
+ XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR| \
+ XFS_SB_FEAT_INCOMPAT_NREXT64)
#define XFS_SB_FEAT_INCOMPAT_UNKNOWN ~XFS_SB_FEAT_INCOMPAT_ALL
static inline bool
@@ -388,7 +390,9 @@ xfs_sb_has_incompat_feature(
return (sbp->sb_features_incompat & feature) != 0;
}
-#define XFS_SB_FEAT_INCOMPAT_LOG_ALL 0
+#define XFS_SB_FEAT_INCOMPAT_LOG_XATTRS (1 << 0) /* Delayed Attributes */
+#define XFS_SB_FEAT_INCOMPAT_LOG_ALL \
+ (XFS_SB_FEAT_INCOMPAT_LOG_XATTRS)
#define XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN ~XFS_SB_FEAT_INCOMPAT_LOG_ALL
static inline bool
xfs_sb_has_incompat_log_feature(
@@ -413,6 +417,11 @@ xfs_sb_add_incompat_log_features(
sbp->sb_features_log_incompat |= features;
}
+static inline bool xfs_sb_version_haslogxattrs(struct xfs_sb *sbp)
+{
+ return xfs_sb_is_v5(sbp) && (sbp->sb_features_log_incompat &
+ XFS_SB_FEAT_INCOMPAT_LOG_XATTRS);
+}
static inline bool
xfs_is_quota_inode(struct xfs_sb *sbp, xfs_ino_t ino)
@@ -525,26 +534,26 @@ typedef struct xfs_agf {
#define XFS_AGF_CRC_OFF offsetof(struct xfs_agf, agf_crc)
-#define XFS_AGF_MAGICNUM 0x00000001
-#define XFS_AGF_VERSIONNUM 0x00000002
-#define XFS_AGF_SEQNO 0x00000004
-#define XFS_AGF_LENGTH 0x00000008
-#define XFS_AGF_ROOTS 0x00000010
-#define XFS_AGF_LEVELS 0x00000020
-#define XFS_AGF_FLFIRST 0x00000040
-#define XFS_AGF_FLLAST 0x00000080
-#define XFS_AGF_FLCOUNT 0x00000100
-#define XFS_AGF_FREEBLKS 0x00000200
-#define XFS_AGF_LONGEST 0x00000400
-#define XFS_AGF_BTREEBLKS 0x00000800
-#define XFS_AGF_UUID 0x00001000
-#define XFS_AGF_RMAP_BLOCKS 0x00002000
-#define XFS_AGF_REFCOUNT_BLOCKS 0x00004000
-#define XFS_AGF_REFCOUNT_ROOT 0x00008000
-#define XFS_AGF_REFCOUNT_LEVEL 0x00010000
-#define XFS_AGF_SPARE64 0x00020000
+#define XFS_AGF_MAGICNUM (1u << 0)
+#define XFS_AGF_VERSIONNUM (1u << 1)
+#define XFS_AGF_SEQNO (1u << 2)
+#define XFS_AGF_LENGTH (1u << 3)
+#define XFS_AGF_ROOTS (1u << 4)
+#define XFS_AGF_LEVELS (1u << 5)
+#define XFS_AGF_FLFIRST (1u << 6)
+#define XFS_AGF_FLLAST (1u << 7)
+#define XFS_AGF_FLCOUNT (1u << 8)
+#define XFS_AGF_FREEBLKS (1u << 9)
+#define XFS_AGF_LONGEST (1u << 10)
+#define XFS_AGF_BTREEBLKS (1u << 11)
+#define XFS_AGF_UUID (1u << 12)
+#define XFS_AGF_RMAP_BLOCKS (1u << 13)
+#define XFS_AGF_REFCOUNT_BLOCKS (1u << 14)
+#define XFS_AGF_REFCOUNT_ROOT (1u << 15)
+#define XFS_AGF_REFCOUNT_LEVEL (1u << 16)
+#define XFS_AGF_SPARE64 (1u << 17)
#define XFS_AGF_NUM_BITS 18
-#define XFS_AGF_ALL_BITS ((1 << XFS_AGF_NUM_BITS) - 1)
+#define XFS_AGF_ALL_BITS ((1u << XFS_AGF_NUM_BITS) - 1)
#define XFS_AGF_FLAGS \
{ XFS_AGF_MAGICNUM, "MAGICNUM" }, \
@@ -619,22 +628,22 @@ typedef struct xfs_agi {
#define XFS_AGI_CRC_OFF offsetof(struct xfs_agi, agi_crc)
-#define XFS_AGI_MAGICNUM (1 << 0)
-#define XFS_AGI_VERSIONNUM (1 << 1)
-#define XFS_AGI_SEQNO (1 << 2)
-#define XFS_AGI_LENGTH (1 << 3)
-#define XFS_AGI_COUNT (1 << 4)
-#define XFS_AGI_ROOT (1 << 5)
-#define XFS_AGI_LEVEL (1 << 6)
-#define XFS_AGI_FREECOUNT (1 << 7)
-#define XFS_AGI_NEWINO (1 << 8)
-#define XFS_AGI_DIRINO (1 << 9)
-#define XFS_AGI_UNLINKED (1 << 10)
+#define XFS_AGI_MAGICNUM (1u << 0)
+#define XFS_AGI_VERSIONNUM (1u << 1)
+#define XFS_AGI_SEQNO (1u << 2)
+#define XFS_AGI_LENGTH (1u << 3)
+#define XFS_AGI_COUNT (1u << 4)
+#define XFS_AGI_ROOT (1u << 5)
+#define XFS_AGI_LEVEL (1u << 6)
+#define XFS_AGI_FREECOUNT (1u << 7)
+#define XFS_AGI_NEWINO (1u << 8)
+#define XFS_AGI_DIRINO (1u << 9)
+#define XFS_AGI_UNLINKED (1u << 10)
#define XFS_AGI_NUM_BITS_R1 11 /* end of the 1st agi logging region */
-#define XFS_AGI_ALL_BITS_R1 ((1 << XFS_AGI_NUM_BITS_R1) - 1)
-#define XFS_AGI_FREE_ROOT (1 << 11)
-#define XFS_AGI_FREE_LEVEL (1 << 12)
-#define XFS_AGI_IBLOCKS (1 << 13) /* both inobt/finobt block counters */
+#define XFS_AGI_ALL_BITS_R1 ((1u << XFS_AGI_NUM_BITS_R1) - 1)
+#define XFS_AGI_FREE_ROOT (1u << 11)
+#define XFS_AGI_FREE_LEVEL (1u << 12)
+#define XFS_AGI_IBLOCKS (1u << 13) /* both inobt/finobt block counters */
#define XFS_AGI_NUM_BITS_R2 14
/* disk block (xfs_daddr_t) in the AG */
@@ -695,7 +704,7 @@ struct xfs_agfl {
* When the bigtime feature is enabled, ondisk inode timestamps become an
* unsigned 64-bit nanoseconds counter. This means that the bigtime inode
* timestamp epoch is the start of the classic timestamp range, which is
- * Dec 31 20:45:52 UTC 1901. Because the epochs are not the same, callers
+ * Dec 13 20:45:52 UTC 1901. Because the epochs are not the same, callers
* /must/ use the bigtime conversion functions when encoding and decoding raw
* timestamps.
*/
@@ -791,16 +800,41 @@ struct xfs_dinode {
__be32 di_nlink; /* number of links to file */
__be16 di_projid_lo; /* lower part of owner's project id */
__be16 di_projid_hi; /* higher part owner's project id */
- __u8 di_pad[6]; /* unused, zeroed space */
- __be16 di_flushiter; /* incremented on flush */
+ union {
+ /* Number of data fork extents if NREXT64 is set */
+ __be64 di_big_nextents;
+
+ /* Padding for V3 inodes without NREXT64 set. */
+ __be64 di_v3_pad;
+
+ /* Padding and inode flush counter for V2 inodes. */
+ struct {
+ __u8 di_v2_pad[6];
+ __be16 di_flushiter;
+ };
+ };
xfs_timestamp_t di_atime; /* time last accessed */
xfs_timestamp_t di_mtime; /* time last modified */
xfs_timestamp_t di_ctime; /* time created/inode modified */
__be64 di_size; /* number of bytes in file */
__be64 di_nblocks; /* # of direct & btree blocks used */
__be32 di_extsize; /* basic/minimum extent size for file */
- __be32 di_nextents; /* number of extents in data fork */
- __be16 di_anextents; /* number of extents in attribute fork*/
+ union {
+ /*
+ * For V2 inodes and V3 inodes without NREXT64 set, this
+ * is the number of data and attr fork extents.
+ */
+ struct {
+ __be32 di_nextents;
+ __be16 di_anextents;
+ } __packed;
+
+ /* Number of attr fork extents if NREXT64 is set. */
+ struct {
+ __be32 di_big_anextents;
+ __be16 di_nrext64_pad;
+ } __packed;
+ } __packed;
__u8 di_forkoff; /* attr fork offs, <<3 for 64b align */
__s8 di_aformat; /* format of attr fork's data */
__be32 di_dmevmask; /* DMIG event mask */
@@ -870,6 +904,56 @@ enum xfs_dinode_fmt {
{ XFS_DINODE_FMT_UUID, "uuid" }
/*
+ * Max values for extnum and aextnum.
+ *
+ * The original on-disk extent counts were held in signed fields, resulting in
+ * maximum extent counts of 2^31 and 2^15 for the data and attr forks
+ * respectively. Similarly the maximum extent length is limited to 2^21 blocks
+ * by the 21-bit wide blockcount field of a BMBT extent record.
+ *
+ * The newly introduced data fork extent counter can hold a 64-bit value,
+ * however the maximum number of extents in a file is also limited to 2^54
+ * extents by the 54-bit wide startoff field of a BMBT extent record.
+ *
+ * It is further limited by the maximum supported file size of 2^63
+ * *bytes*. This leads to a maximum extent count for maximally sized filesystem
+ * blocks (64kB) of:
+ *
+ * 2^63 bytes / 2^16 bytes per block = 2^47 blocks
+ *
+ * Rounding up 47 to the nearest multiple of bits-per-byte results in 48. Hence
+ * 2^48 was chosen as the maximum data fork extent count.
+ *
+ * The maximum file size that can be represented by the data fork extent counter
+ * in the worst case occurs when all extents are 1 block in length and each
+ * block is 1KB in size.
+ *
+ * With XFS_MAX_EXTCNT_DATA_FORK_SMALL representing maximum extent count and
+ * with 1KB sized blocks, a file can reach upto,
+ * 1KB * (2^31) = 2TB
+ *
+ * This is much larger than the theoretical maximum size of a directory
+ * i.e. XFS_DIR2_SPACE_SIZE * XFS_DIR2_MAX_SPACES = ~96GB.
+ *
+ * Hence, a directory inode can never overflow its data fork extent counter.
+ */
+#define XFS_MAX_EXTCNT_DATA_FORK_LARGE ((xfs_extnum_t)((1ULL << 48) - 1))
+#define XFS_MAX_EXTCNT_ATTR_FORK_LARGE ((xfs_extnum_t)((1ULL << 32) - 1))
+#define XFS_MAX_EXTCNT_DATA_FORK_SMALL ((xfs_extnum_t)((1ULL << 31) - 1))
+#define XFS_MAX_EXTCNT_ATTR_FORK_SMALL ((xfs_extnum_t)((1ULL << 15) - 1))
+
+/*
+ * When we upgrade an inode to the large extent counts, the maximum value by
+ * which the extent count can increase is bound by the change in size of the
+ * on-disk field. No upgrade operation should ever be adding more than a few
+ * tens of extents, so if we get a really large value it is a sign of a code bug
+ * or corruption.
+ */
+#define XFS_MAX_EXTCNT_UPGRADE_NR \
+ min(XFS_MAX_EXTCNT_ATTR_FORK_LARGE - XFS_MAX_EXTCNT_ATTR_FORK_SMALL, \
+ XFS_MAX_EXTCNT_DATA_FORK_LARGE - XFS_MAX_EXTCNT_DATA_FORK_SMALL)
+
+/*
* Inode minimum and maximum sizes.
*/
#define XFS_DINODE_MIN_LOG 8
@@ -918,10 +1002,6 @@ enum xfs_dinode_fmt {
((w) == XFS_DATA_FORK ? \
(dip)->di_format : \
(dip)->di_aformat)
-#define XFS_DFORK_NEXTENTS(dip,w) \
- ((w) == XFS_DATA_FORK ? \
- be32_to_cpu((dip)->di_nextents) : \
- be16_to_cpu((dip)->di_anextents))
/*
* For block and character special files the 32bit dev_t is stored at the
@@ -988,15 +1068,17 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
#define XFS_DIFLAG2_REFLINK_BIT 1 /* file's blocks may be shared */
#define XFS_DIFLAG2_COWEXTSIZE_BIT 2 /* copy on write extent size hint */
#define XFS_DIFLAG2_BIGTIME_BIT 3 /* big timestamps */
+#define XFS_DIFLAG2_NREXT64_BIT 4 /* large extent counters */
#define XFS_DIFLAG2_DAX (1 << XFS_DIFLAG2_DAX_BIT)
#define XFS_DIFLAG2_REFLINK (1 << XFS_DIFLAG2_REFLINK_BIT)
#define XFS_DIFLAG2_COWEXTSIZE (1 << XFS_DIFLAG2_COWEXTSIZE_BIT)
#define XFS_DIFLAG2_BIGTIME (1 << XFS_DIFLAG2_BIGTIME_BIT)
+#define XFS_DIFLAG2_NREXT64 (1 << XFS_DIFLAG2_NREXT64_BIT)
#define XFS_DIFLAG2_ANY \
(XFS_DIFLAG2_DAX | XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE | \
- XFS_DIFLAG2_BIGTIME)
+ XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_NREXT64)
static inline bool xfs_dinode_has_bigtime(const struct xfs_dinode *dip)
{
@@ -1004,6 +1086,13 @@ static inline bool xfs_dinode_has_bigtime(const struct xfs_dinode *dip)
(dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_BIGTIME));
}
+static inline bool xfs_dinode_has_large_extent_counts(
+ const struct xfs_dinode *dip)
+{
+ return dip->di_version >= 3 &&
+ (dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_NREXT64));
+}
+
/*
* Inode number format:
* low inopblog bits - offset in block
@@ -1085,10 +1174,10 @@ static inline bool xfs_dinode_has_bigtime(const struct xfs_dinode *dip)
#define XFS_DQUOT_MAGIC 0x4451 /* 'DQ' */
#define XFS_DQUOT_VERSION (uint8_t)0x01 /* latest version number */
-#define XFS_DQTYPE_USER 0x01 /* user dquot record */
-#define XFS_DQTYPE_PROJ 0x02 /* project dquot record */
-#define XFS_DQTYPE_GROUP 0x04 /* group dquot record */
-#define XFS_DQTYPE_BIGTIME 0x80 /* large expiry timestamps */
+#define XFS_DQTYPE_USER (1u << 0) /* user dquot record */
+#define XFS_DQTYPE_PROJ (1u << 1) /* project dquot record */
+#define XFS_DQTYPE_GROUP (1u << 2) /* group dquot record */
+#define XFS_DQTYPE_BIGTIME (1u << 7) /* large expiry timestamps */
/* bitmask to determine if this is a user/group/project dquot */
#define XFS_DQTYPE_REC_MASK (XFS_DQTYPE_USER | \
@@ -1475,20 +1564,6 @@ struct xfs_rmap_rec {
#define RMAPBT_UNUSED_OFFSET_BITLEN 7
#define RMAPBT_OFFSET_BITLEN 54
-#define XFS_RMAP_ATTR_FORK (1 << 0)
-#define XFS_RMAP_BMBT_BLOCK (1 << 1)
-#define XFS_RMAP_UNWRITTEN (1 << 2)
-#define XFS_RMAP_KEY_FLAGS (XFS_RMAP_ATTR_FORK | \
- XFS_RMAP_BMBT_BLOCK)
-#define XFS_RMAP_REC_FLAGS (XFS_RMAP_UNWRITTEN)
-struct xfs_rmap_irec {
- xfs_agblock_t rm_startblock; /* extent start block */
- xfs_extlen_t rm_blockcount; /* extent length */
- uint64_t rm_owner; /* extent owner */
- uint64_t rm_offset; /* offset within the owner */
- unsigned int rm_flags; /* state flags */
-};
-
/*
* Key structure
*
@@ -1537,7 +1612,7 @@ unsigned int xfs_refc_block(struct xfs_mount *mp);
* on the startblock. This speeds up mount time deletion of stale
* staging extents because they're all at the right side of the tree.
*/
-#define XFS_REFC_COW_START ((xfs_agblock_t)(1U << 31))
+#define XFS_REFC_COWFLAG (1U << 31)
#define REFCNTBT_COWFLAG_BITLEN 1
#define REFCNTBT_AGBLOCK_BITLEN 31
@@ -1551,12 +1626,6 @@ struct xfs_refcount_key {
__be32 rc_startblock; /* starting block number */
};
-struct xfs_refcount_irec {
- xfs_agblock_t rc_startblock; /* starting block number */
- xfs_extlen_t rc_blockcount; /* count of free blocks */
- xfs_nlink_t rc_refcount; /* number of inodes linked here */
-};
-
#define MAXREFCOUNT ((xfs_nlink_t)~0U)
#define MAXREFCEXTLEN ((xfs_extlen_t)~0U)
@@ -1596,6 +1665,8 @@ typedef struct xfs_bmdr_block {
#define BMBT_STARTOFF_MASK ((1ULL << BMBT_STARTOFF_BITLEN) - 1)
#define BMBT_BLOCKCOUNT_MASK ((1ULL << BMBT_BLOCKCOUNT_BITLEN) - 1)
+#define XFS_MAX_BMBT_EXTLEN ((xfs_extlen_t)(BMBT_BLOCKCOUNT_MASK))
+
/*
* bmbt records have a file offset (block) field that is 54 bits wide, so this
* is the largest xfs_fileoff_t that we ever expect to see.
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index c43877c8a279..1cfd5bc6520a 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -93,21 +93,6 @@ struct getbmapx {
#define XFS_FMR_OWN_DEFECTIVE FMR_OWNER('X', 8) /* bad blocks */
/*
- * Structure for XFS_IOC_FSSETDM.
- * For use by backup and restore programs to set the XFS on-disk inode
- * fields di_dmevmask and di_dmstate. These must be set to exactly and
- * only values previously obtained via xfs_bulkstat! (Specifically the
- * struct xfs_bstat fields bs_dmevmask and bs_dmstate.)
- */
-#ifndef HAVE_FSDMIDATA
-struct fsdmidata {
- __u32 fsd_dmevmask; /* corresponds to di_dmevmask */
- __u16 fsd_padding;
- __u16 fsd_dmstate; /* corresponds to di_dmstate */
-};
-#endif
-
-/*
* File segment locking set data type for 64 bit access.
* Also used for all the RESV/FREE interfaces.
*/
@@ -251,6 +236,7 @@ typedef struct xfs_fsop_resblks {
#define XFS_FSOP_GEOM_FLAGS_REFLINK (1 << 20) /* files can share blocks */
#define XFS_FSOP_GEOM_FLAGS_BIGTIME (1 << 21) /* 64-bit nsec timestamps */
#define XFS_FSOP_GEOM_FLAGS_INOBTCNT (1 << 22) /* inobt btree counter */
+#define XFS_FSOP_GEOM_FLAGS_NREXT64 (1 << 23) /* large extent counters */
/*
* Minimum and maximum sizes need for growth checks.
@@ -392,7 +378,7 @@ struct xfs_bulkstat {
uint32_t bs_extsize_blks; /* extent size hint, blocks */
uint32_t bs_nlink; /* number of links */
- uint32_t bs_extents; /* number of extents */
+ uint32_t bs_extents; /* 32-bit data fork extent counter */
uint32_t bs_aextents; /* attribute number of extents */
uint16_t bs_version; /* structure version */
uint16_t bs_forkoff; /* inode fork offset in bytes */
@@ -401,8 +387,9 @@ struct xfs_bulkstat {
uint16_t bs_checked; /* checked inode metadata */
uint16_t bs_mode; /* type and mode */
uint16_t bs_pad2; /* zeroed */
+ uint64_t bs_extents64; /* 64-bit data fork extent counter */
- uint64_t bs_pad[7]; /* zeroed */
+ uint64_t bs_pad[6]; /* zeroed */
};
#define XFS_BULKSTAT_VERSION_V1 (1)
@@ -474,17 +461,28 @@ struct xfs_bulk_ireq {
* Only return results from the specified @agno. If @ino is zero, start
* with the first inode of @agno.
*/
-#define XFS_BULK_IREQ_AGNO (1 << 0)
+#define XFS_BULK_IREQ_AGNO (1U << 0)
/*
* Return bulkstat information for a single inode, where @ino value is a
* special value, not a literal inode number. See the XFS_BULK_IREQ_SPECIAL_*
* values below. Not compatible with XFS_BULK_IREQ_AGNO.
*/
-#define XFS_BULK_IREQ_SPECIAL (1 << 1)
+#define XFS_BULK_IREQ_SPECIAL (1U << 1)
-#define XFS_BULK_IREQ_FLAGS_ALL (XFS_BULK_IREQ_AGNO | \
- XFS_BULK_IREQ_SPECIAL)
+/*
+ * Return data fork extent count via xfs_bulkstat->bs_extents64 field and assign
+ * 0 to xfs_bulkstat->bs_extents when the flag is set. Otherwise, use
+ * xfs_bulkstat->bs_extents for returning data fork extent count and set
+ * xfs_bulkstat->bs_extents64 to 0. In the second case, return -EOVERFLOW and
+ * assign 0 to xfs_bulkstat->bs_extents if data fork extent count is larger than
+ * XFS_MAX_EXTCNT_DATA_FORK_OLD.
+ */
+#define XFS_BULK_IREQ_NREXT64 (1U << 2)
+
+#define XFS_BULK_IREQ_FLAGS_ALL (XFS_BULK_IREQ_AGNO | \
+ XFS_BULK_IREQ_SPECIAL | \
+ XFS_BULK_IREQ_NREXT64)
/* Operate on the root directory inode. */
#define XFS_BULK_IREQ_SPECIAL_ROOT (1)
@@ -562,16 +560,10 @@ typedef struct xfs_fsop_handlereq {
/*
* Compound structures for passing args through Handle Request interfaces
- * xfs_fssetdm_by_handle, xfs_attrlist_by_handle, xfs_attrmulti_by_handle
- * - ioctls: XFS_IOC_FSSETDM_BY_HANDLE, XFS_IOC_ATTRLIST_BY_HANDLE, and
- * XFS_IOC_ATTRMULTI_BY_HANDLE
+ * xfs_attrlist_by_handle, xfs_attrmulti_by_handle
+ * - ioctls: XFS_IOC_ATTRLIST_BY_HANDLE, and XFS_IOC_ATTRMULTI_BY_HANDLE
*/
-typedef struct xfs_fsop_setdm_handlereq {
- struct xfs_fsop_handlereq hreq; /* handle information */
- struct fsdmidata __user *data; /* DMAPI data */
-} xfs_fsop_setdm_handlereq_t;
-
/*
* Flags passed in xfs_attr_multiop.am_flags for the attr ioctl interface.
*
@@ -720,34 +712,34 @@ struct xfs_scrub_metadata {
#define XFS_SCRUB_TYPE_NR 25
/* i: Repair this metadata. */
-#define XFS_SCRUB_IFLAG_REPAIR (1 << 0)
+#define XFS_SCRUB_IFLAG_REPAIR (1u << 0)
/* o: Metadata object needs repair. */
-#define XFS_SCRUB_OFLAG_CORRUPT (1 << 1)
+#define XFS_SCRUB_OFLAG_CORRUPT (1u << 1)
/*
* o: Metadata object could be optimized. It's not corrupt, but
* we could improve on it somehow.
*/
-#define XFS_SCRUB_OFLAG_PREEN (1 << 2)
+#define XFS_SCRUB_OFLAG_PREEN (1u << 2)
/* o: Cross-referencing failed. */
-#define XFS_SCRUB_OFLAG_XFAIL (1 << 3)
+#define XFS_SCRUB_OFLAG_XFAIL (1u << 3)
/* o: Metadata object disagrees with cross-referenced metadata. */
-#define XFS_SCRUB_OFLAG_XCORRUPT (1 << 4)
+#define XFS_SCRUB_OFLAG_XCORRUPT (1u << 4)
/* o: Scan was not complete. */
-#define XFS_SCRUB_OFLAG_INCOMPLETE (1 << 5)
+#define XFS_SCRUB_OFLAG_INCOMPLETE (1u << 5)
/* o: Metadata object looked funny but isn't corrupt. */
-#define XFS_SCRUB_OFLAG_WARNING (1 << 6)
+#define XFS_SCRUB_OFLAG_WARNING (1u << 6)
/*
* o: IFLAG_REPAIR was set but metadata object did not need fixing or
* optimization and has therefore not been altered.
*/
-#define XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED (1 << 7)
+#define XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED (1u << 7)
#define XFS_SCRUB_FLAGS_IN (XFS_SCRUB_IFLAG_REPAIR)
#define XFS_SCRUB_FLAGS_OUT (XFS_SCRUB_OFLAG_CORRUPT | \
@@ -781,15 +773,15 @@ struct xfs_scrub_metadata {
* For 'documentation' purposed more than anything else,
* the "cmd #" field reflects the IRIX fcntl number.
*/
-#define XFS_IOC_ALLOCSP _IOW ('X', 10, struct xfs_flock64)
-#define XFS_IOC_FREESP _IOW ('X', 11, struct xfs_flock64)
+/* XFS_IOC_ALLOCSP ------- deprecated 10 */
+/* XFS_IOC_FREESP -------- deprecated 11 */
#define XFS_IOC_DIOINFO _IOR ('X', 30, struct dioattr)
#define XFS_IOC_FSGETXATTR FS_IOC_FSGETXATTR
#define XFS_IOC_FSSETXATTR FS_IOC_FSSETXATTR
-#define XFS_IOC_ALLOCSP64 _IOW ('X', 36, struct xfs_flock64)
-#define XFS_IOC_FREESP64 _IOW ('X', 37, struct xfs_flock64)
+/* XFS_IOC_ALLOCSP64 ----- deprecated 36 */
+/* XFS_IOC_FREESP64 ------ deprecated 37 */
#define XFS_IOC_GETBMAP _IOWR('X', 38, struct getbmap)
-#define XFS_IOC_FSSETDM _IOW ('X', 39, struct fsdmidata)
+/* XFS_IOC_FSSETDM ------- deprecated 39 */
#define XFS_IOC_RESVSP _IOW ('X', 40, struct xfs_flock64)
#define XFS_IOC_UNRESVSP _IOW ('X', 41, struct xfs_flock64)
#define XFS_IOC_RESVSP64 _IOW ('X', 42, struct xfs_flock64)
@@ -831,7 +823,7 @@ struct xfs_scrub_metadata {
#define XFS_IOC_FREEZE _IOWR('X', 119, int) /* aka FIFREEZE */
#define XFS_IOC_THAW _IOWR('X', 120, int) /* aka FITHAW */
-#define XFS_IOC_FSSETDM_BY_HANDLE _IOW ('X', 121, struct xfs_fsop_setdm_handlereq)
+/* XFS_IOC_FSSETDM_BY_HANDLE -- deprecated 121 */
#define XFS_IOC_ATTRLIST_BY_HANDLE _IOW ('X', 122, struct xfs_fsop_attrlist_handlereq)
#define XFS_IOC_ATTRMULTI_BY_HANDLE _IOW ('X', 123, struct xfs_fsop_attrmulti_handlereq)
#define XFS_IOC_FSGEOMETRY_V4 _IOR ('X', 124, struct xfs_fsop_geom_v4)
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index b418fe0c0679..94db50eb706a 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -105,7 +105,6 @@ xfs_inobt_get_rec(
int *stat)
{
struct xfs_mount *mp = cur->bc_mp;
- xfs_agnumber_t agno = cur->bc_ag.pag->pag_agno;
union xfs_btree_rec *rec;
int error;
uint64_t realfree;
@@ -116,7 +115,7 @@ xfs_inobt_get_rec(
xfs_inobt_btrec_to_irec(mp, rec, irec);
- if (!xfs_verify_agino(mp, agno, irec->ir_startino))
+ if (!xfs_verify_agino(cur->bc_ag.pag, irec->ir_startino))
goto out_bad_rec;
if (irec->ir_count < XFS_INODES_PER_HOLEMASK_BIT ||
irec->ir_count > XFS_INODES_PER_CHUNK)
@@ -137,7 +136,8 @@ xfs_inobt_get_rec(
out_bad_rec:
xfs_warn(mp,
"%s Inode BTree record corruption in AG %d detected!",
- cur->bc_btnum == XFS_BTNUM_INO ? "Used" : "Free", agno);
+ cur->bc_btnum == XFS_BTNUM_INO ? "Used" : "Free",
+ cur->bc_ag.pag->pag_agno);
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,
@@ -636,7 +636,7 @@ xfs_ialloc_ag_alloc(
/* randomly do sparse inode allocations */
if (xfs_has_sparseinodes(tp->t_mountp) &&
igeo->ialloc_min_blks < igeo->ialloc_blks)
- do_sparse = prandom_u32() & 1;
+ do_sparse = prandom_u32_max(2);
#endif
/*
@@ -805,7 +805,7 @@ sparse_alloc:
* number from being easily guessable.
*/
error = xfs_ialloc_inode_init(args.mp, tp, NULL, newlen, pag->pag_agno,
- args.agbno, args.len, prandom_u32());
+ args.agbno, args.len, get_random_u32());
if (error)
return error;
@@ -1610,7 +1610,7 @@ xfs_dialloc_good_ag(
return false;
if (!pag->pagi_init) {
- error = xfs_ialloc_pagi_init(mp, tp, pag->pag_agno);
+ error = xfs_ialloc_read_agi(pag, tp, NULL);
if (error)
return false;
}
@@ -1621,7 +1621,7 @@ xfs_dialloc_good_ag(
return false;
if (!pag->pagf_init) {
- error = xfs_alloc_pagf_init(mp, tp, pag->pag_agno, flags);
+ error = xfs_alloc_read_agf(pag, tp, flags, NULL);
if (error)
return false;
}
@@ -1679,7 +1679,7 @@ xfs_dialloc_try_ag(
* Then read in the AGI buffer and recheck with the AGI buffer
* lock held.
*/
- error = xfs_ialloc_read_agi(pag->pag_mount, *tpp, pag->pag_agno, &agbp);
+ error = xfs_ialloc_read_agi(pag, *tpp, &agbp);
if (error)
return error;
@@ -2169,7 +2169,7 @@ xfs_difree(
/*
* Get the allocation group header.
*/
- error = xfs_ialloc_read_agi(mp, tp, pag->pag_agno, &agbp);
+ error = xfs_ialloc_read_agi(pag, tp, &agbp);
if (error) {
xfs_warn(mp, "%s: xfs_ialloc_read_agi() returned error %d.",
__func__, error);
@@ -2215,7 +2215,7 @@ xfs_imap_lookup(
int error;
int i;
- error = xfs_ialloc_read_agi(mp, tp, pag->pag_agno, &agbp);
+ error = xfs_ialloc_read_agi(pag, tp, &agbp);
if (error) {
xfs_alert(mp,
"%s: xfs_ialloc_read_agi() returned error %d, agno %d",
@@ -2414,9 +2414,9 @@ out_drop:
*/
void
xfs_ialloc_log_agi(
- xfs_trans_t *tp, /* transaction pointer */
- struct xfs_buf *bp, /* allocation group header buffer */
- int fields) /* bitmask of fields to log */
+ struct xfs_trans *tp,
+ struct xfs_buf *bp,
+ uint32_t fields)
{
int first; /* first byte number */
int last; /* last byte number */
@@ -2571,47 +2571,48 @@ const struct xfs_buf_ops xfs_agi_buf_ops = {
*/
int
xfs_read_agi(
- struct xfs_mount *mp, /* file system mount structure */
- struct xfs_trans *tp, /* transaction pointer */
- xfs_agnumber_t agno, /* allocation group number */
- struct xfs_buf **bpp) /* allocation group hdr buf */
+ struct xfs_perag *pag,
+ struct xfs_trans *tp,
+ struct xfs_buf **agibpp)
{
+ struct xfs_mount *mp = pag->pag_mount;
int error;
- trace_xfs_read_agi(mp, agno);
+ trace_xfs_read_agi(pag->pag_mount, pag->pag_agno);
- ASSERT(agno != NULLAGNUMBER);
error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
- XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
- XFS_FSS_TO_BB(mp, 1), 0, bpp, &xfs_agi_buf_ops);
+ XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGI_DADDR(mp)),
+ XFS_FSS_TO_BB(mp, 1), 0, agibpp, &xfs_agi_buf_ops);
if (error)
return error;
if (tp)
- xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_AGI_BUF);
+ xfs_trans_buf_set_type(tp, *agibpp, XFS_BLFT_AGI_BUF);
- xfs_buf_set_ref(*bpp, XFS_AGI_REF);
+ xfs_buf_set_ref(*agibpp, XFS_AGI_REF);
return 0;
}
+/*
+ * Read in the agi and initialise the per-ag data. If the caller supplies a
+ * @agibpp, return the locked AGI buffer to them, otherwise release it.
+ */
int
xfs_ialloc_read_agi(
- struct xfs_mount *mp, /* file system mount structure */
- struct xfs_trans *tp, /* transaction pointer */
- xfs_agnumber_t agno, /* allocation group number */
- struct xfs_buf **bpp) /* allocation group hdr buf */
+ struct xfs_perag *pag,
+ struct xfs_trans *tp,
+ struct xfs_buf **agibpp)
{
- struct xfs_agi *agi; /* allocation group header */
- struct xfs_perag *pag; /* per allocation group data */
+ struct xfs_buf *agibp;
+ struct xfs_agi *agi;
int error;
- trace_xfs_ialloc_read_agi(mp, agno);
+ trace_xfs_ialloc_read_agi(pag->pag_mount, pag->pag_agno);
- error = xfs_read_agi(mp, tp, agno, bpp);
+ error = xfs_read_agi(pag, tp, &agibp);
if (error)
return error;
- agi = (*bpp)->b_addr;
- pag = (*bpp)->b_pag;
+ agi = agibp->b_addr;
if (!pag->pagi_init) {
pag->pagi_freecount = be32_to_cpu(agi->agi_freecount);
pag->pagi_count = be32_to_cpu(agi->agi_count);
@@ -2623,27 +2624,11 @@ xfs_ialloc_read_agi(
* we are in the middle of a forced shutdown.
*/
ASSERT(pag->pagi_freecount == be32_to_cpu(agi->agi_freecount) ||
- xfs_is_shutdown(mp));
- return 0;
-}
-
-/*
- * Read in the agi to initialise the per-ag data in the mount structure
- */
-int
-xfs_ialloc_pagi_init(
- xfs_mount_t *mp, /* file system mount structure */
- xfs_trans_t *tp, /* transaction pointer */
- xfs_agnumber_t agno) /* allocation group number */
-{
- struct xfs_buf *bp = NULL;
- int error;
-
- error = xfs_ialloc_read_agi(mp, tp, agno, &bp);
- if (error)
- return error;
- if (bp)
- xfs_trans_brelse(tp, bp);
+ xfs_is_shutdown(pag->pag_mount));
+ if (agibpp)
+ *agibpp = agibp;
+ else
+ xfs_trans_brelse(tp, agibp);
return 0;
}
@@ -2772,6 +2757,8 @@ xfs_ialloc_setup_geometry(
igeo->new_diflags2 = 0;
if (xfs_has_bigtime(mp))
igeo->new_diflags2 |= XFS_DIFLAG2_BIGTIME;
+ if (xfs_has_large_extent_counts(mp))
+ igeo->new_diflags2 |= XFS_DIFLAG2_NREXT64;
/* Compute inode btree geometry. */
igeo->agino_log = sbp->sb_inopblog + sbp->sb_agblklog;
@@ -2910,8 +2897,7 @@ xfs_ialloc_calc_rootino(
* allocation group, or very odd geometries created by old mkfs
* versions on very small filesystems.
*/
- if (mp->m_sb.sb_logstart &&
- XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart) == 0)
+ if (xfs_ag_contains_log(mp, 0))
first_bno += mp->m_sb.sb_logblocks;
/*
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index 8b5c2b709022..9bbbca6ac4ed 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -60,27 +60,12 @@ void
xfs_ialloc_log_agi(
struct xfs_trans *tp, /* transaction pointer */
struct xfs_buf *bp, /* allocation group header buffer */
- int fields); /* bitmask of fields to log */
+ uint32_t fields); /* bitmask of fields to log */
-/*
- * Read in the allocation group header (inode allocation section)
- */
-int /* error */
-xfs_ialloc_read_agi(
- struct xfs_mount *mp, /* file system mount structure */
- struct xfs_trans *tp, /* transaction pointer */
- xfs_agnumber_t agno, /* allocation group number */
- struct xfs_buf **bpp); /* allocation group hdr buf */
-
-/*
- * Read in the allocation group header to initialise the per-ag data
- * in the mount structure
- */
-int
-xfs_ialloc_pagi_init(
- struct xfs_mount *mp, /* file system mount structure */
- struct xfs_trans *tp, /* transaction pointer */
- xfs_agnumber_t agno); /* allocation group number */
+int xfs_read_agi(struct xfs_perag *pag, struct xfs_trans *tp,
+ struct xfs_buf **agibpp);
+int xfs_ialloc_read_agi(struct xfs_perag *pag, struct xfs_trans *tp,
+ struct xfs_buf **agibpp);
/*
* Lookup a record by ino in the btree given by cur.
@@ -102,8 +87,6 @@ int xfs_ialloc_inode_init(struct xfs_mount *mp, struct xfs_trans *tp,
xfs_agnumber_t agno, xfs_agblock_t agbno,
xfs_agblock_t length, unsigned int gen);
-int xfs_read_agi(struct xfs_mount *mp, struct xfs_trans *tp,
- xfs_agnumber_t agno, struct xfs_buf **bpp);
union xfs_btree_rec;
void xfs_inobt_btrec_to_irec(struct xfs_mount *mp,
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index b2ad2fdc40f5..8c83e265770c 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -683,10 +683,10 @@ xfs_inobt_rec_check_count(
static xfs_extlen_t
xfs_inobt_max_size(
- struct xfs_mount *mp,
- xfs_agnumber_t agno)
+ struct xfs_perag *pag)
{
- xfs_agblock_t agblocks = xfs_ag_block_count(mp, agno);
+ struct xfs_mount *mp = pag->pag_mount;
+ xfs_agblock_t agblocks = pag->block_count;
/* Bail out if we're uninitialized, which can happen in mkfs. */
if (M_IGEO(mp)->inobt_mxr[0] == 0)
@@ -697,8 +697,7 @@ xfs_inobt_max_size(
* never be available for the kinds of things that would require btree
* expansion. We therefore can pretend the space isn't there.
*/
- if (mp->m_sb.sb_logstart &&
- XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart) == agno)
+ if (xfs_ag_contains_log(mp, pag->pag_agno))
agblocks -= mp->m_sb.sb_logblocks;
return xfs_btree_calc_size(M_IGEO(mp)->inobt_mnr,
@@ -722,7 +721,7 @@ xfs_inobt_cur(
ASSERT(*agi_bpp == NULL);
ASSERT(*curpp == NULL);
- error = xfs_ialloc_read_agi(mp, tp, pag->pag_agno, agi_bpp);
+ error = xfs_ialloc_read_agi(pag, tp, agi_bpp);
if (error)
return error;
@@ -757,16 +756,15 @@ xfs_inobt_count_blocks(
/* Read finobt block count from AGI header. */
static int
xfs_finobt_read_blocks(
- struct xfs_mount *mp,
- struct xfs_trans *tp,
struct xfs_perag *pag,
+ struct xfs_trans *tp,
xfs_extlen_t *tree_blocks)
{
struct xfs_buf *agbp;
struct xfs_agi *agi;
int error;
- error = xfs_ialloc_read_agi(mp, tp, pag->pag_agno, &agbp);
+ error = xfs_ialloc_read_agi(pag, tp, &agbp);
if (error)
return error;
@@ -794,14 +792,14 @@ xfs_finobt_calc_reserves(
return 0;
if (xfs_has_inobtcounts(mp))
- error = xfs_finobt_read_blocks(mp, tp, pag, &tree_len);
+ error = xfs_finobt_read_blocks(pag, tp, &tree_len);
else
error = xfs_inobt_count_blocks(mp, tp, pag, XFS_BTNUM_FINO,
&tree_len);
if (error)
return error;
- *ask += xfs_inobt_max_size(mp, pag->pag_agno);
+ *ask += xfs_inobt_max_size(pag);
*used += tree_len;
return 0;
}
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index cae9708c8587..758aacd8166b 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -10,6 +10,7 @@
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
+#include "xfs_ag.h"
#include "xfs_inode.h"
#include "xfs_errortag.h"
#include "xfs_error.h"
@@ -41,14 +42,12 @@ xfs_inode_buf_verify(
bool readahead)
{
struct xfs_mount *mp = bp->b_mount;
- xfs_agnumber_t agno;
int i;
int ni;
/*
* Validate the magic number and version of every inode in the buffer
*/
- agno = xfs_daddr_to_agno(mp, xfs_buf_daddr(bp));
ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
for (i = 0; i < ni; i++) {
struct xfs_dinode *dip;
@@ -59,7 +58,7 @@ xfs_inode_buf_verify(
unlinked_ino = be32_to_cpu(dip->di_next_unlinked);
di_ok = xfs_verify_magic16(bp, dip->di_magic) &&
xfs_dinode_good_version(mp, dip->di_version) &&
- xfs_verify_agino_or_null(mp, agno, unlinked_ino);
+ xfs_verify_agino_or_null(bp->b_pag, unlinked_ino);
if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
XFS_ERRTAG_ITOBP_INOTOBP))) {
if (readahead) {
@@ -178,7 +177,6 @@ xfs_inode_from_disk(
xfs_failaddr_t fa;
ASSERT(ip->i_cowfp == NULL);
- ASSERT(ip->i_afp == NULL);
fa = xfs_dinode_verify(ip->i_mount, ip->i_ino, from);
if (fa) {
@@ -230,7 +228,8 @@ xfs_inode_from_disk(
ip->i_nblocks = be64_to_cpu(from->di_nblocks);
ip->i_extsize = be32_to_cpu(from->di_extsize);
ip->i_forkoff = from->di_forkoff;
- ip->i_diflags = be16_to_cpu(from->di_flags);
+ ip->i_diflags = be16_to_cpu(from->di_flags);
+ ip->i_next_unlinked = be32_to_cpu(from->di_next_unlinked);
if (from->di_dmevmask || from->di_dmstate)
xfs_iflags_set(ip, XFS_IPRESERVE_DM_FIELDS);
@@ -279,6 +278,25 @@ xfs_inode_to_disk_ts(
return ts;
}
+static inline void
+xfs_inode_to_disk_iext_counters(
+ struct xfs_inode *ip,
+ struct xfs_dinode *to)
+{
+ if (xfs_inode_has_large_extent_counts(ip)) {
+ to->di_big_nextents = cpu_to_be64(xfs_ifork_nextents(&ip->i_df));
+ to->di_big_anextents = cpu_to_be32(xfs_ifork_nextents(&ip->i_af));
+ /*
+ * We might be upgrading the inode to use larger extent counters
+ * than was previously used. Hence zero the unused field.
+ */
+ to->di_nrext64_pad = cpu_to_be16(0);
+ } else {
+ to->di_nextents = cpu_to_be32(xfs_ifork_nextents(&ip->i_df));
+ to->di_anextents = cpu_to_be16(xfs_ifork_nextents(&ip->i_af));
+ }
+}
+
void
xfs_inode_to_disk(
struct xfs_inode *ip,
@@ -296,7 +314,6 @@ xfs_inode_to_disk(
to->di_projid_lo = cpu_to_be16(ip->i_projid & 0xffff);
to->di_projid_hi = cpu_to_be16(ip->i_projid >> 16);
- memset(to->di_pad, 0, sizeof(to->di_pad));
to->di_atime = xfs_inode_to_disk_ts(ip, inode->i_atime);
to->di_mtime = xfs_inode_to_disk_ts(ip, inode->i_mtime);
to->di_ctime = xfs_inode_to_disk_ts(ip, inode->i_ctime);
@@ -307,10 +324,8 @@ xfs_inode_to_disk(
to->di_size = cpu_to_be64(ip->i_disk_size);
to->di_nblocks = cpu_to_be64(ip->i_nblocks);
to->di_extsize = cpu_to_be32(ip->i_extsize);
- to->di_nextents = cpu_to_be32(xfs_ifork_nextents(&ip->i_df));
- to->di_anextents = cpu_to_be16(xfs_ifork_nextents(ip->i_afp));
to->di_forkoff = ip->i_forkoff;
- to->di_aformat = xfs_ifork_format(ip->i_afp);
+ to->di_aformat = xfs_ifork_format(&ip->i_af);
to->di_flags = cpu_to_be16(ip->i_diflags);
if (xfs_has_v3inodes(ip->i_mount)) {
@@ -323,11 +338,14 @@ xfs_inode_to_disk(
to->di_lsn = cpu_to_be64(lsn);
memset(to->di_pad2, 0, sizeof(to->di_pad2));
uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid);
- to->di_flushiter = 0;
+ to->di_v3_pad = 0;
} else {
to->di_version = 2;
to->di_flushiter = cpu_to_be16(ip->i_flushiter);
+ memset(to->di_v2_pad, 0, sizeof(to->di_v2_pad));
}
+
+ xfs_inode_to_disk_iext_counters(ip, to);
}
static xfs_failaddr_t
@@ -336,20 +354,40 @@ xfs_dinode_verify_fork(
struct xfs_mount *mp,
int whichfork)
{
- uint32_t di_nextents = XFS_DFORK_NEXTENTS(dip, whichfork);
+ xfs_extnum_t di_nextents;
+ xfs_extnum_t max_extents;
+ mode_t mode = be16_to_cpu(dip->di_mode);
+ uint32_t fork_size = XFS_DFORK_SIZE(dip, mp, whichfork);
+ uint32_t fork_format = XFS_DFORK_FORMAT(dip, whichfork);
+
+ di_nextents = xfs_dfork_nextents(dip, whichfork);
+
+ /*
+ * For fork types that can contain local data, check that the fork
+ * format matches the size of local data contained within the fork.
+ *
+ * For all types, check that when the size says the should be in extent
+ * or btree format, the inode isn't claiming it is in local format.
+ */
+ if (whichfork == XFS_DATA_FORK) {
+ if (S_ISDIR(mode) || S_ISLNK(mode)) {
+ if (be64_to_cpu(dip->di_size) <= fork_size &&
+ fork_format != XFS_DINODE_FMT_LOCAL)
+ return __this_address;
+ }
- switch (XFS_DFORK_FORMAT(dip, whichfork)) {
+ if (be64_to_cpu(dip->di_size) > fork_size &&
+ fork_format == XFS_DINODE_FMT_LOCAL)
+ return __this_address;
+ }
+
+ switch (fork_format) {
case XFS_DINODE_FMT_LOCAL:
/*
- * no local regular files yet
+ * No local regular files yet.
*/
- if (whichfork == XFS_DATA_FORK) {
- if (S_ISREG(be16_to_cpu(dip->di_mode)))
- return __this_address;
- if (be64_to_cpu(dip->di_size) >
- XFS_DFORK_SIZE(dip, mp, whichfork))
- return __this_address;
- }
+ if (S_ISREG(mode) && whichfork == XFS_DATA_FORK)
+ return __this_address;
if (di_nextents)
return __this_address;
break;
@@ -358,12 +396,11 @@ xfs_dinode_verify_fork(
return __this_address;
break;
case XFS_DINODE_FMT_BTREE:
- if (whichfork == XFS_ATTR_FORK) {
- if (di_nextents > MAXAEXTNUM)
- return __this_address;
- } else if (di_nextents > MAXEXTNUM) {
+ max_extents = xfs_iext_max_nextents(
+ xfs_dinode_has_large_extent_counts(dip),
+ whichfork);
+ if (di_nextents > max_extents)
return __this_address;
- }
break;
default:
return __this_address;
@@ -396,6 +433,24 @@ xfs_dinode_verify_forkoff(
return NULL;
}
+static xfs_failaddr_t
+xfs_dinode_verify_nrext64(
+ struct xfs_mount *mp,
+ struct xfs_dinode *dip)
+{
+ if (xfs_dinode_has_large_extent_counts(dip)) {
+ if (!xfs_has_large_extent_counts(mp))
+ return __this_address;
+ if (dip->di_nrext64_pad != 0)
+ return __this_address;
+ } else if (dip->di_version >= 3) {
+ if (dip->di_v3_pad != 0)
+ return __this_address;
+ }
+
+ return NULL;
+}
+
xfs_failaddr_t
xfs_dinode_verify(
struct xfs_mount *mp,
@@ -407,6 +462,9 @@ xfs_dinode_verify(
uint16_t flags;
uint64_t flags2;
uint64_t di_size;
+ xfs_extnum_t nextents;
+ xfs_extnum_t naextents;
+ xfs_filblks_t nblocks;
if (dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC))
return __this_address;
@@ -437,10 +495,19 @@ xfs_dinode_verify(
if ((S_ISLNK(mode) || S_ISDIR(mode)) && di_size == 0)
return __this_address;
+ fa = xfs_dinode_verify_nrext64(mp, dip);
+ if (fa)
+ return fa;
+
+ nextents = xfs_dfork_data_extents(dip);
+ naextents = xfs_dfork_attr_extents(dip);
+ nblocks = be64_to_cpu(dip->di_nblocks);
+
/* Fork checks carried over from xfs_iformat_fork */
- if (mode &&
- be32_to_cpu(dip->di_nextents) + be16_to_cpu(dip->di_anextents) >
- be64_to_cpu(dip->di_nblocks))
+ if (mode && nextents + naextents > nblocks)
+ return __this_address;
+
+ if (S_ISDIR(mode) && nextents > mp->m_dir_geo->max_extents)
return __this_address;
if (mode && XFS_DFORK_BOFF(dip) > mp->m_sb.sb_inodesize)
@@ -497,7 +564,7 @@ xfs_dinode_verify(
default:
return __this_address;
}
- if (dip->di_anextents)
+ if (naextents)
return __this_address;
}
@@ -639,7 +706,7 @@ xfs_inode_validate_extsize(
if (extsize_bytes % blocksize_bytes)
return __this_address;
- if (extsize > MAXEXTLEN)
+ if (extsize > XFS_MAX_BMBT_EXTLEN)
return __this_address;
if (!rt_flag && extsize > mp->m_sb.sb_agblocks / 2)
@@ -696,7 +763,7 @@ xfs_inode_validate_cowextsize(
if (cowextsize_bytes % mp->m_sb.sb_blocksize)
return __this_address;
- if (cowextsize > MAXEXTLEN)
+ if (cowextsize > XFS_MAX_BMBT_EXTLEN)
return __this_address;
if (cowextsize > mp->m_sb.sb_agblocks / 2)
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 9149f4f796fc..6b21760184d9 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -35,8 +35,8 @@ xfs_init_local_fork(
const void *data,
int64_t size)
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
- int mem_size = size, real_size = 0;
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
+ int mem_size = size;
bool zero_terminate;
/*
@@ -50,8 +50,7 @@ xfs_init_local_fork(
mem_size++;
if (size) {
- real_size = roundup(mem_size, 4);
- ifp->if_u1.if_data = kmem_alloc(real_size, KM_NOFS);
+ ifp->if_u1.if_data = kmem_alloc(mem_size, KM_NOFS);
memcpy(ifp->if_u1.if_data, data, size);
if (zero_terminate)
ifp->if_u1.if_data[size] = '\0';
@@ -79,7 +78,7 @@ xfs_iformat_local(
*/
if (unlikely(size > XFS_DFORK_SIZE(dip, ip->i_mount, whichfork))) {
xfs_warn(ip->i_mount,
- "corrupt inode %Lu (bad size %d for local fork, size = %zd).",
+ "corrupt inode %llu (bad size %d for local fork, size = %zd).",
(unsigned long long) ip->i_ino, size,
XFS_DFORK_SIZE(dip, ip->i_mount, whichfork));
xfs_inode_verifier_error(ip, -EFSCORRUPTED,
@@ -103,9 +102,9 @@ xfs_iformat_extents(
int whichfork)
{
struct xfs_mount *mp = ip->i_mount;
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
int state = xfs_bmap_fork_to_state(whichfork);
- int nex = XFS_DFORK_NEXTENTS(dip, whichfork);
+ xfs_extnum_t nex = xfs_dfork_nextents(dip, whichfork);
int size = nex * sizeof(xfs_bmbt_rec_t);
struct xfs_iext_cursor icur;
struct xfs_bmbt_rec *dp;
@@ -117,8 +116,8 @@ xfs_iformat_extents(
* we just bail out rather than crash in kmem_alloc() or memcpy() below.
*/
if (unlikely(size < 0 || size > XFS_DFORK_SIZE(dip, mp, whichfork))) {
- xfs_warn(ip->i_mount, "corrupt inode %Lu ((a)extents = %d).",
- (unsigned long long) ip->i_ino, nex);
+ xfs_warn(ip->i_mount, "corrupt inode %llu ((a)extents = %llu).",
+ ip->i_ino, nex);
xfs_inode_verifier_error(ip, -EFSCORRUPTED,
"xfs_iformat_extents(1)", dip, sizeof(*dip),
__this_address);
@@ -174,7 +173,7 @@ xfs_iformat_btree(
int size;
int level;
- ifp = XFS_IFORK_PTR(ip, whichfork);
+ ifp = xfs_ifork_ptr(ip, whichfork);
dfp = (xfs_bmdr_block_t *)XFS_DFORK_PTR(dip, whichfork);
size = XFS_BMAP_BROOT_SPACE(mp, dfp);
nrecs = be16_to_cpu(dfp->bb_numrecs);
@@ -193,7 +192,7 @@ xfs_iformat_btree(
XFS_DFORK_SIZE(dip, mp, whichfork) ||
ifp->if_nextents > ip->i_nblocks) ||
level == 0 || level > XFS_BM_MAXLEVELS(mp, whichfork)) {
- xfs_warn(mp, "corrupt inode %Lu (btree).",
+ xfs_warn(mp, "corrupt inode %llu (btree).",
(unsigned long long) ip->i_ino);
xfs_inode_verifier_error(ip, -EFSCORRUPTED,
"xfs_iformat_btree", dfp, size,
@@ -230,7 +229,7 @@ xfs_iformat_data_fork(
* depend on it.
*/
ip->i_df.if_format = dip->di_format;
- ip->i_df.if_nextents = be32_to_cpu(dip->di_nextents);
+ ip->i_df.if_nextents = xfs_dfork_data_extents(dip);
switch (inode->i_mode & S_IFMT) {
case S_IFIFO:
@@ -277,17 +276,23 @@ xfs_dfork_attr_shortform_size(
return be16_to_cpu(atp->hdr.totsize);
}
-struct xfs_ifork *
-xfs_ifork_alloc(
+void
+xfs_ifork_init_attr(
+ struct xfs_inode *ip,
enum xfs_dinode_fmt format,
xfs_extnum_t nextents)
{
- struct xfs_ifork *ifp;
+ ip->i_af.if_format = format;
+ ip->i_af.if_nextents = nextents;
+}
- ifp = kmem_cache_zalloc(xfs_ifork_cache, GFP_NOFS | __GFP_NOFAIL);
- ifp->if_format = format;
- ifp->if_nextents = nextents;
- return ifp;
+void
+xfs_ifork_zap_attr(
+ struct xfs_inode *ip)
+{
+ xfs_idestroy_fork(&ip->i_af);
+ memset(&ip->i_af, 0, sizeof(struct xfs_ifork));
+ ip->i_af.if_format = XFS_DINODE_FMT_EXTENTS;
}
int
@@ -295,16 +300,16 @@ xfs_iformat_attr_fork(
struct xfs_inode *ip,
struct xfs_dinode *dip)
{
+ xfs_extnum_t naextents = xfs_dfork_attr_extents(dip);
int error = 0;
/*
* Initialize the extent count early, as the per-format routines may
* depend on it.
*/
- ip->i_afp = xfs_ifork_alloc(dip->di_aformat,
- be16_to_cpu(dip->di_anextents));
+ xfs_ifork_init_attr(ip, dip->di_aformat, naextents);
- switch (ip->i_afp->if_format) {
+ switch (ip->i_af.if_format) {
case XFS_DINODE_FMT_LOCAL:
error = xfs_iformat_local(ip, dip, XFS_ATTR_FORK,
xfs_dfork_attr_shortform_size(dip));
@@ -324,10 +329,8 @@ xfs_iformat_attr_fork(
break;
}
- if (error) {
- kmem_cache_free(xfs_ifork_cache, ip->i_afp);
- ip->i_afp = NULL;
- }
+ if (error)
+ xfs_ifork_zap_attr(ip);
return error;
}
@@ -371,7 +374,7 @@ xfs_iroot_realloc(
return;
}
- ifp = XFS_IFORK_PTR(ip, whichfork);
+ ifp = xfs_ifork_ptr(ip, whichfork);
if (rec_diff > 0) {
/*
* If there wasn't any memory allocated before, just
@@ -401,7 +404,7 @@ xfs_iroot_realloc(
(int)new_size);
ifp->if_broot_bytes = (int)new_size;
ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <=
- XFS_IFORK_SIZE(ip, whichfork));
+ xfs_inode_fork_size(ip, whichfork));
memmove(np, op, cur_max * (uint)sizeof(xfs_fsblock_t));
return;
}
@@ -455,7 +458,7 @@ xfs_iroot_realloc(
ifp->if_broot_bytes = (int)new_size;
if (ifp->if_broot)
ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <=
- XFS_IFORK_SIZE(ip, whichfork));
+ xfs_inode_fork_size(ip, whichfork));
return;
}
@@ -481,11 +484,11 @@ xfs_idata_realloc(
int64_t byte_diff,
int whichfork)
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
int64_t new_size = ifp->if_bytes + byte_diff;
ASSERT(new_size >= 0);
- ASSERT(new_size <= XFS_IFORK_SIZE(ip, whichfork));
+ ASSERT(new_size <= xfs_inode_fork_size(ip, whichfork));
if (byte_diff == 0)
return;
@@ -497,12 +500,7 @@ xfs_idata_realloc(
return;
}
- /*
- * For inline data, the underlying buffer must be a multiple of 4 bytes
- * in size so that it can be logged and stay on word boundaries.
- * We enforce that here.
- */
- ifp->if_u1.if_data = krealloc(ifp->if_u1.if_data, roundup(new_size, 4),
+ ifp->if_u1.if_data = krealloc(ifp->if_u1.if_data, new_size,
GFP_NOFS | __GFP_NOFAIL);
ifp->if_bytes = new_size;
}
@@ -545,7 +543,7 @@ xfs_iextents_copy(
int whichfork)
{
int state = xfs_bmap_fork_to_state(whichfork);
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
struct xfs_iext_cursor icur;
struct xfs_bmbt_irec rec;
int64_t copied = 0;
@@ -597,7 +595,7 @@ xfs_iflush_fork(
if (!iip)
return;
- ifp = XFS_IFORK_PTR(ip, whichfork);
+ ifp = xfs_ifork_ptr(ip, whichfork);
/*
* This can happen if we gave up in iformat in an error path,
* for the attribute fork.
@@ -613,7 +611,7 @@ xfs_iflush_fork(
if ((iip->ili_fields & dataflag[whichfork]) &&
(ifp->if_bytes > 0)) {
ASSERT(ifp->if_u1.if_data != NULL);
- ASSERT(ifp->if_bytes <= XFS_IFORK_SIZE(ip, whichfork));
+ ASSERT(ifp->if_bytes <= xfs_inode_fork_size(ip, whichfork));
memcpy(cp, ifp->if_u1.if_data, ifp->if_bytes);
}
break;
@@ -632,7 +630,7 @@ xfs_iflush_fork(
(ifp->if_broot_bytes > 0)) {
ASSERT(ifp->if_broot != NULL);
ASSERT(XFS_BMAP_BMDR_SPACE(ifp->if_broot) <=
- XFS_IFORK_SIZE(ip, whichfork));
+ xfs_inode_fork_size(ip, whichfork));
xfs_bmbt_to_bmdr(mp, ifp->if_broot, ifp->if_broot_bytes,
(xfs_bmdr_block_t *)cp,
XFS_DFORK_SIZE(dip, mp, whichfork));
@@ -662,7 +660,7 @@ xfs_iext_state_to_fork(
if (state & BMAP_COWFORK)
return ip->i_cowfp;
else if (state & BMAP_ATTRFORK)
- return ip->i_afp;
+ return &ip->i_af;
return &ip->i_df;
}
@@ -713,18 +711,17 @@ int
xfs_ifork_verify_local_attr(
struct xfs_inode *ip)
{
- struct xfs_ifork *ifp = ip->i_afp;
+ struct xfs_ifork *ifp = &ip->i_af;
xfs_failaddr_t fa;
- if (!ifp)
+ if (!xfs_inode_has_attr_fork(ip))
fa = __this_address;
else
fa = xfs_attr_shortform_verify(ip);
if (fa) {
xfs_inode_verifier_error(ip, -EFSCORRUPTED, "attr fork",
- ifp ? ifp->if_u1.if_data : NULL,
- ifp ? ifp->if_bytes : 0, fa);
+ ifp->if_u1.if_data, ifp->if_bytes, fa);
return -EFSCORRUPTED;
}
@@ -737,14 +734,15 @@ xfs_iext_count_may_overflow(
int whichfork,
int nr_to_add)
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
uint64_t max_exts;
uint64_t nr_exts;
if (whichfork == XFS_COW_FORK)
return 0;
- max_exts = (whichfork == XFS_ATTR_FORK) ? MAXAEXTNUM : MAXEXTNUM;
+ max_exts = xfs_iext_max_nextents(xfs_inode_has_large_extent_counts(ip),
+ whichfork);
if (XFS_TEST_ERROR(false, ip->i_mount, XFS_ERRTAG_REDUCE_MAX_IEXTENTS))
max_exts = 10;
@@ -755,3 +753,27 @@ xfs_iext_count_may_overflow(
return 0;
}
+
+/*
+ * Upgrade this inode's extent counter fields to be able to handle a potential
+ * increase in the extent count by nr_to_add. Normally this is the same
+ * quantity that caused xfs_iext_count_may_overflow() to return -EFBIG.
+ */
+int
+xfs_iext_count_upgrade(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip,
+ uint nr_to_add)
+{
+ ASSERT(nr_to_add <= XFS_MAX_EXTCNT_UPGRADE_NR);
+
+ if (!xfs_has_large_extent_counts(ip->i_mount) ||
+ xfs_inode_has_large_extent_counts(ip) ||
+ XFS_TEST_ERROR(false, ip->i_mount, XFS_ERRTAG_REDUCE_MAX_IEXTENTS))
+ return -EFBIG;
+
+ ip->i_diflags2 |= XFS_DIFLAG2_NREXT64;
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+ return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 3d64a3acb0ed..d3943d6ad0b9 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -21,9 +21,9 @@ struct xfs_ifork {
void *if_root; /* extent tree root */
char *if_data; /* inline file data */
} if_u1;
+ xfs_extnum_t if_nextents; /* # of extents in this fork */
short if_broot_bytes; /* bytes allocated for root */
int8_t if_format; /* format of this fork */
- xfs_extnum_t if_nextents; /* # of extents in this fork */
};
/*
@@ -40,19 +40,6 @@ struct xfs_ifork {
#define XFS_IEXT_PUNCH_HOLE_CNT (1)
/*
- * Directory entry addition can cause the following,
- * 1. Data block can be added/removed.
- * A new extent can cause extent count to increase by 1.
- * 2. Free disk block can be added/removed.
- * Same behaviour as described above for Data block.
- * 3. Dabtree blocks.
- * XFS_DA_NODE_MAXDEPTH blocks can be added. Each of these can be new
- * extents. Hence extent count can increase by XFS_DA_NODE_MAXDEPTH.
- */
-#define XFS_IEXT_DIR_MANIP_CNT(mp) \
- ((XFS_DA_NODE_MAXDEPTH + 1 + 1) * (mp)->m_dir_geo->fsbcount)
-
-/*
* Adding/removing an xattr can cause XFS_DA_NODE_MAXDEPTH extents to
* be added. One extra extent for dabtree in case a local attr is
* large enough to cause a double split. It can also cause extent
@@ -90,28 +77,8 @@ struct xfs_ifork {
/*
* Fork handling.
*/
-
-#define XFS_IFORK_Q(ip) ((ip)->i_forkoff != 0)
-#define XFS_IFORK_BOFF(ip) ((int)((ip)->i_forkoff << 3))
-
-#define XFS_IFORK_PTR(ip,w) \
- ((w) == XFS_DATA_FORK ? \
- &(ip)->i_df : \
- ((w) == XFS_ATTR_FORK ? \
- (ip)->i_afp : \
- (ip)->i_cowfp))
-#define XFS_IFORK_DSIZE(ip) \
- (XFS_IFORK_Q(ip) ? XFS_IFORK_BOFF(ip) : XFS_LITINO((ip)->i_mount))
-#define XFS_IFORK_ASIZE(ip) \
- (XFS_IFORK_Q(ip) ? XFS_LITINO((ip)->i_mount) - XFS_IFORK_BOFF(ip) : 0)
-#define XFS_IFORK_SIZE(ip,w) \
- ((w) == XFS_DATA_FORK ? \
- XFS_IFORK_DSIZE(ip) : \
- ((w) == XFS_ATTR_FORK ? \
- XFS_IFORK_ASIZE(ip) : \
- 0))
#define XFS_IFORK_MAXEXT(ip, w) \
- (XFS_IFORK_SIZE(ip, w) / sizeof(xfs_bmbt_rec_t))
+ (xfs_inode_fork_size(ip, w) / sizeof(xfs_bmbt_rec_t))
static inline bool xfs_ifork_has_extents(struct xfs_ifork *ifp)
{
@@ -133,8 +100,68 @@ static inline int8_t xfs_ifork_format(struct xfs_ifork *ifp)
return ifp->if_format;
}
-struct xfs_ifork *xfs_ifork_alloc(enum xfs_dinode_fmt format,
- xfs_extnum_t nextents);
+static inline xfs_extnum_t xfs_iext_max_nextents(bool has_large_extent_counts,
+ int whichfork)
+{
+ switch (whichfork) {
+ case XFS_DATA_FORK:
+ case XFS_COW_FORK:
+ if (has_large_extent_counts)
+ return XFS_MAX_EXTCNT_DATA_FORK_LARGE;
+ return XFS_MAX_EXTCNT_DATA_FORK_SMALL;
+
+ case XFS_ATTR_FORK:
+ if (has_large_extent_counts)
+ return XFS_MAX_EXTCNT_ATTR_FORK_LARGE;
+ return XFS_MAX_EXTCNT_ATTR_FORK_SMALL;
+
+ default:
+ ASSERT(0);
+ return 0;
+ }
+}
+
+static inline xfs_extnum_t
+xfs_dfork_data_extents(
+ struct xfs_dinode *dip)
+{
+ if (xfs_dinode_has_large_extent_counts(dip))
+ return be64_to_cpu(dip->di_big_nextents);
+
+ return be32_to_cpu(dip->di_nextents);
+}
+
+static inline xfs_extnum_t
+xfs_dfork_attr_extents(
+ struct xfs_dinode *dip)
+{
+ if (xfs_dinode_has_large_extent_counts(dip))
+ return be32_to_cpu(dip->di_big_anextents);
+
+ return be16_to_cpu(dip->di_anextents);
+}
+
+static inline xfs_extnum_t
+xfs_dfork_nextents(
+ struct xfs_dinode *dip,
+ int whichfork)
+{
+ switch (whichfork) {
+ case XFS_DATA_FORK:
+ return xfs_dfork_data_extents(dip);
+ case XFS_ATTR_FORK:
+ return xfs_dfork_attr_extents(dip);
+ default:
+ ASSERT(0);
+ break;
+ }
+
+ return 0;
+}
+
+void xfs_ifork_zap_attr(struct xfs_inode *ip);
+void xfs_ifork_init_attr(struct xfs_inode *ip, enum xfs_dinode_fmt format,
+ xfs_extnum_t nextents);
struct xfs_ifork *xfs_iext_state_to_fork(struct xfs_inode *ip, int state);
int xfs_iformat_data_fork(struct xfs_inode *, struct xfs_dinode *);
@@ -229,6 +256,8 @@ int xfs_ifork_verify_local_data(struct xfs_inode *ip);
int xfs_ifork_verify_local_attr(struct xfs_inode *ip);
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);
/* returns true if the fork has extents but they are not read in yet. */
static inline bool xfs_need_iread_extents(struct xfs_ifork *ifp)
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index b322db523d65..f13e0809dc63 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -69,7 +69,6 @@ static inline uint xlog_get_cycle(char *ptr)
/* Log Clients */
#define XFS_TRANSACTION 0x69
-#define XFS_VOLUME 0x2
#define XFS_LOG 0xaa
#define XLOG_UNMOUNT_TYPE 0x556e /* Un for Unmount */
@@ -114,7 +113,12 @@ struct xfs_unmount_log_format {
#define XLOG_REG_TYPE_CUD_FORMAT 24
#define XLOG_REG_TYPE_BUI_FORMAT 25
#define XLOG_REG_TYPE_BUD_FORMAT 26
-#define XLOG_REG_TYPE_MAX 26
+#define XLOG_REG_TYPE_ATTRI_FORMAT 27
+#define XLOG_REG_TYPE_ATTRD_FORMAT 28
+#define XLOG_REG_TYPE_ATTR_NAME 29
+#define XLOG_REG_TYPE_ATTR_VALUE 30
+#define XLOG_REG_TYPE_MAX 30
+
/*
* Flags to log operation header
@@ -237,6 +241,8 @@ typedef struct xfs_trans_header {
#define XFS_LI_CUD 0x1243
#define XFS_LI_BUI 0x1244 /* bmbt update intent */
#define XFS_LI_BUD 0x1245
+#define XFS_LI_ATTRI 0x1246 /* attr set/remove intent*/
+#define XFS_LI_ATTRD 0x1247 /* attr set/remove done */
#define XFS_LI_TYPE_DESC \
{ XFS_LI_EFI, "XFS_LI_EFI" }, \
@@ -252,7 +258,9 @@ typedef struct xfs_trans_header {
{ XFS_LI_CUI, "XFS_LI_CUI" }, \
{ XFS_LI_CUD, "XFS_LI_CUD" }, \
{ XFS_LI_BUI, "XFS_LI_BUI" }, \
- { XFS_LI_BUD, "XFS_LI_BUD" }
+ { XFS_LI_BUD, "XFS_LI_BUD" }, \
+ { XFS_LI_ATTRI, "XFS_LI_ATTRI" }, \
+ { XFS_LI_ATTRD, "XFS_LI_ATTRD" }
/*
* Inode Log Item Format definitions.
@@ -388,16 +396,41 @@ struct xfs_log_dinode {
uint32_t di_nlink; /* number of links to file */
uint16_t di_projid_lo; /* lower part of owner's project id */
uint16_t di_projid_hi; /* higher part of owner's project id */
- uint8_t di_pad[6]; /* unused, zeroed space */
- uint16_t di_flushiter; /* incremented on flush */
+ union {
+ /* Number of data fork extents if NREXT64 is set */
+ uint64_t di_big_nextents;
+
+ /* Padding for V3 inodes without NREXT64 set. */
+ uint64_t di_v3_pad;
+
+ /* Padding and inode flush counter for V2 inodes. */
+ struct {
+ uint8_t di_v2_pad[6]; /* V2 inode zeroed space */
+ uint16_t di_flushiter; /* V2 inode incremented on flush */
+ };
+ };
xfs_log_timestamp_t di_atime; /* time last accessed */
xfs_log_timestamp_t di_mtime; /* time last modified */
xfs_log_timestamp_t di_ctime; /* time created/inode modified */
xfs_fsize_t di_size; /* number of bytes in file */
xfs_rfsblock_t di_nblocks; /* # of direct & btree blocks used */
xfs_extlen_t di_extsize; /* basic/minimum extent size for file */
- xfs_extnum_t di_nextents; /* number of extents in data fork */
- xfs_aextnum_t di_anextents; /* number of extents in attribute fork*/
+ union {
+ /*
+ * For V2 inodes and V3 inodes without NREXT64 set, this
+ * is the number of data and attr fork extents.
+ */
+ struct {
+ uint32_t di_nextents;
+ uint16_t di_anextents;
+ } __packed;
+
+ /* Number of attr fork extents if NREXT64 is set. */
+ struct {
+ uint32_t di_big_anextents;
+ uint16_t di_nrext64_pad;
+ } __packed;
+ } __packed;
uint8_t di_forkoff; /* attr fork offs, <<3 for 64b align */
int8_t di_aformat; /* format of attr fork's data */
uint32_t di_dmevmask; /* DMIG event mask */
@@ -580,25 +613,49 @@ typedef struct xfs_efi_log_format {
uint16_t efi_size; /* size of this item */
uint32_t efi_nextents; /* # extents to free */
uint64_t efi_id; /* efi identifier */
- xfs_extent_t efi_extents[1]; /* array of extents to free */
+ xfs_extent_t efi_extents[]; /* array of extents to free */
} xfs_efi_log_format_t;
+static inline size_t
+xfs_efi_log_format_sizeof(
+ unsigned int nr)
+{
+ return sizeof(struct xfs_efi_log_format) +
+ nr * sizeof(struct xfs_extent);
+}
+
typedef struct xfs_efi_log_format_32 {
uint16_t efi_type; /* efi log item type */
uint16_t efi_size; /* size of this item */
uint32_t efi_nextents; /* # extents to free */
uint64_t efi_id; /* efi identifier */
- xfs_extent_32_t efi_extents[1]; /* array of extents to free */
+ xfs_extent_32_t efi_extents[]; /* array of extents to free */
} __attribute__((packed)) xfs_efi_log_format_32_t;
+static inline size_t
+xfs_efi_log_format32_sizeof(
+ unsigned int nr)
+{
+ return sizeof(struct xfs_efi_log_format_32) +
+ nr * sizeof(struct xfs_extent_32);
+}
+
typedef struct xfs_efi_log_format_64 {
uint16_t efi_type; /* efi log item type */
uint16_t efi_size; /* size of this item */
uint32_t efi_nextents; /* # extents to free */
uint64_t efi_id; /* efi identifier */
- xfs_extent_64_t efi_extents[1]; /* array of extents to free */
+ xfs_extent_64_t efi_extents[]; /* array of extents to free */
} xfs_efi_log_format_64_t;
+static inline size_t
+xfs_efi_log_format64_sizeof(
+ unsigned int nr)
+{
+ return sizeof(struct xfs_efi_log_format_64) +
+ nr * sizeof(struct xfs_extent_64);
+}
+
/*
* This is the structure used to lay out an efd log item in the
* log. The efd_extents array is a variable size array whose
@@ -609,25 +666,49 @@ typedef struct xfs_efd_log_format {
uint16_t efd_size; /* size of this item */
uint32_t efd_nextents; /* # of extents freed */
uint64_t efd_efi_id; /* id of corresponding efi */
- xfs_extent_t efd_extents[1]; /* array of extents freed */
+ xfs_extent_t efd_extents[]; /* array of extents freed */
} xfs_efd_log_format_t;
+static inline size_t
+xfs_efd_log_format_sizeof(
+ unsigned int nr)
+{
+ return sizeof(struct xfs_efd_log_format) +
+ nr * sizeof(struct xfs_extent);
+}
+
typedef struct xfs_efd_log_format_32 {
uint16_t efd_type; /* efd log item type */
uint16_t efd_size; /* size of this item */
uint32_t efd_nextents; /* # of extents freed */
uint64_t efd_efi_id; /* id of corresponding efi */
- xfs_extent_32_t efd_extents[1]; /* array of extents freed */
+ xfs_extent_32_t efd_extents[]; /* array of extents freed */
} __attribute__((packed)) xfs_efd_log_format_32_t;
+static inline size_t
+xfs_efd_log_format32_sizeof(
+ unsigned int nr)
+{
+ return sizeof(struct xfs_efd_log_format_32) +
+ nr * sizeof(struct xfs_extent_32);
+}
+
typedef struct xfs_efd_log_format_64 {
uint16_t efd_type; /* efd log item type */
uint16_t efd_size; /* size of this item */
uint32_t efd_nextents; /* # of extents freed */
uint64_t efd_efi_id; /* id of corresponding efi */
- xfs_extent_64_t efd_extents[1]; /* array of extents freed */
+ xfs_extent_64_t efd_extents[]; /* array of extents freed */
} xfs_efd_log_format_64_t;
+static inline size_t
+xfs_efd_log_format64_sizeof(
+ unsigned int nr)
+{
+ return sizeof(struct xfs_efd_log_format_64) +
+ nr * sizeof(struct xfs_extent_64);
+}
+
/*
* RUI/RUD (reverse mapping) log format definitions
*/
@@ -869,4 +950,44 @@ struct xfs_icreate_log {
__be32 icl_gen; /* inode generation number to use */
};
+/*
+ * Flags for deferred attribute operations.
+ * Upper bits are flags, lower byte is type code
+ */
+#define XFS_ATTRI_OP_FLAGS_SET 1 /* Set the attribute */
+#define XFS_ATTRI_OP_FLAGS_REMOVE 2 /* Remove the attribute */
+#define XFS_ATTRI_OP_FLAGS_REPLACE 3 /* Replace the attribute */
+#define XFS_ATTRI_OP_FLAGS_TYPE_MASK 0xFF /* Flags type mask */
+
+/*
+ * alfi_attr_filter captures the state of xfs_da_args.attr_filter, so it should
+ * never have any other bits set.
+ */
+#define XFS_ATTRI_FILTER_MASK (XFS_ATTR_ROOT | \
+ XFS_ATTR_SECURE | \
+ XFS_ATTR_INCOMPLETE)
+
+/*
+ * This is the structure used to lay out an attr log item in the
+ * log.
+ */
+struct xfs_attri_log_format {
+ uint16_t alfi_type; /* attri log item type */
+ uint16_t alfi_size; /* size of this item */
+ uint32_t __pad; /* pad to 64 bit aligned */
+ uint64_t alfi_id; /* attri identifier */
+ uint64_t alfi_ino; /* the inode for this attr operation */
+ uint32_t alfi_op_flags; /* marks the op as a set or remove */
+ uint32_t alfi_name_len; /* attr name length */
+ uint32_t alfi_value_len; /* attr value length */
+ uint32_t alfi_attr_filter;/* attr filter flags */
+};
+
+struct xfs_attrd_log_format {
+ uint16_t alfd_type; /* attrd log item type */
+ uint16_t alfd_size; /* size of this item */
+ uint32_t __pad; /* pad to 64 bit aligned */
+ uint64_t alfd_alf_id; /* id of corresponding attri */
+};
+
#endif /* __XFS_LOG_FORMAT_H__ */
diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h
index ff69a0000817..2420865f3007 100644
--- a/fs/xfs/libxfs/xfs_log_recover.h
+++ b/fs/xfs/libxfs/xfs_log_recover.h
@@ -72,6 +72,8 @@ extern const struct xlog_recover_item_ops xlog_rui_item_ops;
extern const struct xlog_recover_item_ops xlog_rud_item_ops;
extern const struct xlog_recover_item_ops xlog_cui_item_ops;
extern const struct xlog_recover_item_ops xlog_cud_item_ops;
+extern const struct xlog_recover_item_ops xlog_attri_item_ops;
+extern const struct xlog_recover_item_ops xlog_attrd_item_ops;
/*
* Macros, structures, prototypes for internal log manager use.
@@ -108,12 +110,6 @@ struct xlog_recover {
#define ITEM_TYPE(i) (*(unsigned short *)(i)->ri_buf[0].i_addr)
-/*
- * This is the number of entries in the l_buf_cancel_table used during
- * recovery.
- */
-#define XLOG_BC_TABLE_SIZE 64
-
#define XLOG_RECOVER_CRCPASS 0
#define XLOG_RECOVER_PASS1 1
#define XLOG_RECOVER_PASS2 2
@@ -126,5 +122,13 @@ int xlog_recover_iget(struct xfs_mount *mp, xfs_ino_t ino,
struct xfs_inode **ipp);
void xlog_recover_release_intent(struct xlog *log, unsigned short intent_type,
uint64_t intent_id);
+int xlog_alloc_buf_cancel_table(struct xlog *log);
+void xlog_free_buf_cancel_table(struct xlog *log);
+
+#ifdef DEBUG
+void xlog_check_buf_cancel_table(struct xlog *log);
+#else
+#define xlog_check_buf_cancel_table(log) do { } while (0)
+#endif
#endif /* __XFS_LOG_RECOVER_H__ */
diff --git a/fs/xfs/libxfs/xfs_log_rlimit.c b/fs/xfs/libxfs/xfs_log_rlimit.c
index 67798ff5e14e..9975b93a7412 100644
--- a/fs/xfs/libxfs/xfs_log_rlimit.c
+++ b/fs/xfs/libxfs/xfs_log_rlimit.c
@@ -14,6 +14,7 @@
#include "xfs_trans_space.h"
#include "xfs_da_btree.h"
#include "xfs_bmap_btree.h"
+#include "xfs_trace.h"
/*
* Calculate the maximum length in bytes that would be required for a local
@@ -37,6 +38,65 @@ xfs_log_calc_max_attrsetm_res(
}
/*
+ * Compute an alternate set of log reservation sizes for use exclusively with
+ * minimum log size calculations.
+ */
+static void
+xfs_log_calc_trans_resv_for_minlogblocks(
+ struct xfs_mount *mp,
+ struct xfs_trans_resv *resv)
+{
+ unsigned int rmap_maxlevels = mp->m_rmap_maxlevels;
+
+ /*
+ * In the early days of rmap+reflink, we always set the rmap maxlevels
+ * to 9 even if the AG was small enough that it would never grow to
+ * that height. Transaction reservation sizes influence the minimum
+ * log size calculation, which influences the size of the log that mkfs
+ * creates. Use the old value here to ensure that newly formatted
+ * small filesystems will mount on older kernels.
+ */
+ if (xfs_has_rmapbt(mp) && xfs_has_reflink(mp))
+ mp->m_rmap_maxlevels = XFS_OLD_REFLINK_RMAP_MAXLEVELS;
+
+ xfs_trans_resv_calc(mp, resv);
+
+ if (xfs_has_reflink(mp)) {
+ /*
+ * In the early days of reflink, typical log operation counts
+ * were greatly overestimated.
+ */
+ resv->tr_write.tr_logcount = XFS_WRITE_LOG_COUNT_REFLINK;
+ resv->tr_itruncate.tr_logcount =
+ XFS_ITRUNCATE_LOG_COUNT_REFLINK;
+ resv->tr_qm_dqalloc.tr_logcount = XFS_WRITE_LOG_COUNT_REFLINK;
+ } else if (xfs_has_rmapbt(mp)) {
+ /*
+ * In the early days of non-reflink rmap, the impact of rmapbt
+ * updates on log counts were not taken into account at all.
+ */
+ resv->tr_write.tr_logcount = XFS_WRITE_LOG_COUNT;
+ resv->tr_itruncate.tr_logcount = XFS_ITRUNCATE_LOG_COUNT;
+ resv->tr_qm_dqalloc.tr_logcount = XFS_WRITE_LOG_COUNT;
+ }
+
+ /*
+ * In the early days of reflink, we did not use deferred refcount
+ * update log items, so log reservations must be recomputed using the
+ * old calculations.
+ */
+ resv->tr_write.tr_logres =
+ xfs_calc_write_reservation_minlogsize(mp);
+ resv->tr_itruncate.tr_logres =
+ xfs_calc_itruncate_reservation_minlogsize(mp);
+ resv->tr_qm_dqalloc.tr_logres =
+ xfs_calc_qm_dqalloc_reservation_minlogsize(mp);
+
+ /* Put everything back the way it was. This goes at the end. */
+ mp->m_rmap_maxlevels = rmap_maxlevels;
+}
+
+/*
* Iterate over the log space reservation table to figure out and return
* the maximum one in terms of the pre-calculated values which were done
* at mount time.
@@ -46,19 +106,25 @@ xfs_log_get_max_trans_res(
struct xfs_mount *mp,
struct xfs_trans_res *max_resp)
{
+ struct xfs_trans_resv resv = {};
struct xfs_trans_res *resp;
struct xfs_trans_res *end_resp;
+ unsigned int i;
int log_space = 0;
int attr_space;
attr_space = xfs_log_calc_max_attrsetm_res(mp);
- resp = (struct xfs_trans_res *)M_RES(mp);
- end_resp = (struct xfs_trans_res *)(M_RES(mp) + 1);
- for (; resp < end_resp; resp++) {
+ xfs_log_calc_trans_resv_for_minlogblocks(mp, &resv);
+
+ resp = (struct xfs_trans_res *)&resv;
+ end_resp = (struct xfs_trans_res *)(&resv + 1);
+ for (i = 0; resp < end_resp; i++, resp++) {
int tmp = resp->tr_logcount > 1 ?
resp->tr_logres * resp->tr_logcount :
resp->tr_logres;
+
+ trace_xfs_trans_resv_calc_minlogsize(mp, i, resp);
if (log_space < tmp) {
log_space = tmp;
*max_resp = *resp; /* struct copy */
@@ -66,9 +132,10 @@ xfs_log_get_max_trans_res(
}
if (attr_space > log_space) {
- *max_resp = M_RES(mp)->tr_attrsetm; /* struct copy */
+ *max_resp = resv.tr_attrsetm; /* struct copy */
max_resp->tr_logres = attr_space;
}
+ trace_xfs_log_get_max_trans_res(mp, max_resp);
}
/*
diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h
index a02c5062f9b2..cb035da3f990 100644
--- a/fs/xfs/libxfs/xfs_quota_defs.h
+++ b/fs/xfs/libxfs/xfs_quota_defs.h
@@ -16,7 +16,6 @@
* and quota-limits. This is a waste in the common case, but hey ...
*/
typedef uint64_t xfs_qcnt_t;
-typedef uint16_t xfs_qwarncnt_t;
typedef uint8_t xfs_dqtype_t;
@@ -29,8 +28,8 @@ typedef uint8_t xfs_dqtype_t;
/*
* flags for q_flags field in the dquot.
*/
-#define XFS_DQFLAG_DIRTY (1 << 0) /* dquot is dirty */
-#define XFS_DQFLAG_FREEING (1 << 1) /* dquot is being torn down */
+#define XFS_DQFLAG_DIRTY (1u << 0) /* dquot is dirty */
+#define XFS_DQFLAG_FREEING (1u << 1) /* dquot is being torn down */
#define XFS_DQFLAG_STRINGS \
{ XFS_DQFLAG_DIRTY, "DIRTY" }, \
@@ -73,29 +72,45 @@ typedef uint8_t xfs_dqtype_t;
* to a single function. None of these XFS_QMOPT_* flags are meant to have
* persistent values (ie. their values can and will change between versions)
*/
-#define XFS_QMOPT_UQUOTA 0x0000004 /* user dquot requested */
-#define XFS_QMOPT_PQUOTA 0x0000008 /* project dquot requested */
-#define XFS_QMOPT_FORCE_RES 0x0000010 /* ignore quota limits */
-#define XFS_QMOPT_SBVERSION 0x0000040 /* change superblock version num */
-#define XFS_QMOPT_GQUOTA 0x0002000 /* group dquot requested */
+#define XFS_QMOPT_UQUOTA (1u << 0) /* user dquot requested */
+#define XFS_QMOPT_GQUOTA (1u << 1) /* group dquot requested */
+#define XFS_QMOPT_PQUOTA (1u << 2) /* project dquot requested */
+#define XFS_QMOPT_FORCE_RES (1u << 3) /* ignore quota limits */
+#define XFS_QMOPT_SBVERSION (1u << 4) /* change superblock version num */
/*
* flags to xfs_trans_mod_dquot to indicate which field needs to be
* modified.
*/
-#define XFS_QMOPT_RES_REGBLKS 0x0010000
-#define XFS_QMOPT_RES_RTBLKS 0x0020000
-#define XFS_QMOPT_BCOUNT 0x0040000
-#define XFS_QMOPT_ICOUNT 0x0080000
-#define XFS_QMOPT_RTBCOUNT 0x0100000
-#define XFS_QMOPT_DELBCOUNT 0x0200000
-#define XFS_QMOPT_DELRTBCOUNT 0x0400000
-#define XFS_QMOPT_RES_INOS 0x0800000
+#define XFS_QMOPT_RES_REGBLKS (1u << 7)
+#define XFS_QMOPT_RES_RTBLKS (1u << 8)
+#define XFS_QMOPT_BCOUNT (1u << 9)
+#define XFS_QMOPT_ICOUNT (1u << 10)
+#define XFS_QMOPT_RTBCOUNT (1u << 11)
+#define XFS_QMOPT_DELBCOUNT (1u << 12)
+#define XFS_QMOPT_DELRTBCOUNT (1u << 13)
+#define XFS_QMOPT_RES_INOS (1u << 14)
/*
* flags for dqalloc.
*/
-#define XFS_QMOPT_INHERIT 0x1000000
+#define XFS_QMOPT_INHERIT (1u << 31)
+
+#define XFS_QMOPT_FLAGS \
+ { XFS_QMOPT_UQUOTA, "UQUOTA" }, \
+ { XFS_QMOPT_PQUOTA, "PQUOTA" }, \
+ { XFS_QMOPT_FORCE_RES, "FORCE_RES" }, \
+ { XFS_QMOPT_SBVERSION, "SBVERSION" }, \
+ { XFS_QMOPT_GQUOTA, "GQUOTA" }, \
+ { XFS_QMOPT_INHERIT, "INHERIT" }, \
+ { XFS_QMOPT_RES_REGBLKS, "RES_REGBLKS" }, \
+ { XFS_QMOPT_RES_RTBLKS, "RES_RTBLKS" }, \
+ { XFS_QMOPT_BCOUNT, "BCOUNT" }, \
+ { XFS_QMOPT_ICOUNT, "ICOUNT" }, \
+ { XFS_QMOPT_RTBCOUNT, "RTBCOUNT" }, \
+ { XFS_QMOPT_DELBCOUNT, "DELBCOUNT" }, \
+ { XFS_QMOPT_DELRTBCOUNT, "DELRTBCOUNT" }, \
+ { XFS_QMOPT_RES_INOS, "RES_INOS" }
/*
* flags to xfs_trans_mod_dquot.
@@ -114,6 +129,7 @@ typedef uint8_t xfs_dqtype_t;
(XFS_QMOPT_UQUOTA | XFS_QMOPT_PQUOTA | XFS_QMOPT_GQUOTA)
#define XFS_QMOPT_RESBLK_MASK (XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_RES_RTBLKS)
+
extern xfs_failaddr_t xfs_dquot_verify(struct xfs_mount *mp,
struct xfs_disk_dquot *ddq, xfs_dqid_t id);
extern xfs_failaddr_t xfs_dqblk_verify(struct xfs_mount *mp,
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 327ba25e9e17..3f34bafe18dd 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -46,13 +46,16 @@ STATIC int __xfs_refcount_cow_free(struct xfs_btree_cur *rcur,
int
xfs_refcount_lookup_le(
struct xfs_btree_cur *cur,
+ enum xfs_refc_domain domain,
xfs_agblock_t bno,
int *stat)
{
- trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, bno,
+ trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno,
+ xfs_refcount_encode_startblock(bno, domain),
XFS_LOOKUP_LE);
cur->bc_rec.rc.rc_startblock = bno;
cur->bc_rec.rc.rc_blockcount = 0;
+ cur->bc_rec.rc.rc_domain = domain;
return xfs_btree_lookup(cur, XFS_LOOKUP_LE, stat);
}
@@ -63,13 +66,16 @@ xfs_refcount_lookup_le(
int
xfs_refcount_lookup_ge(
struct xfs_btree_cur *cur,
+ enum xfs_refc_domain domain,
xfs_agblock_t bno,
int *stat)
{
- trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, bno,
+ trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno,
+ xfs_refcount_encode_startblock(bno, domain),
XFS_LOOKUP_GE);
cur->bc_rec.rc.rc_startblock = bno;
cur->bc_rec.rc.rc_blockcount = 0;
+ cur->bc_rec.rc.rc_domain = domain;
return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat);
}
@@ -80,13 +86,16 @@ xfs_refcount_lookup_ge(
int
xfs_refcount_lookup_eq(
struct xfs_btree_cur *cur,
+ enum xfs_refc_domain domain,
xfs_agblock_t bno,
int *stat)
{
- trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, bno,
+ trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno,
+ xfs_refcount_encode_startblock(bno, domain),
XFS_LOOKUP_LE);
cur->bc_rec.rc.rc_startblock = bno;
cur->bc_rec.rc.rc_blockcount = 0;
+ cur->bc_rec.rc.rc_domain = domain;
return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat);
}
@@ -96,7 +105,17 @@ xfs_refcount_btrec_to_irec(
const union xfs_btree_rec *rec,
struct xfs_refcount_irec *irec)
{
- irec->rc_startblock = be32_to_cpu(rec->refc.rc_startblock);
+ uint32_t start;
+
+ start = be32_to_cpu(rec->refc.rc_startblock);
+ if (start & XFS_REFC_COWFLAG) {
+ start &= ~XFS_REFC_COWFLAG;
+ irec->rc_domain = XFS_REFC_DOMAIN_COW;
+ } else {
+ irec->rc_domain = XFS_REFC_DOMAIN_SHARED;
+ }
+
+ irec->rc_startblock = start;
irec->rc_blockcount = be32_to_cpu(rec->refc.rc_blockcount);
irec->rc_refcount = be32_to_cpu(rec->refc.rc_refcount);
}
@@ -111,48 +130,35 @@ xfs_refcount_get_rec(
int *stat)
{
struct xfs_mount *mp = cur->bc_mp;
- xfs_agnumber_t agno = cur->bc_ag.pag->pag_agno;
+ struct xfs_perag *pag = cur->bc_ag.pag;
union xfs_btree_rec *rec;
int error;
- xfs_agblock_t realstart;
error = xfs_btree_get_rec(cur, &rec, stat);
if (error || !*stat)
return error;
xfs_refcount_btrec_to_irec(rec, irec);
-
- agno = cur->bc_ag.pag->pag_agno;
if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN)
goto out_bad_rec;
- /* handle special COW-staging state */
- realstart = irec->rc_startblock;
- if (realstart & XFS_REFC_COW_START) {
- if (irec->rc_refcount != 1)
- goto out_bad_rec;
- realstart &= ~XFS_REFC_COW_START;
- } else if (irec->rc_refcount < 2) {
+ if (!xfs_refcount_check_domain(irec))
goto out_bad_rec;
- }
/* check for valid extent range, including overflow */
- if (!xfs_verify_agbno(mp, agno, realstart))
- goto out_bad_rec;
- if (realstart > realstart + irec->rc_blockcount)
- goto out_bad_rec;
- if (!xfs_verify_agbno(mp, agno, realstart + irec->rc_blockcount - 1))
+ if (!xfs_verify_agbext(pag, irec->rc_startblock, irec->rc_blockcount))
goto out_bad_rec;
if (irec->rc_refcount == 0 || irec->rc_refcount > MAXREFCOUNT)
goto out_bad_rec;
- trace_xfs_refcount_get(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec);
+ trace_xfs_refcount_get(cur->bc_mp, pag->pag_agno, irec);
return 0;
out_bad_rec:
xfs_warn(mp,
- "Refcount BTree record corruption in AG %d detected!", agno);
+ "Refcount BTree record corruption in AG %d detected!",
+ pag->pag_agno);
xfs_warn(mp,
"Start block 0x%x, block count 0x%x, references 0x%x",
irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount);
@@ -170,12 +176,17 @@ xfs_refcount_update(
struct xfs_refcount_irec *irec)
{
union xfs_btree_rec rec;
+ uint32_t start;
int error;
trace_xfs_refcount_update(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec);
- rec.refc.rc_startblock = cpu_to_be32(irec->rc_startblock);
+
+ start = xfs_refcount_encode_startblock(irec->rc_startblock,
+ irec->rc_domain);
+ rec.refc.rc_startblock = cpu_to_be32(start);
rec.refc.rc_blockcount = cpu_to_be32(irec->rc_blockcount);
rec.refc.rc_refcount = cpu_to_be32(irec->rc_refcount);
+
error = xfs_btree_update(cur, &rec);
if (error)
trace_xfs_refcount_update_error(cur->bc_mp,
@@ -197,9 +208,12 @@ xfs_refcount_insert(
int error;
trace_xfs_refcount_insert(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec);
+
cur->bc_rec.rc.rc_startblock = irec->rc_startblock;
cur->bc_rec.rc.rc_blockcount = irec->rc_blockcount;
cur->bc_rec.rc.rc_refcount = irec->rc_refcount;
+ cur->bc_rec.rc.rc_domain = irec->rc_domain;
+
error = xfs_btree_insert(cur, i);
if (error)
goto out_error;
@@ -245,7 +259,8 @@ xfs_refcount_delete(
}
if (error)
goto out_error;
- error = xfs_refcount_lookup_ge(cur, irec.rc_startblock, &found_rec);
+ error = xfs_refcount_lookup_ge(cur, irec.rc_domain, irec.rc_startblock,
+ &found_rec);
out_error:
if (error)
trace_xfs_refcount_delete_error(cur->bc_mp,
@@ -344,6 +359,7 @@ xfs_refc_next(
STATIC int
xfs_refcount_split_extent(
struct xfs_btree_cur *cur,
+ enum xfs_refc_domain domain,
xfs_agblock_t agbno,
bool *shape_changed)
{
@@ -352,7 +368,7 @@ xfs_refcount_split_extent(
int error;
*shape_changed = false;
- error = xfs_refcount_lookup_le(cur, agbno, &found_rec);
+ error = xfs_refcount_lookup_le(cur, domain, agbno, &found_rec);
if (error)
goto out_error;
if (!found_rec)
@@ -365,6 +381,8 @@ xfs_refcount_split_extent(
error = -EFSCORRUPTED;
goto out_error;
}
+ if (rcext.rc_domain != domain)
+ return 0;
if (rcext.rc_startblock == agbno || xfs_refc_next(&rcext) <= agbno)
return 0;
@@ -416,6 +434,9 @@ xfs_refcount_merge_center_extents(
trace_xfs_refcount_merge_center_extents(cur->bc_mp,
cur->bc_ag.pag->pag_agno, left, center, right);
+ ASSERT(left->rc_domain == center->rc_domain);
+ ASSERT(right->rc_domain == center->rc_domain);
+
/*
* Make sure the center and right extents are not in the btree.
* If the center extent was synthesized, the first delete call
@@ -424,8 +445,8 @@ xfs_refcount_merge_center_extents(
* call removes the center and the second one removes the right
* extent.
*/
- error = xfs_refcount_lookup_ge(cur, center->rc_startblock,
- &found_rec);
+ error = xfs_refcount_lookup_ge(cur, center->rc_domain,
+ center->rc_startblock, &found_rec);
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -452,8 +473,8 @@ xfs_refcount_merge_center_extents(
}
/* Enlarge the left extent. */
- error = xfs_refcount_lookup_le(cur, left->rc_startblock,
- &found_rec);
+ error = xfs_refcount_lookup_le(cur, left->rc_domain,
+ left->rc_startblock, &found_rec);
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -492,10 +513,12 @@ xfs_refcount_merge_left_extent(
trace_xfs_refcount_merge_left_extent(cur->bc_mp,
cur->bc_ag.pag->pag_agno, left, cleft);
+ ASSERT(left->rc_domain == cleft->rc_domain);
+
/* If the extent at agbno (cleft) wasn't synthesized, remove it. */
if (cleft->rc_refcount > 1) {
- error = xfs_refcount_lookup_le(cur, cleft->rc_startblock,
- &found_rec);
+ error = xfs_refcount_lookup_le(cur, cleft->rc_domain,
+ cleft->rc_startblock, &found_rec);
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -513,8 +536,8 @@ xfs_refcount_merge_left_extent(
}
/* Enlarge the left extent. */
- error = xfs_refcount_lookup_le(cur, left->rc_startblock,
- &found_rec);
+ error = xfs_refcount_lookup_le(cur, left->rc_domain,
+ left->rc_startblock, &found_rec);
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -553,13 +576,15 @@ xfs_refcount_merge_right_extent(
trace_xfs_refcount_merge_right_extent(cur->bc_mp,
cur->bc_ag.pag->pag_agno, cright, right);
+ ASSERT(right->rc_domain == cright->rc_domain);
+
/*
* If the extent ending at agbno+aglen (cright) wasn't synthesized,
* remove it.
*/
if (cright->rc_refcount > 1) {
- error = xfs_refcount_lookup_le(cur, cright->rc_startblock,
- &found_rec);
+ error = xfs_refcount_lookup_le(cur, cright->rc_domain,
+ cright->rc_startblock, &found_rec);
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -577,8 +602,8 @@ xfs_refcount_merge_right_extent(
}
/* Enlarge the right extent. */
- error = xfs_refcount_lookup_le(cur, right->rc_startblock,
- &found_rec);
+ error = xfs_refcount_lookup_le(cur, right->rc_domain,
+ right->rc_startblock, &found_rec);
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -601,8 +626,6 @@ out_error:
return error;
}
-#define XFS_FIND_RCEXT_SHARED 1
-#define XFS_FIND_RCEXT_COW 2
/*
* Find the left extent and the one after it (cleft). This function assumes
* that we've already split any extent crossing agbno.
@@ -612,16 +635,16 @@ xfs_refcount_find_left_extents(
struct xfs_btree_cur *cur,
struct xfs_refcount_irec *left,
struct xfs_refcount_irec *cleft,
+ enum xfs_refc_domain domain,
xfs_agblock_t agbno,
- xfs_extlen_t aglen,
- int flags)
+ xfs_extlen_t aglen)
{
struct xfs_refcount_irec tmp;
int error;
int found_rec;
left->rc_startblock = cleft->rc_startblock = NULLAGBLOCK;
- error = xfs_refcount_lookup_le(cur, agbno - 1, &found_rec);
+ error = xfs_refcount_lookup_le(cur, domain, agbno - 1, &found_rec);
if (error)
goto out_error;
if (!found_rec)
@@ -635,11 +658,9 @@ xfs_refcount_find_left_extents(
goto out_error;
}
- if (xfs_refc_next(&tmp) != agbno)
- return 0;
- if ((flags & XFS_FIND_RCEXT_SHARED) && tmp.rc_refcount < 2)
+ if (tmp.rc_domain != domain)
return 0;
- if ((flags & XFS_FIND_RCEXT_COW) && tmp.rc_refcount > 1)
+ if (xfs_refc_next(&tmp) != agbno)
return 0;
/* We have a left extent; retrieve (or invent) the next right one */
*left = tmp;
@@ -656,6 +677,9 @@ xfs_refcount_find_left_extents(
goto out_error;
}
+ if (tmp.rc_domain != domain)
+ goto not_found;
+
/* if tmp starts at the end of our range, just use that */
if (tmp.rc_startblock == agbno)
*cleft = tmp;
@@ -672,8 +696,10 @@ xfs_refcount_find_left_extents(
cleft->rc_blockcount = min(aglen,
tmp.rc_startblock - agbno);
cleft->rc_refcount = 1;
+ cleft->rc_domain = domain;
}
} else {
+not_found:
/*
* No extents, so pretend that there's one covering the whole
* range.
@@ -681,6 +707,7 @@ xfs_refcount_find_left_extents(
cleft->rc_startblock = agbno;
cleft->rc_blockcount = aglen;
cleft->rc_refcount = 1;
+ cleft->rc_domain = domain;
}
trace_xfs_refcount_find_left_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno,
left, cleft, agbno);
@@ -701,16 +728,16 @@ xfs_refcount_find_right_extents(
struct xfs_btree_cur *cur,
struct xfs_refcount_irec *right,
struct xfs_refcount_irec *cright,
+ enum xfs_refc_domain domain,
xfs_agblock_t agbno,
- xfs_extlen_t aglen,
- int flags)
+ xfs_extlen_t aglen)
{
struct xfs_refcount_irec tmp;
int error;
int found_rec;
right->rc_startblock = cright->rc_startblock = NULLAGBLOCK;
- error = xfs_refcount_lookup_ge(cur, agbno + aglen, &found_rec);
+ error = xfs_refcount_lookup_ge(cur, domain, agbno + aglen, &found_rec);
if (error)
goto out_error;
if (!found_rec)
@@ -724,11 +751,9 @@ xfs_refcount_find_right_extents(
goto out_error;
}
- if (tmp.rc_startblock != agbno + aglen)
- return 0;
- if ((flags & XFS_FIND_RCEXT_SHARED) && tmp.rc_refcount < 2)
+ if (tmp.rc_domain != domain)
return 0;
- if ((flags & XFS_FIND_RCEXT_COW) && tmp.rc_refcount > 1)
+ if (tmp.rc_startblock != agbno + aglen)
return 0;
/* We have a right extent; retrieve (or invent) the next left one */
*right = tmp;
@@ -745,6 +770,9 @@ xfs_refcount_find_right_extents(
goto out_error;
}
+ if (tmp.rc_domain != domain)
+ goto not_found;
+
/* if tmp ends at the end of our range, just use that */
if (xfs_refc_next(&tmp) == agbno + aglen)
*cright = tmp;
@@ -761,8 +789,10 @@ xfs_refcount_find_right_extents(
cright->rc_blockcount = right->rc_startblock -
cright->rc_startblock;
cright->rc_refcount = 1;
+ cright->rc_domain = domain;
}
} else {
+not_found:
/*
* No extents, so pretend that there's one covering the whole
* range.
@@ -770,6 +800,7 @@ xfs_refcount_find_right_extents(
cright->rc_startblock = agbno;
cright->rc_blockcount = aglen;
cright->rc_refcount = 1;
+ cright->rc_domain = domain;
}
trace_xfs_refcount_find_right_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno,
cright, right, agbno + aglen);
@@ -795,10 +826,10 @@ xfs_refc_valid(
STATIC int
xfs_refcount_merge_extents(
struct xfs_btree_cur *cur,
+ enum xfs_refc_domain domain,
xfs_agblock_t *agbno,
xfs_extlen_t *aglen,
enum xfs_refc_adjust_op adjust,
- int flags,
bool *shape_changed)
{
struct xfs_refcount_irec left = {0}, cleft = {0};
@@ -813,12 +844,12 @@ xfs_refcount_merge_extents(
* just below (agbno + aglen) [cright], and just above (agbno + aglen)
* [right].
*/
- error = xfs_refcount_find_left_extents(cur, &left, &cleft, *agbno,
- *aglen, flags);
+ error = xfs_refcount_find_left_extents(cur, &left, &cleft, domain,
+ *agbno, *aglen);
if (error)
return error;
- error = xfs_refcount_find_right_extents(cur, &right, &cright, *agbno,
- *aglen, flags);
+ error = xfs_refcount_find_right_extents(cur, &right, &cright, domain,
+ *agbno, *aglen);
if (error)
return error;
@@ -871,7 +902,7 @@ xfs_refcount_merge_extents(
aglen);
}
- return error;
+ return 0;
}
/*
@@ -886,8 +917,13 @@ xfs_refcount_still_have_space(
{
unsigned long overhead;
- overhead = cur->bc_ag.refc.shape_changes *
- xfs_allocfree_log_count(cur->bc_mp, 1);
+ /*
+ * Worst case estimate: full splits of the free space and rmap btrees
+ * 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);
+ overhead += cur->bc_mp->m_refc_maxlevels;
overhead *= cur->bc_mp->m_sb.sb_blocksize;
/*
@@ -929,7 +965,8 @@ xfs_refcount_adjust_extents(
if (*aglen == 0)
return 0;
- error = xfs_refcount_lookup_ge(cur, *agbno, &found_rec);
+ error = xfs_refcount_lookup_ge(cur, XFS_REFC_DOMAIN_SHARED, *agbno,
+ &found_rec);
if (error)
goto out_error;
@@ -937,10 +974,11 @@ xfs_refcount_adjust_extents(
error = xfs_refcount_get_rec(cur, &ext, &found_rec);
if (error)
goto out_error;
- if (!found_rec) {
+ if (!found_rec || ext.rc_domain != XFS_REFC_DOMAIN_SHARED) {
ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks;
ext.rc_blockcount = 0;
ext.rc_refcount = 0;
+ ext.rc_domain = XFS_REFC_DOMAIN_SHARED;
}
/*
@@ -953,6 +991,8 @@ xfs_refcount_adjust_extents(
tmp.rc_blockcount = min(*aglen,
ext.rc_startblock - *agbno);
tmp.rc_refcount = 1 + adj;
+ tmp.rc_domain = XFS_REFC_DOMAIN_SHARED;
+
trace_xfs_refcount_modify_extent(cur->bc_mp,
cur->bc_ag.pag->pag_agno, &tmp);
@@ -960,6 +1000,7 @@ xfs_refcount_adjust_extents(
* Either cover the hole (increment) or
* delete the range (decrement).
*/
+ cur->bc_ag.refc.nr_ops++;
if (tmp.rc_refcount) {
error = xfs_refcount_insert(cur, &tmp,
&found_tmp);
@@ -970,7 +1011,6 @@ xfs_refcount_adjust_extents(
error = -EFSCORRUPTED;
goto out_error;
}
- cur->bc_ag.refc.nr_ops++;
} else {
fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
cur->bc_ag.pag->pag_agno,
@@ -982,15 +1022,30 @@ xfs_refcount_adjust_extents(
(*agbno) += tmp.rc_blockcount;
(*aglen) -= tmp.rc_blockcount;
- error = xfs_refcount_lookup_ge(cur, *agbno,
+ /* Stop if there's nothing left to modify */
+ if (*aglen == 0 || !xfs_refcount_still_have_space(cur))
+ break;
+
+ /* Move the cursor to the start of ext. */
+ error = xfs_refcount_lookup_ge(cur,
+ XFS_REFC_DOMAIN_SHARED, *agbno,
&found_rec);
if (error)
goto out_error;
}
- /* Stop if there's nothing left to modify */
- if (*aglen == 0 || !xfs_refcount_still_have_space(cur))
- break;
+ /*
+ * A previous step trimmed agbno/aglen such that the end of the
+ * range would not be in the middle of the record. If this is
+ * no longer the case, something is seriously wrong with the
+ * btree. Make sure we never feed the synthesized record into
+ * the processing loop below.
+ */
+ if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount == 0) ||
+ XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount > *aglen)) {
+ error = -EFSCORRUPTED;
+ goto out_error;
+ }
/*
* Adjust the reference count and either update the tree
@@ -1001,11 +1056,11 @@ 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++;
if (ext.rc_refcount > 1) {
error = xfs_refcount_update(cur, &ext);
if (error)
goto out_error;
- cur->bc_ag.refc.nr_ops++;
} else if (ext.rc_refcount == 1) {
error = xfs_refcount_delete(cur, &found_rec);
if (error)
@@ -1014,7 +1069,6 @@ xfs_refcount_adjust_extents(
error = -EFSCORRUPTED;
goto out_error;
}
- cur->bc_ag.refc.nr_ops++;
goto advloop;
} else {
fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
@@ -1067,13 +1121,15 @@ xfs_refcount_adjust(
/*
* Ensure that no rcextents cross the boundary of the adjustment range.
*/
- error = xfs_refcount_split_extent(cur, agbno, &shape_changed);
+ error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED,
+ agbno, &shape_changed);
if (error)
goto out_error;
if (shape_changed)
shape_changes++;
- error = xfs_refcount_split_extent(cur, agbno + aglen, &shape_changed);
+ error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED,
+ agbno + aglen, &shape_changed);
if (error)
goto out_error;
if (shape_changed)
@@ -1082,8 +1138,8 @@ xfs_refcount_adjust(
/*
* Try to merge with the left or right extents of the range.
*/
- error = xfs_refcount_merge_extents(cur, new_agbno, new_aglen, adj,
- XFS_FIND_RCEXT_SHARED, &shape_changed);
+ error = xfs_refcount_merge_extents(cur, XFS_REFC_DOMAIN_SHARED,
+ new_agbno, new_aglen, adj, &shape_changed);
if (error)
goto out_error;
if (shape_changed)
@@ -1122,6 +1178,32 @@ xfs_refcount_finish_one_cleanup(
}
/*
+ * Set up a continuation a deferred refcount operation by updating the intent.
+ * Checks to make sure we're not going to run off the end of the AG.
+ */
+static inline int
+xfs_refcount_continue_op(
+ struct xfs_btree_cur *cur,
+ xfs_fsblock_t startblock,
+ xfs_agblock_t new_agbno,
+ xfs_extlen_t new_len,
+ xfs_fsblock_t *new_fsbno)
+{
+ struct xfs_mount *mp = cur->bc_mp;
+ struct xfs_perag *pag = cur->bc_ag.pag;
+
+ if (XFS_IS_CORRUPT(mp, !xfs_verify_agbext(pag, new_agbno, new_len)))
+ return -EFSCORRUPTED;
+
+ *new_fsbno = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
+
+ ASSERT(xfs_verify_fsbext(mp, *new_fsbno, new_len));
+ ASSERT(pag->pag_agno == XFS_FSB_TO_AGNO(mp, *new_fsbno));
+
+ return 0;
+}
+
+/*
* Process one of the deferred refcount operations. We pass back the
* btree cursor to maintain our lock on the btree between calls.
* This saves time and eliminates a buffer deadlock between the
@@ -1173,8 +1255,8 @@ xfs_refcount_finish_one(
*pcur = NULL;
}
if (rcur == NULL) {
- error = xfs_alloc_read_agf(tp->t_mountp, tp, pag->pag_agno,
- XFS_ALLOC_FLAG_FREEING, &agbp);
+ error = xfs_alloc_read_agf(pag, tp, XFS_ALLOC_FLAG_FREEING,
+ &agbp);
if (error)
goto out_drop;
@@ -1188,12 +1270,20 @@ xfs_refcount_finish_one(
case XFS_REFCOUNT_INCREASE:
error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
new_len, XFS_REFCOUNT_ADJUST_INCREASE);
- *new_fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
+ if (error)
+ goto out_drop;
+ if (*new_len > 0)
+ error = xfs_refcount_continue_op(rcur, startblock,
+ new_agbno, *new_len, new_fsb);
break;
case XFS_REFCOUNT_DECREASE:
error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
new_len, XFS_REFCOUNT_ADJUST_DECREASE);
- *new_fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
+ if (error)
+ goto out_drop;
+ if (*new_len > 0)
+ error = xfs_refcount_continue_op(rcur, startblock,
+ new_agbno, *new_len, new_fsb);
break;
case XFS_REFCOUNT_ALLOC_COW:
*new_fsb = startblock + blockcount;
@@ -1304,7 +1394,8 @@ xfs_refcount_find_shared(
*flen = 0;
/* Try to find a refcount extent that crosses the start */
- error = xfs_refcount_lookup_le(cur, agbno, &have);
+ error = xfs_refcount_lookup_le(cur, XFS_REFC_DOMAIN_SHARED, agbno,
+ &have);
if (error)
goto out_error;
if (!have) {
@@ -1322,6 +1413,8 @@ xfs_refcount_find_shared(
error = -EFSCORRUPTED;
goto out_error;
}
+ if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED)
+ goto done;
/* If the extent ends before the start, look at the next one */
if (tmp.rc_startblock + tmp.rc_blockcount <= agbno) {
@@ -1337,6 +1430,8 @@ xfs_refcount_find_shared(
error = -EFSCORRUPTED;
goto out_error;
}
+ if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED)
+ goto done;
}
/* If the extent starts after the range we want, bail out */
@@ -1368,7 +1463,8 @@ xfs_refcount_find_shared(
error = -EFSCORRUPTED;
goto out_error;
}
- if (tmp.rc_startblock >= agbno + aglen ||
+ if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED ||
+ tmp.rc_startblock >= agbno + aglen ||
tmp.rc_startblock != *fbno + *flen)
break;
*flen = min(*flen + tmp.rc_blockcount, agbno + aglen - *fbno);
@@ -1452,17 +1548,23 @@ xfs_refcount_adjust_cow_extents(
return 0;
/* Find any overlapping refcount records */
- error = xfs_refcount_lookup_ge(cur, agbno, &found_rec);
+ error = xfs_refcount_lookup_ge(cur, XFS_REFC_DOMAIN_COW, agbno,
+ &found_rec);
if (error)
goto out_error;
error = xfs_refcount_get_rec(cur, &ext, &found_rec);
if (error)
goto out_error;
+ if (XFS_IS_CORRUPT(cur->bc_mp, found_rec &&
+ ext.rc_domain != XFS_REFC_DOMAIN_COW)) {
+ error = -EFSCORRUPTED;
+ goto out_error;
+ }
if (!found_rec) {
- ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks +
- XFS_REFC_COW_START;
+ ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks;
ext.rc_blockcount = 0;
ext.rc_refcount = 0;
+ ext.rc_domain = XFS_REFC_DOMAIN_COW;
}
switch (adj) {
@@ -1477,6 +1579,8 @@ xfs_refcount_adjust_cow_extents(
tmp.rc_startblock = agbno;
tmp.rc_blockcount = aglen;
tmp.rc_refcount = 1;
+ tmp.rc_domain = XFS_REFC_DOMAIN_COW;
+
trace_xfs_refcount_modify_extent(cur->bc_mp,
cur->bc_ag.pag->pag_agno, &tmp);
@@ -1539,24 +1643,24 @@ xfs_refcount_adjust_cow(
bool shape_changed;
int error;
- agbno += XFS_REFC_COW_START;
-
/*
* Ensure that no rcextents cross the boundary of the adjustment range.
*/
- error = xfs_refcount_split_extent(cur, agbno, &shape_changed);
+ error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_COW,
+ agbno, &shape_changed);
if (error)
goto out_error;
- error = xfs_refcount_split_extent(cur, agbno + aglen, &shape_changed);
+ error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_COW,
+ agbno + aglen, &shape_changed);
if (error)
goto out_error;
/*
* Try to merge with the left or right extents of the range.
*/
- error = xfs_refcount_merge_extents(cur, &agbno, &aglen, adj,
- XFS_FIND_RCEXT_COW, &shape_changed);
+ error = xfs_refcount_merge_extents(cur, XFS_REFC_DOMAIN_COW, &agbno,
+ &aglen, adj, &shape_changed);
if (error)
goto out_error;
@@ -1663,10 +1767,18 @@ xfs_refcount_recover_extent(
be32_to_cpu(rec->refc.rc_refcount) != 1))
return -EFSCORRUPTED;
- rr = kmem_alloc(sizeof(struct xfs_refcount_recovery), 0);
+ rr = kmalloc(sizeof(struct xfs_refcount_recovery),
+ GFP_KERNEL | __GFP_NOFAIL);
+ INIT_LIST_HEAD(&rr->rr_list);
xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec);
- list_add_tail(&rr->rr_list, debris);
+ if (XFS_IS_CORRUPT(cur->bc_mp,
+ rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) {
+ kfree(rr);
+ return -EFSCORRUPTED;
+ }
+
+ list_add_tail(&rr->rr_list, debris);
return 0;
}
@@ -1684,10 +1796,11 @@ xfs_refcount_recover_cow_leftovers(
union xfs_btree_irec low;
union xfs_btree_irec high;
xfs_fsblock_t fsb;
- xfs_agblock_t agbno;
int error;
- if (mp->m_sb.sb_agblocks >= XFS_REFC_COW_START)
+ /* reflink filesystems mustn't have AGs larger than 2^31-1 blocks */
+ BUILD_BUG_ON(XFS_MAX_CRC_AG_BLOCKS >= XFS_REFC_COWFLAG);
+ if (mp->m_sb.sb_agblocks > XFS_MAX_CRC_AG_BLOCKS)
return -EOPNOTSUPP;
INIT_LIST_HEAD(&debris);
@@ -1706,7 +1819,7 @@ xfs_refcount_recover_cow_leftovers(
if (error)
return error;
- error = xfs_alloc_read_agf(mp, tp, pag->pag_agno, 0, &agbp);
+ error = xfs_alloc_read_agf(pag, tp, 0, &agbp);
if (error)
goto out_trans;
cur = xfs_refcountbt_init_cursor(mp, tp, agbp, pag);
@@ -1714,7 +1827,7 @@ xfs_refcount_recover_cow_leftovers(
/* Find all the leftover CoW staging extents. */
memset(&low, 0, sizeof(low));
memset(&high, 0, sizeof(high));
- low.rc.rc_startblock = XFS_REFC_COW_START;
+ low.rc.rc_domain = high.rc.rc_domain = XFS_REFC_DOMAIN_COW;
high.rc.rc_startblock = -1U;
error = xfs_btree_query_range(cur, &low, &high,
xfs_refcount_recover_extent, &debris);
@@ -1735,8 +1848,8 @@ xfs_refcount_recover_cow_leftovers(
&rr->rr_rrec);
/* Free the orphan record */
- agbno = rr->rr_rrec.rc_startblock - XFS_REFC_COW_START;
- fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, agbno);
+ fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno,
+ rr->rr_rrec.rc_startblock);
xfs_refcount_free_cow_extent(tp, fsb,
rr->rr_rrec.rc_blockcount);
@@ -1748,7 +1861,7 @@ xfs_refcount_recover_cow_leftovers(
goto out_free;
list_del(&rr->rr_list);
- kmem_free(rr);
+ kfree(rr);
}
return error;
@@ -1758,7 +1871,7 @@ out_free:
/* Free the leftover list */
list_for_each_entry_safe(rr, n, &debris, rr_list) {
list_del(&rr->rr_list);
- kmem_free(rr);
+ kfree(rr);
}
return error;
}
@@ -1767,6 +1880,7 @@ out_free:
int
xfs_refcount_has_record(
struct xfs_btree_cur *cur,
+ enum xfs_refc_domain domain,
xfs_agblock_t bno,
xfs_extlen_t len,
bool *exists)
@@ -1778,6 +1892,7 @@ xfs_refcount_has_record(
low.rc.rc_startblock = bno;
memset(&high, 0xFF, sizeof(high));
high.rc.rc_startblock = bno + len - 1;
+ low.rc.rc_domain = high.rc.rc_domain = domain;
return xfs_btree_has_record(cur, &low, &high, exists);
}
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index 9eb01edbd89d..452f30556f5a 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -14,14 +14,33 @@ struct xfs_bmbt_irec;
struct xfs_refcount_irec;
extern int xfs_refcount_lookup_le(struct xfs_btree_cur *cur,
- xfs_agblock_t bno, int *stat);
+ enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat);
extern int xfs_refcount_lookup_ge(struct xfs_btree_cur *cur,
- xfs_agblock_t bno, int *stat);
+ enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat);
extern int xfs_refcount_lookup_eq(struct xfs_btree_cur *cur,
- xfs_agblock_t bno, int *stat);
+ enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat);
extern int xfs_refcount_get_rec(struct xfs_btree_cur *cur,
struct xfs_refcount_irec *irec, int *stat);
+static inline uint32_t
+xfs_refcount_encode_startblock(
+ xfs_agblock_t startblock,
+ enum xfs_refc_domain domain)
+{
+ uint32_t start;
+
+ /*
+ * low level btree operations need to handle the generic btree range
+ * query functions (which set rc_domain == -1U), so we check that the
+ * domain is /not/ shared.
+ */
+ start = startblock & ~XFS_REFC_COWFLAG;
+ if (domain != XFS_REFC_DOMAIN_SHARED)
+ start |= XFS_REFC_COWFLAG;
+
+ return start;
+}
+
enum xfs_refcount_intent_type {
XFS_REFCOUNT_INCREASE = 1,
XFS_REFCOUNT_DECREASE,
@@ -36,6 +55,18 @@ struct xfs_refcount_intent {
xfs_fsblock_t ri_startblock;
};
+/* Check that the refcount is appropriate for the record domain. */
+static inline bool
+xfs_refcount_check_domain(
+ const struct xfs_refcount_irec *irec)
+{
+ if (irec->rc_domain == XFS_REFC_DOMAIN_COW && irec->rc_refcount != 1)
+ return false;
+ if (irec->rc_domain == XFS_REFC_DOMAIN_SHARED && irec->rc_refcount < 2)
+ return false;
+ return true;
+}
+
void xfs_refcount_increase_extent(struct xfs_trans *tp,
struct xfs_bmbt_irec *irec);
void xfs_refcount_decrease_extent(struct xfs_trans *tp,
@@ -67,16 +98,20 @@ extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp,
* log (plus any key updates) so we'll conservatively assume 32 bytes
* per record. We must also leave space for btree splits on both ends
* of the range and space for the CUD and a new CUI.
+ *
+ * Each EFI that we attach to the transaction is assumed to consume ~32 bytes.
+ * This is a low estimate for an EFI tracking a single extent (16 bytes for the
+ * EFI header, 16 for the extent, and 12 for the xlog op header), but the
+ * estimate is acceptable if there's more than one extent being freed.
+ * In the worst case of freeing every other block during a refcount decrease
+ * operation, we amortize the space used for one EFI log item across 16
+ * extents.
*/
#define XFS_REFCOUNT_ITEM_OVERHEAD 32
-static inline xfs_fileoff_t xfs_refcount_max_unmap(int log_res)
-{
- return (log_res * 3 / 4) / XFS_REFCOUNT_ITEM_OVERHEAD;
-}
-
extern int xfs_refcount_has_record(struct xfs_btree_cur *cur,
- xfs_agblock_t bno, xfs_extlen_t len, bool *exists);
+ enum xfs_refc_domain domain, xfs_agblock_t bno,
+ xfs_extlen_t len, bool *exists);
union xfs_btree_rec;
extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec,
struct xfs_refcount_irec *irec);
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index d14c1720b0fb..e1f789866683 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -13,6 +13,7 @@
#include "xfs_btree.h"
#include "xfs_btree_staging.h"
#include "xfs_refcount_btree.h"
+#include "xfs_refcount.h"
#include "xfs_alloc.h"
#include "xfs_error.h"
#include "xfs_trace.h"
@@ -160,7 +161,12 @@ xfs_refcountbt_init_rec_from_cur(
struct xfs_btree_cur *cur,
union xfs_btree_rec *rec)
{
- rec->refc.rc_startblock = cpu_to_be32(cur->bc_rec.rc.rc_startblock);
+ const struct xfs_refcount_irec *irec = &cur->bc_rec.rc;
+ uint32_t start;
+
+ start = xfs_refcount_encode_startblock(irec->rc_startblock,
+ irec->rc_domain);
+ rec->refc.rc_startblock = cpu_to_be32(start);
rec->refc.rc_blockcount = cpu_to_be32(cur->bc_rec.rc.rc_blockcount);
rec->refc.rc_refcount = cpu_to_be32(cur->bc_rec.rc.rc_refcount);
}
@@ -182,10 +188,13 @@ xfs_refcountbt_key_diff(
struct xfs_btree_cur *cur,
const union xfs_btree_key *key)
{
- struct xfs_refcount_irec *rec = &cur->bc_rec.rc;
const struct xfs_refcount_key *kp = &key->refc;
+ const struct xfs_refcount_irec *irec = &cur->bc_rec.rc;
+ uint32_t start;
- return (int64_t)be32_to_cpu(kp->rc_startblock) - rec->rc_startblock;
+ start = xfs_refcount_encode_startblock(irec->rc_startblock,
+ irec->rc_domain);
+ return (int64_t)be32_to_cpu(kp->rc_startblock) - start;
}
STATIC int64_t
@@ -493,7 +502,7 @@ xfs_refcountbt_calc_reserves(
if (!xfs_has_reflink(mp))
return 0;
- error = xfs_alloc_read_agf(mp, tp, pag->pag_agno, 0, &agbp);
+ error = xfs_alloc_read_agf(pag, tp, 0, &agbp);
if (error)
return error;
@@ -507,8 +516,7 @@ xfs_refcountbt_calc_reserves(
* never be available for the kinds of things that would require btree
* expansion. We therefore can pretend the space isn't there.
*/
- if (mp->m_sb.sb_logstart &&
- XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart) == pag->pag_agno)
+ if (xfs_ag_contains_log(mp, pag->pag_agno))
agblocks -= mp->m_sb.sb_logblocks;
*ask += xfs_refcountbt_max_size(mp, agblocks);
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index cd322174dbff..b56aca1e7c66 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -34,18 +34,32 @@ int
xfs_rmap_lookup_le(
struct xfs_btree_cur *cur,
xfs_agblock_t bno,
- xfs_extlen_t len,
uint64_t owner,
uint64_t offset,
unsigned int flags,
+ struct xfs_rmap_irec *irec,
int *stat)
{
+ int get_stat = 0;
+ int error;
+
cur->bc_rec.r.rm_startblock = bno;
- cur->bc_rec.r.rm_blockcount = len;
+ cur->bc_rec.r.rm_blockcount = 0;
cur->bc_rec.r.rm_owner = owner;
cur->bc_rec.r.rm_offset = offset;
cur->bc_rec.r.rm_flags = flags;
- return xfs_btree_lookup(cur, XFS_LOOKUP_LE, stat);
+
+ error = xfs_btree_lookup(cur, XFS_LOOKUP_LE, stat);
+ if (error || !(*stat) || !irec)
+ return error;
+
+ error = xfs_rmap_get_rec(cur, irec, &get_stat);
+ if (error)
+ return error;
+ if (!get_stat)
+ return -EFSCORRUPTED;
+
+ return 0;
}
/*
@@ -201,7 +215,7 @@ xfs_rmap_get_rec(
int *stat)
{
struct xfs_mount *mp = cur->bc_mp;
- xfs_agnumber_t agno = cur->bc_ag.pag->pag_agno;
+ struct xfs_perag *pag = cur->bc_ag.pag;
union xfs_btree_rec *rec;
int error;
@@ -221,13 +235,8 @@ xfs_rmap_get_rec(
goto out_bad_rec;
} else {
/* check for valid extent range, including overflow */
- if (!xfs_verify_agbno(mp, agno, irec->rm_startblock))
- goto out_bad_rec;
- if (irec->rm_startblock >
- irec->rm_startblock + irec->rm_blockcount)
- goto out_bad_rec;
- if (!xfs_verify_agbno(mp, agno,
- irec->rm_startblock + irec->rm_blockcount - 1))
+ if (!xfs_verify_agbext(pag, irec->rm_startblock,
+ irec->rm_blockcount))
goto out_bad_rec;
}
@@ -240,7 +249,7 @@ xfs_rmap_get_rec(
out_bad_rec:
xfs_warn(mp,
"Reverse Mapping BTree record corruption in AG %d detected!",
- agno);
+ pag->pag_agno);
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,
@@ -251,7 +260,6 @@ out_bad_rec:
struct xfs_find_left_neighbor_info {
struct xfs_rmap_irec high;
struct xfs_rmap_irec *irec;
- int *stat;
};
/* For each rmap given, figure out if it matches the key we want. */
@@ -276,7 +284,6 @@ xfs_rmap_find_left_neighbor_helper(
return 0;
*info->irec = *rec;
- *info->stat = 1;
return -ECANCELED;
}
@@ -285,7 +292,7 @@ xfs_rmap_find_left_neighbor_helper(
* return a match with the same owner and adjacent physical and logical
* block ranges.
*/
-int
+STATIC int
xfs_rmap_find_left_neighbor(
struct xfs_btree_cur *cur,
xfs_agblock_t bno,
@@ -296,6 +303,7 @@ xfs_rmap_find_left_neighbor(
int *stat)
{
struct xfs_find_left_neighbor_info info;
+ int found = 0;
int error;
*stat = 0;
@@ -313,21 +321,44 @@ xfs_rmap_find_left_neighbor(
info.high.rm_flags = flags;
info.high.rm_blockcount = 0;
info.irec = irec;
- info.stat = stat;
trace_xfs_rmap_find_left_neighbor_query(cur->bc_mp,
cur->bc_ag.pag->pag_agno, bno, 0, owner, offset, flags);
- error = xfs_rmap_query_range(cur, &info.high, &info.high,
- xfs_rmap_find_left_neighbor_helper, &info);
- if (error == -ECANCELED)
- error = 0;
- if (*stat)
- trace_xfs_rmap_find_left_neighbor_result(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, irec->rm_startblock,
- irec->rm_blockcount, irec->rm_owner,
- irec->rm_offset, irec->rm_flags);
- return error;
+ /*
+ * Historically, we always used the range query to walk every reverse
+ * mapping that could possibly overlap the key that the caller asked
+ * for, and filter out the ones that don't. That is very slow when
+ * there are a lot of records.
+ *
+ * However, there are two scenarios where the classic btree search can
+ * produce correct results -- if the index contains a record that is an
+ * exact match for the lookup key; and if there are no other records
+ * between the record we want and the key we supplied.
+ *
+ * As an optimization, try a non-overlapped lookup first. This makes
+ * extent conversion and remap operations run a bit faster if the
+ * physical extents aren't being shared. If we don't find what we
+ * want, we fall back to the overlapped query.
+ */
+ error = xfs_rmap_lookup_le(cur, bno, owner, offset, flags, irec,
+ &found);
+ if (error)
+ return error;
+ if (found)
+ error = xfs_rmap_find_left_neighbor_helper(cur, irec, &info);
+ if (!error)
+ error = xfs_rmap_query_range(cur, &info.high, &info.high,
+ xfs_rmap_find_left_neighbor_helper, &info);
+ if (error != -ECANCELED)
+ return error;
+
+ *stat = 1;
+ trace_xfs_rmap_find_left_neighbor_result(cur->bc_mp,
+ cur->bc_ag.pag->pag_agno, irec->rm_startblock,
+ irec->rm_blockcount, irec->rm_owner, irec->rm_offset,
+ irec->rm_flags);
+ return 0;
}
/* For each rmap given, figure out if it matches the key we want. */
@@ -353,7 +384,6 @@ xfs_rmap_lookup_le_range_helper(
return 0;
*info->irec = *rec;
- *info->stat = 1;
return -ECANCELED;
}
@@ -374,6 +404,7 @@ xfs_rmap_lookup_le_range(
int *stat)
{
struct xfs_find_left_neighbor_info info;
+ int found = 0;
int error;
info.high.rm_startblock = bno;
@@ -386,20 +417,44 @@ xfs_rmap_lookup_le_range(
info.high.rm_blockcount = 0;
*stat = 0;
info.irec = irec;
- info.stat = stat;
- trace_xfs_rmap_lookup_le_range(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, bno, 0, owner, offset, flags);
- error = xfs_rmap_query_range(cur, &info.high, &info.high,
- xfs_rmap_lookup_le_range_helper, &info);
- if (error == -ECANCELED)
- error = 0;
- if (*stat)
- trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, irec->rm_startblock,
- irec->rm_blockcount, irec->rm_owner,
- irec->rm_offset, irec->rm_flags);
- return error;
+ trace_xfs_rmap_lookup_le_range(cur->bc_mp, cur->bc_ag.pag->pag_agno,
+ bno, 0, owner, offset, flags);
+
+ /*
+ * Historically, we always used the range query to walk every reverse
+ * mapping that could possibly overlap the key that the caller asked
+ * for, and filter out the ones that don't. That is very slow when
+ * there are a lot of records.
+ *
+ * However, there are two scenarios where the classic btree search can
+ * produce correct results -- if the index contains a record that is an
+ * exact match for the lookup key; and if there are no other records
+ * between the record we want and the key we supplied.
+ *
+ * As an optimization, try a non-overlapped lookup first. This makes
+ * scrub run much faster on most filesystems because bmbt records are
+ * usually an exact match for rmap records. If we don't find what we
+ * want, we fall back to the overlapped query.
+ */
+ error = xfs_rmap_lookup_le(cur, bno, owner, offset, flags, irec,
+ &found);
+ if (error)
+ return error;
+ if (found)
+ error = xfs_rmap_lookup_le_range_helper(cur, irec, &info);
+ if (!error)
+ error = xfs_rmap_query_range(cur, &info.high, &info.high,
+ xfs_rmap_lookup_le_range_helper, &info);
+ if (error != -ECANCELED)
+ return error;
+
+ *stat = 1;
+ trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
+ cur->bc_ag.pag->pag_agno, irec->rm_startblock,
+ irec->rm_blockcount, irec->rm_owner, irec->rm_offset,
+ irec->rm_flags);
+ return 0;
}
/*
@@ -510,7 +565,7 @@ xfs_rmap_unmap(
* for the AG headers at rm_startblock == 0 created by mkfs/growfs that
* will not ever be removed from the tree.
*/
- error = xfs_rmap_lookup_le(cur, bno, len, owner, offset, flags, &i);
+ error = xfs_rmap_lookup_le(cur, bno, owner, offset, flags, &ltrec, &i);
if (error)
goto out_error;
if (XFS_IS_CORRUPT(mp, i != 1)) {
@@ -518,13 +573,6 @@ xfs_rmap_unmap(
goto out_error;
}
- error = xfs_rmap_get_rec(cur, &ltrec, &i);
- if (error)
- goto out_error;
- if (XFS_IS_CORRUPT(mp, i != 1)) {
- error = -EFSCORRUPTED;
- goto out_error;
- }
trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
cur->bc_ag.pag->pag_agno, ltrec.rm_startblock,
ltrec.rm_blockcount, ltrec.rm_owner,
@@ -786,18 +834,11 @@ xfs_rmap_map(
* record for our insertion point. This will also give us the record for
* start block contiguity tests.
*/
- error = xfs_rmap_lookup_le(cur, bno, len, owner, offset, flags,
+ error = xfs_rmap_lookup_le(cur, bno, owner, offset, flags, &ltrec,
&have_lt);
if (error)
goto out_error;
if (have_lt) {
- error = xfs_rmap_get_rec(cur, &ltrec, &have_lt);
- if (error)
- goto out_error;
- if (XFS_IS_CORRUPT(mp, have_lt != 1)) {
- error = -EFSCORRUPTED;
- goto out_error;
- }
trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
cur->bc_ag.pag->pag_agno, ltrec.rm_startblock,
ltrec.rm_blockcount, ltrec.rm_owner,
@@ -1022,7 +1063,7 @@ xfs_rmap_convert(
* record for our insertion point. This will also give us the record for
* start block contiguity tests.
*/
- error = xfs_rmap_lookup_le(cur, bno, len, owner, offset, oldext, &i);
+ error = xfs_rmap_lookup_le(cur, bno, owner, offset, oldext, &PREV, &i);
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
@@ -1030,13 +1071,6 @@ xfs_rmap_convert(
goto done;
}
- error = xfs_rmap_get_rec(cur, &PREV, &i);
- if (error)
- goto done;
- if (XFS_IS_CORRUPT(mp, i != 1)) {
- error = -EFSCORRUPTED;
- goto done;
- }
trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
cur->bc_ag.pag->pag_agno, PREV.rm_startblock,
PREV.rm_blockcount, PREV.rm_owner,
@@ -1140,7 +1174,7 @@ xfs_rmap_convert(
_RET_IP_);
/* reset the cursor back to PREV */
- error = xfs_rmap_lookup_le(cur, bno, len, owner, offset, oldext, &i);
+ error = xfs_rmap_lookup_le(cur, bno, owner, offset, oldext, NULL, &i);
if (error)
goto done;
if (XFS_IS_CORRUPT(mp, i != 1)) {
@@ -2677,7 +2711,7 @@ xfs_rmap_record_exists(
ASSERT(XFS_RMAP_NON_INODE_OWNER(owner) ||
(flags & XFS_RMAP_BMBT_BLOCK));
- error = xfs_rmap_lookup_le(cur, bno, len, owner, offset, flags,
+ error = xfs_rmap_lookup_le(cur, bno, owner, offset, flags, &irec,
&has_record);
if (error)
return error;
@@ -2686,14 +2720,6 @@ xfs_rmap_record_exists(
return 0;
}
- error = xfs_rmap_get_rec(cur, &irec, &has_record);
- if (error)
- return error;
- if (!has_record) {
- *has_rmap = false;
- return 0;
- }
-
*has_rmap = (irec.rm_owner == owner && irec.rm_startblock <= bno &&
irec.rm_startblock + irec.rm_blockcount >= bno + len);
return 0;
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index b718ebeda372..54741a591a17 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -122,8 +122,8 @@ int xfs_rmap_free(struct xfs_trans *tp, struct xfs_buf *agbp,
const struct xfs_owner_info *oinfo);
int xfs_rmap_lookup_le(struct xfs_btree_cur *cur, xfs_agblock_t bno,
- xfs_extlen_t len, uint64_t owner, uint64_t offset,
- unsigned int flags, int *stat);
+ uint64_t owner, uint64_t offset, unsigned int flags,
+ struct xfs_rmap_irec *irec, int *stat);
int xfs_rmap_lookup_eq(struct xfs_btree_cur *cur, xfs_agblock_t bno,
xfs_extlen_t len, uint64_t owner, uint64_t offset,
unsigned int flags, int *stat);
@@ -184,9 +184,6 @@ int xfs_rmap_finish_one(struct xfs_trans *tp, enum xfs_rmap_intent_type type,
xfs_fsblock_t startblock, xfs_filblks_t blockcount,
xfs_exntst_t state, struct xfs_btree_cur **pcur);
-int xfs_rmap_find_left_neighbor(struct xfs_btree_cur *cur, xfs_agblock_t bno,
- uint64_t owner, uint64_t offset, unsigned int flags,
- struct xfs_rmap_irec *irec, int *stat);
int xfs_rmap_lookup_le_range(struct xfs_btree_cur *cur, xfs_agblock_t bno,
uint64_t owner, uint64_t offset, unsigned int flags,
struct xfs_rmap_irec *irec, int *stat);
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 69e104d0277f..7f83f62e51e0 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -90,7 +90,7 @@ xfs_rmapbt_alloc_block(
xfs_agblock_t bno;
/* Allocate the new block from the freelist. If we can't, give up. */
- error = xfs_alloc_get_freelist(cur->bc_tp, cur->bc_ag.agbp,
+ error = xfs_alloc_get_freelist(pag, cur->bc_tp, cur->bc_ag.agbp,
&bno, 1);
if (error)
return error;
@@ -129,7 +129,7 @@ xfs_rmapbt_free_block(
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(cur->bc_tp, agbp, NULL, bno, 1);
+ error = xfs_alloc_put_freelist(pag, cur->bc_tp, agbp, NULL, bno, 1);
if (error)
return error;
@@ -652,7 +652,7 @@ xfs_rmapbt_calc_reserves(
if (!xfs_has_rmapbt(mp))
return 0;
- error = xfs_alloc_read_agf(mp, tp, pag->pag_agno, 0, &agbp);
+ error = xfs_alloc_read_agf(pag, tp, 0, &agbp);
if (error)
return error;
@@ -666,8 +666,7 @@ xfs_rmapbt_calc_reserves(
* never be available for the kinds of things that would require btree
* expansion. We therefore can pretend the space isn't there.
*/
- if (mp->m_sb.sb_logstart &&
- XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart) == pag->pag_agno)
+ if (xfs_ag_contains_log(mp, pag->pag_agno))
agblocks -= mp->m_sb.sb_logblocks;
/* Reserve 1% of the AG or enough for 1 block per record. */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 5740ba664867..fa180ab66b73 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1008,6 +1008,7 @@ xfs_rtfree_extent(
/* Find all the free records within a given range. */
int
xfs_rtalloc_query_range(
+ struct xfs_mount *mp,
struct xfs_trans *tp,
const struct xfs_rtalloc_rec *low_rec,
const struct xfs_rtalloc_rec *high_rec,
@@ -1015,7 +1016,6 @@ xfs_rtalloc_query_range(
void *priv)
{
struct xfs_rtalloc_rec rec;
- struct xfs_mount *mp = tp->t_mountp;
xfs_rtblock_t rtstart;
xfs_rtblock_t rtend;
xfs_rtblock_t high_key;
@@ -1048,7 +1048,7 @@ xfs_rtalloc_query_range(
rec.ar_startext = rtstart;
rec.ar_extcount = rtend - rtstart + 1;
- error = fn(tp, &rec, priv);
+ error = fn(mp, tp, &rec, priv);
if (error)
break;
}
@@ -1062,6 +1062,7 @@ xfs_rtalloc_query_range(
/* Find all the free records. */
int
xfs_rtalloc_query_all(
+ struct xfs_mount *mp,
struct xfs_trans *tp,
xfs_rtalloc_query_range_fn fn,
void *priv)
@@ -1069,10 +1070,10 @@ xfs_rtalloc_query_all(
struct xfs_rtalloc_rec keys[2];
keys[0].ar_startext = 0;
- keys[1].ar_startext = tp->t_mountp->m_sb.sb_rextents - 1;
+ keys[1].ar_startext = mp->m_sb.sb_rextents - 1;
keys[0].ar_extcount = keys[1].ar_extcount = 0;
- return xfs_rtalloc_query_range(tp, &keys[0], &keys[1], fn, priv);
+ return xfs_rtalloc_query_range(mp, tp, &keys[0], &keys[1], fn, priv);
}
/* Is the given extent all free? */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index f4e84aa1d50a..a20cade590e9 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -31,15 +31,66 @@
*/
/*
+ * Check that all the V4 feature bits that the V5 filesystem format requires are
+ * correctly set.
+ */
+static bool
+xfs_sb_validate_v5_features(
+ struct xfs_sb *sbp)
+{
+ /* We must not have any unknown V4 feature bits set */
+ if (sbp->sb_versionnum & ~XFS_SB_VERSION_OKBITS)
+ return false;
+
+ /*
+ * The CRC bit is considered an invalid V4 flag, so we have to add it
+ * manually to the OKBITS mask.
+ */
+ if (sbp->sb_features2 & ~(XFS_SB_VERSION2_OKBITS |
+ XFS_SB_VERSION2_CRCBIT))
+ return false;
+
+ /* Now check all the required V4 feature flags are set. */
+
+#define V5_VERS_FLAGS (XFS_SB_VERSION_NLINKBIT | \
+ XFS_SB_VERSION_ALIGNBIT | \
+ XFS_SB_VERSION_LOGV2BIT | \
+ XFS_SB_VERSION_EXTFLGBIT | \
+ XFS_SB_VERSION_DIRV2BIT | \
+ XFS_SB_VERSION_MOREBITSBIT)
+
+#define V5_FEAT_FLAGS (XFS_SB_VERSION2_LAZYSBCOUNTBIT | \
+ XFS_SB_VERSION2_ATTR2BIT | \
+ XFS_SB_VERSION2_PROJID32BIT | \
+ XFS_SB_VERSION2_CRCBIT)
+
+ if ((sbp->sb_versionnum & V5_VERS_FLAGS) != V5_VERS_FLAGS)
+ return false;
+ if ((sbp->sb_features2 & V5_FEAT_FLAGS) != V5_FEAT_FLAGS)
+ return false;
+ return true;
+}
+
+/*
* We support all XFS versions newer than a v4 superblock with V2 directories.
*/
bool
xfs_sb_good_version(
struct xfs_sb *sbp)
{
- /* all v5 filesystems are supported */
+ /*
+ * All v5 filesystems are supported, but we must check that all the
+ * required v4 feature flags are enabled correctly as the code checks
+ * those flags and not for v5 support.
+ */
if (xfs_sb_is_v5(sbp))
- return true;
+ return xfs_sb_validate_v5_features(sbp);
+
+ /* We must not have any unknown v4 feature bits set */
+ if ((sbp->sb_versionnum & ~XFS_SB_VERSION_OKBITS) ||
+ ((sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) &&
+ (sbp->sb_features2 & ~XFS_SB_VERSION2_OKBITS)))
+ return false;
/* versions prior to v4 are not supported */
if (XFS_SB_VERSION_NUM(sbp) < XFS_SB_VERSION_4)
@@ -51,12 +102,6 @@ xfs_sb_good_version(
if (!(sbp->sb_versionnum & XFS_SB_VERSION_EXTFLGBIT))
return false;
- /* And must not have any unknown v4 feature bits set */
- if ((sbp->sb_versionnum & ~XFS_SB_VERSION_OKBITS) ||
- ((sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) &&
- (sbp->sb_features2 & ~XFS_SB_VERSION2_OKBITS)))
- return false;
-
/* It's a supported v4 filesystem */
return true;
}
@@ -70,6 +115,8 @@ xfs_sb_version_to_features(
/* optional V4 features */
if (sbp->sb_rblocks > 0)
features |= XFS_FEAT_REALTIME;
+ if (sbp->sb_versionnum & XFS_SB_VERSION_NLINKBIT)
+ features |= XFS_FEAT_NLINK;
if (sbp->sb_versionnum & XFS_SB_VERSION_ATTRBIT)
features |= XFS_FEAT_ATTR;
if (sbp->sb_versionnum & XFS_SB_VERSION_QUOTABIT)
@@ -124,6 +171,9 @@ xfs_sb_version_to_features(
features |= XFS_FEAT_BIGTIME;
if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_NEEDSREPAIR)
features |= XFS_FEAT_NEEDSREPAIR;
+ if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_NREXT64)
+ features |= XFS_FEAT_NREXT64;
+
return features;
}
@@ -262,12 +312,15 @@ xfs_validate_sb_common(
bool has_dalign;
if (!xfs_verify_magic(bp, dsb->sb_magicnum)) {
- xfs_warn(mp, "bad magic number");
+ xfs_warn(mp,
+"Superblock has bad magic number 0x%x. Not an XFS filesystem?",
+ be32_to_cpu(dsb->sb_magicnum));
return -EWRONGFS;
}
if (!xfs_sb_good_version(sbp)) {
- xfs_warn(mp, "bad version");
+ xfs_warn(mp,
+"Superblock has unknown features enabled or corrupted feature masks.");
return -EWRONGFS;
}
@@ -911,6 +964,11 @@ xfs_log_sb(
* reservations that have been taken out percpu counters. If we have an
* unclean shutdown, this will be corrected by log recovery rebuilding
* the counters from the AGF block counts.
+ *
+ * Do not update sb_frextents here because it is not part of the lazy
+ * sb counters, despite having a percpu counter. It is always kept
+ * consistent with the ondisk rtbitmap by xfs_trans_apply_sb_deltas()
+ * and hence we don't need have to update it here.
*/
if (xfs_has_lazysbcount(mp)) {
mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount);
@@ -1135,6 +1193,8 @@ xfs_fs_geometry(
} else {
geo->logsectsize = BBSIZE;
}
+ if (xfs_has_large_extent_counts(mp))
+ geo->flags |= XFS_FSOP_GEOM_FLAGS_NREXT64;
geo->rtsectsize = sbp->sb_blocksize;
geo->dirblocksize = xfs_dir2_dirblock_bytes(sbp);
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 25c4cab58851..c4381388c0c1 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -54,13 +54,23 @@ void xfs_log_get_max_trans_res(struct xfs_mount *mp,
/*
* Values for t_flags.
*/
-#define XFS_TRANS_DIRTY 0x01 /* something needs to be logged */
-#define XFS_TRANS_SB_DIRTY 0x02 /* superblock is modified */
-#define XFS_TRANS_PERM_LOG_RES 0x04 /* xact took a permanent log res */
-#define XFS_TRANS_SYNC 0x08 /* make commit synchronous */
-#define XFS_TRANS_RESERVE 0x20 /* OK to use reserved data blocks */
-#define XFS_TRANS_NO_WRITECOUNT 0x40 /* do not elevate SB writecount */
-#define XFS_TRANS_RES_FDBLKS 0x80 /* reserve newly freed blocks */
+/* Transaction needs to be logged */
+#define XFS_TRANS_DIRTY (1u << 0)
+/* Superblock is dirty and needs to be logged */
+#define XFS_TRANS_SB_DIRTY (1u << 1)
+/* Transaction took a permanent log reservation */
+#define XFS_TRANS_PERM_LOG_RES (1u << 2)
+/* Synchronous transaction commit needed */
+#define XFS_TRANS_SYNC (1u << 3)
+/* Transaction can use reserve block pool */
+#define XFS_TRANS_RESERVE (1u << 4)
+/* Transaction should avoid VFS level superblock write accounting */
+#define XFS_TRANS_NO_WRITECOUNT (1u << 5)
+/* Transaction has freed blocks returned to it's reservation */
+#define XFS_TRANS_RES_FDBLKS (1u << 6)
+/* Transaction contains an intent done log item */
+#define XFS_TRANS_HAS_INTENT_DONE (1u << 7)
+
/*
* LOWMODE is used by the allocator to activate the lowspace algorithm - when
* free space is running low the extent allocator may choose to allocate an
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index f0b38f4aba80..bdc777b9ec4a 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -204,7 +204,7 @@ xfs_failaddr_t
xfs_symlink_shortform_verify(
struct xfs_inode *ip)
{
- struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+ struct xfs_ifork *ifp = xfs_ifork_ptr(ip, XFS_DATA_FORK);
char *sfp = (char *)ifp->if_u1.if_data;
int size = ifp->if_bytes;
char *endp = sfp + size;
@@ -213,7 +213,7 @@ xfs_symlink_shortform_verify(
/*
* Zero length symlinks should never occur in memory as they are
- * never alllowed to exist on disk.
+ * never allowed to exist on disk.
*/
if (!size)
return __this_address;
diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c
index 6f83d9b306ee..5b2f27cbdb80 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.c
+++ b/fs/xfs/libxfs/xfs_trans_resv.c
@@ -56,15 +56,14 @@ xfs_calc_buf_res(
* Per-extent log reservation for the btree changes involved in freeing or
* allocating an extent. In classic XFS there were two trees that will be
* modified (bnobt + cntbt). With rmap enabled, there are three trees
- * (rmapbt). With reflink, there are four trees (refcountbt). The number of
- * blocks reserved is based on the formula:
+ * (rmapbt). The number of blocks reserved is based on the formula:
*
* num trees * ((2 blocks/level * max depth) - 1)
*
* Keep in mind that max depth is calculated separately for each type of tree.
*/
uint
-xfs_allocfree_log_count(
+xfs_allocfree_block_count(
struct xfs_mount *mp,
uint num_ops)
{
@@ -73,13 +72,24 @@ xfs_allocfree_log_count(
blocks = num_ops * 2 * (2 * mp->m_alloc_maxlevels - 1);
if (xfs_has_rmapbt(mp))
blocks += num_ops * (2 * mp->m_rmap_maxlevels - 1);
- if (xfs_has_reflink(mp))
- blocks += num_ops * (2 * mp->m_refc_maxlevels - 1);
return blocks;
}
/*
+ * Per-extent log reservation for refcount btree changes. These are never done
+ * in the same transaction as an allocation or a free, so we compute them
+ * separately.
+ */
+static unsigned int
+xfs_refcountbt_block_count(
+ struct xfs_mount *mp,
+ unsigned int num_ops)
+{
+ return num_ops * (2 * mp->m_refc_maxlevels - 1);
+}
+
+/*
* Logging inodes is really tricksy. They are logged in memory format,
* which means that what we write into the log doesn't directly translate into
* the amount of space they use on disk.
@@ -136,7 +146,7 @@ xfs_calc_inobt_res(
{
return xfs_calc_buf_res(M_IGEO(mp)->inobt_maxlevels,
XFS_FSB_TO_B(mp, 1)) +
- xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1),
+ xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1),
XFS_FSB_TO_B(mp, 1));
}
@@ -183,7 +193,7 @@ xfs_calc_inode_chunk_res(
{
uint res, size = 0;
- res = xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1),
+ res = xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1),
XFS_FSB_TO_B(mp, 1));
if (alloc) {
/* icreate tx uses ordered buffers */
@@ -199,18 +209,18 @@ xfs_calc_inode_chunk_res(
/*
* Per-extent log reservation for the btree changes involved in freeing or
* allocating a realtime extent. We have to be able to log as many rtbitmap
- * blocks as needed to mark inuse MAXEXTLEN blocks' worth of realtime extents,
- * as well as the realtime summary block.
+ * blocks as needed to mark inuse XFS_BMBT_MAX_EXTLEN blocks' worth of realtime
+ * extents, as well as the realtime summary block.
*/
static unsigned int
-xfs_rtalloc_log_count(
+xfs_rtalloc_block_count(
struct xfs_mount *mp,
unsigned int num_ops)
{
unsigned int blksz = XFS_FSB_TO_B(mp, 1);
unsigned int rtbmp_bytes;
- rtbmp_bytes = (MAXEXTLEN / mp->m_sb.sb_rextsize) / NBBY;
+ rtbmp_bytes = (XFS_MAX_BMBT_EXTLEN / mp->m_sb.sb_rextsize) / NBBY;
return (howmany(rtbmp_bytes, blksz) + 1) * num_ops;
}
@@ -233,6 +243,28 @@ xfs_rtalloc_log_count(
* register overflow from temporaries in the calculations.
*/
+/*
+ * Compute the log reservation required to handle the refcount update
+ * transaction. Refcount updates are always done via deferred log items.
+ *
+ * This is calculated as:
+ * Data device refcount updates (t1):
+ * the agfs of the ags containing the blocks: nr_ops * sector size
+ * the refcount btrees: nr_ops * 1 trees * (2 * max depth - 1) * block size
+ */
+static unsigned int
+xfs_calc_refcountbt_reservation(
+ struct xfs_mount *mp,
+ unsigned int nr_ops)
+{
+ unsigned int blksz = XFS_FSB_TO_B(mp, 1);
+
+ if (!xfs_has_reflink(mp))
+ return 0;
+
+ return xfs_calc_buf_res(nr_ops, mp->m_sb.sb_sectsize) +
+ xfs_calc_buf_res(xfs_refcountbt_block_count(mp, nr_ops), blksz);
+}
/*
* In a write transaction we can allocate a maximum of 2
@@ -247,7 +279,7 @@ xfs_rtalloc_log_count(
* the inode's bmap btree: max depth * block size
* the agfs of the ags from which the extents are allocated: 2 * sector
* the superblock free block counter: sector size
- * the realtime bitmap: ((MAXEXTLEN / rtextsize) / NBBY) bytes
+ * the realtime bitmap: ((XFS_BMBT_MAX_EXTLEN / rtextsize) / NBBY) bytes
* the realtime summary: 1 block
* the allocation btrees: 2 trees * (2 * max depth - 1) * block size
* And the bmap_finish transaction can free bmap blocks in a join (t3):
@@ -255,34 +287,65 @@ xfs_rtalloc_log_count(
* the agfls of the ags containing the blocks: 2 * sector size
* the super block free block counter: sector size
* the allocation btrees: 2 exts * 2 trees * (2 * max depth - 1) * block size
+ * And any refcount updates that happen in a separate transaction (t4).
*/
STATIC uint
xfs_calc_write_reservation(
- struct xfs_mount *mp)
+ struct xfs_mount *mp,
+ bool for_minlogsize)
{
- unsigned int t1, t2, t3;
+ unsigned int t1, t2, t3, t4;
unsigned int blksz = XFS_FSB_TO_B(mp, 1);
t1 = xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK), blksz) +
xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
- xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), blksz);
+ xfs_calc_buf_res(xfs_allocfree_block_count(mp, 2), blksz);
if (xfs_has_realtime(mp)) {
t2 = xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK),
blksz) +
xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
- xfs_calc_buf_res(xfs_rtalloc_log_count(mp, 1), blksz) +
- xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1), blksz);
+ xfs_calc_buf_res(xfs_rtalloc_block_count(mp, 1), blksz) +
+ xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1), blksz);
} else {
t2 = 0;
}
t3 = xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) +
- xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), blksz);
+ xfs_calc_buf_res(xfs_allocfree_block_count(mp, 2), blksz);
- return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3);
+ /*
+ * In the early days of reflink, we included enough reservation to log
+ * two refcountbt splits for each transaction. The codebase runs
+ * refcountbt updates in separate transactions now, so to compute the
+ * minimum log size, add the refcountbtree splits back to t1 and t3 and
+ * do not account them separately as t4. Reflink did not support
+ * realtime when the reservations were established, so no adjustment to
+ * t2 is needed.
+ */
+ if (for_minlogsize) {
+ unsigned int adj = 0;
+
+ if (xfs_has_reflink(mp))
+ adj = xfs_calc_buf_res(
+ xfs_refcountbt_block_count(mp, 2),
+ blksz);
+ t1 += adj;
+ t3 += adj;
+ return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3);
+ }
+
+ t4 = xfs_calc_refcountbt_reservation(mp, 1);
+ return XFS_DQUOT_LOGRES(mp) + max(t4, max3(t1, t2, t3));
+}
+
+unsigned int
+xfs_calc_write_reservation_minlogsize(
+ struct xfs_mount *mp)
+{
+ return xfs_calc_write_reservation(mp, true);
}
/*
@@ -299,38 +362,67 @@ xfs_calc_write_reservation(
* the agf for each of the ags: 2 * sector size
* the agfl for each of the ags: 2 * sector size
* the super block to reflect the freed blocks: sector size
- * the realtime bitmap: 2 exts * ((MAXEXTLEN / rtextsize) / NBBY) bytes
+ * the realtime bitmap:
+ * 2 exts * ((XFS_BMBT_MAX_EXTLEN / rtextsize) / NBBY) bytes
* the realtime summary: 2 exts * 1 block
* worst case split in allocation btrees per extent assuming 2 extents:
* 2 exts * 2 trees * (2 * max depth - 1) * block size
+ * And any refcount updates that happen in a separate transaction (t4).
*/
STATIC uint
xfs_calc_itruncate_reservation(
- struct xfs_mount *mp)
+ struct xfs_mount *mp,
+ bool for_minlogsize)
{
- unsigned int t1, t2, t3;
+ unsigned int t1, t2, t3, t4;
unsigned int blksz = XFS_FSB_TO_B(mp, 1);
t1 = xfs_calc_inode_res(mp, 1) +
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1, blksz);
t2 = xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) +
- xfs_calc_buf_res(xfs_allocfree_log_count(mp, 4), blksz);
+ xfs_calc_buf_res(xfs_allocfree_block_count(mp, 4), blksz);
if (xfs_has_realtime(mp)) {
t3 = xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) +
- xfs_calc_buf_res(xfs_rtalloc_log_count(mp, 2), blksz) +
- xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), blksz);
+ xfs_calc_buf_res(xfs_rtalloc_block_count(mp, 2), blksz) +
+ xfs_calc_buf_res(xfs_allocfree_block_count(mp, 2), blksz);
} else {
t3 = 0;
}
- return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3);
+ /*
+ * In the early days of reflink, we included enough reservation to log
+ * four refcountbt splits in the same transaction as bnobt/cntbt
+ * updates. The codebase runs refcountbt updates in separate
+ * transactions now, so to compute the minimum log size, add the
+ * refcount btree splits back here and do not compute them separately
+ * as t4. Reflink did not support realtime when the reservations were
+ * established, so do not adjust t3.
+ */
+ if (for_minlogsize) {
+ if (xfs_has_reflink(mp))
+ t2 += xfs_calc_buf_res(
+ xfs_refcountbt_block_count(mp, 4),
+ blksz);
+
+ return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3);
+ }
+
+ t4 = xfs_calc_refcountbt_reservation(mp, 2);
+ return XFS_DQUOT_LOGRES(mp) + max(t4, max3(t1, t2, t3));
+}
+
+unsigned int
+xfs_calc_itruncate_reservation_minlogsize(
+ struct xfs_mount *mp)
+{
+ return xfs_calc_itruncate_reservation(mp, true);
}
/*
* In renaming a files we can modify:
- * the four inodes involved: 4 * inode size
+ * the five inodes involved: 5 * inode size
* the two directory btrees: 2 * (max depth + v2) * dir block size
* the two directory bmap btrees: 2 * max depth * block size
* And the bmap_finish transaction can free dir and bmap blocks (two sets
@@ -345,11 +437,11 @@ xfs_calc_rename_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
- max((xfs_calc_inode_res(mp, 4) +
+ max((xfs_calc_inode_res(mp, 5) +
xfs_calc_buf_res(2 * XFS_DIROP_LOG_COUNT(mp),
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(7, mp->m_sb.sb_sectsize) +
- xfs_calc_buf_res(xfs_allocfree_log_count(mp, 3),
+ xfs_calc_buf_res(xfs_allocfree_block_count(mp, 3),
XFS_FSB_TO_B(mp, 1))));
}
@@ -389,7 +481,7 @@ xfs_calc_link_reservation(
xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
- xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1),
+ xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1),
XFS_FSB_TO_B(mp, 1))));
}
@@ -423,11 +515,11 @@ xfs_calc_remove_reservation(
{
return XFS_DQUOT_LOGRES(mp) +
xfs_calc_iunlink_add_reservation(mp) +
- max((xfs_calc_inode_res(mp, 1) +
+ max((xfs_calc_inode_res(mp, 2) +
xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(4, mp->m_sb.sb_sectsize) +
- xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2),
+ xfs_calc_buf_res(xfs_allocfree_block_count(mp, 2),
XFS_FSB_TO_B(mp, 1))));
}
@@ -572,7 +664,7 @@ xfs_calc_growdata_reservation(
struct xfs_mount *mp)
{
return xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
- xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1),
+ xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1),
XFS_FSB_TO_B(mp, 1));
}
@@ -594,7 +686,7 @@ xfs_calc_growrtalloc_reservation(
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK),
XFS_FSB_TO_B(mp, 1)) +
xfs_calc_inode_res(mp, 1) +
- xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1),
+ xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1),
XFS_FSB_TO_B(mp, 1));
}
@@ -670,7 +762,7 @@ xfs_calc_addafork_reservation(
xfs_calc_buf_res(1, mp->m_dir_geo->blksize) +
xfs_calc_buf_res(XFS_DAENTER_BMAP1B(mp, XFS_DATA_FORK) + 1,
XFS_FSB_TO_B(mp, 1)) +
- xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1),
+ xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1),
XFS_FSB_TO_B(mp, 1));
}
@@ -693,7 +785,7 @@ xfs_calc_attrinval_reservation(
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK),
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) +
- xfs_calc_buf_res(xfs_allocfree_log_count(mp, 4),
+ xfs_calc_buf_res(xfs_allocfree_block_count(mp, 4),
XFS_FSB_TO_B(mp, 1))));
}
@@ -760,7 +852,7 @@ xfs_calc_attrrm_reservation(
XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK)) +
xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK), 0)),
(xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) +
- xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2),
+ xfs_calc_buf_res(xfs_allocfree_block_count(mp, 2),
XFS_FSB_TO_B(mp, 1))));
}
@@ -791,13 +883,21 @@ xfs_calc_qm_setqlim_reservation(void)
*/
STATIC uint
xfs_calc_qm_dqalloc_reservation(
- struct xfs_mount *mp)
+ struct xfs_mount *mp,
+ bool for_minlogsize)
{
- return xfs_calc_write_reservation(mp) +
+ return xfs_calc_write_reservation(mp, for_minlogsize) +
xfs_calc_buf_res(1,
XFS_FSB_TO_B(mp, XFS_DQUOT_CLUSTER_SIZE_FSB) - 1);
}
+unsigned int
+xfs_calc_qm_dqalloc_reservation_minlogsize(
+ struct xfs_mount *mp)
+{
+ return xfs_calc_qm_dqalloc_reservation(mp, true);
+}
+
/*
* Syncing the incore super block changes to disk.
* the super block to reflect the changes: sector size
@@ -814,36 +914,18 @@ xfs_trans_resv_calc(
struct xfs_mount *mp,
struct xfs_trans_resv *resp)
{
- unsigned int rmap_maxlevels = mp->m_rmap_maxlevels;
-
- /*
- * In the early days of rmap+reflink, we always set the rmap maxlevels
- * to 9 even if the AG was small enough that it would never grow to
- * that height. Transaction reservation sizes influence the minimum
- * log size calculation, which influences the size of the log that mkfs
- * creates. Use the old value here to ensure that newly formatted
- * small filesystems will mount on older kernels.
- */
- if (xfs_has_rmapbt(mp) && xfs_has_reflink(mp))
- mp->m_rmap_maxlevels = XFS_OLD_REFLINK_RMAP_MAXLEVELS;
+ int logcount_adj = 0;
/*
* The following transactions are logged in physical format and
* require a permanent reservation on space.
*/
- resp->tr_write.tr_logres = xfs_calc_write_reservation(mp);
- if (xfs_has_reflink(mp))
- resp->tr_write.tr_logcount = XFS_WRITE_LOG_COUNT_REFLINK;
- else
- resp->tr_write.tr_logcount = XFS_WRITE_LOG_COUNT;
+ resp->tr_write.tr_logres = xfs_calc_write_reservation(mp, false);
+ resp->tr_write.tr_logcount = XFS_WRITE_LOG_COUNT;
resp->tr_write.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
- resp->tr_itruncate.tr_logres = xfs_calc_itruncate_reservation(mp);
- if (xfs_has_reflink(mp))
- resp->tr_itruncate.tr_logcount =
- XFS_ITRUNCATE_LOG_COUNT_REFLINK;
- else
- resp->tr_itruncate.tr_logcount = XFS_ITRUNCATE_LOG_COUNT;
+ resp->tr_itruncate.tr_logres = xfs_calc_itruncate_reservation(mp, false);
+ resp->tr_itruncate.tr_logcount = XFS_ITRUNCATE_LOG_COUNT;
resp->tr_itruncate.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
resp->tr_rename.tr_logres = xfs_calc_rename_reservation(mp);
@@ -899,11 +981,9 @@ xfs_trans_resv_calc(
resp->tr_growrtalloc.tr_logcount = XFS_DEFAULT_PERM_LOG_COUNT;
resp->tr_growrtalloc.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
- resp->tr_qm_dqalloc.tr_logres = xfs_calc_qm_dqalloc_reservation(mp);
- if (xfs_has_reflink(mp))
- resp->tr_qm_dqalloc.tr_logcount = XFS_WRITE_LOG_COUNT_REFLINK;
- else
- resp->tr_qm_dqalloc.tr_logcount = XFS_WRITE_LOG_COUNT;
+ resp->tr_qm_dqalloc.tr_logres = xfs_calc_qm_dqalloc_reservation(mp,
+ false);
+ resp->tr_qm_dqalloc.tr_logcount = XFS_WRITE_LOG_COUNT;
resp->tr_qm_dqalloc.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
/*
@@ -930,6 +1010,19 @@ xfs_trans_resv_calc(
resp->tr_growrtzero.tr_logres = xfs_calc_growrtzero_reservation(mp);
resp->tr_growrtfree.tr_logres = xfs_calc_growrtfree_reservation(mp);
- /* Put everything back the way it was. This goes at the end. */
- mp->m_rmap_maxlevels = rmap_maxlevels;
+ /*
+ * Add one logcount for BUI items that appear with rmap or reflink,
+ * one logcount for refcount intent items, and one logcount for rmap
+ * intent items.
+ */
+ if (xfs_has_reflink(mp) || xfs_has_rmapbt(mp))
+ logcount_adj++;
+ if (xfs_has_reflink(mp))
+ logcount_adj++;
+ if (xfs_has_rmapbt(mp))
+ logcount_adj++;
+
+ resp->tr_itruncate.tr_logcount += logcount_adj;
+ resp->tr_write.tr_logcount += logcount_adj;
+ resp->tr_qm_dqalloc.tr_logcount += logcount_adj;
}
diff --git a/fs/xfs/libxfs/xfs_trans_resv.h b/fs/xfs/libxfs/xfs_trans_resv.h
index fc4e9b369a3a..0554b9d775d2 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.h
+++ b/fs/xfs/libxfs/xfs_trans_resv.h
@@ -73,7 +73,6 @@ struct xfs_trans_resv {
#define XFS_DEFAULT_LOG_COUNT 1
#define XFS_DEFAULT_PERM_LOG_COUNT 2
#define XFS_ITRUNCATE_LOG_COUNT 2
-#define XFS_ITRUNCATE_LOG_COUNT_REFLINK 8
#define XFS_INACTIVE_LOG_COUNT 2
#define XFS_CREATE_LOG_COUNT 2
#define XFS_CREATE_TMPFILE_LOG_COUNT 2
@@ -83,13 +82,24 @@ struct xfs_trans_resv {
#define XFS_LINK_LOG_COUNT 2
#define XFS_RENAME_LOG_COUNT 2
#define XFS_WRITE_LOG_COUNT 2
-#define XFS_WRITE_LOG_COUNT_REFLINK 8
#define XFS_ADDAFORK_LOG_COUNT 2
#define XFS_ATTRINVAL_LOG_COUNT 1
#define XFS_ATTRSET_LOG_COUNT 3
#define XFS_ATTRRM_LOG_COUNT 3
+/*
+ * Original log operation counts were overestimated in the early days of
+ * reflink. These are retained here purely for minimum log size calculations
+ * and must not be used for runtime reservations.
+ */
+#define XFS_ITRUNCATE_LOG_COUNT_REFLINK 8
+#define XFS_WRITE_LOG_COUNT_REFLINK 8
+
void xfs_trans_resv_calc(struct xfs_mount *mp, struct xfs_trans_resv *resp);
-uint xfs_allocfree_log_count(struct xfs_mount *mp, uint num_ops);
+uint xfs_allocfree_block_count(struct xfs_mount *mp, uint num_ops);
+
+unsigned int xfs_calc_itruncate_reservation_minlogsize(struct xfs_mount *mp);
+unsigned int xfs_calc_write_reservation_minlogsize(struct xfs_mount *mp);
+unsigned int xfs_calc_qm_dqalloc_reservation_minlogsize(struct xfs_mount *mp);
#endif /* __XFS_TRANS_RESV_H__ */
diff --git a/fs/xfs/libxfs/xfs_types.c b/fs/xfs/libxfs/xfs_types.c
index e810d23f2d97..5c2765934732 100644
--- a/fs/xfs/libxfs/xfs_types.c
+++ b/fs/xfs/libxfs/xfs_types.c
@@ -13,25 +13,13 @@
#include "xfs_mount.h"
#include "xfs_ag.h"
-/* Find the size of the AG, in blocks. */
-inline xfs_agblock_t
-xfs_ag_block_count(
- struct xfs_mount *mp,
- xfs_agnumber_t agno)
-{
- ASSERT(agno < mp->m_sb.sb_agcount);
-
- if (agno < mp->m_sb.sb_agcount - 1)
- return mp->m_sb.sb_agblocks;
- return mp->m_sb.sb_dblocks - (agno * mp->m_sb.sb_agblocks);
-}
/*
* Verify that an AG block number pointer neither points outside the AG
* nor points at static metadata.
*/
-inline bool
-xfs_verify_agbno(
+static inline bool
+xfs_verify_agno_agbno(
struct xfs_mount *mp,
xfs_agnumber_t agno,
xfs_agblock_t agbno)
@@ -59,7 +47,7 @@ xfs_verify_fsbno(
if (agno >= mp->m_sb.sb_agcount)
return false;
- return xfs_verify_agbno(mp, agno, XFS_FSB_TO_AGBNO(mp, fsbno));
+ return xfs_verify_agno_agbno(mp, agno, XFS_FSB_TO_AGBNO(mp, fsbno));
}
/*
@@ -85,40 +73,12 @@ xfs_verify_fsbext(
XFS_FSB_TO_AGNO(mp, fsbno + len - 1);
}
-/* Calculate the first and last possible inode number in an AG. */
-inline void
-xfs_agino_range(
- struct xfs_mount *mp,
- xfs_agnumber_t agno,
- xfs_agino_t *first,
- xfs_agino_t *last)
-{
- xfs_agblock_t bno;
- xfs_agblock_t eoag;
-
- eoag = xfs_ag_block_count(mp, agno);
-
- /*
- * Calculate the first inode, which will be in the first
- * cluster-aligned block after the AGFL.
- */
- bno = round_up(XFS_AGFL_BLOCK(mp) + 1, M_IGEO(mp)->cluster_align);
- *first = XFS_AGB_TO_AGINO(mp, bno);
-
- /*
- * Calculate the last inode, which will be at the end of the
- * last (aligned) cluster that can be allocated in the AG.
- */
- bno = round_down(eoag, M_IGEO(mp)->cluster_align);
- *last = XFS_AGB_TO_AGINO(mp, bno) - 1;
-}
-
/*
* Verify that an AG inode number pointer neither points outside the AG
* nor points at static metadata.
*/
-inline bool
-xfs_verify_agino(
+static inline bool
+xfs_verify_agno_agino(
struct xfs_mount *mp,
xfs_agnumber_t agno,
xfs_agino_t agino)
@@ -131,19 +91,6 @@ xfs_verify_agino(
}
/*
- * Verify that an AG inode number pointer neither points outside the AG
- * nor points at static metadata, or is NULLAGINO.
- */
-bool
-xfs_verify_agino_or_null(
- struct xfs_mount *mp,
- xfs_agnumber_t agno,
- xfs_agino_t agino)
-{
- return agino == NULLAGINO || xfs_verify_agino(mp, agno, agino);
-}
-
-/*
* Verify that an FS inode number pointer neither points outside the
* filesystem nor points at static AG metadata.
*/
@@ -159,7 +106,7 @@ xfs_verify_ino(
return false;
if (XFS_AGINO_TO_INO(mp, agno, agino) != ino)
return false;
- return xfs_verify_agino(mp, agno, agino);
+ return xfs_verify_agno_agino(mp, agno, agino);
}
/* Is this an internal inode number? */
@@ -229,12 +176,8 @@ xfs_icount_range(
/* root, rtbitmap, rtsum all live in the first chunk */
*min = XFS_INODES_PER_CHUNK;
- for_each_perag(mp, agno, pag) {
- xfs_agino_t first, last;
-
- xfs_agino_range(mp, agno, &first, &last);
- nr_inos += last - first + 1;
- }
+ for_each_perag(mp, agno, pag)
+ nr_inos += pag->agino_max - pag->agino_min + 1;
*max = nr_inos;
}
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index b6da06b40989..5ebdda7e1078 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -12,8 +12,8 @@ typedef uint32_t xfs_agblock_t; /* blockno in alloc. group */
typedef uint32_t xfs_agino_t; /* inode # within allocation grp */
typedef uint32_t xfs_extlen_t; /* extent length in blocks */
typedef uint32_t xfs_agnumber_t; /* allocation group number */
-typedef int32_t xfs_extnum_t; /* # of extents in a file */
-typedef int16_t xfs_aextnum_t; /* # extents in an attribute fork */
+typedef uint64_t xfs_extnum_t; /* # of extents in a file */
+typedef uint32_t xfs_aextnum_t; /* # extents in an attribute fork */
typedef int64_t xfs_fsize_t; /* bytes in a file */
typedef uint64_t xfs_ufsize_t; /* unsigned bytes in a file */
@@ -57,13 +57,6 @@ typedef void * xfs_failaddr_t;
#define NULLAGINO ((xfs_agino_t)-1)
/*
- * Max values for extlen, extnum, aextnum.
- */
-#define MAXEXTLEN ((xfs_extlen_t)0x001fffff) /* 21 bits */
-#define MAXEXTNUM ((xfs_extnum_t)0x7fffffff) /* signed int */
-#define MAXAEXTNUM ((xfs_aextnum_t)0x7fff) /* signed short */
-
-/*
* Minimum and maximum blocksize and sectorsize.
* The blocksize upper limit is pretty much arbitrary.
* The sectorsize upper limit is due to sizeof(sb_sectsize).
@@ -173,6 +166,36 @@ typedef struct xfs_bmbt_irec
xfs_exntst_t br_state; /* extent state */
} xfs_bmbt_irec_t;
+enum xfs_refc_domain {
+ XFS_REFC_DOMAIN_SHARED = 0,
+ XFS_REFC_DOMAIN_COW,
+};
+
+#define XFS_REFC_DOMAIN_STRINGS \
+ { XFS_REFC_DOMAIN_SHARED, "shared" }, \
+ { XFS_REFC_DOMAIN_COW, "cow" }
+
+struct xfs_refcount_irec {
+ xfs_agblock_t rc_startblock; /* starting block number */
+ xfs_extlen_t rc_blockcount; /* count of free blocks */
+ xfs_nlink_t rc_refcount; /* number of inodes linked here */
+ enum xfs_refc_domain rc_domain; /* shared or cow staging extent? */
+};
+
+#define XFS_RMAP_ATTR_FORK (1 << 0)
+#define XFS_RMAP_BMBT_BLOCK (1 << 1)
+#define XFS_RMAP_UNWRITTEN (1 << 2)
+#define XFS_RMAP_KEY_FLAGS (XFS_RMAP_ATTR_FORK | \
+ XFS_RMAP_BMBT_BLOCK)
+#define XFS_RMAP_REC_FLAGS (XFS_RMAP_UNWRITTEN)
+struct xfs_rmap_irec {
+ xfs_agblock_t rm_startblock; /* extent start block */
+ xfs_extlen_t rm_blockcount; /* extent length */
+ uint64_t rm_owner; /* extent owner */
+ uint64_t rm_offset; /* offset within the owner */
+ unsigned int rm_flags; /* state flags */
+};
+
/* per-AG block reservation types */
enum xfs_ag_resv_type {
XFS_AG_RESV_NONE = 0,
@@ -186,19 +209,10 @@ enum xfs_ag_resv_type {
*/
struct xfs_mount;
-xfs_agblock_t xfs_ag_block_count(struct xfs_mount *mp, xfs_agnumber_t agno);
-bool xfs_verify_agbno(struct xfs_mount *mp, xfs_agnumber_t agno,
- xfs_agblock_t agbno);
bool xfs_verify_fsbno(struct xfs_mount *mp, xfs_fsblock_t fsbno);
bool xfs_verify_fsbext(struct xfs_mount *mp, xfs_fsblock_t fsbno,
xfs_fsblock_t len);
-void xfs_agino_range(struct xfs_mount *mp, xfs_agnumber_t agno,
- xfs_agino_t *first, xfs_agino_t *last);
-bool xfs_verify_agino(struct xfs_mount *mp, xfs_agnumber_t agno,
- xfs_agino_t agino);
-bool xfs_verify_agino_or_null(struct xfs_mount *mp, xfs_agnumber_t agno,
- xfs_agino_t agino);
bool xfs_verify_ino(struct xfs_mount *mp, xfs_ino_t ino);
bool xfs_internal_inum(struct xfs_mount *mp, xfs_ino_t ino);
bool xfs_verify_dir_ino(struct xfs_mount *mp, xfs_ino_t ino);