summaryrefslogtreecommitdiff
path: root/fs/xfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs')
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c41
-rw-r--r--fs/xfs/libxfs/xfs_alloc_btree.c52
-rw-r--r--fs/xfs/libxfs/xfs_bmap_btree.c32
-rw-r--r--fs/xfs/libxfs/xfs_btree.c33
-rw-r--r--fs/xfs/libxfs/xfs_btree.h41
-rw-r--r--fs/xfs/libxfs/xfs_format.h2
-rw-r--r--fs/xfs/libxfs/xfs_group.c17
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.c31
-rw-r--r--fs/xfs/libxfs/xfs_ialloc_btree.c24
-rw-r--r--fs/xfs/libxfs/xfs_log_recover.h4
-rw-r--r--fs/xfs/libxfs/xfs_refcount.c4
-rw-r--r--fs/xfs/libxfs/xfs_refcount_btree.c18
-rw-r--r--fs/xfs/libxfs/xfs_rmap_btree.c67
-rw-r--r--fs/xfs/libxfs/xfs_rtrefcount_btree.c18
-rw-r--r--fs/xfs/libxfs/xfs_rtrmap_btree.c67
-rw-r--r--fs/xfs/scrub/btree.c2
-rw-r--r--fs/xfs/scrub/common.c7
-rw-r--r--fs/xfs/scrub/common.h2
-rw-r--r--fs/xfs/scrub/dir_repair.c8
-rw-r--r--fs/xfs/scrub/fscounters.c3
-rw-r--r--fs/xfs/scrub/metapath.c4
-rw-r--r--fs/xfs/scrub/nlinks.c8
-rw-r--r--fs/xfs/scrub/nlinks_repair.c4
-rw-r--r--fs/xfs/scrub/parent_repair.c12
-rw-r--r--fs/xfs/scrub/quotacheck.c4
-rw-r--r--fs/xfs/scrub/rcbag_btree.c38
-rw-r--r--fs/xfs/scrub/repair.c36
-rw-r--r--fs/xfs/scrub/repair.h4
-rw-r--r--fs/xfs/scrub/rmap_repair.c14
-rw-r--r--fs/xfs/scrub/rtrmap_repair.c14
-rw-r--r--fs/xfs/scrub/scrub.c5
-rw-r--r--fs/xfs/scrub/trace.h2
-rw-r--r--fs/xfs/xfs_aops.c212
-rw-r--r--fs/xfs/xfs_attr_item.c148
-rw-r--r--fs/xfs/xfs_attr_item.h8
-rw-r--r--fs/xfs/xfs_bmap_item.c18
-rw-r--r--fs/xfs/xfs_buf.c53
-rw-r--r--fs/xfs/xfs_buf.h9
-rw-r--r--fs/xfs/xfs_buf_item.c303
-rw-r--r--fs/xfs/xfs_buf_item.h5
-rw-r--r--fs/xfs/xfs_buf_item_recover.c38
-rw-r--r--fs/xfs/xfs_discard.c41
-rw-r--r--fs/xfs/xfs_dquot.c4
-rw-r--r--fs/xfs/xfs_dquot_item_recover.c20
-rw-r--r--fs/xfs/xfs_exchmaps_item.c8
-rw-r--r--fs/xfs/xfs_extent_busy.h8
-rw-r--r--fs/xfs/xfs_extfree_item.c59
-rw-r--r--fs/xfs/xfs_file.c54
-rw-r--r--fs/xfs/xfs_fsmap.c4
-rw-r--r--fs/xfs/xfs_icache.c13
-rw-r--r--fs/xfs/xfs_icreate_item.c2
-rw-r--r--fs/xfs/xfs_inode.c9
-rw-r--r--fs/xfs/xfs_inode.h2
-rw-r--r--fs/xfs/xfs_inode_item.c11
-rw-r--r--fs/xfs/xfs_inode_item.h4
-rw-r--r--fs/xfs/xfs_inode_item_recover.c26
-rw-r--r--fs/xfs/xfs_ioctl.c21
-rw-r--r--fs/xfs/xfs_ioctl.h4
-rw-r--r--fs/xfs/xfs_iomap.c14
-rw-r--r--fs/xfs/xfs_iomap.h1
-rw-r--r--fs/xfs/xfs_iops.c6
-rw-r--r--fs/xfs/xfs_itable.c18
-rw-r--r--fs/xfs/xfs_iwalk.c11
-rw-r--r--fs/xfs/xfs_log.c16
-rw-r--r--fs/xfs/xfs_log.h16
-rw-r--r--fs/xfs/xfs_log_cil.c75
-rw-r--r--fs/xfs/xfs_log_priv.h4
-rw-r--r--fs/xfs/xfs_log_recover.c16
-rw-r--r--fs/xfs/xfs_mount.c97
-rw-r--r--fs/xfs/xfs_mount.h17
-rw-r--r--fs/xfs/xfs_mru_cache.c19
-rw-r--r--fs/xfs/xfs_notify_failure.c9
-rw-r--r--fs/xfs/xfs_qm.c96
-rw-r--r--fs/xfs/xfs_refcount_item.c34
-rw-r--r--fs/xfs/xfs_reflink.c3
-rw-r--r--fs/xfs/xfs_rmap_item.c34
-rw-r--r--fs/xfs/xfs_rtalloc.c15
-rw-r--r--fs/xfs/xfs_super.c5
-rw-r--r--fs/xfs/xfs_trace.h121
-rw-r--r--fs/xfs/xfs_trans.c211
-rw-r--r--fs/xfs/xfs_trans.h4
-rw-r--r--fs/xfs/xfs_xattr.c2
-rw-r--r--fs/xfs/xfs_zone_alloc.c87
-rw-r--r--fs/xfs/xfs_zone_alloc.h4
-rw-r--r--fs/xfs/xfs_zone_gc.c18
-rw-r--r--fs/xfs/xfs_zone_info.c2
-rw-r--r--fs/xfs/xfs_zone_priv.h16
-rw-r--r--fs/xfs/xfs_zone_space_resv.c17
88 files changed, 1229 insertions, 1461 deletions
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 7839efe050bf..000cc7f4a3ce 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -3444,16 +3444,41 @@ xfs_alloc_read_agf(
set_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate);
}
+
#ifdef DEBUG
- else if (!xfs_is_shutdown(mp)) {
- 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));
- ASSERT(pag->pagf_longest == be32_to_cpu(agf->agf_longest));
- ASSERT(pag->pagf_bno_level == be32_to_cpu(agf->agf_bno_level));
- ASSERT(pag->pagf_cnt_level == be32_to_cpu(agf->agf_cnt_level));
+ /*
+ * It's possible for the AGF to be out of sync if the block device is
+ * silently dropping writes. This can happen in fstests with dmflakey
+ * enabled, which allows the buffer to be cleaned and reclaimed by
+ * memory pressure and then re-read from disk here. We will get a
+ * stale version of the AGF from disk, and nothing good can happen from
+ * here. Hence if we detect this situation, immediately shut down the
+ * filesystem.
+ *
+ * This can also happen if we are already in the middle of a forced
+ * shutdown, so don't bother checking if we are already shut down.
+ */
+ if (!xfs_is_shutdown(pag_mount(pag))) {
+ bool ok = true;
+
+ ok &= pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks);
+ ok &= pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks);
+ ok &= pag->pagf_btreeblks == be32_to_cpu(agf->agf_btreeblks);
+ ok &= pag->pagf_flcount == be32_to_cpu(agf->agf_flcount);
+ ok &= pag->pagf_longest == be32_to_cpu(agf->agf_longest);
+ ok &= pag->pagf_bno_level == be32_to_cpu(agf->agf_bno_level);
+ ok &= pag->pagf_cnt_level == be32_to_cpu(agf->agf_cnt_level);
+
+ if (XFS_IS_CORRUPT(pag_mount(pag), !ok)) {
+ xfs_ag_mark_sick(pag, XFS_SICK_AG_AGF);
+ xfs_trans_brelse(tp, agfbp);
+ xfs_force_shutdown(pag_mount(pag),
+ SHUTDOWN_CORRUPT_ONDISK);
+ return -EFSCORRUPTED;
+ }
}
-#endif
+#endif /* DEBUG */
+
if (agfbpp)
*agfbpp = agfbp;
else
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index a4ac37ba5d51..fa1f03c1331e 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -186,35 +186,32 @@ xfs_allocbt_init_ptr_from_cur(
ptr->s = agf->agf_cnt_root;
}
-STATIC int64_t
-xfs_bnobt_key_diff(
+STATIC int
+xfs_bnobt_cmp_key_with_cur(
struct xfs_btree_cur *cur,
const union xfs_btree_key *key)
{
struct xfs_alloc_rec_incore *rec = &cur->bc_rec.a;
const struct xfs_alloc_rec *kp = &key->alloc;
- return (int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock;
+ return cmp_int(be32_to_cpu(kp->ar_startblock),
+ rec->ar_startblock);
}
-STATIC int64_t
-xfs_cntbt_key_diff(
+STATIC int
+xfs_cntbt_cmp_key_with_cur(
struct xfs_btree_cur *cur,
const union xfs_btree_key *key)
{
struct xfs_alloc_rec_incore *rec = &cur->bc_rec.a;
const struct xfs_alloc_rec *kp = &key->alloc;
- int64_t diff;
- diff = (int64_t)be32_to_cpu(kp->ar_blockcount) - rec->ar_blockcount;
- if (diff)
- return diff;
-
- return (int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock;
+ return cmp_int(be32_to_cpu(kp->ar_blockcount), rec->ar_blockcount) ?:
+ cmp_int(be32_to_cpu(kp->ar_startblock), rec->ar_startblock);
}
-STATIC int64_t
-xfs_bnobt_diff_two_keys(
+STATIC int
+xfs_bnobt_cmp_two_keys(
struct xfs_btree_cur *cur,
const union xfs_btree_key *k1,
const union xfs_btree_key *k2,
@@ -222,29 +219,24 @@ xfs_bnobt_diff_two_keys(
{
ASSERT(!mask || mask->alloc.ar_startblock);
- return (int64_t)be32_to_cpu(k1->alloc.ar_startblock) -
- be32_to_cpu(k2->alloc.ar_startblock);
+ return cmp_int(be32_to_cpu(k1->alloc.ar_startblock),
+ be32_to_cpu(k2->alloc.ar_startblock));
}
-STATIC int64_t
-xfs_cntbt_diff_two_keys(
+STATIC int
+xfs_cntbt_cmp_two_keys(
struct xfs_btree_cur *cur,
const union xfs_btree_key *k1,
const union xfs_btree_key *k2,
const union xfs_btree_key *mask)
{
- int64_t diff;
-
ASSERT(!mask || (mask->alloc.ar_blockcount &&
mask->alloc.ar_startblock));
- diff = be32_to_cpu(k1->alloc.ar_blockcount) -
- be32_to_cpu(k2->alloc.ar_blockcount);
- if (diff)
- return diff;
-
- return be32_to_cpu(k1->alloc.ar_startblock) -
- be32_to_cpu(k2->alloc.ar_startblock);
+ return cmp_int(be32_to_cpu(k1->alloc.ar_blockcount),
+ be32_to_cpu(k2->alloc.ar_blockcount)) ?:
+ cmp_int(be32_to_cpu(k1->alloc.ar_startblock),
+ be32_to_cpu(k2->alloc.ar_startblock));
}
static xfs_failaddr_t
@@ -438,9 +430,9 @@ const struct xfs_btree_ops xfs_bnobt_ops = {
.init_high_key_from_rec = xfs_bnobt_init_high_key_from_rec,
.init_rec_from_cur = xfs_allocbt_init_rec_from_cur,
.init_ptr_from_cur = xfs_allocbt_init_ptr_from_cur,
- .key_diff = xfs_bnobt_key_diff,
+ .cmp_key_with_cur = xfs_bnobt_cmp_key_with_cur,
.buf_ops = &xfs_bnobt_buf_ops,
- .diff_two_keys = xfs_bnobt_diff_two_keys,
+ .cmp_two_keys = xfs_bnobt_cmp_two_keys,
.keys_inorder = xfs_bnobt_keys_inorder,
.recs_inorder = xfs_bnobt_recs_inorder,
.keys_contiguous = xfs_allocbt_keys_contiguous,
@@ -468,9 +460,9 @@ const struct xfs_btree_ops xfs_cntbt_ops = {
.init_high_key_from_rec = xfs_cntbt_init_high_key_from_rec,
.init_rec_from_cur = xfs_allocbt_init_rec_from_cur,
.init_ptr_from_cur = xfs_allocbt_init_ptr_from_cur,
- .key_diff = xfs_cntbt_key_diff,
+ .cmp_key_with_cur = xfs_cntbt_cmp_key_with_cur,
.buf_ops = &xfs_cntbt_buf_ops,
- .diff_two_keys = xfs_cntbt_diff_two_keys,
+ .cmp_two_keys = xfs_cntbt_cmp_two_keys,
.keys_inorder = xfs_cntbt_keys_inorder,
.recs_inorder = xfs_cntbt_recs_inorder,
.keys_contiguous = NULL, /* not needed right now */
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 908d7b050e9c..188feac04b60 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -369,38 +369,26 @@ xfs_bmbt_init_rec_from_cur(
xfs_bmbt_disk_set_all(&rec->bmbt, &cur->bc_rec.b);
}
-STATIC int64_t
-xfs_bmbt_key_diff(
+STATIC int
+xfs_bmbt_cmp_key_with_cur(
struct xfs_btree_cur *cur,
const union xfs_btree_key *key)
{
- return (int64_t)be64_to_cpu(key->bmbt.br_startoff) -
- cur->bc_rec.b.br_startoff;
+ return cmp_int(be64_to_cpu(key->bmbt.br_startoff),
+ cur->bc_rec.b.br_startoff);
}
-STATIC int64_t
-xfs_bmbt_diff_two_keys(
+STATIC int
+xfs_bmbt_cmp_two_keys(
struct xfs_btree_cur *cur,
const union xfs_btree_key *k1,
const union xfs_btree_key *k2,
const union xfs_btree_key *mask)
{
- uint64_t a = be64_to_cpu(k1->bmbt.br_startoff);
- uint64_t b = be64_to_cpu(k2->bmbt.br_startoff);
-
ASSERT(!mask || mask->bmbt.br_startoff);
- /*
- * Note: This routine previously casted a and b to int64 and subtracted
- * them to generate a result. This lead to problems if b was the
- * "maximum" key value (all ones) being signed incorrectly, hence this
- * somewhat less efficient version.
- */
- if (a > b)
- return 1;
- if (b > a)
- return -1;
- return 0;
+ return cmp_int(be64_to_cpu(k1->bmbt.br_startoff),
+ be64_to_cpu(k2->bmbt.br_startoff));
}
static xfs_failaddr_t
@@ -647,8 +635,8 @@ const struct xfs_btree_ops xfs_bmbt_ops = {
.init_key_from_rec = xfs_bmbt_init_key_from_rec,
.init_high_key_from_rec = xfs_bmbt_init_high_key_from_rec,
.init_rec_from_cur = xfs_bmbt_init_rec_from_cur,
- .key_diff = xfs_bmbt_key_diff,
- .diff_two_keys = xfs_bmbt_diff_two_keys,
+ .cmp_key_with_cur = xfs_bmbt_cmp_key_with_cur,
+ .cmp_two_keys = xfs_bmbt_cmp_two_keys,
.buf_ops = &xfs_bmbt_buf_ops,
.keys_inorder = xfs_bmbt_keys_inorder,
.recs_inorder = xfs_bmbt_recs_inorder,
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 299ce7fd11b0..a61211d253f1 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -1985,7 +1985,7 @@ xfs_btree_lookup(
int *stat) /* success/failure */
{
struct xfs_btree_block *block; /* current btree block */
- int64_t diff; /* difference for the current key */
+ int cmp_r; /* current key comparison result */
int error; /* error return value */
int keyno; /* current key number */
int level; /* level in the btree */
@@ -2013,13 +2013,13 @@ xfs_btree_lookup(
* on the lookup record, then follow the corresponding block
* pointer down to the next level.
*/
- for (level = cur->bc_nlevels - 1, diff = 1; level >= 0; level--) {
+ for (level = cur->bc_nlevels - 1, cmp_r = 1; level >= 0; level--) {
/* Get the block we need to do the lookup on. */
error = xfs_btree_lookup_get_block(cur, level, pp, &block);
if (error)
goto error0;
- if (diff == 0) {
+ if (cmp_r == 0) {
/*
* If we already had a key match at a higher level, we
* know we need to use the first entry in this block.
@@ -2065,15 +2065,16 @@ xfs_btree_lookup(
keyno, block, &key);
/*
- * Compute difference to get next direction:
+ * Compute comparison result to get next
+ * direction:
* - less than, move right
* - greater than, move left
* - equal, we're done
*/
- diff = cur->bc_ops->key_diff(cur, kp);
- if (diff < 0)
+ cmp_r = cur->bc_ops->cmp_key_with_cur(cur, kp);
+ if (cmp_r < 0)
low = keyno + 1;
- else if (diff > 0)
+ else if (cmp_r > 0)
high = keyno - 1;
else
break;
@@ -2089,7 +2090,7 @@ xfs_btree_lookup(
* If we moved left, need the previous key number,
* unless there isn't one.
*/
- if (diff > 0 && --keyno < 1)
+ if (cmp_r > 0 && --keyno < 1)
keyno = 1;
pp = xfs_btree_ptr_addr(cur, keyno, block);
@@ -2102,7 +2103,7 @@ xfs_btree_lookup(
}
/* Done with the search. See if we need to adjust the results. */
- if (dir != XFS_LOOKUP_LE && diff < 0) {
+ if (dir != XFS_LOOKUP_LE && cmp_r < 0) {
keyno++;
/*
* If ge search and we went off the end of the block, but it's
@@ -2125,14 +2126,14 @@ xfs_btree_lookup(
*stat = 1;
return 0;
}
- } else if (dir == XFS_LOOKUP_LE && diff > 0)
+ } else if (dir == XFS_LOOKUP_LE && cmp_r > 0)
keyno--;
cur->bc_levels[0].ptr = keyno;
/* Return if we succeeded or not. */
if (keyno == 0 || keyno > xfs_btree_get_numrecs(block))
*stat = 0;
- else if (dir != XFS_LOOKUP_EQ || diff == 0)
+ else if (dir != XFS_LOOKUP_EQ || cmp_r == 0)
*stat = 1;
else
*stat = 0;
@@ -5058,7 +5059,7 @@ xfs_btree_simple_query_range(
int error;
ASSERT(cur->bc_ops->init_high_key_from_rec);
- ASSERT(cur->bc_ops->diff_two_keys);
+ ASSERT(cur->bc_ops->cmp_two_keys);
/*
* Find the leftmost record. The btree cursor must be set
@@ -5352,15 +5353,15 @@ xfs_btree_count_blocks(
}
/* Compare two btree pointers. */
-int64_t
-xfs_btree_diff_two_ptrs(
+int
+xfs_btree_cmp_two_ptrs(
struct xfs_btree_cur *cur,
const union xfs_btree_ptr *a,
const union xfs_btree_ptr *b)
{
if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN)
- return (int64_t)be64_to_cpu(a->l) - be64_to_cpu(b->l);
- return (int64_t)be32_to_cpu(a->s) - be32_to_cpu(b->s);
+ return cmp_int(be64_to_cpu(a->l), be64_to_cpu(b->l));
+ return cmp_int(be32_to_cpu(a->s), be32_to_cpu(b->s));
}
struct xfs_btree_has_records {
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 355b304696e6..60e78572e725 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -171,20 +171,23 @@ struct xfs_btree_ops {
void (*init_high_key_from_rec)(union xfs_btree_key *key,
const union xfs_btree_rec *rec);
- /* difference between key value and cursor value */
- int64_t (*key_diff)(struct xfs_btree_cur *cur,
- const union xfs_btree_key *key);
+ /*
+ * Compare key value and cursor value -- positive if key > cur,
+ * negative if key < cur, and zero if equal.
+ */
+ int (*cmp_key_with_cur)(struct xfs_btree_cur *cur,
+ const union xfs_btree_key *key);
/*
- * Difference between key2 and key1 -- positive if key1 > key2,
- * negative if key1 < key2, and zero if equal. If the @mask parameter
- * is non NULL, each key field to be used in the comparison must
- * contain a nonzero value.
+ * Compare key1 and key2 -- positive if key1 > key2, negative if
+ * key1 < key2, and zero if equal. If the @mask parameter is non NULL,
+ * each key field to be used in the comparison must contain a nonzero
+ * value.
*/
- int64_t (*diff_two_keys)(struct xfs_btree_cur *cur,
- const union xfs_btree_key *key1,
- const union xfs_btree_key *key2,
- const union xfs_btree_key *mask);
+ int (*cmp_two_keys)(struct xfs_btree_cur *cur,
+ const union xfs_btree_key *key1,
+ const union xfs_btree_key *key2,
+ const union xfs_btree_key *mask);
const struct xfs_buf_ops *buf_ops;
@@ -516,9 +519,9 @@ struct xfs_btree_block *xfs_btree_get_block(struct xfs_btree_cur *cur,
int level, struct xfs_buf **bpp);
bool xfs_btree_ptr_is_null(struct xfs_btree_cur *cur,
const union xfs_btree_ptr *ptr);
-int64_t xfs_btree_diff_two_ptrs(struct xfs_btree_cur *cur,
- const union xfs_btree_ptr *a,
- const union xfs_btree_ptr *b);
+int xfs_btree_cmp_two_ptrs(struct xfs_btree_cur *cur,
+ const union xfs_btree_ptr *a,
+ const union xfs_btree_ptr *b);
void xfs_btree_get_sibling(struct xfs_btree_cur *cur,
struct xfs_btree_block *block,
union xfs_btree_ptr *ptr, int lr);
@@ -546,7 +549,7 @@ xfs_btree_keycmp_lt(
const union xfs_btree_key *key1,
const union xfs_btree_key *key2)
{
- return cur->bc_ops->diff_two_keys(cur, key1, key2, NULL) < 0;
+ return cur->bc_ops->cmp_two_keys(cur, key1, key2, NULL) < 0;
}
static inline bool
@@ -555,7 +558,7 @@ xfs_btree_keycmp_gt(
const union xfs_btree_key *key1,
const union xfs_btree_key *key2)
{
- return cur->bc_ops->diff_two_keys(cur, key1, key2, NULL) > 0;
+ return cur->bc_ops->cmp_two_keys(cur, key1, key2, NULL) > 0;
}
static inline bool
@@ -564,7 +567,7 @@ xfs_btree_keycmp_eq(
const union xfs_btree_key *key1,
const union xfs_btree_key *key2)
{
- return cur->bc_ops->diff_two_keys(cur, key1, key2, NULL) == 0;
+ return cur->bc_ops->cmp_two_keys(cur, key1, key2, NULL) == 0;
}
static inline bool
@@ -602,7 +605,7 @@ xfs_btree_masked_keycmp_lt(
const union xfs_btree_key *key2,
const union xfs_btree_key *mask)
{
- return cur->bc_ops->diff_two_keys(cur, key1, key2, mask) < 0;
+ return cur->bc_ops->cmp_two_keys(cur, key1, key2, mask) < 0;
}
static inline bool
@@ -612,7 +615,7 @@ xfs_btree_masked_keycmp_gt(
const union xfs_btree_key *key2,
const union xfs_btree_key *mask)
{
- return cur->bc_ops->diff_two_keys(cur, key1, key2, mask) > 0;
+ return cur->bc_ops->cmp_two_keys(cur, key1, key2, mask) > 0;
}
static inline bool
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 9566a7623365..779dac59b1f3 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -112,7 +112,7 @@ typedef struct xfs_sb {
uint16_t sb_sectsize; /* volume sector size, bytes */
uint16_t sb_inodesize; /* inode size, bytes */
uint16_t sb_inopblock; /* inodes per block */
- char sb_fname[XFSLABEL_MAX]; /* file system name */
+ char sb_fname[XFSLABEL_MAX] __nonstring; /* file system name */
uint8_t sb_blocklog; /* log2 of sb_blocksize */
uint8_t sb_sectlog; /* log2 of sb_sectsize */
uint8_t sb_inodelog; /* log2 of sb_inodesize */
diff --git a/fs/xfs/libxfs/xfs_group.c b/fs/xfs/libxfs/xfs_group.c
index e9d76bcdc820..792f76d2e2a0 100644
--- a/fs/xfs/libxfs/xfs_group.c
+++ b/fs/xfs/libxfs/xfs_group.c
@@ -163,7 +163,8 @@ xfs_group_free(
xfs_defer_drain_free(&xg->xg_intents_drain);
#ifdef __KERNEL__
- kfree(xg->xg_busy_extents);
+ if (xfs_group_has_extent_busy(xg->xg_mount, xg->xg_type))
+ kfree(xg->xg_busy_extents);
#endif
if (uninit)
@@ -171,7 +172,8 @@ xfs_group_free(
/* drop the mount's active reference */
xfs_group_rele(xg);
- XFS_IS_CORRUPT(mp, atomic_read(&xg->xg_active_ref) != 0);
+ XFS_IS_CORRUPT(mp, atomic_read(&xg->xg_active_ref) > 0);
+ XFS_IS_CORRUPT(mp, atomic_read(&xg->xg_active_ref) < 0);
kfree_rcu_mightsleep(xg);
}
@@ -189,9 +191,11 @@ xfs_group_insert(
xg->xg_type = type;
#ifdef __KERNEL__
- xg->xg_busy_extents = xfs_extent_busy_alloc();
- if (!xg->xg_busy_extents)
- return -ENOMEM;
+ if (xfs_group_has_extent_busy(mp, type)) {
+ xg->xg_busy_extents = xfs_extent_busy_alloc();
+ if (!xg->xg_busy_extents)
+ return -ENOMEM;
+ }
spin_lock_init(&xg->xg_state_lock);
xfs_hooks_init(&xg->xg_rmap_update_hooks);
#endif
@@ -210,7 +214,8 @@ xfs_group_insert(
out_drain:
xfs_defer_drain_free(&xg->xg_intents_drain);
#ifdef __KERNEL__
- kfree(xg->xg_busy_extents);
+ if (xfs_group_has_extent_busy(xg->xg_mount, xg->xg_type))
+ kfree(xg->xg_busy_extents);
#endif
return error;
}
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 0c47b5c6ca7d..750111634d9f 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -2801,12 +2801,35 @@ xfs_ialloc_read_agi(
set_bit(XFS_AGSTATE_AGI_INIT, &pag->pag_opstate);
}
+#ifdef DEBUG
/*
- * It's possible for these to be out of sync if
- * we are in the middle of a forced shutdown.
+ * It's possible for the AGF to be out of sync if the block device is
+ * silently dropping writes. This can happen in fstests with dmflakey
+ * enabled, which allows the buffer to be cleaned and reclaimed by
+ * memory pressure and then re-read from disk here. We will get a
+ * stale version of the AGF from disk, and nothing good can happen from
+ * here. Hence if we detect this situation, immediately shut down the
+ * filesystem.
+ *
+ * This can also happen if we are already in the middle of a forced
+ * shutdown, so don't bother checking if we are already shut down.
*/
- ASSERT(pag->pagi_freecount == be32_to_cpu(agi->agi_freecount) ||
- xfs_is_shutdown(pag_mount(pag)));
+ if (!xfs_is_shutdown(pag_mount(pag))) {
+ bool ok = true;
+
+ ok &= pag->pagi_freecount == be32_to_cpu(agi->agi_freecount);
+ ok &= pag->pagi_count == be32_to_cpu(agi->agi_count);
+
+ if (XFS_IS_CORRUPT(pag_mount(pag), !ok)) {
+ xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
+ xfs_trans_brelse(tp, agibp);
+ xfs_force_shutdown(pag_mount(pag),
+ SHUTDOWN_CORRUPT_ONDISK);
+ return -EFSCORRUPTED;
+ }
+ }
+#endif /* DEBUG */
+
if (agibpp)
*agibpp = agibp;
else
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 6f270d8f4270..100afdd66cdd 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -265,17 +265,17 @@ xfs_finobt_init_ptr_from_cur(
ptr->s = agi->agi_free_root;
}
-STATIC int64_t
-xfs_inobt_key_diff(
+STATIC int
+xfs_inobt_cmp_key_with_cur(
struct xfs_btree_cur *cur,
const union xfs_btree_key *key)
{
- return (int64_t)be32_to_cpu(key->inobt.ir_startino) -
- cur->bc_rec.i.ir_startino;
+ return cmp_int(be32_to_cpu(key->inobt.ir_startino),
+ cur->bc_rec.i.ir_startino);
}
-STATIC int64_t
-xfs_inobt_diff_two_keys(
+STATIC int
+xfs_inobt_cmp_two_keys(
struct xfs_btree_cur *cur,
const union xfs_btree_key *k1,
const union xfs_btree_key *k2,
@@ -283,8 +283,8 @@ xfs_inobt_diff_two_keys(
{
ASSERT(!mask || mask->inobt.ir_startino);
- return (int64_t)be32_to_cpu(k1->inobt.ir_startino) -
- be32_to_cpu(k2->inobt.ir_startino);
+ return cmp_int(be32_to_cpu(k1->inobt.ir_startino),
+ be32_to_cpu(k2->inobt.ir_startino));
}
static xfs_failaddr_t
@@ -430,9 +430,9 @@ const struct xfs_btree_ops xfs_inobt_ops = {
.init_high_key_from_rec = xfs_inobt_init_high_key_from_rec,
.init_rec_from_cur = xfs_inobt_init_rec_from_cur,
.init_ptr_from_cur = xfs_inobt_init_ptr_from_cur,
- .key_diff = xfs_inobt_key_diff,
+ .cmp_key_with_cur = xfs_inobt_cmp_key_with_cur,
.buf_ops = &xfs_inobt_buf_ops,
- .diff_two_keys = xfs_inobt_diff_two_keys,
+ .cmp_two_keys = xfs_inobt_cmp_two_keys,
.keys_inorder = xfs_inobt_keys_inorder,
.recs_inorder = xfs_inobt_recs_inorder,
.keys_contiguous = xfs_inobt_keys_contiguous,
@@ -460,9 +460,9 @@ const struct xfs_btree_ops xfs_finobt_ops = {
.init_high_key_from_rec = xfs_inobt_init_high_key_from_rec,
.init_rec_from_cur = xfs_inobt_init_rec_from_cur,
.init_ptr_from_cur = xfs_finobt_init_ptr_from_cur,
- .key_diff = xfs_inobt_key_diff,
+ .cmp_key_with_cur = xfs_inobt_cmp_key_with_cur,
.buf_ops = &xfs_finobt_buf_ops,
- .diff_two_keys = xfs_inobt_diff_two_keys,
+ .cmp_two_keys = xfs_inobt_cmp_two_keys,
.keys_inorder = xfs_inobt_keys_inorder,
.recs_inorder = xfs_inobt_recs_inorder,
.keys_contiguous = xfs_inobt_keys_contiguous,
diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h
index 66c7916fb5cd..95de23095030 100644
--- a/fs/xfs/libxfs/xfs_log_recover.h
+++ b/fs/xfs/libxfs/xfs_log_recover.h
@@ -104,7 +104,7 @@ struct xlog_recover_item {
struct list_head ri_list;
int ri_cnt; /* count of regions found */
int ri_total; /* total regions */
- struct xfs_log_iovec *ri_buf; /* ptr to regions buffer */
+ struct kvec *ri_buf; /* ptr to regions buffer */
const struct xlog_recover_item_ops *ri_ops;
};
@@ -117,7 +117,7 @@ struct xlog_recover {
struct list_head r_itemq; /* q for items */
};
-#define ITEM_TYPE(i) (*(unsigned short *)(i)->ri_buf[0].i_addr)
+#define ITEM_TYPE(i) (*(unsigned short *)(i)->ri_buf[0].iov_base)
#define XLOG_RECOVER_CRCPASS 0
#define XLOG_RECOVER_PASS1 1
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index cebe83f7842a..897784037483 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -2099,9 +2099,7 @@ xfs_refcount_recover_cow_leftovers(
* recording the CoW debris we cancel the (empty) transaction
* and everything goes away cleanly.
*/
- error = xfs_trans_alloc_empty(mp, &tp);
- if (error)
- return error;
+ tp = xfs_trans_alloc_empty(mp);
if (isrt) {
xfs_rtgroup_lock(to_rtg(xg), XFS_RTGLOCK_REFCOUNT);
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 54505fee1852..06da3ca14727 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -174,8 +174,8 @@ xfs_refcountbt_init_ptr_from_cur(
ptr->s = agf->agf_refcount_root;
}
-STATIC int64_t
-xfs_refcountbt_key_diff(
+STATIC int
+xfs_refcountbt_cmp_key_with_cur(
struct xfs_btree_cur *cur,
const union xfs_btree_key *key)
{
@@ -185,11 +185,11 @@ xfs_refcountbt_key_diff(
start = xfs_refcount_encode_startblock(irec->rc_startblock,
irec->rc_domain);
- return (int64_t)be32_to_cpu(kp->rc_startblock) - start;
+ return cmp_int(be32_to_cpu(kp->rc_startblock), start);
}
-STATIC int64_t
-xfs_refcountbt_diff_two_keys(
+STATIC int
+xfs_refcountbt_cmp_two_keys(
struct xfs_btree_cur *cur,
const union xfs_btree_key *k1,
const union xfs_btree_key *k2,
@@ -197,8 +197,8 @@ xfs_refcountbt_diff_two_keys(
{
ASSERT(!mask || mask->refc.rc_startblock);
- return (int64_t)be32_to_cpu(k1->refc.rc_startblock) -
- be32_to_cpu(k2->refc.rc_startblock);
+ return cmp_int(be32_to_cpu(k1->refc.rc_startblock),
+ be32_to_cpu(k2->refc.rc_startblock));
}
STATIC xfs_failaddr_t
@@ -339,9 +339,9 @@ const struct xfs_btree_ops xfs_refcountbt_ops = {
.init_high_key_from_rec = xfs_refcountbt_init_high_key_from_rec,
.init_rec_from_cur = xfs_refcountbt_init_rec_from_cur,
.init_ptr_from_cur = xfs_refcountbt_init_ptr_from_cur,
- .key_diff = xfs_refcountbt_key_diff,
+ .cmp_key_with_cur = xfs_refcountbt_cmp_key_with_cur,
.buf_ops = &xfs_refcountbt_buf_ops,
- .diff_two_keys = xfs_refcountbt_diff_two_keys,
+ .cmp_two_keys = xfs_refcountbt_cmp_two_keys,
.keys_inorder = xfs_refcountbt_keys_inorder,
.recs_inorder = xfs_refcountbt_recs_inorder,
.keys_contiguous = xfs_refcountbt_keys_contiguous,
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 2cab694ac58a..bf16aee50d73 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -243,38 +243,22 @@ static inline uint64_t offset_keymask(uint64_t offset)
return offset & ~XFS_RMAP_OFF_UNWRITTEN;
}
-STATIC int64_t
-xfs_rmapbt_key_diff(
+STATIC int
+xfs_rmapbt_cmp_key_with_cur(
struct xfs_btree_cur *cur,
const union xfs_btree_key *key)
{
struct xfs_rmap_irec *rec = &cur->bc_rec.r;
const struct xfs_rmap_key *kp = &key->rmap;
- __u64 x, y;
- int64_t d;
- d = (int64_t)be32_to_cpu(kp->rm_startblock) - rec->rm_startblock;
- if (d)
- return d;
-
- x = be64_to_cpu(kp->rm_owner);
- y = rec->rm_owner;
- if (x > y)
- return 1;
- else if (y > x)
- return -1;
-
- x = offset_keymask(be64_to_cpu(kp->rm_offset));
- y = offset_keymask(xfs_rmap_irec_offset_pack(rec));
- if (x > y)
- return 1;
- else if (y > x)
- return -1;
- return 0;
+ return cmp_int(be32_to_cpu(kp->rm_startblock), rec->rm_startblock) ?:
+ cmp_int(be64_to_cpu(kp->rm_owner), rec->rm_owner) ?:
+ cmp_int(offset_keymask(be64_to_cpu(kp->rm_offset)),
+ offset_keymask(xfs_rmap_irec_offset_pack(rec)));
}
-STATIC int64_t
-xfs_rmapbt_diff_two_keys(
+STATIC int
+xfs_rmapbt_cmp_two_keys(
struct xfs_btree_cur *cur,
const union xfs_btree_key *k1,
const union xfs_btree_key *k2,
@@ -282,36 +266,31 @@ xfs_rmapbt_diff_two_keys(
{
const struct xfs_rmap_key *kp1 = &k1->rmap;
const struct xfs_rmap_key *kp2 = &k2->rmap;
- int64_t d;
- __u64 x, y;
+ int d;
/* Doesn't make sense to mask off the physical space part */
ASSERT(!mask || mask->rmap.rm_startblock);
- d = (int64_t)be32_to_cpu(kp1->rm_startblock) -
- be32_to_cpu(kp2->rm_startblock);
+ d = cmp_int(be32_to_cpu(kp1->rm_startblock),
+ be32_to_cpu(kp2->rm_startblock));
if (d)
return d;
if (!mask || mask->rmap.rm_owner) {
- x = be64_to_cpu(kp1->rm_owner);
- y = be64_to_cpu(kp2->rm_owner);
- if (x > y)
- return 1;
- else if (y > x)
- return -1;
+ d = cmp_int(be64_to_cpu(kp1->rm_owner),
+ be64_to_cpu(kp2->rm_owner));
+ if (d)
+ return d;
}
if (!mask || mask->rmap.rm_offset) {
/* Doesn't make sense to allow offset but not owner */
ASSERT(!mask || mask->rmap.rm_owner);
- x = offset_keymask(be64_to_cpu(kp1->rm_offset));
- y = offset_keymask(be64_to_cpu(kp2->rm_offset));
- if (x > y)
- return 1;
- else if (y > x)
- return -1;
+ d = cmp_int(offset_keymask(be64_to_cpu(kp1->rm_offset)),
+ offset_keymask(be64_to_cpu(kp2->rm_offset)));
+ if (d)
+ return d;
}
return 0;
@@ -515,9 +494,9 @@ const struct xfs_btree_ops xfs_rmapbt_ops = {
.init_high_key_from_rec = xfs_rmapbt_init_high_key_from_rec,
.init_rec_from_cur = xfs_rmapbt_init_rec_from_cur,
.init_ptr_from_cur = xfs_rmapbt_init_ptr_from_cur,
- .key_diff = xfs_rmapbt_key_diff,
+ .cmp_key_with_cur = xfs_rmapbt_cmp_key_with_cur,
.buf_ops = &xfs_rmapbt_buf_ops,
- .diff_two_keys = xfs_rmapbt_diff_two_keys,
+ .cmp_two_keys = xfs_rmapbt_cmp_two_keys,
.keys_inorder = xfs_rmapbt_keys_inorder,
.recs_inorder = xfs_rmapbt_recs_inorder,
.keys_contiguous = xfs_rmapbt_keys_contiguous,
@@ -632,9 +611,9 @@ const struct xfs_btree_ops xfs_rmapbt_mem_ops = {
.init_high_key_from_rec = xfs_rmapbt_init_high_key_from_rec,
.init_rec_from_cur = xfs_rmapbt_init_rec_from_cur,
.init_ptr_from_cur = xfbtree_init_ptr_from_cur,
- .key_diff = xfs_rmapbt_key_diff,
+ .cmp_key_with_cur = xfs_rmapbt_cmp_key_with_cur,
.buf_ops = &xfs_rmapbt_mem_buf_ops,
- .diff_two_keys = xfs_rmapbt_diff_two_keys,
+ .cmp_two_keys = xfs_rmapbt_cmp_two_keys,
.keys_inorder = xfs_rmapbt_keys_inorder,
.recs_inorder = xfs_rmapbt_recs_inorder,
.keys_contiguous = xfs_rmapbt_keys_contiguous,
diff --git a/fs/xfs/libxfs/xfs_rtrefcount_btree.c b/fs/xfs/libxfs/xfs_rtrefcount_btree.c
index 3db5e7a4a945..ac11e94b42ae 100644
--- a/fs/xfs/libxfs/xfs_rtrefcount_btree.c
+++ b/fs/xfs/libxfs/xfs_rtrefcount_btree.c
@@ -156,8 +156,8 @@ xfs_rtrefcountbt_init_ptr_from_cur(
ptr->l = 0;
}
-STATIC int64_t
-xfs_rtrefcountbt_key_diff(
+STATIC int
+xfs_rtrefcountbt_cmp_key_with_cur(
struct xfs_btree_cur *cur,
const union xfs_btree_key *key)
{
@@ -167,11 +167,11 @@ xfs_rtrefcountbt_key_diff(
start = xfs_refcount_encode_startblock(irec->rc_startblock,
irec->rc_domain);
- return (int64_t)be32_to_cpu(kp->rc_startblock) - start;
+ return cmp_int(be32_to_cpu(kp->rc_startblock), start);
}
-STATIC int64_t
-xfs_rtrefcountbt_diff_two_keys(
+STATIC int
+xfs_rtrefcountbt_cmp_two_keys(
struct xfs_btree_cur *cur,
const union xfs_btree_key *k1,
const union xfs_btree_key *k2,
@@ -179,8 +179,8 @@ xfs_rtrefcountbt_diff_two_keys(
{
ASSERT(!mask || mask->refc.rc_startblock);
- return (int64_t)be32_to_cpu(k1->refc.rc_startblock) -
- be32_to_cpu(k2->refc.rc_startblock);
+ return cmp_int(be32_to_cpu(k1->refc.rc_startblock),
+ be32_to_cpu(k2->refc.rc_startblock));
}
static xfs_failaddr_t
@@ -387,9 +387,9 @@ const struct xfs_btree_ops xfs_rtrefcountbt_ops = {
.init_high_key_from_rec = xfs_rtrefcountbt_init_high_key_from_rec,
.init_rec_from_cur = xfs_rtrefcountbt_init_rec_from_cur,
.init_ptr_from_cur = xfs_rtrefcountbt_init_ptr_from_cur,
- .key_diff = xfs_rtrefcountbt_key_diff,
+ .cmp_key_with_cur = xfs_rtrefcountbt_cmp_key_with_cur,
.buf_ops = &xfs_rtrefcountbt_buf_ops,
- .diff_two_keys = xfs_rtrefcountbt_diff_two_keys,
+ .cmp_two_keys = xfs_rtrefcountbt_cmp_two_keys,
.keys_inorder = xfs_rtrefcountbt_keys_inorder,
.recs_inorder = xfs_rtrefcountbt_recs_inorder,
.keys_contiguous = xfs_rtrefcountbt_keys_contiguous,
diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.c b/fs/xfs/libxfs/xfs_rtrmap_btree.c
index 9bdc2cbfc113..55f903165769 100644
--- a/fs/xfs/libxfs/xfs_rtrmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rtrmap_btree.c
@@ -185,38 +185,22 @@ static inline uint64_t offset_keymask(uint64_t offset)
return offset & ~XFS_RMAP_OFF_UNWRITTEN;
}
-STATIC int64_t
-xfs_rtrmapbt_key_diff(
+STATIC int
+xfs_rtrmapbt_cmp_key_with_cur(
struct xfs_btree_cur *cur,
const union xfs_btree_key *key)
{
struct xfs_rmap_irec *rec = &cur->bc_rec.r;
const struct xfs_rmap_key *kp = &key->rmap;
- __u64 x, y;
- int64_t d;
- d = (int64_t)be32_to_cpu(kp->rm_startblock) - rec->rm_startblock;
- if (d)
- return d;
-
- x = be64_to_cpu(kp->rm_owner);
- y = rec->rm_owner;
- if (x > y)
- return 1;
- else if (y > x)
- return -1;
-
- x = offset_keymask(be64_to_cpu(kp->rm_offset));
- y = offset_keymask(xfs_rmap_irec_offset_pack(rec));
- if (x > y)
- return 1;
- else if (y > x)
- return -1;
- return 0;
+ return cmp_int(be32_to_cpu(kp->rm_startblock), rec->rm_startblock) ?:
+ cmp_int(be64_to_cpu(kp->rm_owner), rec->rm_owner) ?:
+ cmp_int(offset_keymask(be64_to_cpu(kp->rm_offset)),
+ offset_keymask(xfs_rmap_irec_offset_pack(rec)));
}
-STATIC int64_t
-xfs_rtrmapbt_diff_two_keys(
+STATIC int
+xfs_rtrmapbt_cmp_two_keys(
struct xfs_btree_cur *cur,
const union xfs_btree_key *k1,
const union xfs_btree_key *k2,
@@ -224,36 +208,31 @@ xfs_rtrmapbt_diff_two_keys(
{
const struct xfs_rmap_key *kp1 = &k1->rmap;
const struct xfs_rmap_key *kp2 = &k2->rmap;
- int64_t d;
- __u64 x, y;
+ int d;
/* Doesn't make sense to mask off the physical space part */
ASSERT(!mask || mask->rmap.rm_startblock);
- d = (int64_t)be32_to_cpu(kp1->rm_startblock) -
- be32_to_cpu(kp2->rm_startblock);
+ d = cmp_int(be32_to_cpu(kp1->rm_startblock),
+ be32_to_cpu(kp2->rm_startblock));
if (d)
return d;
if (!mask || mask->rmap.rm_owner) {
- x = be64_to_cpu(kp1->rm_owner);
- y = be64_to_cpu(kp2->rm_owner);
- if (x > y)
- return 1;
- else if (y > x)
- return -1;
+ d = cmp_int(be64_to_cpu(kp1->rm_owner),
+ be64_to_cpu(kp2->rm_owner));
+ if (d)
+ return d;
}
if (!mask || mask->rmap.rm_offset) {
/* Doesn't make sense to allow offset but not owner */
ASSERT(!mask || mask->rmap.rm_owner);
- x = offset_keymask(be64_to_cpu(kp1->rm_offset));
- y = offset_keymask(be64_to_cpu(kp2->rm_offset));
- if (x > y)
- return 1;
- else if (y > x)
- return -1;
+ d = cmp_int(offset_keymask(be64_to_cpu(kp1->rm_offset)),
+ offset_keymask(be64_to_cpu(kp2->rm_offset)));
+ if (d)
+ return d;
}
return 0;
@@ -511,9 +490,9 @@ const struct xfs_btree_ops xfs_rtrmapbt_ops = {
.init_high_key_from_rec = xfs_rtrmapbt_init_high_key_from_rec,
.init_rec_from_cur = xfs_rtrmapbt_init_rec_from_cur,
.init_ptr_from_cur = xfs_rtrmapbt_init_ptr_from_cur,
- .key_diff = xfs_rtrmapbt_key_diff,
+ .cmp_key_with_cur = xfs_rtrmapbt_cmp_key_with_cur,
.buf_ops = &xfs_rtrmapbt_buf_ops,
- .diff_two_keys = xfs_rtrmapbt_diff_two_keys,
+ .cmp_two_keys = xfs_rtrmapbt_cmp_two_keys,
.keys_inorder = xfs_rtrmapbt_keys_inorder,
.recs_inorder = xfs_rtrmapbt_recs_inorder,
.keys_contiguous = xfs_rtrmapbt_keys_contiguous,
@@ -620,9 +599,9 @@ const struct xfs_btree_ops xfs_rtrmapbt_mem_ops = {
.init_high_key_from_rec = xfs_rtrmapbt_init_high_key_from_rec,
.init_rec_from_cur = xfs_rtrmapbt_init_rec_from_cur,
.init_ptr_from_cur = xfbtree_init_ptr_from_cur,
- .key_diff = xfs_rtrmapbt_key_diff,
+ .cmp_key_with_cur = xfs_rtrmapbt_cmp_key_with_cur,
.buf_ops = &xfs_rtrmapbt_mem_buf_ops,
- .diff_two_keys = xfs_rtrmapbt_diff_two_keys,
+ .cmp_two_keys = xfs_rtrmapbt_cmp_two_keys,
.keys_inorder = xfs_rtrmapbt_keys_inorder,
.recs_inorder = xfs_rtrmapbt_recs_inorder,
.keys_contiguous = xfs_rtrmapbt_keys_contiguous,
diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index fe678a0438bc..cd6f0ff382a7 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -306,7 +306,7 @@ xchk_btree_block_check_sibling(
if (pbp)
xchk_buffer_recheck(bs->sc, pbp);
- if (xfs_btree_diff_two_ptrs(cur, pp, sibling))
+ if (xfs_btree_cmp_two_ptrs(cur, pp, sibling))
xchk_btree_set_corrupt(bs->sc, cur, level);
out:
xfs_btree_del_cursor(ncur, XFS_BTREE_ERROR);
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 28ad341df8ee..2ef7742be7d3 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -866,11 +866,11 @@ xchk_trans_cancel(
sc->tp = NULL;
}
-int
+void
xchk_trans_alloc_empty(
struct xfs_scrub *sc)
{
- return xfs_trans_alloc_empty(sc->mp, &sc->tp);
+ sc->tp = xfs_trans_alloc_empty(sc->mp);
}
/*
@@ -892,7 +892,8 @@ xchk_trans_alloc(
return xfs_trans_alloc(sc->mp, &M_RES(sc->mp)->tr_itruncate,
resblks, 0, 0, &sc->tp);
- return xchk_trans_alloc_empty(sc);
+ xchk_trans_alloc_empty(sc);
+ return 0;
}
/* Set us up with a transaction and an empty context. */
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 19877d99f255..ddbc065c798c 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -7,7 +7,7 @@
#define __XFS_SCRUB_COMMON_H__
int xchk_trans_alloc(struct xfs_scrub *sc, uint resblks);
-int xchk_trans_alloc_empty(struct xfs_scrub *sc);
+void xchk_trans_alloc_empty(struct xfs_scrub *sc);
void xchk_trans_cancel(struct xfs_scrub *sc);
bool xchk_process_error(struct xfs_scrub *sc, xfs_agnumber_t agno,
diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c
index 249313882108..8d3b550990b5 100644
--- a/fs/xfs/scrub/dir_repair.c
+++ b/fs/xfs/scrub/dir_repair.c
@@ -1289,9 +1289,7 @@ xrep_dir_scan_dirtree(
if (sc->ilock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL))
xchk_iunlock(sc, sc->ilock_flags & (XFS_ILOCK_SHARED |
XFS_ILOCK_EXCL));
- error = xchk_trans_alloc_empty(sc);
- if (error)
- return error;
+ xchk_trans_alloc_empty(sc);
while ((error = xchk_iscan_iter(&rd->pscan.iscan, &ip)) == 1) {
bool flush;
@@ -1317,9 +1315,7 @@ xrep_dir_scan_dirtree(
if (error)
break;
- error = xchk_trans_alloc_empty(sc);
- if (error)
- break;
+ xchk_trans_alloc_empty(sc);
}
if (xchk_should_terminate(sc, &error))
diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c
index 9b598c5790ad..cebd0d526926 100644
--- a/fs/xfs/scrub/fscounters.c
+++ b/fs/xfs/scrub/fscounters.c
@@ -237,7 +237,8 @@ xchk_setup_fscounters(
return error;
}
- return xchk_trans_alloc_empty(sc);
+ xchk_trans_alloc_empty(sc);
+ return 0;
}
/*
diff --git a/fs/xfs/scrub/metapath.c b/fs/xfs/scrub/metapath.c
index e21c16fbd15d..14939d7de349 100644
--- a/fs/xfs/scrub/metapath.c
+++ b/fs/xfs/scrub/metapath.c
@@ -318,9 +318,7 @@ xchk_metapath(
return 0;
}
- error = xchk_trans_alloc_empty(sc);
- if (error)
- return error;
+ xchk_trans_alloc_empty(sc);
error = xchk_metapath_ilock_both(mpath);
if (error)
diff --git a/fs/xfs/scrub/nlinks.c b/fs/xfs/scrub/nlinks.c
index 4a47d0aabf73..26721fab5cab 100644
--- a/fs/xfs/scrub/nlinks.c
+++ b/fs/xfs/scrub/nlinks.c
@@ -555,9 +555,7 @@ xchk_nlinks_collect(
* do not take sb_internal.
*/
xchk_trans_cancel(sc);
- error = xchk_trans_alloc_empty(sc);
- if (error)
- return error;
+ xchk_trans_alloc_empty(sc);
while ((error = xchk_iscan_iter(&xnc->collect_iscan, &ip)) == 1) {
if (S_ISDIR(VFS_I(ip)->i_mode))
@@ -880,9 +878,7 @@ xchk_nlinks_compare(
* inactivation workqueue.
*/
xchk_trans_cancel(sc);
- error = xchk_trans_alloc_empty(sc);
- if (error)
- return error;
+ xchk_trans_alloc_empty(sc);
/*
* Use the inobt to walk all allocated inodes to compare the link
diff --git a/fs/xfs/scrub/nlinks_repair.c b/fs/xfs/scrub/nlinks_repair.c
index 4ebdee095428..6ef2ee9c3814 100644
--- a/fs/xfs/scrub/nlinks_repair.c
+++ b/fs/xfs/scrub/nlinks_repair.c
@@ -340,9 +340,7 @@ xrep_nlinks(
* We can only push the inactivation workqueues with an empty
* transaction.
*/
- error = xchk_trans_alloc_empty(sc);
- if (error)
- break;
+ xchk_trans_alloc_empty(sc);
}
xchk_iscan_iter_finish(&xnc->compare_iscan);
xchk_iscan_teardown(&xnc->compare_iscan);
diff --git a/fs/xfs/scrub/parent_repair.c b/fs/xfs/scrub/parent_repair.c
index 31bfe10be22a..2949feda6271 100644
--- a/fs/xfs/scrub/parent_repair.c
+++ b/fs/xfs/scrub/parent_repair.c
@@ -569,9 +569,7 @@ xrep_parent_scan_dirtree(
if (sc->ilock_flags & (XFS_ILOCK_SHARED | XFS_ILOCK_EXCL))
xchk_iunlock(sc, sc->ilock_flags & (XFS_ILOCK_SHARED |
XFS_ILOCK_EXCL));
- error = xchk_trans_alloc_empty(sc);
- if (error)
- return error;
+ xchk_trans_alloc_empty(sc);
while ((error = xchk_iscan_iter(&rp->pscan.iscan, &ip)) == 1) {
bool flush;
@@ -597,9 +595,7 @@ xrep_parent_scan_dirtree(
if (error)
break;
- error = xchk_trans_alloc_empty(sc);
- if (error)
- break;
+ xchk_trans_alloc_empty(sc);
}
if (xchk_should_terminate(sc, &error))
@@ -1099,9 +1095,7 @@ xrep_parent_flush_xattrs(
xrep_tempfile_iounlock(rp->sc);
/* Recreate the empty transaction and relock the inode. */
- error = xchk_trans_alloc_empty(rp->sc);
- if (error)
- return error;
+ xchk_trans_alloc_empty(rp->sc);
xchk_ilock(rp->sc, XFS_ILOCK_EXCL);
return 0;
}
diff --git a/fs/xfs/scrub/quotacheck.c b/fs/xfs/scrub/quotacheck.c
index dc4033b91e44..e4105aaafe84 100644
--- a/fs/xfs/scrub/quotacheck.c
+++ b/fs/xfs/scrub/quotacheck.c
@@ -505,9 +505,7 @@ xqcheck_collect_counts(
* transactions do not take sb_internal.
*/
xchk_trans_cancel(sc);
- error = xchk_trans_alloc_empty(sc);
- if (error)
- return error;
+ xchk_trans_alloc_empty(sc);
while ((error = xchk_iscan_iter(&xqc->iscan, &ip)) == 1) {
error = xqcheck_collect_inode(xqc, ip);
diff --git a/fs/xfs/scrub/rcbag_btree.c b/fs/xfs/scrub/rcbag_btree.c
index 709356dc6256..9a4ef823c5a7 100644
--- a/fs/xfs/scrub/rcbag_btree.c
+++ b/fs/xfs/scrub/rcbag_btree.c
@@ -47,29 +47,20 @@ rcbagbt_init_rec_from_cur(
bag_rec->rbg_refcount = bag_irec->rbg_refcount;
}
-STATIC int64_t
-rcbagbt_key_diff(
+STATIC int
+rcbagbt_cmp_key_with_cur(
struct xfs_btree_cur *cur,
const union xfs_btree_key *key)
{
struct rcbag_rec *rec = (struct rcbag_rec *)&cur->bc_rec;
const struct rcbag_key *kp = (const struct rcbag_key *)key;
- if (kp->rbg_startblock > rec->rbg_startblock)
- return 1;
- if (kp->rbg_startblock < rec->rbg_startblock)
- return -1;
-
- if (kp->rbg_blockcount > rec->rbg_blockcount)
- return 1;
- if (kp->rbg_blockcount < rec->rbg_blockcount)
- return -1;
-
- return 0;
+ return cmp_int(kp->rbg_startblock, rec->rbg_startblock) ?:
+ cmp_int(kp->rbg_blockcount, rec->rbg_blockcount);
}
-STATIC int64_t
-rcbagbt_diff_two_keys(
+STATIC int
+rcbagbt_cmp_two_keys(
struct xfs_btree_cur *cur,
const union xfs_btree_key *k1,
const union xfs_btree_key *k2,
@@ -80,17 +71,8 @@ rcbagbt_diff_two_keys(
ASSERT(mask == NULL);
- if (kp1->rbg_startblock > kp2->rbg_startblock)
- return 1;
- if (kp1->rbg_startblock < kp2->rbg_startblock)
- return -1;
-
- if (kp1->rbg_blockcount > kp2->rbg_blockcount)
- return 1;
- if (kp1->rbg_blockcount < kp2->rbg_blockcount)
- return -1;
-
- return 0;
+ return cmp_int(kp1->rbg_startblock, kp2->rbg_startblock) ?:
+ cmp_int(kp1->rbg_blockcount, kp2->rbg_blockcount);
}
STATIC int
@@ -201,9 +183,9 @@ static const struct xfs_btree_ops rcbagbt_mem_ops = {
.init_key_from_rec = rcbagbt_init_key_from_rec,
.init_rec_from_cur = rcbagbt_init_rec_from_cur,
.init_ptr_from_cur = xfbtree_init_ptr_from_cur,
- .key_diff = rcbagbt_key_diff,
+ .cmp_key_with_cur = rcbagbt_cmp_key_with_cur,
.buf_ops = &rcbagbt_mem_buf_ops,
- .diff_two_keys = rcbagbt_diff_two_keys,
+ .cmp_two_keys = rcbagbt_cmp_two_keys,
.keys_inorder = rcbagbt_keys_inorder,
.recs_inorder = rcbagbt_recs_inorder,
};
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index f8f9ed30f56b..d00c18954a26 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -1269,42 +1269,6 @@ xrep_setup_xfbtree(
}
/*
- * Create a dummy transaction for use in a live update hook function. This
- * function MUST NOT be called from regular repair code because the current
- * process' transaction is saved via the cookie.
- */
-int
-xrep_trans_alloc_hook_dummy(
- struct xfs_mount *mp,
- void **cookiep,
- struct xfs_trans **tpp)
-{
- int error;
-
- *cookiep = current->journal_info;
- current->journal_info = NULL;
-
- error = xfs_trans_alloc_empty(mp, tpp);
- if (!error)
- return 0;
-
- current->journal_info = *cookiep;
- *cookiep = NULL;
- return error;
-}
-
-/* Cancel a dummy transaction used by a live update hook function. */
-void
-xrep_trans_cancel_hook_dummy(
- void **cookiep,
- struct xfs_trans *tp)
-{
- xfs_trans_cancel(tp);
- current->journal_info = *cookiep;
- *cookiep = NULL;
-}
-
-/*
* See if this buffer can pass the given ->verify_struct() function.
*
* If the buffer already has ops attached and they're not the ones that were
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index af0a3a9e5ed9..9c04295742c8 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -180,10 +180,6 @@ int xrep_quotacheck(struct xfs_scrub *sc);
int xrep_reinit_pagf(struct xfs_scrub *sc);
int xrep_reinit_pagi(struct xfs_scrub *sc);
-int xrep_trans_alloc_hook_dummy(struct xfs_mount *mp, void **cookiep,
- struct xfs_trans **tpp);
-void xrep_trans_cancel_hook_dummy(void **cookiep, struct xfs_trans *tp);
-
bool xrep_buf_verify_struct(struct xfs_buf *bp, const struct xfs_buf_ops *ops);
void xrep_inode_set_nblocks(struct xfs_scrub *sc, int64_t new_blocks);
int xrep_reset_metafile_resv(struct xfs_scrub *sc);
diff --git a/fs/xfs/scrub/rmap_repair.c b/fs/xfs/scrub/rmap_repair.c
index f5f73078ffe2..17d4a38d735c 100644
--- a/fs/xfs/scrub/rmap_repair.c
+++ b/fs/xfs/scrub/rmap_repair.c
@@ -951,9 +951,7 @@ end_agscan:
sa->agf_bp = NULL;
sa->agi_bp = NULL;
xchk_trans_cancel(sc);
- error = xchk_trans_alloc_empty(sc);
- if (error)
- return error;
+ xchk_trans_alloc_empty(sc);
/* Iterate all AGs for inodes rmaps. */
while ((error = xchk_iscan_iter(&rr->iscan, &ip)) == 1) {
@@ -1612,7 +1610,6 @@ xrep_rmapbt_live_update(
struct xfs_mount *mp;
struct xfs_btree_cur *mcur;
struct xfs_trans *tp;
- void *txcookie;
int error;
rr = container_of(nb, struct xrep_rmap, rhook.rmap_hook.nb);
@@ -1623,9 +1620,7 @@ xrep_rmapbt_live_update(
trace_xrep_rmap_live_update(pag_group(rr->sc->sa.pag), action, p);
- error = xrep_trans_alloc_hook_dummy(mp, &txcookie, &tp);
- if (error)
- goto out_abort;
+ tp = xfs_trans_alloc_empty(mp);
mutex_lock(&rr->lock);
mcur = xfs_rmapbt_mem_cursor(rr->sc->sa.pag, tp, &rr->rmap_btree);
@@ -1639,14 +1634,13 @@ xrep_rmapbt_live_update(
if (error)
goto out_cancel;
- xrep_trans_cancel_hook_dummy(&txcookie, tp);
+ xfs_trans_cancel(tp);
mutex_unlock(&rr->lock);
return NOTIFY_DONE;
out_cancel:
xfbtree_trans_cancel(&rr->rmap_btree, tp);
- xrep_trans_cancel_hook_dummy(&txcookie, tp);
-out_abort:
+ xfs_trans_cancel(tp);
mutex_unlock(&rr->lock);
xchk_iscan_abort(&rr->iscan);
out_unlock:
diff --git a/fs/xfs/scrub/rtrmap_repair.c b/fs/xfs/scrub/rtrmap_repair.c
index fc2592c53af5..7561941a337a 100644
--- a/fs/xfs/scrub/rtrmap_repair.c
+++ b/fs/xfs/scrub/rtrmap_repair.c
@@ -580,9 +580,7 @@ xrep_rtrmap_find_rmaps(
*/
xchk_trans_cancel(sc);
xchk_rtgroup_unlock(&sc->sr);
- error = xchk_trans_alloc_empty(sc);
- if (error)
- return error;
+ xchk_trans_alloc_empty(sc);
while ((error = xchk_iscan_iter(&rr->iscan, &ip)) == 1) {
error = xrep_rtrmap_scan_inode(rr, ip);
@@ -846,7 +844,6 @@ xrep_rtrmapbt_live_update(
struct xfs_mount *mp;
struct xfs_btree_cur *mcur;
struct xfs_trans *tp;
- void *txcookie;
int error;
rr = container_of(nb, struct xrep_rtrmap, rhook.rmap_hook.nb);
@@ -857,9 +854,7 @@ xrep_rtrmapbt_live_update(
trace_xrep_rmap_live_update(rtg_group(rr->sc->sr.rtg), action, p);
- error = xrep_trans_alloc_hook_dummy(mp, &txcookie, &tp);
- if (error)
- goto out_abort;
+ tp = xfs_trans_alloc_empty(mp);
mutex_lock(&rr->lock);
mcur = xfs_rtrmapbt_mem_cursor(rr->sc->sr.rtg, tp, &rr->rtrmap_btree);
@@ -873,14 +868,13 @@ xrep_rtrmapbt_live_update(
if (error)
goto out_cancel;
- xrep_trans_cancel_hook_dummy(&txcookie, tp);
+ xfs_trans_cancel(tp);
mutex_unlock(&rr->lock);
return NOTIFY_DONE;
out_cancel:
xfbtree_trans_cancel(&rr->rtrmap_btree, tp);
- xrep_trans_cancel_hook_dummy(&txcookie, tp);
-out_abort:
+ xfs_trans_cancel(tp);
xchk_iscan_abort(&rr->iscan);
mutex_unlock(&rr->lock);
out_unlock:
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 76e24032e99a..3c3b0d25006f 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -876,10 +876,7 @@ xchk_scrubv_open_by_handle(
struct xfs_inode *ip;
int error;
- error = xfs_trans_alloc_empty(mp, &tp);
- if (error)
- return NULL;
-
+ tp = xfs_trans_alloc_empty(mp);
error = xfs_iget(mp, tp, head->svh_ino, XCHK_IGET_FLAGS, 0, &ip);
xfs_trans_cancel(tp);
if (error)
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index d7c4ced47c15..1e6e9c10cea2 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -2996,7 +2996,7 @@ DEFINE_EVENT(xrep_pptr_salvage_class, name, \
DEFINE_XREP_PPTR_SALVAGE_EVENT(xrep_xattr_salvage_pptr);
DEFINE_XREP_PPTR_SALVAGE_EVENT(xrep_xattr_insert_pptr);
-TRACE_EVENT(xrep_xattr_class,
+DECLARE_EVENT_CLASS(xrep_xattr_class,
TP_PROTO(struct xfs_inode *ip, struct xfs_inode *arg_ip),
TP_ARGS(ip, arg_ip),
TP_STRUCT__entry(
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 63151feb9c3f..1ee4f835ac3c 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -234,6 +234,47 @@ xfs_end_bio(
}
/*
+ * We cannot cancel the ioend directly on error. We may have already set other
+ * pages under writeback and hence we have to run I/O completion to mark the
+ * error state of the pages under writeback appropriately.
+ *
+ * If the folio has delalloc blocks on it, the caller is asking us to punch them
+ * out. If we don't, we can leave a stale delalloc mapping covered by a clean
+ * page that needs to be dirtied again before the delalloc mapping can be
+ * converted. This stale delalloc mapping can trip up a later direct I/O read
+ * operation on the same region.
+ *
+ * We prevent this by truncating away the delalloc regions on the folio. Because
+ * they are delalloc, we can do this without needing a transaction. Indeed - if
+ * we get ENOSPC errors, we have to be able to do this truncation without a
+ * transaction as there is no space left for block reservation (typically why
+ * we see a ENOSPC in writeback).
+ */
+static void
+xfs_discard_folio(
+ struct folio *folio,
+ loff_t pos)
+{
+ struct xfs_inode *ip = XFS_I(folio->mapping->host);
+ struct xfs_mount *mp = ip->i_mount;
+
+ if (xfs_is_shutdown(mp))
+ return;
+
+ xfs_alert_ratelimited(mp,
+ "page discard on page "PTR_FMT", inode 0x%llx, pos %llu.",
+ folio, ip->i_ino, pos);
+
+ /*
+ * The end of the punch range is always the offset of the first
+ * byte of the next folio. Hence the end offset is only dependent on the
+ * folio itself and not the start offset that is passed in.
+ */
+ xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, pos,
+ folio_pos(folio) + folio_size(folio), NULL);
+}
+
+/*
* Fast revalidation of the cached writeback mapping. Return true if the current
* mapping is valid, false otherwise.
*/
@@ -278,13 +319,12 @@ xfs_imap_valid(
static int
xfs_map_blocks(
struct iomap_writepage_ctx *wpc,
- struct inode *inode,
loff_t offset,
unsigned int len)
{
- struct xfs_inode *ip = XFS_I(inode);
+ struct xfs_inode *ip = XFS_I(wpc->inode);
struct xfs_mount *mp = ip->i_mount;
- ssize_t count = i_blocksize(inode);
+ ssize_t count = i_blocksize(wpc->inode);
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + count);
xfs_fileoff_t cow_fsb;
@@ -436,6 +476,24 @@ allocate_blocks:
return 0;
}
+static ssize_t
+xfs_writeback_range(
+ struct iomap_writepage_ctx *wpc,
+ struct folio *folio,
+ u64 offset,
+ unsigned int len,
+ u64 end_pos)
+{
+ ssize_t ret;
+
+ ret = xfs_map_blocks(wpc, offset, len);
+ if (!ret)
+ ret = iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
+ if (ret < 0)
+ xfs_discard_folio(folio, offset);
+ return ret;
+}
+
static bool
xfs_ioend_needs_wq_completion(
struct iomap_ioend *ioend)
@@ -456,79 +514,40 @@ xfs_ioend_needs_wq_completion(
}
static int
-xfs_submit_ioend(
- struct iomap_writepage_ctx *wpc,
- int status)
+xfs_writeback_submit(
+ struct iomap_writepage_ctx *wpc,
+ int error)
{
- struct iomap_ioend *ioend = wpc->ioend;
- unsigned int nofs_flag;
+ struct iomap_ioend *ioend = wpc->wb_ctx;
/*
- * We can allocate memory here while doing writeback on behalf of
- * memory reclaim. To avoid memory allocation deadlocks set the
- * task-wide nofs context for the following operations.
+ * Convert CoW extents to regular.
+ *
+ * We can allocate memory here while doing writeback on behalf of memory
+ * reclaim. To avoid memory allocation deadlocks, set the task-wide
+ * nofs context.
*/
- nofs_flag = memalloc_nofs_save();
+ if (!error && (ioend->io_flags & IOMAP_IOEND_SHARED)) {
+ unsigned int nofs_flag;
- /* Convert CoW extents to regular */
- if (!status && (ioend->io_flags & IOMAP_IOEND_SHARED)) {
- status = xfs_reflink_convert_cow(XFS_I(ioend->io_inode),
+ nofs_flag = memalloc_nofs_save();
+ error = xfs_reflink_convert_cow(XFS_I(ioend->io_inode),
ioend->io_offset, ioend->io_size);
+ memalloc_nofs_restore(nofs_flag);
}
- memalloc_nofs_restore(nofs_flag);
-
- /* send ioends that might require a transaction to the completion wq */
+ /*
+ * Send ioends that might require a transaction to the completion wq.
+ */
if (xfs_ioend_needs_wq_completion(ioend))
ioend->io_bio.bi_end_io = xfs_end_bio;
- if (status)
- return status;
- submit_bio(&ioend->io_bio);
- return 0;
-}
-
-/*
- * If the folio has delalloc blocks on it, the caller is asking us to punch them
- * out. If we don't, we can leave a stale delalloc mapping covered by a clean
- * page that needs to be dirtied again before the delalloc mapping can be
- * converted. This stale delalloc mapping can trip up a later direct I/O read
- * operation on the same region.
- *
- * We prevent this by truncating away the delalloc regions on the folio. Because
- * they are delalloc, we can do this without needing a transaction. Indeed - if
- * we get ENOSPC errors, we have to be able to do this truncation without a
- * transaction as there is no space left for block reservation (typically why
- * we see a ENOSPC in writeback).
- */
-static void
-xfs_discard_folio(
- struct folio *folio,
- loff_t pos)
-{
- struct xfs_inode *ip = XFS_I(folio->mapping->host);
- struct xfs_mount *mp = ip->i_mount;
-
- if (xfs_is_shutdown(mp))
- return;
-
- xfs_alert_ratelimited(mp,
- "page discard on page "PTR_FMT", inode 0x%llx, pos %llu.",
- folio, ip->i_ino, pos);
-
- /*
- * The end of the punch range is always the offset of the first
- * byte of the next folio. Hence the end offset is only dependent on the
- * folio itself and not the start offset that is passed in.
- */
- xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, pos,
- folio_pos(folio) + folio_size(folio), NULL);
+ return iomap_ioend_writeback_submit(wpc, error);
}
static const struct iomap_writeback_ops xfs_writeback_ops = {
- .map_blocks = xfs_map_blocks,
- .submit_ioend = xfs_submit_ioend,
- .discard_folio = xfs_discard_folio,
+ .writeback_range = xfs_writeback_range,
+ .writeback_submit = xfs_writeback_submit,
};
struct xfs_zoned_writepage_ctx {
@@ -545,11 +564,10 @@ XFS_ZWPC(struct iomap_writepage_ctx *ctx)
static int
xfs_zoned_map_blocks(
struct iomap_writepage_ctx *wpc,
- struct inode *inode,
loff_t offset,
unsigned int len)
{
- struct xfs_inode *ip = XFS_I(inode);
+ struct xfs_inode *ip = XFS_I(wpc->inode);
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset);
xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + len);
@@ -608,22 +626,44 @@ xfs_zoned_map_blocks(
return 0;
}
-static int
-xfs_zoned_submit_ioend(
+static ssize_t
+xfs_zoned_writeback_range(
struct iomap_writepage_ctx *wpc,
- int status)
+ struct folio *folio,
+ u64 offset,
+ unsigned int len,
+ u64 end_pos)
{
- wpc->ioend->io_bio.bi_end_io = xfs_end_bio;
- if (status)
- return status;
- xfs_zone_alloc_and_submit(wpc->ioend, &XFS_ZWPC(wpc)->open_zone);
+ ssize_t ret;
+
+ ret = xfs_zoned_map_blocks(wpc, offset, len);
+ if (!ret)
+ ret = iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
+ if (ret < 0)
+ xfs_discard_folio(folio, offset);
+ return ret;
+}
+
+static int
+xfs_zoned_writeback_submit(
+ struct iomap_writepage_ctx *wpc,
+ int error)
+{
+ struct iomap_ioend *ioend = wpc->wb_ctx;
+
+ ioend->io_bio.bi_end_io = xfs_end_bio;
+ if (error) {
+ ioend->io_bio.bi_status = errno_to_blk_status(error);
+ bio_endio(&ioend->io_bio);
+ return error;
+ }
+ xfs_zone_alloc_and_submit(ioend, &XFS_ZWPC(wpc)->open_zone);
return 0;
}
static const struct iomap_writeback_ops xfs_zoned_writeback_ops = {
- .map_blocks = xfs_zoned_map_blocks,
- .submit_ioend = xfs_zoned_submit_ioend,
- .discard_folio = xfs_discard_folio,
+ .writeback_range = xfs_zoned_writeback_range,
+ .writeback_submit = xfs_zoned_writeback_submit,
};
STATIC int
@@ -636,19 +676,29 @@ xfs_vm_writepages(
xfs_iflags_clear(ip, XFS_ITRUNCATED);
if (xfs_is_zoned_inode(ip)) {
- struct xfs_zoned_writepage_ctx xc = { };
+ struct xfs_zoned_writepage_ctx xc = {
+ .ctx = {
+ .inode = mapping->host,
+ .wbc = wbc,
+ .ops = &xfs_zoned_writeback_ops
+ },
+ };
int error;
- error = iomap_writepages(mapping, wbc, &xc.ctx,
- &xfs_zoned_writeback_ops);
+ error = iomap_writepages(&xc.ctx);
if (xc.open_zone)
xfs_open_zone_put(xc.open_zone);
return error;
} else {
- struct xfs_writepage_ctx wpc = { };
-
- return iomap_writepages(mapping, wbc, &wpc.ctx,
- &xfs_writeback_ops);
+ struct xfs_writepage_ctx wpc = {
+ .ctx = {
+ .inode = mapping->host,
+ .wbc = wbc,
+ .ops = &xfs_writeback_ops
+ },
+ };
+
+ return iomap_writepages(&wpc.ctx);
}
}
diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c
index f683b7a9323f..5eef3bc30bda 100644
--- a/fs/xfs/xfs_attr_item.c
+++ b/fs/xfs/xfs_attr_item.c
@@ -91,41 +91,37 @@ xfs_attri_log_nameval_alloc(
name_len + new_name_len + value_len +
new_value_len);
- nv->name.i_addr = nv + 1;
- nv->name.i_len = name_len;
- nv->name.i_type = XLOG_REG_TYPE_ATTR_NAME;
- memcpy(nv->name.i_addr, name, name_len);
+ nv->name.iov_base = nv + 1;
+ nv->name.iov_len = name_len;
+ memcpy(nv->name.iov_base, name, name_len);
if (new_name_len) {
- nv->new_name.i_addr = nv->name.i_addr + name_len;
- nv->new_name.i_len = new_name_len;
- memcpy(nv->new_name.i_addr, new_name, new_name_len);
+ nv->new_name.iov_base = nv->name.iov_base + name_len;
+ nv->new_name.iov_len = new_name_len;
+ memcpy(nv->new_name.iov_base, new_name, new_name_len);
} else {
- nv->new_name.i_addr = NULL;
- nv->new_name.i_len = 0;
+ nv->new_name.iov_base = NULL;
+ nv->new_name.iov_len = 0;
}
- nv->new_name.i_type = XLOG_REG_TYPE_ATTR_NEWNAME;
if (value_len) {
- nv->value.i_addr = nv->name.i_addr + name_len + new_name_len;
- nv->value.i_len = value_len;
- memcpy(nv->value.i_addr, value, value_len);
+ nv->value.iov_base = nv->name.iov_base + name_len + new_name_len;
+ nv->value.iov_len = value_len;
+ memcpy(nv->value.iov_base, value, value_len);
} else {
- nv->value.i_addr = NULL;
- nv->value.i_len = 0;
+ nv->value.iov_base = NULL;
+ nv->value.iov_len = 0;
}
- nv->value.i_type = XLOG_REG_TYPE_ATTR_VALUE;
if (new_value_len) {
- nv->new_value.i_addr = nv->name.i_addr + name_len +
+ nv->new_value.iov_base = nv->name.iov_base + name_len +
new_name_len + value_len;
- nv->new_value.i_len = new_value_len;
- memcpy(nv->new_value.i_addr, new_value, new_value_len);
+ nv->new_value.iov_len = new_value_len;
+ memcpy(nv->new_value.iov_base, new_value, new_value_len);
} else {
- nv->new_value.i_addr = NULL;
- nv->new_value.i_len = 0;
+ nv->new_value.iov_base = NULL;
+ nv->new_value.iov_len = 0;
}
- nv->new_value.i_type = XLOG_REG_TYPE_ATTR_NEWVALUE;
refcount_set(&nv->refcount, 1);
return nv;
@@ -170,21 +166,21 @@ xfs_attri_item_size(
*nvecs += 2;
*nbytes += sizeof(struct xfs_attri_log_format) +
- xlog_calc_iovec_len(nv->name.i_len);
+ xlog_calc_iovec_len(nv->name.iov_len);
- if (nv->new_name.i_len) {
+ if (nv->new_name.iov_len) {
*nvecs += 1;
- *nbytes += xlog_calc_iovec_len(nv->new_name.i_len);
+ *nbytes += xlog_calc_iovec_len(nv->new_name.iov_len);
}
- if (nv->value.i_len) {
+ if (nv->value.iov_len) {
*nvecs += 1;
- *nbytes += xlog_calc_iovec_len(nv->value.i_len);
+ *nbytes += xlog_calc_iovec_len(nv->value.iov_len);
}
- if (nv->new_value.i_len) {
+ if (nv->new_value.iov_len) {
*nvecs += 1;
- *nbytes += xlog_calc_iovec_len(nv->new_value.i_len);
+ *nbytes += xlog_calc_iovec_len(nv->new_value.iov_len);
}
}
@@ -212,31 +208,36 @@ xfs_attri_item_format(
* the log recovery.
*/
- ASSERT(nv->name.i_len > 0);
+ ASSERT(nv->name.iov_len > 0);
attrip->attri_format.alfi_size++;
- if (nv->new_name.i_len > 0)
+ if (nv->new_name.iov_len > 0)
attrip->attri_format.alfi_size++;
- if (nv->value.i_len > 0)
+ if (nv->value.iov_len > 0)
attrip->attri_format.alfi_size++;
- if (nv->new_value.i_len > 0)
+ if (nv->new_value.iov_len > 0)
attrip->attri_format.alfi_size++;
xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_ATTRI_FORMAT,
&attrip->attri_format,
sizeof(struct xfs_attri_log_format));
- xlog_copy_from_iovec(lv, &vecp, &nv->name);
- if (nv->new_name.i_len > 0)
- xlog_copy_from_iovec(lv, &vecp, &nv->new_name);
+ xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_ATTR_NAME, nv->name.iov_base,
+ nv->name.iov_len);
- if (nv->value.i_len > 0)
- xlog_copy_from_iovec(lv, &vecp, &nv->value);
+ if (nv->new_name.iov_len > 0)
+ xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_ATTR_NEWNAME,
+ nv->new_name.iov_base, nv->new_name.iov_len);
- if (nv->new_value.i_len > 0)
- xlog_copy_from_iovec(lv, &vecp, &nv->new_value);
+ if (nv->value.iov_len > 0)
+ xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_ATTR_VALUE,
+ nv->value.iov_base, nv->value.iov_len);
+
+ if (nv->new_value.iov_len > 0)
+ xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_ATTR_NEWVALUE,
+ nv->new_value.iov_base, nv->new_value.iov_len);
}
/*
@@ -383,22 +384,22 @@ xfs_attr_log_item(
attrp->alfi_ino = args->dp->i_ino;
ASSERT(!(attr->xattri_op_flags & ~XFS_ATTRI_OP_FLAGS_TYPE_MASK));
attrp->alfi_op_flags = attr->xattri_op_flags;
- attrp->alfi_value_len = nv->value.i_len;
+ attrp->alfi_value_len = nv->value.iov_len;
switch (xfs_attr_log_item_op(attrp)) {
case XFS_ATTRI_OP_FLAGS_PPTR_REPLACE:
- ASSERT(nv->value.i_len == nv->new_value.i_len);
+ ASSERT(nv->value.iov_len == nv->new_value.iov_len);
attrp->alfi_igen = VFS_I(args->dp)->i_generation;
- attrp->alfi_old_name_len = nv->name.i_len;
- attrp->alfi_new_name_len = nv->new_name.i_len;
+ attrp->alfi_old_name_len = nv->name.iov_len;
+ attrp->alfi_new_name_len = nv->new_name.iov_len;
break;
case XFS_ATTRI_OP_FLAGS_PPTR_REMOVE:
case XFS_ATTRI_OP_FLAGS_PPTR_SET:
attrp->alfi_igen = VFS_I(args->dp)->i_generation;
fallthrough;
default:
- attrp->alfi_name_len = nv->name.i_len;
+ attrp->alfi_name_len = nv->name.iov_len;
break;
}
@@ -616,10 +617,7 @@ xfs_attri_iread_extents(
struct xfs_trans *tp;
int error;
- error = xfs_trans_alloc_empty(ip->i_mount, &tp);
- if (error)
- return error;
-
+ tp = xfs_trans_alloc_empty(ip->i_mount);
xfs_ilock(ip, XFS_ILOCK_EXCL);
error = xfs_iread_extents(tp, ip, XFS_ATTR_FORK);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -690,14 +688,14 @@ xfs_attri_recover_work(
args->dp = ip;
args->geo = mp->m_attr_geo;
args->whichfork = XFS_ATTR_FORK;
- args->name = nv->name.i_addr;
- args->namelen = nv->name.i_len;
- args->new_name = nv->new_name.i_addr;
- args->new_namelen = nv->new_name.i_len;
- args->value = nv->value.i_addr;
- args->valuelen = nv->value.i_len;
- args->new_value = nv->new_value.i_addr;
- args->new_valuelen = nv->new_value.i_len;
+ args->name = nv->name.iov_base;
+ args->namelen = nv->name.iov_len;
+ args->new_name = nv->new_name.iov_base;
+ args->new_namelen = nv->new_name.iov_len;
+ args->value = nv->value.iov_base;
+ args->valuelen = nv->value.iov_len;
+ args->new_value = nv->new_value.iov_base;
+ args->new_valuelen = nv->new_value.iov_len;
args->attr_filter = attrp->alfi_attr_filter & XFS_ATTRI_FILTER_MASK;
args->op_flags = XFS_DA_OP_RECOVERY | XFS_DA_OP_OKNOENT |
XFS_DA_OP_LOGGED;
@@ -754,8 +752,8 @@ xfs_attr_recover_work(
*/
attrp = &attrip->attri_format;
if (!xfs_attri_validate(mp, attrp) ||
- !xfs_attr_namecheck(attrp->alfi_attr_filter, nv->name.i_addr,
- nv->name.i_len))
+ !xfs_attr_namecheck(attrp->alfi_attr_filter, nv->name.iov_base,
+ nv->name.iov_len))
return -EFSCORRUPTED;
attr = xfs_attri_recover_work(mp, dfp, attrp, &ip, nv);
@@ -953,50 +951,50 @@ static inline void *
xfs_attri_validate_name_iovec(
struct xfs_mount *mp,
struct xfs_attri_log_format *attri_formatp,
- const struct xfs_log_iovec *iovec,
+ const struct kvec *iovec,
unsigned int name_len)
{
- if (iovec->i_len != xlog_calc_iovec_len(name_len)) {
+ if (iovec->iov_len != xlog_calc_iovec_len(name_len)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
attri_formatp, sizeof(*attri_formatp));
return NULL;
}
- if (!xfs_attr_namecheck(attri_formatp->alfi_attr_filter, iovec->i_addr,
+ if (!xfs_attr_namecheck(attri_formatp->alfi_attr_filter, iovec->iov_base,
name_len)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
attri_formatp, sizeof(*attri_formatp));
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- iovec->i_addr, iovec->i_len);
+ iovec->iov_base, iovec->iov_len);
return NULL;
}
- return iovec->i_addr;
+ return iovec->iov_base;
}
static inline void *
xfs_attri_validate_value_iovec(
struct xfs_mount *mp,
struct xfs_attri_log_format *attri_formatp,
- const struct xfs_log_iovec *iovec,
+ const struct kvec *iovec,
unsigned int value_len)
{
- if (iovec->i_len != xlog_calc_iovec_len(value_len)) {
+ if (iovec->iov_len != xlog_calc_iovec_len(value_len)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
attri_formatp, sizeof(*attri_formatp));
return NULL;
}
if ((attri_formatp->alfi_attr_filter & XFS_ATTR_PARENT) &&
- !xfs_parent_valuecheck(mp, iovec->i_addr, value_len)) {
+ !xfs_parent_valuecheck(mp, iovec->iov_base, value_len)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
attri_formatp, sizeof(*attri_formatp));
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- iovec->i_addr, iovec->i_len);
+ iovec->iov_base, iovec->iov_len);
return NULL;
}
- return iovec->i_addr;
+ return iovec->iov_base;
}
STATIC int
@@ -1023,13 +1021,13 @@ xlog_recover_attri_commit_pass2(
/* Validate xfs_attri_log_format before the large memory allocation */
len = sizeof(struct xfs_attri_log_format);
- if (item->ri_buf[i].i_len != len) {
+ if (item->ri_buf[i].iov_len != len) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
- attri_formatp = item->ri_buf[i].i_addr;
+ attri_formatp = item->ri_buf[i].iov_base;
if (!xfs_attri_validate(mp, attri_formatp)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
attri_formatp, len);
@@ -1218,10 +1216,10 @@ xlog_recover_attrd_commit_pass2(
{
struct xfs_attrd_log_format *attrd_formatp;
- attrd_formatp = item->ri_buf[0].i_addr;
- if (item->ri_buf[0].i_len != sizeof(struct xfs_attrd_log_format)) {
+ attrd_formatp = item->ri_buf[0].iov_base;
+ if (item->ri_buf[0].iov_len != sizeof(struct xfs_attrd_log_format)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/xfs_attr_item.h b/fs/xfs/xfs_attr_item.h
index e74128cbb722..d108a11b55ae 100644
--- a/fs/xfs/xfs_attr_item.h
+++ b/fs/xfs/xfs_attr_item.h
@@ -12,10 +12,10 @@ struct xfs_mount;
struct kmem_zone;
struct xfs_attri_log_nameval {
- struct xfs_log_iovec name;
- struct xfs_log_iovec new_name; /* PPTR_REPLACE only */
- struct xfs_log_iovec value;
- struct xfs_log_iovec new_value; /* PPTR_REPLACE only */
+ struct kvec name;
+ struct kvec new_name; /* PPTR_REPLACE only */
+ struct kvec value;
+ struct kvec new_value; /* PPTR_REPLACE only */
refcount_t refcount;
/* name and value follow the end of this struct */
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 646c515ee355..80f0c4bcc483 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -654,24 +654,24 @@ xlog_recover_bui_commit_pass2(
struct xfs_bui_log_format *bui_formatp;
size_t len;
- bui_formatp = item->ri_buf[0].i_addr;
+ bui_formatp = item->ri_buf[0].iov_base;
- if (item->ri_buf[0].i_len < xfs_bui_log_format_sizeof(0)) {
+ if (item->ri_buf[0].iov_len < xfs_bui_log_format_sizeof(0)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
if (bui_formatp->bui_nextents != XFS_BUI_MAX_FAST_EXTENTS) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
len = xfs_bui_log_format_sizeof(bui_formatp->bui_nextents);
- if (item->ri_buf[0].i_len != len) {
+ if (item->ri_buf[0].iov_len != len) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
@@ -705,10 +705,10 @@ xlog_recover_bud_commit_pass2(
{
struct xfs_bud_log_format *bud_formatp;
- bud_formatp = item->ri_buf[0].i_addr;
- if (item->ri_buf[0].i_len != sizeof(struct xfs_bud_log_format)) {
+ bud_formatp = item->ri_buf[0].iov_base;
+ if (item->ri_buf[0].iov_len != sizeof(struct xfs_bud_log_format)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 8af83bd161f9..f9ef3b2a332a 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1683,7 +1683,7 @@ xfs_free_buftarg(
fs_put_dax(btp->bt_daxdev, btp->bt_mount);
/* the main block device is closed by kill_block_super */
if (btp->bt_bdev != btp->bt_mount->m_super->s_bdev)
- bdev_fput(btp->bt_bdev_file);
+ bdev_fput(btp->bt_file);
kfree(btp);
}
@@ -1712,8 +1712,8 @@ xfs_configure_buftarg_atomic_writes(
max_bytes = 0;
}
- btp->bt_bdev_awu_min = min_bytes;
- btp->bt_bdev_awu_max = max_bytes;
+ btp->bt_awu_min = min_bytes;
+ btp->bt_awu_max = max_bytes;
}
/* Configure a buffer target that abstracts a block device. */
@@ -1738,14 +1738,9 @@ xfs_configure_buftarg(
return -EINVAL;
}
- /*
- * Flush the block device pagecache so our bios see anything dirtied
- * before mount.
- */
if (bdev_can_atomic_write(btp->bt_bdev))
xfs_configure_buftarg_atomic_writes(btp);
-
- return sync_blockdev(btp->bt_bdev);
+ return 0;
}
int
@@ -1803,7 +1798,7 @@ xfs_alloc_buftarg(
btp = kzalloc(sizeof(*btp), GFP_KERNEL | __GFP_NOFAIL);
btp->bt_mount = mp;
- btp->bt_bdev_file = bdev_file;
+ btp->bt_file = bdev_file;
btp->bt_bdev = file_bdev(bdev_file);
btp->bt_dev = btp->bt_bdev->bd_dev;
btp->bt_daxdev = fs_dax_get_by_bdev(btp->bt_bdev, &btp->bt_dax_part_off,
@@ -2082,44 +2077,6 @@ xfs_buf_delwri_submit(
return error;
}
-/*
- * Push a single buffer on a delwri queue.
- *
- * The purpose of this function is to submit a single buffer of a delwri queue
- * and return with the buffer still on the original queue.
- *
- * The buffer locking and queue management logic between _delwri_pushbuf() and
- * _delwri_queue() guarantee that the buffer cannot be queued to another list
- * before returning.
- */
-int
-xfs_buf_delwri_pushbuf(
- struct xfs_buf *bp,
- struct list_head *buffer_list)
-{
- int error;
-
- ASSERT(bp->b_flags & _XBF_DELWRI_Q);
-
- trace_xfs_buf_delwri_pushbuf(bp, _RET_IP_);
-
- xfs_buf_lock(bp);
- bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC);
- bp->b_flags |= XBF_WRITE;
- xfs_buf_submit(bp);
-
- /*
- * The buffer is now locked, under I/O but still on the original delwri
- * queue. Wait for I/O completion, restore the DELWRI_Q flag and
- * return with the buffer unlocked and still on the original queue.
- */
- error = xfs_buf_iowait(bp);
- bp->b_flags |= _XBF_DELWRI_Q;
- xfs_buf_unlock(bp);
-
- return error;
-}
-
void xfs_buf_set_ref(struct xfs_buf *bp, int lru_ref)
{
/*
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 9d2ab567cf81..b269e115d9ac 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -94,7 +94,6 @@ void xfs_buf_cache_destroy(struct xfs_buf_cache *bch);
*/
struct xfs_buftarg {
dev_t bt_dev;
- struct file *bt_bdev_file;
struct block_device *bt_bdev;
struct dax_device *bt_daxdev;
struct file *bt_file;
@@ -112,9 +111,9 @@ struct xfs_buftarg {
struct percpu_counter bt_readahead_count;
struct ratelimit_state bt_ioerror_rl;
- /* Atomic write unit values, bytes */
- unsigned int bt_bdev_awu_min;
- unsigned int bt_bdev_awu_max;
+ /* Hardware atomic write unit values, bytes */
+ unsigned int bt_awu_min;
+ unsigned int bt_awu_max;
/* built-in cache, if we're not using the perag one */
struct xfs_buf_cache bt_cache[];
@@ -326,7 +325,6 @@ extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
void xfs_buf_delwri_queue_here(struct xfs_buf *bp, struct list_head *bl);
extern int xfs_buf_delwri_submit(struct list_head *);
extern int xfs_buf_delwri_submit_nowait(struct list_head *);
-extern int xfs_buf_delwri_pushbuf(struct xfs_buf *, struct list_head *);
static inline xfs_daddr_t xfs_buf_daddr(struct xfs_buf *bp)
{
@@ -376,7 +374,6 @@ extern void xfs_buftarg_wait(struct xfs_buftarg *);
extern void xfs_buftarg_drain(struct xfs_buftarg *);
int xfs_configure_buftarg(struct xfs_buftarg *btp, unsigned int sectorsize);
-#define xfs_getsize_buftarg(buftarg) block_size((buftarg)->bt_bdev)
#define xfs_readonly_buftarg(buftarg) bdev_read_only((buftarg)->bt_bdev)
int xfs_buf_reverify(struct xfs_buf *bp, const struct xfs_buf_ops *ops);
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 90139e0f3271..8d85b5eee444 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -32,19 +32,74 @@ static inline struct xfs_buf_log_item *BUF_ITEM(struct xfs_log_item *lip)
return container_of(lip, struct xfs_buf_log_item, bli_item);
}
+static void
+xfs_buf_item_get_format(
+ struct xfs_buf_log_item *bip,
+ int count)
+{
+ ASSERT(bip->bli_formats == NULL);
+ bip->bli_format_count = count;
+
+ if (count == 1) {
+ bip->bli_formats = &bip->__bli_format;
+ return;
+ }
+
+ bip->bli_formats = kzalloc(count * sizeof(struct xfs_buf_log_format),
+ GFP_KERNEL | __GFP_NOFAIL);
+}
+
+static void
+xfs_buf_item_free_format(
+ struct xfs_buf_log_item *bip)
+{
+ if (bip->bli_formats != &bip->__bli_format) {
+ kfree(bip->bli_formats);
+ bip->bli_formats = NULL;
+ }
+}
+
+static void
+xfs_buf_item_free(
+ struct xfs_buf_log_item *bip)
+{
+ xfs_buf_item_free_format(bip);
+ kvfree(bip->bli_item.li_lv_shadow);
+ kmem_cache_free(xfs_buf_item_cache, bip);
+}
+
+/*
+ * xfs_buf_item_relse() is called when the buf log item is no longer needed.
+ */
+static void
+xfs_buf_item_relse(
+ struct xfs_buf_log_item *bip)
+{
+ struct xfs_buf *bp = bip->bli_buf;
+
+ trace_xfs_buf_item_relse(bp, _RET_IP_);
+
+ ASSERT(!test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags));
+ ASSERT(atomic_read(&bip->bli_refcount) == 0);
+
+ bp->b_log_item = NULL;
+ xfs_buf_rele(bp);
+ xfs_buf_item_free(bip);
+}
+
/* Is this log iovec plausibly large enough to contain the buffer log format? */
bool
xfs_buf_log_check_iovec(
- struct xfs_log_iovec *iovec)
+ struct kvec *iovec)
{
- struct xfs_buf_log_format *blfp = iovec->i_addr;
+ struct xfs_buf_log_format *blfp = iovec->iov_base;
char *bmp_end;
char *item_end;
- if (offsetof(struct xfs_buf_log_format, blf_data_map) > iovec->i_len)
+ if (offsetof(struct xfs_buf_log_format, blf_data_map) > iovec->iov_len)
return false;
- item_end = (char *)iovec->i_addr + iovec->i_len;
+ item_end = (char *)iovec->iov_base + iovec->iov_len;
bmp_end = (char *)&blfp->blf_data_map[blfp->blf_map_size];
return bmp_end <= item_end;
}
@@ -390,6 +445,42 @@ xfs_buf_item_pin(
}
/*
+ * For a stale BLI, process all the necessary completions that must be
+ * performed when the final BLI reference goes away. The buffer will be
+ * referenced and locked here - we return to the caller with the buffer still
+ * referenced and locked for them to finalise processing of the buffer.
+ */
+static void
+xfs_buf_item_finish_stale(
+ struct xfs_buf_log_item *bip)
+{
+ struct xfs_buf *bp = bip->bli_buf;
+ struct xfs_log_item *lip = &bip->bli_item;
+
+ ASSERT(bip->bli_flags & XFS_BLI_STALE);
+ ASSERT(xfs_buf_islocked(bp));
+ ASSERT(bp->b_flags & XBF_STALE);
+ ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
+ ASSERT(list_empty(&lip->li_trans));
+ ASSERT(!bp->b_transp);
+
+ if (bip->bli_flags & XFS_BLI_STALE_INODE) {
+ xfs_buf_item_done(bp);
+ xfs_buf_inode_iodone(bp);
+ ASSERT(list_empty(&bp->b_li_list));
+ return;
+ }
+
+ /*
+ * We may or may not be on the AIL here, xfs_trans_ail_delete() will do
+ * the right thing regardless of the situation in which we are called.
+ */
+ xfs_trans_ail_delete(lip, SHUTDOWN_LOG_IO_ERROR);
+ xfs_buf_item_relse(bip);
+ ASSERT(bp->b_log_item == NULL);
+}
+
+/*
* This is called to unpin the buffer associated with the buf log item which was
* previously pinned with a call to xfs_buf_item_pin(). We enter this function
* with a buffer pin count, a buffer reference and a BLI reference.
@@ -438,13 +529,6 @@ xfs_buf_item_unpin(
}
if (stale) {
- ASSERT(bip->bli_flags & XFS_BLI_STALE);
- ASSERT(xfs_buf_islocked(bp));
- ASSERT(bp->b_flags & XBF_STALE);
- ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
- ASSERT(list_empty(&lip->li_trans));
- ASSERT(!bp->b_transp);
-
trace_xfs_buf_item_unpin_stale(bip);
/*
@@ -455,22 +539,7 @@ xfs_buf_item_unpin(
* processing is complete.
*/
xfs_buf_rele(bp);
-
- /*
- * If we get called here because of an IO error, we may or may
- * not have the item on the AIL. xfs_trans_ail_delete() will
- * take care of that situation. xfs_trans_ail_delete() drops
- * the AIL lock.
- */
- if (bip->bli_flags & XFS_BLI_STALE_INODE) {
- xfs_buf_item_done(bp);
- xfs_buf_inode_iodone(bp);
- ASSERT(list_empty(&bp->b_li_list));
- } else {
- xfs_trans_ail_delete(lip, SHUTDOWN_LOG_IO_ERROR);
- xfs_buf_item_relse(bp);
- ASSERT(bp->b_log_item == NULL);
- }
+ xfs_buf_item_finish_stale(bip);
xfs_buf_relse(bp);
return;
}
@@ -543,43 +612,42 @@ xfs_buf_item_push(
* Drop the buffer log item refcount and take appropriate action. This helper
* determines whether the bli must be freed or not, since a decrement to zero
* does not necessarily mean the bli is unused.
- *
- * Return true if the bli is freed, false otherwise.
*/
-bool
+void
xfs_buf_item_put(
struct xfs_buf_log_item *bip)
{
- struct xfs_log_item *lip = &bip->bli_item;
- bool aborted;
- bool dirty;
+
+ ASSERT(xfs_buf_islocked(bip->bli_buf));
/* drop the bli ref and return if it wasn't the last one */
if (!atomic_dec_and_test(&bip->bli_refcount))
- return false;
+ return;
- /*
- * We dropped the last ref and must free the item if clean or aborted.
- * If the bli is dirty and non-aborted, the buffer was clean in the
- * transaction but still awaiting writeback from previous changes. In
- * that case, the bli is freed on buffer writeback completion.
- */
- aborted = test_bit(XFS_LI_ABORTED, &lip->li_flags) ||
- xlog_is_shutdown(lip->li_log);
- dirty = bip->bli_flags & XFS_BLI_DIRTY;
- if (dirty && !aborted)
- return false;
+ /* If the BLI is in the AIL, then it is still dirty and in use */
+ if (test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags)) {
+ ASSERT(bip->bli_flags & XFS_BLI_DIRTY);
+ return;
+ }
/*
- * The bli is aborted or clean. An aborted item may be in the AIL
- * regardless of dirty state. For example, consider an aborted
- * transaction that invalidated a dirty bli and cleared the dirty
- * state.
+ * In shutdown conditions, we can be asked to free a dirty BLI that
+ * isn't in the AIL. This can occur due to a checkpoint aborting a BLI
+ * instead of inserting it into the AIL at checkpoint IO completion. If
+ * there's another bli reference (e.g. a btree cursor holds a clean
+ * reference) and it is released via xfs_trans_brelse(), we can get here
+ * with that aborted, dirty BLI. In this case, it is safe to free the
+ * dirty BLI immediately, as it is not in the AIL and there are no
+ * other references to it.
+ *
+ * We should never get here with a stale BLI via that path as
+ * xfs_trans_brelse() specifically holds onto stale buffers rather than
+ * releasing them.
*/
- if (aborted)
- xfs_trans_ail_delete(lip, 0);
- xfs_buf_item_relse(bip->bli_buf);
- return true;
+ ASSERT(!(bip->bli_flags & XFS_BLI_DIRTY) ||
+ test_bit(XFS_LI_ABORTED, &bip->bli_item.li_flags));
+ ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
+ xfs_buf_item_relse(bip);
}
/*
@@ -600,6 +668,15 @@ xfs_buf_item_put(
* if necessary but do not unlock the buffer. This is for support of
* xfs_trans_bhold(). Make sure the XFS_BLI_HOLD field is cleared if we don't
* free the item.
+ *
+ * If the XFS_BLI_STALE flag is set, the last reference to the BLI *must*
+ * perform a completion abort of any objects attached to the buffer for IO
+ * tracking purposes. This generally only happens in shutdown situations,
+ * normally xfs_buf_item_unpin() will drop the last BLI reference and perform
+ * completion processing. However, because transaction completion can race with
+ * checkpoint completion during a shutdown, this release context may end up
+ * being the last active reference to the BLI and so needs to perform this
+ * cleanup.
*/
STATIC void
xfs_buf_item_release(
@@ -607,18 +684,19 @@ xfs_buf_item_release(
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
struct xfs_buf *bp = bip->bli_buf;
- bool released;
bool hold = bip->bli_flags & XFS_BLI_HOLD;
bool stale = bip->bli_flags & XFS_BLI_STALE;
-#if defined(DEBUG) || defined(XFS_WARN)
- bool ordered = bip->bli_flags & XFS_BLI_ORDERED;
- bool dirty = bip->bli_flags & XFS_BLI_DIRTY;
bool aborted = test_bit(XFS_LI_ABORTED,
&lip->li_flags);
+ bool dirty = bip->bli_flags & XFS_BLI_DIRTY;
+#if defined(DEBUG) || defined(XFS_WARN)
+ bool ordered = bip->bli_flags & XFS_BLI_ORDERED;
#endif
trace_xfs_buf_item_release(bip);
+ ASSERT(xfs_buf_islocked(bp));
+
/*
* The bli dirty state should match whether the blf has logged segments
* except for ordered buffers, where only the bli should be dirty.
@@ -634,16 +712,56 @@ xfs_buf_item_release(
bp->b_transp = NULL;
bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED);
+ /* If there are other references, then we have nothing to do. */
+ if (!atomic_dec_and_test(&bip->bli_refcount))
+ goto out_release;
+
+ /*
+ * Stale buffer completion frees the BLI, unlocks and releases the
+ * buffer. Neither the BLI or buffer are safe to reference after this
+ * call, so there's nothing more we need to do here.
+ *
+ * If we get here with a stale buffer and references to the BLI remain,
+ * we must not unlock the buffer as the last BLI reference owns lock
+ * context, not us.
+ */
+ if (stale) {
+ xfs_buf_item_finish_stale(bip);
+ xfs_buf_relse(bp);
+ ASSERT(!hold);
+ return;
+ }
+
/*
- * Unref the item and unlock the buffer unless held or stale. Stale
- * buffers remain locked until final unpin unless the bli is freed by
- * the unref call. The latter implies shutdown because buffer
- * invalidation dirties the bli and transaction.
+ * Dirty or clean, aborted items are done and need to be removed from
+ * the AIL and released. This frees the BLI, but leaves the buffer
+ * locked and referenced.
*/
- released = xfs_buf_item_put(bip);
- if (hold || (stale && !released))
+ if (aborted || xlog_is_shutdown(lip->li_log)) {
+ ASSERT(list_empty(&bip->bli_buf->b_li_list));
+ xfs_buf_item_done(bp);
+ goto out_release;
+ }
+
+ /*
+ * Clean, unreferenced BLIs can be immediately freed, leaving the buffer
+ * locked and referenced.
+ *
+ * Dirty, unreferenced BLIs *must* be in the AIL awaiting writeback.
+ */
+ if (!dirty)
+ xfs_buf_item_relse(bip);
+ else
+ ASSERT(test_bit(XFS_LI_IN_AIL, &lip->li_flags));
+
+ /* Not safe to reference the BLI from here */
+out_release:
+ /*
+ * If we get here with a stale buffer, we must not unlock the
+ * buffer as the last BLI reference owns lock context, not us.
+ */
+ if (stale || hold)
return;
- ASSERT(!stale || aborted);
xfs_buf_relse(bp);
}
@@ -729,33 +847,6 @@ static const struct xfs_item_ops xfs_buf_item_ops = {
.iop_push = xfs_buf_item_push,
};
-STATIC void
-xfs_buf_item_get_format(
- struct xfs_buf_log_item *bip,
- int count)
-{
- ASSERT(bip->bli_formats == NULL);
- bip->bli_format_count = count;
-
- if (count == 1) {
- bip->bli_formats = &bip->__bli_format;
- return;
- }
-
- bip->bli_formats = kzalloc(count * sizeof(struct xfs_buf_log_format),
- GFP_KERNEL | __GFP_NOFAIL);
-}
-
-STATIC void
-xfs_buf_item_free_format(
- struct xfs_buf_log_item *bip)
-{
- if (bip->bli_formats != &bip->__bli_format) {
- kfree(bip->bli_formats);
- bip->bli_formats = NULL;
- }
-}
-
/*
* Allocate a new buf log item to go with the given buffer.
* Set the buffer's b_log_item field to point to the new
@@ -976,34 +1067,6 @@ xfs_buf_item_dirty_format(
return false;
}
-STATIC void
-xfs_buf_item_free(
- struct xfs_buf_log_item *bip)
-{
- xfs_buf_item_free_format(bip);
- kvfree(bip->bli_item.li_lv_shadow);
- kmem_cache_free(xfs_buf_item_cache, bip);
-}
-
-/*
- * xfs_buf_item_relse() is called when the buf log item is no longer needed.
- */
-void
-xfs_buf_item_relse(
- struct xfs_buf *bp)
-{
- struct xfs_buf_log_item *bip = bp->b_log_item;
-
- trace_xfs_buf_item_relse(bp, _RET_IP_);
- ASSERT(!test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags));
-
- if (atomic_read(&bip->bli_refcount))
- return;
- bp->b_log_item = NULL;
- xfs_buf_rele(bp);
- xfs_buf_item_free(bip);
-}
-
void
xfs_buf_item_done(
struct xfs_buf *bp)
@@ -1023,5 +1086,5 @@ xfs_buf_item_done(
xfs_trans_ail_delete(&bp->b_log_item->bli_item,
(bp->b_flags & _XBF_LOGRECOVERY) ? 0 :
SHUTDOWN_CORRUPT_INCORE);
- xfs_buf_item_relse(bp);
+ xfs_buf_item_relse(bp->b_log_item);
}
diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h
index e10e324cd245..3159325dd17b 100644
--- a/fs/xfs/xfs_buf_item.h
+++ b/fs/xfs/xfs_buf_item.h
@@ -49,8 +49,7 @@ struct xfs_buf_log_item {
int xfs_buf_item_init(struct xfs_buf *, struct xfs_mount *);
void xfs_buf_item_done(struct xfs_buf *bp);
-void xfs_buf_item_relse(struct xfs_buf *);
-bool xfs_buf_item_put(struct xfs_buf_log_item *);
+void xfs_buf_item_put(struct xfs_buf_log_item *bip);
void xfs_buf_item_log(struct xfs_buf_log_item *, uint, uint);
bool xfs_buf_item_dirty_format(struct xfs_buf_log_item *);
void xfs_buf_inode_iodone(struct xfs_buf *);
@@ -62,7 +61,7 @@ static inline void xfs_buf_dquot_iodone(struct xfs_buf *bp)
}
#endif /* CONFIG_XFS_QUOTA */
void xfs_buf_iodone(struct xfs_buf *);
-bool xfs_buf_log_check_iovec(struct xfs_log_iovec *iovec);
+bool xfs_buf_log_check_iovec(struct kvec *iovec);
unsigned int xfs_buf_inval_log_space(unsigned int map_count,
unsigned int blocksize);
diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c
index d4c5cef5bc43..5d58e2ae4972 100644
--- a/fs/xfs/xfs_buf_item_recover.c
+++ b/fs/xfs/xfs_buf_item_recover.c
@@ -159,7 +159,7 @@ STATIC enum xlog_recover_reorder
xlog_recover_buf_reorder(
struct xlog_recover_item *item)
{
- struct xfs_buf_log_format *buf_f = item->ri_buf[0].i_addr;
+ struct xfs_buf_log_format *buf_f = item->ri_buf[0].iov_base;
if (buf_f->blf_flags & XFS_BLF_CANCEL)
return XLOG_REORDER_CANCEL_LIST;
@@ -173,7 +173,7 @@ xlog_recover_buf_ra_pass2(
struct xlog *log,
struct xlog_recover_item *item)
{
- struct xfs_buf_log_format *buf_f = item->ri_buf[0].i_addr;
+ struct xfs_buf_log_format *buf_f = item->ri_buf[0].iov_base;
xlog_buf_readahead(log, buf_f->blf_blkno, buf_f->blf_len, NULL);
}
@@ -187,11 +187,11 @@ xlog_recover_buf_commit_pass1(
struct xlog *log,
struct xlog_recover_item *item)
{
- struct xfs_buf_log_format *bf = item->ri_buf[0].i_addr;
+ struct xfs_buf_log_format *bf = item->ri_buf[0].iov_base;
if (!xfs_buf_log_check_iovec(&item->ri_buf[0])) {
- xfs_err(log->l_mp, "bad buffer log item size (%d)",
- item->ri_buf[0].i_len);
+ xfs_err(log->l_mp, "bad buffer log item size (%zd)",
+ item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
@@ -487,8 +487,8 @@ xlog_recover_do_reg_buffer(
nbits = xfs_contig_bits(buf_f->blf_data_map,
buf_f->blf_map_size, bit);
ASSERT(nbits > 0);
- ASSERT(item->ri_buf[i].i_addr != NULL);
- ASSERT(item->ri_buf[i].i_len % XFS_BLF_CHUNK == 0);
+ ASSERT(item->ri_buf[i].iov_base != NULL);
+ ASSERT(item->ri_buf[i].iov_len % XFS_BLF_CHUNK == 0);
ASSERT(BBTOB(bp->b_length) >=
((uint)bit << XFS_BLF_SHIFT) + (nbits << XFS_BLF_SHIFT));
@@ -500,8 +500,8 @@ xlog_recover_do_reg_buffer(
* the log. Hence we need to trim nbits back to the length of
* the current region being copied out of the log.
*/
- if (item->ri_buf[i].i_len < (nbits << XFS_BLF_SHIFT))
- nbits = item->ri_buf[i].i_len >> XFS_BLF_SHIFT;
+ if (item->ri_buf[i].iov_len < (nbits << XFS_BLF_SHIFT))
+ nbits = item->ri_buf[i].iov_len >> XFS_BLF_SHIFT;
/*
* Do a sanity check if this is a dquot buffer. Just checking
@@ -511,18 +511,18 @@ xlog_recover_do_reg_buffer(
fa = NULL;
if (buf_f->blf_flags &
(XFS_BLF_UDQUOT_BUF|XFS_BLF_PDQUOT_BUF|XFS_BLF_GDQUOT_BUF)) {
- if (item->ri_buf[i].i_addr == NULL) {
+ if (item->ri_buf[i].iov_base == NULL) {
xfs_alert(mp,
"XFS: NULL dquot in %s.", __func__);
goto next;
}
- if (item->ri_buf[i].i_len < size_disk_dquot) {
+ if (item->ri_buf[i].iov_len < size_disk_dquot) {
xfs_alert(mp,
- "XFS: dquot too small (%d) in %s.",
- item->ri_buf[i].i_len, __func__);
+ "XFS: dquot too small (%zd) in %s.",
+ item->ri_buf[i].iov_len, __func__);
goto next;
}
- fa = xfs_dquot_verify(mp, item->ri_buf[i].i_addr, -1);
+ fa = xfs_dquot_verify(mp, item->ri_buf[i].iov_base, -1);
if (fa) {
xfs_alert(mp,
"dquot corrupt at %pS trying to replay into block 0x%llx",
@@ -533,7 +533,7 @@ xlog_recover_do_reg_buffer(
memcpy(xfs_buf_offset(bp,
(uint)bit << XFS_BLF_SHIFT), /* dest */
- item->ri_buf[i].i_addr, /* source */
+ item->ri_buf[i].iov_base, /* source */
nbits<<XFS_BLF_SHIFT); /* length */
next:
i++;
@@ -669,8 +669,8 @@ xlog_recover_do_inode_buffer(
if (next_unlinked_offset < reg_buf_offset)
continue;
- ASSERT(item->ri_buf[item_index].i_addr != NULL);
- ASSERT((item->ri_buf[item_index].i_len % XFS_BLF_CHUNK) == 0);
+ ASSERT(item->ri_buf[item_index].iov_base != NULL);
+ ASSERT((item->ri_buf[item_index].iov_len % XFS_BLF_CHUNK) == 0);
ASSERT((reg_buf_offset + reg_buf_bytes) <= BBTOB(bp->b_length));
/*
@@ -678,7 +678,7 @@ xlog_recover_do_inode_buffer(
* current di_next_unlinked field. Extract its value
* and copy it to the buffer copy.
*/
- logged_nextp = item->ri_buf[item_index].i_addr +
+ logged_nextp = item->ri_buf[item_index].iov_base +
next_unlinked_offset - reg_buf_offset;
if (XFS_IS_CORRUPT(mp, *logged_nextp == 0)) {
xfs_alert(mp,
@@ -1002,7 +1002,7 @@ xlog_recover_buf_commit_pass2(
struct xlog_recover_item *item,
xfs_lsn_t current_lsn)
{
- struct xfs_buf_log_format *buf_f = item->ri_buf[0].i_addr;
+ struct xfs_buf_log_format *buf_f = item->ri_buf[0].iov_base;
struct xfs_mount *mp = log->l_mp;
struct xfs_buf *bp;
int error;
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 94d0873bcd62..ee49f20875af 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -103,24 +103,6 @@ xfs_discard_endio(
bio_put(bio);
}
-static inline struct block_device *
-xfs_group_bdev(
- const struct xfs_group *xg)
-{
- struct xfs_mount *mp = xg->xg_mount;
-
- switch (xg->xg_type) {
- case XG_TYPE_AG:
- return mp->m_ddev_targp->bt_bdev;
- case XG_TYPE_RTG:
- return mp->m_rtdev_targp->bt_bdev;
- default:
- ASSERT(0);
- break;
- }
- return NULL;
-}
-
/*
* Walk the discard list and issue discards on all the busy extents in the
* list. We plug and chain the bios so that we only need a single completion
@@ -138,11 +120,14 @@ xfs_discard_extents(
blk_start_plug(&plug);
list_for_each_entry(busyp, &extents->extent_list, list) {
- trace_xfs_discard_extent(busyp->group, busyp->bno,
- busyp->length);
+ struct xfs_group *xg = busyp->group;
+ struct xfs_buftarg *btp =
+ xfs_group_type_buftarg(xg->xg_mount, xg->xg_type);
- error = __blkdev_issue_discard(xfs_group_bdev(busyp->group),
- xfs_gbno_to_daddr(busyp->group, busyp->bno),
+ trace_xfs_discard_extent(xg, busyp->bno, busyp->length);
+
+ error = __blkdev_issue_discard(btp->bt_bdev,
+ xfs_gbno_to_daddr(xg, busyp->bno),
XFS_FSB_TO_BB(mp, busyp->length),
GFP_KERNEL, &bio);
if (error && error != -EOPNOTSUPP) {
@@ -204,9 +189,7 @@ xfs_trim_gather_extents(
*/
xfs_log_force(mp, XFS_LOG_SYNC);
- error = xfs_trans_alloc_empty(mp, &tp);
- if (error)
- return error;
+ tp = xfs_trans_alloc_empty(mp);
error = xfs_alloc_read_agf(pag, tp, 0, &agbp);
if (error)
@@ -598,9 +581,7 @@ xfs_trim_rtextents(
struct xfs_trans *tp;
int error;
- error = xfs_trans_alloc_empty(mp, &tp);
- if (error)
- return error;
+ tp = xfs_trans_alloc_empty(mp);
/*
* Walk the free ranges between low and high. The query_range function
@@ -716,9 +697,7 @@ xfs_trim_rtgroup_extents(
struct xfs_trans *tp;
int error;
- error = xfs_trans_alloc_empty(mp, &tp);
- if (error)
- return error;
+ tp = xfs_trans_alloc_empty(mp);
/*
* Walk the free ranges between low and high. The query_range function
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index b4e32f0860b7..0bd8022e47b4 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -1398,11 +1398,9 @@ xfs_qm_dqflush(
ASSERT(XFS_DQ_IS_LOCKED(dqp));
ASSERT(!completion_done(&dqp->q_flush));
+ ASSERT(atomic_read(&dqp->q_pincount) == 0);
trace_xfs_dqflush(dqp);
-
- xfs_qm_dqunpin_wait(dqp);
-
fa = xfs_qm_dqflush_check(dqp);
if (fa) {
xfs_alert(mp, "corrupt dquot ID 0x%x in memory at %pS",
diff --git a/fs/xfs/xfs_dquot_item_recover.c b/fs/xfs/xfs_dquot_item_recover.c
index 2c2720ce6923..89bc9bcaf51e 100644
--- a/fs/xfs/xfs_dquot_item_recover.c
+++ b/fs/xfs/xfs_dquot_item_recover.c
@@ -34,10 +34,10 @@ xlog_recover_dquot_ra_pass2(
if (mp->m_qflags == 0)
return;
- recddq = item->ri_buf[1].i_addr;
+ recddq = item->ri_buf[1].iov_base;
if (recddq == NULL)
return;
- if (item->ri_buf[1].i_len < sizeof(struct xfs_disk_dquot))
+ if (item->ri_buf[1].iov_len < sizeof(struct xfs_disk_dquot))
return;
type = recddq->d_type & XFS_DQTYPE_REC_MASK;
@@ -45,7 +45,7 @@ xlog_recover_dquot_ra_pass2(
if (log->l_quotaoffs_flag & type)
return;
- dq_f = item->ri_buf[0].i_addr;
+ dq_f = item->ri_buf[0].iov_base;
ASSERT(dq_f);
ASSERT(dq_f->qlf_len == 1);
@@ -79,14 +79,14 @@ xlog_recover_dquot_commit_pass2(
if (mp->m_qflags == 0)
return 0;
- recddq = item->ri_buf[1].i_addr;
+ recddq = item->ri_buf[1].iov_base;
if (recddq == NULL) {
xfs_alert(log->l_mp, "NULL dquot in %s.", __func__);
return -EFSCORRUPTED;
}
- if (item->ri_buf[1].i_len < sizeof(struct xfs_disk_dquot)) {
- xfs_alert(log->l_mp, "dquot too small (%d) in %s.",
- item->ri_buf[1].i_len, __func__);
+ if (item->ri_buf[1].iov_len < sizeof(struct xfs_disk_dquot)) {
+ xfs_alert(log->l_mp, "dquot too small (%zd) in %s.",
+ item->ri_buf[1].iov_len, __func__);
return -EFSCORRUPTED;
}
@@ -108,7 +108,7 @@ xlog_recover_dquot_commit_pass2(
* The other possibility, of course, is that the quota subsystem was
* removed since the last mount - ENOSYS.
*/
- dq_f = item->ri_buf[0].i_addr;
+ dq_f = item->ri_buf[0].iov_base;
ASSERT(dq_f);
fa = xfs_dquot_verify(mp, recddq, dq_f->qlf_id);
if (fa) {
@@ -147,7 +147,7 @@ xlog_recover_dquot_commit_pass2(
}
}
- memcpy(ddq, recddq, item->ri_buf[1].i_len);
+ memcpy(ddq, recddq, item->ri_buf[1].iov_len);
if (xfs_has_crc(mp)) {
xfs_update_cksum((char *)dqb, sizeof(struct xfs_dqblk),
XFS_DQUOT_CRC_OFF);
@@ -192,7 +192,7 @@ xlog_recover_quotaoff_commit_pass1(
struct xlog *log,
struct xlog_recover_item *item)
{
- struct xfs_qoff_logformat *qoff_f = item->ri_buf[0].i_addr;
+ struct xfs_qoff_logformat *qoff_f = item->ri_buf[0].iov_base;
ASSERT(qoff_f);
/*
diff --git a/fs/xfs/xfs_exchmaps_item.c b/fs/xfs/xfs_exchmaps_item.c
index 264a121c5e16..229cbe0adf17 100644
--- a/fs/xfs/xfs_exchmaps_item.c
+++ b/fs/xfs/xfs_exchmaps_item.c
@@ -558,12 +558,12 @@ xlog_recover_xmi_commit_pass2(
size_t len;
len = sizeof(struct xfs_xmi_log_format);
- if (item->ri_buf[0].i_len != len) {
+ if (item->ri_buf[0].iov_len != len) {
XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
return -EFSCORRUPTED;
}
- xmi_formatp = item->ri_buf[0].i_addr;
+ xmi_formatp = item->ri_buf[0].iov_base;
if (xmi_formatp->__pad != 0) {
XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
return -EFSCORRUPTED;
@@ -598,8 +598,8 @@ xlog_recover_xmd_commit_pass2(
{
struct xfs_xmd_log_format *xmd_formatp;
- xmd_formatp = item->ri_buf[0].i_addr;
- if (item->ri_buf[0].i_len != sizeof(struct xfs_xmd_log_format)) {
+ xmd_formatp = item->ri_buf[0].iov_base;
+ if (item->ri_buf[0].iov_len != sizeof(struct xfs_xmd_log_format)) {
XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h
index f069b04e8ea1..3e6e019b6146 100644
--- a/fs/xfs/xfs_extent_busy.h
+++ b/fs/xfs/xfs_extent_busy.h
@@ -68,4 +68,12 @@ static inline void xfs_extent_busy_sort(struct list_head *list)
list_sort(NULL, list, xfs_extent_busy_ag_cmp);
}
+/*
+ * Zoned RTGs don't need to track busy extents, as the actual block freeing only
+ * happens by a zone reset, which forces out all transactions that touched the
+ * to be reset zone first.
+ */
+#define xfs_group_has_extent_busy(mp, type) \
+ ((type) == XG_TYPE_AG || !xfs_has_zoned((mp)))
+
#endif /* __XFS_EXTENT_BUSY_H__ */
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index d574f5f639fa..47ee598a9827 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -182,15 +182,18 @@ xfs_efi_init(
* It will handle the conversion of formats if necessary.
*/
STATIC int
-xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt)
+xfs_efi_copy_format(
+ struct kvec *buf,
+ struct xfs_efi_log_format *dst_efi_fmt)
{
- xfs_efi_log_format_t *src_efi_fmt = buf->i_addr;
- uint i;
- uint len = xfs_efi_log_format_sizeof(src_efi_fmt->efi_nextents);
- uint len32 = xfs_efi_log_format32_sizeof(src_efi_fmt->efi_nextents);
- uint len64 = xfs_efi_log_format64_sizeof(src_efi_fmt->efi_nextents);
+ struct xfs_efi_log_format *src_efi_fmt = buf->iov_base;
+ uint len, len32, len64, i;
- if (buf->i_len == len) {
+ len = xfs_efi_log_format_sizeof(src_efi_fmt->efi_nextents);
+ len32 = xfs_efi_log_format32_sizeof(src_efi_fmt->efi_nextents);
+ len64 = xfs_efi_log_format64_sizeof(src_efi_fmt->efi_nextents);
+
+ if (buf->iov_len == len) {
memcpy(dst_efi_fmt, src_efi_fmt,
offsetof(struct xfs_efi_log_format, efi_extents));
for (i = 0; i < src_efi_fmt->efi_nextents; i++)
@@ -198,8 +201,8 @@ xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt)
&src_efi_fmt->efi_extents[i],
sizeof(struct xfs_extent));
return 0;
- } else if (buf->i_len == len32) {
- xfs_efi_log_format_32_t *src_efi_fmt_32 = buf->i_addr;
+ } else if (buf->iov_len == len32) {
+ xfs_efi_log_format_32_t *src_efi_fmt_32 = buf->iov_base;
dst_efi_fmt->efi_type = src_efi_fmt_32->efi_type;
dst_efi_fmt->efi_size = src_efi_fmt_32->efi_size;
@@ -212,8 +215,8 @@ xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt)
src_efi_fmt_32->efi_extents[i].ext_len;
}
return 0;
- } else if (buf->i_len == len64) {
- xfs_efi_log_format_64_t *src_efi_fmt_64 = buf->i_addr;
+ } else if (buf->iov_len == len64) {
+ xfs_efi_log_format_64_t *src_efi_fmt_64 = buf->iov_base;
dst_efi_fmt->efi_type = src_efi_fmt_64->efi_type;
dst_efi_fmt->efi_size = src_efi_fmt_64->efi_size;
@@ -227,8 +230,8 @@ xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt)
}
return 0;
}
- XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, NULL, buf->i_addr,
- buf->i_len);
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, NULL, buf->iov_base,
+ buf->iov_len);
return -EFSCORRUPTED;
}
@@ -865,11 +868,11 @@ xlog_recover_efi_commit_pass2(
struct xfs_efi_log_format *efi_formatp;
int error;
- efi_formatp = item->ri_buf[0].i_addr;
+ efi_formatp = item->ri_buf[0].iov_base;
- if (item->ri_buf[0].i_len < xfs_efi_log_format_sizeof(0)) {
+ if (item->ri_buf[0].iov_len < xfs_efi_log_format_sizeof(0)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
@@ -904,11 +907,11 @@ xlog_recover_rtefi_commit_pass2(
struct xfs_efi_log_format *efi_formatp;
int error;
- efi_formatp = item->ri_buf[0].i_addr;
+ efi_formatp = item->ri_buf[0].iov_base;
- if (item->ri_buf[0].i_len < xfs_efi_log_format_sizeof(0)) {
+ if (item->ri_buf[0].iov_len < xfs_efi_log_format_sizeof(0)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
@@ -933,7 +936,7 @@ xlog_recover_rtefi_commit_pass2(
xfs_lsn_t lsn)
{
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
#endif
@@ -958,9 +961,9 @@ xlog_recover_efd_commit_pass2(
xfs_lsn_t lsn)
{
struct xfs_efd_log_format *efd_formatp;
- int buflen = item->ri_buf[0].i_len;
+ int buflen = item->ri_buf[0].iov_len;
- efd_formatp = item->ri_buf[0].i_addr;
+ efd_formatp = item->ri_buf[0].iov_base;
if (buflen < sizeof(struct xfs_efd_log_format)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
@@ -968,9 +971,9 @@ xlog_recover_efd_commit_pass2(
return -EFSCORRUPTED;
}
- if (item->ri_buf[0].i_len != xfs_efd_log_format32_sizeof(
+ if (item->ri_buf[0].iov_len != xfs_efd_log_format32_sizeof(
efd_formatp->efd_nextents) &&
- item->ri_buf[0].i_len != xfs_efd_log_format64_sizeof(
+ item->ri_buf[0].iov_len != xfs_efd_log_format64_sizeof(
efd_formatp->efd_nextents)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
efd_formatp, buflen);
@@ -995,9 +998,9 @@ xlog_recover_rtefd_commit_pass2(
xfs_lsn_t lsn)
{
struct xfs_efd_log_format *efd_formatp;
- int buflen = item->ri_buf[0].i_len;
+ int buflen = item->ri_buf[0].iov_len;
- efd_formatp = item->ri_buf[0].i_addr;
+ efd_formatp = item->ri_buf[0].iov_base;
if (buflen < sizeof(struct xfs_efd_log_format)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
@@ -1005,9 +1008,9 @@ xlog_recover_rtefd_commit_pass2(
return -EFSCORRUPTED;
}
- if (item->ri_buf[0].i_len != xfs_efd_log_format32_sizeof(
+ if (item->ri_buf[0].iov_len != xfs_efd_log_format32_sizeof(
efd_formatp->efd_nextents) &&
- item->ri_buf[0].i_len != xfs_efd_log_format64_sizeof(
+ item->ri_buf[0].iov_len != xfs_efd_log_format64_sizeof(
efd_formatp->efd_nextents)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
efd_formatp, buflen);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 48254a72071b..b04c59d87378 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -497,7 +497,7 @@ restart:
static ssize_t
xfs_zoned_write_space_reserve(
- struct xfs_inode *ip,
+ struct xfs_mount *mp,
struct kiocb *iocb,
struct iov_iter *from,
unsigned int flags,
@@ -533,8 +533,8 @@ xfs_zoned_write_space_reserve(
*
* Any remaining block will be returned after the write.
*/
- return xfs_zoned_space_reserve(ip,
- XFS_B_TO_FSB(ip->i_mount, count) + 1 + 2, flags, ac);
+ return xfs_zoned_space_reserve(mp, XFS_B_TO_FSB(mp, count) + 1 + 2,
+ flags, ac);
}
static int
@@ -718,13 +718,13 @@ xfs_file_dio_write_zoned(
struct xfs_zone_alloc_ctx ac = { };
ssize_t ret;
- ret = xfs_zoned_write_space_reserve(ip, iocb, from, 0, &ac);
+ ret = xfs_zoned_write_space_reserve(ip->i_mount, iocb, from, 0, &ac);
if (ret < 0)
return ret;
ret = xfs_file_dio_write_aligned(ip, iocb, from,
&xfs_zoned_direct_write_iomap_ops,
&xfs_dio_zoned_write_ops, &ac);
- xfs_zoned_space_unreserve(ip, &ac);
+ xfs_zoned_space_unreserve(ip->i_mount, &ac);
return ret;
}
@@ -752,7 +752,7 @@ xfs_file_dio_write_atomic(
* HW offload should be faster, so try that first if it is already
* known that the write length is not too large.
*/
- if (ocount > xfs_inode_buftarg(ip)->bt_bdev_awu_max)
+ if (ocount > xfs_inode_buftarg(ip)->bt_awu_max)
dops = &xfs_atomic_write_cow_iomap_ops;
else
dops = &xfs_direct_write_iomap_ops;
@@ -979,7 +979,8 @@ write_retry:
trace_xfs_file_buffered_write(iocb, from);
ret = iomap_file_buffered_write(iocb, from,
- &xfs_buffered_write_iomap_ops, NULL);
+ &xfs_buffered_write_iomap_ops, &xfs_iomap_write_ops,
+ NULL);
/*
* If we hit a space limit, try to free up some lingering preallocated
@@ -1032,7 +1033,7 @@ xfs_file_buffered_write_zoned(
struct xfs_zone_alloc_ctx ac = { };
ssize_t ret;
- ret = xfs_zoned_write_space_reserve(ip, iocb, from, XFS_ZR_GREEDY, &ac);
+ ret = xfs_zoned_write_space_reserve(mp, iocb, from, XFS_ZR_GREEDY, &ac);
if (ret < 0)
return ret;
@@ -1059,7 +1060,8 @@ xfs_file_buffered_write_zoned(
retry:
trace_xfs_file_buffered_write(iocb, from);
ret = iomap_file_buffered_write(iocb, from,
- &xfs_buffered_write_iomap_ops, &ac);
+ &xfs_buffered_write_iomap_ops, &xfs_iomap_write_ops,
+ &ac);
if (ret == -ENOSPC && !cleared_space) {
/*
* Kick off writeback to convert delalloc space and release the
@@ -1073,7 +1075,7 @@ retry:
out_unlock:
xfs_iunlock(ip, iolock);
out_unreserve:
- xfs_zoned_space_unreserve(ip, &ac);
+ xfs_zoned_space_unreserve(ip->i_mount, &ac);
if (ret > 0) {
XFS_STATS_ADD(mp, xs_write_bytes, ret);
ret = generic_write_sync(iocb, ret);
@@ -1335,9 +1337,10 @@ xfs_falloc_allocate_range(
}
#define XFS_FALLOC_FL_SUPPORTED \
- (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | \
- FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | \
- FALLOC_FL_INSERT_RANGE | FALLOC_FL_UNSHARE_RANGE)
+ (FALLOC_FL_ALLOCATE_RANGE | FALLOC_FL_KEEP_SIZE | \
+ FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | \
+ FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE | \
+ FALLOC_FL_UNSHARE_RANGE)
STATIC long
__xfs_file_fallocate(
@@ -1413,11 +1416,11 @@ xfs_file_zoned_fallocate(
struct xfs_inode *ip = XFS_I(file_inode(file));
int error;
- error = xfs_zoned_space_reserve(ip, 2, XFS_ZR_RESERVED, &ac);
+ error = xfs_zoned_space_reserve(ip->i_mount, 2, XFS_ZR_RESERVED, &ac);
if (error)
return error;
error = __xfs_file_fallocate(file, mode, offset, len, &ac);
- xfs_zoned_space_unreserve(ip, &ac);
+ xfs_zoned_space_unreserve(ip->i_mount, &ac);
return error;
}
@@ -1827,12 +1830,12 @@ xfs_write_fault_zoned(
* But as the overallocation is limited to less than a folio and will be
* release instantly that's just fine.
*/
- error = xfs_zoned_space_reserve(ip, XFS_B_TO_FSB(ip->i_mount, len), 0,
- &ac);
+ error = xfs_zoned_space_reserve(ip->i_mount,
+ XFS_B_TO_FSB(ip->i_mount, len), 0, &ac);
if (error < 0)
return vmf_fs_error(error);
ret = __xfs_write_fault(vmf, order, &ac);
- xfs_zoned_space_unreserve(ip, &ac);
+ xfs_zoned_space_unreserve(ip->i_mount, &ac);
return ret;
}
@@ -1913,10 +1916,10 @@ static const struct vm_operations_struct xfs_file_vm_ops = {
};
STATIC int
-xfs_file_mmap(
- struct file *file,
- struct vm_area_struct *vma)
+xfs_file_mmap_prepare(
+ struct vm_area_desc *desc)
{
+ struct file *file = desc->file;
struct inode *inode = file_inode(file);
struct xfs_buftarg *target = xfs_inode_buftarg(XFS_I(inode));
@@ -1924,13 +1927,14 @@ xfs_file_mmap(
* We don't support synchronous mappings for non-DAX files and
* for DAX files if underneath dax_device is not synchronous.
*/
- if (!daxdev_mapping_supported(vma, target->bt_daxdev))
+ if (!daxdev_mapping_supported(desc->vm_flags, file_inode(file),
+ target->bt_daxdev))
return -EOPNOTSUPP;
file_accessed(file);
- vma->vm_ops = &xfs_file_vm_ops;
+ desc->vm_ops = &xfs_file_vm_ops;
if (IS_DAX(inode))
- vm_flags_set(vma, VM_HUGEPAGE);
+ desc->vm_flags |= VM_HUGEPAGE;
return 0;
}
@@ -1945,7 +1949,7 @@ const struct file_operations xfs_file_operations = {
#ifdef CONFIG_COMPAT
.compat_ioctl = xfs_file_compat_ioctl,
#endif
- .mmap = xfs_file_mmap,
+ .mmap_prepare = xfs_file_mmap_prepare,
.open = xfs_file_open,
.release = xfs_file_release,
.fsync = xfs_file_fsync,
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 414b27a86458..af68c7de8ee8 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -1270,9 +1270,7 @@ xfs_getfsmap(
* buffer locking abilities to detect cycles in the rmapbt
* without deadlocking.
*/
- error = xfs_trans_alloc_empty(mp, &tp);
- if (error)
- break;
+ tp = xfs_trans_alloc_empty(mp);
info.dev = handlers[i].dev;
info.last = false;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 726e29b837e6..4cf7abe50143 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -893,10 +893,7 @@ xfs_metafile_iget(
struct xfs_trans *tp;
int error;
- error = xfs_trans_alloc_empty(mp, &tp);
- if (error)
- return error;
-
+ tp = xfs_trans_alloc_empty(mp);
error = xfs_trans_metafile_iget(tp, ino, metafile_type, ipp);
xfs_trans_cancel(tp);
return error;
@@ -979,7 +976,15 @@ xfs_reclaim_inode(
*/
if (xlog_is_shutdown(ip->i_mount->m_log)) {
xfs_iunpin_wait(ip);
+ /*
+ * Avoid a ABBA deadlock on the inode cluster buffer vs
+ * concurrent xfs_ifree_cluster() trying to mark the inode
+ * stale. We don't need the inode locked to run the flush abort
+ * code, but the flush abort needs to lock the cluster buffer.
+ */
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_iflush_shutdown_abort(ip);
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
goto reclaim;
}
if (xfs_ipincount(ip))
diff --git a/fs/xfs/xfs_icreate_item.c b/fs/xfs/xfs_icreate_item.c
index 4345db501714..f83ec2bd0583 100644
--- a/fs/xfs/xfs_icreate_item.c
+++ b/fs/xfs/xfs_icreate_item.c
@@ -158,7 +158,7 @@ xlog_recover_icreate_commit_pass2(
int nbufs;
int i;
- icl = (struct xfs_icreate_log *)item->ri_buf[0].i_addr;
+ icl = (struct xfs_icreate_log *)item->ri_buf[0].iov_base;
if (icl->icl_type != XFS_LI_ICREATE) {
xfs_warn(log->l_mp, "xlog_recover_do_icreate_trans: bad type");
return -EINVAL;
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index ee3e0f284287..9c39251961a3 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1635,7 +1635,7 @@ retry:
iip = ip->i_itemp;
if (__xfs_iflags_test(ip, XFS_IFLUSHING)) {
ASSERT(!list_empty(&iip->ili_item.li_bio_list));
- ASSERT(iip->ili_last_fields);
+ ASSERT(iip->ili_last_fields || xlog_is_shutdown(mp->m_log));
goto out_iunlock;
}
@@ -2932,12 +2932,9 @@ xfs_inode_reload_unlinked(
struct xfs_inode *ip)
{
struct xfs_trans *tp;
- int error;
-
- error = xfs_trans_alloc_empty(ip->i_mount, &tp);
- if (error)
- return error;
+ int error = 0;
+ tp = xfs_trans_alloc_empty(ip->i_mount);
xfs_ilock(ip, XFS_ILOCK_SHARED);
if (xfs_inode_unlinked_incomplete(ip))
error = xfs_inode_reload_unlinked_bucket(tp, ip);
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index d7e2b902ef5c..07fbdcc4cbf5 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -358,7 +358,7 @@ static inline bool xfs_inode_has_bigrtalloc(const struct xfs_inode *ip)
static inline bool xfs_inode_can_hw_atomic_write(const struct xfs_inode *ip)
{
- return xfs_inode_buftarg(ip)->bt_bdev_awu_max > 0;
+ return xfs_inode_buftarg(ip)->bt_awu_max > 0;
}
/*
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index c6cb0b6b9e46..829675700fcd 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -758,11 +758,14 @@ xfs_inode_item_push(
* completed and items removed from the AIL before the next push
* attempt.
*/
+ trace_xfs_inode_push_stale(ip, _RET_IP_);
return XFS_ITEM_PINNED;
}
- if (xfs_ipincount(ip) > 0 || xfs_buf_ispinned(bp))
+ if (xfs_ipincount(ip) > 0 || xfs_buf_ispinned(bp)) {
+ trace_xfs_inode_push_pinned(ip, _RET_IP_);
return XFS_ITEM_PINNED;
+ }
if (xfs_iflags_test(ip, XFS_IFLUSHING))
return XFS_ITEM_FLUSHING;
@@ -1179,12 +1182,12 @@ xfs_iflush_shutdown_abort(
*/
int
xfs_inode_item_format_convert(
- struct xfs_log_iovec *buf,
+ struct kvec *buf,
struct xfs_inode_log_format *in_f)
{
- struct xfs_inode_log_format_32 *in_f32 = buf->i_addr;
+ struct xfs_inode_log_format_32 *in_f32 = buf->iov_base;
- if (buf->i_len != sizeof(*in_f32)) {
+ if (buf->iov_len != sizeof(*in_f32)) {
XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/xfs_inode_item.h b/fs/xfs/xfs_inode_item.h
index 377e06007804..ba92ce11a011 100644
--- a/fs/xfs/xfs_inode_item.h
+++ b/fs/xfs/xfs_inode_item.h
@@ -46,8 +46,8 @@ extern void xfs_inode_item_init(struct xfs_inode *, struct xfs_mount *);
extern void xfs_inode_item_destroy(struct xfs_inode *);
extern void xfs_iflush_abort(struct xfs_inode *);
extern void xfs_iflush_shutdown_abort(struct xfs_inode *);
-extern int xfs_inode_item_format_convert(xfs_log_iovec_t *,
- struct xfs_inode_log_format *);
+int xfs_inode_item_format_convert(struct kvec *buf,
+ struct xfs_inode_log_format *in_f);
extern struct kmem_cache *xfs_ili_cache;
diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c
index 7205fd14f6b3..9d1999d41be1 100644
--- a/fs/xfs/xfs_inode_item_recover.c
+++ b/fs/xfs/xfs_inode_item_recover.c
@@ -30,13 +30,13 @@ xlog_recover_inode_ra_pass2(
struct xlog *log,
struct xlog_recover_item *item)
{
- if (item->ri_buf[0].i_len == sizeof(struct xfs_inode_log_format)) {
- struct xfs_inode_log_format *ilfp = item->ri_buf[0].i_addr;
+ if (item->ri_buf[0].iov_len == sizeof(struct xfs_inode_log_format)) {
+ struct xfs_inode_log_format *ilfp = item->ri_buf[0].iov_base;
xlog_buf_readahead(log, ilfp->ilf_blkno, ilfp->ilf_len,
&xfs_inode_buf_ra_ops);
} else {
- struct xfs_inode_log_format_32 *ilfp = item->ri_buf[0].i_addr;
+ struct xfs_inode_log_format_32 *ilfp = item->ri_buf[0].iov_base;
xlog_buf_readahead(log, ilfp->ilf_blkno, ilfp->ilf_len,
&xfs_inode_buf_ra_ops);
@@ -326,8 +326,8 @@ xlog_recover_inode_commit_pass2(
int need_free = 0;
xfs_failaddr_t fa;
- if (item->ri_buf[0].i_len == sizeof(struct xfs_inode_log_format)) {
- in_f = item->ri_buf[0].i_addr;
+ if (item->ri_buf[0].iov_len == sizeof(struct xfs_inode_log_format)) {
+ in_f = item->ri_buf[0].iov_base;
} else {
in_f = kmalloc(sizeof(struct xfs_inode_log_format),
GFP_KERNEL | __GFP_NOFAIL);
@@ -366,7 +366,7 @@ xlog_recover_inode_commit_pass2(
error = -EFSCORRUPTED;
goto out_release;
}
- ldip = item->ri_buf[1].i_addr;
+ ldip = item->ri_buf[1].iov_base;
if (XFS_IS_CORRUPT(mp, ldip->di_magic != XFS_DINODE_MAGIC)) {
xfs_alert(mp,
"%s: Bad inode log record, rec ptr "PTR_FMT", ino %lld",
@@ -472,12 +472,12 @@ xlog_recover_inode_commit_pass2(
goto out_release;
}
isize = xfs_log_dinode_size(mp);
- if (unlikely(item->ri_buf[1].i_len > isize)) {
+ if (unlikely(item->ri_buf[1].iov_len > isize)) {
XFS_CORRUPTION_ERROR("Bad log dinode size", XFS_ERRLEVEL_LOW,
mp, ldip, sizeof(*ldip));
xfs_alert(mp,
- "Bad inode 0x%llx log dinode size 0x%x",
- in_f->ilf_ino, item->ri_buf[1].i_len);
+ "Bad inode 0x%llx log dinode size 0x%zx",
+ in_f->ilf_ino, item->ri_buf[1].iov_len);
error = -EFSCORRUPTED;
goto out_release;
}
@@ -500,8 +500,8 @@ xlog_recover_inode_commit_pass2(
if (in_f->ilf_size == 2)
goto out_owner_change;
- len = item->ri_buf[2].i_len;
- src = item->ri_buf[2].i_addr;
+ len = item->ri_buf[2].iov_len;
+ src = item->ri_buf[2].iov_base;
ASSERT(in_f->ilf_size <= 4);
ASSERT((in_f->ilf_size == 3) || (fields & XFS_ILOG_AFORK));
ASSERT(!(fields & XFS_ILOG_DFORK) ||
@@ -538,8 +538,8 @@ xlog_recover_inode_commit_pass2(
} else {
attr_index = 2;
}
- len = item->ri_buf[attr_index].i_len;
- src = item->ri_buf[attr_index].i_addr;
+ len = item->ri_buf[attr_index].iov_len;
+ src = item->ri_buf[attr_index].iov_base;
ASSERT(len == xlog_calc_iovec_len(in_f->ilf_asize));
switch (in_f->ilf_fields & XFS_ILOG_AFORK) {
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index d250f7f74e3b..fe1f74a3b6a3 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -444,7 +444,7 @@ static void
xfs_fill_fsxattr(
struct xfs_inode *ip,
int whichfork,
- struct fileattr *fa)
+ struct file_kattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
struct xfs_ifork *ifp = xfs_ifork_ptr(ip, whichfork);
@@ -496,7 +496,7 @@ xfs_ioc_fsgetxattra(
xfs_inode_t *ip,
void __user *arg)
{
- struct fileattr fa;
+ struct file_kattr fa;
xfs_ilock(ip, XFS_ILOCK_SHARED);
xfs_fill_fsxattr(ip, XFS_ATTR_FORK, &fa);
@@ -508,7 +508,7 @@ xfs_ioc_fsgetxattra(
int
xfs_fileattr_get(
struct dentry *dentry,
- struct fileattr *fa)
+ struct file_kattr *fa)
{
struct xfs_inode *ip = XFS_I(d_inode(dentry));
@@ -526,7 +526,7 @@ static int
xfs_ioctl_setattr_xflags(
struct xfs_trans *tp,
struct xfs_inode *ip,
- struct fileattr *fa)
+ struct file_kattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
bool rtflag = (fa->fsx_xflags & FS_XFLAG_REALTIME);
@@ -582,7 +582,7 @@ xfs_ioctl_setattr_xflags(
static void
xfs_ioctl_setattr_prepare_dax(
struct xfs_inode *ip,
- struct fileattr *fa)
+ struct file_kattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
struct inode *inode = VFS_I(ip);
@@ -642,7 +642,7 @@ out_error:
static int
xfs_ioctl_setattr_check_extsize(
struct xfs_inode *ip,
- struct fileattr *fa)
+ struct file_kattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
xfs_failaddr_t failaddr;
@@ -684,7 +684,7 @@ xfs_ioctl_setattr_check_extsize(
static int
xfs_ioctl_setattr_check_cowextsize(
struct xfs_inode *ip,
- struct fileattr *fa)
+ struct file_kattr *fa)
{
struct xfs_mount *mp = ip->i_mount;
xfs_failaddr_t failaddr;
@@ -709,7 +709,7 @@ xfs_ioctl_setattr_check_cowextsize(
static int
xfs_ioctl_setattr_check_projid(
struct xfs_inode *ip,
- struct fileattr *fa)
+ struct file_kattr *fa)
{
if (!fa->fsx_valid)
return 0;
@@ -725,7 +725,7 @@ int
xfs_fileattr_set(
struct mnt_idmap *idmap,
struct dentry *dentry,
- struct fileattr *fa)
+ struct file_kattr *fa)
{
struct xfs_inode *ip = XFS_I(d_inode(dentry));
struct xfs_mount *mp = ip->i_mount;
@@ -990,9 +990,8 @@ xfs_ioc_getlabel(
BUILD_BUG_ON(sizeof(sbp->sb_fname) > FSLABEL_MAX);
/* 1 larger than sb_fname, so this ensures a trailing NUL char */
- memset(label, 0, sizeof(label));
spin_lock(&mp->m_sb_lock);
- strncpy(label, sbp->sb_fname, XFSLABEL_MAX);
+ memtostr_pad(label, sbp->sb_fname);
spin_unlock(&mp->m_sb_lock);
if (copy_to_user(user_label, label, sizeof(label)))
diff --git a/fs/xfs/xfs_ioctl.h b/fs/xfs/xfs_ioctl.h
index 12124946f347..f5ed5cf9d3df 100644
--- a/fs/xfs/xfs_ioctl.h
+++ b/fs/xfs/xfs_ioctl.h
@@ -17,13 +17,13 @@ xfs_ioc_swapext(
extern int
xfs_fileattr_get(
struct dentry *dentry,
- struct fileattr *fa);
+ struct file_kattr *fa);
extern int
xfs_fileattr_set(
struct mnt_idmap *idmap,
struct dentry *dentry,
- struct fileattr *fa);
+ struct file_kattr *fa);
extern long
xfs_file_ioctl(
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index ff05e6b1b0bb..2a74f2957341 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -79,6 +79,9 @@ xfs_iomap_valid(
{
struct xfs_inode *ip = XFS_I(inode);
+ if (iomap->type == IOMAP_HOLE)
+ return true;
+
if (iomap->validity_cookie !=
xfs_iomap_inode_sequence(ip, iomap->flags)) {
trace_xfs_iomap_invalid(ip, iomap);
@@ -89,7 +92,7 @@ xfs_iomap_valid(
return true;
}
-static const struct iomap_folio_ops xfs_iomap_folio_ops = {
+const struct iomap_write_ops xfs_iomap_write_ops = {
.iomap_valid = xfs_iomap_valid,
};
@@ -151,7 +154,6 @@ xfs_bmbt_to_iomap(
iomap->flags |= IOMAP_F_DIRTY;
iomap->validity_cookie = sequence_cookie;
- iomap->folio_ops = &xfs_iomap_folio_ops;
return 0;
}
@@ -827,7 +829,7 @@ xfs_bmap_hw_atomic_write_possible(
/*
* The ->iomap_begin caller should ensure this, but check anyway.
*/
- return len <= xfs_inode_buftarg(ip)->bt_bdev_awu_max;
+ return len <= xfs_inode_buftarg(ip)->bt_awu_max;
}
static int
@@ -2198,7 +2200,8 @@ xfs_zero_range(
return dax_zero_range(inode, pos, len, did_zero,
&xfs_dax_write_iomap_ops);
return iomap_zero_range(inode, pos, len, did_zero,
- &xfs_buffered_write_iomap_ops, ac);
+ &xfs_buffered_write_iomap_ops, &xfs_iomap_write_ops,
+ ac);
}
int
@@ -2214,5 +2217,6 @@ xfs_truncate_page(
return dax_truncate_page(inode, pos, did_zero,
&xfs_dax_write_iomap_ops);
return iomap_truncate_page(inode, pos, did_zero,
- &xfs_buffered_write_iomap_ops, ac);
+ &xfs_buffered_write_iomap_ops, &xfs_iomap_write_ops,
+ ac);
}
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 674f8ac1b9bd..ebcce7d49446 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -57,5 +57,6 @@ extern const struct iomap_ops xfs_seek_iomap_ops;
extern const struct iomap_ops xfs_xattr_iomap_ops;
extern const struct iomap_ops xfs_dax_write_iomap_ops;
extern const struct iomap_ops xfs_atomic_write_cow_iomap_ops;
+extern const struct iomap_write_ops xfs_iomap_write_ops;
#endif /* __XFS_IOMAP_H__*/
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 8cddbb7c149b..149b5460fbfd 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -665,7 +665,7 @@ xfs_get_atomic_write_max_opt(
* less than our out of place write limit, but we don't want to exceed
* the awu_max.
*/
- return min(awu_max, xfs_inode_buftarg(ip)->bt_bdev_awu_max);
+ return min(awu_max, xfs_inode_buftarg(ip)->bt_awu_max);
}
static void
@@ -970,7 +970,7 @@ xfs_setattr_size(
* change.
*/
if (xfs_is_zoned_inode(ip)) {
- error = xfs_zoned_space_reserve(ip, 1,
+ error = xfs_zoned_space_reserve(mp, 1,
XFS_ZR_NOWAIT | XFS_ZR_RESERVED, &ac);
if (error) {
if (error == -EAGAIN)
@@ -998,7 +998,7 @@ xfs_setattr_size(
}
if (xfs_is_zoned_inode(ip))
- xfs_zoned_space_unreserve(ip, &ac);
+ xfs_zoned_space_unreserve(mp, &ac);
if (error)
return error;
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 1fa1c0564b0c..c8c9b8d8309f 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -239,14 +239,10 @@ xfs_bulkstat_one(
* Grab an empty transaction so that we can use its recursive buffer
* locking abilities to detect cycles in the inobt without deadlocking.
*/
- error = xfs_trans_alloc_empty(breq->mp, &tp);
- if (error)
- goto out;
-
+ tp = xfs_trans_alloc_empty(breq->mp);
error = xfs_bulkstat_one_int(breq->mp, breq->idmap, tp,
breq->startino, &bc);
xfs_trans_cancel(tp);
-out:
kfree(bc.buf);
/*
@@ -331,17 +327,13 @@ xfs_bulkstat(
* Grab an empty transaction so that we can use its recursive buffer
* locking abilities to detect cycles in the inobt without deadlocking.
*/
- error = xfs_trans_alloc_empty(breq->mp, &tp);
- if (error)
- goto out;
-
+ tp = xfs_trans_alloc_empty(breq->mp);
if (breq->flags & XFS_IBULK_SAME_AG)
iwalk_flags |= XFS_IWALK_SAME_AG;
error = xfs_iwalk(breq->mp, tp, breq->startino, iwalk_flags,
xfs_bulkstat_iwalk, breq->icount, &bc);
xfs_trans_cancel(tp);
-out:
kfree(bc.buf);
/*
@@ -464,14 +456,10 @@ xfs_inumbers(
* Grab an empty transaction so that we can use its recursive buffer
* locking abilities to detect cycles in the inobt without deadlocking.
*/
- error = xfs_trans_alloc_empty(breq->mp, &tp);
- if (error)
- goto out;
-
+ tp = xfs_trans_alloc_empty(breq->mp);
error = xfs_inobt_walk(breq->mp, tp, breq->startino, breq->flags,
xfs_inumbers_walk, breq->icount, &ic);
xfs_trans_cancel(tp);
-out:
/*
* We found some inode groups, so clear the error status and return
diff --git a/fs/xfs/xfs_iwalk.c b/fs/xfs/xfs_iwalk.c
index 7db3ece370b1..c1c31d1a8e21 100644
--- a/fs/xfs/xfs_iwalk.c
+++ b/fs/xfs/xfs_iwalk.c
@@ -377,11 +377,8 @@ xfs_iwalk_run_callbacks(
if (!has_more)
return 0;
- if (iwag->drop_trans) {
- error = xfs_trans_alloc_empty(mp, &iwag->tp);
- if (error)
- return error;
- }
+ if (iwag->drop_trans)
+ iwag->tp = xfs_trans_alloc_empty(mp);
/* ...and recreate the cursor just past where we left off. */
error = xfs_ialloc_read_agi(iwag->pag, iwag->tp, 0, agi_bpp);
@@ -617,9 +614,7 @@ xfs_iwalk_ag_work(
* Grab an empty transaction so that we can use its recursive buffer
* locking abilities to detect cycles in the inobt without deadlocking.
*/
- error = xfs_trans_alloc_empty(mp, &iwag->tp);
- if (error)
- goto out;
+ iwag->tp = xfs_trans_alloc_empty(mp);
iwag->drop_trans = 1;
error = xfs_iwalk_ag(iwag);
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 793468b4d30d..c8a57e21a1d3 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -109,14 +109,14 @@ xlog_prepare_iovec(
vec = &lv->lv_iovecp[0];
}
- len = lv->lv_buf_len + sizeof(struct xlog_op_header);
+ len = lv->lv_buf_used + sizeof(struct xlog_op_header);
if (!IS_ALIGNED(len, sizeof(uint64_t))) {
- lv->lv_buf_len = round_up(len, sizeof(uint64_t)) -
+ lv->lv_buf_used = round_up(len, sizeof(uint64_t)) -
sizeof(struct xlog_op_header);
}
vec->i_type = type;
- vec->i_addr = lv->lv_buf + lv->lv_buf_len;
+ vec->i_addr = lv->lv_buf + lv->lv_buf_used;
oph = vec->i_addr;
oph->oh_clientid = XFS_TRANSACTION;
@@ -1931,9 +1931,9 @@ xlog_print_trans(
if (!lv)
continue;
xfs_warn(mp, " niovecs = %d", lv->lv_niovecs);
- xfs_warn(mp, " size = %d", lv->lv_size);
+ xfs_warn(mp, " alloc_size = %d", lv->lv_alloc_size);
xfs_warn(mp, " bytes = %d", lv->lv_bytes);
- xfs_warn(mp, " buf len = %d", lv->lv_buf_len);
+ xfs_warn(mp, " buf used= %d", lv->lv_buf_used);
/* dump each iovec for the log item */
vec = lv->lv_iovecp;
@@ -3092,16 +3092,16 @@ xfs_log_force_seq(
*/
void
xfs_log_ticket_put(
- xlog_ticket_t *ticket)
+ struct xlog_ticket *ticket)
{
ASSERT(atomic_read(&ticket->t_ref) > 0);
if (atomic_dec_and_test(&ticket->t_ref))
kmem_cache_free(xfs_log_ticket_cache, ticket);
}
-xlog_ticket_t *
+struct xlog_ticket *
xfs_log_ticket_get(
- xlog_ticket_t *ticket)
+ struct xlog_ticket *ticket)
{
ASSERT(atomic_read(&ticket->t_ref) > 0);
atomic_inc(&ticket->t_ref);
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index 13455854365f..af6daf4f6792 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -16,8 +16,8 @@ struct xfs_log_vec {
struct xfs_log_item *lv_item; /* owner */
char *lv_buf; /* formatted buffer */
int lv_bytes; /* accounted space in buffer */
- int lv_buf_len; /* aligned size of buffer */
- int lv_size; /* size of allocated lv */
+ int lv_buf_used; /* buffer space used so far */
+ int lv_alloc_size; /* size of allocated lv */
};
#define XFS_LOG_VEC_ORDERED (-1)
@@ -64,12 +64,13 @@ xlog_finish_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec *vec,
oph->oh_len = cpu_to_be32(len);
len += sizeof(struct xlog_op_header);
- lv->lv_buf_len += len;
+ lv->lv_buf_used += len;
lv->lv_bytes += len;
vec->i_len = len;
/* Catch buffer overruns */
- ASSERT((void *)lv->lv_buf + lv->lv_bytes <= (void *)lv + lv->lv_size);
+ ASSERT((void *)lv->lv_buf + lv->lv_bytes <=
+ (void *)lv + lv->lv_alloc_size);
}
/*
@@ -87,13 +88,6 @@ xlog_copy_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec **vecp,
return buf;
}
-static inline void *
-xlog_copy_from_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec **vecp,
- const struct xfs_log_iovec *src)
-{
- return xlog_copy_iovec(lv, vecp, src->i_type, src->i_addr, src->i_len);
-}
-
/*
* By comparing each component, we don't have to worry about extra
* endian issues in treating two 32 bit numbers as one 64 bit number
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index f66d2d430e4f..f443757e93c2 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -275,7 +275,7 @@ xlog_cil_alloc_shadow_bufs(
struct xfs_log_vec *lv;
int niovecs = 0;
int nbytes = 0;
- int buf_size;
+ int alloc_size;
bool ordered = false;
/* Skip items which aren't dirty in this transaction. */
@@ -316,14 +316,14 @@ xlog_cil_alloc_shadow_bufs(
* that space to ensure we can align it appropriately and not
* overrun the buffer.
*/
- buf_size = nbytes + xlog_cil_iovec_space(niovecs);
+ alloc_size = nbytes + xlog_cil_iovec_space(niovecs);
/*
* if we have no shadow buffer, or it is too small, we need to
* reallocate it.
*/
if (!lip->li_lv_shadow ||
- buf_size > lip->li_lv_shadow->lv_size) {
+ alloc_size > lip->li_lv_shadow->lv_alloc_size) {
/*
* We free and allocate here as a realloc would copy
* unnecessary data. We don't use kvzalloc() for the
@@ -332,15 +332,15 @@ xlog_cil_alloc_shadow_bufs(
* storage.
*/
kvfree(lip->li_lv_shadow);
- lv = xlog_kvmalloc(buf_size);
+ lv = xlog_kvmalloc(alloc_size);
memset(lv, 0, xlog_cil_iovec_space(niovecs));
INIT_LIST_HEAD(&lv->lv_list);
lv->lv_item = lip;
- lv->lv_size = buf_size;
+ lv->lv_alloc_size = alloc_size;
if (ordered)
- lv->lv_buf_len = XFS_LOG_VEC_ORDERED;
+ lv->lv_buf_used = XFS_LOG_VEC_ORDERED;
else
lv->lv_iovecp = (struct xfs_log_iovec *)&lv[1];
lip->li_lv_shadow = lv;
@@ -348,9 +348,9 @@ xlog_cil_alloc_shadow_bufs(
/* same or smaller, optimise common overwrite case */
lv = lip->li_lv_shadow;
if (ordered)
- lv->lv_buf_len = XFS_LOG_VEC_ORDERED;
+ lv->lv_buf_used = XFS_LOG_VEC_ORDERED;
else
- lv->lv_buf_len = 0;
+ lv->lv_buf_used = 0;
lv->lv_bytes = 0;
}
@@ -370,30 +370,30 @@ xlog_cil_alloc_shadow_bufs(
STATIC void
xfs_cil_prepare_item(
struct xlog *log,
+ struct xfs_log_item *lip,
struct xfs_log_vec *lv,
- struct xfs_log_vec *old_lv,
int *diff_len)
{
/* Account for the new LV being passed in */
- if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED)
+ if (lv->lv_buf_used != XFS_LOG_VEC_ORDERED)
*diff_len += lv->lv_bytes;
/*
* If there is no old LV, this is the first time we've seen the item in
* this CIL context and so we need to pin it. If we are replacing the
- * old_lv, then remove the space it accounts for and make it the shadow
+ * old lv, then remove the space it accounts for and make it the shadow
* buffer for later freeing. In both cases we are now switching to the
* shadow buffer, so update the pointer to it appropriately.
*/
- if (!old_lv) {
+ if (!lip->li_lv) {
if (lv->lv_item->li_ops->iop_pin)
lv->lv_item->li_ops->iop_pin(lv->lv_item);
lv->lv_item->li_lv_shadow = NULL;
- } else if (old_lv != lv) {
- ASSERT(lv->lv_buf_len != XFS_LOG_VEC_ORDERED);
+ } else if (lip->li_lv != lv) {
+ ASSERT(lv->lv_buf_used != XFS_LOG_VEC_ORDERED);
- *diff_len -= old_lv->lv_bytes;
- lv->lv_item->li_lv_shadow = old_lv;
+ *diff_len -= lip->li_lv->lv_bytes;
+ lv->lv_item->li_lv_shadow = lip->li_lv;
}
/* attach new log vector to log item */
@@ -452,10 +452,8 @@ xlog_cil_insert_format_items(
}
list_for_each_entry(lip, &tp->t_items, li_trans) {
- struct xfs_log_vec *lv;
- struct xfs_log_vec *old_lv = NULL;
- struct xfs_log_vec *shadow;
- bool ordered = false;
+ struct xfs_log_vec *lv = lip->li_lv;
+ struct xfs_log_vec *shadow = lip->li_lv_shadow;
/* Skip items which aren't dirty in this transaction. */
if (!test_bit(XFS_LI_DIRTY, &lip->li_flags))
@@ -465,22 +463,23 @@ xlog_cil_insert_format_items(
* The formatting size information is already attached to
* the shadow lv on the log item.
*/
- shadow = lip->li_lv_shadow;
- if (shadow->lv_buf_len == XFS_LOG_VEC_ORDERED)
- ordered = true;
+ if (shadow->lv_buf_used == XFS_LOG_VEC_ORDERED) {
+ if (!lv) {
+ lv = shadow;
+ lv->lv_item = lip;
+ }
+ ASSERT(shadow->lv_alloc_size == lv->lv_alloc_size);
+ xfs_cil_prepare_item(log, lip, lv, diff_len);
+ continue;
+ }
/* Skip items that do not have any vectors for writing */
- if (!shadow->lv_niovecs && !ordered)
+ if (!shadow->lv_niovecs)
continue;
/* compare to existing item size */
- old_lv = lip->li_lv;
- if (lip->li_lv && shadow->lv_size <= lip->li_lv->lv_size) {
+ if (lv && shadow->lv_alloc_size <= lv->lv_alloc_size) {
/* same or smaller, optimise common overwrite case */
- lv = lip->li_lv;
-
- if (ordered)
- goto insert;
/*
* set the item up as though it is a new insertion so
@@ -492,7 +491,7 @@ xlog_cil_insert_format_items(
lv->lv_niovecs = shadow->lv_niovecs;
/* reset the lv buffer information for new formatting */
- lv->lv_buf_len = 0;
+ lv->lv_buf_used = 0;
lv->lv_bytes = 0;
lv->lv_buf = (char *)lv +
xlog_cil_iovec_space(lv->lv_niovecs);
@@ -500,17 +499,11 @@ xlog_cil_insert_format_items(
/* switch to shadow buffer! */
lv = shadow;
lv->lv_item = lip;
- if (ordered) {
- /* track as an ordered logvec */
- ASSERT(lip->li_lv == NULL);
- goto insert;
- }
}
ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t)));
lip->li_ops->iop_format(lip, lv);
-insert:
- xfs_cil_prepare_item(log, lv, old_lv, diff_len);
+ xfs_cil_prepare_item(log, lip, lv, diff_len);
}
}
@@ -793,8 +786,10 @@ xlog_cil_ail_insert(
struct xfs_log_item *lip = lv->lv_item;
xfs_lsn_t item_lsn;
- if (aborted)
+ if (aborted) {
+ trace_xlog_ail_insert_abort(lip);
set_bit(XFS_LI_ABORTED, &lip->li_flags);
+ }
if (lip->li_ops->flags & XFS_ITEM_RELEASE_WHEN_COMMITTED) {
lip->li_ops->iop_release(lip);
@@ -1243,7 +1238,7 @@ xlog_cil_build_lv_chain(
lv->lv_order_id = item->li_order_id;
/* we don't write ordered log vectors */
- if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED)
+ if (lv->lv_buf_used != XFS_LOG_VEC_ORDERED)
*num_bytes += lv->lv_bytes;
*num_iovecs += lv->lv_niovecs;
list_add_tail(&lv->lv_list, &ctx->lv_chain);
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 39a102cc1b43..a9a7a271c15b 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -144,7 +144,7 @@ enum xlog_iclog_state {
#define XLOG_COVER_OPS 5
-typedef struct xlog_ticket {
+struct xlog_ticket {
struct list_head t_queue; /* reserve/write queue */
struct task_struct *t_task; /* task that owns this ticket */
xlog_tid_t t_tid; /* transaction identifier */
@@ -155,7 +155,7 @@ typedef struct xlog_ticket {
char t_cnt; /* current unit count */
uint8_t t_flags; /* properties of reservation */
int t_iclog_hdrs; /* iclog hdrs in t_curr_res */
-} xlog_ticket_t;
+};
/*
* - A log record header is 512 bytes. There is plenty of room to grow the
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 2f76531842f8..e6ed9e09c027 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2131,15 +2131,15 @@ xlog_recover_add_to_cont_trans(
item = list_entry(trans->r_itemq.prev, struct xlog_recover_item,
ri_list);
- old_ptr = item->ri_buf[item->ri_cnt-1].i_addr;
- old_len = item->ri_buf[item->ri_cnt-1].i_len;
+ old_ptr = item->ri_buf[item->ri_cnt-1].iov_base;
+ old_len = item->ri_buf[item->ri_cnt-1].iov_len;
ptr = kvrealloc(old_ptr, len + old_len, GFP_KERNEL);
if (!ptr)
return -ENOMEM;
memcpy(&ptr[old_len], dp, len);
- item->ri_buf[item->ri_cnt-1].i_len += len;
- item->ri_buf[item->ri_cnt-1].i_addr = ptr;
+ item->ri_buf[item->ri_cnt-1].iov_len += len;
+ item->ri_buf[item->ri_cnt-1].iov_base = ptr;
trace_xfs_log_recover_item_add_cont(log, trans, item, 0);
return 0;
}
@@ -2223,7 +2223,7 @@ xlog_recover_add_to_trans(
}
item->ri_total = in_f->ilf_size;
- item->ri_buf = kzalloc(item->ri_total * sizeof(xfs_log_iovec_t),
+ item->ri_buf = kcalloc(item->ri_total, sizeof(*item->ri_buf),
GFP_KERNEL | __GFP_NOFAIL);
}
@@ -2237,8 +2237,8 @@ xlog_recover_add_to_trans(
}
/* Description region is ri_buf[0] */
- item->ri_buf[item->ri_cnt].i_addr = ptr;
- item->ri_buf[item->ri_cnt].i_len = len;
+ item->ri_buf[item->ri_cnt].iov_base = ptr;
+ item->ri_buf[item->ri_cnt].iov_len = len;
item->ri_cnt++;
trace_xfs_log_recover_item_add(log, trans, item, 0);
return 0;
@@ -2262,7 +2262,7 @@ xlog_recover_free_trans(
/* Free the regions in the item. */
list_del(&item->ri_list);
for (i = 0; i < item->ri_cnt; i++)
- kvfree(item->ri_buf[i].i_addr);
+ kvfree(item->ri_buf[i].iov_base);
/* Free the item itself */
kfree(item->ri_buf);
kfree(item);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 29276fe60df9..0b690bc119d7 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -171,19 +171,16 @@ xfs_readsb(
ASSERT(mp->m_ddev_targp != NULL);
/*
- * For the initial read, we must guess at the sector
- * size based on the block device. It's enough to
- * get the sb_sectsize out of the superblock and
- * then reread with the proper length.
- * We don't verify it yet, because it may not be complete.
+ * In the first pass, use the device sector size to just read enough
+ * of the superblock to extract the XFS sector size.
+ *
+ * The device sector size must be smaller than or equal to the XFS
+ * sector size and thus we can always read the superblock. Once we know
+ * the XFS sector size, re-read it and run the buffer verifier.
*/
- sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
+ sector_size = mp->m_ddev_targp->bt_logical_sectorsize;
buf_ops = NULL;
- /*
- * Allocate a (locked) buffer to hold the superblock. This will be kept
- * around at all times to optimize access to the superblock.
- */
reread:
error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
BTOBB(sector_size), &bp, buf_ops);
@@ -247,6 +244,10 @@ reread:
/* no need to be quiet anymore, so reset the buf ops */
bp->b_ops = &xfs_sb_buf_ops;
+ /*
+ * Keep a pointer of the sb buffer around instead of caching it in the
+ * buffer cache because we access it frequently.
+ */
mp->m_sb_bp = bp;
xfs_buf_unlock(bp);
return 0;
@@ -678,68 +679,46 @@ static inline unsigned int max_pow_of_two_factor(const unsigned int nr)
}
/*
- * If the data device advertises atomic write support, limit the size of data
- * device atomic writes to the greatest power-of-two factor of the AG size so
- * that every atomic write unit aligns with the start of every AG. This is
- * required so that the per-AG allocations for an atomic write will always be
+ * If the underlying device advertises atomic write support, limit the size of
+ * atomic writes to the greatest power-of-two factor of the group size so
+ * that every atomic write unit aligns with the start of every group. This is
+ * required so that the allocations for an atomic write will always be
* aligned compatibly with the alignment requirements of the storage.
*
- * If the data device doesn't advertise atomic writes, then there are no
- * alignment restrictions and the largest out-of-place write we can do
- * ourselves is the number of blocks that user files can allocate from any AG.
- */
-static inline xfs_extlen_t xfs_calc_perag_awu_max(struct xfs_mount *mp)
-{
- if (mp->m_ddev_targp->bt_bdev_awu_min > 0)
- return max_pow_of_two_factor(mp->m_sb.sb_agblocks);
- return rounddown_pow_of_two(mp->m_ag_max_usable);
-}
-
-/*
- * Reflink on the realtime device requires rtgroups, and atomic writes require
- * reflink.
- *
- * If the realtime device advertises atomic write support, limit the size of
- * data device atomic writes to the greatest power-of-two factor of the rtgroup
- * size so that every atomic write unit aligns with the start of every rtgroup.
- * This is required so that the per-rtgroup allocations for an atomic write
- * will always be aligned compatibly with the alignment requirements of the
- * storage.
- *
- * If the rt device doesn't advertise atomic writes, then there are no
- * alignment restrictions and the largest out-of-place write we can do
- * ourselves is the number of blocks that user files can allocate from any
- * rtgroup.
+ * If the device doesn't advertise atomic writes, then there are no alignment
+ * restrictions and the largest out-of-place write we can do ourselves is the
+ * number of blocks that user files can allocate from any group.
*/
-static inline xfs_extlen_t xfs_calc_rtgroup_awu_max(struct xfs_mount *mp)
+static xfs_extlen_t
+xfs_calc_group_awu_max(
+ struct xfs_mount *mp,
+ enum xfs_group_type type)
{
- struct xfs_groups *rgs = &mp->m_groups[XG_TYPE_RTG];
+ struct xfs_groups *g = &mp->m_groups[type];
+ struct xfs_buftarg *btp = xfs_group_type_buftarg(mp, type);
- if (rgs->blocks == 0)
+ if (g->blocks == 0)
return 0;
- if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_bdev_awu_min > 0)
- return max_pow_of_two_factor(rgs->blocks);
- return rounddown_pow_of_two(rgs->blocks);
+ if (btp && btp->bt_awu_min > 0)
+ return max_pow_of_two_factor(g->blocks);
+ return rounddown_pow_of_two(g->blocks);
}
/* Compute the maximum atomic write unit size for each section. */
static inline void
xfs_calc_atomic_write_unit_max(
- struct xfs_mount *mp)
+ struct xfs_mount *mp,
+ enum xfs_group_type type)
{
- struct xfs_groups *ags = &mp->m_groups[XG_TYPE_AG];
- struct xfs_groups *rgs = &mp->m_groups[XG_TYPE_RTG];
+ struct xfs_groups *g = &mp->m_groups[type];
const xfs_extlen_t max_write = xfs_calc_atomic_write_max(mp);
const xfs_extlen_t max_ioend = xfs_reflink_max_atomic_cow(mp);
- const xfs_extlen_t max_agsize = xfs_calc_perag_awu_max(mp);
- const xfs_extlen_t max_rgsize = xfs_calc_rtgroup_awu_max(mp);
-
- ags->awu_max = min3(max_write, max_ioend, max_agsize);
- rgs->awu_max = min3(max_write, max_ioend, max_rgsize);
+ const xfs_extlen_t max_gsize = xfs_calc_group_awu_max(mp, type);
- trace_xfs_calc_atomic_write_unit_max(mp, max_write, max_ioend,
- max_agsize, max_rgsize);
+ g->awu_max = min3(max_write, max_ioend, max_gsize);
+ trace_xfs_calc_atomic_write_unit_max(mp, type, max_write, max_ioend,
+ max_gsize, g->awu_max);
}
/*
@@ -757,7 +736,8 @@ xfs_set_max_atomic_write_opt(
max(mp->m_groups[XG_TYPE_AG].blocks,
mp->m_groups[XG_TYPE_RTG].blocks);
const xfs_extlen_t max_group_write =
- max(xfs_calc_perag_awu_max(mp), xfs_calc_rtgroup_awu_max(mp));
+ max(xfs_calc_group_awu_max(mp, XG_TYPE_AG),
+ xfs_calc_group_awu_max(mp, XG_TYPE_RTG));
int error;
if (new_max_bytes == 0)
@@ -813,7 +793,8 @@ set_limit:
return error;
}
- xfs_calc_atomic_write_unit_max(mp);
+ xfs_calc_atomic_write_unit_max(mp, XG_TYPE_AG);
+ xfs_calc_atomic_write_unit_max(mp, XG_TYPE_RTG);
mp->m_awu_max_bytes = new_max_bytes;
return 0;
}
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index d85084f9f317..97de44c32272 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -802,4 +802,21 @@ static inline void xfs_mod_sb_delalloc(struct xfs_mount *mp, int64_t delta)
int xfs_set_max_atomic_write_opt(struct xfs_mount *mp,
unsigned long long new_max_bytes);
+static inline struct xfs_buftarg *
+xfs_group_type_buftarg(
+ struct xfs_mount *mp,
+ enum xfs_group_type type)
+{
+ switch (type) {
+ case XG_TYPE_AG:
+ return mp->m_ddev_targp;
+ case XG_TYPE_RTG:
+ return mp->m_rtdev_targp;
+ default:
+ ASSERT(0);
+ break;
+ }
+ return NULL;
+}
+
#endif /* __XFS_MOUNT_H__ */
diff --git a/fs/xfs/xfs_mru_cache.c b/fs/xfs/xfs_mru_cache.c
index 08443ceec329..866c71d9fbae 100644
--- a/fs/xfs/xfs_mru_cache.c
+++ b/fs/xfs/xfs_mru_cache.c
@@ -320,7 +320,7 @@ xfs_mru_cache_create(
xfs_mru_cache_free_func_t free_func)
{
struct xfs_mru_cache *mru = NULL;
- int err = 0, grp;
+ int grp;
unsigned int grp_time;
if (mrup)
@@ -341,8 +341,8 @@ xfs_mru_cache_create(
mru->lists = kzalloc(mru->grp_count * sizeof(*mru->lists),
GFP_KERNEL | __GFP_NOFAIL);
if (!mru->lists) {
- err = -ENOMEM;
- goto exit;
+ kfree(mru);
+ return -ENOMEM;
}
for (grp = 0; grp < mru->grp_count; grp++)
@@ -361,14 +361,7 @@ xfs_mru_cache_create(
mru->free_func = free_func;
mru->data = data;
*mrup = mru;
-
-exit:
- if (err && mru && mru->lists)
- kfree(mru->lists);
- if (err && mru)
- kfree(mru);
-
- return err;
+ return 0;
}
/*
@@ -425,10 +418,6 @@ xfs_mru_cache_insert(
{
int error = -EINVAL;
- ASSERT(mru && mru->lists);
- if (!mru || !mru->lists)
- goto out_free;
-
error = -ENOMEM;
if (radix_tree_preload(GFP_KERNEL))
goto out_free;
diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c
index 3545dc1d953c..fbeddcac4792 100644
--- a/fs/xfs/xfs_notify_failure.c
+++ b/fs/xfs/xfs_notify_failure.c
@@ -253,8 +253,7 @@ xfs_dax_notify_dev_failure(
return -EOPNOTSUPP;
}
- error = xfs_dax_translate_range(type == XG_TYPE_RTG ?
- mp->m_rtdev_targp : mp->m_ddev_targp,
+ error = xfs_dax_translate_range(xfs_group_type_buftarg(mp, type),
offset, len, &daddr, &bblen);
if (error)
return error;
@@ -280,10 +279,7 @@ xfs_dax_notify_dev_failure(
kernel_frozen = xfs_dax_notify_failure_freeze(mp) == 0;
}
- error = xfs_trans_alloc_empty(mp, &tp);
- if (error)
- goto out;
-
+ tp = xfs_trans_alloc_empty(mp);
start_gno = xfs_fsb_to_gno(mp, start_bno, type);
end_gno = xfs_fsb_to_gno(mp, end_bno, type);
while ((xg = xfs_group_next_range(mp, xg, start_gno, end_gno, type))) {
@@ -354,7 +350,6 @@ xfs_dax_notify_dev_failure(
error = -EFSCORRUPTED;
}
-out:
/* Thaw the fs if it has been frozen before. */
if (mf_flags & MF_MEM_PRE_REMOVE)
xfs_dax_notify_failure_thaw(mp, kernel_frozen);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 417439b58785..23ba84ec919a 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -134,6 +134,7 @@ xfs_qm_dqpurge(
dqp->q_flags |= XFS_DQFLAG_FREEING;
+ xfs_qm_dqunpin_wait(dqp);
xfs_dqflock(dqp);
/*
@@ -465,6 +466,7 @@ xfs_qm_dquot_isolate(
struct xfs_dquot *dqp = container_of(item,
struct xfs_dquot, q_lru);
struct xfs_qm_isolate *isol = arg;
+ enum lru_status ret = LRU_SKIP;
if (!xfs_dqlock_nowait(dqp))
goto out_miss_busy;
@@ -478,6 +480,16 @@ xfs_qm_dquot_isolate(
goto out_miss_unlock;
/*
+ * If the dquot is pinned or dirty, rotate it to the end of the LRU to
+ * give some time for it to be cleaned before we try to isolate it
+ * again.
+ */
+ ret = LRU_ROTATE;
+ if (XFS_DQ_IS_DIRTY(dqp) || atomic_read(&dqp->q_pincount) > 0) {
+ goto out_miss_unlock;
+ }
+
+ /*
* This dquot has acquired a reference in the meantime remove it from
* the freelist and try again.
*/
@@ -492,41 +504,14 @@ xfs_qm_dquot_isolate(
}
/*
- * If the dquot is dirty, flush it. If it's already being flushed, just
- * skip it so there is time for the IO to complete before we try to
- * reclaim it again on the next LRU pass.
+ * The dquot may still be under IO, in which case the flush lock will be
+ * held. If we can't get the flush lock now, just skip over the dquot as
+ * if it was dirty.
*/
if (!xfs_dqflock_nowait(dqp))
goto out_miss_unlock;
- if (XFS_DQ_IS_DIRTY(dqp)) {
- struct xfs_buf *bp = NULL;
- int error;
-
- trace_xfs_dqreclaim_dirty(dqp);
-
- /* we have to drop the LRU lock to flush the dquot */
- spin_unlock(&lru->lock);
-
- error = xfs_dquot_use_attached_buf(dqp, &bp);
- if (!bp || error == -EAGAIN) {
- xfs_dqfunlock(dqp);
- goto out_unlock_dirty;
- }
-
- /*
- * dqflush completes dqflock on error, and the delwri ioend
- * does it on success.
- */
- error = xfs_qm_dqflush(dqp, bp);
- if (error)
- goto out_unlock_dirty;
-
- xfs_buf_delwri_queue(bp, &isol->buffers);
- xfs_buf_relse(bp);
- goto out_unlock_dirty;
- }
-
+ ASSERT(!XFS_DQ_IS_DIRTY(dqp));
xfs_dquot_detach_buf(dqp);
xfs_dqfunlock(dqp);
@@ -548,13 +533,7 @@ out_miss_unlock:
out_miss_busy:
trace_xfs_dqreclaim_busy(dqp);
XFS_STATS_INC(dqp->q_mount, xs_qm_dqreclaim_misses);
- return LRU_SKIP;
-
-out_unlock_dirty:
- trace_xfs_dqreclaim_busy(dqp);
- XFS_STATS_INC(dqp->q_mount, xs_qm_dqreclaim_misses);
- xfs_dqunlock(dqp);
- return LRU_RETRY;
+ return ret;
}
static unsigned long
@@ -681,10 +660,7 @@ xfs_qm_load_metadir_qinos(
struct xfs_trans *tp;
int error;
- error = xfs_trans_alloc_empty(mp, &tp);
- if (error)
- return error;
-
+ tp = xfs_trans_alloc_empty(mp);
error = xfs_dqinode_load_parent(tp, &qi->qi_dirip);
if (error == -ENOENT) {
/* no quota dir directory, but we'll create one later */
@@ -1486,7 +1462,6 @@ xfs_qm_flush_one(
struct xfs_dquot *dqp,
void *data)
{
- struct xfs_mount *mp = dqp->q_mount;
struct list_head *buffer_list = data;
struct xfs_buf *bp = NULL;
int error = 0;
@@ -1497,34 +1472,8 @@ xfs_qm_flush_one(
if (!XFS_DQ_IS_DIRTY(dqp))
goto out_unlock;
- /*
- * The only way the dquot is already flush locked by the time quotacheck
- * gets here is if reclaim flushed it before the dqadjust walk dirtied
- * it for the final time. Quotacheck collects all dquot bufs in the
- * local delwri queue before dquots are dirtied, so reclaim can't have
- * possibly queued it for I/O. The only way out is to push the buffer to
- * cycle the flush lock.
- */
- if (!xfs_dqflock_nowait(dqp)) {
- /* buf is pinned in-core by delwri list */
- error = xfs_buf_incore(mp->m_ddev_targp, dqp->q_blkno,
- mp->m_quotainfo->qi_dqchunklen, 0, &bp);
- if (error)
- goto out_unlock;
-
- if (!(bp->b_flags & _XBF_DELWRI_Q)) {
- error = -EAGAIN;
- xfs_buf_relse(bp);
- goto out_unlock;
- }
- xfs_buf_unlock(bp);
-
- xfs_buf_delwri_pushbuf(bp, buffer_list);
- xfs_buf_rele(bp);
-
- error = -EAGAIN;
- goto out_unlock;
- }
+ xfs_qm_dqunpin_wait(dqp);
+ xfs_dqflock(dqp);
error = xfs_dquot_use_attached_buf(dqp, &bp);
if (error)
@@ -1803,10 +1752,7 @@ xfs_qm_qino_load(
struct xfs_inode *dp = NULL;
int error;
- error = xfs_trans_alloc_empty(mp, &tp);
- if (error)
- return error;
-
+ tp = xfs_trans_alloc_empty(mp);
if (xfs_has_metadir(mp)) {
error = xfs_dqinode_load_parent(tp, &dp);
if (error)
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 076501123d89..3728234699a2 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -717,18 +717,18 @@ xlog_recover_cui_commit_pass2(
struct xfs_cui_log_format *cui_formatp;
size_t len;
- cui_formatp = item->ri_buf[0].i_addr;
+ cui_formatp = item->ri_buf[0].iov_base;
- if (item->ri_buf[0].i_len < xfs_cui_log_format_sizeof(0)) {
+ if (item->ri_buf[0].iov_len < xfs_cui_log_format_sizeof(0)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
len = xfs_cui_log_format_sizeof(cui_formatp->cui_nextents);
- if (item->ri_buf[0].i_len != len) {
+ if (item->ri_buf[0].iov_len != len) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
@@ -759,18 +759,18 @@ xlog_recover_rtcui_commit_pass2(
struct xfs_cui_log_format *cui_formatp;
size_t len;
- cui_formatp = item->ri_buf[0].i_addr;
+ cui_formatp = item->ri_buf[0].iov_base;
- if (item->ri_buf[0].i_len < xfs_cui_log_format_sizeof(0)) {
+ if (item->ri_buf[0].iov_len < xfs_cui_log_format_sizeof(0)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
len = xfs_cui_log_format_sizeof(cui_formatp->cui_nextents);
- if (item->ri_buf[0].i_len != len) {
+ if (item->ri_buf[0].iov_len != len) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
@@ -791,7 +791,7 @@ xlog_recover_rtcui_commit_pass2(
xfs_lsn_t lsn)
{
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
#endif
@@ -817,10 +817,10 @@ xlog_recover_cud_commit_pass2(
{
struct xfs_cud_log_format *cud_formatp;
- cud_formatp = item->ri_buf[0].i_addr;
- if (item->ri_buf[0].i_len != sizeof(struct xfs_cud_log_format)) {
+ cud_formatp = item->ri_buf[0].iov_base;
+ if (item->ri_buf[0].iov_len != sizeof(struct xfs_cud_log_format)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
@@ -843,10 +843,10 @@ xlog_recover_rtcud_commit_pass2(
{
struct xfs_cud_log_format *cud_formatp;
- cud_formatp = item->ri_buf[0].i_addr;
- if (item->ri_buf[0].i_len != sizeof(struct xfs_cud_log_format)) {
+ cud_formatp = item->ri_buf[0].iov_base;
+ if (item->ri_buf[0].iov_len != sizeof(struct xfs_cud_log_format)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index ad3bcb76d805..3f177b4ec131 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1881,7 +1881,8 @@ xfs_reflink_unshare(
&xfs_dax_write_iomap_ops);
else
error = iomap_file_unshare(inode, offset, len,
- &xfs_buffered_write_iomap_ops);
+ &xfs_buffered_write_iomap_ops,
+ &xfs_iomap_write_ops);
if (error)
goto out;
diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c
index c99700318ec2..15f0903f6fd4 100644
--- a/fs/xfs/xfs_rmap_item.c
+++ b/fs/xfs/xfs_rmap_item.c
@@ -746,18 +746,18 @@ xlog_recover_rui_commit_pass2(
struct xfs_rui_log_format *rui_formatp;
size_t len;
- rui_formatp = item->ri_buf[0].i_addr;
+ rui_formatp = item->ri_buf[0].iov_base;
- if (item->ri_buf[0].i_len < xfs_rui_log_format_sizeof(0)) {
+ if (item->ri_buf[0].iov_len < xfs_rui_log_format_sizeof(0)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
len = xfs_rui_log_format_sizeof(rui_formatp->rui_nextents);
- if (item->ri_buf[0].i_len != len) {
+ if (item->ri_buf[0].iov_len != len) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
@@ -788,18 +788,18 @@ xlog_recover_rtrui_commit_pass2(
struct xfs_rui_log_format *rui_formatp;
size_t len;
- rui_formatp = item->ri_buf[0].i_addr;
+ rui_formatp = item->ri_buf[0].iov_base;
- if (item->ri_buf[0].i_len < xfs_rui_log_format_sizeof(0)) {
+ if (item->ri_buf[0].iov_len < xfs_rui_log_format_sizeof(0)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
len = xfs_rui_log_format_sizeof(rui_formatp->rui_nextents);
- if (item->ri_buf[0].i_len != len) {
+ if (item->ri_buf[0].iov_len != len) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
@@ -820,7 +820,7 @@ xlog_recover_rtrui_commit_pass2(
xfs_lsn_t lsn)
{
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
- item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ item->ri_buf[0].iov_base, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
#endif
@@ -846,10 +846,10 @@ xlog_recover_rud_commit_pass2(
{
struct xfs_rud_log_format *rud_formatp;
- rud_formatp = item->ri_buf[0].i_addr;
- if (item->ri_buf[0].i_len != sizeof(struct xfs_rud_log_format)) {
+ rud_formatp = item->ri_buf[0].iov_base;
+ if (item->ri_buf[0].iov_len != sizeof(struct xfs_rud_log_format)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
- rud_formatp, item->ri_buf[0].i_len);
+ rud_formatp, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
@@ -872,10 +872,10 @@ xlog_recover_rtrud_commit_pass2(
{
struct xfs_rud_log_format *rud_formatp;
- rud_formatp = item->ri_buf[0].i_addr;
- if (item->ri_buf[0].i_len != sizeof(struct xfs_rud_log_format)) {
+ rud_formatp = item->ri_buf[0].iov_base;
+ if (item->ri_buf[0].iov_len != sizeof(struct xfs_rud_log_format)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
- rud_formatp, item->ri_buf[0].i_len);
+ rud_formatp, item->ri_buf[0].iov_len);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 6484c596ecea..6907e871fa15 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -729,9 +729,7 @@ xfs_rtginode_ensure(
if (rtg->rtg_inodes[type])
return 0;
- error = xfs_trans_alloc_empty(rtg_mount(rtg), &tp);
- if (error)
- return error;
+ tp = xfs_trans_alloc_empty(rtg_mount(rtg));
error = xfs_rtginode_load(rtg, type, tp);
xfs_trans_cancel(tp);
@@ -1259,6 +1257,8 @@ xfs_growfs_check_rtgeom(
kfree(nmp);
+ trace_xfs_growfs_check_rtgeom(mp, min_logfsbs);
+
if (min_logfsbs > mp->m_sb.sb_logblocks)
return -EINVAL;
@@ -1303,9 +1303,7 @@ xfs_growfs_rt_prep_groups(
if (!mp->m_rtdirip) {
struct xfs_trans *tp;
- error = xfs_trans_alloc_empty(mp, &tp);
- if (error)
- return error;
+ tp = xfs_trans_alloc_empty(mp);
error = xfs_rtginode_load_parent(tp);
xfs_trans_cancel(tp);
@@ -1672,10 +1670,7 @@ xfs_rtmount_inodes(
struct xfs_rtgroup *rtg = NULL;
int error;
- error = xfs_trans_alloc_empty(mp, &tp);
- if (error)
- return error;
-
+ tp = xfs_trans_alloc_empty(mp);
if (xfs_has_rtgroups(mp) && mp->m_sb.sb_rgcount > 0) {
error = xfs_rtginode_load_parent(tp);
if (error)
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 0bc4b5489078..bb0a82635a77 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -2020,14 +2020,13 @@ xfs_remount_rw(
int error;
if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp &&
- bdev_read_only(mp->m_logdev_targp->bt_bdev)) {
+ xfs_readonly_buftarg(mp->m_logdev_targp)) {
xfs_warn(mp,
"ro->rw transition prohibited by read-only logdev");
return -EACCES;
}
- if (mp->m_rtdev_targp &&
- bdev_read_only(mp->m_rtdev_targp->bt_bdev)) {
+ if (mp->m_rtdev_targp && xfs_readonly_buftarg(mp->m_rtdev_targp)) {
xfs_warn(mp,
"ro->rw transition prohibited by read-only rtdev");
return -EACCES;
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 01d284a1c759..e1794e3e3156 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -171,36 +171,33 @@ DEFINE_ATTR_LIST_EVENT(xfs_attr_leaf_list);
DEFINE_ATTR_LIST_EVENT(xfs_attr_node_list);
TRACE_EVENT(xfs_calc_atomic_write_unit_max,
- TP_PROTO(struct xfs_mount *mp, unsigned int max_write,
- unsigned int max_ioend, unsigned int max_agsize,
- unsigned int max_rgsize),
- TP_ARGS(mp, max_write, max_ioend, max_agsize, max_rgsize),
+ TP_PROTO(struct xfs_mount *mp, enum xfs_group_type type,
+ unsigned int max_write, unsigned int max_ioend,
+ unsigned int max_gsize, unsigned int awu_max),
+ TP_ARGS(mp, type, max_write, max_ioend, max_gsize, awu_max),
TP_STRUCT__entry(
__field(dev_t, dev)
+ __field(enum xfs_group_type, type)
__field(unsigned int, max_write)
__field(unsigned int, max_ioend)
- __field(unsigned int, max_agsize)
- __field(unsigned int, max_rgsize)
- __field(unsigned int, data_awu_max)
- __field(unsigned int, rt_awu_max)
+ __field(unsigned int, max_gsize)
+ __field(unsigned int, awu_max)
),
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
+ __entry->type = type;
__entry->max_write = max_write;
__entry->max_ioend = max_ioend;
- __entry->max_agsize = max_agsize;
- __entry->max_rgsize = max_rgsize;
- __entry->data_awu_max = mp->m_groups[XG_TYPE_AG].awu_max;
- __entry->rt_awu_max = mp->m_groups[XG_TYPE_RTG].awu_max;
+ __entry->max_gsize = max_gsize;
+ __entry->awu_max = awu_max;
),
- TP_printk("dev %d:%d max_write %u max_ioend %u max_agsize %u max_rgsize %u data_awu_max %u rt_awu_max %u",
+ TP_printk("dev %d:%d %s max_write %u max_ioend %u max_gsize %u awu_max %u",
MAJOR(__entry->dev), MINOR(__entry->dev),
+ __print_symbolic(__entry->type, XG_TYPE_STRINGS),
__entry->max_write,
__entry->max_ioend,
- __entry->max_agsize,
- __entry->max_rgsize,
- __entry->data_awu_max,
- __entry->rt_awu_max)
+ __entry->max_gsize,
+ __entry->awu_max)
);
TRACE_EVENT(xfs_calc_max_atomic_write_fsblocks,
@@ -428,8 +425,8 @@ DECLARE_EVENT_CLASS(xfs_zone_alloc_class,
__field(dev_t, dev)
__field(xfs_rgnumber_t, rgno)
__field(xfs_rgblock_t, used)
+ __field(xfs_rgblock_t, allocated)
__field(xfs_rgblock_t, written)
- __field(xfs_rgblock_t, write_pointer)
__field(xfs_rgblock_t, rgbno)
__field(xfs_extlen_t, len)
),
@@ -437,17 +434,17 @@ DECLARE_EVENT_CLASS(xfs_zone_alloc_class,
__entry->dev = rtg_mount(oz->oz_rtg)->m_super->s_dev;
__entry->rgno = rtg_rgno(oz->oz_rtg);
__entry->used = rtg_rmap(oz->oz_rtg)->i_used_blocks;
+ __entry->allocated = oz->oz_allocated;
__entry->written = oz->oz_written;
- __entry->write_pointer = oz->oz_write_pointer;
__entry->rgbno = rgbno;
__entry->len = len;
),
- TP_printk("dev %d:%d rgno 0x%x used 0x%x written 0x%x wp 0x%x rgbno 0x%x len 0x%x",
+ TP_printk("dev %d:%d rgno 0x%x used 0x%x alloced 0x%x written 0x%x rgbno 0x%x len 0x%x",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->rgno,
__entry->used,
+ __entry->allocated,
__entry->written,
- __entry->write_pointer,
__entry->rgbno,
__entry->len)
);
@@ -778,7 +775,6 @@ DEFINE_BUF_EVENT(xfs_buf_iowait_done);
DEFINE_BUF_EVENT(xfs_buf_delwri_queue);
DEFINE_BUF_EVENT(xfs_buf_delwri_queued);
DEFINE_BUF_EVENT(xfs_buf_delwri_split);
-DEFINE_BUF_EVENT(xfs_buf_delwri_pushbuf);
DEFINE_BUF_EVENT(xfs_buf_get_uncached);
DEFINE_BUF_EVENT(xfs_buf_item_relse);
DEFINE_BUF_EVENT(xfs_buf_iodone_async);
@@ -1083,7 +1079,9 @@ DEFINE_INODE_EVENT(xfs_get_acl);
#endif
DEFINE_INODE_EVENT(xfs_vm_bmap);
DEFINE_INODE_EVENT(xfs_file_ioctl);
+#ifdef CONFIG_COMPAT
DEFINE_INODE_EVENT(xfs_file_compat_ioctl);
+#endif
DEFINE_INODE_EVENT(xfs_ioctl_setattr);
DEFINE_INODE_EVENT(xfs_dir_fsync);
DEFINE_INODE_EVENT(xfs_file_fsync);
@@ -1147,6 +1145,7 @@ DECLARE_EVENT_CLASS(xfs_iref_class,
__field(xfs_ino_t, ino)
__field(int, count)
__field(int, pincount)
+ __field(unsigned long, iflags)
__field(unsigned long, caller_ip)
),
TP_fast_assign(
@@ -1154,13 +1153,15 @@ DECLARE_EVENT_CLASS(xfs_iref_class,
__entry->ino = ip->i_ino;
__entry->count = atomic_read(&VFS_I(ip)->i_count);
__entry->pincount = atomic_read(&ip->i_pincount);
+ __entry->iflags = ip->i_flags;
__entry->caller_ip = caller_ip;
),
- TP_printk("dev %d:%d ino 0x%llx count %d pincount %d caller %pS",
+ TP_printk("dev %d:%d ino 0x%llx count %d pincount %d iflags 0x%lx caller %pS",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->ino,
__entry->count,
__entry->pincount,
+ __entry->iflags,
(char *)__entry->caller_ip)
)
@@ -1250,6 +1251,8 @@ DEFINE_IREF_EVENT(xfs_irele);
DEFINE_IREF_EVENT(xfs_inode_pin);
DEFINE_IREF_EVENT(xfs_inode_unpin);
DEFINE_IREF_EVENT(xfs_inode_unpin_nowait);
+DEFINE_IREF_EVENT(xfs_inode_push_pinned);
+DEFINE_IREF_EVENT(xfs_inode_push_stale);
DECLARE_EVENT_CLASS(xfs_namespace_class,
TP_PROTO(struct xfs_inode *dp, const struct xfs_name *name),
@@ -1393,7 +1396,6 @@ DEFINE_EVENT(xfs_dquot_class, name, \
TP_ARGS(dqp))
DEFINE_DQUOT_EVENT(xfs_dqadjust);
DEFINE_DQUOT_EVENT(xfs_dqreclaim_want);
-DEFINE_DQUOT_EVENT(xfs_dqreclaim_dirty);
DEFINE_DQUOT_EVENT(xfs_dqreclaim_busy);
DEFINE_DQUOT_EVENT(xfs_dqreclaim_done);
DEFINE_DQUOT_EVENT(xfs_dqattach_found);
@@ -1598,7 +1600,6 @@ DEFINE_LOGGRANT_EVENT(xfs_log_ticket_ungrant);
DEFINE_LOGGRANT_EVENT(xfs_log_ticket_ungrant_sub);
DEFINE_LOGGRANT_EVENT(xfs_log_ticket_ungrant_exit);
DEFINE_LOGGRANT_EVENT(xfs_log_cil_wait);
-DEFINE_LOGGRANT_EVENT(xfs_log_cil_return);
DECLARE_EVENT_CLASS(xfs_log_item_class,
TP_PROTO(struct xfs_log_item *lip),
@@ -1654,6 +1655,8 @@ DEFINE_LOG_ITEM_EVENT(xfs_ail_flushing);
DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_mark);
DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_skip);
DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_unpin);
+DEFINE_LOG_ITEM_EVENT(xlog_ail_insert_abort);
+DEFINE_LOG_ITEM_EVENT(xfs_trans_free_abort);
DECLARE_EVENT_CLASS(xfs_ail_class,
TP_PROTO(struct xfs_log_item *lip, xfs_lsn_t old_lsn, xfs_lsn_t new_lsn),
@@ -1859,8 +1862,6 @@ DEFINE_SIMPLE_IO_EVENT(xfs_unwritten_convert);
DEFINE_SIMPLE_IO_EVENT(xfs_setfilesize);
DEFINE_SIMPLE_IO_EVENT(xfs_zero_eof);
DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write);
-DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_unwritten);
-DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_append);
DEFINE_SIMPLE_IO_EVENT(xfs_file_splice_read);
DEFINE_SIMPLE_IO_EVENT(xfs_zoned_map_blocks);
@@ -1893,31 +1894,6 @@ DEFINE_EVENT(xfs_itrunc_class, name, \
DEFINE_ITRUNC_EVENT(xfs_itruncate_extents_start);
DEFINE_ITRUNC_EVENT(xfs_itruncate_extents_end);
-TRACE_EVENT(xfs_pagecache_inval,
- TP_PROTO(struct xfs_inode *ip, xfs_off_t start, xfs_off_t finish),
- TP_ARGS(ip, start, finish),
- TP_STRUCT__entry(
- __field(dev_t, dev)
- __field(xfs_ino_t, ino)
- __field(xfs_fsize_t, size)
- __field(xfs_off_t, start)
- __field(xfs_off_t, finish)
- ),
- TP_fast_assign(
- __entry->dev = VFS_I(ip)->i_sb->s_dev;
- __entry->ino = ip->i_ino;
- __entry->size = ip->i_disk_size;
- __entry->start = start;
- __entry->finish = finish;
- ),
- TP_printk("dev %d:%d ino 0x%llx disize 0x%llx start 0x%llx finish 0x%llx",
- MAJOR(__entry->dev), MINOR(__entry->dev),
- __entry->ino,
- __entry->size,
- __entry->start,
- __entry->finish)
-);
-
TRACE_EVENT(xfs_bunmap,
TP_PROTO(struct xfs_inode *ip, xfs_fileoff_t fileoff, xfs_filblks_t len,
int flags, unsigned long caller_ip),
@@ -2263,14 +2239,12 @@ DEFINE_EVENT(xfs_alloc_class, name, \
DEFINE_ALLOC_EVENT(xfs_alloc_exact_done);
DEFINE_ALLOC_EVENT(xfs_alloc_exact_notfound);
DEFINE_ALLOC_EVENT(xfs_alloc_exact_error);
-DEFINE_ALLOC_EVENT(xfs_alloc_near_nominleft);
DEFINE_ALLOC_EVENT(xfs_alloc_near_first);
DEFINE_ALLOC_EVENT(xfs_alloc_cur);
DEFINE_ALLOC_EVENT(xfs_alloc_cur_right);
DEFINE_ALLOC_EVENT(xfs_alloc_cur_left);
DEFINE_ALLOC_EVENT(xfs_alloc_cur_lookup);
DEFINE_ALLOC_EVENT(xfs_alloc_cur_lookup_done);
-DEFINE_ALLOC_EVENT(xfs_alloc_near_error);
DEFINE_ALLOC_EVENT(xfs_alloc_near_noentry);
DEFINE_ALLOC_EVENT(xfs_alloc_near_busy);
DEFINE_ALLOC_EVENT(xfs_alloc_size_neither);
@@ -2465,13 +2439,8 @@ DEFINE_ATTR_EVENT(xfs_attr_leaf_toosmall);
DEFINE_ATTR_EVENT(xfs_attr_node_addname);
DEFINE_ATTR_EVENT(xfs_attr_node_get);
DEFINE_ATTR_EVENT(xfs_attr_node_replace);
-DEFINE_ATTR_EVENT(xfs_attr_node_removename);
-
-DEFINE_ATTR_EVENT(xfs_attr_fillstate);
-DEFINE_ATTR_EVENT(xfs_attr_refillstate);
DEFINE_ATTR_EVENT(xfs_attr_rmtval_get);
-DEFINE_ATTR_EVENT(xfs_attr_rmtval_set);
#define DEFINE_DA_EVENT(name) \
DEFINE_EVENT(xfs_da_class, name, \
@@ -2889,7 +2858,6 @@ DEFINE_EVENT(xfs_rtdiscard_class, name, \
TP_ARGS(mp, rtbno, len))
DEFINE_RTDISCARD_EVENT(xfs_discard_rtextent);
DEFINE_RTDISCARD_EVENT(xfs_discard_rttoosmall);
-DEFINE_RTDISCARD_EVENT(xfs_discard_rtrelax);
DECLARE_EVENT_CLASS(xfs_btree_cur_class,
TP_PROTO(struct xfs_btree_cur *cur, int level, struct xfs_buf *bp),
@@ -4206,36 +4174,6 @@ DEFINE_INODE_ERROR_EVENT(xfs_reflink_remap_extent_error);
DEFINE_INODE_IREC_EVENT(xfs_reflink_remap_extent_src);
DEFINE_INODE_IREC_EVENT(xfs_reflink_remap_extent_dest);
-/* dedupe tracepoints */
-DEFINE_DOUBLE_IO_EVENT(xfs_reflink_compare_extents);
-DEFINE_INODE_ERROR_EVENT(xfs_reflink_compare_extents_error);
-
-/* ioctl tracepoints */
-TRACE_EVENT(xfs_ioctl_clone,
- TP_PROTO(struct inode *src, struct inode *dest),
- TP_ARGS(src, dest),
- TP_STRUCT__entry(
- __field(dev_t, dev)
- __field(unsigned long, src_ino)
- __field(loff_t, src_isize)
- __field(unsigned long, dest_ino)
- __field(loff_t, dest_isize)
- ),
- TP_fast_assign(
- __entry->dev = src->i_sb->s_dev;
- __entry->src_ino = src->i_ino;
- __entry->src_isize = i_size_read(src);
- __entry->dest_ino = dest->i_ino;
- __entry->dest_isize = i_size_read(dest);
- ),
- TP_printk("dev %d:%d ino 0x%lx isize 0x%llx -> ino 0x%lx isize 0x%llx",
- MAJOR(__entry->dev), MINOR(__entry->dev),
- __entry->src_ino,
- __entry->src_isize,
- __entry->dest_ino,
- __entry->dest_isize)
-);
-
/* unshare tracepoints */
DEFINE_SIMPLE_IO_EVENT(xfs_reflink_unshare);
DEFINE_INODE_ERROR_EVENT(xfs_reflink_unshare_error);
@@ -4243,7 +4181,6 @@ DEFINE_INODE_ERROR_EVENT(xfs_reflink_unshare_error);
/* copy on write */
DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_around_shared);
DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_found);
-DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_enospc);
DEFINE_INODE_IREC_EVENT(xfs_reflink_convert_cow);
DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range);
@@ -5028,7 +4965,6 @@ DEFINE_ICLOG_EVENT(xlog_iclog_switch);
DEFINE_ICLOG_EVENT(xlog_iclog_sync);
DEFINE_ICLOG_EVENT(xlog_iclog_syncing);
DEFINE_ICLOG_EVENT(xlog_iclog_sync_done);
-DEFINE_ICLOG_EVENT(xlog_iclog_want_sync);
DEFINE_ICLOG_EVENT(xlog_iclog_wait_on);
DEFINE_ICLOG_EVENT(xlog_iclog_write);
@@ -5077,7 +5013,6 @@ DEFINE_DAS_STATE_EVENT(xfs_attr_sf_addname_return);
DEFINE_DAS_STATE_EVENT(xfs_attr_set_iter_return);
DEFINE_DAS_STATE_EVENT(xfs_attr_leaf_addname_return);
DEFINE_DAS_STATE_EVENT(xfs_attr_node_addname_return);
-DEFINE_DAS_STATE_EVENT(xfs_attr_remove_iter_return);
DEFINE_DAS_STATE_EVENT(xfs_attr_rmtval_alloc);
DEFINE_DAS_STATE_EVENT(xfs_attr_rmtval_remove_return);
DEFINE_DAS_STATE_EVENT(xfs_attr_defer_add);
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index c6657072361a..ece374d622b3 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -134,18 +134,14 @@ xfs_trans_dup(
}
/*
- * This is called to reserve free disk blocks and log space for the
- * given transaction. This must be done before allocating any resources
- * within the transaction.
+ * This is called to reserve free disk blocks and log space for the given
+ * transaction before allocating any resources within the transaction.
*
* This will return ENOSPC if there are not enough blocks available.
* It will sleep waiting for available log space.
- * The only valid value for the flags parameter is XFS_RES_LOG_PERM, which
- * is used by long running transactions. If any one of the reservations
- * fails then they will all be backed out.
*
- * This does not do quota reservations. That typically is done by the
- * caller afterwards.
+ * This does not do quota reservations. That typically is done by the caller
+ * afterwards.
*/
static int
xfs_trans_reserve(
@@ -158,10 +154,12 @@ xfs_trans_reserve(
int error = 0;
bool rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0;
+ ASSERT(resp->tr_logres > 0);
+
/*
- * Attempt to reserve the needed disk blocks by decrementing
- * the number needed from the number available. This will
- * fail if the count would go below zero.
+ * Attempt to reserve the needed disk blocks by decrementing the number
+ * needed from the number available. This will fail if the count would
+ * go below zero.
*/
if (blocks > 0) {
error = xfs_dec_fdblocks(mp, blocks, rsvd);
@@ -173,42 +171,20 @@ xfs_trans_reserve(
/*
* Reserve the log space needed for this transaction.
*/
- if (resp->tr_logres > 0) {
- bool permanent = false;
-
- ASSERT(tp->t_log_res == 0 ||
- tp->t_log_res == resp->tr_logres);
- ASSERT(tp->t_log_count == 0 ||
- tp->t_log_count == resp->tr_logcount);
-
- if (resp->tr_logflags & XFS_TRANS_PERM_LOG_RES) {
- tp->t_flags |= XFS_TRANS_PERM_LOG_RES;
- permanent = true;
- } else {
- ASSERT(tp->t_ticket == NULL);
- ASSERT(!(tp->t_flags & XFS_TRANS_PERM_LOG_RES));
- }
-
- if (tp->t_ticket != NULL) {
- ASSERT(resp->tr_logflags & XFS_TRANS_PERM_LOG_RES);
- error = xfs_log_regrant(mp, tp->t_ticket);
- } else {
- error = xfs_log_reserve(mp, resp->tr_logres,
- resp->tr_logcount,
- &tp->t_ticket, permanent);
- }
-
- if (error)
- goto undo_blocks;
+ if (resp->tr_logflags & XFS_TRANS_PERM_LOG_RES)
+ tp->t_flags |= XFS_TRANS_PERM_LOG_RES;
+ error = xfs_log_reserve(mp, resp->tr_logres, resp->tr_logcount,
+ &tp->t_ticket, (tp->t_flags & XFS_TRANS_PERM_LOG_RES));
+ if (error)
+ goto undo_blocks;
- tp->t_log_res = resp->tr_logres;
- tp->t_log_count = resp->tr_logcount;
- }
+ tp->t_log_res = resp->tr_logres;
+ tp->t_log_count = resp->tr_logcount;
/*
- * Attempt to reserve the needed realtime extents by decrementing
- * the number needed from the number available. This will
- * fail if the count would go below zero.
+ * Attempt to reserve the needed realtime extents by decrementing the
+ * number needed from the number available. This will fail if the
+ * count would go below zero.
*/
if (rtextents > 0) {
error = xfs_dec_frextents(mp, rtextents);
@@ -221,18 +197,11 @@ xfs_trans_reserve(
return 0;
- /*
- * Error cases jump to one of these labels to undo any
- * reservations which have already been performed.
- */
undo_log:
- if (resp->tr_logres > 0) {
- xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket);
- tp->t_ticket = NULL;
- tp->t_log_res = 0;
- tp->t_flags &= ~XFS_TRANS_PERM_LOG_RES;
- }
-
+ xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket);
+ tp->t_ticket = NULL;
+ tp->t_log_res = 0;
+ tp->t_flags &= ~XFS_TRANS_PERM_LOG_RES;
undo_blocks:
if (blocks > 0) {
xfs_add_fdblocks(mp, blocks);
@@ -241,6 +210,28 @@ undo_blocks:
return error;
}
+static struct xfs_trans *
+__xfs_trans_alloc(
+ struct xfs_mount *mp,
+ uint flags)
+{
+ struct xfs_trans *tp;
+
+ ASSERT(!(flags & XFS_TRANS_RES_FDBLKS) || xfs_has_lazysbcount(mp));
+
+ tp = kmem_cache_zalloc(xfs_trans_cache, GFP_KERNEL | __GFP_NOFAIL);
+ if (!(flags & XFS_TRANS_NO_WRITECOUNT))
+ sb_start_intwrite(mp->m_super);
+ xfs_trans_set_context(tp);
+ tp->t_flags = flags;
+ tp->t_mountp = mp;
+ INIT_LIST_HEAD(&tp->t_items);
+ INIT_LIST_HEAD(&tp->t_busy);
+ INIT_LIST_HEAD(&tp->t_dfops);
+ tp->t_highest_agno = NULLAGNUMBER;
+ return tp;
+}
+
int
xfs_trans_alloc(
struct xfs_mount *mp,
@@ -254,33 +245,16 @@ xfs_trans_alloc(
bool want_retry = true;
int error;
+ ASSERT(resp->tr_logres > 0);
+
/*
* Allocate the handle before we do our freeze accounting and setting up
* GFP_NOFS allocation context so that we avoid lockdep false positives
* by doing GFP_KERNEL allocations inside sb_start_intwrite().
*/
retry:
- tp = kmem_cache_zalloc(xfs_trans_cache, GFP_KERNEL | __GFP_NOFAIL);
- if (!(flags & XFS_TRANS_NO_WRITECOUNT))
- sb_start_intwrite(mp->m_super);
- xfs_trans_set_context(tp);
-
- /*
- * Zero-reservation ("empty") transactions can't modify anything, so
- * they're allowed to run while we're frozen.
- */
- WARN_ON(resp->tr_logres > 0 &&
- mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
- ASSERT(!(flags & XFS_TRANS_RES_FDBLKS) ||
- xfs_has_lazysbcount(mp));
-
- tp->t_flags = flags;
- tp->t_mountp = mp;
- INIT_LIST_HEAD(&tp->t_items);
- INIT_LIST_HEAD(&tp->t_busy);
- INIT_LIST_HEAD(&tp->t_dfops);
- tp->t_highest_agno = NULLAGNUMBER;
-
+ WARN_ON(mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
+ tp = __xfs_trans_alloc(mp, flags);
error = xfs_trans_reserve(tp, resp, blocks, rtextents);
if (error == -ENOSPC && want_retry) {
xfs_trans_cancel(tp);
@@ -324,14 +298,11 @@ retry:
* where we can be grabbing buffers at the same time that freeze is trying to
* drain the buffer LRU list.
*/
-int
+struct xfs_trans *
xfs_trans_alloc_empty(
- struct xfs_mount *mp,
- struct xfs_trans **tpp)
+ struct xfs_mount *mp)
{
- struct xfs_trans_res resv = {0};
-
- return xfs_trans_alloc(mp, &resv, 0, 0, XFS_TRANS_NO_WRITECOUNT, tpp);
+ return __xfs_trans_alloc(mp, XFS_TRANS_NO_WRITECOUNT);
}
/*
@@ -742,8 +713,10 @@ xfs_trans_free_items(
list_for_each_entry_safe(lip, next, &tp->t_items, li_trans) {
xfs_trans_del_item(lip);
- if (abort)
+ if (abort) {
+ trace_xfs_trans_free_abort(lip);
set_bit(XFS_LI_ABORTED, &lip->li_flags);
+ }
if (lip->li_ops->iop_release)
lip->li_ops->iop_release(lip);
}
@@ -1024,51 +997,57 @@ xfs_trans_cancel(
}
/*
- * Roll from one trans in the sequence of PERMANENT transactions to
- * the next: permanent transactions are only flushed out when
- * committed with xfs_trans_commit(), but we still want as soon
- * as possible to let chunks of it go to the log. So we commit the
- * chunk we've been working on and get a new transaction to continue.
+ * Roll from one trans in the sequence of PERMANENT transactions to the next:
+ * permanent transactions are only flushed out when committed with
+ * xfs_trans_commit(), but we still want as soon as possible to let chunks of it
+ * go to the log. So we commit the chunk we've been working on and get a new
+ * transaction to continue.
*/
int
xfs_trans_roll(
struct xfs_trans **tpp)
{
- struct xfs_trans *trans = *tpp;
- struct xfs_trans_res tres;
+ struct xfs_trans *tp = *tpp;
+ unsigned int log_res = tp->t_log_res;
+ unsigned int log_count = tp->t_log_count;
int error;
- trace_xfs_trans_roll(trans, _RET_IP_);
+ trace_xfs_trans_roll(tp, _RET_IP_);
+
+ ASSERT(log_res > 0);
/*
* Copy the critical parameters from one trans to the next.
*/
- tres.tr_logres = trans->t_log_res;
- tres.tr_logcount = trans->t_log_count;
-
- *tpp = xfs_trans_dup(trans);
+ *tpp = xfs_trans_dup(tp);
/*
* Commit the current transaction.
- * If this commit failed, then it'd just unlock those items that
- * are not marked ihold. That also means that a filesystem shutdown
- * is in progress. The caller takes the responsibility to cancel
- * the duplicate transaction that gets returned.
+ *
+ * If this commit failed, then it'd just unlock those items that are not
+ * marked ihold. That also means that a filesystem shutdown is in
+ * progress. The caller takes the responsibility to cancel the
+ * duplicate transaction that gets returned.
*/
- error = __xfs_trans_commit(trans, true);
+ error = __xfs_trans_commit(tp, true);
if (error)
return error;
/*
* Reserve space in the log for the next transaction.
- * This also pushes items in the "AIL", the list of logged items,
- * out to disk if they are taking up space at the tail of the log
- * that we want to use. This requires that either nothing be locked
- * across this call, or that anything that is locked be logged in
- * the prior and the next transactions.
+ *
+ * This also pushes items in the AIL out to disk if they are taking up
+ * space at the tail of the log that we want to use. This requires that
+ * either nothing be locked across this call, or that anything that is
+ * locked be logged in the prior and the next transactions.
*/
- tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
- return xfs_trans_reserve(*tpp, &tres, 0, 0);
+ tp = *tpp;
+ error = xfs_log_regrant(tp->t_mountp, tp->t_ticket);
+ if (error)
+ return error;
+ tp->t_log_res = log_res;
+ tp->t_log_count = log_count;
+ return 0;
}
/*
@@ -1144,9 +1123,18 @@ xfs_trans_reserve_more(
unsigned int blocks,
unsigned int rtextents)
{
- struct xfs_trans_res resv = { };
-
- return xfs_trans_reserve(tp, &resv, blocks, rtextents);
+ bool rsvd = tp->t_flags & XFS_TRANS_RESERVE;
+
+ if (blocks && xfs_dec_fdblocks(tp->t_mountp, blocks, rsvd))
+ return -ENOSPC;
+ if (rtextents && xfs_dec_frextents(tp->t_mountp, rtextents)) {
+ if (blocks)
+ xfs_add_fdblocks(tp->t_mountp, blocks);
+ return -ENOSPC;
+ }
+ tp->t_blk_res += blocks;
+ tp->t_rtx_res += rtextents;
+ return 0;
}
/*
@@ -1161,14 +1149,13 @@ xfs_trans_reserve_more_inode(
unsigned int rblocks,
bool force_quota)
{
- struct xfs_trans_res resv = { };
struct xfs_mount *mp = ip->i_mount;
unsigned int rtx = xfs_extlen_to_rtxlen(mp, rblocks);
int error;
xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
- error = xfs_trans_reserve(tp, &resv, dblocks, rtx);
+ error = xfs_trans_reserve_more(tp, dblocks, rtx);
if (error)
return error;
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 2b366851e9a4..7fb860f645a3 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -15,7 +15,6 @@ struct xfs_efd_log_item;
struct xfs_efi_log_item;
struct xfs_inode;
struct xfs_item_ops;
-struct xfs_log_iovec;
struct xfs_mount;
struct xfs_trans;
struct xfs_trans_res;
@@ -168,8 +167,7 @@ int xfs_trans_alloc(struct xfs_mount *mp, struct xfs_trans_res *resp,
struct xfs_trans **tpp);
int xfs_trans_reserve_more(struct xfs_trans *tp,
unsigned int blocks, unsigned int rtextents);
-int xfs_trans_alloc_empty(struct xfs_mount *mp,
- struct xfs_trans **tpp);
+struct xfs_trans *xfs_trans_alloc_empty(struct xfs_mount *mp);
void xfs_trans_mod_sb(xfs_trans_t *, uint, int64_t);
int xfs_trans_get_buf_map(struct xfs_trans *tp, struct xfs_buftarg *target,
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 0f641a9091ec..ac5cecec9aa1 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -243,7 +243,7 @@ __xfs_xattr_put_listent(
offset = context->buffer + context->count;
memcpy(offset, prefix, prefix_len);
offset += prefix_len;
- strncpy(offset, (char *)name, namelen); /* real name */
+ memcpy(offset, (char *)name, namelen); /* real name */
offset += namelen;
*offset = '\0';
diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
index 80add26c0111..33f7eee521a8 100644
--- a/fs/xfs/xfs_zone_alloc.c
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -434,7 +434,7 @@ xfs_init_open_zone(
spin_lock_init(&oz->oz_alloc_lock);
atomic_set(&oz->oz_ref, 1);
oz->oz_rtg = rtg;
- oz->oz_write_pointer = write_pointer;
+ oz->oz_allocated = write_pointer;
oz->oz_written = write_pointer;
oz->oz_write_hint = write_hint;
oz->oz_is_gc = is_gc;
@@ -569,7 +569,7 @@ xfs_try_use_zone(
struct xfs_open_zone *oz,
bool lowspace)
{
- if (oz->oz_write_pointer == rtg_blocks(oz->oz_rtg))
+ if (oz->oz_allocated == rtg_blocks(oz->oz_rtg))
return false;
if (!lowspace && !xfs_good_hint_match(oz, file_hint))
return false;
@@ -654,13 +654,6 @@ static inline bool xfs_zoned_pack_tight(struct xfs_inode *ip)
!(ip->i_diflags & XFS_DIFLAG_APPEND);
}
-/*
- * Pick a new zone for writes.
- *
- * If we aren't using up our budget of open zones just open a new one from the
- * freelist. Else try to find one that matches the expected data lifetime. If
- * we don't find one that is good pick any zone that is available.
- */
static struct xfs_open_zone *
xfs_select_zone_nowait(
struct xfs_mount *mp,
@@ -688,7 +681,8 @@ xfs_select_zone_nowait(
goto out_unlock;
/*
- * See if we can open a new zone and use that.
+ * See if we can open a new zone and use that so that data for different
+ * files is mixed as little as possible.
*/
oz = xfs_try_open_zone(mp, write_hint);
if (oz)
@@ -727,7 +721,7 @@ xfs_select_zone(
for (;;) {
prepare_to_wait(&zi->zi_zone_wait, &wait, TASK_UNINTERRUPTIBLE);
oz = xfs_select_zone_nowait(mp, write_hint, pack_tight);
- if (oz)
+ if (oz || xfs_is_shutdown(mp))
break;
schedule();
}
@@ -744,25 +738,25 @@ xfs_zone_alloc_blocks(
{
struct xfs_rtgroup *rtg = oz->oz_rtg;
struct xfs_mount *mp = rtg_mount(rtg);
- xfs_rgblock_t rgbno;
+ xfs_rgblock_t allocated;
spin_lock(&oz->oz_alloc_lock);
count_fsb = min3(count_fsb, XFS_MAX_BMBT_EXTLEN,
- (xfs_filblks_t)rtg_blocks(rtg) - oz->oz_write_pointer);
+ (xfs_filblks_t)rtg_blocks(rtg) - oz->oz_allocated);
if (!count_fsb) {
spin_unlock(&oz->oz_alloc_lock);
return 0;
}
- rgbno = oz->oz_write_pointer;
- oz->oz_write_pointer += count_fsb;
+ allocated = oz->oz_allocated;
+ oz->oz_allocated += count_fsb;
spin_unlock(&oz->oz_alloc_lock);
- trace_xfs_zone_alloc_blocks(oz, rgbno, count_fsb);
+ trace_xfs_zone_alloc_blocks(oz, allocated, count_fsb);
*sector = xfs_gbno_to_daddr(&rtg->rtg_group, 0);
*is_seq = bdev_zone_is_seq(mp->m_rtdev_targp->bt_bdev, *sector);
if (!*is_seq)
- *sector += XFS_FSB_TO_BB(mp, rgbno);
+ *sector += XFS_FSB_TO_BB(mp, allocated);
return XFS_FSB_TO_B(mp, count_fsb);
}
@@ -777,26 +771,6 @@ xfs_mark_rtg_boundary(
ioend->io_flags |= IOMAP_IOEND_BOUNDARY;
}
-static void
-xfs_submit_zoned_bio(
- struct iomap_ioend *ioend,
- struct xfs_open_zone *oz,
- bool is_seq)
-{
- ioend->io_bio.bi_iter.bi_sector = ioend->io_sector;
- ioend->io_private = oz;
- atomic_inc(&oz->oz_ref); /* for xfs_zoned_end_io */
-
- if (is_seq) {
- ioend->io_bio.bi_opf &= ~REQ_OP_WRITE;
- ioend->io_bio.bi_opf |= REQ_OP_ZONE_APPEND;
- } else {
- xfs_mark_rtg_boundary(ioend);
- }
-
- submit_bio(&ioend->io_bio);
-}
-
/*
* Cache the last zone written to for an inode so that it is considered first
* for subsequent writes.
@@ -891,6 +865,26 @@ xfs_zone_cache_create_association(
xfs_mru_cache_insert(mp->m_zone_cache, ip->i_ino, &item->mru);
}
+static void
+xfs_submit_zoned_bio(
+ struct iomap_ioend *ioend,
+ struct xfs_open_zone *oz,
+ bool is_seq)
+{
+ ioend->io_bio.bi_iter.bi_sector = ioend->io_sector;
+ ioend->io_private = oz;
+ atomic_inc(&oz->oz_ref); /* for xfs_zoned_end_io */
+
+ if (is_seq) {
+ ioend->io_bio.bi_opf &= ~REQ_OP_WRITE;
+ ioend->io_bio.bi_opf |= REQ_OP_ZONE_APPEND;
+ } else {
+ xfs_mark_rtg_boundary(ioend);
+ }
+
+ submit_bio(&ioend->io_bio);
+}
+
void
xfs_zone_alloc_and_submit(
struct iomap_ioend *ioend,
@@ -983,7 +977,7 @@ xfs_zone_rgbno_is_valid(
lockdep_assert_held(&rtg_rmap(rtg)->i_lock);
if (rtg->rtg_open_zone)
- return rgbno < rtg->rtg_open_zone->oz_write_pointer;
+ return rgbno < rtg->rtg_open_zone->oz_allocated;
return !xa_get_mark(&rtg_mount(rtg)->m_groups[XG_TYPE_RTG].xa,
rtg_rgno(rtg), XFS_RTG_FREE);
}
@@ -1017,7 +1011,7 @@ xfs_init_zone(
{
struct xfs_mount *mp = rtg_mount(rtg);
struct xfs_zone_info *zi = mp->m_zone_info;
- uint64_t used = rtg_rmap(rtg)->i_used_blocks;
+ uint32_t used = rtg_rmap(rtg)->i_used_blocks;
xfs_rgblock_t write_pointer, highest_rgbno;
int error;
@@ -1114,24 +1108,27 @@ xfs_get_zone_info_cb(
}
/*
- * Calculate the max open zone limit based on the of number of
- * backing zones available
+ * Calculate the max open zone limit based on the of number of backing zones
+ * available.
*/
static inline uint32_t
xfs_max_open_zones(
struct xfs_mount *mp)
{
unsigned int max_open, max_open_data_zones;
+
/*
- * We need two zones for every open data zone,
- * one in reserve as we don't reclaim open zones. One data zone
- * and its spare is included in XFS_MIN_ZONES.
+ * We need two zones for every open data zone, one in reserve as we
+ * don't reclaim open zones. One data zone and its spare is included
+ * in XFS_MIN_ZONES to support at least one user data writer.
*/
max_open_data_zones = (mp->m_sb.sb_rgcount - XFS_MIN_ZONES) / 2 + 1;
max_open = max_open_data_zones + XFS_OPEN_GC_ZONES;
/*
- * Cap the max open limit to 1/4 of available space
+ * Cap the max open limit to 1/4 of available space. Without this we'd
+ * run out of easy reclaim targets too quickly and storage devices don't
+ * handle huge numbers of concurrent write streams overly well.
*/
max_open = min(max_open, mp->m_sb.sb_rgcount / 4);
diff --git a/fs/xfs/xfs_zone_alloc.h b/fs/xfs/xfs_zone_alloc.h
index ecf39106704c..4db02816d0fd 100644
--- a/fs/xfs/xfs_zone_alloc.h
+++ b/fs/xfs/xfs_zone_alloc.h
@@ -23,9 +23,9 @@ struct xfs_zone_alloc_ctx {
*/
#define XFS_ZR_RESERVED (1U << 2)
-int xfs_zoned_space_reserve(struct xfs_inode *ip, xfs_filblks_t count_fsb,
+int xfs_zoned_space_reserve(struct xfs_mount *mp, xfs_filblks_t count_fsb,
unsigned int flags, struct xfs_zone_alloc_ctx *ac);
-void xfs_zoned_space_unreserve(struct xfs_inode *ip,
+void xfs_zoned_space_unreserve(struct xfs_mount *mp,
struct xfs_zone_alloc_ctx *ac);
void xfs_zoned_add_available(struct xfs_mount *mp, xfs_filblks_t count_fsb);
diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c
index 9c00fc5baa30..064cd1a857a0 100644
--- a/fs/xfs/xfs_zone_gc.c
+++ b/fs/xfs/xfs_zone_gc.c
@@ -328,10 +328,7 @@ xfs_zone_gc_query(
iter->rec_idx = 0;
iter->rec_count = 0;
- error = xfs_trans_alloc_empty(mp, &tp);
- if (error)
- return error;
-
+ tp = xfs_trans_alloc_empty(mp);
xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP);
cur = xfs_rtrmapbt_init_cursor(tp, rtg);
error = xfs_rmap_query_range(cur, &ri_low, &ri_high,
@@ -533,8 +530,7 @@ xfs_zone_gc_steal_open(
spin_lock(&zi->zi_open_zones_lock);
list_for_each_entry(oz, &zi->zi_open_zones, oz_entry) {
- if (!found ||
- oz->oz_write_pointer < found->oz_write_pointer)
+ if (!found || oz->oz_allocated < found->oz_allocated)
found = oz;
}
@@ -584,7 +580,7 @@ xfs_zone_gc_ensure_target(
{
struct xfs_open_zone *oz = mp->m_zone_info->zi_open_gc_zone;
- if (!oz || oz->oz_write_pointer == rtg_blocks(oz->oz_rtg))
+ if (!oz || oz->oz_allocated == rtg_blocks(oz->oz_rtg))
return xfs_zone_gc_select_target(mp);
return oz;
}
@@ -605,7 +601,7 @@ xfs_zone_gc_space_available(
oz = xfs_zone_gc_ensure_target(data->mp);
if (!oz)
return false;
- return oz->oz_write_pointer < rtg_blocks(oz->oz_rtg) &&
+ return oz->oz_allocated < rtg_blocks(oz->oz_rtg) &&
xfs_zone_gc_scratch_available(data);
}
@@ -647,7 +643,7 @@ xfs_zone_gc_alloc_blocks(
*/
spin_lock(&mp->m_sb_lock);
*count_fsb = min(*count_fsb,
- rtg_blocks(oz->oz_rtg) - oz->oz_write_pointer);
+ rtg_blocks(oz->oz_rtg) - oz->oz_allocated);
*count_fsb = min3(*count_fsb,
mp->m_free[XC_FREE_RTEXTENTS].res_avail,
mp->m_free[XC_FREE_RTAVAILABLE].res_avail);
@@ -661,8 +657,8 @@ xfs_zone_gc_alloc_blocks(
*daddr = xfs_gbno_to_daddr(&oz->oz_rtg->rtg_group, 0);
*is_seq = bdev_zone_is_seq(mp->m_rtdev_targp->bt_bdev, *daddr);
if (!*is_seq)
- *daddr += XFS_FSB_TO_BB(mp, oz->oz_write_pointer);
- oz->oz_write_pointer += *count_fsb;
+ *daddr += XFS_FSB_TO_BB(mp, oz->oz_allocated);
+ oz->oz_allocated += *count_fsb;
atomic_inc(&oz->oz_ref);
return oz;
}
diff --git a/fs/xfs/xfs_zone_info.c b/fs/xfs/xfs_zone_info.c
index 733bcc2f8645..07e30c596975 100644
--- a/fs/xfs/xfs_zone_info.c
+++ b/fs/xfs/xfs_zone_info.c
@@ -32,7 +32,7 @@ xfs_show_open_zone(
{
seq_printf(m, "\t zone %d, wp %u, written %u, used %u, hint %s\n",
rtg_rgno(oz->oz_rtg),
- oz->oz_write_pointer, oz->oz_written,
+ oz->oz_allocated, oz->oz_written,
rtg_rmap(oz->oz_rtg)->i_used_blocks,
xfs_write_hint_to_str(oz->oz_write_hint));
}
diff --git a/fs/xfs/xfs_zone_priv.h b/fs/xfs/xfs_zone_priv.h
index ab696975a993..35e6de3d25ed 100644
--- a/fs/xfs/xfs_zone_priv.h
+++ b/fs/xfs/xfs_zone_priv.h
@@ -11,18 +11,18 @@ struct xfs_open_zone {
atomic_t oz_ref;
/*
- * oz_write_pointer is the write pointer at which space is handed out
- * for conventional zones, or simple the count of blocks handed out
- * so far for sequential write required zones and is protected by
- * oz_alloc_lock/
+ * oz_allocated is the amount of space already allocated out of the zone
+ * and is protected by oz_alloc_lock.
+ *
+ * For conventional zones it also is the offset of the next write.
*/
spinlock_t oz_alloc_lock;
- xfs_rgblock_t oz_write_pointer;
+ xfs_rgblock_t oz_allocated;
/*
- * oz_written is the number of blocks for which we've received a
- * write completion. oz_written must always be <= oz_write_pointer
- * and is protected by the ILOCK of the rmap inode.
+ * oz_written is the number of blocks for which we've received a write
+ * completion. oz_written must always be <= oz_allocated and is
+ * protected by the ILOCK of the rmap inode.
*/
xfs_rgblock_t oz_written;
diff --git a/fs/xfs/xfs_zone_space_resv.c b/fs/xfs/xfs_zone_space_resv.c
index 93c9a7721139..1313c55b8cbe 100644
--- a/fs/xfs/xfs_zone_space_resv.c
+++ b/fs/xfs/xfs_zone_space_resv.c
@@ -117,11 +117,10 @@ xfs_zoned_space_wait_error(
static int
xfs_zoned_reserve_available(
- struct xfs_inode *ip,
+ struct xfs_mount *mp,
xfs_filblks_t count_fsb,
unsigned int flags)
{
- struct xfs_mount *mp = ip->i_mount;
struct xfs_zone_info *zi = mp->m_zone_info;
struct xfs_zone_reservation reservation = {
.task = current,
@@ -198,11 +197,10 @@ xfs_zoned_reserve_available(
*/
static int
xfs_zoned_reserve_extents_greedy(
- struct xfs_inode *ip,
+ struct xfs_mount *mp,
xfs_filblks_t *count_fsb,
unsigned int flags)
{
- struct xfs_mount *mp = ip->i_mount;
struct xfs_zone_info *zi = mp->m_zone_info;
s64 len = *count_fsb;
int error = -ENOSPC;
@@ -220,12 +218,11 @@ xfs_zoned_reserve_extents_greedy(
int
xfs_zoned_space_reserve(
- struct xfs_inode *ip,
+ struct xfs_mount *mp,
xfs_filblks_t count_fsb,
unsigned int flags,
struct xfs_zone_alloc_ctx *ac)
{
- struct xfs_mount *mp = ip->i_mount;
int error;
ASSERT(ac->reserved_blocks == 0);
@@ -234,11 +231,11 @@ xfs_zoned_space_reserve(
error = xfs_dec_freecounter(mp, XC_FREE_RTEXTENTS, count_fsb,
flags & XFS_ZR_RESERVED);
if (error == -ENOSPC && (flags & XFS_ZR_GREEDY) && count_fsb > 1)
- error = xfs_zoned_reserve_extents_greedy(ip, &count_fsb, flags);
+ error = xfs_zoned_reserve_extents_greedy(mp, &count_fsb, flags);
if (error)
return error;
- error = xfs_zoned_reserve_available(ip, count_fsb, flags);
+ error = xfs_zoned_reserve_available(mp, count_fsb, flags);
if (error) {
xfs_add_freecounter(mp, XC_FREE_RTEXTENTS, count_fsb);
return error;
@@ -249,12 +246,10 @@ xfs_zoned_space_reserve(
void
xfs_zoned_space_unreserve(
- struct xfs_inode *ip,
+ struct xfs_mount *mp,
struct xfs_zone_alloc_ctx *ac)
{
if (ac->reserved_blocks > 0) {
- struct xfs_mount *mp = ip->i_mount;
-
xfs_zoned_add_available(mp, ac->reserved_blocks);
xfs_add_freecounter(mp, XC_FREE_RTEXTENTS, ac->reserved_blocks);
}