summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--fs/xfs/libxfs/xfs_ag.c3
-rw-r--r--fs/xfs/libxfs/xfs_btree.c63
-rw-r--r--fs/xfs/libxfs/xfs_log_recover.h14
-rw-r--r--fs/xfs/xfs_buf_item_recover.c66
-rw-r--r--fs/xfs/xfs_inode.c2
-rw-r--r--fs/xfs/xfs_log_priv.h3
-rw-r--r--fs/xfs/xfs_log_recover.c34
-rw-r--r--fs/xfs/xfs_qm.c9
8 files changed, 140 insertions, 54 deletions
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 1e4ee042d52f..3e920cf1b454 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -173,7 +173,6 @@ __xfs_free_perag(
struct xfs_perag *pag = container_of(head, struct xfs_perag, rcu_head);
ASSERT(!delayed_work_pending(&pag->pag_blockgc_work));
- ASSERT(atomic_read(&pag->pag_ref) == 0);
kmem_free(pag);
}
@@ -192,7 +191,7 @@ xfs_free_perag(
pag = radix_tree_delete(&mp->m_perag_tree, agno);
spin_unlock(&mp->m_perag_lock);
ASSERT(pag);
- ASSERT(atomic_read(&pag->pag_ref) == 0);
+ XFS_IS_CORRUPT(pag->pag_mount, atomic_read(&pag->pag_ref) != 0);
cancel_delayed_work_sync(&pag->pag_blockgc_work);
xfs_iunlink_destroy(pag);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 2aa300f7461f..2eecc49fc1b2 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -51,16 +51,31 @@ xfs_btree_magic(
return magic;
}
-static xfs_failaddr_t
+/*
+ * These sibling pointer checks are optimised for null sibling pointers. This
+ * happens a lot, and we don't need to byte swap at runtime if the sibling
+ * pointer is NULL.
+ *
+ * These are explicitly marked at inline because the cost of calling them as
+ * functions instead of inlining them is about 36 bytes extra code per call site
+ * on x86-64. Yes, gcc-11 fails to inline them, and explicit inlining of these
+ * two sibling check functions reduces the compiled code size by over 300
+ * bytes.
+ */
+static inline xfs_failaddr_t
xfs_btree_check_lblock_siblings(
struct xfs_mount *mp,
struct xfs_btree_cur *cur,
int level,
xfs_fsblock_t fsb,
- xfs_fsblock_t sibling)
+ __be64 dsibling)
{
- if (sibling == NULLFSBLOCK)
+ xfs_fsblock_t sibling;
+
+ if (dsibling == cpu_to_be64(NULLFSBLOCK))
return NULL;
+
+ sibling = be64_to_cpu(dsibling);
if (sibling == fsb)
return __this_address;
if (level >= 0) {
@@ -74,17 +89,21 @@ xfs_btree_check_lblock_siblings(
return NULL;
}
-static xfs_failaddr_t
+static inline xfs_failaddr_t
xfs_btree_check_sblock_siblings(
struct xfs_mount *mp,
struct xfs_btree_cur *cur,
int level,
xfs_agnumber_t agno,
xfs_agblock_t agbno,
- xfs_agblock_t sibling)
+ __be32 dsibling)
{
- if (sibling == NULLAGBLOCK)
+ xfs_agblock_t sibling;
+
+ if (dsibling == cpu_to_be32(NULLAGBLOCK))
return NULL;
+
+ sibling = be32_to_cpu(dsibling);
if (sibling == agbno)
return __this_address;
if (level >= 0) {
@@ -136,10 +155,10 @@ __xfs_btree_check_lblock(
fsb = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
fa = xfs_btree_check_lblock_siblings(mp, cur, level, fsb,
- be64_to_cpu(block->bb_u.l.bb_leftsib));
+ block->bb_u.l.bb_leftsib);
if (!fa)
fa = xfs_btree_check_lblock_siblings(mp, cur, level, fsb,
- be64_to_cpu(block->bb_u.l.bb_rightsib));
+ block->bb_u.l.bb_rightsib);
return fa;
}
@@ -204,10 +223,10 @@ __xfs_btree_check_sblock(
}
fa = xfs_btree_check_sblock_siblings(mp, cur, level, agno, agbno,
- be32_to_cpu(block->bb_u.s.bb_leftsib));
+ block->bb_u.s.bb_leftsib);
if (!fa)
fa = xfs_btree_check_sblock_siblings(mp, cur, level, agno,
- agbno, be32_to_cpu(block->bb_u.s.bb_rightsib));
+ agbno, block->bb_u.s.bb_rightsib);
return fa;
}
@@ -426,8 +445,14 @@ xfs_btree_del_cursor(
break;
}
+ /*
+ * If we are doing a BMBT update, the number of unaccounted blocks
+ * allocated during this cursor life time should be zero. If it's not
+ * zero, then we should be shut down or on our way to shutdown due to
+ * cancelling a dirty transaction on error.
+ */
ASSERT(cur->bc_btnum != XFS_BTNUM_BMAP || cur->bc_ino.allocated == 0 ||
- xfs_is_shutdown(cur->bc_mp));
+ xfs_is_shutdown(cur->bc_mp) || error != 0);
if (unlikely(cur->bc_flags & XFS_BTREE_STAGING))
kmem_free(cur->bc_ops);
if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) && cur->bc_ag.pag)
@@ -3247,7 +3272,7 @@ xfs_btree_insrec(
struct xfs_btree_block *block; /* btree block */
struct xfs_buf *bp; /* buffer for block */
union xfs_btree_ptr nptr; /* new block ptr */
- struct xfs_btree_cur *ncur; /* new btree cursor */
+ struct xfs_btree_cur *ncur = NULL; /* new btree cursor */
union xfs_btree_key nkey; /* new block key */
union xfs_btree_key *lkey;
int optr; /* old key/record index */
@@ -3327,7 +3352,7 @@ xfs_btree_insrec(
#ifdef DEBUG
error = xfs_btree_check_block(cur, block, level, bp);
if (error)
- return error;
+ goto error0;
#endif
/*
@@ -3347,7 +3372,7 @@ xfs_btree_insrec(
for (i = numrecs - ptr; i >= 0; i--) {
error = xfs_btree_debug_check_ptr(cur, pp, i, level);
if (error)
- return error;
+ goto error0;
}
xfs_btree_shift_keys(cur, kp, 1, numrecs - ptr + 1);
@@ -3432,6 +3457,8 @@ xfs_btree_insrec(
return 0;
error0:
+ if (ncur)
+ xfs_btree_del_cursor(ncur, error);
return error;
}
@@ -4523,10 +4550,10 @@ xfs_btree_lblock_verify(
/* sibling pointer verification */
fsb = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
fa = xfs_btree_check_lblock_siblings(mp, NULL, -1, fsb,
- be64_to_cpu(block->bb_u.l.bb_leftsib));
+ block->bb_u.l.bb_leftsib);
if (!fa)
fa = xfs_btree_check_lblock_siblings(mp, NULL, -1, fsb,
- be64_to_cpu(block->bb_u.l.bb_rightsib));
+ block->bb_u.l.bb_rightsib);
return fa;
}
@@ -4580,10 +4607,10 @@ xfs_btree_sblock_verify(
agno = xfs_daddr_to_agno(mp, xfs_buf_daddr(bp));
agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp));
fa = xfs_btree_check_sblock_siblings(mp, NULL, -1, agno, agbno,
- be32_to_cpu(block->bb_u.s.bb_leftsib));
+ block->bb_u.s.bb_leftsib);
if (!fa)
fa = xfs_btree_check_sblock_siblings(mp, NULL, -1, agno, agbno,
- be32_to_cpu(block->bb_u.s.bb_rightsib));
+ block->bb_u.s.bb_rightsib);
return fa;
}
diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h
index 32e216255cb0..2420865f3007 100644
--- a/fs/xfs/libxfs/xfs_log_recover.h
+++ b/fs/xfs/libxfs/xfs_log_recover.h
@@ -110,12 +110,6 @@ struct xlog_recover {
#define ITEM_TYPE(i) (*(unsigned short *)(i)->ri_buf[0].i_addr)
-/*
- * This is the number of entries in the l_buf_cancel_table used during
- * recovery.
- */
-#define XLOG_BC_TABLE_SIZE 64
-
#define XLOG_RECOVER_CRCPASS 0
#define XLOG_RECOVER_PASS1 1
#define XLOG_RECOVER_PASS2 2
@@ -128,5 +122,13 @@ int xlog_recover_iget(struct xfs_mount *mp, xfs_ino_t ino,
struct xfs_inode **ipp);
void xlog_recover_release_intent(struct xlog *log, unsigned short intent_type,
uint64_t intent_id);
+int xlog_alloc_buf_cancel_table(struct xlog *log);
+void xlog_free_buf_cancel_table(struct xlog *log);
+
+#ifdef DEBUG
+void xlog_check_buf_cancel_table(struct xlog *log);
+#else
+#define xlog_check_buf_cancel_table(log) do { } while (0)
+#endif
#endif /* __XFS_LOG_RECOVER_H__ */
diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c
index e484251dc9c8..ffa94102094d 100644
--- a/fs/xfs/xfs_buf_item_recover.c
+++ b/fs/xfs/xfs_buf_item_recover.c
@@ -24,6 +24,15 @@
#include "xfs_quota.h"
/*
+ * This is the number of entries in the l_buf_cancel_table used during
+ * recovery.
+ */
+#define XLOG_BC_TABLE_SIZE 64
+
+#define XLOG_BUF_CANCEL_BUCKET(log, blkno) \
+ ((log)->l_buf_cancel_table + ((uint64_t)blkno % XLOG_BC_TABLE_SIZE))
+
+/*
* This structure is used during recovery to record the buf log items which
* have been canceled and should not be replayed.
*/
@@ -993,3 +1002,60 @@ const struct xlog_recover_item_ops xlog_buf_item_ops = {
.commit_pass1 = xlog_recover_buf_commit_pass1,
.commit_pass2 = xlog_recover_buf_commit_pass2,
};
+
+#ifdef DEBUG
+void
+xlog_check_buf_cancel_table(
+ struct xlog *log)
+{
+ int i;
+
+ for (i = 0; i < XLOG_BC_TABLE_SIZE; i++)
+ ASSERT(list_empty(&log->l_buf_cancel_table[i]));
+}
+#endif
+
+int
+xlog_alloc_buf_cancel_table(
+ struct xlog *log)
+{
+ void *p;
+ int i;
+
+ ASSERT(log->l_buf_cancel_table == NULL);
+
+ p = kmalloc_array(XLOG_BC_TABLE_SIZE, sizeof(struct list_head),
+ GFP_KERNEL);
+ if (!p)
+ return -ENOMEM;
+
+ log->l_buf_cancel_table = p;
+ for (i = 0; i < XLOG_BC_TABLE_SIZE; i++)
+ INIT_LIST_HEAD(&log->l_buf_cancel_table[i]);
+
+ return 0;
+}
+
+void
+xlog_free_buf_cancel_table(
+ struct xlog *log)
+{
+ int i;
+
+ if (!log->l_buf_cancel_table)
+ return;
+
+ for (i = 0; i < XLOG_BC_TABLE_SIZE; i++) {
+ struct xfs_buf_cancel *bc;
+
+ while ((bc = list_first_entry_or_null(
+ &log->l_buf_cancel_table[i],
+ struct xfs_buf_cancel, bc_list))) {
+ list_del(&bc->bc_list);
+ kmem_free(bc);
+ }
+ }
+
+ kmem_free(log->l_buf_cancel_table);
+ log->l_buf_cancel_table = NULL;
+}
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index b2879870a17e..52d6f2c7d58b 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2622,7 +2622,7 @@ xfs_ifree(
*/
error = xfs_difree(tp, pag, ip->i_ino, &xic);
if (error)
- return error;
+ goto out;
error = xfs_iunlink_remove(tp, pag, ip);
if (error)
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 67fd9789e69a..686c01eb3661 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -428,9 +428,6 @@ struct xlog {
struct rw_semaphore l_incompat_users;
};
-#define XLOG_BUF_CANCEL_BUCKET(log, blkno) \
- ((log)->l_buf_cancel_table + ((uint64_t)blkno % XLOG_BC_TABLE_SIZE))
-
/*
* Bits for operational state
*/
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index b1980d7cbbee..5f7e4e6e33ce 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -3223,7 +3223,7 @@ xlog_do_log_recovery(
xfs_daddr_t head_blk,
xfs_daddr_t tail_blk)
{
- int error, i;
+ int error;
ASSERT(head_blk != tail_blk);
@@ -3231,37 +3231,25 @@ xlog_do_log_recovery(
* First do a pass to find all of the cancelled buf log items.
* Store them in the buf_cancel_table for use in the second pass.
*/
- log->l_buf_cancel_table = kmem_zalloc(XLOG_BC_TABLE_SIZE *
- sizeof(struct list_head),
- 0);
- for (i = 0; i < XLOG_BC_TABLE_SIZE; i++)
- INIT_LIST_HEAD(&log->l_buf_cancel_table[i]);
+ error = xlog_alloc_buf_cancel_table(log);
+ if (error)
+ return error;
error = xlog_do_recovery_pass(log, head_blk, tail_blk,
XLOG_RECOVER_PASS1, NULL);
- if (error != 0) {
- kmem_free(log->l_buf_cancel_table);
- log->l_buf_cancel_table = NULL;
- return error;
- }
+ if (error != 0)
+ goto out_cancel;
+
/*
* Then do a second pass to actually recover the items in the log.
* When it is complete free the table of buf cancel items.
*/
error = xlog_do_recovery_pass(log, head_blk, tail_blk,
XLOG_RECOVER_PASS2, NULL);
-#ifdef DEBUG
- if (!error) {
- int i;
-
- for (i = 0; i < XLOG_BC_TABLE_SIZE; i++)
- ASSERT(list_empty(&log->l_buf_cancel_table[i]));
- }
-#endif /* DEBUG */
-
- kmem_free(log->l_buf_cancel_table);
- log->l_buf_cancel_table = NULL;
-
+ if (!error)
+ xlog_check_buf_cancel_table(log);
+out_cancel:
+ xlog_free_buf_cancel_table(log);
return error;
}
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 8fc813cb6011..abf08bbf34a9 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1308,8 +1308,15 @@ xfs_qm_quotacheck(
error = xfs_iwalk_threaded(mp, 0, 0, xfs_qm_dqusage_adjust, 0, true,
NULL);
- if (error)
+ if (error) {
+ /*
+ * The inode walk may have partially populated the dquot
+ * caches. We must purge them before disabling quota and
+ * tearing down the quotainfo, or else the dquots will leak.
+ */
+ xfs_qm_dqpurge_all(mp);
goto error_return;
+ }
/*
* We've made all the changes that we need to make incore. Flush them
generated by cgit v1.2.3 (git 2.46.0) at 2025-07-24 13:36:26 +0000