summaryrefslogtreecommitdiff
path: root/fs/xfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs')
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c7
-rw-r--r--fs/xfs/libxfs/xfs_btree.c2
-rw-r--r--fs/xfs/xfs_bmap_util.c2
-rw-r--r--fs/xfs/xfs_buf.c24
-rw-r--r--fs/xfs/xfs_buf.h1
-rw-r--r--fs/xfs/xfs_dir2_readdir.c15
-rw-r--r--fs/xfs/xfs_icache.c58
-rw-r--r--fs/xfs/xfs_icache.h8
-rw-r--r--fs/xfs/xfs_inode.h4
-rw-r--r--fs/xfs/xfs_ioctl.c5
-rw-r--r--fs/xfs/xfs_itable.c2
-rw-r--r--fs/xfs/xfs_log.c2
-rw-r--r--fs/xfs/xfs_mount.h1
-rw-r--r--fs/xfs/xfs_qm.c7
-rw-r--r--fs/xfs/xfs_qm_syscalls.c3
-rw-r--r--fs/xfs/xfs_super.c8
16 files changed, 119 insertions, 30 deletions
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index f1026e86dabc..51c85b6a0c34 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -2180,8 +2180,10 @@ xfs_bmap_add_extent_delay_real(
}
temp = xfs_bmap_worst_indlen(bma->ip, temp);
temp2 = xfs_bmap_worst_indlen(bma->ip, temp2);
- diff = (int)(temp + temp2 - startblockval(PREV.br_startblock) -
- (bma->cur ? bma->cur->bc_private.b.allocated : 0));
+ diff = (int)(temp + temp2 -
+ (startblockval(PREV.br_startblock) -
+ (bma->cur ?
+ bma->cur->bc_private.b.allocated : 0)));
if (diff > 0) {
error = xfs_mod_fdblocks(bma->ip->i_mount,
-((int64_t)diff), false);
@@ -2233,7 +2235,6 @@ xfs_bmap_add_extent_delay_real(
temp = da_new;
if (bma->cur)
temp += bma->cur->bc_private.b.allocated;
- ASSERT(temp <= da_old);
if (temp < da_old)
xfs_mod_fdblocks(bma->ip->i_mount,
(int64_t)(da_old - temp), false);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index c72283dd8d44..1c677b7c274b 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -4049,7 +4049,7 @@ xfs_btree_change_owner(
xfs_btree_readahead_ptr(cur, ptr, 1);
/* save for the next iteration of the loop */
- lptr = *ptr;
+ xfs_btree_copy_ptrs(cur, &lptr, ptr, 1);
}
/* for each buffer in the level */
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index a52bbd3abc7d..80b540c75512 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -656,7 +656,7 @@ xfs_getbmap(
* extents.
*/
if (map[i].br_startblock == DELAYSTARTBLOCK &&
- map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
+ map[i].br_startoff < XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
ASSERT((iflags & BMV_IF_DELALLOC) != 0);
if (map[i].br_startblock == HOLESTARTBLOCK &&
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 6e2b892b58ee..fb0eb697a621 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -979,6 +979,8 @@ void
xfs_buf_unlock(
struct xfs_buf *bp)
{
+ ASSERT(xfs_buf_islocked(bp));
+
XB_CLEAR_OWNER(bp);
up(&bp->b_sema);
@@ -1713,6 +1715,28 @@ error:
}
/*
+ * Cancel a delayed write list.
+ *
+ * Remove each buffer from the list, clear the delwri queue flag and drop the
+ * associated buffer reference.
+ */
+void
+xfs_buf_delwri_cancel(
+ struct list_head *list)
+{
+ struct xfs_buf *bp;
+
+ while (!list_empty(list)) {
+ bp = list_first_entry(list, struct xfs_buf, b_list);
+
+ xfs_buf_lock(bp);
+ bp->b_flags &= ~_XBF_DELWRI_Q;
+ list_del_init(&bp->b_list);
+ xfs_buf_relse(bp);
+ }
+}
+
+/*
* Add a buffer to the delayed write list.
*
* This queues a buffer for writeout if it hasn't already been. Note that
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 110cb85e04f3..102b77af00b6 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -303,6 +303,7 @@ extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
extern xfs_caddr_t xfs_buf_offset(xfs_buf_t *, size_t);
/* Delayed Write Buffer Routines */
+extern void xfs_buf_delwri_cancel(struct list_head *);
extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
extern int xfs_buf_delwri_submit(struct list_head *);
extern int xfs_buf_delwri_submit_nowait(struct list_head *);
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 098cd78fe708..21d43c33a2cc 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -403,6 +403,7 @@ xfs_dir2_leaf_readbuf(
/*
* Do we need more readahead?
+ * Each loop tries to process 1 full dir blk; last may be partial.
*/
blk_start_plug(&plug);
for (mip->ra_index = mip->ra_offset = i = 0;
@@ -413,7 +414,8 @@ xfs_dir2_leaf_readbuf(
* Read-ahead a contiguous directory block.
*/
if (i > mip->ra_current &&
- map[mip->ra_index].br_blockcount >= geo->fsbcount) {
+ (map[mip->ra_index].br_blockcount - mip->ra_offset) >=
+ geo->fsbcount) {
xfs_dir3_data_readahead(dp,
map[mip->ra_index].br_startoff + mip->ra_offset,
XFS_FSB_TO_DADDR(dp->i_mount,
@@ -434,14 +436,19 @@ xfs_dir2_leaf_readbuf(
}
/*
- * Advance offset through the mapping table.
+ * Advance offset through the mapping table, processing a full
+ * dir block even if it is fragmented into several extents.
+ * But stop if we have consumed all valid mappings, even if
+ * it's not yet a full directory block.
*/
- for (j = 0; j < geo->fsbcount; j += length ) {
+ for (j = 0;
+ j < geo->fsbcount && mip->ra_index < mip->map_valid;
+ j += length ) {
/*
* The rest of this extent but not more than a dir
* block.
*/
- length = min_t(int, geo->fsbcount,
+ length = min_t(int, geo->fsbcount - j,
map[mip->ra_index].br_blockcount -
mip->ra_offset);
mip->ra_offset += length;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 76a9f2783282..d5d5333afa81 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -210,14 +210,17 @@ xfs_iget_cache_hit(
error = inode_init_always(mp->m_super, inode);
if (error) {
+ bool wake;
/*
* Re-initializing the inode failed, and we are in deep
* trouble. Try to re-add it to the reclaim list.
*/
rcu_read_lock();
spin_lock(&ip->i_flags_lock);
-
+ wake = !!__xfs_iflags_test(ip, XFS_INEW);
ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM);
+ if (wake)
+ wake_up_bit(&ip->i_flags, __XFS_INEW_BIT);
ASSERT(ip->i_flags & XFS_IRECLAIMABLE);
trace_xfs_iget_reclaim_fail(ip);
goto out_error;
@@ -363,6 +366,22 @@ out_destroy:
return error;
}
+static void
+xfs_inew_wait(
+ struct xfs_inode *ip)
+{
+ wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_INEW_BIT);
+ DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_INEW_BIT);
+
+ do {
+ prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+ if (!xfs_iflags_test(ip, XFS_INEW))
+ break;
+ schedule();
+ } while (true);
+ finish_wait(wq, &wait.wait);
+}
+
/*
* Look up an inode by number in the given file system.
* The inode is looked up in the cache held in each AG.
@@ -465,9 +484,11 @@ out_error_or_again:
STATIC int
xfs_inode_ag_walk_grab(
- struct xfs_inode *ip)
+ struct xfs_inode *ip,
+ int flags)
{
struct inode *inode = VFS_I(ip);
+ bool newinos = !!(flags & XFS_AGITER_INEW_WAIT);
ASSERT(rcu_read_lock_held());
@@ -485,7 +506,8 @@ xfs_inode_ag_walk_grab(
goto out_unlock_noent;
/* avoid new or reclaimable inodes. Leave for reclaim code to flush */
- if (__xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
+ if ((!newinos && __xfs_iflags_test(ip, XFS_INEW)) ||
+ __xfs_iflags_test(ip, XFS_IRECLAIMABLE | XFS_IRECLAIM))
goto out_unlock_noent;
spin_unlock(&ip->i_flags_lock);
@@ -513,7 +535,8 @@ xfs_inode_ag_walk(
void *args),
int flags,
void *args,
- int tag)
+ int tag,
+ int iter_flags)
{
uint32_t first_index;
int last_error = 0;
@@ -555,7 +578,7 @@ restart:
for (i = 0; i < nr_found; i++) {
struct xfs_inode *ip = batch[i];
- if (done || xfs_inode_ag_walk_grab(ip))
+ if (done || xfs_inode_ag_walk_grab(ip, iter_flags))
batch[i] = NULL;
/*
@@ -583,6 +606,9 @@ restart:
for (i = 0; i < nr_found; i++) {
if (!batch[i])
continue;
+ if ((iter_flags & XFS_AGITER_INEW_WAIT) &&
+ xfs_iflags_test(batch[i], XFS_INEW))
+ xfs_inew_wait(batch[i]);
error = execute(batch[i], flags, args);
IRELE(batch[i]);
if (error == -EAGAIN) {
@@ -635,12 +661,13 @@ xfs_eofblocks_worker(
}
int
-xfs_inode_ag_iterator(
+xfs_inode_ag_iterator_flags(
struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip, int flags,
void *args),
int flags,
- void *args)
+ void *args,
+ int iter_flags)
{
struct xfs_perag *pag;
int error = 0;
@@ -650,7 +677,8 @@ xfs_inode_ag_iterator(
ag = 0;
while ((pag = xfs_perag_get(mp, ag))) {
ag = pag->pag_agno + 1;
- error = xfs_inode_ag_walk(mp, pag, execute, flags, args, -1);
+ error = xfs_inode_ag_walk(mp, pag, execute, flags, args, -1,
+ iter_flags);
xfs_perag_put(pag);
if (error) {
last_error = error;
@@ -662,6 +690,17 @@ xfs_inode_ag_iterator(
}
int
+xfs_inode_ag_iterator(
+ struct xfs_mount *mp,
+ int (*execute)(struct xfs_inode *ip, int flags,
+ void *args),
+ int flags,
+ void *args)
+{
+ return xfs_inode_ag_iterator_flags(mp, execute, flags, args, 0);
+}
+
+int
xfs_inode_ag_iterator_tag(
struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip, int flags,
@@ -678,7 +717,8 @@ xfs_inode_ag_iterator_tag(
ag = 0;
while ((pag = xfs_perag_get_tag(mp, ag, tag))) {
ag = pag->pag_agno + 1;
- error = xfs_inode_ag_walk(mp, pag, execute, flags, args, tag);
+ error = xfs_inode_ag_walk(mp, pag, execute, flags, args, tag,
+ 0);
xfs_perag_put(pag);
if (error) {
last_error = error;
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index 62f1f91c32cb..147a79212e63 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -48,6 +48,11 @@ struct xfs_eofblocks {
#define XFS_IGET_UNTRUSTED 0x2
#define XFS_IGET_DONTCACHE 0x4
+/*
+ * flags for AG inode iterator
+ */
+#define XFS_AGITER_INEW_WAIT 0x1 /* wait on new inodes */
+
int xfs_iget(struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino,
uint flags, uint lock_flags, xfs_inode_t **ipp);
@@ -72,6 +77,9 @@ void xfs_eofblocks_worker(struct work_struct *);
int xfs_inode_ag_iterator(struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip, int flags, void *args),
int flags, void *args);
+int xfs_inode_ag_iterator_flags(struct xfs_mount *mp,
+ int (*execute)(struct xfs_inode *ip, int flags, void *args),
+ int flags, void *args, int iter_flags);
int xfs_inode_ag_iterator_tag(struct xfs_mount *mp,
int (*execute)(struct xfs_inode *ip, int flags, void *args),
int flags, void *args, int tag);
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 8f22d20368d8..bc719acd602b 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -208,7 +208,8 @@ xfs_get_initial_prid(struct xfs_inode *dp)
#define XFS_IRECLAIM (1 << 0) /* started reclaiming this inode */
#define XFS_ISTALE (1 << 1) /* inode has been staled */
#define XFS_IRECLAIMABLE (1 << 2) /* inode can be reclaimed */
-#define XFS_INEW (1 << 3) /* inode has just been allocated */
+#define __XFS_INEW_BIT 3 /* inode has just been allocated */
+#define XFS_INEW (1 << __XFS_INEW_BIT)
#define XFS_ITRUNCATED (1 << 5) /* truncated down so flush-on-close */
#define XFS_IDIRTY_RELEASE (1 << 6) /* dirty release already seen */
#define __XFS_IFLOCK_BIT 7 /* inode is being flushed right now */
@@ -420,6 +421,7 @@ static inline void xfs_finish_inode_setup(struct xfs_inode *ip)
xfs_iflags_clear(ip, XFS_INEW);
barrier();
unlock_new_inode(VFS_I(ip));
+ wake_up_bit(&ip->i_flags, __XFS_INEW_BIT);
}
static inline void xfs_setup_existing_inode(struct xfs_inode *ip)
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 82e49109d0b6..e69a0899bc05 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1368,10 +1368,11 @@ xfs_ioc_getbmap(
unsigned int cmd,
void __user *arg)
{
- struct getbmapx bmx;
+ struct getbmapx bmx = { 0 };
int error;
- if (copy_from_user(&bmx, arg, sizeof(struct getbmapx)))
+ /* struct getbmap is a strict subset of struct getbmapx. */
+ if (copy_from_user(&bmx, arg, offsetof(struct getbmapx, bmv_iflags)))
return -EFAULT;
if (bmx.bmv_count < 2)
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 80429891dc9b..b5cab0d1831b 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -570,7 +570,7 @@ xfs_inumbers(
return error;
bcount = MIN(left, (int)(PAGE_SIZE / sizeof(*buffer)));
- buffer = kmem_alloc(bcount * sizeof(*buffer), KM_SLEEP);
+ buffer = kmem_zalloc(bcount * sizeof(*buffer), KM_SLEEP);
do {
struct xfs_inobt_rec_incore r;
int stat;
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index bcc7cfabb787..7ee735c0f490 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -1273,7 +1273,7 @@ void
xfs_log_work_queue(
struct xfs_mount *mp)
{
- queue_delayed_work(mp->m_log_workqueue, &mp->m_log->l_work,
+ queue_delayed_work(mp->m_sync_workqueue, &mp->m_log->l_work,
msecs_to_jiffies(xfs_syncd_centisecs * 10));
}
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 8c995a2ccb6f..9cccfd6f18c7 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -133,6 +133,7 @@ typedef struct xfs_mount {
struct workqueue_struct *m_reclaim_workqueue;
struct workqueue_struct *m_log_workqueue;
struct workqueue_struct *m_eofblocks_workqueue;
+ struct workqueue_struct *m_sync_workqueue;
/*
* Generation of the filesysyem layout. This is incremented by each
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 5538468c7f63..7d81032a645f 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1356,12 +1356,7 @@ xfs_qm_quotacheck(
mp->m_qflags |= flags;
error_return:
- while (!list_empty(&buffer_list)) {
- struct xfs_buf *bp =
- list_first_entry(&buffer_list, struct xfs_buf, b_list);
- list_del_init(&bp->b_list);
- xfs_buf_relse(bp);
- }
+ xfs_buf_delwri_cancel(&buffer_list);
if (error) {
xfs_warn(mp,
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 9a25c9275fb3..a3b3f5c689bb 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -766,5 +766,6 @@ xfs_qm_dqrele_all_inodes(
uint flags)
{
ASSERT(mp->m_quotainfo);
- xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags, NULL);
+ xfs_inode_ag_iterator_flags(mp, xfs_dqrele_inode, flags, NULL,
+ XFS_AGITER_INEW_WAIT);
}
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 2a517576f2bc..9ea51a71028e 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -853,8 +853,15 @@ xfs_init_mount_workqueues(
if (!mp->m_eofblocks_workqueue)
goto out_destroy_log;
+ mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s", WQ_FREEZABLE, 0,
+ mp->m_fsname);
+ if (!mp->m_sync_workqueue)
+ goto out_destroy_eofb;
+
return 0;
+out_destroy_eofb:
+ destroy_workqueue(mp->m_eofblocks_workqueue);
out_destroy_log:
destroy_workqueue(mp->m_log_workqueue);
out_destroy_reclaim:
@@ -875,6 +882,7 @@ STATIC void
xfs_destroy_mount_workqueues(
struct xfs_mount *mp)
{
+ destroy_workqueue(mp->m_sync_workqueue);
destroy_workqueue(mp->m_eofblocks_workqueue);
destroy_workqueue(mp->m_log_workqueue);
destroy_workqueue(mp->m_reclaim_workqueue);