From 8a00ebe4cfc90eda9ecb575ba97e22021cd8cf70 Mon Sep 17 00:00:00 2001
From: Dave Chinner <david@fromorbit.com>
Date: Fri, 13 Apr 2012 12:10:44 +0000
Subject: xfs: Ensure inode reclaim can run during quotacheck
Because the mount process can run a quotacheck and consume lots of
inodes, we need to be able to run periodic inode reclaim during the
mount process. This will prevent running the system out of memory
during quota checks.
This essentially reverts 2bcf6e97, but that is safe to do now that
the quota sync code that was causing problems during long quotacheck
executions is now gone.
The reclaim work is currently protected from running during the
unmount process by a check against MS_ACTIVE. Unfortunately, this
also means that the reclaim work cannot run during mount. The
unmount process should stop the reclaim cleanly before freeing
anything that the reclaim work depends on, so there is no need to
have this guard in place.
Also, the inode reclaim work is demand driven, so there is no need
to start it immediately during mount. It will be started the moment
an inode is queued for reclaim, so qutoacheck will trigger it just
fine.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>
---
fs/xfs/xfs_sync.c | 19 +++++++++----------
1 file changed, 9 insertions(+), 10 deletions(-)
(limited to 'fs/xfs/xfs_sync.c')
diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index 205ebcb34d9e..c318d8a4a631 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -460,7 +460,15 @@ xfs_sync_worker(
struct xfs_mount, m_sync_work);
int error;
- if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
+ /*
+ * We shouldn't write/force the log if we are in the mount/unmount
+ * process or on a read only filesystem. The workqueue still needs to be
+ * active in both cases, however, because it is used for inode reclaim
+ * during these times. hence use the MS_ACTIVE flag to avoid doing
+ * anything in these periods.
+ */
+ if (!(mp->m_super->s_flags & MS_ACTIVE) &&
+ !(mp->m_flags & XFS_MOUNT_RDONLY)) {
/* dgc: errors ignored here */
if (mp->m_super->s_frozen == SB_UNFROZEN &&
xfs_log_need_covered(mp))
@@ -488,14 +496,6 @@ xfs_syncd_queue_reclaim(
struct xfs_mount *mp)
{
- /*
- * We can have inodes enter reclaim after we've shut down the syncd
- * workqueue during unmount, so don't allow reclaim work to be queued
- * during unmount.
- */
- if (!(mp->m_super->s_flags & MS_ACTIVE))
- return;
-
rcu_read_lock();
if (radix_tree_tagged(&mp->m_perag_tree, XFS_ICI_RECLAIM_TAG)) {
queue_delayed_work(xfs_syncd_wq, &mp->m_reclaim_work,
@@ -564,7 +564,6 @@ xfs_syncd_init(
INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
xfs_syncd_queue_sync(mp);
- xfs_syncd_queue_reclaim(mp);
return 0;
}
--
cgit v1.2.3
From 32ce90a4b79155a155de2b284d8b69023e5e8fea Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@infradead.org>
Date: Mon, 23 Apr 2012 15:58:32 +1000
Subject: xfs: remove log item from AIL in xfs_iflush after a shutdown
If a filesystem has been forced shutdown we are never going to write inodes
to disk, which means the inode items will stay in the AIL until we free
the inode. Currently that is not a problem, but a pending change requires us
to empty the AIL before shutting down the filesystem. In that case leaving
the inode in the AIL is lethal. Make sure to remove the log item from the AIL
to allow emptying the AIL on shutdown filesystems.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>
---
fs/xfs/xfs_dquot.c | 3 +--
fs/xfs/xfs_iget.c | 18 +-----------------
fs/xfs/xfs_inode.c | 17 +++++++++--------
fs/xfs/xfs_sync.c | 1 +
4 files changed, 12 insertions(+), 27 deletions(-)
(limited to 'fs/xfs/xfs_sync.c')
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index e2f6f7c877db..786a61e1cccd 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -915,8 +915,7 @@ xfs_qm_dqflush(
spin_lock(&mp->m_ail->xa_lock);
if (lip->li_flags & XFS_LI_IN_AIL)
- xfs_trans_ail_delete(mp->m_ail, lip,
- SHUTDOWN_CORRUPT_INCORE);
+ xfs_trans_ail_delete(mp->m_ail, lip);
else
spin_unlock(&mp->m_ail->xa_lock);
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index bcc6c249b2c7..ab89ca7fdb95 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -123,23 +123,7 @@ xfs_inode_free(
xfs_idestroy_fork(ip, XFS_ATTR_FORK);
if (ip->i_itemp) {
- /*
- * Only if we are shutting down the fs will we see an
- * inode still in the AIL. If it is there, we should remove
- * it to prevent a use-after-free from occurring.
- */
- xfs_log_item_t *lip = &ip->i_itemp->ili_item;
- struct xfs_ail *ailp = lip->li_ailp;
-
- ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
- XFS_FORCED_SHUTDOWN(ip->i_mount));
- if (lip->li_flags & XFS_LI_IN_AIL) {
- spin_lock(&ailp->xa_lock);
- if (lip->li_flags & XFS_LI_IN_AIL)
- xfs_trans_ail_delete(ailp, lip);
- else
- spin_unlock(&ailp->xa_lock);
- }
+ ASSERT(!(ip->i_itemp->ili_item.li_flags & XFS_LI_IN_AIL));
xfs_inode_item_destroy(ip);
ip->i_itemp = NULL;
}
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index bc46c0a133d3..00f9c2f34e1f 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2397,7 +2397,6 @@ xfs_iflush(
xfs_inode_t *ip,
uint flags)
{
- xfs_inode_log_item_t *iip;
xfs_buf_t *bp;
xfs_dinode_t *dip;
xfs_mount_t *mp;
@@ -2410,7 +2409,6 @@ xfs_iflush(
ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
- iip = ip->i_itemp;
mp = ip->i_mount;
/*
@@ -2447,13 +2445,14 @@ xfs_iflush(
/*
* This may have been unpinned because the filesystem is shutting
* down forcibly. If that's the case we must not write this inode
- * to disk, because the log record didn't make it to disk!
+ * to disk, because the log record didn't make it to disk.
+ *
+ * We also have to remove the log item from the AIL in this case,
+ * as we wait for an empty AIL as part of the unmount process.
*/
if (XFS_FORCED_SHUTDOWN(mp)) {
- if (iip)
- iip->ili_fields = 0;
- xfs_ifunlock(ip);
- return XFS_ERROR(EIO);
+ error = XFS_ERROR(EIO);
+ goto abort_out;
}
/*
@@ -2500,11 +2499,13 @@ corrupt_out:
xfs_buf_relse(bp);
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
cluster_corrupt_out:
+ error = XFS_ERROR(EFSCORRUPTED);
+abort_out:
/*
* Unlocks the flush lock
*/
xfs_iflush_abort(ip);
- return XFS_ERROR(EFSCORRUPTED);
+ return error;
}
diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index c318d8a4a631..7648776e0a9e 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -782,6 +782,7 @@ restart:
goto reclaim;
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_iunpin_wait(ip);
+ xfs_iflush_abort(ip);
goto reclaim;
}
if (xfs_ipincount(ip)) {
--
cgit v1.2.3
From 211e4d434bd737be38aabad0247ce3da9964370e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@infradead.org>
Date: Mon, 23 Apr 2012 15:58:34 +1000
Subject: xfs: implement freezing by emptying the AIL
Now that we write back all metadata either synchronously or through
the AIL we can simply implement metadata freezing in terms of
emptying the AIL.
The implementation for this is fairly simply and straight-forward:
A new routine is added that asks the xfsaild to push the AIL to the
end and waits for it to complete and send a wakeup. The routine will
then loop if the AIL is not actually empty, and continue to do so
until the AIL is compeltely empty.
We keep an inode reclaim pass in the freeze process to avoid having
memory pressure have to reclaim inodes that require dirtying the
filesystem to be reclaimed after the freeze has completed. This
means we can also treat unmount in the exact same way as freeze.
As an upside we can now remove the radix tree based inode writeback
and xfs_unmountfs_writesb.
[ Dave Chinner:
- Cleaned up commit message.
- Added inode reclaim passes back into freeze.
- Cleaned up wakeup mechanism to avoid the use of a new
sleep counter variable. ]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>
---
fs/xfs/xfs_mount.c | 56 +++++++----------------------
fs/xfs/xfs_mount.h | 1 -
fs/xfs/xfs_sync.c | 96 +++++++------------------------------------------
fs/xfs/xfs_trans_ail.c | 36 +++++++++++++++----
fs/xfs/xfs_trans_priv.h | 2 ++
5 files changed, 56 insertions(+), 135 deletions(-)
(limited to 'fs/xfs/xfs_sync.c')
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 1ffead4b2296..385a3b11d3dd 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -22,6 +22,7 @@
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
+#include "xfs_trans_priv.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
@@ -1475,15 +1476,15 @@ xfs_unmountfs(
xfs_log_force(mp, XFS_LOG_SYNC);
/*
- * Do a delwri reclaim pass first so that as many dirty inodes are
- * queued up for IO as possible. Then flush the buffers before making
- * a synchronous path to catch all the remaining inodes are reclaimed.
- * This makes the reclaim process as quick as possible by avoiding
- * synchronous writeout and blocking on inodes already in the delwri
- * state as much as possible.
+ * Flush all pending changes from the AIL.
+ */
+ xfs_ail_push_all_sync(mp->m_ail);
+
+ /*
+ * And reclaim all inodes. At this point there should be no dirty
+ * inode, and none should be pinned or locked, but use synchronous
+ * reclaim just to be sure.
*/
- xfs_reclaim_inodes(mp, 0);
- xfs_flush_buftarg(mp->m_ddev_targp, 1);
xfs_reclaim_inodes(mp, SYNC_WAIT);
xfs_qm_unmount(mp);
@@ -1519,15 +1520,12 @@ xfs_unmountfs(
if (error)
xfs_warn(mp, "Unable to update superblock counters. "
"Freespace may not be correct on next mount.");
- xfs_unmountfs_writesb(mp);
/*
- * Make sure all buffers have been flushed and completed before
- * unmounting the log.
+ * At this point we might have modified the superblock again and thus
+ * added an item to the AIL, thus flush it again.
*/
- error = xfs_flush_buftarg(mp->m_ddev_targp, 1);
- if (error)
- xfs_warn(mp, "%d busy buffers during unmount.", error);
+ xfs_ail_push_all_sync(mp->m_ail);
xfs_wait_buftarg(mp->m_ddev_targp);
xfs_log_unmount_write(mp);
@@ -1588,36 +1586,6 @@ xfs_log_sbcount(xfs_mount_t *mp)
return error;
}
-int
-xfs_unmountfs_writesb(xfs_mount_t *mp)
-{
- xfs_buf_t *sbp;
- int error = 0;
-
- /*
- * skip superblock write if fs is read-only, or
- * if we are doing a forced umount.
- */
- if (!((mp->m_flags & XFS_MOUNT_RDONLY) ||
- XFS_FORCED_SHUTDOWN(mp))) {
-
- sbp = xfs_getsb(mp, 0);
-
- XFS_BUF_UNDONE(sbp);
- XFS_BUF_UNREAD(sbp);
- xfs_buf_delwri_dequeue(sbp);
- XFS_BUF_WRITE(sbp);
- XFS_BUF_UNASYNC(sbp);
- ASSERT(sbp->b_target == mp->m_ddev_targp);
- xfsbdstrat(mp, sbp);
- error = xfs_buf_iowait(sbp);
- if (error)
- xfs_buf_ioerror_alert(sbp, __func__);
- xfs_buf_relse(sbp);
- }
- return error;
-}
-
/*
* xfs_mod_sb() can be used to copy arbitrary changes to the
* in-core superblock into the superblock buffer to be logged.
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 9eba73887829..19fd5eda92b8 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -378,7 +378,6 @@ extern __uint64_t xfs_default_resblks(xfs_mount_t *mp);
extern int xfs_mountfs(xfs_mount_t *mp);
extern void xfs_unmountfs(xfs_mount_t *);
-extern int xfs_unmountfs_writesb(xfs_mount_t *);
extern int xfs_mod_incore_sb(xfs_mount_t *, xfs_sb_field_t, int64_t, int);
extern int xfs_mod_incore_sb_batch(xfs_mount_t *, xfs_mod_sb_t *,
uint, int);
diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index 7648776e0a9e..85d03e6a2677 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -241,45 +241,6 @@ xfs_sync_inode_data(
return error;
}
-STATIC int
-xfs_sync_inode_attr(
- struct xfs_inode *ip,
- struct xfs_perag *pag,
- int flags)
-{
- int error = 0;
-
- xfs_ilock(ip, XFS_ILOCK_SHARED);
- if (xfs_inode_clean(ip))
- goto out_unlock;
- if (!xfs_iflock_nowait(ip)) {
- if (!(flags & SYNC_WAIT))
- goto out_unlock;
- xfs_iflock(ip);
- }
-
- if (xfs_inode_clean(ip)) {
- xfs_ifunlock(ip);
- goto out_unlock;
- }
-
- error = xfs_iflush(ip, flags);
-
- /*
- * We don't want to try again on non-blocking flushes that can't run
- * again immediately. If an inode really must be written, then that's
- * what the SYNC_WAIT flag is for.
- */
- if (error == EAGAIN) {
- ASSERT(!(flags & SYNC_WAIT));
- error = 0;
- }
-
- out_unlock:
- xfs_iunlock(ip, XFS_ILOCK_SHARED);
- return error;
-}
-
/*
* Write out pagecache data for the whole filesystem.
*/
@@ -300,19 +261,6 @@ xfs_sync_data(
return 0;
}
-/*
- * Write out inode metadata (attributes) for the whole filesystem.
- */
-STATIC int
-xfs_sync_attr(
- struct xfs_mount *mp,
- int flags)
-{
- ASSERT((flags & ~SYNC_WAIT) == 0);
-
- return xfs_inode_ag_iterator(mp, xfs_sync_inode_attr, flags);
-}
-
STATIC int
xfs_sync_fsdata(
struct xfs_mount *mp)
@@ -350,7 +298,7 @@ xfs_sync_fsdata(
* First stage of freeze - no writers will make progress now we are here,
* so we flush delwri and delalloc buffers here, then wait for all I/O to
* complete. Data is frozen at that point. Metadata is not frozen,
- * transactions can still occur here so don't bother flushing the buftarg
+ * transactions can still occur here so don't bother emptying the AIL
* because it'll just get dirty again.
*/
int
@@ -379,33 +327,6 @@ xfs_quiesce_data(
return error ? error : error2;
}
-STATIC void
-xfs_quiesce_fs(
- struct xfs_mount *mp)
-{
- int count = 0, pincount;
-
- xfs_reclaim_inodes(mp, 0);
- xfs_flush_buftarg(mp->m_ddev_targp, 0);
-
- /*
- * This loop must run at least twice. The first instance of the loop
- * will flush most meta data but that will generate more meta data
- * (typically directory updates). Which then must be flushed and
- * logged before we can write the unmount record. We also so sync
- * reclaim of inodes to catch any that the above delwri flush skipped.
- */
- do {
- xfs_reclaim_inodes(mp, SYNC_WAIT);
- xfs_sync_attr(mp, SYNC_WAIT);
- pincount = xfs_flush_buftarg(mp->m_ddev_targp, 1);
- if (!pincount) {
- delay(50);
- count++;
- }
- } while (count < 2);
-}
-
/*
* Second stage of a quiesce. The data is already synced, now we have to take
* care of the metadata. New transactions are already blocked, so we need to
@@ -421,8 +342,12 @@ xfs_quiesce_attr(
while (atomic_read(&mp->m_active_trans) > 0)
delay(100);
- /* flush inodes and push all remaining buffers out to disk */
- xfs_quiesce_fs(mp);
+ /* reclaim inodes to do any IO before the freeze completes */
+ xfs_reclaim_inodes(mp, 0);
+ xfs_reclaim_inodes(mp, SYNC_WAIT);
+
+ /* flush all pending changes from the AIL */
+ xfs_ail_push_all_sync(mp->m_ail);
/*
* Just warn here till VFS can correctly support
@@ -436,7 +361,12 @@ xfs_quiesce_attr(
xfs_warn(mp, "xfs_attr_quiesce: failed to log sb changes. "
"Frozen image may not be consistent.");
xfs_log_unmount_write(mp);
- xfs_unmountfs_writesb(mp);
+
+ /*
+ * At this point we might have modified the superblock again and thus
+ * added an item to the AIL, thus flush it again.
+ */
+ xfs_ail_push_all_sync(mp->m_ail);
}
static void
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 77acc53f2f31..0425ca16738b 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -383,9 +383,8 @@ xfsaild_push(
spin_lock(&ailp->xa_lock);
}
- target = ailp->xa_target;
lip = xfs_trans_ail_cursor_first(ailp, &cur, ailp->xa_last_pushed_lsn);
- if (!lip || XFS_FORCED_SHUTDOWN(mp)) {
+ if (!lip) {
/*
* AIL is empty or our push has reached the end.
*/
@@ -408,6 +407,7 @@ xfsaild_push(
* lots of contention on the AIL lists.
*/
lsn = lip->li_lsn;
+ target = ailp->xa_target;
while ((XFS_LSN_CMP(lip->li_lsn, target) <= 0)) {
int lock_result;
/*
@@ -466,11 +466,6 @@ xfsaild_push(
}
spin_lock(&ailp->xa_lock);
- /* should we bother continuing? */
- if (XFS_FORCED_SHUTDOWN(mp))
- break;
- ASSERT(mp->m_log);
-
count++;
/*
@@ -610,6 +605,30 @@ xfs_ail_push_all(
xfs_ail_push(ailp, threshold_lsn);
}
+/*
+ * Push out all items in the AIL immediately and wait until the AIL is empty.
+ */
+void
+xfs_ail_push_all_sync(
+ struct xfs_ail *ailp)
+{
+ struct xfs_log_item *lip;
+ DEFINE_WAIT(wait);
+
+ spin_lock(&ailp->xa_lock);
+ while ((lip = xfs_ail_max(ailp)) != NULL) {
+ prepare_to_wait(&ailp->xa_empty, &wait, TASK_UNINTERRUPTIBLE);
+ ailp->xa_target = lip->li_lsn;
+ wake_up_process(ailp->xa_task);
+ spin_unlock(&ailp->xa_lock);
+ schedule();
+ spin_lock(&ailp->xa_lock);
+ }
+ spin_unlock(&ailp->xa_lock);
+
+ finish_wait(&ailp->xa_empty, &wait);
+}
+
/*
* xfs_trans_ail_update - bulk AIL insertion operation.
*
@@ -737,6 +756,8 @@ xfs_trans_ail_delete_bulk(
if (mlip_changed) {
if (!XFS_FORCED_SHUTDOWN(ailp->xa_mount))
xlog_assign_tail_lsn_locked(ailp->xa_mount);
+ if (list_empty(&ailp->xa_ail))
+ wake_up_all(&ailp->xa_empty);
spin_unlock(&ailp->xa_lock);
xfs_log_space_wake(ailp->xa_mount);
@@ -773,6 +794,7 @@ xfs_trans_ail_init(
INIT_LIST_HEAD(&ailp->xa_ail);
INIT_LIST_HEAD(&ailp->xa_cursors);
spin_lock_init(&ailp->xa_lock);
+ init_waitqueue_head(&ailp->xa_empty);
ailp->xa_task = kthread_run(xfsaild, ailp, "xfsaild/%s",
ailp->xa_mount->m_fsname);
diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
index 46a1ebd4a7a2..218304a8cdc7 100644
--- a/fs/xfs/xfs_trans_priv.h
+++ b/fs/xfs/xfs_trans_priv.h
@@ -71,6 +71,7 @@ struct xfs_ail {
spinlock_t xa_lock;
xfs_lsn_t xa_last_pushed_lsn;
int xa_log_flush;
+ wait_queue_head_t xa_empty;
};
/*
@@ -102,6 +103,7 @@ xfs_trans_ail_delete(
void xfs_ail_push(struct xfs_ail *, xfs_lsn_t);
void xfs_ail_push_all(struct xfs_ail *);
+void xfs_ail_push_all_sync(struct xfs_ail *);
struct xfs_log_item *xfs_ail_min(struct xfs_ail *ailp);
xfs_lsn_t xfs_ail_min_lsn(struct xfs_ail *ailp);
--
cgit v1.2.3
From 8a48088f6439249019b5e17f6391e710656879d9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@infradead.org>
Date: Mon, 23 Apr 2012 15:58:35 +1000
Subject: xfs: don't flush inodes from background inode reclaim
We already flush dirty inodes throug the AIL regularly, there is no reason
to have second thread compete with it and disturb the I/O pattern. We still
do write inodes when doing a synchronous reclaim from the shrinker or during
unmount for now.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>
---
fs/xfs/xfs_sync.c | 102 ++++++++++++++++++++++--------------------------------
1 file changed, 42 insertions(+), 60 deletions(-)
(limited to 'fs/xfs/xfs_sync.c')
diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index 85d03e6a2677..7b2bccc4d67b 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -631,11 +631,8 @@ xfs_reclaim_inode_grab(
}
/*
- * Inodes in different states need to be treated differently, and the return
- * value of xfs_iflush is not sufficient to get this right. The following table
- * lists the inode states and the reclaim actions necessary for non-blocking
- * reclaim:
- *
+ * Inodes in different states need to be treated differently. The following
+ * table lists the inode states and the reclaim actions necessary:
*
* inode state iflush ret required action
* --------------- ---------- ---------------
@@ -645,9 +642,8 @@ xfs_reclaim_inode_grab(
* stale, unpinned 0 reclaim
* clean, pinned(*) 0 requeue
* stale, pinned EAGAIN requeue
- * dirty, delwri ok 0 requeue
- * dirty, delwri blocked EAGAIN requeue
- * dirty, sync flush 0 reclaim
+ * dirty, async - requeue
+ * dirty, sync 0 reclaim
*
* (*) dgc: I don't think the clean, pinned state is possible but it gets
* handled anyway given the order of checks implemented.
@@ -658,26 +654,23 @@ xfs_reclaim_inode_grab(
*
* Also, because we get the flush lock first, we know that any inode that has
* been flushed delwri has had the flush completed by the time we check that
- * the inode is clean. The clean inode check needs to be done before flushing
- * the inode delwri otherwise we would loop forever requeuing clean inodes as
- * we cannot tell apart a successful delwri flush and a clean inode from the
- * return value of xfs_iflush().
+ * the inode is clean.
*
- * Note that because the inode is flushed delayed write by background
- * writeback, the flush lock may already be held here and waiting on it can
- * result in very long latencies. Hence for sync reclaims, where we wait on the
- * flush lock, the caller should push out delayed write inodes first before
- * trying to reclaim them to minimise the amount of time spent waiting. For
- * background relaim, we just requeue the inode for the next pass.
+ * Note that because the inode is flushed delayed write by AIL pushing, the
+ * flush lock may already be held here and waiting on it can result in very
+ * long latencies. Hence for sync reclaims, where we wait on the flush lock,
+ * the caller should push the AIL first before trying to reclaim inodes to
+ * minimise the amount of time spent waiting. For background relaim, we only
+ * bother to reclaim clean inodes anyway.
*
* Hence the order of actions after gaining the locks should be:
* bad => reclaim
* shutdown => unpin and reclaim
- * pinned, delwri => requeue
+ * pinned, async => requeue
* pinned, sync => unpin
* stale => reclaim
* clean => reclaim
- * dirty, delwri => flush and requeue
+ * dirty, async => requeue
* dirty, sync => flush, wait and reclaim
*/
STATIC int
@@ -716,10 +709,8 @@ restart:
goto reclaim;
}
if (xfs_ipincount(ip)) {
- if (!(sync_mode & SYNC_WAIT)) {
- xfs_ifunlock(ip);
- goto out;
- }
+ if (!(sync_mode & SYNC_WAIT))
+ goto out_ifunlock;
xfs_iunpin_wait(ip);
}
if (xfs_iflags_test(ip, XFS_ISTALE))
@@ -727,6 +718,13 @@ restart:
if (xfs_inode_clean(ip))
goto reclaim;
+ /*
+ * Never flush out dirty data during non-blocking reclaim, as it would
+ * just contend with AIL pushing trying to do the same job.
+ */
+ if (!(sync_mode & SYNC_WAIT))
+ goto out_ifunlock;
+
/*
* Now we have an inode that needs flushing.
*
@@ -745,42 +743,13 @@ restart:
* pass through will see the stale flag set on the inode.
*/
error = xfs_iflush(ip, SYNC_TRYLOCK | sync_mode);
- if (sync_mode & SYNC_WAIT) {
- if (error == EAGAIN) {
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- /* backoff longer than in xfs_ifree_cluster */
- delay(2);
- goto restart;
- }
- xfs_iflock(ip);
- goto reclaim;
- }
-
- /*
- * When we have to flush an inode but don't have SYNC_WAIT set, we
- * flush the inode out using a delwri buffer and wait for the next
- * call into reclaim to find it in a clean state instead of waiting for
- * it now. We also don't return errors here - if the error is transient
- * then the next reclaim pass will flush the inode, and if the error
- * is permanent then the next sync reclaim will reclaim the inode and
- * pass on the error.
- */
- if (error && error != EAGAIN && !XFS_FORCED_SHUTDOWN(ip->i_mount)) {
- xfs_warn(ip->i_mount,
- "inode 0x%llx background reclaim flush failed with %d",
- (long long)ip->i_ino, error);
+ if (error == EAGAIN) {
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ /* backoff longer than in xfs_ifree_cluster */
+ delay(2);
+ goto restart;
}
-out:
- xfs_iflags_clear(ip, XFS_IRECLAIM);
- xfs_iunlock(ip, XFS_ILOCK_EXCL);
- /*
- * We could return EAGAIN here to make reclaim rescan the inode tree in
- * a short while. However, this just burns CPU time scanning the tree
- * waiting for IO to complete and xfssyncd never goes back to the idle
- * state. Instead, return 0 to let the next scheduled background reclaim
- * attempt to reclaim the inode again.
- */
- return 0;
+ xfs_iflock(ip);
reclaim:
xfs_ifunlock(ip);
@@ -814,8 +783,21 @@ reclaim:
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_inode_free(ip);
-
return error;
+
+out_ifunlock:
+ xfs_ifunlock(ip);
+out:
+ xfs_iflags_clear(ip, XFS_IRECLAIM);
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ /*
+ * We could return EAGAIN here to make reclaim rescan the inode tree in
+ * a short while. However, this just burns CPU time scanning the tree
+ * waiting for IO to complete and xfssyncd never goes back to the idle
+ * state. Instead, return 0 to let the next scheduled background reclaim
+ * attempt to reclaim the inode again.
+ */
+ return 0;
}
/*
--
cgit v1.2.3
From 4c46819a8097a75d3b378c5e56d2bcf47bb7408d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@infradead.org>
Date: Mon, 23 Apr 2012 15:58:36 +1000
Subject: xfs: do not write the buffer from xfs_iflush
Instead of writing the buffer directly from inside xfs_iflush return it to
the caller and let the caller decide what to do with the buffer. Also
remove the pincount check in xfs_iflush that all non-blocking callers already
implement and the now unused flags parameter.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>
---
fs/xfs/xfs_inode.c | 54 +++++++++++++++----------------------------------
fs/xfs/xfs_inode.h | 2 +-
fs/xfs/xfs_inode_item.c | 17 +++++++++++++++-
fs/xfs/xfs_sync.c | 29 +++++++++++++-------------
4 files changed, 48 insertions(+), 54 deletions(-)
(limited to 'fs/xfs/xfs_sync.c')
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 00f9c2f34e1f..0fa987dea242 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2384,22 +2384,22 @@ cluster_corrupt_out:
}
/*
- * xfs_iflush() will write a modified inode's changes out to the
- * inode's on disk home. The caller must have the inode lock held
- * in at least shared mode and the inode flush completion must be
- * active as well. The inode lock will still be held upon return from
- * the call and the caller is free to unlock it.
- * The inode flush will be completed when the inode reaches the disk.
- * The flags indicate how the inode's buffer should be written out.
+ * Flush dirty inode metadata into the backing buffer.
+ *
+ * The caller must have the inode lock and the inode flush lock held. The
+ * inode lock will still be held upon return to the caller, and the inode
+ * flush lock will be released after the inode has reached the disk.
+ *
+ * The caller must write out the buffer returned in *bpp and release it.
*/
int
xfs_iflush(
- xfs_inode_t *ip,
- uint flags)
+ struct xfs_inode *ip,
+ struct xfs_buf **bpp)
{
- xfs_buf_t *bp;
- xfs_dinode_t *dip;
- xfs_mount_t *mp;
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_buf *bp;
+ struct xfs_dinode *dip;
int error;
XFS_STATS_INC(xs_iflush_count);
@@ -2409,24 +2409,8 @@ xfs_iflush(
ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
- mp = ip->i_mount;
+ *bpp = NULL;
- /*
- * We can't flush the inode until it is unpinned, so wait for it if we
- * are allowed to block. We know no one new can pin it, because we are
- * holding the inode lock shared and you need to hold it exclusively to
- * pin the inode.
- *
- * If we are not allowed to block, force the log out asynchronously so
- * that when we come back the inode will be unpinned. If other inodes
- * in the same cluster are dirty, they will probably write the inode
- * out for us if they occur after the log force completes.
- */
- if (!(flags & SYNC_WAIT) && xfs_ipincount(ip)) {
- xfs_iunpin(ip);
- xfs_ifunlock(ip);
- return EAGAIN;
- }
xfs_iunpin_wait(ip);
/*
@@ -2458,8 +2442,7 @@ xfs_iflush(
/*
* Get the buffer containing the on-disk inode.
*/
- error = xfs_itobp(mp, NULL, ip, &dip, &bp,
- (flags & SYNC_TRYLOCK) ? XBF_TRYLOCK : XBF_LOCK);
+ error = xfs_itobp(mp, NULL, ip, &dip, &bp, XBF_TRYLOCK);
if (error || !bp) {
xfs_ifunlock(ip);
return error;
@@ -2487,13 +2470,8 @@ xfs_iflush(
if (error)
goto cluster_corrupt_out;
- if (flags & SYNC_WAIT)
- error = xfs_bwrite(bp);
- else
- xfs_buf_delwri_queue(bp);
-
- xfs_buf_relse(bp);
- return error;
+ *bpp = bp;
+ return 0;
corrupt_out:
xfs_buf_relse(bp);
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 7fee3387e1c8..a2fa79ae410f 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -529,7 +529,7 @@ int xfs_iunlink(struct xfs_trans *, xfs_inode_t *);
void xfs_iext_realloc(xfs_inode_t *, int, int);
void xfs_iunpin_wait(xfs_inode_t *);
-int xfs_iflush(xfs_inode_t *, uint);
+int xfs_iflush(struct xfs_inode *, struct xfs_buf **);
void xfs_promote_inode(struct xfs_inode *);
void xfs_lock_inodes(xfs_inode_t **, int, uint);
void xfs_lock_two_inodes(xfs_inode_t *, xfs_inode_t *, uint);
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 05d924efceaf..d3601ab75dd3 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -506,6 +506,15 @@ xfs_inode_item_trylock(
if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED))
return XFS_ITEM_LOCKED;
+ /*
+ * Re-check the pincount now that we stabilized the value by
+ * taking the ilock.
+ */
+ if (xfs_ipincount(ip) > 0) {
+ xfs_iunlock(ip, XFS_ILOCK_SHARED);
+ return XFS_ITEM_PINNED;
+ }
+
if (!xfs_iflock_nowait(ip)) {
/*
* inode has already been flushed to the backing buffer,
@@ -666,6 +675,8 @@ xfs_inode_item_push(
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
+ struct xfs_buf *bp = NULL;
+ int error;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED));
ASSERT(xfs_isiflocked(ip));
@@ -689,7 +700,11 @@ xfs_inode_item_push(
* will pull the inode from the AIL, mark it clean and unlock the flush
* lock.
*/
- (void) xfs_iflush(ip, SYNC_TRYLOCK);
+ error = xfs_iflush(ip, &bp);
+ if (!error) {
+ xfs_buf_delwri_queue(bp);
+ xfs_buf_relse(bp);
+ }
xfs_iunlock(ip, XFS_ILOCK_SHARED);
}
diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index 7b2bccc4d67b..468c3c0a4f9f 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -648,10 +648,6 @@ xfs_reclaim_inode_grab(
* (*) dgc: I don't think the clean, pinned state is possible but it gets
* handled anyway given the order of checks implemented.
*
- * As can be seen from the table, the return value of xfs_iflush() is not
- * sufficient to correctly decide the reclaim action here. The checks in
- * xfs_iflush() might look like duplicates, but they are not.
- *
* Also, because we get the flush lock first, we know that any inode that has
* been flushed delwri has had the flush completed by the time we check that
* the inode is clean.
@@ -679,7 +675,8 @@ xfs_reclaim_inode(
struct xfs_perag *pag,
int sync_mode)
{
- int error;
+ struct xfs_buf *bp = NULL;
+ int error;
restart:
error = 0;
@@ -728,29 +725,33 @@ restart:
/*
* Now we have an inode that needs flushing.
*
- * We do a nonblocking flush here even if we are doing a SYNC_WAIT
- * reclaim as we can deadlock with inode cluster removal.
+ * Note that xfs_iflush will never block on the inode buffer lock, as
* xfs_ifree_cluster() can lock the inode buffer before it locks the
- * ip->i_lock, and we are doing the exact opposite here. As a result,
- * doing a blocking xfs_itobp() to get the cluster buffer will result
+ * ip->i_lock, and we are doing the exact opposite here. As a result,
+ * doing a blocking xfs_itobp() to get the cluster buffer would result
* in an ABBA deadlock with xfs_ifree_cluster().
*
* As xfs_ifree_cluser() must gather all inodes that are active in the
* cache to mark them stale, if we hit this case we don't actually want
* to do IO here - we want the inode marked stale so we can simply
- * reclaim it. Hence if we get an EAGAIN error on a SYNC_WAIT flush,
- * just unlock the inode, back off and try again. Hopefully the next
- * pass through will see the stale flag set on the inode.
+ * reclaim it. Hence if we get an EAGAIN error here, just unlock the
+ * inode, back off and try again. Hopefully the next pass through will
+ * see the stale flag set on the inode.
*/
- error = xfs_iflush(ip, SYNC_TRYLOCK | sync_mode);
+ error = xfs_iflush(ip, &bp);
if (error == EAGAIN) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
/* backoff longer than in xfs_ifree_cluster */
delay(2);
goto restart;
}
- xfs_iflock(ip);
+ if (!error) {
+ error = xfs_bwrite(bp);
+ xfs_buf_relse(bp);
+ }
+
+ xfs_iflock(ip);
reclaim:
xfs_ifunlock(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
--
cgit v1.2.3
From 43ff2122e6492bcc88b065c433453dce88223b30 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@infradead.org>
Date: Mon, 23 Apr 2012 15:58:39 +1000
Subject: xfs: on-stack delayed write buffer lists
Queue delwri buffers on a local on-stack list instead of a per-buftarg one,
and write back the buffers per-process instead of by waking up xfsbufd.
This is now easily doable given that we have very few places left that write
delwri buffers:
- log recovery:
Only done at mount time, and already forcing out the buffers
synchronously using xfs_flush_buftarg
- quotacheck:
Same story.
- dquot reclaim:
Writes out dirty dquots on the LRU under memory pressure. We might
want to look into doing more of this via xfsaild, but it's already
more optimal than the synchronous inode reclaim that writes each
buffer synchronously.
- xfsaild:
This is the main beneficiary of the change. By keeping a local list
of buffers to write we reduce latency of writing out buffers, and
more importably we can remove all the delwri list promotions which
were hitting the buffer cache hard under sustained metadata loads.
The implementation is very straight forward - xfs_buf_delwri_queue now gets
a new list_head pointer that it adds the delwri buffers to, and all callers
need to eventually submit the list using xfs_buf_delwi_submit or
xfs_buf_delwi_submit_nowait. Buffers that already are on a delwri list are
skipped in xfs_buf_delwri_queue, assuming they already are on another delwri
list. The biggest change to pass down the buffer list was done to the AIL
pushing. Now that we operate on buffers the trylock, push and pushbuf log
item methods are merged into a single push routine, which tries to lock the
item, and if possible add the buffer that needs writeback to the buffer list.
This leads to much simpler code than the previous split but requires the
individual IOP_PUSH instances to unlock and reacquire the AIL around calls
to blocking routines.
Given that xfsailds now also handle writing out buffers, the conditions for
log forcing and the sleep times needed some small changes. The most
important one is that we consider an AIL busy as long we still have buffers
to push, and the other one is that we do increment the pushed LSN for
buffers that are under flushing at this moment, but still count them towards
the stuck items for restart purposes. Without this we could hammer on stuck
items without ever forcing the log and not make progress under heavy random
delete workloads on fast flash storage devices.
[ Dave Chinner:
- rebase on previous patches.
- improved comments for XBF_DELWRI_Q handling
- fix XBF_ASYNC handling in queue submission (test 106 failure)
- rename delwri submit function buffer list parameters for clarity
- xfs_efd_item_push() should return XFS_ITEM_PINNED ]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>
---
fs/xfs/xfs_buf.c | 341 ++++++++++++++++++----------------------------
fs/xfs/xfs_buf.h | 28 +---
fs/xfs/xfs_buf_item.c | 96 ++++---------
fs/xfs/xfs_dquot.c | 33 -----
fs/xfs/xfs_dquot.h | 1 -
fs/xfs/xfs_dquot_item.c | 161 +++++-----------------
fs/xfs/xfs_extfree_item.c | 55 ++------
fs/xfs/xfs_inode.c | 25 +---
fs/xfs/xfs_inode.h | 1 -
fs/xfs/xfs_inode_item.c | 152 +++++----------------
fs/xfs/xfs_log_recover.c | 46 ++++---
fs/xfs/xfs_qm.c | 148 ++++++++++----------
fs/xfs/xfs_super.c | 16 ---
fs/xfs/xfs_sync.c | 18 ---
fs/xfs/xfs_trace.h | 7 +-
fs/xfs/xfs_trans.h | 18 +--
fs/xfs/xfs_trans_ail.c | 129 ++++++++----------
fs/xfs/xfs_trans_buf.c | 84 ++++--------
fs/xfs/xfs_trans_priv.h | 1 +
19 files changed, 442 insertions(+), 918 deletions(-)
(limited to 'fs/xfs/xfs_sync.c')
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 6819b5163e33..b82fc5c67fed 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -42,7 +42,6 @@
#include "xfs_trace.h"
static kmem_zone_t *xfs_buf_zone;
-STATIC int xfsbufd(void *);
static struct workqueue_struct *xfslogd_workqueue;
@@ -144,8 +143,17 @@ void
xfs_buf_stale(
struct xfs_buf *bp)
{
+ ASSERT(xfs_buf_islocked(bp));
+
bp->b_flags |= XBF_STALE;
- xfs_buf_delwri_dequeue(bp);
+
+ /*
+ * Clear the delwri status so that a delwri queue walker will not
+ * flush this buffer to disk now that it is stale. The delwri queue has
+ * a reference to the buffer, so this is safe to do.
+ */
+ bp->b_flags &= ~_XBF_DELWRI_Q;
+
atomic_set(&(bp)->b_lru_ref, 0);
if (!list_empty(&bp->b_lru)) {
struct xfs_buftarg *btp = bp->b_target;
@@ -592,10 +600,10 @@ _xfs_buf_read(
{
int status;
- ASSERT(!(flags & (XBF_DELWRI|XBF_WRITE)));
+ ASSERT(!(flags & XBF_WRITE));
ASSERT(bp->b_bn != XFS_BUF_DADDR_NULL);
- bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_DELWRI | XBF_READ_AHEAD);
+ bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD);
bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
status = xfs_buf_iorequest(bp);
@@ -855,7 +863,7 @@ xfs_buf_rele(
spin_unlock(&pag->pag_buf_lock);
} else {
xfs_buf_lru_del(bp);
- ASSERT(!(bp->b_flags & (XBF_DELWRI|_XBF_DELWRI_Q)));
+ ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
rb_erase(&bp->b_rbnode, &pag->pag_buf_tree);
spin_unlock(&pag->pag_buf_lock);
xfs_perag_put(pag);
@@ -915,13 +923,6 @@ xfs_buf_lock(
trace_xfs_buf_lock_done(bp, _RET_IP_);
}
-/*
- * Releases the lock on the buffer object.
- * If the buffer is marked delwri but is not queued, do so before we
- * unlock the buffer as we need to set flags correctly. We also need to
- * take a reference for the delwri queue because the unlocker is going to
- * drop their's and they don't know we just queued it.
- */
void
xfs_buf_unlock(
struct xfs_buf *bp)
@@ -1019,10 +1020,11 @@ xfs_bwrite(
{
int error;
+ ASSERT(xfs_buf_islocked(bp));
+
bp->b_flags |= XBF_WRITE;
- bp->b_flags &= ~(XBF_ASYNC | XBF_READ);
+ bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q);
- xfs_buf_delwri_dequeue(bp);
xfs_bdstrat_cb(bp);
error = xfs_buf_iowait(bp);
@@ -1254,7 +1256,7 @@ xfs_buf_iorequest(
{
trace_xfs_buf_iorequest(bp, _RET_IP_);
- ASSERT(!(bp->b_flags & XBF_DELWRI));
+ ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
if (bp->b_flags & XBF_WRITE)
xfs_buf_wait_unpin(bp);
@@ -1435,11 +1437,9 @@ xfs_free_buftarg(
{
unregister_shrinker(&btp->bt_shrinker);
- xfs_flush_buftarg(btp, 1);
if (mp->m_flags & XFS_MOUNT_BARRIER)
xfs_blkdev_issue_flush(btp);
- kthread_stop(btp->bt_task);
kmem_free(btp);
}
@@ -1491,20 +1491,6 @@ xfs_setsize_buftarg(
return xfs_setsize_buftarg_flags(btp, blocksize, sectorsize, 1);
}
-STATIC int
-xfs_alloc_delwri_queue(
- xfs_buftarg_t *btp,
- const char *fsname)
-{
- INIT_LIST_HEAD(&btp->bt_delwri_queue);
- spin_lock_init(&btp->bt_delwri_lock);
- btp->bt_flags = 0;
- btp->bt_task = kthread_run(xfsbufd, btp, "xfsbufd/%s", fsname);
- if (IS_ERR(btp->bt_task))
- return PTR_ERR(btp->bt_task);
- return 0;
-}
-
xfs_buftarg_t *
xfs_alloc_buftarg(
struct xfs_mount *mp,
@@ -1527,8 +1513,6 @@ xfs_alloc_buftarg(
spin_lock_init(&btp->bt_lru_lock);
if (xfs_setsize_buftarg_early(btp, bdev))
goto error;
- if (xfs_alloc_delwri_queue(btp, fsname))
- goto error;
btp->bt_shrinker.shrink = xfs_buftarg_shrink;
btp->bt_shrinker.seeks = DEFAULT_SEEKS;
register_shrinker(&btp->bt_shrinker);
@@ -1539,125 +1523,52 @@ error:
return NULL;
}
-
/*
- * Delayed write buffer handling
+ * Add a buffer to the delayed write list.
+ *
+ * This queues a buffer for writeout if it hasn't already been. Note that
+ * neither this routine nor the buffer list submission functions perform
+ * any internal synchronization. It is expected that the lists are thread-local
+ * to the callers.
+ *
+ * Returns true if we queued up the buffer, or false if it already had
+ * been on the buffer list.
*/
-void
+bool
xfs_buf_delwri_queue(
- xfs_buf_t *bp)
+ struct xfs_buf *bp,
+ struct list_head *list)
{
- struct xfs_buftarg *btp = bp->b_target;
-
- trace_xfs_buf_delwri_queue(bp, _RET_IP_);
-
+ ASSERT(xfs_buf_islocked(bp));
ASSERT(!(bp->b_flags & XBF_READ));
- spin_lock(&btp->bt_delwri_lock);
- if (!list_empty(&bp->b_list)) {
- /* if already in the queue, move it to the tail */
- ASSERT(bp->b_flags & _XBF_DELWRI_Q);
- list_move_tail(&bp->b_list, &btp->bt_delwri_queue);
- } else {
- /* start xfsbufd as it is about to have something to do */
- if (list_empty(&btp->bt_delwri_queue))
- wake_up_process(bp->b_target->bt_task);
-
- atomic_inc(&bp->b_hold);
- bp->b_flags |= XBF_DELWRI | _XBF_DELWRI_Q | XBF_ASYNC;
- list_add_tail(&bp->b_list, &btp->bt_delwri_queue);
- }
- bp->b_queuetime = jiffies;
- spin_unlock(&btp->bt_delwri_lock);
-}
-
-void
-xfs_buf_delwri_dequeue(
- xfs_buf_t *bp)
-{
- int dequeued = 0;
-
- spin_lock(&bp->b_target->bt_delwri_lock);
- if ((bp->b_flags & XBF_DELWRI) && !list_empty(&bp->b_list)) {
- ASSERT(bp->b_flags & _XBF_DELWRI_Q);
- list_del_init(&bp->b_list);
- dequeued = 1;
+ /*
+ * If the buffer is already marked delwri it already is queued up
+ * by someone else for imediate writeout. Just ignore it in that
+ * case.
+ */
+ if (bp->b_flags & _XBF_DELWRI_Q) {
+ trace_xfs_buf_delwri_queued(bp, _RET_IP_);
+ return false;
}
- bp->b_flags &= ~(XBF_DELWRI|_XBF_DELWRI_Q);
- spin_unlock(&bp->b_target->bt_delwri_lock);
-
- if (dequeued)
- xfs_buf_rele(bp);
-
- trace_xfs_buf_delwri_dequeue(bp, _RET_IP_);
-}
-/*
- * If a delwri buffer needs to be pushed before it has aged out, then promote
- * it to the head of the delwri queue so that it will be flushed on the next
- * xfsbufd run. We do this by resetting the queuetime of the buffer to be older
- * than the age currently needed to flush the buffer. Hence the next time the
- * xfsbufd sees it is guaranteed to be considered old enough to flush.
- */
-void
-xfs_buf_delwri_promote(
- struct xfs_buf *bp)
-{
- struct xfs_buftarg *btp = bp->b_target;
- long age = xfs_buf_age_centisecs * msecs_to_jiffies(10) + 1;
-
- ASSERT(bp->b_flags & XBF_DELWRI);
- ASSERT(bp->b_flags & _XBF_DELWRI_Q);
+ trace_xfs_buf_delwri_queue(bp, _RET_IP_);
/*
- * Check the buffer age before locking the delayed write queue as we
- * don't need to promote buffers that are already past the flush age.
+ * If a buffer gets written out synchronously or marked stale while it
+ * is on a delwri list we lazily remove it. To do this, the other party
+ * clears the _XBF_DELWRI_Q flag but otherwise leaves the buffer alone.
+ * It remains referenced and on the list. In a rare corner case it
+ * might get readded to a delwri list after the synchronous writeout, in
+ * which case we need just need to re-add the flag here.
*/
- if (bp->b_queuetime < jiffies - age)
- return;
- bp->b_queuetime = jiffies - age;
- spin_lock(&btp->bt_delwri_lock);
- list_move(&bp->b_list, &btp->bt_delwri_queue);
- spin_unlock(&btp->bt_delwri_lock);
-}
-
-/*
- * Move as many buffers as specified to the supplied list
- * idicating if we skipped any buffers to prevent deadlocks.
- */
-STATIC int
-xfs_buf_delwri_split(
- xfs_buftarg_t *target,
- struct list_head *list,
- unsigned long age)
-{
- xfs_buf_t *bp, *n;
- int skipped = 0;
- int force;
-
- force = test_and_clear_bit(XBT_FORCE_FLUSH, &target->bt_flags);
- INIT_LIST_HEAD(list);
- spin_lock(&target->bt_delwri_lock);
- list_for_each_entry_safe(bp, n, &target->bt_delwri_queue, b_list) {
- ASSERT(bp->b_flags & XBF_DELWRI);
-
- if (!xfs_buf_ispinned(bp) && xfs_buf_trylock(bp)) {
- if (!force &&
- time_before(jiffies, bp->b_queuetime + age)) {
- xfs_buf_unlock(bp);
- break;
- }
-
- bp->b_flags &= ~(XBF_DELWRI | _XBF_DELWRI_Q);
- bp->b_flags |= XBF_WRITE;
- list_move_tail(&bp->b_list, list);
- trace_xfs_buf_delwri_split(bp, _RET_IP_);
- } else
- skipped++;
+ bp->b_flags |= _XBF_DELWRI_Q;
+ if (list_empty(&bp->b_list)) {
+ atomic_inc(&bp->b_hold);
+ list_add_tail(&bp->b_list, list);
}
- spin_unlock(&target->bt_delwri_lock);
- return skipped;
+ return true;
}
/*
@@ -1683,99 +1594,109 @@ xfs_buf_cmp(
return 0;
}
-STATIC int
-xfsbufd(
- void *data)
+static int
+__xfs_buf_delwri_submit(
+ struct list_head *buffer_list,
+ struct list_head *io_list,
+ bool wait)
{
- xfs_buftarg_t *target = (xfs_buftarg_t *)data;
-
- current->flags |= PF_MEMALLOC;
-
- set_freezable();
+ struct blk_plug plug;
+ struct xfs_buf *bp, *n;
+ int pinned = 0;
+
+ list_for_each_entry_safe(bp, n, buffer_list, b_list) {
+ if (!wait) {
+ if (xfs_buf_ispinned(bp)) {
+ pinned++;
+ continue;
+ }
+ if (!xfs_buf_trylock(bp))
+ continue;
+ } else {
+ xfs_buf_lock(bp);
+ }
- do {
- long age = xfs_buf_age_centisecs * msecs_to_jiffies(10);
- long tout = xfs_buf_timer_centisecs * msecs_to_jiffies(10);
- struct list_head tmp;
- struct blk_plug plug;
+ /*
+ * Someone else might have written the buffer synchronously or
+ * marked it stale in the meantime. In that case only the
+ * _XBF_DELWRI_Q flag got cleared, and we have to drop the
+ * reference and remove it from the list here.
+ */
+ if (!(bp->b_flags & _XBF_DELWRI_Q)) {
+ list_del_init(&bp->b_list);
+ xfs_buf_relse(bp);
+ continue;
+ }
- if (unlikely(freezing(current)))
- try_to_freeze();
+ list_move_tail(&bp->b_list, io_list);
+ trace_xfs_buf_delwri_split(bp, _RET_IP_);
+ }
- /* sleep for a long time if there is nothing to do. */
- if (list_empty(&target->bt_delwri_queue))
- tout = MAX_SCHEDULE_TIMEOUT;
- schedule_timeout_interruptible(tout);
+ list_sort(NULL, io_list, xfs_buf_cmp);
- xfs_buf_delwri_split(target, &tmp, age);
- list_sort(NULL, &tmp, xfs_buf_cmp);
+ blk_start_plug(&plug);
+ list_for_each_entry_safe(bp, n, io_list, b_list) {
+ bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC);
+ bp->b_flags |= XBF_WRITE;
- blk_start_plug(&plug);
- while (!list_empty(&tmp)) {
- struct xfs_buf *bp;
- bp = list_first_entry(&tmp, struct xfs_buf, b_list);
+ if (!wait) {
+ bp->b_flags |= XBF_ASYNC;
list_del_init(&bp->b_list);
- xfs_bdstrat_cb(bp);
}
- blk_finish_plug(&plug);
- } while (!kthread_should_stop());
+ xfs_bdstrat_cb(bp);
+ }
+ blk_finish_plug(&plug);
- return 0;
+ return pinned;
}
/*
- * Go through all incore buffers, and release buffers if they belong to
- * the given device. This is used in filesystem error handling to
- * preserve the consistency of its metadata.
+ * Write out a buffer list asynchronously.
+ *
+ * This will take the @buffer_list, write all non-locked and non-pinned buffers
+ * out and not wait for I/O completion on any of the buffers. This interface
+ * is only safely useable for callers that can track I/O completion by higher
+ * level means, e.g. AIL pushing as the @buffer_list is consumed in this
+ * function.
*/
int
-xfs_flush_buftarg(
- xfs_buftarg_t *target,
- int wait)
+xfs_buf_delwri_submit_nowait(
+ struct list_head *buffer_list)
{
- xfs_buf_t *bp;
- int pincount = 0;
- LIST_HEAD(tmp_list);
- LIST_HEAD(wait_list);
- struct blk_plug plug;
+ LIST_HEAD (io_list);
+ return __xfs_buf_delwri_submit(buffer_list, &io_list, false);
+}
- flush_workqueue(xfslogd_workqueue);
+/*
+ * Write out a buffer list synchronously.
+ *
+ * This will take the @buffer_list, write all buffers out and wait for I/O
+ * completion on all of the buffers. @buffer_list is consumed by the function,
+ * so callers must have some other way of tracking buffers if they require such
+ * functionality.
+ */
+int
+xfs_buf_delwri_submit(
+ struct list_head *buffer_list)
+{
+ LIST_HEAD (io_list);
+ int error = 0, error2;
+ struct xfs_buf *bp;
- set_bit(XBT_FORCE_FLUSH, &target->bt_flags);
- pincount = xfs_buf_delwri_split(target, &tmp_list, 0);
+ __xfs_buf_delwri_submit(buffer_list, &io_list, true);
- /*
- * Dropped the delayed write list lock, now walk the temporary list.
- * All I/O is issued async and then if we need to wait for completion
- * we do that after issuing all the IO.
- */
- list_sort(NULL, &tmp_list, xfs_buf_cmp);
+ /* Wait for IO to complete. */
+ while (!list_empty(&io_list)) {
+ bp = list_first_entry(&io_list, struct xfs_buf, b_list);
- blk_start_plug(&plug);
- while (!list_empty(&tmp_list)) {
- bp = list_first_entry(&tmp_list, struct xfs_buf, b_list);
- ASSERT(target == bp->b_target);
list_del_init(&bp->b_list);
- if (wait) {
- bp->b_flags &= ~XBF_ASYNC;
- list_add(&bp->b_list, &wait_list);
- }
- xfs_bdstrat_cb(bp);
- }
- blk_finish_plug(&plug);
-
- if (wait) {
- /* Wait for IO to complete. */
- while (!list_empty(&wait_list)) {
- bp = list_first_entry(&wait_list, struct xfs_buf, b_list);
-
- list_del_init(&bp->b_list);
- xfs_buf_iowait(bp);
- xfs_buf_relse(bp);
- }
+ error2 = xfs_buf_iowait(bp);
+ xfs_buf_relse(bp);
+ if (!error)
+ error = error2;
}
- return pincount;
+ return error;
}
int __init
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 5bf3be45f543..7083cf44d95f 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -49,8 +49,7 @@ typedef enum {
#define XBF_MAPPED (1 << 3) /* buffer mapped (b_addr valid) */
#define XBF_ASYNC (1 << 4) /* initiator will not wait for completion */
#define XBF_DONE (1 << 5) /* all pages in the buffer uptodate */
-#define XBF_DELWRI (1 << 6) /* buffer has dirty pages */
-#define XBF_STALE (1 << 7) /* buffer has been staled, do not find it */
+#define XBF_STALE (1 << 6) /* buffer has been staled, do not find it */
/* I/O hints for the BIO layer */
#define XBF_SYNCIO (1 << 10)/* treat this buffer as synchronous I/O */
@@ -65,7 +64,7 @@ typedef enum {
/* flags used only internally */
#define _XBF_PAGES (1 << 20)/* backed by refcounted pages */
#define _XBF_KMEM (1 << 21)/* backed by heap memory */
-#define _XBF_DELWRI_Q (1 << 22)/* buffer on delwri queue */
+#define _XBF_DELWRI_Q (1 << 22)/* buffer on a delwri queue */
typedef unsigned int xfs_buf_flags_t;
@@ -76,7 +75,6 @@ typedef unsigned int xfs_buf_flags_t;
{ XBF_MAPPED, "MAPPED" }, \
{ XBF_ASYNC, "ASYNC" }, \
{ XBF_DONE, "DONE" }, \
- { XBF_DELWRI, "DELWRI" }, \
{ XBF_STALE, "STALE" }, \
{ XBF_SYNCIO, "SYNCIO" }, \
{ XBF_FUA, "FUA" }, \
@@ -88,10 +86,6 @@ typedef unsigned int xfs_buf_flags_t;
{ _XBF_KMEM, "KMEM" }, \
{ _XBF_DELWRI_Q, "DELWRI_Q" }
-typedef enum {
- XBT_FORCE_FLUSH = 0,
-} xfs_buftarg_flags_t;
-
typedef struct xfs_buftarg {
dev_t bt_dev;
struct block_device *bt_bdev;
@@ -101,12 +95,6 @@ typedef struct xfs_buftarg {
unsigned int bt_sshift;
size_t bt_smask;
- /* per device delwri queue */
- struct task_struct *bt_task;
- struct list_head bt_delwri_queue;
- spinlock_t bt_delwri_lock;
- unsigned long bt_flags;
-
/* LRU control structures */
struct shrinker bt_shrinker;
struct list_head bt_lru;
@@ -150,7 +138,6 @@ typedef struct xfs_buf {
struct xfs_trans *b_transp;
struct page **b_pages; /* array of page pointers */
struct page *b_page_array[XB_PAGES]; /* inline pages */
- unsigned long b_queuetime; /* time buffer was queued */
atomic_t b_pin_count; /* pin count */
atomic_t b_io_remaining; /* #outstanding I/O requests */
unsigned int b_page_count; /* size of page array */
@@ -220,24 +207,22 @@ static inline int xfs_buf_geterror(xfs_buf_t *bp)
extern xfs_caddr_t xfs_buf_offset(xfs_buf_t *, size_t);
/* Delayed Write Buffer Routines */
-extern void xfs_buf_delwri_queue(struct xfs_buf *);
-extern void xfs_buf_delwri_dequeue(struct xfs_buf *);
-extern void xfs_buf_delwri_promote(struct xfs_buf *);
+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 *);
/* Buffer Daemon Setup Routines */
extern int xfs_buf_init(void);
extern void xfs_buf_terminate(void);
#define XFS_BUF_ZEROFLAGS(bp) \
- ((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC|XBF_DELWRI| \
+ ((bp)->b_flags &= ~(XBF_READ|XBF_WRITE|XBF_ASYNC| \
XBF_SYNCIO|XBF_FUA|XBF_FLUSH))
void xfs_buf_stale(struct xfs_buf *bp);
#define XFS_BUF_UNSTALE(bp) ((bp)->b_flags &= ~XBF_STALE)
#define XFS_BUF_ISSTALE(bp) ((bp)->b_flags & XBF_STALE)
-#define XFS_BUF_ISDELAYWRITE(bp) ((bp)->b_flags & XBF_DELWRI)
-
#define XFS_BUF_DONE(bp) ((bp)->b_flags |= XBF_DONE)
#define XFS_BUF_UNDONE(bp) ((bp)->b_flags &= ~XBF_DONE)
#define XFS_BUF_ISDONE(bp) ((bp)->b_flags & XBF_DONE)
@@ -287,7 +272,6 @@ extern xfs_buftarg_t *xfs_alloc_buftarg(struct xfs_mount *,
extern void xfs_free_buftarg(struct xfs_mount *, struct xfs_buftarg *);
extern void xfs_wait_buftarg(xfs_buftarg_t *);
extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int, unsigned int);
-extern int xfs_flush_buftarg(xfs_buftarg_t *, int);
#define xfs_getsize_buftarg(buftarg) block_size((buftarg)->bt_bdev)
#define xfs_readonly_buftarg(buftarg) bdev_read_only((buftarg)->bt_bdev)
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 3a0bc38f1859..fb20f384b566 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -418,7 +418,6 @@ xfs_buf_item_unpin(
if (freed && stale) {
ASSERT(bip->bli_flags & XFS_BLI_STALE);
ASSERT(xfs_buf_islocked(bp));
- ASSERT(!(XFS_BUF_ISDELAYWRITE(bp)));
ASSERT(XFS_BUF_ISSTALE(bp));
ASSERT(bip->bli_format.blf_flags & XFS_BLF_CANCEL);
@@ -469,34 +468,28 @@ xfs_buf_item_unpin(
}
}
-/*
- * This is called to attempt to lock the buffer associated with this
- * buf log item. Don't sleep on the buffer lock. If we can't get
- * the lock right away, return 0. If we can get the lock, take a
- * reference to the buffer. If this is a delayed write buffer that
- * needs AIL help to be written back, invoke the pushbuf routine
- * rather than the normal success path.
- */
STATIC uint
-xfs_buf_item_trylock(
- struct xfs_log_item *lip)
+xfs_buf_item_push(
+ struct xfs_log_item *lip,
+ struct list_head *buffer_list)
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
struct xfs_buf *bp = bip->bli_buf;
+ uint rval = XFS_ITEM_SUCCESS;
if (xfs_buf_ispinned(bp))
return XFS_ITEM_PINNED;
if (!xfs_buf_trylock(bp))
return XFS_ITEM_LOCKED;
- /* take a reference to the buffer. */
- xfs_buf_hold(bp);
-
ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
- trace_xfs_buf_item_trylock(bip);
- if (XFS_BUF_ISDELAYWRITE(bp))
- return XFS_ITEM_PUSHBUF;
- return XFS_ITEM_SUCCESS;
+
+ trace_xfs_buf_item_push(bip);
+
+ if (!xfs_buf_delwri_queue(bp, buffer_list))
+ rval = XFS_ITEM_FLUSHING;
+ xfs_buf_unlock(bp);
+ return rval;
}
/*
@@ -609,48 +602,6 @@ xfs_buf_item_committed(
return lsn;
}
-/*
- * The buffer is locked, but is not a delayed write buffer.
- */
-STATIC void
-xfs_buf_item_push(
- struct xfs_log_item *lip)
-{
- struct xfs_buf_log_item *bip = BUF_ITEM(lip);
- struct xfs_buf *bp = bip->bli_buf;
-
- ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
- ASSERT(!XFS_BUF_ISDELAYWRITE(bp));
-
- trace_xfs_buf_item_push(bip);
-
- xfs_buf_delwri_queue(bp);
- xfs_buf_relse(bp);
-}
-
-/*
- * The buffer is locked and is a delayed write buffer. Promote the buffer
- * in the delayed write queue as the caller knows that they must invoke
- * the xfsbufd to get this buffer written. We have to unlock the buffer
- * to allow the xfsbufd to write it, too.
- */
-STATIC bool
-xfs_buf_item_pushbuf(
- struct xfs_log_item *lip)
-{
- struct xfs_buf_log_item *bip = BUF_ITEM(lip);
- struct xfs_buf *bp = bip->bli_buf;
-
- ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
- ASSERT(XFS_BUF_ISDELAYWRITE(bp));
-
- trace_xfs_buf_item_pushbuf(bip);
-
- xfs_buf_delwri_promote(bp);
- xfs_buf_relse(bp);
- return true;
-}
-
STATIC void
xfs_buf_item_committing(
struct xfs_log_item *lip,
@@ -666,11 +617,9 @@ static const struct xfs_item_ops xfs_buf_item_ops = {
.iop_format = xfs_buf_item_format,
.iop_pin = xfs_buf_item_pin,
.iop_unpin = xfs_buf_item_unpin,
- .iop_trylock = xfs_buf_item_trylock,
.iop_unlock = xfs_buf_item_unlock,
.iop_committed = xfs_buf_item_committed,
.iop_push = xfs_buf_item_push,
- .iop_pushbuf = xfs_buf_item_pushbuf,
.iop_committing = xfs_buf_item_committing
};
@@ -989,20 +938,27 @@ xfs_buf_iodone_callbacks(
* If the write was asynchronous then no one will be looking for the
* error. Clear the error state and write the buffer out again.
*
- * During sync or umount we'll write all pending buffers again
- * synchronous, which will catch these errors if they keep hanging
- * around.
+ * XXX: This helps against transient write errors, but we need to find
+ * a way to shut the filesystem down if the writes keep failing.
+ *
+ * In practice we'll shut the filesystem down soon as non-transient
+ * erorrs tend to affect the whole device and a failing log write
+ * will make us give up. But we really ought to do better here.
*/
if (XFS_BUF_ISASYNC(bp)) {
+ ASSERT(bp->b_iodone != NULL);
+
+ trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
+
xfs_buf_ioerror(bp, 0); /* errno of 0 unsets the flag */
if (!XFS_BUF_ISSTALE(bp)) {
- xfs_buf_delwri_queue(bp);
- XFS_BUF_DONE(bp);
+ bp->b_flags |= XBF_WRITE | XBF_ASYNC | XBF_DONE;
+ xfs_bdstrat_cb(bp);
+ } else {
+ xfs_buf_relse(bp);
}
- ASSERT(bp->b_iodone != NULL);
- trace_xfs_buf_item_iodone_async(bp, _RET_IP_);
- xfs_buf_relse(bp);
+
return;
}
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 53757d83e4f6..65b8aa37622e 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -1005,39 +1005,6 @@ xfs_dqlock2(
}
}
-/*
- * Give the buffer a little push if it is incore and
- * wait on the flush lock.
- */
-void
-xfs_dqflock_pushbuf_wait(
- xfs_dquot_t *dqp)
-{
- xfs_mount_t *mp = dqp->q_mount;
- xfs_buf_t *bp;
-
- /*
- * Check to see if the dquot has been flushed delayed
- * write. If so, grab its buffer and send it
- * out immediately. We'll be able to acquire
- * the flush lock when the I/O completes.
- */
- bp = xfs_incore(mp->m_ddev_targp, dqp->q_blkno,
- mp->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK);
- if (!bp)
- goto out_lock;
-
- if (XFS_BUF_ISDELAYWRITE(bp)) {
- if (xfs_buf_ispinned(bp))
- xfs_log_force(mp, 0);
- xfs_buf_delwri_promote(bp);
- wake_up_process(bp->b_target->bt_task);
- }
- xfs_buf_relse(bp);
-out_lock:
- xfs_dqflock(dqp);
-}
-
int __init
xfs_qm_init(void)
{
diff --git a/fs/xfs/xfs_dquot.h b/fs/xfs/xfs_dquot.h
index 5f2a2f2c0c5b..7d20af27346d 100644
--- a/fs/xfs/xfs_dquot.h
+++ b/fs/xfs/xfs_dquot.h
@@ -152,7 +152,6 @@ extern int xfs_qm_dqget(xfs_mount_t *, xfs_inode_t *,
extern void xfs_qm_dqput(xfs_dquot_t *);
extern void xfs_dqlock2(struct xfs_dquot *, struct xfs_dquot *);
-extern void xfs_dqflock_pushbuf_wait(struct xfs_dquot *dqp);
static inline struct xfs_dquot *xfs_qm_dqhold(struct xfs_dquot *dqp)
{
diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c
index 8d8295814272..9c5d58d24e54 100644
--- a/fs/xfs/xfs_dquot_item.c
+++ b/fs/xfs/xfs_dquot_item.c
@@ -108,46 +108,6 @@ xfs_qm_dquot_logitem_unpin(
wake_up(&dqp->q_pinwait);
}
-/*
- * Given the logitem, this writes the corresponding dquot entry to disk
- * asynchronously. This is called with the dquot entry securely locked;
- * we simply get xfs_qm_dqflush() to do the work, and unlock the dquot
- * at the end.
- */
-STATIC void
-xfs_qm_dquot_logitem_push(
- struct xfs_log_item *lip)
-{
- struct xfs_dquot *dqp = DQUOT_ITEM(lip)->qli_dquot;
- struct xfs_buf *bp = NULL;
- int error;
-
- ASSERT(XFS_DQ_IS_LOCKED(dqp));
- ASSERT(!completion_done(&dqp->q_flush));
- ASSERT(atomic_read(&dqp->q_pincount) == 0);
-
- /*
- * Since we were able to lock the dquot's flush lock and
- * we found it on the AIL, the dquot must be dirty. This
- * is because the dquot is removed from the AIL while still
- * holding the flush lock in xfs_dqflush_done(). Thus, if
- * we found it in the AIL and were able to obtain the flush
- * lock without sleeping, then there must not have been
- * anyone in the process of flushing the dquot.
- */
- error = xfs_qm_dqflush(dqp, &bp);
- if (error) {
- xfs_warn(dqp->q_mount, "%s: push error %d on dqp %p",
- __func__, error, dqp);
- goto out_unlock;
- }
-
- xfs_buf_delwri_queue(bp);
- xfs_buf_relse(bp);
-out_unlock:
- xfs_dqunlock(dqp);
-}
-
STATIC xfs_lsn_t
xfs_qm_dquot_logitem_committed(
struct xfs_log_item *lip,
@@ -179,67 +139,15 @@ xfs_qm_dqunpin_wait(
wait_event(dqp->q_pinwait, (atomic_read(&dqp->q_pincount) == 0));
}
-/*
- * This is called when IOP_TRYLOCK returns XFS_ITEM_PUSHBUF to indicate that
- * the dquot is locked by us, but the flush lock isn't. So, here we are
- * going to see if the relevant dquot buffer is incore, waiting on DELWRI.
- * If so, we want to push it out to help us take this item off the AIL as soon
- * as possible.
- *
- * We must not be holding the AIL lock at this point. Calling incore() to
- * search the buffer cache can be a time consuming thing, and AIL lock is a
- * spinlock.
- */
-STATIC bool
-xfs_qm_dquot_logitem_pushbuf(
- struct xfs_log_item *lip)
-{
- struct xfs_dq_logitem *qlip = DQUOT_ITEM(lip);
- struct xfs_dquot *dqp = qlip->qli_dquot;
- struct xfs_buf *bp;
- bool ret = true;
-
- ASSERT(XFS_DQ_IS_LOCKED(dqp));
-
- /*
- * If flushlock isn't locked anymore, chances are that the
- * inode flush completed and the inode was taken off the AIL.
- * So, just get out.
- */
- if (completion_done(&dqp->q_flush) ||
- !(lip->li_flags & XFS_LI_IN_AIL)) {
- xfs_dqunlock(dqp);
- return true;
- }
-
- bp = xfs_incore(dqp->q_mount->m_ddev_targp, qlip->qli_format.qlf_blkno,
- dqp->q_mount->m_quotainfo->qi_dqchunklen, XBF_TRYLOCK);
- xfs_dqunlock(dqp);
- if (!bp)
- return true;
- if (XFS_BUF_ISDELAYWRITE(bp))
- xfs_buf_delwri_promote(bp);
- if (xfs_buf_ispinned(bp))
- ret = false;
- xfs_buf_relse(bp);
- return ret;
-}
-
-/*
- * This is called to attempt to lock the dquot associated with this
- * dquot log item. Don't sleep on the dquot lock or the flush lock.
- * If the flush lock is already held, indicating that the dquot has
- * been or is in the process of being flushed, then see if we can
- * find the dquot's buffer in the buffer cache without sleeping. If
- * we can and it is marked delayed write, then we want to send it out.
- * We delay doing so until the push routine, though, to avoid sleeping
- * in any device strategy routines.
- */
STATIC uint
-xfs_qm_dquot_logitem_trylock(
- struct xfs_log_item *lip)
+xfs_qm_dquot_logitem_push(
+ struct xfs_log_item *lip,
+ struct list_head *buffer_list)
{
struct xfs_dquot *dqp = DQUOT_ITEM(lip)->qli_dquot;
+ struct xfs_buf *bp = NULL;
+ uint rval = XFS_ITEM_SUCCESS;
+ int error;
if (atomic_read(&dqp->q_pincount) > 0)
return XFS_ITEM_PINNED;
@@ -252,20 +160,36 @@ xfs_qm_dquot_logitem_trylock(
* taking the quota lock.
*/
if (atomic_read(&dqp->q_pincount) > 0) {
- xfs_dqunlock(dqp);
- return XFS_ITEM_PINNED;
+ rval = XFS_ITEM_PINNED;
+ goto out_unlock;
}
+ /*
+ * Someone else is already flushing the dquot. Nothing we can do
+ * here but wait for the flush to finish and remove the item from
+ * the AIL.
+ */
if (!xfs_dqflock_nowait(dqp)) {
- /*
- * dquot has already been flushed to the backing buffer,
- * leave it locked, pushbuf routine will unlock it.
- */
- return XFS_ITEM_PUSHBUF;
+ rval = XFS_ITEM_FLUSHING;
+ goto out_unlock;
+ }
+
+ spin_unlock(&lip->li_ailp->xa_lock);
+
+ error = xfs_qm_dqflush(dqp, &bp);
+ if (error) {
+ xfs_warn(dqp->q_mount, "%s: push error %d on dqp %p",
+ __func__, error, dqp);
+ } else {
+ if (!xfs_buf_delwri_queue(bp, buffer_list))
+ rval = XFS_ITEM_FLUSHING;
+ xfs_buf_relse(bp);
}
- ASSERT(lip->li_flags & XFS_LI_IN_AIL);
- return XFS_ITEM_SUCCESS;
+ spin_lock(&lip->li_ailp->xa_lock);
+out_unlock:
+ xfs_dqunlock(dqp);
+ return rval;
}
/*
@@ -316,11 +240,9 @@ static const struct xfs_item_ops xfs_dquot_item_ops = {
.iop_format = xfs_qm_dquot_logitem_format,
.iop_pin = xfs_qm_dquot_logitem_pin,
.iop_unpin = xfs_qm_dquot_logitem_unpin,
- .iop_trylock = xfs_qm_dquot_logitem_trylock,
.iop_unlock = xfs_qm_dquot_logitem_unlock,
.iop_committed = xfs_qm_dquot_logitem_committed,
.iop_push = xfs_qm_dquot_logitem_push,
- .iop_pushbuf = xfs_qm_dquot_logitem_pushbuf,
.iop_committing = xfs_qm_dquot_logitem_committing
};
@@ -415,11 +337,13 @@ xfs_qm_qoff_logitem_unpin(
}
/*
- * Quotaoff items have no locking, so just return success.
+ * There isn't much you can do to push a quotaoff item. It is simply
+ * stuck waiting for the log to be flushed to disk.
*/
STATIC uint
-xfs_qm_qoff_logitem_trylock(
- struct xfs_log_item *lip)
+xfs_qm_qoff_logitem_push(
+ struct xfs_log_item *lip,
+ struct list_head *buffer_list)
{
return XFS_ITEM_LOCKED;
}
@@ -446,17 +370,6 @@ xfs_qm_qoff_logitem_committed(
return lsn;
}
-/*
- * There isn't much you can do to push on an quotaoff item. It is simply
- * stuck waiting for the log to be flushed to disk.
- */
-STATIC void
-xfs_qm_qoff_logitem_push(
- struct xfs_log_item *lip)
-{
-}
-
-
STATIC xfs_lsn_t
xfs_qm_qoffend_logitem_committed(
struct xfs_log_item *lip,
@@ -504,7 +417,6 @@ static const struct xfs_item_ops xfs_qm_qoffend_logitem_ops = {
.iop_format = xfs_qm_qoff_logitem_format,
.iop_pin = xfs_qm_qoff_logitem_pin,
.iop_unpin = xfs_qm_qoff_logitem_unpin,
- .iop_trylock = xfs_qm_qoff_logitem_trylock,
.iop_unlock = xfs_qm_qoff_logitem_unlock,
.iop_committed = xfs_qm_qoffend_logitem_committed,
.iop_push = xfs_qm_qoff_logitem_push,
@@ -519,7 +431,6 @@ static const struct xfs_item_ops xfs_qm_qoff_logitem_ops = {
.iop_format = xfs_qm_qoff_logitem_format,
.iop_pin = xfs_qm_qoff_logitem_pin,
.iop_unpin = xfs_qm_qoff_logitem_unpin,
- .iop_trylock = xfs_qm_qoff_logitem_trylock,
.iop_unlock = xfs_qm_qoff_logitem_unlock,
.iop_committed = xfs_qm_qoff_logitem_committed,
.iop_push = xfs_qm_qoff_logitem_push,
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index 35c2aff38b20..9549ef179e06 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -147,22 +147,20 @@ xfs_efi_item_unpin(
}
/*
- * Efi items have no locking or pushing. However, since EFIs are
- * pulled from the AIL when their corresponding EFDs are committed
- * to disk, their situation is very similar to being pinned. Return
- * XFS_ITEM_PINNED so that the caller will eventually flush the log.
- * This should help in getting the EFI out of the AIL.
+ * Efi items have no locking or pushing. However, since EFIs are pulled from
+ * the AIL when their corresponding EFDs are committed to disk, their situation
+ * is very similar to being pinned. Return XFS_ITEM_PINNED so that the caller
+ * will eventually flush the log. This should help in getting the EFI out of
+ * the AIL.
*/
STATIC uint
-xfs_efi_item_trylock(
- struct xfs_log_item *lip)
+xfs_efi_item_push(
+ struct xfs_log_item *lip,
+ struct list_head *buffer_list)
{
return XFS_ITEM_PINNED;
}
-/*
- * Efi items have no locking, so just return.
- */
STATIC void
xfs_efi_item_unlock(
struct xfs_log_item *lip)
@@ -189,17 +187,6 @@ xfs_efi_item_committed(
return lsn;
}
-/*
- * There isn't much you can do to push on an efi item. It is simply
- * stuck waiting for all of its corresponding efd items to be
- * committed to disk.
- */
-STATIC void
-xfs_efi_item_push(
- struct xfs_log_item *lip)
-{
-}
-
/*
* The EFI dependency tracking op doesn't do squat. It can't because
* it doesn't know where the free extent is coming from. The dependency
@@ -222,7 +209,6 @@ static const struct xfs_item_ops xfs_efi_item_ops = {
.iop_format = xfs_efi_item_format,
.iop_pin = xfs_efi_item_pin,
.iop_unpin = xfs_efi_item_unpin,
- .iop_trylock = xfs_efi_item_trylock,
.iop_unlock = xfs_efi_item_unlock,
.iop_committed = xfs_efi_item_committed,
.iop_push = xfs_efi_item_push,
@@ -404,19 +390,17 @@ xfs_efd_item_unpin(
}
/*
- * Efd items have no locking, so just return success.
+ * There isn't much you can do to push on an efd item. It is simply stuck
+ * waiting for the log to be flushed to disk.
*/
STATIC uint
-xfs_efd_item_trylock(
- struct xfs_log_item *lip)
+xfs_efd_item_push(
+ struct xfs_log_item *lip,
+ struct list_head *buffer_list)
{
- return XFS_ITEM_LOCKED;
+ return XFS_ITEM_PINNED;
}
-/*
- * Efd items have no locking or pushing, so return failure
- * so that the caller doesn't bother with us.
- */
STATIC void
xfs_efd_item_unlock(
struct xfs_log_item *lip)
@@ -450,16 +434,6 @@ xfs_efd_item_committed(
return (xfs_lsn_t)-1;
}
-/*
- * There isn't much you can do to push on an efd item. It is simply
- * stuck waiting for the log to be flushed to disk.
- */
-STATIC void
-xfs_efd_item_push(
- struct xfs_log_item *lip)
-{
-}
-
/*
* The EFD dependency tracking op doesn't do squat. It can't because
* it doesn't know where the free extent is coming from. The dependency
@@ -482,7 +456,6 @@ static const struct xfs_item_ops xfs_efd_item_ops = {
.iop_format = xfs_efd_item_format,
.iop_pin = xfs_efd_item_pin,
.iop_unpin = xfs_efd_item_unpin,
- .iop_trylock = xfs_efd_item_trylock,
.iop_unlock = xfs_efd_item_unlock,
.iop_committed = xfs_efd_item_committed,
.iop_push = xfs_efd_item_push,
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 0fa987dea242..acd846d808b2 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2347,11 +2347,11 @@ cluster_corrupt_out:
*/
rcu_read_unlock();
/*
- * Clean up the buffer. If it was B_DELWRI, just release it --
+ * Clean up the buffer. If it was delwri, just release it --
* brelse can handle it with no problems. If not, shut down the
* filesystem before releasing the buffer.
*/
- bufwasdelwri = XFS_BUF_ISDELAYWRITE(bp);
+ bufwasdelwri = (bp->b_flags & _XBF_DELWRI_Q);
if (bufwasdelwri)
xfs_buf_relse(bp);
@@ -2685,27 +2685,6 @@ corrupt_out:
return XFS_ERROR(EFSCORRUPTED);
}
-void
-xfs_promote_inode(
- struct xfs_inode *ip)
-{
- struct xfs_buf *bp;
-
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
-
- bp = xfs_incore(ip->i_mount->m_ddev_targp, ip->i_imap.im_blkno,
- ip->i_imap.im_len, XBF_TRYLOCK);
- if (!bp)
- return;
-
- if (XFS_BUF_ISDELAYWRITE(bp)) {
- xfs_buf_delwri_promote(bp);
- wake_up_process(ip->i_mount->m_ddev_targp->bt_task);
- }
-
- xfs_buf_relse(bp);
-}
-
/*
* Return a pointer to the extent record at file index idx.
*/
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index a2fa79ae410f..f0e252f384f9 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -530,7 +530,6 @@ int xfs_iunlink(struct xfs_trans *, xfs_inode_t *);
void xfs_iext_realloc(xfs_inode_t *, int, int);
void xfs_iunpin_wait(xfs_inode_t *);
int xfs_iflush(struct xfs_inode *, struct xfs_buf **);
-void xfs_promote_inode(struct xfs_inode *);
void xfs_lock_inodes(xfs_inode_t **, int, uint);
void xfs_lock_two_inodes(xfs_inode_t *, xfs_inode_t *, uint);
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index d3601ab75dd3..8aaebb2f9efa 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -480,25 +480,16 @@ xfs_inode_item_unpin(
wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT);
}
-/*
- * This is called to attempt to lock the inode associated with this
- * inode log item, in preparation for the push routine which does the actual
- * iflush. Don't sleep on the inode lock or the flush lock.
- *
- * If the flush lock is already held, indicating that the inode has
- * been or is in the process of being flushed, then (ideally) we'd like to
- * see if the inode's buffer is still incore, and if so give it a nudge.
- * We delay doing so until the pushbuf routine, though, to avoid holding
- * the AIL lock across a call to the blackhole which is the buffer cache.
- * Also we don't want to sleep in any device strategy routines, which can happen
- * if we do the subsequent bawrite in here.
- */
STATIC uint
-xfs_inode_item_trylock(
- struct xfs_log_item *lip)
+xfs_inode_item_push(
+ struct xfs_log_item *lip,
+ struct list_head *buffer_list)
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
+ struct xfs_buf *bp = NULL;
+ uint rval = XFS_ITEM_SUCCESS;
+ int error;
if (xfs_ipincount(ip) > 0)
return XFS_ITEM_PINNED;
@@ -511,34 +502,45 @@ xfs_inode_item_trylock(
* taking the ilock.
*/
if (xfs_ipincount(ip) > 0) {
- xfs_iunlock(ip, XFS_ILOCK_SHARED);
- return XFS_ITEM_PINNED;
+ rval = XFS_ITEM_PINNED;
+ goto out_unlock;
}
+ /*
+ * Someone else is already flushing the inode. Nothing we can do
+ * here but wait for the flush to finish and remove the item from
+ * the AIL.
+ */
if (!xfs_iflock_nowait(ip)) {
- /*
- * inode has already been flushed to the backing buffer,
- * leave it locked in shared mode, pushbuf routine will
- * unlock it.
- */
- return XFS_ITEM_PUSHBUF;
+ rval = XFS_ITEM_FLUSHING;
+ goto out_unlock;
}
- /* Stale items should force out the iclog */
+ /*
+ * Stale inode items should force out the iclog.
+ */
if (ip->i_flags & XFS_ISTALE) {
xfs_ifunlock(ip);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
return XFS_ITEM_PINNED;
}
-#ifdef DEBUG
- if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
- ASSERT(iip->ili_fields != 0);
- ASSERT(iip->ili_logged == 0);
- ASSERT(lip->li_flags & XFS_LI_IN_AIL);
+ ASSERT(iip->ili_fields != 0 || XFS_FORCED_SHUTDOWN(ip->i_mount));
+ ASSERT(iip->ili_logged == 0 || XFS_FORCED_SHUTDOWN(ip->i_mount));
+
+ spin_unlock(&lip->li_ailp->xa_lock);
+
+ error = xfs_iflush(ip, &bp);
+ if (!error) {
+ if (!xfs_buf_delwri_queue(bp, buffer_list))
+ rval = XFS_ITEM_FLUSHING;
+ xfs_buf_relse(bp);
}
-#endif
- return XFS_ITEM_SUCCESS;
+
+ spin_lock(&lip->li_ailp->xa_lock);
+out_unlock:
+ xfs_iunlock(ip, XFS_ILOCK_SHARED);
+ return rval;
}
/*
@@ -622,92 +624,6 @@ xfs_inode_item_committed(
return lsn;
}
-/*
- * This gets called by xfs_trans_push_ail(), when IOP_TRYLOCK
- * failed to get the inode flush lock but did get the inode locked SHARED.
- * Here we're trying to see if the inode buffer is incore, and if so whether it's
- * marked delayed write. If that's the case, we'll promote it and that will
- * allow the caller to write the buffer by triggering the xfsbufd to run.
- */
-STATIC bool
-xfs_inode_item_pushbuf(
- struct xfs_log_item *lip)
-{
- struct xfs_inode_log_item *iip = INODE_ITEM(lip);
- struct xfs_inode *ip = iip->ili_inode;
- struct xfs_buf *bp;
- bool ret = true;
-
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED));
-
- /*
- * If a flush is not in progress anymore, chances are that the
- * inode was taken off the AIL. So, just get out.
- */
- if (!xfs_isiflocked(ip) ||
- !(lip->li_flags & XFS_LI_IN_AIL)) {
- xfs_iunlock(ip, XFS_ILOCK_SHARED);
- return true;
- }
-
- bp = xfs_incore(ip->i_mount->m_ddev_targp, iip->ili_format.ilf_blkno,
- iip->ili_format.ilf_len, XBF_TRYLOCK);
-
- xfs_iunlock(ip, XFS_ILOCK_SHARED);
- if (!bp)
- return true;
- if (XFS_BUF_ISDELAYWRITE(bp))
- xfs_buf_delwri_promote(bp);
- if (xfs_buf_ispinned(bp))
- ret = false;
- xfs_buf_relse(bp);
- return ret;
-}
-
-/*
- * This is called to asynchronously write the inode associated with this
- * inode log item out to disk. The inode will already have been locked by
- * a successful call to xfs_inode_item_trylock().
- */
-STATIC void
-xfs_inode_item_push(
- struct xfs_log_item *lip)
-{
- struct xfs_inode_log_item *iip = INODE_ITEM(lip);
- struct xfs_inode *ip = iip->ili_inode;
- struct xfs_buf *bp = NULL;
- int error;
-
- ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED));
- ASSERT(xfs_isiflocked(ip));
-
- /*
- * Since we were able to lock the inode's flush lock and
- * we found it on the AIL, the inode must be dirty. This
- * is because the inode is removed from the AIL while still
- * holding the flush lock in xfs_iflush_done(). Thus, if
- * we found it in the AIL and were able to obtain the flush
- * lock without sleeping, then there must not have been
- * anyone in the process of flushing the inode.
- */
- ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || iip->ili_fields != 0);
-
- /*
- * Push the inode to it's backing buffer. This will not remove the
- * inode from the AIL - a further push will be required to trigger a
- * buffer push. However, this allows all the dirty inodes to be pushed
- * to the buffer before it is pushed to disk. The buffer IO completion
- * will pull the inode from the AIL, mark it clean and unlock the flush
- * lock.
- */
- error = xfs_iflush(ip, &bp);
- if (!error) {
- xfs_buf_delwri_queue(bp);
- xfs_buf_relse(bp);
- }
- xfs_iunlock(ip, XFS_ILOCK_SHARED);
-}
-
/*
* XXX rcc - this one really has to do something. Probably needs
* to stamp in a new field in the incore inode.
@@ -728,11 +644,9 @@ static const struct xfs_item_ops xfs_inode_item_ops = {
.iop_format = xfs_inode_item_format,
.iop_pin = xfs_inode_item_pin,
.iop_unpin = xfs_inode_item_unpin,
- .iop_trylock = xfs_inode_item_trylock,
.iop_unlock = xfs_inode_item_unlock,
.iop_committed = xfs_inode_item_committed,
.iop_push = xfs_inode_item_push,
- .iop_pushbuf = xfs_inode_item_pushbuf,
.iop_committing = xfs_inode_item_committing
};
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 8ecad5bad66c..5e864a9c0ccf 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2103,6 +2103,7 @@ xlog_recover_do_dquot_buffer(
STATIC int
xlog_recover_buffer_pass2(
xlog_t *log,
+ struct list_head *buffer_list,
xlog_recover_item_t *item)
{
xfs_buf_log_format_t *buf_f = item->ri_buf[0].i_addr;
@@ -2173,7 +2174,7 @@ xlog_recover_buffer_pass2(
} else {
ASSERT(bp->b_target->bt_mount == mp);
bp->b_iodone = xlog_recover_iodone;
- xfs_buf_delwri_queue(bp);
+ xfs_buf_delwri_queue(bp, buffer_list);
}
xfs_buf_relse(bp);
@@ -2183,6 +2184,7 @@ xlog_recover_buffer_pass2(
STATIC int
xlog_recover_inode_pass2(
xlog_t *log,
+ struct list_head *buffer_list,
xlog_recover_item_t *item)
{
xfs_inode_log_format_t *in_f;
@@ -2436,7 +2438,7 @@ xlog_recover_inode_pass2(
write_inode_buffer:
ASSERT(bp->b_target->bt_mount == mp);
bp->b_iodone = xlog_recover_iodone;
- xfs_buf_delwri_queue(bp);
+ xfs_buf_delwri_queue(bp, buffer_list);
xfs_buf_relse(bp);
error:
if (need_free)
@@ -2477,6 +2479,7 @@ xlog_recover_quotaoff_pass1(
STATIC int
xlog_recover_dquot_pass2(
xlog_t *log,
+ struct list_head *buffer_list,
xlog_recover_item_t *item)
{
xfs_mount_t *mp = log->l_mp;
@@ -2558,7 +2561,7 @@ xlog_recover_dquot_pass2(
ASSERT(dq_f->qlf_size == 2);
ASSERT(bp->b_target->bt_mount == mp);
bp->b_iodone = xlog_recover_iodone;
- xfs_buf_delwri_queue(bp);
+ xfs_buf_delwri_queue(bp, buffer_list);
xfs_buf_relse(bp);
return (0);
@@ -2712,21 +2715,22 @@ STATIC int
xlog_recover_commit_pass2(
struct log *log,
struct xlog_recover *trans,
+ struct list_head *buffer_list,
xlog_recover_item_t *item)
{
trace_xfs_log_recover_item_recover(log, trans, item, XLOG_RECOVER_PASS2);
switch (ITEM_TYPE(item)) {
case XFS_LI_BUF:
- return xlog_recover_buffer_pass2(log, item);
+ return xlog_recover_buffer_pass2(log, buffer_list, item);
case XFS_LI_INODE:
- return xlog_recover_inode_pass2(log, item);
+ return xlog_recover_inode_pass2(log, buffer_list, item);
case XFS_LI_EFI:
return xlog_recover_efi_pass2(log, item, trans->r_lsn);
case XFS_LI_EFD:
return xlog_recover_efd_pass2(log, item);
case XFS_LI_DQUOT:
- return xlog_recover_dquot_pass2(log, item);
+ return xlog_recover_dquot_pass2(log, buffer_list, item);
case XFS_LI_QUOTAOFF:
/* nothing to do in pass2 */
return 0;
@@ -2750,8 +2754,9 @@ xlog_recover_commit_trans(
struct xlog_recover *trans,
int pass)
{
- int error = 0;
+ int error = 0, error2;
xlog_recover_item_t *item;
+ LIST_HEAD (buffer_list);
hlist_del(&trans->r_list);
@@ -2760,16 +2765,27 @@ xlog_recover_commit_trans(
return error;
list_for_each_entry(item, &trans->r_itemq, ri_list) {
- if (pass == XLOG_RECOVER_PASS1)
+ switch (pass) {
+ case XLOG_RECOVER_PASS1:
error = xlog_recover_commit_pass1(log, trans, item);
- else
- error = xlog_recover_commit_pass2(log, trans, item);
+ break;
+ case XLOG_RECOVER_PASS2:
+ error = xlog_recover_commit_pass2(log, trans,
+ &buffer_list, item);
+ break;
+ default:
+ ASSERT(0);
+ }
+
if (error)
- return error;
+ goto out;
}
xlog_recover_free_trans(trans);
- return 0;
+
+out:
+ error2 = xfs_buf_delwri_submit(&buffer_list);
+ return error ? error : error2;
}
STATIC int
@@ -3639,11 +3655,8 @@ xlog_do_recover(
* First replay the images in the log.
*/
error = xlog_do_log_recovery(log, head_blk, tail_blk);
- if (error) {
+ if (error)
return error;
- }
-
- xfs_flush_buftarg(log->l_mp->m_ddev_targp, 1);
/*
* If IO errors happened during recovery, bail out.
@@ -3670,7 +3683,6 @@ xlog_do_recover(
bp = xfs_getsb(log->l_mp, 0);
XFS_BUF_UNDONE(bp);
ASSERT(!(XFS_BUF_ISWRITE(bp)));
- ASSERT(!(XFS_BUF_ISDELAYWRITE(bp)));
XFS_BUF_READ(bp);
XFS_BUF_UNASYNC(bp);
xfsbdstrat(log->l_mp, bp);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 95aecf52475d..755a9bd749d0 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -65,7 +65,8 @@ STATIC int
xfs_qm_dquot_walk(
struct xfs_mount *mp,
int type,
- int (*execute)(struct xfs_dquot *dqp))
+ int (*execute)(struct xfs_dquot *dqp, void *data),
+ void *data)
{
struct xfs_quotainfo *qi = mp->m_quotainfo;
struct radix_tree_root *tree = XFS_DQUOT_TREE(qi, type);
@@ -97,7 +98,7 @@ restart:
next_index = be32_to_cpu(dqp->q_core.d_id) + 1;
- error = execute(batch[i]);
+ error = execute(batch[i], data);
if (error == EAGAIN) {
skipped++;
continue;
@@ -129,7 +130,8 @@ restart:
*/
STATIC int
xfs_qm_dqpurge(
- struct xfs_dquot *dqp)
+ struct xfs_dquot *dqp,
+ void *data)
{
struct xfs_mount *mp = dqp->q_mount;
struct xfs_quotainfo *qi = mp->m_quotainfo;
@@ -153,21 +155,7 @@ xfs_qm_dqpurge(
dqp->dq_flags |= XFS_DQ_FREEING;
- /*
- * If we're turning off quotas, we have to make sure that, for
- * example, we don't delete quota disk blocks while dquots are
- * in the process of getting written to those disk blocks.
- * This dquot might well be on AIL, and we can't leave it there
- * if we're turning off quotas. Basically, we need this flush
- * lock, and are willing to block on it.
- */
- if (!xfs_dqflock_nowait(dqp)) {
- /*
- * Block on the flush lock after nudging dquot buffer,
- * if it is incore.
- */
- xfs_dqflock_pushbuf_wait(dqp);
- }
+ xfs_dqflock(dqp);
/*
* If we are turning this type of quotas off, we don't care
@@ -231,11 +219,11 @@ xfs_qm_dqpurge_all(
uint flags)
{
if (flags & XFS_QMOPT_UQUOTA)
- xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge);
+ xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_dqpurge, NULL);
if (flags & XFS_QMOPT_GQUOTA)
- xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_dqpurge);
+ xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_dqpurge, NULL);
if (flags & XFS_QMOPT_PQUOTA)
- xfs_qm_dquot_walk(mp, XFS_DQ_PROJ, xfs_qm_dqpurge);
+ xfs_qm_dquot_walk(mp, XFS_DQ_PROJ, xfs_qm_dqpurge, NULL);
}
/*
@@ -876,15 +864,16 @@ xfs_qm_reset_dqcounts(
STATIC int
xfs_qm_dqiter_bufs(
- xfs_mount_t *mp,
- xfs_dqid_t firstid,
- xfs_fsblock_t bno,
- xfs_filblks_t blkcnt,
- uint flags)
+ struct xfs_mount *mp,
+ xfs_dqid_t firstid,
+ xfs_fsblock_t bno,
+ xfs_filblks_t blkcnt,
+ uint flags,
+ struct list_head *buffer_list)
{
- xfs_buf_t *bp;
- int error;
- int type;
+ struct xfs_buf *bp;
+ int error;
+ int type;
ASSERT(blkcnt > 0);
type = flags & XFS_QMOPT_UQUOTA ? XFS_DQ_USER :
@@ -908,7 +897,7 @@ xfs_qm_dqiter_bufs(
break;
xfs_qm_reset_dqcounts(mp, bp, firstid, type);
- xfs_buf_delwri_queue(bp);
+ xfs_buf_delwri_queue(bp, buffer_list);
xfs_buf_relse(bp);
/*
* goto the next block.
@@ -916,6 +905,7 @@ xfs_qm_dqiter_bufs(
bno++;
firstid += mp->m_quotainfo->qi_dqperchunk;
}
+
return error;
}
@@ -925,11 +915,12 @@ xfs_qm_dqiter_bufs(
*/
STATIC int
xfs_qm_dqiterate(
- xfs_mount_t *mp,
- xfs_inode_t *qip,
- uint flags)
+ struct xfs_mount *mp,
+ struct xfs_inode *qip,
+ uint flags,
+ struct list_head *buffer_list)
{
- xfs_bmbt_irec_t *map;
+ struct xfs_bmbt_irec *map;
int i, nmaps; /* number of map entries */
int error; /* return value */
xfs_fileoff_t lblkno;
@@ -996,21 +987,17 @@ xfs_qm_dqiterate(
* Iterate thru all the blks in the extent and
* reset the counters of all the dquots inside them.
*/
- if ((error = xfs_qm_dqiter_bufs(mp,
- firstid,
- map[i].br_startblock,
- map[i].br_blockcount,
- flags))) {
- break;
- }
+ error = xfs_qm_dqiter_bufs(mp, firstid,
+ map[i].br_startblock,
+ map[i].br_blockcount,
+ flags, buffer_list);
+ if (error)
+ goto out;
}
-
- if (error)
- break;
} while (nmaps > 0);
+out:
kmem_free(map);
-
return error;
}
@@ -1203,8 +1190,10 @@ error0:
STATIC int
xfs_qm_flush_one(
- struct xfs_dquot *dqp)
+ struct xfs_dquot *dqp,
+ void *data)
{
+ struct list_head *buffer_list = data;
struct xfs_buf *bp = NULL;
int error = 0;
@@ -1214,14 +1203,12 @@ xfs_qm_flush_one(
if (!XFS_DQ_IS_DIRTY(dqp))
goto out_unlock;
- if (!xfs_dqflock_nowait(dqp))
- xfs_dqflock_pushbuf_wait(dqp);
-
+ xfs_dqflock(dqp);
error = xfs_qm_dqflush(dqp, &bp);
if (error)
goto out_unlock;
- xfs_buf_delwri_queue(bp);
+ xfs_buf_delwri_queue(bp, buffer_list);
xfs_buf_relse(bp);
out_unlock:
xfs_dqunlock(dqp);
@@ -1241,6 +1228,7 @@ xfs_qm_quotacheck(
size_t structsz;
xfs_inode_t *uip, *gip;
uint flags;
+ LIST_HEAD (buffer_list);
count = INT_MAX;
structsz = 1;
@@ -1259,7 +1247,8 @@ xfs_qm_quotacheck(
*/
uip = mp->m_quotainfo->qi_uquotaip;
if (uip) {
- error = xfs_qm_dqiterate(mp, uip, XFS_QMOPT_UQUOTA);
+ error = xfs_qm_dqiterate(mp, uip, XFS_QMOPT_UQUOTA,
+ &buffer_list);
if (error)
goto error_return;
flags |= XFS_UQUOTA_CHKD;
@@ -1268,7 +1257,8 @@ xfs_qm_quotacheck(
gip = mp->m_quotainfo->qi_gquotaip;
if (gip) {
error = xfs_qm_dqiterate(mp, gip, XFS_IS_GQUOTA_ON(mp) ?
- XFS_QMOPT_GQUOTA : XFS_QMOPT_PQUOTA);
+ XFS_QMOPT_GQUOTA : XFS_QMOPT_PQUOTA,
+ &buffer_list);
if (error)
goto error_return;
flags |= XFS_OQUOTA_CHKD;
@@ -1291,19 +1281,27 @@ xfs_qm_quotacheck(
* We've made all the changes that we need to make incore. Flush them
* down to disk buffers if everything was updated successfully.
*/
- if (XFS_IS_UQUOTA_ON(mp))
- error = xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_flush_one);
+ if (XFS_IS_UQUOTA_ON(mp)) {
+ error = xfs_qm_dquot_walk(mp, XFS_DQ_USER, xfs_qm_flush_one,
+ &buffer_list);
+ }
if (XFS_IS_GQUOTA_ON(mp)) {
- error2 = xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_flush_one);
+ error2 = xfs_qm_dquot_walk(mp, XFS_DQ_GROUP, xfs_qm_flush_one,
+ &buffer_list);
if (!error)
error = error2;
}
if (XFS_IS_PQUOTA_ON(mp)) {
- error2 = xfs_qm_dquot_walk(mp, XFS_DQ_PROJ, xfs_qm_flush_one);
+ error2 = xfs_qm_dquot_walk(mp, XFS_DQ_PROJ, xfs_qm_flush_one,
+ &buffer_list);
if (!error)
error = error2;
}
+ error2 = xfs_buf_delwri_submit(&buffer_list);
+ if (!error)
+ error = error2;
+
/*
* We can get this error if we couldn't do a dquot allocation inside
* xfs_qm_dqusage_adjust (via bulkstat). We don't care about the
@@ -1316,15 +1314,6 @@ xfs_qm_quotacheck(
goto error_return;
}
- /*
- * We didn't log anything, because if we crashed, we'll have to
- * start the quotacheck from scratch anyway. However, we must make
- * sure that our dquot changes are secure before we put the
- * quotacheck'd stamp on the superblock. So, here we do a synchronous
- * flush.
- */
- xfs_flush_buftarg(mp->m_ddev_targp, 1);
-
/*
* If one type of quotas is off, then it will lose its
* quotachecked status, since we won't be doing accounting for
@@ -1334,6 +1323,13 @@ 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);
+ }
+
if (error) {
xfs_warn(mp,
"Quotacheck: Unsuccessful (Error %d): Disabling quotas.",
@@ -1450,6 +1446,7 @@ xfs_qm_dqfree_one(
STATIC void
xfs_qm_dqreclaim_one(
struct xfs_dquot *dqp,
+ struct list_head *buffer_list,
struct list_head *dispose_list)
{
struct xfs_mount *mp = dqp->q_mount;
@@ -1482,21 +1479,11 @@ xfs_qm_dqreclaim_one(
if (!xfs_dqflock_nowait(dqp))
goto out_busy;
- /*
- * We have the flush lock so we know that this is not in the
- * process of being flushed. So, if this is dirty, flush it
- * DELWRI so that we don't get a freelist infested with
- * dirty dquots.
- */
if (XFS_DQ_IS_DIRTY(dqp)) {
struct xfs_buf *bp = NULL;
trace_xfs_dqreclaim_dirty(dqp);
- /*
- * We flush it delayed write, so don't bother releasing the
- * freelist lock.
- */
error = xfs_qm_dqflush(dqp, &bp);
if (error) {
xfs_warn(mp, "%s: dquot %p flush failed",
@@ -1504,7 +1491,7 @@ xfs_qm_dqreclaim_one(
goto out_busy;
}
- xfs_buf_delwri_queue(bp);
+ xfs_buf_delwri_queue(bp, buffer_list);
xfs_buf_relse(bp);
/*
* Give the dquot another try on the freelist, as the
@@ -1549,8 +1536,10 @@ xfs_qm_shake(
struct xfs_quotainfo *qi =
container_of(shrink, struct xfs_quotainfo, qi_shrinker);
int nr_to_scan = sc->nr_to_scan;
+ LIST_HEAD (buffer_list);
LIST_HEAD (dispose_list);
struct xfs_dquot *dqp;
+ int error;
if ((sc->gfp_mask & (__GFP_FS|__GFP_WAIT)) != (__GFP_FS|__GFP_WAIT))
return 0;
@@ -1563,15 +1552,20 @@ xfs_qm_shake(
break;
dqp = list_first_entry(&qi->qi_lru_list, struct xfs_dquot,
q_lru);
- xfs_qm_dqreclaim_one(dqp, &dispose_list);
+ xfs_qm_dqreclaim_one(dqp, &buffer_list, &dispose_list);
}
mutex_unlock(&qi->qi_lru_lock);
+ error = xfs_buf_delwri_submit(&buffer_list);
+ if (error)
+ xfs_warn(NULL, "%s: dquot reclaim failed", __func__);
+
while (!list_empty(&dispose_list)) {
dqp = list_first_entry(&dispose_list, struct xfs_dquot, q_lru);
list_del_init(&dqp->q_lru);
xfs_qm_dqfree_one(dqp);
}
+
out:
return (qi->qi_lru_count / 100) * sysctl_vfs_cache_pressure;
}
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 28d1f508b578..fa07b7731cf2 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -981,15 +981,7 @@ xfs_fs_put_super(
{
struct xfs_mount *mp = XFS_M(sb);
- /*
- * Blow away any referenced inode in the filestreams cache.
- * This can and will cause log traffic as inodes go inactive
- * here.
- */
xfs_filestream_unmount(mp);
-
- xfs_flush_buftarg(mp->m_ddev_targp, 1);
-
xfs_unmountfs(mp);
xfs_syncd_stop(mp);
xfs_freesb(mp);
@@ -1404,15 +1396,7 @@ out_destroy_workqueues:
return -error;
out_unmount:
- /*
- * Blow away any referenced inode in the filestreams cache.
- * This can and will cause log traffic as inodes go inactive
- * here.
- */
xfs_filestream_unmount(mp);
-
- xfs_flush_buftarg(mp->m_ddev_targp, 1);
-
xfs_unmountfs(mp);
xfs_syncd_stop(mp);
goto out_free_sb;
diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index 468c3c0a4f9f..cdb644fd0bd1 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -313,17 +313,10 @@ xfs_quiesce_data(
/* write superblock and hoover up shutdown errors */
error = xfs_sync_fsdata(mp);
- /* make sure all delwri buffers are written out */
- xfs_flush_buftarg(mp->m_ddev_targp, 1);
-
/* mark the log as covered if needed */
if (xfs_log_need_covered(mp))
error2 = xfs_fs_log_dummy(mp);
- /* flush data-only devices */
- if (mp->m_rtdev_targp)
- xfs_flush_buftarg(mp->m_rtdev_targp, 1);
-
return error ? error : error2;
}
@@ -684,17 +677,6 @@ restart:
if (!xfs_iflock_nowait(ip)) {
if (!(sync_mode & SYNC_WAIT))
goto out;
-
- /*
- * If we only have a single dirty inode in a cluster there is
- * a fair chance that the AIL push may have pushed it into
- * the buffer, but xfsbufd won't touch it until 30 seconds
- * from now, and thus we will lock up here.
- *
- * Promote the inode buffer to the front of the delwri list
- * and wake up xfsbufd now.
- */
- xfs_promote_inode(ip);
xfs_iflock(ip);
}
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 06838c42b2a0..2e41756e263a 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -328,7 +328,7 @@ DEFINE_BUF_EVENT(xfs_buf_unlock);
DEFINE_BUF_EVENT(xfs_buf_iowait);
DEFINE_BUF_EVENT(xfs_buf_iowait_done);
DEFINE_BUF_EVENT(xfs_buf_delwri_queue);
-DEFINE_BUF_EVENT(xfs_buf_delwri_dequeue);
+DEFINE_BUF_EVENT(xfs_buf_delwri_queued);
DEFINE_BUF_EVENT(xfs_buf_delwri_split);
DEFINE_BUF_EVENT(xfs_buf_get_uncached);
DEFINE_BUF_EVENT(xfs_bdstrat_shut);
@@ -486,12 +486,10 @@ DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format_stale);
DEFINE_BUF_ITEM_EVENT(xfs_buf_item_pin);
DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin);
DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin_stale);
-DEFINE_BUF_ITEM_EVENT(xfs_buf_item_trylock);
DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unlock);
DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unlock_stale);
DEFINE_BUF_ITEM_EVENT(xfs_buf_item_committed);
DEFINE_BUF_ITEM_EVENT(xfs_buf_item_push);
-DEFINE_BUF_ITEM_EVENT(xfs_buf_item_pushbuf);
DEFINE_BUF_ITEM_EVENT(xfs_trans_get_buf);
DEFINE_BUF_ITEM_EVENT(xfs_trans_get_buf_recur);
DEFINE_BUF_ITEM_EVENT(xfs_trans_getsb);
@@ -881,10 +879,9 @@ DEFINE_EVENT(xfs_log_item_class, name, \
TP_PROTO(struct xfs_log_item *lip), \
TP_ARGS(lip))
DEFINE_LOG_ITEM_EVENT(xfs_ail_push);
-DEFINE_LOG_ITEM_EVENT(xfs_ail_pushbuf);
-DEFINE_LOG_ITEM_EVENT(xfs_ail_pushbuf_pinned);
DEFINE_LOG_ITEM_EVENT(xfs_ail_pinned);
DEFINE_LOG_ITEM_EVENT(xfs_ail_locked);
+DEFINE_LOG_ITEM_EVENT(xfs_ail_flushing);
DECLARE_EVENT_CLASS(xfs_file_class,
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index f6118703f20d..7ab99e1898c8 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -345,11 +345,9 @@ struct xfs_item_ops {
void (*iop_format)(xfs_log_item_t *, struct xfs_log_iovec *);
void (*iop_pin)(xfs_log_item_t *);
void (*iop_unpin)(xfs_log_item_t *, int remove);
- uint (*iop_trylock)(xfs_log_item_t *);
+ uint (*iop_push)(struct xfs_log_item *, struct list_head *);
void (*iop_unlock)(xfs_log_item_t *);
xfs_lsn_t (*iop_committed)(xfs_log_item_t *, xfs_lsn_t);
- void (*iop_push)(xfs_log_item_t *);
- bool (*iop_pushbuf)(xfs_log_item_t *);
void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t);
};
@@ -357,20 +355,18 @@ struct xfs_item_ops {
#define IOP_FORMAT(ip,vp) (*(ip)->li_ops->iop_format)(ip, vp)
#define IOP_PIN(ip) (*(ip)->li_ops->iop_pin)(ip)
#define IOP_UNPIN(ip, remove) (*(ip)->li_ops->iop_unpin)(ip, remove)
-#define IOP_TRYLOCK(ip) (*(ip)->li_ops->iop_trylock)(ip)
+#define IOP_PUSH(ip, list) (*(ip)->li_ops->iop_push)(ip, list)
#define IOP_UNLOCK(ip) (*(ip)->li_ops->iop_unlock)(ip)
#define IOP_COMMITTED(ip, lsn) (*(ip)->li_ops->iop_committed)(ip, lsn)
-#define IOP_PUSH(ip) (*(ip)->li_ops->iop_push)(ip)
-#define IOP_PUSHBUF(ip) (*(ip)->li_ops->iop_pushbuf)(ip)
#define IOP_COMMITTING(ip, lsn) (*(ip)->li_ops->iop_committing)(ip, lsn)
/*
- * Return values for the IOP_TRYLOCK() routines.
+ * Return values for the IOP_PUSH() routines.
*/
-#define XFS_ITEM_SUCCESS 0
-#define XFS_ITEM_PINNED 1
-#define XFS_ITEM_LOCKED 2
-#define XFS_ITEM_PUSHBUF 3
+#define XFS_ITEM_SUCCESS 0
+#define XFS_ITEM_PINNED 1
+#define XFS_ITEM_LOCKED 2
+#define XFS_ITEM_FLUSHING 3
/*
* This is the type of function which can be given to xfs_trans_callback()
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 0425ca16738b..49d9cde33bb3 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -364,29 +364,31 @@ xfsaild_push(
xfs_log_item_t *lip;
xfs_lsn_t lsn;
xfs_lsn_t target;
- long tout = 10;
+ long tout;
int stuck = 0;
+ int flushing = 0;
int count = 0;
- int push_xfsbufd = 0;
/*
- * If last time we ran we encountered pinned items, force the log first
- * and wait for it before pushing again.
+ * If we encountered pinned items or did not finish writing out all
+ * buffers the last time we ran, force the log first and wait for it
+ * before pushing again.
*/
- spin_lock(&ailp->xa_lock);
- if (ailp->xa_last_pushed_lsn == 0 && ailp->xa_log_flush &&
- !list_empty(&ailp->xa_ail)) {
+ if (ailp->xa_log_flush && ailp->xa_last_pushed_lsn == 0 &&
+ (!list_empty_careful(&ailp->xa_buf_list) ||
+ xfs_ail_min_lsn(ailp))) {
ailp->xa_log_flush = 0;
- spin_unlock(&ailp->xa_lock);
+
XFS_STATS_INC(xs_push_ail_flush);
xfs_log_force(mp, XFS_LOG_SYNC);
- spin_lock(&ailp->xa_lock);
}
+ spin_lock(&ailp->xa_lock);
lip = xfs_trans_ail_cursor_first(ailp, &cur, ailp->xa_last_pushed_lsn);
if (!lip) {
/*
- * AIL is empty or our push has reached the end.
+ * If the AIL is empty or our push has reached the end we are
+ * done now.
*/
xfs_trans_ail_cursor_done(ailp, &cur);
spin_unlock(&ailp->xa_lock);
@@ -395,55 +397,42 @@ xfsaild_push(
XFS_STATS_INC(xs_push_ail);
- /*
- * While the item we are looking at is below the given threshold
- * try to flush it out. We'd like not to stop until we've at least
- * tried to push on everything in the AIL with an LSN less than
- * the given threshold.
- *
- * However, we will stop after a certain number of pushes and wait
- * for a reduced timeout to fire before pushing further. This
- * prevents use from spinning when we can't do anything or there is
- * lots of contention on the AIL lists.
- */
lsn = lip->li_lsn;
target = ailp->xa_target;
while ((XFS_LSN_CMP(lip->li_lsn, target) <= 0)) {
int lock_result;
+
/*
- * If we can lock the item without sleeping, unlock the AIL
- * lock and flush the item. Then re-grab the AIL lock so we
- * can look for the next item on the AIL. List changes are
- * handled by the AIL lookup functions internally
- *
- * If we can't lock the item, either its holder will flush it
- * or it is already being flushed or it is being relogged. In
- * any of these case it is being taken care of and we can just
- * skip to the next item in the list.
+ * Note that IOP_PUSH may unlock and reacquire the AIL lock. We
+ * rely on the AIL cursor implementation to be able to deal with
+ * the dropped lock.
*/
- lock_result = IOP_TRYLOCK(lip);
- spin_unlock(&ailp->xa_lock);
+ lock_result = IOP_PUSH(lip, &ailp->xa_buf_list);
switch (lock_result) {
case XFS_ITEM_SUCCESS:
XFS_STATS_INC(xs_push_ail_success);
trace_xfs_ail_push(lip);
- IOP_PUSH(lip);
ailp->xa_last_pushed_lsn = lsn;
break;
- case XFS_ITEM_PUSHBUF:
- XFS_STATS_INC(xs_push_ail_pushbuf);
- trace_xfs_ail_pushbuf(lip);
-
- if (!IOP_PUSHBUF(lip)) {
- trace_xfs_ail_pushbuf_pinned(lip);
- stuck++;
- ailp->xa_log_flush++;
- } else {
- ailp->xa_last_pushed_lsn = lsn;
- }
- push_xfsbufd = 1;
+ case XFS_ITEM_FLUSHING:
+ /*
+ * The item or its backing buffer is already beeing
+ * flushed. The typical reason for that is that an
+ * inode buffer is locked because we already pushed the
+ * updates to it as part of inode clustering.
+ *
+ * We do not want to to stop flushing just because lots
+ * of items are already beeing flushed, but we need to
+ * re-try the flushing relatively soon if most of the
+ * AIL is beeing flushed.
+ */
+ XFS_STATS_INC(xs_push_ail_flushing);
+ trace_xfs_ail_flushing(lip);
+
+ flushing++;
+ ailp->xa_last_pushed_lsn = lsn;
break;
case XFS_ITEM_PINNED:
@@ -453,23 +442,22 @@ xfsaild_push(
stuck++;
ailp->xa_log_flush++;
break;
-
case XFS_ITEM_LOCKED:
XFS_STATS_INC(xs_push_ail_locked);
trace_xfs_ail_locked(lip);
+
stuck++;
break;
-
default:
ASSERT(0);
break;
}
- spin_lock(&ailp->xa_lock);
count++;
/*
* Are there too many items we can't do anything with?
+ *
* If we we are skipping too many items because we can't flush
* them or they are already being flushed, we back off and
* given them time to complete whatever operation is being
@@ -491,42 +479,36 @@ xfsaild_push(
xfs_trans_ail_cursor_done(ailp, &cur);
spin_unlock(&ailp->xa_lock);
- if (push_xfsbufd) {
- /* we've got delayed write buffers to flush */
- wake_up_process(mp->m_ddev_targp->bt_task);
- }
+ if (xfs_buf_delwri_submit_nowait(&ailp->xa_buf_list))
+ ailp->xa_log_flush++;
- /* assume we have more work to do in a short while */
+ if (!count || XFS_LSN_CMP(lsn, target) >= 0) {
out_done:
- if (!count) {
- /* We're past our target or empty, so idle */
- ailp->xa_last_pushed_lsn = 0;
- ailp->xa_log_flush = 0;
-
- tout = 50;
- } else if (XFS_LSN_CMP(lsn, target) >= 0) {
/*
- * We reached the target so wait a bit longer for I/O to
- * complete and remove pushed items from the AIL before we
- * start the next scan from the start of the AIL.
+ * We reached the target or the AIL is empty, so wait a bit
+ * longer for I/O to complete and remove pushed items from the
+ * AIL before we start the next scan from the start of the AIL.
*/
tout = 50;
ailp->xa_last_pushed_lsn = 0;
- } else if ((stuck * 100) / count > 90) {
+ } else if (((stuck + flushing) * 100) / count > 90) {
/*
- * Either there is a lot of contention on the AIL or we
- * are stuck due to operations in progress. "Stuck" in this
- * case is defined as >90% of the items we tried to push
- * were stuck.
+ * Either there is a lot of contention on the AIL or we are
+ * stuck due to operations in progress. "Stuck" in this case
+ * is defined as >90% of the items we tried to push were stuck.
*
* Backoff a bit more to allow some I/O to complete before
- * restarting from the start of the AIL. This prevents us
- * from spinning on the same items, and if they are pinned will
- * all the restart to issue a log force to unpin the stuck
- * items.
+ * restarting from the start of the AIL. This prevents us from
+ * spinning on the same items, and if they are pinned will all
+ * the restart to issue a log force to unpin the stuck items.
*/
tout = 20;
ailp->xa_last_pushed_lsn = 0;
+ } else {
+ /*
+ * Assume we have more work to do in a short while.
+ */
+ tout = 10;
}
return tout;
@@ -539,6 +521,8 @@ xfsaild(
struct xfs_ail *ailp = data;
long tout = 0; /* milliseconds */
+ current->flags |= PF_MEMALLOC;
+
while (!kthread_should_stop()) {
if (tout && tout <= 20)
__set_current_state(TASK_KILLABLE);
@@ -794,6 +778,7 @@ xfs_trans_ail_init(
INIT_LIST_HEAD(&ailp->xa_ail);
INIT_LIST_HEAD(&ailp->xa_cursors);
spin_lock_init(&ailp->xa_lock);
+ INIT_LIST_HEAD(&ailp->xa_buf_list);
init_waitqueue_head(&ailp->xa_empty);
ailp->xa_task = kthread_run(xfsaild, ailp, "xfsaild/%s",
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 296a7995a007..9132d162c4b8 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -165,14 +165,6 @@ xfs_trans_get_buf(xfs_trans_t *tp,
XFS_BUF_DONE(bp);
}
- /*
- * If the buffer is stale then it was binval'ed
- * since last read. This doesn't matter since the
- * caller isn't allowed to use the data anyway.
- */
- else if (XFS_BUF_ISSTALE(bp))
- ASSERT(!XFS_BUF_ISDELAYWRITE(bp));
-
ASSERT(bp->b_transp == tp);
bip = bp->b_fspriv;
ASSERT(bip != NULL);
@@ -418,19 +410,6 @@ xfs_trans_read_buf(
return 0;
shutdown_abort:
- /*
- * the theory here is that buffer is good but we're
- * bailing out because the filesystem is being forcibly
- * shut down. So we should leave the b_flags alone since
- * the buffer's not staled and just get out.
- */
-#if defined(DEBUG)
- if (XFS_BUF_ISSTALE(bp) && XFS_BUF_ISDELAYWRITE(bp))
- xfs_notice(mp, "about to pop assert, bp == 0x%p", bp);
-#endif
- ASSERT((bp->b_flags & (XBF_STALE|XBF_DELWRI)) !=
- (XBF_STALE|XBF_DELWRI));
-
trace_xfs_trans_read_buf_shut(bp, _RET_IP_);
xfs_buf_relse(bp);
*bpp = NULL;
@@ -649,22 +628,33 @@ xfs_trans_log_buf(xfs_trans_t *tp,
/*
- * This called to invalidate a buffer that is being used within
- * a transaction. Typically this is because the blocks in the
- * buffer are being freed, so we need to prevent it from being
- * written out when we're done. Allowing it to be written again
- * might overwrite data in the free blocks if they are reallocated
- * to a file.
+ * Invalidate a buffer that is being used within a transaction.
+ *
+ * Typically this is because the blocks in the buffer are being freed, so we
+ * need to prevent it from being written out when we're done. Allowing it
+ * to be written again might overwrite data in the free blocks if they are
+ * reallocated to a file.
*
- * We prevent the buffer from being written out by clearing the
- * B_DELWRI flag. We can't always
- * get rid of the buf log item at this point, though, because
- * the buffer may still be pinned by another transaction. If that
- * is the case, then we'll wait until the buffer is committed to
- * disk for the last time (we can tell by the ref count) and
- * free it in xfs_buf_item_unpin(). Until it is cleaned up we
- * will keep the buffer locked so that the buffer and buf log item
- * are not reused.
+ * We prevent the buffer from being written out by marking it stale. We can't
+ * get rid of the buf log item at this point because the buffer may still be
+ * pinned by another transaction. If that is the case, then we'll wait until
+ * the buffer is committed to disk for the last time (we can tell by the ref
+ * count) and free it in xfs_buf_item_unpin(). Until that happens we will
+ * keep the buffer locked so that the buffer and buf log item are not reused.
+ *
+ * We also set the XFS_BLF_CANCEL flag in the buf log format structure and log
+ * the buf item. This will be used at recovery time to determine that copies
+ * of the buffer in the log before this should not be replayed.
+ *
+ * We mark the item descriptor and the transaction dirty so that we'll hold
+ * the buffer until after the commit.
+ *
+ * Since we're invalidating the buffer, we also clear the state about which
+ * parts of the buffer have been logged. We also clear the flag indicating
+ * that this is an inode buffer since the data in the buffer will no longer
+ * be valid.
+ *
+ * We set the stale bit in the buffer as well since we're getting rid of it.
*/
void
xfs_trans_binval(
@@ -684,7 +674,6 @@ xfs_trans_binval(
* If the buffer is already invalidated, then
* just return.
*/
- ASSERT(!(XFS_BUF_ISDELAYWRITE(bp)));
ASSERT(XFS_BUF_ISSTALE(bp));
ASSERT(!(bip->bli_flags & (XFS_BLI_LOGGED | XFS_BLI_DIRTY)));
ASSERT(!(bip->bli_format.blf_flags & XFS_BLF_INODE_BUF));
@@ -694,27 +683,8 @@ xfs_trans_binval(
return;
}
- /*
- * Clear the dirty bit in the buffer and set the STALE flag
- * in the buf log item. The STALE flag will be used in
- * xfs_buf_item_unpin() to determine if it should clean up
- * when the last reference to the buf item is given up.
- * We set the XFS_BLF_CANCEL flag in the buf log format structure
- * and log the buf item. This will be used at recovery time
- * to determine that copies of the buffer in the log before
- * this should not be replayed.
- * We mark the item descriptor and the transaction dirty so
- * that we'll hold the buffer until after the commit.
- *
- * Since we're invalidating the buffer, we also clear the state
- * about which parts of the buffer have been logged. We also
- * clear the flag indicating that this is an inode buffer since
- * the data in the buffer will no longer be valid.
- *
- * We set the stale bit in the buffer as well since we're getting
- * rid of it.
- */
xfs_buf_stale(bp);
+
bip->bli_flags |= XFS_BLI_STALE;
bip->bli_flags &= ~(XFS_BLI_INODE_BUF | XFS_BLI_LOGGED | XFS_BLI_DIRTY);
bip->bli_format.blf_flags &= ~XFS_BLF_INODE_BUF;
diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
index 218304a8cdc7..f72bdd48a5c1 100644
--- a/fs/xfs/xfs_trans_priv.h
+++ b/fs/xfs/xfs_trans_priv.h
@@ -71,6 +71,7 @@ struct xfs_ail {
spinlock_t xa_lock;
xfs_lsn_t xa_last_pushed_lsn;
int xa_log_flush;
+ struct list_head xa_buf_list;
wait_queue_head_t xa_empty;
};
--
cgit v1.2.3
From 04913fdd91f342e537005ef1233f98068b925a7f Mon Sep 17 00:00:00 2001
From: Dave Chinner <dchinner@redhat.com>
Date: Mon, 23 Apr 2012 15:58:41 +1000
Subject: xfs: pass shutdown method into xfs_trans_ail_delete_bulk
xfs_trans_ail_delete_bulk() can be called from different contexts so
if the item is not in the AIL we need different shutdown for each
context. Pass in the shutdown method needed so the correct action
can be taken.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>
---
fs/xfs/xfs_buf_item.c | 4 ++--
fs/xfs/xfs_dquot.c | 5 +++--
fs/xfs/xfs_dquot_item.c | 2 +-
fs/xfs/xfs_extfree_item.c | 3 ++-
fs/xfs/xfs_inode.c | 4 ++--
fs/xfs/xfs_inode_item.c | 23 +++++++++++++----------
fs/xfs/xfs_inode_item.h | 2 +-
fs/xfs/xfs_log_recover.c | 3 ++-
fs/xfs/xfs_sync.c | 2 +-
fs/xfs/xfs_trans_ail.c | 5 +++--
fs/xfs/xfs_trans_priv.h | 8 +++++---
11 files changed, 35 insertions(+), 26 deletions(-)
(limited to 'fs/xfs/xfs_sync.c')
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index fb20f384b566..7f0abeaf919c 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -454,7 +454,7 @@ xfs_buf_item_unpin(
bp->b_iodone = NULL;
} else {
spin_lock(&ailp->xa_lock);
- xfs_trans_ail_delete(ailp, (xfs_log_item_t *)bip);
+ xfs_trans_ail_delete(ailp, lip, SHUTDOWN_LOG_IO_ERROR);
xfs_buf_item_relse(bp);
ASSERT(bp->b_fspriv == NULL);
}
@@ -1006,6 +1006,6 @@ xfs_buf_iodone(
* Either way, AIL is useless if we're forcing a shutdown.
*/
spin_lock(&ailp->xa_lock);
- xfs_trans_ail_delete(ailp, lip);
+ xfs_trans_ail_delete(ailp, lip, SHUTDOWN_CORRUPT_INCORE);
xfs_buf_item_free(BUF_ITEM(lip));
}
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 65b8aa37622e..7bf38556254e 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -857,7 +857,7 @@ xfs_qm_dqflush_done(
/* xfs_trans_ail_delete() drops the AIL lock. */
spin_lock(&ailp->xa_lock);
if (lip->li_lsn == qip->qli_flush_lsn)
- xfs_trans_ail_delete(ailp, lip);
+ xfs_trans_ail_delete(ailp, lip, SHUTDOWN_CORRUPT_INCORE);
else
spin_unlock(&ailp->xa_lock);
}
@@ -909,7 +909,8 @@ xfs_qm_dqflush(
spin_lock(&mp->m_ail->xa_lock);
if (lip->li_flags & XFS_LI_IN_AIL)
- xfs_trans_ail_delete(mp->m_ail, lip);
+ xfs_trans_ail_delete(mp->m_ail, lip,
+ SHUTDOWN_CORRUPT_INCORE);
else
spin_unlock(&mp->m_ail->xa_lock);
error = XFS_ERROR(EIO);
diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c
index 9c5d58d24e54..aa6a2a6bd9a8 100644
--- a/fs/xfs/xfs_dquot_item.c
+++ b/fs/xfs/xfs_dquot_item.c
@@ -384,7 +384,7 @@ xfs_qm_qoffend_logitem_committed(
* xfs_trans_ail_delete() drops the AIL lock.
*/
spin_lock(&ailp->xa_lock);
- xfs_trans_ail_delete(ailp, (xfs_log_item_t *)qfs);
+ xfs_trans_ail_delete(ailp, &qfs->qql_item, SHUTDOWN_LOG_IO_ERROR);
kmem_free(qfs);
kmem_free(qfe);
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index 9549ef179e06..2960fc104cb7 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -64,7 +64,8 @@ __xfs_efi_release(
if (!test_and_clear_bit(XFS_EFI_COMMITTED, &efip->efi_flags)) {
spin_lock(&ailp->xa_lock);
/* xfs_trans_ail_delete() drops the AIL lock. */
- xfs_trans_ail_delete(ailp, &efip->efi_item);
+ xfs_trans_ail_delete(ailp, &efip->efi_item,
+ SHUTDOWN_LOG_IO_ERROR);
xfs_efi_item_free(efip);
}
}
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index acd846d808b2..65d7d994d499 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2377,7 +2377,7 @@ cluster_corrupt_out:
/*
* Unlocks the flush lock
*/
- xfs_iflush_abort(iq);
+ xfs_iflush_abort(iq, false);
kmem_free(ilist);
xfs_perag_put(pag);
return XFS_ERROR(EFSCORRUPTED);
@@ -2482,7 +2482,7 @@ abort_out:
/*
* Unlocks the flush lock
*/
- xfs_iflush_abort(ip);
+ xfs_iflush_abort(ip, false);
return error;
}
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 8aaebb2f9efa..3f96a949d963 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -777,7 +777,8 @@ xfs_iflush_done(
ASSERT(i <= need_ail);
}
/* xfs_trans_ail_delete_bulk() drops the AIL lock. */
- xfs_trans_ail_delete_bulk(ailp, log_items, i);
+ xfs_trans_ail_delete_bulk(ailp, log_items, i,
+ SHUTDOWN_CORRUPT_INCORE);
}
@@ -798,16 +799,15 @@ xfs_iflush_done(
}
/*
- * This is the inode flushing abort routine. It is called
- * from xfs_iflush when the filesystem is shutting down to clean
- * up the inode state.
- * It is responsible for removing the inode item
- * from the AIL if it has not been re-logged, and unlocking the inode's
- * flush lock.
+ * This is the inode flushing abort routine. It is called from xfs_iflush when
+ * the filesystem is shutting down to clean up the inode state. It is
+ * responsible for removing the inode item from the AIL if it has not been
+ * re-logged, and unlocking the inode's flush lock.
*/
void
xfs_iflush_abort(
- xfs_inode_t *ip)
+ xfs_inode_t *ip,
+ bool stale)
{
xfs_inode_log_item_t *iip = ip->i_itemp;
@@ -817,7 +817,10 @@ xfs_iflush_abort(
spin_lock(&ailp->xa_lock);
if (iip->ili_item.li_flags & XFS_LI_IN_AIL) {
/* xfs_trans_ail_delete() drops the AIL lock. */
- xfs_trans_ail_delete(ailp, (xfs_log_item_t *)iip);
+ xfs_trans_ail_delete(ailp, &iip->ili_item,
+ stale ?
+ SHUTDOWN_LOG_IO_ERROR :
+ SHUTDOWN_CORRUPT_INCORE);
} else
spin_unlock(&ailp->xa_lock);
}
@@ -844,7 +847,7 @@ xfs_istale_done(
struct xfs_buf *bp,
struct xfs_log_item *lip)
{
- xfs_iflush_abort(INODE_ITEM(lip)->ili_inode);
+ xfs_iflush_abort(INODE_ITEM(lip)->ili_inode, true);
}
/*
diff --git a/fs/xfs/xfs_inode_item.h b/fs/xfs/xfs_inode_item.h
index 41d61c3b7a36..376d4d0b2635 100644
--- a/fs/xfs/xfs_inode_item.h
+++ b/fs/xfs/xfs_inode_item.h
@@ -165,7 +165,7 @@ 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_done(struct xfs_buf *, struct xfs_log_item *);
extern void xfs_istale_done(struct xfs_buf *, struct xfs_log_item *);
-extern void xfs_iflush_abort(struct xfs_inode *);
+extern void xfs_iflush_abort(struct xfs_inode *, bool);
extern int xfs_inode_item_format_convert(xfs_log_iovec_t *,
xfs_inode_log_format_t *);
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 5e864a9c0ccf..396e3bfd0496 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2645,7 +2645,8 @@ xlog_recover_efd_pass2(
* xfs_trans_ail_delete() drops the
* AIL lock.
*/
- xfs_trans_ail_delete(ailp, lip);
+ xfs_trans_ail_delete(ailp, lip,
+ SHUTDOWN_CORRUPT_INCORE);
xfs_efi_item_free(efip);
spin_lock(&ailp->xa_lock);
break;
diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index cdb644fd0bd1..24180cd86264 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -684,7 +684,7 @@ restart:
goto reclaim;
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_iunpin_wait(ip);
- xfs_iflush_abort(ip);
+ xfs_iflush_abort(ip, false);
goto reclaim;
}
if (xfs_ipincount(ip)) {
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 959374a0d028..2c0db81f035d 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -707,7 +707,8 @@ void
xfs_trans_ail_delete_bulk(
struct xfs_ail *ailp,
struct xfs_log_item **log_items,
- int nr_items) __releases(ailp->xa_lock)
+ int nr_items,
+ int shutdown_type) __releases(ailp->xa_lock)
{
xfs_log_item_t *mlip;
int mlip_changed = 0;
@@ -725,7 +726,7 @@ xfs_trans_ail_delete_bulk(
xfs_alert_tag(mp, XFS_PTAG_AILDELETE,
"%s: attempting to delete a log item that is not in the AIL",
__func__);
- xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+ xfs_force_shutdown(mp, shutdown_type);
}
return;
}
diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
index f72bdd48a5c1..fb62377d1cbc 100644
--- a/fs/xfs/xfs_trans_priv.h
+++ b/fs/xfs/xfs_trans_priv.h
@@ -92,14 +92,16 @@ xfs_trans_ail_update(
}
void xfs_trans_ail_delete_bulk(struct xfs_ail *ailp,
- struct xfs_log_item **log_items, int nr_items)
+ struct xfs_log_item **log_items, int nr_items,
+ int shutdown_type)
__releases(ailp->xa_lock);
static inline void
xfs_trans_ail_delete(
struct xfs_ail *ailp,
- xfs_log_item_t *lip) __releases(ailp->xa_lock)
+ xfs_log_item_t *lip,
+ int shutdown_type) __releases(ailp->xa_lock)
{
- xfs_trans_ail_delete_bulk(ailp, &lip, 1);
+ xfs_trans_ail_delete_bulk(ailp, &lip, 1, shutdown_type);
}
void xfs_ail_push(struct xfs_ail *, xfs_lsn_t);
--
cgit v1.2.3
From ad1e95c54eb3980ab2b4683fba29ad0ef954ec51 Mon Sep 17 00:00:00 2001
From: Dave Chinner <dchinner@redhat.com>
Date: Mon, 23 Apr 2012 15:59:04 +1000
Subject: xfs: clean up xfs_bit.h includes
With the removal of xfs_rw.h and other changes over time, xfs_bit.h
is being included in many files that don't actually need it. Clean
up the includes as necessary.
Also move the only-used-once xfs_ialloc_find_free() static inline
function out of a header file that is widely included to reduce
the number of needless dependencies on xfs_bit.h.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>
---
fs/xfs/xfs_alloc_btree.c | 1 -
fs/xfs/xfs_aops.c | 1 -
fs/xfs/xfs_dfrag.c | 1 -
fs/xfs/xfs_dir2.c | 1 -
fs/xfs/xfs_dquot_item.c | 1 -
fs/xfs/xfs_file.c | 1 -
fs/xfs/xfs_fsops.c | 1 -
fs/xfs/xfs_ialloc.c | 7 +++++++
fs/xfs/xfs_ialloc.h | 9 ---------
fs/xfs/xfs_iget.c | 1 -
fs/xfs/xfs_inode.c | 1 -
fs/xfs/xfs_inode_item.c | 1 -
fs/xfs/xfs_ioctl.c | 1 -
fs/xfs/xfs_ioctl32.c | 1 -
fs/xfs/xfs_iomap.c | 1 -
fs/xfs/xfs_iops.c | 1 -
fs/xfs/xfs_itable.c | 1 -
fs/xfs/xfs_log.c | 1 -
fs/xfs/xfs_log_cil.c | 1 -
fs/xfs/xfs_qm_bhv.c | 1 -
fs/xfs/xfs_super.c | 1 -
fs/xfs/xfs_sync.c | 1 -
fs/xfs/xfs_trace.c | 1 -
fs/xfs/xfs_trans.c | 1 -
fs/xfs/xfs_trans_buf.c | 1 -
fs/xfs/xfs_trans_dquot.c | 1 -
fs/xfs/xfs_trans_inode.c | 1 -
fs/xfs/xfs_utils.c | 1 -
28 files changed, 7 insertions(+), 35 deletions(-)
(limited to 'fs/xfs/xfs_sync.c')
diff --git a/fs/xfs/xfs_alloc_btree.c b/fs/xfs/xfs_alloc_btree.c
index 68ebabc388c6..f1647caace8f 100644
--- a/fs/xfs/xfs_alloc_btree.c
+++ b/fs/xfs/xfs_alloc_btree.c
@@ -18,7 +18,6 @@
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index f03c9b401ce5..ae31c313a79e 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -16,7 +16,6 @@
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "xfs.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index f39205f5c772..e00de08dc8ac 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -18,7 +18,6 @@
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c
index a2e27010c7fb..67a250c36d41 100644
--- a/fs/xfs/xfs_dir2.c
+++ b/fs/xfs/xfs_dir2.c
@@ -18,7 +18,6 @@
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c
index 9610e52e5b4b..57aa4b03720c 100644
--- a/fs/xfs/xfs_dquot_item.c
+++ b/fs/xfs/xfs_dquot_item.c
@@ -17,7 +17,6 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 415e97add439..51fc2cf07d5e 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -17,7 +17,6 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 537c2aeb1ad2..75593d9bd70f 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -18,7 +18,6 @@
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index d094a23e1030..177a21a7ac49 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -609,6 +609,13 @@ xfs_ialloc_get_rec(
/*
* Visible inode allocation functions.
*/
+/*
+ * Find a free (set) bit in the inode bitmask.
+ */
+static inline int xfs_ialloc_find_free(xfs_inofree_t *fp)
+{
+ return xfs_lowbit64(*fp);
+}
/*
* Allocate an inode on disk.
diff --git a/fs/xfs/xfs_ialloc.h b/fs/xfs/xfs_ialloc.h
index 666a037398d6..65ac57c8063c 100644
--- a/fs/xfs/xfs_ialloc.h
+++ b/fs/xfs/xfs_ialloc.h
@@ -46,15 +46,6 @@ xfs_make_iptr(struct xfs_mount *mp, struct xfs_buf *b, int o)
(xfs_buf_offset(b, o << (mp)->m_sb.sb_inodelog));
}
-/*
- * Find a free (set) bit in the inode bitmask.
- */
-static inline int xfs_ialloc_find_free(xfs_inofree_t *fp)
-{
- return xfs_lowbit64(*fp);
-}
-
-
/*
* Allocate an inode on disk.
* Mode is used to tell whether the new inode will need space, and whether
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index ab89ca7fdb95..7f81397eeec2 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -19,7 +19,6 @@
#include "xfs_fs.h"
#include "xfs_types.h"
#include "xfs_acl.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index c6fb5f0577b8..72ec1a4cc477 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -20,7 +20,6 @@
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index a8d5fddc7200..6cdbf90c6f7b 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -18,7 +18,6 @@
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 706029fd1a7e..3a05a41b5d76 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -17,7 +17,6 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index c79fa5f1f9d4..c4f2da0d2bf5 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -22,7 +22,6 @@
#include <asm/uaccess.h>
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index d3a4a8d10440..69c6e251c012 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -17,7 +17,6 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index e7a6660e19fb..1a25fd802798 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -18,7 +18,6 @@
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_acl.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index acc2bf264dab..eff577a9b67f 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -18,7 +18,6 @@
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 97e489b90f29..9b10a15295a2 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -18,7 +18,6 @@
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 601ccf02618a..7d6197c58493 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -18,7 +18,6 @@
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c
index cd705296c3b7..6b39115bf145 100644
--- a/fs/xfs/xfs_qm_bhv.c
+++ b/fs/xfs/xfs_qm_bhv.c
@@ -17,7 +17,6 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 49197e24d8db..2fcfd5b0b046 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -17,7 +17,6 @@
*/
#include "xfs.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index 24180cd86264..d2422683ed76 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -18,7 +18,6 @@
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
index 0115378b444e..624bedd81357 100644
--- a/fs/xfs/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -18,7 +18,6 @@
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index f674855c8dc9..cdf896fcbfa4 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -19,7 +19,6 @@
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 743d7a5835f3..d250afaeb70c 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -18,7 +18,6 @@
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
diff --git a/fs/xfs/xfs_trans_dquot.c b/fs/xfs/xfs_trans_dquot.c
index 72236b0d0731..bcb60542fcf1 100644
--- a/fs/xfs/xfs_trans_dquot.c
+++ b/fs/xfs/xfs_trans_dquot.c
@@ -17,7 +17,6 @@
*/
#include "xfs.h"
#include "xfs_fs.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c
index 82fd5206f1e8..d2eee20d5f5b 100644
--- a/fs/xfs/xfs_trans_inode.c
+++ b/fs/xfs/xfs_trans_inode.c
@@ -18,7 +18,6 @@
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
diff --git a/fs/xfs/xfs_utils.c b/fs/xfs/xfs_utils.c
index 073223176566..4e5b9ad5cb97 100644
--- a/fs/xfs/xfs_utils.c
+++ b/fs/xfs/xfs_utils.c
@@ -18,7 +18,6 @@
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
-#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
--
cgit v1.2.3
From 1307bbd2af67283131728637e9489002adb26f10 Mon Sep 17 00:00:00 2001
From: Ben Myers <bpm@sgi.com>
Date: Tue, 15 May 2012 14:26:55 -0500
Subject: xfs: protect xfs_sync_worker with s_umount semaphore
xfs_sync_worker checks the MS_ACTIVE flag in s_flags to avoid doing
work during mount and unmount. This flag can be cleared by unmount
after the xfs_sync_worker checks it but before the work is completed.
The has caused crashes in the completion handler for the dummy
transaction commited by xfs_sync_worker:
PID: 27544 TASK: ffff88013544e040 CPU: 3 COMMAND: "kworker/3:0"
#0 [ffff88016fdff930] machine_kexec at ffffffff810244e9
#1 [ffff88016fdff9a0] crash_kexec at ffffffff8108d053
#2 [ffff88016fdffa70] oops_end at ffffffff813ad1b8
#3 [ffff88016fdffaa0] no_context at ffffffff8102bd48
#4 [ffff88016fdffaf0] __bad_area_nosemaphore at ffffffff8102c04d
#5 [ffff88016fdffb40] bad_area_nosemaphore at ffffffff8102c12e
#6 [ffff88016fdffb50] do_page_fault at ffffffff813afaee
#7 [ffff88016fdffc60] page_fault at ffffffff813ac635
[exception RIP: xlog_get_lowest_lsn+0x30]
RIP: ffffffffa04a9910 RSP: ffff88016fdffd10 RFLAGS: 00010246
RAX: ffffc90014e48000 RBX: ffff88014d879980 RCX: ffff88014d879980
RDX: ffff8802214ee4c0 RSI: 0000000000000000 RDI: 0000000000000000
RBP: ffff88016fdffd10 R8: ffff88014d879a80 R9: 0000000000000000
R10: 0000000000000001 R11: 0000000000000000 R12: ffff8802214ee400
R13: ffff88014d879980 R14: 0000000000000000 R15: ffff88022fd96605
ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018
#8 [ffff88016fdffd18] xlog_state_do_callback at ffffffffa04aa186 [xfs]
#9 [ffff88016fdffd98] xlog_state_done_syncing at ffffffffa04aa568 [xfs]
Protect xfs_sync_worker by using the s_umount semaphore at the read
level to provide exclusion with unmount while work is progressing.
Reviewed-by: Mark Tinguely <tinguely@sgi.com>
Signed-off-by: Ben Myers <bpm@sgi.com>
---
fs/xfs/xfs_sync.c | 29 ++++++++++++++++-------------
1 file changed, 16 insertions(+), 13 deletions(-)
(limited to 'fs/xfs/xfs_sync.c')
diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index d2422683ed76..c9d3409c5ca3 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -386,20 +386,23 @@ xfs_sync_worker(
* We shouldn't write/force the log if we are in the mount/unmount
* process or on a read only filesystem. The workqueue still needs to be
* active in both cases, however, because it is used for inode reclaim
- * during these times. hence use the MS_ACTIVE flag to avoid doing
- * anything in these periods.
+ * during these times. Use the s_umount semaphore to provide exclusion
+ * with unmount.
*/
- if (!(mp->m_super->s_flags & MS_ACTIVE) &&
- !(mp->m_flags & XFS_MOUNT_RDONLY)) {
- /* dgc: errors ignored here */
- if (mp->m_super->s_frozen == SB_UNFROZEN &&
- xfs_log_need_covered(mp))
- error = xfs_fs_log_dummy(mp);
- else
- xfs_log_force(mp, 0);
-
- /* start pushing all the metadata that is currently dirty */
- xfs_ail_push_all(mp->m_ail);
+ if (down_read_trylock(&mp->m_super->s_umount)) {
+ if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
+ /* dgc: errors ignored here */
+ if (mp->m_super->s_frozen == SB_UNFROZEN &&
+ xfs_log_need_covered(mp))
+ error = xfs_fs_log_dummy(mp);
+ else
+ xfs_log_force(mp, 0);
+
+ /* start pushing all the metadata that is currently
+ * dirty */
+ xfs_ail_push_all(mp->m_ail);
+ }
+ up_read(&mp->m_super->s_umount);
}
/* queue us up again */
--
cgit v1.2.3