summaryrefslogtreecommitdiff
path: root/fs/xfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs')
-rw-r--r--fs/xfs/xfs_aops.c3
-rw-r--r--fs/xfs/xfs_buf_item.c3
-rw-r--r--fs/xfs/xfs_dquot_item.c10
-rw-r--r--fs/xfs/xfs_inode_item.c10
-rw-r--r--fs/xfs/xfs_iops.c14
-rw-r--r--fs/xfs/xfs_linux.h2
-rw-r--r--fs/xfs/xfs_super.c49
-rw-r--r--fs/xfs/xfs_trans.h2
-rw-r--r--fs/xfs/xfs_trans_ail.c83
-rw-r--r--fs/xfs/xfs_trans_priv.h8
10 files changed, 93 insertions, 91 deletions
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 63e971e2b837..8c37dde4c521 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1300,6 +1300,7 @@ xfs_end_io_direct_write(
bool is_async)
{
struct xfs_ioend *ioend = iocb->private;
+ struct inode *inode = ioend->io_inode;
/*
* blockdev_direct_IO can return an error even after the I/O
@@ -1331,7 +1332,7 @@ xfs_end_io_direct_write(
}
/* XXX: probably should move into the real I/O completion handler */
- inode_dio_done(ioend->io_inode);
+ inode_dio_done(inode);
}
STATIC ssize_t
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index cac2ecfa6746..ef43fce519a1 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -629,7 +629,7 @@ xfs_buf_item_push(
* the xfsbufd to get this buffer written. We have to unlock the buffer
* to allow the xfsbufd to write it, too.
*/
-STATIC void
+STATIC bool
xfs_buf_item_pushbuf(
struct xfs_log_item *lip)
{
@@ -643,6 +643,7 @@ xfs_buf_item_pushbuf(
xfs_buf_delwri_promote(bp);
xfs_buf_relse(bp);
+ return true;
}
STATIC void
diff --git a/fs/xfs/xfs_dquot_item.c b/fs/xfs/xfs_dquot_item.c
index 9e0e2fa3f2c8..bb3f71d236d2 100644
--- a/fs/xfs/xfs_dquot_item.c
+++ b/fs/xfs/xfs_dquot_item.c
@@ -183,13 +183,14 @@ xfs_qm_dqunpin_wait(
* search the buffer cache can be a time consuming thing, and AIL lock is a
* spinlock.
*/
-STATIC void
+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));
@@ -201,17 +202,20 @@ xfs_qm_dquot_logitem_pushbuf(
if (completion_done(&dqp->q_flush) ||
!(lip->li_flags & XFS_LI_IN_AIL)) {
xfs_dqunlock(dqp);
- return;
+ 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;
+ 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;
}
/*
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 588406dc6a35..836ad80d4f2b 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -708,13 +708,14 @@ xfs_inode_item_committed(
* 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 void
+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));
@@ -725,7 +726,7 @@ xfs_inode_item_pushbuf(
if (completion_done(&ip->i_flush) ||
!(lip->li_flags & XFS_LI_IN_AIL)) {
xfs_iunlock(ip, XFS_ILOCK_SHARED);
- return;
+ return true;
}
bp = xfs_incore(ip->i_mount->m_ddev_targp, iip->ili_format.ilf_blkno,
@@ -733,10 +734,13 @@ xfs_inode_item_pushbuf(
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (!bp)
- return;
+ 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;
}
/*
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index b9c172b3fbbe..673704fab748 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -70,9 +70,8 @@ xfs_synchronize_times(
}
/*
- * If the linux inode is valid, mark it dirty.
- * Used when committing a dirty inode into a transaction so that
- * the inode will get written back by the linux code
+ * If the linux inode is valid, mark it dirty, else mark the dirty state
+ * in the XFS inode to make sure we pick it up when reclaiming the inode.
*/
void
xfs_mark_inode_dirty_sync(
@@ -82,6 +81,10 @@ xfs_mark_inode_dirty_sync(
if (!(inode->i_state & (I_WILL_FREE|I_FREEING)))
mark_inode_dirty_sync(inode);
+ else {
+ barrier();
+ ip->i_update_core = 1;
+ }
}
void
@@ -92,6 +95,11 @@ xfs_mark_inode_dirty(
if (!(inode->i_state & (I_WILL_FREE|I_FREEING)))
mark_inode_dirty(inode);
+ else {
+ barrier();
+ ip->i_update_core = 1;
+ }
+
}
/*
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index 1e8a45e74c3e..828662f70d64 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -68,6 +68,8 @@
#include <linux/ctype.h>
#include <linux/writeback.h>
#include <linux/capability.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
#include <linux/list_sort.h>
#include <asm/page.h>
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 9a72dda58bd0..5cf06b85fd9d 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -356,6 +356,8 @@ xfs_parseargs(
mp->m_flags |= XFS_MOUNT_DELAYLOG;
} else if (!strcmp(this_char, MNTOPT_NODELAYLOG)) {
mp->m_flags &= ~XFS_MOUNT_DELAYLOG;
+ xfs_warn(mp,
+ "nodelaylog is deprecated and will be removed in Linux 3.3");
} else if (!strcmp(this_char, MNTOPT_DISCARD)) {
mp->m_flags |= XFS_MOUNT_DISCARD;
} else if (!strcmp(this_char, MNTOPT_NODISCARD)) {
@@ -877,33 +879,17 @@ xfs_log_inode(
struct xfs_trans *tp;
int error;
- xfs_iunlock(ip, XFS_ILOCK_SHARED);
tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0);
-
if (error) {
xfs_trans_cancel(tp, 0);
- /* we need to return with the lock hold shared */
- xfs_ilock(ip, XFS_ILOCK_SHARED);
return error;
}
xfs_ilock(ip, XFS_ILOCK_EXCL);
-
- /*
- * Note - it's possible that we might have pushed ourselves out of the
- * way during trans_reserve which would flush the inode. But there's
- * no guarantee that the inode buffer has actually gone out yet (it's
- * delwri). Plus the buffer could be pinned anyway if it's part of
- * an inode in another recent transaction. So we play it safe and
- * fire off the transaction anyway.
- */
- xfs_trans_ijoin(tp, ip);
+ xfs_trans_ijoin_ref(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
- error = xfs_trans_commit(tp, 0);
- xfs_ilock_demote(ip, XFS_ILOCK_EXCL);
-
- return error;
+ return xfs_trans_commit(tp, 0);
}
STATIC int
@@ -918,7 +904,9 @@ xfs_fs_write_inode(
trace_xfs_write_inode(ip);
if (XFS_FORCED_SHUTDOWN(mp))
- return XFS_ERROR(EIO);
+ return -XFS_ERROR(EIO);
+ if (!ip->i_update_core)
+ return 0;
if (wbc->sync_mode == WB_SYNC_ALL) {
/*
@@ -929,12 +917,10 @@ xfs_fs_write_inode(
* of synchronous log foces dramatically.
*/
xfs_ioend_wait(ip);
- xfs_ilock(ip, XFS_ILOCK_SHARED);
- if (ip->i_update_core) {
- error = xfs_log_inode(ip);
- if (error)
- goto out_unlock;
- }
+ error = xfs_log_inode(ip);
+ if (error)
+ goto out;
+ return 0;
} else {
/*
* We make this non-blocking if the inode is contended, return
@@ -1666,24 +1652,13 @@ xfs_init_workqueues(void)
*/
xfs_syncd_wq = alloc_workqueue("xfssyncd", WQ_CPU_INTENSIVE, 8);
if (!xfs_syncd_wq)
- goto out;
-
- xfs_ail_wq = alloc_workqueue("xfsail", WQ_CPU_INTENSIVE, 8);
- if (!xfs_ail_wq)
- goto out_destroy_syncd;
-
+ return -ENOMEM;
return 0;
-
-out_destroy_syncd:
- destroy_workqueue(xfs_syncd_wq);
-out:
- return -ENOMEM;
}
STATIC void
xfs_destroy_workqueues(void)
{
- destroy_workqueue(xfs_ail_wq);
destroy_workqueue(xfs_syncd_wq);
}
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 06a9759b6352..53597f4db9b5 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -350,7 +350,7 @@ typedef struct xfs_item_ops {
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 *);
- void (*iop_pushbuf)(xfs_log_item_t *);
+ bool (*iop_pushbuf)(xfs_log_item_t *);
void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t);
} xfs_item_ops_t;
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index c15aa29fa169..3a1e7ca54c2d 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -28,8 +28,6 @@
#include "xfs_trans_priv.h"
#include "xfs_error.h"
-struct workqueue_struct *xfs_ail_wq; /* AIL workqueue */
-
#ifdef DEBUG
/*
* Check that the list is sorted as it should be.
@@ -356,16 +354,10 @@ xfs_ail_delete(
xfs_trans_ail_cursor_clear(ailp, lip);
}
-/*
- * xfs_ail_worker does the work of pushing on the AIL. It will requeue itself
- * to run at a later time if there is more work to do to complete the push.
- */
-STATIC void
-xfs_ail_worker(
- struct work_struct *work)
+static long
+xfsaild_push(
+ struct xfs_ail *ailp)
{
- struct xfs_ail *ailp = container_of(to_delayed_work(work),
- struct xfs_ail, xa_work);
xfs_mount_t *mp = ailp->xa_mount;
struct xfs_ail_cursor cur;
xfs_log_item_t *lip;
@@ -427,8 +419,13 @@ xfs_ail_worker(
case XFS_ITEM_PUSHBUF:
XFS_STATS_INC(xs_push_ail_pushbuf);
- IOP_PUSHBUF(lip);
- ailp->xa_last_pushed_lsn = lsn;
+
+ if (!IOP_PUSHBUF(lip)) {
+ stuck++;
+ flush_log = 1;
+ } else {
+ ailp->xa_last_pushed_lsn = lsn;
+ }
push_xfsbufd = 1;
break;
@@ -440,7 +437,6 @@ xfs_ail_worker(
case XFS_ITEM_LOCKED:
XFS_STATS_INC(xs_push_ail_locked);
- ailp->xa_last_pushed_lsn = lsn;
stuck++;
break;
@@ -501,20 +497,6 @@ out_done:
/* We're past our target or empty, so idle */
ailp->xa_last_pushed_lsn = 0;
- /*
- * We clear the XFS_AIL_PUSHING_BIT first before checking
- * whether the target has changed. If the target has changed,
- * this pushes the requeue race directly onto the result of the
- * atomic test/set bit, so we are guaranteed that either the
- * the pusher that changed the target or ourselves will requeue
- * the work (but not both).
- */
- clear_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags);
- smp_rmb();
- if (XFS_LSN_CMP(ailp->xa_target, target) == 0 ||
- test_and_set_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags))
- return;
-
tout = 50;
} else if (XFS_LSN_CMP(lsn, target) >= 0) {
/*
@@ -537,9 +519,30 @@ out_done:
tout = 20;
}
- /* There is more to do, requeue us. */
- queue_delayed_work(xfs_syncd_wq, &ailp->xa_work,
- msecs_to_jiffies(tout));
+ return tout;
+}
+
+static int
+xfsaild(
+ void *data)
+{
+ struct xfs_ail *ailp = data;
+ long tout = 0; /* milliseconds */
+
+ while (!kthread_should_stop()) {
+ if (tout && tout <= 20)
+ __set_current_state(TASK_KILLABLE);
+ else
+ __set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(tout ?
+ msecs_to_jiffies(tout) : MAX_SCHEDULE_TIMEOUT);
+
+ try_to_freeze();
+
+ tout = xfsaild_push(ailp);
+ }
+
+ return 0;
}
/*
@@ -574,8 +577,9 @@ xfs_ail_push(
*/
smp_wmb();
xfs_trans_ail_copy_lsn(ailp, &ailp->xa_target, &threshold_lsn);
- if (!test_and_set_bit(XFS_AIL_PUSHING_BIT, &ailp->xa_flags))
- queue_delayed_work(xfs_syncd_wq, &ailp->xa_work, 0);
+ smp_wmb();
+
+ wake_up_process(ailp->xa_task);
}
/*
@@ -813,9 +817,18 @@ xfs_trans_ail_init(
INIT_LIST_HEAD(&ailp->xa_ail);
INIT_LIST_HEAD(&ailp->xa_cursors);
spin_lock_init(&ailp->xa_lock);
- INIT_DELAYED_WORK(&ailp->xa_work, xfs_ail_worker);
+
+ ailp->xa_task = kthread_run(xfsaild, ailp, "xfsaild/%s",
+ ailp->xa_mount->m_fsname);
+ if (IS_ERR(ailp->xa_task))
+ goto out_free_ailp;
+
mp->m_ail = ailp;
return 0;
+
+out_free_ailp:
+ kmem_free(ailp);
+ return ENOMEM;
}
void
@@ -824,6 +837,6 @@ xfs_trans_ail_destroy(
{
struct xfs_ail *ailp = mp->m_ail;
- cancel_delayed_work_sync(&ailp->xa_work);
+ kthread_stop(ailp->xa_task);
kmem_free(ailp);
}
diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
index 212946b97239..22750b5e4a8f 100644
--- a/fs/xfs/xfs_trans_priv.h
+++ b/fs/xfs/xfs_trans_priv.h
@@ -64,23 +64,17 @@ struct xfs_ail_cursor {
*/
struct xfs_ail {
struct xfs_mount *xa_mount;
+ struct task_struct *xa_task;
struct list_head xa_ail;
xfs_lsn_t xa_target;
struct list_head xa_cursors;
spinlock_t xa_lock;
- struct delayed_work xa_work;
xfs_lsn_t xa_last_pushed_lsn;
- unsigned long xa_flags;
};
-#define XFS_AIL_PUSHING_BIT 0
-
/*
* From xfs_trans_ail.c
*/
-
-extern struct workqueue_struct *xfs_ail_wq; /* AIL workqueue */
-
void xfs_trans_ail_update_bulk(struct xfs_ail *ailp,
struct xfs_ail_cursor *cur,
struct xfs_log_item **log_items, int nr_items,
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-20 20:02:46 +0300