#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"
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.
*/
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)
* 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
/* 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;
}
-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
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
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
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. Use the MS_ACTIVE flag to avoid doing anything
+ * during mount. Doing work during unmount is avoided by calling
+ * cancel_delayed_work_sync on this work queue before tearing down
+ * the ail and the log in xfs_log_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))
else
xfs_log_force(mp, 0);
- /* start pushing all the metadata that is currently dirty */
+ /* start pushing all the metadata that is currently
+ * dirty */
xfs_ail_push_all(mp->m_ail);
}
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,
INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
xfs_syncd_queue_sync(mp);
- xfs_syncd_queue_reclaim(mp);
return 0;
}
}
/*
- * 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
* --------------- ---------- ---------------
* 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.
*
- * 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. 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
struct xfs_perag *pag,
int sync_mode)
{
- int error;
+ struct xfs_buf *bp = NULL;
+ int error;
restart:
error = 0;
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);
}
goto reclaim;
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_iunpin_wait(ip);
+ xfs_iflush_abort(ip, false);
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))
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.
*
- * 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);
- 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;
+ 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;
}
- /*
- * 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) {
+ error = xfs_bwrite(bp);
+ xfs_buf_relse(bp);
}
-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);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
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;
}
/*
projects / GitHub / mt8127 / android_kernel_alcatel_ttab.git / blobdiff