summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_inode.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-10-14 14:06:06 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-10-14 14:06:06 -0700
commit2fc61f25fb296827387a5f01129dbc00cbe3ca58 (patch)
tree5659c402b3a5f357158a7d8e4f284db15ee69e7f /fs/xfs/xfs_inode.c
parent37187df45af7d28d27b5c130c23f407ca9dbefa2 (diff)
parentfe341eb151ec0ba80fb74edd6201fc78e5232b6b (diff)
Merge tag 'xfs-5.10-merge-2' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux
Pull xfs updates from Darrick Wong: "The biggest changes are two new features for the ondisk metadata: one to record the sizes of the inode btrees in the AG to increase redundancy checks and to improve mount times; and a second new feature to support timestamps until the year 2486. We also fixed a problem where reflinking into a file that requires synchronous writes wouldn't actually flush the updates to disk; clean up a fair amount of cruft; and started fixing some bugs in the realtime volume code. Summary: - Clean up the buffer ioend calling path so that the retry strategy isn't quite so scattered everywhere. - Clean up m_sb_bp handling. - New feature: storing inode btree counts in the AGI to speed up certain mount time per-AG block reservation operatoins and add a little more metadata redundancy. - New feature: Widen inode timestamps and quota grace expiration timestamps to support dates through the year 2486. - Get rid of more of our custom buffer allocation API wrappers. - Use a proper VLA for shortform xattr structure namevals. - Force the log after reflinking or deduping into a file that is opened with O_SYNC or O_DSYNC. - Fix some math errors in the realtime allocator" * tag 'xfs-5.10-merge-2' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (42 commits) xfs: ensure that fpunch, fcollapse, and finsert operations are aligned to rt extent size xfs: make sure the rt allocator doesn't run off the end xfs: Remove unneeded semicolon xfs: force the log after remapping a synchronous-writes file xfs: Convert xfs_attr_sf macros to inline functions xfs: Use variable-size array for nameval in xfs_attr_sf_entry xfs: Remove typedef xfs_attr_shortform_t xfs: remove typedef xfs_attr_sf_entry_t xfs: Remove kmem_zalloc_large() xfs: enable big timestamps xfs: trace timestamp limits xfs: widen ondisk quota expiration timestamps to handle y2038+ xfs: widen ondisk inode timestamps to deal with y2038+ xfs: redefine xfs_ictimestamp_t xfs: redefine xfs_timestamp_t xfs: move xfs_log_dinode_to_disk to the log recovery code xfs: refactor quota timestamp coding xfs: refactor default quota grace period setting code xfs: refactor quota expiration timer modification xfs: explicitly define inode timestamp range ...
Diffstat (limited to 'fs/xfs/xfs_inode.c')
-rw-r--r--fs/xfs/xfs_inode.c83
1 files changed, 32 insertions, 51 deletions
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index c06129cffba9..49624973eecc 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -598,22 +598,6 @@ xfs_lock_two_inodes(
}
}
-void
-__xfs_iflock(
- struct xfs_inode *ip)
-{
- wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_IFLOCK_BIT);
- DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IFLOCK_BIT);
-
- do {
- prepare_to_wait_exclusive(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
- if (xfs_isiflocked(ip))
- io_schedule();
- } while (!xfs_iflock_nowait(ip));
-
- finish_wait(wq, &wait.wq_entry);
-}
-
STATIC uint
_xfs_dic2xflags(
uint16_t di_flags,
@@ -840,7 +824,7 @@ xfs_ialloc(
if (xfs_sb_version_has_v3inode(&mp->m_sb)) {
inode_set_iversion(inode, 1);
- ip->i_d.di_flags2 = 0;
+ ip->i_d.di_flags2 = mp->m_ino_geo.new_diflags2;
ip->i_d.di_cowextsize = 0;
ip->i_d.di_crtime = tv;
}
@@ -2531,11 +2515,8 @@ retry:
* valid, the wrong inode or stale.
*/
spin_lock(&ip->i_flags_lock);
- if (ip->i_ino != inum || __xfs_iflags_test(ip, XFS_ISTALE)) {
- spin_unlock(&ip->i_flags_lock);
- rcu_read_unlock();
- return;
- }
+ if (ip->i_ino != inum || __xfs_iflags_test(ip, XFS_ISTALE))
+ goto out_iflags_unlock;
/*
* Don't try to lock/unlock the current inode, but we _cannot_ skip the
@@ -2552,16 +2533,14 @@ retry:
}
}
ip->i_flags |= XFS_ISTALE;
- spin_unlock(&ip->i_flags_lock);
- rcu_read_unlock();
/*
- * If we can't get the flush lock, the inode is already attached. All
+ * If the inode is flushing, it is already attached to the buffer. All
* we needed to do here is mark the inode stale so buffer IO completion
* will remove it from the AIL.
*/
iip = ip->i_itemp;
- if (!xfs_iflock_nowait(ip)) {
+ if (__xfs_iflags_test(ip, XFS_IFLUSHING)) {
ASSERT(!list_empty(&iip->ili_item.li_bio_list));
ASSERT(iip->ili_last_fields);
goto out_iunlock;
@@ -2573,10 +2552,12 @@ retry:
* commit as the flock synchronises removal of the inode from the
* cluster buffer against inode reclaim.
*/
- if (!iip || list_empty(&iip->ili_item.li_bio_list)) {
- xfs_ifunlock(ip);
+ if (!iip || list_empty(&iip->ili_item.li_bio_list))
goto out_iunlock;
- }
+
+ __xfs_iflags_set(ip, XFS_IFLUSHING);
+ spin_unlock(&ip->i_flags_lock);
+ rcu_read_unlock();
/* we have a dirty inode in memory that has not yet been flushed. */
spin_lock(&iip->ili_lock);
@@ -2586,9 +2567,16 @@ retry:
spin_unlock(&iip->ili_lock);
ASSERT(iip->ili_last_fields);
+ if (ip != free_ip)
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
+ return;
+
out_iunlock:
if (ip != free_ip)
xfs_iunlock(ip, XFS_ILOCK_EXCL);
+out_iflags_unlock:
+ spin_unlock(&ip->i_flags_lock);
+ rcu_read_unlock();
}
/*
@@ -2631,8 +2619,9 @@ xfs_ifree_cluster(
/*
* We obtain and lock the backing buffer first in the process
- * here, as we have to ensure that any dirty inode that we
- * can't get the flush lock on is attached to the buffer.
+ * here to ensure dirty inodes attached to the buffer remain in
+ * the flushing state while we mark them stale.
+ *
* If we scan the in-memory inodes first, then buffer IO can
* complete before we get a lock on it, and hence we may fail
* to mark all the active inodes on the buffer stale.
@@ -2717,7 +2706,7 @@ xfs_ifree(
VFS_I(ip)->i_mode = 0; /* mark incore inode as free */
ip->i_d.di_flags = 0;
- ip->i_d.di_flags2 = 0;
+ ip->i_d.di_flags2 = ip->i_mount->m_ino_geo.new_diflags2;
ip->i_d.di_dmevmask = 0;
ip->i_d.di_forkoff = 0; /* mark the attr fork not in use */
ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
@@ -3443,7 +3432,7 @@ xfs_iflush(
int error;
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
- ASSERT(xfs_isiflocked(ip));
+ ASSERT(xfs_iflags_test(ip, XFS_IFLUSHING));
ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
ip->i_df.if_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
ASSERT(iip->ili_item.li_buf == bp);
@@ -3553,8 +3542,8 @@ xfs_iflush(
*
* What we do is move the bits to the ili_last_fields field. When
* logging the inode, these bits are moved back to the ili_fields field.
- * In the xfs_iflush_done() routine we clear ili_last_fields, since we
- * know that the information those bits represent is permanently on
+ * In the xfs_buf_inode_iodone() routine we clear ili_last_fields, since
+ * we know that the information those bits represent is permanently on
* disk. As long as the flush completes before the inode is logged
* again, then both ili_fields and ili_last_fields will be cleared.
*/
@@ -3568,7 +3557,7 @@ flush_out:
/*
* Store the current LSN of the inode so that we can tell whether the
- * item has moved in the AIL from xfs_iflush_done().
+ * item has moved in the AIL from xfs_buf_inode_iodone().
*/
xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
&iip->ili_item.li_lsn);
@@ -3613,7 +3602,7 @@ xfs_iflush_cluster(
/*
* Quick and dirty check to avoid locks if possible.
*/
- if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLOCK))
+ if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLUSHING))
continue;
if (xfs_ipincount(ip))
continue;
@@ -3627,7 +3616,7 @@ xfs_iflush_cluster(
*/
spin_lock(&ip->i_flags_lock);
ASSERT(!__xfs_iflags_test(ip, XFS_ISTALE));
- if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLOCK)) {
+ if (__xfs_iflags_test(ip, XFS_IRECLAIM | XFS_IFLUSHING)) {
spin_unlock(&ip->i_flags_lock);
continue;
}
@@ -3635,24 +3624,17 @@ xfs_iflush_cluster(
/*
* ILOCK will pin the inode against reclaim and prevent
* concurrent transactions modifying the inode while we are
- * flushing the inode.
+ * flushing the inode. If we get the lock, set the flushing
+ * state before we drop the i_flags_lock.
*/
if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
spin_unlock(&ip->i_flags_lock);
continue;
}
+ __xfs_iflags_set(ip, XFS_IFLUSHING);
spin_unlock(&ip->i_flags_lock);
/*
- * Skip inodes that are already flush locked as they have
- * already been written to the buffer.
- */
- if (!xfs_iflock_nowait(ip)) {
- xfs_iunlock(ip, XFS_ILOCK_SHARED);
- continue;
- }
-
- /*
* Abort flushing this inode if we are shut down because the
* inode may not currently be in the AIL. This can occur when
* log I/O failure unpins the inode without inserting into the
@@ -3661,7 +3643,6 @@ xfs_iflush_cluster(
*/
if (XFS_FORCED_SHUTDOWN(mp)) {
xfs_iunpin_wait(ip);
- /* xfs_iflush_abort() drops the flush lock */
xfs_iflush_abort(ip);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
error = -EIO;
@@ -3670,7 +3651,7 @@ xfs_iflush_cluster(
/* don't block waiting on a log force to unpin dirty inodes */
if (xfs_ipincount(ip)) {
- xfs_ifunlock(ip);
+ xfs_iflags_clear(ip, XFS_IFLUSHING);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
continue;
}
@@ -3678,7 +3659,7 @@ xfs_iflush_cluster(
if (!xfs_inode_clean(ip))
error = xfs_iflush(ip, bp);
else
- xfs_ifunlock(ip);
+ xfs_iflags_clear(ip, XFS_IFLUSHING);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (error)
break;