[XFS] avoid all reclaimable inodes in xfs_sync_inodes_ag

If we are syncing data in xfs_sync_inodes_ag(), the VFS inode must still
be referencable as the dirty data state is carried on the VFS inode. hence
if we can't get a reference via igrab(), the inode must be in reclaim
which implies that it has no dirty data attached.

Leave such inodes to the reclaim code to flush the dirty inode state to
disk and so avoid attempting to access the VFS inode when it may not exist
in xfs_sync_inodes_ag().

Version 4:
o don't reference linux inode until after igrab() succeeds

Version 3:
o converted unlock/rele to an xfs_iput() call.

Version 2:
o change igrab logic to be more linear
o remove initial reclaimable inode check now that we are using
  igrab() failure to find reclaimable inodes
o assert that igrab failure occurs only on reclaimable inodes
o clean up inode locking - only grab the iolock if we are doing
  a SYNC_DELWRI call and we have a dirty inode.

SGI-PV: 987246

SGI-Modid: xfs-linux-melb:xfs-kern:32391a

Signed-off-by: David Chinner <david@fromorbit.com>
Signed-off-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Peter Leckie <pleckie@sgi.com>
Signed-off-by: Lachlan McIlroy <lachlan@sgi.com>

diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index ee1648b..fb5cca3 100644 (file)
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -63,25 +63,16 @@ xfs_sync_inodes_ag(
        int             error = 0;
        int             last_error = 0;
        int             fflag = XFS_B_ASYNC;
-       int             lock_flags = XFS_ILOCK_SHARED;
 
        if (flags & SYNC_DELWRI)
                fflag = XFS_B_DELWRI;
        if (flags & SYNC_WAIT)
                fflag = 0;              /* synchronous overrides all */
 
-       if (flags & SYNC_DELWRI) {
-               /*
-                * We need the I/O lock if we're going to call any of
-                * the flush/inval routines.
-                */
-               lock_flags |= XFS_IOLOCK_SHARED;
-       }
-
        do {
                struct inode    *inode;
-               boolean_t       inode_refed;
                xfs_inode_t     *ip = NULL;
+               int             lock_flags = XFS_ILOCK_SHARED;
 
                /*
                 * use a gang lookup to find the next inode in the tree
@@ -109,22 +100,6 @@ xfs_sync_inodes_ag(
                        break;
                }
 
-               /*
-                * skip inodes in reclaim. Let xfs_syncsub do that for
-                * us so we don't need to worry.
-                */
-               if (xfs_iflags_test(ip, (XFS_IRECLAIM|XFS_IRECLAIMABLE))) {
-                       read_unlock(&pag->pag_ici_lock);
-                       continue;
-               }
-
-               /* bad inodes are dealt with elsewhere */
-               inode = VFS_I(ip);
-               if (is_bad_inode(inode)) {
-                       read_unlock(&pag->pag_ici_lock);
-                       continue;
-               }
-
                /* nothing to sync during shutdown */
                if (XFS_FORCED_SHUTDOWN(mp)) {
                        read_unlock(&pag->pag_ici_lock);
@@ -132,42 +107,34 @@ xfs_sync_inodes_ag(
                }
 
                /*
-                * If we can't get a reference on the VFS_I, the inode must be
-                * in reclaim. If we can get the inode lock without blocking,
-                * it is safe to flush the inode because we hold the tree lock
-                * and xfs_iextract will block right now. Hence if we lock the
-                * inode while holding the tree lock, xfs_ireclaim() is
-                * guaranteed to block on the inode lock we now hold and hence
-                * it is safe to reference the inode until we drop the inode
-                * locks completely.
+                * If we can't get a reference on the inode, it must be
+                * in reclaim. Leave it for the reclaim code to flush.
                 */
-               inode_refed = B_FALSE;
-               if (igrab(inode)) {
-                       read_unlock(&pag->pag_ici_lock);
-                       xfs_ilock(ip, lock_flags);
-                       inode_refed = B_TRUE;
-               } else {
-                       if (!xfs_ilock_nowait(ip, lock_flags)) {
-                               /* leave it to reclaim */
-                               read_unlock(&pag->pag_ici_lock);
-                               continue;
-                       }
+               inode = VFS_I(ip);
+               if (!igrab(inode)) {
                        read_unlock(&pag->pag_ici_lock);
+                       continue;
+               }
+               read_unlock(&pag->pag_ici_lock);
+
+               /* bad inodes are dealt with elsewhere */
+               if (is_bad_inode(inode)) {
+                       IRELE(ip);
+                       continue;
                }
 
                /*
                 * If we have to flush data or wait for I/O completion
-                * we need to drop the ilock that we currently hold.
-                * If we need to drop the lock, insert a marker if we
-                * have not already done so.
+                * we need to hold the iolock.
                 */
                if ((flags & SYNC_DELWRI) && VN_DIRTY(inode)) {
-                       xfs_iunlock(ip, XFS_ILOCK_SHARED);
+                       xfs_ilock(ip, XFS_IOLOCK_SHARED);
+                       lock_flags |= XFS_IOLOCK_SHARED;
                        error = xfs_flush_pages(ip, 0, -1, fflag, FI_NONE);
                        if (flags & SYNC_IOWAIT)
                                vn_iowait(ip);
-                       xfs_ilock(ip, XFS_ILOCK_SHARED);
                }
+               xfs_ilock(ip, XFS_ILOCK_SHARED);
 
                if ((flags & SYNC_ATTR) && !xfs_inode_clean(ip)) {
                        if (flags & SYNC_WAIT) {
@@ -183,13 +150,7 @@ xfs_sync_inodes_ag(
                                        xfs_ifunlock(ip);
                        }
                }
-
-               if (lock_flags)
-                       xfs_iunlock(ip, lock_flags);
-
-               if (inode_refed) {
-                       IRELE(ip);
-               }
+               xfs_iput(ip, lock_flags);
 
                if (error)
                        last_error = error;