xfs: block callers of xfs_flush_inodes() correctly

xfs_flush_inodes() currently uses a magic timeout to wait for
some inodes to be flushed before returning. This isn't
really reliable but used to be the best that could be done
due to deadlock potential of waiting for the entire flush.

Now the inode flush is safe to execute while we hold page
and inode locks, we can wait for all the inodes to flush
synchronously. Convert the wait mechanism to a completion
to do this efficiently. This should remove all remaining
spurious ENOSPC errors from the delayed allocation reservation
path.

This is extracted almost line for line from a larger patch
from Mikulas Patocka.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>

diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index 73cf8dc197389b75f19c68af1375fd5a16709c96..f7ba76633c292396d88f0bd4ce3fc0dffe1734f4 100644 (file)
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -404,7 +404,8 @@ STATIC void
 xfs_syncd_queue_work(
        struct xfs_mount *mp,
        void            *data,
-       void            (*syncer)(struct xfs_mount *, void *))
+       void            (*syncer)(struct xfs_mount *, void *),
+       struct completion *completion)
 {
        struct xfs_sync_work *work;
 
@@ -413,6 +414,7 @@ xfs_syncd_queue_work(
        work->w_syncer = syncer;
        work->w_data = data;
        work->w_mount = mp;
+       work->w_completion = completion;
        spin_lock(&mp->m_sync_lock);
        list_add_tail(&work->w_list, &mp->m_sync_list);
        spin_unlock(&mp->m_sync_lock);
@@ -441,10 +443,11 @@ xfs_flush_inodes(
        xfs_inode_t     *ip)
 {
        struct inode    *inode = VFS_I(ip);
+       DECLARE_COMPLETION_ONSTACK(completion);
 
        igrab(inode);
-       xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inodes_work);
-       delay(msecs_to_jiffies(500));
+       xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inodes_work, &completion);
+       wait_for_completion(&completion);
        xfs_log_force(ip->i_mount, (xfs_lsn_t)0, XFS_LOG_FORCE|XFS_LOG_SYNC);
 }
 
@@ -514,6 +517,8 @@ xfssyncd(
                        list_del(&work->w_list);
                        if (work == &mp->m_sync_work)
                                continue;
+                       if (work->w_completion)
+                               complete(work->w_completion);
                        kmem_free(work);
                }
        }
@@ -527,6 +532,7 @@ xfs_syncd_init(
 {
        mp->m_sync_work.w_syncer = xfs_sync_worker;
        mp->m_sync_work.w_mount = mp;
+       mp->m_sync_work.w_completion = NULL;
        mp->m_sync_task = kthread_run(xfssyncd, mp, "xfssyncd");
        if (IS_ERR(mp->m_sync_task))
                return -PTR_ERR(mp->m_sync_task);

diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
index 6e83a35626ed3e86656a2483ca61c8e49502f159..308d5bf6dfbda281376be436cfd0434085ccdaec 100644 (file)
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -26,6 +26,7 @@ typedef struct xfs_sync_work {
        struct xfs_mount        *w_mount;
        void                    *w_data;        /* syncer routine argument */
        void                    (*w_syncer)(struct xfs_mount *, void *);
+       struct completion       *w_completion;
 } xfs_sync_work_t;
 
 #define SYNC_ATTR              0x0001  /* sync attributes */