[PATCH V2] Re-dirty pages on ENOSPC when converting delayed allocations

[Lachlan McIlroy <lachlan@xxxxxxx>]

If we get an error in xfs_page_state_convert() - and it's not EAGAIN - then
we throw away the dirty page without converting the delayed allocation.  This
leaves delayed allocations that can never be removed and confuses code that
expects a flush of the file to clear them.  We need to re-dirty the page on
error so we can try again later or report that the flush failed.

This change is needed to handle the condition where we are at ENOSPC and we
exhaust the reserved block pool (because many transactions are executing
concurrently) and calls to xfs_trans_reserve() start failing with ENOSPC
errors.

Version 2 wont return EAGAIN from xfs_vm_writepage() and also converts an
ENOSPC error to an EAGAIN for asynchronous writeback to avoid setting an
error in the inode mapping when we don't need to.

--- a/fs/xfs/linux-2.6/xfs_aops.c       2008-10-07 17:02:04.000000000 +1000
+++ b/fs/xfs/linux-2.6/xfs_aops.c       2008-10-07 17:58:04.000000000 +1000
@@ -1147,16 +1147,6 @@ error:
        if (iohead)
                xfs_cancel_ioend(iohead);

-       /*
-        * If it's delalloc and we have nowhere to put it,
-        * throw it away, unless the lower layers told
-        * us to try again.
-        */
-       if (err != -EAGAIN) {
-               if (!unmapped)
-                       block_invalidatepage(page, 0);
-               ClearPageUptodate(page);
-       }
        return err;
}

@@ -1185,7 +1175,7 @@ xfs_vm_writepage(
        struct page             *page,
        struct writeback_control *wbc)
{
-       int                     error;
+       int                     error = 0;
        int                     need_trans;
        int                     delalloc, unmapped, unwritten;
        struct inode            *inode = page->mapping->host;
@@ -1231,19 +1221,16 @@ xfs_vm_writepage(
         * to real space and flush out to disk.
         */
        error = xfs_page_state_convert(inode, page, wbc, 1, unmapped);
-       if (error == -EAGAIN)
-               goto out_fail;
        if (unlikely(error < 0))
-               goto out_unlock;
+               goto out_fail;

        return 0;

out_fail:
        redirty_page_for_writepage(wbc, page);
        unlock_page(page);
-       return 0;
-out_unlock:
-       unlock_page(page);
+       if (error == -EAGAIN)
+               error = 0;
        return error;
}

--- a/fs/xfs/xfs_iomap.c        2008-10-07 17:02:04.000000000 +1000
+++ b/fs/xfs/xfs_iomap.c        2008-10-07 17:58:04.000000000 +1000
@@ -269,6 +269,8 @@ xfs_iomap(

                error = xfs_iomap_write_allocate(ip, offset, count,
                                                 &imap, &nimaps);
+               if ((flags & BMAPI_TRYLOCK) && error == ENOSPC)
+                       error = EAGAIN;
                break;
        }