pNFS: Fix a deadlock when coalescing writes and returning the layout

Consider the following deadlock:

Process P1	Process P2		Process P3
==========	==========		==========
					lock_page(page)

		lseg = pnfs_update_layout(inode)

lo = NFS_I(inode)->layout
pnfs_error_mark_layout_for_return(lo)

		lock_page(page)

					lseg = pnfs_update_layout(inode)

In this scenario,
- P1 has declared the layout to be in error, but P2 holds a reference to
  a layout segment on that inode, so the layoutreturn is deferred.
- P2 is waiting for a page lock held by P3.
- P3 is asking for a new layout segment, but is blocked waiting
  for the layoutreturn.

The fix is to ensure that pnfs_error_mark_layout_for_return() does
not set the NFS_LAYOUT_RETURN flag, which blocks P3. Instead, we allow
the latter to call LAYOUTGET so that it can make progress and unblock
P2.

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
This commit is contained in:
Trond Myklebust 2017-05-01 17:06:56 -04:00
parent 5466d21411
commit 61f454e30c
1 changed files with 0 additions and 2 deletions

View File

@ -2063,8 +2063,6 @@ void pnfs_error_mark_layout_for_return(struct inode *inode,
return;
}
pnfs_set_plh_return_info(lo, range.iomode, 0);
/* Block LAYOUTGET */
set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
/*
* mark all matching lsegs so that we are sure to have no live
* segments at hand when sending layoutreturn. See pnfs_put_lseg()