From 8b2180b3bf0338625cab07da6543acb436df9c40 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 17 Aug 2016 08:31:33 +1000 Subject: [PATCH] xfs: don't invalidate whole file on DAX read/write When we do DAX IO, we try to invalidate the entire page cache held on the file. This is incorrect as it will trash the entire mapping tree that now tracks dirty state in exceptional entries in the radix tree slots. What we are trying to do is remove cached pages (e.g from reads into holes) that sit in the radix tree over the range we are about to write to. Hence we should just limit the invalidation to the range we are about to overwrite. Reported-by: Jan Kara Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/xfs_file.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index ed95e5bb04e6..e612a0233710 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -741,9 +741,20 @@ xfs_file_dax_write( * page is inserted into the pagecache when we have to serve a write * fault on a hole. It should never be dirtied and can simply be * dropped from the pagecache once we get real data for the page. + * + * XXX: This is racy against mmap, and there's nothing we can do about + * it. dax_do_io() should really do this invalidation internally as + * it will know if we've allocated over a holei for this specific IO and + * if so it needs to update the mapping tree and invalidate existing + * PTEs over the newly allocated range. Remove this invalidation when + * dax_do_io() is fixed up. */ if (mapping->nrpages) { - ret = invalidate_inode_pages2(mapping); + loff_t end = iocb->ki_pos + iov_iter_count(from) - 1; + + ret = invalidate_inode_pages2_range(mapping, + iocb->ki_pos >> PAGE_SHIFT, + end >> PAGE_SHIFT); WARN_ON_ONCE(ret); }