From b2442c5a7fe92cca08437070c8a45a7aa0d1703e Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 29 Jul 2015 11:48:00 +1000 Subject: xfs: call dax_fault on read page faults for DAX When modifying the patch series to handle the XFS MMAP_LOCK nesting of page faults, I botched the conversion of the read page fault path, and so it is only every calling through the page cache. Re-add the necessary __dax_fault() call for such files. Because the get_blocks callback on read faults may not set up the mapping buffer correctly to allow unwritten extent completion to be run, we need to allow callers of __dax_fault() to pass a null complete_unwritten() callback. The DAX code always zeros the unwritten page when it is read faulted so there are no stale data exposure issues with not doing the conversion. The only downside will be the potential for increased CPU overhead on repeated read faults of the same page. If this proves to be a problem, then the filesystem needs to fix it's get_block callback and provide a convert_unwritten() callback to the read fault path. Signed-off-by: Dave Chinner Reviewed-by: Matthew Wilcox Reviewed-by: Brian Foster Signed-off-by: Dave Chinner --- fs/xfs/xfs_file.c | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'fs/xfs/xfs_file.c') diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index f0e8249722d4..db4acc1c3e73 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1514,18 +1514,27 @@ xfs_filemap_fault( struct vm_area_struct *vma, struct vm_fault *vmf) { - struct xfs_inode *ip = XFS_I(file_inode(vma->vm_file)); + struct inode *inode = file_inode(vma->vm_file); int ret; - trace_xfs_filemap_fault(ip); + trace_xfs_filemap_fault(XFS_I(inode)); /* DAX can shortcut the normal fault path on write faults! */ - if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(VFS_I(ip))) + if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(inode)) return xfs_filemap_page_mkwrite(vma, vmf); - xfs_ilock(ip, XFS_MMAPLOCK_SHARED); - ret = filemap_fault(vma, vmf); - xfs_iunlock(ip, XFS_MMAPLOCK_SHARED); + xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED); + if (IS_DAX(inode)) { + /* + * we do not want to trigger unwritten extent conversion on read + * faults - that is unnecessary overhead and would also require + * changes to xfs_get_blocks_direct() to map unwritten extent + * ioend for conversion on read-only mappings. + */ + ret = __dax_fault(vma, vmf, xfs_get_blocks_direct, NULL); + } else + ret = filemap_fault(vma, vmf); + xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED); return ret; } -- cgit v1.2.3-59-g8ed1b