From 85e584da3212140ee80fd047f9058bbee0bc00d5 Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Tue, 2 Sep 2014 12:12:52 +1000 Subject: xfs: don't zero partial page cache pages during O_DIRECT writes xfs is using truncate_pagecache_range to invalidate the page cache during DIO reads. This is different from the other filesystems who only invalidate pages during DIO writes. truncate_pagecache_range is meant to be used when we are freeing the underlying data structs from disk, so it will zero any partial ranges in the page. This means a DIO read can zero out part of the page cache page, and it is possible the page will stay in cache. buffered reads will find an up to date page with zeros instead of the data actually on disk. This patch fixes things by using invalidate_inode_pages2_range instead. It preserves the page cache invalidation, but won't zero any pages. [dchinner: catch error and warn if it fails. Comment.] cc: stable@vger.kernel.org Signed-off-by: Chris Mason Reviewed-by: Dave Chinner Reviewed-by: Brian Foster Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/xfs_file.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'fs/xfs/xfs_file.c') diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 076b1708d134..827cfb2451b1 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -296,7 +296,16 @@ xfs_file_read_iter( xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL); return ret; } - truncate_pagecache_range(VFS_I(ip), pos, -1); + + /* + * Invalidate whole pages. This can return an error if + * we fail to invalidate a page, but this should never + * happen on XFS. Warn if it does fail. + */ + ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping, + pos >> PAGE_CACHE_SHIFT, -1); + WARN_ON_ONCE(ret); + ret = 0; } xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL); } -- cgit From 834ffca6f7e345a79f6f2e2d131b0dfba8a4b67a Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 2 Sep 2014 12:12:52 +1000 Subject: xfs: don't zero partial page cache pages during O_DIRECT writes Similar to direct IO reads, direct IO writes are using truncate_pagecache_range to invalidate the page cache. This is incorrect due to the sub-block zeroing in the page cache that truncate_pagecache_range() triggers. This patch fixes things by using invalidate_inode_pages2_range instead. It preserves the page cache invalidation, but won't zero any pages. cc: stable@vger.kernel.org Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/xfs_file.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'fs/xfs/xfs_file.c') diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 827cfb2451b1..19917faac2d2 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -644,7 +644,15 @@ xfs_file_dio_aio_write( pos, -1); if (ret) goto out; - truncate_pagecache_range(VFS_I(ip), pos, -1); + /* + * Invalidate whole pages. This can return an error if + * we fail to invalidate a page, but this should never + * happen on XFS. Warn if it does fail. + */ + ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping, + pos >> PAGE_CACHE_SHIFT, -1); + WARN_ON_ONCE(ret); + ret = 0; } /* -- cgit From 7d4ea3ce63a6bc532abb334c469c18481798af8c Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 2 Sep 2014 12:12:53 +1000 Subject: xfs: use ranged writeback and invalidation for direct IO Now we are not doing silly things with dirtying buffers beyond EOF and using invalidation correctly, we can finally reduce the ranges of writeback and invalidation used by direct IO to match that of the IO being issued. Bring the writeback and invalidation ranges back to match the generic direct IO code - this will greatly reduce the perturbation of cached data when direct IO and buffered IO are mixed, but still provide the same buffered vs direct IO coherency behaviour we currently have. Signed-off-by: Dave Chinner Reviewed-by: Brian Foster Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/xfs/xfs_file.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'fs/xfs/xfs_file.c') diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 19917faac2d2..de5368c803f9 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -291,7 +291,7 @@ xfs_file_read_iter( if (inode->i_mapping->nrpages) { ret = filemap_write_and_wait_range( VFS_I(ip)->i_mapping, - pos, -1); + pos, pos + size - 1); if (ret) { xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL); return ret; @@ -303,7 +303,8 @@ xfs_file_read_iter( * happen on XFS. Warn if it does fail. */ ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping, - pos >> PAGE_CACHE_SHIFT, -1); + pos >> PAGE_CACHE_SHIFT, + (pos + size - 1) >> PAGE_CACHE_SHIFT); WARN_ON_ONCE(ret); ret = 0; } @@ -641,7 +642,7 @@ xfs_file_dio_aio_write( if (mapping->nrpages) { ret = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, - pos, -1); + pos, pos + count - 1); if (ret) goto out; /* @@ -650,7 +651,8 @@ xfs_file_dio_aio_write( * happen on XFS. Warn if it does fail. */ ret = invalidate_inode_pages2_range(VFS_I(ip)->i_mapping, - pos >> PAGE_CACHE_SHIFT, -1); + pos >> PAGE_CACHE_SHIFT, + (pos + count - 1) >> PAGE_CACHE_SHIFT); WARN_ON_ONCE(ret); ret = 0; } -- cgit