From c553ea4fdf2701d64b9e9cca4497a8a2512bb025 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Mon, 13 May 2019 17:22:30 -0700
Subject: [PATCH] fs/sync.c: sync_file_range(2) may use WB_SYNC_ALL writeback
Git-commit: c553ea4fdf2701d64b9e9cca4497a8a2512bb025
Patch-mainline: v5.2-rc1
References: bsc#1136432
23d0127096cb ("fs/sync.c: make sync_file_range(2) use WB_SYNC_NONE
writeback") claims that sync_file_range(2) syscall was "created for
userspace to be able to issue background writeout and so waiting for
in-flight IO is undesirable there" and changes the writeback (back) to
WB_SYNC_NONE.
This claim is only partially true. It is true for users that use the flag
SYNC_FILE_RANGE_WRITE by itself, as does PostgreSQL, the user that was the
reason for changing to WB_SYNC_NONE writeback.
However, that claim is not true for users that use that flag combination
SYNC_FILE_RANGE_{WAIT_BEFORE|WRITE|_WAIT_AFTER}. Those users explicitly
requested to wait for in-flight IO as well as to writeback of dirty pages.
Re-brand that flag combination as SYNC_FILE_RANGE_WRITE_AND_WAIT and use
WB_SYNC_ALL writeback to perform the full range sync request.
Link: http://lkml.kernel.org/r/20190409114922.30095-1-amir73il@gmail.com
Link: http://lkml.kernel.org/r/20190419072938.31320-1-amir73il@gmail.com
Fixes: 23d0127096cb ("fs/sync.c: make sync_file_range(2) use WB_SYNC_NONE")
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Acked-by: Jan Kara <jack@suse.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Jan Kara <jack@suse.cz>
---
fs/sync.c | 15 ++++++++++++---
include/uapi/linux/fs.h | 3 +++
2 files changed, 15 insertions(+), 3 deletions(-)
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -264,10 +264,13 @@ SYSCALL_DEFINE1(fdatasync, unsigned int,
* earlier SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE operation to wait
* for that operation to complete and to return the result.
*
- * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE|SYNC_FILE_RANGE_WAIT_AFTER:
+ * SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE|SYNC_FILE_RANGE_WAIT_AFTER
+ * (a.k.a. SYNC_FILE_RANGE_WRITE_AND_WAIT):
* a traditional sync() operation. This is a write-for-data-integrity operation
* which will ensure that all pages in the range which were dirty on entry to
- * sys_sync_file_range() are committed to disk.
+ * sys_sync_file_range() are written to disk. It should be noted that disk
+ * caches are not flushed by this call, so there are no guarantees here that the
+ * data will be available on disk after a crash.
*
*
* SYNC_FILE_RANGE_WAIT_BEFORE and SYNC_FILE_RANGE_WAIT_AFTER will detect any
@@ -348,8 +351,14 @@ SYSCALL_DEFINE4(sync_file_range, int, fd
}
if (flags & SYNC_FILE_RANGE_WRITE) {
+ int sync_mode = WB_SYNC_NONE;
+
+ if ((flags & SYNC_FILE_RANGE_WRITE_AND_WAIT) ==
+ SYNC_FILE_RANGE_WRITE_AND_WAIT)
+ sync_mode = WB_SYNC_ALL;
+
ret = __filemap_fdatawrite_range(mapping, offset, endbyte,
- WB_SYNC_NONE);
+ sync_mode);
if (ret < 0)
goto out_put;
}
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -355,6 +355,9 @@ struct fscrypt_key {
#define SYNC_FILE_RANGE_WAIT_BEFORE 1
#define SYNC_FILE_RANGE_WRITE 2
#define SYNC_FILE_RANGE_WAIT_AFTER 4
+#define SYNC_FILE_RANGE_WRITE_AND_WAIT (SYNC_FILE_RANGE_WRITE | \
+ SYNC_FILE_RANGE_WAIT_BEFORE | \
+ SYNC_FILE_RANGE_WAIT_AFTER)
/* flags for preadv2/pwritev2: */
#define RWF_HIPRI 0x00000001 /* high priority request, poll if possible */