From 7db05c8a732fbdc986a40aadf0de6dd23057d044 Mon Sep 17 00:00:00 2001
From: Max Reitz <mreitz@redhat.com>
Date: Fri, 1 Nov 2019 16:25:10 +0100
Subject: [PATCH] block/file-posix: Let post-EOF fallocate serialize

The XFS kernel driver has a bug that may cause data corruption for qcow2
images as of qemu commit c8bb23cbdbe32f.  We can work around it by
treating post-EOF fallocates as serializing up until infinity (INT64_MAX
in practice).

Cc: qemu-stable@nongnu.org
Signed-off-by: Max Reitz <mreitz@redhat.com>
Message-id: 20191101152510.11719-4-mreitz@redhat.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
(cherry picked from commit 292d06b925b2787ee6f2430996b95651cae42fce)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
 block/file-posix.c | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/block/file-posix.c b/block/file-posix.c
index 992eb4a798..c5df61b477 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -2623,6 +2623,42 @@ raw_do_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes,
     RawPosixAIOData acb;
     ThreadPoolFunc *handler;
 
+#ifdef CONFIG_FALLOCATE
+    if (offset + bytes > bs->total_sectors * BDRV_SECTOR_SIZE) {
+        BdrvTrackedRequest *req;
+        uint64_t end;
+
+        /*
+         * This is a workaround for a bug in the Linux XFS driver,
+         * where writes submitted through the AIO interface will be
+         * discarded if they happen beyond a concurrently running
+         * fallocate() that increases the file length (i.e., both the
+         * write and the fallocate() happen beyond the EOF).
+         *
+         * To work around it, we extend the tracked request for this
+         * zero write until INT64_MAX (effectively infinity), and mark
+         * it as serializing.
+         *
+         * We have to enable this workaround for all filesystems and
+         * AIO modes (not just XFS with aio=native), because for
+         * remote filesystems we do not know the host configuration.
+         */
+
+        req = bdrv_co_get_self_request(bs);
+        assert(req);
+        assert(req->type == BDRV_TRACKED_WRITE);
+        assert(req->offset <= offset);
+        assert(req->offset + req->bytes >= offset + bytes);
+
+        end = INT64_MAX & -(uint64_t)bs->bl.request_alignment;
+        req->bytes = end - req->offset;
+        req->overlap_bytes = req->bytes;
+
+        bdrv_mark_request_serialising(req, bs->bl.request_alignment);
+        bdrv_wait_serialising_requests(req);
+    }
+#endif
+
     acb = (RawPosixAIOData) {
         .bs             = bs,
         .aio_fildes     = s->fd,
-- 
2.23.0