For block drivers that don't advertise FUA support, we already call
bdrv_co_flush(), which considers BDRV_O_NO_FLUSH. However, drivers that
do support FUA still see the FUA flag with BDRV_O_NO_FLUSH and get the
associated performance penalty that cache.no-flush=on was supposed to
avoid.

Clear FUA for write requests if BDRV_O_NO_FLUSH is set.

Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
 block/io.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/block/io.c b/block/io.c
index d369b994df..1ba8d1aeea 100644
--- a/block/io.c
+++ b/block/io.c
@@ -1058,6 +1058,10 @@ bdrv_driver_pwritev(BlockDriverState *bs, int64_t offset, int64_t bytes,
         return -ENOMEDIUM;
     }
 
+    if (bs->open_flags & BDRV_O_NO_FLUSH) {
+        flags &= ~BDRV_REQ_FUA;
+    }
+
     if ((flags & BDRV_REQ_FUA) &&
         (~bs->supported_write_flags & BDRV_REQ_FUA)) {
         flags &= ~BDRV_REQ_FUA;
-- 
2.48.1

On Fri, Mar 07, 2025 at 11:16:31PM +0100, Kevin Wolf wrote:
> For block drivers that don't advertise FUA support, we already call
> bdrv_co_flush(), which considers BDRV_O_NO_FLUSH. However, drivers that
> do support FUA still see the FUA flag with BDRV_O_NO_FLUSH and get the
> associated performance penalty that cache.no-flush=on was supposed to
> avoid.
> 
> Clear FUA for write requests if BDRV_O_NO_FLUSH is set.
> 
> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
> ---
>  block/io.c | 4 ++++
>  1 file changed, 4 insertions(+)

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>