4.12-stable review patch.  If anyone has any objections, please let me know.

------------------

From: "Michael S. Tsirkin" <m...@redhat.com>


[ Upstream commit 1daa8790d0280d2c719658e39bd59fce65efa909 ]

Seth Forshee noticed a performance degradation with some workloads.
This turns out to be due to packet drops.  Euan Kemp noticed that this
is because we drop all packets where length exceeds the truesize, but
for some packets we add in extra memory without updating the truesize.
This in turn was kept around unchanged from ab7db91705e95 ("virtio-net:
auto-tune mergeable rx buffer size for improved performance").  That
commit had an internal reason not to account for the extra space: not
enough bits to do it.  No longer true so let's account for the allocated
length exactly.

Many thanks to Seth Forshee for the report and bisecting and Euan Kemp
for debugging the issue.

Fixes: 680557cf79f8 ("virtio_net: rework mergeable buffer handling")
Reported-by: Euan Kemp <euan.k...@coreos.com>
Tested-by: Euan Kemp <euan.k...@coreos.com>
Reported-by: Seth Forshee <seth.fors...@canonical.com>
Tested-by: Seth Forshee <seth.fors...@canonical.com>
Signed-off-by: Michael S. Tsirkin <m...@redhat.com>
Signed-off-by: David S. Miller <da...@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gre...@linuxfoundation.org>
---
 drivers/net/virtio_net.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -889,21 +889,20 @@ static int add_recvbuf_mergeable(struct
 
        buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset;
        buf += headroom; /* advance address leaving hole at front of pkt */
-       ctx = (void *)(unsigned long)len;
        get_page(alloc_frag->page);
        alloc_frag->offset += len + headroom;
        hole = alloc_frag->size - alloc_frag->offset;
        if (hole < len + headroom) {
                /* To avoid internal fragmentation, if there is very likely not
                 * enough space for another buffer, add the remaining space to
-                * the current buffer. This extra space is not included in
-                * the truesize stored in ctx.
+                * the current buffer.
                 */
                len += hole;
                alloc_frag->offset += hole;
        }
 
        sg_init_one(rq->sg, buf, len);
+       ctx = (void *)(unsigned long)len;
        err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
        if (err < 0)
                put_page(virt_to_head_page(buf));


Reply via email to