netdev - [PATCH V3 04/15] vhost-net: don't use vhost_add_used

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20190717105255.63488-5-jasowang@redhat.com>
Date:   Wed, 17 Jul 2019 06:52:44 -0400
From:   Jason Wang <jasowang@...hat.com>
To:     mst@...hat.com, jasowang@...hat.com
Cc:     kvm@...r.kernel.org, virtualization@...ts.linux-foundation.org,
        netdev@...r.kernel.org, linux-kernel@...r.kernel.org,
        jfreimann@...hat.com, tiwei.bie@...el.com,
        maxime.coquelin@...hat.com
Subject: [PATCH V3 04/15] vhost-net: don't use vhost_add_used_n() for zerocopy

We tried to use vhost_add_used_n() for the packets that is not
zero-copied. This can help to mitigate HOL issue but not a total
solution. What's more, it may lead out of order completion and cause
extra complexity for packed virtqueue implementation that needs to
maintain wrap counters.

So this patch switch to constantly use vq->heads[] to maintain
heads. This will ease the introduction of zerocopy shadow used ring
API and reduce the complexity for packed virtqueues.

After this, vhost_net became a in order device.

Signed-off-by: Jason Wang <jasowang@...hat.com>
---
 drivers/vhost/net.c | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 78d248574f8e..ac31983d2d77 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -894,9 +894,6 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
 		if (zcopy_used) {
 			struct ubuf_info *ubuf;
 			ubuf = nvq->ubuf_info + nvq->upend_idx;
-
-			vq->heads[nvq->upend_idx].id = cpu_to_vhost32(vq, head);
-			vq->heads[nvq->upend_idx].len = VHOST_DMA_IN_PROGRESS;
 			ubuf->callback = vhost_zerocopy_callback;
 			ubuf->ctx = nvq->ubufs;
 			ubuf->desc = nvq->upend_idx;
@@ -907,11 +904,14 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
 			msg.msg_controllen = sizeof(ctl);
 			ubufs = nvq->ubufs;
 			atomic_inc(&ubufs->refcount);
-			nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV;
 		} else {
 			msg.msg_control = NULL;
 			ubufs = NULL;
 		}
+		vq->heads[nvq->upend_idx].id = cpu_to_vhost32(vq, head);
+		vq->heads[nvq->upend_idx].len = zcopy_used ?
+			 VHOST_DMA_IN_PROGRESS : VHOST_DMA_DONE_LEN;
+		nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV;
 		total_len += len;
 		if (tx_can_batch(vq, total_len) &&
 		    likely(!vhost_exceeds_maxpend(net))) {
@@ -923,11 +923,10 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
 		/* TODO: Check specific error and bomb out unless ENOBUFS? */
 		err = sock->ops->sendmsg(sock, &msg, len);
 		if (unlikely(err < 0)) {
-			if (zcopy_used) {
+			if (zcopy_used)
 				vhost_net_ubuf_put(ubufs);
-				nvq->upend_idx = ((unsigned)nvq->upend_idx - 1)
-					% UIO_MAXIOV;
-			}
+			nvq->upend_idx = ((unsigned int)nvq->upend_idx - 1)
+					 % UIO_MAXIOV;
 			vhost_discard_vq_desc(vq, 1);
 			vhost_net_enable_vq(net, vq);
 			break;
@@ -935,10 +934,8 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
 		if (err != len)
 			pr_debug("Truncated TX packet: "
 				 " len %d != %zd\n", err, len);
-		if (!zcopy_used)
-			vhost_add_used_and_signal(&net->dev, vq, head, 0);
-		else
-			vhost_zerocopy_signal_used(net, vq);
+
+		vhost_zerocopy_signal_used(net, vq);
 		vhost_net_tx_packet(net);
 	} while (likely(!vhost_exceeds_weight(vq, ++sent_pkts, total_len)));
 }
-- 
2.18.1