qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Jason Wang <jasowang@redhat.com>
To: peter.maydell@linaro.org, qemu-devel@nongnu.org
Cc: Akihiko Odaki <akihiko.odaki@daynix.com>,
	Jason Wang <jasowang@redhat.com>
Subject: [PULL 09/20] virtio-net: Copy header only when necessary
Date: Tue,  4 Jun 2024 15:37:44 +0800	[thread overview]
Message-ID: <20240604073755.1859-10-jasowang@redhat.com> (raw)
In-Reply-To: <20240604073755.1859-1-jasowang@redhat.com>

From: Akihiko Odaki <akihiko.odaki@daynix.com>

The copied header is only used for byte swapping.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
 hw/net/virtio-net.c | 26 ++++++++++++--------------
 1 file changed, 12 insertions(+), 14 deletions(-)

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c
index a8db8bfd9c..13a17a1e5a 100644
--- a/hw/net/virtio-net.c
+++ b/hw/net/virtio-net.c
@@ -360,7 +360,8 @@ static void virtio_net_vnet_endian_status(VirtIONet *n, uint8_t status)
          * can't do it, we fallback onto fixing the headers in the core
          * virtio-net code.
          */
-        n->needs_vnet_hdr_swap = virtio_net_set_vnet_endian(vdev, n->nic->ncs,
+        n->needs_vnet_hdr_swap = n->has_vnet_hdr &&
+                                 virtio_net_set_vnet_endian(vdev, n->nic->ncs,
                                                             queue_pairs, true);
     } else if (virtio_net_started(n, vdev->status)) {
         /* After using the device, we need to reset the network backend to
@@ -2751,7 +2752,7 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
             return -EINVAL;
         }
 
-        if (n->has_vnet_hdr) {
+        if (n->needs_vnet_hdr_swap) {
             if (iov_to_buf(out_sg, out_num, 0, &vhdr, n->guest_hdr_len) <
                 n->guest_hdr_len) {
                 virtio_error(vdev, "virtio-net header incorrect");
@@ -2759,19 +2760,16 @@ static int32_t virtio_net_flush_tx(VirtIONetQueue *q)
                 g_free(elem);
                 return -EINVAL;
             }
-            if (n->needs_vnet_hdr_swap) {
-                virtio_net_hdr_swap(vdev, (void *) &vhdr);
-                sg2[0].iov_base = &vhdr;
-                sg2[0].iov_len = n->guest_hdr_len;
-                out_num = iov_copy(&sg2[1], ARRAY_SIZE(sg2) - 1,
-                                   out_sg, out_num,
-                                   n->guest_hdr_len, -1);
-                if (out_num == VIRTQUEUE_MAX_SIZE) {
-                    goto drop;
-                }
-                out_num += 1;
-                out_sg = sg2;
+            virtio_net_hdr_swap(vdev, (void *) &vhdr);
+            sg2[0].iov_base = &vhdr;
+            sg2[0].iov_len = n->guest_hdr_len;
+            out_num = iov_copy(&sg2[1], ARRAY_SIZE(sg2) - 1, out_sg, out_num,
+                               n->guest_hdr_len, -1);
+            if (out_num == VIRTQUEUE_MAX_SIZE) {
+                goto drop;
             }
+            out_num += 1;
+            out_sg = sg2;
         }
         /*
          * If host wants to see the guest header as is, we can
-- 
2.42.0



  parent reply	other threads:[~2024-06-04  7:40 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-06-04  7:37 [PULL 00/20] Net patches Jason Wang
2024-06-04  7:37 ` [PULL 01/20] tap: Remove tap_probe_vnet_hdr_len() Jason Wang
2024-06-04  7:37 ` [PULL 02/20] tap: Remove qemu_using_vnet_hdr() Jason Wang
2024-06-04  7:37 ` [PULL 03/20] net: Move virtio-net header length assertion Jason Wang
2024-06-04  7:37 ` [PULL 04/20] net: Remove receive_raw() Jason Wang
2024-06-04  7:37 ` [PULL 05/20] tap: Call tap_receive_iov() from tap_receive() Jason Wang
2024-06-04  7:37 ` [PULL 06/20] tap: Shrink zeroed virtio-net header Jason Wang
2024-06-04  7:37 ` [PULL 07/20] virtio-net: Do not propagate ebpf-rss-fds errors Jason Wang
2024-06-05 10:23   ` Daniel P. Berrangé
2024-06-05 20:14     ` Akihiko Odaki
2024-06-06  7:14       ` Daniel P. Berrangé
2024-06-06  7:19         ` Akihiko Odaki
2024-06-06  7:59           ` Daniel P. Berrangé
2024-06-07  6:04             ` Akihiko Odaki
2024-06-04  7:37 ` [PULL 08/20] virtio-net: Add only one queue pair when realizing Jason Wang
2024-10-14  8:30   ` Laurent Vivier
2024-10-14 15:16     ` Laurent Vivier
2024-10-17  6:59       ` Jason Wang
2024-10-17  7:32         ` Laurent Vivier
2024-10-17  9:07           ` Akihiko Odaki
2024-10-17  9:17             ` Laurent Vivier
2024-10-17  9:42               ` Akihiko Odaki
2024-10-18  4:50                 ` Jason Wang
2024-10-19 12:38                   ` Akihiko Odaki
2024-10-21  7:23                     ` Jason Wang
2024-10-21  8:40                       ` Akihiko Odaki
2024-06-04  7:37 ` Jason Wang [this message]
2024-06-04  7:37 ` [PULL 10/20] virtio-net: Shrink header byte swapping buffer Jason Wang
2024-06-04  7:37 ` [PULL 11/20] virtio-net: Disable RSS on reset Jason Wang
2024-06-04  7:37 ` [PULL 12/20] virtio-net: Unify the logic to update NIC state for RSS Jason Wang
2024-06-04  7:37 ` [PULL 13/20] virtio-net: Always set populate_hash Jason Wang
2024-06-04  7:37 ` [PULL 14/20] virtio-net: Do not write hashes to peer buffer Jason Wang
2024-06-04  7:37 ` [PULL 15/20] ebpf: Fix RSS error handling Jason Wang
2024-06-04  7:37 ` [PULL 16/20] ebpf: Return 0 when configuration fails Jason Wang
2024-06-04  7:37 ` [PULL 17/20] ebpf: Refactor tun_rss_steering_prog() Jason Wang
2024-06-04  7:37 ` [PULL 18/20] ebpf: Add a separate target for skeleton Jason Wang
2024-06-04  7:37 ` [PULL 19/20] virtio-net: drop too short packets early Jason Wang
2024-06-04  7:37 ` [PULL 20/20] ebpf: Added traces back. Changed source set for eBPF to 'system' Jason Wang
2024-06-04 19:52 ` [PULL 00/20] Net patches Richard Henderson
2024-06-05 10:14 ` Michael Tokarev
2024-06-05 20:18   ` Akihiko Odaki
2024-06-06  0:13   ` Jason Wang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20240604073755.1859-10-jasowang@redhat.com \
    --to=jasowang@redhat.com \
    --cc=akihiko.odaki@daynix.com \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-devel@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).