public inbox for virtualization@lists.linux-foundation.org
 help / color / mirror / Atom feed
From: Vishwanath Seshagiri <vishs@meta.com>
To: Omar Elghoul <oelghoul@linux.ibm.com>,
	"Michael S. Tsirkin" <mst@redhat.com>
Cc: andrew+netdev@lunn.ch, davem@davemloft.net, dw@davidwei.uk,
	edumazet@google.com, eperezma@redhat.com,
	ilias.apalodimas@linaro.org, jasowang@redhat.com,
	kernel-team@meta.com, kuba@kernel.org,
	linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
	pabeni@redhat.com, technoboy85@gmail.com,
	virtualization@lists.linux.dev, xuanzhuo@linux.alibaba.com
Subject: Re: [PATCH net-next v11] virtio_net: add page_pool support for buffer allocation
Date: Mon, 23 Mar 2026 13:50:29 -0400	[thread overview]
Message-ID: <f91a42f7-1e90-4db0-923a-371dac8245e0@meta.com> (raw)
In-Reply-To: <6b6bea74-4bff-4301-8dbf-a9c162456185@linux.ibm.com>



On 3/23/26 10:39 PM, Omar Elghoul wrote:
> On 3/23/26 12:58 PM, Michael S. Tsirkin wrote:
> 
>> On Mon, Mar 23, 2026 at 11:52:34AM -0400, Michael S. Tsirkin wrote:
>>> On Mon, Mar 23, 2026 at 11:01:31AM -0400, Omar Elghoul wrote:
>>>> [...]
>>> Well... I am not sure how I missed it. Obvious in hindsight:
>>>
>>> static void receive_buf(struct virtnet_info *vi, struct receive_queue 
>>> *rq,
>>>                          void *buf, unsigned int len, void **ctx,
>>>                          unsigned int *xdp_xmit,
>>>                          struct virtnet_rq_stats *stats)
>>> {
>>>          struct net_device *dev = vi->dev;
>>>          struct sk_buff *skb;
>>>          u8 flags;
>>>          if (unlikely(len < vi->hdr_len + ETH_HLEN)) {
>>>                  pr_debug("%s: short packet %i\n", dev->name, len);
>>>                  DEV_STATS_INC(dev, rx_length_errors);
>>>                  virtnet_rq_free_buf(vi, rq, buf);
>>>                  return;
>>>          }
>>>          /* About the flags below:
>>>           * 1. Save the flags early, as the XDP program might 
>>> overwrite them.
>>>           * These flags ensure packets marked as 
>>> VIRTIO_NET_HDR_F_DATA_VALID
>>>           * stay valid after XDP processing.
>>>           * 2. XDP doesn't work with partially checksummed packets 
>>> (refer to
>>>           * virtnet_xdp_set()), so packets marked as
>>>           * VIRTIO_NET_HDR_F_NEEDS_CSUM get dropped during XDP 
>>> processing.
>>>           */
>>>          if (vi->mergeable_rx_bufs) {
>>>                  flags = ((struct virtio_net_common_hdr *)buf)- 
>>> >hdr.flags;
>>>                  skb = receive_mergeable(dev, vi, rq, buf, ctx, len, 
>>> xdp_xmit,
>>>                                          stats);
>>>          } else if (vi->big_packets) {
>>>                  void *p = page_address((struct page *)buf);
>>>                  flags = ((struct virtio_net_common_hdr *)p)->hdr.flags;
>>>                  skb = receive_big(dev, vi, rq, buf, len, stats);
>>>          } else {
>>>                  flags = ((struct virtio_net_common_hdr *)buf)- 
>>> >hdr.flags;
>>>                  skb = receive_small(dev, vi, rq, buf, ctx, len, 
>>> xdp_xmit, stats);
>>>          }
>>>
>>>
>>> So we are reading the header, before dma sync, which is within
>>> receive_mergeable and friends:
>>>
>>> static struct sk_buff *receive_mergeable(struct net_device *dev,
>>>                                           struct virtnet_info *vi,
>>>                                           struct receive_queue *rq,
>>>                                           void *buf,
>>>                                           void *ctx,
>>>                                           unsigned int len,
>>>                                           unsigned int *xdp_xmit,
>>>                                           struct virtnet_rq_stats 
>>> *stats)
>>> {
>>>          struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
>>>          int num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
>>>          struct page *page = virt_to_head_page(buf);
>>>          int offset = buf - page_address(page);
>>>          struct sk_buff *head_skb, *curr_skb;
>>>          unsigned int truesize = mergeable_ctx_to_truesize(ctx);
>>>          unsigned int headroom = mergeable_ctx_to_headroom(ctx);
>>>          head_skb = NULL;
>>>          if (rq->use_page_pool_dma)
>>>                  page_pool_dma_sync_for_cpu(rq->page_pool, page, 
>>> offset, len);
>>>
>>>
>>> Just as a test, the below should fix it (compiled only), but the real
>>> fix is more complex since we need to be careful to avoid expensive 
>>> syncing
>>> twice.
>>>
>>>
>>> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
>>> index 97035b49bae7..57b4f5954bed 100644
>>> --- a/drivers/net/virtio_net.c
>>> +++ b/drivers/net/virtio_net.c
>>> @@ -931,9 +931,19 @@ static struct sk_buff *page_to_skb(struct 
>>> virtnet_info *vi,
>>>   static void *virtnet_rq_get_buf(struct receive_queue *rq, u32 *len, 
>>> void **ctx)
>>>   {
>>> +    void *buf;
>>> +
>>>       BUG_ON(!rq->page_pool);
>>> -    return virtqueue_get_buf_ctx(rq->vq, len, ctx);
>>> +    buf = virtqueue_get_buf_ctx(rq->vq, len, ctx);
>>> +    if (buf && rq->use_page_pool_dma && *len) {
>>> +        struct page *page = virt_to_head_page(buf);
>>> +        int offset = buf - page_address(page);
>>> +
>>> +        page_pool_dma_sync_for_cpu(rq->page_pool, page, offset, *len);
>>> +    }
>>> +
>>> +    return buf;
>>>   }
>>>   static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf)
>>>
>>>
>>>
>>>
>>> -- 
>>> MST
>> or maybe like this:
> Both of these patches resolve the issue on my end.
>>
>> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
>> index 97035b49bae7..835f52651006 100644
>> --- a/drivers/net/virtio_net.c
>> +++ b/drivers/net/virtio_net.c
>> @@ -1956,13 +1956,6 @@ static struct sk_buff *receive_small(struct 
>> net_device *dev,
>>        */
>>       buf -= VIRTNET_RX_PAD + xdp_headroom;
>> -    if (rq->use_page_pool_dma) {
>> -        int offset = buf - page_address(page) +
>> -                 VIRTNET_RX_PAD + xdp_headroom;
>> -
>> -        page_pool_dma_sync_for_cpu(rq->page_pool, page, offset, len);
>> -    }
>> -
>>       len -= vi->hdr_len;
>>       u64_stats_add(&stats->bytes, len);
>> @@ -2398,9 +2391,6 @@ static struct sk_buff *receive_mergeable(struct 
>> net_device *dev,
>>       head_skb = NULL;
>> -    if (rq->use_page_pool_dma)
>> -        page_pool_dma_sync_for_cpu(rq->page_pool, page, offset, len);
>> -
>>       u64_stats_add(&stats->bytes, len - vi->hdr_len);
>>       if (check_mergeable_len(dev, ctx, len))
>> @@ -2563,6 +2553,13 @@ static void receive_buf(struct virtnet_info 
>> *vi, struct receive_queue *rq,
>>           return;
>>       }
>> +    if (rq->use_page_pool_dma) {
>> +        struct page *page = virt_to_head_page(buf);
>> +        int offset = buf - page_address(page);
>> +
>> +        page_pool_dma_sync_for_cpu(rq->page_pool, page, offset, len);
>> +    }
>> +
>>       /* About the flags below:
>>        * 1. Save the flags early, as the XDP program might overwrite 
>> them.
>>        * These flags ensure packets marked as VIRTIO_NET_HDR_F_DATA_VALID
>>

Hello Omar. Thank you for the bisect, apologies for breaking the
functionality. Thank you Michael for the patch, I will be careful next
time about DMA sync issues. Looks like the bug is fixed, is there
anything else needed from my end?


  reply	other threads:[~2026-03-23 17:51 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-10 18:31 [PATCH net-next v11] virtio_net: add page_pool support for buffer allocation Vishwanath Seshagiri
2026-03-13  7:51 ` Jason Wang
2026-03-13  9:26   ` Vishwanath Seshagiri
2026-03-16  7:41     ` Jason Wang
2026-03-13 16:50   ` Vishwanath Seshagiri
2026-03-16  7:35     ` Jason Wang
2026-03-16  9:56 ` Michael S. Tsirkin
2026-03-16 10:43   ` Michael S. Tsirkin
2026-03-16 11:57     ` Vishwanath Seshagiri
2026-03-16 12:04       ` Michael S. Tsirkin
2026-03-17  2:30 ` patchwork-bot+netdevbpf
2026-03-23 15:01 ` Omar Elghoul
2026-03-23 15:52   ` Michael S. Tsirkin
2026-03-23 16:54     ` Omar Elghoul
2026-03-23 17:10       ` Michael S. Tsirkin
2026-03-23 16:58     ` Michael S. Tsirkin
2026-03-23 17:09       ` Omar Elghoul
2026-03-23 17:50         ` Vishwanath Seshagiri [this message]
2026-03-23 23:37           ` Michael S. Tsirkin
2026-03-24  0:34       ` Jason Wang
2026-03-24  8:20       ` Aithal, Srikanth

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=f91a42f7-1e90-4db0-923a-371dac8245e0@meta.com \
    --to=vishs@meta.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=davem@davemloft.net \
    --cc=dw@davidwei.uk \
    --cc=edumazet@google.com \
    --cc=eperezma@redhat.com \
    --cc=ilias.apalodimas@linaro.org \
    --cc=jasowang@redhat.com \
    --cc=kernel-team@meta.com \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=oelghoul@linux.ibm.com \
    --cc=pabeni@redhat.com \
    --cc=technoboy85@gmail.com \
    --cc=virtualization@lists.linux.dev \
    --cc=xuanzhuo@linux.alibaba.com \
    /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