From: Jason Wang <jasowang@redhat.com>
To: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Cc: Wei Wang <weiwan@google.com>, David Miller <davem@davemloft.net>,
Network Development <netdev@vger.kernel.org>,
Jakub Kicinski <kuba@kernel.org>,
Willem de Bruijn <willemb@google.com>,
virtualization@lists.linux-foundation.org
Subject: Re: [PATCH net] virtio-net: suppress bad irq warning for tx napi
Date: Wed, 3 Feb 2021 13:33:13 +0800 [thread overview]
Message-ID: <3a3e005d-f9b2-c16a-5ada-6e04242c618e@redhat.com> (raw)
In-Reply-To: <CAF=yD-+aPBF2RaCR8L5orTM37bf7Z4Z8Qko2D2LZjOz0khHTUg@mail.gmail.com>
On 2021/2/2 下午10:37, Willem de Bruijn wrote:
> On Mon, Feb 1, 2021 at 10:09 PM Jason Wang <jasowang@redhat.com> wrote:
>>
>> On 2021/1/29 上午8:21, Wei Wang wrote:
>>> With the implementation of napi-tx in virtio driver, we clean tx
>>> descriptors from rx napi handler, for the purpose of reducing tx
>>> complete interrupts. But this could introduce a race where tx complete
>>> interrupt has been raised, but the handler found there is no work to do
>>> because we have done the work in the previous rx interrupt handler.
>>> This could lead to the following warning msg:
>>> [ 3588.010778] irq 38: nobody cared (try booting with the
>>> "irqpoll" option)
>>> [ 3588.017938] CPU: 4 PID: 0 Comm: swapper/4 Not tainted
>>> 5.3.0-19-generic #20~18.04.2-Ubuntu
>>> [ 3588.017940] Call Trace:
>>> [ 3588.017942] <IRQ>
>>> [ 3588.017951] dump_stack+0x63/0x85
>>> [ 3588.017953] __report_bad_irq+0x35/0xc0
>>> [ 3588.017955] note_interrupt+0x24b/0x2a0
>>> [ 3588.017956] handle_irq_event_percpu+0x54/0x80
>>> [ 3588.017957] handle_irq_event+0x3b/0x60
>>> [ 3588.017958] handle_edge_irq+0x83/0x1a0
>>> [ 3588.017961] handle_irq+0x20/0x30
>>> [ 3588.017964] do_IRQ+0x50/0xe0
>>> [ 3588.017966] common_interrupt+0xf/0xf
>>> [ 3588.017966] </IRQ>
>>> [ 3588.017989] handlers:
>>> [ 3588.020374] [<000000001b9f1da8>] vring_interrupt
>>> [ 3588.025099] Disabling IRQ #38
>>>
>>> This patch adds a new param to struct vring_virtqueue, and we set it for
>>> tx virtqueues if napi-tx is enabled, to suppress the warning in such
>>> case.
>>>
>>> Fixes: 7b0411ef4aa6 ("virtio-net: clean tx descriptors from rx napi")
>>> Reported-by: Rick Jones <jonesrick@google.com>
>>> Signed-off-by: Wei Wang <weiwan@google.com>
>>> Signed-off-by: Willem de Bruijn <willemb@google.com>
>>
>> Please use get_maintainer.pl to make sure Michael and me were cced.
> Will do. Sorry about that. I suggested just the virtualization list, my bad.
>
>>> ---
>>> drivers/net/virtio_net.c | 19 ++++++++++++++-----
>>> drivers/virtio/virtio_ring.c | 16 ++++++++++++++++
>>> include/linux/virtio.h | 2 ++
>>> 3 files changed, 32 insertions(+), 5 deletions(-)
>>>
>>> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
>>> index 508408fbe78f..e9a3f30864e8 100644
>>> --- a/drivers/net/virtio_net.c
>>> +++ b/drivers/net/virtio_net.c
>>> @@ -1303,13 +1303,22 @@ static void virtnet_napi_tx_enable(struct virtnet_info *vi,
>>> return;
>>> }
>>>
>>> + /* With napi_tx enabled, free_old_xmit_skbs() could be called from
>>> + * rx napi handler. Set work_steal to suppress bad irq warning for
>>> + * IRQ_NONE case from tx complete interrupt handler.
>>> + */
>>> + virtqueue_set_work_steal(vq, true);
>>> +
>>> return virtnet_napi_enable(vq, napi);
>>
>> Do we need to force the ordering between steal set and napi enable?
> The warning only occurs after one hundred spurious interrupts, so not
> really.
Ok, so it looks like a hint. Then I wonder how much value do we need to
introduce helper like virtqueue_set_work_steal() that allows the caller
to toggle. How about disable the check forever during virtqueue
initialization?
>
>>> }
>>>
>>> -static void virtnet_napi_tx_disable(struct napi_struct *napi)
>>> +static void virtnet_napi_tx_disable(struct virtqueue *vq,
>>> + struct napi_struct *napi)
>>> {
>>> - if (napi->weight)
>>> + if (napi->weight) {
>>> napi_disable(napi);
>>> + virtqueue_set_work_steal(vq, false);
>>> + }
>>> }
>>>
>>> static void refill_work(struct work_struct *work)
>>> @@ -1835,7 +1844,7 @@ static int virtnet_close(struct net_device *dev)
>>> for (i = 0; i < vi->max_queue_pairs; i++) {
>>> xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq);
>>> napi_disable(&vi->rq[i].napi);
>>> - virtnet_napi_tx_disable(&vi->sq[i].napi);
>>> + virtnet_napi_tx_disable(vi->sq[i].vq, &vi->sq[i].napi);
>>> }
>>>
>>> return 0;
>>> @@ -2315,7 +2324,7 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
>>> if (netif_running(vi->dev)) {
>>> for (i = 0; i < vi->max_queue_pairs; i++) {
>>> napi_disable(&vi->rq[i].napi);
>>> - virtnet_napi_tx_disable(&vi->sq[i].napi);
>>> + virtnet_napi_tx_disable(vi->sq[i].vq, &vi->sq[i].napi);
>>> }
>>> }
>>> }
>>> @@ -2440,7 +2449,7 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
>>> if (netif_running(dev)) {
>>> for (i = 0; i < vi->max_queue_pairs; i++) {
>>> napi_disable(&vi->rq[i].napi);
>>> - virtnet_napi_tx_disable(&vi->sq[i].napi);
>>> + virtnet_napi_tx_disable(vi->sq[i].vq, &vi->sq[i].napi);
>>> }
>>> }
>>>
>>> diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
>>> index 71e16b53e9c1..f7c5d697c302 100644
>>> --- a/drivers/virtio/virtio_ring.c
>>> +++ b/drivers/virtio/virtio_ring.c
>>> @@ -105,6 +105,9 @@ struct vring_virtqueue {
>>> /* Host publishes avail event idx */
>>> bool event;
>>>
>>> + /* Tx side napi work could be done from rx side. */
>>> + bool work_steal;
>>
>> So vring_vritqueue is a general structure, let's avoid mentioning
>> network specific stuffs here. And we need a better name like
>> "no_interrupt_check"?
>>
>> And we need a separate patch for virtio core changes.
> Ack. Will change.
>
>>> +
>>> /* Head of free buffer list. */
>>> unsigned int free_head;
>>> /* Number we've added since last sync. */
>>> @@ -1604,6 +1607,7 @@ static struct virtqueue *vring_create_virtqueue_packed(
>>> vq->notify = notify;
>>> vq->weak_barriers = weak_barriers;
>>> vq->broken = false;
>>> + vq->work_steal = false;
>>> vq->last_used_idx = 0;
>>> vq->num_added = 0;
>>> vq->packed_ring = true;
>>> @@ -2038,6 +2042,9 @@ irqreturn_t vring_interrupt(int irq, void *_vq)
>>>
>>> if (!more_used(vq)) {
>>> pr_debug("virtqueue interrupt with no work for %p\n", vq);
>>
>> Do we still need to keep this warning?
> Come to think of it, I would say no, in this case.
>
>>
>>> + if (vq->work_steal)
>>> + return IRQ_HANDLED;
>>
>> So I wonder instead of doing trick like this, maybe it's time to unify
>> TX/RX NAPI with the help of[1] (virtio-net use queue pairs).
>>
>> Thanks
>>
>> [1] https://lkml.org/lkml/2014/12/25/169
> Interesting idea. It does sound like a good fit for this model. The
> patch in the Fixes line proved effective at suppressing unnecessary TX
> interrupts when processing in RX interrupt handler. So not sure how
> much will help in practice. Might be a nice project to evaluate
> separate for net-next at some point.
Right, basically the idea is that if an irq is shared among several
virtqueues, there's no need to check for more_used() there.
Yes, we can try sometime in the future. (Or e.g we have more than 128
queue pairs).
Thanks
>
> Thanks for the review!
>
next prev parent reply other threads:[~2021-02-03 5:34 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-29 0:21 [PATCH net] virtio-net: suppress bad irq warning for tx napi Wei Wang
2021-02-02 2:24 ` Jakub Kicinski
2021-02-02 3:06 ` Jason Wang
2021-02-02 14:37 ` Willem de Bruijn
2021-02-03 5:33 ` Jason Wang [this message]
2021-02-03 18:28 ` Willem de Bruijn
2021-02-04 3:06 ` Jason Wang
2021-02-04 20:50 ` Willem de Bruijn
2021-02-08 3:29 ` Jason Wang
2021-02-08 19:08 ` Willem de Bruijn
2021-02-09 3:27 ` Jason Wang
2021-02-09 14:58 ` Willem de Bruijn
2021-02-09 18:00 ` Wei Wang
2021-02-10 9:14 ` Michael S. Tsirkin
2021-02-11 0:13 ` Wei Wang
2021-02-18 5:39 ` Jason Wang
2021-02-21 11:33 ` Michael S. Tsirkin
2021-02-02 23:11 ` Michael S. Tsirkin
2021-02-02 23:47 ` Wei Wang
2021-02-02 23:53 ` Willem de Bruijn
2021-02-03 0:06 ` Willem de Bruijn
2021-02-03 10:38 ` Michael S. Tsirkin
2021-02-03 18:24 ` Willem de Bruijn
2021-02-03 23:09 ` Michael S. Tsirkin
2021-02-03 23:52 ` Wei Wang
2021-02-04 20:47 ` Willem de Bruijn
2021-02-05 22:28 ` Wei Wang
2021-04-13 5:15 ` Michael S. Tsirkin
2021-09-29 20:21 ` Wei Wang
2021-09-29 21:53 ` Michael S. Tsirkin
2021-09-29 23:08 ` Wei Wang
2021-09-30 5:40 ` Michael S. Tsirkin
2021-09-30 18:10 ` Dave Taht
2021-04-12 22:08 ` Michael S. Tsirkin
2021-04-12 22:33 ` Michael S. Tsirkin
2021-04-12 23:14 ` David Miller
2021-04-13 4:24 ` Michael S. Tsirkin
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=3a3e005d-f9b2-c16a-5ada-6e04242c618e@redhat.com \
--to=jasowang@redhat.com \
--cc=davem@davemloft.net \
--cc=kuba@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=virtualization@lists.linux-foundation.org \
--cc=weiwan@google.com \
--cc=willemb@google.com \
--cc=willemdebruijn.kernel@gmail.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;
as well as URLs for NNTP newsgroup(s).