Re: [PATCH v6.1-rt 00/15] net: Backport backlog-NAPI threads to resolve PREEMPT_RT softirq warning in SMP flush

Re: [PATCH v6.1-rt 00/15] net: Backport backlog-NAPI threads to resolve PREEMPT_RT softirq warning in SMP flush

[Sebastian Andrzej Siewior]

-net folks and lkml
+ linux-rt-devel@lists.linux.dev

On 2026-10-14 17:08:55 [+0200], To wen.yang@linux.dev wrote:
> Please keep the networking folks out of the loop. This is a backport
> request which goes entirely via the RT-queue.
> 
> On 2026-10-14 01:58:34 [+0800], wen.yang@linux.dev wrote:
> > From: Wen Yang <wen.yang@linux.dev>
> > 
> > *** Overview ***
> > Backport the backlog-NAPI smpboot-thread mechanism and its prerequisite
> > NAPI/RPS/defer_list work from upstream (v6.4 - v6.9) to v6.1-rt-next.
> > 
> > *** Problem ***
> > On PREEMPT_RT, RPS steers packets to a remote CPU's backlog by sending an
> > IPI. The IPI handler (rps_trigger_softirq) calls ____napi_schedule(), which
> > raises NET_RX_SOFTIRQ. do_softirq_post_smp_call_flush() then sees a softirq
> > pending that was not pending before the flush, and NET_RX_SOFTIRQ is not
> > masked by SCHED_SOFTIRQ_MASK, so it fires:
> 
> I was about to point out that v6.1-RT should have duct tape for this but
> from reading 1/15 is see that this duct is not complete and is missing
> RPS. Indeed.
> 
> A backport of what is merged is my preference, too. However, we should
> get v6.6-rt fixed first then v6.1-rt. Otherwise users upgrading from
> v6.1 to v6.6 will have this case broken.
> 
> Clark, any objections here from your side?
> 
Sebastian

Re: [PATCH v6.1-rt 00/15] net: Backport backlog-NAPI threads to resolve PREEMPT_RT softirq warning in SMP flush

[Sebastian Andrzej Siewior]

- NET + proper list

On 2026-10-15 08:34:28 [-0500], Clark Williams wrote:
> I don't have a fundamental objection to the backport and agree we should
> do v6.6-rt first, then move that back to v6.1-rt.

Okay.

> So it sounds like we need to pull in the RPS code first?

Yes. Wen, do you mind preparing a series for v6.6-RT?

> Clark

Sebastian

Re: [PATCH v6.1-rt 00/15] net: Backport backlog-NAPI threads to resolve PREEMPT_RT softirq warning in SMP flush

[Wen Yang]

On 10/15/26 21:38, Sebastian Andrzej Siewior wrote:
> - NET + proper list
> 
> On 2026-10-15 08:34:28 [-0500], Clark Williams wrote:
>> I don't have a fundamental objection to the backport and agree we should
>> do v6.6-rt first, then move that back to v6.1-rt.
> 
> Okay.
> 
>> So it sounds like we need to pull in the RPS code first?
> 
> Yes. Wen, do you mind preparing a series for v6.6-RT?
> 

Hi Sebastian, Clark,

Thanks for the feedback.
Agreed, v6.6-rt should be fixed first to avoid reintroducing the issue
when users upgrade from v6.1-rt. Regarding the RPS prerequisites, I will
check which upstream changes are already present in v6.6-rt and identify
the remaining dependencies for the backlog-NAPI threads and defer_list
cleanup. I will prepare and test a series for v6.6-RT soon.

Thanks,
Wen

Re: [PATCH v6.1-rt 00/15] net: Backport backlog-NAPI threads to resolve PREEMPT_RT softirq warning in SMP flush

[Clark Williams]

On Sat, Oct 17, 2026 at 02:16:02AM +0800, Wen Yang wrote:
> 
> 
> On 10/15/26 21:38, Sebastian Andrzej Siewior wrote:
> > - NET + proper list
> > 
> > On 2026-10-15 08:34:28 [-0500], Clark Williams wrote:
> > > I don't have a fundamental objection to the backport and agree we should
> > > do v6.6-rt first, then move that back to v6.1-rt.
> > 
> > Okay.
> > 
> > > So it sounds like we need to pull in the RPS code first?
> > 
> > Yes. Wen, do you mind preparing a series for v6.6-RT?
> > 
> 
> Hi Sebastian, Clark,
> 
> Thanks for the feedback.
> Agreed, v6.6-rt should be fixed first to avoid reintroducing the issue
> when users upgrade from v6.1-rt. Regarding the RPS prerequisites, I will
> check which upstream changes are already present in v6.6-rt and identify
> the remaining dependencies for the backlog-NAPI threads and defer_list
> cleanup. I will prepare and test a series for v6.6-RT soon.
> 
> Thanks,
> Wen

Perfect. I expect you'll have a small series for v6.6-rt and then a
pretty large one for v6.1-rt.

Thanks Wen, I'll be ready to apply/test when you send it. 

Clark

-- 
The United States Coast Guard
Ruining Natural Selection since 1790

Re: [PATCH v6.1-rt 00/15] net: Backport backlog-NAPI threads to resolve PREEMPT_RT softirq warning in SMP flush

[Sebastian Andrzej Siewior]

On 2026-10-16 14:00:59 [-0500], Clark Williams wrote:
> Perfect. I expect you'll have a small series for v6.6-rt and then a
> pretty large one for v6.1-rt.
> 
> Thanks Wen, I'll be ready to apply/test when you send it. 

"[PATCH 03/15] net: napi_schedule_rps() cleanup" has

| commit 8fcb76b934daff12cde76adeab3d502eeb0734b1 upstream.

in the middle of the commit message.

"[PATCH 14/15] net: Allow to use SMP threads for backlog NAPI." has only
context related changes.

I don't see any SMP-function calls with the series applied. This looks
complete to me.

> Clark

Sebastian

Re: [PATCH v6.1-rt 00/15] net: Backport backlog-NAPI threads to resolve PREEMPT_RT softirq warning in SMP flush

[Wen Yang]

On 10/22/26 17:25, Sebastian Andrzej Siewior wrote:
> On 2026-10-16 14:00:59 [-0500], Clark Williams wrote:
>> Perfect. I expect you'll have a small series for v6.6-rt and then a
>> pretty large one for v6.1-rt.
>>
>> Thanks Wen, I'll be ready to apply/test when you send it.
> 
> "[PATCH 03/15] net: napi_schedule_rps() cleanup" has
> 
> | commit 8fcb76b934daff12cde76adeab3d502eeb0734b1 upstream.
> 
> in the middle of the commit message.
> 
> "[PATCH 14/15] net: Allow to use SMP threads for backlog NAPI." has only
> context related changes.
> 
> I don't see any SMP-function calls with the series applied. This looks
> complete to me.
> 
>> Clark
> 
> Sebastian

Hi Sebastian, hi Clark,

Thanks for checking and confirming the RPS coverage.

Clark, would you mind moving the upstream commit reference in patch 03
to the beginning of the commit message when applying the series? This
would be a message-only correction; the code is unchanged.

I'm happy to resend if you would prefer an updated series.


Thanks,
Wen

Re: [PATCH v6.1-rt 00/15] net: Backport backlog-NAPI threads to resolve PREEMPT_RT softirq warning in SMP flush

[Clark Williams]

On Sat, Oct 24, 2026 at 01:42:22AM +0800, Wen Yang wrote:
> 
> 
> On 10/22/26 17:25, Sebastian Andrzej Siewior wrote:
> > On 2026-10-16 14:00:59 [-0500], Clark Williams wrote:
> > > Perfect. I expect you'll have a small series for v6.6-rt and then a
> > > pretty large one for v6.1-rt.
> > > 
> > > Thanks Wen, I'll be ready to apply/test when you send it.
> > 
> > "[PATCH 03/15] net: napi_schedule_rps() cleanup" has
> > 
> > | commit 8fcb76b934daff12cde76adeab3d502eeb0734b1 upstream.
> > 
> > in the middle of the commit message.
> > 
> > "[PATCH 14/15] net: Allow to use SMP threads for backlog NAPI." has only
> > context related changes.
> > 
> > I don't see any SMP-function calls with the series applied. This looks
> > complete to me.
> > 
> > > Clark
> > 
> > Sebastian
> 
> Hi Sebastian, hi Clark,
> 
> Thanks for checking and confirming the RPS coverage.
> 
> Clark, would you mind moving the upstream commit reference in patch 03
> to the beginning of the commit message when applying the series? This
> would be a message-only correction; the code is unchanged.
> 
> I'm happy to resend if you would prefer an updated series.
> 

Hi Wen,

Yes, Please resend an updated series with the reference(s) the way you want
them. I'll pull them in, push up up to -next with -rc2 (just to make sure
I didn't miss anything) and then go ahead and release it.

Clark
-- 
The United States Coast Guard
Ruining Natural Selection since 1790