netdev - Re: [PATCH net] net: fix raising a softirq on the current cpu with rps enabled

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>] [day] [month] [year] [list]

Date:   Sun, 26 Mar 2023 11:30:45 +0800
From:   Jason Xing <kerneljasonxing@...il.com>
To:     Hillf Danton <hdanton@...a.com>
Cc:     pabeni@...hat.com, Eric Dumazet <edumazet@...gle.com>,
        netdev@...r.kernel.org, linux-kernel@...r.kernel.org,
        Jason Xing <kernelxing@...cent.com>
Subject: Re: [PATCH net] net: fix raising a softirq on the current cpu with
 rps enabled

On Sun, Mar 26, 2023 at 9:39 AM Hillf Danton <hdanton@...a.com> wrote:
>
> On Sat, Mar 25, 2023 at 8:26 AM Jason Xing <kerneljasonxing@...il.com>
> >
> > @@ -4594,8 +4594,6 @@ static int napi_schedule_rps(struct softnet_data *sd)
> >         if (sd !=3D mysd) {
> >                 sd->rps_ipi_next =3D mysd->rps_ipi_list;
> >                 mysd->rps_ipi_list =3D sd;
> > -
> > -               __raise_softirq_irqoff(NET_RX_SOFTIRQ);
> >                 return 1;
> >         }
>
> Nope, ipi should be sent. But no ipi can go without irq enabled.
>

Sorry, I didn't get it. IPI is sent in net_rx_action() and apparently
I didn't touch this part in this patch. Here is only about whether we
should raise an IRQ even if the skb will be enqueued into another cpu.

> So feel free to work out what sense made by disabling irq at the call site
> then directly send ipi instead.