Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Wed, 17 Jan 2018 23:54:05 +0100 (CET)
From:   Thomas Gleixner <tglx@linutronix.de>
To:     David Miller <davem@davemloft.net>
cc:     edumazet@google.com, torvalds@linux-foundation.org, efault@gmx.de,
        peterz@infradead.org, dima@arista.com, frederic@kernel.org,
        linux-kernel@vger.kernel.org, 0x7f454c46@gmail.com,
        akpm@linux-foundation.org, fweisbec@gmail.com,
        hannes@stressinduktion.org, mingo@kernel.org,
        alexander.levin@verizon.com, pabeni@redhat.com,
        paulmck@linux.vnet.ibm.com, rrendec@arista.com, riel@redhat.com,
        sgruszka@redhat.com, wanpeng.li@hotmail.com
Subject: Re: [RFC 1/2] softirq: Defer net rx/tx processing to ksoftirqd
 context
In-Reply-To: <20180117.172447.1568697383040902713.davem@davemloft.net>
Message-ID: <alpine.DEB.2.20.1801172344500.2326@nanos>
References: <CA+55aFzk0Lh1kQRRvOQKrjMfkcuQem0aV5D9cCUmmtfw7ZamkQ@mail.gmail.com> <alpine.DEB.2.20.1801172258540.2326@nanos> <CANn89iJmA-21uL+pPBiV6zsrR7nY6RJ6bamDCgPctMoNWpa4Hw@mail.gmail.com> <20180117.172447.1568697383040902713.davem@davemloft.net>
User-Agent: Alpine 2.20 (DEB 67 2015-01-07)
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed, 17 Jan 2018, David Miller wrote:
> From: Eric Dumazet <edumazet@google.com>
> Date: Wed, 17 Jan 2018 14:02:43 -0800
> 
> > On Wed, Jan 17, 2018 at 2:00 PM, Thomas Gleixner <tglx@linutronix.de> wrote:
> >> On Wed, 17 Jan 2018, Linus Torvalds wrote:
> >>
> >>> On Wed, Jan 17, 2018 at 1:54 PM, Thomas Gleixner <tglx@linutronix.de> wrote:
> >>> > raise_softirq() -> raise_softirq_irqoff()
> >>> >
> >>> >         set_softirq_bit();
> >>> >
> >>> >         if (!in_interrupt())
> >>> >                 wake_softirqd();
> >>> >
> >>> > So if the caller is not in hard or soft interrupt context, which includes
> >>> > bottom half disabled regions softirqd is woken.
> >>>
> >>> That does seem unnecessarily expensive, and maybe we could just do it
> >>> with thread flag (TIF_NOTIFY_RESUME or whatever).
> >>>
> >>> In fact, that was what I *thought* we did. Maybe I just remember some
> >>> historical behavior.
> >>>
> >>> Since networking seems to largely prefer softirqd anyway, maybe that
> >>> wake_softirqd() is the right thing to do anyway.
> >>
> >> Well, but we only do it when we are not in a bh disabled region. The places
> >> where thread context raises the network softirqs is usually inside a bh
> >> disabled region, so the softirq is executed on local_bh_enable(). The
> >> thread is woken up rarely.
> > 
> > There is also the netif_rx_ni() stuff.
> > 
> > Can't remember right now why it is not using
> > local_bh_{diable,enable}() pair instead
> > of preempt_disable() ... if (local_softirq_pending()) do_softirq();
> 
> Hmmm, that code predates the initial GIT repository build.
> 
> I do remember we had some back and forth with that stuff.

commit 3ace873f40916682583562c1e1f324a4a50a2811 in

https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git

deinlines that function and drops a comment while at it:

-/* Post buffer to the network code from _non interrupt_ context.
- * see net/core/dev.c for netif_rx description.
- */
-static inline int netif_rx_ni(struct sk_buff *skb)

It was added somewhere around 2.5.0

Thanks,

	tglx