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;
MIME-Version: 1.0
References: <20190613064813.8102-1-namit@vmware.com> <20190613064813.8102-9-namit@vmware.com>
 <aa90347f-d1da-6bd7-dbf0-786f157eb370@intel.com>
In-Reply-To: <aa90347f-d1da-6bd7-dbf0-786f157eb370@intel.com>
From:   Andy Lutomirski <luto@kernel.org>
Date:   Tue, 25 Jun 2019 20:57:54 -0700
Message-ID: <CALCETrVM8GafRLTzbE-3CFjRxhorMeB=s2LYWNuH0nZn8YO2Yw@mail.gmail.com>
Subject: Re: [PATCH 8/9] x86/tlb: Privatize cpu_tlbstate
To:     Dave Hansen <dave.hansen@intel.com>
Cc:     Nadav Amit <namit@vmware.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Andy Lutomirski <luto@kernel.org>,
        LKML <linux-kernel@vger.kernel.org>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
        X86 ML <x86@kernel.org>, Thomas Gleixner <tglx@linutronix.de>,
        Dave Hansen <dave.hansen@linux.intel.com>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Tue, Jun 25, 2019 at 2:52 PM Dave Hansen <dave.hansen@intel.com> wrote:
>
> On 6/12/19 11:48 PM, Nadav Amit wrote:
> > cpu_tlbstate is mostly private and only the variable is_lazy is shared.
> > This causes some false-sharing when TLB flushes are performed.
>
> Presumably, all CPUs doing TLB flushes read 'is_lazy'.  Because of this,
> when we write to it we have to do the cache coherency dance to get rid
> of all the CPUs that might have a read-only copy.
>
> I would have *thought* that we only do writes when we enter or exist
> lazy mode.  That's partially true.  We do write in enter_lazy_tlb(), but
> we also *unconditionally* write in switch_mm_irqs_off().  That seems
> like it might be responsible for a chunk (or even a vast majority) of
> the cacheline bounces.
>
> Is there anything preventing us from turning the switch_mm_irqs_off()
> write into:
>
>         if (was_lazy)
>                 this_cpu_write(cpu_tlbstate.is_lazy, false);
>
> ?
>
> I think this patch is probably still a good general idea, but I just
> wonder if reducing the writes is a better way to reduce bounces.

Good catch!  I'm usually pretty good about this for
test_and_set()-style things, but I totally missed this obvious
unnecessary write when I did this.  I hereby apologize for all the
cycles I wasted :)

--Andy