Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Tue, 04 Aug 2020 22:10:22 -0700
User-Agent: K-9 Mail for Android
In-Reply-To: <20200805050808.GC9127@nazgul.tnic>
References: <20200805021059.1331-1-ricardo.neri-calderon@linux.intel.com> <20200805044840.GA9127@nazgul.tnic> <47A60E6A-0742-45FB-B707-175E87C58184@zytor.com> <20200805050808.GC9127@nazgul.tnic>
MIME-Version: 1.0
Content-Type: text/plain;
 charset=utf-8
Content-Transfer-Encoding: quoted-printable
Subject: Re: [PATCH v2] x86/cpu: Use SERIALIZE in sync_core() when available
To:     Borislav Petkov <bp@alien8.de>
CC:     Borislav Petkov <bp@suse.de>,
        Ricardo Neri <ricardo.neri-calderon@linux.intel.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@kernel.org>,
        Andy Lutomirski <luto@kernel.org>, x86@kernel.org,
        "Peter Zijlstra (Intel)" <peterz@infradead.org>,
        Dave Hansen <dave.hansen@intel.com>,
        Tony Luck <tony.luck@intel.com>,
        Cathy Zhang <cathy.zhang@intel.com>,
        Fenghua Yu <fenghua.yu@intel.com>,
        Kyung Min Park <kyung.min.park@intel.com>,
        "Ravi V. Shankar" <ravi.v.shankar@intel.com>,
        Sean Christopherson <sean.j.christopherson@intel.com>,
        linux-kernel@vger.kernel.org,
        Ricardo Neri <ricardo.neri@intel.com>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        linux-edac@vger.kernel.org
From:   hpa@zytor.com
Message-ID: <2511352F-5D28-4337-A4A2-1B54073F1F72@zytor.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On August 4, 2020 10:08:08 PM PDT, Borislav Petkov <bp@alien8=2Ede> wrote:
>On Tue, Aug 04, 2020 at 09:58:25PM -0700, hpa@zytor=2Ecom wrote:
>> Because why use an alternative to jump over one instruction?
>>
>> I personally would prefer to have the IRET put out of line
>
>Can't yet - SERIALIZE CPUs are a minority at the moment=2E
>
>> and have the call/jmp replaced by SERIALIZE inline=2E
>
>Well, we could do:
>
>	alternative_io("=2E=2E=2E IRET bunch", __ASM_SERIALIZE,
>X86_FEATURE_SERIALIZE, =2E=2E=2E);
>
>and avoid all kinds of jumping=2E Alternatives get padded so there
>would be a couple of NOPs following when SERIALIZE gets patched in
>but it shouldn't be a problem=2E I guess one needs to look at what gcc
>generates=2E=2E=2E

I didn't say behind a trap=2E IRET is a control transfer instruction, and =
slow, so putting it out of line really isn't unreasonable=2E Can even do a =
call to a common handler=2E
--=20
Sent from my Android device with K-9 Mail=2E Please excuse my brevity=2E