Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Feedback-ID: i56a14606:Fastmail
User-Agent: Cyrus-JMAP/3.9.0-alpha0-592-ga9d4a09b4b-fm-defalarms-20230725.001-ga9d4a09b
Mime-Version: 1.0
Message-Id: <92c00ddb-e956-4861-af80-5f5558c9a8f5@app.fastmail.com>
In-Reply-To: <CAJM55Z8vF8_xq0QyByLUGM2W-8m6R-_6SdOFdLETV7J-yo5DMQ@mail.gmail.com>
References: <20230702203429.237615-1-prabhakar.mahadev-lad.rj@bp.renesas.com>
 <20230702203429.237615-4-prabhakar.mahadev-lad.rj@bp.renesas.com>
 <ZMZ6XB6gX2kFd/Nt@xhacker>
 <CAJM55Z8vF8_xq0QyByLUGM2W-8m6R-_6SdOFdLETV7J-yo5DMQ@mail.gmail.com>
Date:   Sun, 30 Jul 2023 22:35:50 +0200
From:   "Arnd Bergmann" <arnd@arndb.de>
To:     "Emil Renner Berthing" <emil.renner.berthing@canonical.com>,
        "Jisheng Zhang" <jszhang@kernel.org>
Cc:     Prabhakar <prabhakar.csengg@gmail.com>,
        "Conor.Dooley" <conor.dooley@microchip.com>,
        "Geert Uytterhoeven" <geert+renesas@glider.be>,
        guoren <guoren@kernel.org>,
        "Andrew Jones" <ajones@ventanamicro.com>,
        "Paul Walmsley" <paul.walmsley@sifive.com>,
        "Palmer Dabbelt" <palmer@dabbelt.com>,
        "Albert Ou" <aou@eecs.berkeley.edu>,
        "Samuel Holland" <samuel@sholland.org>,
        linux-riscv@lists.infradead.org,
        "Christoph Hellwig" <hch@infradead.org>,
        "Rob Herring" <robh+dt@kernel.org>,
        "Krzysztof Kozlowski" <krzysztof.kozlowski+dt@linaro.org>,
        devicetree@vger.kernel.org, linux-kernel@vger.kernel.org,
        Linux-Renesas <linux-renesas-soc@vger.kernel.org>,
        "Biju Das" <biju.das.jz@bp.renesas.com>,
        "Lad, Prabhakar" <prabhakar.mahadev-lad.rj@bp.renesas.com>
Subject: Re: [PATCH v10 3/6] riscv: mm: dma-noncoherent: nonstandard cache operations
 support
Content-Type: text/plain
Precedence: bulk

On Sun, Jul 30, 2023, at 17:42, Emil Renner Berthing wrote:
> On Sun, 30 Jul 2023 at 17:11, Jisheng Zhang <jszhang@kernel.org> wrote:

>> > +
>> >  static inline void arch_dma_cache_wback(phys_addr_t paddr, size_t size)
>> >  {
>> >       void *vaddr = phys_to_virt(paddr);
>> >
>> > +#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS
>> > +     if (unlikely(noncoherent_cache_ops.wback)) {
>>
>> I'm worried about the performance impact here.
>> For unified kernel Image reason, RISCV_NONSTANDARD_CACHE_OPS will be
>> enabled by default, so standard CMO and T-HEAD's CMO platform's
>> performance will be impacted, because even an unlikely is put
>> here, the check action still needs to be done.
>
> On IRC I asked why not use a static key so the overhead is just a
> single nop when the standard CMO ops are available, but the consensus
> seemed to be that the flushing would completely dominate this branch.
> And on platforms with the standard CMO ops the branch be correctly
> predicted anyway.

Not just the flushing, but also loading back the invalidated
cache lines afterwards is just very expensive. I don't think
you would be able to measure a difference between the static
key and a correctly predicted branch on any relevant usecase here.

     Arnd