Received-SPF: pass (google.com: domain of linux-kernel+bounces-112799-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Precedence: bulk
MIME-Version: 1.0
References: <20240322112629.68170-1-alexghiti@rivosinc.com> <20240323062625.2488-1-dqfext@gmail.com>
In-Reply-To: <20240323062625.2488-1-dqfext@gmail.com>
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Sun, 24 Mar 2024 19:19:56 +0100
Message-ID: <CAHVXubisa6HQJDbj_GfjwhP1Y4as0DzrxsU0B7N6DSU6HZNaaw@mail.gmail.com>
Subject: Re: [PATCH] riscv: Improve sbi_ecall() code generation by reordering arguments
To: Qingfang Deng <dqfext@gmail.com>
Cc: aou@eecs.berkeley.edu, linux-kernel@vger.kernel.org, 
	linux-riscv@lists.infradead.org, palmer@dabbelt.com, paul.walmsley@sifive.com, 
	samuel.holland@sifive.com
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

Hi Qingfang,

On Sat, Mar 23, 2024 at 7:26=E2=80=AFAM Qingfang Deng <dqfext@gmail.com> wr=
ote:
>
> Hi Alexandre,
>
> You can simply make sbi_ecall `__always_inline`, so the C function call
> overhead can be fully avoided.

I understand your point, though I don't think we need to mark
sbi_ecall() as inline, it's not in any hot path so it's not worth it.
This patch simply gets rid of a really useless overhead, but it does
not visibly accelerate anything.

I hope it makes sense,

Thanks,

Alex