Received-SPF: pass (google.com: domain of linux-crypto-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Wed, 12 Oct 2022 23:03:13 -0700
From:   Eric Biggers <ebiggers@kernel.org>
To:     Robert Elliott <elliott@hpe.com>
Cc:     herbert@gondor.apana.org.au, davem@davemloft.net,
        tim.c.chen@linux.intel.com, ap420073@gmail.com, ardb@kernel.org,
        linux-crypto@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 08/19] crypto: x86/ghash - limit FPU preemption
Message-ID: <Y0eqIQ9PC3Edd+D/@sol.localdomain>
References: <20221006223151.22159-1-elliott@hpe.com>
 <20221012215931.3896-1-elliott@hpe.com>
 <20221012215931.3896-9-elliott@hpe.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20221012215931.3896-9-elliott@hpe.com>
Precedence: bulk

On Wed, Oct 12, 2022 at 04:59:20PM -0500, Robert Elliott wrote:
> -	kernel_fpu_begin();
> -	clmul_ghash_update(dst, src, srclen, &ctx->shash);
> -	kernel_fpu_end();
> +	while (srclen >= GHASH_BLOCK_SIZE) {
> +		unsigned int fpulen = min(srclen, FPU_BYTES);
> +
> +		kernel_fpu_begin();
> +		while (fpulen >= GHASH_BLOCK_SIZE) {
> +			int n = min_t(unsigned int, fpulen, GHASH_BLOCK_SIZE);
> +
> +			clmul_ghash_update(dst, src, n, &ctx->shash);
> +
> +			srclen -= n;
> +			fpulen -= n;
> +			src += n;
> +		}
> +		kernel_fpu_end();
> +	}

Another loop that doesn't make sense.  Why is this only passing 16 bytes at a
time into the assembly code?  There shouldn't be an inner loop here at all.

- Eric