Re: [PATCH v8 0/7] Optimize dm-verity and fsverity using multibuffer hashing
From: Ard Biesheuvel
Date: Tue Feb 18 2025 - 02:42:23 EST
On Tue, 18 Feb 2025 at 04:43, Herbert Xu <herbert@xxxxxxxxxxxxxxxxxxx> wrote:
>
> On Mon, Feb 17, 2025 at 09:40:32AM -0800, Jakub Kicinski wrote:
> >
> > Yes, that's true for tunnels and for IPsec.
> > TLS does crypto in sendmsg/recvmsg, process context.
>
> OK that's good to know. So whether SIMD is always allowed or
> not won't impact TLS at least.
>
And for IPsec, I'd assume that the cryptd fallback is only needed when
TX and RX are competing for the same CPU.
So for modern systems, I don't think the SIMD helper does anything
useful, and we should just remove it, especially if we can relax the
softirq/preemption rules for kernel SIMD on x86 like I did for arm64.