Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:6 as permitted sender) client-ip=2620:137:e000::3:6;
Message-ID: <41b3c8c8-260d-4de1-92a4-245973274a60@rivosinc.com>
Date:   Thu, 12 Oct 2023 14:43:18 +0200
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH v2 1/2] riscv: errata: thead: use riscv_nonstd_cache_ops
 for CMO
Content-Language: en-US
To:     Jisheng Zhang <jszhang@kernel.org>,
        Paul Walmsley <paul.walmsley@sifive.com>,
        Palmer Dabbelt <palmer@dabbelt.com>,
        Albert Ou <aou@eecs.berkeley.edu>
Cc:     Guo Ren <guoren@kernel.org>, linux-riscv@lists.infradead.org,
        linux-kernel@vger.kernel.org,
        Emil Renner Berthing <emil.renner.berthing@canonical.com>
References: <20231001103433.3187-1-jszhang@kernel.org>
 <20231001103433.3187-2-jszhang@kernel.org>
From:   =?UTF-8?B?Q2zDqW1lbnQgTMOpZ2Vy?= <cleger@rivosinc.com>
In-Reply-To: <20231001103433.3187-2-jszhang@kernel.org>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Precedence: bulk


On 01/10/2023 12:34, Jisheng Zhang wrote:
> Previously, we use alternative mechanism to dynamically patch
> the CMO operations for THEAD C906/C910 during boot for performance
> reason. But as pointed out by Arnd, "there is already a significant
> cost in accessing the invalidated cache lines afterwards, which is
> likely going to be much higher than the cost of an indirect branch".
> And indeed, there's no performance difference with GMAC and EMMC per
> my test on Sipeed Lichee Pi 4A board.
> 
> Use riscv_nonstd_cache_ops for THEAD C906/C910 CMO to simplify
> the alternative code, and to acchieve Arnd's goal -- "I think
> moving the THEAD ops at the same level as all nonstandard operations
> makes sense, but I'd still leave CMO as an explicit fast path that
> avoids the indirect branch. This seems like the right thing to do both
> for readability and for platforms on which the indirect branch has a
> noticeable overhead."
> 
> Signed-off-by: Jisheng Zhang <jszhang@kernel.org>
> Tested-by: Emil Renner Berthing <emil.renner.berthing@canonical.com>
> ---
>  arch/riscv/Kconfig.errata            |  1 +
>  arch/riscv/errata/thead/errata.c     | 75 +++++++++++++++++++++++++++-
>  arch/riscv/include/asm/errata_list.h | 50 +++----------------
>  3 files changed, 80 insertions(+), 46 deletions(-)
> 
> diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata
> index 566bcefeab50..d7972914f9de 100644
> --- a/arch/riscv/Kconfig.errata
> +++ b/arch/riscv/Kconfig.errata
> @@ -78,6 +78,7 @@ config ERRATA_THEAD_CMO
>  	bool "Apply T-Head cache management errata"
>  	depends on ERRATA_THEAD && MMU
>  	select RISCV_DMA_NONCOHERENT
> +	select RISCV_NONSTANDARD_CACHE_OPS
>  	default y
>  	help
>  	  This will apply the cache management errata to handle the
> diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c
> index 0554ed4bf087..3fefeb1b456e 100644
> --- a/arch/riscv/errata/thead/errata.c
> +++ b/arch/riscv/errata/thead/errata.c
> @@ -12,8 +12,10 @@
>  #include <asm/alternative.h>
>  #include <asm/cacheflush.h>
>  #include <asm/cpufeature.h>
> +#include <asm/dma-noncoherent.h>
>  #include <asm/errata_list.h>
>  #include <asm/hwprobe.h>
> +#include <asm/io.h>
>  #include <asm/patch.h>
>  #include <asm/vendorid_list.h>
>  
> @@ -33,6 +35,75 @@ static bool errata_probe_pbmt(unsigned int stage,
>  	return false;
>  }
>  
> +/*
> + * dcache.ipa rs1 (invalidate, physical address)
> + * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
> + *   0000001    01010      rs1       000      00000  0001011
> + * dache.iva rs1 (invalida, virtual address)

Small typo here: invalidate instead of invalida

Thanks,

Clément