Received-SPF: pass (google.com: domain of linux-kernel+bounces-9129-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
Feedback-ID: ifd894703:Fastmail
Message-ID: <f31d929c-fa0a-4046-be05-38e92afa5d92@flygoat.com>
Date: Thu, 21 Dec 2023 22:27:33 +0000
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCH 1/1] riscv: set ARCH_DMA_DEFAULT_COHERENT if
 RISCV_DMA_NONCOHERENT is not set
Content-Language: en-US
To: Maxim Kochetkov <fido_max@inbox.ru>
Cc: linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org,
 robh@kernel.org, mpe@ellerman.id.au, aou@eecs.berkeley.edu,
 palmer@dabbelt.com, paul.walmsley@sifive.com, Conor Dooley
 <conor@kernel.org>, hch@lst.de
References: <20231221185152.327231-1-fido_max@inbox.ru>
 <20231221-discount-decade-e306e5878c46@spud>
From: Jiaxun Yang <jiaxun.yang@flygoat.com>
In-Reply-To: <20231221-discount-decade-e306e5878c46@spud>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit


在 2023/12/21 20:29, Conor Dooley 写道:
> + Christoph
>
> I don't think this patch is correct. Regardless of whether we support
> cache management operations, DMA is assumed to be coherent unless
> peripherals etc are specified to otherwise in DT (or however ACPI deals
> with that kind of thing).
>
> What problem are you trying to solve here?
>
> On Thu, Dec 21, 2023 at 09:51:52PM +0300, Maxim Kochetkov wrote:
>> Not all the RISCV are DMA coherent by default.

Sorry for chime in here.
IMO if your platform is not coherent by default, just insert 
"dma-noncoherent"
at devicetree root node.

Thanks
- Jiaxun

> What is a "RISCV"? I believe this sentence should be "not all RISC-V
> systems are DMA coherent." but that is provided for by the
> "dma-noncoherent" property, set for peripherals (or buses) that are not
> DMA coherent.
>
>> Moreover we have
>> RISCV_DMA_NONCOHERENT option.
>> So set ARCH_DMA_DEFAULT_COHERENT only when RISCV_DMA_NONCOHERENT is not set
>>
>> Fixes: c00a60d6f4a1 ("of: address: always use dma_default_coherent for default coherency")
>> Signed-off-by: Maxim Kochetkov <fido_max@inbox.ru>
>> ---
>>   arch/riscv/Kconfig | 2 +-
>>   1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
>> index d6824bec2c00..111c5d92d503 100644
>> --- a/arch/riscv/Kconfig
>> +++ b/arch/riscv/Kconfig
>> @@ -14,7 +14,7 @@ config RISCV
>>   	def_bool y
>>   	select ACPI_GENERIC_GSI if ACPI
>>   	select ACPI_REDUCED_HARDWARE_ONLY if ACPI
>> -	select ARCH_DMA_DEFAULT_COHERENT
>> +	select ARCH_DMA_DEFAULT_COHERENT if !RISCV_DMA_NONCOHERENT
> I think this is actually buggy, for things like distro kernels
> RISCV_DMA_COHERENT will always be set, but those kernels are expected
> to be used on systems that are cache coherent also.
>
> Thanks,
> Conor.
>
>>   	select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION
>>   	select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
>>   	select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
>> -- 
>> 2.40.1
>>
>>
>> _______________________________________________
>> linux-riscv mailing list
>> linux-riscv@lists.infradead.org
>> http://lists.infradead.org/mailman/listinfo/linux-riscv