Re: [PATCH] LoongArch: Make WriteCombine configurable for ioremap()

[WANG Xuerui]

On 2023/3/14 16:54, Huacai Chen wrote:
> LoongArch maintains cache coherency in hardware, but when works with

but when paired with current LS7A chipsets

> LS7A chipsets the WUC attribute (Weak-ordered UnCached, which is similar
> to WriteCombine) is out of the scope of cache coherency machanism for
> PCIe devices (this is a PCIe protocol violation, may be fixed in newer

which may be fixed

> chipsets).
>
> This means WUC can only used for write-only memory regions now, so this
> option is disabled by default (means WUC falls back to SUC for ioremap).

by default, making ioremap_wc silently fallback to SUC.

> You can enable this option if the kernel is ensured to run on bug-free
> hardwares.

if you can ensure the kernel will always be running on hardware without 
this bug

> Suggested-by: WANG Xuerui <kernel@xxxxxxxxxx>
> Signed-off-by: Huacai Chen <chenhuacai@xxxxxxxxxxx>
> ---
>   arch/loongarch/Kconfig          | 14 ++++++++++++++
>   arch/loongarch/include/asm/io.h |  5 +++++
>   2 files changed, 19 insertions(+)
>
> diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
> index 0d11738a861a..e3f5c422636f 100644
> --- a/arch/loongarch/Kconfig
> +++ b/arch/loongarch/Kconfig
> @@ -446,6 +446,20 @@ config ARCH_IOREMAP
>   	  protection support. However, you can enable LoongArch DMW-based
>   	  ioremap() for better performance.
>   
> +config ARCH_WRITECOMBINE
> +	bool "Enable WriteCombine (WUC) for ioremap()"
> +	help
> +	  LoongArch maintains cache coherency in hardware, but with LS7A
> +	  chipsets the WUC attribute (Weak-ordered UnCached, which is similar
> +	  to WriteCombine) is out of the scope of cache coherency machanism
> +	  for PCIe devices (this is a PCIe protocol violation, may be fixed
> +	  in newer chipsets).
> +
> +	  This means WUC can only used for write-only memory regions now, so
> +	  this option is disabled by default (means WUC falls back to SUC for
> +	  ioremap). You can enable this option if the kernel is ensured to run
> +	  on bug-free hardwares.

Fix text here like with the commit message.

Then add a "If unsure, say N" line to serve as a warning?

> +
>   config ARCH_STRICT_ALIGN
>   	bool "Enable -mstrict-align to prevent unaligned accesses" if EXPERT
>   	default y
> diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h
> index 402a7d9e3a53..079ef897ed1a 100644
> --- a/arch/loongarch/include/asm/io.h
> +++ b/arch/loongarch/include/asm/io.h
> @@ -54,8 +54,13 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
>    * @offset:    bus address of the memory
>    * @size:      size of the resource to map
>    */
> +#ifdef CONFIG_ARCH_WRITECOMBINE
>   #define ioremap_wc(offset, size)	\
>   	ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL_WUC))
> +#else
> +#define ioremap_wc(offset, size)	\
> +	ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL_SUC))
> +#endif
>   
>   #define ioremap_cache(offset, size)	\
>   	ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL))

I'll test this later tonight with my RX 6400. See you in a few hours...

--
WANG "xen0n" Xuerui

Linux/LoongArch mailing list: https://lore.kernel.org/loongarch/