[PATCH 3/6] arm64: Provide dcache_inval_poc_nosync helper

[Robin Murphy]

On 2025-12-19 5:36 am, Barry Song wrote:
> From: Barry Song <v-songbaohua at oppo.com>
> 
> dcache_inval_poc_nosync does not wait for the data cache invalidation to
> complete. Later, we defer the synchronization so we can wait for all SG
> entries together.
> 
> Cc: Catalin Marinas <catalin.marinas at arm.com>
> Cc: Will Deacon <will at kernel.org>
> Cc: Marek Szyprowski <m.szyprowski at samsung.com>
> Cc: Robin Murphy <robin.murphy at arm.com>
> Cc: Ada Couprie Diaz <ada.coupriediaz at arm.com>
> Cc: Ard Biesheuvel <ardb at kernel.org>
> Cc: Marc Zyngier <maz at kernel.org>
> Cc: Anshuman Khandual <anshuman.khandual at arm.com>
> Cc: Ryan Roberts <ryan.roberts at arm.com>
> Cc: Suren Baghdasaryan <surenb at google.com>
> Cc: Tangquan Zheng <zhengtangquan at oppo.com>
> Signed-off-by: Barry Song <v-songbaohua at oppo.com>
> ---
>   arch/arm64/include/asm/cacheflush.h |  1 +
>   arch/arm64/mm/cache.S               | 43 +++++++++++++++++++++--------
>   2 files changed, 33 insertions(+), 11 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
> index 9b6d0a62cf3d..382b4ac3734d 100644
> --- a/arch/arm64/include/asm/cacheflush.h
> +++ b/arch/arm64/include/asm/cacheflush.h
> @@ -74,6 +74,7 @@ extern void icache_inval_pou(unsigned long start, unsigned long end);
>   extern void dcache_clean_inval_poc(unsigned long start, unsigned long end);
>   extern void dcache_inval_poc(unsigned long start, unsigned long end);
>   extern void dcache_clean_poc(unsigned long start, unsigned long end);
> +extern void dcache_inval_poc_nosync(unsigned long start, unsigned long end);
>   extern void dcache_clean_poc_nosync(unsigned long start, unsigned long end);
>   extern void dcache_clean_pop(unsigned long start, unsigned long end);
>   extern void dcache_clean_pou(unsigned long start, unsigned long end);
> diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
> index 4a7c7e03785d..8c1043c9b9e5 100644
> --- a/arch/arm64/mm/cache.S
> +++ b/arch/arm64/mm/cache.S
> @@ -132,17 +132,7 @@ alternative_else_nop_endif
>   	ret
>   SYM_FUNC_END(dcache_clean_pou)
>   
> -/*
> - *	dcache_inval_poc(start, end)
> - *
> - * 	Ensure that any D-cache lines for the interval [start, end)
> - * 	are invalidated. Any partial lines at the ends of the interval are
> - *	also cleaned to PoC to prevent data loss.
> - *
> - *	- start   - kernel start address of region
> - *	- end     - kernel end address of region
> - */
> -SYM_FUNC_START(__pi_dcache_inval_poc)
> +.macro _dcache_inval_poc_impl, do_sync
>   	dcache_line_size x2, x3
>   	sub	x3, x2, #1
>   	tst	x1, x3				// end cache line aligned?
> @@ -158,11 +148,42 @@ SYM_FUNC_START(__pi_dcache_inval_poc)
>   3:	add	x0, x0, x2
>   	cmp	x0, x1
>   	b.lo	2b
> +.if \do_sync
>   	dsb	sy
> +.endif

Similarly, don't bother with complication like this, just put the DSB in 
the one place it needs to be.

Thanks,
Robin.

>   	ret
> +.endm
> +
> +/*
> + *	dcache_inval_poc(start, end)
> + *
> + * 	Ensure that any D-cache lines for the interval [start, end)
> + * 	are invalidated. Any partial lines at the ends of the interval are
> + *	also cleaned to PoC to prevent data loss.
> + *
> + *	- start   - kernel start address of region
> + *	- end     - kernel end address of region
> + */
> +SYM_FUNC_START(__pi_dcache_inval_poc)
> +	_dcache_inval_poc_impl 1
>   SYM_FUNC_END(__pi_dcache_inval_poc)
>   SYM_FUNC_ALIAS(dcache_inval_poc, __pi_dcache_inval_poc)
>   
> +/*
> + *	dcache_inval_poc_nosync(start, end)
> + *
> + * 	Issue the instructions of D-cache lines for the interval [start, end)
> + * 	for invalidation. Not necessarily cleaned to PoC till an explicit dsb
> + *	sy later
> + *
> + *	- start   - kernel start address of region
> + *	- end     - kernel end address of region
> + */
> +SYM_FUNC_START(__pi_dcache_inval_poc_nosync)
> +	_dcache_inval_poc_impl 0
> +SYM_FUNC_END(__pi_dcache_inval_poc_nosync)
> +SYM_FUNC_ALIAS(dcache_inval_poc_nosync, __pi_dcache_inval_poc_nosync)
> +
>   /*
>    *	dcache_clean_poc(start, end)
>    *