Re: [PATCH v6 RESED 1/2] dma: replace zone_dma_bits by zone_dma_limit

[Will Deacon <will@kernel.org>]

On Sun, Aug 11, 2024 at 10:09:35AM +0300, Baruch Siach wrote:
> From: Catalin Marinas <catalin.marinas@arm.com>
> 
> Hardware DMA limit might not be power of 2. When RAM range starts above
> 0, say 4GB, DMA limit of 30 bits should end at 5GB. A single high bit
> can not encode this limit.
> 
> Use plain address for DMA zone limit.
> 
> Since DMA zone can now potentially span beyond 4GB physical limit of
> DMA32, make sure to use DMA zone for GFP_DMA32 allocations in that case.
> 
> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
> Co-developed-by: Baruch Siach <baruch@tkos.co.il>
> Signed-off-by: Baruch Siach <baruch@tkos.co.il>
> ---
>  arch/arm64/mm/init.c       | 30 +++++++++++++++---------------
>  arch/powerpc/mm/mem.c      |  5 ++++-
>  arch/s390/mm/init.c        |  2 +-
>  include/linux/dma-direct.h |  2 +-
>  kernel/dma/direct.c        |  6 +++---
>  kernel/dma/pool.c          |  4 ++--
>  kernel/dma/swiotlb.c       |  6 +++---
>  7 files changed, 29 insertions(+), 26 deletions(-)
> 
> diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
> index 9b5ab6818f7f..c45e2152ca9e 100644
> --- a/arch/arm64/mm/init.c
> +++ b/arch/arm64/mm/init.c
> @@ -115,35 +115,35 @@ static void __init arch_reserve_crashkernel(void)
>  }
>  
>  /*
> - * Return the maximum physical address for a zone accessible by the given bits
> - * limit. If DRAM starts above 32-bit, expand the zone to the maximum
> + * Return the maximum physical address for a zone given its limit.
> + * If DRAM starts above 32-bit, expand the zone to the maximum
>   * available memory, otherwise cap it at 32-bit.
>   */
> -static phys_addr_t __init max_zone_phys(unsigned int zone_bits)
> +static phys_addr_t __init max_zone_phys(phys_addr_t zone_limit)
>  {
> -	phys_addr_t zone_mask = DMA_BIT_MASK(zone_bits);
>  	phys_addr_t phys_start = memblock_start_of_DRAM();
>  
>  	if (phys_start > U32_MAX)
> -		zone_mask = PHYS_ADDR_MAX;
> -	else if (phys_start > zone_mask)
> -		zone_mask = U32_MAX;
> +		zone_limit = PHYS_ADDR_MAX;
> +	else if (phys_start > zone_limit)
> +		zone_limit = U32_MAX;
>  
> -	return min(zone_mask, memblock_end_of_DRAM() - 1) + 1;
> +	return min(zone_limit, memblock_end_of_DRAM() - 1) + 1;

Why do we need to adjust +-1 now that we're no longer using a mask?

>  }
>  
>  static void __init zone_sizes_init(void)
>  {
>  	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
> -	unsigned int __maybe_unused acpi_zone_dma_bits;
> -	unsigned int __maybe_unused dt_zone_dma_bits;
> -	phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32);
> +	phys_addr_t __maybe_unused acpi_zone_dma_limit;
> +	phys_addr_t __maybe_unused dt_zone_dma_limit;
> +	phys_addr_t __maybe_unused dma32_phys_limit =
> +		max_zone_phys(DMA_BIT_MASK(32));
>  
>  #ifdef CONFIG_ZONE_DMA
> -	acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address());
> -	dt_zone_dma_bits = fls64(of_dma_get_max_cpu_address(NULL));
> -	zone_dma_bits = min3(32U, dt_zone_dma_bits, acpi_zone_dma_bits);
> -	arm64_dma_phys_limit = max_zone_phys(zone_dma_bits);
> +	acpi_zone_dma_limit = acpi_iort_dma_get_max_cpu_address();
> +	dt_zone_dma_limit = of_dma_get_max_cpu_address(NULL);
> +	zone_dma_limit = min(dt_zone_dma_limit, acpi_zone_dma_limit);
> +	arm64_dma_phys_limit = max_zone_phys(zone_dma_limit);
>  	max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
>  #endif

Maybe move this block into a helper function so we can avoid three
__maybe_unused variables?

Will