[PATCH v1 08/13] arm64: mm: Simplify __flush_tlb_range_limit_excess()

[Dev Jain]

On 16/12/25 8:15 pm, Ryan Roberts wrote:
> From: Will Deacon <will at kernel.org>
>
> __flush_tlb_range_limit_excess() is unnecessarily complicated:
>
>   - It takes a 'start', 'end' and 'pages' argument, whereas it only
>     needs 'pages' (which the caller has computed from the other two
>     arguments!).
>
>   - It erroneously compares 'pages' with MAX_TLBI_RANGE_PAGES when
>     the system doesn't support range-based invalidation but the range to
>     be invalidated would result in fewer than MAX_DVM_OPS invalidations.
>
> Simplify the function so that it no longer takes the 'start' and 'end'
> arguments and only considers the MAX_TLBI_RANGE_PAGES threshold on
> systems that implement range-based invalidation.
>
> Signed-off-by: Will Deacon <will at kernel.org>
> Signed-off-by: Ryan Roberts <ryan.roberts at arm.com>
> ---
>  arch/arm64/include/asm/tlbflush.h | 20 ++++++--------------
>  1 file changed, 6 insertions(+), 14 deletions(-)
>
> diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
> index 0e1902f66e01..3b72a71feac0 100644
> --- a/arch/arm64/include/asm/tlbflush.h
> +++ b/arch/arm64/include/asm/tlbflush.h
> @@ -527,21 +527,13 @@ static __always_inline void __flush_tlb_range_op(tlbi_op lop, tlbi_op rop,
>  #define __flush_s2_tlb_range_op(op, start, pages, stride, tlb_level) \
>  	__flush_tlb_range_op(op, r##op, start, pages, stride, 0, tlb_level, kvm_lpa2_is_enabled())
>  
> -static inline bool __flush_tlb_range_limit_excess(unsigned long start,
> -		unsigned long end, unsigned long pages, unsigned long stride)
> +static inline bool __flush_tlb_range_limit_excess(unsigned long pages,
> +						  unsigned long stride)
>  {
> -	/*
> -	 * When the system does not support TLB range based flush
> -	 * operation, (MAX_DVM_OPS - 1) pages can be handled. But
> -	 * with TLB range based operation, MAX_TLBI_RANGE_PAGES
> -	 * pages can be handled.
> -	 */
> -	if ((!system_supports_tlb_range() &&
> -	     (end - start) >= (MAX_DVM_OPS * stride)) ||
> -	    pages > MAX_TLBI_RANGE_PAGES)
> +	if (system_supports_tlb_range() && pages > MAX_TLBI_RANGE_PAGES)
>  		return true;
>  
> -	return false;
> +	return pages >= (MAX_DVM_OPS * stride) >> PAGE_SHIFT;

The function will return true if tlb range is supported, but
((MAX_DVM_OPS * stride) >> PAGE_SHIFT) < pages <= MAX_TLBI_RANGE_PAGES.
So I think you need to do
https://lore.kernel.org/all/1b15b4f0-5490-4dac-8344-e716dd189751@arm.com/

>  }
>  
>  static inline void __flush_tlb_range_nosync(struct mm_struct *mm,
> @@ -555,7 +547,7 @@ static inline void __flush_tlb_range_nosync(struct mm_struct *mm,
>  	end = round_up(end, stride);
>  	pages = (end - start) >> PAGE_SHIFT;
>  
> -	if (__flush_tlb_range_limit_excess(start, end, pages, stride)) {
> +	if (__flush_tlb_range_limit_excess(pages, stride)) {
>  		flush_tlb_mm(mm);
>  		return;
>  	}
> @@ -619,7 +611,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
>  	end = round_up(end, stride);
>  	pages = (end - start) >> PAGE_SHIFT;
>  
> -	if (__flush_tlb_range_limit_excess(start, end, pages, stride)) {
> +	if (__flush_tlb_range_limit_excess(pages, stride)) {
>  		flush_tlb_all();
>  		return;
>  	}