linux-kernel - Re: [PATCH 09/10] arm64: mm: Simplify __flush_tlb_range_limit

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <b10fd873-6de9-445a-a43a-cd588b433f42@arm.com>
Date: Mon, 14 Jul 2025 10:30:29 +0100
From: Ryan Roberts <ryan.roberts@....com>
To: Will Deacon <will@...nel.org>, linux-arm-kernel@...ts.infradead.org
Cc: linux-kernel@...r.kernel.org, Ard Biesheuvel <ardb@...nel.org>,
 Catalin Marinas <catalin.marinas@....com>,
 Mark Rutland <mark.rutland@....com>,
 Linus Torvalds <torvalds@...ux-foundation.org>,
 Oliver Upton <oliver.upton@...ux.dev>, Marc Zyngier <maz@...nel.org>
Subject: Re: [PATCH 09/10] arm64: mm: Simplify
 __flush_tlb_range_limit_excess()

On 11/07/2025 17:17, Will Deacon wrote:
> __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@...nel.org>

Does this warrant a Fixes: tag?

> ---
>  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 8618a85d5cd3..2541863721af 100644
> --- a/arch/arm64/include/asm/tlbflush.h
> +++ b/arch/arm64/include/asm/tlbflush.h
> @@ -470,21 +470,13 @@ do {									\
>  #define __flush_s2_tlb_range_op(op, start, pages, stride, tlb_level) \
>  	__flush_tlb_range_op(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;
>  }

I'm still not sure I totally get this... Aren't these really 2 separate
concepts? MAX_TLBI_RANGE_PAGES is the max amount of VA that can be handled by a
single tlbi-by-range (and due to implementation, the largest range that can be
handled by the loop in __flush_tlb_range_op()). Whereas MAX_DVM_OPS is the max
number of tlbi instrcutions you want to issue with the PTL held? Perhaps it is
better to split these out; For the range case, calculate the number of ops you
actually need and compare with MAX_DVM_OPS?


>  
>  static inline void __flush_tlb_range_nosync(struct mm_struct *mm,
> @@ -498,7 +490,7 @@ 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;
>  	}
> @@ -547,7 +539,7 @@ 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;
>  	}