1. Patchew
  2. linux
  3. [PATCH v1 00/13] arm64: Refactor TLB invalidation API and implementation
  4. View patch

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

Ryan Roberts posted 13 patches 1 month, 3 weeks ago
There is a newer version of this series
[PATCH v1 08/13] arm64: mm: Simplify __flush_tlb_range_limit_excess()
Posted by Ryan Roberts 1 month, 3 weeks ago 
From: Will Deacon <will@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@kernel.org>
Signed-off-by: Ryan Roberts <ryan.roberts@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;
 }
 
 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;
 	}
-- 
2.43.0
Re: [PATCH v1 08/13] arm64: mm: Simplify __flush_tlb_range_limit_excess()
Posted by Dev Jain 1 month, 3 weeks ago 
On 16/12/25 8:15 pm, Ryan Roberts wrote:
> From: Will Deacon <will@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@kernel.org>
> Signed-off-by: Ryan Roberts <ryan.roberts@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;
>  	}
Re: [PATCH v1 08/13] arm64: mm: Simplify __flush_tlb_range_limit_excess()
Posted by Ryan Roberts 1 month, 1 week ago 
On 17/12/2025 08:12, Dev Jain wrote:
> 
> On 16/12/25 8:15 pm, Ryan Roberts wrote:
>> From: Will Deacon <will@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@kernel.org>
>> Signed-off-by: Ryan Roberts <ryan.roberts@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/

I agree with your overall proposal, but I think a few of the details are not
quite correct.

I think the max number of DVM ops that could be issued by a single
__flush_tlb_range() call on a system with tlb-range is 20, not 4 as you suggest;

- 4 for each of the scales
- 1 for the final single page
- 15 to align to a 64K boundary on systems with LPA2 (with 4K page size)

But that doesn't really change your argument.

So proposing to change it to this in next version:

static inline bool __flush_tlb_range_limit_excess(unsigned long pages,
						  unsigned long stride)
{
	/*
	 * Assume that the worst case number of DVM ops required to flush a
	 * given range on a system that supports tlb-range is 20 (4 scales, 1
	 * final page, 15 for alignment on LPA2 systems), which is much smaller
	 * than MAX_DVM_OPS.
	 */
	if (system_supports_tlb_range())
		return pages > MAX_TLBI_RANGE_PAGES;

	return pages >= (MAX_DVM_OPS * stride) >> PAGE_SHIFT;
}

Thanks,
Ryan

> 
>>  }
>>  
>>  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;
>>  	}

Patchew 2.1-devel-b67e4c2

© 2016 - 2026 Red Hat, Inc.