Currently arm64 does an unconditional TLB flush in mprotect(). This is not
required for some cases, for example, when changing from PROT_NONE to
PROT_READ | PROT_WRITE (a real usecase - glibc malloc does this to emulate
growing into the non-main heaps), and unsetting uffd-wp in a range.

Therefore, implement pte_needs_flush() for arm64, which is already
implemented by some other arches as well.

Running a userspace program changing permissions back and forth between
PROT_NONE and PROT_READ | PROT_WRITE, and measuring the average time taken
for the none->rw transition, I get a reduction from 3.2 microseconds to
2.95 microseconds, giving an 8.5% improvement.

Signed-off-by: Dev Jain <dev.jain@arm.com>
---
mm-selftests pass. Based on 6.17-rc6.

 arch/arm64/include/asm/tlbflush.h | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 18a5dc0c9a54..4a566d589100 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -524,6 +524,35 @@ static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *b
 {
 	__flush_tlb_range_nosync(mm, start, end, PAGE_SIZE, true, 3);
 }
+
+static inline bool __pte_flags_need_flush(pteval_t oldval, pteval_t newval)
+{
+	pteval_t diff = oldval ^ newval;
+
+	/* invalid to valid transition requires no flush */
+	if (!(oldval & PTE_VALID) || (oldval & PTE_PRESENT_INVALID))
+		return false;
+
+	/* Transition in the SW bits and access flag requires no flush */
+	diff &= ~(PTE_SWBITS_MASK | PTE_AF);
+
+	if (!diff)
+		return false;
+	return true;
+}
+
+static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte)
+{
+	return __pte_flags_need_flush(pte_val(oldpte), pte_val(newpte));
+}
+#define pte_needs_flush pte_needs_flush
+
+static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd)
+{
+	return __pte_flags_need_flush(pmd_val(oldpmd), pmd_val(newpmd));
+}
+#define huge_pmd_needs_flush huge_pmd_needs_flush
+
 #endif
 
 #endif
-- 
2.30.2

On 18/09/2025 11:36, Dev Jain wrote:
> Currently arm64 does an unconditional TLB flush in mprotect(). This is not
> required for some cases, for example, when changing from PROT_NONE to
> PROT_READ | PROT_WRITE (a real usecase - glibc malloc does this to emulate
> growing into the non-main heaps), and unsetting uffd-wp in a range.
> 
> Therefore, implement pte_needs_flush() for arm64, which is already
> implemented by some other arches as well.
> 
> Running a userspace program changing permissions back and forth between
> PROT_NONE and PROT_READ | PROT_WRITE, and measuring the average time taken
> for the none->rw transition, I get a reduction from 3.2 microseconds to
> 2.95 microseconds, giving an 8.5% improvement.
> 
> Signed-off-by: Dev Jain <dev.jain@arm.com>
> ---
> mm-selftests pass. Based on 6.17-rc6.
> 
>  arch/arm64/include/asm/tlbflush.h | 29 +++++++++++++++++++++++++++++
>  1 file changed, 29 insertions(+)
> 
> diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
> index 18a5dc0c9a54..4a566d589100 100644
> --- a/arch/arm64/include/asm/tlbflush.h
> +++ b/arch/arm64/include/asm/tlbflush.h
> @@ -524,6 +524,35 @@ static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *b
>  {
>  	__flush_tlb_range_nosync(mm, start, end, PAGE_SIZE, true, 3);
>  }
> +
> +static inline bool __pte_flags_need_flush(pteval_t oldval, pteval_t newval)

ptdesc_t is the preferred any-level type.

> +{
> +	pteval_t diff = oldval ^ newval;
> +
> +	/* invalid to valid transition requires no flush */
> +	if (!(oldval & PTE_VALID) || (oldval & PTE_PRESENT_INVALID))

Is the PTE_PRESENT_INVALID really required? If the oldval was invalid, there
can't be a TLB entry for it, so no flush is required; that's it, I think?

In fact, PTE_PRESENT_INVALID is overlaid with PTE_NG; it only means
PTE_PRESENT_INVALID when PTE_INVALID=0, so I think this is broken as is. Valid
user-space PTEs always have PTE_NG set, so you will never flush.

> +		return false;
> +
> +	/* Transition in the SW bits and access flag requires no flush */
> +	diff &= ~(PTE_SWBITS_MASK | PTE_AF);

Could you explain your thinking on why PTE_AF changes don't need a flush? I
would have thought if we want to clear the access flag, that would definitely
require a flush? Otherwise how would the MMU know to set the acccess bit on next
access if it already has a TLB entry?

> +
> +	if (!diff)
> +		return false;
> +	return true;

Perhaps just "return !!diff;" here?

Thanks,
Ryan


> +}
> +
> +static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte)
> +{
> +	return __pte_flags_need_flush(pte_val(oldpte), pte_val(newpte));
> +}
> +#define pte_needs_flush pte_needs_flush
> +
> +static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd)
> +{
> +	return __pte_flags_need_flush(pmd_val(oldpmd), pmd_val(newpmd));
> +}
> +#define huge_pmd_needs_flush huge_pmd_needs_flush
> +
>  #endif
>  
>  #endif

On 18/09/25 6:19 pm, Ryan Roberts wrote:
> On 18/09/2025 11:36, Dev Jain wrote:
>> Currently arm64 does an unconditional TLB flush in mprotect(). This is not
>> required for some cases, for example, when changing from PROT_NONE to
>> PROT_READ | PROT_WRITE (a real usecase - glibc malloc does this to emulate
>> growing into the non-main heaps), and unsetting uffd-wp in a range.
>>
>> Therefore, implement pte_needs_flush() for arm64, which is already
>> implemented by some other arches as well.
>>
>> Running a userspace program changing permissions back and forth between
>> PROT_NONE and PROT_READ | PROT_WRITE, and measuring the average time taken
>> for the none->rw transition, I get a reduction from 3.2 microseconds to
>> 2.95 microseconds, giving an 8.5% improvement.
>>
>> Signed-off-by: Dev Jain <dev.jain@arm.com>
>> ---
>> mm-selftests pass. Based on 6.17-rc6.
>>
>>   arch/arm64/include/asm/tlbflush.h | 29 +++++++++++++++++++++++++++++
>>   1 file changed, 29 insertions(+)
>>
>> diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
>> index 18a5dc0c9a54..4a566d589100 100644
>> --- a/arch/arm64/include/asm/tlbflush.h
>> +++ b/arch/arm64/include/asm/tlbflush.h
>> @@ -524,6 +524,35 @@ static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *b
>>   {
>>   	__flush_tlb_range_nosync(mm, start, end, PAGE_SIZE, true, 3);
>>   }
>> +
>> +static inline bool __pte_flags_need_flush(pteval_t oldval, pteval_t newval)
> ptdesc_t is the preferred any-level type.

I keep forgetting this :)

>
>> +{
>> +	pteval_t diff = oldval ^ newval;
>> +
>> +	/* invalid to valid transition requires no flush */
>> +	if (!(oldval & PTE_VALID) || (oldval & PTE_PRESENT_INVALID))
> Is the PTE_PRESENT_INVALID really required? If the oldval was invalid, there
> can't be a TLB entry for it, so no flush is required; that's it, I think?
>
> In fact, PTE_PRESENT_INVALID is overlaid with PTE_NG; it only means
> PTE_PRESENT_INVALID when PTE_INVALID=0, so I think this is broken as is. Valid
> user-space PTEs always have PTE_NG set, so you will never flush.

Not sure I get you. The condition as I wrote means

1. If PTE_VALID is not set, then do not flush.
2. If PTE_VALID is set, *and* PTE_PRESENT_INVALID is set, then do not flush.

So when you say "it only means PTE_PRESENT_INVALID when PTE_INVALID=0", the
second condition meets that.

>
>> +		return false;
>> +
>> +	/* Transition in the SW bits and access flag requires no flush */
>> +	diff &= ~(PTE_SWBITS_MASK | PTE_AF);
> Could you explain your thinking on why PTE_AF changes don't need a flush? I
> would have thought if we want to clear the access flag, that would definitely
> require a flush? Otherwise how would the MMU know to set the acccess bit on next
> access if it already has a TLB entry?

You are correct, but AFAIK losing access bit information is not fatal, it will only
mess with page aging. So potentially reclaim will lose some accuracy.

>
>> +
>> +	if (!diff)
>> +		return false;
>> +	return true;
> Perhaps just "return !!diff;" here?

Sure.

>
> Thanks,
> Ryan
>
>
>> +}
>> +
>> +static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte)
>> +{
>> +	return __pte_flags_need_flush(pte_val(oldpte), pte_val(newpte));
>> +}
>> +#define pte_needs_flush pte_needs_flush
>> +
>> +static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd)
>> +{
>> +	return __pte_flags_need_flush(pmd_val(oldpmd), pmd_val(newpmd));
>> +}
>> +#define huge_pmd_needs_flush huge_pmd_needs_flush
>> +
>>   #endif
>>   
>>   #endif

On 18/09/2025 16:04, Dev Jain wrote:
> 
> On 18/09/25 6:19 pm, Ryan Roberts wrote:
>> On 18/09/2025 11:36, Dev Jain wrote:
>>> Currently arm64 does an unconditional TLB flush in mprotect(). This is not
>>> required for some cases, for example, when changing from PROT_NONE to
>>> PROT_READ | PROT_WRITE (a real usecase - glibc malloc does this to emulate
>>> growing into the non-main heaps), and unsetting uffd-wp in a range.
>>>
>>> Therefore, implement pte_needs_flush() for arm64, which is already
>>> implemented by some other arches as well.
>>>
>>> Running a userspace program changing permissions back and forth between
>>> PROT_NONE and PROT_READ | PROT_WRITE, and measuring the average time taken
>>> for the none->rw transition, I get a reduction from 3.2 microseconds to
>>> 2.95 microseconds, giving an 8.5% improvement.
>>>
>>> Signed-off-by: Dev Jain <dev.jain@arm.com>
>>> ---
>>> mm-selftests pass. Based on 6.17-rc6.
>>>
>>>   arch/arm64/include/asm/tlbflush.h | 29 +++++++++++++++++++++++++++++
>>>   1 file changed, 29 insertions(+)
>>>
>>> diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/
>>> tlbflush.h
>>> index 18a5dc0c9a54..4a566d589100 100644
>>> --- a/arch/arm64/include/asm/tlbflush.h
>>> +++ b/arch/arm64/include/asm/tlbflush.h
>>> @@ -524,6 +524,35 @@ static inline void arch_tlbbatch_add_pending(struct
>>> arch_tlbflush_unmap_batch *b
>>>   {
>>>       __flush_tlb_range_nosync(mm, start, end, PAGE_SIZE, true, 3);
>>>   }
>>> +
>>> +static inline bool __pte_flags_need_flush(pteval_t oldval, pteval_t newval)
>> ptdesc_t is the preferred any-level type.
> 
> I keep forgetting this :)
> 
>>
>>> +{
>>> +    pteval_t diff = oldval ^ newval;
>>> +
>>> +    /* invalid to valid transition requires no flush */
>>> +    if (!(oldval & PTE_VALID) || (oldval & PTE_PRESENT_INVALID))
>> Is the PTE_PRESENT_INVALID really required? If the oldval was invalid, there
>> can't be a TLB entry for it, so no flush is required; that's it, I think?
>>
>> In fact, PTE_PRESENT_INVALID is overlaid with PTE_NG; it only means
>> PTE_PRESENT_INVALID when PTE_INVALID=0, so I think this is broken as is. Valid
>> user-space PTEs always have PTE_NG set, so you will never flush.
> 
> Not sure I get you. The condition as I wrote means
> 
> 1. If PTE_VALID is not set, then do not flush.
> 2. If PTE_VALID is set, *and* PTE_PRESENT_INVALID is set, then do not flush.
> 
> So when you say "it only means PTE_PRESENT_INVALID when PTE_INVALID=0", the
> second condition meets that.

Sorry I meant PTE_VALID=0. Your second condition is wrong; PTE_PRESENT_INVALID
is only defined when PTE_VALID=0.

Think about it; the PTE is valid from the HW's perspective if and only if
PTE_VALID=1. So that's the only condition that needs to be checked.


See this comment in the code for more info:

/*
 * PTE_PRESENT_INVALID=1 & PTE_VALID=0 indicates that the pte's fields should be
 * interpreted according to the HW layout by SW but any attempted HW access to
 * the address will result in a fault. pte_present() returns true.
 */
#define PTE_PRESENT_INVALID	(PTE_NG)     /* only when !PTE_VALID */


> 
>>
>>> +        return false;
>>> +
>>> +    /* Transition in the SW bits and access flag requires no flush */
>>> +    diff &= ~(PTE_SWBITS_MASK | PTE_AF);
>> Could you explain your thinking on why PTE_AF changes don't need a flush? I
>> would have thought if we want to clear the access flag, that would definitely
>> require a flush? Otherwise how would the MMU know to set the acccess bit on next
>> access if it already has a TLB entry?
> 
> You are correct, but AFAIK losing access bit information is not fatal, it will only
> mess with page aging. So potentially reclaim will lose some accuracy.

Sure, but it means that your change has a cost; reduced page aging accuracy.
That part of the change should at least be separated into its own commit and
probably backed up with performance numbers. Otherwise, I think we should retain
the original behaviour.


> 
>>
>>> +
>>> +    if (!diff)
>>> +        return false;
>>> +    return true;
>> Perhaps just "return !!diff;" here?
> 
> Sure.
> 
>>
>> Thanks,
>> Ryan
>>
>>
>>> +}
>>> +
>>> +static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte)
>>> +{
>>> +    return __pte_flags_need_flush(pte_val(oldpte), pte_val(newpte));
>>> +}
>>> +#define pte_needs_flush pte_needs_flush
>>> +
>>> +static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd)
>>> +{
>>> +    return __pte_flags_need_flush(pmd_val(oldpmd), pmd_val(newpmd));
>>> +}
>>> +#define huge_pmd_needs_flush huge_pmd_needs_flush
>>> +
>>>   #endif
>>>     #endif

On 18/09/25 8:52 pm, Ryan Roberts wrote:
> On 18/09/2025 16:04, Dev Jain wrote:
>> On 18/09/25 6:19 pm, Ryan Roberts wrote:
>>> On 18/09/2025 11:36, Dev Jain wrote:
>>>> Currently arm64 does an unconditional TLB flush in mprotect(). This is not
>>>> required for some cases, for example, when changing from PROT_NONE to
>>>> PROT_READ | PROT_WRITE (a real usecase - glibc malloc does this to emulate
>>>> growing into the non-main heaps), and unsetting uffd-wp in a range.
>>>>
>>>> Therefore, implement pte_needs_flush() for arm64, which is already
>>>> implemented by some other arches as well.
>>>>
>>>> Running a userspace program changing permissions back and forth between
>>>> PROT_NONE and PROT_READ | PROT_WRITE, and measuring the average time taken
>>>> for the none->rw transition, I get a reduction from 3.2 microseconds to
>>>> 2.95 microseconds, giving an 8.5% improvement.
>>>>
>>>> Signed-off-by: Dev Jain <dev.jain@arm.com>
>>>> ---
>>>> mm-selftests pass. Based on 6.17-rc6.
>>>>
>>>>    arch/arm64/include/asm/tlbflush.h | 29 +++++++++++++++++++++++++++++
>>>>    1 file changed, 29 insertions(+)
>>>>
>>>> diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/
>>>> tlbflush.h
>>>> index 18a5dc0c9a54..4a566d589100 100644
>>>> --- a/arch/arm64/include/asm/tlbflush.h
>>>> +++ b/arch/arm64/include/asm/tlbflush.h
>>>> @@ -524,6 +524,35 @@ static inline void arch_tlbbatch_add_pending(struct
>>>> arch_tlbflush_unmap_batch *b
>>>>    {
>>>>        __flush_tlb_range_nosync(mm, start, end, PAGE_SIZE, true, 3);
>>>>    }
>>>> +
>>>> +static inline bool __pte_flags_need_flush(pteval_t oldval, pteval_t newval)
>>> ptdesc_t is the preferred any-level type.
>> I keep forgetting this :)
>>
>>>> +{
>>>> +    pteval_t diff = oldval ^ newval;
>>>> +
>>>> +    /* invalid to valid transition requires no flush */
>>>> +    if (!(oldval & PTE_VALID) || (oldval & PTE_PRESENT_INVALID))
>>> Is the PTE_PRESENT_INVALID really required? If the oldval was invalid, there
>>> can't be a TLB entry for it, so no flush is required; that's it, I think?
>>>
>>> In fact, PTE_PRESENT_INVALID is overlaid with PTE_NG; it only means
>>> PTE_PRESENT_INVALID when PTE_INVALID=0, so I think this is broken as is. Valid
>>> user-space PTEs always have PTE_NG set, so you will never flush.
>> Not sure I get you. The condition as I wrote means
>>
>> 1. If PTE_VALID is not set, then do not flush.
>> 2. If PTE_VALID is set, *and* PTE_PRESENT_INVALID is set, then do not flush.
>>
>> So when you say "it only means PTE_PRESENT_INVALID when PTE_INVALID=0", the
>> second condition meets that.
> Sorry I meant PTE_VALID=0. Your second condition is wrong; PTE_PRESENT_INVALID
> is only defined when PTE_VALID=0.
>
> Think about it; the PTE is valid from the HW's perspective if and only if
> PTE_VALID=1. So that's the only condition that needs to be checked.
>
>
> See this comment in the code for more info:
>
> /*
>   * PTE_PRESENT_INVALID=1 & PTE_VALID=0 indicates that the pte's fields should be
>   * interpreted according to the HW layout by SW but any attempted HW access to
>   * the address will result in a fault. pte_present() returns true.
>   */
> #define PTE_PRESENT_INVALID	(PTE_NG)     /* only when !PTE_VALID */

Got it, thanks.

>
>>>> +        return false;
>>>> +
>>>> +    /* Transition in the SW bits and access flag requires no flush */
>>>> +    diff &= ~(PTE_SWBITS_MASK | PTE_AF);
>>> Could you explain your thinking on why PTE_AF changes don't need a flush? I
>>> would have thought if we want to clear the access flag, that would definitely
>>> require a flush? Otherwise how would the MMU know to set the acccess bit on next
>>> access if it already has a TLB entry?
>> You are correct, but AFAIK losing access bit information is not fatal, it will only
>> mess with page aging. So potentially reclaim will lose some accuracy.
> Sure, but it means that your change has a cost; reduced page aging accuracy.
> That part of the change should at least be separated into its own commit and
> probably backed up with performance numbers. Otherwise, I think we should retain
> the original behaviour.

You are right, I checked other callsites clearing the access bit and they do some
sort of TLB maintenance. I'll drop this.

>
>
>>>> +
>>>> +    if (!diff)
>>>> +        return false;
>>>> +    return true;
>>> Perhaps just "return !!diff;" here?
>> Sure.
>>
>>> Thanks,
>>> Ryan
>>>
>>>
>>>> +}
>>>> +
>>>> +static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte)
>>>> +{
>>>> +    return __pte_flags_need_flush(pte_val(oldpte), pte_val(newpte));
>>>> +}
>>>> +#define pte_needs_flush pte_needs_flush
>>>> +
>>>> +static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd)
>>>> +{
>>>> +    return __pte_flags_need_flush(pmd_val(oldpmd), pmd_val(newpmd));
>>>> +}
>>>> +#define huge_pmd_needs_flush huge_pmd_needs_flush
>>>> +
>>>>    #endif
>>>>      #endif

On 2025/9/18 18:36, Dev Jain wrote:
> Currently arm64 does an unconditional TLB flush in mprotect(). This is not
> required for some cases, for example, when changing from PROT_NONE to
> PROT_READ | PROT_WRITE (a real usecase - glibc malloc does this to emulate
> growing into the non-main heaps), and unsetting uffd-wp in a range.
> 
> Therefore, implement pte_needs_flush() for arm64, which is already
> implemented by some other arches as well.
> 
> Running a userspace program changing permissions back and forth between
> PROT_NONE and PROT_READ | PROT_WRITE, and measuring the average time taken
> for the none->rw transition, I get a reduction from 3.2 microseconds to
> 2.95 microseconds, giving an 8.5% improvement.
> 

Hi Dev，

> Signed-off-by: Dev Jain <dev.jain@arm.com>
> ---
> mm-selftests pass. Based on 6.17-rc6.
> 
>   arch/arm64/include/asm/tlbflush.h | 29 +++++++++++++++++++++++++++++
>   1 file changed, 29 insertions(+)
> 
> diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
> index 18a5dc0c9a54..4a566d589100 100644
> --- a/arch/arm64/include/asm/tlbflush.h
> +++ b/arch/arm64/include/asm/tlbflush.h
> @@ -524,6 +524,35 @@ static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *b
>   {
>   	__flush_tlb_range_nosync(mm, start, end, PAGE_SIZE, true, 3);
>   }
> +
> +static inline bool __pte_flags_need_flush(pteval_t oldval, pteval_t newval)
> +{
> +	pteval_t diff = oldval ^ newval;
> +
> +	/* invalid to valid transition requires no flush */
> +	if (!(oldval & PTE_VALID) || (oldval & PTE_PRESENT_INVALID))
> +		return false;
> +
> +	/* Transition in the SW bits and access flag requires no flush */
> +	diff &= ~(PTE_SWBITS_MASK | PTE_AF);
> +
> +	if (!diff)
> +		return false;
> +	return true;
> +}
> +

LibMicro mprotect testcase show 3~5% improvement with different size in
old kernel(we did this before, but only check PTE_VALID and 
PTE_PROT_NONE in our kernel), it seems that no one change other sw bit 
by mprotect?

Anyway, Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com>

> +static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte)
> +{
> +	return __pte_flags_need_flush(pte_val(oldpte), pte_val(newpte));
> +}
> +#define pte_needs_flush pte_needs_flush
> +
> +static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd)
> +{
> +	return __pte_flags_need_flush(pmd_val(oldpmd), pmd_val(newpmd));
> +}
> +#define huge_pmd_needs_flush huge_pmd_needs_flush
> +
>   #endif
>   
>   #endif

On 18/09/25 5:52 pm, Kefeng Wang wrote:
>
>
> On 2025/9/18 18:36, Dev Jain wrote:
>> Currently arm64 does an unconditional TLB flush in mprotect(). This 
>> is not
>> required for some cases, for example, when changing from PROT_NONE to
>> PROT_READ | PROT_WRITE (a real usecase - glibc malloc does this to 
>> emulate
>> growing into the non-main heaps), and unsetting uffd-wp in a range.
>>
>> Therefore, implement pte_needs_flush() for arm64, which is already
>> implemented by some other arches as well.
>>
>> Running a userspace program changing permissions back and forth between
>> PROT_NONE and PROT_READ | PROT_WRITE, and measuring the average time 
>> taken
>> for the none->rw transition, I get a reduction from 3.2 microseconds to
>> 2.95 microseconds, giving an 8.5% improvement.
>>
>
> Hi Dev，
>
>> Signed-off-by: Dev Jain <dev.jain@arm.com>
>> ---
>> mm-selftests pass. Based on 6.17-rc6.
>>
>>   arch/arm64/include/asm/tlbflush.h | 29 +++++++++++++++++++++++++++++
>>   1 file changed, 29 insertions(+)
>>
>> diff --git a/arch/arm64/include/asm/tlbflush.h 
>> b/arch/arm64/include/asm/tlbflush.h
>> index 18a5dc0c9a54..4a566d589100 100644
>> --- a/arch/arm64/include/asm/tlbflush.h
>> +++ b/arch/arm64/include/asm/tlbflush.h
>> @@ -524,6 +524,35 @@ static inline void 
>> arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *b
>>   {
>>       __flush_tlb_range_nosync(mm, start, end, PAGE_SIZE, true, 3);
>>   }
>> +
>> +static inline bool __pte_flags_need_flush(pteval_t oldval, pteval_t 
>> newval)
>> +{
>> +    pteval_t diff = oldval ^ newval;
>> +
>> +    /* invalid to valid transition requires no flush */
>> +    if (!(oldval & PTE_VALID) || (oldval & PTE_PRESENT_INVALID))
>> +        return false;
>> +
>> +    /* Transition in the SW bits and access flag requires no flush */
>> +    diff &= ~(PTE_SWBITS_MASK | PTE_AF);
>> +
>> +    if (!diff)
>> +        return false;
>> +    return true;
>> +}
>> +
>
> LibMicro mprotect testcase show 3~5% improvement with different size in
> old kernel(we did this before, but only check PTE_VALID and 
> PTE_PROT_NONE in our kernel), it seems that no one change other sw bit 
> by mprotect?

Not mprotect, but when unsetting uffd-wp, we do mwriteprotect_range -> 
uffd_wp_range -> change_protection() with MM_CP_UFFD_WP_RESOLVE set.


>
> Anyway, Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com>

Thanks!


>
>> +static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte)
>> +{
>> +    return __pte_flags_need_flush(pte_val(oldpte), pte_val(newpte));
>> +}
>> +#define pte_needs_flush pte_needs_flush
>> +
>> +static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd)
>> +{
>> +    return __pte_flags_need_flush(pmd_val(oldpmd), pmd_val(newpmd));
>> +}
>> +#define huge_pmd_needs_flush huge_pmd_needs_flush
>> +
>>   #endif
>>     #endif
>