[PATCH v1 02/13] arm64: mm: Introduce a C wrapper for by-range TLB invalidation

Ryan Roberts posted 13 patches 1 month, 3 weeks ago
There is a newer version of this series
[PATCH v1 02/13] arm64: mm: Introduce a C wrapper for by-range TLB invalidation
Posted by Ryan Roberts 1 month, 3 weeks ago
As part of efforts to reduce our reliance on complex preprocessor macros
for TLB invalidation routines, introduce a new C wrapper for by-range
TLB invalidation which can be used instead of the __tlbi() macro and can
additionally be called from C code.

Each specific tlbi range op is implemented as a C function and the
appropriate function pointer is passed to __tlbi_range(). Since
everything is declared inline and is statically resolvable, the compiler
will convert the indirect function call to a direct inline execution.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
---
 arch/arm64/include/asm/tlbflush.h | 33 ++++++++++++++++++++++++++++++-
 1 file changed, 32 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 13a59cf28943..c5111d2afc66 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -459,6 +459,37 @@ static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
  *    operations can only span an even number of pages. We save this for last to
  *    ensure 64KB start alignment is maintained for the LPA2 case.
  */
+static __always_inline void rvae1is(u64 arg)
+{
+	__tlbi(rvae1is, arg);
+}
+
+static __always_inline void rvale1(u64 arg)
+{
+	__tlbi(rvale1, arg);
+	__tlbi_user(rvale1, arg);
+}
+
+static __always_inline void rvale1is(u64 arg)
+{
+	__tlbi(rvale1is, arg);
+}
+
+static __always_inline void rvaale1is(u64 arg)
+{
+	__tlbi(rvaale1is, arg);
+}
+
+static __always_inline void ripas2e1is(u64 arg)
+{
+	__tlbi(ripas2e1is, arg);
+}
+
+static __always_inline void __tlbi_range(tlbi_op op, u64 arg)
+{
+	op(arg);
+}
+
 #define __flush_tlb_range_op(op, start, pages, stride,			\
 				asid, tlb_level, tlbi_user, lpa2)	\
 do {									\
@@ -486,7 +517,7 @@ do {									\
 		if (num >= 0) {						\
 			addr = __TLBI_VADDR_RANGE(__flush_start >> shift, asid, \
 						scale, num, tlb_level);	\
-			__tlbi(r##op, addr);				\
+			__tlbi_range(r##op, addr);			\
 			if (tlbi_user)					\
 				__tlbi_user(r##op, addr);		\
 			__flush_start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \
-- 
2.43.0
Re: [PATCH v1 02/13] arm64: mm: Introduce a C wrapper for by-range TLB invalidation
Posted by Linu Cherian 1 month ago
Ryan,

On Tue, Dec 16, 2025 at 02:45:47PM +0000, Ryan Roberts wrote:
> As part of efforts to reduce our reliance on complex preprocessor macros
> for TLB invalidation routines, introduce a new C wrapper for by-range
> TLB invalidation which can be used instead of the __tlbi() macro and can
> additionally be called from C code.
> 
> Each specific tlbi range op is implemented as a C function and the
> appropriate function pointer is passed to __tlbi_range(). Since
> everything is declared inline and is statically resolvable, the compiler
> will convert the indirect function call to a direct inline execution.
> 
> Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> ---
>  arch/arm64/include/asm/tlbflush.h | 33 ++++++++++++++++++++++++++++++-
>  1 file changed, 32 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
> index 13a59cf28943..c5111d2afc66 100644
> --- a/arch/arm64/include/asm/tlbflush.h
> +++ b/arch/arm64/include/asm/tlbflush.h
> @@ -459,6 +459,37 @@ static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
>   *    operations can only span an even number of pages. We save this for last to
>   *    ensure 64KB start alignment is maintained for the LPA2 case.
>   */
> +static __always_inline void rvae1is(u64 arg)
> +{
> +	__tlbi(rvae1is, arg);
> +}
> +
> +static __always_inline void rvale1(u64 arg)
> +{
> +	__tlbi(rvale1, arg);
> +	__tlbi_user(rvale1, arg);

Should this __tlbi_user be added as part of patch 3 ?

> +}
> +
> +static __always_inline void rvale1is(u64 arg)
> +{
> +	__tlbi(rvale1is, arg);
> +}
> +
> +static __always_inline void rvaale1is(u64 arg)
> +{
> +	__tlbi(rvaale1is, arg);
> +}
> +
> +static __always_inline void ripas2e1is(u64 arg)
> +{
> +	__tlbi(ripas2e1is, arg);
> +}
> +
> +static __always_inline void __tlbi_range(tlbi_op op, u64 arg)
> +{
> +	op(arg);
> +}
> +
>  #define __flush_tlb_range_op(op, start, pages, stride,			\
>  				asid, tlb_level, tlbi_user, lpa2)	\
>  do {									\
> @@ -486,7 +517,7 @@ do {									\
>  		if (num >= 0) {						\
>  			addr = __TLBI_VADDR_RANGE(__flush_start >> shift, asid, \
>  						scale, num, tlb_level);	\
> -			__tlbi(r##op, addr);				\
> +			__tlbi_range(r##op, addr);			\
>  			if (tlbi_user)					\
>  				__tlbi_user(r##op, addr);		\
>  			__flush_start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \
> -- 
> 2.43.0
>
Re: [PATCH v1 02/13] arm64: mm: Introduce a C wrapper for by-range TLB invalidation
Posted by Ryan Roberts 1 month ago
On 05/01/2026 05:33, Linu Cherian wrote:
> Ryan,
> 
> On Tue, Dec 16, 2025 at 02:45:47PM +0000, Ryan Roberts wrote:
>> As part of efforts to reduce our reliance on complex preprocessor macros
>> for TLB invalidation routines, introduce a new C wrapper for by-range
>> TLB invalidation which can be used instead of the __tlbi() macro and can
>> additionally be called from C code.
>>
>> Each specific tlbi range op is implemented as a C function and the
>> appropriate function pointer is passed to __tlbi_range(). Since
>> everything is declared inline and is statically resolvable, the compiler
>> will convert the indirect function call to a direct inline execution.
>>
>> Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
>> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
>> ---
>>  arch/arm64/include/asm/tlbflush.h | 33 ++++++++++++++++++++++++++++++-
>>  1 file changed, 32 insertions(+), 1 deletion(-)
>>
>> diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
>> index 13a59cf28943..c5111d2afc66 100644
>> --- a/arch/arm64/include/asm/tlbflush.h
>> +++ b/arch/arm64/include/asm/tlbflush.h
>> @@ -459,6 +459,37 @@ static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
>>   *    operations can only span an even number of pages. We save this for last to
>>   *    ensure 64KB start alignment is maintained for the LPA2 case.
>>   */
>> +static __always_inline void rvae1is(u64 arg)
>> +{
>> +	__tlbi(rvae1is, arg);
>> +}
>> +
>> +static __always_inline void rvale1(u64 arg)
>> +{
>> +	__tlbi(rvale1, arg);
>> +	__tlbi_user(rvale1, arg);
> 
> Should this __tlbi_user be added as part of patch 3 ?

Yes! I've screwed up a rebase since vale1/rvale1 only started being used in
v6.19-rc1; I attempted to add it incrementally and have clearly screwed it up.
I'll fix it all in the next rev.

Thanks,
Ryan

> 
>> +}
>> +
>> +static __always_inline void rvale1is(u64 arg)
>> +{
>> +	__tlbi(rvale1is, arg);
>> +}
>> +
>> +static __always_inline void rvaale1is(u64 arg)
>> +{
>> +	__tlbi(rvaale1is, arg);
>> +}
>> +
>> +static __always_inline void ripas2e1is(u64 arg)
>> +{
>> +	__tlbi(ripas2e1is, arg);
>> +}
>> +
>> +static __always_inline void __tlbi_range(tlbi_op op, u64 arg)
>> +{
>> +	op(arg);
>> +}
>> +
>>  #define __flush_tlb_range_op(op, start, pages, stride,			\
>>  				asid, tlb_level, tlbi_user, lpa2)	\
>>  do {									\
>> @@ -486,7 +517,7 @@ do {									\
>>  		if (num >= 0) {						\
>>  			addr = __TLBI_VADDR_RANGE(__flush_start >> shift, asid, \
>>  						scale, num, tlb_level);	\
>> -			__tlbi(r##op, addr);				\
>> +			__tlbi_range(r##op, addr);			\
>>  			if (tlbi_user)					\
>>  				__tlbi_user(r##op, addr);		\
>>  			__flush_start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \
>> -- 
>> 2.43.0
>>