The lazy_mmu API now allows nested sections to be handled by arch
code: enter() can return a flag if called inside another lazy_mmu
section, so that the matching call to leave() leaves any
optimisation enabled.

This patch implements that new logic for powerpc: if there is an
active batch, then enter() returns LAZY_MMU_NESTED and the matching
leave() leaves batch->active set. The preempt_{enable,disable} calls
are left untouched as they already handle nesting themselves.

TLB flushing is still done in leave() regardless of the nesting
level, as the caller may rely on it whether nesting is occurring or
not.

Signed-off-by: Kevin Brodsky <kevin.brodsky@arm.com>
---
 .../powerpc/include/asm/book3s/64/tlbflush-hash.h | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h
index c9f1e819e567..001c474da1fe 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h
@@ -30,6 +30,7 @@ typedef int lazy_mmu_state_t;
 static inline lazy_mmu_state_t arch_enter_lazy_mmu_mode(void)
 {
 	struct ppc64_tlb_batch *batch;
+	int lazy_mmu_nested;
 
 	if (radix_enabled())
 		return LAZY_MMU_DEFAULT;
@@ -39,9 +40,14 @@ static inline lazy_mmu_state_t arch_enter_lazy_mmu_mode(void)
 	 */
 	preempt_disable();
 	batch = this_cpu_ptr(&ppc64_tlb_batch);
-	batch->active = 1;
+	lazy_mmu_nested = batch->active;
 
-	return LAZY_MMU_DEFAULT;
+	if (!lazy_mmu_nested) {
+		batch->active = 1;
+		return LAZY_MMU_DEFAULT;
+	} else {
+		return LAZY_MMU_NESTED;
+	}
 }
 
 static inline void arch_leave_lazy_mmu_mode(lazy_mmu_state_t state)
@@ -54,7 +60,10 @@ static inline void arch_leave_lazy_mmu_mode(lazy_mmu_state_t state)
 
 	if (batch->index)
 		__flush_tlb_pending(batch);
-	batch->active = 0;
+
+	if (state != LAZY_MMU_NESTED)
+		batch->active = 0;
+
 	preempt_enable();
 }
 
-- 
2.47.0

On Thu, Sep 04, 2025 at 01:57:34PM +0100, Kevin Brodsky wrote:
...
>  static inline lazy_mmu_state_t arch_enter_lazy_mmu_mode(void)
>  {
>  	struct ppc64_tlb_batch *batch;
> +	int lazy_mmu_nested;
>  
>  	if (radix_enabled())
>  		return LAZY_MMU_DEFAULT;
> @@ -39,9 +40,14 @@ static inline lazy_mmu_state_t arch_enter_lazy_mmu_mode(void)
>  	 */
>  	preempt_disable();
>  	batch = this_cpu_ptr(&ppc64_tlb_batch);
> -	batch->active = 1;
> +	lazy_mmu_nested = batch->active;
>  
> -	return LAZY_MMU_DEFAULT;
> +	if (!lazy_mmu_nested) {

Why not just?

	if (!batch->active) {

> +		batch->active = 1;
> +		return LAZY_MMU_DEFAULT;
> +	} else {
> +		return LAZY_MMU_NESTED;
> +	}
>  }
>  
>  static inline void arch_leave_lazy_mmu_mode(lazy_mmu_state_t state)
> @@ -54,7 +60,10 @@ static inline void arch_leave_lazy_mmu_mode(lazy_mmu_state_t state)
>  
>  	if (batch->index)
>  		__flush_tlb_pending(batch);
> -	batch->active = 0;
> +
> +	if (state != LAZY_MMU_NESTED)
> +		batch->active = 0;
> +
>  	preempt_enable();
>  }

Thanks!

On 05/09/2025 17:52, Alexander Gordeev wrote:
> On Thu, Sep 04, 2025 at 01:57:34PM +0100, Kevin Brodsky wrote:
> ...
>>  static inline lazy_mmu_state_t arch_enter_lazy_mmu_mode(void)
>>  {
>>  	struct ppc64_tlb_batch *batch;
>> +	int lazy_mmu_nested;
>>  
>>  	if (radix_enabled())
>>  		return LAZY_MMU_DEFAULT;
>> @@ -39,9 +40,14 @@ static inline lazy_mmu_state_t arch_enter_lazy_mmu_mode(void)
>>  	 */
>>  	preempt_disable();
>>  	batch = this_cpu_ptr(&ppc64_tlb_batch);
>> -	batch->active = 1;
>> +	lazy_mmu_nested = batch->active;
>>  
>> -	return LAZY_MMU_DEFAULT;
>> +	if (!lazy_mmu_nested) {
> Why not just?
>
> 	if (!batch->active) {

Very fair question! I think the extra variable made sense in an earlier
version of that patch, but now it's used only once and doesn't really
improve readability either. Will remove it in v2, also in patch 6
(basically the same code). Thanks!

- Kevin