get_preempt_count() is enabled to return preempt_count for powerpc,
so that bpf_in_interrupt()/get_preempt_count() works for powerpc as
well.

Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
---
 tools/testing/selftests/bpf/bpf_experimental.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
index 2cd9165c7348..c3f039a878f3 100644
--- a/tools/testing/selftests/bpf/bpf_experimental.h
+++ b/tools/testing/selftests/bpf/bpf_experimental.h
@@ -630,6 +630,8 @@ static inline int get_preempt_count(void)
 	return *(int *) bpf_this_cpu_ptr(&__preempt_count);
 #elif defined(bpf_target_arm64)
 	return bpf_get_current_task_btf()->thread_info.preempt.count;
+#elif defined(bpf_target_powerpc)
+	return bpf_get_current_task_btf()->thread_info.preempt_count;
 #endif
 	return 0;
 }
-- 
2.52.0

On 29/01/26 11:10 am, Saket Kumar Bhaskar wrote:
> get_preempt_count() is enabled to return preempt_count for powerpc,
> so that bpf_in_interrupt()/get_preempt_count() works for powerpc as
> well.
>
> Signed-off-by: Saket Kumar Bhaskar <skb99@linux.ibm.com>
> ---
>   tools/testing/selftests/bpf/bpf_experimental.h | 2 ++
>   1 file changed, 2 insertions(+)
>
> diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
> index 2cd9165c7348..c3f039a878f3 100644
> --- a/tools/testing/selftests/bpf/bpf_experimental.h
> +++ b/tools/testing/selftests/bpf/bpf_experimental.h
> @@ -630,6 +630,8 @@ static inline int get_preempt_count(void)
>   	return *(int *) bpf_this_cpu_ptr(&__preempt_count);
>   #elif defined(bpf_target_arm64)
>   	return bpf_get_current_task_btf()->thread_info.preempt.count;
> +#elif defined(bpf_target_powerpc)
> +	return bpf_get_current_task_btf()->thread_info.preempt_count;
>   #endif
>   	return 0;
>   }

Tested this patch by applying on mainline kernel and it passes the below 
selftest.


./test_progs -t timer_interrupt
#481     timer_interrupt:OK
Summary: 1/0 PASSED, 0 SKIPPED, 0 FAILED


Please add below tag.


Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>



Regards,

Venkat.

> diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h
> index a39576c8ba..147bbf6cd3 100644
> --- a/tools/testing/selftests/bpf/bpf_experimental.h
> +++ b/tools/testing/selftests/bpf/bpf_experimental.h
> @@ -627,6 +627,8 @@ static inline int get_preempt_count(void)
>  	return *(int *) bpf_this_cpu_ptr(&__preempt_count);
>  #elif defined(bpf_target_arm64)
>  	return bpf_get_current_task_btf()->thread_info.preempt.count;
> +#elif defined(bpf_target_powerpc)
> +	return bpf_get_current_task_btf()->thread_info.preempt_count;
>  #endif
>  	return 0;
>  }

Now that get_preempt_count() supports PowerPC, should the documentation
comments for bpf_in_interrupt(), bpf_in_nmi(), bpf_in_hardirq(),
bpf_in_serving_softirq(), and bpf_in_task() be updated to include
PowerPC in their supported architecture lists? Currently these comments
still say "Only works on the following archs: x86, arm64" but they now
also work on PowerPC via this change to get_preempt_count().


---
AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md

CI run summary: https://github.com/kernel-patches/bpf/actions/runs/21467281843

AI-authorship-score: low
AI-authorship-explanation: Straightforward kernel patch with natural technical writing style and minimal code changes consistent with human-authored commits.
issues-found: 1
issue-severity-score: low
issue-severity-explanation: Documentation comments not updated to reflect PowerPC support in helper functions; minor documentation mismatch in test code.