linux-perf-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH] perf/x86/intel: Use early_initcall() to hook bts_init()
@ 2025-06-06 11:16 Dapeng Mi
  2025-06-19  1:10 ` Mi, Dapeng
  2025-07-11  2:37 ` Mi, Dapeng
  0 siblings, 2 replies; 3+ messages in thread
From: Dapeng Mi @ 2025-06-06 11:16 UTC (permalink / raw)
  To: Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
	Namhyung Kim, Ian Rogers, Adrian Hunter, Alexander Shishkin,
	Kan Liang, Andi Kleen, Eranian Stephane
  Cc: linux-kernel, linux-perf-users, Andrew Zaborowski, Dapeng Mi,
	Dapeng Mi

After the commit 'd971342d38bf ("perf/x86/intel: Decouple BTS
 initialization from PEBS initialization")' is introduced, x86_pmu.bts
would initialized in bts_init() which is hooked by arch_initcall().

Whereas init_hw_perf_events() is hooked by early_initcall(). Once the
core PMU is initialized, nmi watchdog initialization is called
immediately before bts_init() is called. It leads to the BTS buffer is
not really initialized since bts_init() is not called and x86_pmu.bts is
still false at that time. Worse, BTS buffer would never be initialized
then unless all core PMU events are freed and reserve_ds_buffers()
is called again.

Thus aligning with init_hw_perf_events(), use early_initcall() to hook
bts_init() to ensure x86_pmu.bts is initialized before nmi watchdog
initialization.

Fixes: d971342d38bf ("perf/x86/intel: Decouple BTS initialization from PEBS initialization")
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
---
 arch/x86/events/intel/bts.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 9560f693fac0..f0d9729ed255 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -642,4 +642,4 @@ static __init int bts_init(void)
 
 	return perf_pmu_register(&bts_pmu, "intel_bts", -1);
 }
-arch_initcall(bts_init);
+early_initcall(bts_init);

base-commit: e7d952cc39fca34386ec9f15f68cb2eaac01b5ae
-- 
2.43.0


^ permalink raw reply related	[flat|nested] 3+ messages in thread

* Re: [PATCH] perf/x86/intel: Use early_initcall() to hook bts_init()
  2025-06-06 11:16 [PATCH] perf/x86/intel: Use early_initcall() to hook bts_init() Dapeng Mi
@ 2025-06-19  1:10 ` Mi, Dapeng
  2025-07-11  2:37 ` Mi, Dapeng
  1 sibling, 0 replies; 3+ messages in thread
From: Mi, Dapeng @ 2025-06-19  1:10 UTC (permalink / raw)
  To: Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
	Namhyung Kim, Ian Rogers, Adrian Hunter, Alexander Shishkin,
	Kan Liang, Andi Kleen, Eranian Stephane
  Cc: linux-kernel, linux-perf-users, Andrew Zaborowski, Dapeng Mi

Kindly ping...   Thanks.

On 6/6/2025 7:16 PM, Dapeng Mi wrote:
> After the commit 'd971342d38bf ("perf/x86/intel: Decouple BTS
>  initialization from PEBS initialization")' is introduced, x86_pmu.bts
> would initialized in bts_init() which is hooked by arch_initcall().
>
> Whereas init_hw_perf_events() is hooked by early_initcall(). Once the
> core PMU is initialized, nmi watchdog initialization is called
> immediately before bts_init() is called. It leads to the BTS buffer is
> not really initialized since bts_init() is not called and x86_pmu.bts is
> still false at that time. Worse, BTS buffer would never be initialized
> then unless all core PMU events are freed and reserve_ds_buffers()
> is called again.
>
> Thus aligning with init_hw_perf_events(), use early_initcall() to hook
> bts_init() to ensure x86_pmu.bts is initialized before nmi watchdog
> initialization.
>
> Fixes: d971342d38bf ("perf/x86/intel: Decouple BTS initialization from PEBS initialization")
> Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
> ---
>  arch/x86/events/intel/bts.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
> index 9560f693fac0..f0d9729ed255 100644
> --- a/arch/x86/events/intel/bts.c
> +++ b/arch/x86/events/intel/bts.c
> @@ -642,4 +642,4 @@ static __init int bts_init(void)
>  
>  	return perf_pmu_register(&bts_pmu, "intel_bts", -1);
>  }
> -arch_initcall(bts_init);
> +early_initcall(bts_init);
>
> base-commit: e7d952cc39fca34386ec9f15f68cb2eaac01b5ae

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: [PATCH] perf/x86/intel: Use early_initcall() to hook bts_init()
  2025-06-06 11:16 [PATCH] perf/x86/intel: Use early_initcall() to hook bts_init() Dapeng Mi
  2025-06-19  1:10 ` Mi, Dapeng
@ 2025-07-11  2:37 ` Mi, Dapeng
  1 sibling, 0 replies; 3+ messages in thread
From: Mi, Dapeng @ 2025-07-11  2:37 UTC (permalink / raw)
  To: Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
	Namhyung Kim, Ian Rogers, Adrian Hunter, Alexander Shishkin,
	Kan Liang, Andi Kleen, Eranian Stephane
  Cc: linux-kernel, linux-perf-users, Andrew Zaborowski, Dapeng Mi

Kindly ping.

@Peter, not sure you have bandwidth to review this change? Thanks.

On 6/6/2025 7:16 PM, Dapeng Mi wrote:
> After the commit 'd971342d38bf ("perf/x86/intel: Decouple BTS
>  initialization from PEBS initialization")' is introduced, x86_pmu.bts
> would initialized in bts_init() which is hooked by arch_initcall().
>
> Whereas init_hw_perf_events() is hooked by early_initcall(). Once the
> core PMU is initialized, nmi watchdog initialization is called
> immediately before bts_init() is called. It leads to the BTS buffer is
> not really initialized since bts_init() is not called and x86_pmu.bts is
> still false at that time. Worse, BTS buffer would never be initialized
> then unless all core PMU events are freed and reserve_ds_buffers()
> is called again.
>
> Thus aligning with init_hw_perf_events(), use early_initcall() to hook
> bts_init() to ensure x86_pmu.bts is initialized before nmi watchdog
> initialization.
>
> Fixes: d971342d38bf ("perf/x86/intel: Decouple BTS initialization from PEBS initialization")
> Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
> ---
>  arch/x86/events/intel/bts.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
> index 9560f693fac0..f0d9729ed255 100644
> --- a/arch/x86/events/intel/bts.c
> +++ b/arch/x86/events/intel/bts.c
> @@ -642,4 +642,4 @@ static __init int bts_init(void)
>  
>  	return perf_pmu_register(&bts_pmu, "intel_bts", -1);
>  }
> -arch_initcall(bts_init);
> +early_initcall(bts_init);
>
> base-commit: e7d952cc39fca34386ec9f15f68cb2eaac01b5ae

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2025-07-11  2:37 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-06-06 11:16 [PATCH] perf/x86/intel: Use early_initcall() to hook bts_init() Dapeng Mi
2025-06-19  1:10 ` Mi, Dapeng
2025-07-11  2:37 ` Mi, Dapeng

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).