* [PATCH] perf/arm-cmn: Initialise cmn->cpu earlier
@ 2025-05-12 17:11 Robin Murphy
2025-05-13 19:10 ` Ilkka Koskinen
2025-05-16 15:37 ` Will Deacon
0 siblings, 2 replies; 3+ messages in thread
From: Robin Murphy @ 2025-05-12 17:11 UTC (permalink / raw)
To: will; +Cc: mark.rutland, linux-arm-kernel, linux-perf-users, stable
For all the complexity of handling affinity for CPU hotplug, what we've
apparently managed to overlook is that arm_cmn_init_irqs() has in fact
always been setting the *initial* affinity of all IRQs to CPU 0, not the
CPU we subsequently choose for event scheduling. Oh dear.
Cc: stable@vger.kernel.org
Fixes: 0ba64770a2f2 ("perf: Add Arm CMN-600 PMU driver")
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
---
drivers/perf/arm-cmn.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index aa2908313558..e385f187a084 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -2558,6 +2558,7 @@ static int arm_cmn_probe(struct platform_device *pdev)
cmn->dev = &pdev->dev;
cmn->part = (unsigned long)device_get_match_data(cmn->dev);
+ cmn->cpu = cpumask_local_spread(0, dev_to_node(cmn->dev));
platform_set_drvdata(pdev, cmn);
if (cmn->part == PART_CMN600 && has_acpi_companion(cmn->dev)) {
@@ -2585,7 +2586,6 @@ static int arm_cmn_probe(struct platform_device *pdev)
if (err)
return err;
- cmn->cpu = cpumask_local_spread(0, dev_to_node(cmn->dev));
cmn->pmu = (struct pmu) {
.module = THIS_MODULE,
.parent = cmn->dev,
--
2.39.2.101.g768bb238c484.dirty
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH] perf/arm-cmn: Initialise cmn->cpu earlier
2025-05-12 17:11 [PATCH] perf/arm-cmn: Initialise cmn->cpu earlier Robin Murphy
@ 2025-05-13 19:10 ` Ilkka Koskinen
2025-05-16 15:37 ` Will Deacon
1 sibling, 0 replies; 3+ messages in thread
From: Ilkka Koskinen @ 2025-05-13 19:10 UTC (permalink / raw)
To: Robin Murphy
Cc: will, mark.rutland, linux-arm-kernel, linux-perf-users, stable
On Mon, 12 May 2025, Robin Murphy wrote:
> For all the complexity of handling affinity for CPU hotplug, what we've
> apparently managed to overlook is that arm_cmn_init_irqs() has in fact
> always been setting the *initial* affinity of all IRQs to CPU 0, not the
> CPU we subsequently choose for event scheduling. Oh dear.
>
> Cc: stable@vger.kernel.org
> Fixes: 0ba64770a2f2 ("perf: Add Arm CMN-600 PMU driver")
> Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Good catch.
Reviewed-by: Ilkka Koskinen <ilkka@os.amperecomputing.com>
> ---
> drivers/perf/arm-cmn.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
> index aa2908313558..e385f187a084 100644
> --- a/drivers/perf/arm-cmn.c
> +++ b/drivers/perf/arm-cmn.c
> @@ -2558,6 +2558,7 @@ static int arm_cmn_probe(struct platform_device *pdev)
>
> cmn->dev = &pdev->dev;
> cmn->part = (unsigned long)device_get_match_data(cmn->dev);
> + cmn->cpu = cpumask_local_spread(0, dev_to_node(cmn->dev));
> platform_set_drvdata(pdev, cmn);
>
> if (cmn->part == PART_CMN600 && has_acpi_companion(cmn->dev)) {
> @@ -2585,7 +2586,6 @@ static int arm_cmn_probe(struct platform_device *pdev)
> if (err)
> return err;
>
> - cmn->cpu = cpumask_local_spread(0, dev_to_node(cmn->dev));
> cmn->pmu = (struct pmu) {
> .module = THIS_MODULE,
> .parent = cmn->dev,
> --
> 2.39.2.101.g768bb238c484.dirty
>
>
>
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH] perf/arm-cmn: Initialise cmn->cpu earlier
2025-05-12 17:11 [PATCH] perf/arm-cmn: Initialise cmn->cpu earlier Robin Murphy
2025-05-13 19:10 ` Ilkka Koskinen
@ 2025-05-16 15:37 ` Will Deacon
1 sibling, 0 replies; 3+ messages in thread
From: Will Deacon @ 2025-05-16 15:37 UTC (permalink / raw)
To: Robin Murphy
Cc: catalin.marinas, kernel-team, Will Deacon, mark.rutland,
linux-arm-kernel, linux-perf-users, stable
On Mon, 12 May 2025 18:11:54 +0100, Robin Murphy wrote:
> For all the complexity of handling affinity for CPU hotplug, what we've
> apparently managed to overlook is that arm_cmn_init_irqs() has in fact
> always been setting the *initial* affinity of all IRQs to CPU 0, not the
> CPU we subsequently choose for event scheduling. Oh dear.
>
>
Applied to will (for-next/perf), thanks!
[1/1] perf/arm-cmn: Initialise cmn->cpu earlier
https://git.kernel.org/will/c/597704e20106
Cheers,
--
Will
https://fixes.arm64.dev
https://next.arm64.dev
https://will.arm64.dev
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2025-05-16 16:06 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2025-05-12 17:11 [PATCH] perf/arm-cmn: Initialise cmn->cpu earlier Robin Murphy
2025-05-13 19:10 ` Ilkka Koskinen
2025-05-16 15:37 ` Will Deacon
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).