public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
* [PATCH V2 1/2] perf/x86/rapl: Move the pmu allocation out of CPU hotplug
@ 2024-10-10 14:26 kan.liang
  2024-10-10 14:26 ` [PATCH V2 2/2] perf/x86/rapl: Clean up cpumask and hotplug kan.liang
  2024-10-31 10:08 ` [tip: perf/core] perf/x86/rapl: Move the pmu allocation out of CPU hotplug tip-bot2 for Kan Liang
  0 siblings, 2 replies; 5+ messages in thread
From: kan.liang @ 2024-10-10 14:26 UTC (permalink / raw)
  To: peterz, mingo, tglx, linux-kernel
  Cc: Kan Liang, Oliver Sang, Dhananjay Ugwekar

From: Kan Liang <kan.liang@linux.intel.com>

There are extra codes in the CPU hotplug function to allocate rapl pmus.
The generic PMU hotplug support is hard to be applied.

As long as the rapl pmus can be allocated upfront for each die/socket,
the code doesn't need to be implemented in the CPU hotplug function.
Move the code to the init_rapl_pmus(), and allocate a PMU for each
possible die/socket.

Tested-by: Oliver Sang <oliver.sang@intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Dhananjay Ugwekar <Dhananjay.Ugwekar@amd.com>
---
 arch/x86/events/rapl.c | 44 ++++++++++++++++++++++++++++--------------
 1 file changed, 30 insertions(+), 14 deletions(-)

diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index a481a939862e..7764f739fa0a 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -602,19 +602,8 @@ static int rapl_cpu_online(unsigned int cpu)
 	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
 	int target;
 
-	if (!pmu) {
-		pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
-		if (!pmu)
-			return -ENOMEM;
-
-		raw_spin_lock_init(&pmu->lock);
-		INIT_LIST_HEAD(&pmu->active_list);
-		pmu->pmu = &rapl_pmus->pmu;
-		pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
-		rapl_hrtimer_init(pmu);
-
-		rapl_pmus->pmus[rapl_pmu_idx] = pmu;
-	}
+	if (!pmu)
+		return -ENOMEM;
 
 	/*
 	 * Check if there is an online cpu in the package which collects rapl
@@ -707,6 +696,32 @@ static const struct attribute_group *rapl_attr_update[] = {
 	NULL,
 };
 
+static int __init init_rapl_pmu(void)
+{
+	struct rapl_pmu *pmu;
+	int idx;
+
+	for (idx = 0; idx < rapl_pmus->nr_rapl_pmu; idx++) {
+		pmu = kzalloc(sizeof(*pmu), GFP_KERNEL);
+		if (!pmu)
+			goto free;
+
+		raw_spin_lock_init(&pmu->lock);
+		INIT_LIST_HEAD(&pmu->active_list);
+		pmu->pmu = &rapl_pmus->pmu;
+		pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
+		rapl_hrtimer_init(pmu);
+
+		rapl_pmus->pmus[idx] = pmu;
+	}
+
+	return 0;
+free:
+	for (; idx > 0; idx--)
+		kfree(rapl_pmus->pmus[idx - 1]);
+	return -ENOMEM;
+}
+
 static int __init init_rapl_pmus(void)
 {
 	int nr_rapl_pmu = topology_max_packages();
@@ -730,7 +745,8 @@ static int __init init_rapl_pmus(void)
 	rapl_pmus->pmu.read		= rapl_pmu_event_read;
 	rapl_pmus->pmu.module		= THIS_MODULE;
 	rapl_pmus->pmu.capabilities	= PERF_PMU_CAP_NO_EXCLUDE;
-	return 0;
+
+	return init_rapl_pmu();
 }
 
 static struct rapl_model model_snb = {
-- 
2.38.1


^ permalink raw reply related	[flat|nested] 5+ messages in thread
end of thread, other threads:[~2024-10-31 10:09 UTC | newest]

Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2024-10-10 14:26 [PATCH V2 1/2] perf/x86/rapl: Move the pmu allocation out of CPU hotplug kan.liang
2024-10-10 14:26 ` [PATCH V2 2/2] perf/x86/rapl: Clean up cpumask and hotplug kan.liang
2024-10-14 16:07   ` Dhananjay Ugwekar
2024-10-31 10:08   ` [tip: perf/core] " tip-bot2 for Kan Liang
2024-10-31 10:08 ` [tip: perf/core] perf/x86/rapl: Move the pmu allocation out of CPU hotplug tip-bot2 for Kan Liang

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox