[tip: perf/core] perf: Add PERF_EV_CAP_READ_SCOPE

[tip-bot2 for Kan Liang]

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     a48a36b316ae5d3ab83f9b545dba15998e96d59c
Gitweb:        https://git.kernel.org/tip/a48a36b316ae5d3ab83f9b545dba15998e96d59c
Author:        Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
AuthorDate:    Fri, 02 Aug 2024 08:16:38 -07:00
Committer:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Tue, 10 Sep 2024 11:44:13 +02:00

perf: Add PERF_EV_CAP_READ_SCOPE

Usually, an event can be read from any CPU of the scope. It doesn't need
to be read from the advertised CPU.

Add a new event cap, PERF_EV_CAP_READ_SCOPE. An event of a PMU with
scope can be read from any active CPU in the scope.

Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20240802151643.1691631-3-kan.liang@xxxxxxxxxxxxxxx
---
 include/linux/perf_event.h |  3 +++
 kernel/events/core.c       | 14 +++++++++++---
 2 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index a3cbcd7..794f660 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -636,10 +636,13 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *,
  * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and
  * cannot be a group leader. If an event with this flag is detached from the
  * group it is scheduled out and moved into an unrecoverable ERROR state.
+ * PERF_EV_CAP_READ_SCOPE: A CPU event that can be read from any CPU of the
+ * PMU scope where it is active.
  */
 #define PERF_EV_CAP_SOFTWARE		BIT(0)
 #define PERF_EV_CAP_READ_ACTIVE_PKG	BIT(1)
 #define PERF_EV_CAP_SIBLING		BIT(2)
+#define PERF_EV_CAP_READ_SCOPE		BIT(3)
 
 #define SWEVENT_HLIST_BITS		8
 #define SWEVENT_HLIST_SIZE		(1 << SWEVENT_HLIST_BITS)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5ff9735..2766090 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4556,16 +4556,24 @@ struct perf_read_data {
 	int ret;
 };
 
+static inline const struct cpumask *perf_scope_cpu_topology_cpumask(unsigned int scope, int cpu);
+
 static int __perf_event_read_cpu(struct perf_event *event, int event_cpu)
 {
+	int local_cpu = smp_processor_id();
 	u16 local_pkg, event_pkg;
 
 	if ((unsigned)event_cpu >= nr_cpu_ids)
 		return event_cpu;
 
-	if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
-		int local_cpu = smp_processor_id();
+	if (event->group_caps & PERF_EV_CAP_READ_SCOPE) {
+		const struct cpumask *cpumask = perf_scope_cpu_topology_cpumask(event->pmu->scope, event_cpu);
+
+		if (cpumask && cpumask_test_cpu(local_cpu, cpumask))
+			return local_cpu;
+	}
 
+	if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
 		event_pkg = topology_physical_package_id(event_cpu);
 		local_pkg = topology_physical_package_id(local_cpu);
 
@@ -11905,7 +11913,7 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
 				if (cpu >= nr_cpu_ids)
 					ret = -ENODEV;
 				else
-					event->cpu = cpu;
+					event->event_caps |= PERF_EV_CAP_READ_SCOPE;
 			} else {
 				ret = -ENODEV;
 			}