diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index aab05e2c01a5..07da6c790b63 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -77,6 +77,7 @@ perf-y += sort.o
 perf-y += hist.o
 perf-y += util.o
 perf-y += cpumap.o
+perf-y += affinity.o
 perf-y += cputopo.o
 perf-y += cgroup.o
 perf-y += target.o
diff --git a/tools/perf/util/affinity.c b/tools/perf/util/affinity.c
new file mode 100644
index 000000000000..a5e31f826828
--- /dev/null
+++ b/tools/perf/util/affinity.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Manage affinity to optimize IPIs inside the kernel perf API. */
+#define _GNU_SOURCE 1
+#include <sched.h>
+#include <stdlib.h>
+#include <linux/bitmap.h>
+#include <linux/zalloc.h>
+#include "perf.h"
+#include "cpumap.h"
+#include "affinity.h"
+
+static int get_cpu_set_size(void)
+{
+	int sz = cpu__max_cpu() + 8 - 1;
+	/*
+	 * sched_getaffinity doesn't like masks smaller than the kernel.
+	 * Hopefully that's big enough.
+	 */
+	if (sz < 4096)
+		sz = 4096;
+	return sz / 8;
+}
+
+int affinity__setup(struct affinity *a)
+{
+	int cpu_set_size = get_cpu_set_size();
+
+	a->orig_cpus = bitmap_alloc(cpu_set_size * 8);
+	if (!a->orig_cpus)
+		return -1;
+	sched_getaffinity(0, cpu_set_size, (cpu_set_t *)a->orig_cpus);
+	a->sched_cpus = bitmap_alloc(cpu_set_size * 8);
+	if (!a->sched_cpus) {
+		zfree(&a->orig_cpus);
+		return -1;
+	}
+	bitmap_zero((unsigned long *)a->sched_cpus, cpu_set_size);
+	a->changed = false;
+	return 0;
+}
+
+/*
+ * perf_event_open does an IPI internally to the target CPU.
+ * It is more efficient to change perf's affinity to the target
+ * CPU and then set up all events on that CPU, so we amortize
+ * CPU communication.
+ */
+void affinity__set(struct affinity *a, int cpu)
+{
+	int cpu_set_size = get_cpu_set_size();
+
+	if (cpu == -1)
+		return;
+	a->changed = true;
+	set_bit(cpu, a->sched_cpus);
+	/*
+	 * We ignore errors because affinity is just an optimization.
+	 * This could happen for example with isolated CPUs or cpusets.
+	 * In this case the IPIs inside the kernel's perf API still work.
+	 */
+	sched_setaffinity(0, cpu_set_size, (cpu_set_t *)a->sched_cpus);
+	clear_bit(cpu, a->sched_cpus);
+}
+
+void affinity__cleanup(struct affinity *a)
+{
+	int cpu_set_size = get_cpu_set_size();
+
+	if (a->changed)
+		sched_setaffinity(0, cpu_set_size, (cpu_set_t *)a->orig_cpus);
+	zfree(&a->sched_cpus);
+	zfree(&a->orig_cpus);
+}
diff --git a/tools/perf/util/affinity.h b/tools/perf/util/affinity.h
new file mode 100644
index 000000000000..0ad6a18ef20c
--- /dev/null
+++ b/tools/perf/util/affinity.h
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef PERF_AFFINITY_H
+#define PERF_AFFINITY_H 1
+
+#include <stdbool.h>
+
+struct affinity {
+	unsigned long *orig_cpus;
+	unsigned long *sched_cpus;
+	bool changed;
+};
+
+void affinity__cleanup(struct affinity *a);
+void affinity__set(struct affinity *a, int cpu);
+int affinity__setup(struct affinity *a);
+
+#endif // PERF_AFFINITY_H
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 9af183860fbd..e7279ea6043a 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -33,3 +33,4 @@ util/trace-event.c
 util/string.c
 util/symbol_fprintf.c
 util/units.c
+util/affinity.c