Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:

 - Make /sys/devices/cpu/rdpmc based RDPMC enforcement more
   instantaneous

 - decoder: Update the Intel opcode map

 - Various tooling fixes, including a few late optimizations and
   cleanups.

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  perf script: Fix invalid LBR/binary mismatch error
  perf script: Fix brstackinsn for AUXTRACE
  perf affinity: Add infrastructure to save/restore affinity
  perf pmu: Use file system cache to optimize sysfs access
  perf regs: Make perf_reg_name() return "unknown" instead of NULL
  perf diff: Use llabs() with 64-bit values
  perf diff: Use llabs() with 64-bit values
  perf/x86: Implement immediate enforcement of /sys/devices/cpu/rdpmc value of 0
  perf tools: Allow to link with libbpf dynamicaly
  perf tests: Rename tests/map_groups.c to tests/maps.c
  perf tests: Rename thread-mg-share to thread-maps-share
  perf maps: Rename map_groups.h to maps.h
  perf maps: Rename 'mg' variables to 'maps'
  perf map_symbol: Rename ms->mg to ms->maps
  perf addr_location: Rename al->mg to al->maps
  perf thread: Rename thread->mg to thread->maps
  perf maps: Merge 'struct maps' with 'struct map_groups'
  x86/insn: perf tools: Add some more instructions to the new instructions test
  x86/insn: Add some more Intel instructions to the opcode map
  perf map: Remove unused functions
  ...

1 files changed, 73 insertions, 0 deletions

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);
+}