Merge tag 'perf-core-2024-05-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf events updates from Ingo Molnar:

 - Combine perf and BPF for fast evalution of HW breakpoint
   conditions

 - Add LBR capture support outside of hardware events

 - Trigger IO signals for watermark_wakeup

 - Add RAPL support for Intel Arrow Lake and Lunar Lake

 - Optimize frequency-throttling

 - Miscellaneous cleanups & fixes

* tag 'perf-core-2024-05-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (21 commits)
  perf/bpf: Mark perf_event_set_bpf_handler() and perf_event_free_bpf_handler() as inline too
  selftests/perf_events: Test FASYNC with watermark wakeups
  perf/ring_buffer: Trigger IO signals for watermark_wakeup
  perf: Move perf_event_fasync() to perf_event.h
  perf/bpf: Change the !CONFIG_BPF_SYSCALL stubs to static inlines
  selftest/bpf: Test a perf BPF program that suppresses side effects
  perf/bpf: Allow a BPF program to suppress all sample side effects
  perf/bpf: Remove unneeded uses_default_overflow_handler()
  perf/bpf: Call BPF handler directly, not through overflow machinery
  perf/bpf: Remove #ifdef CONFIG_BPF_SYSCALL from struct perf_event members
  perf/bpf: Create bpf_overflow_handler() stub for !CONFIG_BPF_SYSCALL
  perf/bpf: Reorder bpf_overflow_handler() ahead of __perf_event_overflow()
  perf/x86/rapl: Add support for Intel Lunar Lake
  perf/x86/rapl: Add support for Intel Arrow Lake
  perf/core: Reduce PMU access to adjust sample freq
  perf/core: Optimize perf_adjust_freq_unthr_context()
  perf/x86/amd: Don't reject non-sampling events with configured LBR
  perf/x86/amd: Support capturing LBR from software events
  perf/x86/amd: Avoid taking branches before disabling LBR
  perf/x86/amd: Ensure amd_pmu_core_disable_all() is always inlined
  ...

5 files changed, 300 insertions, 1 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/perf_skip.c b/tools/testing/selftests/bpf/prog_tests/perf_skip.c
new file mode 100644
index 000000000000..37d8618800e4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/perf_skip.c
@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <test_progs.h>
+#include "test_perf_skip.skel.h"
+#include <linux/compiler.h>
+#include <linux/hw_breakpoint.h>
+#include <sys/mman.h>
+
+#ifndef TRAP_PERF
+#define TRAP_PERF 6
+#endif
+
+int sigio_count, sigtrap_count;
+
+static void handle_sigio(int sig __always_unused)
+{
+	++sigio_count;
+}
+
+static void handle_sigtrap(int signum __always_unused,
+			   siginfo_t *info,
+			   void *ucontext __always_unused)
+{
+	ASSERT_EQ(info->si_code, TRAP_PERF, "si_code");
+	++sigtrap_count;
+}
+
+static noinline int test_function(void)
+{
+	asm volatile ("");
+	return 0;
+}
+
+void serial_test_perf_skip(void)
+{
+	struct sigaction action = {};
+	struct sigaction previous_sigtrap;
+	sighandler_t previous_sigio = SIG_ERR;
+	struct test_perf_skip *skel = NULL;
+	struct perf_event_attr attr = {};
+	int perf_fd = -1;
+	int err;
+	struct f_owner_ex owner;
+	struct bpf_link *prog_link = NULL;
+
+	action.sa_flags = SA_SIGINFO | SA_NODEFER;
+	action.sa_sigaction = handle_sigtrap;
+	sigemptyset(&action.sa_mask);
+	if (!ASSERT_OK(sigaction(SIGTRAP, &action, &previous_sigtrap), "sigaction"))
+		return;
+
+	previous_sigio = signal(SIGIO, handle_sigio);
+	if (!ASSERT_NEQ(previous_sigio, SIG_ERR, "signal"))
+		goto cleanup;
+
+	skel = test_perf_skip__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	attr.type = PERF_TYPE_BREAKPOINT;
+	attr.size = sizeof(attr);
+	attr.bp_type = HW_BREAKPOINT_X;
+	attr.bp_addr = (uintptr_t)test_function;
+	attr.bp_len = sizeof(long);
+	attr.sample_period = 1;
+	attr.sample_type = PERF_SAMPLE_IP;
+	attr.pinned = 1;
+	attr.exclude_kernel = 1;
+	attr.exclude_hv = 1;
+	attr.precise_ip = 3;
+	attr.sigtrap = 1;
+	attr.remove_on_exec = 1;
+
+	perf_fd = syscall(__NR_perf_event_open, &attr, 0, -1, -1, 0);
+	if (perf_fd < 0 && (errno == ENOENT || errno == EOPNOTSUPP)) {
+		printf("SKIP:no PERF_TYPE_BREAKPOINT/HW_BREAKPOINT_X\n");
+		test__skip();
+		goto cleanup;
+	}
+	if (!ASSERT_OK(perf_fd < 0, "perf_event_open"))
+		goto cleanup;
+
+	/* Configure the perf event to signal on sample. */
+	err = fcntl(perf_fd, F_SETFL, O_ASYNC);
+	if (!ASSERT_OK(err, "fcntl(F_SETFL, O_ASYNC)"))
+		goto cleanup;
+
+	owner.type = F_OWNER_TID;
+	owner.pid = syscall(__NR_gettid);
+	err = fcntl(perf_fd, F_SETOWN_EX, &owner);
+	if (!ASSERT_OK(err, "fcntl(F_SETOWN_EX)"))
+		goto cleanup;
+
+	/* Allow at most one sample. A sample rejected by bpf should
+	 * not count against this.
+	 */
+	err = ioctl(perf_fd, PERF_EVENT_IOC_REFRESH, 1);
+	if (!ASSERT_OK(err, "ioctl(PERF_EVENT_IOC_REFRESH)"))
+		goto cleanup;
+
+	prog_link = bpf_program__attach_perf_event(skel->progs.handler, perf_fd);
+	if (!ASSERT_OK_PTR(prog_link, "bpf_program__attach_perf_event"))
+		goto cleanup;
+
+	/* Configure the bpf program to suppress the sample. */
+	skel->bss->ip = (uintptr_t)test_function;
+	test_function();
+
+	ASSERT_EQ(sigio_count, 0, "sigio_count");
+	ASSERT_EQ(sigtrap_count, 0, "sigtrap_count");
+
+	/* Configure the bpf program to allow the sample. */
+	skel->bss->ip = 0;
+	test_function();
+
+	ASSERT_EQ(sigio_count, 1, "sigio_count");
+	ASSERT_EQ(sigtrap_count, 1, "sigtrap_count");
+
+	/* Test that the sample above is the only one allowed (by perf, not
+	 * by bpf)
+	 */
+	test_function();
+
+	ASSERT_EQ(sigio_count, 1, "sigio_count");
+	ASSERT_EQ(sigtrap_count, 1, "sigtrap_count");
+
+cleanup:
+	bpf_link__destroy(prog_link);
+	if (perf_fd >= 0)
+		close(perf_fd);
+	test_perf_skip__destroy(skel);
+
+	if (previous_sigio != SIG_ERR)
+		signal(SIGIO, previous_sigio);
+	sigaction(SIGTRAP, &previous_sigtrap, NULL);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_perf_skip.c b/tools/testing/selftests/bpf/progs/test_perf_skip.c
new file mode 100644
index 000000000000..7eb8b6de7a57
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_perf_skip.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+uintptr_t ip;
+
+SEC("perf_event")
+int handler(struct bpf_perf_event_data *data)
+{
+	/* Skip events that have the correct ip. */
+	return ip != PT_REGS_IP(&data->regs);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/perf_events/.gitignore b/tools/testing/selftests/perf_events/.gitignore
index 790c47001e77..ee93dc4969b8 100644
--- a/tools/testing/selftests/perf_events/.gitignore
+++ b/tools/testing/selftests/perf_events/.gitignore
@@ -1,3 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
 sigtrap_threads
 remove_on_exec
+watermark_signal
diff --git a/tools/testing/selftests/perf_events/Makefile b/tools/testing/selftests/perf_events/Makefile
index db93c4ff081a..70e3ff211278 100644
--- a/tools/testing/selftests/perf_events/Makefile
+++ b/tools/testing/selftests/perf_events/Makefile
@@ -2,5 +2,5 @@
 CFLAGS += -Wl,-no-as-needed -Wall $(KHDR_INCLUDES)
 LDFLAGS += -lpthread
 
-TEST_GEN_PROGS := sigtrap_threads remove_on_exec
+TEST_GEN_PROGS := sigtrap_threads remove_on_exec watermark_signal
 include ../lib.mk
diff --git a/tools/testing/selftests/perf_events/watermark_signal.c b/tools/testing/selftests/perf_events/watermark_signal.c
new file mode 100644
index 000000000000..49dc1e831174
--- /dev/null
+++ b/tools/testing/selftests/perf_events/watermark_signal.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/perf_event.h>
+#include <stddef.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/syscall.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "../kselftest_harness.h"
+
+#define __maybe_unused __attribute__((__unused__))
+
+static int sigio_count;
+
+static void handle_sigio(int signum __maybe_unused,
+			 siginfo_t *oh __maybe_unused,
+			 void *uc __maybe_unused)
+{
+	++sigio_count;
+}
+
+static void do_child(void)
+{
+	raise(SIGSTOP);
+
+	for (int i = 0; i < 20; ++i)
+		sleep(1);
+
+	raise(SIGSTOP);
+
+	exit(0);
+}
+
+TEST(watermark_signal)
+{
+	struct perf_event_attr attr;
+	struct perf_event_mmap_page *p = NULL;
+	struct sigaction previous_sigio, sigio = { 0 };
+	pid_t child = -1;
+	int child_status;
+	int fd = -1;
+	long page_size = sysconf(_SC_PAGE_SIZE);
+
+	sigio.sa_sigaction = handle_sigio;
+	EXPECT_EQ(sigaction(SIGIO, &sigio, &previous_sigio), 0);
+
+	memset(&attr, 0, sizeof(attr));
+	attr.size = sizeof(attr);
+	attr.type = PERF_TYPE_SOFTWARE;
+	attr.config = PERF_COUNT_SW_DUMMY;
+	attr.sample_period = 1;
+	attr.disabled = 1;
+	attr.watermark = 1;
+	attr.context_switch = 1;
+	attr.wakeup_watermark = 1;
+
+	child = fork();
+	EXPECT_GE(child, 0);
+	if (child == 0)
+		do_child();
+	else if (child < 0) {
+		perror("fork()");
+		goto cleanup;
+	}
+
+	if (waitpid(child, &child_status, WSTOPPED) != child ||
+	    !(WIFSTOPPED(child_status) && WSTOPSIG(child_status) == SIGSTOP)) {
+		fprintf(stderr,
+			"failed to sycnhronize with child errno=%d status=%x\n",
+			errno,
+			child_status);
+		goto cleanup;
+	}
+
+	fd = syscall(__NR_perf_event_open, &attr, child, -1, -1,
+		     PERF_FLAG_FD_CLOEXEC);
+	if (fd < 0) {
+		fprintf(stderr, "failed opening event %llx\n", attr.config);
+		goto cleanup;
+	}
+
+	if (fcntl(fd, F_SETFL, FASYNC)) {
+		perror("F_SETFL FASYNC");
+		goto cleanup;
+	}
+
+	if (fcntl(fd, F_SETOWN, getpid())) {
+		perror("F_SETOWN getpid()");
+		goto cleanup;
+	}
+
+	if (fcntl(fd, F_SETSIG, SIGIO)) {
+		perror("F_SETSIG SIGIO");
+		goto cleanup;
+	}
+
+	p = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+	if (p == NULL) {
+		perror("mmap");
+		goto cleanup;
+	}
+
+	if (ioctl(fd, PERF_EVENT_IOC_ENABLE, 0)) {
+		perror("PERF_EVENT_IOC_ENABLE");
+		goto cleanup;
+	}
+
+	if (kill(child, SIGCONT) < 0) {
+		perror("SIGCONT");
+		goto cleanup;
+	}
+
+	if (waitpid(child, &child_status, WSTOPPED) != -1 || errno != EINTR)
+		fprintf(stderr,
+			"expected SIGIO to terminate wait errno=%d status=%x\n%d",
+			errno,
+			child_status,
+			sigio_count);
+
+	EXPECT_GE(sigio_count, 1);
+
+cleanup:
+	if (p != NULL)
+		munmap(p, 2 * page_size);
+
+	if (fd >= 0)
+		close(fd);
+
+	if (child > 0) {
+		kill(child, SIGKILL);
+		waitpid(child, NULL, 0);
+	}
+
+	sigaction(SIGIO, &previous_sigio, NULL);
+}
+
+TEST_HARNESS_MAIN