Merge tag 'perf-core-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf event updates from Ingo Molnar:

 - Improve Intel uncore PMU support:

     - Parse uncore 'discovery tables' - a new hardware capability
       enumeration method introduced on the latest Intel platforms. This
       table is in a well-defined PCI namespace location and is read via
       MMIO. It is organized in an rbtree.

       These uncore tables will allow the discovery of standard counter
       blocks, but fancier counters still need to be enumerated
       explicitly.

     - Add Alder Lake support

     - Improve IIO stacks to PMON mapping support on Skylake servers

 - Add Intel Alder Lake PMU support - which requires the introduction of
   'hybrid' CPUs and PMUs. Alder Lake is a mix of Golden Cove ('big')
   and Gracemont ('small' - Atom derived) cores.

   The CPU-side feature set is entirely symmetrical - but on the PMU
   side there's core type dependent PMU functionality.

 - Reduce data loss with CPU level hardware tracing on Intel PT / AUX
   profiling, by fixing the AUX allocation watermark logic.

 - Improve ring buffer allocation on NUMA systems

 - Put 'struct perf_event' into their separate kmem_cache pool

 - Add support for synchronous signals for select perf events. The
   immediate motivation is to support low-overhead sampling-based race
   detection for user-space code. The feature consists of the following
   main changes:

     - Add thread-only event inheritance via
       perf_event_attr::inherit_thread, which limits inheritance of
       events to CLONE_THREAD.

     - Add the ability for events to not leak through exec(), via
       perf_event_attr::remove_on_exec.

     - Allow the generation of SIGTRAP via perf_event_attr::sigtrap,
       extend siginfo with an u64 ::si_perf, and add the breakpoint
       information to ::si_addr and ::si_perf if the event is
       PERF_TYPE_BREAKPOINT.

   The siginfo support is adequate for breakpoints right now - but the
   new field can be used to introduce support for other types of
   metadata passed over siginfo as well.

 - Misc fixes, cleanups and smaller updates.

* tag 'perf-core-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
  signal, perf: Add missing TRAP_PERF case in siginfo_layout()
  signal, perf: Fix siginfo_t by avoiding u64 on 32-bit architectures
  perf/x86: Allow for 8<num_fixed_counters<16
  perf/x86/rapl: Add support for Intel Alder Lake
  perf/x86/cstate: Add Alder Lake CPU support
  perf/x86/msr: Add Alder Lake CPU support
  perf/x86/intel/uncore: Add Alder Lake support
  perf: Extend PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE
  perf/x86/intel: Add Alder Lake Hybrid support
  perf/x86: Support filter_match callback
  perf/x86/intel: Add attr_update for Hybrid PMUs
  perf/x86: Add structures for the attributes of Hybrid PMUs
  perf/x86: Register hybrid PMUs
  perf/x86: Factor out x86_pmu_show_pmu_cap
  perf/x86: Remove temporary pmu assignment in event_init
  perf/x86/intel: Factor out intel_pmu_check_extra_regs
  perf/x86/intel: Factor out intel_pmu_check_event_constraints
  perf/x86/intel: Factor out intel_pmu_check_num_counters
  perf/x86: Hybrid PMU support for extra_regs
  perf/x86: Hybrid PMU support for event constraints
  ...

7 files changed, 487 insertions, 0 deletions

diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index a6420c647959..6df0dc00d73a 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -776,6 +776,12 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		}
 	}
 
+	if (!opts->auxtrace_snapshot_mode && !opts->auxtrace_sample_mode) {
+		u32 aux_watermark = opts->auxtrace_mmap_pages * page_size / 4;
+
+		intel_pt_evsel->core.attr.aux_watermark = aux_watermark;
+	}
+
 	intel_pt_parse_terms(intel_pt_pmu->name, &intel_pt_pmu->format,
 			     "tsc", &tsc_bit);
 
diff --git a/tools/testing/selftests/perf_events/.gitignore b/tools/testing/selftests/perf_events/.gitignore
new file mode 100644
index 000000000000..790c47001e77
--- /dev/null
+++ b/tools/testing/selftests/perf_events/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+sigtrap_threads
+remove_on_exec
diff --git a/tools/testing/selftests/perf_events/Makefile b/tools/testing/selftests/perf_events/Makefile
new file mode 100644
index 000000000000..fcafa5f0d34c
--- /dev/null
+++ b/tools/testing/selftests/perf_events/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -Wl,-no-as-needed -Wall -I../../../../usr/include
+LDFLAGS += -lpthread
+
+TEST_GEN_PROGS := sigtrap_threads remove_on_exec
+include ../lib.mk
diff --git a/tools/testing/selftests/perf_events/config b/tools/testing/selftests/perf_events/config
new file mode 100644
index 000000000000..ba58ff2203e4
--- /dev/null
+++ b/tools/testing/selftests/perf_events/config
@@ -0,0 +1 @@
+CONFIG_PERF_EVENTS=y
diff --git a/tools/testing/selftests/perf_events/remove_on_exec.c b/tools/testing/selftests/perf_events/remove_on_exec.c
new file mode 100644
index 000000000000..5814611a1dc7
--- /dev/null
+++ b/tools/testing/selftests/perf_events/remove_on_exec.c
@@ -0,0 +1,260 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test for remove_on_exec.
+ *
+ * Copyright (C) 2021, Google LLC.
+ */
+
+#define _GNU_SOURCE
+
+/* We need the latest siginfo from the kernel repo. */
+#include <sys/types.h>
+#include <asm/siginfo.h>
+#define __have_siginfo_t 1
+#define __have_sigval_t 1
+#define __have_sigevent_t 1
+#define __siginfo_t_defined
+#define __sigval_t_defined
+#define __sigevent_t_defined
+#define _BITS_SIGINFO_CONSTS_H 1
+#define _BITS_SIGEVENT_CONSTS_H 1
+
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <linux/perf_event.h>
+#include <pthread.h>
+#include <signal.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "../kselftest_harness.h"
+
+static volatile int signal_count;
+
+static struct perf_event_attr make_event_attr(void)
+{
+	struct perf_event_attr attr = {
+		.type		= PERF_TYPE_HARDWARE,
+		.size		= sizeof(attr),
+		.config		= PERF_COUNT_HW_INSTRUCTIONS,
+		.sample_period	= 1000,
+		.exclude_kernel = 1,
+		.exclude_hv	= 1,
+		.disabled	= 1,
+		.inherit	= 1,
+		/*
+		 * Children normally retain their inherited event on exec; with
+		 * remove_on_exec, we'll remove their event, but the parent and
+		 * any other non-exec'd children will keep their events.
+		 */
+		.remove_on_exec = 1,
+		.sigtrap	= 1,
+	};
+	return attr;
+}
+
+static void sigtrap_handler(int signum, siginfo_t *info, void *ucontext)
+{
+	if (info->si_code != TRAP_PERF) {
+		fprintf(stderr, "%s: unexpected si_code %d\n", __func__, info->si_code);
+		return;
+	}
+
+	signal_count++;
+}
+
+FIXTURE(remove_on_exec)
+{
+	struct sigaction oldact;
+	int fd;
+};
+
+FIXTURE_SETUP(remove_on_exec)
+{
+	struct perf_event_attr attr = make_event_attr();
+	struct sigaction action = {};
+
+	signal_count = 0;
+
+	/* Initialize sigtrap handler. */
+	action.sa_flags = SA_SIGINFO | SA_NODEFER;
+	action.sa_sigaction = sigtrap_handler;
+	sigemptyset(&action.sa_mask);
+	ASSERT_EQ(sigaction(SIGTRAP, &action, &self->oldact), 0);
+
+	/* Initialize perf event. */
+	self->fd = syscall(__NR_perf_event_open, &attr, 0, -1, -1, PERF_FLAG_FD_CLOEXEC);
+	ASSERT_NE(self->fd, -1);
+}
+
+FIXTURE_TEARDOWN(remove_on_exec)
+{
+	close(self->fd);
+	sigaction(SIGTRAP, &self->oldact, NULL);
+}
+
+/* Verify event propagates to fork'd child. */
+TEST_F(remove_on_exec, fork_only)
+{
+	int status;
+	pid_t pid = fork();
+
+	if (pid == 0) {
+		ASSERT_EQ(signal_count, 0);
+		ASSERT_EQ(ioctl(self->fd, PERF_EVENT_IOC_ENABLE, 0), 0);
+		while (!signal_count);
+		_exit(42);
+	}
+
+	while (!signal_count); /* Child enables event. */
+	EXPECT_EQ(waitpid(pid, &status, 0), pid);
+	EXPECT_EQ(WEXITSTATUS(status), 42);
+}
+
+/*
+ * Verify that event does _not_ propagate to fork+exec'd child; event enabled
+ * after fork+exec.
+ */
+TEST_F(remove_on_exec, fork_exec_then_enable)
+{
+	pid_t pid_exec, pid_only_fork;
+	int pipefd[2];
+	int tmp;
+
+	/*
+	 * Non-exec child, to ensure exec does not affect inherited events of
+	 * other children.
+	 */
+	pid_only_fork = fork();
+	if (pid_only_fork == 0) {
+		/* Block until parent enables event. */
+		while (!signal_count);
+		_exit(42);
+	}
+
+	ASSERT_NE(pipe(pipefd), -1);
+	pid_exec = fork();
+	if (pid_exec == 0) {
+		ASSERT_NE(dup2(pipefd[1], STDOUT_FILENO), -1);
+		close(pipefd[0]);
+		execl("/proc/self/exe", "exec_child", NULL);
+		_exit((perror("exec failed"), 1));
+	}
+	close(pipefd[1]);
+
+	ASSERT_EQ(waitpid(pid_exec, &tmp, WNOHANG), 0); /* Child is running. */
+	/* Wait for exec'd child to start spinning. */
+	EXPECT_EQ(read(pipefd[0], &tmp, sizeof(int)), sizeof(int));
+	EXPECT_EQ(tmp, 42);
+	close(pipefd[0]);
+	/* Now we can enable the event, knowing the child is doing work. */
+	EXPECT_EQ(ioctl(self->fd, PERF_EVENT_IOC_ENABLE, 0), 0);
+	/* If the event propagated to the exec'd child, it will exit normally... */
+	usleep(100000); /* ... give time for event to trigger (in case of bug). */
+	EXPECT_EQ(waitpid(pid_exec, &tmp, WNOHANG), 0); /* Should still be running. */
+	EXPECT_EQ(kill(pid_exec, SIGKILL), 0);
+
+	/* Verify removal from child did not affect this task's event. */
+	tmp = signal_count;
+	while (signal_count == tmp); /* Should not hang! */
+	/* Nor should it have affected the first child. */
+	EXPECT_EQ(waitpid(pid_only_fork, &tmp, 0), pid_only_fork);
+	EXPECT_EQ(WEXITSTATUS(tmp), 42);
+}
+
+/*
+ * Verify that event does _not_ propagate to fork+exec'd child; event enabled
+ * before fork+exec.
+ */
+TEST_F(remove_on_exec, enable_then_fork_exec)
+{
+	pid_t pid_exec;
+	int tmp;
+
+	EXPECT_EQ(ioctl(self->fd, PERF_EVENT_IOC_ENABLE, 0), 0);
+
+	pid_exec = fork();
+	if (pid_exec == 0) {
+		execl("/proc/self/exe", "exec_child", NULL);
+		_exit((perror("exec failed"), 1));
+	}
+
+	/*
+	 * The child may exit abnormally at any time if the event propagated and
+	 * a SIGTRAP is sent before the handler was set up.
+	 */
+	usleep(100000); /* ... give time for event to trigger (in case of bug). */
+	EXPECT_EQ(waitpid(pid_exec, &tmp, WNOHANG), 0); /* Should still be running. */
+	EXPECT_EQ(kill(pid_exec, SIGKILL), 0);
+
+	/* Verify removal from child did not affect this task's event. */
+	tmp = signal_count;
+	while (signal_count == tmp); /* Should not hang! */
+}
+
+TEST_F(remove_on_exec, exec_stress)
+{
+	pid_t pids[30];
+	int i, tmp;
+
+	for (i = 0; i < sizeof(pids) / sizeof(pids[0]); i++) {
+		pids[i] = fork();
+		if (pids[i] == 0) {
+			execl("/proc/self/exe", "exec_child", NULL);
+			_exit((perror("exec failed"), 1));
+		}
+
+		/* Some forked with event disabled, rest with enabled. */
+		if (i > 10)
+			EXPECT_EQ(ioctl(self->fd, PERF_EVENT_IOC_ENABLE, 0), 0);
+	}
+
+	usleep(100000); /* ... give time for event to trigger (in case of bug). */
+
+	for (i = 0; i < sizeof(pids) / sizeof(pids[0]); i++) {
+		/* All children should still be running. */
+		EXPECT_EQ(waitpid(pids[i], &tmp, WNOHANG), 0);
+		EXPECT_EQ(kill(pids[i], SIGKILL), 0);
+	}
+
+	/* Verify event is still alive. */
+	tmp = signal_count;
+	while (signal_count == tmp);
+}
+
+/* For exec'd child. */
+static void exec_child(void)
+{
+	struct sigaction action = {};
+	const int val = 42;
+
+	/* Set up sigtrap handler in case we erroneously receive a trap. */
+	action.sa_flags = SA_SIGINFO | SA_NODEFER;
+	action.sa_sigaction = sigtrap_handler;
+	sigemptyset(&action.sa_mask);
+	if (sigaction(SIGTRAP, &action, NULL))
+		_exit((perror("sigaction failed"), 1));
+
+	/* Signal parent that we're starting to spin. */
+	if (write(STDOUT_FILENO, &val, sizeof(int)) == -1)
+		_exit((perror("write failed"), 1));
+
+	/* Should hang here until killed. */
+	while (!signal_count);
+}
+
+#define main test_main
+TEST_HARNESS_MAIN
+#undef main
+int main(int argc, char *argv[])
+{
+	if (!strcmp(argv[0], "exec_child")) {
+		exec_child();
+		return 1;
+	}
+
+	return test_main(argc, argv);
+}
diff --git a/tools/testing/selftests/perf_events/settings b/tools/testing/selftests/perf_events/settings
new file mode 100644
index 000000000000..6091b45d226b
--- /dev/null
+++ b/tools/testing/selftests/perf_events/settings
@@ -0,0 +1 @@
+timeout=120
diff --git a/tools/testing/selftests/perf_events/sigtrap_threads.c b/tools/testing/selftests/perf_events/sigtrap_threads.c
new file mode 100644
index 000000000000..78ddf5e11625
--- /dev/null
+++ b/tools/testing/selftests/perf_events/sigtrap_threads.c
@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test for perf events with SIGTRAP across all threads.
+ *
+ * Copyright (C) 2021, Google LLC.
+ */
+
+#define _GNU_SOURCE
+
+/* We need the latest siginfo from the kernel repo. */
+#include <sys/types.h>
+#include <asm/siginfo.h>
+#define __have_siginfo_t 1
+#define __have_sigval_t 1
+#define __have_sigevent_t 1
+#define __siginfo_t_defined
+#define __sigval_t_defined
+#define __sigevent_t_defined
+#define _BITS_SIGINFO_CONSTS_H 1
+#define _BITS_SIGEVENT_CONSTS_H 1
+
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/perf_event.h>
+#include <pthread.h>
+#include <signal.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "../kselftest_harness.h"
+
+#define NUM_THREADS 5
+
+/* Data shared between test body, threads, and signal handler. */
+static struct {
+	int tids_want_signal;		/* Which threads still want a signal. */
+	int signal_count;		/* Sanity check number of signals received. */
+	volatile int iterate_on;	/* Variable to set breakpoint on. */
+	siginfo_t first_siginfo;	/* First observed siginfo_t. */
+} ctx;
+
+/* Unique value to check si_perf is correctly set from perf_event_attr::sig_data. */
+#define TEST_SIG_DATA(addr) (~(unsigned long)(addr))
+
+static struct perf_event_attr make_event_attr(bool enabled, volatile void *addr)
+{
+	struct perf_event_attr attr = {
+		.type		= PERF_TYPE_BREAKPOINT,
+		.size		= sizeof(attr),
+		.sample_period	= 1,
+		.disabled	= !enabled,
+		.bp_addr	= (unsigned long)addr,
+		.bp_type	= HW_BREAKPOINT_RW,
+		.bp_len		= HW_BREAKPOINT_LEN_1,
+		.inherit	= 1, /* Children inherit events ... */
+		.inherit_thread = 1, /* ... but only cloned with CLONE_THREAD. */
+		.remove_on_exec = 1, /* Required by sigtrap. */
+		.sigtrap	= 1, /* Request synchronous SIGTRAP on event. */
+		.sig_data	= TEST_SIG_DATA(addr),
+	};
+	return attr;
+}
+
+static void sigtrap_handler(int signum, siginfo_t *info, void *ucontext)
+{
+	if (info->si_code != TRAP_PERF) {
+		fprintf(stderr, "%s: unexpected si_code %d\n", __func__, info->si_code);
+		return;
+	}
+
+	/*
+	 * The data in siginfo_t we're interested in should all be the same
+	 * across threads.
+	 */
+	if (!__atomic_fetch_add(&ctx.signal_count, 1, __ATOMIC_RELAXED))
+		ctx.first_siginfo = *info;
+	__atomic_fetch_sub(&ctx.tids_want_signal, syscall(__NR_gettid), __ATOMIC_RELAXED);
+}
+
+static void *test_thread(void *arg)
+{
+	pthread_barrier_t *barrier = (pthread_barrier_t *)arg;
+	pid_t tid = syscall(__NR_gettid);
+	int iter;
+	int i;
+
+	pthread_barrier_wait(barrier);
+
+	__atomic_fetch_add(&ctx.tids_want_signal, tid, __ATOMIC_RELAXED);
+	iter = ctx.iterate_on; /* read */
+	for (i = 0; i < iter - 1; i++) {
+		__atomic_fetch_add(&ctx.tids_want_signal, tid, __ATOMIC_RELAXED);
+		ctx.iterate_on = iter; /* idempotent write */
+	}
+
+	return NULL;
+}
+
+FIXTURE(sigtrap_threads)
+{
+	struct sigaction oldact;
+	pthread_t threads[NUM_THREADS];
+	pthread_barrier_t barrier;
+	int fd;
+};
+
+FIXTURE_SETUP(sigtrap_threads)
+{
+	struct perf_event_attr attr = make_event_attr(false, &ctx.iterate_on);
+	struct sigaction action = {};
+	int i;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	/* Initialize sigtrap handler. */
+	action.sa_flags = SA_SIGINFO | SA_NODEFER;
+	action.sa_sigaction = sigtrap_handler;
+	sigemptyset(&action.sa_mask);
+	ASSERT_EQ(sigaction(SIGTRAP, &action, &self->oldact), 0);
+
+	/* Initialize perf event. */
+	self->fd = syscall(__NR_perf_event_open, &attr, 0, -1, -1, PERF_FLAG_FD_CLOEXEC);
+	ASSERT_NE(self->fd, -1);
+
+	/* Spawn threads inheriting perf event. */
+	pthread_barrier_init(&self->barrier, NULL, NUM_THREADS + 1);
+	for (i = 0; i < NUM_THREADS; i++)
+		ASSERT_EQ(pthread_create(&self->threads[i], NULL, test_thread, &self->barrier), 0);
+}
+
+FIXTURE_TEARDOWN(sigtrap_threads)
+{
+	pthread_barrier_destroy(&self->barrier);
+	close(self->fd);
+	sigaction(SIGTRAP, &self->oldact, NULL);
+}
+
+static void run_test_threads(struct __test_metadata *_metadata,
+			     FIXTURE_DATA(sigtrap_threads) *self)
+{
+	int i;
+
+	pthread_barrier_wait(&self->barrier);
+	for (i = 0; i < NUM_THREADS; i++)
+		ASSERT_EQ(pthread_join(self->threads[i], NULL), 0);
+}
+
+TEST_F(sigtrap_threads, remain_disabled)
+{
+	run_test_threads(_metadata, self);
+	EXPECT_EQ(ctx.signal_count, 0);
+	EXPECT_NE(ctx.tids_want_signal, 0);
+}
+
+TEST_F(sigtrap_threads, enable_event)
+{
+	EXPECT_EQ(ioctl(self->fd, PERF_EVENT_IOC_ENABLE, 0), 0);
+	run_test_threads(_metadata, self);
+
+	EXPECT_EQ(ctx.signal_count, NUM_THREADS);
+	EXPECT_EQ(ctx.tids_want_signal, 0);
+	EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
+	EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT);
+	EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on));
+
+	/* Check enabled for parent. */
+	ctx.iterate_on = 0;
+	EXPECT_EQ(ctx.signal_count, NUM_THREADS + 1);
+}
+
+/* Test that modification propagates to all inherited events. */
+TEST_F(sigtrap_threads, modify_and_enable_event)
+{
+	struct perf_event_attr new_attr = make_event_attr(true, &ctx.iterate_on);
+
+	EXPECT_EQ(ioctl(self->fd, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &new_attr), 0);
+	run_test_threads(_metadata, self);
+
+	EXPECT_EQ(ctx.signal_count, NUM_THREADS);
+	EXPECT_EQ(ctx.tids_want_signal, 0);
+	EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
+	EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT);
+	EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on));
+
+	/* Check enabled for parent. */
+	ctx.iterate_on = 0;
+	EXPECT_EQ(ctx.signal_count, NUM_THREADS + 1);
+}
+
+/* Stress test event + signal handling. */
+TEST_F(sigtrap_threads, signal_stress)
+{
+	ctx.iterate_on = 3000;
+
+	EXPECT_EQ(ioctl(self->fd, PERF_EVENT_IOC_ENABLE, 0), 0);
+	run_test_threads(_metadata, self);
+	EXPECT_EQ(ioctl(self->fd, PERF_EVENT_IOC_DISABLE, 0), 0);
+
+	EXPECT_EQ(ctx.signal_count, NUM_THREADS * ctx.iterate_on);
+	EXPECT_EQ(ctx.tids_want_signal, 0);
+	EXPECT_EQ(ctx.first_siginfo.si_addr, &ctx.iterate_on);
+	EXPECT_EQ(ctx.first_siginfo.si_errno, PERF_TYPE_BREAKPOINT);
+	EXPECT_EQ(ctx.first_siginfo.si_perf, TEST_SIG_DATA(&ctx.iterate_on));
+}
+
+TEST_HARNESS_MAIN