arm64 userspace counter access support

Userspace counter access only works on heterogeneous systems with some restrictions. The userspace process must be pinned to a homogeneous subset of CPUs and must open the corresponding PMU for those CPUs. This commit adds a test implementing these requirements.

Signed-off-by Rob Herring <[email protected]>

---
v6:
- Add a check on cap_user_rdpmc
v5:
- Adapt to libperf mmap API changes
v4:
- Update perf_evsel__mmap params
v2:
- Drop all but heterogeneous test as others covered by libperf tests
- Rework to use libperf

---
 tools/perf/arch/arm64/include/arch-tests.h |   7 +
 tools/perf/arch/arm64/tests/Build          |   1 +
 tools/perf/arch/arm64/tests/arch-tests.c   |   4 +
 tools/perf/arch/arm64/tests/user-events.c  | 177 +++++++++++++++++++++
 4 files changed, 189 insertions(+)
 create mode 100644 tools/perf/arch/arm64/tests/user-events.c

tools/perf/arch/arm64/include/arch-tests.h +0 -0

index 90ec4c8cb880..380ad34a3f09 100644
@@ -2,11 +2,18 @@
 #ifndef ARCH_TESTS_H

tools/perf/arch/arm64/include/arch-tests.h +3 -0

 extern struct test arch_tests[];
+int test__rd_pinned(struct test __maybe_unused *test,
+		       int __maybe_unused subtest);
+
 
 #endif

tools/perf/arch/arm64/tests/Build +1 -0

index a61c06bdb757..3f9a20c17fc6 100644
@@ -1,4 +1,5 @@
 perf-y += regs_load.o
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 
+perf-y += user-events.o
 perf-y += arch-tests.o

tools/perf/arch/arm64/tests/arch-tests.c +4 -0

index 5b1543c98022..80ce7bd3c16d 100644
@@ -10,6 +10,10 @@ struct test arch_tests[] = {
 		.func = test__dwarf_unwind,
 	},
 #endif
+	{
+		.desc = "Pinned CPU user counter access",
+		.func = test__rd_pinned,
+	},
 	{
 		.func = NULL,
 	},

tools/perf/arch/arm64/tests/user-events.c new file +177 -0

new file mode 100644
index 000000000000..c8efc6b369e6
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <unistd.h>
+#include <sched.h>
+#include <cpumap.h>
+
+#include <perf/core.h>
+#include <perf/threadmap.h>
+#include <perf/evsel.h>
+
+#include "pmu.h"
+#include "debug.h"
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+static int run_test(struct perf_evsel *evsel)
+{
+	int n;
+	volatile int tmp = 0;
+	u64 delta, i, loops = 1000;
+	struct perf_counts_values counts = { .val = 0 };
+
+	for (n = 0; n < 6; n++) {
+		u64 stamp, now;
+
+		perf_evsel__read(evsel, 0, 0, &counts);
+		stamp = counts.val;
+
+		for (i = 0; i < loops; i++)
+			tmp++;
+
+		perf_evsel__read(evsel, 0, 0, &counts);
+		now = counts.val;
+		loops *= 10;
+
+		delta = now - stamp;
+		pr_debug("%14d: %14llu\n", n, (long long)delta);
+
+		if (!delta)
+			break;
+	}
+	return delta ? 0 : -1;
+}
+
+static struct perf_pmu *pmu_for_cpu(int cpu)
+{
+	int acpu, idx;
+	struct perf_pmu *pmu = NULL;
+
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+		if (pmu->is_uncore)
+			continue;
+		perf_cpu_map__for_each_cpu(acpu, idx, pmu->cpus)
+			if (acpu == cpu)
+				return pmu;
+	}
+	return NULL;
+}
+
+static bool pmu_is_homogeneous(void)
+{
+	int core_cnt = 0;
+	struct perf_pmu *pmu = NULL;
+
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+		if (!pmu->is_uncore && !perf_cpu_map__empty(pmu->cpus))
+			core_cnt++;
+	}
+	return core_cnt == 1;
+}
+
+static int libperf_print(enum libperf_print_level level,
+			 const char *fmt, va_list ap)
+{
+	(void)level;
+	return vfprintf(stderr, fmt, ap);
+}
+
+static struct perf_evsel *perf_init(struct perf_event_attr *attr)
+{
+	int err;
+	struct perf_thread_map *threads;
+	struct perf_evsel *evsel;
+	struct perf_event_mmap_page *pc;
+
+	libperf_init(libperf_print);
+
+	threads = perf_thread_map__new_dummy();
+	if (!threads) {
+		pr_err("failed to create threads\n");
+		return NULL;
+	}
+
+	perf_thread_map__set_pid(threads, 0, 0);
+
+	evsel = perf_evsel__new(attr);
+	if (!evsel) {
+		pr_err("failed to create evsel\n");
+		goto out_thread;
+	}
+
+	err = perf_evsel__open(evsel, NULL, threads);
+	if (err) {
+		pr_err("failed to open evsel\n");
+		goto out_open;
+	}
+
+	if (perf_evsel__mmap(evsel, 0)) {
+		pr_err("failed to mmap evsel\n");
+		goto out_mmap;
+	}
+
+	pc = perf_evsel__mmap_base(evsel, 0, 0);
+	if (!pc->cap_user_rdpmc) {
+		pr_err("userspace access not enabled\n");
+		goto out_mmap;
+	}
+
+	return evsel;
+
+out_mmap:
+	perf_evsel__close(evsel);
+out_open:
+	perf_evsel__delete(evsel);
+out_thread:
+	perf_thread_map__put(threads);
+	return NULL;
+}
+
+int test__rd_pinned(struct test __maybe_unused *test,
+		    int __maybe_unused subtest)
+{
+	int cpu, cputmp, ret = -1;
+	struct perf_evsel *evsel;
+	struct perf_event_attr attr = {
+		.config = 0x8, /* Instruction count */
+		.config1 = 0, /* 32-bit counter */
+		.exclude_kernel = 1,
+	};
+	cpu_set_t cpu_set;
+	struct perf_pmu *pmu;
+
+	if (pmu_is_homogeneous())
+		return TEST_SKIP;
+
+	cpu = sched_getcpu();
+	pmu = pmu_for_cpu(cpu);
+	if (!pmu)
+		return -1;
+	attr.type = pmu->type;
+
+	CPU_ZERO(&cpu_set);
+	perf_cpu_map__for_each_cpu(cpu, cputmp, pmu->cpus)
+		CPU_SET(cpu, &cpu_set);
+	if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0)
+		pr_err("Could not set affinity\n");
+
+	evsel = perf_init(&attr);
+	if (!evsel)
+		return -1;
+
+	perf_cpu_map__for_each_cpu(cpu, cputmp, pmu->cpus) {
+		CPU_ZERO(&cpu_set);
+		CPU_SET(cpu, &cpu_set);
+		if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0)
+			pr_err("Could not set affinity\n");
+
+		pr_debug("Running on CPU %d\n", cpu);
+
+		ret = run_test(evsel);
+		if (ret)
+			break;
+	}
+
+	perf_evsel__close(evsel);
+	perf_evsel__delete(evsel);
+	return ret;
+}

Signature · 7 lines

2.27.0


_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Quoted 30 lines · Rob Herring

Userspace counter access only works on heterogeneous systems with some restrictions. The userspace process must be pinned to a homogeneous subset of CPUs and must open the corresponding PMU for those CPUs. This commit adds a test implementing these requirements.

Signed-off-by Rob Herring <[email protected]>

---
v6:
- Add a check on cap_user_rdpmc
v5:
- Adapt to libperf mmap API changes
v4:
- Update perf_evsel__mmap params
v2:
- Drop all but heterogeneous test as others covered by libperf tests
- Rework to use libperf

---
 tools/perf/arch/arm64/include/arch-tests.h |   7 +
 tools/perf/arch/arm64/tests/Build          |   1 +
 tools/perf/arch/arm64/tests/arch-tests.c   |   4 +
 tools/perf/arch/arm64/tests/user-events.c  | 177 +++++++++++++++++++++
 4 files changed, 189 insertions(+)
 create mode 100644 tools/perf/arch/arm64/tests/user-events.c

tools/perf/arch/arm64/include/arch-tests.h +0 -0

index 90ec4c8cb880..380ad34a3f09 100644
@@ -2,11 +2,18 @@
 #ifndef ARCH_TESTS_H

tools/perf/arch/arm64/include/arch-tests.h line 12

Quoted 10 lines

tools/perf/arch/arm64/include/arch-tests.h +4 -0

 #define ARCH_TESTS_H
 
+#include <linux/compiler.h>
+
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
 struct perf_sample;
+int test__arch_unwind_sample(struct perf_sample *sample,
+                          struct thread *thread);
 #endif

Hello,

I got the following compile error with aarch64 on Fedora33.

    # make tools/perf
    ...
    In file included from arch/arm64/tests/arch-tests.c:4:
    /root//libperf_v7/tools/perf/arch/arm64/include/arch-tests.h:10:5: error: redundant redeclaration of ‘test__arch_unwind_sample’ [-Werror=redundant-decls]
       10 | int test__arch_unwind_sample(struct perf_sample *sample,
          |     ^~~~~~~~~~~~~~~~~~~~~~~~
    In file included from arch/arm64/tests/arch-tests.c:3:
    /root//libperf_v7/tools/perf/tests/tests.h:140:5: note: previous declaration of ‘test__arch_unwind_sample’ was here
      140 | int test__arch_unwind_sample(struct perf_sample *sample,
          |     ^~~~~~~~~~~~~~~~~~~~~~~~
    cc1: all warnings being treated as errors
    make[8]: *** [/root//libperf_v7/tools/build/Makefile.build:97: /root/libperf_v7/tools/perf/arch/arm64/tests/arch-tests.o] Error 1
    make[8]: *** Waiting for unfinished jobs....
    In file included from arch/arm64/tests/user-events.c:13:
    /root//libperf_v7/tools/perf/arch/arm64/include/arch-tests.h:10:5: error: redundant redeclaration of ‘test__arch_unwind_sample’ [-Werror=redundant-decls]
       10 | int test__arch_unwind_sample(struct perf_sample *sample,
          |     ^~~~~~~~~~~~~~~~~~~~~~~~
    In file included from arch/arm64/tests/user-events.c:12:
    /root//libperf_v7/tools/perf/tests/tests.h:140:5: note: previous declaration of ‘test__arch_unwind_sample’ was here
      140 | int test__arch_unwind_sample(struct perf_sample *sample,
          |     ^~~~~~~~~~~~~~~~~~~~~~~~
    cc1: all warnings being treated as errors
    ...

The error is gone after the following patch is applied.

---
 tools/perf/arch/arm64/include/arch-tests.h | 7 -------
 1 file changed, 7 deletions(-)

tools/perf/arch/arm64/include/arch-tests.h +0 -8

index ddfa7460e..7ff2e29bd 100644
@@ -4,13 +4,6 @@
 
 #include <linux/compiler.h>
 
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-struct thread;
-struct perf_sample;
-int test__arch_unwind_sample(struct perf_sample *sample,
-                            struct thread *thread);
-#endif
-
 extern struct test arch_tests[];
 int test__rd_pinned(struct test __maybe_unused *test,
                       int __maybe_unused subtest);
--

Thanks!
Masa

Quoted 223 lines

tools/perf/arch/arm64/include/arch-tests.h +3 -0

 extern struct test arch_tests[];
+int test__rd_pinned(struct test __maybe_unused *test,
+                    int __maybe_unused subtest);
+
 
 #endif

tools/perf/arch/arm64/tests/Build +1 -0

index a61c06bdb757..3f9a20c17fc6 100644
@@ -1,4 +1,5 @@
 perf-y += regs_load.o
 perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o
 
+perf-y += user-events.o
 perf-y += arch-tests.o

tools/perf/arch/arm64/tests/arch-tests.c +4 -0

index 5b1543c98022..80ce7bd3c16d 100644
@@ -10,6 +10,10 @@ struct test arch_tests[] = {
              .func = test__dwarf_unwind,
      },
 #endif
+     {
+             .desc = "Pinned CPU user counter access",
+             .func = test__rd_pinned,
+     },
      {
              .func = NULL,
      },

tools/perf/arch/arm64/tests/user-events.c new file +177 -1

new file mode 100644
index 000000000000..c8efc6b369e6
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <unistd.h>
+#include <sched.h>
+#include <cpumap.h>
+
+#include <perf/core.h>
+#include <perf/threadmap.h>
+#include <perf/evsel.h>
+
+#include "pmu.h"
+#include "debug.h"
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+static int run_test(struct perf_evsel *evsel)
+{
+     int n;
+     volatile int tmp = 0;
+     u64 delta, i, loops = 1000;
+     struct perf_counts_values counts = { .val = 0 };
+
+     for (n = 0; n < 6; n++) {
+             u64 stamp, now;
+
+             perf_evsel__read(evsel, 0, 0, &counts);
+             stamp = counts.val;
+
+             for (i = 0; i < loops; i++)
+                     tmp++;
+
+             perf_evsel__read(evsel, 0, 0, &counts);
+             now = counts.val;
+             loops *= 10;
+
+             delta = now - stamp;
+             pr_debug("%14d: %14llu\n", n, (long long)delta);
+
+             if (!delta)
+                     break;
+     }
+     return delta ? 0 : -1;
+}
+
+static struct perf_pmu *pmu_for_cpu(int cpu)
+{
+     int acpu, idx;
+     struct perf_pmu *pmu = NULL;
+
+     while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+             if (pmu->is_uncore)
+                     continue;
+             perf_cpu_map__for_each_cpu(acpu, idx, pmu->cpus)
+                     if (acpu == cpu)
+                             return pmu;
+     }
+     return NULL;
+}
+
+static bool pmu_is_homogeneous(void)
+{
+     int core_cnt = 0;
+     struct perf_pmu *pmu = NULL;
+
+     while ((pmu = perf_pmu__scan(pmu)) != NULL) {
+             if (!pmu->is_uncore && !perf_cpu_map__empty(pmu->cpus))
+                     core_cnt++;
+     }
+     return core_cnt == 1;
+}
+
+static int libperf_print(enum libperf_print_level level,
+                      const char *fmt, va_list ap)
+{
+     (void)level;
+     return vfprintf(stderr, fmt, ap);
+}
+
+static struct perf_evsel *perf_init(struct perf_event_attr *attr)
+{
+     int err;
+     struct perf_thread_map *threads;
+     struct perf_evsel *evsel;
+     struct perf_event_mmap_page *pc;
+
+     libperf_init(libperf_print);
+
+     threads = perf_thread_map__new_dummy();
+     if (!threads) {
+             pr_err("failed to create threads\n");
+             return NULL;
+     }
+
+     perf_thread_map__set_pid(threads, 0, 0);
+
+     evsel = perf_evsel__new(attr);
+     if (!evsel) {
+             pr_err("failed to create evsel\n");
+             goto out_thread;
+     }
+
+     err = perf_evsel__open(evsel, NULL, threads);
+     if (err) {
+             pr_err("failed to open evsel\n");
+             goto out_open;
+     }
+
+     if (perf_evsel__mmap(evsel, 0)) {
+             pr_err("failed to mmap evsel\n");
+             goto out_mmap;
+     }
+
+     pc = perf_evsel__mmap_base(evsel, 0, 0);
+     if (!pc->cap_user_rdpmc) {
+             pr_err("userspace access not enabled\n");
+             goto out_mmap;
+     }
+
+     return evsel;
+
+out_mmap:
+     perf_evsel__close(evsel);
+out_open:
+     perf_evsel__delete(evsel);
+out_thread:
+     perf_thread_map__put(threads);
+     return NULL;
+}
+
+int test__rd_pinned(struct test __maybe_unused *test,
+                 int __maybe_unused subtest)
+{
+     int cpu, cputmp, ret = -1;
+     struct perf_evsel *evsel;
+     struct perf_event_attr attr = {
+             .config = 0x8, /* Instruction count */
+             .config1 = 0, /* 32-bit counter */
+             .exclude_kernel = 1,
+     };
+     cpu_set_t cpu_set;
+     struct perf_pmu *pmu;
+
+     if (pmu_is_homogeneous())
+             return TEST_SKIP;
+
+     cpu = sched_getcpu();
+     pmu = pmu_for_cpu(cpu);
+     if (!pmu)
+             return -1;
+     attr.type = pmu->type;
+
+     CPU_ZERO(&cpu_set);
+     perf_cpu_map__for_each_cpu(cpu, cputmp, pmu->cpus)
+             CPU_SET(cpu, &cpu_set);
+     if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0)
+             pr_err("Could not set affinity\n");
+
+     evsel = perf_init(&attr);
+     if (!evsel)
+             return -1;
+
+     perf_cpu_map__for_each_cpu(cpu, cputmp, pmu->cpus) {
+             CPU_ZERO(&cpu_set);
+             CPU_SET(cpu, &cpu_set);
+             if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0)
+                     pr_err("Could not set affinity\n");
+
+             pr_debug("Running on CPU %d\n", cpu);
+
+             ret = run_test(evsel);
+             if (ret)
+                     break;
+     }
+
+     perf_evsel__close(evsel);
+     perf_evsel__delete(evsel);
+     return ret;
+}
--

2.27.0

_______________________________________________
linux-arm-kernel mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

Quoted 71 lines · Masayoshi Mizuma

Quoted 30 lines · Rob Herring

Userspace counter access only works on heterogeneous systems with some restrictions. The userspace process must be pinned to a homogeneous subset of CPUs and must open the corresponding PMU for those CPUs. This commit adds a test implementing these requirements.

Signed-off-by Rob Herring <[email protected]>

---
v6:
- Add a check on cap_user_rdpmc
v5:
- Adapt to libperf mmap API changes
v4:
- Update perf_evsel__mmap params
v2:
- Drop all but heterogeneous test as others covered by libperf tests
- Rework to use libperf

---
 tools/perf/arch/arm64/include/arch-tests.h |   7 +
 tools/perf/arch/arm64/tests/Build          |   1 +
 tools/perf/arch/arm64/tests/arch-tests.c   |   4 +
 tools/perf/arch/arm64/tests/user-events.c  | 177 +++++++++++++++++++++
 4 files changed, 189 insertions(+)
 create mode 100644 tools/perf/arch/arm64/tests/user-events.c

tools/perf/arch/arm64/include/arch-tests.h +0 -0

index 90ec4c8cb880..380ad34a3f09 100644
@@ -2,11 +2,18 @@
 #ifndef ARCH_TESTS_H

tools/perf/arch/arm64/include/arch-tests.h line 12

Quoted 10 lines

tools/perf/arch/arm64/include/arch-tests.h +4 -0

 #define ARCH_TESTS_H
 
+#include <linux/compiler.h>
+
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
 struct perf_sample;
+int test__arch_unwind_sample(struct perf_sample *sample,
+                          struct thread *thread);
 #endif

Hello,

I got the following compile error with aarch64 on Fedora33.

    # make tools/perf
    ...
    In file included from arch/arm64/tests/arch-tests.c:4:
    /root//libperf_v7/tools/perf/arch/arm64/include/arch-tests.h:10:5: error: redundant redeclaration of ‘test__arch_unwind_sample’ [-Werror=redundant-decls]
       10 | int test__arch_unwind_sample(struct perf_sample *sample,
          |     ^~~~~~~~~~~~~~~~~~~~~~~~
    In file included from arch/arm64/tests/arch-tests.c:3:
    /root//libperf_v7/tools/perf/tests/tests.h:140:5: note: previous declaration of ‘test__arch_unwind_sample’ was here
      140 | int test__arch_unwind_sample(struct perf_sample *sample,
          |     ^~~~~~~~~~~~~~~~~~~~~~~~
    cc1: all warnings being treated as errors
    make[8]: *** [/root//libperf_v7/tools/build/Makefile.build:97: /root/libperf_v7/tools/perf/arch/arm64/tests/arch-tests.o] Error 1
    make[8]: *** Waiting for unfinished jobs....
    In file included from arch/arm64/tests/user-events.c:13:
    /root//libperf_v7/tools/perf/arch/arm64/include/arch-tests.h:10:5: error: redundant redeclaration of ‘test__arch_unwind_sample’ [-Werror=redundant-decls]
       10 | int test__arch_unwind_sample(struct perf_sample *sample,
          |     ^~~~~~~~~~~~~~~~~~~~~~~~
    In file included from arch/arm64/tests/user-events.c:12:
    /root//libperf_v7/tools/perf/tests/tests.h:140:5: note: previous declaration of ‘test__arch_unwind_sample’ was here
      140 | int test__arch_unwind_sample(struct perf_sample *sample,
          |     ^~~~~~~~~~~~~~~~~~~~~~~~
    cc1: all warnings being treated as errors
    ...

Quoted 1 line

The error is gone after the following patch is applied.

Thanks. Honestly, I'm not sure why it was there in the first place. Looking at the git history and this series history doesn't give any clues.

Quoted 73 lines · Rob Herring

Quoted 71 lines · Masayoshi Mizuma

Quoted 30 lines · Rob Herring

Userspace counter access only works on heterogeneous systems with some restrictions. The userspace process must be pinned to a homogeneous subset of CPUs and must open the corresponding PMU for those CPUs. This commit adds a test implementing these requirements.

Signed-off-by Rob Herring <[email protected]>

---
v6:
- Add a check on cap_user_rdpmc
v5:
- Adapt to libperf mmap API changes
v4:
- Update perf_evsel__mmap params
v2:
- Drop all but heterogeneous test as others covered by libperf tests
- Rework to use libperf

---
 tools/perf/arch/arm64/include/arch-tests.h |   7 +
 tools/perf/arch/arm64/tests/Build          |   1 +
 tools/perf/arch/arm64/tests/arch-tests.c   |   4 +
 tools/perf/arch/arm64/tests/user-events.c  | 177 +++++++++++++++++++++
 4 files changed, 189 insertions(+)
 create mode 100644 tools/perf/arch/arm64/tests/user-events.c

tools/perf/arch/arm64/include/arch-tests.h +0 -0

index 90ec4c8cb880..380ad34a3f09 100644
@@ -2,11 +2,18 @@
 #ifndef ARCH_TESTS_H

tools/perf/arch/arm64/include/arch-tests.h line 12

Quoted 10 lines

tools/perf/arch/arm64/include/arch-tests.h +4 -0

 #define ARCH_TESTS_H
 
+#include <linux/compiler.h>
+
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
 struct perf_sample;
+int test__arch_unwind_sample(struct perf_sample *sample,
+                          struct thread *thread);
 #endif

Hello,

I got the following compile error with aarch64 on Fedora33.

    # make tools/perf
    ...
    In file included from arch/arm64/tests/arch-tests.c:4:
    /root//libperf_v7/tools/perf/arch/arm64/include/arch-tests.h:10:5: error: redundant redeclaration of ‘test__arch_unwind_sample’ [-Werror=redundant-decls]
       10 | int test__arch_unwind_sample(struct perf_sample *sample,
          |     ^~~~~~~~~~~~~~~~~~~~~~~~
    In file included from arch/arm64/tests/arch-tests.c:3:
    /root//libperf_v7/tools/perf/tests/tests.h:140:5: note: previous declaration of ‘test__arch_unwind_sample’ was here
      140 | int test__arch_unwind_sample(struct perf_sample *sample,
          |     ^~~~~~~~~~~~~~~~~~~~~~~~
    cc1: all warnings being treated as errors
    make[8]: *** [/root//libperf_v7/tools/build/Makefile.build:97: /root/libperf_v7/tools/perf/arch/arm64/tests/arch-tests.o] Error 1
    make[8]: *** Waiting for unfinished jobs....
    In file included from arch/arm64/tests/user-events.c:13:
    /root//libperf_v7/tools/perf/arch/arm64/include/arch-tests.h:10:5: error: redundant redeclaration of ‘test__arch_unwind_sample’ [-Werror=redundant-decls]
       10 | int test__arch_unwind_sample(struct perf_sample *sample,
          |     ^~~~~~~~~~~~~~~~~~~~~~~~
    In file included from arch/arm64/tests/user-events.c:12:
    /root//libperf_v7/tools/perf/tests/tests.h:140:5: note: previous declaration of ‘test__arch_unwind_sample’ was here
      140 | int test__arch_unwind_sample(struct perf_sample *sample,
          |     ^~~~~~~~~~~~~~~~~~~~~~~~
    cc1: all warnings being treated as errors
    ...

Quoted 5 lines

Quoted 1 line

The error is gone after the following patch is applied.

Thanks. Honestly, I'm not sure why it was there in the first place. Looking at the git history and this series history doesn't give any clues.

Well, except that both x86 and powerpc have the same hunk in their arch-tests.h. Do you see errors on those arches?

Userspace counter access only works on heterogeneous systems with some restrictions. The userspace process must be pinned to a homogeneous subset of CPUs and must open the corresponding PMU for those CPUs. This commit adds a test implementing these requirements.

Hi Rob

Quoted 4 lines

Userspace counter access only works on heterogeneous systems with some restrictions. The userspace process must be pinned to a homogeneous subset of CPUs and must open the corresponding PMU for those CPUs. This commit adds a test implementing these requirements.

Are you planning to change x86 tests (tools/perf/arch/x86/tests/rdpmc.c) to use libperf as well?

Hi all,

Another version of arm64 userspace counter access support. I sent out the libperf bits separately and those are now applied (Thanks!), so this is just the arm64 bits.

This originally resurrected Raphael's series[1] to enable userspace counter access on arm64. My previous versions are here[2][3][4][5][6][7]. A git branch is here[8].

Changes in v7:
- Handling of dirty counter leakage and reworking of context switch and user access enabling. The .sched_task hook and undef instruction handler are now utilized. (Patch 3)
- Add a userspace disable switch like x86. (Patch 5)

Changes in v6:
- Reworking of the handling of 64-bit counters and user access. There's a new config1 flag to request user access. This takes priority over the 64-bit flag and the user will get the maximum size the h/w supports without chaining.
- The libperf evsel mmap struct is stored in its own xyarray
- New tests for user 64-bit and 32-bit counters
- Rebase to v5.12-rc2

Changes in v5:
- Limit enabling/disabling access to CPUs associated with the PMU (supported_cpus) and with the mm_struct matching current->active_mm. The x86 method of using mm_cpumask doesn't work for arm64 as it is not updated.
- Only set cap_user_rdpmc if event is on current cpu. See patch 2.
- Create an mmap for every event in an evsel. This results in some changes to the libperf mmap API from the last version.
- Rebase to v5.11-rc2

Changes in v4:
- Dropped 'arm64: pmu: Add hook to handle pmu-related undefined instructions'. The onus is on userspace to pin itself to a homogeneous subset of CPUs and avoid any aborts on heterogeneous systems, so the hook is not needed.
- Make perf_evsel__mmap() take pages rather than bytes for size
- Fix building arm64 heterogeneous test.

Changes in v3:
- Dropped removing x86 rdpmc test until libperf tests can run via 'perf test'
- Added verbose prints for tests
- Split adding perf_evsel__mmap() to separate patch

The following changes to the arm64 support have been made compared to Raphael's last version:

The major change is support for heterogeneous systems with some restrictions. Specifically, userspace must pin itself to like CPUs, open a specific PMU by type, and use h/w specific events. The tests have been reworked to demonstrate this.

Chained events are not supported. The problem with supporting chained events was there's no way to distinguish between a chained event and a native 64-bit counter. We could add some flag, but do self monitoring processes really need that? Native 64-bit counters are supported if the PMU h/w has support. As there's already an explicit ABI to request 64-bit counters, userspace can request 64-bit counters and if user access is not enabled, then it must retry with 32-bit counters.

Prior versions broke the build on arm32 (surprisingly never caught by 0-day). As a result, event_mapped and event_unmapped implementations have been moved into the arm64 code.

There was a bug in that pmc_width was not set in the user page. The tests now check for this.

The documentation has been converted to rST. I've added sections on chained events and heterogeneous.

The tests have been expanded to test the cycle counter access.

Rob

[1] https://lore.kernel.org/r/[email protected]/
[2] https://lore.kernel.org/r/[email protected]/
[3] https://lore.kernel.org/r/[email protected]/
[4] https://lore.kernel.org/r/[email protected]/
[5] https://lore.kernel.org/r/[email protected]/
[6] https://lore.kernel.org/r/[email protected]/
[7] https://lore.kernel.org/r/[email protected]/
[8] git://git.kernel.org/pub/scm/linux/kernel/git/robh/linux.git user-perf-event-v7

Raphael Gault (4):
arm64: Restrict undef hook for cpufeature registers
arm64: pmu: Add function implementation to update event index in
userpage
arm64: perf: Enable PMU counter direct access for perf event
Documentation: arm64: Document PMU counters access from userspace

Rob Herring (5):
drivers/perf: arm_pmu: Export the per_cpu cpu_armpmu
arm64: perf: Add userspace counter access disable switch
libperf: Add arm64 support to perf_mmap__read_self()
perf: arm64: Add test for userspace counter access on heterogeneous
systems
perf: arm64: Add tests for 32-bit and 64-bit counter size userspace
access

 Documentation/arm64/perf.rst               |  67 +++++-
 arch/arm64/include/asm/mmu.h               |   5 +
 arch/arm64/kernel/cpufeature.c             |   4 +-
 arch/arm64/kernel/perf_event.c             | 254 ++++++++++++++++++++-
 drivers/perf/arm_pmu.c                     |   2 +-
 include/linux/perf/arm_pmu.h               |  14 +-
 tools/lib/perf/mmap.c                      |  98 ++++++++
 tools/lib/perf/tests/test-evsel.c          |   2 +-
 tools/perf/arch/arm64/include/arch-tests.h |  12 +
 tools/perf/arch/arm64/tests/Build          |   1 +
 tools/perf/arch/arm64/tests/arch-tests.c   |  12 +
 tools/perf/arch/arm64/tests/user-events.c  | 215 +++++++++++++++++
 12 files changed, 672 insertions(+), 14 deletions(-)
 create mode 100644 tools/perf/arch/arm64/tests/user-events.c

--
2.27.0

Em Mon, Apr 19, 2021 at 10:15:02PM -0500, Rob Herring escreveu:

Quoted 7 lines

Hi all,

Another version of arm64 userspace counter access support. I sent out the libperf bits separately and those are now applied (Thanks!), so this is just the arm64 bits.

Quoted 3 lines

This originally resurrected Raphael's series[1] to enable userspace counter access on arm64. My previous versions are here[2][3][4][5][6][7]. A git branch is here[8].

Rob, please don't mix kernel patches with tools patches. The kernel bits, if arch specific should go via the arch maintainer, core stuff to PeterZ/Ingo/bpetkov/tglx, and tooling stuff I'll collect.

We did it on purpose to avoid any semblance of kernel/tool lockstep.

The kernel changes should not prevent the tooling from working and the tooling changes shouldn't require the kernel changes.

Preexisting kernels should work with new tools and vice versa.