* [PATCH 01/23] perf cpumap: Maintain cpumaps ordered and without dups
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
@ 2019-12-03 13:55 ` Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 02/23] perf evlist: Maintain evlist->all_cpus Arnaldo Carvalho de Melo
` (22 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:55 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Andi Kleen, Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
Enforce this in _trim()
Needed for followon change.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lore.kernel.org/lkml/20191121001522.180827-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/lib/cpumap.c | 16 +++++++++++++++-
1 file changed, 15 insertions(+), 1 deletion(-)
diff --git a/tools/perf/lib/cpumap.c b/tools/perf/lib/cpumap.c
index 2ca1fafa620d..d81656b4635e 100644
--- a/tools/perf/lib/cpumap.c
+++ b/tools/perf/lib/cpumap.c
@@ -68,14 +68,28 @@ static struct perf_cpu_map *cpu_map__default_new(void)
return cpus;
}
+static int cmp_int(const void *a, const void *b)
+{
+ return *(const int *)a - *(const int*)b;
+}
+
static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
{
size_t payload_size = nr_cpus * sizeof(int);
struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + payload_size);
+ int i, j;
if (cpus != NULL) {
- cpus->nr = nr_cpus;
memcpy(cpus->map, tmp_cpus, payload_size);
+ qsort(cpus->map, nr_cpus, sizeof(int), cmp_int);
+ /* Remove dups */
+ j = 0;
+ for (i = 0; i < nr_cpus; i++) {
+ if (i == 0 || cpus->map[i] != cpus->map[i - 1])
+ cpus->map[j++] = cpus->map[i];
+ }
+ cpus->nr = j;
+ assert(j <= nr_cpus);
refcount_set(&cpus->refcnt, 1);
}
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 02/23] perf evlist: Maintain evlist->all_cpus
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 01/23] perf cpumap: Maintain cpumaps ordered and without dups Arnaldo Carvalho de Melo
@ 2019-12-03 13:55 ` Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 03/23] perf evsel: Add iterator to iterate over events ordered by CPU Arnaldo Carvalho de Melo
` (21 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:55 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Andi Kleen, Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
Maintain a cpumap in the evlist that is the union of all the cpus of the
events.
This needs a cpumap merge operation, which is added together with tests.
v2:
Add tests for cpu map merge
Fix handling of duplicates
Rename _update to _merge
Factor out sorting.
Fix handling of NULL maps in merge
v3:
Add comments and empty lines to _merge
Committer testing:
# perf test "Merge cpu map"
52: Merge cpu map : Ok
#
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Link: http://lore.kernel.org/lkml/20191121001522.180827-5-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/lib/cpumap.c | 57 ++++++++++++++++++++++++
tools/perf/lib/evlist.c | 1 +
tools/perf/lib/include/internal/evlist.h | 1 +
tools/perf/lib/include/perf/cpumap.h | 2 +
tools/perf/tests/builtin-test.c | 5 +++
tools/perf/tests/cpumap.c | 16 +++++++
tools/perf/tests/tests.h | 1 +
7 files changed, 83 insertions(+)
diff --git a/tools/perf/lib/cpumap.c b/tools/perf/lib/cpumap.c
index d81656b4635e..f93f4e703e4c 100644
--- a/tools/perf/lib/cpumap.c
+++ b/tools/perf/lib/cpumap.c
@@ -286,3 +286,60 @@ int perf_cpu_map__max(struct perf_cpu_map *map)
return max;
}
+
+/*
+ * Merge two cpumaps
+ *
+ * orig either gets freed and replaced with a new map, or reused
+ * with no reference count change (similar to "realloc")
+ * other has its reference count increased.
+ */
+
+struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
+ struct perf_cpu_map *other)
+{
+ int *tmp_cpus;
+ int tmp_len;
+ int i, j, k;
+ struct perf_cpu_map *merged;
+
+ if (!orig && !other)
+ return NULL;
+ if (!orig) {
+ perf_cpu_map__get(other);
+ return other;
+ }
+ if (!other)
+ return orig;
+ if (orig->nr == other->nr &&
+ !memcmp(orig->map, other->map, orig->nr * sizeof(int)))
+ return orig;
+
+ tmp_len = orig->nr + other->nr;
+ tmp_cpus = malloc(tmp_len * sizeof(int));
+ if (!tmp_cpus)
+ return NULL;
+
+ /* Standard merge algorithm from wikipedia */
+ i = j = k = 0;
+ while (i < orig->nr && j < other->nr) {
+ if (orig->map[i] <= other->map[j]) {
+ if (orig->map[i] == other->map[j])
+ j++;
+ tmp_cpus[k++] = orig->map[i++];
+ } else
+ tmp_cpus[k++] = other->map[j++];
+ }
+
+ while (i < orig->nr)
+ tmp_cpus[k++] = orig->map[i++];
+
+ while (j < other->nr)
+ tmp_cpus[k++] = other->map[j++];
+ assert(k <= tmp_len);
+
+ merged = cpu_map__trim_new(k, tmp_cpus);
+ free(tmp_cpus);
+ perf_cpu_map__put(orig);
+ return merged;
+}
diff --git a/tools/perf/lib/evlist.c b/tools/perf/lib/evlist.c
index 205ddbb80bc1..ae9e65aa2491 100644
--- a/tools/perf/lib/evlist.c
+++ b/tools/perf/lib/evlist.c
@@ -54,6 +54,7 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
perf_thread_map__put(evsel->threads);
evsel->threads = perf_thread_map__get(evlist->threads);
+ evlist->all_cpus = perf_cpu_map__merge(evlist->all_cpus, evsel->cpus);
}
static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
diff --git a/tools/perf/lib/include/internal/evlist.h b/tools/perf/lib/include/internal/evlist.h
index a2fbccf1922f..74dc8c3f0b66 100644
--- a/tools/perf/lib/include/internal/evlist.h
+++ b/tools/perf/lib/include/internal/evlist.h
@@ -18,6 +18,7 @@ struct perf_evlist {
int nr_entries;
bool has_user_cpus;
struct perf_cpu_map *cpus;
+ struct perf_cpu_map *all_cpus;
struct perf_thread_map *threads;
int nr_mmaps;
size_t mmap_len;
diff --git a/tools/perf/lib/include/perf/cpumap.h b/tools/perf/lib/include/perf/cpumap.h
index ac9aa497f84a..6a17ad730cbc 100644
--- a/tools/perf/lib/include/perf/cpumap.h
+++ b/tools/perf/lib/include/perf/cpumap.h
@@ -12,6 +12,8 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void);
LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file);
LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
+LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
+ struct perf_cpu_map *other);
LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 7115aa32a51e..82d19a8fcac7 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -259,6 +259,11 @@ static struct test generic_tests[] = {
.desc = "Print cpu map",
.func = test__cpu_map_print,
},
+ {
+ .desc = "Merge cpu map",
+ .func = test__cpu_map_merge,
+ },
+
{
.desc = "Probe SDT events",
.func = test__sdt_event,
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index 8a0d236202b0..4ac56741ac5f 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -120,3 +120,19 @@ int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_un
TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1-10,12-20,22-30,32-40"));
return 0;
}
+
+int test__cpu_map_merge(struct test *test __maybe_unused, int subtest __maybe_unused)
+{
+ struct perf_cpu_map *a = perf_cpu_map__new("4,2,1");
+ struct perf_cpu_map *b = perf_cpu_map__new("4,5,7");
+ struct perf_cpu_map *c = perf_cpu_map__merge(a, b);
+ char buf[100];
+
+ TEST_ASSERT_VAL("failed to merge map: bad nr", c->nr == 5);
+ cpu_map__snprint(c, buf, sizeof(buf));
+ TEST_ASSERT_VAL("failed to merge map: bad result", !strcmp(buf, "1-2,4-5,7"));
+ perf_cpu_map__put(a);
+ perf_cpu_map__put(b);
+ perf_cpu_map__put(c);
+ return 0;
+}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 25aea387e2bf..4f9ae6af78ec 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -98,6 +98,7 @@ int test__event_update(struct test *test, int subtest);
int test__event_times(struct test *test, int subtest);
int test__backward_ring_buffer(struct test *test, int subtest);
int test__cpu_map_print(struct test *test, int subtest);
+int test__cpu_map_merge(struct test *test, int subtest);
int test__sdt_event(struct test *test, int subtest);
int test__is_printable_array(struct test *test, int subtest);
int test__bitmap_print(struct test *test, int subtest);
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 03/23] perf evsel: Add iterator to iterate over events ordered by CPU
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 01/23] perf cpumap: Maintain cpumaps ordered and without dups Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 02/23] perf evlist: Maintain evlist->all_cpus Arnaldo Carvalho de Melo
@ 2019-12-03 13:55 ` Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 04/23] perf evsel: Add functions to close evsel on a CPU Arnaldo Carvalho de Melo
` (20 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:55 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Andi Kleen, Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
Add some common code that is needed to iterate over all events
in CPU order. Used in followon patches
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lore.kernel.org/lkml/20191121001522.180827-6-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/cpumap.h | 1 +
tools/perf/util/evlist.c | 32 ++++++++++++++++++++++++++++++++
tools/perf/util/evlist.h | 8 ++++++++
tools/perf/util/evsel.h | 1 +
4 files changed, 42 insertions(+)
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index 57943f3685f8..3a442f021468 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -63,4 +63,5 @@ int cpu_map__build_map(struct perf_cpu_map *cpus, struct perf_cpu_map **res,
int cpu_map__cpu(struct perf_cpu_map *cpus, int idx);
bool cpu_map__has(struct perf_cpu_map *cpus, int cpu);
+
#endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index fdce590d2278..dae6e846b2f8 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -342,6 +342,38 @@ static int perf_evlist__nr_threads(struct evlist *evlist,
return perf_thread_map__nr(evlist->core.threads);
}
+void evlist__cpu_iter_start(struct evlist *evlist)
+{
+ struct evsel *pos;
+
+ /*
+ * Reset the per evsel cpu_iter. This is needed because
+ * each evsel's cpumap may have a different index space,
+ * and some operations need the index to modify
+ * the FD xyarray (e.g. open, close)
+ */
+ evlist__for_each_entry(evlist, pos)
+ pos->cpu_iter = 0;
+}
+
+bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu)
+{
+ if (ev->cpu_iter >= ev->core.cpus->nr)
+ return true;
+ if (cpu >= 0 && ev->core.cpus->map[ev->cpu_iter] != cpu)
+ return true;
+ return false;
+}
+
+bool evsel__cpu_iter_skip(struct evsel *ev, int cpu)
+{
+ if (!evsel__cpu_iter_skip_no_inc(ev, cpu)) {
+ ev->cpu_iter++;
+ return false;
+ }
+ return true;
+}
+
void evlist__disable(struct evlist *evlist)
{
struct evsel *pos;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 3655b9ebb147..22e2f58eabea 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -334,9 +334,17 @@ void perf_evlist__to_front(struct evlist *evlist,
#define evlist__for_each_entry_safe(evlist, tmp, evsel) \
__evlist__for_each_entry_safe(&(evlist)->core.entries, tmp, evsel)
+#define evlist__for_each_cpu(evlist, index, cpu) \
+ evlist__cpu_iter_start(evlist); \
+ perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus)
+
void perf_evlist__set_tracking_event(struct evlist *evlist,
struct evsel *tracking_evsel);
+void evlist__cpu_iter_start(struct evlist *evlist);
+bool evsel__cpu_iter_skip(struct evsel *ev, int cpu);
+bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu);
+
struct evsel *
perf_evlist__find_evsel_by_str(struct evlist *evlist, const char *str);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index ddc5ee6f6592..b10d5ba21966 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -95,6 +95,7 @@ struct evsel {
bool collect_stat;
bool weak_group;
bool percore;
+ int cpu_iter;
const char *pmu_name;
struct {
perf_evsel__sb_cb_t *cb;
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 04/23] perf evsel: Add functions to close evsel on a CPU
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (2 preceding siblings ...)
2019-12-03 13:55 ` [PATCH 03/23] perf evsel: Add iterator to iterate over events ordered by CPU Arnaldo Carvalho de Melo
@ 2019-12-03 13:55 ` Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 05/23] perf stat: Use affinity for closing file descriptors Arnaldo Carvalho de Melo
` (19 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:55 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Andi Kleen, Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
Refactor the existing all CPU function to use the per CPU close
internally.
Export APIs to close per CPU.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lore.kernel.org/lkml/20191121001522.180827-7-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/lib/evsel.c | 27 +++++++++++++++++++++------
tools/perf/lib/include/perf/evsel.h | 1 +
2 files changed, 22 insertions(+), 6 deletions(-)
diff --git a/tools/perf/lib/evsel.c b/tools/perf/lib/evsel.c
index 5a89857b0381..ea775dacbd2d 100644
--- a/tools/perf/lib/evsel.c
+++ b/tools/perf/lib/evsel.c
@@ -114,16 +114,23 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
return err;
}
+static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu)
+{
+ int thread;
+
+ for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) {
+ if (FD(evsel, cpu, thread) >= 0)
+ close(FD(evsel, cpu, thread));
+ FD(evsel, cpu, thread) = -1;
+ }
+}
+
void perf_evsel__close_fd(struct perf_evsel *evsel)
{
- int cpu, thread;
+ int cpu;
for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++)
- for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) {
- if (FD(evsel, cpu, thread) >= 0)
- close(FD(evsel, cpu, thread));
- FD(evsel, cpu, thread) = -1;
- }
+ perf_evsel__close_fd_cpu(evsel, cpu);
}
void perf_evsel__free_fd(struct perf_evsel *evsel)
@@ -141,6 +148,14 @@ void perf_evsel__close(struct perf_evsel *evsel)
perf_evsel__free_fd(evsel);
}
+void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu)
+{
+ if (evsel->fd == NULL)
+ return;
+
+ perf_evsel__close_fd_cpu(evsel, cpu);
+}
+
int perf_evsel__read_size(struct perf_evsel *evsel)
{
u64 read_format = evsel->attr.read_format;
diff --git a/tools/perf/lib/include/perf/evsel.h b/tools/perf/lib/include/perf/evsel.h
index 557f5815a9c9..e7add554f861 100644
--- a/tools/perf/lib/include/perf/evsel.h
+++ b/tools/perf/lib/include/perf/evsel.h
@@ -26,6 +26,7 @@ LIBPERF_API void perf_evsel__delete(struct perf_evsel *evsel);
LIBPERF_API int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
struct perf_thread_map *threads);
LIBPERF_API void perf_evsel__close(struct perf_evsel *evsel);
+LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu);
LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
struct perf_counts_values *count);
LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel);
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 05/23] perf stat: Use affinity for closing file descriptors
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (3 preceding siblings ...)
2019-12-03 13:55 ` [PATCH 04/23] perf evsel: Add functions to close evsel on a CPU Arnaldo Carvalho de Melo
@ 2019-12-03 13:55 ` Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 06/23] perf stat: Factor out open error handling Arnaldo Carvalho de Melo
` (18 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:55 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Andi Kleen, Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
Closing a perf fd can also trigger an IPI to the target CPU.
Use the same affinity technique as we use for reading/enabling events to
closing to optimize the CPU transitions.
Before on a large test case with 94 CPUs:
% time seconds usecs/call calls errors syscall
------ ----------- ----------- --------- --------- ----------------
32.56 3.085463 50 61483 close
After:
10.54 0.735704 11 61485 close
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lore.kernel.org/lkml/20191121001522.180827-8-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/evlist.c | 31 +++++++++++++++++++++++++++++--
1 file changed, 29 insertions(+), 2 deletions(-)
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index dae6e846b2f8..2e8d38a324be 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -18,6 +18,7 @@
#include "debug.h"
#include "units.h"
#include <internal/lib.h> // page_size
+#include "affinity.h"
#include "../perf.h"
#include "asm/bug.h"
#include "bpf-event.h"
@@ -1169,9 +1170,35 @@ void perf_evlist__set_selected(struct evlist *evlist,
void evlist__close(struct evlist *evlist)
{
struct evsel *evsel;
+ struct affinity affinity;
+ int cpu, i;
- evlist__for_each_entry_reverse(evlist, evsel)
- evsel__close(evsel);
+ /*
+ * With perf record core.cpus is usually NULL.
+ * Use the old method to handle this for now.
+ */
+ if (!evlist->core.cpus) {
+ evlist__for_each_entry_reverse(evlist, evsel)
+ evsel__close(evsel);
+ return;
+ }
+
+ if (affinity__setup(&affinity) < 0)
+ return;
+ evlist__for_each_cpu(evlist, i, cpu) {
+ affinity__set(&affinity, cpu);
+
+ evlist__for_each_entry_reverse(evlist, evsel) {
+ if (evsel__cpu_iter_skip(evsel, cpu))
+ continue;
+ perf_evsel__close_cpu(&evsel->core, evsel->cpu_iter - 1);
+ }
+ }
+ affinity__cleanup(&affinity);
+ evlist__for_each_entry_reverse(evlist, evsel) {
+ perf_evsel__free_fd(&evsel->core);
+ perf_evsel__free_id(&evsel->core);
+ }
}
static int perf_evlist__create_syswide_maps(struct evlist *evlist)
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 06/23] perf stat: Factor out open error handling
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (4 preceding siblings ...)
2019-12-03 13:55 ` [PATCH 05/23] perf stat: Use affinity for closing file descriptors Arnaldo Carvalho de Melo
@ 2019-12-03 13:55 ` Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 07/23] perf stat: Use affinity for opening events Arnaldo Carvalho de Melo
` (17 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:55 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Andi Kleen, Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
Factor out the open error handling into a separate function. This is
useful for followon patches who need to duplicate this.
No behavior change intended.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lore.kernel.org/lkml/20191121001522.180827-9-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-stat.c | 100 +++++++++++++++++++++++---------------
1 file changed, 60 insertions(+), 40 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 0a15253b438c..1d9d7161815e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -420,6 +420,57 @@ static bool is_target_alive(struct target *_target,
return false;
}
+enum counter_recovery {
+ COUNTER_SKIP,
+ COUNTER_RETRY,
+ COUNTER_FATAL,
+};
+
+static enum counter_recovery stat_handle_error(struct evsel *counter)
+{
+ char msg[BUFSIZ];
+ /*
+ * PPC returns ENXIO for HW counters until 2.6.37
+ * (behavior changed with commit b0a873e).
+ */
+ if (errno == EINVAL || errno == ENOSYS ||
+ errno == ENOENT || errno == EOPNOTSUPP ||
+ errno == ENXIO) {
+ if (verbose > 0)
+ ui__warning("%s event is not supported by the kernel.\n",
+ perf_evsel__name(counter));
+ counter->supported = false;
+
+ if ((counter->leader != counter) ||
+ !(counter->leader->core.nr_members > 1))
+ return COUNTER_SKIP;
+ } else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
+ if (verbose > 0)
+ ui__warning("%s\n", msg);
+ return COUNTER_RETRY;
+ } else if (target__has_per_thread(&target) &&
+ evsel_list->core.threads &&
+ evsel_list->core.threads->err_thread != -1) {
+ /*
+ * For global --per-thread case, skip current
+ * error thread.
+ */
+ if (!thread_map__remove(evsel_list->core.threads,
+ evsel_list->core.threads->err_thread)) {
+ evsel_list->core.threads->err_thread = -1;
+ return COUNTER_RETRY;
+ }
+ }
+
+ perf_evsel__open_strerror(counter, &target,
+ errno, msg, sizeof(msg));
+ ui__error("%s\n", msg);
+
+ if (child_pid != -1)
+ kill(child_pid, SIGTERM);
+ return COUNTER_FATAL;
+}
+
static int __run_perf_stat(int argc, const char **argv, int run_idx)
{
int interval = stat_config.interval;
@@ -469,47 +520,16 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
goto try_again;
}
- /*
- * PPC returns ENXIO for HW counters until 2.6.37
- * (behavior changed with commit b0a873e).
- */
- if (errno == EINVAL || errno == ENOSYS ||
- errno == ENOENT || errno == EOPNOTSUPP ||
- errno == ENXIO) {
- if (verbose > 0)
- ui__warning("%s event is not supported by the kernel.\n",
- perf_evsel__name(counter));
- counter->supported = false;
-
- if ((counter->leader != counter) ||
- !(counter->leader->core.nr_members > 1))
- continue;
- } else if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
- if (verbose > 0)
- ui__warning("%s\n", msg);
- goto try_again;
- } else if (target__has_per_thread(&target) &&
- evsel_list->core.threads &&
- evsel_list->core.threads->err_thread != -1) {
- /*
- * For global --per-thread case, skip current
- * error thread.
- */
- if (!thread_map__remove(evsel_list->core.threads,
- evsel_list->core.threads->err_thread)) {
- evsel_list->core.threads->err_thread = -1;
- goto try_again;
- }
+ switch (stat_handle_error(counter)) {
+ case COUNTER_FATAL:
+ return -1;
+ case COUNTER_RETRY:
+ goto try_again;
+ case COUNTER_SKIP:
+ continue;
+ default:
+ break;
}
-
- perf_evsel__open_strerror(counter, &target,
- errno, msg, sizeof(msg));
- ui__error("%s\n", msg);
-
- if (child_pid != -1)
- kill(child_pid, SIGTERM);
-
- return -1;
}
counter->supported = true;
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 07/23] perf stat: Use affinity for opening events
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (5 preceding siblings ...)
2019-12-03 13:55 ` [PATCH 06/23] perf stat: Factor out open error handling Arnaldo Carvalho de Melo
@ 2019-12-03 13:55 ` Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 08/23] perf stat: Use affinity for reading Arnaldo Carvalho de Melo
` (16 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:55 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Andi Kleen, Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
Restructure the event opening in perf stat to cycle through the events
by CPU after setting affinity to that CPU.
This eliminates IPI overhead in the perf API.
We have to loop through the CPU in the outter builtin-stat code instead
of leaving that to low level functions.
It has to change the weak group fallback strategy slightly. Since we
cannot easily undo the opens for other CPUs move the weak group retry to
a separate loop.
Before with a large test case with 94 CPUs:
% time seconds usecs/call calls errors syscall
------ ----------- ----------- --------- --------- ----------------
42.75 4.050910 67 60046 110 perf_event_open
After:
26.86 0.944396 16 58069 110 perf_event_open
(the number changes slightly because the weak group retries
work differently and the test case relies on weak groups)
Committer notes:
Added one of the hunks in a patch provided by Andi after I noticed that
the "event times" 'perf test' entry was segfaulting.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lore.kernel.org/lkml/20191121001522.180827-10-andi@firstfloor.org
Link: http://lore.kernel.org/lkml/20191127232657.GL84886@tassilo.jf.intel.com # Fix
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-record.c | 2 +-
tools/perf/builtin-stat.c | 121 +++++++++++++++++++++++++++------
tools/perf/tests/event-times.c | 4 +-
tools/perf/util/evlist.c | 10 ++-
tools/perf/util/evlist.h | 3 +-
tools/perf/util/evsel.c | 22 ++++--
tools/perf/util/evsel.h | 5 +-
tools/perf/util/stat.c | 5 +-
tools/perf/util/stat.h | 3 +-
9 files changed, 141 insertions(+), 34 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index b5063d3b6fd0..fb19ef63cc35 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -832,7 +832,7 @@ static int record__open(struct record *rec)
if ((errno == EINVAL || errno == EBADF) &&
pos->leader != pos &&
pos->weak_group) {
- pos = perf_evlist__reset_weak_group(evlist, pos);
+ pos = perf_evlist__reset_weak_group(evlist, pos, true);
goto try_again;
}
rc = -errno;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 1d9d7161815e..cf8516e701e2 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -65,6 +65,7 @@
#include "util/target.h"
#include "util/time-utils.h"
#include "util/top.h"
+#include "util/affinity.h"
#include "asm/bug.h"
#include <linux/time64.h>
@@ -440,6 +441,11 @@ static enum counter_recovery stat_handle_error(struct evsel *counter)
ui__warning("%s event is not supported by the kernel.\n",
perf_evsel__name(counter));
counter->supported = false;
+ /*
+ * errored is a sticky flag that means one of the counter's
+ * cpu event had a problem and needs to be reexamined.
+ */
+ counter->errored = true;
if ((counter->leader != counter) ||
!(counter->leader->core.nr_members > 1))
@@ -484,6 +490,9 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
int status = 0;
const bool forks = (argc > 0);
bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false;
+ struct affinity affinity;
+ int i, cpu;
+ bool second_pass = false;
if (interval) {
ts.tv_sec = interval / USEC_PER_MSEC;
@@ -508,30 +517,104 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
if (group)
perf_evlist__set_leader(evsel_list);
- evlist__for_each_entry(evsel_list, counter) {
+ if (affinity__setup(&affinity) < 0)
+ return -1;
+
+ evlist__for_each_cpu (evsel_list, i, cpu) {
+ affinity__set(&affinity, cpu);
+
+ evlist__for_each_entry(evsel_list, counter) {
+ if (evsel__cpu_iter_skip(counter, cpu))
+ continue;
+ if (counter->reset_group || counter->errored)
+ continue;
try_again:
- if (create_perf_stat_counter(counter, &stat_config, &target) < 0) {
-
- /* Weak group failed. Reset the group. */
- if ((errno == EINVAL || errno == EBADF) &&
- counter->leader != counter &&
- counter->weak_group) {
- counter = perf_evlist__reset_weak_group(evsel_list, counter);
- goto try_again;
+ if (create_perf_stat_counter(counter, &stat_config, &target,
+ counter->cpu_iter - 1) < 0) {
+
+ /*
+ * Weak group failed. We cannot just undo this here
+ * because earlier CPUs might be in group mode, and the kernel
+ * doesn't support mixing group and non group reads. Defer
+ * it to later.
+ * Don't close here because we're in the wrong affinity.
+ */
+ if ((errno == EINVAL || errno == EBADF) &&
+ counter->leader != counter &&
+ counter->weak_group) {
+ perf_evlist__reset_weak_group(evsel_list, counter, false);
+ assert(counter->reset_group);
+ second_pass = true;
+ continue;
+ }
+
+ switch (stat_handle_error(counter)) {
+ case COUNTER_FATAL:
+ return -1;
+ case COUNTER_RETRY:
+ goto try_again;
+ case COUNTER_SKIP:
+ continue;
+ default:
+ break;
+ }
+
}
+ counter->supported = true;
+ }
+ }
- switch (stat_handle_error(counter)) {
- case COUNTER_FATAL:
- return -1;
- case COUNTER_RETRY:
- goto try_again;
- case COUNTER_SKIP:
- continue;
- default:
- break;
+ if (second_pass) {
+ /*
+ * Now redo all the weak group after closing them,
+ * and also close errored counters.
+ */
+
+ evlist__for_each_cpu(evsel_list, i, cpu) {
+ affinity__set(&affinity, cpu);
+ /* First close errored or weak retry */
+ evlist__for_each_entry(evsel_list, counter) {
+ if (!counter->reset_group && !counter->errored)
+ continue;
+ if (evsel__cpu_iter_skip_no_inc(counter, cpu))
+ continue;
+ perf_evsel__close_cpu(&counter->core, counter->cpu_iter);
+ }
+ /* Now reopen weak */
+ evlist__for_each_entry(evsel_list, counter) {
+ if (!counter->reset_group && !counter->errored)
+ continue;
+ if (evsel__cpu_iter_skip(counter, cpu))
+ continue;
+ if (!counter->reset_group)
+ continue;
+try_again_reset:
+ pr_debug2("reopening weak %s\n", perf_evsel__name(counter));
+ if (create_perf_stat_counter(counter, &stat_config, &target,
+ counter->cpu_iter - 1) < 0) {
+
+ switch (stat_handle_error(counter)) {
+ case COUNTER_FATAL:
+ return -1;
+ case COUNTER_RETRY:
+ goto try_again_reset;
+ case COUNTER_SKIP:
+ continue;
+ default:
+ break;
+ }
+ }
+ counter->supported = true;
}
}
- counter->supported = true;
+ }
+ affinity__cleanup(&affinity);
+
+ evlist__for_each_entry(evsel_list, counter) {
+ if (!counter->supported) {
+ perf_evsel__free_fd(&counter->core);
+ continue;
+ }
l = strlen(counter->unit);
if (l > stat_config.unit_width)
diff --git a/tools/perf/tests/event-times.c b/tools/perf/tests/event-times.c
index 1ee8704e2284..1e8a9f5c356d 100644
--- a/tools/perf/tests/event-times.c
+++ b/tools/perf/tests/event-times.c
@@ -125,7 +125,7 @@ static int attach__cpu_disabled(struct evlist *evlist)
evsel->core.attr.disabled = 1;
- err = perf_evsel__open_per_cpu(evsel, cpus);
+ err = perf_evsel__open_per_cpu(evsel, cpus, -1);
if (err) {
if (err == -EACCES)
return TEST_SKIP;
@@ -152,7 +152,7 @@ static int attach__cpu_enabled(struct evlist *evlist)
return -1;
}
- err = perf_evsel__open_per_cpu(evsel, cpus);
+ err = perf_evsel__open_per_cpu(evsel, cpus, -1);
if (err == -EACCES)
return TEST_SKIP;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 2e8d38a324be..096a4ea65b1b 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1636,7 +1636,8 @@ void perf_evlist__force_leader(struct evlist *evlist)
}
struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list,
- struct evsel *evsel)
+ struct evsel *evsel,
+ bool close)
{
struct evsel *c2, *leader;
bool is_open = true;
@@ -1653,10 +1654,15 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list,
if (c2 == evsel)
is_open = false;
if (c2->leader == leader) {
- if (is_open)
+ if (is_open && close)
perf_evsel__close(&c2->core);
c2->leader = c2;
c2->core.nr_members = 0;
+ /*
+ * Set this for all former members of the group
+ * to indicate they get reopened.
+ */
+ c2->reset_group = true;
}
}
return leader;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 22e2f58eabea..f5bd5c386df1 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -356,5 +356,6 @@ bool perf_evlist__exclude_kernel(struct evlist *evlist);
void perf_evlist__force_leader(struct evlist *evlist);
struct evsel *perf_evlist__reset_weak_group(struct evlist *evlist,
- struct evsel *evsel);
+ struct evsel *evsel,
+ bool close);
#endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f4dea055b080..aa180d1df50f 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1587,8 +1587,9 @@ static int perf_event_open(struct evsel *evsel,
return fd;
}
-int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
- struct perf_thread_map *threads)
+static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
+ struct perf_thread_map *threads,
+ int start_cpu, int end_cpu)
{
int cpu, thread, nthreads;
unsigned long flags = PERF_FLAG_FD_CLOEXEC;
@@ -1665,7 +1666,7 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
display_attr(&evsel->core.attr);
- for (cpu = 0; cpu < cpus->nr; cpu++) {
+ for (cpu = start_cpu; cpu < end_cpu; cpu++) {
for (thread = 0; thread < nthreads; thread++) {
int fd, group_fd;
@@ -1843,6 +1844,12 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
return err;
}
+int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
+ struct perf_thread_map *threads)
+{
+ return evsel__open_cpu(evsel, cpus, threads, 0, cpus ? cpus->nr : 1);
+}
+
void evsel__close(struct evsel *evsel)
{
perf_evsel__close(&evsel->core);
@@ -1850,9 +1857,14 @@ void evsel__close(struct evsel *evsel)
}
int perf_evsel__open_per_cpu(struct evsel *evsel,
- struct perf_cpu_map *cpus)
+ struct perf_cpu_map *cpus,
+ int cpu)
{
- return evsel__open(evsel, cpus, NULL);
+ if (cpu == -1)
+ return evsel__open_cpu(evsel, cpus, NULL, 0,
+ cpus ? cpus->nr : 1);
+
+ return evsel__open_cpu(evsel, cpus, NULL, cpu, cpu + 1);
}
int perf_evsel__open_per_thread(struct evsel *evsel,
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index b10d5ba21966..ca82a93960cd 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -94,6 +94,8 @@ struct evsel {
struct evsel *metric_leader;
bool collect_stat;
bool weak_group;
+ bool reset_group;
+ bool errored;
bool percore;
int cpu_iter;
const char *pmu_name;
@@ -223,7 +225,8 @@ int evsel__enable(struct evsel *evsel);
int evsel__disable(struct evsel *evsel);
int perf_evsel__open_per_cpu(struct evsel *evsel,
- struct perf_cpu_map *cpus);
+ struct perf_cpu_map *cpus,
+ int cpu);
int perf_evsel__open_per_thread(struct evsel *evsel,
struct perf_thread_map *threads);
int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 332cb730785b..5f26137b8d60 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -464,7 +464,8 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
int create_perf_stat_counter(struct evsel *evsel,
struct perf_stat_config *config,
- struct target *target)
+ struct target *target,
+ int cpu)
{
struct perf_event_attr *attr = &evsel->core.attr;
struct evsel *leader = evsel->leader;
@@ -518,7 +519,7 @@ int create_perf_stat_counter(struct evsel *evsel,
}
if (target__has_cpu(target) && !target__has_per_thread(target))
- return perf_evsel__open_per_cpu(evsel, evsel__cpus(evsel));
+ return perf_evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu);
return perf_evsel__open_per_thread(evsel, evsel->core.threads);
}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index bfa9aaf36ce6..fb990efa54a8 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -214,7 +214,8 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
int create_perf_stat_counter(struct evsel *evsel,
struct perf_stat_config *config,
- struct target *target);
+ struct target *target,
+ int cpu);
void
perf_evlist__print_counters(struct evlist *evlist,
struct perf_stat_config *config,
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 08/23] perf stat: Use affinity for reading
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (6 preceding siblings ...)
2019-12-03 13:55 ` [PATCH 07/23] perf stat: Use affinity for opening events Arnaldo Carvalho de Melo
@ 2019-12-03 13:55 ` Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 09/23] perf evsel: Add functions to enable/disable for a specific CPU Arnaldo Carvalho de Melo
` (15 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:55 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Andi Kleen, Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
Restructure event reading to use affinity to minimize the number of IPIs
needed.
Before on a large test case with 94 CPUs:
% time seconds usecs/call calls errors syscall
------ ----------- ----------- --------- --------- ----------------
3.16 0.106079 4 22082 read
After:
3.43 0.081295 3 22082 read
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lore.kernel.org/lkml/20191121001522.180827-11-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-stat.c | 97 ++++++++++++++++++++++-----------------
tools/perf/util/evsel.h | 1 +
2 files changed, 57 insertions(+), 41 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index cf8516e701e2..a098c2ebf4ea 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -266,15 +266,10 @@ static int read_single_counter(struct evsel *counter, int cpu,
* Read out the results of a single counter:
* do not aggregate counts across CPUs in system-wide mode
*/
-static int read_counter(struct evsel *counter, struct timespec *rs)
+static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
{
int nthreads = perf_thread_map__nr(evsel_list->core.threads);
- int ncpus, cpu, thread;
-
- if (target__has_cpu(&target) && !target__has_per_thread(&target))
- ncpus = perf_evsel__nr_cpus(counter);
- else
- ncpus = 1;
+ int thread;
if (!counter->supported)
return -ENOENT;
@@ -283,40 +278,38 @@ static int read_counter(struct evsel *counter, struct timespec *rs)
nthreads = 1;
for (thread = 0; thread < nthreads; thread++) {
- for (cpu = 0; cpu < ncpus; cpu++) {
- struct perf_counts_values *count;
-
- count = perf_counts(counter->counts, cpu, thread);
-
- /*
- * The leader's group read loads data into its group members
- * (via perf_evsel__read_counter) and sets threir count->loaded.
- */
- if (!perf_counts__is_loaded(counter->counts, cpu, thread) &&
- read_single_counter(counter, cpu, thread, rs)) {
- counter->counts->scaled = -1;
- perf_counts(counter->counts, cpu, thread)->ena = 0;
- perf_counts(counter->counts, cpu, thread)->run = 0;
- return -1;
- }
+ struct perf_counts_values *count;
- perf_counts__set_loaded(counter->counts, cpu, thread, false);
+ count = perf_counts(counter->counts, cpu, thread);
- if (STAT_RECORD) {
- if (perf_evsel__write_stat_event(counter, cpu, thread, count)) {
- pr_err("failed to write stat event\n");
- return -1;
- }
- }
+ /*
+ * The leader's group read loads data into its group members
+ * (via perf_evsel__read_counter()) and sets their count->loaded.
+ */
+ if (!perf_counts__is_loaded(counter->counts, cpu, thread) &&
+ read_single_counter(counter, cpu, thread, rs)) {
+ counter->counts->scaled = -1;
+ perf_counts(counter->counts, cpu, thread)->ena = 0;
+ perf_counts(counter->counts, cpu, thread)->run = 0;
+ return -1;
+ }
+
+ perf_counts__set_loaded(counter->counts, cpu, thread, false);
- if (verbose > 1) {
- fprintf(stat_config.output,
- "%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
- perf_evsel__name(counter),
- cpu,
- count->val, count->ena, count->run);
+ if (STAT_RECORD) {
+ if (perf_evsel__write_stat_event(counter, cpu, thread, count)) {
+ pr_err("failed to write stat event\n");
+ return -1;
}
}
+
+ if (verbose > 1) {
+ fprintf(stat_config.output,
+ "%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
+ perf_evsel__name(counter),
+ cpu,
+ count->val, count->ena, count->run);
+ }
}
return 0;
@@ -325,15 +318,37 @@ static int read_counter(struct evsel *counter, struct timespec *rs)
static void read_counters(struct timespec *rs)
{
struct evsel *counter;
- int ret;
+ struct affinity affinity;
+ int i, ncpus, cpu;
+
+ if (affinity__setup(&affinity) < 0)
+ return;
+
+ ncpus = perf_cpu_map__nr(evsel_list->core.all_cpus);
+ if (!target__has_cpu(&target) || target__has_per_thread(&target))
+ ncpus = 1;
+ evlist__for_each_cpu(evsel_list, i, cpu) {
+ if (i >= ncpus)
+ break;
+ affinity__set(&affinity, cpu);
+
+ evlist__for_each_entry(evsel_list, counter) {
+ if (evsel__cpu_iter_skip(counter, cpu))
+ continue;
+ if (!counter->err) {
+ counter->err = read_counter_cpu(counter, rs,
+ counter->cpu_iter - 1);
+ }
+ }
+ }
+ affinity__cleanup(&affinity);
evlist__for_each_entry(evsel_list, counter) {
- ret = read_counter(counter, rs);
- if (ret)
+ if (counter->err)
pr_debug("failed to read counter %s\n", counter->name);
-
- if (ret == 0 && perf_stat_process_counter(&stat_config, counter))
+ if (counter->err == 0 && perf_stat_process_counter(&stat_config, counter))
pr_warning("failed to process counter %s\n", counter->name);
+ counter->err = 0;
}
}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index ca82a93960cd..c8af4bc23f8f 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -86,6 +86,7 @@ struct evsel {
struct list_head config_terms;
struct bpf_object *bpf_obj;
int bpf_fd;
+ int err;
bool auto_merge_stats;
bool merged_stat;
const char * metric_expr;
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 09/23] perf evsel: Add functions to enable/disable for a specific CPU
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (7 preceding siblings ...)
2019-12-03 13:55 ` [PATCH 08/23] perf stat: Use affinity for reading Arnaldo Carvalho de Melo
@ 2019-12-03 13:55 ` Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 10/23] perf stat: Use affinity for enabling/disabling events Arnaldo Carvalho de Melo
` (14 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:55 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Andi Kleen, Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
Refactor the existing functions to use these functions internally.
Used in the next patch.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lore.kernel.org/lkml/20191121001522.180827-12-andi@firstfloor.org
Link: http://lore.kernel.org/lkml/20191127232657.GL84886@tassilo.jf.intel.com # Fix
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/lib/evsel.c | 49 +++++++++++++++++++++--------
tools/perf/lib/include/perf/evsel.h | 2 ++
tools/perf/util/evsel.c | 13 +++++++-
tools/perf/util/evsel.h | 2 ++
4 files changed, 52 insertions(+), 14 deletions(-)
diff --git a/tools/perf/lib/evsel.c b/tools/perf/lib/evsel.c
index ea775dacbd2d..4dc06289f4c7 100644
--- a/tools/perf/lib/evsel.c
+++ b/tools/perf/lib/evsel.c
@@ -198,38 +198,61 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
}
static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
- int ioc, void *arg)
+ int ioc, void *arg,
+ int cpu)
{
- int cpu, thread;
+ int thread;
- for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
- for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
- int fd = FD(evsel, cpu, thread),
- err = ioctl(fd, ioc, arg);
+ for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
+ int fd = FD(evsel, cpu, thread),
+ err = ioctl(fd, ioc, arg);
- if (err)
- return err;
- }
+ if (err)
+ return err;
}
return 0;
}
+int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu)
+{
+ return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu);
+}
+
int perf_evsel__enable(struct perf_evsel *evsel)
{
- return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, 0);
+ int i;
+ int err = 0;
+
+ for (i = 0; i < xyarray__max_x(evsel->fd) && !err; i++)
+ err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, i);
+ return err;
+}
+
+int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu)
+{
+ return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu);
}
int perf_evsel__disable(struct perf_evsel *evsel)
{
- return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, 0);
+ int i;
+ int err = 0;
+
+ for (i = 0; i < xyarray__max_x(evsel->fd) && !err; i++)
+ err = perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, i);
+ return err;
}
int perf_evsel__apply_filter(struct perf_evsel *evsel, const char *filter)
{
- return perf_evsel__run_ioctl(evsel,
+ int err = 0, i;
+
+ for (i = 0; i < evsel->cpus->nr && !err; i++)
+ err = perf_evsel__run_ioctl(evsel,
PERF_EVENT_IOC_SET_FILTER,
- (void *)filter);
+ (void *)filter, i);
+ return err;
}
struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
diff --git a/tools/perf/lib/include/perf/evsel.h b/tools/perf/lib/include/perf/evsel.h
index e7add554f861..c82ec39a4ad0 100644
--- a/tools/perf/lib/include/perf/evsel.h
+++ b/tools/perf/lib/include/perf/evsel.h
@@ -30,7 +30,9 @@ LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu);
LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
struct perf_counts_values *count);
LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel);
+LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu);
LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel);
+LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu);
LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel);
LIBPERF_API struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel);
LIBPERF_API struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index aa180d1df50f..a69e64236120 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1223,16 +1223,27 @@ int perf_evsel__append_addr_filter(struct evsel *evsel, const char *filter)
return perf_evsel__append_filter(evsel, "%s,%s", filter);
}
+/* Caller has to clear disabled after going through all CPUs. */
+int evsel__enable_cpu(struct evsel *evsel, int cpu)
+{
+ return perf_evsel__enable_cpu(&evsel->core, cpu);
+}
+
int evsel__enable(struct evsel *evsel)
{
int err = perf_evsel__enable(&evsel->core);
if (!err)
evsel->disabled = false;
-
return err;
}
+/* Caller has to set disabled after going through all CPUs. */
+int evsel__disable_cpu(struct evsel *evsel, int cpu)
+{
+ return perf_evsel__disable_cpu(&evsel->core, cpu);
+}
+
int evsel__disable(struct evsel *evsel)
{
int err = perf_evsel__disable(&evsel->core);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index c8af4bc23f8f..dc14f4a823cd 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -222,8 +222,10 @@ int perf_evsel__set_filter(struct evsel *evsel, const char *filter);
int perf_evsel__append_tp_filter(struct evsel *evsel, const char *filter);
int perf_evsel__append_addr_filter(struct evsel *evsel,
const char *filter);
+int evsel__enable_cpu(struct evsel *evsel, int cpu);
int evsel__enable(struct evsel *evsel);
int evsel__disable(struct evsel *evsel);
+int evsel__disable_cpu(struct evsel *evsel, int cpu);
int perf_evsel__open_per_cpu(struct evsel *evsel,
struct perf_cpu_map *cpus,
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 10/23] perf stat: Use affinity for enabling/disabling events
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (8 preceding siblings ...)
2019-12-03 13:55 ` [PATCH 09/23] perf evsel: Add functions to enable/disable for a specific CPU Arnaldo Carvalho de Melo
@ 2019-12-03 13:55 ` Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 11/23] perf jit: Move test functionality in to a test Arnaldo Carvalho de Melo
` (13 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:55 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Andi Kleen, Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
Restructure event enabling/disabling to use affinity, which
minimizes the number of IPIs needed.
Before on a large test case with 94 CPUs:
% time seconds usecs/call calls errors syscall
------ ----------- ----------- --------- --------- ----------------
54.65 1.899986 22 84812 660 ioctl
after:
39.21 0.930451 10 84796 644 ioctl
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lore.kernel.org/lkml/20191121001522.180827-13-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/evlist.c | 40 +++++++++++++++++++++++++++++++++++++---
1 file changed, 37 insertions(+), 3 deletions(-)
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 096a4ea65b1b..1548237b6558 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -378,11 +378,28 @@ bool evsel__cpu_iter_skip(struct evsel *ev, int cpu)
void evlist__disable(struct evlist *evlist)
{
struct evsel *pos;
+ struct affinity affinity;
+ int cpu, i;
+
+ if (affinity__setup(&affinity) < 0)
+ return;
+
+ evlist__for_each_cpu(evlist, i, cpu) {
+ affinity__set(&affinity, cpu);
+ evlist__for_each_entry(evlist, pos) {
+ if (evsel__cpu_iter_skip(pos, cpu))
+ continue;
+ if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->core.fd)
+ continue;
+ evsel__disable_cpu(pos, pos->cpu_iter - 1);
+ }
+ }
+ affinity__cleanup(&affinity);
evlist__for_each_entry(evlist, pos) {
- if (pos->disabled || !perf_evsel__is_group_leader(pos) || !pos->core.fd)
+ if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
continue;
- evsel__disable(pos);
+ pos->disabled = true;
}
evlist->enabled = false;
@@ -391,11 +408,28 @@ void evlist__disable(struct evlist *evlist)
void evlist__enable(struct evlist *evlist)
{
struct evsel *pos;
+ struct affinity affinity;
+ int cpu, i;
+ if (affinity__setup(&affinity) < 0)
+ return;
+
+ evlist__for_each_cpu(evlist, i, cpu) {
+ affinity__set(&affinity, cpu);
+
+ evlist__for_each_entry(evlist, pos) {
+ if (evsel__cpu_iter_skip(pos, cpu))
+ continue;
+ if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
+ continue;
+ evsel__enable_cpu(pos, pos->cpu_iter - 1);
+ }
+ }
+ affinity__cleanup(&affinity);
evlist__for_each_entry(evlist, pos) {
if (!perf_evsel__is_group_leader(pos) || !pos->core.fd)
continue;
- evsel__enable(pos);
+ pos->disabled = false;
}
evlist->enabled = true;
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 11/23] perf jit: Move test functionality in to a test
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (9 preceding siblings ...)
2019-12-03 13:55 ` [PATCH 10/23] perf stat: Use affinity for enabling/disabling events Arnaldo Carvalho de Melo
@ 2019-12-03 13:55 ` Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 12/23] perf machine: Fill map_symbol->maps in append_inlines() to fix segfault Arnaldo Carvalho de Melo
` (12 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:55 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Ian Rogers, Arnaldo Carvalho de Melo,
Adrian Hunter, Alexander Shishkin, Alexios Zavras,
Allison Randal, Florian Fainelli, Greg Kroah-Hartman, Jiri Olsa,
Kate Stewart, Leo Yan, Mark Rutland, Michael Petlan,
Peter Zijlstra, Song Liu, Stephane Eranian
From: Ian Rogers <irogers@google.com>
Adds a test for minimal jit_write_elf functionality.
Committer testing:
# perf test jit
61: Test jit_write_elf : Ok
#
# perf test -v jit
61: Test jit_write_elf :
--- start ---
test child forked, pid 10460
Writing jit code to: /tmp/perf-test-KqxURR
test child finished with 0
---- end ----
Test jit_write_elf: Ok
#
Committer notes:
Fix up the case where HAVE_JITDUMP is no defined.
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexios Zavras <alexios.zavras@intel.com>
Cc: Allison Randal <allison@lohutok.net>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kate Stewart <kstewart@linuxfoundation.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lore.kernel.org/lkml/20191126235913.41855-1-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/tests/Build | 1 +
tools/perf/tests/builtin-test.c | 4 +++
tools/perf/tests/genelf.c | 51 +++++++++++++++++++++++++++++++++
tools/perf/tests/tests.h | 1 +
tools/perf/util/genelf.c | 46 -----------------------------
5 files changed, 57 insertions(+), 46 deletions(-)
create mode 100644 tools/perf/tests/genelf.c
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index a3c595fba943..1692529639b0 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -54,6 +54,7 @@ perf-y += unit_number__scnprintf.o
perf-y += mem2node.o
perf-y += maps.o
perf-y += time-utils-test.o
+perf-y += genelf.o
$(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
$(call rule_mkdir)
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 82d19a8fcac7..5f05db75cdd8 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -301,6 +301,10 @@ static struct test generic_tests[] = {
.desc = "time utils",
.func = test__time_utils,
},
+ {
+ .desc = "Test jit_write_elf",
+ .func = test__jit_write_elf,
+ },
{
.desc = "maps__merge_in",
.func = test__maps__merge_in,
diff --git a/tools/perf/tests/genelf.c b/tools/perf/tests/genelf.c
new file mode 100644
index 000000000000..f797f9823e89
--- /dev/null
+++ b/tools/perf/tests/genelf.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <limits.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/compiler.h>
+
+#include "debug.h"
+#include "tests.h"
+
+#ifdef HAVE_JITDUMP
+#include <libelf.h>
+#include "../util/genelf.h"
+#endif
+
+#define TEMPL "/tmp/perf-test-XXXXXX"
+
+int test__jit_write_elf(struct test *test __maybe_unused,
+ int subtest __maybe_unused)
+{
+#ifdef HAVE_JITDUMP
+ static unsigned char x86_code[] = {
+ 0xBB, 0x2A, 0x00, 0x00, 0x00, /* movl $42, %ebx */
+ 0xB8, 0x01, 0x00, 0x00, 0x00, /* movl $1, %eax */
+ 0xCD, 0x80 /* int $0x80 */
+ };
+ char path[PATH_MAX];
+ int fd, ret;
+
+ strcpy(path, TEMPL);
+
+ fd = mkstemp(path);
+ if (fd < 0) {
+ perror("mkstemp failed");
+ return TEST_FAIL;
+ }
+
+ pr_info("Writing jit code to: %s\n", path);
+
+ ret = jit_write_elf(fd, 0, "main", x86_code, sizeof(x86_code),
+ NULL, 0, NULL, 0, 0);
+ close(fd);
+
+ unlink(path);
+
+ return ret ? TEST_FAIL : 0;
+#else
+ return TEST_SKIP;
+#endif
+}
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 4f9ae6af78ec..9a160fef47c9 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -110,6 +110,7 @@ int test__unit_number__scnprint(struct test *test, int subtest);
int test__mem2node(struct test *t, int subtest);
int test__maps__merge_in(struct test *t, int subtest);
int test__time_utils(struct test *t, int subtest);
+int test__jit_write_elf(struct test *test, int subtest);
bool test__bp_signal_is_supported(void);
bool test__bp_account_is_supported(void);
diff --git a/tools/perf/util/genelf.c b/tools/perf/util/genelf.c
index f9f18b8b1df9..aed49806a09b 100644
--- a/tools/perf/util/genelf.c
+++ b/tools/perf/util/genelf.c
@@ -8,15 +8,12 @@
*/
#include <sys/types.h>
-#include <stdio.h>
-#include <getopt.h>
#include <stddef.h>
#include <libelf.h>
#include <string.h>
#include <stdlib.h>
#include <unistd.h>
#include <inttypes.h>
-#include <limits.h>
#include <fcntl.h>
#include <err.h>
#ifdef HAVE_DWARF_SUPPORT
@@ -31,8 +28,6 @@
#define NT_GNU_BUILD_ID 3
#endif
-#define JVMTI
-
#define BUILD_ID_URANDOM /* different uuid for each run */
#ifdef HAVE_LIBCRYPTO
@@ -511,44 +506,3 @@ jit_write_elf(int fd, uint64_t load_addr, const char *sym,
return retval;
}
-
-#ifndef JVMTI
-
-static unsigned char x86_code[] = {
- 0xBB, 0x2A, 0x00, 0x00, 0x00, /* movl $42, %ebx */
- 0xB8, 0x01, 0x00, 0x00, 0x00, /* movl $1, %eax */
- 0xCD, 0x80 /* int $0x80 */
-};
-
-static struct options options;
-
-int main(int argc, char **argv)
-{
- int c, fd, ret;
-
- while ((c = getopt(argc, argv, "o:h")) != -1) {
- switch (c) {
- case 'o':
- options.output = optarg;
- break;
- case 'h':
- printf("Usage: genelf -o output_file [-h]\n");
- return 0;
- default:
- errx(1, "unknown option");
- }
- }
-
- fd = open(options.output, O_CREAT|O_TRUNC|O_RDWR, 0666);
- if (fd == -1)
- err(1, "cannot create file %s", options.output);
-
- ret = jit_write_elf(fd, "main", x86_code, sizeof(x86_code));
- close(fd);
-
- if (ret != 0)
- unlink(options.output);
-
- return ret;
-}
-#endif
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 12/23] perf machine: Fill map_symbol->maps in append_inlines() to fix segfault
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (10 preceding siblings ...)
2019-12-03 13:55 ` [PATCH 11/23] perf jit: Move test functionality in to a test Arnaldo Carvalho de Melo
@ 2019-12-03 13:55 ` Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 13/23] perf bench: Update the copies of x86's mem{cpy,set}_64.S Arnaldo Carvalho de Melo
` (11 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:55 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Arnaldo Carvalho de Melo, Adrian Hunter
From: Arnaldo Carvalho de Melo <acme@redhat.com>
I forgot to fill in the map_symbol->maps field in append_inlines() which
then makes code down the line segfault when trying to deref it.
It doesn't make any sense to have an addr_location with its 'map' member
not NULL while its 'maps' is NULL, after all al->maps is where al->map
is in.
It is done that way so that we don't have to have in each 'struct map' a
pointer to the 'struct maps' it is in, as we had in the past when we
would have 'map->mg', before 'struct maps' was combined with 'struct
map_groups', because there was always a one-to-one relationship for
these structs.
This fixes a segfault when processing DWARF callgraphs in 'perf report'.
Reported-by: Jiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Fixes: 08f6680e627e ("perf tools: Add a 'struct map_groups' pointer to 'struct map_symbol'")
Link: http://lore.kernel.org/lkml/20191129160631.GD26963@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/machine.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 416d174d223c..c8c5410315e8 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2446,6 +2446,7 @@ static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms
list_for_each_entry(ilist, &inline_node->val, list) {
struct map_symbol ilist_ms = {
+ .maps = ms->maps,
.map = map,
.sym = ilist->symbol,
};
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 13/23] perf bench: Update the copies of x86's mem{cpy,set}_64.S
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (11 preceding siblings ...)
2019-12-03 13:55 ` [PATCH 12/23] perf machine: Fill map_symbol->maps in append_inlines() to fix segfault Arnaldo Carvalho de Melo
@ 2019-12-03 13:55 ` Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 14/23] tools arch x86: Sync the msr-index.h copy with the kernel sources Arnaldo Carvalho de Melo
` (10 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:55 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Arnaldo Carvalho de Melo, Adrian Hunter,
Borislav Petkov, Jiri Slaby
From: Arnaldo Carvalho de Melo <acme@redhat.com>
And update linux/linkage.h, which requires in turn that we make these
files switch from ENTRY()/ENDPROC() to SYM_FUNC_START()/SYM_FUNC_END():
tools/perf/arch/arm64/tests/regs_load.S
tools/perf/arch/arm/tests/regs_load.S
tools/perf/arch/powerpc/tests/regs_load.S
tools/perf/arch/x86/tests/regs_load.S
We also need to switch SYM_FUNC_START_LOCAL() to SYM_FUNC_START() for
the functions used directly by 'perf bench', and update
tools/perf/check_headers.sh to ignore those changes when checking if the
kernel original files drifted from the copies we carry.
This is to get the changes from:
6dcc5627f6ae ("x86/asm: Change all ENTRY+ENDPROC to SYM_FUNC_*")
ef1e03152cb0 ("x86/asm: Make some functions local")
e9b9d020c487 ("x86/asm: Annotate aliases")
And address these tools/perf build warnings:
Warning: Kernel ABI header at 'tools/arch/x86/lib/memcpy_64.S' differs from latest version at 'arch/x86/lib/memcpy_64.S'
diff -u tools/arch/x86/lib/memcpy_64.S arch/x86/lib/memcpy_64.S
Warning: Kernel ABI header at 'tools/arch/x86/lib/memset_64.S' differs from latest version at 'arch/x86/lib/memset_64.S'
diff -u tools/arch/x86/lib/memset_64.S arch/x86/lib/memset_64.S
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-tay3l8x8k11p7y3qcpqh9qh5@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/arch/x86/lib/memcpy_64.S | 20 +++---
tools/arch/x86/lib/memset_64.S | 16 ++---
tools/perf/arch/arm/tests/regs_load.S | 4 +-
tools/perf/arch/arm64/tests/regs_load.S | 4 +-
tools/perf/arch/x86/tests/regs_load.S | 8 +--
| 4 +-
tools/perf/util/include/linux/linkage.h | 89 ++++++++++++++++++++++++-
7 files changed, 114 insertions(+), 31 deletions(-)
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 92748660ba51..df767afc690f 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -28,8 +28,8 @@
* Output:
* rax original destination
*/
-ENTRY(__memcpy)
-ENTRY(memcpy)
+SYM_FUNC_START_ALIAS(__memcpy)
+SYM_FUNC_START_LOCAL(memcpy)
ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
"jmp memcpy_erms", X86_FEATURE_ERMS
@@ -41,8 +41,8 @@ ENTRY(memcpy)
movl %edx, %ecx
rep movsb
ret
-ENDPROC(memcpy)
-ENDPROC(__memcpy)
+SYM_FUNC_END(memcpy)
+SYM_FUNC_END_ALIAS(__memcpy)
EXPORT_SYMBOL(memcpy)
EXPORT_SYMBOL(__memcpy)
@@ -50,14 +50,14 @@ EXPORT_SYMBOL(__memcpy)
* memcpy_erms() - enhanced fast string memcpy. This is faster and
* simpler than memcpy. Use memcpy_erms when possible.
*/
-ENTRY(memcpy_erms)
+SYM_FUNC_START(memcpy_erms)
movq %rdi, %rax
movq %rdx, %rcx
rep movsb
ret
-ENDPROC(memcpy_erms)
+SYM_FUNC_END(memcpy_erms)
-ENTRY(memcpy_orig)
+SYM_FUNC_START(memcpy_orig)
movq %rdi, %rax
cmpq $0x20, %rdx
@@ -182,7 +182,7 @@ ENTRY(memcpy_orig)
.Lend:
retq
-ENDPROC(memcpy_orig)
+SYM_FUNC_END(memcpy_orig)
#ifndef CONFIG_UML
@@ -193,7 +193,7 @@ MCSAFE_TEST_CTL
* Note that we only catch machine checks when reading the source addresses.
* Writes to target are posted and don't generate machine checks.
*/
-ENTRY(__memcpy_mcsafe)
+SYM_FUNC_START(__memcpy_mcsafe)
cmpl $8, %edx
/* Less than 8 bytes? Go to byte copy loop */
jb .L_no_whole_words
@@ -260,7 +260,7 @@ ENTRY(__memcpy_mcsafe)
xorl %eax, %eax
.L_done:
ret
-ENDPROC(__memcpy_mcsafe)
+SYM_FUNC_END(__memcpy_mcsafe)
EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
.section .fixup, "ax"
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index f8f3dc0a6690..fd5d25a474b7 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -18,8 +18,8 @@
*
* rax original destination
*/
-ENTRY(memset)
-ENTRY(__memset)
+SYM_FUNC_START_ALIAS(memset)
+SYM_FUNC_START(__memset)
/*
* Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
* to use it when possible. If not available, use fast string instructions.
@@ -42,8 +42,8 @@ ENTRY(__memset)
rep stosb
movq %r9,%rax
ret
-ENDPROC(memset)
-ENDPROC(__memset)
+SYM_FUNC_END(__memset)
+SYM_FUNC_END_ALIAS(memset)
/*
* ISO C memset - set a memory block to a byte value. This function uses
@@ -56,16 +56,16 @@ ENDPROC(__memset)
*
* rax original destination
*/
-ENTRY(memset_erms)
+SYM_FUNC_START(memset_erms)
movq %rdi,%r9
movb %sil,%al
movq %rdx,%rcx
rep stosb
movq %r9,%rax
ret
-ENDPROC(memset_erms)
+SYM_FUNC_END(memset_erms)
-ENTRY(memset_orig)
+SYM_FUNC_START(memset_orig)
movq %rdi,%r10
/* expand byte value */
@@ -136,4 +136,4 @@ ENTRY(memset_orig)
subq %r8,%rdx
jmp .Lafter_bad_alignment
.Lfinal:
-ENDPROC(memset_orig)
+SYM_FUNC_END(memset_orig)
diff --git a/tools/perf/arch/arm/tests/regs_load.S b/tools/perf/arch/arm/tests/regs_load.S
index 6e2495cc4517..4284307d7822 100644
--- a/tools/perf/arch/arm/tests/regs_load.S
+++ b/tools/perf/arch/arm/tests/regs_load.S
@@ -37,7 +37,7 @@
.text
.type perf_regs_load,%function
-ENTRY(perf_regs_load)
+SYM_FUNC_START(perf_regs_load)
str r0, [r0, #R0]
str r1, [r0, #R1]
str r2, [r0, #R2]
@@ -56,4 +56,4 @@ ENTRY(perf_regs_load)
str lr, [r0, #PC] // store pc as lr in order to skip the call
// to this function
mov pc, lr
-ENDPROC(perf_regs_load)
+SYM_FUNC_END(perf_regs_load)
diff --git a/tools/perf/arch/arm64/tests/regs_load.S b/tools/perf/arch/arm64/tests/regs_load.S
index 07042511dca9..d49de40b6818 100644
--- a/tools/perf/arch/arm64/tests/regs_load.S
+++ b/tools/perf/arch/arm64/tests/regs_load.S
@@ -7,7 +7,7 @@
#define LDR_REG(r) ldr x##r, [x0, 8 * r]
#define SP (8 * 31)
#define PC (8 * 32)
-ENTRY(perf_regs_load)
+SYM_FUNC_START(perf_regs_load)
STR_REG(0)
STR_REG(1)
STR_REG(2)
@@ -44,4 +44,4 @@ ENTRY(perf_regs_load)
str x30, [x0, #PC]
LDR_REG(1)
ret
-ENDPROC(perf_regs_load)
+SYM_FUNC_END(perf_regs_load)
diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S
index bbe5a0d16e51..80f14f52e3f6 100644
--- a/tools/perf/arch/x86/tests/regs_load.S
+++ b/tools/perf/arch/x86/tests/regs_load.S
@@ -28,7 +28,7 @@
.text
#ifdef HAVE_ARCH_X86_64_SUPPORT
-ENTRY(perf_regs_load)
+SYM_FUNC_START(perf_regs_load)
movq %rax, AX(%rdi)
movq %rbx, BX(%rdi)
movq %rcx, CX(%rdi)
@@ -60,9 +60,9 @@ ENTRY(perf_regs_load)
movq %r14, R14(%rdi)
movq %r15, R15(%rdi)
ret
-ENDPROC(perf_regs_load)
+SYM_FUNC_END(perf_regs_load)
#else
-ENTRY(perf_regs_load)
+SYM_FUNC_START(perf_regs_load)
push %edi
movl 8(%esp), %edi
movl %eax, AX(%edi)
@@ -88,7 +88,7 @@ ENTRY(perf_regs_load)
movl $0, FS(%edi)
movl $0, GS(%edi)
ret
-ENDPROC(perf_regs_load)
+SYM_FUNC_END(perf_regs_load)
#endif
/*
--git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index a1dc16724352..68039a96c1dc 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -110,8 +110,8 @@ for i in $FILES; do
done
# diff with extra ignore lines
-check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
-check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
+check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))"'
+check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"'
check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"'
check include/linux/ctype.h '-I "isdigit("'
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
index f01d48a8d707..b8a5159361b4 100644
--- a/tools/perf/util/include/linux/linkage.h
+++ b/tools/perf/util/include/linux/linkage.h
@@ -5,10 +5,93 @@
/* linkage.h ... for including arch/x86/lib/memcpy_64.S */
-#define ENTRY(name) \
- .globl name; \
+/* Some toolchains use other characters (e.g. '`') to mark new line in macro */
+#ifndef ASM_NL
+#define ASM_NL ;
+#endif
+
+#ifndef __ALIGN
+#define __ALIGN .align 4,0x90
+#define __ALIGN_STR ".align 4,0x90"
+#endif
+
+/* SYM_T_FUNC -- type used by assembler to mark functions */
+#ifndef SYM_T_FUNC
+#define SYM_T_FUNC STT_FUNC
+#endif
+
+/* SYM_A_* -- align the symbol? */
+#define SYM_A_ALIGN ALIGN
+
+/* SYM_L_* -- linkage of symbols */
+#define SYM_L_GLOBAL(name) .globl name
+#define SYM_L_LOCAL(name) /* nothing */
+
+#define ALIGN __ALIGN
+
+/* === generic annotations === */
+
+/* SYM_ENTRY -- use only if you have to for non-paired symbols */
+#ifndef SYM_ENTRY
+#define SYM_ENTRY(name, linkage, align...) \
+ linkage(name) ASM_NL \
+ align ASM_NL \
name:
+#endif
+
+/* SYM_START -- use only if you have to */
+#ifndef SYM_START
+#define SYM_START(name, linkage, align...) \
+ SYM_ENTRY(name, linkage, align)
+#endif
+
+/* SYM_END -- use only if you have to */
+#ifndef SYM_END
+#define SYM_END(name, sym_type) \
+ .type name sym_type ASM_NL \
+ .size name, .-name
+#endif
+
+/*
+ * SYM_FUNC_START_ALIAS -- use where there are two global names for one
+ * function
+ */
+#ifndef SYM_FUNC_START_ALIAS
+#define SYM_FUNC_START_ALIAS(name) \
+ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
+#endif
+
+/* SYM_FUNC_START -- use for global functions */
+#ifndef SYM_FUNC_START
+/*
+ * The same as SYM_FUNC_START_ALIAS, but we will need to distinguish these two
+ * later.
+ */
+#define SYM_FUNC_START(name) \
+ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
+#endif
+
+/* SYM_FUNC_START_LOCAL -- use for local functions */
+#ifndef SYM_FUNC_START_LOCAL
+/* the same as SYM_FUNC_START_LOCAL_ALIAS, see comment near SYM_FUNC_START */
+#define SYM_FUNC_START_LOCAL(name) \
+ SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN)
+#endif
+
+/* SYM_FUNC_END_ALIAS -- the end of LOCAL_ALIASed or ALIASed function */
+#ifndef SYM_FUNC_END_ALIAS
+#define SYM_FUNC_END_ALIAS(name) \
+ SYM_END(name, SYM_T_FUNC)
+#endif
-#define ENDPROC(name)
+/*
+ * SYM_FUNC_END -- the end of SYM_FUNC_START_LOCAL, SYM_FUNC_START,
+ * SYM_FUNC_START_WEAK, ...
+ */
+#ifndef SYM_FUNC_END
+/* the same as SYM_FUNC_END_ALIAS, see comment near SYM_FUNC_START */
+#define SYM_FUNC_END(name) \
+ SYM_END(name, SYM_T_FUNC)
+#endif
#endif /* PERF_LINUX_LINKAGE_H_ */
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 14/23] tools arch x86: Sync the msr-index.h copy with the kernel sources
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (12 preceding siblings ...)
2019-12-03 13:55 ` [PATCH 13/23] perf bench: Update the copies of x86's mem{cpy,set}_64.S Arnaldo Carvalho de Melo
@ 2019-12-03 13:55 ` Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 15/23] tools headers uapi: Sync linux/fscrypt.h " Arnaldo Carvalho de Melo
` (9 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:55 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Arnaldo Carvalho de Melo, Adrian Hunter,
Jan Beulich, Juergen Gross, Pawan Gupta, Vineela Tummalapalli
From: Arnaldo Carvalho de Melo <acme@redhat.com>
To pick up the changes from these csets:
3f3c8be973af Merge tag 'for-linus-5.5a-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip
4e3f77d8419b ("xen/mcelog: add PPIN to record when available")
db4d30fbb71b ("x86/bugs: Add ITLB_MULTIHIT bug infrastructure")
1b42f017415b ("x86/speculation/taa: Add mitigation for TSX Async Abort")
c2955f270a84 ("x86/msr: Add the IA32_TSX_CTRL MSR")
These are the changes in tooling that this udpate ensues:
$ tools/perf/trace/beauty/tracepoints/x86_msr.sh > /tmp/before
$
$ cp arch/x86/include/asm/msr-index.h tools/arch/x86/include/asm/msr-index.h
$
$ tools/perf/trace/beauty/tracepoints/x86_msr.sh > /tmp/after
$ diff -u /tmp/before /tmp/after
--- /tmp/before 2019-12-02 11:54:44.371035723 -0300
+++ /tmp/after 2019-12-02 11:55:31.847859784 -0300
@@ -48,6 +48,7 @@
[0x00000119] = "IA32_BBL_CR_CTL",
[0x0000011e] = "IA32_BBL_CR_CTL3",
[0x00000120] = "IDT_MCR_CTRL",
+ [0x00000122] = "IA32_TSX_CTRL",
[0x00000140] = "MISC_FEATURES_ENABLES",
[0x00000174] = "IA32_SYSENTER_CS",
[0x00000175] = "IA32_SYSENTER_ESP",
@@ -283,4 +284,6 @@
[0xc0010240 - x86_AMD_V_KVM_MSRs_offset] = "F15H_NB_PERF_CTL",
[0xc0010241 - x86_AMD_V_KVM_MSRs_offset] = "F15H_NB_PERF_CTR",
[0xc0010280 - x86_AMD_V_KVM_MSRs_offset] = "F15H_PTSC",
+ [0xc00102f0 - x86_AMD_V_KVM_MSRs_offset] = "AMD_PPIN_CTL",
+ [0xc00102f1 - x86_AMD_V_KVM_MSRs_offset] = "AMD_PPIN",
};
$
CC /tmp/build/perf/trace/beauty/tracepoints/x86_msr.o
LD /tmp/build/perf/trace/beauty/tracepoints/perf-in.o
LD /tmp/build/perf/trace/beauty/perf-in.o
LD /tmp/build/perf/perf-in.o
Now it is possible to use these strings when setting up filters for the msr:*
tracepoints, like:
# perf trace -e msr:* --filter=msr==IA32_TSX_CTRL
^C[root@quaco ~]#
If we use an invalid operator we can check what is the filter that is put in
place:
# perf trace -e msr:* --filter=msr=IA32_TSX_CTRL
Failed to set filter "(msr=0x122) && (common_pid != 25976 && common_pid != 25860)" on event msr:read_msr with 22 (Invalid argument)
One can as well use -v to see the tracepoints and its filters:
# perf trace -v -e msr:* --filter=msr==IA32_TSX_CTRL
Using CPUID GenuineIntel-6-8E-A
New filter for msr:read_msr: (msr==0x122) && (common_pid != 26110 && common_pid != 25860)
New filter for msr:write_msr: (msr==0x122) && (common_pid != 26110 && common_pid != 25860)
New filter for msr:rdpmc: (msr==0x122) && (common_pid != 26110 && common_pid != 25860)
mmap size 528384B
^C#
Better than keep looking up those numbers, works with callchains as
well, e.g. for something more common:
# perf trace -e msr:*/max-stack=16/ --filter="msr==IA32_SPEC_CTRL" --max-events=2
0.000 SCTP timer/6158 msr:write_msr(msr: IA32_SPEC_CTRL, val: 6)
do_trace_write_msr ([kernel.kallsyms])
do_trace_write_msr ([kernel.kallsyms])
__switch_to_xtra ([kernel.kallsyms])
__switch_to ([kernel.kallsyms])
__sched_text_start ([kernel.kallsyms])
schedule ([kernel.kallsyms])
schedule_hrtimeout_range_clock ([kernel.kallsyms])
poll_schedule_timeout.constprop.0 ([kernel.kallsyms])
do_select ([kernel.kallsyms])
core_sys_select ([kernel.kallsyms])
kern_select ([kernel.kallsyms])
__x64_sys_select ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
__select (/usr/lib64/libc-2.29.so)
[0] ([unknown])
0.024 :0/0 msr:write_msr(msr: IA32_SPEC_CTRL)
do_trace_write_msr ([kernel.kallsyms])
do_trace_write_msr ([kernel.kallsyms])
__switch_to_xtra ([kernel.kallsyms])
__switch_to ([kernel.kallsyms])
__sched_text_start ([kernel.kallsyms])
schedule_idle ([kernel.kallsyms])
do_idle ([kernel.kallsyms])
cpu_startup_entry ([kernel.kallsyms])
start_secondary ([kernel.kallsyms])
[0x2000d4] ([kernel.kallsyms])
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Juergen Gross <jgross@suse.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vineela Tummalapalli <vineela.tummalapalli@intel.com>
Link: https://lkml.kernel.org/n/tip-n1xd78fpd5lxn4q1brqi2jl6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/arch/x86/include/asm/msr-index.h | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 20ce682a2540..084e98da04a7 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -93,6 +93,18 @@
* Microarchitectural Data
* Sampling (MDS) vulnerabilities.
*/
+#define ARCH_CAP_PSCHANGE_MC_NO BIT(6) /*
+ * The processor is not susceptible to a
+ * machine check error due to modifying the
+ * code page size along with either the
+ * physical address or cache type
+ * without TLB invalidation.
+ */
+#define ARCH_CAP_TSX_CTRL_MSR BIT(7) /* MSR for TSX control is available. */
+#define ARCH_CAP_TAA_NO BIT(8) /*
+ * Not susceptible to
+ * TSX Async Abort (TAA) vulnerabilities.
+ */
#define MSR_IA32_FLUSH_CMD 0x0000010b
#define L1D_FLUSH BIT(0) /*
@@ -103,6 +115,10 @@
#define MSR_IA32_BBL_CR_CTL 0x00000119
#define MSR_IA32_BBL_CR_CTL3 0x0000011e
+#define MSR_IA32_TSX_CTRL 0x00000122
+#define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */
+#define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */
+
#define MSR_IA32_SYSENTER_CS 0x00000174
#define MSR_IA32_SYSENTER_ESP 0x00000175
#define MSR_IA32_SYSENTER_EIP 0x00000176
@@ -393,6 +409,8 @@
#define MSR_AMD_PSTATE_DEF_BASE 0xc0010064
#define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140
#define MSR_AMD64_OSVW_STATUS 0xc0010141
+#define MSR_AMD_PPIN_CTL 0xc00102f0
+#define MSR_AMD_PPIN 0xc00102f1
#define MSR_AMD64_LS_CFG 0xc0011020
#define MSR_AMD64_DC_CFG 0xc0011022
#define MSR_AMD64_BU_CFG2 0xc001102a
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 15/23] tools headers uapi: Sync linux/fscrypt.h with the kernel sources
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (13 preceding siblings ...)
2019-12-03 13:55 ` [PATCH 14/23] tools arch x86: Sync the msr-index.h copy with the kernel sources Arnaldo Carvalho de Melo
@ 2019-12-03 13:55 ` Arnaldo Carvalho de Melo
2019-12-03 13:55 ` [PATCH 16/23] tools headers uapi: Sync linux/stat.h " Arnaldo Carvalho de Melo
` (8 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:55 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Arnaldo Carvalho de Melo, Adrian Hunter,
Eric Biggers
From: Arnaldo Carvalho de Melo <acme@redhat.com>
To pick the changes from:
b103fb7653ff ("fscrypt: add support for IV_INO_LBLK_64 policies")
That don't trigger any changes in tooling.
This silences this perf build warning:
Warning: Kernel ABI header at 'tools/include/uapi/linux/fscrypt.h' differs from latest version at 'include/uapi/linux/fscrypt.h'
diff -u tools/include/uapi/linux/fscrypt.h include/uapi/linux/fscrypt.h
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Eric Biggers <ebiggers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-cgfz3ffe07pw2m8hmstvkudl@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/include/uapi/linux/fscrypt.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index 39ccfe9311c3..1beb174ad950 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -17,7 +17,8 @@
#define FSCRYPT_POLICY_FLAGS_PAD_32 0x03
#define FSCRYPT_POLICY_FLAGS_PAD_MASK 0x03
#define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04
-#define FSCRYPT_POLICY_FLAGS_VALID 0x07
+#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 0x08
+#define FSCRYPT_POLICY_FLAGS_VALID 0x0F
/* Encryption algorithms */
#define FSCRYPT_MODE_AES_256_XTS 1
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 16/23] tools headers uapi: Sync linux/stat.h with the kernel sources
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (14 preceding siblings ...)
2019-12-03 13:55 ` [PATCH 15/23] tools headers uapi: Sync linux/fscrypt.h " Arnaldo Carvalho de Melo
@ 2019-12-03 13:55 ` Arnaldo Carvalho de Melo
2019-12-03 13:56 ` [PATCH 17/23] tools headers kvm: Sync kvm headers " Arnaldo Carvalho de Melo
` (7 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:55 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Arnaldo Carvalho de Melo, Adrian Hunter,
Eric Biggers
From: Arnaldo Carvalho de Melo <acme@redhat.com>
To pick the changes from:
3ad2522c64cf ("statx: define STATX_ATTR_VERITY")
That don't trigger any changes in tooling.
This silences this perf build warning:
Warning: Kernel ABI header at 'tools/include/uapi/linux/stat.h' differs from latest version at 'include/uapi/linux/stat.h'
diff -u tools/include/uapi/linux/stat.h include/uapi/linux/stat.h
At some point we wi'll beautify structs passed in pointers to syscalls
and then we'll need to have tables for these defines, for now update the
file to silence the warning as this file is used for doing this type of
number -> string translations for other defines found in these file.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Eric Biggers <ebiggers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-thcy60dpry5qrpn7nmc58bwg@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/include/uapi/linux/stat.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index 7b35e98d3c58..ad80a5c885d5 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -167,8 +167,8 @@ struct statx {
#define STATX_ATTR_APPEND 0x00000020 /* [I] File is append-only */
#define STATX_ATTR_NODUMP 0x00000040 /* [I] File is not to be dumped */
#define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */
-
#define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */
+#define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */
#endif /* _UAPI_LINUX_STAT_H */
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 17/23] tools headers kvm: Sync kvm headers with the kernel sources
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (15 preceding siblings ...)
2019-12-03 13:55 ` [PATCH 16/23] tools headers uapi: Sync linux/stat.h " Arnaldo Carvalho de Melo
@ 2019-12-03 13:56 ` Arnaldo Carvalho de Melo
2019-12-03 13:56 ` [PATCH 18/23] tools headers UAPI: Sync sched.h with the kernel Arnaldo Carvalho de Melo
` (6 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:56 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Arnaldo Carvalho de Melo, Adrian Hunter,
Christoffer Dall, Fabiano Rosas, Greg Kurz, Marc Zyngier,
Paul Mackerras, Steven Price
From: Arnaldo Carvalho de Melo <acme@redhat.com>
To pick up the changes from:
14edff88315a Merge tag 'kvmarm-5.5' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
a4b28f5c6798 Merge remote-tracking branch 'kvmarm/kvm-arm64/stolen-time' into kvmarm-master/next
58772e9a3db7 ("KVM: arm64: Provide VCPU attributes for stolen time")
da345174ceca ("KVM: arm/arm64: Allow user injection of external data aborts")
c726200dd106 ("KVM: arm/arm64: Allow reporting non-ISV data aborts to userspace")
efe5ddcae496 ("KVM: PPC: Book3S HV: XIVE: Allow userspace to set the # of VPs")
No tools changes are caused by this, as the only defines so far used
from these files are for syscall arg pretty printing are:
$ grep KVM tools/perf/trace/beauty/*.sh
tools/perf/trace/beauty/kvm_ioctl.sh:regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
$
Some are also include by:
tools/perf/arch/x86/util/kvm-stat.c
tools/perf/arch/powerpc/util/kvm-stat.c
This addresses these tools/perf build warnings:
Warning: Kernel ABI header at 'tools/include/uapi/linux/kvm.h' differs from latest version at 'include/uapi/linux/kvm.h'
diff -u tools/include/uapi/linux/kvm.h include/uapi/linux/kvm.h
Warning: Kernel ABI header at 'tools/arch/powerpc/include/uapi/asm/kvm.h' differs from latest version at 'arch/powerpc/include/uapi/asm/kvm.h'
diff -u tools/arch/powerpc/include/uapi/asm/kvm.h arch/powerpc/include/uapi/asm/kvm.h
Warning: Kernel ABI header at 'tools/arch/arm/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm/include/uapi/asm/kvm.h'
diff -u tools/arch/arm/include/uapi/asm/kvm.h arch/arm/include/uapi/asm/kvm.h
Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h'
diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Christoffer Dall <christoffer.dall@arm.com>
Cc: Fabiano Rosas <farosas@linux.ibm.com>
Cc: Greg Kurz <groug@kaod.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Steven Price <steven.price@arm.com>
Link: https://lkml.kernel.org/n/tip-qrjdudhq25mk5bfnhveofbm4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/arch/arm/include/uapi/asm/kvm.h | 3 ++-
tools/arch/arm64/include/uapi/asm/kvm.h | 5 ++++-
tools/arch/powerpc/include/uapi/asm/kvm.h | 3 +++
tools/include/uapi/linux/kvm.h | 11 +++++++++++
4 files changed, 20 insertions(+), 2 deletions(-)
diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h
index 2769360f195c..03cd7c19a683 100644
--- a/tools/arch/arm/include/uapi/asm/kvm.h
+++ b/tools/arch/arm/include/uapi/asm/kvm.h
@@ -131,8 +131,9 @@ struct kvm_vcpu_events {
struct {
__u8 serror_pending;
__u8 serror_has_esr;
+ __u8 ext_dabt_pending;
/* Align it to 8 bytes */
- __u8 pad[6];
+ __u8 pad[5];
__u64 serror_esr;
} exception;
__u32 reserved[12];
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index 67c21f9bdbad..820e5751ada7 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -164,8 +164,9 @@ struct kvm_vcpu_events {
struct {
__u8 serror_pending;
__u8 serror_has_esr;
+ __u8 ext_dabt_pending;
/* Align it to 8 bytes */
- __u8 pad[6];
+ __u8 pad[5];
__u64 serror_esr;
} exception;
__u32 reserved[12];
@@ -323,6 +324,8 @@ struct kvm_vcpu_events {
#define KVM_ARM_VCPU_TIMER_CTRL 1
#define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0
#define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1
+#define KVM_ARM_VCPU_PVTIME_CTRL 2
+#define KVM_ARM_VCPU_PVTIME_IPA 0
/* KVM_IRQ_LINE irq field index values */
#define KVM_ARM_IRQ_VCPU2_SHIFT 28
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index b0f72dea8b11..264e266a85bf 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -667,6 +667,8 @@ struct kvm_ppc_cpu_char {
/* PPC64 eXternal Interrupt Controller Specification */
#define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */
+#define KVM_DEV_XICS_GRP_CTRL 2
+#define KVM_DEV_XICS_NR_SERVERS 1
/* Layout of 64-bit source attribute values */
#define KVM_XICS_DESTINATION_SHIFT 0
@@ -683,6 +685,7 @@ struct kvm_ppc_cpu_char {
#define KVM_DEV_XIVE_GRP_CTRL 1
#define KVM_DEV_XIVE_RESET 1
#define KVM_DEV_XIVE_EQ_SYNC 2
+#define KVM_DEV_XIVE_NR_SERVERS 3
#define KVM_DEV_XIVE_GRP_SOURCE 2 /* 64-bit source identifier */
#define KVM_DEV_XIVE_GRP_SOURCE_CONFIG 3 /* 64-bit source identifier */
#define KVM_DEV_XIVE_GRP_EQ_CONFIG 4 /* 64-bit EQ identifier */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 52641d8ca9e8..e6f17c8e2dba 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -235,6 +235,7 @@ struct kvm_hyperv_exit {
#define KVM_EXIT_S390_STSI 25
#define KVM_EXIT_IOAPIC_EOI 26
#define KVM_EXIT_HYPERV 27
+#define KVM_EXIT_ARM_NISV 28
/* For KVM_EXIT_INTERNAL_ERROR */
/* Emulate instruction failed. */
@@ -394,6 +395,11 @@ struct kvm_run {
} eoi;
/* KVM_EXIT_HYPERV */
struct kvm_hyperv_exit hyperv;
+ /* KVM_EXIT_ARM_NISV */
+ struct {
+ __u64 esr_iss;
+ __u64 fault_ipa;
+ } arm_nisv;
/* Fix the size of the union. */
char padding[256];
};
@@ -1000,6 +1006,9 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_PMU_EVENT_FILTER 173
#define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174
#define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 175
+#define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176
+#define KVM_CAP_ARM_NISV_TO_USER 177
+#define KVM_CAP_ARM_INJECT_EXT_DABT 178
#ifdef KVM_CAP_IRQ_ROUTING
@@ -1227,6 +1236,8 @@ enum kvm_device_type {
#define KVM_DEV_TYPE_ARM_VGIC_ITS KVM_DEV_TYPE_ARM_VGIC_ITS
KVM_DEV_TYPE_XIVE,
#define KVM_DEV_TYPE_XIVE KVM_DEV_TYPE_XIVE
+ KVM_DEV_TYPE_ARM_PV_TIME,
+#define KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_ARM_PV_TIME
KVM_DEV_TYPE_MAX,
};
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 18/23] tools headers UAPI: Sync sched.h with the kernel
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (16 preceding siblings ...)
2019-12-03 13:56 ` [PATCH 17/23] tools headers kvm: Sync kvm headers " Arnaldo Carvalho de Melo
@ 2019-12-03 13:56 ` Arnaldo Carvalho de Melo
2019-12-03 15:40 ` Christian Brauner
2019-12-03 13:56 ` [PATCH 19/23] perf beauty: Add CLEAR_SIGHAND support for clone's flags arg Arnaldo Carvalho de Melo
` (5 subsequent siblings)
23 siblings, 1 reply; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:56 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Arnaldo Carvalho de Melo, Adrian Hunter,
Adrian Reber, Christian Brauner
From: Arnaldo Carvalho de Melo <acme@redhat.com>
To get the changes in:
0acefef58451 ("Merge tag 'threads-v5.5' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux")
49cb2fc42ce4 ("fork: extend clone3() to support setting a PID")
fa729c4df558 ("clone3: validate stack arguments")
b612e5df4587 ("clone3: add CLONE_CLEAR_SIGHAND")
This file gets rebuilt, but no changes ensues:
CC /tmp/build/perf/trace/beauty/clone.o
This addresses this perf build warning:
Warning: Kernel ABI header at 'tools/include/uapi/linux/sched.h' differs from latest version at 'include/uapi/linux/sched.h'
diff -u tools/include/uapi/linux/sched.h include/uapi/linux/sched.
The CLONE_CLEAR_SIGHAND one will be used in tools/perf/trace/beauty/clone.c
in a followup patch to show that string when this bit is set in the
syscall arg. Keeping a copy of this file allows us to build this in
older systems and have the binary support printing that flag whenever
that system gets its kernel updated to one where this feature is
present.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Adrian Reber <areber@redhat.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-nprqsvvzbhzoy64cbvos6c5b@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/include/uapi/linux/sched.h | 60 ++++++++++++++++++++++----------
1 file changed, 42 insertions(+), 18 deletions(-)
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index 99335e1f4a27..4a0217832464 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -33,27 +33,48 @@
#define CLONE_NEWNET 0x40000000 /* New network namespace */
#define CLONE_IO 0x80000000 /* Clone io context */
+/* Flags for the clone3() syscall. */
+#define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
+
#ifndef __ASSEMBLY__
/**
* struct clone_args - arguments for the clone3 syscall
- * @flags: Flags for the new process as listed above.
- * All flags are valid except for CSIGNAL and
- * CLONE_DETACHED.
- * @pidfd: If CLONE_PIDFD is set, a pidfd will be
- * returned in this argument.
- * @child_tid: If CLONE_CHILD_SETTID is set, the TID of the
- * child process will be returned in the child's
- * memory.
- * @parent_tid: If CLONE_PARENT_SETTID is set, the TID of
- * the child process will be returned in the
- * parent's memory.
- * @exit_signal: The exit_signal the parent process will be
- * sent when the child exits.
- * @stack: Specify the location of the stack for the
- * child process.
- * @stack_size: The size of the stack for the child process.
- * @tls: If CLONE_SETTLS is set, the tls descriptor
- * is set to tls.
+ * @flags: Flags for the new process as listed above.
+ * All flags are valid except for CSIGNAL and
+ * CLONE_DETACHED.
+ * @pidfd: If CLONE_PIDFD is set, a pidfd will be
+ * returned in this argument.
+ * @child_tid: If CLONE_CHILD_SETTID is set, the TID of the
+ * child process will be returned in the child's
+ * memory.
+ * @parent_tid: If CLONE_PARENT_SETTID is set, the TID of
+ * the child process will be returned in the
+ * parent's memory.
+ * @exit_signal: The exit_signal the parent process will be
+ * sent when the child exits.
+ * @stack: Specify the location of the stack for the
+ * child process.
+ * Note, @stack is expected to point to the
+ * lowest address. The stack direction will be
+ * determined by the kernel and set up
+ * appropriately based on @stack_size.
+ * @stack_size: The size of the stack for the child process.
+ * @tls: If CLONE_SETTLS is set, the tls descriptor
+ * is set to tls.
+ * @set_tid: Pointer to an array of type *pid_t. The size
+ * of the array is defined using @set_tid_size.
+ * This array is used to select PIDs/TIDs for
+ * newly created processes. The first element in
+ * this defines the PID in the most nested PID
+ * namespace. Each additional element in the array
+ * defines the PID in the parent PID namespace of
+ * the original PID namespace. If the array has
+ * less entries than the number of currently
+ * nested PID namespaces only the PIDs in the
+ * corresponding namespaces are set.
+ * @set_tid_size: This defines the size of the array referenced
+ * in @set_tid. This cannot be larger than the
+ * kernel's limit of nested PID namespaces.
*
* The structure is versioned by size and thus extensible.
* New struct members must go at the end of the struct and
@@ -68,10 +89,13 @@ struct clone_args {
__aligned_u64 stack;
__aligned_u64 stack_size;
__aligned_u64 tls;
+ __aligned_u64 set_tid;
+ __aligned_u64 set_tid_size;
};
#endif
#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
+#define CLONE_ARGS_SIZE_VER1 80 /* sizeof second published struct */
/*
* Scheduling policies
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* Re: [PATCH 18/23] tools headers UAPI: Sync sched.h with the kernel
2019-12-03 13:56 ` [PATCH 18/23] tools headers UAPI: Sync sched.h with the kernel Arnaldo Carvalho de Melo
@ 2019-12-03 15:40 ` Christian Brauner
0 siblings, 0 replies; 27+ messages in thread
From: Christian Brauner @ 2019-12-03 15:40 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Ingo Molnar, Thomas Gleixner, Jiri Olsa, Namhyung Kim,
Clark Williams, linux-kernel, linux-perf-users,
Arnaldo Carvalho de Melo, Adrian Hunter, Adrian Reber
On Tue, Dec 03, 2019 at 10:56:01AM -0300, Arnaldo Carvalho de Melo wrote:
> From: Arnaldo Carvalho de Melo <acme@redhat.com>
>
> To get the changes in:
>
> 0acefef58451 ("Merge tag 'threads-v5.5' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux")
> 49cb2fc42ce4 ("fork: extend clone3() to support setting a PID")
> fa729c4df558 ("clone3: validate stack arguments")
> b612e5df4587 ("clone3: add CLONE_CLEAR_SIGHAND")
>
> This file gets rebuilt, but no changes ensues:
>
> CC /tmp/build/perf/trace/beauty/clone.o
>
> This addresses this perf build warning:
>
> Warning: Kernel ABI header at 'tools/include/uapi/linux/sched.h' differs from latest version at 'include/uapi/linux/sched.h'
> diff -u tools/include/uapi/linux/sched.h include/uapi/linux/sched.
>
> The CLONE_CLEAR_SIGHAND one will be used in tools/perf/trace/beauty/clone.c
> in a followup patch to show that string when this bit is set in the
> syscall arg. Keeping a copy of this file allows us to build this in
> older systems and have the binary support printing that flag whenever
> that system gets its kernel updated to one where this feature is
> present.
>
> Cc: Adrian Hunter <adrian.hunter@intel.com>
> Cc: Adrian Reber <areber@redhat.com>
> Cc: Christian Brauner <christian.brauner@ubuntu.com>
> Cc: Jiri Olsa <jolsa@kernel.org>
> Cc: Namhyung Kim <namhyung@kernel.org>
> Link: https://lkml.kernel.org/n/tip-nprqsvvzbhzoy64cbvos6c5b@git.kernel.org
> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Thanks!
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
^ permalink raw reply [flat|nested] 27+ messages in thread
* [PATCH 19/23] perf beauty: Add CLEAR_SIGHAND support for clone's flags arg
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (17 preceding siblings ...)
2019-12-03 13:56 ` [PATCH 18/23] tools headers UAPI: Sync sched.h with the kernel Arnaldo Carvalho de Melo
@ 2019-12-03 13:56 ` Arnaldo Carvalho de Melo
2019-12-03 15:41 ` Christian Brauner
2019-12-03 13:56 ` [PATCH 20/23] tools arch x86: Sync asm/cpufeatures.h with the kernel sources Arnaldo Carvalho de Melo
` (4 subsequent siblings)
23 siblings, 1 reply; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:56 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Arnaldo Carvalho de Melo, Adrian Hunter,
Adrian Reber, Christian Brauner
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Add support for the recently added CLONE_CLEAR_SIGHAND flag.
This takes advantage of the copy of the uapi/linux/sched.h we have in
tools/include, which allows us to build tools/perf in older systems and
have the binary support printing that flag whenever that system gets its
kernel updated to one where this feature is present.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Adrian Reber <areber@redhat.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org
Link: https://lkml.kernel.org/n/tip-1vnz497ubtu5oz16ygdcul0e@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/trace/beauty/clone.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/perf/trace/beauty/clone.c b/tools/perf/trace/beauty/clone.c
index 1a8d3be2030e..062ca849c8fd 100644
--- a/tools/perf/trace/beauty/clone.c
+++ b/tools/perf/trace/beauty/clone.c
@@ -45,6 +45,7 @@ static size_t clone__scnprintf_flags(unsigned long flags, char *bf, size_t size,
P_FLAG(NEWPID);
P_FLAG(NEWNET);
P_FLAG(IO);
+ P_FLAG(CLEAR_SIGHAND);
#undef P_FLAG
if (flags)
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* Re: [PATCH 19/23] perf beauty: Add CLEAR_SIGHAND support for clone's flags arg
2019-12-03 13:56 ` [PATCH 19/23] perf beauty: Add CLEAR_SIGHAND support for clone's flags arg Arnaldo Carvalho de Melo
@ 2019-12-03 15:41 ` Christian Brauner
0 siblings, 0 replies; 27+ messages in thread
From: Christian Brauner @ 2019-12-03 15:41 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Ingo Molnar, Thomas Gleixner, Jiri Olsa, Namhyung Kim,
Clark Williams, linux-kernel, linux-perf-users,
Arnaldo Carvalho de Melo, Adrian Hunter, Adrian Reber
On Tue, Dec 03, 2019 at 10:56:02AM -0300, Arnaldo Carvalho de Melo wrote:
> From: Arnaldo Carvalho de Melo <acme@redhat.com>
>
> Add support for the recently added CLONE_CLEAR_SIGHAND flag.
>
> This takes advantage of the copy of the uapi/linux/sched.h we have in
> tools/include, which allows us to build tools/perf in older systems and
> have the binary support printing that flag whenever that system gets its
> kernel updated to one where this feature is present.
>
> Cc: Adrian Hunter <adrian.hunter@intel.com>
> Cc: Adrian Reber <areber@redhat.com>
> Cc: Christian Brauner <christian.brauner@ubuntu.com>
> Cc: Jiri Olsa <jolsa@kernel.org>
> Cc: Namhyung Kim <namhyung@kernel.org
> Link: https://lkml.kernel.org/n/tip-1vnz497ubtu5oz16ygdcul0e@git.kernel.org
> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Thanks!
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
^ permalink raw reply [flat|nested] 27+ messages in thread
* [PATCH 20/23] tools arch x86: Sync asm/cpufeatures.h with the kernel sources
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (18 preceding siblings ...)
2019-12-03 13:56 ` [PATCH 19/23] perf beauty: Add CLEAR_SIGHAND support for clone's flags arg Arnaldo Carvalho de Melo
@ 2019-12-03 13:56 ` Arnaldo Carvalho de Melo
2019-12-03 13:56 ` [PATCH 21/23] perf kvm: Clarify the 'perf kvm' -i and -o command line options Arnaldo Carvalho de Melo
` (3 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:56 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Arnaldo Carvalho de Melo, Adrian Hunter,
Babu Moger, Borislav Petkov, Pawan Gupta, Vineela Tummalapalli
From: Arnaldo Carvalho de Melo <acme@redhat.com>
To pick up the changes from:
a25bbc2644f0 ("Merge branches 'x86-cpu-for-linus' and 'x86-fpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip")
db4d30fbb71b ("x86/bugs: Add ITLB_MULTIHIT bug infrastructure")
1b42f017415b ("x86/speculation/taa: Add mitigation for TSX Async Abort")
9d40b85bb46a ("x86/cpufeatures: Add feature bit RDPRU on AMD")
These don't cause any changes in tooling, just silences this perf build
warning:
Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h'
diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Babu Moger <babu.moger@amd.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vineela Tummalapalli <vineela.tummalapalli@intel.com>
Link: https://lkml.kernel.org/n/tip-yufg9yt2nbkh45r9xvxnnscq@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/arch/x86/include/asm/cpufeatures.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 0652d3eed9bd..e9b62498fe75 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -292,6 +292,7 @@
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
#define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */
#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */
+#define X86_FEATURE_RDPRU (13*32+ 4) /* Read processor register at user level */
#define X86_FEATURE_WBNOINVD (13*32+ 9) /* WBNOINVD instruction */
#define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */
#define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */
@@ -399,5 +400,7 @@
#define X86_BUG_MDS X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */
#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* CPU is only affected by the MSDBS variant of BUG_MDS */
#define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */
+#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */
+#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
#endif /* _ASM_X86_CPUFEATURES_H */
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 21/23] perf kvm: Clarify the 'perf kvm' -i and -o command line options
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (19 preceding siblings ...)
2019-12-03 13:56 ` [PATCH 20/23] tools arch x86: Sync asm/cpufeatures.h with the kernel sources Arnaldo Carvalho de Melo
@ 2019-12-03 13:56 ` Arnaldo Carvalho de Melo
2019-12-03 13:56 ` [PATCH 22/23] libtraceevent: Fix lib installation with O= Arnaldo Carvalho de Melo
` (2 subsequent siblings)
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:56 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Arnaldo Carvalho de Melo, Adrian Hunter,
Steve Dickson, William Cohen
From: Arnaldo Carvalho de Melo <acme@redhat.com>
The 'perf kvm' subcommand has options that it in turn passes to other
perf subcommands such as 'report' and 'record', particularly -i and -o
end up setting the same variable that will then be used for 'record's -o
and report '-i', which ends up being confusing, leading some to think
that both -i and -o can be used with 'report'.
Improve the man page to state that -i is used with the post-processing
subcommands while -o is used just with 'record' and that to save the
output of 'report' one should simply redirect its output to a file.
Noticed while reading the https://www.linux-kvm.org/page/Perf_events
page.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Steve Dickson <steved@redhat.com>
Cc: William Cohen <wcohen@redhat.com>
Link: https://lkml.kernel.org/n/tip-tclbttvmgtm525fvmh85f7d9@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Documentation/perf-kvm.txt | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index 6a5bb2b17039..cf95baef7b61 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -68,10 +68,11 @@ OPTIONS
-------
-i::
--input=<path>::
- Input file name.
+ Input file name, for the 'report', 'diff' and 'buildid-list' subcommands.
-o::
--output=<path>::
- Output file name.
+ Output file name, for the 'record' subcommand. Doesn't work with 'report',
+ just redirect the output to a file when using 'report'.
--host::
Collect host side performance profile.
--guest::
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 22/23] libtraceevent: Fix lib installation with O=
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (20 preceding siblings ...)
2019-12-03 13:56 ` [PATCH 21/23] perf kvm: Clarify the 'perf kvm' -i and -o command line options Arnaldo Carvalho de Melo
@ 2019-12-03 13:56 ` Arnaldo Carvalho de Melo
2019-12-03 13:56 ` [PATCH 23/23] libtraceevent: Copy pkg-config file to output folder when using O= Arnaldo Carvalho de Melo
2019-12-04 7:51 ` [GIT PULL] perf/core improvements and fixes Ingo Molnar
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:56 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Sudip Mukherjee, Steven Rostedt,
linux-trace-devel, Arnaldo Carvalho de Melo
From: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
When we use 'O=' with make to build libtraceevent in a separate folder
it fails to install libtraceevent.a and libtraceevent.so.1.1.0 with the
error:
INSTALL /home/sudip/linux/obj-trace/libtraceevent.a
INSTALL /home/sudip/linux/obj-trace/libtraceevent.so.1.1.0
cp: cannot stat 'libtraceevent.a': No such file or directory
Makefile:225: recipe for target 'install_lib' failed
make: *** [install_lib] Error 1
I used the command:
make O=../../../obj-trace DESTDIR=~/test prefix==/usr install
It turns out libtraceevent Makefile, even though it builds in a separate
folder, searches for libtraceevent.a and libtraceevent.so.1.1.0 in its
source folder.
So, add the 'OUTPUT' prefix to the source path so that 'make' looks for
the files in the correct place.
Signed-off-by: Sudipm Mukherjee <sudipm.mukherjee@gmail.com>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lore.kernel.org/lkml/20191115113610.21493-1-sudipm.mukherjee@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/lib/traceevent/Makefile | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index cbb429f55062..83446fe2cf01 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -97,6 +97,7 @@ EVENT_PARSE_VERSION = $(EP_VERSION).$(EP_PATCHLEVEL).$(EP_EXTRAVERSION)
LIB_TARGET = libtraceevent.a libtraceevent.so.$(EVENT_PARSE_VERSION)
LIB_INSTALL = libtraceevent.a libtraceevent.so*
+LIB_INSTALL := $(addprefix $(OUTPUT),$(LIB_INSTALL))
INCLUDES = -I. -I $(srctree)/tools/include $(CONFIG_INCLUDES)
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* [PATCH 23/23] libtraceevent: Copy pkg-config file to output folder when using O=
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (21 preceding siblings ...)
2019-12-03 13:56 ` [PATCH 22/23] libtraceevent: Fix lib installation with O= Arnaldo Carvalho de Melo
@ 2019-12-03 13:56 ` Arnaldo Carvalho de Melo
2019-12-04 7:51 ` [GIT PULL] perf/core improvements and fixes Ingo Molnar
23 siblings, 0 replies; 27+ messages in thread
From: Arnaldo Carvalho de Melo @ 2019-12-03 13:56 UTC (permalink / raw)
To: Ingo Molnar, Thomas Gleixner
Cc: Jiri Olsa, Namhyung Kim, Clark Williams, linux-kernel,
linux-perf-users, Sudip Mukherjee, Steven Rostedt,
linux-trace-devel, Arnaldo Carvalho de Melo
From: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
When we use 'O=' with make to build libtraceevent in a separate folder
it still copies 'libtraceevent.pc' to its source folder. Modify the
Makefile so that it uses the output folder to copy the pkg-config file
and install from there.
Signed-off-by: Sudipm Mukherjee <sudipm.mukherjee@gmail.com>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: linux-trace-devel@vger.kernel.org
Link: http://lore.kernel.org/lkml/20191115113610.21493-2-sudipm.mukherjee@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/lib/traceevent/Makefile | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 83446fe2cf01..c5a03356a999 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -208,10 +208,11 @@ define do_install
$(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2'
endef
-PKG_CONFIG_FILE = libtraceevent.pc
+PKG_CONFIG_SOURCE_FILE = libtraceevent.pc
+PKG_CONFIG_FILE := $(addprefix $(OUTPUT),$(PKG_CONFIG_SOURCE_FILE))
define do_install_pkgconfig_file
if [ -n "${pkgconfig_dir}" ]; then \
- cp -f ${PKG_CONFIG_FILE}.template ${PKG_CONFIG_FILE}; \
+ cp -f ${PKG_CONFIG_SOURCE_FILE}.template ${PKG_CONFIG_FILE}; \
sed -i "s|INSTALL_PREFIX|${1}|g" ${PKG_CONFIG_FILE}; \
sed -i "s|LIB_VERSION|${EVENT_PARSE_VERSION}|g" ${PKG_CONFIG_FILE}; \
sed -i "s|LIB_DIR|${libdir}|g" ${PKG_CONFIG_FILE}; \
--
2.21.0
^ permalink raw reply related [flat|nested] 27+ messages in thread* Re: [GIT PULL] perf/core improvements and fixes
2019-12-03 13:55 [GIT PULL] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (22 preceding siblings ...)
2019-12-03 13:56 ` [PATCH 23/23] libtraceevent: Copy pkg-config file to output folder when using O= Arnaldo Carvalho de Melo
@ 2019-12-04 7:51 ` Ingo Molnar
23 siblings, 0 replies; 27+ messages in thread
From: Ingo Molnar @ 2019-12-04 7:51 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Thomas Gleixner, Jiri Olsa, Namhyung Kim, Clark Williams,
linux-kernel, linux-perf-users, Andi Kleen, Ian Rogers,
Sudipm Mukherjee, Arnaldo Carvalho de Melo
* Arnaldo Carvalho de Melo <acme@kernel.org> wrote:
> Hi Ingo/Thomas,
>
> Please consider pulling,
>
> Best regards,
>
> - Arnaldo
>
> Test results at the end of this message, as usual.
>
> The following changes since commit e680a41fcaf07ccac8817c589fc4824988b48eac:
>
> Merge tag 'perf-core-for-mingo-5.5-20191128' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent (2019-11-29 06:56:05 +0100)
>
> are available in the Git repository at:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-core-for-mingo-5.5-20191203
>
> for you to fetch changes up to 15b3904f8e884e0d34d5f09906cf6526d0b889a2:
>
> libtraceevent: Copy pkg-config file to output folder when using O= (2019-12-02 21:58:20 -0300)
>
> ----------------------------------------------------------------
> perf/core improvements and fixes:
>
> perf report/top:
>
> - Fix segfault due to missing initialization of recently introduced
> struct map_symbol 'maps' field in append_inlines(), when running
> with DWARF callchains.
>
> perf stat:
>
> Andi Kleen:
>
> - Affinity based optimizations for sessions with many events in
> machines with large core counts, avoiding excessive number of IPIs.
>
> libtraceevent:
>
> - Sudip Mukherjee:
>
> - Fix installation with O=.
>
> - Copy pkg-config file to output folder when using O=.
>
> perf bench:
>
> Arnaldo Carvalho de Melo:
>
> - Update the copies of x86's mem{cpy,set}_64.S, and because that
> now uses new stuff in linux/linkage.h, update that header too, which
> made the minimal clang version to build perf to be 3.5, as
> 3.4 as found in some of the container images used to test build perf
> can't grok STT_FUNC as a token in .type lines.
>
> ABI headers:
>
> Arnaldo Carvalho de Melo:
>
> - Sync x86's msr-index.h copy with the kernel sources, resulting
> in new MSRs to be usable in filter expressions in 'perf trace',
> such as IA32_TSX_CTRL.
>
> - Sync linux/fscrypt.h, linux/stat.h, sched.h and the kvm headers.
>
> perf trace:
>
> Arnaldo Carvalho de Melo:
>
> - Add CLEAR_SIGHAND support for clone's flags arg
>
> perf kvm:
>
> Arnaldo Carvalho de Melo:
>
> - Clarify the 'perf kvm' -i and -o command line options
>
> perf test:
>
> Ian Rogers:
>
> - Move test functionality in to a 'perf test' entry.
>
> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
>
> ----------------------------------------------------------------
> Andi Kleen (10):
> perf cpumap: Maintain cpumaps ordered and without dups
> perf evlist: Maintain evlist->all_cpus
> perf evsel: Add iterator to iterate over events ordered by CPU
> perf evsel: Add functions to close evsel on a CPU
> perf stat: Use affinity for closing file descriptors
> perf stat: Factor out open error handling
> perf stat: Use affinity for opening events
> perf stat: Use affinity for reading
> perf evsel: Add functions to enable/disable for a specific CPU
> perf stat: Use affinity for enabling/disabling events
>
> Arnaldo Carvalho de Melo (10):
> perf machine: Fill map_symbol->maps in append_inlines() to fix segfault
> perf bench: Update the copies of x86's mem{cpy,set}_64.S
> tools arch x86: Sync the msr-index.h copy with the kernel sources
> tools headers uapi: Sync linux/fscrypt.h with the kernel sources
> tools headers uapi: Sync linux/stat.h with the kernel sources
> tools headers kvm: Sync kvm headers with the kernel sources
> tools headers UAPI: Sync sched.h with the kernel
> perf beauty: Add CLEAR_SIGHAND support for clone's flags arg
> tools arch x86: Sync asm/cpufeatures.h with the kernel sources
> perf kvm: Clarify the 'perf kvm' -i and -o command line options
>
> Ian Rogers (1):
> perf jit: Move test functionality in to a test
>
> Sudip Mukherjee (2):
> libtraceevent: Fix lib installation with O=
> libtraceevent: Copy pkg-config file to output folder when using O=
>
> tools/arch/arm/include/uapi/asm/kvm.h | 3 +-
> tools/arch/arm64/include/uapi/asm/kvm.h | 5 +-
> tools/arch/powerpc/include/uapi/asm/kvm.h | 3 +
> tools/arch/x86/include/asm/cpufeatures.h | 3 +
> tools/arch/x86/include/asm/msr-index.h | 18 ++
> tools/arch/x86/lib/memcpy_64.S | 20 +--
> tools/arch/x86/lib/memset_64.S | 16 +-
> tools/include/uapi/linux/fscrypt.h | 3 +-
> tools/include/uapi/linux/kvm.h | 11 ++
> tools/include/uapi/linux/sched.h | 60 +++++--
> tools/include/uapi/linux/stat.h | 2 +-
> tools/lib/traceevent/Makefile | 6 +-
> tools/perf/Documentation/perf-kvm.txt | 5 +-
> tools/perf/arch/arm/tests/regs_load.S | 4 +-
> tools/perf/arch/arm64/tests/regs_load.S | 4 +-
> tools/perf/arch/x86/tests/regs_load.S | 8 +-
> tools/perf/builtin-record.c | 2 +-
> tools/perf/builtin-stat.c | 288 +++++++++++++++++++++---------
> tools/perf/check-headers.sh | 4 +-
> tools/perf/lib/cpumap.c | 73 +++++++-
> tools/perf/lib/evlist.c | 1 +
> tools/perf/lib/evsel.c | 76 ++++++--
> tools/perf/lib/include/internal/evlist.h | 1 +
> tools/perf/lib/include/perf/cpumap.h | 2 +
> tools/perf/lib/include/perf/evsel.h | 3 +
> tools/perf/tests/Build | 1 +
> tools/perf/tests/builtin-test.c | 9 +
> tools/perf/tests/cpumap.c | 16 ++
> tools/perf/tests/event-times.c | 4 +-
> tools/perf/tests/genelf.c | 51 ++++++
> tools/perf/tests/tests.h | 2 +
> tools/perf/trace/beauty/clone.c | 1 +
> tools/perf/util/cpumap.h | 1 +
> tools/perf/util/evlist.c | 113 +++++++++++-
> tools/perf/util/evlist.h | 11 +-
> tools/perf/util/evsel.c | 35 +++-
> tools/perf/util/evsel.h | 9 +-
> tools/perf/util/genelf.c | 46 -----
> tools/perf/util/include/linux/linkage.h | 89 ++++++++-
> tools/perf/util/machine.c | 1 +
> tools/perf/util/stat.c | 5 +-
> tools/perf/util/stat.h | 3 +-
> 42 files changed, 789 insertions(+), 229 deletions(-)
> create mode 100644 tools/perf/tests/genelf.c
Pulled, thanks a lot Arnaldo!
Ingo
^ permalink raw reply [flat|nested] 27+ messages in thread