* [PATCH 01/11] tools headers: Follow the upstream UAPI header version 100% differ from the kernel
2017-11-24 15:02 [GIT PULL 00/11] perf/core improvements and fixes Arnaldo Carvalho de Melo
@ 2017-11-24 15:02 ` Arnaldo Carvalho de Melo
2017-11-24 15:02 ` [PATCH 02/11] perf bench numa: Fixup discontiguous/sparse numa nodes Arnaldo Carvalho de Melo
` (9 subsequent siblings)
10 siblings, 0 replies; 12+ messages in thread
From: Arnaldo Carvalho de Melo @ 2017-11-24 15:02 UTC (permalink / raw)
To: Ingo Molnar
Cc: linux-kernel, linux-perf-users, Adrian Hunter, Arnaldo Carvalho de Melo
From: Ingo Molnar <mingo@kernel.org>
Remove this from check-headers.sh:
opts="--ignore-blank-lines --ignore-space-change"
as the easiest policy is to just follow the upstream UAPI header version 100%.
Pure space-only changes are comparatively rare.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Link: http://lkml.kernel.org/r/20171121084111.y6p5zwqso2cbms5s@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
| 1 -
1 file changed, 1 deletion(-)
--git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 77406d25e521..e66a8a7bcced 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -45,7 +45,6 @@ include/uapi/asm-generic/mman-common.h
check () {
file=$1
- opts="--ignore-blank-lines --ignore-space-change"
shift
while [ -n "$*" ]; do
--
2.13.6
^ permalink raw reply related [flat|nested] 12+ messages in thread
* [PATCH 02/11] perf bench numa: Fixup discontiguous/sparse numa nodes
2017-11-24 15:02 [GIT PULL 00/11] perf/core improvements and fixes Arnaldo Carvalho de Melo
2017-11-24 15:02 ` [PATCH 01/11] tools headers: Follow the upstream UAPI header version 100% differ from the kernel Arnaldo Carvalho de Melo
@ 2017-11-24 15:02 ` Arnaldo Carvalho de Melo
2017-11-24 15:02 ` [PATCH 03/11] perf test: Disable test cases 19 and 20 on s390x Arnaldo Carvalho de Melo
` (8 subsequent siblings)
10 siblings, 0 replies; 12+ messages in thread
From: Arnaldo Carvalho de Melo @ 2017-11-24 15:02 UTC (permalink / raw)
To: Ingo Molnar
Cc: linux-kernel, linux-perf-users, Satheesh Rajendran,
Balamuruhan S, Arnaldo Carvalho de Melo
From: Satheesh Rajendran <sathnaga@linux.vnet.ibm.com>
Certain systems are designed to have sparse/discontiguous nodes. On
such systems, 'perf bench numa' hangs, shows wrong number of nodes and
shows values for non-existent nodes. Handle this by only taking nodes
that are exposed by kernel to userspace.
Signed-off-by: Satheesh Rajendran <sathnaga@linux.vnet.ibm.com>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1edbcd353c009e109e93d78f2f46381930c340fe.1511368645.git.sathnaga@linux.vnet.ibm.com
Signed-off-by: Balamuruhan S <bala24@linux.vnet.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/bench/numa.c | 56 ++++++++++++++++++++++++++++++++++++++++++++-----
1 file changed, 51 insertions(+), 5 deletions(-)
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index d95fdcc26f4b..944070e98a2c 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -216,6 +216,47 @@ static const char * const numa_usage[] = {
NULL
};
+/*
+ * To get number of numa nodes present.
+ */
+static int nr_numa_nodes(void)
+{
+ int i, nr_nodes = 0;
+
+ for (i = 0; i < g->p.nr_nodes; i++) {
+ if (numa_bitmask_isbitset(numa_nodes_ptr, i))
+ nr_nodes++;
+ }
+
+ return nr_nodes;
+}
+
+/*
+ * To check if given numa node is present.
+ */
+static int is_node_present(int node)
+{
+ return numa_bitmask_isbitset(numa_nodes_ptr, node);
+}
+
+/*
+ * To check given numa node has cpus.
+ */
+static bool node_has_cpus(int node)
+{
+ struct bitmask *cpu = numa_allocate_cpumask();
+ unsigned int i;
+
+ if (cpu && !numa_node_to_cpus(node, cpu)) {
+ for (i = 0; i < cpu->size; i++) {
+ if (numa_bitmask_isbitset(cpu, i))
+ return true;
+ }
+ }
+
+ return false; /* lets fall back to nocpus safely */
+}
+
static cpu_set_t bind_to_cpu(int target_cpu)
{
cpu_set_t orig_mask, mask;
@@ -244,12 +285,12 @@ static cpu_set_t bind_to_cpu(int target_cpu)
static cpu_set_t bind_to_node(int target_node)
{
- int cpus_per_node = g->p.nr_cpus/g->p.nr_nodes;
+ int cpus_per_node = g->p.nr_cpus / nr_numa_nodes();
cpu_set_t orig_mask, mask;
int cpu;
int ret;
- BUG_ON(cpus_per_node*g->p.nr_nodes != g->p.nr_cpus);
+ BUG_ON(cpus_per_node * nr_numa_nodes() != g->p.nr_cpus);
BUG_ON(!cpus_per_node);
ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
@@ -649,7 +690,7 @@ static int parse_setup_node_list(void)
int i;
for (i = 0; i < mul; i++) {
- if (t >= g->p.nr_tasks) {
+ if (t >= g->p.nr_tasks || !node_has_cpus(bind_node)) {
printf("\n# NOTE: ignoring bind NODEs starting at NODE#%d\n", bind_node);
goto out;
}
@@ -964,6 +1005,8 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
sum = 0;
for (node = 0; node < g->p.nr_nodes; node++) {
+ if (!is_node_present(node))
+ continue;
nr = nodes[node];
nr_min = min(nr, nr_min);
nr_max = max(nr, nr_max);
@@ -984,8 +1027,11 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
process_groups = 0;
for (node = 0; node < g->p.nr_nodes; node++) {
- int processes = count_node_processes(node);
+ int processes;
+ if (!is_node_present(node))
+ continue;
+ processes = count_node_processes(node);
nr = nodes[node];
tprintf(" %2d/%-2d", nr, processes);
@@ -1291,7 +1337,7 @@ static void print_summary(void)
printf("\n ###\n");
printf(" # %d %s will execute (on %d nodes, %d CPUs):\n",
- g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", g->p.nr_nodes, g->p.nr_cpus);
+ g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", nr_numa_nodes(), g->p.nr_cpus);
printf(" # %5dx %5ldMB global shared mem operations\n",
g->p.nr_loops, g->p.bytes_global/1024/1024);
printf(" # %5dx %5ldMB process shared mem operations\n",
--
2.13.6
^ permalink raw reply related [flat|nested] 12+ messages in thread
* [PATCH 03/11] perf test: Disable test cases 19 and 20 on s390x
2017-11-24 15:02 [GIT PULL 00/11] perf/core improvements and fixes Arnaldo Carvalho de Melo
2017-11-24 15:02 ` [PATCH 01/11] tools headers: Follow the upstream UAPI header version 100% differ from the kernel Arnaldo Carvalho de Melo
2017-11-24 15:02 ` [PATCH 02/11] perf bench numa: Fixup discontiguous/sparse numa nodes Arnaldo Carvalho de Melo
@ 2017-11-24 15:02 ` Arnaldo Carvalho de Melo
2017-11-24 15:02 ` [PATCH 04/11] perf test: Fix test 21 for s390x Arnaldo Carvalho de Melo
` (7 subsequent siblings)
10 siblings, 0 replies; 12+ messages in thread
From: Arnaldo Carvalho de Melo @ 2017-11-24 15:02 UTC (permalink / raw)
To: Ingo Molnar
Cc: linux-kernel, linux-perf-users, Thomas Richter,
Martin Schwidefsky, Arnaldo Carvalho de Melo
From: Thomas Richter <tmricht@linux.vnet.ibm.com>
The s390x CPU sampling and measurement facilities do not support perf
events of type PERF_TYPE_BREAKPOINT. The test cases are executed and
fail with -ENOENT due to missing hardware support.
Disable the execution of both test cases based on a
platform check. This is the same approach as done for
PowerPC.
Signed-off-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
LPU-Reference: 20171123074623.20817-1-tmricht@linux.vnet.ibm.com
Link: https://lkml.kernel.org/n/tip-uqvoy6a1tsu8jddo5jjg4h85@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/tests/bp_signal.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index 335b695f4970..a467615c5a0e 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -296,7 +296,7 @@ bool test__bp_signal_is_supported(void)
* instruction breakpoint using the perf event interface.
* Once it's there we can release this.
*/
-#ifdef __powerpc__
+#if defined(__powerpc__) || defined(__s390x__)
return false;
#else
return true;
--
2.13.6
^ permalink raw reply related [flat|nested] 12+ messages in thread
* [PATCH 04/11] perf test: Fix test 21 for s390x
2017-11-24 15:02 [GIT PULL 00/11] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (2 preceding siblings ...)
2017-11-24 15:02 ` [PATCH 03/11] perf test: Disable test cases 19 and 20 on s390x Arnaldo Carvalho de Melo
@ 2017-11-24 15:02 ` Arnaldo Carvalho de Melo
2017-11-24 15:02 ` [PATCH 05/11] perf record: Synthesize unit/scale/... in event update Arnaldo Carvalho de Melo
` (6 subsequent siblings)
10 siblings, 0 replies; 12+ messages in thread
From: Arnaldo Carvalho de Melo @ 2017-11-24 15:02 UTC (permalink / raw)
To: Ingo Molnar
Cc: linux-kernel, linux-perf-users, Thomas Richter,
Martin Schwidefsky, Arnaldo Carvalho de Melo
From: Thomas Richter <tmricht@linux.vnet.ibm.com>
Test case 21 (Number of exit events of a simple workload) fails on
s390x. The reason is the invalid sample frequency supplied for this
test. On s390x the minimum sample frequency is much higher (see output
of /proc/service_levels).
Supply a save sample frequency value for s390x to fix this. The value
will be adjusted by the s390x CPUMF frequency convertion function to a
value well below the sysctl kernel.perf_event_max_sample_rate value.
Signed-off-by: Thomas Richter <tmricht@linux.vnet.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
LPU-Reference: 20171123114611.93397-1-tmricht@linux.vnet.ibm.com
Link: https://lkml.kernel.org/n/tip-1ynblyhi1n81idpido59nt1y@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/tests/task-exit.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 98c098475e71..5d06ac81f7f1 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -84,7 +84,11 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
evsel = perf_evlist__first(evlist);
evsel->attr.task = 1;
+#ifdef __s390x__
+ evsel->attr.sample_freq = 1000000;
+#else
evsel->attr.sample_freq = 1;
+#endif
evsel->attr.inherit = 0;
evsel->attr.watermark = 0;
evsel->attr.wakeup_events = 1;
--
2.13.6
^ permalink raw reply related [flat|nested] 12+ messages in thread
* [PATCH 05/11] perf record: Synthesize unit/scale/... in event update
2017-11-24 15:02 [GIT PULL 00/11] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (3 preceding siblings ...)
2017-11-24 15:02 ` [PATCH 04/11] perf test: Fix test 21 for s390x Arnaldo Carvalho de Melo
@ 2017-11-24 15:02 ` Arnaldo Carvalho de Melo
2017-11-24 15:02 ` [PATCH 06/11] perf record: Synthesize thread map and cpu map Arnaldo Carvalho de Melo
` (5 subsequent siblings)
10 siblings, 0 replies; 12+ messages in thread
From: Arnaldo Carvalho de Melo @ 2017-11-24 15:02 UTC (permalink / raw)
To: Ingo Molnar
Cc: linux-kernel, linux-perf-users, Andi Kleen, Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
Move the code to synthesize event updates for scale/unit/cpus to a
common utility file, and use it both from stat and record.
This allows to access scale and other extra qualifiers from perf script.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20171117214300.32746-2-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-record.c | 9 ++++++
tools/perf/builtin-stat.c | 62 +++--------------------------------------
| 68 +++++++++++++++++++++++++++++++++++++++++++++
| 5 ++++
4 files changed, 86 insertions(+), 58 deletions(-)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 003255910c05..b92d6d67bca8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -372,6 +372,8 @@ static int record__open(struct record *rec)
ui__error("%s\n", msg);
goto out;
}
+
+ pos->supported = true;
}
if (perf_evlist__apply_filters(evlist, &pos)) {
@@ -784,6 +786,13 @@ static int record__synthesize(struct record *rec, bool tail)
perf_event__synthesize_guest_os, tool);
}
+ err = perf_event__synthesize_extra_attr(&rec->tool,
+ rec->evlist,
+ process_synthesized_event,
+ data->is_pipe);
+ if (err)
+ goto out;
+
err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
process_synthesized_event, opts->sample_address,
opts->proc_map_timeout, 1);
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 59af5a8419e2..a027b4712e48 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -458,19 +458,8 @@ static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *inf
workload_exec_errno = info->si_value.sival_int;
}
-static bool has_unit(struct perf_evsel *counter)
-{
- return counter->unit && *counter->unit;
-}
-
-static bool has_scale(struct perf_evsel *counter)
-{
- return counter->scale != 1;
-}
-
static int perf_stat_synthesize_config(bool is_pipe)
{
- struct perf_evsel *counter;
int err;
if (is_pipe) {
@@ -482,53 +471,10 @@ static int perf_stat_synthesize_config(bool is_pipe)
}
}
- /*
- * Synthesize other events stuff not carried within
- * attr event - unit, scale, name
- */
- evlist__for_each_entry(evsel_list, counter) {
- if (!counter->supported)
- continue;
-
- /*
- * Synthesize unit and scale only if it's defined.
- */
- if (has_unit(counter)) {
- err = perf_event__synthesize_event_update_unit(NULL, counter, process_synthesized_event);
- if (err < 0) {
- pr_err("Couldn't synthesize evsel unit.\n");
- return err;
- }
- }
-
- if (has_scale(counter)) {
- err = perf_event__synthesize_event_update_scale(NULL, counter, process_synthesized_event);
- if (err < 0) {
- pr_err("Couldn't synthesize evsel scale.\n");
- return err;
- }
- }
-
- if (counter->own_cpus) {
- err = perf_event__synthesize_event_update_cpus(NULL, counter, process_synthesized_event);
- if (err < 0) {
- pr_err("Couldn't synthesize evsel scale.\n");
- return err;
- }
- }
-
- /*
- * Name is needed only for pipe output,
- * perf.data carries event names.
- */
- if (is_pipe) {
- err = perf_event__synthesize_event_update_name(NULL, counter, process_synthesized_event);
- if (err < 0) {
- pr_err("Couldn't synthesize evsel name.\n");
- return err;
- }
- }
- }
+ err = perf_event__synthesize_extra_attr(NULL,
+ evsel_list,
+ process_synthesized_event,
+ is_pipe);
err = perf_event__synthesize_thread_map2(NULL, evsel_list->threads,
process_synthesized_event,
--git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 7c0e9d587bfa..5890e08e0754 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3258,6 +3258,74 @@ int perf_event__synthesize_attrs(struct perf_tool *tool,
return err;
}
+static bool has_unit(struct perf_evsel *counter)
+{
+ return counter->unit && *counter->unit;
+}
+
+static bool has_scale(struct perf_evsel *counter)
+{
+ return counter->scale != 1;
+}
+
+int perf_event__synthesize_extra_attr(struct perf_tool *tool,
+ struct perf_evlist *evsel_list,
+ perf_event__handler_t process,
+ bool is_pipe)
+{
+ struct perf_evsel *counter;
+ int err;
+
+ /*
+ * Synthesize other events stuff not carried within
+ * attr event - unit, scale, name
+ */
+ evlist__for_each_entry(evsel_list, counter) {
+ if (!counter->supported)
+ continue;
+
+ /*
+ * Synthesize unit and scale only if it's defined.
+ */
+ if (has_unit(counter)) {
+ err = perf_event__synthesize_event_update_unit(tool, counter, process);
+ if (err < 0) {
+ pr_err("Couldn't synthesize evsel unit.\n");
+ return err;
+ }
+ }
+
+ if (has_scale(counter)) {
+ err = perf_event__synthesize_event_update_scale(tool, counter, process);
+ if (err < 0) {
+ pr_err("Couldn't synthesize evsel counter.\n");
+ return err;
+ }
+ }
+
+ if (counter->own_cpus) {
+ err = perf_event__synthesize_event_update_cpus(tool, counter, process);
+ if (err < 0) {
+ pr_err("Couldn't synthesize evsel cpus.\n");
+ return err;
+ }
+ }
+
+ /*
+ * Name is needed only for pipe output,
+ * perf.data carries event names.
+ */
+ if (is_pipe) {
+ err = perf_event__synthesize_event_update_name(tool, counter, process);
+ if (err < 0) {
+ pr_err("Couldn't synthesize evsel name.\n");
+ return err;
+ }
+ }
+ }
+ return 0;
+}
+
int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct perf_evlist **pevlist)
--git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 29ccbfdf8724..91befc3b550d 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -107,6 +107,11 @@ int perf_event__synthesize_features(struct perf_tool *tool,
struct perf_evlist *evlist,
perf_event__handler_t process);
+int perf_event__synthesize_extra_attr(struct perf_tool *tool,
+ struct perf_evlist *evsel_list,
+ perf_event__handler_t process,
+ bool is_pipe);
+
int perf_event__process_feature(struct perf_tool *tool,
union perf_event *event,
struct perf_session *session);
--
2.13.6
^ permalink raw reply related [flat|nested] 12+ messages in thread
* [PATCH 06/11] perf record: Synthesize thread map and cpu map
2017-11-24 15:02 [GIT PULL 00/11] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (4 preceding siblings ...)
2017-11-24 15:02 ` [PATCH 05/11] perf record: Synthesize unit/scale/... in event update Arnaldo Carvalho de Melo
@ 2017-11-24 15:02 ` Arnaldo Carvalho de Melo
2017-11-24 15:02 ` [PATCH 07/11] perf script: Allow computing 'perf stat' style metrics Arnaldo Carvalho de Melo
` (4 subsequent siblings)
10 siblings, 0 replies; 12+ messages in thread
From: Arnaldo Carvalho de Melo @ 2017-11-24 15:02 UTC (permalink / raw)
To: Ingo Molnar
Cc: linux-kernel, linux-perf-users, Andi Kleen, Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
Synthesize the per attr thread maps and cpu maps in 'perf record'.
This allows code from 'perf stat' called from 'perf script' to access
this information.
Committer testing:
Please see the PERF_RECORD_THREAD_MAP and PERF_RECORD_CPU_MAP records,
added by this patch:
$ perf record sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.001 MB perf.data (8 samples) ]
$ perf report -D | grep PERF_RECORD_ | head
0xe8 [0x20]: PERF_RECORD_TIME_CONV: unhandled!
0x108 [0x28]: PERF_RECORD_THREAD_MAP nr: 1 thread: 23568
0x130 [0x18]: PERF_RECORD_CPU_MAP: 0-3
0 0x148 [0x28]: PERF_RECORD_COMM: perf:23568/23568
0x570 [0x8]: PERF_RECORD_FINISHED_ROUND
445342677837144 0x170 [0x28]: PERF_RECORD_COMM exec: sleep:23568/23568
445342677847339 0x198 [0x68]: PERF_RECORD_MMAP2 23568/23568: [0x564c943a4000(0x208000) @ 0 fd:00 3147174 2566255743]: r-xp /usr/bin/sleep
445342677862450 0x200 [0x70]: PERF_RECORD_MMAP2 23568/23568: [0x7f25968a8000(0x229000) @ 0 fd:00 3151761 2566238119]: r-xp /usr/lib64/ld-2.25.so
445342677873174 0x270 [0x60]: PERF_RECORD_MMAP2 23568/23568: [0x7ffc98176000(0x2000) @ 0 00:00 0 0]: r-xp [vdso]
445342677891928 0x2d0 [0x28]: PERF_RECORD_SAMPLE(IP, 0x4002): 23568/23568: 0xffffffff8f84c7e7 period: 1 addr: 0
$
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://lkml.kernel.org/r/20171117214300.32746-3-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-record.c | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index b92d6d67bca8..e304bc47fe9b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -793,6 +793,21 @@ static int record__synthesize(struct record *rec, bool tail)
if (err)
goto out;
+ err = perf_event__synthesize_thread_map2(&rec->tool, rec->evlist->threads,
+ process_synthesized_event,
+ NULL);
+ if (err < 0) {
+ pr_err("Couldn't synthesize thread map.\n");
+ return err;
+ }
+
+ err = perf_event__synthesize_cpu_map(&rec->tool, rec->evlist->cpus,
+ process_synthesized_event, NULL);
+ if (err < 0) {
+ pr_err("Couldn't synthesize cpu map.\n");
+ return err;
+ }
+
err = __machine__synthesize_threads(machine, tool, &opts->target, rec->evlist->threads,
process_synthesized_event, opts->sample_address,
opts->proc_map_timeout, 1);
--
2.13.6
^ permalink raw reply related [flat|nested] 12+ messages in thread
* [PATCH 07/11] perf script: Allow computing 'perf stat' style metrics
2017-11-24 15:02 [GIT PULL 00/11] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (5 preceding siblings ...)
2017-11-24 15:02 ` [PATCH 06/11] perf record: Synthesize thread map and cpu map Arnaldo Carvalho de Melo
@ 2017-11-24 15:02 ` Arnaldo Carvalho de Melo
2017-11-24 15:02 ` [PATCH 08/11] perf buildid-cache: Document for Node.js USDT Arnaldo Carvalho de Melo
` (3 subsequent siblings)
10 siblings, 0 replies; 12+ messages in thread
From: Arnaldo Carvalho de Melo @ 2017-11-24 15:02 UTC (permalink / raw)
To: Ingo Molnar
Cc: linux-kernel, linux-perf-users, Andi Kleen, Arnaldo Carvalho de Melo
From: Andi Kleen <ak@linux.intel.com>
Add support for computing 'perf stat' style metrics in 'perf script'.
When using leader sampling we can get metrics for each sampling period
by computing formulas over the values of the different group members.
This allows things like fine grained IPC tracking through sampling, much
more fine grained than with 'perf stat'.
The metric is still averaged over the sampling period, it is not just
for the sampling point.
This patch adds a new metric output field for 'perf script' that uses
the existing 'perf stat' metrics infrastructure to compute any metrics
supported by 'perf stat'.
For example to sample IPC:
$ perf record -e '{ref-cycles,cycles,instructions}:S' -a sleep 1
$ perf script -F metric,ip,sym,time,cpu,comm
...
alsa-sink-ALC32 [000] 42815.856074: 7fd65937d6cc [unknown]
alsa-sink-ALC32 [000] 42815.856074: 7fd65937d6cc [unknown]
alsa-sink-ALC32 [000] 42815.856074: 7fd65937d6cc [unknown]
alsa-sink-ALC32 [000] 42815.856074: metric: 0.13 insn per cycle
swapper [000] 42815.857961: ffffffff81655df0 __schedule
swapper [000] 42815.857961: ffffffff81655df0 __schedule
swapper [000] 42815.857961: ffffffff81655df0 __schedule
swapper [000] 42815.857961: metric: 0.23 insn per cycle
qemu-system-x86 [000] 42815.858130: ffffffff8165ad0e _raw_spin_unlock_irqrestore
qemu-system-x86 [000] 42815.858130: ffffffff8165ad0e _raw_spin_unlock_irqrestore
qemu-system-x86 [000] 42815.858130: ffffffff8165ad0e _raw_spin_unlock_irqrestore
qemu-system-x86 [000] 42815.858130: metric: 0.46 insn per cycle
:4972 [000] 42815.858312: ffffffffa080e5f2 vmx_vcpu_run
:4972 [000] 42815.858312: ffffffffa080e5f2 vmx_vcpu_run
:4972 [000] 42815.858312: ffffffffa080e5f2 vmx_vcpu_run
:4972 [000] 42815.858312: metric: 0.45 insn per cycle
TopDown:
This requires disabling SMT if you have it enabled, because SMT would
require sampling per core, which is not supported.
$ perf record -e '{ref-cycles,topdown-fetch-bubbles,\
topdown-recovery-bubbles,\
topdown-slots-retired,topdown-total-slots,\
topdown-slots-issued}:S' -a sleep 1
$ perf script --header -I -F cpu,ip,sym,event,metric,period
...
[000] 121108 ref-cycles: ffffffff8165222e copy_user_enhanced_fast_string
[000] 190350 topdown-fetch-bubbles: ffffffff8165222e copy_user_enhanced_fast_string
[000] 2055 topdown-recovery-bubbles: ffffffff8165222e copy_user_enhanced_fast_string
[000] 148729 topdown-slots-retired: ffffffff8165222e copy_user_enhanced_fast_string
[000] 144324 topdown-total-slots: ffffffff8165222e copy_user_enhanced_fast_string
[000] 160852 topdown-slots-issued: ffffffff8165222e copy_user_enhanced_fast_string
[000] metric: 33.0% frontend bound
[000] metric: 3.5% bad speculation
[000] metric: 25.8% retiring
[000] metric: 37.7% backend bound
[000] 112112 ref-cycles: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] 357222 topdown-fetch-bubbles: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] 3325 topdown-recovery-bubbles: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] 323553 topdown-slots-retired: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] 270507 topdown-total-slots: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] 341226 topdown-slots-issued: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] metric: 33.0% frontend bound
[000] metric: 2.9% bad speculation
[000] metric: 29.9% retiring
[000] metric: 34.2% backend bound
...
v2:
Use evsel->priv for new fields
Port to new base line, support fp output.
Handle stats in ->stats, not ->priv
Minor cleanups
Extra explanation about the use of the term 'averaging', from Andi in the
thread in the Link: tag below:
<quote Andi>
The current samples contains the sum of event counts for a sampling period.
EventA-1 EventA-2 EventA-3 EventA-4
EventB-1 EventB-2 EventC-3
gap with no events overflow
|-----------------------------------------------------------------|
period-start period-end
^ ^
| |
previous sample current sample
So EventA = 4 and EventB = 3 at the sample point
I generate a metric, let's say EventA / EventB. It applies to the whole period.
But the metric is over a longer time which does not have the same behavior. For
example the gap above doesn't have any events, while they are clustered at the
beginning and end of the sample period.
But we're summing everything together. The metric doesn't know that the gap is
different than the busy period.
That's what I'm trying to express with averaging.
</quote>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20171117214300.32746-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Documentation/perf-script.txt | 10 +++-
tools/perf/builtin-script.c | 97 +++++++++++++++++++++++++++++++-
tools/perf/util/metricgroup.c | 4 ++
3 files changed, 108 insertions(+), 3 deletions(-)
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 2811fcf684cb..974ceb12c7f3 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -117,7 +117,7 @@ OPTIONS
Comma separated list of fields to print. Options are:
comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn,
- brstackoff, callindent, insn, insnlen, synth, phys_addr.
+ brstackoff, callindent, insn, insnlen, synth, phys_addr, metric.
Field list can be prepended with the type, trace, sw or hw,
to indicate to which event type the field list applies.
e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace
@@ -217,6 +217,14 @@ OPTIONS
The brstackoff field will print an offset into a specific dso/binary.
+ With the metric option perf script can compute metrics for
+ sampling periods, similar to perf stat. This requires
+ specifying a group with multiple metrics with the :S option
+ for perf record. perf will sample on the first event, and
+ compute metrics for all the events in the group. Please note
+ that the metric computed is averaged over the whole sampling
+ period, not just for the sample point.
+
-k::
--vmlinux=<file>::
vmlinux pathname
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ee7c7aaaae72..39d8b55f0db3 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -22,6 +22,7 @@
#include "util/cpumap.h"
#include "util/thread_map.h"
#include "util/stat.h"
+#include "util/color.h"
#include "util/string2.h"
#include "util/thread-stack.h"
#include "util/time-utils.h"
@@ -90,6 +91,7 @@ enum perf_output_field {
PERF_OUTPUT_SYNTH = 1U << 25,
PERF_OUTPUT_PHYS_ADDR = 1U << 26,
PERF_OUTPUT_UREGS = 1U << 27,
+ PERF_OUTPUT_METRIC = 1U << 28,
};
struct output_option {
@@ -124,6 +126,7 @@ struct output_option {
{.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
{.str = "synth", .field = PERF_OUTPUT_SYNTH},
{.str = "phys_addr", .field = PERF_OUTPUT_PHYS_ADDR},
+ {.str = "metric", .field = PERF_OUTPUT_METRIC},
};
enum {
@@ -215,12 +218,20 @@ struct perf_evsel_script {
char *filename;
FILE *fp;
u64 samples;
+ /* For metric output */
+ u64 val;
+ int gnum;
};
+static inline struct perf_evsel_script *evsel_script(struct perf_evsel *evsel)
+{
+ return (struct perf_evsel_script *)evsel->priv;
+}
+
static struct perf_evsel_script *perf_evsel_script__new(struct perf_evsel *evsel,
struct perf_data *data)
{
- struct perf_evsel_script *es = malloc(sizeof(*es));
+ struct perf_evsel_script *es = zalloc(sizeof(*es));
if (es != NULL) {
if (asprintf(&es->filename, "%s.%s.dump", data->file.path, perf_evsel__name(evsel)) < 0)
@@ -228,7 +239,6 @@ static struct perf_evsel_script *perf_evsel_script__new(struct perf_evsel *evsel
es->fp = fopen(es->filename, "w");
if (es->fp == NULL)
goto out_free_filename;
- es->samples = 0;
}
return es;
@@ -1472,6 +1482,86 @@ static int data_src__fprintf(u64 data_src, FILE *fp)
return fprintf(fp, "%-*s", maxlen, out);
}
+struct metric_ctx {
+ struct perf_sample *sample;
+ struct thread *thread;
+ struct perf_evsel *evsel;
+ FILE *fp;
+};
+
+static void script_print_metric(void *ctx, const char *color,
+ const char *fmt,
+ const char *unit, double val)
+{
+ struct metric_ctx *mctx = ctx;
+
+ if (!fmt)
+ return;
+ perf_sample__fprintf_start(mctx->sample, mctx->thread, mctx->evsel,
+ mctx->fp);
+ fputs("\tmetric: ", mctx->fp);
+ if (color)
+ color_fprintf(mctx->fp, color, fmt, val);
+ else
+ printf(fmt, val);
+ fprintf(mctx->fp, " %s\n", unit);
+}
+
+static void script_new_line(void *ctx)
+{
+ struct metric_ctx *mctx = ctx;
+
+ perf_sample__fprintf_start(mctx->sample, mctx->thread, mctx->evsel,
+ mctx->fp);
+ fputs("\tmetric: ", mctx->fp);
+}
+
+static void perf_sample__fprint_metric(struct perf_script *script,
+ struct thread *thread,
+ struct perf_evsel *evsel,
+ struct perf_sample *sample,
+ FILE *fp)
+{
+ struct perf_stat_output_ctx ctx = {
+ .print_metric = script_print_metric,
+ .new_line = script_new_line,
+ .ctx = &(struct metric_ctx) {
+ .sample = sample,
+ .thread = thread,
+ .evsel = evsel,
+ .fp = fp,
+ },
+ .force_header = false,
+ };
+ struct perf_evsel *ev2;
+ static bool init;
+ u64 val;
+
+ if (!init) {
+ perf_stat__init_shadow_stats();
+ init = true;
+ }
+ if (!evsel->stats)
+ perf_evlist__alloc_stats(script->session->evlist, false);
+ if (evsel_script(evsel->leader)->gnum++ == 0)
+ perf_stat__reset_shadow_stats();
+ val = sample->period * evsel->scale;
+ perf_stat__update_shadow_stats(evsel,
+ val,
+ sample->cpu);
+ evsel_script(evsel)->val = val;
+ if (evsel_script(evsel->leader)->gnum == evsel->leader->nr_members) {
+ for_each_group_member (ev2, evsel->leader) {
+ perf_stat__print_shadow_stats(ev2,
+ evsel_script(ev2)->val,
+ sample->cpu,
+ &ctx,
+ NULL);
+ }
+ evsel_script(evsel->leader)->gnum = 0;
+ }
+}
+
static void process_event(struct perf_script *script,
struct perf_sample *sample, struct perf_evsel *evsel,
struct addr_location *al,
@@ -1559,6 +1649,9 @@ static void process_event(struct perf_script *script,
if (PRINT_FIELD(PHYS_ADDR))
fprintf(fp, "%16" PRIx64, sample->phys_addr);
fprintf(fp, "\n");
+
+ if (PRINT_FIELD(METRIC))
+ perf_sample__fprint_metric(script, thread, evsel, sample, fp);
}
static struct scripting_ops *scripting_ops;
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 0ddd9c199227..6fd709017bbc 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -38,6 +38,10 @@ struct metric_event *metricgroup__lookup(struct rblist *metric_events,
struct metric_event me = {
.evsel = evsel
};
+
+ if (!metric_events)
+ return NULL;
+
nd = rblist__find(metric_events, &me);
if (nd)
return container_of(nd, struct metric_event, nd);
--
2.13.6
^ permalink raw reply related [flat|nested] 12+ messages in thread
* [PATCH 08/11] perf buildid-cache: Document for Node.js USDT
2017-11-24 15:02 [GIT PULL 00/11] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (6 preceding siblings ...)
2017-11-24 15:02 ` [PATCH 07/11] perf script: Allow computing 'perf stat' style metrics Arnaldo Carvalho de Melo
@ 2017-11-24 15:02 ` Arnaldo Carvalho de Melo
2017-11-24 15:02 ` [PATCH 09/11] perf report: Fix -D output for user metadata events Arnaldo Carvalho de Melo
` (2 subsequent siblings)
10 siblings, 0 replies; 12+ messages in thread
From: Arnaldo Carvalho de Melo @ 2017-11-24 15:02 UTC (permalink / raw)
To: Ingo Molnar
Cc: linux-kernel, linux-perf-users, Hansuk Hong, Jiri Olsa,
Namhyung Kim, Arnaldo Carvalho de Melo
From: Hansuk Hong <flavono123@gmail.com>
Add a tip for Node.js USDT(User-Level Statically Defined Tracing) probes
in tips.txt
Signed-off-by: Hansuk Hong <flavono123@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/20171123160546.9722-1-flavono123@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Documentation/tips.txt | 1 +
1 file changed, 1 insertion(+)
diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
index db0ca3063eae..3dd1dbe28407 100644
--- a/tools/perf/Documentation/tips.txt
+++ b/tools/perf/Documentation/tips.txt
@@ -32,3 +32,4 @@ Order by the overhead of source file name and line number: perf report -s srclin
System-wide collection from all CPUs: perf record -a
Show current config key-value pairs: perf config --list
Show user configuration overrides: perf config --user --list
+To add Node.js USDT(User-Level Statically Defined Tracing): perf buildid-cache --add `which node`
--
2.13.6
^ permalink raw reply related [flat|nested] 12+ messages in thread
* [PATCH 09/11] perf report: Fix -D output for user metadata events
2017-11-24 15:02 [GIT PULL 00/11] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (7 preceding siblings ...)
2017-11-24 15:02 ` [PATCH 08/11] perf buildid-cache: Document for Node.js USDT Arnaldo Carvalho de Melo
@ 2017-11-24 15:02 ` Arnaldo Carvalho de Melo
2017-11-24 15:02 ` [PATCH 10/11] perf intel-pt: Improve build messages for files that differ from the kernel Arnaldo Carvalho de Melo
2017-11-24 15:02 ` [PATCH 11/11] perf intel-pt: Bring instruction decoder files into line with " Arnaldo Carvalho de Melo
10 siblings, 0 replies; 12+ messages in thread
From: Arnaldo Carvalho de Melo @ 2017-11-24 15:02 UTC (permalink / raw)
To: Ingo Molnar
Cc: linux-kernel, linux-perf-users, Arnaldo Carvalho de Melo,
Adrian Hunter, Andi Kleen, David Ahern, Jiri Olsa, Namhyung Kim,
Wang Nan, Thomas Gleixner
From: Arnaldo Carvalho de Melo <acme@redhat.com>
The PERF_RECORD_USER_ events are synthesized by the tool to assist in
processing the PERF_RECORD_ ones generated by the kernel, the printing
of that information doesn't come with a perf_sample structure, so, when
dumping the event fields using 'perf report -D' there were columns that
end up not being printed.
To tidy up a bit this, fake a perf_sample structure with zeroes to have
the missing columns printed and avoid the occasional surprise with that.
Before:
0 0x45b8 [0x68]: PERF_RECORD_MMAP -1/0: [0xffffffffc12ec000(0x4000) @ 0]: x /lib/modules/4.14.0+/kernel/fs/nls/nls_utf8.ko
0x4620 [0x28]: PERF_RECORD_THREAD_MAP nr: 1 thread: 27820
0x4648 [0x18]: PERF_RECORD_CPU_MAP: 0-3
0 0x4660 [0x28]: PERF_RECORD_COMM: perf:27820/27820
0x4a58 [0x8]: PERF_RECORD_FINISHED_ROUND
447723433020976 0x4688 [0x28]: PERF_RECORD_SAMPLE(IP, 0x4001): 27820/27820: 0xffffffff8f1b6d7a period: 1 addr: 0
After:
$ perf report -D | grep PERF_RECORD_ | head
0 0xe8 [0x20]: PERF_RECORD_TIME_CONV: unhandled!
0 0x108 [0x28]: PERF_RECORD_THREAD_MAP nr: 1 thread: 32555
0 0x130 [0x18]: PERF_RECORD_CPU_MAP: 0-3
0 0x148 [0x28]: PERF_RECORD_COMM: perf:32555/32555
0 0x4e8 [0x8]: PERF_RECORD_FINISHED_ROUND
448743409421205 0x170 [0x28]: PERF_RECORD_COMM exec: sleep:32555/32555
448743409431883 0x198 [0x68]: PERF_RECORD_MMAP2 32555/32555: [0x55e11d75a000(0x208000) @ 0 fd:00 3147174 2566255743]: r-xp /usr/bin/sleep
448743409443873 0x200 [0x70]: PERF_RECORD_MMAP2 32555/32555: [0x7f0ced316000(0x229000) @ 0 fd:00 3151761 2566238119]: r-xp /usr/lib64/ld-2.25.so
448743409454790 0x270 [0x60]: PERF_RECORD_MMAP2 32555/32555: [0x7ffe84f6d000(0x2000) @ 0 00:00 0 0]: r-xp [vdso]
448743409479500 0x2d0 [0x28]: PERF_RECORD_SAMPLE(IP, 0x4002): 32555/32555: 0xffffffff8f84c7e7 period: 1 addr: 0
$
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 9aefcab0de47 ("perf session: Consolidate the dump code")
Link: https://lkml.kernel.org/n/tip-todcu15x0cwgppkh1gi6uhru@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/session.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index df2857137908..54e30f1bcbd7 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1348,10 +1348,11 @@ static s64 perf_session__process_user_event(struct perf_session *session,
{
struct ordered_events *oe = &session->ordered_events;
struct perf_tool *tool = session->tool;
+ struct perf_sample sample = { .time = 0, };
int fd = perf_data__fd(session->data);
int err;
- dump_event(session->evlist, event, file_offset, NULL);
+ dump_event(session->evlist, event, file_offset, &sample);
/* These events are processed right away */
switch (event->header.type) {
--
2.13.6
^ permalink raw reply related [flat|nested] 12+ messages in thread
* [PATCH 10/11] perf intel-pt: Improve build messages for files that differ from the kernel
2017-11-24 15:02 [GIT PULL 00/11] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (8 preceding siblings ...)
2017-11-24 15:02 ` [PATCH 09/11] perf report: Fix -D output for user metadata events Arnaldo Carvalho de Melo
@ 2017-11-24 15:02 ` Arnaldo Carvalho de Melo
2017-11-24 15:02 ` [PATCH 11/11] perf intel-pt: Bring instruction decoder files into line with " Arnaldo Carvalho de Melo
10 siblings, 0 replies; 12+ messages in thread
From: Arnaldo Carvalho de Melo @ 2017-11-24 15:02 UTC (permalink / raw)
To: Ingo Molnar
Cc: linux-kernel, linux-perf-users, Adrian Hunter, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
Print file names of files that differ. For example, instead of:
Warning: Intel PT: x86 instruction decoder differs from kernel
print:
Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat.h' differs from latest version at 'arch/x86/include/asm/inat.h'
Reported-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Link: http://lkml.kernel.org/r/1511253326-22308-2-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/intel-pt-decoder/Build | 24 +++++++++++++++---------
1 file changed, 15 insertions(+), 9 deletions(-)
diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 10e0814bb8d2..1b704fbea9de 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -11,15 +11,21 @@ $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_table
$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
@(diff -I 2>&1 | grep -q 'option requires an argument' && \
- test -d ../../kernel -a -d ../../tools -a -d ../perf && (( \
- diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null && \
- diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null && \
- diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null && \
- diff -B util/intel-pt-decoder/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null && \
- diff -B -I'^#include' util/intel-pt-decoder/insn.h ../../arch/x86/include/asm/insn.h >/dev/null && \
- diff -B -I'^#include' util/intel-pt-decoder/inat.h ../../arch/x86/include/asm/inat.h >/dev/null && \
- diff -B -I'^#include' util/intel-pt-decoder/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) \
- || echo "Warning: Intel PT: x86 instruction decoder differs from kernel" >&2 )) || true
+ test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
+ ((diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null) || \
+ (echo "Warning: Intel PT: x86 instruction decoder C file at 'tools/perf/util/intel-pt-decoder/insn.c' differs from latest version at 'arch/x86/lib/insn.c'" >&2)) && \
+ ((diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null) || \
+ (echo "Warning: Intel PT: x86 instruction decoder C file at 'tools/perf/util/intel-pt-decoder/inat.c' differs from latest version at 'arch/x86/lib/inat.c'" >&2)) && \
+ ((diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null) || \
+ (echo "Warning: Intel PT: x86 instruction decoder map file at 'tools/perf/util/intel-pt-decoder/x86-opcode-map.txt' differs from latest version at 'arch/x86/lib/x86-opcode-map.txt'" >&2)) && \
+ ((diff -B util/intel-pt-decoder/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null) || \
+ (echo "Warning: Intel PT: x86 instruction decoder script at 'tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk' differs from latest version at 'arch/x86/tools/gen-insn-attr-x86.awk'" >&2)) && \
+ ((diff -B -I'^#include' util/intel-pt-decoder/insn.h ../../arch/x86/include/asm/insn.h >/dev/null) || \
+ (echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/insn.h' differs from latest version at 'arch/x86/include/asm/insn.h'" >&2)) && \
+ ((diff -B -I'^#include' util/intel-pt-decoder/inat.h ../../arch/x86/include/asm/inat.h >/dev/null) || \
+ (echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat.h' differs from latest version at 'arch/x86/include/asm/inat.h'" >&2)) && \
+ ((diff -B -I'^#include' util/intel-pt-decoder/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) || \
+ (echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat_types.h' differs from latest version at 'arch/x86/include/asm/inat_types.h'" >&2)))) || true
$(call rule_mkdir)
$(call if_changed_dep,cc_o_c)
--
2.13.6
^ permalink raw reply related [flat|nested] 12+ messages in thread
* [PATCH 11/11] perf intel-pt: Bring instruction decoder files into line with the kernel
2017-11-24 15:02 [GIT PULL 00/11] perf/core improvements and fixes Arnaldo Carvalho de Melo
` (9 preceding siblings ...)
2017-11-24 15:02 ` [PATCH 10/11] perf intel-pt: Improve build messages for files that differ from the kernel Arnaldo Carvalho de Melo
@ 2017-11-24 15:02 ` Arnaldo Carvalho de Melo
10 siblings, 0 replies; 12+ messages in thread
From: Arnaldo Carvalho de Melo @ 2017-11-24 15:02 UTC (permalink / raw)
To: Ingo Molnar
Cc: linux-kernel, linux-perf-users, Adrian Hunter, Arnaldo Carvalho de Melo
From: Adrian Hunter <adrian.hunter@intel.com>
There are just a few new defines which do not affect perf tools.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Link: http://lkml.kernel.org/r/1511253326-22308-3-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/intel-pt-decoder/inat.h | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/tools/perf/util/intel-pt-decoder/inat.h b/tools/perf/util/intel-pt-decoder/inat.h
index 125ecd2a300d..52dc8d911173 100644
--- a/tools/perf/util/intel-pt-decoder/inat.h
+++ b/tools/perf/util/intel-pt-decoder/inat.h
@@ -97,6 +97,16 @@
#define INAT_MAKE_GROUP(grp) ((grp << INAT_GRP_OFFS) | INAT_MODRM)
#define INAT_MAKE_IMM(imm) (imm << INAT_IMM_OFFS)
+/* Identifiers for segment registers */
+#define INAT_SEG_REG_IGNORE 0
+#define INAT_SEG_REG_DEFAULT 1
+#define INAT_SEG_REG_CS 2
+#define INAT_SEG_REG_SS 3
+#define INAT_SEG_REG_DS 4
+#define INAT_SEG_REG_ES 5
+#define INAT_SEG_REG_FS 6
+#define INAT_SEG_REG_GS 7
+
/* Attribute search APIs */
extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
--
2.13.6
^ permalink raw reply related [flat|nested] 12+ messages in thread