perf record: Make per-cpu mmaps the default.

This affects the -p, -t and -u options that previously defaulted to
per-thread mmaps.

Consequently add an option to select per-thread mmaps to support the old
behaviour.

Note that per-thread can be used with a workload-only (i.e. none of -p,
-t, -u, -a or -C is selected) to get a per-thread mmap with no
inheritance.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/5286271D.3020808@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

7 files changed, 29 insertions, 14 deletions

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 43b42c4f4a91..6ac867e7667f 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -201,11 +201,11 @@ abort events and some memory events in precise mode on modern Intel CPUs.
 --transaction::
 Record transaction flags for transaction related events.
 
---force-per-cpu::
-Force the use of per-cpu mmaps.  By default, when tasks are specified (i.e. -p,
--t or -u options) per-thread mmaps are created.  This option overrides that and
-forces per-cpu mmaps.  A side-effect of that is that inheritance is
-automatically enabled.  Add the -i option also to disable inheritance.
+--per-thread::
+Use per-thread mmaps.  By default per-cpu mmaps are created.  This option
+overrides that and uses per-thread mmaps.  A side-effect of that is that
+inheritance is automatically disabled.  --per-thread is ignored with a warning
+if combined with -a or -C options.
 
 SEE ALSO
 --------
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 7c8020a32784..f5b18b8fe8c9 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -800,6 +800,7 @@ static struct perf_record record = {
                 .freq                = 4000,
                 .target              = {
                         .uses_mmap   = true,
+                        .default_per_cpu = true,
                 },
         },
 };
@@ -888,8 +889,8 @@ const struct option record_options[] = {
                     "sample by weight (on special events only)"),
         OPT_BOOLEAN(0, "transaction", &record.opts.sample_transaction,
                     "sample transaction flags (special events only)"),
-        OPT_BOOLEAN(0, "force-per-cpu", &record.opts.target.force_per_cpu,
-                    "force the use of per-cpu mmaps"),
+        OPT_BOOLEAN(0, "per-thread", &record.opts.target.per_thread,
+                    "use per-thread mmaps"),
         OPT_END()
 };
 
diff --git a/tools/perf/tests/attr/test-record-no-inherit b/tools/perf/tests/attr/test-record-no-inherit
index 9079a25cd643..44edcb2edcd5 100644
--- a/tools/perf/tests/attr/test-record-no-inherit
+++ b/tools/perf/tests/attr/test-record-no-inherit
@@ -3,5 +3,5 @@ command = record
 args    = -i kill >/dev/null 2>&1
 
 [event:base-record]
-sample_type=259
+sample_type=263
 inherit=0
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index bbc746aa5716..76fa76431329 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -819,8 +819,10 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
         if (evlist->threads == NULL)
                 return -1;
 
-        if (target->force_per_cpu)
-                evlist->cpus = cpu_map__new(target->cpu_list);
+        if (target->default_per_cpu)
+                evlist->cpus = target->per_thread ?
+                                        cpu_map__dummy_new() :
+                                        cpu_map__new(target->cpu_list);
         else if (target__has_task(target))
                 evlist->cpus = cpu_map__dummy_new();
         else if (!target__has_cpu(target) && !target->uses_mmap)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index dad64926170f..b5fe7f9b2e15 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -574,6 +574,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
         struct perf_evsel *leader = evsel->leader;
         struct perf_event_attr *attr = &evsel->attr;
         int track = !evsel->idx; /* only the first counter needs these */
+        bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread;
 
         attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1;
         attr->inherit       = !opts->no_inherit;
@@ -647,7 +648,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
                 }
         }
 
-        if (target__has_cpu(&opts->target) || opts->target.force_per_cpu)
+        if (target__has_cpu(&opts->target))
                 perf_evsel__set_sample_bit(evsel, CPU);
 
         if (opts->period)
@@ -655,7 +656,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 
         if (!perf_missing_features.sample_id_all &&
             (opts->sample_time || !opts->no_inherit ||
-             target__has_cpu(&opts->target) || opts->target.force_per_cpu))
+             target__has_cpu(&opts->target) || per_cpu))
                 perf_evsel__set_sample_bit(evsel, TIME);
 
         if (opts->raw_samples) {
diff --git a/tools/perf/util/target.c b/tools/perf/util/target.c
index 3c778a07b7cc..e74c5963dc7a 100644
--- a/tools/perf/util/target.c
+++ b/tools/perf/util/target.c
@@ -55,6 +55,13 @@ enum target_errno target__validate(struct target *target)
                         ret = TARGET_ERRNO__UID_OVERRIDE_SYSTEM;
         }
 
+        /* THREAD and SYSTEM/CPU are mutually exclusive */
+        if (target->per_thread && (target->system_wide || target->cpu_list)) {
+                target->per_thread = false;
+                if (ret == TARGET_ERRNO__SUCCESS)
+                        ret = TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD;
+        }
+
         return ret;
 }
 
@@ -100,6 +107,7 @@ static const char *target__error_str[] = {
         "UID switch overriding CPU",
         "PID/TID switch overriding SYSTEM",
         "UID switch overriding SYSTEM",
+        "SYSTEM/CPU switch overriding PER-THREAD",
         "Invalid User: %s",
         "Problems obtaining information for user %s",
 };
@@ -131,7 +139,8 @@ int target__strerror(struct target *target, int errnum,
         msg = target__error_str[idx];
 
         switch (errnum) {
-        case TARGET_ERRNO__PID_OVERRIDE_CPU ... TARGET_ERRNO__UID_OVERRIDE_SYSTEM:
+        case TARGET_ERRNO__PID_OVERRIDE_CPU ...
+             TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD:
                 snprintf(buf, buflen, "%s", msg);
                 break;
 
diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
index 2d0c50690892..31dd2e9a27d0 100644
--- a/tools/perf/util/target.h
+++ b/tools/perf/util/target.h
@@ -12,7 +12,8 @@ struct target {
         uid_t        uid;
         bool         system_wide;
         bool         uses_mmap;
-        bool         force_per_cpu;
+        bool         default_per_cpu;
+        bool         per_thread;
 };
 
 enum target_errno {
@@ -33,6 +34,7 @@ enum target_errno {
         TARGET_ERRNO__UID_OVERRIDE_CPU,
         TARGET_ERRNO__PID_OVERRIDE_SYSTEM,
         TARGET_ERRNO__UID_OVERRIDE_SYSTEM,
+        TARGET_ERRNO__SYSTEM_OVERRIDE_THREAD,
 
         /* for target__parse_uid() */
         TARGET_ERRNO__INVALID_UID,