[PATCH 18/19] perf record: add an option to force per-cpu mmaps

[Adrian Hunter <adrian.hunter@intel.com>]

By default, when tasks are specified (i.e. -p, -t
or -u options) per-thread mmaps are created.  Add
an option to override that and force per-cpu mmaps.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 tools/perf/Documentation/perf-record.txt | 6 ++++++
 tools/perf/builtin-record.c              | 2 ++
 tools/perf/util/evlist.c                 | 4 +++-
 tools/perf/util/evsel.c                  | 4 ++--
 tools/perf/util/target.h                 | 1 +
 5 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index f10ab63..2ea6685 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -189,6 +189,12 @@ 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.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index d269dfa..fb09430 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -890,6 +890,8 @@ 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_END()
 };
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 18784dc..ffcccdd 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -791,7 +791,9 @@ int perf_evlist__create_maps(struct perf_evlist *evlist,
 	if (evlist->threads == NULL)
 		return -1;
 
-	if (perf_target__has_task(target))
+	if (target->force_per_cpu)
+		evlist->cpus = cpu_map__new(target->cpu_list);
+	else if (perf_target__has_task(target))
 		evlist->cpus = cpu_map__dummy_new();
 	else if (!perf_target__has_cpu(target) && !target->uses_mmap)
 		evlist->cpus = cpu_map__dummy_new();
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e09c7e6..f1839b0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -645,7 +645,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 		}
 	}
 
-	if (perf_target__has_cpu(&opts->target))
+	if (perf_target__has_cpu(&opts->target) || opts->target.force_per_cpu)
 		perf_evsel__set_sample_bit(evsel, CPU);
 
 	if (opts->period)
@@ -653,7 +653,7 @@ void perf_evsel__config(struct perf_evsel *evsel,
 
 	if (!perf_missing_features.sample_id_all &&
 	    (opts->sample_time || !opts->no_inherit ||
-	     perf_target__has_cpu(&opts->target)))
+	     perf_target__has_cpu(&opts->target) || opts->target.force_per_cpu))
 		perf_evsel__set_sample_bit(evsel, TIME);
 
 	if (opts->raw_samples) {
diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
index a4be857..6d7efbd 100644
--- a/tools/perf/util/target.h
+++ b/tools/perf/util/target.h
@@ -12,6 +12,7 @@ struct perf_target {
 	uid_t	     uid;
 	bool	     system_wide;
 	bool	     uses_mmap;
+	bool	     force_per_cpu;
 };
 
 enum perf_target_errno {
-- 
1.7.11.7