perf tools: Add support for pinned modifier

This commit adds support for a new modifier "D", which requests that the
event, or group of events, be pinned to the PMU.

The "p" modifier is already taken for precise, and "P" may be used in
future to mean "fully precise".

So we use "D", which stands for pinneD - and looks like a padlock, or if
you're using the ":D" syntax perf smiles at you.

This is an oft-requested feature from our HW folks, who want to be able
to run a large number of events, but also want 100% accurate results for
instructions per cycle.

Comparison of results with and without pinning:

$ perf stat -e '{cycles,instructions}:D' -e cycles,instructions,...

  79,590,480,683 cycles         #  0.000 GHz
 166,123,716,524 instructions   #  2.09  insns per cycle
                                #  0.11  stalled cycles per insn

  79,352,134,463 cycles         #  0.000 GHz                     [11.11%]
 165,178,301,818 instructions   #  2.08  insns per cycle
                                #  0.11  stalled cycles per insn [11.13%]

As you can see although perf does a very good job of scaling the values
in the non-pinned case, there is some small discrepancy.

The patch is fairly straight forward, the one detail is that we need to
make sure we only request pinning for the group leader when we have a
group.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Jiri Olsa <jolsa@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1375795686-4226-1-git-send-email-michael@ellerman.id.au
[ Use perf_evsel__is_group_leader instead of open coded equivalent, as
  suggested by Jiri Olsa ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

3 files changed, 13 insertions, 2 deletions

diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index eb03f063f0a2..6fce6a622206 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -30,6 +30,7 @@ counted. The following modifiers exist:
  H - host counting (not in KVM guests)
  p - precise level
  S - read sample value (PERF_SAMPLE_READ)
+ D - pin the event to the PMU
 
 The 'p' modifier can be used for specifying how precise the instruction
 address should be. The 'p' modifier can be specified multiple times:
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index dba877dc9482..9cba92386a82 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -688,6 +688,7 @@ struct event_modifier {
         int precise;
         int exclude_GH;
         int sample_read;
+        int pinned;
 };
 
 static int get_event_modifier(struct event_modifier *mod, char *str,
@@ -700,6 +701,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
         int eG = evsel ? evsel->attr.exclude_guest : 0;
         int precise = evsel ? evsel->attr.precise_ip : 0;
         int sample_read = 0;
+        int pinned = evsel ? evsel->attr.pinned : 0;
 
         int exclude = eu | ek | eh;
         int exclude_GH = evsel ? evsel->exclude_GH : 0;
@@ -734,6 +736,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
                                 eG = 1;
                 } else if (*str == 'S') {
                         sample_read = 1;
+                } else if (*str == 'D') {
+                        pinned = 1;
                 } else
                         break;
 
@@ -761,6 +765,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str,
         mod->precise = precise;
         mod->exclude_GH = exclude_GH;
         mod->sample_read = sample_read;
+        mod->pinned = pinned;
+
         return 0;
 }
 
@@ -773,7 +779,7 @@ static int check_modifier(char *str)
         char *p = str;
 
         /* The sizeof includes 0 byte as well. */
-        if (strlen(str) > (sizeof("ukhGHpppS") - 1))
+        if (strlen(str) > (sizeof("ukhGHpppSD") - 1))
                 return -1;
 
         while (*p) {
@@ -812,6 +818,9 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add)
                 evsel->attr.exclude_guest  = mod.eG;
                 evsel->exclude_GH          = mod.exclude_GH;
                 evsel->sample_read         = mod.sample_read;
+
+                if (perf_evsel__is_group_leader(evsel))
+                        evsel->attr.pinned = mod.pinned;
         }
 
         return 0;
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index b36115fe416a..0790452658b3 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -82,7 +82,8 @@ num_hex		0x[a-fA-F0-9]+
 num_raw_hex     [a-fA-F0-9]+
 name            [a-zA-Z_*?][a-zA-Z0-9_*?]*
 name_minus      [a-zA-Z_*?][a-zA-Z0-9\-_*?]*
-modifier_event  [ukhpGHS]+
+/* If you add a modifier you need to update check_modifier() */
+modifier_event  [ukhpGHSD]+
 modifier_bp     [rwx]{1,3}
 
 %%