perf evsel: Don't set exclude_guest by default

Perf tool sets exclude_guest by default while calling perf_event_open().
Because IBS does not have filtering capability, it always gets rejected
by IBS PMU driver and thus perf falls back to non-precise sampling. Fix
it by not setting exclude_guest by default on AMD.

Before:
  $ sudo ./perf record -C 0 -vvv true |& grep precise
    precise_ip                       3
  decreasing precise_ip by one (2)
    precise_ip                       2
  decreasing precise_ip by one (1)
    precise_ip                       1
  decreasing precise_ip by one (0)

After:
  $ sudo ./perf record -C 0 -vvv true |& grep precise
    precise_ip                       3
  decreasing precise_ip by one (2)
    precise_ip                       2

Committer notes:

Fixup init to zero for perf_env in older compilers:

  arch/x86/util/evsel.c:15:26: error: missing field 'os_release' initializer [-Werror,-Wmissing-field-initializers]
          struct perf_env env = {0};
                                  ^

Committer notes:

Namhyung remarked:

  It'd be nice if it can cover explicit "-e cycles:pp" as well.

Ravi clarified:

  For explicit :pp modifier, evsel->precise_max does not get set and thus perf
  does not try with different attr->precise_ip values while exclude_guest set.
  So no issue with explicit :pp:

    $ sudo ./perf record -C 0 -e cycles:pp -vvv |& grep "precise_ip\|exclude_guest"
      precise_ip                       2
      exclude_guest                    1
      precise_ip                       2
      exclude_guest                    1
    switching off exclude_guest, exclude_host
      precise_ip                       2
    ^C

  Also, with :P modifier, evsel->precise_max gets set but exclude_guest does
  not and thus :P also works fine:

    $ sudo ./perf record -C 0 -e cycles:P -vvv |& grep "precise_ip\|exclude_guest"
      precise_ip                       3
    decreasing precise_ip by one (2)
      precise_ip                       2
    ^C

Reported-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20211103072112.32312-1-ravi.bangoria@amd.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c
index 2f733cdc8dbbe2946c923804fc3902a141e99a1f..ac2899a25b7a32cda59e251978ea01e2a92110a0 100644 (file)
--- a/tools/perf/arch/x86/util/evsel.c
+++ b/tools/perf/arch/x86/util/evsel.c
@@ -1,8 +1,31 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
+#include <stdlib.h>
 #include "util/evsel.h"
+#include "util/env.h"
+#include "linux/string.h"
 
 void arch_evsel__set_sample_weight(struct evsel *evsel)
 {
        evsel__set_sample_bit(evsel, WEIGHT_STRUCT);
 }
+
+void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr)
+{
+       struct perf_env env = { .total_mem = 0, } ;
+
+       if (!perf_env__cpuid(&env))
+               return;
+
+       /*
+        * On AMD, precise cycles event sampling internally uses IBS pmu.
+        * But IBS does not have filtering capabilities and perf by default
+        * sets exclude_guest = 1. This makes IBS pmu event init fail and
+        * thus perf ends up doing non-precise sampling. Avoid it by clearing
+        * exclude_guest.
+        */
+       if (env.cpuid && strstarts(env.cpuid, "AuthenticAMD"))
+               attr->exclude_guest = 0;
+
+       free(env.cpuid);
+}

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 3cc1f8fcf15ce3559ddf71b6c4dab04641736e87..ec967fb8d7d9f01d5416af7cc643040dd8c66168 100644 (file)
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -294,7 +294,7 @@ static bool perf_event_can_profile_kernel(void)
        return perf_event_paranoid_check(1);
 }
 
-struct evsel *evsel__new_cycles(bool precise, __u32 type, __u64 config)
+struct evsel *evsel__new_cycles(bool precise __maybe_unused, __u32 type, __u64 config)
 {
        struct perf_event_attr attr = {
                .type   = type,
@@ -305,18 +305,16 @@ struct evsel *evsel__new_cycles(bool precise, __u32 type, __u64 config)
 
        event_attr_init(&attr);
 
-       if (!precise)
-               goto new_event;
-
        /*
         * Now let the usual logic to set up the perf_event_attr defaults
         * to kick in when we return and before perf_evsel__open() is called.
         */
-new_event:
        evsel = evsel__new(&attr);
        if (evsel == NULL)
                goto out;
 
+       arch_evsel__fixup_new_cycles(&evsel->core.attr);
+
        evsel->precise_max = true;
 
        /* use asprintf() because free(evsel) assumes name is allocated */
@@ -1063,6 +1061,10 @@ void __weak arch_evsel__set_sample_weight(struct evsel *evsel)
        evsel__set_sample_bit(evsel, WEIGHT);
 }
 
+void __weak arch_evsel__fixup_new_cycles(struct perf_event_attr *attr __maybe_unused)
+{
+}
+
 /*
  * The enable_on_exec/disabled value strategy:
  *

diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index dcc87c2881b85b57eb4618a0bd6a0c4067c4c266..3ea687141afa68147ae7e285f6cffe4b6769aa3f 100644 (file)
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -283,6 +283,7 @@ void __evsel__reset_sample_bit(struct evsel *evsel, enum perf_event_sample_forma
 void evsel__set_sample_id(struct evsel *evsel, bool use_sample_identifier);
 
 void arch_evsel__set_sample_weight(struct evsel *evsel);
+void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr);
 
 int evsel__set_filter(struct evsel *evsel, const char *filter);
 int evsel__append_tp_filter(struct evsel *evsel, const char *filter);