perf tools: Add core support for sampling intr machine state regs

Add the infrastructure to setup, collect and report the interrupt
machine state regs which can be captured by the kernel.

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: cebbert.lkml@gmail.com
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Jean Pihet <jean.pihet@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Waiman Long <Waiman.Long@hp.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1411559322-16548-4-git-send-email-eranian@google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

5 files changed, 87 insertions, 6 deletions

diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 511c2831aa81..1dabb8553499 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -52,6 +52,7 @@ struct record_opts {
         bool         sample_weight;
         bool         sample_time;
         bool         period;
+        bool         sample_intr_regs;
         unsigned int freq;
         unsigned int mmap_pages;
         unsigned int user_freq;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 7be389735402..09b9e8d3fcf7 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -188,6 +188,7 @@ struct perf_sample {
         struct ip_callchain *callchain;
         struct branch_stack *branch_stack;
         struct regs_dump  user_regs;
+        struct regs_dump  intr_regs;
         struct stack_dump user_stack;
         struct sample_read read;
 };
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 12b4396c7175..34344ffa79ca 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -661,6 +661,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
         if (callchain_param.enabled && !evsel->no_aux_samples)
                 perf_evsel__config_callgraph(evsel);
 
+        if (opts->sample_intr_regs) {
+                attr->sample_regs_intr = PERF_REGS_MASK;
+                perf_evsel__set_sample_bit(evsel, REGS_INTR);
+        }
+
         if (target__has_cpu(&opts->target))
                 perf_evsel__set_sample_bit(evsel, CPU);
 
@@ -1037,6 +1042,7 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
         ret += PRINT_ATTR_X64(branch_sample_type);
         ret += PRINT_ATTR_X64(sample_regs_user);
         ret += PRINT_ATTR_U32(sample_stack_user);
+        ret += PRINT_ATTR_X64(sample_regs_intr);
 
         ret += fprintf(fp, "%.60s\n", graph_dotted_line);
 
@@ -1536,6 +1542,23 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
                 array++;
         }
 
+        data->intr_regs.abi = PERF_SAMPLE_REGS_ABI_NONE;
+        if (type & PERF_SAMPLE_REGS_INTR) {
+                OVERFLOW_CHECK_u64(array);
+                data->intr_regs.abi = *array;
+                array++;
+
+                if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {
+                        u64 mask = evsel->attr.sample_regs_intr;
+
+                        sz = hweight_long(mask) * sizeof(u64);
+                        OVERFLOW_CHECK(array, sz, max_size);
+                        data->intr_regs.mask = mask;
+                        data->intr_regs.regs = (u64 *)array;
+                        array = (void *)array + sz;
+                }
+        }
+
         return 0;
 }
 
@@ -1631,6 +1654,16 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
         if (type & PERF_SAMPLE_TRANSACTION)
                 result += sizeof(u64);
 
+        if (type & PERF_SAMPLE_REGS_INTR) {
+                if (sample->intr_regs.abi) {
+                        result += sizeof(u64);
+                        sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+                        result += sz;
+                } else {
+                        result += sizeof(u64);
+                }
+        }
+
         return result;
 }
 
@@ -1809,6 +1842,17 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
                 array++;
         }
 
+        if (type & PERF_SAMPLE_REGS_INTR) {
+                if (sample->intr_regs.abi) {
+                        *array++ = sample->intr_regs.abi;
+                        sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+                        memcpy(array, sample->intr_regs.regs, sz);
+                        array = (void *)array + sz;
+                } else {
+                        *array++ = 0;
+                }
+        }
+
         return 0;
 }
 
@@ -1938,7 +1982,7 @@ static int sample_type__fprintf(FILE *fp, bool *first, u64 value)
                 bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU),
                 bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
                 bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
-                bit_name(IDENTIFIER),
+                bit_name(IDENTIFIER), bit_name(REGS_INTR),
                 { .name = NULL, }
         };
 #undef bit_name
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 76442caca37e..05fab7a188dc 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2143,6 +2143,7 @@ static const int attr_file_abi_sizes[] = {
         [1] = PERF_ATTR_SIZE_VER1,
         [2] = PERF_ATTR_SIZE_VER2,
         [3] = PERF_ATTR_SIZE_VER3,
+        [4] = PERF_ATTR_SIZE_VER4,
         0,
 };
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f4478ce72fdb..6ac62ae6b8fa 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -592,15 +592,46 @@ static void regs_dump__printf(u64 mask, u64 *regs)
         }
 }
 
+static const char *regs_abi[] = {
+        [PERF_SAMPLE_REGS_ABI_NONE] = "none",
+        [PERF_SAMPLE_REGS_ABI_32] = "32-bit",
+        [PERF_SAMPLE_REGS_ABI_64] = "64-bit",
+};
+
+static inline const char *regs_dump_abi(struct regs_dump *d)
+{
+        if (d->abi > PERF_SAMPLE_REGS_ABI_64)
+                return "unknown";
+
+        return regs_abi[d->abi];
+}
+
+static void regs__printf(const char *type, struct regs_dump *regs)
+{
+        u64 mask = regs->mask;
+
+        printf("... %s regs: mask 0x%" PRIx64 " ABI %s\n",
+               type,
+               mask,
+               regs_dump_abi(regs));
+
+        regs_dump__printf(mask, regs->regs);
+}
+
 static void regs_user__printf(struct perf_sample *sample)
 {
         struct regs_dump *user_regs = &sample->user_regs;
 
-        if (user_regs->regs) {
-                u64 mask = user_regs->mask;
-                printf("... user regs: mask 0x%" PRIx64 "\n", mask);
-                regs_dump__printf(mask, user_regs->regs);
-        }
+        if (user_regs->regs)
+                regs__printf("user", user_regs);
+}
+
+static void regs_intr__printf(struct perf_sample *sample)
+{
+        struct regs_dump *intr_regs = &sample->intr_regs;
+
+        if (intr_regs->regs)
+                regs__printf("intr", intr_regs);
 }
 
 static void stack_user__printf(struct stack_dump *dump)
@@ -699,6 +730,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
         if (sample_type & PERF_SAMPLE_REGS_USER)
                 regs_user__printf(sample);
 
+        if (sample_type & PERF_SAMPLE_REGS_INTR)
+                regs_intr__printf(sample);
+
         if (sample_type & PERF_SAMPLE_STACK_USER)
                 stack_user__printf(&sample->user_stack);