Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "The main updates in this cycle were:

   - Lots of perf tooling changes too voluminous to list (big perf trace
     and perf stat improvements, lots of libtraceevent reorganization,
     etc.), so I'll list the authors and refer to the changelog for
     details:

       Benjamin Peterson, Jérémie Galarneau, Kim Phillips, Peter
       Zijlstra, Ravi Bangoria, Sangwon Hong, Sean V Kelley, Steven
       Rostedt, Thomas Gleixner, Ding Xiang, Eduardo Habkost, Thomas
       Richter, Andi Kleen, Sanskriti Sharma, Adrian Hunter, Tzvetomir
       Stoyanov, Arnaldo Carvalho de Melo, Jiri Olsa.

     ... with the bulk of the changes written by Jiri Olsa, Tzvetomir
     Stoyanov and Arnaldo Carvalho de Melo.

   - Continued intel_rdt work with a focus on playing well with perf
     events. This also imported some non-perf RDT work due to
     dependencies. (Reinette Chatre)

   - Implement counter freezing for Arch Perfmon v4 (Skylake and newer).
     This allows to speed up the PMI handler by avoiding unnecessary MSR
     writes and make it more accurate. (Andi Kleen)

   - kprobes cleanups and simplification (Masami Hiramatsu)

   - Intel Goldmont PMU updates (Kan Liang)

   - ... plus misc other fixes and updates"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (155 commits)
  kprobes/x86: Use preempt_enable() in optimized_callback()
  x86/intel_rdt: Prevent pseudo-locking from using stale pointers
  kprobes, x86/ptrace.h: Make regs_get_kernel_stack_nth() not fault on bad stack
  perf/x86/intel: Export mem events only if there's PEBS support
  x86/cpu: Drop pointless static qualifier in punit_dev_state_show()
  x86/intel_rdt: Fix initial allocation to consider CDP
  x86/intel_rdt: CBM overlap should also check for overlap with CDP peer
  x86/intel_rdt: Introduce utility to obtain CDP peer
  tools lib traceevent, perf tools: Move struct tep_handler definition in a local header file
  tools lib traceevent: Separate out tep_strerror() for strerror_r() issues
  perf python: More portable way to make CFLAGS work with clang
  perf python: Make clang_has_option() work on Python 3
  perf tools: Free temporary 'sys' string in read_event_files()
  perf tools: Avoid double free in read_event_file()
  perf tools: Free 'printk' string in parse_ftrace_printk()
  perf tools: Cleanup trace-event-info 'tdata' leak
  perf strbuf: Match va_{add,copy} with va_end
  perf test: S390 does not support watchpoints in test 22
  perf auxtrace: Include missing asm/bitsperlong.h to get BITS_PER_LONG
  tools include: Adopt linux/bits.h
  ...

1 files changed, 69 insertions, 41 deletions

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ba481d73f910..4da5e32b9e03 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -406,9 +406,10 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
                                         PERF_OUTPUT_WEIGHT))
                 return -EINVAL;
 
-        if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) {
+        if (PRINT_FIELD(SYM) &&
+                !(evsel->attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) {
                 pr_err("Display of symbols requested but neither sample IP nor "
-                           "sample address\nis selected. Hence, no addresses to convert "
+                           "sample address\navailable. Hence, no addresses to convert "
                        "to symbols.\n");
                 return -EINVAL;
         }
@@ -417,10 +418,9 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
                        "selected.\n");
                 return -EINVAL;
         }
-        if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR) &&
-            !PRINT_FIELD(BRSTACK) && !PRINT_FIELD(BRSTACKSYM) && !PRINT_FIELD(BRSTACKOFF)) {
-                pr_err("Display of DSO requested but no address to convert.  Select\n"
-                       "sample IP, sample address, brstack, brstacksym, or brstackoff.\n");
+        if (PRINT_FIELD(DSO) &&
+                !(evsel->attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) {
+                pr_err("Display of DSO requested but no address to convert.\n");
                 return -EINVAL;
         }
         if (PRINT_FIELD(SRCLINE) && !PRINT_FIELD(IP)) {
@@ -1115,6 +1115,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
         const char *name = NULL;
         static int spacing;
         int len = 0;
+        int dlen = 0;
         u64 ip = 0;
 
         /*
@@ -1141,6 +1142,12 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
                         ip = sample->ip;
         }
 
+        if (PRINT_FIELD(DSO) && !(PRINT_FIELD(IP) || PRINT_FIELD(ADDR))) {
+                dlen += fprintf(fp, "(");
+                dlen += map__fprintf_dsoname(al->map, fp);
+                dlen += fprintf(fp, ")\t");
+        }
+
         if (name)
                 len = fprintf(fp, "%*s%s", (int)depth * 4, "", name);
         else if (ip)
@@ -1159,7 +1166,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
         if (len < spacing)
                 len += fprintf(fp, "%*s", spacing - len, "");
 
-        return len;
+        return len + dlen;
 }
 
 static int perf_sample__fprintf_insn(struct perf_sample *sample,
@@ -1255,6 +1262,18 @@ static struct {
         {0, NULL}
 };
 
+static const char *sample_flags_to_name(u32 flags)
+{
+        int i;
+
+        for (i = 0; sample_flags[i].name ; i++) {
+                if (sample_flags[i].flags == flags)
+                        return sample_flags[i].name;
+        }
+
+        return NULL;
+}
+
 static int perf_sample__fprintf_flags(u32 flags, FILE *fp)
 {
         const char *chars = PERF_IP_FLAG_CHARS;
@@ -1264,11 +1283,20 @@ static int perf_sample__fprintf_flags(u32 flags, FILE *fp)
         char str[33];
         int i, pos = 0;
 
-        for (i = 0; sample_flags[i].name ; i++) {
-                if (sample_flags[i].flags == (flags & ~PERF_IP_FLAG_IN_TX)) {
-                        name = sample_flags[i].name;
-                        break;
-                }
+        name = sample_flags_to_name(flags & ~PERF_IP_FLAG_IN_TX);
+        if (name)
+                return fprintf(fp, "  %-15s%4s ", name, in_tx ? "(x)" : "");
+
+        if (flags & PERF_IP_FLAG_TRACE_BEGIN) {
+                name = sample_flags_to_name(flags & ~(PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_TRACE_BEGIN));
+                if (name)
+                        return fprintf(fp, "  tr strt %-7s%4s ", name, in_tx ? "(x)" : "");
+        }
+
+        if (flags & PERF_IP_FLAG_TRACE_END) {
+                name = sample_flags_to_name(flags & ~(PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_TRACE_END));
+                if (name)
+                        return fprintf(fp, "  tr end  %-7s%4s ", name, in_tx ? "(x)" : "");
         }
 
         for (i = 0; i < n; i++, flags >>= 1) {
@@ -1281,10 +1309,7 @@ static int perf_sample__fprintf_flags(u32 flags, FILE *fp)
         }
         str[pos] = 0;
 
-        if (name)
-                return fprintf(fp, "  %-7s%4s ", name, in_tx ? "(x)" : "");
-
-        return fprintf(fp, "  %-11s ", str);
+        return fprintf(fp, "  %-19s ", str);
 }
 
 struct printer_data {
@@ -1544,7 +1569,8 @@ struct metric_ctx {
         FILE                    *fp;
 };
 
-static void script_print_metric(void *ctx, const char *color,
+static void script_print_metric(struct perf_stat_config *config __maybe_unused,
+                                void *ctx, const char *color,
                                 const char *fmt,
                                 const char *unit, double val)
 {
@@ -1562,7 +1588,8 @@ static void script_print_metric(void *ctx, const char *color,
         fprintf(mctx->fp, " %s\n", unit);
 }
 
-static void script_new_line(void *ctx)
+static void script_new_line(struct perf_stat_config *config __maybe_unused,
+                            void *ctx)
 {
         struct metric_ctx *mctx = ctx;
 
@@ -1608,7 +1635,7 @@ static void perf_sample__fprint_metric(struct perf_script *script,
         evsel_script(evsel)->val = val;
         if (evsel_script(evsel->leader)->gnum == evsel->leader->nr_members) {
                 for_each_group_member (ev2, evsel->leader) {
-                        perf_stat__print_shadow_stats(ev2,
+                        perf_stat__print_shadow_stats(&stat_config, ev2,
                                                       evsel_script(ev2)->val,
                                                       sample->cpu,
                                                       &ctx,
@@ -2489,6 +2516,8 @@ parse:
                                                 output[j].fields &= ~all_output_options[i].field;
                                         else
                                                 output[j].fields |= all_output_options[i].field;
+                                        output[j].user_set = true;
+                                        output[j].wildcard_set = true;
                                 }
                         }
                 } else {
@@ -2499,7 +2528,8 @@ parse:
                                 rc = -EINVAL;
                                 goto out;
                         }
-                        output[type].fields |= all_output_options[i].field;
+                        output[type].user_set = true;
+                        output[type].wildcard_set = true;
                 }
         }
 
@@ -2963,9 +2993,8 @@ static void script__setup_sample_type(struct perf_script *script)
         }
 }
 
-static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
-                                    union perf_event *event,
-                                    struct perf_session *session)
+static int process_stat_round_event(struct perf_session *session,
+                                    union perf_event *event)
 {
         struct stat_round_event *round = &event->stat_round;
         struct perf_evsel *counter;
@@ -2979,9 +3008,8 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
         return 0;
 }
 
-static int process_stat_config_event(struct perf_tool *tool __maybe_unused,
-                                     union perf_event *event,
-                                     struct perf_session *session __maybe_unused)
+static int process_stat_config_event(struct perf_session *session __maybe_unused,
+                                     union perf_event *event)
 {
         perf_event__read_stat_config(&stat_config, &event->stat_config);
         return 0;
@@ -3007,10 +3035,10 @@ static int set_maps(struct perf_script *script)
 }
 
 static
-int process_thread_map_event(struct perf_tool *tool,
-                             union perf_event *event,
-                             struct perf_session *session __maybe_unused)
+int process_thread_map_event(struct perf_session *session,
+                             union perf_event *event)
 {
+        struct perf_tool *tool = session->tool;
         struct perf_script *script = container_of(tool, struct perf_script, tool);
 
         if (script->threads) {
@@ -3026,10 +3054,10 @@ int process_thread_map_event(struct perf_tool *tool,
 }
 
 static
-int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
-                          union perf_event *event,
-                          struct perf_session *session __maybe_unused)
+int process_cpu_map_event(struct perf_session *session,
+                          union perf_event *event)
 {
+        struct perf_tool *tool = session->tool;
         struct perf_script *script = container_of(tool, struct perf_script, tool);
 
         if (script->cpus) {
@@ -3044,21 +3072,21 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused,
         return set_maps(script);
 }
 
-static int process_feature_event(struct perf_tool *tool,
-                                 union perf_event *event,
-                                 struct perf_session *session)
+static int process_feature_event(struct perf_session *session,
+                                 union perf_event *event)
 {
         if (event->feat.feat_id < HEADER_LAST_FEATURE)
-                return perf_event__process_feature(tool, event, session);
+                return perf_event__process_feature(session, event);
         return 0;
 }
 
 #ifdef HAVE_AUXTRACE_SUPPORT
-static int perf_script__process_auxtrace_info(struct perf_tool *tool,
-                                              union perf_event *event,
-                                              struct perf_session *session)
+static int perf_script__process_auxtrace_info(struct perf_session *session,
+                                              union perf_event *event)
 {
-        int ret = perf_event__process_auxtrace_info(tool, event, session);
+        struct perf_tool *tool = session->tool;
+
+        int ret = perf_event__process_auxtrace_info(session, event);
 
         if (ret == 0) {
                 struct perf_script *script = container_of(tool, struct perf_script, tool);
@@ -3193,7 +3221,7 @@ int cmd_script(int argc, const char **argv)
         OPT_BOOLEAN(0, "ns", &nanosecs,
                     "Use 9 decimal places when displaying time"),
         OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
-                            "Instruction Tracing options",
+                            "Instruction Tracing options\n" ITRACE_HELP,
                             itrace_parse_synth_opts),
         OPT_BOOLEAN(0, "full-source-path", &srcline_full_filename,
                         "Show full source file name path for source lines"),