Merge tag 'perf-core-for-mingo-20160516' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

User visible changes:

- Honour the kernel.perf_event_max_stack knob more precisely by not counting
  PERF_CONTEXT_{KERNEL,USER} when deciding when to stop adding entries to
  the perf_sample->ip_callchain[] array (Arnaldo Carvalho de Melo)

- Fix identation of 'stalled-backend-cycles' in 'perf stat' (Namhyung Kim)

- Update runtime using 'cpu-clock' event in 'perf stat' (Namhyung Kim)

- Use 'cpu-clock' for cpu targets in 'perf stat' (Namhyung Kim)

- Avoid fractional digits for integer scales in 'perf stat' (Andi Kleen)

- Store vdso buildid unconditionally, as it appears in callchains and
  we're not checking those when creating the build-id table, so we
  end up not being able to resolve VDSO symbols when doing analysis
  on a different machine than the one where recording was done, possibly
  of a different arch even (arm -> x86_64) (He Kuang)

Infrastructure changes:

- Generalize max_stack sysctl handler, will be used for configuring
  multiple kernel knobs related to callchains (Arnaldo Carvalho de Melo)

Cleanups:

- Introduce DSO__NAME_KALLSYMS and DSO__NAME_KCORE, to stop using
  open coded strings (Masami Hiramatsu)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

12 files changed, 59 insertions, 36 deletions

diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 632efc6b79a0..d75bded21fe0 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -119,8 +119,8 @@ static int build_id_cache__add_kcore(const char *filename, bool force)
         if (build_id_cache__kcore_buildid(from_dir, sbuildid) < 0)
                 return -1;
 
-        scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s",
-                  buildid_dir, sbuildid);
+        scnprintf(to_dir, sizeof(to_dir), "%s/%s/%s",
+                  buildid_dir, DSO__NAME_KCORE, sbuildid);
 
         if (!force &&
             !build_id_cache__kcore_existing(from_dir, to_dir, sizeof(to_dir))) {
@@ -131,8 +131,8 @@ static int build_id_cache__add_kcore(const char *filename, bool force)
         if (build_id_cache__kcore_dir(dir, sizeof(dir)))
                 return -1;
 
-        scnprintf(to_dir, sizeof(to_dir), "%s/[kernel.kcore]/%s/%s",
-                  buildid_dir, sbuildid, dir);
+        scnprintf(to_dir, sizeof(to_dir), "%s/%s/%s/%s",
+                  buildid_dir, DSO__NAME_KCORE, sbuildid, dir);
 
         if (mkdir_p(to_dir, 0755))
                 return -1;
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e459b685a4e9..ee7ada78d86f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -66,6 +66,7 @@
 #include <stdlib.h>
 #include <sys/prctl.h>
 #include <locale.h>
+#include <math.h>
 
 #define DEFAULT_SEPARATOR       " "
 #define CNTR_NOT_SUPPORTED      "<not supported>"
@@ -991,12 +992,12 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
         const char *fmt;
 
         if (csv_output) {
-                fmt = sc != 1.0 ?  "%.2f%s" : "%.0f%s";
+                fmt = floor(sc) != sc ?  "%.2f%s" : "%.0f%s";
         } else {
                 if (big_num)
-                        fmt = sc != 1.0 ? "%'18.2f%s" : "%'18.0f%s";
+                        fmt = floor(sc) != sc ? "%'18.2f%s" : "%'18.0f%s";
                 else
-                        fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s";
+                        fmt = floor(sc) != sc ? "%18.2f%s" : "%18.0f%s";
         }
 
         aggr_printout(evsel, id, nr);
@@ -1909,6 +1910,9 @@ static int add_default_attributes(void)
         }
 
         if (!evsel_list->nr_entries) {
+                if (target__has_cpu(&target))
+                        default_attrs0[0].config = PERF_COUNT_SW_CPU_CLOCK;
+
                 if (perf_evlist__add_default_attrs(evsel_list, default_attrs0) < 0)
                         return -1;
                 if (pmu_have_event("cpu", "stalled-cycles-frontend")) {
@@ -2000,7 +2004,7 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
                                     union perf_event *event,
                                     struct perf_session *session)
 {
-        struct stat_round_event *round = &event->stat_round;
+        struct stat_round_event *stat_round = &event->stat_round;
         struct perf_evsel *counter;
         struct timespec tsh, *ts = NULL;
         const char **argv = session->header.env.cmdline_argv;
@@ -2009,12 +2013,12 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused,
         evlist__for_each(evsel_list, counter)
                 perf_stat_process_counter(&stat_config, counter);
 
-        if (round->type == PERF_STAT_ROUND_TYPE__FINAL)
-                update_stats(&walltime_nsecs_stats, round->time);
+        if (stat_round->type == PERF_STAT_ROUND_TYPE__FINAL)
+                update_stats(&walltime_nsecs_stats, stat_round->time);
 
-        if (stat_config.interval && round->time) {
-                tsh.tv_sec  = round->time / NSECS_PER_SEC;
-                tsh.tv_nsec = round->time % NSECS_PER_SEC;
+        if (stat_config.interval && stat_round->time) {
+                tsh.tv_sec  = stat_round->time / NSECS_PER_SEC;
+                tsh.tv_nsec = stat_round->time % NSECS_PER_SEC;
                 ts = &tsh;
         }
 
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 797000842d40..15982cee5ef3 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -549,6 +549,9 @@ int main(int argc, const char **argv)
         if (sysctl__read_int("kernel/perf_event_max_stack", &value) == 0)
                 sysctl_perf_event_max_stack = value;
 
+        if (sysctl__read_int("kernel/perf_event_max_contexts_per_stack", &value) == 0)
+                sysctl_perf_event_max_contexts_per_stack = value;
+
         cmd = extract_argv0_path(argv[0]);
         if (!cmd)
                 cmd = "perf-help";
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 4db73d5a0dbc..b811924e5e1b 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1122,7 +1122,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
         } else if (dso__is_kcore(dso)) {
                 goto fallback;
         } else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
-                   strstr(command, "[kernel.kallsyms]") ||
+                   strstr(command, DSO__NAME_KALLSYMS) ||
                    access(symfs_filename, R_OK)) {
                 free(filename);
 fallback:
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index bff425e1232c..67e5966503b2 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -256,7 +256,7 @@ static int machine__write_buildid_table(struct machine *machine, int fd)
                 size_t name_len;
                 bool in_kernel = false;
 
-                if (!pos->hit)
+                if (!pos->hit && !dso__is_vdso(pos))
                         continue;
 
                 if (dso__is_vdso(pos)) {
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 3357479082ca..75b75615e2f8 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -7,6 +7,7 @@
 #include "auxtrace.h"
 #include "util.h"
 #include "debug.h"
+#include "vdso.h"
 
 char dso__symtab_origin(const struct dso *dso)
 {
@@ -1169,7 +1170,7 @@ bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
         struct dso *pos;
 
         list_for_each_entry(pos, head, node) {
-                if (with_hits && !pos->hit)
+                if (with_hits && !pos->hit && !dso__is_vdso(pos))
                         continue;
                 if (pos->has_build_id) {
                         have_build_id = true;
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 639a2903065e..7ba9fadb68af 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -709,7 +709,7 @@ static struct dso *machine__get_kernel(struct machine *machine)
         if (machine__is_host(machine)) {
                 vmlinux_name = symbol_conf.vmlinux_name;
                 if (!vmlinux_name)
-                        vmlinux_name = "[kernel.kallsyms]";
+                        vmlinux_name = DSO__NAME_KALLSYMS;
 
                 kernel = machine__findnew_kernel(machine, vmlinux_name,
                                                  "[kernel]", DSO_TYPE_KERNEL);
@@ -1811,9 +1811,9 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 {
         struct branch_stack *branch = sample->branch_stack;
         struct ip_callchain *chain = sample->callchain;
-        int chain_nr = min(max_stack, (int)chain->nr);
+        int chain_nr = chain->nr;
         u8 cpumode = PERF_RECORD_MISC_USER;
-        int i, j, err;
+        int i, j, err, nr_entries, nr_contexts;
         int skip_idx = -1;
         int first_call = 0;
 
@@ -1828,7 +1828,7 @@ static int thread__resolve_callchain_sample(struct thread *thread,
          * Based on DWARF debug information, some architectures skip
          * a callchain entry saved by the kernel.
          */
-        if (chain->nr < sysctl_perf_event_max_stack)
+        if (chain_nr < sysctl_perf_event_max_stack)
                 skip_idx = arch_skip_callchain_idx(thread, chain);
 
         /*
@@ -1889,12 +1889,8 @@ static int thread__resolve_callchain_sample(struct thread *thread,
         }
 
 check_calls:
-        if (chain->nr > sysctl_perf_event_max_stack && (int)chain->nr > max_stack) {
-                pr_warning("corrupted callchain. skipping...\n");
-                return 0;
-        }
-
-        for (i = first_call; i < chain_nr; i++) {
+        for (i = first_call, nr_entries = 0, nr_contexts = 0;
+             i < chain_nr && nr_entries < max_stack; i++) {
                 u64 ip;
 
                 if (callchain_param.order == ORDER_CALLEE)
@@ -1908,6 +1904,14 @@ check_calls:
 #endif
                 ip = chain->ips[j];
 
+                if (ip >= PERF_CONTEXT_MAX) {
+                        if (++nr_contexts > sysctl_perf_event_max_contexts_per_stack)
+                                goto out_corrupted_callchain;
+                } else {
+                        if (++nr_entries > sysctl_perf_event_max_stack)
+                                goto out_corrupted_callchain;
+                }
+
                 err = add_callchain_ip(thread, cursor, parent, root_al, &cpumode, ip);
 
                 if (err)
@@ -1915,6 +1919,10 @@ check_calls:
         }
 
         return 0;
+
+out_corrupted_callchain:
+        pr_warning("corrupted callchain. skipping...\n");
+        return 0;
 }
 
 static int unwind_entry(struct unwind_entry *entry, void *arg)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index fdb71961143e..aa9efe08762b 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -94,7 +94,8 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 {
         int ctx = evsel_context(counter);
 
-        if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
+        if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK) ||
+            perf_evsel__match(counter, SOFTWARE, SW_CPU_CLOCK))
                 update_stats(&runtime_nsecs_stats[cpu], count[0]);
         else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
                 update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
@@ -188,7 +189,7 @@ static void print_stalled_cycles_backend(int cpu,
 
         color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
 
-        out->print_metric(out->ctx, color, "%6.2f%%", "backend cycles idle", ratio);
+        out->print_metric(out->ctx, color, "%7.2f%%", "backend cycles idle", ratio);
 }
 
 static void print_branch_misses(int cpu,
@@ -444,7 +445,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
                         ratio = total / avg;
 
                 print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
-        } else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) {
+        } else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) ||
+                   perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) {
                 if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
                         print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
                                      avg / ratio);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 7fb33304fb4e..2252b545ff43 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1662,8 +1662,8 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
 
         build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
 
-        scnprintf(path, sizeof(path), "%s/[kernel.kcore]/%s", buildid_dir,
-                  sbuild_id);
+        scnprintf(path, sizeof(path), "%s/%s/%s", buildid_dir,
+                  DSO__NAME_KCORE, sbuild_id);
 
         /* Use /proc/kallsyms if possible */
         if (is_host) {
@@ -1699,8 +1699,8 @@ static char *dso__find_kallsyms(struct dso *dso, struct map *map)
         if (!find_matching_kcore(map, path, sizeof(path)))
                 return strdup(path);
 
-        scnprintf(path, sizeof(path), "%s/[kernel.kallsyms]/%s",
-                  buildid_dir, sbuild_id);
+        scnprintf(path, sizeof(path), "%s/%s/%s",
+                  buildid_dir, DSO__NAME_KALLSYMS, sbuild_id);
 
         if (access(path, F_OK)) {
                 pr_err("No kallsyms or vmlinux with build-id %s was found\n",
@@ -1769,7 +1769,7 @@ do_kallsyms:
 
         if (err > 0 && !dso__is_kcore(dso)) {
                 dso->binary_type = DSO_BINARY_TYPE__KALLSYMS;
-                dso__set_long_name(dso, "[kernel.kallsyms]", false);
+                dso__set_long_name(dso, DSO__NAME_KALLSYMS, false);
                 map__fixup_start(map);
                 map__fixup_end(map);
         }
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 2b5e4ed76fcb..25f2fd672c2e 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -44,6 +44,9 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
 #define DMGL_ANSI        (1 << 1)       /* Include const, volatile, etc */
 #endif
 
+#define DSO__NAME_KALLSYMS      "[kernel.kallsyms]"
+#define DSO__NAME_KCORE         "[kernel.kcore]"
+
 /** struct symbol - symtab entry
  *
  * @ignore - resolvable but tools ignore it (e.g. idle routines)
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index eab077ad6ca9..23504ad5d6dd 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -33,7 +33,8 @@ struct callchain_param	callchain_param = {
 unsigned int page_size;
 int cacheline_size;
 
-unsigned int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
+int sysctl_perf_event_max_stack = PERF_MAX_STACK_DEPTH;
+int sysctl_perf_event_max_contexts_per_stack = PERF_MAX_CONTEXTS_PER_STACK;
 
 bool test_attr__enabled;
 
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 7651633a8dc7..1e8c3167b9fb 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -261,7 +261,8 @@ void sighandler_dump_stack(int sig);
 
 extern unsigned int page_size;
 extern int cacheline_size;
-extern unsigned int sysctl_perf_event_max_stack;
+extern int sysctl_perf_event_max_stack;
+extern int sysctl_perf_event_max_contexts_per_stack;
 
 struct parse_tag {
         char tag;