9 files changed, 152 insertions, 68 deletions

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 27fc3617c6a4..5054d9147f0f 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -430,6 +430,10 @@ that gets then processed, possibly via a perf script, to decide if that
 particular perf.data snapshot should be kept or not.
 
 Implies --timestamp-filename, --no-buildid and --no-buildid-cache.
+The reason for the latter two is to reduce the data file switching
+overhead. You can still switch them on with:
+
+  --switch-output --no-no-buildid  --no-no-buildid-cache
 
 --dry-run::
 Parse options then exit. --dry-run can be used to detect errors in cmdline
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 8fc24824705e..8bb16aa9d661 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -704,9 +704,9 @@ install-tests: all install-gtk
                 $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'; \
                 $(INSTALL) tests/attr/* '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/tests/attr'
 
-install-bin: install-tools install-tests
+install-bin: install-tools install-tests install-traceevent-plugins
 
-install: install-bin try-install-man install-traceevent-plugins
+install: install-bin try-install-man
 
 install-python_ext:
         $(PYTHON_WORD) util/setup.py --quiet install --root='/$(DESTDIR_SQ)'
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 35a02f8e5a4a..915869e00d86 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -655,7 +655,6 @@ static const struct {
         { "__GFP_RECLAIM",              "R" },
         { "__GFP_DIRECT_RECLAIM",       "DR" },
         { "__GFP_KSWAPD_RECLAIM",       "KR" },
-        { "__GFP_OTHER_NODE",           "ON" },
 };
 
 static size_t max_gfp_len;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 74d6a035133a..4ec10e9427d9 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1405,7 +1405,7 @@ static bool dry_run;
  * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
  * using pipes, etc.
  */
-struct option __record_options[] = {
+static struct option __record_options[] = {
         OPT_CALLBACK('e', "event", &record.evlist, "event",
                      "event selector. use 'perf list' to list available events",
                      parse_events_option),
@@ -1636,7 +1636,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
                  * overhead. Still generate buildid if they are required
                  * explicitly using
                  *
-                 *  perf record --signal-trigger --no-no-buildid \
+                 *  perf record --switch-output --no-no-buildid \
                  *              --no-no-buildid-cache
                  *
                  * Following code equals to:
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index d53e706a6f17..5b134b0d1ff3 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -209,6 +209,7 @@ struct perf_sched {
         u64             skipped_samples;
         const char      *time_str;
         struct perf_time_interval ptime;
+        struct perf_time_interval hist_time;
 };
 
 /* per thread run time data */
@@ -2460,6 +2461,11 @@ static int timehist_sched_change_event(struct perf_tool *tool,
                 timehist_print_sample(sched, sample, &al, thread, t);
 
 out:
+        if (sched->hist_time.start == 0 && t >= ptime->start)
+                sched->hist_time.start = t;
+        if (ptime->end == 0 || t <= ptime->end)
+                sched->hist_time.end = t;
+
         if (tr) {
                 /* time of this sched_switch event becomes last time task seen */
                 tr->last_time = sample->time;
@@ -2624,6 +2630,7 @@ static void timehist_print_summary(struct perf_sched *sched,
         struct thread *t;
         struct thread_runtime *r;
         int i;
+        u64 hist_time = sched->hist_time.end - sched->hist_time.start;
 
         memset(&totals, 0, sizeof(totals));
 
@@ -2665,7 +2672,7 @@ static void timehist_print_summary(struct perf_sched *sched,
                         totals.sched_count += r->run_stats.n;
                         printf("    CPU %2d idle for ", i);
                         print_sched_time(r->total_run_time, 6);
-                        printf(" msec\n");
+                        printf(" msec  (%6.2f%%)\n", 100.0 * r->total_run_time / hist_time);
                 } else
                         printf("    CPU %2d idle entire time window\n", i);
         }
@@ -2701,12 +2708,16 @@ static void timehist_print_summary(struct perf_sched *sched,
 
         printf("\n"
                "    Total number of unique tasks: %" PRIu64 "\n"
-               "Total number of context switches: %" PRIu64 "\n"
-               "           Total run time (msec): ",
+               "Total number of context switches: %" PRIu64 "\n",
                totals.task_count, totals.sched_count);
 
+        printf("           Total run time (msec): ");
         print_sched_time(totals.total_run_time, 2);
         printf("\n");
+
+        printf("    Total scheduling time (msec): ");
+        print_sched_time(hist_time, 2);
+        printf(" (x %d)\n", sched->max_cpu);
 }
 
 typedef int (*sched_handler)(struct perf_tool *tool,
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index d281ae2b54e8..6a6f44dd594b 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -163,7 +163,7 @@ static struct map *kernel_get_module_map(const char *module)
 
         /* A file path -- this is an offline module */
         if (module && strchr(module, '/'))
-                return machine__findnew_module_map(host_machine, 0, module);
+                return dso__new_map(module);
 
         if (!module)
                 module = "kernel";
@@ -173,6 +173,7 @@ static struct map *kernel_get_module_map(const char *module)
                 if (strncmp(pos->dso->short_name + 1, module,
                             pos->dso->short_name_len - 2) == 0 &&
                     module[pos->dso->short_name_len - 2] == '\0') {
+                        map__get(pos);
                         return pos;
                 }
         }
@@ -188,15 +189,6 @@ struct map *get_target_map(const char *target, bool user)
                 return kernel_get_module_map(target);
 }
 
-static void put_target_map(struct map *map, bool user)
-{
-        if (map && user) {
-                /* Only the user map needs to be released */
-                map__put(map);
-        }
-}
-
-
 static int convert_exec_to_group(const char *exec, char **result)
 {
         char *ptr1, *ptr2, *exec_copy;
@@ -268,21 +260,6 @@ static bool kprobe_warn_out_range(const char *symbol, unsigned long address)
 }
 
 /*
- * NOTE:
- * '.gnu.linkonce.this_module' section of kernel module elf directly
- * maps to 'struct module' from linux/module.h. This section contains
- * actual module name which will be used by kernel after loading it.
- * But, we cannot use 'struct module' here since linux/module.h is not
- * exposed to user-space. Offset of 'name' has remained same from long
- * time, so hardcoding it here.
- */
-#ifdef __LP64__
-#define MOD_NAME_OFFSET 24
-#else
-#define MOD_NAME_OFFSET 12
-#endif
-
-/*
  * @module can be module name of module file path. In case of path,
  * inspect elf and find out what is actual module name.
  * Caller has to free mod_name after using it.
@@ -296,6 +273,7 @@ static char *find_module_name(const char *module)
         Elf_Data *data;
         Elf_Scn *sec;
         char *mod_name = NULL;
+        int name_offset;
 
         fd = open(module, O_RDONLY);
         if (fd < 0)
@@ -317,7 +295,21 @@ static char *find_module_name(const char *module)
         if (!data || !data->d_buf)
                 goto ret_err;
 
-        mod_name = strdup((char *)data->d_buf + MOD_NAME_OFFSET);
+        /*
+         * NOTE:
+         * '.gnu.linkonce.this_module' section of kernel module elf directly
+         * maps to 'struct module' from linux/module.h. This section contains
+         * actual module name which will be used by kernel after loading it.
+         * But, we cannot use 'struct module' here since linux/module.h is not
+         * exposed to user-space. Offset of 'name' has remained same from long
+         * time, so hardcoding it here.
+         */
+        if (ehdr.e_ident[EI_CLASS] == ELFCLASS32)
+                name_offset = 12;
+        else    /* expect ELFCLASS64 by default */
+                name_offset = 24;
+
+        mod_name = strdup((char *)data->d_buf + name_offset);
 
 ret_err:
         elf_end(elf);
@@ -412,7 +404,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo,
         }
 
 out:
-        put_target_map(map, uprobes);
+        map__put(map);
         return ret;
 
 }
@@ -618,6 +610,67 @@ error:
         return ret ? : -ENOENT;
 }
 
+/* Adjust symbol name and address */
+static int post_process_probe_trace_point(struct probe_trace_point *tp,
+                                           struct map *map, unsigned long offs)
+{
+        struct symbol *sym;
+        u64 addr = tp->address + tp->offset - offs;
+
+        sym = map__find_symbol(map, addr);
+        if (!sym)
+                return -ENOENT;
+
+        if (strcmp(sym->name, tp->symbol)) {
+                /* If we have no realname, use symbol for it */
+                if (!tp->realname)
+                        tp->realname = tp->symbol;
+                else
+                        free(tp->symbol);
+                tp->symbol = strdup(sym->name);
+                if (!tp->symbol)
+                        return -ENOMEM;
+        }
+        tp->offset = addr - sym->start;
+        tp->address -= offs;
+
+        return 0;
+}
+
+/*
+ * Rename DWARF symbols to ELF symbols -- gcc sometimes optimizes functions
+ * and generate new symbols with suffixes such as .constprop.N or .isra.N
+ * etc. Since those symbols are not recorded in DWARF, we have to find
+ * correct generated symbols from offline ELF binary.
+ * For online kernel or uprobes we don't need this because those are
+ * rebased on _text, or already a section relative address.
+ */
+static int
+post_process_offline_probe_trace_events(struct probe_trace_event *tevs,
+                                        int ntevs, const char *pathname)
+{
+        struct map *map;
+        unsigned long stext = 0;
+        int i, ret = 0;
+
+        /* Prepare a map for offline binary */
+        map = dso__new_map(pathname);
+        if (!map || get_text_start_address(pathname, &stext) < 0) {
+                pr_warning("Failed to get ELF symbols for %s\n", pathname);
+                return -EINVAL;
+        }
+
+        for (i = 0; i < ntevs; i++) {
+                ret = post_process_probe_trace_point(&tevs[i].point,
+                                                     map, stext);
+                if (ret < 0)
+                        break;
+        }
+        map__put(map);
+
+        return ret;
+}
+
 static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
                                           int ntevs, const char *exec)
 {
@@ -645,18 +698,31 @@ static int add_exec_to_probe_trace_events(struct probe_trace_event *tevs,
         return ret;
 }
 
-static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
-                                            int ntevs, const char *module)
+static int
+post_process_module_probe_trace_events(struct probe_trace_event *tevs,
+                                       int ntevs, const char *module,
+                                       struct debuginfo *dinfo)
 {
+        Dwarf_Addr text_offs = 0;
         int i, ret = 0;
         char *mod_name = NULL;
+        struct map *map;
 
         if (!module)
                 return 0;
 
-        mod_name = find_module_name(module);
+        map = get_target_map(module, false);
+        if (!map || debuginfo__get_text_offset(dinfo, &text_offs, true) < 0) {
+                pr_warning("Failed to get ELF symbols for %s\n", module);
+                return -EINVAL;
+        }
 
+        mod_name = find_module_name(module);
         for (i = 0; i < ntevs; i++) {
+                ret = post_process_probe_trace_point(&tevs[i].point,
+                                                map, (unsigned long)text_offs);
+                if (ret < 0)
+                        break;
                 tevs[i].point.module =
                         strdup(mod_name ? mod_name : module);
                 if (!tevs[i].point.module) {
@@ -666,6 +732,8 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs,
         }
 
         free(mod_name);
+        map__put(map);
+
         return ret;
 }
 
@@ -679,7 +747,8 @@ post_process_kernel_probe_trace_events(struct probe_trace_event *tevs,
 
         /* Skip post process if the target is an offline kernel */
         if (symbol_conf.ignore_vmlinux_buildid)
-                return 0;
+                return post_process_offline_probe_trace_events(tevs, ntevs,
+                                                symbol_conf.vmlinux_name);
 
         reloc_sym = kernel_get_ref_reloc_sym();
         if (!reloc_sym) {
@@ -722,7 +791,7 @@ arch__post_process_probe_trace_events(struct perf_probe_event *pev __maybe_unuse
 static int post_process_probe_trace_events(struct perf_probe_event *pev,
                                            struct probe_trace_event *tevs,
                                            int ntevs, const char *module,
-                                           bool uprobe)
+                                           bool uprobe, struct debuginfo *dinfo)
 {
         int ret;
 
@@ -730,7 +799,8 @@ static int post_process_probe_trace_events(struct perf_probe_event *pev,
                 ret = add_exec_to_probe_trace_events(tevs, ntevs, module);
         else if (module)
                 /* Currently ref_reloc_sym based probe is not for drivers */
-                ret = add_module_to_probe_trace_events(tevs, ntevs, module);
+                ret = post_process_module_probe_trace_events(tevs, ntevs,
+                                                             module, dinfo);
         else
                 ret = post_process_kernel_probe_trace_events(tevs, ntevs);
 
@@ -774,30 +844,27 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev,
                 }
         }
 
-        debuginfo__delete(dinfo);
-
         if (ntevs > 0) {        /* Succeeded to find trace events */
                 pr_debug("Found %d probe_trace_events.\n", ntevs);
                 ret = post_process_probe_trace_events(pev, *tevs, ntevs,
-                                                pev->target, pev->uprobes);
+                                        pev->target, pev->uprobes, dinfo);
                 if (ret < 0 || ret == ntevs) {
+                        pr_debug("Post processing failed or all events are skipped. (%d)\n", ret);
                         clear_probe_trace_events(*tevs, ntevs);
                         zfree(tevs);
+                        ntevs = 0;
                 }
-                if (ret != ntevs)
-                        return ret < 0 ? ret : ntevs;
-                ntevs = 0;
-                /* Fall through */
         }
 
+        debuginfo__delete(dinfo);
+
         if (ntevs == 0) {       /* No error but failed to find probe point. */
                 pr_warning("Probe point '%s' not found.\n",
                            synthesize_perf_probe_point(&pev->point));
                 return -ENOENT;
-        }
-        /* Error path : ntevs < 0 */
-        pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
-        if (ntevs < 0) {
+        } else if (ntevs < 0) {
+                /* Error path : ntevs < 0 */
+                pr_debug("An error occurred in debuginfo analysis (%d).\n", ntevs);
                 if (ntevs == -EBADF)
                         pr_warning("Warning: No dwarf info found in the vmlinux - "
                                 "please rebuild kernel with CONFIG_DEBUG_INFO=y.\n");
@@ -2869,7 +2936,7 @@ static int find_probe_trace_events_from_map(struct perf_probe_event *pev,
         }
 
 out:
-        put_target_map(map, pev->uprobes);
+        map__put(map);
         free(syms);
         return ret;
 
@@ -3362,10 +3429,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
                 return ret;
 
         /* Get a symbol map */
-        if (user)
-                map = dso__new_map(target);
-        else
-                map = kernel_get_module_map(target);
+        map = get_target_map(target, user);
         if (!map) {
                 pr_err("Failed to get a map for %s\n", (target) ? : "kernel");
                 return -EINVAL;
@@ -3397,9 +3461,7 @@ int show_available_funcs(const char *target, struct strfilter *_filter,
         }
 
 end:
-        if (user) {
-                map__put(map);
-        }
+        map__put(map);
         exit_probe_symbol_maps();
 
         return ret;
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index df4debe564da..0d9d6e0803b8 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1501,7 +1501,8 @@ int debuginfo__find_available_vars_at(struct debuginfo *dbg,
 }
 
 /* For the kernel module, we need a special code to get a DIE */
-static int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs)
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+                                bool adjust_offset)
 {
         int n, i;
         Elf32_Word shndx;
@@ -1530,6 +1531,8 @@ static int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs)
                         if (!shdr)
                                 return -ENOENT;
                         *offs = shdr->sh_addr;
+                        if (adjust_offset)
+                                *offs -= shdr->sh_offset;
                 }
         }
         return 0;
@@ -1543,16 +1546,12 @@ int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
         Dwarf_Addr _addr = 0, baseaddr = 0;
         const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp;
         int baseline = 0, lineno = 0, ret = 0;
-        bool reloc = false;
 
-retry:
+        /* We always need to relocate the address for aranges */
+        if (debuginfo__get_text_offset(dbg, &baseaddr, false) == 0)
+                addr += baseaddr;
         /* Find cu die */
         if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) {
-                if (!reloc && debuginfo__get_text_offset(dbg, &baseaddr) == 0) {
-                        addr += baseaddr;
-                        reloc = true;
-                        goto retry;
-                }
                 pr_warning("Failed to find debug information for address %lx\n",
                            addr);
                 ret = -EINVAL;
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index f1d8558f498e..2956c5198652 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -46,6 +46,9 @@ int debuginfo__find_trace_events(struct debuginfo *dbg,
 int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
                                 struct perf_probe_point *ppt);
 
+int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
+                               bool adjust_offset);
+
 /* Find a line range */
 int debuginfo__find_line_range(struct debuginfo *dbg, struct line_range *lr);
 
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 99400b0e8f2a..adbc6c02c3aa 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -537,6 +537,12 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
                                 break;
                 } else {
                         int n = namesz + descsz;
+
+                        if (n > (int)sizeof(bf)) {
+                                n = sizeof(bf);
+                                pr_debug("%s: truncating reading of build id in sysfs file %s: n_namesz=%u, n_descsz=%u.\n",
+                                         __func__, filename, nhdr.n_namesz, nhdr.n_descsz);
+                        }
                         if (read(fd, bf, n) != n)
                                 break;
                 }