14 files changed, 161 insertions, 85 deletions

diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index d69a759a104..0854f110bf7 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -10,6 +10,7 @@ perf-stat
 perf-top
 perf*.1
 perf*.xml
+perf*.html
 common-cmds.h
 tags
 TAGS
diff --git a/tools/perf/Documentation/perf-timechart.txt b/tools/perf/Documentation/perf-timechart.txt
index 1c2ed3090cc..a7910099d6f 100644
--- a/tools/perf/Documentation/perf-timechart.txt
+++ b/tools/perf/Documentation/perf-timechart.txt
@@ -31,6 +31,9 @@ OPTIONS
 -w::
 --width=::
         Select the width of the SVG file (default: 1000)
+-p::
+--power-only::
+        Only output the CPU power section of the diagram
 
 
 SEE ALSO
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index b5f1953b614..5881943f0c3 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -728,7 +728,7 @@ $(BUILT_INS): perf$X
 common-cmds.h: util/generate-cmdlist.sh command-list.txt
 
 common-cmds.h: $(wildcard Documentation/perf-*.txt)
-        $(QUIET_GEN)util/generate-cmdlist.sh > $@+ && mv $@+ $@
+        $(QUIET_GEN). util/generate-cmdlist.sh > $@+ && mv $@+ $@
 
 $(patsubst %.sh,%,$(SCRIPT_SH)) : % : %.sh
         $(QUIET_GEN)$(RM) $@ $@+ && \
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index a5a050af8e7..3eeef339c78 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -41,6 +41,7 @@ static int			raw_samples			= 0;
 static int                      system_wide                     = 0;
 static int                      profile_cpu                     = -1;
 static pid_t                    target_pid                      = -1;
+static pid_t                    child_pid                       = -1;
 static int                      inherit                         = 1;
 static int                      force                           = 0;
 static int                      append_file                     = 0;
@@ -184,6 +185,9 @@ static void sig_handler(int sig)
 
 static void sig_atexit(void)
 {
+        if (child_pid != -1)
+                kill(child_pid, SIGTERM);
+
         if (signr == -1)
                 return;
 
@@ -610,6 +614,8 @@ static int __cmd_record(int argc, const char **argv)
                                 exit(-1);
                         }
                 }
+
+                child_pid = pid;
         }
 
         if (realtime_prio) {
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 16af2d82e85..3db31e7bf17 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -69,7 +69,8 @@ static int			run_idx				=  0;
 static int                      run_count                       =  1;
 static int                      inherit                         =  1;
 static int                      scale                           =  1;
-static int                      target_pid                      = -1;
+static pid_t                    target_pid                      = -1;
+static pid_t                    child_pid                       = -1;
 static int                      null_run                        =  0;
 
 static int                      fd[MAX_NR_CPUS][MAX_COUNTERS];
@@ -285,6 +286,8 @@ static int run_perf_stat(int argc __used, const char **argv)
                 exit(-1);
         }
 
+        child_pid = pid;
+
         /*
          * Wait for the child to be ready to exec.
          */
@@ -338,14 +341,24 @@ static void nsec_printout(int counter, double avg)
 
 static void abs_printout(int counter, double avg)
 {
+        double total, ratio = 0.0;
+
         fprintf(stderr, " %14.0f  %-24s", avg, event_name(counter));
 
         if (MATCH_EVENT(HARDWARE, HW_INSTRUCTIONS, counter)) {
-                fprintf(stderr, " # %10.3f IPC  ",
-                                avg / avg_stats(&runtime_cycles_stats));
+                total = avg_stats(&runtime_cycles_stats);
+
+                if (total)
+                        ratio = avg / total;
+
+                fprintf(stderr, " # %10.3f IPC  ", ratio);
         } else {
-                fprintf(stderr, " # %10.3f M/sec",
-                                1000.0 * avg / avg_stats(&runtime_nsecs_stats));
+                total = avg_stats(&runtime_nsecs_stats);
+
+                if (total)
+                        ratio = 1000.0 * avg / total;
+
+                fprintf(stderr, " # %10.3f M/sec", ratio);
         }
 }
 
@@ -423,6 +436,9 @@ static void skip_signal(int signo)
 
 static void sig_atexit(void)
 {
+        if (child_pid != -1)
+                kill(child_pid, SIGTERM);
+
         if (signr == -1)
                 return;
 
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 4405681b313..702d8fe58fb 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -46,6 +46,8 @@ static u64		turbo_frequency;
 
 static u64              first_time, last_time;
 
+static int              power_only;
+
 
 static struct perf_header       *header;
 
@@ -547,7 +549,7 @@ static void end_sample_processing(void)
         u64 cpu;
         struct power_event *pwr;
 
-        for (cpu = 0; cpu < numcpus; cpu++) {
+        for (cpu = 0; cpu <= numcpus; cpu++) {
                 pwr = malloc(sizeof(struct power_event));
                 if (!pwr)
                         return;
@@ -871,7 +873,7 @@ static int determine_display_tasks(u64 threshold)
                 /* no exit marker, task kept running to the end */
                 if (p->end_time == 0)
                         p->end_time = last_time;
-                if (p->total_time >= threshold)
+                if (p->total_time >= threshold && !power_only)
                         p->display = 1;
 
                 c = p->all;
@@ -882,7 +884,7 @@ static int determine_display_tasks(u64 threshold)
                         if (c->start_time == 1)
                                 c->start_time = first_time;
 
-                        if (c->total_time >= threshold) {
+                        if (c->total_time >= threshold && !power_only) {
                                 c->display = 1;
                                 count++;
                         }
@@ -1134,6 +1136,8 @@ static const struct option options[] = {
                     "output file name"),
         OPT_INTEGER('w', "width", &svg_page_width,
                     "page width"),
+        OPT_BOOLEAN('p', "power-only", &power_only,
+                    "output power data only"),
         OPT_END()
 };
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1ca88896eee..37512e93623 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -782,6 +782,7 @@ static const char *skip_symbols[] = {
         "exit_idle",
         "mwait_idle",
         "mwait_idle_with_hints",
+        "poll_idle",
         "ppc64_runlatch_off",
         "pseries_dedicated_idle_sleep",
         NULL
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index e9d256e2f47..0c5e4f72f2b 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -219,10 +219,6 @@ remap:
 more:
         event = (event_t *)(buf + head);
 
-        size = event->header.size;
-        if (!size)
-                size = 8;
-
         if (head + event->header.size >= page_size * mmap_window) {
                 unsigned long shift = page_size * (head / page_size);
                 int res;
@@ -237,7 +233,6 @@ more:
 
         size = event->header.size;
 
-
         if (!size || process_event(event, offset, head) < 0) {
 
                 /*
@@ -290,7 +285,6 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
                         usage_with_options(annotate_usage, options);
         }
 
-
         setup_pager();
 
         return __cmd_trace();
diff --git a/tools/perf/design.txt b/tools/perf/design.txt
index f1946d107b1..fdd42a824c9 100644
--- a/tools/perf/design.txt
+++ b/tools/perf/design.txt
@@ -455,3 +455,6 @@ will need at least this:
 
 If your architecture does have hardware capabilities, you can override the
 weak stub hw_perf_event_init() to register hardware counters.
+
+Architectures that have d-cache aliassing issues, such as Sparc and ARM,
+should select PERF_USE_VMALLOC in order to avoid these for perf mmap().
diff --git a/tools/perf/util/module.c b/tools/perf/util/module.c
index 3d567fe59c7..0d8c85defcd 100644
--- a/tools/perf/util/module.c
+++ b/tools/perf/util/module.c
@@ -4,6 +4,7 @@
 #include "module.h"
 
 #include <libelf.h>
+#include <libgen.h>
 #include <gelf.h>
 #include <elf.h>
 #include <dirent.h>
@@ -409,35 +410,40 @@ out_failure:
 static int mod_dso__load_module_paths(struct mod_dso *self)
 {
         struct utsname uts;
-        int count = 0, len;
+        int count = 0, len, err = -1;
         char *line = NULL;
         FILE *file;
-        char *path;
+        char *dpath, *dir;
         size_t n;
 
         if (uname(&uts) < 0)
-                goto out_failure;
+                return err;
 
         len = strlen("/lib/modules/");
         len += strlen(uts.release);
         len += strlen("/modules.dep");
 
-        path = calloc(1, len);
-        if (path == NULL)
-                goto out_failure;
+        dpath = calloc(1, len + 1);
+        if (dpath == NULL)
+                return err;
 
-        strcat(path, "/lib/modules/");
-        strcat(path, uts.release);
-        strcat(path, "/modules.dep");
+        strcat(dpath, "/lib/modules/");
+        strcat(dpath, uts.release);
+        strcat(dpath, "/modules.dep");
 
-        file = fopen(path, "r");
-        free(path);
+        file = fopen(dpath, "r");
         if (file == NULL)
                 goto out_failure;
 
+        dir = dirname(dpath);
+        if (!dir)
+                goto out_failure;
+        strcat(dir, "/");
+
         while (!feof(file)) {
-                char *name, *tmp;
                 struct module *module;
+                char *name, *path, *tmp;
+                FILE *modfile;
                 int line_len;
 
                 line_len = getline(&line, &n, file);
@@ -445,17 +451,41 @@ static int mod_dso__load_module_paths(struct mod_dso *self)
                         break;
 
                 if (!line)
-                        goto out_failure;
+                        break;
 
                 line[--line_len] = '\0'; /* \n */
 
-                path = strtok(line, ":");
+                path = strchr(line, ':');
+                if (!path)
+                        break;
+                *path = '\0';
+
+                path = strdup(line);
                 if (!path)
-                        goto out_failure;
+                        break;
+
+                if (!strstr(path, dir)) {
+                        if (strncmp(path, "kernel/", 7))
+                                break;
+
+                        free(path);
+                        path = calloc(1, strlen(dir) + strlen(line) + 1);
+                        if (!path)
+                                break;
+                        strcat(path, dir);
+                        strcat(path, line);
+                }
+
+                modfile = fopen(path, "r");
+                if (modfile == NULL)
+                        break;
+                fclose(modfile);
 
                 name = strdup(path);
-                name = strtok(name, "/");
+                if (!name)
+                        break;
 
+                name = strtok(name, "/");
                 tmp = name;
 
                 while (tmp) {
@@ -463,26 +493,25 @@ static int mod_dso__load_module_paths(struct mod_dso *self)
                         if (tmp)
                                 name = tmp;
                 }
+
                 name = strsep(&name, ".");
+                if (!name)
+                        break;
 
-                /* Quirk: replace '-' with '_' in sound modules */
+                /* Quirk: replace '-' with '_' in all modules */
                 for (len = strlen(name); len; len--) {
                         if (*(name+len) == '-')
                                 *(name+len) = '_';
                 }
 
                 module = module__new(name, path);
-                if (!module) {
-                        fprintf(stderr, "load_module_paths: allocation error\n");
-                        goto out_failure;
-                }
+                if (!module)
+                        break;
                 mod_dso__insert_module(self, module);
 
                 module->sections = sec_dso__new_dso("sections");
-                if (!module->sections) {
-                        fprintf(stderr, "load_module_paths: allocation error\n");
-                        goto out_failure;
-                }
+                if (!module->sections)
+                        break;
 
                 module->active = mod_dso__load_sections(module);
 
@@ -490,13 +519,20 @@ static int mod_dso__load_module_paths(struct mod_dso *self)
                         count++;
         }
 
-        free(line);
-        fclose(file);
-
-        return count;
+        if (feof(file))
+                err = count;
+        else
+                fprintf(stderr, "load_module_paths: modules.dep parsing failure!\n");
 
 out_failure:
-        return -1;
+        if (dpath)
+                free(dpath);
+        if (file)
+                fclose(file);
+        if (line)
+                free(line);
+
+        return err;
 }
 
 int mod_dso__load_modules(struct mod_dso *dso)
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 13ab4b842d4..87c424de79e 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -165,33 +165,31 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
         DIR *sys_dir, *evt_dir;
         struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
         char id_buf[4];
-        int sys_dir_fd, fd;
+        int fd;
         u64 id;
         char evt_path[MAXPATHLEN];
+        char dir_path[MAXPATHLEN];
 
         if (valid_debugfs_mount(debugfs_path))
                 return NULL;
 
         sys_dir = opendir(debugfs_path);
         if (!sys_dir)
-                goto cleanup;
-        sys_dir_fd = dirfd(sys_dir);
+                return NULL;
 
         for_each_subsystem(sys_dir, sys_dirent, sys_next) {
-                int dfd = openat(sys_dir_fd, sys_dirent.d_name,
-                                 O_RDONLY|O_DIRECTORY), evt_dir_fd;
-                if (dfd == -1)
-                        continue;
-                evt_dir = fdopendir(dfd);
-                if (!evt_dir) {
-                        close(dfd);
+
+                snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path,
+                         sys_dirent.d_name);
+                evt_dir = opendir(dir_path);
+                if (!evt_dir)
                         continue;
-                }
-                evt_dir_fd = dirfd(evt_dir);
+
                 for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
-                        snprintf(evt_path, MAXPATHLEN, "%s/id",
+
+                        snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path,
                                  evt_dirent.d_name);
-                        fd = openat(evt_dir_fd, evt_path, O_RDONLY);
+                        fd = open(evt_path, O_RDONLY);
                         if (fd < 0)
                                 continue;
                         if (read(fd, id_buf, sizeof(id_buf)) < 0) {
@@ -225,7 +223,6 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
                 closedir(evt_dir);
         }
 
-cleanup:
         closedir(sys_dir);
         return NULL;
 }
@@ -761,28 +758,24 @@ static void print_tracepoint_events(void)
 {
         DIR *sys_dir, *evt_dir;
         struct dirent *sys_next, *evt_next, sys_dirent, evt_dirent;
-        int sys_dir_fd;
         char evt_path[MAXPATHLEN];
+        char dir_path[MAXPATHLEN];
 
         if (valid_debugfs_mount(debugfs_path))
                 return;
 
         sys_dir = opendir(debugfs_path);
         if (!sys_dir)
-                goto cleanup;
-        sys_dir_fd = dirfd(sys_dir);
+                return;
 
         for_each_subsystem(sys_dir, sys_dirent, sys_next) {
-                int dfd = openat(sys_dir_fd, sys_dirent.d_name,
-                                 O_RDONLY|O_DIRECTORY), evt_dir_fd;
-                if (dfd == -1)
-                        continue;
-                evt_dir = fdopendir(dfd);
-                if (!evt_dir) {
-                        close(dfd);
+
+                snprintf(dir_path, MAXPATHLEN, "%s/%s", debugfs_path,
+                         sys_dirent.d_name);
+                evt_dir = opendir(dir_path);
+                if (!evt_dir)
                         continue;
-                }
-                evt_dir_fd = dirfd(evt_dir);
+
                 for_each_event(sys_dirent, evt_dir, evt_dirent, evt_next) {
                         snprintf(evt_path, MAXPATHLEN, "%s:%s",
                                  sys_dirent.d_name, evt_dirent.d_name);
@@ -791,8 +784,6 @@ static void print_tracepoint_events(void)
                 }
                 closedir(evt_dir);
         }
-
-cleanup:
         closedir(sys_dir);
 }
 
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index a778fd0f4ae..856655d8b0b 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -28,7 +28,7 @@ static u64 turbo_frequency, max_freq;
 
 int svg_page_width = 1000;
 
-#define MIN_TEXT_SIZE 0.001
+#define MIN_TEXT_SIZE 0.01
 
 static u64 total_height;
 static FILE *svgfile;
@@ -217,6 +217,18 @@ static char *cpu_model(void)
                 }
                 fclose(file);
         }
+
+        /* CPU type */
+        file = fopen("/sys/devices/system/cpu/cpu0/cpufreq/scaling_available_frequencies", "r");
+        if (file) {
+                while (fgets(buf, 255, file)) {
+                        unsigned int freq;
+                        freq = strtoull(buf, NULL, 10);
+                        if (freq > max_freq)
+                                max_freq = freq;
+                }
+                fclose(file);
+        }
         return cpu_m;
 }
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index fd3d9c8e90f..47ea0609a76 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -324,8 +324,7 @@ static inline int elf_sym__is_function(const GElf_Sym *sym)
 {
         return elf_sym__type(sym) == STT_FUNC &&
                sym->st_name != 0 &&
-               sym->st_shndx != SHN_UNDEF &&
-               sym->st_size != 0;
+               sym->st_shndx != SHN_UNDEF;
 }
 
 static inline int elf_sym__is_label(const GElf_Sym *sym)
@@ -833,7 +832,7 @@ int dso__load_modules(struct dso *self, symbol_filter_t filter, int v)
         struct mod_dso *mods = mod_dso__new_dso("modules");
         struct module *pos;
         struct rb_node *next;
-        int err;
+        int err, count = 0;
 
         err = mod_dso__load_modules(mods);
 
@@ -852,14 +851,16 @@ int dso__load_modules(struct dso *self, symbol_filter_t filter, int v)
                         break;
 
                 next = rb_next(&pos->rb_node);
+                count += err;
         }
 
         if (err < 0) {
                 mod_dso__delete_modules(mods);
                 mod_dso__delete_self(mods);
+                return err;
         }
 
-        return err;
+        return count;
 }
 
 static inline void dso__fill_symbol_holes(struct dso *self)
@@ -913,8 +914,15 @@ int dso__load_kernel(struct dso *self, const char *vmlinux,
 
         if (vmlinux) {
                 err = dso__load_vmlinux(self, vmlinux, filter, v);
-                if (err > 0 && use_modules)
-                        err = dso__load_modules(self, filter, v);
+                if (err > 0 && use_modules) {
+                        int syms = dso__load_modules(self, filter, v);
+
+                        if (syms < 0) {
+                                fprintf(stderr, "dso__load_modules failed!\n");
+                                return syms;
+                        }
+                        err += syms;
+                }
         }
 
         if (err <= 0)
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index f6a8437141c..55b41b9e383 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -1968,10 +1968,11 @@ static const struct flag flags[] = {
         { "NET_TX_SOFTIRQ", 2 },
         { "NET_RX_SOFTIRQ", 3 },
         { "BLOCK_SOFTIRQ", 4 },
-        { "TASKLET_SOFTIRQ", 5 },
-        { "SCHED_SOFTIRQ", 6 },
-        { "HRTIMER_SOFTIRQ", 7 },
-        { "RCU_SOFTIRQ", 8 },
+        { "BLOCK_IOPOLL_SOFTIRQ", 5 },
+        { "TASKLET_SOFTIRQ", 6 },
+        { "SCHED_SOFTIRQ", 7 },
+        { "HRTIMER_SOFTIRQ", 8 },
+        { "RCU_SOFTIRQ", 9 },
 
         { "HRTIMER_NORESTART", 0 },
         { "HRTIMER_RESTART", 1 },