perf events: Change perf parameter --pid to process-wide collection instead of thread-wide

Parameter --pid (or -p) of perf currently means a thread-wide
collection. For exmaple, if a process whose id is 8888 has 10
threads, 'perf top -p 8888' just collects the main thread
statistics. That's misleading. Users are used to attach a whole
process when debugging a process by gdb. To follow normal usage
style, the patch change --pid to process-wide collection and add
--tid (-t) to mean a thread-wide collection.

Usage example is:

 # perf top -p 8888
 # perf record -p 8888 -f sleep 10
 # perf stat -p 8888 -f sleep 10

Above commands collect the statistics of all threads of process
8888.

Signed-off-by: Zhang Yanmin <yanmin_zhang@linux.intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Sheng Yang <sheng@linux.intel.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Jes Sorensen <Jes.Sorensen@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Gleb Natapov <gleb@redhat.com>
Cc: zhiteng.huang@intel.com
Cc: Zachary Amsden <zamsden@redhat.com>
LKML-Reference: <1268922965-14774-3-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

5 files changed, 372 insertions, 193 deletions

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index e2b35ad82a77..bb5b23db4239 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -27,7 +27,7 @@
 #include <unistd.h>
 #include <sched.h>
 
-static int                      fd[MAX_NR_CPUS][MAX_COUNTERS];
+static int                      *fd[MAX_NR_CPUS][MAX_COUNTERS];
 
 static long                     default_interval                =      0;
 
@@ -43,6 +43,9 @@ static int			raw_samples			=      0;
 static int                      system_wide                     =      0;
 static int                      profile_cpu                     =     -1;
 static pid_t                    target_pid                      =     -1;
+static pid_t                    target_tid                      =     -1;
+static pid_t                    *all_tids                       =      NULL;
+static int                      thread_num                      =      0;
 static pid_t                    child_pid                       =     -1;
 static int                      inherit                         =      1;
 static int                      force                           =      0;
@@ -60,7 +63,7 @@ static struct timeval		this_read;
 
 static u64                      bytes_written                   =      0;
 
-static struct pollfd            event_array[MAX_NR_CPUS * MAX_COUNTERS];
+static struct pollfd            *event_array;
 
 static int                      nr_poll                         =      0;
 static int                      nr_cpu                          =      0;
@@ -77,7 +80,7 @@ struct mmap_data {
         unsigned int            prev;
 };
 
-static struct mmap_data         mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
+static struct mmap_data         *mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
 
 static unsigned long mmap_read_head(struct mmap_data *md)
 {
@@ -225,12 +228,13 @@ static struct perf_header_attr *get_header_attr(struct perf_event_attr *a, int n
         return h_attr;
 }
 
-static void create_counter(int counter, int cpu, pid_t pid)
+static void create_counter(int counter, int cpu)
 {
         char *filter = filters[counter];
         struct perf_event_attr *attr = attrs + counter;
         struct perf_header_attr *h_attr;
         int track = !counter; /* only the first counter needs these */
+        int thread_index;
         int ret;
         struct {
                 u64 count;
@@ -280,115 +284,124 @@ static void create_counter(int counter, int cpu, pid_t pid)
                 attr->enable_on_exec = 1;
         }
 
+        for (thread_index = 0; thread_index < thread_num; thread_index++) {
 try_again:
-        fd[nr_cpu][counter] = sys_perf_event_open(attr, pid, cpu, group_fd, 0);
-
-        if (fd[nr_cpu][counter] < 0) {
-                int err = errno;
-
-                if (err == EPERM || err == EACCES)
-                        die("Permission error - are you root?\n"
-                            "\t Consider tweaking /proc/sys/kernel/perf_event_paranoid.\n");
-                else if (err ==  ENODEV && profile_cpu != -1)
-                        die("No such device - did you specify an out-of-range profile CPU?\n");
+                fd[nr_cpu][counter][thread_index] = sys_perf_event_open(attr,
+                                all_tids[thread_index], cpu, group_fd, 0);
+
+                if (fd[nr_cpu][counter][thread_index] < 0) {
+                        int err = errno;
+
+                        if (err == EPERM || err == EACCES)
+                                die("Permission error - are you root?\n"
+                                        "\t Consider tweaking"
+                                        " /proc/sys/kernel/perf_event_paranoid.\n");
+                        else if (err ==  ENODEV && profile_cpu != -1) {
+                                die("No such device - did you specify"
+                                        " an out-of-range profile CPU?\n");
+                        }
 
-                /*
-                 * If it's cycles then fall back to hrtimer
-                 * based cpu-clock-tick sw counter, which
-                 * is always available even if no PMU support:
-                 */
-                if (attr->type == PERF_TYPE_HARDWARE
-                        && attr->config == PERF_COUNT_HW_CPU_CYCLES) {
-
-                        if (verbose)
-                                warning(" ... trying to fall back to cpu-clock-ticks\n");
-                        attr->type = PERF_TYPE_SOFTWARE;
-                        attr->config = PERF_COUNT_SW_CPU_CLOCK;
-                        goto try_again;
-                }
-                printf("\n");
-                error("perfcounter syscall returned with %d (%s)\n",
-                        fd[nr_cpu][counter], strerror(err));
+                        /*
+                         * If it's cycles then fall back to hrtimer
+                         * based cpu-clock-tick sw counter, which
+                         * is always available even if no PMU support:
+                         */
+                        if (attr->type == PERF_TYPE_HARDWARE
+                                        && attr->config == PERF_COUNT_HW_CPU_CYCLES) {
+
+                                if (verbose)
+                                        warning(" ... trying to fall back to cpu-clock-ticks\n");
+                                attr->type = PERF_TYPE_SOFTWARE;
+                                attr->config = PERF_COUNT_SW_CPU_CLOCK;
+                                goto try_again;
+                        }
+                        printf("\n");
+                        error("perfcounter syscall returned with %d (%s)\n",
+                                        fd[nr_cpu][counter][thread_index], strerror(err));
 
 #if defined(__i386__) || defined(__x86_64__)
-                if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP)
-                        die("No hardware sampling interrupt available. No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.\n");
+                        if (attr->type == PERF_TYPE_HARDWARE && err == EOPNOTSUPP)
+                                die("No hardware sampling interrupt available."
+                                    " No APIC? If so then you can boot the kernel"
+                                    " with the \"lapic\" boot parameter to"
+                                    " force-enable it.\n");
 #endif
 
-                die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
-                exit(-1);
-        }
+                        die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
+                        exit(-1);
+                }
 
-        h_attr = get_header_attr(attr, counter);
-        if (h_attr == NULL)
-                die("nomem\n");
+                h_attr = get_header_attr(attr, counter);
+                if (h_attr == NULL)
+                        die("nomem\n");
 
-        if (!file_new) {
-                if (memcmp(&h_attr->attr, attr, sizeof(*attr))) {
-                        fprintf(stderr, "incompatible append\n");
-                        exit(-1);
+                if (!file_new) {
+                        if (memcmp(&h_attr->attr, attr, sizeof(*attr))) {
+                                fprintf(stderr, "incompatible append\n");
+                                exit(-1);
+                        }
                 }
-        }
 
-        if (read(fd[nr_cpu][counter], &read_data, sizeof(read_data)) == -1) {
-                perror("Unable to read perf file descriptor\n");
-                exit(-1);
-        }
+                if (read(fd[nr_cpu][counter][thread_index], &read_data, sizeof(read_data)) == -1) {
+                        perror("Unable to read perf file descriptor\n");
+                        exit(-1);
+                }
 
-        if (perf_header_attr__add_id(h_attr, read_data.id) < 0) {
-                pr_warning("Not enough memory to add id\n");
-                exit(-1);
-        }
+                if (perf_header_attr__add_id(h_attr, read_data.id) < 0) {
+                        pr_warning("Not enough memory to add id\n");
+                        exit(-1);
+                }
 
-        assert(fd[nr_cpu][counter] >= 0);
-        fcntl(fd[nr_cpu][counter], F_SETFL, O_NONBLOCK);
+                assert(fd[nr_cpu][counter][thread_index] >= 0);
+                fcntl(fd[nr_cpu][counter][thread_index], F_SETFL, O_NONBLOCK);
 
-        /*
-         * First counter acts as the group leader:
-         */
-        if (group && group_fd == -1)
-                group_fd = fd[nr_cpu][counter];
-        if (multiplex && multiplex_fd == -1)
-                multiplex_fd = fd[nr_cpu][counter];
+                /*
+                 * First counter acts as the group leader:
+                 */
+                if (group && group_fd == -1)
+                        group_fd = fd[nr_cpu][counter][thread_index];
+                if (multiplex && multiplex_fd == -1)
+                        multiplex_fd = fd[nr_cpu][counter][thread_index];
 
-        if (multiplex && fd[nr_cpu][counter] != multiplex_fd) {
+                if (multiplex && fd[nr_cpu][counter][thread_index] != multiplex_fd) {
 
-                ret = ioctl(fd[nr_cpu][counter], PERF_EVENT_IOC_SET_OUTPUT, multiplex_fd);
-                assert(ret != -1);
-        } else {
-                event_array[nr_poll].fd = fd[nr_cpu][counter];
-                event_array[nr_poll].events = POLLIN;
-                nr_poll++;
-
-                mmap_array[nr_cpu][counter].counter = counter;
-                mmap_array[nr_cpu][counter].prev = 0;
-                mmap_array[nr_cpu][counter].mask = mmap_pages*page_size - 1;
-                mmap_array[nr_cpu][counter].base = mmap(NULL, (mmap_pages+1)*page_size,
-                                PROT_READ|PROT_WRITE, MAP_SHARED, fd[nr_cpu][counter], 0);
-                if (mmap_array[nr_cpu][counter].base == MAP_FAILED) {
-                        error("failed to mmap with %d (%s)\n", errno, strerror(errno));
-                        exit(-1);
+                        ret = ioctl(fd[nr_cpu][counter][thread_index], PERF_EVENT_IOC_SET_OUTPUT, multiplex_fd);
+                        assert(ret != -1);
+                } else {
+                        event_array[nr_poll].fd = fd[nr_cpu][counter][thread_index];
+                        event_array[nr_poll].events = POLLIN;
+                        nr_poll++;
+
+                        mmap_array[nr_cpu][counter][thread_index].counter = counter;
+                        mmap_array[nr_cpu][counter][thread_index].prev = 0;
+                        mmap_array[nr_cpu][counter][thread_index].mask = mmap_pages*page_size - 1;
+                        mmap_array[nr_cpu][counter][thread_index].base = mmap(NULL, (mmap_pages+1)*page_size,
+                                PROT_READ|PROT_WRITE, MAP_SHARED, fd[nr_cpu][counter][thread_index], 0);
+                        if (mmap_array[nr_cpu][counter][thread_index].base == MAP_FAILED) {
+                                error("failed to mmap with %d (%s)\n", errno, strerror(errno));
+                                exit(-1);
+                        }
                 }
-        }
 
-        if (filter != NULL) {
-                ret = ioctl(fd[nr_cpu][counter],
-                            PERF_EVENT_IOC_SET_FILTER, filter);
-                if (ret) {
-                        error("failed to set filter with %d (%s)\n", errno,
-                              strerror(errno));
-                        exit(-1);
+                if (filter != NULL) {
+                        ret = ioctl(fd[nr_cpu][counter][thread_index],
+                                        PERF_EVENT_IOC_SET_FILTER, filter);
+                        if (ret) {
+                                error("failed to set filter with %d (%s)\n", errno,
+                                                strerror(errno));
+                                exit(-1);
+                        }
                 }
         }
 }
 
-static void open_counters(int cpu, pid_t pid)
+static void open_counters(int cpu)
 {
         int counter;
 
         group_fd = -1;
         for (counter = 0; counter < nr_counters; counter++)
-                create_counter(counter, cpu, pid);
+                create_counter(counter, cpu);
 
         nr_cpu++;
 }
@@ -529,6 +542,9 @@ static int __cmd_record(int argc, const char **argv)
                         exit(-1);
                 }
 
+                if (!system_wide && target_tid == -1 && target_pid == -1)
+                        all_tids[0] = child_pid;
+
                 close(child_ready_pipe[1]);
                 close(go_pipe[0]);
                 /*
@@ -541,17 +557,12 @@ static int __cmd_record(int argc, const char **argv)
                 close(child_ready_pipe[0]);
         }
 
-        if (forks && target_pid == -1 && !system_wide)
-                pid = child_pid;
-        else
-                pid = target_pid;
-
         if ((!system_wide && !inherit) || profile_cpu != -1) {
-                open_counters(profile_cpu, pid);
+                open_counters(profile_cpu);
         } else {
                 nr_cpus = read_cpu_map();
                 for (i = 0; i < nr_cpus; i++)
-                        open_counters(cpumap[i], pid);
+                        open_counters(cpumap[i]);
         }
 
         if (file_new) {
@@ -576,7 +587,7 @@ static int __cmd_record(int argc, const char **argv)
         }
 
         if (!system_wide && profile_cpu == -1)
-                event__synthesize_thread(target_pid, process_synthesized_event,
+                event__synthesize_thread(target_tid, process_synthesized_event,
                                          session);
         else
                 event__synthesize_threads(process_synthesized_event, session);
@@ -599,11 +610,16 @@ static int __cmd_record(int argc, const char **argv)
 
         for (;;) {
                 int hits = samples;
+                int thread;
 
                 for (i = 0; i < nr_cpu; i++) {
                         for (counter = 0; counter < nr_counters; counter++) {
-                                if (mmap_array[i][counter].base)
-                                        mmap_read(&mmap_array[i][counter]);
+                                for (thread = 0;
+                                        thread < thread_num; thread++) {
+                                        if (mmap_array[i][counter][thread].base)
+                                                mmap_read(&mmap_array[i][counter][thread]);
+                                }
+
                         }
                 }
 
@@ -616,8 +632,15 @@ static int __cmd_record(int argc, const char **argv)
 
                 if (done) {
                         for (i = 0; i < nr_cpu; i++) {
-                                for (counter = 0; counter < nr_counters; counter++)
-                                        ioctl(fd[i][counter], PERF_EVENT_IOC_DISABLE);
+                                for (counter = 0;
+                                        counter < nr_counters;
+                                        counter++) {
+                                        for (thread = 0;
+                                                thread < thread_num;
+                                                thread++)
+                                                ioctl(fd[i][counter][thread],
+                                                        PERF_EVENT_IOC_DISABLE);
+                                }
                         }
                 }
         }
@@ -649,7 +672,9 @@ static const struct option options[] = {
         OPT_CALLBACK(0, "filter", NULL, "filter",
                      "event filter", parse_filter),
         OPT_INTEGER('p', "pid", &target_pid,
-                    "record events on existing pid"),
+                    "record events on existing process id"),
+        OPT_INTEGER('t', "tid", &target_tid,
+                    "record events on existing thread id"),
         OPT_INTEGER('r', "realtime", &realtime_prio,
                     "collect data with this RT SCHED_FIFO priority"),
         OPT_BOOLEAN('R', "raw-samples", &raw_samples,
@@ -690,10 +715,12 @@ static const struct option options[] = {
 int cmd_record(int argc, const char **argv, const char *prefix __used)
 {
         int counter;
+        int i,j;
 
         argc = parse_options(argc, argv, options, record_usage,
                             PARSE_OPT_STOP_AT_NON_OPTION);
-        if (!argc && target_pid == -1 && !system_wide && profile_cpu == -1)
+        if (!argc && target_pid == -1 && target_tid == -1 &&
+                !system_wide && profile_cpu == -1)
                 usage_with_options(record_usage, options);
 
         symbol__init();
@@ -704,6 +731,37 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
                 attrs[0].config = PERF_COUNT_HW_CPU_CYCLES;
         }
 
+        if (target_pid != -1) {
+                target_tid = target_pid;
+                thread_num = find_all_tid(target_pid, &all_tids);
+                if (thread_num <= 0) {
+                        fprintf(stderr, "Can't find all threads of pid %d\n",
+                                        target_pid);
+                        usage_with_options(record_usage, options);
+                }
+        } else {
+                all_tids=malloc(sizeof(pid_t));
+                if (!all_tids)
+                        return -ENOMEM;
+
+                all_tids[0] = target_tid;
+                thread_num = 1;
+        }
+
+        for (i = 0; i < MAX_NR_CPUS; i++) {
+                for (j = 0; j < MAX_COUNTERS; j++) {
+                        fd[i][j] = malloc(sizeof(int)*thread_num);
+                        mmap_array[i][j] = malloc(
+                                sizeof(struct mmap_data)*thread_num);
+                        if (!fd[i][j] || !mmap_array[i][j])
+                                return -ENOMEM;
+                }
+        }
+        event_array = malloc(
+                sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num);
+        if (!event_array)
+                return -ENOMEM;
+
         /*
          * User specified count overrides default frequency.
          */
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 5f41244cbbf2..c92f90ff5a9f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -46,6 +46,7 @@
 #include "util/debug.h"
 #include "util/header.h"
 #include "util/cpumap.h"
+#include "util/thread.h"
 
 #include <sys/prctl.h>
 #include <math.h>
@@ -74,10 +75,13 @@ static int			run_count			=  1;
 static int                      inherit                         =  1;
 static int                      scale                           =  1;
 static pid_t                    target_pid                      = -1;
+static pid_t                    target_tid                      = -1;
+static pid_t                    *all_tids                       =  NULL;
+static int                      thread_num                      =  0;
 static pid_t                    child_pid                       = -1;
 static int                      null_run                        =  0;
 
-static int                      fd[MAX_NR_CPUS][MAX_COUNTERS];
+static int                      *fd[MAX_NR_CPUS][MAX_COUNTERS];
 
 static int                      event_scaled[MAX_COUNTERS];
 
@@ -140,9 +144,10 @@ struct stats			runtime_branches_stats;
 #define ERR_PERF_OPEN \
 "Error: counter %d, sys_perf_event_open() syscall returned with %d (%s)\n"
 
-static void create_perf_stat_counter(int counter, int pid)
+static void create_perf_stat_counter(int counter)
 {
         struct perf_event_attr *attr = attrs + counter;
+        int thread;
 
         if (scale)
                 attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
@@ -152,10 +157,11 @@ static void create_perf_stat_counter(int counter, int pid)
                 unsigned int cpu;
 
                 for (cpu = 0; cpu < nr_cpus; cpu++) {
-                        fd[cpu][counter] = sys_perf_event_open(attr, -1, cpumap[cpu], -1, 0);
-                        if (fd[cpu][counter] < 0 && verbose)
+                        fd[cpu][counter][0] = sys_perf_event_open(attr,
+                                        -1, cpumap[cpu], -1, 0);
+                        if (fd[cpu][counter][0] < 0 && verbose)
                                 fprintf(stderr, ERR_PERF_OPEN, counter,
-                                        fd[cpu][counter], strerror(errno));
+                                        fd[cpu][counter][0], strerror(errno));
                 }
         } else {
                 attr->inherit        = inherit;
@@ -163,11 +169,14 @@ static void create_perf_stat_counter(int counter, int pid)
                         attr->disabled = 1;
                         attr->enable_on_exec = 1;
                 }
-
-                fd[0][counter] = sys_perf_event_open(attr, pid, -1, -1, 0);
-                if (fd[0][counter] < 0 && verbose)
-                        fprintf(stderr, ERR_PERF_OPEN, counter,
-                                fd[0][counter], strerror(errno));
+                for (thread = 0; thread < thread_num; thread++) {
+                        fd[0][counter][thread] = sys_perf_event_open(attr,
+                                all_tids[thread], -1, -1, 0);
+                        if (fd[0][counter][thread] < 0 && verbose)
+                                fprintf(stderr, ERR_PERF_OPEN, counter,
+                                        fd[0][counter][thread],
+                                        strerror(errno));
+                }
         }
 }
 
@@ -192,25 +201,28 @@ static void read_counter(int counter)
         unsigned int cpu;
         size_t res, nv;
         int scaled;
-        int i;
+        int i, thread;
 
         count[0] = count[1] = count[2] = 0;
 
         nv = scale ? 3 : 1;
         for (cpu = 0; cpu < nr_cpus; cpu++) {
-                if (fd[cpu][counter] < 0)
-                        continue;
-
-                res = read(fd[cpu][counter], single_count, nv * sizeof(u64));
-                assert(res == nv * sizeof(u64));
-
-                close(fd[cpu][counter]);
-                fd[cpu][counter] = -1;
-
-                count[0] += single_count[0];
-                if (scale) {
-                        count[1] += single_count[1];
-                        count[2] += single_count[2];
+                for (thread = 0; thread < thread_num; thread++) {
+                        if (fd[cpu][counter][thread] < 0)
+                                continue;
+
+                        res = read(fd[cpu][counter][thread],
+                                        single_count, nv * sizeof(u64));
+                        assert(res == nv * sizeof(u64));
+
+                        close(fd[cpu][counter][thread]);
+                        fd[cpu][counter][thread] = -1;
+
+                        count[0] += single_count[0];
+                        if (scale) {
+                                count[1] += single_count[1];
+                                count[2] += single_count[2];
+                        }
                 }
         }
 
@@ -253,7 +265,6 @@ static int run_perf_stat(int argc __used, const char **argv)
         unsigned long long t0, t1;
         int status = 0;
         int counter;
-        int pid;
         int child_ready_pipe[2], go_pipe[2];
         const bool forks = (argc > 0);
         char buf;
@@ -299,6 +310,9 @@ static int run_perf_stat(int argc __used, const char **argv)
                         exit(-1);
                 }
 
+                if (target_tid == -1 && target_pid == -1 && !system_wide)
+                        all_tids[0] = child_pid;
+
                 /*
                  * Wait for the child to be ready to exec.
                  */
@@ -309,12 +323,8 @@ static int run_perf_stat(int argc __used, const char **argv)
                 close(child_ready_pipe[0]);
         }
 
-        if (target_pid == -1)
-                pid = child_pid;
-        else
-                pid = target_pid;
         for (counter = 0; counter < nr_counters; counter++)
-                create_perf_stat_counter(counter, pid);
+                create_perf_stat_counter(counter);
 
         /*
          * Enable counters and exec the command:
@@ -433,12 +443,14 @@ static void print_stat(int argc, const char **argv)
 
         fprintf(stderr, "\n");
         fprintf(stderr, " Performance counter stats for ");
-        if(target_pid == -1) {
+        if(target_pid == -1 && target_tid == -1) {
                 fprintf(stderr, "\'%s", argv[0]);
                 for (i = 1; i < argc; i++)
                         fprintf(stderr, " %s", argv[i]);
-        }else
-                fprintf(stderr, "task pid \'%d", target_pid);
+        } else if (target_pid != -1)
+                fprintf(stderr, "process id \'%d", target_pid);
+        else
+                fprintf(stderr, "thread id \'%d", target_tid);
 
         fprintf(stderr, "\'");
         if (run_count > 1)
@@ -493,7 +505,9 @@ static const struct option options[] = {
         OPT_BOOLEAN('i', "inherit", &inherit,
                     "child tasks inherit counters"),
         OPT_INTEGER('p', "pid", &target_pid,
-                    "stat events on existing pid"),
+                    "stat events on existing process id"),
+        OPT_INTEGER('t', "tid", &target_tid,
+                    "stat events on existing thread id"),
         OPT_BOOLEAN('a', "all-cpus", &system_wide,
                     "system-wide collection from all CPUs"),
         OPT_BOOLEAN('c', "scale", &scale,
@@ -510,10 +524,11 @@ static const struct option options[] = {
 int cmd_stat(int argc, const char **argv, const char *prefix __used)
 {
         int status;
+        int i,j;
 
         argc = parse_options(argc, argv, options, stat_usage,
                 PARSE_OPT_STOP_AT_NON_OPTION);
-        if (!argc && target_pid == -1)
+        if (!argc && target_pid == -1 && target_tid == -1)
                 usage_with_options(stat_usage, options);
         if (run_count <= 0)
                 usage_with_options(stat_usage, options);
@@ -529,6 +544,31 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
         else
                 nr_cpus = 1;
 
+        if (target_pid != -1) {
+                target_tid = target_pid;
+                thread_num = find_all_tid(target_pid, &all_tids);
+                if (thread_num <= 0) {
+                        fprintf(stderr, "Can't find all threads of pid %d\n",
+                                        target_pid);
+                        usage_with_options(stat_usage, options);
+                }
+        } else {
+                all_tids=malloc(sizeof(pid_t));
+                if (!all_tids)
+                        return -ENOMEM;
+
+                all_tids[0] = target_tid;
+                thread_num = 1;
+        }
+
+        for (i = 0; i < MAX_NR_CPUS; i++) {
+                for (j = 0; j < MAX_COUNTERS; j++) {
+                        fd[i][j] = malloc(sizeof(int)*thread_num);
+                        if (!fd[i][j])
+                                return -ENOMEM;
+                }
+        }
+
         /*
          * We dont want to block the signals - that would cause
          * child tasks to inherit that and Ctrl-C would not work.
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 887ebbf5d1ff..5f3ac9ff354d 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -55,7 +55,7 @@
 #include <linux/unistd.h>
 #include <linux/types.h>
 
-static int                      fd[MAX_NR_CPUS][MAX_COUNTERS];
+static int                      *fd[MAX_NR_CPUS][MAX_COUNTERS];
 
 static int                      system_wide                     =      0;
 
@@ -65,6 +65,9 @@ static int			count_filter			=      5;
 static int                      print_entries;
 
 static int                      target_pid                      =     -1;
+static int                      target_tid                      =     -1;
+static pid_t                    *all_tids                       =      NULL;
+static int                      thread_num                      =      0;
 static int                      inherit                         =      0;
 static int                      profile_cpu                     =     -1;
 static int                      nr_cpus                         =      0;
@@ -524,13 +527,15 @@ static void print_sym_table(void)
 
         if (target_pid != -1)
                 printf(" (target_pid: %d", target_pid);
+        else if (target_tid != -1)
+                printf(" (target_tid: %d", target_tid);
         else
                 printf(" (all");
 
         if (profile_cpu != -1)
                 printf(", cpu: %d)\n", profile_cpu);
         else {
-                if (target_pid != -1)
+                if (target_tid != -1)
                         printf(")\n");
                 else
                         printf(", %d CPUs)\n", nr_cpus);
@@ -1129,16 +1134,21 @@ static void perf_session__mmap_read_counter(struct perf_session *self,
         md->prev = old;
 }
 
-static struct pollfd event_array[MAX_NR_CPUS * MAX_COUNTERS];
-static struct mmap_data mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
+static struct pollfd *event_array;
+static struct mmap_data *mmap_array[MAX_NR_CPUS][MAX_COUNTERS];
 
 static void perf_session__mmap_read(struct perf_session *self)
 {
-        int i, counter;
+        int i, counter, thread_index;
 
         for (i = 0; i < nr_cpus; i++) {
                 for (counter = 0; counter < nr_counters; counter++)
-                        perf_session__mmap_read_counter(self, &mmap_array[i][counter]);
+                        for (thread_index = 0;
+                                thread_index < thread_num;
+                                thread_index++) {
+                                perf_session__mmap_read_counter(self,
+                                        &mmap_array[i][counter][thread_index]);
+                        }
         }
 }
 
@@ -1149,9 +1159,10 @@ static void start_counter(int i, int counter)
 {
         struct perf_event_attr *attr;
         int cpu;
+        int thread_index;
 
         cpu = profile_cpu;
-        if (target_pid == -1 && profile_cpu == -1)
+        if (target_tid == -1 && profile_cpu == -1)
                 cpu = cpumap[i];
 
         attr = attrs + counter;
@@ -1167,55 +1178,58 @@ static void start_counter(int i, int counter)
         attr->inherit           = (cpu < 0) && inherit;
         attr->mmap              = 1;
 
+        for (thread_index = 0; thread_index < thread_num; thread_index++) {
 try_again:
-        fd[i][counter] = sys_perf_event_open(attr, target_pid, cpu, group_fd, 0);
-
-        if (fd[i][counter] < 0) {
-                int err = errno;
+                fd[i][counter][thread_index] = sys_perf_event_open(attr,
+                                all_tids[thread_index], cpu, group_fd, 0);
+
+                if (fd[i][counter][thread_index] < 0) {
+                        int err = errno;
+
+                        if (err == EPERM || err == EACCES)
+                                die("No permission - are you root?\n");
+                        /*
+                         * If it's cycles then fall back to hrtimer
+                         * based cpu-clock-tick sw counter, which
+                         * is always available even if no PMU support:
+                         */
+                        if (attr->type == PERF_TYPE_HARDWARE
+                                        && attr->config == PERF_COUNT_HW_CPU_CYCLES) {
+
+                                if (verbose)
+                                        warning(" ... trying to fall back to cpu-clock-ticks\n");
+
+                                attr->type = PERF_TYPE_SOFTWARE;
+                                attr->config = PERF_COUNT_SW_CPU_CLOCK;
+                                goto try_again;
+                        }
+                        printf("\n");
+                        error("perfcounter syscall returned with %d (%s)\n",
+                                        fd[i][counter][thread_index], strerror(err));
+                        die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
+                        exit(-1);
+                }
+                assert(fd[i][counter][thread_index] >= 0);
+                fcntl(fd[i][counter][thread_index], F_SETFL, O_NONBLOCK);
 
-                if (err == EPERM || err == EACCES)
-                        die("No permission - are you root?\n");
                 /*
-                 * If it's cycles then fall back to hrtimer
-                 * based cpu-clock-tick sw counter, which
-                 * is always available even if no PMU support:
+                 * First counter acts as the group leader:
                  */
-                if (attr->type == PERF_TYPE_HARDWARE
-                        && attr->config == PERF_COUNT_HW_CPU_CYCLES) {
-
-                        if (verbose)
-                                warning(" ... trying to fall back to cpu-clock-ticks\n");
-
-                        attr->type = PERF_TYPE_SOFTWARE;
-                        attr->config = PERF_COUNT_SW_CPU_CLOCK;
-                        goto try_again;
-                }
-                printf("\n");
-                error("perfcounter syscall returned with %d (%s)\n",
-                        fd[i][counter], strerror(err));
-                die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
-                exit(-1);
+                if (group && group_fd == -1)
+                        group_fd = fd[i][counter][thread_index];
+
+                event_array[nr_poll].fd = fd[i][counter][thread_index];
+                event_array[nr_poll].events = POLLIN;
+                nr_poll++;
+
+                mmap_array[i][counter][thread_index].counter = counter;
+                mmap_array[i][counter][thread_index].prev = 0;
+                mmap_array[i][counter][thread_index].mask = mmap_pages*page_size - 1;
+                mmap_array[i][counter][thread_index].base = mmap(NULL, (mmap_pages+1)*page_size,
+                                PROT_READ, MAP_SHARED, fd[i][counter][thread_index], 0);
+                if (mmap_array[i][counter][thread_index].base == MAP_FAILED)
+                        die("failed to mmap with %d (%s)\n", errno, strerror(errno));
         }
-        assert(fd[i][counter] >= 0);
-        fcntl(fd[i][counter], F_SETFL, O_NONBLOCK);
-
-        /*
-         * First counter acts as the group leader:
-         */
-        if (group && group_fd == -1)
-                group_fd = fd[i][counter];
-
-        event_array[nr_poll].fd = fd[i][counter];
-        event_array[nr_poll].events = POLLIN;
-        nr_poll++;
-
-        mmap_array[i][counter].counter = counter;
-        mmap_array[i][counter].prev = 0;
-        mmap_array[i][counter].mask = mmap_pages*page_size - 1;
-        mmap_array[i][counter].base = mmap(NULL, (mmap_pages+1)*page_size,
-                        PROT_READ, MAP_SHARED, fd[i][counter], 0);
-        if (mmap_array[i][counter].base == MAP_FAILED)
-                die("failed to mmap with %d (%s)\n", errno, strerror(errno));
 }
 
 static int __cmd_top(void)
@@ -1231,8 +1245,8 @@ static int __cmd_top(void)
         if (session == NULL)
                 return -ENOMEM;
 
-        if (target_pid != -1)
-                event__synthesize_thread(target_pid, event__process, session);
+        if (target_tid != -1)
+                event__synthesize_thread(target_tid, event__process, session);
         else
                 event__synthesize_threads(event__process, session);
 
@@ -1243,7 +1257,7 @@ static int __cmd_top(void)
         }
 
         /* Wait for a minimal set of events before starting the snapshot */
-        poll(event_array, nr_poll, 100);
+        poll(&event_array[0], nr_poll, 100);
 
         perf_session__mmap_read(session);
 
@@ -1286,7 +1300,9 @@ static const struct option options[] = {
         OPT_INTEGER('c', "count", &default_interval,
                     "event period to sample"),
         OPT_INTEGER('p', "pid", &target_pid,
-                    "profile events on existing pid"),
+                    "profile events on existing process id"),
+        OPT_INTEGER('t', "tid", &target_tid,
+                    "profile events on existing thread id"),
         OPT_BOOLEAN('a', "all-cpus", &system_wide,
                             "system-wide collection from all CPUs"),
         OPT_INTEGER('C', "CPU", &profile_cpu,
@@ -1327,6 +1343,7 @@ static const struct option options[] = {
 int cmd_top(int argc, const char **argv, const char *prefix __used)
 {
         int counter;
+        int i,j;
 
         page_size = sysconf(_SC_PAGE_SIZE);
 
@@ -1334,8 +1351,39 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
         if (argc)
                 usage_with_options(top_usage, options);
 
+        if (target_pid != -1) {
+                target_tid = target_pid;
+                thread_num = find_all_tid(target_pid, &all_tids);
+                if (thread_num <= 0) {
+                        fprintf(stderr, "Can't find all threads of pid %d\n",
+                                target_pid);
+                        usage_with_options(top_usage, options);
+                }
+        } else {
+                all_tids=malloc(sizeof(pid_t));
+                if (!all_tids)
+                        return -ENOMEM;
+
+                all_tids[0] = target_tid;
+                thread_num = 1;
+        }
+
+        for (i = 0; i < MAX_NR_CPUS; i++) {
+                for (j = 0; j < MAX_COUNTERS; j++) {
+                        fd[i][j] = malloc(sizeof(int)*thread_num);
+                        mmap_array[i][j] = malloc(
+                                sizeof(struct mmap_data)*thread_num);
+                        if (!fd[i][j] || !mmap_array[i][j])
+                                return -ENOMEM;
+                }
+        }
+        event_array = malloc(
+                sizeof(struct pollfd)*MAX_NR_CPUS*MAX_COUNTERS*thread_num);
+        if (!event_array)
+                return -ENOMEM;
+
         /* CPU and PID are mutually exclusive */
-        if (target_pid != -1 && profile_cpu != -1) {
+        if (target_tid > 0 && profile_cpu != -1) {
                 printf("WARNING: PID switch overriding CPU\n");
                 sleep(1);
                 profile_cpu = -1;
@@ -1376,7 +1424,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __used)
                 attrs[counter].sample_period = default_interval;
         }
 
-        if (target_pid != -1 || profile_cpu != -1)
+        if (target_tid != -1 || profile_cpu != -1)
                 nr_cpus = 1;
         else
                 nr_cpus = read_cpu_map();
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index fa968312ee7d..ea6506234d57 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -7,6 +7,37 @@
 #include "util.h"
 #include "debug.h"
 
+int find_all_tid(int pid, pid_t ** all_tid)
+{
+        char name[256];
+        int items;
+        struct dirent **namelist = NULL;
+        int ret = 0;
+        int i;
+
+        sprintf(name, "/proc/%d/task", pid);
+        items = scandir(name, &namelist, NULL, NULL);
+        if (items <= 0)
+                return -ENOENT;
+        *all_tid = malloc(sizeof(pid_t) * items);
+        if (!*all_tid) {
+                ret = -ENOMEM;
+                goto failure;
+        }
+
+        for (i = 0; i < items; i++)
+                (*all_tid)[i] = atoi(namelist[i]->d_name);
+
+        ret = items;
+
+failure:
+        for (i=0; i<items; i++)
+                free(namelist[i]);
+        free(namelist);
+
+        return ret;
+}
+
 void map_groups__init(struct map_groups *self)
 {
         int i;
@@ -348,3 +379,4 @@ struct symbol *map_groups__find_symbol(struct map_groups *self,
 
         return NULL;
 }
+
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index dcf70303e58e..a81426a891bf 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -23,6 +23,7 @@ struct thread {
         int                     comm_len;
 };
 
+int find_all_tid(int pid, pid_t ** all_tid);
 void map_groups__init(struct map_groups *self);
 int thread__set_comm(struct thread *self, const char *comm);
 int thread__comm_len(struct thread *self);