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>

1 files changed, 105 insertions, 57 deletions

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();