perf tools: Store the cpu socket and core ids in the perf.data header

This patch stores the cpu socket_id and core_id in a perf.data header,
and reads them into the perf_env struct when processing perf.data files.

The changes modifies the CPU_TOPOLOGY section, making sure it is
backward/forward compatible.

The patch checks the section size before reading the core and socket ids.

It never reads data crossing the section boundary.  An old perf binary
without this patch can also correctly read the perf.data from a new perf
with this patch.

Because the new info is added at the end of the cpu_topology section, an
old perf tool ignores the extra data.

Examples:

1. New perf with this patch read perf.data from an old perf without the
   patch:

  $ perf_new report -i perf_old.data --header-only -I
  ......
  # sibling threads : 33
  # sibling threads : 34
  # sibling threads : 35
  # Core ID and Socket ID information is not available
  # node0 meminfo  : total = 32823872 kB, free = 29315548 kB
  # node0 cpu list : 0-17,36-53
  ......

2. Old perf without the patch reads perf.data from a new perf with the
   patch:

  $ perf_old report -i perf_new.data --header-only -I
  ......
  # sibling threads : 33
  # sibling threads : 34
  # sibling threads : 35
  # node0 meminfo  : total = 32823872 kB, free = 29190932 kB
  # node0 cpu list : 0-17,36-53
  ......

3. New perf read new perf.data:

  $ perf_new report -i perf_new.data --header-only -I
  ......
  # sibling threads : 33
  # sibling threads : 34
  # sibling threads : 35
  # CPU 0: Core ID 0, Socket ID 0
  # CPU 1: Core ID 1, Socket ID 0
  ......
  # CPU 61: Core ID 10, Socket ID 1
  # CPU 62: Core ID 11, Socket ID 1
  # CPU 63: Core ID 16, Socket ID 1
  # node0 meminfo  : total = 32823872 kB, free = 29190932 kB
  # node0 cpu list : 0-17,36-53

Signed-off-by: Kan Liang <kan.liang@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/1441115893-22006-2-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 41814547da159a14ac00eca8c774f3a46ae20558..8fd7b7de1acd702b64a91d5368f2ca8a650a09f2 100644 (file)
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -88,6 +88,9 @@ int write_padded(int fd, const void *bf, size_t count, size_t count_aligned)
        return err;
 }
 
+#define string_size(str)                                               \
+       (PERF_ALIGN((strlen(str) + 1), NAME_ALIGN) + sizeof(u32))
+
 static int do_write_string(int fd, const char *str)
 {
        u32 len, olen;
@@ -441,10 +444,13 @@ static int write_cmdline(int fd, struct perf_header *h __maybe_unused,
        "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list"
 
 struct cpu_topo {
+       u32 cpu_nr;
        u32 core_sib;
        u32 thread_sib;
        char **core_siblings;
        char **thread_siblings;
+       int *core_id;
+       int *phy_pkg_id;
 };
 
 static int build_cpu_topo(struct cpu_topo *tp, int cpu)
@@ -507,6 +513,9 @@ try_threads:
        }
        ret = 0;
 done:
+       tp->core_id[cpu] = cpu_map__get_core_id(cpu);
+       tp->phy_pkg_id[cpu] = cpu_map__get_socket_id(cpu);
+
        if(fp)
                fclose(fp);
        free(buf);
@@ -534,7 +543,7 @@ static struct cpu_topo *build_cpu_topology(void)
        struct cpu_topo *tp;
        void *addr;
        u32 nr, i;
-       size_t sz;
+       size_t sz, sz_id;
        long ncpus;
        int ret = -1;
 
@@ -545,17 +554,22 @@ static struct cpu_topo *build_cpu_topology(void)
        nr = (u32)(ncpus & UINT_MAX);
 
        sz = nr * sizeof(char *);
+       sz_id = nr * sizeof(int);
 
-       addr = calloc(1, sizeof(*tp) + 2 * sz);
+       addr = calloc(1, sizeof(*tp) + 2 * sz + 2 * sz_id);
        if (!addr)
                return NULL;
 
        tp = addr;
-
+       tp->cpu_nr = nr;
        addr += sizeof(*tp);
        tp->core_siblings = addr;
        addr += sz;
        tp->thread_siblings = addr;
+       addr += sz;
+       tp->core_id = addr;
+       addr += sz_id;
+       tp->phy_pkg_id = addr;
 
        for (i = 0; i < nr; i++) {
                ret = build_cpu_topo(tp, i);
@@ -598,6 +612,15 @@ static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused,
                if (ret < 0)
                        break;
        }
+
+       for (i = 0; i < tp->cpu_nr; i++) {
+               ret = do_write(fd, &tp->core_id[i], sizeof(int));
+               if (ret < 0)
+                       return ret;
+               ret = do_write(fd, &tp->phy_pkg_id[i], sizeof(int));
+               if (ret < 0)
+                       return ret;
+       }
 done:
        free_cpu_topo(tp);
        return ret;
@@ -938,6 +961,7 @@ static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused,
 {
        int nr, i;
        char *str;
+       int cpu_nr = ph->env.nr_cpus_online;
 
        nr = ph->env.nr_sibling_cores;
        str = ph->env.sibling_cores;
@@ -954,6 +978,13 @@ static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused,
                fprintf(fp, "# sibling threads : %s\n", str);
                str += strlen(str) + 1;
        }
+
+       if (ph->env.cpu != NULL) {
+               for (i = 0; i < cpu_nr; i++)
+                       fprintf(fp, "# CPU %d: Core ID %d, Socket ID %d\n", i,
+                               ph->env.cpu[i].core_id, ph->env.cpu[i].socket_id);
+       } else
+               fprintf(fp, "# Core ID and Socket ID information is not available\n");
 }
 
 static void free_event_desc(struct perf_evsel *events)
@@ -1582,7 +1613,7 @@ error:
        return -1;
 }
 
-static int process_cpu_topology(struct perf_file_section *section __maybe_unused,
+static int process_cpu_topology(struct perf_file_section *section,
                                struct perf_header *ph, int fd,
                                void *data __maybe_unused)
 {
@@ -1590,15 +1621,22 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused
        u32 nr, i;
        char *str;
        struct strbuf sb;
+       int cpu_nr = ph->env.nr_cpus_online;
+       u64 size = 0;
+
+       ph->env.cpu = calloc(cpu_nr, sizeof(*ph->env.cpu));
+       if (!ph->env.cpu)
+               return -1;
 
        ret = readn(fd, &nr, sizeof(nr));
        if (ret != sizeof(nr))
-               return -1;
+               goto free_cpu;
 
        if (ph->needs_swap)
                nr = bswap_32(nr);
 
        ph->env.nr_sibling_cores = nr;
+       size += sizeof(u32);
        strbuf_init(&sb, 128);
 
        for (i = 0; i < nr; i++) {
@@ -1608,6 +1646,7 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused
 
                /* include a NULL character at the end */
                strbuf_add(&sb, str, strlen(str) + 1);
+               size += string_size(str);
                free(str);
        }
        ph->env.sibling_cores = strbuf_detach(&sb, NULL);
@@ -1620,6 +1659,7 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused
                nr = bswap_32(nr);
 
        ph->env.nr_sibling_threads = nr;
+       size += sizeof(u32);
 
        for (i = 0; i < nr; i++) {
                str = do_read_string(fd, ph);
@@ -1628,13 +1668,57 @@ static int process_cpu_topology(struct perf_file_section *section __maybe_unused
 
                /* include a NULL character at the end */
                strbuf_add(&sb, str, strlen(str) + 1);
+               size += string_size(str);
                free(str);
        }
        ph->env.sibling_threads = strbuf_detach(&sb, NULL);
+
+       /*
+        * The header may be from old perf,
+        * which doesn't include core id and socket id information.
+        */
+       if (section->size <= size) {
+               zfree(&ph->env.cpu);
+               return 0;
+       }
+
+       for (i = 0; i < (u32)cpu_nr; i++) {
+               ret = readn(fd, &nr, sizeof(nr));
+               if (ret != sizeof(nr))
+                       goto free_cpu;
+
+               if (ph->needs_swap)
+                       nr = bswap_32(nr);
+
+               if (nr > (u32)cpu_nr) {
+                       pr_debug("core_id number is too big."
+                                "You may need to upgrade the perf tool.\n");
+                       goto free_cpu;
+               }
+               ph->env.cpu[i].core_id = nr;
+
+               ret = readn(fd, &nr, sizeof(nr));
+               if (ret != sizeof(nr))
+                       goto free_cpu;
+
+               if (ph->needs_swap)
+                       nr = bswap_32(nr);
+
+               if (nr > (u32)cpu_nr) {
+                       pr_debug("socket_id number is too big."
+                                "You may need to upgrade the perf tool.\n");
+                       goto free_cpu;
+               }
+
+               ph->env.cpu[i].socket_id = nr;
+       }
+
        return 0;
 
 error:
        strbuf_release(&sb);
+free_cpu:
+       zfree(&ph->env.cpu);
        return -1;
 }
 

diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 396e4965f0c97469056324e55183883a58b151b5..975d803f46c8bfac4d0628e21e4fd4a3664fea79 100644 (file)
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -66,6 +66,11 @@ struct perf_header;
 int perf_file_header__read(struct perf_file_header *header,
                           struct perf_header *ph, int fd);
 
+struct cpu_topology_map {
+       int     socket_id;
+       int     core_id;
+};
+
 struct perf_env {
        char                    *hostname;
        char                    *os_release;
@@ -89,6 +94,7 @@ struct perf_env {
        char                    *sibling_threads;
        char                    *numa_nodes;
        char                    *pmu_mappings;
+       struct cpu_topology_map *cpu;
 };
 
 struct perf_header {

diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8a4537ee9bc374166c31d05f6e48b6ca6943a4b3..61669be150561408525fe94bf3dd16821bc98835 100644 (file)
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -185,6 +185,7 @@ static void perf_session_env__exit(struct perf_env *env)
        zfree(&env->sibling_threads);
        zfree(&env->numa_nodes);
        zfree(&env->pmu_mappings);
+       zfree(&env->cpu);
 }
 
 void perf_session__delete(struct perf_session *session)