1 files changed, 762 insertions, 301 deletions

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 74ea3c2f8138..7daad237dea5 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -20,11 +20,14 @@
 #include "symbol.h"
 #include "debug.h"
 #include "cpumap.h"
+#include "pmu.h"
+#include "vdso.h"
+#include "strbuf.h"
 
 static bool no_buildid_cache = false;
 
-static int event_count;
-static struct perf_trace_event_type *events;
+static int trace_event_count;
+static struct perf_trace_event_type *trace_events;
 
 static u32 header_argc;
 static const char **header_argv;
@@ -36,24 +39,24 @@ int perf_header__push_event(u64 id, const char *name)
         if (strlen(name) > MAX_EVENT_NAME)
                 pr_warning("Event %s will be truncated\n", name);
 
-        nevents = realloc(events, (event_count + 1) * sizeof(*events));
+        nevents = realloc(trace_events, (trace_event_count + 1) * sizeof(*trace_events));
         if (nevents == NULL)
                 return -ENOMEM;
-        events = nevents;
+        trace_events = nevents;
 
-        memset(&events[event_count], 0, sizeof(struct perf_trace_event_type));
-        events[event_count].event_id = id;
-        strncpy(events[event_count].name, name, MAX_EVENT_NAME - 1);
-        event_count++;
+        memset(&trace_events[trace_event_count], 0, sizeof(struct perf_trace_event_type));
+        trace_events[trace_event_count].event_id = id;
+        strncpy(trace_events[trace_event_count].name, name, MAX_EVENT_NAME - 1);
+        trace_event_count++;
         return 0;
 }
 
 char *perf_header__find_event(u64 id)
 {
         int i;
-        for (i = 0 ; i < event_count; i++) {
-                if (events[i].event_id == id)
-                        return events[i].name;
+        for (i = 0 ; i < trace_event_count; i++) {
+                if (trace_events[i].event_id == id)
+                        return trace_events[i].name;
         }
         return NULL;
 }
@@ -128,7 +131,7 @@ static int do_write_string(int fd, const char *str)
         int ret;
 
         olen = strlen(str) + 1;
-        len = ALIGN(olen, NAME_ALIGN);
+        len = PERF_ALIGN(olen, NAME_ALIGN);
 
         /* write len, incl. \0 */
         ret = do_write(fd, &len, sizeof(len));
@@ -206,6 +209,29 @@ perf_header__set_cmdline(int argc, const char **argv)
                         continue;               \
                 else
 
+static int write_buildid(char *name, size_t name_len, u8 *build_id,
+                         pid_t pid, u16 misc, int fd)
+{
+        int err;
+        struct build_id_event b;
+        size_t len;
+
+        len = name_len + 1;
+        len = PERF_ALIGN(len, NAME_ALIGN);
+
+        memset(&b, 0, sizeof(b));
+        memcpy(&b.build_id, build_id, BUILD_ID_SIZE);
+        b.pid = pid;
+        b.header.misc = misc;
+        b.header.size = sizeof(b) + len;
+
+        err = do_write(fd, &b, sizeof(b));
+        if (err < 0)
+                return err;
+
+        return write_padded(fd, name, name_len + 1, len);
+}
+
 static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
                                 u16 misc, int fd)
 {
@@ -213,24 +239,23 @@ static int __dsos__write_buildid_table(struct list_head *head, pid_t pid,
 
         dsos__for_each_with_build_id(pos, head) {
                 int err;
-                struct build_id_event b;
-                size_t len;
+                char  *name;
+                size_t name_len;
 
                 if (!pos->hit)
                         continue;
-                len = pos->long_name_len + 1;
-                len = ALIGN(len, NAME_ALIGN);
-                memset(&b, 0, sizeof(b));
-                memcpy(&b.build_id, pos->build_id, sizeof(pos->build_id));
-                b.pid = pid;
-                b.header.misc = misc;
-                b.header.size = sizeof(b) + len;
-                err = do_write(fd, &b, sizeof(b));
-                if (err < 0)
-                        return err;
-                err = write_padded(fd, pos->long_name,
-                                   pos->long_name_len + 1, len);
-                if (err < 0)
+
+                if (is_vdso_map(pos->short_name)) {
+                        name = (char *) VDSO__MAP_NAME;
+                        name_len = sizeof(VDSO__MAP_NAME) + 1;
+                } else {
+                        name = pos->long_name;
+                        name_len = pos->long_name_len + 1;
+                }
+
+                err = write_buildid(name, name_len, pos->build_id,
+                                    pid, misc, fd);
+                if (err)
                         return err;
         }
 
@@ -276,19 +301,20 @@ static int dsos__write_buildid_table(struct perf_header *header, int fd)
 }
 
 int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
-                          const char *name, bool is_kallsyms)
+                          const char *name, bool is_kallsyms, bool is_vdso)
 {
         const size_t size = PATH_MAX;
         char *realname, *filename = zalloc(size),
              *linkname = zalloc(size), *targetname;
         int len, err = -1;
+        bool slash = is_kallsyms || is_vdso;
 
         if (is_kallsyms) {
                 if (symbol_conf.kptr_restrict) {
                         pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
                         return 0;
                 }
-                realname = (char *)name;
+                realname = (char *) name;
         } else
                 realname = realpath(name, NULL);
 
@@ -296,7 +322,8 @@ int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
                 goto out_free;
 
         len = scnprintf(filename, size, "%s%s%s",
-                       debugdir, is_kallsyms ? "/" : "", realname);
+                       debugdir, slash ? "/" : "",
+                       is_vdso ? VDSO__MAP_NAME : realname);
         if (mkdir_p(filename, 0755))
                 goto out_free;
 
@@ -332,13 +359,14 @@ out_free:
 
 static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
                                  const char *name, const char *debugdir,
-                                 bool is_kallsyms)
+                                 bool is_kallsyms, bool is_vdso)
 {
         char sbuild_id[BUILD_ID_SIZE * 2 + 1];
 
         build_id__sprintf(build_id, build_id_size, sbuild_id);
 
-        return build_id_cache__add_s(sbuild_id, debugdir, name, is_kallsyms);
+        return build_id_cache__add_s(sbuild_id, debugdir, name,
+                                     is_kallsyms, is_vdso);
 }
 
 int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir)
@@ -382,9 +410,11 @@ out_free:
 static int dso__cache_build_id(struct dso *dso, const char *debugdir)
 {
         bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
+        bool is_vdso = is_vdso_map(dso->short_name);
 
         return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id),
-                                     dso->long_name, debugdir, is_kallsyms);
+                                     dso->long_name, debugdir,
+                                     is_kallsyms, is_vdso);
 }
 
 static int __dsos__cache_build_ids(struct list_head *head, const char *debugdir)
@@ -446,7 +476,7 @@ static bool perf_session__read_build_ids(struct perf_session *session, bool with
         return ret;
 }
 
-static int write_tracing_data(int fd, struct perf_header *h __used,
+static int write_tracing_data(int fd, struct perf_header *h __maybe_unused,
                             struct perf_evlist *evlist)
 {
         return read_tracing_data(fd, &evlist->entries);
@@ -454,7 +484,7 @@ static int write_tracing_data(int fd, struct perf_header *h __used,
 
 
 static int write_build_id(int fd, struct perf_header *h,
-                          struct perf_evlist *evlist __used)
+                          struct perf_evlist *evlist __maybe_unused)
 {
         struct perf_session *session;
         int err;
@@ -475,8 +505,8 @@ static int write_build_id(int fd, struct perf_header *h,
         return 0;
 }
 
-static int write_hostname(int fd, struct perf_header *h __used,
-                          struct perf_evlist *evlist __used)
+static int write_hostname(int fd, struct perf_header *h __maybe_unused,
+                          struct perf_evlist *evlist __maybe_unused)
 {
         struct utsname uts;
         int ret;
@@ -488,8 +518,8 @@ static int write_hostname(int fd, struct perf_header *h __used,
         return do_write_string(fd, uts.nodename);
 }
 
-static int write_osrelease(int fd, struct perf_header *h __used,
-                           struct perf_evlist *evlist __used)
+static int write_osrelease(int fd, struct perf_header *h __maybe_unused,
+                           struct perf_evlist *evlist __maybe_unused)
 {
         struct utsname uts;
         int ret;
@@ -501,8 +531,8 @@ static int write_osrelease(int fd, struct perf_header *h __used,
         return do_write_string(fd, uts.release);
 }
 
-static int write_arch(int fd, struct perf_header *h __used,
-                      struct perf_evlist *evlist __used)
+static int write_arch(int fd, struct perf_header *h __maybe_unused,
+                      struct perf_evlist *evlist __maybe_unused)
 {
         struct utsname uts;
         int ret;
@@ -514,14 +544,14 @@ static int write_arch(int fd, struct perf_header *h __used,
         return do_write_string(fd, uts.machine);
 }
 
-static int write_version(int fd, struct perf_header *h __used,
-                         struct perf_evlist *evlist __used)
+static int write_version(int fd, struct perf_header *h __maybe_unused,
+                         struct perf_evlist *evlist __maybe_unused)
 {
         return do_write_string(fd, perf_version_string);
 }
 
-static int write_cpudesc(int fd, struct perf_header *h __used,
-                       struct perf_evlist *evlist __used)
+static int write_cpudesc(int fd, struct perf_header *h __maybe_unused,
+                       struct perf_evlist *evlist __maybe_unused)
 {
 #ifndef CPUINFO_PROC
 #define CPUINFO_PROC NULL
@@ -579,8 +609,8 @@ done:
         return ret;
 }
 
-static int write_nrcpus(int fd, struct perf_header *h __used,
-                        struct perf_evlist *evlist __used)
+static int write_nrcpus(int fd, struct perf_header *h __maybe_unused,
+                        struct perf_evlist *evlist __maybe_unused)
 {
         long nr;
         u32 nrc, nra;
@@ -605,15 +635,14 @@ static int write_nrcpus(int fd, struct perf_header *h __used,
         return do_write(fd, &nra, sizeof(nra));
 }
 
-static int write_event_desc(int fd, struct perf_header *h __used,
+static int write_event_desc(int fd, struct perf_header *h __maybe_unused,
                             struct perf_evlist *evlist)
 {
-        struct perf_evsel *attr;
-        u32 nre = 0, nri, sz;
+        struct perf_evsel *evsel;
+        u32 nre, nri, sz;
         int ret;
 
-        list_for_each_entry(attr, &evlist->entries, node)
-                nre++;
+        nre = evlist->nr_entries;
 
         /*
          * write number of events
@@ -625,14 +654,14 @@ static int write_event_desc(int fd, struct perf_header *h __used,
         /*
          * size of perf_event_attr struct
          */
-        sz = (u32)sizeof(attr->attr);
+        sz = (u32)sizeof(evsel->attr);
         ret = do_write(fd, &sz, sizeof(sz));
         if (ret < 0)
                 return ret;
 
-        list_for_each_entry(attr, &evlist->entries, node) {
+        list_for_each_entry(evsel, &evlist->entries, node) {
 
-                ret = do_write(fd, &attr->attr, sz);
+                ret = do_write(fd, &evsel->attr, sz);
                 if (ret < 0)
                         return ret;
                 /*
@@ -642,7 +671,7 @@ static int write_event_desc(int fd, struct perf_header *h __used,
                  * copy into an nri to be independent of the
                  * type of ids,
                  */
-                nri = attr->ids;
+                nri = evsel->ids;
                 ret = do_write(fd, &nri, sizeof(nri));
                 if (ret < 0)
                         return ret;
@@ -650,21 +679,21 @@ static int write_event_desc(int fd, struct perf_header *h __used,
                 /*
                  * write event string as passed on cmdline
                  */
-                ret = do_write_string(fd, perf_evsel__name(attr));
+                ret = do_write_string(fd, perf_evsel__name(evsel));
                 if (ret < 0)
                         return ret;
                 /*
                  * write unique ids for this event
                  */
-                ret = do_write(fd, attr->id, attr->ids * sizeof(u64));
+                ret = do_write(fd, evsel->id, evsel->ids * sizeof(u64));
                 if (ret < 0)
                         return ret;
         }
         return 0;
 }
 
-static int write_cmdline(int fd, struct perf_header *h __used,
-                         struct perf_evlist *evlist __used)
+static int write_cmdline(int fd, struct perf_header *h __maybe_unused,
+                         struct perf_evlist *evlist __maybe_unused)
 {
         char buf[MAXPATHLEN];
         char proc[32];
@@ -832,8 +861,8 @@ static struct cpu_topo *build_cpu_topology(void)
         return tp;
 }
 
-static int write_cpu_topology(int fd, struct perf_header *h __used,
-                          struct perf_evlist *evlist __used)
+static int write_cpu_topology(int fd, struct perf_header *h __maybe_unused,
+                          struct perf_evlist *evlist __maybe_unused)
 {
         struct cpu_topo *tp;
         u32 i;
@@ -868,8 +897,8 @@ done:
 
 
 
-static int write_total_mem(int fd, struct perf_header *h __used,
-                          struct perf_evlist *evlist __used)
+static int write_total_mem(int fd, struct perf_header *h __maybe_unused,
+                          struct perf_evlist *evlist __maybe_unused)
 {
         char *buf = NULL;
         FILE *fp;
@@ -954,8 +983,8 @@ done:
         return ret;
 }
 
-static int write_numa_topology(int fd, struct perf_header *h __used,
-                          struct perf_evlist *evlist __used)
+static int write_numa_topology(int fd, struct perf_header *h __maybe_unused,
+                          struct perf_evlist *evlist __maybe_unused)
 {
         char *buf = NULL;
         size_t len = 0;
@@ -1004,16 +1033,56 @@ done:
 }
 
 /*
+ * File format:
+ *
+ * struct pmu_mappings {
+ *      u32     pmu_num;
+ *      struct pmu_map {
+ *              u32     type;
+ *              char    name[];
+ *      }[pmu_num];
+ * };
+ */
+
+static int write_pmu_mappings(int fd, struct perf_header *h __maybe_unused,
+                              struct perf_evlist *evlist __maybe_unused)
+{
+        struct perf_pmu *pmu = NULL;
+        off_t offset = lseek(fd, 0, SEEK_CUR);
+        __u32 pmu_num = 0;
+
+        /* write real pmu_num later */
+        do_write(fd, &pmu_num, sizeof(pmu_num));
+
+        while ((pmu = perf_pmu__scan(pmu))) {
+                if (!pmu->name)
+                        continue;
+                pmu_num++;
+                do_write(fd, &pmu->type, sizeof(pmu->type));
+                do_write_string(fd, pmu->name);
+        }
+
+        if (pwrite(fd, &pmu_num, sizeof(pmu_num), offset) != sizeof(pmu_num)) {
+                /* discard all */
+                lseek(fd, offset, SEEK_SET);
+                return -1;
+        }
+
+        return 0;
+}
+
+/*
  * default get_cpuid(): nothing gets recorded
  * actual implementation must be in arch/$(ARCH)/util/header.c
  */
-int __attribute__((weak)) get_cpuid(char *buffer __used, size_t sz __used)
+int __attribute__ ((weak)) get_cpuid(char *buffer __maybe_unused,
+                                     size_t sz __maybe_unused)
 {
         return -1;
 }
 
-static int write_cpuid(int fd, struct perf_header *h __used,
-                       struct perf_evlist *evlist __used)
+static int write_cpuid(int fd, struct perf_header *h __maybe_unused,
+                       struct perf_evlist *evlist __maybe_unused)
 {
         char buffer[64];
         int ret;
@@ -1027,133 +1096,113 @@ write_it:
         return do_write_string(fd, buffer);
 }
 
-static int write_branch_stack(int fd __used, struct perf_header *h __used,
-                       struct perf_evlist *evlist __used)
+static int write_branch_stack(int fd __maybe_unused,
+                              struct perf_header *h __maybe_unused,
+                       struct perf_evlist *evlist __maybe_unused)
 {
         return 0;
 }
 
-static void print_hostname(struct perf_header *ph, int fd, FILE *fp)
+static void print_hostname(struct perf_header *ph, int fd __maybe_unused,
+                           FILE *fp)
 {
-        char *str = do_read_string(fd, ph);
-        fprintf(fp, "# hostname : %s\n", str);
-        free(str);
+        fprintf(fp, "# hostname : %s\n", ph->env.hostname);
 }
 
-static void print_osrelease(struct perf_header *ph, int fd, FILE *fp)
+static void print_osrelease(struct perf_header *ph, int fd __maybe_unused,
+                            FILE *fp)
 {
-        char *str = do_read_string(fd, ph);
-        fprintf(fp, "# os release : %s\n", str);
-        free(str);
+        fprintf(fp, "# os release : %s\n", ph->env.os_release);
 }
 
-static void print_arch(struct perf_header *ph, int fd, FILE *fp)
+static void print_arch(struct perf_header *ph, int fd __maybe_unused, FILE *fp)
 {
-        char *str = do_read_string(fd, ph);
-        fprintf(fp, "# arch : %s\n", str);
-        free(str);
+        fprintf(fp, "# arch : %s\n", ph->env.arch);
 }
 
-static void print_cpudesc(struct perf_header *ph, int fd, FILE *fp)
+static void print_cpudesc(struct perf_header *ph, int fd __maybe_unused,
+                          FILE *fp)
 {
-        char *str = do_read_string(fd, ph);
-        fprintf(fp, "# cpudesc : %s\n", str);
-        free(str);
+        fprintf(fp, "# cpudesc : %s\n", ph->env.cpu_desc);
 }
 
-static void print_nrcpus(struct perf_header *ph, int fd, FILE *fp)
+static void print_nrcpus(struct perf_header *ph, int fd __maybe_unused,
+                         FILE *fp)
 {
-        ssize_t ret;
-        u32 nr;
-
-        ret = read(fd, &nr, sizeof(nr));
-        if (ret != (ssize_t)sizeof(nr))
-                nr = -1; /* interpreted as error */
-
-        if (ph->needs_swap)
-                nr = bswap_32(nr);
-
-        fprintf(fp, "# nrcpus online : %u\n", nr);
-
-        ret = read(fd, &nr, sizeof(nr));
-        if (ret != (ssize_t)sizeof(nr))
-                nr = -1; /* interpreted as error */
-
-        if (ph->needs_swap)
-                nr = bswap_32(nr);
-
-        fprintf(fp, "# nrcpus avail : %u\n", nr);
+        fprintf(fp, "# nrcpus online : %u\n", ph->env.nr_cpus_online);
+        fprintf(fp, "# nrcpus avail : %u\n", ph->env.nr_cpus_avail);
 }
 
-static void print_version(struct perf_header *ph, int fd, FILE *fp)
+static void print_version(struct perf_header *ph, int fd __maybe_unused,
+                          FILE *fp)
 {
-        char *str = do_read_string(fd, ph);
-        fprintf(fp, "# perf version : %s\n", str);
-        free(str);
+        fprintf(fp, "# perf version : %s\n", ph->env.version);
 }
 
-static void print_cmdline(struct perf_header *ph, int fd, FILE *fp)
+static void print_cmdline(struct perf_header *ph, int fd __maybe_unused,
+                          FILE *fp)
 {
-        ssize_t ret;
+        int nr, i;
         char *str;
-        u32 nr, i;
-
-        ret = read(fd, &nr, sizeof(nr));
-        if (ret != (ssize_t)sizeof(nr))
-                return;
 
-        if (ph->needs_swap)
-                nr = bswap_32(nr);
+        nr = ph->env.nr_cmdline;
+        str = ph->env.cmdline;
 
         fprintf(fp, "# cmdline : ");
 
         for (i = 0; i < nr; i++) {
-                str = do_read_string(fd, ph);
                 fprintf(fp, "%s ", str);
-                free(str);
+                str += strlen(str) + 1;
         }
         fputc('\n', fp);
 }
 
-static void print_cpu_topology(struct perf_header *ph, int fd, FILE *fp)
+static void print_cpu_topology(struct perf_header *ph, int fd __maybe_unused,
+                               FILE *fp)
 {
-        ssize_t ret;
-        u32 nr, i;
+        int nr, i;
         char *str;
 
-        ret = read(fd, &nr, sizeof(nr));
-        if (ret != (ssize_t)sizeof(nr))
-                return;
-
-        if (ph->needs_swap)
-                nr = bswap_32(nr);
+        nr = ph->env.nr_sibling_cores;
+        str = ph->env.sibling_cores;
 
         for (i = 0; i < nr; i++) {
-                str = do_read_string(fd, ph);
                 fprintf(fp, "# sibling cores   : %s\n", str);
-                free(str);
+                str += strlen(str) + 1;
         }
 
-        ret = read(fd, &nr, sizeof(nr));
-        if (ret != (ssize_t)sizeof(nr))
-                return;
-
-        if (ph->needs_swap)
-                nr = bswap_32(nr);
+        nr = ph->env.nr_sibling_threads;
+        str = ph->env.sibling_threads;
 
         for (i = 0; i < nr; i++) {
-                str = do_read_string(fd, ph);
                 fprintf(fp, "# sibling threads : %s\n", str);
-                free(str);
+                str += strlen(str) + 1;
         }
 }
 
-static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
+static void free_event_desc(struct perf_evsel *events)
+{
+        struct perf_evsel *evsel;
+
+        if (!events)
+                return;
+
+        for (evsel = events; evsel->attr.size; evsel++) {
+                if (evsel->name)
+                        free(evsel->name);
+                if (evsel->id)
+                        free(evsel->id);
+        }
+
+        free(events);
+}
+
+static struct perf_evsel *
+read_event_desc(struct perf_header *ph, int fd)
 {
-        struct perf_event_attr attr;
-        uint64_t id;
+        struct perf_evsel *evsel, *events = NULL;
+        u64 *id;
         void *buf = NULL;
-        char *str;
         u32 nre, sz, nr, i, j;
         ssize_t ret;
         size_t msz;
@@ -1173,18 +1222,22 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
         if (ph->needs_swap)
                 sz = bswap_32(sz);
 
-        memset(&attr, 0, sizeof(attr));
-
         /* buffer to hold on file attr struct */
         buf = malloc(sz);
         if (!buf)
                 goto error;
 
-        msz = sizeof(attr);
+        /* the last event terminates with evsel->attr.size == 0: */
+        events = calloc(nre + 1, sizeof(*events));
+        if (!events)
+                goto error;
+
+        msz = sizeof(evsel->attr);
         if (sz < msz)
                 msz = sz;
 
-        for (i = 0 ; i < nre; i++) {
+        for (i = 0, evsel = events; i < nre; evsel++, i++) {
+                evsel->idx = i;
 
                 /*
                  * must read entire on-file attr struct to
@@ -1197,146 +1250,188 @@ static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
                 if (ph->needs_swap)
                         perf_event__attr_swap(buf);
 
-                memcpy(&attr, buf, msz);
+                memcpy(&evsel->attr, buf, msz);
 
                 ret = read(fd, &nr, sizeof(nr));
                 if (ret != (ssize_t)sizeof(nr))
                         goto error;
 
-                if (ph->needs_swap)
+                if (ph->needs_swap) {
                         nr = bswap_32(nr);
+                        evsel->needs_swap = true;
+                }
 
-                str = do_read_string(fd, ph);
-                fprintf(fp, "# event : name = %s, ", str);
-                free(str);
+                evsel->name = do_read_string(fd, ph);
+
+                if (!nr)
+                        continue;
+
+                id = calloc(nr, sizeof(*id));
+                if (!id)
+                        goto error;
+                evsel->ids = nr;
+                evsel->id = id;
+
+                for (j = 0 ; j < nr; j++) {
+                        ret = read(fd, id, sizeof(*id));
+                        if (ret != (ssize_t)sizeof(*id))
+                                goto error;
+                        if (ph->needs_swap)
+                                *id = bswap_64(*id);
+                        id++;
+                }
+        }
+out:
+        if (buf)
+                free(buf);
+        return events;
+error:
+        if (events)
+                free_event_desc(events);
+        events = NULL;
+        goto out;
+}
+
+static void print_event_desc(struct perf_header *ph, int fd, FILE *fp)
+{
+        struct perf_evsel *evsel, *events = read_event_desc(ph, fd);
+        u32 j;
+        u64 *id;
+
+        if (!events) {
+                fprintf(fp, "# event desc: not available or unable to read\n");
+                return;
+        }
+
+        for (evsel = events; evsel->attr.size; evsel++) {
+                fprintf(fp, "# event : name = %s, ", evsel->name);
 
                 fprintf(fp, "type = %d, config = 0x%"PRIx64
                             ", config1 = 0x%"PRIx64", config2 = 0x%"PRIx64,
-                                attr.type,
-                                (u64)attr.config,
-                                (u64)attr.config1,
-                                (u64)attr.config2);
+                                evsel->attr.type,
+                                (u64)evsel->attr.config,
+                                (u64)evsel->attr.config1,
+                                (u64)evsel->attr.config2);
 
                 fprintf(fp, ", excl_usr = %d, excl_kern = %d",
-                                attr.exclude_user,
-                                attr.exclude_kernel);
+                                evsel->attr.exclude_user,
+                                evsel->attr.exclude_kernel);
 
                 fprintf(fp, ", excl_host = %d, excl_guest = %d",
-                                attr.exclude_host,
-                                attr.exclude_guest);
+                                evsel->attr.exclude_host,
+                                evsel->attr.exclude_guest);
 
-                fprintf(fp, ", precise_ip = %d", attr.precise_ip);
+                fprintf(fp, ", precise_ip = %d", evsel->attr.precise_ip);
 
-                if (nr)
+                if (evsel->ids) {
                         fprintf(fp, ", id = {");
-
-                for (j = 0 ; j < nr; j++) {
-                        ret = read(fd, &id, sizeof(id));
-                        if (ret != (ssize_t)sizeof(id))
-                                goto error;
-
-                        if (ph->needs_swap)
-                                id = bswap_64(id);
-
-                        if (j)
-                                fputc(',', fp);
-
-                        fprintf(fp, " %"PRIu64, id);
-                }
-                if (nr && j == nr)
+                        for (j = 0, id = evsel->id; j < evsel->ids; j++, id++) {
+                                if (j)
+                                        fputc(',', fp);
+                                fprintf(fp, " %"PRIu64, *id);
+                        }
                         fprintf(fp, " }");
+                }
+
                 fputc('\n', fp);
         }
-        free(buf);
-        return;
-error:
-        fprintf(fp, "# event desc: not available or unable to read\n");
+
+        free_event_desc(events);
 }
 
-static void print_total_mem(struct perf_header *h __used, int fd, FILE *fp)
+static void print_total_mem(struct perf_header *ph, int fd __maybe_unused,
+                            FILE *fp)
 {
-        uint64_t mem;
-        ssize_t ret;
-
-        ret = read(fd, &mem, sizeof(mem));
-        if (ret != sizeof(mem))
-                goto error;
-
-        if (h->needs_swap)
-                mem = bswap_64(mem);
-
-        fprintf(fp, "# total memory : %"PRIu64" kB\n", mem);
-        return;
-error:
-        fprintf(fp, "# total memory : unknown\n");
+        fprintf(fp, "# total memory : %Lu kB\n", ph->env.total_mem);
 }
 
-static void print_numa_topology(struct perf_header *h __used, int fd, FILE *fp)
+static void print_numa_topology(struct perf_header *ph, int fd __maybe_unused,
+                                FILE *fp)
 {
-        ssize_t ret;
         u32 nr, c, i;
-        char *str;
+        char *str, *tmp;
         uint64_t mem_total, mem_free;
 
         /* nr nodes */
-        ret = read(fd, &nr, sizeof(nr));
-        if (ret != (ssize_t)sizeof(nr))
-                goto error;
-
-        if (h->needs_swap)
-                nr = bswap_32(nr);
+        nr = ph->env.nr_numa_nodes;
+        str = ph->env.numa_nodes;
 
         for (i = 0; i < nr; i++) {
-
                 /* node number */
-                ret = read(fd, &c, sizeof(c));
-                if (ret != (ssize_t)sizeof(c))
+                c = strtoul(str, &tmp, 0);
+                if (*tmp != ':')
                         goto error;
 
-                if (h->needs_swap)
-                        c = bswap_32(c);
-
-                ret = read(fd, &mem_total, sizeof(u64));
-                if (ret != sizeof(u64))
+                str = tmp + 1;
+                mem_total = strtoull(str, &tmp, 0);
+                if (*tmp != ':')
                         goto error;
 
-                ret = read(fd, &mem_free, sizeof(u64));
-                if (ret != sizeof(u64))
+                str = tmp + 1;
+                mem_free = strtoull(str, &tmp, 0);
+                if (*tmp != ':')
                         goto error;
 
-                if (h->needs_swap) {
-                        mem_total = bswap_64(mem_total);
-                        mem_free = bswap_64(mem_free);
-                }
-
                 fprintf(fp, "# node%u meminfo  : total = %"PRIu64" kB,"
                             " free = %"PRIu64" kB\n",
-                        c,
-                        mem_total,
-                        mem_free);
+                        c, mem_total, mem_free);
 
-                str = do_read_string(fd, h);
+                str = tmp + 1;
                 fprintf(fp, "# node%u cpu list : %s\n", c, str);
-                free(str);
         }
         return;
 error:
         fprintf(fp, "# numa topology : not available\n");
 }
 
-static void print_cpuid(struct perf_header *ph, int fd, FILE *fp)
+static void print_cpuid(struct perf_header *ph, int fd __maybe_unused, FILE *fp)
 {
-        char *str = do_read_string(fd, ph);
-        fprintf(fp, "# cpuid : %s\n", str);
-        free(str);
+        fprintf(fp, "# cpuid : %s\n", ph->env.cpuid);
 }
 
-static void print_branch_stack(struct perf_header *ph __used, int fd __used,
-                               FILE *fp)
+static void print_branch_stack(struct perf_header *ph __maybe_unused,
+                               int fd __maybe_unused, FILE *fp)
 {
         fprintf(fp, "# contains samples with branch stack\n");
 }
 
+static void print_pmu_mappings(struct perf_header *ph, int fd __maybe_unused,
+                               FILE *fp)
+{
+        const char *delimiter = "# pmu mappings: ";
+        char *str, *tmp;
+        u32 pmu_num;
+        u32 type;
+
+        pmu_num = ph->env.nr_pmu_mappings;
+        if (!pmu_num) {
+                fprintf(fp, "# pmu mappings: not available\n");
+                return;
+        }
+
+        str = ph->env.pmu_mappings;
+
+        while (pmu_num) {
+                type = strtoul(str, &tmp, 0);
+                if (*tmp != ':')
+                        goto error;
+
+                str = tmp + 1;
+                fprintf(fp, "%s%s = %" PRIu32, delimiter, str, type);
+
+                delimiter = ", ";
+                str += strlen(str) + 1;
+                pmu_num--;
+        }
+
+        fprintf(fp, "\n");
+
+        if (!pmu_num)
+                return;
+error:
+        fprintf(fp, "# pmu mappings: unable to read\n");
+}
+
 static int __event_process_build_id(struct build_id_event *bev,
                                     char *filename,
                                     struct perf_session *session)
@@ -1398,7 +1493,7 @@ static int perf_header__read_build_ids_abi_quirk(struct perf_header *header,
         struct perf_session *session = container_of(header, struct perf_session, header);
         struct {
                 struct perf_event_header   header;
-                u8                         build_id[ALIGN(BUILD_ID_SIZE, sizeof(u64))];
+                u8                         build_id[PERF_ALIGN(BUILD_ID_SIZE, sizeof(u64))];
                 char                       filename[0];
         } old_bev;
         struct build_id_event bev;
@@ -1487,28 +1582,375 @@ out:
         return err;
 }
 
-static int process_tracing_data(struct perf_file_section *section __unused,
-                              struct perf_header *ph __unused,
-                              int feat __unused, int fd, void *data)
+static int process_tracing_data(struct perf_file_section *section __maybe_unused,
+                                struct perf_header *ph __maybe_unused,
+                                int fd, void *data)
 {
         trace_report(fd, data, false);
         return 0;
 }
 
 static int process_build_id(struct perf_file_section *section,
-                            struct perf_header *ph,
-                            int feat __unused, int fd, void *data __used)
+                            struct perf_header *ph, int fd,
+                            void *data __maybe_unused)
 {
         if (perf_header__read_build_ids(ph, fd, section->offset, section->size))
                 pr_debug("Failed to read buildids, continuing...\n");
         return 0;
 }
 
+static int process_hostname(struct perf_file_section *section __maybe_unused,
+                            struct perf_header *ph, int fd,
+                            void *data __maybe_unused)
+{
+        ph->env.hostname = do_read_string(fd, ph);
+        return ph->env.hostname ? 0 : -ENOMEM;
+}
+
+static int process_osrelease(struct perf_file_section *section __maybe_unused,
+                             struct perf_header *ph, int fd,
+                             void *data __maybe_unused)
+{
+        ph->env.os_release = do_read_string(fd, ph);
+        return ph->env.os_release ? 0 : -ENOMEM;
+}
+
+static int process_version(struct perf_file_section *section __maybe_unused,
+                           struct perf_header *ph, int fd,
+                           void *data __maybe_unused)
+{
+        ph->env.version = do_read_string(fd, ph);
+        return ph->env.version ? 0 : -ENOMEM;
+}
+
+static int process_arch(struct perf_file_section *section __maybe_unused,
+                        struct perf_header *ph, int fd,
+                        void *data __maybe_unused)
+{
+        ph->env.arch = do_read_string(fd, ph);
+        return ph->env.arch ? 0 : -ENOMEM;
+}
+
+static int process_nrcpus(struct perf_file_section *section __maybe_unused,
+                          struct perf_header *ph, int fd,
+                          void *data __maybe_unused)
+{
+        size_t ret;
+        u32 nr;
+
+        ret = read(fd, &nr, sizeof(nr));
+        if (ret != sizeof(nr))
+                return -1;
+
+        if (ph->needs_swap)
+                nr = bswap_32(nr);
+
+        ph->env.nr_cpus_online = nr;
+
+        ret = read(fd, &nr, sizeof(nr));
+        if (ret != sizeof(nr))
+                return -1;
+
+        if (ph->needs_swap)
+                nr = bswap_32(nr);
+
+        ph->env.nr_cpus_avail = nr;
+        return 0;
+}
+
+static int process_cpudesc(struct perf_file_section *section __maybe_unused,
+                           struct perf_header *ph, int fd,
+                           void *data __maybe_unused)
+{
+        ph->env.cpu_desc = do_read_string(fd, ph);
+        return ph->env.cpu_desc ? 0 : -ENOMEM;
+}
+
+static int process_cpuid(struct perf_file_section *section __maybe_unused,
+                         struct perf_header *ph,  int fd,
+                         void *data __maybe_unused)
+{
+        ph->env.cpuid = do_read_string(fd, ph);
+        return ph->env.cpuid ? 0 : -ENOMEM;
+}
+
+static int process_total_mem(struct perf_file_section *section __maybe_unused,
+                             struct perf_header *ph, int fd,
+                             void *data __maybe_unused)
+{
+        uint64_t mem;
+        size_t ret;
+
+        ret = read(fd, &mem, sizeof(mem));
+        if (ret != sizeof(mem))
+                return -1;
+
+        if (ph->needs_swap)
+                mem = bswap_64(mem);
+
+        ph->env.total_mem = mem;
+        return 0;
+}
+
+static struct perf_evsel *
+perf_evlist__find_by_index(struct perf_evlist *evlist, int idx)
+{
+        struct perf_evsel *evsel;
+
+        list_for_each_entry(evsel, &evlist->entries, node) {
+                if (evsel->idx == idx)
+                        return evsel;
+        }
+
+        return NULL;
+}
+
+static void
+perf_evlist__set_event_name(struct perf_evlist *evlist,
+                            struct perf_evsel *event)
+{
+        struct perf_evsel *evsel;
+
+        if (!event->name)
+                return;
+
+        evsel = perf_evlist__find_by_index(evlist, event->idx);
+        if (!evsel)
+                return;
+
+        if (evsel->name)
+                return;
+
+        evsel->name = strdup(event->name);
+}
+
+static int
+process_event_desc(struct perf_file_section *section __maybe_unused,
+                   struct perf_header *header, int fd,
+                   void *data __maybe_unused)
+{
+        struct perf_session *session;
+        struct perf_evsel *evsel, *events = read_event_desc(header, fd);
+
+        if (!events)
+                return 0;
+
+        session = container_of(header, struct perf_session, header);
+        for (evsel = events; evsel->attr.size; evsel++)
+                perf_evlist__set_event_name(session->evlist, evsel);
+
+        free_event_desc(events);
+
+        return 0;
+}
+
+static int process_cmdline(struct perf_file_section *section __maybe_unused,
+                           struct perf_header *ph, int fd,
+                           void *data __maybe_unused)
+{
+        size_t ret;
+        char *str;
+        u32 nr, i;
+        struct strbuf sb;
+
+        ret = read(fd, &nr, sizeof(nr));
+        if (ret != sizeof(nr))
+                return -1;
+
+        if (ph->needs_swap)
+                nr = bswap_32(nr);
+
+        ph->env.nr_cmdline = nr;
+        strbuf_init(&sb, 128);
+
+        for (i = 0; i < nr; i++) {
+                str = do_read_string(fd, ph);
+                if (!str)
+                        goto error;
+
+                /* include a NULL character at the end */
+                strbuf_add(&sb, str, strlen(str) + 1);
+                free(str);
+        }
+        ph->env.cmdline = strbuf_detach(&sb, NULL);
+        return 0;
+
+error:
+        strbuf_release(&sb);
+        return -1;
+}
+
+static int process_cpu_topology(struct perf_file_section *section __maybe_unused,
+                                struct perf_header *ph, int fd,
+                                void *data __maybe_unused)
+{
+        size_t ret;
+        u32 nr, i;
+        char *str;
+        struct strbuf sb;
+
+        ret = read(fd, &nr, sizeof(nr));
+        if (ret != sizeof(nr))
+                return -1;
+
+        if (ph->needs_swap)
+                nr = bswap_32(nr);
+
+        ph->env.nr_sibling_cores = nr;
+        strbuf_init(&sb, 128);
+
+        for (i = 0; i < nr; i++) {
+                str = do_read_string(fd, ph);
+                if (!str)
+                        goto error;
+
+                /* include a NULL character at the end */
+                strbuf_add(&sb, str, strlen(str) + 1);
+                free(str);
+        }
+        ph->env.sibling_cores = strbuf_detach(&sb, NULL);
+
+        ret = read(fd, &nr, sizeof(nr));
+        if (ret != sizeof(nr))
+                return -1;
+
+        if (ph->needs_swap)
+                nr = bswap_32(nr);
+
+        ph->env.nr_sibling_threads = nr;
+
+        for (i = 0; i < nr; i++) {
+                str = do_read_string(fd, ph);
+                if (!str)
+                        goto error;
+
+                /* include a NULL character at the end */
+                strbuf_add(&sb, str, strlen(str) + 1);
+                free(str);
+        }
+        ph->env.sibling_threads = strbuf_detach(&sb, NULL);
+        return 0;
+
+error:
+        strbuf_release(&sb);
+        return -1;
+}
+
+static int process_numa_topology(struct perf_file_section *section __maybe_unused,
+                                 struct perf_header *ph, int fd,
+                                 void *data __maybe_unused)
+{
+        size_t ret;
+        u32 nr, node, i;
+        char *str;
+        uint64_t mem_total, mem_free;
+        struct strbuf sb;
+
+        /* nr nodes */
+        ret = read(fd, &nr, sizeof(nr));
+        if (ret != sizeof(nr))
+                goto error;
+
+        if (ph->needs_swap)
+                nr = bswap_32(nr);
+
+        ph->env.nr_numa_nodes = nr;
+        strbuf_init(&sb, 256);
+
+        for (i = 0; i < nr; i++) {
+                /* node number */
+                ret = read(fd, &node, sizeof(node));
+                if (ret != sizeof(node))
+                        goto error;
+
+                ret = read(fd, &mem_total, sizeof(u64));
+                if (ret != sizeof(u64))
+                        goto error;
+
+                ret = read(fd, &mem_free, sizeof(u64));
+                if (ret != sizeof(u64))
+                        goto error;
+
+                if (ph->needs_swap) {
+                        node = bswap_32(node);
+                        mem_total = bswap_64(mem_total);
+                        mem_free = bswap_64(mem_free);
+                }
+
+                strbuf_addf(&sb, "%u:%"PRIu64":%"PRIu64":",
+                            node, mem_total, mem_free);
+
+                str = do_read_string(fd, ph);
+                if (!str)
+                        goto error;
+
+                /* include a NULL character at the end */
+                strbuf_add(&sb, str, strlen(str) + 1);
+                free(str);
+        }
+        ph->env.numa_nodes = strbuf_detach(&sb, NULL);
+        return 0;
+
+error:
+        strbuf_release(&sb);
+        return -1;
+}
+
+static int process_pmu_mappings(struct perf_file_section *section __maybe_unused,
+                                struct perf_header *ph, int fd,
+                                void *data __maybe_unused)
+{
+        size_t ret;
+        char *name;
+        u32 pmu_num;
+        u32 type;
+        struct strbuf sb;
+
+        ret = read(fd, &pmu_num, sizeof(pmu_num));
+        if (ret != sizeof(pmu_num))
+                return -1;
+
+        if (ph->needs_swap)
+                pmu_num = bswap_32(pmu_num);
+
+        if (!pmu_num) {
+                pr_debug("pmu mappings not available\n");
+                return 0;
+        }
+
+        ph->env.nr_pmu_mappings = pmu_num;
+        strbuf_init(&sb, 128);
+
+        while (pmu_num) {
+                if (read(fd, &type, sizeof(type)) != sizeof(type))
+                        goto error;
+                if (ph->needs_swap)
+                        type = bswap_32(type);
+
+                name = do_read_string(fd, ph);
+                if (!name)
+                        goto error;
+
+                strbuf_addf(&sb, "%u:%s", type, name);
+                /* include a NULL character at the end */
+                strbuf_add(&sb, "", 1);
+
+                free(name);
+                pmu_num--;
+        }
+        ph->env.pmu_mappings = strbuf_detach(&sb, NULL);
+        return 0;
+
+error:
+        strbuf_release(&sb);
+        return -1;
+}
+
 struct feature_ops {
         int (*write)(int fd, struct perf_header *h, struct perf_evlist *evlist);
         void (*print)(struct perf_header *h, int fd, FILE *fp);
         int (*process)(struct perf_file_section *section,
-                       struct perf_header *h, int feat, int fd, void *data);
+                       struct perf_header *h, int fd, void *data);
         const char *name;
         bool full_only;
 };
@@ -1520,7 +1962,7 @@ struct feature_ops {
                 .process = process_##func }
 #define FEAT_OPF(n, func) \
         [n] = { .name = #n, .write = write_##func, .print = print_##func, \
-                .full_only = true }
+                .process = process_##func, .full_only = true }
 
 /* feature_ops not implemented: */
 #define print_tracing_data      NULL
@@ -1529,19 +1971,20 @@ struct feature_ops {
 static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
         FEAT_OPP(HEADER_TRACING_DATA,   tracing_data),
         FEAT_OPP(HEADER_BUILD_ID,       build_id),
-        FEAT_OPA(HEADER_HOSTNAME,       hostname),
-        FEAT_OPA(HEADER_OSRELEASE,      osrelease),
-        FEAT_OPA(HEADER_VERSION,        version),
-        FEAT_OPA(HEADER_ARCH,           arch),
-        FEAT_OPA(HEADER_NRCPUS,         nrcpus),
-        FEAT_OPA(HEADER_CPUDESC,        cpudesc),
-        FEAT_OPA(HEADER_CPUID,          cpuid),
-        FEAT_OPA(HEADER_TOTAL_MEM,      total_mem),
-        FEAT_OPA(HEADER_EVENT_DESC,     event_desc),
-        FEAT_OPA(HEADER_CMDLINE,        cmdline),
+        FEAT_OPP(HEADER_HOSTNAME,       hostname),
+        FEAT_OPP(HEADER_OSRELEASE,      osrelease),
+        FEAT_OPP(HEADER_VERSION,        version),
+        FEAT_OPP(HEADER_ARCH,           arch),
+        FEAT_OPP(HEADER_NRCPUS,         nrcpus),
+        FEAT_OPP(HEADER_CPUDESC,        cpudesc),
+        FEAT_OPP(HEADER_CPUID,          cpuid),
+        FEAT_OPP(HEADER_TOTAL_MEM,      total_mem),
+        FEAT_OPP(HEADER_EVENT_DESC,     event_desc),
+        FEAT_OPP(HEADER_CMDLINE,        cmdline),
         FEAT_OPF(HEADER_CPU_TOPOLOGY,   cpu_topology),
         FEAT_OPF(HEADER_NUMA_TOPOLOGY,  numa_topology),
         FEAT_OPA(HEADER_BRANCH_STACK,   branch_stack),
+        FEAT_OPP(HEADER_PMU_MAPPINGS,   pmu_mappings),
 };
 
 struct header_print_data {
@@ -1683,17 +2126,17 @@ int perf_session__write_header(struct perf_session *session,
         struct perf_file_header f_header;
         struct perf_file_attr   f_attr;
         struct perf_header *header = &session->header;
-        struct perf_evsel *attr, *pair = NULL;
+        struct perf_evsel *evsel, *pair = NULL;
         int err;
 
         lseek(fd, sizeof(f_header), SEEK_SET);
 
         if (session->evlist != evlist)
-                pair = list_entry(session->evlist->entries.next, struct perf_evsel, node);
+                pair = perf_evlist__first(session->evlist);
 
-        list_for_each_entry(attr, &evlist->entries, node) {
-                attr->id_offset = lseek(fd, 0, SEEK_CUR);
-                err = do_write(fd, attr->id, attr->ids * sizeof(u64));
+        list_for_each_entry(evsel, &evlist->entries, node) {
+                evsel->id_offset = lseek(fd, 0, SEEK_CUR);
+                err = do_write(fd, evsel->id, evsel->ids * sizeof(u64));
                 if (err < 0) {
 out_err_write:
                         pr_debug("failed to write perf header\n");
@@ -1703,19 +2146,19 @@ out_err_write:
                         err = do_write(fd, pair->id, pair->ids * sizeof(u64));
                         if (err < 0)
                                 goto out_err_write;
-                        attr->ids += pair->ids;
-                        pair = list_entry(pair->node.next, struct perf_evsel, node);
+                        evsel->ids += pair->ids;
+                        pair = perf_evsel__next(pair);
                 }
         }
 
         header->attr_offset = lseek(fd, 0, SEEK_CUR);
 
-        list_for_each_entry(attr, &evlist->entries, node) {
+        list_for_each_entry(evsel, &evlist->entries, node) {
                 f_attr = (struct perf_file_attr){
-                        .attr = attr->attr,
+                        .attr = evsel->attr,
                         .ids  = {
-                                .offset = attr->id_offset,
-                                .size   = attr->ids * sizeof(u64),
+                                .offset = evsel->id_offset,
+                                .size   = evsel->ids * sizeof(u64),
                         }
                 };
                 err = do_write(fd, &f_attr, sizeof(f_attr));
@@ -1726,9 +2169,9 @@ out_err_write:
         }
 
         header->event_offset = lseek(fd, 0, SEEK_CUR);
-        header->event_size = event_count * sizeof(struct perf_trace_event_type);
-        if (events) {
-                err = do_write(fd, events, header->event_size);
+        header->event_size = trace_event_count * sizeof(struct perf_trace_event_type);
+        if (trace_events) {
+                err = do_write(fd, trace_events, header->event_size);
                 if (err < 0) {
                         pr_debug("failed to write perf header events\n");
                         return err;
@@ -1829,6 +2272,8 @@ out_free:
 static const int attr_file_abi_sizes[] = {
         [0] = PERF_ATTR_SIZE_VER0,
         [1] = PERF_ATTR_SIZE_VER1,
+        [2] = PERF_ATTR_SIZE_VER2,
+        [3] = PERF_ATTR_SIZE_VER3,
         0,
 };
 
@@ -2019,7 +2464,7 @@ static int perf_file_section__process(struct perf_file_section *section,
         if (!feat_ops[feat].process)
                 return 0;
 
-        return feat_ops[feat].process(section, ph, feat, fd, data);
+        return feat_ops[feat].process(section, ph, fd, data);
 }
 
 static int perf_file_header__read_pipe(struct perf_pipe_file_header *header,
@@ -2108,32 +2553,39 @@ static int read_attr(int fd, struct perf_header *ph,
         return ret <= 0 ? -1 : 0;
 }
 
-static int perf_evsel__set_tracepoint_name(struct perf_evsel *evsel,
-                                           struct pevent *pevent)
+static int perf_evsel__prepare_tracepoint_event(struct perf_evsel *evsel,
+                                                struct pevent *pevent)
 {
-        struct event_format *event = pevent_find_event(pevent,
-                                                       evsel->attr.config);
+        struct event_format *event;
         char bf[128];
 
+        /* already prepared */
+        if (evsel->tp_format)
+                return 0;
+
+        event = pevent_find_event(pevent, evsel->attr.config);
         if (event == NULL)
                 return -1;
 
-        snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name);
-        evsel->name = strdup(bf);
-        if (event->name == NULL)
-                return -1;
+        if (!evsel->name) {
+                snprintf(bf, sizeof(bf), "%s:%s", event->system, event->name);
+                evsel->name = strdup(bf);
+                if (evsel->name == NULL)
+                        return -1;
+        }
 
+        evsel->tp_format = event;
         return 0;
 }
 
-static int perf_evlist__set_tracepoint_names(struct perf_evlist *evlist,
-                                             struct pevent *pevent)
+static int perf_evlist__prepare_tracepoint_events(struct perf_evlist *evlist,
+                                                  struct pevent *pevent)
 {
         struct perf_evsel *pos;
 
         list_for_each_entry(pos, &evlist->entries, node) {
                 if (pos->attr.type == PERF_TYPE_TRACEPOINT &&
-                    perf_evsel__set_tracepoint_name(pos, pevent))
+                    perf_evsel__prepare_tracepoint_event(pos, pevent))
                         return -1;
         }
 
@@ -2176,6 +2628,8 @@ int perf_session__read_header(struct perf_session *session, int fd)
 
                 if (evsel == NULL)
                         goto out_delete_evlist;
+
+                evsel->needs_swap = header->needs_swap;
                 /*
                  * Do it before so that if perf_evsel__alloc_id fails, this
                  * entry gets purged too at perf_evlist__delete().
@@ -2207,13 +2661,13 @@ int perf_session__read_header(struct perf_session *session, int fd)
 
         if (f_header.event_types.size) {
                 lseek(fd, f_header.event_types.offset, SEEK_SET);
-                events = malloc(f_header.event_types.size);
-                if (events == NULL)
+                trace_events = malloc(f_header.event_types.size);
+                if (trace_events == NULL)
                         return -ENOMEM;
-                if (perf_header__getbuffer64(header, fd, events,
+                if (perf_header__getbuffer64(header, fd, trace_events,
                                              f_header.event_types.size))
                         goto out_errno;
-                event_count =  f_header.event_types.size / sizeof(struct perf_trace_event_type);
+                trace_event_count =  f_header.event_types.size / sizeof(struct perf_trace_event_type);
         }
 
         perf_header__process_sections(header, fd, &session->pevent,
@@ -2221,7 +2675,8 @@ int perf_session__read_header(struct perf_session *session, int fd)
 
         lseek(fd, header->data_offset, SEEK_SET);
 
-        if (perf_evlist__set_tracepoint_names(session->evlist, session->pevent))
+        if (perf_evlist__prepare_tracepoint_events(session->evlist,
+                                                   session->pevent))
                 goto out_delete_evlist;
 
         header->frozen = 1;
@@ -2236,7 +2691,7 @@ out_delete_evlist:
 }
 
 int perf_event__synthesize_attr(struct perf_tool *tool,
-                                struct perf_event_attr *attr, u16 ids, u64 *id,
+                                struct perf_event_attr *attr, u32 ids, u64 *id,
                                 perf_event__handler_t process)
 {
         union perf_event *ev;
@@ -2244,7 +2699,7 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
         int err;
 
         size = sizeof(struct perf_event_attr);
-        size = ALIGN(size, sizeof(u64));
+        size = PERF_ALIGN(size, sizeof(u64));
         size += sizeof(struct perf_event_header);
         size += ids * sizeof(u64);
 
@@ -2257,9 +2712,12 @@ int perf_event__synthesize_attr(struct perf_tool *tool,
         memcpy(ev->attr.id, id, ids * sizeof(u64));
 
         ev->attr.header.type = PERF_RECORD_HEADER_ATTR;
-        ev->attr.header.size = size;
+        ev->attr.header.size = (u16)size;
 
-        err = process(tool, ev, NULL, NULL);
+        if (ev->attr.header.size == size)
+                err = process(tool, ev, NULL, NULL);
+        else
+                err = -E2BIG;
 
         free(ev);
 
@@ -2270,12 +2728,12 @@ int perf_event__synthesize_attrs(struct perf_tool *tool,
                                    struct perf_session *session,
                                    perf_event__handler_t process)
 {
-        struct perf_evsel *attr;
+        struct perf_evsel *evsel;
         int err = 0;
 
-        list_for_each_entry(attr, &session->evlist->entries, node) {
-                err = perf_event__synthesize_attr(tool, &attr->attr, attr->ids,
-                                                  attr->id, process);
+        list_for_each_entry(evsel, &session->evlist->entries, node) {
+                err = perf_event__synthesize_attr(tool, &evsel->attr, evsel->ids,
+                                                  evsel->id, process);
                 if (err) {
                         pr_debug("failed to create perf header attribute\n");
                         return err;
@@ -2288,7 +2746,7 @@ int perf_event__synthesize_attrs(struct perf_tool *tool,
 int perf_event__process_attr(union perf_event *event,
                              struct perf_evlist **pevlist)
 {
-        unsigned int i, ids, n_ids;
+        u32 i, ids, n_ids;
         struct perf_evsel *evsel;
         struct perf_evlist *evlist = *pevlist;
 
@@ -2339,7 +2797,7 @@ int perf_event__synthesize_event_type(struct perf_tool *tool,
 
         ev.event_type.header.type = PERF_RECORD_HEADER_EVENT_TYPE;
         size = strlen(ev.event_type.event_type.name);
-        size = ALIGN(size, sizeof(u64));
+        size = PERF_ALIGN(size, sizeof(u64));
         ev.event_type.header.size = sizeof(ev.event_type) -
                 (sizeof(ev.event_type.event_type.name) - size);
 
@@ -2355,8 +2813,8 @@ int perf_event__synthesize_event_types(struct perf_tool *tool,
         struct perf_trace_event_type *type;
         int i, err = 0;
 
-        for (i = 0; i < event_count; i++) {
-                type = &events[i];
+        for (i = 0; i < trace_event_count; i++) {
+                type = &trace_events[i];
 
                 err = perf_event__synthesize_event_type(tool, type->event_id,
                                                         type->name, process,
@@ -2370,7 +2828,7 @@ int perf_event__synthesize_event_types(struct perf_tool *tool,
         return err;
 }
 
-int perf_event__process_event_type(struct perf_tool *tool __unused,
+int perf_event__process_event_type(struct perf_tool *tool __maybe_unused,
                                    union perf_event *event)
 {
         if (perf_header__push_event(event->event_type.event_type.event_id,
@@ -2387,7 +2845,7 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
         union perf_event ev;
         struct tracing_data *tdata;
         ssize_t size = 0, aligned_size = 0, padding;
-        int err __used = 0;
+        int err __maybe_unused = 0;
 
         /*
          * We are going to store the size of the data followed
@@ -2408,7 +2866,7 @@ int perf_event__synthesize_tracing_data(struct perf_tool *tool, int fd,
 
         ev.tracing_data.header.type = PERF_RECORD_HEADER_TRACING_DATA;
         size = tdata->size;
-        aligned_size = ALIGN(size, sizeof(u64));
+        aligned_size = PERF_ALIGN(size, sizeof(u64));
         padding = aligned_size - size;
         ev.tracing_data.header.size = sizeof(ev.tracing_data);
         ev.tracing_data.size = aligned_size;
@@ -2439,7 +2897,7 @@ int perf_event__process_tracing_data(union perf_event *event,
 
         size_read = trace_report(session->fd, &session->pevent,
                                  session->repipe);
-        padding = ALIGN(size_read, sizeof(u64)) - size_read;
+        padding = PERF_ALIGN(size_read, sizeof(u64)) - size_read;
 
         if (read(session->fd, buf, padding) < 0)
                 die("reading input file");
@@ -2452,6 +2910,9 @@ int perf_event__process_tracing_data(union perf_event *event,
         if (size_read + padding != size)
                 die("tracing data size mismatch");
 
+        perf_evlist__prepare_tracepoint_events(session->evlist,
+                                               session->pevent);
+
         return size_read + padding;
 }
 
@@ -2470,7 +2931,7 @@ int perf_event__synthesize_build_id(struct perf_tool *tool,
         memset(&ev, 0, sizeof(ev));
 
         len = pos->long_name_len + 1;
-        len = ALIGN(len, NAME_ALIGN);
+        len = PERF_ALIGN(len, NAME_ALIGN);
         memcpy(&ev.build_id.build_id, pos->build_id, sizeof(pos->build_id));
         ev.build_id.header.type = PERF_RECORD_HEADER_BUILD_ID;
         ev.build_id.header.misc = misc;
@@ -2483,7 +2944,7 @@ int perf_event__synthesize_build_id(struct perf_tool *tool,
         return err;
 }
 
-int perf_event__process_build_id(struct perf_tool *tool __used,
+int perf_event__process_build_id(struct perf_tool *tool __maybe_unused,
                                  union perf_event *event,
                                  struct perf_session *session)
 {