12 files changed, 167 insertions, 100 deletions

diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 207dee5c5b16..0c542563ea6c 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -35,15 +35,21 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/i386/ -e s/sun4u/sparc64/ \
                                   -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
                                   -e s/sh[234].*/sh/ )
 
+CC = $(CROSS_COMPILE)gcc
+AR = $(CROSS_COMPILE)ar
+
 # Additional ARCH settings for x86
 ifeq ($(ARCH),i386)
         ARCH := x86
 endif
 ifeq ($(ARCH),x86_64)
-        RAW_ARCH := x86_64
-        ARCH := x86
-        ARCH_CFLAGS := -DARCH_X86_64
-        ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
+        ARCH := x86
+        IS_X86_64 := $(shell echo __x86_64__ | ${CC} -E -xc - | tail -n 1)
+        ifeq (${IS_X86_64}, 1)
+                RAW_ARCH := x86_64
+                ARCH_CFLAGS := -DARCH_X86_64
+                ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
+        endif
 endif
 
 #
@@ -119,8 +125,6 @@ lib = lib
 
 export prefix bindir sharedir sysconfdir
 
-CC = $(CROSS_COMPILE)gcc
-AR = $(CROSS_COMPILE)ar
 RM = rm -f
 MKDIR = mkdir
 FIND = find
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 17d1dcb3c667..0974f957b8fa 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -163,6 +163,7 @@ static void config_attr(struct perf_evsel *evsel, struct perf_evlist *evlist)
         struct perf_event_attr *attr = &evsel->attr;
         int track = !evsel->idx; /* only the first counter needs these */
 
+        attr->inherit           = !no_inherit;
         attr->read_format       = PERF_FORMAT_TOTAL_TIME_ENABLED |
                                   PERF_FORMAT_TOTAL_TIME_RUNNING |
                                   PERF_FORMAT_ID;
@@ -251,6 +252,9 @@ static void open_counters(struct perf_evlist *evlist)
 {
         struct perf_evsel *pos;
 
+        if (evlist->cpus->map[0] < 0)
+                no_inherit = true;
+
         list_for_each_entry(pos, &evlist->entries, node) {
                 struct perf_event_attr *attr = &pos->attr;
                 /*
@@ -271,8 +275,7 @@ static void open_counters(struct perf_evlist *evlist)
 retry_sample_id:
                 attr->sample_id_all = sample_id_all_avail ? 1 : 0;
 try_again:
-                if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group,
-                                     !no_inherit) < 0) {
+                if (perf_evsel__open(pos, evlist->cpus, evlist->threads, group) < 0) {
                         int err = errno;
 
                         if (err == EPERM || err == EACCES) {
@@ -424,7 +427,7 @@ static void mmap_read_all(void)
 {
         int i;
 
-        for (i = 0; i < evsel_list->cpus->nr; i++) {
+        for (i = 0; i < evsel_list->nr_mmaps; i++) {
                 if (evsel_list->mmap[i].base)
                         mmap_read(&evsel_list->mmap[i]);
         }
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e2109f9b43eb..03f0e45f1479 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -167,16 +167,17 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
                 attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
                                     PERF_FORMAT_TOTAL_TIME_RUNNING;
 
+        attr->inherit = !no_inherit;
+
         if (system_wide)
-                return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, false, false);
+                return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, false);
 
-        attr->inherit = !no_inherit;
         if (target_pid == -1 && target_tid == -1) {
                 attr->disabled = 1;
                 attr->enable_on_exec = 1;
         }
 
-        return perf_evsel__open_per_thread(evsel, evsel_list->threads, false, false);
+        return perf_evsel__open_per_thread(evsel, evsel_list->threads, false);
 }
 
 /*
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 1b2106c58f66..2f9a337b182f 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -290,7 +290,7 @@ static int test__open_syscall_event(void)
                 goto out_thread_map_delete;
         }
 
-        if (perf_evsel__open_per_thread(evsel, threads, false, false) < 0) {
+        if (perf_evsel__open_per_thread(evsel, threads, false) < 0) {
                 pr_debug("failed to open counter: %s, "
                          "tweak /proc/sys/kernel/perf_event_paranoid?\n",
                          strerror(errno));
@@ -303,7 +303,7 @@ static int test__open_syscall_event(void)
         }
 
         if (perf_evsel__read_on_cpu(evsel, 0, 0) < 0) {
-                pr_debug("perf_evsel__open_read_on_cpu\n");
+                pr_debug("perf_evsel__read_on_cpu\n");
                 goto out_close_fd;
         }
 
@@ -365,7 +365,7 @@ static int test__open_syscall_event_on_all_cpus(void)
                 goto out_thread_map_delete;
         }
 
-        if (perf_evsel__open(evsel, cpus, threads, false, false) < 0) {
+        if (perf_evsel__open(evsel, cpus, threads, false) < 0) {
                 pr_debug("failed to open counter: %s, "
                          "tweak /proc/sys/kernel/perf_event_paranoid?\n",
                          strerror(errno));
@@ -418,7 +418,7 @@ static int test__open_syscall_event_on_all_cpus(void)
                         continue;
 
                 if (perf_evsel__read_on_cpu(evsel, cpu, 0) < 0) {
-                        pr_debug("perf_evsel__open_read_on_cpu\n");
+                        pr_debug("perf_evsel__read_on_cpu\n");
                         err = -1;
                         break;
                 }
@@ -529,7 +529,7 @@ static int test__basic_mmap(void)
 
                 perf_evlist__add(evlist, evsels[i]);
 
-                if (perf_evsel__open(evsels[i], cpus, threads, false, false) < 0) {
+                if (perf_evsel__open(evsels[i], cpus, threads, false) < 0) {
                         pr_debug("failed to open counter: %s, "
                                  "tweak /proc/sys/kernel/perf_event_paranoid?\n",
                                  strerror(errno));
@@ -549,7 +549,7 @@ static int test__basic_mmap(void)
                         ++foo;
                 }
 
-        while ((event = perf_evlist__read_on_cpu(evlist, 0)) != NULL) {
+        while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
                 struct perf_sample sample;
 
                 if (event->header.type != PERF_RECORD_SAMPLE) {
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index fc1273e976c5..ebfc7cf5f63b 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -801,12 +801,12 @@ static void perf_event__process_sample(const union perf_event *event,
         }
 }
 
-static void perf_session__mmap_read_cpu(struct perf_session *self, int cpu)
+static void perf_session__mmap_read_idx(struct perf_session *self, int idx)
 {
         struct perf_sample sample;
         union perf_event *event;
 
-        while ((event = perf_evlist__read_on_cpu(top.evlist, cpu)) != NULL) {
+        while ((event = perf_evlist__mmap_read(top.evlist, idx)) != NULL) {
                 perf_session__parse_sample(self, event, &sample);
 
                 if (event->header.type == PERF_RECORD_SAMPLE)
@@ -820,8 +820,8 @@ static void perf_session__mmap_read(struct perf_session *self)
 {
         int i;
 
-        for (i = 0; i < top.evlist->cpus->nr; i++)
-                perf_session__mmap_read_cpu(self, i);
+        for (i = 0; i < top.evlist->nr_mmaps; i++)
+                perf_session__mmap_read_idx(self, i);
 }
 
 static void start_counters(struct perf_evlist *evlist)
@@ -845,9 +845,10 @@ static void start_counters(struct perf_evlist *evlist)
                 }
 
                 attr->mmap = 1;
+                attr->inherit = inherit;
 try_again:
                 if (perf_evsel__open(counter, top.evlist->cpus,
-                                     top.evlist->threads, group, inherit) < 0) {
+                                     top.evlist->threads, group) < 0) {
                         int err = errno;
 
                         if (err == EPERM || err == EACCES) {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d852cefa20de..23eb22b05d27 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -12,6 +12,7 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "util.h"
+#include "debug.h"
 
 #include <sys/mman.h>
 
@@ -165,11 +166,11 @@ struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id)
         return NULL;
 }
 
-union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu)
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 {
         /* XXX Move this to perf.c, making it generally available */
         unsigned int page_size = sysconf(_SC_PAGE_SIZE);
-        struct perf_mmap *md = &evlist->mmap[cpu];
+        struct perf_mmap *md = &evlist->mmap[idx];
         unsigned int head = perf_mmap__read_head(md);
         unsigned int old = md->prev;
         unsigned char *data = md->base + page_size;
@@ -234,36 +235,126 @@ union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *evlist, int cpu)
 
 void perf_evlist__munmap(struct perf_evlist *evlist)
 {
-        int cpu;
+        int i;
 
-        for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
-                if (evlist->mmap[cpu].base != NULL) {
-                        munmap(evlist->mmap[cpu].base, evlist->mmap_len);
-                        evlist->mmap[cpu].base = NULL;
+        for (i = 0; i < evlist->nr_mmaps; i++) {
+                if (evlist->mmap[i].base != NULL) {
+                        munmap(evlist->mmap[i].base, evlist->mmap_len);
+                        evlist->mmap[i].base = NULL;
                 }
         }
+
+        free(evlist->mmap);
+        evlist->mmap = NULL;
 }
 
 int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 {
-        evlist->mmap = zalloc(evlist->cpus->nr * sizeof(struct perf_mmap));
+        evlist->nr_mmaps = evlist->cpus->nr;
+        if (evlist->cpus->map[0] == -1)
+                evlist->nr_mmaps = evlist->threads->nr;
+        evlist->mmap = zalloc(evlist->nr_mmaps * sizeof(struct perf_mmap));
         return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
 
-static int __perf_evlist__mmap(struct perf_evlist *evlist, int cpu, int prot,
-                               int mask, int fd)
+static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *evsel,
+                               int idx, int prot, int mask, int fd)
 {
-        evlist->mmap[cpu].prev = 0;
-        evlist->mmap[cpu].mask = mask;
-        evlist->mmap[cpu].base = mmap(NULL, evlist->mmap_len, prot,
+        evlist->mmap[idx].prev = 0;
+        evlist->mmap[idx].mask = mask;
+        evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
                                       MAP_SHARED, fd, 0);
-        if (evlist->mmap[cpu].base == MAP_FAILED)
+        if (evlist->mmap[idx].base == MAP_FAILED) {
+                if (evlist->cpus->map[idx] == -1 && evsel->attr.inherit)
+                        ui__warning("Inherit is not allowed on per-task "
+                                    "events using mmap.\n");
                 return -1;
+        }
 
         perf_evlist__add_pollfd(evlist, fd);
         return 0;
 }
 
+static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int mask)
+{
+        struct perf_evsel *evsel;
+        int cpu, thread;
+
+        for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+                int output = -1;
+
+                for (thread = 0; thread < evlist->threads->nr; thread++) {
+                        list_for_each_entry(evsel, &evlist->entries, node) {
+                                int fd = FD(evsel, cpu, thread);
+
+                                if (output == -1) {
+                                        output = fd;
+                                        if (__perf_evlist__mmap(evlist, evsel, cpu,
+                                                                prot, mask, output) < 0)
+                                                goto out_unmap;
+                                } else {
+                                        if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
+                                                goto out_unmap;
+                                }
+
+                                if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+                                    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
+                                        goto out_unmap;
+                        }
+                }
+        }
+
+        return 0;
+
+out_unmap:
+        for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+                if (evlist->mmap[cpu].base != NULL) {
+                        munmap(evlist->mmap[cpu].base, evlist->mmap_len);
+                        evlist->mmap[cpu].base = NULL;
+                }
+        }
+        return -1;
+}
+
+static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, int mask)
+{
+        struct perf_evsel *evsel;
+        int thread;
+
+        for (thread = 0; thread < evlist->threads->nr; thread++) {
+                int output = -1;
+
+                list_for_each_entry(evsel, &evlist->entries, node) {
+                        int fd = FD(evsel, 0, thread);
+
+                        if (output == -1) {
+                                output = fd;
+                                if (__perf_evlist__mmap(evlist, evsel, thread,
+                                                        prot, mask, output) < 0)
+                                        goto out_unmap;
+                        } else {
+                                if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT, output) != 0)
+                                        goto out_unmap;
+                        }
+
+                        if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
+                            perf_evlist__id_add_fd(evlist, evsel, 0, thread, fd) < 0)
+                                goto out_unmap;
+                }
+        }
+
+        return 0;
+
+out_unmap:
+        for (thread = 0; thread < evlist->threads->nr; thread++) {
+                if (evlist->mmap[thread].base != NULL) {
+                        munmap(evlist->mmap[thread].base, evlist->mmap_len);
+                        evlist->mmap[thread].base = NULL;
+                }
+        }
+        return -1;
+}
+
 /** perf_evlist__mmap - Create per cpu maps to receive events
  *
  * @evlist - list of events
@@ -282,11 +373,11 @@ static int __perf_evlist__mmap(struct perf_evlist *evlist, int cpu, int prot,
 int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
 {
         unsigned int page_size = sysconf(_SC_PAGE_SIZE);
-        int mask = pages * page_size - 1, cpu;
-        struct perf_evsel *first_evsel, *evsel;
+        int mask = pages * page_size - 1;
+        struct perf_evsel *evsel;
         const struct cpu_map *cpus = evlist->cpus;
         const struct thread_map *threads = evlist->threads;
-        int thread, prot = PROT_READ | (overwrite ? 0 : PROT_WRITE);
+        int prot = PROT_READ | (overwrite ? 0 : PROT_WRITE);
 
         if (evlist->mmap == NULL && perf_evlist__alloc_mmap(evlist) < 0)
                 return -ENOMEM;
@@ -296,42 +387,18 @@ int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite)
 
         evlist->overwrite = overwrite;
         evlist->mmap_len = (pages + 1) * page_size;
-        first_evsel = list_entry(evlist->entries.next, struct perf_evsel, node);
 
         list_for_each_entry(evsel, &evlist->entries, node) {
                 if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
                     evsel->sample_id == NULL &&
                     perf_evsel__alloc_id(evsel, cpus->nr, threads->nr) < 0)
                         return -ENOMEM;
-
-                for (cpu = 0; cpu < cpus->nr; cpu++) {
-                        for (thread = 0; thread < threads->nr; thread++) {
-                                int fd = FD(evsel, cpu, thread);
-
-                                if (evsel->idx || thread) {
-                                        if (ioctl(fd, PERF_EVENT_IOC_SET_OUTPUT,
-                                                  FD(first_evsel, cpu, 0)) != 0)
-                                                goto out_unmap;
-                                } else if (__perf_evlist__mmap(evlist, cpu, prot, mask, fd) < 0)
-                                        goto out_unmap;
-
-                                if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
-                                    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
-                                        goto out_unmap;
-                        }
-                }
         }
 
-        return 0;
+        if (evlist->cpus->map[0] == -1)
+                return perf_evlist__mmap_per_thread(evlist, prot, mask);
 
-out_unmap:
-        for (cpu = 0; cpu < cpus->nr; cpu++) {
-                if (evlist->mmap[cpu].base != NULL) {
-                        munmap(evlist->mmap[cpu].base, evlist->mmap_len);
-                        evlist->mmap[cpu].base = NULL;
-                }
-        }
-        return -1;
+        return perf_evlist__mmap_per_cpu(evlist, prot, mask);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
@@ -342,7 +409,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
         if (evlist->threads == NULL)
                 return -1;
 
-        if (target_tid != -1)
+        if (cpu_list == NULL && target_tid != -1)
                 evlist->cpus = cpu_map__dummy_new();
         else
                 evlist->cpus = cpu_map__new(cpu_list);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 8b1cb7a4c5f1..7109d7add14e 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -17,6 +17,7 @@ struct perf_evlist {
         struct hlist_head heads[PERF_EVLIST__HLIST_SIZE];
         int              nr_entries;
         int              nr_fds;
+        int              nr_mmaps;
         int              mmap_len;
         bool             overwrite;
         union perf_event event_copy;
@@ -46,7 +47,7 @@ void perf_evlist__add_pollfd(struct perf_evlist *evlist, int fd);
 
 struct perf_evsel *perf_evlist__id2evsel(struct perf_evlist *evlist, u64 id);
 
-union perf_event *perf_evlist__read_on_cpu(struct perf_evlist *self, int cpu);
+union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
 
 int perf_evlist__alloc_mmap(struct perf_evlist *evlist);
 int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 662596afd7f1..d6fd59beb860 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -175,7 +175,7 @@ int __perf_evsel__read(struct perf_evsel *evsel,
 }
 
 static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-                              struct thread_map *threads, bool group, bool inherit)
+                              struct thread_map *threads, bool group)
 {
         int cpu, thread;
         unsigned long flags = 0;
@@ -192,19 +192,6 @@ static int __perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 
         for (cpu = 0; cpu < cpus->nr; cpu++) {
                 int group_fd = -1;
-                /*
-                 * Don't allow mmap() of inherited per-task counters. This
-                 * would create a performance issue due to all children writing
-                 * to the same buffer.
-                 *
-                 * FIXME:
-                 * Proper fix is not to pass 'inherit' to perf_evsel__open*,
-                 * but a 'flags' parameter, with 'group' folded there as well,
-                 * then introduce a PERF_O_{MMAP,GROUP,INHERIT} enum, and if
-                 * O_MMAP is set, emit a warning if cpu < 0 and O_INHERIT is
-                 * set. Lets go for the minimal fix first tho.
-                 */
-                evsel->attr.inherit = (cpus->map[cpu] >= 0) && inherit;
 
                 for (thread = 0; thread < threads->nr; thread++) {
 
@@ -253,7 +240,7 @@ static struct {
 };
 
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-                     struct thread_map *threads, bool group, bool inherit)
+                     struct thread_map *threads, bool group)
 {
         if (cpus == NULL) {
                 /* Work around old compiler warnings about strict aliasing */
@@ -263,19 +250,19 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
         if (threads == NULL)
                 threads = &empty_thread_map.map;
 
-        return __perf_evsel__open(evsel, cpus, threads, group, inherit);
+        return __perf_evsel__open(evsel, cpus, threads, group);
 }
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-                             struct cpu_map *cpus, bool group, bool inherit)
+                             struct cpu_map *cpus, bool group)
 {
-        return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group, inherit);
+        return __perf_evsel__open(evsel, cpus, &empty_thread_map.map, group);
 }
 
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-                                struct thread_map *threads, bool group, bool inherit)
+                                struct thread_map *threads, bool group)
 {
-        return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group, inherit);
+        return __perf_evsel__open(evsel, &empty_cpu_map.map, threads, group);
 }
 
 static int perf_event__parse_id_sample(const union perf_event *event, u64 type,
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 6710ab538342..f79bb2c09a6c 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -81,11 +81,11 @@ void perf_evsel__free_id(struct perf_evsel *evsel);
 void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
 
 int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
-                             struct cpu_map *cpus, bool group, bool inherit);
+                             struct cpu_map *cpus, bool group);
 int perf_evsel__open_per_thread(struct perf_evsel *evsel,
-                                struct thread_map *threads, bool group, bool inherit);
+                                struct thread_map *threads, bool group);
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
-                     struct thread_map *threads, bool group, bool inherit);
+                     struct thread_map *threads, bool group);
 
 #define perf_evsel__match(evsel, t, c)          \
         (evsel->attr.type == PERF_TYPE_##t &&   \
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index a9f2d7e1204d..99c722672f84 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -498,11 +498,11 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
         struct cpu_map *cpus = NULL;
         struct thread_map *threads = NULL;
         PyObject *pcpus = NULL, *pthreads = NULL;
-        int group = 0, overwrite = 0;
-        static char *kwlist[] = {"cpus", "threads", "group", "overwrite", NULL, NULL};
+        int group = 0, inherit = 0;
+        static char *kwlist[] = {"cpus", "threads", "group", "inherit", NULL, NULL};
 
         if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOii", kwlist,
-                                         &pcpus, &pthreads, &group, &overwrite))
+                                         &pcpus, &pthreads, &group, &inherit))
                 return NULL;
 
         if (pthreads != NULL)
@@ -511,7 +511,8 @@ static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
         if (pcpus != NULL)
                 cpus = ((struct pyrf_cpu_map *)pcpus)->cpus;
 
-        if (perf_evsel__open(evsel, cpus, threads, group, overwrite) < 0) {
+        evsel->attr.inherit = inherit;
+        if (perf_evsel__open(evsel, cpus, threads, group) < 0) {
                 PyErr_SetFromErrno(PyExc_OSError);
                 return NULL;
         }
@@ -679,7 +680,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
                                          &cpu, &sample_id_all))
                 return NULL;
 
-        event = perf_evlist__read_on_cpu(evlist, cpu);
+        event = perf_evlist__mmap_read(evlist, cpu);
         if (event != NULL) {
                 struct perf_evsel *first;
                 PyObject *pyevent = pyrf_event__new(event);
diff --git a/tools/perf/util/ui/browsers/annotate.c b/tools/perf/util/ui/browsers/annotate.c
index 8c17a8730e4a..15633d608133 100644
--- a/tools/perf/util/ui/browsers/annotate.c
+++ b/tools/perf/util/ui/browsers/annotate.c
@@ -256,10 +256,9 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
                          int refresh)
 {
         struct objdump_line *pos, *n;
-        struct annotation *notes = symbol__annotation(sym);
+        struct annotation *notes;
         struct annotate_browser browser = {
                 .b = {
-                        .entries = &notes->src->source,
                         .refresh = ui_browser__list_head_refresh,
                         .seek    = ui_browser__list_head_seek,
                         .write   = annotate_browser__write,
@@ -281,6 +280,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 
         ui_helpline__push("Press <- or ESC to exit");
 
+        notes = symbol__annotation(sym);
+
         list_for_each_entry(pos, &notes->src->source, node) {
                 struct objdump_line_rb_node *rbpos;
                 size_t line_len = strlen(pos->line);
@@ -291,6 +292,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
                 rbpos->idx = browser.b.nr_entries++;
         }
 
+        browser.b.entries = &notes->src->source,
         browser.b.width += 18; /* Percentage */
         ret = annotate_browser__run(&browser, evidx, refresh);
         list_for_each_entry_safe(pos, n, &notes->src->source, node) {
diff --git a/tools/perf/util/ui/browsers/hists.c b/tools/perf/util/ui/browsers/hists.c
index 798efdca3ead..5d767c622dfc 100644
--- a/tools/perf/util/ui/browsers/hists.c
+++ b/tools/perf/util/ui/browsers/hists.c
@@ -851,7 +851,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel,
                         goto out_free_stack;
                 case 'a':
                         if (browser->selection == NULL ||
-                            browser->selection->map == NULL ||
+                            browser->selection->sym == NULL ||
                             browser->selection->map->dso->annotate_warned)
                                 continue;
                         goto do_annotate;