6 files changed, 29 insertions, 10 deletions

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index f35eb72739c0..9de8780ac8d9 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -646,10 +646,12 @@ struct perf_event_mmap_page {
  *
  *   PERF_RECORD_MISC_MMAP_DATA  - PERF_RECORD_MMAP* events
  *   PERF_RECORD_MISC_COMM_EXEC  - PERF_RECORD_COMM event
+ *   PERF_RECORD_MISC_FORK_EXEC  - PERF_RECORD_FORK event (perf internal)
  *   PERF_RECORD_MISC_SWITCH_OUT - PERF_RECORD_SWITCH* events
  */
 #define PERF_RECORD_MISC_MMAP_DATA              (1 << 13)
 #define PERF_RECORD_MISC_COMM_EXEC              (1 << 13)
+#define PERF_RECORD_MISC_FORK_EXEC              (1 << 13)
 #define PERF_RECORD_MISC_SWITCH_OUT             (1 << 13)
 /*
  * These PERF_RECORD_MISC_* flags below are safely reused
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index f35eb72739c0..9de8780ac8d9 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -646,10 +646,12 @@ struct perf_event_mmap_page {
  *
  *   PERF_RECORD_MISC_MMAP_DATA  - PERF_RECORD_MMAP* events
  *   PERF_RECORD_MISC_COMM_EXEC  - PERF_RECORD_COMM event
+ *   PERF_RECORD_MISC_FORK_EXEC  - PERF_RECORD_FORK event (perf internal)
  *   PERF_RECORD_MISC_SWITCH_OUT - PERF_RECORD_SWITCH* events
  */
 #define PERF_RECORD_MISC_MMAP_DATA              (1 << 13)
 #define PERF_RECORD_MISC_COMM_EXEC              (1 << 13)
+#define PERF_RECORD_MISC_FORK_EXEC              (1 << 13)
 #define PERF_RECORD_MISC_SWITCH_OUT             (1 << 13)
 /*
  * These PERF_RECORD_MISC_* flags below are safely reused
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index bc646185f8d9..e9c108a6b1c3 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -308,6 +308,7 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
         event->fork.pid  = tgid;
         event->fork.tid  = pid;
         event->fork.header.type = PERF_RECORD_FORK;
+        event->fork.header.misc = PERF_RECORD_MISC_FORK_EXEC;
 
         event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 8ee8ab39d8ac..8f36ce813bc5 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1708,6 +1708,7 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
         struct thread *parent = machine__findnew_thread(machine,
                                                         event->fork.ppid,
                                                         event->fork.ptid);
+        bool do_maps_clone = true;
         int err = 0;
 
         if (dump_trace)
@@ -1736,9 +1737,25 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 
         thread = machine__findnew_thread(machine, event->fork.pid,
                                          event->fork.tid);
+        /*
+         * When synthesizing FORK events, we are trying to create thread
+         * objects for the already running tasks on the machine.
+         *
+         * Normally, for a kernel FORK event, we want to clone the parent's
+         * maps because that is what the kernel just did.
+         *
+         * But when synthesizing, this should not be done.  If we do, we end up
+         * with overlapping maps as we process the sythesized MMAP2 events that
+         * get delivered shortly thereafter.
+         *
+         * Use the FORK event misc flags in an internal way to signal this
+         * situation, so we can elide the map clone when appropriate.
+         */
+        if (event->fork.header.misc & PERF_RECORD_MISC_FORK_EXEC)
+                do_maps_clone = false;
 
         if (thread == NULL || parent == NULL ||
-            thread__fork(thread, parent, sample->time) < 0) {
+            thread__fork(thread, parent, sample->time, do_maps_clone) < 0) {
                 dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
                 err = -1;
         }
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 2048d393ece6..3d9ed7d0e281 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -330,7 +330,8 @@ static int thread__prepare_access(struct thread *thread)
 }
 
 static int thread__clone_map_groups(struct thread *thread,
-                                    struct thread *parent)
+                                    struct thread *parent,
+                                    bool do_maps_clone)
 {
         /* This is new thread, we share map groups for process. */
         if (thread->pid_ == parent->pid_)
@@ -341,15 +342,11 @@ static int thread__clone_map_groups(struct thread *thread,
                          thread->pid_, thread->tid, parent->pid_, parent->tid);
                 return 0;
         }
-
         /* But this one is new process, copy maps. */
-        if (map_groups__clone(thread, parent->mg) < 0)
-                return -ENOMEM;
-
-        return 0;
+        return do_maps_clone ? map_groups__clone(thread, parent->mg) : 0;
 }
 
-int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone)
 {
         if (parent->comm_set) {
                 const char *comm = thread__comm_str(parent);
@@ -362,7 +359,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
         }
 
         thread->ppid = parent->tid;
-        return thread__clone_map_groups(thread, parent);
+        return thread__clone_map_groups(thread, parent, do_maps_clone);
 }
 
 void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 36c09a9904e6..30e2b4c165fe 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -89,7 +89,7 @@ struct comm *thread__comm(const struct thread *thread);
 struct comm *thread__exec_comm(const struct thread *thread);
 const char *thread__comm_str(const struct thread *thread);
 int thread__insert_map(struct thread *thread, struct map *map);
-int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
 struct thread *thread__main_thread(struct machine *machine, struct thread *thread);