With data file indexing is enabled, it needs to search thread based on
sample time since sample processing is done after other (task, comm and
mmap) events are processed.  This can be a problem if a session is very
long and pid is recycled - in that case it'll only see the last one.

So keep thread start time in it, and search thread based on the time.
This patch introduces machine__find{,new}_thread_by_time() function
for this.  It'll first search current (i.e. recent) thread rbtree and
then dead thread tree (and tid list).  If it couldn't find anyone,
it'll create a new (missing) thread.

The sample timestamp of 0 means that this is called from synthesized
event so just use current rbtree.  The timestamp will be -1 if sample
didn't record the timestamp so will see current threads automatically.

Cc: Frederic Weisbecker <fweis...@gmail.com>
Signed-off-by: Namhyung Kim <namhy...@kernel.org>
---
 tools/perf/tests/dwarf-unwind.c |   8 +--
 tools/perf/tests/hists_common.c |   3 +-
 tools/perf/tests/hists_link.c   |   2 +-
 tools/perf/util/event.c         |   6 +-
 tools/perf/util/machine.c       | 126 +++++++++++++++++++++++++++++++++++++++-
 tools/perf/util/machine.h       |  10 +++-
 tools/perf/util/thread.c        |   4 ++
 tools/perf/util/thread.h        |   1 +
 8 files changed, 148 insertions(+), 12 deletions(-)

diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 40b36c462427..b9ca0a72fc4d 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -16,10 +16,10 @@
 
 static int mmap_handler(struct perf_tool *tool __maybe_unused,
                        union perf_event *event,
-                       struct perf_sample *sample __maybe_unused,
+                       struct perf_sample *sample,
                        struct machine *machine)
 {
-       return machine__process_mmap2_event(machine, event, NULL);
+       return machine__process_mmap2_event(machine, event, sample);
 }
 
 static int init_live_machine(struct machine *machine)
@@ -66,12 +66,10 @@ static int unwind_entry(struct unwind_entry *entry, void 
*arg)
 __attribute__ ((noinline))
 static int unwind_thread(struct thread *thread)
 {
-       struct perf_sample sample;
+       struct perf_sample sample = { .time = -1ULL, };
        unsigned long cnt = 0;
        int err = -1;
 
-       memset(&sample, 0, sizeof(sample));
-
        if (test__arch_unwind_sample(&sample, thread)) {
                pr_debug("failed to get unwind sample\n");
                goto out;
diff --git a/tools/perf/tests/hists_common.c b/tools/perf/tests/hists_common.c
index ce80b274b097..1d657fa2830f 100644
--- a/tools/perf/tests/hists_common.c
+++ b/tools/perf/tests/hists_common.c
@@ -80,6 +80,7 @@ static struct {
 struct machine *setup_fake_machine(struct machines *machines)
 {
        struct machine *machine = machines__find(machines, HOST_KERNEL_ID);
+       struct perf_sample sample = { .time = -1ULL, };
        size_t i;
 
        if (machine == NULL) {
@@ -114,7 +115,7 @@ struct machine *setup_fake_machine(struct machines 
*machines)
                strcpy(fake_mmap_event.mmap.filename,
                       fake_mmap_info[i].filename);
 
-               machine__process_mmap_event(machine, &fake_mmap_event, NULL);
+               machine__process_mmap_event(machine, &fake_mmap_event, &sample);
        }
 
        for (i = 0; i < ARRAY_SIZE(fake_symbols); i++) {
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 27bae90c9a95..cacc8617bf02 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -64,7 +64,7 @@ static int add_hist_entries(struct perf_evlist *evlist, 
struct machine *machine)
        struct perf_evsel *evsel;
        struct addr_location al;
        struct hist_entry *he;
-       struct perf_sample sample = { .period = 1, };
+       struct perf_sample sample = { .period = 1, .time = -1ULL, };
        size_t i = 0, k;
 
        /*
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index cb98b5af9e17..3dff1b5cd4cc 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -9,6 +9,7 @@
 #include "strlist.h"
 #include "thread.h"
 #include "thread_map.h"
+#include "session.h"
 #include "symbol/kallsyms.h"
 
 static const char *perf_event__names[] = {
@@ -992,9 +993,10 @@ int perf_event__preprocess_sample(const union perf_event 
*event,
                                  struct perf_sample *sample)
 {
        u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
-       struct thread *thread = machine__findnew_thread(machine, sample->pid,
-                                                       sample->tid);
+       struct thread *thread;
 
+       thread = machine__findnew_thread_by_time(machine, sample->pid,
+                                                sample->tid, sample->time);
        if (thread == NULL)
                return -1;
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 2b9fbe55c896..7cfaa2c3f131 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -475,6 +475,120 @@ struct thread *machine__find_thread(struct machine 
*machine, pid_t pid,
        return th;
 }
 
+static struct thread *
+__machine__findnew_thread_by_time(struct machine *machine, pid_t pid, pid_t 
tid,
+                                 u64 timestamp, bool create)
+{
+       struct thread *curr, *pos, *new;
+       struct thread *th = NULL;
+       struct rb_node **p;
+       struct rb_node *parent = NULL;
+
+       if (!perf_has_index)
+               return ____machine__findnew_thread(machine, pid, tid, create);
+
+       /* lookup current thread first */
+       curr = ____machine__findnew_thread(machine, pid, tid, false);
+       if (curr && timestamp >= curr->start_time)
+               return curr;
+
+       /* and then check dead threads tree & list */
+       p = &machine->dead_threads.rb_node;
+       while (*p != NULL) {
+               parent = *p;
+               th = rb_entry(parent, struct thread, rb_node);
+
+               if (th->tid == tid) {
+                       list_for_each_entry(pos, &th->tid_list, tid_list) {
+                               if (timestamp >= pos->start_time &&
+                                   pos->start_time > th->start_time) {
+                                       th = pos;
+                                       break;
+                               }
+                       }
+
+                       if (timestamp >= th->start_time) {
+                               machine__update_thread_pid(machine, th, pid);
+                               return th;
+                       }
+                       break;
+               }
+
+               if (tid < th->tid)
+                       p = &(*p)->rb_left;
+               else
+                       p = &(*p)->rb_right;
+       }
+
+       if (!create)
+               return NULL;
+
+       if (!curr && !*p) {
+               /* found no thread.  create one as current thread */
+               return __machine__findnew_thread(machine, pid, tid);
+       }
+
+       new = thread__new(pid, tid);
+       if (new == NULL)
+               return NULL;
+
+       new->dead = true;
+       new->start_time = timestamp;
+
+       if (*p) {
+               list_for_each_entry(pos, &th->tid_list, tid_list) {
+                       /* sort by time */
+                       if (timestamp >= pos->start_time) {
+                               th = pos;
+                               break;
+                       }
+               }
+               list_add_tail(&new->tid_list, &th->tid_list);
+       } else {
+               rb_link_node(&new->rb_node, parent, p);
+               rb_insert_color(&new->rb_node, &machine->dead_threads);
+       }
+
+       thread__get(new);
+
+       /*
+        * We have to initialize map_groups separately
+        * after rb tree is updated.
+        *
+        * The reason is that we call machine__findnew_thread
+        * within thread__init_map_groups to find the thread
+        * leader and that would screwed the rb tree.
+        */
+       if (thread__init_map_groups(new, machine))
+               thread__zput(new);
+
+       return new;
+}
+
+struct thread *machine__find_thread_by_time(struct machine *machine, pid_t pid,
+                                           pid_t tid, u64 timestamp)
+{
+       struct thread *th;
+
+       pthread_rwlock_rdlock(&machine->threads_lock);
+       th = thread__get(__machine__findnew_thread_by_time(machine, pid, tid,
+                                                          timestamp, false));
+       pthread_rwlock_unlock(&machine->threads_lock);
+       return th;
+}
+
+struct thread *machine__findnew_thread_by_time(struct machine *machine, pid_t 
pid,
+                                              pid_t tid, u64 timestamp)
+{
+       struct thread *th;
+
+       pthread_rwlock_wrlock(&machine->threads_lock);
+       th = thread__get(__machine__findnew_thread_by_time(machine, pid, tid,
+                                                          timestamp, true));
+       pthread_rwlock_unlock(&machine->threads_lock);
+       return th;
+}
+
 struct comm *machine__thread_exec_comm(struct machine *machine,
                                       struct thread *thread)
 {
@@ -1299,7 +1413,7 @@ int machine__process_mmap2_event(struct machine *machine,
        }
 
        thread = machine__findnew_thread(machine, event->mmap2.pid,
-                                       event->mmap2.tid);
+                                        event->mmap2.tid);
        if (thread == NULL)
                goto out_problem;
 
@@ -1419,6 +1533,16 @@ static void __machine__remove_thread(struct machine 
*machine, struct thread *th,
                pos = rb_entry(parent, struct thread, rb_node);
 
                if (pos->tid == th->tid) {
+                       struct thread *old;
+
+                       /* sort by time */
+                       list_for_each_entry(old, &pos->tid_list, tid_list) {
+                               if (th->start_time >= old->start_time) {
+                                       pos = old;
+                                       break;
+                               }
+                       }
+
                        list_add_tail(&th->tid_list, &pos->tid_list);
                        goto out;
                }
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 23242de926df..f0c2cc9c90ae 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -75,8 +75,6 @@ static inline bool machine__kernel_ip(struct machine 
*machine, u64 ip)
        return ip >= kernel_start;
 }
 
-struct thread *machine__find_thread(struct machine *machine, pid_t pid,
-                                   pid_t tid);
 struct comm *machine__thread_exec_comm(struct machine *machine,
                                       struct thread *thread);
 
@@ -164,6 +162,14 @@ static inline bool machine__is_host(struct machine 
*machine)
 
 struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, 
pid_t tid);
 struct thread *machine__findnew_thread(struct machine *machine, pid_t pid, 
pid_t tid);
+struct thread *machine__find_thread(struct machine *machine, pid_t pid,
+                                   pid_t tid);
+struct thread *machine__findnew_thread_by_time(struct machine *machine,
+                                              pid_t pid, pid_t tid,
+                                              u64 timestamp);
+struct thread *machine__find_thread_by_time(struct machine *machine,
+                                           pid_t pid, pid_t tid,
+                                           u64 timestamp);
 
 struct dso *machine__findnew_dso(struct machine *machine, const char 
*filename);
 
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 674792e8fa2f..ad7c2a00bff8 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -160,6 +160,9 @@ int __thread__set_comm(struct thread *thread, const char 
*str, u64 timestamp,
 
        /* Override the default :tid entry */
        if (!thread->comm_set) {
+               if (!thread->start_time)
+                       thread->start_time = timestamp;
+
                err = comm__override(curr, str, timestamp, exec);
                if (err)
                        return err;
@@ -266,6 +269,7 @@ int thread__fork(struct thread *thread, struct thread 
*parent, u64 timestamp)
        }
 
        thread->ppid = parent->tid;
+       thread->start_time = timestamp;
        return thread__clone_map_groups(thread, parent);
 }
 
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index b8f794d97b75..97026a9660ec 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -28,6 +28,7 @@ struct thread {
        bool                    dead; /* thread is in dead_threads list */
        struct list_head        comm_list;
        u64                     db_id;
+       u64                     start_time;
 
        void                    *priv;
        struct thread_stack     *ts;
-- 
2.6.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Reply via email to