gdb.threads/{siginfo-thread.c,watchthreads-reorder.c,ia64-sigill.c} races with GDB

These three test all spawn a few threads and then send a SIGSTOP to
their parent GDB in order to pause it while the new threads set things
up for the test.  With a GDB patch that changes the inferior thread's
scheduling a bit, I sometimes see:

  FAIL: gdb.threads/siginfo-threads.exp: catch signal 0 (timeout)
  ...
  FAIL: gdb.threads/watchthreads-reorder.exp: reorder1: continue a (timeout)
  ...
  FAIL: gdb.threads/ia64-sigill.exp: continue (timeout)
  ...

The issue is that the test program stops GDB before it had a chance of
processing the new thread's clone event:

  (gdb) PASS: gdb.threads/siginfo-threads.exp: get pid
  continue
  Continuing.
  Stopping GDB PID 21541.
  Waiting till the threads initialize their TIDs.
  FAIL: gdb.threads/siginfo-threads.exp: catch signal 0 (timeout)

On Linux (at least), new threads start stopped, and the debugger must
resume them.  The fix is to make the test program wait for the new
threads to be running before stopping GDB.

gdb/testsuite/
2015-01-09  Pedro Alves  <palves@redhat.com>

	* gdb.threads/ia64-sigill.c (threads_started_barrier): New global.
	(thread_func): Wait on barrier.
	(main): Wait for all threads to start before stopping GDB.
	* gdb.threads/siginfo-threads.c (threads_started_barrier): New
	global.
	(thread1_func, thread2_func): Wait on barrier.
	(main): Wait for all threads to start before stopping GDB.
	* gdb.threads/watchthreads-reorder.c (threads_started_barrier):
	New global.
	(thread1_func, thread2_func): Wait on barrier.
	(main): Wait for all threads to start before stopping GDB.

diff --git a/gdb/testsuite/ChangeLog b/gdb/testsuite/ChangeLog
index 77758f18ad96edb5d3cb40bf46945b6d30a47300..cd38459b698d82c3946cedcb6c4854ab298d4957 100644 (file)
--- a/gdb/testsuite/ChangeLog
+++ b/gdb/testsuite/ChangeLog
@@ -1,3 +1,17 @@
+2015-01-09  Pedro Alves  <palves@redhat.com>
+
+       * gdb.threads/ia64-sigill.c (threads_started_barrier): New global.
+       (thread_func): Wait on barrier.
+       (main): Wait for all threads to start before stopping GDB.
+       * gdb.threads/siginfo-threads.c (threads_started_barrier): New
+       global.
+       (thread1_func, thread2_func): Wait on barrier.
+       (main): Wait for all threads to start before stopping GDB.
+       * gdb.threads/watchthreads-reorder.c (threads_started_barrier):
+       New global.
+       (thread1_func, thread2_func): Wait on barrier.
+       (main): Wait for all threads to start before stopping GDB.
+
 2015-01-09  Pedro Alves  <palves@redhat.com>
 
        * gdb.threads/attach-many-short-lived-threads.c: New file.

diff --git a/gdb/testsuite/gdb.threads/ia64-sigill.c b/gdb/testsuite/gdb.threads/ia64-sigill.c
index 6af01385e13c8d282120086f4db7ec506977aa82..11782fad3470ef9e780683f20d246da3595b67af 100644 (file)
--- a/gdb/testsuite/gdb.threads/ia64-sigill.c
+++ b/gdb/testsuite/gdb.threads/ia64-sigill.c
@@ -44,6 +44,8 @@ static pthread_mutex_t thread2_tid_mutex = PTHREAD_ERRORCHECK_MUTEX_INITIALIZER_
 
 static pthread_mutex_t terminate_mutex = PTHREAD_ERRORCHECK_MUTEX_INITIALIZER_NP;
 
+static pthread_barrier_t threads_started_barrier;
+
 /* Do not use alarm as it would create a ptrace event which would hang up us if
    we are being traced by GDB which we stopped ourselves.  */
 
@@ -78,6 +80,8 @@ thread_func (void *threadno_voidp)
   int threadno = (intptr_t) threadno_voidp;
   int i;
 
+  pthread_barrier_wait (&threads_started_barrier);
+
   switch (threadno)
   {
     case 1:
@@ -272,6 +276,8 @@ main (int argc, char **argv)
 
   timed_mutex_lock (&terminate_mutex);
 
+  pthread_barrier_init (&threads_started_barrier, NULL, 3);
+
   i = pthread_create (&thread1, NULL, thread_func, (void *) (intptr_t) 1);
   assert (i == 0);
 
@@ -298,6 +304,11 @@ main (int argc, char **argv)
 
   atexit (cleanup);
 
+  /* Wait until all threads are seen running.  On Linux (at least),
+     new threads start stopped, and the debugger must resume them.
+     Need to wait for that before stopping GDB.  */
+  pthread_barrier_wait (&threads_started_barrier);
+
   printf ("Stopping GDB PID %lu.\n", (unsigned long) tracer);
 
   if (tracer)

diff --git a/gdb/testsuite/gdb.threads/siginfo-threads.c b/gdb/testsuite/gdb.threads/siginfo-threads.c
index 95c3927aef310b1f6fcb0a79506262c736d43828..a8e54463bd7442cfe77701ff2b78623f5232371a 100644 (file)
--- a/gdb/testsuite/gdb.threads/siginfo-threads.c
+++ b/gdb/testsuite/gdb.threads/siginfo-threads.c
@@ -54,6 +54,8 @@ static int thread2_sigusr2_hit;
 static pthread_mutex_t terminate_mutex
   = PTHREAD_ERRORCHECK_MUTEX_INITIALIZER_NP;
 
+static pthread_barrier_t threads_started_barrier;
+
 /* Do not use alarm as it would create a ptrace event which would hang
    us up if we are being traced by GDB, which we stopped
    ourselves.  */
@@ -128,6 +130,8 @@ thread1_func (void *unused)
 {
   int i;
 
+  pthread_barrier_wait (&threads_started_barrier);
+
   timed_mutex_lock (&thread1_tid_mutex);
 
   /* THREAD1_TID_MUTEX must be already locked to avoid a race.  */
@@ -163,6 +167,8 @@ thread2_func (void *unused)
 {
   int i;
 
+  pthread_barrier_wait (&threads_started_barrier);
+
   timed_mutex_lock (&thread2_tid_mutex);
 
   /* THREAD2_TID_MUTEX must be already locked to avoid a race.  */
@@ -354,6 +360,8 @@ main (int argc, char **argv)
   assert_perror (errno);
   assert (i == 0);
 
+  pthread_barrier_init (&threads_started_barrier, NULL, 3);
+
   i = pthread_create (&thread1, NULL, thread1_func, NULL);
   assert (i == 0);
 
@@ -380,6 +388,11 @@ main (int argc, char **argv)
 
   atexit (cleanup);
 
+  /* Wait until all threads are seen running.  On Linux (at least),
+     new threads start stopped, and the debugger must resume them.
+     Need to wait for that before stopping GDB.  */
+  pthread_barrier_wait (&threads_started_barrier);
+
   printf ("Stopping GDB PID %lu.\n", (unsigned long) tracer);
 
   if (tracer)

diff --git a/gdb/testsuite/gdb.threads/watchthreads-reorder.c b/gdb/testsuite/gdb.threads/watchthreads-reorder.c
index 353b4a16eae194158c615aa9a387cfa12c88b04f..b28a0dea827caa4da8ceddbdb62362f466135f22 100644 (file)
--- a/gdb/testsuite/gdb.threads/watchthreads-reorder.c
+++ b/gdb/testsuite/gdb.threads/watchthreads-reorder.c
@@ -44,6 +44,8 @@ static pthread_mutex_t thread2_tid_mutex = PTHREAD_ERRORCHECK_MUTEX_INITIALIZER_
 
 static pthread_mutex_t terminate_mutex = PTHREAD_ERRORCHECK_MUTEX_INITIALIZER_NP;
 
+static pthread_barrier_t threads_started_barrier;
+
 /* These variables must have lower in-memory addresses than thread1_rwatch and
    thread2_rwatch so that they take their watchpoint slots.  */
 
@@ -87,6 +89,8 @@ thread1_func (void *unused)
   int i;
   volatile int rwatch_store;
 
+  pthread_barrier_wait (&threads_started_barrier);
+
   timed_mutex_lock (&thread1_tid_mutex);
 
   /* THREAD1_TID_MUTEX must be already locked to avoid race.  */
@@ -113,6 +117,8 @@ thread2_func (void *unused)
   int i;
   volatile int rwatch_store;
 
+  pthread_barrier_wait (&threads_started_barrier);
+
   timed_mutex_lock (&thread2_tid_mutex);
 
   /* THREAD2_TID_MUTEX must be already locked to avoid race.  */
@@ -279,6 +285,8 @@ main (int argc, char **argv)
 
   timed_mutex_lock (&terminate_mutex);
 
+  pthread_barrier_init (&threads_started_barrier, NULL, 3);
+
   i = pthread_create (&thread1, NULL, thread1_func, NULL);
   assert (i == 0);
 
@@ -305,6 +313,11 @@ main (int argc, char **argv)
 
   atexit (cleanup);
 
+  /* Wait until all threads are seen running.  On Linux (at least),
+     new threads start stopped, and the debugger must resume them.
+     Need to wait for that before stopping GDB.  */
+  pthread_barrier_wait (&threads_started_barrier);
+
   printf ("Stopping GDB PID %lu.\n", (unsigned long) tracer);
 
   if (tracer)