libgomp: Use TLS storage for omp_get_num_teams()/omp_get_team_num() values

When thinking about GOMP_teams3, I've realized that using global variables
for the values returned by omp_get_num_teams()/omp_get_team_num() calls
is incorrect even with our right now dumb way of implementing host teams.
The problems are two, one is if host teams is used from multiple pthread_create
created threads - the spec says that host teams can't be nested inside of
explicit parallel or other teams constructs, but with pthread_create the
standard says obviously nothing about it.  Another more important thing
is host fallback, right now we don't do anything for omp_get_num_teams()
or omp_get_team_num() which was fine before host teams was introduced and
the 5.1 requirement that num_teams clause specifies minimum of teams, but
with the global vars it means inside of target teams num_teams (2) we happily
return omp_get_num_teams() == 4 if the target teams is inside of host teams
with num_teams(4).  With target fallback being invoked from parallel
regions global vars simply can't work right on the host.

So, this patch moves them to struct gomp_thread and propagates those for
parallel to child threads.  For host fallback, the implicit zeroing of
*thr results in us returning omp_get_num_teams () == 1 and
omp_get_team_num () == 0 which is fine for target teams without num_teams
clause, for target teams with num_teams clause something to work on and
for target without teams nested in it I've asked on omp-lang what should
be done.

2021-11-11  Jakub Jelinek  <jakub@redhat.com>

	* libgomp.h (struct gomp_thread): Add num_teams and team_num members.
	* team.c (struct gomp_thread_start_data): Likewise.
	(gomp_thread_start): Initialize thr->num_teams and thr->team_num.
	(gomp_team_start): Initialize start_data->num_teams and
	start_data->team_num.  Update nthr->num_teams and nthr->team_num.
	* teams.c (gomp_num_teams, gomp_team_num): Remove.
	(GOMP_teams_reg): Set and restore thr->num_teams and thr->team_num
	instead of gomp_num_teams and gomp_team_num.
	(omp_get_num_teams): Use thr->num_teams + 1 instead of gomp_num_teams.
	(omp_get_team_num): Use thr->team_num instead of gomp_team_num.
	* testsuite/libgomp.c/teams-4.c: New test.

4 files changed, 55 insertions, 9 deletions

diff --git a/libgomp/libgomp.h b/libgomp/libgomp.h
index 023d8a8c1df..ceef643216c 100644
--- a/libgomp/libgomp.h
+++ b/libgomp/libgomp.h
@@ -768,6 +768,14 @@ struct gomp_thread
   /* User pthread thread pool */
   struct gomp_thread_pool *thread_pool;
 
+#ifdef LIBGOMP_USE_PTHREADS
+  /* omp_get_num_teams () - 1.  */
+  unsigned int num_teams;
+
+  /* omp_get_team_num ().  */
+  unsigned int team_num;
+#endif
+
 #if defined(LIBGOMP_USE_PTHREADS) \
     && (!defined(HAVE_TLS) \
 	|| !defined(__GLIBC__) \
diff --git a/libgomp/team.c b/libgomp/team.c
index 11a2521057f..3bcc8174d1d 100644
--- a/libgomp/team.c
+++ b/libgomp/team.c
@@ -56,6 +56,8 @@ struct gomp_thread_start_data
   struct gomp_task *task;
   struct gomp_thread_pool *thread_pool;
   unsigned int place;
+  unsigned int num_teams;
+  unsigned int team_num;
   bool nested;
   pthread_t handle;
 };
@@ -88,6 +90,8 @@ gomp_thread_start (void *xdata)
   thr->ts = data->ts;
   thr->task = data->task;
   thr->place = data->place;
+  thr->num_teams = data->num_teams;
+  thr->team_num = data->team_num;
 #ifdef GOMP_NEEDS_THREAD_HANDLE
   thr->handle = data->handle;
 #endif
@@ -645,6 +649,8 @@ gomp_team_start (void (*fn) (void *), void *data, unsigned nthreads,
 	  nthr->ts.single_count = 0;
 #endif
 	  nthr->ts.static_trip = 0;
+	  nthr->num_teams = thr->num_teams;
+	  nthr->team_num = thr->team_num;
 	  nthr->task = &team->implicit_task[i];
 	  nthr->place = place;
 	  gomp_init_task (nthr->task, task, icv);
@@ -833,6 +839,8 @@ gomp_team_start (void (*fn) (void *), void *data, unsigned nthreads,
       start_data->ts.single_count = 0;
 #endif
       start_data->ts.static_trip = 0;
+      start_data->num_teams = thr->num_teams;
+      start_data->team_num = thr->team_num;
       start_data->task = &team->implicit_task[i];
       gomp_init_task (start_data->task, task, icv);
       team->implicit_task[i].icv.nthreads_var = nthreads_var;
diff --git a/libgomp/teams.c b/libgomp/teams.c
index 9409f8ee6aa..a93fb7cc6e1 100644
--- a/libgomp/teams.c
+++ b/libgomp/teams.c
@@ -28,14 +28,12 @@
 #include "libgomp.h"
 #include <limits.h>
 
-static unsigned gomp_num_teams = 1, gomp_team_num = 0;
-
 void
 GOMP_teams_reg (void (*fn) (void *), void *data, unsigned int num_teams,
 		unsigned int thread_limit, unsigned int flags)
 {
+  struct gomp_thread *thr = gomp_thread ();
   (void) flags;
-  (void) num_teams;
   unsigned old_thread_limit_var = 0;
   if (thread_limit == 0)
     thread_limit = gomp_teams_thread_limit_var;
@@ -48,11 +46,11 @@ GOMP_teams_reg (void (*fn) (void *), void *data, unsigned int num_teams,
     }
   if (num_teams == 0)
     num_teams = gomp_nteams_var ? gomp_nteams_var : 3;
-  gomp_num_teams = num_teams;
-  for (gomp_team_num = 0; gomp_team_num < num_teams; gomp_team_num++)
+  thr->num_teams = num_teams - 1;
+  for (thr->team_num = 0; thr->team_num < num_teams; thr->team_num++)
     fn (data);
-  gomp_num_teams = 1;
-  gomp_team_num = 0;
+  thr->num_teams = 0;
+  thr->team_num = 0;
   if (thread_limit)
     {
       struct gomp_task_icv *icv = gomp_icv (true);
@@ -63,13 +61,15 @@ GOMP_teams_reg (void (*fn) (void *), void *data, unsigned int num_teams,
 int
 omp_get_num_teams (void)
 {
-  return gomp_num_teams;
+  struct gomp_thread *thr = gomp_thread ();
+  return thr->num_teams + 1;
 }
 
 int
 omp_get_team_num (void)
 {
-  return gomp_team_num;
+  struct gomp_thread *thr = gomp_thread ();
+  return thr->team_num;
 }
 
 ialias (omp_get_num_teams)
diff --git a/libgomp/testsuite/libgomp.c/teams-4.c b/libgomp/testsuite/libgomp.c/teams-4.c
new file mode 100644
index 00000000000..c1f5356c622
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/teams-4.c
@@ -0,0 +1,30 @@
+#include <omp.h>
+#include <stdlib.h>
+
+int
+main ()
+{
+  if (omp_get_num_teams () != 1 || omp_get_team_num () != 0)
+    abort ();
+  #pragma omp parallel num_threads (2)
+  if (omp_get_num_teams () != 1 || omp_get_team_num () != 0)
+    abort ();
+  #pragma omp teams num_teams (4)
+  {
+    int team = omp_get_team_num ();
+    if (omp_get_num_teams () != 4 || (unsigned) team >= 4U)
+      abort ();
+    #pragma omp parallel num_threads (3)
+    if (omp_get_num_teams () != 4 || omp_get_team_num () != team)
+      abort ();
+    #pragma omp parallel if (0)
+    #pragma omp target
+    #pragma omp teams num_teams (2)
+    if (omp_get_num_teams () > 2
+	|| (unsigned) omp_get_team_num () >= 2U)
+      abort ();
+    if (omp_get_num_teams () != 4 || (unsigned) team >= 4U)
+      abort ();
+  }
+  return 0;
+}