gdb/testsuite: update test gdb.base/step-over-syscall.exp

I was looking at PR gdb/19675 and the related test
gdb.base/step-over-syscall.exp.  This test includes a call to kfail
when we are testing a displaced step over a clone syscall.

While looking at the test I removed the call to kfail and ran the
test, and was surprised that the test passed.

I ran the test a few times and it does sometimes fail, but mostly it
passed fine.

PR gdb/19675 describes how, when we displaced step over a clone, the
new thread is created with a $pc in the displaced step buffer.  GDB
then fails to "fix" this $pc (for the new thread), and the thread will
be set running with its current $pc value.  This means that the new
thread will just start executing from whatever happens to be after the
displaced stepping buffer.

In the original PR gdb/19675 bug report Yao Qi was seeing the new
thread cause a segfault, the problem is, what actually happens is
totally undefined.

On my machine, I'm seeing the new thread reenter main, it then starts
trying to run the test again (in the new thread).  This just happens
to be safe enough (in this simple test) that most of the time the
inferior doesn't crash.

In this commit I try to make the test slightly more likely to fail by
doing a couple of things.

First, I added a static variable to main, this is set true when the
first thread enters main, if a second thread ever enters main then I
force an abort.

Second, when the test is finishing I want to ensure that the new
threads have had a chance to do "something bad" if they are going to.
So I added a global counter, as each thread starts successfully it
decrements the counter.  The main thread does not proceed to the final
marker function (where GDB has placed a breakpoint) until all threads
have started successfully.  This means that if the newly created
thread doesn't successfully enter clone_fn then the counter will never
reach zero and the test will timeout.

With these two changes my hope is that the test should fail more
reliably, and so, I have also changed the test to call setup_kfail
before the specific steps that we expect to misbehave instead of just
calling kfail and skipping parts of the test completely.  The benefit
of this is that if/when we fix GDB this test will start to KPASS and
we'll know to update this test to remove the setup_kfail call.

2 files changed, 97 insertions, 11 deletions

diff --git a/gdb/testsuite/gdb.base/step-over-clone.c b/gdb/testsuite/gdb.base/step-over-clone.c
index 581bf5f..ef6fd92 100644
--- a/gdb/testsuite/gdb.base/step-over-clone.c
+++ b/gdb/testsuite/gdb.base/step-over-clone.c
@@ -19,6 +19,7 @@
 #include <stdlib.h>
 #include <unistd.h>
 #include <sched.h>
+#include <pthread.h>
 
 static void
 marker ()
@@ -26,9 +27,22 @@ marker ()
 
 #define STACK_SIZE 0x1000
 
+/* These are used to signal that the threads have started correctly.  The
+   GLOBAL_THREAD_COUNT is set to the number of threads in main, then
+   decremented (under a lock) in each new thread.  */
+pthread_mutex_t global_lock = PTHREAD_MUTEX_INITIALIZER;
+int global_thread_count = 0;
+
 static int
 clone_fn (void *unused)
 {
+  /* Signal that this thread has started correctly.  */
+  if (pthread_mutex_lock (&global_lock) != 0)
+    abort ();
+  global_thread_count--;
+  if (pthread_mutex_unlock (&global_lock) != 0)
+    abort ();
+
   return 0;
 }
 
@@ -38,9 +52,21 @@ main (void)
   int i, pid;
   unsigned char *stack[6];
 
+  /* Due to bug gdb/19675 the cloned thread _might_ try to reenter main
+     (this depends on where the displaced instruction is placed for
+     execution).  However, if we do reenter main then lets ensure we fail
+     hard rather then just silently executing the code below.  */
+  static int started = 0;
+  if (!started)
+    started = 1;
+  else
+    abort ();
+
   for (i = 0; i < (sizeof (stack) / sizeof (stack[0])); i++)
     stack[i] = malloc (STACK_SIZE);
 
+  global_thread_count = (sizeof (stack) / sizeof (stack[0]));
+
   for (i = 0; i < (sizeof (stack) / sizeof (stack[0])); i++)
     {
       pid = clone (clone_fn, stack[i] + STACK_SIZE, CLONE_FILES | CLONE_VM,
@@ -50,5 +76,18 @@ main (void)
   for (i = 0; i < (sizeof (stack) / sizeof (stack[0])); i++)
     free (stack[i]);
 
+  /* Set an alarm so we don't end up stuck waiting for threads that might
+     never start correctly.  */
+  alarm (120);
+
+  /* Now wait for all the threads to start up.  */
+  while (global_thread_count != 0)
+    {
+      /* Force memory barrier so GLOBAL_THREAD_COUNT will be refetched.  */
+      asm volatile ("" ::: "memory");
+      sleep (1);
+    }
+
+  /* Call marker, this is what GDB is waiting for.  */
   marker ();
 }
diff --git a/gdb/testsuite/gdb.base/step-over-syscall.exp b/gdb/testsuite/gdb.base/step-over-syscall.exp
index ecfb7be..5d4a75f 100644
--- a/gdb/testsuite/gdb.base/step-over-syscall.exp
+++ b/gdb/testsuite/gdb.base/step-over-syscall.exp
@@ -41,11 +41,50 @@ if { [istarget "i\[34567\]86-*-linux*"] || [istarget "x86_64-*-linux*"] } {
     return -1
 }
 
-proc_with_prefix check_pc_after_cross_syscall { syscall syscall_insn_next_addr } {
+proc_with_prefix check_pc_after_cross_syscall { displaced syscall syscall_insn_next_addr } {
+    global gdb_prompt
+
     set syscall_insn_next_addr_found [get_hexadecimal_valueof "\$pc" "0"]
 
+    # After the 'stepi' we expect thread 1 to still be selected.
+    # However, when displaced stepping over a clone bug gdb/19675
+    # means this might not be the case.
+    #
+    # Which thread we end up in depends on a race between the original
+    # thread-1, and the new thread (created by the clone), so we can't
+    # guarantee which thread we will be in at this point.
+    #
+    # For the fork/vfork syscalls, which are correctly handled by
+    # displaced stepping we will always be in thread-1 or the original
+    # process at this point.
+    set curr_thread "unknown"
+    gdb_test_multiple "info threads" "" {
+	-re "Id\\s+Target Id\\s+Frame\\s*\r\n" {
+	    exp_continue
+	}
+	-re "^\\* (\\d+)\\s+\[^\r\n\]+\r\n" {
+	    set curr_thread $expect_out(1,string)
+	    exp_continue
+	}
+	-re "^\\s+\\d+\\s+\[^\r\n\]+\r\n" {
+	    exp_continue
+	}
+	-re "$gdb_prompt " {
+	}
+    }
+
+    # If we are displaced stepping over a clone, and we ended up in
+    # the wrong thread then the following check of the $pc value will
+    # fail.
+    if { $displaced == "on" && $syscall == "clone" && $curr_thread != 1 } {
+	# GDB doesn't support stepping over clone syscall with
+	# displaced stepping.
+	setup_kfail "*-*-*" "gdb/19675"
+    }
+
     gdb_assert {$syscall_insn_next_addr != 0 \
-      && $syscall_insn_next_addr == $syscall_insn_next_addr_found} \
+      && $syscall_insn_next_addr == $syscall_insn_next_addr_found \
+      && $curr_thread == 1} \
 	"single step over $syscall final pc"
 }
 
@@ -203,7 +242,12 @@ proc step_over_syscall { syscall } {
 
 	set testfile "step-over-$syscall"
 
-	if [build_executable ${testfile}.exp ${testfile} ${testfile}.c {debug}] {
+	set options [list debug]
+	if { $syscall == "clone" } {
+	    lappend options "pthreads"
+	}
+
+	if [build_executable ${testfile}.exp ${testfile} ${testfile}.c $options] {
 	    untested "failed to compile"
 	    return -1
 	}
@@ -213,13 +257,6 @@ proc step_over_syscall { syscall } {
 		continue
 	    }
 
-	    if { $displaced == "on" && $syscall == "clone" } {
-		# GDB doesn't support stepping over clone syscall with
-		# displaced stepping.
-		kfail "gdb/19675" "single step over clone"
-		continue
-	    }
-
 	    set ret [setup $syscall]
 
 	    set syscall_insn_addr [lindex $ret 0]
@@ -256,12 +293,22 @@ proc step_over_syscall { syscall } {
 	    if {[gdb_test "stepi" "x/i .*=>.*" "single step over $syscall"] != 0} {
 		return -1
 	    }
-	    check_pc_after_cross_syscall $syscall $syscall_insn_next_addr
+	    check_pc_after_cross_syscall $displaced $syscall $syscall_insn_next_addr
 
 	    # Delete breakpoint syscall insns to avoid interference to other syscalls.
 	    delete_breakpoints
 
 	    gdb_test "break marker" "Breakpoint.*at.* file .*${testfile}.c, line.*"
+
+	    # If we are displaced stepping over a clone syscall then
+	    # we expect the following check to fail.  See also the
+	    # code in check_pc_after_cross_syscall.
+	    if { $displaced == "on" && $syscall == "clone" } {
+		# GDB doesn't support stepping over clone syscall with
+		# displaced stepping.
+		setup_kfail "*-*-*" "gdb/19675"
+	    }
+
 	    gdb_test "continue" "Continuing\\..*Breakpoint \[0-9\]+, marker \\(\\) at.*" \
 		"continue to marker ($syscall)"
 	}