kgdb: fix SMP NMI kgdb_handle_exception exit race

Fix the problem of protecting the kgdb handle_exception exit
which had an NMI race condition, while trying to restore
normal system operation.

There was a small window after the master processor sets cpu_in_debug
to zero but before it has set kgdb_active to zero where a
non-master processor in an SMP system could receive an NMI and
re-enter the kgdb_wait() loop.

As long as the master processor sets the cpu_in_debug before sending
the cpu roundup the cpu_in_debug variable can also be used to guard
against the race condition.

The kgdb_wait() function no longer needs to check
kgdb_active because it is done in the arch specific code
and handled along with the nmi traps at the low level.
This also allows kgdb_wait() to exit correctly if it was
entered for some unknown reason due to a spurious NMI that
could not be handled by the arch specific code.

Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 8 insertions, 19 deletions

diff --git a/kernel/kgdb.c b/kernel/kgdb.c
index 85b7e5b934a7..4d1b3c232377 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -561,18 +561,6 @@ static void kgdb_wait(struct pt_regs *regs)
 	smp_wmb();
 	atomic_set(&cpu_in_kgdb[cpu], 1);
 
-	/*
-	 * The primary CPU must be active to enter here, but this is
-	 * guard in case the primary CPU had not been selected if
-	 * this was an entry via nmi.
-	 */
-	while (atomic_read(&kgdb_active) == -1)
-		cpu_relax();
-
-	/* Wait till primary CPU goes completely into the debugger. */
-	while (!atomic_read(&cpu_in_kgdb[atomic_read(&kgdb_active)]))
-		cpu_relax();
-
 	/* Wait till primary CPU is done with debugging */
 	while (atomic_read(&passive_cpu_wait[cpu]))
 		cpu_relax();
@@ -1447,18 +1435,18 @@ acquirelock:
 			atomic_set(&passive_cpu_wait[i], 1);
 	}
 
-#ifdef CONFIG_SMP
-	/* Signal the other CPUs to enter kgdb_wait() */
-	if ((!kgdb_single_step || !kgdb_contthread) && kgdb_do_roundup)
-		kgdb_roundup_cpus(flags);
-#endif
-
 	/*
 	 * spin_lock code is good enough as a barrier so we don't
 	 * need one here:
 	 */
 	atomic_set(&cpu_in_kgdb[ks->cpu], 1);
 
+#ifdef CONFIG_SMP
+	/* Signal the other CPUs to enter kgdb_wait() */
+	if ((!kgdb_single_step || !kgdb_contthread) && kgdb_do_roundup)
+		kgdb_roundup_cpus(flags);
+#endif
+
 	/*
 	 * Wait for the other CPUs to be notified and be waiting for us:
 	 */
@@ -1514,7 +1502,8 @@ int kgdb_nmicallback(int cpu, void *regs)
 {
 #ifdef CONFIG_SMP
 	if (!atomic_read(&cpu_in_kgdb[cpu]) &&
-			atomic_read(&kgdb_active) != cpu) {
+			atomic_read(&kgdb_active) != cpu &&
+			atomic_read(&cpu_in_kgdb[atomic_read(&kgdb_active)])) {
 		kgdb_wait((struct pt_regs *)regs);
 		return 0;
 	}