powerpc: Fix deadlock with multiple calls to smp_send_stop

smp_send_stop can lock up the IPI path for any subsequent calls,
because the receiving CPUs spin in their handler function. This
started becoming a problem with the addition of an smp_send_stop
call in the reboot path, because panics can reboot after doing
their own smp_send_stop.

The NMI IPI variant was fixed with ac61c11566 ("powerpc: Fix
smp_send_stop NMI IPI handling"), which leaves the smp_call_function
variant.

This is fixed by having smp_send_stop only ever do the
smp_call_function once. This is a bit less robust than the NMI IPI
fix, because any other call to smp_call_function after smp_send_stop
could deadlock, but that has always been the case, and it was not
been a problem before.

Fixes: f2748bdfe1573 ("powerpc/powernv: Always stop secondaries before reboot/shutdown")
Reported-by: Abdul Haleem <abdhalee@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

1 files changed, 39 insertions, 16 deletions

diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 3582f30b60b7..9ca7148b5881 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -565,17 +565,6 @@ void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *))
 }
 #endif
 
-static void stop_this_cpu(void *dummy)
-{
-	/* Remove this CPU */
-	set_cpu_online(smp_processor_id(), false);
-
-	hard_irq_disable();
-	spin_begin();
-	while (1)
-		spin_cpu_relax();
-}
-
 #ifdef CONFIG_NMI_IPI
 static void nmi_stop_this_cpu(struct pt_regs *regs)
 {
@@ -583,23 +572,57 @@ static void nmi_stop_this_cpu(struct pt_regs *regs)
 	 * This is a special case because it never returns, so the NMI IPI
 	 * handling would never mark it as done, which makes any later
 	 * smp_send_nmi_ipi() call spin forever. Mark it done now.
+	 *
+	 * IRQs are already hard disabled by the smp_handle_nmi_ipi.
 	 */
 	nmi_ipi_lock();
 	nmi_ipi_busy_count--;
 	nmi_ipi_unlock();
 
-	stop_this_cpu(NULL);
+	/* Remove this CPU */
+	set_cpu_online(smp_processor_id(), false);
+
+	spin_begin();
+	while (1)
+		spin_cpu_relax();
 }
-#endif
 
 void smp_send_stop(void)
 {
-#ifdef CONFIG_NMI_IPI
 	smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, nmi_stop_this_cpu, 1000000);
-#else
+}
+
+#else /* CONFIG_NMI_IPI */
+
+static void stop_this_cpu(void *dummy)
+{
+	/* Remove this CPU */
+	set_cpu_online(smp_processor_id(), false);
+
+	hard_irq_disable();
+	spin_begin();
+	while (1)
+		spin_cpu_relax();
+}
+
+void smp_send_stop(void)
+{
+	static bool stopped = false;
+
+	/*
+	 * Prevent waiting on csd lock from a previous smp_send_stop.
+	 * This is racy, but in general callers try to do the right
+	 * thing and only fire off one smp_send_stop (e.g., see
+	 * kernel/panic.c)
+	 */
+	if (stopped)
+		return;
+
+	stopped = true;
+
 	smp_call_function(stop_this_cpu, NULL, 0);
-#endif
 }
+#endif /* CONFIG_NMI_IPI */
 
 struct thread_info *current_set[NR_CPUS];