The NMI IPI handler for a receiving CPU increments nmi_ipi_busy_count
over the handler function call, which causes later smp_send_nmi_ipi()
callers to spin until the call is finished.
The smp_send_stop function never returns, so the busy count is never
decremeted, which can cause the system to hang in some cases. For
example panic() will call smp_send_stop early on, then later in the
reboot path, pnv_restart will call smp_send_stop again, which hangs.
Fix this by adding a special case to the smp_send_stop handler to
decrement the busy count, because it will never return.
Fixes: 6bed3237624e3 ("powerpc: use NMI IPI for smp_send_stop")
Reported-by: Abdul Haleem <abdha...@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npig...@gmail.com>
---
Changes since v1:
- Reduce #ifdef spaghetti suggested by mpe
arch/powerpc/kernel/smp.c | 36 +++++++++++++++++++++++++++++-------
1 file changed, 29 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index e16ec7b3b427..41d42c2f88d4 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -566,10 +566,35 @@ void crash_send_ipi(void (*crash_ipi_callback)(struct
pt_regs *))
#endif
#ifdef CONFIG_NMI_IPI
-static void stop_this_cpu(struct pt_regs *regs)
-#else
+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();
+
+ /* Remove this CPU */
+ set_cpu_online(smp_processor_id(), false);
+
+ spin_begin();
+ while (1)
+ spin_cpu_relax();
+}
+
+void smp_send_stop(void)
+{
+ smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, nmi_stop_this_cpu, 1000000);
+}
+
+#else /* CONFIG_NMI_IPI */
+
static void stop_this_cpu(void *dummy)
-#endif
{
/* Remove this CPU */
set_cpu_online(smp_processor_id(), false);
@@ -582,12 +607,9 @@ static void stop_this_cpu(void *dummy)
void smp_send_stop(void)
{
-#ifdef CONFIG_NMI_IPI
- smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, stop_this_cpu, 1000000);
-#else
smp_call_function(stop_this_cpu, NULL, 0);
-#endif
}
+#endif /* CONFIG_NMI_IPI */
struct thread_info *current_set[NR_CPUS];
--
2.17.0
