CPU needs to be marked offline before stopping it. When not marked
offline, the xcall receives HV_EWOULDBLOCK and so assumes that not all
CPUs received the message, and retries. After 10000 retries, it finally
fails with fatal mondo timeout.

Signed-off-by: Vijay Kumar <vijay.ac.ku...@oracle.com>
---
 arch/sparc/kernel/smp_64.c |    3 +++
 1 files changed, 3 insertions(+), 0 deletions(-)

diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index 0ce347f..712bf1b 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -1443,6 +1443,7 @@ void __irq_entry smp_receive_signal_client(int irq, 
struct pt_regs *regs)
 
 static void stop_this_cpu(void *dummy)
 {
+       set_cpu_online(smp_processor_id(), false);
        prom_stopself();
 }
 
@@ -1454,6 +1455,8 @@ void smp_send_stop(void)
                for_each_online_cpu(cpu) {
                        if (cpu == smp_processor_id())
                                continue;
+
+                       set_cpu_online(cpu, false);
 #ifdef CONFIG_SUN_LDOMS
                        if (ldom_domaining_enabled) {
                                unsigned long hv_err;
-- 
1.7.1

Reply via email to