[PATCH] i386/x86-64: Fix NMI watchdog suspend/resume

Making NMI suspend/resume work with SMP. We use CPU hotplug to offline
APs in SMP suspend/resume. Only BSP executes sysdev's .suspend/.resume
method. APs should follow CPU hotplug code path.

And:

+From: Don Zickus <dzickus@redhat.com>

Makes the start/stop paths of nmi watchdog more robust to handle the
suspend/resume cases more gracefully.

AK: I merged the two patches together

Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>

1 files changed, 26 insertions, 7 deletions

diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index 6241e4448cab..8e4ed930ce6b 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -63,7 +63,6 @@ struct nmi_watchdog_ctlblk {
 static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk);
 
 /* local prototypes */
-static void stop_apic_nmi_watchdog(void *unused);
 static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu);
 
 extern void show_registers(struct pt_regs *regs);
@@ -341,15 +340,20 @@ static int nmi_pm_active; /* nmi_active before suspend */
 
 static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state)
 {
+        /* only CPU0 goes here, other CPUs should be offline */
         nmi_pm_active = atomic_read(&nmi_active);
-        disable_lapic_nmi_watchdog();
+        stop_apic_nmi_watchdog(NULL);
+        BUG_ON(atomic_read(&nmi_active) != 0);
         return 0;
 }
 
 static int lapic_nmi_resume(struct sys_device *dev)
 {
-        if (nmi_pm_active > 0)
-                enable_lapic_nmi_watchdog();
+        /* only CPU0 goes here, other CPUs should be offline */
+        if (nmi_pm_active > 0) {
+                setup_apic_nmi_watchdog(NULL);
+                touch_nmi_watchdog();
+        }
         return 0;
 }
 
@@ -626,11 +630,21 @@ static void stop_p4_watchdog(void)
 
 void setup_apic_nmi_watchdog (void *unused)
 {
+        struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
+
         /* only support LOCAL and IO APICs for now */
         if ((nmi_watchdog != NMI_LOCAL_APIC) &&
             (nmi_watchdog != NMI_IO_APIC))
                 return;
 
+        if (wd->enabled == 1)
+                return;
+
+        /* cheap hack to support suspend/resume */
+        /* if cpu0 is not active neither should the other cpus */
+        if ((smp_processor_id() != 0) && (atomic_read(&nmi_active) <= 0))
+                return;
+
         if (nmi_watchdog == NMI_LOCAL_APIC) {
                 switch (boot_cpu_data.x86_vendor) {
                 case X86_VENDOR_AMD:
@@ -663,17 +677,22 @@ void setup_apic_nmi_watchdog (void *unused)
                         return;
                 }
         }
-        __get_cpu_var(nmi_watchdog_ctlblk.enabled) = 1;
+        wd->enabled = 1;
         atomic_inc(&nmi_active);
 }
 
-static void stop_apic_nmi_watchdog(void *unused)
+void stop_apic_nmi_watchdog(void *unused)
 {
+        struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
+
         /* only support LOCAL and IO APICs for now */
         if ((nmi_watchdog != NMI_LOCAL_APIC) &&
             (nmi_watchdog != NMI_IO_APIC))
                 return;
 
+        if (wd->enabled == 0)
+                return;
+
         if (nmi_watchdog == NMI_LOCAL_APIC) {
                 switch (boot_cpu_data.x86_vendor) {
                 case X86_VENDOR_AMD:
@@ -697,7 +716,7 @@ static void stop_apic_nmi_watchdog(void *unused)
                         return;
                 }
         }
-        __get_cpu_var(nmi_watchdog_ctlblk.enabled) = 0;
+        wd->enabled = 0;
         atomic_dec(&nmi_active);
 }