powerpc/xmon: Wait for secondaries before IPI'ing on system reset

An externally triggered system reset (e.g., via QEMU nmi command, or pseries
reset button) can cause system reset interrupts on all CPUs. In case this causes
xmon to be entered, it is undesirable for the primary (first) CPU into xmon to
trigger an NMI IPI to others, because this may cause a nested system reset
interrupt.

So spin for a time waiting for secondaries to join xmon before performing the
NMI IPI, similarly to what the crash dump code does.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Only do it when we come in from system reset, not via sysrq etc.]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 682506821bba0f647ac52f3da03dadbafdbb2a1f..da5619847517b9e40906612cb66e6fde885d6155 100644 (file)
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -418,7 +418,22 @@ int cpus_are_in_xmon(void)
 {
        return !cpumask_empty(&cpus_in_xmon);
 }
-#endif
+
+static bool wait_for_other_cpus(int ncpus)
+{
+       unsigned long timeout;
+
+       /* We wait for 2s, which is a metric "little while" */
+       for (timeout = 20000; timeout != 0; --timeout) {
+               if (cpumask_weight(&cpus_in_xmon) >= ncpus)
+                       return true;
+               udelay(100);
+               barrier();
+       }
+
+       return false;
+}
+#endif /* CONFIG_SMP */
 
 static inline int unrecoverable_excp(struct pt_regs *regs)
 {
@@ -440,7 +455,6 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
 #ifdef CONFIG_SMP
        int cpu;
        int secondary;
-       unsigned long timeout;
 #endif
 
        local_irq_save(flags);
@@ -527,13 +541,17 @@ static int xmon_core(struct pt_regs *regs, int fromipi)
                xmon_owner = cpu;
                mb();
                if (ncpus > 1) {
-                       smp_send_debugger_break();
-                       /* wait for other cpus to come in */
-                       for (timeout = 100000000; timeout != 0; --timeout) {
-                               if (cpumask_weight(&cpus_in_xmon) >= ncpus)
-                                       break;
-                               barrier();
-                       }
+                       /*
+                        * A system reset (trap == 0x100) can be triggered on
+                        * all CPUs, so when we come in via 0x100 try waiting
+                        * for the other CPUs to come in before we send the
+                        * debugger break (IPI). This is similar to
+                        * crash_kexec_secondary().
+                        */
+                       if (TRAP(regs) != 0x100 || !wait_for_other_cpus(ncpus))
+                               smp_send_debugger_break();
+
+                       wait_for_other_cpus(ncpus);
                }
                remove_bpts();
                disable_surveillance();