Skip to contentSkip to conversation

ia64_mca_rendez_int_handler use of hard_smp_processor_id

Linux-ia64 Keith Owens 1 participant 1 message Mar 26, 2003

lore
Share & tools
lore
#0 lore raw
Quoted 12 lines · Peter Chubb

Index: 20.5/arch/ia64/kernel/mca.c

arch/ia64/kernel/mca.c Wed, 26 Mar 2003 08:14:29 +1100 kaos (linux-2.4/s/c/5_mca.c 1.1.3.2.3.1.1.1.1.3 644) renamed from arch/ia64/kernel/mca.c Wed, 11 Dec 2002 20:58:53 +1100 kaos (linux-2.4/s/c/5_mca.c 1.1.3.2.3.1.1.1.1.3 644) +0 -0
@@ -640,13 +640,10 @@ ia64_mca_wakeup_all(void)

void
ia64_mca_rendez_int_handler(int rendez_irq, void *arg, struct pt_regs *ptregs) {

arch/ia64/kernel/mca.c Wed, 26 Mar 2003 08:14:29 +1100 kaos (linux-2.4/s/c/5_mca.c 1.1.3.2.3.1.1.1.1.3 644) renamed from arch/ia64/kernel/mca.c Wed, 11 Dec 2002 20:58:53 +1100 kaos (linux-2.4/s/c/5_mca.c 1.1.3.2.3.1.1.1.1.3 644) +1 -1
-	int flags, cpu = 0;
+	int flags, cpu = smp_processor_id();
	/* Mask all interrupts */
	save_and_cli(flags);
Quoted 3 lines

If this is called from a preemptible context, then move the cpu >cmp_processor_id() within the save_and_cli() section, or it won't be preempt safe. (thread could be migrated between getting the processor
ID and stopping interrupts.)

2.4, preempt is not my problem :). In any case, MCA rendezvous is a normal interrupt

ivt.S:interrupt ->

    ia64_handle_irq ->
      ia64_mca_rendez_int_handler.

It is my understanding that the interrupt handler will not migrate off the current cpu, even with preempt.