[PATCH] i386 CPU hotplug

(The i386 CPU hotplug patch provides infrastructure for some work which Pavel
is doing as well as for ACPI S3 (suspend-to-RAM) work which Li Shaohua
<shaohua.li@intel.com> is doing)

The following provides i386 architecture support for safely unregistering and
registering processors during runtime, updated for the current -mm tree.  In
order to avoid dumping cpu hotplug code into kernel/irq/* i dropped the
cpu_online check in do_IRQ() by modifying fixup_irqs().  The difference being
that on cpu offline, fixup_irqs() is called before we clear the cpu from
cpu_online_map and a long delay in order to ensure that we never have any
queued external interrupts on the APICs.  There are additional changes to s390
and ppc64 to account for this change.

1) Add CONFIG_HOTPLUG_CPU
2) disable local APIC timer on dead cpus.
3) Disable preempt around irq balancing to prevent CPUs going down.
4) Print irq stats for all possible cpus.
5) Debugging check for interrupts on offline cpus.
6) Hacky fixup_irqs() to redirect irqs when cpus go off/online.
7) play_dead() for offline cpus to spin inside.
8) Handle offline cpus set in flush_tlb_others().
9) Grab lock earlier in smp_call_function() to prevent CPUs going down.
10) Implement __cpu_disable() and __cpu_die().
11) Enable local interrupts in cpu_enable() after fixup_irqs()
12) Don't fiddle with NMI on dead cpu, but leave intact on other cpus.
13) Program IRQ affinity whilst cpu is still in cpu_online_map on offline.

Signed-off-by: Zwane Mwaikambo <zwane@linuxpower.ca>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 54 insertions, 13 deletions

diff --git a/arch/i386/kernel/irq.c b/arch/i386/kernel/irq.c
index 73945a3c53c4c..af115004aec58 100644
--- a/arch/i386/kernel/irq.c
+++ b/arch/i386/kernel/irq.c
@@ -15,6 +15,9 @@
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
 
 DEFINE_PER_CPU(irq_cpustat_t, irq_stat) ____cacheline_maxaligned_in_smp;
 EXPORT_PER_CPU_SYMBOL(irq_stat);
@@ -210,9 +213,8 @@ int show_interrupts(struct seq_file *p, void *v)
 
 	if (i == 0) {
 		seq_printf(p, "           ");
-		for (j=0; j<NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "CPU%d       ",j);
+		for_each_cpu(j)
+			seq_printf(p, "CPU%d       ",j);
 		seq_putc(p, '\n');
 	}
 
@@ -225,9 +227,8 @@ int show_interrupts(struct seq_file *p, void *v)
 #ifndef CONFIG_SMP
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
-		for (j = 0; j < NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+		for_each_cpu(j)
+			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
 #endif
 		seq_printf(p, " %14s", irq_desc[i].handler->typename);
 		seq_printf(p, "  %s", action->name);
@@ -240,16 +241,14 @@ skip:
 		spin_unlock_irqrestore(&irq_desc[i].lock, flags);
 	} else if (i == NR_IRQS) {
 		seq_printf(p, "NMI: ");
-		for (j = 0; j < NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "%10u ", nmi_count(j));
+		for_each_cpu(j)
+			seq_printf(p, "%10u ", nmi_count(j));
 		seq_putc(p, '\n');
 #ifdef CONFIG_X86_LOCAL_APIC
 		seq_printf(p, "LOC: ");
-		for (j = 0; j < NR_CPUS; j++)
-			if (cpu_online(j))
-				seq_printf(p, "%10u ",
-					per_cpu(irq_stat,j).apic_timer_irqs);
+		for_each_cpu(j)
+			seq_printf(p, "%10u ",
+				per_cpu(irq_stat,j).apic_timer_irqs);
 		seq_putc(p, '\n');
 #endif
 		seq_printf(p, "ERR: %10u\n", atomic_read(&irq_err_count));
@@ -259,3 +258,45 @@ skip:
 	}
 	return 0;
 }
+
+#ifdef CONFIG_HOTPLUG_CPU
+#include <mach_apic.h>
+
+void fixup_irqs(cpumask_t map)
+{
+	unsigned int irq;
+	static int warned;
+
+	for (irq = 0; irq < NR_IRQS; irq++) {
+		cpumask_t mask;
+		if (irq == 2)
+			continue;
+
+		cpus_and(mask, irq_affinity[irq], map);
+		if (any_online_cpu(mask) == NR_CPUS) {
+			printk("Breaking affinity for irq %i\n", irq);
+			mask = map;
+		}
+		if (irq_desc[irq].handler->set_affinity)
+			irq_desc[irq].handler->set_affinity(irq, mask);
+		else if (irq_desc[irq].action && !(warned++))
+			printk("Cannot set affinity for irq %i\n", irq);
+	}
+
+#if 0
+	barrier();
+	/* Ingo Molnar says: "after the IO-APIC masks have been redirected
+	   [note the nop - the interrupt-enable boundary on x86 is two
+	   instructions from sti] - to flush out pending hardirqs and
+	   IPIs. After this point nothing is supposed to reach this CPU." */
+	__asm__ __volatile__("sti; nop; cli");
+	barrier();
+#else
+	/* That doesn't seem sufficient.  Give it 1ms. */
+	local_irq_enable();
+	mdelay(1);
+	local_irq_disable();
+#endif
+}
+#endif
+