Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (92 commits)
  powerpc: Remove unused 'protect4gb' boot parameter
  powerpc: Build-in e1000e for pseries & ppc64_defconfig
  powerpc/pseries: Make request_ras_irqs() available to other pseries code
  powerpc/numa: Use ibm,architecture-vec-5 to detect form 1 affinity
  powerpc/numa: Set a smaller value for RECLAIM_DISTANCE to enable zone reclaim
  powerpc: Use smt_snooze_delay=-1 to always busy loop
  powerpc: Remove check of ibm,smt-snooze-delay OF property
  powerpc/kdump: Fix race in kdump shutdown
  powerpc/kexec: Fix race in kexec shutdown
  powerpc/kexec: Speedup kexec hash PTE tear down
  powerpc/pseries: Add hcall to read 4 ptes at a time in real mode
  powerpc: Use more accurate limit for first segment memory allocations
  powerpc/kdump: Use chip->shutdown to disable IRQs
  powerpc/kdump: CPUs assume the context of the oopsing CPU
  powerpc/crashdump: Do not fail on NULL pointer dereferencing
  powerpc/eeh: Fix oops when probing in early boot
  powerpc/pci: Check devices status property when scanning OF tree
  powerpc/vio: Switch VIO Bus PM to use generic helpers
  powerpc: Avoid bad relocations in iSeries code
  powerpc: Use common cpu_die (fixes SMP+SUSPEND build)
  ...

1 files changed, 34 insertions, 14 deletions

diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index 040bd1de8d99..26f9900f773c 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -155,33 +155,38 @@ void kexec_copy_flush(struct kimage *image)
 
 #ifdef CONFIG_SMP
 
-/* FIXME: we should schedule this function to be called on all cpus based
- * on calling the interrupts, but we would like to call it off irq level
- * so that the interrupt controller is clean.
- */
+static int kexec_all_irq_disabled = 0;
+
 static void kexec_smp_down(void *arg)
 {
+	local_irq_disable();
+	mb(); /* make sure our irqs are disabled before we say they are */
+	get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF;
+	while(kexec_all_irq_disabled == 0)
+		cpu_relax();
+	mb(); /* make sure all irqs are disabled before this */
+	/*
+	 * Now every CPU has IRQs off, we can clear out any pending
+	 * IPIs and be sure that no more will come in after this.
+	 */
 	if (ppc_md.kexec_cpu_down)
 		ppc_md.kexec_cpu_down(0, 1);
 
-	local_irq_disable();
 	kexec_smp_wait();
 	/* NOTREACHED */
 }
 
-static void kexec_prepare_cpus(void)
+static void kexec_prepare_cpus_wait(int wait_state)
 {
 	int my_cpu, i, notified=-1;
 
-	smp_call_function(kexec_smp_down, NULL, /* wait */0);
 	my_cpu = get_cpu();
-
-	/* check the others cpus are now down (via paca hw cpu id == -1) */
+	/* Make sure each CPU has atleast made it to the state we need */
 	for (i=0; i < NR_CPUS; i++) {
 		if (i == my_cpu)
 			continue;
 
-		while (paca[i].hw_cpu_id != -1) {
+		while (paca[i].kexec_state < wait_state) {
 			barrier();
 			if (!cpu_possible(i)) {
 				printk("kexec: cpu %d hw_cpu_id %d is not"
@@ -201,20 +206,35 @@ static void kexec_prepare_cpus(void)
 			}
 			if (i != notified) {
 				printk( "kexec: waiting for cpu %d (physical"
-						" %d) to go down\n",
-						i, paca[i].hw_cpu_id);
+						" %d) to enter %i state\n",
+					i, paca[i].hw_cpu_id, wait_state);
 				notified = i;
 			}
 		}
 	}
+	mb();
+}
+
+static void kexec_prepare_cpus(void)
+{
+
+	smp_call_function(kexec_smp_down, NULL, /* wait */0);
+	local_irq_disable();
+	mb(); /* make sure IRQs are disabled before we say they are */
+	get_paca()->kexec_state = KEXEC_STATE_IRQS_OFF;
+
+	kexec_prepare_cpus_wait(KEXEC_STATE_IRQS_OFF);
+	/* we are sure every CPU has IRQs off at this point */
+	kexec_all_irq_disabled = 1;
 
 	/* after we tell the others to go down */
 	if (ppc_md.kexec_cpu_down)
 		ppc_md.kexec_cpu_down(0, 0);
 
-	put_cpu();
+	/* Before removing MMU mapings make sure all CPUs have entered real mode */
+	kexec_prepare_cpus_wait(KEXEC_STATE_REAL_MODE);
 
-	local_irq_disable();
+	put_cpu();
 }
 
 #else /* ! SMP */