[PATCH] powerpc: Turn cpu_irq_down into kexec_cpu_down

We currently have a ppc_md member called cpu_irq_down, which disables IRQs
for the cpu in question. The only caller of cpu_irq_down is the kexec code.

On pSeries we need to do more than just teardown IRQs at kexec time, so rename
the ppc_md member to kexec_cpu_down and expand it. The pSeries code needs to
know, and other platforms might too, whether we're doing a crash shutdown (ie.
panicking) or a regular kexec, so add a flag for that.

The pSeries implementation of kexec_cpu_down does an unregister VPA call, which
tells the Hypervisor to stop writing stuff into our pacas. Without this we can
get weird memory corruption bugs when we kexec, caused by the Hypervisor
writing into the first kernel's pacas which happens to be somewhere interesting
in the second kernel's memory.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>

3 files changed, 33 insertions, 9 deletions

diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 31990829310c..b9d9732b2e06 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -200,14 +200,12 @@ static void __init pSeries_setup_arch(void)
 	if (ppc64_interrupt_controller == IC_OPEN_PIC) {
 		ppc_md.init_IRQ       = pSeries_init_mpic;
 		ppc_md.get_irq        = mpic_get_irq;
-	 	ppc_md.cpu_irq_down   = mpic_teardown_this_cpu;
 		/* Allocate the mpic now, so that find_and_init_phbs() can
 		 * fill the ISUs */
 		pSeries_setup_mpic();
 	} else {
 		ppc_md.init_IRQ       = xics_init_IRQ;
 		ppc_md.get_irq        = xics_get_irq;
-		ppc_md.cpu_irq_down   = xics_teardown_cpu;
 	}
 
 #ifdef CONFIG_SMP
@@ -595,6 +593,27 @@ static int pSeries_pci_probe_mode(struct pci_bus *bus)
 	return PCI_PROBE_NORMAL;
 }
 
+#ifdef CONFIG_KEXEC
+static void pseries_kexec_cpu_down(int crash_shutdown, int secondary)
+{
+	/* Don't risk a hypervisor call if we're crashing */
+	if (!crash_shutdown) {
+		unsigned long vpa = __pa(&get_paca()->lppaca);
+
+		if (unregister_vpa(hard_smp_processor_id(), vpa)) {
+			printk("VPA deregistration of cpu %u (hw_cpu_id %d) "
+					"failed\n", smp_processor_id(),
+					hard_smp_processor_id());
+		}
+	}
+
+	if (ppc64_interrupt_controller == IC_OPEN_PIC)
+		mpic_teardown_this_cpu(secondary);
+	else
+		xics_teardown_cpu(secondary);
+}
+#endif
+
 struct machdep_calls __initdata pSeries_md = {
 	.probe			= pSeries_probe,
 	.setup_arch		= pSeries_setup_arch,
@@ -617,4 +636,7 @@ struct machdep_calls __initdata pSeries_md = {
 	.check_legacy_ioport	= pSeries_check_legacy_ioport,
 	.system_reset_exception = pSeries_system_reset_exception,
 	.machine_check_exception = pSeries_machine_check_exception,
+#ifdef CONFIG_KEXEC
+	.kexec_cpu_down		= pseries_kexec_cpu_down,
+#endif
 };
diff --git a/arch/ppc64/kernel/machine_kexec.c b/arch/ppc64/kernel/machine_kexec.c
index 07ea03598c00..203f1d5e6f10 100644
--- a/arch/ppc64/kernel/machine_kexec.c
+++ b/arch/ppc64/kernel/machine_kexec.c
@@ -185,8 +185,8 @@ void kexec_copy_flush(struct kimage *image)
  */
 void kexec_smp_down(void *arg)
 {
-	if (ppc_md.cpu_irq_down)
-		ppc_md.cpu_irq_down(1);
+	if (ppc_md.kexec_cpu_down)
+		ppc_md.kexec_cpu_down(0, 1);
 
 	local_irq_disable();
 	kexec_smp_wait();
@@ -233,8 +233,8 @@ static void kexec_prepare_cpus(void)
 	}
 
 	/* after we tell the others to go down */
-	if (ppc_md.cpu_irq_down)
-		ppc_md.cpu_irq_down(0);
+	if (ppc_md.kexec_cpu_down)
+		ppc_md.kexec_cpu_down(0, 0);
 
 	put_cpu();
 
@@ -255,8 +255,8 @@ static void kexec_prepare_cpus(void)
 	 * UP to an SMP kernel.
 	 */
 	smp_release_cpus();
-	if (ppc_md.cpu_irq_down)
-		ppc_md.cpu_irq_down(0);
+	if (ppc_md.kexec_cpu_down)
+		ppc_md.kexec_cpu_down(0, 0);
 	local_irq_disable();
 }
 
diff --git a/include/asm-powerpc/machdep.h b/include/asm-powerpc/machdep.h
index 5670f0cd6143..c011abb8b600 100644
--- a/include/asm-powerpc/machdep.h
+++ b/include/asm-powerpc/machdep.h
@@ -93,7 +93,9 @@ struct machdep_calls {
 
 	void		(*init_IRQ)(void);
 	int		(*get_irq)(struct pt_regs *);
-	void		(*cpu_irq_down)(int secondary);
+#ifdef CONFIG_KEXEC
+	void		(*kexec_cpu_down)(int crash_shutdown, int secondary);
+#endif
 
 	/* PCI stuff */
 	/* Called after scanning the bus, before allocating resources */