diff mbox

[v35,08/14] arm64: kdump: implement machine_crash_shutdown()

Message ID 20170403022440.12515-6-takahiro.akashi@linaro.org (mailing list archive)
State New, archived
Headers show

Commit Message

AKASHI Takahiro April 3, 2017, 2:24 a.m. UTC
Primary kernel calls machine_crash_shutdown() to shut down non-boot cpus
and save registers' status in per-cpu ELF notes before starting crash
dump kernel. See kernel_kexec().
Even if not all secondary cpus have shut down, we do kdump anyway.

As we don't have to make non-boot(crashed) cpus offline (to preserve
correct status of cpus at crash dump) before shutting down, this patch
also adds a variant of smp_send_stop().

Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Reviewed-by: James Morse <james.morse@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/include/asm/hardirq.h  |  2 +-
 arch/arm64/include/asm/kexec.h    | 42 +++++++++++++++++++++++-
 arch/arm64/include/asm/smp.h      |  3 ++
 arch/arm64/kernel/machine_kexec.c | 58 ++++++++++++++++++++++++++++++---
 arch/arm64/kernel/smp.c           | 68 +++++++++++++++++++++++++++++++++++++++
 5 files changed, 167 insertions(+), 6 deletions(-)

Comments

David Woodhouse April 3, 2017, 9:21 a.m. UTC | #1
On Mon, 2017-04-03 at 11:24 +0900, AKASHI Takahiro wrote:
> 
> +static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs
> *regs)
> +{
> +#ifdef CONFIG_KEXEC_CORE
> +       crash_save_cpu(regs, cpu);
> +
> +       atomic_dec(&waiting_for_crash_ipi);
> +
> +       local_irq_disable();

Shouldn't the above two be the other way round? Stop handling
interrupts *before* we tell the surviving CPU that we're done?

Also, should the surviving CPU be calling __cpu_die() to attempt to
check that the others really have died? Sure, it can't do much more
than print a warning if the call to ->cpu_kill() times out, but that's
still useful information. And perhaps we could allow platforms to
register a method to shoot other CPUs down forcefully if they don't
respond. My board could apparently support that.

It would certainly be useful to allow smp_send_crash_stop() to be
overridden with a platform-specific method instead of normal IPIs. The
platform might be able to do something... less maskable.
AKASHI Takahiro April 4, 2017, 7:29 a.m. UTC | #2
On Mon, Apr 03, 2017 at 10:21:34AM +0100, David Woodhouse wrote:
> On Mon, 2017-04-03 at 11:24 +0900, AKASHI Takahiro wrote:
> > 
> > +static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs
> > *regs)
> > +{
> > +#ifdef CONFIG_KEXEC_CORE
> > +       crash_save_cpu(regs, cpu);
> > +
> > +       atomic_dec(&waiting_for_crash_ipi);
> > +
> > +       local_irq_disable();
> 
> Shouldn't the above two be the other way round? Stop handling
> interrupts *before* we tell the surviving CPU that we're done?

Might be, but I'm not sure how well such a change works.
Do you see any improvement in, say, saving failed-to-reboot cases?

> Also, should the surviving CPU be calling __cpu_die() to attempt to
> check that the others really have died? Sure, it can't do much more
> than print a warning if the call to ->cpu_kill() times out, but that's
> still useful information.

A pair of cpu_wait_death() and cpu_report_death() merely does
a hand-shake protocol over per-cpu "cpu_hotplug_state" variable.
In this sense, it's not much different from "waiting_for_crash_ipi"
approach used here in ipi_cpu_crash_stop().

Having said that, cpu_ops->cpu_kill() might help forcefully tear down
the cpu(s). One of my concerns is that we may lose some data in cache.

> And perhaps we could allow platforms to
> register a method to shoot other CPUs down forcefully if they don't
> respond. My board could apparently support that.
> 
> It would certainly be useful to allow smp_send_crash_stop() to be
> overridden with a platform-specific method instead of normal IPIs. The
> platform might be able to do something... less maskable.

I agree.
It would be great if you post your own patch for such a new interface.
(Without any hardware, I can't implement/test this feature, anyway.)

Thanks,
-Takahiro AKASHI
diff mbox

Patch

diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
index 8740297dac77..1473fc2f7ab7 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -20,7 +20,7 @@ 
 #include <linux/threads.h>
 #include <asm/irq.h>
 
-#define NR_IPI	6
+#define NR_IPI	7
 
 typedef struct {
 	unsigned int __softirq_pending;
diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h
index 90aabbe893b7..e17f0529a882 100644
--- a/arch/arm64/include/asm/kexec.h
+++ b/arch/arm64/include/asm/kexec.h
@@ -40,7 +40,47 @@ 
 static inline void crash_setup_regs(struct pt_regs *newregs,
 				    struct pt_regs *oldregs)
 {
-	/* Empty routine needed to avoid build errors. */
+	if (oldregs) {
+		memcpy(newregs, oldregs, sizeof(*newregs));
+	} else {
+		u64 tmp1, tmp2;
+
+		__asm__ __volatile__ (
+			"stp	 x0,   x1, [%2, #16 *  0]\n"
+			"stp	 x2,   x3, [%2, #16 *  1]\n"
+			"stp	 x4,   x5, [%2, #16 *  2]\n"
+			"stp	 x6,   x7, [%2, #16 *  3]\n"
+			"stp	 x8,   x9, [%2, #16 *  4]\n"
+			"stp	x10,  x11, [%2, #16 *  5]\n"
+			"stp	x12,  x13, [%2, #16 *  6]\n"
+			"stp	x14,  x15, [%2, #16 *  7]\n"
+			"stp	x16,  x17, [%2, #16 *  8]\n"
+			"stp	x18,  x19, [%2, #16 *  9]\n"
+			"stp	x20,  x21, [%2, #16 * 10]\n"
+			"stp	x22,  x23, [%2, #16 * 11]\n"
+			"stp	x24,  x25, [%2, #16 * 12]\n"
+			"stp	x26,  x27, [%2, #16 * 13]\n"
+			"stp	x28,  x29, [%2, #16 * 14]\n"
+			"mov	 %0,  sp\n"
+			"stp	x30,  %0,  [%2, #16 * 15]\n"
+
+			"/* faked current PSTATE */\n"
+			"mrs	 %0, CurrentEL\n"
+			"mrs	 %1, SPSEL\n"
+			"orr	 %0, %0, %1\n"
+			"mrs	 %1, DAIF\n"
+			"orr	 %0, %0, %1\n"
+			"mrs	 %1, NZCV\n"
+			"orr	 %0, %0, %1\n"
+			/* pc */
+			"adr	 %1, 1f\n"
+		"1:\n"
+			"stp	 %1, %0,   [%2, #16 * 16]\n"
+			: "=&r" (tmp1), "=&r" (tmp2)
+			: "r" (newregs)
+			: "memory"
+		);
+	}
 }
 
 #if defined(CONFIG_KEXEC_CORE) && defined(CONFIG_HIBERNATION)
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index d050d720a1b4..55f08c5acfad 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -148,6 +148,9 @@  static inline void cpu_panic_kernel(void)
  */
 bool cpus_are_stuck_in_kernel(void);
 
+extern void smp_send_crash_stop(void);
+extern bool smp_crash_stop_failed(void);
+
 #endif /* ifndef __ASSEMBLY__ */
 
 #endif /* ifndef __ASM_SMP_H */
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index a6d66b98d795..779a80046066 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -9,6 +9,9 @@ 
  * published by the Free Software Foundation.
  */
 
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
 #include <linux/kexec.h>
 #include <linux/page-flags.h>
 #include <linux/smp.h>
@@ -143,11 +146,15 @@  void machine_kexec(struct kimage *kimage)
 {
 	phys_addr_t reboot_code_buffer_phys;
 	void *reboot_code_buffer;
+	bool in_kexec_crash = (kimage == kexec_crash_image);
+	bool stuck_cpus = cpus_are_stuck_in_kernel();
 
 	/*
 	 * New cpus may have become stuck_in_kernel after we loaded the image.
 	 */
-	BUG_ON(cpus_are_stuck_in_kernel() || (num_online_cpus() > 1));
+	BUG_ON(!in_kexec_crash && (stuck_cpus || (num_online_cpus() > 1)));
+	WARN(in_kexec_crash && (stuck_cpus || smp_crash_stop_failed()),
+		"Some CPUs may be stale, kdump will be unreliable.\n");
 
 	reboot_code_buffer_phys = page_to_phys(kimage->control_code_page);
 	reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys);
@@ -199,15 +206,58 @@  void machine_kexec(struct kimage *kimage)
 	 * relocation is complete.
 	 */
 
-	cpu_soft_restart(1, reboot_code_buffer_phys, kimage->head,
-		kimage->start, 0);
+	cpu_soft_restart(kimage != kexec_crash_image,
+		reboot_code_buffer_phys, kimage->head, kimage->start, 0);
 
 	BUG(); /* Should never get here. */
 }
 
+static void machine_kexec_mask_interrupts(void)
+{
+	unsigned int i;
+	struct irq_desc *desc;
+
+	for_each_irq_desc(i, desc) {
+		struct irq_chip *chip;
+		int ret;
+
+		chip = irq_desc_get_chip(desc);
+		if (!chip)
+			continue;
+
+		/*
+		 * First try to remove the active state. If this
+		 * fails, try to EOI the interrupt.
+		 */
+		ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false);
+
+		if (ret && irqd_irq_inprogress(&desc->irq_data) &&
+		    chip->irq_eoi)
+			chip->irq_eoi(&desc->irq_data);
+
+		if (chip->irq_mask)
+			chip->irq_mask(&desc->irq_data);
+
+		if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
+			chip->irq_disable(&desc->irq_data);
+	}
+}
+
+/**
+ * machine_crash_shutdown - shutdown non-crashing cpus and save registers
+ */
 void machine_crash_shutdown(struct pt_regs *regs)
 {
-	/* Empty routine needed to avoid build errors. */
+	local_irq_disable();
+
+	/* shutdown non-crashing cpus */
+	smp_send_crash_stop();
+
+	/* for crashing cpu */
+	crash_save_cpu(regs, smp_processor_id());
+	machine_kexec_mask_interrupts();
+
+	pr_info("Starting crashdump kernel...\n");
 }
 
 void arch_kexec_protect_crashkres(void)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index d4739552da28..ffee4e454ac5 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -39,6 +39,7 @@ 
 #include <linux/completion.h>
 #include <linux/of.h>
 #include <linux/irq_work.h>
+#include <linux/kexec.h>
 
 #include <asm/alternative.h>
 #include <asm/atomic.h>
@@ -76,6 +77,7 @@  enum ipi_msg_type {
 	IPI_RESCHEDULE,
 	IPI_CALL_FUNC,
 	IPI_CPU_STOP,
+	IPI_CPU_CRASH_STOP,
 	IPI_TIMER,
 	IPI_IRQ_WORK,
 	IPI_WAKEUP
@@ -756,6 +758,7 @@  static const char *ipi_types[NR_IPI] __tracepoint_string = {
 	S(IPI_RESCHEDULE, "Rescheduling interrupts"),
 	S(IPI_CALL_FUNC, "Function call interrupts"),
 	S(IPI_CPU_STOP, "CPU stop interrupts"),
+	S(IPI_CPU_CRASH_STOP, "CPU stop (for crash dump) interrupts"),
 	S(IPI_TIMER, "Timer broadcast interrupts"),
 	S(IPI_IRQ_WORK, "IRQ work interrupts"),
 	S(IPI_WAKEUP, "CPU wake-up interrupts"),
@@ -830,6 +833,29 @@  static void ipi_cpu_stop(unsigned int cpu)
 		cpu_relax();
 }
 
+#ifdef CONFIG_KEXEC_CORE
+static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0);
+#endif
+
+static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
+{
+#ifdef CONFIG_KEXEC_CORE
+	crash_save_cpu(regs, cpu);
+
+	atomic_dec(&waiting_for_crash_ipi);
+
+	local_irq_disable();
+
+#ifdef CONFIG_HOTPLUG_CPU
+	if (cpu_ops[cpu]->cpu_die)
+		cpu_ops[cpu]->cpu_die(cpu);
+#endif
+
+	/* just in case */
+	cpu_park_loop();
+#endif
+}
+
 /*
  * Main handler for inter-processor interrupts
  */
@@ -860,6 +886,15 @@  void handle_IPI(int ipinr, struct pt_regs *regs)
 		irq_exit();
 		break;
 
+	case IPI_CPU_CRASH_STOP:
+		if (IS_ENABLED(CONFIG_KEXEC_CORE)) {
+			irq_enter();
+			ipi_cpu_crash_stop(cpu, regs);
+
+			unreachable();
+		}
+		break;
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 	case IPI_TIMER:
 		irq_enter();
@@ -932,6 +967,39 @@  void smp_send_stop(void)
 			   cpumask_pr_args(cpu_online_mask));
 }
 
+#ifdef CONFIG_KEXEC_CORE
+void smp_send_crash_stop(void)
+{
+	cpumask_t mask;
+	unsigned long timeout;
+
+	if (num_online_cpus() == 1)
+		return;
+
+	cpumask_copy(&mask, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), &mask);
+
+	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+
+	pr_crit("SMP: stopping secondary CPUs\n");
+	smp_cross_call(&mask, IPI_CPU_CRASH_STOP);
+
+	/* Wait up to one second for other CPUs to stop */
+	timeout = USEC_PER_SEC;
+	while ((atomic_read(&waiting_for_crash_ipi) > 0) && timeout--)
+		udelay(1);
+
+	if (atomic_read(&waiting_for_crash_ipi) > 0)
+		pr_warning("SMP: failed to stop secondary CPUs %*pbl\n",
+			   cpumask_pr_args(&mask));
+}
+
+bool smp_crash_stop_failed(void)
+{
+	return (atomic_read(&waiting_for_crash_ipi) > 0);
+}
+#endif
+
 /*
  * not supported here
  */