Commit bb905274 authored by Suzuki K Poulose's avatar Suzuki K Poulose Committed by Catalin Marinas
Browse files

arm64: Handle early CPU boot failures 



A secondary CPU could fail to come online due to insufficient
capabilities and could simply die or loop in the kernel.
e.g, a CPU with no support for the selected kernel PAGE_SIZE
loops in kernel with MMU turned off.
or a hotplugged CPU which doesn't have one of the advertised
system capability will die during the activation.

There is no way to synchronise the status of the failing CPU
back to the master. This patch solves the issue by adding a
field to the secondary_data which can be updated by the failing
CPU. If the secondary CPU fails even before turning the MMU on,
it updates the status in a special variable reserved in the head.txt
section to make sure that the update can be cache invalidated safely
without possible sharing of cache write back granule.

Here are the possible states :

 -1. CPU_MMU_OFF - Initial value set by the master CPU, this value
indicates that the CPU could not turn the MMU on, hence the status
could not be reliably updated in the secondary_data. Instead, the
CPU has updated the status @ __early_cpu_boot_status.

 0. CPU_BOOT_SUCCESS - CPU has booted successfully.

 1. CPU_KILL_ME - CPU has invoked cpu_ops->die, indicating the
master CPU to synchronise by issuing a cpu_ops->cpu_kill.

 2. CPU_STUCK_IN_KERNEL - CPU couldn't invoke die(), instead is
looping in the kernel. This information could be used by say,
kexec to check if it is really safe to do a kexec reboot.

 3. CPU_PANIC_KERNEL - CPU detected some serious issues which
requires kernel to crash immediately. The secondary CPU cannot
call panic() until it has initialised the GIC. This flag can
be used to instruct the master to do so.

Cc: Mark Rutland <mark.rutland@arm.com>
Acked-by: default avatarWill Deacon <will.deacon@arm.com>
Signed-off-by: default avatarSuzuki K Poulose <suzuki.poulose@arm.com>
[catalin.marinas@arm.com: conflict resolution]
[catalin.marinas@arm.com: converted "status" from int to long]
[catalin.marinas@arm.com: updated update_early_cpu_boot_status to use str_l]
Signed-off-by: default avatarCatalin Marinas <catalin.marinas@arm.com>
parent fce6361f

arch/arm64/include/asm/smp.h

+28 −0
Original line number Diff line number Diff line
@@ -16,6 +16,19 @@ 
#ifndef __ASM_SMP_H

#define __ASM_SMP_H



/* Values for secondary_data.status */



#define CPU_MMU_OFF		(-1)

#define CPU_BOOT_SUCCESS	(0)

/* The cpu invoked ops->cpu_die, synchronise it with cpu_kill */

#define CPU_KILL_ME		(1)

/* The cpu couldn't die gracefully and is looping in the kernel */

#define CPU_STUCK_IN_KERNEL	(2)

/* Fatal system error detected by secondary CPU, crash the system */

#define CPU_PANIC_KERNEL	(3)



#ifndef __ASSEMBLY__



#include <linux/threads.h>

#include <linux/cpumask.h>

#include <linux/thread_info.h>
@@ -54,11 +67,17 @@ asmlinkage void secondary_start_kernel(void); 


/*

 * Initial data for bringing up a secondary CPU.

 * @stack  - sp for the secondary CPU

 * @status - Result passed back from the secondary CPU to

 *           indicate failure.

 */

struct secondary_data {

	void *stack;

	long status;

};



extern struct secondary_data secondary_data;

extern long __early_cpu_boot_status;

extern void secondary_entry(void);



extern void arch_send_call_function_single_ipi(int cpu);
@@ -87,4 +106,13 @@ static inline void cpu_park_loop(void) 
	}

}



static inline void update_cpu_boot_status(int val)

{

	WRITE_ONCE(secondary_data.status, val);

	/* Ensure the visibility of the status update */

	dsb(ishst);

}



#endif /* ifndef __ASSEMBLY__ */



#endif /* ifndef __ASM_SMP_H */

arch/arm64/kernel/asm-offsets.c

+2 −0
Original line number Diff line number Diff line
@@ -104,6 +104,8 @@ int main(void) 
  DEFINE(TZ_MINWEST,		offsetof(struct timezone, tz_minuteswest));

  DEFINE(TZ_DSTTIME,		offsetof(struct timezone, tz_dsttime));

  BLANK();

  DEFINE(CPU_BOOT_STACK,	offsetof(struct secondary_data, stack));

  BLANK();

#ifdef CONFIG_KVM_ARM_HOST

  DEFINE(VCPU_CONTEXT,		offsetof(struct kvm_vcpu, arch.ctxt));

  DEFINE(CPU_GP_REGS,		offsetof(struct kvm_cpu_context, gp_regs));

arch/arm64/kernel/head.S

+32 −2
Original line number Diff line number Diff line
@@ -35,6 +35,7 @@ 
#include <asm/pgtable-hwdef.h>

#include <asm/pgtable.h>

#include <asm/page.h>

#include <asm/smp.h>

#include <asm/sysreg.h>

#include <asm/thread_info.h>

#include <asm/virt.h>
@@ -686,7 +687,8 @@ ENTRY(__secondary_switched) 
	msr	vbar_el1, x5

	isb



	ldr_l	x0, secondary_data		// get secondary_data.stack

	adr_l	x0, secondary_data

	ldr	x0, [x0, #CPU_BOOT_STACK]	// get secondary_data.stack

	mov	sp, x0

	and	x0, x0, #~(THREAD_SIZE - 1)

	msr	sp_el0, x0			// save thread_info
@@ -694,6 +696,29 @@ ENTRY(__secondary_switched) 
	b	secondary_start_kernel

ENDPROC(__secondary_switched)



/*

 * The booting CPU updates the failed status @__early_cpu_boot_status,

 * with MMU turned off.

 *

 * update_early_cpu_boot_status tmp, status

 *  - Corrupts tmp1, tmp2

 *  - Writes 'status' to __early_cpu_boot_status and makes sure

 *    it is committed to memory.

 */



	.macro	update_early_cpu_boot_status status, tmp1, tmp2

	mov	\tmp2, #\status

	str_l	\tmp2, __early_cpu_boot_status, \tmp1

	dmb	sy

	dc	ivac, \tmp1			// Invalidate potentially stale cache line

	.endm



	.pushsection	.data..cacheline_aligned

	.align	L1_CACHE_SHIFT

ENTRY(__early_cpu_boot_status)

	.long 	0

	.popsection



/*

 * Enable the MMU.

 *
@@ -712,6 +737,7 @@ __enable_mmu: 
	ubfx	x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4

	cmp	x2, #ID_AA64MMFR0_TGRAN_SUPPORTED

	b.ne	__no_granule_support

	update_early_cpu_boot_status 0, x1, x2

	msr	ttbr0_el1, x25			// load TTBR0

	msr	ttbr1_el1, x26			// load TTBR1

	isb
@@ -748,6 +774,10 @@ __enable_mmu: 
ENDPROC(__enable_mmu)



__no_granule_support:

	/* Indicate that this CPU can't boot and is stuck in the kernel */

	update_early_cpu_boot_status CPU_STUCK_IN_KERNEL, x1, x2

1:

	wfe

	b __no_granule_support

	wfi

	b 1b

ENDPROC(__no_granule_support)

arch/arm64/kernel/smp.c

+45 −0
Original line number Diff line number Diff line
@@ -63,6 +63,8 @@ 
 * where to place its SVC stack

 */

struct secondary_data secondary_data;

/* Number of CPUs which aren't online, but looping in kernel text. */

int cpus_stuck_in_kernel;



enum ipi_msg_type {

	IPI_RESCHEDULE,
@@ -73,6 +75,16 @@ enum ipi_msg_type { 
	IPI_WAKEUP

};



#ifdef CONFIG_HOTPLUG_CPU

static int op_cpu_kill(unsigned int cpu);

#else

static inline int op_cpu_kill(unsigned int cpu)

{

	return -ENOSYS;

}

#endif





/*

 * Boot a secondary CPU, and assign it the specified idle task.

 * This also gives us the initial stack to use for this CPU.
@@ -90,12 +102,14 @@ static DECLARE_COMPLETION(cpu_running); 
int __cpu_up(unsigned int cpu, struct task_struct *idle)

{

	int ret;

	long status;



	/*

	 * We need to tell the secondary core where to find its stack and the

	 * page tables.

	 */

	secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;

	update_cpu_boot_status(CPU_MMU_OFF);

	__flush_dcache_area(&secondary_data, sizeof(secondary_data));



	/*
@@ -119,6 +133,32 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) 
	}



	secondary_data.stack = NULL;

	status = READ_ONCE(secondary_data.status);

	if (ret && status) {



		if (status == CPU_MMU_OFF)

			status = READ_ONCE(__early_cpu_boot_status);



		switch (status) {

		default:

			pr_err("CPU%u: failed in unknown state : 0x%lx\n",

					cpu, status);

			break;

		case CPU_KILL_ME:

			if (!op_cpu_kill(cpu)) {

				pr_crit("CPU%u: died during early boot\n", cpu);

				break;

			}

			/* Fall through */

			pr_crit("CPU%u: may not have shut down cleanly\n", cpu);

		case CPU_STUCK_IN_KERNEL:

			pr_crit("CPU%u: is stuck in kernel\n", cpu);

			cpus_stuck_in_kernel++;

			break;

		case CPU_PANIC_KERNEL:

			panic("CPU%u detected unsupported configuration\n", cpu);

		}

	}



	return ret;

}
@@ -184,6 +224,9 @@ asmlinkage void secondary_start_kernel(void) 
	 */

	pr_info("CPU%u: Booted secondary processor [%08x]\n",

					 cpu, read_cpuid_id());

	update_cpu_boot_status(CPU_BOOT_SUCCESS);

	/* Make sure the status update is visible before we complete */

	smp_wmb();

	set_cpu_online(cpu, true);

	complete(&cpu_running);
@@ -326,10 +369,12 @@ void cpu_die_early(void) 
	set_cpu_present(cpu, 0);



#ifdef CONFIG_HOTPLUG_CPU

	update_cpu_boot_status(CPU_KILL_ME);

	/* Check if we can park ourselves */

	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die)

		cpu_ops[cpu]->cpu_die(cpu);

#endif

	update_cpu_boot_status(CPU_STUCK_IN_KERNEL);



	cpu_park_loop();

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE