[PATCH v5 4/7] arm64: Handle early CPU boot failures
Suzuki K Poulose
suzuki.poulose at arm.com
Tue Feb 23 02:31:42 PST 2016
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 at arm.com>
Cc: Catalin Marinas <catalin.marinas at arm.com>
Acked-by: Will Deacon <will.deacon at arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose at arm.com>
---
Changes since V4:
- Add braces around status values.
- Use adr_l macro for write to __early_cpu_boot_status
- Move __early_cpu_boot_status to .data..cacheline_aligned section. Invalidate
only on the write side.
- Get rid of the smp_{w,r}mb() around updates to secondary_data.status.
- Add dsb() to update_boot_cpu_status()
---
arch/arm64/include/asm/smp.h | 28 ++++++++++++++++++++++++
arch/arm64/kernel/asm-offsets.c | 2 ++
arch/arm64/kernel/head.S | 34 +++++++++++++++++++++++++++--
arch/arm64/kernel/smp.c | 45 +++++++++++++++++++++++++++++++++++++++
4 files changed, 107 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 32e75ee..42baa97 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -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;
+ int status;
};
+
extern struct secondary_data secondary_data;
+extern int __early_cpu_boot_status;
extern void secondary_entry(void);
extern void arch_send_call_function_single_ipi(int cpu);
@@ -78,4 +97,13 @@ 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 */
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index fffa4ac6..463fcf1 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -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));
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 917d981..4d26d92 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -34,6 +34,7 @@
#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>
@@ -611,7 +612,7 @@ ENTRY(secondary_startup)
ENDPROC(secondary_startup)
ENTRY(__secondary_switched)
- ldr x0, [x21] // get secondary_data.stack
+ ldr x0, [x21, #CPU_BOOT_STACK] // get secondary_data.stack
mov sp, x0
and x0, x0, #~(THREAD_SIZE - 1)
msr sp_el0, x0 // save thread_info
@@ -620,6 +621,30 @@ ENTRY(__secondary_switched)
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
+ adr_l \tmp1, __early_cpu_boot_status
+ mov \tmp2, #\status
+ str \tmp2, [\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.
*
* x0 = SCTLR_EL1 value for turning on the MMU.
@@ -636,6 +661,7 @@ __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
ldr x5, =vectors
msr vbar_el1, x5
msr ttbr0_el1, x25 // load TTBR0
@@ -655,6 +681,10 @@ __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)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 59f032b..a0bba03 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -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,
@@ -72,6 +74,16 @@ enum ipi_msg_type {
IPI_IRQ_WORK,
};
+#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.
@@ -89,12 +101,14 @@ static DECLARE_COMPLETION(cpu_running);
int __cpu_up(unsigned int cpu, struct task_struct *idle)
{
int ret;
+ int 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));
/*
@@ -118,6 +132,32 @@ 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%x\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;
}
@@ -185,6 +225,9 @@ 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);
@@ -327,10 +370,12 @@ 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();
}
--
1.7.9.5
More information about the linux-arm-kernel
mailing list