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: Will Deacon <will.deacon@arm.com>
Signed-off-by: Suzuki 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: Catalin Marinas <catalin.marinas@arm.com>

1 files changed, 28 insertions, 0 deletions

diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 51913be35a0a..817a067ba058 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;
+	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 */