[PATCH v5 0/7] Verify early CPU features

@@ -68,6 +68,7 @@ extern int __cpu_disable(void);
 
 extern void __cpu_die(unsigned int cpu);
 extern void cpu_die(void);
+extern void cpu_die_early(void);
 
 static inline void cpu_park_loop(void)
 {

@@ -827,25 +827,6 @@ static u64 __raw_read_system_reg(u32 sys_id)
 }
 
 /*
- * Kill the calling secondary CPU, early in bringup before it is turned
- * online.
- */
-void cpu_die_early(void)
-{
-	int cpu = smp_processor_id();
-
-	pr_crit("CPU%d: will not boot\n", cpu);
-
-	/* Mark this CPU absent */
-	set_cpu_present(cpu, 0);
-
-	/* Check if we can park ourselves */
-	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die)
-		cpu_ops[cpu]->cpu_die(cpu);
-	cpu_park_loop();
-}
-
-/*
  * Run through the enabled system capabilities and enable() it on this CPU.
  * The capabilities were decided based on the available CPUs at the boot time.
  * Any new CPU should match the system wide status of the capability. If the

@@ -313,6 +313,28 @@ void cpu_die(void)
 }
 #endif
 
+/*
+ * Kill the calling secondary CPU, early in bringup before it is turned
+ * online.
+ */
+void cpu_die_early(void)
+{
+	int cpu = smp_processor_id();
+
+	pr_crit("CPU%d: will not boot\n", cpu);
+
+	/* Mark this CPU absent */
+	set_cpu_present(cpu, 0);
+
+#ifdef CONFIG_HOTPLUG_CPU
+	/* Check if we can park ourselves */
+	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die)
+		cpu_ops[cpu]->cpu_die(cpu);
+#endif
+
+	cpu_park_loop();
+}
+
 static void __init hyp_mode_check(void)
 {
 	if (is_hyp_mode_available())

@@ -827,15 +827,15 @@ static u64 __raw_read_system_reg(u32 sys_id)
 }
 
 /*
- * Park the CPU which doesn't have the capability as advertised
- * by the system.
+ * Kill the calling secondary CPU, early in bringup before it is turned
+ * online.
  */
-static void fail_incapable_cpu(char *cap_type,
-				 const struct arm64_cpu_capabilities *cap)
+void cpu_die_early(void)
 {
 	int cpu = smp_processor_id();
 
-	pr_crit("CPU%d: missing %s : %s\n", cpu, cap_type, cap->desc);
+	pr_crit("CPU%d: will not boot\n", cpu);
+
 	/* Mark this CPU absent */
 	set_cpu_present(cpu, 0);
 

@@ -873,8 +873,11 @@ void verify_local_cpu_capabilities(void)
 		 * If the new CPU misses an advertised feature, we cannot proceed
 		 * further, park the cpu.
 		 */
-		if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i]))
-			fail_incapable_cpu("arm64_features", &caps[i]);
+		if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i])) {
+			pr_crit("CPU%d: missing feature: %s\n",
+					smp_processor_id(), caps[i].desc);
+			cpu_die_early();
+		}
 		if (caps[i].enable)
 			caps[i].enable(NULL);
 	}

@@ -882,8 +885,11 @@ void verify_local_cpu_capabilities(void)
 	for (i = 0, caps = arm64_hwcaps; caps[i].desc; i++) {
 		if (!cpus_have_hwcap(&caps[i]))
 			continue;
-		if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i]))
-			fail_incapable_cpu("arm64_hwcaps", &caps[i]);
+		if (!feature_matches(__raw_read_system_reg(caps[i].sys_reg), &caps[i])) {
+			pr_crit("CPU%d: missing HWCAP: %s\n",
+					smp_processor_id(), caps[i].desc);
+			cpu_die_early();
+		}
 	}
 }
 

@@ -69,4 +69,12 @@ extern int __cpu_disable(void);
 extern void __cpu_die(unsigned int cpu);
 extern void cpu_die(void);
 
+static inline void cpu_park_loop(void)
+{
+	for (;;) {
+		wfe();
+		wfi();
+	}
+}
+
 #endif /* ifndef __ASM_SMP_H */

@@ -842,10 +842,7 @@ static void fail_incapable_cpu(char *cap_type,
 	/* Check if we can park ourselves */
 	if (cpu_ops[cpu] && cpu_ops[cpu]->cpu_die)
 		cpu_ops[cpu]->cpu_die(cpu);
-	asm(
-	"1:	wfe\n"
-	"	wfi\n"
-	"	b	1b");
+	cpu_park_loop();
 }
 
 /*

@@ -147,4 +147,6 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 #define deactivate_mm(tsk,mm)	do { } while (0)
 #define activate_mm(prev,next)	switch_mm(prev, next, NULL)
 
+void verify_cpu_asid_bits(void);
+
 #endif

@@ -24,6 +24,7 @@
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
+#include <asm/mmu_context.h>
 #include <asm/processor.h>
 #include <asm/sysreg.h>
 

@@ -825,6 +826,15 @@ static u64 __raw_read_system_reg(u32 sys_id)
 }
 
 /*
+ * Check for CPU features that are used in early boot
+ * based on the Boot CPU value.
+ */
+static void check_early_cpu_features(void)
+{
+	verify_cpu_asid_bits();
+}
+
+/*
  * Run through the enabled system capabilities and enable() it on this CPU.
  * The capabilities were decided based on the available CPUs at the boot time.
  * Any new CPU should match the system wide status of the capability. If the

@@ -837,6 +847,8 @@ void verify_local_cpu_capabilities(void)
 	int i;
 	const struct arm64_cpu_capabilities *caps;
 
+	check_early_cpu_features();
+
 	/*
 	 * If we haven't computed the system capabilities, there is nothing
 	 * to verify.

@@ -24,6 +24,7 @@
 
 #include <asm/cpufeature.h>
 #include <asm/mmu_context.h>
+#include <asm/smp.h>
 #include <asm/tlbflush.h>
 
 static u32 asid_bits;

@@ -62,6 +63,23 @@ static u32 get_cpu_asid_bits(void)
 	return asid;
 }
 
+/* Check if the current cpu's ASIDBits is compatible with asid_bits */
+void verify_cpu_asid_bits(void)
+{
+	u32 asid = get_cpu_asid_bits();
+
+	if (asid < asid_bits) {
+		/*
+		 * We cannot decrease the ASID size@runtime, so panic if we support
+		 * fewer ASID bits than the boot CPU.
+		 */
+		pr_crit("CPU%d: smaller ASID size(%u) than boot CPU (%u)\n",
+				smp_processor_id(), asid, asid_bits);
+		update_cpu_boot_status(CPU_PANIC_KERNEL);
+		cpu_park_loop();
+	}
+}
+
 static void flush_context(unsigned int cpu)
 {
 	int i;

@@ -40,6 +40,28 @@ static cpumask_t tlb_flush_pending;
 #define ASID_FIRST_VERSION	(1UL << asid_bits)
 #define NUM_USER_ASIDS		ASID_FIRST_VERSION
 
+/* Get the ASIDBits supported by the current CPU */
+static u32 get_cpu_asid_bits(void)
+{
+	u32 asid;
+	int fld = cpuid_feature_extract_field(read_cpuid(ID_AA64MMFR0_EL1),
+						ID_AA64MMFR0_ASID_SHIFT);
+
+	switch (fld) {
+	default:
+		pr_warn("CPU%d: Unknown ASID size (%d); assuming 8-bit\n",
+					smp_processor_id(),  fld);
+		/* Fallthrough */
+	case 0:
+		asid = 8;
+		break;
+	case 2:
+		asid = 16;
+	}
+
+	return asid;
+}
+
 static void flush_context(unsigned int cpu)
 {
 	int i;

@@ -187,19 +209,7 @@ switch_mm_fastpath:
 
 static int asids_init(void)
 {
-	int fld = cpuid_feature_extract_field(read_cpuid(ID_AA64MMFR0_EL1), 4);
-
-	switch (fld) {
-	default:
-		pr_warn("Unknown ASID size (%d); assuming 8-bit\n", fld);
-		/* Fallthrough */
-	case 0:
-		asid_bits = 8;
-		break;
-	case 2:
-		asid_bits = 16;
-	}
-
+	asid_bits = get_cpu_asid_bits();
 	/* If we end up with more CPUs than ASIDs, expect things to crash */
 	WARN_ON(NUM_USER_ASIDS < num_possible_cpus());
 	atomic64_set(&asid_generation, ASID_FIRST_VERSION);

@@ -164,13 +164,7 @@ void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 			    const char *info);
 void check_local_cpu_errata(void);
 
-#ifdef CONFIG_HOTPLUG_CPU
 void verify_local_cpu_capabilities(void);
-#else
-static inline void verify_local_cpu_capabilities(void)
-{
-}
-#endif
 
 u64 read_system_reg(u32 id);
 

@@ -768,8 +768,6 @@ enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps)
 			on_each_cpu(caps[i].enable, NULL, true);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-
 /*
  * Flag to indicate if we have computed the system wide
  * capabilities based on the boot time active CPUs. This

@@ -874,14 +872,6 @@ void verify_local_cpu_capabilities(void)
 	}
 }
 
-#else	/* !CONFIG_HOTPLUG_CPU */
-
-static inline void set_sys_caps_initialised(void)
-{
-}
-
-#endif	/* CONFIG_HOTPLUG_CPU */
-
 static void __init setup_feature_capabilities(void)
 {
 	update_cpu_capabilities(arm64_features, "detected feature:");

@@ -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 */

@@ -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));

@@ -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)

@@ -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();
 }