1 files changed, 339 insertions, 224 deletions

diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index d4ed9a19d8fe..4ced34f62dab 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -30,8 +30,11 @@
 #include <linux/completion.h>
 #include <linux/of.h>
 #include <linux/irq_work.h>
+#include <linux/kernel_stat.h>
 #include <linux/kexec.h>
+#include <linux/kgdb.h>
 #include <linux/kvm_host.h>
+#include <linux/nmi.h>
 
 #include <asm/alternative.h>
 #include <asm/atomic.h>
@@ -43,8 +46,6 @@
 #include <asm/kvm_mmu.h>
 #include <asm/mmu_context.h>
 #include <asm/numa.h>
-#include <asm/pgtable.h>
-#include <asm/pgalloc.h>
 #include <asm/processor.h>
 #include <asm/smp_plat.h>
 #include <asm/sections.h>
@@ -52,7 +53,6 @@
 #include <asm/ptrace.h>
 #include <asm/virt.h>
 
-#define CREATE_TRACE_POINTS
 #include <trace/events/ipi.h>
 
 DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number);
@@ -65,7 +65,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_number);
  */
 struct secondary_data secondary_data;
 /* Number of CPUs which aren't online, but looping in kernel text. */
-int cpus_stuck_in_kernel;
+static int cpus_stuck_in_kernel;
 
 enum ipi_msg_type {
 	IPI_RESCHEDULE,
@@ -74,10 +74,24 @@ enum ipi_msg_type {
 	IPI_CPU_CRASH_STOP,
 	IPI_TIMER,
 	IPI_IRQ_WORK,
-	IPI_WAKEUP
+	NR_IPI,
+	/*
+	 * Any enum >= NR_IPI and < MAX_IPI is special and not tracable
+	 * with trace_ipi_*
+	 */
+	IPI_CPU_BACKTRACE = NR_IPI,
+	IPI_KGDB_ROUNDUP,
+	MAX_IPI
 };
 
+static int ipi_irq_base __ro_after_init;
+static int nr_ipi __ro_after_init = NR_IPI;
+static struct irq_desc *ipi_desc[MAX_IPI] __ro_after_init;
+
+static void ipi_setup(int cpu);
+
 #ifdef CONFIG_HOTPLUG_CPU
+static void ipi_teardown(int cpu);
 static int op_cpu_kill(unsigned int cpu);
 #else
 static inline int op_cpu_kill(unsigned int cpu)
@@ -93,8 +107,10 @@ static inline int op_cpu_kill(unsigned int cpu)
  */
 static int boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	if (cpu_ops[cpu]->cpu_boot)
-		return cpu_ops[cpu]->cpu_boot(cpu);
+	const struct cpu_operations *ops = get_cpu_ops(cpu);
+
+	if (ops->cpu_boot)
+		return ops->cpu_boot(cpu);
 
 	return -EOPNOTSUPP;
 }
@@ -111,67 +127,58 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	 * page tables.
 	 */
 	secondary_data.task = idle;
-	secondary_data.stack = task_stack_page(idle) + THREAD_SIZE;
 	update_cpu_boot_status(CPU_MMU_OFF);
-	__flush_dcache_area(&secondary_data, sizeof(secondary_data));
 
-	/*
-	 * Now bring the CPU into our world.
-	 */
+	/* Now bring the CPU into our world */
 	ret = boot_secondary(cpu, idle);
-	if (ret == 0) {
-		/*
-		 * CPU was successfully started, wait for it to come online or
-		 * time out.
-		 */
-		wait_for_completion_timeout(&cpu_running,
-					    msecs_to_jiffies(5000));
-
-		if (!cpu_online(cpu)) {
-			pr_crit("CPU%u: failed to come online\n", cpu);
-			ret = -EIO;
-		}
-	} else {
+	if (ret) {
 		pr_err("CPU%u: failed to boot: %d\n", cpu, ret);
 		return ret;
 	}
 
+	/*
+	 * CPU was successfully started, wait for it to come online or
+	 * time out.
+	 */
+	wait_for_completion_timeout(&cpu_running,
+				    msecs_to_jiffies(5000));
+	if (cpu_online(cpu))
+		return 0;
+
+	pr_crit("CPU%u: failed to come online\n", cpu);
 	secondary_data.task = NULL;
-	secondary_data.stack = NULL;
-	__flush_dcache_area(&secondary_data, sizeof(secondary_data));
 	status = READ_ONCE(secondary_data.status);
-	if (ret && status) {
+	if (status == CPU_MMU_OFF)
+		status = READ_ONCE(__early_cpu_boot_status);
 
-		if (status == CPU_MMU_OFF)
-			status = READ_ONCE(__early_cpu_boot_status);
-
-		switch (status & CPU_BOOT_STATUS_MASK) {
-		default:
-			pr_err("CPU%u: failed in unknown state : 0x%lx\n",
-					cpu, status);
-			cpus_stuck_in_kernel++;
-			break;
-		case CPU_KILL_ME:
-			if (!op_cpu_kill(cpu)) {
-				pr_crit("CPU%u: died during early boot\n", cpu);
-				break;
-			}
-			pr_crit("CPU%u: may not have shut down cleanly\n", cpu);
-			/* Fall through */
-		case CPU_STUCK_IN_KERNEL:
-			pr_crit("CPU%u: is stuck in kernel\n", cpu);
-			if (status & CPU_STUCK_REASON_52_BIT_VA)
-				pr_crit("CPU%u: does not support 52-bit VAs\n", cpu);
-			if (status & CPU_STUCK_REASON_NO_GRAN)
-				pr_crit("CPU%u: does not support %luK granule \n", cpu, PAGE_SIZE / SZ_1K);
-			cpus_stuck_in_kernel++;
+	switch (status & CPU_BOOT_STATUS_MASK) {
+	default:
+		pr_err("CPU%u: failed in unknown state : 0x%lx\n",
+		       cpu, status);
+		cpus_stuck_in_kernel++;
+		break;
+	case CPU_KILL_ME:
+		if (!op_cpu_kill(cpu)) {
+			pr_crit("CPU%u: died during early boot\n", cpu);
 			break;
-		case CPU_PANIC_KERNEL:
-			panic("CPU%u detected unsupported configuration\n", cpu);
 		}
+		pr_crit("CPU%u: may not have shut down cleanly\n", cpu);
+		fallthrough;
+	case CPU_STUCK_IN_KERNEL:
+		pr_crit("CPU%u: is stuck in kernel\n", cpu);
+		if (status & CPU_STUCK_REASON_52_BIT_VA)
+			pr_crit("CPU%u: does not support 52-bit VAs\n", cpu);
+		if (status & CPU_STUCK_REASON_NO_GRAN) {
+			pr_crit("CPU%u: does not support %luK granule\n",
+				cpu, PAGE_SIZE / SZ_1K);
+		}
+		cpus_stuck_in_kernel++;
+		break;
+	case CPU_PANIC_KERNEL:
+		panic("CPU%u detected unsupported configuration\n", cpu);
 	}
 
-	return ret;
+	return -EIO;
 }
 
 static void init_gic_priority_masking(void)
@@ -184,6 +191,7 @@ static void init_gic_priority_masking(void)
 	cpuflags = read_sysreg(daif);
 
 	WARN_ON(!(cpuflags & PSR_I_BIT));
+	WARN_ON(!(cpuflags & PSR_F_BIT));
 
 	gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
 }
@@ -196,10 +204,8 @@ asmlinkage notrace void secondary_start_kernel(void)
 {
 	u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
 	struct mm_struct *mm = &init_mm;
-	unsigned int cpu;
-
-	cpu = task_cpu(current);
-	set_my_cpu_offset(per_cpu_offset(cpu));
+	const struct cpu_operations *ops;
+	unsigned int cpu = smp_processor_id();
 
 	/*
 	 * All kernel threads share the same mm context; grab a
@@ -217,7 +223,7 @@ asmlinkage notrace void secondary_start_kernel(void)
 	if (system_uses_irq_prio_masking())
 		init_gic_priority_masking();
 
-	preempt_disable();
+	rcutree_report_cpu_starting(cpu);
 	trace_hardirqs_off();
 
 	/*
@@ -227,20 +233,23 @@ asmlinkage notrace void secondary_start_kernel(void)
 	 */
 	check_local_cpu_capabilities();
 
-	if (cpu_ops[cpu]->cpu_postboot)
-		cpu_ops[cpu]->cpu_postboot();
+	ops = get_cpu_ops(cpu);
+	if (ops->cpu_postboot)
+		ops->cpu_postboot();
 
 	/*
 	 * Log the CPU info before it is marked online and might get read.
 	 */
 	cpuinfo_store_cpu();
+	store_cpu_topology(cpu);
 
 	/*
 	 * Enable GIC and timers.
 	 */
 	notify_cpu_starting(cpu);
 
-	store_cpu_topology(cpu);
+	ipi_setup(cpu);
+
 	numa_add_cpu(cpu);
 
 	/*
@@ -266,19 +275,21 @@ asmlinkage notrace void secondary_start_kernel(void)
 #ifdef CONFIG_HOTPLUG_CPU
 static int op_cpu_disable(unsigned int cpu)
 {
+	const struct cpu_operations *ops = get_cpu_ops(cpu);
+
 	/*
 	 * If we don't have a cpu_die method, abort before we reach the point
 	 * of no return. CPU0 may not have an cpu_ops, so test for it.
 	 */
-	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_die)
+	if (!ops || !ops->cpu_die)
 		return -EOPNOTSUPP;
 
 	/*
 	 * We may need to abort a hot unplug for some other mechanism-specific
 	 * reason.
 	 */
-	if (cpu_ops[cpu]->cpu_disable)
-		return cpu_ops[cpu]->cpu_disable(cpu);
+	if (ops->cpu_disable)
+		return ops->cpu_disable(cpu);
 
 	return 0;
 }
@@ -303,6 +314,7 @@ int __cpu_disable(void)
 	 * and we must not schedule until we're ready to give up the cpu.
 	 */
 	set_cpu_online(cpu, false);
+	ipi_teardown(cpu);
 
 	/*
 	 * OK - migrate IRQs away from this CPU
@@ -314,30 +326,28 @@ int __cpu_disable(void)
 
 static int op_cpu_kill(unsigned int cpu)
 {
+	const struct cpu_operations *ops = get_cpu_ops(cpu);
+
 	/*
 	 * If we have no means of synchronising with the dying CPU, then assume
 	 * that it is really dead. We can only wait for an arbitrary length of
 	 * time and hope that it's dead, so let's skip the wait and just hope.
 	 */
-	if (!cpu_ops[cpu]->cpu_kill)
+	if (!ops->cpu_kill)
 		return 0;
 
-	return cpu_ops[cpu]->cpu_kill(cpu);
+	return ops->cpu_kill(cpu);
 }
 
 /*
- * called on the thread which is asking for a CPU to be shutdown -
- * waits until shutdown has completed, or it is timed out.
+ * Called on the thread which is asking for a CPU to be shutdown after the
+ * shutdown completed.
  */
-void __cpu_die(unsigned int cpu)
+void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu)
 {
 	int err;
 
-	if (!cpu_wait_death(cpu, 5)) {
-		pr_crit("CPU%u: cpu didn't die\n", cpu);
-		return;
-	}
-	pr_notice("CPU%u: shutdown\n", cpu);
+	pr_debug("CPU%u: shutdown\n", cpu);
 
 	/*
 	 * Now that the dying CPU is beyond the point of no return w.r.t.
@@ -354,33 +364,44 @@ void __cpu_die(unsigned int cpu)
  * Called from the idle thread for the CPU which has been shutdown.
  *
  */
-void cpu_die(void)
+void __noreturn cpu_die(void)
 {
 	unsigned int cpu = smp_processor_id();
+	const struct cpu_operations *ops = get_cpu_ops(cpu);
 
 	idle_task_exit();
 
 	local_daif_mask();
 
-	/* Tell __cpu_die() that this CPU is now safe to dispose of */
-	(void)cpu_report_death();
+	/* Tell cpuhp_bp_sync_dead() that this CPU is now safe to dispose of */
+	cpuhp_ap_report_dead();
 
 	/*
 	 * Actually shutdown the CPU. This must never fail. The specific hotplug
 	 * mechanism must perform all required cache maintenance to ensure that
 	 * no dirty lines are lost in the process of shutting down the CPU.
 	 */
-	cpu_ops[cpu]->cpu_die(cpu);
+	ops->cpu_die(cpu);
 
 	BUG();
 }
 #endif
 
+static void __cpu_try_die(int cpu)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	const struct cpu_operations *ops = get_cpu_ops(cpu);
+
+	if (ops && ops->cpu_die)
+		ops->cpu_die(cpu);
+#endif
+}
+
 /*
  * Kill the calling secondary CPU, early in bringup before it is turned
  * online.
  */
-void cpu_die_early(void)
+void __noreturn cpu_die_early(void)
 {
 	int cpu = smp_processor_id();
 
@@ -388,13 +409,13 @@ void cpu_die_early(void)
 
 	/* Mark this CPU absent */
 	set_cpu_present(cpu, 0);
+	rcutree_report_cpu_dead();
+
+	if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
+		update_cpu_boot_status(CPU_KILL_ME);
+		__cpu_try_die(cpu);
+	}
 
-#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();
@@ -409,61 +430,38 @@ static void __init hyp_mode_check(void)
 			   "CPU: CPUs started in inconsistent modes");
 	else
 		pr_info("CPU: All CPU(s) started at EL1\n");
-	if (IS_ENABLED(CONFIG_KVM_ARM_HOST))
+	if (IS_ENABLED(CONFIG_KVM) && !is_kernel_in_hyp_mode()) {
 		kvm_compute_layout();
+		kvm_apply_hyp_relocations();
+	}
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
 {
 	pr_info("SMP: Total of %d processors activated.\n", num_online_cpus());
-	setup_cpu_features();
 	hyp_mode_check();
-	apply_alternatives_all();
+	setup_system_features();
+	setup_user_features();
 	mark_linear_text_alias_ro();
 }
 
 void __init smp_prepare_boot_cpu(void)
 {
-	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
-	cpuinfo_store_boot_cpu();
-
 	/*
-	 * We now know enough about the boot CPU to apply the
-	 * alternatives that cannot wait until interrupt handling
-	 * and/or scheduling is enabled.
+	 * The runtime per-cpu areas have been allocated by
+	 * setup_per_cpu_areas(), and CPU0's boot time per-cpu area will be
+	 * freed shortly, so we must move over to the runtime per-cpu area.
 	 */
-	apply_boot_alternatives();
+	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
+
+	cpuinfo_store_boot_cpu();
+	setup_boot_cpu_features();
 
 	/* Conditionally switch to GIC PMR for interrupt masking */
 	if (system_uses_irq_prio_masking())
 		init_gic_priority_masking();
-}
-
-static u64 __init of_get_cpu_mpidr(struct device_node *dn)
-{
-	const __be32 *cell;
-	u64 hwid;
-
-	/*
-	 * A cpu node with missing "reg" property is
-	 * considered invalid to build a cpu_logical_map
-	 * entry.
-	 */
-	cell = of_get_property(dn, "reg", NULL);
-	if (!cell) {
-		pr_err("%pOF: missing reg property\n", dn);
-		return INVALID_HWID;
-	}
 
-	hwid = of_read_number(cell, of_n_addr_cells(dn));
-	/*
-	 * Non affinity bits must be set to 0 in the DT
-	 */
-	if (hwid & ~MPIDR_HWID_BITMASK) {
-		pr_err("%pOF: invalid reg property\n", dn);
-		return INVALID_HWID;
-	}
-	return hwid;
+	kasan_init_hw_tags();
 }
 
 /*
@@ -488,10 +486,13 @@ static bool __init is_mpidr_duplicate(unsigned int cpu, u64 hwid)
  */
 static int __init smp_cpu_setup(int cpu)
 {
-	if (cpu_read_ops(cpu))
+	const struct cpu_operations *ops;
+
+	if (init_cpu_ops(cpu))
 		return -ENODEV;
 
-	if (cpu_ops[cpu]->cpu_init(cpu))
+	ops = get_cpu_ops(cpu);
+	if (ops->cpu_init(cpu))
 		return -ENODEV;
 
 	set_cpu_possible(cpu, true);
@@ -509,6 +510,7 @@ struct acpi_madt_generic_interrupt *acpi_cpu_get_madt_gicc(int cpu)
 {
 	return &cpu_madt_gicc[cpu];
 }
+EXPORT_SYMBOL_GPL(acpi_cpu_get_madt_gicc);
 
 /*
  * acpi_map_gic_cpu_interface - parse processor MADT entry
@@ -521,7 +523,7 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 {
 	u64 hwid = processor->arm_mpidr;
 
-	if (!(processor->flags & ACPI_MADT_ENABLED)) {
+	if (!acpi_gicc_is_usable(processor)) {
 		pr_debug("skipping disabled CPU entry with 0x%llx MPIDR\n", hwid);
 		return;
 	}
@@ -552,7 +554,7 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 		return;
 
 	/* map the logical cpu id to cpu MPIDR */
-	cpu_logical_map(cpu_count) = hwid;
+	set_cpu_logical_map(cpu_count, hwid);
 
 	cpu_madt_gicc[cpu_count] = *processor;
 
@@ -626,9 +628,9 @@ static void __init of_parse_and_init_cpus(void)
 	struct device_node *dn;
 
 	for_each_of_cpu_node(dn) {
-		u64 hwid = of_get_cpu_mpidr(dn);
+		u64 hwid = of_get_cpu_hwid(dn, 0);
 
-		if (hwid == INVALID_HWID)
+		if (hwid & ~MPIDR_HWID_BITMASK)
 			goto next;
 
 		if (is_mpidr_duplicate(cpu_count, hwid)) {
@@ -666,7 +668,7 @@ static void __init of_parse_and_init_cpus(void)
 			goto next;
 
 		pr_debug("cpu logical map 0x%llx\n", hwid);
-		cpu_logical_map(cpu_count) = hwid;
+		set_cpu_logical_map(cpu_count, hwid);
 
 		early_map_cpu_to_node(cpu_count, of_node_to_nid(dn));
 next:
@@ -707,13 +709,14 @@ void __init smp_init_cpus(void)
 	for (i = 1; i < nr_cpu_ids; i++) {
 		if (cpu_logical_map(i) != INVALID_HWID) {
 			if (smp_cpu_setup(i))
-				cpu_logical_map(i) = INVALID_HWID;
+				set_cpu_logical_map(i, INVALID_HWID);
 		}
 	}
 }
 
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
+	const struct cpu_operations *ops;
 	int err;
 	unsigned int cpu;
 	unsigned int this_cpu;
@@ -744,10 +747,11 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 		if (cpu == smp_processor_id())
 			continue;
 
-		if (!cpu_ops[cpu])
+		ops = get_cpu_ops(cpu);
+		if (!ops)
 			continue;
 
-		err = cpu_ops[cpu]->cpu_prepare(cpu);
+		err = ops->cpu_prepare(cpu);
 		if (err)
 			continue;
 
@@ -756,31 +760,20 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	}
 }
 
-void (*__smp_cross_call)(const struct cpumask *, unsigned int);
-
-void __init set_smp_cross_call(void (*fn)(const struct cpumask *, unsigned int))
-{
-	__smp_cross_call = fn;
-}
-
 static const char *ipi_types[NR_IPI] __tracepoint_string = {
-#define S(x,s)	[x] = s
-	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"),
+	[IPI_RESCHEDULE]	= "Rescheduling interrupts",
+	[IPI_CALL_FUNC]		= "Function call interrupts",
+	[IPI_CPU_STOP]		= "CPU stop interrupts",
+	[IPI_CPU_CRASH_STOP]	= "CPU stop (for crash dump) interrupts",
+	[IPI_TIMER]		= "Timer broadcast interrupts",
+	[IPI_IRQ_WORK]		= "IRQ work interrupts",
 };
 
-static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
-{
-	trace_ipi_raise(target, ipi_types[ipinr]);
-	__smp_cross_call(target, ipinr);
-}
+static void smp_cross_call(const struct cpumask *target, unsigned int ipinr);
+
+unsigned long irq_err_count;
 
-void show_ipi_list(struct seq_file *p, int prec)
+int arch_show_interrupts(struct seq_file *p, int prec)
 {
 	unsigned int cpu, i;
 
@@ -788,21 +781,12 @@ void show_ipi_list(struct seq_file *p, int prec)
 		seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
 			   prec >= 4 ? " " : "");
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10u ",
-				   __get_irq_stat(cpu, ipi_irqs[i]));
+			seq_printf(p, "%10u ", irq_desc_kstat_cpu(ipi_desc[i], cpu));
 		seq_printf(p, "      %s\n", ipi_types[i]);
 	}
-}
-
-u64 smp_irq_stat_cpu(unsigned int cpu)
-{
-	u64 sum = 0;
-	int i;
 
-	for (i = 0; i < NR_IPI; i++)
-		sum += __get_irq_stat(cpu, ipi_irqs[i]);
-
-	return sum;
+	seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count);
+	return 0;
 }
 
 void arch_send_call_function_ipi_mask(const struct cpumask *mask)
@@ -815,22 +799,14 @@ void arch_send_call_function_single_ipi(int cpu)
 	smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC);
 }
 
-#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
-void arch_send_wakeup_ipi_mask(const struct cpumask *mask)
-{
-	smp_cross_call(mask, IPI_WAKEUP);
-}
-#endif
-
 #ifdef CONFIG_IRQ_WORK
 void arch_irq_work_raise(void)
 {
-	if (__smp_cross_call)
-		smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
+	smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
 }
 #endif
 
-static void local_cpu_stop(void)
+static void __noreturn local_cpu_stop(void)
 {
 	set_cpu_online(smp_processor_id(), false);
 
@@ -844,7 +820,7 @@ static void local_cpu_stop(void)
  * that cpu_online_mask gets correctly updated and smp_send_stop() can skip
  * CPUs that have already stopped themselves.
  */
-void panic_smp_self_stop(void)
+void __noreturn panic_smp_self_stop(void)
 {
 	local_cpu_stop();
 }
@@ -853,7 +829,7 @@ void panic_smp_self_stop(void)
 static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0);
 #endif
 
-static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
+static void __noreturn ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
 {
 #ifdef CONFIG_KEXEC_CORE
 	crash_save_cpu(regs, cpu);
@@ -863,28 +839,57 @@ static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
 	local_irq_disable();
 	sdei_mask_local_cpu();
 
-#ifdef CONFIG_HOTPLUG_CPU
-	if (cpu_ops[cpu]->cpu_die)
-		cpu_ops[cpu]->cpu_die(cpu);
-#endif
+	if (IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		__cpu_try_die(cpu);
 
 	/* just in case */
 	cpu_park_loop();
+#else
+	BUG();
 #endif
 }
 
+static void arm64_backtrace_ipi(cpumask_t *mask)
+{
+	__ipi_send_mask(ipi_desc[IPI_CPU_BACKTRACE], mask);
+}
+
+void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu)
+{
+	/*
+	 * NOTE: though nmi_trigger_cpumask_backtrace() has "nmi_" in the name,
+	 * nothing about it truly needs to be implemented using an NMI, it's
+	 * just that it's _allowed_ to work with NMIs. If ipi_should_be_nmi()
+	 * returned false our backtrace attempt will just use a regular IPI.
+	 */
+	nmi_trigger_cpumask_backtrace(mask, exclude_cpu, arm64_backtrace_ipi);
+}
+
+#ifdef CONFIG_KGDB
+void kgdb_roundup_cpus(void)
+{
+	int this_cpu = raw_smp_processor_id();
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		/* No need to roundup ourselves */
+		if (cpu == this_cpu)
+			continue;
+
+		__ipi_send_single(ipi_desc[IPI_KGDB_ROUNDUP], cpu);
+	}
+}
+#endif
+
 /*
  * Main handler for inter-processor interrupts
  */
-void handle_IPI(int ipinr, struct pt_regs *regs)
+static void do_handle_IPI(int ipinr)
 {
 	unsigned int cpu = smp_processor_id();
-	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	if ((unsigned)ipinr < NR_IPI) {
-		trace_ipi_entry_rcuidle(ipi_types[ipinr]);
-		__inc_irq_stat(cpu, ipi_irqs[ipinr]);
-	}
+	if ((unsigned)ipinr < NR_IPI)
+		trace_ipi_entry(ipi_types[ipinr]);
 
 	switch (ipinr) {
 	case IPI_RESCHEDULE:
@@ -892,21 +897,16 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 		break;
 
 	case IPI_CALL_FUNC:
-		irq_enter();
 		generic_smp_call_function_interrupt();
-		irq_exit();
 		break;
 
 	case IPI_CPU_STOP:
-		irq_enter();
 		local_cpu_stop();
-		irq_exit();
 		break;
 
 	case IPI_CPU_CRASH_STOP:
 		if (IS_ENABLED(CONFIG_KEXEC_CORE)) {
-			irq_enter();
-			ipi_cpu_crash_stop(cpu, regs);
+			ipi_cpu_crash_stop(cpu, get_irq_regs());
 
 			unreachable();
 		}
@@ -914,27 +914,27 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 	case IPI_TIMER:
-		irq_enter();
 		tick_receive_broadcast();
-		irq_exit();
 		break;
 #endif
 
 #ifdef CONFIG_IRQ_WORK
 	case IPI_IRQ_WORK:
-		irq_enter();
 		irq_work_run();
-		irq_exit();
 		break;
 #endif
 
-#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
-	case IPI_WAKEUP:
-		WARN_ONCE(!acpi_parking_protocol_valid(cpu),
-			  "CPU%u: Wake-up IPI outside the ACPI parking protocol\n",
-			  cpu);
+	case IPI_CPU_BACKTRACE:
+		/*
+		 * NOTE: in some cases this _won't_ be NMI context. See the
+		 * comment in arch_trigger_cpumask_backtrace().
+		 */
+		nmi_cpu_backtrace(get_irq_regs());
+		break;
+
+	case IPI_KGDB_ROUNDUP:
+		kgdb_nmicallback(cpu, get_irq_regs());
 		break;
-#endif
 
 	default:
 		pr_crit("CPU%u: Unknown IPI message 0x%x\n", cpu, ipinr);
@@ -942,15 +942,121 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 	}
 
 	if ((unsigned)ipinr < NR_IPI)
-		trace_ipi_exit_rcuidle(ipi_types[ipinr]);
-	set_irq_regs(old_regs);
+		trace_ipi_exit(ipi_types[ipinr]);
+}
+
+static irqreturn_t ipi_handler(int irq, void *data)
+{
+	do_handle_IPI(irq - ipi_irq_base);
+	return IRQ_HANDLED;
+}
+
+static void smp_cross_call(const struct cpumask *target, unsigned int ipinr)
+{
+	trace_ipi_raise(target, ipi_types[ipinr]);
+	__ipi_send_mask(ipi_desc[ipinr], target);
+}
+
+static bool ipi_should_be_nmi(enum ipi_msg_type ipi)
+{
+	if (!system_uses_irq_prio_masking())
+		return false;
+
+	switch (ipi) {
+	case IPI_CPU_STOP:
+	case IPI_CPU_CRASH_STOP:
+	case IPI_CPU_BACKTRACE:
+	case IPI_KGDB_ROUNDUP:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static void ipi_setup(int cpu)
+{
+	int i;
+
+	if (WARN_ON_ONCE(!ipi_irq_base))
+		return;
+
+	for (i = 0; i < nr_ipi; i++) {
+		if (ipi_should_be_nmi(i)) {
+			prepare_percpu_nmi(ipi_irq_base + i);
+			enable_percpu_nmi(ipi_irq_base + i, 0);
+		} else {
+			enable_percpu_irq(ipi_irq_base + i, 0);
+		}
+	}
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void ipi_teardown(int cpu)
+{
+	int i;
+
+	if (WARN_ON_ONCE(!ipi_irq_base))
+		return;
+
+	for (i = 0; i < nr_ipi; i++) {
+		if (ipi_should_be_nmi(i)) {
+			disable_percpu_nmi(ipi_irq_base + i);
+			teardown_percpu_nmi(ipi_irq_base + i);
+		} else {
+			disable_percpu_irq(ipi_irq_base + i);
+		}
+	}
+}
+#endif
+
+void __init set_smp_ipi_range(int ipi_base, int n)
+{
+	int i;
+
+	WARN_ON(n < MAX_IPI);
+	nr_ipi = min(n, MAX_IPI);
+
+	for (i = 0; i < nr_ipi; i++) {
+		int err;
+
+		if (ipi_should_be_nmi(i)) {
+			err = request_percpu_nmi(ipi_base + i, ipi_handler,
+						 "IPI", &cpu_number);
+			WARN(err, "Could not request IPI %d as NMI, err=%d\n",
+			     i, err);
+		} else {
+			err = request_percpu_irq(ipi_base + i, ipi_handler,
+						 "IPI", &cpu_number);
+			WARN(err, "Could not request IPI %d as IRQ, err=%d\n",
+			     i, err);
+		}
+
+		ipi_desc[i] = irq_to_desc(ipi_base + i);
+		irq_set_status_flags(ipi_base + i, IRQ_HIDDEN);
+	}
+
+	ipi_irq_base = ipi_base;
+
+	/* Setup the boot CPU immediately */
+	ipi_setup(smp_processor_id());
 }
 
-void smp_send_reschedule(int cpu)
+void arch_smp_send_reschedule(int cpu)
 {
 	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
+#ifdef CONFIG_ARM64_ACPI_PARKING_PROTOCOL
+void arch_send_wakeup_ipi(unsigned int cpu)
+{
+	/*
+	 * We use a scheduler IPI to wake the CPU as this avoids the need for a
+	 * dedicated IPI and we can safely handle spurious scheduler IPIs.
+	 */
+	smp_send_reschedule(cpu);
+}
+#endif
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 void tick_broadcast(const struct cpumask *mask)
 {
@@ -958,11 +1064,22 @@ void tick_broadcast(const struct cpumask *mask)
 }
 #endif
 
+/*
+ * The number of CPUs online, not counting this CPU (which may not be
+ * fully online and so not counted in num_online_cpus()).
+ */
+static inline unsigned int num_other_online_cpus(void)
+{
+	unsigned int this_cpu_online = cpu_online(smp_processor_id());
+
+	return num_online_cpus() - this_cpu_online;
+}
+
 void smp_send_stop(void)
 {
 	unsigned long timeout;
 
-	if (num_online_cpus() > 1) {
+	if (num_other_online_cpus()) {
 		cpumask_t mask;
 
 		cpumask_copy(&mask, cpu_online_mask);
@@ -975,10 +1092,10 @@ void smp_send_stop(void)
 
 	/* Wait up to one second for other CPUs to stop */
 	timeout = USEC_PER_SEC;
-	while (num_online_cpus() > 1 && timeout--)
+	while (num_other_online_cpus() && timeout--)
 		udelay(1);
 
-	if (num_online_cpus() > 1)
+	if (num_other_online_cpus())
 		pr_warn("SMP: failed to stop secondary CPUs %*pbl\n",
 			cpumask_pr_args(cpu_online_mask));
 
@@ -1001,15 +1118,17 @@ void crash_smp_send_stop(void)
 
 	cpus_stopped = 1;
 
-	if (num_online_cpus() == 1) {
-		sdei_mask_local_cpu();
-		return;
-	}
+	/*
+	 * If this cpu is the only one alive at this point in time, online or
+	 * not, there are no stop messages to be sent around, so just back out.
+	 */
+	if (num_other_online_cpus() == 0)
+		goto skip_ipi;
 
 	cpumask_copy(&mask, cpu_online_mask);
 	cpumask_clear_cpu(smp_processor_id(), &mask);
 
-	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+	atomic_set(&waiting_for_crash_ipi, num_other_online_cpus());
 
 	pr_crit("SMP: stopping secondary CPUs\n");
 	smp_cross_call(&mask, IPI_CPU_CRASH_STOP);
@@ -1023,7 +1142,9 @@ void crash_smp_send_stop(void)
 		pr_warn("SMP: failed to stop secondary CPUs %*pbl\n",
 			cpumask_pr_args(&mask));
 
+skip_ipi:
 	sdei_mask_local_cpu();
+	sdei_handler_abort();
 }
 
 bool smp_crash_stop_failed(void)
@@ -1032,20 +1153,13 @@ bool smp_crash_stop_failed(void)
 }
 #endif
 
-/*
- * not supported here
- */
-int setup_profiling_timer(unsigned int multiplier)
-{
-	return -EINVAL;
-}
-
 static bool have_cpu_die(void)
 {
 #ifdef CONFIG_HOTPLUG_CPU
 	int any_cpu = raw_smp_processor_id();
+	const struct cpu_operations *ops = get_cpu_ops(any_cpu);
 
-	if (cpu_ops[any_cpu] && cpu_ops[any_cpu]->cpu_die)
+	if (ops && ops->cpu_die)
 		return true;
 #endif
 	return false;
@@ -1055,5 +1169,6 @@ bool cpus_are_stuck_in_kernel(void)
 {
 	bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die());
 
-	return !!cpus_stuck_in_kernel || smp_spin_tables;
+	return !!cpus_stuck_in_kernel || smp_spin_tables ||
+		is_protected_kvm_enabled();
 }