1 files changed, 137 insertions, 70 deletions

diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 62ed361a4376..4ced34f62dab 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -32,7 +32,9 @@
 #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>
@@ -51,7 +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);
@@ -73,13 +74,19 @@ enum ipi_msg_type {
 	IPI_CPU_CRASH_STOP,
 	IPI_TIMER,
 	IPI_IRQ_WORK,
-	IPI_WAKEUP,
-	NR_IPI
+	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 __read_mostly;
-static int nr_ipi __read_mostly = NR_IPI;
-static struct irq_desc *ipi_desc[NR_IPI] __read_mostly;
+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);
 
@@ -216,7 +223,7 @@ asmlinkage notrace void secondary_start_kernel(void)
 	if (system_uses_irq_prio_masking())
 		init_gic_priority_masking();
 
-	rcu_cpu_starting(cpu);
+	rcutree_report_cpu_starting(cpu);
 	trace_hardirqs_off();
 
 	/*
@@ -333,17 +340,13 @@ static int op_cpu_kill(unsigned int 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_debug("CPU%u: shutdown\n", cpu);
 
 	/*
@@ -361,7 +364,7 @@ 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);
@@ -370,8 +373,8 @@ void cpu_die(void)
 
 	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
@@ -398,7 +401,7 @@ static void __cpu_try_die(int cpu)
  * 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();
 
@@ -406,7 +409,7 @@ void cpu_die_early(void)
 
 	/* Mark this CPU absent */
 	set_cpu_present(cpu, 0);
-	rcu_report_dead(cpu);
+	rcutree_report_cpu_dead();
 
 	if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
 		update_cpu_boot_status(CPU_KILL_ME);
@@ -436,9 +439,9 @@ static void __init hyp_mode_check(void)
 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();
 }
 
@@ -450,14 +453,9 @@ void __init smp_prepare_boot_cpu(void)
 	 * freed shortly, so we must move over to the runtime per-cpu area.
 	 */
 	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.
-	 */
-	apply_boot_alternatives();
+	cpuinfo_store_boot_cpu();
+	setup_boot_cpu_features();
 
 	/* Conditionally switch to GIC PMR for interrupt masking */
 	if (system_uses_irq_prio_masking())
@@ -525,7 +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;
 	}
@@ -769,7 +767,6 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = {
 	[IPI_CPU_CRASH_STOP]	= "CPU stop (for crash dump) interrupts",
 	[IPI_TIMER]		= "Timer broadcast interrupts",
 	[IPI_IRQ_WORK]		= "IRQ work interrupts",
-	[IPI_WAKEUP]		= "CPU wake-up interrupts",
 };
 
 static void smp_cross_call(const struct cpumask *target, unsigned int ipinr);
@@ -802,13 +799,6 @@ 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)
 {
@@ -816,7 +806,7 @@ void arch_irq_work_raise(void)
 }
 #endif
 
-static void local_cpu_stop(void)
+static void __noreturn local_cpu_stop(void)
 {
 	set_cpu_online(smp_processor_id(), false);
 
@@ -830,7 +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();
 }
@@ -839,7 +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);
@@ -854,9 +844,43 @@ static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
 
 	/* 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
  */
@@ -865,7 +889,7 @@ static void do_handle_IPI(int ipinr)
 	unsigned int cpu = smp_processor_id();
 
 	if ((unsigned)ipinr < NR_IPI)
-		trace_ipi_entry_rcuidle(ipi_types[ipinr]);
+		trace_ipi_entry(ipi_types[ipinr]);
 
 	switch (ipinr) {
 	case IPI_RESCHEDULE:
@@ -900,13 +924,17 @@ static void do_handle_IPI(int ipinr)
 		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);
@@ -914,7 +942,7 @@ static void do_handle_IPI(int ipinr)
 	}
 
 	if ((unsigned)ipinr < NR_IPI)
-		trace_ipi_exit_rcuidle(ipi_types[ipinr]);
+		trace_ipi_exit(ipi_types[ipinr]);
 }
 
 static irqreturn_t ipi_handler(int irq, void *data)
@@ -929,6 +957,22 @@ static void smp_cross_call(const struct cpumask *target, unsigned int 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;
@@ -936,8 +980,14 @@ static void ipi_setup(int cpu)
 	if (WARN_ON_ONCE(!ipi_irq_base))
 		return;
 
-	for (i = 0; i < nr_ipi; i++)
-		enable_percpu_irq(ipi_irq_base + i, 0);
+	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
@@ -948,8 +998,14 @@ static void ipi_teardown(int cpu)
 	if (WARN_ON_ONCE(!ipi_irq_base))
 		return;
 
-	for (i = 0; i < nr_ipi; i++)
-		disable_percpu_irq(ipi_irq_base + i);
+	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
 
@@ -957,15 +1013,23 @@ void __init set_smp_ipi_range(int ipi_base, int n)
 {
 	int i;
 
-	WARN_ON(n < NR_IPI);
-	nr_ipi = min(n, NR_IPI);
+	WARN_ON(n < MAX_IPI);
+	nr_ipi = min(n, MAX_IPI);
 
 	for (i = 0; i < nr_ipi; i++) {
 		int err;
 
-		err = request_percpu_irq(ipi_base + i, ipi_handler,
-					 "IPI", &cpu_number);
-		WARN_ON(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);
@@ -977,11 +1041,22 @@ void __init set_smp_ipi_range(int ipi_base, int n)
 	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)
 {
@@ -1047,10 +1122,8 @@ void crash_smp_send_stop(void)
 	 * 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) {
-		sdei_mask_local_cpu();
-		return;
-	}
+	if (num_other_online_cpus() == 0)
+		goto skip_ipi;
 
 	cpumask_copy(&mask, cpu_online_mask);
 	cpumask_clear_cpu(smp_processor_id(), &mask);
@@ -1069,7 +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)
@@ -1078,14 +1153,6 @@ 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