1 files changed, 125 insertions, 160 deletions

diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index cdaa347dfcad..b014e6d229f9 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *	Intel SMP support routines.
  *
@@ -6,9 +7,6 @@
  *      (c) 2002,2003 Andi Kleen, SuSE Labs.
  *
  *	i386 and x86_64 integration by Glauber Costa <gcosta@redhat.com>
- *
- *	This code is released under the GNU General Public License version 2 or
- *	later.
  */
 
 #include <linux/init.h>
@@ -23,14 +21,21 @@
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
 #include <linux/gfp.h>
+#include <linux/kexec.h>
 
 #include <asm/mtrr.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
 #include <asm/proto.h>
 #include <asm/apic.h>
+#include <asm/cpu.h>
+#include <asm/idtentry.h>
 #include <asm/nmi.h>
+#include <asm/mce.h>
 #include <asm/trace/irq_vectors.h>
+#include <asm/kexec.h>
+#include <asm/reboot.h>
+
 /*
  *	Some notes on x86 processor bugs affecting SMP operation:
  *
@@ -64,7 +69,7 @@
  *	5AP.	symmetric IO mode (normal Linux operation) not affected.
  *		'noapic' mode has vector 0xf filled out properly.
  *	6AP.	'noapic' mode might be affected - fixed in later steppings
- *	7AP.	We do not assume writes to the LVT deassering IRQs
+ *	7AP.	We do not assume writes to the LVT deasserting IRQs
  *	8AP.	We do not enable low power mode (deep sleep) during MP bootup
  *	9AP.	We do not use mixed mode
  *
@@ -113,52 +118,13 @@
 static atomic_t stopping_cpu = ATOMIC_INIT(-1);
 static bool smp_no_nmi_ipi = false;
 
-/*
- * this function sends a 'reschedule' IPI to another CPU.
- * it goes straight through and wastes no time serializing
- * anything. Worst case is that we lose a reschedule ...
- */
-static void native_smp_send_reschedule(int cpu)
-{
-	if (unlikely(cpu_is_offline(cpu))) {
-		WARN_ON(1);
-		return;
-	}
-	apic->send_IPI_mask(cpumask_of(cpu), RESCHEDULE_VECTOR);
-}
-
-void native_send_call_func_single_ipi(int cpu)
-{
-	apic->send_IPI_mask(cpumask_of(cpu), CALL_FUNCTION_SINGLE_VECTOR);
-}
-
-void native_send_call_func_ipi(const struct cpumask *mask)
-{
-	cpumask_var_t allbutself;
-
-	if (!alloc_cpumask_var(&allbutself, GFP_ATOMIC)) {
-		apic->send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
-		return;
-	}
-
-	cpumask_copy(allbutself, cpu_online_mask);
-	cpumask_clear_cpu(smp_processor_id(), allbutself);
-
-	if (cpumask_equal(mask, allbutself) &&
-	    cpumask_equal(cpu_online_mask, cpu_callout_mask))
-		apic->send_IPI_allbutself(CALL_FUNCTION_VECTOR);
-	else
-		apic->send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
-
-	free_cpumask_var(allbutself);
-}
-
 static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
 {
 	/* We are registered on stopping cpu too, avoid spurious NMI */
 	if (raw_smp_processor_id() == atomic_read(&stopping_cpu))
 		return NMI_HANDLED;
 
+	cpu_emergency_disable_virtualization();
 	stop_this_cpu(NULL);
 
 	return NMI_HANDLED;
@@ -167,170 +133,143 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
 /*
  * this function calls the 'stop' function on all other CPUs in the system.
  */
-
-asmlinkage void smp_reboot_interrupt(void)
+DEFINE_IDTENTRY_SYSVEC(sysvec_reboot)
 {
-	ack_APIC_irq();
-	irq_enter();
+	apic_eoi();
+	cpu_emergency_disable_virtualization();
 	stop_this_cpu(NULL);
-	irq_exit();
+}
+
+static int register_stop_handler(void)
+{
+	return register_nmi_handler(NMI_LOCAL, smp_stop_nmi_callback,
+				    NMI_FLAG_FIRST, "smp_stop");
 }
 
 static void native_stop_other_cpus(int wait)
 {
-	unsigned long flags;
-	unsigned long timeout;
+	unsigned int old_cpu, this_cpu;
+	unsigned long flags, timeout;
 
 	if (reboot_force)
 		return;
 
-	/*
-	 * Use an own vector here because smp_call_function
-	 * does lots of things not suitable in a panic situation.
-	 */
+	/* Only proceed if this is the first CPU to reach this code */
+	old_cpu = -1;
+	this_cpu = smp_processor_id();
+	if (!atomic_try_cmpxchg(&stopping_cpu, &old_cpu, this_cpu))
+		return;
+
+	/* For kexec, ensure that offline CPUs are out of MWAIT and in HLT */
+	if (kexec_in_progress)
+		smp_kick_mwait_play_dead();
 
 	/*
-	 * We start by using the REBOOT_VECTOR irq.
-	 * The irq is treated as a sync point to allow critical
-	 * regions of code on other cpus to release their spin locks
-	 * and re-enable irqs.  Jumping straight to an NMI might
-	 * accidentally cause deadlocks with further shutdown/panic
-	 * code.  By syncing, we give the cpus up to one second to
-	 * finish their work before we force them off with the NMI.
+	 * 1) Send an IPI on the reboot vector to all other CPUs.
+	 *
+	 *    The other CPUs should react on it after leaving critical
+	 *    sections and re-enabling interrupts. They might still hold
+	 *    locks, but there is nothing which can be done about that.
+	 *
+	 * 2) Wait for all other CPUs to report that they reached the
+	 *    HLT loop in stop_this_cpu()
+	 *
+	 * 3) If #2 timed out send an NMI to the CPUs which did not
+	 *    yet report
+	 *
+	 * 4) Wait for all other CPUs to report that they reached the
+	 *    HLT loop in stop_this_cpu()
+	 *
+	 * #3 can obviously race against a CPU reaching the HLT loop late.
+	 * That CPU will have reported already and the "have all CPUs
+	 * reached HLT" condition will be true despite the fact that the
+	 * other CPU is still handling the NMI. Again, there is no
+	 * protection against that as "disabled" APICs still respond to
+	 * NMIs.
 	 */
-	if (num_online_cpus() > 1) {
-		/* did someone beat us here? */
-		if (atomic_cmpxchg(&stopping_cpu, -1, safe_smp_processor_id()) != -1)
-			return;
-
-		/* sync above data before sending IRQ */
-		wmb();
+	cpumask_copy(&cpus_stop_mask, cpu_online_mask);
+	cpumask_clear_cpu(this_cpu, &cpus_stop_mask);
 
-		apic->send_IPI_allbutself(REBOOT_VECTOR);
+	if (!cpumask_empty(&cpus_stop_mask)) {
+		apic_send_IPI_allbutself(REBOOT_VECTOR);
 
 		/*
-		 * Don't wait longer than a second if the caller
-		 * didn't ask us to wait.
+		 * Don't wait longer than a second for IPI completion. The
+		 * wait request is not checked here because that would
+		 * prevent an NMI shutdown attempt in case that not all
+		 * CPUs reach shutdown state.
 		 */
 		timeout = USEC_PER_SEC;
-		while (num_online_cpus() > 1 && (wait || timeout--))
+		while (!cpumask_empty(&cpus_stop_mask) && timeout--)
 			udelay(1);
 	}
-	
-	/* if the REBOOT_VECTOR didn't work, try with the NMI */
-	if ((num_online_cpus() > 1) && (!smp_no_nmi_ipi))  {
-		if (register_nmi_handler(NMI_LOCAL, smp_stop_nmi_callback,
-					 NMI_FLAG_FIRST, "smp_stop"))
-			/* Note: we ignore failures here */
-			/* Hope the REBOOT_IRQ is good enough */
-			goto finish;
-
-		/* sync above data before sending IRQ */
-		wmb();
 
-		pr_emerg("Shutting down cpus with NMI\n");
+	/* if the REBOOT_VECTOR didn't work, try with the NMI */
+	if (!cpumask_empty(&cpus_stop_mask)) {
+		/*
+		 * If NMI IPI is enabled, try to register the stop handler
+		 * and send the IPI. In any case try to wait for the other
+		 * CPUs to stop.
+		 */
+		if (!smp_no_nmi_ipi && !register_stop_handler()) {
+			unsigned int cpu;
 
-		apic->send_IPI_allbutself(NMI_VECTOR);
+			pr_emerg("Shutting down cpus with NMI\n");
 
+			for_each_cpu(cpu, &cpus_stop_mask)
+				__apic_send_IPI(cpu, NMI_VECTOR);
+		}
 		/*
-		 * Don't wait longer than a 10 ms if the caller
-		 * didn't ask us to wait.
+		 * Don't wait longer than 10 ms if the caller didn't
+		 * request it. If wait is true, the machine hangs here if
+		 * one or more CPUs do not reach shutdown state.
 		 */
 		timeout = USEC_PER_MSEC * 10;
-		while (num_online_cpus() > 1 && (wait || timeout--))
+		while (!cpumask_empty(&cpus_stop_mask) && (wait || timeout--))
 			udelay(1);
 	}
 
-finish:
 	local_irq_save(flags);
 	disable_local_APIC();
+	mcheck_cpu_clear(this_cpu_ptr(&cpu_info));
 	local_irq_restore(flags);
-}
-
-/*
- * Reschedule call back.
- */
-static inline void __smp_reschedule_interrupt(void)
-{
-	inc_irq_stat(irq_resched_count);
-	scheduler_ipi();
-}
 
-void smp_reschedule_interrupt(struct pt_regs *regs)
-{
-	ack_APIC_irq();
-	__smp_reschedule_interrupt();
 	/*
-	 * KVM uses this interrupt to force a cpu out of guest mode
+	 * Ensure that the cpus_stop_mask cache lines are invalidated on
+	 * the other CPUs. See comment vs. SME in stop_this_cpu().
 	 */
+	cpumask_clear(&cpus_stop_mask);
 }
 
-static inline void smp_entering_irq(void)
-{
-	ack_APIC_irq();
-	irq_enter();
-}
-
-void smp_trace_reschedule_interrupt(struct pt_regs *regs)
+/*
+ * Reschedule call back. KVM uses this interrupt to force a cpu out of
+ * guest mode.
+ */
+DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_reschedule_ipi)
 {
-	/*
-	 * Need to call irq_enter() before calling the trace point.
-	 * __smp_reschedule_interrupt() calls irq_enter/exit() too (in
-	 * scheduler_ipi(). This is OK, since those functions are allowed
-	 * to nest.
-	 */
-	smp_entering_irq();
+	apic_eoi();
 	trace_reschedule_entry(RESCHEDULE_VECTOR);
-	__smp_reschedule_interrupt();
+	inc_irq_stat(irq_resched_count);
+	scheduler_ipi();
 	trace_reschedule_exit(RESCHEDULE_VECTOR);
-	exiting_irq();
-	/*
-	 * KVM uses this interrupt to force a cpu out of guest mode
-	 */
-}
-
-static inline void __smp_call_function_interrupt(void)
-{
-	generic_smp_call_function_interrupt();
-	inc_irq_stat(irq_call_count);
-}
-
-void smp_call_function_interrupt(struct pt_regs *regs)
-{
-	smp_entering_irq();
-	__smp_call_function_interrupt();
-	exiting_irq();
 }
 
-void smp_trace_call_function_interrupt(struct pt_regs *regs)
+DEFINE_IDTENTRY_SYSVEC(sysvec_call_function)
 {
-	smp_entering_irq();
+	apic_eoi();
 	trace_call_function_entry(CALL_FUNCTION_VECTOR);
-	__smp_call_function_interrupt();
-	trace_call_function_exit(CALL_FUNCTION_VECTOR);
-	exiting_irq();
-}
-
-static inline void __smp_call_function_single_interrupt(void)
-{
-	generic_smp_call_function_single_interrupt();
 	inc_irq_stat(irq_call_count);
+	generic_smp_call_function_interrupt();
+	trace_call_function_exit(CALL_FUNCTION_VECTOR);
 }
 
-void smp_call_function_single_interrupt(struct pt_regs *regs)
-{
-	smp_entering_irq();
-	__smp_call_function_single_interrupt();
-	exiting_irq();
-}
-
-void smp_trace_call_function_single_interrupt(struct pt_regs *regs)
+DEFINE_IDTENTRY_SYSVEC(sysvec_call_function_single)
 {
-	smp_entering_irq();
+	apic_eoi();
 	trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR);
-	__smp_call_function_single_interrupt();
+	inc_irq_stat(irq_call_count);
+	generic_smp_call_function_single_interrupt();
 	trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR);
-	exiting_irq();
 }
 
 static int __init nonmi_ipi_setup(char *str)
@@ -347,10 +286,12 @@ struct smp_ops smp_ops = {
 	.smp_cpus_done		= native_smp_cpus_done,
 
 	.stop_other_cpus	= native_stop_other_cpus,
+#if defined(CONFIG_CRASH_DUMP)
+	.crash_stop_other_cpus	= kdump_nmi_shootdown_cpus,
+#endif
 	.smp_send_reschedule	= native_smp_send_reschedule,
 
-	.cpu_up			= native_cpu_up,
-	.cpu_die		= native_cpu_die,
+	.kick_ap_alive		= native_kick_ap,
 	.cpu_disable		= native_cpu_disable,
 	.play_dead		= native_play_dead,
 
@@ -358,3 +299,27 @@ struct smp_ops smp_ops = {
 	.send_call_func_single_ipi = native_send_call_func_single_ipi,
 };
 EXPORT_SYMBOL_GPL(smp_ops);
+
+int arch_cpu_rescan_dead_smt_siblings(void)
+{
+	enum cpuhp_smt_control old = cpu_smt_control;
+	int ret;
+
+	/*
+	 * If SMT has been disabled and SMT siblings are in HLT, bring them back
+	 * online and offline them again so that they end up in MWAIT proper.
+	 *
+	 * Called with hotplug enabled.
+	 */
+	if (old != CPU_SMT_DISABLED && old != CPU_SMT_FORCE_DISABLED)
+		return 0;
+
+	ret = cpuhp_smt_enable();
+	if (ret)
+		return ret;
+
+	ret = cpuhp_smt_disable(old);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(arch_cpu_rescan_dead_smt_siblings);