1 files changed, 91 insertions, 59 deletions

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 59abbdad7729..d4e48b4a438b 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -69,6 +69,7 @@ static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __align
 DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible;
 static int has_steal_clock = 0;
 
+static int has_guest_poll = 0;
 /*
  * No need for any "IO delay" on KVM
  */
@@ -190,7 +191,7 @@ void kvm_async_pf_task_wake(u32 token)
 {
 	u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
 	struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
-	struct kvm_task_sleep_node *n;
+	struct kvm_task_sleep_node *n, *dummy = NULL;
 
 	if (token == ~0) {
 		apf_task_wake_all();
@@ -202,28 +203,40 @@ again:
 	n = _find_apf_task(b, token);
 	if (!n) {
 		/*
-		 * async PF was not yet handled.
-		 * Add dummy entry for the token.
+		 * Async #PF not yet handled, add a dummy entry for the token.
+		 * Allocating the token must be down outside of the raw lock
+		 * as the allocator is preemptible on PREEMPT_RT kernels.
 		 */
-		n = kzalloc(sizeof(*n), GFP_ATOMIC);
-		if (!n) {
+		if (!dummy) {
+			raw_spin_unlock(&b->lock);
+			dummy = kzalloc(sizeof(*dummy), GFP_ATOMIC);
+
 			/*
-			 * Allocation failed! Busy wait while other cpu
-			 * handles async PF.
+			 * Continue looping on allocation failure, eventually
+			 * the async #PF will be handled and allocating a new
+			 * node will be unnecessary.
+			 */
+			if (!dummy)
+				cpu_relax();
+
+			/*
+			 * Recheck for async #PF completion before enqueueing
+			 * the dummy token to avoid duplicate list entries.
 			 */
-			raw_spin_unlock(&b->lock);
-			cpu_relax();
 			goto again;
 		}
-		n->token = token;
-		n->cpu = smp_processor_id();
-		init_swait_queue_head(&n->wq);
-		hlist_add_head(&n->link, &b->list);
+		dummy->token = token;
+		dummy->cpu = smp_processor_id();
+		init_swait_queue_head(&dummy->wq);
+		hlist_add_head(&dummy->link, &b->list);
+		dummy = NULL;
 	} else {
 		apf_task_wake_one(n);
 	}
 	raw_spin_unlock(&b->lock);
-	return;
+
+	/* A dummy token might be allocated and ultimately not used.  */
+	kfree(dummy);
 }
 EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake);
 
@@ -313,7 +326,7 @@ static void kvm_register_steal_time(void)
 		return;
 
 	wrmsrl(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED));
-	pr_info("stealtime: cpu %d, msr %llx\n", cpu,
+	pr_debug("stealtime: cpu %d, msr %llx\n", cpu,
 		(unsigned long long) slow_virt_to_phys(st));
 }
 
@@ -350,7 +363,7 @@ static void kvm_guest_cpu_init(void)
 
 		wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
 		__this_cpu_write(apf_reason.enabled, 1);
-		pr_info("setup async PF for cpu %d\n", smp_processor_id());
+		pr_debug("setup async PF for cpu %d\n", smp_processor_id());
 	}
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI)) {
@@ -376,7 +389,7 @@ static void kvm_pv_disable_apf(void)
 	wrmsrl(MSR_KVM_ASYNC_PF_EN, 0);
 	__this_cpu_write(apf_reason.enabled, 0);
 
-	pr_info("disable async PF for cpu %d\n", smp_processor_id());
+	pr_debug("disable async PF for cpu %d\n", smp_processor_id());
 }
 
 static void kvm_disable_steal_time(void)
@@ -462,19 +475,24 @@ static bool pv_tlb_flush_supported(void)
 {
 	return (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) &&
 		!kvm_para_has_hint(KVM_HINTS_REALTIME) &&
-		kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
+		kvm_para_has_feature(KVM_FEATURE_STEAL_TIME) &&
+		!boot_cpu_has(X86_FEATURE_MWAIT) &&
+		(num_possible_cpus() != 1));
 }
 
 static bool pv_ipi_supported(void)
 {
-	return kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI);
+	return (kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI) &&
+	       (num_possible_cpus() != 1));
 }
 
 static bool pv_sched_yield_supported(void)
 {
 	return (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) &&
 		!kvm_para_has_hint(KVM_HINTS_REALTIME) &&
-	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME));
+	    kvm_para_has_feature(KVM_FEATURE_STEAL_TIME) &&
+	    !boot_cpu_has(X86_FEATURE_MWAIT) &&
+	    (num_possible_cpus() != 1));
 }
 
 #define KVM_IPI_CLUSTER_SIZE	(2 * BITS_PER_LONG)
@@ -512,7 +530,7 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
 		} else if (apic_id < min && max - apic_id < KVM_IPI_CLUSTER_SIZE) {
 			ipi_bitmap <<= min - apic_id;
 			min = apic_id;
-		} else if (apic_id < min + KVM_IPI_CLUSTER_SIZE) {
+		} else if (apic_id > min && apic_id < min + KVM_IPI_CLUSTER_SIZE) {
 			max = apic_id < max ? max : apic_id;
 		} else {
 			ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
@@ -619,7 +637,7 @@ static void kvm_smp_send_call_func_ipi(const struct cpumask *mask)
 
 	/* Make sure other vCPUs get a chance to run if they need to. */
 	for_each_cpu(cpu, mask) {
-		if (vcpu_is_preempted(cpu)) {
+		if (!idle_cpu(cpu) && vcpu_is_preempted(cpu)) {
 			kvm_hypercall1(KVM_HC_SCHED_YIELD, per_cpu(x86_cpu_to_apicid, cpu));
 			break;
 		}
@@ -701,14 +719,26 @@ static int kvm_cpu_down_prepare(unsigned int cpu)
 
 static int kvm_suspend(void)
 {
+	u64 val = 0;
+
 	kvm_guest_cpu_offline(false);
 
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+	if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL))
+		rdmsrl(MSR_KVM_POLL_CONTROL, val);
+	has_guest_poll = !(val & 1);
+#endif
 	return 0;
 }
 
 static void kvm_resume(void)
 {
 	kvm_cpu_online(raw_smp_processor_id());
+
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+	if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL) && has_guest_poll)
+		wrmsrl(MSR_KVM_POLL_CONTROL, 0);
+#endif
 }
 
 static struct syscore_ops kvm_syscore_ops = {
@@ -747,6 +777,42 @@ static void kvm_crash_shutdown(struct pt_regs *regs)
 }
 #endif
 
+#if defined(CONFIG_X86_32) || !defined(CONFIG_SMP)
+bool __kvm_vcpu_is_preempted(long cpu);
+
+__visible bool __kvm_vcpu_is_preempted(long cpu)
+{
+	struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
+
+	return !!(src->preempted & KVM_VCPU_PREEMPTED);
+}
+PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
+
+#else
+
+#include <asm/asm-offsets.h>
+
+extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);
+
+/*
+ * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and
+ * restoring to/from the stack.
+ */
+asm(
+".pushsection .text;"
+".global __raw_callee_save___kvm_vcpu_is_preempted;"
+".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
+"__raw_callee_save___kvm_vcpu_is_preempted:"
+ASM_ENDBR
+"movq	__per_cpu_offset(,%rdi,8), %rax;"
+"cmpb	$0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
+"setne	%al;"
+ASM_RET
+".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;"
+".popsection");
+
+#endif
+
 static void __init kvm_guest_init(void)
 {
 	int i;
@@ -759,6 +825,9 @@ static void __init kvm_guest_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
 		has_steal_clock = 1;
 		static_call_update(pv_steal_clock, kvm_steal_clock);
+
+		pv_ops.lock.vcpu_is_preempted =
+			PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
 	}
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -1000,39 +1069,6 @@ static void kvm_wait(u8 *ptr, u8 val)
 	}
 }
 
-#ifdef CONFIG_X86_32
-__visible bool __kvm_vcpu_is_preempted(long cpu)
-{
-	struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
-
-	return !!(src->preempted & KVM_VCPU_PREEMPTED);
-}
-PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
-
-#else
-
-#include <asm/asm-offsets.h>
-
-extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);
-
-/*
- * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and
- * restoring to/from the stack.
- */
-asm(
-".pushsection .text;"
-".global __raw_callee_save___kvm_vcpu_is_preempted;"
-".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
-"__raw_callee_save___kvm_vcpu_is_preempted:"
-"movq	__per_cpu_offset(,%rdi,8), %rax;"
-"cmpb	$0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
-"setne	%al;"
-"ret;"
-".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;"
-".popsection");
-
-#endif
-
 /*
  * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
  */
@@ -1076,10 +1112,6 @@ void __init kvm_spinlock_init(void)
 	pv_ops.lock.wait = kvm_wait;
 	pv_ops.lock.kick = kvm_kick_cpu;
 
-	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
-		pv_ops.lock.vcpu_is_preempted =
-			PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
-	}
 	/*
 	 * When PV spinlock is enabled which is preferred over
 	 * virt_spin_lock(), virt_spin_lock_key's value is meaningless.