[PATCH RFC V6 1/5] kvm hypervisor : Add a hypercall to KVM hypervisor to support pv-ticketlocks

[Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>]

From: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>

KVM_HC_KICK_CPU allows the calling vcpu to kick another vcpu out of halt state.
    
The presence of these hypercalls is indicated to guest via
KVM_FEATURE_PV_UNHALT/KVM_CAP_PV_UNHALT.

Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Suzuki Poulose <suzuki@in.ibm.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
---
diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index e35b3a8..3252339 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -597,6 +597,9 @@ void kvm_sal_emul(struct kvm_vcpu *vcpu);
 struct kvm *kvm_arch_alloc_vm(void);
 void kvm_arch_free_vm(struct kvm *kvm);
 
+static inline void kvm_arch_vcpu_reset_pv_unhalted(struct kvm_vcpu *vcpu)
+{
+}
 #endif /* __ASSEMBLY__*/
 
 #endif
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 52eb9c1..28446de 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -498,4 +498,8 @@ struct kvm_vcpu_arch {
 #define KVM_MMIO_REG_QPR	0x0040
 #define KVM_MMIO_REG_FQPR	0x0060
 
+static inline void kvm_arch_vcpu_reset_pv_unhalted(struct kvm_vcpu *vcpu)
+{
+}
+
 #endif /* __POWERPC_KVM_HOST_H__ */
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 7343872..c47f874 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -256,4 +256,8 @@ struct kvm_arch{
 };
 
 extern int sie64a(struct kvm_s390_sie_block *, u64 *);
+static inline void kvm_arch_vcpu_reset_pv_unhalted(struct kvm_vcpu *vcpu)
+{
+}
+
 #endif
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index e216ba0..dad475b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -481,6 +481,10 @@ struct kvm_vcpu_arch {
 		u64 length;
 		u64 status;
 	} osvw;
+	/* pv related host specific info */
+	struct {
+		int pv_unhalted;
+	} pv;
 };
 
 struct kvm_lpage_info {
@@ -967,4 +971,6 @@ int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
 void kvm_handle_pmu_event(struct kvm_vcpu *vcpu);
 void kvm_deliver_pmi(struct kvm_vcpu *vcpu);
 
+void kvm_arch_vcpu_reset_pv_unhalted(struct kvm_vcpu *vcpu);
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 734c376..5b647ea 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -16,12 +16,14 @@
 #define KVM_FEATURE_CLOCKSOURCE		0
 #define KVM_FEATURE_NOP_IO_DELAY	1
 #define KVM_FEATURE_MMU_OP		2
+
 /* This indicates that the new set of kvmclock msrs
  * are available. The use of 0x11 and 0x12 is deprecated
  */
 #define KVM_FEATURE_CLOCKSOURCE2        3
 #define KVM_FEATURE_ASYNC_PF		4
 #define KVM_FEATURE_STEAL_TIME		5
+#define KVM_FEATURE_PV_UNHALT		6
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 9fed5be..7c93806 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -408,7 +408,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			     (1 << KVM_FEATURE_NOP_IO_DELAY) |
 			     (1 << KVM_FEATURE_CLOCKSOURCE2) |
 			     (1 << KVM_FEATURE_ASYNC_PF) |
-			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT);
+			     (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) |
+			     (1 << KVM_FEATURE_PV_UNHALT);
 
 		if (sched_info_on())
 			entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4044ce0..7fc9be6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2147,6 +2147,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_ASYNC_PF:
 	case KVM_CAP_GET_TSC_KHZ:
 	case KVM_CAP_PCI_2_3:
+	case KVM_CAP_PV_UNHALT:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -4993,6 +4994,36 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+/*
+ * kvm_pv_kick_cpu_op:  Kick a vcpu.
+ *
+ * @apicid - apicid of vcpu to be kicked.
+ */
+static void kvm_pv_kick_cpu_op(struct kvm *kvm, int apicid)
+{
+	struct kvm_vcpu *vcpu = NULL;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (!kvm_apic_present(vcpu))
+			continue;
+
+		if (kvm_apic_match_dest(vcpu, 0, 0, apicid, 0))
+			break;
+	}
+	if (vcpu) {
+		/*
+		 * Setting unhalt flag here can result in spurious runnable
+		 * state when unhalt reset does not happen in vcpu_block.
+		 * But that is harmless since that should soon result in halt.
+		 */
+		vcpu->arch.pv.pv_unhalted = 1;
+		/* We need everybody see unhalt before vcpu unblocks */
+		smp_mb();
+		kvm_vcpu_kick(vcpu);
+	}
+}
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
@@ -5026,6 +5057,10 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 	case KVM_HC_VAPIC_POLL_IRQ:
 		ret = 0;
 		break;
+	case KVM_HC_KICK_CPU:
+		kvm_pv_kick_cpu_op(vcpu->kvm, a0);
+		ret = 0;
+		break;
 	default:
 		ret = -KVM_ENOSYS;
 		break;
@@ -6128,6 +6163,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	BUG_ON(vcpu->kvm == NULL);
 	kvm = vcpu->kvm;
 
+	kvm_arch_vcpu_reset_pv_unhalted(vcpu);
 	vcpu->arch.emulate_ctxt.ops = &emulate_ops;
 	if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu))
 		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
@@ -6398,11 +6434,17 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 		!vcpu->arch.apf.halted)
 		|| !list_empty_careful(&vcpu->async_pf.done)
 		|| vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED
+		|| vcpu->arch.pv.pv_unhalted
 		|| atomic_read(&vcpu->arch.nmi_queued) ||
 		(kvm_arch_interrupt_allowed(vcpu) &&
 		 kvm_cpu_has_interrupt(vcpu));
 }
 
+void kvm_arch_vcpu_reset_pv_unhalted(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.pv.pv_unhalted = 0;
+}
+
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 {
 	int me;
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 6c322a9..a189f02 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -589,6 +589,7 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_S390_UCONTROL 73
 #define KVM_CAP_SYNC_REGS 74
 #define KVM_CAP_PCI_2_3 75
+#define KVM_CAP_PV_UNHALT 76
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h
index ff476dd..38226e1 100644
--- a/include/linux/kvm_para.h
+++ b/include/linux/kvm_para.h
@@ -19,6 +19,7 @@
 #define KVM_HC_MMU_OP			2
 #define KVM_HC_FEATURES			3
 #define KVM_HC_PPC_MAP_MAGIC_PAGE	4
+#define KVM_HC_KICK_CPU			5
 
 /*
  * hypercalls use architecture specific
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 42b7393..edf56d4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1500,6 +1500,14 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 		prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
 
 		if (kvm_arch_vcpu_runnable(vcpu)) {
+			/*
+			 * This is the only safe place to reset unhalt flag.
+			 * otherwise it results in loosing the notification
+			 * which eventually can result in vcpu hangs.
+			 */
+			kvm_arch_vcpu_reset_pv_unhalted(vcpu);
+			/* preventing reordering should be enough here */
+			barrier();
 			kvm_make_request(KVM_REQ_UNHALT, vcpu);
 			break;
 		}