arm/arm64: KVM: Allow a VCPU to fully reset itself

The current kvm_psci_vcpu_on implementation will directly try to
manipulate the state of the VCPU to reset it.  However, since this is
not done on the thread that runs the VCPU, we can end up in a strangely
corrupted state when the source and target VCPUs are running at the same
time.

Fix this by factoring out all reset logic from the PSCI implementation
and forwarding the required information along with a request to the
target VCPU.

Reviewed-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <christoffer.dall@arm.com>

2 files changed, 26 insertions, 20 deletions

diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 9e350fd34504..9c486fad3f9f 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -626,6 +626,13 @@ static void vcpu_req_sleep(struct kvm_vcpu *vcpu)
 		/* Awaken to handle a signal, request we sleep again later. */
 		kvm_make_request(KVM_REQ_SLEEP, vcpu);
 	}
+
+	/*
+	 * Make sure we will observe a potential reset request if we've
+	 * observed a change to the power state. Pairs with the smp_wmb() in
+	 * kvm_psci_vcpu_on().
+	 */
+	smp_rmb();
 }
 
 static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
@@ -639,6 +646,9 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)
 		if (kvm_check_request(KVM_REQ_SLEEP, vcpu))
 			vcpu_req_sleep(vcpu);
 
+		if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu))
+			kvm_reset_vcpu(vcpu);
+
 		/*
 		 * Clear IRQ_PENDING requests that were made to guarantee
 		 * that a VCPU sees new virtual interrupts.
diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c
index 9b73d3ad918a..34d08ee63747 100644
--- a/virt/kvm/arm/psci.c
+++ b/virt/kvm/arm/psci.c
@@ -104,12 +104,10 @@ static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
 
 static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 {
+	struct vcpu_reset_state *reset_state;
 	struct kvm *kvm = source_vcpu->kvm;
 	struct kvm_vcpu *vcpu = NULL;
-	struct swait_queue_head *wq;
 	unsigned long cpu_id;
-	unsigned long context_id;
-	phys_addr_t target_pc;
 
 	cpu_id = smccc_get_arg1(source_vcpu) & MPIDR_HWID_BITMASK;
 	if (vcpu_mode_is_32bit(source_vcpu))
@@ -130,32 +128,30 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 			return PSCI_RET_INVALID_PARAMS;
 	}
 
-	target_pc = smccc_get_arg2(source_vcpu);
-	context_id = smccc_get_arg3(source_vcpu);
+	reset_state = &vcpu->arch.reset_state;
 
-	kvm_reset_vcpu(vcpu);
-
-	/* Gracefully handle Thumb2 entry point */
-	if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) {
-		target_pc &= ~((phys_addr_t) 1);
-		vcpu_set_thumb(vcpu);
-	}
+	reset_state->pc = smccc_get_arg2(source_vcpu);
 
 	/* Propagate caller endianness */
-	if (kvm_vcpu_is_be(source_vcpu))
-		kvm_vcpu_set_be(vcpu);
+	reset_state->be = kvm_vcpu_is_be(source_vcpu);
 
-	*vcpu_pc(vcpu) = target_pc;
 	/*
 	 * NOTE: We always update r0 (or x0) because for PSCI v0.1
 	 * the general puspose registers are undefined upon CPU_ON.
 	 */
-	smccc_set_retval(vcpu, context_id, 0, 0, 0);
-	vcpu->arch.power_off = false;
-	smp_mb();		/* Make sure the above is visible */
+	reset_state->r0 = smccc_get_arg3(source_vcpu);
+
+	WRITE_ONCE(reset_state->reset, true);
+	kvm_make_request(KVM_REQ_VCPU_RESET, vcpu);
 
-	wq = kvm_arch_vcpu_wq(vcpu);
-	swake_up_one(wq);
+	/*
+	 * Make sure the reset request is observed if the change to
+	 * power_state is observed.
+	 */
+	smp_wmb();
+
+	vcpu->arch.power_off = false;
+	kvm_vcpu_wake_up(vcpu);
 
 	return PSCI_RET_SUCCESS;
 }