1 files changed, 58 insertions, 20 deletions

diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index e3d3aed46184..624166004e36 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -53,6 +53,17 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 	struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr;
 	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
 	struct kvm_cpu_context *reset_cntx = &vcpu->arch.guest_reset_context;
+	bool loaded;
+
+	/**
+	 * The preemption should be disabled here because it races with
+	 * kvm_sched_out/kvm_sched_in(called from preempt notifiers) which
+	 * also calls vcpu_load/put.
+	 */
+	get_cpu();
+	loaded = (vcpu->cpu != -1);
+	if (loaded)
+		kvm_arch_vcpu_put(vcpu);
 
 	memcpy(csr, reset_csr, sizeof(*csr));
 
@@ -64,6 +75,11 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 
 	WRITE_ONCE(vcpu->arch.irqs_pending, 0);
 	WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0);
+
+	/* Reset the guest CSRs for hotplug usecase */
+	if (loaded)
+		kvm_arch_vcpu_load(vcpu, smp_processor_id());
+	put_cpu();
 }
 
 int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
@@ -74,9 +90,11 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
 int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *cntx;
+	struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr;
 
 	/* Mark this VCPU never ran */
 	vcpu->arch.ran_atleast_once = false;
+	vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO;
 
 	/* Setup ISA features available to VCPU */
 	vcpu->arch.isa = riscv_isa_extension_base(NULL) & KVM_RISCV_ISA_ALLOWED;
@@ -89,6 +107,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	cntx->hstatus |= HSTATUS_SPVP;
 	cntx->hstatus |= HSTATUS_SPV;
 
+	/* By default, make CY, TM, and IR counters accessible in VU mode */
+	reset_csr->scounteren = 0x7;
+
 	/* Setup VCPU timer */
 	kvm_riscv_vcpu_timer_init(vcpu);
 
@@ -100,6 +121,13 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
+	/**
+	 * vcpu with id 0 is the designated boot cpu.
+	 * Keep all vcpus with non-zero id in power-off state so that
+	 * they can be brought up using SBI HSM extension.
+	 */
+	if (vcpu->vcpu_idx != 0)
+		kvm_riscv_vcpu_power_off(vcpu);
 }
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
@@ -107,8 +135,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	/* Cleanup VCPU timer */
 	kvm_riscv_vcpu_timer_deinit(vcpu);
 
-	/* Flush the pages pre-allocated for Stage2 page table mappings */
-	kvm_riscv_stage2_flush_cache(vcpu);
+	/* Free unused pages pre-allocated for Stage2 page table mappings */
+	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
 }
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
@@ -675,6 +703,20 @@ static void kvm_riscv_update_hvip(struct kvm_vcpu *vcpu)
 	csr_write(CSR_HVIP, csr->hvip);
 }
 
+/*
+ * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while
+ * the vCPU is running.
+ *
+ * This must be noinstr as instrumentation may make use of RCU, and this is not
+ * safe during the EQS.
+ */
+static void noinstr kvm_riscv_vcpu_enter_exit(struct kvm_vcpu *vcpu)
+{
+	guest_state_enter_irqoff();
+	__kvm_riscv_switch_to(&vcpu->arch);
+	guest_state_exit_irqoff();
+}
+
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 {
 	int ret;
@@ -740,7 +782,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 * Ensure we set mode to IN_GUEST_MODE after we disable
 		 * interrupts and before the final VCPU requests check.
 		 * See the comment in kvm_vcpu_exiting_guest_mode() and
-		 * Documentation/virtual/kvm/vcpu-requests.rst
+		 * Documentation/virt/kvm/vcpu-requests.rst
 		 */
 		vcpu->mode = IN_GUEST_MODE;
 
@@ -766,9 +808,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			continue;
 		}
 
-		guest_enter_irqoff();
+		guest_timing_enter_irqoff();
 
-		__kvm_riscv_switch_to(&vcpu->arch);
+		kvm_riscv_vcpu_enter_exit(vcpu);
 
 		vcpu->mode = OUTSIDE_GUEST_MODE;
 		vcpu->stat.exits++;
@@ -788,25 +830,21 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		kvm_riscv_vcpu_sync_interrupts(vcpu);
 
 		/*
-		 * We may have taken a host interrupt in VS/VU-mode (i.e.
-		 * while executing the guest). This interrupt is still
-		 * pending, as we haven't serviced it yet!
+		 * We must ensure that any pending interrupts are taken before
+		 * we exit guest timing so that timer ticks are accounted as
+		 * guest time. Transiently unmask interrupts so that any
+		 * pending interrupts are taken.
 		 *
-		 * We're now back in HS-mode with interrupts disabled
-		 * so enabling the interrupts now will have the effect
-		 * of taking the interrupt again, in HS-mode this time.
+		 * There's no barrier which ensures that pending interrupts are
+		 * recognised, so we just hope that the CPU takes any pending
+		 * interrupts between the enable and disable.
 		 */
 		local_irq_enable();
+		local_irq_disable();
 
-		/*
-		 * We do local_irq_enable() before calling guest_exit() so
-		 * that if a timer interrupt hits while running the guest
-		 * we account that tick as being spent in the guest. We
-		 * enable preemption after calling guest_exit() so that if
-		 * we get preempted we make sure ticks after that is not
-		 * counted as guest time.
-		 */
-		guest_exit();
+		guest_timing_exit_irqoff();
+
+		local_irq_enable();
 
 		preempt_enable();