Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "S390:

   - ultravisor communication device driver

   - fix TEID on terminating storage key ops

  RISC-V:

   - Added Sv57x4 support for G-stage page table

   - Added range based local HFENCE functions

   - Added remote HFENCE functions based on VCPU requests

   - Added ISA extension registers in ONE_REG interface

   - Updated KVM RISC-V maintainers entry to cover selftests support

  ARM:

   - Add support for the ARMv8.6 WFxT extension

   - Guard pages for the EL2 stacks

   - Trap and emulate AArch32 ID registers to hide unsupported features

   - Ability to select and save/restore the set of hypercalls exposed to
     the guest

   - Support for PSCI-initiated suspend in collaboration with userspace

   - GICv3 register-based LPI invalidation support

   - Move host PMU event merging into the vcpu data structure

   - GICv3 ITS save/restore fixes

   - The usual set of small-scale cleanups and fixes

  x86:

   - New ioctls to get/set TSC frequency for a whole VM

   - Allow userspace to opt out of hypercall patching

   - Only do MSR filtering for MSRs accessed by rdmsr/wrmsr

  AMD SEV improvements:

   - Add KVM_EXIT_SHUTDOWN metadata for SEV-ES

   - V_TSC_AUX support

  Nested virtualization improvements for AMD:

   - Support for "nested nested" optimizations (nested vVMLOAD/VMSAVE,
     nested vGIF)

   - Allow AVIC to co-exist with a nested guest running

   - Fixes for LBR virtualizations when a nested guest is running, and
     nested LBR virtualization support

   - PAUSE filtering for nested hypervisors

  Guest support:

   - Decoupling of vcpu_is_preempted from PV spinlocks"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (199 commits)
  KVM: x86: Fix the intel_pt PMI handling wrongly considered from guest
  KVM: selftests: x86: Sync the new name of the test case to .gitignore
  Documentation: kvm: reorder ARM-specific section about KVM_SYSTEM_EVENT_SUSPEND
  x86, kvm: use correct GFP flags for preemption disabled
  KVM: LAPIC: Drop pending LAPIC timer injection when canceling the timer
  x86/kvm: Alloc dummy async #PF token outside of raw spinlock
  KVM: x86: avoid calling x86 emulator without a decoded instruction
  KVM: SVM: Use kzalloc for sev ioctl interfaces to prevent kernel data leak
  x86/fpu: KVM: Set the base guest FPU uABI size to sizeof(struct kvm_xsave)
  s390/uv_uapi: depend on CONFIG_S390
  KVM: selftests: x86: Fix test failure on arch lbr capable platforms
  KVM: LAPIC: Trace LAPIC timer expiration on every vmentry
  KVM: s390: selftest: Test suppression indication on key prot exception
  KVM: s390: Don't indicate suppression on dirtying, failing memop
  selftests: drivers/s390x: Add uvdevice tests
  drivers/s390/char: Add Ultravisor io device
  MAINTAINERS: Update KVM RISC-V entry to cover selftests support
  RISC-V: KVM: Introduce ISA extension register
  RISC-V: KVM: Cleanup stale TLB entries when host CPU changes
  RISC-V: KVM: Add remote HFENCE functions based on VCPU requests
  ...

1 files changed, 137 insertions, 7 deletions

diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index 7461f964d20a..7f4ad5e4373a 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -67,6 +67,8 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 	if (loaded)
 		kvm_arch_vcpu_put(vcpu);
 
+	vcpu->arch.last_exit_cpu = -1;
+
 	memcpy(csr, reset_csr, sizeof(*csr));
 
 	memcpy(cntx, reset_cntx, sizeof(*cntx));
@@ -78,6 +80,10 @@ 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);
 
+	vcpu->arch.hfence_head = 0;
+	vcpu->arch.hfence_tail = 0;
+	memset(vcpu->arch.hfence_queue, 0, sizeof(vcpu->arch.hfence_queue));
+
 	/* Reset the guest CSRs for hotplug usecase */
 	if (loaded)
 		kvm_arch_vcpu_load(vcpu, smp_processor_id());
@@ -101,6 +107,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	/* Setup ISA features available to VCPU */
 	vcpu->arch.isa = riscv_isa_extension_base(NULL) & KVM_RISCV_ISA_ALLOWED;
 
+	/* Setup VCPU hfence queue */
+	spin_lock_init(&vcpu->arch.hfence_lock);
+
 	/* Setup reset state of shadow SSTATUS and HSTATUS CSRs */
 	cntx = &vcpu->arch.guest_reset_context;
 	cntx->sstatus = SR_SPP | SR_SPIE;
@@ -137,7 +146,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	/* Cleanup VCPU timer */
 	kvm_riscv_vcpu_timer_deinit(vcpu);
 
-	/* Free unused pages pre-allocated for Stage2 page table mappings */
+	/* Free unused pages pre-allocated for G-stage page table mappings */
 	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
 }
 
@@ -365,6 +374,101 @@ static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+/* Mapping between KVM ISA Extension ID & Host ISA extension ID */
+static unsigned long kvm_isa_ext_arr[] = {
+	RISCV_ISA_EXT_a,
+	RISCV_ISA_EXT_c,
+	RISCV_ISA_EXT_d,
+	RISCV_ISA_EXT_f,
+	RISCV_ISA_EXT_h,
+	RISCV_ISA_EXT_i,
+	RISCV_ISA_EXT_m,
+};
+
+static int kvm_riscv_vcpu_get_reg_isa_ext(struct kvm_vcpu *vcpu,
+					  const struct kvm_one_reg *reg)
+{
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_ISA_EXT);
+	unsigned long reg_val = 0;
+	unsigned long host_isa_ext;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	if (reg_num >= KVM_RISCV_ISA_EXT_MAX || reg_num >= ARRAY_SIZE(kvm_isa_ext_arr))
+		return -EINVAL;
+
+	host_isa_ext = kvm_isa_ext_arr[reg_num];
+	if (__riscv_isa_extension_available(&vcpu->arch.isa, host_isa_ext))
+		reg_val = 1; /* Mark the given extension as available */
+
+	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu,
+					  const struct kvm_one_reg *reg)
+{
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_ISA_EXT);
+	unsigned long reg_val;
+	unsigned long host_isa_ext;
+	unsigned long host_isa_ext_mask;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	if (reg_num >= KVM_RISCV_ISA_EXT_MAX || reg_num >= ARRAY_SIZE(kvm_isa_ext_arr))
+		return -EINVAL;
+
+	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	host_isa_ext = kvm_isa_ext_arr[reg_num];
+	if (!__riscv_isa_extension_available(NULL, host_isa_ext))
+		return	-EOPNOTSUPP;
+
+	if (host_isa_ext >= RISCV_ISA_EXT_BASE &&
+	    host_isa_ext < RISCV_ISA_EXT_MAX) {
+		/*
+		 * Multi-letter ISA extension. Currently there is no provision
+		 * to enable/disable the multi-letter ISA extensions for guests.
+		 * Return success if the request is to enable any ISA extension
+		 * that is available in the hardware.
+		 * Return -EOPNOTSUPP otherwise.
+		 */
+		if (!reg_val)
+			return -EOPNOTSUPP;
+		else
+			return 0;
+	}
+
+	/* Single letter base ISA extension */
+	if (!vcpu->arch.ran_atleast_once) {
+		host_isa_ext_mask = BIT_MASK(host_isa_ext);
+		if (!reg_val && (host_isa_ext_mask & KVM_RISCV_ISA_DISABLE_ALLOWED))
+			vcpu->arch.isa &= ~host_isa_ext_mask;
+		else
+			vcpu->arch.isa |= host_isa_ext_mask;
+		vcpu->arch.isa &= riscv_isa_extension_base(NULL);
+		vcpu->arch.isa &= KVM_RISCV_ISA_ALLOWED;
+		kvm_riscv_vcpu_fp_reset(vcpu);
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 static int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
 				  const struct kvm_one_reg *reg)
 {
@@ -382,6 +486,8 @@ static int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
 	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_FP_D)
 		return kvm_riscv_vcpu_set_reg_fp(vcpu, reg,
 						 KVM_REG_RISCV_FP_D);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_ISA_EXT)
+		return kvm_riscv_vcpu_set_reg_isa_ext(vcpu, reg);
 
 	return -EINVAL;
 }
@@ -403,6 +509,8 @@ static int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu,
 	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_FP_D)
 		return kvm_riscv_vcpu_get_reg_fp(vcpu, reg,
 						 KVM_REG_RISCV_FP_D);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_ISA_EXT)
+		return kvm_riscv_vcpu_get_reg_isa_ext(vcpu, reg);
 
 	return -EINVAL;
 }
@@ -635,7 +743,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	csr_write(CSR_HVIP, csr->hvip);
 	csr_write(CSR_VSATP, csr->vsatp);
 
-	kvm_riscv_stage2_update_hgatp(vcpu);
+	kvm_riscv_gstage_update_hgatp(vcpu);
 
 	kvm_riscv_vcpu_timer_restore(vcpu);
 
@@ -690,10 +798,23 @@ static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu)
 			kvm_riscv_reset_vcpu(vcpu);
 
 		if (kvm_check_request(KVM_REQ_UPDATE_HGATP, vcpu))
-			kvm_riscv_stage2_update_hgatp(vcpu);
+			kvm_riscv_gstage_update_hgatp(vcpu);
 
-		if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
-			__kvm_riscv_hfence_gvma_all();
+		if (kvm_check_request(KVM_REQ_FENCE_I, vcpu))
+			kvm_riscv_fence_i_process(vcpu);
+
+		/*
+		 * The generic KVM_REQ_TLB_FLUSH is same as
+		 * KVM_REQ_HFENCE_GVMA_VMID_ALL
+		 */
+		if (kvm_check_request(KVM_REQ_HFENCE_GVMA_VMID_ALL, vcpu))
+			kvm_riscv_hfence_gvma_vmid_all_process(vcpu);
+
+		if (kvm_check_request(KVM_REQ_HFENCE_VVMA_ALL, vcpu))
+			kvm_riscv_hfence_vvma_all_process(vcpu);
+
+		if (kvm_check_request(KVM_REQ_HFENCE, vcpu))
+			kvm_riscv_hfence_process(vcpu);
 	}
 }
 
@@ -715,6 +836,7 @@ static void noinstr kvm_riscv_vcpu_enter_exit(struct kvm_vcpu *vcpu)
 {
 	guest_state_enter_irqoff();
 	__kvm_riscv_switch_to(&vcpu->arch);
+	vcpu->arch.last_exit_cpu = vcpu->cpu;
 	guest_state_exit_irqoff();
 }
 
@@ -762,7 +884,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		/* Check conditions before entering the guest */
 		cond_resched();
 
-		kvm_riscv_stage2_vmid_update(vcpu);
+		kvm_riscv_gstage_vmid_update(vcpu);
 
 		kvm_riscv_check_vcpu_requests(vcpu);
 
@@ -800,7 +922,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		kvm_riscv_update_hvip(vcpu);
 
 		if (ret <= 0 ||
-		    kvm_riscv_stage2_vmid_ver_changed(&vcpu->kvm->arch.vmid) ||
+		    kvm_riscv_gstage_vmid_ver_changed(&vcpu->kvm->arch.vmid) ||
 		    kvm_request_pending(vcpu)) {
 			vcpu->mode = OUTSIDE_GUEST_MODE;
 			local_irq_enable();
@@ -809,6 +931,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 			continue;
 		}
 
+		/*
+		 * Cleanup stale TLB enteries
+		 *
+		 * Note: This should be done after G-stage VMID has been
+		 * updated using kvm_riscv_gstage_vmid_ver_changed()
+		 */
+		kvm_riscv_local_tlb_sanitize(vcpu);
+
 		guest_timing_enter_irqoff();
 
 		kvm_riscv_vcpu_enter_exit(vcpu);