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

Pull KVM updates from Paolo Bonzini:
 "PPC:
   - Better machine check handling for HV KVM
   - Ability to support guests with threads=2, 4 or 8 on POWER9
   - Fix for a race that could cause delayed recognition of signals
   - Fix for a bug where POWER9 guests could sleep with interrupts pending.

  ARM:
   - VCPU request overhaul
   - allow timer and PMU to have their interrupt number selected from userspace
   - workaround for Cavium erratum 30115
   - handling of memory poisonning
   - the usual crop of fixes and cleanups

  s390:
   - initial machine check forwarding
   - migration support for the CMMA page hinting information
   - cleanups and fixes

  x86:
   - nested VMX bugfixes and improvements
   - more reliable NMI window detection on AMD
   - APIC timer optimizations

  Generic:
   - VCPU request overhaul + documentation of common code patterns
   - kvm_stat improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (124 commits)
  Update my email address
  kvm: vmx: allow host to access guest MSR_IA32_BNDCFGS
  x86: kvm: mmu: use ept a/d in vmcs02 iff used in vmcs12
  kvm: x86: mmu: allow A/D bits to be disabled in an mmu
  x86: kvm: mmu: make spte mmio mask more explicit
  x86: kvm: mmu: dead code thanks to access tracking
  KVM: PPC: Book3S: Fix typo in XICS-on-XIVE state saving code
  KVM: PPC: Book3S HV: Close race with testing for signals on guest entry
  KVM: PPC: Book3S HV: Simplify dynamic micro-threading code
  KVM: x86: remove ignored type attribute
  KVM: LAPIC: Fix lapic timer injection delay
  KVM: lapic: reorganize restart_apic_timer
  KVM: lapic: reorganize start_hv_timer
  kvm: nVMX: Check memory operand to INVVPID
  KVM: s390: Inject machine check into the nested guest
  KVM: s390: Inject machine check into the guest
  tools/kvm_stat: add new interactive command 'b'
  tools/kvm_stat: add new command line switch '-i'
  tools/kvm_stat: fix error on interactive command 'g'
  KVM: SVM: suppress unnecessary NMI singlestep on GIF=0 and nested exit
  ...

6 files changed, 64 insertions, 49 deletions

diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index b37446a8ffdb..5c7f657dd207 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -390,6 +390,9 @@ int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
 	case KVM_ARM_VCPU_PMU_V3_CTRL:
 		ret = kvm_arm_pmu_v3_set_attr(vcpu, attr);
 		break;
+	case KVM_ARM_VCPU_TIMER_CTRL:
+		ret = kvm_arm_timer_set_attr(vcpu, attr);
+		break;
 	default:
 		ret = -ENXIO;
 		break;
@@ -407,6 +410,9 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
 	case KVM_ARM_VCPU_PMU_V3_CTRL:
 		ret = kvm_arm_pmu_v3_get_attr(vcpu, attr);
 		break;
+	case KVM_ARM_VCPU_TIMER_CTRL:
+		ret = kvm_arm_timer_get_attr(vcpu, attr);
+		break;
 	default:
 		ret = -ENXIO;
 		break;
@@ -424,6 +430,9 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
 	case KVM_ARM_VCPU_PMU_V3_CTRL:
 		ret = kvm_arm_pmu_v3_has_attr(vcpu, attr);
 		break;
+	case KVM_ARM_VCPU_TIMER_CTRL:
+		ret = kvm_arm_timer_has_attr(vcpu, attr);
+		break;
 	default:
 		ret = -ENXIO;
 		break;
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index fa1b18e364fc..17d8a1677a0b 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -89,6 +89,7 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false);
 		vcpu->stat.wfi_exit_stat++;
 		kvm_vcpu_block(vcpu);
+		kvm_clear_request(KVM_REQ_UNHALT, vcpu);
 	}
 
 	kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index aede1658aeda..945e79c641c4 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -350,6 +350,20 @@ again:
 		}
 	}
 
+	if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
+	    exit_code == ARM_EXCEPTION_TRAP &&
+	    (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 ||
+	     kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
+		int ret = __vgic_v3_perform_cpuif_access(vcpu);
+
+		if (ret == 1) {
+			__skip_instr(vcpu);
+			goto again;
+		}
+
+		/* 0 falls through to be handled out of EL2 */
+	}
+
 	fp_enabled = __fpsimd_enabled();
 
 	__sysreg_save_guest_state(guest_ctxt);
@@ -422,6 +436,7 @@ void __hyp_text __noreturn __hyp_panic(void)
 
 		vcpu = (struct kvm_vcpu *)read_sysreg(tpidr_el2);
 		host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context);
+		__timer_save_state(vcpu);
 		__deactivate_traps(vcpu);
 		__deactivate_vm(vcpu);
 		__sysreg_restore_host_state(host_ctxt);
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 561badf93de8..3256b9228e75 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -46,16 +46,6 @@ static const struct kvm_regs default_regs_reset32 = {
 			COMPAT_PSR_I_BIT | COMPAT_PSR_F_BIT),
 };
 
-static const struct kvm_irq_level default_ptimer_irq = {
-	.irq	= 30,
-	.level	= 1,
-};
-
-static const struct kvm_irq_level default_vtimer_irq = {
-	.irq	= 27,
-	.level	= 1,
-};
-
 static bool cpu_has_32bit_el1(void)
 {
 	u64 pfr0;
@@ -108,8 +98,6 @@ int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext)
  */
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 {
-	const struct kvm_irq_level *cpu_vtimer_irq;
-	const struct kvm_irq_level *cpu_ptimer_irq;
 	const struct kvm_regs *cpu_reset;
 
 	switch (vcpu->arch.target) {
@@ -122,8 +110,6 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 			cpu_reset = &default_regs_reset;
 		}
 
-		cpu_vtimer_irq = &default_vtimer_irq;
-		cpu_ptimer_irq = &default_ptimer_irq;
 		break;
 	}
 
@@ -137,5 +123,5 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	kvm_pmu_vcpu_reset(vcpu);
 
 	/* Reset timer */
-	return kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq, cpu_ptimer_irq);
+	return kvm_timer_vcpu_reset(vcpu);
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 0fe27024a2e1..77862881ae86 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -56,7 +56,8 @@
  */
 
 static bool read_from_write_only(struct kvm_vcpu *vcpu,
-				 const struct sys_reg_params *params)
+				 struct sys_reg_params *params,
+				 const struct sys_reg_desc *r)
 {
 	WARN_ONCE(1, "Unexpected sys_reg read to write-only register\n");
 	print_sys_reg_instr(params);
@@ -64,6 +65,16 @@ static bool read_from_write_only(struct kvm_vcpu *vcpu,
 	return false;
 }
 
+static bool write_to_read_only(struct kvm_vcpu *vcpu,
+			       struct sys_reg_params *params,
+			       const struct sys_reg_desc *r)
+{
+	WARN_ONCE(1, "Unexpected sys_reg write to read-only register\n");
+	print_sys_reg_instr(params);
+	kvm_inject_undefined(vcpu);
+	return false;
+}
+
 /* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */
 static u32 cache_levels;
 
@@ -93,7 +104,7 @@ static bool access_dcsw(struct kvm_vcpu *vcpu,
 			const struct sys_reg_desc *r)
 {
 	if (!p->is_write)
-		return read_from_write_only(vcpu, p);
+		return read_from_write_only(vcpu, p, r);
 
 	kvm_set_way_flush(vcpu);
 	return true;
@@ -135,7 +146,7 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu,
 			   const struct sys_reg_desc *r)
 {
 	if (!p->is_write)
-		return read_from_write_only(vcpu, p);
+		return read_from_write_only(vcpu, p, r);
 
 	vgic_v3_dispatch_sgi(vcpu, p->regval);
 
@@ -773,7 +784,7 @@ static bool access_pmswinc(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		return trap_raz_wi(vcpu, p, r);
 
 	if (!p->is_write)
-		return read_from_write_only(vcpu, p);
+		return read_from_write_only(vcpu, p, r);
 
 	if (pmu_write_swinc_el0_disabled(vcpu))
 		return false;
@@ -953,7 +964,15 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 
 	{ SYS_DESC(SYS_VBAR_EL1), NULL, reset_val, VBAR_EL1, 0 },
 
+	{ SYS_DESC(SYS_ICC_IAR0_EL1), write_to_read_only },
+	{ SYS_DESC(SYS_ICC_EOIR0_EL1), read_from_write_only },
+	{ SYS_DESC(SYS_ICC_HPPIR0_EL1), write_to_read_only },
+	{ SYS_DESC(SYS_ICC_DIR_EL1), read_from_write_only },
+	{ SYS_DESC(SYS_ICC_RPR_EL1), write_to_read_only },
 	{ SYS_DESC(SYS_ICC_SGI1R_EL1), access_gic_sgi },
+	{ SYS_DESC(SYS_ICC_IAR1_EL1), write_to_read_only },
+	{ SYS_DESC(SYS_ICC_EOIR1_EL1), read_from_write_only },
+	{ SYS_DESC(SYS_ICC_HPPIR1_EL1), write_to_read_only },
 	{ SYS_DESC(SYS_ICC_SRE_EL1), access_gic_sre },
 
 	{ SYS_DESC(SYS_CONTEXTIDR_EL1), access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
diff --git a/arch/arm64/kvm/vgic-sys-reg-v3.c b/arch/arm64/kvm/vgic-sys-reg-v3.c
index 6260b69e5622..116786d2e8e8 100644
--- a/arch/arm64/kvm/vgic-sys-reg-v3.c
+++ b/arch/arm64/kvm/vgic-sys-reg-v3.c
@@ -268,36 +268,21 @@ static bool access_gic_sre(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	return true;
 }
 static const struct sys_reg_desc gic_v3_icc_reg_descs[] = {
-	/* ICC_PMR_EL1 */
-	{ Op0(3), Op1(0), CRn(4), CRm(6), Op2(0), access_gic_pmr },
-	/* ICC_BPR0_EL1 */
-	{ Op0(3), Op1(0), CRn(12), CRm(8), Op2(3), access_gic_bpr0 },
-	/* ICC_AP0R0_EL1 */
-	{ Op0(3), Op1(0), CRn(12), CRm(8), Op2(4), access_gic_ap0r },
-	/* ICC_AP0R1_EL1 */
-	{ Op0(3), Op1(0), CRn(12), CRm(8), Op2(5), access_gic_ap0r },
-	/* ICC_AP0R2_EL1 */
-	{ Op0(3), Op1(0), CRn(12), CRm(8), Op2(6), access_gic_ap0r },
-	/* ICC_AP0R3_EL1 */
-	{ Op0(3), Op1(0), CRn(12), CRm(8), Op2(7), access_gic_ap0r },
-	/* ICC_AP1R0_EL1 */
-	{ Op0(3), Op1(0), CRn(12), CRm(9), Op2(0), access_gic_ap1r },
-	/* ICC_AP1R1_EL1 */
-	{ Op0(3), Op1(0), CRn(12), CRm(9), Op2(1), access_gic_ap1r },
-	/* ICC_AP1R2_EL1 */
-	{ Op0(3), Op1(0), CRn(12), CRm(9), Op2(2), access_gic_ap1r },
-	/* ICC_AP1R3_EL1 */
-	{ Op0(3), Op1(0), CRn(12), CRm(9), Op2(3), access_gic_ap1r },
-	/* ICC_BPR1_EL1 */
-	{ Op0(3), Op1(0), CRn(12), CRm(12), Op2(3), access_gic_bpr1 },
-	/* ICC_CTLR_EL1 */
-	{ Op0(3), Op1(0), CRn(12), CRm(12), Op2(4), access_gic_ctlr },
-	/* ICC_SRE_EL1 */
-	{ Op0(3), Op1(0), CRn(12), CRm(12), Op2(5), access_gic_sre },
-	/* ICC_IGRPEN0_EL1 */
-	{ Op0(3), Op1(0), CRn(12), CRm(12), Op2(6), access_gic_grpen0 },
-	/* ICC_GRPEN1_EL1 */
-	{ Op0(3), Op1(0), CRn(12), CRm(12), Op2(7), access_gic_grpen1 },
+	{ SYS_DESC(SYS_ICC_PMR_EL1), access_gic_pmr },
+	{ SYS_DESC(SYS_ICC_BPR0_EL1), access_gic_bpr0 },
+	{ SYS_DESC(SYS_ICC_AP0R0_EL1), access_gic_ap0r },
+	{ SYS_DESC(SYS_ICC_AP0R1_EL1), access_gic_ap0r },
+	{ SYS_DESC(SYS_ICC_AP0R2_EL1), access_gic_ap0r },
+	{ SYS_DESC(SYS_ICC_AP0R3_EL1), access_gic_ap0r },
+	{ SYS_DESC(SYS_ICC_AP1R0_EL1), access_gic_ap1r },
+	{ SYS_DESC(SYS_ICC_AP1R1_EL1), access_gic_ap1r },
+	{ SYS_DESC(SYS_ICC_AP1R2_EL1), access_gic_ap1r },
+	{ SYS_DESC(SYS_ICC_AP1R3_EL1), access_gic_ap1r },
+	{ SYS_DESC(SYS_ICC_BPR1_EL1), access_gic_bpr1 },
+	{ SYS_DESC(SYS_ICC_CTLR_EL1), access_gic_ctlr },
+	{ SYS_DESC(SYS_ICC_SRE_EL1), access_gic_sre },
+	{ SYS_DESC(SYS_ICC_IGRPEN0_EL1), access_gic_grpen0 },
+	{ SYS_DESC(SYS_ICC_IGRPEN1_EL1), access_gic_grpen1 },
 };
 
 int vgic_v3_has_cpu_sysregs_attr(struct kvm_vcpu *vcpu, bool is_write, u64 id,