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

Pull kvm fixes from Paolo Bonzini:
"ARM:

   - Fix the pKVM stage-1 walker erronously using the stage-2 accessor

   - Correctly convert vcpu->kvm to a hyp pointer when generating an
     exception in a nVHE+MTE configuration

   - Check that KVM_CAP_DIRTY_LOG_* are valid before enabling them

   - Fix SMPRI_EL1/TPIDR2_EL0 trapping on VHE

   - Document the boot requirements for FGT when entering the kernel at
     EL1

  x86:

   - Use SRCU to protect zap in __kvm_set_or_clear_apicv_inhibit()

   - Make argument order consistent for kvcalloc()

   - Userspace API fixes for DEBUGCTL and LBRs"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: Fix a typo about the usage of kvcalloc()
  KVM: x86: Use SRCU to protect zap in __kvm_set_or_clear_apicv_inhibit()
  KVM: VMX: Ignore guest CPUID for host userspace writes to DEBUGCTL
  KVM: VMX: Fold vmx_supported_debugctl() into vcpu_supported_debugctl()
  KVM: VMX: Advertise PMU LBRs if and only if perf supports LBRs
  arm64: booting: Document our requirements for fine grained traps with SME
  KVM: arm64: Fix SMPRI_EL1/TPIDR2_EL0 trapping on VHE
  KVM: Check KVM_CAP_DIRTY_LOG_{RING, RING_ACQ_REL} prior to enabling them
  KVM: arm64: Fix bad dereference on MTE-enabled systems
  KVM: arm64: Use correct accessor to parse stage-1 PTEs

Documentation/arm64/booting.rst

@@ -340,6 +340,14 @@ Before jumping into the kernel, the following conditions must be met:
     - SMCR_EL2.LEN must be initialised to the same value for all CPUs the
       kernel will execute on.
 
+    - HWFGRTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01.
+
+    - HWFGWTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01.
+
+    - HWFGRTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01.
+
+    - HWFGWTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01.
+
   For CPUs with the Scalable Matrix Extension FA64 feature (FEAT_SME_FA64)
 
   - If EL3 is present:

arch/arm64/kvm/hyp/exception.c

@@ -13,6 +13,7 @@
 #include <hyp/adjust_pc.h>
 #include <linux/kvm_host.h>
 #include <asm/kvm_emulate.h>
+#include <asm/kvm_mmu.h>
 
 #if !defined (__KVM_NVHE_HYPERVISOR__) && !defined (__KVM_VHE_HYPERVISOR__)
 #error Hypervisor code only!
@@ -115,7 +116,7 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
 	new |= (old & PSR_C_BIT);
 	new |= (old & PSR_V_BIT);
 
-	if (kvm_has_mte(vcpu->kvm))
+	if (kvm_has_mte(kern_hyp_va(vcpu->kvm)))
 		new |= PSR_TCO_BIT;
 
 	new |= (old & PSR_DIT_BIT);

arch/arm64/kvm/hyp/include/hyp/switch.h

@@ -87,6 +87,17 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.mdcr_el2_host = read_sysreg(mdcr_el2);
 	write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
+
+	if (cpus_have_final_cap(ARM64_SME)) {
+		sysreg_clear_set_s(SYS_HFGRTR_EL2,
+				   HFGxTR_EL2_nSMPRI_EL1_MASK |
+				   HFGxTR_EL2_nTPIDR2_EL0_MASK,
+				   0);
+		sysreg_clear_set_s(SYS_HFGWTR_EL2,
+				   HFGxTR_EL2_nSMPRI_EL1_MASK |
+				   HFGxTR_EL2_nTPIDR2_EL0_MASK,
+				   0);
+	}
 }
 
 static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
@@ -96,6 +107,15 @@ static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
 	write_sysreg(0, hstr_el2);
 	if (kvm_arm_support_pmu_v3())
 		write_sysreg(0, pmuserenr_el0);
+
+	if (cpus_have_final_cap(ARM64_SME)) {
+		sysreg_clear_set_s(SYS_HFGRTR_EL2, 0,
+				   HFGxTR_EL2_nSMPRI_EL1_MASK |
+				   HFGxTR_EL2_nTPIDR2_EL0_MASK);
+		sysreg_clear_set_s(SYS_HFGWTR_EL2, 0,
+				   HFGxTR_EL2_nSMPRI_EL1_MASK |
+				   HFGxTR_EL2_nTPIDR2_EL0_MASK);
+	}
 }
 
 static inline void ___activate_traps(struct kvm_vcpu *vcpu)

arch/arm64/kvm/hyp/nvhe/mem_protect.c

@@ -516,7 +516,7 @@ static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte)
 	if (!kvm_pte_valid(pte))
 		return PKVM_NOPAGE;
 
-	return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte));
+	return pkvm_getstate(kvm_pgtable_hyp_pte_prot(pte));
 }
 
 static int __hyp_check_page_state_range(u64 addr, u64 size,

arch/arm64/kvm/hyp/nvhe/switch.c

@@ -55,18 +55,6 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 	write_sysreg(val, cptr_el2);
 	write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2);
 
-	if (cpus_have_final_cap(ARM64_SME)) {
-		val = read_sysreg_s(SYS_HFGRTR_EL2);
-		val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK |
-			 HFGxTR_EL2_nSMPRI_EL1_MASK);
-		write_sysreg_s(val, SYS_HFGRTR_EL2);
-
-		val = read_sysreg_s(SYS_HFGWTR_EL2);
-		val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK |
-			 HFGxTR_EL2_nSMPRI_EL1_MASK);
-		write_sysreg_s(val, SYS_HFGWTR_EL2);
-	}
-
 	if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
 		struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
 
@@ -110,20 +98,6 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 
 	write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2);
 
-	if (cpus_have_final_cap(ARM64_SME)) {
-		u64 val;
-
-		val = read_sysreg_s(SYS_HFGRTR_EL2);
-		val |= HFGxTR_EL2_nTPIDR2_EL0_MASK |
-			HFGxTR_EL2_nSMPRI_EL1_MASK;
-		write_sysreg_s(val, SYS_HFGRTR_EL2);
-
-		val = read_sysreg_s(SYS_HFGWTR_EL2);
-		val |= HFGxTR_EL2_nTPIDR2_EL0_MASK |
-			HFGxTR_EL2_nSMPRI_EL1_MASK;
-		write_sysreg_s(val, SYS_HFGWTR_EL2);
-	}
-
 	cptr = CPTR_EL2_DEFAULT;
 	if (vcpu_has_sve(vcpu) && (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED))
 		cptr |= CPTR_EL2_TZ;

arch/arm64/kvm/hyp/vhe/switch.c

@@ -63,10 +63,6 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 		__activate_traps_fpsimd32(vcpu);
 	}
 
-	if (cpus_have_final_cap(ARM64_SME))
-		write_sysreg(read_sysreg(sctlr_el2) & ~SCTLR_ELx_ENTP2,
-			     sctlr_el2);
-
 	write_sysreg(val, cpacr_el1);
 
 	write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1);
@@ -88,10 +84,6 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 	 */
 	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
 
-	if (cpus_have_final_cap(ARM64_SME))
-		write_sysreg(read_sysreg(sctlr_el2) | SCTLR_ELx_ENTP2,
-			     sctlr_el2);
-
 	write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
 
 	if (!arm64_kernel_unmapped_at_el0())

arch/x86/kvm/cpuid.c

@@ -1338,7 +1338,7 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
 	if (sanity_check_entries(entries, cpuid->nent, type))
 		return -EINVAL;
 
-	array.entries = kvcalloc(sizeof(struct kvm_cpuid_entry2), cpuid->nent, GFP_KERNEL);
+	array.entries = kvcalloc(cpuid->nent, sizeof(struct kvm_cpuid_entry2), GFP_KERNEL);
 	if (!array.entries)
 		return -ENOMEM;
 

arch/x86/kvm/vmx/capabilities.h

@@ -24,8 +24,6 @@ extern int __read_mostly pt_mode;
 #define PMU_CAP_FW_WRITES	(1ULL << 13)
 #define PMU_CAP_LBR_FMT		0x3f
 
-#define DEBUGCTLMSR_LBR_MASK		(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI)
-
 struct nested_vmx_msrs {
 	/*
 	 * We only store the "true" versions of the VMX capability MSRs. We
@@ -400,6 +398,7 @@ static inline bool vmx_pebs_supported(void)
 static inline u64 vmx_get_perf_capabilities(void)
 {
 	u64 perf_cap = PMU_CAP_FW_WRITES;
+	struct x86_pmu_lbr lbr;
 	u64 host_perf_cap = 0;
 
 	if (!enable_pmu)
@@ -408,6 +407,7 @@ static inline u64 vmx_get_perf_capabilities(void)
 	if (boot_cpu_has(X86_FEATURE_PDCM))
 		rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
 
+	if (x86_perf_get_lbr(&lbr) >= 0 && lbr.nr)
 		perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT;
 
 	if (vmx_pebs_supported()) {
@@ -419,19 +419,6 @@ static inline u64 vmx_get_perf_capabilities(void)
 	return perf_cap;
 }
 
-static inline u64 vmx_supported_debugctl(void)
-{
-	u64 debugctl = 0;
-
-	if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT))
-		debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT;
-
-	if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT)
-		debugctl |= DEBUGCTLMSR_LBR_MASK;
-
-	return debugctl;
-}
-
 static inline bool cpu_has_notify_vmexit(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &

arch/x86/kvm/vmx/vmx.c

@@ -2021,15 +2021,17 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu,
 	return (unsigned long)data;
 }
 
-static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu)
+static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
 {
-	u64 debugctl = vmx_supported_debugctl();
+	u64 debugctl = 0;
 
-	if (!intel_pmu_lbr_is_enabled(vcpu))
-		debugctl &= ~DEBUGCTLMSR_LBR_MASK;
+	if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) &&
+	    (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)))
+		debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT;
 
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))
-		debugctl &= ~DEBUGCTLMSR_BUS_LOCK_DETECT;
+	if ((vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) &&
+	    (host_initiated || intel_pmu_lbr_is_enabled(vcpu)))
+		debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
 
 	return debugctl;
 }
@@ -2103,7 +2105,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vmcs_writel(GUEST_SYSENTER_ESP, data);
 		break;
 	case MSR_IA32_DEBUGCTLMSR: {
-		u64 invalid = data & ~vcpu_supported_debugctl(vcpu);
+		u64 invalid;
+
+		invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated);
 		if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) {
 			if (report_ignored_msrs)
 				vcpu_unimpl(vcpu, "%s: BTF|LBR in IA32_DEBUGCTLMSR 0x%llx, nop\n",

arch/x86/kvm/x86.c

@@ -10404,7 +10404,10 @@ void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
 		kvm->arch.apicv_inhibit_reasons = new;
 		if (new) {
 			unsigned long gfn = gpa_to_gfn(APIC_DEFAULT_PHYS_BASE);
+			int idx = srcu_read_lock(&kvm->srcu);
+
 			kvm_zap_gfn_range(kvm, gfn, gfn+1);
+			srcu_read_unlock(&kvm->srcu, idx);
 		}
 	} else {
 		kvm->arch.apicv_inhibit_reasons = new;

virt/kvm/kvm_main.c

@@ -4585,6 +4585,9 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 	}
 	case KVM_CAP_DIRTY_LOG_RING:
 	case KVM_CAP_DIRTY_LOG_RING_ACQ_REL:
+		if (!kvm_vm_ioctl_check_extension_generic(kvm, cap->cap))
+			return -EINVAL;
+
 		return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]);
 	default:
 		return kvm_vm_ioctl_enable_cap(kvm, cap);