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

Pull kvm fixes from Paolo Bonzini:
 "ARM:
   - selftest fix
   - force PTE mapping on device pages provided via VFIO
   - fix detection of cacheable mapping at S2
   - fallback to PMD/PTE mappings for composite huge pages
   - fix accounting of Stage-2 PGD allocation
   - fix AArch32 handling of some of the debug registers
   - simplify host HYP entry
   - fix stray pointer conversion on nVHE TLB invalidation
   - fix initialization of the nVHE code
   - simplify handling of capabilities exposed to HYP
   - nuke VCPUs caught using a forbidden AArch32 EL0

  x86:
   - new nested virtualization selftest
   - miscellaneous fixes
   - make W=1 fixes
   - reserve new CPUID bit in the KVM leaves"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: vmx: remove unused variable
  KVM: selftests: Don't require THP to run tests
  KVM: VMX: eVMCS: make evmcs_sanitize_exec_ctrls() work again
  KVM: selftests: test behavior of unmapped L2 APIC-access address
  KVM: x86: Fix NULL dereference at kvm_msr_ignored_check()
  KVM: x86: replace static const variables with macros
  KVM: arm64: Handle Asymmetric AArch32 systems
  arm64: cpufeature: upgrade hyp caps to final
  arm64: cpufeature: reorder cpus_have_{const, final}_cap()
  KVM: arm64: Factor out is_{vhe,nvhe}_hyp_code()
  KVM: arm64: Force PTE mapping on fault resulting in a device mapping
  KVM: arm64: Use fallback mapping sizes for contiguous huge page sizes
  KVM: arm64: Fix masks in stage2_pte_cacheable()
  KVM: arm64: Fix AArch32 handling of DBGD{CCINT,SCRext} and DBGVCR
  KVM: arm64: Allocate stage-2 pgd pages with GFP_KERNEL_ACCOUNT
  KVM: arm64: Drop useless PAN setting on host EL1 to EL2 transition
  KVM: arm64: Remove leftover kern_hyp_va() in nVHE TLB invalidation
  KVM: arm64: Don't corrupt tpidr_el2 on failed HVC call
  x86/kvm: Reserve KVM_FEATURE_MSI_EXT_DEST_ID

7 files changed, 60 insertions, 22 deletions

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 8f8fca47abfc..5750ec34960e 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -808,6 +808,25 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 
 		preempt_enable();
 
+		/*
+		 * The ARMv8 architecture doesn't give the hypervisor
+		 * a mechanism to prevent a guest from dropping to AArch32 EL0
+		 * if implemented by the CPU. If we spot the guest in such
+		 * state and that we decided it wasn't supposed to do so (like
+		 * with the asymmetric AArch32 case), return to userspace with
+		 * a fatal error.
+		 */
+		if (!system_supports_32bit_el0() && vcpu_mode_is_32bit(vcpu)) {
+			/*
+			 * As we have caught the guest red-handed, decide that
+			 * it isn't fit for purpose anymore by making the vcpu
+			 * invalid. The VMM can try and fix it by issuing  a
+			 * KVM_ARM_VCPU_INIT if it really wants to.
+			 */
+			vcpu->arch.target = -1;
+			ret = ARM_EXCEPTION_IL;
+		}
+
 		ret = handle_exit(vcpu, ret);
 	}
 
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index ff9a0f547b9f..ed27f06a31ba 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -17,8 +17,6 @@ SYM_FUNC_START(__host_exit)
 
 	get_host_ctxt	x0, x1
 
-	ALTERNATIVE(nop, SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
-
 	/* Store the host regs x2 and x3 */
 	stp	x2, x3,   [x0, #CPU_XREG_OFFSET(2)]
 
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 47224dc62c51..b11a9d7db677 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -57,16 +57,25 @@ __do_hyp_init:
 	cmp	x0, #HVC_STUB_HCALL_NR
 	b.lo	__kvm_handle_stub_hvc
 
-	/* Set tpidr_el2 for use by HYP to free a register */
-	msr	tpidr_el2, x2
-
-	mov	x2, #KVM_HOST_SMCCC_FUNC(__kvm_hyp_init)
-	cmp	x0, x2
-	b.eq	1f
+	// We only actively check bits [24:31], and everything
+	// else has to be zero, which we check at build time.
+#if (KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) & 0xFFFFFFFF00FFFFFF)
+#error Unexpected __KVM_HOST_SMCCC_FUNC___kvm_hyp_init value
+#endif
+
+	ror	x0, x0, #24
+	eor	x0, x0, #((KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) >> 24) & 0xF)
+	ror	x0, x0, #4
+	eor	x0, x0, #((KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) >> 28) & 0xF)
+	cbz	x0, 1f
 	mov	x0, #SMCCC_RET_NOT_SUPPORTED
 	eret
 
-1:	phys_to_ttbr x0, x1
+1:
+	/* Set tpidr_el2 for use by HYP to free a register */
+	msr	tpidr_el2, x2
+
+	phys_to_ttbr x0, x1
 alternative_if ARM64_HAS_CNP
 	orr	x0, x0, #TTBR_CNP_BIT
 alternative_else_nop_endif
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index 39ca71ab8866..fbde89a2c6e8 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -128,7 +128,6 @@ void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
 	struct tlb_inv_context cxt;
 
 	/* Switch to requested VMID */
-	mmu = kern_hyp_va(mmu);
 	__tlb_switch_to_guest(mmu, &cxt);
 
 	__tlbi(vmalle1);
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 0cdf6e461cbd..0271b4a3b9fe 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -635,7 +635,7 @@ static void stage2_flush_dcache(void *addr, u64 size)
 
 static bool stage2_pte_cacheable(kvm_pte_t pte)
 {
-	u64 memattr = FIELD_GET(KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR, pte);
+	u64 memattr = pte & KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR;
 	return memattr == PAGE_S2_MEMATTR(NORMAL);
 }
 
@@ -846,7 +846,7 @@ int kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm *kvm)
 	u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0;
 
 	pgd_sz = kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE;
-	pgt->pgd = alloc_pages_exact(pgd_sz, GFP_KERNEL | __GFP_ZERO);
+	pgt->pgd = alloc_pages_exact(pgd_sz, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
 	if (!pgt->pgd)
 		return -ENOMEM;
 
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 19aacc7d64de..57972bdb213a 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -787,14 +787,26 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		vma_shift = PAGE_SHIFT;
 	}
 
-	if (vma_shift == PUD_SHIFT &&
-	    !fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE))
-	       vma_shift = PMD_SHIFT;
-
-	if (vma_shift == PMD_SHIFT &&
-	    !fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) {
-		force_pte = true;
+	switch (vma_shift) {
+	case PUD_SHIFT:
+		if (fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE))
+			break;
+		fallthrough;
+	case CONT_PMD_SHIFT:
+		vma_shift = PMD_SHIFT;
+		fallthrough;
+	case PMD_SHIFT:
+		if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE))
+			break;
+		fallthrough;
+	case CONT_PTE_SHIFT:
 		vma_shift = PAGE_SHIFT;
+		force_pte = true;
+		fallthrough;
+	case PAGE_SHIFT:
+		break;
+	default:
+		WARN_ONCE(1, "Unknown vma_shift %d", vma_shift);
 	}
 
 	vma_pagesize = 1UL << vma_shift;
@@ -839,6 +851,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 
 	if (kvm_is_device_pfn(pfn)) {
 		device = true;
+		force_pte = true;
 	} else if (logging_active && !write_fault) {
 		/*
 		 * Only actually map the page as writable if this was a write
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 41348a7781d9..fb12d3ef423a 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1897,9 +1897,9 @@ static const struct sys_reg_desc cp14_regs[] = {
 	{ Op1( 0), CRn( 0), CRm( 1), Op2( 0), trap_raz_wi },
 	DBG_BCR_BVR_WCR_WVR(1),
 	/* DBGDCCINT */
-	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32 },
+	{ Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32, NULL, cp14_DBGDCCINT },
 	/* DBGDSCRext */
-	{ Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32 },
+	{ Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32, NULL, cp14_DBGDSCRext },
 	DBG_BCR_BVR_WCR_WVR(2),
 	/* DBGDTR[RT]Xint */
 	{ Op1( 0), CRn( 0), CRm( 3), Op2( 0), trap_raz_wi },
@@ -1914,7 +1914,7 @@ static const struct sys_reg_desc cp14_regs[] = {
 	{ Op1( 0), CRn( 0), CRm( 6), Op2( 2), trap_raz_wi },
 	DBG_BCR_BVR_WCR_WVR(6),
 	/* DBGVCR */
-	{ Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32 },
+	{ Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32, NULL, cp14_DBGVCR },
 	DBG_BCR_BVR_WCR_WVR(7),
 	DBG_BCR_BVR_WCR_WVR(8),
 	DBG_BCR_BVR_WCR_WVR(9),