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

8 files changed, 31 insertions, 32 deletions

diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 812e9b4c1114..950afebfba88 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -32,6 +32,7 @@
 #define KVM_FEATURE_POLL_CONTROL	12
 #define KVM_FEATURE_PV_SCHED_YIELD	13
 #define KVM_FEATURE_ASYNC_PF_INT	14
+#define KVM_FEATURE_MSI_EXT_DEST_ID	15
 
 #define KVM_HINTS_REALTIME      0
 
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 17587f496ec7..1f96adff8dc4 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -225,7 +225,7 @@ static gfn_t get_mmio_spte_gfn(u64 spte)
 {
 	u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask;
 
-	gpa |= (spte >> shadow_nonpresent_or_rsvd_mask_len)
+	gpa |= (spte >> SHADOW_NONPRESENT_OR_RSVD_MASK_LEN)
 	       & shadow_nonpresent_or_rsvd_mask;
 
 	return gpa >> PAGE_SHIFT;
@@ -591,15 +591,15 @@ static u64 mmu_spte_get_lockless(u64 *sptep)
 static u64 restore_acc_track_spte(u64 spte)
 {
 	u64 new_spte = spte;
-	u64 saved_bits = (spte >> shadow_acc_track_saved_bits_shift)
-			 & shadow_acc_track_saved_bits_mask;
+	u64 saved_bits = (spte >> SHADOW_ACC_TRACK_SAVED_BITS_SHIFT)
+			 & SHADOW_ACC_TRACK_SAVED_BITS_MASK;
 
 	WARN_ON_ONCE(spte_ad_enabled(spte));
 	WARN_ON_ONCE(!is_access_track_spte(spte));
 
 	new_spte &= ~shadow_acc_track_mask;
-	new_spte &= ~(shadow_acc_track_saved_bits_mask <<
-		      shadow_acc_track_saved_bits_shift);
+	new_spte &= ~(SHADOW_ACC_TRACK_SAVED_BITS_MASK <<
+		      SHADOW_ACC_TRACK_SAVED_BITS_SHIFT);
 	new_spte |= saved_bits;
 
 	return new_spte;
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index d9c5665a55e9..fcac2cac78fe 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -55,7 +55,7 @@ u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access)
 	mask |= shadow_mmio_value | access;
 	mask |= gpa | shadow_nonpresent_or_rsvd_mask;
 	mask |= (gpa & shadow_nonpresent_or_rsvd_mask)
-		<< shadow_nonpresent_or_rsvd_mask_len;
+		<< SHADOW_NONPRESENT_OR_RSVD_MASK_LEN;
 
 	return mask;
 }
@@ -231,12 +231,12 @@ u64 mark_spte_for_access_track(u64 spte)
 		  !spte_can_locklessly_be_made_writable(spte),
 		  "kvm: Writable SPTE is not locklessly dirty-trackable\n");
 
-	WARN_ONCE(spte & (shadow_acc_track_saved_bits_mask <<
-			  shadow_acc_track_saved_bits_shift),
+	WARN_ONCE(spte & (SHADOW_ACC_TRACK_SAVED_BITS_MASK <<
+			  SHADOW_ACC_TRACK_SAVED_BITS_SHIFT),
 		  "kvm: Access Tracking saved bit locations are not zero\n");
 
-	spte |= (spte & shadow_acc_track_saved_bits_mask) <<
-		shadow_acc_track_saved_bits_shift;
+	spte |= (spte & SHADOW_ACC_TRACK_SAVED_BITS_MASK) <<
+		SHADOW_ACC_TRACK_SAVED_BITS_SHIFT;
 	spte &= ~shadow_acc_track_mask;
 
 	return spte;
@@ -245,7 +245,7 @@ u64 mark_spte_for_access_track(u64 spte)
 void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 access_mask)
 {
 	BUG_ON((u64)(unsigned)access_mask != access_mask);
-	WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask << shadow_nonpresent_or_rsvd_mask_len));
+	WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask << SHADOW_NONPRESENT_OR_RSVD_MASK_LEN));
 	WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask);
 	shadow_mmio_value = mmio_value | SPTE_MMIO_MASK;
 	shadow_mmio_access_mask = access_mask;
@@ -306,9 +306,9 @@ void kvm_mmu_reset_all_pte_masks(void)
 	low_phys_bits = boot_cpu_data.x86_phys_bits;
 	if (boot_cpu_has_bug(X86_BUG_L1TF) &&
 	    !WARN_ON_ONCE(boot_cpu_data.x86_cache_bits >=
-			  52 - shadow_nonpresent_or_rsvd_mask_len)) {
+			  52 - SHADOW_NONPRESENT_OR_RSVD_MASK_LEN)) {
 		low_phys_bits = boot_cpu_data.x86_cache_bits
-			- shadow_nonpresent_or_rsvd_mask_len;
+			- SHADOW_NONPRESENT_OR_RSVD_MASK_LEN;
 		shadow_nonpresent_or_rsvd_mask =
 			rsvd_bits(low_phys_bits, boot_cpu_data.x86_cache_bits - 1);
 	}
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 4ecf40e0b8fe..5c75a451c000 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -105,19 +105,19 @@ extern u64 __read_mostly shadow_acc_track_mask;
 extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
 
 /*
+ * The number of high-order 1 bits to use in the mask above.
+ */
+#define SHADOW_NONPRESENT_OR_RSVD_MASK_LEN 5
+
+/*
  * The mask/shift to use for saving the original R/X bits when marking the PTE
  * as not-present for access tracking purposes. We do not save the W bit as the
  * PTEs being access tracked also need to be dirty tracked, so the W bit will be
  * restored only when a write is attempted to the page.
  */
-static const u64 shadow_acc_track_saved_bits_mask = PT64_EPT_READABLE_MASK |
-						    PT64_EPT_EXECUTABLE_MASK;
-static const u64 shadow_acc_track_saved_bits_shift = PT64_SECOND_AVAIL_BITS_SHIFT;
-
-/*
- * The number of high-order 1 bits to use in the mask above.
- */
-static const u64 shadow_nonpresent_or_rsvd_mask_len = 5;
+#define SHADOW_ACC_TRACK_SAVED_BITS_MASK (PT64_EPT_READABLE_MASK | \
+					  PT64_EPT_EXECUTABLE_MASK)
+#define SHADOW_ACC_TRACK_SAVED_BITS_SHIFT PT64_SECOND_AVAIL_BITS_SHIFT
 
 /*
  * In some cases, we need to preserve the GFN of a non-present or reserved
diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c
index e5325bd0f304..f3199bb02f22 100644
--- a/arch/x86/kvm/vmx/evmcs.c
+++ b/arch/x86/kvm/vmx/evmcs.c
@@ -297,14 +297,13 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = {
 };
 const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1);
 
-void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf)
+__init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf)
 {
 	vmcs_conf->pin_based_exec_ctrl &= ~EVMCS1_UNSUPPORTED_PINCTRL;
 	vmcs_conf->cpu_based_2nd_exec_ctrl &= ~EVMCS1_UNSUPPORTED_2NDEXEC;
 
 	vmcs_conf->vmexit_ctrl &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
 	vmcs_conf->vmentry_ctrl &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
-
 }
 #endif
 
diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h
index e5f7a7ebf27d..bd41d9462355 100644
--- a/arch/x86/kvm/vmx/evmcs.h
+++ b/arch/x86/kvm/vmx/evmcs.h
@@ -185,7 +185,7 @@ static inline void evmcs_load(u64 phys_addr)
 	vp_ap->enlighten_vmentry = 1;
 }
 
-void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf);
+__init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf);
 #else /* !IS_ENABLED(CONFIG_HYPERV) */
 static inline void evmcs_write64(unsigned long field, u64 value) {}
 static inline void evmcs_write32(unsigned long field, u32 value) {}
@@ -194,7 +194,6 @@ static inline u64 evmcs_read64(unsigned long field) { return 0; }
 static inline u32 evmcs_read32(unsigned long field) { return 0; }
 static inline u16 evmcs_read16(unsigned long field) { return 0; }
 static inline void evmcs_load(u64 phys_addr) {}
-static inline void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) {}
 static inline void evmcs_touch_msr_bitmap(void) {}
 #endif /* IS_ENABLED(CONFIG_HYPERV) */
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index d14c94d0aff1..47b8357b9751 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2560,8 +2560,10 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 	vmcs_conf->vmexit_ctrl         = _vmexit_control;
 	vmcs_conf->vmentry_ctrl        = _vmentry_control;
 
-	if (static_branch_unlikely(&enable_evmcs))
+#if IS_ENABLED(CONFIG_HYPERV)
+	if (enlightened_vmcs)
 		evmcs_sanitize_exec_ctrls(vmcs_conf);
+#endif
 
 	return 0;
 }
@@ -6834,7 +6836,6 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx;
-	unsigned long *msr_bitmap;
 	int i, cpu, err;
 
 	BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0);
@@ -6894,7 +6895,6 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 	bitmap_fill(vmx->shadow_msr_intercept.read, MAX_POSSIBLE_PASSTHROUGH_MSRS);
 	bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS);
 
-	msr_bitmap = vmx->vmcs01.msr_bitmap;
 	vmx_disable_intercept_for_msr(vcpu, MSR_IA32_TSC, MSR_TYPE_R);
 	vmx_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW);
 	vmx_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 397f599b20e5..f5ede41bf9e6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -265,13 +265,13 @@ static int kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr,
 
 	if (ignore_msrs) {
 		if (report_ignored_msrs)
-			vcpu_unimpl(vcpu, "ignored %s: 0x%x data 0x%llx\n",
-				    op, msr, data);
+			kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n",
+				      op, msr, data);
 		/* Mask the error */
 		return 0;
 	} else {
-		vcpu_debug_ratelimited(vcpu, "unhandled %s: 0x%x data 0x%llx\n",
-				       op, msr, data);
+		kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n",
+				      op, msr, data);
 		return -ENOENT;
 	}
 }