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

Pull kvm fixes from Paolo Bonzini:
 "Two larger x86 series:

   - Redo incorrect fix for SEV/SMAP erratum

   - Windows 11 Hyper-V workaround

  Other x86 changes:

   - Various x86 cleanups

   - Re-enable access_tracking_perf_test

   - Fix for #GP handling on SVM

   - Fix for CPUID leaf 0Dh in KVM_GET_SUPPORTED_CPUID

   - Fix for ICEBP in interrupt shadow

   - Avoid false-positive RCU splat

   - Enable Enlightened MSR-Bitmap support for real

  ARM:

   - Correctly update the shadow register on exception injection when
     running in nVHE mode

   - Correctly use the mm_ops indirection when performing cache
     invalidation from the page-table walker

   - Restrict the vgic-v3 workaround for SEIS to the two known broken
     implementations

  Generic code changes:

   - Dead code cleanup"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (43 commits)
  KVM: eventfd: Fix false positive RCU usage warning
  KVM: nVMX: Allow VMREAD when Enlightened VMCS is in use
  KVM: nVMX: Implement evmcs_field_offset() suitable for handle_vmread()
  KVM: nVMX: Rename vmcs_to_field_offset{,_table}
  KVM: nVMX: eVMCS: Filter out VM_EXIT_SAVE_VMX_PREEMPTION_TIMER
  KVM: nVMX: Also filter MSR_IA32_VMX_TRUE_PINBASED_CTLS when eVMCS
  selftests: kvm: check dynamic bits against KVM_X86_XCOMP_GUEST_SUPP
  KVM: x86: add system attribute to retrieve full set of supported xsave states
  KVM: x86: Add a helper to retrieve userspace address from kvm_device_attr
  selftests: kvm: move vm_xsave_req_perm call to amx_test
  KVM: x86: Sync the states size with the XCR0/IA32_XSS at, any time
  KVM: x86: Update vCPU's runtime CPUID on write to MSR_IA32_XSS
  KVM: x86: Keep MSR_IA32_XSS unchanged for INIT
  KVM: x86: Free kvm_cpuid_entry2 array on post-KVM_RUN KVM_SET_CPUID{,2}
  KVM: nVMX: WARN on any attempt to allocate shadow VMCS for vmcs02
  KVM: selftests: Don't skip L2's VMCALL in SMM test for SVM guest
  KVM: x86: Check .flags in kvm_cpuid_check_equal() too
  KVM: x86: Forcibly leave nested virt when SMM state is toggled
  KVM: SVM: drop unnecessary code in svm_hv_vmcb_dirty_nested_enlightenments()
  KVM: SVM: hyper-v: Enable Enlightened MSR-Bitmap support for real
  ...

1 files changed, 54 insertions, 28 deletions

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index f235f77cbc03..ba34e94049c7 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -7,6 +7,7 @@
 #include <asm/mmu_context.h>
 
 #include "cpuid.h"
+#include "evmcs.h"
 #include "hyperv.h"
 #include "mmu.h"
 #include "nested.h"
@@ -4851,18 +4852,20 @@ static struct vmcs *alloc_shadow_vmcs(struct kvm_vcpu *vcpu)
 	struct loaded_vmcs *loaded_vmcs = vmx->loaded_vmcs;
 
 	/*
-	 * We should allocate a shadow vmcs for vmcs01 only when L1
-	 * executes VMXON and free it when L1 executes VMXOFF.
-	 * As it is invalid to execute VMXON twice, we shouldn't reach
-	 * here when vmcs01 already have an allocated shadow vmcs.
+	 * KVM allocates a shadow VMCS only when L1 executes VMXON and frees it
+	 * when L1 executes VMXOFF or the vCPU is forced out of nested
+	 * operation.  VMXON faults if the CPU is already post-VMXON, so it
+	 * should be impossible to already have an allocated shadow VMCS.  KVM
+	 * doesn't support virtualization of VMCS shadowing, so vmcs01 should
+	 * always be the loaded VMCS.
 	 */
-	WARN_ON(loaded_vmcs == &vmx->vmcs01 && loaded_vmcs->shadow_vmcs);
+	if (WARN_ON(loaded_vmcs != &vmx->vmcs01 || loaded_vmcs->shadow_vmcs))
+		return loaded_vmcs->shadow_vmcs;
+
+	loaded_vmcs->shadow_vmcs = alloc_vmcs(true);
+	if (loaded_vmcs->shadow_vmcs)
+		vmcs_clear(loaded_vmcs->shadow_vmcs);
 
-	if (!loaded_vmcs->shadow_vmcs) {
-		loaded_vmcs->shadow_vmcs = alloc_vmcs(true);
-		if (loaded_vmcs->shadow_vmcs)
-			vmcs_clear(loaded_vmcs->shadow_vmcs);
-	}
 	return loaded_vmcs->shadow_vmcs;
 }
 
@@ -5099,27 +5102,49 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	/*
-	 * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA,
-	 * any VMREAD sets the ALU flags for VMfailInvalid.
-	 */
-	if (vmx->nested.current_vmptr == INVALID_GPA ||
-	    (is_guest_mode(vcpu) &&
-	     get_vmcs12(vcpu)->vmcs_link_pointer == INVALID_GPA))
-		return nested_vmx_failInvalid(vcpu);
-
 	/* Decode instruction info and find the field to read */
 	field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf));
 
-	offset = vmcs_field_to_offset(field);
-	if (offset < 0)
-		return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
+	if (!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) {
+		/*
+		 * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA,
+		 * any VMREAD sets the ALU flags for VMfailInvalid.
+		 */
+		if (vmx->nested.current_vmptr == INVALID_GPA ||
+		    (is_guest_mode(vcpu) &&
+		     get_vmcs12(vcpu)->vmcs_link_pointer == INVALID_GPA))
+			return nested_vmx_failInvalid(vcpu);
 
-	if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field))
-		copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
+		offset = get_vmcs12_field_offset(field);
+		if (offset < 0)
+			return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
+
+		if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field))
+			copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
 
-	/* Read the field, zero-extended to a u64 value */
-	value = vmcs12_read_any(vmcs12, field, offset);
+		/* Read the field, zero-extended to a u64 value */
+		value = vmcs12_read_any(vmcs12, field, offset);
+	} else {
+		/*
+		 * Hyper-V TLFS (as of 6.0b) explicitly states, that while an
+		 * enlightened VMCS is active VMREAD/VMWRITE instructions are
+		 * unsupported. Unfortunately, certain versions of Windows 11
+		 * don't comply with this requirement which is not enforced in
+		 * genuine Hyper-V. Allow VMREAD from an enlightened VMCS as a
+		 * workaround, as misbehaving guests will panic on VM-Fail.
+		 * Note, enlightened VMCS is incompatible with shadow VMCS so
+		 * all VMREADs from L2 should go to L1.
+		 */
+		if (WARN_ON_ONCE(is_guest_mode(vcpu)))
+			return nested_vmx_failInvalid(vcpu);
+
+		offset = evmcs_field_offset(field, NULL);
+		if (offset < 0)
+			return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
+
+		/* Read the field, zero-extended to a u64 value */
+		value = evmcs_read_any(vmx->nested.hv_evmcs, field, offset);
+	}
 
 	/*
 	 * Now copy part of this value to register or memory, as requested.
@@ -5214,7 +5239,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
 
 	field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf));
 
-	offset = vmcs_field_to_offset(field);
+	offset = get_vmcs12_field_offset(field);
 	if (offset < 0)
 		return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
 
@@ -6462,7 +6487,7 @@ static u64 nested_vmx_calc_vmcs_enum_msr(void)
 	max_idx = 0;
 	for (i = 0; i < nr_vmcs12_fields; i++) {
 		/* The vmcs12 table is very, very sparsely populated. */
-		if (!vmcs_field_to_offset_table[i])
+		if (!vmcs12_field_offsets[i])
 			continue;
 
 		idx = vmcs_field_index(VMCS12_IDX_TO_ENC(i));
@@ -6771,6 +6796,7 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
 }
 
 struct kvm_x86_nested_ops vmx_nested_ops = {
+	.leave_nested = vmx_leave_nested,
 	.check_events = vmx_check_nested_events,
 	.hv_timer_pending = nested_vmx_preemption_timer_pending,
 	.triple_fault = nested_vmx_triple_fault,