Merge tag 'v5.17-rc2' into char-misc-next

We need the char/misc fixes in here as well.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

16 files changed, 416 insertions, 186 deletions

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 3902c28fb6cb..28be02adc669 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -133,6 +133,7 @@ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2
 		orig = &vcpu->arch.cpuid_entries[i];
 		if (e2[i].function != orig->function ||
 		    e2[i].index != orig->index ||
+		    e2[i].flags != orig->flags ||
 		    e2[i].eax != orig->eax || e2[i].ebx != orig->ebx ||
 		    e2[i].ecx != orig->ecx || e2[i].edx != orig->edx)
 			return -EINVAL;
@@ -196,10 +197,26 @@ void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
 		vcpu->arch.pv_cpuid.features = best->eax;
 }
 
+/*
+ * Calculate guest's supported XCR0 taking into account guest CPUID data and
+ * supported_xcr0 (comprised of host configuration and KVM_SUPPORTED_XCR0).
+ */
+static u64 cpuid_get_supported_xcr0(struct kvm_cpuid_entry2 *entries, int nent)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = cpuid_entry2_find(entries, nent, 0xd, 0);
+	if (!best)
+		return 0;
+
+	return (best->eax | ((u64)best->edx << 32)) & supported_xcr0;
+}
+
 static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entries,
 				       int nent)
 {
 	struct kvm_cpuid_entry2 *best;
+	u64 guest_supported_xcr0 = cpuid_get_supported_xcr0(entries, nent);
 
 	best = cpuid_entry2_find(entries, nent, 1, 0);
 	if (best) {
@@ -238,6 +255,21 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e
 					   vcpu->arch.ia32_misc_enable_msr &
 					   MSR_IA32_MISC_ENABLE_MWAIT);
 	}
+
+	/*
+	 * Bits 127:0 of the allowed SECS.ATTRIBUTES (CPUID.0x12.0x1) enumerate
+	 * the supported XSAVE Feature Request Mask (XFRM), i.e. the enclave's
+	 * requested XCR0 value.  The enclave's XFRM must be a subset of XCRO
+	 * at the time of EENTER, thus adjust the allowed XFRM by the guest's
+	 * supported XCR0.  Similar to XCR0 handling, FP and SSE are forced to
+	 * '1' even on CPUs that don't support XSAVE.
+	 */
+	best = cpuid_entry2_find(entries, nent, 0x12, 0x1);
+	if (best) {
+		best->ecx &= guest_supported_xcr0 & 0xffffffff;
+		best->edx &= guest_supported_xcr0 >> 32;
+		best->ecx |= XFEATURE_MASK_FPSSE;
+	}
 }
 
 void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
@@ -261,27 +293,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		kvm_apic_set_version(vcpu);
 	}
 
-	best = kvm_find_cpuid_entry(vcpu, 0xD, 0);
-	if (!best)
-		vcpu->arch.guest_supported_xcr0 = 0;
-	else
-		vcpu->arch.guest_supported_xcr0 =
-			(best->eax | ((u64)best->edx << 32)) & supported_xcr0;
-
-	/*
-	 * Bits 127:0 of the allowed SECS.ATTRIBUTES (CPUID.0x12.0x1) enumerate
-	 * the supported XSAVE Feature Request Mask (XFRM), i.e. the enclave's
-	 * requested XCR0 value.  The enclave's XFRM must be a subset of XCRO
-	 * at the time of EENTER, thus adjust the allowed XFRM by the guest's
-	 * supported XCR0.  Similar to XCR0 handling, FP and SSE are forced to
-	 * '1' even on CPUs that don't support XSAVE.
-	 */
-	best = kvm_find_cpuid_entry(vcpu, 0x12, 0x1);
-	if (best) {
-		best->ecx &= vcpu->arch.guest_supported_xcr0 & 0xffffffff;
-		best->edx &= vcpu->arch.guest_supported_xcr0 >> 32;
-		best->ecx |= XFEATURE_MASK_FPSSE;
-	}
+	vcpu->arch.guest_supported_xcr0 =
+		cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent);
 
 	kvm_update_pv_runtime(vcpu);
 
@@ -346,8 +359,14 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
 	 * KVM_SET_CPUID{,2} again. To support this legacy behavior, check
 	 * whether the supplied CPUID data is equal to what's already set.
 	 */
-	if (vcpu->arch.last_vmentry_cpu != -1)
-		return kvm_cpuid_check_equal(vcpu, e2, nent);
+	if (vcpu->arch.last_vmentry_cpu != -1) {
+		r = kvm_cpuid_check_equal(vcpu, e2, nent);
+		if (r)
+			return r;
+
+		kvfree(e2);
+		return 0;
+	}
 
 	r = kvm_check_cpuid(vcpu, e2, nent);
 	if (r)
@@ -887,13 +906,14 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		}
 		break;
 	case 0xd: {
-		u64 guest_perm = xstate_get_guest_group_perm();
+		u64 permitted_xcr0 = supported_xcr0 & xstate_get_guest_group_perm();
+		u64 permitted_xss = supported_xss;
 
-		entry->eax &= supported_xcr0 & guest_perm;
-		entry->ebx = xstate_required_size(supported_xcr0, false);
+		entry->eax &= permitted_xcr0;
+		entry->ebx = xstate_required_size(permitted_xcr0, false);
 		entry->ecx = entry->ebx;
-		entry->edx &= (supported_xcr0 & guest_perm) >> 32;
-		if (!supported_xcr0)
+		entry->edx &= permitted_xcr0 >> 32;
+		if (!permitted_xcr0)
 			break;
 
 		entry = do_host_cpuid(array, function, 1);
@@ -902,20 +922,20 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 
 		cpuid_entry_override(entry, CPUID_D_1_EAX);
 		if (entry->eax & (F(XSAVES)|F(XSAVEC)))
-			entry->ebx = xstate_required_size(supported_xcr0 | supported_xss,
+			entry->ebx = xstate_required_size(permitted_xcr0 | permitted_xss,
 							  true);
 		else {
-			WARN_ON_ONCE(supported_xss != 0);
+			WARN_ON_ONCE(permitted_xss != 0);
 			entry->ebx = 0;
 		}
-		entry->ecx &= supported_xss;
-		entry->edx &= supported_xss >> 32;
+		entry->ecx &= permitted_xss;
+		entry->edx &= permitted_xss >> 32;
 
 		for (i = 2; i < 64; ++i) {
 			bool s_state;
-			if (supported_xcr0 & BIT_ULL(i))
+			if (permitted_xcr0 & BIT_ULL(i))
 				s_state = false;
-			else if (supported_xss & BIT_ULL(i))
+			else if (permitted_xss & BIT_ULL(i))
 				s_state = true;
 			else
 				continue;
@@ -929,7 +949,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 			 * invalid sub-leafs.  Only valid sub-leafs should
 			 * reach this point, and they should have a non-zero
 			 * save state size.  Furthermore, check whether the
-			 * processor agrees with supported_xcr0/supported_xss
+			 * processor agrees with permitted_xcr0/permitted_xss
 			 * on whether this is an XCR0- or IA32_XSS-managed area.
 			 */
 			if (WARN_ON_ONCE(!entry->eax || (entry->ecx & 0x1) != s_state)) {
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index baca9fa37a91..4662469240bc 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2629,7 +2629,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
 	kvm_apic_set_version(vcpu);
 
 	apic_update_ppr(apic);
-	hrtimer_cancel(&apic->lapic_timer.timer);
+	cancel_apic_timer(apic);
 	apic->lapic_timer.expired_tscdeadline = 0;
 	apic_update_lvtt(apic);
 	apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0));
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index cf206855ebf0..1218b5a342fc 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -983,9 +983,9 @@ void svm_free_nested(struct vcpu_svm *svm)
 /*
  * Forcibly leave nested mode in order to be able to reset the VCPU later on.
  */
-void svm_leave_nested(struct vcpu_svm *svm)
+void svm_leave_nested(struct kvm_vcpu *vcpu)
 {
-	struct kvm_vcpu *vcpu = &svm->vcpu;
+	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if (is_guest_mode(vcpu)) {
 		svm->nested.nested_run_pending = 0;
@@ -1411,7 +1411,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 	if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE)) {
-		svm_leave_nested(svm);
+		svm_leave_nested(vcpu);
 		svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET));
 		return 0;
 	}
@@ -1478,7 +1478,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	 */
 
 	if (is_guest_mode(vcpu))
-		svm_leave_nested(svm);
+		svm_leave_nested(vcpu);
 	else
 		svm->nested.vmcb02.ptr->save = svm->vmcb01.ptr->save;
 
@@ -1532,6 +1532,7 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
 }
 
 struct kvm_x86_nested_ops svm_nested_ops = {
+	.leave_nested = svm_leave_nested,
 	.check_events = svm_check_nested_events,
 	.triple_fault = nested_svm_triple_fault,
 	.get_nested_state_pages = svm_get_nested_state_pages,
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 6a22798eaaee..17b53457d866 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2100,8 +2100,13 @@ void __init sev_hardware_setup(void)
 	if (!sev_enabled || !npt_enabled)
 		goto out;
 
-	/* Does the CPU support SEV? */
-	if (!boot_cpu_has(X86_FEATURE_SEV))
+	/*
+	 * SEV must obviously be supported in hardware.  Sanity check that the
+	 * CPU supports decode assists, which is mandatory for SEV guests to
+	 * support instruction emulation.
+	 */
+	if (!boot_cpu_has(X86_FEATURE_SEV) ||
+	    WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS)))
 		goto out;
 
 	/* Retrieve SEV CPUID information */
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 2c99b18d76c0..6d97629655e3 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -290,7 +290,7 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 
 	if ((old_efer & EFER_SVME) != (efer & EFER_SVME)) {
 		if (!(efer & EFER_SVME)) {
-			svm_leave_nested(svm);
+			svm_leave_nested(vcpu);
 			svm_set_gif(svm, true);
 			/* #GP intercept is still needed for vmware backdoor */
 			if (!enable_vmware_backdoor)
@@ -312,7 +312,11 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 				return ret;
 			}
 
-			if (svm_gp_erratum_intercept)
+			/*
+			 * Never intercept #GP for SEV guests, KVM can't
+			 * decrypt guest memory to workaround the erratum.
+			 */
+			if (svm_gp_erratum_intercept && !sev_guest(vcpu->kvm))
 				set_exception_intercept(svm, GP_VECTOR);
 		}
 	}
@@ -1010,9 +1014,10 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
 	 * Guest access to VMware backdoor ports could legitimately
 	 * trigger #GP because of TSS I/O permission bitmap.
 	 * We intercept those #GP and allow access to them anyway
-	 * as VMware does.
+	 * as VMware does.  Don't intercept #GP for SEV guests as KVM can't
+	 * decrypt guest memory to decode the faulting instruction.
 	 */
-	if (enable_vmware_backdoor)
+	if (enable_vmware_backdoor && !sev_guest(vcpu->kvm))
 		set_exception_intercept(svm, GP_VECTOR);
 
 	svm_set_intercept(svm, INTERCEPT_INTR);
@@ -2091,10 +2096,6 @@ static int gp_interception(struct kvm_vcpu *vcpu)
 	if (error_code)
 		goto reinject;
 
-	/* All SVM instructions expect page aligned RAX */
-	if (svm->vmcb->save.rax & ~PAGE_MASK)
-		goto reinject;
-
 	/* Decode the instruction for usage later */
 	if (x86_decode_emulated_instruction(vcpu, 0, NULL, 0) != EMULATION_OK)
 		goto reinject;
@@ -2112,8 +2113,13 @@ static int gp_interception(struct kvm_vcpu *vcpu)
 		if (!is_guest_mode(vcpu))
 			return kvm_emulate_instruction(vcpu,
 				EMULTYPE_VMWARE_GP | EMULTYPE_NO_DECODE);
-	} else
+	} else {
+		/* All SVM instructions expect page aligned RAX */
+		if (svm->vmcb->save.rax & ~PAGE_MASK)
+			goto reinject;
+
 		return emulate_svm_instr(vcpu, opcode);
+	}
 
 reinject:
 	kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
@@ -4252,79 +4258,140 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu)
 	}
 }
 
-static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, void *insn, int insn_len)
+static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
+					void *insn, int insn_len)
 {
 	bool smep, smap, is_user;
 	unsigned long cr4;
+	u64 error_code;
+
+	/* Emulation is always possible when KVM has access to all guest state. */
+	if (!sev_guest(vcpu->kvm))
+		return true;
+
+	/* #UD and #GP should never be intercepted for SEV guests. */
+	WARN_ON_ONCE(emul_type & (EMULTYPE_TRAP_UD |
+				  EMULTYPE_TRAP_UD_FORCED |
+				  EMULTYPE_VMWARE_GP));
 
 	/*
-	 * When the guest is an SEV-ES guest, emulation is not possible.
+	 * Emulation is impossible for SEV-ES guests as KVM doesn't have access
+	 * to guest register state.
 	 */
 	if (sev_es_guest(vcpu->kvm))
 		return false;
 
 	/*
+	 * Emulation is possible if the instruction is already decoded, e.g.
+	 * when completing I/O after returning from userspace.
+	 */
+	if (emul_type & EMULTYPE_NO_DECODE)
+		return true;
+
+	/*
+	 * Emulation is possible for SEV guests if and only if a prefilled
+	 * buffer containing the bytes of the intercepted instruction is
+	 * available. SEV guest memory is encrypted with a guest specific key
+	 * and cannot be decrypted by KVM, i.e. KVM would read cyphertext and
+	 * decode garbage.
+	 *
+	 * Inject #UD if KVM reached this point without an instruction buffer.
+	 * In practice, this path should never be hit by a well-behaved guest,
+	 * e.g. KVM doesn't intercept #UD or #GP for SEV guests, but this path
+	 * is still theoretically reachable, e.g. via unaccelerated fault-like
+	 * AVIC access, and needs to be handled by KVM to avoid putting the
+	 * guest into an infinite loop.   Injecting #UD is somewhat arbitrary,
+	 * but its the least awful option given lack of insight into the guest.
+	 */
+	if (unlikely(!insn)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return false;
+	}
+
+	/*
+	 * Emulate for SEV guests if the insn buffer is not empty.  The buffer
+	 * will be empty if the DecodeAssist microcode cannot fetch bytes for
+	 * the faulting instruction because the code fetch itself faulted, e.g.
+	 * the guest attempted to fetch from emulated MMIO or a guest page
+	 * table used to translate CS:RIP resides in emulated MMIO.
+	 */
+	if (likely(insn_len))
+		return true;
+
+	/*
 	 * Detect and workaround Errata 1096 Fam_17h_00_0Fh.
 	 *
 	 * Errata:
-	 * When CPU raise #NPF on guest data access and vCPU CR4.SMAP=1, it is
-	 * possible that CPU microcode implementing DecodeAssist will fail
-	 * to read bytes of instruction which caused #NPF. In this case,
-	 * GuestIntrBytes field of the VMCB on a VMEXIT will incorrectly
-	 * return 0 instead of the correct guest instruction bytes.
-	 *
-	 * This happens because CPU microcode reading instruction bytes
-	 * uses a special opcode which attempts to read data using CPL=0
-	 * privileges. The microcode reads CS:RIP and if it hits a SMAP
-	 * fault, it gives up and returns no instruction bytes.
+	 * When CPU raises #NPF on guest data access and vCPU CR4.SMAP=1, it is
+	 * possible that CPU microcode implementing DecodeAssist will fail to
+	 * read guest memory at CS:RIP and vmcb.GuestIntrBytes will incorrectly
+	 * be '0'.  This happens because microcode reads CS:RIP using a _data_
+	 * loap uop with CPL=0 privileges.  If the load hits a SMAP #PF, ucode
+	 * gives up and does not fill the instruction bytes buffer.
 	 *
-	 * Detection:
-	 * We reach here in case CPU supports DecodeAssist, raised #NPF and
-	 * returned 0 in GuestIntrBytes field of the VMCB.
-	 * First, errata can only be triggered in case vCPU CR4.SMAP=1.
-	 * Second, if vCPU CR4.SMEP=1, errata could only be triggered
-	 * in case vCPU CPL==3 (Because otherwise guest would have triggered
-	 * a SMEP fault instead of #NPF).
-	 * Otherwise, vCPU CR4.SMEP=0, errata could be triggered by any vCPU CPL.
-	 * As most guests enable SMAP if they have also enabled SMEP, use above
-	 * logic in order to attempt minimize false-positive of detecting errata
-	 * while still preserving all cases semantic correctness.
+	 * As above, KVM reaches this point iff the VM is an SEV guest, the CPU
+	 * supports DecodeAssist, a #NPF was raised, KVM's page fault handler
+	 * triggered emulation (e.g. for MMIO), and the CPU returned 0 in the
+	 * GuestIntrBytes field of the VMCB.
 	 *
-	 * Workaround:
-	 * To determine what instruction the guest was executing, the hypervisor
-	 * will have to decode the instruction at the instruction pointer.
+	 * This does _not_ mean that the erratum has been encountered, as the
+	 * DecodeAssist will also fail if the load for CS:RIP hits a legitimate
+	 * #PF, e.g. if the guest attempt to execute from emulated MMIO and
+	 * encountered a reserved/not-present #PF.
 	 *
-	 * In non SEV guest, hypervisor will be able to read the guest
-	 * memory to decode the instruction pointer when insn_len is zero
-	 * so we return true to indicate that decoding is possible.
+	 * To hit the erratum, the following conditions must be true:
+	 *    1. CR4.SMAP=1 (obviously).
+	 *    2. CR4.SMEP=0 || CPL=3.  If SMEP=1 and CPL<3, the erratum cannot
+	 *       have been hit as the guest would have encountered a SMEP
+	 *       violation #PF, not a #NPF.
+	 *    3. The #NPF is not due to a code fetch, in which case failure to
+	 *       retrieve the instruction bytes is legitimate (see abvoe).
 	 *
-	 * But in the SEV guest, the guest memory is encrypted with the
-	 * guest specific key and hypervisor will not be able to decode the
-	 * instruction pointer so we will not able to workaround it. Lets
-	 * print the error and request to kill the guest.
+	 * In addition, don't apply the erratum workaround if the #NPF occurred
+	 * while translating guest page tables (see below).
 	 */
-	if (likely(!insn || insn_len))
-		return true;
-
-	/*
-	 * If RIP is invalid, go ahead with emulation which will cause an
-	 * internal error exit.
-	 */
-	if (!kvm_vcpu_gfn_to_memslot(vcpu, kvm_rip_read(vcpu) >> PAGE_SHIFT))
-		return true;
+	error_code = to_svm(vcpu)->vmcb->control.exit_info_1;
+	if (error_code & (PFERR_GUEST_PAGE_MASK | PFERR_FETCH_MASK))
+		goto resume_guest;
 
 	cr4 = kvm_read_cr4(vcpu);
 	smep = cr4 & X86_CR4_SMEP;
 	smap = cr4 & X86_CR4_SMAP;
 	is_user = svm_get_cpl(vcpu) == 3;
 	if (smap && (!smep || is_user)) {
-		if (!sev_guest(vcpu->kvm))
-			return true;
-
 		pr_err_ratelimited("KVM: SEV Guest triggered AMD Erratum 1096\n");
-		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+
+		/*
+		 * If the fault occurred in userspace, arbitrarily inject #GP
+		 * to avoid killing the guest and to hopefully avoid confusing
+		 * the guest kernel too much, e.g. injecting #PF would not be
+		 * coherent with respect to the guest's page tables.  Request
+		 * triple fault if the fault occurred in the kernel as there's
+		 * no fault that KVM can inject without confusing the guest.
+		 * In practice, the triple fault is moot as no sane SEV kernel
+		 * will execute from user memory while also running with SMAP=1.
+		 */
+		if (is_user)
+			kvm_inject_gp(vcpu, 0);
+		else
+			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 	}
 
+resume_guest:
+	/*
+	 * If the erratum was not hit, simply resume the guest and let it fault
+	 * again.  While awful, e.g. the vCPU may get stuck in an infinite loop
+	 * if the fault is at CPL=0, it's the lesser of all evils.  Exiting to
+	 * userspace will kill the guest, and letting the emulator read garbage
+	 * will yield random behavior and potentially corrupt the guest.
+	 *
+	 * Simply resuming the guest is technically not a violation of the SEV
+	 * architecture.  AMD's APM states that all code fetches and page table
+	 * accesses for SEV guest are encrypted, regardless of the C-Bit.  The
+	 * APM also states that encrypted accesses to MMIO are "ignored", but
+	 * doesn't explicitly define "ignored", i.e. doing nothing and letting
+	 * the guest spin is technically "ignoring" the access.
+	 */
 	return false;
 }
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 47ef8f4a9358..73525353e424 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -304,11 +304,6 @@ static inline void vmcb_mark_all_clean(struct vmcb *vmcb)
 			       & ~VMCB_ALWAYS_DIRTY_MASK;
 }
 
-static inline bool vmcb_is_clean(struct vmcb *vmcb, int bit)
-{
-	return (vmcb->control.clean & (1 << bit));
-}
-
 static inline void vmcb_mark_dirty(struct vmcb *vmcb, int bit)
 {
 	vmcb->control.clean &= ~(1 << bit);
@@ -525,7 +520,7 @@ static inline bool nested_exit_on_nmi(struct vcpu_svm *svm)
 
 int enter_svm_guest_mode(struct kvm_vcpu *vcpu,
 			 u64 vmcb_gpa, struct vmcb *vmcb12, bool from_vmrun);
-void svm_leave_nested(struct vcpu_svm *svm);
+void svm_leave_nested(struct kvm_vcpu *vcpu);
 void svm_free_nested(struct vcpu_svm *svm);
 int svm_allocate_nested(struct vcpu_svm *svm);
 int nested_svm_vmrun(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h
index c53b8bf8d013..489ca56212c6 100644
--- a/arch/x86/kvm/svm/svm_onhyperv.h
+++ b/arch/x86/kvm/svm/svm_onhyperv.h
@@ -46,6 +46,9 @@ static inline void svm_hv_init_vmcb(struct vmcb *vmcb)
 	if (npt_enabled &&
 	    ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB)
 		hve->hv_enlightenments_control.enlightened_npt_tlb = 1;
+
+	if (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)
+		hve->hv_enlightenments_control.msr_bitmap = 1;
 }
 
 static inline void svm_hv_hardware_setup(void)
@@ -83,14 +86,7 @@ static inline void svm_hv_vmcb_dirty_nested_enlightenments(
 	struct hv_enlightenments *hve =
 		(struct hv_enlightenments *)vmcb->control.reserved_sw;
 
-	/*
-	 * vmcb can be NULL if called during early vcpu init.
-	 * And its okay not to mark vmcb dirty during vcpu init
-	 * as we mark it dirty unconditionally towards end of vcpu
-	 * init phase.
-	 */
-	if (vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) &&
-	    hve->hv_enlightenments_control.msr_bitmap)
+	if (hve->hv_enlightenments_control.msr_bitmap)
 		vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS);
 }
 
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 959b59d13b5a..3f430e218375 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -54,7 +54,6 @@ struct nested_vmx_msrs {
 
 struct vmcs_config {
 	int size;
-	int order;
 	u32 basic_cap;
 	u32 revision_id;
 	u32 pin_based_exec_ctrl;
diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c
index ba6f99f584ac..87e3dc10edf4 100644
--- a/arch/x86/kvm/vmx/evmcs.c
+++ b/arch/x86/kvm/vmx/evmcs.c
@@ -12,8 +12,6 @@
 
 DEFINE_STATIC_KEY_FALSE(enable_evmcs);
 
-#if IS_ENABLED(CONFIG_HYPERV)
-
 #define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x)
 #define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \
 		{EVMCS1_OFFSET(name), clean_field}
@@ -296,6 +294,7 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = {
 };
 const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1);
 
+#if IS_ENABLED(CONFIG_HYPERV)
 __init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf)
 {
 	vmcs_conf->pin_based_exec_ctrl &= ~EVMCS1_UNSUPPORTED_PINCTRL;
@@ -362,6 +361,7 @@ void nested_evmcs_filter_control_msr(u32 msr_index, u64 *pdata)
 	case MSR_IA32_VMX_PROCBASED_CTLS2:
 		ctl_high &= ~EVMCS1_UNSUPPORTED_2NDEXEC;
 		break;
+	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
 	case MSR_IA32_VMX_PINBASED_CTLS:
 		ctl_high &= ~EVMCS1_UNSUPPORTED_PINCTRL;
 		break;
diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h
index 16731d2cf231..8d70f9aea94b 100644
--- a/arch/x86/kvm/vmx/evmcs.h
+++ b/arch/x86/kvm/vmx/evmcs.h
@@ -59,12 +59,12 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs);
 	 SECONDARY_EXEC_SHADOW_VMCS |					\
 	 SECONDARY_EXEC_TSC_SCALING |					\
 	 SECONDARY_EXEC_PAUSE_LOOP_EXITING)
-#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL (VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL					\
+	(VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL |				\
+	 VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)
 #define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
 #define EVMCS1_UNSUPPORTED_VMFUNC (VMX_VMFUNC_EPTP_SWITCHING)
 
-#if IS_ENABLED(CONFIG_HYPERV)
-
 struct evmcs_field {
 	u16 offset;
 	u16 clean_field;
@@ -73,26 +73,56 @@ struct evmcs_field {
 extern const struct evmcs_field vmcs_field_to_evmcs_1[];
 extern const unsigned int nr_evmcs_1_fields;
 
-static __always_inline int get_evmcs_offset(unsigned long field,
-					    u16 *clean_field)
+static __always_inline int evmcs_field_offset(unsigned long field,
+					      u16 *clean_field)
 {
 	unsigned int index = ROL16(field, 6);
 	const struct evmcs_field *evmcs_field;
 
-	if (unlikely(index >= nr_evmcs_1_fields)) {
-		WARN_ONCE(1, "KVM: accessing unsupported EVMCS field %lx\n",
-			  field);
+	if (unlikely(index >= nr_evmcs_1_fields))
 		return -ENOENT;
-	}
 
 	evmcs_field = &vmcs_field_to_evmcs_1[index];
 
+	/*
+	 * Use offset=0 to detect holes in eVMCS. This offset belongs to
+	 * 'revision_id' but this field has no encoding and is supposed to
+	 * be accessed directly.
+	 */
+	if (unlikely(!evmcs_field->offset))
+		return -ENOENT;
+
 	if (clean_field)
 		*clean_field = evmcs_field->clean_field;
 
 	return evmcs_field->offset;
 }
 
+static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs,
+				 unsigned long field, u16 offset)
+{
+	/*
+	 * vmcs12_read_any() doesn't care whether the supplied structure
+	 * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes
+	 * the exact offset of the required field, use it for convenience
+	 * here.
+	 */
+	return vmcs12_read_any((void *)evmcs, field, offset);
+}
+
+#if IS_ENABLED(CONFIG_HYPERV)
+
+static __always_inline int get_evmcs_offset(unsigned long field,
+					    u16 *clean_field)
+{
+	int offset = evmcs_field_offset(field, clean_field);
+
+	WARN_ONCE(offset < 0, "KVM: accessing unsupported EVMCS field %lx\n",
+		  field);
+
+	return offset;
+}
+
 static __always_inline void evmcs_write64(unsigned long field, u64 value)
 {
 	u16 clean_field;
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,
diff --git a/arch/x86/kvm/vmx/vmcs12.c b/arch/x86/kvm/vmx/vmcs12.c
index cab6ba7a5005..2251b60920f8 100644
--- a/arch/x86/kvm/vmx/vmcs12.c
+++ b/arch/x86/kvm/vmx/vmcs12.c
@@ -8,7 +8,7 @@
 	FIELD(number, name),						\
 	[ROL16(number##_HIGH, 6)] = VMCS12_OFFSET(name) + sizeof(u32)
 
-const unsigned short vmcs_field_to_offset_table[] = {
+const unsigned short vmcs12_field_offsets[] = {
 	FIELD(VIRTUA