Merge tag 'kvm-x86-misc-6.13' of https://github.com/kvm-x86/linux into HEAD

KVM x86 misc changes for 6.13

 - Clean up and optimize KVM's handling of writes to MSR_IA32_APICBASE.

 - Quirk KVM's misguided behavior of initialized certain feature MSRs to
   their maximum supported feature set, which can result in KVM creating
   invalid vCPU state.  E.g. initializing PERF_CAPABILITIES to a non-zero
   value results in the vCPU having invalid state if userspace hides PDCM
   from the guest, which can lead to save/restore failures.

 - Fix KVM's handling of non-canonical checks for vCPUs that support LA57
   to better follow the "architecture", in quotes because the actual
   behavior is poorly documented.  E.g. most MSR writes and descriptor
   table loads ignore CR4.LA57 and operate purely on whether the CPU
   supports LA57.

 - Bypass the register cache when querying CPL from kvm_sched_out(), as
   filling the cache from IRQ context is generally unsafe, and harden the
   cache accessors to try to prevent similar issues from occuring in the
   future.

 - Advertise AMD_IBPB_RET to userspace, and fix a related bug where KVM
   over-advertises SPEC_CTRL when trying to support cross-vendor VMs.

 - Minor cleanups

30 files changed, 419 insertions, 156 deletions

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index edc070c6e19b..061ec93d9ecb 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -8107,6 +8107,28 @@ KVM_X86_QUIRK_SLOT_ZAP_ALL          By default, for KVM_X86_DEFAULT_VM VMs, KVM
                                     or moved memslot isn't reachable, i.e KVM
                                     _may_ invalidate only SPTEs related to the
                                     memslot.
+
+KVM_X86_QUIRK_STUFF_FEATURE_MSRS    By default, at vCPU creation, KVM sets the
+                                    vCPU's MSR_IA32_PERF_CAPABILITIES (0x345),
+                                    MSR_IA32_ARCH_CAPABILITIES (0x10a),
+                                    MSR_PLATFORM_INFO (0xce), and all VMX MSRs
+                                    (0x480..0x492) to the maximal capabilities
+                                    supported by KVM.  KVM also sets
+                                    MSR_IA32_UCODE_REV (0x8b) to an arbitrary
+                                    value (which is different for Intel vs.
+                                    AMD).  Lastly, when guest CPUID is set (by
+                                    userspace), KVM modifies select VMX MSR
+                                    fields to force consistency between guest
+                                    CPUID and L2's effective ISA.  When this
+                                    quirk is disabled, KVM zeroes the vCPU's MSR
+                                    values (with two exceptions, see below),
+                                    i.e. treats the feature MSRs like CPUID
+                                    leaves and gives userspace full control of
+                                    the vCPU model definition.  This quirk does
+                                    not affect VMX MSRs CR0/CR4_FIXED1 (0x487
+                                    and 0x489), as KVM does now allow them to
+                                    be set by userspace (KVM sets them based on
+                                    guest CPUID, for safety purposes).
 =================================== ============================================
 
 7.32 KVM_CAP_MAX_VCPU_ID
diff --git a/Documentation/virt/kvm/x86/errata.rst b/Documentation/virt/kvm/x86/errata.rst
index 4116045a8744..37c79362a48f 100644
--- a/Documentation/virt/kvm/x86/errata.rst
+++ b/Documentation/virt/kvm/x86/errata.rst
@@ -33,6 +33,18 @@ Note however that any software (e.g ``WIN87EM.DLL``) expecting these features
 to be present likely predates these CPUID feature bits, and therefore
 doesn't know to check for them anyway.
 
+``KVM_SET_VCPU_EVENTS`` issue
+-----------------------------
+
+Invalid KVM_SET_VCPU_EVENTS input with respect to error codes *may* result in
+failed VM-Entry on Intel CPUs.  Pre-CET Intel CPUs require that exception
+injection through the VMCS correctly set the "error code valid" flag, e.g.
+require the flag be set when injecting a #GP, clear when injecting a #UD,
+clear when injecting a soft exception, etc.  Intel CPUs that enumerate
+IA32_VMX_BASIC[56] as '1' relax VMX's consistency checks, and AMD CPUs have no
+restrictions whatsoever.  KVM_SET_VCPU_EVENTS doesn't sanity check the vector
+versus "has_error_code", i.e. KVM's ABI follows AMD behavior.
+
 Nested virtualization features
 ------------------------------
 
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 861d080ed4c6..5aff7222e40f 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -34,6 +34,7 @@ KVM_X86_OP(set_msr)
 KVM_X86_OP(get_segment_base)
 KVM_X86_OP(get_segment)
 KVM_X86_OP(get_cpl)
+KVM_X86_OP(get_cpl_no_cache)
 KVM_X86_OP(set_segment)
 KVM_X86_OP(get_cs_db_l_bits)
 KVM_X86_OP(is_valid_cr0)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 433e65974e2b..3e8afc82ae2f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1655,6 +1655,7 @@ struct kvm_x86_ops {
 	void (*get_segment)(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg);
 	int (*get_cpl)(struct kvm_vcpu *vcpu);
+	int (*get_cpl_no_cache)(struct kvm_vcpu *vcpu);
 	void (*set_segment)(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg);
 	void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
@@ -2358,7 +2359,8 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
 	 KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT |	\
 	 KVM_X86_QUIRK_FIX_HYPERCALL_INSN |	\
 	 KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS |	\
-	 KVM_X86_QUIRK_SLOT_ZAP_ALL)
+	 KVM_X86_QUIRK_SLOT_ZAP_ALL |		\
+	 KVM_X86_QUIRK_STUFF_FEATURE_MSRS)
 
 /*
  * KVM previously used a u32 field in kvm_run to indicate the hypercall was
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index a8debbf2f702..88585c1de416 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -440,6 +440,7 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_FIX_HYPERCALL_INSN	(1 << 5)
 #define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS	(1 << 6)
 #define KVM_X86_QUIRK_SLOT_ZAP_ALL		(1 << 7)
+#define KVM_X86_QUIRK_STUFF_FEATURE_MSRS	(1 << 8)
 
 #define KVM_STATE_NESTED_FORMAT_VMX	0
 #define KVM_STATE_NESTED_FORMAT_SVM	1
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 41786b834b16..d695e7bc41ed 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -690,7 +690,9 @@ void kvm_set_cpu_caps(void)
 	kvm_cpu_cap_set(X86_FEATURE_TSC_ADJUST);
 	kvm_cpu_cap_set(X86_FEATURE_ARCH_CAPABILITIES);
 
-	if (boot_cpu_has(X86_FEATURE_IBPB) && boot_cpu_has(X86_FEATURE_IBRS))
+	if (boot_cpu_has(X86_FEATURE_AMD_IBPB_RET) &&
+	    boot_cpu_has(X86_FEATURE_AMD_IBPB) &&
+	    boot_cpu_has(X86_FEATURE_AMD_IBRS))
 		kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL);
 	if (boot_cpu_has(X86_FEATURE_STIBP))
 		kvm_cpu_cap_set(X86_FEATURE_INTEL_STIBP);
@@ -755,7 +757,7 @@ void kvm_set_cpu_caps(void)
 		F(CLZERO) | F(XSAVEERPTR) |
 		F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) |
 		F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON) |
-		F(AMD_PSFD)
+		F(AMD_PSFD) | F(AMD_IBPB_RET)
 	);
 
 	/*
@@ -763,8 +765,12 @@ void kvm_set_cpu_caps(void)
 	 * arch/x86/kernel/cpu/bugs.c is kind enough to
 	 * record that in cpufeatures so use them.
 	 */
-	if (boot_cpu_has(X86_FEATURE_IBPB))
+	if (boot_cpu_has(X86_FEATURE_IBPB)) {
 		kvm_cpu_cap_set(X86_FEATURE_AMD_IBPB);
+		if (boot_cpu_has(X86_FEATURE_SPEC_CTRL) &&
+		    !boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB))
+			kvm_cpu_cap_set(X86_FEATURE_AMD_IBPB_RET);
+	}
 	if (boot_cpu_has(X86_FEATURE_IBRS))
 		kvm_cpu_cap_set(X86_FEATURE_AMD_IBRS);
 	if (boot_cpu_has(X86_FEATURE_STIBP))
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 41697cca354e..c8dc66eddefd 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -2,7 +2,6 @@
 #ifndef ARCH_X86_KVM_CPUID_H
 #define ARCH_X86_KVM_CPUID_H
 
-#include "x86.h"
 #include "reverse_cpuid.h"
 #include <asm/cpu.h>
 #include <asm/processor.h>
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index e72aed25d721..60986f67c35a 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -651,9 +651,10 @@ static inline u8 ctxt_virt_addr_bits(struct x86_emulate_ctxt *ctxt)
 }
 
 static inline bool emul_is_noncanonical_address(u64 la,
-						struct x86_emulate_ctxt *ctxt)
+						struct x86_emulate_ctxt *ctxt,
+						unsigned int flags)
 {
-	return !__is_canonical_address(la, ctxt_virt_addr_bits(ctxt));
+	return !ctxt->ops->is_canonical_addr(ctxt, la, flags);
 }
 
 /*
@@ -1733,7 +1734,8 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
 		if (ret != X86EMUL_CONTINUE)
 			return ret;
 		if (emul_is_noncanonical_address(get_desc_base(&seg_desc) |
-						 ((u64)base3 << 32), ctxt))
+						 ((u64)base3 << 32), ctxt,
+						 X86EMUL_F_DT_LOAD))
 			return emulate_gp(ctxt, err_code);
 	}
 
@@ -2516,8 +2518,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
 		ss_sel = cs_sel + 8;
 		cs.d = 0;
 		cs.l = 1;
-		if (emul_is_noncanonical_address(rcx, ctxt) ||
-		    emul_is_noncanonical_address(rdx, ctxt))
+		if (emul_is_noncanonical_address(rcx, ctxt, 0) ||
+		    emul_is_noncanonical_address(rdx, ctxt, 0))
 			return emulate_gp(ctxt, 0);
 		break;
 	}
@@ -3494,7 +3496,8 @@ static int em_lgdt_lidt(struct x86_emulate_ctxt *ctxt, bool lgdt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 	if (ctxt->mode == X86EMUL_MODE_PROT64 &&
-	    emul_is_noncanonical_address(desc_ptr.address, ctxt))
+	    emul_is_noncanonical_address(desc_ptr.address, ctxt,
+					 X86EMUL_F_DT_LOAD))
 		return emulate_gp(ctxt, 0);
 	if (lgdt)
 		ctxt->ops->set_gdt(ctxt, &desc_ptr);
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index b1eb46e26b2e..36a8786db291 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -44,6 +44,18 @@ BUILD_KVM_GPR_ACCESSORS(r15, R15)
 #endif
 
 /*
+ * Using the register cache from interrupt context is generally not allowed, as
+ * caching a register and marking it available/dirty can't be done atomically,
+ * i.e. accesses from interrupt context may clobber state or read stale data if
+ * the vCPU task is in the process of updating the cache.  The exception is if
+ * KVM is handling a PMI IRQ/NMI VM-Exit, as that bound code sequence doesn't
+ * touch the cache, it runs after the cache is reset (post VM-Exit), and PMIs
+ * need to access several registers that are cacheable.
+ */
+#define kvm_assert_register_caching_allowed(vcpu)		\
+	lockdep_assert_once(in_task() || kvm_arch_pmi_in_guest(vcpu))
+
+/*
  * avail  dirty
  * 0	  0	  register in VMCS/VMCB
  * 0	  1	  *INVALID*
@@ -53,24 +65,28 @@ BUILD_KVM_GPR_ACCESSORS(r15, R15)
 static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu,
 					     enum kvm_reg reg)
 {
+	kvm_assert_register_caching_allowed(vcpu);
 	return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
 }
 
 static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu,
 					 enum kvm_reg reg)
 {
+	kvm_assert_register_caching_allowed(vcpu);
 	return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
 }
 
 static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu,
 					       enum kvm_reg reg)
 {
+	kvm_assert_register_caching_allowed(vcpu);
 	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
 }
 
 static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu,
 					   enum kvm_reg reg)
 {
+	kvm_assert_register_caching_allowed(vcpu);
 	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
 	__set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty);
 }
@@ -84,6 +100,7 @@ static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu,
 static __always_inline bool kvm_register_test_and_mark_available(struct kvm_vcpu *vcpu,
 								 enum kvm_reg reg)
 {
+	kvm_assert_register_caching_allowed(vcpu);
 	return arch___test_and_set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail);
 }
 
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 55a18e2f2dcd..10495fffb890 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -94,6 +94,8 @@ struct x86_instruction_info {
 #define X86EMUL_F_FETCH			BIT(1)
 #define X86EMUL_F_IMPLICIT		BIT(2)
 #define X86EMUL_F_INVLPG		BIT(3)
+#define X86EMUL_F_MSR			BIT(4)
+#define X86EMUL_F_DT_LOAD		BIT(5)
 
 struct x86_emulate_ops {
 	void (*vm_bugged)(struct x86_emulate_ctxt *ctxt);
@@ -235,6 +237,9 @@ struct x86_emulate_ops {
 
 	gva_t (*get_untagged_addr)(struct x86_emulate_ctxt *ctxt, gva_t addr,
 				   unsigned int flags);
+
+	bool (*is_canonical_addr)(struct x86_emulate_ctxt *ctxt, gva_t addr,
+				  unsigned int flags);
 };
 
 /* Type, address-of, and value of an instruction's operand. */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 65412640cfc7..59a64b703aad 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -382,7 +382,7 @@ enum {
 	DIRTY
 };
 
-void kvm_recalculate_apic_map(struct kvm *kvm)
+static void kvm_recalculate_apic_map(struct kvm *kvm)
 {
 	struct kvm_apic_map *new, *old = NULL;
 	struct kvm_vcpu *vcpu;
@@ -2577,7 +2577,7 @@ u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu)
 	return (tpr & 0xf0) >> 4;
 }
 
-void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
+static void __kvm_apic_set_base(struct kvm_vcpu *vcpu, u64 value)
 {
 	u64 old_value = vcpu->arch.apic_base;
 	struct kvm_lapic *apic = vcpu->arch.apic;
@@ -2625,6 +2625,31 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 	}
 }
 
+int kvm_apic_set_base(struct kvm_vcpu *vcpu, u64 value, bool host_initiated)
+{
+	enum lapic_mode old_mode = kvm_get_apic_mode(vcpu);
+	enum lapic_mode new_mode = kvm_apic_mode(value);
+
+	if (vcpu->arch.apic_base == value)
+		return 0;
+
+	u64 reserved_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu) | 0x2ff |
+		(guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE);
+
+	if ((value & reserved_bits) != 0 || new_mode == LAPIC_MODE_INVALID)
+		return 1;
+	if (!host_initiated) {
+		if (old_mode == LAPIC_MODE_X2APIC && new_mode == LAPIC_MODE_XAPIC)
+			return 1;
+		if (old_mode == LAPIC_MODE_DISABLED && new_mode == LAPIC_MODE_X2APIC)
+			return 1;
+	}
+
+	__kvm_apic_set_base(vcpu, value);
+	kvm_recalculate_apic_map(vcpu->kvm);
+	return 0;
+}
+
 void kvm_apic_update_apicv(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
@@ -2716,7 +2741,14 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 		msr_val = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE;
 		if (kvm_vcpu_is_reset_bsp(vcpu))
 			msr_val |= MSR_IA32_APICBASE_BSP;
-		kvm_lapic_set_base(vcpu, msr_val);
+
+		/*
+		 * Use the inner helper to avoid an extra recalcuation of the
+		 * optimized APIC map if some other task has dirtied the map.
+		 * The recalculation needed for this vCPU will be done after
+		 * all APIC state has been initialized (see below).
+		 */
+		__kvm_apic_set_base(vcpu, msr_val);
 	}
 
 	if (!apic)
@@ -3057,7 +3089,6 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
 
 	kvm_x86_call(apicv_pre_state_restore)(vcpu);
 
-	kvm_lapic_set_base(vcpu, vcpu->arch.apic_base);
 	/* set SPIV separately to get count of SW disabled APICs right */
 	apic_set_spiv(apic, *((u32 *)(s->regs + APIC_SPIV)));
 
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 1b8ef9856422..24add38beaf0 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -95,8 +95,6 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event);
 u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu);
 void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8);
 void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu);
-void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value);
-void kvm_recalculate_apic_map(struct kvm *kvm);
 void kvm_apic_set_version(struct kvm_vcpu *vcpu);
 void kvm_apic_after_set_mcg_cap(struct kvm_vcpu *vcpu);
 bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
@@ -117,11 +115,9 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 		struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map);
 void kvm_apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high);
 
-u64 kvm_get_apic_base(struct kvm_vcpu *vcpu);
-int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
+int kvm_apic_set_base(struct kvm_vcpu *vcpu, u64 value, bool host_initiated);
 int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s);
 int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s);
-enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu);
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
 
 u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu);
@@ -271,6 +267,11 @@ static inline enum lapic_mode kvm_apic_mode(u64 apic_base)
 	return apic_base & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
 }
 
+static inline enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu)
+{
+	return kvm_apic_mode(vcpu->arch.apic_base);
+}
+
 static inline u8 kvm_xapic_id(struct kvm_lapic *apic)
 {
 	return kvm_lapic_get_reg(apic, APIC_ID) >> 24;
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 9dc5dd43ae7f..e9322358678b 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -4,6 +4,7 @@
 
 #include <linux/kvm_host.h>
 #include "kvm_cache_regs.h"
+#include "x86.h"
 #include "cpuid.h"
 
 extern bool __read_mostly enable_mmio_caching;
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 38128e7b9af1..d7b391fe2c23 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6179,7 +6179,7 @@ void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	/* It's actually a GPA for vcpu->arch.guest_mmu.  */
 	if (mmu != &vcpu->arch.guest_mmu) {
 		/* INVLPG on a non-canonical address is a NOP according to the SDM.  */
-		if (is_noncanonical_address(addr, vcpu))
+		if (is_noncanonical_invlpg_address(addr, vcpu))
 			return;
 
 		kvm_x86_call(flush_tlb_gva)(vcpu, addr);
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index 05490b9d8a43..6f74e2b27c1e 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -19,6 +19,7 @@
 #include <asm/mtrr.h>
 
 #include "cpuid.h"
+#include "x86.h"
 
 static u64 *find_mtrr(struct kvm_vcpu *vcpu, unsigned int msr)
 {
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index c1e29307826b..dd15cc635655 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1390,7 +1390,9 @@ static void __svm_vcpu_reset(struct kvm_vcpu *vcpu)
 	svm_vcpu_init_msrpm(vcpu, svm->msrpm);
 
 	svm_init_osvw(vcpu);
-	vcpu->arch.microcode_version = 0x01000065;
+
+	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS))
+		vcpu->arch.microcode_version = 0x01000065;
 	svm->tsc_ratio_msr = kvm_caps.default_tsc_scaling_ratio;
 
 	svm->nmi_masked = false;
@@ -5031,6 +5033,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.get_segment = svm_get_segment,
 	.set_segment = svm_set_segment,
 	.get_cpl = svm_get_cpl,
+	.get_cpl_no_cache = svm_get_cpl,
 	.get_cs_db_l_bits = svm_get_cs_db_l_bits,
 	.is_valid_cr0 = svm_is_valid_cr0,
 	.set_cr0 = svm_set_cr0,
diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c
index fab6a1ad98dc..fa41d036acd4 100644
--- a/arch/x86/kvm/vmx/hyperv.c
+++ b/arch/x86/kvm/vmx/hyperv.c
@@ -4,6 +4,7 @@
 #include <linux/errno.h>
 #include <linux/smp.h>
 
+#include "x86.h"
 #include "../cpuid.h"
 #include "hyperv.h"
 #include "nested.h"
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 7668e2fb8043..92d35cc6cd15 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -50,6 +50,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
 	.get_segment = vmx_get_segment,
 	.set_segment = vmx_set_segment,
 	.get_cpl = vmx_get_cpl,
+	.get_cpl_no_cache = vmx_get_cpl_no_cache,
 	.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
 	.is_valid_cr0 = vmx_is_valid_cr0,
 	.set_cr0 = vmx_set_cr0,
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 259fe445e695..746cb41c5b98 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -7,6 +7,7 @@
 #include <asm/debugreg.h>
 #include <asm/mmu_context.h>
 
+#include "x86.h"
 #include "cpuid.h"
 #include "hyperv.h"
 #include "mmu.h"
@@ -16,7 +17,6 @@
 #include "sgx.h"
 #include "trace.h"
 #include "vmx.h"
-#include "x86.h"
 #include "smm.h"
 
 static bool __read_mostly enable_shadow_vmcs = 1;
@@ -2996,6 +2996,17 @@ static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static bool is_l1_noncanonical_address_on_vmexit(u64 la, struct vmcs12 *vmcs12)
+{
+	/*
+	 * Check that the given linear address is canonical after a VM exit
+	 * from L2, based on HOST_CR4.LA57 value that will be loaded for L1.
+	 */
+	u8 l1_address_bits_on_exit = (vmcs12->host_cr4 & X86_CR4_LA57) ? 57 : 48;
+
+	return !__is_canonical_address(la, l1_address_bits_on_exit);
+}
+
 static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 				       struct vmcs12 *vmcs12)
 {
@@ -3006,8 +3017,8 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 	    CC(!kvm_vcpu_is_legal_cr3(vcpu, vmcs12->host_cr3)))
 		return -EINVAL;
 
-	if (CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) ||
-	    CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu)))
+	if (CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_esp, vcpu)) ||
+	    CC(is_noncanonical_msr_address(vmcs12->host_ia32_sysenter_eip, vcpu)))
 		return -EINVAL;
 
 	if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) &&
@@ -3041,12 +3052,12 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
 	    CC(vmcs12->host_ss_selector == 0 && !ia32e))
 		return -EINVAL;
 
-	if (CC(is_noncanonical_address(vmcs12->host_fs_base, vcpu)) ||
-	    CC(is_noncanonical_address(vmcs12->host_gs_base, vcpu)) ||
-	    CC(is_noncanonical_address(vmcs12->host_gdtr_base, vcpu)) ||
-	    CC(is_noncanonical_address(vmcs12->host_idtr_base, vcpu)) ||
-	    CC(is_noncanonical_address(vmcs12->host_tr_base, vcpu)) ||
-	    CC(is_noncanonical_address(vmcs12->host_rip, vcpu)))
+	if (CC(is_noncanonical_base_address(vmcs12->host_fs_base, vcpu)) ||
+	    CC(is_noncanonical_base_address(vmcs12->host_gs_base, vcpu)) ||
+	    CC(is_noncanonical_base_address(vmcs12->host_gdtr_base, vcpu)) ||
+	    CC(is_noncanonical_base_address(vmcs12->host_idtr_base, vcpu)) ||
+	    CC(is_noncanonical_base_address(vmcs12->host_tr_base, vcpu)) ||
+	    CC(is_l1_noncanonical_address_on_vmexit(vmcs12->host_rip, vmcs12)))
 		return -EINVAL;
 
 	/*
@@ -3164,7 +3175,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 	}
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) &&
-	    (CC(is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) ||
+	    (CC(is_noncanonical_msr_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu)) ||
 	     CC((vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD))))
 		return -EINVAL;
 
@@ -5149,7 +5160,7 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
 		 * non-canonical form. This is the only check on the memory
 		 * destination for long mode!
 		 */
-		exn = is_noncanonical_address(*ret, vcpu);
+		exn = is_noncanonical_address(*ret, vcpu, 0);
 	} else {
 		/*
 		 * When not in long mode, the virtual/linear address is
@@ -5954,7 +5965,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 		 * invalidation.
 		 */
 		if (!operand.vpid ||
-		    is_noncanonical_address(operand.gla, vcpu))
+		    is_noncanonical_invlpg_address(operand.gla, vcpu))
 			return nested_vmx_fail(vcpu,
 				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
 		vpid_sync_vcpu_addr(vpid02, operand.gla);
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 83382a4d1d66..9c9d4a336166 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -365,7 +365,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		}
 		break;
 	case MSR_IA32_DS_AREA:
-		if (is_noncanonical_address(data, vcpu))
+		if (is_noncanonical_msr_address(data, vcpu))
 			return 1;
 
 		pmu->ds_area = data;
diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c
index a3c3d2a51f47..b352a3ba7354 100644
--- a/arch/x86/kvm/vmx/sgx.c
+++ b/arch/x86/kvm/vmx/sgx.c
@@ -4,12 +4,11 @@
 
 #include <asm/sgx.h>
 
-#include "cpuid.h"
+#include "x86.h"
 #include "kvm_cache_regs.h"
 #include "nested.h"
 #include "sgx.h"
 #include "vmx.h"
-#include "x86.h"
 
 bool __read_mostly enable_sgx = 1;
 module_param_named(sgx, enable_sgx, bool, 0444);
@@ -38,7 +37,7 @@ static int sgx_get_encls_gva(struct kvm_vcpu *vcpu, unsigned long offset,
 		fault = true;
 	} else if (likely(is_64_bit_mode(vcpu))) {
 		*gva = vmx_get_untagged_addr(vcpu, *gva, 0);
-		fault = is_noncanonical_address(*gva, vcpu);
+		fault = is_noncanonical_address(*gva, vcpu, 0);
 	} else {
 		*gva &= 0xffffffff;
 		fault = (s.unusable) ||
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index b1bb64890cb2..6ed801ffe33f 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -2282,7 +2282,7 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		    (!msr_info->host_initiated &&
 		     !guest_cpuid_has(vcpu, X86_FEATURE_MPX)))
 			return 1;
-		if (is_noncanonical_address(data & PAGE_MASK, vcpu) ||
+		if (is_noncanonical_msr_address(data & PAGE_MASK, vcpu) ||
 		    (data & MSR_IA32_BNDCFGS_RSVD))
 			return 1;
 
@@ -2447,7 +2447,7 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		index = msr_info->index - MSR_IA32_RTIT_ADDR0_A;
 		if (index >= 2 * vmx->pt_desc.num_address_ranges)
 			return 1;
-		if (is_noncanonical_address(data, vcpu))
+		if (is_noncanonical_msr_address(data, vcpu))
 			return 1;
 		if (index % 2)
 			vmx->pt_desc.guest.addr_b[index / 2] = data;
@@ -2455,8 +2455,6 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			vmx->pt_desc.guest.addr_a[index / 2] = data;
 		break;
 	case MSR_IA32_PERF_CAPABILITIES:
-		if (data && !vcpu_to_pmu(vcpu)->version)
-			return 1;
 		if (data & PMU_CAP_LBR_FMT) {
 			if ((data & PMU_CAP_LBR_FMT) !=
 			    (kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT))
@@ -3567,16 +3565,29 @@ u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
 	return vmx_read_guest_seg_base(to_vmx(vcpu), seg);
 }
 
-int vmx_get_cpl(struct kvm_vcpu *vcpu)
+static int __vmx_get_cpl(struct kvm_vcpu *vcpu, bool no_cache)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int ar;
 
 	if (unlikely(vmx->rmode.vm86_active))
 		return 0;
-	else {
-		int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS);
-		return VMX_AR_DPL(ar);
-	}
+
+	if (no_cache)
+		ar = vmcs_read32(GUEST_SS_AR_BYTES);
+	else
+		ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS);
+	return VMX_AR_DPL(ar);
+}
+
+int vmx_get_cpl(struct kvm_vcpu *vcpu)
+{
+	return __vmx_get_cpl(vcpu, false);
+}
+
+int vmx_get_cpl_no_cache(struct kvm_vcpu *vcpu)
+{
+	return __vmx_get_cpl(vcpu, true);
 }
 
 static u32 vmx_segment_access_rights(struct kvm_segment *var)
@@ -4558,7 +4569,8 @@ vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control,
 	 * Update the nested MSR settings so that a nested VMM can/can't set
 	 * controls for features that are/aren't exposed to the guest.
 	 */
-	if (nested) {
+	if (nested &&
+	    kvm_check_has_quirk(vmx->vcpu.kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) {
 		/*
 		 * All features that can be added or removed to VMX MSRs must
 		 * be supported in the first place for nested virtualization.
@@ -4848,7 +4860,8 @@ static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 
 	init_vmcs(vmx);
 
-	if (nested)
+	if (nested &&
+	    kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS))
 		memcpy(&vmx->nested.msrs, &vmcs_config.nested, sizeof(vmx->nested.msrs));
 
 	vcpu_setup_sgx_lepubkeyhash(vcpu);
@@ -4861,7 +4874,8 @@ static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 	vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID;
 #endif
 
-	vcpu->arch.microcode_version = 0x100000000ULL;
+	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS))
+		vcpu->arch.microcode_version = 0x100000000ULL;
 	vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED;
 
 	/*
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 40303b43da6c..43f573f6ca46 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -383,6 +383,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
 void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
 			unsigned long fs_base, unsigned long gs_base);
 int vmx_get_cpl(struct kvm_vcpu *vcpu);
+int vmx_get_cpl_no_cache(struct kvm_vcpu *vcpu);
 bool vmx_emulation_required(struct kvm_vcpu *vcpu);
 unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu);
 void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8507b300ff43..8637bc001096 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -451,6 +451,7 @@ static const u32 msr_based_features_all_except_vmx[] = {
 	MSR_IA32_UCODE_REV,
 	MSR_IA32_ARCH_CAPABILITIES,
 	MSR_IA32_PERF_CAPABILITIES,
+	MSR_PLATFORM_INFO,
 };
 
 static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all_except_vmx) +
@@ -667,38 +668,6 @@ static void drop_user_return_notifiers(void)
 		kvm_on_user_return(&msrs->urn);
 }
 
-u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.apic_base;
-}
-
-enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu)
-{
-	return kvm_apic_mode(kvm_get_apic_base(vcpu));
-}
-EXPORT_SYMBOL_GPL(kvm_get_apic_mode);
-
-int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
-{
-	enum lapic_mode old_mode = kvm_get_apic_mode(vcpu);
-	enum lapic_mode new_mode = kvm_apic_mode(msr_info->data);
-	u64 reserved_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu) | 0x2ff |
-		(guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE);
-
-	if ((msr_info->data & reserved_bits) != 0 || new_mode == LAPIC_MODE_INVALID)
-		return 1;
-	if (!msr_info->host_initiated) {
-		if (old_mode == LAPIC_MODE_X2APIC && new_mode == LAPIC_MODE_XAPIC)
-			return 1;
-		if (old_mode == LAPIC_MODE_DISABLED && new_mode == LAPIC_MODE_X2APIC)
-			return 1;
-	}
-
-	kvm_lapic_set_base(vcpu, msr_info->data);
-	kvm_recalculate_apic_map(vcpu->kvm);
-	return 0;
-}
-
 /*
  * Handle a fault on a hardware virtualization (VMX or SVM) instruction.
  *
@@ -1854,7 +1823,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
 	case MSR_KERNEL_GS_BASE:
 	case MSR_CSTAR:
 	case MSR_LSTAR:
-		if (is_noncanonical_address(data, vcpu))
+		if (is_noncanonical_msr_address(data, vcpu))
 			return 1;
 		break;
 	case MSR_IA32_SYSENTER_EIP:
@@ -1871,7 +1840,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
 		 * value, and that something deterministic happens if the guest
 		 * invokes 64-bit SYSENTER.
 		 */
-		data = __canonical_address(data, vcpu_virt_addr_bits(vcpu));
+		data = __canonical_address(data, max_host_virt_addr_bits());
 		break;
 	case MSR_TSC_AUX:
 		if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX))
@@ -2144,8 +2113,9 @@ EXPORT_SYMBOL_GPL(kvm_emulate_monitor);
 static inline bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu)
 {
 	xfer_to_guest_mode_prepare();
-	return vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) ||
-		xfer_to_guest_mode_work_pending();
+
+	return READ_ONCE(vcpu->mode) == EXITING_GUEST_MODE ||
+	       kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending();
 }
 
 /*
@@ -3793,13 +3763,16 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			vcpu->arch.microcode_version = data;
 		break;
 	case MSR_IA32_ARCH_CAPABILITIES:
-		if (!msr_info->host_initiated)
-			return 1;
+		if (!msr_info->host_initiated ||
+		    !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES))
+			return KVM_MSR_RET_UNSUPPORTED;
 		vcpu->arch.arch_capabilities = data;
 		break;
 	case MSR_IA32_PERF_CAPABILITIES:
-		if (!msr_info->host_initiated)
-			return 1;
+		if (!msr_info->host_initiated ||
+		    !guest_cpuid_has(vcpu, X86_FEATURE_PDCM))
+			return KVM_MSR_RET_UNSUPPORTED;
+
 		if (data & ~kvm_caps.supported_perf_cap)
 			return 1;
 
@@ -3890,7 +3863,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_MTRRdefType:
 		return kvm_mtrr_set_msr(vcpu, msr, data);
 	case MSR_IA32_APICBASE:
-		return kvm_set_apic_base(vcpu, msr_info);
+		return kvm_apic_set_base(vcpu, data, msr_info->host_initiated);
 	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_write(vcpu, msr, data);
 	case MSR_IA32_TSC_DEADLINE:
@@ -4111,9 +4084,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vcpu->arch.osvw.status = data;
 		break;
 	case MSR_PLATFORM_INFO:
-		if (!msr_info->host_initiated ||
-		    (!(data & MSR_PLATFORM_INFO_CPUID_FAULT) &&
-		     cpuid_fault_enabled(vcpu)))
+		if (!msr_info->host_initiated)
 			return 1;
 		vcpu->arch.msr_platform_info = data;
 		break;
@@ -4252,15 +4223,13 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = vcpu->arch.microcode_version;
 		break;
 	case MSR_IA32_ARCH_CAPABILITIES:
-		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES))
-			return 1;
+		if (!guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES))
+			return KVM_MSR_RET_UNSUPPORTED;
 		msr_info->data = vcpu->arch.arch_capabilities;
 		break;
 	case MSR_IA32_PERF_CAPABILITIES:
-		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_PDCM))
-			return 1;
+		if (!guest_cpuid_has(vcpu, X86_FEATURE_PDCM))
+			return KVM_MSR_RET_UNSUPPORTED;
 		msr_info->data = vcpu->arch.perf_capabilities;
 		break;
 	case MSR_IA32_POWER_CTL:
@@ -4314,7 +4283,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = 1 << 24;
 		break;
 	case MSR_IA32_APICBASE:
-		msr_info->data = kvm_get_apic_base(vcpu);
+		msr_info->data = vcpu->arch.apic_base;
 		break;
 	case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
 		return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data);
@@ -5094,7 +5063,13 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	int idx;
 
 	if (vcpu->preempted) {
-		vcpu->arch.preempted_in_kernel = kvm_arch_vcpu_in_kernel(vcpu);
+		/*
+		 * Assume protected guests are in-kernel.  Inefficient yielding
+		 * due to false positives is preferable to never yielding due
+		 * to false negatives.
+		 */
+		vcpu->arch.preempted_in_kernel = vcpu->arch.guest_state_protected ||
+						 !kvm_x86_call(get_cpl_no_cache)(vcpu);
 
 		/*
 		 * Take the srcu lock as memslots will be accessed to check the gfn
@@ -8612,6 +8587,12 @@ static gva_t emulator_get_untagged_addr(struct x86_emulate_ctxt *ctxt,
 					       addr, flags);
 }
 
+static bool emulator_is_canonical_addr(struct x86_emulate_ctxt *ctxt,
+				       gva_t addr, unsigned int flags)
+{
+	return !is_noncanonical_address(addr, emul_to_vcpu(ctxt), flags);
+}
+
 static const struct x86_emulate_ops emulate_ops = {
 	.vm_bugged           = emulator_vm_bugged,
 	.read_gpr            = emulator_read_gpr,
@@ -8658,6 +8639,7 @@ static const struct x86_emulate_ops emulate_ops = {
 	.triple_fault        = emulator_triple_fault,
 	.set_xcr             = emulator_set_xcr,
 	.get_untagged_addr   = emulator_get_untagged_addr,
+	.is_canonical_addr   = emulator_is_canonical_addr,
 };
 
 static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
@@ -10159,7 +10141,7 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 
 	kvm_run->if_flag = kvm_x86_call(get_if_flag)(vcpu);
 	kvm_run->cr8 = kvm_get_cr8(vcpu);
-	kvm_run->apic_base = kvm_get_apic_base(vcpu);
+	kvm_run->apic_base = vcpu->arch.apic_base;
 
 	kvm_run->ready_for_interrupt_injection =
 		pic_in_kernel(vcpu->kvm) ||
@@ -10576,8 +10558,8 @@ static void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu)
 	 * deleted if any vCPU has xAPIC virtualization and x2APIC enabled, but
 	 * and hardware doesn't support x2APIC virtualization.  E.g. some AMD
 	 * CPUs support AVIC but not x2APIC.  KVM still allows enabling AVIC in
-	 * this case so that KVM can the AVIC doorbell to inject interrupts to
-	 * running vCPUs, but KVM must not create SPTEs for the APIC base as
+	 * this case so that KVM can use the AVIC doorbell to inject interrupts
+	 * to running vCPUs, but KVM must not create SPTEs for the APIC base as
 	 * the vCPU would incorrectly be able to access the vAPIC page via MMIO
 	 * despite being in x2APIC mode.  For simplicity, inhibiting the APIC
 	 * access page is sticky.
@@ -10606,11 +10588,11 @@ void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
 	if (!!old != !!new) {
 		/*
 		 * Kick all vCPUs before setting apicv_inhibit_reasons to avoid
-		 * false positives in the sanity check WARN in svm_vcpu_run().
+		 * false positives in the sanity check WARN in vcpu_enter_guest().
 		 * This task will wait for all vCPUs to ack the kick IRQ before
 		 * updating apicv_inhibit_reasons, and all other vCPUs will
 		 * block on acquiring apicv_update_lock so that vCPUs can't
-		 * redo svm_vcpu_run() without seeing the new inhibit state.
+		 * redo vcpu_enter_guest() without seeing the new inhibit state.
 		 *
 		 * Note, holding apicv_update_lock and taking it in the read
 		 * side (handling the request) also prevents other vCPUs from
@@ -11711,7 +11693,7 @@ skip_protected_regs:
 	sregs->cr4 = kvm_read_cr4(vcpu);
 	sregs->cr8 = kvm_get_cr8(vcpu);
 	sregs->efer = vcpu->arch.efer;
-	sregs->apic_base = kvm_get_apic_base(vcpu);
+	sregs->apic_base = vcpu->arch.apic_base;
 }
 
 static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
@@ -11888,16 +11870,13 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs,
 		int *mmu_reset_needed, bool update_pdptrs)
 {
-	struct msr_data apic_base_msr;
 	int idx;
 	struct desc_ptr dt;
 
 	if (!kvm_is_valid_sregs(vcpu, sregs))
 		return -EINVAL;
 
-	apic_base_msr.data = sregs->apic_base;
-	apic_base_msr.host_initiated = true;
-	if (kvm_set_apic_base(vcpu, &apic_base_msr))
+	if (kvm_apic_set_base(vcpu, sregs->apic_base, true))
 		return -EINVAL;
 
 	if (vcpu->arch.guest_state_protected)
@@ -12299,7 +12278,11 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 
 	kvm_async_pf_hash_reset(vcpu);
 
-	vcpu->arch.perf_capabilities = kvm_caps.supported_perf_cap;
+	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) {
+		vcpu->arch.arch_capabilities = kvm_get_arch_capabilities();
+		vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT;
+		vcpu->arch.perf_capabilities = kvm_caps.supported_perf_cap;
+	}
 	kvm_pmu_init(vcpu);
 
 	vcpu->arch.pending_external_vector = -1;
@@ -12313,8 +12296,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	if (r)
 		goto free_guest_fpu;
 
-	vcpu->arch.arch_capabilities = kvm_get_arch_capabilities();
-	vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT;
 	kvm_xen_init_vcpu(vcpu);
 	vcpu_load(vcpu);
 	kvm_set_tsc_khz(vcpu, vcpu->kvm->arch.default_tsc_khz);
@@ -13203,6 +13184,8 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 {
+	WARN_ON_ONCE(!kvm_arch_pmi_in_guest(vcpu));
+
 	if (vcpu->arch.guest_state_protected)
 		return true;
 
@@ -13211,6 +13194,11 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
 
 unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu)
 {
+	WARN_ON_ONCE(!kvm_arch_pmi_in_guest(vcpu));
+
+	if (vcpu->arch.guest_state_protected)
+		return 0;
+
 	return kvm_rip_read(vcpu);
 }
 
@@ -13726,7 +13714,7 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva)
 		 * invalidation.
 		 */
 		if ((!pcid_enabled && (operand.pcid != 0)) ||
-		    is_noncanonical_address(operand.gla, vcpu)) {
+		    is_noncanonical_invlpg_address(operand.gla, vcpu)) {
 			kvm_inject_gp(vcpu, 0);
 			return 1;
 		}
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index a84c48ef5278..ec623d23d13d 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -8,6 +8,7 @@
 #include <asm/pvclock.h>
 #include "kvm_cache_regs.h"
 #include "kvm_emulate.h"
+#include "cpuid.h"
 
 struct kvm_caps {
 	/* control of guest tsc rate supported? */
@@ -233,9 +234,52 @@ static inline u8 vcpu_virt_addr_bits(struct kvm_vcpu *vcpu)
 	return kvm_is_cr4_bit_set(vcpu, X86_CR4_LA57) ? 57 : 48;
 }
 
-static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu)
+static inline u8 max_host_virt_addr_bits(void)
 {
-	return !__is_canonical_address(la, vcpu_virt_addr_bits(vcpu));
+	return kvm_cpu_cap_has(X86_FEATURE_LA57) ? 57 : 48;
+}
+
+/*
+ * x86 MSRs which contain linear addresses, x86 hidden segment bases, and
+ * IDT/GDT bases have static canonicality checks, the size of which depends
+ * only on the CPU's support for 5-level paging, rather than on the state of
+ * CR4.LA57.  This applies to both WRMSR and to other instructions that set
+ * their values, e.g. SGDT.
+ *
+ * KVM passes through most of these MSRS and also doesn't intercept the
+ * instructions that set the hidden segment bases.
+ *
+ * Because of this, to be consistent with hardware, even if the guest doesn't
+ * have LA57 enabled in its CPUID, perform canonicality checks based on *host*
+ * support for 5 level paging.
+ *
+ * Finally, instructions which are related to MMU invalidation of a given
+ * linear address, also have a similar static canonical check on address.
+ * This allows for example to invalidate 5-level addresses of a guest from a
+ * host which uses 4-level paging.
+ */
+static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu,
+					   unsigned int flags)
+{
+	if (flags & (X86EMUL_F_INVLPG | X86EMUL_F_MSR | X86EMUL_F_DT_LOAD))
+		return !__is_canonical_address(la, max_host_virt_addr_bits());
+	else
+		return !__is_canonical_address(la, vcpu_virt_addr_bits(vcpu));
+}
+
+static inline bool is_noncanonical_msr_address(u64 la, struct kvm_vcpu *vcpu)
+{
+	return is_noncanonical_address(la, vcpu, X86EMUL_F_MSR);
+}
+
+static inline bool is_noncanonical_base_address(u64 la, struct kvm_vcpu *vcpu)
+{
+	return is_noncanonical_address(la, vcpu, X86EMUL_F_DT_LOAD);
+}
+
+static inline bool is_noncanonical_invlpg_address(u64 la, struct kvm_vcpu *vcpu)
+{
+	return is_noncanonical_address(la, vcpu, X86EMUL_F_INVLPG);
 }
 
 static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu,
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 5e5e0b5aae60..01a000a41693 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -68,7 +68,7 @@ TEST_PROGS_x86_64 += x86_64/nx_huge_pages_test.sh
 TEST_GEN_PROGS_x86_64 = x86_64/cpuid_test
 TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86_64 += x86_64/dirty_log_page_splitting_test
-TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features
+TEST_GEN_PROGS_x86_64 += x86_64/feature_msrs_test
 TEST_GEN_PROGS_x86_64 += x86_64/exit_on_emulation_failure_test
 TEST_GEN_PROGS_x86_64 += x86_64/fix_hypercall_test
 TEST_GEN_PROGS_x86_64 += x86_64/hwcr_msr_test
diff --git a/tools/testing/selftests/kvm/x86_64/feature_msrs_test.c b/tools/testing/selftests/kvm/x86_64/feature_msrs_test.c
new file mode 100644
index 000000000000..a72f13ae2edb
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/feature_msrs_test.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+static bool is_kvm_controlled_msr(uint32_t msr)
+{
+	return msr == MSR_IA32_VMX_CR0_FIXED1 || msr == MSR_IA32_VMX_CR4_FIXED1;
+}
+
+/*
+ * For VMX MSRs with a "true" variant, KVM requires userspace to set the "true"
+ * MSR, and doesn't allow setting the hidden version.
+ */
+static bool is_hidden_vmx_msr(uint32_t msr)
+{
+	switch (msr) {
+	case MSR_IA32_VMX_PINBASED_CTLS:
+	case MSR_IA32_VMX_PROCBASED_CTLS:
+	case MSR_IA32_VMX_EXIT_CTLS:
+	case MSR_IA32_VMX_ENTRY_CTLS:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool is_quirked_msr(uint32_t msr)
+{
+	return msr != MSR_AMD64_DE_CFG;
+}
+
+static void test_feature_msr(uint32_t msr)
+{
+	const uint64_t supported_mask = kvm_get_feature_msr(msr);
+	uint64_t reset_value = is_quirked_msr(msr) ? supported_mask : 0;
+	struct kvm_vcpu *vcpu;
+	struct kvm_vm *vm;
+
+	/*
+	 * Don't bother testing KVM-controlled MSRs beyond verifying that the
+	 * MSR can be read from userspace.  Any value is effectively legal, as
+	 * KVM is bound by x86 architecture, not by ABI.
+	 */
+	if (is_kvm_controlled_msr(msr))
+		return;
+
+	/*
+	 * More goofy behavior.  KVM reports the host CPU's actual revision ID,
+	 * but initializes the vCPU's revision ID to an arbitrary value.
+	 */
+	if (msr == MSR_IA32_UCODE_REV)
+		reset_value = host_cpu_is_intel ? 0x100000000ULL : 0x01000065;
+
+	/*
+	 * For quirked MSRs, KVM's ABI is to initialize the vCPU's value to the
+	 * full set of features supported by KVM.  For non-quirked MSRs, and
+	 * when the quirk is disabled, KVM must zero-initialize the MSR and let
+	 * userspace do the configuration.
+	 */
+	vm = vm_create_with_one_vcpu(&vcpu, NULL);
+	TEST_ASSERT(vcpu_get_msr(vcpu, msr) == reset_value,
+		    "Wanted 0x%lx for %squirked MSR 0x%x, got 0x%lx",
+		    reset_value, is_quirked_msr(msr) ? "" : "non-", msr,
+		    vcpu_get_msr(vcpu, msr));
+	if (!is_hidden_vmx_msr(msr))
+		vcpu_set_msr(vcpu, msr, supported_mask);
+	kvm_vm_free(vm);
+
+	if (is_hidden_vmx_msr(msr))
+		return;
+
+	if (!kvm_has_cap(KVM_CAP_DISABLE_QUIRKS2) ||
+	    !(kvm_check_cap(KVM_CAP_DISABLE_QUIRKS2) & KVM_X86_QUIRK_STUFF_FEATURE_MSRS))
+		return;
+
+	vm = vm_create(1);
+	vm_enable_cap(vm, KVM_CAP_DISABLE_QUIRKS2, KVM_X86_QUIRK_STUFF_FEATURE_MSRS);
+
+	vcpu = vm_vcpu_add(vm, 0, NULL);
+	TEST_ASSERT(!vcpu_get_msr(vcpu, msr),
+		    "Quirk disabled, wanted '0' for MSR 0x%x, got 0x%lx",
+		    msr, vcpu_get_msr(vcpu, msr));
+	kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+	const struct kvm_msr_list *feature_list;
+	int i;
+
+	/*
+	 * Skip the entire test if MSR_FEATURES isn't supported, other tests
+	 * will cover the "regular" list of MSRs, the coverage here is purely
+	 * opportunistic and not interesting on its own.
+	 */
+	TEST_REQUIRE(kvm_has_cap(KVM_CAP_GET_MSR_FEATURES));
+
+	(void)kvm_get_msr_index_list();
+
+	feature_list = kvm_get_feature_msr_index_list();
+	for (i = 0; i < feature_list->nmsrs; i++)
+		test_feature_msr(feature_list->indices[i]);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c b/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c
deleted file mode 100644
index d09b3cbcadc6..000000000000
--- a/tools/testing/selftests/kvm/x86_64/get_msr_index_features.c
+++ /dev/null
@@ -1,35 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Test that KVM_GET_MSR_INDEX_LIST and
- * KVM_GET_MSR_FEATURE_INDEX_LIST work as intended
- *
- * Copyright (C) 2020, Red Hat, Inc.
- */
-#include <fcntl.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <sys/ioctl.h>
-
-#include "test_util.h"
-#include "kvm_util.h"
-#include "processor.h"
-
-int main(int argc, char *argv[])
-{
-	const struct kvm_msr_list *feature_list;
-	int i;
-
-	/*
-	 * Skip the entire test if MSR_FEATURES isn't supported, other tests
-	 * will cover the "regular" list of MSRs, the coverage here is purely
-	 * opportunistic and not interesting on its own.
-	 */
-	TEST_REQUIRE(kvm_has_cap(KVM_CAP_GET_MSR_FEATURES));
-
-	(void)kvm_get_msr_index_list();
-
-	feature_list = kvm_get_feature_msr_index_list();
-	for (i = 0; i < feature_list->nmsrs; i++)
-		kvm_get_feature_msr(feature_list->indices[i]);
-}
diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
index eda88080c186..9cbf283ebc55 100644
--- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c
+++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
@@ -72,8 +72,6 @@ int main(int argc, char *argv[])
 	}
 
 done:
-	vcpu_set_msr(vcpu, MSR_PLATFORM_INFO, msr_platform_info);
-
 	kvm_vm_free(vm);
 
 	return 0;
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
index 7c92536551cc..a1f5ff45d518 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
@@ -207,6 +207,29 @@ KVM_ONE_VCPU_TEST(vmx_pmu_caps, lbr_perf_capabilities, guest_code)
 	TEST_ASSERT(!r, "Writing LBR_TOS should fail after disabling vPMU");
 }
 
+KVM_ONE_VCPU_TEST(vmx_pmu_caps, perf_capabilities_unsupported, guest_code)
+{
+	uint64_t val;
+	int i, r;
+
+	vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities);
+	val = vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES);
+	TEST_ASSERT_EQ(val, host_cap.capabilities);
+
+	vcpu_clear_cpuid_feature(vcpu, X86_FEATURE_PDCM);
+
+	val = vcpu_get_msr(vcpu, MSR_IA32_PERF_CAPABILITIES);
+	TEST_ASSERT_EQ(val, 0);
+
+	vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, 0);
+
+	for (i = 0; i < 64; i++) {
+		r = _vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, BIT_ULL(i));
+		TEST_ASSERT(!r, "Setting PERF_CAPABILITIES bit %d (= 0x%llx) should fail without PDCM",
+			    i, BIT_ULL(i));
+	}
+}
+
 int main(int argc, char *argv[])
 {
 	TEST_REQUIRE(kvm_is_pmu_enabled());