Merge tag 'kvmarm-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for Linux 5.10

- New page table code for both hypervisor and guest stage-2
- Introduction of a new EL2-private host context
- Allow EL2 to have its own private per-CPU variables
- Support of PMU event filtering
- Complete rework of the Spectre mitigation
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index d2b733d..425325f 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -4498,11 +4498,14 @@
  - HYPERV_CPUID_ENLIGHTMENT_INFO
  - HYPERV_CPUID_IMPLEMENT_LIMITS
  - HYPERV_CPUID_NESTED_FEATURES
+ - HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS
+ - HYPERV_CPUID_SYNDBG_INTERFACE
+ - HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES
 
 HYPERV_CPUID_NESTED_FEATURES leaf is only exposed when Enlightened VMCS was
 enabled on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS).
 
-Userspace invokes KVM_GET_SUPPORTED_CPUID by passing a kvm_cpuid2 structure
+Userspace invokes KVM_GET_SUPPORTED_HV_CPUID by passing a kvm_cpuid2 structure
 with the 'nent' field indicating the number of entries in the variable-size
 array 'entries'.  If the number of entries is too low to describe all Hyper-V
 feature leaves, an error (E2BIG) is returned. If the number is more or equal
@@ -4704,6 +4707,99 @@
   Verify the integrity of the unpacked image. Only if this succeeds,
   KVM is allowed to start protected VCPUs.
 
+4.126 KVM_X86_SET_MSR_FILTER
+----------------------------
+
+:Capability: KVM_X86_SET_MSR_FILTER
+:Architectures: x86
+:Type: vm ioctl
+:Parameters: struct kvm_msr_filter
+:Returns: 0 on success, < 0 on error
+
+::
+
+  struct kvm_msr_filter_range {
+  #define KVM_MSR_FILTER_READ  (1 << 0)
+  #define KVM_MSR_FILTER_WRITE (1 << 1)
+	__u32 flags;
+	__u32 nmsrs; /* number of msrs in bitmap */
+	__u32 base;  /* MSR index the bitmap starts at */
+	__u8 *bitmap; /* a 1 bit allows the operations in flags, 0 denies */
+  };
+
+  #define KVM_MSR_FILTER_MAX_RANGES 16
+  struct kvm_msr_filter {
+  #define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0)
+  #define KVM_MSR_FILTER_DEFAULT_DENY  (1 << 0)
+	__u32 flags;
+	struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
+  };
+
+flags values for struct kvm_msr_filter_range:
+
+KVM_MSR_FILTER_READ
+
+  Filter read accesses to MSRs using the given bitmap. A 0 in the bitmap
+  indicates that a read should immediately fail, while a 1 indicates that
+  a read for a particular MSR should be handled regardless of the default
+  filter action.
+
+KVM_MSR_FILTER_WRITE
+
+  Filter write accesses to MSRs using the given bitmap. A 0 in the bitmap
+  indicates that a write should immediately fail, while a 1 indicates that
+  a write for a particular MSR should be handled regardless of the default
+  filter action.
+
+KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE
+
+  Filter both read and write accesses to MSRs using the given bitmap. A 0
+  in the bitmap indicates that both reads and writes should immediately fail,
+  while a 1 indicates that reads and writes for a particular MSR are not
+  filtered by this range.
+
+flags values for struct kvm_msr_filter:
+
+KVM_MSR_FILTER_DEFAULT_ALLOW
+
+  If no filter range matches an MSR index that is getting accessed, KVM will
+  fall back to allowing access to the MSR.
+
+KVM_MSR_FILTER_DEFAULT_DENY
+
+  If no filter range matches an MSR index that is getting accessed, KVM will
+  fall back to rejecting access to the MSR. In this mode, all MSRs that should
+  be processed by KVM need to explicitly be marked as allowed in the bitmaps.
+
+This ioctl allows user space to define up to 16 bitmaps of MSR ranges to
+specify whether a certain MSR access should be explicitly filtered for or not.
+
+If this ioctl has never been invoked, MSR accesses are not guarded and the
+old KVM in-kernel emulation behavior is fully preserved.
+
+As soon as the filtering is in place, every MSR access is processed through
+the filtering. If a bit is within one of the defined ranges, read and write
+accesses are guarded by the bitmap's value for the MSR index. If it is not
+defined in any range, whether MSR access is rejected is determined by the flags
+field in the kvm_msr_filter struct: KVM_MSR_FILTER_DEFAULT_ALLOW and
+KVM_MSR_FILTER_DEFAULT_DENY.
+
+Calling this ioctl with an empty set of ranges (all nmsrs == 0) disables MSR
+filtering. In that mode, KVM_MSR_FILTER_DEFAULT_DENY no longer has any effect.
+
+Each bitmap range specifies a range of MSRs to potentially allow access on.
+The range goes from MSR index [base .. base+nmsrs]. The flags field
+indicates whether reads, writes or both reads and writes are filtered
+by setting a 1 bit in the bitmap for the corresponding MSR index.
+
+If an MSR access is not permitted through the filtering, it generates a
+#GP inside the guest. When combined with KVM_CAP_X86_USER_SPACE_MSR, that
+allows user space to deflect and potentially handle various MSR accesses
+into user space.
+
+If a vCPU is in running state while this ioctl is invoked, the vCPU may
+experience inconsistent filtering behavior on MSR accesses.
+
 
 5. The kvm_run structure
 ========================
@@ -4869,14 +4965,13 @@
 
 .. note::
 
-      For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR and
-      KVM_EXIT_EPR the corresponding
-
-operations are complete (and guest state is consistent) only after userspace
-has re-entered the kernel with KVM_RUN.  The kernel side will first finish
-incomplete operations and then check for pending signals.  Userspace
-can re-enter the guest with an unmasked signal pending to complete
-pending operations.
+      For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR,
+      KVM_EXIT_EPR, KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR the corresponding
+      operations are complete (and guest state is consistent) only after userspace
+      has re-entered the kernel with KVM_RUN.  The kernel side will first finish
+      incomplete operations and then check for pending signals.  Userspace
+      can re-enter the guest with an unmasked signal pending to complete
+      pending operations.
 
 ::
 
@@ -5165,6 +5260,44 @@
 
 ::
 
+		/* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */
+		struct {
+			__u8 error; /* user -> kernel */
+			__u8 pad[7];
+			__u32 reason; /* kernel -> user */
+			__u32 index; /* kernel -> user */
+			__u64 data; /* kernel <-> user */
+		} msr;
+
+Used on x86 systems. When the VM capability KVM_CAP_X86_USER_SPACE_MSR is
+enabled, MSR accesses to registers that would invoke a #GP by KVM kernel code
+will instead trigger a KVM_EXIT_X86_RDMSR exit for reads and KVM_EXIT_X86_WRMSR
+exit for writes.
+
+The "reason" field specifies why the MSR trap occurred. User space will only
+receive MSR exit traps when a particular reason was requested during through
+ENABLE_CAP. Currently valid exit reasons are:
+
+	KVM_MSR_EXIT_REASON_UNKNOWN - access to MSR that is unknown to KVM
+	KVM_MSR_EXIT_REASON_INVAL - access to invalid MSRs or reserved bits
+	KVM_MSR_EXIT_REASON_FILTER - access blocked by KVM_X86_SET_MSR_FILTER
+
+For KVM_EXIT_X86_RDMSR, the "index" field tells user space which MSR the guest
+wants to read. To respond to this request with a successful read, user space
+writes the respective data into the "data" field and must continue guest
+execution to ensure the read data is transferred into guest register state.
+
+If the RDMSR request was unsuccessful, user space indicates that with a "1" in
+the "error" field. This will inject a #GP into the guest when the VCPU is
+executed again.
+
+For KVM_EXIT_X86_WRMSR, the "index" field tells user space which MSR the guest
+wants to write. Once finished processing the event, user space must continue
+vCPU execution. If the MSR write was unsuccessful, user space also sets the
+"error" field to "1".
+
+::
+
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -5852,6 +5985,28 @@
 the maximum halt time to specified on a per-VM basis, effectively overriding
 the module parameter for the target VM.
 
+7.21 KVM_CAP_X86_USER_SPACE_MSR
+-------------------------------
+
+:Architectures: x86
+:Target: VM
+:Parameters: args[0] contains the mask of KVM_MSR_EXIT_REASON_* events to report
+:Returns: 0 on success; -1 on error
+
+This capability enables trapping of #GP invoking RDMSR and WRMSR instructions
+into user space.
+
+When a guest requests to read or write an MSR, KVM may not implement all MSRs
+that are relevant to a respective system. It also does not differentiate by
+CPU type.
+
+To allow more fine grained control over MSR handling, user space may enable
+this capability. With it enabled, MSR accesses that match the mask specified in
+args[0] and trigger a #GP event inside the guest by KVM will instead trigger
+KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR exit notifications which user space
+can then handle to implement model specific MSR handling and/or user notifications
+to inform a user that an MSR was not handled.
+
 8. Other capabilities.
 ======================
 
@@ -6173,3 +6328,48 @@
 is supported, than the other should as well and vice versa.  For arm64
 see Documentation/virt/kvm/devices/vcpu.rst "KVM_ARM_VCPU_PVTIME_CTRL".
 For x86 see Documentation/virt/kvm/msr.rst "MSR_KVM_STEAL_TIME".
+
+8.25 KVM_CAP_S390_DIAG318
+-------------------------
+
+:Architectures: s390
+
+This capability enables a guest to set information about its control program
+(i.e. guest kernel type and version). The information is helpful during
+system/firmware service events, providing additional data about the guest
+environments running on the machine.
+
+The information is associated with the DIAGNOSE 0x318 instruction, which sets
+an 8-byte value consisting of a one-byte Control Program Name Code (CPNC) and
+a 7-byte Control Program Version Code (CPVC). The CPNC determines what
+environment the control program is running in (e.g. Linux, z/VM...), and the
+CPVC is used for information specific to OS (e.g. Linux version, Linux
+distribution...)
+
+If this capability is available, then the CPNC and CPVC can be synchronized
+between KVM and userspace via the sync regs mechanism (KVM_SYNC_DIAG318).
+
+8.26 KVM_CAP_X86_USER_SPACE_MSR
+-------------------------------
+
+:Architectures: x86
+
+This capability indicates that KVM supports deflection of MSR reads and
+writes to user space. It can be enabled on a VM level. If enabled, MSR
+accesses that would usually trigger a #GP by KVM into the guest will
+instead get bounced to user space through the KVM_EXIT_X86_RDMSR and
+KVM_EXIT_X86_WRMSR exit notifications.
+
+8.25 KVM_X86_SET_MSR_FILTER
+---------------------------
+
+:Architectures: x86
+
+This capability indicates that KVM supports that accesses to user defined MSRs
+may be rejected. With this capability exposed, KVM exports new VM ioctl
+KVM_X86_SET_MSR_FILTER which user space can call to specify bitmaps of MSR
+ranges that KVM should reject access to.
+
+In combination with KVM_CAP_X86_USER_SPACE_MSR, this allows user space to
+trap and emulate MSRs that are outside of the scope of KVM as well as
+limit the attack surface on KVM's MSR emulation code.
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 96eccb1..5ef2669 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -298,15 +298,15 @@ static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
 	return (kvm_vcpu_get_esr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
 }
 
-static __always_inline bool kvm_vcpu_dabt_iss1tw(const struct kvm_vcpu *vcpu)
+static __always_inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu)
 {
 	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_S1PTW);
 }
 
+/* Always check for S1PTW *before* using this. */
 static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
 {
-	return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR) ||
-		kvm_vcpu_dabt_iss1tw(vcpu); /* AF/DBM update */
+	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR;
 }
 
 static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
@@ -335,6 +335,11 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
 	return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW;
 }
 
+static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu);
+}
+
 static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
 {
 	return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC;
@@ -372,6 +377,9 @@ static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
 
 static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
 {
+	if (kvm_vcpu_abt_iss1tw(vcpu))
+		return true;
+
 	if (kvm_vcpu_trap_is_iabt(vcpu))
 		return false;
 
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index eeac62b..313a8fa3 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -446,7 +446,7 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 			kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
 			kvm_vcpu_dabt_isvalid(vcpu) &&
 			!kvm_vcpu_abt_issea(vcpu) &&
-			!kvm_vcpu_dabt_iss1tw(vcpu);
+			!kvm_vcpu_abt_iss1tw(vcpu);
 
 		if (valid) {
 			int ret = __vgic_v2_perform_cpuif_access(vcpu);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index a816cb8..19aacc7 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -759,7 +759,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	struct kvm_pgtable *pgt;
 
 	write_fault = kvm_is_write_fault(vcpu);
-	exec_fault = kvm_vcpu_trap_is_iabt(vcpu);
+	exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
 	VM_BUG_ON(write_fault && exec_fault);
 
 	if (fault_status == FSC_PERM && !write_fault && !exec_fault) {
@@ -984,7 +984,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
 			goto out;
 		}
 
-		if (kvm_vcpu_dabt_iss1tw(vcpu)) {
+		if (kvm_vcpu_abt_iss1tw(vcpu)) {
 			kvm_inject_dabt(vcpu, kvm_vcpu_get_hfar(vcpu));
 			ret = 1;
 			goto out_unlock;
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 825d337..24f3d0f 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -341,7 +341,7 @@ struct kvm_mips_tlb {
 #define KVM_MIPS_GUEST_TLB_SIZE	64
 struct kvm_vcpu_arch {
 	void *guest_ebase;
-	int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu);
+	int (*vcpu_run)(struct kvm_vcpu *vcpu);
 
 	/* Host registers preserved across guest mode execution */
 	unsigned long host_stack;
@@ -852,7 +852,7 @@ int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks);
 /* Debug: dump vcpu state */
 int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu);
 
-extern int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu);
+extern int kvm_mips_handle_exit(struct kvm_vcpu *vcpu);
 
 /* Building of entry/exception code */
 int kvm_mips_entry_setup(void);
diff --git a/arch/mips/kvm/entry.c b/arch/mips/kvm/entry.c
index fd71694..832475b 100644
--- a/arch/mips/kvm/entry.c
+++ b/arch/mips/kvm/entry.c
@@ -205,7 +205,7 @@ static inline void build_set_exc_base(u32 **p, unsigned int reg)
  * Assemble the start of the vcpu_run function to run a guest VCPU. The function
  * conforms to the following prototype:
  *
- * int vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu);
+ * int vcpu_run(struct kvm_vcpu *vcpu);
  *
  * The exit from the guest and return to the caller is handled by the code
  * generated by kvm_mips_build_ret_to_host().
@@ -218,8 +218,7 @@ void *kvm_mips_build_vcpu_run(void *addr)
 	unsigned int i;
 
 	/*
-	 * A0: run
-	 * A1: vcpu
+	 * A0: vcpu
 	 */
 
 	/* k0/k1 not being used in host kernel context */
@@ -238,10 +237,10 @@ void *kvm_mips_build_vcpu_run(void *addr)
 	kvm_mips_build_save_scratch(&p, V1, K1);
 
 	/* VCPU scratch register has pointer to vcpu */
-	UASM_i_MTC0(&p, A1, scratch_vcpu[0], scratch_vcpu[1]);
+	UASM_i_MTC0(&p, A0, scratch_vcpu[0], scratch_vcpu[1]);
 
 	/* Offset into vcpu->arch */
-	UASM_i_ADDIU(&p, K1, A1, offsetof(struct kvm_vcpu, arch));
+	UASM_i_ADDIU(&p, K1, A0, offsetof(struct kvm_vcpu, arch));
 
 	/*
 	 * Save the host stack to VCPU, used for exception processing
@@ -645,10 +644,7 @@ void *kvm_mips_build_exit(void *addr)
 	/* Now that context has been saved, we can use other registers */
 
 	/* Restore vcpu */
-	UASM_i_MFC0(&p, S1, scratch_vcpu[0], scratch_vcpu[1]);
-
-	/* Restore run (vcpu->run) */
-	UASM_i_LW(&p, S0, offsetof(struct kvm_vcpu, run), S1);
+	UASM_i_MFC0(&p, S0, scratch_vcpu[0], scratch_vcpu[1]);
 
 	/*
 	 * Save Host level EPC, BadVaddr and Cause to VCPU, useful to process
@@ -810,7 +806,6 @@ void *kvm_mips_build_exit(void *addr)
 	 * with this in the kernel
 	 */
 	uasm_i_move(&p, A0, S0);
-	uasm_i_move(&p, A1, S1);
 	UASM_i_LA(&p, T9, (unsigned long)kvm_mips_handle_exit);
 	uasm_i_jalr(&p, RA, T9);
 	 UASM_i_ADDIU(&p, SP, SP, -CALLFRAME_SIZ);
@@ -852,7 +847,7 @@ static void *kvm_mips_build_ret_from_exit(void *addr)
 	 * guest, reload k1
 	 */
 
-	uasm_i_move(&p, K1, S1);
+	uasm_i_move(&p, K1, S0);
 	UASM_i_ADDIU(&p, K1, K1, offsetof(struct kvm_vcpu, arch));
 
 	/*
@@ -886,8 +881,8 @@ static void *kvm_mips_build_ret_to_guest(void *addr)
 {
 	u32 *p = addr;
 
-	/* Put the saved pointer to vcpu (s1) back into the scratch register */
-	UASM_i_MTC0(&p, S1, scratch_vcpu[0], scratch_vcpu[1]);
+	/* Put the saved pointer to vcpu (s0) back into the scratch register */
+	UASM_i_MTC0(&p, S0, scratch_vcpu[0], scratch_vcpu[1]);
 
 	/* Load up the Guest EBASE to minimize the window where BEV is set */
 	UASM_i_LW(&p, T0, offsetof(struct kvm_vcpu_arch, guest_ebase), K1);
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 7de85d2..3d6a7f5 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -137,6 +137,8 @@ extern void kvm_init_loongson_ipi(struct kvm *kvm);
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	switch (type) {
+	case KVM_VM_MIPS_AUTO:
+		break;
 #ifdef CONFIG_KVM_MIPS_VZ
 	case KVM_VM_MIPS_VZ:
 #else
@@ -1197,8 +1199,9 @@ static void kvm_mips_set_c0_status(void)
 /*
  * Return value is in the form (errcode<<2 | RESUME_FLAG_HOST | RESUME_FLAG_NV)
  */
-int kvm_mips_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
+int kvm_mips_handle_exit(struct kvm_vcpu *vcpu)
 {
+	struct kvm_run *run = vcpu->run;
 	u32 cause = vcpu->arch.host_cp0_cause;
 	u32 exccode = (cause >> CAUSEB_EXCCODE) & 0x1f;
 	u32 __user *opc = (u32 __user *) vcpu->arch.pc;
diff --git a/arch/mips/kvm/trap_emul.c b/arch/mips/kvm/trap_emul.c
index f8cba51..0788c00 100644
--- a/arch/mips/kvm/trap_emul.c
+++ b/arch/mips/kvm/trap_emul.c
@@ -1241,7 +1241,7 @@ static int kvm_trap_emul_vcpu_run(struct kvm_vcpu *vcpu)
 	 */
 	kvm_mips_suspend_mm(cpu);
 
-	r = vcpu->arch.vcpu_run(vcpu->run, vcpu);
+	r = vcpu->arch.vcpu_run(vcpu);
 
 	/* We may have migrated while handling guest exits */
 	cpu = smp_processor_id();
diff --git a/arch/mips/kvm/vz.c b/arch/mips/kvm/vz.c
index c299e5d..2ffbe92 100644
--- a/arch/mips/kvm/vz.c
+++ b/arch/mips/kvm/vz.c
@@ -3266,7 +3266,7 @@ static int kvm_vz_vcpu_run(struct kvm_vcpu *vcpu)
 	kvm_vz_vcpu_load_tlb(vcpu, cpu);
 	kvm_vz_vcpu_load_wired(vcpu);
 
-	r = vcpu->arch.vcpu_run(vcpu->run, vcpu);
+	r = vcpu->arch.vcpu_run(vcpu);
 
 	kvm_vz_vcpu_save_wired(vcpu);
 
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 10ded83..d67a470 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -326,6 +326,7 @@ struct kvm_arch {
 #endif
 #ifdef CONFIG_KVM_XICS
 	struct kvmppc_xics *xics;
+	struct kvmppc_xics *xics_device;
 	struct kvmppc_xive *xive;    /* Current XIVE device in use */
 	struct {
 		struct kvmppc_xive *native;
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 49db50d..44bf567 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -558,12 +558,12 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
@@ -879,13 +879,15 @@ void kvmppc_core_destroy_vm(struct kvm *kvm)
 
 #ifdef CONFIG_KVM_XICS
 	/*
-	 * Free the XIVE devices which are not directly freed by the
+	 * Free the XIVE and XICS devices which are not directly freed by the
 	 * device 'release' method
 	 */
 	kfree(kvm->arch.xive_devices.native);
 	kvm->arch.xive_devices.native = NULL;
 	kfree(kvm->arch.xive_devices.xics_on_xive);
 	kvm->arch.xive_devices.xics_on_xive = NULL;
+	kfree(kvm->arch.xics_device);
+	kvm->arch.xics_device = NULL;
 #endif /* CONFIG_KVM_XICS */
 }
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 22a677b..bb35490 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -347,7 +347,7 @@ static unsigned long kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep,
 	return __radix_pte_update(ptep, clr, set);
 }
 
-void kvmppc_radix_set_pte_at(struct kvm *kvm, unsigned long addr,
+static void kvmppc_radix_set_pte_at(struct kvm *kvm, unsigned long addr,
 			     pte_t *ptep, pte_t pte)
 {
 	radix__set_pte_at(kvm->mm, addr, ptep, pte, 0);
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 1a529df..8da93fd 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -283,7 +283,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	struct kvmppc_spapr_tce_table *siter;
 	struct mm_struct *mm = kvm->mm;
 	unsigned long npages, size = args->size;
-	int ret = -ENOMEM;
+	int ret;
 
 	if (!args->size || args->page_shift < 12 || args->page_shift > 34 ||
 		(args->offset + args->size > (ULLONG_MAX >> args->page_shift)))
@@ -489,7 +489,7 @@ static long kvmppc_tce_iommu_unmap(struct kvm *kvm,
 	return ret;
 }
 
-long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
+static long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 		unsigned long entry, unsigned long ua,
 		enum dma_data_direction dir)
 {
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index ac6ac19..470e7c5 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -237,7 +237,7 @@ static long iommu_tce_xchg_no_kill_rm(struct mm_struct *mm,
 	return ret;
 }
 
-extern void iommu_tce_kill_rm(struct iommu_table *tbl,
+static void iommu_tce_kill_rm(struct iommu_table *tbl,
 		unsigned long entry, unsigned long pages)
 {
 	if (tbl->it_ops->tce_kill)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 4ba06a2..490a0f6 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3442,9 +3442,19 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 	unsigned long host_psscr = mfspr(SPRN_PSSCR);
 	unsigned long host_pidr = mfspr(SPRN_PID);
 
+	/*
+	 * P8 and P9 suppress the HDEC exception when LPCR[HDICE] = 0,
+	 * so set HDICE before writing HDEC.
+	 */
+	mtspr(SPRN_LPCR, vcpu->kvm->arch.host_lpcr | LPCR_HDICE);
+	isync();
+
 	hdec = time_limit - mftb();
-	if (hdec < 0)
+	if (hdec < 0) {
+		mtspr(SPRN_LPCR, vcpu->kvm->arch.host_lpcr);
+		isync();
 		return BOOK3S_INTERRUPT_HV_DECREMENTER;
+	}
 	mtspr(SPRN_HDEC, hdec);
 
 	if (vc->tb_offset) {
@@ -3558,7 +3568,7 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
  * Virtual-mode guest entry for POWER9 and later when the host and
  * guest are both using the radix MMU.  The LPIDR has already been set.
  */
-int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
+static int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 			 unsigned long lpcr)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
@@ -3572,7 +3582,7 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	dec = mfspr(SPRN_DEC);
 	tb = mftb();
-	if (dec < 512)
+	if (dec < 0)
 		return BOOK3S_INTERRUPT_HV_DECREMENTER;
 	local_paca->kvm_hstate.dec_expires = dec + tb;
 	if (local_paca->kvm_hstate.dec_expires < time_limit)
@@ -5250,6 +5260,12 @@ static long kvm_arch_vm_ioctl_hv(struct file *filp,
 	case KVM_PPC_ALLOCATE_HTAB: {
 		u32 htab_order;
 
+		/* If we're a nested hypervisor, we currently only support radix */
+		if (kvmhv_on_pseries()) {
+			r = -EOPNOTSUPP;
+			break;
+		}
+
 		r = -EFAULT;
 		if (get_user(htab_order, (u32 __user *)argp))
 			break;
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index 59822cb..327417d 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -58,13 +58,16 @@
 	/*
 	 * Put whatever is in the decrementer into the
 	 * hypervisor decrementer.
+	 * Because of a hardware deviation in P8 and P9,
+	 * we need to set LPCR[HDICE] before writing HDEC.
 	 */
-BEGIN_FTR_SECTION
 	ld	r5, HSTATE_KVM_VCORE(r13)
 	ld	r6, VCORE_KVM(r5)
 	ld	r9, KVM_HOST_LPCR(r6)
-	andis.	r9, r9, LPCR_LD@h
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+	ori	r8, r9, LPCR_HDICE
+	mtspr	SPRN_LPCR, r8
+	isync
+	andis.	r0, r9, LPCR_LD@h
 	mfspr	r8,SPRN_DEC
 	mftb	r7
 BEGIN_FTR_SECTION
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 6822d23..33b5854 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -569,7 +569,7 @@ static void kvmhv_update_ptbl_cache(struct kvm_nested_guest *gp)
 	kvmhv_set_nested_ptbl(gp);
 }
 
-struct kvm_nested_guest *kvmhv_alloc_nested(struct kvm *kvm, unsigned int lpid)
+static struct kvm_nested_guest *kvmhv_alloc_nested(struct kvm *kvm, unsigned int lpid)
 {
 	struct kvm_nested_guest *gp;
 	long shadow_lpid;
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index 4d7e561..c2c9c73 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -764,7 +764,7 @@ int xics_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
 	return ics_rm_eoi(vcpu, irq);
 }
 
-unsigned long eoi_rc;
+static unsigned long eoi_rc;
 
 static void icp_eoi(struct irq_chip *c, u32 hwirq, __be32 xirr, bool *again)
 {
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 88fac22..b1fefa6 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -569,7 +569,7 @@ static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr)
 #endif
 }
 
-void kvmppc_set_pvr_pr(struct kvm_vcpu *vcpu, u32 pvr)
+static void kvmppc_set_pvr_pr(struct kvm_vcpu *vcpu, u32 pvr)
 {
 	u32 host_pvr;
 
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index 381bf8d..5fee5a1 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -1334,47 +1334,97 @@ static int xics_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 	return -ENXIO;
 }
 
-static void kvmppc_xics_free(struct kvm_device *dev)
+/*
+ * Called when device fd is closed. kvm->lock is held.
+ */
+static void kvmppc_xics_release(struct kvm_device *dev)
 {
 	struct kvmppc_xics *xics = dev->private;
 	int i;
 	struct kvm *kvm = xics->kvm;
+	struct kvm_vcpu *vcpu;
+
+	pr_devel("Releasing xics device\n");
+
+	/*
+	 * Since this is the device release function, we know that
+	 * userspace does not have any open fd referring to the
+	 * device.  Therefore there can not be any of the device
+	 * attribute set/get functions being executed concurrently,
+	 * and similarly, the connect_vcpu and set/clr_mapped
+	 * functions also cannot be being executed.
+	 */
 
 	debugfs_remove(xics->dentry);
 
+	/*
+	 * We should clean up the vCPU interrupt presenters first.
+	 */
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		/*
+		 * Take vcpu->mutex to ensure that no one_reg get/set ioctl
+		 * (i.e. kvmppc_xics_[gs]et_icp) can be done concurrently.
+		 * Holding the vcpu->mutex also means that execution is
+		 * excluded for the vcpu until the ICP was freed. When the vcpu
+		 * can execute again, vcpu->arch.icp and vcpu->arch.irq_type
+		 * have been cleared and the vcpu will not be going into the
+		 * XICS code anymore.
+		 */
+		mutex_lock(&vcpu->mutex);
+		kvmppc_xics_free_icp(vcpu);
+		mutex_unlock(&vcpu->mutex);
+	}
+
 	if (kvm)
 		kvm->arch.xics = NULL;
 
-	for (i = 0; i <= xics->max_icsid; i++)
+	for (i = 0; i <= xics->max_icsid; i++) {
 		kfree(xics->ics[i]);
-	kfree(xics);
+		xics->ics[i] = NULL;
+	}
+	/*
+	 * A reference of the kvmppc_xics pointer is now kept under
+	 * the xics_device pointer of the machine for reuse. It is
+	 * freed when the VM is destroyed for now until we fix all the
+	 * execution paths.
+	 */
 	kfree(dev);
 }
 
+static struct kvmppc_xics *kvmppc_xics_get_device(struct kvm *kvm)
+{
+	struct kvmppc_xics **kvm_xics_device = &kvm->arch.xics_device;
+	struct kvmppc_xics *xics = *kvm_xics_device;
+
+	if (!xics) {
+		xics = kzalloc(sizeof(*xics), GFP_KERNEL);
+		*kvm_xics_device = xics;
+	} else {
+		memset(xics, 0, sizeof(*xics));
+	}
+
+	return xics;
+}
+
 static int kvmppc_xics_create(struct kvm_device *dev, u32 type)
 {
 	struct kvmppc_xics *xics;
 	struct kvm *kvm = dev->kvm;
-	int ret = 0;
 
-	xics = kzalloc(sizeof(*xics), GFP_KERNEL);
+	pr_devel("Creating xics for partition\n");
+
+	/* Already there ? */
+	if (kvm->arch.xics)
+		return -EEXIST;
+
+	xics = kvmppc_xics_get_device(kvm);
 	if (!xics)
 		return -ENOMEM;
 
 	dev->private = xics;
 	xics->dev = dev;
 	xics->kvm = kvm;
-
-	/* Already there ? */
-	if (kvm->arch.xics)
-		ret = -EEXIST;
-	else
-		kvm->arch.xics = xics;
-
-	if (ret) {
-		kfree(xics);
-		return ret;
-	}
+	kvm->arch.xics = xics;
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	if (cpu_has_feature(CPU_FTR_ARCH_206) &&
@@ -1399,7 +1449,7 @@ struct kvm_device_ops kvm_xics_ops = {
 	.name = "kvm-xics",
 	.create = kvmppc_xics_create,
 	.init = kvmppc_xics_init,
-	.destroy = kvmppc_xics_free,
+	.release = kvmppc_xics_release,
 	.set_attr = xics_set_attr,
 	.get_attr = xics_get_attr,
 	.has_attr = xics_has_attr,
@@ -1415,7 +1465,7 @@ int kvmppc_xics_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu,
 		return -EPERM;
 	if (xics->kvm != vcpu->kvm)
 		return -EPERM;
-	if (vcpu->arch.irq_type)
+	if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT)
 		return -EBUSY;
 
 	r = kvmppc_xics_create_icp(vcpu, xcpu);
diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
index bdea91d..d0c2db0 100644
--- a/arch/powerpc/kvm/book3s_xive_native.c
+++ b/arch/powerpc/kvm/book3s_xive_native.c
@@ -1227,17 +1227,7 @@ static int xive_native_debug_show(struct seq_file *m, void *private)
 	return 0;
 }
 
-static int xive_native_debug_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, xive_native_debug_show, inode->i_private);
-}
-
-static const struct file_operations xive_native_debug_fops = {
-	.open = xive_native_debug_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(xive_native_debug);
 
 static void xive_native_debugfs_init(struct kvmppc_xive *xive)
 {
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 3e1c9f0..b1abcb8 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -1747,12 +1747,12 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
 
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
@@ -1773,7 +1773,7 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 
 int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index dde7cb3..877970d 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -36,6 +36,10 @@
 #define STATIC
 #include <linux/decompress/mm.h>
 
+#define _SETUP
+#include <asm/setup.h>	/* For COMMAND_LINE_SIZE */
+#undef _SETUP
+
 #ifdef CONFIG_X86_5LEVEL
 unsigned int __pgtable_l5_enabled;
 unsigned int pgdir_shift __ro_after_init = 39;
@@ -87,8 +91,11 @@ static unsigned long get_boot_seed(void)
 static bool memmap_too_large;
 
 
-/* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */
-static unsigned long long mem_limit = ULLONG_MAX;
+/*
+ * Store memory limit: MAXMEM on 64-bit and KERNEL_IMAGE_SIZE on 32-bit.
+ * It may be reduced by "mem=nn[KMG]" or "memmap=nn[KMG]" command line options.
+ */
+static u64 mem_limit;
 
 /* Number of immovable memory regions */
 static int num_immovable_mem;
@@ -131,8 +138,7 @@ enum parse_mode {
 };
 
 static int
-parse_memmap(char *p, unsigned long long *start, unsigned long long *size,
-		enum parse_mode mode)
+parse_memmap(char *p, u64 *start, u64 *size, enum parse_mode mode)
 {
 	char *oldp;
 
@@ -162,7 +168,7 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size,
 			 */
 			*size = 0;
 		} else {
-			unsigned long long flags;
+			u64 flags;
 
 			/*
 			 * efi_fake_mem=nn@ss:attr the attr specifies
@@ -201,7 +207,7 @@ static void mem_avoid_memmap(enum parse_mode mode, char *str)
 
 	while (str && (i < MAX_MEMMAP_REGIONS)) {
 		int rc;
-		unsigned long long start, size;
+		u64 start, size;
 		char *k = strchr(str, ',');
 
 		if (k)
@@ -214,7 +220,7 @@ static void mem_avoid_memmap(enum parse_mode mode, char *str)
 
 		if (start == 0) {
 			/* Store the specified memory limit if size > 0 */
-			if (size > 0)
+			if (size > 0 && size < mem_limit)
 				mem_limit = size;
 
 			continue;
@@ -261,15 +267,15 @@ static void parse_gb_huge_pages(char *param, char *val)
 static void handle_mem_options(void)
 {
 	char *args = (char *)get_cmd_line_ptr();
-	size_t len = strlen((char *)args);
+	size_t len;
 	char *tmp_cmdline;
 	char *param, *val;
 	u64 mem_size;
 
-	if (!strstr(args, "memmap=") && !strstr(args, "mem=") &&
-		!strstr(args, "hugepages"))
+	if (!args)
 		return;
 
+	len = strnlen(args, COMMAND_LINE_SIZE-1);
 	tmp_cmdline = malloc(len + 1);
 	if (!tmp_cmdline)
 		error("Failed to allocate space for tmp_cmdline");
@@ -284,14 +290,12 @@ static void handle_mem_options(void)
 	while (*args) {
 		args = next_arg(args, &param, &val);
 		/* Stop at -- */
-		if (!val && strcmp(param, "--") == 0) {
-			warn("Only '--' specified in cmdline");
-			goto out;
-		}
+		if (!val && strcmp(param, "--") == 0)
+			break;
 
 		if (!strcmp(param, "memmap")) {
 			mem_avoid_memmap(PARSE_MEMMAP, val);
-		} else if (strstr(param, "hugepages")) {
+		} else if (IS_ENABLED(CONFIG_X86_64) && strstr(param, "hugepages")) {
 			parse_gb_huge_pages(param, val);
 		} else if (!strcmp(param, "mem")) {
 			char *p = val;
@@ -300,21 +304,23 @@ static void handle_mem_options(void)
 				continue;
 			mem_size = memparse(p, &p);
 			if (mem_size == 0)
-				goto out;
+				break;
 
-			mem_limit = mem_size;
+			if (mem_size < mem_limit)
+				mem_limit = mem_size;
 		} else if (!strcmp(param, "efi_fake_mem")) {
 			mem_avoid_memmap(PARSE_EFI, val);
 		}
 	}
 
-out:
 	free(tmp_cmdline);
 	return;
 }
 
 /*
- * In theory, KASLR can put the kernel anywhere in the range of [16M, 64T).
+ * In theory, KASLR can put the kernel anywhere in the range of [16M, MAXMEM)
+ * on 64-bit, and [16M, KERNEL_IMAGE_SIZE) on 32-bit.
+ *
  * The mem_avoid array is used to store the ranges that need to be avoided
  * when KASLR searches for an appropriate random address. We must avoid any
  * regions that are unsafe to overlap with during decompression, and other
@@ -392,8 +398,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 {
 	unsigned long init_size = boot_params->hdr.init_size;
 	u64 initrd_start, initrd_size;
-	u64 cmd_line, cmd_line_size;
-	char *ptr;
+	unsigned long cmd_line, cmd_line_size;
 
 	/*
 	 * Avoid the region that is unsafe to overlap during
@@ -414,16 +419,15 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 	/* No need to set mapping for initrd, it will be handled in VO. */
 
 	/* Avoid kernel command line. */
-	cmd_line  = (u64)boot_params->ext_cmd_line_ptr << 32;
-	cmd_line |= boot_params->hdr.cmd_line_ptr;
+	cmd_line = get_cmd_line_ptr();
 	/* Calculate size of cmd_line. */
-	ptr = (char *)(unsigned long)cmd_line;
-	for (cmd_line_size = 0; ptr[cmd_line_size++];)
-		;
-	mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line;
-	mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size;
-	add_identity_map(mem_avoid[MEM_AVOID_CMDLINE].start,
-			 mem_avoid[MEM_AVOID_CMDLINE].size);
+	if (cmd_line) {
+		cmd_line_size = strnlen((char *)cmd_line, COMMAND_LINE_SIZE-1) + 1;
+		mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line;
+		mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size;
+		add_identity_map(mem_avoid[MEM_AVOID_CMDLINE].start,
+				 mem_avoid[MEM_AVOID_CMDLINE].size);
+	}
 
 	/* Avoid boot parameters. */
 	mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params;
@@ -454,7 +458,7 @@ static bool mem_avoid_overlap(struct mem_vector *img,
 {
 	int i;
 	struct setup_data *ptr;
-	unsigned long earliest = img->start + img->size;
+	u64 earliest = img->start + img->size;
 	bool is_overlapping = false;
 
 	for (i = 0; i < MEM_AVOID_MAX; i++) {
@@ -499,18 +503,16 @@ static bool mem_avoid_overlap(struct mem_vector *img,
 }
 
 struct slot_area {
-	unsigned long addr;
-	int num;
+	u64 addr;
+	unsigned long num;
 };
 
 #define MAX_SLOT_AREA 100
 
 static struct slot_area slot_areas[MAX_SLOT_AREA];
-
+static unsigned int slot_area_index;
 static unsigned long slot_max;
 
-static unsigned long slot_area_index;
-
 static void store_slot_info(struct mem_vector *region, unsigned long image_size)
 {
 	struct slot_area slot_area;
@@ -519,13 +521,10 @@ static void store_slot_info(struct mem_vector *region, unsigned long image_size)
 		return;
 
 	slot_area.addr = region->start;
-	slot_area.num = (region->size - image_size) /
-			CONFIG_PHYSICAL_ALIGN + 1;
+	slot_area.num = 1 + (region->size - image_size) / CONFIG_PHYSICAL_ALIGN;
 
-	if (slot_area.num > 0) {
-		slot_areas[slot_area_index++] = slot_area;
-		slot_max += slot_area.num;
-	}
+	slot_areas[slot_area_index++] = slot_area;
+	slot_max += slot_area.num;
 }
 
 /*
@@ -535,57 +534,53 @@ static void store_slot_info(struct mem_vector *region, unsigned long image_size)
 static void
 process_gb_huge_pages(struct mem_vector *region, unsigned long image_size)
 {
-	unsigned long addr, size = 0;
+	u64 pud_start, pud_end;
+	unsigned long gb_huge_pages;
 	struct mem_vector tmp;
-	int i = 0;
 
-	if (!max_gb_huge_pages) {
+	if (!IS_ENABLED(CONFIG_X86_64) || !max_gb_huge_pages) {
 		store_slot_info(region, image_size);
 		return;
 	}
 
-	addr = ALIGN(region->start, PUD_SIZE);
-	/* Did we raise the address above the passed in memory entry? */
-	if (addr < region->start + region->size)
-		size = region->size - (addr - region->start);
-
-	/* Check how many 1GB huge pages can be filtered out: */
-	while (size > PUD_SIZE && max_gb_huge_pages) {
-		size -= PUD_SIZE;
-		max_gb_huge_pages--;
-		i++;
-	}
+	/* Are there any 1GB pages in the region? */
+	pud_start = ALIGN(region->start, PUD_SIZE);
+	pud_end = ALIGN_DOWN(region->start + region->size, PUD_SIZE);
 
 	/* No good 1GB huge pages found: */
-	if (!i) {
+	if (pud_start >= pud_end) {
 		store_slot_info(region, image_size);
 		return;
 	}
 
-	/*
-	 * Skip those 'i'*1GB good huge pages, and continue checking and
-	 * processing the remaining head or tail part of the passed region
-	 * if available.
-	 */
-
-	if (addr >= region->start + image_size) {
+	/* Check if the head part of the region is usable. */
+	if (pud_start >= region->start + image_size) {
 		tmp.start = region->start;
-		tmp.size = addr - region->start;
+		tmp.size = pud_start - region->start;
 		store_slot_info(&tmp, image_size);
 	}
 
-	size  = region->size - (addr - region->start) - i * PUD_SIZE;
-	if (size >= image_size) {
-		tmp.start = addr + i * PUD_SIZE;
-		tmp.size = size;
+	/* Skip the good 1GB pages. */
+	gb_huge_pages = (pud_end - pud_start) >> PUD_SHIFT;
+	if (gb_huge_pages > max_gb_huge_pages) {
+		pud_end = pud_start + (max_gb_huge_pages << PUD_SHIFT);
+		max_gb_huge_pages = 0;
+	} else {
+		max_gb_huge_pages -= gb_huge_pages;
+	}
+
+	/* Check if the tail part of the region is usable. */
+	if (region->start + region->size >= pud_end + image_size) {
+		tmp.start = pud_end;
+		tmp.size = region->start + region->size - pud_end;
 		store_slot_info(&tmp, image_size);
 	}
 }
 
-static unsigned long slots_fetch_random(void)
+static u64 slots_fetch_random(void)
 {
 	unsigned long slot;
-	int i;
+	unsigned int i;
 
 	/* Handle case of no slots stored. */
 	if (slot_max == 0)
@@ -598,7 +593,7 @@ static unsigned long slots_fetch_random(void)
 			slot -= slot_areas[i].num;
 			continue;
 		}
-		return slot_areas[i].addr + slot * CONFIG_PHYSICAL_ALIGN;
+		return slot_areas[i].addr + ((u64)slot * CONFIG_PHYSICAL_ALIGN);
 	}
 
 	if (i == slot_area_index)
@@ -611,49 +606,23 @@ static void __process_mem_region(struct mem_vector *entry,
 				 unsigned long image_size)
 {
 	struct mem_vector region, overlap;
-	unsigned long start_orig, end;
-	struct mem_vector cur_entry;
+	u64 region_end;
 
-	/* On 32-bit, ignore entries entirely above our maximum. */
-	if (IS_ENABLED(CONFIG_X86_32) && entry->start >= KERNEL_IMAGE_SIZE)
-		return;
-
-	/* Ignore entries entirely below our minimum. */
-	if (entry->start + entry->size < minimum)
-		return;
-
-	/* Ignore entries above memory limit */
-	end = min(entry->size + entry->start, mem_limit);
-	if (entry->start >= end)
-		return;
-	cur_entry.start = entry->start;
-	cur_entry.size = end - entry->start;
-
-	region.start = cur_entry.start;
-	region.size = cur_entry.size;
+	/* Enforce minimum and memory limit. */
+	region.start = max_t(u64, entry->start, minimum);
+	region_end = min(entry->start + entry->size, mem_limit);
 
 	/* Give up if slot area array is full. */
 	while (slot_area_index < MAX_SLOT_AREA) {
-		start_orig = region.start;
-
-		/* Potentially raise address to minimum location. */
-		if (region.start < minimum)
-			region.start = minimum;
-
 		/* Potentially raise address to meet alignment needs. */
 		region.start = ALIGN(region.start, CONFIG_PHYSICAL_ALIGN);
 
 		/* Did we raise the address above the passed in memory entry? */
-		if (region.start > cur_entry.start + cur_entry.size)
+		if (region.start > region_end)
 			return;
 
 		/* Reduce size by any delta from the original address. */
-		region.size -= region.start - start_orig;
-
-		/* On 32-bit, reduce region size to fit within max size. */
-		if (IS_ENABLED(CONFIG_X86_32) &&
-		    region.start + region.size > KERNEL_IMAGE_SIZE)
-			region.size = KERNEL_IMAGE_SIZE - region.start;
+		region.size = region_end - region.start;
 
 		/* Return if region can't contain decompressed kernel */
 		if (region.size < image_size)
@@ -666,27 +635,19 @@ static void __process_mem_region(struct mem_vector *entry,
 		}
 
 		/* Store beginning of region if holds at least image_size. */
-		if (overlap.start > region.start + image_size) {
-			struct mem_vector beginning;
-
-			beginning.start = region.start;
-			beginning.size = overlap.start - region.start;
-			process_gb_huge_pages(&beginning, image_size);
+		if (overlap.start >= region.start + image_size) {
+			region.size = overlap.start - region.start;
+			process_gb_huge_pages(&region, image_size);
 		}
 
-		/* Return if overlap extends to or past end of region. */
-		if (overlap.start + overlap.size >= region.start + region.size)
-			return;
-
 		/* Clip off the overlapping region and start over. */
-		region.size -= overlap.start - region.start + overlap.size;
 		region.start = overlap.start + overlap.size;
 	}
 }
 
 static bool process_mem_region(struct mem_vector *region,
-			       unsigned long long minimum,
-			       unsigned long long image_size)
+			       unsigned long minimum,
+			       unsigned long image_size)
 {
 	int i;
 	/*
@@ -709,7 +670,7 @@ static bool process_mem_region(struct mem_vector *region,
 	 * immovable memory and @region.
 	 */
 	for (i = 0; i < num_immovable_mem; i++) {
-		unsigned long long start, end, entry_end, region_end;
+		u64 start, end, entry_end, region_end;
 		struct mem_vector entry;
 
 		if (!mem_overlaps(region, &immovable_mem[i]))
@@ -736,8 +697,8 @@ static bool process_mem_region(struct mem_vector *region,
 
 #ifdef CONFIG_EFI
 /*
- * Returns true if mirror region found (and must have been processed
- * for slots adding)
+ * Returns true if we processed the EFI memmap, which we prefer over the E820
+ * table if it is available.
  */
 static bool
 process_efi_entries(unsigned long minimum, unsigned long image_size)
@@ -839,20 +800,30 @@ static void process_e820_entries(unsigned long minimum,
 static unsigned long find_random_phys_addr(unsigned long minimum,
 					   unsigned long image_size)
 {
+	u64 phys_addr;
+
+	/* Bail out early if it's impossible to succeed. */
+	if (minimum + image_size > mem_limit)
+		return 0;
+
 	/* Check if we had too many memmaps. */
 	if (memmap_too_large) {
 		debug_putstr("Aborted memory entries scan (more than 4 memmap= args)!\n");
 		return 0;
 	}
 
-	/* Make sure minimum is aligned. */
-	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
+	if (!process_efi_entries(minimum, image_size))
+		process_e820_entries(minimum, image_size);
 
-	if (process_efi_entries(minimum, image_size))
-		return slots_fetch_random();
+	phys_addr = slots_fetch_random();
 
-	process_e820_entries(minimum, image_size);
-	return slots_fetch_random();
+	/* Perform a final check to make sure the address is in range. */
+	if (phys_addr < minimum || phys_addr + image_size > mem_limit) {
+		warn("Invalid physical address chosen!\n");
+		return 0;
+	}
+
+	return (unsigned long)phys_addr;
 }
 
 static unsigned long find_random_virt_addr(unsigned long minimum,
@@ -860,18 +831,12 @@ static unsigned long find_random_virt_addr(unsigned long minimum,
 {
 	unsigned long slots, random_addr;
 
-	/* Make sure minimum is aligned. */
-	minimum = ALIGN(minimum, CONFIG_PHYSICAL_ALIGN);
-	/* Align image_size for easy slot calculations. */
-	image_size = ALIGN(image_size, CONFIG_PHYSICAL_ALIGN);
-
 	/*
 	 * There are how many CONFIG_PHYSICAL_ALIGN-sized slots
 	 * that can hold image_size within the range of minimum to
 	 * KERNEL_IMAGE_SIZE?
 	 */
-	slots = (KERNEL_IMAGE_SIZE - minimum - image_size) /
-		 CONFIG_PHYSICAL_ALIGN + 1;
+	slots = 1 + (KERNEL_IMAGE_SIZE - minimum - image_size) / CONFIG_PHYSICAL_ALIGN;
 
 	random_addr = kaslr_get_random_long("Virtual") % slots;
 
@@ -908,6 +873,11 @@ void choose_random_location(unsigned long input,
 	/* Prepare to add new identity pagetables on demand. */
 	initialize_identity_maps();
 
+	if (IS_ENABLED(CONFIG_X86_32))
+		mem_limit = KERNEL_IMAGE_SIZE;
+	else
+		mem_limit = MAXMEM;
+
 	/* Record the various known unsafe memory ranges. */
 	mem_avoid_init(input, input_size, *output);
 
@@ -917,6 +887,8 @@ void choose_random_location(unsigned long input,
 	 * location:
 	 */
 	min_addr = min(*output, 512UL << 20);
+	/* Make sure minimum is aligned. */
+	min_addr = ALIGN(min_addr, CONFIG_PHYSICAL_ALIGN);
 
 	/* Walk available memory entries to find a random address. */
 	random_addr = find_random_phys_addr(min_addr, output_size);
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 726e264..3efce27 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -70,8 +70,8 @@ int cmdline_find_option(const char *option, char *buffer, int bufsize);
 int cmdline_find_option_bool(const char *option);
 
 struct mem_vector {
-	unsigned long long start;
-	unsigned long long size;
+	u64 start;
+	u64 size;
 };
 
 #if CONFIG_RANDOMIZE_BASE
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 2901d5d..83fc9d3 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -368,6 +368,7 @@
 #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_SERIALIZE		(18*32+14) /* SERIALIZE instruction */
+#define X86_FEATURE_TSXLDTRK		(18*32+16) /* TSX Suspend Load Address Tracking */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_ARCH_LBR		(18*32+19) /* Intel ARCH LBR */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 0a460f2..21a8b52 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -602,9 +602,7 @@ static inline u64 xgetbv(u32 index)
 {
 	u32 eax, edx;
 
-	asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */
-		     : "=a" (eax), "=d" (edx)
-		     : "c" (index));
+	asm volatile("xgetbv" : "=a" (eax), "=d" (edx) : "c" (index));
 	return eax + ((u64)edx << 32);
 }
 
@@ -613,8 +611,7 @@ static inline void xsetbv(u32 index, u64 value)
 	u32 eax = value;
 	u32 edx = value >> 32;
 
-	asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */
-		     : : "a" (eax), "d" (edx), "c" (index));
+	asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index));
 }
 
 #endif /* _ASM_X86_FPU_INTERNAL_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 5303dbc..d0f77235 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -80,13 +80,14 @@
 #define KVM_REQ_HV_EXIT			KVM_ARCH_REQ(21)
 #define KVM_REQ_HV_STIMER		KVM_ARCH_REQ(22)
 #define KVM_REQ_LOAD_EOI_EXITMAP	KVM_ARCH_REQ(23)
-#define KVM_REQ_GET_VMCS12_PAGES	KVM_ARCH_REQ(24)
+#define KVM_REQ_GET_NESTED_STATE_PAGES	KVM_ARCH_REQ(24)
 #define KVM_REQ_APICV_UPDATE \
 	KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_TLB_FLUSH_CURRENT	KVM_ARCH_REQ(26)
 #define KVM_REQ_HV_TLB_FLUSH \
 	KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_APF_READY		KVM_ARCH_REQ(28)
+#define KVM_REQ_MSR_FILTER_CHANGED	KVM_ARCH_REQ(29)
 
 #define CR0_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
@@ -860,6 +861,13 @@ struct kvm_hv {
 	struct kvm_hv_syndbg hv_syndbg;
 };
 
+struct msr_bitmap_range {
+	u32 flags;
+	u32 nmsrs;
+	u32 base;
+	unsigned long *bitmap;
+};
+
 enum kvm_irqchip_mode {
 	KVM_IRQCHIP_NONE,
 	KVM_IRQCHIP_KERNEL,       /* created with KVM_CREATE_IRQCHIP */
@@ -961,6 +969,15 @@ struct kvm_arch {
 	bool guest_can_read_msr_platform_info;
 	bool exception_payload_enabled;
 
+	/* Deflect RDMSR and WRMSR to user space when they trigger a #GP */
+	u32 user_space_msr_mask;
+
+	struct {
+		u8 count;
+		bool default_allow:1;
+		struct msr_bitmap_range ranges[16];
+	} msr_filter;
+
 	struct kvm_pmu_event_filter *pmu_event_filter;
 	struct task_struct *nx_lpage_recovery_thread;
 };
@@ -1143,7 +1160,12 @@ struct kvm_x86_ops {
 	/* Returns actual tsc_offset set in active VMCS */
 	u64 (*write_l1_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
 
-	void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);
+	/*
+	 * Retrieve somewhat arbitrary exit information.  Intended to be used
+	 * only from within tracepoints to avoid VMREADs when tracing is off.
+	 */
+	void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2,
+			      u32 *exit_int_info, u32 *exit_int_info_err_code);
 
 	int (*check_intercept)(struct kvm_vcpu *vcpu,
 			       struct x86_instruction_info *info,
@@ -1221,12 +1243,13 @@ struct kvm_x86_ops {
 
 	int (*get_msr_feature)(struct kvm_msr_entry *entry);
 
-	bool (*need_emulation_on_page_fault)(struct kvm_vcpu *vcpu);
+	bool (*can_emulate_instruction)(struct kvm_vcpu *vcpu, void *insn, int insn_len);
 
 	bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu);
 	int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu);
 
 	void (*migrate_timers)(struct kvm_vcpu *vcpu);
+	void (*msr_filter_changed)(struct kvm_vcpu *vcpu);
 };
 
 struct kvm_x86_nested_ops {
@@ -1238,7 +1261,7 @@ struct kvm_x86_nested_ops {
 	int (*set_state)(struct kvm_vcpu *vcpu,
 			 struct kvm_nested_state __user *user_kvm_nested_state,
 			 struct kvm_nested_state *kvm_state);
-	bool (*get_vmcs12_pages)(struct kvm_vcpu *vcpu);
+	bool (*get_nested_state_pages)(struct kvm_vcpu *vcpu);
 	int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa);
 
 	int (*enable_evmcs)(struct kvm_vcpu *vcpu,
@@ -1612,8 +1635,8 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low,
 		    unsigned long ipi_bitmap_high, u32 min,
 		    unsigned long icr, int op_64_bit);
 
-void kvm_define_shared_msr(unsigned index, u32 msr);
-int kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
+void kvm_define_user_return_msr(unsigned index, u32 msr);
+int kvm_set_user_return_msr(unsigned index, u64 val, u64 mask);
 
 u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc);
 u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc);
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 59a3e13..5999b0b 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -234,6 +234,12 @@ static inline void clwb(volatile void *__p)
 
 #define nop() asm volatile ("nop")
 
+static inline void serialize(void)
+{
+	/* Instruction opcode for SERIALIZE; supported in binutils >= 2.35. */
+	asm volatile(".byte 0xf, 0x1, 0xe8" ::: "memory");
+}
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_SPECIAL_INSNS_H */
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 8a1f538..71d630b 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -3,10 +3,54 @@
 #define __SVM_H
 
 #include <uapi/asm/svm.h>
+#include <uapi/asm/kvm.h>
 
+/*
+ * 32-bit intercept words in the VMCB Control Area, starting
+ * at Byte offset 000h.
+ */
+
+enum intercept_words {
+	INTERCEPT_CR = 0,
+	INTERCEPT_DR,
+	INTERCEPT_EXCEPTION,
+	INTERCEPT_WORD3,
+	INTERCEPT_WORD4,
+	INTERCEPT_WORD5,
+	MAX_INTERCEPT,
+};
 
 enum {
-	INTERCEPT_INTR,
+	/* Byte offset 000h (word 0) */
+	INTERCEPT_CR0_READ = 0,
+	INTERCEPT_CR3_READ = 3,
+	INTERCEPT_CR4_READ = 4,
+	INTERCEPT_CR8_READ = 8,
+	INTERCEPT_CR0_WRITE = 16,
+	INTERCEPT_CR3_WRITE = 16 + 3,
+	INTERCEPT_CR4_WRITE = 16 + 4,
+	INTERCEPT_CR8_WRITE = 16 + 8,
+	/* Byte offset 004h (word 1) */
+	INTERCEPT_DR0_READ = 32,
+	INTERCEPT_DR1_READ,
+	INTERCEPT_DR2_READ,
+	INTERCEPT_DR3_READ,
+	INTERCEPT_DR4_READ,
+	INTERCEPT_DR5_READ,
+	INTERCEPT_DR6_READ,
+	INTERCEPT_DR7_READ,
+	INTERCEPT_DR0_WRITE = 48,
+	INTERCEPT_DR1_WRITE,
+	INTERCEPT_DR2_WRITE,
+	INTERCEPT_DR3_WRITE,
+	INTERCEPT_DR4_WRITE,
+	INTERCEPT_DR5_WRITE,
+	INTERCEPT_DR6_WRITE,
+	INTERCEPT_DR7_WRITE,
+	/* Byte offset 008h (word 2) */
+	INTERCEPT_EXCEPTION_OFFSET = 64,
+	/* Byte offset 00Ch (word 3) */
+	INTERCEPT_INTR = 96,
 	INTERCEPT_NMI,
 	INTERCEPT_SMI,
 	INTERCEPT_INIT,
@@ -38,7 +82,8 @@ enum {
 	INTERCEPT_TASK_SWITCH,
 	INTERCEPT_FERR_FREEZE,
 	INTERCEPT_SHUTDOWN,
-	INTERCEPT_VMRUN,
+	/* Byte offset 010h (word 4) */
+	INTERCEPT_VMRUN = 128,
 	INTERCEPT_VMMCALL,
 	INTERCEPT_VMLOAD,
 	INTERCEPT_VMSAVE,
@@ -53,15 +98,18 @@ enum {
 	INTERCEPT_MWAIT_COND,
 	INTERCEPT_XSETBV,
 	INTERCEPT_RDPRU,
+	/* Byte offset 014h (word 5) */
+	INTERCEPT_INVLPGB = 160,
+	INTERCEPT_INVLPGB_ILLEGAL,
+	INTERCEPT_INVPCID,
+	INTERCEPT_MCOMMIT,
+	INTERCEPT_TLBSYNC,
 };
 
 
 struct __attribute__ ((__packed__)) vmcb_control_area {
-	u32 intercept_cr;
-	u32 intercept_dr;
-	u32 intercept_exceptions;
-	u64 intercept;
-	u8 reserved_1[40];
+	u32 intercepts[MAX_INTERCEPT];
+	u32 reserved_1[15 - MAX_INTERCEPT];
 	u16 pause_filter_thresh;
 	u16 pause_filter_count;
 	u64 iopm_base_pa;
@@ -150,14 +198,14 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 #define SVM_NESTED_CTL_NP_ENABLE	BIT(0)
 #define SVM_NESTED_CTL_SEV_ENABLE	BIT(1)
 
-struct __attribute__ ((__packed__)) vmcb_seg {
+struct vmcb_seg {
 	u16 selector;
 	u16 attrib;
 	u32 limit;
 	u64 base;
-};
+} __packed;
 
-struct __attribute__ ((__packed__)) vmcb_save_area {
+struct vmcb_save_area {
 	struct vmcb_seg es;
 	struct vmcb_seg cs;
 	struct vmcb_seg ss;
@@ -200,20 +248,67 @@ struct __attribute__ ((__packed__)) vmcb_save_area {
 	u64 br_to;
 	u64 last_excp_from;
 	u64 last_excp_to;
-};
 
+	/*
+	 * The following part of the save area is valid only for
+	 * SEV-ES guests when referenced through the GHCB.
+	 */
+	u8 reserved_7[104];
+	u64 reserved_8;		/* rax already available at 0x01f8 */
+	u64 rcx;
+	u64 rdx;
+	u64 rbx;
+	u64 reserved_9;		/* rsp already available at 0x01d8 */
+	u64 rbp;
+	u64 rsi;
+	u64 rdi;
+	u64 r8;
+	u64 r9;
+	u64 r10;
+	u64 r11;
+	u64 r12;
+	u64 r13;
+	u64 r14;
+	u64 r15;
+	u8 reserved_10[16];
+	u64 sw_exit_code;
+	u64 sw_exit_info_1;
+	u64 sw_exit_info_2;
+	u64 sw_scratch;
+	u8 reserved_11[56];
+	u64 xcr0;
+	u8 valid_bitmap[16];
+	u64 x87_state_gpa;
+} __packed;
+
+struct ghcb {
+	struct vmcb_save_area save;
+	u8 reserved_save[2048 - sizeof(struct vmcb_save_area)];
+
+	u8 shared_buffer[2032];
+
+	u8 reserved_1[10];
+	u16 protocol_version;	/* negotiated SEV-ES/GHCB protocol version */
+	u32 ghcb_usage;
+} __packed;
+
+
+#define EXPECTED_VMCB_SAVE_AREA_SIZE		1032
+#define EXPECTED_VMCB_CONTROL_AREA_SIZE		256
+#define EXPECTED_GHCB_SIZE			PAGE_SIZE
 
 static inline void __unused_size_checks(void)
 {
-	BUILD_BUG_ON(sizeof(struct vmcb_save_area) != 0x298);
-	BUILD_BUG_ON(sizeof(struct vmcb_control_area) != 256);
+	BUILD_BUG_ON(sizeof(struct vmcb_save_area)	!= EXPECTED_VMCB_SAVE_AREA_SIZE);
+	BUILD_BUG_ON(sizeof(struct vmcb_control_area)	!= EXPECTED_VMCB_CONTROL_AREA_SIZE);
+	BUILD_BUG_ON(sizeof(struct ghcb)		!= EXPECTED_GHCB_SIZE);
 }
 
-struct __attribute__ ((__packed__)) vmcb {
+struct vmcb {
 	struct vmcb_control_area control;
 	u8 reserved_control[1024 - sizeof(struct vmcb_control_area)];
 	struct vmcb_save_area save;
-};
+} __packed;
 
 #define SVM_CPUID_FUNC 0x8000000a
 
@@ -240,32 +335,6 @@ struct __attribute__ ((__packed__)) vmcb {
 #define SVM_SELECTOR_READ_MASK SVM_SELECTOR_WRITE_MASK
 #define SVM_SELECTOR_CODE_MASK (1 << 3)
 
-#define INTERCEPT_CR0_READ	0
-#define INTERCEPT_CR3_READ	3
-#define INTERCEPT_CR4_READ	4
-#define INTERCEPT_CR8_READ	8
-#define INTERCEPT_CR0_WRITE	(16 + 0)
-#define INTERCEPT_CR3_WRITE	(16 + 3)
-#define INTERCEPT_CR4_WRITE	(16 + 4)
-#define INTERCEPT_CR8_WRITE	(16 + 8)
-
-#define INTERCEPT_DR0_READ	0
-#define INTERCEPT_DR1_READ	1
-#define INTERCEPT_DR2_READ	2
-#define INTERCEPT_DR3_READ	3
-#define INTERCEPT_DR4_READ	4
-#define INTERCEPT_DR5_READ	5
-#define INTERCEPT_DR6_READ	6
-#define INTERCEPT_DR7_READ	7
-#define INTERCEPT_DR0_WRITE	(16 + 0)
-#define INTERCEPT_DR1_WRITE	(16 + 1)
-#define INTERCEPT_DR2_WRITE	(16 + 2)
-#define INTERCEPT_DR3_WRITE	(16 + 3)
-#define INTERCEPT_DR4_WRITE	(16 + 4)
-#define INTERCEPT_DR5_WRITE	(16 + 5)
-#define INTERCEPT_DR6_WRITE	(16 + 6)
-#define INTERCEPT_DR7_WRITE	(16 + 7)
-
 #define SVM_EVTINJ_VEC_MASK 0xff
 
 #define SVM_EVTINJ_TYPE_SHIFT 8
@@ -298,4 +367,47 @@ struct __attribute__ ((__packed__)) vmcb {
 
 #define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP)
 
+/* GHCB Accessor functions */
+
+#define GHCB_BITMAP_IDX(field)							\
+	(offsetof(struct vmcb_save_area, field) / sizeof(u64))
+
+#define DEFINE_GHCB_ACCESSORS(field)						\
+	static inline bool ghcb_##field##_is_valid(const struct ghcb *ghcb)	\
+	{									\
+		return test_bit(GHCB_BITMAP_IDX(field),				\
+				(unsigned long *)&ghcb->save.valid_bitmap);	\
+	}									\
+										\
+	static inline void ghcb_set_##field(struct ghcb *ghcb, u64 value)	\
+	{									\
+		__set_bit(GHCB_BITMAP_IDX(field),				\
+			  (unsigned long *)&ghcb->save.valid_bitmap);		\
+		ghcb->save.field = value;					\
+	}
+
+DEFINE_GHCB_ACCESSORS(cpl)
+DEFINE_GHCB_ACCESSORS(rip)
+DEFINE_GHCB_ACCESSORS(rsp)
+DEFINE_GHCB_ACCESSORS(rax)
+DEFINE_GHCB_ACCESSORS(rcx)
+DEFINE_GHCB_ACCESSORS(rdx)
+DEFINE_GHCB_ACCESSORS(rbx)
+DEFINE_GHCB_ACCESSORS(rbp)
+DEFINE_GHCB_ACCESSORS(rsi)
+DEFINE_GHCB_ACCESSORS(rdi)
+DEFINE_GHCB_ACCESSORS(r8)
+DEFINE_GHCB_ACCESSORS(r9)
+DEFINE_GHCB_ACCESSORS(r10)
+DEFINE_GHCB_ACCESSORS(r11)
+DEFINE_GHCB_ACCESSORS(r12)
+DEFINE_GHCB_ACCESSORS(r13)
+DEFINE_GHCB_ACCESSORS(r14)
+DEFINE_GHCB_ACCESSORS(r15)
+DEFINE_GHCB_ACCESSORS(sw_exit_code)
+DEFINE_GHCB_ACCESSORS(sw_exit_info_1)
+DEFINE_GHCB_ACCESSORS(sw_exit_info_2)
+DEFINE_GHCB_ACCESSORS(sw_scratch)
+DEFINE_GHCB_ACCESSORS(xcr0)
+
 #endif
diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h
index fdb5b35..0fd4a9d 100644
--- a/arch/x86/include/asm/sync_core.h
+++ b/arch/x86/include/asm/sync_core.h
@@ -5,6 +5,7 @@
 #include <linux/preempt.h>
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
+#include <asm/special_insns.h>
 
 #ifdef CONFIG_X86_32
 static inline void iret_to_self(void)
@@ -46,22 +47,34 @@ static inline void iret_to_self(void)
  *
  *  b) Text was modified on a different CPU, may subsequently be
  *     executed on this CPU, and you want to make sure the new version
- *     gets executed.  This generally means you're calling this in a IPI.
+ *     gets executed.  This generally means you're calling this in an IPI.
  *
  * If you're calling this for a different reason, you're probably doing
  * it wrong.
+ *
+ * Like all of Linux's memory ordering operations, this is a
+ * compiler barrier as well.
  */
 static inline void sync_core(void)
 {
 	/*
-	 * There are quite a few ways to do this.  IRET-to-self is nice
-	 * because it works on every CPU, at any CPL (so it's compatible
-	 * with paravirtualization), and it never exits to a hypervisor.
-	 * The only down sides are that it's a bit slow (it seems to be
-	 * a bit more than 2x slower than the fastest options) and that
-	 * it unmasks NMIs.  The "push %cs" is needed because, in
-	 * paravirtual environments, __KERNEL_CS may not be a valid CS
-	 * value when we do IRET directly.
+	 * The SERIALIZE instruction is the most straightforward way to
+	 * do this, but it is not universally available.
+	 */
+	if (static_cpu_has(X86_FEATURE_SERIALIZE)) {
+		serialize();
+		return;
+	}
+
+	/*
+	 * For all other processors, there are quite a few ways to do this.
+	 * IRET-to-self is nice because it works on every CPU, at any CPL
+	 * (so it's compatible with paravirtualization), and it never exits
+	 * to a hypervisor.  The only downsides are that it's a bit slow
+	 * (it seems to be a bit more than 2x slower than the fastest
+	 * options) and that it unmasks NMIs.  The "push %cs" is needed,
+	 * because in paravirtual environments __KERNEL_CS may not be a
+	 * valid CS value when we do IRET directly.
 	 *
 	 * In case NMI unmasking or performance ever becomes a problem,
 	 * the next best option appears to be MOV-to-CR2 and an
@@ -71,9 +84,6 @@ static inline void sync_core(void)
 	 * CPUID is the conventional way, but it's nasty: it doesn't
 	 * exist on some 486-like CPUs, and it usually exits to a
 	 * hypervisor.
-	 *
-	 * Like all of Linux's memory ordering operations, this is a
-	 * compiler barrier as well.
 	 */
 	iret_to_self();
 }
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index cd7de4b..f8ba528 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -52,7 +52,7 @@
 #define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES VMCS_CONTROL_BIT(VIRT_APIC_ACCESSES)
 #define SECONDARY_EXEC_ENABLE_EPT               VMCS_CONTROL_BIT(EPT)
 #define SECONDARY_EXEC_DESC			VMCS_CONTROL_BIT(DESC_EXITING)
-#define SECONDARY_EXEC_RDTSCP			VMCS_CONTROL_BIT(RDTSCP)
+#define SECONDARY_EXEC_ENABLE_RDTSCP		VMCS_CONTROL_BIT(RDTSCP)
 #define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE   VMCS_CONTROL_BIT(VIRTUAL_X2APIC)
 #define SECONDARY_EXEC_ENABLE_VPID              VMCS_CONTROL_BIT(VPID)
 #define SECONDARY_EXEC_WBINVD_EXITING		VMCS_CONTROL_BIT(WBINVD_EXITING)
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 0780f97..89e5f3d 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -192,6 +192,26 @@ struct kvm_msr_list {
 	__u32 indices[0];
 };
 
+/* Maximum size of any access bitmap in bytes */
+#define KVM_MSR_FILTER_MAX_BITMAP_SIZE 0x600
+
+/* for KVM_X86_SET_MSR_FILTER */
+struct kvm_msr_filter_range {
+#define KVM_MSR_FILTER_READ  (1 << 0)
+#define KVM_MSR_FILTER_WRITE (1 << 1)
+	__u32 flags;
+	__u32 nmsrs; /* number of msrs in bitmap */
+	__u32 base;  /* MSR index the bitmap starts at */
+	__u8 *bitmap; /* a 1 bit allows the operations in flags, 0 denies */
+};
+
+#define KVM_MSR_FILTER_MAX_RANGES 16
+struct kvm_msr_filter {
+#define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0)
+#define KVM_MSR_FILTER_DEFAULT_DENY  (1 << 0)
+	__u32 flags;
+	struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
+};
 
 struct kvm_cpuid_entry {
 	__u32 function;
diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
index 2e8a30f..522d42d 100644
--- a/arch/x86/include/uapi/asm/svm.h
+++ b/arch/x86/include/uapi/asm/svm.h
@@ -76,6 +76,7 @@
 #define SVM_EXIT_MWAIT_COND    0x08c
 #define SVM_EXIT_XSETBV        0x08d
 #define SVM_EXIT_RDPRU         0x08e
+#define SVM_EXIT_INVPCID       0x0a2
 #define SVM_EXIT_NPF           0x400
 #define SVM_EXIT_AVIC_INCOMPLETE_IPI		0x401
 #define SVM_EXIT_AVIC_UNACCELERATED_ACCESS	0x402
@@ -171,6 +172,7 @@
 	{ SVM_EXIT_MONITOR,     "monitor" }, \
 	{ SVM_EXIT_MWAIT,       "mwait" }, \
 	{ SVM_EXIT_XSETBV,      "xsetbv" }, \
+	{ SVM_EXIT_INVPCID,     "invpcid" }, \
 	{ SVM_EXIT_NPF,         "npf" }, \
 	{ SVM_EXIT_AVIC_INCOMPLETE_IPI,		"avic_incomplete_ipi" }, \
 	{ SVM_EXIT_AVIC_UNACCELERATED_ACCESS,   "avic_unaccelerated_access" }, \
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 08320b0..42c6e0d 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -270,9 +270,8 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 	u32 token;
-	irqentry_state_t state;
 
-	state = irqentry_enter(regs);
+	ack_APIC_irq();
 
 	inc_irq_stat(irq_hv_callback_count);
 
@@ -283,7 +282,6 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt)
 		wrmsrl(MSR_KVM_ASYNC_PF_ACK, 1);
 	}
 
-	irqentry_exit(regs, state);
 	set_irq_regs(old_regs);
 }
 
@@ -954,7 +952,7 @@ void arch_haltpoll_disable(unsigned int cpu)
 	if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL))
 		return;
 
-	/* Enable guest halt poll disables host halt poll */
+	/* Disable guest halt poll enables host halt poll */
 	smp_call_function_single(cpu, kvm_enable_host_haltpoll, NULL, 1);
 }
 EXPORT_SYMBOL_GPL(arch_haltpoll_disable);
diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c
index 8d5cbe1..2c304fd 100644
--- a/arch/x86/kernel/umip.c
+++ b/arch/x86/kernel/umip.c
@@ -45,11 +45,12 @@
  * value that, lies close to the top of the kernel memory. The limit for the GDT
  * and the IDT are set to zero.
  *
- * Given that SLDT and STR are not commonly used in programs that run on WineHQ
- * or DOSEMU2, they are not emulated.
- *
- * The instruction smsw is emulated to return the value that the register CR0
+ * The instruction SMSW is emulated to return the value that the register CR0
  * has at boot time as set in the head_32.
+ * SLDT and STR are emulated to return the values that the kernel programmatically
+ * assigns:
+ * - SLDT returns (GDT_ENTRY_LDT * 8) if an LDT has been set, 0 if not.
+ * - STR returns (GDT_ENTRY_TSS * 8).
  *
  * Emulation is provided for both 32-bit and 64-bit processes.
  *
@@ -244,16 +245,34 @@ static int emulate_umip_insn(struct insn *insn, int umip_inst,
 		*data_size += UMIP_GDT_IDT_LIMIT_SIZE;
 		memcpy(data, &dummy_limit, UMIP_GDT_IDT_LIMIT_SIZE);
 
-	} else if (umip_inst == UMIP_INST_SMSW) {
-		unsigned long dummy_value = CR0_STATE;
+	} else if (umip_inst == UMIP_INST_SMSW || umip_inst == UMIP_INST_SLDT ||
+		   umip_inst == UMIP_INST_STR) {
+		unsigned long dummy_value;
+
+		if (umip_inst == UMIP_INST_SMSW) {
+			dummy_value = CR0_STATE;
+		} else if (umip_inst == UMIP_INST_STR) {
+			dummy_value = GDT_ENTRY_TSS * 8;
+		} else if (umip_inst == UMIP_INST_SLDT) {
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+			down_read(&current->mm->context.ldt_usr_sem);
+			if (current->mm->context.ldt)
+				dummy_value = GDT_ENTRY_LDT * 8;
+			else
+				dummy_value = 0;
+			up_read(&current->mm->context.ldt_usr_sem);
+#else
+			dummy_value = 0;
+#endif
+		}
 
 		/*
-		 * Even though the CR0 register has 4 bytes, the number
+		 * For these 3 instructions, the number
 		 * of bytes to be copied in the result buffer is determined
 		 * by whether the operand is a register or a memory location.
 		 * If operand is a register, return as many bytes as the operand
 		 * size. If operand is memory, return only the two least
-		 * siginificant bytes of CR0.
+		 * siginificant bytes.
 		 */
 		if (X86_MODRM_MOD(insn->modrm.value) == 3)
 			*data_size = insn->opnd_bytes;
@@ -261,7 +280,6 @@ static int emulate_umip_insn(struct insn *insn, int umip_inst,
 			*data_size = 2;
 
 		memcpy(data, &dummy_value, *data_size);
-	/* STR and SLDT  are not emulated */
 	} else {
 		return -EINVAL;
 	}
@@ -383,10 +401,6 @@ bool fixup_umip_exception(struct pt_regs *regs)
 	umip_pr_warn(regs, "%s instruction cannot be used by applications.\n",
 			umip_insns[umip_inst]);
 
-	/* Do not emulate (spoof) SLDT or STR. */
-	if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT)
-		return false;
-
 	umip_pr_warn(regs, "For now, expensive software emulation returns the result.\n");
 
 	if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size,
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 4a3081e..7f86a14 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -17,7 +17,8 @@
 			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
 			   hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o
 
-kvm-intel-y		+= vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o vmx/evmcs.o vmx/nested.o
+kvm-intel-y		+= vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \
+			   vmx/evmcs.o vmx/nested.o vmx/posted_intr.o
 kvm-amd-y		+= svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o svm/sev.o
 
 obj-$(CONFIG_KVM)	+= kvm.o
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 3fd6eec..37c3668 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -186,7 +186,6 @@ int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu)
 not_found:
 	return 36;
 }
-EXPORT_SYMBOL_GPL(cpuid_query_maxphyaddr);
 
 /* when an old userspace process fills a new kernel module */
 int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
@@ -371,7 +370,7 @@ void kvm_set_cpu_caps(void)
 		F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
 		F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) |
 		F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) |
-		F(SERIALIZE)
+		F(SERIALIZE) | F(TSXLDTRK)
 	);
 
 	/* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index 3a923ae..1d2c4f2 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -34,6 +34,11 @@ static inline int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
 	return vcpu->arch.maxphyaddr;
 }
 
+static inline bool kvm_vcpu_is_illegal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
+{
+	return (gpa >= BIT_ULL(cpuid_maxphyaddr(vcpu)));
+}
+
 struct cpuid_reg {
 	u32 function;
 	u32 index;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 5299ef5..0cc0db5 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2505,9 +2505,14 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
 		*reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
 
 	val = GET_SMSTATE(u32, smstate, 0x7fcc);
-	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
+
+	if (ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1))
+		return X86EMUL_UNHANDLEABLE;
+
 	val = GET_SMSTATE(u32, smstate, 0x7fc8);
-	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
+
+	if (ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1))
+		return X86EMUL_UNHANDLEABLE;
 
 	selector =                 GET_SMSTATE(u32, smstate, 0x7fc4);
 	set_desc_base(&desc,       GET_SMSTATE(u32, smstate, 0x7f64));
@@ -2560,16 +2565,23 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
 	ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED;
 
 	val = GET_SMSTATE(u32, smstate, 0x7f68);
-	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
+
+	if (ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1))
+		return X86EMUL_UNHANDLEABLE;
+
 	val = GET_SMSTATE(u32, smstate, 0x7f60);
-	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
+
+	if (ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1))
+		return X86EMUL_UNHANDLEABLE;
 
 	cr0 =                       GET_SMSTATE(u64, smstate, 0x7f58);
 	cr3 =                       GET_SMSTATE(u64, smstate, 0x7f50);
 	cr4 =                       GET_SMSTATE(u64, smstate, 0x7f48);
 	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00));
 	val =                       GET_SMSTATE(u64, smstate, 0x7ed0);
-	ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA);
+
+	if (ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA))
+		return X86EMUL_UNHANDLEABLE;
 
 	selector =                  GET_SMSTATE(u32, smstate, 0x7e90);
 	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smstate, 0x7e92) << 8);
@@ -3594,7 +3606,7 @@ static int em_rdpid(struct x86_emulate_ctxt *ctxt)
 	u64 tsc_aux = 0;
 
 	if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux))
-		return emulate_gp(ctxt, 0);
+		return emulate_ud(ctxt);
 	ctxt->dst.val = tsc_aux;
 	return X86EMUL_CONTINUE;
 }
@@ -3689,11 +3701,18 @@ static int em_dr_write(struct x86_emulate_ctxt *ctxt)
 
 static int em_wrmsr(struct x86_emulate_ctxt *ctxt)
 {
+	u64 msr_index = reg_read(ctxt, VCPU_REGS_RCX);
 	u64 msr_data;
+	int r;
 
 	msr_data = (u32)reg_read(ctxt, VCPU_REGS_RAX)
 		| ((u64)reg_read(ctxt, VCPU_REGS_RDX) << 32);
-	if (ctxt->ops->set_msr(ctxt, reg_read(ctxt, VCPU_REGS_RCX), msr_data))
+	r = ctxt->ops->set_msr(ctxt, msr_index, msr_data);
+
+	if (r == X86EMUL_IO_NEEDED)
+		return r;
+
+	if (r)
 		return emulate_gp(ctxt, 0);
 
 	return X86EMUL_CONTINUE;
@@ -3701,9 +3720,16 @@ static int em_wrmsr(struct x86_emulate_ctxt *ctxt)
 
 static int em_rdmsr(struct x86_emulate_ctxt *ctxt)
 {
+	u64 msr_index = reg_read(ctxt, VCPU_REGS_RCX);
 	u64 msr_data;
+	int r;
 
-	if (ctxt->ops->get_msr(ctxt, reg_read(ctxt, VCPU_REGS_RCX), &msr_data))
+	r = ctxt->ops->get_msr(ctxt, msr_index, &msr_data);
+
+	if (r == X86EMUL_IO_NEEDED)
+		return r;
+
+	if (r)
 		return emulate_gp(ctxt, 0);
 
 	*reg_write(ctxt, VCPU_REGS_RAX) = (u32)msr_data;
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 1d33056..67a4f60 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -633,6 +633,11 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config,
 {
 	union hv_stimer_config new_config = {.as_uint64 = config},
 		old_config = {.as_uint64 = stimer->config.as_uint64};
+	struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer);
+	struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu);
+
+	if (!synic->active && !host)
+		return 1;
 
 	trace_kvm_hv_stimer_set_config(stimer_to_vcpu(stimer)->vcpu_id,
 				       stimer->index, config, host);
@@ -652,6 +657,12 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config,
 static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count,
 			    bool host)
 {
+	struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer);
+	struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu);
+
+	if (!synic->active && !host)
+		return 1;
+
 	trace_kvm_hv_stimer_set_count(stimer_to_vcpu(stimer)->vcpu_id,
 				      stimer->index, count, host);
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 35cca2e..105e785 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -310,6 +310,12 @@ static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id)
 	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
 }
 
+static inline void kvm_apic_set_dfr(struct kvm_lapic *apic, u32 val)
+{
+	kvm_lapic_set_reg(apic, APIC_DFR, val);
+	atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
+}
+
 static inline u32 kvm_apic_calc_x2apic_ldr(u32 id)
 {
 	return ((id >> 4) << 16) | (1 << (id & 0xf));
@@ -488,6 +494,12 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
 	}
 }
 
+void kvm_apic_clear_irr(struct kvm_vcpu *vcpu, int vec)
+{
+	apic_clear_irr(vec, vcpu->arch.apic);
+}
+EXPORT_SYMBOL_GPL(kvm_apic_clear_irr);
+
 static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
 {
 	struct kvm_vcpu *vcpu;
@@ -1576,9 +1588,6 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u64 guest_tsc, tsc_deadline;
 
-	if (apic->lapic_timer.expired_tscdeadline == 0)
-		return;
-
 	tsc_deadline = apic->lapic_timer.expired_tscdeadline;
 	apic->lapic_timer.expired_tscdeadline = 0;
 	guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
@@ -1593,7 +1602,10 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
 
 void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
 {
-	if (lapic_timer_int_injected(vcpu))
+	if (lapic_in_kernel(vcpu) &&
+	    vcpu->arch.apic->lapic_timer.expired_tscdeadline &&
+	    vcpu->arch.apic->lapic_timer.timer_advance_ns &&
+	    lapic_timer_int_injected(vcpu))
 		__kvm_wait_lapic_expire(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_wait_lapic_expire);
@@ -1629,14 +1641,15 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn)
 	}
 
 	if (kvm_use_posted_timer_interrupt(apic->vcpu)) {
-		if (apic->lapic_timer.timer_advance_ns)
-			__kvm_wait_lapic_expire(vcpu);
+		kvm_wait_lapic_expire(vcpu);
 		kvm_apic_inject_pending_timer_irqs(apic);
 		return;
 	}
 
 	atomic_inc(&apic->lapic_timer.pending);
-	kvm_set_pending_timer(vcpu);
+	kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
+	if (from_timer_fn)
+		kvm_vcpu_kick(vcpu);
 }
 
 static void start_sw_tscdeadline(struct kvm_lapic *apic)
@@ -1984,10 +1997,9 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 		break;
 
 	case APIC_DFR:
-		if (!apic_x2apic_mode(apic)) {
-			kvm_lapic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF);
-			atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY);
-		} else
+		if (!apic_x2apic_mode(apic))
+			kvm_apic_set_dfr(apic, val | 0x0FFFFFFF);
+		else
 			ret = 1;
 		break;
 
@@ -2183,8 +2195,7 @@ u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!lapic_in_kernel(vcpu) ||
-		!apic_lvtt_tscdeadline(apic))
+	if (!kvm_apic_present(vcpu) || !apic_lvtt_tscdeadline(apic))
 		return 0;
 
 	return apic->lapic_timer.tscdeadline;
@@ -2194,8 +2205,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!kvm_apic_present(vcpu) || apic_lvtt_oneshot(apic) ||
-			apic_lvtt_period(apic))
+	if (!kvm_apic_present(vcpu) || !apic_lvtt_tscdeadline(apic))
 		return;
 
 	hrtimer_cancel(&apic->lapic_timer.timer);
@@ -2303,7 +2313,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 			     SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
 	apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0));
 
-	kvm_lapic_set_reg(apic, APIC_DFR, 0xffffffffU);
+	kvm_apic_set_dfr(apic, 0xffffffffU);
 	apic_set_spiv(apic, 0xff);
 	kvm_lapic_set_reg(apic, APIC_TASKPRI, 0);
 	if (!apic_x2apic_mode(apic))
@@ -2461,6 +2471,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
 	__apic_update_ppr(apic, &ppr);
 	return apic_has_interrupt_for_ppr(apic, ppr);
 }
+EXPORT_SYMBOL_GPL(kvm_apic_has_interrupt);
 
 int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 754f29b..4fb86e3 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -89,6 +89,7 @@ int kvm_lapic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
 bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 			   int shorthand, unsigned int dest, int dest_mode);
 int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
+void kvm_apic_clear_irr(struct kvm_vcpu *vcpu, int vec);
 bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr);
 bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr);
 void kvm_apic_update_ppr(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 5efc608..9c4a9c8 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -155,11 +155,6 @@ static inline bool is_write_protection(struct kvm_vcpu *vcpu)
 	return kvm_read_cr0_bits(vcpu, X86_CR0_WP);
 }
 
-static inline bool kvm_mmu_is_illegal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
-{
-        return (gpa >= BIT_ULL(cpuid_maxphyaddr(vcpu)));
-}
-
 /*
  * Check if a given access (described through the I/D, W/R and U/S bits of a
  * page fault error code pfec) causes a permission fault with the given PTE
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 43fdb0c..32e0e5c 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -198,17 +198,20 @@ module_param(dbg, bool, 0644);
 #define PTE_LIST_EXT 3
 
 /*
- * Return values of handle_mmio_page_fault and mmu.page_fault:
+ * Return values of handle_mmio_page_fault, mmu.page_fault, and fast_page_fault().
+ *
  * RET_PF_RETRY: let CPU fault again on the address.
  * RET_PF_EMULATE: mmio page fault, emulate the instruction directly.
- *
- * For handle_mmio_page_fault only:
  * RET_PF_INVALID: the spte is invalid, let the real page fault path update it.
+ * RET_PF_FIXED: The faulting entry has been fixed.
+ * RET_PF_SPURIOUS: The faulting entry was already fixed, e.g. by another vCPU.
  */
 enum {
 	RET_PF_RETRY = 0,
-	RET_PF_EMULATE = 1,
-	RET_PF_INVALID = 2,
+	RET_PF_EMULATE,
+	RET_PF_INVALID,
+	RET_PF_FIXED,
+	RET_PF_SPURIOUS,
 };
 
 struct pte_list_desc {
@@ -521,7 +524,7 @@ static gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
                                   struct x86_exception *exception)
 {
 	/* Check if guest physical address doesn't exceed guest maximum */
-	if (kvm_mmu_is_illegal_gpa(vcpu, gpa)) {
+	if (kvm_vcpu_is_illegal_gpa(vcpu, gpa)) {
 		exception->error_code |= PFERR_RSVD_MASK;
 		return UNMAPPED_GVA;
 	}
@@ -2469,7 +2472,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 		}
 
 		if (sp->unsync_children)
-			kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
+			kvm_make_request(KVM_REQ_MMU_SYNC, vcpu);
 
 		__clear_sp_write_flooding_count(sp);
 
@@ -2615,8 +2618,9 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	}
 }
 
-static bool mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
-			     u64 *spte)
+/* Returns the number of zapped non-leaf child shadow pages. */
+static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
+			    u64 *spte, struct list_head *invalid_list)
 {
 	u64 pte;
 	struct kvm_mmu_page *child;
@@ -2630,23 +2634,34 @@ static bool mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
 		} else {
 			child = to_shadow_page(pte & PT64_BASE_ADDR_MASK);
 			drop_parent_pte(child, spte);
+
+			/*
+			 * Recursively zap nested TDP SPs, parentless SPs are
+			 * unlikely to be used again in the near future.  This
+			 * avoids retaining a large number of stale nested SPs.
+			 */
+			if (tdp_enabled && invalid_list &&
+			    child->role.guest_mode && !child->parent_ptes.val)
+				return kvm_mmu_prepare_zap_page(kvm, child,
+								invalid_list);
 		}
-		return true;
-	}
-
-	if (is_mmio_spte(pte))
+	} else if (is_mmio_spte(pte)) {
 		mmu_spte_clear_no_track(spte);
-
-	return false;
+	}
+	return 0;
 }
 
-static void kvm_mmu_page_unlink_children(struct kvm *kvm,
-					 struct kvm_mmu_page *sp)
+static int kvm_mmu_page_unlink_children(struct kvm *kvm,
+					struct kvm_mmu_page *sp,
+					struct list_head *invalid_list)
 {
+	int zapped = 0;
 	unsigned i;
 
 	for (i = 0; i < PT64_ENT_PER_PAGE; ++i)
-		mmu_page_zap_pte(kvm, sp, sp->spt + i);
+		zapped += mmu_page_zap_pte(kvm, sp, sp->spt + i, invalid_list);
+
+	return zapped;
 }
 
 static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp)
@@ -2692,7 +2707,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
 	trace_kvm_mmu_prepare_zap_page(sp);
 	++kvm->stat.mmu_shadow_zapped;
 	*nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list);
-	kvm_mmu_page_unlink_children(kvm, sp);
+	*nr_zapped += kvm_mmu_page_unlink_children(kvm, sp, invalid_list);
 	kvm_mmu_unlink_parents(kvm, sp);
 
 	/* Zapping children means active_mmu_pages has become unstable. */
@@ -2970,6 +2985,7 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn)
 /* Bits which may be returned by set_spte() */
 #define SET_SPTE_WRITE_PROTECTED_PT	BIT(0)
 #define SET_SPTE_NEED_REMOTE_TLB_FLUSH	BIT(1)
+#define SET_SPTE_SPURIOUS		BIT(2)
 
 static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		    unsigned int pte_access, int level,
@@ -3058,20 +3074,22 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		spte = mark_spte_for_access_track(spte);
 
 set_pte:
-	if (mmu_spte_update(sptep, spte))
+	if (*sptep == spte)
+		ret |= SET_SPTE_SPURIOUS;
+	else if (mmu_spte_update(sptep, spte))
 		ret |= SET_SPTE_NEED_REMOTE_TLB_FLUSH;
 	return ret;
 }
 
 static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
-			unsigned int pte_access, int write_fault, int level,
+			unsigned int pte_access, bool write_fault, int level,
 			gfn_t gfn, kvm_pfn_t pfn, bool speculative,
 			bool host_writable)
 {
 	int was_rmapped = 0;
 	int rmap_count;
 	int set_spte_ret;
-	int ret = RET_PF_RETRY;
+	int ret = RET_PF_FIXED;
 	bool flush = false;
 
 	pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__,
@@ -3113,6 +3131,15 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	if (unlikely(is_mmio_spte(*sptep)))
 		ret = RET_PF_EMULATE;
 
+	/*
+	 * The fault is fully spurious if and only if the new SPTE and old SPTE
+	 * are identical, and emulation is not required.
+	 */
+	if ((set_spte_ret & SET_SPTE_SPURIOUS) && ret == RET_PF_FIXED) {
+		WARN_ON_ONCE(!was_rmapped);
+		return RET_PF_SPURIOUS;
+	}
+
 	pgprintk("%s: setting spte %llx\n", __func__, *sptep);
 	trace_kvm_mmu_set_spte(level, gfn, sptep);
 	if (!was_rmapped && is_large_pte(*sptep))
@@ -3161,7 +3188,7 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
 		return -1;
 
 	for (i = 0; i < ret; i++, gfn++, start++) {
-		mmu_set_spte(vcpu, start, access, 0, sp->role.level, gfn,
+		mmu_set_spte(vcpu, start, access, false, sp->role.level, gfn,
 			     page_to_pfn(pages[i]), true, true);
 		put_page(pages[i]);
 	}
@@ -3240,7 +3267,8 @@ static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn,
 }
 
 static int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn,
-				   int max_level, kvm_pfn_t *pfnp)
+				   int max_level, kvm_pfn_t *pfnp,
+				   bool huge_page_disallowed, int *req_level)
 {
 	struct kvm_memory_slot *slot;
 	struct kvm_lpage_info *linfo;
@@ -3248,6 +3276,8 @@ static int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn,
 	kvm_pfn_t mask;
 	int level;
 
+	*req_level = PG_LEVEL_4K;
+
 	if (unlikely(max_level == PG_LEVEL_4K))
 		return PG_LEVEL_4K;
 
@@ -3272,7 +3302,14 @@ static int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn,
 	if (level == PG_LEVEL_4K)
 		return level;
 
-	level = min(level, max_level);
+	*req_level = level = min(level, max_level);
+
+	/*
+	 * Enforce the iTLB multihit workaround after capturing the requested
+	 * level, which will be used to do precise, accurate accounting.
+	 */
+	if (huge_page_disallowed)
+		return PG_LEVEL_4K;
 
 	/*
 	 * mmu_notifier_retry() was successful and mmu_lock is held, so
@@ -3292,7 +3329,6 @@ static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it,
 	u64 spte = *it.sptep;
 
 	if (it.level == level && level > PG_LEVEL_4K &&
-	    is_nx_huge_page_enabled() &&
 	    is_shadow_present_pte(spte) &&
 	    !is_large_pte(spte)) {
 		/*
@@ -3308,20 +3344,25 @@ static void disallowed_hugepage_adjust(struct kvm_shadow_walk_iterator it,
 	}
 }
 
-static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
+static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 			int map_writable, int max_level, kvm_pfn_t pfn,
-			bool prefault, bool account_disallowed_nx_lpage)
+			bool prefault, bool is_tdp)
 {
+	bool nx_huge_page_workaround_enabled = is_nx_huge_page_enabled();
+	bool write = error_code & PFERR_WRITE_MASK;
+	bool exec = error_code & PFERR_FETCH_MASK;
+	bool huge_page_disallowed = exec && nx_huge_page_workaround_enabled;
 	struct kvm_shadow_walk_iterator it;
 	struct kvm_mmu_page *sp;
-	int level, ret;
+	int level, req_level, ret;
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	gfn_t base_gfn = gfn;
 
 	if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root_hpa)))
 		return RET_PF_RETRY;
 
-	level = kvm_mmu_hugepage_adjust(vcpu, gfn, max_level, &pfn);
+	level = kvm_mmu_hugepage_adjust(vcpu, gfn, max_level, &pfn,
+					huge_page_disallowed, &req_level);
 
 	trace_kvm_mmu_spte_requested(gpa, level, pfn);
 	for_each_shadow_entry(vcpu, gpa, it) {
@@ -3329,7 +3370,8 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
 		 * We cannot overwrite existing page tables with an NX
 		 * large page, as the leaf could be executable.
 		 */
-		disallowed_hugepage_adjust(it, gfn, &pfn, &level);
+		if (nx_huge_page_workaround_enabled)
+			disallowed_hugepage_adjust(it, gfn, &pfn, &level);
 
 		base_gfn = gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
 		if (it.level == level)
@@ -3341,7 +3383,8 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
 					      it.level - 1, true, ACC_ALL);
 
 			link_shadow_page(vcpu, it.sptep, sp);
-			if (account_disallowed_nx_lpage)
+			if (is_tdp && huge_page_disallowed &&
+			    req_level >= it.level)
 				account_huge_nx_page(vcpu->kvm, sp);
 		}
 	}
@@ -3349,6 +3392,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t gpa, int write,
 	ret = mmu_set_spte(vcpu, it.sptep, ACC_ALL,
 			   write, level, base_gfn, pfn, prefault,
 			   map_writable);
+	if (ret == RET_PF_SPURIOUS)
+		return ret;
+
 	direct_pte_prefetch(vcpu, it.sptep);
 	++vcpu->stat.pf_fixed;
 	return ret;
@@ -3479,21 +3525,19 @@ static bool is_access_allowed(u32 fault_err_code, u64 spte)
 }
 
 /*
- * Return value:
- * - true: let the vcpu to access on the same address again.
- * - false: let the real page fault path to fix it.
+ * Returns one of RET_PF_INVALID, RET_PF_FIXED or RET_PF_SPURIOUS.
  */
-static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
-			    u32 error_code)
+static int fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+			   u32 error_code)
 {
 	struct kvm_shadow_walk_iterator iterator;
 	struct kvm_mmu_page *sp;
-	bool fault_handled = false;
+	int ret = RET_PF_INVALID;
 	u64 spte = 0ull;
 	uint retry_count = 0;
 
 	if (!page_fault_can_be_fast(error_code))
-		return false;
+		return ret;
 
 	walk_shadow_page_lockless_begin(vcpu);
 
@@ -3519,7 +3563,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 		 * they are always ACC_ALL.
 		 */
 		if (is_access_allowed(error_code, spte)) {
-			fault_handled = true;
+			ret = RET_PF_SPURIOUS;
 			break;
 		}
 
@@ -3562,11 +3606,11 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 		 * since the gfn is not stable for indirect shadow page. See
 		 * Documentation/virt/kvm/locking.rst to get more detail.
 		 */
-		fault_handled = fast_pf_fix_direct_spte(vcpu, sp,
-							iterator.sptep, spte,
-							new_spte);
-		if (fault_handled)
+		if (fast_pf_fix_direct_spte(vcpu, sp, iterator.sptep, spte,
+					    new_spte)) {
+			ret = RET_PF_FIXED;
 			break;
+		}
 
 		if (++retry_count > 4) {
 			printk_once(KERN_WARNING
@@ -3577,10 +3621,10 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 	} while (true);
 
 	trace_fast_page_fault(vcpu, cr2_or_gpa, error_code, iterator.sptep,
-			      spte, fault_handled);
+			      spte, ret);
 	walk_shadow_page_lockless_end(vcpu);
 
-	return fault_handled;
+	return ret;
 }
 
 static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
@@ -3603,6 +3647,7 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
 void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 			ulong roots_to_free)
 {
+	struct kvm *kvm = vcpu->kvm;
 	int i;
 	LIST_HEAD(invalid_list);
 	bool free_active_root = roots_to_free & KVM_MMU_ROOT_CURRENT;
@@ -3620,22 +3665,21 @@ void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 			return;
 	}
 
-	spin_lock(&vcpu->kvm->mmu_lock);
+	spin_lock(&kvm->mmu_lock);
 
 	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
 		if (roots_to_free & KVM_MMU_ROOT_PREVIOUS(i))
-			mmu_free_root_page(vcpu->kvm, &mmu->prev_roots[i].hpa,
+			mmu_free_root_page(kvm, &mmu->prev_roots[i].hpa,
 					   &invalid_list);
 
 	if (free_active_root) {
 		if (mmu->shadow_root_level >= PT64_ROOT_4LEVEL &&
 		    (mmu->root_level >= PT64_ROOT_4LEVEL || mmu->direct_map)) {
-			mmu_free_root_page(vcpu->kvm, &mmu->root_hpa,
-					   &invalid_list);
+			mmu_free_root_page(kvm, &mmu->root_hpa, &invalid_list);
 		} else {
 			for (i = 0; i < 4; ++i)
 				if (mmu->pae_root[i] != 0)
-					mmu_free_root_page(vcpu->kvm,
+					mmu_free_root_page(kvm,
 							   &mmu->pae_root[i],
 							   &invalid_list);
 			mmu->root_hpa = INVALID_PAGE;
@@ -3643,8 +3687,8 @@ void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 		mmu->root_pgd = 0;
 	}
 
-	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
-	spin_unlock(&vcpu->kvm->mmu_lock);
+	kvm_mmu_commit_zap_page(kvm, &invalid_list);
+	spin_unlock(&kvm->mmu_lock);
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_free_roots);
 
@@ -4080,8 +4124,6 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 			     bool prefault, int max_level, bool is_tdp)
 {
 	bool write = error_code & PFERR_WRITE_MASK;
-	bool exec = error_code & PFERR_FETCH_MASK;
-	bool lpage_disallowed = exec && is_nx_huge_page_enabled();
 	bool map_writable;
 
 	gfn_t gfn = gpa >> PAGE_SHIFT;
@@ -4092,16 +4134,14 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 	if (page_fault_handle_page_track(vcpu, error_code, gfn))
 		return RET_PF_EMULATE;
 
-	if (fast_page_fault(vcpu, gpa, error_code))
-		return RET_PF_RETRY;
+	r = fast_page_fault(vcpu, gpa, error_code);
+	if (r != RET_PF_INVALID)
+		return r;
 
 	r = mmu_topup_memory_caches(vcpu, false);
 	if (r)
 		return r;
 
-	if (lpage_disallowed)
-		max_level = PG_LEVEL_4K;
-
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
 
@@ -4118,8 +4158,8 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 	r = make_mmu_pages_available(vcpu);
 	if (r)
 		goto out_unlock;
-	r = __direct_map(vcpu, gpa, write, map_writable, max_level, pfn,
-			 prefault, is_tdp && lpage_disallowed);
+	r = __direct_map(vcpu, gpa, error_code, map_writable, max_level, pfn,
+			 prefault, is_tdp);
 
 out_unlock:
 	spin_unlock(&vcpu->kvm->mmu_lock);
@@ -5400,7 +5440,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 			u32 base_role = vcpu->arch.mmu->mmu_role.base.word;
 
 			entry = *spte;
-			mmu_page_zap_pte(vcpu->kvm, sp, spte);
+			mmu_page_zap_pte(vcpu->kvm, sp, spte, NULL);
 			if (gentry &&
 			    !((sp->role.word ^ base_role) & ~role_ign.word) &&
 			    rmap_can_add(vcpu))
@@ -5450,13 +5490,14 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 	if (r == RET_PF_INVALID) {
 		r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa,
 					  lower_32_bits(error_code), false);
-		WARN_ON(r == RET_PF_INVALID);
+		if (WARN_ON_ONCE(r == RET_PF_INVALID))
+			return -EIO;
 	}
 
-	if (r == RET_PF_RETRY)
-		return 1;
 	if (r < 0)
 		return r;
+	if (r != RET_PF_EMULATE)
+		return 1;
 
 	/*
 	 * Before emulating the instruction, check if the error code
@@ -5485,18 +5526,6 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
 	if (!mmio_info_in_cache(vcpu, cr2_or_gpa, direct) && !is_guest_mode(vcpu))
 		emulation_type |= EMULTYPE_ALLOW_RETRY_PF;
 emulate:
-	/*
-	 * On AMD platforms, under certain conditions insn_len may be zero on #NPF.
-	 * This can happen if a guest gets a page-fault on data access but the HW
-	 * table walker is not able to read the instruction page (e.g instruction
-	 * page is not present in memory). In those cases we simply restart the
-	 * guest, with the exception of AMD Erratum 1096 which is unrecoverable.
-	 */
-	if (unlikely(insn && !insn_len)) {
-		if (!kvm_x86_ops.need_emulation_on_page_fault(vcpu))
-			return 1;
-	}
-
 	return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn,
 				       insn_len);
 }
@@ -5682,11 +5711,17 @@ static void free_mmu_pages(struct kvm_mmu *mmu)
 	free_page((unsigned long)mmu->lm_root);
 }
 
-static int alloc_mmu_pages(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
 {
 	struct page *page;
 	int i;
 
+	mmu->root_hpa = INVALID_PAGE;
+	mmu->root_pgd = 0;
+	mmu->translate_gpa = translate_gpa;
+	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
+		mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
+
 	/*
 	 * When using PAE paging, the four PDPTEs are treated as 'root' pages,
 	 * while the PDP table is a per-vCPU construct that's allocated at MMU
@@ -5712,7 +5747,6 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
 
 int kvm_mmu_create(struct kvm_vcpu *vcpu)
 {
-	uint i;
 	int ret;
 
 	vcpu->arch.mmu_pte_list_desc_cache.kmem_cache = pte_list_desc_cache;
@@ -5726,25 +5760,13 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
 	vcpu->arch.mmu = &vcpu->arch.root_mmu;
 	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
 
-	vcpu->arch.root_mmu.root_hpa = INVALID_PAGE;
-	vcpu->arch.root_mmu.root_pgd = 0;
-	vcpu->arch.root_mmu.translate_gpa = translate_gpa;
-	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
-		vcpu->arch.root_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
-
-	vcpu->arch.guest_mmu.root_hpa = INVALID_PAGE;
-	vcpu->arch.guest_mmu.root_pgd = 0;
-	vcpu->arch.guest_mmu.translate_gpa = translate_gpa;
-	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
-		vcpu->arch.guest_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
-
 	vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;
 
-	ret = alloc_mmu_pages(vcpu, &vcpu->arch.guest_mmu);
+	ret = __kvm_mmu_create(vcpu, &vcpu->arch.guest_mmu);
 	if (ret)
 		return ret;
 
-	ret = alloc_mmu_pages(vcpu, &vcpu->arch.root_mmu);
+	ret = __kvm_mmu_create(vcpu, &vcpu->arch.root_mmu);
 	if (ret)
 		goto fail_allocate_root;
 
@@ -6357,7 +6379,10 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 
 	ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
 	to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0;
-	while (to_zap && !list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) {
+	for ( ; to_zap; --to_zap) {
+		if (list_empty(&kvm->arch.lpage_disallowed_mmu_pages))
+			break;
+
 		/*
 		 * We use a separate list instead of just using active_mmu_pages
 		 * because the number of lpage_disallowed pages is expected to
@@ -6370,12 +6395,12 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 		kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
 		WARN_ON_ONCE(sp->lpage_disallowed);
 
-		if (!--to_zap || need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+		if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
 			kvm_mmu_commit_zap_page(kvm, &invalid_list);
-			if (to_zap)
-				cond_resched_lock(&kvm->mmu_lock);
+			cond_resched_lock(&kvm->mmu_lock);
 		}
 	}
+	kvm_mmu_commit_zap_page(kvm, &invalid_list);
 
 	spin_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, rcu_idx);
diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h
index 9d15bc0..2080f9c 100644
--- a/arch/x86/kvm/mmu/mmutrace.h
+++ b/arch/x86/kvm/mmu/mmutrace.h
@@ -244,14 +244,11 @@ TRACE_EVENT(
 		  __entry->access)
 );
 
-#define __spte_satisfied(__spte)				\
-	(__entry->retry && is_writable_pte(__entry->__spte))
-
 TRACE_EVENT(
 	fast_page_fault,
 	TP_PROTO(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 error_code,
-		 u64 *sptep, u64 old_spte, bool retry),
-	TP_ARGS(vcpu, cr2_or_gpa, error_code, sptep, old_spte, retry),
+		 u64 *sptep, u64 old_spte, int ret),
+	TP_ARGS(vcpu, cr2_or_gpa, error_code, sptep, old_spte, ret),
 
 	TP_STRUCT__entry(
 		__field(int, vcpu_id)
@@ -260,7 +257,7 @@ TRACE_EVENT(
 		__field(u64 *, sptep)
 		__field(u64, old_spte)
 		__field(u64, new_spte)
-		__field(bool, retry)
+		__field(int, ret)
 	),
 
 	TP_fast_assign(
@@ -270,7 +267,7 @@ TRACE_EVENT(
 		__entry->sptep = sptep;
 		__entry->old_spte = old_spte;
 		__entry->new_spte = *sptep;
-		__entry->retry = retry;
+		__entry->ret = ret;
 	),
 
 	TP_printk("vcpu %d gva %llx error_code %s sptep %p old %#llx"
@@ -278,7 +275,7 @@ TRACE_EVENT(
 		  __entry->cr2_or_gpa, __print_flags(__entry->error_code, "|",
 		  kvm_mmu_trace_pferr_flags), __entry->sptep,
 		  __entry->old_spte, __entry->new_spte,
-		  __spte_satisfied(old_spte), __spte_satisfied(new_spte)
+		  __entry->ret == RET_PF_SPURIOUS, __entry->ret == RET_PF_FIXED
 	)
 );
 
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 4dd6b1e..9a1a15f 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -550,7 +550,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	 * we call mmu_set_spte() with host_writable = true because
 	 * pte_prefetch_gfn_to_pfn always gets a writable pfn.
 	 */
-	mmu_set_spte(vcpu, spte, pte_access, 0, PG_LEVEL_4K, gfn, pfn,
+	mmu_set_spte(vcpu, spte, pte_access, false, PG_LEVEL_4K, gfn, pfn,
 		     true, true);
 
 	kvm_release_pfn_clean(pfn);
@@ -625,15 +625,18 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
  * emulate this operation, return 1 to indicate this case.
  */
 static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
-			 struct guest_walker *gw,
-			 int write_fault, int max_level,
-			 kvm_pfn_t pfn, bool map_writable, bool prefault,
-			 bool lpage_disallowed)
+			 struct guest_walker *gw, u32 error_code,
+			 int max_level, kvm_pfn_t pfn, bool map_writable,
+			 bool prefault)
 {
+	bool nx_huge_page_workaround_enabled = is_nx_huge_page_enabled();
+	bool write_fault = error_code & PFERR_WRITE_MASK;
+	bool exec = error_code & PFERR_FETCH_MASK;
+	bool huge_page_disallowed = exec && nx_huge_page_workaround_enabled;
 	struct kvm_mmu_page *sp = NULL;
 	struct kvm_shadow_walk_iterator it;
 	unsigned direct_access, access = gw->pt_access;
-	int top_level, hlevel, ret;
+	int top_level, level, req_level, ret;
 	gfn_t base_gfn = gw->gfn;
 
 	direct_access = gw->pte_access;
@@ -679,7 +682,8 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
 			link_shadow_page(vcpu, it.sptep, sp);
 	}
 
-	hlevel = kvm_mmu_hugepage_adjust(vcpu, gw->gfn, max_level, &pfn);
+	level = kvm_mmu_hugepage_adjust(vcpu, gw->gfn, max_level, &pfn,
+					huge_page_disallowed, &req_level);
 
 	trace_kvm_mmu_spte_requested(addr, gw->level, pfn);
 
@@ -690,10 +694,11 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
 		 * We cannot overwrite existing page tables with an NX
 		 * large page, as the leaf could be executable.
 		 */
-		disallowed_hugepage_adjust(it, gw->gfn, &pfn, &hlevel);
+		if (nx_huge_page_workaround_enabled)
+			disallowed_hugepage_adjust(it, gw->gfn, &pfn, &level);
 
 		base_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1);
-		if (it.level == hlevel)
+		if (it.level == level)
 			break;
 
 		validate_direct_spte(vcpu, it.sptep, direct_access);
@@ -704,13 +709,16 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
 			sp = kvm_mmu_get_page(vcpu, base_gfn, addr,
 					      it.level - 1, true, direct_access);
 			link_shadow_page(vcpu, it.sptep, sp);
-			if (lpage_disallowed)
+			if (huge_page_disallowed && req_level >= it.level)
 				account_huge_nx_page(vcpu->kvm, sp);
 		}
 	}
 
 	ret = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault,
 			   it.level, base_gfn, pfn, prefault, map_writable);
+	if (ret == RET_PF_SPURIOUS)
+		return ret;
+
 	FNAME(pte_prefetch)(vcpu, gw, it.sptep);
 	++vcpu->stat.pf_fixed;
 	return ret;
@@ -738,7 +746,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gpa_t addr,
  */
 static bool
 FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu,
-			      struct guest_walker *walker, int user_fault,
+			      struct guest_walker *walker, bool user_fault,
 			      bool *write_fault_to_shadow_pgtable)
 {
 	int level;
@@ -776,15 +784,13 @@ FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu,
 static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 			     bool prefault)
 {
-	int write_fault = error_code & PFERR_WRITE_MASK;
-	int user_fault = error_code & PFERR_USER_MASK;
+	bool write_fault = error_code & PFERR_WRITE_MASK;
+	bool user_fault = error_code & PFERR_USER_MASK;
 	struct guest_walker walker;
 	int r;
 	kvm_pfn_t pfn;
 	unsigned long mmu_seq;
 	bool map_writable, is_self_change_mapping;
-	bool lpage_disallowed = (error_code & PFERR_FETCH_MASK) &&
-				is_nx_huge_page_enabled();
 	int max_level;
 
 	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
@@ -825,7 +831,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 	is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu,
 	      &walker, user_fault, &vcpu->arch.write_fault_to_shadow_pgtable);
 
-	if (lpage_disallowed || is_self_change_mapping)
+	if (is_self_change_mapping)
 		max_level = PG_LEVEL_4K;
 	else
 		max_level = walker.level;
@@ -869,8 +875,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 	r = make_mmu_pages_available(vcpu);
 	if (r)
 		goto out_unlock;
-	r = FNAME(fetch)(vcpu, addr, &walker, write_fault, max_level, pfn,
-			 map_writable, prefault, lpage_disallowed);
+	r = FNAME(fetch)(vcpu, addr, &walker, error_code, max_level, pfn,
+			 map_writable, prefault);
 	kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT);
 
 out_unlock:
@@ -895,6 +901,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
 {
 	struct kvm_shadow_walk_iterator iterator;
 	struct kvm_mmu_page *sp;
+	u64 old_spte;
 	int level;
 	u64 *sptep;
 
@@ -917,7 +924,8 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
 		sptep = iterator.sptep;
 
 		sp = sptep_to_sp(sptep);
-		if (is_last_spte(*sptep, level)) {
+		old_spte = *sptep;
+		if (is_last_spte(old_spte, level)) {
 			pt_element_t gpte;
 			gpa_t pte_gpa;
 
@@ -927,7 +935,8 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa)
 			pte_gpa = FNAME(get_level1_sp_gpa)(sp);
 			pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t);
 
-			if (mmu_page_zap_pte(vcpu->kvm, sp, sptep))
+			mmu_page_zap_pte(vcpu->kvm, sp, sptep, NULL);
+			if (is_shadow_present_pte(old_spte))
 				kvm_flush_remote_tlbs_with_address(vcpu->kvm,
 					sp->gfn, KVM_PAGES_PER_HPAGE(sp->role.level));
 
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index ac830cd..f73f84d 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -153,20 +153,18 @@ int avic_vm_init(struct kvm *kvm)
 		return 0;
 
 	/* Allocating physical APIC ID table (4KB) */
-	p_page = alloc_page(GFP_KERNEL_ACCOUNT);
+	p_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
 	if (!p_page)
 		goto free_avic;
 
 	kvm_svm->avic_physical_id_table_page = p_page;
-	clear_page(page_address(p_page));
 
 	/* Allocating logical APIC ID table (4KB) */
-	l_page = alloc_page(GFP_KERNEL_ACCOUNT);
+	l_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
 	if (!l_page)
 		goto free_avic;
 
 	kvm_svm->avic_logical_id_table_page = l_page;
-	clear_page(page_address(l_page));
 
 	spin_lock_irqsave(&svm_vm_data_hash_lock, flags);
  again:
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index fb68467..ba50ff6 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -98,6 +98,7 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu)
 void recalc_intercepts(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *c, *h, *g;
+	unsigned int i;
 
 	vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
 
@@ -108,42 +109,37 @@ void recalc_intercepts(struct vcpu_svm *svm)
 	h = &svm->nested.hsave->control;
 	g = &svm->nested.ctl;
 
-	svm->nested.host_intercept_exceptions = h->intercept_exceptions;
-
-	c->intercept_cr = h->intercept_cr;
-	c->intercept_dr = h->intercept_dr;
-	c->intercept_exceptions = h->intercept_exceptions;
-	c->intercept = h->intercept;
+	for (i = 0; i < MAX_INTERCEPT; i++)
+		c->intercepts[i] = h->intercepts[i];
 
 	if (g->int_ctl & V_INTR_MASKING_MASK) {
 		/* We only want the cr8 intercept bits of L1 */
-		c->intercept_cr &= ~(1U << INTERCEPT_CR8_READ);
-		c->intercept_cr &= ~(1U << INTERCEPT_CR8_WRITE);
+		vmcb_clr_intercept(c, INTERCEPT_CR8_READ);
+		vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE);
 
 		/*
 		 * Once running L2 with HF_VINTR_MASK, EFLAGS.IF does not
 		 * affect any interrupt we may want to inject; therefore,
 		 * interrupt window vmexits are irrelevant to L0.
 		 */
-		c->intercept &= ~(1ULL << INTERCEPT_VINTR);
+		vmcb_clr_intercept(c, INTERCEPT_VINTR);
 	}
 
 	/* We don't want to see VMMCALLs from a nested guest */
-	c->intercept &= ~(1ULL << INTERCEPT_VMMCALL);
+	vmcb_clr_intercept(c, INTERCEPT_VMMCALL);
 
-	c->intercept_cr |= g->intercept_cr;
-	c->intercept_dr |= g->intercept_dr;
-	c->intercept_exceptions |= g->intercept_exceptions;
-	c->intercept |= g->intercept;
+	for (i = 0; i < MAX_INTERCEPT; i++)
+		c->intercepts[i] |= g->intercepts[i];
 }
 
 static void copy_vmcb_control_area(struct vmcb_control_area *dst,
 				   struct vmcb_control_area *from)
 {
-	dst->intercept_cr         = from->intercept_cr;
-	dst->intercept_dr         = from->intercept_dr;
-	dst->intercept_exceptions = from->intercept_exceptions;
-	dst->intercept            = from->intercept;
+	unsigned int i;
+
+	for (i = 0; i < MAX_INTERCEPT; i++)
+		dst->intercepts[i] = from->intercepts[i];
+
 	dst->iopm_base_pa         = from->iopm_base_pa;
 	dst->msrpm_base_pa        = from->msrpm_base_pa;
 	dst->tsc_offset           = from->tsc_offset;
@@ -176,7 +172,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 	 */
 	int i;
 
-	if (!(svm->nested.ctl.intercept & (1ULL << INTERCEPT_MSR_PROT)))
+	if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)))
 		return true;
 
 	for (i = 0; i < MSRPM_OFFSETS; i++) {
@@ -200,9 +196,23 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 	return true;
 }
 
+static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	if (!nested_svm_vmrun_msrpm(svm)) {
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->internal.suberror =
+			KVM_INTERNAL_ERROR_EMULATION;
+		vcpu->run->internal.ndata = 0;
+		return false;
+	}
+
+	return true;
+}
+
 static bool nested_vmcb_check_controls(struct vmcb_control_area *control)
 {
-	if ((control->intercept & (1ULL << INTERCEPT_VMRUN)) == 0)
+	if ((vmcb_is_intercept(control, INTERCEPT_VMRUN)) == 0)
 		return false;
 
 	if (control->asid == 0)
@@ -215,41 +225,39 @@ static bool nested_vmcb_check_controls(struct vmcb_control_area *control)
 	return true;
 }
 
-static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb)
+static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12)
 {
-	bool nested_vmcb_lma;
-	if ((vmcb->save.efer & EFER_SVME) == 0)
+	bool vmcb12_lma;
+
+	if ((vmcb12->save.efer & EFER_SVME) == 0)
 		return false;
 
-	if (((vmcb->save.cr0 & X86_CR0_CD) == 0) &&
-	    (vmcb->save.cr0 & X86_CR0_NW))
+	if (((vmcb12->save.cr0 & X86_CR0_CD) == 0) && (vmcb12->save.cr0 & X86_CR0_NW))
 		return false;
 
-	if (!kvm_dr6_valid(vmcb->save.dr6) || !kvm_dr7_valid(vmcb->save.dr7))
+	if (!kvm_dr6_valid(vmcb12->save.dr6) || !kvm_dr7_valid(vmcb12->save.dr7))
 		return false;
 
-	nested_vmcb_lma =
-	        (vmcb->save.efer & EFER_LME) &&
-		(vmcb->save.cr0 & X86_CR0_PG);
+	vmcb12_lma = (vmcb12->save.efer & EFER_LME) && (vmcb12->save.cr0 & X86_CR0_PG);
 
-	if (!nested_vmcb_lma) {
-		if (vmcb->save.cr4 & X86_CR4_PAE) {
-			if (vmcb->save.cr3 & MSR_CR3_LEGACY_PAE_RESERVED_MASK)
+	if (!vmcb12_lma) {
+		if (vmcb12->save.cr4 & X86_CR4_PAE) {
+			if (vmcb12->save.cr3 & MSR_CR3_LEGACY_PAE_RESERVED_MASK)
 				return false;
 		} else {
-			if (vmcb->save.cr3 & MSR_CR3_LEGACY_RESERVED_MASK)
+			if (vmcb12->save.cr3 & MSR_CR3_LEGACY_RESERVED_MASK)
 				return false;
 		}
 	} else {
-		if (!(vmcb->save.cr4 & X86_CR4_PAE) ||
-		    !(vmcb->save.cr0 & X86_CR0_PE) ||
-		    (vmcb->save.cr3 & MSR_CR3_LONG_RESERVED_MASK))
+		if (!(vmcb12->save.cr4 & X86_CR4_PAE) ||
+		    !(vmcb12->save.cr0 & X86_CR0_PE) ||
+		    (vmcb12->save.cr3 & MSR_CR3_LONG_MBZ_MASK))
 			return false;
 	}
-	if (kvm_valid_cr4(&svm->vcpu, vmcb->save.cr4))
+	if (kvm_valid_cr4(&svm->vcpu, vmcb12->save.cr4))
 		return false;
 
-	return nested_vmcb_check_controls(&vmcb->control);
+	return nested_vmcb_check_controls(&vmcb12->control);
 }
 
 static void load_nested_vmcb_control(struct vcpu_svm *svm,
@@ -296,7 +304,7 @@ void sync_nested_vmcb_control(struct vcpu_svm *svm)
  * EXIT_INT_INFO.
  */
 static void nested_vmcb_save_pending_event(struct vcpu_svm *svm,
-					   struct vmcb *nested_vmcb)
+					   struct vmcb *vmcb12)
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 	u32 exit_int_info = 0;
@@ -308,7 +316,7 @@ static void nested_vmcb_save_pending_event(struct vcpu_svm *svm,
 
 		if (vcpu->arch.exception.has_error_code) {
 			exit_int_info |= SVM_EVTINJ_VALID_ERR;
-			nested_vmcb->control.exit_int_info_err =
+			vmcb12->control.exit_int_info_err =
 				vcpu->arch.exception.error_code;
 		}
 
@@ -325,7 +333,7 @@ static void nested_vmcb_save_pending_event(struct vcpu_svm *svm,
 			exit_int_info |= SVM_EVTINJ_TYPE_INTR;
 	}
 
-	nested_vmcb->control.exit_int_info = exit_int_info;
+	vmcb12->control.exit_int_info = exit_int_info;
 }
 
 static inline bool nested_npt_enabled(struct vcpu_svm *svm)
@@ -364,31 +372,31 @@ static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3,
 	return 0;
 }
 
-static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *nested_vmcb)
+static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
 {
 	/* Load the nested guest state */
-	svm->vmcb->save.es = nested_vmcb->save.es;
-	svm->vmcb->save.cs = nested_vmcb->save.cs;
-	svm->vmcb->save.ss = nested_vmcb->save.ss;
-	svm->vmcb->save.ds = nested_vmcb->save.ds;
-	svm->vmcb->save.gdtr = nested_vmcb->save.gdtr;
-	svm->vmcb->save.idtr = nested_vmcb->save.idtr;
-	kvm_set_rflags(&svm->vcpu, nested_vmcb->save.rflags);
-	svm_set_efer(&svm->vcpu, nested_vmcb->save.efer);
-	svm_set_cr0(&svm->vcpu, nested_vmcb->save.cr0);
-	svm_set_cr4(&svm->vcpu, nested_vmcb->save.cr4);
-	svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = nested_vmcb->save.cr2;
-	kvm_rax_write(&svm->vcpu, nested_vmcb->save.rax);
-	kvm_rsp_write(&svm->vcpu, nested_vmcb->save.rsp);
-	kvm_rip_write(&svm->vcpu, nested_vmcb->save.rip);
+	svm->vmcb->save.es = vmcb12->save.es;
+	svm->vmcb->save.cs = vmcb12->save.cs;
+	svm->vmcb->save.ss = vmcb12->save.ss;
+	svm->vmcb->save.ds = vmcb12->save.ds;
+	svm->vmcb->save.gdtr = vmcb12->save.gdtr;
+	svm->vmcb->save.idtr = vmcb12->save.idtr;
+	kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags);
+	svm_set_efer(&svm->vcpu, vmcb12->save.efer);
+	svm_set_cr0(&svm->vcpu, vmcb12->save.cr0);
+	svm_set_cr4(&svm->vcpu, vmcb12->save.cr4);
+	svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = vmcb12->save.cr2;
+	kvm_rax_write(&svm->vcpu, vmcb12->save.rax);
+	kvm_rsp_write(&svm->vcpu, vmcb12->save.rsp);
+	kvm_rip_write(&svm->vcpu, vmcb12->save.rip);
 
 	/* In case we don't even reach vcpu_run, the fields are not updated */
-	svm->vmcb->save.rax = nested_vmcb->save.rax;
-	svm->vmcb->save.rsp = nested_vmcb->save.rsp;
-	svm->vmcb->save.rip = nested_vmcb->save.rip;
-	svm->vmcb->save.dr7 = nested_vmcb->save.dr7;
-	svm->vcpu.arch.dr6  = nested_vmcb->save.dr6;
-	svm->vmcb->save.cpl = nested_vmcb->save.cpl;
+	svm->vmcb->save.rax = vmcb12->save.rax;
+	svm->vmcb->save.rsp = vmcb12->save.rsp;
+	svm->vmcb->save.rip = vmcb12->save.rip;
+	svm->vmcb->save.dr7 = vmcb12->save.dr7;
+	svm->vcpu.arch.dr6  = vmcb12->save.dr6;
+	svm->vmcb->save.cpl = vmcb12->save.cpl;
 }
 
 static void nested_prepare_vmcb_control(struct vcpu_svm *svm)
@@ -426,17 +434,17 @@ static void nested_prepare_vmcb_control(struct vcpu_svm *svm)
 	vmcb_mark_all_dirty(svm->vmcb);
 }
 
-int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
-			  struct vmcb *nested_vmcb)
+int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb12_gpa,
+			 struct vmcb *vmcb12)
 {
 	int ret;
 
-	svm->nested.vmcb = vmcb_gpa;
-	load_nested_vmcb_control(svm, &nested_vmcb->control);
-	nested_prepare_vmcb_save(svm, nested_vmcb);
+	svm->nested.vmcb12_gpa = vmcb12_gpa;
+	load_nested_vmcb_control(svm, &vmcb12->control);
+	nested_prepare_vmcb_save(svm, vmcb12);
 	nested_prepare_vmcb_control(svm);
 
-	ret = nested_svm_load_cr3(&svm->vcpu, nested_vmcb->save.cr3,
+	ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3,
 				  nested_npt_enabled(svm));
 	if (ret)
 		return ret;
@@ -449,19 +457,19 @@ int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
 int nested_svm_vmrun(struct vcpu_svm *svm)
 {
 	int ret;
-	struct vmcb *nested_vmcb;
+	struct vmcb *vmcb12;
 	struct vmcb *hsave = svm->nested.hsave;
 	struct vmcb *vmcb = svm->vmcb;
 	struct kvm_host_map map;
-	u64 vmcb_gpa;
+	u64 vmcb12_gpa;
 
 	if (is_smm(&svm->vcpu)) {
 		kvm_queue_exception(&svm->vcpu, UD_VECTOR);
 		return 1;
 	}
 
-	vmcb_gpa = svm->vmcb->save.rax;
-	ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb_gpa), &map);
+	vmcb12_gpa = svm->vmcb->save.rax;
+	ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb12_gpa), &map);
 	if (ret == -EINVAL) {
 		kvm_inject_gp(&svm->vcpu, 0);
 		return 1;
@@ -471,26 +479,28 @@ int nested_svm_vmrun(struct vcpu_svm *svm)
 
 	ret = kvm_skip_emulated_instruction(&svm->vcpu);
 
-	nested_vmcb = map.hva;
+	vmcb12 = map.hva;
 
-	if (!nested_vmcb_checks(svm, nested_vmcb)) {
-		nested_vmcb->control.exit_code    = SVM_EXIT_ERR;
-		nested_vmcb->control.exit_code_hi = 0;
-		nested_vmcb->control.exit_info_1  = 0;
-		nested_vmcb->control.exit_info_2  = 0;
+	if (!nested_vmcb_checks(svm, vmcb12)) {
+		vmcb12->control.exit_code    = SVM_EXIT_ERR;
+		vmcb12->control.exit_code_hi = 0;
+		vmcb12->control.exit_info_1  = 0;
+		vmcb12->control.exit_info_2  = 0;
 		goto out;
 	}
 
-	trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb_gpa,
-			       nested_vmcb->save.rip,
-			       nested_vmcb->control.int_ctl,
-			       nested_vmcb->control.event_inj,
-			       nested_vmcb->control.nested_ctl);
+	trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb12_gpa,
+			       vmcb12->save.rip,
+			       vmcb12->control.int_ctl,
+			       vmcb12->control.event_inj,
+			       vmcb12->control.nested_ctl);
 
-	trace_kvm_nested_intercepts(nested_vmcb->control.intercept_cr & 0xffff,
-				    nested_vmcb->control.intercept_cr >> 16,
-				    nested_vmcb->control.intercept_exceptions,
-				    nested_vmcb->control.intercept);
+	trace_kvm_nested_intercepts(vmcb12->control.intercepts[INTERCEPT_CR] & 0xffff,
+				    vmcb12->control.intercepts[INTERCEPT_CR] >> 16,
+				    vmcb12->control.intercepts[INTERCEPT_EXCEPTION],
+				    vmcb12->control.intercepts[INTERCEPT_WORD3],
+				    vmcb12->control.intercepts[INTERCEPT_WORD4],
+				    vmcb12->control.intercepts[INTERCEPT_WORD5]);
 
 	/* Clear internal status */
 	kvm_clear_exception_queue(&svm->vcpu);
@@ -522,7 +532,7 @@ int nested_svm_vmrun(struct vcpu_svm *svm)
 
 	svm->nested.nested_run_pending = 1;
 
-	if (enter_svm_guest_mode(svm, vmcb_gpa, nested_vmcb))
+	if (enter_svm_guest_mode(svm, vmcb12_gpa, vmcb12))
 		goto out_exit_err;
 
 	if (nested_svm_vmrun_msrpm(svm))
@@ -563,75 +573,77 @@ void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
 int nested_svm_vmexit(struct vcpu_svm *svm)
 {
 	int rc;
-	struct vmcb *nested_vmcb;
+	struct vmcb *vmcb12;
 	struct vmcb *hsave = svm->nested.hsave;
 	struct vmcb *vmcb = svm->vmcb;
 	struct kvm_host_map map;
 
-	rc = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->nested.vmcb), &map);
+	rc = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->nested.vmcb12_gpa), &map);
 	if (rc) {
 		if (rc == -EINVAL)
 			kvm_inject_gp(&svm->vcpu, 0);
 		return 1;
 	}
 
-	nested_vmcb = map.hva;
+	vmcb12 = map.hva;
 
 	/* Exit Guest-Mode */
 	leave_guest_mode(&svm->vcpu);
-	svm->nested.vmcb = 0;
+	svm->nested.vmcb12_gpa = 0;
 	WARN_ON_ONCE(svm->nested.nested_run_pending);
 
 	/* in case we halted in L2 */
 	svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
 	/* Give the current vmcb to the guest */
-	svm_set_gif(svm, false);
 
-	nested_vmcb->save.es     = vmcb->save.es;
-	nested_vmcb->save.cs     = vmcb->save.cs;
-	nested_vmcb->save.ss     = vmcb->save.ss;
-	nested_vmcb->save.ds     = vmcb->save.ds;
-	nested_vmcb->save.gdtr   = vmcb->save.gdtr;
-	nested_vmcb->save.idtr   = vmcb->save.idtr;
-	nested_vmcb->save.efer   = svm->vcpu.arch.efer;
-	nested_vmcb->save.cr0    = kvm_read_cr0(&svm->vcpu);
-	nested_vmcb->save.cr3    = kvm_read_cr3(&svm->vcpu);
-	nested_vmcb->save.cr2    = vmcb->save.cr2;
-	nested_vmcb->save.cr4    = svm->vcpu.arch.cr4;
-	nested_vmcb->save.rflags = kvm_get_rflags(&svm->vcpu);
-	nested_vmcb->save.rip    = kvm_rip_read(&svm->vcpu);
-	nested_vmcb->save.rsp    = kvm_rsp_read(&svm->vcpu);
-	nested_vmcb->save.rax    = kvm_rax_read(&svm->vcpu);
-	nested_vmcb->save.dr7    = vmcb->save.dr7;
-	nested_vmcb->save.dr6    = svm->vcpu.arch.dr6;
-	nested_vmcb->save.cpl    = vmcb->save.cpl;
+	vmcb12->save.es     = vmcb->save.es;
+	vmcb12->save.cs     = vmcb->save.cs;
+	vmcb12->save.ss     = vmcb->save.ss;
+	vmcb12->save.ds     = vmcb->save.ds;
+	vmcb12->save.gdtr   = vmcb->save.gdtr;
+	vmcb12->save.idtr   = vmcb->save.idtr;
+	vmcb12->save.efer   = svm->vcpu.arch.efer;
+	vmcb12->save.cr0    = kvm_read_cr0(&svm->vcpu);
+	vmcb12->save.cr3    = kvm_read_cr3(&svm->vcpu);
+	vmcb12->save.cr2    = vmcb->save.cr2;
+	vmcb12->save.cr4    = svm->vcpu.arch.cr4;
+	vmcb12->save.rflags = kvm_get_rflags(&svm->vcpu);
+	vmcb12->save.rip    = kvm_rip_read(&svm->vcpu);
+	vmcb12->save.rsp    = kvm_rsp_read(&svm->vcpu);
+	vmcb12->save.rax    = kvm_rax_read(&svm->vcpu);
+	vmcb12->save.dr7    = vmcb->save.dr7;
+	vmcb12->save.dr6    = svm->vcpu.arch.dr6;
+	vmcb12->save.cpl    = vmcb->save.cpl;
 
-	nested_vmcb->control.int_state         = vmcb->control.int_state;
-	nested_vmcb->control.exit_code         = vmcb->control.exit_code;
-	nested_vmcb->control.exit_code_hi      = vmcb->control.exit_code_hi;
-	nested_vmcb->control.exit_info_1       = vmcb->control.exit_info_1;
-	nested_vmcb->control.exit_info_2       = vmcb->control.exit_info_2;
+	vmcb12->control.int_state         = vmcb->control.int_state;
+	vmcb12->control.exit_code         = vmcb->control.exit_code;
+	vmcb12->control.exit_code_hi      = vmcb->control.exit_code_hi;
+	vmcb12->control.exit_info_1       = vmcb->control.exit_info_1;
+	vmcb12->control.exit_info_2       = vmcb->control.exit_info_2;
 
-	if (nested_vmcb->control.exit_code != SVM_EXIT_ERR)
-		nested_vmcb_save_pending_event(svm, nested_vmcb);
+	if (vmcb12->control.exit_code != SVM_EXIT_ERR)
+		nested_vmcb_save_pending_event(svm, vmcb12);
 
 	if (svm->nrips_enabled)
-		nested_vmcb->control.next_rip  = vmcb->control.next_rip;
+		vmcb12->control.next_rip  = vmcb->control.next_rip;
 
-	nested_vmcb->control.int_ctl           = svm->nested.ctl.int_ctl;
-	nested_vmcb->control.tlb_ctl           = svm->nested.ctl.tlb_ctl;
-	nested_vmcb->control.event_inj         = svm->nested.ctl.event_inj;
-	nested_vmcb->control.event_inj_err     = svm->nested.ctl.event_inj_err;
+	vmcb12->control.int_ctl           = svm->nested.ctl.int_ctl;
+	vmcb12->control.tlb_ctl           = svm->nested.ctl.tlb_ctl;
+	vmcb12->control.event_inj         = svm->nested.ctl.event_inj;
+	vmcb12->control.event_inj_err     = svm->nested.ctl.event_inj_err;
 
-	nested_vmcb->control.pause_filter_count =
+	vmcb12->control.pause_filter_count =
 		svm->vmcb->control.pause_filter_count;
-	nested_vmcb->control.pause_filter_thresh =
+	vmcb12->control.pause_filter_thresh =
 		svm->vmcb->control.pause_filter_thresh;
 
 	/* Restore the original control entries */
 	copy_vmcb_control_area(&vmcb->control, &hsave->control);
 
+	/* On vmexit the  GIF is set to false */
+	svm_set_gif(svm, false);
+
 	svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset =
 		svm->vcpu.arch.l1_tsc_offset;
 
@@ -657,11 +669,11 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 
 	vmcb_mark_all_dirty(svm->vmcb);
 
-	trace_kvm_nested_vmexit_inject(nested_vmcb->control.exit_code,
-				       nested_vmcb->control.exit_info_1,
-				       nested_vmcb->control.exit_info_2,
-				       nested_vmcb->control.exit_int_info,
-				       nested_vmcb->control.exit_int_info_err,
+	trace_kvm_nested_vmexit_inject(vmcb12->control.exit_code,
+				       vmcb12->control.exit_info_1,
+				       vmcb12->control.exit_info_2,
+				       vmcb12->control.exit_int_info,
+				       vmcb12->control.exit_int_info_err,
 				       KVM_ISA_SVM);
 
 	kvm_vcpu_unmap(&svm->vcpu, &map, true);
@@ -700,6 +712,8 @@ void svm_leave_nested(struct vcpu_svm *svm)
 		copy_vmcb_control_area(&vmcb->control, &hsave->control);
 		nested_svm_uninit_mmu_context(&svm->vcpu);
 	}
+
+	kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, &svm->vcpu);
 }
 
 static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
@@ -707,7 +721,7 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
 	u32 offset, msr, value;
 	int write, mask;
 
-	if (!(svm->nested.ctl.intercept & (1ULL << INTERCEPT_MSR_PROT)))
+	if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)))
 		return NESTED_EXIT_HOST;
 
 	msr    = svm->vcpu.arch.regs[VCPU_REGS_RCX];
@@ -734,7 +748,7 @@ static int nested_svm_intercept_ioio(struct vcpu_svm *svm)
 	u8 start_bit;
 	u64 gpa;
 
-	if (!(svm->nested.ctl.intercept & (1ULL << INTERCEPT_IOIO_PROT)))
+	if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_IOIO_PROT)))
 		return NESTED_EXIT_HOST;
 
 	port = svm->vmcb->control.exit_info_1 >> 16;
@@ -765,14 +779,12 @@ static int nested_svm_intercept(struct vcpu_svm *svm)
 		vmexit = nested_svm_intercept_ioio(svm);
 		break;
 	case SVM_EXIT_READ_CR0 ... SVM_EXIT_WRITE_CR8: {
-		u32 bit = 1U << (exit_code - SVM_EXIT_READ_CR0);
-		if (svm->nested.ctl.intercept_cr & bit)
+		if (vmcb_is_intercept(&svm->nested.ctl, exit_code))
 			vmexit = NESTED_EXIT_DONE;
 		break;
 	}
 	case SVM_EXIT_READ_DR0 ... SVM_EXIT_WRITE_DR7: {
-		u32 bit = 1U << (exit_code - SVM_EXIT_READ_DR0);
-		if (svm->nested.ctl.intercept_dr & bit)
+		if (vmcb_is_intercept(&svm->nested.ctl, exit_code))
 			vmexit = NESTED_EXIT_DONE;
 		break;
 	}
@@ -790,8 +802,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm)
 		break;
 	}
 	default: {
-		u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR);
-		if (svm->nested.ctl.intercept & exit_bits)
+		if (vmcb_is_intercept(&svm->nested.ctl, exit_code))
 			vmexit = NESTED_EXIT_DONE;
 	}
 	}
@@ -831,7 +842,7 @@ static bool nested_exit_on_exception(struct vcpu_svm *svm)
 {
 	unsigned int nr = svm->vcpu.arch.exception.nr;
 
-	return (svm->nested.ctl.intercept_exceptions & (1 << nr));
+	return (svm->nested.ctl.intercepts[INTERCEPT_EXCEPTION] & BIT(nr));
 }
 
 static void nested_svm_inject_exception_vmexit(struct vcpu_svm *svm)
@@ -899,7 +910,7 @@ static void nested_svm_intr(struct vcpu_svm *svm)
 
 static inline bool nested_exit_on_init(struct vcpu_svm *svm)
 {
-	return (svm->nested.ctl.intercept & (1ULL << INTERCEPT_INIT));
+	return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_INIT);
 }
 
 static void nested_svm_init(struct vcpu_svm *svm)
@@ -980,7 +991,8 @@ int nested_svm_exit_special(struct vcpu_svm *svm)
 	case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: {
 		u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE);
 
-		if (get_host_vmcb(svm)->control.intercept_exceptions & excp_bits)
+		if (get_host_vmcb(svm)->control.intercepts[INTERCEPT_EXCEPTION] &
+				excp_bits)
 			return NESTED_EXIT_HOST;
 		else if (exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR &&
 			 svm->vcpu.arch.apf.host_apf_flags)
@@ -1018,7 +1030,7 @@ static int svm_get_nested_state(struct kvm_vcpu *vcpu,
 
 	/* First fill in the header and copy it out.  */
 	if (is_guest_mode(vcpu)) {
-		kvm_state.hdr.svm.vmcb_pa = svm->nested.vmcb;
+		kvm_state.hdr.svm.vmcb_pa = svm->nested.vmcb12_gpa;
 		kvm_state.size += KVM_STATE_NESTED_SVM_VMCB_SIZE;
 		kvm_state.flags |= KVM_STATE_NESTED_GUEST_MODE;
 
@@ -1060,10 +1072,14 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	struct vmcb *hsave = svm->nested.hsave;
 	struct vmcb __user *user_vmcb = (struct vmcb __user *)
 		&user_kvm_nested_state->data.svm[0];
-	struct vmcb_control_area ctl;
-	struct vmcb_save_area save;
+	struct vmcb_control_area *ctl;
+	struct vmcb_save_area *save;
+	int ret;
 	u32 cr0;
 
+	BUILD_BUG_ON(sizeof(struct vmcb_control_area) + sizeof(struct vmcb_save_area) >
+		     KVM_STATE_NESTED_SVM_VMCB_SIZE);
+
 	if (kvm_state->format != KVM_STATE_NESTED_FORMAT_SVM)
 		return -EINVAL;
 
@@ -1088,20 +1104,30 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 
 	if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE)) {
 		svm_leave_nested(svm);
-		goto out_set_gif;
+		svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET));
+		return 0;
 	}
 
 	if (!page_address_valid(vcpu, kvm_state->hdr.svm.vmcb_pa))
 		return -EINVAL;
 	if (kvm_state->size < sizeof(*kvm_state) + KVM_STATE_NESTED_SVM_VMCB_SIZE)
 		return -EINVAL;
-	if (copy_from_user(&ctl, &user_vmcb->control, sizeof(ctl)))
-		return -EFAULT;
-	if (copy_from_user(&save, &user_vmcb->save, sizeof(save)))
-		return -EFAULT;
 
-	if (!nested_vmcb_check_controls(&ctl))
-		return -EINVAL;
+	ret  = -ENOMEM;
+	ctl  = kzalloc(sizeof(*ctl),  GFP_KERNEL);
+	save = kzalloc(sizeof(*save), GFP_KERNEL);
+	if (!ctl || !save)
+		goto out_free;
+
+	ret = -EFAULT;
+	if (copy_from_user(ctl, &user_vmcb->control, sizeof(*ctl)))
+		goto out_free;
+	if (copy_from_user(save, &user_vmcb->save, sizeof(*save)))
+		goto out_free;
+
+	ret = -EINVAL;
+	if (!nested_vmcb_check_controls(ctl))
+		goto out_free;
 
 	/*
 	 * Processor state contains L2 state.  Check that it is
@@ -1109,15 +1135,15 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	 */
 	cr0 = kvm_read_cr0(vcpu);
         if (((cr0 & X86_CR0_CD) == 0) && (cr0 & X86_CR0_NW))
-                return -EINVAL;
+		goto out_free;
 
 	/*
 	 * Validate host state saved from before VMRUN (see
 	 * nested_svm_check_permissions).
 	 * TODO: validate reserved bits for all saved state.
 	 */
-	if (!(save.cr0 & X86_CR0_PG))
-		return -EINVAL;
+	if (!(save->cr0 & X86_CR0_PG))
+		goto out_free;
 
 	/*
 	 * All checks done, we can enter guest mode.  L1 control fields
@@ -1126,19 +1152,24 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	 * contains saved L1 state.
 	 */
 	copy_vmcb_control_area(&hsave->control, &svm->vmcb->control);
-	hsave->save = save;
+	hsave->save = *save;
 
-	svm->nested.vmcb = kvm_state->hdr.svm.vmcb_pa;
-	load_nested_vmcb_control(svm, &ctl);
+	svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa;
+	load_nested_vmcb_control(svm, ctl);
 	nested_prepare_vmcb_control(svm);
 
-out_set_gif:
-	svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET));
-	return 0;
+	kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
+	ret = 0;
+out_free:
+	kfree(save);
+	kfree(ctl);
+
+	return ret;
 }
 
 struct kvm_x86_nested_ops svm_nested_ops = {
 	.check_events = svm_check_nested_events,
+	.get_nested_state_pages = svm_get_nested_state_pages,
 	.get_state = svm_get_nested_state,
 	.set_state = svm_set_nested_state,
 };
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 402dc42..65e15c2 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -446,10 +446,8 @@ static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	}
 
 	/*
-	 * The LAUNCH_UPDATE command will perform in-place encryption of the
-	 * memory content (i.e it will write the same memory region with C=1).
-	 * It's possible that the cache may contain the data with C=0, i.e.,
-	 * unencrypted so invalidate it first.
+	 * Flush (on non-coherent CPUs) before LAUNCH_UPDATE encrypts pages in
+	 * place; the cache may contain the data that was written unencrypted.
 	 */
 	sev_clflush_pages(inpages, npages);
 
@@ -805,10 +803,9 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
 		}
 
 		/*
-		 * The DBG_{DE,EN}CRYPT commands will perform {dec,en}cryption of the
-		 * memory content (i.e it will write the same memory region with C=1).
-		 * It's possible that the cache may contain the data with C=0, i.e.,
-		 * unencrypted so invalidate it first.
+		 * Flush (on non-coherent CPUs) before DBG_{DE,EN}CRYPT read or modify
+		 * the pages; flush the destination too so that future accesses do not
+		 * see stale data.
 		 */
 		sev_clflush_pages(src_p, 1);
 		sev_clflush_pages(dst_p, 1);
@@ -856,7 +853,7 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	struct kvm_sev_launch_secret params;
 	struct page **pages;
 	void *blob, *hdr;
-	unsigned long n;
+	unsigned long n, i;
 	int ret, offset;
 
 	if (!sev_guest(kvm))
@@ -870,6 +867,12 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp)
 		return PTR_ERR(pages);
 
 	/*
+	 * Flush (on non-coherent CPUs) before LAUNCH_SECRET encrypts pages in
+	 * place; the cache may contain the data that was written unencrypted.
+	 */
+	sev_clflush_pages(pages, n);
+
+	/*
 	 * The secret must be copied into contiguous memory region, lets verify
 	 * that userspace memory pages are contiguous before we issue command.
 	 */
@@ -914,6 +917,11 @@ static int sev_launch_secret(struct kvm *kvm, struct kvm_sev_cmd *argp)
 e_free:
 	kfree(data);
 e_unpin_memory:
+	/* content of memory is updated, mark pages dirty */
+	for (i = 0; i < n; i++) {
+		set_page_dirty_lock(pages[i]);
+		mark_page_accessed(pages[i]);
+	}
 	sev_unpin_memory(kvm, pages, n);
 	return ret;
 }
@@ -1106,6 +1114,7 @@ void sev_vm_destroy(struct kvm *kvm)
 		list_for_each_safe(pos, q, head) {
 			__unregister_enc_region_locked(kvm,
 				list_entry(pos, struct enc_region, list));
+			cond_resched();
 		}
 	}
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 0194336..4f401fc 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -91,7 +91,7 @@ static DEFINE_PER_CPU(u64, current_tsc_ratio);
 static const struct svm_direct_access_msrs {
 	u32 index;   /* Index of the MSR */
 	bool always; /* True if intercept is always on */
-} direct_access_msrs[] = {
+} direct_access_msrs[MAX_DIRECT_ACCESS_MSRS] = {
 	{ .index = MSR_STAR,				.always = true  },
 	{ .index = MSR_IA32_SYSENTER_CS,		.always = true  },
 #ifdef CONFIG_X86_64
@@ -553,18 +553,44 @@ static int svm_cpu_init(int cpu)
 
 }
 
-static bool valid_msr_intercept(u32 index)
+static int direct_access_msr_slot(u32 msr)
 {
-	int i;
+	u32 i;
 
 	for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++)
-		if (direct_access_msrs[i].index == index)
-			return true;
+		if (direct_access_msrs[i].index == msr)
+			return i;
 
-	return false;
+	return -ENOENT;
 }
 
-static bool msr_write_intercepted(struct kvm_vcpu *vcpu, unsigned msr)
+static void set_shadow_msr_intercept(struct kvm_vcpu *vcpu, u32 msr, int read,
+				     int write)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	int slot = direct_access_msr_slot(msr);
+
+	if (slot == -ENOENT)
+		return;
+
+	/* Set the shadow bitmaps to the desired intercept states */
+	if (read)
+		set_bit(slot, svm->shadow_msr_intercept.read);
+	else
+		clear_bit(slot, svm->shadow_msr_intercept.read);
+
+	if (write)
+		set_bit(slot, svm->shadow_msr_intercept.write);
+	else
+		clear_bit(slot, svm->shadow_msr_intercept.write);
+}
+
+static bool valid_msr_intercept(u32 index)
+{
+	return direct_access_msr_slot(index) != -ENOENT;
+}
+
+static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
 {
 	u8 bit_write;
 	unsigned long tmp;
@@ -583,8 +609,8 @@ static bool msr_write_intercepted(struct kvm_vcpu *vcpu, unsigned msr)
 	return !!test_bit(bit_write,  &tmp);
 }
 
-static void set_msr_interception(u32 *msrpm, unsigned msr,
-				 int read, int write)
+static void set_msr_interception_bitmap(struct kvm_vcpu *vcpu, u32 *msrpm,
+					u32 msr, int read, int write)
 {
 	u8 bit_read, bit_write;
 	unsigned long tmp;
@@ -596,6 +622,13 @@ static void set_msr_interception(u32 *msrpm, unsigned msr,
 	 */
 	WARN_ON(!valid_msr_intercept(msr));
 
+	/* Enforce non allowed MSRs to trap */
+	if (read && !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ))
+		read = 0;
+
+	if (write && !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE))
+		write = 0;
+
 	offset    = svm_msrpm_offset(msr);
 	bit_read  = 2 * (msr & 0x0f);
 	bit_write = 2 * (msr & 0x0f) + 1;
@@ -609,17 +642,59 @@ static void set_msr_interception(u32 *msrpm, unsigned msr,
 	msrpm[offset] = tmp;
 }
 
-static void svm_vcpu_init_msrpm(u32 *msrpm)
+static void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr,
+				 int read, int write)
+{
+	set_shadow_msr_intercept(vcpu, msr, read, write);
+	set_msr_interception_bitmap(vcpu, msrpm, msr, read, write);
+}
+
+static u32 *svm_vcpu_alloc_msrpm(void)
+{
+	struct page *pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER);
+	u32 *msrpm;
+
+	if (!pages)
+		return NULL;
+
+	msrpm = page_address(pages);
+	memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER));
+
+	return msrpm;
+}
+
+static void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm)
 {
 	int i;
 
-	memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER));
-
 	for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
 		if (!direct_access_msrs[i].always)
 			continue;
+		set_msr_interception(vcpu, msrpm, direct_access_msrs[i].index, 1, 1);
+	}
+}
 
-		set_msr_interception(msrpm, direct_access_msrs[i].index, 1, 1);
+static void svm_vcpu_free_msrpm(u32 *msrpm)
+{
+	__free_pages(virt_to_page(msrpm), MSRPM_ALLOC_ORDER);
+}
+
+static void svm_msr_filter_changed(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	u32 i;
+
+	/*
+	 * Set intercept permissions for all direct access MSRs again. They
+	 * will automatically get filtered through the MSR filter, so we are
+	 * back in sync after this.
+	 */
+	for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
+		u32 msr = direct_access_msrs[i].index;
+		u32 read = test_bit(i, svm->shadow_msr_intercept.read);
+		u32 write = test_bit(i, svm->shadow_msr_intercept.write);
+
+		set_msr_interception_bitmap(vcpu, svm->msrpm, msr, read, write);
 	}
 }
 
@@ -666,26 +741,26 @@ static void init_msrpm_offsets(void)
 	}
 }
 
-static void svm_enable_lbrv(struct vcpu_svm *svm)
+static void svm_enable_lbrv(struct kvm_vcpu *vcpu)
 {
-	u32 *msrpm = svm->msrpm;
+	struct vcpu_svm *svm = to_svm(vcpu);
 
 	svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
-	set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
-	set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
-	set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
-	set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
 }
 
-static void svm_disable_lbrv(struct vcpu_svm *svm)
+static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
 {
-	u32 *msrpm = svm->msrpm;
+	struct vcpu_svm *svm = to_svm(vcpu);
 
 	svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK;
-	set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
-	set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
-	set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 0, 0);
-	set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 0, 0);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
 }
 
 void disable_nmi_singlestep(struct vcpu_svm *svm)
@@ -813,6 +888,9 @@ static __init void svm_set_cpu_caps(void)
 	if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) ||
 	    boot_cpu_has(X86_FEATURE_AMD_SSBD))
 		kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD);
+
+	/* Enable INVPCID feature */
+	kvm_cpu_cap_check_and_set(X86_FEATURE_INVPCID);
 }
 
 static __init int svm_hardware_setup(void)
@@ -985,6 +1063,21 @@ static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 	return svm->vmcb->control.tsc_offset;
 }
 
+static void svm_check_invpcid(struct vcpu_svm *svm)
+{
+	/*
+	 * Intercept INVPCID instruction only if shadow page table is
+	 * enabled. Interception is not required with nested page table
+	 * enabled.
+	 */
+	if (kvm_cpu_cap_has(X86_FEATURE_INVPCID)) {
+		if (!npt_enabled)
+			svm_set_intercept(svm, INTERCEPT_INVPCID);
+		else
+			svm_clr_intercept(svm, INTERCEPT_INVPCID);
+	}
+}
+
 static void init_vmcb(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
@@ -992,14 +1085,14 @@ static void init_vmcb(struct vcpu_svm *svm)
 
 	svm->vcpu.arch.hflags = 0;
 
-	set_cr_intercept(svm, INTERCEPT_CR0_READ);
-	set_cr_intercept(svm, INTERCEPT_CR3_READ);
-	set_cr_intercept(svm, INTERCEPT_CR4_READ);
-	set_cr_intercept(svm, INTERCEPT_CR0_WRITE);
-	set_cr_intercept(svm, INTERCEPT_CR3_WRITE);
-	set_cr_intercept(svm, INTERCEPT_CR4_WRITE);
+	svm_set_intercept(svm, INTERCEPT_CR0_READ);
+	svm_set_intercept(svm, INTERCEPT_CR3_READ);
+	svm_set_intercept(svm, INTERCEPT_CR4_READ);
+	svm_set_intercept(svm, INTERCEPT_CR0_WRITE);
+	svm_set_intercept(svm, INTERCEPT_CR3_WRITE);
+	svm_set_intercept(svm, INTERCEPT_CR4_WRITE);
 	if (!kvm_vcpu_apicv_active(&svm->vcpu))
-		set_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+		svm_set_intercept(svm, INTERCEPT_CR8_WRITE);
 
 	set_dr_intercepts(svm);
 
@@ -1094,15 +1187,15 @@ static void init_vmcb(struct vcpu_svm *svm)
 		control->nested_ctl |= SVM_NESTED_CTL_NP_ENABLE;
 		svm_clr_intercept(svm, INTERCEPT_INVLPG);
 		clr_exception_intercept(svm, PF_VECTOR);
-		clr_cr_intercept(svm, INTERCEPT_CR3_READ);
-		clr_cr_intercept(svm, INTERCEPT_CR3_WRITE);
+		svm_clr_intercept(svm, INTERCEPT_CR3_READ);
+		svm_clr_intercept(svm, INTERCEPT_CR3_WRITE);
 		save->g_pat = svm->vcpu.arch.pat;
 		save->cr3 = 0;
 		save->cr4 = 0;
 	}
 	svm->asid_generation = 0;
 
-	svm->nested.vmcb = 0;
+	svm->nested.vmcb12_gpa = 0;
 	svm->vcpu.arch.hflags = 0;
 
 	if (!kvm_pause_in_guest(svm->vcpu.kvm)) {
@@ -1114,6 +1207,8 @@ static void init_vmcb(struct vcpu_svm *svm)
 		svm_clr_intercept(svm, INTERCEPT_PAUSE);
 	}
 
+	svm_check_invpcid(svm);
+
 	if (kvm_vcpu_apicv_active(&svm->vcpu))
 		avic_init_vmcb(svm);
 
@@ -1171,35 +1266,25 @@ static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm;
-	struct page *page;
-	struct page *msrpm_pages;
+	struct page *vmcb_page;
 	struct page *hsave_page;
-	struct page *nested_msrpm_pages;
 	int err;
 
 	BUILD_BUG_ON(offsetof(struct vcpu_svm, vcpu) != 0);
 	svm = to_svm(vcpu);
 
 	err = -ENOMEM;
-	page = alloc_page(GFP_KERNEL_ACCOUNT);
-	if (!page)
+	vmcb_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+	if (!vmcb_page)
 		goto out;
 
-	msrpm_pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER);
-	if (!msrpm_pages)
-		goto free_page1;
-
-	nested_msrpm_pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER);
-	if (!nested_msrpm_pages)
-		goto free_page2;
-
-	hsave_page = alloc_page(GFP_KERNEL_ACCOUNT);
+	hsave_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
 	if (!hsave_page)
-		goto free_page3;
+		goto error_free_vmcb_page;
 
 	err = avic_init_vcpu(svm);
 	if (err)
-		goto free_page4;
+		goto error_free_hsave_page;
 
 	/* We initialize this flag to true to make sure that the is_running
 	 * bit would be set the first time the vcpu is loaded.
@@ -1208,17 +1293,22 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 		svm->avic_is_running = true;
 
 	svm->nested.hsave = page_address(hsave_page);
-	clear_page(svm->nested.hsave);
 
-	svm->msrpm = page_address(msrpm_pages);
-	svm_vcpu_init_msrpm(svm->msrpm);
+	svm->msrpm = svm_vcpu_alloc_msrpm();
+	if (!svm->msrpm)
+		goto error_free_hsave_page;
 
-	svm->nested.msrpm = page_address(nested_msrpm_pages);
-	svm_vcpu_init_msrpm(svm->nested.msrpm);
+	svm_vcpu_init_msrpm(vcpu, svm->msrpm);
 
-	svm->vmcb = page_address(page);
-	clear_page(svm->vmcb);
-	svm->vmcb_pa = __sme_set(page_to_pfn(page) << PAGE_SHIFT);
+	svm->nested.msrpm = svm_vcpu_alloc_msrpm();
+	if (!svm->nested.msrpm)
+		goto error_free_msrpm;
+
+	/* We only need the L1 pass-through MSR state, so leave vcpu as NULL */
+	svm_vcpu_init_msrpm(vcpu, svm->nested.msrpm);
+
+	svm->vmcb = page_address(vmcb_page);
+	svm->vmcb_pa = __sme_set(page_to_pfn(vmcb_page) << PAGE_SHIFT);
 	svm->asid_generation = 0;
 	init_vmcb(svm);
 
@@ -1227,14 +1317,12 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 
 	return 0;
 
-free_page4:
+error_free_msrpm:
+	svm_vcpu_free_msrpm(svm->msrpm);
+error_free_hsave_page:
 	__free_page(hsave_page);
-free_page3:
-	__free_pages(nested_msrpm_pages, MSRPM_ALLOC_ORDER);
-free_page2:
-	__free_pages(msrpm_pages, MSRPM_ALLOC_ORDER);
-free_page1:
-	__free_page(page);
+error_free_vmcb_page:
+	__free_page(vmcb_page);
 out:
 	return err;
 }
@@ -1549,11 +1637,11 @@ static void update_cr0_intercept(struct vcpu_svm *svm)
 	vmcb_mark_dirty(svm->vmcb, VMCB_CR);
 
 	if (gcr0 == *hcr0) {
-		clr_cr_intercept(svm, INTERCEPT_CR0_READ);
-		clr_cr_intercept(svm, INTERCEPT_CR0_WRITE);
+		svm_clr_intercept(svm, INTERCEPT_CR0_READ);
+		svm_clr_intercept(svm, INTERCEPT_CR0_WRITE);
 	} else {
-		set_cr_intercept(svm, INTERCEPT_CR0_READ);
-		set_cr_intercept(svm, INTERCEPT_CR0_WRITE);
+		svm_set_intercept(svm, INTERCEPT_CR0_READ);
+		svm_set_intercept(svm, INTERCEPT_CR0_WRITE);
 	}
 }
 
@@ -2218,12 +2306,9 @@ static bool check_selective_cr0_intercepted(struct vcpu_svm *svm,
 {
 	unsigned long cr0 = svm->vcpu.arch.cr0;
 	bool ret = false;
-	u64 intercept;
-
-	intercept = svm->nested.ctl.intercept;
 
 	if (!is_guest_mode(&svm->vcpu) ||
-	    (!(intercept & (1ULL << INTERCEPT_SELECTIVE_CR0))))
+	    (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_SELECTIVE_CR0))))
 		return false;
 
 	cr0 &= ~SVM_CR0_SELECTIVE_MASK;
@@ -2261,6 +2346,7 @@ static int cr_interception(struct vcpu_svm *svm)
 	if (cr >= 16) { /* mov to cr */
 		cr -= 16;
 		val = kvm_register_read(&svm->vcpu, reg);
+		trace_kvm_cr_write(cr, val);
 		switch (cr) {
 		case 0:
 			if (!check_selective_cr0_intercepted(svm, val))
@@ -2306,6 +2392,7 @@ static int cr_interception(struct vcpu_svm *svm)
 			return 1;
 		}
 		kvm_register_write(&svm->vcpu, reg, val);
+		trace_kvm_cr_read(cr, val);
 	}
 	return kvm_complete_insn_gp(&svm->vcpu, err);
 }
@@ -2556,7 +2643,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		 * We update the L1 MSR bit as well since it will end up
 		 * touching the MSR anyway now.
 		 */
-		set_msr_interception(svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
 		break;
 	case MSR_IA32_PRED_CMD:
 		if (!msr->host_initiated &&
@@ -2571,7 +2658,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 			break;
 
 		wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
-		set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
 		break;
 	case MSR_AMD64_VIRT_SPEC_CTRL:
 		if (!msr->host_initiated &&
@@ -2635,9 +2722,9 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		svm->vmcb->save.dbgctl = data;
 		vmcb_mark_dirty(svm->vmcb, VMCB_LBR);
 		if (data & (1ULL<<0))
-			svm_enable_lbrv(svm);
+			svm_enable_lbrv(vcpu);
 		else
-			svm_disable_lbrv(svm);
+			svm_disable_lbrv(vcpu);
 		break;
 	case MSR_VM_HSAVE_PA:
 		svm->nested.hsave_msr = data;
@@ -2733,6 +2820,33 @@ static int mwait_interception(struct vcpu_svm *svm)
 	return nop_interception(svm);
 }
 
+static int invpcid_interception(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	unsigned long type;
+	gva_t gva;
+
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) {
+		kvm_queue_exception(vcpu, UD_VECTOR);
+		return 1;
+	}
+
+	/*
+	 * For an INVPCID intercept:
+	 * EXITINFO1 provides the linear address of the memory operand.
+	 * EXITINFO2 provides the contents of the register operand.
+	 */
+	type = svm->vmcb->control.exit_info_2;
+	gva = svm->vmcb->control.exit_info_1;
+
+	if (type > 3) {
+		kvm_inject_gp(vcpu, 0);
+		return 1;
+	}
+
+	return kvm_handle_invpcid(vcpu, type, gva);
+}
+
 static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_READ_CR0]			= cr_interception,
 	[SVM_EXIT_READ_CR3]			= cr_interception,
@@ -2795,6 +2909,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_MWAIT]			= mwait_interception,
 	[SVM_EXIT_XSETBV]			= xsetbv_interception,
 	[SVM_EXIT_RDPRU]			= rdpru_interception,
+	[SVM_EXIT_INVPCID]                      = invpcid_interception,
 	[SVM_EXIT_NPF]				= npf_interception,
 	[SVM_EXIT_RSM]                          = rsm_interception,
 	[SVM_EXIT_AVIC_INCOMPLETE_IPI]		= avic_incomplete_ipi_interception,
@@ -2813,12 +2928,14 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 	}
 
 	pr_err("VMCB Control Area:\n");
-	pr_err("%-20s%04x\n", "cr_read:", control->intercept_cr & 0xffff);
-	pr_err("%-20s%04x\n", "cr_write:", control->intercept_cr >> 16);
-	pr_err("%-20s%04x\n", "dr_read:", control->intercept_dr & 0xffff);
-	pr_err("%-20s%04x\n", "dr_write:", control->intercept_dr >> 16);
-	pr_err("%-20s%08x\n", "exceptions:", control->intercept_exceptions);
-	pr_err("%-20s%016llx\n", "intercepts:", control->intercept);
+	pr_err("%-20s%04x\n", "cr_read:", control->intercepts[INTERCEPT_CR] & 0xffff);
+	pr_err("%-20s%04x\n", "cr_write:", control->intercepts[INTERCEPT_CR] >> 16);
+	pr_err("%-20s%04x\n", "dr_read:", control->intercepts[INTERCEPT_DR] & 0xffff);
+	pr_err("%-20s%04x\n", "dr_write:", control->intercepts[INTERCEPT_DR] >> 16);
+	pr_err("%-20s%08x\n", "exceptions:", control->intercepts[INTERCEPT_EXCEPTION]);
+	pr_err("%-20s%08x %08x\n", "intercepts:",
+              control->intercepts[INTERCEPT_WORD3],
+	       control->intercepts[INTERCEPT_WORD4]);
 	pr_err("%-20s%d\n", "pause filter count:", control->pause_filter_count);
 	pr_err("%-20s%d\n", "pause filter threshold:",
 	       control->pause_filter_thresh);
@@ -2917,12 +3034,19 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
 	       "excp_to:", save->last_excp_to);
 }
 
-static void svm_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
+static void svm_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2,
+			      u32 *intr_info, u32 *error_code)
 {
 	struct vmcb_control_area *control = &to_svm(vcpu)->vmcb->control;
 
 	*info1 = control->exit_info_1;
 	*info2 = control->exit_info_2;
+	*intr_info = control->exit_int_info;
+	if ((*intr_info & SVM_EXITINTINFO_VALID) &&
+	    (*intr_info & SVM_EXITINTINFO_VALID_ERR))
+		*error_code = control->exit_int_info_err;
+	else
+		*error_code = 0;
 }
 
 static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
@@ -2933,22 +3057,15 @@ static int handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 
 	trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM);
 
-	if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE))
+	if (!svm_is_intercept(svm, INTERCEPT_CR0_WRITE))
 		vcpu->arch.cr0 = svm->vmcb->save.cr0;
 	if (npt_enabled)
 		vcpu->arch.cr3 = svm->vmcb->save.cr3;
 
-	svm_complete_interrupts(svm);
-
 	if (is_guest_mode(vcpu)) {
 		int vmexit;
 
-		trace_kvm_nested_vmexit(svm->vmcb->save.rip, exit_code,
-					svm->vmcb->control.exit_info_1,
-					svm->vmcb->control.exit_info_2,
-					svm->vmcb->control.exit_int_info,
-					svm->vmcb->control.exit_int_info_err,
-					KVM_ISA_SVM);
+		trace_kvm_nested_vmexit(exit_code, vcpu, KVM_ISA_SVM);
 
 		vmexit = nested_svm_exit_special(svm);
 
@@ -3058,13 +3175,13 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 	if (nested_svm_virtualize_tpr(vcpu))
 		return;
 
-	clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+	svm_clr_intercept(svm, INTERCEPT_CR8_WRITE);
 
 	if (irr == -1)
 		return;
 
 	if (tpr >= irr)
-		set_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+		svm_set_intercept(svm, INTERCEPT_CR8_WRITE);
 }
 
 bool svm_nmi_blocked(struct kvm_vcpu *vcpu)
@@ -3252,7 +3369,7 @@ static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu)
 	if (nested_svm_virtualize_tpr(vcpu))
 		return;
 
-	if (!is_cr_intercept(svm, INTERCEPT_CR8_WRITE)) {
+	if (!svm_is_intercept(svm, INTERCEPT_CR8_WRITE)) {
 		int cr8 = svm->vmcb->control.int_ctl & V_TPR_MASK;
 		kvm_set_cr8(vcpu, cr8);
 	}
@@ -3349,8 +3466,7 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu)
 
 static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
 {
-	if (!is_guest_mode(vcpu) &&
-	    to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR &&
+	if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR &&
 	    to_svm(vcpu)->vmcb->control.exit_info_1)
 		return handle_fastpath_set_msr_irqoff(vcpu);
 
@@ -3415,7 +3531,6 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 
 static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 {
-	fastpath_t exit_fastpath;
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
@@ -3456,9 +3571,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 	clgi();
 	kvm_load_guest_xsave_state(vcpu);
 
-	if (lapic_in_kernel(vcpu) &&
-		vcpu->arch.apic->lapic_timer.timer_advance_ns)
-		kvm_wait_lapic_expire(vcpu);
+	kvm_wait_lapic_expire(vcpu);
 
 	/*
 	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
@@ -3504,7 +3617,6 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 	stgi();
 
 	/* Any pending NMI will happen here */
-	exit_fastpath = svm_exit_handlers_fastpath(vcpu);
 
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_after_interrupt(&svm->vcpu);
@@ -3518,6 +3630,7 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 	}
 
 	svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING;
+	vmcb_mark_all_clean(svm->vmcb);
 
 	/* if exit due to PF check for async PF */
 	if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR)
@@ -3537,8 +3650,12 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 		     SVM_EXIT_EXCP_BASE + MC_VECTOR))
 		svm_handle_mce(svm);
 
-	vmcb_mark_all_clean(svm->vmcb);
-	return exit_fastpath;
+	svm_complete_interrupts(svm);
+
+	if (is_guest_mode(vcpu))
+		return EXIT_FASTPATH_NONE;
+
+	return svm_exit_handlers_fastpath(vcpu);
 }
 
 static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long root,
@@ -3624,6 +3741,9 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	svm->nrips_enabled = kvm_cpu_cap_has(X86_FEATURE_NRIPS) &&
 			     guest_cpuid_has(&svm->vcpu, X86_FEATURE_NRIPS);
 
+	/* Check again if INVPCID interception if required */
+	svm_check_invpcid(svm);
+
 	if (!kvm_vcpu_apicv_active(vcpu))
 		return;
 
@@ -3738,7 +3858,6 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu,
 		break;
 	case SVM_EXIT_WRITE_CR0: {
 		unsigned long cr0, val;
-		u64 intercept;
 
 		if (info->intercept == x86_intercept_cr_write)
 			icpt_info.exit_code += info->modrm_reg;
@@ -3747,9 +3866,8 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu,
 		    info->intercept == x86_intercept_clts)
 			break;
 
-		intercept = svm->nested.ctl.intercept;
-
-		if (!(intercept & (1ULL << INTERCEPT_SELECTIVE_CR0)))
+		if (!(vmcb_is_intercept(&svm->nested.ctl,
+					INTERCEPT_SELECTIVE_CR0)))
 			break;
 
 		cr0 = vcpu->arch.cr0 & ~SVM_CR0_SELECTIVE_MASK;
@@ -3884,7 +4002,7 @@ static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 		/* FED8h - SVM Guest */
 		put_smstate(u64, smstate, 0x7ed8, 1);
 		/* FEE0h - SVM Guest VMCB Physical Address */
-		put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb);
+		put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa);
 
 		svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
 		svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
@@ -3900,21 +4018,28 @@ static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	struct vmcb *nested_vmcb;
 	struct kvm_host_map map;
-	u64 guest;
-	u64 vmcb;
 	int ret = 0;
 
-	guest = GET_SMSTATE(u64, smstate, 0x7ed8);
-	vmcb = GET_SMSTATE(u64, smstate, 0x7ee0);
+	if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
+		u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
+		u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8);
+		u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
 
-	if (guest) {
-		if (kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb), &map) == -EINVAL)
-			return 1;
-		nested_vmcb = map.hva;
-		ret = enter_svm_guest_mode(svm, vmcb, nested_vmcb);
-		kvm_vcpu_unmap(&svm->vcpu, &map, true);
+		if (guest) {
+			if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
+				return 1;
+
+			if (!(saved_efer & EFER_SVME))
+				return 1;
+
+			if (kvm_vcpu_map(&svm->vcpu,
+					 gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
+				return 1;
+
+			ret = enter_svm_guest_mode(svm, vmcb12_gpa, map.hva);
+			kvm_vcpu_unmap(&svm->vcpu, &map, true);
+		}
 	}
 
 	return ret;
@@ -3933,19 +4058,10 @@ static void enable_smi_window(struct kvm_vcpu *vcpu)
 	}
 }
 
-static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu)
+static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, void *insn, int insn_len)
 {
-	unsigned long cr4 = kvm_read_cr4(vcpu);
-	bool smep = cr4 & X86_CR4_SMEP;
-	bool smap = cr4 & X86_CR4_SMAP;
-	bool is_user = svm_get_cpl(vcpu) == 3;
-
-	/*
-	 * 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;
+	bool smep, smap, is_user;
+	unsigned long cr4;
 
 	/*
 	 * Detect and workaround Errata 1096 Fam_17h_00_0Fh.
@@ -3987,6 +4103,20 @@ static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu)
 	 * instruction pointer so we will not able to workaround it. Lets
 	 * print the error and request to kill the guest.
 	 */
+	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;
+
+	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;
@@ -4010,7 +4140,7 @@ static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
 	 * if an INIT signal is pending.
 	 */
 	return !gif_set(svm) ||
-		   (svm->vmcb->control.intercept & (1ULL << INTERCEPT_INIT));
+		   (vmcb_is_intercept(&svm->vmcb->control, INTERCEPT_INIT));
 }
 
 static void svm_vm_destroy(struct kvm *kvm)
@@ -4148,9 +4278,11 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.mem_enc_reg_region = svm_register_enc_region,
 	.mem_enc_unreg_region = svm_unregister_enc_region,
 
-	.need_emulation_on_page_fault = svm_need_emulation_on_page_fault,
+	.can_emulate_instruction = svm_can_emulate_instruction,
 
 	.apic_init_signal_blocked = svm_apic_init_signal_blocked,
+
+	.msr_filter_changed = svm_msr_filter_changed,
 };
 
 static struct kvm_x86_init_ops svm_init_ops __initdata = {
@@ -4164,6 +4296,8 @@ static struct kvm_x86_init_ops svm_init_ops __initdata = {
 
 static int __init svm_init(void)
 {
+	__unused_size_checks();
+
 	return kvm_init(&svm_init_ops, sizeof(struct vcpu_svm),
 			__alignof__(struct vcpu_svm), THIS_MODULE);
 }
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index a798e17..a7f9974 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -31,6 +31,7 @@ static const u32 host_save_user_msrs[] = {
 
 #define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs)
 
+#define MAX_DIRECT_ACCESS_MSRS	15
 #define MSRPM_OFFSETS	16
 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
 extern bool npt_enabled;
@@ -85,8 +86,7 @@ struct svm_nested_state {
 	struct vmcb *hsave;
 	u64 hsave_msr;
 	u64 vm_cr_msr;
-	u64 vmcb;
-	u32 host_intercept_exceptions;
+	u64 vmcb12_gpa;
 
 	/* These are the merged vectors */
 	u32 *msrpm;
@@ -158,6 +158,12 @@ struct vcpu_svm {
 	 */
 	struct list_head ir_list;
 	spinlock_t ir_list_lock;
+
+	/* Save desired MSR intercept (read: pass-through) state */
+	struct {
+		DECLARE_BITMAP(read, MAX_DIRECT_ACCESS_MSRS);
+		DECLARE_BITMAP(write, MAX_DIRECT_ACCESS_MSRS);
+	} shadow_msr_intercept;
 };
 
 struct svm_cpu_data {
@@ -214,51 +220,44 @@ static inline struct vmcb *get_host_vmcb(struct vcpu_svm *svm)
 		return svm->vmcb;
 }
 
-static inline void set_cr_intercept(struct vcpu_svm *svm, int bit)
+static inline void vmcb_set_intercept(struct vmcb_control_area *control, u32 bit)
 {
-	struct vmcb *vmcb = get_host_vmcb(svm);
-
-	vmcb->control.intercept_cr |= (1U << bit);
-
-	recalc_intercepts(svm);
+	WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT);
+	__set_bit(bit, (unsigned long *)&control->intercepts);
 }
 
-static inline void clr_cr_intercept(struct vcpu_svm *svm, int bit)
+static inline void vmcb_clr_intercept(struct vmcb_control_area *control, u32 bit)
 {
-	struct vmcb *vmcb = get_host_vmcb(svm);
-
-	vmcb->control.intercept_cr &= ~(1U << bit);
-
-	recalc_intercepts(svm);
+	WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT);
+	__clear_bit(bit, (unsigned long *)&control->intercepts);
 }
 
-static inline bool is_cr_intercept(struct vcpu_svm *svm, int bit)
+static inline bool vmcb_is_intercept(struct vmcb_control_area *control, u32 bit)
 {
-	struct vmcb *vmcb = get_host_vmcb(svm);
-
-	return vmcb->control.intercept_cr & (1U << bit);
+	WARN_ON_ONCE(bit >= 32 * MAX_INTERCEPT);
+	return test_bit(bit, (unsigned long *)&control->intercepts);
 }
 
 static inline void set_dr_intercepts(struct vcpu_svm *svm)
 {
 	struct vmcb *vmcb = get_host_vmcb(svm);
 
-	vmcb->control.intercept_dr = (1 << INTERCEPT_DR0_READ)
-		| (1 << INTERCEPT_DR1_READ)
-		| (1 << INTERCEPT_DR2_READ)
-		| (1 << INTERCEPT_DR3_READ)
-		| (1 << INTERCEPT_DR4_READ)
-		| (1 << INTERCEPT_DR5_READ)
-		| (1 << INTERCEPT_DR6_READ)
-		| (1 << INTERCEPT_DR7_READ)
-		| (1 << INTERCEPT_DR0_WRITE)
-		| (1 << INTERCEPT_DR1_WRITE)
-		| (1 << INTERCEPT_DR2_WRITE)
-		| (1 << INTERCEPT_DR3_WRITE)
-		| (1 << INTERCEPT_DR4_WRITE)
-		| (1 << INTERCEPT_DR5_WRITE)
-		| (1 << INTERCEPT_DR6_WRITE)
-		| (1 << INTERCEPT_DR7_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR0_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR1_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR2_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR3_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR4_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR5_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR6_WRITE);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
 
 	recalc_intercepts(svm);
 }
@@ -267,25 +266,27 @@ static inline void clr_dr_intercepts(struct vcpu_svm *svm)
 {
 	struct vmcb *vmcb = get_host_vmcb(svm);
 
-	vmcb->control.intercept_dr = 0;
+	vmcb->control.intercepts[INTERCEPT_DR] = 0;
 
 	recalc_intercepts(svm);
 }
 
-static inline void set_exception_intercept(struct vcpu_svm *svm, int bit)
+static inline void set_exception_intercept(struct vcpu_svm *svm, u32 bit)
 {
 	struct vmcb *vmcb = get_host_vmcb(svm);
 
-	vmcb->control.intercept_exceptions |= (1U << bit);
+	WARN_ON_ONCE(bit >= 32);
+	vmcb_set_intercept(&vmcb->control, INTERCEPT_EXCEPTION_OFFSET + bit);
 
 	recalc_intercepts(svm);
 }
 
-static inline void clr_exception_intercept(struct vcpu_svm *svm, int bit)
+static inline void clr_exception_intercept(struct vcpu_svm *svm, u32 bit)
 {
 	struct vmcb *vmcb = get_host_vmcb(svm);
 
-	vmcb->control.intercept_exceptions &= ~(1U << bit);
+	WARN_ON_ONCE(bit >= 32);
+	vmcb_clr_intercept(&vmcb->control, INTERCEPT_EXCEPTION_OFFSET + bit);
 
 	recalc_intercepts(svm);
 }
@@ -294,7 +295,7 @@ static inline void svm_set_intercept(struct vcpu_svm *svm, int bit)
 {
 	struct vmcb *vmcb = get_host_vmcb(svm);
 
-	vmcb->control.intercept |= (1ULL << bit);
+	vmcb_set_intercept(&vmcb->control, bit);
 
 	recalc_intercepts(svm);
 }
@@ -303,14 +304,14 @@ static inline void svm_clr_intercept(struct vcpu_svm *svm, int bit)
 {
 	struct vmcb *vmcb = get_host_vmcb(svm);
 
-	vmcb->control.intercept &= ~(1ULL << bit);
+	vmcb_clr_intercept(&vmcb->control, bit);
 
 	recalc_intercepts(svm);
 }
 
 static inline bool svm_is_intercept(struct vcpu_svm *svm, int bit)
 {
-	return (svm->vmcb->control.intercept & (1ULL << bit)) != 0;
+	return vmcb_is_intercept(&svm->vmcb->control, bit);
 }
 
 static inline bool vgif_enabled(struct vcpu_svm *svm)
@@ -345,7 +346,7 @@ static inline bool gif_set(struct vcpu_svm *svm)
 /* svm.c */
 #define MSR_CR3_LEGACY_RESERVED_MASK		0xfe7U
 #define MSR_CR3_LEGACY_PAE_RESERVED_MASK	0x7U
-#define MSR_CR3_LONG_RESERVED_MASK		0xfff0000000000fe7U
+#define MSR_CR3_LONG_MBZ_MASK			0xfff0000000000000U
 #define MSR_INVALID				0xffffffffU
 
 u32 svm_msrpm_offset(u32 msr);
@@ -374,17 +375,17 @@ static inline bool nested_svm_virtualize_tpr(struct kvm_vcpu *vcpu)
 
 static inline bool nested_exit_on_smi(struct vcpu_svm *svm)
 {
-	return (svm->nested.ctl.intercept & (1ULL << INTERCEPT_SMI));
+	return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_SMI);
 }
 
 static inline bool nested_exit_on_intr(struct vcpu_svm *svm)
 {
-	return (svm->nested.ctl.intercept & (1ULL << INTERCEPT_INTR));
+	return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_INTR);
 }
 
 static inline bool nested_exit_on_nmi(struct vcpu_svm *svm)
 {
-	return (svm->nested.ctl.intercept & (1ULL << INTERCEPT_NMI));
+	return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_NMI);
 }
 
 int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index b66432b..aef960f 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -15,18 +15,20 @@
  * Tracepoint for guest mode entry.
  */
 TRACE_EVENT(kvm_entry,
-	TP_PROTO(unsigned int vcpu_id),
-	TP_ARGS(vcpu_id),
+	TP_PROTO(struct kvm_vcpu *vcpu),
+	TP_ARGS(vcpu),
 
 	TP_STRUCT__entry(
 		__field(	unsigned int,	vcpu_id		)
+		__field(	unsigned long,	rip		)
 	),
 
 	TP_fast_assign(
-		__entry->vcpu_id	= vcpu_id;
+		__entry->vcpu_id        = vcpu->vcpu_id;
+		__entry->rip		= kvm_rip_read(vcpu);
 	),
 
-	TP_printk("vcpu %u", __entry->vcpu_id)
+	TP_printk("vcpu %u, rip 0x%lx", __entry->vcpu_id, __entry->rip)
 );
 
 /*
@@ -233,36 +235,45 @@ TRACE_EVENT(kvm_apic,
 	(isa == KVM_ISA_VMX) ?						\
 	__print_flags(exit_reason & ~0xffff, " ", VMX_EXIT_REASON_FLAGS) : ""
 
+#define TRACE_EVENT_KVM_EXIT(name)					     \
+TRACE_EVENT(name,							     \
+	TP_PROTO(unsigned int exit_reason, struct kvm_vcpu *vcpu, u32 isa),  \
+	TP_ARGS(exit_reason, vcpu, isa),				     \
+									     \
+	TP_STRUCT__entry(						     \
+		__field(	unsigned int,	exit_reason	)	     \
+		__field(	unsigned long,	guest_rip	)	     \
+		__field(	u32,	        isa             )	     \
+		__field(	u64,	        info1           )	     \
+		__field(	u64,	        info2           )	     \
+		__field(	u32,	        intr_info	)	     \
+		__field(	u32,	        error_code	)	     \
+		__field(	unsigned int,	vcpu_id         )	     \
+	),								     \
+									     \
+	TP_fast_assign(							     \
+		__entry->exit_reason	= exit_reason;			     \
+		__entry->guest_rip	= kvm_rip_read(vcpu);		     \
+		__entry->isa            = isa;				     \
+		__entry->vcpu_id        = vcpu->vcpu_id;		     \
+		kvm_x86_ops.get_exit_info(vcpu, &__entry->info1,	     \
+					  &__entry->info2,		     \
+					  &__entry->intr_info,		     \
+					  &__entry->error_code);	     \
+	),								     \
+									     \
+	TP_printk("vcpu %u reason %s%s%s rip 0x%lx info1 0x%016llx "	     \
+		  "info2 0x%016llx intr_info 0x%08x error_code 0x%08x",	     \
+		  __entry->vcpu_id,					     \
+		  kvm_print_exit_reason(__entry->exit_reason, __entry->isa), \
+		  __entry->guest_rip, __entry->info1, __entry->info2,	     \
+		  __entry->intr_info, __entry->error_code)		     \
+)
+
 /*
  * Tracepoint for kvm guest exit:
  */
-TRACE_EVENT(kvm_exit,
-	TP_PROTO(unsigned int exit_reason, struct kvm_vcpu *vcpu, u32 isa),
-	TP_ARGS(exit_reason, vcpu, isa),
-
-	TP_STRUCT__entry(
-		__field(	unsigned int,	exit_reason	)
-		__field(	unsigned long,	guest_rip	)
-		__field(	u32,	        isa             )
-		__field(	u64,	        info1           )
-		__field(	u64,	        info2           )
-		__field(	unsigned int,	vcpu_id         )
-	),
-
-	TP_fast_assign(
-		__entry->exit_reason	= exit_reason;
-		__entry->guest_rip	= kvm_rip_read(vcpu);
-		__entry->isa            = isa;
-		__entry->vcpu_id        = vcpu->vcpu_id;
-		kvm_x86_ops.get_exit_info(vcpu, &__entry->info1,
-					   &__entry->info2);
-	),
-
-	TP_printk("vcpu %u reason %s%s%s rip 0x%lx info %llx %llx",
-		  __entry->vcpu_id,
-		  kvm_print_exit_reason(__entry->exit_reason, __entry->isa),
-		  __entry->guest_rip, __entry->info1, __entry->info2)
-);
+TRACE_EVENT_KVM_EXIT(kvm_exit);
 
 /*
  * Tracepoint for kvm interrupt injection:
@@ -544,63 +555,38 @@ TRACE_EVENT(kvm_nested_vmrun,
 );
 
 TRACE_EVENT(kvm_nested_intercepts,
-	    TP_PROTO(__u16 cr_read, __u16 cr_write, __u32 exceptions, __u64 intercept),
-	    TP_ARGS(cr_read, cr_write, exceptions, intercept),
+	    TP_PROTO(__u16 cr_read, __u16 cr_write, __u32 exceptions,
+		     __u32 intercept1, __u32 intercept2, __u32 intercept3),
+	    TP_ARGS(cr_read, cr_write, exceptions, intercept1,
+		    intercept2, intercept3),
 
 	TP_STRUCT__entry(
 		__field(	__u16,		cr_read		)
 		__field(	__u16,		cr_write	)
 		__field(	__u32,		exceptions	)
-		__field(	__u64,		intercept	)
+		__field(	__u32,		intercept1	)
+		__field(	__u32,		intercept2	)
+		__field(	__u32,		intercept3	)
 	),
 
 	TP_fast_assign(
 		__entry->cr_read	= cr_read;
 		__entry->cr_write	= cr_write;
 		__entry->exceptions	= exceptions;
-		__entry->intercept	= intercept;
+		__entry->intercept1	= intercept1;
+		__entry->intercept2	= intercept2;
+		__entry->intercept3	= intercept3;
 	),
 
-	TP_printk("cr_read: %04x cr_write: %04x excp: %08x intercept: %016llx",
-		__entry->cr_read, __entry->cr_write, __entry->exceptions,
-		__entry->intercept)
+	TP_printk("cr_read: %04x cr_write: %04x excp: %08x "
+		  "intercepts: %08x %08x %08x",
+		  __entry->cr_read, __entry->cr_write, __entry->exceptions,
+		  __entry->intercept1, __entry->intercept2, __entry->intercept3)
 );
 /*
  * Tracepoint for #VMEXIT while nested
  */
-TRACE_EVENT(kvm_nested_vmexit,
-	    TP_PROTO(__u64 rip, __u32 exit_code,
-		     __u64 exit_info1, __u64 exit_info2,
-		     __u32 exit_int_info, __u32 exit_int_info_err, __u32 isa),
-	    TP_ARGS(rip, exit_code, exit_info1, exit_info2,
-		    exit_int_info, exit_int_info_err, isa),
-
-	TP_STRUCT__entry(
-		__field(	__u64,		rip			)
-		__field(	__u32,		exit_code		)
-		__field(	__u64,		exit_info1		)
-		__field(	__u64,		exit_info2		)
-		__field(	__u32,		exit_int_info		)
-		__field(	__u32,		exit_int_info_err	)
-		__field(	__u32,		isa			)
-	),
-
-	TP_fast_assign(
-		__entry->rip			= rip;
-		__entry->exit_code		= exit_code;
-		__entry->exit_info1		= exit_info1;
-		__entry->exit_info2		= exit_info2;
-		__entry->exit_int_info		= exit_int_info;
-		__entry->exit_int_info_err	= exit_int_info_err;
-		__entry->isa			= isa;
-	),
-	TP_printk("rip: 0x%016llx reason: %s%s%s ext_inf1: 0x%016llx "
-		  "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x",
-		  __entry->rip,
-		  kvm_print_exit_reason(__entry->exit_code, __entry->isa),
-		  __entry->exit_info1, __entry->exit_info2,
-		  __entry->exit_int_info, __entry->exit_int_info_err)
-);
+TRACE_EVENT_KVM_EXIT(kvm_nested_vmexit);
 
 /*
  * Tracepoint for #VMEXIT reinjected to the guest
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 4bbd8b4..3a18614 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -151,7 +151,7 @@ static inline bool vmx_umip_emulated(void)
 static inline bool cpu_has_vmx_rdtscp(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
-		SECONDARY_EXEC_RDTSCP;
+		SECONDARY_EXEC_ENABLE_RDTSCP;
 }
 
 static inline bool cpu_has_vmx_virtualize_x2apic_mode(void)
@@ -196,7 +196,7 @@ static inline bool cpu_has_vmx_ple(void)
 		SECONDARY_EXEC_PAUSE_LOOP_EXITING;
 }
 
-static inline bool vmx_rdrand_supported(void)
+static inline bool cpu_has_vmx_rdrand(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
 		SECONDARY_EXEC_RDRAND_EXITING;
@@ -233,7 +233,7 @@ static inline bool cpu_has_vmx_encls_vmexit(void)
 		SECONDARY_EXEC_ENCLS_EXITING;
 }
 
-static inline bool vmx_rdseed_supported(void)
+static inline bool cpu_has_vmx_rdseed(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
 		SECONDARY_EXEC_RDSEED_EXITING;
@@ -244,13 +244,13 @@ static inline bool cpu_has_vmx_pml(void)
 	return vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_ENABLE_PML;
 }
 
-static inline bool vmx_xsaves_supported(void)
+static inline bool cpu_has_vmx_xsaves(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
 		SECONDARY_EXEC_XSAVES;
 }
 
-static inline bool vmx_waitpkg_supported(void)
+static inline bool cpu_has_vmx_waitpkg(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
 		SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 23b58c2..6eca8a7 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -233,6 +233,44 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
 	vmx->nested.hv_evmcs = NULL;
 }
 
+static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
+				     struct loaded_vmcs *prev)
+{
+	struct vmcs_host_state *dest, *src;
+
+	if (unlikely(!vmx->guest_state_loaded))
+		return;
+
+	src = &prev->host_state;
+	dest = &vmx->loaded_vmcs->host_state;
+
+	vmx_set_host_fs_gs(dest, src->fs_sel, src->gs_sel, src->fs_base, src->gs_base);
+	dest->ldt_sel = src->ldt_sel;
+#ifdef CONFIG_X86_64
+	dest->ds_sel = src->ds_sel;
+	dest->es_sel = src->es_sel;
+#endif
+}
+
+static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct loaded_vmcs *prev;
+	int cpu;
+
+	if (WARN_ON_ONCE(vmx->loaded_vmcs == vmcs))
+		return;
+
+	cpu = get_cpu();
+	prev = vmx->loaded_vmcs;
+	vmx->loaded_vmcs = vmcs;
+	vmx_vcpu_load_vmcs(vcpu, cpu, prev);
+	vmx_sync_vmcs_host_state(vmx, prev);
+	put_cpu();
+
+	vmx_register_cache_reset(vcpu);
+}
+
 /*
  * Free whatever needs to be freed from vmx->nested when L1 goes down, or
  * just stops using VMX.
@@ -241,10 +279,13 @@ static void free_nested(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	if (WARN_ON_ONCE(vmx->loaded_vmcs != &vmx->vmcs01))
+		vmx_switch_vmcs(vcpu, &vmx->vmcs01);
+
 	if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
 		return;
 
-	kvm_clear_request(KVM_REQ_GET_VMCS12_PAGES, vcpu);
+	kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
 
 	vmx->nested.vmxon = false;
 	vmx->nested.smm.vmxon = false;
@@ -277,44 +318,6 @@ static void free_nested(struct kvm_vcpu *vcpu)
 	free_loaded_vmcs(&vmx->nested.vmcs02);
 }
 
-static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
-				     struct loaded_vmcs *prev)
-{
-	struct vmcs_host_state *dest, *src;
-
-	if (unlikely(!vmx->guest_state_loaded))
-		return;
-
-	src = &prev->host_state;
-	dest = &vmx->loaded_vmcs->host_state;
-
-	vmx_set_host_fs_gs(dest, src->fs_sel, src->gs_sel, src->fs_base, src->gs_base);
-	dest->ldt_sel = src->ldt_sel;
-#ifdef CONFIG_X86_64
-	dest->ds_sel = src->ds_sel;
-	dest->es_sel = src->es_sel;
-#endif
-}
-
-static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct loaded_vmcs *prev;
-	int cpu;
-
-	if (vmx->loaded_vmcs == vmcs)
-		return;
-
-	cpu = get_cpu();
-	prev = vmx->loaded_vmcs;
-	vmx->loaded_vmcs = vmcs;
-	vmx_vcpu_load_vmcs(vcpu, cpu, prev);
-	vmx_sync_vmcs_host_state(vmx, prev);
-	put_cpu();
-
-	vmx_register_cache_reset(vcpu);
-}
-
 /*
  * Ensure that the current vmcs of the logical processor is the
  * vmcs01 of the vcpu before calling free_nested().
@@ -323,8 +326,6 @@ void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu)
 {
 	vcpu_load(vcpu);
 	vmx_leave_nested(vcpu);
-	vmx_switch_vmcs(vcpu, &to_vmx(vcpu)->vmcs01);
-	free_nested(vcpu);
 	vcpu_put(vcpu);
 }
 
@@ -938,11 +939,11 @@ static bool nested_vmx_get_vmexit_msr_value(struct kvm_vcpu *vcpu,
 	 * VM-exit in L0, use the more accurate value.
 	 */
 	if (msr_index == MSR_IA32_TSC) {
-		int index = vmx_find_msr_index(&vmx->msr_autostore.guest,
-					       MSR_IA32_TSC);
+		int i = vmx_find_loadstore_msr_slot(&vmx->msr_autostore.guest,
+						    MSR_IA32_TSC);
 
-		if (index >= 0) {
-			u64 val = vmx->msr_autostore.guest.val[index].value;
+		if (i >= 0) {
+			u64 val = vmx->msr_autostore.guest.val[i].value;
 
 			*data = kvm_read_l1_tsc(vcpu, val);
 			return true;
@@ -1031,16 +1032,16 @@ static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu,
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmx_msrs *autostore = &vmx->msr_autostore.guest;
 	bool in_vmcs12_store_list;
-	int msr_autostore_index;
+	int msr_autostore_slot;
 	bool in_autostore_list;
 	int last;
 
-	msr_autostore_index = vmx_find_msr_index(autostore, msr_index);
-	in_autostore_list = msr_autostore_index >= 0;
+	msr_autostore_slot = vmx_find_loadstore_msr_slot(autostore, msr_index);
+	in_autostore_list = msr_autostore_slot >= 0;
 	in_vmcs12_store_list = nested_msr_store_list_has_msr(vcpu, msr_index);
 
 	if (in_vmcs12_store_list && !in_autostore_list) {
-		if (autostore->nr == NR_LOADSTORE_MSRS) {
+		if (autostore->nr == MAX_NR_LOADSTORE_MSRS) {
 			/*
 			 * Emulated VMEntry does not fail here.  Instead a less
 			 * accurate value will be returned by
@@ -1057,7 +1058,7 @@ static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu,
 		autostore->val[last].index = msr_index;
 	} else if (!in_vmcs12_store_list && in_autostore_list) {
 		last = --autostore->nr;
-		autostore->val[msr_autostore_index] = autostore->val[last];
+		autostore->val[msr_autostore_slot] = autostore->val[last];
 	}
 }
 
@@ -2286,7 +2287,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 		/* Take the following fields only from vmcs12 */
 		exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
 				  SECONDARY_EXEC_ENABLE_INVPCID |
-				  SECONDARY_EXEC_RDTSCP |
+				  SECONDARY_EXEC_ENABLE_RDTSCP |
 				  SECONDARY_EXEC_XSAVES |
 				  SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |
 				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
@@ -2314,6 +2315,9 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 			vmcs_write16(GUEST_INTR_STATUS,
 				vmcs12->guest_intr_status);
 
+		if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST))
+		    exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
+
 		secondary_exec_controls_set(vmx, exec_control);
 	}
 
@@ -2408,6 +2412,8 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 		vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base);
 		vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
 		vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
+
+		vmx->segment_cache.bitmask = 0;
 	}
 
 	if (!hv_evmcs || !(hv_evmcs->hv_clean_fields &
@@ -2571,7 +2577,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	 * which means L1 attempted VMEntry to L2 with invalid state.
 	 * Fail the VMEntry.
 	 */
-	if (vmx->emulation_required) {
+	if (CC(!vmx_guest_state_valid(vcpu))) {
 		*entry_failure_code = ENTRY_FAIL_DEFAULT;
 		return -EINVAL;
 	}
@@ -3344,8 +3350,10 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 	prepare_vmcs02_early(vmx, vmcs12);
 
 	if (from_vmentry) {
-		if (unlikely(!nested_get_vmcs12_pages(vcpu)))
+		if (unlikely(!nested_get_vmcs12_pages(vcpu))) {
+			vmx_switch_vmcs(vcpu, &vmx->vmcs01);
 			return NVMX_VMENTRY_KVM_INTERNAL_ERROR;
+		}
 
 		if (nested_vmx_check_vmentry_hw(vcpu)) {
 			vmx_switch_vmcs(vcpu, &vmx->vmcs01);
@@ -3387,7 +3395,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 		 * to nested_get_vmcs12_pages before the next VM-entry.  The MSRs
 		 * have already been set at vmentry time and should not be reset.
 		 */
-		kvm_make_request(KVM_REQ_GET_VMCS12_PAGES, vcpu);
+		kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
 	}
 
 	/*
@@ -3468,11 +3476,11 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	if (evmptrld_status == EVMPTRLD_ERROR) {
 		kvm_queue_exception(vcpu, UD_VECTOR);
 		return 1;
-	} else if (evmptrld_status == EVMPTRLD_VMFAIL) {
+	} else if (CC(evmptrld_status == EVMPTRLD_VMFAIL)) {
 		return nested_vmx_failInvalid(vcpu);
 	}
 
-	if (!vmx->nested.hv_evmcs && vmx->nested.current_vmptr == -1ull)
+	if (CC(!vmx->nested.hv_evmcs && vmx->nested.current_vmptr == -1ull))
 		return nested_vmx_failInvalid(vcpu);
 
 	vmcs12 = get_vmcs12(vcpu);
@@ -3483,7 +3491,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	 * rather than RFLAGS.ZF, and no error number is stored to the
 	 * VM-instruction error field.
 	 */
-	if (vmcs12->hdr.shadow_vmcs)
+	if (CC(vmcs12->hdr.shadow_vmcs))
 		return nested_vmx_failInvalid(vcpu);
 
 	if (vmx->nested.hv_evmcs) {
@@ -3504,10 +3512,10 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	 * for misconfigurations which will anyway be caught by the processor
 	 * when using the merged vmcs02.
 	 */
-	if (interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS)
+	if (CC(interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS))
 		return nested_vmx_fail(vcpu, VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS);
 
-	if (vmcs12->launch_state == launch)
+	if (CC(vmcs12->launch_state == launch))
 		return nested_vmx_fail(vcpu,
 			launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS
 			       : VMXERR_VMRESUME_NONLAUNCHED_VMCS);
@@ -3528,6 +3536,14 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	if (unlikely(status != NVMX_VMENTRY_SUCCESS))
 		goto vmentry_failed;
 
+	/* Emulate processing of posted interrupts on VM-Enter. */
+	if (nested_cpu_has_posted_intr(vmcs12) &&
+	    kvm_apic_has_interrupt(vcpu) == vmx->nested.posted_intr_nv) {
+		vmx->nested.pi_pending = true;
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+		kvm_apic_clear_irr(vcpu, vmx->nested.posted_intr_nv);
+	}
+
 	/* Hide L1D cache contents from the nested guest.  */
 	vmx->vcpu.arch.l1tf_flush_l1d = true;
 
@@ -4257,7 +4273,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 
 static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx)
 {
-	struct shared_msr_entry *efer_msr;
+	struct vmx_uret_msr *efer_msr;
 	unsigned int i;
 
 	if (vm_entry_controls_get(vmx) & VM_ENTRY_LOAD_IA32_EFER)
@@ -4271,7 +4287,7 @@ static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx)
 			return vmx->msr_autoload.guest.val[i].value;
 	}
 
-	efer_msr = find_msr_entry(vmx, MSR_EFER);
+	efer_msr = vmx_find_uret_msr(vmx, MSR_EFER);
 	if (efer_msr)
 		return efer_msr->data;
 
@@ -4404,6 +4420,14 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 	if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
 		kvm_vcpu_flush_tlb_current(vcpu);
 
+	/*
+	 * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between
+	 * now and the new vmentry.  Ensure that the VMCS02 PDPTR fields are
+	 * up-to-date before switching to L1.
+	 */
+	if (enable_ept && is_pae_paging(vcpu))
+		vmx_ept_load_pdptrs(vcpu);
+
 	leave_guest_mode(vcpu);
 
 	if (nested_cpu_has_preemption_timer(vmcs12))
@@ -4668,7 +4692,7 @@ void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
 		vmx->nested.msrs.entry_ctls_high &=
 				~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
 		vmx->nested.msrs.exit_ctls_high &=
-				~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+				~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
 	}
 }
 
@@ -4688,7 +4712,7 @@ static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer,
 
 	r = kvm_read_guest_virt(vcpu, gva, vmpointer, sizeof(*vmpointer), &e);
 	if (r != X86EMUL_CONTINUE) {
-		*ret = vmx_handle_memory_failure(vcpu, r, &e);
+		*ret = kvm_handle_memory_failure(vcpu, r, &e);
 		return -EINVAL;
 	}
 
@@ -4752,7 +4776,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
 
 	if (vmx_pt_mode_is_host_guest()) {
 		vmx->pt_desc.guest.ctl = 0;
-		pt_update_intercept_for_msr(vmx);
+		pt_update_intercept_for_msr(vcpu);
 	}
 
 	return 0;
@@ -4995,7 +5019,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 		/* _system ok, nested_vmx_check_permission has verified cpl=0 */
 		r = kvm_write_guest_virt_system(vcpu, gva, &value, len, &e);
 		if (r != X86EMUL_CONTINUE)
-			return vmx_handle_memory_failure(vcpu, r, &e);
+			return kvm_handle_memory_failure(vcpu, r, &e);
 	}
 
 	return nested_vmx_succeed(vcpu);
@@ -5068,7 +5092,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
 			return 1;
 		r = kvm_read_guest_virt(vcpu, gva, &value, len, &e);
 		if (r != X86EMUL_CONTINUE)
-			return vmx_handle_memory_failure(vcpu, r, &e);
+			return kvm_handle_memory_failure(vcpu, r, &e);
 	}
 
 	field = kvm_register_readl(vcpu, (((instr_info) >> 28) & 0xf));
@@ -5230,7 +5254,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
 	r = kvm_write_guest_virt_system(vcpu, gva, (void *)&current_vmptr,
 					sizeof(gpa_t), &e);
 	if (r != X86EMUL_CONTINUE)
-		return vmx_handle_memory_failure(vcpu, r, &e);
+		return kvm_handle_memory_failure(vcpu, r, &e);
 
 	return nested_vmx_succeed(vcpu);
 }
@@ -5283,7 +5307,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 		return 1;
 	r = kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e);
 	if (r != X86EMUL_CONTINUE)
-		return vmx_handle_memory_failure(vcpu, r, &e);
+		return kvm_handle_memory_failure(vcpu, r, &e);
 
 	/*
 	 * Nested EPT roots are always held through guest_mmu,
@@ -5365,7 +5389,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 		return 1;
 	r = kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e);
 	if (r != X86EMUL_CONTINUE)
-		return vmx_handle_memory_failure(vcpu, r, &e);
+		return kvm_handle_memory_failure(vcpu, r, &e);
 
 	if (operand.vpid >> 16)
 		return nested_vmx_fail(vcpu,
@@ -5910,13 +5934,7 @@ bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu)
 		goto reflect_vmexit;
 	}
 
-	exit_intr_info = vmx_get_intr_info(vcpu);
-	exit_qual = vmx_get_exit_qual(vcpu);
-
-	trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason, exit_qual,
-				vmx->idt_vectoring_info, exit_intr_info,
-				vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
-				KVM_ISA_VMX);
+	trace_kvm_nested_vmexit(exit_reason, vcpu, KVM_ISA_VMX);
 
 	/* If L0 (KVM) wants the exit, it trumps L1's desires. */
 	if (nested_vmx_l0_wants_exit(vcpu, exit_reason))
@@ -5932,14 +5950,14 @@ bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu)
 	 * need to be synthesized by querying the in-kernel LAPIC, but external
 	 * interrupts are never reflected to L1 so it's a non-issue.
 	 */
-	if ((exit_intr_info &
-	     (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) ==
-	    (INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK)) {
+	exit_intr_info = vmx_get_intr_info(vcpu);
+	if (is_exception_with_error_code(exit_intr_info)) {
 		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 
 		vmcs12->vm_exit_intr_error_code =
 			vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
 	}
+	exit_qual = vmx_get_exit_qual(vcpu);
 
 reflect_vmexit:
 	nested_vmx_vmexit(vcpu, exit_reason, exit_intr_info, exit_qual);
@@ -6174,7 +6192,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 		 * restored yet. EVMCS will be mapped from
 		 * nested_get_vmcs12_pages().
 		 */
-		kvm_make_request(KVM_REQ_GET_VMCS12_PAGES, vcpu);
+		kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
 	} else {
 		return -EINVAL;
 	}
@@ -6310,7 +6328,8 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 #ifdef CONFIG_X86_64
 		VM_EXIT_HOST_ADDR_SPACE_SIZE |
 #endif
-		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT;
+		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT |
+		VM_EXIT_CLEAR_BNDCFGS | VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
 	msrs->exit_ctls_high |=
 		VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
 		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
@@ -6329,7 +6348,8 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 #ifdef CONFIG_X86_64
 		VM_ENTRY_IA32E_MODE |
 #endif
-		VM_ENTRY_LOAD_IA32_PAT;
+		VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS |
+		VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
 	msrs->entry_ctls_high |=
 		(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);
 
@@ -6383,7 +6403,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 	msrs->secondary_ctls_low = 0;
 	msrs->secondary_ctls_high &=
 		SECONDARY_EXEC_DESC |
-		SECONDARY_EXEC_RDTSCP |
+		SECONDARY_EXEC_ENABLE_RDTSCP |
 		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
 		SECONDARY_EXEC_WBINVD_EXITING |
 		SECONDARY_EXEC_APIC_REGISTER_VIRT |
@@ -6553,7 +6573,7 @@ struct kvm_x86_nested_ops vmx_nested_ops = {
 	.hv_timer_pending = nested_vmx_preemption_timer_pending,
 	.get_state = vmx_get_nested_state,
 	.set_state = vmx_set_nested_state,
-	.get_vmcs12_pages = nested_get_vmcs12_pages,
+	.get_nested_state_pages = nested_get_vmcs12_pages,
 	.write_log_dirty = nested_vmx_write_pml_buffer,
 	.enable_evmcs = nested_enable_evmcs,
 	.get_evmcs_version = nested_get_evmcs_version,
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
new file mode 100644
index 0000000..e4e7adf
--- /dev/null
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -0,0 +1,332 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/kvm_host.h>
+
+#include <asm/irq_remapping.h>
+#include <asm/cpu.h>
+
+#include "lapic.h"
+#include "posted_intr.h"
+#include "trace.h"
+#include "vmx.h"
+
+/*
+ * We maintian a per-CPU linked-list of vCPU, so in wakeup_handler() we
+ * can find which vCPU should be waken up.
+ */
+static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu);
+static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock);
+
+static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
+{
+	return &(to_vmx(vcpu)->pi_desc);
+}
+
+void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+	struct pi_desc old, new;
+	unsigned int dest;
+
+	/*
+	 * In case of hot-plug or hot-unplug, we may have to undo
+	 * vmx_vcpu_pi_put even if there is no assigned device.  And we
+	 * always keep PI.NDST up to date for simplicity: it makes the
+	 * code easier, and CPU migration is not a fast path.
+	 */
+	if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
+		return;
+
+	/*
+	 * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
+	 * PI.NDST: pi_post_block is the one expected to change PID.NDST and the
+	 * wakeup handler expects the vCPU to be on the blocked_vcpu_list that
+	 * matches PI.NDST. Otherwise, a vcpu may not be able to be woken up
+	 * correctly.
+	 */
+	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || vcpu->cpu == cpu) {
+		pi_clear_sn(pi_desc);
+		goto after_clear_sn;
+	}
+
+	/* The full case.  */
+	do {
+		old.control = new.control = pi_desc->control;
+
+		dest = cpu_physical_id(cpu);
+
+		if (x2apic_enabled())
+			new.ndst = dest;
+		else
+			new.ndst = (dest << 8) & 0xFF00;
+
+		new.sn = 0;
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
+
+after_clear_sn:
+
+	/*
+	 * Clear SN before reading the bitmap.  The VT-d firmware
+	 * writes the bitmap and reads SN atomically (5.2.3 in the
+	 * spec), so it doesn't really have a memory barrier that
+	 * pairs with this, but we cannot do that and we need one.
+	 */
+	smp_mb__after_atomic();
+
+	if (!pi_is_pir_empty(pi_desc))
+		pi_set_on(pi_desc);
+}
+
+void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
+{
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+
+	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
+		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
+		!kvm_vcpu_apicv_active(vcpu))
+		return;
+
+	/* Set SN when the vCPU is preempted */
+	if (vcpu->preempted)
+		pi_set_sn(pi_desc);
+}
+
+static void __pi_post_block(struct kvm_vcpu *vcpu)
+{
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+	struct pi_desc old, new;
+	unsigned int dest;
+
+	do {
+		old.control = new.control = pi_desc->control;
+		WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR,
+		     "Wakeup handler not enabled while the VCPU is blocked\n");
+
+		dest = cpu_physical_id(vcpu->cpu);
+
+		if (x2apic_enabled())
+			new.ndst = dest;
+		else
+			new.ndst = (dest << 8) & 0xFF00;
+
+		/* set 'NV' to 'notification vector' */
+		new.nv = POSTED_INTR_VECTOR;
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
+
+	if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) {
+		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+		list_del(&vcpu->blocked_vcpu_list);
+		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+		vcpu->pre_pcpu = -1;
+	}
+}
+
+/*
+ * This routine does the following things for vCPU which is going
+ * to be blocked if VT-d PI is enabled.
+ * - Store the vCPU to the wakeup list, so when interrupts happen
+ *   we can find the right vCPU to wake up.
+ * - Change the Posted-interrupt descriptor as below:
+ *      'NDST' <-- vcpu->pre_pcpu
+ *      'NV' <-- POSTED_INTR_WAKEUP_VECTOR
+ * - If 'ON' is set during this process, which means at least one
+ *   interrupt is posted for this vCPU, we cannot block it, in
+ *   this case, return 1, otherwise, return 0.
+ *
+ */
+int pi_pre_block(struct kvm_vcpu *vcpu)
+{
+	unsigned int dest;
+	struct pi_desc old, new;
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+
+	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
+		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
+		!kvm_vcpu_apicv_active(vcpu))
+		return 0;
+
+	WARN_ON(irqs_disabled());
+	local_irq_disable();
+	if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) {
+		vcpu->pre_pcpu = vcpu->cpu;
+		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+		list_add_tail(&vcpu->blocked_vcpu_list,
+			      &per_cpu(blocked_vcpu_on_cpu,
+				       vcpu->pre_pcpu));
+		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+	}
+
+	do {
+		old.control = new.control = pi_desc->control;
+
+		WARN((pi_desc->sn == 1),
+		     "Warning: SN field of posted-interrupts "
+		     "is set before blocking\n");
+
+		/*
+		 * Since vCPU can be preempted during this process,
+		 * vcpu->cpu could be different with pre_pcpu, we
+		 * need to set pre_pcpu as the destination of wakeup
+		 * notification event, then we can find the right vCPU
+		 * to wakeup in wakeup handler if interrupts happen
+		 * when the vCPU is in blocked state.
+		 */
+		dest = cpu_physical_id(vcpu->pre_pcpu);
+
+		if (x2apic_enabled())
+			new.ndst = dest;
+		else
+			new.ndst = (dest << 8) & 0xFF00;
+
+		/* set 'NV' to 'wakeup vector' */
+		new.nv = POSTED_INTR_WAKEUP_VECTOR;
+	} while (cmpxchg64(&pi_desc->control, old.control,
+			   new.control) != old.control);
+
+	/* We should not block the vCPU if an interrupt is posted for it.  */
+	if (pi_test_on(pi_desc) == 1)
+		__pi_post_block(vcpu);
+
+	local_irq_enable();
+	return (vcpu->pre_pcpu == -1);
+}
+
+void pi_post_block(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->pre_pcpu == -1)
+		return;
+
+	WARN_ON(irqs_disabled());
+	local_irq_disable();
+	__pi_post_block(vcpu);
+	local_irq_enable();
+}
+
+/*
+ * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR.
+ */
+void pi_wakeup_handler(void)
+{
+	struct kvm_vcpu *vcpu;
+	int cpu = smp_processor_id();
+
+	spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+	list_for_each_entry(vcpu, &per_cpu(blocked_vcpu_on_cpu, cpu),
+			blocked_vcpu_list) {
+		struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+
+		if (pi_test_on(pi_desc) == 1)
+			kvm_vcpu_kick(vcpu);
+	}
+	spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+}
+
+void __init pi_init(int cpu)
+{
+	INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
+	spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+}
+
+bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu)
+{
+	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
+
+	return pi_test_on(pi_desc) ||
+		(pi_test_sn(pi_desc) && !pi_is_pir_empty(pi_desc));
+}
+
+
+/*
+ * pi_update_irte - set IRTE for Posted-Interrupts
+ *
+ * @kvm: kvm
+ * @host_irq: host irq of the interrupt
+ * @guest_irq: gsi of the interrupt
+ * @set: set or unset PI
+ * returns 0 on success, < 0 on failure
+ */
+int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq,
+		   bool set)
+{
+	struct kvm_kernel_irq_routing_entry *e;
+	struct kvm_irq_routing_table *irq_rt;
+	struct kvm_lapic_irq irq;
+	struct kvm_vcpu *vcpu;
+	struct vcpu_data vcpu_info;
+	int idx, ret = 0;
+
+	if (!kvm_arch_has_assigned_device(kvm) ||
+	    !irq_remapping_cap(IRQ_POSTING_CAP) ||
+	    !kvm_vcpu_apicv_active(kvm->vcpus[0]))
+		return 0;
+
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
+	if (guest_irq >= irq_rt->nr_rt_entries ||
+	    hlist_empty(&irq_rt->map[guest_irq])) {
+		pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
+			     guest_irq, irq_rt->nr_rt_entries);
+		goto out;
+	}
+
+	hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
+		if (e->type != KVM_IRQ_ROUTING_MSI)
+			continue;
+		/*
+		 * VT-d PI cannot support posting multicast/broadcast
+		 * interrupts to a vCPU, we still use interrupt remapping
+		 * for these kind of interrupts.
+		 *
+		 * For lowest-priority interrupts, we only support
+		 * those with single CPU as the destination, e.g. user
+		 * configures the interrupts via /proc/irq or uses
+		 * irqbalance to make the interrupts single-CPU.
+		 *
+		 * We will support full lowest-priority interrupt later.
+		 *
+		 * In addition, we can only inject generic interrupts using
+		 * the PI mechanism, refuse to route others through it.
+		 */
+
+		kvm_set_msi_irq(kvm, e, &irq);
+		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
+		    !kvm_irq_is_postable(&irq)) {
+			/*
+			 * Make sure the IRTE is in remapped mode if
+			 * we don't handle it in posted mode.
+			 */
+			ret = irq_set_vcpu_affinity(host_irq, NULL);
+			if (ret < 0) {
+				printk(KERN_INFO
+				   "failed to back to remapped mode, irq: %u\n",
+				   host_irq);
+				goto out;
+			}
+
+			continue;
+		}
+
+		vcpu_info.pi_desc_addr = __pa(&to_vmx(vcpu)->pi_desc);
+		vcpu_info.vector = irq.vector;
+
+		trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
+				vcpu_info.vector, vcpu_info.pi_desc_addr, set);
+
+		if (set)
+			ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
+		else
+			ret = irq_set_vcpu_affinity(host_irq, NULL);
+
+		if (ret < 0) {
+			printk(KERN_INFO "%s: failed to update PI IRTE\n",
+					__func__);
+			goto out;
+		}
+	}
+
+	ret = 0;
+out:
+	srcu_read_unlock(&kvm->irq_srcu, idx);
+	return ret;
+}
diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h
new file mode 100644
index 0000000..e53b97f
--- /dev/null
+++ b/arch/x86/kvm/vmx/posted_intr.h
@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_VMX_POSTED_INTR_H
+#define __KVM_X86_VMX_POSTED_INTR_H
+
+#define POSTED_INTR_ON  0
+#define POSTED_INTR_SN  1
+
+/* Posted-Interrupt Descriptor */
+struct pi_desc {
+	u32 pir[8];     /* Posted interrupt requested */
+	union {
+		struct {
+				/* bit 256 - Outstanding Notification */
+			u16	on	: 1,
+				/* bit 257 - Suppress Notification */
+				sn	: 1,
+				/* bit 271:258 - Reserved */
+				rsvd_1	: 14;
+				/* bit 279:272 - Notification Vector */
+			u8	nv;
+				/* bit 287:280 - Reserved */
+			u8	rsvd_2;
+				/* bit 319:288 - Notification Destination */
+			u32	ndst;
+		};
+		u64 control;
+	};
+	u32 rsvd[6];
+} __aligned(64);
+
+static inline bool pi_test_and_set_on(struct pi_desc *pi_desc)
+{
+	return test_and_set_bit(POSTED_INTR_ON,
+			(unsigned long *)&pi_desc->control);
+}
+
+static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc)
+{
+	return test_and_clear_bit(POSTED_INTR_ON,
+			(unsigned long *)&pi_desc->control);
+}
+
+static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
+{
+	return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
+}
+
+static inline bool pi_is_pir_empty(struct pi_desc *pi_desc)
+{
+	return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS);
+}
+
+static inline void pi_set_sn(struct pi_desc *pi_desc)
+{
+	set_bit(POSTED_INTR_SN,
+		(unsigned long *)&pi_desc->control);
+}
+
+static inline void pi_set_on(struct pi_desc *pi_desc)
+{
+	set_bit(POSTED_INTR_ON,
+		(unsigned long *)&pi_desc->control);
+}
+
+static inline void pi_clear_on(struct pi_desc *pi_desc)
+{
+	clear_bit(POSTED_INTR_ON,
+		(unsigned long *)&pi_desc->control);
+}
+
+static inline void pi_clear_sn(struct pi_desc *pi_desc)
+{
+	clear_bit(POSTED_INTR_SN,
+		(unsigned long *)&pi_desc->control);
+}
+
+static inline int pi_test_on(struct pi_desc *pi_desc)
+{
+	return test_bit(POSTED_INTR_ON,
+			(unsigned long *)&pi_desc->control);
+}
+
+static inline int pi_test_sn(struct pi_desc *pi_desc)
+{
+	return test_bit(POSTED_INTR_SN,
+			(unsigned long *)&pi_desc->control);
+}
+
+void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu);
+void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu);
+int pi_pre_block(struct kvm_vcpu *vcpu);
+void pi_post_block(struct kvm_vcpu *vcpu);
+void pi_wakeup_handler(void);
+void __init pi_init(int cpu);
+bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu);
+int pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq,
+		   bool set);
+
+#endif /* __KVM_X86_VMX_POSTED_INTR_H */
\ No newline at end of file
diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h
index 7a3675f..1472c6c 100644
--- a/arch/x86/kvm/vmx/vmcs.h
+++ b/arch/x86/kvm/vmx/vmcs.h
@@ -138,6 +138,13 @@ static inline bool is_external_intr(u32 intr_info)
 	return is_intr_type(intr_info, INTR_TYPE_EXT_INTR);
 }
 
+static inline bool is_exception_with_error_code(u32 intr_info)
+{
+	const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_DELIVER_CODE_MASK;
+
+	return (intr_info & mask) == mask;
+}
+
 enum vmcs_field_width {
 	VMCS_FIELD_WIDTH_U16 = 0,
 	VMCS_FIELD_WIDTH_U64 = 1,
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 799db08..90ad7a6 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -4,6 +4,7 @@
 #include <asm/bitsperlong.h>
 #include <asm/kvm_vcpu_regs.h>
 #include <asm/nospec-branch.h>
+#include <asm/segment.h>
 
 #define WORD_SIZE (BITS_PER_LONG / 8)
 
@@ -294,3 +295,36 @@
 
 	ret
 SYM_FUNC_END(vmread_error_trampoline)
+
+SYM_FUNC_START(vmx_do_interrupt_nmi_irqoff)
+	/*
+	 * Unconditionally create a stack frame, getting the correct RSP on the
+	 * stack (for x86-64) would take two instructions anyways, and RBP can
+	 * be used to restore RSP to make objtool happy (see below).
+	 */
+	push %_ASM_BP
+	mov %_ASM_SP, %_ASM_BP
+
+#ifdef CONFIG_X86_64
+	/*
+	 * Align RSP to a 16-byte boundary (to emulate CPU behavior) before
+	 * creating the synthetic interrupt stack frame for the IRQ/NMI.
+	 */
+	and  $-16, %rsp
+	push $__KERNEL_DS
+	push %rbp
+#endif
+	pushf
+	push $__KERNEL_CS
+	CALL_NOSPEC _ASM_ARG1
+
+	/*
+	 * "Restore" RSP from RBP, even though IRET has already unwound RSP to
+	 * the correct value.  objtool doesn't know the callee will IRET and,
+	 * without the explicit restore, thinks the stack is getting walloped.
+	 * Using an unwind hint is problematic due to x86-64's dynamic alignment.
+	 */
+	mov %_ASM_BP, %_ASM_SP
+	pop %_ASM_BP
+	ret
+SYM_FUNC_END(vmx_do_interrupt_nmi_irqoff)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 819c185..4797ec9 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -56,7 +56,6 @@
 #include "lapic.h"
 #include "mmu.h"
 #include "nested.h"
-#include "ops.h"
 #include "pmu.h"
 #include "trace.h"
 #include "vmcs.h"
@@ -146,8 +145,25 @@ module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
 	RTIT_STATUS_ERROR | RTIT_STATUS_STOPPED | \
 	RTIT_STATUS_BYTECNT))
 
-#define MSR_IA32_RTIT_OUTPUT_BASE_MASK \
-	(~((1UL << cpuid_query_maxphyaddr(vcpu)) - 1) | 0x7f)
+/*
+ * List of MSRs that can be directly passed to the guest.
+ * In addition to these x2apic and PT MSRs are handled specially.
+ */
+static u32 vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = {
+	MSR_IA32_SPEC_CTRL,
+	MSR_IA32_PRED_CMD,
+	MSR_IA32_TSC,
+	MSR_FS_BASE,
+	MSR_GS_BASE,
+	MSR_KERNEL_GS_BASE,
+	MSR_IA32_SYSENTER_CS,
+	MSR_IA32_SYSENTER_ESP,
+	MSR_IA32_SYSENTER_EIP,
+	MSR_CORE_C1_RES,
+	MSR_CORE_C3_RESIDENCY,
+	MSR_CORE_C6_RESIDENCY,
+	MSR_CORE_C7_RESIDENCY,
+};
 
 /*
  * These 2 parameters are used to config the controls for Pause-Loop Exiting:
@@ -341,9 +357,8 @@ static const struct kernel_param_ops vmentry_l1d_flush_ops = {
 };
 module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644);
 
-static bool guest_state_valid(struct kvm_vcpu *vcpu);
 static u32 vmx_segment_access_rights(struct kvm_segment *var);
-static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+static __always_inline void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu,
 							  u32 msr, int type);
 
 void vmx_vmexit(void);
@@ -398,13 +413,6 @@ DEFINE_PER_CPU(struct vmcs *, current_vmcs);
  */
 static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu);
 
-/*
- * We maintian a per-CPU linked-list of vCPU, so in wakeup_handler() we
- * can find which vCPU should be waken up.
- */
-static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu);
-static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock);
-
 static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS);
 static DEFINE_SPINLOCK(vmx_vpid_lock);
 
@@ -447,9 +455,9 @@ static unsigned long host_idt_base;
  * will emulate SYSCALL in legacy mode if the vendor string in guest
  * CPUID.0:{EBX,ECX,EDX} is "AuthenticAMD" or "AMDisbetter!" To
  * support this emulation, IA32_STAR must always be included in
- * vmx_msr_index[], even in i386 builds.
+ * vmx_uret_msrs_list[], even in i386 builds.
  */
-const u32 vmx_msr_index[] = {
+static const u32 vmx_uret_msrs_list[] = {
 #ifdef CONFIG_X86_64
 	MSR_SYSCALL_MASK, MSR_LSTAR, MSR_CSTAR,
 #endif
@@ -623,36 +631,71 @@ static inline bool report_flexpriority(void)
 	return flexpriority_enabled;
 }
 
-static inline int __find_msr_index(struct vcpu_vmx *vmx, u32 msr)
+static int possible_passthrough_msr_slot(u32 msr)
+{
+	u32 i;
+
+	for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++)
+		if (vmx_possible_passthrough_msrs[i] == msr)
+			return i;
+
+	return -ENOENT;
+}
+
+static bool is_valid_passthrough_msr(u32 msr)
+{
+	bool r;
+
+	switch (msr) {
+	case 0x800 ... 0x8ff:
+		/* x2APIC MSRs. These are handled in vmx_update_msr_bitmap_x2apic() */
+		return true;
+	case MSR_IA32_RTIT_STATUS:
+	case MSR_IA32_RTIT_OUTPUT_BASE:
+	case MSR_IA32_RTIT_OUTPUT_MASK:
+	case MSR_IA32_RTIT_CR3_MATCH:
+	case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B:
+		/* PT MSRs. These are handled in pt_update_intercept_for_msr() */
+		return true;
+	}
+
+	r = possible_passthrough_msr_slot(msr) != -ENOENT;
+
+	WARN(!r, "Invalid MSR %x, please adapt vmx_possible_passthrough_msrs[]", msr);
+
+	return r;
+}
+
+static inline int __vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr)
 {
 	int i;
 
-	for (i = 0; i < vmx->nmsrs; ++i)
-		if (vmx_msr_index[vmx->guest_msrs[i].index] == msr)
+	for (i = 0; i < vmx->nr_uret_msrs; ++i)
+		if (vmx_uret_msrs_list[vmx->guest_uret_msrs[i].slot] == msr)
 			return i;
 	return -1;
 }
 
-struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr)
+struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr)
 {
 	int i;
 
-	i = __find_msr_index(vmx, msr);
+	i = __vmx_find_uret_msr(vmx, msr);
 	if (i >= 0)
-		return &vmx->guest_msrs[i];
+		return &vmx->guest_uret_msrs[i];
 	return NULL;
 }
 
-static int vmx_set_guest_msr(struct vcpu_vmx *vmx, struct shared_msr_entry *msr, u64 data)
+static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx,
+				  struct vmx_uret_msr *msr, u64 data)
 {
 	int ret = 0;
 
 	u64 old_msr_data = msr->data;
 	msr->data = data;
-	if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
+	if (msr - vmx->guest_uret_msrs < vmx->nr_active_uret_msrs) {
 		preempt_disable();
-		ret = kvm_set_shared_msr(msr->index, msr->data,
-					 msr->mask);
+		ret = kvm_set_user_return_msr(msr->slot, msr->data, msr->mask);
 		preempt_enable();
 		if (ret)
 			msr->data = old_msr_data;
@@ -825,7 +868,7 @@ static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
 	vm_exit_controls_clearbit(vmx, exit);
 }
 
-int vmx_find_msr_index(struct vmx_msrs *m, u32 msr)
+int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr)
 {
 	unsigned int i;
 
@@ -859,7 +902,7 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 		}
 		break;
 	}
-	i = vmx_find_msr_index(&m->guest, msr);
+	i = vmx_find_loadstore_msr_slot(&m->guest, msr);
 	if (i < 0)
 		goto skip_guest;
 	--m->guest.nr;
@@ -867,7 +910,7 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
 
 skip_guest:
-	i = vmx_find_msr_index(&m->host, msr);
+	i = vmx_find_loadstore_msr_slot(&m->host, msr);
 	if (i < 0)
 		return;
 
@@ -926,12 +969,12 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 	}
 
-	i = vmx_find_msr_index(&m->guest, msr);
+	i = vmx_find_loadstore_msr_slot(&m->guest, msr);
 	if (!entry_only)
-		j = vmx_find_msr_index(&m->host, msr);
+		j = vmx_find_loadstore_msr_slot(&m->host, msr);
 
-	if ((i < 0 && m->guest.nr == NR_LOADSTORE_MSRS) ||
-		(j < 0 &&  m->host.nr == NR_LOADSTORE_MSRS)) {
+	if ((i < 0 && m->guest.nr == MAX_NR_LOADSTORE_MSRS) ||
+	    (j < 0 &&  m->host.nr == MAX_NR_LOADSTORE_MSRS)) {
 		printk_once(KERN_WARNING "Not enough msr switch entries. "
 				"Can't add msr %x\n", msr);
 		return;
@@ -954,10 +997,11 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 	m->host.val[j].value = host_val;
 }
 
-static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
+static bool update_transition_efer(struct vcpu_vmx *vmx)
 {
 	u64 guest_efer = vmx->vcpu.arch.efer;
 	u64 ignore_bits = 0;
+	int i;
 
 	/* Shadow paging assumes NX to be available.  */
 	if (!enable_ept)
@@ -989,17 +1033,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 		else
 			clear_atomic_switch_msr(vmx, MSR_EFER);
 		return false;
-	} else {
-		clear_atomic_switch_msr(vmx, MSR_EFER);
-
-		guest_efer &= ~ignore_bits;
-		guest_efer |= host_efer & ignore_bits;
-
-		vmx->guest_msrs[efer_offset].data = guest_efer;
-		vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
-
-		return true;
 	}
+
+	i = __vmx_find_uret_msr(vmx, MSR_EFER);
+	if (i < 0)
+		return false;
+
+	clear_atomic_switch_msr(vmx, MSR_EFER);
+
+	guest_efer &= ~ignore_bits;
+	guest_efer |= host_efer & ignore_bits;
+
+	vmx->guest_uret_msrs[i].data = guest_efer;
+	vmx->guest_uret_msrs[i].mask = ~ignore_bits;
+
+	return true;
 }
 
 #ifdef CONFIG_X86_32
@@ -1037,6 +1085,12 @@ static inline bool pt_can_write_msr(struct vcpu_vmx *vmx)
 	       !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN);
 }
 
+static inline bool pt_output_base_valid(struct kvm_vcpu *vcpu, u64 base)
+{
+	/* The base must be 128-byte aligned and a legal physical address. */
+	return !kvm_vcpu_is_illegal_gpa(vcpu, base) && !(base & 0x7f);
+}
+
 static inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range)
 {
 	u32 i;
@@ -1141,12 +1195,12 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 	 * when guest state is loaded. This happens when guest transitions
 	 * to/from long-mode by setting MSR_EFER.LMA.
 	 */
-	if (!vmx->guest_msrs_ready) {
-		vmx->guest_msrs_ready = true;
-		for (i = 0; i < vmx->save_nmsrs; ++i)
-			kvm_set_shared_msr(vmx->guest_msrs[i].index,
-					   vmx->guest_msrs[i].data,
-					   vmx->guest_msrs[i].mask);
+	if (!vmx->guest_uret_msrs_loaded) {
+		vmx->guest_uret_msrs_loaded = true;
+		for (i = 0; i < vmx->nr_active_uret_msrs; ++i)
+			kvm_set_user_return_msr(vmx->guest_uret_msrs[i].slot,
+						vmx->guest_uret_msrs[i].data,
+						vmx->guest_uret_msrs[i].mask);
 
 	}
 
@@ -1230,7 +1284,7 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
 #endif
 	load_fixmap_gdt(raw_smp_processor_id());
 	vmx->guest_state_loaded = false;
-	vmx->guest_msrs_ready = false;
+	vmx->guest_uret_msrs_loaded = false;
 }
 
 #ifdef CONFIG_X86_64
@@ -1253,62 +1307,6 @@ static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data)
 }
 #endif
 
-static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
-{
-	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-	struct pi_desc old, new;
-	unsigned int dest;
-
-	/*
-	 * In case of hot-plug or hot-unplug, we may have to undo
-	 * vmx_vcpu_pi_put even if there is no assigned device.  And we
-	 * always keep PI.NDST up to date for simplicity: it makes the
-	 * code easier, and CPU migration is not a fast path.
-	 */
-	if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
-		return;
-
-	/*
-	 * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
-	 * PI.NDST: pi_post_block is the one expected to change PID.NDST and the
-	 * wakeup handler expects the vCPU to be on the blocked_vcpu_list that
-	 * matches PI.NDST. Otherwise, a vcpu may not be able to be woken up
-	 * correctly.
-	 */
-	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || vcpu->cpu == cpu) {
-		pi_clear_sn(pi_desc);
-		goto after_clear_sn;
-	}
-
-	/* The full case.  */
-	do {
-		old.control = new.control = pi_desc->control;
-
-		dest = cpu_physical_id(cpu);
-
-		if (x2apic_enabled())
-			new.ndst = dest;
-		else
-			new.ndst = (dest << 8) & 0xFF00;
-
-		new.sn = 0;
-	} while (cmpxchg64(&pi_desc->control, old.control,
-			   new.control) != old.control);
-
-after_clear_sn:
-
-	/*
-	 * Clear SN before reading the bitmap.  The VT-d firmware
-	 * writes the bitmap and reads SN atomically (5.2.3 in the
-	 * spec), so it doesn't really have a memory barrier that
-	 * pairs with this, but we cannot do that and we need one.
-	 */
-	smp_mb__after_atomic();
-
-	if (!pi_is_pir_empty(pi_desc))
-		pi_set_on(pi_desc);
-}
-
 void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
 			struct loaded_vmcs *buddy)
 {
@@ -1392,20 +1390,6 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	vmx->host_debugctlmsr = get_debugctlmsr();
 }
 
-static void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
-{
-	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
-		return;
-
-	/* Set SN when the vCPU is preempted */
-	if (vcpu->preempted)
-		pi_set_sn(pi_desc);
-}
-
 static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	vmx_vcpu_pi_put(vcpu);
@@ -1415,7 +1399,7 @@ static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
 
 static bool emulation_required(struct kvm_vcpu *vcpu)
 {
-	return emulate_invalid_guest_state && !guest_state_valid(vcpu);
+	return emulate_invalid_guest_state && !vmx_guest_state_valid(vcpu);
 }
 
 unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
@@ -1441,7 +1425,7 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long old_rflags;
 
-	if (enable_unrestricted_guest) {
+	if (is_unrestricted_guest(vcpu)) {
 		kvm_register_mark_available(vcpu, VCPU_EXREG_RFLAGS);
 		vmx->rflags = rflags;
 		vmcs_writel(GUEST_RFLAGS, rflags);
@@ -1561,6 +1545,11 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data)
 	return 0;
 }
 
+static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, void *insn, int insn_len)
+{
+	return true;
+}
+
 static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
 	unsigned long rip, orig_rip;
@@ -1599,33 +1588,6 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
 }
 
 /*
- * Handles kvm_read/write_guest_virt*() result and either injects #PF or returns
- * KVM_EXIT_INTERNAL_ERROR for cases not currently handled by KVM. Return value
- * indicates whether exit to userspace is needed.
- */
-int vmx_handle_memory_failure(struct kvm_vcpu *vcpu, int r,
-			      struct x86_exception *e)
-{
-	if (r == X86EMUL_PROPAGATE_FAULT) {
-		kvm_inject_emulated_page_fault(vcpu, e);
-		return 1;
-	}
-
-	/*
-	 * In case kvm_read/write_guest_virt*() failed with X86EMUL_IO_NEEDED
-	 * while handling a VMX instruction KVM could've handled the request
-	 * correctly by exiting to userspace and performing I/O but there
-	 * doesn't seem to be a real use-case behind such requests, just return
-	 * KVM_EXIT_INTERNAL_ERROR for now.
-	 */
-	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
-	vcpu->run->internal.ndata = 0;
-
-	return 0;
-}
-
-/*
  * Recognizes a pending MTF VM-exit and records the nested state for later
  * delivery.
  */
@@ -1708,16 +1670,19 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
 	vmx_clear_hlt(vcpu);
 }
 
-/*
- * Swap MSR entry in host/guest MSR entry array.
- */
-static void move_msr_up(struct vcpu_vmx *vmx, int from, int to)
+static void vmx_setup_uret_msr(struct vcpu_vmx *vmx, unsigned int msr)
 {
-	struct shared_msr_entry tmp;
+	struct vmx_uret_msr tmp;
+	int from, to;
 
-	tmp = vmx->guest_msrs[to];
-	vmx->guest_msrs[to] = vmx->guest_msrs[from];
-	vmx->guest_msrs[from] = tmp;
+	from = __vmx_find_uret_msr(vmx, msr);
+	if (from < 0)
+		return;
+	to = vmx->nr_active_uret_msrs++;
+
+	tmp = vmx->guest_uret_msrs[to];
+	vmx->guest_uret_msrs[to] = vmx->guest_uret_msrs[from];
+	vmx->guest_uret_msrs[from] = tmp;
 }
 
 /*
@@ -1727,38 +1692,26 @@ static void move_msr_up(struct vcpu_vmx *vmx, int from, int to)
  */
 static void setup_msrs(struct vcpu_vmx *vmx)
 {
-	int save_nmsrs, index;
-
-	save_nmsrs = 0;
+	vmx->guest_uret_msrs_loaded = false;
+	vmx->nr_active_uret_msrs = 0;
 #ifdef CONFIG_X86_64
 	/*
 	 * The SYSCALL MSRs are only needed on long mode guests, and only
 	 * when EFER.SCE is set.
 	 */
 	if (is_long_mode(&vmx->vcpu) && (vmx->vcpu.arch.efer & EFER_SCE)) {
-		index = __find_msr_index(vmx, MSR_STAR);
-		if (index >= 0)
-			move_msr_up(vmx, index, save_nmsrs++);
-		index = __find_msr_index(vmx, MSR_LSTAR);
-		if (index >= 0)
-			move_msr_up(vmx, index, save_nmsrs++);
-		index = __find_msr_index(vmx, MSR_SYSCALL_MASK);
-		if (index >= 0)
-			move_msr_up(vmx, index, save_nmsrs++);
+		vmx_setup_uret_msr(vmx, MSR_STAR);
+		vmx_setup_uret_msr(vmx, MSR_LSTAR);
+		vmx_setup_uret_msr(vmx, MSR_SYSCALL_MASK);
 	}
 #endif
-	index = __find_msr_index(vmx, MSR_EFER);
-	if (index >= 0 && update_transition_efer(vmx, index))
-		move_msr_up(vmx, index, save_nmsrs++);
-	index = __find_msr_index(vmx, MSR_TSC_AUX);
-	if (index >= 0 && guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP))
-		move_msr_up(vmx, index, save_nmsrs++);
-	index = __find_msr_index(vmx, MSR_IA32_TSX_CTRL);
-	if (index >= 0)
-		move_msr_up(vmx, index, save_nmsrs++);
+	if (update_transition_efer(vmx))
+		vmx_setup_uret_msr(vmx, MSR_EFER);
 
-	vmx->save_nmsrs = save_nmsrs;
-	vmx->guest_msrs_ready = false;
+	if (guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP))
+		vmx_setup_uret_msr(vmx, MSR_TSC_AUX);
+
+	vmx_setup_uret_msr(vmx, MSR_IA32_TSX_CTRL);
 
 	if (cpu_has_vmx_msr_bitmap())
 		vmx_update_msr_bitmap(&vmx->vcpu);
@@ -1828,7 +1781,7 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr)
 static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct shared_msr_entry *msr;
+	struct vmx_uret_msr *msr;
 	u32 index;
 
 	switch (msr_info->index) {
@@ -1849,7 +1802,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!msr_info->host_initiated &&
 		    !(vcpu->arch.arch_capabilities & ARCH_CAP_TSX_CTRL_MSR))
 			return 1;
-		goto find_shared_msr;
+		goto find_uret_msr;
 	case MSR_IA32_UMWAIT_CONTROL:
 		if (!msr_info->host_initiated && !vmx_has_waitpkg(vmx))
 			return 1;
@@ -1956,10 +1909,10 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
 			return 1;
-		goto find_shared_msr;
+		goto find_uret_msr;
 	default:
-	find_shared_msr:
-		msr = find_msr_entry(vmx, msr_info->index);
+	find_uret_msr:
+		msr = vmx_find_uret_msr(vmx, msr_info->index);
 		if (msr) {
 			msr_info->data = msr->data;
 			break;
@@ -1988,7 +1941,7 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu,
 static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct shared_msr_entry *msr;
+	struct vmx_uret_msr *msr;
 	int ret = 0;
 	u32 msr_index = msr_info->index;
 	u64 data = msr_info->data;
@@ -2082,7 +2035,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		 * in the merging. We update the vmcs01 here for L1 as well
 		 * since it will end up touching the MSR anyway now.
 		 */
-		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap,
+		vmx_disable_intercept_for_msr(vcpu,
 					      MSR_IA32_SPEC_CTRL,
 					      MSR_TYPE_RW);
 		break;
@@ -2092,7 +2045,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		if (data & ~(TSX_CTRL_RTM_DISABLE | TSX_CTRL_CPUID_CLEAR))
 			return 1;
-		goto find_shared_msr;
+		goto find_uret_msr;
 	case MSR_IA32_PRED_CMD:
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL))
@@ -2118,8 +2071,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		 * vmcs02.msr_bitmap here since it gets completely overwritten
 		 * in the merging.
 		 */
-		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD,
-					      MSR_TYPE_W);
+		vmx_disable_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W);
 		break;
 	case MSR_IA32_CR_PAT:
 		if (!kvm_pat_valid(data))
@@ -2169,7 +2121,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		vmcs_write64(GUEST_IA32_RTIT_CTL, data);
 		vmx->pt_desc.guest.ctl = data;
-		pt_update_intercept_for_msr(vmx);
+		pt_update_intercept_for_msr(vcpu);
 		break;
 	case MSR_IA32_RTIT_STATUS:
 		if (!pt_can_write_msr(vmx))
@@ -2194,7 +2146,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		    !intel_pt_validate_cap(vmx->pt_desc.caps,
 					   PT_CAP_single_range_output))
 			return 1;
-		if (data & MSR_IA32_RTIT_OUTPUT_BASE_MASK)
+		if (!pt_output_base_valid(vcpu, data))
 			return 1;
 		vmx->pt_desc.guest.output_base = data;
 		break;
@@ -2229,13 +2181,13 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		/* Check reserved bit, higher 32 bits should be zero */
 		if ((data >> 32) != 0)
 			return 1;
-		goto find_shared_msr;
+		goto find_uret_msr;
 
 	default:
-	find_shared_msr:
-		msr = find_msr_entry(vmx, msr_index);
+	find_uret_msr:
+		msr = vmx_find_uret_msr(vmx, msr_index);
 		if (msr)
-			ret = vmx_set_guest_msr(vmx, msr, data);
+			ret = vmx_set_guest_uret_msr(vmx, msr, data);
 		else
 			ret = kvm_set_msr_common(vcpu, msr_info);
 	}
@@ -2267,7 +2219,8 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 		vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & guest_owned_bits;
 		break;
 	case VCPU_EXREG_CR3:
-		if (enable_unrestricted_guest || (enable_ept && is_paging(vcpu)))
+		if (is_unrestricted_guest(vcpu) ||
+		    (enable_ept && is_paging(vcpu)))
 			vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
 		break;
 	case VCPU_EXREG_CR4:
@@ -2448,7 +2401,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 			SECONDARY_EXEC_UNRESTRICTED_GUEST |
 			SECONDARY_EXEC_PAUSE_LOOP_EXITING |
 			SECONDARY_EXEC_DESC |
-			SECONDARY_EXEC_RDTSCP |
+			SECONDARY_EXEC_ENABLE_RDTSCP |
 			SECONDARY_EXEC_ENABLE_INVPCID |
 			SECONDARY_EXEC_APIC_REGISTER_VIRT |
 			SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
@@ -2865,7 +2818,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
 void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct shared_msr_entry *msr = find_msr_entry(vmx, MSR_EFER);
+	struct vmx_uret_msr *msr = vmx_find_uret_msr(vmx, MSR_EFER);
 
 	if (!msr)
 		return;
@@ -2971,7 +2924,7 @@ static void vmx_flush_tlb_guest(struct kvm_vcpu *vcpu)
 	vpid_sync_context(to_vmx(vcpu)->vpid);
 }
 
-static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
+void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
 
@@ -3033,7 +2986,7 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	unsigned long hw_cr0;
 
 	hw_cr0 = (cr0 & ~KVM_VM_CR0_ALWAYS_OFF);
-	if (enable_unrestricted_guest)
+	if (is_unrestricted_guest(vcpu))
 		hw_cr0 |= KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST;
 	else {
 		hw_cr0 |= KVM_VM_CR0_ALWAYS_ON;
@@ -3054,7 +3007,7 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	}
 #endif
 
-	if (enable_ept && !enable_unrestricted_guest)
+	if (enable_ept && !is_unrestricted_guest(vcpu))
 		ept_update_paging_mode_cr0(&hw_cr0, cr0, vcpu);
 
 	vmcs_writel(CR0_READ_SHADOW, cr0);
@@ -3114,7 +3067,7 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long pgd,
 			guest_cr3 = vcpu->arch.cr3;
 		else /* vmcs01.GUEST_CR3 is already up-to-date. */
 			update_guest_cr3 = false;
-		ept_load_pdptrs(vcpu);
+		vmx_ept_load_pdptrs(vcpu);
 	} else {
 		guest_cr3 = pgd;
 	}
@@ -3134,7 +3087,7 @@ int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	unsigned long hw_cr4;
 
 	hw_cr4 = (cr4_read_shadow() & X86_CR4_MCE) | (cr4 & ~X86_CR4_MCE);
-	if (enable_unrestricted_guest)
+	if (is_unrestricted_guest(vcpu))
 		hw_cr4 |= KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST;
 	else if (vmx->rmode.vm86_active)
 		hw_cr4 |= KVM_RMODE_VM_CR4_ALWAYS_ON;
@@ -3169,7 +3122,7 @@ int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	vcpu->arch.cr4 = cr4;
 	kvm_register_mark_available(vcpu, VCPU_EXREG_CR4);
 
-	if (!enable_unrestricted_guest) {
+	if (!is_unrestricted_guest(vcpu)) {
 		if (enable_ept) {
 			if (!is_paging(vcpu)) {
 				hw_cr4 &= ~X86_CR4_PAE;
@@ -3309,7 +3262,7 @@ void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg)
 	 * tree. Newer qemu binaries with that qemu fix would not need this
 	 * kvm hack.
 	 */
-	if (enable_unrestricted_guest && (seg != VCPU_SREG_LDTR))
+	if (is_unrestricted_guest(vcpu) && (seg != VCPU_SREG_LDTR))
 		var->type |= 0x1; /* Accessed */
 
 	vmcs_write32(sf->ar_bytes, vmx_segment_access_rights(var));
@@ -3498,11 +3451,8 @@ static bool cs_ss_rpl_check(struct kvm_vcpu *vcpu)
  * not.
  * We assume that registers are always usable
  */
-static bool guest_state_valid(struct kvm_vcpu *vcpu)
+bool __vmx_guest_state_valid(struct kvm_vcpu *vcpu)
 {
-	if (enable_unrestricted_guest)
-		return true;
-
 	/* real mode guest state checks */
 	if (!is_protmode(vcpu) || (vmx_get_rflags(vcpu) & X86_EFLAGS_VM)) {
 		if (!rmode_segment_valid(vcpu, VCPU_SREG_CS))
@@ -3688,10 +3638,51 @@ void free_vpid(int vpid)
 	spin_unlock(&vmx_vpid_lock);
 }
 
-static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
+static void vmx_clear_msr_bitmap_read(ulong *msr_bitmap, u32 msr)
+{
+	int f = sizeof(unsigned long);
+
+	if (msr <= 0x1fff)
+		__clear_bit(msr, msr_bitmap + 0x000 / f);
+	else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff))
+		__clear_bit(msr & 0x1fff, msr_bitmap + 0x400 / f);
+}
+
+static void vmx_clear_msr_bitmap_write(ulong *msr_bitmap, u32 msr)
+{
+	int f = sizeof(unsigned long);
+
+	if (msr <= 0x1fff)
+		__clear_bit(msr, msr_bitmap + 0x800 / f);
+	else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff))
+		__clear_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f);
+}
+
+static void vmx_set_msr_bitmap_read(ulong *msr_bitmap, u32 msr)
+{
+	int f = sizeof(unsigned long);
+
+	if (msr <= 0x1fff)
+		__set_bit(msr, msr_bitmap + 0x000 / f);
+	else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff))
+		__set_bit(msr & 0x1fff, msr_bitmap + 0x400 / f);
+}
+
+static void vmx_set_msr_bitmap_write(ulong *msr_bitmap, u32 msr)
+{
+	int f = sizeof(unsigned long);
+
+	if (msr <= 0x1fff)
+		__set_bit(msr, msr_bitmap + 0x800 / f);
+	else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff))
+		__set_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f);
+}
+
+static __always_inline void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu,
 							  u32 msr, int type)
 {
-	int f = sizeof(unsigned long);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
 
 	if (!cpu_has_vmx_msr_bitmap())
 		return;
@@ -3700,36 +3691,44 @@ static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bit
 		evmcs_touch_msr_bitmap();
 
 	/*
-	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
-	 * have the write-low and read-high bitmap offsets the wrong way round.
-	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
-	 */
-	if (msr <= 0x1fff) {
-		if (type & MSR_TYPE_R)
-			/* read-low */
-			__clear_bit(msr, msr_bitmap + 0x000 / f);
+	 * Mark the desired intercept state in shadow bitmap, this is needed
+	 * for resync when the MSR filters change.
+	*/
+	if (is_valid_passthrough_msr(msr)) {
+		int idx = possible_passthrough_msr_slot(msr);
 
-		if (type & MSR_TYPE_W)
-			/* write-low */
-			__clear_bit(msr, msr_bitmap + 0x800 / f);
-
-	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
-		msr &= 0x1fff;
-		if (type & MSR_TYPE_R)
-			/* read-high */
-			__clear_bit(msr, msr_bitmap + 0x400 / f);
-
-		if (type & MSR_TYPE_W)
-			/* write-high */
-			__clear_bit(msr, msr_bitmap + 0xc00 / f);
-
+		if (idx != -ENOENT) {
+			if (type & MSR_TYPE_R)
+				clear_bit(idx, vmx->shadow_msr_intercept.read);
+			if (type & MSR_TYPE_W)
+				clear_bit(idx, vmx->shadow_msr_intercept.write);
+		}
 	}
+
+	if ((type & MSR_TYPE_R) &&
+	    !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ)) {
+		vmx_set_msr_bitmap_read(msr_bitmap, msr);
+		type &= ~MSR_TYPE_R;
+	}
+
+	if ((type & MSR_TYPE_W) &&
+	    !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE)) {
+		vmx_set_msr_bitmap_write(msr_bitmap, msr);
+		type &= ~MSR_TYPE_W;
+	}
+
+	if (type & MSR_TYPE_R)
+		vmx_clear_msr_bitmap_read(msr_bitmap, msr);
+
+	if (type & MSR_TYPE_W)
+		vmx_clear_msr_bitmap_write(msr_bitmap, msr);
 }
 
-static __always_inline void vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
+static __always_inline void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu,
 							 u32 msr, int type)
 {
-	int f = sizeof(unsigned long);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
 
 	if (!cpu_has_vmx_msr_bitmap())
 		return;
@@ -3738,39 +3737,34 @@ static __always_inline void vmx_enable_intercept_for_msr(unsigned long *msr_bitm
 		evmcs_touch_msr_bitmap();
 
 	/*
-	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
-	 * have the write-low and read-high bitmap offsets the wrong way round.
-	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
-	 */
-	if (msr <= 0x1fff) {
-		if (type & MSR_TYPE_R)
-			/* read-low */
-			__set_bit(msr, msr_bitmap + 0x000 / f);
+	 * Mark the desired intercept state in shadow bitmap, this is needed
+	 * for resync when the MSR filter changes.
+	*/
+	if (is_valid_passthrough_msr(msr)) {
+		int idx = possible_passthrough_msr_slot(msr);
 
-		if (type & MSR_TYPE_W)
-			/* write-low */
-			__set_bit(msr, msr_bitmap + 0x800 / f);
-
-	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
-		msr &= 0x1fff;
-		if (type & MSR_TYPE_R)
-			/* read-high */
-			__set_bit(msr, msr_bitmap + 0x400 / f);
-
-		if (type & MSR_TYPE_W)
-			/* write-high */
-			__set_bit(msr, msr_bitmap + 0xc00 / f);
-
+		if (idx != -ENOENT) {
+			if (type & MSR_TYPE_R)
+				set_bit(idx, vmx->shadow_msr_intercept.read);
+			if (type & MSR_TYPE_W)
+				set_bit(idx, vmx->shadow_msr_intercept.write);
+		}
 	}
+
+	if (type & MSR_TYPE_R)
+		vmx_set_msr_bitmap_read(msr_bitmap, msr);
+
+	if (type & MSR_TYPE_W)
+		vmx_set_msr_bitmap_write(msr_bitmap, msr);
 }
 
-static __always_inline void vmx_set_intercept_for_msr(unsigned long *msr_bitmap,
-			     			      u32 msr, int type, bool value)
+static __always_inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu,
+						      u32 msr, int type, bool value)
 {
 	if (value)
-		vmx_enable_intercept_for_msr(msr_bitmap, msr, type);
+		vmx_enable_intercept_for_msr(vcpu, msr, type);
 	else
-		vmx_disable_intercept_for_msr(msr_bitmap, msr, type);
+		vmx_disable_intercept_for_msr(vcpu, msr, type);
 }
 
 static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
@@ -3788,15 +3782,15 @@ static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
 	return mode;
 }
 
-static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap,
-					 u8 mode)
+static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu, u8 mode)
 {
 	int msr;
 
-	for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
-		unsigned word = msr / BITS_PER_LONG;
-		msr_bitmap[word] = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0;
-		msr_bitmap[word + (0x800 / sizeof(long))] = ~0;
+	for (msr = 0x800; msr <= 0x8ff; msr++) {
+		bool apicv = !!(mode & MSR_BITMAP_MODE_X2APIC_APICV);
+
+		vmx_set_intercept_for_msr(vcpu, msr, MSR_TYPE_R, !apicv);
+		vmx_set_intercept_for_msr(vcpu, msr, MSR_TYPE_W, true);
 	}
 
 	if (mode & MSR_BITMAP_MODE_X2APIC) {
@@ -3804,11 +3798,11 @@ static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap,
 		 * TPR reads and writes can be virtualized even if virtual interrupt
 		 * delivery is not in use.
 		 */
-		vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW);
+		vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW);
 		if (mode & MSR_BITMAP_MODE_X2APIC_APICV) {
-			vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R);
-			vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W);
-			vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W);
+			vmx_enable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_RW);
+			vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_EOI), MSR_TYPE_W);
+			vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W);
 		}
 	}
 }
@@ -3816,7 +3810,6 @@ static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap,
 void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
 	u8 mode = vmx_msr_bitmap_mode(vcpu);
 	u8 changed = mode ^ vmx->msr_bitmap_mode;
 
@@ -3824,30 +3817,24 @@ void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu)
 		return;
 
 	if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV))
-		vmx_update_msr_bitmap_x2apic(msr_bitmap, mode);
+		vmx_update_msr_bitmap_x2apic(vcpu, mode);
 
 	vmx->msr_bitmap_mode = mode;
 }
 
-void pt_update_intercept_for_msr(struct vcpu_vmx *vmx)
+void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu)
 {
-	unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	bool flag = !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN);
 	u32 i;
 
-	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_STATUS,
-							MSR_TYPE_RW, flag);
-	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_OUTPUT_BASE,
-							MSR_TYPE_RW, flag);
-	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_OUTPUT_MASK,
-							MSR_TYPE_RW, flag);
-	vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_CR3_MATCH,
-							MSR_TYPE_RW, flag);
+	vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_STATUS, MSR_TYPE_RW, flag);
+	vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_OUTPUT_BASE, MSR_TYPE_RW, flag);
+	vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_OUTPUT_MASK, MSR_TYPE_RW, flag);
+	vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_CR3_MATCH, MSR_TYPE_RW, flag);
 	for (i = 0; i < vmx->pt_desc.addr_range; i++) {
-		vmx_set_intercept_for_msr(msr_bitmap,
-			MSR_IA32_RTIT_ADDR0_A + i * 2, MSR_TYPE_RW, flag);
-		vmx_set_intercept_for_msr(msr_bitmap,
-			MSR_IA32_RTIT_ADDR0_B + i * 2, MSR_TYPE_RW, flag);
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_ADDR0_A + i * 2, MSR_TYPE_RW, flag);
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_ADDR0_B + i * 2, MSR_TYPE_RW, flag);
 	}
 }
 
@@ -3871,6 +3858,29 @@ static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
 	return ((rvi & 0xf0) > (vppr & 0xf0));
 }
 
+static void vmx_msr_filter_changed(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u32 i;
+
+	/*
+	 * Set intercept permissions for all potentially passed through MSRs
+	 * again. They will automatically get filtered through the MSR filter,
+	 * so we are back in sync after this.
+	 */
+	for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++) {
+		u32 msr = vmx_possible_passthrough_msrs[i];
+		bool read = test_bit(i, vmx->shadow_msr_intercept.read);
+		bool write = test_bit(i, vmx->shadow_msr_intercept.write);
+
+		vmx_set_intercept_for_msr(vcpu, msr, MSR_TYPE_R, read);
+		vmx_set_intercept_for_msr(vcpu, msr, MSR_TYPE_W, write);
+	}
+
+	pt_update_intercept_for_msr(vcpu);
+	vmx_update_msr_bitmap_x2apic(vcpu, vmx_msr_bitmap_mode(vcpu));
+}
+
 static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
 						     bool nested)
 {
@@ -4099,6 +4109,61 @@ u32 vmx_exec_control(struct vcpu_vmx *vmx)
 	return exec_control;
 }
 
+/*
+ * Adjust a single secondary execution control bit to intercept/allow an
+ * instruction in the guest.  This is usually done based on whether or not a
+ * feature has been exposed to the guest in order to correctly emulate faults.
+ */
+static inline void
+vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control,
+				  u32 control, bool enabled, bool exiting)
+{
+	/*
+	 * If the control is for an opt-in feature, clear the control if the
+	 * feature is not exposed to the guest, i.e. not enabled.  If the
+	 * control is opt-out, i.e. an exiting control, clear the control if
+	 * the feature _is_ exposed to the guest, i.e. exiting/interception is
+	 * disabled for the associated instruction.  Note, the caller is
+	 * responsible presetting exec_control to set all supported bits.
+	 */
+	if (enabled == exiting)
+		*exec_control &= ~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 (enabled)
+			vmx->nested.msrs.secondary_ctls_high |= control;
+		else
+			vmx->nested.msrs.secondary_ctls_high &= ~control;
+	}
+}
+
+/*
+ * Wrapper macro for the common case of adjusting a secondary execution control
+ * based on a single guest CPUID bit, with a dedicated feature bit.  This also
+ * verifies that the control is actually supported by KVM and hardware.
+ */
+#define vmx_adjust_sec_exec_control(vmx, exec_control, name, feat_name, ctrl_name, exiting) \
+({									 \
+	bool __enabled;							 \
+									 \
+	if (cpu_has_vmx_##name()) {					 \
+		__enabled = guest_cpuid_has(&(vmx)->vcpu,		 \
+					    X86_FEATURE_##feat_name);	 \
+		vmx_adjust_secondary_exec_control(vmx, exec_control,	 \
+			SECONDARY_EXEC_##ctrl_name, __enabled, exiting); \
+	}								 \
+})
+
+/* More macro magic for ENABLE_/opt-in versus _EXITING/opt-out controls. */
+#define vmx_adjust_sec_exec_feature(vmx, exec_control, lname, uname) \
+	vmx_adjust_sec_exec_control(vmx, exec_control, lname, uname, ENABLE_##uname, false)
+
+#define vmx_adjust_sec_exec_exiting(vmx, exec_control, lname, uname) \
+	vmx_adjust_sec_exec_control(vmx, exec_control, lname, uname, uname##_EXITING, true)
 
 static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
 {
@@ -4139,7 +4204,7 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
 	if (!enable_pml)
 		exec_control &= ~SECONDARY_EXEC_ENABLE_PML;
 
-	if (vmx_xsaves_supported()) {
+	if (cpu_has_vmx_xsaves()) {
 		/* Exposing XSAVES only when XSAVE is exposed */
 		bool xsaves_enabled =
 			boot_cpu_has(X86_FEATURE_XSAVE) &&
@@ -4148,101 +4213,29 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
 
 		vcpu->arch.xsaves_enabled = xsaves_enabled;
 
-		if (!xsaves_enabled)
-			exec_control &= ~SECONDARY_EXEC_XSAVES;
-
-		if (nested) {
-			if (xsaves_enabled)
-				vmx->nested.msrs.secondary_ctls_high |=
-					SECONDARY_EXEC_XSAVES;
-			else
-				vmx->nested.msrs.secondary_ctls_high &=
-					~SECONDARY_EXEC_XSAVES;
-		}
+		vmx_adjust_secondary_exec_control(vmx, &exec_control,
+						  SECONDARY_EXEC_XSAVES,
+						  xsaves_enabled, false);
 	}
 
-	if (cpu_has_vmx_rdtscp()) {
-		bool rdtscp_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP);
-		if (!rdtscp_enabled)
-			exec_control &= ~SECONDARY_EXEC_RDTSCP;
+	vmx_adjust_sec_exec_feature(vmx, &exec_control, rdtscp, RDTSCP);
 
-		if (nested) {
-			if (rdtscp_enabled)
-				vmx->nested.msrs.secondary_ctls_high |=
-					SECONDARY_EXEC_RDTSCP;
-			else
-				vmx->nested.msrs.secondary_ctls_high &=
-					~SECONDARY_EXEC_RDTSCP;
-		}
-	}
+	/*
+	 * Expose INVPCID if and only if PCID is also exposed to the guest.
+	 * INVPCID takes a #UD when it's disabled in the VMCS, but a #GP or #PF
+	 * if CR4.PCIDE=0.  Enumerating CPUID.INVPCID=1 would lead to incorrect
+	 * behavior from the guest perspective (it would expect #GP or #PF).
+	 */
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_PCID))
+		guest_cpuid_clear(vcpu, X86_FEATURE_INVPCID);
+	vmx_adjust_sec_exec_feature(vmx, &exec_control, invpcid, INVPCID);
 
-	if (cpu_has_vmx_invpcid()) {
-		/* Exposing INVPCID only when PCID is exposed */
-		bool invpcid_enabled =
-			guest_cpuid_has(vcpu, X86_FEATURE_INVPCID) &&
-			guest_cpuid_has(vcpu, X86_FEATURE_PCID);
 
-		if (!invpcid_enabled) {
-			exec_control &= ~SECONDARY_EXEC_ENABLE_INVPCID;
-			guest_cpuid_clear(vcpu, X86_FEATURE_INVPCID);
-		}
+	vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdrand, RDRAND);
+	vmx_adjust_sec_exec_exiting(vmx, &exec_control, rdseed, RDSEED);
 
-		if (nested) {
-			if (invpcid_enabled)
-				vmx->nested.msrs.secondary_ctls_high |=
-					SECONDARY_EXEC_ENABLE_INVPCID;
-			else
-				vmx->nested.msrs.secondary_ctls_high &=
-					~SECONDARY_EXEC_ENABLE_INVPCID;
-		}
-	}
-
-	if (vmx_rdrand_supported()) {
-		bool rdrand_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDRAND);
-		if (rdrand_enabled)
-			exec_control &= ~SECONDARY_EXEC_RDRAND_EXITING;
-
-		if (nested) {
-			if (rdrand_enabled)
-				vmx->nested.msrs.secondary_ctls_high |=
-					SECONDARY_EXEC_RDRAND_EXITING;
-			else
-				vmx->nested.msrs.secondary_ctls_high &=
-					~SECONDARY_EXEC_RDRAND_EXITING;
-		}
-	}
-
-	if (vmx_rdseed_supported()) {
-		bool rdseed_enabled = guest_cpuid_has(vcpu, X86_FEATURE_RDSEED);
-		if (rdseed_enabled)
-			exec_control &= ~SECONDARY_EXEC_RDSEED_EXITING;
-
-		if (nested) {
-			if (rdseed_enabled)
-				vmx->nested.msrs.secondary_ctls_high |=
-					SECONDARY_EXEC_RDSEED_EXITING;
-			else
-				vmx->nested.msrs.secondary_ctls_high &=
-					~SECONDARY_EXEC_RDSEED_EXITING;
-		}
-	}
-
-	if (vmx_waitpkg_supported()) {
-		bool waitpkg_enabled =
-			guest_cpuid_has(vcpu, X86_FEATURE_WAITPKG);
-
-		if (!waitpkg_enabled)
-			exec_control &= ~SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
-
-		if (nested) {
-			if (waitpkg_enabled)
-				vmx->nested.msrs.secondary_ctls_high |=
-					SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
-			else
-				vmx->nested.msrs.secondary_ctls_high &=
-					~SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE;
-		}
-	}
+	vmx_adjust_sec_exec_control(vmx, &exec_control, waitpkg, WAITPKG,
+				    ENABLE_USR_WAIT_PAUSE, false);
 
 	vmx->secondary_exec_control = exec_control;
 }
@@ -4335,7 +4328,7 @@ static void init_vmcs(struct vcpu_vmx *vmx)
 	if (vmx->vpid != 0)
 		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
 
-	if (vmx_xsaves_supported())
+	if (cpu_has_vmx_xsaves())
 		vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP);
 
 	if (enable_pml) {
@@ -5148,7 +5141,8 @@ static int handle_vmcall(struct kvm_vcpu *vcpu)
 
 static int handle_invd(struct kvm_vcpu *vcpu)
 {
-	return kvm_emulate_instruction(vcpu, 0);
+	/* Treat an INVD instruction as a NOP and just skip it. */
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 static int handle_invlpg(struct kvm_vcpu *vcpu)
@@ -5331,7 +5325,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 	 * would also use advanced VM-exit information for EPT violations to
 	 * reconstruct the page fault error code.
 	 */
-	if (unlikely(kvm_mmu_is_illegal_gpa(vcpu, gpa)))
+	if (unlikely(kvm_vcpu_is_illegal_gpa(vcpu, gpa)))
 		return kvm_emulate_instruction(vcpu, 0);
 
 	return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
@@ -5442,25 +5436,6 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu)
 	}
 }
 
-/*
- * Handler for POSTED_INTERRUPT_WAKEUP_VECTOR.
- */
-static void wakeup_handler(void)
-{
-	struct kvm_vcpu *vcpu;
-	int cpu = smp_processor_id();
-
-	spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
-	list_for_each_entry(vcpu, &per_cpu(blocked_vcpu_on_cpu, cpu),
-			blocked_vcpu_list) {
-		struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-
-		if (pi_test_on(pi_desc) == 1)
-			kvm_vcpu_kick(vcpu);
-	}
-	spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
-}
-
 static void vmx_enable_tdp(void)
 {
 	kvm_mmu_set_mask_ptes(VMX_EPT_READABLE_MASK,
@@ -5524,16 +5499,11 @@ static int handle_invpcid(struct kvm_vcpu *vcpu)
 {
 	u32 vmx_instruction_info;
 	unsigned long type;
-	bool pcid_enabled;
 	gva_t gva;
-	struct x86_exception e;
-	unsigned i;
-	unsigned long roots_to_free = 0;
 	struct {
 		u64 pcid;
 		u64 gla;
 	} operand;
-	int r;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) {
 		kvm_queue_exception(vcpu, UD_VECTOR);
@@ -5556,68 +5526,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu)
 				sizeof(operand), &gva))
 		return 1;
 
-	r = kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e);
-	if (r != X86EMUL_CONTINUE)
-		return vmx_handle_memory_failure(vcpu, r, &e);
-
-	if (operand.pcid >> 12 != 0) {
-		kvm_inject_gp(vcpu, 0);
-		return 1;
-	}
-
-	pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE);
-
-	switch (type) {
-	case INVPCID_TYPE_INDIV_ADDR:
-		if ((!pcid_enabled && (operand.pcid != 0)) ||
-		    is_noncanonical_address(operand.gla, vcpu)) {
-			kvm_inject_gp(vcpu, 0);
-			return 1;
-		}
-		kvm_mmu_invpcid_gva(vcpu, operand.gla, operand.pcid);
-		return kvm_skip_emulated_instruction(vcpu);
-
-	case INVPCID_TYPE_SINGLE_CTXT:
-		if (!pcid_enabled && (operand.pcid != 0)) {
-			kvm_inject_gp(vcpu, 0);
-			return 1;
-		}
-
-		if (kvm_get_active_pcid(vcpu) == operand.pcid) {
-			kvm_mmu_sync_roots(vcpu);
-			kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
-		}
-
-		for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
-			if (kvm_get_pcid(vcpu, vcpu->arch.mmu->prev_roots[i].pgd)
-			    == operand.pcid)
-				roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
-
-		kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free);
-		/*
-		 * If neither the current cr3 nor any of the prev_roots use the
-		 * given PCID, then nothing needs to be done here because a
-		 * resync will happen anyway before switching to any other CR3.
-		 */
-
-		return kvm_skip_emulated_instruction(vcpu);
-
-	case INVPCID_TYPE_ALL_NON_GLOBAL:
-		/*
-		 * Currently, KVM doesn't mark global entries in the shadow
-		 * page tables, so a non-global flush just degenerates to a
-		 * global flush. If needed, we could optimize this later by
-		 * keeping track of global entries in shadow page tables.
-		 */
-
-		fallthrough;
-	case INVPCID_TYPE_ALL_INCL_GLOBAL:
-		kvm_mmu_unload(vcpu);
-		return kvm_skip_emulated_instruction(vcpu);
-
-	default:
-		BUG(); /* We have already checked above that type <= 3 */
-	}
+	return kvm_handle_invpcid(vcpu, type, gva);
 }
 
 static int handle_pml_full(struct kvm_vcpu *vcpu)
@@ -5746,10 +5655,24 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 static const int kvm_vmx_max_exit_handlers =
 	ARRAY_SIZE(kvm_vmx_exit_handlers);
 
-static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
+static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2,
+			      u32 *intr_info, u32 *error_code)
 {
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
 	*info1 = vmx_get_exit_qual(vcpu);
-	*info2 = vmx_get_intr_info(vcpu);
+	if (!(vmx->exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY)) {
+		*info2 = vmx->idt_vectoring_info;
+		*intr_info = vmx_get_intr_info(vcpu);
+		if (is_exception_with_error_code(*intr_info))
+			*error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
+		else
+			*error_code = 0;
+	} else {
+		*info2 = 0;
+		*intr_info = 0;
+		*error_code = 0;
+	}
 }
 
 static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx)
@@ -6054,6 +5977,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
 			exit_reason != EXIT_REASON_EPT_VIOLATION &&
 			exit_reason != EXIT_REASON_PML_FULL &&
+			exit_reason != EXIT_REASON_APIC_ACCESS &&
 			exit_reason != EXIT_REASON_TASK_SWITCH)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
@@ -6382,14 +6306,6 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 	return max_irr;
 }
 
-static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
-{
-	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-
-	return pi_test_on(pi_desc) ||
-		(pi_test_sn(pi_desc) && !pi_is_pir_empty(pi_desc));
-}
-
 static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
 {
 	if (!kvm_vcpu_apicv_active(vcpu))
@@ -6409,70 +6325,43 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu)
 	memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir));
 }
 
+void vmx_do_interrupt_nmi_irqoff(unsigned long entry);
+
+static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu, u32 intr_info)
+{
+	unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK;
+	gate_desc *desc = (gate_desc *)host_idt_base + vector;
+
+	kvm_before_interrupt(vcpu);
+	vmx_do_interrupt_nmi_irqoff(gate_offset(desc));
+	kvm_after_interrupt(vcpu);
+}
+
 static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx)
 {
 	u32 intr_info = vmx_get_intr_info(&vmx->vcpu);
 
 	/* if exit due to PF check for async PF */
-	if (is_page_fault(intr_info)) {
+	if (is_page_fault(intr_info))
 		vmx->vcpu.arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags();
 	/* Handle machine checks before interrupts are enabled */
-	} else if (is_machine_check(intr_info)) {
+	else if (is_machine_check(intr_info))
 		kvm_machine_check();
 	/* We need to handle NMIs before interrupts are enabled */
-	} else if (is_nmi(intr_info)) {
-		kvm_before_interrupt(&vmx->vcpu);
-		asm("int $2");
-		kvm_after_interrupt(&vmx->vcpu);
-	}
+	else if (is_nmi(intr_info))
+		handle_interrupt_nmi_irqoff(&vmx->vcpu, intr_info);
 }
 
 static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu)
 {
-	unsigned int vector;
-	unsigned long entry;
-#ifdef CONFIG_X86_64
-	unsigned long tmp;
-#endif
-	gate_desc *desc;
 	u32 intr_info = vmx_get_intr_info(vcpu);
 
 	if (WARN_ONCE(!is_external_intr(intr_info),
 	    "KVM: unexpected VM-Exit interrupt info: 0x%x", intr_info))
 		return;
 
-	vector = intr_info & INTR_INFO_VECTOR_MASK;
-	desc = (gate_desc *)host_idt_base + vector;
-	entry = gate_offset(desc);
-
-	kvm_before_interrupt(vcpu);
-
-	asm volatile(
-#ifdef CONFIG_X86_64
-		"mov %%rsp, %[sp]\n\t"
-		"and $-16, %%rsp\n\t"
-		"push %[ss]\n\t"
-		"push %[sp]\n\t"
-#endif
-		"pushf\n\t"
-		"push %[cs]\n\t"
-		CALL_NOSPEC
-		:
-#ifdef CONFIG_X86_64
-		[sp]"=&r"(tmp),
-#endif
-		ASM_CALL_CONSTRAINT
-		:
-		[thunk_target]"r"(entry),
-#ifdef CONFIG_X86_64
-		[ss]"i"(__KERNEL_DS),
-#endif
-		[cs]"i"(__KERNEL_CS)
-	);
-
-	kvm_after_interrupt(vcpu);
+	handle_interrupt_nmi_irqoff(vcpu, intr_info);
 }
-STACK_FRAME_NON_STANDARD(handle_external_interrupt_irqoff);
 
 static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
 {
@@ -6799,9 +6688,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (enable_preemption_timer)
 		vmx_update_hv_timer(vcpu);
 
-	if (lapic_in_kernel(vcpu) &&
-		vcpu->arch.apic->lapic_timer.timer_advance_ns)
-		kvm_wait_lapic_expire(vcpu);
+	kvm_wait_lapic_expire(vcpu);
 
 	/*
 	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
@@ -6945,20 +6832,20 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 			goto free_vpid;
 	}
 
-	BUILD_BUG_ON(ARRAY_SIZE(vmx_msr_index) != NR_SHARED_MSRS);
+	BUILD_BUG_ON(ARRAY_SIZE(vmx_uret_msrs_list) != MAX_NR_USER_RETURN_MSRS);
 
-	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i) {
-		u32 index = vmx_msr_index[i];
+	for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i) {
+		u32 index = vmx_uret_msrs_list[i];
 		u32 data_low, data_high;
-		int j = vmx->nmsrs;
+		int j = vmx->nr_uret_msrs;
 
 		if (rdmsr_safe(index, &data_low, &data_high) < 0)
 			continue;
 		if (wrmsr_safe(index, data_low, data_high) < 0)
 			continue;
 
-		vmx->guest_msrs[j].index = i;
-		vmx->guest_msrs[j].data = 0;
+		vmx->guest_uret_msrs[j].slot = i;
+		vmx->guest_uret_msrs[j].data = 0;
 		switch (index) {
 		case MSR_IA32_TSX_CTRL:
 			/*
@@ -6966,32 +6853,36 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 			 * let's avoid changing CPUID bits under the host
 			 * kernel's feet.
 			 */
-			vmx->guest_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR;
+			vmx->guest_uret_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR;
 			break;
 		default:
-			vmx->guest_msrs[j].mask = -1ull;
+			vmx->guest_uret_msrs[j].mask = -1ull;
 			break;
 		}
-		++vmx->nmsrs;
+		++vmx->nr_uret_msrs;
 	}
 
 	err = alloc_loaded_vmcs(&vmx->vmcs01);
 	if (err < 0)
 		goto free_pml;
 
+	/* The MSR bitmap starts with all ones */
+	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(msr_bitmap, MSR_IA32_TSC, MSR_TYPE_R);
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
-	vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
+	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);
+	vmx_disable_intercept_for_msr(vcpu, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
+	vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
 	if (kvm_cstate_in_guest(vcpu->kvm)) {
-		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C1_RES, MSR_TYPE_R);
-		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R);
-		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R);
-		vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C1_RES, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R);
+		vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R);
 	}
 	vmx->msr_bitmap_mode = 0;
 
@@ -7015,8 +6906,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 	}
 
 	if (nested)
-		nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
-					   vmx_capability.ept);
+		memcpy(&vmx->nested.msrs, &vmcs_config.nested, sizeof(vmx->nested.msrs));
 	else
 		memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs));
 
@@ -7336,11 +7226,11 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		update_intel_pt_cfg(vcpu);
 
 	if (boot_cpu_has(X86_FEATURE_RTM)) {
-		struct shared_msr_entry *msr;
-		msr = find_msr_entry(vmx, MSR_IA32_TSX_CTRL);
+		struct vmx_uret_msr *msr;
+		msr = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL);
 		if (msr) {
 			bool enabled = guest_cpuid_has(vcpu, X86_FEATURE_RTM);
-			vmx_set_guest_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE);
+			vmx_set_guest_uret_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE);
 		}
 	}
 }
@@ -7366,14 +7256,14 @@ static __init void vmx_set_cpu_caps(void)
 
 	/* CPUID 0xD.1 */
 	supported_xss = 0;
-	if (!vmx_xsaves_supported())
+	if (!cpu_has_vmx_xsaves())
 		kvm_cpu_cap_clear(X86_FEATURE_XSAVES);
 
 	/* CPUID 0x80000001 */
 	if (!cpu_has_vmx_rdtscp())
 		kvm_cpu_cap_clear(X86_FEATURE_RDTSCP);
 
-	if (vmx_waitpkg_supported())
+	if (cpu_has_vmx_waitpkg())
 		kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG);
 }
 
@@ -7429,7 +7319,7 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu,
 	 * Because it is marked as EmulateOnUD, we need to intercept it here.
 	 */
 	case x86_intercept_rdtscp:
-		if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_RDTSCP)) {
+		if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_RDTSCP)) {
 			exception->vector = UD_VECTOR;
 			exception->error_code_valid = false;
 			return X86EMUL_PROPAGATE_FAULT;
@@ -7561,107 +7451,6 @@ static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
 	kvm_mmu_clear_dirty_pt_masked(kvm, memslot, offset, mask);
 }
 
-static void __pi_post_block(struct kvm_vcpu *vcpu)
-{
-	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-	struct pi_desc old, new;
-	unsigned int dest;
-
-	do {
-		old.control = new.control = pi_desc->control;
-		WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR,
-		     "Wakeup handler not enabled while the VCPU is blocked\n");
-
-		dest = cpu_physical_id(vcpu->cpu);
-
-		if (x2apic_enabled())
-			new.ndst = dest;
-		else
-			new.ndst = (dest << 8) & 0xFF00;
-
-		/* set 'NV' to 'notification vector' */
-		new.nv = POSTED_INTR_VECTOR;
-	} while (cmpxchg64(&pi_desc->control, old.control,
-			   new.control) != old.control);
-
-	if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) {
-		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
-		list_del(&vcpu->blocked_vcpu_list);
-		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
-		vcpu->pre_pcpu = -1;
-	}
-}
-
-/*
- * This routine does the following things for vCPU which is going
- * to be blocked if VT-d PI is enabled.
- * - Store the vCPU to the wakeup list, so when interrupts happen
- *   we can find the right vCPU to wake up.
- * - Change the Posted-interrupt descriptor as below:
- *      'NDST' <-- vcpu->pre_pcpu
- *      'NV' <-- POSTED_INTR_WAKEUP_VECTOR
- * - If 'ON' is set during this process, which means at least one
- *   interrupt is posted for this vCPU, we cannot block it, in
- *   this case, return 1, otherwise, return 0.
- *
- */
-static int pi_pre_block(struct kvm_vcpu *vcpu)
-{
-	unsigned int dest;
-	struct pi_desc old, new;
-	struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
-
-	if (!kvm_arch_has_assigned_device(vcpu->kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP)  ||
-		!kvm_vcpu_apicv_active(vcpu))
-		return 0;
-
-	WARN_ON(irqs_disabled());
-	local_irq_disable();
-	if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) {
-		vcpu->pre_pcpu = vcpu->cpu;
-		spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
-		list_add_tail(&vcpu->blocked_vcpu_list,
-			      &per_cpu(blocked_vcpu_on_cpu,
-				       vcpu->pre_pcpu));
-		spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
-	}
-
-	do {
-		old.control = new.control = pi_desc->control;
-
-		WARN((pi_desc->sn == 1),
-		     "Warning: SN field of posted-interrupts "
-		     "is set before blocking\n");
-
-		/*
-		 * Since vCPU can be preempted during this process,
-		 * vcpu->cpu could be different with pre_pcpu, we
-		 * need to set pre_pcpu as the destination of wakeup
-		 * notification event, then we can find the right vCPU
-		 * to wakeup in wakeup handler if interrupts happen
-		 * when the vCPU is in blocked state.
-		 */
-		dest = cpu_physical_id(vcpu->pre_pcpu);
-
-		if (x2apic_enabled())
-			new.ndst = dest;
-		else
-			new.ndst = (dest << 8) & 0xFF00;
-
-		/* set 'NV' to 'wakeup vector' */
-		new.nv = POSTED_INTR_WAKEUP_VECTOR;
-	} while (cmpxchg64(&pi_desc->control, old.control,
-			   new.control) != old.control);
-
-	/* We should not block the vCPU if an interrupt is posted for it.  */
-	if (pi_test_on(pi_desc) == 1)
-		__pi_post_block(vcpu);
-
-	local_irq_enable();
-	return (vcpu->pre_pcpu == -1);
-}
-
 static int vmx_pre_block(struct kvm_vcpu *vcpu)
 {
 	if (pi_pre_block(vcpu))
@@ -7673,17 +7462,6 @@ static int vmx_pre_block(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static void pi_post_block(struct kvm_vcpu *vcpu)
-{
-	if (vcpu->pre_pcpu == -1)
-		return;
-
-	WARN_ON(irqs_disabled());
-	local_irq_disable();
-	__pi_post_block(vcpu);
-	local_irq_enable();
-}
-
 static void vmx_post_block(struct kvm_vcpu *vcpu)
 {
 	if (kvm_x86_ops.set_hv_timer)
@@ -7692,100 +7470,6 @@ static void vmx_post_block(struct kvm_vcpu *vcpu)
 	pi_post_block(vcpu);
 }
 
-/*
- * vmx_update_pi_irte - set IRTE for Posted-Interrupts
- *
- * @kvm: kvm
- * @host_irq: host irq of the interrupt
- * @guest_irq: gsi of the interrupt
- * @set: set or unset PI
- * returns 0 on success, < 0 on failure
- */
-static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
-			      uint32_t guest_irq, bool set)
-{
-	struct kvm_kernel_irq_routing_entry *e;
-	struct kvm_irq_routing_table *irq_rt;
-	struct kvm_lapic_irq irq;
-	struct kvm_vcpu *vcpu;
-	struct vcpu_data vcpu_info;
-	int idx, ret = 0;
-
-	if (!kvm_arch_has_assigned_device(kvm) ||
-		!irq_remapping_cap(IRQ_POSTING_CAP) ||
-		!kvm_vcpu_apicv_active(kvm->vcpus[0]))
-		return 0;
-
-	idx = srcu_read_lock(&kvm->irq_srcu);
-	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
-	if (guest_irq >= irq_rt->nr_rt_entries ||
-	    hlist_empty(&irq_rt->map[guest_irq])) {
-		pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
-			     guest_irq, irq_rt->nr_rt_entries);
-		goto out;
-	}
-
-	hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
-		if (e->type != KVM_IRQ_ROUTING_MSI)
-			continue;
-		/*
-		 * VT-d PI cannot support posting multicast/broadcast
-		 * interrupts to a vCPU, we still use interrupt remapping
-		 * for these kind of interrupts.
-		 *
-		 * For lowest-priority interrupts, we only support
-		 * those with single CPU as the destination, e.g. user
-		 * configures the interrupts via /proc/irq or uses
-		 * irqbalance to make the interrupts single-CPU.
-		 *
-		 * We will support full lowest-priority interrupt later.
-		 *
-		 * In addition, we can only inject generic interrupts using
-		 * the PI mechanism, refuse to route others through it.
-		 */
-
-		kvm_set_msi_irq(kvm, e, &irq);
-		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
-		    !kvm_irq_is_postable(&irq)) {
-			/*
-			 * Make sure the IRTE is in remapped mode if
-			 * we don't handle it in posted mode.
-			 */
-			ret = irq_set_vcpu_affinity(host_irq, NULL);
-			if (ret < 0) {
-				printk(KERN_INFO
-				   "failed to back to remapped mode, irq: %u\n",
-				   host_irq);
-				goto out;
-			}
-
-			continue;
-		}
-
-		vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
-		vcpu_info.vector = irq.vector;
-
-		trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
-				vcpu_info.vector, vcpu_info.pi_desc_addr, set);
-
-		if (set)
-			ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
-		else
-			ret = irq_set_vcpu_affinity(host_irq, NULL);
-
-		if (ret < 0) {
-			printk(KERN_INFO "%s: failed to update PI IRTE\n",
-					__func__);
-			goto out;
-		}
-	}
-
-	ret = 0;
-out:
-	srcu_read_unlock(&kvm->irq_srcu, idx);
-	return ret;
-}
-
 static void vmx_setup_mce(struct kvm_vcpu *vcpu)
 {
 	if (vcpu->arch.mcg_cap & MCG_LMCE_P)
@@ -7843,11 +7527,6 @@ static void enable_smi_window(struct kvm_vcpu *vcpu)
 	/* RSM will cause a vmexit anyway.  */
 }
 
-static bool vmx_need_emulation_on_page_fault(struct kvm_vcpu *vcpu)
-{
-	return false;
-}
-
 static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
 {
 	return to_vmx(vcpu)->nested.vmxon;
@@ -7954,7 +7633,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
 	.sync_pir_to_irr = vmx_sync_pir_to_irr,
 	.deliver_posted_interrupt = vmx_deliver_posted_interrupt,
-	.dy_apicv_has_pending_interrupt = vmx_dy_apicv_has_pending_interrupt,
+	.dy_apicv_has_pending_interrupt = pi_has_pending_interrupt,
 
 	.set_tss_addr = vmx_set_tss_addr,
 	.set_identity_map_addr = vmx_set_identity_map_addr,
@@ -7988,7 +7667,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.pmu_ops = &intel_pmu_ops,
 	.nested_ops = &vmx_nested_ops,
 
-	.update_pi_irte = vmx_update_pi_irte,
+	.update_pi_irte = pi_update_irte,
 
 #ifdef CONFIG_X86_64
 	.set_hv_timer = vmx_set_hv_timer,
@@ -8002,9 +7681,11 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.pre_leave_smm = vmx_pre_leave_smm,
 	.enable_smi_window = enable_smi_window,
 
-	.need_emulation_on_page_fault = vmx_need_emulation_on_page_fault,
+	.can_emulate_instruction = vmx_can_emulate_instruction,
 	.apic_init_signal_blocked = vmx_apic_init_signal_blocked,
 	.migrate_timers = vmx_migrate_timers,
+
+	.msr_filter_changed = vmx_msr_filter_changed,
 };
 
 static __init int hardware_setup(void)
@@ -8016,8 +7697,8 @@ static __init int hardware_setup(void)
 	store_idt(&dt);
 	host_idt_base = dt.address;
 
-	for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i)
-		kvm_define_shared_msr(i, vmx_msr_index[i]);
+	for (i = 0; i < ARRAY_SIZE(vmx_uret_msrs_list); ++i)
+		kvm_define_user_return_msr(i, vmx_uret_msrs_list[i]);
 
 	if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0)
 		return -EIO;
@@ -8154,7 +7835,7 @@ static __init int hardware_setup(void)
 		vmx_x86_ops.request_immediate_exit = __kvm_request_immediate_exit;
 	}
 
-	kvm_set_posted_intr_wakeup_handler(wakeup_handler);
+	kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler);
 
 	kvm_mce_cap_supported |= MCG_LMCE_P;
 
@@ -8293,8 +7974,8 @@ static int __init vmx_init(void)
 
 	for_each_possible_cpu(cpu) {
 		INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
-		INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
-		spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+
+		pi_init(cpu);
 	}
 
 #ifdef CONFIG_KEXEC_CORE
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 26175a4..5961cb8 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -9,8 +9,9 @@
 
 #include "capabilities.h"
 #include "kvm_cache_regs.h"
-#include "ops.h"
+#include "posted_intr.h"
 #include "vmcs.h"
+#include "vmx_ops.h"
 #include "cpuid.h"
 
 extern const u32 vmx_msr_index[];
@@ -22,20 +23,20 @@ extern const u32 vmx_msr_index[];
 #define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4))
 
 #ifdef CONFIG_X86_64
-#define NR_SHARED_MSRS	7
+#define MAX_NR_USER_RETURN_MSRS	7
 #else
-#define NR_SHARED_MSRS	4
+#define MAX_NR_USER_RETURN_MSRS	4
 #endif
 
-#define NR_LOADSTORE_MSRS 8
+#define MAX_NR_LOADSTORE_MSRS	8
 
 struct vmx_msrs {
 	unsigned int		nr;
-	struct vmx_msr_entry	val[NR_LOADSTORE_MSRS];
+	struct vmx_msr_entry	val[MAX_NR_LOADSTORE_MSRS];
 };
 
-struct shared_msr_entry {
-	unsigned index;
+struct vmx_uret_msr {
+	unsigned int slot; /* The MSR's slot in kvm_user_return_msrs. */
 	u64 data;
 	u64 mask;
 };
@@ -49,29 +50,6 @@ enum segment_cache_field {
 	SEG_FIELD_NR = 4
 };
 
-/* Posted-Interrupt Descriptor */
-struct pi_desc {
-	u32 pir[8];     /* Posted interrupt requested */
-	union {
-		struct {
-				/* bit 256 - Outstanding Notification */
-			u16	on	: 1,
-				/* bit 257 - Suppress Notification */
-				sn	: 1,
-				/* bit 271:258 - Reserved */
-				rsvd_1	: 14;
-				/* bit 279:272 - Notification Vector */
-			u8	nv;
-				/* bit 287:280 - Reserved */
-			u8	rsvd_2;
-				/* bit 319:288 - Notification Destination */
-			u32	ndst;
-		};
-		u64 control;
-	};
-	u32 rsvd[6];
-} __aligned(64);
-
 #define RTIT_ADDR_RANGE		4
 
 struct pt_ctx {
@@ -218,10 +196,10 @@ struct vcpu_vmx {
 	u32                   idt_vectoring_info;
 	ulong                 rflags;
 
-	struct shared_msr_entry guest_msrs[NR_SHARED_MSRS];
-	int                   nmsrs;
-	int                   save_nmsrs;
-	bool                  guest_msrs_ready;
+	struct vmx_uret_msr   guest_uret_msrs[MAX_NR_USER_RETURN_MSRS];
+	int                   nr_uret_msrs;
+	int                   nr_active_uret_msrs;
+	bool                  guest_uret_msrs_loaded;
 #ifdef CONFIG_X86_64
 	u64		      msr_host_kernel_gs_base;
 	u64		      msr_guest_kernel_gs_base;
@@ -301,6 +279,13 @@ struct vcpu_vmx {
 	u64 ept_pointer;
 
 	struct pt_desc pt_desc;
+
+	/* Save desired MSR intercept (read: pass-through) state */
+#define MAX_POSSIBLE_PASSTHROUGH_MSRS	13
+	struct {
+		DECLARE_BITMAP(read, MAX_POSSIBLE_PASSTHROUGH_MSRS);
+		DECLARE_BITMAP(write, MAX_POSSIBLE_PASSTHROUGH_MSRS);
+	} shadow_msr_intercept;
 };
 
 enum ept_pointers_status {
@@ -343,6 +328,7 @@ void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
 void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
 u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa,
 		   int root_level);
+
 void update_exception_bitmap(struct kvm_vcpu *vcpu);
 void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu);
 bool vmx_nmi_blocked(struct kvm_vcpu *vcpu);
@@ -350,73 +336,11 @@ bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu);
 bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu);
 void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
 void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
-struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr);
-void pt_update_intercept_for_msr(struct vcpu_vmx *vmx);
+struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr);
+void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu);
 void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp);
-int vmx_find_msr_index(struct vmx_msrs *m, u32 msr);
-int vmx_handle_memory_failure(struct kvm_vcpu *vcpu, int r,
-			      struct x86_exception *e);
-
-#define POSTED_INTR_ON  0
-#define POSTED_INTR_SN  1
-
-static inline bool pi_test_and_set_on(struct pi_desc *pi_desc)
-{
-	return test_and_set_bit(POSTED_INTR_ON,
-			(unsigned long *)&pi_desc->control);
-}
-
-static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc)
-{
-	return test_and_clear_bit(POSTED_INTR_ON,
-			(unsigned long *)&pi_desc->control);
-}
-
-static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
-{
-	return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
-}
-
-static inline bool pi_is_pir_empty(struct pi_desc *pi_desc)
-{
-	return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS);
-}
-
-static inline void pi_set_sn(struct pi_desc *pi_desc)
-{
-	set_bit(POSTED_INTR_SN,
-		(unsigned long *)&pi_desc->control);
-}
-
-static inline void pi_set_on(struct pi_desc *pi_desc)
-{
-	set_bit(POSTED_INTR_ON,
-		(unsigned long *)&pi_desc->control);
-}
-
-static inline void pi_clear_on(struct pi_desc *pi_desc)
-{
-	clear_bit(POSTED_INTR_ON,
-		(unsigned long *)&pi_desc->control);
-}
-
-static inline void pi_clear_sn(struct pi_desc *pi_desc)
-{
-	clear_bit(POSTED_INTR_SN,
-		(unsigned long *)&pi_desc->control);
-}
-
-static inline int pi_test_on(struct pi_desc *pi_desc)
-{
-	return test_bit(POSTED_INTR_ON,
-			(unsigned long *)&pi_desc->control);
-}
-
-static inline int pi_test_sn(struct pi_desc *pi_desc)
-{
-	return test_bit(POSTED_INTR_SN,
-			(unsigned long *)&pi_desc->control);
-}
+int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr);
+void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu);
 
 static inline u8 vmx_get_rvi(void)
 {
@@ -498,11 +422,6 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
 	return container_of(vcpu, struct vcpu_vmx, vcpu);
 }
 
-static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
-{
-	return &(to_vmx(vcpu)->pi_desc);
-}
-
 static inline unsigned long vmx_get_exit_qual(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -554,6 +473,19 @@ static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu)
 	return !enable_ept || cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits;
 }
 
+static inline bool is_unrestricted_guest(struct kvm_vcpu *vcpu)
+{
+	return enable_unrestricted_guest && (!is_guest_mode(vcpu) ||
+	    (secondary_exec_controls_get(to_vmx(vcpu)) &
+	    SECONDARY_EXEC_UNRESTRICTED_GUEST));
+}
+
+bool __vmx_guest_state_valid(struct kvm_vcpu *vcpu);
+static inline bool vmx_guest_state_valid(struct kvm_vcpu *vcpu)
+{
+	return is_unrestricted_guest(vcpu) || __vmx_guest_state_valid(vcpu);
+}
+
 void dump_vmcs(void);
 
 #endif /* __KVM_X86_VMX_H */
diff --git a/arch/x86/kvm/vmx/ops.h b/arch/x86/kvm/vmx/vmx_ops.h
similarity index 100%
rename from arch/x86/kvm/vmx/ops.h
rename to arch/x86/kvm/vmx/vmx_ops.h
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7527022..c4015a4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -71,6 +71,7 @@
 #include <asm/irq_remapping.h>
 #include <asm/mshyperv.h>
 #include <asm/hypervisor.h>
+#include <asm/tlbflush.h>
 #include <asm/intel_pt.h>
 #include <asm/emulate_prefix.h>
 #include <clocksource/hyperv_timer.h>
@@ -161,24 +162,29 @@ module_param(force_emulation_prefix, bool, S_IRUGO);
 int __read_mostly pi_inject_timer = -1;
 module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR);
 
-#define KVM_NR_SHARED_MSRS 16
+/*
+ * Restoring the host value for MSRs that are only consumed when running in
+ * usermode, e.g. SYSCALL MSRs and TSC_AUX, can be deferred until the CPU
+ * returns to userspace, i.e. the kernel can run with the guest's value.
+ */
+#define KVM_MAX_NR_USER_RETURN_MSRS 16
 
-struct kvm_shared_msrs_global {
+struct kvm_user_return_msrs_global {
 	int nr;
-	u32 msrs[KVM_NR_SHARED_MSRS];
+	u32 msrs[KVM_MAX_NR_USER_RETURN_MSRS];
 };
 
-struct kvm_shared_msrs {
+struct kvm_user_return_msrs {
 	struct user_return_notifier urn;
 	bool registered;
-	struct kvm_shared_msr_values {
+	struct kvm_user_return_msr_values {
 		u64 host;
 		u64 curr;
-	} values[KVM_NR_SHARED_MSRS];
+	} values[KVM_MAX_NR_USER_RETURN_MSRS];
 };
 
-static struct kvm_shared_msrs_global __read_mostly shared_msrs_global;
-static struct kvm_shared_msrs __percpu *shared_msrs;
+static struct kvm_user_return_msrs_global __read_mostly user_return_msrs_global;
+static struct kvm_user_return_msrs __percpu *user_return_msrs;
 
 #define KVM_SUPPORTED_XCR0     (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \
 				| XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \
@@ -266,7 +272,7 @@ static int kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr,
 	} else {
 		vcpu_debug_ratelimited(vcpu, "unhandled %s: 0x%x data 0x%llx\n",
 				       op, msr, data);
-		return 1;
+		return -ENOENT;
 	}
 }
 
@@ -293,9 +299,9 @@ static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu)
 static void kvm_on_user_return(struct user_return_notifier *urn)
 {
 	unsigned slot;
-	struct kvm_shared_msrs *locals
-		= container_of(urn, struct kvm_shared_msrs, urn);
-	struct kvm_shared_msr_values *values;
+	struct kvm_user_return_msrs *msrs
+		= container_of(urn, struct kvm_user_return_msrs, urn);
+	struct kvm_user_return_msr_values *values;
 	unsigned long flags;
 
 	/*
@@ -303,73 +309,73 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 	 * interrupted and executed through kvm_arch_hardware_disable()
 	 */
 	local_irq_save(flags);
-	if (locals->registered) {
-		locals->registered = false;
+	if (msrs->registered) {
+		msrs->registered = false;
 		user_return_notifier_unregister(urn);
 	}
 	local_irq_restore(flags);
-	for (slot = 0; slot < shared_msrs_global.nr; ++slot) {
-		values = &locals->values[slot];
+	for (slot = 0; slot < user_return_msrs_global.nr; ++slot) {
+		values = &msrs->values[slot];
 		if (values->host != values->curr) {
-			wrmsrl(shared_msrs_global.msrs[slot], values->host);
+			wrmsrl(user_return_msrs_global.msrs[slot], values->host);
 			values->curr = values->host;
 		}
 	}
 }
 
-void kvm_define_shared_msr(unsigned slot, u32 msr)
+void kvm_define_user_return_msr(unsigned slot, u32 msr)
 {
-	BUG_ON(slot >= KVM_NR_SHARED_MSRS);
-	shared_msrs_global.msrs[slot] = msr;
-	if (slot >= shared_msrs_global.nr)
-		shared_msrs_global.nr = slot + 1;
+	BUG_ON(slot >= KVM_MAX_NR_USER_RETURN_MSRS);
+	user_return_msrs_global.msrs[slot] = msr;
+	if (slot >= user_return_msrs_global.nr)
+		user_return_msrs_global.nr = slot + 1;
 }
-EXPORT_SYMBOL_GPL(kvm_define_shared_msr);
+EXPORT_SYMBOL_GPL(kvm_define_user_return_msr);
 
-static void kvm_shared_msr_cpu_online(void)
+static void kvm_user_return_msr_cpu_online(void)
 {
 	unsigned int cpu = smp_processor_id();
-	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
+	struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu);
 	u64 value;
 	int i;
 
-	for (i = 0; i < shared_msrs_global.nr; ++i) {
-		rdmsrl_safe(shared_msrs_global.msrs[i], &value);
-		smsr->values[i].host = value;
-		smsr->values[i].curr = value;
+	for (i = 0; i < user_return_msrs_global.nr; ++i) {
+		rdmsrl_safe(user_return_msrs_global.msrs[i], &value);
+		msrs->values[i].host = value;
+		msrs->values[i].curr = value;
 	}
 }
 
-int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
+int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask)
 {
 	unsigned int cpu = smp_processor_id();
-	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
+	struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu);
 	int err;
 
-	value = (value & mask) | (smsr->values[slot].host & ~mask);
-	if (value == smsr->values[slot].curr)
+	value = (value & mask) | (msrs->values[slot].host & ~mask);
+	if (value == msrs->values[slot].curr)
 		return 0;
-	err = wrmsrl_safe(shared_msrs_global.msrs[slot], value);
+	err = wrmsrl_safe(user_return_msrs_global.msrs[slot], value);
 	if (err)
 		return 1;
 
-	smsr->values[slot].curr = value;
-	if (!smsr->registered) {
-		smsr->urn.on_user_return = kvm_on_user_return;
-		user_return_notifier_register(&smsr->urn);
-		smsr->registered = true;
+	msrs->values[slot].curr = value;
+	if (!msrs->registered) {
+		msrs->urn.on_user_return = kvm_on_user_return;
+		user_return_notifier_register(&msrs->urn);
+		msrs->registered = true;
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
+EXPORT_SYMBOL_GPL(kvm_set_user_return_msr);
 
 static void drop_user_return_notifiers(void)
 {
 	unsigned int cpu = smp_processor_id();
-	struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
+	struct kvm_user_return_msrs *msrs = per_cpu_ptr(user_return_msrs, cpu);
 
-	if (smsr->registered)
-		kvm_on_user_return(&smsr->urn);
+	if (msrs->registered)
+		kvm_on_user_return(&msrs->urn);
 }
 
 u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
@@ -1482,6 +1488,40 @@ void kvm_enable_efer_bits(u64 mask)
 }
 EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
 
+bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges;
+	u32 count = kvm->arch.msr_filter.count;
+	u32 i;
+	bool r = kvm->arch.msr_filter.default_allow;
+	int idx;
+
+	/* MSR filtering not set up, allow everything */
+	if (!count)
+		return true;
+
+	/* Prevent collision with set_msr_filter */
+	idx = srcu_read_lock(&kvm->srcu);
+
+	for (i = 0; i < count; i++) {
+		u32 start = ranges[i].base;
+		u32 end = start + ranges[i].nmsrs;
+		u32 flags = ranges[i].flags;
+		unsigned long *bitmap = ranges[i].bitmap;
+
+		if ((index >= start) && (index < end) && (flags & type)) {
+			r = !!test_bit(index - start, bitmap);
+			break;
+		}
+	}
+
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(kvm_msr_allowed);
+
 /*
  * Write @data into the MSR specified by @index.  Select MSR specific fault
  * checks are bypassed if @host_initiated is %true.
@@ -1493,6 +1533,9 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
 {
 	struct msr_data msr;
 
+	if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE))
+		return -EPERM;
+
 	switch (index) {
 	case MSR_FS_BASE:
 	case MSR_GS_BASE:
@@ -1549,6 +1592,9 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
 	struct msr_data msr;
 	int ret;
 
+	if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ))
+		return -EPERM;
+
 	msr.index = index;
 	msr.host_initiated = host_initiated;
 
@@ -1584,12 +1630,91 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data)
 }
 EXPORT_SYMBOL_GPL(kvm_set_msr);
 
+static int complete_emulated_msr(struct kvm_vcpu *vcpu, bool is_read)
+{
+	if (vcpu->run->msr.error) {
+		kvm_inject_gp(vcpu, 0);
+		return 1;
+	} else if (is_read) {
+		kvm_rax_write(vcpu, (u32)vcpu->run->msr.data);
+		kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32);
+	}
+
+	return kvm_skip_emulated_instruction(vcpu);
+}
+
+static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu)
+{
+	return complete_emulated_msr(vcpu, true);
+}
+
+static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu)
+{
+	return complete_emulated_msr(vcpu, false);
+}
+
+static u64 kvm_msr_reason(int r)
+{
+	switch (r) {
+	case -ENOENT:
+		return KVM_MSR_EXIT_REASON_UNKNOWN;
+	case -EPERM:
+		return KVM_MSR_EXIT_REASON_FILTER;
+	default:
+		return KVM_MSR_EXIT_REASON_INVAL;
+	}
+}
+
+static int kvm_msr_user_space(struct kvm_vcpu *vcpu, u32 index,
+			      u32 exit_reason, u64 data,
+			      int (*completion)(struct kvm_vcpu *vcpu),
+			      int r)
+{
+	u64 msr_reason = kvm_msr_reason(r);
+
+	/* Check if the user wanted to know about this MSR fault */
+	if (!(vcpu->kvm->arch.user_space_msr_mask & msr_reason))
+		return 0;
+
+	vcpu->run->exit_reason = exit_reason;
+	vcpu->run->msr.error = 0;
+	memset(vcpu->run->msr.pad, 0, sizeof(vcpu->run->msr.pad));
+	vcpu->run->msr.reason = msr_reason;
+	vcpu->run->msr.index = index;
+	vcpu->run->msr.data = data;
+	vcpu->arch.complete_userspace_io = completion;
+
+	return 1;
+}
+
+static int kvm_get_msr_user_space(struct kvm_vcpu *vcpu, u32 index, int r)
+{
+	return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_RDMSR, 0,
+				   complete_emulated_rdmsr, r);
+}
+
+static int kvm_set_msr_user_space(struct kvm_vcpu *vcpu, u32 index, u64 data, int r)
+{
+	return kvm_msr_user_space(vcpu, index, KVM_EXIT_X86_WRMSR, data,
+				   complete_emulated_wrmsr, r);
+}
+
 int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu)
 {
 	u32 ecx = kvm_rcx_read(vcpu);
 	u64 data;
+	int r;
 
-	if (kvm_get_msr(vcpu, ecx, &data)) {
+	r = kvm_get_msr(vcpu, ecx, &data);
+
+	/* MSR read failed? See if we should ask user space */
+	if (r && kvm_get_msr_user_space(vcpu, ecx, r)) {
+		/* Bounce to user space */
+		return 0;
+	}
+
+	/* MSR read failed? Inject a #GP */
+	if (r) {
 		trace_kvm_msr_read_ex(ecx);
 		kvm_inject_gp(vcpu, 0);
 		return 1;
@@ -1607,8 +1732,18 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu)
 {
 	u32 ecx = kvm_rcx_read(vcpu);
 	u64 data = kvm_read_edx_eax(vcpu);
+	int r;
 
-	if (kvm_set_msr(vcpu, ecx, data)) {
+	r = kvm_set_msr(vcpu, ecx, data);
+
+	/* MSR write failed? See if we should ask user space */
+	if (r && kvm_set_msr_user_space(vcpu, ecx, data, r)) {
+		/* Bounce to user space */
+		return 0;
+	}
+
+	/* MSR write failed? Inject a #GP */
+	if (r) {
 		trace_kvm_msr_write_ex(ecx, data);
 		kvm_inject_gp(vcpu, 0);
 		return 1;
@@ -1774,12 +1909,6 @@ static s64 get_kvmclock_base_ns(void)
 }
 #endif
 
-void kvm_set_pending_timer(struct kvm_vcpu *vcpu)
-{
-	kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
-	kvm_vcpu_kick(vcpu);
-}
-
 static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 {
 	int version;
@@ -1978,12 +2107,6 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
 #endif
 }
 
-static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset)
-{
-	u64 curr_offset = vcpu->arch.l1_tsc_offset;
-	vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset;
-}
-
 /*
  * Multiply tsc by a fixed point number represented by ratio.
  *
@@ -2045,14 +2168,13 @@ static inline bool kvm_check_tsc_unstable(void)
 	return check_tsc_unstable();
 }
 
-void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
+static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
 {
 	struct kvm *kvm = vcpu->kvm;
 	u64 offset, ns, elapsed;
 	unsigned long flags;
 	bool matched;
 	bool already_matched;
-	u64 data = msr->data;
 	bool synchronizing = false;
 
 	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
@@ -2061,7 +2183,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	elapsed = ns - kvm->arch.last_tsc_nsec;
 
 	if (vcpu->arch.virtual_tsc_khz) {
-		if (data == 0 && msr->host_initiated) {
+		if (data == 0) {
 			/*
 			 * detection of vcpu initialization -- need to sync
 			 * with other vCPUs. This particularly helps to keep
@@ -2131,9 +2253,6 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec;
 	vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write;
 
-	if (!msr->host_initiated && guest_cpuid_has(vcpu, X86_FEATURE_TSC_ADJUST))
-		update_ia32_tsc_adjust_msr(vcpu, offset);
-
 	kvm_vcpu_write_tsc_offset(vcpu, offset);
 	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
 
@@ -2148,8 +2267,6 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	spin_unlock(&kvm->arch.pvclock_gtod_sync_lock);
 }
 
-EXPORT_SYMBOL_GPL(kvm_write_tsc);
-
 static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
 					   s64 adjustment)
 {
@@ -2731,7 +2848,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 		return 1;
 
 	if (!lapic_in_kernel(vcpu))
-		return 1;
+		return data ? 1 : 0;
 
 	vcpu->arch.apf.msr_en_val = data;
 
@@ -2944,7 +3061,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vcpu->arch.msr_ia32_power_ctl = data;
 		break;
 	case MSR_IA32_TSC:
-		kvm_write_tsc(vcpu, msr_info);
+		if (msr_info->host_initiated) {
+			kvm_synchronize_tsc(vcpu, data);
+		} else {
+			u64 adj = kvm_compute_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset;
+			adjust_tsc_offset_guest(vcpu, adj);
+			vcpu->arch.ia32_tsc_adjust_msr += adj;
+		}
 		break;
 	case MSR_IA32_XSS:
 		if (!msr_info->host_initiated &&
@@ -3221,9 +3344,22 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_POWER_CTL:
 		msr_info->data = vcpu->arch.msr_ia32_power_ctl;
 		break;
-	case MSR_IA32_TSC:
-		msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset;
+	case MSR_IA32_TSC: {
+		/*
+		 * Intel SDM states that MSR_IA32_TSC read adds the TSC offset
+		 * even when not intercepted. AMD manual doesn't explicitly
+		 * state this but appears to behave the same.
+		 *
+		 * Unconditionally return L1's TSC offset on userspace reads
+		 * so that userspace reads and writes always operate on L1's
+		 * offset, e.g. to ensure deterministic behavior for migration.
+		 */
+		u64 tsc_offset = msr_info->host_initiated ? vcpu->arch.l1_tsc_offset :
+							    vcpu->arch.tsc_offset;
+
+		msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + tsc_offset;
 		break;
+	}
 	case MSR_MTRRcap:
 	case 0x200 ... 0x2ff:
 		return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data);
@@ -3513,6 +3649,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_EXCEPTION_PAYLOAD:
 	case KVM_CAP_SET_GUEST_DEBUG:
 	case KVM_CAP_LAST_CPU:
+	case KVM_CAP_X86_USER_SPACE_MSR:
+	case KVM_CAP_X86_MSR_FILTER:
 		r = 1;
 		break;
 	case KVM_CAP_SYNC_REGS:
@@ -5033,6 +5171,10 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 		kvm->arch.exception_payload_enabled = cap->args[0];
 		r = 0;
 		break;
+	case KVM_CAP_X86_USER_SPACE_MSR:
+		kvm->arch.user_space_msr_mask = cap->args[0];
+		r = 0;
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -5040,6 +5182,103 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 	return r;
 }
 
+static void kvm_clear_msr_filter(struct kvm *kvm)
+{
+	u32 i;
+	u32 count = kvm->arch.msr_filter.count;
+	struct msr_bitmap_range ranges[16];
+
+	mutex_lock(&kvm->lock);
+	kvm->arch.msr_filter.count = 0;
+	memcpy(ranges, kvm->arch.msr_filter.ranges, count * sizeof(ranges[0]));
+	mutex_unlock(&kvm->lock);
+	synchronize_srcu(&kvm->srcu);
+
+	for (i = 0; i < count; i++)
+		kfree(ranges[i].bitmap);
+}
+
+static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user_range)
+{
+	struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges;
+	struct msr_bitmap_range range;
+	unsigned long *bitmap = NULL;
+	size_t bitmap_size;
+	int r;
+
+	if (!user_range->nmsrs)
+		return 0;
+
+	bitmap_size = BITS_TO_LONGS(user_range->nmsrs) * sizeof(long);
+	if (!bitmap_size || bitmap_size > KVM_MSR_FILTER_MAX_BITMAP_SIZE)
+		return -EINVAL;
+
+	bitmap = memdup_user((__user u8*)user_range->bitmap, bitmap_size);
+	if (IS_ERR(bitmap))
+		return PTR_ERR(bitmap);
+
+	range = (struct msr_bitmap_range) {
+		.flags = user_range->flags,
+		.base = user_range->base,
+		.nmsrs = user_range->nmsrs,
+		.bitmap = bitmap,
+	};
+
+	if (range.flags & ~(KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE)) {
+		r = -EINVAL;
+		goto err;
+	}
+
+	if (!range.flags) {
+		r = -EINVAL;
+		goto err;
+	}
+
+	/* Everything ok, add this range identifier to our global pool */
+	ranges[kvm->arch.msr_filter.count] = range;
+	/* Make sure we filled the array before we tell anyone to walk it */
+	smp_wmb();
+	kvm->arch.msr_filter.count++;
+
+	return 0;
+err:
+	kfree(bitmap);
+	return r;
+}
+
+static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
+{
+	struct kvm_msr_filter __user *user_msr_filter = argp;
+	struct kvm_msr_filter filter;
+	bool default_allow;
+	int r = 0;
+	u32 i;
+
+	if (copy_from_user(&filter, user_msr_filter, sizeof(filter)))
+		return -EFAULT;
+
+	kvm_clear_msr_filter(kvm);
+
+	default_allow = !(filter.flags & KVM_MSR_FILTER_DEFAULT_DENY);
+	kvm->arch.msr_filter.default_allow = default_allow;
+
+	/*
+	 * Protect from concurrent calls to this function that could trigger
+	 * a TOCTOU violation on kvm->arch.msr_filter.count.
+	 */
+	mutex_lock(&kvm->lock);
+	for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) {
+		r = kvm_add_msr_filter(kvm, &filter.ranges[i]);
+		if (r)
+			break;
+	}
+
+	kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED);
+	mutex_unlock(&kvm->lock);
+
+	return r;
+}
+
 long kvm_arch_vm_ioctl(struct file *filp,
 		       unsigned int ioctl, unsigned long arg)
 {
@@ -5346,6 +5585,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	case KVM_SET_PMU_EVENT_FILTER:
 		r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp);
 		break;
+	case KVM_X86_SET_MSR_FILTER:
+		r = kvm_vm_ioctl_set_msr_filter(kvm, argp);
+		break;
 	default:
 		r = -ENOTTY;
 	}
@@ -5707,6 +5949,9 @@ int handle_ud(struct kvm_vcpu *vcpu)
 	char sig[5]; /* ud2; .ascii "kvm" */
 	struct x86_exception e;
 
+	if (unlikely(!kvm_x86_ops.can_emulate_instruction(vcpu, NULL, 0)))
+		return 1;
+
 	if (force_emulation_prefix &&
 	    kvm_read_guest_virt(vcpu, kvm_get_linear_rip(vcpu),
 				sig, sizeof(sig), &e) == 0 &&
@@ -6362,13 +6607,33 @@ static void emulator_set_segment(struct x86_emulate_ctxt *ctxt, u16 selector,
 static int emulator_get_msr(struct x86_emulate_ctxt *ctxt,
 			    u32 msr_index, u64 *pdata)
 {
-	return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata);
+	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+	int r;
+
+	r = kvm_get_msr(vcpu, msr_index, pdata);
+
+	if (r && kvm_get_msr_user_space(vcpu, msr_index, r)) {
+		/* Bounce to user space */
+		return X86EMUL_IO_NEEDED;
+	}
+
+	return r;
 }
 
 static int emulator_set_msr(struct x86_emulate_ctxt *ctxt,
 			    u32 msr_index, u64 data)
 {
-	return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data);
+	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+	int r;
+
+	r = kvm_set_msr(vcpu, msr_index, data);
+
+	if (r && kvm_set_msr_user_space(vcpu, msr_index, data, r)) {
+		/* Bounce to user space */
+		return X86EMUL_IO_NEEDED;
+	}
+
+	return r;
 }
 
 static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt)
@@ -6912,7 +7177,10 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 	int r;
 	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
 	bool writeback = true;
-	bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable;
+	bool write_fault_to_spt;
+
+	if (unlikely(!kvm_x86_ops.can_emulate_instruction(vcpu, insn, insn_len)))
+		return 1;
 
 	vcpu->arch.l1tf_flush_l1d = true;
 
@@ -6920,6 +7188,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 	 * Clear write_fault_to_shadow_pgtable here to ensure it is
 	 * never reused.
 	 */
+	write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable;
 	vcpu->arch.write_fault_to_shadow_pgtable = false;
 	kvm_clear_exception_queue(vcpu);
 
@@ -7514,9 +7783,9 @@ int kvm_arch_init(void *opaque)
 		goto out_free_x86_fpu_cache;
 	}
 
-	shared_msrs = alloc_percpu(struct kvm_shared_msrs);
-	if (!shared_msrs) {
-		printk(KERN_ERR "kvm: failed to allocate percpu kvm_shared_msrs\n");
+	user_return_msrs = alloc_percpu(struct kvm_user_return_msrs);
+	if (!user_return_msrs) {
+		printk(KERN_ERR "kvm: failed to allocate percpu kvm_user_return_msrs\n");
 		goto out_free_x86_emulator_cache;
 	}
 
@@ -7549,7 +7818,7 @@ int kvm_arch_init(void *opaque)
 	return 0;
 
 out_free_percpu:
-	free_percpu(shared_msrs);
+	free_percpu(user_return_msrs);
 out_free_x86_emulator_cache:
 	kmem_cache_destroy(x86_emulator_cache);
 out_free_x86_fpu_cache:
@@ -7576,7 +7845,7 @@ void kvm_arch_exit(void)
 #endif
 	kvm_x86_ops.hardware_enable = NULL;
 	kvm_mmu_module_exit();
-	free_percpu(shared_msrs);
+	free_percpu(user_return_msrs);
 	kmem_cache_destroy(x86_fpu_cache);
 }
 
@@ -8365,8 +8634,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	bool req_immediate_exit = false;
 
 	if (kvm_request_pending(vcpu)) {
-		if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) {
-			if (unlikely(!kvm_x86_ops.nested_ops->get_vmcs12_pages(vcpu))) {
+		if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
+			if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) {
 				r = 0;
 				goto out;
 			}
@@ -8473,6 +8742,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_vcpu_update_apicv(vcpu);
 		if (kvm_check_request(KVM_REQ_APF_READY, vcpu))
 			kvm_check_async_pf_completion(vcpu);
+		if (kvm_check_request(KVM_REQ_MSR_FILTER_CHANGED, vcpu))
+			kvm_x86_ops.msr_filter_changed(vcpu);
 	}
 
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
@@ -8548,7 +8819,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		kvm_x86_ops.request_immediate_exit(vcpu);
 	}
 
-	trace_kvm_entry(vcpu->vcpu_id);
+	trace_kvm_entry(vcpu);
 
 	fpregs_assert_state_consistent();
 	if (test_thread_flag(TIF_NEED_FPU_LOAD))
@@ -9562,7 +9833,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
-	struct msr_data msr;
 	struct kvm *kvm = vcpu->kvm;
 
 	kvm_hv_vcpu_postcreate(vcpu);
@@ -9570,10 +9840,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 	if (mutex_lock_killable(&vcpu->mutex))
 		return;
 	vcpu_load(vcpu);
-	msr.data = 0x0;
-	msr.index = MSR_IA32_TSC;
-	msr.host_initiated = true;
-	kvm_write_tsc(vcpu, &msr);
+	kvm_synchronize_tsc(vcpu, 0);
 	vcpu_put(vcpu);
 
 	/* poll control enabled by default */
@@ -9707,7 +9974,7 @@ int kvm_arch_hardware_enable(void)
 	u64 max_tsc = 0;
 	bool stable, backwards_tsc = false;
 
-	kvm_shared_msr_cpu_online();
+	kvm_user_return_msr_cpu_online();
 	ret = kvm_x86_ops.hardware_enable();
 	if (ret != 0)
 		return ret;
@@ -10025,6 +10292,8 @@ void kvm_arch_pre_destroy_vm(struct kvm *kvm)
 
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
+	u32 i;
+
 	if (current->mm == kvm->mm) {
 		/*
 		 * Free memory regions allocated on behalf of userspace,
@@ -10041,6 +10310,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	}
 	if (kvm_x86_ops.vm_destroy)
 		kvm_x86_ops.vm_destroy(kvm);
+	for (i = 0; i < kvm->arch.msr_filter.count; i++)
+		kfree(kvm->arch.msr_filter.ranges[i].bitmap);
 	kvm_pic_destroy(kvm);
 	kvm_ioapic_destroy(kvm);
 	kvm_free_vcpus(kvm);
@@ -10771,6 +11042,111 @@ void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_c
 }
 EXPORT_SYMBOL_GPL(kvm_fixup_and_inject_pf_error);
 
+/*
+ * Handles kvm_read/write_guest_virt*() result and either injects #PF or returns
+ * KVM_EXIT_INTERNAL_ERROR for cases not currently handled by KVM. Return value
+ * indicates whether exit to userspace is needed.
+ */
+int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r,
+			      struct x86_exception *e)
+{
+	if (r == X86EMUL_PROPAGATE_FAULT) {
+		kvm_inject_emulated_page_fault(vcpu, e);
+		return 1;
+	}
+
+	/*
+	 * In case kvm_read/write_guest_virt*() failed with X86EMUL_IO_NEEDED
+	 * while handling a VMX instruction KVM could've handled the request
+	 * correctly by exiting to userspace and performing I/O but there
+	 * doesn't seem to be a real use-case behind such requests, just return
+	 * KVM_EXIT_INTERNAL_ERROR for now.
+	 */
+	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+	vcpu->run->internal.ndata = 0;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_handle_memory_failure);
+
+int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva)
+{
+	bool pcid_enabled;
+	struct x86_exception e;
+	unsigned i;
+	unsigned long roots_to_free = 0;
+	struct {
+		u64 pcid;
+		u64 gla;
+	} operand;
+	int r;
+
+	r = kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e);
+	if (r != X86EMUL_CONTINUE)
+		return kvm_handle_memory_failure(vcpu, r, &e);
+
+	if (operand.pcid >> 12 != 0) {
+		kvm_inject_gp(vcpu, 0);
+		return 1;
+	}
+
+	pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE);
+
+	switch (type) {
+	case INVPCID_TYPE_INDIV_ADDR:
+		if ((!pcid_enabled && (operand.pcid != 0)) ||
+		    is_noncanonical_address(operand.gla, vcpu)) {
+			kvm_inject_gp(vcpu, 0);
+			return 1;
+		}
+		kvm_mmu_invpcid_gva(vcpu, operand.gla, operand.pcid);
+		return kvm_skip_emulated_instruction(vcpu);
+
+	case INVPCID_TYPE_SINGLE_CTXT:
+		if (!pcid_enabled && (operand.pcid != 0)) {
+			kvm_inject_gp(vcpu, 0);
+			return 1;
+		}
+
+		if (kvm_get_active_pcid(vcpu) == operand.pcid) {
+			kvm_mmu_sync_roots(vcpu);
+			kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
+		}
+
+		for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
+			if (kvm_get_pcid(vcpu, vcpu->arch.mmu->prev_roots[i].pgd)
+			    == operand.pcid)
+				roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
+
+		kvm_mmu_free_roots(vcpu, vcpu->arch.mmu, roots_to_free);
+		/*
+		 * If neither the current cr3 nor any of the prev_roots use the
+		 * given PCID, then nothing needs to be done here because a
+		 * resync will happen anyway before switching to any other CR3.
+		 */
+
+		return kvm_skip_emulated_instruction(vcpu);
+
+	case INVPCID_TYPE_ALL_NON_GLOBAL:
+		/*
+		 * Currently, KVM doesn't mark global entries in the shadow
+		 * page tables, so a non-global flush just degenerates to a
+		 * global flush. If needed, we could optimize this later by
+		 * keeping track of global entries in shadow page tables.
+		 */
+
+		fallthrough;
+	case INVPCID_TYPE_ALL_INCL_GLOBAL:
+		kvm_mmu_unload(vcpu);
+		return kvm_skip_emulated_instruction(vcpu);
+
+	default:
+		BUG(); /* We have already checked above that type <= 3 */
+	}
+}
+EXPORT_SYMBOL_GPL(kvm_handle_invpcid);
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 995ab69..3900ab0 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -246,7 +246,6 @@ static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu)
 	return is_smm(vcpu) || kvm_x86_ops.apic_init_signal_blocked(vcpu);
 }
 
-void kvm_set_pending_timer(struct kvm_vcpu *vcpu);
 void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
 
 void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr);
@@ -372,6 +371,10 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu);
 int kvm_spec_ctrl_test_value(u64 value);
 int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
 bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu);
+int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r,
+			      struct x86_exception *e);
+int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva);
+bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type);
 
 #define  KVM_MSR_RET_INVALID  2
 
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 9417a34..26cfb0f 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -17,7 +17,7 @@
 	ERSN(NMI), ERSN(INTERNAL_ERROR), ERSN(OSI), ERSN(PAPR_HCALL),	\
 	ERSN(S390_UCONTROL), ERSN(WATCHDOG), ERSN(S390_TSCH), ERSN(EPR),\
 	ERSN(SYSTEM_EVENT), ERSN(S390_STSI), ERSN(IOAPIC_EOI),          \
-	ERSN(HYPERV), ERSN(ARM_NISV)
+	ERSN(HYPERV), ERSN(ARM_NISV), ERSN(X86_RDMSR), ERSN(X86_WRMSR)
 
 TRACE_EVENT(kvm_userspace_exit,
 	    TP_PROTO(__u32 reason, int errno),
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 3d80234..58f43aa 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -248,6 +248,8 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_IOAPIC_EOI       26
 #define KVM_EXIT_HYPERV           27
 #define KVM_EXIT_ARM_NISV         28
+#define KVM_EXIT_X86_RDMSR        29
+#define KVM_EXIT_X86_WRMSR        30
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -413,6 +415,17 @@ struct kvm_run {
 			__u64 esr_iss;
 			__u64 fault_ipa;
 		} arm_nisv;
+		/* KVM_EXIT_X86_RDMSR / KVM_EXIT_X86_WRMSR */
+		struct {
+			__u8 error; /* user -> kernel */
+			__u8 pad[7];
+#define KVM_MSR_EXIT_REASON_INVAL	(1 << 0)
+#define KVM_MSR_EXIT_REASON_UNKNOWN	(1 << 1)
+#define KVM_MSR_EXIT_REASON_FILTER	(1 << 2)
+			__u32 reason; /* kernel -> user */
+			__u32 index; /* kernel -> user */
+			__u64 data; /* kernel <-> user */
+		} msr;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -790,9 +803,10 @@ struct kvm_ppc_resize_hpt {
 #define KVM_VM_PPC_HV 1
 #define KVM_VM_PPC_PR 2
 
-/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */
-#define KVM_VM_MIPS_TE		0
+/* on MIPS, 0 indicates auto, 1 forces VZ ASE, 2 forces trap & emulate */
+#define KVM_VM_MIPS_AUTO	0
 #define KVM_VM_MIPS_VZ		1
+#define KVM_VM_MIPS_TE		2
 
 #define KVM_S390_SIE_PAGE_OFFSET 1
 
@@ -1036,6 +1050,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_SMALLER_MAXPHYADDR 185
 #define KVM_CAP_S390_DIAG318 186
 #define KVM_CAP_STEAL_TIME 187
+#define KVM_CAP_X86_USER_SPACE_MSR 188
+#define KVM_CAP_X86_MSR_FILTER 189
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1537,6 +1553,9 @@ struct kvm_pv_cmd {
 /* Available with KVM_CAP_S390_PROTECTED */
 #define KVM_S390_PV_COMMAND		_IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
 
+/* Available with KVM_CAP_X86_MSR_FILTER */
+#define KVM_X86_SET_MSR_FILTER	_IOW(KVMIO,  0xc6, struct kvm_msr_filter)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 4527871..307ceaa 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -11,6 +11,7 @@
 /x86_64/set_sregs_test
 /x86_64/smm_test
 /x86_64/state_test
+/x86_64/user_msr_test
 /x86_64/vmx_preemption_timer_test
 /x86_64/svm_vmcall_test
 /x86_64/sync_regs_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 4a16658..7ebe71f 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -55,6 +55,8 @@
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test
 TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test
 TEST_GEN_PROGS_x86_64 += x86_64/debug_regs
+TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test
+TEST_GEN_PROGS_x86_64 += x86_64/user_msr_test
 TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
 TEST_GEN_PROGS_x86_64 += demand_paging_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index 16fa21e..54d624d 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -48,7 +48,7 @@
 #define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
 #define SECONDARY_EXEC_ENABLE_EPT		0x00000002
 #define SECONDARY_EXEC_DESC			0x00000004
-#define SECONDARY_EXEC_RDTSCP			0x00000008
+#define SECONDARY_EXEC_ENABLE_RDTSCP		0x00000008
 #define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE	0x00000010
 #define SECONDARY_EXEC_ENABLE_VPID		0x00000020
 #define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
new file mode 100644
index 0000000..f8e7611
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Tests for MSR_IA32_TSC and MSR_IA32_TSC_ADJUST.
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#include <stdio.h>
+#include <string.h>
+#include "kvm_util.h"
+#include "processor.h"
+
+#define VCPU_ID 0
+
+#define UNITY                  (1ull << 30)
+#define HOST_ADJUST            (UNITY * 64)
+#define GUEST_STEP             (UNITY * 4)
+#define ROUND(x)               ((x + UNITY / 2) & -UNITY)
+#define rounded_rdmsr(x)       ROUND(rdmsr(x))
+#define rounded_host_rdmsr(x)  ROUND(vcpu_get_msr(vm, 0, x))
+
+#define GUEST_ASSERT_EQ(a, b) do {				\
+	__typeof(a) _a = (a);					\
+	__typeof(b) _b = (b);					\
+	if (_a != _b)						\
+                ucall(UCALL_ABORT, 4,				\
+                        "Failed guest assert: "			\
+                        #a " == " #b, __LINE__, _a, _b);	\
+  } while(0)
+
+static void guest_code(void)
+{
+	u64 val = 0;
+
+	GUEST_ASSERT_EQ(rounded_rdmsr(MSR_IA32_TSC), val);
+	GUEST_ASSERT_EQ(rounded_rdmsr(MSR_IA32_TSC_ADJUST), val);
+
+	/* Guest: writes to MSR_IA32_TSC affect both MSRs.  */
+	val = 1ull * GUEST_STEP;
+	wrmsr(MSR_IA32_TSC, val);
+	GUEST_ASSERT_EQ(rounded_rdmsr(MSR_IA32_TSC), val);
+	GUEST_ASSERT_EQ(rounded_rdmsr(MSR_IA32_TSC_ADJUST), val);
+
+	/* Guest: writes to MSR_IA32_TSC_ADJUST affect both MSRs.  */
+	GUEST_SYNC(2);
+	val = 2ull * GUEST_STEP;
+	wrmsr(MSR_IA32_TSC_ADJUST, val);
+	GUEST_ASSERT_EQ(rounded_rdmsr(MSR_IA32_TSC), val);
+	GUEST_ASSERT_EQ(rounded_rdmsr(MSR_IA32_TSC_ADJUST), val);
+
+	/* Host: setting the TSC offset.  */
+	GUEST_SYNC(3);
+	GUEST_ASSERT_EQ(rounded_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val);
+	GUEST_ASSERT_EQ(rounded_rdmsr(MSR_IA32_TSC_ADJUST), val);
+
+	/*
+	 * Guest: writes to MSR_IA32_TSC_ADJUST do not destroy the
+	 * host-side offset and affect both MSRs.
+	 */
+	GUEST_SYNC(4);
+	val = 3ull * GUEST_STEP;
+	wrmsr(MSR_IA32_TSC_ADJUST, val);
+	GUEST_ASSERT_EQ(rounded_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val);
+	GUEST_ASSERT_EQ(rounded_rdmsr(MSR_IA32_TSC_ADJUST), val);
+
+	/*
+	 * Guest: writes to MSR_IA32_TSC affect both MSRs, so the host-side
+	 * offset is now visible in MSR_IA32_TSC_ADJUST.
+	 */
+	GUEST_SYNC(5);
+	val = 4ull * GUEST_STEP;
+	wrmsr(MSR_IA32_TSC, val);
+	GUEST_ASSERT_EQ(rounded_rdmsr(MSR_IA32_TSC), val);
+	GUEST_ASSERT_EQ(rounded_rdmsr(MSR_IA32_TSC_ADJUST), val - HOST_ADJUST);
+
+	GUEST_DONE();
+}
+
+static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid, int stage)
+{
+	struct ucall uc;
+
+	vcpu_args_set(vm, vcpuid, 1, vcpuid);
+
+	vcpu_ioctl(vm, vcpuid, KVM_RUN, NULL);
+
+	switch (get_ucall(vm, vcpuid, &uc)) {
+	case UCALL_SYNC:
+		TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+                            uc.args[1] == stage + 1, "Stage %d: Unexpected register values vmexit, got %lx",
+                            stage + 1, (ulong)uc.args[1]);
+		return;
+	case UCALL_DONE:
+		return;
+	case UCALL_ABORT:
+		TEST_ASSERT(false, "%s at %s:%ld\n" \
+			    "\tvalues: %#lx, %#lx", (const char *)uc.args[0],
+			    __FILE__, uc.args[1], uc.args[2], uc.args[3]);
+	default:
+		TEST_ASSERT(false, "Unexpected exit: %s",
+			    exit_reason_str(vcpu_state(vm, vcpuid)->exit_reason));
+	}
+}
+
+int main(void)
+{
+	struct kvm_vm *vm;
+	uint64_t val;
+
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+	val = 0;
+	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val);
+	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
+
+	/* Guest: writes to MSR_IA32_TSC affect both MSRs.  */
+	run_vcpu(vm, VCPU_ID, 1);
+	val = 1ull * GUEST_STEP;
+	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val);
+	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
+
+	/* Guest: writes to MSR_IA32_TSC_ADJUST affect both MSRs.  */
+	run_vcpu(vm, VCPU_ID, 2);
+	val = 2ull * GUEST_STEP;
+	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val);
+	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
+
+	/*
+	 * Host: writes to MSR_IA32_TSC set the host-side offset
+	 * and therefore do not change MSR_IA32_TSC_ADJUST.
+	 */
+	vcpu_set_msr(vm, 0, MSR_IA32_TSC, HOST_ADJUST + val);
+	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val);
+	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
+	run_vcpu(vm, VCPU_ID, 3);
+
+	/* Host: writes to MSR_IA32_TSC_ADJUST do not modify the TSC.  */
+	vcpu_set_msr(vm, 0, MSR_IA32_TSC_ADJUST, UNITY * 123456);
+	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val);
+	ASSERT_EQ(vcpu_get_msr(vm, 0, MSR_IA32_TSC_ADJUST), UNITY * 123456);
+
+	/* Restore previous value.  */
+	vcpu_set_msr(vm, 0, MSR_IA32_TSC_ADJUST, val);
+	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val);
+	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
+
+	/*
+	 * Guest: writes to MSR_IA32_TSC_ADJUST do not destroy the
+	 * host-side offset and affect both MSRs.
+	 */
+	run_vcpu(vm, VCPU_ID, 4);
+	val = 3ull * GUEST_STEP;
+	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), HOST_ADJUST + val);
+	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val);
+
+	/*
+	 * Guest: writes to MSR_IA32_TSC affect both MSRs, so the host-side
+	 * offset is now visible in MSR_IA32_TSC_ADJUST.
+	 */
+	run_vcpu(vm, VCPU_ID, 5);
+	val = 4ull * GUEST_STEP;
+	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC), val);
+	ASSERT_EQ(rounded_host_rdmsr(MSR_IA32_TSC_ADJUST), val - HOST_ADJUST);
+
+	kvm_vm_free(vm);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/user_msr_test.c b/tools/testing/selftests/kvm/x86_64/user_msr_test.c
new file mode 100644
index 0000000..cbe1b08
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/user_msr_test.c
@@ -0,0 +1,248 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * tests for KVM_CAP_X86_USER_SPACE_MSR and KVM_X86_SET_MSR_FILTER
+ *
+ * Copyright (C) 2020, Amazon Inc.
+ *
+ * This is a functional test to verify that we can deflect MSR events
+ * into user space.
+ */
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#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"
+
+#define VCPU_ID                  5
+
+static u32 msr_reads, msr_writes;
+
+static u8 bitmap_00000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE];
+static u8 bitmap_00000000_write[KVM_MSR_FILTER_MAX_BITMAP_SIZE];
+static u8 bitmap_40000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE];
+static u8 bitmap_c0000000[KVM_MSR_FILTER_MAX_BITMAP_SIZE];
+static u8 bitmap_c0000000_read[KVM_MSR_FILTER_MAX_BITMAP_SIZE];
+static u8 bitmap_deadbeef[1] = { 0x1 };
+
+static void deny_msr(uint8_t *bitmap, u32 msr)
+{
+	u32 idx = msr & (KVM_MSR_FILTER_MAX_BITMAP_SIZE - 1);
+
+	bitmap[idx / 8] &= ~(1 << (idx % 8));
+}
+
+static void prepare_bitmaps(void)
+{
+	memset(bitmap_00000000, 0xff, sizeof(bitmap_00000000));
+	memset(bitmap_00000000_write, 0xff, sizeof(bitmap_00000000_write));
+	memset(bitmap_40000000, 0xff, sizeof(bitmap_40000000));
+	memset(bitmap_c0000000, 0xff, sizeof(bitmap_c0000000));
+	memset(bitmap_c0000000_read, 0xff, sizeof(bitmap_c0000000_read));
+
+	deny_msr(bitmap_00000000_write, MSR_IA32_POWER_CTL);
+	deny_msr(bitmap_c0000000_read, MSR_SYSCALL_MASK);
+	deny_msr(bitmap_c0000000_read, MSR_GS_BASE);
+}
+
+struct kvm_msr_filter filter = {
+	.flags = KVM_MSR_FILTER_DEFAULT_DENY,
+	.ranges = {
+		{
+			.flags = KVM_MSR_FILTER_READ,
+			.base = 0x00000000,
+			.nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE,
+			.bitmap = bitmap_00000000,
+		}, {
+			.flags = KVM_MSR_FILTER_WRITE,
+			.base = 0x00000000,
+			.nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE,
+			.bitmap = bitmap_00000000_write,
+		}, {
+			.flags = KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE,
+			.base = 0x40000000,
+			.nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE,
+			.bitmap = bitmap_40000000,
+		}, {
+			.flags = KVM_MSR_FILTER_READ,
+			.base = 0xc0000000,
+			.nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE,
+			.bitmap = bitmap_c0000000_read,
+		}, {
+			.flags = KVM_MSR_FILTER_WRITE,
+			.base = 0xc0000000,
+			.nmsrs = KVM_MSR_FILTER_MAX_BITMAP_SIZE * BITS_PER_BYTE,
+			.bitmap = bitmap_c0000000,
+		}, {
+			.flags = KVM_MSR_FILTER_WRITE | KVM_MSR_FILTER_READ,
+			.base = 0xdeadbeef,
+			.nmsrs = 1,
+			.bitmap = bitmap_deadbeef,
+		},
+	},
+};
+
+struct kvm_msr_filter no_filter = {
+	.flags = KVM_MSR_FILTER_DEFAULT_ALLOW,
+};
+
+static void guest_msr_calls(bool trapped)
+{
+	/* This goes into the in-kernel emulation */
+	wrmsr(MSR_SYSCALL_MASK, 0);
+
+	if (trapped) {
+		/* This goes into user space emulation */
+		GUEST_ASSERT(rdmsr(MSR_SYSCALL_MASK) == MSR_SYSCALL_MASK);
+		GUEST_ASSERT(rdmsr(MSR_GS_BASE) == MSR_GS_BASE);
+	} else {
+		GUEST_ASSERT(rdmsr(MSR_SYSCALL_MASK) != MSR_SYSCALL_MASK);
+		GUEST_ASSERT(rdmsr(MSR_GS_BASE) != MSR_GS_BASE);
+	}
+
+	/* If trapped == true, this goes into user space emulation */
+	wrmsr(MSR_IA32_POWER_CTL, 0x1234);
+
+	/* This goes into the in-kernel emulation */
+	rdmsr(MSR_IA32_POWER_CTL);
+
+	/* Invalid MSR, should always be handled by user space exit */
+	GUEST_ASSERT(rdmsr(0xdeadbeef) == 0xdeadbeef);
+	wrmsr(0xdeadbeef, 0x1234);
+}
+
+static void guest_code(void)
+{
+	guest_msr_calls(true);
+
+	/*
+	 * Disable msr filtering, so that the kernel
+	 * handles everything in the next round
+	 */
+	GUEST_SYNC(0);
+
+	guest_msr_calls(false);
+
+	GUEST_DONE();
+}
+
+static int handle_ucall(struct kvm_vm *vm)
+{
+	struct ucall uc;
+
+	switch (get_ucall(vm, VCPU_ID, &uc)) {
+	case UCALL_ABORT:
+		TEST_FAIL("Guest assertion not met");
+		break;
+	case UCALL_SYNC:
+		vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &no_filter);
+		break;
+	case UCALL_DONE:
+		return 1;
+	default:
+		TEST_FAIL("Unknown ucall %lu", uc.cmd);
+	}
+
+	return 0;
+}
+
+static void handle_rdmsr(struct kvm_run *run)
+{
+	run->msr.data = run->msr.index;
+	msr_reads++;
+
+	if (run->msr.index == MSR_SYSCALL_MASK ||
+	    run->msr.index == MSR_GS_BASE) {
+		TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_FILTER,
+			    "MSR read trap w/o access fault");
+	}
+
+	if (run->msr.index == 0xdeadbeef) {
+		TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_UNKNOWN,
+			    "MSR deadbeef read trap w/o inval fault");
+	}
+}
+
+static void handle_wrmsr(struct kvm_run *run)
+{
+	/* ignore */
+	msr_writes++;
+
+	if (run->msr.index == MSR_IA32_POWER_CTL) {
+		TEST_ASSERT(run->msr.data == 0x1234,
+			    "MSR data for MSR_IA32_POWER_CTL incorrect");
+		TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_FILTER,
+			    "MSR_IA32_POWER_CTL trap w/o access fault");
+	}
+
+	if (run->msr.index == 0xdeadbeef) {
+		TEST_ASSERT(run->msr.data == 0x1234,
+			    "MSR data for deadbeef incorrect");
+		TEST_ASSERT(run->msr.reason == KVM_MSR_EXIT_REASON_UNKNOWN,
+			    "deadbeef trap w/o inval fault");
+	}
+}
+
+int main(int argc, char *argv[])
+{
+	struct kvm_enable_cap cap = {
+		.cap = KVM_CAP_X86_USER_SPACE_MSR,
+		.args[0] = KVM_MSR_EXIT_REASON_INVAL |
+			   KVM_MSR_EXIT_REASON_UNKNOWN |
+			   KVM_MSR_EXIT_REASON_FILTER,
+	};
+	struct kvm_vm *vm;
+	struct kvm_run *run;
+	int rc;
+
+	/* Tell stdout not to buffer its content */
+	setbuf(stdout, NULL);
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+	run = vcpu_state(vm, VCPU_ID);
+
+	rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR);
+	TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available");
+	vm_enable_cap(vm, &cap);
+
+	rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER);
+	TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available");
+
+	prepare_bitmaps();
+	vm_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter);
+
+	while (1) {
+		rc = _vcpu_run(vm, VCPU_ID);
+
+		TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc);
+
+		switch (run->exit_reason) {
+		case KVM_EXIT_X86_RDMSR:
+			handle_rdmsr(run);
+			break;
+		case KVM_EXIT_X86_WRMSR:
+			handle_wrmsr(run);
+			break;
+		case KVM_EXIT_IO:
+			if (handle_ucall(vm))
+				goto done;
+			break;
+		}
+
+	}
+
+done:
+	TEST_ASSERT(msr_reads == 4, "Handled 4 rdmsr in user space");
+	TEST_ASSERT(msr_writes == 3, "Handled 3 wrmsr in user space");
+
+	kvm_vm_free(vm);
+
+	return 0;
+}
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index d6408bb..c2323c2 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -853,15 +853,17 @@ kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx,
 	struct eventfd_ctx       *eventfd;
 	struct kvm_io_bus	 *bus;
 	int                       ret = -ENOENT;
+	bool                      wildcard;
 
 	eventfd = eventfd_ctx_fdget(args->fd);
 	if (IS_ERR(eventfd))
 		return PTR_ERR(eventfd);
 
+	wildcard = !(args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH);
+
 	mutex_lock(&kvm->slots_lock);
 
 	list_for_each_entry_safe(p, tmp, &kvm->ioeventfds, list) {
-		bool wildcard = !(args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH);
 
 		if (p->bus_idx != bus_idx ||
 		    p->eventfd != eventfd  ||
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 67cd0b8..68edd25 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4332,7 +4332,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 			       struct kvm_io_device *dev)
 {
-	int i;
+	int i, j;
 	struct kvm_io_bus *new_bus, *bus;
 
 	bus = kvm_get_bus(kvm, bus_idx);
@@ -4349,17 +4349,20 @@ void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 
 	new_bus = kmalloc(struct_size(bus, range, bus->dev_count - 1),
 			  GFP_KERNEL_ACCOUNT);
-	if (!new_bus)  {
+	if (new_bus) {
+		memcpy(new_bus, bus, struct_size(bus, range, i));
+		new_bus->dev_count--;
+		memcpy(new_bus->range + i, bus->range + i + 1,
+				flex_array_size(new_bus, range, new_bus->dev_count - i));
+	} else {
 		pr_err("kvm: failed to shrink bus, removing it completely\n");
-		goto broken;
+		for (j = 0; j < bus->dev_count; j++) {
+			if (j == i)
+				continue;
+			kvm_iodevice_destructor(bus->range[j].dev);
+		}
 	}
 
-	memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range));
-	new_bus->dev_count--;
-	memcpy(new_bus->range + i, bus->range + i + 1,
-	       (new_bus->dev_count - i) * sizeof(struct kvm_io_range));
-
-broken:
 	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
 	synchronize_srcu_expedited(&kvm->srcu);
 	kfree(bus);