24 files changed, 169 insertions, 135 deletions

diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 9860ca5979f8..9e38ffaadb5d 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -83,7 +83,7 @@ cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin \
 
 $(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE
 	$(call if_changed,image)
-	@$(kecho) 'Kernel: $@ is ready' ' (#'`cat .version`')'
+	@$(kecho) 'Kernel: $@ is ready' ' (#'$(or $(KBUILD_BUILD_VERSION),`cat .version`)')'
 
 OBJCOPYFLAGS_vmlinux.bin := -O binary -R .note -R .comment -S
 $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 8b70237c33f7..d6f3703e4119 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -861,8 +861,7 @@ static int amd_pmu_handle_irq(struct pt_regs *regs)
 	pmu_enabled = cpuc->enabled;
 	cpuc->enabled = 0;
 
-	/* stop everything (includes BRS) */
-	amd_pmu_disable_all();
+	amd_brs_disable_all();
 
 	/* Drain BRS is in use (could be inactive) */
 	if (cpuc->lbr_users)
@@ -873,7 +872,7 @@ static int amd_pmu_handle_irq(struct pt_regs *regs)
 
 	cpuc->enabled = pmu_enabled;
 	if (pmu_enabled)
-		amd_pmu_enable_all(0);
+		amd_brs_enable_all();
 
 	return amd_pmu_adjust_nmi_window(handled);
 }
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index d568afc705d2..83f15fe411b3 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -553,6 +553,7 @@ static void uncore_clean_online(void)
 
 	hlist_for_each_entry_safe(uncore, n, &uncore_unused_list, node) {
 		hlist_del(&uncore->node);
+		kfree(uncore->events);
 		kfree(uncore);
 	}
 }
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 82ef87e9a897..42a55794004a 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1263,6 +1263,15 @@ static int pt_buffer_try_single(struct pt_buffer *buf, int nr_pages)
 	if (1 << order != nr_pages)
 		goto out;
 
+	/*
+	 * Some processors cannot always support single range for more than
+	 * 4KB - refer errata TGL052, ADL037 and RPL017. Future processors might
+	 * also be affected, so for now rather than trying to keep track of
+	 * which ones, just disable it for all.
+	 */
+	if (nr_pages > 1)
+		goto out;
+
 	buf->single = true;
 	buf->nr_pages = nr_pages;
 	ret = 0;
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index f49bc3ec76e6..a269049a43ce 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -77,7 +77,7 @@ static int hyperv_init_ghcb(void)
 static int hv_cpu_init(unsigned int cpu)
 {
 	union hv_vp_assist_msr_contents msr = { 0 };
-	struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()];
+	struct hv_vp_assist_page **hvp = &hv_vp_assist_page[cpu];
 	int ret;
 
 	ret = hv_common_cpu_init(cpu);
@@ -87,34 +87,32 @@ static int hv_cpu_init(unsigned int cpu)
 	if (!hv_vp_assist_page)
 		return 0;
 
-	if (!*hvp) {
-		if (hv_root_partition) {
-			/*
-			 * For root partition we get the hypervisor provided VP assist
-			 * page, instead of allocating a new page.
-			 */
-			rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
-			*hvp = memremap(msr.pfn <<
-					HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT,
-					PAGE_SIZE, MEMREMAP_WB);
-		} else {
-			/*
-			 * The VP assist page is an "overlay" page (see Hyper-V TLFS's
-			 * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed
-			 * out to make sure we always write the EOI MSR in
-			 * hv_apic_eoi_write() *after* the EOI optimization is disabled
-			 * in hv_cpu_die(), otherwise a CPU may not be stopped in the
-			 * case of CPU offlining and the VM will hang.
-			 */
+	if (hv_root_partition) {
+		/*
+		 * For root partition we get the hypervisor provided VP assist
+		 * page, instead of allocating a new page.
+		 */
+		rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+		*hvp = memremap(msr.pfn << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT,
+				PAGE_SIZE, MEMREMAP_WB);
+	} else {
+		/*
+		 * The VP assist page is an "overlay" page (see Hyper-V TLFS's
+		 * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed
+		 * out to make sure we always write the EOI MSR in
+		 * hv_apic_eoi_write() *after* the EOI optimization is disabled
+		 * in hv_cpu_die(), otherwise a CPU may not be stopped in the
+		 * case of CPU offlining and the VM will hang.
+		 */
+		if (!*hvp)
 			*hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO);
-			if (*hvp)
-				msr.pfn = vmalloc_to_pfn(*hvp);
-		}
-		WARN_ON(!(*hvp));
-		if (*hvp) {
-			msr.enable = 1;
-			wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
-		}
+		if (*hvp)
+			msr.pfn = vmalloc_to_pfn(*hvp);
+
+	}
+	if (!WARN_ON(!(*hvp))) {
+		msr.enable = 1;
+		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
 	}
 
 	return hyperv_init_ghcb();
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index b71f4f2ecdd5..b2da7cb64b31 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -305,6 +305,9 @@
 #define X86_FEATURE_USE_IBPB_FW		(11*32+16) /* "" Use IBPB during runtime firmware calls */
 #define X86_FEATURE_RSB_VMEXIT_LITE	(11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */
 
+
+#define X86_FEATURE_MSR_TSX_CTRL	(11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */
+
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 10ac52705892..4a2af82553e4 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -535,6 +535,11 @@
 #define MSR_AMD64_CPUID_FN_1		0xc0011004
 #define MSR_AMD64_LS_CFG		0xc0011020
 #define MSR_AMD64_DC_CFG		0xc0011022
+
+#define MSR_AMD64_DE_CFG		0xc0011029
+#define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT	 1
+#define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE	BIT_ULL(MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT)
+
 #define MSR_AMD64_BU_CFG2		0xc001102a
 #define MSR_AMD64_IBSFETCHCTL		0xc0011030
 #define MSR_AMD64_IBSFETCHLINAD		0xc0011031
@@ -640,9 +645,6 @@
 #define FAM10H_MMIO_CONF_BASE_MASK	0xfffffffULL
 #define FAM10H_MMIO_CONF_BASE_SHIFT	20
 #define MSR_FAM10H_NODE_ID		0xc001100c
-#define MSR_F10H_DECFG			0xc0011029
-#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT	1
-#define MSR_F10H_DECFG_LFENCE_SERIALIZE		BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT)
 
 /* K8 MSRs */
 #define MSR_K8_TOP_MEM1			0xc001001a
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index 60ece592b220..dbb38a6b4dfb 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -37,7 +37,7 @@ __PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text");
  *   rsi = lockval           (second argument)
  *   rdx = internal variable (set to 0)
  */
-asm    (".pushsection .spinlock.text;"
+asm    (".pushsection .spinlock.text, \"ax\";"
 	".globl " PV_UNLOCK ";"
 	".type " PV_UNLOCK ", @function;"
 	".align 4,0x90;"
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 860b60273df3..c75d75b9f11a 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -770,8 +770,6 @@ static void init_amd_gh(struct cpuinfo_x86 *c)
 		set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
 }
 
-#define MSR_AMD64_DE_CFG	0xC0011029
-
 static void init_amd_ln(struct cpuinfo_x86 *c)
 {
 	/*
@@ -965,8 +963,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 		 * msr_set_bit() uses the safe accessors, too, even if the MSR
 		 * is not present.
 		 */
-		msr_set_bit(MSR_F10H_DECFG,
-			    MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
+		msr_set_bit(MSR_AMD64_DE_CFG,
+			    MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT);
 
 		/* A serializing LFENCE stops RDTSC speculation */
 		set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 21fd425088fe..c393b8773ace 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -326,8 +326,8 @@ static void init_hygon(struct cpuinfo_x86 *c)
 		 * msr_set_bit() uses the safe accessors, too, even if the MSR
 		 * is not present.
 		 */
-		msr_set_bit(MSR_F10H_DECFG,
-			    MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT);
+		msr_set_bit(MSR_AMD64_DE_CFG,
+			    MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT);
 
 		/* A serializing LFENCE stops RDTSC speculation */
 		set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c
index ebe79d60619f..da8b8ea6b063 100644
--- a/arch/x86/kernel/cpu/sgx/ioctl.c
+++ b/arch/x86/kernel/cpu/sgx/ioctl.c
@@ -356,6 +356,9 @@ static int sgx_validate_offset_length(struct sgx_encl *encl,
 	if (!length || !IS_ALIGNED(length, PAGE_SIZE))
 		return -EINVAL;
 
+	if (offset + length < offset)
+		return -EINVAL;
+
 	if (offset + length - PAGE_SIZE >= encl->size)
 		return -EINVAL;
 
diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c
index ec7bbac3a9f2..8009c8346d8f 100644
--- a/arch/x86/kernel/cpu/tsx.c
+++ b/arch/x86/kernel/cpu/tsx.c
@@ -58,24 +58,6 @@ static void tsx_enable(void)
 	wrmsrl(MSR_IA32_TSX_CTRL, tsx);
 }
 
-static bool tsx_ctrl_is_supported(void)
-{
-	u64 ia32_cap = x86_read_arch_cap_msr();
-
-	/*
-	 * TSX is controlled via MSR_IA32_TSX_CTRL.  However, support for this
-	 * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES.
-	 *
-	 * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a
-	 * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES
-	 * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get
-	 * MSR_IA32_TSX_CTRL support even after a microcode update. Thus,
-	 * tsx= cmdline requests will do nothing on CPUs without
-	 * MSR_IA32_TSX_CTRL support.
-	 */
-	return !!(ia32_cap & ARCH_CAP_TSX_CTRL_MSR);
-}
-
 static enum tsx_ctrl_states x86_get_tsx_auto_mode(void)
 {
 	if (boot_cpu_has_bug(X86_BUG_TAA))
@@ -135,7 +117,7 @@ static void tsx_clear_cpuid(void)
 		rdmsrl(MSR_TSX_FORCE_ABORT, msr);
 		msr |= MSR_TFA_TSX_CPUID_CLEAR;
 		wrmsrl(MSR_TSX_FORCE_ABORT, msr);
-	} else if (tsx_ctrl_is_supported()) {
+	} else if (cpu_feature_enabled(X86_FEATURE_MSR_TSX_CTRL)) {
 		rdmsrl(MSR_IA32_TSX_CTRL, msr);
 		msr |= TSX_CTRL_CPUID_CLEAR;
 		wrmsrl(MSR_IA32_TSX_CTRL, msr);
@@ -158,7 +140,8 @@ static void tsx_dev_mode_disable(void)
 	u64 mcu_opt_ctrl;
 
 	/* Check if RTM_ALLOW exists */
-	if (!boot_cpu_has_bug(X86_BUG_TAA) || !tsx_ctrl_is_supported() ||
+	if (!boot_cpu_has_bug(X86_BUG_TAA) ||
+	    !cpu_feature_enabled(X86_FEATURE_MSR_TSX_CTRL) ||
 	    !cpu_feature_enabled(X86_FEATURE_SRBDS_CTRL))
 		return;
 
@@ -191,7 +174,20 @@ void __init tsx_init(void)
 		return;
 	}
 
-	if (!tsx_ctrl_is_supported()) {
+	/*
+	 * TSX is controlled via MSR_IA32_TSX_CTRL.  However, support for this
+	 * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES.
+	 *
+	 * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a
+	 * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES
+	 * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get
+	 * MSR_IA32_TSX_CTRL support even after a microcode update. Thus,
+	 * tsx= cmdline requests will do nothing on CPUs without
+	 * MSR_IA32_TSX_CTRL support.
+	 */
+	if (x86_read_arch_cap_msr() & ARCH_CAP_TSX_CTRL_MSR) {
+		setup_force_cpu_cap(X86_FEATURE_MSR_TSX_CTRL);
+	} else {
 		tsx_ctrl_state = TSX_CTRL_NOT_SUPPORTED;
 		return;
 	}
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 3b28c5b25e12..d00db56a8868 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -605,9 +605,9 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal)
 	if (test_thread_flag(TIF_NEED_FPU_LOAD))
 		fpregs_restore_userregs();
 	save_fpregs_to_fpstate(dst_fpu);
+	fpregs_unlock();
 	if (!(clone_flags & CLONE_THREAD))
 		fpu_inherit_perms(dst_fpu);
-	fpregs_unlock();
 
 	/*
 	 * Children never inherit PASID state.
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 1ccb769f62af..b6f96d47e596 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2443,6 +2443,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
 {
 	bool list_unstable, zapped_root = false;
 
+	lockdep_assert_held_write(&kvm->mmu_lock);
 	trace_kvm_mmu_prepare_zap_page(sp);
 	++kvm->stat.mmu_shadow_zapped;
 	*nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list);
@@ -4262,14 +4263,14 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	if (is_page_fault_stale(vcpu, fault, mmu_seq))
 		goto out_unlock;
 
-	r = make_mmu_pages_available(vcpu);
-	if (r)
-		goto out_unlock;
-
-	if (is_tdp_mmu_fault)
+	if (is_tdp_mmu_fault) {
 		r = kvm_tdp_mmu_map(vcpu, fault);
-	else
+	} else {
+		r = make_mmu_pages_available(vcpu);
+		if (r)
+			goto out_unlock;
 		r = __direct_map(vcpu, fault);
+	}
 
 out_unlock:
 	if (is_tdp_mmu_fault)
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 4c620999d230..995bc0f90759 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -1091,6 +1091,12 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 
 static void nested_svm_triple_fault(struct kvm_vcpu *vcpu)
 {
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (!vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SHUTDOWN))
+		return;
+
+	kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 	nested_svm_simple_vmexit(to_svm(vcpu), SVM_EXIT_SHUTDOWN);
 }
 
@@ -1125,6 +1131,9 @@ void svm_free_nested(struct vcpu_svm *svm)
 	if (!svm->nested.initialized)
 		return;
 
+	if (WARN_ON_ONCE(svm->vmcb != svm->vmcb01.ptr))
+		svm_switch_vmcb(svm, &svm->vmcb01);
+
 	svm_vcpu_free_msrpm(svm->nested.msrpm);
 	svm->nested.msrpm = NULL;
 
@@ -1143,9 +1152,6 @@ void svm_free_nested(struct vcpu_svm *svm)
 	svm->nested.initialized = false;
 }
 
-/*
- * Forcibly leave nested mode in order to be able to reset the VCPU later on.
- */
 void svm_leave_nested(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 9f88c8e6766e..ce362e88a567 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -346,12 +346,6 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 	return 0;
 }
 
-static int is_external_interrupt(u32 info)
-{
-	info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID;
-	return info == (SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR);
-}
-
 static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -1438,6 +1432,7 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu)
 	 */
 	svm_clear_current_vmcb(svm->vmcb);
 
+	svm_leave_nested(vcpu);
 	svm_free_nested(svm);
 
 	sev_free_vcpu(vcpu);
@@ -2709,9 +2704,9 @@ static int svm_get_msr_feature(struct kvm_msr_entry *msr)
 	msr->data = 0;
 
 	switch (msr->index) {
-	case MSR_F10H_DECFG:
-		if (boot_cpu_has(X86_FEATURE_LFENCE_RDTSC))
-			msr->data |= MSR_F10H_DECFG_LFENCE_SERIALIZE;
+	case MSR_AMD64_DE_CFG:
+		if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC))
+			msr->data |= MSR_AMD64_DE_CFG_LFENCE_SERIALIZE;
 		break;
 	case MSR_IA32_PERF_CAPABILITIES:
 		return 0;
@@ -2812,7 +2807,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			msr_info->data = 0x1E;
 		}
 		break;
-	case MSR_F10H_DECFG:
+	case MSR_AMD64_DE_CFG:
 		msr_info->data = svm->msr_decfg;
 		break;
 	default:
@@ -3041,7 +3036,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_VM_IGNNE:
 		vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
 		break;
-	case MSR_F10H_DECFG: {
+	case MSR_AMD64_DE_CFG: {
 		struct kvm_msr_entry msr_entry;
 
 		msr_entry.index = msr->index;
@@ -3425,15 +3420,6 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 		return 0;
 	}
 
-	if (is_external_interrupt(svm->vmcb->control.exit_int_info) &&
-	    exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR &&
-	    exit_code != SVM_EXIT_NPF && exit_code != SVM_EXIT_TASK_SWITCH &&
-	    exit_code != SVM_EXIT_INTR && exit_code != SVM_EXIT_NMI)
-		printk(KERN_ERR "%s: unexpected exit_int_info 0x%x "
-		       "exit_code 0x%x\n",
-		       __func__, svm->vmcb->control.exit_int_info,
-		       exit_code);
-
 	if (exit_fastpath != EXIT_FASTPATH_NONE)
 		return 1;
 
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 0c62352dda6a..5b0d4859e4b7 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -4854,6 +4854,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 
 static void nested_vmx_triple_fault(struct kvm_vcpu *vcpu)
 {
+	kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 	nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0);
 }
 
@@ -6440,9 +6441,6 @@ out:
 	return kvm_state.size;
 }
 
-/*
- * Forcibly leave nested mode in order to be able to reset the VCPU later on.
- */
 void vmx_leave_nested(struct kvm_vcpu *vcpu)
 {
 	if (is_guest_mode(vcpu)) {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ecea83f0da49..2835bd796639 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -628,6 +628,12 @@ static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vecto
 	ex->payload = payload;
 }
 
+/* Forcibly leave the nested mode in cases like a vCPU reset */
+static void kvm_leave_nested(struct kvm_vcpu *vcpu)
+{
+	kvm_x86_ops.nested_ops->leave_nested(vcpu);
+}
+
 static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 		unsigned nr, bool has_error, u32 error_code,
 	        bool has_payload, unsigned long payload, bool reinject)
@@ -1557,7 +1563,7 @@ static const u32 msr_based_features_all[] = {
 	MSR_IA32_VMX_EPT_VPID_CAP,
 	MSR_IA32_VMX_VMFUNC,
 
-	MSR_F10H_DECFG,
+	MSR_AMD64_DE_CFG,
 	MSR_IA32_UCODE_REV,
 	MSR_IA32_ARCH_CAPABILITIES,
 	MSR_IA32_PERF_CAPABILITIES,
@@ -5195,7 +5201,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 
 	if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
 		if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
-			kvm_x86_ops.nested_ops->leave_nested(vcpu);
+			kvm_leave_nested(vcpu);
 			kvm_smm_changed(vcpu, events->smi.smm);
 		}
 
@@ -9805,7 +9811,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu)
 
 int kvm_check_nested_events(struct kvm_vcpu *vcpu)
 {
-	if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
+	if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
 		kvm_x86_ops.nested_ops->triple_fault(vcpu);
 		return 1;
 	}
@@ -10560,15 +10566,16 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			r = 0;
 			goto out;
 		}
-		if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
-			if (is_guest_mode(vcpu)) {
+		if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
+			if (is_guest_mode(vcpu))
 				kvm_x86_ops.nested_ops->triple_fault(vcpu);
-			} else {
+
+			if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
 				vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
 				vcpu->mmio_needed = 0;
 				r = 0;
-				goto out;
 			}
+			goto out;
 		}
 		if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) {
 			/* Page is swapped out. Do synthetic halt */
@@ -11997,8 +12004,18 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	WARN_ON_ONCE(!init_event &&
 		     (old_cr0 || kvm_read_cr3(vcpu) || kvm_read_cr4(vcpu)));
 
+	/*
+	 * SVM doesn't unconditionally VM-Exit on INIT and SHUTDOWN, thus it's
+	 * possible to INIT the vCPU while L2 is active.  Force the vCPU back
+	 * into L1 as EFER.SVME is cleared on INIT (along with all other EFER
+	 * bits), i.e. virtualization is disabled.
+	 */
+	if (is_guest_mode(vcpu))
+		kvm_leave_nested(vcpu);
+
 	kvm_lapic_reset(vcpu, init_event);
 
+	WARN_ON_ONCE(is_guest_mode(vcpu) || is_smm(vcpu));
 	vcpu->arch.hflags = 0;
 
 	vcpu->arch.smi_pending = 0;
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 2dae413bd62a..f3098c0e386a 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -954,6 +954,14 @@ static int kvm_xen_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
 	return kvm_xen_hypercall_set_result(vcpu, run->xen.u.hcall.result);
 }
 
+static inline int max_evtchn_port(struct kvm *kvm)
+{
+	if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode)
+		return EVTCHN_2L_NR_CHANNELS;
+	else
+		return COMPAT_EVTCHN_2L_NR_CHANNELS;
+}
+
 static bool wait_pending_event(struct kvm_vcpu *vcpu, int nr_ports,
 			       evtchn_port_t *ports)
 {
@@ -1042,6 +1050,10 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode,
 			*r = -EFAULT;
 			goto out;
 		}
+		if (ports[i] >= max_evtchn_port(vcpu->kvm)) {
+			*r = -EINVAL;
+			goto out;
+		}
 	}
 
 	if (sched_poll.nr_ports == 1)
@@ -1215,6 +1227,7 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
 	bool longmode;
 	u64 input, params[6], r = -ENOSYS;
 	bool handled = false;
+	u8 cpl;
 
 	input = (u64)kvm_register_read(vcpu, VCPU_REGS_RAX);
 
@@ -1242,9 +1255,17 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
 		params[5] = (u64)kvm_r9_read(vcpu);
 	}
 #endif
+	cpl = static_call(kvm_x86_get_cpl)(vcpu);
 	trace_kvm_xen_hypercall(input, params[0], params[1], params[2],
 				params[3], params[4], params[5]);
 
+	/*
+	 * Only allow hypercall acceleration for CPL0. The rare hypercalls that
+	 * are permitted in guest userspace can be handled by the VMM.
+	 */
+	if (unlikely(cpl > 0))
+		goto handle_in_userspace;
+
 	switch (input) {
 	case __HYPERVISOR_xen_version:
 		if (params[0] == XENVER_version && vcpu->kvm->arch.xen.xen_version) {
@@ -1279,10 +1300,11 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
 	if (handled)
 		return kvm_xen_hypercall_set_result(vcpu, r);
 
+handle_in_userspace:
 	vcpu->run->exit_reason = KVM_EXIT_XEN;
 	vcpu->run->xen.type = KVM_EXIT_XEN_HCALL;
 	vcpu->run->xen.u.hcall.longmode = longmode;
-	vcpu->run->xen.u.hcall.cpl = static_call(kvm_x86_get_cpl)(vcpu);
+	vcpu->run->xen.u.hcall.cpl = cpl;
 	vcpu->run->xen.u.hcall.input = input;
 	vcpu->run->xen.u.hcall.params[0] = params[0];
 	vcpu->run->xen.u.hcall.params[1] = params[1];
@@ -1297,14 +1319,6 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
-static inline int max_evtchn_port(struct kvm *kvm)
-{
-	if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode)
-		return EVTCHN_2L_NR_CHANNELS;
-	else
-		return COMPAT_EVTCHN_2L_NR_CHANNELS;
-}
-
 static void kvm_xen_check_poller(struct kvm_vcpu *vcpu, int port)
 {
 	int poll_evtchn = vcpu->arch.xen.poll_evtchn;
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 78c5bc654cff..6453fbaedb08 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -217,9 +217,15 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size,
 	 * Mappings have to be page-aligned
 	 */
 	offset = phys_addr & ~PAGE_MASK;
-	phys_addr &= PHYSICAL_PAGE_MASK;
+	phys_addr &= PAGE_MASK;
 	size = PAGE_ALIGN(last_addr+1) - phys_addr;
 
+	/*
+	 * Mask out any bits not part of the actual physical
+	 * address, like memory encryption bits.
+	 */
+	phys_addr &= PHYSICAL_PAGE_MASK;
+
 	retval = memtype_reserve(phys_addr, (u64)phys_addr + size,
 						pcm, &new_pcm);
 	if (retval) {
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 00127abd89ee..99620428ad78 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -11,7 +11,6 @@
 #include <linux/bpf.h>
 #include <linux/memory.h>
 #include <linux/sort.h>
-#include <linux/init.h>
 #include <asm/extable.h>
 #include <asm/set_memory.h>
 #include <asm/nospec-branch.h>
@@ -389,18 +388,6 @@ out:
 	return ret;
 }
 
-int __init bpf_arch_init_dispatcher_early(void *ip)
-{
-	const u8 *nop_insn = x86_nops[5];
-
-	if (is_endbr(*(u32 *)ip))
-		ip += ENDBR_INSN_SIZE;
-
-	if (memcmp(ip, nop_insn, X86_PATCH_SIZE))
-		text_poke_early(ip, nop_insn, X86_PATCH_SIZE);
-	return 0;
-}
-
 int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 		       void *old_addr, void *new_addr)
 {
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index bb176c72891c..93ae33248f42 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -513,15 +513,23 @@ static int pm_cpu_check(const struct x86_cpu_id *c)
 
 static void pm_save_spec_msr(void)
 {
-	u32 spec_msr_id[] = {
-		MSR_IA32_SPEC_CTRL,
-		MSR_IA32_TSX_CTRL,
-		MSR_TSX_FORCE_ABORT,
-		MSR_IA32_MCU_OPT_CTRL,
-		MSR_AMD64_LS_CFG,
+	struct msr_enumeration {
+		u32 msr_no;
+		u32 feature;
+	} msr_enum[] = {
+		{ MSR_IA32_SPEC_CTRL,	 X86_FEATURE_MSR_SPEC_CTRL },
+		{ MSR_IA32_TSX_CTRL,	 X86_FEATURE_MSR_TSX_CTRL },
+		{ MSR_TSX_FORCE_ABORT,	 X86_FEATURE_TSX_FORCE_ABORT },
+		{ MSR_IA32_MCU_OPT_CTRL, X86_FEATURE_SRBDS_CTRL },
+		{ MSR_AMD64_LS_CFG,	 X86_FEATURE_LS_CFG_SSBD },
+		{ MSR_AMD64_DE_CFG,	 X86_FEATURE_LFENCE_RDTSC },
 	};
+	int i;
 
-	msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id));
+	for (i = 0; i < ARRAY_SIZE(msr_enum); i++) {
+		if (boot_cpu_has(msr_enum[i].feature))
+			msr_build_context(&msr_enum[i].msr_no, 1);
+	}
 }
 
 static int pm_check_save_msr(void)
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index f82857e48815..038da45f057a 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -23,6 +23,7 @@
 #include <linux/start_kernel.h>
 #include <linux/sched.h>
 #include <linux/kprobes.h>
+#include <linux/kstrtox.h>
 #include <linux/memblock.h>
 #include <linux/export.h>
 #include <linux/mm.h>
@@ -113,7 +114,7 @@ static __read_mostly bool xen_msr_safe = IS_ENABLED(CONFIG_XEN_PV_MSR_SAFE);
 static int __init parse_xen_msr_safe(char *str)
 {
 	if (str)
-		return strtobool(str, &xen_msr_safe);
+		return kstrtobool(str, &xen_msr_safe);
 	return -EINVAL;
 }
 early_param("xen_msr_safe", parse_xen_msr_safe);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 4f4309500559..8db26f10fb1d 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -7,6 +7,7 @@
 
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/kstrtox.h>
 #include <linux/mm.h>
 #include <linux/pm.h>
 #include <linux/memblock.h>
@@ -85,7 +86,7 @@ static void __init xen_parse_512gb(void)
 	arg = strstr(xen_start_info->cmd_line, "xen_512gb_limit=");
 	if (!arg)
 		val = true;
-	else if (strtobool(arg + strlen("xen_512gb_limit="), &val))
+	else if (kstrtobool(arg + strlen("xen_512gb_limit="), &val))
 		return;
 
 	xen_512gb_limit = val;