24 files changed, 289 insertions, 126 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9f190ec4f953..741a19a2fe38 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1405,7 +1405,7 @@ config HIGHMEM4G
 
 config HIGHMEM64G
 	bool "64GB"
-	depends on !M486SX && !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6
+	depends on !M486SX && !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !MWINCHIP3D && !MK6
 	select X86_PAE
 	help
 	  Select this if you have a 32-bit processor and more than 4
@@ -2833,8 +2833,6 @@ config HAVE_ATOMIC_IOMAP
 	def_bool y
 	depends on X86_32
 
-source "drivers/firmware/Kconfig"
-
 source "arch/x86/kvm/Kconfig"
 
 source "arch/x86/Kconfig.assembler"
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 32a1ad356c18..db2d92fb44da 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -122,17 +122,27 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector,
 	ipi_arg->reserved = 0;
 	ipi_arg->vp_set.valid_bank_mask = 0;
 
-	if (!cpumask_equal(mask, cpu_present_mask)) {
+	/*
+	 * Use HV_GENERIC_SET_ALL and avoid converting cpumask to VP_SET
+	 * when the IPI is sent to all currently present CPUs.
+	 */
+	if (!cpumask_equal(mask, cpu_present_mask) || exclude_self) {
 		ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
 		if (exclude_self)
 			nr_bank = cpumask_to_vpset_noself(&(ipi_arg->vp_set), mask);
 		else
 			nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask);
-	}
-	if (nr_bank < 0)
-		goto ipi_mask_ex_done;
-	if (!nr_bank)
+
+		/*
+		 * 'nr_bank <= 0' means some CPUs in cpumask can't be
+		 * represented in VP_SET. Return an error and fall back to
+		 * native (architectural) method of sending IPIs.
+		 */
+		if (nr_bank <= 0)
+			goto ipi_mask_ex_done;
+	} else {
 		ipi_arg->vp_set.format = HV_GENERIC_SET_ALL;
+	}
 
 	status = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank,
 			      ipi_arg, NULL);
diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index 14ebd2196569..43184640b579 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -25,7 +25,7 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs)
 		 * For !SMAP hardware we patch out CLAC on entry.
 		 */
 		if (boot_cpu_has(X86_FEATURE_SMAP) ||
-		    (IS_ENABLED(CONFIG_64_BIT) && boot_cpu_has(X86_FEATURE_XENPV)))
+		    (IS_ENABLED(CONFIG_64BIT) && boot_cpu_has(X86_FEATURE_XENPV)))
 			mask |= X86_EFLAGS_AC;
 
 		WARN_ON_ONCE(flags & mask);
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index fa5cd05d3b5b..ec060c433589 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -53,6 +53,7 @@ static inline u64 lower_bits(u64 val, unsigned int bits)
 
 struct real_mode_header;
 enum stack_type;
+struct ghcb;
 
 /* Early IDT entry points for #VC handler */
 extern void vc_no_ghcb(void);
@@ -81,6 +82,11 @@ static __always_inline void sev_es_nmi_complete(void)
 		__sev_es_nmi_complete();
 }
 extern int __init sev_es_efi_map_ghcbs(pgd_t *pgd);
+extern enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
+					  bool set_ghcb_msr,
+					  struct es_em_ctxt *ctxt,
+					  u64 exit_code, u64 exit_info_1,
+					  u64 exit_info_2);
 #else
 static inline void sev_es_ist_enter(struct pt_regs *regs) { }
 static inline void sev_es_ist_exit(void) { }
diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h
index 3506d8c598c1..4557f7cb0fa6 100644
--- a/arch/x86/include/asm/xen/pci.h
+++ b/arch/x86/include/asm/xen/pci.h
@@ -14,16 +14,19 @@ static inline int pci_xen_hvm_init(void)
 	return -1;
 }
 #endif
-#if defined(CONFIG_XEN_DOM0)
+#ifdef CONFIG_XEN_PV_DOM0
 int __init pci_xen_initial_domain(void);
-int xen_find_device_domain_owner(struct pci_dev *dev);
-int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain);
-int xen_unregister_device_domain_owner(struct pci_dev *dev);
 #else
 static inline int __init pci_xen_initial_domain(void)
 {
 	return -1;
 }
+#endif
+#ifdef CONFIG_XEN_DOM0
+int xen_find_device_domain_owner(struct pci_dev *dev);
+int xen_register_device_domain_owner(struct pci_dev *dev, uint16_t domain);
+int xen_unregister_device_domain_owner(struct pci_dev *dev);
+#else
 static inline int xen_find_device_domain_owner(struct pci_dev *dev)
 {
 	return -1;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 0f8885949e8c..b3410f1ac217 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -326,6 +326,7 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c)
 #ifdef CONFIG_X86_SMAP
 		cr4_set_bits(X86_CR4_SMAP);
 #else
+		clear_cpu_cap(c, X86_FEATURE_SMAP);
 		cr4_clear_bits(X86_CR4_SMAP);
 #endif
 	}
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 4b8813bafffd..bb1c3f5f60c8 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -527,12 +527,14 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 	rdt_domain_reconfigure_cdp(r);
 
 	if (r->alloc_capable && domain_setup_ctrlval(r, d)) {
-		kfree(d);
+		kfree(hw_dom);
 		return;
 	}
 
 	if (r->mon_capable && domain_setup_mon_state(r, d)) {
-		kfree(d);
+		kfree(hw_dom->ctrl_val);
+		kfree(hw_dom->mbps_val);
+		kfree(hw_dom);
 		return;
 	}
 
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 38837dad46e6..391a4e2b8604 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -714,12 +714,6 @@ static struct chipset early_qrk[] __initdata = {
 	 */
 	{ PCI_VENDOR_ID_INTEL, 0x0f00,
 		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
-	{ PCI_VENDOR_ID_INTEL, 0x3e20,
-		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
-	{ PCI_VENDOR_ID_INTEL, 0x3ec4,
-		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
-	{ PCI_VENDOR_ID_INTEL, 0x8a12,
-		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
 	{ PCI_VENDOR_ID_BROADCOM, 0x4331,
 	  PCI_CLASS_NETWORK_OTHER, PCI_ANY_ID, 0, apple_airport_reset},
 	{}
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 445c57c9c539..fa17a27390ab 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -379,9 +379,14 @@ static int __fpu_restore_sig(void __user *buf, void __user *buf_fx,
 				     sizeof(fpu->state.fxsave)))
 			return -EFAULT;
 
-		/* Reject invalid MXCSR values. */
-		if (fpu->state.fxsave.mxcsr & ~mxcsr_feature_mask)
-			return -EINVAL;
+		if (IS_ENABLED(CONFIG_X86_64)) {
+			/* Reject invalid MXCSR values. */
+			if (fpu->state.fxsave.mxcsr & ~mxcsr_feature_mask)
+				return -EINVAL;
+		} else {
+			/* Mask invalid bits out for historical reasons (broken hardware). */
+			fpu->state.fxsave.mxcsr &= ~mxcsr_feature_mask;
+		}
 
 		/* Enforce XFEATURE_MASK_FPSSE when XSAVE is enabled */
 		if (use_xsave())
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 42fc41dd0e1f..882213df3713 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -10,6 +10,7 @@
 #include <asm/irq_remapping.h>
 #include <asm/hpet.h>
 #include <asm/time.h>
+#include <asm/mwait.h>
 
 #undef  pr_fmt
 #define pr_fmt(fmt) "hpet: " fmt
@@ -916,6 +917,83 @@ static bool __init hpet_counting(void)
 	return false;
 }
 
+static bool __init mwait_pc10_supported(void)
+{
+	unsigned int eax, ebx, ecx, mwait_substates;
+
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return false;
+
+	if (!cpu_feature_enabled(X86_FEATURE_MWAIT))
+		return false;
+
+	if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
+		return false;
+
+	cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &mwait_substates);
+
+	return (ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) &&
+	       (ecx & CPUID5_ECX_INTERRUPT_BREAK) &&
+	       (mwait_substates & (0xF << 28));
+}
+
+/*
+ * Check whether the system supports PC10. If so force disable HPET as that
+ * stops counting in PC10. This check is overbroad as it does not take any
+ * of the following into account:
+ *
+ *	- ACPI tables
+ *	- Enablement of intel_idle
+ *	- Command line arguments which limit intel_idle C-state support
+ *
+ * That's perfectly fine. HPET is a piece of hardware designed by committee
+ * and the only reasons why it is still in use on modern systems is the
+ * fact that it is impossible to reliably query TSC and CPU frequency via
+ * CPUID or firmware.
+ *
+ * If HPET is functional it is useful for calibrating TSC, but this can be
+ * done via PMTIMER as well which seems to be the last remaining timer on
+ * X86/INTEL platforms that has not been completely wreckaged by feature
+ * creep.
+ *
+ * In theory HPET support should be removed altogether, but there are older
+ * systems out there which depend on it because TSC and APIC timer are
+ * dysfunctional in deeper C-states.
+ *
+ * It's only 20 years now that hardware people have been asked to provide
+ * reliable and discoverable facilities which can be used for timekeeping
+ * and per CPU timer interrupts.
+ *
+ * The probability that this problem is going to be solved in the
+ * forseeable future is close to zero, so the kernel has to be cluttered
+ * with heuristics to keep up with the ever growing amount of hardware and
+ * firmware trainwrecks. Hopefully some day hardware people will understand
+ * that the approach of "This can be fixed in software" is not sustainable.
+ * Hope dies last...
+ */
+static bool __init hpet_is_pc10_damaged(void)
+{
+	unsigned long long pcfg;
+
+	/* Check whether PC10 substates are supported */
+	if (!mwait_pc10_supported())
+		return false;
+
+	/* Check whether PC10 is enabled in PKG C-state limit */
+	rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, pcfg);
+	if ((pcfg & 0xF) < 8)
+		return false;
+
+	if (hpet_force_user) {
+		pr_warn("HPET force enabled via command line, but dysfunctional in PC10.\n");
+		return false;
+	}
+
+	pr_info("HPET dysfunctional in PC10. Force disabled.\n");
+	boot_hpet_disable = true;
+	return true;
+}
+
 /**
  * hpet_enable - Try to setup the HPET timer. Returns 1 on success.
  */
@@ -929,6 +1007,9 @@ int __init hpet_enable(void)
 	if (!is_hpet_capable())
 		return 0;
 
+	if (hpet_is_pc10_damaged())
+		return 0;
+
 	hpet_set_mapping();
 	if (!hpet_virt_address)
 		return 0;
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index 9f90f460a28c..0aacd6047ef2 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -94,25 +94,15 @@ static void vc_finish_insn(struct es_em_ctxt *ctxt)
 	ctxt->regs->ip += ctxt->insn.length;
 }
 
-static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
-					  struct es_em_ctxt *ctxt,
-					  u64 exit_code, u64 exit_info_1,
-					  u64 exit_info_2)
+static enum es_result verify_exception_info(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 {
-	enum es_result ret;
-
-	/* Fill in protocol and format specifiers */
-	ghcb->protocol_version = GHCB_PROTOCOL_MAX;
-	ghcb->ghcb_usage       = GHCB_DEFAULT_USAGE;
-
-	ghcb_set_sw_exit_code(ghcb, exit_code);
-	ghcb_set_sw_exit_info_1(ghcb, exit_info_1);
-	ghcb_set_sw_exit_info_2(ghcb, exit_info_2);
+	u32 ret;
 
-	sev_es_wr_ghcb_msr(__pa(ghcb));
-	VMGEXIT();
+	ret = ghcb->save.sw_exit_info_1 & GENMASK_ULL(31, 0);
+	if (!ret)
+		return ES_OK;
 
-	if ((ghcb->save.sw_exit_info_1 & 0xffffffff) == 1) {
+	if (ret == 1) {
 		u64 info = ghcb->save.sw_exit_info_2;
 		unsigned long v;
 
@@ -124,17 +114,40 @@ static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
 		    ((v == X86_TRAP_GP) || (v == X86_TRAP_UD)) &&
 		    ((info & SVM_EVTINJ_TYPE_MASK) == SVM_EVTINJ_TYPE_EXEPT)) {
 			ctxt->fi.vector = v;
+
 			if (info & SVM_EVTINJ_VALID_ERR)
 				ctxt->fi.error_code = info >> 32;
-			ret = ES_EXCEPTION;
-		} else {
-			ret = ES_VMM_ERROR;
+
+			return ES_EXCEPTION;
 		}
-	} else {
-		ret = ES_OK;
 	}
 
-	return ret;
+	return ES_VMM_ERROR;
+}
+
+enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr,
+				   struct es_em_ctxt *ctxt, u64 exit_code,
+				   u64 exit_info_1, u64 exit_info_2)
+{
+	/* Fill in protocol and format specifiers */
+	ghcb->protocol_version = GHCB_PROTOCOL_MAX;
+	ghcb->ghcb_usage       = GHCB_DEFAULT_USAGE;
+
+	ghcb_set_sw_exit_code(ghcb, exit_code);
+	ghcb_set_sw_exit_info_1(ghcb, exit_info_1);
+	ghcb_set_sw_exit_info_2(ghcb, exit_info_2);
+
+	/*
+	 * Hyper-V unenlightened guests use a paravisor for communicating and
+	 * GHCB pages are being allocated and set up by that paravisor. Linux
+	 * should not change the GHCB page's physical address.
+	 */
+	if (set_ghcb_msr)
+		sev_es_wr_ghcb_msr(__pa(ghcb));
+
+	VMGEXIT();
+
+	return verify_exception_info(ghcb, ctxt);
 }
 
 /*
@@ -411,7 +424,7 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 		 */
 		sw_scratch = __pa(ghcb) + offsetof(struct ghcb, shared_buffer);
 		ghcb_set_sw_scratch(ghcb, sw_scratch);
-		ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO,
+		ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_IOIO,
 					  exit_info_1, exit_info_2);
 		if (ret != ES_OK)
 			return ret;
@@ -453,7 +466,8 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 
 		ghcb_set_rax(ghcb, rax);
 
-		ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO, exit_info_1, 0);
+		ret = sev_es_ghcb_hv_call(ghcb, true, ctxt,
+					  SVM_EXIT_IOIO, exit_info_1, 0);
 		if (ret != ES_OK)
 			return ret;
 
@@ -484,7 +498,7 @@ static enum es_result vc_handle_cpuid(struct ghcb *ghcb,
 		/* xgetbv will cause #GP - use reset value for xcr0 */
 		ghcb_set_xcr0(ghcb, 1);
 
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0);
+	ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_CPUID, 0, 0);
 	if (ret != ES_OK)
 		return ret;
 
@@ -509,7 +523,7 @@ static enum es_result vc_handle_rdtsc(struct ghcb *ghcb,
 	bool rdtscp = (exit_code == SVM_EXIT_RDTSCP);
 	enum es_result ret;
 
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, 0, 0);
+	ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, exit_code, 0, 0);
 	if (ret != ES_OK)
 		return ret;
 
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 53a6837d354b..3946e77e622b 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -648,7 +648,8 @@ static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 		ghcb_set_rdx(ghcb, regs->dx);
 	}
 
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MSR, exit_info_1, 0);
+	ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_MSR,
+				  exit_info_1, 0);
 
 	if ((ret == ES_OK) && (!exit_info_1)) {
 		regs->ax = ghcb->save.rax;
@@ -867,7 +868,7 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
 
 	ghcb_set_sw_scratch(ghcb, ghcb_pa + offsetof(struct ghcb, shared_buffer));
 
-	return sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, exit_info_1, exit_info_2);
+	return sev_es_ghcb_hv_call(ghcb, true, ctxt, exit_code, exit_info_1, exit_info_2);
 }
 
 static enum es_result vc_handle_mmio_twobyte_ops(struct ghcb *ghcb,
@@ -1117,7 +1118,7 @@ static enum es_result vc_handle_dr7_write(struct ghcb *ghcb,
 
 	/* Using a value of 0 for ExitInfo1 means RAX holds the value */
 	ghcb_set_rax(ghcb, val);
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WRITE_DR7, 0, 0);
+	ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_WRITE_DR7, 0, 0);
 	if (ret != ES_OK)
 		return ret;
 
@@ -1147,7 +1148,7 @@ static enum es_result vc_handle_dr7_read(struct ghcb *ghcb,
 static enum es_result vc_handle_wbinvd(struct ghcb *ghcb,
 				       struct es_em_ctxt *ctxt)
 {
-	return sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0);
+	return sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_WBINVD, 0, 0);
 }
 
 static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
@@ -1156,7 +1157,7 @@ static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt
 
 	ghcb_set_rcx(ghcb, ctxt->regs->cx);
 
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_RDPMC, 0, 0);
+	ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_RDPMC, 0, 0);
 	if (ret != ES_OK)
 		return ret;
 
@@ -1197,7 +1198,7 @@ static enum es_result vc_handle_vmmcall(struct ghcb *ghcb,
 	if (x86_platform.hyper.sev_es_hcall_prepare)
 		x86_platform.hyper.sev_es_hcall_prepare(ghcb, ctxt->regs);
 
-	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_VMMCALL, 0, 0);
+	ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_VMMCALL, 0, 0);
 	if (ret != ES_OK)
 		return ret;
 
@@ -1319,13 +1320,26 @@ static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt)
 	}
 }
 
-static __always_inline bool on_vc_fallback_stack(struct pt_regs *regs)
+static __always_inline bool is_vc2_stack(unsigned long sp)
 {
-	unsigned long sp = (unsigned long)regs;
-
 	return (sp >= __this_cpu_ist_bottom_va(VC2) && sp < __this_cpu_ist_top_va(VC2));
 }
 
+static __always_inline bool vc_from_invalid_context(struct pt_regs *regs)
+{
+	unsigned long sp, prev_sp;
+
+	sp      = (unsigned long)regs;
+	prev_sp = regs->sp;
+
+	/*
+	 * If the code was already executing on the VC2 stack when the #VC
+	 * happened, let it proceed to the normal handling routine. This way the
+	 * code executing on the VC2 stack can cause #VC exceptions to get handled.
+	 */
+	return is_vc2_stack(sp) && !is_vc2_stack(prev_sp);
+}
+
 static bool vc_raw_handle_exception(struct pt_regs *regs, unsigned long error_code)
 {
 	struct ghcb_state state;
@@ -1406,7 +1420,7 @@ DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication)
 	 * But keep this here in case the noinstr annotations are violated due
 	 * to bug elsewhere.
 	 */
-	if (unlikely(on_vc_fallback_stack(regs))) {
+	if (unlikely(vc_from_invalid_context(regs))) {
 		instrumentation_begin();
 		panic("Can't handle #VC exception from unsupported context\n");
 		instrumentation_end();
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index a58800973aed..f516f2b4797e 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -709,7 +709,7 @@ asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *r
 	stack = (unsigned long *)sp;
 
 	if (!get_stack_info_noinstr(stack, current, &info) || info.type == STACK_TYPE_ENTRY ||
-	    info.type >= STACK_TYPE_EXCEPTION_LAST)
+	    info.type > STACK_TYPE_EXCEPTION_LAST)
 		sp = __this_cpu_ist_top_va(VC2);
 
 sync:
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index f8c612902038..3f0abb403340 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -27,6 +27,15 @@
 #undef CONFIG_PARAVIRT_XXL
 #undef CONFIG_PARAVIRT_SPINLOCKS
 
+/*
+ * This code runs before CPU feature bits are set. By default, the
+ * pgtable_l5_enabled() function uses bit X86_FEATURE_LA57 to determine if
+ * 5-level paging is active, so that won't work here. USE_EARLY_PGTABLE_L5
+ * is provided to handle this situation and, instead, use a variable that
+ * has been set by the early boot code.
+ */
+#define USE_EARLY_PGTABLE_L5
+
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/mem_encrypt.h>
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 3d41a09c2c14..5debe4ac6f81 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -113,7 +113,7 @@ static int acpi_register_gsi_xen_hvm(struct device *dev, u32 gsi,
 				 false /* no mapping of GSI to PIRQ */);
 }
 
-#ifdef CONFIG_XEN_DOM0
+#ifdef CONFIG_XEN_PV_DOM0
 static int xen_register_gsi(u32 gsi, int triggering, int polarity)
 {
 	int rc, irq;
@@ -261,7 +261,7 @@ error:
 	return irq;
 }
 
-#ifdef CONFIG_XEN_DOM0
+#ifdef CONFIG_XEN_PV_DOM0
 static bool __read_mostly pci_seg_supported = true;
 
 static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
@@ -375,10 +375,10 @@ static void xen_initdom_restore_msi_irqs(struct pci_dev *dev)
 		WARN(ret && ret != -ENOSYS, "restore_msi -> %d\n", ret);
 	}
 }
-#else /* CONFIG_XEN_DOM0 */
+#else /* CONFIG_XEN_PV_DOM0 */
 #define xen_initdom_setup_msi_irqs	NULL
 #define xen_initdom_restore_msi_irqs	NULL
-#endif /* !CONFIG_XEN_DOM0 */
+#endif /* !CONFIG_XEN_PV_DOM0 */
 
 static void xen_teardown_msi_irqs(struct pci_dev *dev)
 {
@@ -555,7 +555,7 @@ int __init pci_xen_hvm_init(void)
 	return 0;
 }
 
-#ifdef CONFIG_XEN_DOM0
+#ifdef CONFIG_XEN_PV_DOM0
 int __init pci_xen_initial_domain(void)
 {
 	int irq;
@@ -583,6 +583,9 @@ int __init pci_xen_initial_domain(void)
 	}
 	return 0;
 }
+#endif
+
+#ifdef CONFIG_XEN_DOM0
 
 struct xen_device_domain_owner {
 	domid_t domain;
@@ -656,4 +659,4 @@ int xen_unregister_device_domain_owner(struct pci_dev *dev)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xen_unregister_device_domain_owner);
-#endif
+#endif /* CONFIG_XEN_DOM0 */
diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c
index ee2beda590d0..1d4a00e767ec 100644
--- a/arch/x86/platform/olpc/olpc.c
+++ b/arch/x86/platform/olpc/olpc.c
@@ -274,7 +274,7 @@ static struct olpc_ec_driver ec_xo1_driver = {
 
 static struct olpc_ec_driver ec_xo1_5_driver = {
 	.ec_cmd = olpc_xo1_ec_cmd,
-#ifdef CONFIG_OLPC_XO1_5_SCI
+#ifdef CONFIG_OLPC_XO15_SCI
 	/*
 	 * XO-1.5 EC wakeups are available when olpc-xo15-sci driver is
 	 * compiled in
diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c
index 9ac7457f52a3..ed0442e35434 100644
--- a/arch/x86/platform/pvh/enlighten.c
+++ b/arch/x86/platform/pvh/enlighten.c
@@ -16,15 +16,15 @@
 /*
  * PVH variables.
  *
- * pvh_bootparams and pvh_start_info need to live in the data segment since
+ * pvh_bootparams and pvh_start_info need to live in a data segment since
  * they are used after startup_{32|64}, which clear .bss, are invoked.
  */
-struct boot_params pvh_bootparams __section(".data");
-struct hvm_start_info pvh_start_info __section(".data");
+struct boot_params __initdata pvh_bootparams;
+struct hvm_start_info __initdata pvh_start_info;
 
-unsigned int pvh_start_info_sz = sizeof(pvh_start_info);
+const unsigned int __initconst pvh_start_info_sz = sizeof(pvh_start_info);
 
-static u64 pvh_get_root_pointer(void)
+static u64 __init pvh_get_root_pointer(void)
 {
 	return pvh_start_info.rsdp_paddr;
 }
@@ -107,7 +107,7 @@ void __init __weak xen_pvh_init(struct boot_params *boot_params)
 	BUG();
 }
 
-static void hypervisor_specific_init(bool xen_guest)
+static void __init hypervisor_specific_init(bool xen_guest)
 {
 	if (xen_guest)
 		xen_pvh_init(&pvh_bootparams);
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index afc1da68b06d..6bcd3d8ca6ac 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -43,13 +43,9 @@ config XEN_PV_SMP
 	def_bool y
 	depends on XEN_PV && SMP
 
-config XEN_DOM0
-	bool "Xen PV Dom0 support"
-	default y
-	depends on XEN_PV && PCI_XEN && SWIOTLB_XEN
-	depends on X86_IO_APIC && ACPI && PCI
-	help
-	  Support running as a Xen PV Dom0 guest.
+config XEN_PV_DOM0
+	def_bool y
+	depends on XEN_PV && XEN_DOM0
 
 config XEN_PVHVM
 	def_bool y
@@ -86,3 +82,12 @@ config XEN_PVH
 	def_bool n
 	help
 	  Support for running as a Xen PVH guest.
+
+config XEN_DOM0
+	bool "Xen Dom0 support"
+	default XEN_PV
+	depends on (XEN_PV && SWIOTLB_XEN) || (XEN_PVH && X86_64)
+	depends on X86_IO_APIC && ACPI && PCI
+	select X86_X2APIC if XEN_PVH && X86_64
+	help
+	  Support running as a Xen Dom0 guest.
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 40b5779fce21..4953260e281c 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -45,7 +45,7 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
 
 obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
 
-obj-$(CONFIG_XEN_DOM0)		+= vga.o
+obj-$(CONFIG_XEN_PV_DOM0)	+= vga.o
 
 obj-$(CONFIG_SWIOTLB_XEN)	+= pci-swiotlb-xen.o
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c79bd0af2e8c..95d970359e17 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -3,6 +3,7 @@
 #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG
 #include <linux/memblock.h>
 #endif
+#include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/kexec.h>
 #include <linux/slab.h>
@@ -10,12 +11,15 @@
 
 #include <xen/xen.h>
 #include <xen/features.h>
+#include <xen/interface/sched.h>
+#include <xen/interface/version.h>
 #include <xen/page.h>
 
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/cpu.h>
 #include <asm/e820/api.h> 
+#include <asm/setup.h>
 
 #include "xen-ops.h"
 #include "smp.h"
@@ -52,9 +56,6 @@ DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
 DEFINE_PER_CPU(uint32_t, xen_vcpu_id);
 EXPORT_PER_CPU_SYMBOL(xen_vcpu_id);
 
-enum xen_domain_type xen_domain_type = XEN_NATIVE;
-EXPORT_SYMBOL_GPL(xen_domain_type);
-
 unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START;
 EXPORT_SYMBOL(machine_to_phys_mapping);
 unsigned long  machine_to_phys_nr;
@@ -69,10 +70,12 @@ __read_mostly int xen_have_vector_callback;
 EXPORT_SYMBOL_GPL(xen_have_vector_callback);
 
 /*
- * NB: needs to live in .data because it's used by xen_prepare_pvh which runs
- * before clearing the bss.
+ * NB: These need to live in .data or alike because they're used by
+ * xen_prepare_pvh() which runs before clearing the bss.
  */
-uint32_t xen_start_flags __section(".data") = 0;
+enum xen_domain_type __ro_after_init xen_domain_type = XEN_NATIVE;
+EXPORT_SYMBOL_GPL(xen_domain_type);
+uint32_t __ro_after_init xen_start_flags;
 EXPORT_SYMBOL(xen_start_flags);
 
 /*
@@ -258,6 +261,45 @@ int xen_vcpu_setup(int cpu)
 	return ((per_cpu(xen_vcpu, cpu) == NULL) ? -ENODEV : 0);
 }
 
+void __init xen_banner(void)
+{
+	unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL);
+	struct xen_extraversion extra;
+
+	HYPERVISOR_xen_version(XENVER_extraversion, &extra);
+
+	pr_info("Booting kernel on %s\n", pv_info.name);
+	pr_info("Xen version: %u.%u%s%s\n",
+		version >> 16, version & 0xffff, extra.extraversion,
+		xen_feature(XENFEAT_mmu_pt_update_preserve_ad)
+		? " (preserve-AD)" : "");
+}
+
+/* Check if running on Xen version (major, minor) or later */
+bool xen_running_on_version_or_later(unsigned int major, unsigned int minor)
+{
+	unsigned int version;
+
+	if (!xen_domain())
+		return false;
+
+	version = HYPERVISOR_xen_version(XENVER_version, NULL);
+	if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) ||
+		((version >> 16) > major))
+		return true;
+	return false;
+}
+
+void __init xen_add_preferred_consoles(void)
+{
+	add_preferred_console("xenboot", 0, NULL);
+	if (!boot_params.screen_info.orig_video_isVGA)
+		add_preferred_console("tty", 0, NULL);
+	add_preferred_console("hvc", 0, NULL);
+	if (boot_params.screen_info.orig_video_isVGA)
+		add_preferred_console("tty", 0, NULL);
+}
+
 void xen_reboot(int reason)
 {
 	struct sched_shutdown r = { .reason = reason };
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 6e0d0754f94f..a7b7d674f500 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -28,7 +28,6 @@
 #include <linux/mm.h>
 #include <linux/page-flags.h>
 #include <linux/highmem.h>
-#include <linux/console.h>
 #include <linux/pci.h>
 #include <linux/gfp.h>
 #include <linux/edd.h>
@@ -109,17 +108,6 @@ struct tls_descs {
  */
 static DEFINE_PER_CPU(struct tls_descs, shadow_tls_desc);
 
-static void __init xen_banner(void)
-{
-	unsigned version = HYPERVISOR_xen_version(XENVER_version, NULL);
-	struct xen_extraversion extra;
-	HYPERVISOR_xen_version(XENVER_extraversion, &extra);
-
-	pr_info("Booting paravirtualized kernel on %s\n", pv_info.name);
-	pr_info("Xen version: %d.%d%s (preserve-AD)\n",
-		version >> 16, version & 0xffff, extra.extraversion);
-}
-
 static void __init xen_pv_init_platform(void)
 {
 	populate_extra_pte(fix_to_virt(FIX_PARAVIRT_BOOTMAP));
@@ -142,22 +130,6 @@ static void __init xen_pv_guest_late_init(void)
 #endif
 }
 
-/* Check if running on Xen version (major, minor) or later */
-bool
-xen_running_on_version_or_later(unsigned int major, unsigned int minor)
-{
-	unsigned int version;
-
-	if (!xen_domain())
-		return false;
-
-	version = HYPERVISOR_xen_version(XENVER_version, NULL);
-	if ((((version >> 16) == major) && ((version & 0xffff) >= minor)) ||
-		((version >> 16) > major))
-		return true;
-	return false;
-}
-
 static __read_mostly unsigned int cpuid_leaf5_ecx_val;
 static __read_mostly unsigned int cpuid_leaf5_edx_val;
 
@@ -1364,7 +1336,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	boot_params.hdr.hardware_subarch = X86_SUBARCH_XEN;
 
 	if (!xen_initial_domain()) {
-		add_preferred_console("xenboot", 0, NULL);
 		if (pci_xen)
 			x86_init.pci.arch_init = pci_xen_init;
 		x86_platform.set_legacy_features =
@@ -1409,11 +1380,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 #endif
 	}
 
-	if (!boot_params.screen_info.orig_video_isVGA)
-		add_preferred_console("tty", 0, NULL);
-	add_preferred_console("hvc", 0, NULL);
-	if (boot_params.screen_info.orig_video_isVGA)
-		add_preferred_console("tty", 0, NULL);
+	xen_add_preferred_consoles();
 
 #ifdef CONFIG_PCI
 	/* PCI BIOS service won't work from a PV guest. */
diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c
index 0d5e34b9e6f9..bcae606bbc5c 100644
--- a/arch/x86/xen/enlighten_pvh.c
+++ b/arch/x86/xen/enlighten_pvh.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/acpi.h>
+#include <linux/export.h>
 
 #include <xen/hvc-console.h>
 
@@ -18,10 +19,11 @@
 /*
  * PVH variables.
  *
- * The variable xen_pvh needs to live in the data segment since it is used
+ * The variable xen_pvh needs to live in a data segment since it is used
  * after startup_{32|64} is invoked, which will clear the .bss segment.
  */
-bool xen_pvh __section(".data") = 0;
+bool __ro_after_init xen_pvh;
+EXPORT_SYMBOL_GPL(xen_pvh);
 
 void __init xen_pvh_init(struct boot_params *boot_params)
 {
@@ -36,6 +38,10 @@ void __init xen_pvh_init(struct boot_params *boot_params)
 	pfn = __pa(hypercall_page);
 	wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32));
 
+	if (xen_initial_domain())
+		x86_init.oem.arch_setup = xen_add_preferred_consoles;
+	x86_init.oem.banner = xen_banner;
+
 	xen_efi_init(boot_params);
 }
 
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 8d751939c6f3..3359c23573c5 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -2398,7 +2398,7 @@ static int remap_area_pfn_pte_fn(pte_t *ptep, unsigned long addr, void *data)
 
 int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr,
 		  xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot,
-		  unsigned int domid, bool no_translate, struct page **pages)
+		  unsigned int domid, bool no_translate)
 {
 	int err = 0;
 	struct remap_data rmd;
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 8d7ec49a35fb..8bc8b72a205d 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -51,6 +51,7 @@ void __init xen_remap_memory(void);
 phys_addr_t __init xen_find_free_area(phys_addr_t size);
 char * __init xen_memory_setup(void);
 void __init xen_arch_setup(void);
+void xen_banner(void);
 void xen_enable_sysenter(void);
 void xen_enable_syscall(void);
 void xen_vcpu_restore(void);
@@ -109,7 +110,7 @@ static inline void xen_uninit_lock_cpu(int cpu)
 
 struct dom0_vga_console_info;
 
-#ifdef CONFIG_XEN_DOM0
+#ifdef CONFIG_XEN_PV_DOM0
 void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size);
 #else
 static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
@@ -118,6 +119,8 @@ static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
 }
 #endif
 
+void xen_add_preferred_consoles(void);
+
 void __init xen_init_apic(void);
 
 #ifdef CONFIG_XEN_EFI