Merge branch 'kvm-master' into kvm-next

Fixes to get_mmio_spte, destined to 5.10 stable branch.

45 files changed, 331 insertions, 297 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f6946b81f74a..fbf26e0f7a6a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -100,6 +100,7 @@ config X86
 	select ARCH_WANT_DEFAULT_BPF_JIT	if X86_64
 	select ARCH_WANTS_DYNAMIC_TASK_STRUCT
 	select ARCH_WANT_HUGE_PMD_SHARE
+	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANTS_THP_SWAP		if X86_64
 	select BUILDTIME_TABLE_SORT
 	select CLKEVT_I8253
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 154259f18b8b..1bf21746f4ce 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -209,9 +209,6 @@ ifdef CONFIG_X86_64
 LDFLAGS_vmlinux += -z max-page-size=0x200000
 endif
 
-# We never want expected sections to be placed heuristically by the
-# linker. All sections should be explicitly named in the linker script.
-LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
 
 archscripts: scripts_basic
 	$(Q)$(MAKE) $(build)=arch/x86/tools relocs
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index ee249088cbfe..40b8fd375d52 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -61,7 +61,9 @@ KBUILD_LDFLAGS += $(call ld-option,--no-ld-generated-unwind-info)
 # Compressed kernel should be built as PIE since it may be loaded at any
 # address by the bootloader.
 LDFLAGS_vmlinux := -pie $(call ld-option, --no-dynamic-linker)
-LDFLAGS_vmlinux += $(call ld-option, --orphan-handling=warn)
+ifdef CONFIG_LD_ORPHAN_WARN
+LDFLAGS_vmlinux += --orphan-handling=warn
+endif
 LDFLAGS_vmlinux += -T
 
 hostprogs	:= mkpiggy
diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c
index 954cb2702e23..27826c265aab 100644
--- a/arch/x86/boot/compressed/sev-es.c
+++ b/arch/x86/boot/compressed/sev-es.c
@@ -32,13 +32,12 @@ struct ghcb *boot_ghcb;
  */
 static bool insn_has_rep_prefix(struct insn *insn)
 {
+	insn_byte_t p;
 	int i;
 
 	insn_get_prefixes(insn);
 
-	for (i = 0; i < insn->prefixes.nbytes; i++) {
-		insn_byte_t p = insn->prefixes.bytes[i];
-
+	for_each_insn_prefix(insn, i, p) {
 		if (p == 0xf2 || p == 0xf3)
 			return true;
 	}
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 442e1ed4acd4..4eb7ee5fed72 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -107,14 +107,14 @@
 MODULE_LICENSE("GPL");
 
 #define DEFINE_CSTATE_FORMAT_ATTR(_var, _name, _format)		\
-static ssize_t __cstate_##_var##_show(struct kobject *kobj,	\
-				struct kobj_attribute *attr,	\
+static ssize_t __cstate_##_var##_show(struct device *dev,	\
+				struct device_attribute *attr,	\
 				char *page)			\
 {								\
 	BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE);		\
 	return sprintf(page, _format "\n");			\
 }								\
-static struct kobj_attribute format_attr_##_var =		\
+static struct device_attribute format_attr_##_var =		\
 	__ATTR(_name, 0444, __cstate_##_var##_show, NULL)
 
 static ssize_t cstate_get_attr_cpumask(struct device *dev,
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index b47cc4226934..485c5066f8b8 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1916,7 +1916,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 		 * that caused the PEBS record. It's called collision.
 		 * If collision happened, the record will be dropped.
 		 */
-		if (p->status != (1ULL << bit)) {
+		if (pebs_status != (1ULL << bit)) {
 			for_each_set_bit(i, (unsigned long *)&pebs_status, size)
 				error[i]++;
 			continue;
@@ -1940,7 +1940,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 		if (error[bit]) {
 			perf_log_lost_samples(event, error[bit]);
 
-			if (perf_event_account_interrupt(event))
+			if (iregs && perf_event_account_interrupt(event))
 				x86_pmu_stop(event, 0);
 		}
 
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 86d012b3e0b4..80d52cbe2fde 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -94,8 +94,8 @@ end:
 	return map;
 }
 
-ssize_t uncore_event_show(struct kobject *kobj,
-			  struct kobj_attribute *attr, char *buf)
+ssize_t uncore_event_show(struct device *dev,
+			  struct device_attribute *attr, char *buf)
 {
 	struct uncore_event_desc *event =
 		container_of(attr, struct uncore_event_desc, attr);
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 83d2a7d490e0..9efea154349d 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -157,7 +157,7 @@ struct intel_uncore_box {
 #define UNCORE_BOX_FLAG_CFL8_CBOX_MSR_OFFS	2
 
 struct uncore_event_desc {
-	struct kobj_attribute attr;
+	struct device_attribute attr;
 	const char *config;
 };
 
@@ -179,8 +179,8 @@ struct pci2phy_map {
 struct pci2phy_map *__find_pci2phy_map(int segment);
 int uncore_pcibus_to_physid(struct pci_bus *bus);
 
-ssize_t uncore_event_show(struct kobject *kobj,
-			  struct kobj_attribute *attr, char *buf);
+ssize_t uncore_event_show(struct device *dev,
+			  struct device_attribute *attr, char *buf);
 
 static inline struct intel_uncore_pmu *dev_to_uncore_pmu(struct device *dev)
 {
@@ -201,14 +201,14 @@ extern int __uncore_max_dies;
 }
 
 #define DEFINE_UNCORE_FORMAT_ATTR(_var, _name, _format)			\
-static ssize_t __uncore_##_var##_show(struct kobject *kobj,		\
-				struct kobj_attribute *attr,		\
+static ssize_t __uncore_##_var##_show(struct device *dev,		\
+				struct device_attribute *attr,		\
 				char *page)				\
 {									\
 	BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE);			\
 	return sprintf(page, _format "\n");				\
 }									\
-static struct kobj_attribute format_attr_##_var =			\
+static struct device_attribute format_attr_##_var =			\
 	__ATTR(_name, 0444, __uncore_##_var##_show, NULL)
 
 static inline bool uncore_pmc_fixed(int idx)
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 7c0120e2e957..7dbbeaacd995 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -93,18 +93,6 @@ static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = {
  * any other bit is reserved
  */
 #define RAPL_EVENT_MASK	0xFFULL
-
-#define DEFINE_RAPL_FORMAT_ATTR(_var, _name, _format)		\
-static ssize_t __rapl_##_var##_show(struct kobject *kobj,	\
-				struct kobj_attribute *attr,	\
-				char *page)			\
-{								\
-	BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE);		\
-	return sprintf(page, _format "\n");			\
-}								\
-static struct kobj_attribute format_attr_##_var =		\
-	__ATTR(_name, 0444, __rapl_##_var##_show, NULL)
-
 #define RAPL_CNTR_WIDTH 32
 
 #define RAPL_EVENT_ATTR_STR(_name, v, str)					\
@@ -441,7 +429,7 @@ static struct attribute_group rapl_pmu_events_group = {
 	.attrs = attrs_empty,
 };
 
-DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7");
+PMU_FORMAT_ATTR(event, "config:0-7");
 static struct attribute *rapl_formats_attr[] = {
 	&format_attr_event.attr,
 	NULL,
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 5c1ae3eff9d4..a8c3d284fa46 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -201,6 +201,21 @@ static inline int insn_offset_immediate(struct insn *insn)
 	return insn_offset_displacement(insn) + insn->displacement.nbytes;
 }
 
+/**
+ * for_each_insn_prefix() -- Iterate prefixes in the instruction
+ * @insn: Pointer to struct insn.
+ * @idx:  Index storage.
+ * @prefix: Prefix byte.
+ *
+ * Iterate prefix bytes of given @insn. Each prefix byte is stored in @prefix
+ * and the index is stored in @idx (note that this @idx is just for a cursor,
+ * do not change it.)
+ * Since prefixes.nbytes can be bigger than 4 if some prefixes
+ * are repeated, it cannot be used for looping over the prefixes.
+ */
+#define for_each_insn_prefix(insn, idx, prefix)	\
+	for (idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++)
+
 #define POP_SS_OPCODE 0x1f
 #define MOV_SREG_OPCODE 0x8e
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 39707e72b062..3ab7b46087b7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1667,6 +1667,7 @@ int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
+int kvm_cpu_has_extint(struct kvm_vcpu *v);
 int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index e039a933aca3..29dd27b5a339 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -88,8 +88,6 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx,
 
 static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 {
-	trace_hardirqs_on();
-
 	mds_idle_clear_cpu_buffers();
 	/* "mwait %eax, %ecx;" */
 	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 816b31c68550..394757ee030a 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -155,6 +155,7 @@ enum page_cache_mode {
 #define _PAGE_ENC		(_AT(pteval_t, sme_me_mask))
 
 #define _PAGE_CACHE_MASK	(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)
+#define _PAGE_LARGE_CACHE_MASK	(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT_LARGE)
 
 #define _PAGE_NOCACHE		(cachemode2protval(_PAGE_CACHE_MODE_UC))
 #define _PAGE_CACHE_WP		(cachemode2protval(_PAGE_CACHE_MODE_WP))
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 6bfc878f6771..6a9ccc1b2be5 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -28,4 +28,14 @@
 #endif
 
 #endif /* CONFIG_SPARSEMEM */
+
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_NUMA_KEEP_MEMINFO
+extern int phys_to_target_node(phys_addr_t start);
+#define phys_to_target_node phys_to_target_node
+extern int memory_add_physaddr_to_nid(u64 start);
+#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
+#endif
+#endif /* __ASSEMBLY__ */
+
 #endif /* _ASM_X86_SPARSEMEM_H */
diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h
index 0fd4a9dfb29c..ab7382f92aff 100644
--- a/arch/x86/include/asm/sync_core.h
+++ b/arch/x86/include/asm/sync_core.h
@@ -98,12 +98,13 @@ static inline void sync_core_before_usermode(void)
 	/* With PTI, we unconditionally serialize before running user code. */
 	if (static_cpu_has(X86_FEATURE_PTI))
 		return;
+
 	/*
-	 * Return from interrupt and NMI is done through iret, which is core
-	 * serializing.
+	 * Even if we're in an interrupt, we might reschedule before returning,
+	 * in which case we could switch to a different thread in the same mm
+	 * and return using SYSRET or SYSEXIT.  Instead of trying to keep
+	 * track of our need to sync the core, just sync right away.
 	 */
-	if (in_irq() || in_nmi())
-		return;
 	sync_core();
 }
 
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 1eac53632786..758bbf25ef74 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -273,20 +273,24 @@ static int assign_irq_vector_any_locked(struct irq_data *irqd)
 	const struct cpumask *affmsk = irq_data_get_affinity_mask(irqd);
 	int node = irq_data_get_node(irqd);
 
-	if (node == NUMA_NO_NODE)
-		goto all;
-	/* Try the intersection of @affmsk and node mask */
-	cpumask_and(vector_searchmask, cpumask_of_node(node), affmsk);
-	if (!assign_vector_locked(irqd, vector_searchmask))
-		return 0;
-	/* Try the node mask */
-	if (!assign_vector_locked(irqd, cpumask_of_node(node)))
-		return 0;
-all:
+	if (node != NUMA_NO_NODE) {
+		/* Try the intersection of @affmsk and node mask */
+		cpumask_and(vector_searchmask, cpumask_of_node(node), affmsk);
+		if (!assign_vector_locked(irqd, vector_searchmask))
+			return 0;
+	}
+
 	/* Try the full affinity mask */
 	cpumask_and(vector_searchmask, affmsk, cpu_online_mask);
 	if (!assign_vector_locked(irqd, vector_searchmask))
 		return 0;
+
+	if (node != NUMA_NO_NODE) {
+		/* Try the node mask */
+		if (!assign_vector_locked(irqd, cpumask_of_node(node)))
+			return 0;
+	}
+
 	/* Try the full online mask */
 	return assign_vector_locked(irqd, cpu_online_mask);
 }
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 1b98f8c12b96..235f5cde06fc 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -161,7 +161,7 @@ static int __init early_set_hub_type(void)
 	/* UV4/4A only have a revision difference */
 	case UV4_HUB_PART_NUMBER:
 		uv_min_hub_revision_id = node_id.s.revision
-					 + UV4_HUB_REVISION_BASE;
+					 + UV4_HUB_REVISION_BASE - 1;
 		uv_hub_type_set(UV4);
 		if (uv_min_hub_revision_id == UV4A_HUB_REVISION_BASE)
 			uv_hub_type_set(UV4|UV4A);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 581fb7223ad0..d41b70fe4918 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -739,11 +739,13 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 	if (boot_cpu_has(X86_FEATURE_IBPB)) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBPB);
 
+		spectre_v2_user_ibpb = mode;
 		switch (cmd) {
 		case SPECTRE_V2_USER_CMD_FORCE:
 		case SPECTRE_V2_USER_CMD_PRCTL_IBPB:
 		case SPECTRE_V2_USER_CMD_SECCOMP_IBPB:
 			static_branch_enable(&switch_mm_always_ibpb);
+			spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT;
 			break;
 		case SPECTRE_V2_USER_CMD_PRCTL:
 		case SPECTRE_V2_USER_CMD_AUTO:
@@ -757,8 +759,6 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 		pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n",
 			static_key_enabled(&switch_mm_always_ibpb) ?
 			"always-on" : "conditional");
-
-		spectre_v2_user_ibpb = mode;
 	}
 
 	/*
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 4102b866e7c0..32b7099e3511 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1384,8 +1384,10 @@ noinstr void do_machine_check(struct pt_regs *regs)
 	 * When there's any problem use only local no_way_out state.
 	 */
 	if (!lmce) {
-		if (mce_end(order) < 0)
-			no_way_out = worst >= MCE_PANIC_SEVERITY;
+		if (mce_end(order) < 0) {
+			if (!no_way_out)
+				no_way_out = worst >= MCE_PANIC_SEVERITY;
+		}
 	} else {
 		/*
 		 * If there was a fatal machine check we should have
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 6a99535d7f37..7e8e07bddd5f 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -100,53 +100,6 @@ static int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev
 	return find_matching_signature(mc, csig, cpf);
 }
 
-/*
- * Given CPU signature and a microcode patch, this function finds if the
- * microcode patch has matching family and model with the CPU.
- *
- * %true - if there's a match
- * %false - otherwise
- */
-static bool microcode_matches(struct microcode_header_intel *mc_header,
-			      unsigned long sig)
-{
-	unsigned long total_size = get_totalsize(mc_header);
-	unsigned long data_size = get_datasize(mc_header);
-	struct extended_sigtable *ext_header;
-	unsigned int fam_ucode, model_ucode;
-	struct extended_signature *ext_sig;
-	unsigned int fam, model;
-	int ext_sigcount, i;
-
-	fam   = x86_family(sig);
-	model = x86_model(sig);
-
-	fam_ucode   = x86_family(mc_header->sig);
-	model_ucode = x86_model(mc_header->sig);
-
-	if (fam == fam_ucode && model == model_ucode)
-		return true;
-
-	/* Look for ext. headers: */
-	if (total_size <= data_size + MC_HEADER_SIZE)
-		return false;
-
-	ext_header   = (void *) mc_header + data_size + MC_HEADER_SIZE;
-	ext_sig      = (void *)ext_header + EXT_HEADER_SIZE;
-	ext_sigcount = ext_header->count;
-
-	for (i = 0; i < ext_sigcount; i++) {
-		fam_ucode   = x86_family(ext_sig->sig);
-		model_ucode = x86_model(ext_sig->sig);
-
-		if (fam == fam_ucode && model == model_ucode)
-			return true;
-
-		ext_sig++;
-	}
-	return false;
-}
-
 static struct ucode_patch *memdup_patch(void *data, unsigned int size)
 {
 	struct ucode_patch *p;
@@ -164,7 +117,7 @@ static struct ucode_patch *memdup_patch(void *data, unsigned int size)
 	return p;
 }
 
-static void save_microcode_patch(void *data, unsigned int size)
+static void save_microcode_patch(struct ucode_cpu_info *uci, void *data, unsigned int size)
 {
 	struct microcode_header_intel *mc_hdr, *mc_saved_hdr;
 	struct ucode_patch *iter, *tmp, *p = NULL;
@@ -210,6 +163,9 @@ static void save_microcode_patch(void *data, unsigned int size)
 	if (!p)
 		return;
 
+	if (!find_matching_signature(p->data, uci->cpu_sig.sig, uci->cpu_sig.pf))
+		return;
+
 	/*
 	 * Save for early loading. On 32-bit, that needs to be a physical
 	 * address as the APs are running from physical addresses, before
@@ -344,13 +300,14 @@ scan_microcode(void *data, size_t size, struct ucode_cpu_info *uci, bool save)
 
 		size -= mc_size;
 
-		if (!microcode_matches(mc_header, uci->cpu_sig.sig)) {
+		if (!find_matching_signature(data, uci->cpu_sig.sig,
+					     uci->cpu_sig.pf)) {
 			data += mc_size;
 			continue;
 		}
 
 		if (save) {
-			save_microcode_patch(data, mc_size);
+			save_microcode_patch(uci, data, mc_size);
 			goto next;
 		}
 
@@ -483,14 +440,14 @@ static void show_saved_mc(void)
  * Save this microcode patch. It will be loaded early when a CPU is
  * hot-added or resumes.
  */
-static void save_mc_for_early(u8 *mc, unsigned int size)
+static void save_mc_for_early(struct ucode_cpu_info *uci, u8 *mc, unsigned int size)
 {
 	/* Synchronization during CPU hotplug. */
 	static DEFINE_MUTEX(x86_cpu_microcode_mutex);
 
 	mutex_lock(&x86_cpu_microcode_mutex);
 
-	save_microcode_patch(mc, size);
+	save_microcode_patch(uci, mc, size);
 	show_saved_mc();
 
 	mutex_unlock(&x86_cpu_microcode_mutex);
@@ -935,7 +892,7 @@ static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter)
 	 * permanent memory. So it will be loaded early when a CPU is hot added
 	 * or resumes.
 	 */
-	save_mc_for_early(new_mc, new_mc_size);
+	save_mc_for_early(uci, new_mc, new_mc_size);
 
 	pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n",
 		 cpu, new_rev, uci->cpu_sig.rev);
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index e5f4ee8f4c3b..e8b5f1cf1ae8 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -570,6 +570,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 	if (d) {
 		cpumask_set_cpu(cpu, &d->cpu_mask);
+		if (r->cache.arch_has_per_cpu_cfg)
+			rdt_domain_reconfigure_cdp(r);
 		return;
 	}
 
@@ -923,6 +925,7 @@ static __init void rdt_init_res_defs_intel(void)
 		    r->rid == RDT_RESOURCE_L2CODE) {
 			r->cache.arch_has_sparse_bitmaps = false;
 			r->cache.arch_has_empty_bitmaps = false;
+			r->cache.arch_has_per_cpu_cfg = false;
 		} else if (r->rid == RDT_RESOURCE_MBA) {
 			r->msr_base = MSR_IA32_MBA_THRTL_BASE;
 			r->msr_update = mba_wrmsr_intel;
@@ -943,6 +946,7 @@ static __init void rdt_init_res_defs_amd(void)
 		    r->rid == RDT_RESOURCE_L2CODE) {
 			r->cache.arch_has_sparse_bitmaps = true;
 			r->cache.arch_has_empty_bitmaps = true;
+			r->cache.arch_has_per_cpu_cfg = true;
 		} else if (r->rid == RDT_RESOURCE_MBA) {
 			r->msr_base = MSR_IA32_MBA_BW_BASE;
 			r->msr_update = mba_wrmsr_amd;
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 80fa997fae60..f65d3c0dbc41 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -360,6 +360,8 @@ struct msr_param {
  *			executing entities
  * @arch_has_sparse_bitmaps:	True if a bitmap like f00f is valid.
  * @arch_has_empty_bitmaps:	True if the '0' bitmap is valid.
+ * @arch_has_per_cpu_cfg:	True if QOS_CFG register for this cache
+ *				level has CPU scope.
  */
 struct rdt_cache {
 	unsigned int	cbm_len;
@@ -369,6 +371,7 @@ struct rdt_cache {
 	unsigned int	shareable_bits;
 	bool		arch_has_sparse_bitmaps;
 	bool		arch_has_empty_bitmaps;
+	bool		arch_has_per_cpu_cfg;
 };
 
 /**
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 54dffe574e67..a98519a3a2e6 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -279,7 +279,6 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
 		return;
 
 	chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width);
-	m->chunks += chunks;
 	cur_bw = (chunks * r->mon_scale) >> 20;
 
 	if (m->delta_comp)
@@ -450,15 +449,14 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid)
 	}
 	if (is_mbm_local_enabled()) {
 		rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
+		__mon_event_count(rmid, &rr);
 
 		/*
 		 * Call the MBA software controller only for the
 		 * control groups and when user has enabled
 		 * the software controller explicitly.
 		 */
-		if (!is_mba_sc(NULL))
-			__mon_event_count(rmid, &rr);
-		else
+		if (is_mba_sc(NULL))
 			mbm_bw_count(rmid, &rr);
 	}
 }
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index af323e2e3100..f3418428682b 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -507,6 +507,24 @@ unlock:
 	return ret ?: nbytes;
 }
 
+/**
+ * rdtgroup_remove - the helper to remove resource group safely
+ * @rdtgrp: resource group to remove
+ *
+ * On resource group creation via a mkdir, an extra kernfs_node reference is
+ * taken to ensure that the rdtgroup structure remains accessible for the
+ * rdtgroup_kn_unlock() calls where it is removed.
+ *
+ * Drop the extra reference here, then free the rdtgroup structure.
+ *
+ * Return: void
+ */
+static void rdtgroup_remove(struct rdtgroup *rdtgrp)
+{
+	kernfs_put(rdtgrp->kn);
+	kfree(rdtgrp);
+}
+
 struct task_move_callback {
 	struct callback_head	work;
 	struct rdtgroup		*rdtgrp;
@@ -529,7 +547,7 @@ static void move_myself(struct callback_head *head)
 	    (rdtgrp->flags & RDT_DELETED)) {
 		current->closid = 0;
 		current->rmid = 0;
-		kfree(rdtgrp);
+		rdtgroup_remove(rdtgrp);
 	}
 
 	if (unlikely(current->flags & PF_EXITING))
@@ -1769,7 +1787,6 @@ static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name,
 	if (IS_ERR(kn_subdir))
 		return PTR_ERR(kn_subdir);
 
-	kernfs_get(kn_subdir);
 	ret = rdtgroup_kn_set_ugid(kn_subdir);
 	if (ret)
 		return ret;
@@ -1792,7 +1809,6 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
 	kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL);
 	if (IS_ERR(kn_info))
 		return PTR_ERR(kn_info);
-	kernfs_get(kn_info);
 
 	ret = rdtgroup_add_files(kn_info, RF_TOP_INFO);
 	if (ret)
@@ -1813,12 +1829,6 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
 			goto out_destroy;
 	}
 
-	/*
-	 * This extra ref will be put in kernfs_remove() and guarantees
-	 * that @rdtgrp->kn is always accessible.
-	 */
-	kernfs_get(kn_info);
-
 	ret = rdtgroup_kn_set_ugid(kn_info);
 	if (ret)
 		goto out_destroy;
@@ -1847,12 +1857,6 @@ mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp,
 	if (dest_kn)
 		*dest_kn = kn;
 
-	/*
-	 * This extra ref will be put in kernfs_remove() and guarantees
-	 * that @rdtgrp->kn is always accessible.
-	 */
-	kernfs_get(kn);
-
 	ret = rdtgroup_kn_set_ugid(kn);
 	if (ret)
 		goto out_destroy;
@@ -1905,8 +1909,13 @@ static int set_cache_qos_cfg(int level, bool enable)
 
 	r_l = &rdt_resources_all[level];
 	list_for_each_entry(d, &r_l->domains, list) {
-		/* Pick one CPU from each domain instance to update MSR */
-		cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
+		if (r_l->cache.arch_has_per_cpu_cfg)
+			/* Pick all the CPUs in the domain instance */
+			for_each_cpu(cpu, &d->cpu_mask)
+				cpumask_set_cpu(cpu, cpu_mask);
+		else
+			/* Pick one CPU from each domain instance to update MSR */
+			cpumask_set_cpu(cpumask_any(&d->cpu_mask), cpu_mask);
 	}
 	cpu = get_cpu();
 	/* Update QOS_CFG MSR on this cpu if it's in cpu_mask. */
@@ -2079,8 +2088,7 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn)
 		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
 			rdtgroup_pseudo_lock_remove(rdtgrp);
 		kernfs_unbreak_active_protection(kn);
-		kernfs_put(rdtgrp->kn);
-		kfree(rdtgrp);
+		rdtgroup_remove(rdtgrp);
 	} else {
 		kernfs_unbreak_active_protection(kn);
 	}
@@ -2139,13 +2147,11 @@ static int rdt_get_tree(struct fs_context *fc)
 					  &kn_mongrp);
 		if (ret < 0)
 			goto out_info;
-		kernfs_get(kn_mongrp);
 
 		ret = mkdir_mondata_all(rdtgroup_default.kn,
 					&rdtgroup_default, &kn_mondata);
 		if (ret < 0)
 			goto out_mongrp;
-		kernfs_get(kn_mondata);
 		rdtgroup_default.mon.mon_data_kn = kn_mondata;
 	}
 
@@ -2357,7 +2363,7 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp)
 		if (atomic_read(&sentry->waitcount) != 0)
 			sentry->flags = RDT_DELETED;
 		else
-			kfree(sentry);
+			rdtgroup_remove(sentry);
 	}
 }
 
@@ -2399,7 +2405,7 @@ static void rmdir_all_sub(void)
 		if (atomic_read(&rdtgrp->waitcount) != 0)
 			rdtgrp->flags = RDT_DELETED;
 		else
-			kfree(rdtgrp);
+			rdtgroup_remove(rdtgrp);
 	}
 	/* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */
 	update_closid_rmid(cpu_online_mask, &rdtgroup_default);
@@ -2499,11 +2505,6 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
 	if (IS_ERR(kn))
 		return PTR_ERR(kn);
 
-	/*
-	 * This extra ref will be put in kernfs_remove() and guarantees
-	 * that kn is always accessible.
-	 */
-	kernfs_get(kn);
 	ret = rdtgroup_kn_set_ugid(kn);
 	if (ret)
 		goto out_destroy;
@@ -2838,8 +2839,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 	/*
 	 * kernfs_remove() will drop the reference count on "kn" which
 	 * will free it. But we still need it to stick around for the
-	 * rdtgroup_kn_unlock(kn} call below. Take one extra reference
-	 * here, which will be dropped inside rdtgroup_kn_unlock().
+	 * rdtgroup_kn_unlock(kn) call. Take one extra reference here,
+	 * which will be dropped by kernfs_put() in rdtgroup_remove().
 	 */
 	kernfs_get(kn);
 
@@ -2880,6 +2881,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 out_idfree:
 	free_rmid(rdtgrp->mon.rmid);
 out_destroy:
+	kernfs_put(rdtgrp->kn);
 	kernfs_remove(rdtgrp->kn);
 out_free_rgrp:
 	kfree(rdtgrp);
@@ -2892,7 +2894,7 @@ static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp)
 {
 	kernfs_remove(rgrp->kn);
 	free_rmid(rgrp->mon.rmid);
-	kfree(rgrp);
+	rdtgroup_remove(rgrp);
 }
 
 /*
@@ -3049,11 +3051,6 @@ static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 	WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list));
 	list_del(&rdtgrp->mon.crdtgrp_list);
 
-	/*
-	 * one extra hold on this, will drop when we kfree(rdtgrp)
-	 * in rdtgroup_kn_unlock()
-	 */
-	kernfs_get(kn);
 	kernfs_remove(rdtgrp->kn);
 
 	return 0;
@@ -3065,11 +3062,6 @@ static int rdtgroup_ctrl_remove(struct kernfs_node *kn,
 	rdtgrp->flags = RDT_DELETED;
 	list_del(&rdtgrp->rdtgroup_list);
 
-	/*
-	 * one extra hold on this, will drop when we kfree(rdtgrp)
-	 * in rdtgroup_kn_unlock()
-	 */
-	kernfs_get(kn);
 	kernfs_remove(rdtgrp->kn);
 	return 0;
 }
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 25c06b67e7e0..97aa900386cb 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -78,6 +78,9 @@ static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src,
 	if (!user_mode(regs))
 		return copy_from_kernel_nofault(buf, (u8 *)src, nbytes);
 
+	/* The user space code from other tasks cannot be accessed. */
+	if (regs != task_pt_regs(current))
+		return -EPERM;
 	/*
 	 * Make sure userspace isn't trying to trick us into dumping kernel
 	 * memory by pointing the userspace instruction pointer at it.
@@ -85,6 +88,12 @@ static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src,
 	if (__chk_range_not_ok(src, nbytes, TASK_SIZE_MAX))
 		return -EINVAL;
 
+	/*
+	 * Even if named copy_from_user_nmi() this can be invoked from
+	 * other contexts and will not try to resolve a pagefault, which is
+	 * the correct thing to do here as this code can be called from any
+	 * context.
+	 */
 	return copy_from_user_nmi(buf, (void __user *)src, nbytes);
 }
 
@@ -115,13 +124,19 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl)
 	u8 opcodes[OPCODE_BUFSIZE];
 	unsigned long prologue = regs->ip - PROLOGUE_SIZE;
 
-	if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) {
-		printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n",
-		       loglvl, prologue);
-	} else {
+	switch (copy_code(regs, opcodes, prologue, sizeof(opcodes))) {
+	case 0:
 		printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %"
 		       __stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes,
 		       opcodes[PROLOGUE_SIZE], opcodes + PROLOGUE_SIZE + 1);
+		break;
+	case -EPERM:
+		/* No access to the user space stack of other tasks. Ignore. */
+		break;
+	default:
+		printk("%sCode: Unable to access opcode bytes at RIP 0x%lx.\n",
+		       loglvl, prologue);
+		break;
 	}
 }
 
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 041f0b50bc27..08eb23074f92 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -272,6 +272,19 @@ static int insn_is_indirect_jump(struct insn *insn)
 	return ret;
 }
 
+static bool is_padding_int3(unsigned long addr, unsigned long eaddr)
+{
+	unsigned char ops;
+
+	for (; addr < eaddr; addr++) {
+		if (get_kernel_nofault(ops, (void *)addr) < 0 ||
+		    ops != INT3_INSN_OPCODE)
+			return false;
+	}
+
+	return true;
+}
+
 /* Decode whole function to ensure any instructions don't jump into target */
 static int can_optimize(unsigned long paddr)
 {
@@ -310,9 +323,14 @@ static int can_optimize(unsigned long paddr)
 			return 0;
 		kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
 		insn_get_length(&insn);
-		/* Another subsystem puts a breakpoint */
+		/*
+		 * In the case of detecting unknown breakpoint, this could be
+		 * a padding INT3 between functions. Let's check that all the
+		 * rest of the bytes are also INT3.
+		 */
 		if (insn.opcode.bytes[0] == INT3_INSN_OPCODE)
-			return 0;
+			return is_padding_int3(addr, paddr - offset + size) ? 1 : 0;
+
 		/* Recover address */
 		insn.kaddr = (void *)addr;
 		insn.next_byte = (void *)(addr + insn.length);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ba4593a913fa..145a7ac0c19a 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -685,7 +685,7 @@ void arch_cpu_idle(void)
  */
 void __cpuidle default_idle(void)
 {
-	safe_halt();
+	raw_safe_halt();
 }
 #if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE)
 EXPORT_SYMBOL(default_idle);
@@ -736,6 +736,8 @@ void stop_this_cpu(void *dummy)
 /*
  * AMD Erratum 400 aware idle routine. We handle it the same way as C3 power
  * states (local apic timer and TSC stop).
+ *
+ * XXX this function is completely buggered vs RCU and tracing.
  */
 static void amd_e400_idle(void)
 {
@@ -757,9 +759,9 @@ static void amd_e400_idle(void)
 	 * The switch back from broadcast mode needs to be called with
 	 * interrupts disabled.
 	 */
-	local_irq_disable();
+	raw_local_irq_disable();
 	tick_broadcast_exit();
-	local_irq_enable();
+	raw_local_irq_enable();
 }
 
 /*
@@ -801,9 +803,9 @@ static __cpuidle void mwait_idle(void)
 		if (!need_resched())
 			__sti_mwait(0, 0);
 		else
-			local_irq_enable();
+			raw_local_irq_enable();
 	} else {
-		local_irq_enable();
+		raw_local_irq_enable();
 	}
 	__current_clr_polling();
 }
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 992fb1415c0f..ae64f98ec2ab 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -514,16 +514,10 @@ int tboot_force_iommu(void)
 	if (!tboot_enabled())
 		return 0;
 
-	if (intel_iommu_tboot_noforce)
-		return 1;
-
-	if (no_iommu || swiotlb || dmar_disabled)
+	if (no_iommu || dmar_disabled)
 		pr_warn("Forcing Intel-IOMMU to enabled\n");
 
 	dmar_disabled = 0;
-#ifdef CONFIG_SWIOTLB
-	swiotlb = 0;
-#endif
 	no_iommu = 0;
 
 	return 1;
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 3fdaa042823d..138bdb1fd136 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -255,12 +255,13 @@ static volatile u32 good_2byte_insns[256 / 32] = {
 
 static bool is_prefix_bad(struct insn *insn)
 {
+	insn_byte_t p;
 	int i;
 
-	for (i = 0; i < insn->prefixes.nbytes; i++) {
+	for_each_insn_prefix(insn, i, p) {
 		insn_attr_t attr;
 
-		attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]);
+		attr = inat_get_opcode_attribute(p);
 		switch (attr) {
 		case INAT_MAKE_PREFIX(INAT_PFX_ES):
 		case INAT_MAKE_PREFIX(INAT_PFX_CS):
@@ -715,6 +716,7 @@ static const struct uprobe_xol_ops push_xol_ops = {
 static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 {
 	u8 opc1 = OPCODE1(insn);
+	insn_byte_t p;
 	int i;
 
 	switch (opc1) {
@@ -746,8 +748,8 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 	 * Intel and AMD behavior differ in 64-bit mode: Intel ignores 66 prefix.
 	 * No one uses these insns, reject any branch insns with such prefix.
 	 */
-	for (i = 0; i < insn->prefixes.nbytes; i++) {
-		if (insn->prefixes.bytes[i] == 0x66)
+	for_each_insn_prefix(insn, i, p) {
+		if (p == 0x66)
 			return -ENOTSUPP;
 	}
 
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 99d118ffc67d..814698e5b152 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -40,29 +40,10 @@ static int pending_userspace_extint(struct kvm_vcpu *v)
  * check if there is pending interrupt from
  * non-APIC source without intack.
  */
-static int kvm_cpu_has_extint(struct kvm_vcpu *v)
-{
-	u8 accept = kvm_apic_accept_pic_intr(v);
-
-	if (accept) {
-		if (irqchip_split(v->kvm))
-			return pending_userspace_extint(v);
-		else
-			return v->kvm->arch.vpic->output;
-	} else
-		return 0;
-}
-
-/*
- * check if there is injectable interrupt:
- * when virtual interrupt delivery enabled,
- * interrupt from apic will handled by hardware,
- * we don't need to check it here.
- */
-int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
+int kvm_cpu_has_extint(struct kvm_vcpu *v)
 {
 	/*
-	 * FIXME: interrupt.injected represents an interrupt that it's
+	 * FIXME: interrupt.injected represents an interrupt whose
 	 * side-effects have already been applied (e.g. bit from IRR
 	 * already moved to ISR). Therefore, it is incorrect to rely
 	 * on interrupt.injected to know if there is a pending
@@ -75,6 +56,23 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
 	if (!lapic_in_kernel(v))
 		return v->arch.interrupt.injected;
 
+	if (!kvm_apic_accept_pic_intr(v))
+		return 0;
+
+	if (irqchip_split(v->kvm))
+		return pending_userspace_extint(v);
+	else
+		return v->kvm->arch.vpic->output;
+}
+
+/*
+ * check if there is injectable interrupt:
+ * when virtual interrupt delivery enabled,
+ * interrupt from apic will handled by hardware,
+ * we don't need to check it here.
+ */
+int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
+{
 	if (kvm_cpu_has_extint(v))
 		return 1;
 
@@ -91,20 +89,6 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_injectable_intr);
  */
 int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
 {
-	/*
-	 * FIXME: interrupt.injected represents an interrupt that it's
-	 * side-effects have already been applied (e.g. bit from IRR
-	 * already moved to ISR). Therefore, it is incorrect to rely
-	 * on interrupt.injected to know if there is a pending
-	 * interrupt in the user-mode LAPIC.
-	 * This leads to nVMX/nSVM not be able to distinguish
-	 * if it should exit from L2 to L1 on EXTERNAL_INTERRUPT on
-	 * pending interrupt or should re-inject an injected
-	 * interrupt.
-	 */
-	if (!lapic_in_kernel(v))
-		return v->arch.interrupt.injected;
-
 	if (kvm_cpu_has_extint(v))
 		return 1;
 
@@ -118,16 +102,21 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt);
  */
 static int kvm_cpu_get_extint(struct kvm_vcpu *v)
 {
-	if (kvm_cpu_has_extint(v)) {
-		if (irqchip_split(v->kvm)) {
-			int vector = v->arch.pending_external_vector;
-
-			v->arch.pending_external_vector = -1;
-			return vector;
-		} else
-			return kvm_pic_read_irq(v->kvm); /* PIC */
-	} else
+	if (!kvm_cpu_has_extint(v)) {
+		WARN_ON(!lapic_in_kernel(v));
 		return -1;
+	}
+
+	if (!lapic_in_kernel(v))
+		return v->arch.interrupt.nr;
+
+	if (irqchip_split(v->kvm)) {
+		int vector = v->arch.pending_external_vector;
+
+		v->arch.pending_external_vector = -1;
+		return vector;
+	} else
+		return kvm_pic_read_irq(v->kvm); /* PIC */
 }
 
 /*
@@ -135,13 +124,7 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v)
  */
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
 {
-	int vector;
-
-	if (!lapic_in_kernel(v))
-		return v->arch.interrupt.nr;
-
-	vector = kvm_cpu_get_extint(v);
-
+	int vector = kvm_cpu_get_extint(v);
 	if (vector != -1)
 		return vector;			/* PIC */
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 6a87623aa578..3136e05831cf 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2465,7 +2465,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u32 ppr;
 
-	if (!kvm_apic_hw_enabled(apic))
+	if (!kvm_apic_present(vcpu))
 		return -1;
 
 	__apic_update_ppr(apic, &ppr);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 5dfe0ede0e81..6d16481aa29d 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3493,26 +3493,25 @@ static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct)
  * Return the level of the lowest level SPTE added to sptes.
  * That SPTE may be non-present.
  */
-static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes)
+static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level)
 {
 	struct kvm_shadow_walk_iterator iterator;
-	int leaf = vcpu->arch.mmu->root_level;
+	int leaf = -1;
 	u64 spte;
 
-
 	walk_shadow_page_lockless_begin(vcpu);
 
-	for (shadow_walk_init(&iterator, vcpu, addr);
+	for (shadow_walk_init(&iterator, vcpu, addr),
+	     *root_level = iterator.level;
 	     shadow_walk_okay(&iterator);
 	     __shadow_walk_next(&iterator, spte)) {
 		leaf = iterator.level;
 		spte = mmu_spte_get_lockless(iterator.sptep);
 
-		sptes[leaf - 1] = spte;
+		sptes[leaf] = spte;
 
 		if (!is_shadow_present_pte(spte))
 			break;
-
 	}
 
 	walk_shadow_page_lockless_end(vcpu);
@@ -3520,14 +3519,12 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes)
 	return leaf;
 }
 
-/* return true if reserved bit is detected on spte. */
+/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */
 static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 {
-	u64 sptes[PT64_ROOT_MAX_LEVEL];
+	u64 sptes[PT64_ROOT_MAX_LEVEL + 1];
 	struct rsvd_bits_validate *rsvd_check;
-	int root = vcpu->arch.mmu->root_level;
-	int leaf;
-	int level;
+	int root, leaf, level;
 	bool reserved = false;
 
 	if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) {
@@ -3536,35 +3533,45 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 	}
 
 	if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa))
-		leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes);
+		leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root);
 	else
-		leaf = get_walk(vcpu, addr, sptes);
+		leaf = get_walk(vcpu, addr, sptes, &root);
+
+	if (unlikely(leaf < 0)) {
+		*sptep = 0ull;
+		return reserved;
+	}
+
+	*sptep = sptes[leaf];
+
+	/*
+	 * Skip reserved bits checks on the terminal leaf if it's not a valid
+	 * SPTE.  Note, this also (intentionally) skips MMIO SPTEs, which, by
+	 * design, always have reserved bits set.  The purpose of the checks is
+	 * to detect reserved bits on non-MMIO SPTEs. i.e. buggy SPTEs.
+	 */
+	if (!is_shadow_present_pte(sptes[leaf]))
+		leaf++;
 
 	rsvd_check = &vcpu->arch.mmu->shadow_zero_check;
 
-	for (level = root; level >= leaf; level--) {
-		if (!is_shadow_present_pte(sptes[level - 1]))
-			break;
+	for (level = root; level >= leaf; level--)
 		/*
 		 * Use a bitwise-OR instead of a logical-OR to aggregate the
 		 * reserved bit and EPT's invalid memtype/XWR checks to avoid
 		 * adding a Jcc in the loop.
 		 */
-		reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level - 1]) |
-			    __is_rsvd_bits_set(rsvd_check, sptes[level - 1],
-					       level);
-	}
+		reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level]) |
+			    __is_rsvd_bits_set(rsvd_check, sptes[level], level);
 
 	if (reserved) {
 		pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n",
 		       __func__, addr);
 		for (level = root; level >= leaf; level--)
 			pr_err("------ spte 0x%llx level %d.\n",
-			       sptes[level - 1], level);
+			       sptes[level], level);
 	}
 
-	*sptep = sptes[leaf - 1];
-
 	return reserved;
 }
 
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index fcac2cac78fe..c51ad544f25b 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -40,8 +40,8 @@ static u64 generation_mmio_spte_mask(u64 gen)
 	WARN_ON(gen & ~MMIO_SPTE_GEN_MASK);
 	BUILD_BUG_ON((MMIO_SPTE_GEN_HIGH_MASK | MMIO_SPTE_GEN_LOW_MASK) & SPTE_SPECIAL_MASK);
 
-	mask = (gen << MMIO_SPTE_GEN_LOW_START) & MMIO_SPTE_GEN_LOW_MASK;
-	mask |= (gen << MMIO_SPTE_GEN_HIGH_START) & MMIO_SPTE_GEN_HIGH_MASK;
+	mask = (gen << MMIO_SPTE_GEN_LOW_SHIFT) & MMIO_SPTE_GEN_LOW_MASK;
+	mask |= (gen << MMIO_SPTE_GEN_HIGH_SHIFT) & MMIO_SPTE_GEN_HIGH_MASK;
 	return mask;
 }
 
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 5c75a451c000..2b3a30bd38b0 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -56,11 +56,11 @@
 #define SPTE_MMU_WRITEABLE	(1ULL << (PT_FIRST_AVAIL_BITS_SHIFT + 1))
 
 /*
- * Due to limited space in PTEs, the MMIO generation is a 19 bit subset of
+ * Due to limited space in PTEs, the MMIO generation is a 18 bit subset of
  * the memslots generation and is derived as follows:
  *
  * Bits 0-8 of the MMIO generation are propagated to spte bits 3-11
- * Bits 9-18 of the MMIO generation are propagated to spte bits 52-61
+ * Bits 9-17 of the MMIO generation are propagated to spte bits 54-62
  *
  * The KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS flag is intentionally not included in
  * the MMIO generation number, as doing so would require stealing a bit from
@@ -69,18 +69,29 @@
  * requires a full MMU zap).  The flag is instead explicitly queried when
  * checking for MMIO spte cache hits.
  */
-#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(17, 0)
 
 #define MMIO_SPTE_GEN_LOW_START		3
 #define MMIO_SPTE_GEN_LOW_END		11
-#define MMIO_SPTE_GEN_LOW_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \
-						    MMIO_SPTE_GEN_LOW_START)
 
 #define MMIO_SPTE_GEN_HIGH_START	PT64_SECOND_AVAIL_BITS_SHIFT
 #define MMIO_SPTE_GEN_HIGH_END		62
+
+#define MMIO_SPTE_GEN_LOW_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_END, \
+						    MMIO_SPTE_GEN_LOW_START)
 #define MMIO_SPTE_GEN_HIGH_MASK		GENMASK_ULL(MMIO_SPTE_GEN_HIGH_END, \
 						    MMIO_SPTE_GEN_HIGH_START)
 
+#define MMIO_SPTE_GEN_LOW_BITS		(MMIO_SPTE_GEN_LOW_END - MMIO_SPTE_GEN_LOW_START + 1)
+#define MMIO_SPTE_GEN_HIGH_BITS		(MMIO_SPTE_GEN_HIGH_END - MMIO_SPTE_GEN_HIGH_START + 1)
+
+/* remember to adjust the comment above as well if you change these */
+static_assert(MMIO_SPTE_GEN_LOW_BITS == 9 && MMIO_SPTE_GEN_HIGH_BITS == 9);
+
+#define MMIO_SPTE_GEN_LOW_SHIFT		(MMIO_SPTE_GEN_LOW_START - 0)
+#define MMIO_SPTE_GEN_HIGH_SHIFT	(MMIO_SPTE_GEN_HIGH_START - MMIO_SPTE_GEN_LOW_BITS)
+
+#define MMIO_SPTE_GEN_MASK		GENMASK_ULL(MMIO_SPTE_GEN_LOW_BITS + MMIO_SPTE_GEN_HIGH_BITS - 1, 0)
+
 extern u64 __read_mostly shadow_nx_mask;
 extern u64 __read_mostly shadow_x_mask; /* mutual exclusive with nx_mask */
 extern u64 __read_mostly shadow_user_mask;
@@ -228,8 +239,8 @@ static inline u64 get_mmio_spte_generation(u64 spte)
 {
 	u64 gen;
 
-	gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_START;
-	gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_START;
+	gen = (spte & MMIO_SPTE_GEN_LOW_MASK) >> MMIO_SPTE_GEN_LOW_SHIFT;
+	gen |= (spte & MMIO_SPTE_GEN_HIGH_MASK) >> MMIO_SPTE_GEN_HIGH_SHIFT;
 	return gen;
 }
 
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 75db27fda8f3..6574af2d0994 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -68,7 +68,7 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 
 void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root)
 {
-	gfn_t max_gfn = 1ULL << (boot_cpu_data.x86_phys_bits - PAGE_SHIFT);
+	gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
 
 	lockdep_assert_held(&kvm->mmu_lock);
 
@@ -464,7 +464,7 @@ bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end)
 
 void kvm_tdp_mmu_zap_all(struct kvm *kvm)
 {
-	gfn_t max_gfn = 1ULL << (boot_cpu_data.x86_phys_bits - PAGE_SHIFT);
+	gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT);
 	bool flush;
 
 	flush = kvm_tdp_mmu_zap_gfn_range(kvm, 0, max_gfn);
@@ -1160,16 +1160,19 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
  * Return the level of the lowest level SPTE added to sptes.
  * That SPTE may be non-present.
  */
-int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes)
+int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+			 int *root_level)
 {
 	struct tdp_iter iter;
 	struct kvm_mmu *mmu = vcpu->arch.mmu;
-	int leaf = vcpu->arch.mmu->shadow_root_level;
 	gfn_t gfn = addr >> PAGE_SHIFT;
+	int leaf = -1;
+
+	*root_level = vcpu->arch.mmu->shadow_root_level;
 
 	tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) {
 		leaf = iter.level;
-		sptes[leaf - 1] = iter.old_spte;
+		sptes[leaf] = iter.old_spte;
 	}
 
 	return leaf;
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 556e065503f6..cbbdbadd1526 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -44,5 +44,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm,
 bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
 				   struct kvm_memory_slot *slot, gfn_t gfn);
 
-int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes);
+int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+			 int *root_level);
+
 #endif /* __KVM_X86_MMU_TDP_MMU_H */
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index e57847ff8bd2..9858d5ae9ddd 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -754,8 +754,8 @@ static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr,
 	 * Its safe to read more than we are asked, caller should ensure that
 	 * destination has enough space.
 	 */
-	src_paddr = round_down(src_paddr, 16);
 	offset = src_paddr & 15;
+	src_paddr = round_down(src_paddr, 16);
 	sz = round_up(sz + offset, 16);
 
 	return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 941e5251e13f..cce0143a6f80 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -546,12 +546,12 @@ static int svm_hardware_enable(void)
 
 static void svm_cpu_uninit(int cpu)
 {
-	struct svm_cpu_data *sd = per_cpu(svm_data, raw_smp_processor_id());
+	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
 
 	if (!sd)
 		return;
 
-	per_cpu(svm_data, raw_smp_processor_id()) = NULL;
+	per_cpu(svm_data, cpu) = NULL;
 	kfree(sd->sev_vmcbs);
 	__free_page(sd->save_area);
 	kfree(sd);
@@ -1347,8 +1347,10 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 		svm->avic_is_running = true;
 
 	svm->msrpm = svm_vcpu_alloc_msrpm();
-	if (!svm->msrpm)
+	if (!svm->msrpm) {
+		err = -ENOMEM;
 		goto error_free_vmsa_page;
+	}
 
 	svm_vcpu_init_msrpm(vcpu, svm->msrpm);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 648c677b12e9..e28ab76b80dc 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4082,21 +4082,23 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
 
 static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * We can accept userspace's request for interrupt injection
+	 * as long as we have a place to store the interrupt number.
+	 * The actual injection will happen when the CPU is able to
+	 * deliver the interrupt.
+	 */
+	if (kvm_cpu_has_extint(vcpu))
+		return false;
+
+	/* Acknowledging ExtINT does not happen if LINT0 is masked.  */
 	return (!lapic_in_kernel(vcpu) ||
 		kvm_apic_accept_pic_intr(vcpu));
 }
 
-/*
- * if userspace requested an interrupt window, check that the
- * interrupt window is open.
- *
- * No need to exit to userspace if we already have an interrupt queued.
- */
 static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
 {
 	return kvm_arch_interrupt_allowed(vcpu) &&
-		!kvm_cpu_has_interrupt(vcpu) &&
-		!kvm_event_needs_reinjection(vcpu) &&
 		kvm_cpu_accept_dm_intr(vcpu);
 }
 
diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 58f7fb95c7f4..4229950a5d78 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -63,13 +63,12 @@ static bool is_string_insn(struct insn *insn)
  */
 bool insn_has_rep_prefix(struct insn *insn)
 {
+	insn_byte_t p;
 	int i;
 
 	insn_get_prefixes(insn);
 
-	for (i = 0; i < insn->prefixes.nbytes; i++) {
-		insn_byte_t p = insn->prefixes.bytes[i];
-
+	for_each_insn_prefix(insn, i, p) {
 		if (p == 0xf2 || p == 0xf3)
 			return true;
 	}
@@ -95,14 +94,15 @@ static int get_seg_reg_override_idx(struct insn *insn)
 {
 	int idx = INAT_SEG_REG_DEFAULT;
 	int num_overrides = 0, i;
+	insn_byte_t p;
 
 	insn_get_prefixes(insn);
 
 	/* Look for any segment override prefixes. */
-	for (i = 0; i < insn->prefixes.nbytes; i++) {
+	for_each_insn_prefix(insn, i, p) {
 		insn_attr_t attr;
 
-		attr = inat_get_opcode_attribute(insn->prefixes.bytes[i]);
+		attr = inat_get_opcode_attribute(p);
 		switch (attr) {
 		case INAT_MAKE_PREFIX(INAT_PFX_CS):
 			idx = INAT_SEG_REG_CS;
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index 733b983f3a89..6c5eb6f3f14f 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -45,8 +45,8 @@
 #define PMD_FLAGS_LARGE		(__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL)
 
 #define PMD_FLAGS_DEC		PMD_FLAGS_LARGE
-#define PMD_FLAGS_DEC_WP	((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \
-				 (_PAGE_PAT | _PAGE_PWT))
+#define PMD_FLAGS_DEC_WP	((PMD_FLAGS_DEC & ~_PAGE_LARGE_CACHE_MASK) | \
+				 (_PAGE_PAT_LARGE | _PAGE_PWT))
 
 #define PMD_FLAGS_ENC		(PMD_FLAGS_LARGE | _PAGE_ENC)
 
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 44148691d78b..5eb4dc2b97da 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -938,6 +938,7 @@ int phys_to_target_node(phys_addr_t start)
 
 	return meminfo_to_nid(&numa_reserved_meminfo, start);
 }
+EXPORT_SYMBOL_GPL(phys_to_target_node);
 
 int memory_add_physaddr_to_nid(u64 start)
 {
@@ -947,4 +948,5 @@ int memory_add_physaddr_to_nid(u64 start)
 		nid = numa_meminfo.blk[0].nid;
 	return nid;
 }
+EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #endif
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 11666ba19b62..569ac1d57f55 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -474,8 +474,14 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	/*
 	 * The membarrier system call requires a full memory barrier and
 	 * core serialization before returning to user-space, after
-	 * storing to rq->curr. Writing to CR3 provides that full
-	 * memory barrier and core serializing instruction.
+	 * storing to rq->curr, when changing mm.  This is because
+	 * membarrier() sends IPIs to all CPUs that are in the target mm
+	 * to make them issue memory barriers.  However, if another CPU
+	 * switches to/from the target mm concurrently with
+	 * membarrier(), it can cause that CPU not to receive an IPI
+	 * when it really should issue a memory barrier.  Writing to CR3
+	 * provides that full memory barrier and core serializing
+	 * instruction.
 	 */
 	if (real_prev == next) {
 		VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 8f5759df7776..e1e8d4e3a213 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -78,28 +78,30 @@ int __init efi_alloc_page_tables(void)
 	gfp_mask = GFP_KERNEL | __GFP_ZERO;
 	efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER);
 	if (!efi_pgd)
-		return -ENOMEM;
+		goto fail;
 
 	pgd = efi_pgd + pgd_index(EFI_VA_END);
 	p4d = p4d_alloc(&init_mm, pgd, EFI_VA_END);
-	if (!p4d) {
-		free_page((unsigned long)efi_pgd);
-		return -ENOMEM;
-	}
+	if (!p4d)
+		goto free_pgd;
 
 	pud = pud_alloc(&init_mm, p4d, EFI_VA_END);
-	if (!pud) {
-		if (pgtable_l5_enabled())
-			free_page((unsigned long) pgd_page_vaddr(*pgd));
-		free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
-		return -ENOMEM;
-	}
+	if (!pud)
+		goto free_p4d;
 
 	efi_mm.pgd = efi_pgd;
 	mm_init_cpumask(&efi_mm);
 	init_new_context(NULL, &efi_mm);
 
 	return 0;
+
+free_p4d:
+	if (pgtable_l5_enabled())
+		free_page((unsigned long)pgd_page_vaddr(*pgd));
+free_pgd:
+	free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER);
+fail:
+	return -ENOMEM;
 }
 
 /*
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 799f4eba0a62..043c73dfd2c9 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -93,10 +93,20 @@ void xen_init_lock_cpu(int cpu)
 
 void xen_uninit_lock_cpu(int cpu)
 {
+	int irq;
+
 	if (!xen_pvspin)
 		return;
 
-	unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL);
+	/*
+	 * When booting the kernel with 'mitigations=auto,nosmt', the secondary
+	 * CPUs are not activated, and lock_kicker_irq is not initialized.
+	 */
+	irq = per_cpu(lock_kicker_irq, cpu);
+	if (irq == -1)
+		return;
+
+	unbind_from_irqhandler(irq, NULL);
 	per_cpu(lock_kicker_irq, cpu) = -1;
 	kfree(per_cpu(irq_name, cpu));
 	per_cpu(irq_name, cpu) = NULL;