Merge branch 'linus' into locking/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

20 files changed, 170 insertions, 126 deletions

diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index f105ae8651c94..f62e347862ccc 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -602,10 +602,12 @@ ENTRY(trampoline_32bit_src)
 3:
 	/* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */
 	pushl	%ecx
+	pushl	%edx
 	movl	$MSR_EFER, %ecx
 	rdmsr
 	btsl	$_EFER_LME, %eax
 	wrmsr
+	popl	%edx
 	popl	%ecx
 
 	/* Enable PAE and LA57 (if required) paging modes */
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 374a19712e200..b684f0294f35d 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2278,6 +2278,19 @@ void perf_check_microcode(void)
 		x86_pmu.check_microcode();
 }
 
+static int x86_pmu_check_period(struct perf_event *event, u64 value)
+{
+	if (x86_pmu.check_period && x86_pmu.check_period(event, value))
+		return -EINVAL;
+
+	if (value && x86_pmu.limit_period) {
+		if (x86_pmu.limit_period(event, value) > value)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static struct pmu pmu = {
 	.pmu_enable		= x86_pmu_enable,
 	.pmu_disable		= x86_pmu_disable,
@@ -2302,6 +2315,7 @@ static struct pmu pmu = {
 	.event_idx		= x86_pmu_event_idx,
 	.sched_task		= x86_pmu_sched_task,
 	.task_ctx_size          = sizeof(struct x86_perf_task_context),
+	.check_period		= x86_pmu_check_period,
 };
 
 void arch_perf_update_userpage(struct perf_event *event,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 40e12cfc87f62..730978dff63f5 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3559,6 +3559,14 @@ static void free_excl_cntrs(int cpu)
 
 static void intel_pmu_cpu_dying(int cpu)
 {
+	fini_debug_store_on_cpu(cpu);
+
+	if (x86_pmu.counter_freezing)
+		disable_counter_freeze();
+}
+
+static void intel_pmu_cpu_dead(int cpu)
+{
 	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
 	struct intel_shared_regs *pc;
 
@@ -3570,11 +3578,6 @@ static void intel_pmu_cpu_dying(int cpu)
 	}
 
 	free_excl_cntrs(cpu);
-
-	fini_debug_store_on_cpu(cpu);
-
-	if (x86_pmu.counter_freezing)
-		disable_counter_freeze();
 }
 
 static void intel_pmu_sched_task(struct perf_event_context *ctx,
@@ -3584,6 +3587,11 @@ static void intel_pmu_sched_task(struct perf_event_context *ctx,
 	intel_pmu_lbr_sched_task(ctx, sched_in);
 }
 
+static int intel_pmu_check_period(struct perf_event *event, u64 value)
+{
+	return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0;
+}
+
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -3663,6 +3671,9 @@ static __initconst const struct x86_pmu core_pmu = {
 	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
+	.cpu_dead		= intel_pmu_cpu_dead,
+
+	.check_period		= intel_pmu_check_period,
 };
 
 static struct attribute *intel_pmu_attrs[];
@@ -3703,8 +3714,12 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
+	.cpu_dead		= intel_pmu_cpu_dead,
+
 	.guest_get_msrs		= intel_guest_get_msrs,
 	.sched_task		= intel_pmu_sched_task,
+
+	.check_period		= intel_pmu_check_period,
 };
 
 static __init void intel_clovertown_quirk(void)
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index c07bee31abe85..b10e04387f380 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1222,6 +1222,8 @@ static struct pci_driver snbep_uncore_pci_driver = {
 	.id_table	= snbep_uncore_pci_ids,
 };
 
+#define NODE_ID_MASK	0x7
+
 /*
  * build pci bus to socket mapping
  */
@@ -1243,7 +1245,7 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool
 		err = pci_read_config_dword(ubox_dev, nodeid_loc, &config);
 		if (err)
 			break;
-		nodeid = config;
+		nodeid = config & NODE_ID_MASK;
 		/* get the Node ID mapping */
 		err = pci_read_config_dword(ubox_dev, idmap_loc, &config);
 		if (err)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 78d7b7031bfcc..d46fd6754d920 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -646,6 +646,11 @@ struct x86_pmu {
 	 * Intel host/guest support (KVM)
 	 */
 	struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
+
+	/*
+	 * Check period value for PERF_EVENT_IOC_PERIOD ioctl.
+	 */
+	int (*check_period) (struct perf_event *event, u64 period);
 };
 
 struct x86_perf_task_context {
@@ -857,7 +862,7 @@ static inline int amd_pmu_init(void)
 
 #ifdef CONFIG_CPU_SUP_INTEL
 
-static inline bool intel_pmu_has_bts(struct perf_event *event)
+static inline bool intel_pmu_has_bts_period(struct perf_event *event, u64 period)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned int hw_event, bts_event;
@@ -868,7 +873,14 @@ static inline bool intel_pmu_has_bts(struct perf_event *event)
 	hw_event = hwc->config & INTEL_ARCH_EVENT_MASK;
 	bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
 
-	return hw_event == bts_event && hwc->sample_period == 1;
+	return hw_event == bts_event && period == 1;
+}
+
+static inline bool intel_pmu_has_bts(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	return intel_pmu_has_bts_period(event, hwc->sample_period);
 }
 
 int intel_pmu_save_and_restart(struct perf_event *event);
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index f65b78d32f5eb..7dbbe9ffda173 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -51,7 +51,7 @@ static unsigned long get_dr(int n)
 /*
  * fill in the user structure for a core dump..
  */
-static void dump_thread32(struct pt_regs *regs, struct user32 *dump)
+static void fill_dump(struct pt_regs *regs, struct user32 *dump)
 {
 	u32 fs, gs;
 	memset(dump, 0, sizeof(*dump));
@@ -157,10 +157,12 @@ static int aout_core_dump(struct coredump_params *cprm)
 	fs = get_fs();
 	set_fs(KERNEL_DS);
 	has_dumped = 1;
+
+	fill_dump(cprm->regs, &dump);
+
 	strncpy(dump.u_comm, current->comm, sizeof(current->comm));
 	dump.u_ar0 = offsetof(struct user32, regs);
 	dump.signal = cprm->siginfo->si_signo;
-	dump_thread32(cprm->regs, &dump);
 
 	/*
 	 * If the size of the dump file exceeds the rlimit, then see
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index d9a9993af882a..9f15384c504a4 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -52,6 +52,8 @@
 
 #define INTEL_FAM6_CANNONLAKE_MOBILE	0x66
 
+#define INTEL_FAM6_ICELAKE_MOBILE	0x7E
+
 /* "Small Core" Processors (Atom) */
 
 #define INTEL_FAM6_ATOM_BONNELL		0x1C /* Diamondville, Pineview */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 4660ce90de7ff..180373360e342 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -299,6 +299,7 @@ union kvm_mmu_extended_role {
 		unsigned int cr4_smap:1;
 		unsigned int cr4_smep:1;
 		unsigned int cr4_la57:1;
+		unsigned int maxphyaddr:6;
 	};
 };
 
@@ -397,6 +398,7 @@ struct kvm_mmu {
 	void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 			   u64 *spte, const void *pte);
 	hpa_t root_hpa;
+	gpa_t root_cr3;
 	union kvm_mmu_role mmu_role;
 	u8 root_level;
 	u8 shadow_root_level;
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 40616e8052924..2779ace16d23f 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1065,7 +1065,7 @@ static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
 static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 			      pmd_t *pmdp, pmd_t pmd)
 {
-	native_set_pmd(pmdp, pmd);
+	set_pmd(pmdp, pmd);
 }
 
 static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h
index e652a7cc61863..3f697a9e3f59b 100644
--- a/arch/x86/include/asm/uv/bios.h
+++ b/arch/x86/include/asm/uv/bios.h
@@ -48,7 +48,8 @@ enum {
 	BIOS_STATUS_SUCCESS		=  0,
 	BIOS_STATUS_UNIMPLEMENTED	= -ENOSYS,
 	BIOS_STATUS_EINVAL		= -EINVAL,
-	BIOS_STATUS_UNAVAIL		= -EBUSY
+	BIOS_STATUS_UNAVAIL		= -EBUSY,
+	BIOS_STATUS_ABORT		= -EINTR,
 };
 
 /* Address map parameters */
@@ -167,4 +168,9 @@ extern long system_serial_number;
 
 extern struct kobject *sgi_uv_kobj;	/* /sys/firmware/sgi_uv */
 
+/*
+ * EFI runtime lock; cf. firmware/efi/runtime-wrappers.c for details
+ */
+extern struct semaphore __efi_uv_runtime_lock;
+
 #endif /* _ASM_X86_UV_BIOS_H */
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 672c7225cb1b8..6ce290c506d93 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -784,6 +784,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
 			quirk_no_way_out(i, m, regs);
 
 		if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
+			m->bank = i;
 			mce_read_aux(m, i);
 			*msg = tmp;
 			return 1;
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index bbffa6c54697a..c07958b59f505 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -335,6 +335,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	unsigned f_xsaves = kvm_x86_ops->xsaves_supported() ? F(XSAVES) : 0;
 	unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0;
 	unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0;
+	unsigned f_la57 = 0;
 
 	/* cpuid 1.edx */
 	const u32 kvm_cpuid_1_edx_x86_features =
@@ -489,7 +490,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			// TSC_ADJUST is emulated
 			entry->ebx |= F(TSC_ADJUST);
 			entry->ecx &= kvm_cpuid_7_0_ecx_x86_features;
+			f_la57 = entry->ecx & F(LA57);
 			cpuid_mask(&entry->ecx, CPUID_7_ECX);
+			/* Set LA57 based on hardware capability. */
+			entry->ecx |= f_la57;
 			entry->ecx |= f_umip;
 			/* PKU is not yet implemented for shadow paging. */
 			if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE))
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index da9c42349b1f8..f2d1d230d5b84 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3555,6 +3555,7 @@ void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 							   &invalid_list);
 			mmu->root_hpa = INVALID_PAGE;
 		}
+		mmu->root_cr3 = 0;
 	}
 
 	kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
@@ -3610,6 +3611,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu)
 		vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root);
 	} else
 		BUG();
+	vcpu->arch.mmu->root_cr3 = vcpu->arch.mmu->get_cr3(vcpu);
 
 	return 0;
 }
@@ -3618,10 +3620,11 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu_page *sp;
 	u64 pdptr, pm_mask;
-	gfn_t root_gfn;
+	gfn_t root_gfn, root_cr3;
 	int i;
 
-	root_gfn = vcpu->arch.mmu->get_cr3(vcpu) >> PAGE_SHIFT;
+	root_cr3 = vcpu->arch.mmu->get_cr3(vcpu);
+	root_gfn = root_cr3 >> PAGE_SHIFT;
 
 	if (mmu_check_root(vcpu, root_gfn))
 		return 1;
@@ -3646,7 +3649,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 		++sp->root_count;
 		spin_unlock(&vcpu->kvm->mmu_lock);
 		vcpu->arch.mmu->root_hpa = root;
-		return 0;
+		goto set_root_cr3;
 	}
 
 	/*
@@ -3712,6 +3715,9 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 		vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->lm_root);
 	}
 
+set_root_cr3:
+	vcpu->arch.mmu->root_cr3 = root_cr3;
+
 	return 0;
 }
 
@@ -4163,7 +4169,7 @@ static bool cached_root_available(struct kvm_vcpu *vcpu, gpa_t new_cr3,
 	struct kvm_mmu_root_info root;
 	struct kvm_mmu *mmu = vcpu->arch.mmu;
 
-	root.cr3 = mmu->get_cr3(vcpu);
+	root.cr3 = mmu->root_cr3;
 	root.hpa = mmu->root_hpa;
 
 	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
@@ -4176,6 +4182,7 @@ static bool cached_root_available(struct kvm_vcpu *vcpu, gpa_t new_cr3,
 	}
 
 	mmu->root_hpa = root.hpa;
+	mmu->root_cr3 = root.cr3;
 
 	return i < KVM_MMU_NUM_PREV_ROOTS;
 }
@@ -4770,6 +4777,7 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu)
 	ext.cr4_pse = !!is_pse(vcpu);
 	ext.cr4_pke = !!kvm_read_cr4_bits(vcpu, X86_CR4_PKE);
 	ext.cr4_la57 = !!kvm_read_cr4_bits(vcpu, X86_CR4_LA57);
+	ext.maxphyaddr = cpuid_maxphyaddr(vcpu);
 
 	ext.valid = 1;
 
@@ -5516,11 +5524,13 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
 	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
 
 	vcpu->arch.root_mmu.root_hpa = INVALID_PAGE;
+	vcpu->arch.root_mmu.root_cr3 = 0;
 	vcpu->arch.root_mmu.translate_gpa = translate_gpa;
 	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
 		vcpu->arch.root_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
 
 	vcpu->arch.guest_mmu.root_hpa = INVALID_PAGE;
+	vcpu->arch.guest_mmu.root_cr3 = 0;
 	vcpu->arch.guest_mmu.translate_gpa = translate_gpa;
 	for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
 		vcpu->arch.guest_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 8ff20523661b8..d737a51a53ca3 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -211,6 +211,7 @@ static void free_nested(struct kvm_vcpu *vcpu)
 	if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
 		return;
 
+	hrtimer_cancel(&vmx->nested.preemption_timer);
 	vmx->nested.vmxon = false;
 	vmx->nested.smm.vmxon = false;
 	free_vpid(vmx->nested.vpid02);
@@ -2472,6 +2473,10 @@ static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu,
 	    (nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id))
 		return -EINVAL;
 
+	if (!nested_cpu_has_preemption_timer(vmcs12) &&
+	    nested_cpu_has_save_preemption_timer(vmcs12))
+		return -EINVAL;
+
 	if (nested_cpu_has_ept(vmcs12) &&
 	    !valid_ept_address(vcpu, vmcs12->ept_pointer))
 		return -EINVAL;
@@ -5556,9 +5561,11 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
 	 * secondary cpu-based controls.  Do not include those that
 	 * depend on CPUID bits, they are added later by vmx_cpuid_update.
 	 */
-	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
-		msrs->secondary_ctls_low,
-		msrs->secondary_ctls_high);
+	if (msrs->procbased_ctls_high & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)
+		rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
+		      msrs->secondary_ctls_low,
+		      msrs->secondary_ctls_high);
+
 	msrs->secondary_ctls_low = 0;
 	msrs->secondary_ctls_high &=
 		SECONDARY_EXEC_DESC |
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 95d6180450019..30a6bcd735ec3 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -863,7 +863,8 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 	if (!entry_only)
 		j = find_msr(&m->host, msr);
 
-	if (i == NR_AUTOLOAD_MSRS || j == NR_AUTOLOAD_MSRS) {
+	if ((i < 0 && m->guest.nr == NR_AUTOLOAD_MSRS) ||
+		(j < 0 &&  m->host.nr == NR_AUTOLOAD_MSRS)) {
 		printk_once(KERN_WARNING "Not enough msr switch entries. "
 				"Can't add msr %x\n", msr);
 		return;
@@ -1193,21 +1194,6 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 	if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu)
 		return;
 
-	/*
-	 * First handle the simple case where no cmpxchg is necessary; just
-	 * allow posting non-urgent interrupts.
-	 *
-	 * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change
-	 * PI.NDST: pi_post_block will do it for us and the wakeup_handler
-	 * expects the VCPU to be on the blocked_vcpu_list that matches
-	 * PI.NDST.
-	 */
-	if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR ||
-	    vcpu->cpu == cpu) {
-		pi_clear_sn(pi_desc);
-		return;
-	}
-
 	/* The full case.  */
 	do {
 		old.control = new.control = pi_desc->control;
@@ -1222,6 +1208,17 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 		new.sn = 0;
 	} while (cmpxchg64(&pi_desc->control, old.control,
 			   new.control) != old.control);
+
+	/*
+	 * Clear SN before reading the bitmap.  The VT-d firmware
+	 * writes the bitmap and reads SN atomically (5.2.3 in the
+	 * spec), so it doesn't really have a memory barrier that
+	 * pairs with this, but we cannot do that and we need one.
+	 */
+	smp_mb__after_atomic();
+
+	if (!bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS))
+		pi_set_on(pi_desc);
 }
 
 /*
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 99328954c2fc1..0ac0a64c7790f 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -337,16 +337,16 @@ static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
 	return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
 }
 
-static inline void pi_clear_sn(struct pi_desc *pi_desc)
+static inline void pi_set_sn(struct pi_desc *pi_desc)
 {
-	return clear_bit(POSTED_INTR_SN,
+	return set_bit(POSTED_INTR_SN,
 			(unsigned long *)&pi_desc->control);
 }
 
-static inline void pi_set_sn(struct pi_desc *pi_desc)
+static inline void pi_set_on(struct pi_desc *pi_desc)
 {
-	return set_bit(POSTED_INTR_SN,
-			(unsigned long *)&pi_desc->control);
+	set_bit(POSTED_INTR_ON,
+		(unsigned long *)&pi_desc->control);
 }
 
 static inline void pi_clear_on(struct pi_desc *pi_desc)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3d27206f6c010..941f932373d03 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5116,6 +5116,13 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
 {
 	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
 
+	/*
+	 * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED
+	 * is returned, but our callers are not ready for that and they blindly
+	 * call kvm_inject_page_fault.  Ensure that they at least do not leak
+	 * uninitialized kernel stack memory into cr2 and error code.
+	 */
+	memset(exception, 0, sizeof(*exception));
 	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access,
 					  exception);
 }
@@ -7794,7 +7801,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	 * 1) We should set ->mode before checking ->requests.  Please see
 	 * the comment in kvm_vcpu_exiting_guest_mode().
 	 *
-	 * 2) For APICv, we should set ->mode before checking PIR.ON.  This
+	 * 2) For APICv, we should set ->mode before checking PID.ON. This
 	 * pairs with the memory barrier implicit in pi_test_and_set_on
 	 * (see vmx_deliver_posted_interrupt).
 	 *
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 6521134057e8f..856fa409c5364 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -117,67 +117,11 @@ __visible bool ex_handler_fprestore(const struct exception_table_entry *fixup,
 }
 EXPORT_SYMBOL_GPL(ex_handler_fprestore);
 
-/* Helper to check whether a uaccess fault indicates a kernel bug. */
-static bool bogus_uaccess(struct pt_regs *regs, int trapnr,
-			  unsigned long fault_addr)
-{
-	/* This is the normal case: #PF with a fault address in userspace. */
-	if (trapnr == X86_TRAP_PF && fault_addr < TASK_SIZE_MAX)
-		return false;
-
-	/*
-	 * This code can be reached for machine checks, but only if the #MC
-	 * handler has already decided that it looks like a candidate for fixup.
-	 * This e.g. happens when attempting to access userspace memory which
-	 * the CPU can't access because of uncorrectable bad memory.
-	 */
-	if (trapnr == X86_TRAP_MC)
-		return false;
-
-	/*
-	 * There are two remaining exception types we might encounter here:
-	 *  - #PF for faulting accesses to kernel addresses
-	 *  - #GP for faulting accesses to noncanonical addresses
-	 * Complain about anything else.
-	 */
-	if (trapnr != X86_TRAP_PF && trapnr != X86_TRAP_GP) {
-		WARN(1, "unexpected trap %d in uaccess\n", trapnr);
-		return false;
-	}
-
-	/*
-	 * This is a faulting memory access in kernel space, on a kernel
-	 * address, in a usercopy function. This can e.g. be caused by improper
-	 * use of helpers like __put_user and by improper attempts to access
-	 * userspace addresses in KERNEL_DS regions.
-	 * The one (semi-)legitimate exception are probe_kernel_{read,write}(),
-	 * which can be invoked from places like kgdb, /dev/mem (for reading)
-	 * and privileged BPF code (for reading).
-	 * The probe_kernel_*() functions set the kernel_uaccess_faults_ok flag
-	 * to tell us that faulting on kernel addresses, and even noncanonical
-	 * addresses, in a userspace accessor does not necessarily imply a
-	 * kernel bug, root might just be doing weird stuff.
-	 */
-	if (current->kernel_uaccess_faults_ok)
-		return false;
-
-	/* This is bad. Refuse the fixup so that we go into die(). */
-	if (trapnr == X86_TRAP_PF) {
-		pr_emerg("BUG: pagefault on kernel address 0x%lx in non-whitelisted uaccess\n",
-			 fault_addr);
-	} else {
-		pr_emerg("BUG: GPF in non-whitelisted uaccess (non-canonical address?)\n");
-	}
-	return true;
-}
-
 __visible bool ex_handler_uaccess(const struct exception_table_entry *fixup,
 				  struct pt_regs *regs, int trapnr,
 				  unsigned long error_code,
 				  unsigned long fault_addr)
 {
-	if (bogus_uaccess(regs, trapnr, fault_addr))
-		return false;
 	regs->ip = ex_fixup_addr(fixup);
 	return true;
 }
@@ -188,8 +132,6 @@ __visible bool ex_handler_ext(const struct exception_table_entry *fixup,
 			      unsigned long error_code,
 			      unsigned long fault_addr)
 {
-	if (bogus_uaccess(regs, trapnr, fault_addr))
-		return false;
 	/* Special hack for uaccess_err */
 	current->thread.uaccess_err = 1;
 	regs->ip = ex_fixup_addr(fixup);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 4f8972311a77e..14e6119838a64 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -230,6 +230,29 @@ static bool __cpa_pfn_in_highmap(unsigned long pfn)
 
 #endif
 
+/*
+ * See set_mce_nospec().
+ *
+ * Machine check recovery code needs to change cache mode of poisoned pages to
+ * UC to avoid speculative access logging another error. But passing the
+ * address of the 1:1 mapping to set_memory_uc() is a fine way to encourage a
+ * speculative access. So we cheat and flip the top bit of the address. This
+ * works fine for the code that updates the page tables. But at the end of the
+ * process we need to flush the TLB and cache and the non-canonical address
+ * causes a #GP fault when used by the INVLPG and CLFLUSH instructions.
+ *
+ * But in the common case we already have a canonical address. This code
+ * will fix the top bit if needed and is a no-op otherwise.
+ */
+static inline unsigned long fix_addr(unsigned long addr)
+{
+#ifdef CONFIG_X86_64
+	return (long)(addr << 1) >> 1;
+#else
+	return addr;
+#endif
+}
+
 static unsigned long __cpa_addr(struct cpa_data *cpa, unsigned long idx)
 {
 	if (cpa->flags & CPA_PAGES_ARRAY) {
@@ -313,7 +336,7 @@ void __cpa_flush_tlb(void *data)
 	unsigned int i;
 
 	for (i = 0; i < cpa->numpages; i++)
-		__flush_tlb_one_kernel(__cpa_addr(cpa, i));
+		__flush_tlb_one_kernel(fix_addr(__cpa_addr(cpa, i)));
 }
 
 static void cpa_flush(struct cpa_data *data, int cache)
@@ -347,7 +370,7 @@ static void cpa_flush(struct cpa_data *data, int cache)
 		 * Only flush present addresses:
 		 */
 		if (pte && (pte_val(*pte) & _PAGE_PRESENT))
-			clflush_cache_range_opt((void *)addr, PAGE_SIZE);
+			clflush_cache_range_opt((void *)fix_addr(addr), PAGE_SIZE);
 	}
 	mb();
 }
@@ -1627,29 +1650,6 @@ out:
 	return ret;
 }
 
-/*
- * Machine check recovery code needs to change cache mode of poisoned
- * pages to UC to avoid speculative access logging another error. But
- * passing the address of the 1:1 mapping to set_memory_uc() is a fine
- * way to encourage a speculative access. So we cheat and flip the top
- * bit of the address. This works fine for the code that updates the
- * page tables. But at the end of the process we need to flush the cache
- * and the non-canonical address causes a #GP fault when used by the
- * CLFLUSH instruction.
- *
- * But in the common case we already have a canonical address. This code
- * will fix the top bit if needed and is a no-op otherwise.
- */
-static inline unsigned long make_addr_canonical_again(unsigned long addr)
-{
-#ifdef CONFIG_X86_64
-	return (long)(addr << 1) >> 1;
-#else
-	return addr;
-#endif
-}
-
-
 static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 				    pgprot_t mask_set, pgprot_t mask_clr,
 				    int force_split, int in_flag,
diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c
index 4a6a5a26c5829..eb33432f2f241 100644
--- a/arch/x86/platform/uv/bios_uv.c
+++ b/arch/x86/platform/uv/bios_uv.c
@@ -29,7 +29,8 @@
 
 struct uv_systab *uv_systab;
 
-s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5)
+static s64 __uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
+			u64 a4, u64 a5)
 {
 	struct uv_systab *tab = uv_systab;
 	s64 ret;
@@ -51,6 +52,19 @@ s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5)
 
 	return ret;
 }
+
+s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5)
+{
+	s64 ret;
+
+	if (down_interruptible(&__efi_uv_runtime_lock))
+		return BIOS_STATUS_ABORT;
+
+	ret = __uv_bios_call(which, a1, a2, a3, a4, a5);
+	up(&__efi_uv_runtime_lock);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(uv_bios_call);
 
 s64 uv_bios_call_irqsave(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
@@ -59,10 +73,15 @@ s64 uv_bios_call_irqsave(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
 	unsigned long bios_flags;
 	s64 ret;
 
+	if (down_interruptible(&__efi_uv_runtime_lock))
+		return BIOS_STATUS_ABORT;
+
 	local_irq_save(bios_flags);
-	ret = uv_bios_call(which, a1, a2, a3, a4, a5);
+	ret = __uv_bios_call(which, a1, a2, a3, a4, a5);
 	local_irq_restore(bios_flags);
 
+	up(&__efi_uv_runtime_lock);
+
 	return ret;
 }