Merge branch 'aarch64/for-next/ras-apei' into aarch64/for-next/core

Merge in arm64 ACPI RAS support (APEI/GHES) from Tyler Baicar.

24 files changed, 288 insertions, 147 deletions

diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index a3f0b3d50089..ebf020b02bc8 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -187,6 +187,16 @@
 #define FSC_FAULT	(0x04)
 #define FSC_ACCESS	(0x08)
 #define FSC_PERM	(0x0c)
+#define FSC_SEA		(0x10)
+#define FSC_SEA_TTW0	(0x14)
+#define FSC_SEA_TTW1	(0x15)
+#define FSC_SEA_TTW2	(0x16)
+#define FSC_SEA_TTW3	(0x17)
+#define FSC_SECC	(0x18)
+#define FSC_SECC_TTW0	(0x1c)
+#define FSC_SECC_TTW1	(0x1d)
+#define FSC_SECC_TTW2	(0x1e)
+#define FSC_SECC_TTW3	(0x1f)
 
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
 #define HPFAR_MASK	(~0xf)
diff --git a/arch/arm/include/asm/system_misc.h b/arch/arm/include/asm/system_misc.h
index a3d61ad984af..8c4a89f5ce7d 100644
--- a/arch/arm/include/asm/system_misc.h
+++ b/arch/arm/include/asm/system_misc.h
@@ -22,6 +22,11 @@ extern void (*arm_pm_idle)(void);
 
 extern unsigned int user_debug;
 
+static inline int handle_guest_sea(phys_addr_t addr, unsigned int esr)
+{
+	return -1;
+}
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_ARM_SYSTEM_MISC_H */
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index b37ac9b2a36b..b52db8bb1270 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -20,6 +20,7 @@ config ARM64
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG if ACPI_APEI_SEA
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 	select ARCH_SUPPORTS_ATOMIC_RMW
@@ -94,6 +95,7 @@ config ARM64
 	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP if NUMA
+	select HAVE_NMI if ACPI_APEI_SEA
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index 0e99978da3f0..59cca1d6ec54 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -23,9 +23,9 @@
 #define ACPI_MADT_GICC_LENGTH	\
 	(acpi_gbl_FADT.header.revision < 6 ? 76 : 80)
 
-#define BAD_MADT_GICC_ENTRY(entry, end)						\
-	(!(entry) || (unsigned long)(entry) + sizeof(*(entry)) > (end) ||	\
-	 (entry)->header.length != ACPI_MADT_GICC_LENGTH)
+#define BAD_MADT_GICC_ENTRY(entry, end)					\
+	(!(entry) || (entry)->header.length != ACPI_MADT_GICC_LENGTH ||	\
+	(unsigned long)(entry) + ACPI_MADT_GICC_LENGTH > (end))
 
 /* Basic configuration for ACPI */
 #ifdef	CONFIG_ACPI
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 85997c0e5443..28bf02efce76 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -83,6 +83,7 @@
 #define ESR_ELx_WNR		(UL(1) << 6)
 
 /* Shared ISS field definitions for Data/Instruction aborts */
+#define ESR_ELx_FnV		(UL(1) << 10)
 #define ESR_ELx_EA		(UL(1) << 9)
 #define ESR_ELx_S1PTW		(UL(1) << 7)
 
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 6e99978e83bd..61d694c2eae5 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -204,6 +204,16 @@
 #define FSC_FAULT	ESR_ELx_FSC_FAULT
 #define FSC_ACCESS	ESR_ELx_FSC_ACCESS
 #define FSC_PERM	ESR_ELx_FSC_PERM
+#define FSC_SEA		ESR_ELx_FSC_EXTABT
+#define FSC_SEA_TTW0	(0x14)
+#define FSC_SEA_TTW1	(0x15)
+#define FSC_SEA_TTW2	(0x16)
+#define FSC_SEA_TTW3	(0x17)
+#define FSC_SECC	(0x18)
+#define FSC_SECC_TTW0	(0x1c)
+#define FSC_SECC_TTW1	(0x1d)
+#define FSC_SECC_TTW2	(0x1e)
+#define FSC_SECC_TTW3	(0x1f)
 
 /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
 #define HPFAR_MASK	(~UL(0xf))
diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
index d0beefeb6d25..07aa8e3c5630 100644
--- a/arch/arm64/include/asm/system_misc.h
+++ b/arch/arm64/include/asm/system_misc.h
@@ -56,6 +56,8 @@ extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
 	__show_ratelimited;						\
 })
 
+int handle_guest_sea(phys_addr_t addr, unsigned int esr);
+
 #endif	/* __ASSEMBLY__ */
 
 #endif	/* __ASM_SYSTEM_MISC_H */
diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c
index 108283443336..a7f6c01c13b9 100644
--- a/arch/arm64/kernel/pci.c
+++ b/arch/arm64/kernel/pci.c
@@ -194,8 +194,10 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
 		return NULL;
 
 	root_ops = kzalloc_node(sizeof(*root_ops), GFP_KERNEL, node);
-	if (!root_ops)
+	if (!root_ops) {
+		kfree(ri);
 		return NULL;
+	}
 
 	ri->cfg = pci_acpi_setup_ecam_mapping(root);
 	if (!ri->cfg) {
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index ea2ea68d1bd7..c7861c9864e6 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -43,6 +43,8 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 
+#include <acpi/ghes.h>
+
 struct fault_info {
 	int	(*fn)(unsigned long addr, unsigned int esr,
 		      struct pt_regs *regs);
@@ -559,6 +561,47 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
 	return 1;
 }
 
+/*
+ * This abort handler deals with Synchronous External Abort.
+ * It calls notifiers, and then returns "fault".
+ */
+static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
+{
+	struct siginfo info;
+	const struct fault_info *inf;
+	int ret = 0;
+
+	inf = esr_to_fault_info(esr);
+	pr_err("Synchronous External Abort: %s (0x%08x) at 0x%016lx\n",
+		inf->name, esr, addr);
+
+	/*
+	 * Synchronous aborts may interrupt code which had interrupts masked.
+	 * Before calling out into the wider kernel tell the interested
+	 * subsystems.
+	 */
+	if (IS_ENABLED(CONFIG_ACPI_APEI_SEA)) {
+		if (interrupts_enabled(regs))
+			nmi_enter();
+
+		ret = ghes_notify_sea();
+
+		if (interrupts_enabled(regs))
+			nmi_exit();
+	}
+
+	info.si_signo = SIGBUS;
+	info.si_errno = 0;
+	info.si_code  = 0;
+	if (esr & ESR_ELx_FnV)
+		info.si_addr = NULL;
+	else
+		info.si_addr  = (void __user *)addr;
+	arm64_notify_die("", regs, &info, esr);
+
+	return ret;
+}
+
 static const struct fault_info fault_info[] = {
 	{ do_bad,		SIGBUS,  0,		"ttbr address size fault"	},
 	{ do_bad,		SIGBUS,  0,		"level 1 address size fault"	},
@@ -576,22 +619,22 @@ static const struct fault_info fault_info[] = {
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
 	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort"	},
+	{ do_sea,		SIGBUS,  0,		"synchronous external abort"	},
 	{ do_bad,		SIGBUS,  0,		"unknown 17"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 18"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 19"			},
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error"	},
+	{ do_sea,		SIGBUS,  0,		"level 0 (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 1 (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 2 (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 3 (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"synchronous parity or ECC error" },
 	{ do_bad,		SIGBUS,  0,		"unknown 25"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 26"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 27"			},
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
+	{ do_sea,		SIGBUS,  0,		"level 0 synchronous parity error (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 1 synchronous parity error (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 2 synchronous parity error (translation table walk)"	},
+	{ do_sea,		SIGBUS,  0,		"level 3 synchronous parity error (translation table walk)"	},
 	{ do_bad,		SIGBUS,  0,		"unknown 32"			},
 	{ do_alignment_fault,	SIGBUS,  BUS_ADRALN,	"alignment fault"		},
 	{ do_bad,		SIGBUS,  0,		"unknown 34"			},
@@ -627,6 +670,23 @@ static const struct fault_info fault_info[] = {
 };
 
 /*
+ * Handle Synchronous External Aborts that occur in a guest kernel.
+ *
+ * The return value will be zero if the SEA was successfully handled
+ * and non-zero if there was an error processing the error or there was
+ * no error to process.
+ */
+int handle_guest_sea(phys_addr_t addr, unsigned int esr)
+{
+	int ret = -ENOENT;
+
+	if (IS_ENABLED(CONFIG_ACPI_APEI_SEA))
+		ret = ghes_notify_sea();
+
+	return ret;
+}
+
+/*
  * Dispatch a data abort to the relevant handler.
  */
 asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
diff --git a/arch/frv/include/asm/timex.h b/arch/frv/include/asm/timex.h
index a89bddefdacf..139093fab326 100644
--- a/arch/frv/include/asm/timex.h
+++ b/arch/frv/include/asm/timex.h
@@ -16,5 +16,11 @@ static inline cycles_t get_cycles(void)
 #define vxtime_lock()		do {} while (0)
 #define vxtime_unlock()		do {} while (0)
 
+/* This attribute is used in include/linux/jiffies.h alongside with
+ * __cacheline_aligned_in_smp. It is assumed that __cacheline_aligned_in_smp
+ * for frv does not contain another section specification.
+ */
+#define __jiffy_arch_data	__attribute__((__section__(".data")))
+
 #endif
 
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 918d4c73e951..5351e1f3950d 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -120,7 +120,6 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long usp,
 	struct thread_info *ti = task_thread_info(p);
 	struct pt_regs *childregs, *regs = current_pt_regs();
 	unsigned long childksp;
-	p->set_child_tid = p->clear_child_tid = NULL;
 
 	childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32;
 
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index f8da545854f9..106859ae27ff 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -167,8 +167,6 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
 
 	top_of_kernel_stack = sp;
 
-	p->set_child_tid = p->clear_child_tid = NULL;
-
 	/* Locate userspace context on stack... */
 	sp -= STACK_FRAME_OVERHEAD;	/* redzone */
 	sp -= sizeof(struct pt_regs);
diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h
index e784bed6ed7f..2b498e58b914 100644
--- a/arch/s390/include/asm/sysinfo.h
+++ b/arch/s390/include/asm/sysinfo.h
@@ -109,7 +109,7 @@ struct sysinfo_2_2_2 {
 	unsigned short cpus_shared;
 	char reserved_4[3];
 	unsigned char vsne;
-	uuid_be uuid;
+	uuid_t uuid;
 	char reserved_5[160];
 	char ext_name[256];
 };
@@ -134,7 +134,7 @@ struct sysinfo_3_2_2 {
 		char reserved_1[3];
 		unsigned char evmne;
 		unsigned int reserved_2;
-		uuid_be uuid;
+		uuid_t uuid;
 	} vm[8];
 	char reserved_3[1504];
 	char ext_names[8][256];
diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index eefcb54872a5..fb869b103825 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -242,7 +242,7 @@ static void print_ext_name(struct seq_file *m, int lvl,
 
 static void print_uuid(struct seq_file *m, int i, struct sysinfo_3_2_2 *info)
 {
-	if (!memcmp(&info->vm[i].uuid, &NULL_UUID_BE, sizeof(uuid_be)))
+	if (uuid_is_null(&info->vm[i].uuid))
 		return;
 	seq_printf(m, "VM%02d UUID:            %pUb\n", i, &info->vm[i].uuid);
 }
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 45db4d2ebd01..e9f4d762aa5b 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -320,7 +320,7 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax)
 }
 
 static enum ucode_state
-load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size);
+load_microcode_amd(bool save, u8 family, const u8 *data, size_t size);
 
 int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 {
@@ -338,8 +338,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax)
 	if (!desc.mc)
 		return -EINVAL;
 
-	ret = load_microcode_amd(smp_processor_id(), x86_family(cpuid_1_eax),
-				 desc.data, desc.size);
+	ret = load_microcode_amd(true, x86_family(cpuid_1_eax), desc.data, desc.size);
 	if (ret != UCODE_OK)
 		return -EINVAL;
 
@@ -675,7 +674,7 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
 }
 
 static enum ucode_state
-load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size)
+load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
 {
 	enum ucode_state ret;
 
@@ -689,8 +688,8 @@ load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size)
 
 #ifdef CONFIG_X86_32
 	/* save BSP's matching patch for early load */
-	if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) {
-		struct ucode_patch *p = find_patch(cpu);
+	if (save) {
+		struct ucode_patch *p = find_patch(0);
 		if (p) {
 			memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
 			memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data),
@@ -722,11 +721,12 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 {
 	char fw_name[36] = "amd-ucode/microcode_amd.bin";
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
+	bool bsp = c->cpu_index == boot_cpu_data.cpu_index;
 	enum ucode_state ret = UCODE_NFOUND;
 	const struct firmware *fw;
 
 	/* reload ucode container only on the boot cpu */
-	if (!refresh_fw || c->cpu_index != boot_cpu_data.cpu_index)
+	if (!refresh_fw || !bsp)
 		return UCODE_OK;
 
 	if (c->x86 >= 0x15)
@@ -743,7 +743,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
 		goto fw_release;
 	}
 
-	ret = load_microcode_amd(cpu, c->x86, fw->data, fw->size);
+	ret = load_microcode_amd(bsp, c->x86, fw->data, fw->size);
 
  fw_release:
 	release_firmware(fw);
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index ff40e74c9181..ffeae818aa7a 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -78,7 +78,7 @@ void __show_regs(struct pt_regs *regs, int all)
 
 	printk(KERN_DEFAULT "EIP: %pS\n", (void *)regs->ip);
 	printk(KERN_DEFAULT "EFLAGS: %08lx CPU: %d\n", regs->flags,
-		smp_processor_id());
+		raw_smp_processor_id());
 
 	printk(KERN_DEFAULT "EAX: %08lx EBX: %08lx ECX: %08lx EDX: %08lx\n",
 		regs->ax, regs->bx, regs->cx, regs->dx);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index c329d2894905..d24c8742d9b0 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1495,8 +1495,10 @@ EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use);
 
 static void cancel_hv_timer(struct kvm_lapic *apic)
 {
+	preempt_disable();
 	kvm_x86_ops->cancel_hv_timer(apic->vcpu);
 	apic->lapic_timer.hv_timer_in_use = false;
+	preempt_enable();
 }
 
 static bool start_hv_timer(struct kvm_lapic *apic)
@@ -1934,7 +1936,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
 	for (i = 0; i < KVM_APIC_LVT_NUM; i++)
 		kvm_lapic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
 	apic_update_lvtt(apic);
-	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED))
+	if (kvm_vcpu_is_reset_bsp(vcpu) &&
+	    kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED))
 		kvm_lapic_set_reg(apic, APIC_LVT0,
 			     SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
 	apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0));
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 183ddb235fb4..ba9891ac5c56 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1807,7 +1807,7 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
 	 * AMD's VMCB does not have an explicit unusable field, so emulate it
 	 * for cross vendor migration purposes by "not present"
 	 */
-	var->unusable = !var->present || (var->type == 0);
+	var->unusable = !var->present;
 
 	switch (seg) {
 	case VCPU_SREG_TR:
@@ -1840,6 +1840,7 @@ static void svm_get_segment(struct kvm_vcpu *vcpu,
 		 */
 		if (var->unusable)
 			var->db = 0;
+		/* This is symmetric with svm_set_segment() */
 		var->dpl = to_svm(vcpu)->vmcb->save.cpl;
 		break;
 	}
@@ -1980,18 +1981,14 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
 	s->base = var->base;
 	s->limit = var->limit;
 	s->selector = var->selector;
-	if (var->unusable)
-		s->attrib = 0;
-	else {
-		s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK);
-		s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT;
-		s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT;
-		s->attrib |= (var->present & 1) << SVM_SELECTOR_P_SHIFT;
-		s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT;
-		s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT;
-		s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT;
-		s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT;
-	}
+	s->attrib = (var->type & SVM_SELECTOR_TYPE_MASK);
+	s->attrib |= (var->s & 1) << SVM_SELECTOR_S_SHIFT;
+	s->attrib |= (var->dpl & 3) << SVM_SELECTOR_DPL_SHIFT;
+	s->attrib |= ((var->present & 1) && !var->unusable) << SVM_SELECTOR_P_SHIFT;
+	s->attrib |= (var->avl & 1) << SVM_SELECTOR_AVL_SHIFT;
+	s->attrib |= (var->l & 1) << SVM_SELECTOR_L_SHIFT;
+	s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT;
+	s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT;
 
 	/*
 	 * This is always accurate, except if SYSRET returned to a segment
@@ -2000,7 +1997,8 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
 	 * would entail passing the CPL to userspace and back.
 	 */
 	if (seg == VCPU_SREG_SS)
-		svm->vmcb->save.cpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3;
+		/* This is symmetric with svm_get_segment() */
+		svm->vmcb->save.cpl = (var->dpl & 3);
 
 	mark_dirty(svm->vmcb, VMCB_SEG);
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 72f78396bc09..9b4b5d6dcd34 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6914,97 +6914,21 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-/*
- * This function performs the various checks including
- * - if it's 4KB aligned
- * - No bits beyond the physical address width are set
- * - Returns 0 on success or else 1
- * (Intel SDM Section 30.3)
- */
-static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason,
-				  gpa_t *vmpointer)
+static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer)
 {
 	gva_t gva;
-	gpa_t vmptr;
 	struct x86_exception e;
-	struct page *page;
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	int maxphyaddr = cpuid_maxphyaddr(vcpu);
 
 	if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
 			vmcs_read32(VMX_INSTRUCTION_INFO), false, &gva))
 		return 1;
 
-	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr,
-				sizeof(vmptr), &e)) {
+	if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, vmpointer,
+				sizeof(*vmpointer), &e)) {
 		kvm_inject_page_fault(vcpu, &e);
 		return 1;
 	}
 
-	switch (exit_reason) {
-	case EXIT_REASON_VMON:
-		/*
-		 * SDM 3: 24.11.5
-		 * The first 4 bytes of VMXON region contain the supported
-		 * VMCS revision identifier
-		 *
-		 * Note - IA32_VMX_BASIC[48] will never be 1
-		 * for the nested case;
-		 * which replaces physical address width with 32
-		 *
-		 */
-		if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
-			nested_vmx_failInvalid(vcpu);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-
-		page = nested_get_page(vcpu, vmptr);
-		if (page == NULL) {
-			nested_vmx_failInvalid(vcpu);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-		if (*(u32 *)kmap(page) != VMCS12_REVISION) {
-			kunmap(page);
-			nested_release_page_clean(page);
-			nested_vmx_failInvalid(vcpu);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-		kunmap(page);
-		nested_release_page_clean(page);
-		vmx->nested.vmxon_ptr = vmptr;
-		break;
-	case EXIT_REASON_VMCLEAR:
-		if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
-			nested_vmx_failValid(vcpu,
-					     VMXERR_VMCLEAR_INVALID_ADDRESS);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-
-		if (vmptr == vmx->nested.vmxon_ptr) {
-			nested_vmx_failValid(vcpu,
-					     VMXERR_VMCLEAR_VMXON_POINTER);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-		break;
-	case EXIT_REASON_VMPTRLD:
-		if (!PAGE_ALIGNED(vmptr) || (vmptr >> maxphyaddr)) {
-			nested_vmx_failValid(vcpu,
-					     VMXERR_VMPTRLD_INVALID_ADDRESS);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-
-		if (vmptr == vmx->nested.vmxon_ptr) {
-			nested_vmx_failValid(vcpu,
-					     VMXERR_VMPTRLD_VMXON_POINTER);
-			return kvm_skip_emulated_instruction(vcpu);
-		}
-		break;
-	default:
-		return 1; /* shouldn't happen */
-	}
-
-	if (vmpointer)
-		*vmpointer = vmptr;
 	return 0;
 }
 
@@ -7066,6 +6990,8 @@ out_msr_bitmap:
 static int handle_vmon(struct kvm_vcpu *vcpu)
 {
 	int ret;
+	gpa_t vmptr;
+	struct page *page;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED
 		| FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
@@ -7095,9 +7021,37 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
 		return 1;
 	}
 
-	if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL))
+	if (nested_vmx_get_vmptr(vcpu, &vmptr))
 		return 1;
- 
+
+	/*
+	 * SDM 3: 24.11.5
+	 * The first 4 bytes of VMXON region contain the supported
+	 * VMCS revision identifier
+	 *
+	 * Note - IA32_VMX_BASIC[48] will never be 1 for the nested case;
+	 * which replaces physical address width with 32
+	 */
+	if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
+		nested_vmx_failInvalid(vcpu);
+		return kvm_skip_emulated_instruction(vcpu);
+	}
+
+	page = nested_get_page(vcpu, vmptr);
+	if (page == NULL) {
+		nested_vmx_failInvalid(vcpu);
+		return kvm_skip_emulated_instruction(vcpu);
+	}
+	if (*(u32 *)kmap(page) != VMCS12_REVISION) {
+		kunmap(page);
+		nested_release_page_clean(page);
+		nested_vmx_failInvalid(vcpu);
+		return kvm_skip_emulated_instruction(vcpu);
+	}
+	kunmap(page);
+	nested_release_page_clean(page);
+
+	vmx->nested.vmxon_ptr = vmptr;
 	ret = enter_vmx_operation(vcpu);
 	if (ret)
 		return ret;
@@ -7213,9 +7167,19 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMCLEAR, &vmptr))
+	if (nested_vmx_get_vmptr(vcpu, &vmptr))
 		return 1;
 
+	if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
+		nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS);
+		return kvm_skip_emulated_instruction(vcpu);
+	}
+
+	if (vmptr == vmx->nested.vmxon_ptr) {
+		nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_VMXON_POINTER);
+		return kvm_skip_emulated_instruction(vcpu);
+	}
+
 	if (vmptr == vmx->nested.current_vmptr)
 		nested_release_vmcs12(vmx);
 
@@ -7545,9 +7509,19 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu)
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMPTRLD, &vmptr))
+	if (nested_vmx_get_vmptr(vcpu, &vmptr))
 		return 1;
 
+	if (!PAGE_ALIGNED(vmptr) || (vmptr >> cpuid_maxphyaddr(vcpu))) {
+		nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS);
+		return kvm_skip_emulated_instruction(vcpu);
+	}
+
+	if (vmptr == vmx->nested.vmxon_ptr) {
+		nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_VMXON_POINTER);
+		return kvm_skip_emulated_instruction(vcpu);
+	}
+
 	if (vmx->nested.current_vmptr != vmptr) {
 		struct vmcs12 *new_vmcs12;
 		struct page *page;
@@ -7913,11 +7887,13 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
 {
 	unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 	int cr = exit_qualification & 15;
-	int reg = (exit_qualification >> 8) & 15;
-	unsigned long val = kvm_register_readl(vcpu, reg);
+	int reg;
+	unsigned long val;
 
 	switch ((exit_qualification >> 4) & 3) {
 	case 0: /* mov to cr */
+		reg = (exit_qualification >> 8) & 15;
+		val = kvm_register_readl(vcpu, reg);
 		switch (cr) {
 		case 0:
 			if (vmcs12->cr0_guest_host_mask &
@@ -7972,6 +7948,7 @@ static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
 		 * lmsw can change bits 1..3 of cr0, and only set bit 0 of
 		 * cr0. Other attempted changes are ignored, with no exit.
 		 */
+		val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f;
 		if (vmcs12->cr0_guest_host_mask & 0xe &
 		    (val ^ vmcs12->cr0_read_shadow))
 			return true;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 02363e37d4a6..a2cd0997343c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8394,10 +8394,13 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.pv.pv_unhalted)
 		return true;
 
-	if (atomic_read(&vcpu->arch.nmi_queued))
+	if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
+	    (vcpu->arch.nmi_pending &&
+	     kvm_x86_ops->nmi_allowed(vcpu)))
 		return true;
 
-	if (kvm_test_request(KVM_REQ_SMI, vcpu))
+	if (kvm_test_request(KVM_REQ_SMI, vcpu) ||
+	    (vcpu->arch.smi_pending && !is_smm(vcpu)))
 		return true;
 
 	if (kvm_arch_interrupt_allowed(vcpu) &&
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 83a59a67757a..9b78685b66e6 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -65,11 +65,9 @@ static int __init nopat(char *str)
 }
 early_param("nopat", nopat);
 
-static bool __read_mostly __pat_initialized = false;
-
 bool pat_enabled(void)
 {
-	return __pat_initialized;
+	return !!__pat_enabled;
 }
 EXPORT_SYMBOL_GPL(pat_enabled);
 
@@ -227,14 +225,13 @@ static void pat_bsp_init(u64 pat)
 	}
 
 	wrmsrl(MSR_IA32_CR_PAT, pat);
-	__pat_initialized = true;
 
 	__init_cache_modes(pat);
 }
 
 static void pat_ap_init(u64 pat)
 {
-	if (!this_cpu_has(X86_FEATURE_PAT)) {
+	if (!boot_cpu_has(X86_FEATURE_PAT)) {
 		/*
 		 * If this happens we are on a secondary CPU, but switched to
 		 * PAT on the boot CPU. We have no way to undo PAT.
@@ -309,7 +306,7 @@ void pat_init(void)
 	u64 pat;
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
-	if (!__pat_enabled) {
+	if (!pat_enabled()) {
 		init_cache_modes();
 		return;
 	}
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 7e76a4d8304b..43b96f5f78ba 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -828,9 +828,11 @@ static void __init kexec_enter_virtual_mode(void)
 
 	/*
 	 * We don't do virtual mode, since we don't do runtime services, on
-	 * non-native EFI
+	 * non-native EFI. With efi=old_map, we don't do runtime services in
+	 * kexec kernel because in the initial boot something else might
+	 * have been mapped at these virtual addresses.
 	 */
-	if (!efi_is_native()) {
+	if (!efi_is_native() || efi_enabled(EFI_OLD_MEMMAP)) {
 		efi_memmap_unmap();
 		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 		return;
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index c488625c9712..eb8dff15a7f6 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -71,11 +71,13 @@ static void __init early_code_mapping_set_exec(int executable)
 
 pgd_t * __init efi_call_phys_prolog(void)
 {
-	unsigned long vaddress;
-	pgd_t *save_pgd;
+	unsigned long vaddr, addr_pgd, addr_p4d, addr_pud;
+	pgd_t *save_pgd, *pgd_k, *pgd_efi;
+	p4d_t *p4d, *p4d_k, *p4d_efi;
+	pud_t *pud;
 
 	int pgd;
-	int n_pgds;
+	int n_pgds, i, j;
 
 	if (!efi_enabled(EFI_OLD_MEMMAP)) {
 		save_pgd = (pgd_t *)read_cr3();
@@ -88,10 +90,49 @@ pgd_t * __init efi_call_phys_prolog(void)
 	n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE);
 	save_pgd = kmalloc_array(n_pgds, sizeof(*save_pgd), GFP_KERNEL);
 
+	/*
+	 * Build 1:1 identity mapping for efi=old_map usage. Note that
+	 * PAGE_OFFSET is PGDIR_SIZE aligned when KASLR is disabled, while
+	 * it is PUD_SIZE ALIGNED with KASLR enabled. So for a given physical
+	 * address X, the pud_index(X) != pud_index(__va(X)), we can only copy
+	 * PUD entry of __va(X) to fill in pud entry of X to build 1:1 mapping.
+	 * This means here we can only reuse the PMD tables of the direct mapping.
+	 */
 	for (pgd = 0; pgd < n_pgds; pgd++) {
-		save_pgd[pgd] = *pgd_offset_k(pgd * PGDIR_SIZE);
-		vaddress = (unsigned long)__va(pgd * PGDIR_SIZE);
-		set_pgd(pgd_offset_k(pgd * PGDIR_SIZE), *pgd_offset_k(vaddress));
+		addr_pgd = (unsigned long)(pgd * PGDIR_SIZE);
+		vaddr = (unsigned long)__va(pgd * PGDIR_SIZE);
+		pgd_efi = pgd_offset_k(addr_pgd);
+		save_pgd[pgd] = *pgd_efi;
+
+		p4d = p4d_alloc(&init_mm, pgd_efi, addr_pgd);
+		if (!p4d) {
+			pr_err("Failed to allocate p4d table!\n");
+			goto out;
+		}
+
+		for (i = 0; i < PTRS_PER_P4D; i++) {
+			addr_p4d = addr_pgd + i * P4D_SIZE;
+			p4d_efi = p4d + p4d_index(addr_p4d);
+
+			pud = pud_alloc(&init_mm, p4d_efi, addr_p4d);
+			if (!pud) {
+				pr_err("Failed to allocate pud table!\n");
+				goto out;
+			}
+
+			for (j = 0; j < PTRS_PER_PUD; j++) {
+				addr_pud = addr_p4d + j * PUD_SIZE;
+
+				if (addr_pud > (max_pfn << PAGE_SHIFT))
+					break;
+
+				vaddr = (unsigned long)__va(addr_pud);
+
+				pgd_k = pgd_offset_k(vaddr);
+				p4d_k = p4d_offset(pgd_k, vaddr);
+				pud[j] = *pud_offset(p4d_k, vaddr);
+			}
+		}
 	}
 out:
 	__flush_tlb_all();
@@ -104,8 +145,11 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
 	/*
 	 * After the lock is released, the original page table is restored.
 	 */
-	int pgd_idx;
+	int pgd_idx, i;
 	int nr_pgds;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
 
 	if (!efi_enabled(EFI_OLD_MEMMAP)) {
 		write_cr3((unsigned long)save_pgd);
@@ -115,9 +159,28 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
 
 	nr_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT) , PGDIR_SIZE);
 
-	for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++)
+	for (pgd_idx = 0; pgd_idx < nr_pgds; pgd_idx++) {
+		pgd = pgd_offset_k(pgd_idx * PGDIR_SIZE);
 		set_pgd(pgd_offset_k(pgd_idx * PGDIR_SIZE), save_pgd[pgd_idx]);
 
+		if (!(pgd_val(*pgd) & _PAGE_PRESENT))
+			continue;
+
+		for (i = 0; i < PTRS_PER_P4D; i++) {
+			p4d = p4d_offset(pgd,
+					 pgd_idx * PGDIR_SIZE + i * P4D_SIZE);
+
+			if (!(p4d_val(*p4d) & _PAGE_PRESENT))
+				continue;
+
+			pud = (pud_t *)p4d_page_vaddr(*p4d);
+			pud_free(&init_mm, pud);
+		}
+
+		p4d = (p4d_t *)pgd_page_vaddr(*pgd);
+		p4d_free(&init_mm, p4d);
+	}
+
 	kfree(save_pgd);
 
 	__flush_tlb_all();
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 26615991d69c..e0cf95a83f3f 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -360,6 +360,9 @@ void __init efi_free_boot_services(void)
 		free_bootmem_late(start, size);
 	}
 
+	if (!num_entries)
+		return;
+
 	new_size = efi.memmap.desc_size * num_entries;
 	new_phys = efi_memmap_alloc(num_entries);
 	if (!new_phys) {