20 files changed, 109 insertions, 225 deletions

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 483fb547e3c0..1d2b69fc0ceb 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -49,43 +49,59 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 #define test_cpu_cap(c, bit)						\
 	 test_bit(bit, (unsigned long *)((c)->x86_capability))
 
-#define REQUIRED_MASK_BIT_SET(bit)					\
-	 ( (((bit)>>5)==0  && (1UL<<((bit)&31) & REQUIRED_MASK0 )) ||	\
-	   (((bit)>>5)==1  && (1UL<<((bit)&31) & REQUIRED_MASK1 )) ||	\
-	   (((bit)>>5)==2  && (1UL<<((bit)&31) & REQUIRED_MASK2 )) ||	\
-	   (((bit)>>5)==3  && (1UL<<((bit)&31) & REQUIRED_MASK3 )) ||	\
-	   (((bit)>>5)==4  && (1UL<<((bit)&31) & REQUIRED_MASK4 )) ||	\
-	   (((bit)>>5)==5  && (1UL<<((bit)&31) & REQUIRED_MASK5 )) ||	\
-	   (((bit)>>5)==6  && (1UL<<((bit)&31) & REQUIRED_MASK6 )) ||	\
-	   (((bit)>>5)==7  && (1UL<<((bit)&31) & REQUIRED_MASK7 )) ||	\
-	   (((bit)>>5)==8  && (1UL<<((bit)&31) & REQUIRED_MASK8 )) ||	\
-	   (((bit)>>5)==9  && (1UL<<((bit)&31) & REQUIRED_MASK9 )) ||	\
-	   (((bit)>>5)==10 && (1UL<<((bit)&31) & REQUIRED_MASK10)) ||	\
-	   (((bit)>>5)==11 && (1UL<<((bit)&31) & REQUIRED_MASK11)) ||	\
-	   (((bit)>>5)==12 && (1UL<<((bit)&31) & REQUIRED_MASK12)) ||	\
-	   (((bit)>>5)==13 && (1UL<<((bit)&31) & REQUIRED_MASK13)) ||	\
-	   (((bit)>>5)==14 && (1UL<<((bit)&31) & REQUIRED_MASK14)) ||	\
-	   (((bit)>>5)==15 && (1UL<<((bit)&31) & REQUIRED_MASK15)) ||	\
-	   (((bit)>>5)==16 && (1UL<<((bit)&31) & REQUIRED_MASK16)) )
-
-#define DISABLED_MASK_BIT_SET(bit)					\
-	 ( (((bit)>>5)==0  && (1UL<<((bit)&31) & DISABLED_MASK0 )) ||	\
-	   (((bit)>>5)==1  && (1UL<<((bit)&31) & DISABLED_MASK1 )) ||	\
-	   (((bit)>>5)==2  && (1UL<<((bit)&31) & DISABLED_MASK2 )) ||	\
-	   (((bit)>>5)==3  && (1UL<<((bit)&31) & DISABLED_MASK3 )) ||	\
-	   (((bit)>>5)==4  && (1UL<<((bit)&31) & DISABLED_MASK4 )) ||	\
-	   (((bit)>>5)==5  && (1UL<<((bit)&31) & DISABLED_MASK5 )) ||	\
-	   (((bit)>>5)==6  && (1UL<<((bit)&31) & DISABLED_MASK6 )) ||	\
-	   (((bit)>>5)==7  && (1UL<<((bit)&31) & DISABLED_MASK7 )) ||	\
-	   (((bit)>>5)==8  && (1UL<<((bit)&31) & DISABLED_MASK8 )) ||	\
-	   (((bit)>>5)==9  && (1UL<<((bit)&31) & DISABLED_MASK9 )) ||	\
-	   (((bit)>>5)==10 && (1UL<<((bit)&31) & DISABLED_MASK10)) ||	\
-	   (((bit)>>5)==11 && (1UL<<((bit)&31) & DISABLED_MASK11)) ||	\
-	   (((bit)>>5)==12 && (1UL<<((bit)&31) & DISABLED_MASK12)) ||	\
-	   (((bit)>>5)==13 && (1UL<<((bit)&31) & DISABLED_MASK13)) ||	\
-	   (((bit)>>5)==14 && (1UL<<((bit)&31) & DISABLED_MASK14)) ||	\
-	   (((bit)>>5)==15 && (1UL<<((bit)&31) & DISABLED_MASK15)) ||	\
-	   (((bit)>>5)==16 && (1UL<<((bit)&31) & DISABLED_MASK16)) )
+/*
+ * There are 32 bits/features in each mask word.  The high bits
+ * (selected with (bit>>5) give us the word number and the low 5
+ * bits give us the bit/feature number inside the word.
+ * (1UL<<((bit)&31) gives us a mask for the feature_bit so we can
+ * see if it is set in the mask word.
+ */
+#define CHECK_BIT_IN_MASK_WORD(maskname, word, bit)	\
+	(((bit)>>5)==(word) && (1UL<<((bit)&31) & maskname##word ))
+
+#define REQUIRED_MASK_BIT_SET(feature_bit)		\
+	 ( CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  0, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  1, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  2, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  3, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  4, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  5, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  6, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  7, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  8, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK,  9, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 10, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 11, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 12, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 13, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 14, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 15, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 16, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) ||	\
+	   REQUIRED_MASK_CHECK					  ||	\
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
+
+#define DISABLED_MASK_BIT_SET(feature_bit)				\
+	 ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  0, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  1, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  2, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  3, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  4, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  5, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  6, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  7, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  8, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  9, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 10, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 11, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 12, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 13, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 14, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 15, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 16, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) ||	\
+	   DISABLED_MASK_CHECK					  ||	\
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
 
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index c64b1e9c5d1a..92a8308b96f6 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -225,7 +225,6 @@
 #define X86_FEATURE_RDSEED	( 9*32+18) /* The RDSEED instruction */
 #define X86_FEATURE_ADX		( 9*32+19) /* The ADCX and ADOX instructions */
 #define X86_FEATURE_SMAP	( 9*32+20) /* Supervisor Mode Access Prevention */
-#define X86_FEATURE_PCOMMIT	( 9*32+22) /* PCOMMIT instruction */
 #define X86_FEATURE_CLFLUSHOPT	( 9*32+23) /* CLFLUSHOPT instruction */
 #define X86_FEATURE_CLWB	( 9*32+24) /* CLWB instruction */
 #define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
@@ -310,5 +309,5 @@
 #endif
 #define X86_BUG_NULL_SEG	X86_BUG(10) /* Nulling a selector preserves the base */
 #define X86_BUG_SWAPGS_FENCE	X86_BUG(11) /* SWAPGS without input dep on GS */
-
+#define X86_BUG_MONITOR		X86_BUG(12) /* IPI required to wake up remote CPU */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 911e9358ceb1..85599ad4d024 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -56,5 +56,7 @@
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
 #define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE)
+#define DISABLED_MASK17	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 6999f7d01a0d..627719475457 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -8,7 +8,7 @@
  * "Extreme" ones, like Broadwell-E.
  *
  * Things ending in "2" are usually because we have no better
- * name for them.  There's no processor called "WESTMERE2".
+ * name for them.  There's no processor called "SILVERMONT2".
  */
 
 #define INTEL_FAM6_CORE_YONAH		0x0E
@@ -18,10 +18,10 @@
 #define INTEL_FAM6_CORE2_DUNNINGTON	0x1D
 
 #define INTEL_FAM6_NEHALEM		0x1E
+#define INTEL_FAM6_NEHALEM_G		0x1F /* Auburndale / Havendale */
 #define INTEL_FAM6_NEHALEM_EP		0x1A
 #define INTEL_FAM6_NEHALEM_EX		0x2E
 #define INTEL_FAM6_WESTMERE		0x25
-#define INTEL_FAM6_WESTMERE2		0x1F
 #define INTEL_FAM6_WESTMERE_EP		0x2C
 #define INTEL_FAM6_WESTMERE_EX		0x2F
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 69e62862b622..33ae3a4d0159 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -35,8 +35,9 @@
 #include <asm/asm.h>
 #include <asm/kvm_page_track.h>
 
-#define KVM_MAX_VCPUS 255
-#define KVM_SOFT_MAX_VCPUS 160
+#define KVM_MAX_VCPUS 288
+#define KVM_SOFT_MAX_VCPUS 240
+#define KVM_MAX_VCPU_ID 1023
 #define KVM_USER_MEM_SLOTS 509
 /* memory slots that are not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 3
@@ -599,6 +600,7 @@ struct kvm_vcpu_arch {
 	u64 mcg_cap;
 	u64 mcg_status;
 	u64 mcg_ctl;
+	u64 mcg_ext_ctl;
 	u64 *mce_banks;
 
 	/* Cache MMIO info */
@@ -682,9 +684,12 @@ struct kvm_arch_memory_slot {
 struct kvm_apic_map {
 	struct rcu_head rcu;
 	u8 mode;
-	struct kvm_lapic *phys_map[256];
-	/* first index is cluster id second is cpu id in a cluster */
-	struct kvm_lapic *logical_map[16][16];
+	u32 max_apic_id;
+	union {
+		struct kvm_lapic *xapic_flat_map[8];
+		struct kvm_lapic *xapic_cluster_map[16][4];
+	};
+	struct kvm_lapic *phys_map[];
 };
 
 /* Hyper-V emulation context */
@@ -779,6 +784,9 @@ struct kvm_arch {
 	u32 ldr_mode;
 	struct page *avic_logical_id_table_page;
 	struct page *avic_physical_id_table_page;
+
+	bool x2apic_format;
+	bool x2apic_broadcast_quirk_disabled;
 };
 
 struct kvm_vm_stat {
@@ -1006,6 +1014,11 @@ struct kvm_x86_ops {
 	int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq,
 			      uint32_t guest_irq, bool set);
 	void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
+
+	int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc);
+	void (*cancel_hv_timer)(struct kvm_vcpu *vcpu);
+
+	void (*setup_mce)(struct kvm_vcpu *vcpu);
 };
 
 struct kvm_arch_async_pf {
@@ -1026,7 +1039,7 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu);
 void kvm_mmu_init_vm(struct kvm *kvm);
 void kvm_mmu_uninit_vm(struct kvm *kvm);
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
-		u64 dirty_mask, u64 nx_mask, u64 x_mask);
+		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask);
 
 void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
@@ -1077,6 +1090,10 @@ extern u32  kvm_max_guest_tsc_khz;
 extern u8   kvm_tsc_scaling_ratio_frac_bits;
 /* maximum allowed value of TSC scaling ratio */
 extern u64  kvm_max_tsc_scaling_ratio;
+/* 1ull << kvm_tsc_scaling_ratio_frac_bits */
+extern u64  kvm_default_tsc_scaling_ratio;
+
+extern u64 kvm_mce_cap_supported;
 
 enum emulation_result {
 	EMULATE_DONE,         /* no further processing */
@@ -1352,7 +1369,7 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
 bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq,
 			     struct kvm_vcpu **dest_vcpu);
 
-void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
+void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
 		     struct kvm_lapic_irq *irq);
 
 static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h
index a7f9181f63f3..ed80003ce3e2 100644
--- a/arch/x86/include/asm/livepatch.h
+++ b/arch/x86/include/asm/livepatch.h
@@ -22,7 +22,6 @@
 #define _ASM_X86_LIVEPATCH_H
 
 #include <asm/setup.h>
-#include <linux/module.h>
 #include <linux/ftrace.h>
 
 static inline int klp_check_compiler_support(void)
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 9d3a96c4da78..da0d81fa0b54 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -133,40 +133,14 @@ static inline unsigned int x86_cpuid_family(void)
 #ifdef CONFIG_MICROCODE
 extern void __init load_ucode_bsp(void);
 extern void load_ucode_ap(void);
-extern int __init save_microcode_in_initrd(void);
 void reload_early_microcode(void);
 extern bool get_builtin_firmware(struct cpio_data *cd, const char *name);
 #else
 static inline void __init load_ucode_bsp(void)			{ }
 static inline void load_ucode_ap(void)				{ }
-static inline int __init save_microcode_in_initrd(void)		{ return 0; }
 static inline void reload_early_microcode(void)			{ }
 static inline bool
 get_builtin_firmware(struct cpio_data *cd, const char *name)	{ return false; }
 #endif
 
-static inline unsigned long get_initrd_start(void)
-{
-#ifdef CONFIG_BLK_DEV_INITRD
-	return initrd_start;
-#else
-	return 0;
-#endif
-}
-
-static inline unsigned long get_initrd_start_addr(void)
-{
-#ifdef CONFIG_BLK_DEV_INITRD
-#ifdef CONFIG_X86_32
-	unsigned long *initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start);
-
-	return (unsigned long)__pa_nodebug(*initrd_start_p);
-#else
-	return get_initrd_start();
-#endif
-#else /* CONFIG_BLK_DEV_INITRD */
-	return 0;
-#endif
-}
-
 #endif /* _ASM_X86_MICROCODE_H */
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index adfc847a395e..15eb75484cc0 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -62,7 +62,6 @@ extern int apply_microcode_amd(int cpu);
 extern enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size);
 
 #define PATCH_MAX_SIZE PAGE_SIZE
-extern u8 amd_ucode_patch[PATCH_MAX_SIZE];
 
 #ifdef CONFIG_MICROCODE_AMD
 extern void __init load_ucode_amd_bsp(unsigned int family);
diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h
index 603417f8dd6c..5e69154c9f07 100644
--- a/arch/x86/include/asm/microcode_intel.h
+++ b/arch/x86/include/asm/microcode_intel.h
@@ -70,9 +70,4 @@ static inline int __init save_microcode_in_initrd_intel(void) { return -EINVAL;
 static inline void reload_ucode_intel(void) {}
 #endif
 
-#ifdef CONFIG_HOTPLUG_CPU
-extern int save_mc_for_early(u8 *mc);
-#else
-static inline int save_mc_for_early(u8 *mc) { return 0; }
-#endif
 #endif /* _ASM_X86_MICROCODE_INTEL_H */
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index 0deeb2d26df7..f37f2d8a2989 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -97,7 +97,7 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
  */
 static inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
 {
-	if (!current_set_polling_and_test()) {
+	if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) {
 		if (static_cpu_has_bug(X86_BUG_CLFLUSH_MONITOR)) {
 			mb();
 			clflush((void *)&current_thread_info()->flags);
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index 3a52ee0e726d..3bae4969ac65 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -13,7 +13,8 @@
  * If you want more physical memory than this then see the CONFIG_HIGHMEM4G
  * and CONFIG_HIGHMEM64G options in the kernel configuration.
  */
-#define __PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
+#define __PAGE_OFFSET_BASE	_AC(CONFIG_PAGE_OFFSET, UL)
+#define __PAGE_OFFSET		__PAGE_OFFSET_BASE
 
 #define __START_KERNEL_map	__PAGE_OFFSET
 
diff --git a/arch/x86/include/asm/pmem.h b/arch/x86/include/asm/pmem.h
index fbc5e92e1ecc..643eba42d620 100644
--- a/arch/x86/include/asm/pmem.h
+++ b/arch/x86/include/asm/pmem.h
@@ -26,13 +26,11 @@
  * @n: length of the copy in bytes
  *
  * Copy data to persistent memory media via non-temporal stores so that
- * a subsequent arch_wmb_pmem() can flush cpu and memory controller
- * write buffers to guarantee durability.
+ * a subsequent pmem driver flush operation will drain posted write queues.
  */
-static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
-		size_t n)
+static inline void arch_memcpy_to_pmem(void *dst, const void *src, size_t n)
 {
-	int unwritten;
+	int rem;
 
 	/*
 	 * We are copying between two kernel buffers, if
@@ -40,59 +38,36 @@ static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src,
 	 * fault) we would have already reported a general protection fault
 	 * before the WARN+BUG.
 	 */
-	unwritten = __copy_from_user_inatomic_nocache((void __force *) dst,
-			(void __user *) src, n);
-	if (WARN(unwritten, "%s: fault copying %p <- %p unwritten: %d\n",
-				__func__, dst, src, unwritten))
+	rem = __copy_from_user_inatomic_nocache(dst, (void __user *) src, n);
+	if (WARN(rem, "%s: fault copying %p <- %p unwritten: %d\n",
+				__func__, dst, src, rem))
 		BUG();
 }
 
-static inline int arch_memcpy_from_pmem(void *dst, const void __pmem *src,
-		size_t n)
+static inline int arch_memcpy_from_pmem(void *dst, const void *src, size_t n)
 {
 	if (static_cpu_has(X86_FEATURE_MCE_RECOVERY))
-		return memcpy_mcsafe(dst, (void __force *) src, n);
-	memcpy(dst, (void __force *) src, n);
+		return memcpy_mcsafe(dst, src, n);
+	memcpy(dst, src, n);
 	return 0;
 }
 
 /**
- * arch_wmb_pmem - synchronize writes to persistent memory
- *
- * After a series of arch_memcpy_to_pmem() operations this drains data
- * from cpu write buffers and any platform (memory controller) buffers
- * to ensure that written data is durable on persistent memory media.
- */
-static inline void arch_wmb_pmem(void)
-{
-	/*
-	 * wmb() to 'sfence' all previous writes such that they are
-	 * architecturally visible to 'pcommit'.  Note, that we've
-	 * already arranged for pmem writes to avoid the cache via
-	 * arch_memcpy_to_pmem().
-	 */
-	wmb();
-	pcommit_sfence();
-}
-
-/**
  * arch_wb_cache_pmem - write back a cache range with CLWB
  * @vaddr:	virtual start address
  * @size:	number of bytes to write back
  *
  * Write back a cache range using the CLWB (cache line write back)
- * instruction.  This function requires explicit ordering with an
- * arch_wmb_pmem() call.
+ * instruction.
  */
-static inline void arch_wb_cache_pmem(void __pmem *addr, size_t size)
+static inline void arch_wb_cache_pmem(void *addr, size_t size)
 {
 	u16 x86_clflush_size = boot_cpu_data.x86_clflush_size;
 	unsigned long clflush_mask = x86_clflush_size - 1;
-	void *vaddr = (void __force *)addr;
-	void *vend = vaddr + size;
+	void *vend = addr + size;
 	void *p;
 
-	for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
+	for (p = (void *)((unsigned long)addr & ~clflush_mask);
 	     p < vend; p += x86_clflush_size)
 		clwb(p);
 }
@@ -113,16 +88,14 @@ static inline bool __iter_needs_pmem_wb(struct iov_iter *i)
  * @i:		iterator with source data
  *
  * Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'.
- * This function requires explicit ordering with an arch_wmb_pmem() call.
  */
-static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
+static inline size_t arch_copy_from_iter_pmem(void *addr, size_t bytes,
 		struct iov_iter *i)
 {
-	void *vaddr = (void __force *)addr;
 	size_t len;
 
 	/* TODO: skip the write-back by always using non-temporal stores */
-	len = copy_from_iter_nocache(vaddr, bytes, i);
+	len = copy_from_iter_nocache(addr, bytes, i);
 
 	if (__iter_needs_pmem_wb(i))
 		arch_wb_cache_pmem(addr, bytes);
@@ -136,28 +109,16 @@ static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes,
  * @size:	number of bytes to zero
  *
  * Write zeros into the memory range starting at 'addr' for 'size' bytes.
- * This function requires explicit ordering with an arch_wmb_pmem() call.
  */
-static inline void arch_clear_pmem(void __pmem *addr, size_t size)
+static inline void arch_clear_pmem(void *addr, size_t size)
 {
-	void *vaddr = (void __force *)addr;
-
-	memset(vaddr, 0, size);
+	memset(addr, 0, size);
 	arch_wb_cache_pmem(addr, size);
 }
 
-static inline void arch_invalidate_pmem(void __pmem *addr, size_t size)
+static inline void arch_invalidate_pmem(void *addr, size_t size)
 {
-	clflush_cache_range((void __force *) addr, size);
-}
-
-static inline bool __arch_has_wmb_pmem(void)
-{
-	/*
-	 * We require that wmb() be an 'sfence', that is only guaranteed on
-	 * 64-bit builds
-	 */
-	return static_cpu_has(X86_FEATURE_PCOMMIT);
+	clflush_cache_range(addr, size);
 }
 #endif /* CONFIG_ARCH_HAS_PMEM_API */
 #endif /* __ASM_X86_PMEM_H__ */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 6271281f947d..2b5d686ea9f3 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -83,12 +83,6 @@ extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
 			 int error_code, int si_code);
 
 
-extern unsigned long syscall_trace_enter_phase1(struct pt_regs *, u32 arch);
-extern long syscall_trace_enter_phase2(struct pt_regs *, u32 arch,
-				       unsigned long phase1_result);
-
-extern long syscall_trace_enter(struct pt_regs *);
-
 static inline unsigned long regs_return_value(struct pt_regs *regs)
 {
 	return regs->ax;
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index 4916144e3c42..fac9a5c0abe9 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -99,5 +99,7 @@
 #define REQUIRED_MASK14	0
 #define REQUIRED_MASK15	0
 #define REQUIRED_MASK16	0
+#define REQUIRED_MASK17	0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index d96d04377765..587d7914ea4b 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -253,52 +253,6 @@ static inline void clwb(volatile void *__p)
 		: [pax] "a" (p));
 }
 
-/**
- * pcommit_sfence() - persistent commit and fence
- *
- * The PCOMMIT instruction ensures that data that has been flushed from the
- * processor's cache hierarchy with CLWB, CLFLUSHOPT or CLFLUSH is accepted to
- * memory and is durable on the DIMM.  The primary use case for this is
- * persistent memory.
- *
- * This function shows how to properly use CLWB/CLFLUSHOPT/CLFLUSH and PCOMMIT
- * with appropriate fencing.
- *
- * Example:
- * void flush_and_commit_buffer(void *vaddr, unsigned int size)
- * {
- *         unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1;
- *         void *vend = vaddr + size;
- *         void *p;
- *
- *         for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
- *              p < vend; p += boot_cpu_data.x86_clflush_size)
- *                 clwb(p);
- *
- *         // SFENCE to order CLWB/CLFLUSHOPT/CLFLUSH cache flushes
- *         // MFENCE via mb() also works
- *         wmb();
- *
- *         // PCOMMIT and the required SFENCE for ordering
- *         pcommit_sfence();
- * }
- *
- * After this function completes the data pointed to by 'vaddr' has been
- * accepted to memory and will be durable if the 'vaddr' points to persistent
- * memory.
- *
- * PCOMMIT must always be ordered by an MFENCE or SFENCE, so to help simplify
- * things we include both the PCOMMIT and the required SFENCE in the
- * alternatives generated by pcommit_sfence().
- */
-static inline void pcommit_sfence(void)
-{
-	alternative(ASM_NOP7,
-		    ".byte 0x66, 0x0f, 0xae, 0xf8\n\t" /* pcommit */
-		    "sfence",
-		    X86_FEATURE_PCOMMIT);
-}
-
 #define nop() asm volatile ("nop")
 
 
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index d0fe23ec7e98..14824fc78f7e 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -193,7 +193,6 @@ struct __attribute__ ((__packed__)) vmcb {
 	struct vmcb_save_area save;
 };
 
-#define SVM_CPUID_FEATURE_SHIFT 2
 #define SVM_CPUID_FUNC 0x8000000a
 
 #define SVM_VM_CR_SVM_DISABLE 4
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 89bff044a6f5..b45ffdda3549 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -219,32 +219,8 @@ static inline unsigned long current_stack_pointer(void)
  * have to worry about atomic accesses.
  */
 #define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
-#define TS_RESTORE_SIGMASK	0x0008	/* restore signal mask in do_signal() */
 
 #ifndef __ASSEMBLY__
-#define HAVE_SET_RESTORE_SIGMASK	1
-static inline void set_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	ti->status |= TS_RESTORE_SIGMASK;
-	WARN_ON(!test_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags));
-}
-static inline void clear_restore_sigmask(void)
-{
-	current_thread_info()->status &= ~TS_RESTORE_SIGMASK;
-}
-static inline bool test_restore_sigmask(void)
-{
-	return current_thread_info()->status & TS_RESTORE_SIGMASK;
-}
-static inline bool test_and_clear_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	if (!(ti->status & TS_RESTORE_SIGMASK))
-		return false;
-	ti->status &= ~TS_RESTORE_SIGMASK;
-	return true;
-}
 
 static inline bool in_ia32_syscall(void)
 {
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 43e87a3dd95c..cf75871d2f81 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -36,6 +36,7 @@
 #include <linux/cpumask.h>
 
 #include <asm/mpspec.h>
+#include <asm/percpu.h>
 
 /* Mappings between logical cpu number and node number */
 DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index cce9ee68e335..0116b2ee9e64 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -83,23 +83,19 @@ static inline void cpu_emergency_vmxoff(void)
  */
 static inline int cpu_has_svm(const char **msg)
 {
-	uint32_t eax, ebx, ecx, edx;
-
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) {
 		if (msg)
 			*msg = "not amd";
 		return 0;
 	}
 
-	cpuid(0x80000000, &eax, &ebx, &ecx, &edx);
-	if (eax < SVM_CPUID_FUNC) {
+	if (boot_cpu_data.extended_cpuid_level < SVM_CPUID_FUNC) {
 		if (msg)
 			*msg = "can't execute cpuid_8000000a";
 		return 0;
 	}
 
-	cpuid(0x80000001, &eax, &ebx, &ecx, &edx);
-	if (!(ecx & (1 << SVM_CPUID_FEATURE_SHIFT))) {
+	if (!boot_cpu_has(X86_FEATURE_SVM)) {
 		if (msg)
 			*msg = "svm not available";
 		return 0;
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 14c63c7e8337..a002b07a7099 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -72,7 +72,6 @@
 #define SECONDARY_EXEC_SHADOW_VMCS              0x00004000
 #define SECONDARY_EXEC_ENABLE_PML               0x00020000
 #define SECONDARY_EXEC_XSAVES			0x00100000
-#define SECONDARY_EXEC_PCOMMIT			0x00200000
 #define SECONDARY_EXEC_TSC_SCALING              0x02000000
 
 #define PIN_BASED_EXT_INTR_MASK                 0x00000001