Merge branch master from git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git

Pick up the spectre documentation so the Grand Schemozzle can be added.

37 files changed, 184 insertions, 498 deletions

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 050e5f9ebf81..e647aa095867 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -49,7 +49,7 @@ static inline void generic_apic_probe(void)
 
 #ifdef CONFIG_X86_LOCAL_APIC
 
-extern unsigned int apic_verbosity;
+extern int apic_verbosity;
 extern int local_apic_timer_c2_ok;
 
 extern int disable_apic;
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 8e790ec219a5..ba15d53c1ca7 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -49,23 +49,8 @@
 #define CONST_MASK_ADDR(nr, addr)	WBYTE_ADDR((void *)(addr) + ((nr)>>3))
 #define CONST_MASK(nr)			(1 << ((nr) & 7))
 
-/**
- * set_bit - Atomically set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * This function is atomic and may not be reordered.  See __set_bit()
- * if you do not require the atomic guarantees.
- *
- * Note: there are no guarantees that this function will not be reordered
- * on non x86 architectures, so if you are writing portable code,
- * make sure not to rely on its reordering guarantees.
- *
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
 static __always_inline void
-set_bit(long nr, volatile unsigned long *addr)
+arch_set_bit(long nr, volatile unsigned long *addr)
 {
 	if (IS_IMMEDIATE(nr)) {
 		asm volatile(LOCK_PREFIX "orb %1,%0"
@@ -78,32 +63,14 @@ set_bit(long nr, volatile unsigned long *addr)
 	}
 }
 
-/**
- * __set_bit - Set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * Unlike set_bit(), this function is non-atomic and may be reordered.
- * If it's called on the same region of memory simultaneously, the effect
- * may be that only one operation succeeds.
- */
-static __always_inline void __set_bit(long nr, volatile unsigned long *addr)
+static __always_inline void
+arch___set_bit(long nr, volatile unsigned long *addr)
 {
 	asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
 }
 
-/**
- * clear_bit - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and may not be reordered.  However, it does
- * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
- * in order to ensure changes are visible on other processors.
- */
 static __always_inline void
-clear_bit(long nr, volatile unsigned long *addr)
+arch_clear_bit(long nr, volatile unsigned long *addr)
 {
 	if (IS_IMMEDIATE(nr)) {
 		asm volatile(LOCK_PREFIX "andb %1,%0"
@@ -115,26 +82,21 @@ clear_bit(long nr, volatile unsigned long *addr)
 	}
 }
 
-/*
- * clear_bit_unlock - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and implies release semantics before the memory
- * operation. It can be used for an unlock.
- */
-static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *addr)
+static __always_inline void
+arch_clear_bit_unlock(long nr, volatile unsigned long *addr)
 {
 	barrier();
-	clear_bit(nr, addr);
+	arch_clear_bit(nr, addr);
 }
 
-static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline void
+arch___clear_bit(long nr, volatile unsigned long *addr)
 {
 	asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
 }
 
-static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
+static __always_inline bool
+arch_clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
 {
 	bool negative;
 	asm volatile(LOCK_PREFIX "andb %2,%1"
@@ -143,48 +105,23 @@ static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile
 		: "ir" ((char) ~(1 << nr)) : "memory");
 	return negative;
 }
+#define arch_clear_bit_unlock_is_negative_byte                                 \
+	arch_clear_bit_unlock_is_negative_byte
 
-// Let everybody know we have it
-#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
-
-/*
- * __clear_bit_unlock - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * __clear_bit() is non-atomic and implies release semantics before the memory
- * operation. It can be used for an unlock if no other CPUs can concurrently
- * modify other bits in the word.
- */
-static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
+static __always_inline void
+arch___clear_bit_unlock(long nr, volatile unsigned long *addr)
 {
-	__clear_bit(nr, addr);
+	arch___clear_bit(nr, addr);
 }
 
-/**
- * __change_bit - Toggle a bit in memory
- * @nr: the bit to change
- * @addr: the address to start counting from
- *
- * Unlike change_bit(), this function is non-atomic and may be reordered.
- * If it's called on the same region of memory simultaneously, the effect
- * may be that only one operation succeeds.
- */
-static __always_inline void __change_bit(long nr, volatile unsigned long *addr)
+static __always_inline void
+arch___change_bit(long nr, volatile unsigned long *addr)
 {
 	asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
 }
 
-/**
- * change_bit - Toggle a bit in memory
- * @nr: Bit to change
- * @addr: Address to start counting from
- *
- * change_bit() is atomic and may not be reordered.
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static __always_inline void change_bit(long nr, volatile unsigned long *addr)
+static __always_inline void
+arch_change_bit(long nr, volatile unsigned long *addr)
 {
 	if (IS_IMMEDIATE(nr)) {
 		asm volatile(LOCK_PREFIX "xorb %1,%0"
@@ -196,42 +133,20 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr)
 	}
 }
 
-/**
- * test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool
+arch_test_and_set_bit(long nr, volatile unsigned long *addr)
 {
 	return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), *addr, c, "Ir", nr);
 }
 
-/**
- * test_and_set_bit_lock - Set a bit and return its old value for lock
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This is the same as test_and_set_bit on x86.
- */
 static __always_inline bool
-test_and_set_bit_lock(long nr, volatile unsigned long *addr)
+arch_test_and_set_bit_lock(long nr, volatile unsigned long *addr)
 {
-	return test_and_set_bit(nr, addr);
+	return arch_test_and_set_bit(nr, addr);
 }
 
-/**
- * __test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail.  You must protect multiple accesses with a lock.
- */
-static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool
+arch___test_and_set_bit(long nr, volatile unsigned long *addr)
 {
 	bool oldbit;
 
@@ -242,28 +157,13 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *
 	return oldbit;
 }
 
-/**
- * test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool
+arch_test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
 	return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), *addr, c, "Ir", nr);
 }
 
-/**
- * __test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail.  You must protect multiple accesses with a lock.
- *
+/*
  * Note: the operation is performed atomically with respect to
  * the local CPU, but not other CPUs. Portable code should not
  * rely on this behaviour.
@@ -271,7 +171,8 @@ static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *
  * accessed from a hypervisor on the same CPU if running in a VM: don't change
  * this without also updating arch/x86/kernel/kvm.c
  */
-static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool
+arch___test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
 	bool oldbit;
 
@@ -282,8 +183,8 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long
 	return oldbit;
 }
 
-/* WARNING: non atomic and it can be reordered! */
-static __always_inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool
+arch___test_and_change_bit(long nr, volatile unsigned long *addr)
 {
 	bool oldbit;
 
@@ -295,15 +196,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon
 	return oldbit;
 }
 
-/**
- * test_and_change_bit - Change a bit and return its old value
- * @nr: Bit to change
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool
+arch_test_and_change_bit(long nr, volatile unsigned long *addr)
 {
 	return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr);
 }
@@ -326,16 +220,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l
 	return oldbit;
 }
 
-#if 0 /* Fool kernel-doc since it doesn't do macros yet */
-/**
- * test_bit - Determine whether a bit is set
- * @nr: bit number to test
- * @addr: Address to start counting from
- */
-static bool test_bit(int nr, const volatile unsigned long *addr);
-#endif
-
-#define test_bit(nr, addr)			\
+#define arch_test_bit(nr, addr)			\
 	(__builtin_constant_p((nr))		\
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
@@ -504,6 +389,8 @@ static __always_inline int fls64(__u64 x)
 
 #include <asm-generic/bitops/const_hweight.h>
 
+#include <asm-generic/bitops-instrumented.h>
+
 #include <asm-generic/bitops/le.h>
 
 #include <asm-generic/bitops/ext2-atomic-setbit.h>
diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h
index f6f6ef436599..101eb944f13c 100644
--- a/arch/x86/include/asm/bootparam_utils.h
+++ b/arch/x86/include/asm/bootparam_utils.h
@@ -24,7 +24,7 @@ static void sanitize_boot_params(struct boot_params *boot_params)
 	 * IMPORTANT NOTE TO BOOTLOADER AUTHORS: do not simply clear
 	 * this field.  The purpose of this field is to guarantee
 	 * compliance with the x86 boot spec located in
-	 * Documentation/x86/boot.txt .  That spec says that the
+	 * Documentation/x86/boot.rst .  That spec says that the
 	 * *whole* structure should be cleared, after which only the
 	 * portion defined by struct setup_header (boot_params->hdr)
 	 * should be copied in.
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index 50a30f6c668b..e41cbf2ec41d 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -53,8 +53,20 @@ struct hypervisor_x86 {
 
 	/* runtime callbacks */
 	struct x86_hyper_runtime runtime;
+
+	/* ignore nopv parameter */
+	bool ignore_nopv;
 };
 
+extern const struct hypervisor_x86 x86_hyper_vmware;
+extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
+extern const struct hypervisor_x86 x86_hyper_xen_pv;
+extern const struct hypervisor_x86 x86_hyper_kvm;
+extern const struct hypervisor_x86 x86_hyper_jailhouse;
+extern const struct hypervisor_x86 x86_hyper_acrn;
+extern struct hypervisor_x86 x86_hyper_xen_hvm;
+
+extern bool nopv;
 extern enum x86_hypervisor_type x86_hyper_type;
 extern void init_hypervisor_platform(void);
 static inline bool hypervisor_is_type(enum x86_hypervisor_type type)
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index a06a9f8294ea..6bed97ff6db2 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -165,7 +165,6 @@ static inline unsigned int isa_virt_to_bus(volatile void *address)
 {
 	return (unsigned int)virt_to_phys(address);
 }
-#define isa_page_to_bus(page)	((unsigned int)page_to_phys(page))
 #define isa_bus_to_virt		phys_to_virt
 
 /*
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 26d1eb83f72a..7b0a4ee77313 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -607,15 +607,16 @@ struct kvm_vcpu_arch {
 
 	/*
 	 * QEMU userspace and the guest each have their own FPU state.
-	 * In vcpu_run, we switch between the user, maintained in the
-	 * task_struct struct, and guest FPU contexts. While running a VCPU,
-	 * the VCPU thread will have the guest FPU context.
+	 * In vcpu_run, we switch between the user and guest FPU contexts.
+	 * While running a VCPU, the VCPU thread will have the guest FPU
+	 * context.
 	 *
 	 * Note that while the PKRU state lives inside the fpu registers,
 	 * it is switched out separately at VMENTER and VMEXIT time. The
 	 * "guest_fpu" state here contains the guest FPU context, with the
 	 * host PRKU bits.
 	 */
+	struct fpu *user_fpu;
 	struct fpu *guest_fpu;
 
 	u64 xcr0;
@@ -686,6 +687,7 @@ struct kvm_vcpu_arch {
 	u32 virtual_tsc_mult;
 	u32 virtual_tsc_khz;
 	s64 ia32_tsc_adjust_msr;
+	u64 msr_ia32_power_ctl;
 	u64 tsc_scaling_ratio;
 
 	atomic_t nmi_queued;  /* unprocessed asynchronous NMIs */
@@ -752,6 +754,8 @@ struct kvm_vcpu_arch {
 		struct gfn_to_hva_cache data;
 	} pv_eoi;
 
+	u64 msr_kvm_poll_control;
+
 	/*
 	 * Indicate whether the access faults on its page table in guest
 	 * which is set when fix page fault and used to detect unhandeable
@@ -879,6 +883,7 @@ struct kvm_arch {
 	bool mwait_in_guest;
 	bool hlt_in_guest;
 	bool pause_in_guest;
+	bool cstate_in_guest;
 
 	unsigned long irq_sources_bitmap;
 	s64 kvmclock_offset;
@@ -926,6 +931,8 @@ struct kvm_arch {
 
 	bool guest_can_read_msr_platform_info;
 	bool exception_payload_enabled;
+
+	struct kvm_pmu_event_filter *pmu_event_filter;
 };
 
 struct kvm_vm_stat {
@@ -996,7 +1003,7 @@ struct kvm_x86_ops {
 	int (*disabled_by_bios)(void);             /* __init */
 	int (*hardware_enable)(void);
 	void (*hardware_disable)(void);
-	void (*check_processor_compatibility)(void *rtn);
+	int (*check_processor_compatibility)(void);/* __init */
 	int (*hardware_setup)(void);               /* __init */
 	void (*hardware_unsetup)(void);            /* __exit */
 	bool (*cpu_has_accelerated_tpr)(void);
@@ -1110,7 +1117,7 @@ struct kvm_x86_ops {
 	int (*check_intercept)(struct kvm_vcpu *vcpu,
 			       struct x86_instruction_info *info,
 			       enum x86_intercept_stage stage);
-	void (*handle_external_intr)(struct kvm_vcpu *vcpu);
+	void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu);
 	bool (*mpx_supported)(void);
 	bool (*xsaves_supported)(void);
 	bool (*umip_emulated)(void);
@@ -1490,25 +1497,29 @@ enum {
 #define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
 #define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
 
+asmlinkage void __noreturn kvm_spurious_fault(void);
+
 /*
  * Hardware virtualization extension instructions may fault if a
  * reboot turns off virtualization while processes are running.
- * Trap the fault and ignore the instruction if that happens.
+ * Usually after catching the fault we just panic; during reboot
+ * instead the instruction is ignored.
  */
-asmlinkage void kvm_spurious_fault(void);
-
-#define ____kvm_handle_fault_on_reboot(insn, cleanup_insn)	\
-	"666: " insn "\n\t" \
-	"668: \n\t"                           \
-	".pushsection .fixup, \"ax\" \n" \
-	"667: \n\t" \
-	cleanup_insn "\n\t"		      \
-	"cmpb $0, kvm_rebooting \n\t"	      \
-	"jne 668b \n\t"      		      \
-	__ASM_SIZE(push) " $666b \n\t"	      \
-	"jmp kvm_spurious_fault \n\t"	      \
-	".popsection \n\t" \
-	_ASM_EXTABLE(666b, 667b)
+#define ____kvm_handle_fault_on_reboot(insn, cleanup_insn)		\
+	"666: \n\t"							\
+	insn "\n\t"							\
+	"jmp	668f \n\t"						\
+	"667: \n\t"							\
+	"call	kvm_spurious_fault \n\t"				\
+	"668: \n\t"							\
+	".pushsection .fixup, \"ax\" \n\t"				\
+	"700: \n\t"							\
+	cleanup_insn "\n\t"						\
+	"cmpb	$0, kvm_rebooting\n\t"					\
+	"je	667b \n\t"						\
+	"jmp	668b \n\t"						\
+	".popsection \n\t"						\
+	_ASM_EXTABLE(666b, 700b)
 
 #define __kvm_handle_fault_on_reboot(insn)		\
 	____kvm_handle_fault_on_reboot(insn, "")
@@ -1529,7 +1540,6 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low,
 		    unsigned long ipi_bitmap_high, u32 min,
 		    unsigned long icr, int op_64_bit);
 
-u64 kvm_get_arch_capabilities(void);
 void kvm_define_shared_msr(unsigned index, u32 msr);
 int kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
 
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 5ed3cf1c3934..9b4df6eaa11a 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -92,7 +92,7 @@ void kvm_async_pf_task_wait(u32 token, int interrupt_kernel);
 void kvm_async_pf_task_wake(u32 token);
 u32 kvm_read_and_reset_pf_reason(void);
 extern void kvm_disable_steal_time(void);
-void do_async_page_fault(struct pt_regs *regs, unsigned long error_code);
+void do_async_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address);
 
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
 void __init kvm_spinlock_init(void);
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 5ff3e8af2c20..e78c7db87801 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -59,6 +59,7 @@ typedef struct {
 #define INIT_MM_CONTEXT(mm)						\
 	.context = {							\
 		.ctx_id = 1,						\
+		.lock = __MUTEX_INITIALIZER(mm.context.lock),		\
 	}
 
 void leave_mm(int cpu);
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index f4fa8a9d5d0b..2ef31cc8c529 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -3,84 +3,15 @@
 #define _ASM_X86_MSHYPER_H
 
 #include <linux/types.h>
-#include <linux/atomic.h>
 #include <linux/nmi.h>
 #include <asm/io.h>
 #include <asm/hyperv-tlfs.h>
 #include <asm/nospec-branch.h>
 
-#define VP_INVAL	U32_MAX
-
-struct ms_hyperv_info {
-	u32 features;
-	u32 misc_features;
-	u32 hints;
-	u32 nested_features;
-	u32 max_vp_index;
-	u32 max_lp_index;
-};
-
-extern struct ms_hyperv_info ms_hyperv;
-
-
 typedef int (*hyperv_fill_flush_list_func)(
 		struct hv_guest_mapping_flush_list *flush,
 		void *data);
 
-/*
- * Generate the guest ID.
- */
-
-static inline  __u64 generate_guest_id(__u64 d_info1, __u64 kernel_version,
-				       __u64 d_info2)
-{
-	__u64 guest_id = 0;
-
-	guest_id = (((__u64)HV_LINUX_VENDOR_ID) << 48);
-	guest_id |= (d_info1 << 48);
-	guest_id |= (kernel_version << 16);
-	guest_id |= d_info2;
-
-	return guest_id;
-}
-
-
-/* Free the message slot and signal end-of-message if required */
-static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
-{
-	/*
-	 * On crash we're reading some other CPU's message page and we need
-	 * to be careful: this other CPU may already had cleared the header
-	 * and the host may already had delivered some other message there.
-	 * In case we blindly write msg->header.message_type we're going
-	 * to lose it. We can still lose a message of the same type but
-	 * we count on the fact that there can only be one
-	 * CHANNELMSG_UNLOAD_RESPONSE and we don't care about other messages
-	 * on crash.
-	 */
-	if (cmpxchg(&msg->header.message_type, old_msg_type,
-		    HVMSG_NONE) != old_msg_type)
-		return;
-
-	/*
-	 * Make sure the write to MessageType (ie set to
-	 * HVMSG_NONE) happens before we read the
-	 * MessagePending and EOMing. Otherwise, the EOMing
-	 * will not deliver any more messages since there is
-	 * no empty slot
-	 */
-	mb();
-
-	if (msg->header.message_flags.msg_pending) {
-		/*
-		 * This will cause message queue rescan to
-		 * possibly deliver another msg from the
-		 * hypervisor
-		 */
-		wrmsrl(HV_X64_MSR_EOM, 0);
-	}
-}
-
 #define hv_init_timer(timer, tick) \
 	wrmsrl(HV_X64_MSR_STIMER0_COUNT + (2*timer), tick)
 #define hv_init_timer_config(timer, val) \
@@ -97,6 +28,8 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
 
 #define hv_get_vp_index(index) rdmsrl(HV_X64_MSR_VP_INDEX, index)
 
+#define hv_signal_eom() wrmsrl(HV_X64_MSR_EOM, 0)
+
 #define hv_get_synint_state(int_num, val) \
 	rdmsrl(HV_X64_MSR_SINT0 + int_num, val)
 #define hv_set_synint_state(int_num, val) \
@@ -122,13 +55,6 @@ void hyperv_reenlightenment_vector(void);
 #define trace_hyperv_callback_vector hyperv_callback_vector
 #endif
 void hyperv_vector_handler(struct pt_regs *regs);
-void hv_setup_vmbus_irq(void (*handler)(void));
-void hv_remove_vmbus_irq(void);
-
-void hv_setup_kexec_handler(void (*handler)(void));
-void hv_remove_kexec_handler(void);
-void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs));
-void hv_remove_crash_handler(void);
 
 /*
  * Routines for stimer0 Direct Mode handling.
@@ -136,8 +62,6 @@ void hv_remove_crash_handler(void);
  */
 void hv_stimer0_vector_handler(struct pt_regs *regs);
 void hv_stimer0_callback_vector(void);
-int hv_setup_stimer0_irq(int *irq, int *vector, void (*handler)(void));
-void hv_remove_stimer0_irq(int irq);
 
 static inline void hv_enable_stimer0_percpu_irq(int irq) {}
 static inline void hv_disable_stimer0_percpu_irq(int irq) {}
@@ -282,14 +206,6 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size,
 	return status;
 }
 
-/*
- * Hypervisor's notion of virtual processor ID is different from
- * Linux' notion of CPU ID. This information can only be retrieved
- * in the context of the calling CPU. Setup a map for easy access
- * to this information.
- */
-extern u32 *hv_vp_index;
-extern u32 hv_max_vp_index;
 extern struct hv_vp_assist_page **hv_vp_assist_page;
 
 static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu)
@@ -300,63 +216,8 @@ static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu)
 	return hv_vp_assist_page[cpu];
 }
 
-/**
- * hv_cpu_number_to_vp_number() - Map CPU to VP.
- * @cpu_number: CPU number in Linux terms
- *
- * This function returns the mapping between the Linux processor
- * number and the hypervisor's virtual processor number, useful
- * in making hypercalls and such that talk about specific
- * processors.
- *
- * Return: Virtual processor number in Hyper-V terms
- */
-static inline int hv_cpu_number_to_vp_number(int cpu_number)
-{
-	return hv_vp_index[cpu_number];
-}
-
-static inline int cpumask_to_vpset(struct hv_vpset *vpset,
-				    const struct cpumask *cpus)
-{
-	int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1;
-
-	/* valid_bank_mask can represent up to 64 banks */
-	if (hv_max_vp_index / 64 >= 64)
-		return 0;
-
-	/*
-	 * Clear all banks up to the maximum possible bank as hv_tlb_flush_ex
-	 * structs are not cleared between calls, we risk flushing unneeded
-	 * vCPUs otherwise.
-	 */
-	for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++)
-		vpset->bank_contents[vcpu_bank] = 0;
-
-	/*
-	 * Some banks may end up being empty but this is acceptable.
-	 */
-	for_each_cpu(cpu, cpus) {
-		vcpu = hv_cpu_number_to_vp_number(cpu);
-		if (vcpu == VP_INVAL)
-			return -1;
-		vcpu_bank = vcpu / 64;
-		vcpu_offset = vcpu % 64;
-		__set_bit(vcpu_offset, (unsigned long *)
-			  &vpset->bank_contents[vcpu_bank]);
-		if (vcpu_bank >= nr_bank)
-			nr_bank = vcpu_bank + 1;
-	}
-	vpset->valid_bank_mask = GENMASK_ULL(nr_bank - 1, 0);
-	return nr_bank;
-}
-
 void __init hyperv_init(void);
 void hyperv_setup_mmu_ops(void);
-void hyperv_report_panic(struct pt_regs *regs, long err);
-void hyperv_report_panic_msg(phys_addr_t pa, size_t size);
-bool hv_is_hyperv_initialized(void);
-void hyperv_cleanup(void);
 
 void hyperv_reenlightenment_intr(struct pt_regs *regs);
 void set_hv_tscchange_cb(void (*cb)(void));
@@ -379,8 +240,6 @@ static inline void hv_apic_init(void) {}
 
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
-static inline bool hv_is_hyperv_initialized(void) { return false; }
-static inline void hyperv_cleanup(void) {}
 static inline void hyperv_setup_mmu_ops(void) {}
 static inline void set_hv_tscchange_cb(void (*cb)(void)) {}
 static inline void clear_hv_tscchange_cb(void) {}
@@ -397,4 +256,7 @@ static inline int hyperv_flush_guest_mapping_range(u64 as,
 }
 #endif /* CONFIG_HYPERV */
 
+
+#include <asm-generic/mshyperv.h>
+
 #endif
diff --git a/arch/x86/include/asm/olpc.h b/arch/x86/include/asm/olpc.h
index c2bf1de5d901..6fe76282aceb 100644
--- a/arch/x86/include/asm/olpc.h
+++ b/arch/x86/include/asm/olpc.h
@@ -9,12 +9,10 @@
 struct olpc_platform_t {
 	int flags;
 	uint32_t boardrev;
-	int ecver;
 };
 
 #define OLPC_F_PRESENT		0x01
 #define OLPC_F_DCON		0x02
-#define OLPC_F_EC_WIDE_SCI	0x04
 
 #ifdef CONFIG_OLPC
 
@@ -64,13 +62,6 @@ static inline int olpc_board_at_least(uint32_t rev)
 	return olpc_platform_info.boardrev >= rev;
 }
 
-extern void olpc_ec_wakeup_set(u16 value);
-extern void olpc_ec_wakeup_clear(u16 value);
-extern bool olpc_ec_wakeup_available(void);
-
-extern int olpc_ec_mask_write(u16 bits);
-extern int olpc_ec_sci_query(u16 *sci_value);
-
 #else
 
 static inline int machine_is_olpc(void)
@@ -83,14 +74,6 @@ static inline int olpc_has_dcon(void)
 	return 0;
 }
 
-static inline void olpc_ec_wakeup_set(u16 value) { }
-static inline void olpc_ec_wakeup_clear(u16 value) { }
-
-static inline bool olpc_ec_wakeup_available(void)
-{
-	return false;
-}
-
 #endif
 
 #ifdef CONFIG_OLPC_XO1_PM
@@ -101,20 +84,6 @@ extern void olpc_xo1_pm_wakeup_clear(u16 value);
 
 extern int pci_olpc_init(void);
 
-/* SCI source values */
-
-#define EC_SCI_SRC_EMPTY	0x00
-#define EC_SCI_SRC_GAME		0x01
-#define EC_SCI_SRC_BATTERY	0x02
-#define EC_SCI_SRC_BATSOC	0x04
-#define EC_SCI_SRC_BATERR	0x08
-#define EC_SCI_SRC_EBOOK	0x10	/* XO-1 only */
-#define EC_SCI_SRC_WLAN		0x20	/* XO-1 only */
-#define EC_SCI_SRC_ACPWR	0x40
-#define EC_SCI_SRC_BATCRIT	0x80
-#define EC_SCI_SRC_GPWAKE	0x100	/* XO-1.5 only */
-#define EC_SCI_SRC_ALL		0x1FF
-
 /* GPIO assignments */
 
 #define OLPC_GPIO_MIC_AC	1
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 793c14c372cb..288b065955b7 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -48,7 +48,7 @@
 
 #define __START_KERNEL_map	_AC(0xffffffff80000000, UL)
 
-/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
+/* See Documentation/x86/x86_64/mm.rst for a description of the memory map. */
 
 #define __PHYSICAL_MASK_SHIFT	52
 
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index c25c38a05c1c..dce26f1d13e1 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -116,7 +116,7 @@ static inline void write_cr0(unsigned long x)
 
 static inline unsigned long read_cr2(void)
 {
-	return PVOP_CALL0(unsigned long, mmu.read_cr2);
+	return PVOP_CALLEE0(unsigned long, mmu.read_cr2);
 }
 
 static inline void write_cr2(unsigned long x)
@@ -746,6 +746,7 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
 	    PV_RESTORE_ALL_CALLER_REGS					\
 	    FRAME_END							\
 	    "ret;"							\
+	    ".size " PV_THUNK_NAME(func) ", .-" PV_THUNK_NAME(func) ";"	\
 	    ".popsection")
 
 /* Get a reference to a callee-save function */
@@ -909,13 +910,7 @@ extern void default_banner(void);
 		  ANNOTATE_RETPOLINE_SAFE;				\
 		  call PARA_INDIRECT(pv_ops+PV_CPU_swapgs);		\
 		 )
-#endif
-
-#define GET_CR2_INTO_RAX				\
-	ANNOTATE_RETPOLINE_SAFE;				\
-	call PARA_INDIRECT(pv_ops+PV_MMU_read_cr2);
 
-#ifdef CONFIG_PARAVIRT_XXL
 #define USERGS_SYSRET64							\
 	PARA_SITE(PARA_PATCH(PV_CPU_usergs_sysret64),			\
 		  ANNOTATE_RETPOLINE_SAFE;				\
@@ -929,9 +924,19 @@ extern void default_banner(void);
 		  call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);	    \
 		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
 #endif
-#endif
+#endif /* CONFIG_PARAVIRT_XXL */
+#endif	/* CONFIG_X86_64 */
+
+#ifdef CONFIG_PARAVIRT_XXL
+
+#define GET_CR2_INTO_AX							\
+	PARA_SITE(PARA_PATCH(PV_MMU_read_cr2),				\
+		  ANNOTATE_RETPOLINE_SAFE;				\
+		  call PARA_INDIRECT(pv_ops+PV_MMU_read_cr2);		\
+		 )
+
+#endif /* CONFIG_PARAVIRT_XXL */
 
-#endif	/* CONFIG_X86_32 */
 
 #endif /* __ASSEMBLY__ */
 #else  /* CONFIG_PARAVIRT */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 946f8f1f1efc..639b2df445ee 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -220,7 +220,7 @@ struct pv_mmu_ops {
 	void (*exit_mmap)(struct mm_struct *mm);
 
 #ifdef CONFIG_PARAVIRT_XXL
-	unsigned long (*read_cr2)(void);
+	struct paravirt_callee_save read_cr2;
 	void (*write_cr2)(unsigned long);
 
 	unsigned long (*read_cr3)(void);
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index a281e61ec60c..29aa7859bdee 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -6,6 +6,9 @@
 #include <linux/mm.h>		/* for struct page */
 #include <linux/pagemap.h>
 
+#define __HAVE_ARCH_PTE_ALLOC_ONE
+#include <asm-generic/pgalloc.h>	/* for pte_{alloc,free}_one */
+
 static inline int  __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; }
 
 #ifdef CONFIG_PARAVIRT_XXL
@@ -47,24 +50,8 @@ extern gfp_t __userpte_alloc_gfp;
 extern pgd_t *pgd_alloc(struct mm_struct *);
 extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 
-extern pte_t *pte_alloc_one_kernel(struct mm_struct *);
 extern pgtable_t pte_alloc_one(struct mm_struct *);
 
-/* Should really implement gc for free page table pages. This could be
-   done with a reference count in struct page. */
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	BUG_ON((unsigned long)pte & (PAGE_SIZE-1));
-	free_page((unsigned long)pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, struct page *pte)
-{
-	pgtable_page_dtor(pte);
-	__free_page(pte);
-}
-
 extern void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte);
 
 static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte,
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index f8b1ad2c3828..e3633795fb22 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -285,53 +285,6 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp)
 #define __pte_to_swp_entry(pte)	(__swp_entry(__pteval_swp_type(pte), \
 					     __pteval_swp_offset(pte)))
 
-#define gup_get_pte gup_get_pte
-/*
- * WARNING: only to be used in the get_user_pages_fast() implementation.
- *
- * With get_user_pages_fast(), we walk down the pagetables without taking
- * any locks.  For this we would like to load the pointers atomically,
- * but that is not possible (without expensive cmpxchg8b) on PAE.  What
- * we do have is the guarantee that a PTE will only either go from not
- * present to present, or present to not present or both -- it will not
- * switch to a completely different present page without a TLB flush in
- * between; something that we are blocking by holding interrupts off.
- *
- * Setting ptes from not present to present goes:
- *
- *   ptep->pte_high = h;
- *   smp_wmb();
- *   ptep->pte_low = l;
- *
- * And present to not present goes:
- *
- *   ptep->pte_low = 0;
- *   smp_wmb();
- *   ptep->pte_high = 0;
- *
- * We must ensure here that the load of pte_low sees 'l' iff pte_high
- * sees 'h'. We load pte_high *after* loading pte_low, which ensures we
- * don't see an older value of pte_high.  *Then* we recheck pte_low,
- * which ensures that we haven't picked up a changed pte high. We might
- * have gotten rubbish values from pte_low and pte_high, but we are
- * guaranteed that pte_low will not have the present bit set *unless*
- * it is 'l'. Because get_user_pages_fast() only operates on present ptes
- * we're safe.
- */
-static inline pte_t gup_get_pte(pte_t *ptep)
-{
-	pte_t pte;
-
-	do {
-		pte.pte_low = ptep->pte_low;
-		smp_rmb();
-		pte.pte_high = ptep->pte_high;
-		smp_rmb();
-	} while (unlikely(pte.pte_low != ptep->pte_low));
-
-	return pte;
-}
-
 #include <asm/pgtable-invert.h>
 
 #endif /* _ASM_X86_PGTABLE_3LEVEL_H */
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 5e0509b41986..0bc530c4eb13 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -271,7 +271,7 @@ static inline int has_transparent_hugepage(void)
 	return boot_cpu_has(X86_FEATURE_PSE);
 }
 
-#ifdef __HAVE_ARCH_PTE_DEVMAP
+#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
 static inline int pmd_devmap(pmd_t pmd)
 {
 	return !!(pmd_val(pmd) & _PAGE_DEVMAP);
@@ -732,7 +732,7 @@ static inline int pte_present(pte_t a)
 	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
 }
 
-#ifdef __HAVE_ARCH_PTE_DEVMAP
+#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
 static inline int pte_devmap(pte_t a)
 {
 	return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP;
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 4fe9e7fc74d3..c78da8eda8f2 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -106,6 +106,6 @@ do {						\
  * with only a host target support using a 32-bit type for internal
  * representation.
  */
-#define LOWMEM_PAGES ((((2<<31) - __PAGE_OFFSET) >> PAGE_SHIFT))
+#define LOWMEM_PAGES ((((_ULL(2)<<31) - __PAGE_OFFSET) >> PAGE_SHIFT))
 
 #endif /* _ASM_X86_PGTABLE_32_H */
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 0bb566315621..4990d26dfc73 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -259,14 +259,8 @@ extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
 extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
 
 #define gup_fast_permitted gup_fast_permitted
-static inline bool gup_fast_permitted(unsigned long start, int nr_pages)
+static inline bool gup_fast_permitted(unsigned long start, unsigned long end)
 {
-	unsigned long len, end;
-
-	len = (unsigned long)nr_pages << PAGE_SHIFT;
-	end = start + len;
-	if (end < start)
-		return false;
 	if (end >> __VIRTUAL_MASK_SHIFT)
 		return false;
 	return true;
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 88bca456da99..52e5f5f2240d 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -103,7 +103,7 @@ extern unsigned int ptrs_per_p4d;
 #define PGDIR_MASK	(~(PGDIR_SIZE - 1))
 
 /*
- * See Documentation/x86/x86_64/mm.txt for a description of the memory map.
+ * See Documentation/x86/x86_64/mm.rst for a description of the memory map.
  *
  * Be very careful vs. KASLR when changing anything here. The KASLR address
  * range must not overlap with anything except the KASAN shadow area, which
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index d6ff0bbdb394..b5e49e6bac63 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -103,7 +103,6 @@
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 #define _PAGE_NX	(_AT(pteval_t, 1) << _PAGE_BIT_NX)
 #define _PAGE_DEVMAP	(_AT(u64, 1) << _PAGE_BIT_DEVMAP)
-#define __HAVE_ARCH_PTE_DEVMAP
 #else
 #define _PAGE_NX	(_AT(pteval_t, 0))
 #define _PAGE_DEVMAP	(_AT(pteval_t, 0))
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 3eab6ece52b4..6e0a3b43d027 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -741,6 +741,7 @@ extern void load_direct_gdt(int);
 extern void load_fixmap_gdt(int);
 extern void load_percpu_segment(int);
 extern void cpu_init(void);
+extern void cr4_init(void);
 
 static inline unsigned long get_debugctlmsr(void)
 {
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 3703c91f441e..332eb3525867 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -98,12 +98,10 @@ struct cpuinfo_x86;
 struct task_struct;
 
 extern unsigned long profile_pc(struct pt_regs *regs);
-#define profile_pc profile_pc
 
 extern unsigned long
 convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs);
-extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
-			 int error_code, int si_code);
+extern void send_sigtrap(struct pt_regs *regs, int error_code, int si_code);
 
 
 static inline unsigned long regs_return_value(struct pt_regs *regs)
@@ -171,11 +169,32 @@ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
 	return regs->sp;
 }
 
-#define GET_IP(regs) ((regs)->ip)
-#define GET_FP(regs) ((regs)->bp)
-#define GET_USP(regs) ((regs)->sp)
+static inline unsigned long instruction_pointer(struct pt_regs *regs)
+{
+	return regs->ip;
+}
+
+static inline void instruction_pointer_set(struct pt_regs *regs,
+		unsigned long val)
+{
+	regs->ip = val;
+}
+
+static inline unsigned long frame_pointer(struct pt_regs *regs)
+{
+	return regs->bp;
+}
 
-#include <asm-generic/ptrace.h>
+static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+{
+	return regs->sp;
+}
+
+static inline void user_stack_pointer_set(struct pt_regs *regs,
+		unsigned long val)
+{
+	regs->sp = val;
+}
 
 /* Query offset/name of register from its name/offset */
 extern int regs_query_register_offset(const char *name);
diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h
index 8ea1cfdbeabc..71b32f2570ab 100644
--- a/arch/x86/include/asm/sections.h
+++ b/arch/x86/include/asm/sections.h
@@ -13,4 +13,6 @@ extern char __end_rodata_aligned[];
 extern char __end_rodata_hpage_align[];
 #endif
 
+extern char __end_of_kernel_reserve[];
+
 #endif	/* _ASM_X86_SECTIONS_H */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index b2e84d113f2a..219be88a59d2 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -18,9 +18,7 @@
  */
 extern unsigned long __force_order;
 
-/* Starts false and gets enabled once CPU feature detection is done. */
-DECLARE_STATIC_KEY_FALSE(cr_pinning);
-extern unsigned long cr4_pinned_bits;
+void native_write_cr0(unsigned long val);
 
 static inline unsigned long native_read_cr0(void)
 {
@@ -29,24 +27,6 @@ static inline unsigned long native_read_cr0(void)
 	return val;
 }
 
-static inline void native_write_cr0(unsigned long val)
-{
-	unsigned long bits_missing = 0;
-
-set_register:
-	asm volatile("mov %0,%%cr0": "+r" (val), "+m" (__force_order));
-
-	if (static_branch_likely(&cr_pinning)) {
-		if (unlikely((val & X86_CR0_WP) != X86_CR0_WP)) {
-			bits_missing = X86_CR0_WP;
-			val |= bits_missing;
-			goto set_register;
-		}
-		/* Warn after we've set the missing bits. */
-		WARN_ONCE(bits_missing, "CR0 WP bit went missing!?\n");
-	}
-}
-
 static inline unsigned long native_read_cr2(void)
 {
 	unsigned long val;
@@ -91,24 +71,7 @@ static inline unsigned long native_read_cr4(void)
 	return val;
 }
 
-static inline void native_write_cr4(unsigned long val)
-{
-	unsigned long bits_missing = 0;
-
-set_register:
-	asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits));
-
-	if (static_branch_likely(&cr_pinning)) {
-		if (unlikely((val & cr4_pinned_bits) != cr4_pinned_bits)) {
-			bits_missing = ~val & cr4_pinned_bits;
-			val |= bits_missing;
-			goto set_register;
-		}
-		/* Warn after we've set the missing bits. */
-		WARN_ONCE(bits_missing, "CR4 bits went missing: %lx!?\n",
-			  bits_missing);
-	}
-}
+void native_write_cr4(unsigned long val);
 
 #ifdef CONFIG_X86_64
 static inline unsigned long native_read_cr8(void)
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 7d6f3f3fad78..b25e633033c3 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -40,7 +40,7 @@ asmlinkage void simd_coprocessor_error(void);
 asmlinkage void xen_divide_error(void);
 asmlinkage void xen_xennmi(void);
 asmlinkage void xen_xendebug(void);
-asmlinkage void xen_xenint3(void);
+asmlinkage void xen_int3(void);
 asmlinkage void xen_overflow(void);
 asmlinkage void xen_bounds(void);
 asmlinkage void xen_invalid_op(void);
@@ -74,14 +74,14 @@ dotraplinkage void do_invalid_TSS(struct pt_regs *regs, long error_code);
 dotraplinkage void do_segment_not_present(struct pt_regs *regs, long error_code);
 dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code);
 #ifdef CONFIG_X86_64
-dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code);
+dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code, unsigned long address);
 asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs);
 asmlinkage __visible notrace
 struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s);
 void __init trap_init(void);
 #endif
 dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code);
-dotraplinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code);
+dotraplinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address);
 dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *regs, long error_code);
 dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code);
 dotraplinkage void do_alignment_check(struct pt_regs *regs, long error_code);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index c82abd6e4ca3..9c4435307ff8 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -66,7 +66,9 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
 })
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
-# define WARN_ON_IN_IRQ()	WARN_ON_ONCE(!in_task())
+static inline bool pagefault_disabled(void);
+# define WARN_ON_IN_IRQ()	\
+	WARN_ON_ONCE(!in_task() && !pagefault_disabled())
 #else
 # define WARN_ON_IN_IRQ()
 #endif
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 146859efd83c..097589753fec 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -54,5 +54,6 @@
 # define __ARCH_WANT_SYS_FORK
 # define __ARCH_WANT_SYS_VFORK
 # define __ARCH_WANT_SYS_CLONE
+# define __ARCH_WANT_SYS_CLONE3
 
 #endif /* _ASM_X86_UNISTD_H */
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index b85a7c54c6a1..ac0934189017 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -301,6 +301,8 @@ extern struct x86_apic_ops x86_apic_ops;
 extern void x86_early_init_platform_quirks(void);
 extern void x86_init_noop(void);
 extern void x86_init_uint_noop(unsigned int unused);
+extern bool bool_x86_init_noop(void);
+extern void x86_op_int_noop(int cpu);
 extern bool x86_pnpbios_disabled(void);
 
 #endif
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 39171b3646bb..42e1245af0d8 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -44,14 +44,14 @@ static inline uint32_t xen_cpuid_base(void)
 }
 
 #ifdef CONFIG_XEN
-extern bool xen_hvm_need_lapic(void);
+extern bool __init xen_hvm_need_lapic(void);
 
-static inline bool xen_x2apic_para_available(void)
+static inline bool __init xen_x2apic_para_available(void)
 {
 	return xen_hvm_need_lapic();
 }
 #else
-static inline bool xen_x2apic_para_available(void)
+static inline bool __init xen_x2apic_para_available(void)
 {
 	return (xen_cpuid_base() != 0);
 }
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 60733f137e9a..c895df5482c5 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -29,6 +29,8 @@
 #define XLF_EFI_HANDOVER_32		(1<<2)
 #define XLF_EFI_HANDOVER_64		(1<<3)
 #define XLF_EFI_KEXEC			(1<<4)
+#define XLF_5LEVEL			(1<<5)
+#define XLF_5LEVEL_ENABLED		(1<<6)
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/x86/include/uapi/asm/byteorder.h b/arch/x86/include/uapi/asm/byteorder.h
index 484e3cfd7ef2..149143cab9ff 100644
--- a/arch/x86/include/uapi/asm/byteorder.h
+++ b/arch/x86/include/uapi/asm/byteorder.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _ASM_X86_BYTEORDER_H
 #define _ASM_X86_BYTEORDER_H
 
diff --git a/arch/x86/include/uapi/asm/hwcap2.h b/arch/x86/include/uapi/asm/hwcap2.h
index 6ebaae90e207..8b2effe6efb8 100644
--- a/arch/x86/include/uapi/asm/hwcap2.h
+++ b/arch/x86/include/uapi/asm/hwcap2.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _ASM_X86_HWCAP2_H
 #define _ASM_X86_HWCAP2_H
 
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index d6ab5b4d15e5..503d3f42da16 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -378,10 +378,11 @@ struct kvm_sync_regs {
 	struct kvm_vcpu_events events;
 };
 
-#define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)
-#define KVM_X86_QUIRK_CD_NW_CLEARED	(1 << 1)
-#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE	(1 << 2)
-#define KVM_X86_QUIRK_OUT_7E_INC_RIP	(1 << 3)
+#define KVM_X86_QUIRK_LINT0_REENABLED	   (1 << 0)
+#define KVM_X86_QUIRK_CD_NW_CLEARED	   (1 << 1)
+#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE	   (1 << 2)
+#define KVM_X86_QUIRK_OUT_7E_INC_RIP	   (1 << 3)
+#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4)
 
 #define KVM_STATE_NESTED_FORMAT_VMX	0
 #define KVM_STATE_NESTED_FORMAT_SVM	1	/* unused */
@@ -432,4 +433,17 @@ struct kvm_nested_state {
 	} data;
 };
 
+/* for KVM_CAP_PMU_EVENT_FILTER */
+struct kvm_pmu_event_filter {
+	__u32 action;
+	__u32 nevents;
+	__u32 fixed_counter_bitmap;
+	__u32 flags;
+	__u32 pad[4];
+	__u64 events[0];
+};
+
+#define KVM_PMU_EVENT_ALLOW 0
+#define KVM_PMU_EVENT_DENY 1
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 19980ec1a316..2a8e0b6b9805 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -29,6 +29,8 @@
 #define KVM_FEATURE_PV_TLB_FLUSH	9
 #define KVM_FEATURE_ASYNC_PF_VMEXIT	10
 #define KVM_FEATURE_PV_SEND_IPI	11
+#define KVM_FEATURE_POLL_CONTROL	12
+#define KVM_FEATURE_PV_SCHED_YIELD	13
 
 #define KVM_HINTS_REALTIME      0
 
@@ -47,6 +49,7 @@
 #define MSR_KVM_ASYNC_PF_EN 0x4b564d02
 #define MSR_KVM_STEAL_TIME  0x4b564d03
 #define MSR_KVM_PV_EOI_EN      0x4b564d04
+#define MSR_KVM_POLL_CONTROL	0x4b564d05
 
 struct kvm_steal_time {
 	__u64 steal;
diff --git a/arch/x86/include/uapi/asm/sigcontext32.h b/arch/x86/include/uapi/asm/sigcontext32.h
index 6b18e88de8a6..7114801d0499 100644
--- a/arch/x86/include/uapi/asm/sigcontext32.h
+++ b/arch/x86/include/uapi/asm/sigcontext32.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _ASM_X86_SIGCONTEXT32_H
 #define _ASM_X86_SIGCONTEXT32_H
 
diff --git a/arch/x86/include/uapi/asm/types.h b/arch/x86/include/uapi/asm/types.h
index df55e1ddb0c9..9d5c11a24279 100644
--- a/arch/x86/include/uapi/asm/types.h
+++ b/arch/x86/include/uapi/asm/types.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
 #ifndef _ASM_X86_TYPES_H
 #define _ASM_X86_TYPES_H
 
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index d213ec5c3766..f0b0c90dd398 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -146,7 +146,6 @@
 
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL       2
-#define VMX_ABORT_VMCS_CORRUPTED             3
 #define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
 
 #endif /* _UAPIVMX_H */