Merge branch 'next' into for-linus

Prepare input updates for 4.17 merge window.

133 files changed, 3587 insertions, 1506 deletions

diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 5d6a53fd7521..de690c2d2e33 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -6,7 +6,6 @@ generated-y += unistd_32_ia32.h
 generated-y += unistd_64_x32.h
 generated-y += xen-hypercalls.h
 
-generic-y += clkdev.h
 generic-y += dma-contiguous.h
 generic-y += early_ioremap.h
 generic-y += mcs_spinlock.h
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 8d0ec9df1cbe..11881726ed37 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -49,7 +49,7 @@ extern int acpi_fix_pin2_polarity;
 extern int acpi_disable_cmcff;
 
 extern u8 acpi_sci_flags;
-extern int acpi_sci_override_gsi;
+extern u32 acpi_sci_override_gsi;
 void acpi_pic_sci_set_trigger(unsigned int, u16);
 
 struct device;
@@ -94,7 +94,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
 	if (boot_cpu_data.x86 == 0x0F &&
 	    boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
 	    boot_cpu_data.x86_model <= 0x05 &&
-	    boot_cpu_data.x86_mask < 0x0A)
+	    boot_cpu_data.x86_stepping < 0x0A)
 		return 1;
 	else if (boot_cpu_has(X86_BUG_AMD_APIC_C1E))
 		return 1;
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index dbfd0854651f..cf5961ca8677 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -140,7 +140,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	".popsection\n"							\
 	".pushsection .altinstr_replacement, \"ax\"\n"			\
 	ALTINSTR_REPLACEMENT(newinstr, feature, 1)			\
-	".popsection"
+	".popsection\n"
 
 #define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
 	OLDINSTR_2(oldinstr, 1, 2)					\
@@ -151,7 +151,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
 	".pushsection .altinstr_replacement, \"ax\"\n"			\
 	ALTINSTR_REPLACEMENT(newinstr1, feature1, 1)			\
 	ALTINSTR_REPLACEMENT(newinstr2, feature2, 2)			\
-	".popsection"
+	".popsection\n"
 
 /*
  * Alternative instructions for different CPU types or capabilities.
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 5f01671c68f2..98722773391d 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -53,6 +53,15 @@ extern int local_apic_timer_c2_ok;
 extern int disable_apic;
 extern unsigned int lapic_timer_frequency;
 
+extern enum apic_intr_mode_id apic_intr_mode;
+enum apic_intr_mode_id {
+	APIC_PIC,
+	APIC_VIRTUAL_WIRE,
+	APIC_VIRTUAL_WIRE_NO_CONFIG,
+	APIC_SYMMETRIC_IO,
+	APIC_SYMMETRIC_IO_NO_ROUTING
+};
+
 #ifdef CONFIG_SMP
 extern void __inquire_remote_apic(int apicid);
 #else /* CONFIG_SMP */
@@ -128,13 +137,13 @@ extern void disable_local_APIC(void);
 extern void lapic_shutdown(void);
 extern void sync_Arb_IDs(void);
 extern void init_bsp_APIC(void);
+extern void apic_intr_mode_init(void);
 extern void setup_local_APIC(void);
 extern void init_apic_mappings(void);
 void register_lapic_address(unsigned long address);
 extern void setup_boot_APIC_clock(void);
 extern void setup_secondary_APIC_clock(void);
 extern void lapic_update_tsc_freq(void);
-extern int APIC_init_uniprocessor(void);
 
 #ifdef CONFIG_X86_64
 static inline int apic_force_enable(unsigned long addr)
@@ -145,7 +154,7 @@ static inline int apic_force_enable(unsigned long addr)
 extern int apic_force_enable(unsigned long addr);
 #endif
 
-extern int apic_bsp_setup(bool upmode);
+extern void apic_bsp_setup(bool upmode);
 extern void apic_ap_setup(void);
 
 /*
@@ -161,6 +170,10 @@ static inline int apic_is_clustered_box(void)
 #endif
 
 extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask);
+extern void lapic_assign_system_vectors(void);
+extern void lapic_assign_legacy_vector(unsigned int isairq, bool replace);
+extern void lapic_online(void);
+extern void lapic_offline(void);
 
 #else /* !CONFIG_X86_LOCAL_APIC */
 static inline void lapic_shutdown(void) { }
@@ -170,6 +183,9 @@ static inline void disable_local_APIC(void) { }
 # define setup_boot_APIC_clock x86_init_noop
 # define setup_secondary_APIC_clock x86_init_noop
 static inline void lapic_update_tsc_freq(void) { }
+static inline void apic_intr_mode_init(void) { }
+static inline void lapic_assign_system_vectors(void) { }
+static inline void lapic_assign_legacy_vector(unsigned int i, bool r) { }
 #endif /* !CONFIG_X86_LOCAL_APIC */
 
 #ifdef CONFIG_X86_X2APIC
@@ -265,73 +281,63 @@ struct irq_data;
  * James Cleverdon.
  */
 struct apic {
-	char *name;
-
-	int (*probe)(void);
-	int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
-	int (*apic_id_valid)(int apicid);
-	int (*apic_id_registered)(void);
-
-	u32 irq_delivery_mode;
-	u32 irq_dest_mode;
-
-	const struct cpumask *(*target_cpus)(void);
-
-	int disable_esr;
-
-	int dest_logical;
-	unsigned long (*check_apicid_used)(physid_mask_t *map, int apicid);
-
-	void (*vector_allocation_domain)(int cpu, struct cpumask *retmask,
-					 const struct cpumask *mask);
-	void (*init_apic_ldr)(void);
-
-	void (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap);
-
-	void (*setup_apic_routing)(void);
-	int (*cpu_present_to_apicid)(int mps_cpu);
-	void (*apicid_to_cpu_present)(int phys_apicid, physid_mask_t *retmap);
-	int (*check_phys_apicid_present)(int phys_apicid);
-	int (*phys_pkg_id)(int cpuid_apic, int index_msb);
-
-	unsigned int (*get_apic_id)(unsigned long x);
-	/* Can't be NULL on 64-bit */
-	unsigned long (*set_apic_id)(unsigned int id);
-
-	int (*cpu_mask_to_apicid)(const struct cpumask *cpumask,
-				  struct irq_data *irqdata,
-				  unsigned int *apicid);
-
-	/* ipi */
-	void (*send_IPI)(int cpu, int vector);
-	void (*send_IPI_mask)(const struct cpumask *mask, int vector);
-	void (*send_IPI_mask_allbutself)(const struct cpumask *mask,
-					 int vector);
-	void (*send_IPI_allbutself)(int vector);
-	void (*send_IPI_all)(int vector);
-	void (*send_IPI_self)(int vector);
+	/* Hotpath functions first */
+	void	(*eoi_write)(u32 reg, u32 v);
+	void	(*native_eoi_write)(u32 reg, u32 v);
+	void	(*write)(u32 reg, u32 v);
+	u32	(*read)(u32 reg);
+
+	/* IPI related functions */
+	void	(*wait_icr_idle)(void);
+	u32	(*safe_wait_icr_idle)(void);
+
+	void	(*send_IPI)(int cpu, int vector);
+	void	(*send_IPI_mask)(const struct cpumask *mask, int vector);
+	void	(*send_IPI_mask_allbutself)(const struct cpumask *msk, int vec);
+	void	(*send_IPI_allbutself)(int vector);
+	void	(*send_IPI_all)(int vector);
+	void	(*send_IPI_self)(int vector);
+
+	/* dest_logical is used by the IPI functions */
+	u32	dest_logical;
+	u32	disable_esr;
+	u32	irq_delivery_mode;
+	u32	irq_dest_mode;
+
+	/* Functions and data related to vector allocation */
+	void	(*vector_allocation_domain)(int cpu, struct cpumask *retmask,
+					    const struct cpumask *mask);
+	int	(*cpu_mask_to_apicid)(const struct cpumask *cpumask,
+				      struct irq_data *irqdata,
+				      unsigned int *apicid);
+	u32	(*calc_dest_apicid)(unsigned int cpu);
+
+	/* ICR related functions */
+	u64	(*icr_read)(void);
+	void	(*icr_write)(u32 low, u32 high);
+
+	/* Probe, setup and smpboot functions */
+	int	(*probe)(void);
+	int	(*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
+	int	(*apic_id_valid)(int apicid);
+	int	(*apic_id_registered)(void);
+
+	bool	(*check_apicid_used)(physid_mask_t *map, int apicid);
+	void	(*init_apic_ldr)(void);
+	void	(*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap);
+	void	(*setup_apic_routing)(void);
+	int	(*cpu_present_to_apicid)(int mps_cpu);
+	void	(*apicid_to_cpu_present)(int phys_apicid, physid_mask_t *retmap);
+	int	(*check_phys_apicid_present)(int phys_apicid);
+	int	(*phys_pkg_id)(int cpuid_apic, int index_msb);
+
+	u32	(*get_apic_id)(unsigned long x);
+	u32	(*set_apic_id)(unsigned int id);
 
 	/* wakeup_secondary_cpu */
-	int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip);
+	int	(*wakeup_secondary_cpu)(int apicid, unsigned long start_eip);
 
-	void (*inquire_remote_apic)(int apicid);
-
-	/* apic ops */
-	u32 (*read)(u32 reg);
-	void (*write)(u32 reg, u32 v);
-	/*
-	 * ->eoi_write() has the same signature as ->write().
-	 *
-	 * Drivers can support both ->eoi_write() and ->write() by passing the same
-	 * callback value. Kernel can override ->eoi_write() and fall back
-	 * on write for EOI.
-	 */
-	void (*eoi_write)(u32 reg, u32 v);
-	void (*native_eoi_write)(u32 reg, u32 v);
-	u64 (*icr_read)(void);
-	void (*icr_write)(u32 low, u32 high);
-	void (*wait_icr_idle)(void);
-	u32 (*safe_wait_icr_idle)(void);
+	void	(*inquire_remote_apic)(int apicid);
 
 #ifdef CONFIG_X86_32
 	/*
@@ -346,6 +352,7 @@ struct apic {
 	 */
 	int (*x86_32_early_logical_apicid)(int cpu);
 #endif
+	char	*name;
 };
 
 /*
@@ -380,6 +387,7 @@ extern struct apic *__apicdrivers[], *__apicdrivers_end[];
  */
 #ifdef CONFIG_SMP
 extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip);
+extern int lapic_can_unplug_cpu(void);
 #endif
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -463,84 +471,33 @@ static inline unsigned default_get_apic_id(unsigned long x)
 extern void apic_send_IPI_self(int vector);
 
 DECLARE_PER_CPU(int, x2apic_extra_bits);
-
-extern int default_cpu_present_to_apicid(int mps_cpu);
-extern int default_check_phys_apicid_present(int phys_apicid);
 #endif
 
 extern void generic_bigsmp_probe(void);
 
-
 #ifdef CONFIG_X86_LOCAL_APIC
 
 #include <asm/smp.h>
 
 #define APIC_DFR_VALUE	(APIC_DFR_FLAT)
 
-static inline const struct cpumask *default_target_cpus(void)
-{
-#ifdef CONFIG_SMP
-	return cpu_online_mask;
-#else
-	return cpumask_of(0);
-#endif
-}
-
-static inline const struct cpumask *online_target_cpus(void)
-{
-	return cpu_online_mask;
-}
-
 DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid);
 
+extern struct apic apic_noop;
 
 static inline unsigned int read_apic_id(void)
 {
-	unsigned int reg;
-
-	reg = apic_read(APIC_ID);
+	unsigned int reg = apic_read(APIC_ID);
 
 	return apic->get_apic_id(reg);
 }
 
-static inline int default_apic_id_valid(int apicid)
-{
-	return (apicid < 255);
-}
-
+extern int default_apic_id_valid(int apicid);
 extern int default_acpi_madt_oem_check(char *, char *);
-
 extern void default_setup_apic_routing(void);
 
-extern struct apic apic_noop;
-
-#ifdef CONFIG_X86_32
-
-static inline int noop_x86_32_early_logical_apicid(int cpu)
-{
-	return BAD_APICID;
-}
-
-/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LDR and TPR before enabling
- * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116).  So here it goes...
- */
-extern void default_init_apic_ldr(void);
-
-static inline int default_apic_id_registered(void)
-{
-	return physid_isset(read_apic_id(), phys_cpu_present_map);
-}
-
-static inline int default_phys_pkg_id(int cpuid_apic, int index_msb)
-{
-	return cpuid_apic >> index_msb;
-}
-
-#endif
+extern u32 apic_default_calc_apicid(unsigned int cpu);
+extern u32 apic_flat_calc_apicid(unsigned int cpu);
 
 extern int flat_cpu_mask_to_apicid(const struct cpumask *cpumask,
 				   struct irq_data *irqdata,
@@ -548,71 +505,17 @@ extern int flat_cpu_mask_to_apicid(const struct cpumask *cpumask,
 extern int default_cpu_mask_to_apicid(const struct cpumask *cpumask,
 				      struct irq_data *irqdata,
 				      unsigned int *apicid);
-
-static inline void
-flat_vector_allocation_domain(int cpu, struct cpumask *retmask,
-			      const struct cpumask *mask)
-{
-	/* Careful. Some cpus do not strictly honor the set of cpus
-	 * specified in the interrupt destination when using lowest
-	 * priority interrupt delivery mode.
-	 *
-	 * In particular there was a hyperthreading cpu observed to
-	 * deliver interrupts to the wrong hyperthread when only one
-	 * hyperthread was specified in the interrupt desitination.
-	 */
-	cpumask_clear(retmask);
-	cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
-}
-
-static inline void
-default_vector_allocation_domain(int cpu, struct cpumask *retmask,
-				 const struct cpumask *mask)
-{
-	cpumask_copy(retmask, cpumask_of(cpu));
-}
-
-static inline unsigned long default_check_apicid_used(physid_mask_t *map, int apicid)
-{
-	return physid_isset(apicid, *map);
-}
-
-static inline void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap)
-{
-	*retmap = *phys_map;
-}
-
-static inline int __default_cpu_present_to_apicid(int mps_cpu)
-{
-	if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu))
-		return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu);
-	else
-		return BAD_APICID;
-}
-
-static inline int
-__default_check_phys_apicid_present(int phys_apicid)
-{
-	return physid_isset(phys_apicid, phys_cpu_present_map);
-}
-
-#ifdef CONFIG_X86_32
-static inline int default_cpu_present_to_apicid(int mps_cpu)
-{
-	return __default_cpu_present_to_apicid(mps_cpu);
-}
-
-static inline int
-default_check_phys_apicid_present(int phys_apicid)
-{
-	return __default_check_phys_apicid_present(phys_apicid);
-}
-#else
+extern bool default_check_apicid_used(physid_mask_t *map, int apicid);
+extern void flat_vector_allocation_domain(int cpu, struct cpumask *retmask,
+				   const struct cpumask *mask);
+extern void default_vector_allocation_domain(int cpu, struct cpumask *retmask,
+				      const struct cpumask *mask);
+extern void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap);
 extern int default_cpu_present_to_apicid(int mps_cpu);
 extern int default_check_phys_apicid_present(int phys_apicid);
-#endif
 
 #endif /* CONFIG_X86_LOCAL_APIC */
+
 extern void irq_enter(void);
 extern void irq_exit(void);
 
diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h
index 4d4015ddcf26..c356098b6fb9 100644
--- a/arch/x86/include/asm/apm.h
+++ b/arch/x86/include/asm/apm.h
@@ -7,6 +7,8 @@
 #ifndef _ASM_X86_MACH_DEFAULT_APM_H
 #define _ASM_X86_MACH_DEFAULT_APM_H
 
+#include <asm/nospec-branch.h>
+
 #ifdef APM_ZERO_SEGS
 #	define APM_DO_ZERO_SEGS \
 		"pushl %%ds\n\t" \
@@ -32,6 +34,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
+	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -44,6 +47,7 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 		  "=S" (*esi)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
+	firmware_restrict_branch_speculation_end();
 }
 
 static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
@@ -56,6 +60,7 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
+	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -68,6 +73,7 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
 		  "=S" (si)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
+	firmware_restrict_branch_speculation_end();
 	return error;
 }
 
diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h
index 5b0579abb398..3ac991d81e74 100644
--- a/arch/x86/include/asm/archrandom.h
+++ b/arch/x86/include/asm/archrandom.h
@@ -45,7 +45,7 @@ static inline bool rdrand_long(unsigned long *v)
 	bool ok;
 	unsigned int retry = RDRAND_RETRY_LOOPS;
 	do {
-		asm volatile(RDRAND_LONG "\n\t"
+		asm volatile(RDRAND_LONG
 			     CC_SET(c)
 			     : CC_OUT(c) (ok), "=a" (*v));
 		if (ok)
@@ -59,7 +59,7 @@ static inline bool rdrand_int(unsigned int *v)
 	bool ok;
 	unsigned int retry = RDRAND_RETRY_LOOPS;
 	do {
-		asm volatile(RDRAND_INT "\n\t"
+		asm volatile(RDRAND_INT
 			     CC_SET(c)
 			     : CC_OUT(c) (ok), "=a" (*v));
 		if (ok)
@@ -71,7 +71,7 @@ static inline bool rdrand_int(unsigned int *v)
 static inline bool rdseed_long(unsigned long *v)
 {
 	bool ok;
-	asm volatile(RDSEED_LONG "\n\t"
+	asm volatile(RDSEED_LONG
 		     CC_SET(c)
 		     : CC_OUT(c) (ok), "=a" (*v));
 	return ok;
@@ -80,7 +80,7 @@ static inline bool rdseed_long(unsigned long *v)
 static inline bool rdseed_int(unsigned int *v)
 {
 	bool ok;
-	asm volatile(RDSEED_INT "\n\t"
+	asm volatile(RDSEED_INT
 		     CC_SET(c)
 		     : CC_OUT(c) (ok), "=a" (*v));
 	return ok;
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index ff700d81e91e..1908214b9125 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -11,7 +11,31 @@
 #include <asm/pgtable.h>
 #include <asm/special_insns.h>
 #include <asm/preempt.h>
+#include <asm/asm.h>
 
 #ifndef CONFIG_X86_CMPXCHG64
 extern void cmpxchg8b_emu(void);
 #endif
+
+#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_X86_32
+#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_e ## reg(void);
+#else
+#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_r ## reg(void);
+INDIRECT_THUNK(8)
+INDIRECT_THUNK(9)
+INDIRECT_THUNK(10)
+INDIRECT_THUNK(11)
+INDIRECT_THUNK(12)
+INDIRECT_THUNK(13)
+INDIRECT_THUNK(14)
+INDIRECT_THUNK(15)
+#endif
+INDIRECT_THUNK(ax)
+INDIRECT_THUNK(bx)
+INDIRECT_THUNK(cx)
+INDIRECT_THUNK(dx)
+INDIRECT_THUNK(si)
+INDIRECT_THUNK(di)
+INDIRECT_THUNK(bp)
+#endif /* CONFIG_RETPOLINE */
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 219faaec51df..386a6900e206 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -136,6 +136,7 @@
 #endif
 
 #ifndef __ASSEMBLY__
+#ifndef __BPF__
 /*
  * This output constraint should be used for any inline asm which has a "call"
  * instruction.  Otherwise the asm may be inserted before the frame pointer
@@ -145,5 +146,6 @@
 register unsigned long current_stack_pointer asm(_ASM_SP);
 #define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
 #endif
+#endif
 
 #endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 01727dbc294a..e1259f043ae9 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -12,11 +12,11 @@
  */
 
 #ifdef CONFIG_X86_32
-#define mb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "mfence", \
+#define mb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "mfence", \
 				      X86_FEATURE_XMM2) ::: "memory", "cc")
-#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "lfence", \
+#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "lfence", \
 				       X86_FEATURE_XMM2) ::: "memory", "cc")
-#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "sfence", \
+#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "sfence", \
 				       X86_FEATURE_XMM2) ::: "memory", "cc")
 #else
 #define mb() 	asm volatile("mfence":::"memory")
@@ -24,6 +24,34 @@
 #define wmb()	asm volatile("sfence" ::: "memory")
 #endif
 
+/**
+ * array_index_mask_nospec() - generate a mask that is ~0UL when the
+ * 	bounds check succeeds and 0 otherwise
+ * @index: array element index
+ * @size: number of elements in array
+ *
+ * Returns:
+ *     0 - (index < size)
+ */
+static inline unsigned long array_index_mask_nospec(unsigned long index,
+		unsigned long size)
+{
+	unsigned long mask;
+
+	asm ("cmp %1,%2; sbb %0,%0;"
+			:"=r" (mask)
+			:"g"(size),"r" (index)
+			:"cc");
+	return mask;
+}
+
+/* Override the default implementation from linux/nospec.h. */
+#define array_index_mask_nospec array_index_mask_nospec
+
+/* Prevent speculative execution past this barrier. */
+#define barrier_nospec() alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC, \
+					   "lfence", X86_FEATURE_LFENCE_RDTSC)
+
 #ifdef CONFIG_X86_PPRO_FENCE
 #define dma_rmb()	rmb()
 #else
@@ -31,7 +59,11 @@
 #endif
 #define dma_wmb()	barrier()
 
-#define __smp_mb()	mb()
+#ifdef CONFIG_X86_32
+#define __smp_mb()	asm volatile("lock; addl $0,-4(%%esp)" ::: "memory", "cc")
+#else
+#define __smp_mb()	asm volatile("lock; addl $0,-4(%%rsp)" ::: "memory", "cc")
+#endif
 #define __smp_rmb()	dma_rmb()
 #define __smp_wmb()	barrier()
 #define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 2bcf47314959..9f645ba57dbb 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -78,7 +78,7 @@ set_bit(long nr, volatile unsigned long *addr)
 			: "iq" ((u8)CONST_MASK(nr))
 			: "memory");
 	} else {
-		asm volatile(LOCK_PREFIX "bts %1,%0"
+		asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0"
 			: BITOP_ADDR(addr) : "Ir" (nr) : "memory");
 	}
 }
@@ -94,7 +94,7 @@ set_bit(long nr, volatile unsigned long *addr)
  */
 static __always_inline void __set_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory");
+	asm volatile(__ASM_SIZE(bts) " %1,%0" : ADDR : "Ir" (nr) : "memory");
 }
 
 /**
@@ -115,7 +115,7 @@ clear_bit(long nr, volatile unsigned long *addr)
 			: CONST_MASK_ADDR(nr, addr)
 			: "iq" ((u8)~CONST_MASK(nr)));
 	} else {
-		asm volatile(LOCK_PREFIX "btr %1,%0"
+		asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0"
 			: BITOP_ADDR(addr)
 			: "Ir" (nr));
 	}
@@ -137,13 +137,13 @@ static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *ad
 
 static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
+	asm volatile(__ASM_SIZE(btr) " %1,%0" : ADDR : "Ir" (nr));
 }
 
 static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
 {
 	bool negative;
-	asm volatile(LOCK_PREFIX "andb %2,%1\n\t"
+	asm volatile(LOCK_PREFIX "andb %2,%1"
 		CC_SET(s)
 		: CC_OUT(s) (negative), ADDR
 		: "ir" ((char) ~(1 << nr)) : "memory");
@@ -182,7 +182,7 @@ static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *
  */
 static __always_inline void __change_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("btc %1,%0" : ADDR : "Ir" (nr));
+	asm volatile(__ASM_SIZE(btc) " %1,%0" : ADDR : "Ir" (nr));
 }
 
 /**
@@ -201,7 +201,7 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr)
 			: CONST_MASK_ADDR(nr, addr)
 			: "iq" ((u8)CONST_MASK(nr)));
 	} else {
-		asm volatile(LOCK_PREFIX "btc %1,%0"
+		asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0"
 			: BITOP_ADDR(addr)
 			: "Ir" (nr));
 	}
@@ -217,7 +217,8 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr)
  */
 static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", c);
+	GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts),
+	                 *addr, "Ir", nr, "%0", c);
 }
 
 /**
@@ -246,7 +247,7 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *
 {
 	bool oldbit;
 
-	asm("bts %2,%1\n\t"
+	asm(__ASM_SIZE(bts) " %2,%1"
 	    CC_SET(c)
 	    : CC_OUT(c) (oldbit), ADDR
 	    : "Ir" (nr));
@@ -263,7 +264,8 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *
  */
 static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", c);
+	GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr),
+	                 *addr, "Ir", nr, "%0", c);
 }
 
 /**
@@ -286,7 +288,7 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long
 {
 	bool oldbit;
 
-	asm volatile("btr %2,%1\n\t"
+	asm volatile(__ASM_SIZE(btr) " %2,%1"
 		     CC_SET(c)
 		     : CC_OUT(c) (oldbit), ADDR
 		     : "Ir" (nr));
@@ -298,7 +300,7 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon
 {
 	bool oldbit;
 
-	asm volatile("btc %2,%1\n\t"
+	asm volatile(__ASM_SIZE(btc) " %2,%1"
 		     CC_SET(c)
 		     : CC_OUT(c) (oldbit), ADDR
 		     : "Ir" (nr) : "memory");
@@ -316,7 +318,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon
  */
 static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", c);
+	GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc),
+	                 *addr, "Ir", nr, "%0", c);
 }
 
 static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
@@ -329,7 +332,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l
 {
 	bool oldbit;
 
-	asm volatile("bt %2,%1\n\t"
+	asm volatile(__ASM_SIZE(bt) " %2,%1"
 		     CC_SET(c)
 		     : CC_OUT(c) (oldbit)
 		     : "m" (*(unsigned long *)addr), "Ir" (nr));
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index 34d99af43994..6804d6642767 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -5,23 +5,20 @@
 #include <linux/stringify.h>
 
 /*
- * Since some emulators terminate on UD2, we cannot use it for WARN.
- * Since various instruction decoders disagree on the length of UD1,
- * we cannot use it either. So use UD0 for WARN.
+ * Despite that some emulators terminate on UD2, we use it for WARN().
  *
- * (binutils knows about "ud1" but {en,de}codes it as 2 bytes, whereas
- *  our kernel decoder thinks it takes a ModRM byte, which seems consistent
- *  with various things like the Intel SDM instruction encoding rules)
+ * Since various instruction decoders/specs disagree on the encoding of
+ * UD0/UD1.
  */
 
-#define ASM_UD0		".byte 0x0f, 0xff"
+#define ASM_UD0		".byte 0x0f, 0xff" /* + ModRM (for Intel) */
 #define ASM_UD1		".byte 0x0f, 0xb9" /* + ModRM */
 #define ASM_UD2		".byte 0x0f, 0x0b"
 
 #define INSN_UD0	0xff0f
 #define INSN_UD2	0x0b0f
 
-#define LEN_UD0		2
+#define LEN_UD2		2
 
 #ifdef CONFIG_GENERIC_BUG
 
@@ -77,7 +74,11 @@ do {								\
 	unreachable();						\
 } while (0)
 
-#define __WARN_FLAGS(flags)	_BUG_FLAGS(ASM_UD0, BUGFLAG_WARNING|(flags))
+#define __WARN_FLAGS(flags)					\
+do {								\
+	_BUG_FLAGS(ASM_UD2, BUGFLAG_WARNING|(flags));		\
+	annotate_reachable();					\
+} while (0)
 
 #include <asm-generic/bug.h>
 
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 9eef9cc64c68..e1c8dab86670 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -7,6 +7,7 @@
  */
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <asm/processor.h>
 #include <asm/user32.h>
 #include <asm/unistd.h>
@@ -126,90 +127,7 @@ typedef u32		compat_old_sigset_t;	/* at least 32 bits */
 
 typedef u32               compat_sigset_word;
 
-typedef union compat_sigval {
-	compat_int_t	sival_int;
-	compat_uptr_t	sival_ptr;
-} compat_sigval_t;
-
-typedef struct compat_siginfo {
-	int si_signo;
-	int si_errno;
-	int si_code;
-
-	union {
-		int _pad[128/sizeof(int) - 3];
-
-		/* kill() */
-		struct {
-			unsigned int _pid;	/* sender's pid */
-			unsigned int _uid;	/* sender's uid */
-		} _kill;
-
-		/* POSIX.1b timers */
-		struct {
-			compat_timer_t _tid;	/* timer id */
-			int _overrun;		/* overrun count */
-			compat_sigval_t _sigval;	/* same as below */
-			int _sys_private;	/* not to be passed to user */
-			int _overrun_incr;	/* amount to add to overrun */
-		} _timer;
-
-		/* POSIX.1b signals */
-		struct {
-			unsigned int _pid;	/* sender's pid */
-			unsigned int _uid;	/* sender's uid */
-			compat_sigval_t _sigval;
-		} _rt;
-
-		/* SIGCHLD */
-		struct {
-			unsigned int _pid;	/* which child */
-			unsigned int _uid;	/* sender's uid */
-			int _status;		/* exit code */
-			compat_clock_t _utime;
-			compat_clock_t _stime;
-		} _sigchld;
-
-		/* SIGCHLD (x32 version) */
-		struct {
-			unsigned int _pid;	/* which child */
-			unsigned int _uid;	/* sender's uid */
-			int _status;		/* exit code */
-			compat_s64 _utime;
-			compat_s64 _stime;
-		} _sigchld_x32;
-
-		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
-		struct {
-			unsigned int _addr;	/* faulting insn/memory ref. */
-			short int _addr_lsb;	/* Valid LSB of the reported address. */
-			union {
-				/* used when si_code=SEGV_BNDERR */
-				struct {
-					compat_uptr_t _lower;
-					compat_uptr_t _upper;
-				} _addr_bnd;
-				/* used when si_code=SEGV_PKUERR */
-				compat_u32 _pkey;
-			};
-		} _sigfault;
-
-		/* SIGPOLL */
-		struct {
-			int _band;	/* POLL_IN, POLL_OUT, POLL_MSG */
-			int _fd;
-		} _sigpoll;
-
-		struct {
-			unsigned int _call_addr; /* calling insn */
-			int _syscall;	/* triggering system call number */
-			unsigned int _arch;	/* AUDIT_ARCH_* of syscall */
-		} _sigsys;
-	} _sifields;
-} compat_siginfo_t;
-
 #define COMPAT_OFF_T_MAX	0x7fffffff
-#define COMPAT_LOFF_T_MAX	0x7fffffffffffffffL
 
 struct compat_ipc64_perm {
 	compat_key_t key;
@@ -331,4 +249,8 @@ static inline bool in_compat_syscall(void)
 }
 #define in_compat_syscall in_compat_syscall	/* override the generic impl */
 
+struct compat_siginfo;
+int __copy_siginfo_to_user32(struct compat_siginfo __user *to,
+		const siginfo_t *from, bool x32_ABI);
+
 #endif /* _ASM_X86_COMPAT_H */
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
new file mode 100644
index 000000000000..4a7884b8dca5
--- /dev/null
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _ASM_X86_CPU_ENTRY_AREA_H
+#define _ASM_X86_CPU_ENTRY_AREA_H
+
+#include <linux/percpu-defs.h>
+#include <asm/processor.h>
+#include <asm/intel_ds.h>
+
+/*
+ * cpu_entry_area is a percpu region that contains things needed by the CPU
+ * and early entry/exit code.  Real types aren't used for all fields here
+ * to avoid circular header dependencies.
+ *
+ * Every field is a virtual alias of some other allocated backing store.
+ * There is no direct allocation of a struct cpu_entry_area.
+ */
+struct cpu_entry_area {
+	char gdt[PAGE_SIZE];
+
+	/*
+	 * The GDT is just below entry_stack and thus serves (on x86_64) as
+	 * a a read-only guard page.
+	 */
+	struct entry_stack_page entry_stack_page;
+
+	/*
+	 * On x86_64, the TSS is mapped RO.  On x86_32, it's mapped RW because
+	 * we need task switches to work, and task switches write to the TSS.
+	 */
+	struct tss_struct tss;
+
+	char entry_trampoline[PAGE_SIZE];
+
+#ifdef CONFIG_X86_64
+	/*
+	 * Exception stacks used for IST entries.
+	 *
+	 * In the future, this should have a separate slot for each stack
+	 * with guard pages between them.
+	 */
+	char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ];
+#endif
+#ifdef CONFIG_CPU_SUP_INTEL
+	/*
+	 * Per CPU debug store for Intel performance monitoring. Wastes a
+	 * full page at the moment.
+	 */
+	struct debug_store cpu_debug_store;
+	/*
+	 * The actual PEBS/BTS buffers must be mapped to user space
+	 * Reserve enough fixmap PTEs.
+	 */
+	struct debug_store_buffers cpu_debug_buffers;
+#endif
+};
+
+#define CPU_ENTRY_AREA_SIZE	(sizeof(struct cpu_entry_area))
+#define CPU_ENTRY_AREA_TOT_SIZE	(CPU_ENTRY_AREA_SIZE * NR_CPUS)
+
+DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
+
+extern void setup_cpu_entry_areas(void);
+extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
+
+#define	CPU_ENTRY_AREA_RO_IDT		CPU_ENTRY_AREA_BASE
+#define CPU_ENTRY_AREA_PER_CPU		(CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE)
+
+#define CPU_ENTRY_AREA_RO_IDT_VADDR	((void *)CPU_ENTRY_AREA_RO_IDT)
+
+#define CPU_ENTRY_AREA_MAP_SIZE			\
+	(CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_TOT_SIZE - CPU_ENTRY_AREA_BASE)
+
+extern struct cpu_entry_area *get_cpu_entry_area(int cpu);
+
+static inline struct entry_stack *cpu_entry_stack(int cpu)
+{
+	return &get_cpu_entry_area(cpu)->entry_stack_page.stack;
+}
+
+#endif
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 0dfa68438e80..736771c9822e 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -29,6 +29,7 @@ enum cpuid_leafs
 	CPUID_8000_000A_EDX,
 	CPUID_7_ECX,
 	CPUID_8000_0007_EBX,
+	CPUID_7_EDX,
 };
 
 #ifdef CONFIG_X86_FEATURE_NAMES
@@ -79,8 +80,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   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) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) ||	\
 	   REQUIRED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 19))
 
 #define DISABLED_MASK_BIT_SET(feature_bit)				\
 	 ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  0, feature_bit) ||	\
@@ -101,8 +103,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   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) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) ||	\
 	   DISABLED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 18))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 19))
 
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
@@ -126,16 +129,17 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 #define boot_cpu_has(bit)	cpu_has(&boot_cpu_data, bit)
 
 #define set_cpu_cap(c, bit)	set_bit(bit, (unsigned long *)((c)->x86_capability))
-#define clear_cpu_cap(c, bit)	clear_bit(bit, (unsigned long *)((c)->x86_capability))
-#define setup_clear_cpu_cap(bit) do { \
-	clear_cpu_cap(&boot_cpu_data, bit);	\
-	set_bit(bit, (unsigned long *)cpu_caps_cleared); \
-} while (0)
+
+extern void setup_clear_cpu_cap(unsigned int bit);
+extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
+
 #define setup_force_cpu_cap(bit) do { \
 	set_cpu_cap(&boot_cpu_data, bit);	\
 	set_bit(bit, (unsigned long *)cpu_caps_set);	\
 } while (0)
 
+#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
+
 #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS)
 /*
  * Static testing of CPU features.  Used the same as boot_cpu_has().
@@ -144,45 +148,46 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
  */
 static __always_inline __pure bool _static_cpu_has(u16 bit)
 {
-		asm_volatile_goto("1: jmp 6f\n"
-			 "2:\n"
-			 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
-			         "((5f-4f) - (2b-1b)),0x90\n"
-			 "3:\n"
-			 ".section .altinstructions,\"a\"\n"
-			 " .long 1b - .\n"		/* src offset */
-			 " .long 4f - .\n"		/* repl offset */
-			 " .word %P1\n"			/* always replace */
-			 " .byte 3b - 1b\n"		/* src len */
-			 " .byte 5f - 4f\n"		/* repl len */
-			 " .byte 3b - 2b\n"		/* pad len */
-			 ".previous\n"
-			 ".section .altinstr_replacement,\"ax\"\n"
-			 "4: jmp %l[t_no]\n"
-			 "5:\n"
-			 ".previous\n"
-			 ".section .altinstructions,\"a\"\n"
-			 " .long 1b - .\n"		/* src offset */
-			 " .long 0\n"			/* no replacement */
-			 " .word %P0\n"			/* feature bit */
-			 " .byte 3b - 1b\n"		/* src len */
-			 " .byte 0\n"			/* repl len */
-			 " .byte 0\n"			/* pad len */
-			 ".previous\n"
-			 ".section .altinstr_aux,\"ax\"\n"
-			 "6:\n"
-			 " testb %[bitnum],%[cap_byte]\n"
-			 " jnz %l[t_yes]\n"
-			 " jmp %l[t_no]\n"
-			 ".previous\n"
-			 : : "i" (bit), "i" (X86_FEATURE_ALWAYS),
-			     [bitnum] "i" (1 << (bit & 7)),
-			     [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3])
-			 : : t_yes, t_no);
-	t_yes:
-		return true;
-	t_no:
-		return false;
+	asm_volatile_goto("1: jmp 6f\n"
+		 "2:\n"
+		 ".skip -(((5f-4f) - (2b-1b)) > 0) * "
+			 "((5f-4f) - (2b-1b)),0x90\n"
+		 "3:\n"
+		 ".section .altinstructions,\"a\"\n"
+		 " .long 1b - .\n"		/* src offset */
+		 " .long 4f - .\n"		/* repl offset */
+		 " .word %P[always]\n"		/* always replace */
+		 " .byte 3b - 1b\n"		/* src len */
+		 " .byte 5f - 4f\n"		/* repl len */
+		 " .byte 3b - 2b\n"		/* pad len */
+		 ".previous\n"
+		 ".section .altinstr_replacement,\"ax\"\n"
+		 "4: jmp %l[t_no]\n"
+		 "5:\n"
+		 ".previous\n"
+		 ".section .altinstructions,\"a\"\n"
+		 " .long 1b - .\n"		/* src offset */
+		 " .long 0\n"			/* no replacement */
+		 " .word %P[feature]\n"		/* feature bit */
+		 " .byte 3b - 1b\n"		/* src len */
+		 " .byte 0\n"			/* repl len */
+		 " .byte 0\n"			/* pad len */
+		 ".previous\n"
+		 ".section .altinstr_aux,\"ax\"\n"
+		 "6:\n"
+		 " testb %[bitnum],%[cap_byte]\n"
+		 " jnz %l[t_yes]\n"
+		 " jmp %l[t_no]\n"
+		 ".previous\n"
+		 : : [feature]  "i" (bit),
+		     [always]   "i" (X86_FEATURE_ALWAYS),
+		     [bitnum]   "i" (1 << (bit & 7)),
+		     [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3])
+		 : : t_yes, t_no);
+t_yes:
+	return true;
+t_no:
+	return false;
 }
 
 #define static_cpu_has(bit)					\
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 793690fbda36..f41079da38c5 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -13,173 +13,176 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS	18	/* N 32-bit words worth of info */
-#define NBUGINTS	1	/* N 32-bit bug flags */
+#define NCAPINTS			19	   /* N 32-bit words worth of info */
+#define NBUGINTS			1	   /* N 32-bit bug flags */
 
 /*
  * Note: If the comment begins with a quoted string, that string is used
  * in /proc/cpuinfo instead of the macro name.  If the string is "",
  * this feature bit is not displayed in /proc/cpuinfo at all.
+ *
+ * When adding new features here that depend on other features,
+ * please update the table in kernel/cpu/cpuid-deps.c as well.
  */
 
-/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
-#define X86_FEATURE_FPU		( 0*32+ 0) /* Onboard FPU */
-#define X86_FEATURE_VME		( 0*32+ 1) /* Virtual Mode Extensions */
-#define X86_FEATURE_DE		( 0*32+ 2) /* Debugging Extensions */
-#define X86_FEATURE_PSE		( 0*32+ 3) /* Page Size Extensions */
-#define X86_FEATURE_TSC		( 0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR		( 0*32+ 5) /* Model-Specific Registers */
-#define X86_FEATURE_PAE		( 0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE		( 0*32+ 7) /* Machine Check Exception */
-#define X86_FEATURE_CX8		( 0*32+ 8) /* CMPXCHG8 instruction */
-#define X86_FEATURE_APIC	( 0*32+ 9) /* Onboard APIC */
-#define X86_FEATURE_SEP		( 0*32+11) /* SYSENTER/SYSEXIT */
-#define X86_FEATURE_MTRR	( 0*32+12) /* Memory Type Range Registers */
-#define X86_FEATURE_PGE		( 0*32+13) /* Page Global Enable */
-#define X86_FEATURE_MCA		( 0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV	( 0*32+15) /* CMOV instructions */
-					  /* (plus FCMOVcc, FCOMI with FPU) */
-#define X86_FEATURE_PAT		( 0*32+16) /* Page Attribute Table */
-#define X86_FEATURE_PSE36	( 0*32+17) /* 36-bit PSEs */
-#define X86_FEATURE_PN		( 0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLUSH	( 0*32+19) /* CLFLUSH instruction */
-#define X86_FEATURE_DS		( 0*32+21) /* "dts" Debug Store */
-#define X86_FEATURE_ACPI	( 0*32+22) /* ACPI via MSR */
-#define X86_FEATURE_MMX		( 0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR	( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
-#define X86_FEATURE_XMM		( 0*32+25) /* "sse" */
-#define X86_FEATURE_XMM2	( 0*32+26) /* "sse2" */
-#define X86_FEATURE_SELFSNOOP	( 0*32+27) /* "ss" CPU self snoop */
-#define X86_FEATURE_HT		( 0*32+28) /* Hyper-Threading */
-#define X86_FEATURE_ACC		( 0*32+29) /* "tm" Automatic clock control */
-#define X86_FEATURE_IA64	( 0*32+30) /* IA-64 processor */
-#define X86_FEATURE_PBE		( 0*32+31) /* Pending Break Enable */
+/* Intel-defined CPU features, CPUID level 0x00000001 (EDX), word 0 */
+#define X86_FEATURE_FPU			( 0*32+ 0) /* Onboard FPU */
+#define X86_FEATURE_VME			( 0*32+ 1) /* Virtual Mode Extensions */
+#define X86_FEATURE_DE			( 0*32+ 2) /* Debugging Extensions */
+#define X86_FEATURE_PSE			( 0*32+ 3) /* Page Size Extensions */
+#define X86_FEATURE_TSC			( 0*32+ 4) /* Time Stamp Counter */
+#define X86_FEATURE_MSR			( 0*32+ 5) /* Model-Specific Registers */
+#define X86_FEATURE_PAE			( 0*32+ 6) /* Physical Address Extensions */
+#define X86_FEATURE_MCE			( 0*32+ 7) /* Machine Check Exception */
+#define X86_FEATURE_CX8			( 0*32+ 8) /* CMPXCHG8 instruction */
+#define X86_FEATURE_APIC		( 0*32+ 9) /* Onboard APIC */
+#define X86_FEATURE_SEP			( 0*32+11) /* SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR		( 0*32+12) /* Memory Type Range Registers */
+#define X86_FEATURE_PGE			( 0*32+13) /* Page Global Enable */
+#define X86_FEATURE_MCA			( 0*32+14) /* Machine Check Architecture */
+#define X86_FEATURE_CMOV		( 0*32+15) /* CMOV instructions (plus FCMOVcc, FCOMI with FPU) */
+#define X86_FEATURE_PAT			( 0*32+16) /* Page Attribute Table */
+#define X86_FEATURE_PSE36		( 0*32+17) /* 36-bit PSEs */
+#define X86_FEATURE_PN			( 0*32+18) /* Processor serial number */
+#define X86_FEATURE_CLFLUSH		( 0*32+19) /* CLFLUSH instruction */
+#define X86_FEATURE_DS			( 0*32+21) /* "dts" Debug Store */
+#define X86_FEATURE_ACPI		( 0*32+22) /* ACPI via MSR */
+#define X86_FEATURE_MMX			( 0*32+23) /* Multimedia Extensions */
+#define X86_FEATURE_FXSR		( 0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_XMM			( 0*32+25) /* "sse" */
+#define X86_FEATURE_XMM2		( 0*32+26) /* "sse2" */
+#define X86_FEATURE_SELFSNOOP		( 0*32+27) /* "ss" CPU self snoop */
+#define X86_FEATURE_HT			( 0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_ACC			( 0*32+29) /* "tm" Automatic clock control */
+#define X86_FEATURE_IA64		( 0*32+30) /* IA-64 processor */
+#define X86_FEATURE_PBE			( 0*32+31) /* Pending Break Enable */
 
 /* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
 /* Don't duplicate feature flags which are redundant with Intel! */
-#define X86_FEATURE_SYSCALL	( 1*32+11) /* SYSCALL/SYSRET */
-#define X86_FEATURE_MP		( 1*32+19) /* MP Capable. */
-#define X86_FEATURE_NX		( 1*32+20) /* Execute Disable */
-#define X86_FEATURE_MMXEXT	( 1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_FXSR_OPT	( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
-#define X86_FEATURE_GBPAGES	( 1*32+26) /* "pdpe1gb" GB pages */
-#define X86_FEATURE_RDTSCP	( 1*32+27) /* RDTSCP */
-#define X86_FEATURE_LM		( 1*32+29) /* Long Mode (x86-64) */
-#define X86_FEATURE_3DNOWEXT	( 1*32+30) /* AMD 3DNow! extensions */
-#define X86_FEATURE_3DNOW	( 1*32+31) /* 3DNow! */
+#define X86_FEATURE_SYSCALL		( 1*32+11) /* SYSCALL/SYSRET */
+#define X86_FEATURE_MP			( 1*32+19) /* MP Capable */
+#define X86_FEATURE_NX			( 1*32+20) /* Execute Disable */
+#define X86_FEATURE_MMXEXT		( 1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_FXSR_OPT		( 1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_GBPAGES		( 1*32+26) /* "pdpe1gb" GB pages */
+#define X86_FEATURE_RDTSCP		( 1*32+27) /* RDTSCP */
+#define X86_FEATURE_LM			( 1*32+29) /* Long Mode (x86-64, 64-bit support) */
+#define X86_FEATURE_3DNOWEXT		( 1*32+30) /* AMD 3DNow extensions */
+#define X86_FEATURE_3DNOW		( 1*32+31) /* 3DNow */
 
 /* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
-#define X86_FEATURE_RECOVERY	( 2*32+ 0) /* CPU in recovery mode */
-#define X86_FEATURE_LONGRUN	( 2*32+ 1) /* Longrun power control */
-#define X86_FEATURE_LRTI	( 2*32+ 3) /* LongRun table interface */
+#define X86_FEATURE_RECOVERY		( 2*32+ 0) /* CPU in recovery mode */
+#define X86_FEATURE_LONGRUN		( 2*32+ 1) /* Longrun power control */
+#define X86_FEATURE_LRTI		( 2*32+ 3) /* LongRun table interface */
 
 /* Other features, Linux-defined mapping, word 3 */
 /* This range is used for feature bits which conflict or are synthesized */
-#define X86_FEATURE_CXMMX	( 3*32+ 0) /* Cyrix MMX extensions */
-#define X86_FEATURE_K6_MTRR	( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
-#define X86_FEATURE_CYRIX_ARR	( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
-#define X86_FEATURE_CENTAUR_MCR	( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
-/* cpu types for specific tunings: */
-#define X86_FEATURE_K8		( 3*32+ 4) /* "" Opteron, Athlon64 */
-#define X86_FEATURE_K7		( 3*32+ 5) /* "" Athlon */
-#define X86_FEATURE_P3		( 3*32+ 6) /* "" P3 */
-#define X86_FEATURE_P4		( 3*32+ 7) /* "" P4 */
-#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */
-#define X86_FEATURE_UP		( 3*32+ 9) /* smp kernel running on up */
-#define X86_FEATURE_ART		( 3*32+10) /* Platform has always running timer (ART) */
-#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_PEBS	( 3*32+12) /* Precise-Event Based Sampling */
-#define X86_FEATURE_BTS		( 3*32+13) /* Branch Trace Store */
-#define X86_FEATURE_SYSCALL32	( 3*32+14) /* "" syscall in ia32 userspace */
-#define X86_FEATURE_SYSENTER32	( 3*32+15) /* "" sysenter in ia32 userspace */
-#define X86_FEATURE_REP_GOOD	( 3*32+16) /* rep microcode works well */
-#define X86_FEATURE_MFENCE_RDTSC ( 3*32+17) /* "" Mfence synchronizes RDTSC */
-#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" Lfence synchronizes RDTSC */
-#define X86_FEATURE_ACC_POWER	( 3*32+19) /* AMD Accumulated Power Mechanism */
-#define X86_FEATURE_NOPL	( 3*32+20) /* The NOPL (0F 1F) instructions */
-#define X86_FEATURE_ALWAYS	( 3*32+21) /* "" Always-present feature */
-#define X86_FEATURE_XTOPOLOGY	( 3*32+22) /* cpu topology enum extensions */
-#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* TSC is known to be reliable */
-#define X86_FEATURE_NONSTOP_TSC	( 3*32+24) /* TSC does not stop in C states */
-#define X86_FEATURE_CPUID	( 3*32+25) /* CPU has CPUID instruction itself */
-#define X86_FEATURE_EXTD_APICID	( 3*32+26) /* has extended APICID (8 bits) */
-#define X86_FEATURE_AMD_DCM     ( 3*32+27) /* multi-node processor */
-#define X86_FEATURE_APERFMPERF	( 3*32+28) /* APERFMPERF */
-#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* TSC doesn't stop in S3 state */
-#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* TSC has known frequency */
-
-/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
-#define X86_FEATURE_XMM3	( 4*32+ 0) /* "pni" SSE-3 */
-#define X86_FEATURE_PCLMULQDQ	( 4*32+ 1) /* PCLMULQDQ instruction */
-#define X86_FEATURE_DTES64	( 4*32+ 2) /* 64-bit Debug Store */
-#define X86_FEATURE_MWAIT	( 4*32+ 3) /* "monitor" Monitor/Mwait support */
-#define X86_FEATURE_DSCPL	( 4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
-#define X86_FEATURE_VMX		( 4*32+ 5) /* Hardware virtualization */
-#define X86_FEATURE_SMX		( 4*32+ 6) /* Safer mode */
-#define X86_FEATURE_EST		( 4*32+ 7) /* Enhanced SpeedStep */
-#define X86_FEATURE_TM2		( 4*32+ 8) /* Thermal Monitor 2 */
-#define X86_FEATURE_SSSE3	( 4*32+ 9) /* Supplemental SSE-3 */
-#define X86_FEATURE_CID		( 4*32+10) /* Context ID */
-#define X86_FEATURE_SDBG	( 4*32+11) /* Silicon Debug */
-#define X86_FEATURE_FMA		( 4*32+12) /* Fused multiply-add */
-#define X86_FEATURE_CX16	( 4*32+13) /* CMPXCHG16B */
-#define X86_FEATURE_XTPR	( 4*32+14) /* Send Task Priority Messages */
-#define X86_FEATURE_PDCM	( 4*32+15) /* Performance Capabilities */
-#define X86_FEATURE_PCID	( 4*32+17) /* Process Context Identifiers */
-#define X86_FEATURE_DCA		( 4*32+18) /* Direct Cache Access */
-#define X86_FEATURE_XMM4_1	( 4*32+19) /* "sse4_1" SSE-4.1 */
-#define X86_FEATURE_XMM4_2	( 4*32+20) /* "sse4_2" SSE-4.2 */
-#define X86_FEATURE_X2APIC	( 4*32+21) /* x2APIC */
-#define X86_FEATURE_MOVBE	( 4*32+22) /* MOVBE instruction */
-#define X86_FEATURE_POPCNT      ( 4*32+23) /* POPCNT instruction */
-#define X86_FEATURE_TSC_DEADLINE_TIMER	( 4*32+24) /* Tsc deadline timer */
-#define X86_FEATURE_AES		( 4*32+25) /* AES instructions */
-#define X86_FEATURE_XSAVE	( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
-#define X86_FEATURE_OSXSAVE	( 4*32+27) /* "" XSAVE enabled in the OS */
-#define X86_FEATURE_AVX		( 4*32+28) /* Advanced Vector Extensions */
-#define X86_FEATURE_F16C	( 4*32+29) /* 16-bit fp conversions */
-#define X86_FEATURE_RDRAND	( 4*32+30) /* The RDRAND instruction */
-#define X86_FEATURE_HYPERVISOR	( 4*32+31) /* Running on a hypervisor */
+#define X86_FEATURE_CXMMX		( 3*32+ 0) /* Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR		( 3*32+ 1) /* AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR		( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR		( 3*32+ 3) /* Centaur MCRs (= MTRRs) */
+
+/* CPU types for specific tunings: */
+#define X86_FEATURE_K8			( 3*32+ 4) /* "" Opteron, Athlon64 */
+#define X86_FEATURE_K7			( 3*32+ 5) /* "" Athlon */
+#define X86_FEATURE_P3			( 3*32+ 6) /* "" P3 */
+#define X86_FEATURE_P4			( 3*32+ 7) /* "" P4 */
+#define X86_FEATURE_CONSTANT_TSC	( 3*32+ 8) /* TSC ticks at a constant rate */
+#define X86_FEATURE_UP			( 3*32+ 9) /* SMP kernel running on UP */
+#define X86_FEATURE_ART			( 3*32+10) /* Always running timer (ART) */
+#define X86_FEATURE_ARCH_PERFMON	( 3*32+11) /* Intel Architectural PerfMon */
+#define X86_FEATURE_PEBS		( 3*32+12) /* Precise-Event Based Sampling */
+#define X86_FEATURE_BTS			( 3*32+13) /* Branch Trace Store */
+#define X86_FEATURE_SYSCALL32		( 3*32+14) /* "" syscall in IA32 userspace */
+#define X86_FEATURE_SYSENTER32		( 3*32+15) /* "" sysenter in IA32 userspace */
+#define X86_FEATURE_REP_GOOD		( 3*32+16) /* REP microcode works well */
+#define X86_FEATURE_MFENCE_RDTSC	( 3*32+17) /* "" MFENCE synchronizes RDTSC */
+#define X86_FEATURE_LFENCE_RDTSC	( 3*32+18) /* "" LFENCE synchronizes RDTSC */
+#define X86_FEATURE_ACC_POWER		( 3*32+19) /* AMD Accumulated Power Mechanism */
+#define X86_FEATURE_NOPL		( 3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_ALWAYS		( 3*32+21) /* "" Always-present feature */
+#define X86_FEATURE_XTOPOLOGY		( 3*32+22) /* CPU topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE	( 3*32+23) /* TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC		( 3*32+24) /* TSC does not stop in C states */
+#define X86_FEATURE_CPUID		( 3*32+25) /* CPU has CPUID instruction itself */
+#define X86_FEATURE_EXTD_APICID		( 3*32+26) /* Extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM		( 3*32+27) /* AMD multi-node processor */
+#define X86_FEATURE_APERFMPERF		( 3*32+28) /* P-State hardware coordination feedback capability (APERF/MPERF MSRs) */
+#define X86_FEATURE_NONSTOP_TSC_S3	( 3*32+30) /* TSC doesn't stop in S3 state */
+#define X86_FEATURE_TSC_KNOWN_FREQ	( 3*32+31) /* TSC has known frequency */
+
+/* Intel-defined CPU features, CPUID level 0x00000001 (ECX), word 4 */
+#define X86_FEATURE_XMM3		( 4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_PCLMULQDQ		( 4*32+ 1) /* PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64		( 4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_MWAIT		( 4*32+ 3) /* "monitor" MONITOR/MWAIT support */
+#define X86_FEATURE_DSCPL		( 4*32+ 4) /* "ds_cpl" CPL-qualified (filtered) Debug Store */
+#define X86_FEATURE_VMX			( 4*32+ 5) /* Hardware virtualization */
+#define X86_FEATURE_SMX			( 4*32+ 6) /* Safer Mode eXtensions */
+#define X86_FEATURE_EST			( 4*32+ 7) /* Enhanced SpeedStep */
+#define X86_FEATURE_TM2			( 4*32+ 8) /* Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3		( 4*32+ 9) /* Supplemental SSE-3 */
+#define X86_FEATURE_CID			( 4*32+10) /* Context ID */
+#define X86_FEATURE_SDBG		( 4*32+11) /* Silicon Debug */
+#define X86_FEATURE_FMA			( 4*32+12) /* Fused multiply-add */
+#define X86_FEATURE_CX16		( 4*32+13) /* CMPXCHG16B instruction */
+#define X86_FEATURE_XTPR		( 4*32+14) /* Send Task Priority Messages */
+#define X86_FEATURE_PDCM		( 4*32+15) /* Perf/Debug Capabilities MSR */
+#define X86_FEATURE_PCID		( 4*32+17) /* Process Context Identifiers */
+#define X86_FEATURE_DCA			( 4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_XMM4_1		( 4*32+19) /* "sse4_1" SSE-4.1 */
+#define X86_FEATURE_XMM4_2		( 4*32+20) /* "sse4_2" SSE-4.2 */
+#define X86_FEATURE_X2APIC		( 4*32+21) /* X2APIC */
+#define X86_FEATURE_MOVBE		( 4*32+22) /* MOVBE instruction */
+#define X86_FEATURE_POPCNT		( 4*32+23) /* POPCNT instruction */
+#define X86_FEATURE_TSC_DEADLINE_TIMER	( 4*32+24) /* TSC deadline timer */
+#define X86_FEATURE_AES			( 4*32+25) /* AES instructions */
+#define X86_FEATURE_XSAVE		( 4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV instructions */
+#define X86_FEATURE_OSXSAVE		( 4*32+27) /* "" XSAVE instruction enabled in the OS */
+#define X86_FEATURE_AVX			( 4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_F16C		( 4*32+29) /* 16-bit FP conversions */
+#define X86_FEATURE_RDRAND		( 4*32+30) /* RDRAND instruction */
+#define X86_FEATURE_HYPERVISOR		( 4*32+31) /* Running on a hypervisor */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
-#define X86_FEATURE_XSTORE	( 5*32+ 2) /* "rng" RNG present (xstore) */
-#define X86_FEATURE_XSTORE_EN	( 5*32+ 3) /* "rng_en" RNG enabled */
-#define X86_FEATURE_XCRYPT	( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
-#define X86_FEATURE_XCRYPT_EN	( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
-#define X86_FEATURE_ACE2	( 5*32+ 8) /* Advanced Cryptography Engine v2 */
-#define X86_FEATURE_ACE2_EN	( 5*32+ 9) /* ACE v2 enabled */
-#define X86_FEATURE_PHE		( 5*32+10) /* PadLock Hash Engine */
-#define X86_FEATURE_PHE_EN	( 5*32+11) /* PHE enabled */
-#define X86_FEATURE_PMM		( 5*32+12) /* PadLock Montgomery Multiplier */
-#define X86_FEATURE_PMM_EN	( 5*32+13) /* PMM enabled */
-
-/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
-#define X86_FEATURE_LAHF_LM	( 6*32+ 0) /* LAHF/SAHF in long mode */
-#define X86_FEATURE_CMP_LEGACY	( 6*32+ 1) /* If yes HyperThreading not valid */
-#define X86_FEATURE_SVM		( 6*32+ 2) /* Secure virtual machine */
-#define X86_FEATURE_EXTAPIC	( 6*32+ 3) /* Extended APIC space */
-#define X86_FEATURE_CR8_LEGACY	( 6*32+ 4) /* CR8 in 32-bit mode */
-#define X86_FEATURE_ABM		( 6*32+ 5) /* Advanced bit manipulation */
-#define X86_FEATURE_SSE4A	( 6*32+ 6) /* SSE-4A */
-#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* Misaligned SSE mode */
-#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* 3DNow prefetch instructions */
-#define X86_FEATURE_OSVW	( 6*32+ 9) /* OS Visible Workaround */
-#define X86_FEATURE_IBS		( 6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_XOP		( 6*32+11) /* extended AVX instructions */
-#define X86_FEATURE_SKINIT	( 6*32+12) /* SKINIT/STGI instructions */
-#define X86_FEATURE_WDT		( 6*32+13) /* Watchdog timer */
-#define X86_FEATURE_LWP		( 6*32+15) /* Light Weight Profiling */
-#define X86_FEATURE_FMA4	( 6*32+16) /* 4 operands MAC instructions */
-#define X86_FEATURE_TCE		( 6*32+17) /* translation cache extension */
-#define X86_FEATURE_NODEID_MSR	( 6*32+19) /* NodeId MSR */
-#define X86_FEATURE_TBM		( 6*32+21) /* trailing bit manipulations */
-#define X86_FEATURE_TOPOEXT	( 6*32+22) /* topology extensions CPUID leafs */
-#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* core performance counter extensions */
-#define X86_FEATURE_PERFCTR_NB  ( 6*32+24) /* NB performance counter extensions */
-#define X86_FEATURE_BPEXT	(6*32+26) /* data breakpoint extension */
-#define X86_FEATURE_PTSC	( 6*32+27) /* performance time-stamp counter */
-#define X86_FEATURE_PERFCTR_LLC	( 6*32+28) /* Last Level Cache performance counter extensions */
-#define X86_FEATURE_MWAITX	( 6*32+29) /* MWAIT extension (MONITORX/MWAITX) */
+#define X86_FEATURE_XSTORE		( 5*32+ 2) /* "rng" RNG present (xstore) */
+#define X86_FEATURE_XSTORE_EN		( 5*32+ 3) /* "rng_en" RNG enabled */
+#define X86_FEATURE_XCRYPT		( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
+#define X86_FEATURE_XCRYPT_EN		( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */
+#define X86_FEATURE_ACE2		( 5*32+ 8) /* Advanced Cryptography Engine v2 */
+#define X86_FEATURE_ACE2_EN		( 5*32+ 9) /* ACE v2 enabled */
+#define X86_FEATURE_PHE			( 5*32+10) /* PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN		( 5*32+11) /* PHE enabled */
+#define X86_FEATURE_PMM			( 5*32+12) /* PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN		( 5*32+13) /* PMM enabled */
+
+/* More extended AMD flags: CPUID level 0x80000001, ECX, word 6 */
+#define X86_FEATURE_LAHF_LM		( 6*32+ 0) /* LAHF/SAHF in long mode */
+#define X86_FEATURE_CMP_LEGACY		( 6*32+ 1) /* If yes HyperThreading not valid */
+#define X86_FEATURE_SVM			( 6*32+ 2) /* Secure Virtual Machine */
+#define X86_FEATURE_EXTAPIC		( 6*32+ 3) /* Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY		( 6*32+ 4) /* CR8 in 32-bit mode */
+#define X86_FEATURE_ABM			( 6*32+ 5) /* Advanced bit manipulation */
+#define X86_FEATURE_SSE4A		( 6*32+ 6) /* SSE-4A */
+#define X86_FEATURE_MISALIGNSSE		( 6*32+ 7) /* Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH	( 6*32+ 8) /* 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW		( 6*32+ 9) /* OS Visible Workaround */
+#define X86_FEATURE_IBS			( 6*32+10) /* Instruction Based Sampling */
+#define X86_FEATURE_XOP			( 6*32+11) /* extended AVX instructions */
+#define X86_FEATURE_SKINIT		( 6*32+12) /* SKINIT/STGI instructions */
+#define X86_FEATURE_WDT			( 6*32+13) /* Watchdog timer */
+#define X86_FEATURE_LWP			( 6*32+15) /* Light Weight Profiling */
+#define X86_FEATURE_FMA4		( 6*32+16) /* 4 operands MAC instructions */
+#define X86_FEATURE_TCE			( 6*32+17) /* Translation Cache Extension */
+#define X86_FEATURE_NODEID_MSR		( 6*32+19) /* NodeId MSR */
+#define X86_FEATURE_TBM			( 6*32+21) /* Trailing Bit Manipulations */
+#define X86_FEATURE_TOPOEXT		( 6*32+22) /* Topology extensions CPUID leafs */
+#define X86_FEATURE_PERFCTR_CORE	( 6*32+23) /* Core performance counter extensions */
+#define X86_FEATURE_PERFCTR_NB		( 6*32+24) /* NB performance counter extensions */
+#define X86_FEATURE_BPEXT		( 6*32+26) /* Data breakpoint extension */
+#define X86_FEATURE_PTSC		( 6*32+27) /* Performance time-stamp counter */
+#define X86_FEATURE_PERFCTR_LLC		( 6*32+28) /* Last Level Cache performance counter extensions */
+#define X86_FEATURE_MWAITX		( 6*32+29) /* MWAIT extension (MONITORX/MWAITX instructions) */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -187,146 +190,175 @@
  *
  * Reuse free bits when adding new feature flags!
  */
-#define X86_FEATURE_RING3MWAIT	( 7*32+ 0) /* Ring 3 MONITOR/MWAIT */
-#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* Intel CPUID faulting */
-#define X86_FEATURE_CPB		( 7*32+ 2) /* AMD Core Performance Boost */
-#define X86_FEATURE_EPB		( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
-#define X86_FEATURE_CAT_L3	( 7*32+ 4) /* Cache Allocation Technology L3 */
-#define X86_FEATURE_CAT_L2	( 7*32+ 5) /* Cache Allocation Technology L2 */
-#define X86_FEATURE_CDP_L3	( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_RING3MWAIT		( 7*32+ 0) /* Ring 3 MONITOR/MWAIT instructions */
+#define X86_FEATURE_CPUID_FAULT		( 7*32+ 1) /* Intel CPUID faulting */
+#define X86_FEATURE_CPB			( 7*32+ 2) /* AMD Core Performance Boost */
+#define X86_FEATURE_EPB			( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */
+#define X86_FEATURE_CAT_L3		( 7*32+ 4) /* Cache Allocation Technology L3 */
+#define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
+#define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_INVPCID_SINGLE	( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
 
-#define X86_FEATURE_HW_PSTATE	( 7*32+ 8) /* AMD HW-PState */
-#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
-#define X86_FEATURE_SME		( 7*32+10) /* AMD Secure Memory Encryption */
+#define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
+#define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
+#define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
+#define X86_FEATURE_PTI			( 7*32+11) /* Kernel Page Table Isolation enabled */
+#define X86_FEATURE_RETPOLINE		( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_RETPOLINE_AMD	( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
+#define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
+#define X86_FEATURE_CDP_L2		( 7*32+15) /* Code and Data Prioritization L2 */
 
-#define X86_FEATURE_INTEL_PPIN	( 7*32+14) /* Intel Processor Inventory Number */
-#define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
-#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */
-#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
+#define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* "" Fill RSB on context switches */
+#define X86_FEATURE_SEV			( 7*32+20) /* AMD Secure Encrypted Virtualization */
 
-#define X86_FEATURE_MBA         ( 7*32+18) /* Memory Bandwidth Allocation */
+#define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
+#define X86_FEATURE_USE_IBRS_FW		( 7*32+22) /* "" Use IBRS during runtime firmware calls */
 
 /* Virtualization flags: Linux defined, word 8 */
-#define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
-#define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */
-#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */
-#define X86_FEATURE_EPT         ( 8*32+ 3) /* Intel Extended Page Table */
-#define X86_FEATURE_VPID        ( 8*32+ 4) /* Intel Virtual Processor ID */
-
-#define X86_FEATURE_VMMCALL     ( 8*32+15) /* Prefer vmmcall to vmcall */
-#define X86_FEATURE_XENPV       ( 8*32+16) /* "" Xen paravirtual guest */
-
-
-/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
-#define X86_FEATURE_FSGSBASE	( 9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
-#define X86_FEATURE_TSC_ADJUST	( 9*32+ 1) /* TSC adjustment MSR 0x3b */
-#define X86_FEATURE_BMI1	( 9*32+ 3) /* 1st group bit manipulation extensions */
-#define X86_FEATURE_HLE		( 9*32+ 4) /* Hardware Lock Elision */
-#define X86_FEATURE_AVX2	( 9*32+ 5) /* AVX2 instructions */
-#define X86_FEATURE_SMEP	( 9*32+ 7) /* Supervisor Mode Execution Protection */
-#define X86_FEATURE_BMI2	( 9*32+ 8) /* 2nd group bit manipulation extensions */
-#define X86_FEATURE_ERMS	( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */
-#define X86_FEATURE_INVPCID	( 9*32+10) /* Invalidate Processor Context ID */
-#define X86_FEATURE_RTM		( 9*32+11) /* Restricted Transactional Memory */
-#define X86_FEATURE_CQM		( 9*32+12) /* Cache QoS Monitoring */
-#define X86_FEATURE_MPX		( 9*32+14) /* Memory Protection Extension */
-#define X86_FEATURE_RDT_A	( 9*32+15) /* Resource Director Technology Allocation */
-#define X86_FEATURE_AVX512F	( 9*32+16) /* AVX-512 Foundation */
-#define X86_FEATURE_AVX512DQ	( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
-#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_AVX512IFMA  ( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
-#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 */
-#define X86_FEATURE_AVX512ER	( 9*32+27) /* AVX-512 Exponential and Reciprocal */
-#define X86_FEATURE_AVX512CD	( 9*32+28) /* AVX-512 Conflict Detection */
-#define X86_FEATURE_SHA_NI	( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
-#define X86_FEATURE_AVX512BW	( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */
-#define X86_FEATURE_AVX512VL	( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */
-
-/* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */
-#define X86_FEATURE_XSAVEOPT	(10*32+ 0) /* XSAVEOPT */
-#define X86_FEATURE_XSAVEC	(10*32+ 1) /* XSAVEC */
-#define X86_FEATURE_XGETBV1	(10*32+ 2) /* XGETBV with ECX = 1 */
-#define X86_FEATURE_XSAVES	(10*32+ 3) /* XSAVES/XRSTORS */
-
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */
-#define X86_FEATURE_CQM_LLC	(11*32+ 1) /* LLC QoS if 1 */
-
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */
-#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */
-#define X86_FEATURE_CQM_MBM_TOTAL (12*32+ 1) /* LLC Total MBM monitoring */
-#define X86_FEATURE_CQM_MBM_LOCAL (12*32+ 2) /* LLC Local MBM monitoring */
-
-/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
-#define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
-#define X86_FEATURE_IRPERF	(13*32+1) /* Instructions Retired Count */
-
-/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */
-#define X86_FEATURE_DTHERM	(14*32+ 0) /* Digital Thermal Sensor */
-#define X86_FEATURE_IDA		(14*32+ 1) /* Intel Dynamic Acceleration */
-#define X86_FEATURE_ARAT	(14*32+ 2) /* Always Running APIC Timer */
-#define X86_FEATURE_PLN		(14*32+ 4) /* Intel Power Limit Notification */
-#define X86_FEATURE_PTS		(14*32+ 6) /* Intel Package Thermal Status */
-#define X86_FEATURE_HWP		(14*32+ 7) /* Intel Hardware P-states */
-#define X86_FEATURE_HWP_NOTIFY	(14*32+ 8) /* HWP Notification */
-#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */
-#define X86_FEATURE_HWP_EPP	(14*32+10) /* HWP Energy Perf. Preference */
-#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */
-
-/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */
-#define X86_FEATURE_NPT		(15*32+ 0) /* Nested Page Table support */
-#define X86_FEATURE_LBRV	(15*32+ 1) /* LBR Virtualization support */
-#define X86_FEATURE_SVML	(15*32+ 2) /* "svm_lock" SVM locking MSR */
-#define X86_FEATURE_NRIPS	(15*32+ 3) /* "nrip_save" SVM next_rip save */
-#define X86_FEATURE_TSCRATEMSR  (15*32+ 4) /* "tsc_scale" TSC scaling support */
-#define X86_FEATURE_VMCBCLEAN   (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
-#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */
-#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */
-#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */
-#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */
-#define X86_FEATURE_AVIC	(15*32+13) /* Virtual Interrupt Controller */
-#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
-#define X86_FEATURE_VGIF	(15*32+16) /* Virtual GIF */
-
-/* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */
-#define X86_FEATURE_AVX512VBMI  (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
-#define X86_FEATURE_PKU		(16*32+ 3) /* Protection Keys for Userspace */
-#define X86_FEATURE_OSPKE	(16*32+ 4) /* OS Protection Keys Enable */
-#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
-#define X86_FEATURE_LA57	(16*32+16) /* 5-level page tables */
-#define X86_FEATURE_RDPID	(16*32+22) /* RDPID instruction */
-
-/* AMD-defined CPU features, CPUID level 0x80000007 (ebx), word 17 */
-#define X86_FEATURE_OVERFLOW_RECOV (17*32+0) /* MCA overflow recovery support */
-#define X86_FEATURE_SUCCOR	(17*32+1) /* Uncorrectable error containment and recovery */
-#define X86_FEATURE_SMCA	(17*32+3) /* Scalable MCA */
+#define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
+#define X86_FEATURE_VNMI		( 8*32+ 1) /* Intel Virtual NMI */
+#define X86_FEATURE_FLEXPRIORITY	( 8*32+ 2) /* Intel FlexPriority */
+#define X86_FEATURE_EPT			( 8*32+ 3) /* Intel Extended Page Table */
+#define X86_FEATURE_VPID		( 8*32+ 4) /* Intel Virtual Processor ID */
+
+#define X86_FEATURE_VMMCALL		( 8*32+15) /* Prefer VMMCALL to VMCALL */
+#define X86_FEATURE_XENPV		( 8*32+16) /* "" Xen paravirtual guest */
+
+
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
+#define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
+#define X86_FEATURE_TSC_ADJUST		( 9*32+ 1) /* TSC adjustment MSR 0x3B */
+#define X86_FEATURE_BMI1		( 9*32+ 3) /* 1st group bit manipulation extensions */
+#define X86_FEATURE_HLE			( 9*32+ 4) /* Hardware Lock Elision */
+#define X86_FEATURE_AVX2		( 9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_SMEP		( 9*32+ 7) /* Supervisor Mode Execution Protection */
+#define X86_FEATURE_BMI2		( 9*32+ 8) /* 2nd group bit manipulation extensions */
+#define X86_FEATURE_ERMS		( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */
+#define X86_FEATURE_INVPCID		( 9*32+10) /* Invalidate Processor Context ID */
+#define X86_FEATURE_RTM			( 9*32+11) /* Restricted Transactional Memory */
+#define X86_FEATURE_CQM			( 9*32+12) /* Cache QoS Monitoring */
+#define X86_FEATURE_MPX			( 9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_RDT_A		( 9*32+15) /* Resource Director Technology Allocation */
+#define X86_FEATURE_AVX512F		( 9*32+16) /* AVX-512 Foundation */
+#define X86_FEATURE_AVX512DQ		( 9*32+17) /* AVX-512 DQ (Double/Quad granular) Instructions */
+#define X86_FEATURE_RDSEED		( 9*32+18) /* RDSEED instruction */
+#define X86_FEATURE_ADX			( 9*32+19) /* ADCX and ADOX instructions */
+#define X86_FEATURE_SMAP		( 9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_AVX512IFMA		( 9*32+21) /* AVX-512 Integer Fused Multiply-Add instructions */
+#define X86_FEATURE_CLFLUSHOPT		( 9*32+23) /* CLFLUSHOPT instruction */
+#define X86_FEATURE_CLWB		( 9*32+24) /* CLWB instruction */
+#define X86_FEATURE_INTEL_PT		( 9*32+25) /* Intel Processor Trace */
+#define X86_FEATURE_AVX512PF		( 9*32+26) /* AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER		( 9*32+27) /* AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD		( 9*32+28) /* AVX-512 Conflict Detection */
+#define X86_FEATURE_SHA_NI		( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
+#define X86_FEATURE_AVX512BW		( 9*32+30) /* AVX-512 BW (Byte/Word granular) Instructions */
+#define X86_FEATURE_AVX512VL		( 9*32+31) /* AVX-512 VL (128/256 Vector Length) Extensions */
+
+/* Extended state features, CPUID level 0x0000000d:1 (EAX), word 10 */
+#define X86_FEATURE_XSAVEOPT		(10*32+ 0) /* XSAVEOPT instruction */
+#define X86_FEATURE_XSAVEC		(10*32+ 1) /* XSAVEC instruction */
+#define X86_FEATURE_XGETBV1		(10*32+ 2) /* XGETBV with ECX = 1 instruction */
+#define X86_FEATURE_XSAVES		(10*32+ 3) /* XSAVES/XRSTORS instructions */
+
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (EDX), word 11 */
+#define X86_FEATURE_CQM_LLC		(11*32+ 1) /* LLC QoS if 1 */
+
+/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (EDX), word 12 */
+#define X86_FEATURE_CQM_OCCUP_LLC	(12*32+ 0) /* LLC occupancy monitoring */
+#define X86_FEATURE_CQM_MBM_TOTAL	(12*32+ 1) /* LLC Total MBM monitoring */
+#define X86_FEATURE_CQM_MBM_LOCAL	(12*32+ 2) /* LLC Local MBM monitoring */
+
+/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
+#define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
+#define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
+#define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* Always save/restore FP error pointers */
+#define X86_FEATURE_IBPB		(13*32+12) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_IBRS		(13*32+14) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_STIBP		(13*32+15) /* Single Thread Indirect Branch Predictors */
+
+/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
+#define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
+#define X86_FEATURE_IDA			(14*32+ 1) /* Intel Dynamic Acceleration */
+#define X86_FEATURE_ARAT		(14*32+ 2) /* Always Running APIC Timer */
+#define X86_FEATURE_PLN			(14*32+ 4) /* Intel Power Limit Notification */
+#define X86_FEATURE_PTS			(14*32+ 6) /* Intel Package Thermal Status */
+#define X86_FEATURE_HWP			(14*32+ 7) /* Intel Hardware P-states */
+#define X86_FEATURE_HWP_NOTIFY		(14*32+ 8) /* HWP Notification */
+#define X86_FEATURE_HWP_ACT_WINDOW	(14*32+ 9) /* HWP Activity Window */
+#define X86_FEATURE_HWP_EPP		(14*32+10) /* HWP Energy Perf. Preference */
+#define X86_FEATURE_HWP_PKG_REQ		(14*32+11) /* HWP Package Level Request */
+
+/* AMD SVM Feature Identification, CPUID level 0x8000000a (EDX), word 15 */
+#define X86_FEATURE_NPT			(15*32+ 0) /* Nested Page Table support */
+#define X86_FEATURE_LBRV		(15*32+ 1) /* LBR Virtualization support */
+#define X86_FEATURE_SVML		(15*32+ 2) /* "svm_lock" SVM locking MSR */
+#define X86_FEATURE_NRIPS		(15*32+ 3) /* "nrip_save" SVM next_rip save */
+#define X86_FEATURE_TSCRATEMSR		(15*32+ 4) /* "tsc_scale" TSC scaling support */
+#define X86_FEATURE_VMCBCLEAN		(15*32+ 5) /* "vmcb_clean" VMCB clean bits support */
+#define X86_FEATURE_FLUSHBYASID		(15*32+ 6) /* flush-by-ASID support */
+#define X86_FEATURE_DECODEASSISTS	(15*32+ 7) /* Decode Assists support */
+#define X86_FEATURE_PAUSEFILTER		(15*32+10) /* filtered pause intercept */
+#define X86_FEATURE_PFTHRESHOLD		(15*32+12) /* pause filter threshold */
+#define X86_FEATURE_AVIC		(15*32+13) /* Virtual Interrupt Controller */
+#define X86_FEATURE_V_VMSAVE_VMLOAD	(15*32+15) /* Virtual VMSAVE VMLOAD */
+#define X86_FEATURE_VGIF		(15*32+16) /* Virtual GIF */
+
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
+#define X86_FEATURE_AVX512VBMI		(16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
+#define X86_FEATURE_UMIP		(16*32+ 2) /* User Mode Instruction Protection */
+#define X86_FEATURE_PKU			(16*32+ 3) /* Protection Keys for Userspace */
+#define X86_FEATURE_OSPKE		(16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_AVX512_VBMI2	(16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
+#define X86_FEATURE_GFNI		(16*32+ 8) /* Galois Field New Instructions */
+#define X86_FEATURE_VAES		(16*32+ 9) /* Vector AES */
+#define X86_FEATURE_VPCLMULQDQ		(16*32+10) /* Carry-Less Multiplication Double Quadword */
+#define X86_FEATURE_AVX512_VNNI		(16*32+11) /* Vector Neural Network Instructions */
+#define X86_FEATURE_AVX512_BITALG	(16*32+12) /* Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */
+#define X86_FEATURE_AVX512_VPOPCNTDQ	(16*32+14) /* POPCNT for vectors of DW/QW */
+#define X86_FEATURE_LA57		(16*32+16) /* 5-level page tables */
+#define X86_FEATURE_RDPID		(16*32+22) /* RDPID instruction */
+
+/* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
+#define X86_FEATURE_OVERFLOW_RECOV	(17*32+ 0) /* MCA overflow recovery support */
+#define X86_FEATURE_SUCCOR		(17*32+ 1) /* Uncorrectable error containment and recovery */
+#define X86_FEATURE_SMCA		(17*32+ 3) /* Scalable MCA */
+
+/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
+#define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
+#define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
+#define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
 
 /*
  * BUG word(s)
  */
-#define X86_BUG(x)		(NCAPINTS*32 + (x))
-
-#define X86_BUG_F00F		X86_BUG(0) /* Intel F00F */
-#define X86_BUG_FDIV		X86_BUG(1) /* FPU FDIV */
-#define X86_BUG_COMA		X86_BUG(2) /* Cyrix 6x86 coma */
-#define X86_BUG_AMD_TLB_MMATCH	X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
-#define X86_BUG_AMD_APIC_C1E	X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
-#define X86_BUG_11AP		X86_BUG(5) /* Bad local APIC aka 11AP */
-#define X86_BUG_FXSAVE_LEAK	X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
-#define X86_BUG_CLFLUSH_MONITOR	X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
-#define X86_BUG_SYSRET_SS_ATTRS	X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
+#define X86_BUG(x)			(NCAPINTS*32 + (x))
+
+#define X86_BUG_F00F			X86_BUG(0) /* Intel F00F */
+#define X86_BUG_FDIV			X86_BUG(1) /* FPU FDIV */
+#define X86_BUG_COMA			X86_BUG(2) /* Cyrix 6x86 coma */
+#define X86_BUG_AMD_TLB_MMATCH		X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */
+#define X86_BUG_AMD_APIC_C1E		X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */
+#define X86_BUG_11AP			X86_BUG(5) /* Bad local APIC aka 11AP */
+#define X86_BUG_FXSAVE_LEAK		X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
+#define X86_BUG_CLFLUSH_MONITOR		X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
+#define X86_BUG_SYSRET_SS_ATTRS		X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
 #ifdef CONFIG_X86_32
 /*
  * 64-bit kernels don't use X86_BUG_ESPFIX.  Make the define conditional
  * to avoid confusion.
  */
-#define X86_BUG_ESPFIX		X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
+#define X86_BUG_ESPFIX			X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
 #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 */
-#define X86_BUG_AMD_E400	X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+#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 */
+#define X86_BUG_AMD_E400		X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+#define X86_BUG_CPU_MELTDOWN		X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
+#define X86_BUG_SPECTRE_V1		X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
+#define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
+
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 0a3e808b9123..13c5ee878a47 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -7,6 +7,7 @@
 #include <asm/mmu.h>
 #include <asm/fixmap.h>
 #include <asm/irq_vectors.h>
+#include <asm/cpu_entry_area.h>
 
 #include <linux/smp.h>
 #include <linux/percpu.h>
@@ -20,6 +21,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in
 
 	desc->type		= (info->read_exec_only ^ 1) << 1;
 	desc->type	       |= info->contents << 2;
+	/* Set the ACCESS bit so it can be mapped RO */
+	desc->type	       |= 1;
 
 	desc->s			= 1;
 	desc->dpl		= 0x3;
@@ -60,17 +63,10 @@ static inline struct desc_struct *get_current_gdt_rw(void)
 	return this_cpu_ptr(&gdt_page)->gdt;
 }
 
-/* Get the fixmap index for a specific processor */
-static inline unsigned int get_cpu_gdt_ro_index(int cpu)
-{
-	return FIX_GDT_REMAP_BEGIN + cpu;
-}
-
 /* Provide the fixmap address of the remapped GDT */
 static inline struct desc_struct *get_cpu_gdt_ro(int cpu)
 {
-	unsigned int idx = get_cpu_gdt_ro_index(cpu);
-	return (struct desc_struct *)__fix_to_virt(idx);
+	return (struct desc_struct *)&get_cpu_entry_area(cpu)->gdt;
 }
 
 /* Provide the current read-only GDT */
@@ -185,7 +181,7 @@ static inline void set_tssldt_descriptor(void *d, unsigned long addr,
 #endif
 }
 
-static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr)
+static inline void __set_tss_desc(unsigned cpu, unsigned int entry, struct x86_hw_tss *addr)
 {
 	struct desc_struct *d = get_cpu_gdt_rw(cpu);
 	tss_desc tss;
@@ -393,7 +389,7 @@ static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit)
 void update_intr_gate(unsigned int n, const void *addr);
 void alloc_intr_gate(unsigned int n, const void *addr);
 
-extern unsigned long used_vectors[];
+extern unsigned long system_vectors[];
 
 #ifdef CONFIG_X86_64
 DECLARE_PER_CPU(u32, debug_idt_ctr);
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index c10c9128f54e..33833d1909af 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -16,6 +16,12 @@
 # define DISABLE_MPX	(1<<(X86_FEATURE_MPX & 31))
 #endif
 
+#ifdef CONFIG_X86_INTEL_UMIP
+# define DISABLE_UMIP	0
+#else
+# define DISABLE_UMIP	(1<<(X86_FEATURE_UMIP & 31))
+#endif
+
 #ifdef CONFIG_X86_64
 # define DISABLE_VME		(1<<(X86_FEATURE_VME & 31))
 # define DISABLE_K6_MTRR	(1<<(X86_FEATURE_K6_MTRR & 31))
@@ -44,6 +50,12 @@
 # define DISABLE_LA57	(1<<(X86_FEATURE_LA57 & 31))
 #endif
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define DISABLE_PTI		0
+#else
+# define DISABLE_PTI		(1 << (X86_FEATURE_PTI & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -54,7 +66,7 @@
 #define DISABLED_MASK4	(DISABLE_PCID)
 #define DISABLED_MASK5	0
 #define DISABLED_MASK6	0
-#define DISABLED_MASK7	0
+#define DISABLED_MASK7	(DISABLE_PTI)
 #define DISABLED_MASK8	0
 #define DISABLED_MASK9	(DISABLE_MPX)
 #define DISABLED_MASK10	0
@@ -63,8 +75,9 @@
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
-#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57)
+#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
 #define DISABLED_MASK17	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
+#define DISABLED_MASK18	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/dma-direct.h b/arch/x86/include/asm/dma-direct.h
new file mode 100644
index 000000000000..1295bc622ebe
--- /dev/null
+++ b/arch/x86/include/asm/dma-direct.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ASM_X86_DMA_DIRECT_H
+#define ASM_X86_DMA_DIRECT_H 1
+
+#include <linux/mem_encrypt.h>
+
+#ifdef CONFIG_X86_DMA_REMAP /* Platform code defines bridge-specific code */
+bool dma_capable(struct device *dev, dma_addr_t addr, size_t size);
+dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
+phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
+#else
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+	if (!dev->dma_mask)
+		return 0;
+
+	return addr + size - 1 <= *dev->dma_mask;
+}
+
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	return __sme_set(paddr);
+}
+
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
+{
+	return __sme_clr(daddr);
+}
+#endif /* CONFIG_X86_DMA_REMAP */
+#endif /* ASM_X86_DMA_DIRECT_H */
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 836ca1178a6a..6277c83c0eb1 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -7,13 +7,11 @@
  * Documentation/DMA-API.txt for documentation.
  */
 
-#include <linux/kmemcheck.h>
 #include <linux/scatterlist.h>
 #include <linux/dma-debug.h>
 #include <asm/io.h>
 #include <asm/swiotlb.h>
 #include <linux/dma-contiguous.h>
-#include <linux/mem_encrypt.h>
 
 #ifdef CONFIG_ISA
 # define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
@@ -32,6 +30,9 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return dma_ops;
 }
 
+int arch_dma_supported(struct device *dev, u64 mask);
+#define arch_dma_supported arch_dma_supported
+
 bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp);
 #define arch_dma_alloc_attrs arch_dma_alloc_attrs
 
@@ -43,38 +44,6 @@ extern void dma_generic_free_coherent(struct device *dev, size_t size,
 				      void *vaddr, dma_addr_t dma_addr,
 				      unsigned long attrs);
 
-#ifdef CONFIG_X86_DMA_REMAP /* Platform code defines bridge-specific code */
-extern bool dma_capable(struct device *dev, dma_addr_t addr, size_t size);
-extern dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
-extern phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
-#else
-
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return 0;
-
-	return addr + size - 1 <= *dev->dma_mask;
-}
-
-static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	return __sme_set(paddr);
-}
-
-static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
-	return __sme_clr(daddr);
-}
-#endif /* CONFIG_X86_DMA_REMAP */
-
-static inline void
-dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-	enum dma_data_direction dir)
-{
-	flush_write_buffers();
-}
-
 static inline unsigned long dma_alloc_coherent_mask(struct device *dev,
 						    gfp_t gfp)
 {
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 85f6ccb80b91..a399c1ebf6f0 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -6,6 +6,7 @@
 #include <asm/pgtable.h>
 #include <asm/processor-flags.h>
 #include <asm/tlb.h>
+#include <asm/nospec-branch.h>
 
 /*
  * We map the EFI regions needed for runtime services non-contiguously,
@@ -36,8 +37,18 @@
 
 extern asmlinkage unsigned long efi_call_phys(void *, ...);
 
-#define arch_efi_call_virt_setup()	kernel_fpu_begin()
-#define arch_efi_call_virt_teardown()	kernel_fpu_end()
+#define arch_efi_call_virt_setup()					\
+({									\
+	kernel_fpu_begin();						\
+	firmware_restrict_branch_speculation_start();			\
+})
+
+#define arch_efi_call_virt_teardown()					\
+({									\
+	firmware_restrict_branch_speculation_end();			\
+	kernel_fpu_end();						\
+})
+
 
 /*
  * Wrap all the virtual calls in a way that forces the parameters on the stack.
@@ -73,6 +84,7 @@ struct efi_scratch {
 	efi_sync_low_kernel_mappings();					\
 	preempt_disable();						\
 	__kernel_fpu_begin();						\
+	firmware_restrict_branch_speculation_start();			\
 									\
 	if (efi_scratch.use_pgd) {					\
 		efi_scratch.prev_cr3 = __read_cr3();			\
@@ -91,6 +103,7 @@ struct efi_scratch {
 		__flush_tlb_all();					\
 	}								\
 									\
+	firmware_restrict_branch_speculation_end();			\
 	__kernel_fpu_end();						\
 	preempt_enable();						\
 })
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index c1a125e47ff3..0d157d2a1e2a 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -253,7 +253,7 @@ extern int force_personality32;
  * space open for things that want to use the area for 32-bit pointers.
  */
 #define ELF_ET_DYN_BASE		(mmap_is_ia32() ? 0x000400000UL : \
-						  (TASK_SIZE / 3 * 2))
+						  (DEFAULT_MAP_WINDOW / 3 * 2))
 
 /* This yields a mask that user programs can use to figure out what
    instruction set this CPU supports.  This could be done in user space,
@@ -309,6 +309,7 @@ static inline int mmap_is_ia32(void)
 extern unsigned long task_size_32bit(void);
 extern unsigned long task_size_64bit(int full_addr_space);
 extern unsigned long get_mmap_base(int is_legacy);
+extern bool mmap_address_hint_valid(unsigned long addr, unsigned long len);
 
 #ifdef CONFIG_X86_32
 
diff --git a/arch/x86/include/asm/error-injection.h b/arch/x86/include/asm/error-injection.h
new file mode 100644
index 000000000000..47b7a1296245
--- /dev/null
+++ b/arch/x86/include/asm/error-injection.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ERROR_INJECTION_H
+#define _ASM_ERROR_INJECTION_H
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <asm/ptrace.h>
+#include <asm-generic/error-injection.h>
+
+asmlinkage void just_return_func(void);
+void override_function_with_return(struct pt_regs *regs);
+
+#endif /* _ASM_ERROR_INJECTION_H */
diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h
index 0211029076ea..6777480d8a42 100644
--- a/arch/x86/include/asm/espfix.h
+++ b/arch/x86/include/asm/espfix.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_ESPFIX_H
 #define _ASM_X86_ESPFIX_H
 
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_X86_ESPFIX64
 
 #include <asm/percpu.h>
 
@@ -11,7 +11,8 @@ DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
 
 extern void init_espfix_bsp(void);
 extern void init_espfix_ap(int cpu);
-
-#endif /* CONFIG_X86_64 */
+#else
+static inline void init_espfix_ap(int cpu) { }
+#endif
 
 #endif /* _ASM_X86_ESPFIX_H */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index dcd9fb55e679..e203169931c7 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -44,7 +44,6 @@ extern unsigned long __FIXADDR_TOP;
 			 PAGE_SIZE)
 #endif
 
-
 /*
  * Here we define all the compile-time 'special' virtual
  * addresses. The point is to have a constant address at
@@ -84,7 +83,6 @@ enum fixed_addresses {
 	FIX_IO_APIC_BASE_0,
 	FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
 #endif
-	FIX_RO_IDT,	/* Virtual mapping for read-only IDT */
 #ifdef CONFIG_X86_32
 	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
 	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
@@ -100,9 +98,12 @@ enum fixed_addresses {
 #ifdef	CONFIG_X86_INTEL_MID
 	FIX_LNW_VRTC,
 #endif
-	/* Fixmap entries to remap the GDTs, one per processor. */
-	FIX_GDT_REMAP_BEGIN,
-	FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1,
+
+#ifdef CONFIG_ACPI_APEI_GHES
+	/* Used for GHES mapping from assorted contexts */
+	FIX_APEI_GHES_IRQ,
+	FIX_APEI_GHES_NMI,
+#endif
 
 	__end_of_permanent_fixed_addresses,
 
@@ -136,8 +137,10 @@ enum fixed_addresses {
 
 extern void reserve_top_address(unsigned long reserve);
 
-#define FIXADDR_SIZE	(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_SIZE		(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
 #define FIXADDR_START		(FIXADDR_TOP - FIXADDR_SIZE)
+#define FIXADDR_TOT_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_TOT_START	(FIXADDR_TOP - FIXADDR_TOT_SIZE)
 
 extern int fixmaps_set;
 
diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h
index 4df2754ef380..44bbc39a57b3 100644
--- a/arch/x86/include/asm/fpu/signal.h
+++ b/arch/x86/include/asm/fpu/signal.h
@@ -20,12 +20,6 @@ int ia32_setup_frame(int sig, struct ksignal *ksig,
 # define ia32_setup_rt_frame	__setup_rt_frame
 #endif
 
-#ifdef CONFIG_COMPAT
-int __copy_siginfo_to_user32(compat_siginfo_t __user *to,
-		const siginfo_t *from, bool x32_ABI);
-#endif
-
-
 extern void convert_from_fxsr(struct user_i387_ia32_struct *env,
 			      struct task_struct *tsk);
 extern void convert_to_fxsr(struct task_struct *tsk,
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 51cc979dd364..7c341a74ec8c 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -38,6 +38,9 @@ typedef struct {
 #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
 	unsigned int irq_hv_callback_count;
 #endif
+#if IS_ENABLED(CONFIG_HYPERV)
+	unsigned int irq_hv_reenlightenment_count;
+#endif
 } ____cacheline_aligned irq_cpustat_t;
 
 DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 8ec99a55e6b9..2851077b6051 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -16,6 +16,8 @@
 
 #include <asm/irq_vectors.h>
 
+#define IRQ_MATRIX_BITS		NR_VECTORS
+
 #ifndef __ASSEMBLY__
 
 #include <linux/percpu.h>
@@ -97,14 +99,6 @@ struct irq_alloc_info {
 			void		*dmar_data;
 		};
 #endif
-#ifdef	CONFIG_HT_IRQ
-		struct {
-			int		ht_pos;
-			int		ht_idx;
-			struct pci_dev	*ht_dev;
-			void		*ht_update;
-		};
-#endif
 #ifdef	CONFIG_X86_UV
 		struct {
 			int		uv_limit;
@@ -123,15 +117,13 @@ struct irq_alloc_info {
 
 struct irq_cfg {
 	unsigned int		dest_apicid;
-	u8			vector;
-	u8			old_vector;
+	unsigned int		vector;
 };
 
 extern struct irq_cfg *irq_cfg(unsigned int irq);
 extern struct irq_cfg *irqd_cfg(struct irq_data *irq_data);
 extern void lock_vector_lock(void);
 extern void unlock_vector_lock(void);
-extern void setup_vector_irq(int cpu);
 #ifdef CONFIG_SMP
 extern void send_cleanup_vector(struct irq_cfg *);
 extern void irq_complete_move(struct irq_cfg *cfg);
diff --git a/arch/x86/include/asm/hypertransport.h b/arch/x86/include/asm/hypertransport.h
deleted file mode 100644
index 5d55df352879..000000000000
--- a/arch/x86/include/asm/hypertransport.h
+++ /dev/null
@@ -1,46 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_HYPERTRANSPORT_H
-#define _ASM_X86_HYPERTRANSPORT_H
-
-/*
- * Constants for x86 Hypertransport Interrupts.
- */
-
-#define HT_IRQ_LOW_BASE			0xf8000000
-
-#define HT_IRQ_LOW_VECTOR_SHIFT		16
-#define HT_IRQ_LOW_VECTOR_MASK		0x00ff0000
-#define HT_IRQ_LOW_VECTOR(v)						\
-	(((v) << HT_IRQ_LOW_VECTOR_SHIFT) & HT_IRQ_LOW_VECTOR_MASK)
-
-#define HT_IRQ_LOW_DEST_ID_SHIFT	8
-#define HT_IRQ_LOW_DEST_ID_MASK		0x0000ff00
-#define HT_IRQ_LOW_DEST_ID(v)						\
-	(((v) << HT_IRQ_LOW_DEST_ID_SHIFT) & HT_IRQ_LOW_DEST_ID_MASK)
-
-#define HT_IRQ_LOW_DM_PHYSICAL		0x0000000
-#define HT_IRQ_LOW_DM_LOGICAL		0x0000040
-
-#define HT_IRQ_LOW_RQEOI_EDGE		0x0000000
-#define HT_IRQ_LOW_RQEOI_LEVEL		0x0000020
-
-
-#define HT_IRQ_LOW_MT_FIXED		0x0000000
-#define HT_IRQ_LOW_MT_ARBITRATED	0x0000004
-#define HT_IRQ_LOW_MT_SMI		0x0000008
-#define HT_IRQ_LOW_MT_NMI		0x000000c
-#define HT_IRQ_LOW_MT_INIT		0x0000010
-#define HT_IRQ_LOW_MT_STARTUP		0x0000014
-#define HT_IRQ_LOW_MT_EXTINT		0x0000018
-#define HT_IRQ_LOW_MT_LINT1		0x000008c
-#define HT_IRQ_LOW_MT_LINT0		0x0000098
-
-#define HT_IRQ_LOW_IRQ_MASKED		0x0000001
-
-
-#define HT_IRQ_HIGH_DEST_ID_SHIFT	0
-#define HT_IRQ_HIGH_DEST_ID_MASK	0x00ffffff
-#define HT_IRQ_HIGH_DEST_ID(v)						\
-	((((v) >> 8) << HT_IRQ_HIGH_DEST_ID_SHIFT) & HT_IRQ_HIGH_DEST_ID_MASK)
-
-#endif /* _ASM_X86_HYPERTRANSPORT_H */
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index 0ead9dbb9130..8c5aaba6633f 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -20,14 +20,23 @@
 #ifndef _ASM_X86_HYPERVISOR_H
 #define _ASM_X86_HYPERVISOR_H
 
+/* x86 hypervisor types  */
+enum x86_hypervisor_type {
+	X86_HYPER_NATIVE = 0,
+	X86_HYPER_VMWARE,
+	X86_HYPER_MS_HYPERV,
+	X86_HYPER_XEN_PV,
+	X86_HYPER_XEN_HVM,
+	X86_HYPER_KVM,
+	X86_HYPER_JAILHOUSE,
+};
+
 #ifdef CONFIG_HYPERVISOR_GUEST
 
 #include <asm/kvm_para.h>
+#include <asm/x86_init.h>
 #include <asm/xen/hypervisor.h>
 
-/*
- * x86 hypervisor information
- */
 struct hypervisor_x86 {
 	/* Hypervisor name */
 	const char	*name;
@@ -35,40 +44,27 @@ struct hypervisor_x86 {
 	/* Detection routine */
 	uint32_t	(*detect)(void);
 
-	/* Platform setup (run once per boot) */
-	void		(*init_platform)(void);
-
-	/* X2APIC detection (run once per boot) */
-	bool		(*x2apic_available)(void);
+	/* Hypervisor type */
+	enum x86_hypervisor_type type;
 
-	/* pin current vcpu to specified physical cpu (run rarely) */
-	void		(*pin_vcpu)(int);
+	/* init time callbacks */
+	struct x86_hyper_init init;
 
-	/* called during init_mem_mapping() to setup early mappings. */
-	void		(*init_mem_mapping)(void);
+	/* runtime callbacks */
+	struct x86_hyper_runtime runtime;
 };
 
-extern const struct hypervisor_x86 *x86_hyper;
-
-/* Recognized hypervisors */
-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_xen_hvm;
-extern const struct hypervisor_x86 x86_hyper_kvm;
-
+extern enum x86_hypervisor_type x86_hyper_type;
 extern void init_hypervisor_platform(void);
-extern bool hypervisor_x2apic_available(void);
-extern void hypervisor_pin_vcpu(int cpu);
-
-static inline void hypervisor_init_mem_mapping(void)
+static inline bool hypervisor_is_type(enum x86_hypervisor_type type)
 {
-	if (x86_hyper && x86_hyper->init_mem_mapping)
-		x86_hyper->init_mem_mapping();
+	return x86_hyper_type == type;
 }
 #else
 static inline void init_hypervisor_platform(void) { }
-static inline bool hypervisor_x2apic_available(void) { return false; }
-static inline void hypervisor_init_mem_mapping(void) { }
+static inline bool hypervisor_is_type(enum x86_hypervisor_type type)
+{
+	return type == X86_HYPER_NATIVE;
+}
 #endif /* CONFIG_HYPERVISOR_GUEST */
 #endif /* _ASM_X86_HYPERVISOR_H */
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index c8376b40e882..5cdcdbd4d892 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -69,6 +69,11 @@ struct legacy_pic {
 extern struct legacy_pic *legacy_pic;
 extern struct legacy_pic null_legacy_pic;
 
+static inline bool has_legacy_pic(void)
+{
+	return legacy_pic != &null_legacy_pic;
+}
+
 static inline int nr_legacy_irqs(void)
 {
 	return legacy_pic->nr_legacy_irqs;
diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h
index 02aff0867211..1c78580e58be 100644
--- a/arch/x86/include/asm/inat.h
+++ b/arch/x86/include/asm/inat.h
@@ -97,6 +97,16 @@
 #define INAT_MAKE_GROUP(grp)	((grp << INAT_GRP_OFFS) | INAT_MODRM)
 #define INAT_MAKE_IMM(imm)	(imm << INAT_IMM_OFFS)
 
+/* Identifiers for segment registers */
+#define INAT_SEG_REG_IGNORE	0
+#define INAT_SEG_REG_DEFAULT	1
+#define INAT_SEG_REG_CS		2
+#define INAT_SEG_REG_SS		3
+#define INAT_SEG_REG_DS		4
+#define INAT_SEG_REG_ES		5
+#define INAT_SEG_REG_FS		6
+#define INAT_SEG_REG_GS		7
+
 /* Attribute search APIs */
 extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
 extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h
new file mode 100644
index 000000000000..2b6ccf2c49f1
--- /dev/null
+++ b/arch/x86/include/asm/insn-eval.h
@@ -0,0 +1,23 @@
+#ifndef _ASM_X86_INSN_EVAL_H
+#define _ASM_X86_INSN_EVAL_H
+/*
+ * A collection of utility functions for x86 instruction analysis to be
+ * used in a kernel context. Useful when, for instance, making sense
+ * of the registers indicated by operands.
+ */
+
+#include <linux/compiler.h>
+#include <linux/bug.h>
+#include <linux/err.h>
+#include <asm/ptrace.h>
+
+#define INSN_CODE_SEG_ADDR_SZ(params) ((params >> 4) & 0xf)
+#define INSN_CODE_SEG_OPND_SZ(params) (params & 0xf)
+#define INSN_CODE_SEG_PARAMS(oper_sz, addr_sz) (oper_sz | (addr_sz << 4))
+
+void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs);
+int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs);
+unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx);
+int insn_get_code_seg_params(struct pt_regs *regs);
+
+#endif /* _ASM_X86_INSN_EVAL_H */
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 35a6bc4da8ad..cf090e584202 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -10,6 +10,10 @@
  *
  * Things ending in "2" are usually because we have no better
  * name for them.  There's no processor called "SILVERMONT2".
+ *
+ * While adding a new CPUID for a new microarchitecture, add a new
+ * group to keep logically sorted out in chronological order. Within
+ * that group keep the CPUID for the variants sorted by model number.
  */
 
 #define INTEL_FAM6_CORE_YONAH		0x0E
@@ -49,6 +53,8 @@
 #define INTEL_FAM6_KABYLAKE_MOBILE	0x8E
 #define INTEL_FAM6_KABYLAKE_DESKTOP	0x9E
 
+#define INTEL_FAM6_CANNONLAKE_MOBILE	0x66
+
 /* "Small Core" Processors (Atom) */
 
 #define INTEL_FAM6_ATOM_PINEVIEW	0x1C
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
new file mode 100644
index 000000000000..62a9f4966b42
--- /dev/null
+++ b/arch/x86/include/asm/intel_ds.h
@@ -0,0 +1,36 @@
+#ifndef _ASM_INTEL_DS_H
+#define _ASM_INTEL_DS_H
+
+#include <linux/percpu-defs.h>
+
+#define BTS_BUFFER_SIZE		(PAGE_SIZE << 4)
+#define PEBS_BUFFER_SIZE	(PAGE_SIZE << 4)
+
+/* The maximal number of PEBS events: */
+#define MAX_PEBS_EVENTS		8
+
+/*
+ * A debug store configuration.
+ *
+ * We only support architectures that use 64bit fields.
+ */
+struct debug_store {
+	u64	bts_buffer_base;
+	u64	bts_index;
+	u64	bts_absolute_maximum;
+	u64	bts_interrupt_threshold;
+	u64	pebs_buffer_base;
+	u64	pebs_index;
+	u64	pebs_absolute_maximum;
+	u64	pebs_interrupt_threshold;
+	u64	pebs_event_reset[MAX_PEBS_EVENTS];
+} __aligned(PAGE_SIZE);
+
+DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
+
+struct debug_store_buffers {
+	char	bts_buffer[BTS_BUFFER_SIZE];
+	char	pebs_buffer[PEBS_BUFFER_SIZE];
+};
+
+#endif
diff --git a/arch/x86/include/asm/intel_pmc_ipc.h b/arch/x86/include/asm/intel_pmc_ipc.h
index 528ed4be4393..9e7adcdbe031 100644
--- a/arch/x86/include/asm/intel_pmc_ipc.h
+++ b/arch/x86/include/asm/intel_pmc_ipc.h
@@ -38,6 +38,7 @@ int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen,
 		u32 *out, u32 outlen);
 int intel_pmc_s0ix_counter_read(u64 *data);
 int intel_pmc_gcr_read(u32 offset, u32 *data);
+int intel_pmc_gcr_read64(u32 offset, u64 *data);
 int intel_pmc_gcr_write(u32 offset, u32 data);
 int intel_pmc_gcr_update(u32 offset, u32 mask, u32 val);
 
@@ -70,6 +71,11 @@ static inline int intel_pmc_gcr_read(u32 offset, u32 *data)
 	return -EINVAL;
 }
 
+static inline int intel_pmc_gcr_read64(u32 offset, u64 *data)
+{
+	return -EINVAL;
+}
+
 static inline int intel_pmc_gcr_write(u32 offset, u32 data)
 {
 	return -EINVAL;
diff --git a/arch/x86/include/asm/invpcid.h b/arch/x86/include/asm/invpcid.h
new file mode 100644
index 000000000000..989cfa86de85
--- /dev/null
+++ b/arch/x86/include/asm/invpcid.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_INVPCID
+#define _ASM_X86_INVPCID
+
+static inline void __invpcid(unsigned long pcid, unsigned long addr,
+			     unsigned long type)
+{
+	struct { u64 d[2]; } desc = { { pcid, addr } };
+
+	/*
+	 * The memory clobber is because the whole point is to invalidate
+	 * stale TLB entries and, especially if we're flushing global
+	 * mappings, we don't want the compiler to reorder any subsequent
+	 * memory accesses before the TLB flush.
+	 *
+	 * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
+	 * invpcid (%rcx), %rax in long mode.
+	 */
+	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
+		      : : "m" (desc), "a" (type), "c" (&desc) : "memory");
+}
+
+#define INVPCID_TYPE_INDIV_ADDR		0
+#define INVPCID_TYPE_SINGLE_CTXT	1
+#define INVPCID_TYPE_ALL_INCL_GLOBAL	2
+#define INVPCID_TYPE_ALL_NON_GLOBAL	3
+
+/* Flush all mappings for a given pcid and addr, not including globals. */
+static inline void invpcid_flush_one(unsigned long pcid,
+				     unsigned long addr)
+{
+	__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invpcid_flush_single_context(unsigned long pcid)
+{
+	__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
+static inline void invpcid_flush_all(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invpcid_flush_all_nonglobals(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+}
+
+#endif /* _ASM_X86_INVPCID */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 11398d55aefa..95e948627fd0 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -111,6 +111,10 @@ build_mmio_write(__writeq, "q", unsigned long, "r", )
 
 #endif
 
+#define ARCH_HAS_VALID_PHYS_ADDR_RANGE
+extern int valid_phys_addr_range(phys_addr_t addr, size_t size);
+extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
+
 /**
  *	virt_to_phys	-	map virtual addresses to physical
  *	@address: address to remap
@@ -266,6 +270,21 @@ static inline void slow_down_io(void)
 
 #endif
 
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+#include <linux/jump_label.h>
+
+extern struct static_key_false sev_enable_key;
+static inline bool sev_key_active(void)
+{
+	return static_branch_unlikely(&sev_enable_key);
+}
+
+#else /* !CONFIG_AMD_MEM_ENCRYPT */
+
+static inline bool sev_key_active(void) { return false; }
+
+#endif /* CONFIG_AMD_MEM_ENCRYPT */
+
 #define BUILDIO(bwl, bw, type)						\
 static inline void out##bwl(unsigned type value, int port)		\
 {									\
@@ -296,14 +315,34 @@ static inline unsigned type in##bwl##_p(int port)			\
 									\
 static inline void outs##bwl(int port, const void *addr, unsigned long count) \
 {									\
-	asm volatile("rep; outs" #bwl					\
-		     : "+S"(addr), "+c"(count) : "d"(port) : "memory");	\
+	if (sev_key_active()) {						\
+		unsigned type *value = (unsigned type *)addr;		\
+		while (count) {						\
+			out##bwl(*value, port);				\
+			value++;					\
+			count--;					\
+		}							\
+	} else {							\
+		asm volatile("rep; outs" #bwl				\
+			     : "+S"(addr), "+c"(count)			\
+			     : "d"(port) : "memory");			\
+	}								\
 }									\
 									\
 static inline void ins##bwl(int port, void *addr, unsigned long count)	\
 {									\
-	asm volatile("rep; ins" #bwl					\
-		     : "+D"(addr), "+c"(count) : "d"(port) : "memory");	\
+	if (sev_key_active()) {						\
+		unsigned type *value = (unsigned type *)addr;		\
+		while (count) {						\
+			*value = in##bwl(port);				\
+			value++;					\
+			count--;					\
+		}							\
+	} else {							\
+		asm volatile("rep; ins" #bwl				\
+			     : "+D"(addr), "+c"(count)			\
+			     : "d"(port) : "memory");			\
+	}								\
 }
 
 BUILDIO(b, b, char)
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 5c27e146a166..a8834dd546cd 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -193,7 +193,6 @@ static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
 extern void setup_IO_APIC(void);
 extern void enable_IO_APIC(void);
 extern void disable_IO_APIC(void);
-extern void setup_ioapic_dest(void);
 extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin);
 extern void print_IO_APICs(void);
 #else  /* !CONFIG_X86_IO_APIC */
@@ -233,7 +232,6 @@ static inline void io_apic_init_mappings(void) { }
 
 static inline void setup_IO_APIC(void) { }
 static inline void enable_IO_APIC(void) { }
-static inline void setup_ioapic_dest(void) { }
 
 #endif
 
diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h
index 7d87437bd030..3de0489deade 100644
--- a/arch/x86/include/asm/iosf_mbi.h
+++ b/arch/x86/include/asm/iosf_mbi.h
@@ -147,6 +147,18 @@ int iosf_mbi_register_pmic_bus_access_notifier(struct notifier_block *nb);
 int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb);
 
 /**
+ * iosf_mbi_unregister_pmic_bus_access_notifier_unlocked - Unregister PMIC bus
+ *                                                         notifier, unlocked
+ *
+ * Like iosf_mbi_unregister_pmic_bus_access_notifier(), but for use when the
+ * caller has already called iosf_mbi_punit_acquire() itself.
+ *
+ * @nb: notifier_block to unregister
+ */
+int iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(
+	struct notifier_block *nb);
+
+/**
  * iosf_mbi_call_pmic_bus_access_notifier_chain - Call PMIC bus notifier chain
  *
  * @val: action to pass into listener's notifier_call function
@@ -154,6 +166,11 @@ int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb);
  */
 int iosf_mbi_call_pmic_bus_access_notifier_chain(unsigned long val, void *v);
 
+/**
+ * iosf_mbi_assert_punit_acquired - Assert that the P-Unit has been acquired.
+ */
+void iosf_mbi_assert_punit_acquired(void);
+
 #else /* CONFIG_IOSF_MBI is not enabled */
 static inline
 bool iosf_mbi_available(void)
@@ -197,12 +214,20 @@ int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb)
 	return 0;
 }
 
+static inline int
+iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(struct notifier_block *nb)
+{
+	return 0;
+}
+
 static inline
 int iosf_mbi_call_pmic_bus_access_notifier_chain(unsigned long val, void *v)
 {
 	return 0;
 }
 
+static inline void iosf_mbi_assert_punit_acquired(void) {}
+
 #endif /* CONFIG_IOSF_MBI */
 
 #endif /* IOSF_MBI_SYMS_H */
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index d8632f8fa17d..2395bb794c7b 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -26,11 +26,7 @@ extern void irq_ctx_init(int cpu);
 
 struct irq_desc;
 
-#ifdef CONFIG_HOTPLUG_CPU
-#include <linux/cpumask.h>
-extern int check_irq_vectors_for_cpu_disable(void);
 extern void fixup_irqs(void);
-#endif
 
 #ifdef CONFIG_HAVE_KVM
 extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void));
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index c20ffca8fef1..e71c1120426b 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -102,12 +102,13 @@
 #define POSTED_INTR_NESTED_VECTOR	0xf0
 #endif
 
-/*
- * Local APIC timer IRQ vector is on a different priority level,
- * to work around the 'lost local interrupt if more than 2 IRQ
- * sources per level' errata.
- */
-#define LOCAL_TIMER_VECTOR		0xef
+#define MANAGED_IRQ_SHUTDOWN_VECTOR	0xef
+
+#if IS_ENABLED(CONFIG_HYPERV)
+#define HYPERV_REENLIGHTENMENT_VECTOR	0xee
+#endif
+
+#define LOCAL_TIMER_VECTOR		0xed
 
 #define NR_VECTORS			 256
 
diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h
index 423e112c1e8f..c066ffae222b 100644
--- a/arch/x86/include/asm/irqdomain.h
+++ b/arch/x86/include/asm/irqdomain.h
@@ -9,6 +9,7 @@
 enum {
 	/* Allocate contiguous CPU vectors */
 	X86_IRQ_ALLOC_CONTIGUOUS_VECTORS		= 0x1,
+	X86_IRQ_ALLOC_LEGACY				= 0x2,
 };
 
 extern struct irq_domain *x86_vector_domain;
@@ -42,8 +43,8 @@ extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
 			      unsigned int nr_irqs, void *arg);
 extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
 			      unsigned int nr_irqs);
-extern void mp_irqdomain_activate(struct irq_domain *domain,
-				  struct irq_data *irq_data);
+extern int mp_irqdomain_activate(struct irq_domain *domain,
+				 struct irq_data *irq_data, bool reserve);
 extern void mp_irqdomain_deactivate(struct irq_domain *domain,
 				    struct irq_data *irq_data);
 extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain);
@@ -55,10 +56,4 @@ extern void arch_init_msi_domain(struct irq_domain *domain);
 static inline void arch_init_msi_domain(struct irq_domain *domain) { }
 #endif
 
-#ifdef CONFIG_HT_IRQ
-extern void arch_init_htirq_domain(struct irq_domain *domain);
-#else
-static inline void arch_init_htirq_domain(struct irq_domain *domain) { }
-#endif
-
 #endif
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index c8ef23f2c28f..89f08955fff7 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -142,6 +142,9 @@ static inline notrace unsigned long arch_local_irq_save(void)
 	swapgs;					\
 	sysretl
 
+#ifdef CONFIG_DEBUG_ENTRY
+#define SAVE_FLAGS(x)		pushfq; popq %rax
+#endif
 #else
 #define INTERRUPT_RETURN		iret
 #define ENABLE_INTERRUPTS_SYSEXIT	sti; sysexit
diff --git a/arch/x86/include/asm/jailhouse_para.h b/arch/x86/include/asm/jailhouse_para.h
new file mode 100644
index 000000000000..875b54376689
--- /dev/null
+++ b/arch/x86/include/asm/jailhouse_para.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL2.0 */
+
+/*
+ * Jailhouse paravirt_ops implementation
+ *
+ * Copyright (c) Siemens AG, 2015-2017
+ *
+ * Authors:
+ *  Jan Kiszka <jan.kiszka@siemens.com>
+ */
+
+#ifndef _ASM_X86_JAILHOUSE_PARA_H
+#define _ASM_X86_JAILHOUSE_PARA_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_JAILHOUSE_GUEST
+bool jailhouse_paravirt(void);
+#else
+static inline bool jailhouse_paravirt(void)
+{
+	return false;
+}
+#endif
+
+#endif /* _ASM_X86_JAILHOUSE_PARA_H */
diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h
index b577dd0916aa..13e70da38bed 100644
--- a/arch/x86/include/asm/kasan.h
+++ b/arch/x86/include/asm/kasan.h
@@ -4,6 +4,7 @@
 
 #include <linux/const.h>
 #define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
+#define KASAN_SHADOW_SCALE_SHIFT 3
 
 /*
  * Compiler uses shadow offset assuming that addresses start
@@ -12,12 +13,15 @@
  * 'kernel address space start' >> KASAN_SHADOW_SCALE_SHIFT
  */
 #define KASAN_SHADOW_START      (KASAN_SHADOW_OFFSET + \
-					((-1UL << __VIRTUAL_MASK_SHIFT) >> 3))
+					((-1UL << __VIRTUAL_MASK_SHIFT) >> \
+						KASAN_SHADOW_SCALE_SHIFT))
 /*
- * 47 bits for kernel address -> (47 - 3) bits for shadow
- * 56 bits for kernel address -> (56 - 3) bits for shadow
+ * 47 bits for kernel address -> (47 - KASAN_SHADOW_SCALE_SHIFT) bits for shadow
+ * 56 bits for kernel address -> (56 - KASAN_SHADOW_SCALE_SHIFT) bits for shadow
  */
-#define KASAN_SHADOW_END        (KASAN_SHADOW_START + (1ULL << (__VIRTUAL_MASK_SHIFT - 3)))
+#define KASAN_SHADOW_END        (KASAN_SHADOW_START + \
+					(1ULL << (__VIRTUAL_MASK_SHIFT - \
+						  KASAN_SHADOW_SCALE_SHIFT)))
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index f86a8caa561e..395c9631e000 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -26,6 +26,7 @@ extern void die(const char *, struct pt_regs *,long);
 extern int __must_check __die(const char *, struct pt_regs *, long);
 extern void show_stack_regs(struct pt_regs *regs);
 extern void __show_regs(struct pt_regs *regs, int all);
+extern void show_iret_regs(struct pt_regs *regs);
 extern unsigned long oops_begin(void);
 extern void oops_end(unsigned long, struct pt_regs *, int signr);
 
diff --git a/arch/x86/include/asm/kmemcheck.h b/arch/x86/include/asm/kmemcheck.h
deleted file mode 100644
index 945a0337fbcf..000000000000
--- a/arch/x86/include/asm/kmemcheck.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ASM_X86_KMEMCHECK_H
-#define ASM_X86_KMEMCHECK_H
-
-#include <linux/types.h>
-#include <asm/ptrace.h>
-
-#ifdef CONFIG_KMEMCHECK
-bool kmemcheck_active(struct pt_regs *regs);
-
-void kmemcheck_show(struct pt_regs *regs);
-void kmemcheck_hide(struct pt_regs *regs);
-
-bool kmemcheck_fault(struct pt_regs *regs,
-	unsigned long address, unsigned long error_code);
-bool kmemcheck_trap(struct pt_regs *regs);
-#else
-static inline bool kmemcheck_active(struct pt_regs *regs)
-{
-	return false;
-}
-
-static inline void kmemcheck_show(struct pt_regs *regs)
-{
-}
-
-static inline void kmemcheck_hide(struct pt_regs *regs)
-{
-}
-
-static inline bool kmemcheck_fault(struct pt_regs *regs,
-	unsigned long address, unsigned long error_code)
-{
-	return false;
-}
-
-static inline bool kmemcheck_trap(struct pt_regs *regs)
-{
-	return false;
-}
-#endif /* CONFIG_KMEMCHECK */
-
-#endif
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 6cf65437b5e5..367d99cff426 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -58,8 +58,8 @@ extern __visible kprobe_opcode_t optprobe_template_call[];
 extern __visible kprobe_opcode_t optprobe_template_end[];
 #define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + RELATIVE_ADDR_SIZE)
 #define MAX_OPTINSN_SIZE 				\
-	(((unsigned long)&optprobe_template_end -	\
-	  (unsigned long)&optprobe_template_entry) +	\
+	(((unsigned long)optprobe_template_end -	\
+	  (unsigned long)optprobe_template_entry) +	\
 	 MAX_OPTIMIZED_LENGTH + RELATIVEJUMP_SIZE)
 
 extern const int kretprobe_blacklist_size;
@@ -67,6 +67,8 @@ extern const int kretprobe_blacklist_size;
 void arch_remove_kprobe(struct kprobe *p);
 asmlinkage void kretprobe_trampoline(void);
 
+extern void arch_kprobe_override_function(struct pt_regs *regs);
+
 /* Architecture specific copy of original instruction*/
 struct arch_specific_insn {
 	/* copy of the original instruction */
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index ee23a43386a2..b24b1c8b3979 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -214,8 +214,6 @@ struct x86_emulate_ops {
 	void (*halt)(struct x86_emulate_ctxt *ctxt);
 	void (*wbinvd)(struct x86_emulate_ctxt *ctxt);
 	int (*fix_hypercall)(struct x86_emulate_ctxt *ctxt);
-	void (*get_fpu)(struct x86_emulate_ctxt *ctxt); /* disables preempt */
-	void (*put_fpu)(struct x86_emulate_ctxt *ctxt); /* reenables preempt */
 	int (*intercept)(struct x86_emulate_ctxt *ctxt,
 			 struct x86_instruction_info *info,
 			 enum x86_intercept_stage stage);
@@ -226,6 +224,8 @@ struct x86_emulate_ops {
 
 	unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
 	void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags);
+	int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, u64 smbase);
+
 };
 
 typedef u32 __attribute__((vector_size(16))) sse128_t;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c73e493adf07..b605a5b6a30c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -86,7 +86,7 @@
 			  | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \
 			  | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \
 			  | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \
-			  | X86_CR4_SMAP | X86_CR4_PKE))
+			  | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP))
 
 #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
 
@@ -504,8 +504,10 @@ struct kvm_vcpu_arch {
 	int mp_state;
 	u64 ia32_misc_enable_msr;
 	u64 smbase;
+	u64 smi_count;
 	bool tpr_access_reporting;
 	u64 ia32_xss;
+	u64 microcode_version;
 
 	/*
 	 * Paging state of the vcpu
@@ -536,7 +538,20 @@ struct kvm_vcpu_arch {
 	struct kvm_mmu_memory_cache mmu_page_cache;
 	struct kvm_mmu_memory_cache mmu_page_header_cache;
 
+	/*
+	 * QEMU userspace and the guest each have their own FPU state.
+	 * 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;
 	u64 guest_supported_xcr0;
 	u32 guest_xstate_size;
@@ -747,6 +762,15 @@ enum kvm_irqchip_mode {
 	KVM_IRQCHIP_SPLIT,        /* created with KVM_CAP_SPLIT_IRQCHIP */
 };
 
+struct kvm_sev_info {
+	bool active;		/* SEV enabled guest */
+	unsigned int asid;	/* ASID used for this guest */
+	unsigned int handle;	/* SEV firmware handle */
+	int fd;			/* SEV device fd */
+	unsigned long pages_locked; /* Number of pages locked */
+	struct list_head regions_list;  /* List of registered regions */
+};
+
 struct kvm_arch {
 	unsigned int n_used_mmu_pages;
 	unsigned int n_requested_mmu_pages;
@@ -834,6 +858,8 @@ struct kvm_arch {
 
 	bool x2apic_format;
 	bool x2apic_broadcast_quirk_disabled;
+
+	struct kvm_sev_info sev_info;
 };
 
 struct kvm_vm_stat {
@@ -870,7 +896,6 @@ struct kvm_vcpu_stat {
 	u64 request_irq_exits;
 	u64 irq_exits;
 	u64 host_state_reload;
-	u64 efer_reload;
 	u64 fpu_reload;
 	u64 insn_emulation;
 	u64 insn_emulation_fail;
@@ -952,7 +977,7 @@ struct kvm_x86_ops {
 	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
 	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
 
-	void (*tlb_flush)(struct kvm_vcpu *vcpu);
+	void (*tlb_flush)(struct kvm_vcpu *vcpu, bool invalidate_gpa);
 
 	void (*run)(struct kvm_vcpu *vcpu);
 	int (*handle_exit)(struct kvm_vcpu *vcpu);
@@ -1004,6 +1029,7 @@ struct kvm_x86_ops {
 	void (*handle_external_intr)(struct kvm_vcpu *vcpu);
 	bool (*mpx_supported)(void);
 	bool (*xsaves_supported)(void);
+	bool (*umip_emulated)(void);
 
 	int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
 
@@ -1061,6 +1087,17 @@ struct kvm_x86_ops {
 	void (*cancel_hv_timer)(struct kvm_vcpu *vcpu);
 
 	void (*setup_mce)(struct kvm_vcpu *vcpu);
+
+	int (*smi_allowed)(struct kvm_vcpu *vcpu);
+	int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
+	int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase);
+	int (*enable_smi_window)(struct kvm_vcpu *vcpu);
+
+	int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
+	int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
+	int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp);
+
+	int (*get_msr_feature)(struct kvm_msr_entry *entry);
 };
 
 struct kvm_arch_async_pf {
@@ -1156,7 +1193,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
 static inline int emulate_instruction(struct kvm_vcpu *vcpu,
 			int emulation_type)
 {
-	return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0);
+	return x86_emulate_instruction(vcpu, 0,
+			emulation_type | EMULTYPE_NO_REEXECUTE, NULL, 0);
 }
 
 void kvm_enable_efer_bits(u64);
@@ -1419,11 +1457,14 @@ static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
 static inline int kvm_cpu_get_apicid(int mps_cpu)
 {
 #ifdef CONFIG_X86_LOCAL_APIC
-	return __default_cpu_present_to_apicid(mps_cpu);
+	return default_cpu_present_to_apicid(mps_cpu);
 #else
 	WARN_ON_ONCE(1);
 	return BAD_APICID;
 #endif
 }
 
+#define put_smstate(type, buf, offset, val)                      \
+	*(type *)((buf) + (offset) - 0x7e00) = val
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index c373e44049b1..7b407dda2bd7 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -88,7 +88,6 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
 #ifdef CONFIG_KVM_GUEST
 bool kvm_para_available(void);
 unsigned int kvm_arch_para_features(void);
-void __init kvm_guest_init(void);
 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);
@@ -103,7 +102,6 @@ static inline void kvm_spinlock_init(void)
 #endif /* CONFIG_PARAVIRT_SPINLOCKS */
 
 #else /* CONFIG_KVM_GUEST */
-#define kvm_guest_init() do {} while (0)
 #define kvm_async_pf_task_wait(T, I) do {} while(0)
 #define kvm_async_pf_task_wake(T) do {} while(0)
 
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index b1e8d8db921f..96ea4b5ba658 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -376,6 +376,7 @@ struct smca_bank {
 extern struct smca_bank smca_banks[MAX_NR_BANKS];
 
 extern const char *smca_get_long_name(enum smca_bank_types t);
+extern bool amd_mce_is_memory_error(struct mce *m);
 
 extern int mce_threshold_create_device(unsigned int cpu);
 extern int mce_threshold_remove_device(unsigned int cpu);
@@ -384,6 +385,7 @@ extern int mce_threshold_remove_device(unsigned int cpu);
 
 static inline int mce_threshold_create_device(unsigned int cpu) { return 0; };
 static inline int mce_threshold_remove_device(unsigned int cpu) { return 0; };
+static inline bool amd_mce_is_memory_error(struct mce *m) { return false; };
 
 #endif
 
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 6a77c63540f7..22c5f3e6f820 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -39,14 +39,20 @@ void __init sme_unmap_bootdata(char *real_mode_data);
 
 void __init sme_early_init(void);
 
-void __init sme_encrypt_kernel(void);
+void __init sme_encrypt_kernel(struct boot_params *bp);
 void __init sme_enable(struct boot_params *bp);
 
+int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size);
+int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size);
+
 /* Architecture __weak replacement functions */
 void __init mem_encrypt_init(void);
 
 void swiotlb_set_mem_attributes(void *vaddr, unsigned long size);
 
+bool sme_active(void);
+bool sev_active(void);
+
 #else	/* !CONFIG_AMD_MEM_ENCRYPT */
 
 #define sme_me_mask	0ULL
@@ -61,9 +67,17 @@ static inline void __init sme_unmap_bootdata(char *real_mode_data) { }
 
 static inline void __init sme_early_init(void) { }
 
-static inline void __init sme_encrypt_kernel(void) { }
+static inline void __init sme_encrypt_kernel(struct boot_params *bp) { }
 static inline void __init sme_enable(struct boot_params *bp) { }
 
+static inline bool sme_active(void) { return false; }
+static inline bool sev_active(void) { return false; }
+
+static inline int __init
+early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; }
+static inline int __init
+early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; }
+
 #endif	/* CONFIG_AMD_MEM_ENCRYPT */
 
 /*
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 55520cec8b27..7fb1047d61c7 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -37,7 +37,12 @@ struct cpu_signature {
 
 struct device;
 
-enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND };
+enum ucode_state {
+	UCODE_OK	= 0,
+	UCODE_UPDATED,
+	UCODE_NFOUND,
+	UCODE_ERROR,
+};
 
 struct microcode_ops {
 	enum ucode_state (*request_microcode_user) (int cpu,
@@ -54,7 +59,7 @@ struct microcode_ops {
 	 * are being called.
 	 * See also the "Synchronization" section in microcode_core.c.
 	 */
-	int (*apply_microcode) (int cpu);
+	enum ucode_state (*apply_microcode) (int cpu);
 	int (*collect_cpu_info) (int cpu, struct cpu_signature *csig);
 };
 
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 9ea26f167497..5ff3e8af2c20 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -3,6 +3,7 @@
 #define _ASM_X86_MMU_H
 
 #include <linux/spinlock.h>
+#include <linux/rwsem.h>
 #include <linux/mutex.h>
 #include <linux/atomic.h>
 
@@ -27,7 +28,8 @@ typedef struct {
 	atomic64_t tlb_gen;
 
 #ifdef CONFIG_MODIFY_LDT_SYSCALL
-	struct ldt_struct *ldt;
+	struct rw_semaphore	ldt_usr_sem;
+	struct ldt_struct	*ldt;
 #endif
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 6699fc441644..1de72ce514cd 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -50,22 +50,54 @@ struct ldt_struct {
 	 * call gates.  On native, we could merge the ldt_struct and LDT
 	 * allocations, but it's not worth trying to optimize.
 	 */
-	struct desc_struct *entries;
-	unsigned int nr_entries;
+	struct desc_struct	*entries;
+	unsigned int		nr_entries;
+
+	/*
+	 * If PTI is in use, then the entries array is not mapped while we're
+	 * in user mode.  The whole array will be aliased at the addressed
+	 * given by ldt_slot_va(slot).  We use two slots so that we can allocate
+	 * and map, and enable a new LDT without invalidating the mapping
+	 * of an older, still-in-use LDT.
+	 *
+	 * slot will be -1 if this LDT doesn't have an alias mapping.
+	 */
+	int			slot;
 };
 
+/* This is a multiple of PAGE_SIZE. */
+#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE)
+
+static inline void *ldt_slot_va(int slot)
+{
+#ifdef CONFIG_X86_64
+	return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot);
+#else
+	BUG();
+	return (void *)fix_to_virt(FIX_HOLE);
+#endif
+}
+
 /*
  * Used for LDT copy/destruction.
  */
-int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm);
+static inline void init_new_context_ldt(struct mm_struct *mm)
+{
+	mm->context.ldt = NULL;
+	init_rwsem(&mm->context.ldt_usr_sem);
+}
+int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm);
 void destroy_context_ldt(struct mm_struct *mm);
+void ldt_arch_exit_mmap(struct mm_struct *mm);
 #else	/* CONFIG_MODIFY_LDT_SYSCALL */
-static inline int init_new_context_ldt(struct task_struct *tsk,
-				       struct mm_struct *mm)
+static inline void init_new_context_ldt(struct mm_struct *mm) { }
+static inline int ldt_dup_context(struct mm_struct *oldmm,
+				  struct mm_struct *mm)
 {
 	return 0;
 }
-static inline void destroy_context_ldt(struct mm_struct *mm) {}
+static inline void destroy_context_ldt(struct mm_struct *mm) { }
+static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { }
 #endif
 
 static inline void load_mm_ldt(struct mm_struct *mm)
@@ -73,8 +105,8 @@ static inline void load_mm_ldt(struct mm_struct *mm)
 #ifdef CONFIG_MODIFY_LDT_SYSCALL
 	struct ldt_struct *ldt;
 
-	/* lockless_dereference synchronizes with smp_store_release */
-	ldt = lockless_dereference(mm->context.ldt);
+	/* READ_ONCE synchronizes with smp_store_release */
+	ldt = READ_ONCE(mm->context.ldt);
 
 	/*
 	 * Any change to mm->context.ldt is followed by an IPI to all
@@ -90,10 +122,31 @@ static inline void load_mm_ldt(struct mm_struct *mm)
 	 * that we can see.
 	 */
 
-	if (unlikely(ldt))
-		set_ldt(ldt->entries, ldt->nr_entries);
-	else
+	if (unlikely(ldt)) {
+		if (static_cpu_has(X86_FEATURE_PTI)) {
+			if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) {
+				/*
+				 * Whoops -- either the new LDT isn't mapped
+				 * (if slot == -1) or is mapped into a bogus
+				 * slot (if slot > 1).
+				 */
+				clear_LDT();
+				return;
+			}
+
+			/*
+			 * If page table isolation is enabled, ldt->entries
+			 * will not be mapped in the userspace pagetables.
+			 * Tell the CPU to access the LDT through the alias
+			 * at ldt_slot_va(ldt->slot).
+			 */
+			set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries);
+		} else {
+			set_ldt(ldt->entries, ldt->nr_entries);
+		}
+	} else {
 		clear_LDT();
+	}
 #else
 	clear_LDT();
 #endif
@@ -132,18 +185,21 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
+	mutex_init(&mm->context.lock);
+
 	mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id);
 	atomic64_set(&mm->context.tlb_gen, 0);
 
-	#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 	if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {
 		/* pkey 0 is the default and always allocated */
 		mm->context.pkey_allocation_map = 0x1;
 		/* -1 means unallocated or invalid */
 		mm->context.execute_only_pkey = -1;
 	}
-	#endif
-	return init_new_context_ldt(tsk, mm);
+#endif
+	init_new_context_ldt(mm);
+	return 0;
 }
 static inline void destroy_context(struct mm_struct *mm)
 {
@@ -176,15 +232,16 @@ do {						\
 } while (0)
 #endif
 
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 {
 	paravirt_arch_dup_mmap(oldmm, mm);
+	return ldt_dup_context(oldmm, mm);
 }
 
 static inline void arch_exit_mmap(struct mm_struct *mm)
 {
 	paravirt_arch_exit_mmap(mm);
+	ldt_arch_exit_mmap(mm);
 }
 
 #ifdef CONFIG_X86_64
@@ -282,33 +339,6 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 }
 
 /*
- * If PCID is on, ASID-aware code paths put the ASID+1 into the PCID
- * bits.  This serves two purposes.  It prevents a nasty situation in
- * which PCID-unaware code saves CR3, loads some other value (with PCID
- * == 0), and then restores CR3, thus corrupting the TLB for ASID 0 if
- * the saved ASID was nonzero.  It also means that any bugs involving
- * loading a PCID-enabled CR3 with CR4.PCIDE off will trigger
- * deterministically.
- */
-
-static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid)
-{
-	if (static_cpu_has(X86_FEATURE_PCID)) {
-		VM_WARN_ON_ONCE(asid > 4094);
-		return __sme_pa(mm->pgd) | (asid + 1);
-	} else {
-		VM_WARN_ON_ONCE(asid != 0);
-		return __sme_pa(mm->pgd);
-	}
-}
-
-static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
-{
-	VM_WARN_ON_ONCE(asid > 4094);
-	return __sme_pa(mm->pgd) | (asid + 1) | CR3_NOFLUSH;
-}
-
-/*
  * This can be used from process context to figure out what the value of
  * CR3 is without needing to do a (slow) __read_cr3().
  *
@@ -317,7 +347,7 @@ static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
  */
 static inline unsigned long __get_current_cr3_fast(void)
 {
-	unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm),
+	unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd,
 		this_cpu_read(cpu_tlbstate.loaded_mm_asid));
 
 	/* For now, be very restrictive about when this can be called. */
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index 8546fafa21a9..7948a17febb4 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -6,7 +6,7 @@
 #include <asm/orc_types.h>
 
 struct mod_arch_specific {
-#ifdef CONFIG_ORC_UNWINDER
+#ifdef CONFIG_UNWINDER_ORC
 	unsigned int num_orcs;
 	int *orc_unwind_ip;
 	struct orc_entry *orc_unwind;
diff --git a/arch/x86/include/asm/mpspec_def.h b/arch/x86/include/asm/mpspec_def.h
index 9492893aec52..6fb923a34309 100644
--- a/arch/x86/include/asm/mpspec_def.h
+++ b/arch/x86/include/asm/mpspec_def.h
@@ -59,7 +59,7 @@ struct mpc_table {
 #define	MP_TRANSLATION		192
 
 #define CPU_ENABLED		1	/* Processor is available */
-#define CPU_BOOTPROCESSOR	2	/* Processor is the BP */
+#define CPU_BOOTPROCESSOR	2	/* Processor is the boot CPU */
 
 #define CPU_STEPPING_MASK	0x000F
 #define CPU_MODEL_MASK		0x00F0
@@ -128,9 +128,17 @@ enum mp_irq_source_types {
 	mp_ExtINT = 3
 };
 
-#define MP_IRQDIR_DEFAULT	0
-#define MP_IRQDIR_HIGH		1
-#define MP_IRQDIR_LOW		3
+#define MP_IRQPOL_DEFAULT	0x0
+#define MP_IRQPOL_ACTIVE_HIGH	0x1
+#define MP_IRQPOL_RESERVED	0x2
+#define MP_IRQPOL_ACTIVE_LOW	0x3
+#define MP_IRQPOL_MASK		0x3
+
+#define MP_IRQTRIG_DEFAULT	0x0
+#define MP_IRQTRIG_EDGE		0x4
+#define MP_IRQTRIG_RESERVED	0x8
+#define MP_IRQTRIG_LEVEL	0xc
+#define MP_IRQTRIG_MASK		0xc
 
 #define MP_APIC_ALL	0xFF
 
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 581bb54dd464..25283f7eb299 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -7,6 +7,7 @@
 #include <linux/nmi.h>
 #include <asm/io.h>
 #include <asm/hyperv.h>
+#include <asm/nospec-branch.h>
 
 /*
  * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
@@ -159,6 +160,7 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
 #define hv_set_synint_state(int_num, val) wrmsrl(int_num, val)
 
 void hyperv_callback_vector(void);
+void hyperv_reenlightenment_vector(void);
 #ifdef CONFIG_TRACING
 #define trace_hyperv_callback_vector hyperv_callback_vector
 #endif
@@ -186,10 +188,11 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 		return U64_MAX;
 
 	__asm__ __volatile__("mov %4, %%r8\n"
-			     "call *%5"
+			     CALL_NOSPEC
 			     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 			       "+c" (control), "+d" (input_address)
-			     :  "r" (output_address), "m" (hv_hypercall_pg)
+			     :  "r" (output_address),
+				THUNK_TARGET(hv_hypercall_pg)
 			     : "cc", "memory", "r8", "r9", "r10", "r11");
 #else
 	u32 input_address_hi = upper_32_bits(input_address);
@@ -200,13 +203,13 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 	if (!hv_hypercall_pg)
 		return U64_MAX;
 
-	__asm__ __volatile__("call *%7"
+	__asm__ __volatile__(CALL_NOSPEC
 			     : "=A" (hv_status),
 			       "+c" (input_address_lo), ASM_CALL_CONSTRAINT
 			     : "A" (control),
 			       "b" (input_address_hi),
 			       "D"(output_address_hi), "S"(output_address_lo),
-			       "m" (hv_hypercall_pg)
+			       THUNK_TARGET(hv_hypercall_pg)
 			     : "cc", "memory");
 #endif /* !x86_64 */
 	return hv_status;
@@ -227,10 +230,10 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
 
 #ifdef CONFIG_X86_64
 	{
-		__asm__ __volatile__("call *%4"
+		__asm__ __volatile__(CALL_NOSPEC
 				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 				       "+c" (control), "+d" (input1)
-				     : "m" (hv_hypercall_pg)
+				     : THUNK_TARGET(hv_hypercall_pg)
 				     : "cc", "r8", "r9", "r10", "r11");
 	}
 #else
@@ -238,13 +241,13 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
 		u32 input1_hi = upper_32_bits(input1);
 		u32 input1_lo = lower_32_bits(input1);
 
-		__asm__ __volatile__ ("call *%5"
+		__asm__ __volatile__ (CALL_NOSPEC
 				      : "=A"(hv_status),
 					"+c"(input1_lo),
 					ASM_CALL_CONSTRAINT
 				      :	"A" (control),
 					"b" (input1_hi),
-					"m" (hv_hypercall_pg)
+					THUNK_TARGET(hv_hypercall_pg)
 				      : "cc", "edi", "esi");
 	}
 #endif
@@ -311,21 +314,30 @@ static inline int hv_cpu_number_to_vp_number(int cpu_number)
 void hyperv_init(void);
 void hyperv_setup_mmu_ops(void);
 void hyper_alloc_mmu(void);
-void hyperv_report_panic(struct pt_regs *regs);
-bool hv_is_hypercall_page_setup(void);
+void hyperv_report_panic(struct pt_regs *regs, long err);
+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));
+void clear_hv_tscchange_cb(void);
+void hyperv_stop_tsc_emulation(void);
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
-static inline bool hv_is_hypercall_page_setup(void) { return false; }
+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) {}
+static inline void hyperv_stop_tsc_emulation(void) {};
 #endif /* CONFIG_HYPERV */
 
 #ifdef CONFIG_HYPERV_TSCPAGE
 struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
-static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
+static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
+				       u64 *cur_tsc)
 {
-	u64 scale, offset, cur_tsc;
+	u64 scale, offset;
 	u32 sequence;
 
 	/*
@@ -356,7 +368,7 @@ static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
 
 		scale = READ_ONCE(tsc_pg->tsc_scale);
 		offset = READ_ONCE(tsc_pg->tsc_offset);
-		cur_tsc = rdtsc_ordered();
+		*cur_tsc = rdtsc_ordered();
 
 		/*
 		 * Make sure we read sequence after we read all other values
@@ -366,7 +378,14 @@ static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
 
 	} while (READ_ONCE(tsc_pg->tsc_sequence) != sequence);
 
-	return mul_u64_u64_shr(cur_tsc, scale, 64) + offset;
+	return mul_u64_u64_shr(*cur_tsc, scale, 64) + offset;
+}
+
+static inline u64 hv_read_tsc_page(const struct ms_hyperv_tsc_page *tsc_pg)
+{
+	u64 cur_tsc;
+
+	return hv_read_tsc_page_tsc(tsc_pg, &cur_tsc);
 }
 
 #else
@@ -374,5 +393,12 @@ static inline struct ms_hyperv_tsc_page *hv_get_tsc_page(void)
 {
 	return NULL;
 }
+
+static inline u64 hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
+				       u64 *cur_tsc)
+{
+	BUG();
+	return U64_MAX;
+}
 #endif
 #endif
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index ab022618a50a..c9084dedfcfa 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -39,6 +39,13 @@
 
 /* Intel MSRs. Some also available on other CPUs */
 
+#define MSR_IA32_SPEC_CTRL		0x00000048 /* Speculation Control */
+#define SPEC_CTRL_IBRS			(1 << 0)   /* Indirect Branch Restricted Speculation */
+#define SPEC_CTRL_STIBP			(1 << 1)   /* Single Thread Indirect Branch Predictors */
+
+#define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
+#define PRED_CMD_IBPB			(1 << 0)   /* Indirect Branch Prediction Barrier */
+
 #define MSR_PPIN_CTL			0x0000004e
 #define MSR_PPIN			0x0000004f
 
@@ -57,6 +64,11 @@
 #define SNB_C3_AUTO_UNDEMOTE		(1UL << 28)
 
 #define MSR_MTRRcap			0x000000fe
+
+#define MSR_IA32_ARCH_CAPABILITIES	0x0000010a
+#define ARCH_CAP_RDCL_NO		(1 << 0)   /* Not susceptible to Meltdown */
+#define ARCH_CAP_IBRS_ALL		(1 << 1)   /* Enhanced IBRS support */
+
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
 
@@ -324,6 +336,9 @@
 #define MSR_AMD64_IBSBRTARGET		0xc001103b
 #define MSR_AMD64_IBSOPDATA4		0xc001103d
 #define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
+#define MSR_AMD64_SEV			0xc0010131
+#define MSR_AMD64_SEV_ENABLED_BIT	0
+#define MSR_AMD64_SEV_ENABLED		BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
 
 /* Fam 17h MSRs */
 #define MSR_F17H_IRPERF			0xc00000e9
@@ -352,6 +367,9 @@
 #define FAM10H_MMIO_CONF_BASE_MASK	0xfffffffULL
 #define FAM10H_MMIO_CONF_BASE_SHIFT	20
 #define MSR_FAM10H_NODE_ID		0xc001100c
+#define MSR_F10H_DECFG			0xc0011029
+#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT	1
+#define MSR_F10H_DECFG_LFENCE_SERIALIZE		BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT)
 
 /* K8 MSRs */
 #define MSR_K8_TOP_MEM1			0xc001001a
@@ -379,6 +397,8 @@
 #define MSR_K7_PERFCTR3			0xc0010007
 #define MSR_K7_CLK_CTL			0xc001001b
 #define MSR_K7_HWCR			0xc0010015
+#define MSR_K7_HWCR_SMMLOCK_BIT		0
+#define MSR_K7_HWCR_SMMLOCK		BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
 #define MSR_K7_FID_VID_CTL		0xc0010041
 #define MSR_K7_FID_VID_STATUS		0xc0010042
 
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 07962f5f6fba..30df295f6d94 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -214,8 +214,7 @@ static __always_inline unsigned long long rdtsc_ordered(void)
 	 * that some other imaginary CPU is updating continuously with a
 	 * time stamp.
 	 */
-	alternative_2("", "mfence", X86_FEATURE_MFENCE_RDTSC,
-			  "lfence", X86_FEATURE_LFENCE_RDTSC);
+	barrier_nospec();
 	return rdtsc();
 }
 
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
new file mode 100644
index 000000000000..d0dabeae0505
--- /dev/null
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -0,0 +1,315 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_X86_NOSPEC_BRANCH_H_
+#define _ASM_X86_NOSPEC_BRANCH_H_
+
+#include <asm/alternative.h>
+#include <asm/alternative-asm.h>
+#include <asm/cpufeatures.h>
+#include <asm/msr-index.h>
+
+/*
+ * Fill the CPU return stack buffer.
+ *
+ * Each entry in the RSB, if used for a speculative 'ret', contains an
+ * infinite 'pause; lfence; jmp' loop to capture speculative execution.
+ *
+ * This is required in various cases for retpoline and IBRS-based
+ * mitigations for the Spectre variant 2 vulnerability. Sometimes to
+ * eliminate potentially bogus entries from the RSB, and sometimes
+ * purely to ensure that it doesn't get empty, which on some CPUs would
+ * allow predictions from other (unwanted!) sources to be used.
+ *
+ * We define a CPP macro such that it can be used from both .S files and
+ * inline assembly. It's possible to do a .macro and then include that
+ * from C via asm(".include <asm/nospec-branch.h>") but let's not go there.
+ */
+
+#define RSB_CLEAR_LOOPS		32	/* To forcibly overwrite all entries */
+#define RSB_FILL_LOOPS		16	/* To avoid underflow */
+
+/*
+ * Google experimented with loop-unrolling and this turned out to be
+ * the optimal version — two calls, each with their own speculation
+ * trap should their return address end up getting used, in a loop.
+ */
+#define __FILL_RETURN_BUFFER(reg, nr, sp)	\
+	mov	$(nr/2), reg;			\
+771:						\
+	call	772f;				\
+773:	/* speculation trap */			\
+	pause;					\
+	lfence;					\
+	jmp	773b;				\
+772:						\
+	call	774f;				\
+775:	/* speculation trap */			\
+	pause;					\
+	lfence;					\
+	jmp	775b;				\
+774:						\
+	dec	reg;				\
+	jnz	771b;				\
+	add	$(BITS_PER_LONG/8) * nr, sp;
+
+#ifdef __ASSEMBLY__
+
+/*
+ * This should be used immediately before a retpoline alternative.  It tells
+ * objtool where the retpolines are so that it can make sense of the control
+ * flow by just reading the original instruction(s) and ignoring the
+ * alternatives.
+ */
+.macro ANNOTATE_NOSPEC_ALTERNATIVE
+	.Lannotate_\@:
+	.pushsection .discard.nospec
+	.long .Lannotate_\@ - .
+	.popsection
+.endm
+
+/*
+ * This should be used immediately before an indirect jump/call. It tells
+ * objtool the subsequent indirect jump/call is vouched safe for retpoline
+ * builds.
+ */
+.macro ANNOTATE_RETPOLINE_SAFE
+	.Lannotate_\@:
+	.pushsection .discard.retpoline_safe
+	_ASM_PTR .Lannotate_\@
+	.popsection
+.endm
+
+/*
+ * These are the bare retpoline primitives for indirect jmp and call.
+ * Do not use these directly; they only exist to make the ALTERNATIVE
+ * invocation below less ugly.
+ */
+.macro RETPOLINE_JMP reg:req
+	call	.Ldo_rop_\@
+.Lspec_trap_\@:
+	pause
+	lfence
+	jmp	.Lspec_trap_\@
+.Ldo_rop_\@:
+	mov	\reg, (%_ASM_SP)
+	ret
+.endm
+
+/*
+ * This is a wrapper around RETPOLINE_JMP so the called function in reg
+ * returns to the instruction after the macro.
+ */
+.macro RETPOLINE_CALL reg:req
+	jmp	.Ldo_call_\@
+.Ldo_retpoline_jmp_\@:
+	RETPOLINE_JMP \reg
+.Ldo_call_\@:
+	call	.Ldo_retpoline_jmp_\@
+.endm
+
+/*
+ * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple
+ * indirect jmp/call which may be susceptible to the Spectre variant 2
+ * attack.
+ */
+.macro JMP_NOSPEC reg:req
+#ifdef CONFIG_RETPOLINE
+	ANNOTATE_NOSPEC_ALTERNATIVE
+	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *\reg),	\
+		__stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE,	\
+		__stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *\reg), X86_FEATURE_RETPOLINE_AMD
+#else
+	jmp	*\reg
+#endif
+.endm
+
+.macro CALL_NOSPEC reg:req
+#ifdef CONFIG_RETPOLINE
+	ANNOTATE_NOSPEC_ALTERNATIVE
+	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *\reg),	\
+		__stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\
+		__stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *\reg), X86_FEATURE_RETPOLINE_AMD
+#else
+	call	*\reg
+#endif
+.endm
+
+ /*
+  * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP
+  * monstrosity above, manually.
+  */
+.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req
+#ifdef CONFIG_RETPOLINE
+	ANNOTATE_NOSPEC_ALTERNATIVE
+	ALTERNATIVE "jmp .Lskip_rsb_\@",				\
+		__stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP))	\
+		\ftr
+.Lskip_rsb_\@:
+#endif
+.endm
+
+#else /* __ASSEMBLY__ */
+
+#define ANNOTATE_NOSPEC_ALTERNATIVE				\
+	"999:\n\t"						\
+	".pushsection .discard.nospec\n\t"			\
+	".long 999b - .\n\t"					\
+	".popsection\n\t"
+
+#define ANNOTATE_RETPOLINE_SAFE					\
+	"999:\n\t"						\
+	".pushsection .discard.retpoline_safe\n\t"		\
+	_ASM_PTR " 999b\n\t"					\
+	".popsection\n\t"
+
+#if defined(CONFIG_X86_64) && defined(RETPOLINE)
+
+/*
+ * Since the inline asm uses the %V modifier which is only in newer GCC,
+ * the 64-bit one is dependent on RETPOLINE not CONFIG_RETPOLINE.
+ */
+# define CALL_NOSPEC						\
+	ANNOTATE_NOSPEC_ALTERNATIVE				\
+	ALTERNATIVE(						\
+	ANNOTATE_RETPOLINE_SAFE					\
+	"call *%[thunk_target]\n",				\
+	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
+	X86_FEATURE_RETPOLINE)
+# define THUNK_TARGET(addr) [thunk_target] "r" (addr)
+
+#elif defined(CONFIG_X86_32) && defined(CONFIG_RETPOLINE)
+/*
+ * For i386 we use the original ret-equivalent retpoline, because
+ * otherwise we'll run out of registers. We don't care about CET
+ * here, anyway.
+ */
+# define CALL_NOSPEC ALTERNATIVE("call *%[thunk_target]\n",	\
+	"       jmp    904f;\n"					\
+	"       .align 16\n"					\
+	"901:	call   903f;\n"					\
+	"902:	pause;\n"					\
+	"    	lfence;\n"					\
+	"       jmp    902b;\n"					\
+	"       .align 16\n"					\
+	"903:	addl   $4, %%esp;\n"				\
+	"       pushl  %[thunk_target];\n"			\
+	"       ret;\n"						\
+	"       .align 16\n"					\
+	"904:	call   901b;\n",				\
+	X86_FEATURE_RETPOLINE)
+
+# define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
+#else /* No retpoline for C / inline asm */
+# define CALL_NOSPEC "call *%[thunk_target]\n"
+# define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
+#endif
+
+/* The Spectre V2 mitigation variants */
+enum spectre_v2_mitigation {
+	SPECTRE_V2_NONE,
+	SPECTRE_V2_RETPOLINE_MINIMAL,
+	SPECTRE_V2_RETPOLINE_MINIMAL_AMD,
+	SPECTRE_V2_RETPOLINE_GENERIC,
+	SPECTRE_V2_RETPOLINE_AMD,
+	SPECTRE_V2_IBRS,
+};
+
+extern char __indirect_thunk_start[];
+extern char __indirect_thunk_end[];
+
+/*
+ * On VMEXIT we must ensure that no RSB predictions learned in the guest
+ * can be followed in the host, by overwriting the RSB completely. Both
+ * retpoline and IBRS mitigations for Spectre v2 need this; only on future
+ * CPUs with IBRS_ALL *might* it be avoided.
+ */
+static inline void vmexit_fill_RSB(void)
+{
+#ifdef CONFIG_RETPOLINE
+	unsigned long loops;
+
+	asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE
+		      ALTERNATIVE("jmp 910f",
+				  __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)),
+				  X86_FEATURE_RETPOLINE)
+		      "910:"
+		      : "=r" (loops), ASM_CALL_CONSTRAINT
+		      : : "memory" );
+#endif
+}
+
+#define alternative_msr_write(_msr, _val, _feature)		\
+	asm volatile(ALTERNATIVE("",				\
+				 "movl %[msr], %%ecx\n\t"	\
+				 "movl %[val], %%eax\n\t"	\
+				 "movl $0, %%edx\n\t"		\
+				 "wrmsr",			\
+				 _feature)			\
+		     : : [msr] "i" (_msr), [val] "i" (_val)	\
+		     : "eax", "ecx", "edx", "memory")
+
+static inline void indirect_branch_prediction_barrier(void)
+{
+	alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB,
+			      X86_FEATURE_USE_IBPB);
+}
+
+/*
+ * With retpoline, we must use IBRS to restrict branch prediction
+ * before calling into firmware.
+ *
+ * (Implemented as CPP macros due to header hell.)
+ */
+#define firmware_restrict_branch_speculation_start()			\
+do {									\
+	preempt_disable();						\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS,	\
+			      X86_FEATURE_USE_IBRS_FW);			\
+} while (0)
+
+#define firmware_restrict_branch_speculation_end()			\
+do {									\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, 0,			\
+			      X86_FEATURE_USE_IBRS_FW);			\
+	preempt_enable();						\
+} while (0)
+
+#endif /* __ASSEMBLY__ */
+
+/*
+ * Below is used in the eBPF JIT compiler and emits the byte sequence
+ * for the following assembly:
+ *
+ * With retpolines configured:
+ *
+ *    callq do_rop
+ *  spec_trap:
+ *    pause
+ *    lfence
+ *    jmp spec_trap
+ *  do_rop:
+ *    mov %rax,(%rsp)
+ *    retq
+ *
+ * Without retpolines configured:
+ *
+ *    jmp *%rax
+ */
+#ifdef CONFIG_RETPOLINE
+# define RETPOLINE_RAX_BPF_JIT_SIZE	17
+# define RETPOLINE_RAX_BPF_JIT()				\
+	EMIT1_off32(0xE8, 7);	 /* callq do_rop */		\
+	/* spec_trap: */					\
+	EMIT2(0xF3, 0x90);       /* pause */			\
+	EMIT3(0x0F, 0xAE, 0xE8); /* lfence */			\
+	EMIT2(0xEB, 0xF9);       /* jmp spec_trap */		\
+	/* do_rop: */						\
+	EMIT4(0x48, 0x89, 0x04, 0x24); /* mov %rax,(%rsp) */	\
+	EMIT1(0xC3);             /* retq */
+#else
+# define RETPOLINE_RAX_BPF_JIT_SIZE	2
+# define RETPOLINE_RAX_BPF_JIT()				\
+	EMIT2(0xFF, 0xE0);	 /* jmp *%rax */
+#endif
+
+#endif /* _ASM_X86_NOSPEC_BRANCH_H_ */
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index 4baa6bceb232..d652a3808065 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -52,10 +52,6 @@ static inline void clear_page(void *page)
 
 void copy_page(void *to, void *from);
 
-#ifdef CONFIG_X86_MCE
-#define arch_unmap_kpfn arch_unmap_kpfn
-#endif
-
 #endif	/* !__ASSEMBLY__ */
 
 #ifdef CONFIG_X86_VSYSCALL_EMULATION
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index fd81228e8037..c83a2f418cea 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -7,6 +7,7 @@
 #ifdef CONFIG_PARAVIRT
 #include <asm/pgtable_types.h>
 #include <asm/asm.h>
+#include <asm/nospec-branch.h>
 
 #include <asm/paravirt_types.h>
 
@@ -16,10 +17,9 @@
 #include <linux/cpumask.h>
 #include <asm/frame.h>
 
-static inline void load_sp0(struct tss_struct *tss,
-			     struct thread_struct *thread)
+static inline void load_sp0(unsigned long sp0)
 {
-	PVOP_VCALL2(pv_cpu_ops.load_sp0, tss, thread);
+	PVOP_VCALL1(pv_cpu_ops.load_sp0, sp0);
 }
 
 /* The paravirtualized CPUID instruction. */
@@ -298,9 +298,9 @@ static inline void __flush_tlb_global(void)
 {
 	PVOP_VCALL0(pv_mmu_ops.flush_tlb_kernel);
 }
-static inline void __flush_tlb_single(unsigned long addr)
+static inline void __flush_tlb_one_user(unsigned long addr)
 {
-	PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr);
+	PVOP_VCALL1(pv_mmu_ops.flush_tlb_one_user, addr);
 }
 
 static inline void flush_tlb_others(const struct cpumask *cpumask,
@@ -880,23 +880,27 @@ extern void default_banner(void);
 
 #define INTERRUPT_RETURN						\
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE,	\
-		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret))
+		  ANNOTATE_RETPOLINE_SAFE;					\
+		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret);)
 
 #define DISABLE_INTERRUPTS(clobbers)					\
 	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \
 		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);		\
+		  ANNOTATE_RETPOLINE_SAFE;					\
 		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable);	\
 		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
 
 #define ENABLE_INTERRUPTS(clobbers)					\
 	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers,	\
 		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);		\
+		  ANNOTATE_RETPOLINE_SAFE;					\
 		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable);	\
 		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
 
 #ifdef CONFIG_X86_32
 #define GET_CR0_INTO_EAX				\
 	push %ecx; push %edx;				\
+	ANNOTATE_RETPOLINE_SAFE;				\
 	call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0);	\
 	pop %edx; pop %ecx
 #else	/* !CONFIG_X86_32 */
@@ -918,16 +922,29 @@ extern void default_banner(void);
  */
 #define SWAPGS								\
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE,	\
-		  call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs)		\
+		  ANNOTATE_RETPOLINE_SAFE;					\
+		  call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs);		\
 		 )
 
 #define GET_CR2_INTO_RAX				\
-	call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2)
+	ANNOTATE_RETPOLINE_SAFE;				\
+	call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2);
 
 #define USERGS_SYSRET64							\
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64),	\
 		  CLBR_NONE,						\
-		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64))
+		  ANNOTATE_RETPOLINE_SAFE;					\
+		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64);)
+
+#ifdef CONFIG_DEBUG_ENTRY
+#define SAVE_FLAGS(clobbers)                                        \
+	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \
+		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);        \
+		  ANNOTATE_RETPOLINE_SAFE;				    \
+		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl);    \
+		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
+#endif
+
 #endif	/* CONFIG_X86_32 */
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 10cc3b9709fe..180bc0bff0fb 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -43,6 +43,7 @@
 #include <asm/desc_defs.h>
 #include <asm/kmap_types.h>
 #include <asm/pgtable_types.h>
+#include <asm/nospec-branch.h>
 
 struct page;
 struct thread_struct;
@@ -134,7 +135,7 @@ struct pv_cpu_ops {
 	void (*alloc_ldt)(struct desc_struct *ldt, unsigned entries);
 	void (*free_ldt)(struct desc_struct *ldt, unsigned entries);
 
-	void (*load_sp0)(struct tss_struct *tss, struct thread_struct *t);
+	void (*load_sp0)(unsigned long sp0);
 
 	void (*set_iopl_mask)(unsigned mask);
 
@@ -217,7 +218,7 @@ struct pv_mmu_ops {
 	/* TLB operations */
 	void (*flush_tlb_user)(void);
 	void (*flush_tlb_kernel)(void);
-	void (*flush_tlb_single)(unsigned long addr);
+	void (*flush_tlb_one_user)(unsigned long addr);
 	void (*flush_tlb_others)(const struct cpumask *cpus,
 				 const struct flush_tlb_info *info);
 
@@ -392,7 +393,9 @@ int paravirt_disable_iospace(void);
  * offset into the paravirt_patch_template structure, and can therefore be
  * freely converted back into a structure offset.
  */
-#define PARAVIRT_CALL	"call *%c[paravirt_opptr];"
+#define PARAVIRT_CALL					\
+	ANNOTATE_RETPOLINE_SAFE				\
+	"call *%c[paravirt_opptr];"
 
 /*
  * These macros are intended to wrap calls through one of the paravirt
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index 8a3ee355b422..92015c65fa2a 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -22,4 +22,6 @@ int io_reserve_memtype(resource_size_t start, resource_size_t end,
 
 void io_free_memtype(resource_size_t start, resource_size_t end);
 
+bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn);
+
 #endif /* _ASM_X86_PAT_H */
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 09c06b0fb964..d32175e30259 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -89,10 +89,8 @@ extern unsigned long pci_mem_start;
 #define PCIBIOS_MIN_CARDBUS_IO	0x4000
 
 extern int pcibios_enabled;
-void pcibios_config_init(void);
 void pcibios_scan_root(int bus);
 
-void pcibios_set_master(struct pci_dev *dev);
 struct irq_routing_table *pcibios_get_irq_routing_table(void);
 int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq);
 
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index 7a5d6695abd3..eb66fa9cd0fc 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -38,6 +38,7 @@ do {						\
 #define PCI_NOASSIGN_ROMS	0x80000
 #define PCI_ROOT_NO_CRS		0x100000
 #define PCI_NOASSIGN_BARS	0x200000
+#define PCI_BIG_ROOT_WINDOW	0x400000
 
 extern unsigned int pci_probe;
 extern unsigned long pirq_table_addr;
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 377f1ffd18be..a06b07399d17 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -526,7 +526,7 @@ static inline bool x86_this_cpu_variable_test_bit(int nr,
 {
 	bool oldbit;
 
-	asm volatile("bt "__percpu_arg(2)",%1\n\t"
+	asm volatile("btl "__percpu_arg(2)",%1"
 			CC_SET(c)
 			: CC_OUT(c) (oldbit)
 			: "m" (*(unsigned long __percpu *)addr), "Ir" (nr));
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index 4b5e1eafada7..aff42e1da6ee 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -30,6 +30,17 @@ static inline void paravirt_release_p4d(unsigned long pfn) {}
  */
 extern gfp_t __userpte_alloc_gfp;
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Instead of one PGD, we acquire two PGDs.  Being order-1, it is
+ * both 8k in size and 8k-aligned.  That lets us just flip bit 12
+ * in a pointer to swap between the two 4k halves.
+ */
+#define PGD_ALLOCATION_ORDER 1
+#else
+#define PGD_ALLOCATION_ORDER 0
+#endif
+
 /*
  * Allocate and free page tables.
  */
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index bc4af5453802..f24df59c40b2 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -158,7 +158,6 @@ static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
 #define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
 #endif
 
-#ifdef CONFIG_SMP
 union split_pmd {
 	struct {
 		u32 pmd_low;
@@ -166,6 +165,8 @@ union split_pmd {
 	};
 	pmd_t pmd;
 };
+
+#ifdef CONFIG_SMP
 static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
 {
 	union split_pmd res, *orig = (union split_pmd *)pmdp;
@@ -181,6 +182,40 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
 #define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
 #endif
 
+#ifndef pmdp_establish
+#define pmdp_establish pmdp_establish
+static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmdp, pmd_t pmd)
+{
+	pmd_t old;
+
+	/*
+	 * If pmd has present bit cleared we can get away without expensive
+	 * cmpxchg64: we can update pmdp half-by-half without racing with
+	 * anybody.
+	 */
+	if (!(pmd_val(pmd) & _PAGE_PRESENT)) {
+		union split_pmd old, new, *ptr;
+
+		ptr = (union split_pmd *)pmdp;
+
+		new.pmd = pmd;
+
+		/* xchg acts as a barrier before setting of the high bits */
+		old.pmd_low = xchg(&ptr->pmd_low, new.pmd_low);
+		old.pmd_high = ptr->pmd_high;
+		ptr->pmd_high = new.pmd_high;
+		return old.pmd;
+	}
+
+	do {
+		old = *pmdp;
+	} while (cmpxchg64(&pmdp->pmd, old.pmd, pmd.pmd) != old.pmd);
+
+	return old;
+}
+#endif
+
 #ifdef CONFIG_SMP
 union split_pud {
 	struct {
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index f735c3016325..b444d83cfc95 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -28,6 +28,7 @@ extern pgd_t early_top_pgt[PTRS_PER_PGD];
 int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
 
 void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user);
 void ptdump_walk_pgd_level_checkwx(void);
 
 #ifdef CONFIG_DEBUG_WX
@@ -349,14 +350,14 @@ static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set)
 {
 	pmdval_t v = native_pmd_val(pmd);
 
-	return __pmd(v | set);
+	return native_make_pmd(v | set);
 }
 
 static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
 {
 	pmdval_t v = native_pmd_val(pmd);
 
-	return __pmd(v & ~clear);
+	return native_make_pmd(v & ~clear);
 }
 
 static inline pmd_t pmd_mkold(pmd_t pmd)
@@ -408,14 +409,14 @@ static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
 {
 	pudval_t v = native_pud_val(pud);
 
-	return __pud(v | set);
+	return native_make_pud(v | set);
 }
 
 static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear)
 {
 	pudval_t v = native_pud_val(pud);
 
-	return __pud(v & ~clear);
+	return native_make_pud(v & ~clear);
 }
 
 static inline pud_t pud_mkold(pud_t pud)
@@ -667,11 +668,6 @@ static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
 	return false;
 }
 
-static inline int pte_hidden(pte_t pte)
-{
-	return pte_flags(pte) & _PAGE_HIDDEN;
-}
-
 static inline int pmd_present(pmd_t pmd)
 {
 	/*
@@ -846,7 +842,12 @@ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
 
 static inline int p4d_bad(p4d_t p4d)
 {
-	return (p4d_flags(p4d) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
+	unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER;
+
+	if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+		ignore_flags |= _PAGE_NX;
+
+	return (p4d_flags(p4d) & ~ignore_flags) != 0;
 }
 #endif  /* CONFIG_PGTABLE_LEVELS > 3 */
 
@@ -880,7 +881,12 @@ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
 
 static inline int pgd_bad(pgd_t pgd)
 {
-	return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
+	unsigned long ignore_flags = _PAGE_USER;
+
+	if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+		ignore_flags |= _PAGE_NX;
+
+	return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE;
 }
 
 static inline int pgd_none(pgd_t pgd)
@@ -909,7 +915,11 @@ static inline int pgd_none(pgd_t pgd)
  * pgd_offset() returns a (pgd_t *)
  * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
  */
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
+#define pgd_offset_pgd(pgd, address) (pgd + pgd_index((address)))
+/*
+ * a shortcut to get a pgd_t in a given mm
+ */
+#define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address))
 /*
  * a shortcut which implies the use of the kernel's pgd, instead
  * of a process's
@@ -1066,7 +1076,7 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
 				  unsigned long address, pmd_t *pmdp);
 
 
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
 static inline int pmd_write(pmd_t pmd)
 {
 	return pmd_flags(pmd) & _PAGE_RW;
@@ -1093,6 +1103,27 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 	clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp);
 }
 
+#define pud_write pud_write
+static inline int pud_write(pud_t pud)
+{
+	return pud_flags(pud) & _PAGE_RW;
+}
+
+#ifndef pmdp_establish
+#define pmdp_establish pmdp_establish
+static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
+		unsigned long address, pmd_t *pmdp, pmd_t pmd)
+{
+	if (IS_ENABLED(CONFIG_SMP)) {
+		return xchg(pmdp, pmd);
+	} else {
+		pmd_t old = *pmdp;
+		*pmdp = pmd;
+		return old;
+	}
+}
+#endif
+
 /*
  * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
  *
@@ -1105,7 +1136,14 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
  */
 static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
 {
-       memcpy(dst, src, count * sizeof(pgd_t));
+	memcpy(dst, src, count * sizeof(pgd_t));
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+	/* Clone the user space pgd as well */
+	memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src),
+	       count * sizeof(pgd_t));
+#endif
 }
 
 #define PTE_SHIFT ilog2(PTRS_PER_PTE)
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index e67c0620aec2..b3ec519e3982 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -32,6 +32,7 @@ extern pmd_t initial_pg_pmd[];
 static inline void pgtable_cache_init(void) { }
 static inline void check_pgt_cache(void) { }
 void paging_init(void);
+void sync_initial_page_table(void);
 
 /*
  * Define this if things work differently on an i386 and an i486:
@@ -61,7 +62,7 @@ void paging_init(void);
 #define kpte_clear_flush(ptep, vaddr)		\
 do {						\
 	pte_clear(&init_mm, (vaddr), (ptep));	\
-	__flush_tlb_one((vaddr));		\
+	__flush_tlb_one_kernel((vaddr));		\
 } while (0)
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index f2ca9b28fd68..0777e18a1d23 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -38,13 +38,23 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
 #define LAST_PKMAP 1024
 #endif
 
-#define PKMAP_BASE ((FIXADDR_START - PAGE_SIZE * (LAST_PKMAP + 1))	\
-		    & PMD_MASK)
+/*
+ * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c
+ * to avoid include recursion hell
+ */
+#define CPU_ENTRY_AREA_PAGES	(NR_CPUS * 40)
+
+#define CPU_ENTRY_AREA_BASE						\
+	((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1))   \
+	 & PMD_MASK)
+
+#define PKMAP_BASE		\
+	((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
 
 #ifdef CONFIG_HIGHMEM
 # define VMALLOC_END	(PKMAP_BASE - 2 * PAGE_SIZE)
 #else
-# define VMALLOC_END	(FIXADDR_START - 2 * PAGE_SIZE)
+# define VMALLOC_END	(CPU_ENTRY_AREA_BASE - 2 * PAGE_SIZE)
 #endif
 
 #define MODULES_VADDR	VMALLOC_START
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index e9f05331e732..1149d2112b2e 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -28,6 +28,7 @@ extern pgd_t init_top_pgt[];
 #define swapper_pg_dir init_top_pgt
 
 extern void paging_init(void);
+static inline void sync_initial_page_table(void) { }
 
 #define pte_ERROR(e)					\
 	pr_err("%s:%d: bad pte %p(%016lx)\n",		\
@@ -131,9 +132,97 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp)
 #endif
 }
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
+ * (8k-aligned and 8k in size).  The kernel one is at the beginning 4k and
+ * the user one is in the last 4k.  To switch between them, you
+ * just need to flip the 12th bit in their addresses.
+ */
+#define PTI_PGTABLE_SWITCH_BIT	PAGE_SHIFT
+
+/*
+ * This generates better code than the inline assembly in
+ * __set_bit().
+ */
+static inline void *ptr_set_bit(void *ptr, int bit)
+{
+	unsigned long __ptr = (unsigned long)ptr;
+
+	__ptr |= BIT(bit);
+	return (void *)__ptr;
+}
+static inline void *ptr_clear_bit(void *ptr, int bit)
+{
+	unsigned long __ptr = (unsigned long)ptr;
+
+	__ptr &= ~BIT(bit);
+	return (void *)__ptr;
+}
+
+static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
+{
+	return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
+{
+	return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
+{
+	return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
+{
+	return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
+/*
+ * Page table pages are page-aligned.  The lower half of the top
+ * level is used for userspace and the top half for the kernel.
+ *
+ * Returns true for parts of the PGD that map userspace and
+ * false for the parts that map the kernel.
+ */
+static inline bool pgdp_maps_userspace(void *__ptr)
+{
+	unsigned long ptr = (unsigned long)__ptr;
+
+	return (ptr & ~PAGE_MASK) < (PAGE_SIZE / 2);
+}
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd);
+
+/*
+ * Take a PGD location (pgdp) and a pgd value that needs to be set there.
+ * Populates the user and returns the resulting PGD that must be set in
+ * the kernel copy of the page tables.
+ */
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return pgd;
+	return __pti_set_user_pgd(pgdp, pgd);
+}
+#else
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	return pgd;
+}
+#endif
+
 static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
 {
+#if defined(CONFIG_PAGE_TABLE_ISOLATION) && !defined(CONFIG_X86_5LEVEL)
+	p4dp->pgd = pti_set_user_pgd(&p4dp->pgd, p4d.pgd);
+#else
 	*p4dp = p4d;
+#endif
 }
 
 static inline void native_p4d_clear(p4d_t *p4d)
@@ -147,7 +236,11 @@ static inline void native_p4d_clear(p4d_t *p4d)
 
 static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	*pgdp = pti_set_user_pgd(pgdp, pgd);
+#else
 	*pgdp = pgd;
+#endif
 }
 
 static inline void native_pgd_clear(pgd_t *pgd)
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 6d5f45dcd4a1..6b8f73dcbc2c 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -75,33 +75,52 @@ typedef struct { pteval_t pte; } pte_t;
 #define PGDIR_SIZE	(_AC(1, UL) << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE - 1))
 
-/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
-#define MAXMEM		_AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+/*
+ * See Documentation/x86/x86_64/mm.txt 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
+ * is correct as KASAN disables KASLR.
+ */
+#define MAXMEM			_AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+
 #ifdef CONFIG_X86_5LEVEL
-#define VMALLOC_SIZE_TB _AC(16384, UL)
-#define __VMALLOC_BASE	_AC(0xff92000000000000, UL)
-#define __VMEMMAP_BASE	_AC(0xffd4000000000000, UL)
+# define VMALLOC_SIZE_TB	_AC(12800, UL)
+# define __VMALLOC_BASE		_AC(0xffa0000000000000, UL)
+# define __VMEMMAP_BASE		_AC(0xffd4000000000000, UL)
+# define LDT_PGD_ENTRY		_AC(-112, UL)
+# define LDT_BASE_ADDR		(LDT_PGD_ENTRY << PGDIR_SHIFT)
 #else
-#define VMALLOC_SIZE_TB	_AC(32, UL)
-#define __VMALLOC_BASE	_AC(0xffffc90000000000, UL)
-#define __VMEMMAP_BASE	_AC(0xffffea0000000000, UL)
+# define VMALLOC_SIZE_TB	_AC(32, UL)
+# define __VMALLOC_BASE		_AC(0xffffc90000000000, UL)
+# define __VMEMMAP_BASE		_AC(0xffffea0000000000, UL)
+# define LDT_PGD_ENTRY		_AC(-3, UL)
+# define LDT_BASE_ADDR		(LDT_PGD_ENTRY << PGDIR_SHIFT)
 #endif
+
 #ifdef CONFIG_RANDOMIZE_MEMORY
-#define VMALLOC_START	vmalloc_base
-#define VMEMMAP_START	vmemmap_base
+# define VMALLOC_START		vmalloc_base
+# define VMEMMAP_START		vmemmap_base
 #else
-#define VMALLOC_START	__VMALLOC_BASE
-#define VMEMMAP_START	__VMEMMAP_BASE
+# define VMALLOC_START		__VMALLOC_BASE
+# define VMEMMAP_START		__VMEMMAP_BASE
 #endif /* CONFIG_RANDOMIZE_MEMORY */
-#define VMALLOC_END	(VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
-#define MODULES_VADDR    (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
+
+#define VMALLOC_END		(VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
+
+#define MODULES_VADDR		(__START_KERNEL_map + KERNEL_IMAGE_SIZE)
 /* The module sections ends with the start of the fixmap */
-#define MODULES_END   __fix_to_virt(__end_of_fixed_addresses + 1)
-#define MODULES_LEN   (MODULES_END - MODULES_VADDR)
-#define ESPFIX_PGD_ENTRY _AC(-2, UL)
-#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT)
-#define EFI_VA_START	 ( -4 * (_AC(1, UL) << 30))
-#define EFI_VA_END	 (-68 * (_AC(1, UL) << 30))
+#define MODULES_END		_AC(0xffffffffff000000, UL)
+#define MODULES_LEN		(MODULES_END - MODULES_VADDR)
+
+#define ESPFIX_PGD_ENTRY	_AC(-2, UL)
+#define ESPFIX_BASE_ADDR	(ESPFIX_PGD_ENTRY << P4D_SHIFT)
+
+#define CPU_ENTRY_AREA_PGD	_AC(-4, UL)
+#define CPU_ENTRY_AREA_BASE	(CPU_ENTRY_AREA_PGD << P4D_SHIFT)
+
+#define EFI_VA_START		( -4 * (_AC(1, UL) << 30))
+#define EFI_VA_END		(-68 * (_AC(1, UL) << 30))
 
 #define EARLY_DYNAMIC_PAGE_TABLES	64
 
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 59df7b47a434..246f15b4e64c 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -32,7 +32,6 @@
 
 #define _PAGE_BIT_SPECIAL	_PAGE_BIT_SOFTW1
 #define _PAGE_BIT_CPA_TEST	_PAGE_BIT_SOFTW1
-#define _PAGE_BIT_HIDDEN	_PAGE_BIT_SOFTW3 /* hidden by kmemcheck */
 #define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_SOFTW3 /* software dirty tracking */
 #define _PAGE_BIT_DEVMAP	_PAGE_BIT_SOFTW4
 
@@ -79,18 +78,6 @@
 #define _PAGE_KNL_ERRATUM_MASK 0
 #endif
 
-#ifdef CONFIG_KMEMCHECK
-#define _PAGE_HIDDEN	(_AT(pteval_t, 1) << _PAGE_BIT_HIDDEN)
-#else
-#define _PAGE_HIDDEN	(_AT(pteval_t, 0))
-#endif
-
-/*
- * The same hidden bit is used by kmemcheck, but since kmemcheck
- * works on kernel pages while soft-dirty engine on user space,
- * they do not conflict with each other.
- */
-
 #ifdef CONFIG_MEM_SOFT_DIRTY
 #define _PAGE_SOFT_DIRTY	(_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY)
 #else
@@ -200,10 +187,9 @@ enum page_cache_mode {
 
 #define _PAGE_ENC	(_AT(pteval_t, sme_me_mask))
 
-#define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |	\
-			 _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_ENC)
 #define _KERNPG_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED |	\
 			 _PAGE_DIRTY | _PAGE_ENC)
+#define _PAGE_TABLE	(_KERNPG_TABLE | _PAGE_USER)
 
 #define __PAGE_KERNEL_ENC	(__PAGE_KERNEL | _PAGE_ENC)
 #define __PAGE_KERNEL_ENC_WP	(__PAGE_KERNEL_WP | _PAGE_ENC)
@@ -337,6 +323,11 @@ static inline pudval_t native_pud_val(pud_t pud)
 #else
 #include <asm-generic/pgtable-nopud.h>
 
+static inline pud_t native_make_pud(pudval_t val)
+{
+	return (pud_t) { .p4d.pgd = native_make_pgd(val) };
+}
+
 static inline pudval_t native_pud_val(pud_t pud)
 {
 	return native_pgd_val(pud.p4d.pgd);
@@ -358,6 +349,11 @@ static inline pmdval_t native_pmd_val(pmd_t pmd)
 #else
 #include <asm-generic/pgtable-nopmd.h>
 
+static inline pmd_t native_make_pmd(pmdval_t val)
+{
+	return (pmd_t) { .pud.p4d.pgd = native_make_pgd(val) };
+}
+
 static inline pmdval_t native_pmd_val(pmd_t pmd)
 {
 	return native_pgd_val(pmd.pud.p4d.pgd);
diff --git a/arch/x86/include/asm/pmc_core.h b/arch/x86/include/asm/pmc_core.h
deleted file mode 100644
index d4855f11136d..000000000000
--- a/arch/x86/include/asm/pmc_core.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * Intel Core SoC Power Management Controller Header File
- *
- * Copyright (c) 2016, Intel Corporation.
- * All Rights Reserved.
- *
- * Authors: Rajneesh Bhardwaj <rajneesh.bhardwaj@intel.com>
- *          Vishwanath Somayaji <vishwanath.somayaji@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- */
-
-#ifndef _ASM_PMC_CORE_H
-#define _ASM_PMC_CORE_H
-
-/* API to read SLP_S0_RESIDENCY counter */
-int intel_pmc_slp_s0_counter_read(u32 *data);
-
-#endif /* _ASM_PMC_CORE_H */
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index 43212a43ee69..625a52a5594f 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -38,6 +38,11 @@
 #define CR3_ADDR_MASK	__sme_clr(0x7FFFFFFFFFFFF000ull)
 #define CR3_PCID_MASK	0xFFFull
 #define CR3_NOFLUSH	BIT_ULL(63)
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define X86_CR3_PTI_PCID_USER_BIT	11
+#endif
+
 #else
 /*
  * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index bdac19ab2488..b0ccd4847a58 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -91,7 +91,7 @@ struct cpuinfo_x86 {
 	__u8			x86;		/* CPU family */
 	__u8			x86_vendor;	/* CPU vendor */
 	__u8			x86_model;
-	__u8			x86_mask;
+	__u8			x86_stepping;
 #ifdef CONFIG_X86_64
 	/* Number of 4K pages in DTLB/ITLB combined(in pages): */
 	int			x86_tlbsize;
@@ -109,7 +109,7 @@ struct cpuinfo_x86 {
 	char			x86_vendor_id[16];
 	char			x86_model_id[64];
 	/* in KB - valid for CPUS which support this call: */
-	int			x86_cache_size;
+	unsigned int		x86_cache_size;
 	int			x86_cache_alignment;	/* In bytes */
 	/* Cache QoS architectural values: */
 	int			x86_cache_max_rmid;	/* max index */
@@ -132,6 +132,7 @@ struct cpuinfo_x86 {
 	/* Index into per_cpu list: */
 	u16			cpu_index;
 	u32			microcode;
+	unsigned		initialized : 1;
 } __randomize_layout;
 
 struct cpuid_regs {
@@ -162,9 +163,9 @@ enum cpuid_regs_idx {
 extern struct cpuinfo_x86	boot_cpu_data;
 extern struct cpuinfo_x86	new_cpu_data;
 
-extern struct tss_struct	doublefault_tss;
-extern __u32			cpu_caps_cleared[NCAPINTS];
-extern __u32			cpu_caps_set[NCAPINTS];
+extern struct x86_hw_tss	doublefault_tss;
+extern __u32			cpu_caps_cleared[NCAPINTS + NBUGINTS];
+extern __u32			cpu_caps_set[NCAPINTS + NBUGINTS];
 
 #ifdef CONFIG_SMP
 DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
@@ -252,6 +253,11 @@ static inline void load_cr3(pgd_t *pgdir)
 	write_cr3(__sme_pa(pgdir));
 }
 
+/*
+ * Note that while the legacy 'TSS' name comes from 'Task State Segment',
+ * on modern x86 CPUs the TSS also holds information important to 64-bit mode,
+ * unrelated to the task-switch mechanism:
+ */
 #ifdef CONFIG_X86_32
 /* This is the TSS defined by the hardware. */
 struct x86_hw_tss {
@@ -304,7 +310,13 @@ struct x86_hw_tss {
 struct x86_hw_tss {
 	u32			reserved1;
 	u64			sp0;
+
+	/*
+	 * We store cpu_current_top_of_stack in sp1 so it's always accessible.
+	 * Linux does not use ring 1, so sp1 is not otherwise needed.
+	 */
 	u64			sp1;
+
 	u64			sp2;
 	u64			reserved2;
 	u64			ist[7];
@@ -322,12 +334,22 @@ struct x86_hw_tss {
 #define IO_BITMAP_BITS			65536
 #define IO_BITMAP_BYTES			(IO_BITMAP_BITS/8)
 #define IO_BITMAP_LONGS			(IO_BITMAP_BYTES/sizeof(long))
-#define IO_BITMAP_OFFSET		offsetof(struct tss_struct, io_bitmap)
+#define IO_BITMAP_OFFSET		(offsetof(struct tss_struct, io_bitmap) - offsetof(struct tss_struct, x86_tss))
 #define INVALID_IO_BITMAP_OFFSET	0x8000
 
+struct entry_stack {
+	unsigned long		words[64];
+};
+
+struct entry_stack_page {
+	struct entry_stack stack;
+} __aligned(PAGE_SIZE);
+
 struct tss_struct {
 	/*
-	 * The hardware state:
+	 * The fixed hardware portion.  This must not cross a page boundary
+	 * at risk of violating the SDM's advice and potentially triggering
+	 * errata.
 	 */
 	struct x86_hw_tss	x86_tss;
 
@@ -338,18 +360,9 @@ struct tss_struct {
 	 * be within the limit.
 	 */
 	unsigned long		io_bitmap[IO_BITMAP_LONGS + 1];
+} __aligned(PAGE_SIZE);
 
-#ifdef CONFIG_X86_32
-	/*
-	 * Space for the temporary SYSENTER stack.
-	 */
-	unsigned long		SYSENTER_stack_canary;
-	unsigned long		SYSENTER_stack[64];
-#endif
-
-} ____cacheline_aligned;
-
-DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
+DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw);
 
 /*
  * sizeof(unsigned long) coming from an extra "long" at the end
@@ -363,6 +376,9 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
 
 #ifdef CONFIG_X86_32
 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
+#else
+/* The RO copy can't be accessed with this_cpu_xyz(), so use the RW copy. */
+#define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1
 #endif
 
 /*
@@ -431,7 +447,9 @@ typedef struct {
 struct thread_struct {
 	/* Cached TLS descriptors: */
 	struct desc_struct	tls_array[GDT_ENTRY_TLS_ENTRIES];
+#ifdef CONFIG_X86_32
 	unsigned long		sp0;
+#endif
 	unsigned long		sp;
 #ifdef CONFIG_X86_32
 	unsigned long		sysenter_cs;
@@ -442,8 +460,6 @@ struct thread_struct {
 	unsigned short		gsindex;
 #endif
 
-	u32			status;		/* thread synchronous flags */
-
 #ifdef CONFIG_X86_64
 	unsigned long		fsbase;
 	unsigned long		gsbase;
@@ -489,6 +505,14 @@ struct thread_struct {
 	 */
 };
 
+/* Whitelist the FPU state from the task_struct for hardened usercopy. */
+static inline void arch_thread_struct_whitelist(unsigned long *offset,
+						unsigned long *size)
+{
+	*offset = offsetof(struct thread_struct, fpu.state);
+	*size = fpu_kernel_xstate_size;
+}
+
 /*
  * Thread-synchronous status.
  *
@@ -518,16 +542,9 @@ static inline void native_set_iopl_mask(unsigned mask)
 }
 
 static inline void
-native_load_sp0(struct tss_struct *tss, struct thread_struct *thread)
+native_load_sp0(unsigned long sp0)
 {
-	tss->x86_tss.sp0 = thread->sp0;
-#ifdef CONFIG_X86_32
-	/* Only happens when SEP is enabled, no need to test "SEP"arately: */
-	if (unlikely(tss->x86_tss.ss1 != thread->sysenter_cs)) {
-		tss->x86_tss.ss1 = thread->sysenter_cs;
-		wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
-	}
-#endif
+	this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
 }
 
 static inline void native_swapgs(void)
@@ -539,12 +556,18 @@ static inline void native_swapgs(void)
 
 static inline unsigned long current_top_of_stack(void)
 {
-#ifdef CONFIG_X86_64
-	return this_cpu_read_stable(cpu_tss.x86_tss.sp0);
-#else
-	/* sp0 on x86_32 is special in and around vm86 mode. */
+	/*
+	 *  We can't read directly from tss.sp0: sp0 on x86_32 is special in
+	 *  and around vm86 mode and sp0 on x86_64 is special because of the
+	 *  entry trampoline.
+	 */
 	return this_cpu_read_stable(cpu_current_top_of_stack);
-#endif
+}
+
+static inline bool on_thread_stack(void)
+{
+	return (unsigned long)(current_top_of_stack() -
+			       current_stack_pointer) < THREAD_SIZE;
 }
 
 #ifdef CONFIG_PARAVIRT
@@ -552,10 +575,9 @@ static inline unsigned long current_top_of_stack(void)
 #else
 #define __cpuid			native_cpuid
 
-static inline void load_sp0(struct tss_struct *tss,
-			    struct thread_struct *thread)
+static inline void load_sp0(unsigned long sp0)
 {
-	native_load_sp0(tss, thread);
+	native_load_sp0(sp0);
 }
 
 #define set_iopl_mask native_set_iopl_mask
@@ -804,6 +826,15 @@ static inline void spin_lock_prefetch(const void *x)
 #define TOP_OF_INIT_STACK ((unsigned long)&init_stack + sizeof(init_stack) - \
 			   TOP_OF_KERNEL_STACK_PADDING)
 
+#define task_top_of_stack(task) ((unsigned long)(task_pt_regs(task) + 1))
+
+#define task_pt_regs(task) \
+({									\
+	unsigned long __ptr = (unsigned long)task_stack_page(task);	\
+	__ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;		\
+	((struct pt_regs *)__ptr) - 1;					\
+})
+
 #ifdef CONFIG_X86_32
 /*
  * User space process size: 3GB (default).
@@ -823,34 +854,26 @@ static inline void spin_lock_prefetch(const void *x)
 	.addr_limit		= KERNEL_DS,				  \
 }
 
-/*
- * TOP_OF_KERNEL_STACK_PADDING reserves 8 bytes on top of the ring0 stack.
- * This is necessary to guarantee that the entire "struct pt_regs"
- * is accessible even if the CPU haven't stored the SS/ESP registers
- * on the stack (interrupt gate does not save these registers
- * when switching to the same priv ring).
- * Therefore beware: accessing the ss/esp fields of the
- * "struct pt_regs" is possible, but they may contain the
- * completely wrong values.
- */
-#define task_pt_regs(task) \
-({									\
-	unsigned long __ptr = (unsigned long)task_stack_page(task);	\
-	__ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;		\
-	((struct pt_regs *)__ptr) - 1;					\
-})
-
 #define KSTK_ESP(task)		(task_pt_regs(task)->sp)
 
 #else
 /*
- * User space process size. 47bits minus one guard page.  The guard
- * page is necessary on Intel CPUs: if a SYSCALL instruction is at
- * the highest possible canonical userspace address, then that
- * syscall will enter the kernel with a non-canonical return
- * address, and SYSRET will explode dangerously.  We avoid this
- * particular problem by preventing anything from being mapped
- * at the maximum canonical address.
+ * User space process size.  This is the first address outside the user range.
+ * There are a few constraints that determine this:
+ *
+ * On Intel CPUs, if a SYSCALL instruction is at the highest canonical
+ * address, then that syscall will enter the kernel with a
+ * non-canonical return address, and SYSRET will explode dangerously.
+ * We avoid this particular problem by preventing anything executable
+ * from being mapped at the maximum canonical address.
+ *
+ * On AMD CPUs in the Ryzen family, there's a nasty bug in which the
+ * CPUs malfunction if they execute code from the highest canonical page.
+ * They'll speculate right off the end of the canonical space, and
+ * bad things happen.  This is worked around in the same way as the
+ * Intel problem.
+ *
+ * With page table isolation enabled, we map the LDT in ... [stay tuned]
  */
 #define TASK_SIZE_MAX	((1UL << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE)
 
@@ -873,11 +896,9 @@ static inline void spin_lock_prefetch(const void *x)
 #define STACK_TOP_MAX		TASK_SIZE_MAX
 
 #define INIT_THREAD  {						\
-	.sp0			= TOP_OF_INIT_STACK,		\
 	.addr_limit		= KERNEL_DS,			\
 }
 
-#define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
 extern unsigned long KSTK_ESP(struct task_struct *task);
 
 #endif /* CONFIG_X86_64 */
@@ -956,4 +977,5 @@ bool xen_set_default_idle(void);
 
 void stop_this_cpu(void *dummy);
 void df_debug(struct pt_regs *regs, long error_code);
+void microcode_check(void);
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h
new file mode 100644
index 000000000000..0b5ef05b2d2d
--- /dev/null
+++ b/arch/x86/include/asm/pti.h
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _ASM_X86_PTI_H
+#define _ASM_X86_PTI_H
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+extern void pti_init(void);
+extern void pti_check_boottime_disable(void);
+#else
+static inline void pti_check_boottime_disable(void) { }
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_PTI_H */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index c0e3c45cf6ab..6de1fd3d0097 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -109,6 +109,11 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 	return regs->ax;
 }
 
+static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
+{
+	regs->ax = rc;
+}
+
 /*
  * user_mode(regs) determines whether a register set came from user
  * mode.  On x86_32, this is true if V8086 mode was enabled OR if the
@@ -136,9 +141,9 @@ static inline int v8086_mode(struct pt_regs *regs)
 #endif
 }
 
-#ifdef CONFIG_X86_64
 static inline bool user_64bit_mode(struct pt_regs *regs)
 {
+#ifdef CONFIG_X86_64
 #ifndef CONFIG_PARAVIRT
 	/*
 	 * On non-paravirt systems, this is the only long mode CPL 3
@@ -149,8 +154,12 @@ static inline bool user_64bit_mode(struct pt_regs *regs)
 	/* Headers are too twisted for this to go in paravirt.h. */
 	return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs;
 #endif
+#else /* !CONFIG_X86_64 */
+	return false;
+#endif
 }
 
+#ifdef CONFIG_X86_64
 #define current_user_stack_pointer()	current_pt_regs()->sp
 #define compat_user_stack_pointer()	current_pt_regs()->sp
 #endif
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 3e4ed8fb5f91..a7471dcd2205 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -5,15 +5,6 @@
 #include <linux/clocksource.h>
 #include <asm/pvclock-abi.h>
 
-#ifdef CONFIG_KVM_GUEST
-extern struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void);
-#else
-static inline struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void)
-{
-	return NULL;
-}
-#endif
-
 /* some helper functions for xen and kvm pv clock sources */
 u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
 u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src);
@@ -102,4 +93,14 @@ struct pvclock_vsyscall_time_info {
 
 #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info)
 
+#ifdef CONFIG_PARAVIRT_CLOCK
+void pvclock_set_pvti_cpu0_va(struct pvclock_vsyscall_time_info *pvti);
+struct pvclock_vsyscall_time_info *pvclock_get_pvti_cpu0_va(void);
+#else
+static inline struct pvclock_vsyscall_time_info *pvclock_get_pvti_cpu0_va(void)
+{
+	return NULL;
+}
+#endif
+
 #endif /* _ASM_X86_PVCLOCK_H */
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index 9982dd96f093..5e16b5d40d32 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -2,6 +2,7 @@
 #ifndef _ASM_X86_QSPINLOCK_H
 #define _ASM_X86_QSPINLOCK_H
 
+#include <linux/jump_label.h>
 #include <asm/cpufeature.h>
 #include <asm-generic/qspinlock_types.h>
 #include <asm/paravirt.h>
@@ -47,10 +48,14 @@ static inline void queued_spin_unlock(struct qspinlock *lock)
 #endif
 
 #ifdef CONFIG_PARAVIRT
+DECLARE_STATIC_KEY_TRUE(virt_spin_lock_key);
+
+void native_pv_lock_init(void) __init;
+
 #define virt_spin_lock virt_spin_lock
 static inline bool virt_spin_lock(struct qspinlock *lock)
 {
-	if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
+	if (!static_branch_likely(&virt_spin_lock_key))
 		return false;
 
 	/*
@@ -66,6 +71,10 @@ static inline bool virt_spin_lock(struct qspinlock *lock)
 
 	return true;
 }
+#else
+static inline void native_pv_lock_init(void)
+{
+}
 #endif /* CONFIG_PARAVIRT */
 
 #include <asm-generic/qspinlock.h>
diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
index ff871210b9f2..4cf11d88d3b3 100644
--- a/arch/x86/include/asm/refcount.h
+++ b/arch/x86/include/asm/refcount.h
@@ -15,9 +15,9 @@
  * back to the regular execution flow in .text.
  */
 #define _REFCOUNT_EXCEPTION				\
-	".pushsection .text.unlikely\n"			\
+	".pushsection .text..refcount\n"		\
 	"111:\tlea %[counter], %%" _ASM_CX "\n"		\
-	"112:\t" ASM_UD0 "\n"				\
+	"112:\t" ASM_UD2 "\n"				\
 	ASM_UNREACHABLE					\
 	".popsection\n"					\
 	"113:\n"					\
@@ -67,13 +67,13 @@ static __always_inline __must_check
 bool refcount_sub_and_test(unsigned int i, refcount_t *r)
 {
 	GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO,
-				  r->refs.counter, "er", i, "%0", e);
+				  r->refs.counter, "er", i, "%0", e, "cx");
 }
 
 static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r)
 {
 	GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", REFCOUNT_CHECK_LT_ZERO,
-				 r->refs.counter, "%0", e);
+				 r->refs.counter, "%0", e, "cx");
 }
 
 static __always_inline __must_check
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index d91ba04dd007..fb3a6de7440b 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -106,6 +106,7 @@
 #define REQUIRED_MASK15	0
 #define REQUIRED_MASK16	(NEED_LA57)
 #define REQUIRED_MASK17	0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18)
+#define REQUIRED_MASK18	0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index d8f3a6ae9f6c..4914a3e7c803 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -2,8 +2,7 @@
 #ifndef _ASM_X86_RMWcc
 #define _ASM_X86_RMWcc
 
-#define __CLOBBERS_MEM		"memory"
-#define __CLOBBERS_MEM_CC_CX	"memory", "cc", "cx"
+#define __CLOBBERS_MEM(clb...)	"memory", ## clb
 
 #if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CC_HAVE_ASM_GOTO)
 
@@ -29,7 +28,7 @@ cc_label:								\
 #define __GEN_RMWcc(fullop, var, cc, clobbers, ...)			\
 do {									\
 	bool c;								\
-	asm volatile (fullop ";" CC_SET(cc)				\
+	asm volatile (fullop CC_SET(cc)					\
 			: [counter] "+m" (var), CC_OUT(cc) (c)		\
 			: __VA_ARGS__ : clobbers);			\
 	return c;							\
@@ -40,18 +39,19 @@ do {									\
 #endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */
 
 #define GEN_UNARY_RMWcc(op, var, arg0, cc)				\
-	__GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM)
+	__GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM())
 
-#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc)		\
+#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, arg0, cc, clobbers...)\
 	__GEN_RMWcc(op " " arg0 "\n\t" suffix, var, cc,			\
-		    __CLOBBERS_MEM_CC_CX)
+		    __CLOBBERS_MEM(clobbers))
 
 #define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
 	__GEN_RMWcc(op __BINARY_RMWcc_ARG arg0, var, cc,		\
-		    __CLOBBERS_MEM, vcon (val))
+		    __CLOBBERS_MEM(), vcon (val))
 
-#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc)	\
+#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, vcon, val, arg0, cc,	\
+				  clobbers...)				\
 	__GEN_RMWcc(op __BINARY_RMWcc_ARG arg0 "\n\t" suffix, var, cc,	\
-		    __CLOBBERS_MEM_CC_CX, vcon (val))
+		    __CLOBBERS_MEM(clobbers), vcon (val))
 
 #endif /* _ASM_X86_RMWcc */
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index 4d38d85a16ad..4c25cf6caefa 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -61,18 +61,33 @@
 /*
  * lock for reading
  */
+#define ____down_read(sem, slow_path)					\
+({									\
+	struct rw_semaphore* ret;					\
+	asm volatile("# beginning down_read\n\t"			\
+		     LOCK_PREFIX _ASM_INC "(%[sem])\n\t"		\
+		     /* adds 0x00000001 */				\
+		     "  jns        1f\n"				\
+		     "  call " slow_path "\n"				\
+		     "1:\n\t"						\
+		     "# ending down_read\n\t"				\
+		     : "+m" (sem->count), "=a" (ret),			\
+			ASM_CALL_CONSTRAINT				\
+		     : [sem] "a" (sem)					\
+		     : "memory", "cc");					\
+	ret;								\
+})
+
 static inline void __down_read(struct rw_semaphore *sem)
 {
-	asm volatile("# beginning down_read\n\t"
-		     LOCK_PREFIX _ASM_INC "(%1)\n\t"
-		     /* adds 0x00000001 */
-		     "  jns        1f\n"
-		     "  call call_rwsem_down_read_failed\n"
-		     "1:\n\t"
-		     "# ending down_read\n\t"
-		     : "+m" (sem->count)
-		     : "a" (sem)
-		     : "memory", "cc");
+	____down_read(sem, "call_rwsem_down_read_failed");
+}
+
+static inline int __down_read_killable(struct rw_semaphore *sem)
+{
+	if (IS_ERR(____down_read(sem, "call_rwsem_down_read_failed_killable")))
+		return -EINTR;
+	return 0;
 }
 
 /*
@@ -82,17 +97,18 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem)
 {
 	long result, tmp;
 	asm volatile("# beginning __down_read_trylock\n\t"
-		     "  mov          %0,%1\n\t"
+		     "  mov          %[count],%[result]\n\t"
 		     "1:\n\t"
-		     "  mov          %1,%2\n\t"
-		     "  add          %3,%2\n\t"
+		     "  mov          %[result],%[tmp]\n\t"
+		     "  add          %[inc],%[tmp]\n\t"
 		     "  jle	     2f\n\t"
-		     LOCK_PREFIX "  cmpxchg  %2,%0\n\t"
+		     LOCK_PREFIX "  cmpxchg  %[tmp],%[count]\n\t"
 		     "  jnz	     1b\n\t"
 		     "2:\n\t"
 		     "# ending __down_read_trylock\n\t"
-		     : "+m" (sem->count), "=&a" (result), "=&r" (tmp)
-		     : "i" (RWSEM_ACTIVE_READ_BIAS)
+		     : [count] "+m" (sem->count), [result] "=&a" (result),
+		       [tmp] "=&r" (tmp)
+		     : [inc] "i" (RWSEM_ACTIVE_READ_BIAS)
 		     : "memory", "cc");
 	return result >= 0;
 }
@@ -106,7 +122,7 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem)
 	struct rw_semaphore* ret;			\
 							\
 	asm volatile("# beginning down_write\n\t"	\
-		     LOCK_PREFIX "  xadd      %1,(%4)\n\t"	\
+		     LOCK_PREFIX "  xadd      %[tmp],(%[sem])\n\t"	\
 		     /* adds 0xffff0001, returns the old value */ \
 		     "  test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" \
 		     /* was the active mask 0 before? */\
@@ -114,9 +130,9 @@ static inline bool __down_read_trylock(struct rw_semaphore *sem)
 		     "  call " slow_path "\n"		\
 		     "1:\n"				\
 		     "# ending down_write"		\
-		     : "+m" (sem->count), "=d" (tmp),	\
+		     : "+m" (sem->count), [tmp] "=d" (tmp),	\
 		       "=a" (ret), ASM_CALL_CONSTRAINT	\
-		     : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) \
+		     : [sem] "a" (sem), "[tmp]" (RWSEM_ACTIVE_WRITE_BIAS) \
 		     : "memory", "cc");			\
 	ret;						\
 })
@@ -142,21 +158,21 @@ static inline bool __down_write_trylock(struct rw_semaphore *sem)
 	bool result;
 	long tmp0, tmp1;
 	asm volatile("# beginning __down_write_trylock\n\t"
-		     "  mov          %0,%1\n\t"
+		     "  mov          %[count],%[tmp0]\n\t"
 		     "1:\n\t"
 		     "  test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t"
 		     /* was the active mask 0 before? */
 		     "  jnz          2f\n\t"
-		     "  mov          %1,%2\n\t"
-		     "  add          %4,%2\n\t"
-		     LOCK_PREFIX "  cmpxchg  %2,%0\n\t"
+		     "  mov          %[tmp0],%[tmp1]\n\t"
+		     "  add          %[inc],%[tmp1]\n\t"
+		     LOCK_PREFIX "  cmpxchg  %[tmp1],%[count]\n\t"
 		     "  jnz	     1b\n\t"
 		     "2:\n\t"
 		     CC_SET(e)
 		     "# ending __down_write_trylock\n\t"
-		     : "+m" (sem->count), "=&a" (tmp0), "=&r" (tmp1),
-		       CC_OUT(e) (result)
-		     : "er" (RWSEM_ACTIVE_WRITE_BIAS)
+		     : [count] "+m" (sem->count), [tmp0] "=&a" (tmp0),
+		       [tmp1] "=&r" (tmp1), CC_OUT(e) (result)
+		     : [inc] "er" (RWSEM_ACTIVE_WRITE_BIAS)
 		     : "memory");
 	return result;
 }
@@ -168,14 +184,14 @@ static inline void __up_read(struct rw_semaphore *sem)
 {
 	long tmp;
 	asm volatile("# beginning __up_read\n\t"
-		     LOCK_PREFIX "  xadd      %1,(%2)\n\t"
+		     LOCK_PREFIX "  xadd      %[tmp],(%[sem])\n\t"
 		     /* subtracts 1, returns the old value */
 		     "  jns        1f\n\t"
 		     "  call call_rwsem_wake\n" /* expects old value in %edx */
 		     "1:\n"
 		     "# ending __up_read\n"
-		     : "+m" (sem->count), "=d" (tmp)
-		     : "a" (sem), "1" (-RWSEM_ACTIVE_READ_BIAS)
+		     : "+m" (sem->count), [tmp] "=d" (tmp)
+		     : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_READ_BIAS)
 		     : "memory", "cc");
 }
 
@@ -186,14 +202,14 @@ static inline void __up_write(struct rw_semaphore *sem)
 {
 	long tmp;
 	asm volatile("# beginning __up_write\n\t"
-		     LOCK_PREFIX "  xadd      %1,(%2)\n\t"
+		     LOCK_PREFIX "  xadd      %[tmp],(%[sem])\n\t"
 		     /* subtracts 0xffff0001, returns the old value */
 		     "  jns        1f\n\t"
 		     "  call call_rwsem_wake\n" /* expects old value in %edx */
 		     "1:\n\t"
 		     "# ending __up_write\n"
-		     : "+m" (sem->count), "=d" (tmp)
-		     : "a" (sem), "1" (-RWSEM_ACTIVE_WRITE_BIAS)
+		     : "+m" (sem->count), [tmp] "=d" (tmp)
+		     : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_WRITE_BIAS)
 		     : "memory", "cc");
 }
 
@@ -203,7 +219,7 @@ static inline void __up_write(struct rw_semaphore *sem)
 static inline void __downgrade_write(struct rw_semaphore *sem)
 {
 	asm volatile("# beginning __downgrade_write\n\t"
-		     LOCK_PREFIX _ASM_ADD "%2,(%1)\n\t"
+		     LOCK_PREFIX _ASM_ADD "%[inc],(%[sem])\n\t"
 		     /*
 		      * transitions 0xZZZZ0001 -> 0xYYYY0001 (i386)
 		      *     0xZZZZZZZZ00000001 -> 0xYYYYYYYY00000001 (x86_64)
@@ -213,7 +229,7 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 		     "1:\n\t"
 		     "# ending __downgrade_write\n"
 		     : "+m" (sem->count)
-		     : "a" (sem), "er" (-RWSEM_WAITING_BIAS)
+		     : [sem] "a" (sem), [inc] "er" (-RWSEM_WAITING_BIAS)
 		     : "memory", "cc");
 }
 
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index b20f9d623f9c..8f09012b92e7 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -236,11 +236,23 @@
  */
 #define EARLY_IDT_HANDLER_SIZE 9
 
+/*
+ * xen_early_idt_handler_array is for Xen pv guests: for each entry in
+ * early_idt_handler_array it contains a prequel in the form of
+ * pop %rcx; pop %r11; jmp early_idt_handler_array[i]; summing up to
+ * max 8 bytes.
+ */
+#define XEN_EARLY_IDT_HANDLER_SIZE 8
+
 #ifndef __ASSEMBLY__
 
 extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE];
 extern void early_ignore_irq(void);
 
+#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV)
+extern const char xen_early_idt_handler_array[NUM_EXCEPTION_VECTORS][XEN_EARLY_IDT_HANDLER_SIZE];
+#endif
+
 /*
  * Load a segment. Fall back on loading the zero segment if something goes
  * wrong.  This variant assumes that loading zero fully clears the segment.
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 461f53d27708..a4189762b266 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -129,6 +129,7 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 void cpu_disable_common(void);
 void native_smp_prepare_boot_cpu(void);
 void native_smp_prepare_cpus(unsigned int max_cpus);
+void calculate_max_logical_packages(void);
 void native_smp_cpus_done(unsigned int max_cpus);
 void common_cpu_up(unsigned int cpunum, struct task_struct *tidle);
 int native_cpu_up(unsigned int cpunum, struct task_struct *tidle);
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index b34625796eb2..5b6bc7016c22 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -42,11 +42,4 @@
 
 #include <asm/qrwlock.h>
 
-#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
-#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-
-#define arch_spin_relax(lock)	cpu_relax()
-#define arch_read_relax(lock)	cpu_relax()
-#define arch_write_relax(lock)	cpu_relax()
-
 #endif /* _ASM_X86_SPINLOCK_H */
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 8da111b3c342..f73706878772 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -16,6 +16,7 @@ enum stack_type {
 	STACK_TYPE_TASK,
 	STACK_TYPE_IRQ,
 	STACK_TYPE_SOFTIRQ,
+	STACK_TYPE_ENTRY,
 	STACK_TYPE_EXCEPTION,
 	STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1,
 };
@@ -28,6 +29,8 @@ struct stack_info {
 bool in_task_stack(unsigned long *stack, struct task_struct *task,
 		   struct stack_info *info);
 
+bool in_entry_stack(unsigned long *stack, struct stack_info *info);
+
 int get_stack_info(unsigned long *stack, struct task_struct *task,
 		   struct stack_info *info, unsigned long *visit_mask);
 
diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h
index 076502241eae..55d392c6bd29 100644
--- a/arch/x86/include/asm/string_32.h
+++ b/arch/x86/include/asm/string_32.h
@@ -179,8 +179,6 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len)
  *	No 3D Now!
  */
 
-#ifndef CONFIG_KMEMCHECK
-
 #if (__GNUC__ >= 4)
 #define memcpy(t, f, n) __builtin_memcpy(t, f, n)
 #else
@@ -189,13 +187,6 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len)
 	 ? __constant_memcpy((t), (f), (n))	\
 	 : __memcpy((t), (f), (n)))
 #endif
-#else
-/*
- * kmemcheck becomes very happy if we use the REP instructions unconditionally,
- * because it means that we know both memory operands in advance.
- */
-#define memcpy(t, f, n) __memcpy((t), (f), (n))
-#endif
 
 #endif
 #endif /* !CONFIG_FORTIFY_SOURCE */
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 0b1b4445f4c5..533f74c300c2 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -33,7 +33,6 @@ extern void *memcpy(void *to, const void *from, size_t len);
 extern void *__memcpy(void *to, const void *from, size_t len);
 
 #ifndef CONFIG_FORTIFY_SOURCE
-#ifndef CONFIG_KMEMCHECK
 #if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4
 #define memcpy(dst, src, len)					\
 ({								\
@@ -46,13 +45,6 @@ extern void *__memcpy(void *to, const void *from, size_t len);
 	__ret;							\
 })
 #endif
-#else
-/*
- * kmemcheck becomes very happy if we use the REP instructions unconditionally,
- * because it means that we know both memory operands in advance.
- */
-#define memcpy(dst, src, len) __inline_memcpy((dst), (src), (len))
-#endif
 #endif /* !CONFIG_FORTIFY_SOURCE */
 
 #define __HAVE_ARCH_MEMSET
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index 982c325dad33..8be6afb58471 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -12,7 +12,13 @@
 
 /* image of the saved processor state */
 struct saved_context {
-	u16 es, fs, gs, ss;
+	/*
+	 * On x86_32, all segment registers, with the possible exception of
+	 * gs, are saved at kernel entry in pt_regs.
+	 */
+#ifdef CONFIG_X86_32_LAZY_GS
+	u16 gs;
+#endif
 	unsigned long cr0, cr2, cr3, cr4;
 	u64 misc_enable;
 	bool misc_enable_saved;
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index 7306e911faee..a7af9f53c0cb 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -20,8 +20,20 @@
  */
 struct saved_context {
 	struct pt_regs regs;
-	u16 ds, es, fs, gs, ss;
-	unsigned long gs_base, gs_kernel_base, fs_base;
+
+	/*
+	 * User CS and SS are saved in current_pt_regs().  The rest of the
+	 * segment selectors need to be saved and restored here.
+	 */
+	u16 ds, es, fs, gs;
+
+	/*
+	 * Usermode FSBASE and GSBASE may not match the fs and gs selectors,
+	 * so we save them separately.  We save the kernelmode GSBASE to
+	 * restore percpu access after resume.
+	 */
+	unsigned long kernelmode_gs_base, usermode_gs_base, fs_base;
+
 	unsigned long cr0, cr2, cr3, cr4, cr8;
 	u64 misc_enable;
 	bool misc_enable_saved;
@@ -30,8 +42,7 @@ struct saved_context {
 	u16 gdt_pad; /* Unused */
 	struct desc_ptr gdt_desc;
 	u16 idt_pad;
-	u16 idt_limit;
-	unsigned long idt_base;
+	struct desc_ptr idt;
 	u16 ldt;
 	u16 tss;
 	unsigned long tr;
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 78dd9df88157..0487ac054870 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -146,6 +146,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
 #define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL
 #define SVM_VM_CR_SVM_DIS_MASK  0x0010ULL
 
+#define SVM_NESTED_CTL_NP_ENABLE	BIT(0)
+#define SVM_NESTED_CTL_SEV_ENABLE	BIT(1)
+
 struct __attribute__ ((__packed__)) vmcb_seg {
 	u16 selector;
 	u16 attrib;
diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h
index bdf9aed40403..1c6a6cb230ff 100644
--- a/arch/x86/include/asm/swiotlb.h
+++ b/arch/x86/include/asm/swiotlb.h
@@ -28,8 +28,6 @@ static inline void pci_swiotlb_late_init(void)
 }
 #endif
 
-static inline void dma_mark_clean(void *addr, size_t size) {}
-
 extern void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 					dma_addr_t *dma_handle, gfp_t flags,
 					unsigned long attrs);
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 899084b70412..eb5f7999a893 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_SWITCH_TO_H
 #define _ASM_X86_SWITCH_TO_H
 
+#include <linux/sched/task_stack.h>
+
 struct task_struct; /* one of the stranger aspects of C forward declarations */
 
 struct task_struct *__switch_to_asm(struct task_struct *prev,
@@ -14,8 +16,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		      struct tss_struct *tss);
 
 /* This runs runs on the previous thread's stack. */
-static inline void prepare_switch_to(struct task_struct *prev,
-				     struct task_struct *next)
+static inline void prepare_switch_to(struct task_struct *next)
 {
 #ifdef CONFIG_VMAP_STACK
 	/*
@@ -68,9 +69,33 @@ struct fork_frame {
 
 #define switch_to(prev, next, last)					\
 do {									\
-	prepare_switch_to(prev, next);					\
+	prepare_switch_to(next);					\
 									\
 	((last) = __switch_to_asm((prev), (next)));			\
 } while (0)
 
+#ifdef CONFIG_X86_32
+static inline void refresh_sysenter_cs(struct thread_struct *thread)
+{
+	/* Only happens when SEP is enabled, no need to test "SEP"arately: */
+	if (unlikely(this_cpu_read(cpu_tss_rw.x86_tss.ss1) == thread->sysenter_cs))
+		return;
+
+	this_cpu_write(cpu_tss_rw.x86_tss.ss1, thread->sysenter_cs);
+	wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
+}
+#endif
+
+/* This is used when switching tasks or entering/exiting vm86 mode. */
+static inline void update_sp0(struct task_struct *task)
+{
+	/* On x86_64, sp0 always points to the entry trampoline stack, which is constant: */
+#ifdef CONFIG_X86_32
+	load_sp0(task->thread.sp0);
+#else
+	if (static_cpu_has(X86_FEATURE_XENPV))
+		load_sp0(task_top_of_stack(task));
+#endif
+}
+
 #endif /* _ASM_X86_SWITCH_TO_H */
diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h
new file mode 100644
index 000000000000..c67caafd3381
--- /dev/null
+++ b/arch/x86/include/asm/sync_core.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_SYNC_CORE_H
+#define _ASM_X86_SYNC_CORE_H
+
+#include <linux/preempt.h>
+#include <asm/processor.h>
+#include <asm/cpufeature.h>
+
+/*
+ * Ensure that a core serializing instruction is issued before returning
+ * to user-mode. x86 implements return to user-space through sysexit,
+ * sysrel, and sysretq, which are not core serializing.
+ */
+static inline void sync_core_before_usermode(void)
+{
+	/* With PTI, we unconditionally serialize before running user code. */
+	if (static_cpu_has(X86_FEATURE_PTI))
+		return;
+	/*
+	 * Return from interrupt and NMI is done through iret, which is core
+	 * serializing.
+	 */
+	if (in_irq() || in_nmi())
+		return;
+	sync_core();
+}
+
+#endif /* _ASM_X86_SYNC_CORE_H */
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index e3c95e8e61c5..03eedc21246d 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -60,7 +60,7 @@ static inline long syscall_get_error(struct task_struct *task,
 	 * TS_COMPAT is set for 32-bit syscall entries and then
 	 * remains set until we return to user mode.
 	 */
-	if (task->thread.status & (TS_COMPAT|TS_I386_REGS_POKED))
+	if (task->thread_info.status & (TS_COMPAT|TS_I386_REGS_POKED))
 		/*
 		 * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
 		 * and will match correctly in comparisons.
@@ -116,7 +116,7 @@ static inline void syscall_get_arguments(struct task_struct *task,
 					 unsigned long *args)
 {
 # ifdef CONFIG_IA32_EMULATION
-	if (task->thread.status & TS_COMPAT)
+	if (task->thread_info.status & TS_COMPAT)
 		switch (i) {
 		case 0:
 			if (!n--) break;
@@ -177,7 +177,7 @@ static inline void syscall_set_arguments(struct task_struct *task,
 					 const unsigned long *args)
 {
 # ifdef CONFIG_IA32_EMULATION
-	if (task->thread.status & TS_COMPAT)
+	if (task->thread_info.status & TS_COMPAT)
 		switch (i) {
 		case 0:
 			if (!n--) break;
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 91dfcafe27a6..bad25bb80679 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -21,7 +21,7 @@ asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
 asmlinkage long sys_iopl(unsigned int);
 
 /* kernel/ldt.c */
-asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
+asmlinkage long sys_modify_ldt(int, void __user *, unsigned long);
 
 /* kernel/signal.c */
 asmlinkage long sys_rt_sigreturn(void);
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 70f425947dc5..a5d9521bb2cb 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -55,6 +55,7 @@ struct task_struct;
 
 struct thread_info {
 	unsigned long		flags;		/* low level flags */
+	u32			status;		/* thread synchronous flags */
 };
 
 #define INIT_THREAD_INFO(tsk)			\
@@ -62,8 +63,6 @@ struct thread_info {
 	.flags		= 0,			\
 }
 
-#define init_stack		(init_thread_union.stack)
-
 #else /* !__ASSEMBLY__ */
 
 #include <asm/asm-offsets.h>
@@ -207,7 +206,7 @@ static inline int arch_within_stack_frames(const void * const stack,
 #else /* !__ASSEMBLY__ */
 
 #ifdef CONFIG_X86_64
-# define cpu_current_top_of_stack (cpu_tss + TSS_sp0)
+# define cpu_current_top_of_stack (cpu_tss_rw + TSS_sp1)
 #endif
 
 #endif
@@ -221,7 +220,7 @@ static inline int arch_within_stack_frames(const void * const stack,
 #define in_ia32_syscall() true
 #else
 #define in_ia32_syscall() (IS_ENABLED(CONFIG_IA32_EMULATION) && \
-			   current->thread.status & TS_COMPAT)
+			   current_thread_info()->status & TS_COMPAT)
 #endif
 
 /*
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index 47457ab975fd..7365dd4acffb 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -9,7 +9,7 @@
 #define TICK_SIZE (tick_nsec / 1000)
 
 unsigned long long native_sched_clock(void);
-extern int recalibrate_cpu_khz(void);
+extern void recalibrate_cpu_khz(void);
 
 extern int no_timer_check;
 
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 509046cfa5ce..84137c22fdfa 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -9,70 +9,130 @@
 #include <asm/cpufeature.h>
 #include <asm/special_insns.h>
 #include <asm/smp.h>
+#include <asm/invpcid.h>
+#include <asm/pti.h>
+#include <asm/processor-flags.h>
 
-static inline void __invpcid(unsigned long pcid, unsigned long addr,
-			     unsigned long type)
-{
-	struct { u64 d[2]; } desc = { { pcid, addr } };
+/*
+ * The x86 feature is called PCID (Process Context IDentifier). It is similar
+ * to what is traditionally called ASID on the RISC processors.
+ *
+ * We don't use the traditional ASID implementation, where each process/mm gets
+ * its own ASID and flush/restart when we run out of ASID space.
+ *
+ * Instead we have a small per-cpu array of ASIDs and cache the last few mm's
+ * that came by on this CPU, allowing cheaper switch_mm between processes on
+ * this CPU.
+ *
+ * We end up with different spaces for different things. To avoid confusion we
+ * use different names for each of them:
+ *
+ * ASID  - [0, TLB_NR_DYN_ASIDS-1]
+ *         the canonical identifier for an mm
+ *
+ * kPCID - [1, TLB_NR_DYN_ASIDS]
+ *         the value we write into the PCID part of CR3; corresponds to the
+ *         ASID+1, because PCID 0 is special.
+ *
+ * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS]
+ *         for KPTI each mm has two address spaces and thus needs two
+ *         PCID values, but we can still do with a single ASID denomination
+ *         for each mm. Corresponds to kPCID + 2048.
+ *
+ */
 
-	/*
-	 * The memory clobber is because the whole point is to invalidate
-	 * stale TLB entries and, especially if we're flushing global
-	 * mappings, we don't want the compiler to reorder any subsequent
-	 * memory accesses before the TLB flush.
-	 *
-	 * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
-	 * invpcid (%rcx), %rax in long mode.
-	 */
-	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
-		      : : "m" (desc), "a" (type), "c" (&desc) : "memory");
-}
+/* There are 12 bits of space for ASIDS in CR3 */
+#define CR3_HW_ASID_BITS		12
+
+/*
+ * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for
+ * user/kernel switches
+ */
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define PTI_CONSUMED_PCID_BITS	1
+#else
+# define PTI_CONSUMED_PCID_BITS	0
+#endif
 
-#define INVPCID_TYPE_INDIV_ADDR		0
-#define INVPCID_TYPE_SINGLE_CTXT	1
-#define INVPCID_TYPE_ALL_INCL_GLOBAL	2
-#define INVPCID_TYPE_ALL_NON_GLOBAL	3
+#define CR3_AVAIL_PCID_BITS (X86_CR3_PCID_BITS - PTI_CONSUMED_PCID_BITS)
 
-/* Flush all mappings for a given pcid and addr, not including globals. */
-static inline void invpcid_flush_one(unsigned long pcid,
-				     unsigned long addr)
-{
-	__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
-}
+/*
+ * ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid.  -1 below to account
+ * for them being zero-based.  Another -1 is because PCID 0 is reserved for
+ * use by non-PCID-aware users.
+ */
+#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_PCID_BITS) - 2)
 
-/* Flush all mappings for a given PCID, not including globals. */
-static inline void invpcid_flush_single_context(unsigned long pcid)
+/*
+ * 6 because 6 should be plenty and struct tlb_state will fit in two cache
+ * lines.
+ */
+#define TLB_NR_DYN_ASIDS	6
+
+/*
+ * Given @asid, compute kPCID
+ */
+static inline u16 kern_pcid(u16 asid)
 {
-	__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	/*
+	 * Make sure that the dynamic ASID space does not confict with the
+	 * bit we are using to switch between user and kernel ASIDs.
+	 */
+	BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_PCID_USER_BIT));
+
+	/*
+	 * The ASID being passed in here should have respected the
+	 * MAX_ASID_AVAILABLE and thus never have the switch bit set.
+	 */
+	VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_PCID_USER_BIT));
+#endif
+	/*
+	 * The dynamically-assigned ASIDs that get passed in are small
+	 * (<TLB_NR_DYN_ASIDS).  They never have the high switch bit set,
+	 * so do not bother to clear it.
+	 *
+	 * If PCID is on, ASID-aware code paths put the ASID+1 into the
+	 * PCID bits.  This serves two purposes.  It prevents a nasty
+	 * situation in which PCID-unaware code saves CR3, loads some other
+	 * value (with PCID == 0), and then restores CR3, thus corrupting
+	 * the TLB for ASID 0 if the saved ASID was nonzero.  It also means
+	 * that any bugs involving loading a PCID-enabled CR3 with
+	 * CR4.PCIDE off will trigger deterministically.
+	 */
+	return asid + 1;
 }
 
-/* Flush all mappings, including globals, for all PCIDs. */
-static inline void invpcid_flush_all(void)
+/*
+ * Given @asid, compute uPCID
+ */
+static inline u16 user_pcid(u16 asid)
 {
-	__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+	u16 ret = kern_pcid(asid);
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	ret |= 1 << X86_CR3_PTI_PCID_USER_BIT;
+#endif
+	return ret;
 }
 
-/* Flush all mappings for all PCIDs except globals. */
-static inline void invpcid_flush_all_nonglobals(void)
+struct pgd_t;
+static inline unsigned long build_cr3(pgd_t *pgd, u16 asid)
 {
-	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+	if (static_cpu_has(X86_FEATURE_PCID)) {
+		return __sme_pa(pgd) | kern_pcid(asid);
+	} else {
+		VM_WARN_ON_ONCE(asid != 0);
+		return __sme_pa(pgd);
+	}
 }
 
-static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
+static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
 {
-	u64 new_tlb_gen;
-
-	/*
-	 * Bump the generation count.  This also serves as a full barrier
-	 * that synchronizes with switch_mm(): callers are required to order
-	 * their read of mm_cpumask after their writes to the paging
-	 * structures.
-	 */
-	smp_mb__before_atomic();
-	new_tlb_gen = atomic64_inc_return(&mm->context.tlb_gen);
-	smp_mb__after_atomic();
-
-	return new_tlb_gen;
+	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+	VM_WARN_ON_ONCE(!this_cpu_has(X86_FEATURE_PCID));
+	return __sme_pa(pgd) | kern_pcid(asid) | CR3_NOFLUSH;
 }
 
 #ifdef CONFIG_PARAVIRT
@@ -80,7 +140,7 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
 #else
 #define __flush_tlb() __native_flush_tlb()
 #define __flush_tlb_global() __native_flush_tlb_global()
-#define __flush_tlb_single(addr) __native_flush_tlb_single(addr)
+#define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr)
 #endif
 
 static inline bool tlb_defer_switch_to_init_mm(void)
@@ -99,12 +159,6 @@ static inline bool tlb_defer_switch_to_init_mm(void)
 	return !static_cpu_has(X86_FEATURE_PCID);
 }
 
-/*
- * 6 because 6 should be plenty and struct tlb_state will fit in
- * two cache lines.
- */
-#define TLB_NR_DYN_ASIDS 6
-
 struct tlb_context {
 	u64 ctx_id;
 	u64 tlb_gen;
@@ -120,6 +174,8 @@ struct tlb_state {
 	struct mm_struct *loaded_mm;
 	u16 loaded_mm_asid;
 	u16 next_asid;
+	/* last user mm's ctx id */
+	u64 last_ctx_id;
 
 	/*
 	 * We can be in one of several states:
@@ -139,6 +195,24 @@ struct tlb_state {
 	bool is_lazy;
 
 	/*
+	 * If set we changed the page tables in such a way that we
+	 * needed an invalidation of all contexts (aka. PCIDs / ASIDs).
+	 * This tells us to go invalidate all the non-loaded ctxs[]
+	 * on the next context switch.
+	 *
+	 * The current ctx was kept up-to-date as it ran and does not
+	 * need to be invalidated.
+	 */
+	bool invalidate_other;
+
+	/*
+	 * Mask that contains TLB_NR_DYN_ASIDS+1 bits to indicate
+	 * the corresponding user PCID needs a flush next time we
+	 * switch to it; see SWITCH_TO_USER_CR3.
+	 */
+	unsigned short user_pcid_flush_mask;
+
+	/*
 	 * Access to this CR4 shadow and to H/W CR4 is protected by
 	 * disabling interrupts when modifying either one.
 	 */
@@ -173,40 +247,43 @@ static inline void cr4_init_shadow(void)
 	this_cpu_write(cpu_tlbstate.cr4, __read_cr4());
 }
 
+static inline void __cr4_set(unsigned long cr4)
+{
+	lockdep_assert_irqs_disabled();
+	this_cpu_write(cpu_tlbstate.cr4, cr4);
+	__write_cr4(cr4);
+}
+
 /* Set in this cpu's CR4. */
 static inline void cr4_set_bits(unsigned long mask)
 {
-	unsigned long cr4;
+	unsigned long cr4, flags;
 
+	local_irq_save(flags);
 	cr4 = this_cpu_read(cpu_tlbstate.cr4);
-	if ((cr4 | mask) != cr4) {
-		cr4 |= mask;
-		this_cpu_write(cpu_tlbstate.cr4, cr4);
-		__write_cr4(cr4);
-	}
+	if ((cr4 | mask) != cr4)
+		__cr4_set(cr4 | mask);
+	local_irq_restore(flags);
 }
 
 /* Clear in this cpu's CR4. */
 static inline void cr4_clear_bits(unsigned long mask)
 {
-	unsigned long cr4;
+	unsigned long cr4, flags;
 
+	local_irq_save(flags);
 	cr4 = this_cpu_read(cpu_tlbstate.cr4);
-	if ((cr4 & ~mask) != cr4) {
-		cr4 &= ~mask;
-		this_cpu_write(cpu_tlbstate.cr4, cr4);
-		__write_cr4(cr4);
-	}
+	if ((cr4 & ~mask) != cr4)
+		__cr4_set(cr4 & ~mask);
+	local_irq_restore(flags);
 }
 
-static inline void cr4_toggle_bits(unsigned long mask)
+static inline void cr4_toggle_bits_irqsoff(unsigned long mask)
 {
 	unsigned long cr4;
 
 	cr4 = this_cpu_read(cpu_tlbstate.cr4);
-	cr4 ^= mask;
-	this_cpu_write(cpu_tlbstate.cr4, cr4);
-	__write_cr4(cr4);
+	__cr4_set(cr4 ^ mask);
 }
 
 /* Read the CR4 shadow. */
@@ -216,6 +293,14 @@ static inline unsigned long cr4_read_shadow(void)
 }
 
 /*
+ * Mark all other ASIDs as invalid, preserves the current.
+ */
+static inline void invalidate_other_asid(void)
+{
+	this_cpu_write(cpu_tlbstate.invalidate_other, true);
+}
+
+/*
  * Save some of cr4 feature set we're using (e.g.  Pentium 4MB
  * enable and PPro Global page enable), so that any CPU's that boot
  * up after us can get the correct flags.  This should only be used
@@ -234,37 +319,63 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask)
 
 extern void initialize_tlbstate_and_flush(void);
 
-static inline void __native_flush_tlb(void)
+/*
+ * Given an ASID, flush the corresponding user ASID.  We can delay this
+ * until the next time we switch to it.
+ *
+ * See SWITCH_TO_USER_CR3.
+ */
+static inline void invalidate_user_asid(u16 asid)
 {
+	/* There is no user ASID if address space separation is off */
+	if (!IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+		return;
+
 	/*
-	 * If current->mm == NULL then we borrow a mm which may change during a
-	 * task switch and therefore we must not be preempted while we write CR3
-	 * back:
+	 * We only have a single ASID if PCID is off and the CR3
+	 * write will have flushed it.
 	 */
-	preempt_disable();
-	native_write_cr3(__native_read_cr3());
-	preempt_enable();
+	if (!cpu_feature_enabled(X86_FEATURE_PCID))
+		return;
+
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	__set_bit(kern_pcid(asid),
+		  (unsigned long *)this_cpu_ptr(&cpu_tlbstate.user_pcid_flush_mask));
 }
 
-static inline void __native_flush_tlb_global_irq_disabled(void)
+/*
+ * flush the entire current user mapping
+ */
+static inline void __native_flush_tlb(void)
 {
-	unsigned long cr4;
+	/*
+	 * Preemption or interrupts must be disabled to protect the access
+	 * to the per CPU variable and to prevent being preempted between
+	 * read_cr3() and write_cr3().
+	 */
+	WARN_ON_ONCE(preemptible());
 
-	cr4 = this_cpu_read(cpu_tlbstate.cr4);
-	/* clear PGE */
-	native_write_cr4(cr4 & ~X86_CR4_PGE);
-	/* write old PGE again and flush TLBs */
-	native_write_cr4(cr4);
+	invalidate_user_asid(this_cpu_read(cpu_tlbstate.loaded_mm_asid));
+
+	/* If current->mm == NULL then the read_cr3() "borrows" an mm */
+	native_write_cr3(__native_read_cr3());
 }
 
+/*
+ * flush everything
+ */
 static inline void __native_flush_tlb_global(void)
 {
-	unsigned long flags;
+	unsigned long cr4, flags;
 
 	if (static_cpu_has(X86_FEATURE_INVPCID)) {
 		/*
 		 * Using INVPCID is considerably faster than a pair of writes
 		 * to CR4 sandwiched inside an IRQ flag save/restore.
+		 *
+		 * Note, this works with CR4.PCIDE=0 or 1.
 		 */
 		invpcid_flush_all();
 		return;
@@ -277,36 +388,82 @@ static inline void __native_flush_tlb_global(void)
 	 */
 	raw_local_irq_save(flags);
 
-	__native_flush_tlb_global_irq_disabled();
+	cr4 = this_cpu_read(cpu_tlbstate.cr4);
+	/* toggle PGE */
+	native_write_cr4(cr4 ^ X86_CR4_PGE);
+	/* write old PGE again and flush TLBs */
+	native_write_cr4(cr4);
 
 	raw_local_irq_restore(flags);
 }
 
-static inline void __native_flush_tlb_single(unsigned long addr)
+/*
+ * flush one page in the user mapping
+ */
+static inline void __native_flush_tlb_one_user(unsigned long addr)
 {
+	u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+
 	asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
+
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	/*
+	 * Some platforms #GP if we call invpcid(type=1/2) before CR4.PCIDE=1.
+	 * Just use invalidate_user_asid() in case we are called early.
+	 */
+	if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE))
+		invalidate_user_asid(loaded_mm_asid);
+	else
+		invpcid_flush_one(user_pcid(loaded_mm_asid), addr);
 }
 
+/*
+ * flush everything
+ */
 static inline void __flush_tlb_all(void)
 {
-	if (boot_cpu_has(X86_FEATURE_PGE))
+	if (boot_cpu_has(X86_FEATURE_PGE)) {
 		__flush_tlb_global();
-	else
+	} else {
+		/*
+		 * !PGE -> !PCID (setup_pcid()), thus every flush is total.
+		 */
 		__flush_tlb();
+	}
+}
+
+/*
+ * flush one page in the kernel mapping
+ */
+static inline void __flush_tlb_one_kernel(unsigned long addr)
+{
+	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
 
 	/*
-	 * Note: if we somehow had PCID but not PGE, then this wouldn't work --
-	 * we'd end up flushing kernel translations for the current ASID but
-	 * we might fail to flush kernel translations for other cached ASIDs.
+	 * If PTI is off, then __flush_tlb_one_user() is just INVLPG or its
+	 * paravirt equivalent.  Even with PCID, this is sufficient: we only
+	 * use PCID if we also use global PTEs for the kernel mapping, and
+	 * INVLPG flushes global translations across all address spaces.
 	 *
-	 * To avoid this issue, we force PCID off if PGE is off.
+	 * If PTI is on, then the kernel is mapped with non-global PTEs, and
+	 * __flush_tlb_one_user() will flush the given address for the current
+	 * kernel address space and for its usermode counterpart, but it does
+	 * not flush it for other address spaces.
 	 */
-}
+	__flush_tlb_one_user(addr);
 
-static inline void __flush_tlb_one(unsigned long addr)
-{
-	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
-	__flush_tlb_single(addr);
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	/*
+	 * See above.  We need to propagate the flush to all other address
+	 * spaces.  In principle, we only need to propagate it to kernelmode
+	 * address spaces, but the extra bookkeeping we would need is not
+	 * worth it.
+	 */
+	invalidate_other_asid();
 }
 
 #define TLB_FLUSH_ALL	-1UL
@@ -367,6 +524,17 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
 void native_flush_tlb_others(const struct cpumask *cpumask,
 			     const struct flush_tlb_info *info);
 
+static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
+{
+	/*
+	 * Bump the generation count.  This also serves as a full barrier
+	 * that synchronizes with switch_mm(): callers are required to order
+	 * their read of mm_cpumask after their writes to the paging
+	 * structures.
+	 */
+	return atomic64_inc_return(&mm->context.tlb_gen);
+}
+
 static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
 					struct mm_struct *mm)
 {
diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h
index fa60398bbc3a..069c04be1507 100644
--- a/arch/x86/include/asm/trace/fpu.h
+++ b/arch/x86/include/asm/trace/fpu.h
@@ -34,11 +34,6 @@ DECLARE_EVENT_CLASS(x86_fpu,
 	)
 );
 
-DEFINE_EVENT(x86_fpu, x86_fpu_state,
-	TP_PROTO(struct fpu *fpu),
-	TP_ARGS(fpu)
-);
-
 DEFINE_EVENT(x86_fpu, x86_fpu_before_save,
 	TP_PROTO(struct fpu *fpu),
 	TP_ARGS(fpu)
@@ -74,11 +69,6 @@ DEFINE_EVENT(x86_fpu, x86_fpu_activate_state,
 	TP_ARGS(fpu)
 );
 
-DEFINE_EVENT(x86_fpu, x86_fpu_deactivate_state,
-	TP_PROTO(struct fpu *fpu),
-	TP_ARGS(fpu)
-);
-
 DEFINE_EVENT(x86_fpu, x86_fpu_init_state,
 	TP_PROTO(struct fpu *fpu),
 	TP_ARGS(fpu)
diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h
index 8eb139ed1a03..22647a642e98 100644
--- a/arch/x86/include/asm/trace/irq_vectors.h
+++ b/arch/x86/include/asm/trace/irq_vectors.h
@@ -138,6 +138,254 @@ DEFINE_IRQ_VECTOR_EVENT(deferred_error_apic);
 DEFINE_IRQ_VECTOR_EVENT(thermal_apic);
 #endif
 
+TRACE_EVENT(vector_config,
+
+	TP_PROTO(unsigned int irq, unsigned int vector,
+		 unsigned int cpu, unsigned int apicdest),
+
+	TP_ARGS(irq, vector, cpu, apicdest),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	irq		)
+		__field(	unsigned int,	vector		)
+		__field(	unsigned int,	cpu		)
+		__field(	unsigned int,	apicdest	)
+	),
+
+	TP_fast_assign(
+		__entry->irq		= irq;
+		__entry->vector		= vector;
+		__entry->cpu		= cpu;
+		__entry->apicdest	= apicdest;
+	),
+
+	TP_printk("irq=%u vector=%u cpu=%u apicdest=0x%08x",
+		  __entry->irq, __entry->vector, __entry->cpu,
+		  __entry->apicdest)
+);
+
+DECLARE_EVENT_CLASS(vector_mod,
+
+	TP_PROTO(unsigned int irq, unsigned int vector,
+		 unsigned int cpu, unsigned int prev_vector,
+		 unsigned int prev_cpu),
+
+	TP_ARGS(irq, vector, cpu, prev_vector, prev_cpu),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	irq		)
+		__field(	unsigned int,	vector		)
+		__field(	unsigned int,	cpu		)
+		__field(	unsigned int,	prev_vector	)
+		__field(	unsigned int,	prev_cpu	)
+	),
+
+	TP_fast_assign(
+		__entry->irq		= irq;
+		__entry->vector		= vector;
+		__entry->cpu		= cpu;
+		__entry->prev_vector	= prev_vector;
+		__entry->prev_cpu	= prev_cpu;
+
+	),
+
+	TP_printk("irq=%u vector=%u cpu=%u prev_vector=%u prev_cpu=%u",
+		  __entry->irq, __entry->vector, __entry->cpu,
+		  __entry->prev_vector, __entry->prev_cpu)
+);
+
+#define DEFINE_IRQ_VECTOR_MOD_EVENT(name)				\
+DEFINE_EVENT_FN(vector_mod, name,					\
+	TP_PROTO(unsigned int irq, unsigned int vector,			\
+		 unsigned int cpu, unsigned int prev_vector,		\
+		 unsigned int prev_cpu),				\
+	TP_ARGS(irq, vector, cpu, prev_vector, prev_cpu), NULL, NULL);	\
+
+DEFINE_IRQ_VECTOR_MOD_EVENT(vector_update);
+DEFINE_IRQ_VECTOR_MOD_EVENT(vector_clear);
+
+DECLARE_EVENT_CLASS(vector_reserve,
+
+	TP_PROTO(unsigned int irq, int ret),
+
+	TP_ARGS(irq, ret),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	irq	)
+		__field(	int,		ret	)
+	),
+
+	TP_fast_assign(
+		__entry->irq = irq;
+		__entry->ret = ret;
+	),
+
+	TP_printk("irq=%u ret=%d", __entry->irq, __entry->ret)
+);
+
+#define DEFINE_IRQ_VECTOR_RESERVE_EVENT(name)	\
+DEFINE_EVENT_FN(vector_reserve, name,	\
+	TP_PROTO(unsigned int irq, int ret),	\
+	TP_ARGS(irq, ret), NULL, NULL);		\
+
+DEFINE_IRQ_VECTOR_RESERVE_EVENT(vector_reserve_managed);
+DEFINE_IRQ_VECTOR_RESERVE_EVENT(vector_reserve);
+
+TRACE_EVENT(vector_alloc,
+
+	TP_PROTO(unsigned int irq, unsigned int vector, bool reserved,
+		 int ret),
+
+	TP_ARGS(irq, vector, ret, reserved),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	irq		)
+		__field(	unsigned int,	vector		)
+		__field(	bool,		reserved	)
+		__field(	int,		ret		)
+	),
+
+	TP_fast_assign(
+		__entry->irq		= irq;
+		__entry->vector		= ret < 0 ? 0 : vector;
+		__entry->reserved	= reserved;
+		__entry->ret		= ret > 0 ? 0 : ret;
+	),
+
+	TP_printk("irq=%u vector=%u reserved=%d ret=%d",
+		  __entry->irq, __entry->vector,
+		  __entry->reserved, __entry->ret)
+);
+
+TRACE_EVENT(vector_alloc_managed,
+
+	TP_PROTO(unsigned int irq, unsigned int vector,
+		 int ret),
+
+	TP_ARGS(irq, vector, ret),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	irq		)
+		__field(	unsigned int,	vector		)
+		__field(	int,		ret		)
+	),
+
+	TP_fast_assign(
+		__entry->irq		= irq;
+		__entry->vector		= ret < 0 ? 0 : vector;
+		__entry->ret		= ret > 0 ? 0 : ret;
+	),
+
+	TP_printk("irq=%u vector=%u ret=%d",
+		  __entry->irq, __entry->vector, __entry->ret)
+);
+
+DECLARE_EVENT_CLASS(vector_activate,
+
+	TP_PROTO(unsigned int irq, bool is_managed, bool can_reserve,
+		 bool reserve),
+
+	TP_ARGS(irq, is_managed, can_reserve, reserve),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	irq		)
+		__field(	bool,		is_managed	)
+		__field(	bool,		can_reserve	)
+		__field(	bool,		reserve		)
+	),
+
+	TP_fast_assign(
+		__entry->irq		= irq;
+		__entry->is_managed	= is_managed;
+		__entry->can_reserve	= can_reserve;
+		__entry->reserve	= reserve;
+	),
+
+	TP_printk("irq=%u is_managed=%d can_reserve=%d reserve=%d",
+		  __entry->irq, __entry->is_managed, __entry->can_reserve,
+		  __entry->reserve)
+);
+
+#define DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(name)				\
+DEFINE_EVENT_FN(vector_activate, name,					\
+	TP_PROTO(unsigned int irq, bool is_managed,			\
+		 bool can_reserve, bool reserve),			\
+	TP_ARGS(irq, is_managed, can_reserve, reserve), NULL, NULL);	\
+
+DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(vector_activate);
+DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(vector_deactivate);
+
+TRACE_EVENT(vector_teardown,
+
+	TP_PROTO(unsigned int irq, bool is_managed, bool has_reserved),
+
+	TP_ARGS(irq, is_managed, has_reserved),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	irq		)
+		__field(	bool,		is_managed	)
+		__field(	bool,		has_reserved	)
+	),
+
+	TP_fast_assign(
+		__entry->irq		= irq;
+		__entry->is_managed	= is_managed;
+		__entry->has_reserved	= has_reserved;
+	),
+
+	TP_printk("irq=%u is_managed=%d has_reserved=%d",
+		  __entry->irq, __entry->is_managed, __entry->has_reserved)
+);
+
+TRACE_EVENT(vector_setup,
+
+	TP_PROTO(unsigned int irq, bool is_legacy, int ret),
+
+	TP_ARGS(irq, is_legacy, ret),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	irq		)
+		__field(	bool,		is_legacy	)
+		__field(	int,		ret		)
+	),
+
+	TP_fast_assign(
+		__entry->irq		= irq;
+		__entry->is_legacy	= is_legacy;
+		__entry->ret		= ret;
+	),
+
+	TP_printk("irq=%u is_legacy=%d ret=%d",
+		  __entry->irq, __entry->is_legacy, __entry->ret)
+);
+
+TRACE_EVENT(vector_free_moved,
+
+	TP_PROTO(unsigned int irq, unsigned int cpu, unsigned int vector,
+		 bool is_managed),
+
+	TP_ARGS(irq, cpu, vector, is_managed),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	irq		)
+		__field(	unsigned int,	cpu		)
+		__field(	unsigned int,	vector		)
+		__field(	bool,		is_managed	)
+	),
+
+	TP_fast_assign(
+		__entry->irq		= irq;
+		__entry->cpu		= cpu;
+		__entry->vector		= vector;
+		__entry->is_managed	= is_managed;
+	),
+
+	TP_printk("irq=%u cpu=%u vector=%u is_managed=%d",
+		  __entry->irq, __entry->cpu, __entry->vector,
+		  __entry->is_managed)
+);
+
+
 #endif /* CONFIG_X86_LOCAL_APIC */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index b0cced97a6ce..3de69330e6c5 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -38,9 +38,9 @@ asmlinkage void simd_coprocessor_error(void);
 
 #if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV)
 asmlinkage void xen_divide_error(void);
+asmlinkage void xen_xennmi(void);
 asmlinkage void xen_xendebug(void);
 asmlinkage void xen_xenint3(void);
-asmlinkage void xen_nmi(void);
 asmlinkage void xen_overflow(void);
 asmlinkage void xen_bounds(void);
 asmlinkage void xen_invalid_op(void);
@@ -75,7 +75,6 @@ dotraplinkage void do_segment_not_present(struct pt_regs *, long);
 dotraplinkage void do_stack_segment(struct pt_regs *, long);
 #ifdef CONFIG_X86_64
 dotraplinkage void do_double_fault(struct pt_regs *, long);
-asmlinkage struct pt_regs *sync_regs(struct pt_regs *);
 #endif
 dotraplinkage void do_general_protection(struct pt_regs *, long);
 dotraplinkage void do_page_fault(struct pt_regs *, unsigned long);
@@ -89,6 +88,7 @@ dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long);
 #ifdef CONFIG_X86_32
 dotraplinkage void do_iret_error(struct pt_regs *, long);
 #endif
+dotraplinkage void do_mce(struct pt_regs *, long);
 
 static inline int get_si_code(unsigned long condition)
 {
@@ -145,4 +145,22 @@ enum {
 	X86_TRAP_IRET = 32,	/* 32, IRET Exception */
 };
 
+/*
+ * Page fault error code bits:
+ *
+ *   bit 0 ==	 0: no page found	1: protection fault
+ *   bit 1 ==	 0: read access		1: write access
+ *   bit 2 ==	 0: kernel-mode access	1: user-mode access
+ *   bit 3 ==				1: use of reserved bit detected
+ *   bit 4 ==				1: fault was an instruction fetch
+ *   bit 5 ==				1: protection keys block access
+ */
+enum x86_pf_error_code {
+	X86_PF_PROT	=		1 << 0,
+	X86_PF_WRITE	=		1 << 1,
+	X86_PF_USER	=		1 << 2,
+	X86_PF_RSVD	=		1 << 3,
+	X86_PF_INSTR	=		1 << 4,
+	X86_PF_PK	=		1 << 5,
+};
 #endif /* _ASM_X86_TRAPS_H */
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 8da0efb13544..cf5d53c3f9ea 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -32,15 +32,22 @@ static inline cycles_t get_cycles(void)
 
 extern struct system_counterval_t convert_art_to_tsc(u64 art);
 
+extern void tsc_early_delay_calibrate(void);
 extern void tsc_init(void);
 extern void mark_tsc_unstable(char *reason);
 extern int unsynchronized_tsc(void);
 extern int check_tsc_unstable(void);
+extern void mark_tsc_async_resets(char *reason);
 extern unsigned long native_calibrate_cpu(void);
 extern unsigned long native_calibrate_tsc(void);
 extern unsigned long long native_sched_clock_from_tsc(u64 tsc);
 
 extern int tsc_clocksource_reliable;
+#ifdef CONFIG_X86_TSC
+extern bool tsc_async_resets;
+#else
+# define tsc_async_resets	false
+#endif
 
 /*
  * Boot-time check whether the TSCs are synchronized across
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 574dff4d2913..aae77eb8491c 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -124,6 +124,11 @@ extern int __get_user_bad(void);
 
 #define __uaccess_begin() stac()
 #define __uaccess_end()   clac()
+#define __uaccess_begin_nospec()	\
+({					\
+	stac();				\
+	barrier_nospec();		\
+})
 
 /*
  * This is a type: either unsigned long, if the argument fits into
@@ -445,7 +450,7 @@ do {									\
 ({									\
 	int __gu_err;							\
 	__inttype(*(ptr)) __gu_val;					\
-	__uaccess_begin();						\
+	__uaccess_begin_nospec();					\
 	__get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);	\
 	__uaccess_end();						\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
@@ -487,6 +492,10 @@ struct __large_struct { unsigned long buf[100]; };
 	__uaccess_begin();						\
 	barrier();
 
+#define uaccess_try_nospec do {						\
+	current->thread.uaccess_err = 0;				\
+	__uaccess_begin_nospec();					\
+
 #define uaccess_catch(err)						\
 	__uaccess_end();						\
 	(err) |= (current->thread.uaccess_err ? -EFAULT : 0);		\
@@ -548,7 +557,7 @@ struct __large_struct { unsigned long buf[100]; };
  *	get_user_ex(...);
  * } get_user_catch(err)
  */
-#define get_user_try		uaccess_try
+#define get_user_try		uaccess_try_nospec
 #define get_user_catch(err)	uaccess_catch(err)
 
 #define get_user_ex(x, ptr)	do {					\
@@ -582,7 +591,7 @@ extern void __cmpxchg_wrong_size(void)
 	__typeof__(ptr) __uval = (uval);				\
 	__typeof__(*(ptr)) __old = (old);				\
 	__typeof__(*(ptr)) __new = (new);				\
-	__uaccess_begin();						\
+	__uaccess_begin_nospec();					\
 	switch (size) {							\
 	case 1:								\
 	{								\
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 72950401b223..ba2dc1930630 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -29,21 +29,21 @@ raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 		switch (n) {
 		case 1:
 			ret = 0;
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_asm_nozero(*(u8 *)to, from, ret,
 					      "b", "b", "=q", 1);
 			__uaccess_end();
 			return ret;
 		case 2:
 			ret = 0;
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_asm_nozero(*(u16 *)to, from, ret,
 					      "w", "w", "=r", 2);
 			__uaccess_end();
 			return ret;
 		case 4:
 			ret = 0;
-			__uaccess_begin();
+			__uaccess_begin_nospec();
 			__get_user_asm_nozero(*(u32 *)to, from, ret,
 					      "l", "k", "=r", 4);
 			__uaccess_end();
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index f07ef3c575db..62546b3a398e 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -55,31 +55,31 @@ raw_copy_from_user(void *dst, const void __user *src, unsigned long size)
 		return copy_user_generic(dst, (__force void *)src, size);
 	switch (size) {
 	case 1:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm_nozero(*(u8 *)dst, (u8 __user *)src,
 			      ret, "b", "b", "=q", 1);
 		__uaccess_end();
 		return ret;
 	case 2:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm_nozero(*(u16 *)dst, (u16 __user *)src,
 			      ret, "w", "w", "=r", 2);
 		__uaccess_end();
 		return ret;
 	case 4:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm_nozero(*(u32 *)dst, (u32 __user *)src,
 			      ret, "l", "k", "=r", 4);
 		__uaccess_end();
 		return ret;
 	case 8:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
 			      ret, "q", "", "=r", 8);
 		__uaccess_end();
 		return ret;
 	case 10:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
 			       ret, "q", "", "=r", 10);
 		if (likely(!ret))
@@ -89,7 +89,7 @@ raw_copy_from_user(void *dst, const void __user *src, unsigned long size)
 		__uaccess_end();
 		return ret;
 	case 16:
-		__uaccess_begin();
+		__uaccess_begin_nospec();
 		__get_user_asm_nozero(*(u64 *)dst, (u64 __user *)src,
 			       ret, "q", "", "=r", 16);
 		if (likely(!ret))
diff --git a/arch/x86/include/asm/umip.h b/arch/x86/include/asm/umip.h
new file mode 100644
index 000000000000..db43f2a0d92c
--- /dev/null
+++ b/arch/x86/include/asm/umip.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_X86_UMIP_H
+#define _ASM_X86_UMIP_H
+
+#include <linux/types.h>
+#include <asm/ptrace.h>
+
+#ifdef CONFIG_X86_INTEL_UMIP
+bool fixup_umip_exception(struct pt_regs *regs);
+#else
+static inline bool fixup_umip_exception(struct pt_regs *regs) { return false; }
+#endif  /* CONFIG_X86_INTEL_UMIP */
+#endif  /* _ASM_X86_UMIP_H */
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index 87adc0d38c4a..1f86e1b0a5cd 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -7,17 +7,20 @@
 #include <asm/ptrace.h>
 #include <asm/stacktrace.h>
 
+#define IRET_FRAME_OFFSET (offsetof(struct pt_regs, ip))
+#define IRET_FRAME_SIZE   (sizeof(struct pt_regs) - IRET_FRAME_OFFSET)
+
 struct unwind_state {
 	struct stack_info stack_info;
 	unsigned long stack_mask;
 	struct task_struct *task;
 	int graph_idx;
 	bool error;
-#if defined(CONFIG_ORC_UNWINDER)
+#if defined(CONFIG_UNWINDER_ORC)
 	bool signal, full_regs;
 	unsigned long sp, bp, ip;
 	struct pt_regs *regs;
-#elif defined(CONFIG_FRAME_POINTER_UNWINDER)
+#elif defined(CONFIG_UNWINDER_FRAME_POINTER)
 	bool got_irq;
 	unsigned long *bp, *orig_sp, ip;
 	struct pt_regs *regs;
@@ -51,22 +54,35 @@ void unwind_start(struct unwind_state *state, struct task_struct *task,
 	__unwind_start(state, task, regs, first_frame);
 }
 
-#if defined(CONFIG_ORC_UNWINDER) || defined(CONFIG_FRAME_POINTER_UNWINDER)
-static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+#if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER)
+/*
+ * If 'partial' returns true, only the iret frame registers are valid.
+ */
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state,
+						    bool *partial)
 {
 	if (unwind_done(state))
 		return NULL;
 
+	if (partial) {
+#ifdef CONFIG_UNWINDER_ORC
+		*partial = !state->full_regs;
+#else
+		*partial = false;
+#endif
+	}
+
 	return state->regs;
 }
 #else
-static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state,
+						    bool *partial)
 {
 	return NULL;
 }
 #endif
 
-#ifdef CONFIG_ORC_UNWINDER
+#ifdef CONFIG_UNWINDER_ORC
 void unwind_init(void);
 void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size,
 			void *orc, size_t orc_size);
diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h
index 74f4c2ff6427..d8bfa98fca98 100644
--- a/arch/x86/include/asm/uprobes.h
+++ b/arch/x86/include/asm/uprobes.h
@@ -53,6 +53,10 @@ struct arch_uprobe {
 			u8	fixups;
 			u8	ilen;
 		} 			defparam;
+		struct {
+			u8	reg_offset;	/* to the start of pt_regs */
+			u8	ilen;
+		}			push;
 	};
 };
 
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 7cac79802ad2..7803114aa140 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -48,7 +48,6 @@
 #define UV2_NET_ENDPOINT_INTD		0x28
 #define UV_NET_ENDPOINT_INTD		(is_uv1_hub() ?			\
 			UV1_NET_ENDPOINT_INTD : UV2_NET_ENDPOINT_INTD)
-#define UV_DESC_PSHIFT			49
 #define UV_PAYLOADQ_GNODE_SHIFT		49
 #define UV_PTC_BASENAME			"sgi_uv/ptc_statistics"
 #define UV_BAU_BASENAME			"sgi_uv/bau_tunables"
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 9cffb44a3cf5..44cf6d6deb7a 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -241,6 +241,7 @@ static inline int uv_hub_info_check(int version)
 #define UV2_HUB_REVISION_BASE		3
 #define UV3_HUB_REVISION_BASE		5
 #define UV4_HUB_REVISION_BASE		7
+#define UV4A_HUB_REVISION_BASE		8	/* UV4 (fixed) rev 2 */
 
 #ifdef	UV1_HUB_IS_SUPPORTED
 static inline int is_uv1_hub(void)
@@ -280,6 +281,19 @@ static inline int is_uv3_hub(void)
 }
 #endif
 
+/* First test "is UV4A", then "is UV4" */
+#ifdef	UV4A_HUB_IS_SUPPORTED
+static inline int is_uv4a_hub(void)
+{
+	return (uv_hub_info->hub_revision >= UV4A_HUB_REVISION_BASE);
+}
+#else
+static inline int is_uv4a_hub(void)
+{
+	return 0;
+}
+#endif
+
 #ifdef	UV4_HUB_IS_SUPPORTED
 static inline int is_uv4_hub(void)
 {
@@ -776,23 +790,36 @@ static inline int uv_num_possible_blades(void)
 extern void uv_nmi_setup(void);
 extern void uv_nmi_setup_hubless(void);
 
+/* BIOS/Kernel flags exchange MMR */
+#define UVH_BIOS_KERNEL_MMR		UVH_SCRATCH5
+#define UVH_BIOS_KERNEL_MMR_ALIAS	UVH_SCRATCH5_ALIAS
+#define UVH_BIOS_KERNEL_MMR_ALIAS_2	UVH_SCRATCH5_ALIAS_2
+
+/* TSC sync valid, set by BIOS */
+#define UVH_TSC_SYNC_MMR	UVH_BIOS_KERNEL_MMR
+#define UVH_TSC_SYNC_SHIFT	10
+#define UVH_TSC_SYNC_SHIFT_UV2K	16	/* UV2/3k have different bits */
+#define UVH_TSC_SYNC_MASK	3	/* 0011 */
+#define UVH_TSC_SYNC_VALID	3	/* 0011 */
+#define UVH_TSC_SYNC_INVALID	2	/* 0010 */
+
 /* BMC sets a bit this MMR non-zero before sending an NMI */
-#define UVH_NMI_MMR		UVH_SCRATCH5
-#define UVH_NMI_MMR_CLEAR	UVH_SCRATCH5_ALIAS
+#define UVH_NMI_MMR		UVH_BIOS_KERNEL_MMR
+#define UVH_NMI_MMR_CLEAR	UVH_BIOS_KERNEL_MMR_ALIAS
 #define UVH_NMI_MMR_SHIFT	63
-#define	UVH_NMI_MMR_TYPE	"SCRATCH5"
+#define UVH_NMI_MMR_TYPE	"SCRATCH5"
 
 /* Newer SMM NMI handler, not present in all systems */
 #define UVH_NMI_MMRX		UVH_EVENT_OCCURRED0
 #define UVH_NMI_MMRX_CLEAR	UVH_EVENT_OCCURRED0_ALIAS
 #define UVH_NMI_MMRX_SHIFT	UVH_EVENT_OCCURRED0_EXTIO_INT0_SHFT
-#define	UVH_NMI_MMRX_TYPE	"EXTIO_INT0"
+#define UVH_NMI_MMRX_TYPE	"EXTIO_INT0"
 
 /* Non-zero indicates newer SMM NMI handler present */
 #define UVH_NMI_MMRX_SUPPORTED	UVH_EXTIO_INT0_BROADCAST
 
 /* Indicates to BIOS that we want to use the newer SMM NMI handler */
-#define UVH_NMI_MMRX_REQ	UVH_SCRATCH5_ALIAS_2
+#define UVH_NMI_MMRX_REQ	UVH_BIOS_KERNEL_MMR_ALIAS_2
 #define UVH_NMI_MMRX_REQ_SHIFT	62
 
 struct uv_hub_nmi_s {
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index 548d684a7960..ecb9ddef128f 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -39,9 +39,11 @@
  *	#define UV2Hxxx	b
  *	#define UV3Hxxx	c
  *	#define UV4Hxxx	d
+ *	#define UV4AHxxx e
  *	#define UVHxxx	(is_uv1_hub() ? UV1Hxxx :
  *			(is_uv2_hub() ? UV2Hxxx :
  *			(is_uv3_hub() ? UV3Hxxx :
+ *			(is_uv4a_hub() ? UV4AHxxx :
  *					UV4Hxxx))
  *
  * If the MMR exists on all hub types > 1 but have different addresses, the
@@ -49,8 +51,10 @@
  *	#define UV2Hxxx	b
  *	#define UV3Hxxx	c
  *	#define UV4Hxxx	d
+ *	#define UV4AHxxx e
  *	#define UVHxxx	(is_uv2_hub() ? UV2Hxxx :
  *			(is_uv3_hub() ? UV3Hxxx :
+ *			(is_uv4a_hub() ? UV4AHxxx :
  *					UV4Hxxx))
  *
  *	union uvh_xxx {
@@ -63,6 +67,7 @@
  *		} s2;
  *		struct uv3h_xxx_s {	 # Full UV3 definition (*)
  *		} s3;
+ *		(NOTE: No struct uv4ah_xxx_s members exist)
  *		struct uv4h_xxx_s {	 # Full UV4 definition (*)
  *		} s4;
  *	};
@@ -99,6 +104,7 @@
 #define UV2_HUB_IS_SUPPORTED	1
 #define UV3_HUB_IS_SUPPORTED	1
 #define UV4_HUB_IS_SUPPORTED	1
+#define UV4A_HUB_IS_SUPPORTED	1
 
 /* Error function to catch undefined references */
 extern unsigned long uv_undefined(char *str);
@@ -2779,35 +2785,47 @@ union uvh_lb_bau_sb_activation_status_1_u {
 	/*is_uv4_hub*/ UV4H_LB_BAU_SB_DESCRIPTOR_BASE_32)
 
 #define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_SHFT	12
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT	49
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK	0x7ffe000000000000UL
 
+#define UV1H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT	49
 #define UV1H_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
+#define UV1H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK	0x7ffe000000000000UL
 
-
+#define UV2H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT	49
 #define UV2H_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
+#define UV2H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK	0x7ffe000000000000UL
 
+#define UV3H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT	49
 #define UV3H_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
+#define UV3H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK	0x7ffe000000000000UL
 
+#define UV4H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT	49
 #define UV4H_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x00003ffffffff000UL
-
-
-union uvh_lb_bau_sb_descriptor_base_u {
-	unsigned long	v;
-	struct uvh_lb_bau_sb_descriptor_base_s {
-		unsigned long	rsvd_0_11:12;
-		unsigned long	rsvd_12_48:37;
-		unsigned long	node_id:14;			/* RW */
-		unsigned long	rsvd_63:1;
-	} s;
-	struct uv4h_lb_bau_sb_descriptor_base_s {
-		unsigned long	rsvd_0_11:12;
-		unsigned long	page_address:34;		/* RW */
-		unsigned long	rsvd_46_48:3;
-		unsigned long	node_id:14;			/* RW */
-		unsigned long	rsvd_63:1;
-	} s4;
-};
+#define UV4H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK	0x7ffe000000000000UL
+
+#define UV4AH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT	53
+#define UV4AH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000ffffffffff000UL
+#define UV4AH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK	0xffe0000000000000UL
+
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT (			\
+	is_uv1_hub() ? UV1H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT :	\
+	is_uv2_hub() ? UV2H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT :	\
+	is_uv3_hub() ? UV3H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT :	\
+	is_uv4a_hub() ? UV4AH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT :	\
+	/*is_uv4_hub*/ UV4H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT)
+
+#define UVH_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK (			\
+	is_uv1_hub() ? UV1H_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK :	\
+	is_uv2_hub() ? UV2H_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK :	\
+	is_uv3_hub() ? UV3H_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK :	\
+	is_uv4a_hub() ? UV4AH_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK :	\
+	/*is_uv4_hub*/ UV4H_LB_BAU_SB_DESCRIPTOR_PAGE_ADDRESS_MASK)
+
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK (			\
+	is_uv1_hub() ? UV1H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK :	\
+	is_uv2_hub() ? UV2H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK :	\
+	is_uv3_hub() ? UV3H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK :	\
+	is_uv4a_hub() ? UV4AH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK :	\
+	/*is_uv4_hub*/ UV4H_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK)
 
 /* ========================================================================= */
 /*                               UVH_NODE_ID                                 */
@@ -3031,6 +3049,41 @@ union uvh_node_present_table_u {
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
 
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
 
 union uvh_rh_gam_alias210_overlay_config_0_mmr_u {
 	unsigned long	v;
@@ -3042,6 +3095,46 @@ union uvh_rh_gam_alias210_overlay_config_0_mmr_u {
 		unsigned long	rsvd_53_62:10;
 		unsigned long	enable:1;			/* RW */
 	} s;
+	struct uv1h_rh_gam_alias210_overlay_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s1;
+	struct uvxh_rh_gam_alias210_overlay_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} sx;
+	struct uv2h_rh_gam_alias210_overlay_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s2;
+	struct uv3h_rh_gam_alias210_overlay_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s3;
+	struct uv4h_rh_gam_alias210_overlay_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s4;
 };
 
 /* ========================================================================= */
@@ -3064,6 +3157,41 @@ union uvh_rh_gam_alias210_overlay_config_0_mmr_u {
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
 
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
 
 union uvh_rh_gam_alias210_overlay_config_1_mmr_u {
 	unsigned long	v;
@@ -3075,6 +3203,46 @@ union uvh_rh_gam_alias210_overlay_config_1_mmr_u {
 		unsigned long	rsvd_53_62:10;
 		unsigned long	enable:1;			/* RW */
 	} s;
+	struct uv1h_rh_gam_alias210_overlay_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s1;
+	struct uvxh_rh_gam_alias210_overlay_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} sx;
+	struct uv2h_rh_gam_alias210_overlay_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s2;
+	struct uv3h_rh_gam_alias210_overlay_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s3;
+	struct uv4h_rh_gam_alias210_overlay_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s4;
 };
 
 /* ========================================================================= */
@@ -3097,6 +3265,41 @@ union uvh_rh_gam_alias210_overlay_config_1_mmr_u {
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
 #define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
 
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV1H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVXH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV2H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV3H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UV4H_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
 
 union uvh_rh_gam_alias210_overlay_config_2_mmr_u {
 	unsigned long	v;
@@ -3108,6 +3311,46 @@ union uvh_rh_gam_alias210_overlay_config_2_mmr_u {
 		unsigned long	rsvd_53_62:10;
 		unsigned long	enable:1;			/* RW */
 	} s;
+	struct uv1h_rh_gam_alias210_overlay_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s1;
+	struct uvxh_rh_gam_alias210_overlay_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} sx;
+	struct uv2h_rh_gam_alias210_overlay_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s2;
+	struct uv3h_rh_gam_alias210_overlay_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s3;
+	struct uv4h_rh_gam_alias210_overlay_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	base:8;				/* RW */
+		unsigned long	rsvd_32_47:16;
+		unsigned long	m_alias:5;			/* RW */
+		unsigned long	rsvd_53_62:10;
+		unsigned long	enable:1;			/* RW */
+	} s4;
 };
 
 /* ========================================================================= */
@@ -3126,6 +3369,21 @@ union uvh_rh_gam_alias210_overlay_config_2_mmr_u {
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
 
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
 
 union uvh_rh_gam_alias210_redirect_config_0_mmr_u {
 	unsigned long	v;
@@ -3134,6 +3392,31 @@ union uvh_rh_gam_alias210_redirect_config_0_mmr_u {
 		unsigned long	dest_base:22;			/* RW */
 		unsigned long	rsvd_46_63:18;
 	} s;
+	struct uv1h_rh_gam_alias210_redirect_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s1;
+	struct uvxh_rh_gam_alias210_redirect_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} sx;
+	struct uv2h_rh_gam_alias210_redirect_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s2;
+	struct uv3h_rh_gam_alias210_redirect_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s3;
+	struct uv4h_rh_gam_alias210_redirect_config_0_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s4;
 };
 
 /* ========================================================================= */
@@ -3152,6 +3435,21 @@ union uvh_rh_gam_alias210_redirect_config_0_mmr_u {
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
 
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
 
 union uvh_rh_gam_alias210_redirect_config_1_mmr_u {
 	unsigned long	v;
@@ -3160,6 +3458,31 @@ union uvh_rh_gam_alias210_redirect_config_1_mmr_u {
 		unsigned long	dest_base:22;			/* RW */
 		unsigned long	rsvd_46_63:18;
 	} s;
+	struct uv1h_rh_gam_alias210_redirect_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s1;
+	struct uvxh_rh_gam_alias210_redirect_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} sx;
+	struct uv2h_rh_gam_alias210_redirect_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s2;
+	struct uv3h_rh_gam_alias210_redirect_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s3;
+	struct uv4h_rh_gam_alias210_redirect_config_1_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s4;
 };
 
 /* ========================================================================= */
@@ -3178,6 +3501,21 @@ union uvh_rh_gam_alias210_redirect_config_1_mmr_u {
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
 #define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
 
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UV1H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UVXH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UV2H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UV3H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UV4H_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
 
 union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
 	unsigned long	v;
@@ -3186,6 +3524,31 @@ union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
 		unsigned long	dest_base:22;			/* RW */
 		unsigned long	rsvd_46_63:18;
 	} s;
+	struct uv1h_rh_gam_alias210_redirect_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s1;
+	struct uvxh_rh_gam_alias210_redirect_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} sx;
+	struct uv2h_rh_gam_alias210_redirect_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s2;
+	struct uv3h_rh_gam_alias210_redirect_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s3;
+	struct uv4h_rh_gam_alias210_redirect_config_2_mmr_s {
+		unsigned long	rsvd_0_23:24;
+		unsigned long	dest_base:22;			/* RW */
+		unsigned long	rsvd_46_63:18;
+	} s4;
 };
 
 /* ========================================================================= */
@@ -3384,6 +3747,162 @@ union uvh_rh_gam_gru_overlay_config_mmr_u {
 };
 
 /* ========================================================================= */
+/*                   UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR                    */
+/* ========================================================================= */
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR uv_undefined("UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR")
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR uv_undefined("UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR")
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR 0x1603000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR 0x483000UL
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR (				\
+	is_uv1_hub() ? UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR :		\
+	is_uv2_hub() ? UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR :		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR :		\
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR)
+
+
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_SHFT	26
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT	46
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_SHFT 63
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK	0x00003ffffc000000UL
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK	0x000fc00000000000UL
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_SHFT	26
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT	46
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_SHFT 63
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK	0x00003ffffc000000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK	0x000fc00000000000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT 52
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK 0x000ffffffc000000UL
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK 0x03f0000000000000UL
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT)
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK)
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK)
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK)
+
+union uvh_rh_gam_mmioh_overlay_config0_mmr_u {
+	unsigned long	v;
+	struct uv3h_rh_gam_mmioh_overlay_config0_mmr_s {
+		unsigned long	rsvd_0_25:26;
+		unsigned long	base:20;			/* RW */
+		unsigned long	m_io:6;				/* RW */
+		unsigned long	n_io:4;
+		unsigned long	rsvd_56_62:7;
+		unsigned long	enable:1;			/* RW */
+	} s3;
+	struct uv4h_rh_gam_mmioh_overlay_config0_mmr_s {
+		unsigned long	rsvd_0_25:26;
+		unsigned long	base:20;			/* RW */
+		unsigned long	m_io:6;				/* RW */
+		unsigned long	n_io:4;
+		unsigned long	rsvd_56_62:7;
+		unsigned long	enable:1;			/* RW */
+	} s4;
+	struct uv4ah_rh_gam_mmioh_overlay_config0_mmr_s {
+		unsigned long	rsvd_0_25:26;
+		unsigned long	base:26;			/* RW */
+		unsigned long	m_io:6;				/* RW */
+		unsigned long	n_io:4;
+		unsigned long	undef_62:1;			/* Undefined */
+		unsigned long	enable:1;			/* RW */
+	} s4a;
+};
+
+/* ========================================================================= */
+/*                   UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR                    */
+/* ========================================================================= */
+#define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR uv_undefined("UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR")
+#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR uv_undefined("UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR")
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR 0x1603000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR 0x483000UL
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR (				\
+	is_uv1_hub() ? UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR :		\
+	is_uv2_hub() ? UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR :		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR :		\
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR)
+
+
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_SHFT	26
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT	46
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_SHFT 63
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK	0x00003ffffc000000UL
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK	0x000fc00000000000UL
+#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_SHFT	26
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT	46
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_SHFT 63
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK	0x00003ffffc000000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK	0x000fc00000000000UL
+#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT 52
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK 0x000ffffffc000000UL
+#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK 0x03f0000000000000UL
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT)
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK)
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK)
+
+union uvh_rh_gam_mmioh_overlay_config1_mmr_u {
+	unsigned long	v;
+	struct uv3h_rh_gam_mmioh_overlay_config1_mmr_s {
+		unsigned long	rsvd_0_25:26;
+		unsigned long	base:20;			/* RW */
+		unsigned long	m_io:6;				/* RW */
+		unsigned long	n_io:4;
+		unsigned long	rsvd_56_62:7;
+		unsigned long	enable:1;			/* RW */
+	} s3;
+	struct uv4h_rh_gam_mmioh_overlay_config1_mmr_s {
+		unsigned long	rsvd_0_25:26;
+		unsigned long	base:20;			/* RW */
+		unsigned long	m_io:6;				/* RW */
+		unsigned long	n_io:4;
+		unsigned long	rsvd_56_62:7;
+		unsigned long	enable:1;			/* RW */
+	} s4;
+	struct uv4ah_rh_gam_mmioh_overlay_config1_mmr_s {
+		unsigned long	rsvd_0_25:26;
+		unsigned long	base:26;			/* RW */
+		unsigned long	m_io:6;				/* RW */
+		unsigned long	n_io:4;
+		unsigned long	undef_62:1;			/* Undefined */
+		unsigned long	enable:1;			/* RW */
+	} s4a;
+};
+
+/* ========================================================================= */
 /*                   UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR                     */
 /* ========================================================================= */
 #define UV1H_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR 0x1600030UL
@@ -3438,6 +3957,112 @@ union uvh_rh_gam_mmioh_overlay_config_mmr_u {
 };
 
 /* ========================================================================= */
+/*                  UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR                    */
+/* ========================================================================= */
+#define UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR uv_undefined("UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR")
+#define UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR uv_undefined("UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR")
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR 0x1603800UL
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR 0x483800UL
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR (				\
+	is_uv1_hub() ? UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR :		\
+	is_uv2_hub() ? UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR :		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR :		\
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR)
+
+#define UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH uv_undefined("UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH")
+#define UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH uv_undefined("UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH")
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH 128
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH 128
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH (			\
+	is_uv1_hub() ? UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH :	\
+	is_uv2_hub() ? UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH :	\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH :	\
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH)
+
+
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_SHFT 0
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK 0x0000000000007fffUL
+
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_SHFT 0
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK 0x0000000000007fffUL
+
+#define UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK 0x0000000000000fffUL
+
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK)
+
+union uvh_rh_gam_mmioh_redirect_config0_mmr_u {
+	unsigned long	v;
+	struct uv3h_rh_gam_mmioh_redirect_config0_mmr_s {
+		unsigned long	nasid:15;			/* RW */
+		unsigned long	rsvd_15_63:49;
+	} s3;
+	struct uv4h_rh_gam_mmioh_redirect_config0_mmr_s {
+		unsigned long	nasid:15;			/* RW */
+		unsigned long	rsvd_15_63:49;
+	} s4;
+	struct uv4ah_rh_gam_mmioh_redirect_config0_mmr_s {
+		unsigned long	nasid:12;			/* RW */
+		unsigned long	rsvd_12_63:52;
+	} s4a;
+};
+
+/* ========================================================================= */
+/*                  UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR                    */
+/* ========================================================================= */
+#define UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR uv_undefined("UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR")
+#define UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR uv_undefined("UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR")
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR 0x1604800UL
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR 0x484800UL
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR (				\
+	is_uv1_hub() ? UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR :		\
+	is_uv2_hub() ? UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR :		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR :		\
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR)
+
+#define UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH uv_undefined("UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH")
+#define UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH uv_undefined("UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH")
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH 128
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH 128
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH (			\
+	is_uv1_hub() ? UV1H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH :	\
+	is_uv2_hub() ? UV2H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH :	\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH :	\
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH)
+
+
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_SHFT 0
+#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK 0x0000000000007fffUL
+
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_SHFT 0
+#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK 0x0000000000007fffUL
+
+#define UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK 0x0000000000000fffUL
+
+#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK (		\
+	is_uv3_hub() ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK : \
+	is_uv4a_hub() ? UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK : \
+	/*is_uv4_hub*/ UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK)
+
+union uvh_rh_gam_mmioh_redirect_config1_mmr_u {
+	unsigned long	v;
+	struct uv3h_rh_gam_mmioh_redirect_config1_mmr_s {
+		unsigned long	nasid:15;			/* RW */
+		unsigned long	rsvd_15_63:49;
+	} s3;
+	struct uv4h_rh_gam_mmioh_redirect_config1_mmr_s {
+		unsigned long	nasid:15;			/* RW */
+		unsigned long	rsvd_15_63:49;
+	} s4;
+	struct uv4ah_rh_gam_mmioh_redirect_config1_mmr_s {
+		unsigned long	nasid:12;			/* RW */
+		unsigned long	rsvd_12_63:52;
+	} s4a;
+};
+
+/* ========================================================================= */
 /*                    UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR                      */
 /* ========================================================================= */
 #define UV1H_RH_GAM_MMR_OVERLAY_CONFIG_MMR 0x1600028UL
@@ -4138,88 +4763,6 @@ union uv3h_gr0_gam_gr_config_u {
 };
 
 /* ========================================================================= */
-/*                   UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR                   */
-/* ========================================================================= */
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR		0x1603000UL
-
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_SHFT	26
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT	46
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_SHFT 63
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK	0x00003ffffc000000UL
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK	0x000fc00000000000UL
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK 0x8000000000000000UL
-
-union uv3h_rh_gam_mmioh_overlay_config0_mmr_u {
-	unsigned long	v;
-	struct uv3h_rh_gam_mmioh_overlay_config0_mmr_s {
-		unsigned long	rsvd_0_25:26;
-		unsigned long	base:20;			/* RW */
-		unsigned long	m_io:6;				/* RW */
-		unsigned long	n_io:4;
-		unsigned long	rsvd_56_62:7;
-		unsigned long	enable:1;			/* RW */
-	} s3;
-};
-
-/* ========================================================================= */
-/*                   UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR                   */
-/* ========================================================================= */
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR		0x1604000UL
-
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_SHFT	26
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT	46
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_SHFT 63
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK	0x00003ffffc000000UL
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK	0x000fc00000000000UL
-#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_ENABLE_MASK 0x8000000000000000UL
-
-union uv3h_rh_gam_mmioh_overlay_config1_mmr_u {
-	unsigned long	v;
-	struct uv3h_rh_gam_mmioh_overlay_config1_mmr_s {
-		unsigned long	rsvd_0_25:26;
-		unsigned long	base:20;			/* RW */
-		unsigned long	m_io:6;				/* RW */
-		unsigned long	n_io:4;
-		unsigned long	rsvd_56_62:7;
-		unsigned long	enable:1;			/* RW */
-	} s3;
-};
-
-/* ========================================================================= */
-/*                  UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR                   */
-/* ========================================================================= */
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR		0x1603800UL
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH	128
-
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_SHFT 0
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK 0x0000000000007fffUL
-
-union uv3h_rh_gam_mmioh_redirect_config0_mmr_u {
-	unsigned long	v;
-	struct uv3h_rh_gam_mmioh_redirect_config0_mmr_s {
-		unsigned long	nasid:15;			/* RW */
-		unsigned long	rsvd_15_63:49;
-	} s3;
-};
-
-/* ========================================================================= */
-/*                  UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR                   */
-/* ========================================================================= */
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR		0x1604800UL
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH	128
-
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_SHFT 0
-#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK 0x0000000000007fffUL
-
-union uv3h_rh_gam_mmioh_redirect_config1_mmr_u {
-	unsigned long	v;
-	struct uv3h_rh_gam_mmioh_redirect_config1_mmr_s {
-		unsigned long	nasid:15;			/* RW */
-		unsigned long	rsvd_15_63:49;
-	} s3;
-};
-
-/* ========================================================================= */
 /*                       UV4H_LB_PROC_INTD_QUEUE_FIRST                       */
 /* ========================================================================= */
 #define UV4H_LB_PROC_INTD_QUEUE_FIRST			0xa4100UL
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 52250681f68c..fb856c9f0449 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -49,7 +49,7 @@ static inline unsigned gtod_read_begin(const struct vsyscall_gtod_data *s)
 	unsigned ret;
 
 repeat:
-	ret = ACCESS_ONCE(s->seq);
+	ret = READ_ONCE(s->seq);
 	if (unlikely(ret & 1)) {
 		cpu_relax();
 		goto repeat;
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index caec8417539f..8b6780751132 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -70,11 +70,11 @@
 #define SECONDARY_EXEC_APIC_REGISTER_VIRT       0x00000100
 #define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY    0x00000200
 #define SECONDARY_EXEC_PAUSE_LOOP_EXITING	0x00000400
-#define SECONDARY_EXEC_RDRAND			0x00000800
+#define SECONDARY_EXEC_RDRAND_EXITING		0x00000800
 #define SECONDARY_EXEC_ENABLE_INVPCID		0x00001000
 #define SECONDARY_EXEC_ENABLE_VMFUNC            0x00002000
 #define SECONDARY_EXEC_SHADOW_VMCS              0x00004000
-#define SECONDARY_EXEC_RDSEED			0x00010000
+#define SECONDARY_EXEC_RDSEED_EXITING		0x00010000
 #define SECONDARY_EXEC_ENABLE_PML               0x00020000
 #define SECONDARY_EXEC_XSAVES			0x00100000
 #define SECONDARY_EXEC_TSC_SCALING              0x02000000
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index d9a7c659009c..b986b2ca688a 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -7,6 +7,7 @@
 
 #ifdef CONFIG_X86_VSYSCALL_EMULATION
 extern void map_vsyscall(void);
+extern void set_vsyscall_pgtable_user_bits(pgd_t *root);
 
 /*
  * Called on instruction fetch fault in vsyscall page.
diff --git a/arch/x86/include/asm/x2apic.h b/arch/x86/include/asm/x2apic.h
deleted file mode 100644
index 78ccf28d17db..000000000000
--- a/arch/x86/include/asm/x2apic.h
+++ /dev/null
@@ -1,50 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Common bits for X2APIC cluster/physical modes.
- */
-
-#ifndef _ASM_X86_X2APIC_H
-#define _ASM_X86_X2APIC_H
-
-#include <asm/apic.h>
-#include <asm/ipi.h>
-#include <linux/cpumask.h>
-
-static int x2apic_apic_id_valid(int apicid)
-{
-	return 1;
-}
-
-static int x2apic_apic_id_registered(void)
-{
-	return 1;
-}
-
-static void
-__x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest)
-{
-	unsigned long cfg = __prepare_ICR(0, vector, dest);
-	native_x2apic_icr_write(cfg, apicid);
-}
-
-static unsigned int x2apic_get_apic_id(unsigned long id)
-{
-	return id;
-}
-
-static unsigned long x2apic_set_apic_id(unsigned int id)
-{
-	return id;
-}
-
-static int x2apic_phys_pkg_id(int initial_apicid, int index_msb)
-{
-	return initial_apicid >> index_msb;
-}
-
-static void x2apic_send_IPI_self(int vector)
-{
-	apic_write(APIC_SELF_IPI, vector);
-}
-
-#endif /* _ASM_X86_X2APIC_H */
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 8a1ebf9540dd..fc2f082ac635 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -51,11 +51,13 @@ struct x86_init_resources {
  *				are set up.
  * @intr_init:			interrupt init code
  * @trap_init:			platform specific trap setup
+ * @intr_mode_init:		interrupt delivery mode setup
  */
 struct x86_init_irqs {
 	void (*pre_vector_init)(void);
 	void (*intr_init)(void);
 	void (*trap_init)(void);
+	void (*intr_mode_init)(void);
 };
 
 /**
@@ -115,6 +117,20 @@ struct x86_init_pci {
 };
 
 /**
+ * struct x86_hyper_init - x86 hypervisor init functions
+ * @init_platform:		platform setup
+ * @guest_late_init:		guest late init
+ * @x2apic_available:		X2APIC detection
+ * @init_mem_mapping:		setup early mappings during init_mem_mapping()
+ */
+struct x86_hyper_init {
+	void (*init_platform)(void);
+	void (*guest_late_init)(void);
+	bool (*x2apic_available)(void);
+	void (*init_mem_mapping)(void);
+};
+
+/**
  * struct x86_init_ops - functions for platform specific setup
  *
  */
@@ -127,6 +143,7 @@ struct x86_init_ops {
 	struct x86_init_timers		timers;
 	struct x86_init_iommu		iommu;
 	struct x86_init_pci		pci;
+	struct x86_hyper_init		hyper;
 };
 
 /**
@@ -195,11 +212,22 @@ enum x86_legacy_i8042_state {
 struct x86_legacy_features {
 	enum x86_legacy_i8042_state i8042;
 	int rtc;
+	int warm_reset;
+	int no_vga;
 	int reserve_bios_regions;
 	struct x86_legacy_devices devices;
 };
 
 /**
+ * struct x86_hyper_runtime - x86 hypervisor specific runtime callbacks
+ *
+ * @pin_vcpu:		pin current vcpu to specified physical cpu (run rarely)
+ */
+struct x86_hyper_runtime {
+	void (*pin_vcpu)(int cpu);
+};
+
+/**
  * struct x86_platform_ops - platform specific runtime functions
  * @calibrate_cpu:		calibrate CPU
  * @calibrate_tsc:		calibrate TSC, if different from CPU
@@ -218,6 +246,7 @@ struct x86_legacy_features {
  * 				possible in x86_early_init_platform_quirks() by
  * 				only using the current x86_hardware_subarch
  * 				semantics.
+ * @hyper:			x86 hypervisor specific runtime callbacks
  */
 struct x86_platform_ops {
 	unsigned long (*calibrate_cpu)(void);
@@ -233,6 +262,7 @@ struct x86_platform_ops {
 	void (*apic_post_init)(void);
 	struct x86_legacy_features legacy;
 	void (*set_legacy_features)(void);
+	struct x86_hyper_runtime hyper;
 };
 
 struct pci_dev;
diff --git a/arch/x86/include/asm/xen/cpuid.h b/arch/x86/include/asm/xen/cpuid.h
index 3bdd10d71223..a9630104f1c4 100644
--- a/arch/x86/include/asm/xen/cpuid.h
+++ b/arch/x86/include/asm/xen/cpuid.h
@@ -74,21 +74,43 @@
 #define XEN_CPUID_FEAT1_MMU_PT_UPDATE_PRESERVE_AD  (1u<<0)
 
 /*
+ * Leaf 4 (0x40000x03)
+ * Sub-leaf 0: EAX: bit 0: emulated tsc
+ *                  bit 1: host tsc is known to be reliable
+ *                  bit 2: RDTSCP instruction available
+ *             EBX: tsc_mode: 0=default (emulate if necessary), 1=emulate,
+ *                            2=no emulation, 3=no emulation + TSC_AUX support
+ *             ECX: guest tsc frequency in kHz
+ *             EDX: guest tsc incarnation (migration count)
+ * Sub-leaf 1: EAX: tsc offset low part
+ *             EBX: tsc offset high part
+ *             ECX: multiplicator for tsc->ns conversion
+ *             EDX: shift amount for tsc->ns conversion
+ * Sub-leaf 2: EAX: host tsc frequency in kHz
+ */
+
+/*
  * Leaf 5 (0x40000x04)
  * HVM-specific features
- * EAX: Features
- * EBX: vcpu id (iff EAX has XEN_HVM_CPUID_VCPU_ID_PRESENT flag)
+ * Sub-leaf 0: EAX: Features
+ * Sub-leaf 0: EBX: vcpu id (iff EAX has XEN_HVM_CPUID_VCPU_ID_PRESENT flag)
  */
-
-/* Virtualized APIC registers */
-#define XEN_HVM_CPUID_APIC_ACCESS_VIRT (1u << 0)
-/* Virtualized x2APIC accesses */
-#define XEN_HVM_CPUID_X2APIC_VIRT      (1u << 1)
+#define XEN_HVM_CPUID_APIC_ACCESS_VIRT (1u << 0) /* Virtualized APIC registers */
+#define XEN_HVM_CPUID_X2APIC_VIRT      (1u << 1) /* Virtualized x2APIC accesses */
 /* Memory mapped from other domains has valid IOMMU entries */
 #define XEN_HVM_CPUID_IOMMU_MAPPINGS   (1u << 2)
-/* vcpu id is present in EBX */
-#define XEN_HVM_CPUID_VCPU_ID_PRESENT  (1u << 3)
+#define XEN_HVM_CPUID_VCPU_ID_PRESENT  (1u << 3) /* vcpu id is present in EBX */
+
+/*
+ * Leaf 6 (0x40000x05)
+ * PV-specific parameters
+ * Sub-leaf 0: EAX: max available sub-leaf
+ * Sub-leaf 0: EBX: bits 0-7: max machine address width
+ */
+
+/* Max. address width in bits taking memory hotplug into account. */
+#define XEN_CPUID_MACHINE_ADDRESS_WIDTH_MASK (0xffu << 0)
 
-#define XEN_CPUID_MAX_NUM_LEAVES 4
+#define XEN_CPUID_MAX_NUM_LEAVES 5
 
 #endif /* __XEN_PUBLIC_ARCH_X86_CPUID_H__ */
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 7cb282e9e587..bfd882617613 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -44,6 +44,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/smap.h>
+#include <asm/nospec-branch.h>
 
 #include <xen/interface/xen.h>
 #include <xen/interface/sched.h>
@@ -217,9 +218,9 @@ privcmd_call(unsigned call,
 	__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
 
 	stac();
-	asm volatile("call *%[call]"
+	asm volatile(CALL_NOSPEC
 		     : __HYPERCALL_5PARAM
-		     : [call] "a" (&hypercall_page[call])
+		     : [thunk_target] "a" (&hypercall_page[call])
 		     : __HYPERCALL_CLOBBER5);
 	clac();
 
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index c6b84245e5ab..123e669bf363 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -27,6 +27,15 @@ typedef struct xpaddr {
 	phys_addr_t paddr;
 } xpaddr_t;
 
+#ifdef CONFIG_X86_64
+#define XEN_PHYSICAL_MASK	__sme_clr((1UL << 52) - 1)
+#else
+#define XEN_PHYSICAL_MASK	__PHYSICAL_MASK
+#endif
+
+#define XEN_PTE_MFN_MASK	((pteval_t)(((signed long)PAGE_MASK) & \
+					    XEN_PHYSICAL_MASK))
+
 #define XMADDR(x)	((xmaddr_t) { .maddr = (x) })
 #define XPADDR(x)	((xpaddr_t) { .paddr = (x) })
 
@@ -278,7 +287,7 @@ static inline unsigned long bfn_to_local_pfn(unsigned long mfn)
 
 static inline unsigned long pte_mfn(pte_t pte)
 {
-	return (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT;
+	return (pte.pte & XEN_PTE_MFN_MASK) >> PAGE_SHIFT;
 }
 
 static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot)
diff --git a/arch/x86/include/asm/xor.h b/arch/x86/include/asm/xor.h
index 1f5c5161ead6..45c8605467f1 100644
--- a/arch/x86/include/asm/xor.h
+++ b/arch/x86/include/asm/xor.h
@@ -1,7 +1,4 @@
-#ifdef CONFIG_KMEMCHECK
-/* kmemcheck doesn't handle MMX/SSE/SSE2 instructions */
-# include <asm-generic/xor.h>
-#elif !defined(_ASM_X86_XOR_H)
+#ifndef _ASM_X86_XOR_H
 #define _ASM_X86_XOR_H
 
 /*
diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild
index da1489cb64dc..322681622d1e 100644
--- a/arch/x86/include/uapi/asm/Kbuild
+++ b/arch/x86/include/uapi/asm/Kbuild
@@ -1,6 +1,8 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += bpf_perf_event.h
 generated-y += unistd_32.h
 generated-y += unistd_64.h
 generated-y += unistd_x32.h
+generic-y += poll.h
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index afdd5ae0fcc4..aebf60357758 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -9,6 +9,7 @@
 #define SETUP_PCI			3
 #define SETUP_EFI			4
 #define SETUP_APPLE_PROPERTIES		5
+#define SETUP_JAILHOUSE			6
 
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK	0x07FF
@@ -126,6 +127,27 @@ struct boot_e820_entry {
 	__u32 type;
 } __attribute__((packed));
 
+/*
+ * Smallest compatible version of jailhouse_setup_data required by this kernel.
+ */
+#define JAILHOUSE_SETUP_REQUIRED_VERSION	1
+
+/*
+ * The boot loader is passing platform information via this Jailhouse-specific
+ * setup data structure.
+ */
+struct jailhouse_setup_data {
+	u16	version;
+	u16	compatible_version;
+	u16	pm_timer_address;
+	u16	num_cpus;
+	u64	pci_mmconfig_base;
+	u32	tsc_khz;
+	u32	apic_khz;
+	u8	standard_ioapic;
+	u8	cpu_ids[255];
+} __attribute__((packed));
+
 /* The so-called "zeropage" */
 struct boot_params {
 	struct screen_info screen_info;			/* 0x000 */
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index 1a5bfead93b4..099414345865 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -40,6 +40,9 @@
  */
 #define HV_X64_ACCESS_FREQUENCY_MSRS		(1 << 11)
 
+/* AccessReenlightenmentControls privilege */
+#define HV_X64_ACCESS_REENLIGHTENMENT		BIT(13)
+
 /*
  * Basic SynIC MSRs (HV_X64_MSR_SCONTROL through HV_X64_MSR_EOM
  * and HV_X64_MSR_SINT0 through HV_X64_MSR_SINT15) available
@@ -234,6 +237,30 @@
 #define HV_X64_MSR_CRASH_PARAMS		\
 		(1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0))
 
+/* TSC emulation after migration */
+#define HV_X64_MSR_REENLIGHTENMENT_CONTROL	0x40000106
+
+struct hv_reenlightenment_control {
+	__u64 vector:8;
+	__u64 reserved1:8;
+	__u64 enabled:1;
+	__u64 reserved2:15;
+	__u64 target_vp:32;
+};
+
+#define HV_X64_MSR_TSC_EMULATION_CONTROL	0x40000107
+#define HV_X64_MSR_TSC_EMULATION_STATUS		0x40000108
+
+struct hv_tsc_emulation_control {
+	__u64 enabled:1;
+	__u64 reserved:63;
+};
+
+struct hv_tsc_emulation_status {
+	__u64 inprogress:1;
+	__u64 reserved:63;
+};
+
 #define HV_X64_MSR_HYPERCALL_ENABLE		0x00000001
 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT	12
 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK	\
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 554aa8f24f91..6cfa9c8cb7d6 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -25,6 +25,8 @@
 #define KVM_FEATURE_STEAL_TIME		5
 #define KVM_FEATURE_PV_EOI		6
 #define KVM_FEATURE_PV_UNHALT		7
+#define KVM_FEATURE_PV_TLB_FLUSH	9
+#define KVM_FEATURE_ASYNC_PF_VMEXIT	10
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.
@@ -51,6 +53,9 @@ struct kvm_steal_time {
 	__u32 pad[11];
 };
 
+#define KVM_VCPU_PREEMPTED          (1 << 0)
+#define KVM_VCPU_FLUSH_TLB          (1 << 1)
+
 #define KVM_CLOCK_PAIRING_WALLCLOCK 0
 struct kvm_clock_pairing {
 	__s64 sec;
@@ -110,5 +115,4 @@ struct kvm_vcpu_pv_apf_data {
 #define KVM_PV_EOI_ENABLED KVM_PV_EOI_MASK
 #define KVM_PV_EOI_DISABLED 0x0
 
-
 #endif /* _UAPI_ASM_X86_KVM_PARA_H */
diff --git a/arch/x86/include/uapi/asm/poll.h b/arch/x86/include/uapi/asm/poll.h
deleted file mode 100644
index c98509d3149e..000000000000
--- a/arch/x86/include/uapi/asm/poll.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/poll.h>
diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index 6f3355399665..bcba3c643e63 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -78,7 +78,12 @@
 #define X86_CR3_PWT		_BITUL(X86_CR3_PWT_BIT)
 #define X86_CR3_PCD_BIT		4 /* Page Cache Disable */
 #define X86_CR3_PCD		_BITUL(X86_CR3_PCD_BIT)
-#define X86_CR3_PCID_MASK	_AC(0x00000fff,UL) /* PCID Mask */
+
+#define X86_CR3_PCID_BITS	12
+#define X86_CR3_PCID_MASK	(_AC((1UL << X86_CR3_PCID_BITS) - 1, UL))
+
+#define X86_CR3_PCID_NOFLUSH_BIT 63 /* Preserve old PCID */
+#define X86_CR3_PCID_NOFLUSH    _BITULL(X86_CR3_PCID_NOFLUSH_BIT)
 
 /*
  * Intel CPU features in CR4
@@ -105,6 +110,8 @@
 #define X86_CR4_OSFXSR		_BITUL(X86_CR4_OSFXSR_BIT)
 #define X86_CR4_OSXMMEXCPT_BIT	10 /* enable unmasked SSE exceptions */
 #define X86_CR4_OSXMMEXCPT	_BITUL(X86_CR4_OSXMMEXCPT_BIT)
+#define X86_CR4_UMIP_BIT	11 /* enable UMIP support */
+#define X86_CR4_UMIP		_BITUL(X86_CR4_UMIP_BIT)
 #define X86_CR4_LA57_BIT	12 /* enable 5-level page tables */
 #define X86_CR4_LA57		_BITUL(X86_CR4_LA57_BIT)
 #define X86_CR4_VMXE_BIT	13 /* enable VMX virtualization */
@@ -152,5 +159,8 @@
 #define CX86_ARR_BASE	0xc4
 #define CX86_RCR_BASE	0xdc
 
+#define CR0_STATE	(X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \
+			 X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \
+			 X86_CR0_PG)
 
 #endif /* _UAPI_ASM_X86_PROCESSOR_FLAGS_H */