Merge branch 'x86/asm' into x86/core, to pick up dependent commits

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

27 files changed, 242 insertions, 314 deletions

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 853fbcf68719..6bf1970493a5 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -236,10 +236,12 @@ static inline int alternatives_text_reserved(void *start, void *end)
  * references: i.e., if used for a function, it would add the PLT
  * suffix.
  */
-#define alternative_call(oldfunc, newfunc, ft_flags, output, input...)			\
+#define alternative_call(oldfunc, newfunc, ft_flags, output, input, clobbers...)	\
 	asm_inline volatile(ALTERNATIVE("call %c[old]", "call %c[new]", ft_flags)	\
 		: ALT_OUTPUT_SP(output)							\
-		: [old] "i" (oldfunc), [new] "i" (newfunc), ## input)
+		: [old] "i" (oldfunc), [new] "i" (newfunc)				\
+		  COMMA(input)								\
+		: clobbers)
 
 /*
  * Like alternative_call, but there are two features and respective functions.
@@ -248,24 +250,14 @@ static inline int alternatives_text_reserved(void *start, void *end)
  * Otherwise, old function is used.
  */
 #define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2,		\
-			   output, input...)						\
+			   output, input, clobbers...)					\
 	asm_inline volatile(ALTERNATIVE_2("call %c[old]", "call %c[new1]", ft_flags1,	\
 		"call %c[new2]", ft_flags2)						\
 		: ALT_OUTPUT_SP(output)							\
 		: [old] "i" (oldfunc), [new1] "i" (newfunc1),				\
-		  [new2] "i" (newfunc2), ## input)
-
-/*
- * use this macro(s) if you need more than one output parameter
- * in alternative_io
- */
-#define ASM_OUTPUT2(a...) a
-
-/*
- * use this macro if you need clobbers but no inputs in
- * alternative_{input,io,call}()
- */
-#define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
+		  [new2] "i" (newfunc2)							\
+		  COMMA(input)								\
+		: clobbers)
 
 #define ALT_OUTPUT_SP(...) ASM_CALL_CONSTRAINT, ## __VA_ARGS__
 
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index f21ff1932699..c903d358405d 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -99,8 +99,8 @@ static inline void native_apic_mem_write(u32 reg, u32 v)
 	volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg);
 
 	alternative_io("movl %0, %1", "xchgl %0, %1", X86_BUG_11AP,
-		       ASM_OUTPUT2("=r" (v), "=m" (*addr)),
-		       ASM_OUTPUT2("0" (v), "m" (*addr)));
+		       ASM_OUTPUT("=r" (v), "=m" (*addr)),
+		       ASM_INPUT("0" (v), "m" (*addr)));
 }
 
 static inline u32 native_apic_mem_read(u32 reg)
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 3674006e3974..8d9e62725202 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -16,7 +16,7 @@
 #include <asm/gsseg.h>
 #include <asm/nospec-branch.h>
 
-#ifndef CONFIG_X86_CMPXCHG64
+#ifndef CONFIG_X86_CX8
 extern void cmpxchg8b_emu(void);
 #endif
 
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 2bec0c89a95c..975ae7a9397e 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -213,6 +213,17 @@ static __always_inline __pure void *rip_rel_ptr(void *p)
 
 /* For C file, we already have NOKPROBE_SYMBOL macro */
 
+/* Insert a comma if args are non-empty */
+#define COMMA(x...)		__COMMA(x)
+#define __COMMA(...)		, ##__VA_ARGS__
+
+/*
+ * Combine multiple asm inline constraint args into a single arg for passing to
+ * another macro.
+ */
+#define ASM_OUTPUT(x...)	x
+#define ASM_INPUT(x...)		x
+
 /*
  * 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
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 6c6e9b9f98a4..ab838205c1c6 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -48,17 +48,20 @@ static __always_inline s64 arch_atomic64_read_nonatomic(const atomic64_t *v)
 	ATOMIC64_EXPORT(atomic64_##sym)
 #endif
 
-#ifdef CONFIG_X86_CMPXCHG64
-#define __alternative_atomic64(f, g, out, in...) \
-	asm volatile("call %c[func]" \
+#ifdef CONFIG_X86_CX8
+#define __alternative_atomic64(f, g, out, in, clobbers...)		\
+	asm volatile("call %c[func]"					\
 		     : ALT_OUTPUT_SP(out) \
-		     : [func] "i" (atomic64_##g##_cx8), ## in)
+		     : [func] "i" (atomic64_##g##_cx8)			\
+		       COMMA(in)					\
+		     : clobbers)
 
 #define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8)
 #else
-#define __alternative_atomic64(f, g, out, in...) \
-	alternative_call(atomic64_##f##_386, atomic64_##g##_cx8, \
-			 X86_FEATURE_CX8, ASM_OUTPUT2(out), ## in)
+#define __alternative_atomic64(f, g, out, in, clobbers...)		\
+	alternative_call(atomic64_##f##_386, atomic64_##g##_cx8,	\
+			 X86_FEATURE_CX8, ASM_OUTPUT(out),		\
+			 ASM_INPUT(in), clobbers)
 
 #define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8); \
 	ATOMIC64_DECL_ONE(sym##_386)
@@ -69,8 +72,8 @@ ATOMIC64_DECL_ONE(inc_386);
 ATOMIC64_DECL_ONE(dec_386);
 #endif
 
-#define alternative_atomic64(f, out, in...) \
-	__alternative_atomic64(f, f, ASM_OUTPUT2(out), ## in)
+#define alternative_atomic64(f, out, in, clobbers...) \
+	__alternative_atomic64(f, f, ASM_OUTPUT(out), ASM_INPUT(in), clobbers)
 
 ATOMIC64_DECL(read);
 ATOMIC64_DECL(set);
@@ -105,9 +108,10 @@ static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n)
 	s64 o;
 	unsigned high = (unsigned)(n >> 32);
 	unsigned low = (unsigned)n;
-	alternative_atomic64(xchg, "=&A" (o),
-			     "S" (v), "b" (low), "c" (high)
-			     : "memory");
+	alternative_atomic64(xchg,
+			     "=&A" (o),
+			     ASM_INPUT("S" (v), "b" (low), "c" (high)),
+			     "memory");
 	return o;
 }
 #define arch_atomic64_xchg arch_atomic64_xchg
@@ -116,23 +120,25 @@ static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i)
 {
 	unsigned high = (unsigned)(i >> 32);
 	unsigned low = (unsigned)i;
-	alternative_atomic64(set, /* no output */,
-			     "S" (v), "b" (low), "c" (high)
-			     : "eax", "edx", "memory");
+	alternative_atomic64(set,
+			     /* no output */,
+			     ASM_INPUT("S" (v), "b" (low), "c" (high)),
+			     "eax", "edx", "memory");
 }
 
 static __always_inline s64 arch_atomic64_read(const atomic64_t *v)
 {
 	s64 r;
-	alternative_atomic64(read, "=&A" (r), "c" (v) : "memory");
+	alternative_atomic64(read, "=&A" (r), "c" (v), "memory");
 	return r;
 }
 
 static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 {
 	alternative_atomic64(add_return,
-			     ASM_OUTPUT2("+A" (i), "+c" (v)),
-			     ASM_NO_INPUT_CLOBBER("memory"));
+			     ASM_OUTPUT("+A" (i), "+c" (v)),
+			     /* no input */,
+			     "memory");
 	return i;
 }
 #define arch_atomic64_add_return arch_atomic64_add_return
@@ -140,8 +146,9 @@ static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
 {
 	alternative_atomic64(sub_return,
-			     ASM_OUTPUT2("+A" (i), "+c" (v)),
-			     ASM_NO_INPUT_CLOBBER("memory"));
+			     ASM_OUTPUT("+A" (i), "+c" (v)),
+			     /* no input */,
+			     "memory");
 	return i;
 }
 #define arch_atomic64_sub_return arch_atomic64_sub_return
@@ -149,8 +156,10 @@ static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
 static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v)
 {
 	s64 a;
-	alternative_atomic64(inc_return, "=&A" (a),
-			     "S" (v) : "memory", "ecx");
+	alternative_atomic64(inc_return,
+			     "=&A" (a),
+			     "S" (v),
+			     "memory", "ecx");
 	return a;
 }
 #define arch_atomic64_inc_return arch_atomic64_inc_return
@@ -158,8 +167,10 @@ static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v)
 static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v)
 {
 	s64 a;
-	alternative_atomic64(dec_return, "=&A" (a),
-			     "S" (v) : "memory", "ecx");
+	alternative_atomic64(dec_return,
+			     "=&A" (a),
+			     "S" (v),
+			     "memory", "ecx");
 	return a;
 }
 #define arch_atomic64_dec_return arch_atomic64_dec_return
@@ -167,28 +178,34 @@ static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v)
 static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(add, add_return,
-			       ASM_OUTPUT2("+A" (i), "+c" (v)),
-			       ASM_NO_INPUT_CLOBBER("memory"));
+			       ASM_OUTPUT("+A" (i), "+c" (v)),
+			       /* no input */,
+			       "memory");
 }
 
 static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(sub, sub_return,
-			       ASM_OUTPUT2("+A" (i), "+c" (v)),
-			       ASM_NO_INPUT_CLOBBER("memory"));
+			       ASM_OUTPUT("+A" (i), "+c" (v)),
+			       /* no input */,
+			       "memory");
 }
 
 static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
-	__alternative_atomic64(inc, inc_return, /* no output */,
-			       "S" (v) : "memory", "eax", "ecx", "edx");
+	__alternative_atomic64(inc, inc_return,
+			       /* no output */,
+			       "S" (v),
+			       "memory", "eax", "ecx", "edx");
 }
 #define arch_atomic64_inc arch_atomic64_inc
 
 static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
-	__alternative_atomic64(dec, dec_return, /* no output */,
-			       "S" (v) : "memory", "eax", "ecx", "edx");
+	__alternative_atomic64(dec, dec_return,
+			       /* no output */,
+			       "S" (v),
+			       "memory", "eax", "ecx", "edx");
 }
 #define arch_atomic64_dec arch_atomic64_dec
 
@@ -197,8 +214,9 @@ static __always_inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 	unsigned low = (unsigned)u;
 	unsigned high = (unsigned)(u >> 32);
 	alternative_atomic64(add_unless,
-			     ASM_OUTPUT2("+A" (a), "+c" (low), "+D" (high)),
-			     "S" (v) : "memory");
+			     ASM_OUTPUT("+A" (a), "+c" (low), "+D" (high)),
+			     "S" (v),
+			     "memory");
 	return (int)a;
 }
 #define arch_atomic64_add_unless arch_atomic64_add_unless
@@ -206,8 +224,10 @@ static __always_inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 static __always_inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 {
 	int r;
-	alternative_atomic64(inc_not_zero, "=&a" (r),
-			     "S" (v) : "ecx", "edx", "memory");
+	alternative_atomic64(inc_not_zero,
+			     "=&a" (r),
+			     "S" (v),
+			     "ecx", "edx", "memory");
 	return r;
 }
 #define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero
@@ -215,8 +235,10 @@ static __always_inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	s64 r;
-	alternative_atomic64(dec_if_positive, "=&A" (r),
-			     "S" (v) : "ecx", "memory");
+	alternative_atomic64(dec_if_positive,
+			     "=&A" (r),
+			     "S" (v),
+			     "ecx", "memory");
 	return r;
 }
 #define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index fd1282a783dd..ee89fbc4dd4b 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -69,7 +69,7 @@ static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp,
 	return __arch_try_cmpxchg64(ptr, oldp, new,);
 }
 
-#ifdef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CX8
 
 #define arch_cmpxchg64 __cmpxchg64
 
@@ -91,12 +91,14 @@ static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp,
 	union __u64_halves o = { .full = (_old), },			\
 			   n = { .full = (_new), };			\
 									\
-	asm volatile(ALTERNATIVE(_lock_loc				\
-				 "call cmpxchg8b_emu",			\
-				 _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
-		     : ALT_OUTPUT_SP("+a" (o.low), "+d" (o.high))	\
-		     : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr)	\
-		     : "memory");					\
+	asm_inline volatile(						\
+		ALTERNATIVE(_lock_loc					\
+			    "call cmpxchg8b_emu",			\
+			    _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8)	\
+		: ALT_OUTPUT_SP("+a" (o.low), "+d" (o.high))		\
+		: "b" (n.low), "c" (n.high),				\
+		  [ptr] "S" (_ptr)					\
+		: "memory");						\
 									\
 	o.full;								\
 })
@@ -119,14 +121,16 @@ static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64
 			   n = { .full = (_new), };			\
 	bool ret;							\
 									\
-	asm volatile(ALTERNATIVE(_lock_loc				\
-				 "call cmpxchg8b_emu",			\
-				 _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
-		     CC_SET(e)						\
-		     : ALT_OUTPUT_SP(CC_OUT(e) (ret),			\
-				     "+a" (o.low), "+d" (o.high))	\
-		     : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr)	\
-		     : "memory");					\
+	asm_inline volatile(						\
+		ALTERNATIVE(_lock_loc					\
+			    "call cmpxchg8b_emu",			\
+			    _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
+		CC_SET(e)						\
+		: ALT_OUTPUT_SP(CC_OUT(e) (ret),			\
+				"+a" (o.low), "+d" (o.high))		\
+		: "b" (n.low), "c" (n.high),				\
+		  [ptr] "S" (_ptr)					\
+		: "memory");						\
 									\
 	if (unlikely(!ret))						\
 		*(_oldp) = o.full;					\
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index f44bbce18859..ad235dda1ded 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -49,20 +49,6 @@ static inline void split_lock_init(void) {}
 static inline void bus_lock_init(void) {}
 #endif
 
-#ifdef CONFIG_CPU_SUP_INTEL
-u8 get_this_hybrid_cpu_type(void);
-u32 get_this_hybrid_cpu_native_id(void);
-#else
-static inline u8 get_this_hybrid_cpu_type(void)
-{
-	return 0;
-}
-
-static inline u32 get_this_hybrid_cpu_native_id(void)
-{
-	return 0;
-}
-#endif
 #ifdef CONFIG_IA32_FEAT_CTL
 void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
 #else
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index de1ad09fe8d7..e955da397e0e 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -37,19 +37,15 @@ enum cpuid_leafs
 	NR_CPUID_WORDS,
 };
 
-#define X86_CAP_FMT_NUM "%d:%d"
-#define x86_cap_flag_num(flag) ((flag) >> 5), ((flag) & 31)
-
 extern const char * const x86_cap_flags[NCAPINTS*32];
 extern const char * const x86_power_flags[32];
-#define X86_CAP_FMT "%s"
-#define x86_cap_flag(flag) x86_cap_flags[flag]
 
 /*
  * In order to save room, we index into this array by doing
  * X86_BUG_<name> - NCAPINTS*32.
  */
 extern const char * const x86_bug_flags[NBUGINTS*32];
+#define x86_bug_flag(flag) x86_bug_flags[flag]
 
 #define test_cpu_cap(c, bit)						\
 	 arch_test_bit(bit, (unsigned long *)((c)->x86_capability))
diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h
index b2b9b4ef3dae..a92e4b08820a 100644
--- a/arch/x86/include/asm/cpuid.h
+++ b/arch/x86/include/asm/cpuid.h
@@ -6,6 +6,7 @@
 #ifndef _ASM_X86_CPUID_H
 #define _ASM_X86_CPUID_H
 
+#include <linux/build_bug.h>
 #include <linux/types.h>
 
 #include <asm/string.h>
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 62dc9f59ea76..ec95fe44fa3a 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -46,7 +46,6 @@ struct gdt_page {
 } __attribute__((aligned(PAGE_SIZE)));
 
 DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
-DECLARE_INIT_PER_CPU(gdt_page);
 
 /* Provide the original GDT */
 static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu)
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1fb83d47711f..128602612eca 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -54,8 +54,9 @@ typedef struct user_i387_struct elf_fpregset_t;
 #define R_X86_64_GLOB_DAT	6	/* Create GOT entry */
 #define R_X86_64_JUMP_SLOT	7	/* Create PLT entry */
 #define R_X86_64_RELATIVE	8	/* Adjust by program base */
-#define R_X86_64_GOTPCREL	9	/* 32 bit signed pc relative
-					   offset to GOT */
+#define R_X86_64_GOTPCREL	9	/* 32 bit signed pc relative offset to GOT */
+#define R_X86_64_GOTPCRELX	41
+#define R_X86_64_REX_GOTPCRELX	42
 #define R_X86_64_32		10	/* Direct 32 bit zero extended */
 #define R_X86_64_32S		11	/* Direct 32 bit sign extended */
 #define R_X86_64_16		12	/* Direct 16 bit zero extended */
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 6d7b04ffc5fd..b657d78071c6 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -110,9 +110,9 @@
 
 #define INTEL_SAPPHIRERAPIDS_X		IFM(6, 0x8F) /* Golden Cove */
 
-#define INTEL_EMERALDRAPIDS_X		IFM(6, 0xCF)
+#define INTEL_EMERALDRAPIDS_X		IFM(6, 0xCF) /* Raptor Cove */
 
-#define INTEL_GRANITERAPIDS_X		IFM(6, 0xAD)
+#define INTEL_GRANITERAPIDS_X		IFM(6, 0xAD) /* Redwood Cove */
 #define INTEL_GRANITERAPIDS_D		IFM(6, 0xAE)
 
 /* "Hybrid" Processors (P-Core/E-Core) */
@@ -126,16 +126,16 @@
 #define INTEL_RAPTORLAKE_P		IFM(6, 0xBA)
 #define INTEL_RAPTORLAKE_S		IFM(6, 0xBF)
 
-#define INTEL_METEORLAKE		IFM(6, 0xAC)
+#define INTEL_METEORLAKE		IFM(6, 0xAC) /* Redwood Cove / Crestmont */
 #define INTEL_METEORLAKE_L		IFM(6, 0xAA)
 
-#define INTEL_ARROWLAKE_H		IFM(6, 0xC5)
+#define INTEL_ARROWLAKE_H		IFM(6, 0xC5) /* Lion Cove / Skymont */
 #define INTEL_ARROWLAKE			IFM(6, 0xC6)
 #define INTEL_ARROWLAKE_U		IFM(6, 0xB5)
 
-#define INTEL_LUNARLAKE_M		IFM(6, 0xBD)
+#define INTEL_LUNARLAKE_M		IFM(6, 0xBD) /* Lion Cove / Skymont */
 
-#define INTEL_PANTHERLAKE_L		IFM(6, 0xCC)
+#define INTEL_PANTHERLAKE_L		IFM(6, 0xCC) /* Cougar Cove / Crestmont */
 
 /* "Small Core" Processors (Atom/E-Core) */
 
@@ -149,9 +149,9 @@
 #define INTEL_ATOM_SILVERMONT		IFM(6, 0x37) /* Bay Trail, Valleyview */
 #define INTEL_ATOM_SILVERMONT_D		IFM(6, 0x4D) /* Avaton, Rangely */
 #define INTEL_ATOM_SILVERMONT_MID	IFM(6, 0x4A) /* Merriefield */
+#define INTEL_ATOM_SILVERMONT_MID2	IFM(6, 0x5A) /* Anniedale */
 
 #define INTEL_ATOM_AIRMONT		IFM(6, 0x4C) /* Cherry Trail, Braswell */
-#define INTEL_ATOM_AIRMONT_MID		IFM(6, 0x5A) /* Moorefield */
 #define INTEL_ATOM_AIRMONT_NP		IFM(6, 0x75) /* Lightning Mountain */
 
 #define INTEL_ATOM_GOLDMONT		IFM(6, 0x5C) /* Apollo Lake */
@@ -182,10 +182,23 @@
 /* Family 19 */
 #define INTEL_PANTHERCOVE_X		IFM(19, 0x01) /* Diamond Rapids */
 
-/* CPU core types */
+/*
+ * Intel CPU core types
+ *
+ * CPUID.1AH.EAX[31:0] uniquely identifies the microarchitecture
+ * of the core. Bits 31-24 indicates its core type (Core or Atom)
+ * and Bits [23:0] indicates the native model ID of the core.
+ * Core type and native model ID are defined in below enumerations.
+ */
 enum intel_cpu_type {
+	INTEL_CPU_TYPE_UNKNOWN,
 	INTEL_CPU_TYPE_ATOM = 0x20,
 	INTEL_CPU_TYPE_CORE = 0x40,
 };
 
+enum intel_native_id {
+	INTEL_ATOM_CMT_NATIVE_ID = 0x2,  /* Crestmont */
+	INTEL_ATOM_SKT_NATIVE_ID = 0x3,  /* Skymont */
+};
+
 #endif /* _ASM_X86_INTEL_FAMILY_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index ed580c7f9d0a..1a0dc2b2bf5b 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -175,6 +175,9 @@ extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, un
 extern void __iomem *ioremap_encrypted(resource_size_t phys_addr, unsigned long size);
 #define ioremap_encrypted ioremap_encrypted
 
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags);
+#define arch_memremap_wb arch_memremap_wb
+
 /**
  * ioremap     -   map bus memory into CPU space
  * @offset:    bus address of the memory
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index f91ab1e75f9f..5e6193dbc97e 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -77,11 +77,11 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 		return hv_tdx_hypercall(control, input_address, output_address);
 
 	if (hv_isolation_type_snp() && !hyperv_paravisor_present) {
-		__asm__ __volatile__("mov %4, %%r8\n"
+		__asm__ __volatile__("mov %[output_address], %%r8\n"
 				     "vmmcall"
 				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 				       "+c" (control), "+d" (input_address)
-				     :  "r" (output_address)
+				     : [output_address] "r" (output_address)
 				     : "cc", "memory", "r8", "r9", "r10", "r11");
 		return hv_status;
 	}
@@ -89,12 +89,12 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 	if (!hv_hypercall_pg)
 		return U64_MAX;
 
-	__asm__ __volatile__("mov %4, %%r8\n"
+	__asm__ __volatile__("mov %[output_address], %%r8\n"
 			     CALL_NOSPEC
 			     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 			       "+c" (control), "+d" (input_address)
-			     :  "r" (output_address),
-				THUNK_TARGET(hv_hypercall_pg)
+			     : [output_address] "r" (output_address),
+			       THUNK_TARGET(hv_hypercall_pg)
 			     : "cc", "memory", "r8", "r9", "r10", "r11");
 #else
 	u32 input_address_hi = upper_32_bits(input_address);
@@ -187,18 +187,18 @@ static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2)
 		return hv_tdx_hypercall(control, input1, input2);
 
 	if (hv_isolation_type_snp() && !hyperv_paravisor_present) {
-		__asm__ __volatile__("mov %4, %%r8\n"
+		__asm__ __volatile__("mov %[input2], %%r8\n"
 				     "vmmcall"
 				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 				       "+c" (control), "+d" (input1)
-				     : "r" (input2)
+				     : [input2] "r" (input2)
 				     : "cc", "r8", "r9", "r10", "r11");
 	} else {
-		__asm__ __volatile__("mov %4, %%r8\n"
+		__asm__ __volatile__("mov %[input2], %%r8\n"
 				     CALL_NOSPEC
 				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
 				       "+c" (control), "+d" (input1)
-				     : "r" (input2),
+				     : [input2] "r" (input2),
 				       THUNK_TARGET(hv_hypercall_pg)
 				     : "cc", "r8", "r9", "r10", "r11");
 	}
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 7e8bf78c03d5..aee26bb8230f 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -198,9 +198,8 @@
 .endm
 
 /*
- * Equivalent to -mindirect-branch-cs-prefix; emit the 5 byte jmp/call
- * to the retpoline thunk with a CS prefix when the register requires
- * a RAX prefix byte to encode. Also see apply_retpolines().
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
  */
 .macro __CS_PREFIX reg:req
 	.irp rs,r8,r9,r10,r11,r12,r13,r14,r15
@@ -421,19 +420,26 @@ static inline void call_depth_return_thunk(void) {}
 #ifdef CONFIG_X86_64
 
 /*
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
+ */
+#define __CS_PREFIX(reg)				\
+	".irp rs,r8,r9,r10,r11,r12,r13,r14,r15\n"	\
+	".ifc \\rs," reg "\n"				\
+	".byte 0x2e\n"					\
+	".endif\n"					\
+	".endr\n"
+
+/*
  * Inline asm uses the %V modifier which is only in newer GCC
  * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined.
  */
-# define CALL_NOSPEC						\
-	ALTERNATIVE_2(						\
-	ANNOTATE_RETPOLINE_SAFE					\
-	"call *%[thunk_target]\n",				\
-	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
-	X86_FEATURE_RETPOLINE,					\
-	"lfence;\n"						\
-	ANNOTATE_RETPOLINE_SAFE					\
-	"call *%[thunk_target]\n",				\
-	X86_FEATURE_RETPOLINE_LFENCE)
+#ifdef CONFIG_MITIGATION_RETPOLINE
+#define CALL_NOSPEC	__CS_PREFIX("%V[thunk_target]")	\
+			"call __x86_indirect_thunk_%V[thunk_target]\n"
+#else
+#define CALL_NOSPEC	"call *%[thunk_target]\n"
+#endif
 
 # define THUNK_TARGET(addr) [thunk_target] "r" (addr)
 
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index faf9cc1c14bb..25c32652f404 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -11,8 +11,8 @@
  * a virtual address space of one gigabyte, which limits the
  * amount of physical memory you can use to about 950MB.
  *
- * If you want more physical memory than this then see the CONFIG_HIGHMEM4G
- * and CONFIG_HIGHMEM64G options in the kernel configuration.
+ * If you want more physical memory than this then see the CONFIG_VMSPLIT_2G
+ * and CONFIG_HIGHMEM4G options in the kernel configuration.
  */
 #define __PAGE_OFFSET_BASE	_AC(CONFIG_PAGE_OFFSET, UL)
 #define __PAGE_OFFSET		__PAGE_OFFSET_BASE
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index 5c5cfa076a27..b5279f5d5601 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -55,8 +55,8 @@ static inline void clear_page(void *page)
 			   clear_page_rep, X86_FEATURE_REP_GOOD,
 			   clear_page_erms, X86_FEATURE_ERMS,
 			   "=D" (page),
-			   "D" (page)
-			   : "cc", "memory", "rax", "rcx");
+			   "D" (page),
+			   "cc", "memory", "rax", "rcx");
 }
 
 void copy_page(void *to, void *from);
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 041aff51eb50..38a632a282d4 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -91,11 +91,6 @@ static inline void __flush_tlb_multi(const struct cpumask *cpumask,
 	PVOP_VCALL2(mmu.flush_tlb_multi, cpumask, info);
 }
 
-static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	PVOP_VCALL2(mmu.tlb_remove_table, tlb, table);
-}
-
 static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
 {
 	PVOP_VCALL1(mmu.exit_mmap, mm);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 8e21a1a85e74..127a372dacc9 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -134,8 +134,6 @@ struct pv_mmu_ops {
 	void (*flush_tlb_multi)(const struct cpumask *cpus,
 				const struct flush_tlb_info *info);
 
-	void (*tlb_remove_table)(struct mmu_gather *tlb, void *table);
-
 	/* Hook for intercepting the destruction of an mm_struct. */
 	void (*exit_mmap)(struct mm_struct *mm);
 	void (*notify_page_enc_status_changed)(unsigned long pfn, int npages, bool enc);
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index e525cd85f999..8a8cf86dded3 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -20,14 +20,9 @@
 
 #define PER_CPU_VAR(var)	__percpu(var)__percpu_rel
 
-#ifdef CONFIG_X86_64_SMP
-# define INIT_PER_CPU_VAR(var)  init_per_cpu__##var
-#else
-# define INIT_PER_CPU_VAR(var)  var
-#endif
-
 #else /* !__ASSEMBLY__: */
 
+#include <linux/args.h>
 #include <linux/build_bug.h>
 #include <linux/stringify.h>
 #include <asm/asm.h>
@@ -41,12 +36,7 @@
 # define __seg_fs		__attribute__((address_space(__seg_fs)))
 #endif
 
-#ifdef CONFIG_X86_64
-# define __percpu_seg_override	__seg_gs
-#else
-# define __percpu_seg_override	__seg_fs
-#endif
-
+#define __percpu_seg_override	CONCATENATE(__seg_, __percpu_seg)
 #define __percpu_prefix		""
 
 #else /* !CONFIG_CC_HAS_NAMED_AS: */
@@ -98,22 +88,6 @@
 #define __force_percpu_arg(x)	__force_percpu_prefix "%" #x
 
 /*
- * Initialized pointers to per-CPU variables needed for the boot
- * processor need to use these macros to get the proper address
- * offset from __per_cpu_load on SMP.
- *
- * There also must be an entry in vmlinux_64.lds.S
- */
-#define DECLARE_INIT_PER_CPU(var) \
-       extern typeof(var) init_per_cpu_var(var)
-
-#ifdef CONFIG_X86_64_SMP
-# define init_per_cpu_var(var)  init_per_cpu__##var
-#else
-# define init_per_cpu_var(var)  var
-#endif
-
-/*
  * For arch-specific code, we can use direct single-insn ops (they
  * don't give an lvalue though).
  */
@@ -128,15 +102,10 @@
 #define __pcpu_cast_4(val)	((u32)(((unsigned long) val) & 0xffffffff))
 #define __pcpu_cast_8(val)	((u64)(val))
 
-#define __pcpu_op1_1(op, dst)	op "b " dst
-#define __pcpu_op1_2(op, dst)	op "w " dst
-#define __pcpu_op1_4(op, dst)	op "l " dst
-#define __pcpu_op1_8(op, dst)	op "q " dst
-
-#define __pcpu_op2_1(op, src, dst) op "b " src ", " dst
-#define __pcpu_op2_2(op, src, dst) op "w " src ", " dst
-#define __pcpu_op2_4(op, src, dst) op "l " src ", " dst
-#define __pcpu_op2_8(op, src, dst) op "q " src ", " dst
+#define __pcpu_op_1(op)		op "b "
+#define __pcpu_op_2(op)		op "w "
+#define __pcpu_op_4(op)		op "l "
+#define __pcpu_op_8(op)		op "q "
 
 #define __pcpu_reg_1(mod, x)	mod "q" (x)
 #define __pcpu_reg_2(mod, x)	mod "r" (x)
@@ -168,7 +137,8 @@ do {									\
 ({									\
 	__pcpu_type_##size pfo_val__;					\
 									\
-	asm qual (__pcpu_op2_##size("mov", __percpu_arg([var]), "%[val]") \
+	asm qual (__pcpu_op_##size("mov")				\
+		  __percpu_arg([var]) ", %[val]"			\
 	    : [val] __pcpu_reg_##size("=", pfo_val__)			\
 	    : [var] "m" (__my_cpu_var(_var)));				\
 									\
@@ -184,7 +154,8 @@ do {									\
 		pto_tmp__ = (_val);					\
 		(void)pto_tmp__;					\
 	}								\
-	asm qual(__pcpu_op2_##size("mov", "%[val]", __percpu_arg([var])) \
+	asm qual (__pcpu_op_##size("mov") "%[val], "			\
+		  __percpu_arg([var])					\
 	    : [var] "=m" (__my_cpu_var(_var))				\
 	    : [val] __pcpu_reg_imm_##size(pto_val__));			\
 } while (0)
@@ -201,7 +172,8 @@ do {									\
 ({									\
 	__pcpu_type_##size pfo_val__;					\
 									\
-	asm(__pcpu_op2_##size("mov", __force_percpu_arg(a[var]), "%[val]") \
+	asm(__pcpu_op_##size("mov")					\
+	    __force_percpu_arg(a[var]) ", %[val]"			\
 	    : [val] __pcpu_reg_##size("=", pfo_val__)			\
 	    : [var] "i" (&(_var)));					\
 									\
@@ -210,7 +182,7 @@ do {									\
 
 #define percpu_unary_op(size, qual, op, _var)				\
 ({									\
-	asm qual (__pcpu_op1_##size(op, __percpu_arg([var]))		\
+	asm qual (__pcpu_op_##size(op) __percpu_arg([var])		\
 	    : [var] "+m" (__my_cpu_var(_var)));				\
 })
 
@@ -223,7 +195,7 @@ do {									\
 		pto_tmp__ = (_val);					\
 		(void)pto_tmp__;					\
 	}								\
-	asm qual(__pcpu_op2_##size(op, "%[val]", __percpu_arg([var]))	\
+	asm qual (__pcpu_op_##size(op) "%[val], " __percpu_arg([var])	\
 	    : [var] "+m" (__my_cpu_var(_var))				\
 	    : [val] __pcpu_reg_imm_##size(pto_val__));			\
 } while (0)
@@ -259,8 +231,8 @@ do {									\
 ({									\
 	__pcpu_type_##size paro_tmp__ = __pcpu_cast_##size(_val);	\
 									\
-	asm qual (__pcpu_op2_##size("xadd", "%[tmp]",			\
-				     __percpu_arg([var]))		\
+	asm qual (__pcpu_op_##size("xadd") "%[tmp], "			\
+		  __percpu_arg([var])					\
 		  : [tmp] __pcpu_reg_##size("+", paro_tmp__),		\
 		    [var] "+m" (__my_cpu_var(_var))			\
 		  : : "memory");					\
@@ -303,8 +275,8 @@ do {									\
 	__pcpu_type_##size pco_old__ = __pcpu_cast_##size(_oval);	\
 	__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval);	\
 									\
-	asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]",		\
-				    __percpu_arg([var]))		\
+	asm qual (__pcpu_op_##size("cmpxchg") "%[nval], "		\
+		  __percpu_arg([var])					\
 		  : [oval] "+a" (pco_old__),				\
 		    [var] "+m" (__my_cpu_var(_var))			\
 		  : [nval] __pcpu_reg_##size(, pco_new__)		\
@@ -320,8 +292,8 @@ do {									\
 	__pcpu_type_##size pco_old__ = *pco_oval__;			\
 	__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval);	\
 									\
-	asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]",		\
-				    __percpu_arg([var]))		\
+	asm qual (__pcpu_op_##size("cmpxchg") "%[nval], "		\
+		  __percpu_arg([var])					\
 		  CC_SET(z)						\
 		  : CC_OUT(z) (success),				\
 		    [oval] "+a" (pco_old__),				\
@@ -348,15 +320,14 @@ do {									\
 	old__.var = _oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
-			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
-		  : [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
+			    "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
+		: ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 									\
 	old__.var;							\
 })
@@ -378,17 +349,16 @@ do {									\
 	old__.var = *_oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
-			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
-		  CC_SET(z)						\
-		  : CC_OUT(z) (success),				\
-		    [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
+			    "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
+		CC_SET(z)						\
+		: ALT_OUTPUT_SP(CC_OUT(z) (success),			\
+				[var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 	if (unlikely(!success))						\
 		*_oval = old__.var;					\
 									\
@@ -419,15 +389,14 @@ do {									\
 	old__.var = _oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
-			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
-		  : [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
+			    "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
+		: ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 									\
 	old__.var;							\
 })
@@ -449,19 +418,19 @@ do {									\
 	old__.var = *_oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
-			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
-		  CC_SET(z)						\
-		  : CC_OUT(z) (success),				\
-		    [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
-		  : "b" (new__.low),					\
-		    "c" (new__.high),					\
-		    "S" (&(_var))					\
-		  : "memory");						\
+	asm_inline qual (						\
+		ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
+			    "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
+		CC_SET(z)						\
+		: ALT_OUTPUT_SP(CC_OUT(z) (success),			\
+				[var] "+m" (__my_cpu_var(_var)),	\
+				"+a" (old__.low), "+d" (old__.high))	\
+		: "b" (new__.low), "c" (new__.high),			\
+		  "S" (&(_var))						\
+		: "memory");						\
 	if (unlikely(!success))						\
 		*_oval = old__.var;					\
+									\
 	likely(success);						\
 })
 
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index dd4841231bb9..a33147520044 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -29,11 +29,6 @@ static inline void paravirt_release_pud(unsigned long pfn) {}
 static inline void paravirt_release_p4d(unsigned long pfn) {}
 #endif
 
-/*
- * Flags to use when allocating a user page table page.
- */
-extern gfp_t __userpte_alloc_gfp;
-
 #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 /*
  * Instead of one PGD, we acquire two PGDs.  Being order-1, it is
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 0c911083fdd1..c241dbc1562c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -60,18 +60,13 @@ struct vm86;
 # define ARCH_MIN_MMSTRUCT_ALIGN	0
 #endif
 
-enum tlb_infos {
-	ENTRIES,
-	NR_INFO
-};
-
-extern u16 __read_mostly tlb_lli_4k[NR_INFO];
-extern u16 __read_mostly tlb_lli_2m[NR_INFO];
-extern u16 __read_mostly tlb_lli_4m[NR_INFO];
-extern u16 __read_mostly tlb_lld_4k[NR_INFO];
-extern u16 __read_mostly tlb_lld_2m[NR_INFO];
-extern u16 __read_mostly tlb_lld_4m[NR_INFO];
-extern u16 __read_mostly tlb_lld_1g[NR_INFO];
+extern u16 __read_mostly tlb_lli_4k;
+extern u16 __read_mostly tlb_lli_2m;
+extern u16 __read_mostly tlb_lli_4m;
+extern u16 __read_mostly tlb_lld_4k;
+extern u16 __read_mostly tlb_lld_2m;
+extern u16 __read_mostly tlb_lld_4m;
+extern u16 __read_mostly tlb_lld_1g;
 
 /*
  * CPU type and hardware bug flags. Kept separately for each CPU.
@@ -234,7 +229,7 @@ static inline unsigned long long l1tf_pfn_limit(void)
 void init_cpu_devs(void);
 void get_cpu_vendor(struct cpuinfo_x86 *c);
 extern void early_cpu_init(void);
-extern void identify_secondary_cpu(struct cpuinfo_x86 *);
+extern void identify_secondary_cpu(unsigned int cpu);
 extern void print_cpu_info(struct cpuinfo_x86 *);
 void print_cpu_msr(struct cpuinfo_x86 *);
 
@@ -421,36 +416,20 @@ struct irq_stack {
 } __aligned(IRQ_STACK_SIZE);
 
 #ifdef CONFIG_X86_64
-struct fixed_percpu_data {
-	/*
-	 * GCC hardcodes the stack canary as %gs:40.  Since the
-	 * irq_stack is the object at %gs:0, we reserve the bottom
-	 * 48 bytes of the irq stack for the canary.
-	 *
-	 * Once we are willing to require -mstack-protector-guard-symbol=
-	 * support for x86_64 stackprotector, we can get rid of this.
-	 */
-	char		gs_base[40];
-	unsigned long	stack_canary;
-};
-
-DECLARE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible;
-DECLARE_INIT_PER_CPU(fixed_percpu_data);
-
 static inline unsigned long cpu_kernelmode_gs_base(int cpu)
 {
-	return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu);
+#ifdef CONFIG_SMP
+	return per_cpu_offset(cpu);
+#else
+	return 0;
+#endif
 }
 
 extern asmlinkage void entry_SYSCALL32_ignore(void);
 
 /* Save actual FS/GS selectors and bases to current->thread */
 void current_save_fsgs(void);
-#else	/* X86_64 */
-#ifdef CONFIG_STACKPROTECTOR
-DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
-#endif
-#endif	/* !X86_64 */
+#endif	/* X86_64 */
 
 struct perf_event;
 
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index e9187ddd3d1f..0068133cb622 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -23,7 +23,7 @@
 # define NEED_PAE	0
 #endif
 
-#ifdef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CX8
 # define NEED_CX8	(1<<(X86_FEATURE_CX8 & 31))
 #else
 # define NEED_CX8	0
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 2419e5086c9e..d6f50b91e4a5 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -114,13 +114,12 @@ void wbinvd_on_cpu(int cpu);
 int wbinvd_on_all_cpus(void);
 
 void smp_kick_mwait_play_dead(void);
+void __noreturn mwait_play_dead(unsigned int eax_hint);
 
 void native_smp_send_reschedule(int cpu);
 void native_send_call_func_ipi(const struct cpumask *mask);
 void native_send_call_func_single_ipi(int cpu);
 
-void smp_store_cpu_info(int id);
-
 asmlinkage __visible void smp_reboot_interrupt(void);
 __visible void smp_reschedule_interrupt(struct pt_regs *regs);
 __visible void smp_call_function_interrupt(struct pt_regs *regs);
@@ -158,6 +157,8 @@ static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 {
 	return (struct cpumask *)cpumask_of(0);
 }
+
+static inline void __noreturn mwait_play_dead(unsigned int eax_hint) { BUG(); }
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_DEBUG_NMI_SELFTEST
diff --git a/arch/x86/include/asm/sta2x11.h b/arch/x86/include/asm/sta2x11.h
deleted file mode 100644
index e0975e9c4f47..000000000000
--- a/arch/x86/include/asm/sta2x11.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Header file for STMicroelectronics ConneXt (STA2X11) IOHub
- */
-#ifndef __ASM_STA2X11_H
-#define __ASM_STA2X11_H
-
-#include <linux/pci.h>
-
-/* This needs to be called from the MFD to configure its sub-devices */
-struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev);
-
-#endif /* __ASM_STA2X11_H */
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 00473a650f51..d43fb589fcf6 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -2,26 +2,10 @@
 /*
  * GCC stack protector support.
  *
- * Stack protector works by putting predefined pattern at the start of
+ * Stack protector works by putting a predefined pattern at the start of
  * the stack frame and verifying that it hasn't been overwritten when
- * returning from the function.  The pattern is called stack canary
- * and unfortunately gcc historically required it to be at a fixed offset
- * from the percpu segment base.  On x86_64, the offset is 40 bytes.
- *
- * The same segment is shared by percpu area and stack canary.  On
- * x86_64, percpu symbols are zero based and %gs (64-bit) points to the
- * base of percpu area.  The first occupant of the percpu area is always
- * fixed_percpu_data which contains stack_canary at the appropriate
- * offset.  On x86_32, the stack canary is just a regular percpu
- * variable.
- *
- * Putting percpu data in %fs on 32-bit is a minor optimization compared to
- * using %gs.  Since 32-bit userspace normally has %fs == 0, we are likely
- * to load 0 into %fs on exit to usermode, whereas with percpu data in
- * %gs, we are likely to load a non-null %gs on return to user mode.
- *
- * Once we are willing to require GCC 8.1 or better for 64-bit stackprotector
- * support, we can remove some of this complexity.
+ * returning from the function.  The pattern is called the stack canary
+ * and is a unique value for each task.
  */
 
 #ifndef _ASM_STACKPROTECTOR_H
@@ -36,6 +20,8 @@
 
 #include <linux/sched.h>
 
+DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
+
 /*
  * Initialize the stackprotector canary value.
  *
@@ -51,25 +37,13 @@ static __always_inline void boot_init_stack_canary(void)
 {
 	unsigned long canary = get_random_canary();
 
-#ifdef CONFIG_X86_64
-	BUILD_BUG_ON(offsetof(struct fixed_percpu_data, stack_canary) != 40);
-#endif
-
 	current->stack_canary = canary;
-#ifdef CONFIG_X86_64
-	this_cpu_write(fixed_percpu_data.stack_canary, canary);
-#else
 	this_cpu_write(__stack_chk_guard, canary);
-#endif
 }
 
 static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle)
 {
-#ifdef CONFIG_X86_64
-	per_cpu(fixed_percpu_data.stack_canary, cpu) = idle->stack_canary;
-#else
 	per_cpu(__stack_chk_guard, cpu) = idle->stack_canary;
-#endif
 }
 
 #else	/* STACKPROTECTOR */
diff --git a/arch/x86/include/asm/vermagic.h b/arch/x86/include/asm/vermagic.h
index 75884d2cdec3..5d471253c755 100644
--- a/arch/x86/include/asm/vermagic.h
+++ b/arch/x86/include/asm/vermagic.h
@@ -15,8 +15,6 @@
 #define MODULE_PROC_FAMILY "586TSC "
 #elif defined CONFIG_M586MMX
 #define MODULE_PROC_FAMILY "586MMX "
-#elif defined CONFIG_MCORE2
-#define MODULE_PROC_FAMILY "CORE2 "
 #elif defined CONFIG_MATOM
 #define MODULE_PROC_FAMILY "ATOM "
 #elif defined CONFIG_M686
@@ -33,8 +31,6 @@
 #define MODULE_PROC_FAMILY "K6 "
 #elif defined CONFIG_MK7
 #define MODULE_PROC_FAMILY "K7 "
-#elif defined CONFIG_MK8
-#define MODULE_PROC_FAMILY "K8 "
 #elif defined CONFIG_MELAN
 #define MODULE_PROC_FAMILY "ELAN "
 #elif defined CONFIG_MCRUSOE