Merge tag 'x86_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 core updates from Borislav Petkov:

 - Get rid of all the .fixup sections because this generates
   misleading/wrong stacktraces and confuse RELIABLE_STACKTRACE and
   LIVEPATCH as the backtrace misses the function which is being fixed
   up.

 - Add Straight Line Speculation mitigation support which uses a new
   compiler switch -mharden-sls= which sticks an INT3 after a RET or an
   indirect branch in order to block speculation after them. Reportedly,
   CPUs do speculate behind such insns.

 - The usual set of cleanups and improvements

* tag 'x86_core_for_v5.17_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
  x86/entry_32: Fix segment exceptions
  objtool: Remove .fixup handling
  x86: Remove .fixup section
  x86/word-at-a-time: Remove .fixup usage
  x86/usercopy: Remove .fixup usage
  x86/usercopy_32: Simplify __copy_user_intel_nocache()
  x86/sgx: Remove .fixup usage
  x86/checksum_32: Remove .fixup usage
  x86/vmx: Remove .fixup usage
  x86/kvm: Remove .fixup usage
  x86/segment: Remove .fixup usage
  x86/fpu: Remove .fixup usage
  x86/xen: Remove .fixup usage
  x86/uaccess: Remove .fixup usage
  x86/futex: Remove .fixup usage
  x86/msr: Remove .fixup usage
  x86/extable: Extend extable functionality
  x86/entry_32: Remove .fixup usage
  x86/entry_64: Remove .fixup usage
  x86/copy_mc_64: Remove .fixup usage
  ...

19 files changed, 214 insertions, 178 deletions

diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 3a168483bc8e..c878fed3056f 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -152,6 +152,33 @@
 
 #else /* ! __ASSEMBLY__ */
 
+# define DEFINE_EXTABLE_TYPE_REG \
+	".macro extable_type_reg type:req reg:req\n"						\
+	".set found, 0\n"									\
+	".set regnr, 0\n"									\
+	".irp rs,rax,rcx,rdx,rbx,rsp,rbp,rsi,rdi,r8,r9,r10,r11,r12,r13,r14,r15\n"		\
+	".ifc \\reg, %%\\rs\n"									\
+	".set found, found+1\n"									\
+	".long \\type + (regnr << 8)\n"								\
+	".endif\n"										\
+	".set regnr, regnr+1\n"									\
+	".endr\n"										\
+	".set regnr, 0\n"									\
+	".irp rs,eax,ecx,edx,ebx,esp,ebp,esi,edi,r8d,r9d,r10d,r11d,r12d,r13d,r14d,r15d\n"	\
+	".ifc \\reg, %%\\rs\n"									\
+	".set found, found+1\n"									\
+	".long \\type + (regnr << 8)\n"								\
+	".endif\n"										\
+	".set regnr, regnr+1\n"									\
+	".endr\n"										\
+	".if (found != 1)\n"									\
+	".error \"extable_type_reg: bad register argument\"\n"					\
+	".endif\n"										\
+	".endm\n"
+
+# define UNDEFINE_EXTABLE_TYPE_REG \
+	".purgem extable_type_reg\n"
+
 # define _ASM_EXTABLE_TYPE(from, to, type)			\
 	" .pushsection \"__ex_table\",\"a\"\n"			\
 	" .balign 4\n"						\
@@ -160,6 +187,16 @@
 	" .long " __stringify(type) " \n"			\
 	" .popsection\n"
 
+# define _ASM_EXTABLE_TYPE_REG(from, to, type, reg)				\
+	" .pushsection \"__ex_table\",\"a\"\n"					\
+	" .balign 4\n"								\
+	" .long (" #from ") - .\n"						\
+	" .long (" #to ") - .\n"						\
+	DEFINE_EXTABLE_TYPE_REG							\
+	"extable_type_reg reg=" __stringify(reg) ", type=" __stringify(type) " \n"\
+	UNDEFINE_EXTABLE_TYPE_REG						\
+	" .popsection\n"
+
 /* For C file, we already have NOKPROBE_SYMBOL macro */
 
 /*
diff --git a/arch/x86/include/asm/extable.h b/arch/x86/include/asm/extable.h
index 93f400eb728f..155c991ba95e 100644
--- a/arch/x86/include/asm/extable.h
+++ b/arch/x86/include/asm/extable.h
@@ -21,7 +21,7 @@
  */
 
 struct exception_table_entry {
-	int insn, fixup, type;
+	int insn, fixup, data;
 };
 struct pt_regs;
 
@@ -31,8 +31,8 @@ struct pt_regs;
 	do {							\
 		(a)->fixup = (b)->fixup + (delta);		\
 		(b)->fixup = (tmp).fixup - (delta);		\
-		(a)->type = (b)->type;				\
-		(b)->type = (tmp).type;				\
+		(a)->data = (b)->data;				\
+		(b)->data = (tmp).data;				\
 	} while (0)
 
 extern int fixup_exception(struct pt_regs *regs, int trapnr,
diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h
index 409524d5d2eb..503622627400 100644
--- a/arch/x86/include/asm/extable_fixup_types.h
+++ b/arch/x86/include/asm/extable_fixup_types.h
@@ -2,6 +2,36 @@
 #ifndef _ASM_X86_EXTABLE_FIXUP_TYPES_H
 #define _ASM_X86_EXTABLE_FIXUP_TYPES_H
 
+/*
+ * Our IMM is signed, as such it must live at the top end of the word. Also,
+ * since C99 hex constants are of ambigious type, force cast the mask to 'int'
+ * so that FIELD_GET() will DTRT and sign extend the value when it extracts it.
+ */
+#define EX_DATA_TYPE_MASK		((int)0x000000FF)
+#define EX_DATA_REG_MASK		((int)0x00000F00)
+#define EX_DATA_FLAG_MASK		((int)0x0000F000)
+#define EX_DATA_IMM_MASK		((int)0xFFFF0000)
+
+#define EX_DATA_REG_SHIFT		8
+#define EX_DATA_FLAG_SHIFT		12
+#define EX_DATA_IMM_SHIFT		16
+
+#define EX_DATA_REG(reg)		((reg) << EX_DATA_REG_SHIFT)
+#define EX_DATA_FLAG(flag)		((flag) << EX_DATA_FLAG_SHIFT)
+#define EX_DATA_IMM(imm)		((imm) << EX_DATA_IMM_SHIFT)
+
+/* segment regs */
+#define EX_REG_DS			EX_DATA_REG(8)
+#define EX_REG_ES			EX_DATA_REG(9)
+#define EX_REG_FS			EX_DATA_REG(10)
+#define EX_REG_GS			EX_DATA_REG(11)
+
+/* flags */
+#define EX_FLAG_CLEAR_AX		EX_DATA_FLAG(1)
+#define EX_FLAG_CLEAR_DX		EX_DATA_FLAG(2)
+#define EX_FLAG_CLEAR_AX_DX		EX_DATA_FLAG(3)
+
+/* types */
 #define	EX_TYPE_NONE			 0
 #define	EX_TYPE_DEFAULT			 1
 #define	EX_TYPE_FAULT			 2
@@ -9,14 +39,29 @@
 #define	EX_TYPE_COPY			 4
 #define	EX_TYPE_CLEAR_FS		 5
 #define	EX_TYPE_FPU_RESTORE		 6
-#define	EX_TYPE_WRMSR			 7
-#define	EX_TYPE_RDMSR			 8
-#define	EX_TYPE_BPF			 9
+#define	EX_TYPE_BPF			 7
+#define	EX_TYPE_WRMSR			 8
+#define	EX_TYPE_RDMSR			 9
+#define	EX_TYPE_WRMSR_SAFE		10 /* reg := -EIO */
+#define	EX_TYPE_RDMSR_SAFE		11 /* reg := -EIO */
+#define	EX_TYPE_WRMSR_IN_MCE		12
+#define	EX_TYPE_RDMSR_IN_MCE		13
+#define	EX_TYPE_DEFAULT_MCE_SAFE	14
+#define	EX_TYPE_FAULT_MCE_SAFE		15
+
+#define	EX_TYPE_POP_REG			16 /* sp += sizeof(long) */
+#define EX_TYPE_POP_ZERO		(EX_TYPE_POP_REG | EX_DATA_IMM(0))
+
+#define	EX_TYPE_IMM_REG			17 /* reg := (long)imm */
+#define	EX_TYPE_EFAULT_REG		(EX_TYPE_IMM_REG | EX_DATA_IMM(-EFAULT))
+#define	EX_TYPE_ZERO_REG		(EX_TYPE_IMM_REG | EX_DATA_IMM(0))
+#define	EX_TYPE_ONE_REG			(EX_TYPE_IMM_REG | EX_DATA_IMM(1))
 
-#define	EX_TYPE_WRMSR_IN_MCE		10
-#define	EX_TYPE_RDMSR_IN_MCE		11
+#define	EX_TYPE_FAULT_SGX		18
 
-#define	EX_TYPE_DEFAULT_MCE_SAFE	12
-#define	EX_TYPE_FAULT_MCE_SAFE		13
+#define	EX_TYPE_UCOPY_LEN		19 /* cx := reg + imm*cx */
+#define	EX_TYPE_UCOPY_LEN1		(EX_TYPE_UCOPY_LEN | EX_DATA_IMM(1))
+#define	EX_TYPE_UCOPY_LEN4		(EX_TYPE_UCOPY_LEN | EX_DATA_IMM(4))
+#define	EX_TYPE_UCOPY_LEN8		(EX_TYPE_UCOPY_LEN | EX_DATA_IMM(8))
 
 #endif
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index f9c00110a69a..99d345b686fa 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -17,13 +17,9 @@ do {								\
 	int oldval = 0, ret;					\
 	asm volatile("1:\t" insn "\n"				\
 		     "2:\n"					\
-		     "\t.section .fixup,\"ax\"\n"		\
-		     "3:\tmov\t%3, %1\n"			\
-		     "\tjmp\t2b\n"				\
-		     "\t.previous\n"				\
-		     _ASM_EXTABLE_UA(1b, 3b)			\
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %1) \
 		     : "=r" (oldval), "=r" (ret), "+m" (*uaddr)	\
-		     : "i" (-EFAULT), "0" (oparg), "1" (0));	\
+		     : "0" (oparg), "1" (0));	\
 	if (ret)						\
 		goto label;					\
 	*oval = oldval;						\
@@ -39,15 +35,11 @@ do {								\
 		     "3:\t" LOCK_PREFIX "cmpxchgl %3, %2\n"	\
 		     "\tjnz\t2b\n"				\
 		     "4:\n"					\
-		     "\t.section .fixup,\"ax\"\n"		\
-		     "5:\tmov\t%5, %1\n"			\
-		     "\tjmp\t4b\n"				\
-		     "\t.previous\n"				\
-		     _ASM_EXTABLE_UA(1b, 5b)			\
-		     _ASM_EXTABLE_UA(3b, 5b)			\
+		     _ASM_EXTABLE_TYPE_REG(1b, 4b, EX_TYPE_EFAULT_REG, %1) \
+		     _ASM_EXTABLE_TYPE_REG(3b, 4b, EX_TYPE_EFAULT_REG, %1) \
 		     : "=&a" (oldval), "=&r" (ret),		\
 		       "+m" (*uaddr), "=&r" (tem)		\
-		     : "r" (oparg), "i" (-EFAULT), "1" (0));	\
+		     : "r" (oparg), "1" (0));			\
 	if (ret)						\
 		goto label;					\
 	*oval = oldval;						\
@@ -95,15 +87,11 @@ static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!user_access_begin(uaddr, sizeof(u32)))
 		return -EFAULT;
 	asm volatile("\n"
-		"1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n"
+		"1:\t" LOCK_PREFIX "cmpxchgl %3, %2\n"
 		"2:\n"
-		"\t.section .fixup, \"ax\"\n"
-		"3:\tmov     %3, %0\n"
-		"\tjmp     2b\n"
-		"\t.previous\n"
-		_ASM_EXTABLE_UA(1b, 3b)
+		_ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %0) \
 		: "+r" (ret), "=a" (oldval), "+m" (*uaddr)
-		: "i" (-EFAULT), "r" (newval), "1" (oldval)
+		: "r" (newval), "1" (oldval)
 		: "memory"
 	);
 	user_access_end();
diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h
index 43785ee363f1..f07faa61c7f3 100644
--- a/arch/x86/include/asm/insn-eval.h
+++ b/arch/x86/include/asm/insn-eval.h
@@ -15,6 +15,8 @@
 #define INSN_CODE_SEG_OPND_SZ(params) (params & 0xf)
 #define INSN_CODE_SEG_PARAMS(oper_sz, addr_sz) (oper_sz | (addr_sz << 4))
 
+int pt_regs_offset(struct pt_regs *regs, int regno);
+
 bool insn_has_rep_prefix(struct insn *insn);
 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);
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 365111789cc6..030907922bd0 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -18,6 +18,20 @@
 #define __ALIGN_STR	__stringify(__ALIGN)
 #endif
 
+#ifdef CONFIG_SLS
+#define RET	ret; int3
+#else
+#define RET	ret
+#endif
+
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_SLS
+#define ASM_RET	"ret; int3\n\t"
+#else
+#define ASM_RET	"ret\n\t"
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_LINKAGE_H */
diff --git a/arch/x86/include/asm/mmx.h b/arch/x86/include/asm/mmx.h
index f572d0f944bb..e69de29bb2d1 100644
--- a/arch/x86/include/asm/mmx.h
+++ b/arch/x86/include/asm/mmx.h
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_MMX_H
-#define _ASM_X86_MMX_H
-
-/*
- *	MMX 3Dnow! helper operations
- */
-
-#include <linux/types.h>
-
-extern void *_mmx_memcpy(void *to, const void *from, size_t size);
-extern void mmx_clear_page(void *page);
-extern void mmx_copy_page(void *to, void *from);
-
-#endif /* _ASM_X86_MMX_H */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 6b52182e178a..d42e6c6b47b1 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -137,17 +137,11 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
 {
 	DECLARE_ARGS(val, low, high);
 
-	asm volatile("2: rdmsr ; xor %[err],%[err]\n"
-		     "1:\n\t"
-		     ".section .fixup,\"ax\"\n\t"
-		     "3: mov %[fault],%[err]\n\t"
-		     "xorl %%eax, %%eax\n\t"
-		     "xorl %%edx, %%edx\n\t"
-		     "jmp 1b\n\t"
-		     ".previous\n\t"
-		     _ASM_EXTABLE(2b, 3b)
+	asm volatile("1: rdmsr ; xor %[err],%[err]\n"
+		     "2:\n\t"
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_RDMSR_SAFE, %[err])
 		     : [err] "=r" (*err), EAX_EDX_RET(val, low, high)
-		     : "c" (msr), [fault] "i" (-EIO));
+		     : "c" (msr));
 	if (tracepoint_enabled(read_msr))
 		do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err);
 	return EAX_EDX_VAL(val, low, high);
@@ -169,15 +163,11 @@ native_write_msr_safe(unsigned int msr, u32 low, u32 high)
 {
 	int err;
 
-	asm volatile("2: wrmsr ; xor %[err],%[err]\n"
-		     "1:\n\t"
-		     ".section .fixup,\"ax\"\n\t"
-		     "3:  mov %[fault],%[err] ; jmp 1b\n\t"
-		     ".previous\n\t"
-		     _ASM_EXTABLE(2b, 3b)
+	asm volatile("1: wrmsr ; xor %[err],%[err]\n"
+		     "2:\n\t"
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_WRMSR_SAFE, %[err])
 		     : [err] "=a" (err)
-		     : "c" (msr), "0" (low), "d" (high),
-		       [fault] "i" (-EIO)
+		     : "c" (msr), "0" (low), "d" (high)
 		     : "memory");
 	if (tracepoint_enabled(write_msr))
 		do_trace_write_msr(msr, ((u64)high << 32 | low), err);
diff --git a/arch/x86/include/asm/page_32.h b/arch/x86/include/asm/page_32.h
index b13f8488ac85..df42f8aa99e4 100644
--- a/arch/x86/include/asm/page_32.h
+++ b/arch/x86/include/asm/page_32.h
@@ -19,19 +19,6 @@ extern unsigned long __phys_addr(unsigned long);
 #define pfn_valid(pfn)		((pfn) < max_mapnr)
 #endif /* CONFIG_FLATMEM */
 
-#ifdef CONFIG_X86_USE_3DNOW
-#include <asm/mmx.h>
-
-static inline void clear_page(void *page)
-{
-	mmx_clear_page(page);
-}
-
-static inline void copy_page(void *to, void *from)
-{
-	mmx_copy_page(to, from);
-}
-#else  /* !CONFIG_X86_USE_3DNOW */
 #include <linux/string.h>
 
 static inline void clear_page(void *page)
@@ -43,7 +30,6 @@ static inline void copy_page(void *to, void *from)
 {
 	memcpy(to, from, PAGE_SIZE);
 }
-#endif	/* CONFIG_X86_USE_3DNOW */
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_PAGE_32_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 27d276232c80..0d76502cc6f5 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -671,7 +671,7 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu);
 	    "call " #func ";"						\
 	    PV_RESTORE_ALL_CALLER_REGS					\
 	    FRAME_END							\
-	    "ret;"							\
+	    ASM_RET							\
 	    ".size " PV_THUNK_NAME(func) ", .-" PV_THUNK_NAME(func) ";"	\
 	    ".popsection")
 
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index 159622ee0674..1474cf96251d 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -48,7 +48,7 @@ asm    (".pushsection .text;"
 	"jne   .slowpath;"
 	"pop   %rdx;"
 	FRAME_END
-	"ret;"
+	ASM_RET
 	".slowpath: "
 	"push   %rsi;"
 	"movzbl %al,%esi;"
@@ -56,7 +56,7 @@ asm    (".pushsection .text;"
 	"pop    %rsi;"
 	"pop    %rdx;"
 	FRAME_END
-	"ret;"
+	ASM_RET
 	".size " PV_UNLOCK ", .-" PV_UNLOCK ";"
 	".popsection");
 
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index b2d504f11937..aff774775c67 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -35,11 +35,7 @@
 # define NEED_CMOV	0
 #endif
 
-#ifdef CONFIG_X86_USE_3DNOW
-# define NEED_3DNOW	(1<<(X86_FEATURE_3DNOW & 31))
-#else
 # define NEED_3DNOW	0
-#endif
 
 #if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64)
 # define NEED_NOPL	(1<<(X86_FEATURE_NOPL & 31))
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 8dd8e8ec9fa5..b228c9d44ee7 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -307,14 +307,7 @@ do {									\
 									\
 	asm volatile("						\n"	\
 		     "1:	movl %k0,%%" #seg "		\n"	\
-									\
-		     ".section .fixup,\"ax\"			\n"	\
-		     "2:	xorl %k0,%k0			\n"	\
-		     "		jmp 1b				\n"	\
-		     ".previous					\n"	\
-									\
-		     _ASM_EXTABLE(1b, 2b)				\
-									\
+		     _ASM_EXTABLE_TYPE_REG(1b, 1b, EX_TYPE_ZERO_REG, %k0)\
 		     : "+r" (__val) : : "memory");			\
 } while (0)
 
diff --git a/arch/x86/include/asm/sgx.h b/arch/x86/include/asm/sgx.h
index 05f3e21f01a7..3f9334ef67cd 100644
--- a/arch/x86/include/asm/sgx.h
+++ b/arch/x86/include/asm/sgx.h
@@ -46,6 +46,24 @@ enum sgx_encls_function {
 };
 
 /**
+ * SGX_ENCLS_FAULT_FLAG - flag signifying an ENCLS return code is a trapnr
+ *
+ * ENCLS has its own (positive value) error codes and also generates
+ * ENCLS specific #GP and #PF faults.  And the ENCLS values get munged
+ * with system error codes as everything percolates back up the stack.
+ * Unfortunately (for us), we need to precisely identify each unique
+ * error code, e.g. the action taken if EWB fails varies based on the
+ * type of fault and on the exact SGX error code, i.e. we can't simply
+ * convert all faults to -EFAULT.
+ *
+ * To make all three error types coexist, we set bit 30 to identify an
+ * ENCLS fault.  Bit 31 (technically bits N:31) is used to differentiate
+ * between positive (faults and SGX error codes) and negative (system
+ * error codes) values.
+ */
+#define SGX_ENCLS_FAULT_FLAG 0x40000000
+
+/**
  * enum sgx_return_code - The return code type for ENCLS, ENCLU and ENCLV
  * %SGX_NOT_TRACKED:		Previous ETRACK's shootdown sequence has not
  *				been completed yet.
diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h
index 39ebe0511869..ed4f8bb6c2d9 100644
--- a/arch/x86/include/asm/static_call.h
+++ b/arch/x86/include/asm/static_call.h
@@ -36,7 +36,7 @@
 	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)")
 
 #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)			\
-	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; nop; nop; nop; nop")
+	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop")
 
 
 #define ARCH_ADD_TRAMP_KEY(name)					\
diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h
index f74362b05619..32c0d981a82a 100644
--- a/arch/x86/include/asm/string_32.h
+++ b/arch/x86/include/asm/string_32.h
@@ -146,42 +146,9 @@ static __always_inline void *__constant_memcpy(void *to, const void *from,
 extern void *memcpy(void *, const void *, size_t);
 
 #ifndef CONFIG_FORTIFY_SOURCE
-#ifdef CONFIG_X86_USE_3DNOW
-
-#include <asm/mmx.h>
-
-/*
- *	This CPU favours 3DNow strongly (eg AMD Athlon)
- */
-
-static inline void *__constant_memcpy3d(void *to, const void *from, size_t len)
-{
-	if (len < 512)
-		return __constant_memcpy(to, from, len);
-	return _mmx_memcpy(to, from, len);
-}
-
-static inline void *__memcpy3d(void *to, const void *from, size_t len)
-{
-	if (len < 512)
-		return __memcpy(to, from, len);
-	return _mmx_memcpy(to, from, len);
-}
-
-#define memcpy(t, f, n)				\
-	(__builtin_constant_p((n))		\
-	 ? __constant_memcpy3d((t), (f), (n))	\
-	 : __memcpy3d((t), (f), (n)))
-
-#else
-
-/*
- *	No 3D Now!
- */
 
 #define memcpy(t, f, n) __builtin_memcpy(t, f, n)
 
-#endif
 #endif /* !CONFIG_FORTIFY_SOURCE */
 
 #define __HAVE_ARCH_MEMMOVE
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8ab9e79abb2b..ac96f9b2d64b 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -352,24 +352,22 @@ do {									\
 		     "1:	movl %[lowbits],%%eax\n"		\
 		     "2:	movl %[highbits],%%edx\n"		\
 		     "3:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "4:	mov %[efault],%[errout]\n"		\
-		     "	xorl %%eax,%%eax\n"				\
-		     "	xorl %%edx,%%edx\n"				\
-		     "	jmp 3b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE_UA(1b, 4b)				\
-		     _ASM_EXTABLE_UA(2b, 4b)				\
+		     _ASM_EXTABLE_TYPE_REG(1b, 3b, EX_TYPE_EFAULT_REG |	\
+					   EX_FLAG_CLEAR_AX_DX,		\
+					   %[errout])			\
+		     _ASM_EXTABLE_TYPE_REG(2b, 3b, EX_TYPE_EFAULT_REG |	\
+					   EX_FLAG_CLEAR_AX_DX,		\
+					   %[errout])			\
 		     : [errout] "=r" (retval),				\
 		       [output] "=&A"(x)				\
 		     : [lowbits] "m" (__m(__ptr)),			\
 		       [highbits] "m" __m(((u32 __user *)(__ptr)) + 1),	\
-		       [efault] "i" (-EFAULT), "0" (retval));		\
+		       "0" (retval));					\
 })
 
 #else
 #define __get_user_asm_u64(x, ptr, retval) \
-	 __get_user_asm(x, ptr, retval, "q", "=r")
+	 __get_user_asm(x, ptr, retval, "q")
 #endif
 
 #define __get_user_size(x, ptr, size, retval)				\
@@ -380,14 +378,14 @@ do {									\
 	__chk_user_ptr(ptr);						\
 	switch (size) {							\
 	case 1:								\
-		__get_user_asm(x_u8__, ptr, retval, "b", "=q");		\
+		__get_user_asm(x_u8__, ptr, retval, "b");		\
 		(x) = x_u8__;						\
 		break;							\
 	case 2:								\
-		__get_user_asm(x, ptr, retval, "w", "=r");		\
+		__get_user_asm(x, ptr, retval, "w");			\
 		break;							\
 	case 4:								\
-		__get_user_asm(x, ptr, retval, "l", "=r");		\
+		__get_user_asm(x, ptr, retval, "l");			\
 		break;							\
 	case 8:								\
 		__get_user_asm_u64(x, ptr, retval);			\
@@ -397,20 +395,17 @@ do {									\
 	}								\
 } while (0)
 
-#define __get_user_asm(x, addr, err, itype, ltype)			\
+#define __get_user_asm(x, addr, err, itype)				\
 	asm volatile("\n"						\
 		     "1:	mov"itype" %[umem],%[output]\n"		\
 		     "2:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "3:	mov %[efault],%[errout]\n"		\
-		     "	xorl %k[output],%k[output]\n"			\
-		     "	jmp 2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE_UA(1b, 3b)				\
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG | \
+					   EX_FLAG_CLEAR_AX,		\
+					   %[errout])			\
 		     : [errout] "=r" (err),				\
-		       [output] ltype(x)				\
+		       [output] "=a" (x)				\
 		     : [umem] "m" (__m(addr)),				\
-		       [efault] "i" (-EFAULT), "0" (err))
+		       "0" (err))
 
 #endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT
 
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
index 06006b0351f3..8338b0432b50 100644
--- a/arch/x86/include/asm/word-at-a-time.h
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -77,30 +77,58 @@ static inline unsigned long find_zero(unsigned long mask)
  * and the next page not being mapped, take the exception and
  * return zeroes in the non-existing part.
  */
+#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
+
 static inline unsigned long load_unaligned_zeropad(const void *addr)
 {
-	unsigned long ret, dummy;
+	unsigned long offset, data;
+	unsigned long ret;
+
+	asm_volatile_goto(
+		"1:	mov %[mem], %[ret]\n"
+
+		_ASM_EXTABLE(1b, %l[do_exception])
+
+		: [ret] "=r" (ret)
+		: [mem] "m" (*(unsigned long *)addr)
+		: : do_exception);
+
+	return ret;
+
+do_exception:
+	offset = (unsigned long)addr & (sizeof(long) - 1);
+	addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1));
+	data = *(unsigned long *)addr;
+	ret = data >> offset * 8;
+
+	return ret;
+}
 
-	asm(
-		"1:\tmov %2,%0\n"
+#else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
+
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+	unsigned long offset, data;
+	unsigned long ret, err = 0;
+
+	asm(	"1:	mov %[mem], %[ret]\n"
 		"2:\n"
-		".section .fixup,\"ax\"\n"
-		"3:\t"
-		"lea %2,%1\n\t"
-		"and %3,%1\n\t"
-		"mov (%1),%0\n\t"
-		"leal %2,%%ecx\n\t"
-		"andl %4,%%ecx\n\t"
-		"shll $3,%%ecx\n\t"
-		"shr %%cl,%0\n\t"
-		"jmp 2b\n"
-		".previous\n"
-		_ASM_EXTABLE(1b, 3b)
-		:"=&r" (ret),"=&c" (dummy)
-		:"m" (*(unsigned long *)addr),
-		 "i" (-sizeof(unsigned long)),
-		 "i" (sizeof(unsigned long)-1));
+
+		_ASM_EXTABLE_FAULT(1b, 2b)
+
+		: [ret] "=&r" (ret), "+a" (err)
+		: [mem] "m" (*(unsigned long *)addr));
+
+	if (unlikely(err)) {
+		offset = (unsigned long)addr & (sizeof(long) - 1);
+		addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1));
+		data = *(unsigned long *)addr;
+		ret = data >> offset * 8;
+	}
+
 	return ret;
 }
 
+#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
+
 #endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 1a162e559753..e989bc2269f5 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -96,11 +96,7 @@ static inline int xen_safe_write_ulong(unsigned long *addr, unsigned long val)
 
 	asm volatile("1: mov %[val], %[ptr]\n"
 		     "2:\n"
-		     ".section .fixup, \"ax\"\n"
-		     "3: sub $1, %[ret]\n"
-		     "   jmp 2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %[ret])
 		     : [ret] "+r" (ret), [ptr] "=m" (*addr)
 		     : [val] "r" (val));
 
@@ -110,16 +106,12 @@ static inline int xen_safe_write_ulong(unsigned long *addr, unsigned long val)
 static inline int xen_safe_read_ulong(const unsigned long *addr,
 				      unsigned long *val)
 {
-	int ret = 0;
 	unsigned long rval = ~0ul;
+	int ret = 0;
 
 	asm volatile("1: mov %[ptr], %[rval]\n"
 		     "2:\n"
-		     ".section .fixup, \"ax\"\n"
-		     "3: sub $1, %[ret]\n"
-		     "   jmp 2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %[ret])
 		     : [ret] "+r" (ret), [rval] "+r" (rval)
 		     : [ptr] "m" (*addr));
 	*val = rval;