Merge branch 'core-objtool-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull objtool updates from Ingo Molnar:
 "This is a series from Peter Zijlstra that adds x86 build-time uaccess
  validation of SMAP to objtool, which will detect and warn about the
  following uaccess API usage bugs and weirdnesses:

   - call to %s() with UACCESS enabled
   - return with UACCESS enabled
   - return with UACCESS disabled from a UACCESS-safe function
   - recursive UACCESS enable
   - redundant UACCESS disable
   - UACCESS-safe disables UACCESS

  As it turns out not leaking uaccess permissions outside the intended
  uaccess functionality is hard when the interfaces are complex and when
  such bugs are mostly dormant.

  As a bonus we now also check the DF flag. We had at least one
  high-profile bug in that area in the early days of Linux, and the
  checking is fairly simple. The checks performed and warnings emitted
  are:

   - call to %s() with DF set
   - return with DF set
   - return with modified stack frame
   - recursive STD
   - redundant CLD

  It's all x86-only for now, but later on this can also be used for PAN
  on ARM and objtool is fairly cross-platform in principle.

  While all warnings emitted by this new checking facility that got
  reported to us were fixed, there might be GCC version dependent
  warnings that were not reported yet - which we'll address, should they
  trigger.

  The warnings are non-fatal build warnings"

* 'core-objtool-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (27 commits)
  mm/uaccess: Use 'unsigned long' to placate UBSAN warnings on older GCC versions
  x86/uaccess: Dont leak the AC flag into __put_user() argument evaluation
  sched/x86_64: Don't save flags on context switch
  objtool: Add Direction Flag validation
  objtool: Add UACCESS validation
  objtool: Fix sibling call detection
  objtool: Rewrite alt->skip_orig
  objtool: Add --backtrace support
  objtool: Rewrite add_ignores()
  objtool: Handle function aliases
  objtool: Set insn->func for alternatives
  x86/uaccess, kcov: Disable stack protector
  x86/uaccess, ftrace: Fix ftrace_likely_update() vs. SMAP
  x86/uaccess, ubsan: Fix UBSAN vs. SMAP
  x86/uaccess, kasan: Fix KASAN vs SMAP
  x86/smap: Ditch __stringify()
  x86/uaccess: Introduce user_access_{save,restore}()
  x86/uaccess, signal: Fix AC=1 bloat
  x86/uaccess: Always inline user_access_begin()
  x86/uaccess, xen: Suppress SMAP warnings
  ...

17 files changed, 181 insertions, 108 deletions

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index d309f30cf7af..5fc76b755510 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -650,6 +650,7 @@ ENTRY(__switch_to_asm)
 	pushl	%ebx
 	pushl	%edi
 	pushl	%esi
+	pushfl
 
 	/* switch stack */
 	movl	%esp, TASK_threadsp(%eax)
@@ -672,6 +673,7 @@ ENTRY(__switch_to_asm)
 #endif
 
 	/* restore callee-saved registers */
+	popfl
 	popl	%esi
 	popl	%edi
 	popl	%ebx
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 321fe5f5d0e9..4d5fcd47ab75 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -61,9 +61,8 @@
 } while (0)
 
 #define RELOAD_SEG(seg)		{		\
-	unsigned int pre = GET_SEG(seg);	\
+	unsigned int pre = (seg) | 3;		\
 	unsigned int cur = get_user_seg(seg);	\
-	pre |= 3;				\
 	if (pre != cur)				\
 		set_user_seg(seg, pre);		\
 }
@@ -72,6 +71,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 				   struct sigcontext_32 __user *sc)
 {
 	unsigned int tmpflags, err = 0;
+	u16 gs, fs, es, ds;
 	void __user *buf;
 	u32 tmp;
 
@@ -79,16 +79,10 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 	current->restart_block.fn = do_no_restart_syscall;
 
 	get_user_try {
-		/*
-		 * Reload fs and gs if they have changed in the signal
-		 * handler.  This does not handle long fs/gs base changes in
-		 * the handler, but does not clobber them at least in the
-		 * normal case.
-		 */
-		RELOAD_SEG(gs);
-		RELOAD_SEG(fs);
-		RELOAD_SEG(ds);
-		RELOAD_SEG(es);
+		gs = GET_SEG(gs);
+		fs = GET_SEG(fs);
+		ds = GET_SEG(ds);
+		es = GET_SEG(es);
 
 		COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
 		COPY(dx); COPY(cx); COPY(ip); COPY(ax);
@@ -106,6 +100,17 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 		buf = compat_ptr(tmp);
 	} get_user_catch(err);
 
+	/*
+	 * Reload fs and gs if they have changed in the signal
+	 * handler.  This does not handle long fs/gs base changes in
+	 * the handler, but does not clobber them at least in the
+	 * normal case.
+	 */
+	RELOAD_SEG(gs);
+	RELOAD_SEG(fs);
+	RELOAD_SEG(ds);
+	RELOAD_SEG(es);
+
 	err |= fpu__restore_sig(buf, 1);
 
 	force_iret();
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index 31b627b43a8e..464034db299f 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -20,6 +20,17 @@
 #endif
 
 /*
+ * objtool annotation to ignore the alternatives and only consider the original
+ * instruction(s).
+ */
+.macro ANNOTATE_IGNORE_ALTERNATIVE
+	.Lannotate_\@:
+	.pushsection .discard.ignore_alts
+	.long .Lannotate_\@ - .
+	.popsection
+.endm
+
+/*
  * Issue one struct alt_instr descriptor entry (need to put it into
  * the section .altinstructions, see below). This entry contains
  * enough information for the alternatives patching code to patch an
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 4c74073a19cc..094fbc9c0b1c 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -45,6 +45,16 @@
 #define LOCK_PREFIX ""
 #endif
 
+/*
+ * objtool annotation to ignore the alternatives and only consider the original
+ * instruction(s).
+ */
+#define ANNOTATE_IGNORE_ALTERNATIVE				\
+	"999:\n\t"						\
+	".pushsection .discard.ignore_alts\n\t"			\
+	".long 999b - .\n\t"					\
+	".popsection\n\t"
+
 struct alt_instr {
 	s32 instr_offset;	/* original instruction */
 	s32 repl_offset;	/* offset to replacement instruction */
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 6467757bb39f..3ff577c0b102 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -148,30 +148,6 @@
 	_ASM_PTR (entry);					\
 	.popsection
 
-.macro ALIGN_DESTINATION
-	/* check for bad alignment of destination */
-	movl %edi,%ecx
-	andl $7,%ecx
-	jz 102f				/* already aligned */
-	subl $8,%ecx
-	negl %ecx
-	subl %ecx,%edx
-100:	movb (%rsi),%al
-101:	movb %al,(%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz 100b
-102:
-	.section .fixup,"ax"
-103:	addl %ecx,%edx			/* ecx is zerorest also */
-	jmp copy_user_handle_tail
-	.previous
-
-	_ASM_EXTABLE_UA(100b, 103b)
-	_ASM_EXTABLE_UA(101b, 103b)
-	.endm
-
 #else
 # define _EXPAND_EXTABLE_HANDLE(x) #x
 # define _ASM_EXTABLE_HANDLE(from, to, handler)			\
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index dad12b767ba0..daf25b60c9e3 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -11,6 +11,15 @@
 #include <asm/msr-index.h>
 
 /*
+ * 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.
+ */
+#define ANNOTATE_NOSPEC_ALTERNATIVE \
+	ANNOTATE_IGNORE_ALTERNATIVE
+
+/*
  * Fill the CPU return stack buffer.
  *
  * Each entry in the RSB, if used for a speculative 'ret', contains an
@@ -57,19 +66,6 @@
 #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.
@@ -152,12 +148,6 @@
 
 #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"		\
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index db333300bd4b..f94a7d0ddd49 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -13,13 +13,12 @@
 #ifndef _ASM_X86_SMAP_H
 #define _ASM_X86_SMAP_H
 
-#include <linux/stringify.h>
 #include <asm/nops.h>
 #include <asm/cpufeatures.h>
 
 /* "Raw" instruction opcodes */
-#define __ASM_CLAC	.byte 0x0f,0x01,0xca
-#define __ASM_STAC	.byte 0x0f,0x01,0xcb
+#define __ASM_CLAC	".byte 0x0f,0x01,0xca"
+#define __ASM_STAC	".byte 0x0f,0x01,0xcb"
 
 #ifdef __ASSEMBLY__
 
@@ -28,10 +27,10 @@
 #ifdef CONFIG_X86_SMAP
 
 #define ASM_CLAC \
-	ALTERNATIVE "", __stringify(__ASM_CLAC), X86_FEATURE_SMAP
+	ALTERNATIVE "", __ASM_CLAC, X86_FEATURE_SMAP
 
 #define ASM_STAC \
-	ALTERNATIVE "", __stringify(__ASM_STAC), X86_FEATURE_SMAP
+	ALTERNATIVE "", __ASM_STAC, X86_FEATURE_SMAP
 
 #else /* CONFIG_X86_SMAP */
 
@@ -49,26 +48,46 @@
 static __always_inline void clac(void)
 {
 	/* Note: a barrier is implicit in alternative() */
-	alternative("", __stringify(__ASM_CLAC), X86_FEATURE_SMAP);
+	alternative("", __ASM_CLAC, X86_FEATURE_SMAP);
 }
 
 static __always_inline void stac(void)
 {
 	/* Note: a barrier is implicit in alternative() */
-	alternative("", __stringify(__ASM_STAC), X86_FEATURE_SMAP);
+	alternative("", __ASM_STAC, X86_FEATURE_SMAP);
+}
+
+static __always_inline unsigned long smap_save(void)
+{
+	unsigned long flags;
+
+	asm volatile (ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC,
+				  X86_FEATURE_SMAP)
+		      : "=rm" (flags) : : "memory", "cc");
+
+	return flags;
+}
+
+static __always_inline void smap_restore(unsigned long flags)
+{
+	asm volatile (ALTERNATIVE("", "push %0; popf", X86_FEATURE_SMAP)
+		      : : "g" (flags) : "memory", "cc");
 }
 
 /* These macros can be used in asm() statements */
 #define ASM_CLAC \
-	ALTERNATIVE("", __stringify(__ASM_CLAC), X86_FEATURE_SMAP)
+	ALTERNATIVE("", __ASM_CLAC, X86_FEATURE_SMAP)
 #define ASM_STAC \
-	ALTERNATIVE("", __stringify(__ASM_STAC), X86_FEATURE_SMAP)
+	ALTERNATIVE("", __ASM_STAC, X86_FEATURE_SMAP)
 
 #else /* CONFIG_X86_SMAP */
 
 static inline void clac(void) { }
 static inline void stac(void) { }
 
+static inline unsigned long smap_save(void) { return 0; }
+static inline void smap_restore(unsigned long flags) { }
+
 #define ASM_CLAC
 #define ASM_STAC
 
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 7cf1a270d891..18a4b6890fa8 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -46,6 +46,7 @@ struct inactive_task_frame {
 	unsigned long r13;
 	unsigned long r12;
 #else
+	unsigned long flags;
 	unsigned long si;
 	unsigned long di;
 #endif
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 1954dd5552a2..bb21913885a3 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -427,10 +427,11 @@ do {									\
 ({								\
 	__label__ __pu_label;					\
 	int __pu_err = -EFAULT;					\
-	__typeof__(*(ptr)) __pu_val;				\
-	__pu_val = x;						\
+	__typeof__(*(ptr)) __pu_val = (x);			\
+	__typeof__(ptr) __pu_ptr = (ptr);			\
+	__typeof__(size) __pu_size = (size);			\
 	__uaccess_begin();					\
-	__put_user_size(__pu_val, (ptr), (size), __pu_label);	\
+	__put_user_size(__pu_val, __pu_ptr, __pu_size, __pu_label);	\
 	__pu_err = 0;						\
 __pu_label:							\
 	__uaccess_end();					\
@@ -705,7 +706,7 @@ extern struct movsl_mask {
  * checking before using them, but you have to surround them with the
  * user_access_begin/end() pair.
  */
-static __must_check inline bool user_access_begin(const void __user *ptr, size_t len)
+static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len)
 {
 	if (unlikely(!access_ok(ptr,len)))
 		return 0;
@@ -715,6 +716,9 @@ static __must_check inline bool user_access_begin(const void __user *ptr, size_t
 #define user_access_begin(a,b)	user_access_begin(a,b)
 #define user_access_end()	__uaccess_end()
 
+#define user_access_save()	smap_save()
+#define user_access_restore(x)	smap_restore(x)
+
 #define unsafe_put_user(x, ptr, label)	\
 	__put_user_size((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), label)
 
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index a9d637bc301d..5cd1caa8bc65 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -208,9 +208,6 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
 }
 
 unsigned long
-copy_user_handle_tail(char *to, char *from, unsigned len);
-
-unsigned long
 mcsafe_handle_tail(char *to, char *from, unsigned len);
 
 #endif /* _ASM_X86_UACCESS_64_H */
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 2863c2026655..d50c7b747d8b 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -217,6 +217,22 @@ xen_single_call(unsigned int call,
 	return (long)__res;
 }
 
+static __always_inline void __xen_stac(void)
+{
+	/*
+	 * Suppress objtool seeing the STAC/CLAC and getting confused about it
+	 * calling random code with AC=1.
+	 */
+	asm volatile(ANNOTATE_IGNORE_ALTERNATIVE
+		     ASM_STAC ::: "memory", "flags");
+}
+
+static __always_inline void __xen_clac(void)
+{
+	asm volatile(ANNOTATE_IGNORE_ALTERNATIVE
+		     ASM_CLAC ::: "memory", "flags");
+}
+
 static inline long
 privcmd_call(unsigned int call,
 	     unsigned long a1, unsigned long a2,
@@ -225,9 +241,9 @@ privcmd_call(unsigned int call,
 {
 	long res;
 
-	stac();
+	__xen_stac();
 	res = xen_single_call(call, a1, a2, a3, a4, a5);
-	clac();
+	__xen_clac();
 
 	return res;
 }
@@ -424,9 +440,9 @@ HYPERVISOR_dm_op(
 	domid_t dom, unsigned int nr_bufs, struct xen_dm_op_buf *bufs)
 {
 	int ret;
-	stac();
+	__xen_stac();
 	ret = _hypercall3(int, dm_op, dom, nr_bufs, bufs);
-	clac();
+	__xen_clac();
 	return ret;
 }
 
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index e471d8e6f0b2..70933193878c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -127,6 +127,13 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	struct task_struct *tsk;
 	int err;
 
+	/*
+	 * For a new task use the RESET flags value since there is no before.
+	 * All the status flags are zero; DF and all the system flags must also
+	 * be 0, specifically IF must be 0 because we context switch to the new
+	 * task with interrupts disabled.
+	 */
+	frame->flags = X86_EFLAGS_FIXED;
 	frame->bp = 0;
 	frame->ret_addr = (unsigned long) ret_from_fork;
 	p->thread.sp = (unsigned long) fork_frame;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 6a62f4af9fcf..844a28b29967 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -392,6 +392,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	childregs = task_pt_regs(p);
 	fork_frame = container_of(childregs, struct fork_frame, regs);
 	frame = &fork_frame->frame;
+
 	frame->bp = 0;
 	frame->ret_addr = (unsigned long) ret_from_fork;
 	p->thread.sp = (unsigned long) fork_frame;
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 08dfd4c1a4f9..c8aa58a2bab9 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -132,16 +132,6 @@ static int restore_sigcontext(struct pt_regs *regs,
 		COPY_SEG_CPL3(cs);
 		COPY_SEG_CPL3(ss);
 
-#ifdef CONFIG_X86_64
-		/*
-		 * Fix up SS if needed for the benefit of old DOSEMU and
-		 * CRIU.
-		 */
-		if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) &&
-			     user_64bit_mode(regs)))
-			force_valid_ss(regs);
-#endif
-
 		get_user_ex(tmpflags, &sc->flags);
 		regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
 		regs->orig_ax = -1;		/* disable syscall checks */
@@ -150,6 +140,15 @@ static int restore_sigcontext(struct pt_regs *regs,
 		buf = (void __user *)buf_val;
 	} get_user_catch(err);
 
+#ifdef CONFIG_X86_64
+	/*
+	 * Fix up SS if needed for the benefit of old DOSEMU and
+	 * CRIU.
+	 */
+	if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && user_64bit_mode(regs)))
+		force_valid_ss(regs);
+#endif
+
 	err |= fpu__restore_sig(buf, IS_ENABLED(CONFIG_X86_32));
 
 	force_iret();
@@ -461,6 +460,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 {
 	struct rt_sigframe __user *frame;
 	void __user *fp = NULL;
+	unsigned long uc_flags;
 	int err = 0;
 
 	frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp);
@@ -473,9 +473,11 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 			return -EFAULT;
 	}
 
+	uc_flags = frame_uc_flags(regs);
+
 	put_user_try {
 		/* Create the ucontext.  */
-		put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags);
+		put_user_ex(uc_flags, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
 		save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 
@@ -541,6 +543,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
 {
 #ifdef CONFIG_X86_X32_ABI
 	struct rt_sigframe_x32 __user *frame;
+	unsigned long uc_flags;
 	void __user *restorer;
 	int err = 0;
 	void __user *fpstate = NULL;
@@ -555,9 +558,11 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
 			return -EFAULT;
 	}
 
+	uc_flags = frame_uc_flags(regs);
+
 	put_user_try {
 		/* Create the ucontext.  */
-		put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags);
+		put_user_ex(uc_flags, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
 		compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 		put_user_ex(0, &frame->uc.uc__pad0);
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index db4e5aa0858b..b2f1822084ae 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -16,6 +16,30 @@
 #include <asm/smap.h>
 #include <asm/export.h>
 
+.macro ALIGN_DESTINATION
+	/* check for bad alignment of destination */
+	movl %edi,%ecx
+	andl $7,%ecx
+	jz 102f				/* already aligned */
+	subl $8,%ecx
+	negl %ecx
+	subl %ecx,%edx
+100:	movb (%rsi),%al
+101:	movb %al,(%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz 100b
+102:
+	.section .fixup,"ax"
+103:	addl %ecx,%edx			/* ecx is zerorest also */
+	jmp copy_user_handle_tail
+	.previous
+
+	_ASM_EXTABLE_UA(100b, 103b)
+	_ASM_EXTABLE_UA(101b, 103b)
+	.endm
+
 /*
  * copy_user_generic_unrolled - memory copy with exception handling.
  * This version is for CPUs like P4 that don't have efficient micro
@@ -194,6 +218,30 @@ ENDPROC(copy_user_enhanced_fast_string)
 EXPORT_SYMBOL(copy_user_enhanced_fast_string)
 
 /*
+ * Try to copy last bytes and clear the rest if needed.
+ * Since protection fault in copy_from/to_user is not a normal situation,
+ * it is not necessary to optimize tail handling.
+ *
+ * Input:
+ * rdi destination
+ * rsi source
+ * rdx count
+ *
+ * Output:
+ * eax uncopied bytes or 0 if successful.
+ */
+ALIGN;
+copy_user_handle_tail:
+	movl %edx,%ecx
+1:	rep movsb
+2:	mov %ecx,%eax
+	ASM_CLAC
+	ret
+
+	_ASM_EXTABLE_UA(1b, 2b)
+ENDPROC(copy_user_handle_tail)
+
+/*
  * copy_user_nocache - Uncached memory copy with exception handling
  * This will force destination out of cache for more performance.
  *
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 3b24dc05251c..9d05572370ed 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -257,6 +257,7 @@ ENTRY(__memcpy_mcsafe)
 	/* Copy successful. Return zero */
 .L_done_memcpy_trap:
 	xorl %eax, %eax
+.L_done:
 	ret
 ENDPROC(__memcpy_mcsafe)
 EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
@@ -273,7 +274,7 @@ EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
 	addl	%edx, %ecx
 .E_trailing_bytes:
 	mov	%ecx, %eax
-	ret
+	jmp	.L_done
 
 	/*
 	 * For write fault handling, given the destination is unaligned,
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index ee42bb0cbeb3..9952a01cad24 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -55,26 +55,6 @@ unsigned long clear_user(void __user *to, unsigned long n)
 EXPORT_SYMBOL(clear_user);
 
 /*
- * Try to copy last bytes and clear the rest if needed.
- * Since protection fault in copy_from/to_user is not a normal situation,
- * it is not necessary to optimize tail handling.
- */
-__visible unsigned long
-copy_user_handle_tail(char *to, char *from, unsigned len)
-{
-	for (; len; --len, to++) {
-		char c;
-
-		if (__get_user_nocheck(c, from++, sizeof(char)))
-			break;
-		if (__put_user_nocheck(c, to, sizeof(char)))
-			break;
-	}
-	clac();
-	return len;
-}
-
-/*
  * Similar to copy_user_handle_tail, probe for the write fault point,
  * but reuse __memcpy_mcsafe in case a new read error is encountered.
  * clac() is handled in _copy_to_iter_mcsafe().