x86: Make __get_user() generate an out-of-line call

Instead of inlining the whole stac/lfence/mov/clac sequence (which also
requires individual exception table entries and several asm instruction
alternatives entries), just generate "call __get_user_nocheck_X" for the
__get_user() cases.

We can use all the same infrastructure that we already do for the
regular "get_user()", and the end result is simpler source code, and
much simpler code generation.

It also means that when I introduce asm goto with input for
"unsafe_get_user()", there are no nasty interactions with the
__get_user() code.

Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/x86/include/asm/uaccess.h

@@ -96,25 +96,14 @@ static inline bool pagefault_disabled(void);
 	likely(!__range_not_ok(addr, size, user_addr_max()));		\
 })
 
-/*
- * These are the main single-value transfer routines.  They automatically
- * use the right size if we just have the right pointer type.
- *
- * This gets kind of ugly. We want to return _two_ values in "get_user()"
- * and yet we don't want to do any pointers, because that is too much
- * of a performance impact. Thus we have a few rather ugly macros here,
- * and hide all the ugliness from the user.
- *
- * The "__xxx" versions of the user access functions are versions that
- * do not verify the address space, that must have been done previously
- * with a separate "access_ok()" call (this is used when we do multiple
- * accesses to the same area of user memory).
- */
-
 extern int __get_user_1(void);
 extern int __get_user_2(void);
 extern int __get_user_4(void);
 extern int __get_user_8(void);
+extern int __get_user_nocheck_1(void);
+extern int __get_user_nocheck_2(void);
+extern int __get_user_nocheck_4(void);
+extern int __get_user_nocheck_8(void);
 extern int __get_user_bad(void);
 
 #define __uaccess_begin() stac()
@@ -138,25 +127,12 @@ extern int __get_user_bad(void);
 #define __typefits(x,type,not) \
 	__builtin_choose_expr(sizeof(x)<=sizeof(type),(unsigned type)0,not)
 
-/**
- * get_user - Get a simple variable from user space.
- * @x:   Variable to store result.
- * @ptr: Source address, in user space.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * This macro copies a single simple variable from user space to kernel
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and the result of
- * dereferencing @ptr must be assignable to @x without a cast.
- *
- * Return: zero on success, or -EFAULT on error.
- * On error, the variable @x is set to zero.
- */
 /*
+ * This is used for both get_user() and __get_user() to expand to
+ * the proper special function call that has odd calling conventions
+ * due to returning both a value and an error, and that depends on
+ * the size of the pointer passed in.
+ *
  * Careful: we have to cast the result to the type of the pointer
  * for sign reasons.
  *
@@ -169,13 +145,12 @@ extern int __get_user_bad(void);
  * Clang/LLVM cares about the size of the register, but still wants
  * the base register for something that ends up being a pair.
  */
-#define get_user(x, ptr)						\
+#define do_get_user_call(fn,x,ptr)					\
 ({									\
 	int __ret_gu;							\
 	register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX);		\
 	__chk_user_ptr(ptr);						\
-	might_fault();							\
-	asm volatile("call __get_user_%P4"				\
+	asm volatile("call __" #fn "_%P4"				\
 		     : "=a" (__ret_gu), "=r" (__val_gu),		\
 			ASM_CALL_CONSTRAINT				\
 		     : "0" (ptr), "i" (sizeof(*(ptr))));		\
@@ -183,6 +158,49 @@ extern int __get_user_bad(void);
 	__builtin_expect(__ret_gu, 0);					\
 })
 
+/**
+ * get_user - Get a simple variable from user space.
+ * @x:   Variable to store result.
+ * @ptr: Source address, in user space.
+ *
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
+ *
+ * This macro copies a single simple variable from user space to kernel
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and the result of
+ * dereferencing @ptr must be assignable to @x without a cast.
+ *
+ * Return: zero on success, or -EFAULT on error.
+ * On error, the variable @x is set to zero.
+ */
+#define get_user(x,ptr) ({ might_fault(); do_get_user_call(get_user,x,ptr); })
+
+/**
+ * __get_user - Get a simple variable from user space, with less checking.
+ * @x:   Variable to store result.
+ * @ptr: Source address, in user space.
+ *
+ * Context: User context only. This function may sleep if pagefaults are
+ *          enabled.
+ *
+ * This macro copies a single simple variable from user space to kernel
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and the result of
+ * dereferencing @ptr must be assignable to @x without a cast.
+ *
+ * Caller must check the pointer with access_ok() before calling this
+ * function.
+ *
+ * Return: zero on success, or -EFAULT on error.
+ * On error, the variable @x is set to zero.
+ */
+#define __get_user(x,ptr) do_get_user_call(get_user_nocheck,x,ptr)
+
 #define __put_user_x(size, x, ptr, __ret_pu)			\
 	asm volatile("call __put_user_" #size : "=a" (__ret_pu)	\
 		     : "0" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
@@ -367,19 +385,6 @@ __pu_label:							\
 	__builtin_expect(__pu_err, 0);				\
 })
 
-#define __get_user_nocheck(x, ptr, size)				\
-({									\
-	int __gu_err;							\
-	__inttype(*(ptr)) __gu_val;					\
-	__typeof__(ptr) __gu_ptr = (ptr);				\
-	__typeof__(size) __gu_size = (size);				\
-	__uaccess_begin_nospec();					\
-	__get_user_size(__gu_val, __gu_ptr, __gu_size, __gu_err);	\
-	__uaccess_end();						\
-	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
-	__builtin_expect(__gu_err, 0);					\
-})
-
 /* FIXME: this hack is definitely wrong -AK */
 struct __large_struct { unsigned long buf[100]; };
 #define __m(x) (*(struct __large_struct __user *)(x))
@@ -396,31 +401,6 @@ struct __large_struct { unsigned long buf[100]; };
 		: : ltype(x), "m" (__m(addr))				\
 		: : label)
 
-/**
- * __get_user - Get a simple variable from user space, with less checking.
- * @x:   Variable to store result.
- * @ptr: Source address, in user space.
- *
- * Context: User context only. This function may sleep if pagefaults are
- *          enabled.
- *
- * This macro copies a single simple variable from user space to kernel
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and the result of
- * dereferencing @ptr must be assignable to @x without a cast.
- *
- * Caller must check the pointer with access_ok() before calling this
- * function.
- *
- * Return: zero on success, or -EFAULT on error.
- * On error, the variable @x is set to zero.
- */
-
-#define __get_user(x, ptr)						\
-	__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
-
 /**
  * __put_user - Write a simple value into user space, with less checking.
  * @x:   Value to copy to user space.

arch/x86/lib/getuser.S

@@ -35,6 +35,8 @@
 #include <asm/smap.h>
 #include <asm/export.h>
 
+#define ASM_BARRIER_NOSPEC ALTERNATIVE "", "lfence", X86_FEATURE_LFENCE_RDTSC
+
 	.text
 SYM_FUNC_START(__get_user_1)
 	mov PER_CPU_VAR(current_task), %_ASM_DX
@@ -114,6 +116,52 @@ SYM_FUNC_START(__get_user_8)
 SYM_FUNC_END(__get_user_8)
 EXPORT_SYMBOL(__get_user_8)
 
+/* .. and the same for __get_user, just without the range checks */
+SYM_FUNC_START(__get_user_nocheck_1)
+	ASM_STAC
+	ASM_BARRIER_NOSPEC
+6:	movzbl (%_ASM_AX),%edx
+	xor %eax,%eax
+	ASM_CLAC
+	ret
+SYM_FUNC_END(__get_user_nocheck_1)
+EXPORT_SYMBOL(__get_user_nocheck_1)
+
+SYM_FUNC_START(__get_user_nocheck_2)
+	ASM_STAC
+	ASM_BARRIER_NOSPEC
+7:	movzwl (%_ASM_AX),%edx
+	xor %eax,%eax
+	ASM_CLAC
+	ret
+SYM_FUNC_END(__get_user_nocheck_2)
+EXPORT_SYMBOL(__get_user_nocheck_2)
+
+SYM_FUNC_START(__get_user_nocheck_4)
+	ASM_STAC
+	ASM_BARRIER_NOSPEC
+8:	movl (%_ASM_AX),%edx
+	xor %eax,%eax
+	ASM_CLAC
+	ret
+SYM_FUNC_END(__get_user_nocheck_4)
+EXPORT_SYMBOL(__get_user_nocheck_4)
+
+SYM_FUNC_START(__get_user_nocheck_8)
+	ASM_STAC
+	ASM_BARRIER_NOSPEC
+#ifdef CONFIG_X86_64
+9:	movq (%_ASM_AX),%rdx
+#else
+9:	movl (%_ASM_AX),%edx
+10:	movl 4(%_ASM_AX),%ecx
+#endif
+	xor %eax,%eax
+	ASM_CLAC
+	ret
+SYM_FUNC_END(__get_user_nocheck_8)
+EXPORT_SYMBOL(__get_user_nocheck_8)
+
 
 SYM_CODE_START_LOCAL(.Lbad_get_user_clac)
 	ASM_CLAC
@@ -134,6 +182,7 @@ bad_get_user_8:
 SYM_CODE_END(.Lbad_get_user_8_clac)
 #endif
 
+/* get_user */
 	_ASM_EXTABLE_UA(1b, .Lbad_get_user_clac)
 	_ASM_EXTABLE_UA(2b, .Lbad_get_user_clac)
 	_ASM_EXTABLE_UA(3b, .Lbad_get_user_clac)
@@ -143,3 +192,14 @@ SYM_CODE_END(.Lbad_get_user_8_clac)
 	_ASM_EXTABLE_UA(4b, .Lbad_get_user_8_clac)
 	_ASM_EXTABLE_UA(5b, .Lbad_get_user_8_clac)
 #endif
+
+/* __get_user */
+	_ASM_EXTABLE_UA(6b, .Lbad_get_user_clac)
+	_ASM_EXTABLE_UA(7b, .Lbad_get_user_clac)
+	_ASM_EXTABLE_UA(8b, .Lbad_get_user_clac)
+#ifdef CONFIG_X86_64
+	_ASM_EXTABLE_UA(9b, .Lbad_get_user_clac)
+#else
+	_ASM_EXTABLE_UA(9b, .Lbad_get_user_8_clac)
+	_ASM_EXTABLE_UA(10b, .Lbad_get_user_8_clac)
+#endif