ARM: 8091/2: add get_user() support for 8 byte types

Recent contributions, including to DRM and binder, introduce 64-bit
values in their interfaces. A common motivation for this is to allow
the same ABI for 32- and 64-bit userspaces (and therefore also a shared
ABI for 32/64 hybrid userspaces). Anyhow, the developers would like to
avoid gotchas like having to use copy_from_user().

This feature is already implemented on x86-32 and the majority of other
32-bit architectures. The current list of get_user_8 hold out
architectures are: arm, avr32, blackfin, m32r, metag, microblaze,
mn10300, sh.

Credit:

    My name sits rather uneasily at the top of this patch. The v1 and
    v2 versions of the patch were written by Rob Clark and to produce v4
    I mostly copied code from Russell King and H. Peter Anvin. However I
    have mangled the patch sufficiently that *blame* is rightfully mine
    even if credit should more widely shared.

Changelog:

v5: updated to use the ret macro (requested by Russell King)
v4: remove an inlined add on big endian systems (spotted by Russell King),
    used __ARMEB__ rather than BIG_ENDIAN (to match rest of file),
    cleared r3 on EFAULT during __get_user_8.
v3: fix a couple of checkpatch issues
v2: pass correct size to check_uaccess, and better handling of narrowing
    double word read with __get_user_xb() (Russell King's suggestion)
v1: original
Signed-off-by: Rob Clark <robdclark@gmail.com>
Signed-off-by: Daniel Thompson <daniel.thompson@linaro.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

arch/arm/include/asm/uaccess.h

@@ -107,6 +107,8 @@ static inline void set_fs(mm_segment_t fs)
 extern int __get_user_1(void *);
 extern int __get_user_2(void *);
 extern int __get_user_4(void *);
+extern int __get_user_lo8(void *);
+extern int __get_user_8(void *);
 
 #define __GUP_CLOBBER_1	"lr", "cc"
 #ifdef CONFIG_CPU_USE_DOMAINS
@@ -115,6 +117,8 @@ extern int __get_user_4(void *);
 #define __GUP_CLOBBER_2 "lr", "cc"
 #endif
 #define __GUP_CLOBBER_4	"lr", "cc"
+#define __GUP_CLOBBER_lo8 "lr", "cc"
+#define __GUP_CLOBBER_8	"lr", "cc"
 
 #define __get_user_x(__r2,__p,__e,__l,__s)				\
 	   __asm__ __volatile__ (					\
@@ -125,11 +129,19 @@ extern int __get_user_4(void *);
 		: "0" (__p), "r" (__l)					\
 		: __GUP_CLOBBER_##__s)
 
+/* narrowing a double-word get into a single 32bit word register: */
+#ifdef __ARMEB__
+#define __get_user_xb(__r2, __p, __e, __l, __s)				\
+	__get_user_x(__r2, __p, __e, __l, lo8)
+#else
+#define __get_user_xb __get_user_x
+#endif
+
 #define __get_user_check(x,p)							\
 	({								\
 		unsigned long __limit = current_thread_info()->addr_limit - 1; \
 		register const typeof(*(p)) __user *__p asm("r0") = (p);\
-		register unsigned long __r2 asm("r2");			\
+		register typeof(x) __r2 asm("r2");			\
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		switch (sizeof(*(__p))) {				\
@@ -142,6 +154,12 @@ extern int __get_user_4(void *);
 		case 4:							\
 			__get_user_x(__r2, __p, __e, __l, 4);		\
 			break;						\
+		case 8:							\
+			if (sizeof((x)) < 8)				\
+				__get_user_xb(__r2, __p, __e, __l, 4);	\
+			else						\
+				__get_user_x(__r2, __p, __e, __l, 8);	\
+			break;						\
 		default: __e = __get_user_bad(); break;			\
 		}							\
 		x = (typeof(*(p))) __r2;				\

arch/arm/lib/getuser.S

@@ -18,7 +18,7 @@
  * Inputs:	r0 contains the address
  *		r1 contains the address limit, which must be preserved
  * Outputs:	r0 is the error code
- *		r2 contains the zero-extended value
+ *		r2, r3 contains the zero-extended value
  *		lr corrupted
  *
  * No other registers must be altered.  (see <asm/uaccess.h>
@@ -66,15 +66,50 @@ ENTRY(__get_user_4)
 	ret	lr
 ENDPROC(__get_user_4)
 
+ENTRY(__get_user_8)
+	check_uaccess r0, 8, r1, r2, __get_user_bad
+#ifdef CONFIG_THUMB2_KERNEL
+5: TUSER(ldr)	r2, [r0]
+6: TUSER(ldr)	r3, [r0, #4]
+#else
+5: TUSER(ldr)	r2, [r0], #4
+6: TUSER(ldr)	r3, [r0]
+#endif
+	mov	r0, #0
+	ret	lr
+ENDPROC(__get_user_8)
+
+#ifdef __ARMEB__
+ENTRY(__get_user_lo8)
+	check_uaccess r0, 8, r1, r2, __get_user_bad
+#ifdef CONFIG_CPU_USE_DOMAINS
+	add	r0, r0, #4
+7:	ldrt	r2, [r0]
+#else
+7:	ldr	r2, [r0, #4]
+#endif
+	mov	r0, #0
+	ret	lr
+ENDPROC(__get_user_lo8)
+#endif
+
+__get_user_bad8:
+	mov	r3, #0
 __get_user_bad:
 	mov	r2, #0
 	mov	r0, #-EFAULT
 	ret	lr
 ENDPROC(__get_user_bad)
+ENDPROC(__get_user_bad8)
 
 .pushsection __ex_table, "a"
 	.long	1b, __get_user_bad
 	.long	2b, __get_user_bad
 	.long	3b, __get_user_bad
 	.long	4b, __get_user_bad
+	.long	5b, __get_user_bad8
+	.long	6b, __get_user_bad8
+#ifdef __ARMEB__
+	.long   7b, __get_user_bad
+#endif
 .popsection