MIPS: Unify memcpy.S and memcpy-inatomic.S

We can save the 451 lines of code that comprise memcpy-inatomic.S at the
expense of a single instruction in the memcpy prolog.  We also use an
additional register (t6), so this may cause increased register pressure in
some places as well.  But I think the reduced maintenance burden, of not
having two nearly identical implementations, makes it worth it.
Signed-off-by: David Daney <david.daney@cavium.com>
Cc: linux-mips@linux-mips.org
Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

arch/mips/include/asm/uaccess.h

@@ -687,7 +687,7 @@ extern size_t __copy_user(void *__to, const void *__from, size_t __n);
 	__MODULE_JAL(__copy_user)					\
 	: "+r" (__cu_to_r), "+r" (__cu_from_r), "+r" (__cu_len_r)	\
 	:								\
-	: "$8", "$9", "$10", "$11", "$12", "$15", "$24", "$31",		\
+	: "$8", "$9", "$10", "$11", "$12", "$14", "$15", "$24", "$31",	\
 	  DADDI_SCRATCH, "memory");					\
 	__cu_len_r;							\
 })
@@ -797,7 +797,7 @@ extern size_t __copy_user_inatomic(void *__to, const void *__from, size_t __n);
 	".set\treorder"							\
 	: "+r" (__cu_to_r), "+r" (__cu_from_r), "+r" (__cu_len_r)	\
 	:								\
-	: "$8", "$9", "$10", "$11", "$12", "$15", "$24", "$31",		\
+	: "$8", "$9", "$10", "$11", "$12", "$14", "$15", "$24", "$31",	\
 	  DADDI_SCRATCH, "memory");					\
 	__cu_len_r;							\
 })
@@ -820,7 +820,7 @@ extern size_t __copy_user_inatomic(void *__to, const void *__from, size_t __n);
 	".set\treorder"							\
 	: "+r" (__cu_to_r), "+r" (__cu_from_r), "+r" (__cu_len_r)	\
 	:								\
-	: "$8", "$9", "$10", "$11", "$12", "$15", "$24", "$31",		\
+	: "$8", "$9", "$10", "$11", "$12", "$14", "$15", "$24", "$31",	\
 	  DADDI_SCRATCH, "memory");					\
 	__cu_len_r;							\
 })

arch/mips/lib/Makefile

@@ -2,7 +2,7 @@
 # Makefile for MIPS-specific library files..
 #
 
-lib-y	+= csum_partial.o delay.o memcpy.o memcpy-inatomic.o memset.o \
+lib-y	+= csum_partial.o delay.o memcpy.o memset.o \
 	   strlen_user.o strncpy_user.o strnlen_user.o uncached.o
 
 obj-y			+= iomap.o

arch/mips/lib/memcpy.S

@@ -182,6 +182,14 @@
 	.set	at=v1
 #endif
 
+/*
+ * t6 is used as a flag to note inatomic mode.
+ */
+LEAF(__copy_user_inatomic)
+	b	__copy_user_common
+	 li	t6, 1
+	END(__copy_user_inatomic)
+
 /*
  * A combined memcpy/__copy_user
  * __copy_user sets len to 0 for success; else to an upper bound of
@@ -193,6 +201,8 @@ LEAF(memcpy)					/* a0=dst a1=src a2=len */
 	move	v0, dst				/* return value */
 .L__memcpy:
 FEXPORT(__copy_user)
+	li	t6, 0	/* not inatomic */
+__copy_user_common:
 	/*
 	 * Note: dst & src may be unaligned, len may be 0
 	 * Temps
@@ -458,6 +468,7 @@ EXC(	lb	t1, 0(src),	.Ll_exc)
 	LOAD	t0, THREAD_BUADDR(t0)	# t0 is just past last good address
 	 nop
 	SUB	len, AT, t0		# len number of uncopied bytes
+	bnez	t6, .Ldone	/* Skip the zeroing part if inatomic */
 	/*
 	 * Here's where we rely on src and dst being incremented in tandem,
 	 *   See (3) above.