ARM: implement memset32 & memset64

Reuse the existing optimised memset implementation to implement an
optimised memset32 and memset64.

Link: http://lkml.kernel.org/r/20170720184539.31609-5-willy@infradead.org
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
Reviewed-by: Russell King <rmk+kernel@armlinux.org.uk>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "James E.J. Bottomley" <jejb@linux.vnet.ibm.com>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: David Miller <davem@davemloft.net>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/arm/include/asm/string.h

@@ -24,6 +24,20 @@ extern void * memchr(const void *, int, __kernel_size_t);
 #define __HAVE_ARCH_MEMSET
 extern void * memset(void *, int, __kernel_size_t);
 
+#define __HAVE_ARCH_MEMSET32
+extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t);
+static inline void *memset32(uint32_t *p, uint32_t v, __kernel_size_t n)
+{
+	return __memset32(p, v, n * 4);
+}
+
+#define __HAVE_ARCH_MEMSET64
+extern void *__memset64(uint64_t *, uint32_t low, __kernel_size_t, uint32_t hi);
+static inline void *memset64(uint64_t *p, uint64_t v, __kernel_size_t n)
+{
+	return __memset64(p, v, n * 8, v >> 32);
+}
+
 extern void __memzero(void *ptr, __kernel_size_t n);
 
 #define memset(p,v,n)							\

arch/arm/kernel/armksyms.c

@@ -87,6 +87,8 @@ EXPORT_SYMBOL(__raw_writesl);
 EXPORT_SYMBOL(strchr);
 EXPORT_SYMBOL(strrchr);
 EXPORT_SYMBOL(memset);
+EXPORT_SYMBOL(__memset32);
+EXPORT_SYMBOL(__memset64);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(memchr);

arch/arm/lib/memset.S

@@ -28,7 +28,7 @@ UNWIND( .fnstart         )
 1:	orr	r1, r1, r1, lsl #8
 	orr	r1, r1, r1, lsl #16
 	mov	r3, r1
-	cmp	r2, #16
+7:	cmp	r2, #16
 	blt	4f
 
 #if ! CALGN(1)+0
@@ -41,7 +41,7 @@ UNWIND( .fnend              )
 UNWIND( .fnstart            )
 UNWIND( .save {r8, lr}      )
 	mov	r8, r1
-	mov	lr, r1
+	mov	lr, r3
 
 2:	subs	r2, r2, #64
 	stmgeia	ip!, {r1, r3, r8, lr}	@ 64 bytes at a time.
@@ -73,11 +73,11 @@ UNWIND( .fnend                 )
 UNWIND( .fnstart               )
 UNWIND( .save {r4-r8, lr}      )
 	mov	r4, r1
-	mov	r5, r1
+	mov	r5, r3
 	mov	r6, r1
-	mov	r7, r1
+	mov	r7, r3
 	mov	r8, r1
-	mov	lr, r1
+	mov	lr, r3
 
 	cmp	r2, #96
 	tstgt	ip, #31
@@ -114,7 +114,7 @@ UNWIND( .fnstart            )
 	tst	r2, #4
 	strne	r1, [ip], #4
 /*
- * When we get here, we've got less than 4 bytes to zero.  We
+ * When we get here, we've got less than 4 bytes to set.  We
  * may have an unaligned pointer as well.
  */
 5:	tst	r2, #2
@@ -135,3 +135,15 @@ UNWIND( .fnstart            )
 UNWIND( .fnend   )
 ENDPROC(memset)
 ENDPROC(mmioset)
+
+ENTRY(__memset32)
+UNWIND( .fnstart         )
+	mov	r3, r1			@ copy r1 to r3 and fall into memset64
+UNWIND( .fnend   )
+ENDPROC(__memset32)
+ENTRY(__memset64)
+UNWIND( .fnstart         )
+	mov	ip, r0			@ preserve r0 as return value
+	b	7b			@ jump into the middle of memset
+UNWIND( .fnend   )
+ENDPROC(__memset64)