vga: optimise console scrolling

Where possible, call memset16(), memmove() or memcpy() instead of using
open-coded loops.  I don't like the calling convention that uses a byte
count instead of a count of u16s, but it's a little late to change that.
Reduces code size of fbcon.o by almost 400 bytes on my laptop build.

[akpm@linux-foundation.org: fix build]
Link: http://lkml.kernel.org/r/20170720184539.31609-9-willy@infradead.org
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: David Miller <davem@davemloft.net>
Cc: Sam Ravnborg <sam@ravnborg.org>
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: 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: Richard Henderson <rth@twiddle.net>
Cc: Russell King <rmk+kernel@armlinux.org.uk>
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/sparc/include/asm/vga.h

@@ -8,9 +8,13 @@
 #define _LINUX_ASM_VGA_H_
 
 #include <linux/bug.h>
+#include <linux/string.h>
 #include <asm/types.h>
 
 #define VT_BUF_HAVE_RW
+#define VT_BUF_HAVE_MEMSETW
+#define VT_BUF_HAVE_MEMCPYW
+#define VT_BUF_HAVE_MEMMOVEW
 
 #undef scr_writew
 #undef scr_readw
@@ -29,6 +33,27 @@ static inline u16 scr_readw(const u16 *addr)
 	return *addr;
 }
 
+static inline void scr_memsetw(u16 *p, u16 v, unsigned int n)
+{
+	BUG_ON((long) p >= 0);
+
+	memset16(p, cpu_to_le16(v), n / 2);
+}
+
+static inline void scr_memcpyw(u16 *d, u16 *s, unsigned int n)
+{
+	BUG_ON((long) d >= 0);
+
+	memcpy(d, s, n);
+}
+
+static inline void scr_memmovew(u16 *d, u16 *s, unsigned int n)
+{
+	BUG_ON((long) d >= 0);
+
+	memmove(d, s, n);
+}
+
 #define VGA_MAP_MEM(x,s) (x)
 
 #endif