zlib: optimize inffast when copying direct from output

JFFS2 uses lesser compression ratio and inflate always ends up in "copy
direct from output" case.

This patch tries to optimize the direct copy procedure.  Uses
get_unaligned() but only in one place.

The copy loop just above this one can also use this optimization, but I
havn't done so as I have not tested if it is a win there too.

On my MPC8321 this is about 17% faster on my JFFS2 root FS than the
original.

[akpm@linux-foundation.org: coding-style fixes]
Signed-off-by: Joakim Tjernlund <Joakim.Tjernlund@transmode.se>
Cc: Roel Kluin <roel.kluin@gmail.com>
Cc: Richard Purdie <rpurdie@rpsys.net>
Cc: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/powerpc/boot/Makefile

@@ -20,7 +20,7 @@
 all: $(obj)/zImage
 
 BOOTCFLAGS    := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
-		 -fno-strict-aliasing -Os -msoft-float -pipe \
+		 -fno-strict-aliasing -Os -msoft-float -pipe -D__KERNEL__\
 		 -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \
 		 -isystem $(shell $(CROSS32CC) -print-file-name=include)
 BOOTAFLAGS	:= -D__ASSEMBLY__ $(BOOTCFLAGS) -traditional -nostdinc
@@ -34,6 +34,8 @@ BOOTCFLAGS	+= -fno-stack-protector
 endif
 
 BOOTCFLAGS	+= -I$(obj) -I$(srctree)/$(obj)
+BOOTCFLAGS	+= -include include/linux/autoconf.h -Iarch/powerpc/include
+BOOTCFLAGS	+= -Iinclude
 
 DTS_FLAGS	?= -p 1024
 

lib/zlib_inflate/inffast.c

@@ -4,6 +4,8 @@
  */
 
 #include <linux/zutil.h>
+#include <asm/unaligned.h>
+#include <asm/byteorder.h>
 #include "inftrees.h"
 #include "inflate.h"
 #include "inffast.h"
@@ -24,9 +26,11 @@
 #ifdef POSTINC
 #  define OFF 0
 #  define PUP(a) *(a)++
+#  define UP_UNALIGNED(a) get_unaligned((a)++)
 #else
 #  define OFF 1
 #  define PUP(a) *++(a)
+#  define UP_UNALIGNED(a) get_unaligned(++(a))
 #endif
 
 /*
@@ -239,18 +243,47 @@ void inflate_fast(z_streamp strm, unsigned start)
                     }
                 }
                 else {
+		    unsigned short *sout;
+		    unsigned long loops;
+
                     from = out - dist;          /* copy direct from output */
-                    do {                        /* minimum length is three */
-                        PUP(out) = PUP(from);
-                        PUP(out) = PUP(from);
-                        PUP(out) = PUP(from);
-                        len -= 3;
-                    } while (len > 2);
-                    if (len) {
-                        PUP(out) = PUP(from);
-                        if (len > 1)
+		    /* minimum length is three */
+		    /* Align out addr */
+		    if (!((long)(out - 1 + OFF) & 1)) {
 			PUP(out) = PUP(from);
+			len--;
 		    }
+		    sout = (unsigned short *)(out - OFF);
+		    if (dist > 2) {
+			unsigned short *sfrom;
+
+			sfrom = (unsigned short *)(from - OFF);
+			loops = len >> 1;
+			do
+			    PUP(sout) = UP_UNALIGNED(sfrom);
+			while (--loops);
+			out = (unsigned char *)sout + OFF;
+			from = (unsigned char *)sfrom + OFF;
+		    } else { /* dist == 1 or dist == 2 */
+			unsigned short pat16;
+
+			pat16 = *(sout-2+2*OFF);
+			if (dist == 1)
+#if defined(__BIG_ENDIAN)
+			    pat16 = (pat16 & 0xff) | ((pat16 & 0xff) << 8);
+#elif defined(__LITTLE_ENDIAN)
+			    pat16 = (pat16 & 0xff00) | ((pat16 & 0xff00) >> 8);
+#else
+#error __BIG_ENDIAN nor __LITTLE_ENDIAN is defined
+#endif
+			loops = len >> 1;
+			do
+			    PUP(sout) = pat16;
+			while (--loops);
+			out = (unsigned char *)sout + OFF;
+		    }
+		    if (len & 1)
+			PUP(out) = PUP(from);
                 }
             }
             else if ((op & 64) == 0) {          /* 2nd level distance code */