[PATCH] zlib: Fix big performance regression

[Christophe Leroy]

Commit 340fdf1303dc ("zlib: Port fix for CVE-2016-9841 to U-Boot")
brings a big performance regression in inflate_fast(), which leads
to watchdog timer reset on powerpc 8xx.

It looks like that commit does more than what it describe, it
especially removed an important optimisation that was doing copies
using halfwords instead of bytes. That unexpected change multiplied
by almost 4 the time spent in inflate_fast() and increased by 40%
the overall time needed to uncompress linux kernel image.

So partially revert that commit but keep post incrementation as it
is the initial purpose of said commit.

Fixes: 340fdf1303dc ("zlib: Port fix for CVE-2016-9841 to U-Boot")
Signed-off-by: Christophe Leroy <christophe.leroy at csgroup.eu>
---
 lib/zlib/inffast.c | 51 ++++++++++++++++++++++++++++++++++++----------
 1 file changed, 40 insertions(+), 11 deletions(-)

diff --git a/lib/zlib/inffast.c b/lib/zlib/inffast.c
index 5e2a65ad4d..c4b1d12258 100644
--- a/lib/zlib/inffast.c
+++ b/lib/zlib/inffast.c
@@ -236,18 +236,47 @@ unsigned start;         /* inflate()'s starting value for strm->avail_out */
                     }
                 }
                 else {
+		    unsigned short *sout;
+		    unsigned long loops;
+
                     from = out - dist;          /* copy direct from output */
-                    do {                        /* minimum length is three */
-                        *out++ = *from++;
-                        *out++ = *from++;
-                        *out++ = *from++;
-                        len -= 3;
-                    } while (len > 2);
-                    if (len) {
-                        *out++ = *from++;
-                        if (len > 1)
-                            *out++ = *from++;
-                    }
+                    /* minimum length is three */
+		    /* Align out addr */
+		    if (!((long)(out - 1) & 1)) {
+			*out++ = *from++;
+			len--;
+		    }
+		    sout = (unsigned short *)out;
+		    if (dist > 2 ) {
+			unsigned short *sfrom;
+
+			sfrom = (unsigned short *)from;
+			loops = len >> 1;
+			do
+			    *sout++ = get_unaligned(++sfrom);
+			while (--loops);
+			out = (unsigned char *)sout;
+			from = (unsigned char *)sfrom;
+		    } else { /* dist == 1 or dist == 2 */
+			unsigned short pat16;
+
+			pat16 = *(sout-2);
+			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
+			    *sout++ = pat16;
+			while (--loops);
+			out = (unsigned char *)sout;
+		    }
+		    if (len & 1)
+			*out++ = *from++;
                 }
             }
             else if ((op & 64) == 0) {          /* 2nd level distance code */
-- 
2.44.0