Merge remote-tracking branch 'qatar/master'

* qatar/master: (40 commits)
  H.264: template left MB handling
  H.264: faster fill_decode_caches
  H.264: faster write_back_*
  H.264: faster fill_filter_caches
  H.264: make filter_mb_fast support the case of unavailable top mb
  Do not include log.h in avutil.h
  Do not include pixfmt.h in avutil.h
  Do not include rational.h in avutil.h
  Do not include mathematics.h in avutil.h
  Do not include intfloat_readwrite.h in avutil.h
  Remove return statements following infinite loops without break
  RTSP: Doxygen comment cleanup
  doxygen: Escape '\' in Doxygen documentation.
  md5: cosmetics
  md5: use AV_WL32 to write result
  md5: add fate test
  md5: include correct headers
  md5: fix test program
  doxygen: Drop array size declarations from Doxygen parameter names.
  doxygen: Fix parameter names to match the function prototypes.
  ...

Conflicts:
	libavcodec/x86/dsputil_mmx.c
	libavformat/flvenc.c
	libavformat/oggenc.c
	libavformat/wtv.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>

1 files changed, 79 insertions, 57 deletions

diff --git a/libavutil/md5.c b/libavutil/md5.c
index 173ed0623b..471a510a73 100644
--- a/libavutil/md5.c
+++ b/libavutil/md5.c
@@ -30,8 +30,9 @@
  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
-#include <string.h>
+#include <stdint.h>
 #include "bswap.h"
+#include "intreadwrite.h"
 #include "md5.h"
 
 typedef struct AVMD5{
@@ -40,7 +41,7 @@ typedef struct AVMD5{
     uint32_t ABCD[4];
 } AVMD5;
 
-const int av_md5_size= sizeof(AVMD5);
+const int av_md5_size = sizeof(AVMD5);
 
 static const uint8_t S[4][4] = {
     { 7, 12, 17, 22 },  /* round 1 */
@@ -71,42 +72,49 @@ static const uint32_t T[64] = { // T[i]= fabs(sin(i+1)<<32)
     0xf7537e82, 0xbd3af235, 0x2ad7d2bb, 0xeb86d391,
 };
 
-#define CORE(i, a, b, c, d) \
-        t = S[i>>4][i&3];\
-        a += T[i];\
-\
-        if(i<32){\
-            if(i<16) a += (d ^ (b&(c^d))) + X[      i &15 ];\
-            else     a += (c ^ (d&(c^b))) + X[ (1+5*i)&15 ];\
-        }else{\
-            if(i<48) a += (b^c^d)         + X[ (5+3*i)&15 ];\
-            else     a += (c^(b|~d))      + X[ (  7*i)&15 ];\
-        }\
-        a = b + (( a << t ) | ( a >> (32 - t) ));
-
-static void body(uint32_t ABCD[4], uint32_t X[16]){
-
+#define CORE(i, a, b, c, d) do {                                        \
+        t = S[i >> 4][i & 3];                                           \
+        a += T[i];                                                      \
+                                                                        \
+        if (i < 32) {                                                   \
+            if (i < 16) a += (d ^ (b & (c ^ d))) + X[       i  & 15];   \
+            else        a += (c ^ (d & (c ^ b))) + X[(1 + 5*i) & 15];   \
+        } else {                                                        \
+            if (i < 48) a += (b ^ c ^ d)         + X[(5 + 3*i) & 15];   \
+            else        a += (c ^ (b | ~d))      + X[(    7*i) & 15];   \
+        }                                                               \
+        a = b + (a << t | a >> (32 - t));                               \
+    } while (0)
+
+static void body(uint32_t ABCD[4], uint32_t X[16])
+{
     int t;
     int i av_unused;
-    unsigned int a= ABCD[3];
-    unsigned int b= ABCD[2];
-    unsigned int c= ABCD[1];
-    unsigned int d= ABCD[0];
+    unsigned int a = ABCD[3];
+    unsigned int b = ABCD[2];
+    unsigned int c = ABCD[1];
+    unsigned int d = ABCD[0];
 
 #if HAVE_BIGENDIAN
-    for(i=0; i<16; i++)
-        X[i]= av_bswap32(X[i]);
+    for (i = 0; i < 16; i++)
+        X[i] = av_bswap32(X[i]);
 #endif
 
 #if CONFIG_SMALL
-    for( i = 0; i < 64; i++ ){
-        CORE(i,a,b,c,d)
-        t=d; d=c; c=b; b=a; a=t;
+    for (i = 0; i < 64; i++) {
+        CORE(i, a, b, c, d);
+        t = d;
+        d = c;
+        c = b;
+        b = a;
+        a = t;
     }
 #else
-#define CORE2(i) CORE(i,a,b,c,d) CORE((i+1),d,a,b,c) CORE((i+2),c,d,a,b) CORE((i+3),b,c,d,a)
-#define CORE4(i) CORE2(i) CORE2((i+4)) CORE2((i+8)) CORE2((i+12))
-CORE4(0) CORE4(16) CORE4(32) CORE4(48)
+#define CORE2(i)                                                        \
+    CORE( i,   a,b,c,d); CORE((i+1),d,a,b,c);                           \
+    CORE((i+2),c,d,a,b); CORE((i+3),b,c,d,a)
+#define CORE4(i) CORE2(i); CORE2((i+4)); CORE2((i+8)); CORE2((i+12))
+    CORE4(0); CORE4(16); CORE4(32); CORE4(48);
 #endif
 
     ABCD[0] += d;
@@ -115,8 +123,9 @@ CORE4(0) CORE4(16) CORE4(32) CORE4(48)
     ABCD[3] += a;
 }
 
-void av_md5_init(AVMD5 *ctx){
-    ctx->len    = 0;
+void av_md5_init(AVMD5 *ctx)
+{
+    ctx->len     = 0;
 
     ctx->ABCD[0] = 0x10325476;
     ctx->ABCD[1] = 0x98badcfe;
@@ -124,59 +133,72 @@ void av_md5_init(AVMD5 *ctx){
     ctx->ABCD[3] = 0x67452301;
 }
 
-void av_md5_update(AVMD5 *ctx, const uint8_t *src, const int len){
+void av_md5_update(AVMD5 *ctx, const uint8_t *src, const int len)
+{
     int i, j;
 
-    j= ctx->len & 63;
+    j = ctx->len & 63;
     ctx->len += len;
 
-    for( i = 0; i < len; i++ ){
+    for (i = 0; i < len; i++) {
         ctx->block[j++] = src[i];
-        if( 64 == j ){
-            body(ctx->ABCD, (uint32_t*) ctx->block);
+        if (j == 64) {
+            body(ctx->ABCD, (uint32_t *) ctx->block);
             j = 0;
         }
     }
 }
 
-void av_md5_final(AVMD5 *ctx, uint8_t *dst){
+void av_md5_final(AVMD5 *ctx, uint8_t *dst)
+{
     int i;
-    uint64_t finalcount= av_le2ne64(ctx->len<<3);
+    uint64_t finalcount = av_le2ne64(ctx->len << 3);
 
     av_md5_update(ctx, "\200", 1);
-    while((ctx->len & 63)!=56)
+    while ((ctx->len & 63) != 56)
         av_md5_update(ctx, "", 1);
 
-    av_md5_update(ctx, (uint8_t*)&finalcount, 8);
+    av_md5_update(ctx, (uint8_t *)&finalcount, 8);
 
-    for(i=0; i<4; i++)
-        ((uint32_t*)dst)[i]= av_le2ne32(ctx->ABCD[3-i]);
+    for (i = 0; i < 4; i++)
+        AV_WL32(dst + 4*i, ctx->ABCD[3 - i]);
 }
 
-void av_md5_sum(uint8_t *dst, const uint8_t *src, const int len){
-    AVMD5 ctx[1];
+void av_md5_sum(uint8_t *dst, const uint8_t *src, const int len)
+{
+    AVMD5 ctx;
 
-    av_md5_init(ctx);
-    av_md5_update(ctx, src, len);
-    av_md5_final(ctx, dst);
+    av_md5_init(&ctx);
+    av_md5_update(&ctx, src, len);
+    av_md5_final(&ctx, dst);
 }
 
 #ifdef TEST
-#include <stdio.h>
-#include <inttypes.h>
 #undef printf
+#include <stdio.h>
+
+static void print_md5(uint8_t *md5)
+{
+    int i;
+    for (i = 0; i < 16; i++)
+        printf("%02x", md5[i]);
+    printf("\n");
+}
+
 int main(void){
-    uint64_t md5val;
+    uint8_t md5val[16];
     int i;
     uint8_t in[1000];
 
-    for(i=0; i<1000; i++) in[i]= i*i;
-    av_md5_sum( (uint8_t*)&md5val, in,  1000); printf("%"PRId64"\n", md5val);
-    av_md5_sum( (uint8_t*)&md5val, in,  63); printf("%"PRId64"\n", md5val);
-    av_md5_sum( (uint8_t*)&md5val, in,  64); printf("%"PRId64"\n", md5val);
-    av_md5_sum( (uint8_t*)&md5val, in,  65); printf("%"PRId64"\n", md5val);
-    for(i=0; i<1000; i++) in[i]= i % 127;
-    av_md5_sum( (uint8_t*)&md5val, in,  999); printf("%"PRId64"\n", md5val);
+    for (i = 0; i < 1000; i++)
+        in[i] = i * i;
+    av_md5_sum(md5val, in, 1000); print_md5(md5val);
+    av_md5_sum(md5val, in,   63); print_md5(md5val);
+    av_md5_sum(md5val, in,   64); print_md5(md5val);
+    av_md5_sum(md5val, in,   65); print_md5(md5val);
+    for (i = 0; i < 1000; i++)
+        in[i] = i % 127;
+    av_md5_sum(md5val, in,  999); print_md5(md5val);
 
     return 0;
 }