Merge remote-tracking branch 'qatar/master'

* qatar/master:
  v410dec: Implement explode mode support
  zerocodec: fix direct rendering.
  wav: init st to NULL to avoid a false-positive warning.
  wavpack: set bits_per_raw_sample for S32 samples to properly identify 24-bit
  h264: refactor NAL decode loop
  RTMPTE protocol support
  RTMPE protocol support
  rtmp: Add ff_rtmp_calc_digest_pos()
  rtmp: Rename rtmp_calc_digest to ff_rtmp_calc_digest and make it global
  swscale: add missing HAVE_INLINE_ASM check.
  lavfi: place x86 inline assembly under HAVE_INLINE_ASM.
  vc1: Add a test for interlaced field pictures
  swscale: Mark all init functions as av_cold
  swscale: x86: Drop pointless _mmx suffix from filenames
  lavf: use conditional notation for default codec in muxer declarations.
  swscale: place inline assembly bilinear scaler under HAVE_INLINE_ASM.
  dsputil: ppc: cosmetics: pretty-print
  dsputil: x86: add SHUFFLE_MASK_W macro
  configure: respect CC_O setting in check_cc

Conflicts:
	Changelog
	configure
	libavcodec/v410dec.c
	libavcodec/zerocodec.c
	libavformat/asfenc.c
	libavformat/version.h
	libswscale/utils.c
	libswscale/x86/swscale.c

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

5 files changed, 97 insertions, 82 deletions

diff --git a/libavcodec/h264.c b/libavcodec/h264.c
index 0d3289458a..fdfc221ccd 100644
--- a/libavcodec/h264.c
+++ b/libavcodec/h264.c
@@ -188,42 +188,50 @@ const uint8_t *ff_h264_decode_nal(H264Context *h, const uint8_t *src,
     src++;
     length--;
 
+#define STARTCODE_TEST                                                  \
+        if (i + 2 < length && src[i + 1] == 0 && src[i + 2] <= 3) {     \
+            if (src[i + 2] != 3) {                                      \
+                /* startcode, so we must be past the end */             \
+                length = i;                                             \
+            }                                                           \
+            break;                                                      \
+        }
 #if HAVE_FAST_UNALIGNED
+#define FIND_FIRST_ZERO                                                 \
+        if (i > 0 && !src[i])                                           \
+            i--;                                                        \
+        while (src[i])                                                  \
+            i++
 #if HAVE_FAST_64BIT
-#define RS 7
     for (i = 0; i + 1 < length; i += 9) {
         if (!((~AV_RN64A(src + i) &
                (AV_RN64A(src + i) - 0x0100010001000101ULL)) &
               0x8000800080008080ULL))
+            continue;
+        FIND_FIRST_ZERO;
+        STARTCODE_TEST;
+        i -= 7;
+    }
 #else
-#define RS 3
     for (i = 0; i + 1 < length; i += 5) {
         if (!((~AV_RN32A(src + i) &
                (AV_RN32A(src + i) - 0x01000101U)) &
               0x80008080U))
-#endif
             continue;
-        if (i > 0 && !src[i])
-            i--;
-        while (src[i])
-            i++;
+        FIND_FIRST_ZERO;
+        STARTCODE_TEST;
+        i -= 3;
+    }
+#endif
 #else
-#define RS 0
     for (i = 0; i + 1 < length; i += 2) {
         if (src[i])
             continue;
         if (i > 0 && src[i - 1] == 0)
             i--;
-#endif
-        if (i + 2 < length && src[i + 1] == 0 && src[i + 2] <= 3) {
-            if (src[i + 2] != 3) {
-                /* startcode, so we must be past the end */
-                length = i;
-            }
-            break;
-        }
-        i -= RS;
+        STARTCODE_TEST;
     }
+#endif
 
     // use second escape buffer for inter data
     bufidx = h->nal_unit_type == NAL_DPC ? 1 : 0;
diff --git a/libavcodec/ppc/fmtconvert_altivec.c b/libavcodec/ppc/fmtconvert_altivec.c
index 6f24199023..1e1a3b6865 100644
--- a/libavcodec/ppc/fmtconvert_altivec.c
+++ b/libavcodec/ppc/fmtconvert_altivec.c
@@ -23,7 +23,8 @@
 #include "libavutil/ppc/util_altivec.h"
 #include "dsputil_altivec.h"
 
-static void int32_to_float_fmul_scalar_altivec(float *dst, const int *src, float mul, int len)
+static void int32_to_float_fmul_scalar_altivec(float *dst, const int *src,
+                                               float mul, int len)
 {
     union {
         vector float v;
@@ -36,7 +37,7 @@ static void int32_to_float_fmul_scalar_altivec(float *dst, const int *src, float
     mul_u.s[0] = mul;
     mul_v = vec_splat(mul_u.v, 0);
 
-    for(i=0; i<len; i+=8) {
+    for (i = 0; i < len; i += 8) {
         src1 = vec_ctf(vec_ld(0,  src+i), 0);
         src2 = vec_ctf(vec_ld(16, src+i), 0);
         dst1 = vec_madd(src1, mul_v, zero);
@@ -47,8 +48,7 @@ static void int32_to_float_fmul_scalar_altivec(float *dst, const int *src, float
 }
 
 
-static vector signed short
-float_to_int16_one_altivec(const float *src)
+static vector signed short float_to_int16_one_altivec(const float *src)
 {
     vector float s0 = vec_ld(0, src);
     vector float s1 = vec_ld(16, src);
@@ -62,80 +62,82 @@ static void float_to_int16_altivec(int16_t *dst, const float *src, long len)
     int i;
     vector signed short d0, d1, d;
     vector unsigned char align;
-    if(((long)dst)&15) //FIXME
-    for(i=0; i<len-7; i+=8) {
-        d0 = vec_ld(0, dst+i);
-        d = float_to_int16_one_altivec(src+i);
-        d1 = vec_ld(15, dst+i);
-        d1 = vec_perm(d1, d0, vec_lvsl(0,dst+i));
-        align = vec_lvsr(0, dst+i);
-        d0 = vec_perm(d1, d, align);
-        d1 = vec_perm(d, d1, align);
-        vec_st(d0, 0, dst+i);
-        vec_st(d1,15, dst+i);
-    }
-    else
-    for(i=0; i<len-7; i+=8) {
-        d = float_to_int16_one_altivec(src+i);
-        vec_st(d, 0, dst+i);
+    if (((long)dst) & 15) { //FIXME
+        for (i = 0; i < len - 7; i += 8) {
+            d0 = vec_ld(0, dst+i);
+            d  = float_to_int16_one_altivec(src + i);
+            d1 = vec_ld(15, dst+i);
+            d1 = vec_perm(d1, d0, vec_lvsl(0, dst + i));
+            align = vec_lvsr(0, dst + i);
+            d0 = vec_perm(d1, d, align);
+            d1 = vec_perm(d, d1, align);
+            vec_st(d0,  0, dst + i);
+            vec_st(d1, 15, dst + i);
+        }
+    } else {
+        for (i = 0; i < len - 7; i += 8) {
+            d = float_to_int16_one_altivec(src + i);
+            vec_st(d, 0, dst + i);
+        }
     }
 }
 
-static void
-float_to_int16_interleave_altivec(int16_t *dst, const float **src,
-                                  long len, int channels)
+static void float_to_int16_interleave_altivec(int16_t *dst, const float **src,
+                                              long len, int channels)
 {
     int i;
     vector signed short d0, d1, d2, c0, c1, t0, t1;
     vector unsigned char align;
-    if(channels == 1)
+
+    if (channels == 1)
         float_to_int16_altivec(dst, src[0], len);
-    else
+    else {
         if (channels == 2) {
-        if(((long)dst)&15)
-        for(i=0; i<len-7; i+=8) {
-            d0 = vec_ld(0, dst + i);
-            t0 = float_to_int16_one_altivec(src[0] + i);
-            d1 = vec_ld(31, dst + i);
-            t1 = float_to_int16_one_altivec(src[1] + i);
-            c0 = vec_mergeh(t0, t1);
-            c1 = vec_mergel(t0, t1);
-            d2 = vec_perm(d1, d0, vec_lvsl(0, dst + i));
-            align = vec_lvsr(0, dst + i);
-            d0 = vec_perm(d2, c0, align);
-            d1 = vec_perm(c0, c1, align);
-            vec_st(d0,  0, dst + i);
-            d0 = vec_perm(c1, d2, align);
-            vec_st(d1, 15, dst + i);
-            vec_st(d0, 31, dst + i);
-            dst+=8;
-        }
-        else
-        for(i=0; i<len-7; i+=8) {
-            t0 = float_to_int16_one_altivec(src[0] + i);
-            t1 = float_to_int16_one_altivec(src[1] + i);
-            d0 = vec_mergeh(t0, t1);
-            d1 = vec_mergel(t0, t1);
-            vec_st(d0,  0, dst + i);
-            vec_st(d1, 16, dst + i);
-            dst+=8;
-        }
-    } else {
-        DECLARE_ALIGNED(16, int16_t, tmp)[len];
-        int c, j;
-        for (c = 0; c < channels; c++) {
-            float_to_int16_altivec(tmp, src[c], len);
-            for (i = 0, j = c; i < len; i++, j+=channels) {
-                dst[j] = tmp[i];
+            if (((long)dst) & 15) {
+                for (i = 0; i < len - 7; i += 8) {
+                    d0 = vec_ld(0,  dst + i);
+                    t0 = float_to_int16_one_altivec(src[0] + i);
+                    d1 = vec_ld(31, dst + i);
+                    t1 = float_to_int16_one_altivec(src[1] + i);
+                    c0 = vec_mergeh(t0, t1);
+                    c1 = vec_mergel(t0, t1);
+                    d2 = vec_perm(d1, d0, vec_lvsl(0, dst + i));
+                    align = vec_lvsr(0, dst + i);
+                    d0 = vec_perm(d2, c0, align);
+                    d1 = vec_perm(c0, c1, align);
+                    vec_st(d0,  0, dst + i);
+                    d0 = vec_perm(c1, d2, align);
+                    vec_st(d1, 15, dst + i);
+                    vec_st(d0, 31, dst + i);
+                    dst += 8;
+                }
+            } else {
+                for (i = 0; i < len - 7; i += 8) {
+                    t0 = float_to_int16_one_altivec(src[0] + i);
+                    t1 = float_to_int16_one_altivec(src[1] + i);
+                    d0 = vec_mergeh(t0, t1);
+                    d1 = vec_mergel(t0, t1);
+                    vec_st(d0,  0, dst + i);
+                    vec_st(d1, 16, dst + i);
+                    dst += 8;
+                }
+            }
+        } else {
+            DECLARE_ALIGNED(16, int16_t, tmp)[len];
+            int c, j;
+            for (c = 0; c < channels; c++) {
+                float_to_int16_altivec(tmp, src[c], len);
+                for (i = 0, j = c; i < len; i++, j+=channels)
+                    dst[j] = tmp[i];
             }
         }
-   }
+    }
 }
 
 void ff_fmt_convert_init_altivec(FmtConvertContext *c, AVCodecContext *avctx)
 {
     c->int32_to_float_fmul_scalar = int32_to_float_fmul_scalar_altivec;
-    if(!(avctx->flags & CODEC_FLAG_BITEXACT)) {
+    if (!(avctx->flags & CODEC_FLAG_BITEXACT)) {
         c->float_to_int16 = float_to_int16_altivec;
         c->float_to_int16_interleave = float_to_int16_interleave_altivec;
     }
diff --git a/libavcodec/v410dec.c b/libavcodec/v410dec.c
index 10d73057af..34e397979c 100644
--- a/libavcodec/v410dec.c
+++ b/libavcodec/v410dec.c
@@ -29,7 +29,12 @@ static av_cold int v410_decode_init(AVCodecContext *avctx)
     avctx->bits_per_raw_sample = 10;
 
     if (avctx->width & 1) {
-        av_log(avctx, AV_LOG_WARNING, "v410 requires width to be even.\n");
+        if (avctx->err_recognition & AV_EF_EXPLODE) {
+            av_log(avctx, AV_LOG_ERROR, "v410 requires width to be even, continuing anyway.\n");
+            return AVERROR_INVALIDDATA;
+        } else {
+            av_log(avctx, AV_LOG_WARNING, "v410 requires width to be even.\n");
+        }
     }
 
     avctx->coded_frame = avcodec_alloc_frame();
diff --git a/libavcodec/x86/dsputil_yasm.asm b/libavcodec/x86/dsputil_yasm.asm
index 2c3b6cc2bb..d2e5439e61 100644
--- a/libavcodec/x86/dsputil_yasm.asm
+++ b/libavcodec/x86/dsputil_yasm.asm
@@ -28,7 +28,7 @@ pb_zzzzzzzz77777777: times 8 db -1
 pb_7: times 8 db 7
 pb_zzzz3333zzzzbbbb: db -1,-1,-1,-1,3,3,3,3,-1,-1,-1,-1,11,11,11,11
 pb_zz11zz55zz99zzdd: db -1,-1,1,1,-1,-1,5,5,-1,-1,9,9,-1,-1,13,13
-pb_revwords: db 14, 15, 12, 13, 10, 11, 8, 9, 6, 7, 4, 5, 2, 3, 0, 1
+pb_revwords: SHUFFLE_MASK_W 7, 6, 5, 4, 3, 2, 1, 0
 pd_16384: times 4 dd 16384
 pb_bswap32: db 3, 2, 1, 0, 7, 6, 5, 4, 11, 10, 9, 8, 15, 14, 13, 12
 
diff --git a/libavcodec/zerocodec.c b/libavcodec/zerocodec.c
index 1b1f0be8fa..6581706765 100644
--- a/libavcodec/zerocodec.c
+++ b/libavcodec/zerocodec.c
@@ -94,7 +94,7 @@ static int zerocodec_decode_frame(AVCodecContext *avctx, void *data,
     if (prev_pic->data[0])
         avctx->release_buffer(avctx, prev_pic);
 
-    *data_size = sizeof(AVFrame);
+    *data_size       = sizeof(AVFrame);
     *(AVFrame *)data = *pic;
 
     /* Store the previous frame for use later.