Merge remote-tracking branch 'qatar/master'

* qatar/master:
  libx264: fix indentation.
  vorbis: fix overflows in floor1[] vector and inverse db table index.
  win64: add a XMM clobber test configure option.
  movdec: Parse the dvc1 atom
  ARM: ac3: fix ac3_bit_alloc_calc_bap_armv6
  swscale: K&R formatting cosmetics for Blackfin code
  frwu: lowercase the FRWU codec name
  movdec: fix dts generation in fragmented files
  fate: make acodec-ac3_fixed test output raw AC3
  APIchanges: add missing commit hashes
  swscale: implement MMX, SSE2 and AVX functions for RGB32 input.
  ra144enc: drop pointless "encoder" from .long_name
  bethsoftvideo: fix palette reading.
  mpc7: use av_fast_padded_malloc()
  mpc7: simplify handling of packet sizes that are not a multiple of 4 bytes
  doc: decoding Forward Uncompressed is supported
  Fix a typo in the x86 asm version of ff_vector_clip_int32()
  pcmenc: Do not set avpkt->size.
  ff_alloc_packet: modify the size of the packet to match the requested size

Conflicts:
	doc/APIchanges
	libavcodec/libx264.c
	libavcodec/mpc7.c
	libavformat/isom.h
	libswscale/Makefile
	libswscale/bfin/yuv2rgb_bfin.c
	tests/ref/fate/bethsoft-vid
	tests/ref/seek/ac3_ac3

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

3 files changed, 77 insertions, 72 deletions

diff --git a/libswscale/bfin/internal_bfin.S b/libswscale/bfin/internal_bfin.S
index cb8d71253c..eab30aa6ce 100644
--- a/libswscale/bfin/internal_bfin.S
+++ b/libswscale/bfin/internal_bfin.S
@@ -30,11 +30,11 @@ and converts it to RGB565. R:5 bits, G:6 bits, B:5 bits.. packed into shorts.
 
 The following calculation is used for the conversion:
 
-  r = clipz((y-oy)*cy  + crv*(v-128))
-  g = clipz((y-oy)*cy  + cgv*(v-128) + cgu*(u-128))
-  b = clipz((y-oy)*cy  + cbu*(u-128))
+  r = clipz((y - oy) * cy  + crv * (v - 128))
+  g = clipz((y - oy) * cy  + cgv * (v - 128) + cgu * (u - 128))
+  b = clipz((y - oy) * cy  + cbu * (u - 128))
 
-y,u,v are prescaled by a factor of 4 i.e. left-shifted to gain precision.
+y, u, v are prescaled by a factor of 4 i.e. left-shifted to gain precision.
 
 
 New factorization to eliminate the truncation error which was
@@ -47,7 +47,7 @@ occurring due to the byteop3p.
 2) Scale operands up by a factor of 4 not 8 because Blackfin
    multiplies include a shift.
 
-3) Compute into the accumulators cy*yx0, cy*yx1.
+3) Compute into the accumulators cy * yx0, cy * yx1.
 
 4) Compute each of the linear equations:
      r = clipz((y - oy) * cy  + crv * (v - 128))
@@ -73,7 +73,7 @@ occurring due to the byteop3p.
 
 Where coeffs have the following layout in memory.
 
-uint32_t oy,oc,zero,cy,crv,rmask,cbu,bmask,cgu,cgv;
+uint32_t oy, oc, zero, cy, crv, rmask, cbu, bmask, cgu, cgv;
 
 coeffs is a pointer to oy.
 
diff --git a/libswscale/bfin/swscale_bfin.c b/libswscale/bfin/swscale_bfin.c
index 870636ea05..3cd4f28387 100644
--- a/libswscale/bfin/swscale_bfin.c
+++ b/libswscale/bfin/swscale_bfin.c
@@ -27,32 +27,34 @@
 #include <assert.h>
 #include "config.h"
 #include <unistd.h>
+
 #include "libswscale/rgb2rgb.h"
 #include "libswscale/swscale.h"
 #include "libswscale/swscale_internal.h"
 
 #if defined (__FDPIC__) && CONFIG_SRAM
-#define L1CODE __attribute__ ((l1_text))
+#define L1CODE __attribute__((l1_text))
 #else
 #define L1CODE
 #endif
 
-int ff_bfin_uyvytoyv12(const uint8_t *src, uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
-                       int width, int height,
+int ff_bfin_uyvytoyv12(const uint8_t *src, uint8_t *ydst, uint8_t *udst,
+                       uint8_t *vdst, int width, int height,
                        int lumStride, int chromStride, int srcStride) L1CODE;
 
-int ff_bfin_yuyvtoyv12(const uint8_t *src, uint8_t *ydst, uint8_t *udst, uint8_t *vdst,
-                       int width, int height,
+int ff_bfin_yuyvtoyv12(const uint8_t *src, uint8_t *ydst, uint8_t *udst,
+                       uint8_t *vdst, int width, int height,
                        int lumStride, int chromStride, int srcStride) L1CODE;
 
-static int uyvytoyv12_unscaled(SwsContext *c, uint8_t* src[], int srcStride[], int srcSliceY,
-                               int srcSliceH, uint8_t* dst[], int dstStride[])
+static int uyvytoyv12_unscaled(SwsContext *c, uint8_t *src[], int srcStride[],
+                               int srcSliceY, int srcSliceH, uint8_t *dst[],
+                               int dstStride[])
 {
-    uint8_t *dsty = dst[0] + dstStride[0]*srcSliceY;
-    uint8_t *dstu = dst[1] + dstStride[1]*srcSliceY/2;
-    uint8_t *dstv = dst[2] + dstStride[2]*srcSliceY/2;
-    uint8_t *ip   = src[0] + srcStride[0]*srcSliceY;
-    int w         = dstStride[0];
+    uint8_t *dsty = dst[0] + dstStride[0] * srcSliceY;
+    uint8_t *dstu = dst[1] + dstStride[1] * srcSliceY / 2;
+    uint8_t *dstv = dst[2] + dstStride[2] * srcSliceY / 2;
+    uint8_t *ip   = src[0] + srcStride[0] * srcSliceY;
+    int w = dstStride[0];
 
     ff_bfin_uyvytoyv12(ip, dsty, dstu, dstv, w, srcSliceH,
                        dstStride[0], dstStride[1], srcStride[0]);
@@ -60,14 +62,15 @@ static int uyvytoyv12_unscaled(SwsContext *c, uint8_t* src[], int srcStride[], i
     return srcSliceH;
 }
 
-static int yuyvtoyv12_unscaled(SwsContext *c, uint8_t* src[], int srcStride[], int srcSliceY,
-                               int srcSliceH, uint8_t* dst[], int dstStride[])
+static int yuyvtoyv12_unscaled(SwsContext *c, uint8_t *src[], int srcStride[],
+                               int srcSliceY, int srcSliceH, uint8_t *dst[],
+                               int dstStride[])
 {
-    uint8_t *dsty = dst[0] + dstStride[0]*srcSliceY;
-    uint8_t *dstu = dst[1] + dstStride[1]*srcSliceY/2;
-    uint8_t *dstv = dst[2] + dstStride[2]*srcSliceY/2;
-    uint8_t *ip   = src[0] + srcStride[0]*srcSliceY;
-    int w         = dstStride[0];
+    uint8_t *dsty = dst[0] + dstStride[0] * srcSliceY;
+    uint8_t *dstu = dst[1] + dstStride[1] * srcSliceY / 2;
+    uint8_t *dstv = dst[2] + dstStride[2] * srcSliceY / 2;
+    uint8_t *ip   = src[0] + srcStride[0] * srcSliceY;
+    int w = dstStride[0];
 
     ff_bfin_yuyvtoyv12(ip, dsty, dstu, dstv, w, srcSliceH,
                        dstStride[0], dstStride[1], srcStride[0]);
@@ -75,15 +78,16 @@ static int yuyvtoyv12_unscaled(SwsContext *c, uint8_t* src[], int srcStride[], i
     return srcSliceH;
 }
 
-
 void ff_bfin_get_unscaled_swscale(SwsContext *c)
 {
     if (c->dstFormat == PIX_FMT_YUV420P && c->srcFormat == PIX_FMT_UYVY422) {
-        av_log (NULL, AV_LOG_VERBOSE, "selecting Blackfin optimized uyvytoyv12_unscaled\n");
+        av_log(NULL, AV_LOG_VERBOSE,
+               "selecting Blackfin optimized uyvytoyv12_unscaled\n");
         c->swScale = uyvytoyv12_unscaled;
     }
     if (c->dstFormat == PIX_FMT_YUV420P && c->srcFormat == PIX_FMT_YUYV422) {
-        av_log (NULL, AV_LOG_VERBOSE, "selecting Blackfin optimized yuyvtoyv12_unscaled\n");
+        av_log(NULL, AV_LOG_VERBOSE,
+               "selecting Blackfin optimized yuyvtoyv12_unscaled\n");
         c->swScale = yuyvtoyv12_unscaled;
     }
 }
diff --git a/libswscale/bfin/yuv2rgb_bfin.c b/libswscale/bfin/yuv2rgb_bfin.c
index 7a7dc7f0e6..e7f657fe00 100644
--- a/libswscale/bfin/yuv2rgb_bfin.c
+++ b/libswscale/bfin/yuv2rgb_bfin.c
@@ -26,15 +26,16 @@
 #include <string.h>
 #include <inttypes.h>
 #include <assert.h>
-#include "config.h"
 #include <unistd.h>
 #include "libavutil/pixdesc.h"
+
+#include "config.h"
 #include "libswscale/rgb2rgb.h"
 #include "libswscale/swscale.h"
 #include "libswscale/swscale_internal.h"
 
 #if defined(__FDPIC__) && CONFIG_SRAM
-#define L1CODE __attribute__ ((l1_text))
+#define L1CODE __attribute__((l1_text))
 #else
 #define L1CODE
 #endif
@@ -48,21 +49,20 @@ void ff_bfin_yuv2rgb565_line(uint8_t *Y, uint8_t *U, uint8_t *V, uint8_t *out,
 void ff_bfin_yuv2rgb24_line(uint8_t *Y, uint8_t *U, uint8_t *V, uint8_t *out,
                             int w, uint32_t *coeffs) L1CODE;
 
-typedef void (* ltransform)(uint8_t *Y, uint8_t *U, uint8_t *V, uint8_t *out,
-                            int w, uint32_t *coeffs);
-
+typedef void (*ltransform)(uint8_t *Y, uint8_t *U, uint8_t *V, uint8_t *out,
+                           int w, uint32_t *coeffs);
 
 static void bfin_prepare_coefficients(SwsContext *c, int rgb, int masks)
 {
     int oy;
-    oy      = c->yOffset&0xffff;
-    oy      = oy >> 3; // keep everything U8.0 for offset calculation
+    oy = c->yOffset & 0xffff;
+    oy = oy >> 3;      // keep everything U8.0 for offset calculation
 
-    c->oc   = 128*0x01010101U;
-    c->oy   =  oy*0x01010101U;
+    c->oc = 128 * 0x01010101U;
+    c->oy = oy * 0x01010101U;
 
     /* copy 64bit vector coeffs down to 32bit vector coeffs */
-    c->cy  = c->yCoeff;
+    c->cy   = c->yCoeff;
     c->zero = 0;
 
     if (rgb) {
@@ -77,7 +77,6 @@ static void bfin_prepare_coefficients(SwsContext *c, int rgb, int masks)
         c->cgv = c->ugCoeff;
     }
 
-
     if (masks == 555) {
         c->rmask = 0x001f * 0x00010001U;
         c->gmask = 0x03e0 * 0x00010001U;
@@ -89,27 +88,25 @@ static void bfin_prepare_coefficients(SwsContext *c, int rgb, int masks)
     }
 }
 
-static int core_yuv420_rgb(SwsContext *c,
-                           uint8_t **in, int *instrides,
-                           int srcSliceY, int srcSliceH,
-                           uint8_t **oplanes, int *outstrides,
-                           ltransform lcscf, int rgb, int masks)
+static int core_yuv420_rgb(SwsContext *c, uint8_t **in, int *instrides,
+                           int srcSliceY, int srcSliceH, uint8_t **oplanes,
+                           int *outstrides, ltransform lcscf,
+                           int rgb, int masks)
 {
-    uint8_t *py,*pu,*pv,*op;
+    uint8_t *py, *pu, *pv, *op;
     int w  = instrides[0];
-    int h2 = srcSliceH>>1;
+    int h2 = srcSliceH >> 1;
     int i;
 
     bfin_prepare_coefficients(c, rgb, masks);
 
     py = in[0];
-    pu = in[1+(1^rgb)];
-    pv = in[1+(0^rgb)];
-
-    op = oplanes[0] + srcSliceY*outstrides[0];
+    pu = in[1 + (1 ^ rgb)];
+    pv = in[1 + (0 ^ rgb)];
 
-    for (i=0;i<h2;i++) {
+    op = oplanes[0] + srcSliceY * outstrides[0];
 
+    for (i = 0; i < h2; i++) {
         lcscf(py, pu, pv, op, w, &c->oy);
 
         py += instrides[0];
@@ -126,9 +123,7 @@ static int core_yuv420_rgb(SwsContext *c,
     return srcSliceH;
 }
 
-
-static int bfin_yuv420_rgb555(SwsContext *c,
-                              uint8_t **in, int *instrides,
+static int bfin_yuv420_rgb555(SwsContext *c, uint8_t **in, int *instrides,
                               int srcSliceY, int srcSliceH,
                               uint8_t **oplanes, int *outstrides)
 {
@@ -136,8 +131,7 @@ static int bfin_yuv420_rgb555(SwsContext *c,
                            outstrides, ff_bfin_yuv2rgb555_line, 1, 555);
 }
 
-static int bfin_yuv420_bgr555(SwsContext *c,
-                              uint8_t **in, int *instrides,
+static int bfin_yuv420_bgr555(SwsContext *c, uint8_t **in, int *instrides,
                               int srcSliceY, int srcSliceH,
                               uint8_t **oplanes, int *outstrides)
 {
@@ -145,8 +139,7 @@ static int bfin_yuv420_bgr555(SwsContext *c,
                            outstrides, ff_bfin_yuv2rgb555_line, 0, 555);
 }
 
-static int bfin_yuv420_rgb24(SwsContext *c,
-                             uint8_t **in, int *instrides,
+static int bfin_yuv420_rgb24(SwsContext *c, uint8_t **in, int *instrides,
                              int srcSliceY, int srcSliceH,
                              uint8_t **oplanes, int *outstrides)
 {
@@ -154,8 +147,7 @@ static int bfin_yuv420_rgb24(SwsContext *c,
                            outstrides, ff_bfin_yuv2rgb24_line, 1, 888);
 }
 
-static int bfin_yuv420_bgr24(SwsContext *c,
-                             uint8_t **in, int *instrides,
+static int bfin_yuv420_bgr24(SwsContext *c, uint8_t **in, int *instrides,
                              int srcSliceY, int srcSliceH,
                              uint8_t **oplanes, int *outstrides)
 {
@@ -163,8 +155,7 @@ static int bfin_yuv420_bgr24(SwsContext *c,
                            outstrides, ff_bfin_yuv2rgb24_line, 0, 888);
 }
 
-static int bfin_yuv420_rgb565(SwsContext *c,
-                              uint8_t **in, int *instrides,
+static int bfin_yuv420_rgb565(SwsContext *c, uint8_t **in, int *instrides,
                               int srcSliceY, int srcSliceH,
                               uint8_t **oplanes, int *outstrides)
 {
@@ -172,8 +163,7 @@ static int bfin_yuv420_rgb565(SwsContext *c,
                            outstrides, ff_bfin_yuv2rgb565_line, 1, 565);
 }
 
-static int bfin_yuv420_bgr565(SwsContext *c,
-                              uint8_t **in, int *instrides,
+static int bfin_yuv420_bgr565(SwsContext *c, uint8_t **in, int *instrides,
                               int srcSliceY, int srcSliceH,
                               uint8_t **oplanes, int *outstrides)
 {
@@ -181,18 +171,29 @@ static int bfin_yuv420_bgr565(SwsContext *c,
                            outstrides, ff_bfin_yuv2rgb565_line, 0, 565);
 }
 
-
 SwsFunc ff_yuv2rgb_get_func_ptr_bfin(SwsContext *c)
 {
     SwsFunc f;
 
-    switch(c->dstFormat) {
-    case PIX_FMT_RGB555: f = bfin_yuv420_rgb555; break;
-    case PIX_FMT_BGR555: f = bfin_yuv420_bgr555; break;
-    case PIX_FMT_RGB565: f = bfin_yuv420_rgb565; break;
-    case PIX_FMT_BGR565: f = bfin_yuv420_bgr565; break;
-    case PIX_FMT_RGB24:  f = bfin_yuv420_rgb24;  break;
-    case PIX_FMT_BGR24:  f = bfin_yuv420_bgr24;  break;
+    switch (c->dstFormat) {
+    case PIX_FMT_RGB555:
+        f = bfin_yuv420_rgb555;
+        break;
+    case PIX_FMT_BGR555:
+        f = bfin_yuv420_bgr555;
+        break;
+    case PIX_FMT_RGB565:
+        f = bfin_yuv420_rgb565;
+        break;
+    case PIX_FMT_BGR565:
+        f = bfin_yuv420_bgr565;
+        break;
+    case PIX_FMT_RGB24:
+        f = bfin_yuv420_rgb24;
+        break;
+    case PIX_FMT_BGR24:
+        f = bfin_yuv420_bgr24;
+        break;
     default:
         return 0;
     }