Merge remote-tracking branch 'qatar/master'

* qatar/master:
  pixfmt: support more yuva formats
  swscale: support gray to 9bit and 10bit formats
  configure: rewrite print_config() function using awk
  FATE: fix (AD)PCM test dependencies broken in e519990
  Use ptrdiff_t instead of int for intra pred "stride" function parameter.
  x86: use PRED4x4/8x8/8x8L/16x16 macros to declare intrapred prototypes.

Conflicts:
	libavcodec/h264pred.c
	libavcodec/h264pred_template.c
	libavutil/pixfmt.h
	libswscale/swscale_unscaled.c
	tests/ref/lavfi/pixdesc
	tests/ref/lavfi/pixfmts_copy
	tests/ref/lavfi/pixfmts_null
	tests/ref/lavfi/pixfmts_scale
	tests/ref/lavfi/pixfmts_vflip

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

4 files changed, 133 insertions, 5 deletions

diff --git a/libswscale/input.c b/libswscale/input.c
index 6d76068f9a..d10b4f1062 100644
--- a/libswscale/input.c
+++ b/libswscale/input.c
@@ -935,6 +935,16 @@ av_cold void ff_sws_init_input_funcs(SwsContext *c)
     case AV_PIX_FMT_YUV420P14LE:
     case AV_PIX_FMT_YUV420P16LE:
     case AV_PIX_FMT_YUV422P16LE:
+
+    case AV_PIX_FMT_YUVA444P9LE:
+    case AV_PIX_FMT_YUVA422P9LE:
+    case AV_PIX_FMT_YUVA420P9LE:
+    case AV_PIX_FMT_YUVA444P10LE:
+    case AV_PIX_FMT_YUVA422P10LE:
+    case AV_PIX_FMT_YUVA420P10LE:
+    case AV_PIX_FMT_YUVA420P16LE:
+    case AV_PIX_FMT_YUVA422P16LE:
+    case AV_PIX_FMT_YUVA444P16LE:
     case AV_PIX_FMT_YUV444P16LE:
         c->chrToYV12 = bswap16UV_c;
         break;
@@ -954,6 +964,16 @@ av_cold void ff_sws_init_input_funcs(SwsContext *c)
     case AV_PIX_FMT_YUV420P16BE:
     case AV_PIX_FMT_YUV422P16BE:
     case AV_PIX_FMT_YUV444P16BE:
+
+    case AV_PIX_FMT_YUVA444P9BE:
+    case AV_PIX_FMT_YUVA422P9BE:
+    case AV_PIX_FMT_YUVA420P9BE:
+    case AV_PIX_FMT_YUVA444P10BE:
+    case AV_PIX_FMT_YUVA422P10BE:
+    case AV_PIX_FMT_YUVA420P10BE:
+    case AV_PIX_FMT_YUVA420P16BE:
+    case AV_PIX_FMT_YUVA422P16BE:
+    case AV_PIX_FMT_YUVA444P16BE:
         c->chrToYV12 = bswap16UV_c;
         break;
 #endif
@@ -1165,6 +1185,16 @@ av_cold void ff_sws_init_input_funcs(SwsContext *c)
     case AV_PIX_FMT_YUV420P16LE:
     case AV_PIX_FMT_YUV422P16LE:
     case AV_PIX_FMT_YUV444P16LE:
+
+    case AV_PIX_FMT_YUVA444P9LE:
+    case AV_PIX_FMT_YUVA422P9LE:
+    case AV_PIX_FMT_YUVA420P9LE:
+    case AV_PIX_FMT_YUVA444P10LE:
+    case AV_PIX_FMT_YUVA422P10LE:
+    case AV_PIX_FMT_YUVA420P10LE:
+    case AV_PIX_FMT_YUVA420P16LE:
+    case AV_PIX_FMT_YUVA422P16LE:
+    case AV_PIX_FMT_YUVA444P16LE:
     case AV_PIX_FMT_GRAY16LE:
         c->lumToYV12 = bswap16Y_c;
         break;
@@ -1184,6 +1214,16 @@ av_cold void ff_sws_init_input_funcs(SwsContext *c)
     case AV_PIX_FMT_YUV420P16BE:
     case AV_PIX_FMT_YUV422P16BE:
     case AV_PIX_FMT_YUV444P16BE:
+
+    case AV_PIX_FMT_YUVA444P9BE:
+    case AV_PIX_FMT_YUVA422P9BE:
+    case AV_PIX_FMT_YUVA420P9BE:
+    case AV_PIX_FMT_YUVA444P10BE:
+    case AV_PIX_FMT_YUVA422P10BE:
+    case AV_PIX_FMT_YUVA420P10BE:
+    case AV_PIX_FMT_YUVA420P16BE:
+    case AV_PIX_FMT_YUVA422P16BE:
+    case AV_PIX_FMT_YUVA444P16BE:
     case AV_PIX_FMT_GRAY16BE:
         c->lumToYV12 = bswap16Y_c;
         break;
diff --git a/libswscale/swscale.c b/libswscale/swscale.c
index 37b7712e22..71fb9899c4 100644
--- a/libswscale/swscale.c
+++ b/libswscale/swscale.c
@@ -62,6 +62,28 @@ static av_always_inline void fillPlane(uint8_t *plane, int stride, int width,
     }
 }
 
+static void fill_plane9or10(uint8_t *plane, int stride, int width,
+                            int height, int y, uint8_t val,
+                            const int dst_depth, const int big_endian)
+{
+    int i, j;
+    uint16_t *dst = (uint16_t *) (plane + stride * y);
+#define FILL8TO9_OR_10(wfunc) \
+    for (i = 0; i < height; i++) { \
+        for (j = 0; j < width; j++) { \
+            wfunc(&dst[j], (val << (dst_depth - 8)) |  \
+                               (val >> (16 - dst_depth))); \
+        } \
+        dst += stride / 2; \
+    }
+    if (big_endian) {
+        FILL8TO9_OR_10(AV_WB16);
+    } else {
+        FILL8TO9_OR_10(AV_WL16);
+    }
+}
+
+
 static void hScale16To19_c(SwsContext *c, int16_t *_dst, int dstW,
                            const uint8_t *_src, const int16_t *filter,
                            const int32_t *filterPos, int filterSize)
@@ -660,8 +682,20 @@ static int swScale(SwsContext *c, const uint8_t *src[],
         }
     }
 
-    if (isPlanar(dstFormat) && isALPHA(dstFormat) && !alpPixBuf)
-        fillPlane(dst[3], dstStride[3], dstW, dstY - lastDstY, lastDstY, 255);
+    if (isPlanar(dstFormat) && isALPHA(dstFormat) && !alpPixBuf) {
+        int length = dstW;
+        int height = dstY - lastDstY;
+        if (is16BPS(c->dstFormat))
+            length *= 2;
+
+        if (is9_OR_10BPS(dstFormat)) {
+            const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(dstFormat);
+            fill_plane9or10(dst[3], dstStride[3], length, height, lastDstY,
+                            255, desc->comp[3].depth_minus1 + 1,
+                            isBE(dstFormat));
+        } else
+            fillPlane(dst[3], dstStride[3], length, height, lastDstY, 255);
+    }
 
 #if HAVE_MMXEXT_INLINE
     if (av_get_cpu_flags() & AV_CPU_FLAG_MMXEXT)
diff --git a/libswscale/swscale_unscaled.c b/libswscale/swscale_unscaled.c
index 0fe974f054..08cc2ed146 100644
--- a/libswscale/swscale_unscaled.c
+++ b/libswscale/swscale_unscaled.c
@@ -140,11 +140,11 @@ static void fillPlane(uint8_t *plane, int stride, int width, int height, int y,
 }
 
 static void fillPlane16(uint8_t *plane, int stride, int width, int height, int y,
-                      int alpha, int bits)
+                      int alpha, int bits, const int big_endian)
 {
     int i, j;
     uint8_t *ptr = plane + stride * y;
-    int v = alpha ? -1 : (1<<bits);
+    int v = alpha ? 0xFFFF>>(15-bits) : (1<<bits);
     for (i = 0; i < height; i++) {
         for (j = 0; j < width; j++) {
             AV_WN16(ptr+2*j, v);
@@ -153,6 +153,27 @@ static void fillPlane16(uint8_t *plane, int stride, int width, int height, int y
     }
 }
 
+static void fill_plane9or10(uint8_t *plane, int stride, int width,
+                            int height, int y, uint8_t val,
+                            const int dst_depth, const int big_endian)
+{
+    int i, j;
+    uint16_t *dst = (uint16_t *) (plane + stride * y);
+#define FILL8TO9_OR_10(wfunc) \
+    for (i = 0; i < height; i++) { \
+        for (j = 0; j < width; j++) { \
+            wfunc(&dst[j], (val << (dst_depth - 8)) |  \
+                               (val >> (16 - dst_depth))); \
+        } \
+        dst += stride / 2; \
+    }
+    if (big_endian) {
+        FILL8TO9_OR_10(AV_WB16);
+    } else {
+        FILL8TO9_OR_10(AV_WL16);
+    }
+}
+
 static void copyPlane(const uint8_t *src, int srcStride,
                       int srcSliceY, int srcSliceH, int width,
                       uint8_t *dst, int dstStride)
@@ -780,13 +801,28 @@ static int planarCopyWrapper(SwsContext *c, const uint8_t *src[],
         // ignore palette for GRAY8
         if (plane == 1 && !dst[2]) continue;
         if (!src[plane] || (plane == 1 && !src[2])) {
+#if 1
             if (is16BPS(c->dstFormat) || isNBPS(c->dstFormat)) {
                 fillPlane16(dst[plane], dstStride[plane], length, height, y,
-                        plane == 3, desc_dst->comp[plane].depth_minus1);
+                        plane == 3, desc_dst->comp[plane].depth_minus1,
+                        isBE(c->dstFormat));
             } else {
                 fillPlane(dst[plane], dstStride[plane], length, height, y,
                         (plane == 3) ? 255 : 128);
             }
+#else
+            int val = (plane == 3) ? 255 : 128;
+            if (is16BPS(c->dstFormat))
+                length *= 2;
+            if (is9_OR_10BPS(c->dstFormat)) {
+                fill_plane9or10(dst[plane], dstStride[plane],
+                                length, height, y, val,
+                                desc_dst->comp[plane].depth_minus1 + 1,
+                                isBE(c->dstFormat));
+            } else
+                fillPlane(dst[plane], dstStride[plane], length, height, y,
+                          val);
+#endif
         } else {
             if(isNBPS(c->srcFormat) || isNBPS(c->dstFormat)
                || (is16BPS(c->srcFormat) != is16BPS(c->dstFormat))
diff --git a/libswscale/utils.c b/libswscale/utils.c
index 21fd718e4c..9ee4e824d1 100644
--- a/libswscale/utils.c
+++ b/libswscale/utils.c
@@ -116,6 +116,24 @@ static const FormatEntry format_entries[AV_PIX_FMT_NB] = {
     [AV_PIX_FMT_YUVA420P]    = { 1, 1 },
     [AV_PIX_FMT_YUVA422P]    = { 1, 1 },
     [AV_PIX_FMT_YUVA444P]    = { 1, 1 },
+    [AV_PIX_FMT_YUVA420P9BE] = { 1, 1 },
+    [AV_PIX_FMT_YUVA420P9LE] = { 1, 1 },
+    [AV_PIX_FMT_YUVA422P9BE] = { 1, 1 },
+    [AV_PIX_FMT_YUVA422P9LE] = { 1, 1 },
+    [AV_PIX_FMT_YUVA444P9BE] = { 1, 1 },
+    [AV_PIX_FMT_YUVA444P9LE] = { 1, 1 },
+    [AV_PIX_FMT_YUVA420P10BE]= { 1, 1 },
+    [AV_PIX_FMT_YUVA420P10LE]= { 1, 1 },
+    [AV_PIX_FMT_YUVA422P10BE]= { 1, 1 },
+    [AV_PIX_FMT_YUVA422P10LE]= { 1, 1 },
+    [AV_PIX_FMT_YUVA444P10BE]= { 1, 1 },
+    [AV_PIX_FMT_YUVA444P10LE]= { 1, 1 },
+    [AV_PIX_FMT_YUVA420P16BE]= { 1, 1 },
+    [AV_PIX_FMT_YUVA420P16LE]= { 1, 1 },
+    [AV_PIX_FMT_YUVA422P16BE]= { 1, 1 },
+    [AV_PIX_FMT_YUVA422P16LE]= { 1, 1 },
+    [AV_PIX_FMT_YUVA444P16BE]= { 1, 1 },
+    [AV_PIX_FMT_YUVA444P16LE]= { 1, 1 },
     [AV_PIX_FMT_RGB48BE]     = { 1, 1 },
     [AV_PIX_FMT_RGB48LE]     = { 1, 1 },
     [AV_PIX_FMT_RGBA64BE]    = { 1, 0 },