qsv: adding hevc10 support starting from KBL platform

1 files changed, 149 insertions, 0 deletions

diff --git a/contrib/ffmpeg/A05-p10-output-support.patch b/contrib/ffmpeg/A05-p10-output-support.patch
new file mode 100644
index 000000000..5656cfc46
--- /dev/null
+++ b/contrib/ffmpeg/A05-p10-output-support.patch
@@ -0,0 +1,149 @@
+diff -Naur ./libav-12.org/libswscale/output.c ./libav-12/libswscale/output.c
+--- ./libav-12.org/libswscale/output.c	2016-10-16 23:10:02.000000000 +0200
++++ ./libav-12/libswscale/output.c	2017-02-07 23:37:28.150180400 +0100
+@@ -295,6 +295,98 @@
+         }
+ }
+ 
++
++#define output_pixel(pos, val) \
++    if (big_endian) { \
++        AV_WB16(pos, av_clip_uintp2(val >> shift, 10) << 6); \
++    } else { \
++        AV_WL16(pos, av_clip_uintp2(val >> shift, 10) << 6); \
++    }
++
++static void yuv2p010l1_c(const int16_t *src,
++                         uint16_t *dest, int dstW,
++                         int big_endian)
++{
++    int i;
++    int shift = 5;
++
++    for (i = 0; i < dstW; i++) {
++        int val = src[i] + (1 << (shift - 1));
++        output_pixel(&dest[i], val);
++    }
++}
++
++static void yuv2p010lX_c(const int16_t *filter, int filterSize,
++                         const int16_t **src, uint16_t *dest, int dstW,
++                         int big_endian)
++{
++    int i, j;
++    int shift = 17;
++
++    for (i = 0; i < dstW; i++) {
++        int val = 1 << (shift - 1);
++
++        for (j = 0; j < filterSize; j++)
++            val += src[j][i] * filter[j];
++
++        output_pixel(&dest[i], val);
++    }
++}
++
++static void yuv2p010cX_c(SwsContext *c, const int16_t *chrFilter, int chrFilterSize,
++                         const int16_t **chrUSrc, const int16_t **chrVSrc,
++                         uint8_t *dest8, int chrDstW)
++{
++    uint16_t *dest = (uint16_t*)dest8;
++    int shift = 17;
++    int big_endian = c->dstFormat == AV_PIX_FMT_P010BE;
++    int i, j;
++
++    for (i = 0; i < chrDstW; i++) {
++        int u = 1 << (shift - 1);
++        int v = 1 << (shift - 1);
++
++        for (j = 0; j < chrFilterSize; j++) {
++            u += chrUSrc[j][i] * chrFilter[j];
++            v += chrVSrc[j][i] * chrFilter[j];
++        }
++
++        output_pixel(&dest[2*i]  , u);
++        output_pixel(&dest[2*i+1], v);
++    }
++}
++
++static void yuv2p010l1_LE_c(const int16_t *src,
++                            uint8_t *dest, int dstW,
++                            const uint8_t *dither, int offset)
++{
++    yuv2p010l1_c(src, (uint16_t*)dest, dstW, 0);
++}
++
++static void yuv2p010l1_BE_c(const int16_t *src,
++                            uint8_t *dest, int dstW,
++                            const uint8_t *dither, int offset)
++{
++    yuv2p010l1_c(src, (uint16_t*)dest, dstW, 1);
++}
++
++static void yuv2p010lX_LE_c(const int16_t *filter, int filterSize,
++                            const int16_t **src, uint8_t *dest, int dstW,
++                            const uint8_t *dither, int offset)
++{
++    yuv2p010lX_c(filter, filterSize, src, (uint16_t*)dest, dstW, 0);
++}
++
++static void yuv2p010lX_BE_c(const int16_t *filter, int filterSize,
++                            const int16_t **src, uint8_t *dest, int dstW,
++                            const uint8_t *dither, int offset)
++{
++    yuv2p010lX_c(filter, filterSize, src, (uint16_t*)dest, dstW, 1);
++}
++
++#undef output_pixel
++
++
+ #define accumulate_bit(acc, val) \
+     acc <<= 1; \
+     acc |= (val) >= (128 + 110)
+@@ -1361,7 +1453,11 @@
+     enum AVPixelFormat dstFormat = c->dstFormat;
+     const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(dstFormat);
+ 
+-    if (is16BPS(dstFormat)) {
++    if (dstFormat == AV_PIX_FMT_P010LE || dstFormat == AV_PIX_FMT_P010BE) {
++        *yuv2plane1 = isBE(dstFormat) ? yuv2p010l1_BE_c : yuv2p010l1_LE_c;
++        *yuv2planeX = isBE(dstFormat) ? yuv2p010lX_BE_c : yuv2p010lX_LE_c;
++        *yuv2nv12cX = yuv2p010cX_c;
++    } else if (is16BPS(dstFormat)) {
+         *yuv2planeX = isBE(dstFormat) ? yuv2planeX_16BE_c  : yuv2planeX_16LE_c;
+         *yuv2plane1 = isBE(dstFormat) ? yuv2plane1_16BE_c  : yuv2plane1_16LE_c;
+     } else if (is9_OR_10BPS(dstFormat)) {
+diff -Naur ./libav-12.org/libswscale/utils.c ./libav-12/libswscale/utils.c
+--- ./libav-12.org/libswscale/utils.c	2016-10-16 23:10:02.000000000 +0200
++++ ./libav-12/libswscale/utils.c	2017-02-07 23:20:09.617945500 +0100
+@@ -185,8 +185,8 @@
+     [AV_PIX_FMT_GBRAP16BE]   = { 1, 0 },
+     [AV_PIX_FMT_XYZ12BE]     = { 0, 0, 1 },
+     [AV_PIX_FMT_XYZ12LE]     = { 0, 0, 1 },
+-    [AV_PIX_FMT_P010LE]      = { 1, 0 },
+-    [AV_PIX_FMT_P010BE]      = { 1, 0 },
++    [AV_PIX_FMT_P010LE]      = { 1, 1 },
++    [AV_PIX_FMT_P010BE]      = { 1, 1 },
+ };
+ 
+ int sws_isSupportedInput(enum AVPixelFormat pix_fmt)
+diff -Naur ./libav-12.org/libswscale/x86/swscale.c ./libav-12/libswscale/x86/swscale.c
+--- ./libav-12.org/libswscale/x86/swscale.c	2016-10-16 23:10:02.000000000 +0200
++++ ./libav-12/libswscale/x86/swscale.c	2017-02-07 23:15:14.000000000 +0100
+@@ -338,14 +338,14 @@
+ #define ASSIGN_VSCALEX_FUNC(vscalefn, opt, do_16_case, condition_8bit) \
+ switch(c->dstBpc){ \
+     case 16:                          do_16_case;                          break; \
+-    case 10: if (!isBE(c->dstFormat)) vscalefn = ff_yuv2planeX_10_ ## opt; break; \
++    case 10: if (!isBE(c->dstFormat) && c->dstFormat != AV_PIX_FMT_P010LE) vscalefn = ff_yuv2planeX_10_ ## opt; break; \
+     case 9:  if (!isBE(c->dstFormat)) vscalefn = ff_yuv2planeX_9_  ## opt; break; \
+     default: if (condition_8bit)      vscalefn = ff_yuv2planeX_8_  ## opt; break; \
+     }
+ #define ASSIGN_VSCALE_FUNC(vscalefn, opt1, opt2, opt2chk) \
+     switch(c->dstBpc){ \
+     case 16: if (!isBE(c->dstFormat))            vscalefn = ff_yuv2plane1_16_ ## opt1; break; \
+-    case 10: if (!isBE(c->dstFormat) && opt2chk) vscalefn = ff_yuv2plane1_10_ ## opt2; break; \
++    case 10: if (!isBE(c->dstFormat) && c->dstFormat != AV_PIX_FMT_P010LE && opt2chk) vscalefn = ff_yuv2plane1_10_ ## opt2; break; \
+     case 9:  if (!isBE(c->dstFormat) && opt2chk) vscalefn = ff_yuv2plane1_9_  ## opt2;  break; \
+     default:                                     vscalefn = ff_yuv2plane1_8_  ## opt1;  break; \
+     }