swscale: Add support for NV24 and NV42

The implementation is pretty straight-forward. Most of the existing
NV12 codepaths work regardless of subsampling and are re-used as is.
Where necessary I wrote the slightly different NV24 versions.

Finally, the one thing that confused me for a long time was the
asm specific x86 path that did an explicit exclusion check for NV12.
I replaced that with a semi-planar check and also updated the
equivalent PPC code, which Lauri kindly checked.

1 files changed, 51 insertions, 0 deletions

diff --git a/libswscale/swscale_unscaled.c b/libswscale/swscale_unscaled.c
index be04a236d8..e0b9e99373 100644
--- a/libswscale/swscale_unscaled.c
+++ b/libswscale/swscale_unscaled.c
@@ -180,6 +180,47 @@ static int nv12ToPlanarWrapper(SwsContext *c, const uint8_t *src[],
     return srcSliceH;
 }
 
+static int planarToNv24Wrapper(SwsContext *c, const uint8_t *src[],
+                               int srcStride[], int srcSliceY,
+                               int srcSliceH, uint8_t *dstParam[],
+                               int dstStride[])
+{
+    uint8_t *dst = dstParam[1] + dstStride[1] * srcSliceY;
+
+    copyPlane(src[0], srcStride[0], srcSliceY, srcSliceH, c->srcW,
+              dstParam[0], dstStride[0]);
+
+    if (c->dstFormat == AV_PIX_FMT_NV24)
+        interleaveBytes(src[1], src[2], dst, c->chrSrcW, srcSliceH,
+                        srcStride[1], srcStride[2], dstStride[1]);
+    else
+        interleaveBytes(src[2], src[1], dst, c->chrSrcW, srcSliceH,
+                        srcStride[2], srcStride[1], dstStride[1]);
+
+    return srcSliceH;
+}
+
+static int nv24ToPlanarWrapper(SwsContext *c, const uint8_t *src[],
+                               int srcStride[], int srcSliceY,
+                               int srcSliceH, uint8_t *dstParam[],
+                               int dstStride[])
+{
+    uint8_t *dst1 = dstParam[1] + dstStride[1] * srcSliceY;
+    uint8_t *dst2 = dstParam[2] + dstStride[2] * srcSliceY;
+
+    copyPlane(src[0], srcStride[0], srcSliceY, srcSliceH, c->srcW,
+              dstParam[0], dstStride[0]);
+
+    if (c->srcFormat == AV_PIX_FMT_NV24)
+        deinterleaveBytes(src[1], dst1, dst2, c->chrSrcW, srcSliceH,
+                          srcStride[1], dstStride[1], dstStride[2]);
+    else
+        deinterleaveBytes(src[1], dst2, dst1, c->chrSrcW, srcSliceH,
+                          srcStride[1], dstStride[2], dstStride[1]);
+
+    return srcSliceH;
+}
+
 static int planarToP01xWrapper(SwsContext *c, const uint8_t *src8[],
                                int srcStride[], int srcSliceY,
                                int srcSliceH, uint8_t *dstParam8[],
@@ -1872,11 +1913,21 @@ void ff_get_unscaled_swscale(SwsContext *c)
         (dstFormat == AV_PIX_FMT_NV12 || dstFormat == AV_PIX_FMT_NV21)) {
         c->swscale = planarToNv12Wrapper;
     }
+    /* yv24_to_nv24 */
+    if ((srcFormat == AV_PIX_FMT_YUV444P || srcFormat == AV_PIX_FMT_YUVA444P) &&
+        (dstFormat == AV_PIX_FMT_NV24 || dstFormat == AV_PIX_FMT_NV42)) {
+        c->swscale = planarToNv24Wrapper;
+    }
     /* nv12_to_yv12 */
     if (dstFormat == AV_PIX_FMT_YUV420P &&
         (srcFormat == AV_PIX_FMT_NV12 || srcFormat == AV_PIX_FMT_NV21)) {
         c->swscale = nv12ToPlanarWrapper;
     }
+    /* nv24_to_yv24 */
+    if (dstFormat == AV_PIX_FMT_YUV444P &&
+        (srcFormat == AV_PIX_FMT_NV24 || srcFormat == AV_PIX_FMT_NV42)) {
+        c->swscale = nv24ToPlanarWrapper;
+    }
     /* yuv2bgr */
     if ((srcFormat == AV_PIX_FMT_YUV420P || srcFormat == AV_PIX_FMT_YUV422P ||
          srcFormat == AV_PIX_FMT_YUVA420P) && isAnyRGB(dstFormat) &&