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.

8 files changed, 64 insertions, 9 deletions

diff --git a/libswscale/input.c b/libswscale/input.c
index c2dc356b5d..064f8da314 100644
--- a/libswscale/input.c
+++ b/libswscale/input.c
@@ -1020,9 +1020,11 @@ av_cold void ff_sws_init_input_funcs(SwsContext *c)
         c->chrToYV12 = uyvyToUV_c;
         break;
     case AV_PIX_FMT_NV12:
+    case AV_PIX_FMT_NV24:
         c->chrToYV12 = nv12ToUV_c;
         break;
     case AV_PIX_FMT_NV21:
+    case AV_PIX_FMT_NV42:
         c->chrToYV12 = nv21ToUV_c;
         break;
     case AV_PIX_FMT_RGB8:
diff --git a/libswscale/output.c b/libswscale/output.c
index d3401f0cd1..26b0ff3d48 100644
--- a/libswscale/output.c
+++ b/libswscale/output.c
@@ -410,7 +410,8 @@ static void yuv2nv12cX_c(SwsContext *c, const int16_t *chrFilter, int chrFilterS
     const uint8_t *chrDither = c->chrDither8;
     int i;
 
-    if (dstFormat == AV_PIX_FMT_NV12)
+    if (dstFormat == AV_PIX_FMT_NV12 ||
+        dstFormat == AV_PIX_FMT_NV24)
         for (i=0; i<chrDstW; i++) {
             int u = chrDither[i & 7] << 12;
             int v = chrDither[(i + 3) & 7] << 12;
@@ -2496,7 +2497,8 @@ av_cold void ff_sws_init_output_funcs(SwsContext *c,
     } else {
         *yuv2plane1 = yuv2plane1_8_c;
         *yuv2planeX = yuv2planeX_8_c;
-        if (dstFormat == AV_PIX_FMT_NV12 || dstFormat == AV_PIX_FMT_NV21)
+        if (dstFormat == AV_PIX_FMT_NV12 || dstFormat == AV_PIX_FMT_NV21 ||
+            dstFormat == AV_PIX_FMT_NV24 || dstFormat == AV_PIX_FMT_NV42)
             *yuv2nv12cX = yuv2nv12cX_c;
     }
 
diff --git a/libswscale/ppc/swscale_altivec.c b/libswscale/ppc/swscale_altivec.c
index 3cd9782da4..6b8cc2c194 100644
--- a/libswscale/ppc/swscale_altivec.c
+++ b/libswscale/ppc/swscale_altivec.c
@@ -247,8 +247,7 @@ av_cold void ff_sws_init_swscale_ppc(SwsContext *c)
     if (c->srcBpc == 8 && c->dstBpc <= 14) {
         c->hyScale = c->hcScale = hScale_real_altivec;
     }
-    if (!is16BPS(dstFormat) && !isNBPS(dstFormat) &&
-        dstFormat != AV_PIX_FMT_NV12 && dstFormat != AV_PIX_FMT_NV21 &&
+    if (!is16BPS(dstFormat) && !isNBPS(dstFormat) && !isSemiPlanarYUV(dstFormat) &&
         dstFormat != AV_PIX_FMT_GRAYF32BE && dstFormat != AV_PIX_FMT_GRAYF32LE &&
         !c->needAlpha) {
         c->yuv2planeX = yuv2planeX_altivec;
diff --git a/libswscale/ppc/swscale_vsx.c b/libswscale/ppc/swscale_vsx.c
index a617f76741..75dee5ea58 100644
--- a/libswscale/ppc/swscale_vsx.c
+++ b/libswscale/ppc/swscale_vsx.c
@@ -2096,8 +2096,7 @@ av_cold void ff_sws_init_swscale_vsx(SwsContext *c)
                                                      : hScale16To15_vsx;
         }
     }
-    if (!is16BPS(dstFormat) && !isNBPS(dstFormat) &&
-        dstFormat != AV_PIX_FMT_NV12 && dstFormat != AV_PIX_FMT_NV21 &&
+    if (!is16BPS(dstFormat) && !isNBPS(dstFormat) && !isSemiPlanarYUV(dstFormat) &&
         dstFormat != AV_PIX_FMT_GRAYF32BE && dstFormat != AV_PIX_FMT_GRAYF32LE &&
         !c->needAlpha) {
         c->yuv2planeX = yuv2planeX_vsx;
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) &&
diff --git a/libswscale/utils.c b/libswscale/utils.c
index df68bcc0d9..1b1f779532 100644
--- a/libswscale/utils.c
+++ b/libswscale/utils.c
@@ -264,6 +264,8 @@ static const FormatEntry format_entries[AV_PIX_FMT_NB] = {
     [AV_PIX_FMT_YUVA422P12LE] = { 1, 1 },
     [AV_PIX_FMT_YUVA444P12BE] = { 1, 1 },
     [AV_PIX_FMT_YUVA444P12LE] = { 1, 1 },
+    [AV_PIX_FMT_NV24]        = { 1, 1 },
+    [AV_PIX_FMT_NV42]        = { 1, 1 },
 };
 
 int sws_isSupportedInput(enum AVPixelFormat pix_fmt)
diff --git a/libswscale/version.h b/libswscale/version.h
index 0e28a76e64..891c76d915 100644
--- a/libswscale/version.h
+++ b/libswscale/version.h
@@ -28,7 +28,7 @@
 
 #define LIBSWSCALE_VERSION_MAJOR   5
 #define LIBSWSCALE_VERSION_MINOR   4
-#define LIBSWSCALE_VERSION_MICRO 100
+#define LIBSWSCALE_VERSION_MICRO 101
 
 #define LIBSWSCALE_VERSION_INT  AV_VERSION_INT(LIBSWSCALE_VERSION_MAJOR, \
                                                LIBSWSCALE_VERSION_MINOR, \
diff --git a/libswscale/x86/swscale_template.c b/libswscale/x86/swscale_template.c
index 7c30470679..823056c2ea 100644
--- a/libswscale/x86/swscale_template.c
+++ b/libswscale/x86/swscale_template.c
@@ -1499,8 +1499,8 @@ static av_cold void RENAME(sws_init_swscale)(SwsContext *c)
     enum AVPixelFormat dstFormat = c->dstFormat;
 
     c->use_mmx_vfilter= 0;
-    if (!is16BPS(dstFormat) && !isNBPS(dstFormat) && dstFormat != AV_PIX_FMT_NV12
-        && dstFormat != AV_PIX_FMT_NV21 && dstFormat != AV_PIX_FMT_GRAYF32BE && dstFormat != AV_PIX_FMT_GRAYF32LE
+    if (!is16BPS(dstFormat) && !isNBPS(dstFormat) && !isSemiPlanarYUV(dstFormat)
+        && dstFormat != AV_PIX_FMT_GRAYF32BE && dstFormat != AV_PIX_FMT_GRAYF32LE
         && !(c->flags & SWS_BITEXACT)) {
             if (c->flags & SWS_ACCURATE_RND) {
                 if (!(c->flags & SWS_FULL_CHR_H_INT)) {