swscale/swscale: Fix several invalid shifts related to vChrDrop

[ffmpeg] / libavutil / hwcontext_cuda.c

diff --git a/libavutil/hwcontext_cuda.c b/libavutil/hwcontext_cuda.c
index 540a7610ef954dd94302a7150b0fea541b61fad5..30611b1912051fd031ad54e803df3722d333a076 100644 (file)
--- a/libavutil/hwcontext_cuda.c
+++ b/libavutil/hwcontext_cuda.c
@@ -268,10 +268,6 @@ static int cuda_transfer_data_to(AVHWFramesContext *ctx, AVFrame *dst,
             goto exit;
     }
 
-    ret = CHECK_CU(cu->cuStreamSynchronize(hwctx->stream));
-    if (ret < 0)
-        goto exit;
-
 exit:
     CHECK_CU(cu->cuCtxPopCurrent(&dummy));
 
@@ -284,10 +280,16 @@ static void cuda_device_uninit(AVHWDeviceContext *device_ctx)
 
     if (hwctx->internal) {
         CudaFunctions *cu = hwctx->internal->cuda_dl;
+
         if (hwctx->internal->is_allocated && hwctx->cuda_ctx) {
-            CHECK_CU(cu->cuCtxDestroy(hwctx->cuda_ctx));
+            if (hwctx->internal->flags & AV_CUDA_USE_PRIMARY_CONTEXT)
+                CHECK_CU(cu->cuDevicePrimaryCtxRelease(hwctx->internal->cuda_device));
+            else
+                CHECK_CU(cu->cuCtxDestroy(hwctx->cuda_ctx));
+
             hwctx->cuda_ctx = NULL;
         }
+
         cuda_free_functions(&hwctx->internal->cuda_dl);
     }
 
@@ -326,9 +328,11 @@ static int cuda_device_create(AVHWDeviceContext *device_ctx,
 {
     AVCUDADeviceContext *hwctx = device_ctx->hwctx;
     CudaFunctions *cu;
-    CUdevice cu_device;
     CUcontext dummy;
-    int ret, device_idx = 0;
+    int ret, dev_active = 0, device_idx = 0;
+    unsigned int dev_flags = 0;
+
+    const unsigned int desired_flags = CU_CTX_SCHED_BLOCKING_SYNC;
 
     if (device)
         device_idx = strtol(device, NULL, 0);
@@ -342,21 +346,42 @@ static int cuda_device_create(AVHWDeviceContext *device_ctx,
     if (ret < 0)
         goto error;
 
-    ret = CHECK_CU(cu->cuDeviceGet(&cu_device, device_idx));
+    ret = CHECK_CU(cu->cuDeviceGet(&hwctx->internal->cuda_device, device_idx));
     if (ret < 0)
         goto error;
 
-    ret = CHECK_CU(cu->cuCtxCreate(&hwctx->cuda_ctx, CU_CTX_SCHED_BLOCKING_SYNC, cu_device));
-    if (ret < 0)
-        goto error;
+    hwctx->internal->flags = flags;
 
-    // Setting stream to NULL will make functions automatically use the default CUstream
-    hwctx->stream = NULL;
+    if (flags & AV_CUDA_USE_PRIMARY_CONTEXT) {
+        ret = CHECK_CU(cu->cuDevicePrimaryCtxGetState(hwctx->internal->cuda_device, &dev_flags, &dev_active));
+        if (ret < 0)
+            goto error;
 
-    CHECK_CU(cu->cuCtxPopCurrent(&dummy));
+        if (dev_active && dev_flags != desired_flags) {
+            av_log(device_ctx, AV_LOG_ERROR, "Primary context already active with incompatible flags.\n");
+            goto error;
+        } else if (dev_flags != desired_flags) {
+            ret = CHECK_CU(cu->cuDevicePrimaryCtxSetFlags(hwctx->internal->cuda_device, desired_flags));
+            if (ret < 0)
+                goto error;
+        }
+
+        ret = CHECK_CU(cu->cuDevicePrimaryCtxRetain(&hwctx->cuda_ctx, hwctx->internal->cuda_device));
+        if (ret < 0)
+            goto error;
+    } else {
+        ret = CHECK_CU(cu->cuCtxCreate(&hwctx->cuda_ctx, desired_flags, hwctx->internal->cuda_device));
+        if (ret < 0)
+            goto error;
+
+        CHECK_CU(cu->cuCtxPopCurrent(&dummy));
+    }
 
     hwctx->internal->is_allocated = 1;
 
+    // Setting stream to NULL will make functions automatically use the default CUstream
+    hwctx->stream = NULL;
+
     return 0;
 
 error: