From 21e466b6fbc69ce5b14d26af3bf738a5a5433cc7 Mon Sep 17 00:00:00 2001
From: Timo Rothenpieler <timo@rothenpieler.org>
Date: Sun, 28 Jan 2018 14:43:39 +0100
Subject: [PATCH] Add cuCtxSetLimit CUDA function

---
 ffnvcodec.pc.in                    | 2 +-
 include/ffnvcodec/dynlink_cuda.h   | 9 +++++++++
 include/ffnvcodec/dynlink_loader.h | 2 ++
 3 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/ffnvcodec.pc.in b/ffnvcodec.pc.in
index b751663..c885d56 100644
--- a/ffnvcodec.pc.in
+++ b/ffnvcodec.pc.in
@@ -3,5 +3,5 @@ includedir=${prefix}/include
 
 Name: ffnvcodec
 Description: FFmpeg version of Nvidia Codec SDK headers
-Version: 8.0.14
+Version: 8.0.14.1
 Cflags: -I${includedir}
diff --git a/include/ffnvcodec/dynlink_cuda.h b/include/ffnvcodec/dynlink_cuda.h
index 32a588d..fb2c4b5 100644
--- a/include/ffnvcodec/dynlink_cuda.h
+++ b/include/ffnvcodec/dynlink_cuda.h
@@ -59,6 +59,14 @@ typedef enum CUmemorytype_enum {
     CU_MEMORYTYPE_DEVICE = 2
 } CUmemorytype;
 
+typedef enum CUlimit_enum {
+    CU_LIMIT_STACK_SIZE = 0,
+    CU_LIMIT_PRINTF_FIFO_SIZE = 1,
+    CU_LIMIT_MALLOC_HEAP_SIZE = 2,
+    CU_LIMIT_DEV_RUNTIME_SYNC_DEPTH = 3,
+    CU_LIMIT_DEV_RUNTIME_PENDING_LAUNCH_COUNT = 4
+} CUlimit;
+
 typedef struct CUDA_MEMCPY2D_st {
     size_t srcXInBytes;
     size_t srcY;
@@ -86,6 +94,7 @@ typedef CUresult CUDAAPI tcuDeviceGet(CUdevice *device, int ordinal);
 typedef CUresult CUDAAPI tcuDeviceGetName(char *name, int len, CUdevice dev);
 typedef CUresult CUDAAPI tcuDeviceComputeCapability(int *major, int *minor, CUdevice dev);
 typedef CUresult CUDAAPI tcuCtxCreate_v2(CUcontext *pctx, unsigned int flags, CUdevice dev);
+typedef CUresult CUDAAPI tcuCtxSetLimit(CUlimit limit, size_t value);
 typedef CUresult CUDAAPI tcuCtxPushCurrent_v2(CUcontext *pctx);
 typedef CUresult CUDAAPI tcuCtxPopCurrent_v2(CUcontext *pctx);
 typedef CUresult CUDAAPI tcuCtxDestroy_v2(CUcontext ctx);
diff --git a/include/ffnvcodec/dynlink_loader.h b/include/ffnvcodec/dynlink_loader.h
index b291f81..d597413 100644
--- a/include/ffnvcodec/dynlink_loader.h
+++ b/include/ffnvcodec/dynlink_loader.h
@@ -142,6 +142,7 @@ typedef struct CudaFunctions {
     tcuDeviceGetName *cuDeviceGetName;
     tcuDeviceComputeCapability *cuDeviceComputeCapability;
     tcuCtxCreate_v2 *cuCtxCreate;
+    tcuCtxSetLimit *cuCtxSetLimit;
     tcuCtxPushCurrent_v2 *cuCtxPushCurrent;
     tcuCtxPopCurrent_v2 *cuCtxPopCurrent;
     tcuCtxDestroy_v2 *cuCtxDestroy;
@@ -221,6 +222,7 @@ static inline int cuda_load_functions(CudaFunctions **functions, void *logctx)
     LOAD_SYMBOL(cuDeviceGetName, tcuDeviceGetName, "cuDeviceGetName");
     LOAD_SYMBOL(cuDeviceComputeCapability, tcuDeviceComputeCapability, "cuDeviceComputeCapability");
     LOAD_SYMBOL(cuCtxCreate, tcuCtxCreate_v2, "cuCtxCreate_v2");
+    LOAD_SYMBOL(cuCtxSetLimit, tcuCtxSetLimit, "cuCtxSetLimit");
     LOAD_SYMBOL(cuCtxPushCurrent, tcuCtxPushCurrent_v2, "cuCtxPushCurrent_v2");
     LOAD_SYMBOL(cuCtxPopCurrent, tcuCtxPopCurrent_v2, "cuCtxPopCurrent_v2");
     LOAD_SYMBOL(cuCtxDestroy, tcuCtxDestroy_v2, "cuCtxDestroy_v2");