Initial commit: win32 vGPU stream capture module

Capture backends (NvFBC/DDA/GDI), cursor/region/present helpers, publish API, vendor NvFBC headers; CMake build with mingw-w64 toolchain.

src/stream/include/stream.h

@@ -0,0 +1,56 @@
+#ifndef VGPU_STREAM_ENGINE_H
+#define VGPU_STREAM_ENGINE_H
+
+/* stream.h — OS-agnostic streaming protocol over the shared contract.
+ * Declares the neutral region-view handle (resolved contract pointers) and the
+ * seqlock publish / control-reconcile API. No platform headers: the engine
+ * operates purely on the contract; a platform layer (e.g. src/stream/win32/)
+ * builds the region and hands its pointers in as a vgpu_region_view. */
+
+#include <stdint.h>
+#include "vgpu_stream.h"   /* contract: producer/control types, slot geometry */
+
+/* Neutral view of the live contract: the three resolved blocks the engine
+ * publishes into / reconciles against. The platform region owns the backing
+ * memory; this is a borrowed view (no ownership). */
+typedef struct {
+    vgpu_producer_t* producer;
+    vgpu_control_t*  control;
+    uint8_t*         ring;
+} vgpu_region_view;
+
+/* Resolved view of the control block after a clean generation read. */
+typedef struct {
+    uint32_t gen;            /* even generation that was read (for ctrl_ack) */
+    uint32_t desired_state;  /* VGPU_CMD_* */
+    uint32_t target_fps;
+    uint32_t draw_cursor;
+    uint32_t full_frame_req;
+    uint32_t consumer_tick;
+    uint32_t attached;
+} vgpu_control_view;
+
+/* Seqlock-publish a tight BGRA frame into the next ring slot.
+ * Clamps by SLOT_STRIDE (rejects frames that do not fit). Writes desc[],
+ * bumps frame_id, release-stores latest. Returns 0 on publish, 1 if dropped
+ * (frame too large for a slot). */
+int vgpu_publish_frame(const vgpu_region_view* rv, const uint8_t* tight_bgra,
+                       uint32_t width, uint32_t height, uint64_t timestamp_ns);
+
+/* Read control block under its generation seqlock (bounded retry). Returns 1
+ * on a clean read (view filled), 0 if the writer kept it busy past the limit. */
+int vgpu_control_read(const vgpu_region_view* rv, vgpu_control_view* out);
+
+/* Echo the applied generation back to the host. */
+void vgpu_publish_ctrl_ack(const vgpu_region_view* rv, uint32_t gen);
+
+/* Status / lifecycle helpers (cold line). */
+void vgpu_set_status(const vgpu_region_view* rv, uint32_t status);
+void vgpu_set_backend(const vgpu_region_view* rv, uint32_t backend);
+void vgpu_set_error(const vgpu_region_view* rv, uint32_t error_code);
+void vgpu_set_applied_fps(const vgpu_region_view* rv, uint32_t fps);
+void vgpu_bump_run_epoch(const vgpu_region_view* rv);
+void vgpu_tick_heartbeat(const vgpu_region_view* rv);
+void vgpu_publish_full_frame_ack(const vgpu_region_view* rv, uint32_t req);
+
+#endif /* VGPU_STREAM_ENGINE_H */