vatrog-vm-vgpu-streamer/src/stream/win32/present.c

#define WIN32_LEAN_AND_MEAN
#include <windows.h>
#include <string.h>
#include <stdio.h>
#include "present.h"
#include "stream.h"        /* OS-agnostic publish / control API + region-view */
#include "cursor.h"

/* cursor arena sizing */
#define VGPU_CUR_MAX     256u
#define VGPU_CUR_BGRA    (VGPU_CUR_MAX * VGPU_CUR_MAX * 4u)
#define VGPU_CUR_MASK    (VGPU_CUR_MAX * VGPU_CUR_MAX)

static uint64_t now_ns(void) {
    static LARGE_INTEGER freq = { .QuadPart = 0 };
    if (freq.QuadPart == 0) QueryPerformanceFrequency(&freq);
    LARGE_INTEGER c; QueryPerformanceCounter(&c);
    return (uint64_t)((double)c.QuadPart * 1e9 / (double)freq.QuadPart);
}

int vgpu_present_init(vgpu_ctx* ctx, vgpu_region_t* region, uint32_t default_fps) {
    memset(ctx, 0, sizeof *ctx);
    ctx->view.producer = region->producer;
    ctx->view.control  = region->control;
    ctx->view.ring     = region->ring;
    ctx->default_fps = default_fps ? default_fps : 30u;
    ctx->backend  = VGPU_BK_NONE;
    ctx->draw_cursor_cap = 1;

    /* one arena: content + frame + cursor buffers */
    size_t bytes = VGPU_STAGING_BYTES   /* content */
                 + VGPU_STAGING_BYTES   /* frame   */
                 + VGPU_CUR_BGRA        /* cursor bgra */
                 + VGPU_CUR_MASK        /* and */
                 + VGPU_CUR_MASK;       /* xor */
    uint8_t* a = (uint8_t*)VirtualAlloc(NULL, bytes, MEM_RESERVE | MEM_COMMIT,
                                        PAGE_READWRITE);
    if (!a) {
        fprintf(stderr, "present: arena VirtualAlloc %zu MiB failed (%lu)\n",
                bytes / (1024 * 1024), GetLastError());
        return 1;
    }
    ctx->arena       = a;
    ctx->arena_bytes = bytes;

    size_t off = 0;
    ctx->content_buf      = a + off; off += VGPU_STAGING_BYTES;
    ctx->frame_buf        = a + off; off += VGPU_STAGING_BYTES;
    ctx->cursor.bgra      = a + off; off += VGPU_CUR_BGRA;
    ctx->cursor.and_mask  = a + off; off += VGPU_CUR_MASK;
    ctx->cursor.xor_mask  = a + off; off += VGPU_CUR_MASK;

    InitializeCriticalSection(&ctx->lock);
    ctx->submit_event = CreateEvent(NULL, FALSE, FALSE, NULL);
    ctx->content_seq  = 0;
    ctx->content_w = ctx->content_h = 0;
    return 0;
}

void vgpu_present_deinit(vgpu_ctx* ctx) {
    if (ctx->submit_event) { CloseHandle(ctx->submit_event); ctx->submit_event = NULL; }
    DeleteCriticalSection(&ctx->lock);
    if (ctx->arena) { VirtualFree(ctx->arena, 0, MEM_RELEASE); ctx->arena = NULL; }
}

void vgpu_present_submit(vgpu_ctx* ctx, const uint8_t* src,
                         uint32_t W, uint32_t H, uint32_t src_pitch) {
    if (W > VGPU_MAX_WIDTH)  W = VGPU_MAX_WIDTH;
    if (H > VGPU_MAX_HEIGHT) H = VGPU_MAX_HEIGHT;
    if (W == 0 || H == 0) return;

    EnterCriticalSection(&ctx->lock);
    uint8_t* d = ctx->content_buf;
    const uint32_t row = W * 4u;
    for (uint32_t y = 0; y < H; y++)
        memcpy(d + (size_t)y * row, src + (size_t)y * src_pitch, row);
    ctx->content_w = W;
    ctx->content_h = H;
    ctx->content_seq++;
    LeaveCriticalSection(&ctx->lock);
    SetEvent(ctx->submit_event);
}

void vgpu_present_run(vgpu_ctx* ctx) {
    const vgpu_region_view* rv = &ctx->view;   /* neutral handle for the engine */
    const DWORD poll_ms = 8;
    int64_t  last_seq   = -1;
    uint32_t prev_state = VGPU_CMD_STOP;
    uint32_t last_ff_ack = rv->producer->full_frame_ack;
    DWORD    last_beat  = GetTickCount();
    uint64_t last_publish_ns = 0;   /* 0 → first eligible frame publishes immediately */

    for (;;) {
        WaitForSingleObject(ctx->submit_event, poll_ms);

        /* --- heartbeat: always ticks, independent of desired_state --- */
        DWORD nowt = GetTickCount();
        if (nowt - last_beat >= VGPU_HEARTBEAT_PERIOD_MS) {
            vgpu_tick_heartbeat(rv);
            last_beat = nowt;
        }

        /* --- cursor position: sensor data, reported every tick independent of
         *     draw_cursor / compositing (host may overlay it itself) --- */
        cursor_sample_pos(ctx);
        vgpu_publish_cursor(rv, (int32_t)ctx->cursor.x, (int32_t)ctx->cursor.y,
                            (uint32_t)(ctx->cursor.visible != 0));

        /* --- reconcile control (gen-seqlock -> apply -> ack) --- */
        vgpu_control_view cv;
        uint32_t desired = prev_state;
        uint32_t draw_cursor = 1;
        int      force_full = 0;
        uint32_t fps = ctx->default_fps;   /* publish-rate cap (applied) */
        uint32_t ff_req = last_ff_ack;     /* full_frame_req value to honor */
        if (vgpu_control_read(rv, &cv)) {
            desired = cv.desired_state;
            draw_cursor = cv.draw_cursor;
            fps = cv.target_fps ? cv.target_fps : ctx->default_fps;
            vgpu_set_applied_fps(rv, fps);
            vgpu_publish_ctrl_ack(rv, cv.gen);

            ff_req = cv.full_frame_req;
            if ((ff_req - last_ff_ack) != 0u)
                force_full = 1;            /* edge pending, wrap-tolerant */
        }

        /* --- lifecycle transitions --- */
        if (desired != prev_state) {
            if (desired == VGPU_CMD_RUN && prev_state != VGPU_CMD_RUN) {
                vgpu_bump_run_epoch(rv);
                vgpu_set_status(rv, VGPU_ST_CAPTURING);
                force_full = 1;     /* fresh frame on start */
            } else if (desired == VGPU_CMD_PAUSE) {
                vgpu_set_status(rv, VGPU_ST_PAUSED);
            } else if (desired == VGPU_CMD_STOP) {
                vgpu_set_status(rv, VGPU_ST_STOPPED);
            }
            prev_state = desired;
        } else if (last_seq < 0 && desired == VGPU_CMD_RUN) {
            vgpu_set_status(rv, VGPU_ST_CAPTURING);
        }

        if (desired != VGPU_CMD_RUN) {
            /* PAUSED/STOPPED: no new frames; heartbeat still ticks. We do NOT
             * ack a pending full_frame here — acking without publishing would
             * be a false "honored". A pending request is honored on the next
             * transition to RUN (force_full=1 there → publish + ack). */
            continue;
        }

        /* --- compose + publish on content change OR forced full frame, but
         *     rate-limited to the applied fps cap (the single publish point →
         *     contract-level cap, independent of the capture backend). A
         *     force_full bypasses the cap (due=1). --- */
        int cur_changed = (ctx->draw_cursor_cap && draw_cursor)
                          ? cursor_sample(ctx) : 0;

        uint64_t interval_ns = fps > 0 ? (1000000000ull / fps) : 0;
        uint64_t now = now_ns();
        int due = force_full || interval_ns == 0
                  || (now - last_publish_ns) >= interval_ns;

        EnterCriticalSection(&ctx->lock);
        int64_t  seq = ctx->content_seq;
        uint32_t W = ctx->content_w, H = ctx->content_h;
        int have = (W && H);
        int content_new = have && (seq != last_seq || cur_changed || force_full);
        /* take the frame ONLY when due — so we never drop the latest content;
         * if not due, last_seq is left untouched and it publishes next due. */
        int dirty = content_new && due;
        if (dirty) {
            memcpy(ctx->frame_buf, ctx->content_buf, (size_t)W * H * 4u);
            last_seq = seq;
        }
        LeaveCriticalSection(&ctx->lock);

        if (!dirty) {
            /* not due, or nothing to publish. A force_full with content has
             * due=1 → dirty=1, so it never lands here while have is true; thus
             * no spurious ack edge. */
            continue;
        }

        if (ctx->draw_cursor_cap && draw_cursor)
            cursor_draw(ctx, ctx->frame_buf, W, H);

        if (vgpu_publish_frame(rv, ctx->frame_buf, W, H, now) == 0) {
            last_publish_ns = now;
            if (force_full) {
                vgpu_publish_full_frame_ack(rv, ff_req);
                last_ff_ack = ff_req;
            }
        } else {
            vgpu_set_error(rv, 1u);  /* frame too large for slot (mode > max) */
        }
    }
}