[PATCH v5 4/8] virtio-gpu: Support asynchronous fencing

[Dmitry Osipenko <dmitry.osipenko@collabora.com>]

Support asynchronous fencing feature of virglrenderer. It allows Qemu to
handle fence as soon as it's signalled instead of periodically polling
the fence status. This feature is required for enabling DRM context
support in Qemu because legacy fencing mode isn't supported for DRM
contexts in virglrenderer.

Reviewed-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
---
 hw/display/virtio-gpu-gl.c     |   3 +
 hw/display/virtio-gpu-virgl.c  | 142 ++++++++++++++++++++++++++++++---
 include/hw/virtio/virtio-gpu.h |  13 +++
 3 files changed, 149 insertions(+), 9 deletions(-)

diff --git a/hw/display/virtio-gpu-gl.c b/hw/display/virtio-gpu-gl.c
index 683fad3bf8a8..d9bb50ac1d4a 100644
--- a/hw/display/virtio-gpu-gl.c
+++ b/hw/display/virtio-gpu-gl.c
@@ -169,6 +169,9 @@ static void virtio_gpu_gl_device_unrealize(DeviceState *qdev)
     if (gl->renderer_state >= RS_INITED) {
 #if VIRGL_VERSION_MAJOR >= 1
         qemu_bh_delete(gl->cmdq_resume_bh);
+
+        virtio_gpu_virgl_reset_async_fences(g);
+        qemu_bh_delete(gl->async_fence_bh);
 #endif
         if (virtio_gpu_stats_enabled(g->parent_obj.conf)) {
             timer_free(gl->print_stats);
diff --git a/hw/display/virtio-gpu-virgl.c b/hw/display/virtio-gpu-virgl.c
index 2eb6aaab4e84..15a465acf43b 100644
--- a/hw/display/virtio-gpu-virgl.c
+++ b/hw/display/virtio-gpu-virgl.c
@@ -871,6 +871,7 @@ static void virgl_cmd_set_scanout_blob(VirtIOGPU *g,
 void virtio_gpu_virgl_process_cmd(VirtIOGPU *g,
                                       struct virtio_gpu_ctrl_command *cmd)
 {
+    VirtIOGPUGL *gl = VIRTIO_GPU_GL(g);
     bool cmd_suspended = false;
     int ret;
 
@@ -972,15 +973,29 @@ void virtio_gpu_virgl_process_cmd(VirtIOGPU *g,
 
     trace_virtio_gpu_fence_ctrl(cmd->cmd_hdr.fence_id, cmd->cmd_hdr.type);
 
-    /*
-     * Unlike other virglrenderer functions, this one returns a positive
-     * error code.
-     */
-    ret = virgl_renderer_create_fence(cmd->cmd_hdr.fence_id, 0);
-    if (ret) {
-        qemu_log_mask(LOG_GUEST_ERROR,
-                      "%s: virgl_renderer_create_fence error: %s",
-                      __func__, strerror(ret));
+    if (gl->context_fence_enabled &&
+        (cmd->cmd_hdr.flags & VIRTIO_GPU_FLAG_INFO_RING_IDX)) {
+        uint32_t flags = 0;
+
+        ret = virgl_renderer_context_create_fence(cmd->cmd_hdr.ctx_id, flags,
+                                                  cmd->cmd_hdr.ring_idx,
+                                                  cmd->cmd_hdr.fence_id);
+        if (ret) {
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "%s: virgl_renderer_context_create_fence error: %s",
+                          __func__, strerror(-ret));
+        }
+    } else {
+        /*
+         * Unlike other virglrenderer functions, this one returns a positive
+         * error code.
+         */
+        ret = virgl_renderer_create_fence(cmd->cmd_hdr.fence_id, 0);
+        if (ret) {
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "%s: virgl_renderer_create_fence error: %s",
+                          __func__, strerror(ret));
+        }
     }
 }
 
@@ -1008,6 +1023,102 @@ static void virgl_write_fence(void *opaque, uint32_t fence)
     }
 }
 
+void virtio_gpu_virgl_reset_async_fences(VirtIOGPU *g)
+{
+    struct virtio_gpu_virgl_context_fence *f;
+    VirtIOGPUGL *gl = VIRTIO_GPU_GL(g);
+
+    while (!QSLIST_EMPTY(&gl->async_fenceq)) {
+        f = QSLIST_FIRST(&gl->async_fenceq);
+
+        QSLIST_REMOVE_HEAD(&gl->async_fenceq, next);
+
+        g_free(f);
+    }
+}
+
+#if VIRGL_VERSION_MAJOR >= 1
+static void virtio_gpu_virgl_async_fence_bh(void *opaque)
+{
+    QSLIST_HEAD(, virtio_gpu_virgl_context_fence) async_fenceq;
+    struct virtio_gpu_ctrl_command *cmd, *tmp;
+    struct virtio_gpu_virgl_context_fence *f;
+    VirtIOGPU *g = opaque;
+    VirtIOGPUGL *gl = VIRTIO_GPU_GL(g);
+
+    QSLIST_MOVE_ATOMIC(&async_fenceq, &gl->async_fenceq);
+
+    while (!QSLIST_EMPTY(&async_fenceq)) {
+        f = QSLIST_FIRST(&async_fenceq);
+
+        QSLIST_REMOVE_HEAD(&async_fenceq, next);
+
+        QTAILQ_FOREACH_SAFE(cmd, &g->fenceq, next, tmp) {
+            /*
+             * the guest can end up emitting fences out of order
+             * so we should check all fenced cmds not just the first one.
+             */
+            if (cmd->cmd_hdr.fence_id > f->fence_id) {
+                continue;
+            }
+            if (cmd->cmd_hdr.flags & VIRTIO_GPU_FLAG_INFO_RING_IDX) {
+                if (cmd->cmd_hdr.ring_idx != f->ring_idx) {
+                    continue;
+                }
+                if (cmd->cmd_hdr.ctx_id != f->ctx_id) {
+                    continue;
+                }
+            } else if (f->ring_idx >= 0) {
+                /* ctx0 GL-query fences don't have ring info */
+                continue;
+            }
+            virtio_gpu_ctrl_response_nodata(g, cmd, VIRTIO_GPU_RESP_OK_NODATA);
+            QTAILQ_REMOVE(&g->fenceq, cmd, next);
+            g_free(cmd);
+        }
+
+        trace_virtio_gpu_fence_resp(f->fence_id);
+        g_free(f);
+        g->inflight--;
+        if (virtio_gpu_stats_enabled(g->parent_obj.conf)) {
+            trace_virtio_gpu_dec_inflight_fences(g->inflight);
+        }
+    }
+}
+
+static void
+virtio_gpu_virgl_push_async_fence(VirtIOGPU *g, uint32_t ctx_id,
+                                  int64_t ring_idx, uint64_t fence_id)
+{
+    struct virtio_gpu_virgl_context_fence *f;
+    VirtIOGPUGL *gl = VIRTIO_GPU_GL(g);
+
+    f = g_new(struct virtio_gpu_virgl_context_fence, 1);
+    f->ctx_id = ctx_id;
+    f->ring_idx = ring_idx;
+    f->fence_id = fence_id;
+
+    QSLIST_INSERT_HEAD_ATOMIC(&gl->async_fenceq, f, next);
+
+    qemu_bh_schedule(gl->async_fence_bh);
+}
+
+static void virgl_write_async_fence(void *opaque, uint32_t fence)
+{
+    VirtIOGPU *g = opaque;
+
+    virtio_gpu_virgl_push_async_fence(g, 0, -1, fence);
+}
+
+static void virgl_write_async_context_fence(void *opaque, uint32_t ctx_id,
+                                            uint32_t ring_idx, uint64_t fence)
+{
+    VirtIOGPU *g = opaque;
+
+    virtio_gpu_virgl_push_async_fence(g, ctx_id, ring_idx, fence);
+}
+#endif
+
 static virgl_renderer_gl_context
 virgl_create_context(void *opaque, int scanout_idx,
                      struct virgl_renderer_gl_ctx_param *params)
@@ -1095,6 +1206,8 @@ void virtio_gpu_virgl_reset_scanout(VirtIOGPU *g)
         dpy_gfx_replace_surface(g->parent_obj.scanout[i].con, NULL);
         dpy_gl_scanout_disable(g->parent_obj.scanout[i].con);
     }
+
+    virtio_gpu_virgl_reset_async_fences(g);
 }
 
 void virtio_gpu_virgl_reset(VirtIOGPU *g)
@@ -1112,6 +1225,13 @@ int virtio_gpu_virgl_init(VirtIOGPU *g)
     if (qemu_egl_display) {
         virtio_gpu_3d_cbs.version = 4;
         virtio_gpu_3d_cbs.get_egl_display = virgl_get_egl_display;
+#if VIRGL_VERSION_MAJOR >= 1
+        virtio_gpu_3d_cbs.write_fence         = virgl_write_async_fence;
+        virtio_gpu_3d_cbs.write_context_fence = virgl_write_async_context_fence;
+        flags |= VIRGL_RENDERER_ASYNC_FENCE_CB;
+        flags |= VIRGL_RENDERER_THREAD_SYNC;
+        gl->context_fence_enabled = true;
+#endif
     }
 #endif
 #ifdef VIRGL_RENDERER_D3D11_SHARE_TEXTURE
@@ -1145,6 +1265,10 @@ int virtio_gpu_virgl_init(VirtIOGPU *g)
     gl->cmdq_resume_bh = aio_bh_new(qemu_get_aio_context(),
                                     virtio_gpu_virgl_resume_cmdq_bh,
                                     g);
+
+    gl->async_fence_bh = aio_bh_new(qemu_get_aio_context(),
+                                    virtio_gpu_virgl_async_fence_bh,
+                                    g);
 #endif
 
     return 0;
diff --git a/include/hw/virtio/virtio-gpu.h b/include/hw/virtio/virtio-gpu.h
index a42957c4e2cc..bd2cccdc60d7 100644
--- a/include/hw/virtio/virtio-gpu.h
+++ b/include/hw/virtio/virtio-gpu.h
@@ -230,6 +230,13 @@ struct VirtIOGPUClass {
                              Error **errp);
 };
 
+struct virtio_gpu_virgl_context_fence {
+    uint32_t ctx_id;
+    int64_t ring_idx;
+    uint64_t fence_id;
+    QSLIST_ENTRY(virtio_gpu_virgl_context_fence) next;
+};
+
 /* VirtIOGPUGL renderer states */
 typedef enum {
     RS_START,       /* starting state */
@@ -247,6 +254,11 @@ struct VirtIOGPUGL {
     QEMUTimer *print_stats;
 
     QEMUBH *cmdq_resume_bh;
+
+    QEMUBH *async_fence_bh;
+    QSLIST_HEAD(, virtio_gpu_virgl_context_fence) async_fenceq;
+
+    bool context_fence_enabled;
 };
 
 struct VhostUserGPU {
@@ -376,5 +388,6 @@ void virtio_gpu_virgl_reset_scanout(VirtIOGPU *g);
 void virtio_gpu_virgl_reset(VirtIOGPU *g);
 int virtio_gpu_virgl_init(VirtIOGPU *g);
 GArray *virtio_gpu_virgl_get_capsets(VirtIOGPU *g);
+void virtio_gpu_virgl_reset_async_fences(VirtIOGPU *g);
 
 #endif
-- 
2.47.1