virtio-gpu: Support asynchronous fencing

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>
Tested-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Yiwei Zhang <zzyiwei@gmail.com>
Tested-by: Yiwei Zhang <zzyiwei@gmail.com>
Signed-off-by: Dmitry Osipenko <dmitry.osipenko@collabora.com>
Message-ID: <20260303151422.977399-10-dmitry.osipenko@collabora.com>
Message-ID: <20260304165043.1437519-12-alex.bennee@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>

diff --git a/hw/display/virtio-gpu-gl.c b/hw/display/virtio-gpu-gl.c
index b98ef2ef98770b018188c8b64989fc958ee94f1e..3e0680880e14e412d9b12c654e86dcd8c277debe 100644 (file)
--- a/hw/display/virtio-gpu-gl.c
+++ b/hw/display/virtio-gpu-gl.c
@@ -169,6 +169,11 @@ 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);
+
+        if (gl->async_fence_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 f00c666f61f43481291c11e239466070c1d38a3e..ae1880c358b22254bfa5430d97e5796a47516aec 100644 (file)
--- a/hw/display/virtio-gpu-virgl.c
+++ b/hw/display/virtio-gpu-virgl.c
@@ -24,6 +24,23 @@
 
 #include <virglrenderer.h>
 
+/*
+ * VIRGL_CHECK_VERSION available since libvirglrenderer 1.0.1 and was fixed
+ * in 1.1.0. Undefine bugged version of the macro and provide our own.
+ */
+#if defined(VIRGL_CHECK_VERSION) && \
+    VIRGL_VERSION_MAJOR == 1 && VIRGL_VERSION_MINOR < 1
+#undef VIRGL_CHECK_VERSION
+#endif
+
+#ifndef VIRGL_CHECK_VERSION
+#define VIRGL_CHECK_VERSION(major, minor, micro) \
+    (VIRGL_VERSION_MAJOR > (major) || \
+     VIRGL_VERSION_MAJOR == (major) && VIRGL_VERSION_MINOR > (minor) || \
+     VIRGL_VERSION_MAJOR == (major) && VIRGL_VERSION_MINOR == (minor) && \
+     VIRGL_VERSION_MICRO >= (micro))
+#endif
+
 struct virtio_gpu_virgl_resource {
     struct virtio_gpu_simple_resource base;
     MemoryRegion *mr;
@@ -1079,6 +1096,103 @@ static void virgl_write_context_fence(void *opaque, uint32_t ctx_id,
 }
 #endif
 
+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_CHECK_VERSION(1, 1, 2)
+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);
+
+    if (gl->renderer_state != RS_INITED) {
+        return;
+    }
+
+    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;
+                }
+            }
+            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,
+                                  uint32_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, UINT32_MAX, 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)
@@ -1178,6 +1292,8 @@ void virtio_gpu_virgl_reset_scanout(VirtIOGPU *g)
 void virtio_gpu_virgl_reset(VirtIOGPU *g)
 {
     virgl_renderer_reset();
+
+    virtio_gpu_virgl_reset_async_fences(g);
 }
 
 int virtio_gpu_virgl_init(VirtIOGPU *g)
@@ -1190,6 +1306,12 @@ 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_CHECK_VERSION(1, 1, 2)
+        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;
+#endif
     }
 #endif
 #ifdef VIRGL_RENDERER_D3D11_SHARE_TEXTURE
@@ -1223,6 +1345,11 @@ int virtio_gpu_virgl_init(VirtIOGPU *g)
     gl->cmdq_resume_bh = virtio_bh_io_new_guarded(DEVICE(g),
                                                   virtio_gpu_virgl_resume_cmdq_bh,
                                                   g);
+#if VIRGL_CHECK_VERSION(1, 1, 2)
+    gl->async_fence_bh = virtio_bh_io_new_guarded(DEVICE(g),
+                                                  virtio_gpu_virgl_async_fence_bh,
+                                                  g);
+#endif
 #endif
 
     return 0;

diff --git a/include/hw/virtio/virtio-gpu.h b/include/hw/virtio/virtio-gpu.h
index 65312f869ddb051d73bfb82abfafb3866318fd9c..2610a32e4086a7a49acfdf791fd1fcb9aceed782 100644 (file)
--- a/include/hw/virtio/virtio-gpu.h
+++ b/include/hw/virtio/virtio-gpu.h
@@ -233,6 +233,13 @@ struct VirtIOGPUClass {
                              Error **errp);
 };
 
+struct virtio_gpu_virgl_context_fence {
+    uint32_t ctx_id;
+    uint32_t ring_idx;
+    uint64_t fence_id;
+    QSLIST_ENTRY(virtio_gpu_virgl_context_fence) next;
+};
+
 /* VirtIOGPUGL renderer states */
 typedef enum {
     RS_START,       /* starting state */
@@ -250,6 +257,9 @@ struct VirtIOGPUGL {
     QEMUTimer *print_stats;
 
     QEMUBH *cmdq_resume_bh;
+
+    QEMUBH *async_fence_bh;
+    QSLIST_HEAD(, virtio_gpu_virgl_context_fence) async_fenceq;
 };
 
 struct VhostUserGPU {
@@ -380,5 +390,6 @@ 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

diff --git a/meson.build b/meson.build
index 6b1838b159eb6ee086145f332bcadab50b963374..0029c970b0847bc8b22d5df1708304a980dfa224 100644 (file)
--- a/meson.build
+++ b/meson.build
@@ -2524,6 +2524,8 @@ config_host_data.set('CONFIG_VNC_JPEG', jpeg.found())
 config_host_data.set('CONFIG_VNC_SASL', sasl.found())
 if virgl.found()
   config_host_data.set('VIRGL_VERSION_MAJOR', virgl.version().split('.')[0])
+  config_host_data.set('VIRGL_VERSION_MINOR', virgl.version().split('.')[1])
+  config_host_data.set('VIRGL_VERSION_MICRO', virgl.version().split('.')[2])
 endif
 config_host_data.set('CONFIG_VIRTFS', have_virtfs)
 config_host_data.set('CONFIG_VTE', vte.found())