drm/nouveau: chan: provide nouveau_channel_kill()

The new VM_BIND UAPI implementation introduced in subsequent commits
will allow asynchronous jobs processing push buffers and emitting fences.

If a job times out, we need a way to recover from this situation. For
now, simply kill the channel to unblock all hung up jobs and signal
userspace that the device is dead on the next EXEC or VM_BIND ioctl.

Reviewed-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Danilo Krummrich <dakr@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230804182406.5222-10-dakr@redhat.com

Author: dakr

drivers/gpu/drm/nouveau/nouveau_chan.c

@@ -40,16 +40,24 @@ MODULE_PARM_DESC(vram_pushbuf, "Create DMA push buffers in VRAM");
 int nouveau_vram_pushbuf;
 module_param_named(vram_pushbuf, nouveau_vram_pushbuf, int, 0400);
 
+void
+nouveau_channel_kill(struct nouveau_channel *chan)
+{
+	atomic_set(&chan->killed, 1);
+	if (chan->fence)
+		nouveau_fence_context_kill(chan->fence, -ENODEV);
+}
+
 static int
 nouveau_channel_killed(struct nvif_event *event, void *repv, u32 repc)
 {
 	struct nouveau_channel *chan = container_of(event, typeof(*chan), kill);
 	struct nouveau_cli *cli = (void *)chan->user.client;
 
 	NV_PRINTK(warn, cli, "channel %d killed!\n", chan->chid);
-	atomic_set(&chan->killed, 1);
-	if (chan->fence)
-		nouveau_fence_context_kill(chan->fence, -ENODEV);
+
+	if (unlikely(!atomic_read(&chan->killed)))
+		nouveau_channel_kill(chan);
 
 	return NVIF_EVENT_DROP;
 }

drivers/gpu/drm/nouveau/nouveau_chan.h

@@ -66,6 +66,7 @@ int  nouveau_channel_new(struct nouveau_drm *, struct nvif_device *, bool priv,
 			 u32 vram, u32 gart, struct nouveau_channel **);
 void nouveau_channel_del(struct nouveau_channel **);
 int  nouveau_channel_idle(struct nouveau_channel *);
+void nouveau_channel_kill(struct nouveau_channel *);
 
 extern int nouveau_vram_pushbuf;