drm/nouveau: Refactor context destruction to avoid a lock ordering issue.
The destroy_context() engine hooks call gpuobj management functions to
release the channel resources, these functions use HARDIRQ-unsafe locks
whereas destroy_context() is called with the HARDIRQ-safe
context_switch_lock held, that's a lock ordering violation.
Push the engine-specific channel destruction logic into destroy_context()
and let the hardware-specific code lock and unlock when it's actually
needed. Change the engine destruction order to avoid a race in the small
gap between pgraph and pfifo context uninitialization.
Reported-by: Marcin Slusarz <marcin.slusarz@gmail.com>
Signed-off-by: Francisco Jerez <currojerez@riseup.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
diff --git a/drivers/gpu/drm/nouveau/nv10_graph.c b/drivers/gpu/drm/nouveau/nv10_graph.c
index cd931b5..e3a87a6 100644
--- a/drivers/gpu/drm/nouveau/nv10_graph.c
+++ b/drivers/gpu/drm/nouveau/nv10_graph.c
@@ -875,10 +875,25 @@
void nv10_graph_destroy_context(struct nouveau_channel *chan)
{
+ struct drm_device *dev = chan->dev;
+ struct drm_nouveau_private *dev_priv = dev->dev_private;
+ struct nouveau_pgraph_engine *pgraph = &dev_priv->engine.graph;
struct graph_state *pgraph_ctx = chan->pgraph_ctx;
+ unsigned long flags;
+ spin_lock_irqsave(&dev_priv->context_switch_lock, flags);
+ pgraph->fifo_access(dev, false);
+
+ /* Unload the context if it's the currently active one */
+ if (pgraph->channel(dev) == chan)
+ pgraph->unload_context(dev);
+
+ /* Free the context resources */
kfree(pgraph_ctx);
chan->pgraph_ctx = NULL;
+
+ pgraph->fifo_access(dev, true);
+ spin_unlock_irqrestore(&dev_priv->context_switch_lock, flags);
}
void