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>

1 files changed, 17 insertions, 0 deletions

diff --git a/drivers/gpu/drm/nouveau/nv50_fifo.c b/drivers/gpu/drm/nouveau/nv50_fifo.c
index 815960fe4f43..d3295aae0c4e 100644
--- a/drivers/gpu/drm/nouveau/nv50_fifo.c
+++ b/drivers/gpu/drm/nouveau/nv50_fifo.c
@@ -292,10 +292,23 @@ void
 nv50_fifo_destroy_context(struct nouveau_channel *chan)
 {
         struct drm_device *dev = chan->dev;
+        struct drm_nouveau_private *dev_priv = dev->dev_private;
+        struct nouveau_fifo_engine *pfifo = &dev_priv->engine.fifo;
         struct nouveau_gpuobj *ramfc = NULL;
+        unsigned long flags;
 
         NV_DEBUG(dev, "ch%d\n", chan->id);
 
+        spin_lock_irqsave(&dev_priv->context_switch_lock, flags);
+        pfifo->reassign(dev, false);
+
+        /* Unload the context if it's the currently active one */
+        if (pfifo->channel_id(dev) == chan->id) {
+                pfifo->disable(dev);
+                pfifo->unload_context(dev);
+                pfifo->enable(dev);
+        }
+
         /* This will ensure the channel is seen as disabled. */
         nouveau_gpuobj_ref(chan->ramfc, &ramfc);
         nouveau_gpuobj_ref(NULL, &chan->ramfc);
@@ -306,6 +319,10 @@ nv50_fifo_destroy_context(struct nouveau_channel *chan)
                 nv50_fifo_channel_disable(dev, 127);
         nv50_fifo_playlist_update(dev);
 
+        pfifo->reassign(dev, true);
+        spin_unlock_irqrestore(&dev_priv->context_switch_lock, flags);
+
+        /* Free the channel resources */
         nouveau_gpuobj_ref(NULL, &ramfc);
         nouveau_gpuobj_ref(NULL, &chan->cache);
 }