drm/i915: unload: fix error_work races

This is the first patch to clean up module unload races due to
outstanding timers/work. Preparatory step: Thou shalt not destroy
the workqueue when new work might still get enqued.

Now error_work gets queued by the hangcheck timer and only (atomically)
reads the chip wedged status. So cancel it right after the hangcheck
timer is killed. But the hangcheck is armed by interrupts, so move
everything after irqs are disabled.

Also change a del_timer to a del_timer_sync in the ums gem code, the
hangcheck timer is self-rearming.

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 9d67b48..736cca8 100644 (file)
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -2256,9 +2256,6 @@ int i915_driver_unload(struct drm_device *dev)
        i915_mch_dev = NULL;
        spin_unlock(&mchdev_lock);
 
-       destroy_workqueue(dev_priv->wq);
-       del_timer_sync(&dev_priv->hangcheck_timer);
-
        io_mapping_free(dev_priv->mm.gtt_mapping);
        if (dev_priv->mm.gtt_mtrr >= 0) {
                mtrr_del(dev_priv->mm.gtt_mtrr, dev->agp->base,
@@ -2283,6 +2280,9 @@ int i915_driver_unload(struct drm_device *dev)
                vga_client_register(dev->pdev, NULL, NULL, NULL);
        }
 
+       del_timer_sync(&dev_priv->hangcheck_timer);
+       cancel_work_sync(&dev_priv->error_work);
+
        if (dev->pdev->msi_enabled)
                pci_disable_msi(dev->pdev);
 
@@ -2307,6 +2307,8 @@ int i915_driver_unload(struct drm_device *dev)
 
        intel_teardown_mchbar(dev);
 
+       destroy_workqueue(dev_priv->wq);
+
        pci_dev_put(dev_priv->bridge_dev);
        kfree(dev->dev_private);
 

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 16fca1d..4cccdce 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4408,7 +4408,7 @@ i915_gem_idle(struct drm_device *dev)
         * And not confound mm.suspended!
         */
        dev_priv->mm.suspended = 1;
-       del_timer(&dev_priv->hangcheck_timer);
+       del_timer_sync(&dev_priv->hangcheck_timer);
 
        i915_kernel_lost_context(dev);
        i915_gem_cleanup_ringbuffer(dev);