drm/i915: remove user GTT mappings early during runtime suspend

Currently user space can access GEM buffers mapped to GTT through
existing mappings concurrently while the platform specific suspend
handlers are running. Since these handlers may change the HW state in a
way that would break such accesses, remove the mappings before calling
the handlers. Spotted by Ville.

Also Chris pointed out that the lists that i915_gem_release_all_mmaps()
walks through need dev->struct_mutex, so take this lock. There is a
potential deadlock against a concurrent RPM resume, resolve this by
aborting and rescheduling the suspend (Daniel).

v2:
- take struct_mutex around i915_gem_release_all_mmaps() (Chris, Daniel)

Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Robert Beckett <robert.beckett@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

1 files changed, 25 insertions, 2 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index c83c83b..acb93fa 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -36,6 +36,7 @@
 
 #include <linux/console.h>
 #include <linux/module.h>
+#include <linux/pm_runtime.h>
 #include <drm/drm_crtc_helper.h>
 
 static struct drm_driver driver;
@@ -1356,6 +1357,30 @@ static int intel_runtime_suspend(struct device *device)
 	DRM_DEBUG_KMS("Suspending device\n");
 
 	/*
+	 * We could deadlock here in case another thread holding struct_mutex
+	 * calls RPM suspend concurrently, since the RPM suspend will wait
+	 * first for this RPM suspend to finish. In this case the concurrent
+	 * RPM resume will be followed by its RPM suspend counterpart. Still
+	 * for consistency return -EAGAIN, which will reschedule this suspend.
+	 */
+	if (!mutex_trylock(&dev->struct_mutex)) {
+		DRM_DEBUG_KMS("device lock contention, deffering suspend\n");
+		/*
+		 * Bump the expiration timestamp, otherwise the suspend won't
+		 * be rescheduled.
+		 */
+		pm_runtime_mark_last_busy(device);
+
+		return -EAGAIN;
+	}
+	/*
+	 * We are safe here against re-faults, since the fault handler takes
+	 * an RPM reference.
+	 */
+	i915_gem_release_all_mmaps(dev_priv);
+	mutex_unlock(&dev->struct_mutex);
+
+	/*
 	 * rps.work can't be rearmed here, since we get here only after making
 	 * sure the GPU is idle and the RPS freq is set to the minimum. See
 	 * intel_mark_idle().
@@ -1381,8 +1406,6 @@ static int intel_runtime_suspend(struct device *device)
 		return ret;
 	}
 
-	i915_gem_release_all_mmaps(dev_priv);
-
 	del_timer_sync(&dev_priv->gpu_error.hangcheck_timer);
 	dev_priv->pm.suspended = true;