drm/i915: Fix userptr deadlock with MAP_FIXED
diff mbox

Message ID 1435576151-17803-1-git-send-email-chris@chris-wilson.co.uk
State New
Headers show

Commit Message

Chris Wilson June 29, 2015, 11:09 a.m. UTC
Micha? Winiarski found a really evil way to trigger a struct_mutex
deadlock with userptr. He found that if he allocated a userptr bo and
then GTT mmaped another bo, or even itself, at the same address as the
userptr using MAP_FIXED, he could then cause a deadlock any time we then
had to invalidate the GTT mmappings (so at will).

To counter act the deadlock, we make the observation that when the
MAP_FIXED is made we would have an invalidate_range event for our
object. After that we should no longer alias with the rogue mmapping. If
we are then able to mark the object as no longer in use after the first
invalidate, we do not need to grab the struct_mutex for the subsequent

The patch makes one eye-catching change. That is the removal serial=0
after detecting a to-be-freed object inside the invalidate walker. I
felt setting serial=0 was a questionable pessismation: it denies us the
chance to reuse the current iterator for the next loop (before it is
freed) and being explicit makes the reader question the validity of the
locking (since the object-free race could occur elsewhere). The
serialisation of the iterator is through the spinlock, if the object is
freed before the next loop then the notifier.serial will be incremented
and we start the walk from the beginning as we detect the invalid cache.

Reported-by: Micha? Winiarski <michal.winiarski@intel.com>
Testcase: igt/gem_userptr_blits/map-fixed*
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Micha? Winiarski <michal.winiarski@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: stable@vger.kernel.org
 drivers/gpu/drm/i915/i915_gem_userptr.c | 43 +++++++++++++++++++++++++++------
 1 file changed, 36 insertions(+), 7 deletions(-)

diff mbox

diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index cb367d9f7909..8af2a01d726a 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -59,6 +59,7 @@  struct i915_mmu_object {
 	struct interval_tree_node it;
 	struct list_head link;
 	struct drm_i915_gem_object *obj;
+	bool active;
 	bool is_linear;
@@ -114,7 +115,8 @@  restart:
 		obj = mo->obj;
-		if (!kref_get_unless_zero(&obj->base.refcount))
+		if (!mo->active ||
+		    !kref_get_unless_zero(&obj->base.refcount))
@@ -151,7 +153,8 @@  static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 			it = interval_tree_iter_first(&mn->objects, start, end);
 		if (it != NULL) {
-			obj = container_of(it, struct i915_mmu_object, it)->obj;
+			struct i915_mmu_object *mo =
+				container_of(it, struct i915_mmu_object, it);
 			/* The mmu_object is released late when destroying the
 			 * GEM object so it is entirely possible to gain a
@@ -160,11 +163,9 @@  static void i915_gem_userptr_mn_invalidate_range_start(struct mmu_notifier *_mn,
 			 * the struct_mutex - and consequently use it after it
 			 * is freed and then double free it.
-			if (!kref_get_unless_zero(&obj->base.refcount)) {
-				spin_unlock(&mn->lock);
-				serial = 0;
-				continue;
-			}
+			if (mo->active &&
+			    kref_get_unless_zero(&mo->obj->base.refcount))
+				obj = mo->obj;
 			serial = mn->serial;
@@ -606,6 +607,20 @@  __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
+static void
+__i915_gem_userptr_set_active(struct drm_i915_gem_object *obj,
+			      bool value)
+	if (obj->userptr.mmu_object == NULL)
+		return;
+	spin_lock(&obj->userptr.mmu_object->mn->lock);
+	obj->userptr.mmu_object->active = value;
+	spin_unlock(&obj->userptr.mmu_object->mn->lock);
 static int
 i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
@@ -613,6 +628,18 @@  i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 	struct page **pvec;
 	int pinned, ret;
+	/* During mm_invalidate_range we need to cancel any userptr that
+	 * overlaps the range being invalidated. Doing so requires the
+	 * struct_mutex, and that risks recursion. In order to cause recursion,
+	 * the user must aliasing the userptr address space with a GTT
+	 * mmapping (possible with a MAP_FIXED) - then we we have to invalidate
+	 * that mmaping, mm_invalidate_range is called with the userptr
+	 * address *and* the struct_mutex held.  To prevent that we set
+	 * a flag under the i915_mmu_notifier spinlock to indicate whether
+	 * this object is valid.
+	 */
+	__i915_gem_userptr_set_active(obj, true);
 	/* If userspace should engineer that these pages are replaced in
 	 * the vma between us binding this page into the GTT and completion
 	 * of rendering... Their loss. If they change the mapping of their
@@ -732,6 +759,8 @@  i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj)
+	__i915_gem_userptr_set_active(obj, false);
 static void