This is a note to let you know that I've just added the patch titled
drm/xe: fix UAF around queue destruction
to the 6.10-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
drm-xe-fix-uaf-around-queue-destruction.patch
and it can be found in the queue-6.10 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 671d0dcf2db7037f2c00f262a699860c3609d664
Author: Matthew Auld <matthew.auld@xxxxxxxxx>
Date: Mon Sep 23 15:56:48 2024 +0100
drm/xe: fix UAF around queue destruction
[ Upstream commit 2d2be279f1ca9e7288282d4214f16eea8a727cdb ]
We currently do stuff like queuing the final destruction step on a
random system wq, which will outlive the driver instance. With bad
timing we can teardown the driver with one or more work workqueue still
being alive leading to various UAF splats. Add a fini step to ensure
user queues are properly torn down. At this point GuC should already be
nuked so queue itself should no longer be referenced from hw pov.
v2 (Matt B)
- Looks much safer to use a waitqueue and then just wait for the
xa_array to become empty before triggering the drain.
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2317
Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs")
Signed-off-by: Matthew Auld <matthew.auld@xxxxxxxxx>
Cc: Matthew Brost <matthew.brost@xxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx> # v6.8+
Reviewed-by: Matthew Brost <matthew.brost@xxxxxxxxx>
Link: https://patchwork.freedesktop.org/patch/msgid/20240923145647.77707-2-matthew.auld@xxxxxxxxx
(cherry picked from commit 861108666cc0e999cffeab6aff17b662e68774e3)
Signed-off-by: Lucas De Marchi <lucas.demarchi@xxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index a1cbdafbff75e..599bf7f9e8c5c 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -231,6 +231,9 @@ static void xe_device_destroy(struct drm_device *dev, void *dummy)
if (xe->unordered_wq)
destroy_workqueue(xe->unordered_wq);
+ if (xe->destroy_wq)
+ destroy_workqueue(xe->destroy_wq);
+
ttm_device_fini(&xe->ttm);
}
@@ -293,8 +296,9 @@ struct xe_device *xe_device_create(struct pci_dev *pdev,
xe->preempt_fence_wq = alloc_ordered_workqueue("xe-preempt-fence-wq", 0);
xe->ordered_wq = alloc_ordered_workqueue("xe-ordered-wq", 0);
xe->unordered_wq = alloc_workqueue("xe-unordered-wq", 0, 0);
+ xe->destroy_wq = alloc_workqueue("xe-destroy-wq", 0, 0);
if (!xe->ordered_wq || !xe->unordered_wq ||
- !xe->preempt_fence_wq) {
+ !xe->preempt_fence_wq || !xe->destroy_wq) {
/*
* Cleanup done in xe_device_destroy via
* drmm_add_action_or_reset register above
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 2e62450d86e18..f671300e0c9bd 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -376,6 +376,9 @@ struct xe_device {
/** @unordered_wq: used to serialize unordered work, mostly display */
struct workqueue_struct *unordered_wq;
+ /** @destroy_wq: used to serialize user destroy work, like queue */
+ struct workqueue_struct *destroy_wq;
+
/** @tiles: device tiles */
struct xe_tile tiles[XE_MAX_TILES_PER_DEVICE];
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index a40287a7c3de8..a0f8299488030 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -233,10 +233,26 @@ static struct workqueue_struct *get_submit_wq(struct xe_guc *guc)
}
#endif
+static void xe_guc_submit_fini(struct xe_guc *guc)
+{
+ struct xe_device *xe = guc_to_xe(guc);
+ struct xe_gt *gt = guc_to_gt(guc);
+ int ret;
+
+ ret = wait_event_timeout(guc->submission_state.fini_wq,
+ xa_empty(&guc->submission_state.exec_queue_lookup),
+ HZ * 5);
+
+ drain_workqueue(xe->destroy_wq);
+
+ xe_gt_assert(gt, ret);
+}
+
static void guc_submit_fini(struct drm_device *drm, void *arg)
{
struct xe_guc *guc = arg;
+ xe_guc_submit_fini(guc);
xa_destroy(&guc->submission_state.exec_queue_lookup);
free_submit_wq(guc);
}
@@ -278,6 +294,8 @@ int xe_guc_submit_init(struct xe_guc *guc)
xa_init(&guc->submission_state.exec_queue_lookup);
+ init_waitqueue_head(&guc->submission_state.fini_wq);
+
primelockdep(guc);
return drmm_add_action_or_reset(&xe->drm, guc_submit_fini, guc);
@@ -294,6 +312,9 @@ static void __release_guc_id(struct xe_guc *guc, struct xe_exec_queue *q, u32 xa
xe_guc_id_mgr_release_locked(&guc->submission_state.idm,
q->guc->id, q->width);
+
+ if (xa_empty(&guc->submission_state.exec_queue_lookup))
+ wake_up(&guc->submission_state.fini_wq);
}
static int alloc_guc_id(struct xe_guc *guc, struct xe_exec_queue *q)
@@ -1025,13 +1046,16 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)
static void guc_exec_queue_fini_async(struct xe_exec_queue *q)
{
+ struct xe_guc *guc = exec_queue_to_guc(q);
+ struct xe_device *xe = guc_to_xe(guc);
+
INIT_WORK(&q->guc->fini_async, __guc_exec_queue_fini_async);
/* We must block on kernel engines so slabs are empty on driver unload */
if (q->flags & EXEC_QUEUE_FLAG_PERMANENT)
__guc_exec_queue_fini_async(&q->guc->fini_async);
else
- queue_work(system_wq, &q->guc->fini_async);
+ queue_work(xe->destroy_wq, &q->guc->fini_async);
}
static void __guc_exec_queue_fini(struct xe_guc *guc, struct xe_exec_queue *q)
diff --git a/drivers/gpu/drm/xe/xe_guc_types.h b/drivers/gpu/drm/xe/xe_guc_types.h
index 546ac6350a31f..69046f6982717 100644
--- a/drivers/gpu/drm/xe/xe_guc_types.h
+++ b/drivers/gpu/drm/xe/xe_guc_types.h
@@ -81,6 +81,8 @@ struct xe_guc {
#endif
/** @submission_state.enabled: submission is enabled */
bool enabled;
+ /** @submission_state.fini_wq: submit fini wait queue */
+ wait_queue_head_t fini_wq;
} submission_state;
/** @hwconfig: Hardware config state */
struct {
