drm/amdkfd: Fix debug unregister procedure on process termination

Take the dbgmgr lock and unregister before destroying the debug manager.
Do this before destroying the queues.

v2: Correct locking order in kfd_ioctl_dbg_register to ake sure the
process mutex and dbgmgr mutex are always taken in the same order.

Signed-off-by: Yair Shachar <yair.shachar@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index a25321ff448f2163f0a41b9b62b4bc5c6d1217c9..505d39156acdb1daa5300cc3bdbfd353d6085299 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -450,8 +450,8 @@ static int kfd_ioctl_dbg_register(struct file *filep,
                return -EINVAL;
        }
 
-       mutex_lock(kfd_get_dbgmgr_mutex());
        mutex_lock(&p->mutex);
+       mutex_lock(kfd_get_dbgmgr_mutex());
 
        /*
         * make sure that we have pdd, if this the first queue created for
@@ -479,8 +479,8 @@ static int kfd_ioctl_dbg_register(struct file *filep,
        }
 
 out:
-       mutex_unlock(&p->mutex);
        mutex_unlock(kfd_get_dbgmgr_mutex());
+       mutex_unlock(&p->mutex);
 
        return status;
 }

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index b81ad8164da603a72d88753bd75fd0b8bfe725cb..db08f8f53d4b60debbbabb6fbceb8ad5a025a778 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -224,17 +224,26 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn,
 
        mutex_lock(&p->mutex);
 
+       /* Iterate over all process device data structures and if the
+        * pdd is in debug mode, we should first force unregistration,
+        * then we will be able to destroy the queues
+        */
+       list_for_each_entry(pdd, &p->per_device_data, per_device_list) {
+               struct kfd_dev *dev = pdd->dev;
+
+               mutex_lock(kfd_get_dbgmgr_mutex());
+               if (dev && dev->dbgmgr && dev->dbgmgr->pasid == p->pasid) {
+                       if (!kfd_dbgmgr_unregister(dev->dbgmgr, p)) {
+                               kfd_dbgmgr_destroy(dev->dbgmgr);
+                               dev->dbgmgr = NULL;
+                       }
+               }
+               mutex_unlock(kfd_get_dbgmgr_mutex());
+       }
+
        kfd_process_dequeue_from_all_devices(p);
        pqm_uninit(&p->pqm);
 
-       /* Iterate over all process device data structure and check
-        * if we should delete debug managers
-        */
-       list_for_each_entry(pdd, &p->per_device_data, per_device_list)
-               if ((pdd->dev->dbgmgr) &&
-                               (pdd->dev->dbgmgr->pasid == p->pasid))
-                       kfd_dbgmgr_destroy(pdd->dev->dbgmgr);
-
        mutex_unlock(&p->mutex);
 
        /*
@@ -463,8 +472,16 @@ void kfd_process_iommu_unbind_callback(struct kfd_dev *dev, unsigned int pasid)
 
        pr_debug("Unbinding process %d from IOMMU\n", pasid);
 
-       if ((dev->dbgmgr) && (dev->dbgmgr->pasid == p->pasid))
-               kfd_dbgmgr_destroy(dev->dbgmgr);
+       mutex_lock(kfd_get_dbgmgr_mutex());
+
+       if (dev->dbgmgr && dev->dbgmgr->pasid == p->pasid) {
+               if (!kfd_dbgmgr_unregister(dev->dbgmgr, p)) {
+                       kfd_dbgmgr_destroy(dev->dbgmgr);
+                       dev->dbgmgr = NULL;
+               }
+       }
+
+       mutex_unlock(kfd_get_dbgmgr_mutex());
 
        pdd = kfd_get_process_device_data(dev, p);
        if (pdd)