drm/amdkfd: Free queue after unmap queue success

After queue unmap or remove from MES successfully, free queue sysfs
entries, doorbell and remove from queue list. Otherwise, application may
destroy queue again, cause below kernel warning or crash backtrace.

For outstanding queues, either application forget to destroy or failed
to destroy, kfd_process_notifier_release will remove queue sysfs
entries, kfd_process_wq_release will free queue doorbell.

v2: decrement_queue_count for MES queue

 refcount_t: underflow; use-after-free.
 WARNING: CPU: 7 PID: 3053 at lib/refcount.c:28
  Call Trace:
   kobject_put+0xd6/0x1a0
   kfd_procfs_del_queue+0x27/0x30 [amdgpu]
   pqm_destroy_queue+0xeb/0x240 [amdgpu]
   kfd_ioctl_destroy_queue+0x32/0x70 [amdgpu]
   kfd_ioctl+0x27d/0x500 [amdgpu]
   do_syscall_64+0x35/0x80

 WARNING: CPU: 2 PID: 3053 at drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_device_queue_manager.c:400
  Call Trace:
   deallocate_doorbell.isra.0+0x39/0x40 [amdgpu]
   destroy_queue_cpsch+0xb3/0x270 [amdgpu]
   pqm_destroy_queue+0x108/0x240 [amdgpu]
   kfd_ioctl_destroy_queue+0x32/0x70 [amdgpu]
   kfd_ioctl+0x27d/0x500 [amdgpu]

 general protection fault, probably for non-canonical address
0xdead000000000108:
 Call Trace:
  pqm_destroy_queue+0xf0/0x200 [amdgpu]
  kfd_ioctl_destroy_queue+0x2f/0x60 [amdgpu]
  kfd_ioctl+0x19b/0x600 [amdgpu]

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Graham Sider <Graham.Sider@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 21aeb05..213246a 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1872,6 +1872,22 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 
        }
 
+       if (q->properties.is_active) {
+               if (!dqm->dev->shared_resources.enable_mes) {
+                       retval = execute_queues_cpsch(dqm,
+                                                     KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
+                       if (retval == -ETIME)
+                               qpd->reset_wavefronts = true;
+               } else {
+                       retval = remove_queue_mes(dqm, q, qpd);
+               }
+
+               if (retval)
+                       goto failed_unmap_queue;
+
+               decrement_queue_count(dqm, qpd, q);
+       }
+
        mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type(
                        q->properties.type)];
 
@@ -1885,17 +1901,6 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 
        list_del(&q->list);
        qpd->queue_count--;
-       if (q->properties.is_active) {
-               if (!dqm->dev->shared_resources.enable_mes) {
-                       decrement_queue_count(dqm, qpd, q);
-                       retval = execute_queues_cpsch(dqm,
-                                                     KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
-                       if (retval == -ETIME)
-                               qpd->reset_wavefronts = true;
-               } else {
-                       retval = remove_queue_mes(dqm, q, qpd);
-               }
-       }
 
        /*
         * Unconditionally decrement this counter, regardless of the queue's
@@ -1912,6 +1917,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 
        return retval;
 
+failed_unmap_queue:
 failed_try_destroy_debugged_queue:
 
        dqm_unlock(dqm);

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index dc00484..99f2a64 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -419,7 +419,6 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
        }
 
        if (pqn->q) {
-               kfd_procfs_del_queue(pqn->q);
                dqm = pqn->q->device->dqm;
                retval = dqm->ops.destroy_queue(dqm, &pdd->qpd, pqn->q);
                if (retval) {
@@ -439,6 +438,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
                if (dev->shared_resources.enable_mes)
                        amdgpu_amdkfd_free_gtt_mem(dev->adev,
                                                   pqn->q->gang_ctx_bo);
+               kfd_procfs_del_queue(pqn->q);
                uninit_queue(pqn->q);
        }