drm/amdkfd: Add per-process IDR for buffer handles

Also used for cleaning up on process termination.

v2: Refactored cleanup on process termination

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 0d5d924b31ef6936669224a059122a2cf8850d6b..b2b5ef8c45369717013900ff76f1ab44574047be 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -543,6 +543,9 @@ struct kfd_process_device {
        struct file *drm_file;
        void *vm;
 
+       /* GPUVM allocations storage */
+       struct idr alloc_idr;
+
        /* Flag used to tell the pdd has dequeued from the dqm.
         * This is used to prevent dev->dqm->ops.process_termination() from
         * being called twice when it is already called in IOMMU callback
@@ -678,6 +681,14 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev,
 int kfd_reserved_mem_mmap(struct kfd_process *process,
                          struct vm_area_struct *vma);
 
+/* KFD process API for creating and translating handles */
+int kfd_process_device_create_obj_handle(struct kfd_process_device *pdd,
+                                       void *mem);
+void *kfd_process_device_translate_handle(struct kfd_process_device *p,
+                                       int handle);
+void kfd_process_device_remove_obj_handle(struct kfd_process_device *pdd,
+                                       int handle);
+
 /* Process device data iterator */
 struct kfd_process_device *kfd_get_first_process_device_data(
                                                        struct kfd_process *p);

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 6618aaa6b84f7029c1fcb99ac9a9fbd16782d181..a2ae0236a3ea1bb806f7e1ed5f5c909e66e68035 100644 (file)
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -150,6 +150,40 @@ void kfd_unref_process(struct kfd_process *p)
        kref_put(&p->ref, kfd_process_ref_release);
 }
 
+static void kfd_process_device_free_bos(struct kfd_process_device *pdd)
+{
+       struct kfd_process *p = pdd->process;
+       void *mem;
+       int id;
+
+       /*
+        * Remove all handles from idr and release appropriate
+        * local memory object
+        */
+       idr_for_each_entry(&pdd->alloc_idr, mem, id) {
+               struct kfd_process_device *peer_pdd;
+
+               list_for_each_entry(peer_pdd, &p->per_device_data,
+                                   per_device_list) {
+                       if (!peer_pdd->vm)
+                               continue;
+                       peer_pdd->dev->kfd2kgd->unmap_memory_to_gpu(
+                               peer_pdd->dev->kgd, mem, peer_pdd->vm);
+               }
+
+               pdd->dev->kfd2kgd->free_memory_of_gpu(pdd->dev->kgd, mem);
+               kfd_process_device_remove_obj_handle(pdd, id);
+       }
+}
+
+static void kfd_process_free_outstanding_kfd_bos(struct kfd_process *p)
+{
+       struct kfd_process_device *pdd;
+
+       list_for_each_entry(pdd, &p->per_device_data, per_device_list)
+               kfd_process_device_free_bos(pdd);
+}
+
 static void kfd_process_destroy_pdds(struct kfd_process *p)
 {
        struct kfd_process_device *pdd, *temp;
@@ -171,6 +205,8 @@ static void kfd_process_destroy_pdds(struct kfd_process *p)
                        free_pages((unsigned long)pdd->qpd.cwsr_kaddr,
                                get_order(KFD_CWSR_TBA_TMA_SIZE));
 
+               idr_destroy(&pdd->alloc_idr);
+
                kfree(pdd);
        }
 }
@@ -187,6 +223,8 @@ static void kfd_process_wq_release(struct work_struct *work)
 
        kfd_iommu_unbind_process(p);
 
+       kfd_process_free_outstanding_kfd_bos(p);
+
        kfd_process_destroy_pdds(p);
        dma_fence_put(p->ef);
 
@@ -371,6 +409,7 @@ static struct kfd_process *create_process(const struct task_struct *thread,
        return process;
 
 err_init_cwsr:
+       kfd_process_free_outstanding_kfd_bos(process);
        kfd_process_destroy_pdds(process);
 err_init_apertures:
        pqm_uninit(&process->pqm);
@@ -421,6 +460,9 @@ struct kfd_process_device *kfd_create_process_device_data(struct kfd_dev *dev,
        pdd->already_dequeued = false;
        list_add(&pdd->per_device_list, &p->per_device_data);
 
+       /* Init idr used for memory handle translation */
+       idr_init(&pdd->alloc_idr);
+
        return pdd;
 }
 
@@ -520,6 +562,37 @@ bool kfd_has_process_device_data(struct kfd_process *p)
        return !(list_empty(&p->per_device_data));
 }
 
+/* Create specific handle mapped to mem from process local memory idr
+ * Assumes that the process lock is held.
+ */
+int kfd_process_device_create_obj_handle(struct kfd_process_device *pdd,
+                                       void *mem)
+{
+       return idr_alloc(&pdd->alloc_idr, mem, 0, 0, GFP_KERNEL);
+}
+
+/* Translate specific handle from process local memory idr
+ * Assumes that the process lock is held.
+ */
+void *kfd_process_device_translate_handle(struct kfd_process_device *pdd,
+                                       int handle)
+{
+       if (handle < 0)
+               return NULL;
+
+       return idr_find(&pdd->alloc_idr, handle);
+}
+
+/* Remove specific handle from process local memory idr
+ * Assumes that the process lock is held.
+ */
+void kfd_process_device_remove_obj_handle(struct kfd_process_device *pdd,
+                                       int handle)
+{
+       if (handle >= 0)
+               idr_remove(&pdd->alloc_idr, handle);
+}
+
 /* This increments the process->ref counter. */
 struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid)
 {