drm/amdgpu: use the new drm_exec object for CS v3

Use the new component here as well and remove the old handling.

v2: drop dupplicate handling
v3: fix memory leak pointed out by Tatsuyuki
Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230711133122.3710-7-christian.koenig@amd.com

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -53,7 +53,6 @@
 
 #include <drm/ttm/ttm_bo.h>
 #include <drm/ttm/ttm_placement.h>
-#include <drm/ttm/ttm_execbuf_util.h>
 
 #include <drm/amdgpu_drm.h>
 #include <drm/drm_gem.h>

drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c

@@ -28,6 +28,7 @@
  *    Christian König <deathsimple@vodafone.de>
  */
 
+#include <linux/sort.h>
 #include <linux/uaccess.h>
 
 #include "amdgpu.h"
@@ -50,13 +51,20 @@ static void amdgpu_bo_list_free(struct kref *ref)
 						   refcount);
 	struct amdgpu_bo_list_entry *e;
 
-	amdgpu_bo_list_for_each_entry(e, list) {
-		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);
+	amdgpu_bo_list_for_each_entry(e, list)
+		amdgpu_bo_unref(&e->bo);
+	call_rcu(&list->rhead, amdgpu_bo_list_free_rcu);
+}
 
-		amdgpu_bo_unref(&bo);
-	}
+static int amdgpu_bo_list_entry_cmp(const void *_a, const void *_b)
+{
+	const struct amdgpu_bo_list_entry *a = _a, *b = _b;
 
-	call_rcu(&list->rhead, amdgpu_bo_list_free_rcu);
+	if (a->priority > b->priority)
+		return 1;
+	if (a->priority < b->priority)
+		return -1;
+	return 0;
 }
 
 int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp,
@@ -118,7 +126,7 @@ int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp,
 
 		entry->priority = min(info[i].bo_priority,
 				      AMDGPU_BO_LIST_MAX_PRIORITY);
-		entry->tv.bo = &bo->tbo;
+		entry->bo = bo;
 
 		if (bo->preferred_domains == AMDGPU_GEM_DOMAIN_GDS)
 			list->gds_obj = bo;
@@ -133,6 +141,8 @@ int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp,
 
 	list->first_userptr = first_userptr;
 	list->num_entries = num_entries;
+	sort(array, last_entry, sizeof(struct amdgpu_bo_list_entry),
+	     amdgpu_bo_list_entry_cmp, NULL);
 
 	trace_amdgpu_cs_bo_status(list->num_entries, total_size);
 
@@ -141,16 +151,10 @@ int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp,
 	return 0;
 
 error_free:
-	for (i = 0; i < last_entry; ++i) {
-		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(array[i].tv.bo);
-
-		amdgpu_bo_unref(&bo);
-	}
-	for (i = first_userptr; i < num_entries; ++i) {
-		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(array[i].tv.bo);
-
-		amdgpu_bo_unref(&bo);
-	}
+	for (i = 0; i < last_entry; ++i)
+		amdgpu_bo_unref(&array[i].bo);
+	for (i = first_userptr; i < num_entries; ++i)
+		amdgpu_bo_unref(&array[i].bo);
 	kvfree(list);
 	return r;
 
@@ -182,41 +186,6 @@ int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id,
 	return -ENOENT;
 }
 
-void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
-			     struct list_head *validated)
-{
-	/* This is based on the bucket sort with O(n) time complexity.
-	 * An item with priority "i" is added to bucket[i]. The lists are then
-	 * concatenated in descending order.
-	 */
-	struct list_head bucket[AMDGPU_BO_LIST_NUM_BUCKETS];
-	struct amdgpu_bo_list_entry *e;
-	unsigned i;
-
-	for (i = 0; i < AMDGPU_BO_LIST_NUM_BUCKETS; i++)
-		INIT_LIST_HEAD(&bucket[i]);
-
-	/* Since buffers which appear sooner in the relocation list are
-	 * likely to be used more often than buffers which appear later
-	 * in the list, the sort mustn't change the ordering of buffers
-	 * with the same priority, i.e. it must be stable.
-	 */
-	amdgpu_bo_list_for_each_entry(e, list) {
-		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo);
-		unsigned priority = e->priority;
-
-		if (!bo->parent)
-			list_add_tail(&e->tv.head, &bucket[priority]);
-
-		e->user_pages = NULL;
-		e->range = NULL;
-	}
-
-	/* Connect the sorted buckets in the output list. */
-	for (i = 0; i < AMDGPU_BO_LIST_NUM_BUCKETS; i++)
-		list_splice(&bucket[i], validated);
-}
-
 void amdgpu_bo_list_put(struct amdgpu_bo_list *list)
 {
 	kref_put(&list->refcount, amdgpu_bo_list_free);

drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h

@@ -23,7 +23,6 @@
 #ifndef __AMDGPU_BO_LIST_H__
 #define __AMDGPU_BO_LIST_H__
 
-#include <drm/ttm/ttm_execbuf_util.h>
 #include <drm/amdgpu_drm.h>
 
 struct hmm_range;
@@ -36,7 +35,7 @@ struct amdgpu_bo_va;
 struct amdgpu_fpriv;
 
 struct amdgpu_bo_list_entry {
-	struct ttm_validate_buffer	tv;
+	struct amdgpu_bo		*bo;
 	struct amdgpu_bo_va		*bo_va;
 	uint32_t			priority;
 	struct page			**user_pages;
@@ -60,8 +59,6 @@ struct amdgpu_bo_list {
 
 int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id,
 		       struct amdgpu_bo_list **result);
-void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
-			     struct list_head *validated);
 void amdgpu_bo_list_put(struct amdgpu_bo_list *list);
 int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in,
 				      struct drm_amdgpu_bo_list_entry **info_param);

drivers/gpu/drm/amd/amdgpu/amdgpu_cs.h

@@ -24,6 +24,7 @@
 #define __AMDGPU_CS_H__
 
 #include <linux/ww_mutex.h>
+#include <drm/drm_exec.h>
 
 #include "amdgpu_job.h"
 #include "amdgpu_bo_list.h"
@@ -62,11 +63,9 @@ struct amdgpu_cs_parser {
 	struct amdgpu_job	*gang_leader;
 
 	/* buffer objects */
-	struct ww_acquire_ctx		ticket;
+	struct drm_exec			exec;
 	struct amdgpu_bo_list		*bo_list;
 	struct amdgpu_mn		*mn;
-	struct amdgpu_bo_list_entry	vm_pd;
-	struct list_head		validated;
 	struct dma_fence		*fence;
 	uint64_t			bytes_moved_threshold;
 	uint64_t			bytes_moved_vis_threshold;
@@ -74,7 +73,7 @@ struct amdgpu_cs_parser {
 	uint64_t			bytes_moved_vis;
 
 	/* user fence */
-	struct amdgpu_bo_list_entry	uf_entry;
+	struct amdgpu_bo		*uf_bo;
 
 	unsigned			num_post_deps;
 	struct amdgpu_cs_post_dep	*post_deps;

drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c

@@ -339,28 +339,6 @@ void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
 	amdgpu_vm_bo_evicted(base);
 }
 
-/**
- * amdgpu_vm_get_pd_bo - add the VM PD to a validation list
- *
- * @vm: vm providing the BOs
- * @validated: head of validation list
- * @entry: entry to add
- *
- * Add the page directory to the list of BOs to
- * validate for command submission.
- */
-void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
-			 struct list_head *validated,
-			 struct amdgpu_bo_list_entry *entry)
-{
-	entry->priority = 0;
-	entry->tv.bo = &vm->root.bo->tbo;
-	/* Two for VM updates, one for TTM and one for the CS job */
-	entry->tv.num_shared = 4;
-	entry->user_pages = NULL;
-	list_add(&entry->tv.head, validated);
-}
-
 /**
  * amdgpu_vm_lock_pd - lock PD in drm_exec
  *

drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h

@@ -398,9 +398,6 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
-void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
-			 struct list_head *validated,
-			 struct amdgpu_bo_list_entry *entry);
 int amdgpu_vm_lock_pd(struct amdgpu_vm *vm, struct drm_exec *exec,
 		      unsigned int num_fences);
 bool amdgpu_vm_ready(struct amdgpu_vm *vm);