diff mbox series

[v3,3/4] drm/ttm, drm/amdgpu, drm/xe: Consider hitch moves within bulk sublist moves

Message ID 20240305160202.3555-4-thomas.hellstrom@linux.intel.com (mailing list archive)
State New, archived
Headers show
Series TTM unlockable restartable LRU list iteration | expand

Commit Message

Thomas Hellstrom March 5, 2024, 4:02 p.m. UTC
To address the problem with hitches moving when bulk move
sublists are lru-bumped, register the list cursors with the
ttm_lru_bulk_move structure when traversing its list, and
when lru-bumping the list, move the cursor hitch to the tail.
This also means it's mandatory for drivers to call
ttm_lru_bulk_move_init() and ttm_lru_bulk_move_fini() when
initializing and finalizing the bulk move structure, so add
those calls to the amdgpu- and xe driver.

Compared to v1 this is slightly more code but less fragile
and hopefully easier to understand.

v2:
- Completely rework the functionality
v3:
- Avoid a NULL pointer dereference assigning manager->mem_type

Cc: Christian König <christian.koenig@amd.com>
Cc: Somalapuram Amaranath <Amaranath.Somalapuram@amd.com>
Cc: <dri-devel@lists.freedesktop.org>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c |  4 ++
 drivers/gpu/drm/ttm/ttm_resource.c     | 90 +++++++++++++++++++++++++-
 drivers/gpu/drm/xe/xe_vm.c             |  4 ++
 include/drm/ttm/ttm_device.h           |  5 ++
 include/drm/ttm/ttm_resource.h         | 55 ++++++++++------
 5 files changed, 137 insertions(+), 21 deletions(-)

Comments

kernel test robot March 5, 2024, 10:42 p.m. UTC | #1
Hi Thomas,

kernel test robot noticed the following build warnings:

[auto build test WARNING on drm-misc/drm-misc-next]
[also build test WARNING on drm-intel/for-linux-next drm-tip/drm-tip]
[cannot apply to drm-intel/for-linux-next-fixes linus/master v6.8-rc7 next-20240305]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Thomas-Hellstr-m/drm-ttm-Allow-TTM-LRU-list-nodes-of-different-types/20240306-000453
base:   git://anongit.freedesktop.org/drm/drm-misc drm-misc-next
patch link:    https://lore.kernel.org/r/20240305160202.3555-4-thomas.hellstrom%40linux.intel.com
patch subject: [PATCH v3 3/4] drm/ttm, drm/amdgpu, drm/xe: Consider hitch moves within bulk sublist moves
config: arm-defconfig (https://download.01.org/0day-ci/archive/20240306/202403060640.zCXpVObi-lkp@intel.com/config)
compiler: clang version 14.0.6 (https://github.com/llvm/llvm-project.git f28c006a5895fc0e329fe15fead81e37457cb1d1)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240306/202403060640.zCXpVObi-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202403060640.zCXpVObi-lkp@intel.com/

All warnings (new ones prefixed by >>):

   In file included from drivers/gpu/drm/drm_gem_ttm_helper.c:5:
   In file included from include/drm/drm_gem_ttm_helper.h:10:
   In file included from include/drm/ttm/ttm_bo.h:39:
>> include/drm/ttm/ttm_device.h:286:31: warning: variable 'old' set but not used [-Wunused-but-set-variable]
           struct ttm_resource_manager *old;
                                        ^
   1 warning generated.


vim +/old +286 include/drm/ttm/ttm_device.h

   282	
   283	static inline void ttm_set_driver_manager(struct ttm_device *bdev, int type,
   284						  struct ttm_resource_manager *manager)
   285	{
 > 286		struct ttm_resource_manager *old;
   287	
   288		BUILD_BUG_ON(__builtin_constant_p(type) && type >= TTM_NUM_MEM_TYPES);
   289		old = bdev->man_drv[type];
   290		bdev->man_drv[type] = manager;
   291		if (manager)
   292			manager->mem_type = type;
   293	}
   294
diff mbox series

Patch

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index ed4a8c5d26d7..7c2ee5d12bc1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2264,6 +2264,8 @@  int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	if (r)
 		return r;
 
+	ttm_lru_bulk_move_init(&vm->lru_bulk_move);
+
 	vm->pte_support_ats = false;
 	vm->is_compute_context = false;
 
@@ -2324,6 +2326,7 @@  int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 error_free_delayed:
 	dma_fence_put(vm->last_tlb_flush);
 	dma_fence_put(vm->last_unlocked);
+	ttm_lru_bulk_move_fini(&adev->mman.bdev, &vm->lru_bulk_move);
 	amdgpu_vm_fini_entities(vm);
 
 	return r;
@@ -2497,6 +2500,7 @@  void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		}
 	}
 
+	ttm_lru_bulk_move_fini(&adev->mman.bdev, &vm->lru_bulk_move);
 }
 
 /**
diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c
index 971014fca10a..0acd4bf764b2 100644
--- a/drivers/gpu/drm/ttm/ttm_resource.c
+++ b/drivers/gpu/drm/ttm/ttm_resource.c
@@ -32,6 +32,49 @@ 
 
 #include <drm/drm_util.h>
 
+/* Detach the cursor from the bulk move list*/
+static void
+ttm_resource_cursor_clear_bulk(struct ttm_resource_cursor *cursor)
+{
+	cursor->bulk = NULL;
+	list_del_init(&cursor->bulk_link);
+}
+
+/* Move the cursor to the end of the bulk move list it's in */
+static void ttm_resource_cursor_move_bulk_tail(struct ttm_lru_bulk_move *bulk,
+					       struct ttm_resource_cursor *cursor)
+{
+	struct ttm_lru_bulk_move_pos *pos;
+
+	if (WARN_ON_ONCE(bulk != cursor->bulk)) {
+		list_del_init(&cursor->bulk_link);
+		return;
+	}
+
+	pos = &bulk->pos[cursor->man->mem_type][cursor->priority];
+	if (pos)
+		list_move(&cursor->hitch.link, &pos->last->lru.link);
+	ttm_resource_cursor_clear_bulk(cursor);
+}
+
+/* Move all cursors attached to a bulk move to its end */
+static void ttm_bulk_move_adjust_cursors(struct ttm_lru_bulk_move *bulk)
+{
+	struct ttm_resource_cursor *cursor, *next;
+
+	list_for_each_entry_safe(cursor, next, &bulk->cursor_list, bulk_link)
+		ttm_resource_cursor_move_bulk_tail(bulk, cursor);
+}
+
+/* Remove a cursor from an empty bulk move list */
+static void ttm_bulk_move_drop_cursors(struct ttm_lru_bulk_move *bulk)
+{
+	struct ttm_resource_cursor *cursor, *next;
+
+	list_for_each_entry_safe(cursor, next, &bulk->cursor_list, bulk_link)
+		ttm_resource_cursor_clear_bulk(cursor);
+}
+
 /**
  * ttm_resource_cursor_fini_locked() - Finalize the LRU list cursor usage
  * @cursor: The struct ttm_resource_cursor to finalize.
@@ -44,6 +87,7 @@  void ttm_resource_cursor_fini_locked(struct ttm_resource_cursor *cursor)
 {
 	lockdep_assert_held(&cursor->man->bdev->lru_lock);
 	list_del_init(&cursor->hitch.link);
+	ttm_resource_cursor_clear_bulk(cursor);
 }
 
 /**
@@ -72,9 +116,27 @@  void ttm_resource_cursor_fini(struct ttm_resource_cursor *cursor)
 void ttm_lru_bulk_move_init(struct ttm_lru_bulk_move *bulk)
 {
 	memset(bulk, 0, sizeof(*bulk));
+	INIT_LIST_HEAD(&bulk->cursor_list);
 }
 EXPORT_SYMBOL(ttm_lru_bulk_move_init);
 
+/**
+ * ttm_lru_bulk_move_fini - finalize a bulk move structure
+ * @bdev: The struct ttm_device
+ * @bulk: the structure to finalize
+ *
+ * Sanity checks that bulk moves don't have any
+ * resources left and hence no cursors attached.
+ */
+void ttm_lru_bulk_move_fini(struct ttm_device *bdev,
+			    struct ttm_lru_bulk_move *bulk)
+{
+	spin_lock(&bdev->lru_lock);
+	ttm_bulk_move_drop_cursors(bulk);
+	spin_unlock(&bdev->lru_lock);
+}
+EXPORT_SYMBOL(ttm_lru_bulk_move_fini);
+
 /**
  * ttm_lru_bulk_move_tail - bulk move range of resources to the LRU tail.
  *
@@ -87,6 +149,7 @@  void ttm_lru_bulk_move_tail(struct ttm_lru_bulk_move *bulk)
 {
 	unsigned i, j;
 
+	ttm_bulk_move_adjust_cursors(bulk);
 	for (i = 0; i < TTM_NUM_MEM_TYPES; ++i) {
 		for (j = 0; j < TTM_MAX_BO_PRIORITY; ++j) {
 			struct ttm_lru_bulk_move_pos *pos = &bulk->pos[i][j];
@@ -417,6 +480,7 @@  void ttm_resource_manager_init(struct ttm_resource_manager *man,
 	man->bdev = bdev;
 	man->size = size;
 	man->usage = 0;
+	man->mem_type = TTM_NUM_MEM_TYPES;
 
 	for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i)
 		INIT_LIST_HEAD(&man->lru[i]);
@@ -513,6 +577,27 @@  void ttm_resource_manager_debug(struct ttm_resource_manager *man,
 }
 EXPORT_SYMBOL(ttm_resource_manager_debug);
 
+static void
+ttm_resource_cursor_check_bulk(struct ttm_resource_cursor *cursor,
+			       struct ttm_lru_item *next_lru)
+{
+	struct ttm_resource *next = ttm_lru_item_to_res(next_lru);
+	struct ttm_lru_bulk_move *bulk = NULL;
+	struct ttm_buffer_object *bo = next->bo;
+
+	lockdep_assert_held(&cursor->man->bdev->lru_lock);
+	if (bo && bo->resource == next)
+		bulk = bo->bulk_move;
+
+	if (cursor->bulk != bulk) {
+		if (bulk)
+			list_move_tail(&cursor->bulk_link, &bulk->cursor_list);
+		else
+			list_del_init(&cursor->bulk_link);
+		cursor->bulk = bulk;
+	}
+}
+
 /**
  * ttm_resource_manager_next() - Continue iterating over the resource manager
  * resources
@@ -532,6 +617,7 @@  ttm_resource_manager_next(struct ttm_resource_cursor *cursor)
 		lru = &cursor->hitch;
 		list_for_each_entry_continue(lru, &man->lru[cursor->priority], link) {
 			if (ttm_lru_item_is_res(lru)) {
+				ttm_resource_cursor_check_bulk(cursor, lru);
 				list_move(&cursor->hitch.link, &lru->link);
 				return ttm_lru_item_to_res(lru);
 			}
@@ -541,9 +627,10 @@  ttm_resource_manager_next(struct ttm_resource_cursor *cursor)
 			break;
 
 		list_move(&cursor->hitch.link, &man->lru[cursor->priority]);
+		ttm_resource_cursor_clear_bulk(cursor);
 	} while (true);
 
-	list_del_init(&cursor->hitch.link);
+	ttm_resource_cursor_fini_locked(cursor);
 
 	return NULL;
 }
@@ -568,6 +655,7 @@  ttm_resource_manager_first(struct ttm_resource_manager *man,
 	cursor->priority = 0;
 	cursor->man = man;
 	ttm_lru_item_init(&cursor->hitch, TTM_LRU_HITCH);
+	INIT_LIST_HEAD(&cursor->bulk_link);
 	list_move(&cursor->hitch.link, &man->lru[cursor->priority]);
 
 	return ttm_resource_manager_next(cursor);
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 643b3701a738..9fe638f41515 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1315,6 +1315,8 @@  struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags)
 
 	INIT_WORK(&vm->destroy_work, vm_destroy_work_func);
 
+	ttm_lru_bulk_move_init(&vm->lru_bulk_move);
+
 	INIT_LIST_HEAD(&vm->preempt.exec_queues);
 	vm->preempt.min_run_period_ms = 10;	/* FIXME: Wire up to uAPI */
 
@@ -1433,6 +1435,7 @@  struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags)
 	mutex_destroy(&vm->snap_mutex);
 	for_each_tile(tile, xe, id)
 		xe_range_fence_tree_fini(&vm->rftree[id]);
+	ttm_lru_bulk_move_fini(&xe->ttm, &vm->lru_bulk_move);
 	kfree(vm);
 	if (!(flags & XE_VM_FLAG_MIGRATION))
 		xe_device_mem_access_put(xe);
@@ -1573,6 +1576,7 @@  static void vm_destroy_work_func(struct work_struct *w)
 
 	trace_xe_vm_free(vm);
 	dma_fence_put(vm->rebind_fence);
+	ttm_lru_bulk_move_fini(&xe->ttm, &vm->lru_bulk_move);
 	kfree(vm);
 }
 
diff --git a/include/drm/ttm/ttm_device.h b/include/drm/ttm/ttm_device.h
index c22f30535c84..07722656ffad 100644
--- a/include/drm/ttm/ttm_device.h
+++ b/include/drm/ttm/ttm_device.h
@@ -283,8 +283,13 @@  ttm_manager_type(struct ttm_device *bdev, int mem_type)
 static inline void ttm_set_driver_manager(struct ttm_device *bdev, int type,
 					  struct ttm_resource_manager *manager)
 {
+	struct ttm_resource_manager *old;
+
 	BUILD_BUG_ON(__builtin_constant_p(type) && type >= TTM_NUM_MEM_TYPES);
+	old = bdev->man_drv[type];
 	bdev->man_drv[type] = manager;
+	if (manager)
+		manager->mem_type = type;
 }
 
 int ttm_device_init(struct ttm_device *bdev, const struct ttm_device_funcs *funcs,
diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h
index b9043c183205..9084f91a5802 100644
--- a/include/drm/ttm/ttm_resource.h
+++ b/include/drm/ttm/ttm_resource.h
@@ -211,6 +211,9 @@  struct ttm_resource_manager {
 	 * bdev->lru_lock.
 	 */
 	uint64_t usage;
+
+	/** @mem_type: The memory type used for this manager. */
+	unsigned int mem_type;
 };
 
 /**
@@ -269,25 +272,6 @@  ttm_lru_item_to_res(struct ttm_lru_item *item)
 	return container_of(item, struct ttm_resource, lru);
 }
 
-/**
- * struct ttm_resource_cursor
- * @man: The resource manager currently being iterated over
- * @hitch: A hitch list node inserted before the next resource
- * to iterate over.
- * @priority: the current priority
- *
- * Cursor to iterate over the resources in a manager.
- */
-struct ttm_resource_cursor {
-	struct ttm_resource_manager *man;
-	struct ttm_lru_item hitch;
-	unsigned int priority;
-};
-
-void ttm_resource_cursor_fini_locked(struct ttm_resource_cursor *cursor);
-
-void ttm_resource_cursor_fini(struct ttm_resource_cursor *cursor);
-
 /**
  * struct ttm_lru_bulk_move_pos
  *
@@ -303,16 +287,45 @@  struct ttm_lru_bulk_move_pos {
 
 /**
  * struct ttm_lru_bulk_move
- *
  * @pos: first/last lru entry for resources in the each domain/priority
+ * @cursor_list: The list of cursors currently traversing any of
+ * the sublists of @pos. Protected by the ttm device's lru_lock.
  *
  * Container for the current bulk move state. Should be used with
  * ttm_lru_bulk_move_init() and ttm_bo_set_bulk_move().
  */
 struct ttm_lru_bulk_move {
 	struct ttm_lru_bulk_move_pos pos[TTM_NUM_MEM_TYPES][TTM_MAX_BO_PRIORITY];
+	struct list_head cursor_list;
+};
+
+/**
+ * struct ttm_resource_cursor
+ * @man: The resource manager currently being iterated over
+ * @hitch: A hitch list node inserted before the next resource
+ * to iterate over.
+ * @bulk_link: A list link for the list of cursors traversing the
+ * bulk sublist of @bulk. Protected by the ttm device's lru_lock.
+ * @bulk: Pointer to struct ttm_lru_bulk_move whose subrange @hitch is
+ * inserted to. NULL if none. Never dereference this pointer since
+ * the struct ttm_lru_bulk_move object pointed to might have been
+ * freed. The pointer is only for comparison.
+ * @priority: the current priority
+ *
+ * Cursor to iterate over the resources in a manager.
+ */
+struct ttm_resource_cursor {
+	struct ttm_resource_manager *man;
+	struct ttm_lru_item hitch;
+	struct list_head bulk_link;
+	struct ttm_lru_bulk_move *bulk;
+	unsigned int priority;
 };
 
+void ttm_resource_cursor_fini_locked(struct ttm_resource_cursor *cursor);
+
+void ttm_resource_cursor_fini(struct ttm_resource_cursor *cursor);
+
 /**
  * struct ttm_kmap_iter_iomap - Specialization for a struct io_mapping +
  * struct sg_table backed struct ttm_resource.
@@ -401,6 +414,8 @@  ttm_resource_manager_cleanup(struct ttm_resource_manager *man)
 
 void ttm_lru_bulk_move_init(struct ttm_lru_bulk_move *bulk);
 void ttm_lru_bulk_move_tail(struct ttm_lru_bulk_move *bulk);
+void ttm_lru_bulk_move_fini(struct ttm_device *bdev,
+			    struct ttm_lru_bulk_move *bulk);
 
 void ttm_resource_add_bulk_move(struct ttm_resource *res,
 				struct ttm_buffer_object *bo);