Merge tag 'cgroup-dmem-drm-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/mripard/linux into drm-next

DMEM cgroup pull request

This introduces a new cgroup controller to limit the device memory.
Notable users would be DRM, dma-buf heaps, or v4l2.

This pull request is based on the series developped by Maarten
Lankhorst, Friedrich Vock, and I:
https://lore.kernel.org/all/20241204134410.1161769-1-dev@lankhorst.se/

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Maxime Ripard <mripard@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250110-cryptic-warm-mandrill-b71f5d@houat

5 files changed, 87 insertions, 2 deletions

diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h
index 1b6e59139e6c..9952b846c170 100644
--- a/include/drm/drm_drv.h
+++ b/include/drm/drm_drv.h
@@ -34,6 +34,7 @@
 
 #include <drm/drm_device.h>
 
+struct dmem_cgroup_region;
 struct drm_fb_helper;
 struct drm_fb_helper_surface_size;
 struct drm_file;
@@ -436,6 +437,10 @@ void *__devm_drm_dev_alloc(struct device *parent,
 			   const struct drm_driver *driver,
 			   size_t size, size_t offset);
 
+struct dmem_cgroup_region *
+drmm_cgroup_register_region(struct drm_device *dev,
+			    const char *region_name, u64 size);
+
 /**
  * devm_drm_dev_alloc - Resource managed allocation of a &drm_device instance
  * @parent: Parent device object
diff --git a/include/drm/ttm/ttm_resource.h b/include/drm/ttm/ttm_resource.h
index be034be56ba1..ee688d0c029b 100644
--- a/include/drm/ttm/ttm_resource.h
+++ b/include/drm/ttm/ttm_resource.h
@@ -38,6 +38,7 @@
 #define TTM_MAX_BO_PRIORITY	4U
 #define TTM_NUM_MEM_TYPES 8
 
+struct dmem_cgroup_device;
 struct ttm_device;
 struct ttm_resource_manager;
 struct ttm_resource;
@@ -211,6 +212,11 @@ struct ttm_resource_manager {
 	 * bdev->lru_lock.
 	 */
 	uint64_t usage;
+
+	/**
+	 * @cg: &dmem_cgroup_region used for memory accounting, if not NULL.
+	 */
+	struct dmem_cgroup_region *cg;
 };
 
 /**
@@ -239,6 +245,7 @@ struct ttm_bus_placement {
  * @placement: Placement flags.
  * @bus: Placement on io bus accessible to the CPU
  * @bo: weak reference to the BO, protected by ttm_device::lru_lock
+ * @css: cgroup state this resource is charged to
  *
  * Structure indicating the placement and space resources used by a
  * buffer object.
@@ -251,6 +258,8 @@ struct ttm_resource {
 	struct ttm_bus_placement bus;
 	struct ttm_buffer_object *bo;
 
+	struct dmem_cgroup_pool_state *css;
+
 	/**
 	 * @lru: Least recently used list, see &ttm_resource_manager.lru
 	 */
@@ -432,7 +441,8 @@ void ttm_resource_fini(struct ttm_resource_manager *man,
 
 int ttm_resource_alloc(struct ttm_buffer_object *bo,
 		       const struct ttm_place *place,
-		       struct ttm_resource **res);
+		       struct ttm_resource **res,
+		       struct dmem_cgroup_pool_state **ret_limit_pool);
 void ttm_resource_free(struct ttm_buffer_object *bo, struct ttm_resource **res);
 bool ttm_resource_intersects(struct ttm_device *bdev,
 			     struct ttm_resource *res,
diff --git a/include/linux/cgroup_dmem.h b/include/linux/cgroup_dmem.h
new file mode 100644
index 000000000000..dd4869f1d736
--- /dev/null
+++ b/include/linux/cgroup_dmem.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2023-2024 Intel Corporation
+ */
+
+#ifndef _CGROUP_DMEM_H
+#define _CGROUP_DMEM_H
+
+#include <linux/types.h>
+#include <linux/llist.h>
+
+struct dmem_cgroup_pool_state;
+
+/* Opaque definition of a cgroup region, used internally */
+struct dmem_cgroup_region;
+
+#if IS_ENABLED(CONFIG_CGROUP_DMEM)
+struct dmem_cgroup_region *dmem_cgroup_register_region(u64 size, const char *name_fmt, ...) __printf(2,3);
+void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region);
+int dmem_cgroup_try_charge(struct dmem_cgroup_region *region, u64 size,
+			   struct dmem_cgroup_pool_state **ret_pool,
+			   struct dmem_cgroup_pool_state **ret_limit_pool);
+void dmem_cgroup_uncharge(struct dmem_cgroup_pool_state *pool, u64 size);
+bool dmem_cgroup_state_evict_valuable(struct dmem_cgroup_pool_state *limit_pool,
+				      struct dmem_cgroup_pool_state *test_pool,
+				      bool ignore_low, bool *ret_hit_low);
+
+void dmem_cgroup_pool_state_put(struct dmem_cgroup_pool_state *pool);
+#else
+static inline __printf(2,3) struct dmem_cgroup_region *
+dmem_cgroup_register_region(u64 size, const char *name_fmt, ...)
+{
+	return NULL;
+}
+
+static inline void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region)
+{ }
+
+static inline int dmem_cgroup_try_charge(struct dmem_cgroup_region *region, u64 size,
+					 struct dmem_cgroup_pool_state **ret_pool,
+					 struct dmem_cgroup_pool_state **ret_limit_pool)
+{
+	*ret_pool = NULL;
+
+	if (ret_limit_pool)
+		*ret_limit_pool = NULL;
+
+	return 0;
+}
+
+static inline void dmem_cgroup_uncharge(struct dmem_cgroup_pool_state *pool, u64 size)
+{ }
+
+static inline
+bool dmem_cgroup_state_evict_valuable(struct dmem_cgroup_pool_state *limit_pool,
+				      struct dmem_cgroup_pool_state *test_pool,
+				      bool ignore_low, bool *ret_hit_low)
+{
+	return true;
+}
+
+static inline void dmem_cgroup_pool_state_put(struct dmem_cgroup_pool_state *pool)
+{ }
+
+#endif
+#endif	/* _CGROUP_DMEM_H */
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index 445235487230..3fd0bcbf3080 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -65,6 +65,10 @@ SUBSYS(rdma)
 SUBSYS(misc)
 #endif
 
+#if IS_ENABLED(CONFIG_CGROUP_DMEM)
+SUBSYS(dmem)
+#endif
+
 /*
  * The following subsystems are not supported on the default hierarchy.
  */
diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
index 79dbd8bc35a7..46406f3fe34d 100644
--- a/include/linux/page_counter.h
+++ b/include/linux/page_counter.h
@@ -96,7 +96,7 @@ static inline void page_counter_reset_watermark(struct page_counter *counter)
 	counter->watermark = usage;
 }
 
-#ifdef CONFIG_MEMCG
+#if IS_ENABLED(CONFIG_MEMCG) || IS_ENABLED(CONFIG_CGROUP_DMEM)
 void page_counter_calculate_protection(struct page_counter *root,
 				       struct page_counter *counter,
 				       bool recursive_protection);