// SPDX-License-Identifier: GPL-2.0/* * Copyright 2023-2024 Intel Corporation (Maarten Lankhorst <dev@lankhorst.se>) * Copyright 2024 Red Hat (Maxime Ripard <mripard@kernel.org>) * Partially based on the rdma and misc controllers, which bear the following copyrights: * * Copyright 2020 Google LLC * Copyright (C) 2016 Parav Pandit <pandit.parav@gmail.com> */ #include <linux/cgroup.h>#include <linux/cgroup_dmem.h>#include <linux/list.h>#include <linux/mutex.h>#include <linux/page_counter.h>#include <linux/parser.h>#include <linux/refcount.h>#include <linux/rculist.h>#include <linux/slab.h> struct dmem_cgroup_region { /** * @ref: References keeping the region alive. * Keeps the region reference alive after a succesful RCU lookup. */ struct kref ref; /** @rcu: RCU head for freeing */ struct rcu_head rcu; /** * @region_node: Linked into &dmem_cgroup_regions list. * Protected by RCU and global spinlock. */ struct list_head region_node; /** * @pools: List of pools linked to this region. * Protected by global spinlock only */ struct list_head pools; /** @size: Size of region, in bytes */ u64 size; /** @name: Name describing the node, set by dmem_cgroup_register_region */ char *name; /** * @unregistered: Whether the region is unregistered by its caller. * No new pools should be added to the region afterwards. */ bool unregistered;}; struct dmemcg_state { struct cgroup_subsys_state css; struct list_head pools;}; struct dmem_cgroup_pool_state { struct dmem_cgroup_region *region; struct dmemcg_state *cs; /* css node, RCU protected against region teardown */ struct list_head css_node; /* dev node, no RCU protection required */ struct list_head region_node; struct rcu_head rcu; struct page_counter cnt; struct dmem_cgroup_pool_state *parent; refcount_t ref; bool inited;}; /* * 3 operations require locking protection: * - Registering and unregistering region to/from list, requires global lock. * - Adding a dmem_cgroup_pool_state to a CSS, removing when CSS is freed. * - Adding a dmem_cgroup_pool_state to a region list. * * Since for the most common operations RCU provides enough protection, I * do not think more granular locking makes sense. Most protection is offered * by RCU and the lockless operating page_counter. */static DEFINE_SPINLOCK(dmemcg_lock);static LIST_HEAD(dmem_cgroup_regions); static void dmemcg_free_region(struct kref *ref);static void dmemcg_pool_free_rcu(struct rcu_head *rcu); static inline struct dmemcg_state *css_to_dmemcs(struct cgroup_subsys_state *css){ return container_of(css, struct dmemcg_state, css);} static inline struct dmemcg_state *get_current_dmemcs(void){ return css_to_dmemcs(task_get_css(current, dmem_cgrp_id));} static struct dmemcg_state *parent_dmemcs(struct dmemcg_state *cg){ return cg->css.parent ? css_to_dmemcs(cg->css.parent) : NULL;} static void dmemcg_pool_get(struct dmem_cgroup_pool_state *pool){ refcount_inc(&pool->ref);} static bool dmemcg_pool_tryget(struct dmem_cgroup_pool_state *pool){ return refcount_inc_not_zero(&pool->ref);} static void dmemcg_pool_put(struct dmem_cgroup_pool_state *pool){ if (!refcount_dec_and_test(&pool->ref)) return; call_rcu(&pool->rcu, dmemcg_pool_free_rcu);} static void dmemcg_pool_free_rcu(struct rcu_head *rcu){ struct dmem_cgroup_pool_state *pool = container_of(rcu, typeof(*pool), rcu); if (pool->parent) dmemcg_pool_put(pool->parent); kref_put(&pool->region->ref, dmemcg_free_region); kfree(pool);} static void free_cg_pool(struct dmem_cgroup_pool_state *pool){ list_del(&pool->region_node); dmemcg_pool_put(pool);} static voidset_resource_min(struct dmem_cgroup_pool_state *pool, u64 val){ page_counter_set_min(&pool->cnt, val);} static voidset_resource_low(struct dmem_cgroup_pool_state *pool, u64 val){ page_counter_set_low(&pool->cnt, val);} static voidset_resource_max(struct dmem_cgroup_pool_state *pool, u64 val){ page_counter_set_max(&pool->cnt, val);} static u64 get_resource_low(struct dmem_cgroup_pool_state *pool){ return pool ? READ_ONCE(pool->cnt.low) : 0;} static u64 get_resource_min(struct dmem_cgroup_pool_state *pool){ return pool ? READ_ONCE(pool->cnt.min) : 0;} static u64 get_resource_max(struct dmem_cgroup_pool_state *pool){ return pool ? READ_ONCE(pool->cnt.max) : PAGE_COUNTER_MAX;} static u64 get_resource_current(struct dmem_cgroup_pool_state *pool){ return pool ? page_counter_read(&pool->cnt) : 0;} static void reset_all_resource_limits(struct dmem_cgroup_pool_state *rpool){ set_resource_min(rpool, 0); set_resource_low(rpool, 0); set_resource_max(rpool, PAGE_COUNTER_MAX);} static void dmemcs_offline(struct cgroup_subsys_state *css){ struct dmemcg_state *dmemcs = css_to_dmemcs(css); struct dmem_cgroup_pool_state *pool; rcu_read_lock(); list_for_each_entry_rcu(pool, &dmemcs->pools, css_node) reset_all_resource_limits(pool); rcu_read_unlock();} static void dmemcs_free(struct cgroup_subsys_state *css){ struct dmemcg_state *dmemcs = css_to_dmemcs(css); struct dmem_cgroup_pool_state *pool, *next; spin_lock(&dmemcg_lock); list_for_each_entry_safe(pool, next, &dmemcs->pools, css_node) { /* *The pool is dead and all references are 0, * no need for RCU protection with list_del_rcu or freeing. */ list_del(&pool->css_node); free_cg_pool(pool); } spin_unlock(&dmemcg_lock); kfree(dmemcs);} static struct cgroup_subsys_state *dmemcs_alloc(struct cgroup_subsys_state *parent_css){ struct dmemcg_state *dmemcs = kzalloc_obj(*dmemcs); if (!dmemcs) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&dmemcs->pools); return &dmemcs->css;} static struct dmem_cgroup_pool_state *find_cg_pool_locked(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *region){ struct dmem_cgroup_pool_state *pool; list_for_each_entry_rcu(pool, &dmemcs->pools, css_node, spin_is_locked(&dmemcg_lock)) if (pool->region == region) return pool; return NULL;} static struct dmem_cgroup_pool_state *pool_parent(struct dmem_cgroup_pool_state *pool){ if (!pool->cnt.parent) return NULL; return container_of(pool->cnt.parent, typeof(*pool), cnt);} static voiddmem_cgroup_calculate_protection(struct dmem_cgroup_pool_state *limit_pool, struct dmem_cgroup_pool_state *test_pool){ struct page_counter *climit; struct cgroup_subsys_state *css; struct dmemcg_state *dmemcg_iter; struct dmem_cgroup_pool_state *pool, *found_pool; climit = &limit_pool->cnt; rcu_read_lock(); css_for_each_descendant_pre(css, &limit_pool->cs->css) { dmemcg_iter = container_of(css, struct dmemcg_state, css); found_pool = NULL; list_for_each_entry_rcu(pool, &dmemcg_iter->pools, css_node) { if (pool->region == limit_pool->region) { found_pool = pool; break; } } if (!found_pool) continue; page_counter_calculate_protection( climit, &found_pool->cnt, true); if (found_pool == test_pool) break; } rcu_read_unlock();} /** * dmem_cgroup_state_evict_valuable() - Check if we should evict from test_pool * @limit_pool: The pool for which we hit limits * @test_pool: The pool for which to test * @ignore_low: Whether we have to respect low watermarks. * @ret_hit_low: Pointer to whether it makes sense to consider low watermark. * * This function returns true if we can evict from @test_pool, false if not. * When returning false and @ignore_low is false, @ret_hit_low may * be set to true to indicate this function can be retried with @ignore_low * set to true. * * Return: bool */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){ struct dmem_cgroup_pool_state *pool = test_pool; struct page_counter *ctest; u64 used, min, low; /* Can always evict from current pool, despite limits */ if (limit_pool == test_pool) return true; if (limit_pool) { if (!parent_dmemcs(limit_pool->cs)) return true; for (pool = test_pool; pool && limit_pool != pool; pool = pool_parent(pool)) {} if (!pool) return false; } else { /* * If there is no cgroup limiting memory usage, use the root * cgroup instead for limit calculations. */ for (limit_pool = test_pool; pool_parent(limit_pool); limit_pool = pool_parent(limit_pool)) {} } ctest = &test_pool->cnt; dmem_cgroup_calculate_protection(limit_pool, test_pool); used = page_counter_read(ctest); min = READ_ONCE(ctest->emin); if (used <= min) return false; if (!ignore_low) { low = READ_ONCE(ctest->elow); if (used > low) return true; *ret_hit_low = true; return false; } return true;}EXPORT_SYMBOL_GPL(dmem_cgroup_state_evict_valuable); static struct dmem_cgroup_pool_state *alloc_pool_single(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *region, struct dmem_cgroup_pool_state **allocpool){ struct dmemcg_state *parent = parent_dmemcs(dmemcs); struct dmem_cgroup_pool_state *pool, *ppool = NULL; if (!*allocpool) { pool = kzalloc_obj(*pool, GFP_NOWAIT); if (!pool) return ERR_PTR(-ENOMEM); } else { pool = *allocpool; *allocpool = NULL; } pool->region = region; pool->cs = dmemcs; if (parent) ppool = find_cg_pool_locked(parent, region); page_counter_init(&pool->cnt, ppool ? &ppool->cnt : NULL, true); reset_all_resource_limits(pool); refcount_set(&pool->ref, 1); kref_get(®ion->ref); if (ppool && !pool->parent) { pool->parent = ppool; dmemcg_pool_get(ppool); } list_add_tail_rcu(&pool->css_node, &dmemcs->pools); list_add_tail(&pool->region_node, ®ion->pools); if (!parent) pool->inited = true; else pool->inited = ppool ? ppool->inited : false; return pool;} static struct dmem_cgroup_pool_state *get_cg_pool_locked(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *region, struct dmem_cgroup_pool_state **allocpool){ struct dmem_cgroup_pool_state *pool, *ppool, *retpool; struct dmemcg_state *p, *pp; /* * Recursively create pool, we may not initialize yet on * recursion, this is done as a separate step. */ for (p = dmemcs; p; p = parent_dmemcs(p)) { pool = find_cg_pool_locked(p, region); if (!pool) pool = alloc_pool_single(p, region, allocpool); if (IS_ERR(pool)) return pool; if (p == dmemcs && pool->inited) return pool; if (pool->inited) break; } retpool = pool = find_cg_pool_locked(dmemcs, region); for (p = dmemcs, pp = parent_dmemcs(dmemcs); pp; p = pp, pp = parent_dmemcs(p)) { if (pool->inited) break; /* ppool was created if it didn't exist by above loop. */ ppool = find_cg_pool_locked(pp, region); /* Fix up parent links, mark as inited. */ pool->cnt.parent = &ppool->cnt; if (ppool && !pool->parent) { pool->parent = ppool; dmemcg_pool_get(ppool); } pool->inited = true; pool = ppool; } return retpool;} static void dmemcg_free_rcu(struct rcu_head *rcu){ struct dmem_cgroup_region *region = container_of(rcu, typeof(*region), rcu); struct dmem_cgroup_pool_state *pool, *next; list_for_each_entry_safe(pool, next, ®ion->pools, region_node) free_cg_pool(pool); kfree(region->name); kfree(region);} static void dmemcg_free_region(struct kref *ref){ struct dmem_cgroup_region *cgregion = container_of(ref, typeof(*cgregion), ref); call_rcu(&cgregion->rcu, dmemcg_free_rcu);} /** * dmem_cgroup_unregister_region() - Unregister a previously registered region. * @region: The region to unregister. * * This function undoes dmem_cgroup_register_region. */void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region){ struct dmem_cgroup_pool_state *pool, *next; if (!region) return; spin_lock(&dmemcg_lock); /* Remove from global region list */ list_del_rcu(®ion->region_node); list_for_each_entry_safe(pool, next, ®ion->pools, region_node) { list_del_rcu(&pool->css_node); list_del(&pool->region_node); dmemcg_pool_put(pool); } /* * Ensure any RCU based lookups fail. Additionally, * no new pools should be added to the dead region * by get_cg_pool_unlocked. */ region->unregistered = true; spin_unlock(&dmemcg_lock); kref_put(®ion->ref, dmemcg_free_region);}EXPORT_SYMBOL_GPL(dmem_cgroup_unregister_region); /** * dmem_cgroup_register_region() - Register a regions for dev cgroup. * @size: Size of region to register, in bytes.Lines 1–500 of 886. Load more
// SPDX-License-Identifier: GPL-2.0 /* * Copyright 2023-2024 Intel Corporation (Maarten Lankhorst <dev@lankhorst.se>) * Copyright 2024 Red Hat (Maxime Ripard <mripard@kernel.org>) * Partially based on the rdma and misc controllers, which bear the following copyrights: * * Copyright 2020 Google LLC * Copyright (C) 2016 Parav Pandit <pandit.parav@gmail.com> */ #include <linux/cgroup.h> #include <linux/cgroup_dmem.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/page_counter.h> #include <linux/parser.h> #include <linux/refcount.h> #include <linux/rculist.h> #include <linux/slab.h> struct dmem_cgroup_region { /** * @ref: References keeping the region alive. * Keeps the region reference alive after a succesful RCU lookup. */ struct kref ref; /** @rcu: RCU head for freeing */ struct rcu_head rcu; /** * @region_node: Linked into &dmem_cgroup_regions list. * Protected by RCU and global spinlock. */ struct list_head region_node; /** * @pools: List of pools linked to this region. * Protected by global spinlock only */ struct list_head pools; /** @size: Size of region, in bytes */ u64 size; /** @name: Name describing the node, set by dmem_cgroup_register_region */ char *name; /** * @unregistered: Whether the region is unregistered by its caller. * No new pools should be added to the region afterwards. */ bool unregistered; }; struct dmemcg_state { struct cgroup_subsys_state css; struct list_head pools; }; struct dmem_cgroup_pool_state { struct dmem_cgroup_region *region; struct dmemcg_state *cs; /* css node, RCU protected against region teardown */ struct list_head css_node; /* dev node, no RCU protection required */ struct list_head region_node; struct rcu_head rcu; struct page_counter cnt; struct dmem_cgroup_pool_state *parent; refcount_t ref; bool inited; }; /* * 3 operations require locking protection: * - Registering and unregistering region to/from list, requires global lock. * - Adding a dmem_cgroup_pool_state to a CSS, removing when CSS is freed. * - Adding a dmem_cgroup_pool_state to a region list. * * Since for the most common operations RCU provides enough protection, I * do not think more granular locking makes sense. Most protection is offered * by RCU and the lockless operating page_counter. */ static DEFINE_SPINLOCK(dmemcg_lock); static LIST_HEAD(dmem_cgroup_regions); static void dmemcg_free_region(struct kref *ref); static void dmemcg_pool_free_rcu(struct rcu_head *rcu); static inline struct dmemcg_state * css_to_dmemcs(struct cgroup_subsys_state *css) { return container_of(css, struct dmemcg_state, css); } static inline struct dmemcg_state *get_current_dmemcs(void) { return css_to_dmemcs(task_get_css(current, dmem_cgrp_id)); } static struct dmemcg_state *parent_dmemcs(struct dmemcg_state *cg) { return cg->css.parent ? css_to_dmemcs(cg->css.parent) : NULL; } static void dmemcg_pool_get(struct dmem_cgroup_pool_state *pool) { refcount_inc(&pool->ref); } static bool dmemcg_pool_tryget(struct dmem_cgroup_pool_state *pool) { return refcount_inc_not_zero(&pool->ref); } static void dmemcg_pool_put(struct dmem_cgroup_pool_state *pool) { if (!refcount_dec_and_test(&pool->ref)) return; call_rcu(&pool->rcu, dmemcg_pool_free_rcu); } static void dmemcg_pool_free_rcu(struct rcu_head *rcu) { struct dmem_cgroup_pool_state *pool = container_of(rcu, typeof(*pool), rcu); if (pool->parent) dmemcg_pool_put(pool->parent); kref_put(&pool->region->ref, dmemcg_free_region); kfree(pool); } static void free_cg_pool(struct dmem_cgroup_pool_state *pool) { list_del(&pool->region_node); dmemcg_pool_put(pool); } static void set_resource_min(struct dmem_cgroup_pool_state *pool, u64 val) { page_counter_set_min(&pool->cnt, val); } static void set_resource_low(struct dmem_cgroup_pool_state *pool, u64 val) { page_counter_set_low(&pool->cnt, val); } static void set_resource_max(struct dmem_cgroup_pool_state *pool, u64 val) { page_counter_set_max(&pool->cnt, val); } static u64 get_resource_low(struct dmem_cgroup_pool_state *pool) { return pool ? READ_ONCE(pool->cnt.low) : 0; } static u64 get_resource_min(struct dmem_cgroup_pool_state *pool) { return pool ? READ_ONCE(pool->cnt.min) : 0; } static u64 get_resource_max(struct dmem_cgroup_pool_state *pool) { return pool ? READ_ONCE(pool->cnt.max) : PAGE_COUNTER_MAX; } static u64 get_resource_current(struct dmem_cgroup_pool_state *pool) { return pool ? page_counter_read(&pool->cnt) : 0; } static void reset_all_resource_limits(struct dmem_cgroup_pool_state *rpool) { set_resource_min(rpool, 0); set_resource_low(rpool, 0); set_resource_max(rpool, PAGE_COUNTER_MAX); } static void dmemcs_offline(struct cgroup_subsys_state *css) { struct dmemcg_state *dmemcs = css_to_dmemcs(css); struct dmem_cgroup_pool_state *pool; rcu_read_lock(); list_for_each_entry_rcu(pool, &dmemcs->pools, css_node) reset_all_resource_limits(pool); rcu_read_unlock(); } static void dmemcs_free(struct cgroup_subsys_state *css) { struct dmemcg_state *dmemcs = css_to_dmemcs(css); struct dmem_cgroup_pool_state *pool, *next; spin_lock(&dmemcg_lock); list_for_each_entry_safe(pool, next, &dmemcs->pools, css_node) { /* *The pool is dead and all references are 0, * no need for RCU protection with list_del_rcu or freeing. */ list_del(&pool->css_node); free_cg_pool(pool); } spin_unlock(&dmemcg_lock); kfree(dmemcs); } static struct cgroup_subsys_state * dmemcs_alloc(struct cgroup_subsys_state *parent_css) { struct dmemcg_state *dmemcs = kzalloc_obj(*dmemcs); if (!dmemcs) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&dmemcs->pools); return &dmemcs->css; } static struct dmem_cgroup_pool_state * find_cg_pool_locked(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *region) { struct dmem_cgroup_pool_state *pool; list_for_each_entry_rcu(pool, &dmemcs->pools, css_node, spin_is_locked(&dmemcg_lock)) if (pool->region == region) return pool; return NULL; } static struct dmem_cgroup_pool_state *pool_parent(struct dmem_cgroup_pool_state *pool) { if (!pool->cnt.parent) return NULL; return container_of(pool->cnt.parent, typeof(*pool), cnt); } static void dmem_cgroup_calculate_protection(struct dmem_cgroup_pool_state *limit_pool, struct dmem_cgroup_pool_state *test_pool) { struct page_counter *climit; struct cgroup_subsys_state *css; struct dmemcg_state *dmemcg_iter; struct dmem_cgroup_pool_state *pool, *found_pool; climit = &limit_pool->cnt; rcu_read_lock(); css_for_each_descendant_pre(css, &limit_pool->cs->css) { dmemcg_iter = container_of(css, struct dmemcg_state, css); found_pool = NULL; list_for_each_entry_rcu(pool, &dmemcg_iter->pools, css_node) { if (pool->region == limit_pool->region) { found_pool = pool; break; } } if (!found_pool) continue; page_counter_calculate_protection( climit, &found_pool->cnt, true); if (found_pool == test_pool) break; } rcu_read_unlock(); } /** * dmem_cgroup_state_evict_valuable() - Check if we should evict from test_pool * @limit_pool: The pool for which we hit limits * @test_pool: The pool for which to test * @ignore_low: Whether we have to respect low watermarks. * @ret_hit_low: Pointer to whether it makes sense to consider low watermark. * * This function returns true if we can evict from @test_pool, false if not. * When returning false and @ignore_low is false, @ret_hit_low may * be set to true to indicate this function can be retried with @ignore_low * set to true. * * Return: bool */ 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) { struct dmem_cgroup_pool_state *pool = test_pool; struct page_counter *ctest; u64 used, min, low; /* Can always evict from current pool, despite limits */ if (limit_pool == test_pool) return true; if (limit_pool) { if (!parent_dmemcs(limit_pool->cs)) return true; for (pool = test_pool; pool && limit_pool != pool; pool = pool_parent(pool)) {} if (!pool) return false; } else { /* * If there is no cgroup limiting memory usage, use the root * cgroup instead for limit calculations. */ for (limit_pool = test_pool; pool_parent(limit_pool); limit_pool = pool_parent(limit_pool)) {} } ctest = &test_pool->cnt; dmem_cgroup_calculate_protection(limit_pool, test_pool); used = page_counter_read(ctest); min = READ_ONCE(ctest->emin); if (used <= min) return false; if (!ignore_low) { low = READ_ONCE(ctest->elow); if (used > low) return true; *ret_hit_low = true; return false; } return true; } EXPORT_SYMBOL_GPL(dmem_cgroup_state_evict_valuable); static struct dmem_cgroup_pool_state * alloc_pool_single(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *region, struct dmem_cgroup_pool_state **allocpool) { struct dmemcg_state *parent = parent_dmemcs(dmemcs); struct dmem_cgroup_pool_state *pool, *ppool = NULL; if (!*allocpool) { pool = kzalloc_obj(*pool, GFP_NOWAIT); if (!pool) return ERR_PTR(-ENOMEM); } else { pool = *allocpool; *allocpool = NULL; } pool->region = region; pool->cs = dmemcs; if (parent) ppool = find_cg_pool_locked(parent, region); page_counter_init(&pool->cnt, ppool ? &ppool->cnt : NULL, true); reset_all_resource_limits(pool); refcount_set(&pool->ref, 1); kref_get(®ion->ref); if (ppool && !pool->parent) { pool->parent = ppool; dmemcg_pool_get(ppool); } list_add_tail_rcu(&pool->css_node, &dmemcs->pools); list_add_tail(&pool->region_node, ®ion->pools); if (!parent) pool->inited = true; else pool->inited = ppool ? ppool->inited : false; return pool; } static struct dmem_cgroup_pool_state * get_cg_pool_locked(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *region, struct dmem_cgroup_pool_state **allocpool) { struct dmem_cgroup_pool_state *pool, *ppool, *retpool; struct dmemcg_state *p, *pp; /* * Recursively create pool, we may not initialize yet on * recursion, this is done as a separate step. */ for (p = dmemcs; p; p = parent_dmemcs(p)) { pool = find_cg_pool_locked(p, region); if (!pool) pool = alloc_pool_single(p, region, allocpool); if (IS_ERR(pool)) return pool; if (p == dmemcs && pool->inited) return pool; if (pool->inited) break; } retpool = pool = find_cg_pool_locked(dmemcs, region); for (p = dmemcs, pp = parent_dmemcs(dmemcs); pp; p = pp, pp = parent_dmemcs(p)) { if (pool->inited) break; /* ppool was created if it didn't exist by above loop. */ ppool = find_cg_pool_locked(pp, region); /* Fix up parent links, mark as inited. */ pool->cnt.parent = &ppool->cnt; if (ppool && !pool->parent) { pool->parent = ppool; dmemcg_pool_get(ppool); } pool->inited = true; pool = ppool; } return retpool; } static void dmemcg_free_rcu(struct rcu_head *rcu) { struct dmem_cgroup_region *region = container_of(rcu, typeof(*region), rcu); struct dmem_cgroup_pool_state *pool, *next; list_for_each_entry_safe(pool, next, ®ion->pools, region_node) free_cg_pool(pool); kfree(region->name); kfree(region); } static void dmemcg_free_region(struct kref *ref) { struct dmem_cgroup_region *cgregion = container_of(ref, typeof(*cgregion), ref); call_rcu(&cgregion->rcu, dmemcg_free_rcu); } /** * dmem_cgroup_unregister_region() - Unregister a previously registered region. * @region: The region to unregister. * * This function undoes dmem_cgroup_register_region. */ void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region) { struct dmem_cgroup_pool_state *pool, *next; if (!region) return; spin_lock(&dmemcg_lock); /* Remove from global region list */ list_del_rcu(®ion->region_node); list_for_each_entry_safe(pool, next, ®ion->pools, region_node) { list_del_rcu(&pool->css_node); list_del(&pool->region_node); dmemcg_pool_put(pool); } /* * Ensure any RCU based lookups fail. Additionally, * no new pools should be added to the dead region * by get_cg_pool_unlocked. */ region->unregistered = true; spin_unlock(&dmemcg_lock); kref_put(®ion->ref, dmemcg_free_region); } EXPORT_SYMBOL_GPL(dmem_cgroup_unregister_region); /** * dmem_cgroup_register_region() - Register a regions for dev cgroup. * @size: Size of region to register, in bytes.