From 6c357bd6a8281f4075c868ca5e424dd3366a2efa Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Sun, 29 Oct 2023 06:14:29 +0000 Subject: [PATCH] cgroup: Make operations on the cgroup root_list RCU safe [ Upstream commit d23b5c577715892c87533b13923306acc6243f93 ] At present, when we perform operations on the cgroup root_list, we must hold the cgroup_mutex, which is a relatively heavyweight lock. In reality, we can make operations on this list RCU-safe, eliminating the need to hold the cgroup_mutex during traversal. Modifications to the list only occur in the cgroup root setup and destroy paths, which should be infrequent in a production environment. In contrast, traversal may occur frequently. Therefore, making it RCU-safe would be beneficial. Signed-off-by: Yafang Shao Signed-off-by: Tejun Heo Signed-off-by: Sasha Levin --- include/linux/cgroup-defs.h | 1 + kernel/cgroup/cgroup-internal.h | 3 ++- kernel/cgroup/cgroup.c | 14 +++++++------- 3 files changed, 10 insertions(+), 8 deletions(-) diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 0390fff5d..50fad8b24 100755 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -519,6 +519,7 @@ struct cgroup_root { /* A list running through the active hierarchies */ struct list_head root_list; + struct rcu_head rcu; /* Hierarchy-specific flags */ unsigned int flags; diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index 4307a0904..91e9e3824 100755 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -172,7 +172,8 @@ extern struct list_head cgroup_roots; /* iterate across the hierarchies */ #define for_each_root(root) \ - list_for_each_entry((root), &cgroup_roots, root_list) + list_for_each_entry_rcu((root), &cgroup_roots, root_list, \ + lockdep_is_held(&cgroup_mutex)) /** * for_each_subsys - iterate all enabled cgroup subsystems diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 8114b2616..8d93b8ec1 100755 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1328,7 +1328,7 @@ static void cgroup_exit_root_id(struct cgroup_root *root) void cgroup_free_root(struct cgroup_root *root) { - kfree(root); + kfree_rcu(root, rcu); } static void cgroup_destroy_root(struct cgroup_root *root) @@ -1361,7 +1361,7 @@ static void cgroup_destroy_root(struct cgroup_root *root) spin_unlock_irq(&css_set_lock); if (!list_empty(&root->root_list)) { - list_del(&root->root_list); + list_del_rcu(&root->root_list); cgroup_root_count--; } @@ -1406,7 +1406,6 @@ current_cgns_cgroup_from_root(struct cgroup_root *root) } rcu_read_unlock(); - BUG_ON(!res); return res; } @@ -1416,7 +1415,6 @@ static struct cgroup *cset_cgroup_from_root(struct css_set *cset, { struct cgroup *res = NULL; - lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&css_set_lock); if (cset == &init_css_set) { @@ -1442,7 +1440,9 @@ static struct cgroup *cset_cgroup_from_root(struct css_set *cset, /* * Return the cgroup for "task" from the given hierarchy. Must be - * called with cgroup_mutex and css_set_lock held. + * called with css_set_lock held to prevent task's groups from being modified. + * Must be called with either cgroup_mutex or rcu read lock to prevent the + * cgroup root from being destroyed. */ struct cgroup *task_cgroup_from_root(struct task_struct *task, struct cgroup_root *root) @@ -1974,7 +1974,7 @@ void init_cgroup_root(struct cgroup_fs_context *ctx) struct cgroup_root *root = ctx->root; struct cgroup *cgrp = &root->cgrp; - INIT_LIST_HEAD(&root->root_list); + INIT_LIST_HEAD_RCU(&root->root_list); atomic_set(&root->nr_cgrps, 1); cgrp->root = root; init_cgroup_housekeeping(cgrp); @@ -2052,7 +2052,7 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) * care of subsystems' refcounts, which are explicitly dropped in * the failure exit path. */ - list_add(&root->root_list, &cgroup_roots); + list_add_rcu(&root->root_list, &cgroup_roots); cgroup_root_count++; /*