From: Yafang Shao laoar.shao@gmail.com

mainline inclusion from mainline-v6.8-rc1 commit d23b5c577715892c87533b13923306acc6243f93 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IA7HMV

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

----------------------------------------------------------------------

[ 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 laoar.shao@gmail.com Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Chen Ridong chenridong@huawei.com

[Backport] cgroup: Move rcu_head up near the top of cgroup_root

mainline inclusion from mainline-v6.8-rc1 commit a7fb0423c201ba12815877a0b5a68a6a1710b23a category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IA7HMV

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

----------------------------------------------------------------------

commit a7fb0423c201ba12815877a0b5a68a6a1710b23a upstream.

Commit d23b5c577715 ("cgroup: Make operations on the cgroup root_list RCU safe") adds a new rcu_head to the cgroup_root structure and kvfree_rcu() for freeing the cgroup_root.

The current implementation of kvfree_rcu(), however, has the limitation that the offset of the rcu_head structure within the larger data structure must be less than 4096 or the compilation will fail. See the macro definition of __is_kvfree_rcu_offset() in include/linux/rcupdate.h for more information.

By putting rcu_head below the large cgroup structure, any change to the cgroup structure that makes it larger run the risk of causing build failure under certain configurations. Commit 77070eeb8821 ("cgroup: Avoid false cacheline sharing of read mostly rstat_cpu") happens to be the last straw that breaks it. Fix this problem by moving the rcu_head structure up before the cgroup structure.

Fixes: d23b5c577715 ("cgroup: Make operations on the cgroup root_list RCU safe") Reported-by: Stephen Rothwell sfr@canb.auug.org.au Closes: https://lore.kernel.org/lkml/20231207143806.114e0a74@canb.auug.org.au/ Signed-off-by: Waiman Long longman@redhat.com Acked-by: Yafang Shao laoar.shao@gmail.com Reviewed-by: Yosry Ahmed yosryahmed@google.com Reviewed-by: Michal Koutný mkoutny@suse.com Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

Conflicts: include/linux/cgroup-defs.h kernel/cgroup/cgroup.c [Context is mismatched for wait_queue_head_t wait was merged. cgroup.c is mismatched for some comment.] Signed-off-by: Chen Ridong chenridong@huawei.com --- include/linux/cgroup-defs.h | 7 ++++--- kernel/cgroup/cgroup-internal.h | 3 ++- kernel/cgroup/cgroup.c | 14 +++++++------- 3 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 09f2d58d119b..196d801d74b6 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -526,6 +526,10 @@ struct cgroup_root { /* Unique id for this hierarchy. */ int hierarchy_id;

+ /* A list running through the active hierarchies */ + struct list_head root_list; + struct rcu_head rcu; /* Must be near the top */ + /* The root cgroup. Root is destroyed on its release. */ struct cgroup cgrp;

@@ -538,9 +542,6 @@ struct cgroup_root { /* Wait while cgroups are being destroyed */ wait_queue_head_t wait;

- /* A list running through the active hierarchies */ - struct list_head root_list; - /* Hierarchy-specific flags */ unsigned int flags;

diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index 096cee0e111a..aabc2a89d6b5 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -173,7 +173,8 @@ 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 69b6bbaf28a3..48997f20636c 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1310,7 +1310,7 @@ 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) @@ -1343,7 +1343,7 @@ 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--; }

@@ -1389,7 +1389,6 @@ current_cgns_cgroup_from_root(struct cgroup_root *root) } rcu_read_unlock();

- BUG_ON(!res); return res; }

@@ -1399,7 +1398,6 @@ 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) { @@ -1425,7 +1423,9 @@ 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) @@ -1964,7 +1964,7 @@ 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); @@ -2047,7 +2047,7 @@ 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++;

/*

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IA7HMV

--------------------------------

Commit 02ebfdc9f2bd ("[Backport] cgroup: Make operations on the cgroup root_list RCU safe") added rcu member to struct cgroup_root, which broke KABI. To keep KABI, add cgroup_root_ext.

Fixes: 02ebfdc9f2bd ("[Backport] cgroup: Make operations on the cgroup root_list RCU safe") Signed-off-by: Chen Ridong chenridong@huawei.com --- include/linux/cgroup-defs.h | 16 ++++++++++++---- kernel/cgroup/cgroup-v1.c | 6 ++++-- kernel/cgroup/cgroup.c | 5 ++++- 3 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 196d801d74b6..36103ca580dc 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -526,10 +526,6 @@ struct cgroup_root { /* Unique id for this hierarchy. */ int hierarchy_id;

- /* A list running through the active hierarchies */ - struct list_head root_list; - struct rcu_head rcu; /* Must be near the top */ - /* The root cgroup. Root is destroyed on its release. */ struct cgroup cgrp;

@@ -542,6 +538,9 @@ struct cgroup_root { /* Wait while cgroups are being destroyed */ wait_queue_head_t wait;

+ /* A list running through the active hierarchies */ + struct list_head root_list; + /* Hierarchy-specific flags */ unsigned int flags;

@@ -557,6 +556,15 @@ struct cgroup_root { KABI_RESERVE(4) };

+/* + * To keep kabi uncharged, add cgroup_root_ext, add rcu_head to make operations + * on the cgroup root_list RCU safe + */ +struct cgroup_root_ext { + struct rcu_head rcu; /* Must be near the top */ + struct cgroup_root root; +}; + /* * struct cftype: handler definitions for cgroup control files * diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 879813117556..c8500c3a9340 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -1143,6 +1143,7 @@ static int cgroup1_root_to_use(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct cgroup_root *root; + struct cgroup_root_ext *root_ext; struct cgroup_subsys *ss; int i, ret;

@@ -1215,10 +1216,11 @@ static int cgroup1_root_to_use(struct fs_context *fc) if (ctx->ns != &init_cgroup_ns) return -EPERM;

- root = kzalloc(sizeof(*root), GFP_KERNEL); - if (!root) + root_ext = kzalloc(sizeof(struct cgroup_root_ext), GFP_KERNEL); + if (!root_ext) return -ENOMEM;

+ root = &root_ext->root; ctx->root = root; init_cgroup_root(ctx);

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 48997f20636c..34647f8d6778 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1310,7 +1310,10 @@ static void cgroup_exit_root_id(struct cgroup_root *root)

void cgroup_free_root(struct cgroup_root *root) { - kfree_rcu(root, rcu); + struct cgroup_root_ext *root_ext; + + root_ext = container_of(root, struct cgroup_root_ext, root); + kfree_rcu(root_ext, rcu); }

static void cgroup_destroy_root(struct cgroup_root *root)