cgroup: nest kernfs active protection under cgroup_mutex

After the recent cgroup_kn_lock_live() changes, cgroup_mutex is no
longer nested below kernfs active protection.  The two don't have any
relationship now.

This patch nests kernfs active protection under cgroup_mutex.  All
cftype operations now require both cgroup_tree_mutex and cgroup_mutex,
temporary cgroup_mutex releases over kernfs operations are removed,
and cgroup_add/rm_cftypes() grab both mutexes.

This makes cgroup_tree_mutex redundant, which will be removed by the
next patch.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b7cd80845f6a4c48a9c3bf36424f1b8a36284931..bf1d7ce250ac19fc1fc8ea1d74b667fa82d8c96e 100644 (file)
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1127,7 +1127,7 @@ static struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn)
                cgrp = kn->parent->priv;
 
        /*
-        * We're gonna grab cgroup_tree_mutex which nests outside kernfs
+        * We're gonna grab cgroup_mutex which nests outside kernfs
         * active_ref.  cgroup liveliness check alone provides enough
         * protection against removal.  Ensure @cgrp stays accessible and
         * break the active_ref protection.
@@ -1150,6 +1150,7 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft)
        char name[CGROUP_FILE_NAME_MAX];
 
        lockdep_assert_held(&cgroup_tree_mutex);
+       lockdep_assert_held(&cgroup_mutex);
        kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name));
 }
 
@@ -1216,11 +1217,9 @@ static int rebind_subsystems(struct cgroup_root *dst_root, unsigned int ss_mask)
         * Nothing can fail from this point on.  Remove files for the
         * removed subsystems and rebind each subsystem.
         */
-       mutex_unlock(&cgroup_mutex);
        for_each_subsys(ss, ssid)
                if (ss_mask & (1 << ssid))
                        cgroup_clear_dir(&ss->root->cgrp, 1 << ssid);
-       mutex_lock(&cgroup_mutex);
 
        for_each_subsys(ss, ssid) {
                struct cgroup_root *src_root;
@@ -2946,6 +2945,7 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cftype cfts[],
        int ret;
 
        lockdep_assert_held(&cgroup_tree_mutex);
+       lockdep_assert_held(&cgroup_mutex);
 
        for (cft = cfts; cft->name[0] != '\0'; cft++) {
                /* does cft->flags tell us to skip this file on @cgrp? */
@@ -2981,6 +2981,7 @@ static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add)
        int ret = 0;
 
        lockdep_assert_held(&cgroup_tree_mutex);
+       lockdep_assert_held(&cgroup_mutex);
 
        /* add/rm files for all cgroups created before */
        css_for_each_descendant_pre(css, cgroup_css(root, ss)) {
@@ -3049,6 +3050,7 @@ static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
 static int cgroup_rm_cftypes_locked(struct cftype *cfts)
 {
        lockdep_assert_held(&cgroup_tree_mutex);
+       lockdep_assert_held(&cgroup_mutex);
 
        if (!cfts || !cfts[0].ss)
                return -ENOENT;
@@ -3075,7 +3077,9 @@ int cgroup_rm_cftypes(struct cftype *cfts)
        int ret;
 
        mutex_lock(&cgroup_tree_mutex);
+       mutex_lock(&cgroup_mutex);
        ret = cgroup_rm_cftypes_locked(cfts);
+       mutex_unlock(&cgroup_mutex);
        mutex_unlock(&cgroup_tree_mutex);
        return ret;
 }
@@ -3106,12 +3110,14 @@ int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts)
                return ret;
 
        mutex_lock(&cgroup_tree_mutex);
+       mutex_lock(&cgroup_mutex);
 
        list_add_tail(&cfts->node, &ss->cfts);
        ret = cgroup_apply_cftypes(cfts, true);
        if (ret)
                cgroup_rm_cftypes_locked(cfts);
 
+       mutex_unlock(&cgroup_mutex);
        mutex_unlock(&cgroup_tree_mutex);
        return ret;
 }
@@ -4445,6 +4451,7 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
 static void kill_css(struct cgroup_subsys_state *css)
 {
        lockdep_assert_held(&cgroup_tree_mutex);
+       lockdep_assert_held(&cgroup_mutex);
 
        /*
         * This must happen before css is disassociated with its cgroup.
@@ -4544,13 +4551,10 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
        /*
         * Initiate massacre of all css's.  cgroup_destroy_css_killed()
         * will be invoked to perform the rest of destruction once the
-        * percpu refs of all css's are confirmed to be killed.  This
-        * involves removing the subsystem's files, drop cgroup_mutex.
+        * percpu refs of all css's are confirmed to be killed.
         */
-       mutex_unlock(&cgroup_mutex);
        for_each_css(css, ssid, cgrp)
                kill_css(css);
-       mutex_lock(&cgroup_mutex);
 
        /* CGRP_DEAD is set, remove from ->release_list for the last time */
        raw_spin_lock(&release_list_lock);
@@ -4567,10 +4571,11 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
        if (!cgrp->nr_css)
                cgroup_destroy_css_killed(cgrp);
 
-       /* remove @cgrp directory along with the base files */
-       mutex_unlock(&cgroup_mutex);
-       kernfs_remove(cgrp->kn);        /* @cgrp has an extra ref on its kn */
-       mutex_lock(&cgroup_mutex);
+       /*
+        * Remove @cgrp directory along with the base files.  @cgrp has an
+        * extra ref on its kn.
+        */
+       kernfs_remove(cgrp->kn);
 
        return 0;
 };