cgroup: Use 64bit id from kernfs
Use 64 bit id allocated by kernfs instead of using its own idr since
it seems not used for saving any information no more. So let's get
rid of the cgroup_idr from cgroup_root.
The index of netprio_map is also changed to u64.
Cc: netprio cgroup people
Signed-off-by: Tejun Heo <tj@kernel.org>
[namhyung: split cgroup changes and fix netprio_map access]
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 430e219..3811b34 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -354,15 +354,8 @@
unsigned long flags; /* "unsigned long" so bitops work */
- /*
- * idr allocated in-hierarchy ID.
- *
- * ID 0 is not used, the ID of the root cgroup is always 1, and a
- * new cgroup will be assigned with a smallest available ID.
- *
- * Allocating/Removing ID must be protected by cgroup_mutex.
- */
- int id;
+ /* in-hierarchy ID allocated from kernfs */
+ u64 id;
/*
* The depth this cgroup is at. The root is at depth zero and each
@@ -488,7 +481,7 @@
struct cgroup_freezer_state freezer;
/* ids of the ancestors at each level including self */
- int ancestor_ids[];
+ u64 ancestor_ids[];
};
/*
@@ -509,7 +502,7 @@
struct cgroup cgrp;
/* for cgrp->ancestor_ids[0] */
- int cgrp_ancestor_id_storage;
+ u64 cgrp_ancestor_id_storage;
/* Number of cgroups in the hierarchy, used only for /proc/cgroups */
atomic_t nr_cgrps;
@@ -520,9 +513,6 @@
/* Hierarchy-specific flags */
unsigned int flags;
- /* IDs for cgroups in this hierarchy */
- struct idr cgroup_idr;
-
/* The path to use for release notifications. */
char release_agent_path[PATH_MAX];
diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h
index cfc9441..cd7c17c 100644
--- a/include/net/netprio_cgroup.h
+++ b/include/net/netprio_cgroup.h
@@ -15,14 +15,14 @@
#if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
struct netprio_map {
struct rcu_head rcu;
- u32 priomap_len;
+ u64 priomap_len;
u32 priomap[];
};
-static inline u32 task_netprioidx(struct task_struct *p)
+static inline u64 task_netprioidx(struct task_struct *p)
{
struct cgroup_subsys_state *css;
- u32 idx;
+ u64 idx;
rcu_read_lock();
css = task_css(p, net_prio_cgrp_id);
@@ -41,7 +41,7 @@
#else /* !CONFIG_CGROUP_NET_PRIO */
-static inline u32 task_netprioidx(struct task_struct *p)
+static inline u64 task_netprioidx(struct task_struct *p)
{
return 0;
}
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index b5dcbee5..4dc0f86 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1308,10 +1308,7 @@
void cgroup_free_root(struct cgroup_root *root)
{
- if (root) {
- idr_destroy(&root->cgroup_idr);
- kfree(root);
- }
+ kfree(root);
}
static void cgroup_destroy_root(struct cgroup_root *root)
@@ -1917,7 +1914,6 @@
atomic_set(&root->nr_cgrps, 1);
cgrp->root = root;
init_cgroup_housekeeping(cgrp);
- idr_init(&root->cgroup_idr);
root->flags = ctx->flags;
if (ctx->release_agent)
@@ -1938,12 +1934,6 @@
lockdep_assert_held(&cgroup_mutex);
- ret = cgroup_idr_alloc(&root->cgroup_idr, root_cgrp, 1, 2, GFP_KERNEL);
- if (ret < 0)
- goto out;
- root_cgrp->id = ret;
- root_cgrp->ancestor_ids[0] = ret;
-
ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release,
0, GFP_KERNEL);
if (ret)
@@ -1976,6 +1966,8 @@
goto exit_root_id;
}
root_cgrp->kn = root->kf_root->kn;
+ root_cgrp->id = root_cgrp->kn->id;
+ root_cgrp->ancestor_ids[0] = root_cgrp->id;
ret = css_populate_dir(&root_cgrp->self);
if (ret)
@@ -4987,9 +4979,6 @@
tcgrp->nr_dying_descendants--;
spin_unlock_irq(&css_set_lock);
- cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id);
- cgrp->id = -1;
-
/*
* There are two control paths which try to determine
* cgroup from dentry without going through kernfs -
@@ -5154,10 +5143,12 @@
* it isn't associated with its kernfs_node and doesn't have the control
* mask applied.
*/
-static struct cgroup *cgroup_create(struct cgroup *parent)
+static struct cgroup *cgroup_create(struct cgroup *parent, const char *name,
+ umode_t mode)
{
struct cgroup_root *root = parent->root;
struct cgroup *cgrp, *tcgrp;
+ struct kernfs_node *kn;
int level = parent->level + 1;
int ret;
@@ -5177,15 +5168,14 @@
goto out_cancel_ref;
}
- /*
- * Temporarily set the pointer to NULL, so idr_find() won't return
- * a half-baked cgroup.
- */
- cgrp->id = cgroup_idr_alloc(&root->cgroup_idr, NULL, 2, 0, GFP_KERNEL);
- if (cgrp->id < 0) {
- ret = -ENOMEM;
+ /* create the directory */
+ kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
+ if (IS_ERR(kn)) {
+ ret = PTR_ERR(kn);
goto out_stat_exit;
}
+ cgrp->kn = kn;
+ cgrp->id = kn->id;
init_cgroup_housekeeping(cgrp);
@@ -5195,7 +5185,7 @@
ret = psi_cgroup_alloc(cgrp);
if (ret)
- goto out_idr_free;
+ goto out_kernfs_remove;
ret = cgroup_bpf_inherit(cgrp);
if (ret)
@@ -5249,12 +5239,6 @@
cgroup_get_live(parent);
/*
- * @cgrp is now fully operational. If something fails after this
- * point, it'll be released via the normal destruction path.
- */
- cgroup_idr_replace(&root->cgroup_idr, cgrp, cgrp->id);
-
- /*
* On the default hierarchy, a child doesn't automatically inherit
* subtree_control from the parent. Each is configured manually.
*/
@@ -5267,8 +5251,8 @@
out_psi_free:
psi_cgroup_free(cgrp);
-out_idr_free:
- cgroup_idr_remove(&root->cgroup_idr, cgrp->id);
+out_kernfs_remove:
+ kernfs_remove(cgrp->kn);
out_stat_exit:
if (cgroup_on_dfl(parent))
cgroup_rstat_exit(cgrp);
@@ -5305,7 +5289,6 @@
int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode)
{
struct cgroup *parent, *cgrp;
- struct kernfs_node *kn;
int ret;
/* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */
@@ -5321,27 +5304,19 @@
goto out_unlock;
}
- cgrp = cgroup_create(parent);
+ cgrp = cgroup_create(parent, name, mode);
if (IS_ERR(cgrp)) {
ret = PTR_ERR(cgrp);
goto out_unlock;
}
- /* create the directory */
- kn = kernfs_create_dir(parent->kn, name, mode, cgrp);
- if (IS_ERR(kn)) {
- ret = PTR_ERR(kn);
- goto out_destroy;
- }
- cgrp->kn = kn;
-
/*
* This extra ref will be put in cgroup_free_fn() and guarantees
* that @cgrp->kn is always accessible.
*/
- kernfs_get(kn);
+ kernfs_get(cgrp->kn);
- ret = cgroup_kn_set_ugid(kn);
+ ret = cgroup_kn_set_ugid(cgrp->kn);
if (ret)
goto out_destroy;
@@ -5356,7 +5331,7 @@
TRACE_CGROUP_PATH(mkdir, cgrp);
/* let's create and online css's */
- kernfs_activate(kn);
+ kernfs_activate(cgrp->kn);
ret = 0;
goto out_unlock;
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 256b795..326d2d6 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -93,7 +93,7 @@
static u32 netprio_prio(struct cgroup_subsys_state *css, struct net_device *dev)
{
struct netprio_map *map = rcu_dereference_rtnl(dev->priomap);
- int id = css->cgroup->id;
+ u64 id = css->cgroup->id;
if (map && id < map->priomap_len)
return map->priomap[id];
@@ -113,7 +113,7 @@
struct net_device *dev, u32 prio)
{
struct netprio_map *map;
- int id = css->cgroup->id;
+ u64 id = css->cgroup->id;
int ret;
/* avoid extending priomap for zero writes */
