Merge tag 'cgroup-for-6.19-rc8-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup
Pull cgroup fixes from Tejun Heo:
"Three dmem fixes from Chen Ridong addressing use-after-free, RCU
warning, and NULL pointer dereference issues introduced with the dmem
controller.
All changes are confined to kernel/cgroup/dmem.c and can only affect
dmem controller users"
* tag 'cgroup-for-6.19-rc8-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
cgroup/dmem: avoid pool UAF
cgroup/dmem: avoid rcu warning when unregister region
cgroup/dmem: fix NULL pointer dereference when setting max
diff --git a/kernel/cgroup/dmem.c b/kernel/cgroup/dmem.c
index e12b946..1ea6aff 100644
--- a/kernel/cgroup/dmem.c
+++ b/kernel/cgroup/dmem.c
@@ -14,6 +14,7 @@
#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>
@@ -71,7 +72,9 @@ struct dmem_cgroup_pool_state {
struct rcu_head rcu;
struct page_counter cnt;
+ struct dmem_cgroup_pool_state *parent;
+ refcount_t ref;
bool inited;
};
@@ -88,6 +91,9 @@ struct dmem_cgroup_pool_state {
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)
{
@@ -104,10 +110,38 @@ 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);
- kfree(pool);
+ dmemcg_pool_put(pool);
}
static void
@@ -342,6 +376,12 @@ alloc_pool_single(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *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);
@@ -389,6 +429,10 @@ get_cg_pool_locked(struct dmemcg_state *dmemcs, struct dmem_cgroup_region *regio
/* 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;
@@ -423,7 +467,7 @@ static void dmemcg_free_region(struct kref *ref)
*/
void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region)
{
- struct list_head *entry;
+ struct dmem_cgroup_pool_state *pool, *next;
if (!region)
return;
@@ -433,11 +477,10 @@ void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region)
/* Remove from global region list */
list_del_rcu(®ion->region_node);
- list_for_each_rcu(entry, ®ion->pools) {
- struct dmem_cgroup_pool_state *pool =
- container_of(entry, typeof(*pool), 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);
}
/*
@@ -518,8 +561,10 @@ static struct dmem_cgroup_region *dmemcg_get_region_by_name(const char *name)
*/
void dmem_cgroup_pool_state_put(struct dmem_cgroup_pool_state *pool)
{
- if (pool)
+ if (pool) {
css_put(&pool->cs->css);
+ dmemcg_pool_put(pool);
+ }
}
EXPORT_SYMBOL_GPL(dmem_cgroup_pool_state_put);
@@ -533,6 +578,8 @@ get_cg_pool_unlocked(struct dmemcg_state *cg, struct dmem_cgroup_region *region)
pool = find_cg_pool_locked(cg, region);
if (pool && !READ_ONCE(pool->inited))
pool = NULL;
+ if (pool && !dmemcg_pool_tryget(pool))
+ pool = NULL;
rcu_read_unlock();
while (!pool) {
@@ -541,6 +588,8 @@ get_cg_pool_unlocked(struct dmemcg_state *cg, struct dmem_cgroup_region *region)
pool = get_cg_pool_locked(cg, region, &allocpool);
else
pool = ERR_PTR(-ENODEV);
+ if (!IS_ERR(pool))
+ dmemcg_pool_get(pool);
spin_unlock(&dmemcg_lock);
if (pool == ERR_PTR(-ENOMEM)) {
@@ -576,6 +625,7 @@ void dmem_cgroup_uncharge(struct dmem_cgroup_pool_state *pool, u64 size)
page_counter_uncharge(&pool->cnt, size);
css_put(&pool->cs->css);
+ dmemcg_pool_put(pool);
}
EXPORT_SYMBOL_GPL(dmem_cgroup_uncharge);
@@ -627,7 +677,9 @@ int dmem_cgroup_try_charge(struct dmem_cgroup_region *region, u64 size,
if (ret_limit_pool) {
*ret_limit_pool = container_of(fail, struct dmem_cgroup_pool_state, cnt);
css_get(&(*ret_limit_pool)->cs->css);
+ dmemcg_pool_get(*ret_limit_pool);
}
+ dmemcg_pool_put(pool);
ret = -EAGAIN;
goto err;
}
@@ -700,6 +752,9 @@ static ssize_t dmemcg_limit_write(struct kernfs_open_file *of,
if (!region_name[0])
continue;
+ if (!options || !*options)
+ return -EINVAL;
+
rcu_read_lock();
region = dmemcg_get_region_by_name(region_name);
rcu_read_unlock();
@@ -719,6 +774,7 @@ static ssize_t dmemcg_limit_write(struct kernfs_open_file *of,
/* And commit */
apply(pool, new_limit);
+ dmemcg_pool_put(pool);
out_put:
kref_put(®ion->ref, dmemcg_free_region);
