From 43151f812886be1855d2cba059f9c93e4729460b Mon Sep 17 00:00:00 2001 From: Chen Ridong Date: Mon, 2 Feb 2026 12:27:16 +0000 Subject: cgroup/dmem: fix NULL pointer dereference when setting max An issue was triggered: BUG: kernel NULL pointer dereference, address: 0000000000000000 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP NOPTI CPU: 15 UID: 0 PID: 658 Comm: bash Tainted: 6.19.0-rc6-next-2026012 Tainted: [O]=OOT_MODULE Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), RIP: 0010:strcmp+0x10/0x30 RSP: 0018:ffffc900017f7dc0 EFLAGS: 00000246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff888107cd4358 RDX: 0000000019f73907 RSI: ffffffff82cc381a RDI: 0000000000000000 RBP: ffff8881016bef0d R08: 000000006c0e7145 R09: 0000000056c0e714 R10: 0000000000000001 R11: ffff888107cd4358 R12: 0007ffffffffffff R13: ffff888101399200 R14: ffff888100fcb360 R15: 0007ffffffffffff CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000105c79000 CR4: 00000000000006f0 Call Trace: dmemcg_limit_write.constprop.0+0x16d/0x390 ? __pfx_set_resource_max+0x10/0x10 kernfs_fop_write_iter+0x14e/0x200 vfs_write+0x367/0x510 ksys_write+0x66/0xe0 do_syscall_64+0x6b/0x390 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f42697e1887 It was trriggered setting max without limitation, the command is like: "echo test/region0 > dmem.max". To fix this issue, add check whether options is valid after parsing the region_name. Fixes: b168ed458dde ("kernel/cgroup: Add "dmem" memory accounting cgroup") Cc: stable@vger.kernel.org # v6.14+ Signed-off-by: Chen Ridong Signed-off-by: Tejun Heo --- kernel/cgroup/dmem.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/cgroup/dmem.c b/kernel/cgroup/dmem.c index e12b946278b6..1f0d6caaf2fb 100644 --- a/kernel/cgroup/dmem.c +++ b/kernel/cgroup/dmem.c @@ -700,6 +700,9 @@ 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(); -- cgit v1.2.3 From 592a68212c5664bcaa88f24ed80bf791282790fe Mon Sep 17 00:00:00 2001 From: Chen Ridong Date: Mon, 2 Feb 2026 12:27:17 +0000 Subject: cgroup/dmem: avoid rcu warning when unregister region A warnning was detected: WARNING: suspicious RCU usage 6.19.0-rc7-next-20260129+ #1101 Tainted: G O kernel/cgroup/dmem.c:456 suspicious rcu_dereference_check() usage! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 1 lock held by insmod/532: #0: ffffffff85e78b38 (dmemcg_lock){+.+.}-dmem_cgroup_unregister_region+ stack backtrace: CPU: 2 UID: 0 PID: 532 Comm: insmod Tainted: 6.19.0-rc7-next- Tainted: [O]=OOT_MODULE Call Trace: dump_stack_lvl+0xb0/0xd0 lockdep_rcu_suspicious+0x151/0x1c0 dmem_cgroup_unregister_region+0x1e2/0x380 ? __pfx_dmem_test_init+0x10/0x10 [dmem_uaf] dmem_test_init+0x65/0xff0 [dmem_uaf] do_one_initcall+0xbb/0x3a0 The macro list_for_each_rcu() must be used within an RCU read-side critical section (between rcu_read_lock() and rcu_read_unlock()). Using it outside that context, as seen in dmem_cgroup_unregister_region(), triggers the lockdep warning because the RCU protection is not guaranteed. Replace list_for_each_rcu() with list_for_each_entry_safe(), which is appropriate for traversal under spinlock protection where nodes may be deleted. Fixes: b168ed458dde ("kernel/cgroup: Add "dmem" memory accounting cgroup") Cc: stable@vger.kernel.org # v6.14+ Signed-off-by: Chen Ridong Signed-off-by: Tejun Heo --- kernel/cgroup/dmem.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup/dmem.c b/kernel/cgroup/dmem.c index 1f0d6caaf2fb..787b334e0f5d 100644 --- a/kernel/cgroup/dmem.c +++ b/kernel/cgroup/dmem.c @@ -423,7 +423,7 @@ 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; @@ -433,10 +433,7 @@ 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); } -- cgit v1.2.3 From 99a2ef500906138ba58093b9893972a5c303c734 Mon Sep 17 00:00:00 2001 From: Chen Ridong Date: Mon, 2 Feb 2026 12:27:18 +0000 Subject: cgroup/dmem: avoid pool UAF An UAF issue was observed: BUG: KASAN: slab-use-after-free in page_counter_uncharge+0x65/0x150 Write of size 8 at addr ffff888106715440 by task insmod/527 CPU: 4 UID: 0 PID: 527 Comm: insmod 6.19.0-rc7-next-20260129+ #11 Tainted: [O]=OOT_MODULE Call Trace: dump_stack_lvl+0x82/0xd0 kasan_report+0xca/0x100 kasan_check_range+0x39/0x1c0 page_counter_uncharge+0x65/0x150 dmem_cgroup_uncharge+0x1f/0x260 Allocated by task 527: Freed by task 0: The buggy address belongs to the object at ffff888106715400 which belongs to the cache kmalloc-512 of size 512 The buggy address is located 64 bytes inside of freed 512-byte region [ffff888106715400, ffff888106715600) The buggy address belongs to the physical page: Memory state around the buggy address: ffff888106715300: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff888106715380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff888106715400: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888106715480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff888106715500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb The issue occurs because a pool can still be held by a caller after its associated memory region is unregistered. The current implementation frees the pool even if users still hold references to it (e.g., before uncharge operations complete). This patch adds a reference counter to each pool, ensuring that a pool is only freed when its reference count drops to zero. Fixes: b168ed458dde ("kernel/cgroup: Add "dmem" memory accounting cgroup") Cc: stable@vger.kernel.org # v6.14+ Signed-off-by: Chen Ridong Signed-off-by: Tejun Heo --- kernel/cgroup/dmem.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 58 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/cgroup/dmem.c b/kernel/cgroup/dmem.c index 787b334e0f5d..1ea6afffa985 100644 --- a/kernel/cgroup/dmem.c +++ b/kernel/cgroup/dmem.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -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; @@ -435,6 +479,8 @@ void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region) 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); } /* @@ -515,8 +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); @@ -530,6 +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) { @@ -538,6 +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)) { @@ -573,6 +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); @@ -624,7 +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; } @@ -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); -- cgit v1.2.3