From: Roman Gushchin guro@fb.com
stable inclusion from stable-v5.10.102 commit 8c8385972ea96adeb9b678c9390beaa4d94c4aae bugzilla: https://gitee.com/openeuler/kernel/issues/I567K6
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
commit 0764db9b49c932b89ee4d9e3236dff4bb07b4a66 upstream.
Alexander reported a circular lock dependency revealed by the mmap1 ltp test:
LOCKDEP_CIRCULAR (suite: ltp, case: mtest06 (mmap1)) WARNING: possible circular locking dependency detected 5.17.0-20220113.rc0.git0.f2211f194038.300.fc35.s390x+debug #1 Not tainted ------------------------------------------------------ mmap1/202299 is trying to acquire lock: 00000001892c0188 (css_set_lock){..-.}-{2:2}, at: obj_cgroup_release+0x4a/0xe0 but task is already holding lock: 00000000ca3b3818 (&sighand->siglock){-.-.}-{2:2}, at: force_sig_info_to_task+0x38/0x180 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&sighand->siglock){-.-.}-{2:2}: __lock_acquire+0x604/0xbd8 lock_acquire.part.0+0xe2/0x238 lock_acquire+0xb0/0x200 _raw_spin_lock_irqsave+0x6a/0xd8 __lock_task_sighand+0x90/0x190 cgroup_freeze_task+0x2e/0x90 cgroup_migrate_execute+0x11c/0x608 cgroup_update_dfl_csses+0x246/0x270 cgroup_subtree_control_write+0x238/0x518 kernfs_fop_write_iter+0x13e/0x1e0 new_sync_write+0x100/0x190 vfs_write+0x22c/0x2d8 ksys_write+0x6c/0xf8 __do_syscall+0x1da/0x208 system_call+0x82/0xb0 -> #0 (css_set_lock){..-.}-{2:2}: check_prev_add+0xe0/0xed8 validate_chain+0x736/0xb20 __lock_acquire+0x604/0xbd8 lock_acquire.part.0+0xe2/0x238 lock_acquire+0xb0/0x200 _raw_spin_lock_irqsave+0x6a/0xd8 obj_cgroup_release+0x4a/0xe0 percpu_ref_put_many.constprop.0+0x150/0x168 drain_obj_stock+0x94/0xe8 refill_obj_stock+0x94/0x278 obj_cgroup_charge+0x164/0x1d8 kmem_cache_alloc+0xac/0x528 __sigqueue_alloc+0x150/0x308 __send_signal+0x260/0x550 send_signal+0x7e/0x348 force_sig_info_to_task+0x104/0x180 force_sig_fault+0x48/0x58 __do_pgm_check+0x120/0x1f0 pgm_check_handler+0x11e/0x180 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&sighand->siglock); lock(css_set_lock); lock(&sighand->siglock); lock(css_set_lock); *** DEADLOCK *** 2 locks held by mmap1/202299: #0: 00000000ca3b3818 (&sighand->siglock){-.-.}-{2:2}, at: force_sig_info_to_task+0x38/0x180 #1: 00000001892ad560 (rcu_read_lock){....}-{1:2}, at: percpu_ref_put_many.constprop.0+0x0/0x168 stack backtrace: CPU: 15 PID: 202299 Comm: mmap1 Not tainted 5.17.0-20220113.rc0.git0.f2211f194038.300.fc35.s390x+debug #1 Hardware name: IBM 3906 M04 704 (LPAR) Call Trace: dump_stack_lvl+0x76/0x98 check_noncircular+0x136/0x158 check_prev_add+0xe0/0xed8 validate_chain+0x736/0xb20 __lock_acquire+0x604/0xbd8 lock_acquire.part.0+0xe2/0x238 lock_acquire+0xb0/0x200 _raw_spin_lock_irqsave+0x6a/0xd8 obj_cgroup_release+0x4a/0xe0 percpu_ref_put_many.constprop.0+0x150/0x168 drain_obj_stock+0x94/0xe8 refill_obj_stock+0x94/0x278 obj_cgroup_charge+0x164/0x1d8 kmem_cache_alloc+0xac/0x528 __sigqueue_alloc+0x150/0x308 __send_signal+0x260/0x550 send_signal+0x7e/0x348 force_sig_info_to_task+0x104/0x180 force_sig_fault+0x48/0x58 __do_pgm_check+0x120/0x1f0 pgm_check_handler+0x11e/0x180 INFO: lockdep is turned off.
In this example a slab allocation from __send_signal() caused a refilling and draining of a percpu objcg stock, resulted in a releasing of another non-related objcg. Objcg release path requires taking the css_set_lock, which is used to synchronize objcg lists.
This can create a circular dependency with the sighandler lock, which is taken with the locked css_set_lock by the freezer code (to freeze a task).
In general it seems that using css_set_lock to synchronize objcg lists makes any slab allocations and deallocation with the locked css_set_lock and any intervened locks risky.
To fix the problem and make the code more robust let's stop using css_set_lock to synchronize objcg lists and use a new dedicated spinlock instead.
Link: https://lkml.kernel.org/r/Yfm1IHmoGdyUR81T@carbon.dhcp.thefacebook.com Fixes: bf4f059954dc ("mm: memcg/slab: obj_cgroup API") Signed-off-by: Roman Gushchin guro@fb.com Reported-by: Alexander Egorenkov egorenar@linux.ibm.com Tested-by: Alexander Egorenkov egorenar@linux.ibm.com Reviewed-by: Waiman Long longman@redhat.com Acked-by: Tejun Heo tj@kernel.org Reviewed-by: Shakeel Butt shakeelb@google.com Reviewed-by: Jeremy Linton jeremy.linton@arm.com Tested-by: Jeremy Linton jeremy.linton@arm.com Cc: Johannes Weiner hannes@cmpxchg.org Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yu Liao liaoyu15@huawei.com Reviewed-by: Wei Li liwei391@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- include/linux/memcontrol.h | 5 +++-- mm/memcontrol.c | 10 +++++----- 2 files changed, 8 insertions(+), 7 deletions(-)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 9d3a952024a6..3a4ea9ed39fd 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -235,7 +235,7 @@ struct obj_cgroup { struct mem_cgroup *memcg; atomic_t nr_charged_bytes; union { - struct list_head list; + struct list_head list; /* protected by objcg_lock */ struct rcu_head rcu; }; }; @@ -344,7 +344,8 @@ struct mem_cgroup { int kmemcg_id; enum memcg_kmem_state kmem_state; struct obj_cgroup __rcu *objcg; - struct list_head objcg_list; /* list of inherited objcgs */ + /* list of inherited objcgs, protected by objcg_lock */ + struct list_head objcg_list; #endif
MEMCG_PADDING(_pad2_); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c1ff95b7a82d..7061f9283a34 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -258,7 +258,7 @@ struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr) }
#ifdef CONFIG_MEMCG_KMEM -extern spinlock_t css_set_lock; +static DEFINE_SPINLOCK(objcg_lock);
static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg, unsigned int nr_pages); @@ -295,13 +295,13 @@ static void obj_cgroup_release(struct percpu_ref *ref) WARN_ON_ONCE(nr_bytes & (PAGE_SIZE - 1)); nr_pages = nr_bytes >> PAGE_SHIFT;
- spin_lock_irqsave(&css_set_lock, flags); + spin_lock_irqsave(&objcg_lock, flags); memcg = obj_cgroup_memcg(objcg); if (nr_pages) obj_cgroup_uncharge_pages(objcg, nr_pages); list_del(&objcg->list); mem_cgroup_put(memcg); - spin_unlock_irqrestore(&css_set_lock, flags); + spin_unlock_irqrestore(&objcg_lock, flags);
percpu_ref_exit(ref); kfree_rcu(objcg, rcu); @@ -333,7 +333,7 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg,
objcg = rcu_replace_pointer(memcg->objcg, NULL, true);
- spin_lock_irq(&css_set_lock); + spin_lock_irq(&objcg_lock);
/* Move active objcg to the parent's list */ xchg(&objcg->memcg, parent); @@ -348,7 +348,7 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg, } list_splice(&memcg->objcg_list, &parent->objcg_list);
- spin_unlock_irq(&css_set_lock); + spin_unlock_irq(&objcg_lock);
percpu_ref_kill(&objcg->refcnt); }