From 391acf970d21219a2a5446282d3b20eace0c0d7a Mon Sep 17 00:00:00 2001 From: Gu Zheng Date: Wed, 25 Jun 2014 09:57:18 +0800 Subject: cpuset,mempolicy: fix sleeping function called from invalid context When runing with the kernel(3.15-rc7+), the follow bug occurs: [ 9969.258987] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:586 [ 9969.359906] in_atomic(): 1, irqs_disabled(): 0, pid: 160655, name: python [ 9969.441175] INFO: lockdep is turned off. [ 9969.488184] CPU: 26 PID: 160655 Comm: python Tainted: G A 3.15.0-rc7+ #85 [ 9969.581032] Hardware name: FUJITSU-SV PRIMEQUEST 1800E/SB, BIOS PRIMEQUEST 1000 Series BIOS Version 1.39 11/16/2012 [ 9969.706052] ffffffff81a20e60 ffff8803e941fbd0 ffffffff8162f523 ffff8803e941fd18 [ 9969.795323] ffff8803e941fbe0 ffffffff8109995a ffff8803e941fc58 ffffffff81633e6c [ 9969.884710] ffffffff811ba5dc ffff880405c6b480 ffff88041fdd90a0 0000000000002000 [ 9969.974071] Call Trace: [ 9970.003403] [] dump_stack+0x4d/0x66 [ 9970.065074] [] __might_sleep+0xfa/0x130 [ 9970.130743] [] mutex_lock_nested+0x3c/0x4f0 [ 9970.200638] [] ? kmem_cache_alloc+0x1bc/0x210 [ 9970.272610] [] cpuset_mems_allowed+0x27/0x140 [ 9970.344584] [] ? __mpol_dup+0x63/0x150 [ 9970.409282] [] __mpol_dup+0xe5/0x150 [ 9970.471897] [] ? __mpol_dup+0x63/0x150 [ 9970.536585] [] ? copy_process.part.23+0x606/0x1d40 [ 9970.613763] [] ? trace_hardirqs_on+0xd/0x10 [ 9970.683660] [] ? monotonic_to_bootbased+0x2f/0x50 [ 9970.759795] [] copy_process.part.23+0x670/0x1d40 [ 9970.834885] [] do_fork+0xd8/0x380 [ 9970.894375] [] ? __audit_syscall_entry+0x9c/0xf0 [ 9970.969470] [] SyS_clone+0x16/0x20 [ 9971.030011] [] stub_clone+0x69/0x90 [ 9971.091573] [] ? system_call_fastpath+0x16/0x1b The cause is that cpuset_mems_allowed() try to take mutex_lock(&callback_mutex) under the rcu_read_lock(which was hold in __mpol_dup()). And in cpuset_mems_allowed(), the access to cpuset is under rcu_read_lock, so in __mpol_dup, we can reduce the rcu_read_lock protection region to protect the access to cpuset only in current_cpuset_is_being_rebound(). So that we can avoid this bug. This patch is a temporary solution that just addresses the bug mentioned above, can not fix the long-standing issue about cpuset.mems rebinding on fork(): "When the forker's task_struct is duplicated (which includes ->mems_allowed) and it races with an update to cpuset_being_rebound in update_tasks_nodemask() then the task's mems_allowed doesn't get updated. And the child task's mems_allowed can be wrong if the cpuset's nodemask changes before the child has been added to the cgroup's tasklist." Signed-off-by: Gu Zheng Acked-by: Li Zefan Signed-off-by: Tejun Heo Cc: stable --- kernel/cpuset.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'kernel/cpuset.c') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index f6b33c696224..d3df02e76643 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1181,7 +1181,13 @@ done: int current_cpuset_is_being_rebound(void) { - return task_cs(current) == cpuset_being_rebound; + int ret; + + rcu_read_lock(); + ret = task_cs(current) == cpuset_being_rebound; + rcu_read_unlock(); + + return ret; } static int update_relax_domain_level(struct cpuset *cs, s64 val) -- cgit v1.2.3 From 76bb5ab8f6e3e7bebdcefec4146ff305e7d0b465 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 30 Jun 2014 15:47:32 -0400 Subject: cpuset: break kernfs active protection in cpuset_write_resmask() Writing to either "cpuset.cpus" or "cpuset.mems" file flushes cpuset_hotplug_work so that cpu or memory hotunplug doesn't end up migrating tasks off a cpuset after new resources are added to it. As cpuset_hotplug_work calls into cgroup core via cgroup_transfer_tasks(), this flushing adds the dependency to cgroup core locking from cpuset_write_resmak(). This used to be okay because cgroup interface files were protected by a different mutex; however, 8353da1f91f1 ("cgroup: remove cgroup_tree_mutex") simplified the cgroup core locking and this dependency became a deadlock hazard - cgroup file removal performed under cgroup core lock tries to drain on-going file operation which is trying to flush cpuset_hotplug_work blocked on the same cgroup core lock. The locking simplification was done because kernfs added an a lot easier way to deal with circular dependencies involving kernfs active protection. Let's use the same strategy in cpuset and break active protection in cpuset_write_resmask(). While it isn't the prettiest, this is a very rare, likely unique, situation which also goes away on the unified hierarchy. The commands to trigger the deadlock warning without the patch and the lockdep output follow. localhost:/ # mount -t cgroup -o cpuset xxx /cpuset localhost:/ # mkdir /cpuset/tmp localhost:/ # echo 1 > /cpuset/tmp/cpuset.cpus localhost:/ # echo 0 > cpuset/tmp/cpuset.mems localhost:/ # echo $$ > /cpuset/tmp/tasks localhost:/ # echo 0 > /sys/devices/system/cpu/cpu1/online ====================================================== [ INFO: possible circular locking dependency detected ] 3.16.0-rc1-0.1-default+ #7 Not tainted ------------------------------------------------------- kworker/1:0/32649 is trying to acquire lock: (cgroup_mutex){+.+.+.}, at: [] cgroup_transfer_tasks+0x37/0x150 but task is already holding lock: (cpuset_hotplug_work){+.+...}, at: [] process_one_work+0x192/0x520 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (cpuset_hotplug_work){+.+...}: ... -> #1 (s_active#175){++++.+}: ... -> #0 (cgroup_mutex){+.+.+.}: ... other info that might help us debug this: Chain exists of: cgroup_mutex --> s_active#175 --> cpuset_hotplug_work Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(cpuset_hotplug_work); lock(s_active#175); lock(cpuset_hotplug_work); lock(cgroup_mutex); *** DEADLOCK *** 2 locks held by kworker/1:0/32649: #0: ("events"){.+.+.+}, at: [] process_one_work+0x192/0x520 #1: (cpuset_hotplug_work){+.+...}, at: [] process_one_work+0x192/0x520 stack backtrace: CPU: 1 PID: 32649 Comm: kworker/1:0 Not tainted 3.16.0-rc1-0.1-default+ #7 ... Call Trace: [] dump_stack+0x72/0x8a [] print_circular_bug+0x10f/0x120 [] check_prev_add+0x43e/0x4b0 [] validate_chain+0x656/0x7c0 [] __lock_acquire+0x382/0x660 [] lock_acquire+0xf9/0x170 [] mutex_lock_nested+0x6f/0x380 [] cgroup_transfer_tasks+0x37/0x150 [] hotplug_update_tasks_insane+0x110/0x1d0 [] cpuset_hotplug_update_tasks+0x13d/0x180 [] cpuset_hotplug_workfn+0x18c/0x630 [] process_one_work+0x254/0x520 [] worker_thread+0x13d/0x3d0 [] kthread+0xf8/0x100 [] ret_from_fork+0x7c/0xb0 Signed-off-by: Tejun Heo Reported-by: Li Zefan Tested-by: Li Zefan --- kernel/cpuset.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'kernel/cpuset.c') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index d3df02e76643..116a4164720a 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1623,7 +1623,17 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, * resources, wait for the previously scheduled operations before * proceeding, so that we don't end up keep removing tasks added * after execution capability is restored. + * + * cpuset_hotplug_work calls back into cgroup core via + * cgroup_transfer_tasks() and waiting for it from a cgroupfs + * operation like this one can lead to a deadlock through kernfs + * active_ref protection. Let's break the protection. Losing the + * protection is okay as we check whether @cs is online after + * grabbing cpuset_mutex anyway. This only happens on the legacy + * hierarchies. */ + css_get(&cs->css); + kernfs_break_active_protection(of->kn); flush_work(&cpuset_hotplug_work); mutex_lock(&cpuset_mutex); @@ -1651,6 +1661,8 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, free_trial_cpuset(trialcs); out_unlock: mutex_unlock(&cpuset_mutex); + kernfs_unbreak_active_protection(of->kn); + css_put(&cs->css); return retval ?: nbytes; } -- cgit v1.2.3