Juri hit the below lockdep report: [ 4.303391] ====================================================== [ 4.303392] [ INFO: SOFTIRQ-safe -> SOFTIRQ-unsafe lock order detected ] [ 4.303394] 3.12.0-dl-peterz+ #144 Not tainted [ 4.303395] ------------------------------------------------------ [ 4.303397] kworker/u4:3/689 [HC0[0]:SC0[0]:HE0:SE1] is trying to acquire: [ 4.303399] (&p->mems_allowed_seq){+.+...}, at: [<ffffffff8114e63c>] new_slab+0x6c/0x290 [ 4.303417] [ 4.303417] and this task is already holding: [ 4.303418] (&(&q->__queue_lock)->rlock){..-...}, at: [<ffffffff812d2dfb>] blk_execute_rq_nowait+0x5b/0x100 [ 4.303431] which would create a new lock dependency: [ 4.303432] (&(&q->__queue_lock)->rlock){..-...} -> (&p->mems_allowed_seq){+.+...} [ 4.303436] [ 4.303898] the dependencies between the lock to be acquired and SOFTIRQ-irq-unsafe lock: [ 4.303918] -> (&p->mems_allowed_seq){+.+...} ops: 2762 { [ 4.303922] HARDIRQ-ON-W at: [ 4.303923] [<ffffffff8108ab9a>] __lock_acquire+0x65a/0x1ff0 [ 4.303926] [<ffffffff8108cbe3>] lock_acquire+0x93/0x140 [ 4.303929] [<ffffffff81063dd6>] kthreadd+0x86/0x180 [ 4.303931] [<ffffffff816ded6c>] ret_from_fork+0x7c/0xb0 [ 4.303933] SOFTIRQ-ON-W at: [ 4.303933] [<ffffffff8108abcc>] __lock_acquire+0x68c/0x1ff0 [ 4.303935] [<ffffffff8108cbe3>] lock_acquire+0x93/0x140 [ 4.303940] [<ffffffff81063dd6>] kthreadd+0x86/0x180 [ 4.303955] [<ffffffff816ded6c>] ret_from_fork+0x7c/0xb0 [ 4.303959] INITIAL USE at: [ 4.303960] [<ffffffff8108a884>] __lock_acquire+0x344/0x1ff0 [ 4.303963] [<ffffffff8108cbe3>] lock_acquire+0x93/0x140 [ 4.303966] [<ffffffff81063dd6>] kthreadd+0x86/0x180 [ 4.303969] [<ffffffff816ded6c>] ret_from_fork+0x7c/0xb0 [ 4.303972] } Which reports that we take mems_allowed_seq with interrupts enabled. A little digging found that this can only be from cpuset_change_task_nodemask(). This is an actual deadlock because an interrupt doing an allocation will hit get_mems_allowed()->...->__read_seqcount_begin(), which will spin forever waiting for the write side to complete.
Unified · Split
| @@ -1033,8 +1033,10 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk, · 1032 unmodified lines | |||
| 1033 | need_loop = task_has_mempolicy(tsk) || | 1033 | need_loop = task_has_mempolicy(tsk) || |
| 1034 | !nodes_intersects(*newmems, tsk->mems_allowed); | 1034 | !nodes_intersects(*newmems, tsk->mems_allowed); |
| 1035 | 1035 | ||
| 1036 | if (need_loop) | 1036 | if (need_loop) { |
| 1037 | local_irq_disable(); | ||
| 1037 | write_seqcount_begin(&tsk->mems_allowed_seq); | 1038 | write_seqcount_begin(&tsk->mems_allowed_seq); |
| 1039 | } | ||
| 1038 | 1040 | ||
| 1039 | nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); | 1041 | nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); |
| 1040 | mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1); | 1042 | mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1); |
| @@ -1042,8 +1044,10 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk, · 1 unmodified line | |||
| 1042 | mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2); | 1044 | mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2); |
| 1043 | tsk->mems_allowed = *newmems; | 1045 | tsk->mems_allowed = *newmems; |
| 1044 | 1046 | ||
| 1045 | if (need_loop) | 1047 | if (need_loop) { |
| 1046 | write_seqcount_end(&tsk->mems_allowed_seq); | 1048 | write_seqcount_end(&tsk->mems_allowed_seq); |
| 1049 | local_irq_enable(); | ||
| 1050 | } | ||
| 1047 | 1051 | ||
| 1048 | task_unlock(tsk); | 1052 | task_unlock(tsk); |
| 1049 | } | 1053 | } |