cpuset: Fix memory allocator deadlock

commit 0fc0287c9ed1ffd3706f8b4d9b314aa102ef1245 upstream.

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.

Cc: John Stultz <john.stultz@linaro.org>
Cc: Mel Gorman <mgorman@suse.de>
Reported-by: Juri Lelli <juri.lelli@gmail.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Tested-by: Juri Lelli <juri.lelli@gmail.com>
Acked-by: Li Zefan <lizefan@huawei.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 6 insertions, 2 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 8fe6f6b65006..e372d9495e42 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -983,8 +983,10 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 	need_loop = task_has_mempolicy(tsk) ||
 			!nodes_intersects(*newmems, tsk->mems_allowed);
 
-	if (need_loop)
+	if (need_loop) {
+		local_irq_disable();
 		write_seqcount_begin(&tsk->mems_allowed_seq);
+	}
 
 	nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
 	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
@@ -992,8 +994,10 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2);
 	tsk->mems_allowed = *newmems;
 
-	if (need_loop)
+	if (need_loop) {
 		write_seqcount_end(&tsk->mems_allowed_seq);
+		local_irq_enable();
+	}
 
 	task_unlock(tsk);
 }