summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorJens Axboe <axboe@kernel.dk>2020-02-11 14:30:06 +0100
committerJens Axboe <axboe@kernel.dk>2020-02-13 01:43:22 +0100
commit7563439adfae153b20331f1567c8b5d0e5cbd8a7 (patch)
treee00dba178757a4090d246ae6ecf3ae275bc95398 /fs
parentio_uring: retain sockaddr_storage across send/recvmsg async punt (diff)
downloadlinux-7563439adfae153b20331f1567c8b5d0e5cbd8a7.tar.xz
linux-7563439adfae153b20331f1567c8b5d0e5cbd8a7.zip
io-wq: don't call kXalloc_node() with non-online node
Glauber reports a crash on init on a box he has: RIP: 0010:__alloc_pages_nodemask+0x132/0x340 Code: 18 01 75 04 41 80 ce 80 89 e8 48 8b 54 24 08 8b 74 24 1c c1 e8 0c 48 8b 3c 24 83 e0 01 88 44 24 20 48 85 d2 0f 85 74 01 00 00 <3b> 77 08 0f 82 6b 01 00 00 48 89 7c 24 10 89 ea 48 8b 07 b9 00 02 RSP: 0018:ffffb8be4d0b7c28 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 000000000000e8e8 RDX: 0000000000000000 RSI: 0000000000000002 RDI: 0000000000002080 RBP: 0000000000012cc0 R08: 0000000000000000 R09: 0000000000000002 R10: 0000000000000dc0 R11: ffff995c60400100 R12: 0000000000000000 R13: 0000000000012cc0 R14: 0000000000000001 R15: ffff995c60db00f0 FS: 00007f4d115ca900(0000) GS:ffff995c60d80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000002088 CR3: 00000017cca66002 CR4: 00000000007606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: alloc_slab_page+0x46/0x320 new_slab+0x9d/0x4e0 ___slab_alloc+0x507/0x6a0 ? io_wq_create+0xb4/0x2a0 __slab_alloc+0x1c/0x30 kmem_cache_alloc_node_trace+0xa6/0x260 io_wq_create+0xb4/0x2a0 io_uring_setup+0x97f/0xaa0 ? io_remove_personalities+0x30/0x30 ? io_poll_trigger_evfd+0x30/0x30 do_syscall_64+0x5b/0x1c0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f4d116cb1ed which is due to the 'wqe' and 'worker' allocation being node affine. But it isn't valid to call the node affine allocation if the node isn't online. Setup structures for even offline nodes, as usual, but skip them in terms of thread setup to not waste resources. If the node isn't online, just alloc memory with NUMA_NO_NODE. Reported-by: Glauber Costa <glauber@scylladb.com> Tested-by: Glauber Costa <glauber@scylladb.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'fs')
-rw-r--r--fs/io-wq.c22
1 files changed, 18 insertions, 4 deletions
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 182aa17dc2ca..0a5ab1a8f69a 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -699,11 +699,16 @@ static int io_wq_manager(void *data)
/* create fixed workers */
refcount_set(&wq->refs, workers_to_create);
for_each_node(node) {
+ if (!node_online(node))
+ continue;
if (!create_io_worker(wq, wq->wqes[node], IO_WQ_ACCT_BOUND))
goto err;
workers_to_create--;
}
+ while (workers_to_create--)
+ refcount_dec(&wq->refs);
+
complete(&wq->done);
while (!kthread_should_stop()) {
@@ -711,6 +716,9 @@ static int io_wq_manager(void *data)
struct io_wqe *wqe = wq->wqes[node];
bool fork_worker[2] = { false, false };
+ if (!node_online(node))
+ continue;
+
spin_lock_irq(&wqe->lock);
if (io_wqe_need_worker(wqe, IO_WQ_ACCT_BOUND))
fork_worker[IO_WQ_ACCT_BOUND] = true;
@@ -829,7 +837,9 @@ static bool io_wq_for_each_worker(struct io_wqe *wqe,
list_for_each_entry_rcu(worker, &wqe->all_list, all_list) {
if (io_worker_get(worker)) {
- ret = func(worker, data);
+ /* no task if node is/was offline */
+ if (worker->task)
+ ret = func(worker, data);
io_worker_release(worker);
if (ret)
break;
@@ -1084,6 +1094,8 @@ void io_wq_flush(struct io_wq *wq)
for_each_node(node) {
struct io_wqe *wqe = wq->wqes[node];
+ if (!node_online(node))
+ continue;
init_completion(&data.done);
INIT_IO_WORK(&data.work, io_wq_flush_func);
data.work.flags |= IO_WQ_WORK_INTERNAL;
@@ -1115,12 +1127,15 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
for_each_node(node) {
struct io_wqe *wqe;
+ int alloc_node = node;
- wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, node);
+ if (!node_online(alloc_node))
+ alloc_node = NUMA_NO_NODE;
+ wqe = kzalloc_node(sizeof(struct io_wqe), GFP_KERNEL, alloc_node);
if (!wqe)
goto err;
wq->wqes[node] = wqe;
- wqe->node = node;
+ wqe->node = alloc_node;
wqe->acct[IO_WQ_ACCT_BOUND].max_workers = bounded;
atomic_set(&wqe->acct[IO_WQ_ACCT_BOUND].nr_running, 0);
if (wq->user) {
@@ -1128,7 +1143,6 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
task_rlimit(current, RLIMIT_NPROC);
}
atomic_set(&wqe->acct[IO_WQ_ACCT_UNBOUND].nr_running, 0);
- wqe->node = node;
wqe->wq = wq;
spin_lock_init(&wqe->lock);
INIT_WQ_LIST(&wqe->work_list);