From: Sun Ke sunke32@huawei.com
mainline inclusion from mainline-v5.6-rc1 commit 5c0dd228b5fc30a3b732c7ae2657e0161ec7ed80 category: bugfix bugzilla: 185690 CVE: NA
-----------------------------------------------
When kzalloc fail, may cause trying to destroy the workqueue from inside the workqueue.
If num_connections is m (2 < m), and NO.1 ~ NO.n (1 < n < m) kzalloc are successful. The NO.(n + 1) failed. Then, nbd_start_device will return ENOMEM to nbd_start_device_ioctl, and nbd_start_device_ioctl will return immediately without running flush_workqueue. However, we still have n recv threads. If nbd_release run first, recv threads may have to drop the last config_refs and try to destroy the workqueue from inside the workqueue.
To fix it, add a flush_workqueue in nbd_start_device.
Fixes: e9e006f5fcf2 ("nbd: fix max number of supported devs") Signed-off-by: Sun Ke sunke32@huawei.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Ye Bin yebin10@huawei.com Reviewed-by: Jason Yan yanaijie@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/block/nbd.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 33a52be762d24..775cbb4c1bbcd 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1306,6 +1306,16 @@ static int nbd_start_device(struct nbd_device *nbd) args = kzalloc(sizeof(*args), GFP_KERNEL); if (!args) { sock_shutdown(nbd); + /* + * If num_connections is m (2 < m), + * and NO.1 ~ NO.n(1 < n < m) kzallocs are successful. + * But NO.(n + 1) failed. We still have n recv threads. + * So, add flush_workqueue here to prevent recv threads + * dropping the last config_refs and trying to destroy + * the workqueue from inside the workqueue. + */ + if (i) + flush_workqueue(nbd->recv_workq); return -ENOMEM; } sk_set_memalloc(config->socks[i]->sock->sk);
From: Ye Bin yebin10@huawei.com
mainline inclusion from mainline-v5.16 commit e2daec488c57069a4a431d5b752f50294c4bf273 category: bugfix bugzilla: 185690 CVE: NA
-----------------------------------------------
I got follow issue: [ 247.381177] INFO: task kworker/u10:0:47 blocked for more than 120 seconds. [ 247.382644] Not tainted 4.19.90-dirty #140 [ 247.383502] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 247.385027] Call Trace: [ 247.388384] schedule+0xb8/0x3c0 [ 247.388966] schedule_timeout+0x2b4/0x380 [ 247.392815] wait_for_completion+0x367/0x510 [ 247.397713] flush_workqueue+0x32b/0x1340 [ 247.402700] drain_workqueue+0xda/0x3c0 [ 247.403442] destroy_workqueue+0x7b/0x690 [ 247.405014] nbd_config_put.cold+0x2f9/0x5b6 [ 247.405823] recv_work+0x1fd/0x2b0 [ 247.406485] process_one_work+0x70b/0x1610 [ 247.407262] worker_thread+0x5a9/0x1060 [ 247.408699] kthread+0x35e/0x430 [ 247.410918] ret_from_fork+0x1f/0x30
We can reproduce issue as follows: 1. Inject memory fault in nbd_start_device -1244,10 +1248,18 @@ static int nbd_start_device(struct nbd_device *nbd) nbd_dev_dbg_init(nbd); for (i = 0; i < num_connections; i++) { struct recv_thread_args *args; - - args = kzalloc(sizeof(*args), GFP_KERNEL); + + if (i == 1) { + args = NULL; + printk("%s: inject malloc error\n", __func__); + } + else + args = kzalloc(sizeof(*args), GFP_KERNEL); 2. Inject delay in recv_work -757,6 +760,8 @@ static void recv_work(struct work_struct *work)
blk_mq_complete_request(blk_mq_rq_from_pdu(cmd)); } + printk("%s: comm=%s pid=%d\n", __func__, current->comm, current->pid); + mdelay(5 * 1000); nbd_config_put(nbd); atomic_dec(&config->recv_threads); wake_up(&config->recv_wq); 3. Create nbd server nbd-server 8000 /tmp/disk 4. Create nbd client nbd-client localhost 8000 /dev/nbd1 Then will trigger above issue.
Reason is when add delay in recv_work, lead to release the last reference of 'nbd->config_refs'. nbd_config_put will call flush_workqueue to make all work finish. Obviously, it will lead to deadloop. To solve this issue, according to Josef's suggestion move 'recv_work' init from start device to nbd_dev_add, then destroy 'recv_work'when nbd device teardown.
Signed-off-by: Ye Bin yebin10@huawei.com Reviewed-by: Josef Bacik josef@toxicpanda.com Link: https://lore.kernel.org/r/20211102015237.2309763-5-yebin10@huawei.com Signed-off-by: Jens Axboe axboe@kernel.dk
conflicts: drivers/block/nbd.c
Signed-off-by: Ye Bin yebin10@huawei.com Reviewed-by: Jason Yan yanaijie@huawei.com Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/block/nbd.c | 34 ++++++++++++++-------------------- 1 file changed, 14 insertions(+), 20 deletions(-)
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 775cbb4c1bbcd..e064461b3e144 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -242,6 +242,7 @@ static void nbd_dev_remove(struct nbd_device *nbd) if (test_bit(NBD_DESTROY_ON_DISCONNECT, &nbd->flags) && nbd->destroy_complete) complete(nbd->destroy_complete);
+ destroy_workqueue(nbd->recv_workq); kfree(nbd); }
@@ -1247,10 +1248,6 @@ static void nbd_config_put(struct nbd_device *nbd) kfree(nbd->config); nbd->config = NULL;
- if (nbd->recv_workq) - destroy_workqueue(nbd->recv_workq); - nbd->recv_workq = NULL; - nbd->tag_set.timeout = 0; nbd->disk->queue->limits.discard_granularity = 0; nbd->disk->queue->limits.discard_alignment = 0; @@ -1279,14 +1276,6 @@ static int nbd_start_device(struct nbd_device *nbd) return -EINVAL; }
- nbd->recv_workq = alloc_workqueue("knbd%d-recv", - WQ_MEM_RECLAIM | WQ_HIGHPRI | - WQ_UNBOUND, 0, nbd->index); - if (!nbd->recv_workq) { - dev_err(disk_to_dev(nbd->disk), "Could not allocate knbd recv work queue.\n"); - return -ENOMEM; - } - blk_mq_update_nr_hw_queues(&nbd->tag_set, config->num_connections); nbd->pid = task_pid_nr(current);
@@ -1747,6 +1736,15 @@ static int nbd_dev_add(int index) } disk->queue = q;
+ nbd->recv_workq = alloc_workqueue("nbd%d-recv", + WQ_MEM_RECLAIM | WQ_HIGHPRI | + WQ_UNBOUND, 0, nbd->index); + if (!nbd->recv_workq) { + dev_err(disk_to_dev(nbd->disk), "Could not allocate knbd recv work queue.\n"); + err = -ENOMEM; + goto out_free_tags; + } + /* * Tell the block layer that we are not a rotational device */ @@ -1774,7 +1772,7 @@ static int nbd_dev_add(int index) disk->first_minor = index << part_shift; if (disk->first_minor < index || disk->first_minor > MINORMASK) { err = -EINVAL; - goto out_free_tags; + goto out_free_work; }
disk->fops = &nbd_fops; @@ -1784,6 +1782,8 @@ static int nbd_dev_add(int index) nbd_total_devices++; return index;
+out_free_work: + destroy_workqueue(nbd->recv_workq); out_free_tags: blk_mq_free_tag_set(&nbd->tag_set); out_free_idr: @@ -2035,13 +2035,7 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd) nbd_disconnect(nbd); nbd_clear_sock(nbd); mutex_unlock(&nbd->config_lock); - /* - * Make sure recv thread has finished, so it does not drop the last - * config ref and try to destroy the workqueue from inside the work - * queue. - */ - if (nbd->recv_workq) - flush_workqueue(nbd->recv_workq); + flush_workqueue(nbd->recv_workq); if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF, &nbd->config->runtime_flags)) nbd_config_put(nbd);
-
Yang Yingliang