From 877afadad2dce8aae1f2aad8ce47e072d4f6165e Mon Sep 17 00:00:00 2001 From: Schspa Shi Date: Fri, 3 Jun 2022 16:19:14 +0800 Subject: Bluetooth: When HCI work queue is drained, only queue chained work The HCI command, event, and data packet processing workqueue is drained to avoid deadlock in commit 76727c02c1e1 ("Bluetooth: Call drain_workqueue() before resetting state"). There is another delayed work, which will queue command to this drained workqueue. Which results in the following error report: Bluetooth: hci2: command 0x040f tx timeout WARNING: CPU: 1 PID: 18374 at kernel/workqueue.c:1438 __queue_work+0xdad/0x1140 Workqueue: events hci_cmd_timeout RIP: 0010:__queue_work+0xdad/0x1140 RSP: 0000:ffffc90002cffc60 EFLAGS: 00010093 RAX: 0000000000000000 RBX: ffff8880b9d3ec00 RCX: 0000000000000000 RDX: ffff888024ba0000 RSI: ffffffff814e048d RDI: ffff8880b9d3ec08 RBP: 0000000000000008 R08: 0000000000000000 R09: 00000000b9d39700 R10: ffffffff814f73c6 R11: 0000000000000000 R12: ffff88807cce4c60 R13: 0000000000000000 R14: ffff8880796d8800 R15: ffff8880796d8800 FS: 0000000000000000(0000) GS:ffff8880b9d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000c0174b4000 CR3: 000000007cae9000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? queue_work_on+0xcb/0x110 ? lockdep_hardirqs_off+0x90/0xd0 queue_work_on+0xee/0x110 process_one_work+0x996/0x1610 ? pwq_dec_nr_in_flight+0x2a0/0x2a0 ? rwlock_bug.part.0+0x90/0x90 ? _raw_spin_lock_irq+0x41/0x50 worker_thread+0x665/0x1080 ? process_one_work+0x1610/0x1610 kthread+0x2e9/0x3a0 ? kthread_complete_and_exit+0x40/0x40 ret_from_fork+0x1f/0x30 To fix this, we can add a new HCI_DRAIN_WQ flag, and don't queue the timeout workqueue while command workqueue is draining. Fixes: 76727c02c1e1 ("Bluetooth: Call drain_workqueue() before resetting state") Reported-by: syzbot+63bed493aebbf6872647@syzkaller.appspotmail.com Signed-off-by: Schspa Shi Signed-off-by: Marcel Holtmann --- net/bluetooth/hci_core.c | 10 +++++++++- net/bluetooth/hci_event.c | 5 +++-- 2 files changed, 12 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index a0f99baafd35..6a53bcc5cfbb 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -594,6 +594,11 @@ static int hci_dev_do_reset(struct hci_dev *hdev) skb_queue_purge(&hdev->rx_q); skb_queue_purge(&hdev->cmd_q); + /* Cancel these to avoid queueing non-chained pending work */ + hci_dev_set_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE); + cancel_delayed_work(&hdev->cmd_timer); + cancel_delayed_work(&hdev->ncmd_timer); + /* Avoid potential lockdep warnings from the *_flush() calls by * ensuring the workqueue is empty up front. */ @@ -607,6 +612,8 @@ static int hci_dev_do_reset(struct hci_dev *hdev) if (hdev->flush) hdev->flush(hdev); + hci_dev_clear_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE); + atomic_set(&hdev->cmd_cnt, 1); hdev->acl_cnt = 0; hdev->sco_cnt = 0; hdev->le_cnt = 0; @@ -3864,7 +3871,8 @@ static void hci_cmd_work(struct work_struct *work) if (res < 0) __hci_cmd_sync_cancel(hdev, -res); - if (test_bit(HCI_RESET, &hdev->flags)) + if (test_bit(HCI_RESET, &hdev->flags) || + hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) cancel_delayed_work(&hdev->cmd_timer); else schedule_delayed_work(&hdev->cmd_timer, diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 63585c0bb9ce..34bec7446d00 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3768,8 +3768,9 @@ static inline void handle_cmd_cnt_and_timer(struct hci_dev *hdev, u8 ncmd) cancel_delayed_work(&hdev->ncmd_timer); atomic_set(&hdev->cmd_cnt, 1); } else { - schedule_delayed_work(&hdev->ncmd_timer, - HCI_NCMD_TIMEOUT); + if (!hci_dev_test_flag(hdev, HCI_CMD_DRAIN_WORKQUEUE)) + schedule_delayed_work(&hdev->ncmd_timer, + HCI_NCMD_TIMEOUT); } } } -- cgit v1.2.3-58-ga151