From 33d32fa7120ed184efc9be1ea3c016109b4fea84 Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Tue, 29 Aug 2017 10:20:43 +0200 Subject: drbd: fix potential deadlock when trying to detach during handshake When requesting a detach, we first suspend IO, and also inhibit meta-data IO by means of drbd_md_get_buffer(), because we don't want to "fail" the disk while there is IO in-flight: the transition into D_FAILED for detach purposes may get misinterpreted as actual IO error in a confused endio function. We wrap it all into wait_event(), to retry in case the drbd_req_state() returns SS_IN_TRANSIENT_STATE, as it does for example during an ongoing connection handshake. In that example, the receiver thread may need to grab drbd_md_get_buffer() during the handshake to make progress. To avoid potential deadlock with detach, detach needs to grab and release the meta data buffer inside of that wait_event retry loop. To avoid lock inversion between mutex_lock(&device->state_mutex) and drbd_md_get_buffer(device), introduce a new enum chg_state_flag CS_INHIBIT_MD_IO, and move the call to drbd_md_get_buffer() inside the state_mutex grabbed in drbd_req_state(). Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg Signed-off-by: Jens Axboe --- drivers/block/drbd/drbd_nl.c | 25 ++----------------------- 1 file changed, 2 insertions(+), 23 deletions(-) (limited to 'drivers/block/drbd/drbd_nl.c') diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index c383b6cf272a..6bb58a6836ed 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -2149,34 +2149,13 @@ int drbd_adm_attach(struct sk_buff *skb, struct genl_info *info) static int adm_detach(struct drbd_device *device, int force) { - enum drbd_state_rv retcode; - void *buffer; - int ret; - if (force) { set_bit(FORCE_DETACH, &device->flags); drbd_force_state(device, NS(disk, D_FAILED)); - retcode = SS_SUCCESS; - goto out; + return SS_SUCCESS; } - drbd_suspend_io(device); /* so no-one is stuck in drbd_al_begin_io */ - buffer = drbd_md_get_buffer(device, __func__); /* make sure there is no in-flight meta-data IO */ - if (buffer) { - retcode = drbd_request_state(device, NS(disk, D_FAILED)); - drbd_md_put_buffer(device); - } else /* already <= D_FAILED */ - retcode = SS_NOTHING_TO_DO; - /* D_FAILED will transition to DISKLESS. */ - drbd_resume_io(device); - ret = wait_event_interruptible(device->misc_wait, - device->state.disk != D_FAILED); - if ((int)retcode == (int)SS_IS_DISKLESS) - retcode = SS_NOTHING_TO_DO; - if (ret) - retcode = ERR_INTR; -out: - return retcode; + return drbd_request_detach_interruptible(device); } /* Detaching the disk is a process in multiple stages. First we need to lock -- cgit v1.2.3