drbd: Fixed a deadlock, probably only affected UP machines

After disconnect (most likely mdev->net_cnt == 0) and we are
still in an unstable state (!drbd_state_is_stable()). When we
get an IO request in drbd_get_max_buffers() (called from
__inc_ap_bio_cond(), called from inc_ap_bio()) we wake up
misc_wait. Misc_wait is also used in inc_ap_bio() to sleep
until the outcome of __inc_ap_bio_cond() changes. => Busy loop!

Solution: Have a dedicated wait queue for get_net_conf() and
put_net_conf().

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index e0e08f5..aa9bb21 100644 (file)
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -947,6 +947,7 @@ struct drbd_conf {
        union drbd_state state;
        wait_queue_head_t misc_wait;
        wait_queue_head_t state_wait;  /* upon each state change. */
+       wait_queue_head_t net_cnt_wait;
        unsigned int send_cnt;
        unsigned int recv_cnt;
        unsigned int read_cnt;
@@ -2018,7 +2019,7 @@ static inline void inc_unacked(struct drbd_conf *mdev)
 static inline void put_net_conf(struct drbd_conf *mdev)
 {
        if (atomic_dec_and_test(&mdev->net_cnt))
-               wake_up(&mdev->misc_wait);
+               wake_up(&mdev->net_cnt_wait);
 }
 
 /**

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 440b1d5..9fe9bdd 100644 (file)
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2763,6 +2763,7 @@ void drbd_init_set_defaults(struct drbd_conf *mdev)
 
        init_waitqueue_head(&mdev->misc_wait);
        init_waitqueue_head(&mdev->state_wait);
+       init_waitqueue_head(&mdev->net_cnt_wait);
        init_waitqueue_head(&mdev->ee_wait);
        init_waitqueue_head(&mdev->al_wait);
        init_waitqueue_head(&mdev->seq_wait);

diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 224c79e..22d74d7 100644 (file)
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -3775,7 +3775,7 @@ static void drbd_disconnect(struct drbd_conf *mdev)
 
        if (os.conn == C_DISCONNECTING) {
                struct hlist_head *h;
-               wait_event(mdev->misc_wait, atomic_read(&mdev->net_cnt) == 0);
+               wait_event(mdev->net_cnt_wait, atomic_read(&mdev->net_cnt) == 0);
 
                /* we must not free the tl_hash
                 * while application io is still on the fly */