drbd: fix schedule in atomic

An administrative detach used to request a state change directly to D_DISKLESS,
first suspending IO to avoid the last put_ldev() occuring from an endio handler,
potentially in irq context.

This is not enough on the receiving side (typically secondary), we may miss
some peer_req on the way to local disk, which then may do the last put_ldev()
from their drbd_peer_request_endio().

This patch makes the detach always go through the intermediate D_FAILED state.
We may consider to rename it D_DETACHING.

Alternative approach would be to create yet an other work item to be scheduled
on the worker, do the destructor work from there, and get the timing right.

manually picked commit 564040f from the drbd 8.4 branch.

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 8aa10391115b0c1c183b50a86ecf6c1518f4c2e9..a74d3ee04ba8446c8113e1f970a6f9a8e03c1182 100644 (file)
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -2157,6 +2157,10 @@ static inline int get_net_conf(struct drbd_conf *mdev)
 static inline void put_ldev(struct drbd_conf *mdev)
 {
        int i = atomic_dec_return(&mdev->local_cnt);
+
+       /* This may be called from some endio handler,
+        * so we must not sleep here. */
+
        __release(local);
        D_ASSERT(i >= 0);
        if (i == 0) {

diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 7c64ec042124a117e3bd97c636d0d938caa42ca5..13569635b9220bf880647de56ecf21b00b809e47 100644 (file)
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1334,11 +1334,19 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 static int drbd_nl_detach(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
                          struct drbd_nl_cfg_reply *reply)
 {
+       enum drbd_ret_code retcode;
+       int ret;
        drbd_suspend_io(mdev); /* so no-one is stuck in drbd_al_begin_io */
-       reply->ret_code = drbd_request_state(mdev, NS(disk, D_DISKLESS));
-       if (mdev->state.disk == D_DISKLESS)
-               wait_event(mdev->misc_wait, !atomic_read(&mdev->local_cnt));
+       retcode = drbd_request_state(mdev, NS(disk, D_FAILED));
+       /* D_FAILED will transition to DISKLESS. */
+       ret = wait_event_interruptible(mdev->misc_wait,
+                       mdev->state.disk != D_FAILED);
        drbd_resume_io(mdev);
+       if (retcode == SS_IS_DISKLESS)
+               retcode = SS_NOTHING_TO_DO;
+       if (ret)
+               retcode = ERR_INTR;
+       reply->ret_code = retcode;
        return 0;
 }
 

diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index cec467f5d6768ae92f958058ab93f20edba28ec6..c86283b4fbab0c0c12f0f2be479810b01a305562 100644 (file)
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -53,7 +53,7 @@
 
 
 extern const char *drbd_buildtag(void);
-#define REL_VERSION "8.3.10"
+#define REL_VERSION "8.3.11"
 #define API_VERSION 88
 #define PRO_VERSION_MIN 86
 #define PRO_VERSION_MAX 96