drbd: make suspend_io() / resume_io() must be thread and recursion safe

Avoid to prematurely resume application IO: don't set/clear a single
bit, but inc/dec an atomic counter.

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

3 files changed, 8 insertions, 6 deletions

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index a26265375e1e..df3d89d5777a 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -500,7 +500,6 @@ enum {
 
         MD_NO_FUA,              /* Users wants us to not use FUA/FLUSH on meta data dev */
 
-        SUSPEND_IO,             /* suspend application io */
         BITMAP_IO,              /* suspend application io;
                                    once no more io in flight, start bitmap io */
         BITMAP_IO_QUEUED,       /* Started bitmap IO */
@@ -880,6 +879,7 @@ struct drbd_device {
         atomic_t rs_pending_cnt; /* RS request/data packets on the wire */
         atomic_t unacked_cnt;    /* Need to send replies for */
         atomic_t local_cnt;      /* Waiting for local completion */
+        atomic_t suspend_cnt;
 
         /* Interval tree of pending local requests */
         struct rb_root read_requests;
@@ -2263,7 +2263,7 @@ static inline bool may_inc_ap_bio(struct drbd_device *device)
 
         if (drbd_suspended(device))
                 return false;
-        if (test_bit(SUSPEND_IO, &device->flags))
+        if (atomic_read(&device->suspend_cnt))
                 return false;
 
         /* to avoid potential deadlock or bitmap corruption,
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 613778994b23..c7cd3df8107e 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -865,9 +865,11 @@ char *ppsize(char *buf, unsigned long long size)
  * and can be long lived.
  * This changes an device->flag, is triggered by drbd internals,
  * and should be short-lived. */
+/* It needs to be a counter, since multiple threads might
+   independently suspend and resume IO. */
 void drbd_suspend_io(struct drbd_device *device)
 {
-        set_bit(SUSPEND_IO, &device->flags);
+        atomic_inc(&device->suspend_cnt);
         if (drbd_suspended(device))
                 return;
         wait_event(device->misc_wait, !atomic_read(&device->ap_bio_cnt));
@@ -875,8 +877,8 @@ void drbd_suspend_io(struct drbd_device *device)
 
 void drbd_resume_io(struct drbd_device *device)
 {
-        clear_bit(SUSPEND_IO, &device->flags);
-        wake_up(&device->misc_wait);
+        if (atomic_dec_and_test(&device->suspend_cnt))
+                wake_up(&device->misc_wait);
 }
 
 /**
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index f022e99f9855..5a7ef7873b67 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -1484,7 +1484,7 @@ int drbd_bitmap_io_from_worker(struct drbd_device *device,
         D_ASSERT(device, current == first_peer_device(device)->connection->worker.task);
 
         /* open coded non-blocking drbd_suspend_io(device); */
-        set_bit(SUSPEND_IO, &device->flags);
+        atomic_inc(&device->suspend_cnt);
 
         drbd_bm_lock(device, why, flags);
         rv = io_fn(device);