Merge tag 'for-linus-20180830' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "Small collection of fixes that should go into this series. This pull
  contains:

   - NVMe pull request with three small fixes (via Christoph)

   - Kill useless NULL check before kmem_cache_destroy (Chengguang Xu)

   - Xen block driver pull request with persistent grant flushing fixes
     (Juergen Gross)

   - Final wbt fixes, wrapping up the changes for this series. These
     have been heavily tested (me)

   - cdrom info leak fix (Scott Bauer)

   - ATA dma quirk for SQ201 (Linus Walleij)

   - Straight forward bsg refcount_t conversion (John Pittman)"

* tag 'for-linus-20180830' of git://git.kernel.dk/linux-block:
  cdrom: Fix info leak/OOB read in cdrom_ioctl_drive_status
  nvmet: free workqueue object if module init fails
  nvme-fcloop: Fix dropped LS's to removed target port
  nvme-pci: add a memory barrier to nvme_dbbuf_update_and_check_event
  block: bsg: move atomic_t ref_count variable to refcount API
  block: remove unnecessary condition check
  ata: ftide010: Add a quirk for SQ201
  blk-wbt: remove dead code
  blk-wbt: improve waking of tasks
  blk-wbt: abstract out end IO completion handler
  xen/blkback: remove unused pers_gnts_lock from struct xen_blkif_ring
  xen/blkback: move persistent grants flags to bool
  xen/blkfront: reorder tests in xlblk_init()
  xen/blkfront: cleanup stale persistent grants
  xen/blkback: don't keep persistent grants too long

12 files changed, 269 insertions, 108 deletions

diff --git a/Documentation/ABI/testing/sysfs-driver-xen-blkback b/Documentation/ABI/testing/sysfs-driver-xen-blkback
index 8bb43b66eb55..4e7babb3ba1f 100644
--- a/Documentation/ABI/testing/sysfs-driver-xen-blkback
+++ b/Documentation/ABI/testing/sysfs-driver-xen-blkback
@@ -15,3 +15,13 @@ Description:
                 blkback. If the frontend tries to use more than
                 max_persistent_grants, the LRU kicks in and starts
                 removing 5% of max_persistent_grants every 100ms.
+
+What:           /sys/module/xen_blkback/parameters/persistent_grant_unused_seconds
+Date:           August 2018
+KernelVersion:  4.19
+Contact:        Roger Pau Monné <roger.pau@citrix.com>
+Description:
+                How long a persistent grant is allowed to remain
+                allocated without being in use. The time is in
+                seconds, 0 means indefinitely long.
+                The default is 60 seconds.
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 84507d3e9a98..8e20a0677dcf 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -123,16 +123,11 @@ static void rwb_wake_all(struct rq_wb *rwb)
         }
 }
 
-static void __wbt_done(struct rq_qos *rqos, enum wbt_flags wb_acct)
+static void wbt_rqw_done(struct rq_wb *rwb, struct rq_wait *rqw,
+                         enum wbt_flags wb_acct)
 {
-        struct rq_wb *rwb = RQWB(rqos);
-        struct rq_wait *rqw;
         int inflight, limit;
 
-        if (!(wb_acct & WBT_TRACKED))
-                return;
-
-        rqw = get_rq_wait(rwb, wb_acct);
         inflight = atomic_dec_return(&rqw->inflight);
 
         /*
@@ -166,10 +161,22 @@ static void __wbt_done(struct rq_qos *rqos, enum wbt_flags wb_acct)
                 int diff = limit - inflight;
 
                 if (!inflight || diff >= rwb->wb_background / 2)
-                        wake_up(&rqw->wait);
+                        wake_up_all(&rqw->wait);
         }
 }
 
+static void __wbt_done(struct rq_qos *rqos, enum wbt_flags wb_acct)
+{
+        struct rq_wb *rwb = RQWB(rqos);
+        struct rq_wait *rqw;
+
+        if (!(wb_acct & WBT_TRACKED))
+                return;
+
+        rqw = get_rq_wait(rwb, wb_acct);
+        wbt_rqw_done(rwb, rqw, wb_acct);
+}
+
 /*
  * Called on completion of a request. Note that it's also called when
  * a request is merged, when the request gets freed.
@@ -481,6 +488,34 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
         return limit;
 }
 
+struct wbt_wait_data {
+        struct wait_queue_entry wq;
+        struct task_struct *task;
+        struct rq_wb *rwb;
+        struct rq_wait *rqw;
+        unsigned long rw;
+        bool got_token;
+};
+
+static int wbt_wake_function(struct wait_queue_entry *curr, unsigned int mode,
+                             int wake_flags, void *key)
+{
+        struct wbt_wait_data *data = container_of(curr, struct wbt_wait_data,
+                                                        wq);
+
+        /*
+         * If we fail to get a budget, return -1 to interrupt the wake up
+         * loop in __wake_up_common.
+         */
+        if (!rq_wait_inc_below(data->rqw, get_limit(data->rwb, data->rw)))
+                return -1;
+
+        data->got_token = true;
+        list_del_init(&curr->entry);
+        wake_up_process(data->task);
+        return 1;
+}
+
 /*
  * Block if we will exceed our limit, or if we are currently waiting for
  * the timer to kick off queuing again.
@@ -491,19 +526,40 @@ static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct,
         __acquires(lock)
 {
         struct rq_wait *rqw = get_rq_wait(rwb, wb_acct);
-        DECLARE_WAITQUEUE(wait, current);
+        struct wbt_wait_data data = {
+                .wq = {
+                        .func   = wbt_wake_function,
+                        .entry  = LIST_HEAD_INIT(data.wq.entry),
+                },
+                .task = current,
+                .rwb = rwb,
+                .rqw = rqw,
+                .rw = rw,
+        };
         bool has_sleeper;
 
         has_sleeper = wq_has_sleeper(&rqw->wait);
         if (!has_sleeper && rq_wait_inc_below(rqw, get_limit(rwb, rw)))
                 return;
 
-        add_wait_queue_exclusive(&rqw->wait, &wait);
+        prepare_to_wait_exclusive(&rqw->wait, &data.wq, TASK_UNINTERRUPTIBLE);
         do {
-                set_current_state(TASK_UNINTERRUPTIBLE);
+                if (data.got_token)
+                        break;
 
-                if (!has_sleeper && rq_wait_inc_below(rqw, get_limit(rwb, rw)))
+                if (!has_sleeper &&
+                    rq_wait_inc_below(rqw, get_limit(rwb, rw))) {
+                        finish_wait(&rqw->wait, &data.wq);
+
+                        /*
+                         * We raced with wbt_wake_function() getting a token,
+                         * which means we now have two. Put our local token
+                         * and wake anyone else potentially waiting for one.
+                         */
+                        if (data.got_token)
+                                wbt_rqw_done(rwb, rqw, wb_acct);
                         break;
+                }
 
                 if (lock) {
                         spin_unlock_irq(lock);
@@ -511,11 +567,11 @@ static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct,
                         spin_lock_irq(lock);
                 } else
                         io_schedule();
+
                 has_sleeper = false;
         } while (1);
 
-        __set_current_state(TASK_RUNNING);
-        remove_wait_queue(&rqw->wait, &wait);
+        finish_wait(&rqw->wait, &data.wq);
 }
 
 static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
@@ -580,11 +636,6 @@ static void wbt_wait(struct rq_qos *rqos, struct bio *bio, spinlock_t *lock)
                 return;
         }
 
-        if (current_is_kswapd())
-                flags |= WBT_KSWAPD;
-        if (bio_op(bio) == REQ_OP_DISCARD)
-                flags |= WBT_DISCARD;
-
         __wbt_wait(rwb, flags, bio->bi_opf, lock);
 
         if (!blk_stat_is_active(rwb->cb))
diff --git a/block/bsg.c b/block/bsg.c
index db588add6ba6..9a442c23a715 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -37,7 +37,7 @@ struct bsg_device {