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

Pull block bits from Jens Axboe:
 "As vacation is coming up, thought I'd better get rid of my pending
  changes in my for-linus branch for this iteration.  It contains:

   - Two patches for mtip32xx.  Killing a non-compliant sysfs interface
     and moving it to debugfs, where it belongs.

   - A few patches from Asias.  Two legit bug fixes, and one killing an
     interface that is no longer in use.

   - A patch from Jan, making the annoying partition ioctl warning a bit
     less annoying, by restricting it to !CAP_SYS_RAWIO only.

   - Three bug fixes for drbd from Lars Ellenberg.

   - A fix for an old regression for umem, it hasn't really worked since
     the plugging scheme was changed in 3.0.

   - A few fixes from Tejun.

   - A splice fix from Eric Dumazet, fixing an issue with pipe
     resizing."

* 'for-linus' of git://git.kernel.dk/linux-block:
  scsi: Silence unnecessary warnings about ioctl to partition
  block: Drop dead function blk_abort_queue()
  block: Mitigate lock unbalance caused by lock switching
  block: Avoid missed wakeup in request waitqueue
  umem: fix up unplugging
  splice: fix racy pipe->buffers uses
  drbd: fix null pointer dereference with on-congestion policy when diskless
  drbd: fix list corruption by failing but already aborted reads
  drbd: fix access of unallocated pages and kernel panic
  xen/blkfront: Add WARN to deal with misbehaving backends.
  blkcg: drop local variable @q from blkg_destroy()
  mtip32xx: Create debugfs entries for troubleshooting
  mtip32xx: Remove 'registers' and 'flags' from sysfs
  blkcg: fix blkg_alloc() failure path
  block: blkcg_policy_cfq shouldn't be used if !CONFIG_CFQ_GROUP_IOSCHED
  block: fix return value on cfq_init() failure
  mtip32xx: Remove version.h header file inclusion
  xen/blkback: Copy id field when doing BLKIF_DISCARD.

Documentation/ABI/testing/sysfs-block-rssd

@@ -1,26 +1,5 @@
-What:           /sys/block/rssd*/registers
-Date:           March 2012
-KernelVersion:  3.3
-Contact:        Asai Thambi S P <[email protected]>
-Description:    This is a read-only file. Dumps below driver information and
-                hardware registers.
-                    - S ACTive
-                    - Command Issue
-                    - Completed
-                    - PORT IRQ STAT
-                    - HOST IRQ STAT
-                    - Allocated
-                    - Commands in Q
-
 What:           /sys/block/rssd*/status
 Date:           April 2012
 KernelVersion:  3.4
 Contact:        Asai Thambi S P <[email protected]>
 Description:    This is a read-only file. Indicates the status of the device.
-
-What:           /sys/block/rssd*/flags
-Date:           May 2012
-KernelVersion:  3.5
-Contact:        Asai Thambi S P <[email protected]>
-Description:    This is a read-only file. Dumps the flags in port and driver
-                data structure

block/blk-cgroup.c

@@ -125,12 +125,8 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q)
 
 		blkg->pd[i] = pd;
 		pd->blkg = blkg;
-	}
-
-	/* invoke per-policy init */
-	for (i = 0; i < BLKCG_MAX_POLS; i++) {
-		struct blkcg_policy *pol = blkcg_policy[i];
 
+		/* invoke per-policy init */
 		if (blkcg_policy_enabled(blkg->q, pol))
 			pol->pd_init_fn(blkg);
 	}
@@ -245,10 +241,9 @@ EXPORT_SYMBOL_GPL(blkg_lookup_create);
 
 static void blkg_destroy(struct blkcg_gq *blkg)
 {
-	struct request_queue *q = blkg->q;
 	struct blkcg *blkcg = blkg->blkcg;
 
-	lockdep_assert_held(q->queue_lock);
+	lockdep_assert_held(blkg->q->queue_lock);
 	lockdep_assert_held(&blkcg->lock);
 
 	/* Something wrong if we are trying to remove same group twice */

block/blk-core.c

@@ -361,9 +361,10 @@ EXPORT_SYMBOL(blk_put_queue);
  */
 void blk_drain_queue(struct request_queue *q, bool drain_all)
 {
+	int i;
+
 	while (true) {
 		bool drain = false;
-		int i;
 
 		spin_lock_irq(q->queue_lock);
 
@@ -408,6 +409,18 @@ void blk_drain_queue(struct request_queue *q, bool drain_all)
 			break;
 		msleep(10);
 	}
+
+	/*
+	 * With queue marked dead, any woken up waiter will fail the
+	 * allocation path, so the wakeup chaining is lost and we're
+	 * left with hung waiters. We need to wake up those waiters.
+	 */
+	if (q->request_fn) {
+		spin_lock_irq(q->queue_lock);
+		for (i = 0; i < ARRAY_SIZE(q->rq.wait); i++)
+			wake_up_all(&q->rq.wait[i]);
+		spin_unlock_irq(q->queue_lock);
+	}
 }
 
 /**
@@ -467,7 +480,6 @@ void blk_cleanup_queue(struct request_queue *q)
 	/* mark @q DEAD, no new request or merges will be allowed afterwards */
 	mutex_lock(&q->sysfs_lock);
 	queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q);
-
 	spin_lock_irq(lock);
 
 	/*
@@ -485,10 +497,6 @@ void blk_cleanup_queue(struct request_queue *q)
 	queue_flag_set(QUEUE_FLAG_NOMERGES, q);
 	queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
 	queue_flag_set(QUEUE_FLAG_DEAD, q);
-
-	if (q->queue_lock != &q->__queue_lock)
-		q->queue_lock = &q->__queue_lock;
-
 	spin_unlock_irq(lock);
 	mutex_unlock(&q->sysfs_lock);
 
@@ -499,6 +507,11 @@ void blk_cleanup_queue(struct request_queue *q)
 	del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
 	blk_sync_queue(q);
 
+	spin_lock_irq(lock);
+	if (q->queue_lock != &q->__queue_lock)
+		q->queue_lock = &q->__queue_lock;
+	spin_unlock_irq(lock);
+
 	/* @q is and will stay empty, shutdown and put */
 	blk_put_queue(q);
 }

block/blk-timeout.c

@@ -197,44 +197,3 @@ void blk_add_timer(struct request *req)
 		mod_timer(&q->timeout, expiry);
 }
 
-/**
- * blk_abort_queue -- Abort all request on given queue
- * @queue:	pointer to queue
- *
- */
-void blk_abort_queue(struct request_queue *q)
-{
-	unsigned long flags;
-	struct request *rq, *tmp;
-	LIST_HEAD(list);
-
-	/*
-	 * Not a request based block device, nothing to abort
-	 */
-	if (!q->request_fn)
-		return;
-
-	spin_lock_irqsave(q->queue_lock, flags);
-
-	elv_abort_queue(q);
-
-	/*
-	 * Splice entries to local list, to avoid deadlocking if entries
-	 * get readded to the timeout list by error handling
-	 */
-	list_splice_init(&q->timeout_list, &list);
-
-	list_for_each_entry_safe(rq, tmp, &list, timeout_list)
-		blk_abort_request(rq);
-
-	/*
-	 * Occasionally, blk_abort_request() will return without
-	 * deleting the element from the list. Make sure we add those back
-	 * instead of leaving them on the local stack list.
-	 */
-	list_splice(&list, &q->timeout_list);
-
-	spin_unlock_irqrestore(q->queue_lock, flags);
-
-}
-EXPORT_SYMBOL_GPL(blk_abort_queue);

block/cfq-iosched.c

@@ -17,8 +17,6 @@
 #include "blk.h"
 #include "blk-cgroup.h"
 
-static struct blkcg_policy blkcg_policy_cfq __maybe_unused;
-
 /*
  * tunables
  */
@@ -418,11 +416,6 @@ static inline struct cfq_group *pd_to_cfqg(struct blkg_policy_data *pd)
 	return pd ? container_of(pd, struct cfq_group, pd) : NULL;
 }
 
-static inline struct cfq_group *blkg_to_cfqg(struct blkcg_gq *blkg)
-{
-	return pd_to_cfqg(blkg_to_pd(blkg, &blkcg_policy_cfq));
-}
-
 static inline struct blkcg_gq *cfqg_to_blkg(struct cfq_group *cfqg)
 {
 	return pd_to_blkg(&cfqg->pd);
@@ -572,6 +565,13 @@ static inline void cfqg_stats_update_avg_queue_size(struct cfq_group *cfqg) { }
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 
+static struct blkcg_policy blkcg_policy_cfq;
+
+static inline struct cfq_group *blkg_to_cfqg(struct blkcg_gq *blkg)
+{
+	return pd_to_cfqg(blkg_to_pd(blkg, &blkcg_policy_cfq));
+}
+
 static inline void cfqg_get(struct cfq_group *cfqg)
 {
 	return blkg_get(cfqg_to_blkg(cfqg));
@@ -3951,10 +3951,11 @@ static void cfq_exit_queue(struct elevator_queue *e)
 
 	cfq_shutdown_timer_wq(cfqd);
 
-#ifndef CONFIG_CFQ_GROUP_IOSCHED
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+	blkcg_deactivate_policy(q, &blkcg_policy_cfq);
+#else
 	kfree(cfqd->root_group);
 #endif
-	blkcg_deactivate_policy(q, &blkcg_policy_cfq);
 	kfree(cfqd);
 }
 
@@ -4194,14 +4195,15 @@ static int __init cfq_init(void)
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
 	if (!cfq_group_idle)
 		cfq_group_idle = 1;
-#else
-		cfq_group_idle = 0;
-#endif
 
 	ret = blkcg_policy_register(&blkcg_policy_cfq);
 	if (ret)
 		return ret;
+#else
+	cfq_group_idle = 0;
+#endif
 
+	ret = -ENOMEM;
 	cfq_pool = KMEM_CACHE(cfq_queue, 0);
 	if (!cfq_pool)
 		goto err_pol_unreg;
@@ -4215,13 +4217,17 @@ static int __init cfq_init(void)
 err_free_pool:
 	kmem_cache_destroy(cfq_pool);
 err_pol_unreg:
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
 	blkcg_policy_unregister(&blkcg_policy_cfq);
+#endif
 	return ret;
 }
 
 static void __exit cfq_exit(void)
 {
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
 	blkcg_policy_unregister(&blkcg_policy_cfq);
+#endif
 	elv_unregister(&iosched_cfq);
 	kmem_cache_destroy(cfq_pool);
 }

block/scsi_ioctl.c

@@ -721,11 +721,14 @@ int scsi_verify_blk_ioctl(struct block_device *bd, unsigned int cmd)
 		break;
 	}
 
+	if (capable(CAP_SYS_RAWIO))
+		return 0;
+
 	/* In particular, rule out all resets and host-specific ioctls.  */
 	printk_ratelimited(KERN_WARNING
 			   "%s: sending ioctl %x to a partition!\n", current->comm, cmd);
 
-	return capable(CAP_SYS_RAWIO) ? 0 : -ENOIOCTLCMD;
+	return -ENOIOCTLCMD;
 }
 EXPORT_SYMBOL(scsi_verify_blk_ioctl);
 

drivers/block/drbd/drbd_bitmap.c

@@ -1475,10 +1475,17 @@ void _drbd_bm_set_bits(struct drbd_conf *mdev, const unsigned long s, const unsi
 		first_word = 0;
 		spin_lock_irq(&b->bm_lock);
 	}
-
 	/* last page (respectively only page, for first page == last page) */
 	last_word = MLPP(el >> LN2_BPL);
-	bm_set_full_words_within_one_page(mdev->bitmap, last_page, first_word, last_word);
+
+	/* consider bitmap->bm_bits = 32768, bitmap->bm_number_of_pages = 1. (or multiples).
+	 * ==> e = 32767, el = 32768, last_page = 2,
+	 * and now last_word = 0.
+	 * We do not want to touch last_page in this case,
+	 * as we did not allocate it, it is not present in bitmap->bm_pages.
+	 */
+	if (last_word)
+		bm_set_full_words_within_one_page(mdev->bitmap, last_page, first_word, last_word);
 
 	/* possibly trailing bits.
 	 * example: (e & 63) == 63, el will be e+1.

drivers/block/drbd/drbd_req.c

@@ -472,12 +472,17 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what,
 		req->rq_state |= RQ_LOCAL_COMPLETED;
 		req->rq_state &= ~RQ_LOCAL_PENDING;
 
-		D_ASSERT(!(req->rq_state & RQ_NET_MASK));
+		if (req->rq_state & RQ_LOCAL_ABORTED) {
+			_req_may_be_done(req, m);
+			break;
+		}
 
 		__drbd_chk_io_error(mdev, false);
 
 	goto_queue_for_net_read:
 
+		D_ASSERT(!(req->rq_state & RQ_NET_MASK));
+
 		/* no point in retrying if there is no good remote data,
 		 * or we have no connection. */
 		if (mdev->state.pdsk != D_UP_TO_DATE) {
@@ -765,6 +770,40 @@ static int drbd_may_do_local_read(struct drbd_conf *mdev, sector_t sector, int s
 	return 0 == drbd_bm_count_bits(mdev, sbnr, ebnr);
 }
 
+static void maybe_pull_ahead(struct drbd_conf *mdev)
+{
+	int congested = 0;
+
+	/* If I don't even have good local storage, we can not reasonably try
+	 * to pull ahead of the peer. We also need the local reference to make
+	 * sure mdev->act_log is there.
+	 * Note: caller has to make sure that net_conf is there.
+	 */
+	if (!get_ldev_if_state(mdev, D_UP_TO_DATE))
+		return;
+
+	if (mdev->net_conf->cong_fill &&
+	    atomic_read(&mdev->ap_in_flight) >= mdev->net_conf->cong_fill) {
+		dev_info(DEV, "Congestion-fill threshold reached\n");
+		congested = 1;
+	}
+
+	if (mdev->act_log->used >= mdev->net_conf->cong_extents) {
+		dev_info(DEV, "Congestion-extents threshold reached\n");
+		congested = 1;
+	}
+
+	if (congested) {
+		queue_barrier(mdev); /* last barrier, after mirrored writes */
+
+		if (mdev->net_conf->on_congestion == OC_PULL_AHEAD)
+			_drbd_set_state(_NS(mdev, conn, C_AHEAD), 0, NULL);
+		else  /*mdev->net_conf->on_congestion == OC_DISCONNECT */
+			_drbd_set_state(_NS(mdev, conn, C_DISCONNECTING), 0, NULL);
+	}
+	put_ldev(mdev);
+}
+
 static int drbd_make_request_common(struct drbd_conf *mdev, struct bio *bio, unsigned long start_time)
 {
 	const int rw = bio_rw(bio);
@@ -972,29 +1011,8 @@ static int drbd_make_request_common(struct drbd_conf *mdev, struct bio *bio, uns
 		_req_mod(req, queue_for_send_oos);
 
 	if (remote &&
-	    mdev->net_conf->on_congestion != OC_BLOCK && mdev->agreed_pro_version >= 96) {
-		int congested = 0;
-
-		if (mdev->net_conf->cong_fill &&
-		    atomic_read(&mdev->ap_in_flight) >= mdev->net_conf->cong_fill) {
-			dev_info(DEV, "Congestion-fill threshold reached\n");
-			congested = 1;
-		}
-
-		if (mdev->act_log->used >= mdev->net_conf->cong_extents) {
-			dev_info(DEV, "Congestion-extents threshold reached\n");
-			congested = 1;
-		}
-
-		if (congested) {
-			queue_barrier(mdev); /* last barrier, after mirrored writes */
-
-			if (mdev->net_conf->on_congestion == OC_PULL_AHEAD)
-				_drbd_set_state(_NS(mdev, conn, C_AHEAD), 0, NULL);
-			else  /*mdev->net_conf->on_congestion == OC_DISCONNECT */
-				_drbd_set_state(_NS(mdev, conn, C_DISCONNECTING), 0, NULL);
-		}
-	}
+	    mdev->net_conf->on_congestion != OC_BLOCK && mdev->agreed_pro_version >= 96)
+		maybe_pull_ahead(mdev);
 
 	spin_unlock_irq(&mdev->req_lock);
 	kfree(b); /* if someone else has beaten us to it... */