Reset to 3.12.37

14 files changed, 81 insertions, 77 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 4e491d9..a573d4b 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -80,7 +80,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
 	blkg->q = q;
 	INIT_LIST_HEAD(&blkg->q_node);
 	blkg->blkcg = blkcg;
-	blkg->refcnt = 1;
+	atomic_set(&blkg->refcnt, 1);
 
 	/* root blkg uses @q->root_rl, init rl only for !root blkgs */
 	if (blkcg != &blkcg_root) {
@@ -399,11 +399,8 @@ void __blkg_release_rcu(struct rcu_head *rcu_head)
 
 	/* release the blkcg and parent blkg refs this blkg has been holding */
 	css_put(&blkg->blkcg->css);
-	if (blkg->parent) {
-		spin_lock_irq(blkg->q->queue_lock);
+	if (blkg->parent)
 		blkg_put(blkg->parent);
-		spin_unlock_irq(blkg->q->queue_lock);
-	}
 
 	blkg_free(blkg);
 }
@@ -862,6 +859,20 @@ void blkcg_drain_queue(struct request_queue *q)
 {
 	lockdep_assert_held(q->queue_lock);
 
+	/*
+	 * @q could be exiting and already have destroyed all blkgs as
+	 * indicated by NULL root_blkg.  If so, don't confuse policies.
+	 */
+	if (!q->root_blkg)
+		return;
+
+	/*
+	 * @q could be exiting and already have destroyed all blkgs as
+	 * indicated by NULL root_blkg.  If so, don't confuse policies.
+	 */
+	if (!q->root_blkg)
+		return;
+
 	blk_throtl_drain(q);
 }
 
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 2e34c38..f1c1cfc 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -18,6 +18,7 @@
 #include <linux/seq_file.h>
 #include <linux/radix-tree.h>
 #include <linux/blkdev.h>
+#include <linux/atomic.h>
 
 /* Max limits for throttle policy */
 #define THROTL_IOPS_MAX		UINT_MAX
@@ -104,7 +105,7 @@ struct blkcg_gq {
 	struct request_list		rl;
 
 	/* reference count */
-	int				refcnt;
+	atomic_t			refcnt;
 
 	/* is this blkg online? protected by both blkcg and q locks */
 	bool				online;
@@ -253,13 +254,12 @@ static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
  * blkg_get - get a blkg reference
  * @blkg: blkg to get
  *
- * The caller should be holding queue_lock and an existing reference.
+ * The caller should be holding an existing reference.
  */
 static inline void blkg_get(struct blkcg_gq *blkg)
 {
-	lockdep_assert_held(blkg->q->queue_lock);
-	WARN_ON_ONCE(!blkg->refcnt);
-	blkg->refcnt++;
+	WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0);
+	atomic_inc(&blkg->refcnt);
 }
 
 void __blkg_release_rcu(struct rcu_head *rcu);
@@ -267,14 +267,11 @@ void __blkg_release_rcu(struct rcu_head *rcu);
 /**
  * blkg_put - put a blkg reference
  * @blkg: blkg to put
- *
- * The caller should be holding queue_lock.
  */
 static inline void blkg_put(struct blkcg_gq *blkg)
 {
-	lockdep_assert_held(blkg->q->queue_lock);
-	WARN_ON_ONCE(blkg->refcnt <= 0);
-	if (!--blkg->refcnt)
+	WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0);
+	if (atomic_dec_and_test(&blkg->refcnt))
 		call_rcu(&blkg->rcu_head, __blkg_release_rcu);
 }
 
diff --git a/block/blk-core.c b/block/blk-core.c
index f703f97..bf214ae 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -232,7 +232,7 @@ EXPORT_SYMBOL(blk_delay_queue);
  **/
 void blk_start_queue(struct request_queue *q)
 {
-	WARN_ON_NONRT(!irqs_disabled());
+	WARN_ON(!irqs_disabled());
 
 	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
 	__blk_run_queue(q);
@@ -2297,7 +2297,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	if (!req->bio)
 		return false;
 
-	trace_block_rq_complete(req->q, req);
+	trace_block_rq_complete(req->q, req, nr_bytes);
 
 	/*
 	 * For fs requests, rq is just carrier of independent bio's
@@ -2925,7 +2925,7 @@ static void queue_unplugged(struct request_queue *q, unsigned int depth,
 		blk_run_queue_async(q);
 	else
 		__blk_run_queue(q);
-	spin_unlock_irq(q->queue_lock);
+	spin_unlock(q->queue_lock);
 }
 
 static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule)
@@ -2973,6 +2973,7 @@ EXPORT_SYMBOL(blk_check_plugged);
 void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 {
 	struct request_queue *q;
+	unsigned long flags;
 	struct request *rq;
 	LIST_HEAD(list);
 	unsigned int depth;
@@ -2990,6 +2991,11 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	q = NULL;
 	depth = 0;
 
+	/*
+	 * Save and disable interrupts here, to avoid doing it for every
+	 * queue lock we have to take.
+	 */
+	local_irq_save(flags);
 	while (!list_empty(&list)) {
 		rq = list_entry_rq(list.next);
 		list_del_init(&rq->queuelist);
@@ -3002,7 +3008,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 				queue_unplugged(q, depth, from_schedule);
 			q = rq->q;
 			depth = 0;
-			spin_lock_irq(q->queue_lock);
+			spin_lock(q->queue_lock);
 		}
 
 		/*
@@ -3029,6 +3035,8 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	 */
 	if (q)
 		queue_unplugged(q, depth, from_schedule);
+
+	local_irq_restore(flags);
 }
 
 void blk_finish_plug(struct blk_plug *plug)
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 899d3e4..46cd7bd 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -8,7 +8,6 @@
 #include <linux/blkdev.h>
 #include <linux/bootmem.h>	/* for max_pfn/max_low_pfn */
 #include <linux/slab.h>
-#include <linux/delay.h>
 
 #include "blk.h"
 
@@ -111,7 +110,7 @@ static void ioc_release_fn(struct work_struct *work)
 			spin_unlock(q->queue_lock);
 		} else {
 			spin_unlock_irqrestore(&ioc->lock, flags);
-			cpu_chill();
+			cpu_relax();
 			spin_lock_irqsave_nested(&ioc->lock, flags, 1);
 		}
 	}
@@ -189,7 +188,7 @@ retry:
 			spin_unlock(icq->q->queue_lock);
 		} else {
 			spin_unlock_irqrestore(&ioc->lock, flags);
-			cpu_chill();
+			cpu_relax();
 			goto retry;
 		}
 	}
diff --git a/block/blk-iopoll.c b/block/blk-iopoll.c
index 15b4f08..4b8d9b54 100644
--- a/block/blk-iopoll.c
+++ b/block/blk-iopoll.c
@@ -38,7 +38,6 @@ void blk_iopoll_sched(struct blk_iopoll *iop)
 	list_add_tail(&iop->list, &__get_cpu_var(blk_cpu_iopoll));
 	__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
 	local_irq_restore(flags);
-	preempt_check_resched_rt();
 }
 EXPORT_SYMBOL(blk_iopoll_sched);
 
@@ -136,7 +135,6 @@ static void blk_iopoll_softirq(struct softirq_action *h)
 		__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
 
 	local_irq_enable();
-	preempt_check_resched_rt();
 }
 
 /**
@@ -206,7 +204,6 @@ static int blk_iopoll_cpu_notify(struct notifier_block *self,
 				 &__get_cpu_var(blk_cpu_iopoll));
 		__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
 		local_irq_enable();
-		preempt_check_resched_rt();
 	}
 
 	return NOTIFY_OK;
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 5330933..ec00a0f 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -553,7 +553,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 		bottom = max(b->physical_block_size, b->io_min) + alignment;
 
 		/* Verify that top and bottom intervals line up */
-		if (max(top, bottom) & (min(top, bottom) - 1)) {
+		if (max(top, bottom) % min(top, bottom)) {
 			t->misaligned = 1;
 			ret = -1;
 		}
@@ -594,7 +594,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
 	/* Find lowest common alignment_offset */
 	t->alignment_offset = lcm(t->alignment_offset, alignment)
-		& (max(t->physical_block_size, t->io_min) - 1);
+		% max(t->physical_block_size, t->io_min);
 
 	/* Verify that new alignment_offset is on a logical block boundary */
 	if (t->alignment_offset & (t->logical_block_size - 1)) {
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 814b3db..ec9e606 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -51,7 +51,6 @@ static void trigger_softirq(void *data)
 		raise_softirq_irqoff(BLOCK_SOFTIRQ);
 
 	local_irq_restore(flags);
-	preempt_check_resched_rt();
 }
 
 /*
@@ -94,7 +93,6 @@ static int blk_cpu_notify(struct notifier_block *self, unsigned long action,
 				 &__get_cpu_var(blk_cpu_done));
 		raise_softirq_irqoff(BLOCK_SOFTIRQ);
 		local_irq_enable();
-		preempt_check_resched_rt();
 	}
 
 	return NOTIFY_OK;
@@ -152,7 +150,6 @@ do_local:
 		goto do_local;
 
 	local_irq_restore(flags);
-	preempt_check_resched_rt();
 }
 
 /**
diff --git a/block/blk-tag.c b/block/blk-tag.c
index 3f33d86..a185b86 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -27,18 +27,15 @@ struct request *blk_queue_find_tag(struct request_queue *q, int tag)
 EXPORT_SYMBOL(blk_queue_find_tag);
 
 /**
- * __blk_free_tags - release a given set of tag maintenance info
+ * blk_free_tags - release a given set of tag maintenance info
  * @bqt:	the tag map to free
  *
- * Tries to free the specified @bqt.  Returns true if it was
- * actually freed and false if there are still references using it
+ * Drop the reference count on @bqt and frees it when the last reference
+ * is dropped.
  */
-static int __blk_free_tags(struct blk_queue_tag *bqt)
+void blk_free_tags(struct blk_queue_tag *bqt)
 {
-	int retval;
-
-	retval = atomic_dec_and_test(&bqt->refcnt);
-	if (retval) {
+	if (atomic_dec_and_test(&bqt->refcnt)) {
 		BUG_ON(find_first_bit(bqt->tag_map, bqt->max_depth) <
 							bqt->max_depth);
 
@@ -50,9 +47,8 @@ static int __blk_free_tags(struct blk_queue_tag *bqt)
 
 		kfree(bqt);
 	}
-
-	return retval;
 }
+EXPORT_SYMBOL(blk_free_tags);
 
 /**
  * __blk_queue_free_tags - release tag maintenance info
@@ -69,28 +65,13 @@ void __blk_queue_free_tags(struct request_queue *q)
 	if (!bqt)
 		return;
 
-	__blk_free_tags(bqt);
+	blk_free_tags(bqt);
 
 	q->queue_tags = NULL;
 	queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q);
 }
 
 /**
- * blk_free_tags - release a given set of tag maintenance info
- * @bqt:	the tag map to free
- *
- * For externally managed @bqt frees the map.  Callers of this
- * function must guarantee to have released all the queues that
- * might have been using this tag map.
- */
-void blk_free_tags(struct blk_queue_tag *bqt)
-{
-	if (unlikely(!__blk_free_tags(bqt)))
-		BUG();
-}
-EXPORT_SYMBOL(blk_free_tags);
-
-/**
  * blk_queue_free_tags - release tag maintenance info
  * @q:  the request queue for the device
  *
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 434944c..06c2bab 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1275,12 +1275,16 @@ __cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 static void
 cfq_update_group_weight(struct cfq_group *cfqg)
 {
-	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
-
 	if (cfqg->new_weight) {
 		cfqg->weight = cfqg->new_weight;
 		cfqg->new_weight = 0;
 	}
+}
+
+static void
+cfq_update_group_leaf_weight(struct cfq_group *cfqg)
+{
+	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
 
 	if (cfqg->new_leaf_weight) {
 		cfqg->leaf_weight = cfqg->new_leaf_weight;
@@ -1299,7 +1303,7 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 	/* add to the service tree */
 	BUG_ON(!RB_EMPTY_NODE(&cfqg->rb_node));
 
-	cfq_update_group_weight(cfqg);
+	cfq_update_group_leaf_weight(cfqg);
 	__cfq_group_service_tree_add(st, cfqg);
 
 	/*
@@ -1323,6 +1327,7 @@ cfq_group_service_tree_add(struct cfq_rb_root *st, struct cfq_group *cfqg)
 	 */
 	while ((parent = cfqg_parent(pos))) {
 		if (propagate) {
+			cfq_update_group_weight(pos);
 			propagate = !parent->nr_active++;
 			parent->children_weight += pos->weight;
 		}
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index fbd5a67..a0926a6 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -690,6 +690,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKROSET:
 	case BLKDISCARD:
 	case BLKSECDISCARD:
+	case BLKZEROOUT:
 	/*
 	 * the ones below are implemented in blkdev_locked_ioctl,
 	 * but we call blkdev_ioctl, which gets the lock for us
diff --git a/block/genhd.c b/block/genhd.c
index 791f419..a8d586a 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -28,10 +28,10 @@ struct kobject *block_depr;
 /* for extended dynamic devt allocation, currently only one major is used */
 #define NR_EXT_DEVT		(1 << MINORBITS)
 
-/* For extended devt allocation.  ext_devt_mutex prevents look up
+/* For extended devt allocation.  ext_devt_lock prevents look up
  * results from going away underneath its user.
  */
-static DEFINE_MUTEX(ext_devt_mutex);
+static DEFINE_SPINLOCK(ext_devt_lock);
 static DEFINE_IDR(ext_devt_idr);
 
 static struct device_type disk_type;
@@ -420,9 +420,13 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
 	}
 
 	/* allocate ext devt */
-	mutex_lock(&ext_devt_mutex);
-	idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_KERNEL);
-	mutex_unlock(&ext_devt_mutex);
+	idr_preload(GFP_KERNEL);
+
+	spin_lock(&ext_devt_lock);
+	idx = idr_alloc(&ext_devt_idr, part, 0, NR_EXT_DEVT, GFP_NOWAIT);
+	spin_unlock(&ext_devt_lock);
+
+	idr_preload_end();
 	if (idx < 0)
 		return idx == -ENOSPC ? -EBUSY : idx;
 
@@ -441,15 +445,13 @@ int blk_alloc_devt(struct hd_struct *part, dev_t *devt)
  */
 void blk_free_devt(dev_t devt)
 {
-	might_sleep();
-
 	if (devt == MKDEV(0, 0))
 		return;
 
 	if (MAJOR(devt) == BLOCK_EXT_MAJOR) {
-		mutex_lock(&ext_devt_mutex);
+		spin_lock(&ext_devt_lock);
 		idr_remove(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
-		mutex_unlock(&ext_devt_mutex);
+		spin_unlock(&ext_devt_lock);
 	}
 }
 
@@ -665,7 +667,6 @@ void del_gendisk(struct gendisk *disk)
 		sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
 	pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
 	device_del(disk_to_dev(disk));
-	blk_free_devt(disk_to_dev(disk)->devt);
 }
 EXPORT_SYMBOL(del_gendisk);
 
@@ -690,13 +691,13 @@ struct gendisk *get_gendisk(dev_t devt, int *partno)
 	} else {
 		struct hd_struct *part;
 
-		mutex_lock(&ext_devt_mutex);
+		spin_lock(&ext_devt_lock);
 		part = idr_find(&ext_devt_idr, blk_mangle_minor(MINOR(devt)));
 		if (part && get_disk(part_to_disk(part))) {
 			*partno = part->partno;
 			disk = part_to_disk(part);
 		}
-		mutex_unlock(&ext_devt_mutex);
+		spin_unlock(&ext_devt_lock);
 	}
 
 	return disk;
@@ -1069,9 +1070,16 @@ int disk_expand_part_tbl(struct gendisk *disk, int partno)
 	struct disk_part_tbl *old_ptbl = disk->part_tbl;
 	struct disk_part_tbl *new_ptbl;
 	int len = old_ptbl ? old_ptbl->len : 0;
-	int target = partno + 1;
+	int i, target;
 	size_t size;
-	int i;
+
+	/*
+	 * check for int overflow, since we can get here from blkpg_ioctl()
+	 * with a user passed 'partno'.
+	 */
+	target = partno + 1;
+	if (target < 0)
+		return -EINVAL;
 
 	/* disk_max_parts() is zero during initialization, ignore if so */
 	if (disk_max_parts(disk) && target > disk_max_parts(disk))
@@ -1098,6 +1106,7 @@ static void disk_release(struct device *dev)
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
+	blk_free_devt(dev->devt);
 	disk_release_events(disk);
 	kfree(disk->random);
 	disk_replace_part_tbl(disk, NULL);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 789cdea..0d9e5f9 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -211,6 +211,7 @@ static const struct attribute_group *part_attr_groups[] = {
 static void part_release(struct device *dev)
 {
 	struct hd_struct *p = dev_to_part(dev);
+	blk_free_devt(dev->devt);
 	free_part_stats(p);
 	free_part_info(p);
 	kfree(p);
@@ -253,7 +254,6 @@ void delete_partition(struct gendisk *disk, int partno)
 	rcu_assign_pointer(ptbl->last_lookup, NULL);
 	kobject_put(part->holder_dir);
 	device_del(part_to_dev(part));
-	blk_free_devt(part_devt(part));
 
 	hd_struct_put(part);
 }
diff --git a/block/partitions/aix.c b/block/partitions/aix.c
index 43be471..0931f51 100644
--- a/block/partitions/aix.c
+++ b/block/partitions/aix.c
@@ -253,7 +253,7 @@ int aix_partition(struct parsed_partitions *state)
 				continue;
 			}
 			lv_ix = be16_to_cpu(p->lv_ix) - 1;
-			if (lv_ix > state->limit) {
+			if (lv_ix >= state->limit) {
 				cur_lv_ix = -1;
 				continue;
 			}
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index a5ffcc9..1b4988b 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -506,7 +506,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 
 	if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_WAIT)) {
 		err = DRIVER_ERROR << 24;
-		goto out;
+		goto error;
 	}
 
 	memset(sense, 0, sizeof(sense));
@@ -516,7 +516,6 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 
 	blk_execute_rq(q, disk, rq, 0);
 
-out:
 	err = rq->errors & 0xff;	/* only 8 bit SCSI status */
 	if (err) {
 		if (rq->sense_len && rq->sense) {