Merge branch 'for-3.6/core' of git://git.kernel.dk/linux-block

Pull core block IO bits from Jens Axboe:
 "The most complicated part if this is the request allocation rework by
  Tejun, which has been queued up for a long time and has been in
  for-next ditto as well.

  There are a few commits from yesterday and today, mostly trivial and
  obvious fixes.  So I'm pretty confident that it is sound.  It's also
  smaller than usual."

* 'for-3.6/core' of git://git.kernel.dk/linux-block:
  block: remove dead func declaration
  block: add partition resize function to blkpg ioctl
  block: uninitialized ioc->nr_tasks triggers WARN_ON
  block: do not artificially constrain max_sectors for stacking drivers
  blkcg: implement per-blkg request allocation
  block: prepare for multiple request_lists
  block: add q->nr_rqs[] and move q->rq.elvpriv to q->nr_rqs_elvpriv
  blkcg: inline bio_blkcg() and friends
  block: allocate io_context upfront
  block: refactor get_request[_wait]()
  block: drop custom queue draining used by scsi_transport_{iscsi|fc}
  mempool: add @gfp_mask to mempool_create_node()
  blkcg: make root blkcg allocation use %GFP_KERNEL
  blkcg: __blkg_lookup_create() doesn't need radix preload

Documentation/block/queue-sysfs.txt

@@ -38,6 +38,13 @@ read or write requests. Note that the total allocated number may be twice
 this amount, since it applies only to reads or writes (not the accumulated
 sum).
 
+To avoid priority inversion through request starvation, a request
+queue maintains a separate request pool per each cgroup when
+CONFIG_BLK_CGROUP is enabled, and this parameter applies to each such
+per-block-cgroup request pool.  IOW, if there are N block cgroups,
+each request queue may have upto N request pools, each independently
+regulated by nr_requests.
+
 read_ahead_kb (RW)
 ------------------
 Maximum number of kilobytes to read-ahead for filesystems on this block

block/blk-cgroup.c

@@ -31,27 +31,6 @@ EXPORT_SYMBOL_GPL(blkcg_root);
 
 static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
 
-struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup)
-{
-	return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),
-			    struct blkcg, css);
-}
-EXPORT_SYMBOL_GPL(cgroup_to_blkcg);
-
-static struct blkcg *task_blkcg(struct task_struct *tsk)
-{
-	return container_of(task_subsys_state(tsk, blkio_subsys_id),
-			    struct blkcg, css);
-}
-
-struct blkcg *bio_blkcg(struct bio *bio)
-{
-	if (bio && bio->bi_css)
-		return container_of(bio->bi_css, struct blkcg, css);
-	return task_blkcg(current);
-}
-EXPORT_SYMBOL_GPL(bio_blkcg);
-
 static bool blkcg_policy_enabled(struct request_queue *q,
 				 const struct blkcg_policy *pol)
 {
@@ -84,6 +63,7 @@ static void blkg_free(struct blkcg_gq *blkg)
 		kfree(pd);
 	}
 
+	blk_exit_rl(&blkg->rl);
 	kfree(blkg);
 }
 
@@ -91,16 +71,18 @@ static void blkg_free(struct blkcg_gq *blkg)
  * blkg_alloc - allocate a blkg
  * @blkcg: block cgroup the new blkg is associated with
  * @q: request_queue the new blkg is associated with
+ * @gfp_mask: allocation mask to use
  *
  * Allocate a new blkg assocating @blkcg and @q.
  */
-static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q)
+static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q,
+				   gfp_t gfp_mask)
 {
 	struct blkcg_gq *blkg;
 	int i;
 
 	/* alloc and init base part */
-	blkg = kzalloc_node(sizeof(*blkg), GFP_ATOMIC, q->node);
+	blkg = kzalloc_node(sizeof(*blkg), gfp_mask, q->node);
 	if (!blkg)
 		return NULL;
 
@@ -109,6 +91,13 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q)
 	blkg->blkcg = blkcg;
 	blkg->refcnt = 1;
 
+	/* root blkg uses @q->root_rl, init rl only for !root blkgs */
+	if (blkcg != &blkcg_root) {
+		if (blk_init_rl(&blkg->rl, q, gfp_mask))
+			goto err_free;
+		blkg->rl.blkg = blkg;
+	}
+
 	for (i = 0; i < BLKCG_MAX_POLS; i++) {
 		struct blkcg_policy *pol = blkcg_policy[i];
 		struct blkg_policy_data *pd;
@@ -117,11 +106,9 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q)
 			continue;
 
 		/* alloc per-policy data and attach it to blkg */
-		pd = kzalloc_node(pol->pd_size, GFP_ATOMIC, q->node);
-		if (!pd) {
-			blkg_free(blkg);
-			return NULL;
-		}
+		pd = kzalloc_node(pol->pd_size, gfp_mask, q->node);
+		if (!pd)
+			goto err_free;
 
 		blkg->pd[i] = pd;
 		pd->blkg = blkg;
@@ -132,6 +119,10 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q)
 	}
 
 	return blkg;
+
+err_free:
+	blkg_free(blkg);
+	return NULL;
 }
 
 static struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg,
@@ -175,9 +166,13 @@ struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blkg_lookup);
 
+/*
+ * If @new_blkg is %NULL, this function tries to allocate a new one as
+ * necessary using %GFP_ATOMIC.  @new_blkg is always consumed on return.
+ */
 static struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg,
-					     struct request_queue *q)
-	__releases(q->queue_lock) __acquires(q->queue_lock)
+					     struct request_queue *q,
+					     struct blkcg_gq *new_blkg)
 {
 	struct blkcg_gq *blkg;
 	int ret;
@@ -189,24 +184,26 @@ static struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg,
 	blkg = __blkg_lookup(blkcg, q);
 	if (blkg) {
 		rcu_assign_pointer(blkcg->blkg_hint, blkg);
-		return blkg;
+		goto out_free;
 	}
 
 	/* blkg holds a reference to blkcg */
-	if (!css_tryget(&blkcg->css))
-		return ERR_PTR(-EINVAL);
+	if (!css_tryget(&blkcg->css)) {
+		blkg = ERR_PTR(-EINVAL);
+		goto out_free;
+	}
 
 	/* allocate */
-	ret = -ENOMEM;
-	blkg = blkg_alloc(blkcg, q);
-	if (unlikely(!blkg))
-		goto err_put;
+	if (!new_blkg) {
+		new_blkg = blkg_alloc(blkcg, q, GFP_ATOMIC);
+		if (unlikely(!new_blkg)) {
+			blkg = ERR_PTR(-ENOMEM);
+			goto out_put;
+		}
+	}
+	blkg = new_blkg;
 
 	/* insert */
-	ret = radix_tree_preload(GFP_ATOMIC);
-	if (ret)
-		goto err_free;
-
 	spin_lock(&blkcg->lock);
 	ret = radix_tree_insert(&blkcg->blkg_tree, q->id, blkg);
 	if (likely(!ret)) {
@@ -215,15 +212,15 @@ static struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg,
 	}
 	spin_unlock(&blkcg->lock);
 
-	radix_tree_preload_end();
-
 	if (!ret)
 		return blkg;
-err_free:
-	blkg_free(blkg);
-err_put:
+
+	blkg = ERR_PTR(ret);
+out_put:
 	css_put(&blkcg->css);
-	return ERR_PTR(ret);
+out_free:
+	blkg_free(new_blkg);
+	return blkg;
 }
 
 struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
@@ -235,7 +232,7 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
 	 */
 	if (unlikely(blk_queue_bypass(q)))
 		return ERR_PTR(blk_queue_dead(q) ? -EINVAL : -EBUSY);
-	return __blkg_lookup_create(blkcg, q);
+	return __blkg_lookup_create(blkcg, q, NULL);
 }
 EXPORT_SYMBOL_GPL(blkg_lookup_create);
 
@@ -313,6 +310,38 @@ void __blkg_release(struct blkcg_gq *blkg)
 }
 EXPORT_SYMBOL_GPL(__blkg_release);
 
+/*
+ * The next function used by blk_queue_for_each_rl().  It's a bit tricky
+ * because the root blkg uses @q->root_rl instead of its own rl.
+ */
+struct request_list *__blk_queue_next_rl(struct request_list *rl,
+					 struct request_queue *q)
+{
+	struct list_head *ent;
+	struct blkcg_gq *blkg;
+
+	/*
+	 * Determine the current blkg list_head.  The first entry is
+	 * root_rl which is off @q->blkg_list and mapped to the head.
+	 */
+	if (rl == &q->root_rl) {
+		ent = &q->blkg_list;
+	} else {
+		blkg = container_of(rl, struct blkcg_gq, rl);
+		ent = &blkg->q_node;
+	}
+
+	/* walk to the next list_head, skip root blkcg */
+	ent = ent->next;
+	if (ent == &q->root_blkg->q_node)
+		ent = ent->next;
+	if (ent == &q->blkg_list)
+		return NULL;
+
+	blkg = container_of(ent, struct blkcg_gq, q_node);
+	return &blkg->rl;
+}
+
 static int blkcg_reset_stats(struct cgroup *cgroup, struct cftype *cftype,
 			     u64 val)
 {
@@ -734,24 +763,36 @@ int blkcg_activate_policy(struct request_queue *q,
 	struct blkcg_gq *blkg;
 	struct blkg_policy_data *pd, *n;
 	int cnt = 0, ret;
+	bool preloaded;
 
 	if (blkcg_policy_enabled(q, pol))
 		return 0;
 
+	/* preallocations for root blkg */
+	blkg = blkg_alloc(&blkcg_root, q, GFP_KERNEL);
+	if (!blkg)
+		return -ENOMEM;
+
+	preloaded = !radix_tree_preload(GFP_KERNEL);
+
 	blk_queue_bypass_start(q);
 
 	/* make sure the root blkg exists and count the existing blkgs */
 	spin_lock_irq(q->queue_lock);
 
 	rcu_read_lock();
-	blkg = __blkg_lookup_create(&blkcg_root, q);
+	blkg = __blkg_lookup_create(&blkcg_root, q, blkg);
 	rcu_read_unlock();
 
+	if (preloaded)
+		radix_tree_preload_end();
+
 	if (IS_ERR(blkg)) {
 		ret = PTR_ERR(blkg);
 		goto out_unlock;
 	}
 	q->root_blkg = blkg;
+	q->root_rl.blkg = blkg;
 
 	list_for_each_entry(blkg, &q->blkg_list, q_node)
 		cnt++;

block/blk-cgroup.h

@@ -17,6 +17,7 @@
 #include <linux/u64_stats_sync.h>
 #include <linux/seq_file.h>
 #include <linux/radix-tree.h>
+#include <linux/blkdev.h>
 
 /* Max limits for throttle policy */
 #define THROTL_IOPS_MAX		UINT_MAX
@@ -93,6 +94,8 @@ struct blkcg_gq {
 	struct list_head		q_node;
 	struct hlist_node		blkcg_node;
 	struct blkcg			*blkcg;
+	/* request allocation list for this blkcg-q pair */
+	struct request_list		rl;
 	/* reference count */
 	int				refcnt;
 
@@ -120,8 +123,6 @@ struct blkcg_policy {
 
 extern struct blkcg blkcg_root;
 
-struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup);
-struct blkcg *bio_blkcg(struct bio *bio);
 struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q);
 struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg,
 				    struct request_queue *q);
@@ -160,6 +161,25 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 void blkg_conf_finish(struct blkg_conf_ctx *ctx);
 
 
+static inline struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup)
+{
+	return container_of(cgroup_subsys_state(cgroup, blkio_subsys_id),
+			    struct blkcg, css);
+}
+
+static inline struct blkcg *task_blkcg(struct task_struct *tsk)
+{
+	return container_of(task_subsys_state(tsk, blkio_subsys_id),
+			    struct blkcg, css);
+}
+
+static inline struct blkcg *bio_blkcg(struct bio *bio)
+{
+	if (bio && bio->bi_css)
+		return container_of(bio->bi_css, struct blkcg, css);
+	return task_blkcg(current);
+}
+
 /**
  * blkg_to_pdata - get policy private data
  * @blkg: blkg of interest
@@ -233,6 +253,95 @@ static inline void blkg_put(struct blkcg_gq *blkg)
 		__blkg_release(blkg);
 }
 
+/**
+ * blk_get_rl - get request_list to use
+ * @q: request_queue of interest
+ * @bio: bio which will be attached to the allocated request (may be %NULL)
+ *
+ * The caller wants to allocate a request from @q to use for @bio.  Find
+ * the request_list to use and obtain a reference on it.  Should be called
+ * under queue_lock.  This function is guaranteed to return non-%NULL
+ * request_list.
+ */
+static inline struct request_list *blk_get_rl(struct request_queue *q,
+					      struct bio *bio)
+{
+	struct blkcg *blkcg;
+	struct blkcg_gq *blkg;
+
+	rcu_read_lock();
+
+	blkcg = bio_blkcg(bio);
+
+	/* bypass blkg lookup and use @q->root_rl directly for root */
+	if (blkcg == &blkcg_root)
+		goto root_rl;
+
+	/*
+	 * Try to use blkg->rl.  blkg lookup may fail under memory pressure
+	 * or if either the blkcg or queue is going away.  Fall back to
+	 * root_rl in such cases.
+	 */
+	blkg = blkg_lookup_create(blkcg, q);
+	if (unlikely(IS_ERR(blkg)))
+		goto root_rl;
+
+	blkg_get(blkg);
+	rcu_read_unlock();
+	return &blkg->rl;
+root_rl:
+	rcu_read_unlock();
+	return &q->root_rl;
+}
+
+/**
+ * blk_put_rl - put request_list
+ * @rl: request_list to put
+ *
+ * Put the reference acquired by blk_get_rl().  Should be called under
+ * queue_lock.
+ */
+static inline void blk_put_rl(struct request_list *rl)
+{
+	/* root_rl may not have blkg set */
+	if (rl->blkg && rl->blkg->blkcg != &blkcg_root)
+		blkg_put(rl->blkg);
+}
+
+/**
+ * blk_rq_set_rl - associate a request with a request_list
+ * @rq: request of interest
+ * @rl: target request_list
+ *
+ * Associate @rq with @rl so that accounting and freeing can know the
+ * request_list @rq came from.
+ */
+static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl)
+{
+	rq->rl = rl;
+}
+
+/**
+ * blk_rq_rl - return the request_list a request came from
+ * @rq: request of interest
+ *
+ * Return the request_list @rq is allocated from.
+ */
+static inline struct request_list *blk_rq_rl(struct request *rq)
+{
+	return rq->rl;
+}
+
+struct request_list *__blk_queue_next_rl(struct request_list *rl,
+					 struct request_queue *q);
+/**
+ * blk_queue_for_each_rl - iterate through all request_lists of a request_queue
+ *
+ * Should be used under queue_lock.
+ */
+#define blk_queue_for_each_rl(rl, q)	\
+	for ((rl) = &(q)->root_rl; (rl); (rl) = __blk_queue_next_rl((rl), (q)))
+
 /**
  * blkg_stat_add - add a value to a blkg_stat
  * @stat: target blkg_stat
@@ -351,6 +460,7 @@ static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat)
 #else	/* CONFIG_BLK_CGROUP */
 
 struct cgroup;
+struct blkcg;
 
 struct blkg_policy_data {
 };
@@ -361,8 +471,6 @@ struct blkcg_gq {
 struct blkcg_policy {
 };
 
-static inline struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup) { return NULL; }
-static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; }
 static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
 static inline int blkcg_init_queue(struct request_queue *q) { return 0; }
 static inline void blkcg_drain_queue(struct request_queue *q) { }
@@ -374,6 +482,9 @@ static inline int blkcg_activate_policy(struct request_queue *q,
 static inline void blkcg_deactivate_policy(struct request_queue *q,
 					   const struct blkcg_policy *pol) { }
 
+static inline struct blkcg *cgroup_to_blkcg(struct cgroup *cgroup) { return NULL; }
+static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; }
+
 static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg,
 						  struct blkcg_policy *pol) { return NULL; }
 static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) { return NULL; }
@@ -381,5 +492,14 @@ static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; }
 static inline void blkg_get(struct blkcg_gq *blkg) { }
 static inline void blkg_put(struct blkcg_gq *blkg) { }
 
+static inline struct request_list *blk_get_rl(struct request_queue *q,
+					      struct bio *bio) { return &q->root_rl; }
+static inline void blk_put_rl(struct request_list *rl) { }
+static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) { }
+static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q->root_rl; }
+
+#define blk_queue_for_each_rl(rl, q)	\
+	for ((rl) = &(q)->root_rl; (rl); (rl) = NULL)
+
 #endif	/* CONFIG_BLK_CGROUP */
 #endif	/* _BLK_CGROUP_H */

block/blk-ioc.c

@@ -244,6 +244,7 @@ int create_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node)
 
 	/* initialize */
 	atomic_long_set(&ioc->refcount, 1);
+	atomic_set(&ioc->nr_tasks, 1);
 	atomic_set(&ioc->active_ref, 1);
 	spin_lock_init(&ioc->lock);
 	INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC | __GFP_HIGH);

block/blk-settings.c

@@ -143,8 +143,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	lim->discard_zeroes_data = 1;
 	lim->max_segments = USHRT_MAX;
 	lim->max_hw_sectors = UINT_MAX;
-
-	lim->max_sectors = BLK_DEF_MAX_SECTORS;
+	lim->max_sectors = UINT_MAX;
 }
 EXPORT_SYMBOL(blk_set_stacking_limits);
 

block/blk-sysfs.c

@@ -40,7 +40,7 @@ static ssize_t queue_requests_show(struct request_queue *q, char *page)
 static ssize_t
 queue_requests_store(struct request_queue *q, const char *page, size_t count)
 {
-	struct request_list *rl = &q->rq;
+	struct request_list *rl;
 	unsigned long nr;
 	int ret;
 
@@ -55,6 +55,9 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count)
 	q->nr_requests = nr;
 	blk_queue_congestion_threshold(q);
 
+	/* congestion isn't cgroup aware and follows root blkcg for now */
+	rl = &q->root_rl;
+
 	if (rl->count[BLK_RW_SYNC] >= queue_congestion_on_threshold(q))
 		blk_set_queue_congested(q, BLK_RW_SYNC);
 	else if (rl->count[BLK_RW_SYNC] < queue_congestion_off_threshold(q))
@@ -65,19 +68,22 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count)
 	else if (rl->count[BLK_RW_ASYNC] < queue_congestion_off_threshold(q))
 		blk_clear_queue_congested(q, BLK_RW_ASYNC);
 
-	if (rl->count[BLK_RW_SYNC] >= q->nr_requests) {
-		blk_set_queue_full(q, BLK_RW_SYNC);
-	} else {
-		blk_clear_queue_full(q, BLK_RW_SYNC);
-		wake_up(&rl->wait[BLK_RW_SYNC]);
+	blk_queue_for_each_rl(rl, q) {
+		if (rl->count[BLK_RW_SYNC] >= q->nr_requests) {
+			blk_set_rl_full(rl, BLK_RW_SYNC);
+		} else {
+			blk_clear_rl_full(rl, BLK_RW_SYNC);
+			wake_up(&rl->wait[BLK_RW_SYNC]);
+		}
+
+		if (rl->count[BLK_RW_ASYNC] >= q->nr_requests) {
+			blk_set_rl_full(rl, BLK_RW_ASYNC);
+		} else {
+			blk_clear_rl_full(rl, BLK_RW_ASYNC);
+			wake_up(&rl->wait[BLK_RW_ASYNC]);
+		}
 	}
 
-	if (rl->count[BLK_RW_ASYNC] >= q->nr_requests) {
-		blk_set_queue_full(q, BLK_RW_ASYNC);
-	} else {
-		blk_clear_queue_full(q, BLK_RW_ASYNC);
-		wake_up(&rl->wait[BLK_RW_ASYNC]);
-	}
 	spin_unlock_irq(q->queue_lock);
 	return ret;
 }
@@ -476,7 +482,6 @@ static void blk_release_queue(struct kobject *kobj)
 {
 	struct request_queue *q =
 		container_of(kobj, struct request_queue, kobj);
-	struct request_list *rl = &q->rq;
 
 	blk_sync_queue(q);
 
@@ -489,8 +494,7 @@ static void blk_release_queue(struct kobject *kobj)
 		elevator_exit(q->elevator);
 	}
 
-	if (rl->rq_pool)
-		mempool_destroy(rl->rq_pool);
+	blk_exit_rl(&q->root_rl);
 
 	if (q->queue_tags)
 		__blk_queue_free_tags(q);

block/blk-throttle.c

@@ -1123,9 +1123,6 @@ bool blk_throtl_bio(struct request_queue *q, struct bio *bio)
 		goto out;
 	}
 
-	/* bio_associate_current() needs ioc, try creating */
-	create_io_context(GFP_ATOMIC, q->node);
-
 	/*
 	 * A throtl_grp pointer retrieved under rcu can be used to access
 	 * basic fields like stats and io rates. If a group has no rules,

block/blk.h

@@ -18,6 +18,9 @@ static inline void __blk_get_queue(struct request_queue *q)
 	kobject_get(&q->kobj);
 }
 
+int blk_init_rl(struct request_list *rl, struct request_queue *q,
+		gfp_t gfp_mask);
+void blk_exit_rl(struct request_list *rl);
 void init_request_from_bio(struct request *req, struct bio *bio);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 			struct bio *bio);
@@ -33,7 +36,6 @@ bool __blk_end_bidi_request(struct request *rq, int error,
 void blk_rq_timed_out_timer(unsigned long data);
 void blk_delete_timer(struct request *);
 void blk_add_timer(struct request *);
-void __generic_unplug_device(struct request_queue *);
 
 /*
  * Internal atomic flags for request handling

block/bsg-lib.c

@@ -243,56 +243,3 @@ int bsg_setup_queue(struct device *dev, struct request_queue *q,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(bsg_setup_queue);
-
-/**
- * bsg_remove_queue - Deletes the bsg dev from the q
- * @q:	the request_queue that is to be torn down.
- *
- * Notes:
- *   Before unregistering the queue empty any requests that are blocked
- */
-void bsg_remove_queue(struct request_queue *q)
-{
-	struct request *req; /* block request */
-	int counts; /* totals for request_list count and starved */
-
-	if (!q)
-		return;
-
-	/* Stop taking in new requests */
-	spin_lock_irq(q->queue_lock);
-	blk_stop_queue(q);
-
-	/* drain all requests in the queue */
-	while (1) {
-		/* need the lock to fetch a request
-		 * this may fetch the same reqeust as the previous pass
-		 */
-		req = blk_fetch_request(q);
-		/* save requests in use and starved */
-		counts = q->rq.count[0] + q->rq.count[1] +
-			 q->rq.starved[0] + q->rq.starved[1];
-		spin_unlock_irq(q->queue_lock);
-		/* any requests still outstanding? */
-		if (counts == 0)
-			break;
-
-		/* This may be the same req as the previous iteration,
-		 * always send the blk_end_request_all after a prefetch.
-		 * It is not okay to not end the request because the
-		 * prefetch started the request.
-		 */
-		if (req) {
-			/* return -ENXIO to indicate that this queue is
-			 * going away
-			 */
-			req->errors = -ENXIO;
-			blk_end_request_all(req, -ENXIO);
-		}
-
-		msleep(200); /* allow bsg to possibly finish */
-		spin_lock_irq(q->queue_lock);
-	}
-	bsg_unregister_queue(q);
-}
-EXPORT_SYMBOL_GPL(bsg_remove_queue);

block/genhd.c

@@ -154,7 +154,7 @@ struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
 		part = rcu_dereference(ptbl->part[piter->idx]);
 		if (!part)
 			continue;
-		if (!part->nr_sects &&
+		if (!part_nr_sects_read(part) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
 		      piter->idx == 0))
@@ -191,7 +191,7 @@ EXPORT_SYMBOL_GPL(disk_part_iter_exit);
 static inline int sector_in_part(struct hd_struct *part, sector_t sector)
 {
 	return part->start_sect <= sector &&
-		sector < part->start_sect + part->nr_sects;
+		sector < part->start_sect + part_nr_sects_read(part);
 }
 
 /**
@@ -769,8 +769,8 @@ void __init printk_all_partitions(void)
 
 			printk("%s%s %10llu %s %s", is_part0 ? "" : "  ",
 			       bdevt_str(part_devt(part), devt_buf),
-			       (unsigned long long)part->nr_sects >> 1,
-			       disk_name(disk, part->partno, name_buf),
+			       (unsigned long long)part_nr_sects_read(part) >> 1
+			       , disk_name(disk, part->partno, name_buf),
 			       uuid_buf);
 			if (is_part0) {
 				if (disk->driverfs_dev != NULL &&
@@ -862,7 +862,7 @@ static int show_partition(struct seq_file *seqf, void *v)
 	while ((part = disk_part_iter_next(&piter)))
 		seq_printf(seqf, "%4d  %7d %10llu %s\n",
 			   MAJOR(part_devt(part)), MINOR(part_devt(part)),
-			   (unsigned long long)part->nr_sects >> 1,
+			   (unsigned long long)part_nr_sects_read(part) >> 1,
 			   disk_name(sgp, part->partno, buf));
 	disk_part_iter_exit(&piter);
 
@@ -1268,6 +1268,16 @@ struct gendisk *alloc_disk_node(int minors, int node_id)
 		}
 		disk->part_tbl->part[0] = &disk->part0;
 
+		/*
+		 * set_capacity() and get_capacity() currently don't use
+		 * seqcounter to read/update the part0->nr_sects. Still init
+		 * the counter as we can read the sectors in IO submission
+		 * patch using seqence counters.
+		 *
+		 * TODO: Ideally set_capacity() and get_capacity() should be
+		 * converted to make use of bd_mutex and sequence counters.
+		 */
+		seqcount_init(&disk->part0.nr_sects_seq);
 		hd_ref_init(&disk->part0);
 
 		disk->minors = minors;

block/ioctl.c

@@ -13,7 +13,7 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
 {
 	struct block_device *bdevp;
 	struct gendisk *disk;
-	struct hd_struct *part;
+	struct hd_struct *part, *lpart;
 	struct blkpg_ioctl_arg a;
 	struct blkpg_partition p;
 	struct disk_part_iter piter;
@@ -36,8 +36,8 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
 		case BLKPG_ADD_PARTITION:
 			start = p.start >> 9;
 			length = p.length >> 9;
-			/* check for fit in a hd_struct */ 
-			if (sizeof(sector_t) == sizeof(long) && 
+			/* check for fit in a hd_struct */
+			if (sizeof(sector_t) == sizeof(long) &&
 			    sizeof(long long) > sizeof(long)) {
 				long pstart = start, plength = length;
 				if (pstart != start || plength != length
@@ -91,6 +91,59 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
 			mutex_unlock(&bdevp->bd_mutex);
 			bdput(bdevp);
 
+			return 0;
+		case BLKPG_RESIZE_PARTITION:
+			start = p.start >> 9;
+			/* new length of partition in bytes */
+			length = p.length >> 9;
+			/* check for fit in a hd_struct */
+			if (sizeof(sector_t) == sizeof(long) &&
+			    sizeof(long long) > sizeof(long)) {
+				long pstart = start, plength = length;
+				if (pstart != start || plength != length
+				    || pstart < 0 || plength < 0)
+					return -EINVAL;
+			}
+			part = disk_get_part(disk, partno);
+			if (!part)
+				return -ENXIO;
+			bdevp = bdget(part_devt(part));
+			if (!bdevp) {
+				disk_put_part(part);
+				return -ENOMEM;
+			}
+			mutex_lock(&bdevp->bd_mutex);
+			mutex_lock_nested(&bdev->bd_mutex, 1);
+			if (start != part->start_sect) {
+				mutex_unlock(&bdevp->bd_mutex);
+				mutex_unlock(&bdev->bd_mutex);
+				bdput(bdevp);
+				disk_put_part(part);
+				return -EINVAL;
+			}
+			/* overlap? */
+			disk_part_iter_init(&piter, disk,
+					    DISK_PITER_INCL_EMPTY);
+			while ((lpart = disk_part_iter_next(&piter))) {
+				if (lpart->partno != partno &&
+				   !(start + length <= lpart->start_sect ||
+				   start >= lpart->start_sect + lpart->nr_sects)
+				   ) {
+					disk_part_iter_exit(&piter);
+					mutex_unlock(&bdevp->bd_mutex);
+					mutex_unlock(&bdev->bd_mutex);
+					bdput(bdevp);
+					disk_put_part(part);
+					return -EBUSY;
+				}
+			}
+			disk_part_iter_exit(&piter);
+			part_nr_sects_write(part, (sector_t)length);
+			i_size_write(bdevp->bd_inode, p.length);
+			mutex_unlock(&bdevp->bd_mutex);
+			mutex_unlock(&bdev->bd_mutex);
+			bdput(bdevp);
+			disk_put_part(part);
 			return 0;
 		default:
 			return -EINVAL;

block/partition-generic.c

@@ -84,7 +84,7 @@ ssize_t part_size_show(struct device *dev,
 		       struct device_attribute *attr, char *buf)
 {
 	struct hd_struct *p = dev_to_part(dev);
-	return sprintf(buf, "%llu\n",(unsigned long long)p->nr_sects);
+	return sprintf(buf, "%llu\n",(unsigned long long)part_nr_sects_read(p));
 }
 
 static ssize_t part_ro_show(struct device *dev,
@@ -294,6 +294,8 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
 		err = -ENOMEM;
 		goto out_free;
 	}
+
+	seqcount_init(&p->nr_sects_seq);
 	pdev = part_to_dev(p);
 
 	p->start_sect = start;

drivers/scsi/scsi_transport_fc.c

@@ -4146,45 +4146,7 @@ fc_bsg_rportadd(struct Scsi_Host *shost, struct fc_rport *rport)
 static void
 fc_bsg_remove(struct request_queue *q)
 {
-	struct request *req; /* block request */
-	int counts; /* totals for request_list count and starved */
-
 	if (q) {
-		/* Stop taking in new requests */
-		spin_lock_irq(q->queue_lock);
-		blk_stop_queue(q);
-
-		/* drain all requests in the queue */
-		while (1) {
-			/* need the lock to fetch a request
-			 * this may fetch the same reqeust as the previous pass
-			 */
-			req = blk_fetch_request(q);
-			/* save requests in use and starved */
-			counts = q->rq.count[0] + q->rq.count[1] +
-				q->rq.starved[0] + q->rq.starved[1];
-			spin_unlock_irq(q->queue_lock);
-			/* any requests still outstanding? */
-			if (counts == 0)
-				break;
-
-			/* This may be the same req as the previous iteration,
-			 * always send the blk_end_request_all after a prefetch.
-			 * It is not okay to not end the request because the
-			 * prefetch started the request.
-			 */
-			if (req) {
-				/* return -ENXIO to indicate that this queue is
-				 * going away
-				 */
-				req->errors = -ENXIO;
-				blk_end_request_all(req, -ENXIO);
-			}
-
-			msleep(200); /* allow bsg to possibly finish */
-			spin_lock_irq(q->queue_lock);
-		}
-
 		bsg_unregister_queue(q);
 		blk_cleanup_queue(q);
 	}

drivers/scsi/scsi_transport_iscsi.c

@@ -575,7 +575,7 @@ static int iscsi_remove_host(struct transport_container *tc,
 	struct iscsi_cls_host *ihost = shost->shost_data;
 
 	if (ihost->bsg_q) {
-		bsg_remove_queue(ihost->bsg_q);
+		bsg_unregister_queue(ihost->bsg_q);
 		blk_cleanup_queue(ihost->bsg_q);
 	}
 	return 0;

include/linux/blkdev.h

@@ -46,16 +46,23 @@ struct blkcg_gq;
 struct request;
 typedef void (rq_end_io_fn)(struct request *, int);
 
+#define BLK_RL_SYNCFULL		(1U << 0)
+#define BLK_RL_ASYNCFULL	(1U << 1)
+
 struct request_list {
+	struct request_queue	*q;	/* the queue this rl belongs to */
+#ifdef CONFIG_BLK_CGROUP
+	struct blkcg_gq		*blkg;	/* blkg this request pool belongs to */
+#endif
 	/*
 	 * count[], starved[], and wait[] are indexed by
 	 * BLK_RW_SYNC/BLK_RW_ASYNC
 	 */
-	int count[2];
-	int starved[2];
-	int elvpriv;
-	mempool_t *rq_pool;
-	wait_queue_head_t wait[2];
+	int			count[2];
+	int			starved[2];
+	mempool_t		*rq_pool;
+	wait_queue_head_t	wait[2];
+	unsigned int		flags;
 };
 
 /*
@@ -138,6 +145,7 @@ struct request {
 	struct hd_struct *part;
 	unsigned long start_time;
 #ifdef CONFIG_BLK_CGROUP
+	struct request_list *rl;		/* rl this rq is alloced from */
 	unsigned long long start_time_ns;
 	unsigned long long io_start_time_ns;    /* when passed to hardware */
 #endif
@@ -282,11 +290,16 @@ struct request_queue {
 	struct list_head	queue_head;
 	struct request		*last_merge;
 	struct elevator_queue	*elevator;
+	int			nr_rqs[2];	/* # allocated [a]sync rqs */
+	int			nr_rqs_elvpriv;	/* # allocated rqs w/ elvpriv */
 
 	/*
-	 * the queue request freelist, one for reads and one for writes
+	 * If blkcg is not used, @q->root_rl serves all requests.  If blkcg
+	 * is used, root blkg allocates from @q->root_rl and all other
+	 * blkgs from their own blkg->rl.  Which one to use should be
+	 * determined using bio_request_list().
 	 */
-	struct request_list	rq;
+	struct request_list	root_rl;
 
 	request_fn_proc		*request_fn;
 	make_request_fn		*make_request_fn;
@@ -561,27 +574,25 @@ static inline bool rq_is_sync(struct request *rq)
 	return rw_is_sync(rq->cmd_flags);
 }
 
-static inline int blk_queue_full(struct request_queue *q, int sync)
+static inline bool blk_rl_full(struct request_list *rl, bool sync)
 {
-	if (sync)
-		return test_bit(QUEUE_FLAG_SYNCFULL, &q->queue_flags);
-	return test_bit(QUEUE_FLAG_ASYNCFULL, &q->queue_flags);
+	unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL;
+
+	return rl->flags & flag;
 }
 
-static inline void blk_set_queue_full(struct request_queue *q, int sync)
+static inline void blk_set_rl_full(struct request_list *rl, bool sync)
 {
-	if (sync)
-		queue_flag_set(QUEUE_FLAG_SYNCFULL, q);
-	else
-		queue_flag_set(QUEUE_FLAG_ASYNCFULL, q);
+	unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL;
+
+	rl->flags |= flag;
 }
 
-static inline void blk_clear_queue_full(struct request_queue *q, int sync)
+static inline void blk_clear_rl_full(struct request_list *rl, bool sync)
 {
-	if (sync)
-		queue_flag_clear(QUEUE_FLAG_SYNCFULL, q);
-	else
-		queue_flag_clear(QUEUE_FLAG_ASYNCFULL, q);
+	unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL;
+
+	rl->flags &= ~flag;
 }
 
 

include/linux/blkpg.h

@@ -40,6 +40,7 @@ struct blkpg_ioctl_arg {
 /* The subfunctions (for the op field) */
 #define BLKPG_ADD_PARTITION	1
 #define BLKPG_DEL_PARTITION	2
+#define BLKPG_RESIZE_PARTITION	3
 
 /* Sizes of name fields. Unused at present. */
 #define BLKPG_DEVNAMELTH	64

include/linux/bsg-lib.h

@@ -67,7 +67,6 @@ void bsg_job_done(struct bsg_job *job, int result,
 int bsg_setup_queue(struct device *dev, struct request_queue *q, char *name,
 		    bsg_job_fn *job_fn, int dd_job_size);
 void bsg_request_fn(struct request_queue *q);
-void bsg_remove_queue(struct request_queue *q);
 void bsg_goose_queue(struct request_queue *q);
 
 #endif

include/linux/genhd.h

@@ -97,7 +97,13 @@ struct partition_meta_info {
 
 struct hd_struct {
 	sector_t start_sect;
+	/*
+	 * nr_sects is protected by sequence counter. One might extend a
+	 * partition while IO is happening to it and update of nr_sects
+	 * can be non-atomic on 32bit machines with 64bit sector_t.
+	 */
 	sector_t nr_sects;
+	seqcount_t nr_sects_seq;
 	sector_t alignment_offset;
 	unsigned int discard_alignment;
 	struct device __dev;
@@ -647,6 +653,57 @@ static inline void hd_struct_put(struct hd_struct *part)
 		__delete_partition(part);
 }
 
+/*
+ * Any access of part->nr_sects which is not protected by partition
+ * bd_mutex or gendisk bdev bd_mutex, should be done using this
+ * accessor function.
+ *
+ * Code written along the lines of i_size_read() and i_size_write().
+ * CONFIG_PREEMPT case optimizes the case of UP kernel with preemption
+ * on.
+ */
+static inline sector_t part_nr_sects_read(struct hd_struct *part)
+{
+#if BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_SMP)
+	sector_t nr_sects;
+	unsigned seq;
+	do {
+		seq = read_seqcount_begin(&part->nr_sects_seq);
+		nr_sects = part->nr_sects;
+	} while (read_seqcount_retry(&part->nr_sects_seq, seq));
+	return nr_sects;
+#elif BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_PREEMPT)
+	sector_t nr_sects;
+
+	preempt_disable();
+	nr_sects = part->nr_sects;
+	preempt_enable();
+	return nr_sects;
+#else
+	return part->nr_sects;
+#endif
+}
+
+/*
+ * Should be called with mutex lock held (typically bd_mutex) of partition
+ * to provide mutual exlusion among writers otherwise seqcount might be
+ * left in wrong state leaving the readers spinning infinitely.
+ */
+static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
+{
+#if BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_SMP)
+	write_seqcount_begin(&part->nr_sects_seq);
+	part->nr_sects = size;
+	write_seqcount_end(&part->nr_sects_seq);
+#elif BITS_PER_LONG==32 && defined(CONFIG_LBDAF) && defined(CONFIG_PREEMPT)
+	preempt_disable();
+	part->nr_sects = size;
+	preempt_enable();
+#else
+	part->nr_sects = size;
+#endif
+}
+
 #else /* CONFIG_BLOCK */
 
 static inline void printk_all_partitions(void) { }

include/linux/mempool.h

@@ -26,7 +26,8 @@ typedef struct mempool_s {
 extern mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn,
 			mempool_free_t *free_fn, void *pool_data);
 extern mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn,
-			mempool_free_t *free_fn, void *pool_data, int nid);
+			mempool_free_t *free_fn, void *pool_data,
+			gfp_t gfp_mask, int nid);
 
 extern int mempool_resize(mempool_t *pool, int new_min_nr, gfp_t gfp_mask);
 extern void mempool_destroy(mempool_t *pool);

mm/mempool.c

@@ -63,19 +63,21 @@ EXPORT_SYMBOL(mempool_destroy);
 mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn,
 				mempool_free_t *free_fn, void *pool_data)
 {
-	return  mempool_create_node(min_nr,alloc_fn,free_fn, pool_data,-1);
+	return mempool_create_node(min_nr,alloc_fn,free_fn, pool_data,
+				   GFP_KERNEL, NUMA_NO_NODE);
 }
 EXPORT_SYMBOL(mempool_create);
 
 mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn,
-			mempool_free_t *free_fn, void *pool_data, int node_id)
+			       mempool_free_t *free_fn, void *pool_data,
+			       gfp_t gfp_mask, int node_id)
 {
 	mempool_t *pool;
-	pool = kmalloc_node(sizeof(*pool), GFP_KERNEL | __GFP_ZERO, node_id);
+	pool = kmalloc_node(sizeof(*pool), gfp_mask | __GFP_ZERO, node_id);
 	if (!pool)
 		return NULL;
 	pool->elements = kmalloc_node(min_nr * sizeof(void *),
-					GFP_KERNEL, node_id);
+				      gfp_mask, node_id);
 	if (!pool->elements) {
 		kfree(pool);
 		return NULL;
@@ -93,7 +95,7 @@ mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn,
 	while (pool->curr_nr < pool->min_nr) {
 		void *element;
 
-		element = pool->alloc(GFP_KERNEL, pool->pool_data);
+		element = pool->alloc(gfp_mask, pool->pool_data);
 		if (unlikely(!element)) {
 			mempool_destroy(pool);
 			return NULL;