Merge tag 'v3.15-rc5' into next

Merge with Linux 3.15-rc5 to sync up Wacom and other changes.

22 files changed, 202 insertions, 193 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 4e491d9b5292..e4a4145926f6 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -336,7 +336,7 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 	 * under queue_lock.  If it's not pointing to @blkg now, it never
 	 * will.  Hint assignment itself can race safely.
 	 */
-	if (rcu_dereference_raw(blkcg->blkg_hint) == blkg)
+	if (rcu_access_pointer(blkcg->blkg_hint) == blkg)
 		rcu_assign_pointer(blkcg->blkg_hint, NULL);
 
 	/*
@@ -894,7 +894,7 @@ static int blkcg_can_attach(struct cgroup_subsys_state *css,
 	int ret = 0;
 
 	/* task_lock() is needed to avoid races with exit_io_context() */
-	cgroup_taskset_for_each(task, css, tset) {
+	cgroup_taskset_for_each(task, tset) {
 		task_lock(task);
 		ioc = task->io_context;
 		if (ioc && atomic_read(&ioc->nr_tasks) > 1)
@@ -906,17 +906,14 @@ static int blkcg_can_attach(struct cgroup_subsys_state *css,
 	return ret;
 }
 
-struct cgroup_subsys blkio_subsys = {
-	.name = "blkio",
+struct cgroup_subsys blkio_cgrp_subsys = {
 	.css_alloc = blkcg_css_alloc,
 	.css_offline = blkcg_css_offline,
 	.css_free = blkcg_css_free,
 	.can_attach = blkcg_can_attach,
-	.subsys_id = blkio_subsys_id,
 	.base_cftypes = blkcg_files,
-	.module = THIS_MODULE,
 };
-EXPORT_SYMBOL_GPL(blkio_subsys);
+EXPORT_SYMBOL_GPL(blkio_cgrp_subsys);
 
 /**
  * blkcg_activate_policy - activate a blkcg policy on a request_queue
@@ -1106,7 +1103,7 @@ int blkcg_policy_register(struct blkcg_policy *pol)
 
 	/* everything is in place, add intf files for the new policy */
 	if (pol->cftypes)
-		WARN_ON(cgroup_add_cftypes(&blkio_subsys, pol->cftypes));
+		WARN_ON(cgroup_add_cftypes(&blkio_cgrp_subsys, pol->cftypes));
 	ret = 0;
 out_unlock:
 	mutex_unlock(&blkcg_pol_mutex);
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 86154eab9523..371fe8e92ab5 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -186,7 +186,7 @@ static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css)
 
 static inline struct blkcg *task_blkcg(struct task_struct *tsk)
 {
-	return css_to_blkcg(task_css(tsk, blkio_subsys_id));
+	return css_to_blkcg(task_css(tsk, blkio_cgrp_id));
 }
 
 static inline struct blkcg *bio_blkcg(struct bio *bio)
@@ -241,12 +241,16 @@ static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd)
  */
 static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
 {
-	int ret;
+	char *p;
 
-	ret = cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);
-	if (ret)
+	p = cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);
+	if (!p) {
 		strncpy(buf, "<unavailable>", buflen);
-	return ret;
+		return -ENAMETOOLONG;
+	}
+
+	memmove(buf, p, buf + buflen - p);
+	return 0;
 }
 
 /**
@@ -435,9 +439,9 @@ static inline uint64_t blkg_stat_read(struct blkg_stat *stat)
 	uint64_t v;
 
 	do {
-		start = u64_stats_fetch_begin_bh(&stat->syncp);
+		start = u64_stats_fetch_begin_irq(&stat->syncp);
 		v = stat->cnt;
-	} while (u64_stats_fetch_retry_bh(&stat->syncp, start));
+	} while (u64_stats_fetch_retry_irq(&stat->syncp, start));
 
 	return v;
 }
@@ -508,9 +512,9 @@ static inline struct blkg_rwstat blkg_rwstat_read(struct blkg_rwstat *rwstat)
 	struct blkg_rwstat tmp;
 
 	do {
-		start = u64_stats_fetch_begin_bh(&rwstat->syncp);
+		start = u64_stats_fetch_begin_irq(&rwstat->syncp);
 		tmp = *rwstat;
-	} while (u64_stats_fetch_retry_bh(&rwstat->syncp, start));
+	} while (u64_stats_fetch_retry_irq(&rwstat->syncp, start));
 
 	return tmp;
 }
diff --git a/block/blk-core.c b/block/blk-core.c
index 853f92749202..a0e3096c4bb5 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -693,20 +693,11 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 	if (!uninit_q)
 		return NULL;
 
-	uninit_q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL);
-	if (!uninit_q->flush_rq)
-		goto out_cleanup_queue;
-
 	q = blk_init_allocated_queue(uninit_q, rfn, lock);
 	if (!q)
-		goto out_free_flush_rq;
-	return q;
+		blk_cleanup_queue(uninit_q);
 
-out_free_flush_rq:
-	kfree(uninit_q->flush_rq);
-out_cleanup_queue:
-	blk_cleanup_queue(uninit_q);
-	return NULL;
+	return q;
 }
 EXPORT_SYMBOL(blk_init_queue_node);
 
@@ -717,9 +708,13 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	if (!q)
 		return NULL;
 
-	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
+	q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL);
+	if (!q->flush_rq)
 		return NULL;
 
+	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
+		goto fail;
+
 	q->request_fn		= rfn;
 	q->prep_rq_fn		= NULL;
 	q->unprep_rq_fn		= NULL;
@@ -742,12 +737,16 @@ blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
 	/* init elevator */
 	if (elevator_init(q, NULL)) {
 		mutex_unlock(&q->sysfs_lock);
-		return NULL;
+		goto fail;
 	}
 
 	mutex_unlock(&q->sysfs_lock);
 
 	return q;
+
+fail:
+	kfree(q->flush_rq);
+	return NULL;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
 
@@ -1308,7 +1307,7 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 		struct request_list *rl = blk_rq_rl(req);
 
 		BUG_ON(!list_empty(&req->queuelist));
-		BUG_ON(!hlist_unhashed(&req->hash));
+		BUG_ON(ELV_ON_HASH(req));
 
 		blk_free_request(rl, req);
 		freed_request(rl, flags);
@@ -1929,7 +1928,7 @@ EXPORT_SYMBOL(submit_bio);
  *    in some cases below, so export this function.
  *    Request stacking drivers like request-based dm may change the queue
  *    limits while requests are in the queue (e.g. dm's table swapping).
- *    Such request stacking drivers should check those requests agaist
+ *    Such request stacking drivers should check those requests against
  *    the new queue limits again when they dispatch those requests,
  *    although such checkings are also done against the old queue limits
  *    when submitting requests.
@@ -2354,7 +2353,7 @@ 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
diff --git a/block/blk-exec.c b/block/blk-exec.c
index c68613bb4c79..dbf4502b1d67 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -65,7 +65,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	 * be resued after dying flag is set
 	 */
 	if (q->mq_ops) {
-		blk_mq_insert_request(q, rq, at_head, true);
+		blk_mq_insert_request(rq, at_head, true, false);
 		return;
 	}
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 66e2b697f5db..43e6b4755e9a 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -137,17 +137,20 @@ static void mq_flush_run(struct work_struct *work)
 	rq = container_of(work, struct request, mq_flush_work);
 
 	memset(&rq->csd, 0, sizeof(rq->csd));
-	blk_mq_run_request(rq, true, false);
+	blk_mq_insert_request(rq, false, true, false);
 }
 
-static bool blk_flush_queue_rq(struct request *rq)
+static bool blk_flush_queue_rq(struct request *rq, bool add_front)
 {
 	if (rq->q->mq_ops) {
 		INIT_WORK(&rq->mq_flush_work, mq_flush_run);
 		kblockd_schedule_work(rq->q, &rq->mq_flush_work);
 		return false;
 	} else {
-		list_add_tail(&rq->queuelist, &rq->q->queue_head);
+		if (add_front)
+			list_add(&rq->queuelist, &rq->q->queue_head);
+		else
+			list_add_tail(&rq->queuelist, &rq->q->queue_head);
 		return true;
 	}
 }
@@ -193,7 +196,7 @@ static bool blk_flush_complete_seq(struct request *rq, unsigned int seq,
 
 	case REQ_FSEQ_DATA:
 		list_move_tail(&rq->flush.list, &q->flush_data_in_flight);
-		queued = blk_flush_queue_rq(rq);
+		queued = blk_flush_queue_rq(rq, true);
 		break;
 
 	case REQ_FSEQ_DONE:
@@ -326,7 +329,7 @@ static bool blk_kick_flush(struct request_queue *q)
 	q->flush_rq->rq_disk = first_rq->rq_disk;
 	q->flush_rq->end_io = flush_end_io;
 
-	return blk_flush_queue_rq(q->flush_rq);
+	return blk_flush_queue_rq(q->flush_rq, false);
 }
 
 static void flush_data_end_io(struct request *rq, int error)
@@ -411,7 +414,7 @@ void blk_insert_flush(struct request *rq)
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
 		if (q->mq_ops) {
-			blk_mq_run_request(rq, false, true);
+			blk_mq_insert_request(rq, false, false, true);
 		} else
 			list_add_tail(&rq->queuelist, &q->queue_head);
 		return;
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 242df01413f6..1a27f45ec776 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -68,7 +68,7 @@ static void ioc_destroy_icq(struct io_cq *icq)
 	 * under queue_lock.  If it's not pointing to @icq now, it never
 	 * will.  Hint assignment itself can race safely.
 	 */
-	if (rcu_dereference_raw(ioc->icq_hint) == icq)
+	if (rcu_access_pointer(ioc->icq_hint) == icq)
 		rcu_assign_pointer(ioc->icq_hint, NULL);
 
 	ioc_exit_icq(icq);
diff --git a/block/blk-iopoll.c b/block/blk-iopoll.c
index 1855bf51edb0..c11d24e379e2 100644
--- a/block/blk-iopoll.c
+++ b/block/blk-iopoll.c
@@ -14,9 +14,6 @@
 
 #include "blk.h"
 
-int blk_iopoll_enabled = 1;
-EXPORT_SYMBOL(blk_iopoll_enabled);
-
 static unsigned int blk_iopoll_budget __read_mostly = 256;
 
 static DEFINE_PER_CPU(struct list_head, blk_cpu_iopoll);
diff --git a/block/blk-map.c b/block/blk-map.c
index ae4ae1047fd9..f7b22bc21518 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -188,7 +188,7 @@ EXPORT_SYMBOL(blk_rq_map_user);
  *    unmapping.
  */
 int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
-			struct rq_map_data *map_data, struct sg_iovec *iov,
+			struct rq_map_data *map_data, const struct sg_iovec *iov,
 			int iov_count, unsigned int len, gfp_t gfp_mask)
 {
 	struct bio *bio;
@@ -285,7 +285,7 @@ EXPORT_SYMBOL(blk_rq_unmap_user);
  *
  * Description:
  *    Data will be mapped directly if possible. Otherwise a bounce
- *    buffer is used. Can be called multple times to append multple
+ *    buffer is used. Can be called multiple times to append multiple
  *    buffers.
  */
 int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
diff --git a/block/blk-mq-cpu.c b/block/blk-mq-cpu.c
index 3146befb56aa..136ef8643bba 100644
--- a/block/blk-mq-cpu.c
+++ b/block/blk-mq-cpu.c
@@ -11,7 +11,7 @@
 #include "blk-mq.h"
 
 static LIST_HEAD(blk_mq_cpu_notify_list);
-static DEFINE_SPINLOCK(blk_mq_cpu_notify_lock);
+static DEFINE_RAW_SPINLOCK(blk_mq_cpu_notify_lock);
 
 static int blk_mq_main_cpu_notify(struct notifier_block *self,
 				  unsigned long action, void *hcpu)
@@ -19,12 +19,12 @@ static int blk_mq_main_cpu_notify(struct notifier_block *self,
 	unsigned int cpu = (unsigned long) hcpu;
 	struct blk_mq_cpu_notifier *notify;
 
-	spin_lock(&blk_mq_cpu_notify_lock);
+	raw_spin_lock(&blk_mq_cpu_notify_lock);
 
 	list_for_each_entry(notify, &blk_mq_cpu_notify_list, list)
 		notify->notify(notify->data, action, cpu);
 
-	spin_unlock(&blk_mq_cpu_notify_lock);
+	raw_spin_unlock(&blk_mq_cpu_notify_lock);
 	return NOTIFY_OK;
 }
 
@@ -32,16 +32,16 @@ void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
 {
 	BUG_ON(!notifier->notify);
 
-	spin_lock(&blk_mq_cpu_notify_lock);
+	raw_spin_lock(&blk_mq_cpu_notify_lock);
 	list_add_tail(&notifier->list, &blk_mq_cpu_notify_list);
-	spin_unlock(&blk_mq_cpu_notify_lock);
+	raw_spin_unlock(&blk_mq_cpu_notify_lock);
 }
 
 void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
 {
-	spin_lock(&blk_mq_cpu_notify_lock);
+	raw_spin_lock(&blk_mq_cpu_notify_lock);
 	list_del(&notifier->list);
-	spin_unlock(&blk_mq_cpu_notify_lock);
+	raw_spin_unlock(&blk_mq_cpu_notify_lock);
 }
 
 void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index f8721278601c..097921329619 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -9,15 +9,6 @@
 #include "blk.h"
 #include "blk-mq.h"
 
-static void show_map(unsigned int *map, unsigned int nr)
-{
-	int i;
-
-	pr_info("blk-mq: CPU -> queue map\n");
-	for_each_online_cpu(i)
-		pr_info("  CPU%2u -> Queue %u\n", i, map[i]);
-}
-
 static int cpu_to_queue_index(unsigned int nr_cpus, unsigned int nr_queues,
 			      const int cpu)
 {
@@ -85,7 +76,6 @@ int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues)
 			map[i] = map[first_sibling];
 	}
 
-	show_map(map, nr_cpus);
 	free_cpumask_var(cpus);
 	return 0;
 }
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index b91ce75bd35d..b0ba264b0522 100644
--- a/block/blk-mq-sysfs.c
+++ b/block/blk-mq-sysfs.c
@@ -244,6 +244,32 @@ static ssize_t blk_mq_hw_sysfs_tags_show(struct blk_mq_hw_ctx *hctx, char *page)
 	return blk_mq_tag_sysfs_show(hctx->tags, page);
 }
 
+static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
+{
+	unsigned int i, queue_num, first = 1;
+	ssize_t ret = 0;
+
+	blk_mq_disable_hotplug();
+
+	for_each_online_cpu(i) {
+		queue_num = hctx->queue->mq_map[i];
+		if (queue_num != hctx->queue_num)
+			continue;
+
+		if (first)
+			ret += sprintf(ret + page, "%u", i);
+		else
+			ret += sprintf(ret + page, ", %u", i);
+
+		first = 0;
+	}
+
+	blk_mq_enable_hotplug();
+
+	ret += sprintf(ret + page, "\n");
+	return ret;
+}
+
 static struct blk_mq_ctx_sysfs_entry blk_mq_sysfs_dispatched = {
 	.attr = {.name = "dispatched", .mode = S_IRUGO },
 	.show = blk_mq_sysfs_dispatched_show,
@@ -294,6 +320,10 @@ static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_tags = {
 	.attr = {.name = "tags", .mode = S_IRUGO },
 	.show = blk_mq_hw_sysfs_tags_show,
 };
+static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_cpus = {
+	.attr = {.name = "cpu_list", .mode = S_IRUGO },
+	.show = blk_mq_hw_sysfs_cpus_show,
+};
 
 static struct attribute *default_hw_ctx_attrs[] = {
 	&blk_mq_hw_sysfs_queued.attr,
@@ -302,6 +332,7 @@ static struct attribute *default_hw_ctx_attrs[] = {
 	&blk_mq_hw_sysfs_pending.attr,
 	&blk_mq_hw_sysfs_ipi.attr,
 	&blk_mq_hw_sysfs_tags.attr,
+	&blk_mq_hw_sysfs_cpus.attr,
 	NULL,
 };
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1fa9dd153fde..1d2a9bdbee57 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -73,8 +73,8 @@ static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx,
 		set_bit(ctx->index_hw, hctx->ctx_map);
 }
 
-static struct request *blk_mq_alloc_rq(struct blk_mq_hw_ctx *hctx, gfp_t gfp,
-				       bool reserved)
+static struct request *__blk_mq_alloc_request(struct blk_mq_hw_ctx *hctx,
+					      gfp_t gfp, bool reserved)
 {
 	struct request *rq;
 	unsigned int tag;
@@ -193,12 +193,6 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 	ctx->rq_dispatched[rw_is_sync(rw_flags)]++;
 }
 
-static struct request *__blk_mq_alloc_request(struct blk_mq_hw_ctx *hctx,
-					      gfp_t gfp, bool reserved)
-{
-	return blk_mq_alloc_rq(hctx, gfp, reserved);
-}
-
 static struct request *blk_mq_alloc_request_pinned(struct request_queue *q,
 						   int rw, gfp_t gfp,
 						   bool reserved)
@@ -289,38 +283,10 @@ void blk_mq_free_request(struct request *rq)
 	__blk_mq_free_request(hctx, ctx, rq);
 }
 
-static void blk_mq_bio_endio(struct request *rq, struct bio *bio, int error)
+bool blk_mq_end_io_partial(struct request *rq, int error, unsigned int nr_bytes)
 {
-	if (error)
-		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
-		error = -EIO;
-
-	if (unlikely(rq->cmd_flags & REQ_QUIET))
-		set_bit(BIO_QUIET, &bio->bi_flags);
-
-	/* don't actually finish bio if it's part of flush sequence */
-	if (!(rq->cmd_flags & REQ_FLUSH_SEQ))
-		bio_endio(bio, error);
-}
-
-void blk_mq_end_io(struct request *rq, int error)
-{
-	struct bio *bio = rq->bio;
-	unsigned int bytes = 0;
-
-	trace_block_rq_complete(rq->q, rq);
-
-	while (bio) {
-		struct bio *next = bio->bi_next;
-
-		bio->bi_next = NULL;
-		bytes += bio->bi_iter.bi_size;
-		blk_mq_bio_endio(rq, bio, error);
-		bio = next;
-	}
-
-	blk_account_io_completion(rq, bytes);
+	if (blk_update_request(rq, error, blk_rq_bytes(rq)))
+		return true;
 
 	blk_account_io_done(rq);
 
@@ -328,8 +294,9 @@ void blk_mq_end_io(struct request *rq, int error)
 		rq->end_io(rq, error);
 	else
 		blk_mq_free_request(rq);
+	return false;
 }
-EXPORT_SYMBOL(blk_mq_end_io);
+EXPORT_SYMBOL(blk_mq_end_io_partial);
 
 static void __blk_mq_complete_request_remote(void *data)
 {
@@ -353,7 +320,7 @@ void __blk_mq_complete_request(struct request *rq)
 		rq->csd.func = __blk_mq_complete_request_remote;
 		rq->csd.info = rq;
 		rq->csd.flags = 0;
-		__smp_call_function_single(ctx->cpu, &rq->csd, 0);
+		smp_call_function_single_async(ctx->cpu, &rq->csd);
 	} else {
 		rq->q->softirq_done_fn(rq);
 	}
@@ -547,7 +514,7 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 	LIST_HEAD(rq_list);
 	int bit, queued;
 
-	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->flags)))
+	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
 		return;
 
 	hctx->run++;
@@ -636,7 +603,7 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 
 void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 {
-	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->flags)))
+	if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state)))
 		return;
 
 	if (!async)
@@ -656,7 +623,7 @@ void blk_mq_run_queues(struct request_queue *q, bool async)
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if ((!blk_mq_hctx_has_pending(hctx) &&
 		    list_empty_careful(&hctx->dispatch)) ||
-		    test_bit(BLK_MQ_S_STOPPED, &hctx->flags))
+		    test_bit(BLK_MQ_S_STOPPED, &hctx->state))
 			continue;
 
 		blk_mq_run_hw_queue(hctx, async);
@@ -730,61 +697,28 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
 	blk_mq_add_timer(rq);
 }
 
-void blk_mq_insert_request(struct request_queue *q, struct request *rq,
-			   bool at_head, bool run_queue)
+void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
+		bool async)
 {
+	struct request_queue *q = rq->q;
 	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx, *current_ctx;
+	struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx;
+
+	current_ctx = blk_mq_get_ctx(q);
+	if (!cpu_online(ctx->cpu))
+		rq->mq_ctx = ctx = current_ctx;
 
-	ctx = rq->mq_ctx;
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
-	if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
+	if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA) &&
+	    !(rq->cmd_flags & (REQ_FLUSH_SEQ))) {
 		blk_insert_flush(rq);
 	} else {
-		current_ctx = blk_mq_get_ctx(q);
-
-		if (!cpu_online(ctx->cpu)) {
-			ctx = current_ctx;
-			hctx = q->mq_ops->map_queue(q, ctx->cpu);
-			rq->mq_ctx = ctx;
-		}
 		spin_lock(&ctx->lock);
 		__blk_mq_insert_request(hctx, rq, at_head);
 		spin_unlock(&ctx->lock);
-
-		blk_mq_put_ctx(current_ctx);
 	}
 
-	if (run_queue)
-		__blk_mq_run_hw_queue(hctx);
-}
-EXPORT_SYMBOL(blk_mq_insert_request);
-
-/*
- * This is a special version of blk_mq_insert_request to bypass FLUSH request
- * check. Should only be used internally.
- */
-void blk_mq_run_request(struct request *rq, bool run_queue, bool async)
-{
-	struct request_queue *q = rq->q;
-	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx, *current_ctx;
-
-	current_ctx = blk_mq_get_ctx(q);
-
-	ctx = rq->mq_ctx;
-	if (!cpu_online(ctx->cpu)) {
-		ctx = current_ctx;
-		rq->mq_ctx = ctx;
-	}
-	hctx = q->mq_ops->map_queue(q, ctx->cpu);
-
-	/* ctx->cpu might be offline */
-	spin_lock(&ctx->lock);
-	__blk_mq_insert_request(hctx, rq, false);
-	spin_unlock(&ctx->lock);
-
 	blk_mq_put_ctx(current_ctx);
 
 	if (run_queue)
@@ -926,6 +860,8 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	ctx = blk_mq_get_ctx(q);
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
+	if (is_sync)
+		rw |= REQ_SYNC;
 	trace_block_getrq(q, bio, rw);
 	rq = __blk_mq_alloc_request(hctx, GFP_ATOMIC, false);
 	if (likely(rq))
@@ -1020,6 +956,7 @@ static void blk_mq_hctx_notify(void *data, unsigned long action,
 			       unsigned int cpu)
 {
 	struct blk_mq_hw_ctx *hctx = data;
+	struct request_queue *q = hctx->queue;
 	struct blk_mq_ctx *ctx;
 	LIST_HEAD(tmp);
 
@@ -1029,7 +966,7 @@ static void blk_mq_hctx_notify(void *data, unsigned long action,
 	/*
 	 * Move ctx entries to new CPU, if this one is going away.
 	 */
-	ctx = __blk_mq_get_ctx(hctx->queue, cpu);
+	ctx = __blk_mq_get_ctx(q, cpu);
 
 	spin_lock(&ctx->lock);
 	if (!list_empty(&ctx->rq_list)) {
@@ -1041,7 +978,7 @@ static void blk_mq_hctx_notify(void *data, unsigned long action,
 	if (list_empty(&tmp))
 		return;
 
-	ctx = blk_mq_get_ctx(hctx->queue);
+	ctx = blk_mq_get_ctx(q);
 	spin_lock(&ctx->lock);
 
 	while (!list_empty(&tmp)) {
@@ -1052,14 +989,55 @@ static void blk_mq_hctx_notify(void *data, unsigned long action,
 		list_move_tail(&rq->queuelist, &ctx->rq_list);
 	}
 
+	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 	blk_mq_hctx_mark_pending(hctx, ctx);
 
 	spin_unlock(&ctx->lock);
 	blk_mq_put_ctx(ctx);
+
+	blk_mq_run_hw_queue(hctx, true);
+}
+
+static int blk_mq_init_hw_commands(struct blk_mq_hw_ctx *hctx,
+				   int (*init)(void *, struct blk_mq_hw_ctx *,
+					struct request *, unsigned int),
+				   void *data)
+{
+	unsigned int i;
+	int ret = 0;
+
+	for (i = 0; i < hctx->queue_depth; i++) {
+		struct request *rq = hctx->rqs[i];
+
+		ret = init(data, hctx, rq, i);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+int blk_mq_init_commands(struct request_queue *q,
+			 int (*init)(void *, struct blk_mq_hw_ctx *,
+					struct request *, unsigned int),
+			 void *data)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+	int ret = 0;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		ret = blk_mq_init_hw_commands(hctx, init, data);
+		if (ret)
+			break;
+	}
+
+	return ret;
 }
+EXPORT_SYMBOL(blk_mq_init_commands);
 
-static void blk_mq_init_hw_commands(struct blk_mq_hw_ctx *hctx,
-				    void (*init)(void *, struct blk_mq_hw_ctx *,
+static void blk_mq_free_hw_commands(struct blk_mq_hw_ctx *hctx,
+				    void (*free)(void *, struct blk_mq_hw_ctx *,
 					struct request *, unsigned int),
 				    void *data)
 {
@@ -1068,12 +1046,12 @@ static void blk_mq_init_hw_commands(struct blk_mq_hw_ctx *hctx,
 	for (i = 0; i < hctx->queue_depth; i++) {
 		struct request *rq = hctx->rqs[i];
 
-		init(data, hctx, rq, i);
+		free(data, hctx, rq, i);
 	}
 }
 
-void blk_mq_init_commands(struct request_queue *q,
-			  void (*init)(void *, struct blk_mq_hw_ctx *,
+void blk_mq_free_commands(struct request_queue *q,
+			  void (*free)(void *, struct blk_mq_hw_ctx *,
 					struct request *, unsigned int),
 			  void *data)
 {
@@ -1081,9 +1059,9 @@ void blk_mq_init_commands(struct request_queue *q,
 	unsigned int i;
 
 	queue_for_each_hw_ctx(q, hctx, i)
-		blk_mq_init_hw_commands(hctx, init, data);
+		blk_mq_free_hw_commands(hctx, free, data);
 }
-EXPORT_SYMBOL(blk_mq_init_commands);
+EXPORT_SYMBOL(blk_mq_free_commands);
 
 static void blk_mq_free_rq_map(struct blk_mq_hw_ctx *hctx)
 {
@@ -1494,6 +1472,16 @@ static int blk_mq_queue_reinit_notify(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+void blk_mq_disable_hotplug(void)
+{
+	mutex_lock(&all_q_mutex);
+}
+
+void blk_mq_enable_hotplug(void)
+{
+	mutex_unlock(&all_q_mutex);
+}
+
 static int __init blk_mq_init(void)
 {
 	blk_mq_cpu_init();
diff --git a/block/blk-mq.h b/block/blk-mq.h
index ed0035cd458e..ebbe6bac9d61 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -23,7 +23,6 @@ struct blk_mq_ctx {
 };
 
 void __blk_mq_complete_request(struct request *rq);
-void blk_mq_run_request(struct request *rq, bool run_queue, bool async);
 void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_init_flush(struct request_queue *q);
 void blk_mq_drain_queue(struct request_queue *q);
@@ -40,6 +39,8 @@ void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
 void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier);
 void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier);
 void blk_mq_cpu_init(void);
+void blk_mq_enable_hotplug(void);
+void blk_mq_disable_hotplug(void);
 
 /*
  * CPU -> queue mappings
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 57790c1a97eb..53b1737e978d 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -30,8 +30,8 @@ static void blk_done_softirq(struct softirq_action *h)
 	while (!list_empty(&local_list)) {
 		struct request *rq;
 
-		rq = list_entry(local_list.next, struct request, csd.list);
-		list_del_init(&rq->csd.list);
+		rq = list_entry(local_list.next, struct request, ipi_list);
+		list_del_init(&rq->ipi_list);
 		rq->q->softirq_done_fn(rq);
 	}
 }
@@ -45,9 +45,9 @@ static void trigger_softirq(void *data)
 
 	local_irq_save(flags);
 	list = this_cpu_ptr(&blk_cpu_done);
-	list_add_tail(&rq->csd.list, list);
+	list_add_tail(&rq->ipi_list, list);
 
-	if (list->next == &rq->csd.list)
+	if (list->next == &rq->ipi_list)
 		raise_softirq_irqoff(BLOCK_SOFTIRQ);
 
 	local_irq_restore(flags);
@@ -65,7 +65,7 @@ static int raise_blk_irq(int cpu, struct request *rq)
 		data->info = rq;
 		data->flags = 0;
 
-		__smp_call_function_single(cpu, data, 0);
+		smp_call_function_single_async(cpu, data);
 		return 0;
 	}
 
@@ -136,7 +136,7 @@ void __blk_complete_request(struct request *req)
 		struct list_head *list;
 do_local:
 		list = this_cpu_ptr(&blk_cpu_done);
-		list_add_tail(&req->csd.list, list);
+		list_add_tail(&req->ipi_list, list);
 
 		/*
 		 * if the list only contains our just added request,
@@ -144,7 +144,7 @@ do_local:
 		 * entries there, someone already raised the irq but it
 		 * hasn't run yet.
 		 */
-		if (list->next == &req->csd.list)
+		if (list->next == &req->ipi_list)
 			raise_softirq_irqoff(BLOCK_SOFTIRQ);
 	} else if (raise_blk_irq(ccpu, req))
 		goto do_local;
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 1474c3ab7e72..033745cd7fba 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1408,13 +1408,13 @@ static int tg_set_conf(struct cgroup_subsys_state *css, struct cftype *cft,
 }
 
 static int tg_set_conf_u64(struct cgroup_subsys_state *css, struct cftype *cft,
-			   const char *buf)
+			   char *buf)
 {
 	return tg_set_conf(css, cft, buf, true);
 }
 
 static int tg_set_conf_uint(struct cgroup_subsys_state *css, struct cftype *cft,
-			    const char *buf)
+			    char *buf)
 {
 	return tg_set_conf(css, cft, buf, false);
 }
@@ -1425,28 +1425,24 @@ static struct cftype throtl_files[] = {
 		.private = offsetof(struct throtl_grp, bps[READ]),
 		.seq_show = tg_print_conf_u64,
 		.write_string = tg_set_conf_u64,
-		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.write_bps_device",
 		.private = offsetof(struct throtl_grp, bps[WRITE]),
 		.seq_show = tg_print_conf_u64,
 		.write_string = tg_set_conf_u64,
-		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.read_iops_device",
 		.private = offsetof(struct throtl_grp, iops[READ]),
 		.seq_show = tg_print_conf_uint,
 		.write_string = tg_set_conf_uint,
-		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.write_iops_device",
 		.private = offsetof(struct throtl_grp, iops[WRITE]),
 		.seq_show = tg_print_conf_uint,
 		.write_string = tg_set_conf_uint,
-		.max_write_len = 256,
 	},
 	{
 		.name = "throttle.io_service_bytes",
diff --git a/block/blk.h b/block/blk.h
index d23b415b8a28..1d880f1f957f 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -78,7 +78,7 @@ static inline void blk_clear_rq_complete(struct request *rq)
 /*
  * Internal elevator interface
  */
-#define ELV_ON_HASH(rq) hash_hashed(&(rq)->hash)
+#define ELV_ON_HASH(rq) ((rq)->cmd_flags & REQ_HASHED)
 
 void blk_insert_flush(struct request *rq);
 void blk_abort_flushes(struct request_queue *q);
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 744833b630c6..e0985f1955e7 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -1701,13 +1701,13 @@ static int __cfqg_set_weight_device(struct cgroup_subsys_state *css,
 }
 
 static int cfqg_set_weight_device(struct cgroup_subsys_state *css,
-				  struct cftype *cft, const char *buf)
+				  struct cftype *cft, char *buf)
 {
 	return __cfqg_set_weight_device(css, cft, buf, false);
 }
 
 static int cfqg_set_leaf_weight_device(struct cgroup_subsys_state *css,
-				       struct cftype *cft, const char *buf)
+				       struct cftype *cft, char *buf)
 {
 	return __cfqg_set_weight_device(css, cft, buf, true);
 }
@@ -1838,7 +1838,6 @@ static struct cftype cfq_blkcg_files[] = {
 		.flags = CFTYPE_ONLY_ON_ROOT,
 		.seq_show = cfqg_print_leaf_weight_device,
 		.write_string = cfqg_set_leaf_weight_device,
-		.max_write_len = 256,
 	},
 	{
 		.name = "weight",
@@ -1853,7 +1852,6 @@ static struct cftype cfq_blkcg_files[] = {
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = cfqg_print_weight_device,
 		.write_string = cfqg_set_weight_device,
-		.max_write_len = 256,
 	},
 	{
 		.name = "weight",
@@ -1866,7 +1864,6 @@ static struct cftype cfq_blkcg_files[] = {
 		.name = "leaf_weight_device",
 		.seq_show = cfqg_print_leaf_weight_device,
 		.write_string = cfqg_set_leaf_weight_device,
-		.max_write_len = 256,
 	},
 	{
 		.name = "leaf_weight",
@@ -2367,10 +2364,10 @@ cfq_merged_requests(struct request_queue *q, struct request *rq,
 	 * reposition in fifo if next is older than rq
 	 */
 	if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
-	    time_before(rq_fifo_time(next), rq_fifo_time(rq)) &&
+	    time_before(next->fifo_time, rq->fifo_time) &&
 	    cfqq == RQ_CFQQ(next)) {
 		list_move(&rq->queuelist, &next->queuelist);
-		rq_set_fifo_time(rq, rq_fifo_time(next));
+		rq->fifo_time = next->fifo_time;
 	}
 
 	if (cfqq->next_rq == next)
@@ -2814,7 +2811,7 @@ static struct request *cfq_check_fifo(struct cfq_queue *cfqq)
 		return NULL;
 
 	rq = rq_entry_fifo(cfqq->fifo.next);
-	if (time_before(jiffies, rq_fifo_time(rq)))
+	if (time_before(jiffies, rq->fifo_time))
 		rq = NULL;
 
 	cfq_log_cfqq(cfqq->cfqd, cfqq, "fifo=%p", rq);
@@ -3927,7 +3924,7 @@ static void cfq_insert_request(struct request_queue *q, struct request *rq)
 	cfq_log_cfqq(cfqd, cfqq, "insert_request");
 	cfq_init_prio_data(cfqq, RQ_CIC(rq));
 
-	rq_set_fifo_time(rq, jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)]);
+	rq->fifo_time = jiffies + cfqd->cfq_fifo_expire[rq_is_sync(rq)];
 	list_add_tail(&rq->queuelist, &cfqq->fifo);
 	cfq_add_rq_rb(rq);
 	cfqg_stats_update_io_add(RQ_CFQG(rq), cfqd->serving_group,
diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c
index 9ef66406c625..a753df2b3fc2 100644
--- a/block/deadline-iosched.c
+++ b/block/deadline-iosched.c
@@ -106,7 +106,7 @@ deadline_add_request(struct request_queue *q, struct request *rq)
 	/*
 	 * set expire time and add to fifo list
 	 */
-	rq_set_fifo_time(rq, jiffies + dd->fifo_expire[data_dir]);
+	rq->fifo_time = jiffies + dd->fifo_expire[data_dir];
 	list_add_tail(&rq->queuelist, &dd->fifo_list[data_dir]);
 }
 
@@ -174,9 +174,9 @@ deadline_merged_requests(struct request_queue *q, struct request *req,
 	 * and move into next position (next will be deleted) in fifo
 	 */
 	if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) {
-		if (time_before(rq_fifo_time(next), rq_fifo_time(req))) {
+		if (time_before(next->fifo_time, req->fifo_time)) {
 			list_move(&req->queuelist, &next->queuelist);
-			rq_set_fifo_time(req, rq_fifo_time(next));
+			req->fifo_time = next->fifo_time;
 		}
 	}
 
@@ -230,7 +230,7 @@ static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
 	/*
 	 * rq is expired!
 	 */
-	if (time_after_eq(jiffies, rq_fifo_time(rq)))
+	if (time_after_eq(jiffies, rq->fifo_time))
 		return 1;
 
 	return 0;
diff --git a/block/elevator.c b/block/elevator.c
index 42c45a7d6714..1e01b66a0b92 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -247,6 +247,7 @@ EXPORT_SYMBOL(elevator_exit);
 static inline void __elv_rqhash_del(struct request *rq)
 {
 	hash_del(&rq->hash);
+	rq->cmd_flags &= ~REQ_HASHED;
 }
 
 static void elv_rqhash_del(struct request_queue *q, struct request *rq)
@@ -261,6 +262,7 @@ static void elv_rqhash_add(struct request_queue *q, struct request *rq)
 
 	BUG_ON(ELV_ON_HASH(rq));
 	hash_add(e->hash, &rq->hash, rq_hash_key(rq));
+	rq->cmd_flags |= REQ_HASHED;
 }
 
 static void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
diff --git a/block/partitions/atari.h b/block/partitions/atari.h
index fe2d32a89f36..f2ec43bfeec1 100644
--- a/block/partitions/atari.h
+++ b/block/partitions/atari.h
@@ -11,6 +11,8 @@
  * by Guenther Kelleter (guenther@pool.informatik.rwth-aachen.de)
  */
 
+#include <linux/compiler.h>
+
 struct partition_info
 {
   u8 flg;			/* bit 0: active; bit 7: bootable */
@@ -29,6 +31,6 @@ struct rootsector
   u32 bsl_st;			/* start of bad sector list */
   u32 bsl_cnt;			/* length of bad sector list */
   u16 checksum;			/* checksum for bootable disks */
-} __attribute__((__packed__));
+} __packed;
 
 int atari_partition(struct parsed_partitions *state);
diff --git a/block/partitions/efi.h b/block/partitions/efi.h
index 4efcafba7e64..abd0b19288a6 100644
--- a/block/partitions/efi.h
+++ b/block/partitions/efi.h
@@ -32,6 +32,7 @@
 #include <linux/major.h>
 #include <linux/string.h>
 #include <linux/efi.h>
+#include <linux/compiler.h>
 
 #define MSDOS_MBR_SIGNATURE 0xaa55
 #define EFI_PMBR_OSTYPE_EFI 0xEF
@@ -87,13 +88,13 @@ typedef struct _gpt_header {
 	 *
 	 * uint8_t		reserved2[ BlockSize - 92 ];
 	 */
-} __attribute__ ((packed)) gpt_header;
+} __packed gpt_header;
 
 typedef struct _gpt_entry_attributes {
 	u64 required_to_function:1;
 	u64 reserved:47;
         u64 type_guid_specific:16;
-} __attribute__ ((packed)) gpt_entry_attributes;
+} __packed gpt_entry_attributes;
 
 typedef struct _gpt_entry {
 	efi_guid_t partition_type_guid;
@@ -102,7 +103,7 @@ typedef struct _gpt_entry {
 	__le64 ending_lba;
 	gpt_entry_attributes attributes;
 	efi_char16_t partition_name[72 / sizeof (efi_char16_t)];
-} __attribute__ ((packed)) gpt_entry;
+} __packed gpt_entry;
 
 typedef struct _gpt_mbr_record {
 	u8	boot_indicator; /* unused by EFI, set to 0x80 for bootable */
@@ -124,7 +125,7 @@ typedef struct _legacy_mbr {
 	__le16 unknown;
 	gpt_mbr_record partition_record[4];
 	__le16 signature;
-} __attribute__ ((packed)) legacy_mbr;
+} __packed legacy_mbr;
 
 /* Functions */
 extern int efi_partition(struct parsed_partitions *state);
diff --git a/block/partitions/karma.c b/block/partitions/karma.c
index 0ea19312706b..9721fa589bb1 100644
--- a/block/partitions/karma.c
+++ b/block/partitions/karma.c
@@ -8,6 +8,7 @@
 
 #include "check.h"
 #include "karma.h"
+#include <linux/compiler.h>
 
 int karma_partition(struct parsed_partitions *state)
 {
@@ -26,7 +27,7 @@ int karma_partition(struct parsed_partitions *state)
 		} d_partitions[2];
 		u8 d_blank[208];
 		__le16 d_magic;
-	} __attribute__((packed)) *label;
+	} __packed *label;
 	struct d_partition *p;
 
 	data = read_part_sector(state, 0, &sect);