Merge branch 'v3.1-rc10' into for-3.2/core

Conflicts:
	block/blk-core.c
	include/linux/blkdev.h

Signed-off-by: Jens Axboe <axboe@kernel.dk>

12 files changed, 413 insertions, 54 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 60be1e0455d..e97934eecec 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -65,6 +65,16 @@ config BLK_DEV_BSG
 
 	  If unsure, say Y.
 
+config BLK_DEV_BSGLIB
+	bool "Block layer SG support v4 helper lib"
+	default n
+	select BLK_DEV_BSG
+	help
+	  Subsystems will normally enable this if needed. Users will not
+	  normally need to manually enable this.
+
+	  If unsure, say N.
+
 config BLK_DEV_INTEGRITY
 	bool "Block layer data integrity support"
 	---help---
diff --git a/block/Makefile b/block/Makefile
index 0fec4b3fab5..514c6e4f427 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -8,6 +8,7 @@ obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-iopoll.o blk-lib.o ioctl.o genhd.o scsi_ioctl.o
 
 obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
+obj-$(CONFIG_BLK_DEV_BSGLIB)	+= bsg-lib.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
 obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index bcaf16ee6ad..b596e54ddd7 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -785,10 +785,10 @@ static int blkio_policy_parse_and_set(char *buf,
 {
 	char *s[4], *p, *major_s = NULL, *minor_s = NULL;
 	int ret;
-	unsigned long major, minor, temp;
+	unsigned long major, minor;
 	int i = 0;
 	dev_t dev;
-	u64 bps, iops;
+	u64 temp;
 
 	memset(s, 0, sizeof(s));
 
@@ -826,20 +826,23 @@ static int blkio_policy_parse_and_set(char *buf,
 
 	dev = MKDEV(major, minor);
 
-	ret = blkio_check_dev_num(dev);
+	ret = strict_strtoull(s[1], 10, &temp);
 	if (ret)
-		return ret;
+		return -EINVAL;
 
-	newpn->dev = dev;
+	/* For rule removal, do not check for device presence. */
+	if (temp) {
+		ret = blkio_check_dev_num(dev);
+		if (ret)
+			return ret;
+	}
 
-	if (s[1] == NULL)
-		return -EINVAL;
+	newpn->dev = dev;
 
 	switch (plid) {
 	case BLKIO_POLICY_PROP:
-		ret = strict_strtoul(s[1], 10, &temp);
-		if (ret || (temp < BLKIO_WEIGHT_MIN && temp > 0) ||
-			temp > BLKIO_WEIGHT_MAX)
+		if ((temp < BLKIO_WEIGHT_MIN && temp > 0) ||
+		     temp > BLKIO_WEIGHT_MAX)
 			return -EINVAL;
 
 		newpn->plid = plid;
@@ -850,26 +853,18 @@ static int blkio_policy_parse_and_set(char *buf,
 		switch(fileid) {
 		case BLKIO_THROTL_read_bps_device:
 		case BLKIO_THROTL_write_bps_device:
-			ret = strict_strtoull(s[1], 10, &bps);
-			if (ret)
-				return -EINVAL;
-
 			newpn->plid = plid;
 			newpn->fileid = fileid;
-			newpn->val.bps = bps;
+			newpn->val.bps = temp;
 			break;
 		case BLKIO_THROTL_read_iops_device:
 		case BLKIO_THROTL_write_iops_device:
-			ret = strict_strtoull(s[1], 10, &iops);
-			if (ret)
-				return -EINVAL;
-
-			if (iops > THROTL_IOPS_MAX)
+			if (temp > THROTL_IOPS_MAX)
 				return -EINVAL;
 
 			newpn->plid = plid;
 			newpn->fileid = fileid;
-			newpn->val.iops = (unsigned int)iops;
+			newpn->val.iops = (unsigned int)temp;
 			break;
 		}
 		break;
diff --git a/block/blk-core.c b/block/blk-core.c
index 97e9e5405b8..79e41a76d96 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -346,9 +346,10 @@ void blk_put_queue(struct request_queue *q)
 EXPORT_SYMBOL(blk_put_queue);
 
 /*
- * Note: If a driver supplied the queue lock, it should not zap that lock
- * unexpectedly as some queue cleanup components like elevator_exit() and
- * blk_throtl_exit() need queue lock.
+ * Note: If a driver supplied the queue lock, it is disconnected
+ * by this function. The actual state of the lock doesn't matter
+ * here as the request_queue isn't accessible after this point
+ * (QUEUE_FLAG_DEAD is set) and no other requests will be queued.
  */
 void blk_cleanup_queue(struct request_queue *q)
 {
@@ -365,10 +366,8 @@ void blk_cleanup_queue(struct request_queue *q)
 	queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q);
 	mutex_unlock(&q->sysfs_lock);
 
-	if (q->elevator)
-		elevator_exit(q->elevator);
-
-	blk_throtl_exit(q);
+	if (q->queue_lock != &q->__queue_lock)
+		q->queue_lock = &q->__queue_lock;
 
 	blk_put_queue(q);
 }
@@ -1165,7 +1164,7 @@ static bool bio_attempt_front_merge(struct request_queue *q,
  * true if merge was successful, otherwise false.
  */
 static bool attempt_plug_merge(struct task_struct *tsk, struct request_queue *q,
-			       struct bio *bio)
+			       struct bio *bio, unsigned int *request_count)
 {
 	struct blk_plug *plug;
 	struct request *rq;
@@ -1174,10 +1173,13 @@ static bool attempt_plug_merge(struct task_struct *tsk, struct request_queue *q,
 	plug = tsk->plug;
 	if (!plug)
 		goto out;
+	*request_count = 0;
 
 	list_for_each_entry_reverse(rq, &plug->list, queuelist) {
 		int el_ret;
 
+		(*request_count)++;
+
 		if (rq->q != q)
 			continue;
 
@@ -1217,6 +1219,7 @@ void blk_queue_bio(struct request_queue *q, struct bio *bio)
 	struct blk_plug *plug;
 	int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT;
 	struct request *req;
+	unsigned int request_count = 0;
 
 	/*
 	 * low level driver can indicate that it wants pages above a
@@ -1235,7 +1238,7 @@ void blk_queue_bio(struct request_queue *q, struct bio *bio)
 	 * Check if we can merge with the plugged list before grabbing
 	 * any locks.
 	 */
-	if (attempt_plug_merge(current, q, bio))
+	if (attempt_plug_merge(current, q, bio, &request_count))
 		return;
 
 	spin_lock_irq(q->queue_lock);
@@ -1300,11 +1303,10 @@ get_rq:
 			if (__rq->q != q)
 				plug->should_sort = 1;
 		}
+		if (request_count >= BLK_MAX_REQUEST_COUNT)
+			blk_flush_plug_list(plug, false);
 		list_add_tail(&req->queuelist, &plug->list);
-		plug->count++;
 		drive_stat_acct(req, 1);
-		if (plug->count >= BLK_MAX_REQUEST_COUNT)
-			blk_flush_plug_list(plug, false);
 	} else {
 		spin_lock_irq(q->queue_lock);
 		add_acct_request(q, req, where);
@@ -1675,6 +1677,7 @@ EXPORT_SYMBOL_GPL(blk_rq_check_limits);
 int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 {
 	unsigned long flags;
+	int where = ELEVATOR_INSERT_BACK;
 
 	if (blk_rq_check_limits(q, rq))
 		return -EIO;
@@ -1691,7 +1694,10 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 	 */
 	BUG_ON(blk_queued_rq(rq));
 
-	add_acct_request(q, rq, ELEVATOR_INSERT_BACK);
+	if (rq->cmd_flags & (REQ_FLUSH|REQ_FUA))
+		where = ELEVATOR_INSERT_FLUSH;
+
+	add_acct_request(q, rq, where);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 
 	return 0;
@@ -2248,7 +2254,7 @@ static bool blk_end_bidi_request(struct request *rq, int error,
  *     %false - we are done with this request
  *     %true  - still buffers pending for this request
  **/
-static bool __blk_end_bidi_request(struct request *rq, int error,
+bool __blk_end_bidi_request(struct request *rq, int error,
 				   unsigned int nr_bytes, unsigned int bidi_bytes)
 {
 	if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
@@ -2617,7 +2623,6 @@ void blk_start_plug(struct blk_plug *plug)
 	INIT_LIST_HEAD(&plug->list);
 	INIT_LIST_HEAD(&plug->cb_list);
 	plug->should_sort = 0;
-	plug->count = 0;
 
 	/*
 	 * If this is a nested plug, don't actually assign it. It will be
@@ -2701,7 +2706,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		return;
 
 	list_splice_init(&plug->list, &list);
-	plug->count = 0;
 
 	if (plug->should_sort) {
 		list_sort(NULL, &list, plug_rq_cmp);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index bb21e4c36f7..491eb30a242 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -95,11 +95,12 @@ static unsigned int blk_flush_policy(unsigned int fflags, struct request *rq)
 {
 	unsigned int policy = 0;
 
+	if (blk_rq_sectors(rq))
+		policy |= REQ_FSEQ_DATA;
+
 	if (fflags & REQ_FLUSH) {
 		if (rq->cmd_flags & REQ_FLUSH)
 			policy |= REQ_FSEQ_PREFLUSH;
-		if (blk_rq_sectors(rq))
-			policy |= REQ_FSEQ_DATA;
 		if (!(fflags & REQ_FUA) && (rq->cmd_flags & REQ_FUA))
 			policy |= REQ_FSEQ_POSTFLUSH;
 	}
@@ -122,7 +123,7 @@ static void blk_flush_restore_request(struct request *rq)
 
 	/* make @rq a normal request */
 	rq->cmd_flags &= ~REQ_FLUSH_SEQ;
-	rq->end_io = NULL;
+	rq->end_io = rq->flush.saved_end_io;
 }
 
 /**
@@ -300,9 +301,6 @@ void blk_insert_flush(struct request *rq)
 	unsigned int fflags = q->flush_flags;	/* may change, cache */
 	unsigned int policy = blk_flush_policy(fflags, rq);
 
-	BUG_ON(rq->end_io);
-	BUG_ON(!rq->bio || rq->bio != rq->biotail);
-
 	/*
 	 * @policy now records what operations need to be done.  Adjust
 	 * REQ_FLUSH and FUA for the driver.
@@ -312,6 +310,19 @@ void blk_insert_flush(struct request *rq)
 		rq->cmd_flags &= ~REQ_FUA;
 
 	/*
+	 * An empty flush handed down from a stacking driver may
+	 * translate into nothing if the underlying device does not
+	 * advertise a write-back cache.  In this case, simply
+	 * complete the request.
+	 */
+	if (!policy) {
+		__blk_end_bidi_request(rq, 0, 0, 0);
+		return;
+	}
+
+	BUG_ON(!rq->bio || rq->bio != rq->biotail);
+
+	/*
 	 * If there's data but flush is not necessary, the request can be
 	 * processed directly without going through flush machinery.  Queue
 	 * for normal execution.
@@ -319,6 +330,7 @@ void blk_insert_flush(struct request *rq)
 	if ((policy & REQ_FSEQ_DATA) &&
 	    !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
 		list_add_tail(&rq->queuelist, &q->queue_head);
+		blk_run_queue_async(q);
 		return;
 	}
 
@@ -329,6 +341,7 @@ void blk_insert_flush(struct request *rq)
 	memset(&rq->flush, 0, sizeof(rq->flush));
 	INIT_LIST_HEAD(&rq->flush.list);
 	rq->cmd_flags |= REQ_FLUSH_SEQ;
+	rq->flush.saved_end_io = rq->end_io; /* Usually NULL */
 	rq->end_io = flush_data_end_io;
 
 	blk_flush_complete_seq(rq, REQ_FSEQ_ACTIONS & ~policy, 0);
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 475fab809a8..1366a89d8e6 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -115,7 +115,7 @@ void __blk_complete_request(struct request *req)
 	/*
 	 * Select completion CPU
 	 */
-	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags) && req->cpu != -1) {
+	if (req->cpu != -1) {
 		ccpu = req->cpu;
 		if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) {
 			ccpu = blk_cpu_to_group(ccpu);
@@ -124,6 +124,14 @@ void __blk_complete_request(struct request *req)
 	} else
 		ccpu = cpu;
 
+	/*
+	 * If current CPU and requested CPU are in the same group, running
+	 * softirq in current CPU. One might concern this is just like
+	 * QUEUE_FLAG_SAME_FORCE, but actually not. blk_complete_request() is
+	 * running in interrupt handler, and currently I/O controller doesn't
+	 * support multiple interrupts, so current CPU is unique actually. This
+	 * avoids IPI sending from current CPU to the first CPU of a group.
+	 */
 	if (ccpu == cpu || ccpu == group_cpu) {
 		struct list_head *list;
 do_local:
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index adc923e9d1f..a8eff5f8b9c 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -258,11 +258,13 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
 
 	ret = queue_var_store(&val, page, count);
 	spin_lock_irq(q->queue_lock);
-	if (val) {
+	if (val == 2) {
 		queue_flag_set(QUEUE_FLAG_SAME_COMP, q);
-		if (val == 2)
-			queue_flag_set(QUEUE_FLAG_SAME_FORCE, q);
-	} else {
+		queue_flag_set(QUEUE_FLAG_SAME_FORCE, q);
+	} else if (val == 1) {
+		queue_flag_set(QUEUE_FLAG_SAME_COMP, q);
+		queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q);
+	} else if (val == 0) {
 		queue_flag_clear(QUEUE_FLAG_SAME_COMP, q);
 		queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q);
 	}
@@ -477,6 +479,11 @@ static void blk_release_queue(struct kobject *kobj)
 
 	blk_sync_queue(q);
 
+	if (q->elevator)
+		elevator_exit(q->elevator);
+
+	blk_throtl_exit(q);
+
 	if (rl->rq_pool)
 		mempool_destroy(rl->rq_pool);
 
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index f6a79412050..a19f58c6fc3 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -746,7 +746,7 @@ static bool tg_may_dispatch(struct throtl_data *td, struct throtl_grp *tg,
 static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
 {
 	bool rw = bio_data_dir(bio);
-	bool sync = bio->bi_rw & REQ_SYNC;
+	bool sync = rw_is_sync(bio->bi_rw);
 
 	/* Charge the bio to the group */
 	tg->bytes_disp[rw] += bio->bi_size;
@@ -1150,7 +1150,7 @@ int blk_throtl_bio(struct request_queue *q, struct bio **biop)
 
 		if (tg_no_rule_group(tg, rw)) {
 			blkiocg_update_dispatch_stats(&tg->blkg, bio->bi_size,
-					rw, bio->bi_rw & REQ_SYNC);
+					rw, rw_is_sync(bio->bi_rw));
 			rcu_read_unlock();
 			return 0;
 		}
diff --git a/block/blk.h b/block/blk.h
index d6586287adc..20b900a377c 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -17,6 +17,8 @@ int blk_rq_append_bio(struct request_queue *q, struct request *rq,
 		      struct bio *bio);
 void blk_dequeue_request(struct request *rq);
 void __blk_queue_free_tags(struct request_queue *q);
+bool __blk_end_bidi_request(struct request *rq, int error,
+			    unsigned int nr_bytes, unsigned int bidi_bytes);
 
 void blk_rq_timed_out_timer(unsigned long data);
 void blk_delete_timer(struct request *);
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
new file mode 100644
index 00000000000..6690e6e4103
--- /dev/null
+++ b/block/bsg-lib.c
@@ -0,0 +1,298 @@
+/*
+ *  BSG helper library
+ *
+ *  Copyright (C) 2008   James Smart, Emulex Corporation
+ *  Copyright (C) 2011   Red Hat, Inc.  All rights reserved.
+ *  Copyright (C) 2011   Mike Christie
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <linux/delay.h>
+#include <linux/scatterlist.h>
+#include <linux/bsg-lib.h>
+#include <linux/module.h>
+#include <scsi/scsi_cmnd.h>
+
+/**
+ * bsg_destroy_job - routine to teardown/delete a bsg job
+ * @job: bsg_job that is to be torn down
+ */
+static void bsg_destroy_job(struct bsg_job *job)
+{
+	put_device(job->dev);	/* release reference for the request */
+
+	kfree(job->request_payload.sg_list);
+	kfree(job->reply_payload.sg_list);
+	kfree(job);
+}
+
+/**
+ * bsg_job_done - completion routine for bsg requests
+ * @job: bsg_job that is complete
+ * @result: job reply result
+ * @reply_payload_rcv_len: length of payload recvd
+ *
+ * The LLD should call this when the bsg job has completed.
+ */
+void bsg_job_done(struct bsg_job *job, int result,
+		  unsigned int reply_payload_rcv_len)
+{
+	struct request *req = job->req;
+	struct request *rsp = req->next_rq;
+	int err;
+
+	err = job->req->errors = result;
+	if (err < 0)
+		/* we're only returning the result field in the reply */
+		job->req->sense_len = sizeof(u32);
+	else
+		job->req->sense_len = job->reply_len;
+	/* we assume all request payload was transferred, residual == 0 */
+	req->resid_len = 0;
+
+	if (rsp) {
+		WARN_ON(reply_payload_rcv_len > rsp->resid_len);
+
+		/* set reply (bidi) residual */
+		rsp->resid_len -= min(reply_payload_rcv_len, rsp->resid_len);
+	}
+	blk_complete_request(req);
+}
+EXPORT_SYMBOL_GPL(bsg_job_done);
+
+/**
+ * bsg_softirq_done - softirq done routine for destroying the bsg requests
+ * @rq: BSG request that holds the job to be destroyed
+ */
+static void bsg_softirq_done(struct request *rq)
+{
+	struct bsg_job *job = rq->special;
+
+	blk_end_request_all(rq, rq->errors);
+	bsg_destroy_job(job);
+}
+
+static int bsg_map_buffer(struct bsg_buffer *buf, struct request *req)
+{
+	size_t sz = (sizeof(struct scatterlist) * req->nr_phys_segments);
+
+	BUG_ON(!req->nr_phys_segments);
+
+	buf->sg_list = kzalloc(sz, GFP_KERNEL);
+	if (!buf->sg_list)
+		return -ENOMEM;
+	sg_init_table(buf->sg_list, req->nr_phys_segments);
+	buf->sg_cnt = blk_rq_map_sg(req->q, req, buf->sg_list);
+	buf->payload_len = blk_rq_bytes(req);
+	return 0;
+}
+
+/**
+ * bsg_create_job - create the bsg_job structure for the bsg request
+ * @dev: device that is being sent the bsg request
+ * @req: BSG request that needs a job structure
+ */
+static int bsg_create_job(struct device *dev, struct request *req)
+{
+	struct request *rsp = req->next_rq;
+	struct request_queue *q = req->q;
+	struct bsg_job *job;
+	int ret;
+
+	BUG_ON(req->special);
+
+	job = kzalloc(sizeof(struct bsg_job) + q->bsg_job_size, GFP_KERNEL);
+	if (!job)
+		return -ENOMEM;
+
+	req->special = job;
+	job->req = req;
+	if (q->bsg_job_size)
+		job->dd_data = (void *)&job[1];
+	job->request = req->cmd;
+	job->request_len = req->cmd_len;
+	job->reply = req->sense;
+	job->reply_len = SCSI_SENSE_BUFFERSIZE;	/* Size of sense buffer
+						 * allocated */
+	if (req->bio) {
+		ret = bsg_map_buffer(&job->request_payload, req);
+		if (ret)
+			goto failjob_rls_job;
+	}
+	if (rsp && rsp->bio) {
+		ret = bsg_map_buffer(&job->reply_payload, rsp);
+		if (ret)
+			goto failjob_rls_rqst_payload;
+	}
+	job->dev = dev;
+	/* take a reference for the request */
+	get_device(job->dev);
+	return 0;
+
+failjob_rls_rqst_payload:
+	kfree(job->request_payload.sg_list);
+failjob_rls_job:
+	kfree(job);
+	return -ENOMEM;
+}
+
+/*
+ * bsg_goose_queue - restart queue in case it was stopped
+ * @q: request q to be restarted
+ */
+void bsg_goose_queue(struct request_queue *q)
+{
+	if (!q)
+		return;
+
+	blk_run_queue_async(q);
+}
+EXPORT_SYMBOL_GPL(bsg_goose_queue);
+
+/**
+ * bsg_request_fn - generic handler for bsg requests
+ * @q: request queue to manage
+ *
+ * On error the create_bsg_job function should return a -Exyz error value
+ * that will be set to the req->errors.
+ *
+ * Drivers/subsys should pass this to the queue init function.
+ */
+void bsg_request_fn(struct request_queue *q)
+{
+	struct device *dev = q->queuedata;
+	struct request *req;
+	struct bsg_job *job;
+	int ret;
+
+	if (!get_device(dev))
+		return;
+
+	while (1) {
+		req = blk_fetch_request(q);
+		if (!req)
+			break;
+		spin_unlock_irq(q->queue_lock);
+
+		ret = bsg_create_job(dev, req);
+		if (ret) {
+			req->errors = ret;
+			blk_end_request_all(req, ret);
+			spin_lock_irq(q->queue_lock);
+			continue;
+		}
+
+		job = req->special;
+		ret = q->bsg_job_fn(job);
+		spin_lock_irq(q->queue_lock);
+		if (ret)
+			break;
+	}
+
+	spin_unlock_irq(q->queue_lock);
+	put_device(dev);
+	spin_lock_irq(q->queue_lock);
+}
+EXPORT_SYMBOL_GPL(bsg_request_fn);
+
+/**
+ * bsg_setup_queue - Create and add the bsg hooks so we can receive requests
+ * @dev: device to attach bsg device to
+ * @q: request queue setup by caller
+ * @name: device to give bsg device
+ * @job_fn: bsg job handler
+ * @dd_job_size: size of LLD data needed for each job
+ *
+ * The caller should have setup the reuqest queue with bsg_request_fn
+ * as the request_fn.
+ */
+int bsg_setup_queue(struct device *dev, struct request_queue *q,
+		    char *name, bsg_job_fn *job_fn, int dd_job_size)
+{
+	int ret;
+
+	q->queuedata = dev;
+	q->bsg_job_size = dd_job_size;
+	q->bsg_job_fn = job_fn;
+	queue_flag_set_unlocked(QUEUE_FLAG_BIDI, q);
+	blk_queue_softirq_done(q, bsg_softirq_done);
+	blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT);
+
+	ret = bsg_register_queue(q, dev, name, NULL);
+	if (ret) {
+		printk(KERN_ERR "%s: bsg interface failed to "
+		       "initialize - register queue\n", dev->kobj.name);
+		return ret;
+	}
+
+	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);
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 1f96ad6254f..16ace89613b 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -130,6 +130,8 @@ struct cfq_queue {
 	unsigned long slice_end;
 	long slice_resid;
 
+	/* pending priority requests */
+	int prio_pending;
 	/* number of requests that are on the dispatch list or inside driver */
 	int dispatched;
 
@@ -682,6 +684,9 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2,
 	if (rq_is_sync(rq1) != rq_is_sync(rq2))
 		return rq_is_sync(rq1) ? rq1 : rq2;
 
+	if ((rq1->cmd_flags ^ rq2->cmd_flags) & REQ_PRIO)
+		return rq1->cmd_flags & REQ_PRIO ? rq1 : rq2;
+
 	s1 = blk_rq_pos(rq1);
 	s2 = blk_rq_pos(rq2);
 
@@ -1209,6 +1214,9 @@ static void cfq_destroy_cfqg(struct cfq_data *cfqd, struct cfq_group *cfqg)
 
 	hlist_del_init(&cfqg->cfqd_node);
 
+	BUG_ON(cfqd->nr_blkcg_linked_grps <= 0);
+	cfqd->nr_blkcg_linked_grps--;
+
 	/*
 	 * Put the reference taken at the time of creation so that when all
 	 * queues are gone, group can be destroyed.
@@ -1604,6 +1612,10 @@ static void cfq_remove_request(struct request *rq)
 	cfqq->cfqd->rq_queued--;
 	cfq_blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg,
 					rq_data_dir(rq), rq_is_sync(rq));
+	if (rq->cmd_flags & REQ_PRIO) {
+		WARN_ON(!cfqq->prio_pending);
+		cfqq->prio_pending--;
+	}
 }
 
 static int cfq_merge(struct request_queue *q, struct request **req,
@@ -3357,6 +3369,13 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 		return true;
 
 	/*
+	 * So both queues are sync. Let the new request get disk time if
+	 * it's a metadata request and the current queue is doing regular IO.
+	 */
+	if ((rq->cmd_flags & REQ_PRIO) && !cfqq->prio_pending)
+		return true;
+
+	/*
 	 * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
 	 */
 	if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
@@ -3420,6 +3439,8 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	struct cfq_io_context *cic = RQ_CIC(rq);
 
 	cfqd->rq_queued++;
+	if (rq->cmd_flags & REQ_PRIO)
+		cfqq->prio_pending++;
 
 	cfq_update_io_thinktime(cfqd, cfqq, cic);
 	cfq_update_io_seektime(cfqd, cfqq, rq);
diff --git a/block/genhd.c b/block/genhd.c
index 5cb51c55f6d..e2f67902dd0 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1146,17 +1146,17 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 		cpu = part_stat_lock();
 		part_round_stats(cpu, hd);
 		part_stat_unlock();
-		seq_printf(seqf, "%4d %7d %s %lu %lu %llu "
-			   "%u %lu %lu %llu %u %u %u %u\n",
+		seq_printf(seqf, "%4d %7d %s %lu %lu %lu "
+			   "%u %lu %lu %lu %u %u %u %u\n",
 			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
 			   disk_name(gp, hd->partno, buf),
 			   part_stat_read(hd, ios[READ]),
 			   part_stat_read(hd, merges[READ]),
-			   (unsigned long long)part_stat_read(hd, sectors[READ]),
+			   part_stat_read(hd, sectors[READ]),
 			   jiffies_to_msecs(part_stat_read(hd, ticks[READ])),
 			   part_stat_read(hd, ios[WRITE]),
 			   part_stat_read(hd, merges[WRITE]),
-			   (unsigned long long)part_stat_read(hd, sectors[WRITE]),
+			   part_stat_read(hd, sectors[WRITE]),
 			   jiffies_to_msecs(part_stat_read(hd, ticks[WRITE])),
 			   part_in_flight(hd),
 			   jiffies_to_msecs(part_stat_read(hd, io_ticks)),