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

* 'for-linus' of git://git.kernel.dk/linux-block: (23 commits)
  Revert "cfq: Remove special treatment for metadata rqs."
  block: fix flush machinery for stacking drivers with differring flush flags
  block: improve rq_affinity placement
  blktrace: add FLUSH/FUA support
  Move some REQ flags to the common bio/request area
  allow blk_flush_policy to return REQ_FSEQ_DATA independent of *FLUSH
  xen/blkback: Make description more obvious.
  cfq-iosched: Add documentation about idling
  block: Make rq_affinity = 1 work as expected
  block: swim3: fix unterminated of_device_id table
  block/genhd.c: remove useless cast in diskstats_show()
  drivers/cdrom/cdrom.c: relax check on dvd manufacturer value
  drivers/block/drbd/drbd_nl.c: use bitmap_parse instead of __bitmap_parse
  bsg-lib: add module.h include
  cfq-iosched: Reduce linked group count upon group destruction
  blk-throttle: correctly determine sync bio
  loop: fix deadlock when sysfs and LOOP_CLR_FD race against each other
  loop: add BLK_DEV_LOOP_MIN_COUNT=%i to allow distros 0 pre-allocated loop devices
  loop: add management interface for on-demand device allocation
  loop: replace linked list of allocated devices with an idr index
  ...

Documentation/block/cfq-iosched.txt

@@ -43,3 +43,74 @@ If one sets slice_idle=0 and if storage supports NCQ, CFQ internally switches
 to IOPS mode and starts providing fairness in terms of number of requests
 dispatched. Note that this mode switching takes effect only for group
 scheduling. For non-cgroup users nothing should change.
+
+CFQ IO scheduler Idling Theory
+===============================
+Idling on a queue is primarily about waiting for the next request to come
+on same queue after completion of a request. In this process CFQ will not
+dispatch requests from other cfq queues even if requests are pending there.
+
+The rationale behind idling is that it can cut down on number of seeks
+on rotational media. For example, if a process is doing dependent
+sequential reads (next read will come on only after completion of previous
+one), then not dispatching request from other queue should help as we
+did not move the disk head and kept on dispatching sequential IO from
+one queue.
+
+CFQ has following service trees and various queues are put on these trees.
+
+	sync-idle	sync-noidle	async
+
+All cfq queues doing synchronous sequential IO go on to sync-idle tree.
+On this tree we idle on each queue individually.
+
+All synchronous non-sequential queues go on sync-noidle tree. Also any
+request which are marked with REQ_NOIDLE go on this service tree. On this
+tree we do not idle on individual queues instead idle on the whole group
+of queues or the tree. So if there are 4 queues waiting for IO to dispatch
+we will idle only once last queue has dispatched the IO and there is
+no more IO on this service tree.
+
+All async writes go on async service tree. There is no idling on async
+queues.
+
+CFQ has some optimizations for SSDs and if it detects a non-rotational
+media which can support higher queue depth (multiple requests at in
+flight at a time), then it cuts down on idling of individual queues and
+all the queues move to sync-noidle tree and only tree idle remains. This
+tree idling provides isolation with buffered write queues on async tree.
+
+FAQ
+===
+Q1. Why to idle at all on queues marked with REQ_NOIDLE.
+
+A1. We only do tree idle (all queues on sync-noidle tree) on queues marked
+    with REQ_NOIDLE. This helps in providing isolation with all the sync-idle
+    queues. Otherwise in presence of many sequential readers, other
+    synchronous IO might not get fair share of disk.
+
+    For example, if there are 10 sequential readers doing IO and they get
+    100ms each. If a REQ_NOIDLE request comes in, it will be scheduled
+    roughly after 1 second. If after completion of REQ_NOIDLE request we
+    do not idle, and after a couple of milli seconds a another REQ_NOIDLE
+    request comes in, again it will be scheduled after 1second. Repeat it
+    and notice how a workload can lose its disk share and suffer due to
+    multiple sequential readers.
+
+    fsync can generate dependent IO where bunch of data is written in the
+    context of fsync, and later some journaling data is written. Journaling
+    data comes in only after fsync has finished its IO (atleast for ext4
+    that seemed to be the case). Now if one decides not to idle on fsync
+    thread due to REQ_NOIDLE, then next journaling write will not get
+    scheduled for another second. A process doing small fsync, will suffer
+    badly in presence of multiple sequential readers.
+
+    Hence doing tree idling on threads using REQ_NOIDLE flag on requests
+    provides isolation from multiple sequential readers and at the same
+    time we do not idle on individual threads.
+
+Q2. When to specify REQ_NOIDLE
+A2. I would think whenever one is doing synchronous write and not expecting
+    more writes to be dispatched from same context soon, should be able
+    to specify REQ_NOIDLE on writes and that probably should work well for
+    most of the cases.

Documentation/kernel-parameters.txt

@@ -1350,9 +1350,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			it is equivalent to "nosmp", which also disables
 			the IO APIC.
 
-	max_loop=	[LOOP] Maximum number of loopback devices that can
-			be mounted
-			Format: <1-256>
+	max_loop=	[LOOP] The number of loop block devices that get
+	(loop.max_loop)	unconditionally pre-created at init time. The default
+			number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead
+			of statically allocating a predefined number, loop
+			devices can be requested on-demand with the
+			/dev/loop-control interface.
 
 	mcatest=	[IA-64]
 

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---

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

block/blk-core.c

@@ -1702,6 +1702,7 @@ 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;
@@ -1718,7 +1719,10 @@ 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;
@@ -2275,7 +2279,7 @@ 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))

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.
@@ -311,6 +309,19 @@ void blk_insert_flush(struct request *rq)
 	if (!(fflags & REQ_FUA))
 		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
@@ -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);

block/blk-softirq.c

@@ -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:

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;
 		}

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 *);

block/bsg-lib.c

+/*
+ *  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);

block/cfq-iosched.c

@@ -130,6 +130,8 @@ struct cfq_queue {
 	unsigned long slice_end;
 	long slice_resid;
 
+	/* pending metadata requests */
+	int meta_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_META)
+		return rq1->cmd_flags & REQ_META ? 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_META) {
+		WARN_ON(!cfqq->meta_pending);
+		cfqq->meta_pending--;
+	}
 }
 
 static int cfq_merge(struct request_queue *q, struct request **req,
@@ -3356,6 +3368,13 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	    RB_EMPTY_ROOT(&cfqq->sort_list))
 		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_META) && !cfqq->meta_pending)
+		return true;
+
 	/*
 	 * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice.
 	 */
@@ -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_META)
+		cfqq->meta_pending++;
 
 	cfq_update_io_thinktime(cfqd, cfqq, cic);
 	cfq_update_io_seektime(cfqd, cfqq, rq);

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)),

drivers/block/Kconfig

@@ -256,6 +256,21 @@ config BLK_DEV_LOOP
 
 	  Most users will answer N here.
 
+config BLK_DEV_LOOP_MIN_COUNT
+	int "Number of loop devices to pre-create at init time"
+	depends on BLK_DEV_LOOP
+	default 8
+	help
+	  Static number of loop devices to be unconditionally pre-created
+	  at init time.
+
+	  This default value can be overwritten on the kernel command
+	  line or with module-parameter loop.max_loop.
+
+	  The historic default is 8. If a late 2011 version of losetup(8)
+	  is used, it can be set to 0, since needed loop devices can be
+	  dynamically allocated with the /dev/loop-control interface.
+
 config BLK_DEV_CRYPTOLOOP
 	tristate "Cryptoloop Support"
 	select CRYPTO
@@ -471,7 +486,7 @@ config XEN_BLKDEV_FRONTEND
 	  in another domain which drives the actual block device.
 
 config XEN_BLKDEV_BACKEND
-	tristate "Block-device backend driver"
+	tristate "Xen block-device backend driver"
 	depends on XEN_BACKEND
 	help
 	  The block-device backend driver allows the kernel to export its

drivers/block/drbd/drbd_nl.c

@@ -1829,10 +1829,10 @@ static int drbd_nl_syncer_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *n
 
 	/* silently ignore cpu mask on UP kernel */
 	if (nr_cpu_ids > 1 && sc.cpu_mask[0] != 0) {
-		err = __bitmap_parse(sc.cpu_mask, 32, 0,
+		err = bitmap_parse(sc.cpu_mask, 32,
 				cpumask_bits(new_cpu_mask), nr_cpu_ids);
 		if (err) {
-			dev_warn(DEV, "__bitmap_parse() failed with %d\n", err);
+			dev_warn(DEV, "bitmap_parse() failed with %d\n", err);
 			retcode = ERR_CPU_MASK_PARSE;
 			goto fail;
 		}

drivers/block/swim3.c

@@ -1184,6 +1184,7 @@ static struct of_device_id swim3_match[] =
 	{
 	.compatible	= "swim3"
 	},
+	{ /* end of list */ }
 };
 
 static struct macio_driver swim3_driver =

drivers/block/xen-blkfront.c

@@ -123,8 +123,8 @@ static DEFINE_SPINLOCK(minor_lock);
 #define BLKIF_MINOR_EXT(dev) ((dev)&(~EXTENDED))
 #define EMULATED_HD_DISK_MINOR_OFFSET (0)
 #define EMULATED_HD_DISK_NAME_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET / 256)
-#define EMULATED_SD_DISK_MINOR_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET + (4 * 16))
-#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_HD_DISK_NAME_OFFSET + 4)
+#define EMULATED_SD_DISK_MINOR_OFFSET (0)
+#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_SD_DISK_MINOR_OFFSET / 256)
 
 #define DEV_NAME	"xvd"	/* name in /dev */
 
@@ -529,7 +529,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
 		minor = BLKIF_MINOR_EXT(info->vdevice);
 		nr_parts = PARTS_PER_EXT_DISK;
 		offset = minor / nr_parts;
-		if (xen_hvm_domain() && offset <= EMULATED_HD_DISK_NAME_OFFSET + 4)
+		if (xen_hvm_domain() && offset < EMULATED_HD_DISK_NAME_OFFSET + 4)
 			printk(KERN_WARNING "blkfront: vdevice 0x%x might conflict with "
 					"emulated IDE disks,\n\t choose an xvd device name"
 					"from xvde on\n", info->vdevice);

drivers/cdrom/cdrom.c

@@ -1929,11 +1929,17 @@ static int dvd_read_manufact(struct cdrom_device_info *cdi, dvd_struct *s,
 		goto out;
 
 	s->manufact.len = buf[0] << 8 | buf[1];
-	if (s->manufact.len < 0 || s->manufact.len > 2048) {
+	if (s->manufact.len < 0) {
 		cdinfo(CD_WARNING, "Received invalid manufacture info length"
 				   " (%d)\n", s->manufact.len);
 		ret = -EIO;
 	} else {
+		if (s->manufact.len > 2048) {
+			cdinfo(CD_WARNING, "Received invalid manufacture info "
+					"length (%d): truncating to 2048\n",
+					s->manufact.len);
+			s->manufact.len = 2048;
+		}
 		memcpy(s->manufact.value, &buf[4], s->manufact.len);
 	}
 

include/linux/blk_types.h

@@ -125,7 +125,11 @@ enum rq_flag_bits {
 	__REQ_SYNC,		/* request is sync (sync write or read) */
 	__REQ_META,		/* metadata io request */
 	__REQ_DISCARD,		/* request to discard sectors */
+	__REQ_SECURE,		/* secure discard (used with __REQ_DISCARD) */
+
 	__REQ_NOIDLE,		/* don't anticipate more IO after this one */
+	__REQ_FUA,		/* forced unit access */
+	__REQ_FLUSH,		/* request for cache flush */
 
 	/* bio only flags */
 	__REQ_RAHEAD,		/* read ahead, can fail anytime */
@@ -135,7 +139,6 @@ enum rq_flag_bits {
 	/* request only flags */
 	__REQ_SORTED,		/* elevator knows about this request */
 	__REQ_SOFTBARRIER,	/* may not be passed by ioscheduler */
-	__REQ_FUA,		/* forced unit access */
 	__REQ_NOMERGE,		/* don't touch this for merging */
 	__REQ_STARTED,		/* drive already may have started this one */
 	__REQ_DONTPREP,		/* don't call prep for this one */
@@ -146,11 +149,9 @@ enum rq_flag_bits {
 	__REQ_PREEMPT,		/* set for "ide_preempt" requests */
 	__REQ_ALLOCED,		/* request came from our alloc pool */
 	__REQ_COPY_USER,	/* contains copies of user pages */
-	__REQ_FLUSH,		/* request for cache flush */
 	__REQ_FLUSH_SEQ,	/* request for flush sequence */
 	__REQ_IO_STAT,		/* account I/O stat */
 	__REQ_MIXED_MERGE,	/* merge of different types, fail separately */
-	__REQ_SECURE,		/* secure discard (used with __REQ_DISCARD) */
 	__REQ_NR_BITS,		/* stops here */
 };
 

include/linux/blkdev.h

@@ -30,6 +30,7 @@ struct request_pm_state;
 struct blk_trace;
 struct request;
 struct sg_io_hdr;
+struct bsg_job;
 
 #define BLKDEV_MIN_RQ	4
 #define BLKDEV_MAX_RQ	128	/* Default maximum */
@@ -117,6 +118,7 @@ struct request {
 		struct {
 			unsigned int		seq;
 			struct list_head	list;
+			rq_end_io_fn		*saved_end_io;
 		} flush;
 	};
 
@@ -209,6 +211,7 @@ typedef int (merge_bvec_fn) (struct request_queue *, struct bvec_merge_data *,
 typedef void (softirq_done_fn)(struct request *);
 typedef int (dma_drain_needed_fn)(struct request *);
 typedef int (lld_busy_fn) (struct request_queue *q);
+typedef int (bsg_job_fn) (struct bsg_job *);
 
 enum blk_eh_timer_return {
 	BLK_EH_NOT_HANDLED,
@@ -375,6 +378,8 @@ struct request_queue {
 	struct mutex		sysfs_lock;
 
 #if defined(CONFIG_BLK_DEV_BSG)
+	bsg_job_fn		*bsg_job_fn;
+	int			bsg_job_size;
 	struct bsg_class_device bsg_dev;
 #endif
 

include/linux/blktrace_api.h

@@ -14,7 +14,7 @@
 enum blktrace_cat {
 	BLK_TC_READ	= 1 << 0,	/* reads */
 	BLK_TC_WRITE	= 1 << 1,	/* writes */
-	BLK_TC_BARRIER	= 1 << 2,	/* barrier */
+	BLK_TC_FLUSH	= 1 << 2,	/* flush */
 	BLK_TC_SYNC	= 1 << 3,	/* sync IO */
 	BLK_TC_SYNCIO	= BLK_TC_SYNC,
 	BLK_TC_QUEUE	= 1 << 4,	/* queueing/merging */
@@ -28,8 +28,9 @@ enum blktrace_cat {
 	BLK_TC_META	= 1 << 12,	/* metadata */
 	BLK_TC_DISCARD	= 1 << 13,	/* discard requests */
 	BLK_TC_DRV_DATA	= 1 << 14,	/* binary per-driver data */
+	BLK_TC_FUA	= 1 << 15,	/* fua requests */
 
-	BLK_TC_END	= 1 << 15,	/* only 16-bits, reminder */
+	BLK_TC_END	= 1 << 15,	/* we've run out of bits! */
 };
 
 #define BLK_TC_SHIFT		(16)

include/linux/bsg-lib.h

+/*
+ *  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
+ *
+ */
+#ifndef _BLK_BSG_
+#define _BLK_BSG_
+
+#include <linux/blkdev.h>
+
+struct request;
+struct device;
+struct scatterlist;
+struct request_queue;
+
+struct bsg_buffer {
+	unsigned int payload_len;
+	int sg_cnt;
+	struct scatterlist *sg_list;
+};
+
+struct bsg_job {
+	struct device *dev;
+	struct request *req;
+
+	/* Transport/driver specific request/reply structs */
+	void *request;
+	void *reply;
+
+	unsigned int request_len;
+	unsigned int reply_len;
+	/*
+	 * On entry : reply_len indicates the buffer size allocated for
+	 * the reply.
+	 *
+	 * Upon completion : the message handler must set reply_len
+	 *  to indicates the size of the reply to be returned to the
+	 *  caller.
+	 */
+
+	/* DMA payloads for the request/response */
+	struct bsg_buffer request_payload;
+	struct bsg_buffer reply_payload;
+
+	void *dd_data;		/* Used for driver-specific storage */
+};
+
+void bsg_job_done(struct bsg_job *job, int result,
+		  unsigned int reply_payload_rcv_len);
+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/loop.h

@@ -64,7 +64,6 @@ struct loop_device {
 
 	struct request_queue	*lo_queue;
 	struct gendisk		*lo_disk;
-	struct list_head	lo_list;
 };
 
 #endif /* __KERNEL__ */
@@ -161,4 +160,8 @@ int loop_unregister_transfer(int number);
 #define LOOP_CHANGE_FD		0x4C06
 #define LOOP_SET_CAPACITY	0x4C07
 
+/* /dev/loop-control interface */
+#define LOOP_CTL_ADD		0x4C80
+#define LOOP_CTL_REMOVE		0x4C81
+#define LOOP_CTL_GET_FREE	0x4C82
 #endif

include/linux/miscdevice.h

@@ -40,6 +40,7 @@
 #define BTRFS_MINOR		234
 #define AUTOFS_MINOR		235
 #define MAPPER_CTRL_MINOR	236
+#define LOOP_CTRL_MINOR		237
 #define MISC_DYNAMIC_MINOR	255
 
 struct device;

include/trace/events/block.h

@@ -8,6 +8,8 @@
 #include <linux/blkdev.h>
 #include <linux/tracepoint.h>
 
+#define RWBS_LEN	8
+
 DECLARE_EVENT_CLASS(block_rq_with_error,
 
 	TP_PROTO(struct request_queue *q, struct request *rq),
@@ -19,7 +21,7 @@ DECLARE_EVENT_CLASS(block_rq_with_error,
 		__field(  sector_t,	sector			)
 		__field(  unsigned int,	nr_sector		)
 		__field(  int,		errors			)
-		__array(  char,		rwbs,	6		)
+		__array(  char,		rwbs,	RWBS_LEN	)
 		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
 	),
 
@@ -104,7 +106,7 @@ DECLARE_EVENT_CLASS(block_rq,
 		__field(  sector_t,	sector			)
 		__field(  unsigned int,	nr_sector		)
 		__field(  unsigned int,	bytes			)
-		__array(  char,		rwbs,	6		)
+		__array(  char,		rwbs,	RWBS_LEN	)
 		__array(  char,         comm,   TASK_COMM_LEN   )
 		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
 	),
@@ -183,7 +185,7 @@ TRACE_EVENT(block_bio_bounce,
 		__field( dev_t,		dev			)
 		__field( sector_t,	sector			)
 		__field( unsigned int,	nr_sector		)
-		__array( char,		rwbs,	6		)
+		__array( char,		rwbs,	RWBS_LEN	)
 		__array( char,		comm,	TASK_COMM_LEN	)
 	),
 
@@ -222,7 +224,7 @@ TRACE_EVENT(block_bio_complete,
 		__field( sector_t,	sector		)
 		__field( unsigned,	nr_sector	)
 		__field( int,		error		)
-		__array( char,		rwbs,	6	)
+		__array( char,		rwbs,	RWBS_LEN)
 	),
 
 	TP_fast_assign(
@@ -249,7 +251,7 @@ DECLARE_EVENT_CLASS(block_bio,
 		__field( dev_t,		dev			)
 		__field( sector_t,	sector			)
 		__field( unsigned int,	nr_sector		)
-		__array( char,		rwbs,	6		)
+		__array( char,		rwbs,	RWBS_LEN	)
 		__array( char,		comm,	TASK_COMM_LEN	)
 	),
 
@@ -321,7 +323,7 @@ DECLARE_EVENT_CLASS(block_get_rq,
 		__field( dev_t,		dev			)
 		__field( sector_t,	sector			)
 		__field( unsigned int,	nr_sector		)
-		__array( char,		rwbs,	6		)
+		__array( char,		rwbs,	RWBS_LEN	)
 		__array( char,		comm,	TASK_COMM_LEN	)
         ),
 
@@ -456,7 +458,7 @@ TRACE_EVENT(block_split,
 		__field( dev_t,		dev				)
 		__field( sector_t,	sector				)
 		__field( sector_t,	new_sector			)
-		__array( char,		rwbs,		6		)
+		__array( char,		rwbs,		RWBS_LEN	)
 		__array( char,		comm,		TASK_COMM_LEN	)
 	),
 
@@ -498,7 +500,7 @@ TRACE_EVENT(block_bio_remap,
 		__field( unsigned int,	nr_sector	)
 		__field( dev_t,		old_dev		)
 		__field( sector_t,	old_sector	)
-		__array( char,		rwbs,	6	)
+		__array( char,		rwbs,	RWBS_LEN)
 	),
 
 	TP_fast_assign(
@@ -542,7 +544,7 @@ TRACE_EVENT(block_rq_remap,
 		__field( unsigned int,	nr_sector	)
 		__field( dev_t,		old_dev		)
 		__field( sector_t,	old_sector	)
-		__array( char,		rwbs,	6	)
+		__array( char,		rwbs,	RWBS_LEN)
 	),
 
 	TP_fast_assign(

kernel/trace/blktrace.c

@@ -206,6 +206,8 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	what |= MASK_TC_BIT(rw, RAHEAD);
 	what |= MASK_TC_BIT(rw, META);
 	what |= MASK_TC_BIT(rw, DISCARD);
+	what |= MASK_TC_BIT(rw, FLUSH);
+	what |= MASK_TC_BIT(rw, FUA);
 
 	pid = tsk->pid;
 	if (act_log_check(bt, what, sector, pid))
@@ -1054,6 +1056,9 @@ static void fill_rwbs(char *rwbs, const struct blk_io_trace *t)
 		goto out;
 	}
 
+	if (tc & BLK_TC_FLUSH)
+		rwbs[i++] = 'F';
+
 	if (tc & BLK_TC_DISCARD)
 		rwbs[i++] = 'D';
 	else if (tc & BLK_TC_WRITE)
@@ -1063,10 +1068,10 @@ static void fill_rwbs(char *rwbs, const struct blk_io_trace *t)
 	else
 		rwbs[i++] = 'N';
 
+	if (tc & BLK_TC_FUA)
+		rwbs[i++] = 'F';
 	if (tc & BLK_TC_AHEAD)
 		rwbs[i++] = 'A';
-	if (tc & BLK_TC_BARRIER)
-		rwbs[i++] = 'B';
 	if (tc & BLK_TC_SYNC)
 		rwbs[i++] = 'S';
 	if (tc & BLK_TC_META)
@@ -1132,7 +1137,7 @@ typedef int (blk_log_action_t) (struct trace_iterator *iter, const char *act);
 
 static int blk_log_action_classic(struct trace_iterator *iter, const char *act)
 {
-	char rwbs[6];
+	char rwbs[RWBS_LEN];
 	unsigned long long ts  = iter->ts;
 	unsigned long nsec_rem = do_div(ts, NSEC_PER_SEC);
 	unsigned secs	       = (unsigned long)ts;
@@ -1148,7 +1153,7 @@ static int blk_log_action_classic(struct trace_iterator *iter, const char *act)
 
 static int blk_log_action(struct trace_iterator *iter, const char *act)
 {
-	char rwbs[6];
+	char rwbs[RWBS_LEN];
 	const struct blk_io_trace *t = te_blk_io_trace(iter->ent);
 
 	fill_rwbs(rwbs, t);
@@ -1561,7 +1566,7 @@ static const struct {
 } mask_maps[] = {
 	{ BLK_TC_READ,		"read"		},
 	{ BLK_TC_WRITE,		"write"		},
-	{ BLK_TC_BARRIER,	"barrier"	},
+	{ BLK_TC_FLUSH,		"flush"		},
 	{ BLK_TC_SYNC,		"sync"		},
 	{ BLK_TC_QUEUE,		"queue"		},
 	{ BLK_TC_REQUEUE,	"requeue"	},
@@ -1573,6 +1578,7 @@ static const struct {
 	{ BLK_TC_META,		"meta"		},
 	{ BLK_TC_DISCARD,	"discard"	},
 	{ BLK_TC_DRV_DATA,	"drv_data"	},
+	{ BLK_TC_FUA,		"fua"		},
 };
 
 static int blk_trace_str2mask(const char *str)
@@ -1788,6 +1794,9 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
 {
 	int i = 0;
 
+	if (rw & REQ_FLUSH)
+		rwbs[i++] = 'F';
+
 	if (rw & WRITE)
 		rwbs[i++] = 'W';
 	else if (rw & REQ_DISCARD)
@@ -1797,6 +1806,8 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes)
 	else
 		rwbs[i++] = 'N';
 
+	if (rw & REQ_FUA)
+		rwbs[i++] = 'F';
 	if (rw & REQ_RAHEAD)
 		rwbs[i++] = 'A';
 	if (rw & REQ_SYNC)