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
  ...

10 files changed, 371 insertions, 14 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 60be1e0455da..e97934eececa 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 0fec4b3fab51..514c6e4f427a 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-core.c b/block/blk-core.c
index b627558c461f..90e1ffdeb415 100644
--- a/block/blk-core.c
+++ b/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))
diff --git a/block/blk-flush.c b/block/blk-flush.c
index bb21e4c36f70..491eb30a242d 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 475fab809a80..58340d0cb23a 100644
--- a/block/blk-softirq.c
+++ b/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:
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index f6a794120505..a19f58c6fc3a 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 d6586287adc9..20b900a377c9 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 000000000000..6690e6e41037
--- /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 1f96ad6254f1..a33bd4377c61 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 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,
@@ -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_META) && !cfqq->meta_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_META)
+                cfqq->meta_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 5cb51c55f6d8..e2f67902dd02 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)),