Merge branch 'for-linus' of git://brick.kernel.dk/data/git/linux-2.6-block

* 'for-linus' of git://brick.kernel.dk/data/git/linux-2.6-block:
  [PATCH] block: document io scheduler allow_merge_fn hook
  [PATCH] cfq-iosched: don't allow sync merges across queues
  [PATCH] Fixup blk_rq_unmap_user() API
  [PATCH] __blk_rq_unmap_user() fails to return error
  [PATCH] __blk_rq_map_user() doesn't need to grab the queue_lock
  [PATCH] Remove queue merging hooks
  [PATCH] ->nr_sectors and ->hard_nr_sectors are not used for BLOCK_PC requests
  [PATCH] cciss: fix XFER_READ/XFER_WRITE in do_cciss_request
  [PATCH] cciss: set default raid level when reading geometry fails

10 files changed, 107 insertions, 56 deletions

diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt
index c6c9a9c..3adaace 100644
--- a/Documentation/block/biodoc.txt
+++ b/Documentation/block/biodoc.txt
@@ -946,6 +946,13 @@ elevator_merged_fn		called when a request in the scheduler has been
 				scheduler for example, to reposition the request
 				if its sorting order has changed.
 
+elevator_allow_merge_fn		called whenever the block layer determines
+				that a bio can be merged into an existing
+				request safely. The io scheduler may still
+				want to stop a merge at this point if it
+				results in some sort of conflict internally,
+				this hook allows it to do that.
+
 elevator_dispatch_fn		fills the dispatch queue with ready requests.
 				I/O schedulers are free to postpone requests by
 				not filling the dispatch queue unless @force
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 533a293..9fc5eaf 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -568,6 +568,38 @@ cfq_merged_requests(request_queue_t *q, struct request *rq,
 	cfq_remove_request(next);
 }
 
+static int cfq_allow_merge(request_queue_t *q, struct request *rq,
+			   struct bio *bio)
+{
+	struct cfq_data *cfqd = q->elevator->elevator_data;
+	const int rw = bio_data_dir(bio);
+	struct cfq_queue *cfqq;
+	pid_t key;
+
+	/*
+	 * If bio is async or a write, always allow merge
+	 */
+	if (!bio_sync(bio) || rw == WRITE)
+		return 1;
+
+	/*
+	 * bio is sync. if request is not, disallow.
+	 */
+	if (!rq_is_sync(rq))
+		return 0;
+
+	/*
+	 * Ok, both bio and request are sync. Allow merge if they are
+	 * from the same queue.
+	 */
+	key = cfq_queue_pid(current, rw, 1);
+	cfqq = cfq_find_cfq_hash(cfqd, key, current->ioprio);
+	if (cfqq != RQ_CFQQ(rq))
+		return 0;
+
+	return 1;
+}
+
 static inline void
 __cfq_set_active_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
@@ -2125,6 +2157,7 @@ static struct elevator_type iosched_cfq = {
 		.elevator_merge_fn = 		cfq_merge,
 		.elevator_merged_fn =		cfq_merged_request,
 		.elevator_merge_req_fn =	cfq_merged_requests,
+		.elevator_allow_merge_fn =	cfq_allow_merge,
 		.elevator_dispatch_fn =		cfq_dispatch_requests,
 		.elevator_add_req_fn =		cfq_insert_request,
 		.elevator_activate_req_fn =	cfq_activate_request,
diff --git a/block/elevator.c b/block/elevator.c
index c0063f3..62c7a30 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -51,6 +51,21 @@ static const int elv_hash_shift = 6;
 #define ELV_ON_HASH(rq)		(!hlist_unhashed(&(rq)->hash))
 
 /*
+ * Query io scheduler to see if the current process issuing bio may be
+ * merged with rq.
+ */
+static int elv_iosched_allow_merge(struct request *rq, struct bio *bio)
+{
+	request_queue_t *q = rq->q;
+	elevator_t *e = q->elevator;
+
+	if (e->ops->elevator_allow_merge_fn)
+		return e->ops->elevator_allow_merge_fn(q, rq, bio);
+
+	return 1;
+}
+
+/*
  * can we safely merge with this request?
  */
 inline int elv_rq_merge_ok(struct request *rq, struct bio *bio)
@@ -65,12 +80,15 @@ inline int elv_rq_merge_ok(struct request *rq, struct bio *bio)
 		return 0;
 
 	/*
-	 * same device and no special stuff set, merge is ok
+	 * must be same device and not a special request
 	 */
-	if (rq->rq_disk == bio->bi_bdev->bd_disk && !rq->special)
-		return 1;
+	if (rq->rq_disk != bio->bi_bdev->bd_disk || !rq->special)
+		return 0;
 
-	return 0;
+	if (!elv_iosched_allow_merge(rq, bio))
+		return 0;
+
+	return 1;
 }
 EXPORT_SYMBOL(elv_rq_merge_ok);
 
diff --git a/block/ll_rw_blk.c b/block/ll_rw_blk.c
index 79807db..e07c079 100644
--- a/block/ll_rw_blk.c
+++ b/block/ll_rw_blk.c
@@ -1405,8 +1405,7 @@ static inline int ll_new_hw_segment(request_queue_t *q,
 	return 1;
 }
 
-static int ll_back_merge_fn(request_queue_t *q, struct request *req, 
-			    struct bio *bio)
+int ll_back_merge_fn(request_queue_t *q, struct request *req, struct bio *bio)
 {
 	unsigned short max_sectors;
 	int len;
@@ -1442,6 +1441,7 @@ static int ll_back_merge_fn(request_queue_t *q, struct request *req,
 
 	return ll_new_hw_segment(q, req, bio);
 }
+EXPORT_SYMBOL(ll_back_merge_fn);
 
 static int ll_front_merge_fn(request_queue_t *q, struct request *req, 
 			     struct bio *bio)
@@ -1912,9 +1912,6 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 	}
 
 	q->request_fn		= rfn;
-	q->back_merge_fn       	= ll_back_merge_fn;
-	q->front_merge_fn      	= ll_front_merge_fn;
-	q->merge_requests_fn	= ll_merge_requests_fn;
 	q->prep_rq_fn		= NULL;
 	q->unplug_fn		= generic_unplug_device;
 	q->queue_flags		= (1 << QUEUE_FLAG_CLUSTER);
@@ -2350,40 +2347,29 @@ static int __blk_rq_map_user(request_queue_t *q, struct request *rq,
 	else
 		bio = bio_copy_user(q, uaddr, len, reading);
 
-	if (IS_ERR(bio)) {
+	if (IS_ERR(bio))
 		return PTR_ERR(bio);
-	}
 
 	orig_bio = bio;
 	blk_queue_bounce(q, &bio);
+
 	/*
 	 * We link the bounce buffer in and could have to traverse it
 	 * later so we have to get a ref to prevent it from being freed
 	 */
 	bio_get(bio);
 
-	/*
-	 * for most (all? don't know of any) queues we could
-	 * skip grabbing the queue lock here. only drivers with
-	 * funky private ->back_merge_fn() function could be
-	 * problematic.
-	 */
-	spin_lock_irq(q->queue_lock);
 	if (!rq->bio)
 		blk_rq_bio_prep(q, rq, bio);
-	else if (!q->back_merge_fn(q, rq, bio)) {
+	else if (!ll_back_merge_fn(q, rq, bio)) {
 		ret = -EINVAL;
-		spin_unlock_irq(q->queue_lock);
 		goto unmap_bio;
 	} else {
 		rq->biotail->bi_next = bio;
 		rq->biotail = bio;
 
-		rq->nr_sectors += bio_sectors(bio);
-		rq->hard_nr_sectors = rq->nr_sectors;
 		rq->data_len += bio->bi_size;
 	}
-	spin_unlock_irq(q->queue_lock);
 
 	return bio->bi_size;
 
@@ -2419,6 +2405,7 @@ int blk_rq_map_user(request_queue_t *q, struct request *rq, void __user *ubuf,
 		    unsigned long len)
 {
 	unsigned long bytes_read = 0;
+	struct bio *bio = NULL;
 	int ret;
 
 	if (len > (q->max_hw_sectors << 9))
@@ -2445,6 +2432,8 @@ int blk_rq_map_user(request_queue_t *q, struct request *rq, void __user *ubuf,
 		ret = __blk_rq_map_user(q, rq, ubuf, map_len);
 		if (ret < 0)
 			goto unmap_rq;
+		if (!bio)
+			bio = rq->bio;
 		bytes_read += ret;
 		ubuf += ret;
 	}
@@ -2452,7 +2441,7 @@ int blk_rq_map_user(request_queue_t *q, struct request *rq, void __user *ubuf,
 	rq->buffer = rq->data = NULL;
 	return 0;
 unmap_rq:
-	blk_rq_unmap_user(rq);
+	blk_rq_unmap_user(bio);
 	return ret;
 }
 
@@ -2509,27 +2498,33 @@ EXPORT_SYMBOL(blk_rq_map_user_iov);
 
 /**
  * blk_rq_unmap_user - unmap a request with user data
- * @rq:		rq to be unmapped
+ * @bio:	       start of bio list
  *
  * Description:
- *    Unmap a rq previously mapped by blk_rq_map_user().
- *    rq->bio must be set to the original head of the request.
+ *    Unmap a rq previously mapped by blk_rq_map_user(). The caller must
+ *    supply the original rq->bio from the blk_rq_map_user() return, since
+ *    the io completion may have changed rq->bio.
  */
-int blk_rq_unmap_user(struct request *rq)
+int blk_rq_unmap_user(struct bio *bio)
 {
-	struct bio *bio, *mapped_bio;
+	struct bio *mapped_bio;
+	int ret = 0, ret2;
 
-	while ((bio = rq->bio)) {
-		if (bio_flagged(bio, BIO_BOUNCED))
+	while (bio) {
+		mapped_bio = bio;
+		if (unlikely(bio_flagged(bio, BIO_BOUNCED)))
 			mapped_bio = bio->bi_private;
-		else
-			mapped_bio = bio;
 
-		__blk_rq_unmap_user(mapped_bio);
-		rq->bio = bio->bi_next;
-		bio_put(bio);
+		ret2 = __blk_rq_unmap_user(mapped_bio);
+		if (ret2 && !ret)
+			ret = ret2;
+
+		mapped_bio = bio;
+		bio = bio->bi_next;
+		bio_put(mapped_bio);
 	}
-	return 0;
+
+	return ret;
 }
 
 EXPORT_SYMBOL(blk_rq_unmap_user);
@@ -2822,7 +2817,7 @@ static int attempt_merge(request_queue_t *q, struct request *req,
 	 * will have updated segment counts, update sector
 	 * counts here.
 	 */
-	if (!q->merge_requests_fn(q, req, next))
+	if (!ll_merge_requests_fn(q, req, next))
 		return 0;
 
 	/*
@@ -2939,7 +2934,7 @@ static int __make_request(request_queue_t *q, struct bio *bio)
 		case ELEVATOR_BACK_MERGE:
 			BUG_ON(!rq_mergeable(req));
 
-			if (!q->back_merge_fn(q, req, bio))
+			if (!ll_back_merge_fn(q, req, bio))
 				break;
 
 			blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE);
@@ -2956,7 +2951,7 @@ static int __make_request(request_queue_t *q, struct bio *bio)
 		case ELEVATOR_FRONT_MERGE:
 			BUG_ON(!rq_mergeable(req));
 
-			if (!q->front_merge_fn(q, req, bio))
+			if (!ll_front_merge_fn(q, req, bio))
 				break;
 
 			blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index f322b6a..2528a0c 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -333,8 +333,7 @@ static int sg_io(struct file *file, request_queue_t *q,
 			hdr->sb_len_wr = len;
 	}
 
-	rq->bio = bio;
-	if (blk_rq_unmap_user(rq))
+	if (blk_rq_unmap_user(bio))
 		ret = -EFAULT;
 
 	/* may not have succeeded, but output values written to control
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index d719a5d..9d2ddb2 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -1907,6 +1907,7 @@ static void cciss_geometry_inquiry(int ctlr, int logvol,
 			       "does not support reading geometry\n");
 			drv->heads = 255;
 			drv->sectors = 32;	// Sectors per track
+			drv->raid_level = RAID_UNKNOWN;
 		} else {
 			drv->heads = inq_buff->data_byte[6];
 			drv->sectors = inq_buff->data_byte[7];
@@ -2491,7 +2492,7 @@ static void do_cciss_request(request_queue_t *q)
 	c->Request.Type.Type = TYPE_CMD;	// It is a command.
 	c->Request.Type.Attribute = ATTR_SIMPLE;
 	c->Request.Type.Direction =
-	    (rq_data_dir(creq) == READ) ? h->cciss_read : h->cciss_write;
+	    (rq_data_dir(creq) == READ) ? XFER_READ : XFER_WRITE;
 	c->Request.Timeout = 0;	// Don't time out
 	c->Request.CDB[0] =
 	    (rq_data_dir(creq) == READ) ? h->cciss_read : h->cciss_write;
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index e4a2f8f..66d028d 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -2139,8 +2139,7 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 			cdi->last_sense = s->sense_key;
 		}
 
-		rq->bio = bio;
-		if (blk_rq_unmap_user(rq))
+		if (blk_rq_unmap_user(bio))
 			ret = -EFAULT;
 
 		if (ret)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 1748e27..f02f48a 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -265,13 +265,11 @@ static int scsi_merge_bio(struct request *rq, struct bio *bio)
 
 	if (!rq->bio)
 		blk_rq_bio_prep(q, rq, bio);
-	else if (!q->back_merge_fn(q, rq, bio))
+	else if (!ll_back_merge_fn(q, rq, bio))
 		return -EINVAL;
 	else {
 		rq->biotail->bi_next = bio;
 		rq->biotail = bio;
-		rq->hard_nr_sectors += bio_sectors(bio);
-		rq->nr_sectors = rq->hard_nr_sectors;
 	}
 
 	return 0;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index ea330d7..36a6eac 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -331,10 +331,6 @@ struct request_pm_state
 
 #include <linux/elevator.h>
 
-typedef int (merge_request_fn) (request_queue_t *, struct request *,
-				struct bio *);
-typedef int (merge_requests_fn) (request_queue_t *, struct request *,
-				 struct request *);
 typedef void (request_fn_proc) (request_queue_t *q);
 typedef int (make_request_fn) (request_queue_t *q, struct bio *bio);
 typedef int (prep_rq_fn) (request_queue_t *, struct request *);
@@ -376,9 +372,6 @@ struct request_queue
 	struct request_list	rq;
 
 	request_fn_proc		*request_fn;
-	merge_request_fn	*back_merge_fn;
-	merge_request_fn	*front_merge_fn;
-	merge_requests_fn	*merge_requests_fn;
 	make_request_fn		*make_request_fn;
 	prep_rq_fn		*prep_rq_fn;
 	unplug_fn		*unplug_fn;
@@ -649,6 +642,11 @@ extern int sg_scsi_ioctl(struct file *, struct request_queue *,
 		struct gendisk *, struct scsi_ioctl_command __user *);
 
 /*
+ * Temporary export, until SCSI gets fixed up.
+ */
+extern int ll_back_merge_fn(request_queue_t *, struct request *, struct bio *);
+
+/*
  * A queue has just exitted congestion.  Note this in the global counter of
  * congested queues, and wake up anyone who was waiting for requests to be
  * put back.
@@ -674,7 +672,7 @@ extern void __blk_stop_queue(request_queue_t *q);
 extern void blk_run_queue(request_queue_t *);
 extern void blk_start_queueing(request_queue_t *);
 extern int blk_rq_map_user(request_queue_t *, struct request *, void __user *, unsigned long);
-extern int blk_rq_unmap_user(struct request *);
+extern int blk_rq_unmap_user(struct bio *);
 extern int blk_rq_map_kern(request_queue_t *, struct request *, void *, unsigned int, gfp_t);
 extern int blk_rq_map_user_iov(request_queue_t *, struct request *,
 			       struct sg_iovec *, int, unsigned int);
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index a24931d..e88fcbc 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -12,6 +12,8 @@ typedef void (elevator_merge_req_fn) (request_queue_t *, struct request *, struc
 
 typedef void (elevator_merged_fn) (request_queue_t *, struct request *, int);
 
+typedef int (elevator_allow_merge_fn) (request_queue_t *, struct request *, struct bio *);
+
 typedef int (elevator_dispatch_fn) (request_queue_t *, int);
 
 typedef void (elevator_add_req_fn) (request_queue_t *, struct request *);
@@ -33,6 +35,7 @@ struct elevator_ops
 	elevator_merge_fn *elevator_merge_fn;
 	elevator_merged_fn *elevator_merged_fn;
 	elevator_merge_req_fn *elevator_merge_req_fn;
+	elevator_allow_merge_fn *elevator_allow_merge_fn;
 
 	elevator_dispatch_fn *elevator_dispatch_fn;
 	elevator_add_req_fn *elevator_add_req_fn;