Merge rsync://rsync.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

7 files changed, 207 insertions, 101 deletions

diff --git a/block/as-iosched.c b/block/as-iosched.c
index 5934c4bfd52..ef126277b4b 100644
--- a/block/as-iosched.c
+++ b/block/as-iosched.c
@@ -1462,20 +1462,7 @@ static struct elevator_type iosched_as = {
 
 static int __init as_init(void)
 {
-	int ret;
-
-	ret = elv_register(&iosched_as);
-	if (!ret) {
-		/*
-		 * don't allow AS to get unregistered, since we would have
-		 * to browse all tasks in the system and release their
-		 * as_io_context first
-		 */
-		__module_get(THIS_MODULE);
-		return 0;
-	}
-
-	return ret;
+	return elv_register(&iosched_as);
 }
 
 static void __exit as_exit(void)
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 78c6b312bd3..07b70624377 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -219,9 +219,12 @@ static int cfq_queue_empty(request_queue_t *q)
 	return !cfqd->busy_queues;
 }
 
-static inline pid_t cfq_queue_pid(struct task_struct *task, int rw)
+static inline pid_t cfq_queue_pid(struct task_struct *task, int rw, int is_sync)
 {
-	if (rw == READ || rw == WRITE_SYNC)
+	/*
+	 * Use the per-process queue, for read requests and syncronous writes
+	 */
+	if (!(rw & REQ_RW) || is_sync)
 		return task->pid;
 
 	return CFQ_KEY_ASYNC;
@@ -473,7 +476,7 @@ static struct request *
 cfq_find_rq_fmerge(struct cfq_data *cfqd, struct bio *bio)
 {
 	struct task_struct *tsk = current;
-	pid_t key = cfq_queue_pid(tsk, bio_data_dir(bio));
+	pid_t key = cfq_queue_pid(tsk, bio_data_dir(bio), bio_sync(bio));
 	struct cfq_queue *cfqq;
 
 	cfqq = cfq_find_cfq_hash(cfqd, key, tsk->ioprio);
@@ -565,6 +568,33 @@ 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;
+
+	/*
+	 * Disallow merge of a sync bio into an async request.
+	 */
+	if ((bio_data_dir(bio) == READ || bio_sync(bio)) && !rq_is_sync(rq))
+		return 0;
+
+	/*
+	 * Lookup the cfqq that this bio will be queued with. Allow
+	 * merge only if rq is queued there.
+	 */
+	key = cfq_queue_pid(current, rw, bio_sync(bio));
+	cfqq = cfq_find_cfq_hash(cfqd, key, current->ioprio);
+
+	if (cfqq == RQ_CFQQ(rq))
+		return 1;
+
+	return 0;
+}
+
 static inline void
 __cfq_set_active_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 {
@@ -1748,6 +1778,9 @@ static int cfq_may_queue(request_queue_t *q, int rw)
 	struct cfq_data *cfqd = q->elevator->elevator_data;
 	struct task_struct *tsk = current;
 	struct cfq_queue *cfqq;
+	unsigned int key;
+
+	key = cfq_queue_pid(tsk, rw, rw & REQ_RW_SYNC);
 
 	/*
 	 * don't force setup of a queue from here, as a call to may_queue
@@ -1755,7 +1788,7 @@ static int cfq_may_queue(request_queue_t *q, int rw)
 	 * so just lookup a possibly existing queue, or return 'may queue'
 	 * if that fails
 	 */
-	cfqq = cfq_find_cfq_hash(cfqd, cfq_queue_pid(tsk, rw), tsk->ioprio);
+	cfqq = cfq_find_cfq_hash(cfqd, key, tsk->ioprio);
 	if (cfqq) {
 		cfq_init_prio_data(cfqq);
 		cfq_prio_boost(cfqq);
@@ -1798,10 +1831,10 @@ cfq_set_request(request_queue_t *q, struct request *rq, gfp_t gfp_mask)
 	struct task_struct *tsk = current;
 	struct cfq_io_context *cic;
 	const int rw = rq_data_dir(rq);
-	pid_t key = cfq_queue_pid(tsk, rw);
+	const int is_sync = rq_is_sync(rq);
+	pid_t key = cfq_queue_pid(tsk, rw, is_sync);
 	struct cfq_queue *cfqq;
 	unsigned long flags;
-	int is_sync = key != CFQ_KEY_ASYNC;
 
 	might_sleep_if(gfp_mask & __GFP_WAIT);
 
@@ -2119,6 +2152,7 @@ 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 c0063f345c5..f6dafa8c7c4 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);
 
@@ -572,6 +590,12 @@ void elv_insert(request_queue_t *q, struct request *rq, int where)
 		 */
 		rq->cmd_flags |= REQ_SOFTBARRIER;
 
+		/*
+		 * Most requeues happen because of a busy condition,
+		 * don't force unplug of the queue for that case.
+		 */
+		unplug_it = 0;
+
 		if (q->ordseq == 0) {
 			list_add(&rq->queuelist, &q->queue_head);
 			break;
@@ -586,11 +610,6 @@ void elv_insert(request_queue_t *q, struct request *rq, int where)
 		}
 
 		list_add_tail(&rq->queuelist, pos);
-		/*
-		 * most requeues happen because of a busy condition, don't
-		 * force unplug of the queue for that case.
-		 */
-		unplug_it = 0;
 		break;
 
 	default:
diff --git a/block/genhd.c b/block/genhd.c
index 653919d50cd..457fdac4c17 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -417,6 +417,34 @@ static struct disk_attribute disk_attr_stat = {
 	.show	= disk_stats_read
 };
 
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+
+static ssize_t disk_fail_store(struct gendisk * disk,
+			       const char *buf, size_t count)
+{
+	int i;
+
+	if (count > 0 && sscanf(buf, "%d", &i) > 0) {
+		if (i == 0)
+			disk->flags &= ~GENHD_FL_FAIL;
+		else
+			disk->flags |= GENHD_FL_FAIL;
+	}
+
+	return count;
+}
+static ssize_t disk_fail_read(struct gendisk * disk, char *page)
+{
+	return sprintf(page, "%d\n", disk->flags & GENHD_FL_FAIL ? 1 : 0);
+}
+static struct disk_attribute disk_attr_fail = {
+	.attr = {.name = "make-it-fail", .mode = S_IRUGO | S_IWUSR },
+	.store	= disk_fail_store,
+	.show	= disk_fail_read
+};
+
+#endif
+
 static struct attribute * default_attrs[] = {
 	&disk_attr_uevent.attr,
 	&disk_attr_dev.attr,
@@ -424,6 +452,9 @@ static struct attribute * default_attrs[] = {
 	&disk_attr_removable.attr,
 	&disk_attr_size.attr,
 	&disk_attr_stat.attr,
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+	&disk_attr_fail.attr,
+#endif
 	NULL,
 };
 
diff --git a/block/ioctl.c b/block/ioctl.c
index 58aab630dfc..f6962b64660 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -72,7 +72,7 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
 			bdevp = bdget_disk(disk, part);
 			if (!bdevp)
 				return -ENOMEM;
-			mutex_lock_nested(&bdevp->bd_mutex, BD_MUTEX_PARTITION);
+			mutex_lock(&bdevp->bd_mutex);
 			if (bdevp->bd_openers) {
 				mutex_unlock(&bdevp->bd_mutex);
 				bdput(bdevp);
@@ -82,7 +82,7 @@ static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user
 			fsync_bdev(bdevp);
 			invalidate_bdev(bdevp, 0);
 
-			mutex_lock_nested(&bdev->bd_mutex, BD_MUTEX_WHOLE);
+			mutex_lock(&bdev->bd_mutex);
 			delete_partition(disk, part);
 			mutex_unlock(&bdev->bd_mutex);
 			mutex_unlock(&bdevp->bd_mutex);
@@ -290,7 +290,7 @@ int blkdev_ioctl(struct inode *inode, struct file *file, unsigned cmd,
    ENOIOCTLCMD for unknown ioctls. */
 long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 {
-	struct block_device *bdev = file->f_dentry->d_inode->i_bdev;
+	struct block_device *bdev = file->f_path.dentry->d_inode->i_bdev;
 	struct gendisk *disk = bdev->bd_disk;
 	int ret = -ENOIOCTLCMD;
 	if (disk->fops->compat_ioctl) {
diff --git a/block/ll_rw_blk.c b/block/ll_rw_blk.c
index 31512cd9f3a..38c293b987b 100644
--- a/block/ll_rw_blk.c
+++ b/block/ll_rw_blk.c
@@ -25,9 +25,11 @@
 #include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/writeback.h>
+#include <linux/task_io_accounting_ops.h>
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
 #include <linux/blktrace_api.h>
+#include <linux/fault-inject.h>
 
 /*
  * for max sense size
@@ -127,13 +129,6 @@ struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
 }
 EXPORT_SYMBOL(blk_get_backing_dev_info);
 
-void blk_queue_activity_fn(request_queue_t *q, activity_fn *fn, void *data)
-{
-	q->activity_fn = fn;
-	q->activity_data = data;
-}
-EXPORT_SYMBOL(blk_queue_activity_fn);
-
 /**
  * blk_queue_prep_rq - set a prepare_request function for queue
  * @q:		queue
@@ -236,8 +231,6 @@ void blk_queue_make_request(request_queue_t * q, make_request_fn * mfn)
 	 * by default assume old behaviour and bounce for any highmem page
 	 */
 	blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
-
-	blk_queue_activity_fn(q, NULL, NULL);
 }
 
 EXPORT_SYMBOL(blk_queue_make_request);
@@ -1271,7 +1264,7 @@ new_hw_segment:
 	bio->bi_hw_segments = nr_hw_segs;
 	bio->bi_flags |= (1 << BIO_SEG_VALID);
 }
-
+EXPORT_SYMBOL(blk_recount_segments);
 
 static int blk_phys_contig_segment(request_queue_t *q, struct bio *bio,
 				   struct bio *nxt)
@@ -1412,8 +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;
@@ -1449,6 +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)
@@ -1919,9 +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);
@@ -2065,15 +2055,16 @@ static void freed_request(request_queue_t *q, int rw, int priv)
  * Returns NULL on failure, with queue_lock held.
  * Returns !NULL on success, with queue_lock *not held*.
  */
-static struct request *get_request(request_queue_t *q, int rw, struct bio *bio,
-				   gfp_t gfp_mask)
+static struct request *get_request(request_queue_t *q, int rw_flags,
+				   struct bio *bio, gfp_t gfp_mask)
 {
 	struct request *rq = NULL;
 	struct request_list *rl = &q->rq;
 	struct io_context *ioc = NULL;
+	const int rw = rw_flags & 0x01;
 	int may_queue, priv;
 
-	may_queue = elv_may_queue(q, rw);
+	may_queue = elv_may_queue(q, rw_flags);
 	if (may_queue == ELV_MQUEUE_NO)
 		goto rq_starved;
 
@@ -2121,7 +2112,7 @@ static struct request *get_request(request_queue_t *q, int rw, struct bio *bio,
 
 	spin_unlock_irq(q->queue_lock);
 
-	rq = blk_alloc_request(q, rw, priv, gfp_mask);
+	rq = blk_alloc_request(q, rw_flags, priv, gfp_mask);
 	if (unlikely(!rq)) {
 		/*
 		 * Allocation failed presumably due to memory. Undo anything
@@ -2169,12 +2160,13 @@ out:
  *
  * Called with q->queue_lock held, and returns with it unlocked.
  */
-static struct request *get_request_wait(request_queue_t *q, int rw,
+static struct request *get_request_wait(request_queue_t *q, int rw_flags,
 					struct bio *bio)
 {
+	const int rw = rw_flags & 0x01;
 	struct request *rq;
 
-	rq = get_request(q, rw, bio, GFP_NOIO);
+	rq = get_request(q, rw_flags, bio, GFP_NOIO);
 	while (!rq) {
 		DEFINE_WAIT(wait);
 		struct request_list *rl = &q->rq;
@@ -2182,7 +2174,7 @@ static struct request *get_request_wait(request_queue_t *q, int rw,
 		prepare_to_wait_exclusive(&rl->wait[rw], &wait,
 				TASK_UNINTERRUPTIBLE);
 
-		rq = get_request(q, rw, bio, GFP_NOIO);
+		rq = get_request(q, rw_flags, bio, GFP_NOIO);
 
 		if (!rq) {
 			struct io_context *ioc;
@@ -2355,40 +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;
 
@@ -2424,6 +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))
@@ -2450,6 +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;
 	}
@@ -2457,7 +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;
 }
 
@@ -2469,6 +2453,7 @@ EXPORT_SYMBOL(blk_rq_map_user);
  * @rq:		request to map data to
  * @iov:	pointer to the iovec
  * @iov_count:	number of elements in the iovec
+ * @len:	I/O byte count
  *
  * Description:
  *    Data will be mapped directly for zero copy io, if possible. Otherwise
@@ -2514,27 +2499,33 @@ 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);
@@ -2694,9 +2685,6 @@ static inline void add_request(request_queue_t * q, struct request * req)
 {
 	drive_stat_acct(req, req->nr_sectors, 1);
 
-	if (q->activity_fn)
-		q->activity_fn(q->activity_data, rq_data_dir(req));
-
 	/*
 	 * elevator indicated where it wants this request to be
 	 * inserted at elevator_merge time
@@ -2830,7 +2818,7 @@ 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;
 
 	/*
@@ -2920,6 +2908,7 @@ static int __make_request(request_queue_t *q, struct bio *bio)
 	int el_ret, nr_sectors, barrier, err;
 	const unsigned short prio = bio_prio(bio);
 	const int sync = bio_sync(bio);
+	int rw_flags;
 
 	nr_sectors = bio_sectors(bio);
 
@@ -2946,7 +2935,7 @@ 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);
@@ -2963,7 +2952,7 @@ 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);
@@ -2994,10 +2983,19 @@ static int __make_request(request_queue_t *q, struct bio *bio)
 
 get_rq:
 	/*
+	 * This sync check and mask will be re-done in init_request_from_bio(),
+	 * but we need to set it earlier to expose the sync flag to the
+	 * rq allocator and io schedulers.
+	 */
+	rw_flags = bio_data_dir(bio);
+	if (sync)
+		rw_flags |= REQ_RW_SYNC;
+
+	/*
 	 * Grab a free request. This is might sleep but can not fail.
 	 * Returns with the queue unlocked.
 	 */
-	req = get_request_wait(q, bio_data_dir(bio), bio);
+	req = get_request_wait(q, rw_flags, bio);
 
 	/*
 	 * After dropping the lock and possibly sleeping here, our request
@@ -3056,6 +3054,42 @@ static void handle_bad_sector(struct bio *bio)
 	set_bit(BIO_EOF, &bio->bi_flags);
 }
 
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+
+static DECLARE_FAULT_ATTR(fail_make_request);
+
+static int __init setup_fail_make_request(char *str)
+{
+	return setup_fault_attr(&fail_make_request, str);
+}
+__setup("fail_make_request=", setup_fail_make_request);
+
+static int should_fail_request(struct bio *bio)
+{
+	if ((bio->bi_bdev->bd_disk->flags & GENHD_FL_FAIL) ||
+	    (bio->bi_bdev->bd_part && bio->bi_bdev->bd_part->make_it_fail))
+		return should_fail(&fail_make_request, bio->bi_size);
+
+	return 0;
+}
+
+static int __init fail_make_request_debugfs(void)
+{
+	return init_fault_attr_dentries(&fail_make_request,
+					"fail_make_request");
+}
+
+late_initcall(fail_make_request_debugfs);
+
+#else /* CONFIG_FAIL_MAKE_REQUEST */
+
+static inline int should_fail_request(struct bio *bio)
+{
+	return 0;
+}
+
+#endif /* CONFIG_FAIL_MAKE_REQUEST */
+
 /**
  * generic_make_request: hand a buffer to its device driver for I/O
  * @bio:  The bio describing the location in memory and on the device.
@@ -3141,6 +3175,9 @@ end_io:
 		if (unlikely(test_bit(QUEUE_FLAG_DEAD, &q->queue_flags)))
 			goto end_io;
 
+		if (should_fail_request(bio))
+			goto end_io;
+
 		/*
 		 * If this device has partitions, remap block n
 		 * of partition p to block n+start(p) of the disk.
@@ -3195,10 +3232,12 @@ void submit_bio(int rw, struct bio *bio)
 	BIO_BUG_ON(!bio->bi_size);
 	BIO_BUG_ON(!bio->bi_io_vec);
 	bio->bi_rw |= rw;
-	if (rw & WRITE)
+	if (rw & WRITE) {
 		count_vm_events(PGPGOUT, count);
-	else
+	} else {
+		task_io_account_read(bio->bi_size);
 		count_vm_events(PGPGIN, count);
+	}
 
 	if (unlikely(block_dump)) {
 		char b[BDEVNAME_SIZE];
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index b3e210723a7..65c6a3cba6d 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -223,11 +223,12 @@ static int verify_command(struct file *file, unsigned char *cmd)
 static int sg_io(struct file *file, request_queue_t *q,
 		struct gendisk *bd_disk, struct sg_io_hdr *hdr)
 {
-	unsigned long start_time;
+	unsigned long start_time, timeout;
 	int writing = 0, ret = 0;
 	struct request *rq;
 	char sense[SCSI_SENSE_BUFFERSIZE];
 	unsigned char cmd[BLK_MAX_CDB];
+	struct bio *bio;
 
 	if (hdr->interface_id != 'S')
 		return -EINVAL;
@@ -270,14 +271,8 @@ static int sg_io(struct file *file, request_queue_t *q,
 
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 
-	/*
-	 * bounce this after holding a reference to the original bio, it's
-	 * needed for proper unmapping
-	 */
-	if (rq->bio)
-		blk_queue_bounce(q, &rq->bio);
-
-	rq->timeout = jiffies_to_msecs(hdr->timeout);
+	timeout = msecs_to_jiffies(hdr->timeout);
+	rq->timeout = (timeout < INT_MAX) ? timeout : INT_MAX;
 	if (!rq->timeout)
 		rq->timeout = q->sg_timeout;
 	if (!rq->timeout)
@@ -308,6 +303,7 @@ static int sg_io(struct file *file, request_queue_t *q,
 	if (ret)
 		goto out;
 
+	bio = rq->bio;
 	rq->retries = 0;
 
 	start_time = jiffies;
@@ -338,7 +334,7 @@ static int sg_io(struct file *file, request_queue_t *q,
 			hdr->sb_len_wr = len;
 	}
 
-	if (blk_rq_unmap_user(rq))
+	if (blk_rq_unmap_user(bio))
 		ret = -EFAULT;
 
 	/* may not have succeeded, but output values written to control