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

* 'for-linus' of git://git.kernel.dk/linux-2.6-block:
  block: Skip I/O merges when disabled
  block: add large command support
  block: replace sizeof(rq->cmd) with BLK_MAX_CDB
  ide: use blk_rq_init() to initialize the request
  block: use blk_rq_init() to initialize the request
  block: rename and export rq_init()
  block: no need to initialize rq->cmd with blk_get_request
  block: no need to initialize rq->cmd in prepare_flush_fn hook
  block/blk-barrier.c:blk_ordered_cur_seq() mustn't be inline
  block/elevator.c:elv_rq_merge_ok() mustn't be inline
  block: make queue flags non-atomic
  block: add dma alignment and padding support to blk_rq_map_kern
  unexport blk_max_pfn
  ps3disk: Remove superfluous cast
  block: make rq_init() do a full memset()
  relay: fix splice problem

10 files changed, 105 insertions, 67 deletions

diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index 55c5f1fc4f1..66e55288178 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -53,7 +53,7 @@ EXPORT_SYMBOL(blk_queue_ordered);
 /*
  * Cache flushing for ordered writes handling
  */
-inline unsigned blk_ordered_cur_seq(struct request_queue *q)
+unsigned blk_ordered_cur_seq(struct request_queue *q)
 {
 	if (!q->ordseq)
 		return 0;
@@ -143,10 +143,8 @@ static void queue_flush(struct request_queue *q, unsigned which)
 		end_io = post_flush_end_io;
 	}
 
+	blk_rq_init(q, rq);
 	rq->cmd_flags = REQ_HARDBARRIER;
-	rq_init(q, rq);
-	rq->elevator_private = NULL;
-	rq->elevator_private2 = NULL;
 	rq->rq_disk = q->bar_rq.rq_disk;
 	rq->end_io = end_io;
 	q->prepare_flush_fn(q, rq);
@@ -167,14 +165,11 @@ static inline struct request *start_ordered(struct request_queue *q,
 	blkdev_dequeue_request(rq);
 	q->orig_bar_rq = rq;
 	rq = &q->bar_rq;
-	rq->cmd_flags = 0;
-	rq_init(q, rq);
+	blk_rq_init(q, rq);
 	if (bio_data_dir(q->orig_bar_rq->bio) == WRITE)
 		rq->cmd_flags |= REQ_RW;
 	if (q->ordered & QUEUE_ORDERED_FUA)
 		rq->cmd_flags |= REQ_FUA;
-	rq->elevator_private = NULL;
-	rq->elevator_private2 = NULL;
 	init_request_from_bio(rq, q->orig_bar_rq->bio);
 	rq->end_io = bar_end_io;
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 2a438a93f72..5d09f8c5602 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -107,41 +107,21 @@ struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
 }
 EXPORT_SYMBOL(blk_get_backing_dev_info);
 
-/*
- * We can't just memset() the structure, since the allocation path
- * already stored some information in the request.
- */
-void rq_init(struct request_queue *q, struct request *rq)
+void blk_rq_init(struct request_queue *q, struct request *rq)
 {
+	memset(rq, 0, sizeof(*rq));
+
 	INIT_LIST_HEAD(&rq->queuelist);
 	INIT_LIST_HEAD(&rq->donelist);
 	rq->q = q;
 	rq->sector = rq->hard_sector = (sector_t) -1;
-	rq->nr_sectors = rq->hard_nr_sectors = 0;
-	rq->current_nr_sectors = rq->hard_cur_sectors = 0;
-	rq->bio = rq->biotail = NULL;
 	INIT_HLIST_NODE(&rq->hash);
 	RB_CLEAR_NODE(&rq->rb_node);
-	rq->rq_disk = NULL;
-	rq->nr_phys_segments = 0;
-	rq->nr_hw_segments = 0;
-	rq->ioprio = 0;
-	rq->special = NULL;
-	rq->buffer = NULL;
+	rq->cmd = rq->__cmd;
 	rq->tag = -1;
-	rq->errors = 0;
 	rq->ref_count = 1;
-	rq->cmd_len = 0;
-	memset(rq->cmd, 0, sizeof(rq->cmd));
-	rq->data_len = 0;
-	rq->extra_len = 0;
-	rq->sense_len = 0;
-	rq->data = NULL;
-	rq->sense = NULL;
-	rq->end_io = NULL;
-	rq->end_io_data = NULL;
-	rq->next_rq = NULL;
 }
+EXPORT_SYMBOL(blk_rq_init);
 
 static void req_bio_endio(struct request *rq, struct bio *bio,
 			  unsigned int nbytes, int error)
@@ -194,7 +174,7 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 
 	if (blk_pc_request(rq)) {
 		printk(KERN_INFO "  cdb: ");
-		for (bit = 0; bit < sizeof(rq->cmd); bit++)
+		for (bit = 0; bit < BLK_MAX_CDB; bit++)
 			printk("%02x ", rq->cmd[bit]);
 		printk("\n");
 	}
@@ -220,7 +200,8 @@ void blk_plug_device(struct request_queue *q)
 	if (blk_queue_stopped(q))
 		return;
 
-	if (!test_and_set_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags)) {
+	if (!test_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags)) {
+		__set_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags);
 		mod_timer(&q->unplug_timer, jiffies + q->unplug_delay);
 		blk_add_trace_generic(q, NULL, 0, BLK_TA_PLUG);
 	}
@@ -235,9 +216,10 @@ int blk_remove_plug(struct request_queue *q)
 {
 	WARN_ON(!irqs_disabled());
 
-	if (!test_and_clear_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags))
+	if (!test_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags))
 		return 0;
 
+	queue_flag_clear(QUEUE_FLAG_PLUGGED, q);
 	del_timer(&q->unplug_timer);
 	return 1;
 }
@@ -333,15 +315,16 @@ void blk_start_queue(struct request_queue *q)
 {
 	WARN_ON(!irqs_disabled());
 
-	clear_bit(QUEUE_FLAG_STOPPED, &q->queue_flags);
+	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
 
 	/*
 	 * one level of recursion is ok and is much faster than kicking
 	 * the unplug handling
 	 */
-	if (!test_and_set_bit(QUEUE_FLAG_REENTER, &q->queue_flags)) {
+	if (!test_bit(QUEUE_FLAG_REENTER, &q->queue_flags)) {
+		queue_flag_set(QUEUE_FLAG_REENTER, q);
 		q->request_fn(q);
-		clear_bit(QUEUE_FLAG_REENTER, &q->queue_flags);
+		queue_flag_clear(QUEUE_FLAG_REENTER, q);
 	} else {
 		blk_plug_device(q);
 		kblockd_schedule_work(&q->unplug_work);
@@ -366,7 +349,7 @@ EXPORT_SYMBOL(blk_start_queue);
 void blk_stop_queue(struct request_queue *q)
 {
 	blk_remove_plug(q);
-	set_bit(QUEUE_FLAG_STOPPED, &q->queue_flags);
+	queue_flag_set(QUEUE_FLAG_STOPPED, q);
 }
 EXPORT_SYMBOL(blk_stop_queue);
 
@@ -395,11 +378,8 @@ EXPORT_SYMBOL(blk_sync_queue);
  * blk_run_queue - run a single device queue
  * @q:	The queue to run
  */
-void blk_run_queue(struct request_queue *q)
+void __blk_run_queue(struct request_queue *q)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(q->queue_lock, flags);
 	blk_remove_plug(q);
 
 	/*
@@ -407,15 +387,28 @@ void blk_run_queue(struct request_queue *q)
 	 * handling reinvoke the handler shortly if we already got there.
 	 */
 	if (!elv_queue_empty(q)) {
-		if (!test_and_set_bit(QUEUE_FLAG_REENTER, &q->queue_flags)) {
+		if (!test_bit(QUEUE_FLAG_REENTER, &q->queue_flags)) {
+			queue_flag_set(QUEUE_FLAG_REENTER, q);
 			q->request_fn(q);
-			clear_bit(QUEUE_FLAG_REENTER, &q->queue_flags);
+			queue_flag_clear(QUEUE_FLAG_REENTER, q);
 		} else {
 			blk_plug_device(q);
 			kblockd_schedule_work(&q->unplug_work);
 		}
 	}
+}
+EXPORT_SYMBOL(__blk_run_queue);
+
+/**
+ * blk_run_queue - run a single device queue
+ * @q: The queue to run
+ */
+void blk_run_queue(struct request_queue *q)
+{
+	unsigned long flags;
 
+	spin_lock_irqsave(q->queue_lock, flags);
+	__blk_run_queue(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 EXPORT_SYMBOL(blk_run_queue);
@@ -428,7 +421,7 @@ void blk_put_queue(struct request_queue *q)
 void blk_cleanup_queue(struct request_queue *q)
 {
 	mutex_lock(&q->sysfs_lock);
-	set_bit(QUEUE_FLAG_DEAD, &q->queue_flags);
+	queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q);
 	mutex_unlock(&q->sysfs_lock);
 
 	if (q->elevator)
@@ -607,6 +600,8 @@ blk_alloc_request(struct request_queue *q, int rw, int priv, gfp_t gfp_mask)
 	if (!rq)
 		return NULL;
 
+	blk_rq_init(q, rq);
+
 	/*
 	 * first three bits are identical in rq->cmd_flags and bio->bi_rw,
 	 * see bio.h and blkdev.h
@@ -789,8 +784,6 @@ rq_starved:
 	if (ioc_batching(q, ioc))
 		ioc->nr_batch_requests--;
 
-	rq_init(q, rq);
-
 	blk_add_trace_generic(q, bio, rw, BLK_TA_GETRQ);
 out:
 	return rq;
diff --git a/block/blk-map.c b/block/blk-map.c
index 3c942bd6422..0b1af5a3537 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -255,10 +255,18 @@ EXPORT_SYMBOL(blk_rq_unmap_user);
  * @kbuf:	the kernel buffer
  * @len:	length of user data
  * @gfp_mask:	memory allocation flags
+ *
+ * Description:
+ *    Data will be mapped directly if possible. Otherwise a bounce
+ *    buffer is used.
  */
 int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 		    unsigned int len, gfp_t gfp_mask)
 {
+	unsigned long kaddr;
+	unsigned int alignment;
+	int reading = rq_data_dir(rq) == READ;
+	int do_copy = 0;
 	struct bio *bio;
 
 	if (len > (q->max_hw_sectors << 9))
@@ -266,13 +274,24 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	if (!len || !kbuf)
 		return -EINVAL;
 
-	bio = bio_map_kern(q, kbuf, len, gfp_mask);
+	kaddr = (unsigned long)kbuf;
+	alignment = queue_dma_alignment(q) | q->dma_pad_mask;
+	do_copy = ((kaddr & alignment) || (len & alignment));
+
+	if (do_copy)
+		bio = bio_copy_kern(q, kbuf, len, gfp_mask, reading);
+	else
+		bio = bio_map_kern(q, kbuf, len, gfp_mask);
+
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
 	if (rq_data_dir(rq) == WRITE)
 		bio->bi_rw |= (1 << BIO_RW);
 
+	if (do_copy)
+		rq->cmd_flags |= REQ_COPY_USER;
+
 	blk_rq_bio_prep(q, rq, bio);
 	blk_queue_bounce(q, &rq->bio);
 	rq->buffer = rq->data = NULL;
diff --git a/block/blk-merge.c b/block/blk-merge.c
index b5c5c4a9e3f..73b23562af2 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -55,7 +55,7 @@ void blk_recalc_rq_segments(struct request *rq)
 	if (!rq->bio)
 		return;
 
-	cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);
+	cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
 	hw_seg_size = seg_size = 0;
 	phys_size = hw_size = nr_phys_segs = nr_hw_segs = 0;
 	rq_for_each_segment(bv, rq, iter) {
@@ -128,7 +128,7 @@ EXPORT_SYMBOL(blk_recount_segments);
 static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 				   struct bio *nxt)
 {
-	if (!(q->queue_flags & (1 << QUEUE_FLAG_CLUSTER)))
+	if (!test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags))
 		return 0;
 
 	if (!BIOVEC_PHYS_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt)))
@@ -175,7 +175,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 	int nsegs, cluster;
 
 	nsegs = 0;
-	cluster = q->queue_flags & (1 << QUEUE_FLAG_CLUSTER);
+	cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
 
 	/*
 	 * for each bio in rq
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 5713f7e5cbd..6089384ab06 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -14,7 +14,6 @@ unsigned long blk_max_low_pfn;
 EXPORT_SYMBOL(blk_max_low_pfn);
 
 unsigned long blk_max_pfn;
-EXPORT_SYMBOL(blk_max_pfn);
 
 /**
  * blk_queue_prep_rq - set a prepare_request function for queue
@@ -288,7 +287,7 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 	t->max_segment_size = min(t->max_segment_size, b->max_segment_size);
 	t->hardsect_size = max(t->hardsect_size, b->hardsect_size);
 	if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags))
-		clear_bit(QUEUE_FLAG_CLUSTER, &t->queue_flags);
+		queue_flag_clear(QUEUE_FLAG_CLUSTER, t);
 }
 EXPORT_SYMBOL(blk_queue_stack_limits);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index fc41d83be22..e85c4013e8a 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -135,6 +135,25 @@ static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
 	return queue_var_show(max_hw_sectors_kb, (page));
 }
 
+static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(blk_queue_nomerges(q), page);
+}
+
+static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
+				    size_t count)
+{
+	unsigned long nm;
+	ssize_t ret = queue_var_store(&nm, page, count);
+
+	if (nm)
+	       set_bit(QUEUE_FLAG_NOMERGES, &q->queue_flags);
+	else
+	       clear_bit(QUEUE_FLAG_NOMERGES, &q->queue_flags);
+
+	return ret;
+}
+
 
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
@@ -170,6 +189,12 @@ static struct queue_sysfs_entry queue_hw_sector_size_entry = {
 	.show = queue_hw_sector_size_show,
 };
 
+static struct queue_sysfs_entry queue_nomerges_entry = {
+	.attr = {.name = "nomerges", .mode = S_IRUGO | S_IWUSR },
+	.show = queue_nomerges_show,
+	.store = queue_nomerges_store,
+};
+
 static struct attribute *default_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -177,6 +202,7 @@ static struct attribute *default_attrs[] = {
 	&queue_max_sectors_entry.attr,
 	&queue_iosched_entry.attr,
 	&queue_hw_sector_size_entry.attr,
+	&queue_nomerges_entry.attr,
 	NULL,
 };
 
diff --git a/block/blk-tag.c b/block/blk-tag.c
index 4780a46ce23..e176ddbe599 100644
--- a/block/blk-tag.c
+++ b/block/blk-tag.c
@@ -70,7 +70,7 @@ void __blk_queue_free_tags(struct request_queue *q)
 	__blk_free_tags(bqt);
 
 	q->queue_tags = NULL;
-	q->queue_flags &= ~(1 << QUEUE_FLAG_QUEUED);
+	queue_flag_clear(QUEUE_FLAG_QUEUED, q);
 }
 
 /**
@@ -98,7 +98,7 @@ EXPORT_SYMBOL(blk_free_tags);
  **/
 void blk_queue_free_tags(struct request_queue *q)
 {
-	clear_bit(QUEUE_FLAG_QUEUED, &q->queue_flags);
+	queue_flag_clear(QUEUE_FLAG_QUEUED, q);
 }
 EXPORT_SYMBOL(blk_queue_free_tags);
 
@@ -188,7 +188,7 @@ int blk_queue_init_tags(struct request_queue *q, int depth,
 		rc = blk_queue_resize_tags(q, depth);
 		if (rc)
 			return rc;
-		set_bit(QUEUE_FLAG_QUEUED, &q->queue_flags);
+		queue_flag_set(QUEUE_FLAG_QUEUED, q);
 		return 0;
 	} else
 		atomic_inc(&tags->refcnt);
@@ -197,7 +197,7 @@ int blk_queue_init_tags(struct request_queue *q, int depth,
 	 * assign it, all done
 	 */
 	q->queue_tags = tags;
-	q->queue_flags |= (1 << QUEUE_FLAG_QUEUED);
+	queue_flag_set(QUEUE_FLAG_QUEUED, q);
 	INIT_LIST_HEAD(&q->tag_busy_list);
 	return 0;
 fail:
diff --git a/block/blk.h b/block/blk.h
index ec9120fb789..59776ab4742 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -10,7 +10,6 @@
 extern struct kmem_cache *blk_requestq_cachep;
 extern struct kobj_type blk_queue_ktype;
 
-void rq_init(struct request_queue *q, struct request *rq);
 void init_request_from_bio(struct request *req, struct bio *bio);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 			struct bio *bio);
diff --git a/block/elevator.c b/block/elevator.c
index 88318c38360..ac5310ef827 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -69,7 +69,7 @@ static int elv_iosched_allow_merge(struct request *rq, struct bio *bio)
 /*
  * can we safely merge with this request?
  */
-inline int elv_rq_merge_ok(struct request *rq, struct bio *bio)
+int elv_rq_merge_ok(struct request *rq, struct bio *bio)
 {
 	if (!rq_mergeable(rq))
 		return 0;
@@ -488,6 +488,9 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 		}
 	}
 
+	if (blk_queue_nomerges(q))
+		return ELEVATOR_NO_MERGE;
+
 	/*
 	 * See if our hash lookup can find a potential backmerge.
 	 */
@@ -1070,7 +1073,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	 */
 	spin_lock_irq(q->queue_lock);
 
-	set_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
+	queue_flag_set(QUEUE_FLAG_ELVSWITCH, q);
 
 	elv_drain_elevator(q);
 
@@ -1104,7 +1107,10 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 	 * finally exit old elevator and turn off BYPASS.
 	 */
 	elevator_exit(old_elevator);
-	clear_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
+	spin_lock_irq(q->queue_lock);
+	queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
+	spin_unlock_irq(q->queue_lock);
+
 	return 1;
 
 fail_register:
@@ -1115,7 +1121,11 @@ fail_register:
 	elevator_exit(e);
 	q->elevator = old_elevator;
 	elv_register_queue(q);
-	clear_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
+
+	spin_lock_irq(q->queue_lock);
+	queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
+	spin_unlock_irq(q->queue_lock);
+
 	return 0;
 }
 
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index a2c3a936ebf..ffa3720e6ca 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -217,8 +217,6 @@ EXPORT_SYMBOL_GPL(blk_verify_command);
 static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 			     struct sg_io_hdr *hdr, int has_write_perm)
 {
-	memset(rq->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */
-
 	if (copy_from_user(rq->cmd, hdr->cmdp, hdr->cmd_len))
 		return -EFAULT;
 	if (blk_verify_command(rq->cmd, has_write_perm))
@@ -531,7 +529,6 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 	rq->data_len = 0;
 	rq->extra_len = 0;
 	rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
-	memset(rq->cmd, 0, sizeof(rq->cmd));
 	rq->cmd[0] = cmd;
 	rq->cmd[4] = data;
 	rq->cmd_len = 6;