From e1defc4ff0cf57aca6c5e3ff99fa503f5943c1f1 Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 22 May 2009 17:17:49 -0400
Subject: block: Do away with the notion of hardsect_size

Until now we have had a 1:1 mapping between storage device physical
block size and the logical block sized used when addressing the device.
With SATA 4KB drives coming out that will no longer be the case.  The
sector size will be 4KB but the logical block size will remain
512-bytes.  Hence we need to distinguish between the physical block size
and the logical ditto.

This patch renames hardsect_size to logical_block_size.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-sysfs.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

(limited to 'block/blk-sysfs.c')

diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 3ff9bba3379a..13d38b7e4d0f 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -100,9 +100,9 @@ static ssize_t queue_max_sectors_show(struct request_queue *q, char *page)
 	return queue_var_show(max_sectors_kb, (page));
 }
 
-static ssize_t queue_hw_sector_size_show(struct request_queue *q, char *page)
+static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page)
 {
-	return queue_var_show(q->hardsect_size, page);
+	return queue_var_show(queue_logical_block_size(q), page);
 }
 
 static ssize_t
@@ -249,7 +249,12 @@ static struct queue_sysfs_entry queue_iosched_entry = {
 
 static struct queue_sysfs_entry queue_hw_sector_size_entry = {
 	.attr = {.name = "hw_sector_size", .mode = S_IRUGO },
-	.show = queue_hw_sector_size_show,
+	.show = queue_logical_block_size_show,
+};
+
+static struct queue_sysfs_entry queue_logical_block_size_entry = {
+	.attr = {.name = "logical_block_size", .mode = S_IRUGO },
+	.show = queue_logical_block_size_show,
 };
 
 static struct queue_sysfs_entry queue_nonrot_entry = {
@@ -283,6 +288,7 @@ static struct attribute *default_attrs[] = {
 	&queue_max_sectors_entry.attr,
 	&queue_iosched_entry.attr,
 	&queue_hw_sector_size_entry.attr,
+	&queue_logical_block_size_entry.attr,
 	&queue_nonrot_entry.attr,
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
-- 
cgit v1.2.3


From ae03bf639a5027d27270123f5f6e3ee6a412781d Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 22 May 2009 17:17:50 -0400
Subject: block: Use accessor functions for queue limits

Convert all external users of queue limits to using wrapper functions
instead of poking the request queue variables directly.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-barrier.c            |  8 ++++----
 block/blk-core.c               | 16 ++++++++--------
 block/blk-map.c                |  4 ++--
 block/blk-merge.c              | 27 ++++++++++++++-------------
 block/blk-settings.c           | 15 ++++++++++++---
 block/blk-sysfs.c              |  8 ++++----
 block/compat_ioctl.c           |  2 +-
 block/ioctl.c                  | 10 +++++-----
 block/scsi_ioctl.c             |  8 ++++----
 drivers/block/pktcdvd.c        |  6 ++++--
 drivers/cdrom/cdrom.c          |  4 ++--
 drivers/md/dm-table.c          | 28 ++++++++++++++--------------
 drivers/md/linear.c            |  2 +-
 drivers/md/multipath.c         |  4 ++--
 drivers/md/raid0.c             |  2 +-
 drivers/md/raid1.c             |  4 ++--
 drivers/md/raid10.c            |  8 ++++----
 drivers/md/raid5.c             |  4 ++--
 drivers/scsi/sg.c              | 15 ++++++++-------
 drivers/scsi/st.c              |  4 ++--
 drivers/usb/storage/scsiglue.c |  4 ++--
 fs/bio.c                       | 19 ++++++++++---------
 include/linux/bio.h            |  2 +-
 include/linux/blkdev.h         | 36 ++++++++++++++++++++++++++++++++++++
 mm/bounce.c                    |  4 ++--
 25 files changed, 147 insertions(+), 97 deletions(-)

(limited to 'block/blk-sysfs.c')

diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index 0d98054cdbd7..30022b4e2f63 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -388,10 +388,10 @@ int blkdev_issue_discard(struct block_device *bdev,
 
 		bio->bi_sector = sector;
 
-		if (nr_sects > q->max_hw_sectors) {
-			bio->bi_size = q->max_hw_sectors << 9;
-			nr_sects -= q->max_hw_sectors;
-			sector += q->max_hw_sectors;
+		if (nr_sects > queue_max_hw_sectors(q)) {
+			bio->bi_size = queue_max_hw_sectors(q) << 9;
+			nr_sects -= queue_max_hw_sectors(q);
+			sector += queue_max_hw_sectors(q);
 		} else {
 			bio->bi_size = nr_sects << 9;
 			nr_sects = 0;
diff --git a/block/blk-core.c b/block/blk-core.c
index 59c4af523112..7a4c40184a64 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1437,11 +1437,11 @@ static inline void __generic_make_request(struct bio *bio)
 			goto end_io;
 		}
 
-		if (unlikely(nr_sectors > q->max_hw_sectors)) {
+		if (unlikely(nr_sectors > queue_max_hw_sectors(q))) {
 			printk(KERN_ERR "bio too big device %s (%u > %u)\n",
-				bdevname(bio->bi_bdev, b),
-				bio_sectors(bio),
-				q->max_hw_sectors);
+			       bdevname(bio->bi_bdev, b),
+			       bio_sectors(bio),
+			       queue_max_hw_sectors(q));
 			goto end_io;
 		}
 
@@ -1608,8 +1608,8 @@ EXPORT_SYMBOL(submit_bio);
  */
 int blk_rq_check_limits(struct request_queue *q, struct request *rq)
 {
-	if (blk_rq_sectors(rq) > q->max_sectors ||
-	    blk_rq_bytes(rq) > q->max_hw_sectors << 9) {
+	if (blk_rq_sectors(rq) > queue_max_sectors(q) ||
+	    blk_rq_bytes(rq) > queue_max_hw_sectors(q) << 9) {
 		printk(KERN_ERR "%s: over max size limit.\n", __func__);
 		return -EIO;
 	}
@@ -1621,8 +1621,8 @@ int blk_rq_check_limits(struct request_queue *q, struct request *rq)
 	 * limitation.
 	 */
 	blk_recalc_rq_segments(rq);
-	if (rq->nr_phys_segments > q->max_phys_segments ||
-	    rq->nr_phys_segments > q->max_hw_segments) {
+	if (rq->nr_phys_segments > queue_max_phys_segments(q) ||
+	    rq->nr_phys_segments > queue_max_hw_segments(q)) {
 		printk(KERN_ERR "%s: over max segments limit.\n", __func__);
 		return -EIO;
 	}
diff --git a/block/blk-map.c b/block/blk-map.c
index ef2492adca7e..9083cf0180cc 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -115,7 +115,7 @@ int blk_rq_map_user(struct request_queue *q, struct request *rq,
 	struct bio *bio = NULL;
 	int ret;
 
-	if (len > (q->max_hw_sectors << 9))
+	if (len > (queue_max_hw_sectors(q) << 9))
 		return -EINVAL;
 	if (!len)
 		return -EINVAL;
@@ -292,7 +292,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 	struct bio *bio;
 	int ret;
 
-	if (len > (q->max_hw_sectors << 9))
+	if (len > (queue_max_hw_sectors(q) << 9))
 		return -EINVAL;
 	if (!len || !kbuf)
 		return -EINVAL;
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 4974dd5767e5..39ce64432ba6 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -32,11 +32,12 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 			 * never considered part of another segment, since that
 			 * might change with the bounce page.
 			 */
-			high = page_to_pfn(bv->bv_page) > q->bounce_pfn;
+			high = page_to_pfn(bv->bv_page) > queue_bounce_pfn(q);
 			if (high || highprv)
 				goto new_segment;
 			if (cluster) {
-				if (seg_size + bv->bv_len > q->max_segment_size)
+				if (seg_size + bv->bv_len
+				    > queue_max_segment_size(q))
 					goto new_segment;
 				if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv))
 					goto new_segment;
@@ -91,7 +92,7 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 		return 0;
 
 	if (bio->bi_seg_back_size + nxt->bi_seg_front_size >
-	    q->max_segment_size)
+	    queue_max_segment_size(q))
 		return 0;
 
 	if (!bio_has_data(bio))
@@ -134,7 +135,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 		int nbytes = bvec->bv_len;
 
 		if (bvprv && cluster) {
-			if (sg->length + nbytes > q->max_segment_size)
+			if (sg->length + nbytes > queue_max_segment_size(q))
 				goto new_segment;
 
 			if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec))
@@ -205,8 +206,8 @@ static inline int ll_new_hw_segment(struct request_queue *q,
 {
 	int nr_phys_segs = bio_phys_segments(q, bio);
 
-	if (req->nr_phys_segments + nr_phys_segs > q->max_hw_segments
-	    || req->nr_phys_segments + nr_phys_segs > q->max_phys_segments) {
+	if (req->nr_phys_segments + nr_phys_segs > queue_max_hw_segments(q) ||
+	    req->nr_phys_segments + nr_phys_segs > queue_max_phys_segments(q)) {
 		req->cmd_flags |= REQ_NOMERGE;
 		if (req == q->last_merge)
 			q->last_merge = NULL;
@@ -227,9 +228,9 @@ int ll_back_merge_fn(struct request_queue *q, struct request *req,
 	unsigned short max_sectors;
 
 	if (unlikely(blk_pc_request(req)))
-		max_sectors = q->max_hw_sectors;
+		max_sectors = queue_max_hw_sectors(q);
 	else
-		max_sectors = q->max_sectors;
+		max_sectors = queue_max_sectors(q);
 
 	if (blk_rq_sectors(req) + bio_sectors(bio) > max_sectors) {
 		req->cmd_flags |= REQ_NOMERGE;
@@ -251,9 +252,9 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
 	unsigned short max_sectors;
 
 	if (unlikely(blk_pc_request(req)))
-		max_sectors = q->max_hw_sectors;
+		max_sectors = queue_max_hw_sectors(q);
 	else
-		max_sectors = q->max_sectors;
+		max_sectors = queue_max_sectors(q);
 
 
 	if (blk_rq_sectors(req) + bio_sectors(bio) > max_sectors) {
@@ -287,7 +288,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 	/*
 	 * Will it become too large?
 	 */
-	if ((blk_rq_sectors(req) + blk_rq_sectors(next)) > q->max_sectors)
+	if ((blk_rq_sectors(req) + blk_rq_sectors(next)) > queue_max_sectors(q))
 		return 0;
 
 	total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
@@ -299,10 +300,10 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 		total_phys_segments--;
 	}
 
-	if (total_phys_segments > q->max_phys_segments)
+	if (total_phys_segments > queue_max_phys_segments(q))
 		return 0;
 
-	if (total_phys_segments > q->max_hw_segments)
+	if (total_phys_segments > queue_max_hw_segments(q))
 		return 0;
 
 	/* Merge is OK... */
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 15c3164537b8..0b32f984eed2 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -219,6 +219,15 @@ void blk_queue_max_sectors(struct request_queue *q, unsigned int max_sectors)
 }
 EXPORT_SYMBOL(blk_queue_max_sectors);
 
+void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_sectors)
+{
+	if (BLK_DEF_MAX_SECTORS > max_sectors)
+		q->max_hw_sectors = BLK_DEF_MAX_SECTORS;
+	else
+		q->max_hw_sectors = max_sectors;
+}
+EXPORT_SYMBOL(blk_queue_max_hw_sectors);
+
 /**
  * blk_queue_max_phys_segments - set max phys segments for a request for this queue
  * @q:  the request queue for the device
@@ -395,11 +404,11 @@ int blk_queue_dma_drain(struct request_queue *q,
 			       dma_drain_needed_fn *dma_drain_needed,
 			       void *buf, unsigned int size)
 {
-	if (q->max_hw_segments < 2 || q->max_phys_segments < 2)
+	if (queue_max_hw_segments(q) < 2 || queue_max_phys_segments(q) < 2)
 		return -EINVAL;
 	/* make room for appending the drain */
-	--q->max_hw_segments;
-	--q->max_phys_segments;
+	blk_queue_max_hw_segments(q, queue_max_hw_segments(q) - 1);
+	blk_queue_max_phys_segments(q, queue_max_phys_segments(q) - 1);
 	q->dma_drain_needed = dma_drain_needed;
 	q->dma_drain_buffer = buf;
 	q->dma_drain_size = size;
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 13d38b7e4d0f..142a4acddd43 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -95,7 +95,7 @@ queue_ra_store(struct request_queue *q, const char *page, size_t count)
 
 static ssize_t queue_max_sectors_show(struct request_queue *q, char *page)
 {
-	int max_sectors_kb = q->max_sectors >> 1;
+	int max_sectors_kb = queue_max_sectors(q) >> 1;
 
 	return queue_var_show(max_sectors_kb, (page));
 }
@@ -109,7 +109,7 @@ static ssize_t
 queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 {
 	unsigned long max_sectors_kb,
-			max_hw_sectors_kb = q->max_hw_sectors >> 1,
+		max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1,
 			page_kb = 1 << (PAGE_CACHE_SHIFT - 10);
 	ssize_t ret = queue_var_store(&max_sectors_kb, page, count);
 
@@ -117,7 +117,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 		return -EINVAL;
 
 	spin_lock_irq(q->queue_lock);
-	q->max_sectors = max_sectors_kb << 1;
+	blk_queue_max_sectors(q, max_sectors_kb << 1);
 	spin_unlock_irq(q->queue_lock);
 
 	return ret;
@@ -125,7 +125,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 
 static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
 {
-	int max_hw_sectors_kb = q->max_hw_sectors >> 1;
+	int max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1;
 
 	return queue_var_show(max_hw_sectors_kb, (page));
 }
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 9eaa1940273a..df18a156d011 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -766,7 +766,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 		return compat_put_int(arg, bdev_logical_block_size(bdev));
 	case BLKSECTGET:
 		return compat_put_ushort(arg,
-					 bdev_get_queue(bdev)->max_sectors);
+					 queue_max_sectors(bdev_get_queue(bdev)));
 	case BLKRASET: /* compatible, but no compat_ptr (!) */
 	case BLKFRASET:
 		if (!capable(CAP_SYS_ADMIN))
diff --git a/block/ioctl.c b/block/ioctl.c
index 7aa97f65da82..500e4c73cc52 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -152,10 +152,10 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 		bio->bi_private = &wait;
 		bio->bi_sector = start;
 
-		if (len > q->max_hw_sectors) {
-			bio->bi_size = q->max_hw_sectors << 9;
-			len -= q->max_hw_sectors;
-			start += q->max_hw_sectors;
+		if (len > queue_max_hw_sectors(q)) {
+			bio->bi_size = queue_max_hw_sectors(q) << 9;
+			len -= queue_max_hw_sectors(q);
+			start += queue_max_hw_sectors(q);
 		} else {
 			bio->bi_size = len << 9;
 			len = 0;
@@ -313,7 +313,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKSSZGET: /* get block device hardware sector size */
 		return put_int(arg, bdev_logical_block_size(bdev));
 	case BLKSECTGET:
-		return put_ushort(arg, bdev_get_queue(bdev)->max_sectors);
+		return put_ushort(arg, queue_max_sectors(bdev_get_queue(bdev)));
 	case BLKRASET:
 	case BLKFRASET:
 		if(!capable(CAP_SYS_ADMIN))
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index a9670dd4b5de..5f8e798ede4e 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -75,7 +75,7 @@ static int sg_set_timeout(struct request_queue *q, int __user *p)
 
 static int sg_get_reserved_size(struct request_queue *q, int __user *p)
 {
-	unsigned val = min(q->sg_reserved_size, q->max_sectors << 9);
+	unsigned val = min(q->sg_reserved_size, queue_max_sectors(q) << 9);
 
 	return put_user(val, p);
 }
@@ -89,8 +89,8 @@ static int sg_set_reserved_size(struct request_queue *q, int __user *p)
 
 	if (size < 0)
 		return -EINVAL;
-	if (size > (q->max_sectors << 9))
-		size = q->max_sectors << 9;
+	if (size > (queue_max_sectors(q) << 9))
+		size = queue_max_sectors(q) << 9;
 
 	q->sg_reserved_size = size;
 	return 0;
@@ -264,7 +264,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 	if (hdr->cmd_len > BLK_MAX_CDB)
 		return -EINVAL;
 
-	if (hdr->dxfer_len > (q->max_hw_sectors << 9))
+	if (hdr->dxfer_len > (queue_max_hw_sectors(q) << 9))
 		return -EIO;
 
 	if (hdr->dxfer_len)
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 293f5858921d..d57f11759480 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -991,13 +991,15 @@ static void pkt_iosched_process_queue(struct pktcdvd_device *pd)
  */
 static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_queue *q)
 {
-	if ((pd->settings.size << 9) / CD_FRAMESIZE <= q->max_phys_segments) {
+	if ((pd->settings.size << 9) / CD_FRAMESIZE
+	    <= queue_max_phys_segments(q)) {
 		/*
 		 * The cdrom device can handle one segment/frame
 		 */
 		clear_bit(PACKET_MERGE_SEGS, &pd->flags);
 		return 0;
-	} else if ((pd->settings.size << 9) / PAGE_SIZE <= q->max_phys_segments) {
+	} else if ((pd->settings.size << 9) / PAGE_SIZE
+		   <= queue_max_phys_segments(q)) {
 		/*
 		 * We can handle this case at the expense of some extra memory
 		 * copies during write operations
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index cceace61ef28..71d1b9bab70b 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -2101,8 +2101,8 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 		nr = nframes;
 		if (cdi->cdda_method == CDDA_BPC_SINGLE)
 			nr = 1;
-		if (nr * CD_FRAMESIZE_RAW > (q->max_sectors << 9))
-			nr = (q->max_sectors << 9) / CD_FRAMESIZE_RAW;
+		if (nr * CD_FRAMESIZE_RAW > (queue_max_sectors(q) << 9))
+			nr = (queue_max_sectors(q) << 9) / CD_FRAMESIZE_RAW;
 
 		len = nr * CD_FRAMESIZE_RAW;
 
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 65e2d9759857..e9a73bb242b0 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -510,7 +510,7 @@ void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev)
 	 *        combine_restrictions_low()
 	 */
 	rs->max_sectors =
-		min_not_zero(rs->max_sectors, q->max_sectors);
+		min_not_zero(rs->max_sectors, queue_max_sectors(q));
 
 	/*
 	 * Check if merge fn is supported.
@@ -525,25 +525,25 @@ void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev)
 
 	rs->max_phys_segments =
 		min_not_zero(rs->max_phys_segments,
-			     q->max_phys_segments);
+			     queue_max_phys_segments(q));
 
 	rs->max_hw_segments =
-		min_not_zero(rs->max_hw_segments, q->max_hw_segments);
+		min_not_zero(rs->max_hw_segments, queue_max_hw_segments(q));
 
 	rs->logical_block_size = max(rs->logical_block_size,
 				     queue_logical_block_size(q));
 
 	rs->max_segment_size =
-		min_not_zero(rs->max_segment_size, q->max_segment_size);
+		min_not_zero(rs->max_segment_size, queue_max_segment_size(q));
 
 	rs->max_hw_sectors =
-		min_not_zero(rs->max_hw_sectors, q->max_hw_sectors);
+		min_not_zero(rs->max_hw_sectors, queue_max_hw_sectors(q));
 
 	rs->seg_boundary_mask =
 		min_not_zero(rs->seg_boundary_mask,
-			     q->seg_boundary_mask);
+			     queue_segment_boundary(q));
 
-	rs->bounce_pfn = min_not_zero(rs->bounce_pfn, q->bounce_pfn);
+	rs->bounce_pfn = min_not_zero(rs->bounce_pfn, queue_bounce_pfn(q));
 
 	rs->no_cluster |= !test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
 }
@@ -914,13 +914,13 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q)
 	 * restrictions.
 	 */
 	blk_queue_max_sectors(q, t->limits.max_sectors);
-	q->max_phys_segments = t->limits.max_phys_segments;
-	q->max_hw_segments = t->limits.max_hw_segments;
-	q->logical_block_size = t->limits.logical_block_size;
-	q->max_segment_size = t->limits.max_segment_size;
-	q->max_hw_sectors = t->limits.max_hw_sectors;
-	q->seg_boundary_mask = t->limits.seg_boundary_mask;
-	q->bounce_pfn = t->limits.bounce_pfn;
+	blk_queue_max_phys_segments(q, t->limits.max_phys_segments);
+	blk_queue_max_hw_segments(q, t->limits.max_hw_segments);
+	blk_queue_logical_block_size(q, t->limits.logical_block_size);
+	blk_queue_max_segment_size(q, t->limits.max_segment_size);
+	blk_queue_max_hw_sectors(q, t->limits.max_hw_sectors);
+	blk_queue_segment_boundary(q, t->limits.seg_boundary_mask);
+	blk_queue_bounce_limit(q, t->limits.bounce_pfn);
 
 	if (t->limits.no_cluster)
 		queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q);
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 7a36e38393a1..64f1f3e046e0 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -146,7 +146,7 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 		 * a one page request is never in violation.
 		 */
 		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		disk->num_sectors = rdev->sectors;
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 41ced0cbe823..4ee31aa13c40 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -303,7 +303,7 @@ static int multipath_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 		 * merge_bvec_fn will be involved in multipath.)
 		 */
 			if (q->merge_bvec_fn &&
-			    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+			    queue_max_sectors(q) > (PAGE_SIZE>>9))
 				blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 			conf->working_disks++;
@@ -467,7 +467,7 @@ static int multipath_run (mddev_t *mddev)
 		 * violating it, not that we ever expect a device with
 		 * a merge_bvec_fn to be involved in multipath */
 		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		if (!test_bit(Faulty, &rdev->flags))
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index c08d7559be55..925507e7d673 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -144,7 +144,7 @@ static int create_strip_zones (mddev_t *mddev)
 		 */
 
 		if (rdev1->bdev->bd_disk->queue->merge_bvec_fn &&
-		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		if (!smallest || (rdev1->sectors < smallest->sectors))
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 36df9109cde1..e23758b4a34e 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1130,7 +1130,7 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 			 * a one page request is never in violation.
 			 */
 			if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-			    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+			    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
 				blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 			p->head_position = 0;
@@ -1996,7 +1996,7 @@ static int run(mddev_t *mddev)
 		 * a one page request is never in violation.
 		 */
 		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
+		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		disk->head_position = 0;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 499620afb44b..750550c1166f 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1158,8 +1158,8 @@ static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
 			 * a one page request is never in violation.
 			 */
 			if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-			    mddev->queue->max_sectors > (PAGE_SIZE>>9))
-				mddev->queue->max_sectors = (PAGE_SIZE>>9);
+			    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
+				blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 			p->head_position = 0;
 			rdev->raid_disk = mirror;
@@ -2145,8 +2145,8 @@ static int run(mddev_t *mddev)
 		 * a one page request is never in violation.
 		 */
 		if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
-		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
-			mddev->queue->max_sectors = (PAGE_SIZE>>9);
+		    queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
+			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
 		disk->head_position = 0;
 	}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 4616bc3a6e71..7970dc8c522e 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3463,10 +3463,10 @@ static int bio_fits_rdev(struct bio *bi)
 {
 	struct request_queue *q = bdev_get_queue(bi->bi_bdev);
 
-	if ((bi->bi_size>>9) > q->max_sectors)
+	if ((bi->bi_size>>9) > queue_max_sectors(q))
 		return 0;
 	blk_recount_segments(q, bi);
-	if (bi->bi_phys_segments > q->max_phys_segments)
+	if (bi->bi_phys_segments > queue_max_phys_segments(q))
 		return 0;
 
 	if (q->merge_bvec_fn)
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 0fc2c0ae7691..9bd407fa98e4 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -289,8 +289,8 @@ sg_open(struct inode *inode, struct file *filp)
 	if (list_empty(&sdp->sfds)) {	/* no existing opens on this device */
 		sdp->sgdebug = 0;
 		q = sdp->device->request_queue;
-		sdp->sg_tablesize = min(q->max_hw_segments,
-					q->max_phys_segments);
+		sdp->sg_tablesize = min(queue_max_hw_segments(q),
+					queue_max_phys_segments(q));
 	}
 	if ((sfp = sg_add_sfp(sdp, dev)))
 		filp->private_data = sfp;
@@ -909,7 +909,7 @@ sg_ioctl(struct inode *inode, struct file *filp,
                 if (val < 0)
                         return -EINVAL;
 		val = min_t(int, val,
-				sdp->device->request_queue->max_sectors * 512);
+			    queue_max_sectors(sdp->device->request_queue) * 512);
 		if (val != sfp->reserve.bufflen) {
 			if (sg_res_in_use(sfp) || sfp->mmap_called)
 				return -EBUSY;
@@ -919,7 +919,7 @@ sg_ioctl(struct inode *inode, struct file *filp,
 		return 0;
 	case SG_GET_RESERVED_SIZE:
 		val = min_t(int, sfp->reserve.bufflen,
-				sdp->device->request_queue->max_sectors * 512);
+			    queue_max_sectors(sdp->device->request_queue) * 512);
 		return put_user(val, ip);
 	case SG_SET_COMMAND_Q:
 		result = get_user(val, ip);
@@ -1059,7 +1059,7 @@ sg_ioctl(struct inode *inode, struct file *filp,
 			return -ENODEV;
 		return scsi_ioctl(sdp->device, cmd_in, p);
 	case BLKSECTGET:
-		return put_user(sdp->device->request_queue->max_sectors * 512,
+		return put_user(queue_max_sectors(sdp->device->request_queue) * 512,
 				ip);
 	case BLKTRACESETUP:
 		return blk_trace_setup(sdp->device->request_queue,
@@ -1377,7 +1377,8 @@ static Sg_device *sg_alloc(struct gendisk *disk, struct scsi_device *scsidp)
 	sdp->device = scsidp;
 	INIT_LIST_HEAD(&sdp->sfds);
 	init_waitqueue_head(&sdp->o_excl_wait);
-	sdp->sg_tablesize = min(q->max_hw_segments, q->max_phys_segments);
+	sdp->sg_tablesize = min(queue_max_hw_segments(q),
+				queue_max_phys_segments(q));
 	sdp->index = k;
 	kref_init(&sdp->d_ref);
 
@@ -2055,7 +2056,7 @@ sg_add_sfp(Sg_device * sdp, int dev)
 		sg_big_buff = def_reserved_size;
 
 	bufflen = min_t(int, sg_big_buff,
-			sdp->device->request_queue->max_sectors * 512);
+			queue_max_sectors(sdp->device->request_queue) * 512);
 	sg_build_reserve(sfp, bufflen);
 	SCSI_LOG_TIMEOUT(3, printk("sg_add_sfp:   bufflen=%d, k_use_sg=%d\n",
 			   sfp->reserve.bufflen, sfp->reserve.k_use_sg));
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 8681b708344f..89bd438e1fe3 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -3983,8 +3983,8 @@ static int st_probe(struct device *dev)
 		return -ENODEV;
 	}
 
-	i = min(SDp->request_queue->max_hw_segments,
-		SDp->request_queue->max_phys_segments);
+	i = min(queue_max_hw_segments(SDp->request_queue),
+		queue_max_phys_segments(SDp->request_queue));
 	if (st_max_sg_segs < i)
 		i = st_max_sg_segs;
 	buffer = new_tape_buffer((SDp->host)->unchecked_isa_dma, i);
diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c
index 4ca3b5860643..cfa26d56ce60 100644
--- a/drivers/usb/storage/scsiglue.c
+++ b/drivers/usb/storage/scsiglue.c
@@ -132,7 +132,7 @@ static int slave_configure(struct scsi_device *sdev)
 
 		if (us->fflags & US_FL_MAX_SECTORS_MIN)
 			max_sectors = PAGE_CACHE_SIZE >> 9;
-		if (sdev->request_queue->max_sectors > max_sectors)
+		if (queue_max_sectors(sdev->request_queue) > max_sectors)
 			blk_queue_max_sectors(sdev->request_queue,
 					      max_sectors);
 	} else if (sdev->type == TYPE_TAPE) {
@@ -483,7 +483,7 @@ static ssize_t show_max_sectors(struct device *dev, struct device_attribute *att
 {
 	struct scsi_device *sdev = to_scsi_device(dev);
 
-	return sprintf(buf, "%u\n", sdev->request_queue->max_sectors);
+	return sprintf(buf, "%u\n", queue_max_sectors(sdev->request_queue));
 }
 
 /* Input routine for the sysfs max_sectors file */
diff --git a/fs/bio.c b/fs/bio.c
index 4445c3821730..ab423a1024ab 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -499,11 +499,11 @@ int bio_get_nr_vecs(struct block_device *bdev)
 	struct request_queue *q = bdev_get_queue(bdev);
 	int nr_pages;
 
-	nr_pages = ((q->max_sectors << 9) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	if (nr_pages > q->max_phys_segments)
-		nr_pages = q->max_phys_segments;
-	if (nr_pages > q->max_hw_segments)
-		nr_pages = q->max_hw_segments;
+	nr_pages = ((queue_max_sectors(q) << 9) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (nr_pages > queue_max_phys_segments(q))
+		nr_pages = queue_max_phys_segments(q);
+	if (nr_pages > queue_max_hw_segments(q))
+		nr_pages = queue_max_hw_segments(q);
 
 	return nr_pages;
 }
@@ -562,8 +562,8 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 	 * make this too complex.
 	 */
 
-	while (bio->bi_phys_segments >= q->max_phys_segments
-	       || bio->bi_phys_segments >= q->max_hw_segments) {
+	while (bio->bi_phys_segments >= queue_max_phys_segments(q)
+	       || bio->bi_phys_segments >= queue_max_hw_segments(q)) {
 
 		if (retried_segments)
 			return 0;
@@ -634,7 +634,8 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page,
 		    unsigned int len, unsigned int offset)
 {
-	return __bio_add_page(q, bio, page, len, offset, q->max_hw_sectors);
+	return __bio_add_page(q, bio, page, len, offset,
+			      queue_max_hw_sectors(q));
 }
 
 /**
@@ -654,7 +655,7 @@ int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
 		 unsigned int offset)
 {
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	return __bio_add_page(q, bio, page, len, offset, q->max_sectors);
+	return __bio_add_page(q, bio, page, len, offset, queue_max_sectors(q));
 }
 
 struct bio_map_data {
diff --git a/include/linux/bio.h b/include/linux/bio.h
index d30ec6f30dd7..12737be58601 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -279,7 +279,7 @@ static inline int bio_has_allocated_vec(struct bio *bio)
 #define __BIO_SEG_BOUNDARY(addr1, addr2, mask) \
 	(((addr1) | (mask)) == (((addr2) - 1) | (mask)))
 #define BIOVEC_SEG_BOUNDARY(q, b1, b2) \
-	__BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, (q)->seg_boundary_mask)
+	__BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, queue_segment_boundary((q)))
 #define BIO_SEG_BOUNDARY(q, b1, b2) \
 	BIOVEC_SEG_BOUNDARY((q), __BVEC_END((b1)), __BVEC_START((b2)))
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 872b78b7a101..29b48f7b4ba8 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -898,6 +898,7 @@ extern void blk_cleanup_queue(struct request_queue *);
 extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
 extern void blk_queue_bounce_limit(struct request_queue *, u64);
 extern void blk_queue_max_sectors(struct request_queue *, unsigned int);
+extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
@@ -988,6 +989,41 @@ extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter);
 
 #define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist)
 
+static inline unsigned long queue_bounce_pfn(struct request_queue *q)
+{
+	return q->bounce_pfn;
+}
+
+static inline unsigned long queue_segment_boundary(struct request_queue *q)
+{
+	return q->seg_boundary_mask;
+}
+
+static inline unsigned int queue_max_sectors(struct request_queue *q)
+{
+	return q->max_sectors;
+}
+
+static inline unsigned int queue_max_hw_sectors(struct request_queue *q)
+{
+	return q->max_hw_sectors;
+}
+
+static inline unsigned short queue_max_hw_segments(struct request_queue *q)
+{
+	return q->max_hw_segments;
+}
+
+static inline unsigned short queue_max_phys_segments(struct request_queue *q)
+{
+	return q->max_phys_segments;
+}
+
+static inline unsigned int queue_max_segment_size(struct request_queue *q)
+{
+	return q->max_segment_size;
+}
+
 static inline unsigned short queue_logical_block_size(struct request_queue *q)
 {
 	int retval = 512;
diff --git a/mm/bounce.c b/mm/bounce.c
index e590272fe7a8..8dcd4315e01c 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -192,7 +192,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 		/*
 		 * is destination page below bounce pfn?
 		 */
-		if (page_to_pfn(page) <= q->bounce_pfn)
+		if (page_to_pfn(page) <= queue_bounce_pfn(q))
 			continue;
 
 		/*
@@ -284,7 +284,7 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
 	 * don't waste time iterating over bio segments
 	 */
 	if (!(q->bounce_gfp & GFP_DMA)) {
-		if (q->bounce_pfn >= blk_max_pfn)
+		if (queue_bounce_pfn(q) >= blk_max_pfn)
 			return;
 		pool = page_pool;
 	} else {
-- 
cgit v1.2.3


From cd43e26f071524647e660706b784ebcbefbd2e44 Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 22 May 2009 17:17:52 -0400
Subject: block: Expose stacked device queues in sysfs

Currently stacking devices do not have a queue directory in sysfs.
However, many of the I/O characteristics like sector size, maximum
request size, etc. are queue properties.

This patch enables the queue directory for MD/DM devices.  The elevator
code has been modified to deal with queues that do not have an I/O
scheduler.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-sysfs.c |  6 +++---
 block/elevator.c  | 13 ++++++++++++-
 2 files changed, 15 insertions(+), 4 deletions(-)

(limited to 'block/blk-sysfs.c')

diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 142a4acddd43..3ccdadb8e204 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -395,9 +395,6 @@ int blk_register_queue(struct gendisk *disk)
 	if (WARN_ON(!q))
 		return -ENXIO;
 
-	if (!q->request_fn)
-		return 0;
-
 	ret = kobject_add(&q->kobj, kobject_get(&disk_to_dev(disk)->kobj),
 			  "%s", "queue");
 	if (ret < 0)
@@ -405,6 +402,9 @@ int blk_register_queue(struct gendisk *disk)
 
 	kobject_uevent(&q->kobj, KOBJ_ADD);
 
+	if (!q->request_fn)
+		return 0;
+
 	ret = elv_register_queue(q);
 	if (ret) {
 		kobject_uevent(&q->kobj, KOBJ_REMOVE);
diff --git a/block/elevator.c b/block/elevator.c
index ebee948293eb..bd78f693fcf2 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -575,6 +575,9 @@ void elv_drain_elevator(struct request_queue *q)
  */
 void elv_quiesce_start(struct request_queue *q)
 {
+	if (!q->elevator)
+		return;
+
 	queue_flag_set(QUEUE_FLAG_ELVSWITCH, q);
 
 	/*
@@ -1050,6 +1053,9 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 	char elevator_name[ELV_NAME_MAX];
 	struct elevator_type *e;
 
+	if (!q->elevator)
+		return count;
+
 	strlcpy(elevator_name, name, sizeof(elevator_name));
 	strstrip(elevator_name);
 
@@ -1073,10 +1079,15 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 ssize_t elv_iosched_show(struct request_queue *q, char *name)
 {
 	struct elevator_queue *e = q->elevator;
-	struct elevator_type *elv = e->elevator_type;
+	struct elevator_type *elv;
 	struct elevator_type *__e;
 	int len = 0;
 
+	if (!q->elevator)
+		return sprintf(name, "none\n");
+
+	elv = e->elevator_type;
+
 	spin_lock(&elv_list_lock);
 	list_for_each_entry(__e, &elv_list, list) {
 		if (!strcmp(elv->elevator_name, __e->elevator_name))
-- 
cgit v1.2.3


From c72758f33784e5e2a1a4bb9421ef3e6de8f9fcf3 Mon Sep 17 00:00:00 2001
From: "Martin K. Petersen" <martin.petersen@oracle.com>
Date: Fri, 22 May 2009 17:17:53 -0400
Subject: block: Export I/O topology for block devices and partitions

To support devices with physical block sizes bigger than 512 bytes we
need to ensure proper alignment.  This patch adds support for exposing
I/O topology characteristics as devices are stacked.

  logical_block_size is the smallest unit the device can address.

  physical_block_size indicates the smallest I/O the device can write
  without incurring a read-modify-write penalty.

  The io_min parameter is the smallest preferred I/O size reported by
  the device.  In many cases this is the same as the physical block
  size.  However, the io_min parameter can be scaled up when stacking
  (RAID5 chunk size > physical block size).

  The io_opt characteristic indicates the optimal I/O size reported by
  the device.  This is usually the stripe width for arrays.

  The alignment_offset parameter indicates the number of bytes the start
  of the device/partition is offset from the device's natural alignment.
  Partition tools and MD/DM utilities can use this to pad their offsets
  so filesystems start on proper boundaries.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 Documentation/ABI/testing/sysfs-block |  59 +++++++++++
 block/blk-settings.c                  | 186 ++++++++++++++++++++++++++++++++++
 block/blk-sysfs.c                     |  33 ++++++
 block/genhd.c                         |  11 ++
 fs/partitions/check.c                 |  10 ++
 include/linux/blkdev.h                |  47 +++++++++
 include/linux/genhd.h                 |   1 +
 7 files changed, 347 insertions(+)

(limited to 'block/blk-sysfs.c')

diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index 44f52a4f5903..cbbd3e069945 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -60,3 +60,62 @@ Description:
 		Indicates whether the block layer should automatically
 		generate checksums for write requests bound for
 		devices that support receiving integrity metadata.
+
+What:		/sys/block/<disk>/alignment_offset
+Date:		April 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Storage devices may report a physical block size that is
+		bigger than the logical block size (for instance a drive
+		with 4KB physical sectors exposing 512-byte logical
+		blocks to the operating system).  This parameter
+		indicates how many bytes the beginning of the device is
+		offset from the disk's natural alignment.
+
+What:		/sys/block/<disk>/<partition>/alignment_offset
+Date:		April 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Storage devices may report a physical block size that is
+		bigger than the logical block size (for instance a drive
+		with 4KB physical sectors exposing 512-byte logical
+		blocks to the operating system).  This parameter
+		indicates how many bytes the beginning of the partition
+		is offset from the disk's natural alignment.
+
+What:		/sys/block/<disk>/queue/logical_block_size
+Date:		May 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		This is the smallest unit the storage device can
+		address.  It is typically 512 bytes.
+
+What:		/sys/block/<disk>/queue/physical_block_size
+Date:		May 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		This is the smallest unit the storage device can write
+		without resorting to read-modify-write operation.  It is
+		usually the same as the logical block size but may be
+		bigger.  One example is SATA drives with 4KB sectors
+		that expose a 512-byte logical block size to the
+		operating system.
+
+What:		/sys/block/<disk>/queue/minimum_io_size
+Date:		April 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Storage devices may report a preferred minimum I/O size,
+		which is the smallest request the device can perform
+		without incurring a read-modify-write penalty.  For disk
+		drives this is often the physical block size.  For RAID
+		arrays it is often the stripe chunk size.
+
+What:		/sys/block/<disk>/queue/optimal_io_size
+Date:		April 2009
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Storage devices may report an optimal I/O size, which is
+		the device's preferred unit of receiving I/O.  This is
+		rarely reported for disk drives.  For RAID devices it is
+		usually the stripe width or the internal block size.
diff --git a/block/blk-settings.c b/block/blk-settings.c
index b0f547cecfb8..5649f34adb40 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -309,9 +309,94 @@ EXPORT_SYMBOL(blk_queue_max_segment_size);
 void blk_queue_logical_block_size(struct request_queue *q, unsigned short size)
 {
 	q->limits.logical_block_size = size;
+
+	if (q->limits.physical_block_size < size)
+		q->limits.physical_block_size = size;
+
+	if (q->limits.io_min < q->limits.physical_block_size)
+		q->limits.io_min = q->limits.physical_block_size;
 }
 EXPORT_SYMBOL(blk_queue_logical_block_size);
 
+/**
+ * blk_queue_physical_block_size - set physical block size for the queue
+ * @q:  the request queue for the device
+ * @size:  the physical block size, in bytes
+ *
+ * Description:
+ *   This should be set to the lowest possible sector size that the
+ *   hardware can operate on without reverting to read-modify-write
+ *   operations.
+ */
+void blk_queue_physical_block_size(struct request_queue *q, unsigned short size)
+{
+	q->limits.physical_block_size = size;
+
+	if (q->limits.physical_block_size < q->limits.logical_block_size)
+		q->limits.physical_block_size = q->limits.logical_block_size;
+
+	if (q->limits.io_min < q->limits.physical_block_size)
+		q->limits.io_min = q->limits.physical_block_size;
+}
+EXPORT_SYMBOL(blk_queue_physical_block_size);
+
+/**
+ * blk_queue_alignment_offset - set physical block alignment offset
+ * @q:	the request queue for the device
+ * @alignment:	alignment offset in bytes
+ *
+ * Description:
+ *   Some devices are naturally misaligned to compensate for things like
+ *   the legacy DOS partition table 63-sector offset.  Low-level drivers
+ *   should call this function for devices whose first sector is not
+ *   naturally aligned.
+ */
+void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset)
+{
+	q->limits.alignment_offset =
+		offset & (q->limits.physical_block_size - 1);
+	q->limits.misaligned = 0;
+}
+EXPORT_SYMBOL(blk_queue_alignment_offset);
+
+/**
+ * blk_queue_io_min - set minimum request size for the queue
+ * @q:	the request queue for the device
+ * @io_min:  smallest I/O size in bytes
+ *
+ * Description:
+ *   Some devices have an internal block size bigger than the reported
+ *   hardware sector size.  This function can be used to signal the
+ *   smallest I/O the device can perform without incurring a performance
+ *   penalty.
+ */
+void blk_queue_io_min(struct request_queue *q, unsigned int min)
+{
+	q->limits.io_min = min;
+
+	if (q->limits.io_min < q->limits.logical_block_size)
+		q->limits.io_min = q->limits.logical_block_size;
+
+	if (q->limits.io_min < q->limits.physical_block_size)
+		q->limits.io_min = q->limits.physical_block_size;
+}
+EXPORT_SYMBOL(blk_queue_io_min);
+
+/**
+ * blk_queue_io_opt - set optimal request size for the queue
+ * @q:	the request queue for the device
+ * @io_opt:  optimal request size in bytes
+ *
+ * Description:
+ *   Drivers can call this function to set the preferred I/O request
+ *   size for devices that report such a value.
+ */
+void blk_queue_io_opt(struct request_queue *q, unsigned int opt)
+{
+	q->limits.io_opt = opt;
+}
+EXPORT_SYMBOL(blk_queue_io_opt);
+
 /*
  * Returns the minimum that is _not_ zero, unless both are zero.
  */
@@ -357,6 +442,107 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 }
 EXPORT_SYMBOL(blk_queue_stack_limits);
 
+/**
+ * blk_stack_limits - adjust queue_limits for stacked devices
+ * @t:	the stacking driver limits (top)
+ * @bdev:  the underlying queue limits (bottom)
+ * @offset:  offset to beginning of data within component device
+ *
+ * Description:
+ *    Merges two queue_limit structs.  Returns 0 if alignment didn't
+ *    change.  Returns -1 if adding the bottom device caused
+ *    misalignment.
+ */
+int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
+		     sector_t offset)
+{
+	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
+	t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
+
+	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
+					    b->seg_boundary_mask);
+
+	t->max_phys_segments = min_not_zero(t->max_phys_segments,
+					    b->max_phys_segments);
+
+	t->max_hw_segments = min_not_zero(t->max_hw_segments,
+					  b->max_hw_segments);
+
+	t->max_segment_size = min_not_zero(t->max_segment_size,
+					   b->max_segment_size);
+
+	t->logical_block_size = max(t->logical_block_size,
+				    b->logical_block_size);
+
+	t->physical_block_size = max(t->physical_block_size,
+				     b->physical_block_size);
+
+	t->io_min = max(t->io_min, b->io_min);
+	t->no_cluster |= b->no_cluster;
+
+	/* Bottom device offset aligned? */
+	if (offset &&
+	    (offset & (b->physical_block_size - 1)) != b->alignment_offset) {
+		t->misaligned = 1;
+		return -1;
+	}
+
+	/* If top has no alignment offset, inherit from bottom */
+	if (!t->alignment_offset)
+		t->alignment_offset =
+			b->alignment_offset & (b->physical_block_size - 1);
+
+	/* Top device aligned on logical block boundary? */
+	if (t->alignment_offset & (t->logical_block_size - 1)) {
+		t->misaligned = 1;
+		return -1;
+	}
+
+	return 0;
+}
+
+/**
+ * disk_stack_limits - adjust queue limits for stacked drivers
+ * @t:	MD/DM gendisk (top)
+ * @bdev:  the underlying block device (bottom)
+ * @offset:  offset to beginning of data within component device
+ *
+ * Description:
+ *    Merges the limits for two queues.  Returns 0 if alignment
+ *    didn't change.  Returns -1 if adding the bottom device caused
+ *    misalignment.
+ */
+void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
+		       sector_t offset)
+{
+	struct request_queue *t = disk->queue;
+	struct request_queue *b = bdev_get_queue(bdev);
+
+	offset += get_start_sect(bdev) << 9;
+
+	if (blk_stack_limits(&t->limits, &b->limits, offset) < 0) {
+		char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE];
+
+		disk_name(disk, 0, top);
+		bdevname(bdev, bottom);
+
+		printk(KERN_NOTICE "%s: Warning: Device %s is misaligned\n",
+		       top, bottom);
+	}
+
+	if (!t->queue_lock)
+		WARN_ON_ONCE(1);
+	else if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(t->queue_lock, flags);
+		if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags))
+			queue_flag_clear(QUEUE_FLAG_CLUSTER, t);
+		spin_unlock_irqrestore(t->queue_lock, flags);
+	}
+}
+EXPORT_SYMBOL(disk_stack_limits);
+
 /**
  * blk_queue_dma_pad - set pad mask
  * @q:     the request queue for the device
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 3ccdadb8e204..9337e17f9110 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -105,6 +105,21 @@ static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page
 	return queue_var_show(queue_logical_block_size(q), page);
 }
 
+static ssize_t queue_physical_block_size_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_physical_block_size(q), page);
+}
+
+static ssize_t queue_io_min_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_io_min(q), page);
+}
+
+static ssize_t queue_io_opt_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(queue_io_opt(q), page);
+}
+
 static ssize_t
 queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 {
@@ -257,6 +272,21 @@ static struct queue_sysfs_entry queue_logical_block_size_entry = {
 	.show = queue_logical_block_size_show,
 };
 
+static struct queue_sysfs_entry queue_physical_block_size_entry = {
+	.attr = {.name = "physical_block_size", .mode = S_IRUGO },
+	.show = queue_physical_block_size_show,
+};
+
+static struct queue_sysfs_entry queue_io_min_entry = {
+	.attr = {.name = "minimum_io_size", .mode = S_IRUGO },
+	.show = queue_io_min_show,
+};
+
+static struct queue_sysfs_entry queue_io_opt_entry = {
+	.attr = {.name = "optimal_io_size", .mode = S_IRUGO },
+	.show = queue_io_opt_show,
+};
+
 static struct queue_sysfs_entry queue_nonrot_entry = {
 	.attr = {.name = "rotational", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_nonrot_show,
@@ -289,6 +319,9 @@ static struct attribute *default_attrs[] = {
 	&queue_iosched_entry.attr,
 	&queue_hw_sector_size_entry.attr,
 	&queue_logical_block_size_entry.attr,
+	&queue_physical_block_size_entry.attr,
+	&queue_io_min_entry.attr,
+	&queue_io_opt_entry.attr,
 	&queue_nonrot_entry.attr,
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
diff --git a/block/genhd.c b/block/genhd.c
index 1a4916e01732..fe7ccc0a618f 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -852,11 +852,21 @@ static ssize_t disk_capability_show(struct device *dev,
 	return sprintf(buf, "%x\n", disk->flags);
 }
 
+static ssize_t disk_alignment_offset_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+
+	return sprintf(buf, "%d\n", queue_alignment_offset(disk->queue));
+}
+
 static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL);
 static DEVICE_ATTR(ext_range, S_IRUGO, disk_ext_range_show, NULL);
 static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL);
 static DEVICE_ATTR(ro, S_IRUGO, disk_ro_show, NULL);
 static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
+static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL);
 static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
@@ -875,6 +885,7 @@ static struct attribute *disk_attrs[] = {
 	&dev_attr_removable.attr,
 	&dev_attr_ro.attr,
 	&dev_attr_size.attr,
+	&dev_attr_alignment_offset.attr,
 	&dev_attr_capability.attr,
 	&dev_attr_stat.attr,
 #ifdef CONFIG_FAIL_MAKE_REQUEST
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 99e33ef40be4..0af36085eb28 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -219,6 +219,13 @@ ssize_t part_size_show(struct device *dev,
 	return sprintf(buf, "%llu\n",(unsigned long long)p->nr_sects);
 }
 
+ssize_t part_alignment_offset_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct hd_struct *p = dev_to_part(dev);
+	return sprintf(buf, "%llu\n", (unsigned long long)p->alignment_offset);
+}
+
 ssize_t part_stat_show(struct device *dev,
 		       struct device_attribute *attr, char *buf)
 {
@@ -272,6 +279,7 @@ ssize_t part_fail_store(struct device *dev,
 static DEVICE_ATTR(partition, S_IRUGO, part_partition_show, NULL);
 static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL);
 static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
+static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL);
 static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 static struct device_attribute dev_attr_fail =
@@ -282,6 +290,7 @@ static struct attribute *part_attrs[] = {
 	&dev_attr_partition.attr,
 	&dev_attr_start.attr,
 	&dev_attr_size.attr,
+	&dev_attr_alignment_offset.attr,
 	&dev_attr_stat.attr,
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	&dev_attr_fail.attr,
@@ -383,6 +392,7 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
 	pdev = part_to_dev(p);
 
 	p->start_sect = start;
+	p->alignment_offset = queue_sector_alignment_offset(disk->queue, start);
 	p->nr_sects = len;
 	p->partno = partno;
 	p->policy = get_disk_ro(disk);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b7bb6fdba12c..5e740a135e73 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -314,11 +314,16 @@ struct queue_limits {
 	unsigned int		max_hw_sectors;
 	unsigned int		max_sectors;
 	unsigned int		max_segment_size;
+	unsigned int		physical_block_size;
+	unsigned int		alignment_offset;
+	unsigned int		io_min;
+	unsigned int		io_opt;
 
 	unsigned short		logical_block_size;
 	unsigned short		max_hw_segments;
 	unsigned short		max_phys_segments;
 
+	unsigned char		misaligned;
 	unsigned char		no_cluster;
 };
 
@@ -911,6 +916,15 @@ extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
 extern void blk_queue_logical_block_size(struct request_queue *, unsigned short);
+extern void blk_queue_physical_block_size(struct request_queue *, unsigned short);
+extern void blk_queue_alignment_offset(struct request_queue *q,
+				       unsigned int alignment);
+extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
+extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
+extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
+			    sector_t offset);
+extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
+			      sector_t offset);
 extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b);
 extern void blk_queue_dma_pad(struct request_queue *, unsigned int);
 extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
@@ -1047,6 +1061,39 @@ static inline unsigned short bdev_logical_block_size(struct block_device *bdev)
 	return queue_logical_block_size(bdev_get_queue(bdev));
 }
 
+static inline unsigned int queue_physical_block_size(struct request_queue *q)
+{
+	return q->limits.physical_block_size;
+}
+
+static inline unsigned int queue_io_min(struct request_queue *q)
+{
+	return q->limits.io_min;
+}
+
+static inline unsigned int queue_io_opt(struct request_queue *q)
+{
+	return q->limits.io_opt;
+}
+
+static inline int queue_alignment_offset(struct request_queue *q)
+{
+	if (q && q->limits.misaligned)
+		return -1;
+
+	if (q && q->limits.alignment_offset)
+		return q->limits.alignment_offset;
+
+	return 0;
+}
+
+static inline int queue_sector_alignment_offset(struct request_queue *q,
+						sector_t sector)
+{
+	return ((sector << 9) - q->limits.alignment_offset)
+		& (q->limits.io_min - 1);
+}
+
 static inline int queue_dma_alignment(struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index a1a28caed23d..149fda264c86 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -90,6 +90,7 @@ struct disk_stats {
 struct hd_struct {
 	sector_t start_sect;
 	sector_t nr_sects;
+	sector_t alignment_offset;
 	struct device __dev;
 	struct kobject *holder_dir;
 	int policy, partno;
-- 
cgit v1.2.3