block: Make generic_make_request handle arbitrary sized bios

The way the block layer is currently written, it goes to great lengths
to avoid having to split bios; upper layer code (such as bio_add_page())
checks what the underlying device can handle and tries to always create
bios that don't need to be split.

But this approach becomes unwieldy and eventually breaks down with
stacked devices and devices with dynamic limits, and it adds a lot of
complexity. If the block layer could split bios as needed, we could
eliminate a lot of complexity elsewhere - particularly in stacked
drivers. Code that creates bios can then create whatever size bios are
convenient, and more importantly stacked drivers don't have to deal with
both their own bio size limitations and the limitations of the
(potentially multiple) devices underneath them.  In the future this will
let us delete merge_bvec_fn and a bunch of other code.

We do this by adding calls to blk_queue_split() to the various
make_request functions that need it - a few can already handle arbitrary
size bios. Note that we add the call _after_ any call to blk_queue_bounce();
this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be
concerned with bouncing affecting segment merging.

Some make_request_fns were simple enough to audit and verify they don't
need blk_queue_split() calls. The skipped ones are:

 * nfhd_make_request (arch/m68k/emu/nfblock.c)
 * axon_ram_make_request (arch/powerpc/sysdev/axonram.c)
 * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c)
 * brd_make_request (ramdisk - drivers/block/brd.c)
 * loop_make_request
 * null_queue_bio
 * bcache's make_request fns

Some others are almost certainly safe to remove now, but will be left for future
patches.

Signed-off-by: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Neil Brown <neilb@suse.de>
Cc: Alasdair Kergon <agk@redhat.com>
Cc: dm-devel@redhat.com
Cc: Lars Ellenberg <drbd-dev@lists.linbit.com>
Cc: drbd-user@lists.linbit.com
Cc: Asai Thambi S P <asamymuthupa@micron.com>
Cc: Sam Bradshaw <sbradshaw@micron.com>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: linux-nvme@lists.infradead.org
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Jim Paris <jim@jtan.com>
Cc: Joshua Morris <josh.h.morris@us.ibm.com>
Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Peng Tao <bergwolf@gmail.com>

17 files changed, 183 insertions, 22 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index 9aca8c71e70b..6ed619cae4b3 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -580,6 +580,10 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	if (q->id < 0)
 		goto fail_q;
 
+	q->bio_split = bioset_create(4, 0);
+	if (!q->bio_split)
+		goto fail_id;
+
 	q->backing_dev_info.ra_pages =
 			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
 	q->backing_dev_info.state = 0;
@@ -589,7 +593,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 
 	err = bdi_init(&q->backing_dev_info);
 	if (err)
-		goto fail_id;
+		goto fail_split;
 
 	setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
 		    laptop_mode_timer_fn, (unsigned long) q);
@@ -634,6 +638,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 
 fail_bdi:
 	bdi_destroy(&q->backing_dev_info);
+fail_split:
+	bioset_free(q->bio_split);
 fail_id:
 	ida_simple_remove(&blk_queue_ida, q->id);
 fail_q:
@@ -1551,6 +1557,8 @@ void blk_queue_bio(struct request_queue *q, struct bio *bio)
 	struct request *req;
 	unsigned int request_count = 0;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	/*
 	 * low level driver can indicate that it wants pages above a
 	 * certain limit bounced to low memory (ie for highmem, or even
@@ -1774,15 +1782,6 @@ generic_make_request_checks(struct bio *bio)
 		goto end_io;
 	}
 
-	if (likely(bio_is_rw(bio) &&
-		   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),
-		       queue_max_hw_sectors(q));
-		goto end_io;
-	}
-
 	part = bio->bi_bdev->bd_part;
 	if (should_fail_request(part, bio->bi_iter.bi_size) ||
 	    should_fail_request(&part_to_disk(part)->part0,
diff --git a/block/blk-merge.c b/block/blk-merge.c
index b3bf0df0f4c2..1e6e4eeac07e 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -9,11 +9,149 @@
 
 #include "blk.h"
 
+static struct bio *blk_bio_discard_split(struct request_queue *q,
+					 struct bio *bio,
+					 struct bio_set *bs)
+{
+	unsigned int max_discard_sectors, granularity;
+	int alignment;
+	sector_t tmp;
+	unsigned split_sectors;
+
+	/* Zero-sector (unknown) and one-sector granularities are the same.  */
+	granularity = max(q->limits.discard_granularity >> 9, 1U);
+
+	max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
+	max_discard_sectors -= max_discard_sectors % granularity;
+
+	if (unlikely(!max_discard_sectors)) {
+		/* XXX: warn */
+		return NULL;
+	}
+
+	if (bio_sectors(bio) <= max_discard_sectors)
+		return NULL;
+
+	split_sectors = max_discard_sectors;
+
+	/*
+	 * If the next starting sector would be misaligned, stop the discard at
+	 * the previous aligned sector.
+	 */
+	alignment = (q->limits.discard_alignment >> 9) % granularity;
+
+	tmp = bio->bi_iter.bi_sector + split_sectors - alignment;
+	tmp = sector_div(tmp, granularity);
+
+	if (split_sectors > tmp)
+		split_sectors -= tmp;
+
+	return bio_split(bio, split_sectors, GFP_NOIO, bs);
+}
+
+static struct bio *blk_bio_write_same_split(struct request_queue *q,
+					    struct bio *bio,
+					    struct bio_set *bs)
+{
+	if (!q->limits.max_write_same_sectors)
+		return NULL;
+
+	if (bio_sectors(bio) <= q->limits.max_write_same_sectors)
+		return NULL;
+
+	return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs);
+}
+
+static struct bio *blk_bio_segment_split(struct request_queue *q,
+					 struct bio *bio,
+					 struct bio_set *bs)
+{
+	struct bio *split;
+	struct bio_vec bv, bvprv;
+	struct bvec_iter iter;
+	unsigned seg_size = 0, nsegs = 0;
+	int prev = 0;
+
+	struct bvec_merge_data bvm = {
+		.bi_bdev	= bio->bi_bdev,
+		.bi_sector	= bio->bi_iter.bi_sector,
+		.bi_size	= 0,
+		.bi_rw		= bio->bi_rw,
+	};
+
+	bio_for_each_segment(bv, bio, iter) {
+		if (q->merge_bvec_fn &&
+		    q->merge_bvec_fn(q, &bvm, &bv) < (int) bv.bv_len)
+			goto split;
+
+		bvm.bi_size += bv.bv_len;
+
+		if (bvm.bi_size >> 9 > queue_max_sectors(q))
+			goto split;
+
+		if (prev && blk_queue_cluster(q)) {
+			if (seg_size + bv.bv_len > queue_max_segment_size(q))
+				goto new_segment;
+			if (!BIOVEC_PHYS_MERGEABLE(&bvprv, &bv))
+				goto new_segment;
+			if (!BIOVEC_SEG_BOUNDARY(q, &bvprv, &bv))
+				goto new_segment;
+
+			seg_size += bv.bv_len;
+			bvprv = bv;
+			prev = 1;
+			continue;
+		}
+new_segment:
+		if (nsegs == queue_max_segments(q))
+			goto split;
+
+		nsegs++;
+		bvprv = bv;
+		prev = 1;
+		seg_size = bv.bv_len;
+	}
+
+	return NULL;
+split:
+	split = bio_clone_bioset(bio, GFP_NOIO, bs);
+
+	split->bi_iter.bi_size -= iter.bi_size;
+	bio->bi_iter = iter;
+
+	if (bio_integrity(bio)) {
+		bio_integrity_advance(bio, split->bi_iter.bi_size);
+		bio_integrity_trim(split, 0, bio_sectors(split));
+	}
+
+	return split;
+}
+
+void blk_queue_split(struct request_queue *q, struct bio **bio,
+		     struct bio_set *bs)
+{
+	struct bio *split;
+
+	if ((*bio)->bi_rw & REQ_DISCARD)
+		split = blk_bio_discard_split(q, *bio, bs);
+	else if ((*bio)->bi_rw & REQ_WRITE_SAME)
+		split = blk_bio_write_same_split(q, *bio, bs);
+	else
+		split = blk_bio_segment_split(q, *bio, q->bio_split);
+
+	if (split) {
+		bio_chain(split, *bio);
+		generic_make_request(*bio);
+		*bio = split;
+	}
+}
+EXPORT_SYMBOL(blk_queue_split);
+
 static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 					     struct bio *bio)
 {
 	struct bio_vec bv, bvprv = { NULL };
-	int cluster, high, highprv = 1, no_sg_merge;
+	int cluster, prev = 0, no_sg_merge;
 	unsigned int seg_size, nr_phys_segs;
 	struct bio *fbio, *bbio;
 	struct bvec_iter iter;
@@ -36,7 +174,6 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 	seg_size = 0;
 	nr_phys_segs = 0;
 	no_sg_merge = test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags);
-	high = 0;
 	for_each_bio(bio) {
 		bio_for_each_segment(bv, bio, iter) {
 			/*
@@ -46,13 +183,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 			if (no_sg_merge)
 				goto new_segment;
 
-			/*
-			 * the trick here is making sure that a high page is
-			 * never considered part of another segment, since
-			 * that might change with the bounce page.
-			 */
-			high = page_to_pfn(bv.bv_page) > queue_bounce_pfn(q);
-			if (!high && !highprv && cluster) {
+			if (prev && cluster) {
 				if (seg_size + bv.bv_len
 				    > queue_max_segment_size(q))
 					goto new_segment;
@@ -72,8 +203,8 @@ new_segment:
 
 			nr_phys_segs++;
 			bvprv = bv;
+			prev = 1;
 			seg_size = bv.bv_len;
-			highprv = high;
 		}
 		bbio = bio;
 	}
diff --git a/block/blk-mq.c b/block/blk-mq.c
index e11f5f8e0313..1b53d92f0d78 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1264,6 +1264,8 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		return;
 	}
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	if (use_plug && !blk_queue_nomerges(q) &&
 	    blk_attempt_plug_merge(q, bio, &request_count))
 		return;
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 09803d0d5207..be427ea700ff 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1308,6 +1308,8 @@ void drbd_make_request(struct request_queue *q, struct bio *bio)
 	struct drbd_device *device = (struct drbd_device *) q->queuedata;
 	unsigned long start_time;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	start_time = jiffies;
 
 	/*
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 295f3afbbef5..9dbd1417b9c5 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3716,6 +3716,8 @@ static int mtip_submit_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
 	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
 	unsigned int nents;
 
+	blk_queue_split(queue, &bio, queue->bio_split);
+
 	if (unlikely(dd->dd_flag & MTIP_DDF_STOP_IO)) {
 		if (unlikely(test_bit(MTIP_DDF_REMOVE_PENDING_BIT,
 							&dd->dd_flag))) {
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index a842c71dcc21..b756403b327a 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -794,6 +794,8 @@ static void nvme_make_request(struct request_queue *q, struct bio *bio)
 	struct nvme_queue *nvmeq = get_nvmeq(ns->dev);
 	int result = -EBUSY;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	if (!nvmeq) {
 		put_nvmeq(NULL);
 		bio_endio(bio, -EIO);
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 758ac442c5b5..9e898ee3be93 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2444,6 +2444,10 @@ static void pkt_make_request(struct request_queue *q, struct bio *bio)
 	char b[BDEVNAME_SIZE];
 	struct bio *split;
 
+	blk_queue_bounce(q, &bio);
+
+	blk_queue_split(q, &bio, q->bio_split);
+
 	pd = q->queuedata;
 	if (!pd) {
 		pr_err("%s incorrect request queue\n",
@@ -2474,8 +2478,6 @@ static void pkt_make_request(struct request_queue *q, struct bio *bio)
 		goto end_io;
 	}
 
-	blk_queue_bounce(q, &bio);
-
 	do {
 		sector_t zone = get_zone(bio->bi_iter.bi_sector, pd);
 		sector_t last_zone = get_zone(bio_end_sector(bio) - 1, pd);
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index ef45cfb98fd2..a995972961a4 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -603,6 +603,8 @@ static void ps3vram_make_request(struct request_queue *q, struct bio *bio)
 	struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
 	int busy;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	dev_dbg(&dev->core, "%s\n", __func__);
 
 	spin_lock_irq(&priv->lock);
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index 2839d37e5af7..ff074a3cd429 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -169,6 +169,8 @@ static void rsxx_make_request(struct request_queue *q, struct bio *bio)
 	struct rsxx_bio_meta *bio_meta;
 	int st = -EINVAL;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	might_sleep();
 
 	if (!card)
diff --git a/drivers/block/umem.c b/drivers/block/umem.c
index 4cf81b5bf0f7..13d577cfbcb4 100644
--- a/drivers/block/umem.c
+++ b/drivers/block/umem.c
@@ -531,6 +531,8 @@ static void mm_make_request(struct request_queue *q, struct bio *bio)
 		 (unsigned long long)bio->bi_iter.bi_sector,
 		 bio->bi_iter.bi_size);
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	spin_lock_irq(&card->lock);
 	*card->biotail = bio;
 	bio->bi_next = NULL;
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 48eccb350180..30a4daebf9c2 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -776,6 +776,8 @@ static void zram_make_request(struct request_queue *queue, struct bio *bio)
 {
 	struct zram *zram = queue->queuedata;
 
+	blk_queue_split(queue, &bio, queue->bio_split);
+
 	down_read(&zram->init_lock);
 	if (unlikely(!init_done(zram)))
 		goto error;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index aa9e093343d4..660bfac53f01 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1497,6 +1497,8 @@ static void dm_request(struct request_queue *q, struct bio *bio)
 {
 	struct mapped_device *md = q->queuedata;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	if (dm_request_based(md))
 		blk_queue_bio(q, bio);
 	else
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 34846856dbc6..52a806998d92 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -256,6 +256,8 @@ static void md_make_request(struct request_queue *q, struct bio *bio)
 	int cpu;
 	unsigned int sectors;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	if (mddev == NULL || mddev->pers == NULL
 	    || !mddev->ready) {
 		bio_io_error(bio);
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index ee0e85abe1fd..3abf56ac8eb2 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -815,6 +815,8 @@ dcssblk_make_request(struct request_queue *q, struct bio *bio)
 	unsigned long source_addr;
 	unsigned long bytes_done;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	bytes_done = 0;
 	dev_info = bio->bi_bdev->bd_disk->private_data;
 	if (dev_info == NULL)
diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c
index 6969d39f1e2e..f03c103f13eb 100644
--- a/drivers/s390/block/xpram.c
+++ b/drivers/s390/block/xpram.c
@@ -190,6 +190,8 @@ static void xpram_make_request(struct request_queue *q, struct bio *bio)
 	unsigned long page_addr;
 	unsigned long bytes;
 
+	blk_queue_split(q, &bio, q->bio_split);
+
 	if ((bio->bi_iter.bi_sector & 7) != 0 ||
 	    (bio->bi_iter.bi_size & 4095) != 0)
 		/* Request is not page-aligned. */
diff --git a/drivers/staging/lustre/lustre/llite/lloop.c b/drivers/staging/lustre/lustre/llite/lloop.c
index 0ff8c3362a8d..35d4e3b8e75b 100644
--- a/drivers/staging/lustre/lustre/llite/lloop.c
+++ b/drivers/staging/lustre/lustre/llite/lloop.c
@@ -341,6 +341,8 @@ static void loop_make_request(struct request_queue *q, struct bio *old_bio)
 	int rw = bio_rw(old_bio);
 	int inactive;
 
+	blk_queue_split(q, &old_bio, q->bio_split);
+
 	if (!lo)
 		goto err;
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 31e11051f1ba..78718c9e2ac7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -488,6 +488,7 @@ struct request_queue {
 
 	struct blk_mq_tag_set	*tag_set;
 	struct list_head	tag_set_list;
+	struct bio_set		*bio_split;
 };
 
 #define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */
@@ -810,6 +811,8 @@ extern void blk_rq_unprep_clone(struct request *rq);
 extern int blk_insert_cloned_request(struct request_queue *q,
 				     struct request *rq);
 extern void blk_delay_queue(struct request_queue *, unsigned long);
+extern void blk_queue_split(struct request_queue *, struct bio **,
+			    struct bio_set *);
 extern void blk_recount_segments(struct request_queue *, struct bio *);
 extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int);
 extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t,