block: Abstract out bvec iterator

Immutable biovecs are going to require an explicit iterator. To
implement immutable bvecs, a later patch is going to add a bi_bvec_done
member to this struct; for now, this patch effectively just renames
things.

Signed-off-by: Kent Overstreet <[email protected]>
Cc: Jens Axboe <[email protected]>
Cc: Geert Uytterhoeven <[email protected]>
Cc: Benjamin Herrenschmidt <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: "Ed L. Cashin" <[email protected]>
Cc: Nick Piggin <[email protected]>
Cc: Lars Ellenberg <[email protected]>
Cc: Jiri Kosina <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Geoff Levand <[email protected]>
Cc: Yehuda Sadeh <[email protected]>
Cc: Sage Weil <[email protected]>
Cc: Alex Elder <[email protected]>
Cc: [email protected]
Cc: Joshua Morris <[email protected]>
Cc: Philip Kelleher <[email protected]>
Cc: Rusty Russell <[email protected]>
Cc: "Michael S. Tsirkin" <[email protected]>
Cc: Konrad Rzeszutek Wilk <[email protected]>
Cc: Jeremy Fitzhardinge <[email protected]>
Cc: Neil Brown <[email protected]>
Cc: Alasdair Kergon <[email protected]>
Cc: Mike Snitzer <[email protected]>
Cc: [email protected]
Cc: Martin Schwidefsky <[email protected]>
Cc: Heiko Carstens <[email protected]>
Cc: [email protected]
Cc: Boaz Harrosh <[email protected]>
Cc: Benny Halevy <[email protected]>
Cc: "James E.J. Bottomley" <[email protected]>
Cc: Greg Kroah-Hartman <[email protected]>
Cc: "Nicholas A. Bellinger" <[email protected]>
Cc: Alexander Viro <[email protected]>
Cc: Chris Mason <[email protected]>
Cc: "Theodore Ts'o" <[email protected]>
Cc: Andreas Dilger <[email protected]>
Cc: Jaegeuk Kim <[email protected]>
Cc: Steven Whitehouse <[email protected]>
Cc: Dave Kleikamp <[email protected]>
Cc: Joern Engel <[email protected]>
Cc: Prasad Joshi <[email protected]>
Cc: Trond Myklebust <[email protected]>
Cc: KONISHI Ryusuke <[email protected]>
Cc: Mark Fasheh <[email protected]>
Cc: Joel Becker <[email protected]>
Cc: Ben Myers <[email protected]>
Cc: [email protected]
Cc: Steven Rostedt <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Len Brown <[email protected]>
Cc: Pavel Machek <[email protected]>
Cc: "Rafael J. Wysocki" <[email protected]>
Cc: Herton Ronaldo Krzesinski <[email protected]>
Cc: Ben Hutchings <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Guo Chao <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: Asai Thambi S P <[email protected]>
Cc: Selvan Mani <[email protected]>
Cc: Sam Bradshaw <[email protected]>
Cc: Wei Yongjun <[email protected]>
Cc: "Roger Pau Monné" <[email protected]>
Cc: Jan Beulich <[email protected]>
Cc: Stefano Stabellini <[email protected]>
Cc: Ian Campbell <[email protected]>
Cc: Sebastian Ott <[email protected]>
Cc: Christian Borntraeger <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Jiang Liu <[email protected]>
Cc: Nitin Gupta <[email protected]>
Cc: Jerome Marchand <[email protected]>
Cc: Joe Perches <[email protected]>
Cc: Peng Tao <[email protected]>
Cc: Andy Adamson <[email protected]>
Cc: fanchaoting <[email protected]>
Cc: Jie Liu <[email protected]>
Cc: Sunil Mushran <[email protected]>
Cc: "Martin K. Petersen" <[email protected]>
Cc: Namjae Jeon <[email protected]>
Cc: Pankaj Kumar <[email protected]>
Cc: Dan Magenheimer <[email protected]>
Cc: Mel Gorman <[email protected]>6

Author: Kent Overstreet

Documentation/block/biodoc.txt

@@ -447,14 +447,13 @@ struct bio_vec {
  * main unit of I/O for the block layer and lower layers (ie drivers)
  */
 struct bio {
-       sector_t            bi_sector;
        struct bio          *bi_next;    /* request queue link */
        struct block_device *bi_bdev;	/* target device */
        unsigned long       bi_flags;    /* status, command, etc */
        unsigned long       bi_rw;       /* low bits: r/w, high: priority */
 
        unsigned int	bi_vcnt;     /* how may bio_vec's */
-       unsigned int	bi_idx;		/* current index into bio_vec array */
+       struct bvec_iter	bi_iter;	/* current index into bio_vec array */
 
        unsigned int	bi_size;     /* total size in bytes */
        unsigned short 	bi_phys_segments; /* segments after physaddr coalesce*/
@@ -480,7 +479,7 @@ With this multipage bio design:
 - Code that traverses the req list can find all the segments of a bio
   by using rq_for_each_segment.  This handles the fact that a request
   has multiple bios, each of which can have multiple segments.
-- Drivers which can't process a large bio in one shot can use the bi_idx
+- Drivers which can't process a large bio in one shot can use the bi_iter
   field to keep track of the next bio_vec entry to process.
   (e.g a 1MB bio_vec needs to be handled in max 128kB chunks for IDE)
   [TBD: Should preferably also have a bi_voffset and bi_vlen to avoid modifying
@@ -589,7 +588,7 @@ driver should not modify these values. The block layer sets up the
 nr_sectors and current_nr_sectors fields (based on the corresponding
 hard_xxx values and the number of bytes transferred) and updates it on
 every transfer that invokes end_that_request_first. It does the same for the
-buffer, bio, bio->bi_idx fields too.
+buffer, bio, bio->bi_iter fields too.
 
 The buffer field is just a virtual address mapping of the current segment
 of the i/o buffer in cases where the buffer resides in low-memory. For high

arch/m68k/emu/nfblock.c

@@ -64,7 +64,7 @@ static void nfhd_make_request(struct request_queue *queue, struct bio *bio)
 	struct nfhd_device *dev = queue->queuedata;
 	struct bio_vec *bvec;
 	int i, dir, len, shift;
-	sector_t sec = bio->bi_sector;
+	sector_t sec = bio->bi_iter.bi_sector;
 
 	dir = bio_data_dir(bio);
 	shift = dev->bshift;

arch/powerpc/sysdev/axonram.c

@@ -113,7 +113,8 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio)
 	unsigned int transfered;
 	unsigned short idx;
 
-	phys_mem = bank->io_addr + (bio->bi_sector << AXON_RAM_SECTOR_SHIFT);
+	phys_mem = bank->io_addr + (bio->bi_iter.bi_sector <<
+				    AXON_RAM_SECTOR_SHIFT);
 	phys_end = bank->io_addr + bank->size;
 	transfered = 0;
 	bio_for_each_segment(vec, bio, idx) {

block/blk-core.c

@@ -130,7 +130,7 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 	bio_advance(bio, nbytes);
 
 	/* don't actually finish bio if it's part of flush sequence */
-	if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
+	if (bio->bi_iter.bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
 		bio_endio(bio, error);
 }
 
@@ -1326,7 +1326,7 @@ void blk_add_request_payload(struct request *rq, struct page *page,
 	bio->bi_io_vec->bv_offset = 0;
 	bio->bi_io_vec->bv_len = len;
 
-	bio->bi_size = len;
+	bio->bi_iter.bi_size = len;
 	bio->bi_vcnt = 1;
 	bio->bi_phys_segments = 1;
 
@@ -1351,7 +1351,7 @@ bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
 
 	req->biotail->bi_next = bio;
 	req->biotail = bio;
-	req->__data_len += bio->bi_size;
+	req->__data_len += bio->bi_iter.bi_size;
 	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
 
 	blk_account_io_start(req, false);
@@ -1380,8 +1380,8 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
 	 * not touch req->buffer either...
 	 */
 	req->buffer = bio_data(bio);
-	req->__sector = bio->bi_sector;
-	req->__data_len += bio->bi_size;
+	req->__sector = bio->bi_iter.bi_sector;
+	req->__data_len += bio->bi_iter.bi_size;
 	req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
 
 	blk_account_io_start(req, false);
@@ -1459,7 +1459,7 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 		req->cmd_flags |= REQ_FAILFAST_MASK;
 
 	req->errors = 0;
-	req->__sector = bio->bi_sector;
+	req->__sector = bio->bi_iter.bi_sector;
 	req->ioprio = bio_prio(bio);
 	blk_rq_bio_prep(req->q, req, bio);
 }
@@ -1583,12 +1583,12 @@ static inline void blk_partition_remap(struct bio *bio)
 	if (bio_sectors(bio) && bdev != bdev->bd_contains) {
 		struct hd_struct *p = bdev->bd_part;
 
-		bio->bi_sector += p->start_sect;
+		bio->bi_iter.bi_sector += p->start_sect;
 		bio->bi_bdev = bdev->bd_contains;
 
 		trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), bio,
 				      bdev->bd_dev,
-				      bio->bi_sector - p->start_sect);
+				      bio->bi_iter.bi_sector - p->start_sect);
 	}
 }
 
@@ -1654,7 +1654,7 @@ static inline int bio_check_eod(struct bio *bio, unsigned int nr_sectors)
 	/* Test device or partition size, when known. */
 	maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
 	if (maxsector) {
-		sector_t sector = bio->bi_sector;
+		sector_t sector = bio->bi_iter.bi_sector;
 
 		if (maxsector < nr_sectors || maxsector - nr_sectors < sector) {
 			/*
@@ -1690,7 +1690,7 @@ generic_make_request_checks(struct bio *bio)
 		       "generic_make_request: Trying to access "
 			"nonexistent block-device %s (%Lu)\n",
 			bdevname(bio->bi_bdev, b),
-			(long long) bio->bi_sector);
+			(long long) bio->bi_iter.bi_sector);
 		goto end_io;
 	}
 
@@ -1704,9 +1704,9 @@ generic_make_request_checks(struct bio *bio)
 	}
 
 	part = bio->bi_bdev->bd_part;
-	if (should_fail_request(part, bio->bi_size) ||
+	if (should_fail_request(part, bio->bi_iter.bi_size) ||
 	    should_fail_request(&part_to_disk(part)->part0,
-				bio->bi_size))
+				bio->bi_iter.bi_size))
 		goto end_io;
 
 	/*
@@ -1865,7 +1865,7 @@ void submit_bio(int rw, struct bio *bio)
 		if (rw & WRITE) {
 			count_vm_events(PGPGOUT, count);
 		} else {
-			task_io_account_read(bio->bi_size);
+			task_io_account_read(bio->bi_iter.bi_size);
 			count_vm_events(PGPGIN, count);
 		}
 
@@ -1874,7 +1874,7 @@ void submit_bio(int rw, struct bio *bio)
 			printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n",
 			current->comm, task_pid_nr(current),
 				(rw & WRITE) ? "WRITE" : "READ",
-				(unsigned long long)bio->bi_sector,
+				(unsigned long long)bio->bi_iter.bi_sector,
 				bdevname(bio->bi_bdev, b),
 				count);
 		}
@@ -2007,7 +2007,7 @@ unsigned int blk_rq_err_bytes(const struct request *rq)
 	for (bio = rq->bio; bio; bio = bio->bi_next) {
 		if ((bio->bi_rw & ff) != ff)
 			break;
-		bytes += bio->bi_size;
+		bytes += bio->bi_iter.bi_size;
 	}
 
 	/* this could lead to infinite loop */
@@ -2378,9 +2378,9 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 	total_bytes = 0;
 	while (req->bio) {
 		struct bio *bio = req->bio;
-		unsigned bio_bytes = min(bio->bi_size, nr_bytes);
+		unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
 
-		if (bio_bytes == bio->bi_size)
+		if (bio_bytes == bio->bi_iter.bi_size)
 			req->bio = bio->bi_next;
 
 		req_bio_endio(req, bio, bio_bytes, error);
@@ -2728,7 +2728,7 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		rq->nr_phys_segments = bio_phys_segments(q, bio);
 		rq->buffer = bio_data(bio);
 	}
-	rq->__data_len = bio->bi_size;
+	rq->__data_len = bio->bi_iter.bi_size;
 	rq->bio = rq->biotail = bio;
 
 	if (bio->bi_bdev)

block/blk-flush.c

@@ -548,7 +548,7 @@ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
 	 * copied from blk_rq_pos(rq).
 	 */
 	if (error_sector)
-		*error_sector = bio->bi_sector;
+		*error_sector = bio->bi_iter.bi_sector;
 
 	bio_put(bio);
 	return ret;

block/blk-lib.c

@@ -108,12 +108,12 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 			req_sects = end_sect - sector;
 		}
 
-		bio->bi_sector = sector;
+		bio->bi_iter.bi_sector = sector;
 		bio->bi_end_io = bio_batch_end_io;
 		bio->bi_bdev = bdev;
 		bio->bi_private = &bb;
 
-		bio->bi_size = req_sects << 9;
+		bio->bi_iter.bi_size = req_sects << 9;
 		nr_sects -= req_sects;
 		sector = end_sect;
 
@@ -174,7 +174,7 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 			break;
 		}
 
-		bio->bi_sector = sector;
+		bio->bi_iter.bi_sector = sector;
 		bio->bi_end_io = bio_batch_end_io;
 		bio->bi_bdev = bdev;
 		bio->bi_private = &bb;
@@ -184,11 +184,11 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 		bio->bi_io_vec->bv_len = bdev_logical_block_size(bdev);
 
 		if (nr_sects > max_write_same_sectors) {
-			bio->bi_size = max_write_same_sectors << 9;
+			bio->bi_iter.bi_size = max_write_same_sectors << 9;
 			nr_sects -= max_write_same_sectors;
 			sector += max_write_same_sectors;
 		} else {
-			bio->bi_size = nr_sects << 9;
+			bio->bi_iter.bi_size = nr_sects << 9;
 			nr_sects = 0;
 		}
 
@@ -240,7 +240,7 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 			break;
 		}
 
-		bio->bi_sector = sector;
+		bio->bi_iter.bi_sector = sector;
 		bio->bi_bdev   = bdev;
 		bio->bi_end_io = bio_batch_end_io;
 		bio->bi_private = &bb;

block/blk-map.c

@@ -20,7 +20,7 @@ int blk_rq_append_bio(struct request_queue *q, struct request *rq,
 		rq->biotail->bi_next = bio;
 		rq->biotail = bio;
 
-		rq->__data_len += bio->bi_size;
+		rq->__data_len += bio->bi_iter.bi_size;
 	}
 	return 0;
 }
@@ -76,7 +76,7 @@ static int __blk_rq_map_user(struct request_queue *q, struct request *rq,
 
 	ret = blk_rq_append_bio(q, rq, bio);
 	if (!ret)
-		return bio->bi_size;
+		return bio->bi_iter.bi_size;
 
 	/* if it was boucned we must call the end io function */
 	bio_endio(bio, 0);
@@ -220,7 +220,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 	if (IS_ERR(bio))
 		return PTR_ERR(bio);
 
-	if (bio->bi_size != len) {
+	if (bio->bi_iter.bi_size != len) {
 		/*
 		 * Grab an extra reference to this bio, as bio_unmap_user()
 		 * expects to be able to drop it twice as it happens on the

block/blk-merge.c

@@ -543,9 +543,9 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 
 int blk_try_merge(struct request *rq, struct bio *bio)
 {
-	if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_sector)
+	if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
 		return ELEVATOR_BACK_MERGE;
-	else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_sector)
+	else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_iter.bi_sector)
 		return ELEVATOR_FRONT_MERGE;
 	return ELEVATOR_NO_MERGE;
 }

block/blk-mq.c

@@ -301,7 +301,7 @@ void blk_mq_complete_request(struct request *rq, int error)
 		struct bio *next = bio->bi_next;
 
 		bio->bi_next = NULL;
-		bytes += bio->bi_size;
+		bytes += bio->bi_iter.bi_size;
 		blk_mq_bio_endio(rq, bio, error);
 		bio = next;
 	}

block/blk-throttle.c

@@ -877,14 +877,14 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
 	do_div(tmp, HZ);
 	bytes_allowed = tmp;
 
-	if (tg->bytes_disp[rw] + bio->bi_size <= bytes_allowed) {
+	if (tg->bytes_disp[rw] + bio->bi_iter.bi_size <= bytes_allowed) {
 		if (wait)
 			*wait = 0;
 		return 1;
 	}
 
 	/* Calc approx time to dispatch */
-	extra_bytes = tg->bytes_disp[rw] + bio->bi_size - bytes_allowed;
+	extra_bytes = tg->bytes_disp[rw] + bio->bi_iter.bi_size - bytes_allowed;
 	jiffy_wait = div64_u64(extra_bytes * HZ, tg->bps[rw]);
 
 	if (!jiffy_wait)
@@ -987,7 +987,7 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
 	bool rw = bio_data_dir(bio);
 
 	/* Charge the bio to the group */
-	tg->bytes_disp[rw] += bio->bi_size;
+	tg->bytes_disp[rw] += bio->bi_iter.bi_size;
 	tg->io_disp[rw]++;
 
 	/*
@@ -1003,8 +1003,8 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
 	 */
 	if (!(bio->bi_rw & REQ_THROTTLED)) {
 		bio->bi_rw |= REQ_THROTTLED;
-		throtl_update_dispatch_stats(tg_to_blkg(tg), bio->bi_size,
-					     bio->bi_rw);
+		throtl_update_dispatch_stats(tg_to_blkg(tg),
+					     bio->bi_iter.bi_size, bio->bi_rw);
 	}
 }
 
@@ -1508,7 +1508,7 @@ bool blk_throtl_bio(struct request_queue *q, struct bio *bio)
 	if (tg) {
 		if (!tg->has_rules[rw]) {
 			throtl_update_dispatch_stats(tg_to_blkg(tg),
-						     bio->bi_size, bio->bi_rw);
+					bio->bi_iter.bi_size, bio->bi_rw);
 			goto out_unlock_rcu;
 		}
 	}
@@ -1564,7 +1564,7 @@ bool blk_throtl_bio(struct request_queue *q, struct bio *bio)
 	/* out-of-limit, queue to @tg */
 	throtl_log(sq, "[%c] bio. bdisp=%llu sz=%u bps=%llu iodisp=%u iops=%u queued=%d/%d",
 		   rw == READ ? 'R' : 'W',
-		   tg->bytes_disp[rw], bio->bi_size, tg->bps[rw],
+		   tg->bytes_disp[rw], bio->bi_iter.bi_size, tg->bps[rw],
 		   tg->io_disp[rw], tg->iops[rw],
 		   sq->nr_queued[READ], sq->nr_queued[WRITE]);
 

block/elevator.c

@@ -440,7 +440,7 @@ int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
 	/*
 	 * See if our hash lookup can find a potential backmerge.
 	 */
-	__rq = elv_rqhash_find(q, bio->bi_sector);
+	__rq = elv_rqhash_find(q, bio->bi_iter.bi_sector);
 	if (__rq && elv_rq_merge_ok(__rq, bio)) {
 		*req = __rq;
 		return ELEVATOR_BACK_MERGE;

drivers/block/aoe/aoecmd.c

@@ -929,8 +929,8 @@ bufinit(struct buf *buf, struct request *rq, struct bio *bio)
 	memset(buf, 0, sizeof(*buf));
 	buf->rq = rq;
 	buf->bio = bio;
-	buf->resid = bio->bi_size;
-	buf->sector = bio->bi_sector;
+	buf->resid = bio->bi_iter.bi_size;
+	buf->sector = bio->bi_iter.bi_sector;
 	bio_pageinc(bio);
 	buf->bv = bio_iovec(bio);
 	buf->bv_resid = buf->bv->bv_len;
@@ -1152,7 +1152,7 @@ aoe_end_request(struct aoedev *d, struct request *rq, int fastfail)
 	do {
 		bio = rq->bio;
 		bok = !fastfail && test_bit(BIO_UPTODATE, &bio->bi_flags);
-	} while (__blk_end_request(rq, bok ? 0 : -EIO, bio->bi_size));
+	} while (__blk_end_request(rq, bok ? 0 : -EIO, bio->bi_iter.bi_size));
 
 	/* cf. http://lkml.org/lkml/2006/10/31/28 */
 	if (!fastfail)

drivers/block/brd.c

@@ -333,13 +333,13 @@ static void brd_make_request(struct request_queue *q, struct bio *bio)
 	int i;
 	int err = -EIO;
 
-	sector = bio->bi_sector;
+	sector = bio->bi_iter.bi_sector;
 	if (bio_end_sector(bio) > get_capacity(bdev->bd_disk))
 		goto out;
 
 	if (unlikely(bio->bi_rw & REQ_DISCARD)) {
 		err = 0;
-		discard_from_brd(brd, sector, bio->bi_size);
+		discard_from_brd(brd, sector, bio->bi_iter.bi_size);
 		goto out;
 	}