1 files changed, 72 insertions, 123 deletions

diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 820d8402a1dc..3427555b0cca 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -44,10 +44,10 @@ static void bio_csum(struct bio *bio, struct bkey *k)
 	uint64_t csum = 0;
 
 	bio_for_each_segment(bv, bio, iter) {
-		void *d = kmap(bv.bv_page) + bv.bv_offset;
+		void *d = bvec_kmap_local(&bv);
 
-		csum = bch_crc64_update(csum, d, bv.bv_len);
-		kunmap(bv.bv_page);
+		csum = crc64_be(csum, d, bv.bv_len);
+		kunmap_local(d);
 	}
 
 	k->ptr[KEY_PTRS(k)] = csum & (~0ULL >> 1);
@@ -99,7 +99,7 @@ static int bch_keylist_realloc(struct keylist *l, unsigned int u64s,
 	 * bch_data_insert_keys() will insert the keys created so far
 	 * and finish the rest when the keylist is empty.
 	 */
-	if (newsize * sizeof(uint64_t) > block_bytes(c) - sizeof(struct jset))
+	if (newsize * sizeof(uint64_t) > block_bytes(c->cache) - sizeof(struct jset))
 		return -ENOMEM;
 
 	return __bch_keylist_realloc(l, u64s);
@@ -110,7 +110,7 @@ static void bch_data_invalidate(struct closure *cl)
 	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
 	struct bio *bio = op->bio;
 
-	pr_debug("invalidating %i sectors from %llu",
+	pr_debug("invalidating %i sectors from %llu\n",
 		 bio_sectors(bio), (uint64_t) bio->bi_iter.bi_sector);
 
 	while (bio_sectors(bio)) {
@@ -394,14 +394,14 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio)
 			goto skip;
 	}
 
-	if (bio->bi_iter.bi_sector & (c->sb.block_size - 1) ||
-	    bio_sectors(bio) & (c->sb.block_size - 1)) {
-		pr_debug("skipping unaligned io");
+	if (bio->bi_iter.bi_sector & (c->cache->sb.block_size - 1) ||
+	    bio_sectors(bio) & (c->cache->sb.block_size - 1)) {
+		pr_debug("skipping unaligned io\n");
 		goto skip;
 	}
 
 	if (bypass_torture_test(dc)) {
-		if ((get_random_int() & 3) == 3)
+		if (prandom_u32_max(4) == 3)
 			goto skip;
 		else
 			goto rescale;
@@ -475,6 +475,7 @@ struct search {
 	unsigned int		read_dirty_data:1;
 	unsigned int		cache_missed:1;
 
+	struct block_device	*orig_bdev;
 	unsigned long		start_time;
 
 	struct btree_op		op;
@@ -650,8 +651,8 @@ static void backing_request_endio(struct bio *bio)
 		 */
 		if (unlikely(s->iop.writeback &&
 			     bio->bi_opf & REQ_PREFLUSH)) {
-			pr_err("Can't flush %s: returned bi_status %i",
-				dc->backing_dev_name, bio->bi_status);
+			pr_err("Can't flush %pg: returned bi_status %i\n",
+				dc->bdev, bio->bi_status);
 		} else {
 			/* set to orig_bio->bi_status in bio_complete() */
 			s->iop.status = bio->bi_status;
@@ -668,9 +669,9 @@ static void backing_request_endio(struct bio *bio)
 static void bio_complete(struct search *s)
 {
 	if (s->orig_bio) {
-		generic_end_io_acct(s->d->disk->queue, bio_op(s->orig_bio),
-				    &s->d->disk->part0, s->start_time);
-
+		/* Count on bcache device */
+		bio_end_io_acct_remapped(s->orig_bio, s->start_time,
+					 s->orig_bdev);
 		trace_bcache_request_end(s->d, s->orig_bio);
 		s->orig_bio->bi_status = s->iop.status;
 		bio_endio(s->orig_bio);
@@ -684,8 +685,7 @@ static void do_bio_hook(struct search *s,
 {
 	struct bio *bio = &s->bio.bio;
 
-	bio_init(bio, NULL, 0);
-	__bio_clone_fast(bio, orig_bio);
+	bio_init_clone(orig_bio->bi_bdev, bio, orig_bio, GFP_NOIO);
 	/*
 	 * bi_end_io can be set separately somewhere else, e.g. the
 	 * variants in,
@@ -713,7 +713,8 @@ static void search_free(struct closure *cl)
 }
 
 static inline struct search *search_alloc(struct bio *bio,
-					  struct bcache_device *d)
+		struct bcache_device *d, struct block_device *orig_bdev,
+		unsigned long start_time)
 {
 	struct search *s;
 
@@ -730,8 +731,9 @@ static inline struct search *search_alloc(struct bio *bio,
 	s->recoverable		= 1;
 	s->write		= op_is_write(bio_op(bio));
 	s->read_dirty_data	= 0;
-	s->start_time		= jiffies;
-
+	/* Count on the bcache device */
+	s->orig_bdev		= orig_bdev;
+	s->start_time		= start_time;
 	s->iop.c		= d->c;
 	s->iop.bio		= NULL;
 	s->iop.inode		= d->id;
@@ -828,11 +830,11 @@ static void cached_dev_read_done(struct closure *cl)
 	 */
 
 	if (s->iop.bio) {
-		bio_reset(s->iop.bio);
+		bio_reset(s->iop.bio, s->cache_miss->bi_bdev, REQ_OP_READ);
 		s->iop.bio->bi_iter.bi_sector =
 			s->cache_miss->bi_iter.bi_sector;
-		bio_copy_dev(s->iop.bio, s->cache_miss);
 		s->iop.bio->bi_iter.bi_size = s->insert_bio_sectors << 9;
+		bio_clone_blkg_association(s->iop.bio, s->cache_miss);
 		bch_bio_map(s->iop.bio, NULL);
 
 		bio_copy_data(s->cache_miss, s->iop.bio);
@@ -877,9 +879,9 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 				 struct bio *bio, unsigned int sectors)
 {
 	int ret = MAP_CONTINUE;
-	unsigned int reada = 0;
 	struct cached_dev *dc = container_of(s->d, struct cached_dev, disk);
 	struct bio *miss, *cache_bio;
+	unsigned int size_limit;
 
 	s->cache_missed = 1;
 
@@ -889,13 +891,10 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 		goto out_submit;
 	}
 
-	if (!(bio->bi_opf & REQ_RAHEAD) &&
-	    !(bio->bi_opf & (REQ_META|REQ_PRIO)) &&
-	    s->iop.c->gc_stats.in_use < CUTOFF_CACHE_READA)
-		reada = min_t(sector_t, dc->readahead >> 9,
-			      get_capacity(bio->bi_disk) - bio_end_sector(bio));
-
-	s->insert_bio_sectors = min(sectors, bio_sectors(bio) + reada);
+	/* Limitation for valid replace key size and cache_bio bvecs number */
+	size_limit = min_t(unsigned int, BIO_MAX_VECS * PAGE_SECTORS,
+			   (1 << KEY_SIZE_BITS) - 1);
+	s->insert_bio_sectors = min3(size_limit, sectors, bio_sectors(bio));
 
 	s->iop.replace_key = KEY(s->iop.inode,
 				 bio->bi_iter.bi_sector + s->insert_bio_sectors,
@@ -907,19 +906,19 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 
 	s->iop.replace = true;
 
-	miss = bio_next_split(bio, sectors, GFP_NOIO, &s->d->bio_split);
+	miss = bio_next_split(bio, s->insert_bio_sectors, GFP_NOIO,
+			      &s->d->bio_split);
 
 	/* btree_search_recurse()'s btree iterator is no good anymore */
 	ret = miss == bio ? MAP_DONE : -EINTR;
 
-	cache_bio = bio_alloc_bioset(GFP_NOWAIT,
+	cache_bio = bio_alloc_bioset(miss->bi_bdev,
 			DIV_ROUND_UP(s->insert_bio_sectors, PAGE_SECTORS),
-			&dc->disk.bio_split);
+			0, GFP_NOWAIT, &dc->disk.bio_split);
 	if (!cache_bio)
 		goto out_submit;
 
 	cache_bio->bi_iter.bi_sector	= miss->bi_iter.bi_sector;
-	bio_copy_dev(cache_bio, miss);
 	cache_bio->bi_iter.bi_size	= s->insert_bio_sectors << 9;
 
 	cache_bio->bi_end_io	= backing_request_endio;
@@ -929,9 +928,6 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s,
 	if (bch_bio_alloc_pages(cache_bio, __GFP_NOWARN|GFP_NOIO))
 		goto out_put;
 
-	if (reada)
-		bch_mark_cache_readahead(s->iop.c, s->d);
-
 	s->cache_miss	= miss;
 	s->iop.bio	= cache_bio;
 	bio_get(cache_bio);
@@ -1009,7 +1005,7 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 		bio_get(s->iop.bio);
 
 		if (bio_op(bio) == REQ_OP_DISCARD &&
-		    !blk_queue_discard(bdev_get_queue(dc->bdev)))
+		    !bdev_max_discard_sectors(dc->bdev))
 			goto insert_data;
 
 		/* I/O request sent to backing device */
@@ -1027,21 +1023,21 @@ static void cached_dev_write(struct cached_dev *dc, struct search *s)
 			 */
 			struct bio *flush;
 
-			flush = bio_alloc_bioset(GFP_NOIO, 0,
-						 &dc->disk.bio_split);
+			flush = bio_alloc_bioset(bio->bi_bdev, 0,
+						 REQ_OP_WRITE | REQ_PREFLUSH,
+						 GFP_NOIO, &dc->disk.bio_split);
 			if (!flush) {
 				s->iop.status = BLK_STS_RESOURCE;
 				goto insert_data;
 			}
-			bio_copy_dev(flush, bio);
 			flush->bi_end_io = backing_request_endio;
 			flush->bi_private = cl;
-			flush->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
 			/* I/O request sent to backing device */
 			closure_bio_submit(s->iop.c, flush, cl);
 		}
 	} else {
-		s->iop.bio = bio_clone_fast(bio, GFP_NOIO, &dc->disk.bio_split);
+		s->iop.bio = bio_alloc_clone(bio->bi_bdev, bio, GFP_NOIO,
+					     &dc->disk.bio_split);
 		/* I/O request sent to backing device */
 		bio->bi_end_io = backing_request_endio;
 		closure_bio_submit(s->iop.c, bio, cl);
@@ -1072,6 +1068,7 @@ struct detached_dev_io_private {
 	unsigned long		start_time;
 	bio_end_io_t		*bi_end_io;
 	void			*bi_private;
+	struct block_device	*orig_bdev;
 };
 
 static void detached_dev_end_io(struct bio *bio)
@@ -1082,8 +1079,8 @@ static void detached_dev_end_io(struct bio *bio)
 	bio->bi_end_io = ddip->bi_end_io;
 	bio->bi_private = ddip->bi_private;
 
-	generic_end_io_acct(ddip->d->disk->queue, bio_op(bio),
-			    &ddip->d->disk->part0, ddip->start_time);
+	/* Count on the bcache device */
+	bio_end_io_acct_remapped(bio, ddip->start_time, ddip->orig_bdev);
 
 	if (bio->bi_status) {
 		struct cached_dev *dc = container_of(ddip->d,
@@ -1096,7 +1093,8 @@ static void detached_dev_end_io(struct bio *bio)
 	bio->bi_end_io(bio);
 }
 
-static void detached_dev_do_request(struct bcache_device *d, struct bio *bio)
+static void detached_dev_do_request(struct bcache_device *d, struct bio *bio,
+		struct block_device *orig_bdev, unsigned long start_time)
 {
 	struct detached_dev_io_private *ddip;
 	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
@@ -1107,18 +1105,26 @@ static void detached_dev_do_request(struct bcache_device *d, struct bio *bio)
 	 * which would call closure_get(&dc->disk.cl)
 	 */
 	ddip = kzalloc(sizeof(struct detached_dev_io_private), GFP_NOIO);
+	if (!ddip) {
+		bio->bi_status = BLK_STS_RESOURCE;
+		bio->bi_end_io(bio);
+		return;
+	}
+
 	ddip->d = d;
-	ddip->start_time = jiffies;
+	/* Count on the bcache device */
+	ddip->orig_bdev = orig_bdev;
+	ddip->start_time = start_time;
 	ddip->bi_end_io = bio->bi_end_io;
 	ddip->bi_private = bio->bi_private;
 	bio->bi_end_io = detached_dev_end_io;
 	bio->bi_private = ddip;
 
 	if ((bio_op(bio) == REQ_OP_DISCARD) &&
-	    !blk_queue_discard(bdev_get_queue(dc->bdev)))
+	    !bdev_max_discard_sectors(dc->bdev))
 		bio->bi_end_io(bio);
 	else
-		generic_make_request(bio);
+		submit_bio_noacct(bio);
 }
 
 static void quit_max_writeback_rate(struct cache_set *c,
@@ -1161,19 +1167,20 @@ static void quit_max_writeback_rate(struct cache_set *c,
 
 /* Cached devices - read & write stuff */
 
-static blk_qc_t cached_dev_make_request(struct request_queue *q,
-					struct bio *bio)
+void cached_dev_submit_bio(struct bio *bio)
 {
 	struct search *s;
-	struct bcache_device *d = bio->bi_disk->private_data;
+	struct block_device *orig_bdev = bio->bi_bdev;
+	struct bcache_device *d = orig_bdev->bd_disk->private_data;
 	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
+	unsigned long start_time;
 	int rw = bio_data_dir(bio);
 
 	if (unlikely((d->c && test_bit(CACHE_SET_IO_DISABLE, &d->c->flags)) ||
 		     dc->io_disable)) {
 		bio->bi_status = BLK_STS_IOERR;
 		bio_endio(bio);
-		return BLK_QC_T_NONE;
+		return;
 	}
 
 	if (likely(d->c)) {
@@ -1191,22 +1198,19 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q,
 		}
 	}
 
-	generic_start_io_acct(q,
-			      bio_op(bio),
-			      bio_sectors(bio),
-			      &d->disk->part0);
+	start_time = bio_start_io_acct(bio);
 
 	bio_set_dev(bio, dc->bdev);
 	bio->bi_iter.bi_sector += dc->sb.data_offset;
 
 	if (cached_dev_get(dc)) {
-		s = search_alloc(bio, d);
+		s = search_alloc(bio, d, orig_bdev, start_time);
 		trace_bcache_request_start(s->d, bio);
 
 		if (!bio->bi_iter.bi_size) {
 			/*
 			 * can't call bch_journal_meta from under
-			 * generic_make_request
+			 * submit_bio_noacct
 			 */
 			continue_at_nobarrier(&s->cl,
 					      cached_dev_nodata,
@@ -1221,9 +1225,7 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q,
 		}
 	} else
 		/* I/O request sent to backing device */
-		detached_dev_do_request(d, bio);
-
-	return BLK_QC_T_NONE;
+		detached_dev_do_request(d, bio, orig_bdev, start_time);
 }
 
 static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode,
@@ -1233,41 +1235,13 @@ static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode,
 
 	if (dc->io_disable)
 		return -EIO;
-
-	return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg);
-}
-
-static int cached_dev_congested(void *data, int bits)
-{
-	struct bcache_device *d = data;
-	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
-	struct request_queue *q = bdev_get_queue(dc->bdev);
-	int ret = 0;
-
-	if (bdi_congested(q->backing_dev_info, bits))
-		return 1;
-
-	if (cached_dev_get(dc)) {
-		unsigned int i;
-		struct cache *ca;
-
-		for_each_cache(ca, d->c, i) {
-			q = bdev_get_queue(ca->bdev);
-			ret |= bdi_congested(q->backing_dev_info, bits);
-		}
-
-		cached_dev_put(dc);
-	}
-
-	return ret;
+	if (!dc->bdev->bd_disk->fops->ioctl)
+		return -ENOTTY;
+	return dc->bdev->bd_disk->fops->ioctl(dc->bdev, mode, cmd, arg);
 }
 
 void bch_cached_dev_request_init(struct cached_dev *dc)
 {
-	struct gendisk *g = dc->disk.disk;
-
-	g->queue->make_request_fn		= cached_dev_make_request;
-	g->queue->backing_dev_info->congested_fn = cached_dev_congested;
 	dc->disk.cache_miss			= cached_dev_cache_miss;
 	dc->disk.ioctl				= cached_dev_ioctl;
 }
@@ -1301,22 +1275,19 @@ static void flash_dev_nodata(struct closure *cl)
 	continue_at(cl, search_free, NULL);
 }
 
-static blk_qc_t flash_dev_make_request(struct request_queue *q,
-					     struct bio *bio)
+void flash_dev_submit_bio(struct bio *bio)
 {
 	struct search *s;
 	struct closure *cl;
-	struct bcache_device *d = bio->bi_disk->private_data;
+	struct bcache_device *d = bio->bi_bdev->bd_disk->private_data;
 
 	if (unlikely(d->c && test_bit(CACHE_SET_IO_DISABLE, &d->c->flags))) {
 		bio->bi_status = BLK_STS_IOERR;
 		bio_endio(bio);
-		return BLK_QC_T_NONE;
+		return;
 	}
 
-	generic_start_io_acct(q, bio_op(bio), bio_sectors(bio), &d->disk->part0);
-
-	s = search_alloc(bio, d);
+	s = search_alloc(bio, d, bio->bi_bdev, bio_start_io_acct(bio));
 	cl = &s->cl;
 	bio = &s->bio.bio;
 
@@ -1324,13 +1295,12 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q,
 
 	if (!bio->bi_iter.bi_size) {
 		/*
-		 * can't call bch_journal_meta from under
-		 * generic_make_request
+		 * can't call bch_journal_meta from under submit_bio_noacct
 		 */
 		continue_at_nobarrier(&s->cl,
 				      flash_dev_nodata,
 				      bcache_wq);
-		return BLK_QC_T_NONE;
+		return;
 	} else if (bio_data_dir(bio)) {
 		bch_keybuf_check_overlapping(&s->iop.c->moving_gc_keys,
 					&KEY(d->id, bio->bi_iter.bi_sector, 0),
@@ -1346,7 +1316,6 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q,
 	}
 
 	continue_at(cl, search_free, NULL);
-	return BLK_QC_T_NONE;
 }
 
 static int flash_dev_ioctl(struct bcache_device *d, fmode_t mode,
@@ -1355,28 +1324,8 @@ static int flash_dev_ioctl(struct bcache_device *d, fmode_t mode,
 	return -ENOTTY;
 }
 
-static int flash_dev_congested(void *data, int bits)
-{
-	struct bcache_device *d = data;
-	struct request_queue *q;
-	struct cache *ca;
-	unsigned int i;
-	int ret = 0;
-
-	for_each_cache(ca, d->c, i) {
-		q = bdev_get_queue(ca->bdev);
-		ret |= bdi_congested(q->backing_dev_info, bits);
-	}
-
-	return ret;
-}
-
 void bch_flash_dev_request_init(struct bcache_device *d)
 {
-	struct gendisk *g = d->disk;
-
-	g->queue->make_request_fn		= flash_dev_make_request;
-	g->queue->backing_dev_info->congested_fn = flash_dev_congested;
 	d->cache_miss				= flash_dev_cache_miss;
 	d->ioctl				= flash_dev_ioctl;
 }