request.c

			/* Also need to send a flush to the backing device */
			struct bio *flush = bio_alloc_bioset(0, GFP_NOIO,
							     dc->disk.bio_split);

			flush->bi_rw	= WRITE_FLUSH;
			flush->bi_bdev	= bio->bi_bdev;
			flush->bi_end_io = request_endio;
			flush->bi_private = cl;

			closure_bio_submit(flush, cl, s->d);
		} else {
			s->op.cache_bio = bio;
		}
	}
out:
	closure_call(&s->op.cl, bch_insert_data, NULL, cl);
	continue_at(cl, cached_dev_write_complete, NULL);
skip:
	s->op.skip = true;
	s->op.cache_bio = s->orig_bio;
	bio_get(s->op.cache_bio);

	if ((bio->bi_rw & REQ_DISCARD) &&
	    !blk_queue_discard(bdev_get_queue(dc->bdev)))
		goto out;

	closure_bio_submit(bio, cl, s->d);
	goto out;
}

static void request_nodata(struct cached_dev *dc, struct search *s)
{
	struct closure *cl = &s->cl;
	struct bio *bio = &s->bio.bio;

	if (bio->bi_rw & REQ_DISCARD) {
		request_write(dc, s);
		return;
	}

	if (s->op.flush_journal)
		bch_journal_meta(s->op.c, cl);

	closure_bio_submit(bio, cl, s->d);

	continue_at(cl, cached_dev_bio_complete, NULL);
}

/* Cached devices - read & write stuff */

unsigned bch_get_congested(struct cache_set *c)
{
	int i;
	long rand;

	if (!c->congested_read_threshold_us &&
	    !c->congested_write_threshold_us)
		return 0;

	i = (local_clock_us() - c->congested_last_us) / 1024;
	if (i < 0)
		return 0;

	i += atomic_read(&c->congested);
	if (i >= 0)
		return 0;

	i += CONGESTED_MAX;

	if (i > 0)
		i = fract_exp_two(i, 6);

	rand = get_random_int();
	i -= bitmap_weight(&rand, BITS_PER_LONG);

	return i > 0 ? i : 1;
}

static void add_sequential(struct task_struct *t)
{
	ewma_add(t->sequential_io_avg,
		 t->sequential_io, 8, 0);

	t->sequential_io = 0;
}

static struct hlist_head *iohash(struct cached_dev *dc, uint64_t k)
{
	return &dc->io_hash[hash_64(k, RECENT_IO_BITS)];
}

static void check_should_skip(struct cached_dev *dc, struct search *s)
{
	struct cache_set *c = s->op.c;
	struct bio *bio = &s->bio.bio;
	unsigned mode = cache_mode(dc, bio);
	unsigned sectors, congested = bch_get_congested(c);

	if (atomic_read(&dc->disk.detaching) ||
	    c->gc_stats.in_use > CUTOFF_CACHE_ADD ||
	    (bio->bi_rw & REQ_DISCARD))
		goto skip;

	if (mode == CACHE_MODE_NONE ||
	    (mode == CACHE_MODE_WRITEAROUND &&
	     (bio->bi_rw & REQ_WRITE)))
		goto skip;

	if (bio->bi_sector   & (c->sb.block_size - 1) ||
	    bio_sectors(bio) & (c->sb.block_size - 1)) {
		pr_debug("skipping unaligned io");
		goto skip;
	}

	if (!congested && !dc->sequential_cutoff)
		goto rescale;

	if (!congested &&
	    mode == CACHE_MODE_WRITEBACK &&
	    (bio->bi_rw & REQ_WRITE) &&
	    (bio->bi_rw & REQ_SYNC))
		goto rescale;

	if (dc->sequential_merge) {
		struct io *i;

		spin_lock(&dc->io_lock);

		hlist_for_each_entry(i, iohash(dc, bio->bi_sector), hash)
			if (i->last == bio->bi_sector &&
			    time_before(jiffies, i->jiffies))
				goto found;

		i = list_first_entry(&dc->io_lru, struct io, lru);

		add_sequential(s->task);
		i->sequential = 0;
found:
		if (i->sequential + bio->bi_size > i->sequential)
			i->sequential	+= bio->bi_size;

		i->last			 = bio_end_sector(bio);
		i->jiffies		 = jiffies + msecs_to_jiffies(5000);
		s->task->sequential_io	 = i->sequential;

		hlist_del(&i->hash);
		hlist_add_head(&i->hash, iohash(dc, i->last));
		list_move_tail(&i->lru, &dc->io_lru);

		spin_unlock(&dc->io_lock);
	} else {
		s->task->sequential_io = bio->bi_size;

		add_sequential(s->task);
	}

	sectors = max(s->task->sequential_io,
		      s->task->sequential_io_avg) >> 9;

	if (dc->sequential_cutoff &&
	    sectors >= dc->sequential_cutoff >> 9) {
		trace_bcache_bypass_sequential(s->orig_bio);
		goto skip;
	}

	if (congested && sectors >= congested) {
		trace_bcache_bypass_congested(s->orig_bio);
		goto skip;
	}

rescale:
	bch_rescale_priorities(c, bio_sectors(bio));
	return;
skip:
	bch_mark_sectors_bypassed(s, bio_sectors(bio));
	s->op.skip = true;
}

static void cached_dev_make_request(struct request_queue *q, struct bio *bio)
{
	struct search *s;
	struct bcache_device *d = bio->bi_bdev->bd_disk->private_data;
	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
	int cpu, rw = bio_data_dir(bio);

	cpu = part_stat_lock();
	part_stat_inc(cpu, &d->disk->part0, ios[rw]);
	part_stat_add(cpu, &d->disk->part0, sectors[rw], bio_sectors(bio));
	part_stat_unlock();

	bio->bi_bdev = dc->bdev;
	bio->bi_sector += dc->sb.data_offset;

	if (cached_dev_get(dc)) {
		s = search_alloc(bio, d);
		trace_bcache_request_start(s, bio);

		if (!bio_has_data(bio))
			request_nodata(dc, s);
		else if (rw)
			request_write(dc, s);
		else
			request_read(dc, s);
	} else {
		if ((bio->bi_rw & REQ_DISCARD) &&
		    !blk_queue_discard(bdev_get_queue(dc->bdev)))
			bio_endio(bio, 0);
		else
			bch_generic_make_request(bio, &d->bio_split_hook);
	}
}

static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode,
			    unsigned int cmd, unsigned long arg)
{
	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
	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 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;
}

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;
}

/* Flash backed devices */

static int flash_dev_cache_miss(struct btree *b, struct search *s,
				struct bio *bio, unsigned sectors)
{
	struct bio_vec *bv;
	int i;

	/* Zero fill bio */

	bio_for_each_segment(bv, bio, i) {
		unsigned j = min(bv->bv_len >> 9, sectors);

		void *p = kmap(bv->bv_page);
		memset(p + bv->bv_offset, 0, j << 9);
		kunmap(bv->bv_page);

		sectors	-= j;
	}

	bio_advance(bio, min(sectors << 9, bio->bi_size));

	if (!bio->bi_size)
		s->op.lookup_done = true;

	return 0;
}

static void flash_dev_make_request(struct request_queue *q, struct bio *bio)
{
	struct search *s;
	struct closure *cl;
	struct bcache_device *d = bio->bi_bdev->bd_disk->private_data;
	int cpu, rw = bio_data_dir(bio);

	cpu = part_stat_lock();
	part_stat_inc(cpu, &d->disk->part0, ios[rw]);
	part_stat_add(cpu, &d->disk->part0, sectors[rw], bio_sectors(bio));
	part_stat_unlock();

	s = search_alloc(bio, d);
	cl = &s->cl;
	bio = &s->bio.bio;

	trace_bcache_request_start(s, bio);

	if (bio_has_data(bio) && !rw) {
		closure_call(&s->op.cl, btree_read_async, NULL, cl);
	} else if (bio_has_data(bio) || s->op.skip) {
		bch_keybuf_check_overlapping(&s->op.c->moving_gc_keys,
					&KEY(d->id, bio->bi_sector, 0),
					&KEY(d->id, bio_end_sector(bio), 0));

		s->writeback	= true;
		s->op.cache_bio	= bio;

		closure_call(&s->op.cl, bch_insert_data, NULL, cl);
	} else {
		/* No data - probably a cache flush */
		if (s->op.flush_journal)
			bch_journal_meta(s->op.c, cl);
	}

	continue_at(cl, search_free, NULL);
}

static int flash_dev_ioctl(struct bcache_device *d, fmode_t mode,
			   unsigned int cmd, unsigned long arg)
{
	return -ENOTTY;
}

static int flash_dev_congested(void *data, int bits)
{
	struct bcache_device *d = data;
	struct request_queue *q;
	struct cache *ca;
	unsigned 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;
}

void bch_request_exit(void)
{
#ifdef CONFIG_CGROUP_BCACHE
	cgroup_unload_subsys(&bcache_subsys);
#endif
	if (bch_search_cache)
		kmem_cache_destroy(bch_search_cache);
}

int __init bch_request_init(void)
{
	bch_search_cache = KMEM_CACHE(search, 0);
	if (!bch_search_cache)
		return -ENOMEM;

#ifdef CONFIG_CGROUP_BCACHE
	cgroup_load_subsys(&bcache_subsys);
	init_bch_cgroup(&bcache_default_cgroup);

	cgroup_add_cftypes(&bcache_subsys, bch_files);
#endif
	return 0;
}