Merge tag 'block-5.13-2021-06-12' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A few fixes that should go into 5.13:

   - Fix a regression deadlock introduced in this release between open
     and remove of a bdev (Christoph)

   - Fix an async_xor md regression in this release (Xiao)

   - Fix bcache oversized read issue (Coly)"

* tag 'block-5.13-2021-06-12' of git://git.kernel.dk/linux-block:
  block: loop: fix deadlock between open and remove
  async_xor: check src_offs is not NULL before updating it
  bcache: avoid oversized read request in cache missing code path
  bcache: remove bcache device self-defined readahead

Author: torvalds

crypto/async_tx/async_xor.c

@@ -233,7 +233,8 @@ async_xor_offs(struct page *dest, unsigned int offset,
 		if (submit->flags & ASYNC_TX_XOR_DROP_DST) {
 			src_cnt--;
 			src_list++;
-			src_offs++;
+			if (src_offs)
+				src_offs++;
 		}
 
 		/* wait for any prerequisite operations */

drivers/block/loop.c

@@ -1879,29 +1879,18 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
 
 static int lo_open(struct block_device *bdev, fmode_t mode)
 {
-	struct loop_device *lo;
+	struct loop_device *lo = bdev->bd_disk->private_data;
 	int err;
 
-	/*
-	 * take loop_ctl_mutex to protect lo pointer from race with
-	 * loop_control_ioctl(LOOP_CTL_REMOVE), however, to reduce contention
-	 * release it prior to updating lo->lo_refcnt.
-	 */
-	err = mutex_lock_killable(&loop_ctl_mutex);
-	if (err)
-		return err;
-	lo = bdev->bd_disk->private_data;
-	if (!lo) {
-		mutex_unlock(&loop_ctl_mutex);
-		return -ENXIO;
-	}
 	err = mutex_lock_killable(&lo->lo_mutex);
-	mutex_unlock(&loop_ctl_mutex);
 	if (err)
 		return err;
-	atomic_inc(&lo->lo_refcnt);
+	if (lo->lo_state == Lo_deleting)
+		err = -ENXIO;
+	else
+		atomic_inc(&lo->lo_refcnt);
 	mutex_unlock(&lo->lo_mutex);
-	return 0;
+	return err;
 }
 
 static void lo_release(struct gendisk *disk, fmode_t mode)
@@ -2285,7 +2274,7 @@ static long loop_control_ioctl(struct file *file, unsigned int cmd,
 			mutex_unlock(&lo->lo_mutex);
 			break;
 		}
-		lo->lo_disk->private_data = NULL;
+		lo->lo_state = Lo_deleting;
 		mutex_unlock(&lo->lo_mutex);
 		idr_remove(&loop_index_idr, lo->lo_number);
 		loop_remove(lo);

drivers/block/loop.h

@@ -22,6 +22,7 @@ enum {
 	Lo_unbound,
 	Lo_bound,
 	Lo_rundown,
+	Lo_deleting,
 };
 
 struct loop_func_table;

drivers/md/bcache/bcache.h

@@ -364,7 +364,6 @@ struct cached_dev {
 
 	/* The rest of this all shows up in sysfs */
 	unsigned int		sequential_cutoff;
-	unsigned int		readahead;
 
 	unsigned int		io_disable:1;
 	unsigned int		verify:1;

drivers/md/bcache/request.c

@@ -880,9 +880,9 @@ 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;
 
@@ -892,14 +892,10 @@ 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_bdev->bd_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,
@@ -911,7 +907,8 @@ 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;
@@ -933,9 +930,6 @@ 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);

drivers/md/bcache/stats.c

@@ -46,7 +46,6 @@ read_attribute(cache_misses);
 read_attribute(cache_bypass_hits);
 read_attribute(cache_bypass_misses);
 read_attribute(cache_hit_ratio);
-read_attribute(cache_readaheads);
 read_attribute(cache_miss_collisions);
 read_attribute(bypassed);
 
@@ -64,7 +63,6 @@ SHOW(bch_stats)
 		    DIV_SAFE(var(cache_hits) * 100,
 			     var(cache_hits) + var(cache_misses)));
 
-	var_print(cache_readaheads);
 	var_print(cache_miss_collisions);
 	sysfs_hprint(bypassed,	var(sectors_bypassed) << 9);
 #undef var
@@ -86,7 +84,6 @@ static struct attribute *bch_stats_files[] = {
 	&sysfs_cache_bypass_hits,
 	&sysfs_cache_bypass_misses,
 	&sysfs_cache_hit_ratio,
-	&sysfs_cache_readaheads,
 	&sysfs_cache_miss_collisions,
 	&sysfs_bypassed,
 	NULL
@@ -113,7 +110,6 @@ void bch_cache_accounting_clear(struct cache_accounting *acc)
 	acc->total.cache_misses = 0;
 	acc->total.cache_bypass_hits = 0;
 	acc->total.cache_bypass_misses = 0;
-	acc->total.cache_readaheads = 0;
 	acc->total.cache_miss_collisions = 0;
 	acc->total.sectors_bypassed = 0;
 }
@@ -145,7 +141,6 @@ static void scale_stats(struct cache_stats *stats, unsigned long rescale_at)
 		scale_stat(&stats->cache_misses);
 		scale_stat(&stats->cache_bypass_hits);
 		scale_stat(&stats->cache_bypass_misses);
-		scale_stat(&stats->cache_readaheads);
 		scale_stat(&stats->cache_miss_collisions);
 		scale_stat(&stats->sectors_bypassed);
 	}
@@ -168,7 +163,6 @@ static void scale_accounting(struct timer_list *t)
 	move_stat(cache_misses);
 	move_stat(cache_bypass_hits);
 	move_stat(cache_bypass_misses);
-	move_stat(cache_readaheads);
 	move_stat(cache_miss_collisions);
 	move_stat(sectors_bypassed);
 
@@ -209,14 +203,6 @@ void bch_mark_cache_accounting(struct cache_set *c, struct bcache_device *d,
 	mark_cache_stats(&c->accounting.collector, hit, bypass);
 }
 
-void bch_mark_cache_readahead(struct cache_set *c, struct bcache_device *d)
-{
-	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
-
-	atomic_inc(&dc->accounting.collector.cache_readaheads);
-	atomic_inc(&c->accounting.collector.cache_readaheads);
-}
-
 void bch_mark_cache_miss_collision(struct cache_set *c, struct bcache_device *d)
 {
 	struct cached_dev *dc = container_of(d, struct cached_dev, disk);

drivers/md/bcache/stats.h

@@ -7,7 +7,6 @@ struct cache_stat_collector {
 	atomic_t cache_misses;
 	atomic_t cache_bypass_hits;
 	atomic_t cache_bypass_misses;
-	atomic_t cache_readaheads;
 	atomic_t cache_miss_collisions;
 	atomic_t sectors_bypassed;
 };

drivers/md/bcache/sysfs.c

@@ -137,7 +137,6 @@ rw_attribute(io_disable);
 rw_attribute(discard);
 rw_attribute(running);
 rw_attribute(label);
-rw_attribute(readahead);
 rw_attribute(errors);
 rw_attribute(io_error_limit);
 rw_attribute(io_error_halflife);
@@ -260,7 +259,6 @@ SHOW(__bch_cached_dev)
 	var_printf(partial_stripes_expensive,	"%u");
 
 	var_hprint(sequential_cutoff);
-	var_hprint(readahead);
 
 	sysfs_print(running,		atomic_read(&dc->running));
 	sysfs_print(state,		states[BDEV_STATE(&dc->sb)]);
@@ -365,7 +363,6 @@ STORE(__cached_dev)
 	sysfs_strtoul_clamp(sequential_cutoff,
 			    dc->sequential_cutoff,
 			    0, UINT_MAX);
-	d_strtoi_h(readahead);
 
 	if (attr == &sysfs_clear_stats)
 		bch_cache_accounting_clear(&dc->accounting);
@@ -538,7 +535,6 @@ static struct attribute *bch_cached_dev_files[] = {
 	&sysfs_running,
 	&sysfs_state,
 	&sysfs_label,
-	&sysfs_readahead,
 #ifdef CONFIG_BCACHE_DEBUG
 	&sysfs_verify,
 	&sysfs_bypass_torture_test,