Commit 026d15f6 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md 

Pull MD update from Shaohua Li:

 - fixed deadlock in MD suspend and a potential bug in bio allocation
   (Neil Brown)

 - fixed signal issue (Mikulas Patocka)

 - fixed typo in FailFast test (Guoqing Jiang)

 - other trival fixes

* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md:
  MD: fix sleep in atomic
  MD: fix a null dereference
  md: use a separate bio_set for synchronous IO.
  md: change the initialization value for a spare device spot to MD_DISK_ROLE_SPARE
  md/raid1: remove unused bio in sync_request_write
  md/raid10: fix FailFast test for wrong device
  md: don't use flush_signals in userspace processes
  md: fix deadlock between mddev_suspend() and md_write_start()
parents 43d01209 7184ef8b

drivers/md/faulty.c

+3 −2
Original line number Diff line number Diff line
@@ -170,7 +170,7 @@ static void add_sector(struct faulty_conf *conf, sector_t start, int mode) 
		conf->nfaults = n+1;

}



static void faulty_make_request(struct mddev *mddev, struct bio *bio)

static bool faulty_make_request(struct mddev *mddev, struct bio *bio)

{

	struct faulty_conf *conf = mddev->private;

	int failit = 0;
@@ -182,7 +182,7 @@ static void faulty_make_request(struct mddev *mddev, struct bio *bio) 
			 * just fail immediately

			 */

			bio_io_error(bio);

			return;

			return true;

		}



		if (check_sector(conf, bio->bi_iter.bi_sector,
@@ -224,6 +224,7 @@ static void faulty_make_request(struct mddev *mddev, struct bio *bio) 
		bio->bi_bdev = conf->rdev->bdev;



	generic_make_request(bio);

	return true;

}



static void faulty_status(struct seq_file *seq, struct mddev *mddev)

drivers/md/linear.c

+4 −3
Original line number Diff line number Diff line
@@ -245,7 +245,7 @@ static void linear_free(struct mddev *mddev, void *priv) 
	kfree(conf);

}



static void linear_make_request(struct mddev *mddev, struct bio *bio)

static bool linear_make_request(struct mddev *mddev, struct bio *bio)

{

	char b[BDEVNAME_SIZE];

	struct dev_info *tmp_dev;
@@ -254,7 +254,7 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio) 


	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {

		md_flush_request(mddev, bio);

		return;

		return true;

	}



	tmp_dev = which_dev(mddev, bio_sector);
@@ -292,7 +292,7 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio) 
		mddev_check_write_zeroes(mddev, bio);

		generic_make_request(bio);

	}

	return;

	return true;



out_of_bounds:

	pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %s: %llu sectors, offset %llu\n",
@@ -302,6 +302,7 @@ out_of_bounds: 
	       (unsigned long long)tmp_dev->rdev->sectors,

	       (unsigned long long)start_sector);

	bio_io_error(bio);

	return true;

}



static void linear_status (struct seq_file *seq, struct mddev *mddev)

drivers/md/md.c

+38 −9
Original line number Diff line number Diff line
@@ -203,6 +203,14 @@ struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, 
}

EXPORT_SYMBOL_GPL(bio_alloc_mddev);



static struct bio *md_bio_alloc_sync(struct mddev *mddev)

{

	if (!mddev || !mddev->sync_set)

		return bio_alloc(GFP_NOIO, 1);



	return bio_alloc_bioset(GFP_NOIO, 1, mddev->sync_set);

}



/*

 * We have a system wide 'event count' that is incremented

 * on any 'interesting' event, and readers of /proc/mdstat
@@ -277,7 +285,7 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) 
		bio_endio(bio);

		return BLK_QC_T_NONE;

	}

	smp_rmb(); /* Ensure implications of  'active' are visible */

check_suspended:

	rcu_read_lock();

	if (mddev->suspended) {

		DEFINE_WAIT(__wait);
@@ -302,7 +310,11 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) 
	sectors = bio_sectors(bio);

	/* bio could be mergeable after passing to underlayer */

	bio->bi_opf &= ~REQ_NOMERGE;

	mddev->pers->make_request(mddev, bio);

	if (!mddev->pers->make_request(mddev, bio)) {

		atomic_dec(&mddev->active_io);

		wake_up(&mddev->sb_wait);

		goto check_suspended;

	}



	cpu = part_stat_lock();

	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
@@ -327,6 +339,7 @@ void mddev_suspend(struct mddev *mddev) 
	if (mddev->suspended++)

		return;

	synchronize_rcu();

	wake_up(&mddev->sb_wait);

	wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0);

	mddev->pers->quiesce(mddev, 1);
@@ -462,7 +475,7 @@ static void mddev_delayed_delete(struct work_struct *ws); 


static void mddev_put(struct mddev *mddev)

{

	struct bio_set *bs = NULL;

	struct bio_set *bs = NULL, *sync_bs = NULL;



	if (!atomic_dec_and_lock(&mddev->active, &all_mddevs_lock))

		return;
@@ -472,7 +485,9 @@ static void mddev_put(struct mddev *mddev) 
		 * so destroy it */

		list_del_init(&mddev->all_mddevs);

		bs = mddev->bio_set;

		sync_bs = mddev->sync_set;

		mddev->bio_set = NULL;

		mddev->sync_set = NULL;

		if (mddev->gendisk) {

			/* We did a probe so need to clean up.  Call

			 * queue_work inside the spinlock so that
@@ -487,6 +502,8 @@ static void mddev_put(struct mddev *mddev) 
	spin_unlock(&all_mddevs_lock);

	if (bs)

		bioset_free(bs);

	if (sync_bs)

		bioset_free(sync_bs);

}



static void md_safemode_timeout(unsigned long data);
@@ -751,7 +768,7 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev, 
	if (test_bit(Faulty, &rdev->flags))

		return;



	bio = bio_alloc_mddev(GFP_NOIO, 1, mddev);

	bio = md_bio_alloc_sync(mddev);



	atomic_inc(&rdev->nr_pending);
@@ -783,7 +800,7 @@ int md_super_wait(struct mddev *mddev) 
int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,

		 struct page *page, int op, int op_flags, bool metadata_op)

{

	struct bio *bio = bio_alloc_mddev(GFP_NOIO, 1, rdev->mddev);

	struct bio *bio = md_bio_alloc_sync(rdev->mddev);

	int ret;



	bio->bi_bdev = (metadata_op && rdev->meta_bdev) ?
@@ -1852,7 +1869,7 @@ retry: 
		max_dev = le32_to_cpu(sb->max_dev);



	for (i=0; i<max_dev;i++)

		sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_FAULTY);

		sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_SPARE);



	if (test_bit(MD_HAS_JOURNAL, &mddev->flags))

		sb->feature_map |= cpu_to_le32(MD_FEATURE_JOURNAL);
@@ -5432,6 +5449,11 @@ int md_run(struct mddev *mddev) 
		if (!mddev->bio_set)

			return -ENOMEM;

	}

	if (mddev->sync_set == NULL) {

		mddev->sync_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);

		if (!mddev->sync_set)

			return -ENOMEM;

	}



	spin_lock(&pers_lock);

	pers = find_pers(mddev->level, mddev->clevel);
@@ -7950,12 +7972,14 @@ EXPORT_SYMBOL(md_done_sync); 
 * If we need to update some array metadata (e.g. 'active' flag

 * in superblock) before writing, schedule a superblock update

 * and wait for it to complete.

 * A return value of 'false' means that the write wasn't recorded

 * and cannot proceed as the array is being suspend.

 */

void md_write_start(struct mddev *mddev, struct bio *bi)

bool md_write_start(struct mddev *mddev, struct bio *bi)

{

	int did_change = 0;

	if (bio_data_dir(bi) != WRITE)

		return;

		return true;



	BUG_ON(mddev->ro == 1);

	if (mddev->ro == 2) {
@@ -7987,7 +8011,12 @@ void md_write_start(struct mddev *mddev, struct bio *bi) 
	if (did_change)

		sysfs_notify_dirent_safe(mddev->sysfs_state);

	wait_event(mddev->sb_wait,

		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));

		   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags) && !mddev->suspended);

	if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {

		percpu_ref_put(&mddev->writes_pending);

		return false;

	}

	return true;

}

EXPORT_SYMBOL(md_write_start);

drivers/md/md.h

+5 −2
Original line number Diff line number Diff line
@@ -444,6 +444,9 @@ struct mddev { 
	struct attribute_group		*to_remove;



	struct bio_set			*bio_set;

	struct bio_set			*sync_set; /* for sync operations like

						   * metadata and bitmap writes

						   */



	/* Generic flush handling.

	 * The last to finish preflush schedules a worker to submit
@@ -510,7 +513,7 @@ struct md_personality 
	int level;

	struct list_head list;

	struct module *owner;

	void (*make_request)(struct mddev *mddev, struct bio *bio);

	bool (*make_request)(struct mddev *mddev, struct bio *bio);

	int (*run)(struct mddev *mddev);

	void (*free)(struct mddev *mddev, void *priv);

	void (*status)(struct seq_file *seq, struct mddev *mddev);
@@ -649,7 +652,7 @@ extern void md_wakeup_thread(struct md_thread *thread); 
extern void md_check_recovery(struct mddev *mddev);

extern void md_reap_sync_thread(struct mddev *mddev);

extern int mddev_init_writes_pending(struct mddev *mddev);

extern void md_write_start(struct mddev *mddev, struct bio *bi);

extern bool md_write_start(struct mddev *mddev, struct bio *bi);

extern void md_write_inc(struct mddev *mddev, struct bio *bi);

extern void md_write_end(struct mddev *mddev);

extern void md_done_sync(struct mddev *mddev, int blocks, int ok);

drivers/md/multipath.c

+4 −4
Original line number Diff line number Diff line
@@ -106,7 +106,7 @@ static void multipath_end_request(struct bio *bio) 
	rdev_dec_pending(rdev, conf->mddev);

}



static void multipath_make_request(struct mddev *mddev, struct bio * bio)

static bool multipath_make_request(struct mddev *mddev, struct bio * bio)

{

	struct mpconf *conf = mddev->private;

	struct multipath_bh * mp_bh;
@@ -114,7 +114,7 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio) 


	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {

		md_flush_request(mddev, bio);

		return;

		return true;

	}



	mp_bh = mempool_alloc(conf->pool, GFP_NOIO);
@@ -126,7 +126,7 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio) 
	if (mp_bh->path < 0) {

		bio_io_error(bio);

		mempool_free(mp_bh, conf->pool);

		return;

		return true;

	}

	multipath = conf->multipaths + mp_bh->path;
@@ -141,7 +141,7 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio) 
	mddev_check_writesame(mddev, &mp_bh->bio);

	mddev_check_write_zeroes(mddev, &mp_bh->bio);

	generic_make_request(&mp_bh->bio);

	return;

	return true;

}



static void multipath_status(struct seq_file *seq, struct mddev *mddev)

CRA Git | Maintained and supported by SUSTech CRA and CCSE