Merge tag 'md/3.20' of git://neil.brown.name/md

Pull md updates from Neil Brown:

 - assorted locking changes so that access to /proc/mdstat
   and much of /sys/block/mdXX/md/* is protected by a spinlock
   rather than a mutex and will never block indefinitely.

 - Make an 'if' condition in RAID5 - which has been implicated
   in recent bugs - more readable.

 - misc minor fixes

* tag 'md/3.20' of git://neil.brown.name/md: (28 commits)
  md/raid10: fix conversion from RAID0 to RAID10
  md: wakeup thread upon rdev_dec_pending()
  md: make reconfig_mutex optional for writes to md sysfs files.
  md: move mddev_lock and related to md.h
  md: use mddev->lock to protect updates to resync_{min,max}.
  md: minor cleanup in safe_delay_store.
  md: move GET_BITMAP_FILE ioctl out from mddev_lock.
  md: tidy up set_bitmap_file
  md: remove unnecessary 'buf' from get_bitmap_file.
  md: remove mddev_lock from rdev_attr_show()
  md: remove mddev_lock() from md_attr_show()
  md/raid5: use ->lock to protect accessing raid5 sysfs attributes.
  md: remove need for mddev_lock() in md_seq_show()
  md/bitmap: protect clearing of ->bitmap by mddev->lock
  md: protect ->pers changes with mddev->lock
  md: level_store: group all important changes into one place.
  md: rename ->stop to ->free
  md: split detach operation out from ->stop.
  md/linear: remove rcu protections in favour of suspend/resume
  md: make merge_bvec_fn more robust in face of personality changes.
  ...

Author: torvalds

arch/x86/Makefile

@@ -148,6 +148,7 @@ cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTI
 
 # does binutils support specific instructions?
 asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
+asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1)
 asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1)
 avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
 avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)

drivers/md/bitmap.c

@@ -1619,7 +1619,9 @@ void bitmap_destroy(struct mddev *mddev)
 		return;
 
 	mutex_lock(&mddev->bitmap_info.mutex);
+	spin_lock(&mddev->lock);
 	mddev->bitmap = NULL; /* disconnect from the md device */
+	spin_unlock(&mddev->lock);
 	mutex_unlock(&mddev->bitmap_info.mutex);
 	if (mddev->thread)
 		mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
@@ -2209,11 +2211,13 @@ __ATTR(metadata, S_IRUGO|S_IWUSR, metadata_show, metadata_store);
 static ssize_t can_clear_show(struct mddev *mddev, char *page)
 {
 	int len;
+	spin_lock(&mddev->lock);
 	if (mddev->bitmap)
 		len = sprintf(page, "%s\n", (mddev->bitmap->need_sync ?
 					     "false" : "true"));
 	else
 		len = sprintf(page, "\n");
+	spin_unlock(&mddev->lock);
 	return len;
 }
 
@@ -2238,10 +2242,15 @@ __ATTR(can_clear, S_IRUGO|S_IWUSR, can_clear_show, can_clear_store);
 static ssize_t
 behind_writes_used_show(struct mddev *mddev, char *page)
 {
+	ssize_t ret;
+	spin_lock(&mddev->lock);
 	if (mddev->bitmap == NULL)
-		return sprintf(page, "0\n");
-	return sprintf(page, "%lu\n",
-		       mddev->bitmap->behind_writes_used);
+		ret = sprintf(page, "0\n");
+	else
+		ret = sprintf(page, "%lu\n",
+			      mddev->bitmap->behind_writes_used);
+	spin_unlock(&mddev->lock);
+	return ret;
 }
 
 static ssize_t

drivers/md/dm-raid.c

@@ -746,13 +746,7 @@ static int raid_is_congested(struct dm_target_callbacks *cb, int bits)
 {
 	struct raid_set *rs = container_of(cb, struct raid_set, callbacks);
 
-	if (rs->raid_type->level == 1)
-		return md_raid1_congested(&rs->md, bits);
-
-	if (rs->raid_type->level == 10)
-		return md_raid10_congested(&rs->md, bits);
-
-	return md_raid5_congested(&rs->md, bits);
+	return mddev_congested(&rs->md, bits);
 }
 
 /*

drivers/md/faulty.c

@@ -332,13 +332,11 @@ static int run(struct mddev *mddev)
 	return 0;
 }
 
-static int stop(struct mddev *mddev)
+static void faulty_free(struct mddev *mddev, void *priv)
 {
-	struct faulty_conf *conf = mddev->private;
+	struct faulty_conf *conf = priv;
 
 	kfree(conf);
-	mddev->private = NULL;
-	return 0;
 }
 
 static struct md_personality faulty_personality =
@@ -348,7 +346,7 @@ static struct md_personality faulty_personality =
 	.owner		= THIS_MODULE,
 	.make_request	= make_request,
 	.run		= run,
-	.stop		= stop,
+	.free		= faulty_free,
 	.status		= status,
 	.check_reshape	= reshape,
 	.size		= faulty_size,

drivers/md/linear.c

@@ -34,7 +34,7 @@ static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
 
 	lo = 0;
 	hi = mddev->raid_disks - 1;
-	conf = rcu_dereference(mddev->private);
+	conf = mddev->private;
 
 	/*
 	 * Binary Search
@@ -60,18 +60,16 @@ static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
  *
  *	Return amount of bytes we can take at this offset
  */
-static int linear_mergeable_bvec(struct request_queue *q,
+static int linear_mergeable_bvec(struct mddev *mddev,
 				 struct bvec_merge_data *bvm,
 				 struct bio_vec *biovec)
 {
-	struct mddev *mddev = q->queuedata;
 	struct dev_info *dev0;
 	unsigned long maxsectors, bio_sectors = bvm->bi_size >> 9;
 	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
 	int maxbytes = biovec->bv_len;
 	struct request_queue *subq;
 
-	rcu_read_lock();
 	dev0 = which_dev(mddev, sector);
 	maxsectors = dev0->end_sector - sector;
 	subq = bdev_get_queue(dev0->rdev->bdev);
@@ -81,7 +79,6 @@ static int linear_mergeable_bvec(struct request_queue *q,
 		maxbytes = min(maxbytes, subq->merge_bvec_fn(subq, bvm,
 							     biovec));
 	}
-	rcu_read_unlock();
 
 	if (maxsectors < bio_sectors)
 		maxsectors = 0;
@@ -97,24 +94,18 @@ static int linear_mergeable_bvec(struct request_queue *q,
 		return maxsectors << 9;
 }
 
-static int linear_congested(void *data, int bits)
+static int linear_congested(struct mddev *mddev, int bits)
 {
-	struct mddev *mddev = data;
 	struct linear_conf *conf;
 	int i, ret = 0;
 
-	if (mddev_congested(mddev, bits))
-		return 1;
-
-	rcu_read_lock();
-	conf = rcu_dereference(mddev->private);
+	conf = mddev->private;
 
 	for (i = 0; i < mddev->raid_disks && !ret ; i++) {
 		struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev);
 		ret |= bdi_congested(&q->backing_dev_info, bits);
 	}
 
-	rcu_read_unlock();
 	return ret;
 }
 
@@ -123,12 +114,10 @@ static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disk
 	struct linear_conf *conf;
 	sector_t array_sectors;
 
-	rcu_read_lock();
-	conf = rcu_dereference(mddev->private);
+	conf = mddev->private;
 	WARN_ONCE(sectors || raid_disks,
 		  "%s does not support generic reshape\n", __func__);
 	array_sectors = conf->array_sectors;
-	rcu_read_unlock();
 
 	return array_sectors;
 }
@@ -217,10 +206,6 @@ static int linear_run (struct mddev *mddev)
 	mddev->private = conf;
 	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
 
-	blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
-	mddev->queue->backing_dev_info.congested_fn = linear_congested;
-	mddev->queue->backing_dev_info.congested_data = mddev;
-
 	ret =  md_integrity_register(mddev);
 	if (ret) {
 		kfree(conf);
@@ -252,38 +237,23 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
 	if (!newconf)
 		return -ENOMEM;
 
-	oldconf = rcu_dereference_protected(mddev->private,
-					    lockdep_is_held(
-						    &mddev->reconfig_mutex));
+	mddev_suspend(mddev);
+	oldconf = mddev->private;
 	mddev->raid_disks++;
-	rcu_assign_pointer(mddev->private, newconf);
+	mddev->private = newconf;
 	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
 	set_capacity(mddev->gendisk, mddev->array_sectors);
+	mddev_resume(mddev);
 	revalidate_disk(mddev->gendisk);
-	kfree_rcu(oldconf, rcu);
+	kfree(oldconf);
 	return 0;
 }
 
-static int linear_stop (struct mddev *mddev)
+static void linear_free(struct mddev *mddev, void *priv)
 {
-	struct linear_conf *conf =
-		rcu_dereference_protected(mddev->private,
-					  lockdep_is_held(
-						  &mddev->reconfig_mutex));
+	struct linear_conf *conf = priv;
 
-	/*
-	 * We do not require rcu protection here since
-	 * we hold reconfig_mutex for both linear_add and
-	 * linear_stop, so they cannot race.
-	 * We should make sure any old 'conf's are properly
-	 * freed though.
-	 */
-	rcu_barrier();
-	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
 	kfree(conf);
-	mddev->private = NULL;
-
-	return 0;
 }
 
 static void linear_make_request(struct mddev *mddev, struct bio *bio)
@@ -299,16 +269,12 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio)
 	}
 
 	do {
-		rcu_read_lock();
-
 		tmp_dev = which_dev(mddev, bio->bi_iter.bi_sector);
 		start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors;
 		end_sector = tmp_dev->end_sector;
 		data_offset = tmp_dev->rdev->data_offset;
 		bio->bi_bdev = tmp_dev->rdev->bdev;
 
-		rcu_read_unlock();
-
 		if (unlikely(bio->bi_iter.bi_sector >= end_sector ||
 			     bio->bi_iter.bi_sector < start_sector))
 			goto out_of_bounds;
@@ -355,17 +321,24 @@ static void linear_status (struct seq_file *seq, struct mddev *mddev)
 	seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2);
 }
 
+static void linear_quiesce(struct mddev *mddev, int state)
+{
+}
+
 static struct md_personality linear_personality =
 {
 	.name		= "linear",
 	.level		= LEVEL_LINEAR,
 	.owner		= THIS_MODULE,
 	.make_request	= linear_make_request,
 	.run		= linear_run,
-	.stop		= linear_stop,
+	.free		= linear_free,
 	.status		= linear_status,
 	.hot_add_disk	= linear_add,
 	.size		= linear_size,
+	.quiesce	= linear_quiesce,
+	.congested	= linear_congested,
+	.mergeable_bvec	= linear_mergeable_bvec,
 };
 
 static int __init linear_init (void)