Compactifying bdev flags

We can easily have up to 24 flags with sane
 atomicity, _without_ pushing anything out
 of the first cacheline of struct block_device.
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQQqUNBr3gm4hGXdBJlZ7Krx/gZQ6wUCZkznRwAKCRBZ7Krx/gZQ
 69XpAQDOZCyvYOZ/dlMOKKLf2vAojC/h++E/NjvGt3erbvVN2wEArXMi13ECsoCw
 JYJA3MsmvjuY6VNcm24icf2/p4TMIgo=
 =JyYi
 -----END PGP SIGNATURE-----

Merge tag 'pull-bd_flags-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull bdev flags update from Al Viro:
 "Compactifying bdev flags.

  We can easily have up to 24 flags with sane atomicity, _without_
  pushing anything out of the first cacheline of struct block_device"

* tag 'pull-bd_flags-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  bdev: move ->bd_make_it_fail to ->__bd_flags
  bdev: move ->bd_ro_warned to ->__bd_flags
  bdev: move ->bd_has_subit_bio to ->__bd_flags
  bdev: move ->bd_write_holder into ->__bd_flags
  bdev: move ->bd_read_only to ->__bd_flags
  bdev: infrastructure for flags
  wrapper for access to ->bd_partno
  Use bdev_is_paritition() instead of open-coding it

block/bdev.c

@@ -422,13 +422,11 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno)
 	mutex_init(&bdev->bd_fsfreeze_mutex);
 	spin_lock_init(&bdev->bd_size_lock);
 	mutex_init(&bdev->bd_holder_lock);
-	bdev->bd_partno = partno;
+	atomic_set(&bdev->__bd_flags, partno);
 	bdev->bd_mapping = &inode->i_data;
 	bdev->bd_queue = disk->queue;
-	if (partno)
-		bdev->bd_has_submit_bio = disk->part0->bd_has_submit_bio;
-	else
-		bdev->bd_has_submit_bio = false;
+	if (partno && bdev_test_flag(disk->part0, BD_HAS_SUBMIT_BIO))
+		bdev_set_flag(bdev, BD_HAS_SUBMIT_BIO);
 	bdev->bd_stats = alloc_percpu(struct disk_stats);
 	if (!bdev->bd_stats) {
 		iput(inode);
@@ -642,7 +640,7 @@ static void bd_end_claim(struct block_device *bdev, void *holder)
 		bdev->bd_holder = NULL;
 		bdev->bd_holder_ops = NULL;
 		mutex_unlock(&bdev->bd_holder_lock);
-		if (bdev->bd_write_holder)
+		if (bdev_test_flag(bdev, BD_WRITE_HOLDER))
 			unblock = true;
 	}
 	if (!whole->bd_holders)
@@ -655,7 +653,7 @@ static void bd_end_claim(struct block_device *bdev, void *holder)
 	 */
 	if (unblock) {
 		disk_unblock_events(bdev->bd_disk);
-		bdev->bd_write_holder = false;
+		bdev_clear_flag(bdev, BD_WRITE_HOLDER);
 	}
 }
 
@@ -922,9 +920,10 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder,
 		 * writeable reference is too fragile given the way @mode is
 		 * used in blkdev_get/put().
 		 */
-		if ((mode & BLK_OPEN_WRITE) && !bdev->bd_write_holder &&
+		if ((mode & BLK_OPEN_WRITE) &&
+		    !bdev_test_flag(bdev, BD_WRITE_HOLDER) &&
 		    (disk->event_flags & DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE)) {
-			bdev->bd_write_holder = true;
+			bdev_set_flag(bdev, BD_WRITE_HOLDER);
 			unblock_events = false;
 		}
 	}

block/blk-core.c

@@ -496,7 +496,8 @@ __setup("fail_make_request=", setup_fail_make_request);
 
 bool should_fail_request(struct block_device *part, unsigned int bytes)
 {
-	return part->bd_make_it_fail && should_fail(&fail_make_request, bytes);
+	return bdev_test_flag(part, BD_MAKE_IT_FAIL) &&
+	       should_fail(&fail_make_request, bytes);
 }
 
 static int __init fail_make_request_debugfs(void)
@@ -516,10 +517,11 @@ static inline void bio_check_ro(struct bio *bio)
 		if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
 			return;
 
-		if (bio->bi_bdev->bd_ro_warned)
+		if (bdev_test_flag(bio->bi_bdev, BD_RO_WARNED))
 			return;
 
-		bio->bi_bdev->bd_ro_warned = true;
+		bdev_set_flag(bio->bi_bdev, BD_RO_WARNED);
+
 		/*
 		 * Use ioctl to set underlying disk of raid/dm to read-only
 		 * will trigger this.
@@ -616,7 +618,7 @@ static void __submit_bio(struct bio *bio)
 	if (unlikely(!blk_crypto_bio_prep(&bio)))
 		return;
 
-	if (!bio->bi_bdev->bd_has_submit_bio) {
+	if (!bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO)) {
 		blk_mq_submit_bio(bio);
 	} else if (likely(bio_queue_enter(bio) == 0)) {
 		struct gendisk *disk = bio->bi_bdev->bd_disk;
@@ -730,7 +732,7 @@ void submit_bio_noacct_nocheck(struct bio *bio)
 	 */
 	if (current->bio_list)
 		bio_list_add(&current->bio_list[0], bio);
-	else if (!bio->bi_bdev->bd_has_submit_bio)
+	else if (!bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO))
 		__submit_bio_noacct_mq(bio);
 	else
 		__submit_bio_noacct(bio);
@@ -766,7 +768,8 @@ void submit_bio_noacct(struct bio *bio)
 	if (!bio_flagged(bio, BIO_REMAPPED)) {
 		if (unlikely(bio_check_eod(bio)))
 			goto end_io;
-		if (bdev->bd_partno && unlikely(blk_partition_remap(bio)))
+		if (bdev_is_partition(bdev) &&
+		    unlikely(blk_partition_remap(bio)))
 			goto end_io;
 	}
 
@@ -991,7 +994,7 @@ again:
 	    (end || part_in_flight(part)))
 		__part_stat_add(part, io_ticks, now - stamp);
 
-	if (part->bd_partno) {
+	if (bdev_is_partition(part)) {
 		part = bdev_whole(part);
 		goto again;
 	}

block/blk-mq.c

@@ -93,7 +93,7 @@ static bool blk_mq_check_inflight(struct request *rq, void *priv)
 	struct mq_inflight *mi = priv;
 
 	if (rq->part && blk_do_io_stat(rq) &&
-	    (!mi->part->bd_partno || rq->part == mi->part) &&
+	    (!bdev_is_partition(mi->part) || rq->part == mi->part) &&
 	    blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)
 		mi->inflight[rq_data_dir(rq)]++;
 

block/blk-zoned.c

@@ -1257,7 +1257,7 @@ void blk_zone_write_plug_bio_endio(struct bio *bio)
 	 * is not called. So we need to schedule execution of the next
 	 * plugged BIO here.
 	 */
-	if (bio->bi_bdev->bd_has_submit_bio)
+	if (bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO))
 		disk_zone_wplug_unplug_bio(disk, zwplug);
 
 	/* Drop the reference we took when entering this function. */
@@ -1326,7 +1326,7 @@ static void blk_zone_wplug_bio_work(struct work_struct *work)
 	 * path for BIO-based devices will not do that. So drop this extra
 	 * reference here.
 	 */
-	if (bdev->bd_has_submit_bio)
+	if (bdev_test_flag(bdev, BD_HAS_SUBMIT_BIO))
 		blk_queue_exit(bdev->bd_disk->queue);
 
 put_zwplug:

block/early-lookup.c

@@ -78,7 +78,7 @@ static int __init devt_from_partuuid(const char *uuid_str, dev_t *devt)
 		 * to the partition number found by UUID.
 		 */
 		*devt = part_devt(dev_to_disk(dev),
-				  dev_to_bdev(dev)->bd_partno + offset);
+				  bdev_partno(dev_to_bdev(dev)) + offset);
 	} else {
 		*devt = dev->devt;
 	}

block/genhd.c

@@ -411,7 +411,8 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 	elevator_init_mq(disk->queue);
 
 	/* Mark bdev as having a submit_bio, if needed */
-	disk->part0->bd_has_submit_bio = disk->fops->submit_bio != NULL;
+	if (disk->fops->submit_bio)
+		bdev_set_flag(disk->part0, BD_HAS_SUBMIT_BIO);
 
 	/*
 	 * If the driver provides an explicit major number it also must provide
@@ -1064,7 +1065,8 @@ static DEVICE_ATTR(partscan, 0444, partscan_show, NULL);
 ssize_t part_fail_show(struct device *dev,
 		       struct device_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%d\n", dev_to_bdev(dev)->bd_make_it_fail);
+	return sprintf(buf, "%d\n",
+		       bdev_test_flag(dev_to_bdev(dev), BD_MAKE_IT_FAIL));
 }
 
 ssize_t part_fail_store(struct device *dev,
@@ -1073,9 +1075,12 @@ ssize_t part_fail_store(struct device *dev,
 {
 	int i;
 
-	if (count > 0 && sscanf(buf, "%d", &i) > 0)
-		dev_to_bdev(dev)->bd_make_it_fail = i;
-
+	if (count > 0 && sscanf(buf, "%d", &i) > 0) {
+		if (i)
+			bdev_set_flag(dev_to_bdev(dev), BD_MAKE_IT_FAIL);
+		else
+			bdev_clear_flag(dev_to_bdev(dev), BD_MAKE_IT_FAIL);
+	}
 	return count;
 }
 

block/ioctl.c

@@ -431,7 +431,10 @@ static int blkdev_roset(struct block_device *bdev, unsigned cmd,
 		if (ret)
 			return ret;
 	}
-	bdev->bd_read_only = n;
+	if (n)
+		bdev_set_flag(bdev, BD_READ_ONLY);
+	else
+		bdev_clear_flag(bdev, BD_READ_ONLY);
 	return 0;
 }
 

block/partitions/core.c

@@ -173,7 +173,7 @@ static struct parsed_partitions *check_partition(struct gendisk *hd)
 static ssize_t part_partition_show(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%d\n", dev_to_bdev(dev)->bd_partno);
+	return sprintf(buf, "%d\n", bdev_partno(dev_to_bdev(dev)));
 }
 
 static ssize_t part_start_show(struct device *dev,
@@ -250,7 +250,7 @@ static int part_uevent(const struct device *dev, struct kobj_uevent_env *env)
 {
 	const struct block_device *part = dev_to_bdev(dev);
 
-	add_uevent_var(env, "PARTN=%u", part->bd_partno);
+	add_uevent_var(env, "PARTN=%u", bdev_partno(part));
 	if (part->bd_meta_info && part->bd_meta_info->volname[0])
 		add_uevent_var(env, "PARTNAME=%s", part->bd_meta_info->volname);
 	return 0;
@@ -267,7 +267,7 @@ void drop_partition(struct block_device *part)
 {
 	lockdep_assert_held(&part->bd_disk->open_mutex);
 
-	xa_erase(&part->bd_disk->part_tbl, part->bd_partno);
+	xa_erase(&part->bd_disk->part_tbl, bdev_partno(part));
 	kobject_put(part->bd_holder_dir);
 
 	device_del(&part->bd_device);
@@ -338,8 +338,8 @@ static struct block_device *add_partition(struct gendisk *disk, int partno,
 	pdev->parent = ddev;
 
 	/* in consecutive minor range? */
-	if (bdev->bd_partno < disk->minors) {
-		devt = MKDEV(disk->major, disk->first_minor + bdev->bd_partno);
+	if (bdev_partno(bdev) < disk->minors) {
+		devt = MKDEV(disk->major, disk->first_minor + bdev_partno(bdev));
 	} else {
 		err = blk_alloc_ext_minor();
 		if (err < 0)
@@ -404,7 +404,7 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start,
 
 	rcu_read_lock();
 	xa_for_each_start(&disk->part_tbl, idx, part, 1) {
-		if (part->bd_partno != skip_partno &&
+		if (bdev_partno(part) != skip_partno &&
 		    start < part->bd_start_sect + bdev_nr_sectors(part) &&
 		    start + length > part->bd_start_sect) {
 			overlap = true;

include/linux/blk_types.h

@@ -45,10 +45,15 @@ struct block_device {
 	struct request_queue *	bd_queue;
 	struct disk_stats __percpu *bd_stats;
 	unsigned long		bd_stamp;
-	bool			bd_read_only;	/* read-only policy */
-	u8			bd_partno;
-	bool			bd_write_holder;
-	bool			bd_has_submit_bio;
+	atomic_t		__bd_flags;	// partition number + flags
+#define BD_PARTNO		255	// lower 8 bits; assign-once
+#define BD_READ_ONLY		(1u<<8) // read-only policy
+#define BD_WRITE_HOLDER		(1u<<9)
+#define BD_HAS_SUBMIT_BIO	(1u<<10)
+#define BD_RO_WARNED		(1u<<11)
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+#define BD_MAKE_IT_FAIL		(1u<<12)
+#endif
 	dev_t			bd_dev;
 	struct address_space	*bd_mapping;	/* page cache */
 
@@ -65,10 +70,6 @@ struct block_device {
 	struct mutex		bd_fsfreeze_mutex; /* serialize freeze/thaw */
 
 	struct partition_meta_info *bd_meta_info;
-#ifdef CONFIG_FAIL_MAKE_REQUEST
-	bool			bd_make_it_fail;
-#endif
-	bool			bd_ro_warned;
 	int			bd_writers;
 	/*
 	 * keep this out-of-line as it's both big and not needed in the fast

include/linux/blkdev.h

@@ -718,15 +718,35 @@ void invalidate_disk(struct gendisk *disk);
 void set_disk_ro(struct gendisk *disk, bool read_only);
 void disk_uevent(struct gendisk *disk, enum kobject_action action);
 
+static inline u8 bdev_partno(const struct block_device *bdev)
+{
+	return atomic_read(&bdev->__bd_flags) & BD_PARTNO;
+}
+
+static inline bool bdev_test_flag(const struct block_device *bdev, unsigned flag)
+{
+	return atomic_read(&bdev->__bd_flags) & flag;
+}
+
+static inline void bdev_set_flag(struct block_device *bdev, unsigned flag)
+{
+	atomic_or(flag, &bdev->__bd_flags);
+}
+
+static inline void bdev_clear_flag(struct block_device *bdev, unsigned flag)
+{
+	atomic_andnot(flag, &bdev->__bd_flags);
+}
+
 static inline int get_disk_ro(struct gendisk *disk)
 {
-	return disk->part0->bd_read_only ||
+	return bdev_test_flag(disk->part0, BD_READ_ONLY) ||
 		test_bit(GD_READ_ONLY, &disk->state);
 }
 
 static inline int bdev_read_only(struct block_device *bdev)
 {
-	return bdev->bd_read_only || get_disk_ro(bdev->bd_disk);
+	return bdev_test_flag(bdev, BD_READ_ONLY) || get_disk_ro(bdev->bd_disk);
 }
 
 bool set_capacity_and_notify(struct gendisk *disk, sector_t size);
@@ -1086,7 +1106,7 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
 
 static inline bool bdev_is_partition(struct block_device *bdev)
 {
-	return bdev->bd_partno;
+	return bdev_partno(bdev) != 0;
 }
 
 enum blk_default_limits {

include/linux/part_stat.h

@@ -59,7 +59,7 @@ static inline void part_stat_set_all(struct block_device *part, int value)
 
 #define part_stat_add(part, field, addnd)	do {			\
 	__part_stat_add((part), field, addnd);				\
-	if ((part)->bd_partno)						\
+	if (bdev_is_partition(part))					\
 		__part_stat_add(bdev_whole(part), field, addnd);	\
 } while (0)
 

lib/vsprintf.c

@@ -966,13 +966,13 @@ char *bdev_name(char *buf, char *end, struct block_device *bdev,
 
 	hd = bdev->bd_disk;
 	buf = string(buf, end, hd->disk_name, spec);
-	if (bdev->bd_partno) {
+	if (bdev_is_partition(bdev)) {
 		if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) {
 			if (buf < end)
 				*buf = 'p';
 			buf++;
 		}
-		buf = number(buf, end, bdev->bd_partno, spec);
+		buf = number(buf, end, bdev_partno(bdev), spec);
 	}
 	return buf;
 }