Merge tag 'for-5.12/block-2021-02-17' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:
 "Another nice round of removing more code than what is added, mostly
  due to Christoph's relentless pursuit of tech debt removal/cleanups.
  This pull request contains:

   - Two series of BFQ improvements (Paolo, Jan, Jia)

   - Block iov_iter improvements (Pavel)

   - bsg error path fix (Pan)

   - blk-mq scheduler improvements (Jan)

   - -EBUSY discard fix (Jan)

   - bvec allocation improvements (Ming, Christoph)

   - bio allocation and init improvements (Christoph)

   - Store bdev pointer in bio instead of gendisk + partno (Christoph)

   - Block trace point cleanups (Christoph)

   - hard read-only vs read-only split (Christoph)

   - Block based swap cleanups (Christoph)

   - Zoned write granularity support (Damien)

   - Various fixes/tweaks (Chunguang, Guoqing, Lei, Lukas, Huhai)"

* tag 'for-5.12/block-2021-02-17' of git://git.kernel.dk/linux-block: (104 commits)
  mm: simplify swapdev_block
  sd_zbc: clear zone resources for non-zoned case
  block: introduce blk_queue_clear_zone_settings()
  zonefs: use zone write granularity as block size
  block: introduce zone_write_granularity limit
  block: use blk_queue_set_zoned in add_partition()
  nullb: use blk_queue_set_zoned() to setup zoned devices
  nvme: cleanup zone information initialization
  block: document zone_append_max_bytes attribute
  block: use bi_max_vecs to find the bvec pool
  md/raid10: remove dead code in reshape_request
  block: mark the bio as cloned in bio_iov_bvec_set
  block: set BIO_NO_PAGE_REF in bio_iov_bvec_set
  block: remove a layer of indentation in bio_iov_iter_get_pages
  block: turn the nr_iovecs argument to bio_alloc* into an unsigned short
  block: remove the 1 and 4 vec bvec_slabs entries
  block: streamline bvec_alloc
  block: factor out a bvec_alloc_gfp helper
  block: move struct biovec_slab to bio.c
  block: reuse BIO_INLINE_VECS for integrity bvecs
  ...

1 files changed, 49 insertions, 257 deletions

diff --git a/block/genhd.c b/block/genhd.c
index 9e741a4f351b..36ff45bbaaaf 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -162,15 +162,6 @@ static void part_in_flight_rw(struct block_device *part,
 		inflight[1] = 0;
 }
 
-struct block_device *__disk_get_part(struct gendisk *disk, int partno)
-{
-	struct disk_part_tbl *ptbl = rcu_dereference(disk->part_tbl);
-
-	if (unlikely(partno < 0 || partno >= ptbl->len))
-		return NULL;
-	return rcu_dereference(ptbl->part[partno]);
-}
-
 /**
  * disk_part_iter_init - initialize partition iterator
  * @piter: iterator to initialize
@@ -185,26 +176,14 @@ struct block_device *__disk_get_part(struct gendisk *disk, int partno)
 void disk_part_iter_init(struct disk_part_iter *piter, struct gendisk *disk,
 			  unsigned int flags)
 {
-	struct disk_part_tbl *ptbl;
-
-	rcu_read_lock();
-	ptbl = rcu_dereference(disk->part_tbl);
-
 	piter->disk = disk;
 	piter->part = NULL;
-
-	if (flags & DISK_PITER_REVERSE)
-		piter->idx = ptbl->len - 1;
-	else if (flags & (DISK_PITER_INCL_PART0 | DISK_PITER_INCL_EMPTY_PART0))
+	if (flags & (DISK_PITER_INCL_PART0 | DISK_PITER_INCL_EMPTY_PART0))
 		piter->idx = 0;
 	else
 		piter->idx = 1;
-
 	piter->flags = flags;
-
-	rcu_read_unlock();
 }
-EXPORT_SYMBOL_GPL(disk_part_iter_init);
 
 /**
  * disk_part_iter_next - proceed iterator to the next partition and return it
@@ -217,57 +196,30 @@ EXPORT_SYMBOL_GPL(disk_part_iter_init);
  */
 struct block_device *disk_part_iter_next(struct disk_part_iter *piter)
 {
-	struct disk_part_tbl *ptbl;
-	int inc, end;
+	struct block_device *part;
+	unsigned long idx;
 
 	/* put the last partition */
 	disk_part_iter_exit(piter);
 
-	/* get part_tbl */
 	rcu_read_lock();
-	ptbl = rcu_dereference(piter->disk->part_tbl);
-
-	/* determine iteration parameters */
-	if (piter->flags & DISK_PITER_REVERSE) {
-		inc = -1;
-		if (piter->flags & (DISK_PITER_INCL_PART0 |
-				    DISK_PITER_INCL_EMPTY_PART0))
-			end = -1;
-		else
-			end = 0;
-	} else {
-		inc = 1;
-		end = ptbl->len;
-	}
-
-	/* iterate to the next partition */
-	for (; piter->idx != end; piter->idx += inc) {
-		struct block_device *part;
-
-		part = rcu_dereference(ptbl->part[piter->idx]);
-		if (!part)
-			continue;
-		piter->part = bdgrab(part);
-		if (!piter->part)
-			continue;
+	xa_for_each_start(&piter->disk->part_tbl, idx, part, piter->idx) {
 		if (!bdev_nr_sectors(part) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY) &&
 		    !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
-		      piter->idx == 0)) {
-			bdput(piter->part);
-			piter->part = NULL;
+		      piter->idx == 0))
 			continue;
-		}
 
-		piter->idx += inc;
+		piter->part = bdgrab(part);
+		if (!piter->part)
+			continue;
+		piter->idx = idx + 1;
 		break;
 	}
-
 	rcu_read_unlock();
 
 	return piter->part;
 }
-EXPORT_SYMBOL_GPL(disk_part_iter_next);
 
 /**
  * disk_part_iter_exit - finish up partition iteration
@@ -284,91 +236,6 @@ void disk_part_iter_exit(struct disk_part_iter *piter)
 		bdput(piter->part);
 	piter->part = NULL;
 }
-EXPORT_SYMBOL_GPL(disk_part_iter_exit);
-
-static inline int sector_in_part(struct block_device *part, sector_t sector)
-{
-	return part->bd_start_sect <= sector &&
-		sector < part->bd_start_sect + bdev_nr_sectors(part);
-}
-
-/**
- * disk_map_sector_rcu - map sector to partition
- * @disk: gendisk of interest
- * @sector: sector to map
- *
- * Find out which partition @sector maps to on @disk.  This is
- * primarily used for stats accounting.
- *
- * CONTEXT:
- * RCU read locked.
- *
- * RETURNS:
- * Found partition on success, part0 is returned if no partition matches
- * or the matched partition is being deleted.
- */
-struct block_device *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
-{
-	struct disk_part_tbl *ptbl;
-	struct block_device *part;
-	int i;
-
-	rcu_read_lock();
-	ptbl = rcu_dereference(disk->part_tbl);
-
-	part = rcu_dereference(ptbl->last_lookup);
-	if (part && sector_in_part(part, sector))
-		goto out_unlock;
-
-	for (i = 1; i < ptbl->len; i++) {
-		part = rcu_dereference(ptbl->part[i]);
-		if (part && sector_in_part(part, sector)) {
-			rcu_assign_pointer(ptbl->last_lookup, part);
-			goto out_unlock;
-		}
-	}
-
-	part = disk->part0;
-out_unlock:
-	rcu_read_unlock();
-	return part;
-}
-
-/**
- * disk_has_partitions
- * @disk: gendisk of interest
- *
- * Walk through the partition table and check if valid partition exists.
- *
- * CONTEXT:
- * Don't care.
- *
- * RETURNS:
- * True if the gendisk has at least one valid non-zero size partition.
- * Otherwise false.
- */
-bool disk_has_partitions(struct gendisk *disk)
-{
-	struct disk_part_tbl *ptbl;
-	int i;
-	bool ret = false;
-
-	rcu_read_lock();
-	ptbl = rcu_dereference(disk->part_tbl);
-
-	/* Iterate partitions skipping the whole device at index 0 */
-	for (i = 1; i < ptbl->len; i++) {
-		if (rcu_dereference(ptbl->part[i])) {
-			ret = true;
-			break;
-		}
-	}
-
-	rcu_read_unlock();
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(disk_has_partitions);
 
 /*
  * Can be deleted altogether. Later.
@@ -604,6 +471,18 @@ static char *bdevt_str(dev_t devt, char *buf)
 	return buf;
 }
 
+void disk_uevent(struct gendisk *disk, enum kobject_action action)
+{
+	struct disk_part_iter piter;
+	struct block_device *part;
+
+	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_PART0);
+	while ((part = disk_part_iter_next(&piter)))
+		kobject_uevent(bdev_kobj(part), action);
+	disk_part_iter_exit(&piter);
+}
+EXPORT_SYMBOL_GPL(disk_uevent);
+
 static void disk_scan_partitions(struct gendisk *disk)
 {
 	struct block_device *bdev;
@@ -621,8 +500,6 @@ static void register_disk(struct device *parent, struct gendisk *disk,
 			  const struct attribute_group **groups)
 {
 	struct device *ddev = disk_to_dev(disk);
-	struct disk_part_iter piter;
-	struct block_device *part;
 	int err;
 
 	ddev->parent = parent;
@@ -665,15 +542,9 @@ static void register_disk(struct device *parent, struct gendisk *disk,
 
 	disk_scan_partitions(disk);
 
-	/* announce disk after possible partitions are created */
+	/* announce the disk and partitions after all partitions are created */
 	dev_set_uevent_suppress(ddev, 0);
-	kobject_uevent(&ddev->kobj, KOBJ_ADD);
-
-	/* announce possible partitions */
-	disk_part_iter_init(&piter, disk, 0);
-	while ((part = disk_part_iter_next(&piter)))
-		kobject_uevent(bdev_kobj(part), KOBJ_ADD);
-	disk_part_iter_exit(&piter);
+	disk_uevent(disk, KOBJ_ADD);
 
 	if (disk->queue->backing_dev_info->dev) {
 		err = sysfs_create_link(&ddev->kobj,
@@ -829,8 +700,7 @@ void del_gendisk(struct gendisk *disk)
 	down_write(&bdev_lookup_sem);
 
 	/* invalidate stuff */
-	disk_part_iter_init(&piter, disk,
-			     DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
+	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
 	while ((part = disk_part_iter_next(&piter))) {
 		invalidate_partition(part);
 		delete_partition(part);
@@ -929,7 +799,7 @@ struct block_device *bdget_disk(struct gendisk *disk, int partno)
 	struct block_device *bdev = NULL;
 
 	rcu_read_lock();
-	bdev = __disk_get_part(disk, partno);
+	bdev = xa_load(&disk->part_tbl, partno);
 	if (bdev && !bdgrab(bdev))
 		bdev = NULL;
 	rcu_read_unlock();
@@ -1320,83 +1190,6 @@ static const struct attribute_group *disk_attr_groups[] = {
 };
 
 /**
- * disk_replace_part_tbl - replace disk->part_tbl in RCU-safe way
- * @disk: disk to replace part_tbl for
- * @new_ptbl: new part_tbl to install
- *
- * Replace disk->part_tbl with @new_ptbl in RCU-safe way.  The
- * original ptbl is freed using RCU callback.
- *
- * LOCKING:
- * Matching bd_mutex locked or the caller is the only user of @disk.
- */
-static void disk_replace_part_tbl(struct gendisk *disk,
-				  struct disk_part_tbl *new_ptbl)
-{
-	struct disk_part_tbl *old_ptbl =
-		rcu_dereference_protected(disk->part_tbl, 1);
-
-	rcu_assign_pointer(disk->part_tbl, new_ptbl);
-
-	if (old_ptbl) {
-		rcu_assign_pointer(old_ptbl->last_lookup, NULL);
-		kfree_rcu(old_ptbl, rcu_head);
-	}
-}
-
-/**
- * disk_expand_part_tbl - expand disk->part_tbl
- * @disk: disk to expand part_tbl for
- * @partno: expand such that this partno can fit in
- *
- * Expand disk->part_tbl such that @partno can fit in.  disk->part_tbl
- * uses RCU to allow unlocked dereferencing for stats and other stuff.
- *
- * LOCKING:
- * Matching bd_mutex locked or the caller is the only user of @disk.
- * Might sleep.
- *
- * RETURNS:
- * 0 on success, -errno on failure.
- */
-int disk_expand_part_tbl(struct gendisk *disk, int partno)
-{
-	struct disk_part_tbl *old_ptbl =
-		rcu_dereference_protected(disk->part_tbl, 1);
-	struct disk_part_tbl *new_ptbl;
-	int len = old_ptbl ? old_ptbl->len : 0;
-	int i, target;
-
-	/*
-	 * check for int overflow, since we can get here from blkpg_ioctl()
-	 * with a user passed 'partno'.
-	 */
-	target = partno + 1;
-	if (target < 0)
-		return -EINVAL;
-
-	/* disk_max_parts() is zero during initialization, ignore if so */
-	if (disk_max_parts(disk) && target > disk_max_parts(disk))
-		return -EINVAL;
-
-	if (target <= len)
-		return 0;
-
-	new_ptbl = kzalloc_node(struct_size(new_ptbl, part, target), GFP_KERNEL,
-				disk->node_id);
-	if (!new_ptbl)
-		return -ENOMEM;
-
-	new_ptbl->len = target;
-
-	for (i = 0; i < len; i++)
-		rcu_assign_pointer(new_ptbl->part[i], old_ptbl->part[i]);
-
-	disk_replace_part_tbl(disk, new_ptbl);
-	return 0;
-}
-
-/**
  * disk_release - releases all allocated resources of the gendisk
  * @dev: the device representing this disk
  *
@@ -1419,7 +1212,7 @@ static void disk_release(struct device *dev)
 	blk_free_devt(dev->devt);
 	disk_release_events(disk);
 	kfree(disk->random);
-	disk_replace_part_tbl(disk, NULL);
+	xa_destroy(&disk->part_tbl);
 	bdput(disk->part0);
 	if (disk->queue)
 		blk_put_queue(disk->queue);
@@ -1572,7 +1365,6 @@ dev_t blk_lookup_devt(const char *name, int partno)
 struct gendisk *__alloc_disk_node(int minors, int node_id)
 {
 	struct gendisk *disk;
-	struct disk_part_tbl *ptbl;
 
 	if (minors > DISK_MAX_PARTS) {
 		printk(KERN_ERR
@@ -1590,11 +1382,9 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 		goto out_free_disk;
 
 	disk->node_id = node_id;
-	if (disk_expand_part_tbl(disk, 0))
-		goto out_bdput;
-
-	ptbl = rcu_dereference_protected(disk->part_tbl, 1);
-	rcu_assign_pointer(ptbl->part[0], disk->part0);
+	xa_init(&disk->part_tbl);
+	if (xa_insert(&disk->part_tbl, 0, disk->part0, GFP_KERNEL))
+		goto out_destroy_part_tbl;
 
 	disk->minors = minors;
 	rand_initialize_disk(disk);
@@ -1603,7 +1393,8 @@ struct gendisk *__alloc_disk_node(int minors, int node_id)
 	device_initialize(disk_to_dev(disk));
 	return disk;
 
-out_bdput:
+out_destroy_part_tbl:
+	xa_destroy(&disk->part_tbl);
 	bdput(disk->part0);
 out_free_disk:
 	kfree(disk);
@@ -1638,31 +1429,32 @@ static void set_disk_ro_uevent(struct gendisk *gd, int ro)
 	kobject_uevent_env(&disk_to_dev(gd)->kobj, KOBJ_CHANGE, envp);
 }
 
-void set_disk_ro(struct gendisk *disk, int flag)
+/**
+ * set_disk_ro - set a gendisk read-only
+ * @disk:	gendisk to operate on
+ * @read_only:	%true to set the disk read-only, %false set the disk read/write
+ *
+ * This function is used to indicate whether a given disk device should have its
+ * read-only flag set. set_disk_ro() is typically used by device drivers to
+ * indicate whether the underlying physical device is write-protected.
+ */
+void set_disk_ro(struct gendisk *disk, bool read_only)
 {
-	struct disk_part_iter piter;
-	struct block_device *part;
-
-	if (disk->part0->bd_read_only != flag) {
-		set_disk_ro_uevent(disk, flag);
-		disk->part0->bd_read_only = flag;
+	if (read_only) {
+		if (test_and_set_bit(GD_READ_ONLY, &disk->state))
+			return;
+	} else {
+		if (!test_and_clear_bit(GD_READ_ONLY, &disk->state))
+			return;
 	}
-
-	disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
-	while ((part = disk_part_iter_next(&piter)))
-		part->bd_read_only = flag;
-	disk_part_iter_exit(&piter);
+	set_disk_ro_uevent(disk, read_only);
 }
-
 EXPORT_SYMBOL(set_disk_ro);
 
 int bdev_read_only(struct block_device *bdev)
 {
-	if (!bdev)
-		return 0;
-	return bdev->bd_read_only;
+	return bdev->bd_read_only || get_disk_ro(bdev->bd_disk);
 }
-
 EXPORT_SYMBOL(bdev_read_only);
 
 /*