/*
* BLKRESETZONE ioctl processing.
* Called from blkdev_ioctl.
*/
int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
void __user *argp = (void __user *)arg;
struct request_queue *q;
struct blk_zone_range zrange;
if (!argp)
return -EINVAL;
q = bdev_get_queue(bdev);
if (!q)
return -ENXIO;
if (!blk_queue_is_zoned(q))
return -ENOTTY;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
if (!(mode & FMODE_WRITE))
return -EBADF;
if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range)))
return -EFAULT;
return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors,
GFP_KERNEL);
}
/**
* blkdev_nr_zones - Get number of zones
* @bdev: Target block device
*
* Description:
* Return the total number of zones of a zoned block device.
* For a regular block device, the number of zones is always 0.
*/
unsigned int blkdev_nr_zones(struct block_device *bdev)
{
struct request_queue *q = bdev_get_queue(bdev);
if (!blk_queue_is_zoned(q))
return 0;
return __blkdev_nr_zones(q, bdev->bd_part->nr_sects);
}
/*
* BLKREPORTZONE ioctl processing.
* Called from blkdev_ioctl.
*/
int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
void __user *argp = (void __user *)arg;
struct request_queue *q;
struct blk_zone_report rep;
struct blk_zone *zones;
int ret;
if (!argp)
return -EINVAL;
q = bdev_get_queue(bdev);
if (!q)
return -ENXIO;
if (!blk_queue_is_zoned(q))
return -ENOTTY;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
if (copy_from_user(&rep, argp, sizeof(struct blk_zone_report)))
return -EFAULT;
if (!rep.nr_zones)
return -EINVAL;
rep.nr_zones = min(blkdev_nr_zones(bdev), rep.nr_zones);
zones = kvmalloc_array(rep.nr_zones, sizeof(struct blk_zone),
GFP_KERNEL | __GFP_ZERO);
if (!zones)
return -ENOMEM;
ret = blkdev_report_zones(bdev, rep.sector,
zones, &rep.nr_zones,
GFP_KERNEL);
if (ret)
goto out;
if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) {
ret = -EFAULT;
goto out;
}
if (rep.nr_zones) {
if (copy_to_user(argp + sizeof(struct blk_zone_report), zones,
sizeof(struct blk_zone) * rep.nr_zones))
ret = -EFAULT;
}
out:
kvfree(zones);
return ret;
}
/**
* blkdev_reset_zones - Reset zones write pointer
* @bdev: Target block device
* @sector: Start sector of the first zone to reset
* @nr_sectors: Number of sectors, at least the length of one zone
* @gfp_mask: Memory allocation flags (for bio_alloc)
*
* Description:
* Reset the write pointer of the zones contained in the range
* @sector..@sector+@nr_sectors. Specifying the entire disk sector range
* is valid, but the specified range should not contain conventional zones.
*/
int blkdev_reset_zones(struct block_device *bdev,
sector_t sector, sector_t nr_sectors,
gfp_t gfp_mask)
{
struct request_queue *q = bdev_get_queue(bdev);
sector_t zone_sectors;
sector_t end_sector = sector + nr_sectors;
struct bio *bio = NULL;
struct blk_plug plug;
int ret;
if (!blk_queue_is_zoned(q))
return -EOPNOTSUPP;
if (bdev_read_only(bdev))
return -EPERM;
if (!nr_sectors || end_sector > bdev->bd_part->nr_sects)
/* Out of range */
return -EINVAL;
/* Check alignment (handle eventual smaller last zone) */
zone_sectors = blk_queue_zone_sectors(q);
if (sector & (zone_sectors - 1))
return -EINVAL;
if ((nr_sectors & (zone_sectors - 1)) &&
end_sector != bdev->bd_part->nr_sects)
return -EINVAL;
blk_start_plug(&plug);
while (sector < end_sector) {
bio = blk_next_bio(bio, 0, gfp_mask);
bio->bi_iter.bi_sector = sector;
bio_set_dev(bio, bdev);
bio_set_op_attrs(bio, REQ_OP_ZONE_RESET, 0);
sector += zone_sectors;
/* This may take a while, so be nice to others */
cond_resched();
}
ret = submit_bio_wait(bio);
bio_put(bio);
blk_finish_plug(&plug);
return ret;
}
/**
* blkdev_reset_zones - Reset zones write pointer
* @bdev: Target block device
* @sector: Start sector of the first zone to reset
* @nr_sectors: Number of sectors, at least the length of one zone
* @gfp_mask: Memory allocation flags (for bio_alloc)
*
* Description:
* Reset the write pointer of the zones contained in the range
* @sector..@sector+@nr_sectors. Specifying the entire disk sector range
* is valid, but the specified range should not contain conventional zones.
*/
int blkdev_reset_zones(struct block_device *bdev,
sector_t sector, sector_t nr_sectors,
gfp_t gfp_mask)
{
struct request_queue *q = bdev_get_queue(bdev);
sector_t zone_sectors;
sector_t end_sector = sector + nr_sectors;
struct bio *bio;
int ret;
if (!q)
return -ENXIO;
if (!blk_queue_is_zoned(q))
return -EOPNOTSUPP;
if (end_sector > bdev->bd_part->nr_sects)
/* Out of range */
return -EINVAL;
/* Check alignment (handle eventual smaller last zone) */
zone_sectors = blk_queue_zone_size(q);
if (sector & (zone_sectors - 1))
return -EINVAL;
if ((nr_sectors & (zone_sectors - 1)) &&
end_sector != bdev->bd_part->nr_sects)
return -EINVAL;
while (sector < end_sector) {
bio = bio_alloc(gfp_mask, 0);
bio->bi_iter.bi_sector = sector;
bio->bi_bdev = bdev;
bio_set_op_attrs(bio, REQ_OP_ZONE_RESET, 0);
ret = submit_bio_wait(bio);
bio_put(bio);
if (ret)
return ret;
sector += zone_sectors;
/* This may take a while, so be nice to others */
cond_resched();
}
return 0;
}
/**
* blkdev_report_zones - Get zones information
* @bdev: Target block device
* @sector: Sector from which to report zones
* @zones: Array of zone structures where to return the zones information
* @nr_zones: Number of zone structures in the zone array
* @gfp_mask: Memory allocation flags (for bio_alloc)
*
* Description:
* Get zone information starting from the zone containing @sector.
* The number of zone information reported may be less than the number
* requested by @nr_zones. The number of zones actually reported is
* returned in @nr_zones.
*/
int blkdev_report_zones(struct block_device *bdev, sector_t sector,
struct blk_zone *zones, unsigned int *nr_zones,
gfp_t gfp_mask)
{
struct request_queue *q = bdev_get_queue(bdev);
unsigned int i, nrz;
int ret;
if (!blk_queue_is_zoned(q))
return -EOPNOTSUPP;
/*
* A block device that advertized itself as zoned must have a
* report_zones method. If it does not have one defined, the device
* driver has a bug. So warn about that.
*/
if (WARN_ON_ONCE(!bdev->bd_disk->fops->report_zones))
return -EOPNOTSUPP;
if (!*nr_zones || sector >= bdev->bd_part->nr_sects) {
*nr_zones = 0;
return 0;
}
nrz = min(*nr_zones,
__blkdev_nr_zones(q, bdev->bd_part->nr_sects - sector));
ret = blk_report_zones(bdev->bd_disk, get_start_sect(bdev) + sector,
zones, &nrz, gfp_mask);
if (ret)
return ret;
for (i = 0; i < nrz; i++) {
if (!blkdev_report_zone(bdev, zones))
break;
zones++;
}
*nr_zones = i;
return 0;
}
/**
* blk_revalidate_disk_zones - (re)allocate and initialize zone bitmaps
* @disk: Target disk
*
* Helper function for low-level device drivers to (re) allocate and initialize
* a disk request queue zone bitmaps. This functions should normally be called
* within the disk ->revalidate method. For BIO based queues, no zone bitmap
* is allocated.
*/
int blk_revalidate_disk_zones(struct gendisk *disk)
{
struct request_queue *q = disk->queue;
unsigned int nr_zones = __blkdev_nr_zones(q, get_capacity(disk));
unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL;
unsigned int i, rep_nr_zones = 0, z = 0, nrz;
struct blk_zone *zones = NULL;
sector_t sector = 0;
int ret = 0;
/*
* BIO based queues do not use a scheduler so only q->nr_zones
* needs to be updated so that the sysfs exposed value is correct.
*/
if (!queue_is_rq_based(q)) {
q->nr_zones = nr_zones;
return 0;
}
if (!blk_queue_is_zoned(q) || !nr_zones) {
nr_zones = 0;
goto update;
}
/* Allocate bitmaps */
ret = -ENOMEM;
seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones);
if (!seq_zones_wlock)
goto out;
seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones);
if (!seq_zones_bitmap)
goto out;
/* Get zone information and initialize seq_zones_bitmap */
rep_nr_zones = nr_zones;
zones = blk_alloc_zones(q->node, &rep_nr_zones);
if (!zones)
goto out;
while (z < nr_zones) {
nrz = min(nr_zones - z, rep_nr_zones);
ret = blk_report_zones(disk, sector, zones, &nrz, GFP_NOIO);
if (ret)
goto out;
if (!nrz)
break;
for (i = 0; i < nrz; i++) {
if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL)
set_bit(z, seq_zones_bitmap);
z++;
}
sector += nrz * blk_queue_zone_sectors(q);
}
if (WARN_ON(z != nr_zones)) {
ret = -EIO;
goto out;
}
update:
/*
* Install the new bitmaps, making sure the queue is stopped and
* all I/Os are completed (i.e. a scheduler is not referencing the
* bitmaps).
*/
blk_mq_freeze_queue(q);
q->nr_zones = nr_zones;
swap(q->seq_zones_wlock, seq_zones_wlock);
swap(q->seq_zones_bitmap, seq_zones_bitmap);
blk_mq_unfreeze_queue(q);
out:
free_pages((unsigned long)zones,
get_order(rep_nr_zones * sizeof(struct blk_zone)));
kfree(seq_zones_wlock);
kfree(seq_zones_bitmap);
if (ret) {
pr_warn("%s: failed to revalidate zones\n", disk->disk_name);
blk_mq_freeze_queue(q);
blk_queue_free_zone_bitmaps(q);
blk_mq_unfreeze_queue(q);
}
return ret;
}
/**
* blkdev_report_zones - Get zones information
* @bdev: Target block device
* @sector: Sector from which to report zones
* @zones: Array of zone structures where to return the zones information
* @nr_zones: Number of zone structures in the zone array
* @gfp_mask: Memory allocation flags (for bio_alloc)
*
* Description:
* Get zone information starting from the zone containing @sector.
* The number of zone information reported may be less than the number
* requested by @nr_zones. The number of zones actually reported is
* returned in @nr_zones.
*/
int blkdev_report_zones(struct block_device *bdev,
sector_t sector,
struct blk_zone *zones,
unsigned int *nr_zones,
gfp_t gfp_mask)
{
struct request_queue *q = bdev_get_queue(bdev);
struct blk_zone_report_hdr *hdr;
unsigned int nrz = *nr_zones;
struct page *page;
unsigned int nr_rep;
size_t rep_bytes;
unsigned int nr_pages;
struct bio *bio;
struct bio_vec *bv;
unsigned int i, n, nz;
unsigned int ofst;
void *addr;
int ret = 0;
if (!q)
return -ENXIO;
if (!blk_queue_is_zoned(q))
return -EOPNOTSUPP;
if (!nrz)
return 0;
if (sector > bdev->bd_part->nr_sects) {
*nr_zones = 0;
return 0;
}
/*
* The zone report has a header. So make room for it in the
* payload. Also make sure that the report fits in a single BIO
* that will not be split down the stack.
*/
rep_bytes = sizeof(struct blk_zone_report_hdr) +
sizeof(struct blk_zone) * nrz;
rep_bytes = (rep_bytes + PAGE_SIZE - 1) & PAGE_MASK;
if (rep_bytes > (queue_max_sectors(q) << 9))
rep_bytes = queue_max_sectors(q) << 9;
nr_pages = min_t(unsigned int, BIO_MAX_PAGES,
rep_bytes >> PAGE_SHIFT);
nr_pages = min_t(unsigned int, nr_pages,
queue_max_segments(q));
bio = bio_alloc(gfp_mask, nr_pages);
if (!bio)
return -ENOMEM;
bio->bi_bdev = bdev;
bio->bi_iter.bi_sector = blk_zone_start(q, sector);
bio_set_op_attrs(bio, REQ_OP_ZONE_REPORT, 0);
for (i = 0; i < nr_pages; i++) {
page = alloc_page(gfp_mask);
if (!page) {
ret = -ENOMEM;
goto out;
}
if (!bio_add_page(bio, page, PAGE_SIZE, 0)) {
__free_page(page);
break;
}
}
if (i == 0)
ret = -ENOMEM;
else
ret = submit_bio_wait(bio);
if (ret)
goto out;
/*
* Process the report result: skip the header and go through the
* reported zones to fixup and fixup the zone information for
* partitions. At the same time, return the zone information into
* the zone array.
*/
n = 0;
nz = 0;
nr_rep = 0;
bio_for_each_segment_all(bv, bio, i) {
if (!bv->bv_page)
break;
addr = kmap_atomic(bv->bv_page);
/* Get header in the first page */
ofst = 0;
if (!nr_rep) {
hdr = (struct blk_zone_report_hdr *) addr;
nr_rep = hdr->nr_zones;
ofst = sizeof(struct blk_zone_report_hdr);
}
/* Fixup and report zones */
while (ofst < bv->bv_len &&
n < nr_rep && nz < nrz) {
if (blkdev_report_zone(bdev, addr + ofst, &zones[nz]))
nz++;
ofst += sizeof(struct blk_zone);
n++;
}
kunmap_atomic(addr);
if (n >= nr_rep || nz >= nrz)
break;
}
out:
bio_for_each_segment_all(bv, bio, i)
__free_page(bv->bv_page);
bio_put(bio);
if (ret == 0)
*nr_zones = nz;
return ret;
}
