block: rework zone reporting

Avoid the need to allocate a potentially large array of struct blk_zone
in the block layer by switching the ->report_zones method interface to
a callback model. Now the caller simply supplies a callback that is
executed on each reported zone, and private data for it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Christoph Hellwig 2019-11-11 11:39:30 +09:00 committed by Jens Axboe
parent 23a50861ad
commit d41003513e
12 changed files with 346 additions and 464 deletions

View File

@ -101,44 +101,35 @@ EXPORT_SYMBOL_GPL(blkdev_nr_zones);
* 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
* @nr_zones: Maximum number of zones to report
* @cb: Callback function called for each reported zone
* @data: Private data for the callback
*
* 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.
* The caller must use memalloc_noXX_save/restore() calls to control
* memory allocations done within this function (zone array and command
* buffer allocation by the device driver).
* Get zone information starting from the zone containing @sector for at most
* @nr_zones, and call @cb for each zone reported by the device.
* To report all zones in a device starting from @sector, the BLK_ALL_ZONES
* constant can be passed to @nr_zones.
* Returns the number of zones reported by the device, or a negative errno
* value in case of failure.
*
* Note: The caller must use memalloc_noXX_save/restore() calls to control
* memory allocations done within this function.
*/
int blkdev_report_zones(struct block_device *bdev, sector_t sector,
struct blk_zone *zones, unsigned int *nr_zones)
unsigned int nr_zones, report_zones_cb cb, void *data)
{
struct request_queue *q = bdev_get_queue(bdev);
struct gendisk *disk = bdev->bd_disk;
sector_t capacity = get_capacity(disk);
if (!blk_queue_is_zoned(q))
if (!blk_queue_is_zoned(bdev_get_queue(bdev)) ||
WARN_ON_ONCE(!disk->fops->report_zones))
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(!disk->fops->report_zones))
return -EOPNOTSUPP;
if (!*nr_zones || sector >= capacity) {
*nr_zones = 0;
if (!nr_zones || sector >= capacity)
return 0;
}
*nr_zones = min(*nr_zones, __blkdev_nr_zones(q, capacity - sector));
return disk->fops->report_zones(disk, sector, zones, nr_zones);
return disk->fops->report_zones(disk, sector, nr_zones, cb, data);
}
EXPORT_SYMBOL_GPL(blkdev_report_zones);
@ -232,6 +223,20 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
}
EXPORT_SYMBOL_GPL(blkdev_zone_mgmt);
struct zone_report_args {
struct blk_zone __user *zones;
};
static int blkdev_copy_zone_to_user(struct blk_zone *zone, unsigned int idx,
void *data)
{
struct zone_report_args *args = data;
if (copy_to_user(&args->zones[idx], zone, sizeof(struct blk_zone)))
return -EFAULT;
return 0;
}
/*
* BLKREPORTZONE ioctl processing.
* Called from blkdev_ioctl.
@ -240,9 +245,9 @@ 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 zone_report_args args;
struct request_queue *q;
struct blk_zone_report rep;
struct blk_zone *zones;
int ret;
if (!argp)
@ -264,32 +269,16 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
if (!rep.nr_zones)
return -EINVAL;
rep.nr_zones = min(blkdev_nr_zones(bdev), rep.nr_zones);
args.zones = argp + sizeof(struct blk_zone_report);
ret = blkdev_report_zones(bdev, rep.sector, rep.nr_zones,
blkdev_copy_zone_to_user, &args);
if (ret < 0)
return ret;
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);
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;
rep.nr_zones = ret;
if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report)))
return -EFAULT;
return 0;
}
/*
@ -351,31 +340,6 @@ static inline unsigned long *blk_alloc_zone_bitmap(int node,
GFP_NOIO, node);
}
/*
* Allocate an array of struct blk_zone to get nr_zones zone information.
* The allocated array may be smaller than nr_zones.
*/
static struct blk_zone *blk_alloc_zones(unsigned int *nr_zones)
{
struct blk_zone *zones;
size_t nrz = min(*nr_zones, BLK_ZONED_REPORT_MAX_ZONES);
/*
* GFP_KERNEL here is meaningless as the caller task context has
* the PF_MEMALLOC_NOIO flag set in blk_revalidate_disk_zones()
* with memalloc_noio_save().
*/
zones = kvcalloc(nrz, sizeof(struct blk_zone), GFP_KERNEL);
if (!zones) {
*nr_zones = 0;
return NULL;
}
*nr_zones = nrz;
return zones;
}
void blk_queue_free_zone_bitmaps(struct request_queue *q)
{
kfree(q->seq_zones_bitmap);
@ -384,12 +348,21 @@ void blk_queue_free_zone_bitmaps(struct request_queue *q)
q->seq_zones_wlock = NULL;
}
struct blk_revalidate_zone_args {
struct gendisk *disk;
unsigned long *seq_zones_bitmap;
unsigned long *seq_zones_wlock;
sector_t sector;
};
/*
* Helper function to check the validity of zones of a zoned block device.
*/
static bool blk_zone_valid(struct gendisk *disk, struct blk_zone *zone,
sector_t *sector)
static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
void *data)
{
struct blk_revalidate_zone_args *args = data;
struct gendisk *disk = args->disk;
struct request_queue *q = disk->queue;
sector_t zone_sectors = blk_queue_zone_sectors(q);
sector_t capacity = get_capacity(disk);
@ -409,14 +382,14 @@ static bool blk_zone_valid(struct gendisk *disk, struct blk_zone *zone,
zone->len > zone_sectors) {
pr_warn("%s: Invalid zoned device with larger last zone size\n",
disk->disk_name);
return false;
return -ENODEV;
}
/* Check for holes in the zone report */
if (zone->start != *sector) {
if (zone->start != args->sector) {
pr_warn("%s: Zone gap at sectors %llu..%llu\n",
disk->disk_name, *sector, zone->start);
return false;
disk->disk_name, args->sector, zone->start);
return -ENODEV;
}
/* Check zone type */
@ -428,12 +401,38 @@ static bool blk_zone_valid(struct gendisk *disk, struct blk_zone *zone,
default:
pr_warn("%s: Invalid zone type 0x%x at sectors %llu\n",
disk->disk_name, (int)zone->type, zone->start);
return false;
return -ENODEV;
}
*sector += zone->len;
if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL)
set_bit(idx, args->seq_zones_bitmap);
return true;
args->sector += zone->len;
return 0;
}
static int blk_update_zone_info(struct gendisk *disk, unsigned int nr_zones,
struct blk_revalidate_zone_args *args)
{
/*
* Ensure that all memory allocations in this context are done as
* if GFP_NOIO was specified.
*/
unsigned int noio_flag = memalloc_noio_save();
struct request_queue *q = disk->queue;
int ret;
args->seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones);
if (!args->seq_zones_wlock)
return -ENOMEM;
args->seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones);
if (!args->seq_zones_bitmap)
return -ENOMEM;
ret = disk->fops->report_zones(disk, 0, nr_zones,
blk_revalidate_zone_cb, args);
memalloc_noio_restore(noio_flag);
return ret;
}
/**
@ -449,11 +448,7 @@ 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;
unsigned int noio_flag;
sector_t sector = 0;
struct blk_revalidate_zone_args args = { .disk = disk };
int ret = 0;
if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
@ -468,82 +463,28 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
return 0;
}
/*
* Ensure that all memory allocations in this context are done as
* if GFP_NOIO was specified.
*/
noio_flag = memalloc_noio_save();
if (nr_zones)
ret = blk_update_zone_info(disk, nr_zones, &args);
if (!nr_zones)
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 to check the zones and initialize
* seq_zones_bitmap.
*/
rep_nr_zones = nr_zones;
zones = blk_alloc_zones(&rep_nr_zones);
if (!zones)
goto out;
while (z < nr_zones) {
nrz = min(nr_zones - z, rep_nr_zones);
ret = disk->fops->report_zones(disk, sector, zones, &nrz);
if (ret)
goto out;
if (!nrz)
break;
for (i = 0; i < nrz; i++) {
if (!blk_zone_valid(disk, &zones[i], &sector)) {
ret = -ENODEV;
goto out;
}
if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL)
set_bit(z, seq_zones_bitmap);
z++;
}
}
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);
if (ret >= 0) {
q->nr_zones = nr_zones;
swap(q->seq_zones_wlock, args.seq_zones_wlock);
swap(q->seq_zones_bitmap, args.seq_zones_bitmap);
ret = 0;
} else {
pr_warn("%s: failed to revalidate zones\n", disk->disk_name);
blk_queue_free_zone_bitmaps(q);
}
blk_mq_unfreeze_queue(q);
out:
memalloc_noio_restore(noio_flag);
kvfree(zones);
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);
}
kfree(args.seq_zones_wlock);
kfree(args.seq_zones_bitmap);
return ret;
}
EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);

View File

@ -92,7 +92,7 @@ struct nullb {
int null_zone_init(struct nullb_device *dev);
void null_zone_exit(struct nullb_device *dev);
int null_report_zones(struct gendisk *disk, sector_t sector,
struct blk_zone *zones, unsigned int *nr_zones);
unsigned int nr_zones, report_zones_cb cb, void *data);
blk_status_t null_handle_zoned(struct nullb_cmd *cmd,
enum req_opf op, sector_t sector,
sector_t nr_sectors);

View File

@ -67,21 +67,34 @@ void null_zone_exit(struct nullb_device *dev)
}
int null_report_zones(struct gendisk *disk, sector_t sector,
struct blk_zone *zones, unsigned int *nr_zones)
unsigned int nr_zones, report_zones_cb cb, void *data)
{
struct nullb *nullb = disk->private_data;
struct nullb_device *dev = nullb->dev;
unsigned int zno, nrz = 0;
unsigned int first_zone, i;
struct blk_zone zone;
int error;
zno = null_zone_no(dev, sector);
if (zno < dev->nr_zones) {
nrz = min_t(unsigned int, *nr_zones, dev->nr_zones - zno);
memcpy(zones, &dev->zones[zno], nrz * sizeof(struct blk_zone));
first_zone = null_zone_no(dev, sector);
if (first_zone >= dev->nr_zones)
return 0;
nr_zones = min(nr_zones, dev->nr_zones - first_zone);
for (i = 0; i < nr_zones; i++) {
/*
* Stacked DM target drivers will remap the zone information by
* modifying the zone information passed to the report callback.
* So use a local copy to avoid corruption of the device zone
* array.
*/
memcpy(&zone, &dev->zones[first_zone + i],
sizeof(struct blk_zone));
error = cb(&zone, i, data);
if (error)
return error;
}
*nr_zones = nrz;
return 0;
return nr_zones;
}
size_t null_zone_valid_read_len(struct nullb *nullb,

View File

@ -459,21 +459,15 @@ static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev
}
#ifdef CONFIG_BLK_DEV_ZONED
static int flakey_report_zones(struct dm_target *ti, sector_t sector,
struct blk_zone *zones, unsigned int *nr_zones)
static int flakey_report_zones(struct dm_target *ti,
struct dm_report_zones_args *args, unsigned int nr_zones)
{
struct flakey_c *fc = ti->private;
int ret;
sector_t sector = flakey_map_sector(ti, args->next_sector);
/* Do report and remap it */
ret = blkdev_report_zones(fc->dev->bdev, flakey_map_sector(ti, sector),
zones, nr_zones);
if (ret != 0)
return ret;
if (*nr_zones)
dm_remap_zone_report(ti, fc->start, zones, nr_zones);
return 0;
args->start = fc->start;
return blkdev_report_zones(fc->dev->bdev, sector, nr_zones,
dm_report_zones_cb, args);
}
#endif

View File

@ -136,21 +136,15 @@ static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev
}
#ifdef CONFIG_BLK_DEV_ZONED
static int linear_report_zones(struct dm_target *ti, sector_t sector,
struct blk_zone *zones, unsigned int *nr_zones)
static int linear_report_zones(struct dm_target *ti,
struct dm_report_zones_args *args, unsigned int nr_zones)
{
struct linear_c *lc = (struct linear_c *) ti->private;
int ret;
struct linear_c *lc = ti->private;
sector_t sector = linear_map_sector(ti, args->next_sector);
/* Do report and remap it */
ret = blkdev_report_zones(lc->dev->bdev, linear_map_sector(ti, sector),
zones, nr_zones);
if (ret != 0)
return ret;
if (*nr_zones)
dm_remap_zone_report(ti, lc->start, zones, nr_zones);
return 0;
args->start = lc->start;
return blkdev_report_zones(lc->dev->bdev, sector, nr_zones,
dm_report_zones_cb, args);
}
#endif

View File

@ -1080,9 +1080,10 @@ static int dmz_load_sb(struct dmz_metadata *zmd)
/*
* Initialize a zone descriptor.
*/
static int dmz_init_zone(struct dmz_metadata *zmd, struct dm_zone *zone,
struct blk_zone *blkz)
static int dmz_init_zone(struct blk_zone *blkz, unsigned int idx, void *data)
{
struct dmz_metadata *zmd = data;
struct dm_zone *zone = &zmd->zones[idx];
struct dmz_dev *dev = zmd->dev;
/* Ignore the eventual last runt (smaller) zone */
@ -1096,26 +1097,29 @@ static int dmz_init_zone(struct dmz_metadata *zmd, struct dm_zone *zone,
atomic_set(&zone->refcount, 0);
zone->chunk = DMZ_MAP_UNMAPPED;
if (blkz->type == BLK_ZONE_TYPE_CONVENTIONAL) {
switch (blkz->type) {
case BLK_ZONE_TYPE_CONVENTIONAL:
set_bit(DMZ_RND, &zone->flags);
zmd->nr_rnd_zones++;
} else if (blkz->type == BLK_ZONE_TYPE_SEQWRITE_REQ ||
blkz->type == BLK_ZONE_TYPE_SEQWRITE_PREF) {
break;
case BLK_ZONE_TYPE_SEQWRITE_REQ:
case BLK_ZONE_TYPE_SEQWRITE_PREF:
set_bit(DMZ_SEQ, &zone->flags);
} else
break;
default:
return -ENXIO;
if (blkz->cond == BLK_ZONE_COND_OFFLINE)
set_bit(DMZ_OFFLINE, &zone->flags);
else if (blkz->cond == BLK_ZONE_COND_READONLY)
set_bit(DMZ_READ_ONLY, &zone->flags);
}
if (dmz_is_rnd(zone))
zone->wp_block = 0;
else
zone->wp_block = dmz_sect2blk(blkz->wp - blkz->start);
if (!dmz_is_offline(zone) && !dmz_is_readonly(zone)) {
if (blkz->cond == BLK_ZONE_COND_OFFLINE)
set_bit(DMZ_OFFLINE, &zone->flags);
else if (blkz->cond == BLK_ZONE_COND_READONLY)
set_bit(DMZ_READ_ONLY, &zone->flags);
else {
zmd->nr_useable_zones++;
if (dmz_is_rnd(zone)) {
zmd->nr_rnd_zones++;
@ -1138,12 +1142,6 @@ static void dmz_drop_zones(struct dmz_metadata *zmd)
zmd->zones = NULL;
}
/*
* The size of a zone report in number of zones.
* This results in 4096*64B=256KB report zones commands.
*/
#define DMZ_REPORT_NR_ZONES 4096
/*
* Allocate and initialize zone descriptors using the zone
* information from disk.
@ -1151,11 +1149,7 @@ static void dmz_drop_zones(struct dmz_metadata *zmd)
static int dmz_init_zones(struct dmz_metadata *zmd)
{
struct dmz_dev *dev = zmd->dev;
struct dm_zone *zone;
struct blk_zone *blkz;
unsigned int nr_blkz;
sector_t sector = 0;
int i, ret = 0;
int ret;
/* Init */
zmd->zone_bitmap_size = dev->zone_nr_blocks >> 3;
@ -1169,54 +1163,38 @@ static int dmz_init_zones(struct dmz_metadata *zmd)
dmz_dev_info(dev, "Using %zu B for zone information",
sizeof(struct dm_zone) * dev->nr_zones);
/* Get zone information */
nr_blkz = DMZ_REPORT_NR_ZONES;
blkz = kcalloc(nr_blkz, sizeof(struct blk_zone), GFP_KERNEL);
if (!blkz) {
ret = -ENOMEM;
goto out;
}
/*
* Get zone information and initialize zone descriptors.
* At the same time, determine where the super block
* should be: first block of the first randomly writable
* zone.
* Get zone information and initialize zone descriptors. At the same
* time, determine where the super block should be: first block of the
* first randomly writable zone.
*/
zone = zmd->zones;
while (sector < dev->capacity) {
/* Get zone information */
nr_blkz = DMZ_REPORT_NR_ZONES;
ret = blkdev_report_zones(dev->bdev, sector, blkz, &nr_blkz);
if (ret) {
dmz_dev_err(dev, "Report zones failed %d", ret);
goto out;
}
if (!nr_blkz)
break;
/* Process report */
for (i = 0; i < nr_blkz; i++) {
ret = dmz_init_zone(zmd, zone, &blkz[i]);
if (ret)
goto out;
sector += dev->zone_nr_sectors;
zone++;
}
}
/* The entire zone configuration of the disk should now be known */
if (sector < dev->capacity) {
dmz_dev_err(dev, "Failed to get correct zone information");
ret = -ENXIO;
}
out:
kfree(blkz);
if (ret)
ret = blkdev_report_zones(dev->bdev, 0, BLK_ALL_ZONES, dmz_init_zone,
zmd);
if (ret < 0) {
dmz_drop_zones(zmd);
return ret;
}
return ret;
return 0;
}
static int dmz_update_zone_cb(struct blk_zone *blkz, unsigned int idx,
void *data)
{
struct dm_zone *zone = data;
clear_bit(DMZ_OFFLINE, &zone->flags);
clear_bit(DMZ_READ_ONLY, &zone->flags);
if (blkz->cond == BLK_ZONE_COND_OFFLINE)
set_bit(DMZ_OFFLINE, &zone->flags);
else if (blkz->cond == BLK_ZONE_COND_READONLY)
set_bit(DMZ_READ_ONLY, &zone->flags);
if (dmz_is_seq(zone))
zone->wp_block = dmz_sect2blk(blkz->wp - blkz->start);
else
zone->wp_block = 0;
return 0;
}
/*
@ -1224,9 +1202,7 @@ static int dmz_init_zones(struct dmz_metadata *zmd)
*/
static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
{
unsigned int nr_blkz = 1;
unsigned int noio_flag;
struct blk_zone blkz;
int ret;
/*
@ -1236,29 +1212,18 @@ static int dmz_update_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
* GFP_NOIO was specified.
*/
noio_flag = memalloc_noio_save();
ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone),
&blkz, &nr_blkz);
ret = blkdev_report_zones(zmd->dev->bdev, dmz_start_sect(zmd, zone), 1,
dmz_update_zone_cb, zone);
memalloc_noio_restore(noio_flag);
if (!nr_blkz)
if (ret == 0)
ret = -EIO;
if (ret) {
if (ret < 0) {
dmz_dev_err(zmd->dev, "Get zone %u report failed",
dmz_id(zmd, zone));
return ret;
}
clear_bit(DMZ_OFFLINE, &zone->flags);
clear_bit(DMZ_READ_ONLY, &zone->flags);
if (blkz.cond == BLK_ZONE_COND_OFFLINE)
set_bit(DMZ_OFFLINE, &zone->flags);
else if (blkz.cond == BLK_ZONE_COND_READONLY)
set_bit(DMZ_READ_ONLY, &zone->flags);
if (dmz_is_seq(zone))
zone->wp_block = dmz_sect2blk(blkz.wp - blkz.start);
else
zone->wp_block = 0;
return 0;
}

View File

@ -440,14 +440,48 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
return dm_get_geometry(md, geo);
}
static int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
struct blk_zone *zones, unsigned int *nr_zones)
{
#ifdef CONFIG_BLK_DEV_ZONED
int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, void *data)
{
struct dm_report_zones_args *args = data;
sector_t sector_diff = args->tgt->begin - args->start;
/*
* Ignore zones beyond the target range.
*/
if (zone->start >= args->start + args->tgt->len)
return 0;
/*
* Remap the start sector and write pointer position of the zone
* to match its position in the target range.
*/
zone->start += sector_diff;
if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) {
if (zone->cond == BLK_ZONE_COND_FULL)
zone->wp = zone->start + zone->len;
else if (zone->cond == BLK_ZONE_COND_EMPTY)
zone->wp = zone->start;
else
zone->wp += sector_diff;
}
args->next_sector = zone->start + zone->len;
return args->orig_cb(zone, args->zone_idx++, args->orig_data);
}
EXPORT_SYMBOL_GPL(dm_report_zones_cb);
static int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data)
{
struct mapped_device *md = disk->private_data;
struct dm_target *tgt;
struct dm_table *map;
int srcu_idx, ret;
struct dm_report_zones_args args = {
.next_sector = sector,
.orig_data = data,
.orig_cb = cb,
};
if (dm_suspended_md(md))
return -EAGAIN;
@ -456,32 +490,30 @@ static int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
if (!map)
return -EIO;
tgt = dm_table_find_target(map, sector);
if (!tgt) {
ret = -EIO;
goto out;
}
do {
struct dm_target *tgt;
/*
* If we are executing this, we already know that the block device
* is a zoned device and so each target should have support for that
* type of drive. A missing report_zones method means that the target
* driver has a problem.
*/
if (WARN_ON(!tgt->type->report_zones)) {
ret = -EIO;
goto out;
}
tgt = dm_table_find_target(map, args.next_sector);
if (WARN_ON_ONCE(!tgt->type->report_zones)) {
ret = -EIO;
goto out;
}
ret = tgt->type->report_zones(tgt, sector, zones, nr_zones);
args.tgt = tgt;
ret = tgt->type->report_zones(tgt, &args, nr_zones);
if (ret < 0)
goto out;
} while (args.zone_idx < nr_zones &&
args.next_sector < get_capacity(disk));
ret = args.zone_idx;
out:
dm_put_live_table(md, srcu_idx);
return ret;
#else
return -ENOTSUPP;
#endif
}
#else
#define dm_blk_report_zones NULL
#endif /* CONFIG_BLK_DEV_ZONED */
static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx,
struct block_device **bdev)
@ -1207,51 +1239,6 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
}
EXPORT_SYMBOL_GPL(dm_accept_partial_bio);
/*
* The zone descriptors obtained with a zone report indicate
* zone positions within the underlying device of the target. The zone
* descriptors must be remapped to match their position within the dm device.
*/
void dm_remap_zone_report(struct dm_target *ti, sector_t start,
struct blk_zone *zones, unsigned int *nr_zones)
{
#ifdef CONFIG_BLK_DEV_ZONED
struct blk_zone *zone;
unsigned int nrz = *nr_zones;
int i;
/*
* Remap the start sector and write pointer position of the zones in
* the array. Since we may have obtained from the target underlying
* device more zones that the target size, also adjust the number
* of zones.
*/
for (i = 0; i < nrz; i++) {
zone = zones + i;
if (zone->start >= start + ti->len) {
memset(zone, 0, sizeof(struct blk_zone) * (nrz - i));
break;
}
zone->start = zone->start + ti->begin - start;
if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
continue;
if (zone->cond == BLK_ZONE_COND_FULL)
zone->wp = zone->start + zone->len;
else if (zone->cond == BLK_ZONE_COND_EMPTY)
zone->wp = zone->start;
else
zone->wp = zone->wp + ti->begin - start;
}
*nr_zones = i;
#else /* !CONFIG_BLK_DEV_ZONED */
*nr_zones = 0;
#endif
}
EXPORT_SYMBOL_GPL(dm_remap_zone_report);
static blk_qc_t __map_bio(struct dm_target_io *tio)
{
int r;

View File

@ -213,8 +213,8 @@ blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
unsigned char op, bool all);
extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
struct scsi_sense_hdr *sshdr);
extern int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
struct blk_zone *zones, unsigned int *nr_zones);
int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data);
#else /* CONFIG_BLK_DEV_ZONED */

View File

@ -19,34 +19,27 @@
#include "sd.h"
/**
* sd_zbc_parse_report - Convert a zone descriptor to a struct blk_zone,
* @sdkp: The disk the report originated from
* @buf: Address of the report zone descriptor
* @zone: the destination zone structure
*
* All LBA sized values are converted to 512B sectors unit.
*/
static void sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf,
struct blk_zone *zone)
static int sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf,
unsigned int idx, report_zones_cb cb, void *data)
{
struct scsi_device *sdp = sdkp->device;
struct blk_zone zone = { 0 };
memset(zone, 0, sizeof(struct blk_zone));
zone->type = buf[0] & 0x0f;
zone->cond = (buf[1] >> 4) & 0xf;
zone.type = buf[0] & 0x0f;
zone.cond = (buf[1] >> 4) & 0xf;
if (buf[1] & 0x01)
zone->reset = 1;
zone.reset = 1;
if (buf[1] & 0x02)
zone->non_seq = 1;
zone.non_seq = 1;
zone->len = logical_to_sectors(sdp, get_unaligned_be64(&buf[8]));
zone->start = logical_to_sectors(sdp, get_unaligned_be64(&buf[16]));
zone->wp = logical_to_sectors(sdp, get_unaligned_be64(&buf[24]));
if (zone->type != ZBC_ZONE_TYPE_CONV &&
zone->cond == ZBC_ZONE_COND_FULL)
zone->wp = zone->start + zone->len;
zone.len = logical_to_sectors(sdp, get_unaligned_be64(&buf[8]));
zone.start = logical_to_sectors(sdp, get_unaligned_be64(&buf[16]));
zone.wp = logical_to_sectors(sdp, get_unaligned_be64(&buf[24]));
if (zone.type != ZBC_ZONE_TYPE_CONV &&
zone.cond == ZBC_ZONE_COND_FULL)
zone.wp = zone.start + zone.len;
return cb(&zone, idx, data);
}
/**
@ -153,52 +146,6 @@ static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp,
return NULL;
}
/**
* sd_zbc_report_zones - Disk report zones operation.
* @disk: The target disk
* @sector: Start 512B sector of the report
* @zones: Array of zone descriptors
* @nr_zones: Number of descriptors in the array
*
* Execute a report zones command on the target disk.
*/
int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
struct blk_zone *zones, unsigned int *nr_zones)
{
struct scsi_disk *sdkp = scsi_disk(disk);
unsigned int i, nrz = *nr_zones;
unsigned char *buf;
size_t buflen = 0, offset = 0;
int ret = 0;
if (!sd_is_zoned(sdkp))
/* Not a zoned device */
return -EOPNOTSUPP;
buf = sd_zbc_alloc_report_buffer(sdkp, nrz, &buflen);
if (!buf)
return -ENOMEM;
ret = sd_zbc_do_report_zones(sdkp, buf, buflen,
sectors_to_logical(sdkp->device, sector), true);
if (ret)
goto out;
nrz = min(nrz, get_unaligned_be32(&buf[0]) / 64);
for (i = 0; i < nrz; i++) {
offset += 64;
sd_zbc_parse_report(sdkp, buf + offset, zones);
zones++;
}
*nr_zones = nrz;
out:
kvfree(buf);
return ret;
}
/**
* sd_zbc_zone_sectors - Get the device zone size in number of 512B sectors.
* @sdkp: The target disk
@ -208,6 +155,53 @@ static inline sector_t sd_zbc_zone_sectors(struct scsi_disk *sdkp)
return logical_to_sectors(sdkp->device, sdkp->zone_blocks);
}
int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data)
{
struct scsi_disk *sdkp = scsi_disk(disk);
unsigned int nr, i;
unsigned char *buf;
size_t offset, buflen = 0;
int zone_idx = 0;
int ret;
if (!sd_is_zoned(sdkp))
/* Not a zoned device */
return -EOPNOTSUPP;
buf = sd_zbc_alloc_report_buffer(sdkp, nr_zones, &buflen);
if (!buf)
return -ENOMEM;
while (zone_idx < nr_zones && sector < get_capacity(disk)) {
ret = sd_zbc_do_report_zones(sdkp, buf, buflen,
sectors_to_logical(sdkp->device, sector), true);
if (ret)
goto out;
offset = 0;
nr = min(nr_zones, get_unaligned_be32(&buf[0]) / 64);
if (!nr)
break;
for (i = 0; i < nr && zone_idx < nr_zones; i++) {
offset += 64;
ret = sd_zbc_parse_report(sdkp, buf + offset, zone_idx,
cb, data);
if (ret)
goto out;
zone_idx++;
}
sector += sd_zbc_zone_sectors(sdkp) * i;
}
ret = zone_idx;
out:
kvfree(buf);
return ret;
}
/**
* sd_zbc_setup_zone_mgmt_cmnd - Prepare a zone ZBC_OUT command. The operations
* can be RESET WRITE POINTER, OPEN, CLOSE or FINISH.

View File

@ -2857,15 +2857,21 @@ static int init_percpu_info(struct f2fs_sb_info *sbi)
}
#ifdef CONFIG_BLK_DEV_ZONED
static int f2fs_report_zone_cb(struct blk_zone *zone, unsigned int idx,
void *data)
{
struct f2fs_dev_info *dev = data;
if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL)
set_bit(idx, dev->blkz_seq);
return 0;
}
static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
{
struct block_device *bdev = FDEV(devi).bdev;
sector_t nr_sectors = bdev->bd_part->nr_sects;
sector_t sector = 0;
struct blk_zone *zones;
unsigned int i, nr_zones;
unsigned int n = 0;
int err = -EIO;
int ret;
if (!f2fs_sb_has_blkzoned(sbi))
return 0;
@ -2890,38 +2896,13 @@ static int init_blkz_info(struct f2fs_sb_info *sbi, int devi)
if (!FDEV(devi).blkz_seq)
return -ENOMEM;
#define F2FS_REPORT_NR_ZONES 4096
zones = f2fs_kzalloc(sbi,
array_size(F2FS_REPORT_NR_ZONES,
sizeof(struct blk_zone)),
GFP_KERNEL);
if (!zones)
return -ENOMEM;
/* Get block zones type */
while (zones && sector < nr_sectors) {
ret = blkdev_report_zones(bdev, 0, BLK_ALL_ZONES, f2fs_report_zone_cb,
&FDEV(devi));
if (ret < 0)
return ret;
nr_zones = F2FS_REPORT_NR_ZONES;
err = blkdev_report_zones(bdev, sector, zones, &nr_zones);
if (err)
break;
if (!nr_zones) {
err = -EIO;
break;
}
for (i = 0; i < nr_zones; i++) {
if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL)
set_bit(n, FDEV(devi).blkz_seq);
sector += zones[i].len;
n++;
}
}
kvfree(zones);
return err;
return 0;
}
#endif

View File

@ -349,17 +349,16 @@ struct queue_limits {
enum blk_zoned_model zoned;
};
typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
void *data);
#ifdef CONFIG_BLK_DEV_ZONED
/*
* Maximum number of zones to report with a single report zones command.
*/
#define BLK_ZONED_REPORT_MAX_ZONES 8192U
#define BLK_ALL_ZONES ((unsigned int)-1)
int blkdev_report_zones(struct block_device *bdev, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data);
extern unsigned int blkdev_nr_zones(struct block_device *bdev);
extern int blkdev_report_zones(struct block_device *bdev,
sector_t sector, struct blk_zone *zones,
unsigned int *nr_zones);
extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
sector_t sectors, sector_t nr_sectors,
gfp_t gfp_mask);
@ -1709,7 +1708,7 @@ struct block_device_operations {
/* this callback is with swap_lock and sometimes page table lock held */
void (*swap_slot_free_notify) (struct block_device *, unsigned long);
int (*report_zones)(struct gendisk *, sector_t sector,
struct blk_zone *zones, unsigned int *nr_zones);
unsigned int nr_zones, report_zones_cb cb, void *data);
struct module *owner;
const struct pr_ops *pr_ops;
};

View File

@ -17,6 +17,7 @@
struct dm_dev;
struct dm_target;
struct dm_table;
struct dm_report_zones_args;
struct mapped_device;
struct bio_vec;
@ -93,9 +94,9 @@ typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv,
typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **bdev);
typedef int (*dm_report_zones_fn) (struct dm_target *ti, sector_t sector,
struct blk_zone *zones,
unsigned int *nr_zones);
typedef int (*dm_report_zones_fn) (struct dm_target *ti,
struct dm_report_zones_args *args,
unsigned int nr_zones);
/*
* These iteration functions are typically used to check (and combine)
@ -422,10 +423,23 @@ struct gendisk *dm_disk(struct mapped_device *md);
int dm_suspended(struct dm_target *ti);
int dm_noflush_suspending(struct dm_target *ti);
void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors);
void dm_remap_zone_report(struct dm_target *ti, sector_t start,
struct blk_zone *zones, unsigned int *nr_zones);
union map_info *dm_get_rq_mapinfo(struct request *rq);
#ifdef CONFIG_BLK_DEV_ZONED
struct dm_report_zones_args {
struct dm_target *tgt;
sector_t next_sector;
void *orig_data;
report_zones_cb orig_cb;
unsigned int zone_idx;
/* must be filled by ->report_zones before calling dm_report_zones_cb */
sector_t start;
};
int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, void *data);
#endif /* CONFIG_BLK_DEV_ZONED */
/*
* Device mapper functions to parse and create devices specified by the
* parameter "dm-mod.create="