linux/block/blk-zoned.c

549 lines
13 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Zoned block device handling
*
* Copyright (c) 2015, Hannes Reinecke
* Copyright (c) 2015, SUSE Linux GmbH
*
* Copyright (c) 2016, Damien Le Moal
* Copyright (c) 2016, Western Digital
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/rbtree.h>
#include <linux/blkdev.h>
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 12:08:50 +02:00
#include <linux/blk-mq.h>
#include <linux/mm.h>
#include <linux/vmalloc.h>
#include <linux/sched/mm.h>
#include "blk.h"
static inline sector_t blk_zone_start(struct request_queue *q,
sector_t sector)
{
sector_t zone_mask = blk_queue_zone_sectors(q) - 1;
return sector & ~zone_mask;
}
block: introduce zoned block devices zone write locking Components relying only on the request_queue structure for accessing block devices (e.g. I/O schedulers) have a limited knowledged of the device characteristics. In particular, the device capacity cannot be easily discovered, which for a zoned block device also result in the inability to easily know the number of zones of the device (the zone size is indicated by the chunk_sectors field of the queue limits). Introduce the nr_zones field to the request_queue structure to simplify access to this information. Also, add the bitmap seq_zone_bitmap which indicates which zones of the device are sequential zones (write preferred or write required) and the bitmap seq_zones_wlock which indicates if a zone is write locked, that is, if a write request targeting a zone was dispatched to the device. These fields are initialized by the low level block device driver (sd.c for ZBC/ZAC disks). They are not initialized by stacking drivers (device mappers) handling zoned block devices (e.g. dm-linear). Using this, I/O schedulers can introduce zone write locking to control request dispatching to a zoned block device and avoid write request reordering by limiting to at most a single write request per zone outside of the scheduler at any time. Based on previous patches from Damien Le Moal. Signed-off-by: Christoph Hellwig <hch@lst.de> [Damien] * Fixed comments and identation in blkdev.h * Changed helper functions * Fixed this commit message Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2017-12-21 07:43:38 +01:00
/*
* Return true if a request is a write requests that needs zone write locking.
*/
bool blk_req_needs_zone_write_lock(struct request *rq)
{
if (!rq->q->seq_zones_wlock)
return false;
if (blk_rq_is_passthrough(rq))
return false;
switch (req_op(rq)) {
case REQ_OP_WRITE_ZEROES:
case REQ_OP_WRITE_SAME:
case REQ_OP_WRITE:
return blk_rq_zone_is_seq(rq);
default:
return false;
}
}
EXPORT_SYMBOL_GPL(blk_req_needs_zone_write_lock);
void __blk_req_zone_write_lock(struct request *rq)
{
if (WARN_ON_ONCE(test_and_set_bit(blk_rq_zone_no(rq),
rq->q->seq_zones_wlock)))
return;
WARN_ON_ONCE(rq->rq_flags & RQF_ZONE_WRITE_LOCKED);
rq->rq_flags |= RQF_ZONE_WRITE_LOCKED;
}
EXPORT_SYMBOL_GPL(__blk_req_zone_write_lock);
void __blk_req_zone_write_unlock(struct request *rq)
{
rq->rq_flags &= ~RQF_ZONE_WRITE_LOCKED;
if (rq->q->seq_zones_wlock)
WARN_ON_ONCE(!test_and_clear_bit(blk_rq_zone_no(rq),
rq->q->seq_zones_wlock));
}
EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock);
static inline unsigned int __blkdev_nr_zones(struct request_queue *q,
sector_t nr_sectors)
{
sector_t zone_sectors = blk_queue_zone_sectors(q);
return (nr_sectors + zone_sectors - 1) >> ilog2(zone_sectors);
}
/**
* 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);
}
EXPORT_SYMBOL_GPL(blkdev_nr_zones);
/*
* Check that a zone report belongs to this partition, and if yes, fix its start
* sector and write pointer and return true. Return false otherwise.
*/
static bool blkdev_report_zone(struct block_device *bdev, struct blk_zone *rep)
{
sector_t offset = get_start_sect(bdev);
if (rep->start < offset)
return false;
rep->start -= offset;
if (rep->start + rep->len > bdev->bd_part->nr_sects)
return false;
if (rep->type == BLK_ZONE_TYPE_CONVENTIONAL)
rep->wp = rep->start + rep->len;
else
rep->wp -= offset;
return true;
}
static int blk_report_zones(struct gendisk *disk, sector_t sector,
struct blk_zone *zones, unsigned int *nr_zones)
{
struct request_queue *q = disk->queue;
unsigned int z = 0, n, nrz = *nr_zones;
sector_t capacity = get_capacity(disk);
int ret;
while (z < nrz && sector < capacity) {
n = nrz - z;
ret = disk->fops->report_zones(disk, sector, &zones[z], &n);
if (ret)
return ret;
if (!n)
break;
sector += blk_queue_zone_sectors(q) * n;
z += n;
}
WARN_ON(z > *nr_zones);
*nr_zones = z;
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
*
* 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).
*/
int blkdev_report_zones(struct block_device *bdev, sector_t sector,
struct blk_zone *zones, unsigned int *nr_zones)
{
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);
if (ret)
return ret;
for (i = 0; i < nrz; i++) {
if (!blkdev_report_zone(bdev, zones))
break;
zones++;
}
*nr_zones = i;
return 0;
}
EXPORT_SYMBOL_GPL(blkdev_report_zones);
/*
* Special case of zone reset operation to reset all zones in one command,
* useful for applications like mkfs.
*/
static int __blkdev_reset_all_zones(struct block_device *bdev, gfp_t gfp_mask)
{
struct bio *bio = bio_alloc(gfp_mask, 0);
int ret;
/* across the zones operations, don't need any sectors */
bio_set_dev(bio, bdev);
bio_set_op_attrs(bio, REQ_OP_ZONE_RESET_ALL, 0);
ret = submit_bio_wait(bio);
bio_put(bio);
return ret;
}
static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev,
sector_t nr_sectors)
{
if (!blk_queue_zone_resetall(bdev_get_queue(bdev)))
return false;
if (nr_sectors != part_nr_sects_read(bdev->bd_part))
return false;
/*
* REQ_OP_ZONE_RESET_ALL can be executed only if the block device is
* the entire disk, that is, if the blocks device start offset is 0 and
* its capacity is the same as the entire disk.
*/
return get_start_sect(bdev) == 0 &&
part_nr_sects_read(bdev->bd_part) == get_capacity(bdev->bd_disk);
}
/**
* 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;
if (blkdev_allow_reset_all_zones(bdev, nr_sectors))
return __blkdev_reset_all_zones(bdev, gfp_mask);
/* 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;
}
EXPORT_SYMBOL_GPL(blkdev_reset_zones);
/*
* 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);
treewide: kvmalloc() -> kvmalloc_array() The kvmalloc() function has a 2-factor argument form, kvmalloc_array(). This patch replaces cases of: kvmalloc(a * b, gfp) with: kvmalloc_array(a * b, gfp) as well as handling cases of: kvmalloc(a * b * c, gfp) with: kvmalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kvmalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kvmalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kvmalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kvmalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kvmalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kvmalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kvmalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kvmalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kvmalloc( - sizeof(u8) * COUNT + COUNT , ...) | kvmalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kvmalloc( - sizeof(char) * COUNT + COUNT , ...) | kvmalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kvmalloc + kvmalloc_array ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kvmalloc + kvmalloc_array ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kvmalloc + kvmalloc_array ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kvmalloc + kvmalloc_array ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kvmalloc + kvmalloc_array ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kvmalloc + kvmalloc_array ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kvmalloc + kvmalloc_array ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kvmalloc + kvmalloc_array ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kvmalloc + kvmalloc_array ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kvmalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kvmalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kvmalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kvmalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kvmalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kvmalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kvmalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kvmalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kvmalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kvmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kvmalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kvmalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kvmalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kvmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kvmalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kvmalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kvmalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kvmalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kvmalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kvmalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kvmalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kvmalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kvmalloc(C1 * C2 * C3, ...) | kvmalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kvmalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kvmalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kvmalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kvmalloc(sizeof(THING) * C2, ...) | kvmalloc(sizeof(TYPE) * C2, ...) | kvmalloc(C1 * C2 * C3, ...) | kvmalloc(C1 * C2, ...) | - kvmalloc + kvmalloc_array ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kvmalloc + kvmalloc_array ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kvmalloc + kvmalloc_array ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kvmalloc + kvmalloc_array ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kvmalloc + kvmalloc_array ( - (E1) * E2 + E1, E2 , ...) | - kvmalloc + kvmalloc_array ( - (E1) * (E2) + E1, E2 , ...) | - kvmalloc + kvmalloc_array ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-12 23:04:32 +02:00
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;
}
/*
* 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);
}
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 12:08:50 +02:00
static inline unsigned long *blk_alloc_zone_bitmap(int node,
unsigned int nr_zones)
{
return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long),
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)
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 12:08:50 +02:00
{
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;
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 12:08:50 +02:00
}
*nr_zones = nrz;
return zones;
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 12:08:50 +02:00
}
void blk_queue_free_zone_bitmaps(struct request_queue *q)
{
kfree(q->seq_zones_bitmap);
q->seq_zones_bitmap = NULL;
kfree(q->seq_zones_wlock);
q->seq_zones_wlock = NULL;
}
/**
* 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;
unsigned int noio_flag;
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 12:08:50 +02:00
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_mq(q)) {
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 12:08:50 +02:00
q->nr_zones = nr_zones;
return 0;
}
/*
* Ensure that all memory allocations in this context are done as
* if GFP_NOIO was specified.
*/
noio_flag = memalloc_noio_save();
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 12:08:50 +02:00
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(&rep_nr_zones);
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 12:08:50 +02:00
if (!zones)
goto out;
while (z < nr_zones) {
nrz = min(nr_zones - z, rep_nr_zones);
ret = blk_report_zones(disk, sector, zones, &nrz);
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 12:08:50 +02:00
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:
memalloc_noio_restore(noio_flag);
kvfree(zones);
block: Introduce blk_revalidate_disk_zones() Drivers exposing zoned block devices have to initialize and maintain correctness (i.e. revalidate) of the device zone bitmaps attached to the device request queue (seq_zones_bitmap and seq_zones_wlock). To simplify coding this, introduce a generic helper function blk_revalidate_disk_zones() suitable for most (and likely all) cases. This new function always update the seq_zones_bitmap and seq_zones_wlock bitmaps as well as the queue nr_zones field when called for a disk using a request based queue. For a disk using a BIO based queue, only the number of zones is updated since these queues do not have schedulers and so do not need the zone bitmaps. With this change, the zone bitmap initialization code in sd_zbc.c can be replaced with a call to this function in sd_zbc_read_zones(), which is called from the disk revalidate block operation method. A call to blk_revalidate_disk_zones() is also added to the null_blk driver for devices created with the zoned mode enabled. Finally, to ensure that zoned devices created with dm-linear or dm-flakey expose the correct number of zones through sysfs, a call to blk_revalidate_disk_zones() is added to dm_table_set_restrictions(). The zone bitmaps allocated and initialized with blk_revalidate_disk_zones() are freed automatically from __blk_release_queue() using the block internal function blk_queue_free_zone_bitmaps(). Reviewed-by: Hannes Reinecke <hare@suse.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-10-12 12:08:50 +02:00
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;
}
EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);