linux/block/blk-zoned.c

395 lines
8.7 KiB
C
Raw Normal View History

/*
* 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>
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 06:43:38 +00:00
/*
* 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);
/*
* Check that a zone report belongs to the partition.
* If yes, fix its start sector and write pointer, copy it in the
* zone information array and return true. Return false otherwise.
*/
static bool blkdev_report_zone(struct block_device *bdev,
struct blk_zone *rep,
struct blk_zone *zone)
{
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;
memcpy(zone, rep, sizeof(struct blk_zone));
return true;
}
/**
* 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;
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_set_dev(bio, 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 = 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;
}
*nr_zones = nz;
out:
bio_for_each_segment_all(bv, bio, i)
__free_page(bv->bv_page);
bio_put(bio);
return ret;
}
EXPORT_SYMBOL_GPL(blkdev_report_zones);
/**
* 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_sectors(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_set_dev(bio, 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;
}
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;
if (rep.nr_zones > INT_MAX / sizeof(struct blk_zone))
return -ERANGE;
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 21:04:32 +00:00
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,
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;
}
/*
* 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);
}