Skip to content

Commit

Permalink
Merge tag 'for-5.11/block-2020-12-14' of git://git.kernel.dk/linux-block
Browse files Browse the repository at this point in the history 
Pull block updates from Jens Axboe:
 "Another series of killing more code than what is being added, again
  thanks to Christoph's relentless cleanups and tech debt tackling.

  This contains:

   - blk-iocost improvements (Baolin Wang)

   - part0 iostat fix (Jeffle Xu)

   - Disable iopoll for split bios (Jeffle Xu)

   - block tracepoint cleanups (Christoph Hellwig)

   - Merging of struct block_device and hd_struct (Christoph Hellwig)

   - Rework/cleanup of how block device sizes are updated (Christoph
     Hellwig)

   - Simplification of gendisk lookup and removal of block device
     aliasing (Christoph Hellwig)

   - Block device ioctl cleanups (Christoph Hellwig)

   - Removal of bdget()/blkdev_get() as exported API (Christoph Hellwig)

   - Disk change rework, avoid ->revalidate_disk() (Christoph Hellwig)

   - sbitmap improvements (Pavel Begunkov)

   - Hybrid polling fix (Pavel Begunkov)

   - bvec iteration improvements (Pavel Begunkov)

   - Zone revalidation fixes (Damien Le Moal)

   - blk-throttle limit fix (Yu Kuai)

   - Various little fixes"

* tag 'for-5.11/block-2020-12-14' of git://git.kernel.dk/linux-block: (126 commits)
  blk-mq: fix msec comment from micro to milli seconds
  blk-mq: update arg in comment of blk_mq_map_queue
  blk-mq: add helper allocating tagset->tags
  Revert "block: Fix a lockdep complaint triggered by request queue flushing"
  nvme-loop: use blk_mq_hctx_set_fq_lock_class to set loop's lock class
  blk-mq: add new API of blk_mq_hctx_set_fq_lock_class
  block: disable iopoll for split bio
  block: Improve blk_revalidate_disk_zones() checks
  sbitmap: simplify wrap check
  sbitmap: replace CAS with atomic and
  sbitmap: remove swap_lock
  sbitmap: optimise sbitmap_deferred_clear()
  blk-mq: skip hybrid polling if iopoll doesn't spin
  blk-iocost: Factor out the base vrate change into a separate function
  blk-iocost: Factor out the active iocgs' state check into a separate function
  blk-iocost: Move the usage ratio calculation to the correct place
  blk-iocost: Remove unnecessary advance declaration
  blk-iocost: Fix some typos in comments
  blktrace: fix up a kerneldoc comment
  block: remove the request_queue to argument request based tracepoints
  ...
  • Loading branch information
@torvalds
torvalds committed Dec 16, 2020
2 parents 48aba79 + fa94ba8 commit ac7ac46
Show file tree
Hide file tree
Showing 110 changed files with 2,111 additions and 3,334 deletions.
10 changes: 5 additions & 5 deletions block/bio.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -608,13 +608,13 @@ void bio_truncate(struct bio *bio, unsigned new_size)
void guard_bio_eod(struct bio *bio)
{
sector_t maxsector;
struct hd_struct *part;
struct block_device *part;

rcu_read_lock();
part = __disk_get_part(bio->bi_disk, bio->bi_partno);
if (part)
maxsector = part_nr_sects_read(part);
else
maxsector = bdev_nr_sectors(part);
else
maxsector = get_capacity(bio->bi_disk);
rcu_read_unlock();

Expand Down Expand Up @@ -1212,8 +1212,8 @@ void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,

flush_dcache_page(dst_bv.bv_page);

bio_advance_iter(src, src_iter, bytes);
bio_advance_iter(dst, dst_iter, bytes);
bio_advance_iter_single(src, src_iter, bytes);
bio_advance_iter_single(dst, dst_iter, bytes);
}
}
EXPORT_SYMBOL(bio_copy_data_iter);
Expand Down
51 changes: 25 additions & 26 deletions block/blk-cgroup.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -556,22 +556,22 @@ static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg,
}

/**
* blkg_conf_prep - parse and prepare for per-blkg config update
* blkcg_conf_open_bdev - parse and open bdev for per-blkg config update
* @inputp: input string pointer
*
* Parse the device node prefix part, MAJ:MIN, of per-blkg config update
* from @input and get and return the matching gendisk. *@inputp is
* from @input and get and return the matching bdev. *@inputp is
* updated to point past the device node prefix. Returns an ERR_PTR()
* value on error.
*
* Use this function iff blkg_conf_prep() can't be used for some reason.
*/
struct gendisk *blkcg_conf_get_disk(char **inputp)
struct block_device *blkcg_conf_open_bdev(char **inputp)
{
char *input = *inputp;
unsigned int major, minor;
struct gendisk *disk;
int key_len, part;
struct block_device *bdev;
int key_len;

if (sscanf(input, "%u:%u%n", &major, &minor, &key_len) != 2)
return ERR_PTR(-EINVAL);
Expand All @@ -581,16 +581,16 @@ struct gendisk *blkcg_conf_get_disk(char **inputp)
return ERR_PTR(-EINVAL);
input = skip_spaces(input);

disk = get_gendisk(MKDEV(major, minor), &part);
if (!disk)
bdev = blkdev_get_no_open(MKDEV(major, minor));
if (!bdev)
return ERR_PTR(-ENODEV);
if (part) {
put_disk_and_module(disk);
if (bdev_is_partition(bdev)) {
blkdev_put_no_open(bdev);
return ERR_PTR(-ENODEV);
}

*inputp = input;
return disk;
return bdev;
}

/**
Expand All @@ -607,18 +607,18 @@ struct gendisk *blkcg_conf_get_disk(char **inputp)
*/
int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
char *input, struct blkg_conf_ctx *ctx)
__acquires(rcu) __acquires(&disk->queue->queue_lock)
__acquires(rcu) __acquires(&bdev->bd_disk->queue->queue_lock)
{
struct gendisk *disk;
struct block_device *bdev;
struct request_queue *q;
struct blkcg_gq *blkg;
int ret;

disk = blkcg_conf_get_disk(&input);
if (IS_ERR(disk))
return PTR_ERR(disk);
bdev = blkcg_conf_open_bdev(&input);
if (IS_ERR(bdev))
return PTR_ERR(bdev);

q = disk->queue;
q = bdev->bd_disk->queue;

rcu_read_lock();
spin_lock_irq(&q->queue_lock);
Expand Down Expand Up @@ -689,7 +689,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
goto success;
}
success:
ctx->disk = disk;
ctx->bdev = bdev;
ctx->blkg = blkg;
ctx->body = input;
return 0;
Expand All @@ -700,7 +700,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
spin_unlock_irq(&q->queue_lock);
rcu_read_unlock();
fail:
put_disk_and_module(disk);
blkdev_put_no_open(bdev);
/*
* If queue was bypassing, we should retry. Do so after a
* short msleep(). It isn't strictly necessary but queue
Expand All @@ -723,11 +723,11 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep);
* with blkg_conf_prep().
*/
void blkg_conf_finish(struct blkg_conf_ctx *ctx)
__releases(&ctx->disk->queue->queue_lock) __releases(rcu)
__releases(&ctx->bdev->bd_disk->queue->queue_lock) __releases(rcu)
{
spin_unlock_irq(&ctx->disk->queue->queue_lock);
spin_unlock_irq(&ctx->bdev->bd_disk->queue->queue_lock);
rcu_read_unlock();
put_disk_and_module(ctx->disk);
blkdev_put_no_open(ctx->bdev);
}
EXPORT_SYMBOL_GPL(blkg_conf_finish);

Expand Down Expand Up @@ -820,17 +820,17 @@ static void blkcg_fill_root_iostats(void)

class_dev_iter_init(&iter, &block_class, NULL, &disk_type);
while ((dev = class_dev_iter_next(&iter))) {
struct gendisk *disk = dev_to_disk(dev);
struct hd_struct *part = disk_get_part(disk, 0);
struct blkcg_gq *blkg = blk_queue_root_blkg(disk->queue);
struct block_device *bdev = dev_to_bdev(dev);
struct blkcg_gq *blkg =
blk_queue_root_blkg(bdev->bd_disk->queue);
struct blkg_iostat tmp;
int cpu;

memset(&tmp, 0, sizeof(tmp));
for_each_possible_cpu(cpu) {
struct disk_stats *cpu_dkstats;

cpu_dkstats = per_cpu_ptr(part->dkstats, cpu);
cpu_dkstats = per_cpu_ptr(bdev->bd_stats, cpu);
tmp.ios[BLKG_IOSTAT_READ] +=
cpu_dkstats->ios[STAT_READ];
tmp.ios[BLKG_IOSTAT_WRITE] +=
Expand All @@ -849,7 +849,6 @@ static void blkcg_fill_root_iostats(void)
blkg_iostat_set(&blkg->iostat.cur, &tmp);
u64_stats_update_end(&blkg->iostat.sync);
}
disk_put_part(part);
}
}

Expand Down
70 changes: 32 additions & 38 deletions block/blk-core.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -666,9 +666,9 @@ static int __init setup_fail_make_request(char *str)
}
__setup("fail_make_request=", setup_fail_make_request);

static bool should_fail_request(struct hd_struct *part, unsigned int bytes)
static bool should_fail_request(struct block_device *part, unsigned int bytes)
{
return part->make_it_fail && should_fail(&fail_make_request, bytes);
return part->bd_make_it_fail && should_fail(&fail_make_request, bytes);
}

static int __init fail_make_request_debugfs(void)
Expand All @@ -683,27 +683,27 @@ late_initcall(fail_make_request_debugfs);

#else /* CONFIG_FAIL_MAKE_REQUEST */

static inline bool should_fail_request(struct hd_struct *part,
static inline bool should_fail_request(struct block_device *part,
unsigned int bytes)
{
return false;
}

#endif /* CONFIG_FAIL_MAKE_REQUEST */

static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
static inline bool bio_check_ro(struct bio *bio, struct block_device *part)
{
const int op = bio_op(bio);

if (part->policy && op_is_write(op)) {
if (part->bd_read_only && op_is_write(op)) {
char b[BDEVNAME_SIZE];

if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
return false;

WARN_ONCE(1,
"Trying to write to read-only block-device %s (partno %d)\n",
bio_devname(bio, b), part->partno);
bio_devname(bio, b), part->bd_partno);
/* Older lvm-tools actually trigger this */
return false;
}
Expand All @@ -713,7 +713,7 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)

static noinline int should_fail_bio(struct bio *bio)
{
if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size))
if (should_fail_request(bio->bi_disk->part0, bio->bi_iter.bi_size))
return -EIO;
return 0;
}
Expand Down Expand Up @@ -742,7 +742,7 @@ static inline int bio_check_eod(struct bio *bio, sector_t maxsector)
*/
static inline int blk_partition_remap(struct bio *bio)
{
struct hd_struct *p;
struct block_device *p;
int ret = -EIO;

rcu_read_lock();
Expand All @@ -755,11 +755,12 @@ static inline int blk_partition_remap(struct bio *bio)
goto out;

if (bio_sectors(bio)) {
if (bio_check_eod(bio, part_nr_sects_read(p)))
if (bio_check_eod(bio, bdev_nr_sectors(p)))
goto out;
bio->bi_iter.bi_sector += p->start_sect;
trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p),
bio->bi_iter.bi_sector - p->start_sect);
bio->bi_iter.bi_sector += p->bd_start_sect;
trace_block_bio_remap(bio, p->bd_dev,
bio->bi_iter.bi_sector -
p->bd_start_sect);
}
bio->bi_partno = 0;
ret = 0;
Expand Down Expand Up @@ -829,7 +830,7 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio)
if (unlikely(blk_partition_remap(bio)))
goto end_io;
} else {
if (unlikely(bio_check_ro(bio, &bio->bi_disk->part0)))
if (unlikely(bio_check_ro(bio, bio->bi_disk->part0)))
goto end_io;
if (unlikely(bio_check_eod(bio, get_capacity(bio->bi_disk))))
goto end_io;
Expand Down Expand Up @@ -906,7 +907,7 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio)
blkcg_bio_issue_init(bio);

if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) {
trace_block_bio_queue(q, bio);
trace_block_bio_queue(bio);
/* Now that enqueuing has been traced, we need to trace
* completion as well.
*/
Expand Down Expand Up @@ -1201,7 +1202,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
return ret;

if (rq->rq_disk &&
should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq)))
should_fail_request(rq->rq_disk->part0, blk_rq_bytes(rq)))
return BLK_STS_IOERR;

if (blk_crypto_insert_cloned_request(rq))
Expand Down Expand Up @@ -1260,17 +1261,18 @@ unsigned int blk_rq_err_bytes(const struct request *rq)
}
EXPORT_SYMBOL_GPL(blk_rq_err_bytes);

static void update_io_ticks(struct hd_struct *part, unsigned long now, bool end)
static void update_io_ticks(struct block_device *part, unsigned long now,
bool end)
{
unsigned long stamp;
again:
stamp = READ_ONCE(part->stamp);
stamp = READ_ONCE(part->bd_stamp);
if (unlikely(stamp != now)) {
if (likely(cmpxchg(&part->stamp, stamp, now) == stamp))
if (likely(cmpxchg(&part->bd_stamp, stamp, now) == stamp))
__part_stat_add(part, io_ticks, end ? now - stamp : 1);
}
if (part->partno) {
part = &part_to_disk(part)->part0;
if (part->bd_partno) {
part = bdev_whole(part);
goto again;
}
}
Expand All @@ -1279,11 +1281,9 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes)
{
if (req->part && blk_do_io_stat(req)) {
const int sgrp = op_stat_group(req_op(req));
struct hd_struct *part;

part_stat_lock();
part = req->part;
part_stat_add(part, sectors[sgrp], bytes >> 9);
part_stat_add(req->part, sectors[sgrp], bytes >> 9);
part_stat_unlock();
}
}
Expand All @@ -1298,17 +1298,12 @@ void blk_account_io_done(struct request *req, u64 now)
if (req->part && blk_do_io_stat(req) &&
!(req->rq_flags & RQF_FLUSH_SEQ)) {
const int sgrp = op_stat_group(req_op(req));
struct hd_struct *part;

part_stat_lock();
part = req->part;

update_io_ticks(part, jiffies, true);
part_stat_inc(part, ios[sgrp]);
part_stat_add(part, nsecs[sgrp], now - req->start_time_ns);
update_io_ticks(req->part, jiffies, true);
part_stat_inc(req->part, ios[sgrp]);
part_stat_add(req->part, nsecs[sgrp], now - req->start_time_ns);
part_stat_unlock();

hd_struct_put(part);
}
}

Expand All @@ -1324,7 +1319,7 @@ void blk_account_io_start(struct request *rq)
part_stat_unlock();
}

static unsigned long __part_start_io_acct(struct hd_struct *part,
static unsigned long __part_start_io_acct(struct block_device *part,
unsigned int sectors, unsigned int op)
{
const int sgrp = op_stat_group(op);
Expand All @@ -1340,7 +1335,7 @@ static unsigned long __part_start_io_acct(struct hd_struct *part,
return now;
}

unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part,
unsigned long part_start_io_acct(struct gendisk *disk, struct block_device **part,
struct bio *bio)
{
*part = disk_map_sector_rcu(disk, bio->bi_iter.bi_sector);
Expand All @@ -1352,11 +1347,11 @@ EXPORT_SYMBOL_GPL(part_start_io_acct);
unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors,
unsigned int op)
{
return __part_start_io_acct(&disk->part0, sectors, op);
return __part_start_io_acct(disk->part0, sectors, op);
}
EXPORT_SYMBOL(disk_start_io_acct);

static void __part_end_io_acct(struct hd_struct *part, unsigned int op,
static void __part_end_io_acct(struct block_device *part, unsigned int op,
unsigned long start_time)
{
const int sgrp = op_stat_group(op);
Expand All @@ -1370,18 +1365,17 @@ static void __part_end_io_acct(struct hd_struct *part, unsigned int op,
part_stat_unlock();
}

void part_end_io_acct(struct hd_struct *part, struct bio *bio,
void part_end_io_acct(struct block_device *part, struct bio *bio,
unsigned long start_time)
{
__part_end_io_acct(part, bio_op(bio), start_time);
hd_struct_put(part);
}
EXPORT_SYMBOL_GPL(part_end_io_acct);

void disk_end_io_acct(struct gendisk *disk, unsigned int op,
unsigned long start_time)
{
__part_end_io_acct(&disk->part0, op, start_time);
__part_end_io_acct(disk->part0, op, start_time);
}
EXPORT_SYMBOL(disk_end_io_acct);

Expand Down
Loading

0 comments on commit ac7ac46

Please sign in to comment.