linuxmsm/laptops-kernel
0
0 Fork 0
mirror of https://github.com/linux-msm/laptops-kernel.git synced 2026-08-13 14:19:53 -07:00
Code Issues Packages Projects Releases Wiki Activity

Merge tag 'for-5.11/block-2020-12-14' of git://git.kernel.dk/linux-block

Browse Source 
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
  ...
This commit is contained in:
Linus Torvalds committed 2020-12-16 12:57:51 -08:00
2 parents 48aba79bcf fa94ba8a7b
commit ac7ac4618c
110 files changed
+2145 -3368
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

block/bio.c
+5 -5
View File
@@ -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();
@@ -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);
block/blk-cgroup.c
+25 -26
View File
@@ -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);
@@ -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;
}
/**
@@ -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);
@@ -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;
@@ -700,7 +700,7 @@ fail_unlock:
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
@@ -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);
@@ -820,9 +820,9 @@ 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;
@@ -830,7 +830,7 @@ static void blkcg_fill_root_iostats(void)
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] +=
@@ -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);
}
}
block/blk-core.c
+32 -38
View File
@@ -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)
@@ -683,7 +683,7 @@ 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;
@@ -691,11 +691,11 @@ static inline bool should_fail_request(struct hd_struct *part,
#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))
@@ -703,7 +703,7 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part)
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;
}
@@ -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;
}
@@ -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();
@@ -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;
@@ -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;
@@ -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.
*/
@@ -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))
@@ -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;
}
}
@@ -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();
}
}
@@ -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);
}
}
@@ -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);
@@ -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);
@@ -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);
@@ -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);
block/blk-flush.c
+26 -6
View File
@@ -69,7 +69,6 @@
#include <linux/blkdev.h>
#include <linux/gfp.h>
#include <linux/blk-mq.h>
#include <linux/lockdep.h>
#include "blk.h"
#include "blk-mq.h"
@@ -139,7 +138,7 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front)
static void blk_account_io_flush(struct request *rq)
{
struct hd_struct *part = &rq->rq_disk->part0;
struct block_device *part = rq->rq_disk->part0;
part_stat_lock();
part_stat_inc(part, ios[STAT_FLUSH]);
@@ -474,9 +473,6 @@ struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size,
INIT_LIST_HEAD(&fq->flush_queue[1]);
INIT_LIST_HEAD(&fq->flush_data_in_flight);
lockdep_register_key(&fq->key);
lockdep_set_class(&fq->mq_flush_lock, &fq->key);
return fq;
fail_rq:
@@ -491,7 +487,31 @@ void blk_free_flush_queue(struct blk_flush_queue *fq)
if (!fq)
return;
lockdep_unregister_key(&fq->key);
kfree(fq->flush_rq);
kfree(fq);
}
/*
* Allow driver to set its own lock class to fq->mq_flush_lock for
* avoiding lockdep complaint.
*
* flush_end_io() may be called recursively from some driver, such as
* nvme-loop, so lockdep may complain 'possible recursive locking' because
* all 'struct blk_flush_queue' instance share same mq_flush_lock lock class
* key. We need to assign different lock class for these driver's
* fq->mq_flush_lock for avoiding the lockdep warning.
*
* Use dynamically allocated lock class key for each 'blk_flush_queue'
* instance is over-kill, and more worse it introduces horrible boot delay
* issue because synchronize_rcu() is implied in lockdep_unregister_key which
* is called for each hctx release. SCSI probing may synchronously create and
* destroy lots of MQ request_queues for non-existent devices, and some robot
* test kernel always enable lockdep option. It is observed that more than half
* an hour is taken during SCSI MQ probe with per-fq lock class.
*/
void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx,
struct lock_class_key *key)
{
lockdep_set_class(&hctx->fq->mq_flush_lock, key);
}
EXPORT_SYMBOL_GPL(blk_mq_hctx_set_fq_lock_class);
block/blk-iocost.c
+178 -155
View File
@@ -39,7 +39,7 @@
* On top of that, a size cost proportional to the length of the IO is
* added. While simple, this model captures the operational
* characteristics of a wide varienty of devices well enough. Default
* paramters for several different classes of devices are provided and the
* parameters for several different classes of devices are provided and the
* parameters can be configured from userspace via
* /sys/fs/cgroup/io.cost.model.
*
@@ -77,7 +77,7 @@
*
* This constitutes the basis of IO capacity distribution. Each cgroup's
* vtime is running at a rate determined by its hweight. A cgroup tracks
* the vtime consumed by past IOs and can issue a new IO iff doing so
* the vtime consumed by past IOs and can issue a new IO if doing so
* wouldn't outrun the current device vtime. Otherwise, the IO is
* suspended until the vtime has progressed enough to cover it.
*
@@ -155,7 +155,7 @@
* Instead of debugfs or other clumsy monitoring mechanisms, this
* controller uses a drgn based monitoring script -
* tools/cgroup/iocost_monitor.py. For details on drgn, please see
* https://github.com/osandov/drgn. The ouput looks like the following.
* https://github.com/osandov/drgn. The output looks like the following.
*
* sdb RUN per=300ms cur_per=234.218:v203.695 busy= +1 vrate= 62.12%
* active weight hweight% inflt% dbt delay usages%
@@ -370,8 +370,6 @@ enum {
AUTOP_SSD_FAST,
};
struct ioc_gq;
struct ioc_params {
u32 qos[NR_QOS_PARAMS];
u64 i_lcoefs[NR_I_LCOEFS];
@@ -492,7 +490,7 @@ struct ioc_gq {
/*
* `vtime` is this iocg's vtime cursor which progresses as IOs are
* issued. If lagging behind device vtime, the delta represents
* the currently available IO budget. If runnning ahead, the
* the currently available IO budget. If running ahead, the
* overage.
*
* `vtime_done` is the same but progressed on completion rather
@@ -973,6 +971,58 @@ done:
ioc->vtime_err = clamp(ioc->vtime_err, -vperiod, vperiod);
}
static void ioc_adjust_base_vrate(struct ioc *ioc, u32 rq_wait_pct,
int nr_lagging, int nr_shortages,
int prev_busy_level, u32 *missed_ppm)
{
u64 vrate = ioc->vtime_base_rate;
u64 vrate_min = ioc->vrate_min, vrate_max = ioc->vrate_max;
if (!ioc->busy_level || (ioc->busy_level < 0 && nr_lagging)) {
if (ioc->busy_level != prev_busy_level || nr_lagging)
trace_iocost_ioc_vrate_adj(ioc, atomic64_read(&ioc->vtime_rate),
missed_ppm, rq_wait_pct,
nr_lagging, nr_shortages);
return;
}
/* rq_wait signal is always reliable, ignore user vrate_min */
if (rq_wait_pct > RQ_WAIT_BUSY_PCT)
vrate_min = VRATE_MIN;
/*
* If vrate is out of bounds, apply clamp gradually as the
* bounds can change abruptly. Otherwise, apply busy_level
* based adjustment.
*/
if (vrate < vrate_min) {
vrate = div64_u64(vrate * (100 + VRATE_CLAMP_ADJ_PCT), 100);
vrate = min(vrate, vrate_min);
} else if (vrate > vrate_max) {
vrate = div64_u64(vrate * (100 - VRATE_CLAMP_ADJ_PCT), 100);
vrate = max(vrate, vrate_max);
} else {
int idx = min_t(int, abs(ioc->busy_level),
ARRAY_SIZE(vrate_adj_pct) - 1);
u32 adj_pct = vrate_adj_pct[idx];
if (ioc->busy_level > 0)
adj_pct = 100 - adj_pct;
else
adj_pct = 100 + adj_pct;
vrate = clamp(DIV64_U64_ROUND_UP(vrate * adj_pct, 100),
vrate_min, vrate_max);
}
trace_iocost_ioc_vrate_adj(ioc, vrate, missed_ppm, rq_wait_pct,
nr_lagging, nr_shortages);
ioc->vtime_base_rate = vrate;
ioc_refresh_margins(ioc);
}
/* take a snapshot of the current [v]time and vrate */
static void ioc_now(struct ioc *ioc, struct ioc_now *now)
{
@@ -1046,7 +1096,7 @@ static void __propagate_weights(struct ioc_gq *iocg, u32 active, u32 inuse,
/*
* The delta between inuse and active sums indicates that
* that much of weight is being given away. Parent's inuse
* much of weight is being given away. Parent's inuse
* and active should reflect the ratio.
*/
if (parent->child_active_sum) {
@@ -2071,13 +2121,88 @@ static void ioc_forgive_debts(struct ioc *ioc, u64 usage_us_sum, int nr_debtors,
}
}
/*
* Check the active iocgs' state to avoid oversleeping and deactive
* idle iocgs.
*
* Since waiters determine the sleep durations based on the vrate
* they saw at the time of sleep, if vrate has increased, some
* waiters could be sleeping for too long. Wake up tardy waiters
* which should have woken up in the last period and expire idle
* iocgs.
*/
static int ioc_check_iocgs(struct ioc *ioc, struct ioc_now *now)
{
int nr_debtors = 0;
struct ioc_gq *iocg, *tiocg;
list_for_each_entry_safe(iocg, tiocg, &ioc->active_iocgs, active_list) {
if (!waitqueue_active(&iocg->waitq) && !iocg->abs_vdebt &&
!iocg->delay && !iocg_is_idle(iocg))
continue;
spin_lock(&iocg->waitq.lock);
/* flush wait and indebt stat deltas */
if (iocg->wait_since) {
iocg->local_stat.wait_us += now->now - iocg->wait_since;
iocg->wait_since = now->now;
}
if (iocg->indebt_since) {
iocg->local_stat.indebt_us +=
now->now - iocg->indebt_since;
iocg->indebt_since = now->now;
}
if (iocg->indelay_since) {
iocg->local_stat.indelay_us +=
now->now - iocg->indelay_since;
iocg->indelay_since = now->now;
}
if (waitqueue_active(&iocg->waitq) || iocg->abs_vdebt ||
iocg->delay) {
/* might be oversleeping vtime / hweight changes, kick */
iocg_kick_waitq(iocg, true, now);
if (iocg->abs_vdebt || iocg->delay)
nr_debtors++;
} else if (iocg_is_idle(iocg)) {
/* no waiter and idle, deactivate */
u64 vtime = atomic64_read(&iocg->vtime);
s64 excess;
/*
* @iocg has been inactive for a full duration and will
* have a high budget. Account anything above target as
* error and throw away. On reactivation, it'll start
* with the target budget.
*/
excess = now->vnow - vtime - ioc->margins.target;
if (excess > 0) {
u32 old_hwi;
current_hweight(iocg, NULL, &old_hwi);
ioc->vtime_err -= div64_u64(excess * old_hwi,
WEIGHT_ONE);
}
__propagate_weights(iocg, 0, 0, false, now);
list_del_init(&iocg->active_list);
}
spin_unlock(&iocg->waitq.lock);
}
commit_weights(ioc);
return nr_debtors;
}
static void ioc_timer_fn(struct timer_list *timer)
{
struct ioc *ioc = container_of(timer, struct ioc, timer);
struct ioc_gq *iocg, *tiocg;
struct ioc_now now;
LIST_HEAD(surpluses);
int nr_debtors = 0, nr_shortages = 0, nr_lagging = 0;
int nr_debtors, nr_shortages = 0, nr_lagging = 0;
u64 usage_us_sum = 0;
u32 ppm_rthr = MILLION - ioc->params.qos[QOS_RPPM];
u32 ppm_wthr = MILLION - ioc->params.qos[QOS_WPPM];
@@ -2099,68 +2224,7 @@ static void ioc_timer_fn(struct timer_list *timer)
return;
}
/*
* Waiters determine the sleep durations based on the vrate they
* saw at the time of sleep. If vrate has increased, some waiters
* could be sleeping for too long. Wake up tardy waiters which
* should have woken up in the last period and expire idle iocgs.
*/
list_for_each_entry_safe(iocg, tiocg, &ioc->active_iocgs, active_list) {
if (!waitqueue_active(&iocg->waitq) && !iocg->abs_vdebt &&
!iocg->delay && !iocg_is_idle(iocg))
continue;
spin_lock(&iocg->waitq.lock);
/* flush wait and indebt stat deltas */
if (iocg->wait_since) {
iocg->local_stat.wait_us += now.now - iocg->wait_since;
iocg->wait_since = now.now;
}
if (iocg->indebt_since) {
iocg->local_stat.indebt_us +=
now.now - iocg->indebt_since;
iocg->indebt_since = now.now;
}
if (iocg->indelay_since) {
iocg->local_stat.indelay_us +=
now.now - iocg->indelay_since;
iocg->indelay_since = now.now;
}
if (waitqueue_active(&iocg->waitq) || iocg->abs_vdebt ||
iocg->delay) {
/* might be oversleeping vtime / hweight changes, kick */
iocg_kick_waitq(iocg, true, &now);
if (iocg->abs_vdebt || iocg->delay)
nr_debtors++;
} else if (iocg_is_idle(iocg)) {
/* no waiter and idle, deactivate */
u64 vtime = atomic64_read(&iocg->vtime);
s64 excess;
/*
* @iocg has been inactive for a full duration and will
* have a high budget. Account anything above target as
* error and throw away. On reactivation, it'll start
* with the target budget.
*/
excess = now.vnow - vtime - ioc->margins.target;
if (excess > 0) {
u32 old_hwi;
current_hweight(iocg, NULL, &old_hwi);
ioc->vtime_err -= div64_u64(excess * old_hwi,
WEIGHT_ONE);
}
__propagate_weights(iocg, 0, 0, false, &now);
list_del_init(&iocg->active_list);
}
spin_unlock(&iocg->waitq.lock);
}
commit_weights(ioc);
nr_debtors = ioc_check_iocgs(ioc, &now);
/*
* Wait and indebt stat are flushed above and the donation calculation
@@ -2170,8 +2234,8 @@ static void ioc_timer_fn(struct timer_list *timer)
/* calc usage and see whether some weights need to be moved around */
list_for_each_entry(iocg, &ioc->active_iocgs, active_list) {
u64 vdone, vtime, usage_us, usage_dur;
u32 usage, hw_active, hw_inuse;
u64 vdone, vtime, usage_us;
u32 hw_active, hw_inuse;
/*
* Collect unused and wind vtime closer to vnow to prevent
@@ -2202,30 +2266,32 @@ static void ioc_timer_fn(struct timer_list *timer)
usage_us = iocg->usage_delta_us;
usage_us_sum += usage_us;
if (vdone != vtime) {
u64 inflight_us = DIV64_U64_ROUND_UP(
cost_to_abs_cost(vtime - vdone, hw_inuse),
ioc->vtime_base_rate);
usage_us = max(usage_us, inflight_us);
}
/* convert to hweight based usage ratio */
if (time_after64(iocg->activated_at, ioc->period_at))
usage_dur = max_t(u64, now.now - iocg->activated_at, 1);
else
usage_dur = max_t(u64, now.now - ioc->period_at, 1);
usage = clamp_t(u32,
DIV64_U64_ROUND_UP(usage_us * WEIGHT_ONE,
usage_dur),
1, WEIGHT_ONE);
/* see whether there's surplus vtime */
WARN_ON_ONCE(!list_empty(&iocg->surplus_list));
if (hw_inuse < hw_active ||
(!waitqueue_active(&iocg->waitq) &&
time_before64(vtime, now.vnow - ioc->margins.low))) {
u32 hwa, old_hwi, hwm, new_hwi;
u32 hwa, old_hwi, hwm, new_hwi, usage;
u64 usage_dur;
if (vdone != vtime) {
u64 inflight_us = DIV64_U64_ROUND_UP(
cost_to_abs_cost(vtime - vdone, hw_inuse),
ioc->vtime_base_rate);
usage_us = max(usage_us, inflight_us);
}
/* convert to hweight based usage ratio */
if (time_after64(iocg->activated_at, ioc->period_at))
usage_dur = max_t(u64, now.now - iocg->activated_at, 1);
else
usage_dur = max_t(u64, now.now - ioc->period_at, 1);
usage = clamp_t(u32,
DIV64_U64_ROUND_UP(usage_us * WEIGHT_ONE,
usage_dur),
1, WEIGHT_ONE);
/*
* Already donating or accumulated enough to start.
@@ -2309,51 +2375,8 @@ static void ioc_timer_fn(struct timer_list *timer)
ioc->busy_level = clamp(ioc->busy_level, -1000, 1000);
if (ioc->busy_level > 0 || (ioc->busy_level < 0 && !nr_lagging)) {
u64 vrate = ioc->vtime_base_rate;
u64 vrate_min = ioc->vrate_min, vrate_max = ioc->vrate_max;
/* rq_wait signal is always reliable, ignore user vrate_min */
if (rq_wait_pct > RQ_WAIT_BUSY_PCT)
vrate_min = VRATE_MIN;
/*
* If vrate is out of bounds, apply clamp gradually as the
* bounds can change abruptly. Otherwise, apply busy_level
* based adjustment.
*/
if (vrate < vrate_min) {
vrate = div64_u64(vrate * (100 + VRATE_CLAMP_ADJ_PCT),
100);
vrate = min(vrate, vrate_min);
} else if (vrate > vrate_max) {
vrate = div64_u64(vrate * (100 - VRATE_CLAMP_ADJ_PCT),
100);
vrate = max(vrate, vrate_max);
} else {
int idx = min_t(int, abs(ioc->busy_level),
ARRAY_SIZE(vrate_adj_pct) - 1);
u32 adj_pct = vrate_adj_pct[idx];
if (ioc->busy_level > 0)
adj_pct = 100 - adj_pct;
else
adj_pct = 100 + adj_pct;
vrate = clamp(DIV64_U64_ROUND_UP(vrate * adj_pct, 100),
vrate_min, vrate_max);
}
trace_iocost_ioc_vrate_adj(ioc, vrate, missed_ppm, rq_wait_pct,
nr_lagging, nr_shortages);
ioc->vtime_base_rate = vrate;
ioc_refresh_margins(ioc);
} else if (ioc->busy_level != prev_busy_level || nr_lagging) {
trace_iocost_ioc_vrate_adj(ioc, atomic64_read(&ioc->vtime_rate),
missed_ppm, rq_wait_pct, nr_lagging,
nr_shortages);
}
ioc_adjust_base_vrate(ioc, rq_wait_pct, nr_lagging, nr_shortages,
prev_busy_level, missed_ppm);
ioc_refresh_params(ioc, false);
@@ -2400,7 +2423,7 @@ static u64 adjust_inuse_and_calc_cost(struct ioc_gq *iocg, u64 vtime,
return cost;
/*
* We only increase inuse during period and do so iff the margin has
* We only increase inuse during period and do so if the margin has
* deteriorated since the previous adjustment.
*/
if (margin >= iocg->saved_margin || margin >= margins->low ||
@@ -3120,23 +3143,23 @@ static const match_table_t qos_tokens = {
static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
size_t nbytes, loff_t off)
{
struct gendisk *disk;
struct block_device *bdev;
struct ioc *ioc;
u32 qos[NR_QOS_PARAMS];
bool enable, user;
char *p;
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);
ioc = q_to_ioc(disk->queue);
ioc = q_to_ioc(bdev->bd_disk->queue);
if (!ioc) {
ret = blk_iocost_init(disk->queue);
ret = blk_iocost_init(bdev->bd_disk->queue);
if (ret)
goto err;
ioc = q_to_ioc(disk->queue);
ioc = q_to_ioc(bdev->bd_disk->queue);
}
spin_lock_irq(&ioc->lock);
@@ -3231,12 +3254,12 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input,
ioc_refresh_params(ioc, true);
spin_unlock_irq(&ioc->lock);
put_disk_and_module(disk);
blkdev_put_no_open(bdev);
return nbytes;
einval:
ret = -EINVAL;
err:
put_disk_and_module(disk);
blkdev_put_no_open(bdev);
return ret;
}
@@ -3287,23 +3310,23 @@ static const match_table_t i_lcoef_tokens = {
static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
size_t nbytes, loff_t off)
{
struct gendisk *disk;
struct block_device *bdev;
struct ioc *ioc;
u64 u[NR_I_LCOEFS];
bool user;
char *p;
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);
ioc = q_to_ioc(disk->queue);
ioc = q_to_ioc(bdev->bd_disk->queue);
if (!ioc) {
ret = blk_iocost_init(disk->queue);
ret = blk_iocost_init(bdev->bd_disk->queue);
if (ret)
goto err;
ioc = q_to_ioc(disk->queue);
ioc = q_to_ioc(bdev->bd_disk->queue);
}
spin_lock_irq(&ioc->lock);
@@ -3356,13 +3379,13 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input,
ioc_refresh_params(ioc, true);
spin_unlock_irq(&ioc->lock);
put_disk_and_module(disk);
blkdev_put_no_open(bdev);
return nbytes;
einval:
ret = -EINVAL;
err:
put_disk_and_module(disk);
blkdev_put_no_open(bdev);
return ret;
}
block/blk-lib.c
+1 -1
View File
@@ -65,7 +65,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
/* In case the discard request is in a partition */
if (bdev_is_partition(bdev))
part_offset = bdev->bd_part->start_sect;
part_offset = bdev->bd_start_sect;
while (nr_sects) {
sector_t granularity_aligned_lba, req_sects;
block/blk-merge.c
+12 -6
View File
@@ -279,6 +279,14 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
return NULL;
split:
*segs = nsegs;
/*
* Bio splitting may cause subtle trouble such as hang when doing sync
* iopoll in direct IO routine. Given performance gain of iopoll for
* big IO can be trival, disable iopoll when split needed.
*/
bio->bi_opf &= ~REQ_HIPRI;
return bio_split(bio, sectors, GFP_NOIO, bs);
}
@@ -338,7 +346,7 @@ void __blk_queue_split(struct bio **bio, unsigned int *nr_segs)
split->bi_opf |= REQ_NOMERGE;
bio_chain(split, *bio);
trace_block_split(q, split, (*bio)->bi_iter.bi_sector);
trace_block_split(split, (*bio)->bi_iter.bi_sector);
submit_bio_noacct(*bio);
*bio = split;
}
@@ -683,8 +691,6 @@ static void blk_account_io_merge_request(struct request *req)
part_stat_lock();
part_stat_inc(req->part, merges[op_stat_group(req_op(req))]);
part_stat_unlock();
hd_struct_put(req->part);
}
}
@@ -801,7 +807,7 @@ static struct request *attempt_merge(struct request_queue *q,
*/
blk_account_io_merge_request(next);
trace_block_rq_merge(q, next);
trace_block_rq_merge(next);
/*
* ownership of bio passed from next to req, return 'next' for
@@ -924,7 +930,7 @@ static enum bio_merge_status bio_attempt_back_merge(struct request *req,
if (!ll_back_merge_fn(req, bio, nr_segs))
return BIO_MERGE_FAILED;
trace_block_bio_backmerge(req->q, req, bio);
trace_block_bio_backmerge(bio);
rq_qos_merge(req->q, req, bio);
if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
@@ -948,7 +954,7 @@ static enum bio_merge_status bio_attempt_front_merge(struct request *req,
if (!ll_front_merge_fn(req, bio, nr_segs))
return BIO_MERGE_FAILED;
trace_block_bio_frontmerge(req->q, req, bio);
trace_block_bio_frontmerge(bio);
rq_qos_merge(req->q, req, bio);
if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
block/blk-mq-sched.c
+1 -1
View File
@@ -386,7 +386,7 @@ EXPORT_SYMBOL_GPL(blk_mq_sched_try_insert_merge);
void blk_mq_sched_request_inserted(struct request *rq)
{
trace_block_rq_insert(rq->q, rq);
trace_block_rq_insert(rq);
}
EXPORT_SYMBOL_GPL(blk_mq_sched_request_inserted);
block/blk-mq.c
+30 -16
View File
@@ -95,7 +95,7 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
}
struct mq_inflight {
struct hd_struct *part;
struct block_device *part;
unsigned int inflight[2];
};
@@ -105,13 +105,15 @@ static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
{
struct mq_inflight *mi = priv;
if (rq->part == mi->part && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)
if ((!mi->part->bd_partno || rq->part == mi->part) &&
blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)
mi->inflight[rq_data_dir(rq)]++;
return true;
}
unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part)
unsigned int blk_mq_in_flight(struct request_queue *q,
struct block_device *part)
{
struct mq_inflight mi = { .part = part };
@@ -120,8 +122,8 @@ unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part)
return mi.inflight[0] + mi.inflight[1];
}
void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
unsigned int inflight[2])
void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part,
unsigned int inflight[2])
{
struct mq_inflight mi = { .part = part };
@@ -729,7 +731,7 @@ void blk_mq_start_request(struct request *rq)
{
struct request_queue *q = rq->q;
trace_block_rq_issue(q, rq);
trace_block_rq_issue(rq);
if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
rq->io_start_time_ns = ktime_get_ns();
@@ -756,7 +758,7 @@ static void __blk_mq_requeue_request(struct request *rq)
blk_mq_put_driver_tag(rq);
trace_block_rq_requeue(q, rq);
trace_block_rq_requeue(rq);
rq_qos_requeue(q, rq);
if (blk_mq_request_started(rq)) {
@@ -1590,7 +1592,7 @@ select_cpu:
* __blk_mq_delay_run_hw_queue - Run (or schedule to run) a hardware queue.
* @hctx: Pointer to the hardware queue to run.
* @async: If we want to run the queue asynchronously.
* @msecs: Microseconds of delay to wait before running the queue.
* @msecs: Milliseconds of delay to wait before running the queue.
*
* If !@async, try to run the queue now. Else, run the queue asynchronously and
* with a delay of @msecs.
@@ -1619,7 +1621,7 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
/**
* blk_mq_delay_run_hw_queue - Run a hardware queue asynchronously.
* @hctx: Pointer to the hardware queue to run.
* @msecs: Microseconds of delay to wait before running the queue.
* @msecs: Milliseconds of delay to wait before running the queue.
*
* Run a hardware queue asynchronously with a delay of @msecs.
*/
@@ -1683,7 +1685,7 @@ EXPORT_SYMBOL(blk_mq_run_hw_queues);
/**
* blk_mq_delay_run_hw_queues - Run all hardware queues asynchronously.
* @q: Pointer to the request queue to run.
* @msecs: Microseconds of delay to wait before running the queues.
* @msecs: Milliseconds of delay to wait before running the queues.
*/
void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs)
{
@@ -1817,7 +1819,7 @@ static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
lockdep_assert_held(&ctx->lock);
trace_block_rq_insert(hctx->queue, rq);
trace_block_rq_insert(rq);
if (at_head)
list_add(&rq->queuelist, &ctx->rq_lists[type]);
@@ -1874,7 +1876,7 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
*/
list_for_each_entry(rq, list, queuelist) {
BUG_ON(rq->mq_ctx != ctx);
trace_block_rq_insert(hctx->queue, rq);
trace_block_rq_insert(rq);
}
spin_lock(&ctx->lock);
@@ -2155,6 +2157,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
unsigned int nr_segs;
blk_qc_t cookie;
blk_status_t ret;
bool hipri;
blk_queue_bounce(q, &bio);
__blk_queue_split(&bio, &nr_segs);
@@ -2171,6 +2174,8 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
rq_qos_throttle(q, bio);
hipri = bio->bi_opf & REQ_HIPRI;
data.cmd_flags = bio->bi_opf;
rq = __blk_mq_alloc_request(&data);
if (unlikely(!rq)) {
@@ -2180,7 +2185,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
goto queue_exit;
}
trace_block_getrq(q, bio, bio->bi_opf);
trace_block_getrq(bio);
rq_qos_track(q, rq, bio);
@@ -2263,6 +2268,8 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
blk_mq_sched_insert_request(rq, false, true, true);
}
if (!hipri)
return BLK_QC_T_NONE;
return cookie;
queue_exit:
blk_queue_exit(q);
@@ -3373,6 +3380,12 @@ static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set,
return 0;
}
static int blk_mq_alloc_tag_set_tags(struct blk_mq_tag_set *set,
int new_nr_hw_queues)
{
return blk_mq_realloc_tag_set_tags(set, 0, new_nr_hw_queues);
}
/*
* Alloc a tag set to be associated with one or more request queues.
* May fail with EINVAL for various error conditions. May adjust the
@@ -3426,7 +3439,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids)
set->nr_hw_queues = nr_cpu_ids;
if (blk_mq_realloc_tag_set_tags(set, 0, set->nr_hw_queues) < 0)
if (blk_mq_alloc_tag_set_tags(set, set->nr_hw_queues) < 0)
return -ENOMEM;
ret = -ENOMEM;
@@ -3861,9 +3874,10 @@ int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin)
* the state. Like for the other success return cases, the
* caller is responsible for checking if the IO completed. If
* the IO isn't complete, we'll get called again and will go
* straight to the busy poll loop.
* straight to the busy poll loop. If specified not to spin,
* we also should not sleep.
*/
if (blk_mq_poll_hybrid(q, hctx, cookie))
if (spin && blk_mq_poll_hybrid(q, hctx, cookie))
return 1;
hctx->poll_considered++;
block/blk-mq.h
+5 -4
View File
@@ -99,7 +99,7 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue_type(struct request_queue *
* blk_mq_map_queue() - map (cmd_flags,type) to hardware queue
* @q: request queue
* @flags: request command flags
* @cpu: cpu ctx
* @ctx: software queue cpu ctx
*/
static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
unsigned int flags,
@@ -182,9 +182,10 @@ static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx)
return hctx->nr_ctx && hctx->tags;
}
unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part);
void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
unsigned int inflight[2]);
unsigned int blk_mq_in_flight(struct request_queue *q,
struct block_device *part);
void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part,
unsigned int inflight[2]);
static inline void blk_mq_put_dispatch_budget(struct request_queue *q)
{
block/blk-throttle.c
+6
View File
@@ -587,6 +587,7 @@ static void throtl_pd_online(struct blkg_policy_data *pd)
tg_update_has_rules(tg);
}
#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
static void blk_throtl_update_limit_valid(struct throtl_data *td)
{
struct cgroup_subsys_state *pos_css;
@@ -607,6 +608,11 @@ static void blk_throtl_update_limit_valid(struct throtl_data *td)
td->limit_valid[LIMIT_LOW] = low_valid;
}
#else
static inline void blk_throtl_update_limit_valid(struct throtl_data *td)
{
}
#endif
static void throtl_upgrade_state(struct throtl_data *td);
static void throtl_pd_offline(struct blkg_policy_data *pd)
block/blk-wbt.c
-1
View File
@@ -835,7 +835,6 @@ int wbt_init(struct request_queue *q)
rwb->enable_state = WBT_STATE_ON_DEFAULT;
rwb->wc = 1;
rwb->rq_depth.default_depth = RWB_DEF_DEPTH;
wbt_update_limits(rwb);
/*
* Assign rwb and add the stats callback.
block/blk-zoned.c
+15 -1
View File
@@ -508,15 +508,29 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
noio_flag = memalloc_noio_save();
ret = disk->fops->report_zones(disk, 0, UINT_MAX,
blk_revalidate_zone_cb, &args);
if (!ret) {
pr_warn("%s: No zones reported\n", disk->disk_name);
ret = -ENODEV;
}
memalloc_noio_restore(noio_flag);
/*
* If zones where reported, make sure that the entire disk capacity
* has been checked.
*/
if (ret > 0 && args.sector != get_capacity(disk)) {
pr_warn("%s: Missing zones from sector %llu\n",
disk->disk_name, args.sector);
ret = -ENODEV;
}
/*
* Install the new bitmaps and update nr_zones only once the queue is
* stopped and all I/Os are completed (i.e. a scheduler is not
* referencing the bitmaps).
*/
blk_mq_freeze_queue(q);
if (ret >= 0) {
if (ret > 0) {
blk_queue_chunk_sectors(q, args.zone_sectors);
q->nr_zones = args.nr_zones;
swap(q->seq_zones_wlock, args.seq_zones_wlock);
block/blk.h
+4 -81
View File
@@ -25,7 +25,6 @@ struct blk_flush_queue {
struct list_head flush_data_in_flight;
struct request *flush_rq;
struct lock_class_key key;
spinlock_t mq_flush_lock;
};
@@ -215,7 +214,7 @@ static inline void elevator_exit(struct request_queue *q,
__elevator_exit(q, e);
}
struct hd_struct *__disk_get_part(struct gendisk *disk, int partno);
struct block_device *__disk_get_part(struct gendisk *disk, int partno);
ssize_t part_size_show(struct device *dev, struct device_attribute *attr,
char *buf);
@@ -348,97 +347,21 @@ void blk_queue_free_zone_bitmaps(struct request_queue *q);
static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {}
#endif
struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector);
struct block_device *disk_map_sector_rcu(struct gendisk *disk, sector_t sector);
int blk_alloc_devt(struct hd_struct *part, dev_t *devt);
int blk_alloc_devt(struct block_device *part, dev_t *devt);
void blk_free_devt(dev_t devt);
void blk_invalidate_devt(dev_t devt);
char *disk_name(struct gendisk *hd, int partno, char *buf);
#define ADDPART_FLAG_NONE 0
#define ADDPART_FLAG_RAID 1
#define ADDPART_FLAG_WHOLEDISK 2
void delete_partition(struct hd_struct *part);
void delete_partition(struct block_device *part);
int bdev_add_partition(struct block_device *bdev, int partno,
sector_t start, sector_t length);
int bdev_del_partition(struct block_device *bdev, int partno);
int bdev_resize_partition(struct block_device *bdev, int partno,
sector_t start, sector_t length);
int disk_expand_part_tbl(struct gendisk *disk, int target);
int hd_ref_init(struct hd_struct *part);
/* no need to get/put refcount of part0 */
static inline int hd_struct_try_get(struct hd_struct *part)
{
if (part->partno)
return percpu_ref_tryget_live(&part->ref);
return 1;
}
static inline void hd_struct_put(struct hd_struct *part)
{
if (part->partno)
percpu_ref_put(&part->ref);
}
static inline void hd_free_part(struct hd_struct *part)
{
free_percpu(part->dkstats);
kfree(part->info);
percpu_ref_exit(&part->ref);
}
/*
* Any access of part->nr_sects which is not protected by partition
* bd_mutex or gendisk bdev bd_mutex, should be done using this
* accessor function.
*
* Code written along the lines of i_size_read() and i_size_write().
* CONFIG_PREEMPTION case optimizes the case of UP kernel with preemption
* on.
*/
static inline sector_t part_nr_sects_read(struct hd_struct *part)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
sector_t nr_sects;
unsigned seq;
do {
seq = read_seqcount_begin(&part->nr_sects_seq);
nr_sects = part->nr_sects;
} while (read_seqcount_retry(&part->nr_sects_seq, seq));
return nr_sects;
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
sector_t nr_sects;
preempt_disable();
nr_sects = part->nr_sects;
preempt_enable();
return nr_sects;
#else
return part->nr_sects;
#endif
}
/*
* Should be called with mutex lock held (typically bd_mutex) of partition
* to provide mutual exlusion among writers otherwise seqcount might be
* left in wrong state leaving the readers spinning infinitely.
*/
static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
preempt_disable();
write_seqcount_begin(&part->nr_sects_seq);
part->nr_sects = size;
write_seqcount_end(&part->nr_sects_seq);
preempt_enable();
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
preempt_disable();
part->nr_sects = size;
preempt_enable();
#else
part->nr_sects = size;
#endif
}
int bio_add_hw_page(struct request_queue *q, struct bio *bio,
struct page *page, unsigned int len, unsigned int offset,
block/bounce.c
+1 -1
View File
@@ -340,7 +340,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
}
}
trace_block_bio_bounce(q, *bio_orig);
trace_block_bio_bounce(*bio_orig);
bio->bi_flags |= (1 << BIO_BOUNCED);
block/genhd.c
+172 -393
View File
File diff suppressed because it is too large. Load diff
block/ioctl.c
+12 -62
View File
@@ -35,15 +35,6 @@ static int blkpg_do_ioctl(struct block_device *bdev,
start = p.start >> SECTOR_SHIFT;
length = p.length >> SECTOR_SHIFT;
/* check for fit in a hd_struct */
if (sizeof(sector_t) < sizeof(long long)) {
long pstart = start, plength = length;
if (pstart != start || plength != length || pstart < 0 ||
plength < 0 || p.pno > 65535)
return -EINVAL;
}
switch (op) {
case BLKPG_ADD_PARTITION:
/* check if partition is aligned to blocksize */
@@ -219,23 +210,6 @@ static int compat_put_ulong(compat_ulong_t __user *argp, compat_ulong_t val)
}
#endif
int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
unsigned cmd, unsigned long arg)
{
struct gendisk *disk = bdev->bd_disk;
if (disk->fops->ioctl)
return disk->fops->ioctl(bdev, mode, cmd, arg);
return -ENOTTY;
}
/*
* For the record: _GPL here is only because somebody decided to slap it
* on the previous export. Sheer idiocy, since it wasn't copyrightable
* at all and could be open-coded without any exports by anybody who cares.
*/
EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl);
#ifdef CONFIG_COMPAT
/*
* This is the equivalent of compat_ptr_ioctl(), to be used by block
@@ -346,38 +320,11 @@ static int blkdev_pr_clear(struct block_device *bdev,
return ops->pr_clear(bdev, c.key);
}
/*
* Is it an unrecognized ioctl? The correct returns are either
* ENOTTY (final) or ENOIOCTLCMD ("I don't know this one, try a
* fallback"). ENOIOCTLCMD gets turned into ENOTTY by the ioctl
* code before returning.
*
* Confused drivers sometimes return EINVAL, which is wrong. It
* means "I understood the ioctl command, but the parameters to
* it were wrong".
*
* We should aim to just fix the broken drivers, the EINVAL case
* should go away.
*/
static inline int is_unrecognized_ioctl(int ret)
{
return ret == -EINVAL ||
ret == -ENOTTY ||
ret == -ENOIOCTLCMD;
}
static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
unsigned cmd, unsigned long arg)
{
int ret;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
if (!is_unrecognized_ioctl(ret))
return ret;
fsync_bdev(bdev);
invalidate_bdev(bdev);
return 0;
@@ -391,12 +338,14 @@ static int blkdev_roset(struct block_device *bdev, fmode_t mode,
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
if (!is_unrecognized_ioctl(ret))
return ret;
if (get_user(n, (int __user *)arg))
return -EFAULT;
set_device_ro(bdev, n);
if (bdev->bd_disk->fops->set_read_only) {
ret = bdev->bd_disk->fops->set_read_only(bdev, n);
if (ret)
return ret;
}
bdev->bd_read_only = n;
return 0;
}
@@ -619,10 +568,12 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
}
ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp);
if (ret == -ENOIOCTLCMD)
return __blkdev_driver_ioctl(bdev, mode, cmd, arg);
if (ret != -ENOIOCTLCMD)
return ret;
return ret;
if (!bdev->bd_disk->fops->ioctl)
return -ENOTTY;
return bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg);
}
EXPORT_SYMBOL_GPL(blkdev_ioctl); /* for /dev/raw */
@@ -639,8 +590,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
int ret;
void __user *argp = compat_ptr(arg);
struct inode *inode = file->f_mapping->host;
struct block_device *bdev = inode->i_bdev;
struct block_device *bdev = I_BDEV(file->f_mapping->host);
struct gendisk *disk = bdev->bd_disk;
fmode_t mode = file->f_mode;
loff_t size;
block/partitions/core.c
+80 -168
View File
@@ -85,6 +85,13 @@ static int (*check_part[])(struct parsed_partitions *) = {
NULL
};
static void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors)
{
spin_lock(&bdev->bd_size_lock);
i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT);
spin_unlock(&bdev->bd_size_lock);
}
static struct parsed_partitions *allocate_partitions(struct gendisk *hd)
{
struct parsed_partitions *state;
@@ -175,44 +182,39 @@ static struct parsed_partitions *check_partition(struct gendisk *hd,
static ssize_t part_partition_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct hd_struct *p = dev_to_part(dev);
return sprintf(buf, "%d\n", p->partno);
return sprintf(buf, "%d\n", dev_to_bdev(dev)->bd_partno);
}
static ssize_t part_start_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct hd_struct *p = dev_to_part(dev);
return sprintf(buf, "%llu\n",(unsigned long long)p->start_sect);
return sprintf(buf, "%llu\n", dev_to_bdev(dev)->bd_start_sect);
}
static ssize_t part_ro_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct hd_struct *p = dev_to_part(dev);
return sprintf(buf, "%d\n", p->policy ? 1 : 0);
return sprintf(buf, "%d\n", dev_to_bdev(dev)->bd_read_only);
}
static ssize_t part_alignment_offset_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct hd_struct *p = dev_to_part(dev);
struct block_device *bdev = dev_to_bdev(dev);
return sprintf(buf, "%u\n",
queue_limit_alignment_offset(&part_to_disk(p)->queue->limits,
p->start_sect));
queue_limit_alignment_offset(&bdev->bd_disk->queue->limits,
bdev->bd_start_sect));
}
static ssize_t part_discard_alignment_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct hd_struct *p = dev_to_part(dev);
struct block_device *bdev = dev_to_bdev(dev);
return sprintf(buf, "%u\n",
queue_limit_discard_alignment(&part_to_disk(p)->queue->limits,
p->start_sect));
queue_limit_discard_alignment(&bdev->bd_disk->queue->limits,
bdev->bd_start_sect));
}
static DEVICE_ATTR(partition, 0444, part_partition_show, NULL);
@@ -257,19 +259,17 @@ static const struct attribute_group *part_attr_groups[] = {
static void part_release(struct device *dev)
{
struct hd_struct *p = dev_to_part(dev);
blk_free_devt(dev->devt);
hd_free_part(p);
kfree(p);
bdput(dev_to_bdev(dev));
}
static int part_uevent(struct device *dev, struct kobj_uevent_env *env)
{
struct hd_struct *part = dev_to_part(dev);
struct block_device *part = dev_to_bdev(dev);
add_uevent_var(env, "PARTN=%u", part->partno);
if (part->info && part->info->volname[0])
add_uevent_var(env, "PARTNAME=%s", part->info->volname);
add_uevent_var(env, "PARTN=%u", part->bd_partno);
if (part->bd_meta_info && part->bd_meta_info->volname[0])
add_uevent_var(env, "PARTNAME=%s", part->bd_meta_info->volname);
return 0;
}
@@ -280,73 +280,29 @@ struct device_type part_type = {
.uevent = part_uevent,
};
static void hd_struct_free_work(struct work_struct *work)
{
struct hd_struct *part =
container_of(to_rcu_work(work), struct hd_struct, rcu_work);
struct gendisk *disk = part_to_disk(part);
/*
* Release the disk reference acquired in delete_partition here.
* We can't release it in hd_struct_free because the final put_device
* needs process context and thus can't be run directly from a
* percpu_ref ->release handler.
*/
put_device(disk_to_dev(disk));
part->start_sect = 0;
part->nr_sects = 0;
part_stat_set_all(part, 0);
put_device(part_to_dev(part));
}
static void hd_struct_free(struct percpu_ref *ref)
{
struct hd_struct *part = container_of(ref, struct hd_struct, ref);
struct gendisk *disk = part_to_disk(part);
struct disk_part_tbl *ptbl =
rcu_dereference_protected(disk->part_tbl, 1);
rcu_assign_pointer(ptbl->last_lookup, NULL);
INIT_RCU_WORK(&part->rcu_work, hd_struct_free_work);
queue_rcu_work(system_wq, &part->rcu_work);
}
int hd_ref_init(struct hd_struct *part)
{
if (percpu_ref_init(&part->ref, hd_struct_free, 0, GFP_KERNEL))
return -ENOMEM;
return 0;
}
/*
* Must be called either with bd_mutex held, before a disk can be opened or
* after all disk users are gone.
*/
void delete_partition(struct hd_struct *part)
void delete_partition(struct block_device *part)
{
struct gendisk *disk = part_to_disk(part);
struct gendisk *disk = part->bd_disk;
struct disk_part_tbl *ptbl =
rcu_dereference_protected(disk->part_tbl, 1);
/*
* ->part_tbl is referenced in this part's release handler, so
* we have to hold the disk device
*/
get_device(disk_to_dev(disk));
rcu_assign_pointer(ptbl->part[part->partno], NULL);
kobject_put(part->holder_dir);
device_del(part_to_dev(part));
rcu_assign_pointer(ptbl->part[part->bd_partno], NULL);
rcu_assign_pointer(ptbl->last_lookup, NULL);
kobject_put(part->bd_holder_dir);
device_del(&part->bd_device);
/*
* Remove gendisk pointer from idr so that it cannot be looked up
* while RCU period before freeing gendisk is running to prevent
* use-after-free issues. Note that the device number stays
* "in-use" until we really free the gendisk.
* Remove the block device from the inode hash, so that it cannot be
* looked up any more even when openers still hold references.
*/
blk_invalidate_devt(part_devt(part));
percpu_ref_kill(&part->ref);
remove_inode_hash(part->bd_inode);
put_device(&part->bd_device);
}
static ssize_t whole_disk_show(struct device *dev,
@@ -360,14 +316,14 @@ static DEVICE_ATTR(whole_disk, 0444, whole_disk_show, NULL);
* Must be called either with bd_mutex held, before a disk can be opened or
* after all disk users are gone.
*/
static struct hd_struct *add_partition(struct gendisk *disk, int partno,
static struct block_device *add_partition(struct gendisk *disk, int partno,
sector_t start, sector_t len, int flags,
struct partition_meta_info *info)
{
struct hd_struct *p;
dev_t devt = MKDEV(0, 0);
struct device *ddev = disk_to_dev(disk);
struct device *pdev;
struct block_device *bdev;
struct disk_part_tbl *ptbl;
const char *dname;
int err;
@@ -398,36 +354,22 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
if (ptbl->part[partno])
return ERR_PTR(-EBUSY);
p = kzalloc(sizeof(*p), GFP_KERNEL);
if (!p)
return ERR_PTR(-EBUSY);
bdev = bdev_alloc(disk, partno);
if (!bdev)
return ERR_PTR(-ENOMEM);
p->dkstats = alloc_percpu(struct disk_stats);
if (!p->dkstats) {
err = -ENOMEM;
goto out_free;
}
hd_sects_seq_init(p);
pdev = part_to_dev(p);
p->start_sect = start;
p->nr_sects = len;
p->partno = partno;
p->policy = get_disk_ro(disk);
bdev->bd_start_sect = start;
bdev_set_nr_sectors(bdev, len);
bdev->bd_read_only = get_disk_ro(disk);
if (info) {
struct partition_meta_info *pinfo;
pinfo = kzalloc_node(sizeof(*pinfo), GFP_KERNEL, disk->node_id);
if (!pinfo) {
err = -ENOMEM;
goto out_free_stats;
}
memcpy(pinfo, info, sizeof(*info));
p->info = pinfo;
err = -ENOMEM;
bdev->bd_meta_info = kmemdup(info, sizeof(*info), GFP_KERNEL);
if (!bdev->bd_meta_info)
goto out_bdput;
}
pdev = &bdev->bd_device;
dname = dev_name(ddev);
if (isdigit(dname[strlen(dname) - 1]))
dev_set_name(pdev, "%sp%d", dname, partno);
@@ -439,9 +381,9 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
pdev->type = &part_type;
pdev->parent = ddev;
err = blk_alloc_devt(p, &devt);
err = blk_alloc_devt(bdev, &devt);
if (err)
goto out_free_info;
goto out_bdput;
pdev->devt = devt;
/* delay uevent until 'holders' subdir is created */
@@ -451,8 +393,8 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
goto out_put;
err = -ENOMEM;
p->holder_dir = kobject_create_and_add("holders", &pdev->kobj);
if (!p->holder_dir)
bdev->bd_holder_dir = kobject_create_and_add("holders", &pdev->kobj);
if (!bdev->bd_holder_dir)
goto out_del;
dev_set_uevent_suppress(pdev, 0);
@@ -462,32 +404,20 @@ static struct hd_struct *add_partition(struct gendisk *disk, int partno,
goto out_del;
}
err = hd_ref_init(p);
if (err) {
if (flags & ADDPART_FLAG_WHOLEDISK)
goto out_remove_file;
goto out_del;
}
/* everything is up and running, commence */
rcu_assign_pointer(ptbl->part[partno], p);
bdev_add(bdev, devt);
rcu_assign_pointer(ptbl->part[partno], bdev);
/* suppress uevent if the disk suppresses it */
if (!dev_get_uevent_suppress(ddev))
kobject_uevent(&pdev->kobj, KOBJ_ADD);
return p;
return bdev;
out_free_info:
kfree(p->info);
out_free_stats:
free_percpu(p->dkstats);
out_free:
kfree(p);
out_bdput:
bdput(bdev);
return ERR_PTR(err);
out_remove_file:
device_remove_file(pdev, &dev_attr_whole_disk);
out_del:
kobject_put(p->holder_dir);
kobject_put(bdev->bd_holder_dir);
device_del(pdev);
out_put:
put_device(pdev);
@@ -498,14 +428,14 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start,
sector_t length, int skip_partno)
{
struct disk_part_iter piter;
struct hd_struct *part;
struct block_device *part;
bool overlap = false;
disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
while ((part = disk_part_iter_next(&piter))) {
if (part->partno == skip_partno ||
start >= part->start_sect + part->nr_sects ||
start + length <= part->start_sect)
if (part->bd_partno == skip_partno ||
start >= part->bd_start_sect + bdev_nr_sectors(part) ||
start + length <= part->bd_start_sect)
continue;
overlap = true;
break;
@@ -518,7 +448,7 @@ static bool partition_overlaps(struct gendisk *disk, sector_t start,
int bdev_add_partition(struct block_device *bdev, int partno,
sector_t start, sector_t length)
{
struct hd_struct *part;
struct block_device *part;
mutex_lock(&bdev->bd_mutex);
if (partition_overlaps(bdev->bd_disk, start, length, -1)) {
@@ -534,77 +464,59 @@ int bdev_add_partition(struct block_device *bdev, int partno,
int bdev_del_partition(struct block_device *bdev, int partno)
{
struct block_device *bdevp;
struct hd_struct *part = NULL;
struct block_device *part;
int ret;
bdevp = bdget_disk(bdev->bd_disk, partno);
if (!bdevp)
part = bdget_disk(bdev->bd_disk, partno);
if (!part)
return -ENXIO;
mutex_lock(&bdevp->bd_mutex);
mutex_lock(&part->bd_mutex);
mutex_lock_nested(&bdev->bd_mutex, 1);
ret = -ENXIO;
part = disk_get_part(bdev->bd_disk, partno);
if (!part)
goto out_unlock;
ret = -EBUSY;
if (bdevp->bd_openers)
if (part->bd_openers)
goto out_unlock;
sync_blockdev(bdevp);
invalidate_bdev(bdevp);
sync_blockdev(part);
invalidate_bdev(part);
delete_partition(part);
ret = 0;
out_unlock:
mutex_unlock(&bdev->bd_mutex);
mutex_unlock(&bdevp->bd_mutex);
bdput(bdevp);
if (part)
disk_put_part(part);
mutex_unlock(&part->bd_mutex);
bdput(part);
return ret;
}
int bdev_resize_partition(struct block_device *bdev, int partno,
sector_t start, sector_t length)
{
struct block_device *bdevp;
struct hd_struct *part;
struct block_device *part;
int ret = 0;
part = disk_get_part(bdev->bd_disk, partno);
part = bdget_disk(bdev->bd_disk, partno);
if (!part)
return -ENXIO;
ret = -ENOMEM;
bdevp = bdget_part(part);
if (!bdevp)
goto out_put_part;
mutex_lock(&bdevp->bd_mutex);
mutex_lock(&part->bd_mutex);
mutex_lock_nested(&bdev->bd_mutex, 1);
ret = -EINVAL;
if (start != part->start_sect)
if (start != part->bd_start_sect)
goto out_unlock;
ret = -EBUSY;
if (partition_overlaps(bdev->bd_disk, start, length, partno))
goto out_unlock;
part_nr_sects_write(part, length);
bd_set_nr_sectors(bdevp, length);
bdev_set_nr_sectors(part, length);
ret = 0;
out_unlock:
mutex_unlock(&bdevp->bd_mutex);
mutex_unlock(&part->bd_mutex);
mutex_unlock(&bdev->bd_mutex);
bdput(bdevp);
out_put_part:
disk_put_part(part);
bdput(part);
return ret;
}
@@ -627,7 +539,7 @@ static bool disk_unlock_native_capacity(struct gendisk *disk)
int blk_drop_partitions(struct block_device *bdev)
{
struct disk_part_iter piter;
struct hd_struct *part;
struct block_device *part;
if (bdev->bd_part_count)
return -EBUSY;
@@ -652,7 +564,7 @@ static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev,
{
sector_t size = state->parts[p].size;
sector_t from = state->parts[p].from;
struct hd_struct *part;
struct block_device *part;
if (!size)
return true;
@@ -692,7 +604,7 @@ static bool blk_add_partition(struct gendisk *disk, struct block_device *bdev,
if (IS_BUILTIN(CONFIG_BLK_DEV_MD) &&
(state->parts[p].flags & ADDPART_FLAG_RAID))
md_autodetect_dev(part_to_dev(part)->devt);
md_autodetect_dev(part->bd_dev);
return true;
}
drivers/block/amiflop.c
+56 -44
View File
@@ -201,7 +201,7 @@ struct amiga_floppy_struct {
int busy; /* true when drive is active */
int dirty; /* true when trackbuf is not on disk */
int status; /* current error code for unit */
struct gendisk *gendisk;
struct gendisk *gendisk[2];
struct blk_mq_tag_set tag_set;
};
@@ -1669,6 +1669,11 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
return -EBUSY;
}
if (unit[drive].type->code == FD_NODRIVE) {
mutex_unlock(&amiflop_mutex);
return -ENXIO;
}
if (mode & (FMODE_READ|FMODE_WRITE)) {
bdev_check_media_change(bdev);
if (mode & FMODE_WRITE) {
@@ -1695,7 +1700,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode)
unit[drive].dtype=&data_types[system];
unit[drive].blocks=unit[drive].type->heads*unit[drive].type->tracks*
data_types[system].sects*unit[drive].type->sect_mult;
set_capacity(unit[drive].gendisk, unit[drive].blocks);
set_capacity(unit[drive].gendisk[system], unit[drive].blocks);
printk(KERN_INFO "fd%d: accessing %s-disk with %s-layout\n",drive,
unit[drive].type->name, data_types[system].name);
@@ -1772,36 +1777,68 @@ static const struct blk_mq_ops amiflop_mq_ops = {
.queue_rq = amiflop_queue_rq,
};
static struct gendisk *fd_alloc_disk(int drive)
static int fd_alloc_disk(int drive, int system)
{
struct gendisk *disk;
disk = alloc_disk(1);
if (!disk)
goto out;
disk->queue = blk_mq_init_sq_queue(&unit[drive].tag_set, &amiflop_mq_ops,
2, BLK_MQ_F_SHOULD_MERGE);
if (IS_ERR(disk->queue)) {
disk->queue = NULL;
disk->queue = blk_mq_init_queue(&unit[drive].tag_set);
if (IS_ERR(disk->queue))
goto out_put_disk;
}
unit[drive].trackbuf = kmalloc(FLOPPY_MAX_SECTORS * 512, GFP_KERNEL);
if (!unit[drive].trackbuf)
goto out_cleanup_queue;
disk->major = FLOPPY_MAJOR;
disk->first_minor = drive + system;
disk->fops = &floppy_fops;
disk->events = DISK_EVENT_MEDIA_CHANGE;
if (system)
sprintf(disk->disk_name, "fd%d_msdos", drive);
else
sprintf(disk->disk_name, "fd%d", drive);
disk->private_data = &unit[drive];
set_capacity(disk, 880 * 2);
return disk;
unit[drive].gendisk[system] = disk;
add_disk(disk);
return 0;
out_cleanup_queue:
blk_cleanup_queue(disk->queue);
disk->queue = NULL;
blk_mq_free_tag_set(&unit[drive].tag_set);
out_put_disk:
disk->queue = NULL;
put_disk(disk);
out:
return -ENOMEM;
}
static int fd_alloc_drive(int drive)
{
unit[drive].trackbuf = kmalloc(FLOPPY_MAX_SECTORS * 512, GFP_KERNEL);
if (!unit[drive].trackbuf)
goto out;
memset(&unit[drive].tag_set, 0, sizeof(unit[drive].tag_set));
unit[drive].tag_set.ops = &amiflop_mq_ops;
unit[drive].tag_set.nr_hw_queues = 1;
unit[drive].tag_set.nr_maps = 1;
unit[drive].tag_set.queue_depth = 2;
unit[drive].tag_set.numa_node = NUMA_NO_NODE;
unit[drive].tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
if (blk_mq_alloc_tag_set(&unit[drive].tag_set))
goto out_cleanup_trackbuf;
pr_cont(" fd%d", drive);
if (fd_alloc_disk(drive, 0) || fd_alloc_disk(drive, 1))
goto out_cleanup_tagset;
return 0;
out_cleanup_tagset:
blk_mq_free_tag_set(&unit[drive].tag_set);
out_cleanup_trackbuf:
kfree(unit[drive].trackbuf);
out:
unit[drive].type->code = FD_NODRIVE;
return NULL;
return -ENOMEM;
}
static int __init fd_probe_drives(void)
@@ -1812,29 +1849,16 @@ static int __init fd_probe_drives(void)
drives=0;
nomem=0;
for(drive=0;drive<FD_MAX_UNITS;drive++) {
struct gendisk *disk;
fd_probe(drive);
if (unit[drive].type->code == FD_NODRIVE)
continue;
disk = fd_alloc_disk(drive);
if (!disk) {
if (fd_alloc_drive(drive) < 0) {
pr_cont(" no mem for fd%d", drive);
nomem = 1;
continue;
}
unit[drive].gendisk = disk;
drives++;
pr_cont(" fd%d",drive);
disk->major = FLOPPY_MAJOR;
disk->first_minor = drive;
disk->fops = &floppy_fops;
disk->events = DISK_EVENT_MEDIA_CHANGE;
sprintf(disk->disk_name, "fd%d", drive);
disk->private_data = &unit[drive];
set_capacity(disk, 880*2);
add_disk(disk);
}
if ((drives > 0) || (nomem == 0)) {
if (drives == 0)
@@ -1846,15 +1870,6 @@ static int __init fd_probe_drives(void)
return -ENOMEM;
}
static struct kobject *floppy_find(dev_t dev, int *part, void *data)
{
int drive = *part & 3;
if (unit[drive].type->code == FD_NODRIVE)
return NULL;
*part = 0;
return get_disk_and_module(unit[drive].gendisk);
}
static int __init amiga_floppy_probe(struct platform_device *pdev)
{
int i, ret;
@@ -1884,9 +1899,6 @@ static int __init amiga_floppy_probe(struct platform_device *pdev)
if (fd_probe_drives() < 1) /* No usable drives */
goto out_probe;
blk_register_region(MKDEV(FLOPPY_MAJOR, 0), 256, THIS_MODULE,
floppy_find, NULL, NULL);
/* initialize variables */
timer_setup(&motor_on_timer, motor_on_callback, 0);
motor_on_timer.expires = 0;
drivers/block/aoe/aoecmd.c
+4 -11
View File
@@ -890,19 +890,13 @@ void
aoecmd_sleepwork(struct work_struct *work)
{
struct aoedev *d = container_of(work, struct aoedev, work);
struct block_device *bd;
u64 ssize;
if (d->flags & DEVFL_GDALLOC)
aoeblk_gdalloc(d);
if (d->flags & DEVFL_NEWSIZE) {
ssize = get_capacity(d->gd);
bd = bdget_disk(d->gd, 0);
if (bd) {
bd_set_nr_sectors(bd, ssize);
bdput(bd);
}
set_capacity_and_notify(d->gd, d->ssize);
spin_lock_irq(&d->lock);
d->flags |= DEVFL_UP;
d->flags &= ~DEVFL_NEWSIZE;
@@ -971,10 +965,9 @@ ataid_complete(struct aoedev *d, struct aoetgt *t, unsigned char *id)
d->geo.start = 0;
if (d->flags & (DEVFL_GDALLOC|DEVFL_NEWSIZE))
return;
if (d->gd != NULL) {
set_capacity(d->gd, ssize);
if (d->gd != NULL)
d->flags |= DEVFL_NEWSIZE;
} else
else
d->flags |= DEVFL_GDALLOC;
schedule_work(&d->work);
}
Loaded 20 of 110 files, more files were not shown because too many files have changed in this diff. Show more