Something went wrong. Try again.
Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Something went wrong. Try again.
1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330// SPDX-License-Identifier: GPL-2.0/* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1994, Karl Keyte: Added support for disk statistics * Elevator latency, (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE * Queue request tables / lock, selectable elevator, Jens Axboe <axboe@suse.de> * kernel-doc documentation started by NeilBrown <neilb@cse.unsw.edu.au> * - July2000 * bio rewrite, highmem i/o, etc, Jens Axboe <axboe@suse.de> - may 2001 */
/* * This handles all read/write requests to block devices */#include <linux/kernel.h>#include <linux/module.h>#include <linux/bio.h>#include <linux/blkdev.h>#include <linux/blk-pm.h>#include <linux/blk-integrity.h>#include <linux/highmem.h>#include <linux/mm.h>#include <linux/pagemap.h>#include <linux/kernel_stat.h>#include <linux/string.h>#include <linux/init.h>#include <linux/completion.h>#include <linux/slab.h>#include <linux/swap.h>#include <linux/writeback.h>#include <linux/task_io_accounting_ops.h>#include <linux/fault-inject.h>#include <linux/list_sort.h>#include <linux/delay.h>#include <linux/ratelimit.h>#include <linux/pm_runtime.h>#include <linux/t10-pi.h>#include <linux/debugfs.h>#include <linux/bpf.h>#include <linux/part_stat.h>#include <linux/sched/sysctl.h>#include <linux/blk-crypto.h>
#define CREATE_TRACE_POINTS#include <trace/events/block.h>
#include "blk.h"#include "blk-mq-sched.h"#include "blk-pm.h"#include "blk-cgroup.h"#include "blk-throttle.h"#include "blk-ioprio.h"#include "error-injection.h"
struct dentry *blk_debugfs_root;
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);EXPORT_TRACEPOINT_SYMBOL_GPL(block_split);EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug);EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_insert);
static DEFINE_IDA(blk_queue_ida);
/* * For queue allocation */static struct kmem_cache *blk_requestq_cachep;
/* * Controlling structure to kblockd */static struct workqueue_struct *kblockd_workqueue;
/** * blk_queue_flag_set - atomically set a queue flag * @flag: flag to be set * @q: request queue */void blk_queue_flag_set(unsigned int flag, struct request_queue *q){ set_bit(flag, &q->queue_flags);}EXPORT_SYMBOL(blk_queue_flag_set);
/** * blk_queue_flag_clear - atomically clear a queue flag * @flag: flag to be cleared * @q: request queue */void blk_queue_flag_clear(unsigned int flag, struct request_queue *q){ clear_bit(flag, &q->queue_flags);}EXPORT_SYMBOL(blk_queue_flag_clear);
#define REQ_OP_NAME(name) [REQ_OP_##name] = #namestatic const char *const blk_op_name[] = { REQ_OP_NAME(READ), REQ_OP_NAME(WRITE), REQ_OP_NAME(FLUSH), REQ_OP_NAME(DISCARD), REQ_OP_NAME(SECURE_ERASE), REQ_OP_NAME(ZONE_RESET), REQ_OP_NAME(ZONE_RESET_ALL), REQ_OP_NAME(ZONE_OPEN), REQ_OP_NAME(ZONE_CLOSE), REQ_OP_NAME(ZONE_FINISH), REQ_OP_NAME(ZONE_APPEND), REQ_OP_NAME(WRITE_ZEROES), REQ_OP_NAME(DRV_IN), REQ_OP_NAME(DRV_OUT),};#undef REQ_OP_NAME
/** * blk_op_str - Return the string "name" for an operation REQ_OP_name. * @op: a request operation. * * Convert a request operation REQ_OP_name into the string "name". Useful for * debugging and tracing BIOs and requests. For an invalid request operation * code, the string "UNKNOWN" is returned. */inline const char *blk_op_str(enum req_op op){ const char *op_str = "UNKNOWN";
if (op < ARRAY_SIZE(blk_op_name) && blk_op_name[op]) op_str = blk_op_name[op];
return op_str;}EXPORT_SYMBOL_GPL(blk_op_str);
enum req_op str_to_blk_op(const char *op){ int i;
for (i = 0; i < ARRAY_SIZE(blk_op_name); i++) if (blk_op_name[i] && !strcmp(blk_op_name[i], op)) return (enum req_op)i; return REQ_OP_LAST;}
#define ENT(_tag, _errno, _desc) \[BLK_STS_##_tag] = { \ .errno = _errno, \ .tag = __stringify(_tag), \ .name = _desc, \}static const struct { int errno; const char *tag; const char *name;} blk_errors[] = { ENT(OK, 0, ""), ENT(NOTSUPP, -EOPNOTSUPP, "operation not supported"), ENT(TIMEOUT, -ETIMEDOUT, "timeout"), ENT(NOSPC, -ENOSPC, "critical space allocation"), ENT(TRANSPORT, -ENOLINK, "recoverable transport"), ENT(TARGET, -EREMOTEIO, "critical target"), ENT(RESV_CONFLICT, -EBADE, "reservation conflict"), ENT(MEDIUM, -ENODATA, "critical medium"), ENT(PROTECTION, -EILSEQ, "protection"), ENT(RESOURCE, -ENOMEM, "kernel resource"), ENT(DEV_RESOURCE, -EBUSY, "device resource"), ENT(AGAIN, -EAGAIN, "nonblocking retry"), ENT(OFFLINE, -ENODEV, "device offline"),
/* device mapper special case, should not leak out: */ ENT(DM_REQUEUE, -EREMCHG, "dm internal retry"),
/* zone device specific errors */ ENT(ZONE_OPEN_RESOURCE, -ETOOMANYREFS, "open zones exceeded"), ENT(ZONE_ACTIVE_RESOURCE, -EOVERFLOW, "active zones exceeded"),
/* Command duration limit device-side timeout */ ENT(DURATION_LIMIT, -ETIME, "duration limit exceeded"), ENT(INVAL, -EINVAL, "invalid"),
/* everything else not covered above: */ ENT(IOERR, -EIO, "I/O"),};#undef ENT
blk_status_t errno_to_blk_status(int errno){ int i;
for (i = 0; i < ARRAY_SIZE(blk_errors); i++) { if (blk_errors[i].errno == errno) return (__force blk_status_t)i; }
return BLK_STS_IOERR;}EXPORT_SYMBOL_GPL(errno_to_blk_status);
int blk_status_to_errno(blk_status_t status){ int idx = (__force int)status;
if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors))) return -EIO; return blk_errors[idx].errno;}EXPORT_SYMBOL_GPL(blk_status_to_errno);
const char *blk_status_to_str(blk_status_t status){ int idx = (__force int)status;
if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors))) return "<null>"; return blk_errors[idx].name;}
const char *blk_status_to_tag(blk_status_t status){ int idx = (__force int)status;
if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors) || !blk_errors[idx].tag)) return "<null>"; return blk_errors[idx].tag;}
blk_status_t tag_to_blk_status(const char *tag){ int i;
for (i = 0; i < ARRAY_SIZE(blk_errors); i++) { if (blk_errors[i].tag && !strcmp(blk_errors[i].tag, tag)) return (__force blk_status_t)i; }
/* * Return BLK_STS_OK for mismatches as this function is intended to * parse error status values. */ return BLK_STS_OK;}
/** * blk_sync_queue - cancel any pending callbacks on a queue * @q: the queue * * Description: * The block layer may perform asynchronous callback activity * on a queue, such as calling the unplug function after a timeout. * A block device may call blk_sync_queue to ensure that any * such activity is cancelled, thus allowing it to release resources * that the callbacks might use. The caller must already have made sure * that its ->submit_bio will not re-add plugging prior to calling * this function. * * This function does not cancel any asynchronous activity arising * out of elevator or throttling code. That would require elevator_exit() * and blkcg_exit_queue() to be called with queue lock initialized. * */void blk_sync_queue(struct request_queue *q){ timer_delete_sync(&q->timeout); cancel_work_sync(&q->timeout_work);}EXPORT_SYMBOL(blk_sync_queue);
/** * blk_set_pm_only - increment pm_only counter * @q: request queue pointer */void blk_set_pm_only(struct request_queue *q){ atomic_inc(&q->pm_only);}EXPORT_SYMBOL_GPL(blk_set_pm_only);
void blk_clear_pm_only(struct request_queue *q){ int pm_only;
pm_only = atomic_dec_return(&q->pm_only); WARN_ON_ONCE(pm_only < 0); if (pm_only == 0) wake_up_all(&q->mq_freeze_wq);}EXPORT_SYMBOL_GPL(blk_clear_pm_only);
static void blk_free_queue_rcu(struct rcu_head *rcu_head){ struct request_queue *q = container_of(rcu_head, struct request_queue, rcu_head);
percpu_ref_exit(&q->q_usage_counter); kmem_cache_free(blk_requestq_cachep, q);}
static void blk_free_queue(struct request_queue *q){ blk_free_queue_stats(q->stats); if (queue_is_mq(q)) blk_mq_release(q);
ida_free(&blk_queue_ida, q->id); lockdep_unregister_key(&q->io_lock_cls_key); lockdep_unregister_key(&q->q_lock_cls_key); call_rcu(&q->rcu_head, blk_free_queue_rcu);}
/** * blk_put_queue - decrement the request_queue refcount * @q: the request_queue structure to decrement the refcount for * * Decrements the refcount of the request_queue and free it when the refcount * reaches 0. */void blk_put_queue(struct request_queue *q){ if (refcount_dec_and_test(&q->refs)) blk_free_queue(q);}EXPORT_SYMBOL(blk_put_queue);
bool blk_queue_start_drain(struct request_queue *q){ /* * When queue DYING flag is set, we need to block new req * entering queue, so we call blk_freeze_queue_start() to * prevent I/O from crossing blk_queue_enter(). */ bool freeze = __blk_freeze_queue_start(q, current); if (queue_is_mq(q)) blk_mq_wake_waiters(q); /* Make blk_queue_enter() reexamine the DYING flag. */ wake_up_all(&q->mq_freeze_wq);
return freeze;}
/** * blk_queue_enter() - try to increase q->q_usage_counter * @q: request queue pointer * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PM */int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags){ const bool pm = flags & BLK_MQ_REQ_PM;
while (!blk_try_enter_queue(q, pm)) { if (flags & BLK_MQ_REQ_NOWAIT) return -EAGAIN;
/* * read pair of barrier in blk_freeze_queue_start(), we need to * order reading __PERCPU_REF_DEAD flag of .q_usage_counter and * reading .mq_freeze_depth or queue dying flag, otherwise the * following wait may never return if the two reads are * reordered. */ smp_rmb(); wait_event(q->mq_freeze_wq, (!q->mq_freeze_depth && blk_pm_resume_queue(pm, q)) || blk_queue_dying(q)); if (blk_queue_dying(q)) return -ENODEV; }
rwsem_acquire_read(&q->q_lockdep_map, 0, 0, _RET_IP_); rwsem_release(&q->q_lockdep_map, _RET_IP_); return 0;}
int __bio_queue_enter(struct request_queue *q, struct bio *bio){ while (!blk_try_enter_queue(q, false)) { struct gendisk *disk = bio->bi_bdev->bd_disk;
if (bio->bi_opf & REQ_NOWAIT) { if (test_bit(GD_DEAD, &disk->state)) goto dead; bio_wouldblock_error(bio); return -EAGAIN; }
/* * read pair of barrier in blk_freeze_queue_start(), we need to * order reading __PERCPU_REF_DEAD flag of .q_usage_counter and * reading .mq_freeze_depth or queue dying flag, otherwise the * following wait may never return if the two reads are * reordered. */ smp_rmb(); wait_event(q->mq_freeze_wq, (!q->mq_freeze_depth && blk_pm_resume_queue(false, q)) || test_bit(GD_DEAD, &disk->state)); if (test_bit(GD_DEAD, &disk->state)) goto dead; }
rwsem_acquire_read(&q->io_lockdep_map, 0, 0, _RET_IP_); rwsem_release(&q->io_lockdep_map, _RET_IP_); return 0;dead: bio_io_error(bio); return -ENODEV;}
void blk_queue_exit(struct request_queue *q){ percpu_ref_put(&q->q_usage_counter);}
static void blk_queue_usage_counter_release(struct percpu_ref *ref){ struct request_queue *q = container_of(ref, struct request_queue, q_usage_counter);
wake_up_all(&q->mq_freeze_wq);}
static void blk_rq_timed_out_timer(struct timer_list *t){ struct request_queue *q = timer_container_of(q, t, timeout);
kblockd_schedule_work(&q->timeout_work);}
static void blk_timeout_work(struct work_struct *work){}
struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id){ struct request_queue *q; int error;
q = kmem_cache_alloc_node(blk_requestq_cachep, GFP_KERNEL | __GFP_ZERO, node_id); if (!q) return ERR_PTR(-ENOMEM);
q->last_merge = NULL;
q->id = ida_alloc(&blk_queue_ida, GFP_KERNEL); if (q->id < 0) { error = q->id; goto fail_q; }
q->stats = blk_alloc_queue_stats(); if (!q->stats) { error = -ENOMEM; goto fail_id; }
error = blk_set_default_limits(lim); if (error) goto fail_stats; q->limits = *lim;
q->node = node_id;
atomic_set(&q->nr_active_requests_shared_tags, 0);
timer_setup(&q->timeout, blk_rq_timed_out_timer, 0); INIT_WORK(&q->timeout_work, blk_timeout_work); INIT_LIST_HEAD(&q->icq_list);
refcount_set(&q->refs, 1); mutex_init(&q->debugfs_mutex); mutex_init(&q->elevator_lock); mutex_init(&q->sysfs_lock); mutex_init(&q->limits_lock); mutex_init(&q->rq_qos_mutex); spin_lock_init(&q->queue_lock);
init_waitqueue_head(&q->mq_freeze_wq); mutex_init(&q->mq_freeze_lock);
blkg_init_queue(q);
/* * Init percpu_ref in atomic mode so that it's faster to shutdown. * See blk_register_queue() for details. */ error = percpu_ref_init(&q->q_usage_counter, blk_queue_usage_counter_release, PERCPU_REF_INIT_ATOMIC, GFP_KERNEL); if (error) goto fail_stats; lockdep_register_key(&q->io_lock_cls_key); lockdep_register_key(&q->q_lock_cls_key); lockdep_init_map(&q->io_lockdep_map, "&q->q_usage_counter(io)", &q->io_lock_cls_key, 0); lockdep_init_map(&q->q_lockdep_map, "&q->q_usage_counter(queue)", &q->q_lock_cls_key, 0);
/* Teach lockdep about lock ordering (reclaim WRT queue freeze lock). */ fs_reclaim_acquire(GFP_KERNEL); rwsem_acquire_read(&q->io_lockdep_map, 0, 0, _RET_IP_); rwsem_release(&q->io_lockdep_map, _RET_IP_); fs_reclaim_release(GFP_KERNEL);
q->nr_requests = BLKDEV_DEFAULT_RQ; q->async_depth = BLKDEV_DEFAULT_RQ;
return q;
fail_stats: blk_free_queue_stats(q->stats);fail_id: ida_free(&blk_queue_ida, q->id);fail_q: kmem_cache_free(blk_requestq_cachep, q); return ERR_PTR(error);}
/** * blk_get_queue - increment the request_queue refcount * @q: the request_queue structure to increment the refcount for * * Increment the refcount of the request_queue kobject. * * Context: Any context. */bool blk_get_queue(struct request_queue *q){ if (unlikely(blk_queue_dying(q))) return false; refcount_inc(&q->refs); return true;}EXPORT_SYMBOL(blk_get_queue);
#ifdef CONFIG_FAIL_MAKE_REQUEST
static DECLARE_FAULT_ATTR(fail_make_request);
static int __init setup_fail_make_request(char *str){ return setup_fault_attr(&fail_make_request, str);}__setup("fail_make_request=", setup_fail_make_request);
bool should_fail_request(struct block_device *part, unsigned int bytes){ return bdev_test_flag(part, BD_MAKE_IT_FAIL) && should_fail(&fail_make_request, bytes);}
static int __init fail_make_request_debugfs(void){ struct dentry *dir = fault_create_debugfs_attr("fail_make_request", NULL, &fail_make_request);
return PTR_ERR_OR_ZERO(dir);}
late_initcall(fail_make_request_debugfs);#endif /* CONFIG_FAIL_MAKE_REQUEST */
static inline void bio_check_ro(struct bio *bio){ if (op_is_write(bio_op(bio)) && bdev_read_only(bio->bi_bdev)) { if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) return;
if (bdev_test_flag(bio->bi_bdev, BD_RO_WARNED)) return;
bdev_set_flag(bio->bi_bdev, BD_RO_WARNED);
/* * Use ioctl to set underlying disk of raid/dm to read-only * will trigger this. */ pr_warn("Trying to write to read-only block-device %pg\n", bio->bi_bdev); }}
int should_fail_bio(struct bio *bio){ if (should_fail_request(bdev_whole(bio->bi_bdev), bio->bi_iter.bi_size)) return -EIO; return 0;}ALLOW_ERROR_INJECTION(should_fail_bio, ERRNO);
/* * Check whether this bio extends beyond the end of the device or partition. * This may well happen - the kernel calls bread() without checking the size of * the device, e.g., when mounting a file system. */static inline int bio_check_eod(struct bio *bio){ sector_t maxsector = bdev_nr_sectors(bio->bi_bdev); unsigned int nr_sectors = bio_sectors(bio);
if (nr_sectors && (nr_sectors > maxsector || bio->bi_iter.bi_sector > maxsector - nr_sectors)) { if (!maxsector) return -EIO; pr_info_ratelimited("%s: attempt to access beyond end of device\n" "%pg: rw=%d, sector=%llu, nr_sectors = %u limit=%llu\n", current->comm, bio->bi_bdev, bio->bi_opf, bio->bi_iter.bi_sector, nr_sectors, maxsector); return -EIO; } return 0;}
/* * Remap block n of partition p to block n+start(p) of the disk. */static int blk_partition_remap(struct bio *bio){ struct block_device *p = bio->bi_bdev;
if (unlikely(should_fail_request(p, bio->bi_iter.bi_size))) return -EIO; if (bio_sectors(bio)) { 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_set_flag(bio, BIO_REMAPPED); return 0;}
/* * Check write append to a zoned block device. */static inline blk_status_t blk_check_zone_append(struct request_queue *q, struct bio *bio){ int nr_sectors = bio_sectors(bio);
/* Only applicable to zoned block devices */ if (!bdev_is_zoned(bio->bi_bdev)) return BLK_STS_NOTSUPP;
/* The bio sector must point to the start of a sequential zone */ if (!bdev_is_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector)) return BLK_STS_IOERR;
/* * Not allowed to cross zone boundaries. Otherwise, the BIO will be * split and could result in non-contiguous sectors being written in * different zones. */ if (nr_sectors > q->limits.chunk_sectors) return BLK_STS_IOERR;
/* Make sure the BIO is small enough and will not get split */ if (nr_sectors > q->limits.max_zone_append_sectors) return BLK_STS_IOERR;
bio->bi_opf |= REQ_NOMERGE;
return BLK_STS_OK;}
static void __submit_bio(struct bio *bio){ if (!bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO)) { blk_mq_submit_bio(bio); } else if (likely(bio_queue_enter(bio) == 0)) { struct gendisk *disk = bio->bi_bdev->bd_disk; if ((bio->bi_opf & REQ_POLLED) && !(disk->queue->limits.features & BLK_FEAT_POLL)) bio_endio_status(bio, BLK_STS_NOTSUPP); else disk->fops->submit_bio(bio); blk_queue_exit(disk->queue); }}
/* * The loop in this function may be a bit non-obvious, and so deserves some * explanation: * * - Before entering the loop, bio->bi_next is NULL (as all callers ensure * that), so we have a list with a single bio. * - We pretend that we have just taken it off a longer list, so we assign * bio_list to a pointer to the bio_list_on_stack, thus initialising the * bio_list of new bios to be added. ->submit_bio() may indeed add some more * bios through a recursive call to submit_bio_noacct. If it did, we find a * non-NULL value in bio_list and re-enter the loop from the top. * - In this case we really did just take the bio off the top of the list (no * pretending) and so remove it from bio_list, and call into ->submit_bio() * again. * * bio_list_on_stack[0] contains bios submitted by the current ->submit_bio. * bio_list_on_stack[1] contains bios that were submitted before the current * ->submit_bio(), but that haven't been processed yet. */static void __submit_bio_noacct(struct bio *bio){ struct bio_list bio_list_on_stack[2];
BUG_ON(bio->bi_next);
bio_list_init(&bio_list_on_stack[0]); current->bio_list = bio_list_on_stack;
do { struct request_queue *q = bdev_get_queue(bio->bi_bdev); struct bio_list lower, same;
/* * Create a fresh bio_list for all subordinate requests. */ bio_list_on_stack[1] = bio_list_on_stack[0]; bio_list_init(&bio_list_on_stack[0]);
__submit_bio(bio);
/* * Sort new bios into those for a lower level and those for the * same level. */ bio_list_init(&lower); bio_list_init(&same); while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL) if (q == bdev_get_queue(bio->bi_bdev)) bio_list_add(&same, bio); else bio_list_add(&lower, bio);
/* * Now assemble so we handle the lowest level first. */ bio_list_merge(&bio_list_on_stack[0], &lower); bio_list_merge(&bio_list_on_stack[0], &same); bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]); } while ((bio = bio_list_pop(&bio_list_on_stack[0])));
current->bio_list = NULL;}
static void __submit_bio_noacct_mq(struct bio *bio){ struct bio_list bio_list[2] = { };
current->bio_list = bio_list;
do { __submit_bio(bio); } while ((bio = bio_list_pop(&bio_list[0])));
current->bio_list = NULL;}
void submit_bio_noacct_nocheck(struct bio *bio, bool split){ if (unlikely(blk_error_inject(bio))) return;
blk_cgroup_bio_start(bio);
if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) { trace_block_bio_queue(bio); /* * Now that enqueuing has been traced, we need to trace * completion as well. */ bio_set_flag(bio, BIO_TRACE_COMPLETION); }
/* * We only want one ->submit_bio to be active at a time, else stack * usage with stacked devices could be a problem. Use current->bio_list * to collect a list of requests submitted by a ->submit_bio method * while it is active, and then process them after it returned. */ if (current->bio_list) { if (split) bio_list_add_head(¤t->bio_list[0], bio); else bio_list_add(¤t->bio_list[0], bio); } else if (!bdev_test_flag(bio->bi_bdev, BD_HAS_SUBMIT_BIO)) { __submit_bio_noacct_mq(bio); } else { __submit_bio_noacct(bio); }}
static blk_status_t blk_validate_atomic_write_op_size(struct request_queue *q, struct bio *bio){ if (bio->bi_iter.bi_size > queue_atomic_write_unit_max_bytes(q)) return BLK_STS_INVAL;
if (bio->bi_iter.bi_size % queue_atomic_write_unit_min_bytes(q)) return BLK_STS_INVAL;
return BLK_STS_OK;}
/** * submit_bio_noacct - re-submit a bio to the block device layer for I/O * @bio: The bio describing the location in memory and on the device. * * This is a version of submit_bio() that shall only be used for I/O that is * resubmitted to lower level drivers by stacking block drivers. All file * systems and other upper level users of the block layer should use * submit_bio() instead. */void submit_bio_noacct(struct bio *bio){ struct block_device *bdev = bio->bi_bdev; struct request_queue *q = bdev_get_queue(bdev); blk_status_t status = BLK_STS_IOERR;
might_sleep();
/* * For a REQ_NOWAIT based request, return -EOPNOTSUPP * if queue does not support NOWAIT. */ if ((bio->bi_opf & REQ_NOWAIT) && !bdev_nowait(bdev)) goto not_supported;
if (bio_has_crypt_ctx(bio)) { if (WARN_ON_ONCE(!bio_has_data(bio))) goto end_io; if (!blk_crypto_supported(bio)) goto not_supported; }
if (should_fail_bio(bio)) goto end_io; bio_check_ro(bio); if (!bio_flagged(bio, BIO_REMAPPED)) { if (unlikely(bio_check_eod(bio))) goto end_io; if (bdev_is_partition(bdev) && unlikely(blk_partition_remap(bio))) goto end_io; }
/* * Filter flush bio's early so that bio based drivers without flush * support don't have to worry about them. */ if (op_is_flush(bio->bi_opf)) { if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_WRITE && bio_op(bio) != REQ_OP_ZONE_APPEND)) goto end_io; if (!bdev_write_cache(bdev)) { bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA); if (!bio_sectors(bio)) { status = BLK_STS_OK; goto end_io; } } }
switch (bio_op(bio)) { case REQ_OP_READ: break; case REQ_OP_WRITE: if (bio->bi_opf & REQ_ATOMIC) { status = blk_validate_atomic_write_op_size(q, bio); if (status != BLK_STS_OK) goto end_io; } break; case REQ_OP_FLUSH: /* * REQ_OP_FLUSH can't be submitted through bios, it is only * synthetized in struct request by the flush state machine. */ goto not_supported; case REQ_OP_DISCARD: if (!bdev_max_discard_sectors(bdev)) goto not_supported; break; case REQ_OP_SECURE_ERASE: if (!bdev_max_secure_erase_sectors(bdev)) goto not_supported; break; case REQ_OP_ZONE_APPEND: status = blk_check_zone_append(q, bio); if (status != BLK_STS_OK) goto end_io; break; case REQ_OP_WRITE_ZEROES: if (!q->limits.max_write_zeroes_sectors) goto not_supported; break; case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_OPEN: case REQ_OP_ZONE_CLOSE: case REQ_OP_ZONE_FINISH: case REQ_OP_ZONE_RESET_ALL: if (!bdev_is_zoned(bio->bi_bdev)) goto not_supported; break; case REQ_OP_DRV_IN: case REQ_OP_DRV_OUT: /* * Driver private operations are only used with passthrough * requests. */ fallthrough; default: goto not_supported; }
if (blk_throtl_bio(bio)) return; submit_bio_noacct_nocheck(bio, false); return;
not_supported: status = BLK_STS_NOTSUPP;end_io: bio_endio_status(bio, status);}EXPORT_SYMBOL(submit_bio_noacct);
static void bio_set_ioprio(struct bio *bio){ /* Nobody set ioprio so far? Initialize it based on task's nice value */ if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) == IOPRIO_CLASS_NONE) bio->bi_ioprio = get_current_ioprio(); blkcg_set_ioprio(bio);}
/** * submit_bio - submit a bio to the block device layer for I/O * @bio: The &struct bio which describes the I/O * * submit_bio() is used to submit I/O requests to block devices. It is passed a * fully set up &struct bio that describes the I/O that needs to be done. The * bio will be sent to the device described by the bi_bdev field. * * The success/failure status of the request, along with notification of * completion, is delivered asynchronously through the ->bi_end_io() callback * in @bio. The bio must NOT be touched by the caller until ->bi_end_io() has * been called. */void submit_bio(struct bio *bio){ if (bio_op(bio) == REQ_OP_READ) { task_io_account_read(bio->bi_iter.bi_size); count_vm_events(PGPGIN, bio_sectors(bio)); } else if (bio_op(bio) == REQ_OP_WRITE) { count_vm_events(PGPGOUT, bio_sectors(bio)); }
bio_set_ioprio(bio); submit_bio_noacct(bio);}EXPORT_SYMBOL(submit_bio);
/** * bio_poll - poll for BIO completions * @bio: bio to poll for * @iob: batches of IO * @flags: BLK_POLL_* flags that control the behavior * * Poll for completions on queue associated with the bio. Returns number of * completed entries found. * * Note: the caller must either be the context that submitted @bio, or * be in a RCU critical section to prevent freeing of @bio. */int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags){ blk_qc_t cookie = READ_ONCE(bio->bi_cookie); struct block_device *bdev; struct request_queue *q; int ret = 0;
bdev = READ_ONCE(bio->bi_bdev); if (!bdev) return 0;
q = bdev_get_queue(bdev); if (cookie == BLK_QC_T_NONE) return 0;
blk_flush_plug(current->plug, false);
/* * We need to be able to enter a frozen queue, similar to how * timeouts also need to do that. If that is blocked, then we can * have pending IO when a queue freeze is started, and then the * wait for the freeze to finish will wait for polled requests to * timeout as the poller is preventer from entering the queue and * completing them. As long as we prevent new IO from being queued, * that should be all that matters. */ if (!percpu_ref_tryget(&q->q_usage_counter)) return 0; if (queue_is_mq(q)) { ret = blk_mq_poll(q, cookie, iob, flags); } else { struct gendisk *disk = q->disk;
if ((q->limits.features & BLK_FEAT_POLL) && disk && disk->fops->poll_bio) ret = disk->fops->poll_bio(bio, iob, flags); } blk_queue_exit(q); return ret;}EXPORT_SYMBOL_GPL(bio_poll);
/* * Helper to implement file_operations.iopoll. Requires the bio to be stored * in iocb->private, and cleared before freeing the bio. */int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob, unsigned int flags){ struct bio *bio; int ret = 0;
/* * Note: the bio cache only uses SLAB_TYPESAFE_BY_RCU, so bio can * point to a freshly allocated bio at this point. If that happens * we have a few cases to consider: * * 1) the bio is being initialized and bi_bdev is NULL. We can just * simply nothing in this case * 2) the bio points to a not poll enabled device. bio_poll will catch * this and return 0 * 3) the bio points to a poll capable device, including but not * limited to the one that the original bio pointed to. In this * case we will call into the actual poll method and poll for I/O, * even if we don't need to, but it won't cause harm either. * * For cases 2) and 3) above the RCU grace period ensures that bi_bdev * is still allocated. Because partitions hold a reference to the whole * device bdev and thus disk, the disk is also still valid. Grabbing * a reference to the queue in bio_poll() ensures the hctxs and requests * are still valid as well. */ rcu_read_lock(); bio = READ_ONCE(kiocb->private); if (bio) ret = bio_poll(bio, iob, flags); rcu_read_unlock();
return ret;}EXPORT_SYMBOL_GPL(iocb_bio_iopoll);
void update_io_ticks(struct block_device *part, unsigned long now, bool end){ unsigned long stamp;again: stamp = READ_ONCE(part->bd_stamp); if (unlikely(time_after(now, stamp)) && likely(try_cmpxchg(&part->bd_stamp, &stamp, now)) && (end || bdev_count_inflight(part))) __part_stat_add(part, io_ticks, now - stamp);
if (bdev_is_partition(part)) { part = bdev_whole(part); goto again; }}
unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op, unsigned long start_time){ part_stat_lock(); update_io_ticks(bdev, start_time, false); bdev_inc_in_flight(bdev, op); part_stat_unlock();
return start_time;}EXPORT_SYMBOL(bdev_start_io_acct);
/** * bio_start_io_acct - start I/O accounting for bio based drivers * @bio: bio to start account for * * Returns the start time that should be passed back to bio_end_io_acct(). */unsigned long bio_start_io_acct(struct bio *bio){ return bdev_start_io_acct(bio->bi_bdev, bio_op(bio), jiffies);}EXPORT_SYMBOL_GPL(bio_start_io_acct);
void bdev_end_io_acct(struct block_device *bdev, enum req_op op, unsigned int sectors, unsigned long start_time){ const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); unsigned long duration = now - start_time;
part_stat_lock(); update_io_ticks(bdev, now, true); part_stat_inc(bdev, ios[sgrp]); part_stat_add(bdev, sectors[sgrp], sectors); part_stat_add(bdev, nsecs[sgrp], jiffies_to_nsecs(duration)); bdev_dec_in_flight(bdev, op); part_stat_unlock();}EXPORT_SYMBOL(bdev_end_io_acct);
void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, struct block_device *orig_bdev){ bdev_end_io_acct(orig_bdev, bio_op(bio), bio_sectors(bio), start_time);}EXPORT_SYMBOL_GPL(bio_end_io_acct_remapped);
/** * blk_lld_busy - Check if underlying low-level drivers of a device are busy * @q : the queue of the device being checked * * Description: * Check if underlying low-level drivers of a device are busy. * If the drivers want to export their busy state, they must set own * exporting function using blk_queue_lld_busy() first. * * Basically, this function is used only by request stacking drivers * to stop dispatching requests to underlying devices when underlying * devices are busy. This behavior helps more I/O merging on the queue * of the request stacking driver and prevents I/O throughput regression * on burst I/O load. * * Return: * 0 - Not busy (The request stacking driver should dispatch request) * 1 - Busy (The request stacking driver should stop dispatching request) */int blk_lld_busy(struct request_queue *q){ if (queue_is_mq(q) && q->mq_ops->busy) return q->mq_ops->busy(q);
return 0;}EXPORT_SYMBOL_GPL(blk_lld_busy);
int kblockd_schedule_work(struct work_struct *work){ return queue_work(kblockd_workqueue, work);}EXPORT_SYMBOL(kblockd_schedule_work);
int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay){ return mod_delayed_work_on(cpu, kblockd_workqueue, dwork, delay);}EXPORT_SYMBOL(kblockd_mod_delayed_work_on);
void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios){ struct task_struct *tsk = current;
/* * If this is a nested plug, don't actually assign it. */ if (tsk->plug) return;
plug->cur_ktime = 0; rq_list_init(&plug->mq_list); rq_list_init(&plug->cached_rqs); plug->nr_ios = min_t(unsigned short, nr_ios, BLK_MAX_REQUEST_COUNT); plug->rq_count = 0; plug->multiple_queues = false; plug->has_elevator = false; INIT_LIST_HEAD(&plug->cb_list);
/* * Store ordering should not be needed here, since a potential * preempt will imply a full memory barrier */ tsk->plug = plug;}
/** * blk_start_plug - initialize blk_plug and track it inside the task_struct * @plug: The &struct blk_plug that needs to be initialized * * Description: * blk_start_plug() indicates to the block layer an intent by the caller * to submit multiple I/O requests in a batch. The block layer may use * this hint to defer submitting I/Os from the caller until blk_finish_plug() * is called. However, the block layer may choose to submit requests * before a call to blk_finish_plug() if the number of queued I/Os * exceeds %BLK_MAX_REQUEST_COUNT, or if the size of the I/O is larger than * %BLK_PLUG_FLUSH_SIZE. The queued I/Os may also be submitted early if * the task schedules (see below). * * Tracking blk_plug inside the task_struct will help with auto-flushing the * pending I/O should the task end up blocking between blk_start_plug() and * blk_finish_plug(). This is important from a performance perspective, but * also ensures that we don't deadlock. For instance, if the task is blocking * for a memory allocation, memory reclaim could end up wanting to free a * page belonging to that request that is currently residing in our private * plug. By flushing the pending I/O when the process goes to sleep, we avoid * this kind of deadlock. */void blk_start_plug(struct blk_plug *plug){ blk_start_plug_nr_ios(plug, 1);}EXPORT_SYMBOL(blk_start_plug);
static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule){ LIST_HEAD(callbacks);
while (!list_empty(&plug->cb_list)) { list_splice_init(&plug->cb_list, &callbacks);
while (!list_empty(&callbacks)) { struct blk_plug_cb *cb = list_first_entry(&callbacks, struct blk_plug_cb, list); list_del(&cb->list); cb->callback(cb, from_schedule); } }}
struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data, int size){ struct blk_plug *plug = current->plug; struct blk_plug_cb *cb;
if (!plug) return NULL;
list_for_each_entry(cb, &plug->cb_list, list) if (cb->callback == unplug && cb->data == data) return cb;
/* Not currently on the callback list */ BUG_ON(size < sizeof(*cb)); cb = kzalloc(size, GFP_ATOMIC); if (cb) { cb->data = data; cb->callback = unplug; list_add(&cb->list, &plug->cb_list); } return cb;}EXPORT_SYMBOL(blk_check_plugged);
void __blk_flush_plug(struct blk_plug *plug, bool from_schedule){ if (!list_empty(&plug->cb_list)) flush_plug_callbacks(plug, from_schedule); blk_mq_flush_plug_list(plug, from_schedule); /* * Unconditionally flush out cached requests, even if the unplug * event came from schedule. Since we know hold references to the * queue for cached requests, we don't want a blocked task holding * up a queue freeze/quiesce event. */ if (unlikely(!rq_list_empty(&plug->cached_rqs))) blk_mq_free_plug_rqs(plug);
plug->cur_ktime = 0; current->flags &= ~PF_BLOCK_TS;}
/** * blk_finish_plug - mark the end of a batch of submitted I/O * @plug: The &struct blk_plug passed to blk_start_plug() * * Description: * Indicate that a batch of I/O submissions is complete. This function * must be paired with an initial call to blk_start_plug(). The intent * is to allow the block layer to optimize I/O submission. See the * documentation for blk_start_plug() for more information. */void blk_finish_plug(struct blk_plug *plug){ if (plug == current->plug) { __blk_flush_plug(plug, false); current->plug = NULL; }}EXPORT_SYMBOL(blk_finish_plug);
void blk_io_schedule(void){ /* Prevent hang_check timer from firing at us during very long I/O */ unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2;
if (timeout) io_schedule_timeout(timeout); else io_schedule();}
int __init blk_dev_init(void){ BUILD_BUG_ON((__force u32)REQ_OP_LAST >= (1 << REQ_OP_BITS)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * sizeof_field(struct request, cmd_flags)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * sizeof_field(struct bio, bi_opf));
/* used for unplugging and affects IO latency/throughput - HIGHPRI */ kblockd_workqueue = alloc_workqueue("kblockd", WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_PERCPU, 0); if (!kblockd_workqueue) panic("Failed to create kblockd\n");
blk_requestq_cachep = KMEM_CACHE(request_queue, SLAB_PANIC);
blk_debugfs_root = debugfs_create_dir("block", NULL);
return 0;}