mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-26 10:49:33 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
Pull block updates from Jens Axboe: "This is the main pull request for block IO related changes for the 4.16 kernel. Nothing major in this pull request, but a good amount of improvements and fixes all over the map. This contains: - BFQ improvements, fixes, and cleanups from Angelo, Chiara, and Paolo. - Support for SMR zones for deadline and mq-deadline from Damien and Christoph. - Set of fixes for bcache by way of Michael Lyle, including fixes from himself, Kent, Rui, Tang, and Coly. - Series from Matias for lightnvm with fixes from Hans Holmberg, Javier, and Matias. Mostly centered around pblk, and the removing rrpc 1.2 in preparation for supporting 2.0. - A couple of NVMe pull requests from Christoph. Nothing major in here, just fixes and cleanups, and support for command tracing from Johannes. - Support for blk-throttle for tracking reads and writes separately. From Joseph Qi. A few cleanups/fixes also for blk-throttle from Weiping. - Series from Mike Snitzer that enables dm to register its queue more logically, something that's alwways been problematic on dm since it's a stacked device. - Series from Ming cleaning up some of the bio accessor use, in preparation for supporting multipage bvecs. - Various fixes from Ming closing up holes around queue mapping and quiescing. - BSD partition fix from Richard Narron, fixing a problem where we can't mount newer (10/11) FreeBSD partitions. - Series from Tejun reworking blk-mq timeout handling. The previous scheme relied on atomic bits, but it had races where we would think a request had timed out if it to reused at the wrong time. - null_blk now supports faking timeouts, to enable us to better exercise and test that functionality separately. From me. - Kill the separate atomic poll bit in the request struct. After this, we don't use the atomic bits on blk-mq anymore at all. From me. - sgl_alloc/free helpers from Bart. - Heavily contended tag case scalability improvement from me. - Various little fixes and cleanups from Arnd, Bart, Corentin, Douglas, Eryu, Goldwyn, and myself" * 'for-4.16/block' of git://git.kernel.dk/linux-block: (186 commits) block: remove smart1,2.h nvme: add tracepoint for nvme_complete_rq nvme: add tracepoint for nvme_setup_cmd nvme-pci: introduce RECONNECTING state to mark initializing procedure nvme-rdma: remove redundant boolean for inline_data nvme: don't free uuid pointer before printing it nvme-pci: Suspend queues after deleting them bsg: use pr_debug instead of hand crafted macros blk-mq-debugfs: don't allow write on attributes with seq_operations set nvme-pci: Fix queue double allocations block: Set BIO_TRACE_COMPLETION on new bio during split blk-throttle: use queue_is_rq_based block: Remove kblockd_schedule_delayed_work{,_on}() blk-mq: Avoid that blk_mq_delay_run_hw_queue() introduces unintended delays blk-mq: Rename blk_mq_request_direct_issue() into blk_mq_request_issue_directly() lib/scatterlist: Fix chaining support in sgl_alloc_order() blk-throttle: track read and write request individually block: add bdev_read_only() checks to common helpers block: fail op_is_write() requests to read-only partitions blk-throttle: export io_serviced_recursive, io_service_bytes_recursive ...
343 lines
10 KiB
C
343 lines
10 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef BLK_INTERNAL_H
|
|
#define BLK_INTERNAL_H
|
|
|
|
#include <linux/idr.h>
|
|
#include <linux/blk-mq.h>
|
|
#include "blk-mq.h"
|
|
|
|
/* Amount of time in which a process may batch requests */
|
|
#define BLK_BATCH_TIME (HZ/50UL)
|
|
|
|
/* Number of requests a "batching" process may submit */
|
|
#define BLK_BATCH_REQ 32
|
|
|
|
/* Max future timer expiry for timeouts */
|
|
#define BLK_MAX_TIMEOUT (5 * HZ)
|
|
|
|
#ifdef CONFIG_DEBUG_FS
|
|
extern struct dentry *blk_debugfs_root;
|
|
#endif
|
|
|
|
struct blk_flush_queue {
|
|
unsigned int flush_queue_delayed:1;
|
|
unsigned int flush_pending_idx:1;
|
|
unsigned int flush_running_idx:1;
|
|
unsigned long flush_pending_since;
|
|
struct list_head flush_queue[2];
|
|
struct list_head flush_data_in_flight;
|
|
struct request *flush_rq;
|
|
|
|
/*
|
|
* flush_rq shares tag with this rq, both can't be active
|
|
* at the same time
|
|
*/
|
|
struct request *orig_rq;
|
|
spinlock_t mq_flush_lock;
|
|
};
|
|
|
|
extern struct kmem_cache *blk_requestq_cachep;
|
|
extern struct kmem_cache *request_cachep;
|
|
extern struct kobj_type blk_queue_ktype;
|
|
extern struct ida blk_queue_ida;
|
|
|
|
static inline struct blk_flush_queue *blk_get_flush_queue(
|
|
struct request_queue *q, struct blk_mq_ctx *ctx)
|
|
{
|
|
if (q->mq_ops)
|
|
return blk_mq_map_queue(q, ctx->cpu)->fq;
|
|
return q->fq;
|
|
}
|
|
|
|
static inline void __blk_get_queue(struct request_queue *q)
|
|
{
|
|
kobject_get(&q->kobj);
|
|
}
|
|
|
|
struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q,
|
|
int node, int cmd_size);
|
|
void blk_free_flush_queue(struct blk_flush_queue *q);
|
|
|
|
int blk_init_rl(struct request_list *rl, struct request_queue *q,
|
|
gfp_t gfp_mask);
|
|
void blk_exit_rl(struct request_queue *q, struct request_list *rl);
|
|
void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
|
|
struct bio *bio);
|
|
void blk_queue_bypass_start(struct request_queue *q);
|
|
void blk_queue_bypass_end(struct request_queue *q);
|
|
void __blk_queue_free_tags(struct request_queue *q);
|
|
void blk_freeze_queue(struct request_queue *q);
|
|
|
|
static inline void blk_queue_enter_live(struct request_queue *q)
|
|
{
|
|
/*
|
|
* Given that running in generic_make_request() context
|
|
* guarantees that a live reference against q_usage_counter has
|
|
* been established, further references under that same context
|
|
* need not check that the queue has been frozen (marked dead).
|
|
*/
|
|
percpu_ref_get(&q->q_usage_counter);
|
|
}
|
|
|
|
#ifdef CONFIG_BLK_DEV_INTEGRITY
|
|
void blk_flush_integrity(void);
|
|
bool __bio_integrity_endio(struct bio *);
|
|
static inline bool bio_integrity_endio(struct bio *bio)
|
|
{
|
|
if (bio_integrity(bio))
|
|
return __bio_integrity_endio(bio);
|
|
return true;
|
|
}
|
|
#else
|
|
static inline void blk_flush_integrity(void)
|
|
{
|
|
}
|
|
static inline bool bio_integrity_endio(struct bio *bio)
|
|
{
|
|
return true;
|
|
}
|
|
#endif
|
|
|
|
void blk_timeout_work(struct work_struct *work);
|
|
unsigned long blk_rq_timeout(unsigned long timeout);
|
|
void blk_add_timer(struct request *req);
|
|
void blk_delete_timer(struct request *);
|
|
|
|
|
|
bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
|
|
struct bio *bio);
|
|
bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
|
|
struct bio *bio);
|
|
bool bio_attempt_discard_merge(struct request_queue *q, struct request *req,
|
|
struct bio *bio);
|
|
bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
|
|
unsigned int *request_count,
|
|
struct request **same_queue_rq);
|
|
unsigned int blk_plug_queued_count(struct request_queue *q);
|
|
|
|
void blk_account_io_start(struct request *req, bool new_io);
|
|
void blk_account_io_completion(struct request *req, unsigned int bytes);
|
|
void blk_account_io_done(struct request *req);
|
|
|
|
/*
|
|
* EH timer and IO completion will both attempt to 'grab' the request, make
|
|
* sure that only one of them succeeds. Steal the bottom bit of the
|
|
* __deadline field for this.
|
|
*/
|
|
static inline int blk_mark_rq_complete(struct request *rq)
|
|
{
|
|
return test_and_set_bit(0, &rq->__deadline);
|
|
}
|
|
|
|
static inline void blk_clear_rq_complete(struct request *rq)
|
|
{
|
|
clear_bit(0, &rq->__deadline);
|
|
}
|
|
|
|
static inline bool blk_rq_is_complete(struct request *rq)
|
|
{
|
|
return test_bit(0, &rq->__deadline);
|
|
}
|
|
|
|
/*
|
|
* Internal elevator interface
|
|
*/
|
|
#define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED)
|
|
|
|
void blk_insert_flush(struct request *rq);
|
|
|
|
static inline void elv_activate_rq(struct request_queue *q, struct request *rq)
|
|
{
|
|
struct elevator_queue *e = q->elevator;
|
|
|
|
if (e->type->ops.sq.elevator_activate_req_fn)
|
|
e->type->ops.sq.elevator_activate_req_fn(q, rq);
|
|
}
|
|
|
|
static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq)
|
|
{
|
|
struct elevator_queue *e = q->elevator;
|
|
|
|
if (e->type->ops.sq.elevator_deactivate_req_fn)
|
|
e->type->ops.sq.elevator_deactivate_req_fn(q, rq);
|
|
}
|
|
|
|
int elv_register_queue(struct request_queue *q);
|
|
void elv_unregister_queue(struct request_queue *q);
|
|
|
|
struct hd_struct *__disk_get_part(struct gendisk *disk, int partno);
|
|
|
|
#ifdef CONFIG_FAIL_IO_TIMEOUT
|
|
int blk_should_fake_timeout(struct request_queue *);
|
|
ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
|
|
ssize_t part_timeout_store(struct device *, struct device_attribute *,
|
|
const char *, size_t);
|
|
#else
|
|
static inline int blk_should_fake_timeout(struct request_queue *q)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
int ll_back_merge_fn(struct request_queue *q, struct request *req,
|
|
struct bio *bio);
|
|
int ll_front_merge_fn(struct request_queue *q, struct request *req,
|
|
struct bio *bio);
|
|
struct request *attempt_back_merge(struct request_queue *q, struct request *rq);
|
|
struct request *attempt_front_merge(struct request_queue *q, struct request *rq);
|
|
int blk_attempt_req_merge(struct request_queue *q, struct request *rq,
|
|
struct request *next);
|
|
void blk_recalc_rq_segments(struct request *rq);
|
|
void blk_rq_set_mixed_merge(struct request *rq);
|
|
bool blk_rq_merge_ok(struct request *rq, struct bio *bio);
|
|
enum elv_merge blk_try_merge(struct request *rq, struct bio *bio);
|
|
|
|
void blk_queue_congestion_threshold(struct request_queue *q);
|
|
|
|
int blk_dev_init(void);
|
|
|
|
|
|
/*
|
|
* Return the threshold (number of used requests) at which the queue is
|
|
* considered to be congested. It include a little hysteresis to keep the
|
|
* context switch rate down.
|
|
*/
|
|
static inline int queue_congestion_on_threshold(struct request_queue *q)
|
|
{
|
|
return q->nr_congestion_on;
|
|
}
|
|
|
|
/*
|
|
* The threshold at which a queue is considered to be uncongested
|
|
*/
|
|
static inline int queue_congestion_off_threshold(struct request_queue *q)
|
|
{
|
|
return q->nr_congestion_off;
|
|
}
|
|
|
|
extern int blk_update_nr_requests(struct request_queue *, unsigned int);
|
|
|
|
/*
|
|
* Contribute to IO statistics IFF:
|
|
*
|
|
* a) it's attached to a gendisk, and
|
|
* b) the queue had IO stats enabled when this request was started, and
|
|
* c) it's a file system request
|
|
*/
|
|
static inline int blk_do_io_stat(struct request *rq)
|
|
{
|
|
return rq->rq_disk &&
|
|
(rq->rq_flags & RQF_IO_STAT) &&
|
|
!blk_rq_is_passthrough(rq);
|
|
}
|
|
|
|
static inline void req_set_nomerge(struct request_queue *q, struct request *req)
|
|
{
|
|
req->cmd_flags |= REQ_NOMERGE;
|
|
if (req == q->last_merge)
|
|
q->last_merge = NULL;
|
|
}
|
|
|
|
/*
|
|
* Steal a bit from this field for legacy IO path atomic IO marking. Note that
|
|
* setting the deadline clears the bottom bit, potentially clearing the
|
|
* completed bit. The user has to be OK with this (current ones are fine).
|
|
*/
|
|
static inline void blk_rq_set_deadline(struct request *rq, unsigned long time)
|
|
{
|
|
rq->__deadline = time & ~0x1UL;
|
|
}
|
|
|
|
static inline unsigned long blk_rq_deadline(struct request *rq)
|
|
{
|
|
return rq->__deadline & ~0x1UL;
|
|
}
|
|
|
|
/*
|
|
* Internal io_context interface
|
|
*/
|
|
void get_io_context(struct io_context *ioc);
|
|
struct io_cq *ioc_lookup_icq(struct io_context *ioc, struct request_queue *q);
|
|
struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q,
|
|
gfp_t gfp_mask);
|
|
void ioc_clear_queue(struct request_queue *q);
|
|
|
|
int create_task_io_context(struct task_struct *task, gfp_t gfp_mask, int node);
|
|
|
|
/**
|
|
* rq_ioc - determine io_context for request allocation
|
|
* @bio: request being allocated is for this bio (can be %NULL)
|
|
*
|
|
* Determine io_context to use for request allocation for @bio. May return
|
|
* %NULL if %current->io_context doesn't exist.
|
|
*/
|
|
static inline struct io_context *rq_ioc(struct bio *bio)
|
|
{
|
|
#ifdef CONFIG_BLK_CGROUP
|
|
if (bio && bio->bi_ioc)
|
|
return bio->bi_ioc;
|
|
#endif
|
|
return current->io_context;
|
|
}
|
|
|
|
/**
|
|
* create_io_context - try to create task->io_context
|
|
* @gfp_mask: allocation mask
|
|
* @node: allocation node
|
|
*
|
|
* If %current->io_context is %NULL, allocate a new io_context and install
|
|
* it. Returns the current %current->io_context which may be %NULL if
|
|
* allocation failed.
|
|
*
|
|
* Note that this function can't be called with IRQ disabled because
|
|
* task_lock which protects %current->io_context is IRQ-unsafe.
|
|
*/
|
|
static inline struct io_context *create_io_context(gfp_t gfp_mask, int node)
|
|
{
|
|
WARN_ON_ONCE(irqs_disabled());
|
|
if (unlikely(!current->io_context))
|
|
create_task_io_context(current, gfp_mask, node);
|
|
return current->io_context;
|
|
}
|
|
|
|
/*
|
|
* Internal throttling interface
|
|
*/
|
|
#ifdef CONFIG_BLK_DEV_THROTTLING
|
|
extern void blk_throtl_drain(struct request_queue *q);
|
|
extern int blk_throtl_init(struct request_queue *q);
|
|
extern void blk_throtl_exit(struct request_queue *q);
|
|
extern void blk_throtl_register_queue(struct request_queue *q);
|
|
#else /* CONFIG_BLK_DEV_THROTTLING */
|
|
static inline void blk_throtl_drain(struct request_queue *q) { }
|
|
static inline int blk_throtl_init(struct request_queue *q) { return 0; }
|
|
static inline void blk_throtl_exit(struct request_queue *q) { }
|
|
static inline void blk_throtl_register_queue(struct request_queue *q) { }
|
|
#endif /* CONFIG_BLK_DEV_THROTTLING */
|
|
#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
|
|
extern ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page);
|
|
extern ssize_t blk_throtl_sample_time_store(struct request_queue *q,
|
|
const char *page, size_t count);
|
|
extern void blk_throtl_bio_endio(struct bio *bio);
|
|
extern void blk_throtl_stat_add(struct request *rq, u64 time);
|
|
#else
|
|
static inline void blk_throtl_bio_endio(struct bio *bio) { }
|
|
static inline void blk_throtl_stat_add(struct request *rq, u64 time) { }
|
|
#endif
|
|
|
|
#ifdef CONFIG_BOUNCE
|
|
extern int init_emergency_isa_pool(void);
|
|
extern void blk_queue_bounce(struct request_queue *q, struct bio **bio);
|
|
#else
|
|
static inline int init_emergency_isa_pool(void)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
|
|
{
|
|
}
|
|
#endif /* CONFIG_BOUNCE */
|
|
|
|
extern void blk_drain_queue(struct request_queue *q);
|
|
|
|
#endif /* BLK_INTERNAL_H */
|