#include <linux/backing-dev.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
+ #include <linux/blk-mq.h>
#include <linux/highmem.h>
#include <linux/mm.h>
#include <linux/kernel_stat.h>
/*
* For the allocated request tables
*/
- static struct kmem_cache *request_cachep;
+ struct kmem_cache *request_cachep = NULL;
/*
* For queue allocation
*/
static struct workqueue_struct *kblockd_workqueue;
- static void drive_stat_acct(struct request *rq, int new_io)
- {
- struct hd_struct *part;
- int rw = rq_data_dir(rq);
- int cpu;
-
- if (!blk_do_io_stat(rq))
- return;
-
- cpu = part_stat_lock();
-
- if (!new_io) {
- part = rq->part;
- part_stat_inc(cpu, part, merges[rw]);
- } else {
- part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
- if (!hd_struct_try_get(part)) {
- /*
- * The partition is already being removed,
- * the request will be accounted on the disk only
- *
- * We take a reference on disk->part0 although that
- * partition will never be deleted, so we can treat
- * it as any other partition.
- */
- part = &rq->rq_disk->part0;
- hd_struct_get(part);
- }
- part_round_stats(cpu, part);
- part_inc_in_flight(part, rw);
- rq->part = part;
- }
-
- part_stat_unlock();
- }
-
void blk_queue_congestion_threshold(struct request_queue *q)
{
int nr;
rq->cmd = rq->__cmd;
rq->cmd_len = BLK_MAX_CDB;
rq->tag = -1;
- rq->ref_count = 1;
rq->start_time = jiffies;
set_start_time_ns(rq);
rq->part = NULL;
{
int bit;
- printk(KERN_INFO "%s: dev %s: type=%x, flags=%x\n", msg,
+ printk(KERN_INFO "%s: dev %s: type=%x, flags=%llx\n", msg,
rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
- rq->cmd_flags);
+ (unsigned long long) rq->cmd_flags);
printk(KERN_INFO " sector %llu, nr/cnr %u/%u\n",
(unsigned long long)blk_rq_pos(rq),
if (!q)
return NULL;
+ if (percpu_counter_init(&q->mq_usage_counter, 0))
+ goto fail_q;
+
q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask);
if (q->id < 0)
- goto fail_q;
+ goto fail_c;
q->backing_dev_info.ra_pages =
(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
q->bypass_depth = 1;
__set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags);
+ init_waitqueue_head(&q->mq_freeze_wq);
+
if (blkcg_init_queue(q))
- goto fail_id;
+ goto fail_bdi;
return q;
+fail_bdi:
+ bdi_destroy(&q->backing_dev_info);
fail_id:
ida_simple_remove(&blk_queue_ida, q->id);
+ fail_c:
+ percpu_counter_destroy(&q->mq_usage_counter);
fail_q:
kmem_cache_free(blk_requestq_cachep, q);
return NULL;
q->sg_reserved_size = INT_MAX;
+ /* Protect q->elevator from elevator_change */
+ mutex_lock(&q->sysfs_lock);
+
/* init elevator */
- if (elevator_init(q, NULL))
+ if (elevator_init(q, NULL)) {
+ mutex_unlock(&q->sysfs_lock);
return NULL;
+ }
+
+ mutex_unlock(&q->sysfs_lock);
+
return q;
}
EXPORT_SYMBOL(blk_init_allocated_queue);
goto retry;
}
- struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
+ static struct request *blk_old_get_request(struct request_queue *q, int rw,
+ gfp_t gfp_mask)
{
struct request *rq;
return rq;
}
+
+ struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
+ {
+ if (q->mq_ops)
+ return blk_mq_alloc_request(q, rw, gfp_mask, false);
+ else
+ return blk_old_get_request(q, rw, gfp_mask);
+ }
EXPORT_SYMBOL(blk_get_request);
/**
static void add_acct_request(struct request_queue *q, struct request *rq,
int where)
{
- drive_stat_acct(rq, 1);
+ blk_account_io_start(rq, true);
__elv_add_request(q, rq, where);
}
{
if (unlikely(!q))
return;
- if (unlikely(--req->ref_count))
- return;
blk_pm_put_request(req);
void blk_put_request(struct request *req)
{
- unsigned long flags;
struct request_queue *q = req->q;
- spin_lock_irqsave(q->queue_lock, flags);
- __blk_put_request(q, req);
- spin_unlock_irqrestore(q->queue_lock, flags);
+ if (q->mq_ops)
+ blk_mq_free_request(req);
+ else {
+ unsigned long flags;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+ __blk_put_request(q, req);
+ spin_unlock_irqrestore(q->queue_lock, flags);
+ }
}
EXPORT_SYMBOL(blk_put_request);
}
EXPORT_SYMBOL_GPL(blk_add_request_payload);
- static bool bio_attempt_back_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)
{
const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
req->__data_len += bio->bi_size;
req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
- drive_stat_acct(req, 0);
+ blk_account_io_start(req, false);
return true;
}
- static bool bio_attempt_front_merge(struct request_queue *q,
- struct request *req, struct bio *bio)
+ bool bio_attempt_front_merge(struct request_queue *q, struct request *req,
+ struct bio *bio)
{
const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
req->__data_len += bio->bi_size;
req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
- drive_stat_acct(req, 0);
+ blk_account_io_start(req, false);
return true;
}
/**
- * attempt_plug_merge - try to merge with %current's plugged list
+ * blk_attempt_plug_merge - try to merge with %current's plugged list
* @q: request_queue new bio is being queued at
* @bio: new bio being queued
* @request_count: out parameter for number of traversed plugged requests
* reliable access to the elevator outside queue lock. Only check basic
* merging parameters without querying the elevator.
*/
- static bool attempt_plug_merge(struct request_queue *q, struct bio *bio,
- unsigned int *request_count)
+ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
+ unsigned int *request_count)
{
struct blk_plug *plug;
struct request *rq;
bool ret = false;
+ struct list_head *plug_list;
+ if (blk_queue_nomerges(q))
+ goto out;
+
plug = current->plug;
if (!plug)
goto out;
*request_count = 0;
- list_for_each_entry_reverse(rq, &plug->list, queuelist) {
+ if (q->mq_ops)
+ plug_list = &plug->mq_list;
+ else
+ plug_list = &plug->list;
+
+ list_for_each_entry_reverse(rq, plug_list, queuelist) {
int el_ret;
if (rq->q == q)
* Check if we can merge with the plugged list before grabbing
* any locks.
*/
- if (attempt_plug_merge(q, bio, &request_count))
+ if (blk_attempt_plug_merge(q, bio, &request_count))
return;
spin_lock_irq(q->queue_lock);
}
}
list_add_tail(&req->queuelist, &plug->list);
- drive_stat_acct(req, 1);
+ blk_account_io_start(req, true);
} else {
spin_lock_irq(q->queue_lock);
add_acct_request(q, req, where);
}
EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
- static void blk_account_io_completion(struct request *req, unsigned int bytes)
+ void blk_account_io_completion(struct request *req, unsigned int bytes)
{
if (blk_do_io_stat(req)) {
const int rw = rq_data_dir(req);
}
}
- static void blk_account_io_done(struct request *req)
+ void blk_account_io_done(struct request *req)
{
/*
* Account IO completion. flush_rq isn't accounted as a
}
#endif
+ void blk_account_io_start(struct request *rq, bool new_io)
+ {
+ struct hd_struct *part;
+ int rw = rq_data_dir(rq);
+ int cpu;
+
+ if (!blk_do_io_stat(rq))
+ return;
+
+ cpu = part_stat_lock();
+
+ if (!new_io) {
+ part = rq->part;
+ part_stat_inc(cpu, part, merges[rw]);
+ } else {
+ part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
+ if (!hd_struct_try_get(part)) {
+ /*
+ * The partition is already being removed,
+ * the request will be accounted on the disk only
+ *
+ * We take a reference on disk->part0 although that
+ * partition will never be deleted, so we can treat
+ * it as any other partition.
+ */
+ part = &rq->rq_disk->part0;
+ hd_struct_get(part);
+ }
+ part_round_stats(cpu, part);
+ part_inc_in_flight(part, rw);
+ rq->part = part;
+ }
+
+ part_stat_unlock();
+ }
+
/**
* blk_peek_request - peek at the top of a request queue
* @q: request queue to peek at
if (unlikely(blk_bidi_rq(req)))
req->next_rq->resid_len = blk_rq_bytes(req->next_rq);
+ BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags));
blk_add_timer(req);
}
EXPORT_SYMBOL(blk_start_request);
if (req->cmd_flags & REQ_DONTPREP)
blk_unprep_request(req);
-
blk_account_io_done(req);
if (req->end_io)
plug->magic = PLUG_MAGIC;
INIT_LIST_HEAD(&plug->list);
+ INIT_LIST_HEAD(&plug->mq_list);
INIT_LIST_HEAD(&plug->cb_list);
/*
BUG_ON(plug->magic != PLUG_MAGIC);
flush_plug_callbacks(plug, from_schedule);
+
+ if (!list_empty(&plug->mq_list))
+ blk_mq_flush_plug_list(plug, from_schedule);
+
if (list_empty(&plug->list))
return;
#include <linux/fault-inject.h>
#include "blk.h"
+ #include "blk-mq.h"
#ifdef CONFIG_FAIL_IO_TIMEOUT
struct dentry *dir = fault_create_debugfs_attr("fail_io_timeout",
NULL, &fail_io_timeout);
- return IS_ERR(dir) ? PTR_ERR(dir) : 0;
+ return PTR_ERR_OR_ZERO(dir);
}
late_initcall(fail_io_timeout_debugfs);
ret = q->rq_timed_out_fn(req);
switch (ret) {
case BLK_EH_HANDLED:
- __blk_complete_request(req);
+ /* Can we use req->errors here? */
+ if (q->mq_ops)
+ blk_mq_complete_request(req, req->errors);
+ else
+ __blk_complete_request(req);
break;
case BLK_EH_RESET_TIMER:
- blk_add_timer(req);
- blk_clear_rq_complete(req);
+ if (q->mq_ops)
+ blk_mq_add_timer(req);
+ else
+ blk_add_timer(req);
++
+ blk_clear_rq_complete(req);
break;
case BLK_EH_NOT_HANDLED:
/*
}
}
+ void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout,
+ unsigned int *next_set)
+ {
+ if (time_after_eq(jiffies, rq->deadline)) {
+ list_del_init(&rq->timeout_list);
+
+ /*
+ * Check if we raced with end io completion
+ */
+ if (!blk_mark_rq_complete(rq))
+ blk_rq_timed_out(rq);
+ } else if (!*next_set || time_after(*next_timeout, rq->deadline)) {
+ *next_timeout = rq->deadline;
+ *next_set = 1;
+ }
+ }
+
void blk_rq_timed_out_timer(unsigned long data)
{
struct request_queue *q = (struct request_queue *) data;
spin_lock_irqsave(q->queue_lock, flags);
- list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list) {
- if (time_after_eq(jiffies, rq->deadline)) {
- list_del_init(&rq->timeout_list);
-
- /*
- * Check if we raced with end io completion
- */
- if (blk_mark_rq_complete(rq))
- continue;
- blk_rq_timed_out(rq);
- } else if (!next_set || time_after(next, rq->deadline)) {
- next = rq->deadline;
- next_set = 1;
- }
- }
+ list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list)
+ blk_rq_check_expired(rq, &next, &next_set);
if (next_set)
mod_timer(&q->timeout, round_jiffies_up(next));
}
EXPORT_SYMBOL_GPL(blk_abort_request);
- /**
- * blk_add_timer - Start timeout timer for a single request
- * @req: request that is about to start running.
- *
- * Notes:
- * Each request has its own timer, and as it is added to the queue, we
- * set up the timer. When the request completes, we cancel the timer.
- */
- void blk_add_timer(struct request *req)
+ void __blk_add_timer(struct request *req, struct list_head *timeout_list)
{
struct request_queue *q = req->q;
unsigned long expiry;
return;
BUG_ON(!list_empty(&req->timeout_list));
- BUG_ON(test_bit(REQ_ATOM_COMPLETE, &req->atomic_flags));
/*
* Some LLDs, like scsi, peek at the timeout to prevent a
req->timeout = q->rq_timeout;
req->deadline = jiffies + req->timeout;
- list_add_tail(&req->timeout_list, &q->timeout_list);
+ if (timeout_list)
+ list_add_tail(&req->timeout_list, timeout_list);
/*
* If the timer isn't already pending or this timeout is earlier
if (!timer_pending(&q->timeout) ||
time_before(expiry, q->timeout.expires))
mod_timer(&q->timeout, expiry);
+
+ }
+
+ /**
+ * blk_add_timer - Start timeout timer for a single request
+ * @req: request that is about to start running.
+ *
+ * Notes:
+ * Each request has its own timer, and as it is added to the queue, we
+ * set up the timer. When the request completes, we cancel the timer.
+ */
+ void blk_add_timer(struct request *req)
+ {
+ __blk_add_timer(req, &req->q->timeout_list);
}
projects / linux.git / commitdiff