#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>
#include "blk.h"
#include "blk-cgroup.h"
+#include "blk-mq.h"
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
/*
* 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;
bio_advance(bio, nbytes);
/* don't actually finish bio if it's part of flush sequence */
- if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
+ if (bio->bi_iter.bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
bio_endio(bio, error);
}
{
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),
void blk_sync_queue(struct request_queue *q)
{
del_timer_sync(&q->timeout);
- cancel_delayed_work_sync(&q->delay_work);
+
+ if (q->mq_ops) {
+ struct blk_mq_hw_ctx *hctx;
+ int i;
+
+ queue_for_each_hw_ctx(q, hctx, i)
+ cancel_delayed_work_sync(&hctx->delayed_work);
+ } else {
+ cancel_delayed_work_sync(&q->delay_work);
+ }
}
EXPORT_SYMBOL(blk_sync_queue);
* Drain all requests queued before DYING marking. Set DEAD flag to
* prevent that q->request_fn() gets invoked after draining finished.
*/
- spin_lock_irq(lock);
- __blk_drain_queue(q, true);
+ if (q->mq_ops) {
+ blk_mq_drain_queue(q);
+ spin_lock_irq(lock);
+ } else {
+ spin_lock_irq(lock);
+ __blk_drain_queue(q, true);
+ }
queue_flag_set(QUEUE_FLAG_DEAD, q);
spin_unlock_irq(lock);
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;
if (!uninit_q)
return NULL;
+ uninit_q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL);
+ if (!uninit_q->flush_rq)
+ goto out_cleanup_queue;
+
q = blk_init_allocated_queue(uninit_q, rfn, lock);
if (!q)
- blk_cleanup_queue(uninit_q);
-
+ goto out_free_flush_rq;
return q;
+
+out_free_flush_rq:
+ kfree(uninit_q->flush_rq);
+out_cleanup_queue:
+ blk_cleanup_queue(uninit_q);
+ return NULL;
}
EXPORT_SYMBOL(blk_init_queue_node);
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);
+ 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))
+
+ if (q->mq_ops) {
+ blk_mq_free_request(req);
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);
bio->bi_io_vec->bv_offset = 0;
bio->bi_io_vec->bv_len = len;
- bio->bi_size = len;
+ bio->bi_iter.bi_size = len;
bio->bi_vcnt = 1;
bio->bi_phys_segments = 1;
}
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->biotail->bi_next = bio;
req->biotail = bio;
- req->__data_len += bio->bi_size;
+ req->__data_len += bio->bi_iter.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;
* not touch req->buffer either...
*/
req->buffer = bio_data(bio);
- req->__sector = bio->bi_sector;
- req->__data_len += bio->bi_size;
+ req->__sector = bio->bi_iter.bi_sector;
+ req->__data_len += bio->bi_iter.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)
req->cmd_flags |= REQ_FAILFAST_MASK;
req->errors = 0;
- req->__sector = bio->bi_sector;
+ req->__sector = bio->bi_iter.bi_sector;
req->ioprio = bio_prio(bio);
blk_rq_bio_prep(req->q, req, bio);
}
* 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);
if (bio_sectors(bio) && bdev != bdev->bd_contains) {
struct hd_struct *p = bdev->bd_part;
- bio->bi_sector += p->start_sect;
+ bio->bi_iter.bi_sector += p->start_sect;
bio->bi_bdev = bdev->bd_contains;
trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), bio,
bdev->bd_dev,
- bio->bi_sector - p->start_sect);
+ bio->bi_iter.bi_sector - p->start_sect);
}
}
/* Test device or partition size, when known. */
maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
if (maxsector) {
- sector_t sector = bio->bi_sector;
+ sector_t sector = bio->bi_iter.bi_sector;
if (maxsector < nr_sectors || maxsector - nr_sectors < sector) {
/*
"generic_make_request: Trying to access "
"nonexistent block-device %s (%Lu)\n",
bdevname(bio->bi_bdev, b),
- (long long) bio->bi_sector);
+ (long long) bio->bi_iter.bi_sector);
goto end_io;
}
}
part = bio->bi_bdev->bd_part;
- if (should_fail_request(part, bio->bi_size) ||
+ if (should_fail_request(part, bio->bi_iter.bi_size) ||
should_fail_request(&part_to_disk(part)->part0,
- bio->bi_size))
+ bio->bi_iter.bi_size))
goto end_io;
/*
if (rw & WRITE) {
count_vm_events(PGPGOUT, count);
} else {
- task_io_account_read(bio->bi_size);
+ task_io_account_read(bio->bi_iter.bi_size);
count_vm_events(PGPGIN, count);
}
printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n",
current->comm, task_pid_nr(current),
(rw & WRITE) ? "WRITE" : "READ",
- (unsigned long long)bio->bi_sector,
+ (unsigned long long)bio->bi_iter.bi_sector,
bdevname(bio->bi_bdev, b),
count);
}
for (bio = rq->bio; bio; bio = bio->bi_next) {
if ((bio->bi_rw & ff) != ff)
break;
- bytes += bio->bi_size;
+ bytes += bio->bi_iter.bi_size;
}
/* this could lead to infinite loop */
}
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);
total_bytes = 0;
while (req->bio) {
struct bio *bio = req->bio;
- unsigned bio_bytes = min(bio->bi_size, nr_bytes);
+ unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
- if (bio_bytes == bio->bi_size)
+ if (bio_bytes == bio->bi_iter.bi_size)
req->bio = bio->bi_next;
req_bio_endio(req, bio, bio_bytes, error);
if (req->cmd_flags & REQ_DONTPREP)
blk_unprep_request(req);
-
blk_account_io_done(req);
if (req->end_io)
rq->nr_phys_segments = bio_phys_segments(q, bio);
rq->buffer = bio_data(bio);
}
- rq->__data_len = bio->bi_size;
+ rq->__data_len = bio->bi_iter.bi_size;
rq->bio = rq->biotail = bio;
if (bio->bi_bdev)
void rq_flush_dcache_pages(struct request *rq)
{
struct req_iterator iter;
- struct bio_vec *bvec;
+ struct bio_vec bvec;
rq_for_each_segment(bvec, rq, iter)
- flush_dcache_page(bvec->bv_page);
+ flush_dcache_page(bvec.bv_page);
}
EXPORT_SYMBOL_GPL(rq_flush_dcache_pages);
#endif
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;
projects / karo-tx-linux.git / blobdiff