#include "blk.h"
- EXPORT_TRACEPOINT_SYMBOL_GPL(block_remap);
+ EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
return;
cpu = part_stat_lock();
- part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
- if (!new_io)
+ if (!new_io) {
+ part = rq->part;
part_stat_inc(cpu, part, merges[rw]);
- else {
+ } 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();
rq->ref_count = 1;
rq->start_time = jiffies;
set_start_time_ns(rq);
+ rq->part = NULL;
}
EXPORT_SYMBOL(blk_rq_init);
static void req_bio_endio(struct request *rq, struct bio *bio,
unsigned int nbytes, int error)
{
- struct request_queue *q = rq->q;
-
- if (&q->flush_rq != rq) {
- if (error)
- clear_bit(BIO_UPTODATE, &bio->bi_flags);
- else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
- error = -EIO;
-
- if (unlikely(nbytes > bio->bi_size)) {
- printk(KERN_ERR "%s: want %u bytes done, %u left\n",
- __func__, nbytes, bio->bi_size);
- nbytes = bio->bi_size;
- }
+ if (error)
+ clear_bit(BIO_UPTODATE, &bio->bi_flags);
+ else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
+ error = -EIO;
+
+ if (unlikely(nbytes > bio->bi_size)) {
+ printk(KERN_ERR "%s: want %u bytes done, %u left\n",
+ __func__, nbytes, bio->bi_size);
+ nbytes = bio->bi_size;
+ }
- if (unlikely(rq->cmd_flags & REQ_QUIET))
- set_bit(BIO_QUIET, &bio->bi_flags);
+ if (unlikely(rq->cmd_flags & REQ_QUIET))
+ set_bit(BIO_QUIET, &bio->bi_flags);
- bio->bi_size -= nbytes;
- bio->bi_sector += (nbytes >> 9);
+ bio->bi_size -= nbytes;
+ bio->bi_sector += (nbytes >> 9);
- if (bio_integrity(bio))
- bio_integrity_advance(bio, nbytes);
+ if (bio_integrity(bio))
+ bio_integrity_advance(bio, nbytes);
- if (bio->bi_size == 0)
- bio_endio(bio, error);
- } else {
- /*
- * Okay, this is the sequenced flush request in
- * progress, just record the error;
- */
- if (error && !q->flush_err)
- q->flush_err = error;
- }
+ /* don't actually finish bio if it's part of flush sequence */
+ if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
+ bio_endio(bio, error);
}
void blk_dump_rq_flags(struct request *rq, char *msg)
init_timer(&q->unplug_timer);
setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
INIT_LIST_HEAD(&q->timeout_list);
- INIT_LIST_HEAD(&q->pending_flushes);
+ INIT_LIST_HEAD(&q->flush_queue[0]);
+ INIT_LIST_HEAD(&q->flush_queue[1]);
+ INIT_LIST_HEAD(&q->flush_data_in_flight);
INIT_WORK(&q->unplug_work, blk_unplug_work);
kobject_init(&q->kobj, &blk_queue_ktype);
__freed_request(q, sync ^ 1);
}
+/*
+ * Determine if elevator data should be initialized when allocating the
+ * request associated with @bio.
+ */
+static bool blk_rq_should_init_elevator(struct bio *bio)
+{
+ if (!bio)
+ return true;
+
+ /*
+ * Flush requests do not use the elevator so skip initialization.
+ * This allows a request to share the flush and elevator data.
+ */
+ if (bio->bi_rw & (REQ_FLUSH | REQ_FUA))
+ return false;
+
+ return true;
+}
+
/*
* Get a free request, queue_lock must be held.
* Returns NULL on failure, with queue_lock held.
struct request_list *rl = &q->rq;
struct io_context *ioc = NULL;
const bool is_sync = rw_is_sync(rw_flags) != 0;
- int may_queue, priv;
+ int may_queue, priv = 0;
may_queue = elv_may_queue(q, rw_flags);
if (may_queue == ELV_MQUEUE_NO)
rl->count[is_sync]++;
rl->starved[is_sync] = 0;
- priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
- if (priv)
- rl->elvpriv++;
+ if (blk_rq_should_init_elevator(bio)) {
+ priv = !test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags);
+ if (priv)
+ rl->elvpriv++;
+ }
if (blk_queue_io_stat(q))
rw_flags |= REQ_IO_STAT;
spin_lock_irq(q->queue_lock);
if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
- where = ELEVATOR_INSERT_FRONT;
+ where = ELEVATOR_INSERT_FLUSH;
goto get_rq;
}
bio->bi_sector += p->start_sect;
bio->bi_bdev = bdev->bd_contains;
- trace_block_remap(bdev_get_queue(bio->bi_bdev), bio,
- bdev->bd_dev,
- bio->bi_sector - p->start_sect);
+ trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), bio,
+ bdev->bd_dev,
+ bio->bi_sector - p->start_sect);
}
}
goto end_io;
if (old_sector != -1)
- trace_block_remap(q, bio, old_dev, old_sector);
+ trace_block_bio_remap(q, bio, old_dev, old_sector);
old_sector = bio->bi_sector;
old_dev = bio->bi_bdev->bd_dev;
int cpu;
cpu = part_stat_lock();
- part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
+ part = req->part;
part_stat_add(cpu, part, sectors[rw], bytes >> 9);
part_stat_unlock();
}
* normal IO on queueing nor completion. Accounting the
* containing request is enough.
*/
- if (blk_do_io_stat(req) && req != &req->q->flush_rq) {
+ if (blk_do_io_stat(req) && !(req->cmd_flags & REQ_FLUSH_SEQ)) {
unsigned long duration = jiffies - req->start_time;
const int rw = rq_data_dir(req);
struct hd_struct *part;
int cpu;
cpu = part_stat_lock();
- part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req));
+ part = req->part;
part_stat_inc(cpu, part, ios[rw]);
part_stat_add(cpu, part, ticks[rw], duration);
part_round_stats(cpu, part);
part_dec_in_flight(part, rw);
+ hd_struct_put(part);
part_stat_unlock();
}
}
BUILD_BUG_ON(__REQ_NR_BITS > 8 *
sizeof(((struct request *)0)->cmd_flags));
- kblockd_workqueue = create_workqueue("kblockd");
+ /* used for unplugging and affects IO latency/throughput - HIGHPRI */
+ kblockd_workqueue = alloc_workqueue("kblockd",
+ WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
if (!kblockd_workqueue)
panic("Failed to create kblockd\n");
#define CFQQ_SEEKY(cfqq) (hweight32(cfqq->seek_history) > 32/8)
#define RQ_CIC(rq) \
- ((struct cfq_io_context *) (rq)->elevator_private)
-#define RQ_CFQQ(rq) (struct cfq_queue *) ((rq)->elevator_private2)
-#define RQ_CFQG(rq) (struct cfq_group *) ((rq)->elevator_private3)
+ ((struct cfq_io_context *) (rq)->elevator_private[0])
+#define RQ_CFQQ(rq) (struct cfq_queue *) ((rq)->elevator_private[1])
+#define RQ_CFQG(rq) (struct cfq_group *) ((rq)->elevator_private[2])
static struct kmem_cache *cfq_pool;
static struct kmem_cache *cfq_ioc_pool;
unsigned count;
unsigned total_weight;
u64 min_vdisktime;
- struct rb_node *active;
};
#define CFQ_RB_ROOT (struct cfq_rb_root) { .rb = RB_ROOT, .left = NULL, \
.count = 0, .min_vdisktime = 0, }
*/
struct cfq_queue {
/* reference count */
- atomic_t ref;
+ int ref;
/* various state flags, see below */
unsigned int flags;
/* parent cfq_data */
/* group service_tree key */
u64 vdisktime;
unsigned int weight;
- bool on_st;
/* number of cfqq currently on this group */
int nr_cfqq;
struct blkio_group blkg;
#ifdef CONFIG_CFQ_GROUP_IOSCHED
struct hlist_node cfqd_node;
- atomic_t ref;
+ int ref;
#endif
/* number of requests that are on the dispatch list or inside driver */
int dispatched;
u64 vdisktime = st->min_vdisktime;
struct cfq_group *cfqg;
- if (st->active) {
- cfqg = rb_entry_cfqg(st->active);
- vdisktime = cfqg->vdisktime;
- }
-
if (st->left) {
cfqg = rb_entry_cfqg(st->left);
vdisktime = min_vdisktime(vdisktime, cfqg->vdisktime);
return cfq_target_latency * cfqg->weight / st->total_weight;
}
- static inline void
- cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+ static inline unsigned
+ cfq_scaled_cfqq_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
unsigned slice = cfq_prio_to_slice(cfqd, cfqq);
if (cfqd->cfq_latency) {
low_slice);
}
}
+ return slice;
+ }
+
+ static inline void
+ cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+ {
+ unsigned slice = cfq_scaled_cfqq_slice(cfqd, cfqq);
+
cfqq->slice_start = jiffies;
cfqq->slice_end = jiffies + slice;
cfqq->allocated_slice = slice;
static inline bool cfq_slice_used(struct cfq_queue *cfqq)
{
if (cfq_cfqq_slice_new(cfqq))
- return 0;
+ return false;
if (time_before(jiffies, cfqq->slice_end))
- return 0;
+ return false;
- return 1;
+ return true;
}
/*
struct rb_node *n;
cfqg->nr_cfqq++;
- if (cfqg->on_st)
+ if (!RB_EMPTY_NODE(&cfqg->rb_node))
return;
/*
cfqg->vdisktime = st->min_vdisktime;
__cfq_group_service_tree_add(st, cfqg);
- cfqg->on_st = true;
st->total_weight += cfqg->weight;
}
{
struct cfq_rb_root *st = &cfqd->grp_service_tree;
- if (st->active == &cfqg->rb_node)
- st->active = NULL;
-
BUG_ON(cfqg->nr_cfqq < 1);
cfqg->nr_cfqq--;
return;
cfq_log_cfqg(cfqd, cfqg, "del_from_rr group");
- cfqg->on_st = false;
st->total_weight -= cfqg->weight;
if (!RB_EMPTY_NODE(&cfqg->rb_node))
cfq_rb_erase(&cfqg->rb_node, st);
* elevator which will be dropped by either elevator exit
* or cgroup deletion path depending on who is exiting first.
*/
- atomic_set(&cfqg->ref, 1);
+ cfqg->ref = 1;
/*
* Add group onto cgroup list. It might happen that bdi->dev is
- * not initiliazed yet. Initialize this new group without major
+ * not initialized yet. Initialize this new group without major
* and minor info and this info will be filled in once a new thread
* comes for IO. See code above.
*/
static inline struct cfq_group *cfq_ref_get_cfqg(struct cfq_group *cfqg)
{
- atomic_inc(&cfqg->ref);
+ cfqg->ref++;
return cfqg;
}
cfqq->cfqg = cfqg;
/* cfqq reference on cfqg */
- atomic_inc(&cfqq->cfqg->ref);
+ cfqq->cfqg->ref++;
}
static void cfq_put_cfqg(struct cfq_group *cfqg)
struct cfq_rb_root *st;
int i, j;
- BUG_ON(atomic_read(&cfqg->ref) <= 0);
- if (!atomic_dec_and_test(&cfqg->ref))
+ BUG_ON(cfqg->ref <= 0);
+ cfqg->ref--;
+ if (cfqg->ref)
return;
for_each_cfqg_st(cfqg, i, j, st)
- BUG_ON(!RB_EMPTY_ROOT(&st->rb) || st->active != NULL);
+ BUG_ON(!RB_EMPTY_ROOT(&st->rb));
kfree(cfqg);
}
cfq_group_service_tree_del(cfqd, cfqq->cfqg);
cfqq->orig_cfqg = cfqq->cfqg;
cfqq->cfqg = &cfqd->root_group;
- atomic_inc(&cfqd->root_group.ref);
+ cfqd->root_group.ref++;
group_changed = 1;
} else if (!cfqd->cfq_group_isolation
&& cfqq_type(cfqq) == SYNC_WORKLOAD && cfqq->orig_cfqg) {
/*
* store what was left of this slice, if the queue idled/timed out
*/
- if (timed_out && !cfq_cfqq_slice_new(cfqq)) {
- cfqq->slice_resid = cfqq->slice_end - jiffies;
+ if (timed_out) {
+ if (cfq_cfqq_slice_new(cfqq))
+ cfqq->slice_resid = cfq_scaled_cfqq_slice(cfqd, cfqq);
+ else
+ cfqq->slice_resid = cfqq->slice_end - jiffies;
cfq_log_cfqq(cfqd, cfqq, "resid=%ld", cfqq->slice_resid);
}
if (cfqq == cfqd->active_queue)
cfqd->active_queue = NULL;
- if (&cfqq->cfqg->rb_node == cfqd->grp_service_tree.active)
- cfqd->grp_service_tree.active = NULL;
-
if (cfqd->active_cic) {
put_io_context(cfqd->active_cic->ioc);
cfqd->active_cic = NULL;
* in their service tree.
*/
if (service_tree->count == 1 && cfq_cfqq_sync(cfqq))
- return 1;
+ return true;
cfq_log_cfqq(cfqd, cfqq, "Not idling. st->count:%d",
service_tree->count);
- return 0;
+ return false;
}
static void cfq_arm_slice_timer(struct cfq_data *cfqd)
int process_refs, io_refs;
io_refs = cfqq->allocated[READ] + cfqq->allocated[WRITE];
- process_refs = atomic_read(&cfqq->ref) - io_refs;
+ process_refs = cfqq->ref - io_refs;
BUG_ON(process_refs < 0);
return process_refs;
}
*/
if (new_process_refs >= process_refs) {
cfqq->new_cfqq = new_cfqq;
- atomic_add(process_refs, &new_cfqq->ref);
+ new_cfqq->ref += process_refs;
} else {
new_cfqq->new_cfqq = cfqq;
- atomic_add(new_process_refs, &cfqq->ref);
+ cfqq->ref += new_process_refs;
}
}
unsigned count;
struct cfq_rb_root *st;
unsigned group_slice;
-
- if (!cfqg) {
- cfqd->serving_prio = IDLE_WORKLOAD;
- cfqd->workload_expires = jiffies + 1;
- return;
- }
+ enum wl_prio_t original_prio = cfqd->serving_prio;
/* Choose next priority. RT > BE > IDLE */
if (cfq_group_busy_queues_wl(RT_WORKLOAD, cfqd, cfqg))
return;
}
+ if (original_prio != cfqd->serving_prio)
+ goto new_workload;
+
/*
* For RT and BE, we have to choose also the type
* (SYNC, SYNC_NOIDLE, ASYNC), and to compute a workload
if (count && !time_after(jiffies, cfqd->workload_expires))
return;
+ new_workload:
/* otherwise select new workload type */
cfqd->serving_type =
cfq_choose_wl(cfqd, cfqg, cfqd->serving_prio);
if (RB_EMPTY_ROOT(&st->rb))
return NULL;
cfqg = cfq_rb_first_group(st);
- st->active = &cfqg->rb_node;
update_min_vdisktime(st);
return cfqg;
}
goto keep_queue;
}
+ /*
+ * This is a deep seek queue, but the device is much faster than
+ * the queue can deliver, don't idle
+ **/
+ if (CFQQ_SEEKY(cfqq) && cfq_cfqq_idle_window(cfqq) &&
+ (cfq_cfqq_slice_new(cfqq) ||
+ (cfqq->slice_end - jiffies > jiffies - cfqq->slice_start))) {
+ cfq_clear_cfqq_deep(cfqq);
+ cfq_clear_cfqq_idle_window(cfqq);
+ }
+
if (cfqq->dispatched && cfq_should_idle(cfqd, cfqq)) {
cfqq = NULL;
goto keep_queue;
{
/* the queue hasn't finished any request, can't estimate */
if (cfq_cfqq_slice_new(cfqq))
- return 1;
+ return true;
if (time_after(jiffies + cfqd->cfq_slice_idle * cfqq->dispatched,
cfqq->slice_end))
- return 1;
+ return true;
- return 0;
+ return false;
}
static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
struct cfq_data *cfqd = cfqq->cfqd;
struct cfq_group *cfqg, *orig_cfqg;
- BUG_ON(atomic_read(&cfqq->ref) <= 0);
+ BUG_ON(cfqq->ref <= 0);
- if (!atomic_dec_and_test(&cfqq->ref))
+ cfqq->ref--;
+ if (cfqq->ref)
return;
cfq_log_cfqq(cfqd, cfqq, "put_queue");
RB_CLEAR_NODE(&cfqq->p_node);
INIT_LIST_HEAD(&cfqq->fifo);
- atomic_set(&cfqq->ref, 0);
+ cfqq->ref = 0;
cfqq->cfqd = cfqd;
cfq_mark_cfqq_prio_changed(cfqq);
* pin the queue now that it's allocated, scheduler exit will prune it
*/
if (!is_sync && !(*async_cfqq)) {
- atomic_inc(&cfqq->ref);
+ cfqq->ref++;
*async_cfqq = cfqq;
}
- atomic_inc(&cfqq->ref);
+ cfqq->ref++;
return cfqq;
}
if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq))
return true;
+ /* An idle queue should not be idle now for some reason */
+ if (RB_EMPTY_ROOT(&cfqq->sort_list) && !cfq_should_idle(cfqd, cfqq))
+ return true;
+
if (!cfqd->active_cic || !cfq_cfqq_wait_request(cfqq))
return false;
*/
static void cfq_preempt_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
+ struct cfq_queue *old_cfqq = cfqd->active_queue;
+
cfq_log_cfqq(cfqd, cfqq, "preempt");
cfq_slice_expired(cfqd, 1);
+ /*
+ * workload type is changed, don't save slice, otherwise preempt
+ * doesn't happen
+ */
+ if (cfqq_type(old_cfqq) != cfqq_type(cfqq))
+ cfqq->cfqg->saved_workload_slice = 0;
+
/*
* Put the new queue at the front of the of the current list,
* so we know that it will be selected next.
{
struct cfq_io_context *cic = cfqd->active_cic;
+ /* If the queue already has requests, don't wait */
+ if (!RB_EMPTY_ROOT(&cfqq->sort_list))
+ return false;
+
/* If there are other queues in the group, don't wait */
if (cfqq->cfqg->nr_cfqq > 1)
return false;
put_io_context(RQ_CIC(rq)->ioc);
- rq->elevator_private = NULL;
- rq->elevator_private2 = NULL;
+ rq->elevator_private[0] = NULL;
+ rq->elevator_private[1] = NULL;
/* Put down rq reference on cfqg */
cfq_put_cfqg(RQ_CFQG(rq));
- rq->elevator_private3 = NULL;
+ rq->elevator_private[2] = NULL;
cfq_put_queue(cfqq);
}
}
cfqq->allocated[rw]++;
- atomic_inc(&cfqq->ref);
- cfqq->ref++;
- rq->elevator_private = cic;
- rq->elevator_private2 = cfqq;
- rq->elevator_private3 = cfq_ref_get_cfqg(cfqq->cfqg);
spin_unlock_irqrestore(q->queue_lock, flags);
++ cfqq->ref++;
+ rq->elevator_private[0] = cic;
+ rq->elevator_private[1] = cfqq;
+ rq->elevator_private[2] = cfq_ref_get_cfqg(cfqq->cfqg);
return 0;
queue_fail:
if (!cfqd)
return NULL;
+ /*
+ * Don't need take queue_lock in the routine, since we are
+ * initializing the ioscheduler, and nobody is using cfqd
+ */
cfqd->cic_index = i;
/* Init root service tree */
* Take a reference to root group which we never drop. This is just
* to make sure that cfq_put_cfqg() does not try to kfree root group
*/
- atomic_set(&cfqg->ref, 1);
+ cfqg->ref = 1;
rcu_read_lock();
cfq_blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg,
(void *)cfqd, 0);
* will not attempt to free it.
*/
cfq_init_cfqq(cfqd, &cfqd->oom_cfqq, 1, 0);
- atomic_inc(&cfqd->oom_cfqq.ref);
+ cfqd->oom_cfqq.ref++;
cfq_link_cfqq_cfqg(&cfqd->oom_cfqq, &cfqd->root_group);
INIT_LIST_HEAD(&cfqd->cic_list);