#include <linux/compiler.h>
#include <linux/delay.h>
#include <linux/blktrace_api.h>
-#include <trace/block.h>
#include <linux/hash.h>
#include <linux/uaccess.h>
+#include <trace/events/block.h>
+
#include "blk.h"
static DEFINE_SPINLOCK(elv_list_lock);
static LIST_HEAD(elv_list);
-DEFINE_TRACE(block_rq_abort);
-
/*
* Merge hash stuff.
*/
#define ELV_HASH_FN(sec) \
(hash_long(ELV_HASH_BLOCK((sec)), elv_hash_shift))
#define ELV_HASH_ENTRIES (1 << elv_hash_shift)
-#define rq_hash_key(rq) ((rq)->sector + (rq)->nr_sectors)
-#define ELV_ON_HASH(rq) (!hlist_unhashed(&(rq)->hash))
-
-DEFINE_TRACE(block_rq_insert);
-DEFINE_TRACE(block_rq_issue);
+#define rq_hash_key(rq) (blk_rq_pos(rq) + blk_rq_sectors(rq))
/*
* Query io scheduler to see if the current process issuing bio may be
static int elv_iosched_allow_merge(struct request *rq, struct bio *bio)
{
struct request_queue *q = rq->q;
- elevator_t *e = q->elevator;
+ struct elevator_queue *e = q->elevator;
if (e->ops->elevator_allow_merge_fn)
return e->ops->elevator_allow_merge_fn(q, rq, bio);
/*
* Don't merge file system requests and discard requests
*/
- if (bio_discard(bio) != bio_discard(rq->bio))
+ if ((bio->bi_rw & REQ_DISCARD) != (rq->bio->bi_rw & REQ_DISCARD))
+ return 0;
+
+ /*
+ * Don't merge discard requests and secure discard requests
+ */
+ if ((bio->bi_rw & REQ_SECURE) != (rq->bio->bi_rw & REQ_SECURE))
return 0;
/*
* we can merge and sequence is ok, check if it's possible
*/
if (elv_rq_merge_ok(__rq, bio)) {
- if (__rq->sector + __rq->nr_sectors == bio->bi_sector)
+ if (blk_rq_pos(__rq) + blk_rq_sectors(__rq) == bio->bi_sector)
ret = ELEVATOR_BACK_MERGE;
- else if (__rq->sector - bio_sectors(bio) == bio->bi_sector)
+ else if (blk_rq_pos(__rq) - bio_sectors(bio) == bio->bi_sector)
ret = ELEVATOR_FRONT_MERGE;
}
spin_unlock(&elv_list_lock);
- if (!strcmp(name, "anticipatory"))
- sprintf(elv, "as-iosched");
- else
- sprintf(elv, "%s-iosched", name);
+ snprintf(elv, sizeof(elv), "%s-iosched", name);
request_module("%s", elv);
spin_lock(&elv_list_lock);
* Be backwards-compatible with previous kernels, so users
* won't get the wrong elevator.
*/
- if (!strcmp(str, "as"))
- strcpy(chosen_elevator, "anticipatory");
- else
- strncpy(chosen_elevator, str, sizeof(chosen_elevator) - 1);
+ strncpy(chosen_elevator, str, sizeof(chosen_elevator) - 1);
return 1;
}
static struct kobj_type elv_ktype;
-static elevator_t *elevator_alloc(struct request_queue *q,
+static struct elevator_queue *elevator_alloc(struct request_queue *q,
struct elevator_type *e)
{
- elevator_t *eq;
+ struct elevator_queue *eq;
int i;
- eq = kmalloc_node(sizeof(elevator_t), GFP_KERNEL | __GFP_ZERO, q->node);
+ eq = kmalloc_node(sizeof(*eq), GFP_KERNEL | __GFP_ZERO, q->node);
if (unlikely(!eq))
goto err;
static void elevator_release(struct kobject *kobj)
{
- elevator_t *e = container_of(kobj, elevator_t, kobj);
+ struct elevator_queue *e;
+ e = container_of(kobj, struct elevator_queue, kobj);
elevator_put(e->elevator_type);
kfree(e->hash);
kfree(e);
{
struct elevator_type *e = NULL;
struct elevator_queue *eq;
- int ret = 0;
void *data;
+ if (unlikely(q->elevator))
+ return 0;
+
INIT_LIST_HEAD(&q->queue_head);
q->last_merge = NULL;
q->end_sector = 0;
}
elevator_attach(q, eq, data);
- return ret;
+ return 0;
}
EXPORT_SYMBOL(elevator_init);
-void elevator_exit(elevator_t *e)
+void elevator_exit(struct elevator_queue *e)
{
mutex_lock(&e->sysfs_lock);
if (e->ops->elevator_exit_fn)
}
EXPORT_SYMBOL(elevator_exit);
-static void elv_activate_rq(struct request_queue *q, struct request *rq)
-{
- elevator_t *e = q->elevator;
-
- if (e->ops->elevator_activate_req_fn)
- e->ops->elevator_activate_req_fn(q, rq);
-}
-
-static void elv_deactivate_rq(struct request_queue *q, struct request *rq)
-{
- elevator_t *e = q->elevator;
-
- if (e->ops->elevator_deactivate_req_fn)
- e->ops->elevator_deactivate_req_fn(q, rq);
-}
-
static inline void __elv_rqhash_del(struct request *rq)
{
hlist_del_init(&rq->hash);
static void elv_rqhash_add(struct request_queue *q, struct request *rq)
{
- elevator_t *e = q->elevator;
+ struct elevator_queue *e = q->elevator;
BUG_ON(ELV_ON_HASH(rq));
hlist_add_head(&rq->hash, &e->hash[ELV_HASH_FN(rq_hash_key(rq))]);
static struct request *elv_rqhash_find(struct request_queue *q, sector_t offset)
{
- elevator_t *e = q->elevator;
+ struct elevator_queue *e = q->elevator;
struct hlist_head *hash_list = &e->hash[ELV_HASH_FN(offset)];
struct hlist_node *entry, *next;
struct request *rq;
parent = *p;
__rq = rb_entry(parent, struct request, rb_node);
- if (rq->sector < __rq->sector)
+ if (blk_rq_pos(rq) < blk_rq_pos(__rq))
p = &(*p)->rb_left;
- else if (rq->sector > __rq->sector)
+ else if (blk_rq_pos(rq) > blk_rq_pos(__rq))
p = &(*p)->rb_right;
else
return __rq;
while (n) {
rq = rb_entry(n, struct request, rb_node);
- if (sector < rq->sector)
+ if (sector < blk_rq_pos(rq))
n = n->rb_left;
- else if (sector > rq->sector)
+ else if (sector > blk_rq_pos(rq))
n = n->rb_right;
else
return rq;
list_for_each_prev(entry, &q->queue_head) {
struct request *pos = list_entry_rq(entry);
- if (blk_discard_rq(rq) != blk_discard_rq(pos))
+ if ((rq->cmd_flags & REQ_DISCARD) !=
+ (pos->cmd_flags & REQ_DISCARD))
break;
if (rq_data_dir(rq) != rq_data_dir(pos))
break;
if (pos->cmd_flags & stop_flags)
break;
- if (rq->sector >= boundary) {
- if (pos->sector < boundary)
+ if (blk_rq_pos(rq) >= boundary) {
+ if (blk_rq_pos(pos) < boundary)
continue;
} else {
- if (pos->sector >= boundary)
+ if (blk_rq_pos(pos) >= boundary)
break;
}
- if (rq->sector >= pos->sector)
+ if (blk_rq_pos(rq) >= blk_rq_pos(pos))
break;
}
int elv_merge(struct request_queue *q, struct request **req, struct bio *bio)
{
- elevator_t *e = q->elevator;
+ struct elevator_queue *e = q->elevator;
struct request *__rq;
int ret;
+ /*
+ * Levels of merges:
+ * nomerges: No merges at all attempted
+ * noxmerges: Only simple one-hit cache try
+ * merges: All merge tries attempted
+ */
+ if (blk_queue_nomerges(q))
+ return ELEVATOR_NO_MERGE;
+
/*
* First try one-hit cache.
*/
}
}
- if (blk_queue_nomerges(q))
+ if (blk_queue_noxmerges(q))
return ELEVATOR_NO_MERGE;
/*
void elv_merged_request(struct request_queue *q, struct request *rq, int type)
{
- elevator_t *e = q->elevator;
+ struct elevator_queue *e = q->elevator;
if (e->ops->elevator_merged_fn)
e->ops->elevator_merged_fn(q, rq, type);
void elv_merge_requests(struct request_queue *q, struct request *rq,
struct request *next)
{
- elevator_t *e = q->elevator;
+ struct elevator_queue *e = q->elevator;
if (e->ops->elevator_merge_req_fn)
e->ops->elevator_merge_req_fn(q, rq, next);
q->last_merge = rq;
}
+void elv_bio_merged(struct request_queue *q, struct request *rq,
+ struct bio *bio)
+{
+ struct elevator_queue *e = q->elevator;
+
+ if (e->ops->elevator_bio_merged_fn)
+ e->ops->elevator_bio_merged_fn(q, rq, bio);
+}
+
void elv_requeue_request(struct request_queue *q, struct request *rq)
{
/*
* in_flight count again
*/
if (blk_account_rq(rq)) {
- q->in_flight--;
- if (blk_sorted_rq(rq))
+ q->in_flight[rq_is_sync(rq)]--;
+ if (rq->cmd_flags & REQ_SORTED)
elv_deactivate_rq(q, rq);
}
elv_insert(q, rq, ELEVATOR_INSERT_REQUEUE);
}
-static void elv_drain_elevator(struct request_queue *q)
+void elv_drain_elevator(struct request_queue *q)
{
static int printed;
while (q->elevator->ops->elevator_dispatch_fn(q, 1))
}
}
+/*
+ * Call with queue lock held, interrupts disabled
+ */
+void elv_quiesce_start(struct request_queue *q)
+{
+ if (!q->elevator)
+ return;
+
+ queue_flag_set(QUEUE_FLAG_ELVSWITCH, q);
+
+ /*
+ * make sure we don't have any requests in flight
+ */
+ elv_drain_elevator(q);
+ while (q->rq.elvpriv) {
+ __blk_run_queue(q);
+ spin_unlock_irq(q->queue_lock);
+ msleep(10);
+ spin_lock_irq(q->queue_lock);
+ elv_drain_elevator(q);
+ }
+}
+
+void elv_quiesce_end(struct request_queue *q)
+{
+ queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
+}
+
void elv_insert(struct request_queue *q, struct request *rq, int where)
{
- struct list_head *pos;
- unsigned ordseq;
int unplug_it = 1;
trace_block_rq_insert(q, rq);
rq->q = q;
switch (where) {
+ case ELEVATOR_INSERT_REQUEUE:
+ /*
+ * Most requeues happen because of a busy condition,
+ * don't force unplug of the queue for that case.
+ * Clear unplug_it and fall through.
+ */
+ unplug_it = 0;
+
case ELEVATOR_INSERT_FRONT:
rq->cmd_flags |= REQ_SOFTBARRIER;
-
list_add(&rq->queuelist, &q->queue_head);
break;
* with anything. There's no point in delaying queue
* processing.
*/
- blk_remove_plug(q);
- blk_start_queueing(q);
+ __blk_run_queue(q);
break;
case ELEVATOR_INSERT_SORT:
- BUG_ON(!blk_fs_request(rq) && !blk_discard_rq(rq));
+ BUG_ON(rq->cmd_type != REQ_TYPE_FS &&
+ !(rq->cmd_flags & REQ_DISCARD));
rq->cmd_flags |= REQ_SORTED;
q->nr_sorted++;
if (rq_mergeable(rq)) {
q->elevator->ops->elevator_add_req_fn(q, rq);
break;
- case ELEVATOR_INSERT_REQUEUE:
- /*
- * If ordered flush isn't in progress, we do front
- * insertion; otherwise, requests should be requeued
- * in ordseq order.
- */
- rq->cmd_flags |= REQ_SOFTBARRIER;
-
- /*
- * Most requeues happen because of a busy condition,
- * don't force unplug of the queue for that case.
- */
- unplug_it = 0;
-
- if (q->ordseq == 0) {
- list_add(&rq->queuelist, &q->queue_head);
- break;
- }
-
- ordseq = blk_ordered_req_seq(rq);
-
- list_for_each(pos, &q->queue_head) {
- struct request *pos_rq = list_entry_rq(pos);
- if (ordseq <= blk_ordered_req_seq(pos_rq))
- break;
- }
-
- list_add_tail(&rq->queuelist, pos);
- break;
-
default:
printk(KERN_ERR "%s: bad insertion point %d\n",
__func__, where);
}
if (unplug_it && blk_queue_plugged(q)) {
- int nrq = q->rq.count[READ] + q->rq.count[WRITE]
- - q->in_flight;
+ int nrq = q->rq.count[BLK_RW_SYNC] + q->rq.count[BLK_RW_ASYNC]
+ - queue_in_flight(q);
if (nrq >= q->unplug_thresh)
__generic_unplug_device(q);
void __elv_add_request(struct request_queue *q, struct request *rq, int where,
int plug)
{
- if (q->ordcolor)
- rq->cmd_flags |= REQ_ORDERED_COLOR;
-
if (rq->cmd_flags & (REQ_SOFTBARRIER | REQ_HARDBARRIER)) {
- /*
- * toggle ordered color
- */
- if (blk_barrier_rq(rq))
- q->ordcolor ^= 1;
-
- /*
- * barriers implicitly indicate back insertion
- */
- if (where == ELEVATOR_INSERT_SORT)
- where = ELEVATOR_INSERT_BACK;
-
- /*
- * this request is scheduling boundary, update
- * end_sector
- */
- if (blk_fs_request(rq) || blk_discard_rq(rq)) {
+ /* barriers are scheduling boundary, update end_sector */
+ if (rq->cmd_type == REQ_TYPE_FS ||
+ (rq->cmd_flags & REQ_DISCARD)) {
q->end_sector = rq_end_sector(rq);
q->boundary_rq = rq;
}
}
EXPORT_SYMBOL(elv_add_request);
-static inline struct request *__elv_next_request(struct request_queue *q)
-{
- struct request *rq;
-
- while (1) {
- while (!list_empty(&q->queue_head)) {
- rq = list_entry_rq(q->queue_head.next);
- if (blk_do_ordered(q, &rq))
- return rq;
- }
-
- if (!q->elevator->ops->elevator_dispatch_fn(q, 0))
- return NULL;
- }
-}
-
-struct request *elv_next_request(struct request_queue *q)
-{
- struct request *rq;
- int ret;
-
- while ((rq = __elv_next_request(q)) != NULL) {
- if (!(rq->cmd_flags & REQ_STARTED)) {
- /*
- * This is the first time the device driver
- * sees this request (possibly after
- * requeueing). Notify IO scheduler.
- */
- if (blk_sorted_rq(rq))
- elv_activate_rq(q, rq);
-
- /*
- * just mark as started even if we don't start
- * it, a request that has been delayed should
- * not be passed by new incoming requests
- */
- rq->cmd_flags |= REQ_STARTED;
- trace_block_rq_issue(q, rq);
- }
-
- if (!q->boundary_rq || q->boundary_rq == rq) {
- q->end_sector = rq_end_sector(rq);
- q->boundary_rq = NULL;
- }
-
- if (rq->cmd_flags & REQ_DONTPREP)
- break;
-
- if (q->dma_drain_size && rq->data_len) {
- /*
- * make sure space for the drain appears we
- * know we can do this because max_hw_segments
- * has been adjusted to be one fewer than the
- * device can handle
- */
- rq->nr_phys_segments++;
- }
-
- if (!q->prep_rq_fn)
- break;
-
- ret = q->prep_rq_fn(q, rq);
- if (ret == BLKPREP_OK) {
- break;
- } else if (ret == BLKPREP_DEFER) {
- /*
- * the request may have been (partially) prepped.
- * we need to keep this request in the front to
- * avoid resource deadlock. REQ_STARTED will
- * prevent other fs requests from passing this one.
- */
- if (q->dma_drain_size && rq->data_len &&
- !(rq->cmd_flags & REQ_DONTPREP)) {
- /*
- * remove the space for the drain we added
- * so that we don't add it again
- */
- --rq->nr_phys_segments;
- }
-
- rq = NULL;
- break;
- } else if (ret == BLKPREP_KILL) {
- rq->cmd_flags |= REQ_QUIET;
- __blk_end_request(rq, -EIO, blk_rq_bytes(rq));
- } else {
- printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
- break;
- }
- }
-
- return rq;
-}
-EXPORT_SYMBOL(elv_next_request);
-
-void elv_dequeue_request(struct request_queue *q, struct request *rq)
-{
- BUG_ON(list_empty(&rq->queuelist));
- BUG_ON(ELV_ON_HASH(rq));
-
- list_del_init(&rq->queuelist);
-
- /*
- * the time frame between a request being removed from the lists
- * and to it is freed is accounted as io that is in progress at
- * the driver side.
- */
- if (blk_account_rq(rq))
- q->in_flight++;
-}
-
int elv_queue_empty(struct request_queue *q)
{
- elevator_t *e = q->elevator;
+ struct elevator_queue *e = q->elevator;
if (!list_empty(&q->queue_head))
return 0;
struct request *elv_latter_request(struct request_queue *q, struct request *rq)
{
- elevator_t *e = q->elevator;
+ struct elevator_queue *e = q->elevator;
if (e->ops->elevator_latter_req_fn)
return e->ops->elevator_latter_req_fn(q, rq);
struct request *elv_former_request(struct request_queue *q, struct request *rq)
{
- elevator_t *e = q->elevator;
+ struct elevator_queue *e = q->elevator;
if (e->ops->elevator_former_req_fn)
return e->ops->elevator_former_req_fn(q, rq);
int elv_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask)
{
- elevator_t *e = q->elevator;
+ struct elevator_queue *e = q->elevator;
if (e->ops->elevator_set_req_fn)
return e->ops->elevator_set_req_fn(q, rq, gfp_mask);
void elv_put_request(struct request_queue *q, struct request *rq)
{
- elevator_t *e = q->elevator;
+ struct elevator_queue *e = q->elevator;
if (e->ops->elevator_put_req_fn)
e->ops->elevator_put_req_fn(rq);
int elv_may_queue(struct request_queue *q, int rw)
{
- elevator_t *e = q->elevator;
+ struct elevator_queue *e = q->elevator;
if (e->ops->elevator_may_queue_fn)
return e->ops->elevator_may_queue_fn(q, rw);
rq = list_entry_rq(q->queue_head.next);
rq->cmd_flags |= REQ_QUIET;
trace_block_rq_abort(q, rq);
- __blk_end_request(rq, -EIO, blk_rq_bytes(rq));
+ /*
+ * Mark this request as started so we don't trigger
+ * any debug logic in the end I/O path.
+ */
+ blk_start_request(rq);
+ __blk_end_request_all(rq, -EIO);
}
}
EXPORT_SYMBOL(elv_abort_queue);
void elv_completed_request(struct request_queue *q, struct request *rq)
{
- elevator_t *e = q->elevator;
+ struct elevator_queue *e = q->elevator;
/*
* request is released from the driver, io must be done
*/
if (blk_account_rq(rq)) {
- q->in_flight--;
- if (blk_sorted_rq(rq) && e->ops->elevator_completed_req_fn)
+ q->in_flight[rq_is_sync(rq)]--;
+ if ((rq->cmd_flags & REQ_SORTED) &&
+ e->ops->elevator_completed_req_fn)
e->ops->elevator_completed_req_fn(q, rq);
}
-
- /*
- * Check if the queue is waiting for fs requests to be
- * drained for flush sequence.
- */
- if (unlikely(q->ordseq)) {
- struct request *next = NULL;
-
- if (!list_empty(&q->queue_head))
- next = list_entry_rq(q->queue_head.next);
-
- if (!q->in_flight &&
- blk_ordered_cur_seq(q) == QUEUE_ORDSEQ_DRAIN &&
- (!next || blk_ordered_req_seq(next) > QUEUE_ORDSEQ_DRAIN)) {
- blk_ordered_complete_seq(q, QUEUE_ORDSEQ_DRAIN, 0);
- blk_start_queueing(q);
- }
- }
}
#define to_elv(atr) container_of((atr), struct elv_fs_entry, attr)
static ssize_t
elv_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
{
- elevator_t *e = container_of(kobj, elevator_t, kobj);
struct elv_fs_entry *entry = to_elv(attr);
+ struct elevator_queue *e;
ssize_t error;
if (!entry->show)
return -EIO;
+ e = container_of(kobj, struct elevator_queue, kobj);
mutex_lock(&e->sysfs_lock);
error = e->ops ? entry->show(e, page) : -ENOENT;
mutex_unlock(&e->sysfs_lock);
elv_attr_store(struct kobject *kobj, struct attribute *attr,
const char *page, size_t length)
{
- elevator_t *e = container_of(kobj, elevator_t, kobj);
struct elv_fs_entry *entry = to_elv(attr);
+ struct elevator_queue *e;
ssize_t error;
if (!entry->store)
return -EIO;
+ e = container_of(kobj, struct elevator_queue, kobj);
mutex_lock(&e->sysfs_lock);
error = e->ops ? entry->store(e, page, length) : -ENOENT;
mutex_unlock(&e->sysfs_lock);
return error;
}
-static struct sysfs_ops elv_sysfs_ops = {
+static const struct sysfs_ops elv_sysfs_ops = {
.show = elv_attr_show,
.store = elv_attr_store,
};
int elv_register_queue(struct request_queue *q)
{
- elevator_t *e = q->elevator;
+ struct elevator_queue *e = q->elevator;
int error;
error = kobject_add(&e->kobj, &q->kobj, "%s", "iosched");
}
return error;
}
+EXPORT_SYMBOL(elv_register_queue);
-static void __elv_unregister_queue(elevator_t *e)
+static void __elv_unregister_queue(struct elevator_queue *e)
{
kobject_uevent(&e->kobj, KOBJ_REMOVE);
kobject_del(&e->kobj);
if (q)
__elv_unregister_queue(q->elevator);
}
+EXPORT_SYMBOL(elv_unregister_queue);
void elv_register(struct elevator_type *e)
{
*/
static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
{
- elevator_t *old_elevator, *e;
+ struct elevator_queue *old_elevator, *e;
void *data;
/*
* Turn on BYPASS and drain all requests w/ elevator private data
*/
spin_lock_irq(q->queue_lock);
-
- queue_flag_set(QUEUE_FLAG_ELVSWITCH, q);
-
- elv_drain_elevator(q);
-
- while (q->rq.elvpriv) {
- blk_start_queueing(q);
- spin_unlock_irq(q->queue_lock);
- msleep(10);
- spin_lock_irq(q->queue_lock);
- elv_drain_elevator(q);
- }
+ elv_quiesce_start(q);
/*
* Remember old elevator.
*/
elevator_exit(old_elevator);
spin_lock_irq(q->queue_lock);
- queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
+ elv_quiesce_end(q);
spin_unlock_irq(q->queue_lock);
blk_add_trace_msg(q, "elv switch: %s", e->elevator_type->elevator_name);
char elevator_name[ELV_NAME_MAX];
struct elevator_type *e;
- strlcpy(elevator_name, name, sizeof(elevator_name));
- strstrip(elevator_name);
+ if (!q->elevator)
+ return count;
- e = elevator_get(elevator_name);
+ strlcpy(elevator_name, name, sizeof(elevator_name));
+ e = elevator_get(strstrip(elevator_name));
if (!e) {
printk(KERN_ERR "elevator: type %s not found\n", elevator_name);
return -EINVAL;
ssize_t elv_iosched_show(struct request_queue *q, char *name)
{
- elevator_t *e = q->elevator;
- struct elevator_type *elv = e->elevator_type;
+ struct elevator_queue *e = q->elevator;
+ struct elevator_type *elv;
struct elevator_type *__e;
int len = 0;
+ if (!q->elevator || !blk_queue_stackable(q))
+ return sprintf(name, "none\n");
+
+ elv = e->elevator_type;
+
spin_lock(&elv_list_lock);
list_for_each_entry(__e, &elv_list, list) {
if (!strcmp(elv->elevator_name, __e->elevator_name))
Code Review / linux-2.6.git / blobdiff