#include <linux/module.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
-#include <linux/hash.h>
#include <linux/rbtree.h>
#include <linux/ioprio.h>
#define CFQ_SLICE_SCALE (5)
-#define CFQ_KEY_ASYNC (0)
-
-/*
- * for the hash of cfqq inside the cfqd
- */
-#define CFQ_QHASH_SHIFT 6
-#define CFQ_QHASH_ENTRIES (1 << CFQ_QHASH_SHIFT)
-
#define RQ_CIC(rq) ((struct cfq_io_context*)(rq)->elevator_private)
#define RQ_CFQQ(rq) ((rq)->elevator_private2)
#define ASYNC (0)
#define SYNC (1)
-#define cfq_cfqq_sync(cfqq) ((cfqq)->key != CFQ_KEY_ASYNC)
-
#define sample_valid(samples) ((samples) > 80)
/*
struct cfq_rb_root service_tree;
unsigned int busy_queues;
- /*
- * cfqq lookup hash
- */
- struct hlist_head *cfq_hash;
-
int rq_in_driver;
+ int sync_flight;
int hw_tag;
/*
struct cfq_queue *active_queue;
struct cfq_io_context *active_cic;
- unsigned int dispatch_slice;
+
+ struct cfq_queue *async_cfqq[IOPRIO_BE_NR];
struct timer_list idle_class_timer;
atomic_t ref;
/* parent cfq_data */
struct cfq_data *cfqd;
- /* cfqq lookup hash */
- struct hlist_node cfq_hash;
- /* hash key */
- unsigned int key;
/* service_tree member */
struct rb_node rb_node;
/* service_tree key */
CFQ_CFQQ_FLAG_prio_changed, /* task priority has changed */
CFQ_CFQQ_FLAG_queue_new, /* queue never been serviced */
CFQ_CFQQ_FLAG_slice_new, /* no requests dispatched in slice */
+ CFQ_CFQQ_FLAG_sync, /* synchronous queue */
};
#define CFQ_CFQQ_FNS(name) \
CFQ_CFQQ_FNS(prio_changed);
CFQ_CFQQ_FNS(queue_new);
CFQ_CFQQ_FNS(slice_new);
+CFQ_CFQQ_FNS(sync);
#undef CFQ_CFQQ_FNS
-static struct cfq_queue *cfq_find_cfq_hash(struct cfq_data *, unsigned int, unsigned short);
static void cfq_dispatch_insert(request_queue_t *, struct request *);
-static struct cfq_queue *cfq_get_queue(struct cfq_data *, unsigned int, struct task_struct *, gfp_t);
+static struct cfq_queue *cfq_get_queue(struct cfq_data *, int,
+ struct task_struct *, gfp_t);
+static struct cfq_io_context *cfq_cic_rb_lookup(struct cfq_data *,
+ struct io_context *);
+
+static inline struct cfq_queue *cic_to_cfqq(struct cfq_io_context *cic,
+ int is_sync)
+{
+ return cic->cfqq[!!is_sync];
+}
+
+static inline void cic_set_cfqq(struct cfq_io_context *cic,
+ struct cfq_queue *cfqq, int is_sync)
+{
+ cic->cfqq[!!is_sync] = cfqq;
+}
+
+/*
+ * We regard a request as SYNC, if it's either a read or has the SYNC bit
+ * set (in which case it could also be direct WRITE).
+ */
+static inline int cfq_bio_sync(struct bio *bio)
+{
+ if (bio_data_dir(bio) == READ || bio_sync(bio))
+ return 1;
+
+ return 0;
+}
/*
* scheduler run of queue, if there are requests pending and no one in the
return !cfqd->busy_queues;
}
-static inline pid_t cfq_queue_pid(struct task_struct *task, int rw, int is_sync)
-{
- /*
- * Use the per-process queue, for read requests and syncronous writes
- */
- if (!(rw & REQ_RW) || is_sync)
- return task->pid;
-
- return CFQ_KEY_ASYNC;
-}
-
/*
* Scale schedule slice based on io priority. Use the sync time slice only
* if a queue is marked sync and has sync io queued. A sync queue with async
cfq_find_rq_fmerge(struct cfq_data *cfqd, struct bio *bio)
{
struct task_struct *tsk = current;
- pid_t key = cfq_queue_pid(tsk, bio_data_dir(bio), bio_sync(bio));
+ struct cfq_io_context *cic;
struct cfq_queue *cfqq;
- cfqq = cfq_find_cfq_hash(cfqd, key, tsk->ioprio);
+ cic = cfq_cic_rb_lookup(cfqd, tsk->io_context);
+ if (!cic)
+ return NULL;
+
+ cfqq = cic_to_cfqq(cic, cfq_bio_sync(bio));
if (cfqq) {
sector_t sector = bio->bi_sector + bio_sectors(bio);
struct bio *bio)
{
struct cfq_data *cfqd = q->elevator->elevator_data;
- const int rw = bio_data_dir(bio);
+ struct cfq_io_context *cic;
struct cfq_queue *cfqq;
- pid_t key;
/*
* Disallow merge of a sync bio into an async request.
*/
- if ((bio_data_dir(bio) == READ || bio_sync(bio)) && !rq_is_sync(rq))
+ if (cfq_bio_sync(bio) && !rq_is_sync(rq))
return 0;
/*
* Lookup the cfqq that this bio will be queued with. Allow
* merge only if rq is queued there.
*/
- key = cfq_queue_pid(current, rw, bio_sync(bio));
- cfqq = cfq_find_cfq_hash(cfqd, key, current->ioprio);
+ cic = cfq_cic_rb_lookup(cfqd, current->io_context);
+ if (!cic)
+ return 0;
+ cfqq = cic_to_cfqq(cic, cfq_bio_sync(bio));
if (cfqq == RQ_CFQQ(rq))
return 1;
put_io_context(cfqd->active_cic->ioc);
cfqd->active_cic = NULL;
}
-
- cfqd->dispatch_slice = 0;
}
static inline void cfq_slice_expired(struct cfq_data *cfqd, int timed_out)
*/
static void cfq_dispatch_insert(request_queue_t *q, struct request *rq)
{
+ struct cfq_data *cfqd = q->elevator->elevator_data;
struct cfq_queue *cfqq = RQ_CFQQ(rq);
cfq_remove_request(rq);
cfqq->dispatched++;
elv_dispatch_sort(q, rq);
+
+ if (cfq_cfqq_sync(cfqq))
+ cfqd->sync_flight++;
}
/*
* flight or is idling for a new request, allow either of these
* conditions to happen (or time out) before selecting a new queue.
*/
- if (cfqq->dispatched || timer_pending(&cfqd->idle_slice_timer)) {
+ if (timer_pending(&cfqd->idle_slice_timer) ||
+ (cfqq->dispatched && cfq_cfqq_idle_window(cfqq))) {
cfqq = NULL;
goto keep_queue;
}
*/
cfq_dispatch_insert(cfqd->queue, rq);
- cfqd->dispatch_slice++;
dispatched++;
if (!cfqd->active_cic) {
* queue always expire after 1 dispatch round.
*/
if (cfqd->busy_queues > 1 && ((!cfq_cfqq_sync(cfqq) &&
- cfqd->dispatch_slice >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
+ dispatched >= cfq_prio_to_maxrq(cfqd, cfqq)) ||
cfq_class_idle(cfqq))) {
cfqq->slice_end = jiffies + 1;
cfq_slice_expired(cfqd, 0);
while ((cfqq = cfq_select_queue(cfqd)) != NULL) {
int max_dispatch;
- if (cfqd->busy_queues > 1) {
- /*
- * So we have dispatched before in this round, if the
- * next queue has idling enabled (must be sync), don't
- * allow it service until the previous have completed.
- */
- if (cfqd->rq_in_driver && cfq_cfqq_idle_window(cfqq) &&
- dispatched)
+ max_dispatch = cfqd->cfq_quantum;
+ if (cfq_class_idle(cfqq))
+ max_dispatch = 1;
+
+ if (cfqq->dispatched >= max_dispatch) {
+ if (cfqd->busy_queues > 1)
break;
- if (cfqq->dispatched >= cfqd->cfq_quantum)
+ if (cfqq->dispatched >= 4 * max_dispatch)
break;
}
+ if (cfqd->sync_flight && !cfq_cfqq_sync(cfqq))
+ break;
+
cfq_clear_cfqq_must_dispatch(cfqq);
cfq_clear_cfqq_wait_request(cfqq);
del_timer(&cfqd->idle_slice_timer);
- max_dispatch = cfqd->cfq_quantum;
- if (cfq_class_idle(cfqq))
- max_dispatch = 1;
-
dispatched += __cfq_dispatch_requests(cfqd, cfqq, max_dispatch);
}
cfq_schedule_dispatch(cfqd);
}
- /*
- * it's on the empty list and still hashed
- */
- hlist_del(&cfqq->cfq_hash);
kmem_cache_free(cfq_pool, cfqq);
}
-static struct cfq_queue *
-__cfq_find_cfq_hash(struct cfq_data *cfqd, unsigned int key, unsigned int prio,
- const int hashval)
-{
- struct hlist_head *hash_list = &cfqd->cfq_hash[hashval];
- struct hlist_node *entry;
- struct cfq_queue *__cfqq;
-
- hlist_for_each_entry(__cfqq, entry, hash_list, cfq_hash) {
- const unsigned short __p = IOPRIO_PRIO_VALUE(__cfqq->org_ioprio_class, __cfqq->org_ioprio);
-
- if (__cfqq->key == key && (__p == prio || !prio))
- return __cfqq;
- }
-
- return NULL;
-}
-
-static struct cfq_queue *
-cfq_find_cfq_hash(struct cfq_data *cfqd, unsigned int key, unsigned short prio)
-{
- return __cfq_find_cfq_hash(cfqd, key, prio, hash_long(key, CFQ_QHASH_SHIFT));
-}
-
static void cfq_free_io_context(struct io_context *ioc)
{
struct cfq_io_context *__cic;
struct rb_node *n;
int freed = 0;
+ ioc->ioc_data = NULL;
+
while ((n = rb_first(&ioc->cic_root)) != NULL) {
__cic = rb_entry(n, struct cfq_io_context, rb_node);
rb_erase(&__cic->rb_node, &ioc->cic_root);
struct cfq_io_context *__cic;
struct rb_node *n;
+ ioc->ioc_data = NULL;
+
/*
* put the reference this task is holding to the various queues
*/
-
n = rb_first(&ioc->cic_root);
while (n != NULL) {
__cic = rb_entry(n, struct cfq_io_context, rb_node);
{
struct cfq_io_context *cic;
- cic = kmem_cache_alloc_node(cfq_ioc_pool, gfp_mask, cfqd->queue->node);
+ cic = kmem_cache_alloc_node(cfq_ioc_pool, gfp_mask | __GFP_ZERO,
+ cfqd->queue->node);
if (cic) {
- memset(cic, 0, sizeof(*cic));
cic->last_end_request = jiffies;
INIT_LIST_HEAD(&cic->queue_list);
cic->dtor = cfq_free_io_context;
cfqq = cic->cfqq[ASYNC];
if (cfqq) {
struct cfq_queue *new_cfqq;
- new_cfqq = cfq_get_queue(cfqd, CFQ_KEY_ASYNC, cic->ioc->task,
+ new_cfqq = cfq_get_queue(cfqd, ASYNC, cic->ioc->task,
GFP_ATOMIC);
if (new_cfqq) {
cic->cfqq[ASYNC] = new_cfqq;
}
static struct cfq_queue *
-cfq_get_queue(struct cfq_data *cfqd, unsigned int key, struct task_struct *tsk,
- gfp_t gfp_mask)
+cfq_find_alloc_queue(struct cfq_data *cfqd, int is_sync,
+ struct task_struct *tsk, gfp_t gfp_mask)
{
- const int hashval = hash_long(key, CFQ_QHASH_SHIFT);
struct cfq_queue *cfqq, *new_cfqq = NULL;
- unsigned short ioprio;
+ struct cfq_io_context *cic;
retry:
- ioprio = tsk->ioprio;
- cfqq = __cfq_find_cfq_hash(cfqd, key, ioprio, hashval);
+ cic = cfq_cic_rb_lookup(cfqd, tsk->io_context);
+ /* cic always exists here */
+ cfqq = cic_to_cfqq(cic, is_sync);
if (!cfqq) {
if (new_cfqq) {
* free memory.
*/
spin_unlock_irq(cfqd->queue->queue_lock);
- new_cfqq = kmem_cache_alloc_node(cfq_pool, gfp_mask|__GFP_NOFAIL, cfqd->queue->node);
+ new_cfqq = kmem_cache_alloc_node(cfq_pool,
+ gfp_mask | __GFP_NOFAIL | __GFP_ZERO,
+ cfqd->queue->node);
spin_lock_irq(cfqd->queue->queue_lock);
goto retry;
} else {
- cfqq = kmem_cache_alloc_node(cfq_pool, gfp_mask, cfqd->queue->node);
+ cfqq = kmem_cache_alloc_node(cfq_pool,
+ gfp_mask | __GFP_ZERO,
+ cfqd->queue->node);
if (!cfqq)
goto out;
}
- memset(cfqq, 0, sizeof(*cfqq));
-
- INIT_HLIST_NODE(&cfqq->cfq_hash);
RB_CLEAR_NODE(&cfqq->rb_node);
INIT_LIST_HEAD(&cfqq->fifo);
- cfqq->key = key;
- hlist_add_head(&cfqq->cfq_hash, &cfqd->cfq_hash[hashval]);
atomic_set(&cfqq->ref, 0);
cfqq->cfqd = cfqd;
- if (key != CFQ_KEY_ASYNC)
+ if (is_sync) {
cfq_mark_cfqq_idle_window(cfqq);
+ cfq_mark_cfqq_sync(cfqq);
+ }
cfq_mark_cfqq_prio_changed(cfqq);
cfq_mark_cfqq_queue_new(cfqq);
+
cfq_init_prio_data(cfqq);
}
if (new_cfqq)
kmem_cache_free(cfq_pool, new_cfqq);
- atomic_inc(&cfqq->ref);
out:
WARN_ON((gfp_mask & __GFP_WAIT) && !cfqq);
return cfqq;
}
+static struct cfq_queue *
+cfq_get_queue(struct cfq_data *cfqd, int is_sync, struct task_struct *tsk,
+ gfp_t gfp_mask)
+{
+ const int ioprio = task_ioprio(tsk);
+ struct cfq_queue *cfqq = NULL;
+
+ if (!is_sync)
+ cfqq = cfqd->async_cfqq[ioprio];
+ if (!cfqq)
+ cfqq = cfq_find_alloc_queue(cfqd, is_sync, tsk, gfp_mask);
+
+ /*
+ * pin the queue now that it's allocated, scheduler exit will prune it
+ */
+ if (!is_sync && !cfqd->async_cfqq[ioprio]) {
+ atomic_inc(&cfqq->ref);
+ cfqd->async_cfqq[ioprio] = cfqq;
+ }
+
+ atomic_inc(&cfqq->ref);
+ return cfqq;
+}
+
/*
* We drop cfq io contexts lazily, so we may find a dead one.
*/
cfq_drop_dead_cic(struct io_context *ioc, struct cfq_io_context *cic)
{
WARN_ON(!list_empty(&cic->queue_list));
+
+ if (ioc->ioc_data == cic)
+ ioc->ioc_data = NULL;
+
rb_erase(&cic->rb_node, &ioc->cic_root);
kmem_cache_free(cfq_ioc_pool, cic);
elv_ioc_count_dec(ioc_count);
struct cfq_io_context *cic;
void *k, *key = cfqd;
+ if (unlikely(!ioc))
+ return NULL;
+
+ /*
+ * we maintain a last-hit cache, to avoid browsing over the tree
+ */
+ cic = ioc->ioc_data;
+ if (cic && cic->key == cfqd)
+ return cic;
+
restart:
n = ioc->cic_root.rb_node;
while (n) {
n = n->rb_left;
else if (key > k)
n = n->rb_right;
- else
+ else {
+ ioc->ioc_data = cic;
return cic;
+ }
}
return NULL;
cfq_update_idle_window(struct cfq_data *cfqd, struct cfq_queue *cfqq,
struct cfq_io_context *cic)
{
- int enable_idle = cfq_cfqq_idle_window(cfqq);
+ int enable_idle;
+
+ if (!cfq_cfqq_sync(cfqq))
+ return;
+
+ enable_idle = cfq_cfqq_idle_window(cfqq);
if (!cic->ioc->task || !cfqd->cfq_slice_idle ||
(cfqd->hw_tag && CIC_SEEKY(cic)))
cfqd->rq_in_driver--;
cfqq->dispatched--;
+ if (cfq_cfqq_sync(cfqq))
+ cfqd->sync_flight--;
+
if (!cfq_class_idle(cfqq))
cfqd->last_end_request = now;
{
struct cfq_data *cfqd = q->elevator->elevator_data;
struct task_struct *tsk = current;
+ struct cfq_io_context *cic;
struct cfq_queue *cfqq;
- unsigned int key;
-
- key = cfq_queue_pid(tsk, rw, rw & REQ_RW_SYNC);
/*
* don't force setup of a queue from here, as a call to may_queue
* so just lookup a possibly existing queue, or return 'may queue'
* if that fails
*/
- cfqq = cfq_find_cfq_hash(cfqd, key, tsk->ioprio);
+ cic = cfq_cic_rb_lookup(cfqd, tsk->io_context);
+ if (!cic)
+ return ELV_MQUEUE_MAY;
+
+ cfqq = cic_to_cfqq(cic, rw & REQ_RW_SYNC);
if (cfqq) {
cfq_init_prio_data(cfqq);
cfq_prio_boost(cfqq);
struct cfq_io_context *cic;
const int rw = rq_data_dir(rq);
const int is_sync = rq_is_sync(rq);
- pid_t key = cfq_queue_pid(tsk, rw, is_sync);
struct cfq_queue *cfqq;
unsigned long flags;
if (!cic)
goto queue_fail;
- if (!cic->cfqq[is_sync]) {
- cfqq = cfq_get_queue(cfqd, key, tsk, gfp_mask);
+ cfqq = cic_to_cfqq(cic, is_sync);
+ if (!cfqq) {
+ cfqq = cfq_get_queue(cfqd, is_sync, tsk, gfp_mask);
+
if (!cfqq)
goto queue_fail;
- cic->cfqq[is_sync] = cfqq;
- } else
- cfqq = cic->cfqq[is_sync];
+ cic_set_cfqq(cic, cfqq, is_sync);
+ }
cfqq->allocated[rw]++;
cfq_clear_cfqq_must_alloc(cfqq);
{
struct cfq_data *cfqd = e->elevator_data;
request_queue_t *q = cfqd->queue;
+ int i;
cfq_shutdown_timer_wq(cfqd);
__cfq_exit_single_io_context(cfqd, cic);
}
+ /*
+ * Put the async queues
+ */
+ for (i = 0; i < IOPRIO_BE_NR; i++)
+ if (cfqd->async_cfqq[i])
+ cfq_put_queue(cfqd->async_cfqq[i]);
+
spin_unlock_irq(q->queue_lock);
cfq_shutdown_timer_wq(cfqd);
- kfree(cfqd->cfq_hash);
kfree(cfqd);
}
static void *cfq_init_queue(request_queue_t *q)
{
struct cfq_data *cfqd;
- int i;
- cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL, q->node);
+ cfqd = kmalloc_node(sizeof(*cfqd), GFP_KERNEL | __GFP_ZERO, q->node);
if (!cfqd)
return NULL;
- memset(cfqd, 0, sizeof(*cfqd));
-
cfqd->service_tree = CFQ_RB_ROOT;
INIT_LIST_HEAD(&cfqd->cic_list);
- cfqd->cfq_hash = kmalloc_node(sizeof(struct hlist_head) * CFQ_QHASH_ENTRIES, GFP_KERNEL, q->node);
- if (!cfqd->cfq_hash)
- goto out_free;
-
- for (i = 0; i < CFQ_QHASH_ENTRIES; i++)
- INIT_HLIST_HEAD(&cfqd->cfq_hash[i]);
-
cfqd->queue = q;
init_timer(&cfqd->idle_slice_timer);
cfqd->cfq_slice_idle = cfq_slice_idle;
return cfqd;
-out_free:
- kfree(cfqd);
- return NULL;
}
static void cfq_slab_kill(void)
static int __init cfq_slab_setup(void)
{
- cfq_pool = kmem_cache_create("cfq_pool", sizeof(struct cfq_queue), 0, 0,
- NULL, NULL);
+ cfq_pool = KMEM_CACHE(cfq_queue, 0);
if (!cfq_pool)
goto fail;
- cfq_ioc_pool = kmem_cache_create("cfq_ioc_pool",
- sizeof(struct cfq_io_context), 0, 0, NULL, NULL);
+ cfq_ioc_pool = KMEM_CACHE(cfq_io_context, 0);
if (!cfq_ioc_pool)
goto fail;