/* time when queue got scheduled in to dispatch first request. */
unsigned long dispatch_start;
+ unsigned int allocated_slice;
/* time when first request from queue completed and slice started. */
unsigned long slice_start;
unsigned long slice_end;
struct cfq_rb_root *service_tree;
struct cfq_queue *new_cfqq;
struct cfq_group *cfqg;
+ /* Sectors dispatched in current dispatch round */
+ unsigned long nr_sectors;
};
/*
unsigned long saved_workload_slice;
enum wl_type_t saved_workload;
enum wl_prio_t saved_serving_prio;
+ struct blkio_group blkg;
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+ struct hlist_node cfqd_node;
+ atomic_t ref;
+#endif
};
/*
struct cfq_queue oom_cfqq;
unsigned long last_end_sync_rq;
+
+ /* List of cfq groups being managed on this device*/
+ struct hlist_head cfqg_list;
};
+static struct cfq_group *cfq_get_next_cfqg(struct cfq_data *cfqd);
+
static struct cfq_rb_root *service_tree_for(struct cfq_group *cfqg,
enum wl_prio_t prio,
enum wl_type_t type,
CFQ_CFQQ_FLAG_sync, /* synchronous queue */
CFQ_CFQQ_FLAG_coop, /* cfqq is shared */
CFQ_CFQQ_FLAG_deep, /* sync cfqq experienced large depth */
+ CFQ_CFQQ_FLAG_wait_busy, /* Waiting for next request */
+ CFQ_CFQQ_FLAG_wait_busy_done, /* Got new request. Expire the queue */
};
#define CFQ_CFQQ_FNS(name) \
CFQ_CFQQ_FNS(sync);
CFQ_CFQQ_FNS(coop);
CFQ_CFQQ_FNS(deep);
+CFQ_CFQQ_FNS(wait_busy);
+CFQ_CFQQ_FNS(wait_busy_done);
#undef CFQ_CFQQ_FNS
+#ifdef CONFIG_DEBUG_CFQ_IOSCHED
+#define cfq_log_cfqq(cfqd, cfqq, fmt, args...) \
+ blk_add_trace_msg((cfqd)->queue, "cfq%d%c %s " fmt, (cfqq)->pid, \
+ cfq_cfqq_sync((cfqq)) ? 'S' : 'A', \
+ blkg_path(&(cfqq)->cfqg->blkg), ##args);
+
+#define cfq_log_cfqg(cfqd, cfqg, fmt, args...) \
+ blk_add_trace_msg((cfqd)->queue, "%s " fmt, \
+ blkg_path(&(cfqg)->blkg), ##args); \
+
+#else
#define cfq_log_cfqq(cfqd, cfqq, fmt, args...) \
blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args)
+#define cfq_log_cfqg(cfqd, cfqg, fmt, args...) do {} while (0);
+#endif
#define cfq_log(cfqd, fmt, args...) \
blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)
}
cfqq->slice_start = jiffies;
cfqq->slice_end = jiffies + slice;
+ cfqq->allocated_slice = slice;
cfq_log_cfqq(cfqd, cfqq, "set_slice=%lu", cfqq->slice_end - jiffies);
}
if (cfqg->nr_cfqq)
return;
+ cfq_log_cfqg(cfqd, cfqg, "del_from_rr group");
cfqg->on_st = false;
cfqd->nr_groups--;
st->total_weight -= cfqg->weight;
if (!RB_EMPTY_NODE(&cfqg->rb_node))
cfq_rb_erase(&cfqg->rb_node, st);
cfqg->saved_workload_slice = 0;
+ blkiocg_update_blkio_group_dequeue_stats(&cfqg->blkg, 1);
}
static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
{
- unsigned int slice_used, allocated_slice;
+ unsigned int slice_used;
/*
* Queue got expired before even a single request completed or
1);
} else {
slice_used = jiffies - cfqq->slice_start;
- allocated_slice = cfqq->slice_end - cfqq->slice_start;
- if (slice_used > allocated_slice)
- slice_used = allocated_slice;
+ if (slice_used > cfqq->allocated_slice)
+ slice_used = cfqq->allocated_slice;
}
- cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u", slice_used);
+ cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u sect=%lu", slice_used,
+ cfqq->nr_sectors);
return slice_used;
}
cfqg->saved_serving_prio = cfqd->serving_prio;
} else
cfqg->saved_workload_slice = 0;
+
+ cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime,
+ st->min_vdisktime);
+ blkiocg_update_blkio_group_stats(&cfqg->blkg, used_sl,
+ cfqq->nr_sectors);
+}
+
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+static inline struct cfq_group *cfqg_of_blkg(struct blkio_group *blkg)
+{
+ if (blkg)
+ return container_of(blkg, struct cfq_group, blkg);
+ return NULL;
+}
+
+void
+cfq_update_blkio_group_weight(struct blkio_group *blkg, unsigned int weight)
+{
+ cfqg_of_blkg(blkg)->weight = weight;
+}
+
+static struct cfq_group *
+cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
+{
+ struct blkio_cgroup *blkcg = cgroup_to_blkio_cgroup(cgroup);
+ struct cfq_group *cfqg = NULL;
+ void *key = cfqd;
+ int i, j;
+ struct cfq_rb_root *st;
+ struct backing_dev_info *bdi = &cfqd->queue->backing_dev_info;
+ unsigned int major, minor;
+
+ /* Do we need to take this reference */
+ if (!css_tryget(&blkcg->css))
+ return NULL;;
+
+ cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
+ if (cfqg || !create)
+ goto done;
+
+ cfqg = kzalloc_node(sizeof(*cfqg), GFP_ATOMIC, cfqd->queue->node);
+ if (!cfqg)
+ goto done;
+
+ cfqg->weight = blkcg->weight;
+ for_each_cfqg_st(cfqg, i, j, st)
+ *st = CFQ_RB_ROOT;
+ RB_CLEAR_NODE(&cfqg->rb_node);
+
+ /*
+ * Take the initial reference that will be released on destroy
+ * This can be thought of a joint reference by cgroup and
+ * elevator which will be dropped by either elevator exit
+ * or cgroup deletion path depending on who is exiting first.
+ */
+ atomic_set(&cfqg->ref, 1);
+
+ /* Add group onto cgroup list */
+ sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+ blkiocg_add_blkio_group(blkcg, &cfqg->blkg, (void *)cfqd,
+ MKDEV(major, minor));
+
+ /* Add group on cfqd list */
+ hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
+
+done:
+ css_put(&blkcg->css);
+ return cfqg;
+}
+
+/*
+ * Search for the cfq group current task belongs to. If create = 1, then also
+ * create the cfq group if it does not exist. request_queue lock must be held.
+ */
+static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
+{
+ struct cgroup *cgroup;
+ struct cfq_group *cfqg = NULL;
+
+ rcu_read_lock();
+ cgroup = task_cgroup(current, blkio_subsys_id);
+ cfqg = cfq_find_alloc_cfqg(cfqd, cgroup, create);
+ if (!cfqg && create)
+ cfqg = &cfqd->root_group;
+ rcu_read_unlock();
+ return cfqg;
+}
+
+static void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg)
+{
+ /* Currently, all async queues are mapped to root group */
+ if (!cfq_cfqq_sync(cfqq))
+ cfqg = &cfqq->cfqd->root_group;
+
+ cfqq->cfqg = cfqg;
+ /* cfqq reference on cfqg */
+ atomic_inc(&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))
+ return;
+ for_each_cfqg_st(cfqg, i, j, st)
+ BUG_ON(!RB_EMPTY_ROOT(&st->rb) || st->active != NULL);
+ kfree(cfqg);
+}
+
+static void cfq_destroy_cfqg(struct cfq_data *cfqd, struct cfq_group *cfqg)
+{
+ /* Something wrong if we are trying to remove same group twice */
+ BUG_ON(hlist_unhashed(&cfqg->cfqd_node));
+
+ hlist_del_init(&cfqg->cfqd_node);
+
+ /*
+ * Put the reference taken at the time of creation so that when all
+ * queues are gone, group can be destroyed.
+ */
+ cfq_put_cfqg(cfqg);
+}
+
+static void cfq_release_cfq_groups(struct cfq_data *cfqd)
+{
+ struct hlist_node *pos, *n;
+ struct cfq_group *cfqg;
+
+ hlist_for_each_entry_safe(cfqg, pos, n, &cfqd->cfqg_list, cfqd_node) {
+ /*
+ * If cgroup removal path got to blk_group first and removed
+ * it from cgroup list, then it will take care of destroying
+ * cfqg also.
+ */
+ if (!blkiocg_del_blkio_group(&cfqg->blkg))
+ cfq_destroy_cfqg(cfqd, cfqg);
+ }
+}
+
+/*
+ * Blk cgroup controller notification saying that blkio_group object is being
+ * delinked as associated cgroup object is going away. That also means that
+ * no new IO will come in this group. So get rid of this group as soon as
+ * any pending IO in the group is finished.
+ *
+ * This function is called under rcu_read_lock(). key is the rcu protected
+ * pointer. That means "key" is a valid cfq_data pointer as long as we are rcu
+ * read lock.
+ *
+ * "key" was fetched from blkio_group under blkio_cgroup->lock. That means
+ * it should not be NULL as even if elevator was exiting, cgroup deltion
+ * path got to it first.
+ */
+void cfq_unlink_blkio_group(void *key, struct blkio_group *blkg)
+{
+ unsigned long flags;
+ struct cfq_data *cfqd = key;
+
+ spin_lock_irqsave(cfqd->queue->queue_lock, flags);
+ cfq_destroy_cfqg(cfqd, cfqg_of_blkg(blkg));
+ spin_unlock_irqrestore(cfqd->queue->queue_lock, flags);
}
+#else /* GROUP_IOSCHED */
+static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
+{
+ return &cfqd->root_group;
+}
+static inline void
+cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg) {
+ cfqq->cfqg = cfqg;
+}
+
+static void cfq_release_cfq_groups(struct cfq_data *cfqd) {}
+static inline void cfq_put_cfqg(struct cfq_group *cfqg) {}
+
+#endif /* GROUP_IOSCHED */
+
/*
* The cfqd->service_trees holds all pending cfq_queue's that have
* requests waiting to be processed. It is sorted in the order that
struct cfq_io_context *cic;
struct cfq_queue *cfqq;
+ /* Deny merge if bio and rq don't belong to same cfq group */
+ if ((RQ_CFQQ(rq))->cfqg != cfq_get_cfqg(cfqd, 0))
+ return false;
/*
* Disallow merge of a sync bio into an async request.
*/
cfq_log_cfqq(cfqd, cfqq, "set_active");
cfqq->slice_start = 0;
cfqq->dispatch_start = jiffies;
+ cfqq->allocated_slice = 0;
cfqq->slice_end = 0;
cfqq->slice_dispatch = 0;
+ cfqq->nr_sectors = 0;
cfq_clear_cfqq_wait_request(cfqq);
cfq_clear_cfqq_must_dispatch(cfqq);
del_timer(&cfqd->idle_slice_timer);
cfq_clear_cfqq_wait_request(cfqq);
+ cfq_clear_cfqq_wait_busy(cfqq);
+ cfq_clear_cfqq_wait_busy_done(cfqq);
/*
* store what was left of this slice, if the queue idled/timed out
static struct cfq_queue *cfq_get_next_queue_forced(struct cfq_data *cfqd)
{
- struct cfq_group *cfqg = &cfqd->root_group;
+ struct cfq_group *cfqg;
struct cfq_queue *cfqq;
int i, j;
struct cfq_rb_root *st;
if (!cfqd->rq_queued)
return NULL;
+ cfqg = cfq_get_next_cfqg(cfqd);
+ if (!cfqg)
+ return NULL;
+
for_each_cfqg_st(cfqg, i, j, st)
if ((cfqq = cfq_rb_first(st)) != NULL)
return cfqq;
if (!cfqq)
return NULL;
+ /* If new queue belongs to different cfq_group, don't choose it */
+ if (cur_cfqq->cfqg != cfqq->cfqg)
+ return NULL;
+
/*
* It only makes sense to merge sync queues.
*/
if (cfq_cfqq_sync(cfqq))
cfqd->sync_flight++;
+ cfqq->nr_sectors += blk_rq_sectors(rq);
}
/*
/*
* The active queue has run out of time, expire it and select new.
*/
- if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq))
+ if ((cfq_slice_used(cfqq) || cfq_cfqq_wait_busy_done(cfqq))
+ && !cfq_cfqq_must_dispatch(cfqq))
goto expire;
/*
* task holds one reference to the queue, dropped when task exits. each rq
* in-flight on this queue also holds a reference, dropped when rq is freed.
*
+ * Each cfq queue took a reference on the parent group. Drop it now.
* queue lock must be held here.
*/
static void cfq_put_queue(struct cfq_queue *cfqq)
{
struct cfq_data *cfqd = cfqq->cfqd;
+ struct cfq_group *cfqg;
BUG_ON(atomic_read(&cfqq->ref) <= 0);
cfq_log_cfqq(cfqd, cfqq, "put_queue");
BUG_ON(rb_first(&cfqq->sort_list));
BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
+ cfqg = cfqq->cfqg;
if (unlikely(cfqd->active_queue == cfqq)) {
__cfq_slice_expired(cfqd, cfqq, 0);
BUG_ON(cfq_cfqq_on_rr(cfqq));
kmem_cache_free(cfq_pool, cfqq);
+ cfq_put_cfqg(cfqg);
}
/*
cfqq->pid = pid;
}
-static void cfq_link_cfqq_cfqg(struct cfq_queue *cfqq, struct cfq_group *cfqg)
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+static void changed_cgroup(struct io_context *ioc, struct cfq_io_context *cic)
{
- cfqq->cfqg = cfqg;
+ struct cfq_queue *sync_cfqq = cic_to_cfqq(cic, 1);
+ struct cfq_data *cfqd = cic->key;
+ unsigned long flags;
+ struct request_queue *q;
+
+ if (unlikely(!cfqd))
+ return;
+
+ q = cfqd->queue;
+
+ spin_lock_irqsave(q->queue_lock, flags);
+
+ if (sync_cfqq) {
+ /*
+ * Drop reference to sync queue. A new sync queue will be
+ * assigned in new group upon arrival of a fresh request.
+ */
+ cfq_log_cfqq(cfqd, sync_cfqq, "changed cgroup");
+ cic_set_cfqq(cic, NULL, 1);
+ cfq_put_queue(sync_cfqq);
+ }
+
+ spin_unlock_irqrestore(q->queue_lock, flags);
}
-static struct cfq_group *cfq_get_cfqg(struct cfq_data *cfqd, int create)
+static void cfq_ioc_set_cgroup(struct io_context *ioc)
{
- return &cfqd->root_group;
+ call_for_each_cic(ioc, changed_cgroup);
+ ioc->cgroup_changed = 0;
}
+#endif /* CONFIG_CFQ_GROUP_IOSCHED */
static struct cfq_queue *
cfq_find_alloc_queue(struct cfq_data *cfqd, bool is_sync,
if (unlikely(ioc->ioprio_changed))
cfq_ioc_set_ioprio(ioc);
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+ if (unlikely(ioc->cgroup_changed))
+ cfq_ioc_set_cgroup(ioc);
+#endif
return cic;
err_free:
cfq_cic_free(cic);
if (!cfqq)
return false;
- if (cfq_slice_used(cfqq))
- return true;
-
if (cfq_class_idle(new_cfqq))
return false;
if (cfq_class_idle(cfqq))
return true;
- /* Allow preemption only if we are idling on sync-noidle tree */
- if (cfqd->serving_type == SYNC_NOIDLE_WORKLOAD &&
- cfqq_type(new_cfqq) == SYNC_NOIDLE_WORKLOAD &&
- new_cfqq->service_tree->count == 2 &&
- RB_EMPTY_ROOT(&cfqq->sort_list))
- return true;
-
/*
* if the new request is sync, but the currently running queue is
* not, let the sync request have priority.
if (rq_is_sync(rq) && !cfq_cfqq_sync(cfqq))
return true;
+ if (new_cfqq->cfqg != cfqq->cfqg)
+ return false;
+
+ if (cfq_slice_used(cfqq))
+ return true;
+
+ /* Allow preemption only if we are idling on sync-noidle tree */
+ if (cfqd->serving_type == SYNC_NOIDLE_WORKLOAD &&
+ cfqq_type(new_cfqq) == SYNC_NOIDLE_WORKLOAD &&
+ new_cfqq->service_tree->count == 2 &&
+ RB_EMPTY_ROOT(&cfqq->sort_list))
+ return true;
+
/*
* So both queues are sync. Let the new request get disk time if
* it's a metadata request and the current queue is doing regular IO.
cfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
if (cfqq == cfqd->active_queue) {
+ if (cfq_cfqq_wait_busy(cfqq)) {
+ cfq_clear_cfqq_wait_busy(cfqq);
+ cfq_mark_cfqq_wait_busy_done(cfqq);
+ }
/*
* Remember that we saw a request from this process, but
* don't start queuing just yet. Otherwise we risk seeing lots
unsigned long now;
now = jiffies;
- cfq_log_cfqq(cfqd, cfqq, "complete");
+ cfq_log_cfqq(cfqd, cfqq, "complete rqnoidle %d", !!rq_noidle(rq));
cfq_update_hw_tag(cfqd);
cfq_set_prio_slice(cfqd, cfqq);
cfq_clear_cfqq_slice_new(cfqq);
}
+
+ /*
+ * If this queue consumed its slice and this is last queue
+ * in the group, wait for next request before we expire
+ * the queue
+ */
+ if (cfq_slice_used(cfqq) && cfqq->cfqg->nr_cfqq == 1) {
+ cfqq->slice_end = jiffies + cfqd->cfq_slice_idle;
+ cfq_mark_cfqq_wait_busy(cfqq);
+ }
+
/*
* Idling is not enabled on:
* - expired queues
}
cfq_put_async_queues(cfqd);
+ cfq_release_cfq_groups(cfqd);
+ blkiocg_del_blkio_group(&cfqd->root_group.blkg);
spin_unlock_irq(q->queue_lock);
cfq_shutdown_timer_wq(cfqd);
+ /* Wait for cfqg->blkg->key accessors to exit their grace periods. */
+ synchronize_rcu();
kfree(cfqd);
}
/* Give preference to root group over other groups */
cfqg->weight = 2*BLKIO_WEIGHT_DEFAULT;
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+ /*
+ * 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);
+ blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg, (void *)cfqd,
+ 0);
+#endif
/*
* Not strictly needed (since RB_ROOT just clears the node and we
* zeroed cfqd on alloc), but better be safe in case someone decides