X-Git-Url: http://ftp.safe.ca/?p=safe%2Fjmp%2Flinux-2.6;a=blobdiff_plain;f=block%2Fcfq-iosched.c;h=ee130f14d1fc9228214fb7d0acbd3d4f4a85acdd;hp=7d345e772d88120b5f4065f1f0a4d717a777e9e9;hb=e071041be037eca208b62b84469a06bdfc692bea;hpb=220841906fccafaf4094e87bdb6d252e20cf8c7c

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 7d345e7..ee130f1 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -117,6 +117,7 @@ struct cfq_queue {
 
 	/* 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;
@@ -143,6 +144,7 @@ struct cfq_queue {
 	struct cfq_rb_root *service_tree;
 	struct cfq_queue *new_cfqq;
 	struct cfq_group *cfqg;
+	struct cfq_group *orig_cfqg;
 	/* Sectors dispatched in current dispatch round */
 	unsigned long nr_sectors;
 };
@@ -206,8 +208,6 @@ struct cfq_data {
 	/* Root service tree for cfq_groups */
 	struct cfq_rb_root grp_service_tree;
 	struct cfq_group root_group;
-	/* Number of active cfq groups on group service tree */
-	int nr_groups;
 
 	/*
 	 * The priority currently being served
@@ -272,6 +272,7 @@ struct cfq_data {
 	unsigned int cfq_slice_async_rq;
 	unsigned int cfq_slice_idle;
 	unsigned int cfq_latency;
+	unsigned int cfq_group_isolation;
 
 	struct list_head cic_list;
 
@@ -280,18 +281,18 @@ struct cfq_data {
 	 */
 	struct cfq_queue oom_cfqq;
 
-	unsigned long last_end_sync_rq;
+	unsigned long last_delayed_sync;
 
 	/* List of cfq groups being managed on this device*/
 	struct hlist_head cfqg_list;
+	struct rcu_head rcu;
 };
 
 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,
-					    struct cfq_data *cfqd)
+					    enum wl_type_t type)
 {
 	if (!cfqg)
 		return NULL;
@@ -314,6 +315,7 @@ enum cfqq_state_flags {
 	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 */
 };
 
 #define CFQ_CFQQ_FNS(name)						\
@@ -341,6 +343,7 @@ CFQ_CFQQ_FNS(slice_new);
 CFQ_CFQQ_FNS(sync);
 CFQ_CFQQ_FNS(coop);
 CFQ_CFQQ_FNS(deep);
+CFQ_CFQQ_FNS(wait_busy);
 #undef CFQ_CFQQ_FNS
 
 #ifdef CONFIG_DEBUG_CFQ_IOSCHED
@@ -403,6 +406,13 @@ static inline int cfq_group_busy_queues_wl(enum wl_prio_t wl,
 		+ cfqg->service_trees[wl][SYNC_WORKLOAD].count;
 }
 
+static inline int cfqg_busy_async_queues(struct cfq_data *cfqd,
+					struct cfq_group *cfqg)
+{
+	return cfqg->service_trees[RT_WORKLOAD][ASYNC_WORKLOAD].count
+		+ cfqg->service_trees[BE_WORKLOAD][ASYNC_WORKLOAD].count;
+}
+
 static void cfq_dispatch_insert(struct request_queue *, struct request *);
 static struct cfq_queue *cfq_get_queue(struct cfq_data *, bool,
 				       struct io_context *, gfp_t);
@@ -578,6 +588,7 @@ cfq_set_prio_slice(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	}
 	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);
 }
 
@@ -828,7 +839,6 @@ cfq_group_service_tree_add(struct cfq_data *cfqd, struct cfq_group *cfqg)
 
 	__cfq_group_service_tree_add(st, cfqg);
 	cfqg->on_st = true;
-	cfqd->nr_groups++;
 	st->total_weight += cfqg->weight;
 }
 
@@ -849,7 +859,6 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 
 	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);
@@ -859,7 +868,7 @@ cfq_group_service_tree_del(struct cfq_data *cfqd, struct cfq_group *cfqg)
 
 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
@@ -876,9 +885,8 @@ static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
 					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 sect=%lu", slice_used,
@@ -890,13 +898,19 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 				struct cfq_queue *cfqq)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
-	unsigned int used_sl;
+	unsigned int used_sl, charge_sl;
+	int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg)
+			- cfqg->service_tree_idle.count;
 
-	used_sl = cfq_cfqq_slice_usage(cfqq);
+	BUG_ON(nr_sync < 0);
+	used_sl = charge_sl = cfq_cfqq_slice_usage(cfqq);
+
+	if (!cfq_cfqq_sync(cfqq) && !nr_sync)
+		charge_sl = cfqq->allocated_slice;
 
 	/* Can't update vdisktime while group is on service tree */
 	cfq_rb_erase(&cfqg->rb_node, st);
-	cfqg->vdisktime += cfq_scale_slice(used_sl, cfqg);
+	cfqg->vdisktime += cfq_scale_slice(charge_sl, cfqg);
 	__cfq_group_service_tree_add(st, cfqg);
 
 	/* This group is being expired. Save the context */
@@ -922,6 +936,12 @@ static inline struct cfq_group *cfqg_of_blkg(struct blkio_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)
 {
@@ -934,7 +954,7 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 	unsigned int major, minor;
 
 	/* Do we need to take this reference */
-	if (!css_tryget(&blkcg->css))
+	if (!blkiocg_css_tryget(blkcg))
 		return NULL;;
 
 	cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
@@ -967,7 +987,7 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
 	hlist_add_head(&cfqg->cfqd_node, &cfqd->cfqg_list);
 
 done:
-	css_put(&blkcg->css);
+	blkiocg_css_put(blkcg);
 	return cfqg;
 }
 
@@ -1096,9 +1116,36 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	struct cfq_rb_root *service_tree;
 	int left;
 	int new_cfqq = 1;
+	int group_changed = 0;
+
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+	if (!cfqd->cfq_group_isolation
+	    && cfqq_type(cfqq) == SYNC_NOIDLE_WORKLOAD
+	    && cfqq->cfqg && cfqq->cfqg != &cfqd->root_group) {
+		/* Move this cfq to root group */
+		cfq_log_cfqq(cfqd, cfqq, "moving to root group");
+		if (!RB_EMPTY_NODE(&cfqq->rb_node))
+			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
+		cfqq->orig_cfqg = cfqq->cfqg;
+		cfqq->cfqg = &cfqd->root_group;
+		atomic_inc(&cfqd->root_group.ref);
+		group_changed = 1;
+	} else if (!cfqd->cfq_group_isolation
+		   && cfqq_type(cfqq) == SYNC_WORKLOAD && cfqq->orig_cfqg) {
+		/* cfqq is sequential now needs to go to its original group */
+		BUG_ON(cfqq->cfqg != &cfqd->root_group);
+		if (!RB_EMPTY_NODE(&cfqq->rb_node))
+			cfq_group_service_tree_del(cfqd, cfqq->cfqg);
+		cfq_put_cfqg(cfqq->cfqg);
+		cfqq->cfqg = cfqq->orig_cfqg;
+		cfqq->orig_cfqg = NULL;
+		group_changed = 1;
+		cfq_log_cfqq(cfqd, cfqq, "moved to origin group");
+	}
+#endif
 
 	service_tree = service_tree_for(cfqq->cfqg, cfqq_prio(cfqq),
-						cfqq_type(cfqq), cfqd);
+						cfqq_type(cfqq));
 	if (cfq_class_idle(cfqq)) {
 		rb_key = CFQ_IDLE_DELAY;
 		parent = rb_last(&service_tree->rb);
@@ -1166,7 +1213,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	rb_link_node(&cfqq->rb_node, parent, p);
 	rb_insert_color(&cfqq->rb_node, &service_tree->rb);
 	service_tree->count++;
-	if (add_front || !new_cfqq)
+	if ((add_front || !new_cfqq) && !group_changed)
 		return;
 	cfq_group_service_tree_add(cfqd, cfqq->cfqg);
 }
@@ -1486,6 +1533,7 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
 		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;
@@ -1515,6 +1563,7 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 		del_timer(&cfqd->idle_slice_timer);
 
 	cfq_clear_cfqq_wait_request(cfqq);
+	cfq_clear_cfqq_wait_busy(cfqq);
 
 	/*
 	 * store what was left of this slice, if the queue idled/timed out
@@ -1559,7 +1608,7 @@ static struct cfq_queue *cfq_get_next_queue(struct cfq_data *cfqd)
 {
 	struct cfq_rb_root *service_tree =
 		service_tree_for(cfqd->serving_group, cfqd->serving_prio,
-					cfqd->serving_type, cfqd);
+					cfqd->serving_type);
 
 	if (!cfqd->rq_queued)
 		return NULL;
@@ -1618,13 +1667,17 @@ static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
 #define CFQQ_SEEKY(cfqq)	((cfqq)->seek_mean > CFQQ_SEEK_THR)
 
 static inline int cfq_rq_close(struct cfq_data *cfqd, struct cfq_queue *cfqq,
-			       struct request *rq)
+			       struct request *rq, bool for_preempt)
 {
 	sector_t sdist = cfqq->seek_mean;
 
 	if (!sample_valid(cfqq->seek_samples))
 		sdist = CFQQ_SEEK_THR;
 
+	/* if seek_mean is big, using it as close criteria is meaningless */
+	if (sdist > CFQQ_SEEK_THR && !for_preempt)
+		sdist = CFQQ_SEEK_THR;
+
 	return cfq_dist_from_last(cfqd, rq) <= sdist;
 }
 
@@ -1652,7 +1705,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
 	 * will contain the closest sector.
 	 */
 	__cfqq = rb_entry(parent, struct cfq_queue, p_node);
-	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
+	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
 		return __cfqq;
 
 	if (blk_rq_pos(__cfqq->next_rq) < sector)
@@ -1663,7 +1716,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
 		return NULL;
 
 	__cfqq = rb_entry(node, struct cfq_queue, p_node);
-	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
+	if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq, false))
 		return __cfqq;
 
 	return NULL;
@@ -1690,6 +1743,12 @@ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
 		return NULL;
 
 	/*
+	 * Don't search priority tree if it's the only queue in the group.
+	 */
+	if (cur_cfqq->cfqg->nr_cfqq == 1)
+		return NULL;
+
+	/*
 	 * We should notice if some of the queues are cooperating, eg
 	 * working closely on the same area of the disk. In that case,
 	 * we can group them together and don't waste time idling.
@@ -1698,6 +1757,10 @@ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
 	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.
 	 */
@@ -1732,7 +1795,8 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 		return false;
 
 	/* We do for queues that were marked with idle window flag. */
-	if (cfq_cfqq_idle_window(cfqq))
+	if (cfq_cfqq_idle_window(cfqq) &&
+	   !(blk_queue_nonrot(cfqd->queue) && cfqd->hw_tag))
 		return true;
 
 	/*
@@ -1895,8 +1959,7 @@ static void cfq_setup_merge(struct cfq_queue *cfqq, struct cfq_queue *new_cfqq)
 }
 
 static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
-				struct cfq_group *cfqg, enum wl_prio_t prio,
-				bool prio_changed)
+				struct cfq_group *cfqg, enum wl_prio_t prio)
 {
 	struct cfq_queue *queue;
 	int i;
@@ -1904,24 +1967,9 @@ static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
 	unsigned long lowest_key = 0;
 	enum wl_type_t cur_best = SYNC_NOIDLE_WORKLOAD;
 
-	if (prio_changed) {
-		/*
-		 * When priorities switched, we prefer starting
-		 * from SYNC_NOIDLE (first choice), or just SYNC
-		 * over ASYNC
-		 */
-		if (service_tree_for(cfqg, prio, cur_best, cfqd)->count)
-			return cur_best;
-		cur_best = SYNC_WORKLOAD;
-		if (service_tree_for(cfqg, prio, cur_best, cfqd)->count)
-			return cur_best;
-
-		return ASYNC_WORKLOAD;
-	}
-
-	for (i = 0; i < 3; ++i) {
-		/* otherwise, select the one with lowest rb_key */
-		queue = cfq_rb_first(service_tree_for(cfqg, prio, i, cfqd));
+	for (i = 0; i <= SYNC_WORKLOAD; ++i) {
+		/* select the one with lowest rb_key */
+		queue = cfq_rb_first(service_tree_for(cfqg, prio, i));
 		if (queue &&
 		    (!key_valid || time_before(queue->rb_key, lowest_key))) {
 			lowest_key = queue->rb_key;
@@ -1935,8 +1983,6 @@ static enum wl_type_t cfq_choose_wl(struct cfq_data *cfqd,
 
 static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
 {
-	enum wl_prio_t previous_prio = cfqd->serving_prio;
-	bool prio_changed;
 	unsigned slice;
 	unsigned count;
 	struct cfq_rb_root *st;
@@ -1964,24 +2010,19 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
 	 * (SYNC, SYNC_NOIDLE, ASYNC), and to compute a workload
 	 * expiration time
 	 */
-	prio_changed = (cfqd->serving_prio != previous_prio);
-	st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type,
-				cfqd);
+	st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type);
 	count = st->count;
 
 	/*
-	 * If priority didn't change, check workload expiration,
-	 * and that we still have other queues ready
+	 * check workload expiration, and that we still have other queues ready
 	 */
-	if (!prio_changed && count &&
-	    !time_after(jiffies, cfqd->workload_expires))
+	if (count && !time_after(jiffies, cfqd->workload_expires))
 		return;
 
 	/* otherwise select new workload type */
 	cfqd->serving_type =
-		cfq_choose_wl(cfqd, cfqg, cfqd->serving_prio, prio_changed);
-	st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type,
-				cfqd);
+		cfq_choose_wl(cfqd, cfqg, cfqd->serving_prio);
+	st = service_tree_for(cfqg, cfqd->serving_prio, cfqd->serving_type);
 	count = st->count;
 
 	/*
@@ -1995,11 +2036,24 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
 		max_t(unsigned, cfqg->busy_queues_avg[cfqd->serving_prio],
 		      cfq_group_busy_queues_wl(cfqd->serving_prio, cfqd, cfqg));
 
-	if (cfqd->serving_type == ASYNC_WORKLOAD)
+	if (cfqd->serving_type == ASYNC_WORKLOAD) {
+		unsigned int tmp;
+
+		/*
+		 * Async queues are currently system wide. Just taking
+		 * proportion of queues with-in same group will lead to higher
+		 * async ratio system wide as generally root group is going
+		 * to have higher weight. A more accurate thing would be to
+		 * calculate system wide asnc/sync ratio.
+		 */
+		tmp = cfq_target_latency * cfqg_busy_async_queues(cfqd, cfqg);
+		tmp = tmp/cfqd->busy_queues;
+		slice = min_t(unsigned, slice, tmp);
+
 		/* async workload slice is scaled down according to
 		 * the sync/async slice ratio. */
 		slice = slice * cfqd->cfq_slice[0] / cfqd->cfq_slice[1];
-	else
+	} else
 		/* sync workload slice is at least 2 * cfq_slice_idle */
 		slice = max(slice, 2 * cfqd->cfq_slice_idle);
 
@@ -2032,7 +2086,9 @@ static void cfq_choose_cfqg(struct cfq_data *cfqd)
 		cfqd->workload_expires = jiffies + cfqg->saved_workload_slice;
 		cfqd->serving_type = cfqg->saved_workload;
 		cfqd->serving_prio = cfqg->saved_serving_prio;
-	}
+	} else
+		cfqd->workload_expires = jiffies - 1;
+
 	choose_service_tree(cfqd, cfqg);
 }
 
@@ -2050,13 +2106,35 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 
 	if (!cfqd->rq_queued)
 		return NULL;
+
 	/*
-	 * The active queue has run out of time, expire it and select new.
+	 * We were waiting for group to get backlogged. Expire the queue
 	 */
-	if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq))
+	if (cfq_cfqq_wait_busy(cfqq) && !RB_EMPTY_ROOT(&cfqq->sort_list))
 		goto expire;
 
 	/*
+	 * The active queue has run out of time, expire it and select new.
+	 */
+	if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq)) {
+		/*
+		 * If slice had not expired at the completion of last request
+		 * we might not have turned on wait_busy flag. Don't expire
+		 * the queue yet. Allow the group to get backlogged.
+		 *
+		 * The very fact that we have used the slice, that means we
+		 * have been idling all along on this queue and it should be
+		 * ok to wait for this request to complete.
+		 */
+		if (cfqq->cfqg->nr_cfqq == 1 && RB_EMPTY_ROOT(&cfqq->sort_list)
+		    && cfqq->dispatched && cfq_should_idle(cfqd, cfqq)) {
+			cfqq = NULL;
+			goto keep_queue;
+		} else
+			goto expire;
+	}
+
+	/*
 	 * The active queue has requests and isn't expired, allow it to
 	 * dispatch.
 	 */
@@ -2185,7 +2263,7 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	 * based on the last sync IO we serviced
 	 */
 	if (!cfq_cfqq_sync(cfqq) && cfqd->cfq_latency) {
-		unsigned long last_sync = jiffies - cfqd->last_end_sync_rq;
+		unsigned long last_sync = jiffies - cfqd->last_delayed_sync;
 		unsigned int depth;
 
 		depth = last_sync / cfqd->cfq_slice[1];
@@ -2289,7 +2367,7 @@ static int cfq_dispatch_requests(struct request_queue *q, int force)
 static void cfq_put_queue(struct cfq_queue *cfqq)
 {
 	struct cfq_data *cfqd = cfqq->cfqd;
-	struct cfq_group *cfqg;
+	struct cfq_group *cfqg, *orig_cfqg;
 
 	BUG_ON(atomic_read(&cfqq->ref) <= 0);
 
@@ -2300,6 +2378,7 @@ static void cfq_put_queue(struct cfq_queue *cfqq)
 	BUG_ON(rb_first(&cfqq->sort_list));
 	BUG_ON(cfqq->allocated[READ] + cfqq->allocated[WRITE]);
 	cfqg = cfqq->cfqg;
+	orig_cfqg = cfqq->orig_cfqg;
 
 	if (unlikely(cfqd->active_queue == cfqq)) {
 		__cfq_slice_expired(cfqd, cfqq, 0);
@@ -2309,6 +2388,8 @@ static void cfq_put_queue(struct cfq_queue *cfqq)
 	BUG_ON(cfq_cfqq_on_rr(cfqq));
 	kmem_cache_free(cfq_pool, cfqq);
 	cfq_put_cfqg(cfqg);
+	if (orig_cfqg)
+		cfq_put_cfqg(orig_cfqg);
 }
 
 /*
@@ -2601,6 +2682,41 @@ static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	cfqq->pid = pid;
 }
 
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+static void changed_cgroup(struct io_context *ioc, struct cfq_io_context *cic)
+{
+	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 void cfq_ioc_set_cgroup(struct io_context *ioc)
+{
+	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,
 		     struct io_context *ioc, gfp_t gfp_mask)
@@ -2833,6 +2949,10 @@ out:
 	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);
@@ -2950,21 +3070,17 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	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;
+	/*
+	 * Don't allow a non-RT request to preempt an ongoing RT cfqq timeslice.
+	 */
+	if (cfq_class_rt(cfqq) && !cfq_class_rt(new_cfqq))
+		return false;
 
 	/*
 	 * if the new request is sync, but the currently running queue is
@@ -2973,6 +3089,19 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	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.
@@ -2993,7 +3122,7 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
 	 * if this request is as-good as one we would expect from the
 	 * current cfqq, let it preempt
 	 */
-	if (cfq_rq_close(cfqd, cfqq, rq))
+	if (cfq_rq_close(cfqd, cfqq, rq, true))
 		return true;
 
 	return false;
@@ -3055,6 +3184,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE ||
 			    cfqd->busy_queues > 1) {
 				del_timer(&cfqd->idle_slice_timer);
+				cfq_clear_cfqq_wait_request(cfqq);
 				__blk_run_queue(cfqd->queue);
 			} else
 				cfq_mark_cfqq_must_dispatch(cfqq);
@@ -3123,6 +3253,35 @@ static void cfq_update_hw_tag(struct cfq_data *cfqd)
 		cfqd->hw_tag = 0;
 }
 
+static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	struct cfq_io_context *cic = cfqd->active_cic;
+
+	/* If there are other queues in the group, don't wait */
+	if (cfqq->cfqg->nr_cfqq > 1)
+		return false;
+
+	if (cfq_slice_used(cfqq))
+		return true;
+
+	/* if slice left is less than think time, wait busy */
+	if (cic && sample_valid(cic->ttime_samples)
+	    && (cfqq->slice_end - jiffies < cic->ttime_mean))
+		return true;
+
+	/*
+	 * If think times is less than a jiffy than ttime_mean=0 and above
+	 * will not be true. It might happen that slice has not expired yet
+	 * but will expire soon (4-5 ns) during select_queue(). To cover the
+	 * case where think time is less than a jiffy, mark the queue wait
+	 * busy if only 1 jiffy is left in the slice.
+	 */
+	if (cfqq->slice_end - jiffies == 1)
+		return true;
+
+	return false;
+}
+
 static void cfq_completed_request(struct request_queue *q, struct request *rq)
 {
 	struct cfq_queue *cfqq = RQ_CFQQ(rq);
@@ -3145,7 +3304,8 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 
 	if (sync) {
 		RQ_CIC(rq)->last_end_request = now;
-		cfqd->last_end_sync_rq = now;
+		if (!time_after(rq->start_time + cfqd->cfq_fifo_expire[1], now))
+			cfqd->last_delayed_sync = now;
 	}
 
 	/*
@@ -3159,6 +3319,16 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 			cfq_set_prio_slice(cfqd, cfqq);
 			cfq_clear_cfqq_slice_new(cfqq);
 		}
+
+		/*
+		 * Should we wait for next request to come in before we expire
+		 * the queue.
+		 */
+		if (cfq_should_wait_busy(cfqd, cfqq)) {
+			cfqq->slice_end = jiffies + cfqd->cfq_slice_idle;
+			cfq_mark_cfqq_wait_busy(cfqq);
+		}
+
 		/*
 		 * Idling is not enabled on:
 		 * - expired queues
@@ -3178,7 +3348,8 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 			 * only if we processed at least one !rq_noidle request
 			 */
 			if (cfqd->serving_type == SYNC_WORKLOAD
-			    || cfqd->noidle_tree_requires_idle)
+			    || cfqd->noidle_tree_requires_idle
+			    || cfqq->cfqg->nr_cfqq == 1)
 				cfq_arm_slice_timer(cfqd);
 		}
 	}
@@ -3463,6 +3634,11 @@ static void cfq_put_async_queues(struct cfq_data *cfqd)
 		cfq_put_queue(cfqd->async_idle_cfqq);
 }
 
+static void cfq_cfqd_free(struct rcu_head *head)
+{
+	kfree(container_of(head, struct cfq_data, rcu));
+}
+
 static void cfq_exit_queue(struct elevator_queue *e)
 {
 	struct cfq_data *cfqd = e->elevator_data;
@@ -3492,8 +3668,7 @@ static void cfq_exit_queue(struct elevator_queue *e)
 	cfq_shutdown_timer_wq(cfqd);
 
 	/* Wait for cfqg->blkg->key accessors to exit their grace periods. */
-	synchronize_rcu();
-	kfree(cfqd);
+	call_rcu(&cfqd->rcu, cfq_cfqd_free);
 }
 
 static void *cfq_init_queue(struct request_queue *q)
@@ -3565,8 +3740,14 @@ static void *cfq_init_queue(struct request_queue *q)
 	cfqd->cfq_slice_async_rq = cfq_slice_async_rq;
 	cfqd->cfq_slice_idle = cfq_slice_idle;
 	cfqd->cfq_latency = 1;
+	cfqd->cfq_group_isolation = 0;
 	cfqd->hw_tag = -1;
-	cfqd->last_end_sync_rq = jiffies;
+	/*
+	 * we optimistically start assuming sync ops weren't delayed in last
+	 * second, in order to have larger depth for async operations.
+	 */
+	cfqd->last_delayed_sync = jiffies - HZ;
+	INIT_RCU_HEAD(&cfqd->rcu);
 	return cfqd;
 }
 
@@ -3635,6 +3816,7 @@ SHOW_FUNCTION(cfq_slice_sync_show, cfqd->cfq_slice[1], 1);
 SHOW_FUNCTION(cfq_slice_async_show, cfqd->cfq_slice[0], 1);
 SHOW_FUNCTION(cfq_slice_async_rq_show, cfqd->cfq_slice_async_rq, 0);
 SHOW_FUNCTION(cfq_low_latency_show, cfqd->cfq_latency, 0);
+SHOW_FUNCTION(cfq_group_isolation_show, cfqd->cfq_group_isolation, 0);
 #undef SHOW_FUNCTION
 
 #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
@@ -3667,6 +3849,7 @@ STORE_FUNCTION(cfq_slice_async_store, &cfqd->cfq_slice[0], 1, UINT_MAX, 1);
 STORE_FUNCTION(cfq_slice_async_rq_store, &cfqd->cfq_slice_async_rq, 1,
 		UINT_MAX, 0);
 STORE_FUNCTION(cfq_low_latency_store, &cfqd->cfq_latency, 0, 1, 0);
+STORE_FUNCTION(cfq_group_isolation_store, &cfqd->cfq_group_isolation, 0, 1, 0);
 #undef STORE_FUNCTION
 
 #define CFQ_ATTR(name) \
@@ -3683,6 +3866,7 @@ static struct elv_fs_entry cfq_attrs[] = {
 	CFQ_ATTR(slice_async_rq),
 	CFQ_ATTR(slice_idle),
 	CFQ_ATTR(low_latency),
+	CFQ_ATTR(group_isolation),
 	__ATTR_NULL
 };
 
@@ -3712,6 +3896,17 @@ static struct elevator_type iosched_cfq = {
 	.elevator_owner =	THIS_MODULE,
 };
 
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+static struct blkio_policy_type blkio_policy_cfq = {
+	.ops = {
+		.blkio_unlink_group_fn =	cfq_unlink_blkio_group,
+		.blkio_update_group_weight_fn =	cfq_update_blkio_group_weight,
+	},
+};
+#else
+static struct blkio_policy_type blkio_policy_cfq;
+#endif
+
 static int __init cfq_init(void)
 {
 	/*
@@ -3726,6 +3921,7 @@ static int __init cfq_init(void)
 		return -ENOMEM;
 
 	elv_register(&iosched_cfq);
+	blkio_policy_register(&blkio_policy_cfq);
 
 	return 0;
 }
@@ -3733,6 +3929,7 @@ static int __init cfq_init(void)
 static void __exit cfq_exit(void)
 {
 	DECLARE_COMPLETION_ONSTACK(all_gone);
+	blkio_policy_unregister(&blkio_policy_cfq);
 	elv_unregister(&iosched_cfq);
 	ioc_gone = &all_gone;
 	/* ioc_gone's update must be visible before reading ioc_count */