6 files changed, 130 insertions, 34 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index a6809645d212..2fef1ef931a0 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -966,7 +966,7 @@ blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup)
 
         /* Currently we do not support hierarchy deeper than two level (0,1) */
         if (parent != cgroup->top_cgroup)
-                return ERR_PTR(-EINVAL);
+                return ERR_PTR(-EPERM);
 
         blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
         if (!blkcg)
diff --git a/block/blk-core.c b/block/blk-core.c
index ee1a1e7e63cc..32a1c123dfb3 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1198,9 +1198,9 @@ static int __make_request(struct request_queue *q, struct bio *bio)
         int el_ret;
         unsigned int bytes = bio->bi_size;
         const unsigned short prio = bio_prio(bio);
-        const bool sync = (bio->bi_rw & REQ_SYNC);
-        const bool unplug = (bio->bi_rw & REQ_UNPLUG);
-        const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK;
+        const bool sync = !!(bio->bi_rw & REQ_SYNC);
+        const bool unplug = !!(bio->bi_rw & REQ_UNPLUG);
+        const unsigned long ff = bio->bi_rw & REQ_FAILFAST_MASK;
         int rw_flags;
 
         if ((bio->bi_rw & REQ_HARDBARRIER) &&
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 001ab18078f5..0749b89c6885 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -511,6 +511,7 @@ int blk_register_queue(struct gendisk *disk)
                 kobject_uevent(&q->kobj, KOBJ_REMOVE);
                 kobject_del(&q->kobj);
                 blk_trace_remove_sysfs(disk_to_dev(disk));
+                kobject_put(&dev->kobj);
                 return ret;
         }
 
diff --git a/block/blk.h b/block/blk.h
index 6e7dc87141e4..d6b911ac002c 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -142,14 +142,18 @@ static inline int queue_congestion_off_threshold(struct request_queue *q)
 
 static inline int blk_cpu_to_group(int cpu)
 {
+        int group = NR_CPUS;
 #ifdef CONFIG_SCHED_MC
         const struct cpumask *mask = cpu_coregroup_mask(cpu);
-        return cpumask_first(mask);
+        group = cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
-        return cpumask_first(topology_thread_cpumask(cpu));
+        group = cpumask_first(topology_thread_cpumask(cpu));
 #else
         return cpu;
 #endif
+        if (likely(group < NR_CPUS))
+                return group;
+        return cpu;
 }
 
 /*
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index eb4086f7dfef..f65c6f01c475 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -30,6 +30,7 @@ static const int cfq_slice_sync = HZ / 10;
 static int cfq_slice_async = HZ / 25;
 static const int cfq_slice_async_rq = 2;
 static int cfq_slice_idle = HZ / 125;
+static int cfq_group_idle = HZ / 125;
 static const int cfq_target_latency = HZ * 3/10; /* 300 ms */
 static const int cfq_hist_divisor = 4;
 
@@ -147,6 +148,8 @@ struct cfq_queue {
         struct cfq_queue *new_cfqq;
         struct cfq_group *cfqg;
         struct cfq_group *orig_cfqg;
+        /* Number of sectors dispatched from queue in single dispatch round */
+        unsigned long nr_sectors;
 };
 
 /*
@@ -198,6 +201,8 @@ struct cfq_group {
         struct hlist_node cfqd_node;
         atomic_t ref;
 #endif
+        /* number of requests that are on the dispatch list or inside driver */
+        int dispatched;
 };
 
 /*
@@ -271,6 +276,7 @@ struct cfq_data {
         unsigned int cfq_slice[2];
         unsigned int cfq_slice_async_rq;
         unsigned int cfq_slice_idle;
+        unsigned int cfq_group_idle;
         unsigned int cfq_latency;
         unsigned int cfq_group_isolation;
 
@@ -378,6 +384,21 @@ CFQ_CFQQ_FNS(wait_busy);
                         &cfqg->service_trees[i][j]: NULL) \
 
 
+static inline bool iops_mode(struct cfq_data *cfqd)
+{
+        /*
+         * If we are not idling on queues and it is a NCQ drive, parallel
+         * execution of requests is on and measuring time is not possible
+         * in most of the cases until and unless we drive shallower queue
+         * depths and that becomes a performance bottleneck. In such cases
+         * switch to start providing fairness in terms of number of IOs.
+         */
+        if (!cfqd->cfq_slice_idle && cfqd->hw_tag)
+                return true;
+        else
+                return false;
+}
+
 static inline enum wl_prio_t cfqq_prio(struct cfq_queue *cfqq)
 {
         if (cfq_class_idle(cfqq))
@@ -906,7 +927,6 @@ static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
                         slice_used = cfqq->allocated_slice;
         }
 
-        cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u", slice_used);
         return slice_used;
 }
 
@@ -914,19 +934,21 @@ 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, charge_sl;
+        unsigned int used_sl, charge;
         int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg)
                         - cfqg->service_tree_idle.count;
 
         BUG_ON(nr_sync < 0);
-        used_sl = charge_sl = cfq_cfqq_slice_usage(cfqq);
+        used_sl = charge = cfq_cfqq_slice_usage(cfqq);
 
-        if (!cfq_cfqq_sync(cfqq) && !nr_sync)
-                charge_sl = cfqq->allocated_slice;
+        if (iops_mode(cfqd))
+                charge = cfqq->slice_dispatch;
+        else if (!cfq_cfqq_sync(cfqq) && !nr_sync)
+                charge = 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(charge_sl, cfqg);
+        cfqg->vdisktime += cfq_scale_slice(charge, cfqg);
         __cfq_group_service_tree_add(st, cfqg);
 
         /* This group is being expired. Save the context */
@@ -940,6 +962,9 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 
         cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime,
                                         st->min_vdisktime);
+        cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u disp=%u charge=%u iops=%u"
+                        " sect=%u", used_sl, cfqq->slice_dispatch, charge,
+                        iops_mode(cfqd), cfqq->nr_sectors);
         cfq_blkiocg_update_timeslice_used(&cfqg->blkg, used_sl);
         cfq_blkiocg_set_start_empty_time(&cfqg->blkg);
 }
@@ -1587,6 +1612,7 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
                 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);
@@ -1839,6 +1865,9 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
         BUG_ON(!service_tree);
         BUG_ON(!service_tree->count);
 
+        if (!cfqd->cfq_slice_idle)
+                return false;
+
         /* We never do for idle class queues. */
         if (prio == IDLE_WORKLOAD)
                 return false;
@@ -1863,7 +1892,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 {
         struct cfq_queue *cfqq = cfqd->active_queue;
         struct cfq_io_context *cic;
-        unsigned long sl;
+        unsigned long sl, group_idle = 0;
 
         /*
          * SSD device without seek penalty, disable idling. But only do so
@@ -1879,8 +1908,13 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
         /*
          * idle is disabled, either manually or by past process history
          */
-        if (!cfqd->cfq_slice_idle || !cfq_should_idle(cfqd, cfqq))
-                return;
+        if (!cfq_should_idle(cfqd, cfqq)) {
+                /* no queue idling. Check for group idling */
+                if (cfqd->cfq_group_idle)
+                        group_idle = cfqd->cfq_group_idle;
+                else
+                        return;
+        }
 
         /*
          * still active requests from this queue, don't idle
@@ -1907,13 +1941,21 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
                 return;
         }
 
+        /* There are other queues in the group, don't do group idle */
+        if (group_idle && cfqq->cfqg->nr_cfqq > 1)
+                return;
+
         cfq_mark_cfqq_wait_request(cfqq);
 
-        sl = cfqd->cfq_slice_idle;
+        if (group_idle)
+                sl = cfqd->cfq_group_idle;
+        else
+                sl = cfqd->cfq_slice_idle;
 
         mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
         cfq_blkiocg_update_set_idle_time_stats(&cfqq->cfqg->blkg);
-        cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl);
+        cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu group_idle: %d", sl,
+                        group_idle ? 1 : 0);
 }
 
 /*
@@ -1929,9 +1971,11 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)
         cfqq->next_rq = cfq_find_next_rq(cfqd, cfqq, rq);
         cfq_remove_request(rq);
         cfqq->dispatched++;
+        (RQ_CFQG(rq))->dispatched++;
         elv_dispatch_sort(q, rq);
 
         cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++;
+        cfqq->nr_sectors += blk_rq_sectors(rq);
         cfq_blkiocg_update_dispatch_stats(&cfqq->cfqg->blkg, blk_rq_bytes(rq),
                                         rq_data_dir(rq), rq_is_sync(rq));
 }
@@ -2198,7 +2242,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
                         cfqq = NULL;
                         goto keep_queue;
                 } else
-                        goto expire;
+                        goto check_group_idle;
         }
 
         /*
@@ -2226,8 +2270,23 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
          * flight or is idling for a new request, allow either of these
          * conditions to happen (or time out) before selecting a new queue.
          */
-        if (timer_pending(&cfqd->idle_slice_timer) ||
-            (cfqq->dispatched && cfq_should_idle(cfqd, cfqq))) {
+        if (timer_pending(&cfqd->idle_slice_timer)) {
+                cfqq = NULL;
+                goto keep_queue;
+        }
+
+        if (cfqq->dispatched && cfq_should_idle(cfqd, cfqq)) {
+                cfqq = NULL;
+                goto keep_queue;
+        }
+
+        /*
+         * If group idle is enabled and there are requests dispatched from
+         * this group, wait for requests to complete.
+         */
+check_group_idle:
+        if (cfqd->cfq_group_idle && cfqq->cfqg->nr_cfqq == 1
+            && cfqq->cfqg->dispatched) {
                 cfqq = NULL;
                 goto keep_queue;
         }
@@ -3375,6 +3434,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
         WARN_ON(!cfqq->dispatched);
         cfqd->rq_in_driver--;
         cfqq->dispatched--;
+        (RQ_CFQG(rq))->dispatched--;
         cfq_blkiocg_update_completion_stats(&cfqq->cfqg->blkg,
                         rq_start_time_ns(rq), rq_io_start_time_ns(rq),
                         rq_data_dir(rq), rq_is_sync(rq));
@@ -3404,7 +3464,10 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
                  * the queue.
                  */
                 if (cfq_should_wait_busy(cfqd, cfqq)) {
-                        cfqq->slice_end = jiffies + cfqd->cfq_slice_idle;
+                        unsigned long extend_sl = cfqd->cfq_slice_idle;
+                        if (!cfqd->cfq_slice_idle)
+                                extend_sl = cfqd->cfq_group_idle;
+                        cfqq->slice_end = jiffies + extend_sl;
                         cfq_mark_cfqq_wait_busy(cfqq);
                         cfq_log_cfqq(cfqd, cfqq, "will busy wait");
                 }
@@ -3850,6 +3913,7 @@ static void *cfq_init_queue(struct request_queue *q)
         cfqd->cfq_slice[1] = cfq_slice_sync;
         cfqd->cfq_slice_async_rq = cfq_slice_async_rq;
         cfqd->cfq_slice_idle = cfq_slice_idle;
+        cfqd->cfq_group_idle = cfq_group_idle;
         cfqd->cfq_latency = 1;
         cfqd->cfq_group_isolation = 0;
         cfqd->hw_tag = -1;
@@ -3922,6 +3986,7 @@ SHOW_FUNCTION(cfq_fifo_expire_async_show, cfqd->cfq_fifo_expire[0], 1);
 SHOW_FUNCTION(cfq_back_seek_max_show, cfqd->cfq_back_max, 0);
 SHOW_FUNCTION(cfq_back_seek_penalty_show, cfqd->cfq_back_penalty, 0);
 SHOW_FUNCTION(cfq_slice_idle_show, cfqd->cfq_slice_idle, 1);
+SHOW_FUNCTION(cfq_group_idle_show, cfqd->cfq_group_idle, 1);
 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);
@@ -3954,6 +4019,7 @@ STORE_FUNCTION(cfq_back_seek_max_store, &cfqd->cfq_back_max, 0, UINT_MAX, 0);
 STORE_FUNCTION(cfq_back_seek_penalty_store, &cfqd->cfq_back_penalty, 1,
                 UINT_MAX, 0);
 STORE_FUNCTION(cfq_slice_idle_store, &cfqd->cfq_slice_idle, 0, UINT_MAX, 1);
+STORE_FUNCTION(cfq_group_idle_store, &cfqd->cfq_group_idle, 0, UINT_MAX, 1);
 STORE_FUNCTION(cfq_slice_sync_store, &cfqd->cfq_slice[1], 1, UINT_MAX, 1);
 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,
@@ -3975,6 +4041,7 @@ static struct elv_fs_entry cfq_attrs[] = {
         CFQ_ATTR(slice_async),
         CFQ_ATTR(slice_async_rq),
         CFQ_ATTR(slice_idle),
+        CFQ_ATTR(group_idle),
         CFQ_ATTR(low_latency),
         CFQ_ATTR(group_isolation),
         __ATTR_NULL
@@ -4028,6 +4095,12 @@ static int __init cfq_init(void)
         if (!cfq_slice_idle)
                 cfq_slice_idle = 1;
 
+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+        if (!cfq_group_idle)
+                cfq_group_idle = 1;
+#else
+                cfq_group_idle = 0;
+#endif
         if (cfq_slab_setup())
                 return -ENOMEM;
 
diff --git a/block/elevator.c b/block/elevator.c
index ec585c9554d3..205b09a5bd9e 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -1009,18 +1009,19 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 {
         struct elevator_queue *old_elevator, *e;
         void *data;
+        int err;
 
         /*
          * Allocate new elevator
          */
         e = elevator_alloc(q, new_e);
         if (!e)
-                return 0;
+                return -ENOMEM;
 
         data = elevator_init_queue(q, e);
         if (!data) {
                 kobject_put(&e->kobj);
-                return 0;
+                return -ENOMEM;
         }
 
         /*
@@ -1043,7 +1044,8 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 
         __elv_unregister_queue(old_elevator);
 
-        if (elv_register_queue(q))
+        err = elv_register_queue(q);
+        if (err)
                 goto fail_register;
 
         /*
@@ -1056,7 +1058,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 
         blk_add_trace_msg(q, "elv switch: %s", e->elevator_type->elevator_name);
 
-        return 1;
+        return 0;
 
 fail_register:
         /*
@@ -1071,17 +1073,19 @@ fail_register:
         queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
         spin_unlock_irq(q->queue_lock);
 
-        return 0;
+        return err;
 }
 
-ssize_t elv_iosched_store(struct request_queue *q, const char *name,
-                          size_t count)
+/*
+ * Switch this queue to the given IO scheduler.
+ */
+int elevator_change(struct request_queue *q, const char *name)
 {
         char elevator_name[ELV_NAME_MAX];
         struct elevator_type *e;
 
         if (!q->elevator)
-                return count;
+                return -ENXIO;
 
         strlcpy(elevator_name, name, sizeof(elevator_name));
         e = elevator_get(strstrip(elevator_name));
@@ -1092,13 +1096,27 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,
 
         if (!strcmp(elevator_name, q->elevator->elevator_type->elevator_name)) {
                 elevator_put(e);
-                return count;
+                return 0;
         }
 
-        if (!elevator_switch(q, e))
-                printk(KERN_ERR "elevator: switch to %s failed\n",
-                                                        elevator_name);
-        return count;
+        return elevator_switch(q, e);
+}
+EXPORT_SYMBOL(elevator_change);
+
+ssize_t elv_iosched_store(struct request_queue *q, const char *name,
+                          size_t count)
+{
+        int ret;
+
+        if (!q->elevator)
+                return count;
+
+        ret = elevator_change(q, name);
+        if (!ret)
+                return count;
+
+        printk(KERN_ERR "elevator: switch to %s failed\n", name);
+        return ret;
 }
 
 ssize_t elv_iosched_show(struct request_queue *q, char *name)