7 files changed, 71 insertions, 33 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 62a5921321cd..f9e89f4d94bb 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -78,8 +78,9 @@ config BLK_DEV_INTEGRITY
         Protection.  If in doubt, say N.
 
 config BLK_CGROUP
-        tristate
+        tristate "Block cgroup support"
         depends on CGROUPS
+        depends on CFQ_GROUP_IOSCHED
         default n
         ---help---
         Generic block IO controller cgroup interface. This is the common
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 5fe03def34b2..2cc682b860ea 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -286,16 +286,16 @@ done:
 static struct cgroup_subsys_state *
 blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup)
 {
-        struct blkio_cgroup *blkcg, *parent_blkcg;
+        struct blkio_cgroup *blkcg;
+        struct cgroup *parent = cgroup->parent;
 
-        if (!cgroup->parent) {
+        if (!parent) {
                 blkcg = &blkio_root_cgroup;
                 goto done;
         }
 
         /* Currently we do not support hierarchy deeper than two level (0,1) */
-        parent_blkcg = cgroup_to_blkio_cgroup(cgroup->parent);
-        if (css_depth(&parent_blkcg->css) > 0)
+        if (parent != cgroup->top_cgroup)
                 return ERR_PTR(-EINVAL);
 
         blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
diff --git a/block/blk-settings.c b/block/blk-settings.c
index d9a9db5f0a2b..f5ed5a1187ba 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -8,6 +8,7 @@
 #include <linux/blkdev.h>
 #include <linux/bootmem.h>      /* for max_pfn/max_low_pfn */
 #include <linux/gcd.h>
+#include <linux/lcm.h>
 #include <linux/jiffies.h>
 #include <linux/gfp.h>
 
@@ -462,16 +463,6 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 }
 EXPORT_SYMBOL(blk_queue_stack_limits);
 
-static unsigned int lcm(unsigned int a, unsigned int b)
-{
-        if (a && b)
-                return (a * b) / gcd(a, b);
-        else if (b)
-                return b;
-
-        return a;
-}
-
 /**
  * blk_stack_limits - adjust queue_limits for stacked devices
  * @t:  the stacking driver limits (top device)
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index c2b821fa324a..306759bbdf1b 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -107,6 +107,19 @@ static ssize_t queue_max_sectors_show(struct request_queue *q, char *page)
         return queue_var_show(max_sectors_kb, (page));
 }
 
+static ssize_t queue_max_segments_show(struct request_queue *q, char *page)
+{
+        return queue_var_show(queue_max_segments(q), (page));
+}
+
+static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page)
+{
+        if (test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags))
+                return queue_var_show(queue_max_segment_size(q), (page));
+
+        return queue_var_show(PAGE_CACHE_SIZE, (page));
+}
+
 static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page)
 {
         return queue_var_show(queue_logical_block_size(q), page);
@@ -281,6 +294,16 @@ static struct queue_sysfs_entry queue_max_hw_sectors_entry = {
         .show = queue_max_hw_sectors_show,
 };
 
+static struct queue_sysfs_entry queue_max_segments_entry = {
+        .attr = {.name = "max_segments", .mode = S_IRUGO },
+        .show = queue_max_segments_show,
+};
+
+static struct queue_sysfs_entry queue_max_segment_size_entry = {
+        .attr = {.name = "max_segment_size", .mode = S_IRUGO },
+        .show = queue_max_segment_size_show,
+};
+
 static struct queue_sysfs_entry queue_iosched_entry = {
         .attr = {.name = "scheduler", .mode = S_IRUGO | S_IWUSR },
         .show = elv_iosched_show,
@@ -356,6 +379,8 @@ static struct attribute *default_attrs[] = {
         &queue_ra_entry.attr,
         &queue_max_hw_sectors_entry.attr,
         &queue_max_sectors_entry.attr,
+        &queue_max_segments_entry.attr,
+        &queue_max_segment_size_entry.attr,
         &queue_iosched_entry.attr,
         &queue_hw_sector_size_entry.attr,
         &queue_logical_block_size_entry.attr,
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 1ba7e0aca878..4f0c06c7a338 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -109,6 +109,7 @@ void blk_rq_timed_out_timer(unsigned long data)
         struct request_queue *q = (struct request_queue *) data;
         unsigned long flags, next = 0;
         struct request *rq, *tmp;
+        int next_set = 0;
 
         spin_lock_irqsave(q->queue_lock, flags);
 
@@ -122,16 +123,13 @@ void blk_rq_timed_out_timer(unsigned long data)
                         if (blk_mark_rq_complete(rq))
                                 continue;
                         blk_rq_timed_out(rq);
-                } else if (!next || time_after(next, rq->deadline))
+                } else if (!next_set || time_after(next, rq->deadline)) {
                         next = rq->deadline;
+                        next_set = 1;
+                }
         }
 
-        /*
-         * next can never be 0 here with the list non-empty, since we always
-         * bump ->deadline to 1 so we can detect if the timer was ever added
-         * or not. See comment in blk_add_timer()
-         */
-        if (next)
+        if (next_set)
                 mod_timer(&q->timeout, round_jiffies_up(next));
 
         spin_unlock_irqrestore(q->queue_lock, flags);
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index fc98a48554fd..5f127cfb2e92 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -48,6 +48,7 @@ static const int cfq_hist_divisor = 4;
 #define CFQ_SERVICE_SHIFT       12
 
 #define CFQQ_SEEK_THR           (sector_t)(8 * 100)
+#define CFQQ_CLOSE_THR          (sector_t)(8 * 1024)
 #define CFQQ_SECT_THR_NONROT    (sector_t)(2 * 32)
 #define CFQQ_SEEKY(cfqq)        (hweight32(cfqq->seek_history) > 32/8)
 
@@ -948,6 +949,11 @@ cfq_find_alloc_cfqg(struct cfq_data *cfqd, struct cgroup *cgroup, int create)
         unsigned int major, minor;
 
         cfqg = cfqg_of_blkg(blkiocg_lookup_group(blkcg, key));
+        if (cfqg && !cfqg->blkg.dev && bdi->dev && dev_name(bdi->dev)) {
+                sscanf(dev_name(bdi->dev), "%u:%u", &major, &minor);
+                cfqg->blkg.dev = MKDEV(major, minor);
+                goto done;
+        }
         if (cfqg || !create)
                 goto done;
 
@@ -1518,7 +1524,8 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
                                    struct cfq_queue *cfqq)
 {
         if (cfqq) {
-                cfq_log_cfqq(cfqd, cfqq, "set_active");
+                cfq_log_cfqq(cfqd, cfqq, "set_active wl_prio:%d wl_type:%d",
+                                cfqd->serving_prio, cfqd->serving_type);
                 cfqq->slice_start = 0;
                 cfqq->dispatch_start = jiffies;
                 cfqq->allocated_slice = 0;
@@ -1661,9 +1668,9 @@ static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
 }
 
 static inline int cfq_rq_close(struct cfq_data *cfqd, struct cfq_queue *cfqq,
-                               struct request *rq, bool for_preempt)
+                               struct request *rq)
 {
-        return cfq_dist_from_last(cfqd, rq) <= CFQQ_SEEK_THR;
+        return cfq_dist_from_last(cfqd, rq) <= CFQQ_CLOSE_THR;
 }
 
 static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
@@ -1690,7 +1697,7 @@ 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, false))
+        if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
                 return __cfqq;
 
         if (blk_rq_pos(__cfqq->next_rq) < sector)
@@ -1701,7 +1708,7 @@ 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, false))
+        if (cfq_rq_close(cfqd, cur_cfqq, __cfqq->next_rq))
                 return __cfqq;
 
         return NULL;
@@ -1722,6 +1729,8 @@ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
 {
         struct cfq_queue *cfqq;
 
+        if (cfq_class_idle(cur_cfqq))
+                return NULL;
         if (!cfq_cfqq_sync(cur_cfqq))
                 return NULL;
         if (CFQQ_SEEKY(cur_cfqq))
@@ -1788,7 +1797,11 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
          * Otherwise, we do only if they are the last ones
          * in their service tree.
          */
-        return service_tree->count == 1 && cfq_cfqq_sync(cfqq);
+        if (service_tree->count == 1 && cfq_cfqq_sync(cfqq))
+                return 1;
+        cfq_log_cfqq(cfqd, cfqq, "Not idling. st->count:%d",
+                        service_tree->count);
+        return 0;
 }
 
 static void cfq_arm_slice_timer(struct cfq_data *cfqd)
@@ -1833,8 +1846,11 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
          * time slice.
          */
         if (sample_valid(cic->ttime_samples) &&
-            (cfqq->slice_end - jiffies < cic->ttime_mean))
+            (cfqq->slice_end - jiffies < cic->ttime_mean)) {
+                cfq_log_cfqq(cfqd, cfqq, "Not idling. think_time:%d",
+                                cic->ttime_mean);
                 return;
+        }
 
         cfq_mark_cfqq_wait_request(cfqq);
 
@@ -2042,6 +2058,7 @@ static void choose_service_tree(struct cfq_data *cfqd, struct cfq_group *cfqg)
                 slice = max(slice, 2 * cfqd->cfq_slice_idle);
 
         slice = max_t(unsigned, slice, CFQ_MIN_TT);
+        cfq_log(cfqd, "workload slice:%d", slice);
         cfqd->workload_expires = jiffies + slice;
         cfqd->noidle_tree_requires_idle = false;
 }
@@ -2189,10 +2206,13 @@ static int cfq_forced_dispatch(struct cfq_data *cfqd)
         struct cfq_queue *cfqq;
         int dispatched = 0;
 
-        while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL)
+        /* Expire the timeslice of the current active queue first */
+        cfq_slice_expired(cfqd, 0);
+        while ((cfqq = cfq_get_next_queue_forced(cfqd)) != NULL) {
+                __cfq_set_active_queue(cfqd, cfqq);
                 dispatched += __cfq_forced_dispatch_cfqq(cfqq);
+        }
 
-        cfq_slice_expired(cfqd, 0);
         BUG_ON(cfqd->busy_queues);
 
         cfq_log(cfqd, "forced_dispatch=%d", dispatched);
@@ -3104,7 +3124,7 @@ 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, true))
+        if (cfq_rq_close(cfqd, cfqq, rq))
                 return true;
 
         return false;
@@ -3308,6 +3328,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
                 if (cfq_should_wait_busy(cfqd, cfqq)) {
                         cfqq->slice_end = jiffies + cfqd->cfq_slice_idle;
                         cfq_mark_cfqq_wait_busy(cfqq);
+                        cfq_log_cfqq(cfqd, cfqq, "will busy wait");
                 }
 
                 /*
@@ -3673,8 +3694,10 @@ static void *cfq_init_queue(struct request_queue *q)
          * to make sure that cfq_put_cfqg() does not try to kfree root group
          */
         atomic_set(&cfqg->ref, 1);
+        rcu_read_lock();
         blkiocg_add_blkio_group(&blkio_root_cgroup, &cfqg->blkg, (void *)cfqd,
                                         0);
+        rcu_read_unlock();
 #endif
         /*
          * Not strictly needed (since RB_ROOT just clears the node and we
diff --git a/block/elevator.c b/block/elevator.c
index df75676f6671..76e3702d5381 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -154,7 +154,7 @@ static struct elevator_type *elevator_get(const char *name)
 
                 spin_unlock(&elv_list_lock);
 
-                sprintf(elv, "%s-iosched", name);
+                snprintf(elv, sizeof(elv), "%s-iosched", name);
 
                 request_module("%s", elv);
                 spin_lock(&elv_list_lock);