6 files changed, 63 insertions, 55 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 1fa2654db0a6..e7dbbaf5fb3e 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -147,16 +147,16 @@ blkiocg_weight_write(struct cgroup *cgroup, struct cftype *cftype, u64 val)
                 return -EINVAL;
 
         blkcg = cgroup_to_blkio_cgroup(cgroup);
+        spin_lock(&blkio_list_lock);
         spin_lock_irq(&blkcg->lock);
         blkcg->weight = (unsigned int)val;
         hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node) {
-                spin_lock(&blkio_list_lock);
                 list_for_each_entry(blkiop, &blkio_list, list)
                         blkiop->ops.blkio_update_group_weight_fn(blkg,
                                         blkcg->weight);
-                spin_unlock(&blkio_list_lock);
         }
         spin_unlock_irq(&blkcg->lock);
+        spin_unlock(&blkio_list_lock);
         return 0;
 }
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 718897e6d37f..d1a9a0a64f95 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1147,7 +1147,7 @@ void init_request_from_bio(struct request *req, struct bio *bio)
  */
 static inline bool queue_should_plug(struct request_queue *q)
 {
-        return !(blk_queue_nonrot(q) && blk_queue_queuing(q));
+        return !(blk_queue_nonrot(q) && blk_queue_tagged(q));
 }
 
 static int __make_request(struct request_queue *q, struct bio *bio)
@@ -1859,15 +1859,8 @@ void blk_dequeue_request(struct request *rq)
          * and to it is freed is accounted as io that is in progress at
          * the driver side.
          */
-        if (blk_account_rq(rq)) {
+        if (blk_account_rq(rq))
                 q->in_flight[rq_is_sync(rq)]++;
-                /*
-                 * Mark this device as supporting hardware queuing, if
-                 * we have more IOs in flight than 4.
-                 */
-                if (!blk_queue_queuing(q) && queue_in_flight(q) > 4)
-                        set_bit(QUEUE_FLAG_CQ, &q->queue_flags);
-        }
 }
 
 /**
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index cbdabb0dd6d7..98e6bf61b0ac 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -39,8 +39,6 @@ int put_io_context(struct io_context *ioc)
 
         if (atomic_long_dec_and_test(&ioc->refcount)) {
                 rcu_read_lock();
-                if (ioc->aic && ioc->aic->dtor)
-                        ioc->aic->dtor(ioc->aic);
                 cfq_dtor(ioc);
                 rcu_read_unlock();
 
@@ -76,8 +74,6 @@ void exit_io_context(struct task_struct *task)
         task_unlock(task);
 
         if (atomic_dec_and_test(&ioc->nr_tasks)) {
-                if (ioc->aic && ioc->aic->exit)
-                        ioc->aic->exit(ioc->aic);
                 cfq_exit(ioc);
 
         }
@@ -97,7 +93,6 @@ struct io_context *alloc_io_context(gfp_t gfp_flags, int node)
                 ret->ioprio = 0;
                 ret->last_waited = jiffies; /* doesn't matter... */
                 ret->nr_batch_requests = 0; /* because this is 0 */
-                ret->aic = NULL;
                 INIT_RADIX_TREE(&ret->radix_root, GFP_ATOMIC | __GFP_HIGH);
                 INIT_HLIST_HEAD(&ret->cic_list);
                 ret->ioc_data = NULL;
diff --git a/block/blk-settings.c b/block/blk-settings.c
index d52d4adc440b..5eeb9e0d256e 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -528,7 +528,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
                      sector_t offset)
 {
         sector_t alignment;
-        unsigned int top, bottom;
+        unsigned int top, bottom, ret = 0;
 
         t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
         t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
@@ -546,6 +546,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
         t->max_segment_size = min_not_zero(t->max_segment_size,
                                            b->max_segment_size);
 
+        t->misaligned |= b->misaligned;
+
         alignment = queue_limit_alignment_offset(b, offset);
 
         /* Bottom device has different alignment.  Check that it is
@@ -558,8 +560,10 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
                 bottom = max(b->physical_block_size, b->io_min) + alignment;
 
                 /* Verify that top and bottom intervals line up */
-                if (max(top, bottom) & (min(top, bottom) - 1))
+                if (max(top, bottom) & (min(top, bottom) - 1)) {
                         t->misaligned = 1;
+                        ret = -1;
+                }
         }
 
         t->logical_block_size = max(t->logical_block_size,
@@ -578,18 +582,21 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
         if (t->physical_block_size & (t->logical_block_size - 1)) {
                 t->physical_block_size = t->logical_block_size;
                 t->misaligned = 1;
+                ret = -1;
         }
 
         /* Minimum I/O a multiple of the physical block size? */
         if (t->io_min & (t->physical_block_size - 1)) {
                 t->io_min = t->physical_block_size;
                 t->misaligned = 1;
+                ret = -1;
         }
 
         /* Optimal I/O a multiple of the physical block size? */
         if (t->io_opt & (t->physical_block_size - 1)) {
                 t->io_opt = 0;
                 t->misaligned = 1;
+                ret = -1;
         }
 
         /* Find lowest common alignment_offset */
@@ -597,8 +604,10 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
                 & (max(t->physical_block_size, t->io_min) - 1);
 
         /* Verify that new alignment_offset is on a logical block boundary */
-        if (t->alignment_offset & (t->logical_block_size - 1))
+        if (t->alignment_offset & (t->logical_block_size - 1)) {
                 t->misaligned = 1;
+                ret = -1;
+        }
 
         /* Discard alignment and granularity */
         if (b->discard_granularity) {
@@ -626,11 +635,33 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
                         (t->discard_granularity - 1);
         }
 
-        return t->misaligned ? -1 : 0;
+        return ret;
 }
 EXPORT_SYMBOL(blk_stack_limits);
 
 /**
+ * bdev_stack_limits - adjust queue limits for stacked drivers
+ * @t:  the stacking driver limits (top device)
+ * @bdev:  the component block_device (bottom)
+ * @start:  first data sector within component device
+ *
+ * Description:
+ *    Merges queue limits for a top device and a block_device.  Returns
+ *    0 if alignment didn't change.  Returns -1 if adding the bottom
+ *    device caused misalignment.
+ */
+int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev,
+                      sector_t start)
+{
+        struct request_queue *bq = bdev_get_queue(bdev);
+
+        start += get_start_sect(bdev);
+
+        return blk_stack_limits(t, &bq->limits, start << 9);
+}
+EXPORT_SYMBOL(bdev_stack_limits);
+
+/**
  * disk_stack_limits - adjust queue limits for stacked drivers
  * @disk:  MD/DM gendisk (top)
  * @bdev:  the underlying block device (bottom)
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 918c7fd9aeb1..023f4e69a337 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -42,16 +42,13 @@ static const int cfq_hist_divisor = 4;
  */
 #define CFQ_MIN_TT              (2)
 
-/*
- * Allow merged cfqqs to perform this amount of seeky I/O before
- * deciding to break the queues up again.
- */
-#define CFQQ_COOP_TOUT          (HZ)
-
 #define CFQ_SLICE_SCALE         (5)
 #define CFQ_HW_QUEUE_MIN        (5)
 #define CFQ_SERVICE_SHIFT       12
 
+#define CFQQ_SEEK_THR           8 * 1024
+#define CFQQ_SEEKY(cfqq)        ((cfqq)->seek_mean > CFQQ_SEEK_THR)
+
 #define RQ_CIC(rq)              \
         ((struct cfq_io_context *) (rq)->elevator_private)
 #define RQ_CFQQ(rq)             (struct cfq_queue *) ((rq)->elevator_private2)
@@ -137,7 +134,6 @@ struct cfq_queue {
         u64 seek_total;
         sector_t seek_mean;
         sector_t last_request_pos;
-        unsigned long seeky_start;
 
         pid_t pid;
 
@@ -314,6 +310,7 @@ enum cfqq_state_flags {
         CFQ_CFQQ_FLAG_slice_new,        /* no requests dispatched in slice */
         CFQ_CFQQ_FLAG_sync,             /* synchronous queue */
         CFQ_CFQQ_FLAG_coop,             /* cfqq is shared */
+        CFQ_CFQQ_FLAG_split_coop,       /* shared cfqq will be splitted */
         CFQ_CFQQ_FLAG_deep,             /* sync cfqq experienced large depth */
         CFQ_CFQQ_FLAG_wait_busy,        /* Waiting for next request */
 };
@@ -342,6 +339,7 @@ CFQ_CFQQ_FNS(prio_changed);
 CFQ_CFQQ_FNS(slice_new);
 CFQ_CFQQ_FNS(sync);
 CFQ_CFQQ_FNS(coop);
+CFQ_CFQQ_FNS(split_coop);
 CFQ_CFQQ_FNS(deep);
 CFQ_CFQQ_FNS(wait_busy);
 #undef CFQ_CFQQ_FNS
@@ -1566,6 +1564,15 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
         cfq_clear_cfqq_wait_busy(cfqq);
 
         /*
+         * If this cfqq is shared between multiple processes, check to
+         * make sure that those processes are still issuing I/Os within
+         * the mean seek distance.  If not, it may be time to break the
+         * queues apart again.
+         */
+        if (cfq_cfqq_coop(cfqq) && CFQQ_SEEKY(cfqq))
+                cfq_mark_cfqq_split_coop(cfqq);
+
+        /*
          * store what was left of this slice, if the queue idled/timed out
          */
         if (timed_out && !cfq_cfqq_slice_new(cfqq)) {
@@ -1663,9 +1670,6 @@ static inline sector_t cfq_dist_from_last(struct cfq_data *cfqd,
                 return cfqd->last_position - blk_rq_pos(rq);
 }
 
-#define CFQQ_SEEK_THR           8 * 1024
-#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, bool for_preempt)
 {
@@ -1803,7 +1807,7 @@ 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;
+        return service_tree->count == 1 && cfq_cfqq_sync(cfqq);
 }
 
 static void cfq_arm_slice_timer(struct cfq_data *cfqd)
@@ -3000,19 +3004,6 @@ cfq_update_io_seektime(struct cfq_data *cfqd, struct cfq_queue *cfqq,
         total = cfqq->seek_total + (cfqq->seek_samples/2);
         do_div(total, cfqq->seek_samples);
         cfqq->seek_mean = (sector_t)total;
-
-        /*
-         * If this cfqq is shared between multiple processes, check to
-         * make sure that those processes are still issuing I/Os within
-         * the mean seek distance.  If not, it may be time to break the
-         * queues apart again.
-         */
-        if (cfq_cfqq_coop(cfqq)) {
-                if (CFQQ_SEEKY(cfqq) && !cfqq->seeky_start)
-                        cfqq->seeky_start = jiffies;
-                else if (!CFQQ_SEEKY(cfqq))
-                        cfqq->seeky_start = 0;
-        }
 }
 
 /*
@@ -3077,6 +3068,12 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq,
                 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
          * not, let the sync request have priority.
          */
@@ -3447,14 +3444,6 @@ cfq_merge_cfqqs(struct cfq_data *cfqd, struct cfq_io_context *cic,
         return cic_to_cfqq(cic, 1);
 }
 
-static int should_split_cfqq(struct cfq_queue *cfqq)
-{
-        if (cfqq->seeky_start &&
-            time_after(jiffies, cfqq->seeky_start + CFQQ_COOP_TOUT))
-                return 1;
-        return 0;
-}
-
 /*
  * Returns NULL if a new cfqq should be allocated, or the old cfqq if this
  * was the last process referring to said cfqq.
@@ -3463,9 +3452,9 @@ static struct cfq_queue *
 split_cfqq(struct cfq_io_context *cic, struct cfq_queue *cfqq)
 {
         if (cfqq_process_refs(cfqq) == 1) {
-                cfqq->seeky_start = 0;
                 cfqq->pid = current->pid;
                 cfq_clear_cfqq_coop(cfqq);
+                cfq_clear_cfqq_split_coop(cfqq);
                 return cfqq;
         }
 
@@ -3504,7 +3493,7 @@ new_queue:
                 /*
                  * If the queue was seeky for too long, break it apart.
                  */
-                if (cfq_cfqq_coop(cfqq) && should_split_cfqq(cfqq)) {
+                if (cfq_cfqq_coop(cfqq) && cfq_cfqq_split_coop(cfqq)) {
                         cfq_log_cfqq(cfqd, cfqq, "breaking apart cfqq");
                         cfqq = split_cfqq(cic, cfqq);
                         if (!cfqq)
diff --git a/block/genhd.c b/block/genhd.c
index b11a4ad7d571..d13ba76a169c 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -867,7 +867,7 @@ static ssize_t disk_discard_alignment_show(struct device *dev,
 {
         struct gendisk *disk = dev_to_disk(dev);
 
-        return sprintf(buf, "%u\n", queue_discard_alignment(disk->queue));
+        return sprintf(buf, "%d\n", queue_discard_alignment(disk->queue));
 }
 
 static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL);