5 files changed, 131 insertions, 91 deletions

diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index 8873b9b439ff..8618d8996fea 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -402,7 +402,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
                  * our current implementations need.  If we'll ever need
                  * more the interface will need revisiting.
                  */
-                page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+                page = alloc_page(gfp_mask | __GFP_ZERO);
                 if (!page)
                         goto out_free_bio;
                 if (bio_add_pc_page(q, bio, page, sector_size, 0) < sector_size)
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 6ae118d6e193..5eeb9e0d256e 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -505,21 +505,30 @@ static unsigned int lcm(unsigned int a, unsigned int b)
 
 /**
  * blk_stack_limits - adjust queue_limits for stacked devices
- * @t:  the stacking driver limits (top)
- * @b:  the underlying queue limits (bottom)
+ * @t:  the stacking driver limits (top device)
+ * @b:  the underlying queue limits (bottom, component device)
  * @offset:  offset to beginning of data within component device
  *
  * Description:
- *    Merges two queue_limit structs.  Returns 0 if alignment didn't
- *    change.  Returns -1 if adding the bottom device caused
- *    misalignment.
+ *    This function is used by stacking drivers like MD and DM to ensure
+ *    that all component devices have compatible block sizes and
+ *    alignments.  The stacking driver must provide a queue_limits
+ *    struct (top) and then iteratively call the stacking function for
+ *    all component (bottom) devices.  The stacking function will
+ *    attempt to combine the values and ensure proper alignment.
+ *
+ *    Returns 0 if the top and bottom queue_limits are compatible.  The
+ *    top device's block sizes and alignment offsets may be adjusted to
+ *    ensure alignment with the bottom device. If no compatible sizes
+ *    and alignments exist, -1 is returned and the resulting top
+ *    queue_limits will have the misaligned flag set to indicate that
+ *    the alignment_offset is undefined.
  */
 int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
                      sector_t offset)
 {
-        int ret;
-
-        ret = 0;
+        sector_t alignment;
+        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);
@@ -537,6 +546,26 @@ 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
+         * compatible with the current top alignment.
+         */
+        if (t->alignment_offset != alignment) {
+
+                top = max(t->physical_block_size, t->io_min)
+                        + t->alignment_offset;
+                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)) {
+                        t->misaligned = 1;
+                        ret = -1;
+                }
+        }
+
         t->logical_block_size = max(t->logical_block_size,
                                     b->logical_block_size);
 
@@ -544,58 +573,95 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
                                      b->physical_block_size);
 
         t->io_min = max(t->io_min, b->io_min);
+        t->io_opt = lcm(t->io_opt, b->io_opt);
+
         t->no_cluster |= b->no_cluster;
         t->discard_zeroes_data &= b->discard_zeroes_data;
 
-        /* Bottom device offset aligned? */
-        if (offset &&
-            (offset & (b->physical_block_size - 1)) != b->alignment_offset) {
+        /* Physical block size a multiple of the logical block size? */
+        if (t->physical_block_size & (t->logical_block_size - 1)) {
+                t->physical_block_size = t->logical_block_size;
                 t->misaligned = 1;
                 ret = -1;
         }
 
-        /*
-         * Temporarily disable discard granularity. It's currently buggy
-         * since we default to 0 for discard_granularity, hence this
-         * "failure" will always trigger for non-zero offsets.
-         */
-#if 0
-        if (offset &&
-            (offset & (b->discard_granularity - 1)) != b->discard_alignment) {
-                t->discard_misaligned = 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;
         }
-#endif
 
-        /* If top has no alignment offset, inherit from bottom */
-        if (!t->alignment_offset)
-                t->alignment_offset =
-                        b->alignment_offset & (b->physical_block_size - 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;
+        }
 
-        if (!t->discard_alignment)
-                t->discard_alignment =
-                        b->discard_alignment & (b->discard_granularity - 1);
+        /* Find lowest common alignment_offset */
+        t->alignment_offset = lcm(t->alignment_offset, alignment)
+                & (max(t->physical_block_size, t->io_min) - 1);
 
-        /* Top device aligned on logical block boundary? */
+        /* Verify that new alignment_offset is on a logical block boundary */
         if (t->alignment_offset & (t->logical_block_size - 1)) {
                 t->misaligned = 1;
                 ret = -1;
         }
 
-        /* Find lcm() of optimal I/O size and granularity */
-        t->io_opt = lcm(t->io_opt, b->io_opt);
-        t->discard_granularity = lcm(t->discard_granularity,
-                                     b->discard_granularity);
-
-        /* Verify that optimal I/O size is a multiple of io_min */
-        if (t->io_min && t->io_opt % t->io_min)
-                ret = -1;
+        /* Discard alignment and granularity */
+        if (b->discard_granularity) {
+                unsigned int granularity = b->discard_granularity;
+                offset &= granularity - 1;
+
+                alignment = (granularity + b->discard_alignment - offset)
+                        & (granularity - 1);
+
+                if (t->discard_granularity != 0 &&
+                    t->discard_alignment != alignment) {
+                        top = t->discard_granularity + t->discard_alignment;
+                        bottom = b->discard_granularity + alignment;
+
+                        /* Verify that top and bottom intervals line up */
+                        if (max(top, bottom) & (min(top, bottom) - 1))
+                                t->discard_misaligned = 1;
+                }
+
+                t->max_discard_sectors = min_not_zero(t->max_discard_sectors,
+                                                      b->max_discard_sectors);
+                t->discard_granularity = max(t->discard_granularity,
+                                             b->discard_granularity);
+                t->discard_alignment = lcm(t->discard_alignment, alignment) &
+                        (t->discard_granularity - 1);
+        }
 
         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 e2f80463ed0d..ee130f14d1fc 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -208,8 +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
@@ -294,8 +292,7 @@ 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;
@@ -842,7 +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;
 }
 
@@ -863,7 +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);
@@ -1150,7 +1145,7 @@ static void cfq_service_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 #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);
@@ -1513,9 +1508,6 @@ static int cfq_allow_merge(struct request_queue *q, struct request *rq,
         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.
          */
@@ -1616,7 +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;
@@ -1675,13 +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;
 }
 
@@ -1709,7 +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)
@@ -1720,7 +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;
@@ -1963,8 +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;
@@ -1972,24 +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;
@@ -2003,8 +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;
@@ -2032,24 +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;
 
         /*
@@ -3104,6 +3077,12 @@ 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.
          */
@@ -3143,7 +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;
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);