Pull block layer core bits from Jens Axboe:
 "This is the core pull request for 4.1.  Not a lot of stuff in here for
  this round, mostly little fixes or optimizations.  This pull request
  contains:

   - An optimization that speeds up queue runs on blk-mq, especially for
     the case where there's a large difference between nr_cpu_ids and
     the actual mapped software queues on a hardware queue.  From Chong
     Yuan.

   - Honor node local allocations for requests on legacy devices.  From
     David Rientjes.

   - Cleanup of blk_mq_rq_to_pdu() from me.

   - exit_aio() fixup from me, greatly speeding up exiting multiple IO
     contexts off exit_group().  For my particular test case, fio exit
     took ~6 seconds.  A typical case of both exposing RCU grace periods
     to user space, and serializing exit of them.

   - Make blk_mq_queue_enter() honor the gfp mask passed in, so we only
     wait if __GFP_WAIT is set.  From Keith Busch.

   - blk-mq exports and two added helpers from Mike Snitzer, which will
     be used by the dm-mq code.

   - Cleanups of blk-mq queue init from Wei Fang and Xiaoguang Wang"

* 'for-4.1/core' of git://git.kernel.dk/linux-block:
  blk-mq: reduce unnecessary software queue looping
  aio: fix serial draining in exit_aio()
  blk-mq: cleanup blk_mq_rq_to_pdu()
  blk-mq: put blk_queue_rq_timeout together in blk_mq_init_queue()
  block: remove redundant check about 'set->nr_hw_queues' in blk_mq_alloc_tag_set()
  block: allocate request memory local to request queue
  blk-mq: don't wait in blk_mq_queue_enter() if __GFP_WAIT isn't set
  blk-mq: export blk_mq_run_hw_queues
  blk-mq: add blk_mq_init_allocated_queue and export blk_mq_register_disk