Merge branch 'for-4.12/block' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:

 - Add BFQ IO scheduler under the new blk-mq scheduling framework. BFQ
   was initially a fork of CFQ, but subsequently changed to implement
   fairness based on B-WF2Q+, a modified variant of WF2Q. BFQ is meant
   to be used on desktop type single drives, providing good fairness.
   From Paolo.

 - Add Kyber IO scheduler. This is a full multiqueue aware scheduler,
   using a scalable token based algorithm that throttles IO based on
   live completion IO stats, similary to blk-wbt. From Omar.

 - A series from Jan, moving users to separately allocated backing
   devices. This continues the work of separating backing device life
   times, solving various problems with hot removal.

 - A series of updates for lightnvm, mostly from Javier. Includes a
   'pblk' target that exposes an open channel SSD as a physical block
   device.

 - A series of fixes and improvements for nbd from Josef.

 - A series from Omar, removing queue sharing between devices on mostly
   legacy drivers. This helps us clean up other bits, if we know that a
   queue only has a single device backing. This has been overdue for
   more than a decade.

 - Fixes for the blk-stats, and improvements to unify the stats and user
   windows. This both improves blk-wbt, and enables other users to
   register a need to receive IO stats for a device. From Omar.

 - blk-throttle improvements from Shaohua. This provides a scalable
   framework for implementing scalable priotization - particularly for
   blk-mq, but applicable to any type of block device. The interface is
   marked experimental for now.

 - Bucketized IO stats for IO polling from Stephen Bates. This improves
   efficiency of polled workloads in the presence of mixed block size
   IO.

 - A few fixes for opal, from Scott.

 - A few pulls for NVMe, including a lot of fixes for NVMe-over-fabrics.
   From a variety of folks, mostly Sagi and James Smart.

 - A series from Bart, improving our exposed info and capabilities from
   the blk-mq debugfs support.

 - A series from Christoph, cleaning up how handle WRITE_ZEROES.

 - A series from Christoph, cleaning up the block layer handling of how
   we track errors in a request. On top of being a nice cleanup, it also
   shrinks the size of struct request a bit.

 - Removal of mg_disk and hd (sorry Linus) by Christoph. The former was
   never used by platforms, and the latter has outlived it's usefulness.

 - Various little bug fixes and cleanups from a wide variety of folks.

* 'for-4.12/block' of git://git.kernel.dk/linux-block: (329 commits)
  block: hide badblocks attribute by default
  blk-mq: unify hctx delay_work and run_work
  block: add kblock_mod_delayed_work_on()
  blk-mq: unify hctx delayed_run_work and run_work
  nbd: fix use after free on module unload
  MAINTAINERS: bfq: Add Paolo as maintainer for the BFQ I/O scheduler
  blk-mq-sched: alloate reserved tags out of normal pool
  mtip32xx: use runtime tag to initialize command header
  scsi: Implement blk_mq_ops.show_rq()
  blk-mq: Add blk_mq_ops.show_rq()
  blk-mq: Show operation, cmd_flags and rq_flags names
  blk-mq: Make blk_flags_show() callers append a newline character
  blk-mq: Move the "state" debugfs attribute one level down
  blk-mq: Unregister debugfs attributes earlier
  blk-mq: Only unregister hctxs for which registration succeeded
  blk-mq-debugfs: Rename functions for registering and unregistering the mq directory
  blk-mq: Let blk_mq_debugfs_register() look up the queue name
  blk-mq: Register <dev>/queue/mq after having registered <dev>/queue
  ide-pm: always pass 0 error to ide_complete_rq in ide_do_devset
  ide-pm: always pass 0 error to __blk_end_request_all
  ..

Documentation/ABI/testing/sysfs-block

@@ -213,14 +213,8 @@ What:		/sys/block/<disk>/queue/discard_zeroes_data
 Date:		May 2011
 Contact:	Martin K. Petersen <martin.petersen@oracle.com>
 Description:
-		Devices that support discard functionality may return
-		stale or random data when a previously discarded block
-		is read back. This can cause problems if the filesystem
-		expects discarded blocks to be explicitly cleared. If a
-		device reports that it deterministically returns zeroes
-		when a discarded area is read the discard_zeroes_data
-		parameter will be set to one. Otherwise it will be 0 and
-		the result of reading a discarded area is undefined.
+		Will always return 0.  Don't rely on any specific behavior
+		for discards, and don't read this file.
 
 What:		/sys/block/<disk>/queue/write_same_max_bytes
 Date:		January 2012

Documentation/block/00-INDEX

@@ -1,5 +1,7 @@
 00-INDEX
 	- This file
+bfq-iosched.txt
+	- BFQ IO scheduler and its tunables
 biodoc.txt
 	- Notes on the Generic Block Layer Rewrite in Linux 2.5
 biovecs.txt

Documentation/block/bfq-iosched.txt

@@ -0,0 +1,531 @@
+BFQ (Budget Fair Queueing)
+==========================
+
+BFQ is a proportional-share I/O scheduler, with some extra
+low-latency capabilities. In addition to cgroups support (blkio or io
+controllers), BFQ's main features are:
+- BFQ guarantees a high system and application responsiveness, and a
+  low latency for time-sensitive applications, such as audio or video
+  players;
+- BFQ distributes bandwidth, and not just time, among processes or
+  groups (switching back to time distribution when needed to keep
+  throughput high).
+
+On average CPUs, the current version of BFQ can handle devices
+performing at most ~30K IOPS; at most ~50 KIOPS on faster CPUs. As a
+reference, 30-50 KIOPS correspond to very high bandwidths with
+sequential I/O (e.g., 8-12 GB/s if I/O requests are 256 KB large), and
+to 120-200 MB/s with 4KB random I/O. BFQ has not yet been tested on
+multi-queue devices.
+
+The table of contents follow. Impatients can just jump to Section 3.
+
+CONTENTS
+
+1. When may BFQ be useful?
+ 1-1 Personal systems
+ 1-2 Server systems
+2. How does BFQ work?
+3. What are BFQ's tunable?
+4. BFQ group scheduling
+ 4-1 Service guarantees provided
+ 4-2 Interface
+
+1. When may BFQ be useful?
+==========================
+
+BFQ provides the following benefits on personal and server systems.
+
+1-1 Personal systems
+--------------------
+
+Low latency for interactive applications
+
+Regardless of the actual background workload, BFQ guarantees that, for
+interactive tasks, the storage device is virtually as responsive as if
+it was idle. For example, even if one or more of the following
+background workloads are being executed:
+- one or more large files are being read, written or copied,
+- a tree of source files is being compiled,
+- one or more virtual machines are performing I/O,
+- a software update is in progress,
+- indexing daemons are scanning filesystems and updating their
+  databases,
+starting an application or loading a file from within an application
+takes about the same time as if the storage device was idle. As a
+comparison, with CFQ, NOOP or DEADLINE, and in the same conditions,
+applications experience high latencies, or even become unresponsive
+until the background workload terminates (also on SSDs).
+
+Low latency for soft real-time applications
+
+Also soft real-time applications, such as audio and video
+players/streamers, enjoy a low latency and a low drop rate, regardless
+of the background I/O workload. As a consequence, these applications
+do not suffer from almost any glitch due to the background workload.
+
+Higher speed for code-development tasks
+
+If some additional workload happens to be executed in parallel, then
+BFQ executes the I/O-related components of typical code-development
+tasks (compilation, checkout, merge, ...) much more quickly than CFQ,
+NOOP or DEADLINE.
+
+High throughput
+
+On hard disks, BFQ achieves up to 30% higher throughput than CFQ, and
+up to 150% higher throughput than DEADLINE and NOOP, with all the
+sequential workloads considered in our tests. With random workloads,
+and with all the workloads on flash-based devices, BFQ achieves,
+instead, about the same throughput as the other schedulers.
+
+Strong fairness, bandwidth and delay guarantees
+
+BFQ distributes the device throughput, and not just the device time,
+among I/O-bound applications in proportion their weights, with any
+workload and regardless of the device parameters. From these bandwidth
+guarantees, it is possible to compute tight per-I/O-request delay
+guarantees by a simple formula. If not configured for strict service
+guarantees, BFQ switches to time-based resource sharing (only) for
+applications that would otherwise cause a throughput loss.
+
+1-2 Server systems
+------------------
+
+Most benefits for server systems follow from the same service
+properties as above. In particular, regardless of whether additional,
+possibly heavy workloads are being served, BFQ guarantees:
+
+. audio and video-streaming with zero or very low jitter and drop
+  rate;
+
+. fast retrieval of WEB pages and embedded objects;
+
+. real-time recording of data in live-dumping applications (e.g.,
+  packet logging);
+
+. responsiveness in local and remote access to a server.
+
+
+2. How does BFQ work?
+=====================
+
+BFQ is a proportional-share I/O scheduler, whose general structure,
+plus a lot of code, are borrowed from CFQ.
+
+- Each process doing I/O on a device is associated with a weight and a
+  (bfq_)queue.
+
+- BFQ grants exclusive access to the device, for a while, to one queue
+  (process) at a time, and implements this service model by
+  associating every queue with a budget, measured in number of
+  sectors.
+
+  - After a queue is granted access to the device, the budget of the
+    queue is decremented, on each request dispatch, by the size of the
+    request.
+
+  - The in-service queue is expired, i.e., its service is suspended,
+    only if one of the following events occurs: 1) the queue finishes
+    its budget, 2) the queue empties, 3) a "budget timeout" fires.
+
+    - The budget timeout prevents processes doing random I/O from
+      holding the device for too long and dramatically reducing
+      throughput.
+
+    - Actually, as in CFQ, a queue associated with a process issuing
+      sync requests may not be expired immediately when it empties. In
+      contrast, BFQ may idle the device for a short time interval,
+      giving the process the chance to go on being served if it issues
+      a new request in time. Device idling typically boosts the
+      throughput on rotational devices, if processes do synchronous
+      and sequential I/O. In addition, under BFQ, device idling is
+      also instrumental in guaranteeing the desired throughput
+      fraction to processes issuing sync requests (see the description
+      of the slice_idle tunable in this document, or [1, 2], for more
+      details).
+
+      - With respect to idling for service guarantees, if several
+	processes are competing for the device at the same time, but
+	all processes (and groups, after the following commit) have
+	the same weight, then BFQ guarantees the expected throughput
+	distribution without ever idling the device. Throughput is
+	thus as high as possible in this common scenario.
+
+  - If low-latency mode is enabled (default configuration), BFQ
+    executes some special heuristics to detect interactive and soft
+    real-time applications (e.g., video or audio players/streamers),
+    and to reduce their latency. The most important action taken to
+    achieve this goal is to give to the queues associated with these
+    applications more than their fair share of the device
+    throughput. For brevity, we call just "weight-raising" the whole
+    sets of actions taken by BFQ to privilege these queues. In
+    particular, BFQ provides a milder form of weight-raising for
+    interactive applications, and a stronger form for soft real-time
+    applications.
+
+  - BFQ automatically deactivates idling for queues born in a burst of
+    queue creations. In fact, these queues are usually associated with
+    the processes of applications and services that benefit mostly
+    from a high throughput. Examples are systemd during boot, or git
+    grep.
+
+  - As CFQ, BFQ merges queues performing interleaved I/O, i.e.,
+    performing random I/O that becomes mostly sequential if
+    merged. Differently from CFQ, BFQ achieves this goal with a more
+    reactive mechanism, called Early Queue Merge (EQM). EQM is so
+    responsive in detecting interleaved I/O (cooperating processes),
+    that it enables BFQ to achieve a high throughput, by queue
+    merging, even for queues for which CFQ needs a different
+    mechanism, preemption, to get a high throughput. As such EQM is a
+    unified mechanism to achieve a high throughput with interleaved
+    I/O.
+
+  - Queues are scheduled according to a variant of WF2Q+, named
+    B-WF2Q+, and implemented using an augmented rb-tree to preserve an
+    O(log N) overall complexity.  See [2] for more details. B-WF2Q+ is
+    also ready for hierarchical scheduling. However, for a cleaner
+    logical breakdown, the code that enables and completes
+    hierarchical support is provided in the next commit, which focuses
+    exactly on this feature.
+
+  - B-WF2Q+ guarantees a tight deviation with respect to an ideal,
+    perfectly fair, and smooth service. In particular, B-WF2Q+
+    guarantees that each queue receives a fraction of the device
+    throughput proportional to its weight, even if the throughput
+    fluctuates, and regardless of: the device parameters, the current
+    workload and the budgets assigned to the queue.
+
+  - The last, budget-independence, property (although probably
+    counterintuitive in the first place) is definitely beneficial, for
+    the following reasons:
+
+    - First, with any proportional-share scheduler, the maximum
+      deviation with respect to an ideal service is proportional to
+      the maximum budget (slice) assigned to queues. As a consequence,
+      BFQ can keep this deviation tight not only because of the
+      accurate service of B-WF2Q+, but also because BFQ *does not*
+      need to assign a larger budget to a queue to let the queue
+      receive a higher fraction of the device throughput.
+
+    - Second, BFQ is free to choose, for every process (queue), the
+      budget that best fits the needs of the process, or best
+      leverages the I/O pattern of the process. In particular, BFQ
+      updates queue budgets with a simple feedback-loop algorithm that
+      allows a high throughput to be achieved, while still providing
+      tight latency guarantees to time-sensitive applications. When
+      the in-service queue expires, this algorithm computes the next
+      budget of the queue so as to:
+
+      - Let large budgets be eventually assigned to the queues
+	associated with I/O-bound applications performing sequential
+	I/O: in fact, the longer these applications are served once
+	got access to the device, the higher the throughput is.
+
+      - Let small budgets be eventually assigned to the queues
+	associated with time-sensitive applications (which typically
+	perform sporadic and short I/O), because, the smaller the
+	budget assigned to a queue waiting for service is, the sooner
+	B-WF2Q+ will serve that queue (Subsec 3.3 in [2]).
+
+- If several processes are competing for the device at the same time,
+  but all processes and groups have the same weight, then BFQ
+  guarantees the expected throughput distribution without ever idling
+  the device. It uses preemption instead. Throughput is then much
+  higher in this common scenario.
+
+- ioprio classes are served in strict priority order, i.e.,
+  lower-priority queues are not served as long as there are
+  higher-priority queues.  Among queues in the same class, the
+  bandwidth is distributed in proportion to the weight of each
+  queue. A very thin extra bandwidth is however guaranteed to
+  the Idle class, to prevent it from starving.
+
+
+3. What are BFQ's tunable?
+==========================
+
+The tunables back_seek-max, back_seek_penalty, fifo_expire_async and
+fifo_expire_sync below are the same as in CFQ. Their description is
+just copied from that for CFQ. Some considerations in the description
+of slice_idle are copied from CFQ too.
+
+per-process ioprio and weight
+-----------------------------
+
+Unless the cgroups interface is used (see "4. BFQ group scheduling"),
+weights can be assigned to processes only indirectly, through I/O
+priorities, and according to the relation:
+weight = (IOPRIO_BE_NR - ioprio) * 10.
+
+Beware that, if low-latency is set, then BFQ automatically raises the
+weight of the queues associated with interactive and soft real-time
+applications. Unset this tunable if you need/want to control weights.
+
+slice_idle
+----------
+
+This parameter specifies how long BFQ should idle for next I/O
+request, when certain sync BFQ queues become empty. By default
+slice_idle is a non-zero value. Idling has a double purpose: boosting
+throughput and making sure that the desired throughput distribution is
+respected (see the description of how BFQ works, and, if needed, the
+papers referred there).
+
+As for throughput, idling can be very helpful on highly seeky media
+like single spindle SATA/SAS disks where we can cut down on overall
+number of seeks and see improved throughput.
+
+Setting slice_idle to 0 will remove all the idling on queues and one
+should see an overall improved throughput on faster storage devices
+like multiple SATA/SAS disks in hardware RAID configuration.
+
+So depending on storage and workload, it might be useful to set
+slice_idle=0.  In general for SATA/SAS disks and software RAID of
+SATA/SAS disks keeping slice_idle enabled should be useful. For any
+configurations where there are multiple spindles behind single LUN
+(Host based hardware RAID controller or for storage arrays), setting
+slice_idle=0 might end up in better throughput and acceptable
+latencies.
+
+Idling is however necessary to have service guarantees enforced in
+case of differentiated weights or differentiated I/O-request lengths.
+To see why, suppose that a given BFQ queue A must get several I/O
+requests served for each request served for another queue B. Idling
+ensures that, if A makes a new I/O request slightly after becoming
+empty, then no request of B is dispatched in the middle, and thus A
+does not lose the possibility to get more than one request dispatched
+before the next request of B is dispatched. Note that idling
+guarantees the desired differentiated treatment of queues only in
+terms of I/O-request dispatches. To guarantee that the actual service
+order then corresponds to the dispatch order, the strict_guarantees
+tunable must be set too.
+
+There is an important flipside for idling: apart from the above cases
+where it is beneficial also for throughput, idling can severely impact
+throughput. One important case is random workload. Because of this
+issue, BFQ tends to avoid idling as much as possible, when it is not
+beneficial also for throughput. As a consequence of this behavior, and
+of further issues described for the strict_guarantees tunable,
+short-term service guarantees may be occasionally violated. And, in
+some cases, these guarantees may be more important than guaranteeing
+maximum throughput. For example, in video playing/streaming, a very
+low drop rate may be more important than maximum throughput. In these
+cases, consider setting the strict_guarantees parameter.
+
+strict_guarantees
+-----------------
+
+If this parameter is set (default: unset), then BFQ
+
+- always performs idling when the in-service queue becomes empty;
+
+- forces the device to serve one I/O request at a time, by dispatching a
+  new request only if there is no outstanding request.
+
+In the presence of differentiated weights or I/O-request sizes, both
+the above conditions are needed to guarantee that every BFQ queue
+receives its allotted share of the bandwidth. The first condition is
+needed for the reasons explained in the description of the slice_idle
+tunable.  The second condition is needed because all modern storage
+devices reorder internally-queued requests, which may trivially break
+the service guarantees enforced by the I/O scheduler.
+
+Setting strict_guarantees may evidently affect throughput.
+
+back_seek_max
+-------------
+
+This specifies, given in Kbytes, the maximum "distance" for backward seeking.
+The distance is the amount of space from the current head location to the
+sectors that are backward in terms of distance.
+
+This parameter allows the scheduler to anticipate requests in the "backward"
+direction and consider them as being the "next" if they are within this
+distance from the current head location.
+
+back_seek_penalty
+-----------------
+
+This parameter is used to compute the cost of backward seeking. If the
+backward distance of request is just 1/back_seek_penalty from a "front"
+request, then the seeking cost of two requests is considered equivalent.
+
+So scheduler will not bias toward one or the other request (otherwise scheduler
+will bias toward front request). Default value of back_seek_penalty is 2.
+
+fifo_expire_async
+-----------------
+
+This parameter is used to set the timeout of asynchronous requests. Default
+value of this is 248ms.
+
+fifo_expire_sync
+----------------
+
+This parameter is used to set the timeout of synchronous requests. Default
+value of this is 124ms. In case to favor synchronous requests over asynchronous
+one, this value should be decreased relative to fifo_expire_async.
+
+low_latency
+-----------
+
+This parameter is used to enable/disable BFQ's low latency mode. By
+default, low latency mode is enabled. If enabled, interactive and soft
+real-time applications are privileged and experience a lower latency,
+as explained in more detail in the description of how BFQ works.
+
+DO NOT enable this mode if you need full control on bandwidth
+distribution. In fact, if it is enabled, then BFQ automatically
+increases the bandwidth share of privileged applications, as the main
+means to guarantee a lower latency to them.
+
+timeout_sync
+------------
+
+Maximum amount of device time that can be given to a task (queue) once
+it has been selected for service. On devices with costly seeks,
+increasing this time usually increases maximum throughput. On the
+opposite end, increasing this time coarsens the granularity of the
+short-term bandwidth and latency guarantees, especially if the
+following parameter is set to zero.
+
+max_budget
+----------
+
+Maximum amount of service, measured in sectors, that can be provided
+to a BFQ queue once it is set in service (of course within the limits
+of the above timeout). According to what said in the description of
+the algorithm, larger values increase the throughput in proportion to
+the percentage of sequential I/O requests issued. The price of larger
+values is that they coarsen the granularity of short-term bandwidth
+and latency guarantees.
+
+The default value is 0, which enables auto-tuning: BFQ sets max_budget
+to the maximum number of sectors that can be served during
+timeout_sync, according to the estimated peak rate.
+
+weights
+-------
+
+Read-only parameter, used to show the weights of the currently active
+BFQ queues.
+
+
+wr_ tunables
+------------
+
+BFQ exports a few parameters to control/tune the behavior of
+low-latency heuristics.
+
+wr_coeff
+
+Factor by which the weight of a weight-raised queue is multiplied. If
+the queue is deemed soft real-time, then the weight is further
+multiplied by an additional, constant factor.
+
+wr_max_time
+
+Maximum duration of a weight-raising period for an interactive task
+(ms). If set to zero (default value), then this value is computed
+automatically, as a function of the peak rate of the device. In any
+case, when the value of this parameter is read, it always reports the
+current duration, regardless of whether it has been set manually or
+computed automatically.
+
+wr_max_softrt_rate
+
+Maximum service rate below which a queue is deemed to be associated
+with a soft real-time application, and is then weight-raised
+accordingly (sectors/sec).
+
+wr_min_idle_time
+
+Minimum idle period after which interactive weight-raising may be
+reactivated for a queue (in ms).
+
+wr_rt_max_time
+
+Maximum weight-raising duration for soft real-time queues (in ms). The
+start time from which this duration is considered is automatically
+moved forward if the queue is detected to be still soft real-time
+before the current soft real-time weight-raising period finishes.
+
+wr_min_inter_arr_async
+
+Minimum period between I/O request arrivals after which weight-raising
+may be reactivated for an already busy async queue (in ms).
+
+
+4. Group scheduling with BFQ
+============================
+
+BFQ supports both cgroups-v1 and cgroups-v2 io controllers, namely
+blkio and io. In particular, BFQ supports weight-based proportional
+share. To activate cgroups support, set BFQ_GROUP_IOSCHED.
+
+4-1 Service guarantees provided
+-------------------------------
+
+With BFQ, proportional share means true proportional share of the
+device bandwidth, according to group weights. For example, a group
+with weight 200 gets twice the bandwidth, and not just twice the time,
+of a group with weight 100.
+
+BFQ supports hierarchies (group trees) of any depth. Bandwidth is
+distributed among groups and processes in the expected way: for each
+group, the children of the group share the whole bandwidth of the
+group in proportion to their weights. In particular, this implies
+that, for each leaf group, every process of the group receives the
+same share of the whole group bandwidth, unless the ioprio of the
+process is modified.
+
+The resource-sharing guarantee for a group may partially or totally
+switch from bandwidth to time, if providing bandwidth guarantees to
+the group lowers the throughput too much. This switch occurs on a
+per-process basis: if a process of a leaf group causes throughput loss
+if served in such a way to receive its share of the bandwidth, then
+BFQ switches back to just time-based proportional share for that
+process.
+
+4-2 Interface
+-------------
+
+To get proportional sharing of bandwidth with BFQ for a given device,
+BFQ must of course be the active scheduler for that device.
+
+Within each group directory, the names of the files associated with
+BFQ-specific cgroup parameters and stats begin with the "bfq."
+prefix. So, with cgroups-v1 or cgroups-v2, the full prefix for
+BFQ-specific files is "blkio.bfq." or "io.bfq." For example, the group
+parameter to set the weight of a group with BFQ is blkio.bfq.weight
+or io.bfq.weight.
+
+Parameters to set
+-----------------
+
+For each group, there is only the following parameter to set.
+
+weight (namely blkio.bfq.weight or io.bfq-weight): the weight of the
+group inside its parent. Available values: 1..10000 (default 100). The
+linear mapping between ioprio and weights, described at the beginning
+of the tunable section, is still valid, but all weights higher than
+IOPRIO_BE_NR*10 are mapped to ioprio 0.
+
+Recall that, if low-latency is set, then BFQ automatically raises the
+weight of the queues associated with interactive and soft real-time
+applications. Unset this tunable if you need/want to control weights.
+
+
+[1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
+    Scheduler", Proceedings of the First Workshop on Mobile System
+    Technologies (MST-2015), May 2015.
+    http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf
+
+[2] P. Valente and M. Andreolini, "Improving Application
+    Responsiveness with the BFQ Disk I/O Scheduler", Proceedings of
+    the 5th Annual International Systems and Storage Conference
+    (SYSTOR '12), June 2012.
+    Slightly extended version:
+    http://algogroup.unimore.it/people/paolo/disk_sched/bfq-v1-suite-
+							results.pdf

Documentation/block/kyber-iosched.txt

@@ -0,0 +1,14 @@
+Kyber I/O scheduler tunables
+===========================
+
+The only two tunables for the Kyber scheduler are the target latencies for
+reads and synchronous writes. Kyber will throttle requests in order to meet
+these target latencies.
+
+read_lat_nsec
+-------------
+Target latency for reads (in nanoseconds).
+
+write_lat_nsec
+--------------
+Target latency for synchronous writes (in nanoseconds).

Documentation/block/queue-sysfs.txt

@@ -43,11 +43,6 @@ large discards are issued, setting this value lower will make Linux issue
 smaller discards and potentially help reduce latencies induced by large
 discard operations.
 
-discard_zeroes_data (RO)
-------------------------
-When read, this file will show if the discarded block are zeroed by the
-device or not. If its value is '1' the blocks are zeroed otherwise not.
-
 hw_sector_size (RO)
 -------------------
 This is the hardware sector size of the device, in bytes.
@@ -192,5 +187,11 @@ scaling back writes. Writing a value of '0' to this file disables the
 feature. Writing a value of '-1' to this file resets the value to the
 default setting.
 
+throttle_sample_time (RW)
+-------------------------
+This is the time window that blk-throttle samples data, in millisecond.
+blk-throttle makes decision based on the samplings. Lower time means cgroups
+have more smooth throughput, but higher CPU overhead. This exists only when
+CONFIG_BLK_DEV_THROTTLING_LOW is enabled.
 
 Jens Axboe <jens.axboe@oracle.com>, February 2009

Documentation/blockdev/mflash.txt

@@ -1,84 +0,0 @@
-This document describes m[g]flash support in linux.
-
-Contents
-  1. Overview
-  2. Reserved area configuration
-  3. Example of mflash platform driver registration
-
-1. Overview
-
-Mflash and gflash are embedded flash drive. The only difference is mflash is
-MCP(Multi Chip Package) device. These two device operate exactly same way.
-So the rest mflash repersents mflash and gflash altogether.
-
-Internally, mflash has nand flash and other hardware logics and supports
-2 different operation (ATA, IO) modes. ATA mode doesn't need any new
-driver and currently works well under standard IDE subsystem. Actually it's
-one chip SSD. IO mode is ATA-like custom mode for the host that doesn't have
-IDE interface.
-
-Following are brief descriptions about IO mode.
-A. IO mode based on ATA protocol and uses some custom command. (read confirm,
-write confirm)
-B. IO mode uses SRAM bus interface.
-C. IO mode supports 4kB boot area, so host can boot from mflash.
-
-2. Reserved area configuration
-If host boot from mflash, usually needs raw area for boot loader image. All of
-the mflash's block device operation will be taken this value as start offset.
-Note that boot loader's size of reserved area and kernel configuration value
-must be same.
-
-3. Example of mflash platform driver registration
-Working mflash is very straight forward. Adding platform device stuff to board
-configuration file is all. Here is some pseudo example.
-
-static struct mg_drv_data mflash_drv_data = {
-	/* If you want to polling driver set to 1 */
-	.use_polling = 0,
-	/* device attribution */
-	.dev_attr = MG_BOOT_DEV
-};
-
-static struct resource mg_mflash_rsc[] = {
-	/* Base address of mflash */
-	[0] = {
-		.start = 0x08000000,
-		.end = 0x08000000 + SZ_64K - 1,
-		.flags = IORESOURCE_MEM
-	},
-	/* mflash interrupt pin */
-	[1] = {
-		.start = IRQ_GPIO(84),
-		.end = IRQ_GPIO(84),
-		.flags = IORESOURCE_IRQ
-	},
-	/* mflash reset pin */
-	[2] = {
-		.start = 43,
-		.end = 43,
-		.name = MG_RST_PIN,
-		.flags = IORESOURCE_IO
-	},
-	/* mflash reset-out pin
-	 * If you use mflash as storage device (i.e. other than MG_BOOT_DEV),
-	 * should assign this */
-	[3] = {
-		.start = 51,
-		.end = 51,
-		.name = MG_RSTOUT_PIN,
-		.flags = IORESOURCE_IO
-	}
-};
-
-static struct platform_device mflash_dev = {
-	.name = MG_DEV_NAME,
-	.id = -1,
-	.dev = {
-		.platform_data = &mflash_drv_data,
-	},
-	.num_resources = ARRAY_SIZE(mg_mflash_rsc),
-	.resource = mg_mflash_rsc
-};
-
-platform_device_register(&mflash_dev);

Documentation/lightnvm/pblk.txt

@@ -0,0 +1,21 @@
+pblk: Physical Block Device Target
+==================================
+
+pblk implements a fully associative, host-based FTL that exposes a traditional
+block I/O interface. Its primary responsibilities are:
+
+  - Map logical addresses onto physical addresses (4KB granularity) in a
+    logical-to-physical (L2P) table.
+  - Maintain the integrity and consistency of the L2P table as well as its
+    recovery from normal tear down and power outage.
+  - Deal with controller- and media-specific constrains.
+  - Handle I/O errors.
+  - Implement garbage collection.
+  - Maintain consistency across the I/O stack during synchronization points.
+
+For more information please refer to:
+
+  http://lightnvm.io
+
+which maintains updated FAQs, manual pages, technical documentation, tools,
+contacts, etc.

MAINTAINERS

@@ -2544,6 +2544,14 @@ F:	block/
 F:	kernel/trace/blktrace.c
 F:	lib/sbitmap.c
 
+BFQ I/O SCHEDULER
+M:	Paolo Valente <paolo.valente@linaro.org>
+M:	Jens Axboe <axboe@kernel.dk>
+L:	linux-block@vger.kernel.org
+S:	Maintained
+F:	block/bfq-*
+F:	Documentation/block/bfq-iosched.txt
+
 BLOCK2MTD DRIVER
 M:	Joern Engel <joern@lazybastard.org>
 L:	linux-mtd@lists.infradead.org

block/Kconfig

@@ -115,6 +115,18 @@ config BLK_DEV_THROTTLING
 
 	See Documentation/cgroups/blkio-controller.txt for more information.
 
+config BLK_DEV_THROTTLING_LOW
+	bool "Block throttling .low limit interface support (EXPERIMENTAL)"
+	depends on BLK_DEV_THROTTLING
+	default n
+	---help---
+	Add .low limit interface for block throttling. The low limit is a best
+	effort limit to prioritize cgroups. Depending on the setting, the limit
+	can be used to protect cgroups in terms of bandwidth/iops and better
+	utilize disk resource.
+
+	Note, this is an experimental interface and could be changed someday.
+
 config BLK_CMDLINE_PARSER
 	bool "Block device command line partition parser"
 	default n

block/Kconfig.iosched

@@ -40,6 +40,7 @@ config CFQ_GROUP_IOSCHED
 	  Enable group IO scheduling in CFQ.
 
 choice
+
 	prompt "Default I/O scheduler"
 	default DEFAULT_CFQ
 	help
@@ -69,6 +70,35 @@ config MQ_IOSCHED_DEADLINE
 	---help---
 	  MQ version of the deadline IO scheduler.
 
+config MQ_IOSCHED_KYBER
+	tristate "Kyber I/O scheduler"
+	default y
+	---help---
+	  The Kyber I/O scheduler is a low-overhead scheduler suitable for
+	  multiqueue and other fast devices. Given target latencies for reads and
+	  synchronous writes, it will self-tune queue depths to achieve that
+	  goal.
+
+config IOSCHED_BFQ
+	tristate "BFQ I/O scheduler"
+	default n
+	---help---
+	BFQ I/O scheduler for BLK-MQ. BFQ distributes the bandwidth of
+	of the device among all processes according to their weights,
+	regardless of the device parameters and with any workload. It
+	also guarantees a low latency to interactive and soft
+	real-time applications.  Details in
+	Documentation/block/bfq-iosched.txt
+
+config BFQ_GROUP_IOSCHED
+       bool "BFQ hierarchical scheduling support"
+       depends on IOSCHED_BFQ && BLK_CGROUP
+       default n
+       ---help---
+
+       Enable hierarchical scheduling in BFQ, using the blkio
+       (cgroups-v1) or io (cgroups-v2) controller.
+
 endmenu
 
 endif

block/Makefile

@@ -20,6 +20,9 @@ obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
 obj-$(CONFIG_MQ_IOSCHED_DEADLINE)	+= mq-deadline.o
+obj-$(CONFIG_MQ_IOSCHED_KYBER)	+= kyber-iosched.o
+bfq-y				:= bfq-iosched.o bfq-wf2q.o bfq-cgroup.o
+obj-$(CONFIG_IOSCHED_BFQ)	+= bfq.o
 
 obj-$(CONFIG_BLOCK_COMPAT)	+= compat_ioctl.o
 obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o

block/bfq-cgroup.c

@@ -0,0 +1,1139 @@
+/*
+ * cgroups support for the BFQ I/O scheduler.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License as
+ *  published by the Free Software Foundation; either version 2 of the
+ *  License, or (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ */
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <linux/cgroup.h>
+#include <linux/elevator.h>
+#include <linux/ktime.h>
+#include <linux/rbtree.h>
+#include <linux/ioprio.h>
+#include <linux/sbitmap.h>
+#include <linux/delay.h>
+
+#include "bfq-iosched.h"
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+
+/* bfqg stats flags */
+enum bfqg_stats_flags {
+	BFQG_stats_waiting = 0,
+	BFQG_stats_idling,
+	BFQG_stats_empty,
+};
+
+#define BFQG_FLAG_FNS(name)						\
+static void bfqg_stats_mark_##name(struct bfqg_stats *stats)	\
+{									\
+	stats->flags |= (1 << BFQG_stats_##name);			\
+}									\
+static void bfqg_stats_clear_##name(struct bfqg_stats *stats)	\
+{									\
+	stats->flags &= ~(1 << BFQG_stats_##name);			\
+}									\
+static int bfqg_stats_##name(struct bfqg_stats *stats)		\
+{									\
+	return (stats->flags & (1 << BFQG_stats_##name)) != 0;		\
+}									\
+
+BFQG_FLAG_FNS(waiting)
+BFQG_FLAG_FNS(idling)
+BFQG_FLAG_FNS(empty)
+#undef BFQG_FLAG_FNS
+
+/* This should be called with the queue_lock held. */
+static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
+{
+	unsigned long long now;
+
+	if (!bfqg_stats_waiting(stats))
+		return;
+
+	now = sched_clock();
+	if (time_after64(now, stats->start_group_wait_time))
+		blkg_stat_add(&stats->group_wait_time,
+			      now - stats->start_group_wait_time);
+	bfqg_stats_clear_waiting(stats);
+}
+
+/* This should be called with the queue_lock held. */
+static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
+						 struct bfq_group *curr_bfqg)
+{
+	struct bfqg_stats *stats = &bfqg->stats;
+
+	if (bfqg_stats_waiting(stats))
+		return;
+	if (bfqg == curr_bfqg)
+		return;
+	stats->start_group_wait_time = sched_clock();
+	bfqg_stats_mark_waiting(stats);
+}
+
+/* This should be called with the queue_lock held. */
+static void bfqg_stats_end_empty_time(struct bfqg_stats *stats)
+{
+	unsigned long long now;
+
+	if (!bfqg_stats_empty(stats))
+		return;
+
+	now = sched_clock();
+	if (time_after64(now, stats->start_empty_time))
+		blkg_stat_add(&stats->empty_time,
+			      now - stats->start_empty_time);
+	bfqg_stats_clear_empty(stats);
+}
+
+void bfqg_stats_update_dequeue(struct bfq_group *bfqg)
+{
+	blkg_stat_add(&bfqg->stats.dequeue, 1);
+}
+
+void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg)
+{
+	struct bfqg_stats *stats = &bfqg->stats;
+
+	if (blkg_rwstat_total(&stats->queued))
+		return;
+
+	/*
+	 * group is already marked empty. This can happen if bfqq got new
+	 * request in parent group and moved to this group while being added
+	 * to service tree. Just ignore the event and move on.
+	 */
+	if (bfqg_stats_empty(stats))
+		return;
+
+	stats->start_empty_time = sched_clock();
+	bfqg_stats_mark_empty(stats);
+}
+
+void bfqg_stats_update_idle_time(struct bfq_group *bfqg)
+{
+	struct bfqg_stats *stats = &bfqg->stats;
+
+	if (bfqg_stats_idling(stats)) {
+		unsigned long long now = sched_clock();
+
+		if (time_after64(now, stats->start_idle_time))
+			blkg_stat_add(&stats->idle_time,
+				      now - stats->start_idle_time);
+		bfqg_stats_clear_idling(stats);
+	}
+}
+
+void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg)
+{
+	struct bfqg_stats *stats = &bfqg->stats;
+
+	stats->start_idle_time = sched_clock();
+	bfqg_stats_mark_idling(stats);
+}
+
+void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg)
+{
+	struct bfqg_stats *stats = &bfqg->stats;
+
+	blkg_stat_add(&stats->avg_queue_size_sum,
+		      blkg_rwstat_total(&stats->queued));
+	blkg_stat_add(&stats->avg_queue_size_samples, 1);
+	bfqg_stats_update_group_wait_time(stats);
+}
+
+/*
+ * blk-cgroup policy-related handlers
+ * The following functions help in converting between blk-cgroup
+ * internal structures and BFQ-specific structures.
+ */
+
+static struct bfq_group *pd_to_bfqg(struct blkg_policy_data *pd)
+{
+	return pd ? container_of(pd, struct bfq_group, pd) : NULL;
+}
+
+struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg)
+{
+	return pd_to_blkg(&bfqg->pd);
+}
+
+static struct bfq_group *blkg_to_bfqg(struct blkcg_gq *blkg)
+{
+	return pd_to_bfqg(blkg_to_pd(blkg, &blkcg_policy_bfq));
+}
+
+/*
+ * bfq_group handlers
+ * The following functions help in navigating the bfq_group hierarchy
+ * by allowing to find the parent of a bfq_group or the bfq_group
+ * associated to a bfq_queue.
+ */
+
+static struct bfq_group *bfqg_parent(struct bfq_group *bfqg)
+{
+	struct blkcg_gq *pblkg = bfqg_to_blkg(bfqg)->parent;
+
+	return pblkg ? blkg_to_bfqg(pblkg) : NULL;
+}
+
+struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
+{
+	struct bfq_entity *group_entity = bfqq->entity.parent;
+
+	return group_entity ? container_of(group_entity, struct bfq_group,
+					   entity) :
+			      bfqq->bfqd->root_group;
+}
+
+/*
+ * The following two functions handle get and put of a bfq_group by
+ * wrapping the related blk-cgroup hooks.
+ */
+
+static void bfqg_get(struct bfq_group *bfqg)
+{
+	return blkg_get(bfqg_to_blkg(bfqg));
+}
+
+void bfqg_put(struct bfq_group *bfqg)
+{
+	return blkg_put(bfqg_to_blkg(bfqg));
+}
+
+void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
+			      unsigned int op)
+{
+	blkg_rwstat_add(&bfqg->stats.queued, op, 1);
+	bfqg_stats_end_empty_time(&bfqg->stats);
+	if (!(bfqq == ((struct bfq_data *)bfqg->bfqd)->in_service_queue))
+		bfqg_stats_set_start_group_wait_time(bfqg, bfqq_group(bfqq));
+}
+
+void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op)
+{
+	blkg_rwstat_add(&bfqg->stats.queued, op, -1);
+}
+
+void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op)
+{
+	blkg_rwstat_add(&bfqg->stats.merged, op, 1);
+}
+
+void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
+				  uint64_t io_start_time, unsigned int op)
+{
+	struct bfqg_stats *stats = &bfqg->stats;
+	unsigned long long now = sched_clock();
+
+	if (time_after64(now, io_start_time))
+		blkg_rwstat_add(&stats->service_time, op,
+				now - io_start_time);
+	if (time_after64(io_start_time, start_time))
+		blkg_rwstat_add(&stats->wait_time, op,
+				io_start_time - start_time);
+}
+
+/* @stats = 0 */
+static void bfqg_stats_reset(struct bfqg_stats *stats)
+{
+	/* queued stats shouldn't be cleared */
+	blkg_rwstat_reset(&stats->merged);
+	blkg_rwstat_reset(&stats->service_time);
+	blkg_rwstat_reset(&stats->wait_time);
+	blkg_stat_reset(&stats->time);
+	blkg_stat_reset(&stats->avg_queue_size_sum);
+	blkg_stat_reset(&stats->avg_queue_size_samples);
+	blkg_stat_reset(&stats->dequeue);
+	blkg_stat_reset(&stats->group_wait_time);
+	blkg_stat_reset(&stats->idle_time);
+	blkg_stat_reset(&stats->empty_time);
+}
+
+/* @to += @from */
+static void bfqg_stats_add_aux(struct bfqg_stats *to, struct bfqg_stats *from)
+{
+	if (!to || !from)
+		return;
+
+	/* queued stats shouldn't be cleared */
+	blkg_rwstat_add_aux(&to->merged, &from->merged);
+	blkg_rwstat_add_aux(&to->service_time, &from->service_time);
+	blkg_rwstat_add_aux(&to->wait_time, &from->wait_time);
+	blkg_stat_add_aux(&from->time, &from->time);
+	blkg_stat_add_aux(&to->avg_queue_size_sum, &from->avg_queue_size_sum);
+	blkg_stat_add_aux(&to->avg_queue_size_samples,
+			  &from->avg_queue_size_samples);
+	blkg_stat_add_aux(&to->dequeue, &from->dequeue);
+	blkg_stat_add_aux(&to->group_wait_time, &from->group_wait_time);
+	blkg_stat_add_aux(&to->idle_time, &from->idle_time);
+	blkg_stat_add_aux(&to->empty_time, &from->empty_time);
+}
+
+/*
+ * Transfer @bfqg's stats to its parent's aux counts so that the ancestors'
+ * recursive stats can still account for the amount used by this bfqg after
+ * it's gone.
+ */
+static void bfqg_stats_xfer_dead(struct bfq_group *bfqg)
+{
+	struct bfq_group *parent;
+
+	if (!bfqg) /* root_group */
+		return;
+
+	parent = bfqg_parent(bfqg);
+
+	lockdep_assert_held(bfqg_to_blkg(bfqg)->q->queue_lock);
+
+	if (unlikely(!parent))
+		return;
+
+	bfqg_stats_add_aux(&parent->stats, &bfqg->stats);
+	bfqg_stats_reset(&bfqg->stats);
+}
+
+void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	entity->weight = entity->new_weight;
+	entity->orig_weight = entity->new_weight;
+	if (bfqq) {
+		bfqq->ioprio = bfqq->new_ioprio;
+		bfqq->ioprio_class = bfqq->new_ioprio_class;
+		bfqg_get(bfqg);
+	}
+	entity->parent = bfqg->my_entity; /* NULL for root group */
+	entity->sched_data = &bfqg->sched_data;
+}
+
+static void bfqg_stats_exit(struct bfqg_stats *stats)
+{
+	blkg_rwstat_exit(&stats->merged);
+	blkg_rwstat_exit(&stats->service_time);
+	blkg_rwstat_exit(&stats->wait_time);
+	blkg_rwstat_exit(&stats->queued);
+	blkg_stat_exit(&stats->time);
+	blkg_stat_exit(&stats->avg_queue_size_sum);
+	blkg_stat_exit(&stats->avg_queue_size_samples);
+	blkg_stat_exit(&stats->dequeue);
+	blkg_stat_exit(&stats->group_wait_time);
+	blkg_stat_exit(&stats->idle_time);
+	blkg_stat_exit(&stats->empty_time);
+}
+
+static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
+{
+	if (blkg_rwstat_init(&stats->merged, gfp) ||
+	    blkg_rwstat_init(&stats->service_time, gfp) ||
+	    blkg_rwstat_init(&stats->wait_time, gfp) ||
+	    blkg_rwstat_init(&stats->queued, gfp) ||
+	    blkg_stat_init(&stats->time, gfp) ||
+	    blkg_stat_init(&stats->avg_queue_size_sum, gfp) ||
+	    blkg_stat_init(&stats->avg_queue_size_samples, gfp) ||
+	    blkg_stat_init(&stats->dequeue, gfp) ||
+	    blkg_stat_init(&stats->group_wait_time, gfp) ||
+	    blkg_stat_init(&stats->idle_time, gfp) ||
+	    blkg_stat_init(&stats->empty_time, gfp)) {
+		bfqg_stats_exit(stats);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static struct bfq_group_data *cpd_to_bfqgd(struct blkcg_policy_data *cpd)
+{
+	return cpd ? container_of(cpd, struct bfq_group_data, pd) : NULL;
+}
+
+static struct bfq_group_data *blkcg_to_bfqgd(struct blkcg *blkcg)
+{
+	return cpd_to_bfqgd(blkcg_to_cpd(blkcg, &blkcg_policy_bfq));
+}
+
+struct blkcg_policy_data *bfq_cpd_alloc(gfp_t gfp)
+{
+	struct bfq_group_data *bgd;
+
+	bgd = kzalloc(sizeof(*bgd), gfp);
+	if (!bgd)
+		return NULL;
+	return &bgd->pd;
+}
+
+void bfq_cpd_init(struct blkcg_policy_data *cpd)
+{
+	struct bfq_group_data *d = cpd_to_bfqgd(cpd);
+
+	d->weight = cgroup_subsys_on_dfl(io_cgrp_subsys) ?
+		CGROUP_WEIGHT_DFL : BFQ_WEIGHT_LEGACY_DFL;
+}
+
+void bfq_cpd_free(struct blkcg_policy_data *cpd)
+{
+	kfree(cpd_to_bfqgd(cpd));
+}
+
+struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, int node)
+{
+	struct bfq_group *bfqg;
+
+	bfqg = kzalloc_node(sizeof(*bfqg), gfp, node);
+	if (!bfqg)
+		return NULL;
+
+	if (bfqg_stats_init(&bfqg->stats, gfp)) {
+		kfree(bfqg);
+		return NULL;
+	}
+
+	return &bfqg->pd;
+}
+
+void bfq_pd_init(struct blkg_policy_data *pd)
+{
+	struct blkcg_gq *blkg = pd_to_blkg(pd);
+	struct bfq_group *bfqg = blkg_to_bfqg(blkg);
+	struct bfq_data *bfqd = blkg->q->elevator->elevator_data;
+	struct bfq_entity *entity = &bfqg->entity;
+	struct bfq_group_data *d = blkcg_to_bfqgd(blkg->blkcg);
+
+	entity->orig_weight = entity->weight = entity->new_weight = d->weight;
+	entity->my_sched_data = &bfqg->sched_data;
+	bfqg->my_entity = entity; /*
+				   * the root_group's will be set to NULL
+				   * in bfq_init_queue()
+				   */
+	bfqg->bfqd = bfqd;
+	bfqg->active_entities = 0;
+	bfqg->rq_pos_tree = RB_ROOT;
+}
+
+void bfq_pd_free(struct blkg_policy_data *pd)
+{
+	struct bfq_group *bfqg = pd_to_bfqg(pd);
+
+	bfqg_stats_exit(&bfqg->stats);
+	return kfree(bfqg);
+}
+
+void bfq_pd_reset_stats(struct blkg_policy_data *pd)
+{
+	struct bfq_group *bfqg = pd_to_bfqg(pd);
+
+	bfqg_stats_reset(&bfqg->stats);
+}
+
+static void bfq_group_set_parent(struct bfq_group *bfqg,
+					struct bfq_group *parent)
+{
+	struct bfq_entity *entity;
+
+	entity = &bfqg->entity;
+	entity->parent = parent->my_entity;
+	entity->sched_data = &parent->sched_data;
+}
+
+static struct bfq_group *bfq_lookup_bfqg(struct bfq_data *bfqd,
+					 struct blkcg *blkcg)
+{
+	struct blkcg_gq *blkg;
+
+	blkg = blkg_lookup(blkcg, bfqd->queue);
+	if (likely(blkg))
+		return blkg_to_bfqg(blkg);
+	return NULL;
+}
+
+struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
+				     struct blkcg *blkcg)
+{
+	struct bfq_group *bfqg, *parent;
+	struct bfq_entity *entity;
+
+	bfqg = bfq_lookup_bfqg(bfqd, blkcg);
+
+	if (unlikely(!bfqg))
+		return NULL;
+
+	/*
+	 * Update chain of bfq_groups as we might be handling a leaf group
+	 * which, along with some of its relatives, has not been hooked yet
+	 * to the private hierarchy of BFQ.
+	 */
+	entity = &bfqg->entity;
+	for_each_entity(entity) {
+		bfqg = container_of(entity, struct bfq_group, entity);
+		if (bfqg != bfqd->root_group) {
+			parent = bfqg_parent(bfqg);
+			if (!parent)
+				parent = bfqd->root_group;
+			bfq_group_set_parent(bfqg, parent);
+		}
+	}
+
+	return bfqg;
+}
+
+/**
+ * bfq_bfqq_move - migrate @bfqq to @bfqg.
+ * @bfqd: queue descriptor.
+ * @bfqq: the queue to move.
+ * @bfqg: the group to move to.
+ *
+ * Move @bfqq to @bfqg, deactivating it from its old group and reactivating
+ * it on the new one.  Avoid putting the entity on the old group idle tree.
+ *
+ * Must be called under the queue lock; the cgroup owning @bfqg must
+ * not disappear (by now this just means that we are called under
+ * rcu_read_lock()).
+ */
+void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		   struct bfq_group *bfqg)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	/* If bfqq is empty, then bfq_bfqq_expire also invokes
+	 * bfq_del_bfqq_busy, thereby removing bfqq and its entity
+	 * from data structures related to current group. Otherwise we
+	 * need to remove bfqq explicitly with bfq_deactivate_bfqq, as
+	 * we do below.
+	 */
+	if (bfqq == bfqd->in_service_queue)
+		bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
+				false, BFQQE_PREEMPTED);
+
+	if (bfq_bfqq_busy(bfqq))
+		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
+	else if (entity->on_st)
+		bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
+	bfqg_put(bfqq_group(bfqq));
+
+	/*
+	 * Here we use a reference to bfqg.  We don't need a refcounter
+	 * as the cgroup reference will not be dropped, so that its
+	 * destroy() callback will not be invoked.
+	 */
+	entity->parent = bfqg->my_entity;
+	entity->sched_data = &bfqg->sched_data;
+	bfqg_get(bfqg);
+
+	if (bfq_bfqq_busy(bfqq)) {
+		bfq_pos_tree_add_move(bfqd, bfqq);
+		bfq_activate_bfqq(bfqd, bfqq);
+	}
+
+	if (!bfqd->in_service_queue && !bfqd->rq_in_driver)
+		bfq_schedule_dispatch(bfqd);
+}
+
+/**
+ * __bfq_bic_change_cgroup - move @bic to @cgroup.
+ * @bfqd: the queue descriptor.
+ * @bic: the bic to move.
+ * @blkcg: the blk-cgroup to move to.
+ *
+ * Move bic to blkcg, assuming that bfqd->queue is locked; the caller
+ * has to make sure that the reference to cgroup is valid across the call.
+ *
+ * NOTE: an alternative approach might have been to store the current
+ * cgroup in bfqq and getting a reference to it, reducing the lookup
+ * time here, at the price of slightly more complex code.
+ */
+static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd,
+						struct bfq_io_cq *bic,
+						struct blkcg *blkcg)
+{
+	struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0);
+	struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1);
+	struct bfq_group *bfqg;
+	struct bfq_entity *entity;
+
+	bfqg = bfq_find_set_group(bfqd, blkcg);
+
+	if (unlikely(!bfqg))
+		bfqg = bfqd->root_group;
+
+	if (async_bfqq) {
+		entity = &async_bfqq->entity;
+
+		if (entity->sched_data != &bfqg->sched_data) {
+			bic_set_bfqq(bic, NULL, 0);
+			bfq_log_bfqq(bfqd, async_bfqq,
+				     "bic_change_group: %p %d",
+				     async_bfqq, async_bfqq->ref);
+			bfq_put_queue(async_bfqq);
+		}
+	}
+
+	if (sync_bfqq) {
+		entity = &sync_bfqq->entity;
+		if (entity->sched_data != &bfqg->sched_data)
+			bfq_bfqq_move(bfqd, sync_bfqq, bfqg);
+	}
+
+	return bfqg;
+}
+
+void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio)
+{
+	struct bfq_data *bfqd = bic_to_bfqd(bic);
+	struct bfq_group *bfqg = NULL;
+	uint64_t serial_nr;
+
+	rcu_read_lock();
+	serial_nr = bio_blkcg(bio)->css.serial_nr;
+
+	/*
+	 * Check whether blkcg has changed.  The condition may trigger
+	 * spuriously on a newly created cic but there's no harm.
+	 */
+	if (unlikely(!bfqd) || likely(bic->blkcg_serial_nr == serial_nr))
+		goto out;
+
+	bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio));
+	bic->blkcg_serial_nr = serial_nr;
+out:
+	rcu_read_unlock();
+}
+
+/**
+ * bfq_flush_idle_tree - deactivate any entity on the idle tree of @st.
+ * @st: the service tree being flushed.
+ */
+static void bfq_flush_idle_tree(struct bfq_service_tree *st)
+{
+	struct bfq_entity *entity = st->first_idle;
+
+	for (; entity ; entity = st->first_idle)
+		__bfq_deactivate_entity(entity, false);
+}
+
+/**
+ * bfq_reparent_leaf_entity - move leaf entity to the root_group.
+ * @bfqd: the device data structure with the root group.
+ * @entity: the entity to move.
+ */
+static void bfq_reparent_leaf_entity(struct bfq_data *bfqd,
+				     struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);
+}
+
+/**
+ * bfq_reparent_active_entities - move to the root group all active
+ *                                entities.
+ * @bfqd: the device data structure with the root group.
+ * @bfqg: the group to move from.
+ * @st: the service tree with the entities.
+ *
+ * Needs queue_lock to be taken and reference to be valid over the call.
+ */
+static void bfq_reparent_active_entities(struct bfq_data *bfqd,
+					 struct bfq_group *bfqg,
+					 struct bfq_service_tree *st)
+{
+	struct rb_root *active = &st->active;
+	struct bfq_entity *entity = NULL;
+
+	if (!RB_EMPTY_ROOT(&st->active))
+		entity = bfq_entity_of(rb_first(active));
+
+	for (; entity ; entity = bfq_entity_of(rb_first(active)))
+		bfq_reparent_leaf_entity(bfqd, entity);
+
+	if (bfqg->sched_data.in_service_entity)
+		bfq_reparent_leaf_entity(bfqd,
+			bfqg->sched_data.in_service_entity);
+}
+
+/**
+ * bfq_pd_offline - deactivate the entity associated with @pd,
+ *		    and reparent its children entities.
+ * @pd: descriptor of the policy going offline.
+ *
+ * blkio already grabs the queue_lock for us, so no need to use
+ * RCU-based magic
+ */
+void bfq_pd_offline(struct blkg_policy_data *pd)
+{
+	struct bfq_service_tree *st;
+	struct bfq_group *bfqg = pd_to_bfqg(pd);
+	struct bfq_data *bfqd = bfqg->bfqd;
+	struct bfq_entity *entity = bfqg->my_entity;
+	unsigned long flags;
+	int i;
+
+	if (!entity) /* root group */
+		return;
+
+	spin_lock_irqsave(&bfqd->lock, flags);
+	/*
+	 * Empty all service_trees belonging to this group before
+	 * deactivating the group itself.
+	 */
+	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) {
+		st = bfqg->sched_data.service_tree + i;
+
+		/*
+		 * The idle tree may still contain bfq_queues belonging
+		 * to exited task because they never migrated to a different
+		 * cgroup from the one being destroyed now.  No one else
+		 * can access them so it's safe to act without any lock.
+		 */
+		bfq_flush_idle_tree(st);
+
+		/*
+		 * It may happen that some queues are still active
+		 * (busy) upon group destruction (if the corresponding
+		 * processes have been forced to terminate). We move
+		 * all the leaf entities corresponding to these queues
+		 * to the root_group.
+		 * Also, it may happen that the group has an entity
+		 * in service, which is disconnected from the active
+		 * tree: it must be moved, too.
+		 * There is no need to put the sync queues, as the
+		 * scheduler has taken no reference.
+		 */
+		bfq_reparent_active_entities(bfqd, bfqg, st);
+	}
+
+	__bfq_deactivate_entity(entity, false);
+	bfq_put_async_queues(bfqd, bfqg);
+
+	spin_unlock_irqrestore(&bfqd->lock, flags);
+	/*
+	 * @blkg is going offline and will be ignored by
+	 * blkg_[rw]stat_recursive_sum().  Transfer stats to the parent so
+	 * that they don't get lost.  If IOs complete after this point, the
+	 * stats for them will be lost.  Oh well...
+	 */
+	bfqg_stats_xfer_dead(bfqg);
+}
+
+void bfq_end_wr_async(struct bfq_data *bfqd)
+{
+	struct blkcg_gq *blkg;
+
+	list_for_each_entry(blkg, &bfqd->queue->blkg_list, q_node) {
+		struct bfq_group *bfqg = blkg_to_bfqg(blkg);
+
+		bfq_end_wr_async_queues(bfqd, bfqg);
+	}
+	bfq_end_wr_async_queues(bfqd, bfqd->root_group);
+}
+
+static int bfq_io_show_weight(struct seq_file *sf, void *v)
+{
+	struct blkcg *blkcg = css_to_blkcg(seq_css(sf));
+	struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
+	unsigned int val = 0;
+
+	if (bfqgd)
+		val = bfqgd->weight;
+
+	seq_printf(sf, "%u\n", val);
+
+	return 0;
+}
+
+static int bfq_io_set_weight_legacy(struct cgroup_subsys_state *css,
+				    struct cftype *cftype,
+				    u64 val)
+{
+	struct blkcg *blkcg = css_to_blkcg(css);
+	struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg);
+	struct blkcg_gq *blkg;
+	int ret = -ERANGE;
+
+	if (val < BFQ_MIN_WEIGHT || val > BFQ_MAX_WEIGHT)
+		return ret;
+
+	ret = 0;
+	spin_lock_irq(&blkcg->lock);
+	bfqgd->weight = (unsigned short)val;
+	hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) {
+		struct bfq_group *bfqg = blkg_to_bfqg(blkg);
+
+		if (!bfqg)
+			continue;
+		/*
+		 * Setting the prio_changed flag of the entity
+		 * to 1 with new_weight == weight would re-set
+		 * the value of the weight to its ioprio mapping.
+		 * Set the flag only if necessary.
+		 */
+		if ((unsigned short)val != bfqg->entity.new_weight) {
+			bfqg->entity.new_weight = (unsigned short)val;
+			/*
+			 * Make sure that the above new value has been
+			 * stored in bfqg->entity.new_weight before
+			 * setting the prio_changed flag. In fact,
+			 * this flag may be read asynchronously (in
+			 * critical sections protected by a different
+			 * lock than that held here), and finding this
+			 * flag set may cause the execution of the code
+			 * for updating parameters whose value may
+			 * depend also on bfqg->entity.new_weight (in
+			 * __bfq_entity_update_weight_prio).
+			 * This barrier makes sure that the new value
+			 * of bfqg->entity.new_weight is correctly
+			 * seen in that code.
+			 */
+			smp_wmb();
+			bfqg->entity.prio_changed = 1;
+		}
+	}
+	spin_unlock_irq(&blkcg->lock);
+
+	return ret;
+}
+
+static ssize_t bfq_io_set_weight(struct kernfs_open_file *of,
+				 char *buf, size_t nbytes,
+				 loff_t off)
+{
+	u64 weight;
+	/* First unsigned long found in the file is used */
+	int ret = kstrtoull(strim(buf), 0, &weight);
+
+	if (ret)
+		return ret;
+
+	return bfq_io_set_weight_legacy(of_css(of), NULL, weight);
+}
+
+static int bfqg_print_stat(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
+			  &blkcg_policy_bfq, seq_cft(sf)->private, false);
+	return 0;
+}
+
+static int bfqg_print_rwstat(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat,
+			  &blkcg_policy_bfq, seq_cft(sf)->private, true);
+	return 0;
+}
+
+static u64 bfqg_prfill_stat_recursive(struct seq_file *sf,
+				      struct blkg_policy_data *pd, int off)
+{
+	u64 sum = blkg_stat_recursive_sum(pd_to_blkg(pd),
+					  &blkcg_policy_bfq, off);
+	return __blkg_prfill_u64(sf, pd, sum);
+}
+
+static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf,
+					struct blkg_policy_data *pd, int off)
+{
+	struct blkg_rwstat sum = blkg_rwstat_recursive_sum(pd_to_blkg(pd),
+							   &blkcg_policy_bfq,
+							   off);
+	return __blkg_prfill_rwstat(sf, pd, &sum);
+}
+
+static int bfqg_print_stat_recursive(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  bfqg_prfill_stat_recursive, &blkcg_policy_bfq,
+			  seq_cft(sf)->private, false);
+	return 0;
+}
+
+static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq,
+			  seq_cft(sf)->private, true);
+	return 0;
+}
+
+static u64 bfqg_prfill_sectors(struct seq_file *sf, struct blkg_policy_data *pd,
+			       int off)
+{
+	u64 sum = blkg_rwstat_total(&pd->blkg->stat_bytes);
+
+	return __blkg_prfill_u64(sf, pd, sum >> 9);
+}
+
+static int bfqg_print_stat_sectors(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  bfqg_prfill_sectors, &blkcg_policy_bfq, 0, false);
+	return 0;
+}
+
+static u64 bfqg_prfill_sectors_recursive(struct seq_file *sf,
+					 struct blkg_policy_data *pd, int off)
+{
+	struct blkg_rwstat tmp = blkg_rwstat_recursive_sum(pd->blkg, NULL,
+					offsetof(struct blkcg_gq, stat_bytes));
+	u64 sum = atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_READ]) +
+		atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_WRITE]);
+
+	return __blkg_prfill_u64(sf, pd, sum >> 9);
+}
+
+static int bfqg_print_stat_sectors_recursive(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  bfqg_prfill_sectors_recursive, &blkcg_policy_bfq, 0,
+			  false);
+	return 0;
+}
+
+static u64 bfqg_prfill_avg_queue_size(struct seq_file *sf,
+				      struct blkg_policy_data *pd, int off)
+{
+	struct bfq_group *bfqg = pd_to_bfqg(pd);
+	u64 samples = blkg_stat_read(&bfqg->stats.avg_queue_size_samples);
+	u64 v = 0;
+
+	if (samples) {
+		v = blkg_stat_read(&bfqg->stats.avg_queue_size_sum);
+		v = div64_u64(v, samples);
+	}
+	__blkg_prfill_u64(sf, pd, v);
+	return 0;
+}
+
+/* print avg_queue_size */
+static int bfqg_print_avg_queue_size(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  bfqg_prfill_avg_queue_size, &blkcg_policy_bfq,
+			  0, false);
+	return 0;
+}
+
+struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
+{
+	int ret;
+
+	ret = blkcg_activate_policy(bfqd->queue, &blkcg_policy_bfq);
+	if (ret)
+		return NULL;
+
+	return blkg_to_bfqg(bfqd->queue->root_blkg);
+}
+
+struct blkcg_policy blkcg_policy_bfq = {
+	.dfl_cftypes		= bfq_blkg_files,
+	.legacy_cftypes		= bfq_blkcg_legacy_files,
+
+	.cpd_alloc_fn		= bfq_cpd_alloc,
+	.cpd_init_fn		= bfq_cpd_init,
+	.cpd_bind_fn	        = bfq_cpd_init,
+	.cpd_free_fn		= bfq_cpd_free,
+
+	.pd_alloc_fn		= bfq_pd_alloc,
+	.pd_init_fn		= bfq_pd_init,
+	.pd_offline_fn		= bfq_pd_offline,
+	.pd_free_fn		= bfq_pd_free,
+	.pd_reset_stats_fn	= bfq_pd_reset_stats,
+};
+
+struct cftype bfq_blkcg_legacy_files[] = {
+	{
+		.name = "bfq.weight",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = bfq_io_show_weight,
+		.write_u64 = bfq_io_set_weight_legacy,
+	},
+
+	/* statistics, covers only the tasks in the bfqg */
+	{
+		.name = "bfq.time",
+		.private = offsetof(struct bfq_group, stats.time),
+		.seq_show = bfqg_print_stat,
+	},
+	{
+		.name = "bfq.sectors",
+		.seq_show = bfqg_print_stat_sectors,
+	},
+	{
+		.name = "bfq.io_service_bytes",
+		.private = (unsigned long)&blkcg_policy_bfq,
+		.seq_show = blkg_print_stat_bytes,
+	},
+	{
+		.name = "bfq.io_serviced",
+		.private = (unsigned long)&blkcg_policy_bfq,
+		.seq_show = blkg_print_stat_ios,
+	},
+	{
+		.name = "bfq.io_service_time",
+		.private = offsetof(struct bfq_group, stats.service_time),
+		.seq_show = bfqg_print_rwstat,
+	},
+	{
+		.name = "bfq.io_wait_time",
+		.private = offsetof(struct bfq_group, stats.wait_time),
+		.seq_show = bfqg_print_rwstat,
+	},
+	{
+		.name = "bfq.io_merged",
+		.private = offsetof(struct bfq_group, stats.merged),
+		.seq_show = bfqg_print_rwstat,
+	},
+	{
+		.name = "bfq.io_queued",
+		.private = offsetof(struct bfq_group, stats.queued),
+		.seq_show = bfqg_print_rwstat,
+	},
+
+	/* the same statictics which cover the bfqg and its descendants */
+	{
+		.name = "bfq.time_recursive",
+		.private = offsetof(struct bfq_group, stats.time),
+		.seq_show = bfqg_print_stat_recursive,
+	},
+	{
+		.name = "bfq.sectors_recursive",
+		.seq_show = bfqg_print_stat_sectors_recursive,
+	},
+	{
+		.name = "bfq.io_service_bytes_recursive",
+		.private = (unsigned long)&blkcg_policy_bfq,
+		.seq_show = blkg_print_stat_bytes_recursive,
+	},
+	{
+		.name = "bfq.io_serviced_recursive",
+		.private = (unsigned long)&blkcg_policy_bfq,
+		.seq_show = blkg_print_stat_ios_recursive,
+	},
+	{
+		.name = "bfq.io_service_time_recursive",
+		.private = offsetof(struct bfq_group, stats.service_time),
+		.seq_show = bfqg_print_rwstat_recursive,
+	},
+	{
+		.name = "bfq.io_wait_time_recursive",
+		.private = offsetof(struct bfq_group, stats.wait_time),
+		.seq_show = bfqg_print_rwstat_recursive,
+	},
+	{
+		.name = "bfq.io_merged_recursive",
+		.private = offsetof(struct bfq_group, stats.merged),
+		.seq_show = bfqg_print_rwstat_recursive,
+	},
+	{
+		.name = "bfq.io_queued_recursive",
+		.private = offsetof(struct bfq_group, stats.queued),
+		.seq_show = bfqg_print_rwstat_recursive,
+	},
+	{
+		.name = "bfq.avg_queue_size",
+		.seq_show = bfqg_print_avg_queue_size,
+	},
+	{
+		.name = "bfq.group_wait_time",
+		.private = offsetof(struct bfq_group, stats.group_wait_time),
+		.seq_show = bfqg_print_stat,
+	},
+	{
+		.name = "bfq.idle_time",
+		.private = offsetof(struct bfq_group, stats.idle_time),
+		.seq_show = bfqg_print_stat,
+	},
+	{
+		.name = "bfq.empty_time",
+		.private = offsetof(struct bfq_group, stats.empty_time),
+		.seq_show = bfqg_print_stat,
+	},
+	{
+		.name = "bfq.dequeue",
+		.private = offsetof(struct bfq_group, stats.dequeue),
+		.seq_show = bfqg_print_stat,
+	},
+	{ }	/* terminate */
+};
+
+struct cftype bfq_blkg_files[] = {
+	{
+		.name = "bfq.weight",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = bfq_io_show_weight,
+		.write = bfq_io_set_weight,
+	},
+	{} /* terminate */
+};
+
+#else	/* CONFIG_BFQ_GROUP_IOSCHED */
+
+void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
+			      unsigned int op) { }
+void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op) { }
+void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) { }
+void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
+				  uint64_t io_start_time, unsigned int op) { }
+void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { }
+void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { }
+void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { }
+void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { }
+void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) { }
+
+void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		   struct bfq_group *bfqg) {}
+
+void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	entity->weight = entity->new_weight;
+	entity->orig_weight = entity->new_weight;
+	if (bfqq) {
+		bfqq->ioprio = bfqq->new_ioprio;
+		bfqq->ioprio_class = bfqq->new_ioprio_class;
+	}
+	entity->sched_data = &bfqg->sched_data;
+}
+
+void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) {}
+
+void bfq_end_wr_async(struct bfq_data *bfqd)
+{
+	bfq_end_wr_async_queues(bfqd, bfqd->root_group);
+}
+
+struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, struct blkcg *blkcg)
+{
+	return bfqd->root_group;
+}
+
+struct bfq_group *bfqq_group(struct bfq_queue *bfqq)
+{
+	return bfqq->bfqd->root_group;
+}
+
+struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
+{
+	struct bfq_group *bfqg;
+	int i;
+
+	bfqg = kmalloc_node(sizeof(*bfqg), GFP_KERNEL | __GFP_ZERO, node);
+	if (!bfqg)
+		return NULL;
+
+	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
+		bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
+
+	return bfqg;
+}
+#endif	/* CONFIG_BFQ_GROUP_IOSCHED */

block/bfq-iosched.c

@@ -0,0 +1,5047 @@
+/*
+ * Budget Fair Queueing (BFQ) I/O scheduler.
+ *
+ * Based on ideas and code from CFQ:
+ * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
+ *
+ * Copyright (C) 2008 Fabio Checconi <fabio@gandalf.sssup.it>
+ *		      Paolo Valente <paolo.valente@unimore.it>
+ *
+ * Copyright (C) 2010 Paolo Valente <paolo.valente@unimore.it>
+ *                    Arianna Avanzini <avanzini@google.com>
+ *
+ * Copyright (C) 2017 Paolo Valente <paolo.valente@linaro.org>
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License as
+ *  published by the Free Software Foundation; either version 2 of the
+ *  License, or (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ * BFQ is a proportional-share I/O scheduler, with some extra
+ * low-latency capabilities. BFQ also supports full hierarchical
+ * scheduling through cgroups. Next paragraphs provide an introduction
+ * on BFQ inner workings. Details on BFQ benefits, usage and
+ * limitations can be found in Documentation/block/bfq-iosched.txt.
+ *
+ * BFQ is a proportional-share storage-I/O scheduling algorithm based
+ * on the slice-by-slice service scheme of CFQ. But BFQ assigns
+ * budgets, measured in number of sectors, to processes instead of
+ * time slices. The device is not granted to the in-service process
+ * for a given time slice, but until it has exhausted its assigned
+ * budget. This change from the time to the service domain enables BFQ
+ * to distribute the device throughput among processes as desired,
+ * without any distortion due to throughput fluctuations, or to device
+ * internal queueing. BFQ uses an ad hoc internal scheduler, called
+ * B-WF2Q+, to schedule processes according to their budgets. More
+ * precisely, BFQ schedules queues associated with processes. Each
+ * process/queue is assigned a user-configurable weight, and B-WF2Q+
+ * guarantees that each queue receives a fraction of the throughput
+ * proportional to its weight. Thanks to the accurate policy of
+ * B-WF2Q+, BFQ can afford to assign high budgets to I/O-bound
+ * processes issuing sequential requests (to boost the throughput),
+ * and yet guarantee a low latency to interactive and soft real-time
+ * applications.
+ *
+ * In particular, to provide these low-latency guarantees, BFQ
+ * explicitly privileges the I/O of two classes of time-sensitive
+ * applications: interactive and soft real-time. This feature enables
+ * BFQ to provide applications in these classes with a very low
+ * latency. Finally, BFQ also features additional heuristics for
+ * preserving both a low latency and a high throughput on NCQ-capable,
+ * rotational or flash-based devices, and to get the job done quickly
+ * for applications consisting in many I/O-bound processes.
+ *
+ * BFQ is described in [1], where also a reference to the initial, more
+ * theoretical paper on BFQ can be found. The interested reader can find
+ * in the latter paper full details on the main algorithm, as well as
+ * formulas of the guarantees and formal proofs of all the properties.
+ * With respect to the version of BFQ presented in these papers, this
+ * implementation adds a few more heuristics, such as the one that
+ * guarantees a low latency to soft real-time applications, and a
+ * hierarchical extension based on H-WF2Q+.
+ *
+ * B-WF2Q+ is based on WF2Q+, which is described in [2], together with
+ * H-WF2Q+, while the augmented tree used here to implement B-WF2Q+
+ * with O(log N) complexity derives from the one introduced with EEVDF
+ * in [3].
+ *
+ * [1] P. Valente, A. Avanzini, "Evolution of the BFQ Storage I/O
+ *     Scheduler", Proceedings of the First Workshop on Mobile System
+ *     Technologies (MST-2015), May 2015.
+ *     http://algogroup.unimore.it/people/paolo/disk_sched/mst-2015.pdf
+ *
+ * [2] Jon C.R. Bennett and H. Zhang, "Hierarchical Packet Fair Queueing
+ *     Algorithms", IEEE/ACM Transactions on Networking, 5(5):675-689,
+ *     Oct 1997.
+ *
+ * http://www.cs.cmu.edu/~hzhang/papers/TON-97-Oct.ps.gz
+ *
+ * [3] I. Stoica and H. Abdel-Wahab, "Earliest Eligible Virtual Deadline
+ *     First: A Flexible and Accurate Mechanism for Proportional Share
+ *     Resource Allocation", technical report.
+ *
+ * http://www.cs.berkeley.edu/~istoica/papers/eevdf-tr-95.pdf
+ */
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/blkdev.h>
+#include <linux/cgroup.h>
+#include <linux/elevator.h>
+#include <linux/ktime.h>
+#include <linux/rbtree.h>
+#include <linux/ioprio.h>
+#include <linux/sbitmap.h>
+#include <linux/delay.h>
+
+#include "blk.h"
+#include "blk-mq.h"
+#include "blk-mq-tag.h"
+#include "blk-mq-sched.h"
+#include "bfq-iosched.h"
+
+#define BFQ_BFQQ_FNS(name)						\
+void bfq_mark_bfqq_##name(struct bfq_queue *bfqq)			\
+{									\
+	__set_bit(BFQQF_##name, &(bfqq)->flags);			\
+}									\
+void bfq_clear_bfqq_##name(struct bfq_queue *bfqq)			\
+{									\
+	__clear_bit(BFQQF_##name, &(bfqq)->flags);		\
+}									\
+int bfq_bfqq_##name(const struct bfq_queue *bfqq)			\
+{									\
+	return test_bit(BFQQF_##name, &(bfqq)->flags);		\
+}
+
+BFQ_BFQQ_FNS(just_created);
+BFQ_BFQQ_FNS(busy);
+BFQ_BFQQ_FNS(wait_request);
+BFQ_BFQQ_FNS(non_blocking_wait_rq);
+BFQ_BFQQ_FNS(fifo_expire);
+BFQ_BFQQ_FNS(idle_window);
+BFQ_BFQQ_FNS(sync);
+BFQ_BFQQ_FNS(IO_bound);
+BFQ_BFQQ_FNS(in_large_burst);
+BFQ_BFQQ_FNS(coop);
+BFQ_BFQQ_FNS(split_coop);
+BFQ_BFQQ_FNS(softrt_update);
+#undef BFQ_BFQQ_FNS						\
+
+/* Expiration time of sync (0) and async (1) requests, in ns. */
+static const u64 bfq_fifo_expire[2] = { NSEC_PER_SEC / 4, NSEC_PER_SEC / 8 };
+
+/* Maximum backwards seek (magic number lifted from CFQ), in KiB. */
+static const int bfq_back_max = 16 * 1024;
+
+/* Penalty of a backwards seek, in number of sectors. */
+static const int bfq_back_penalty = 2;
+
+/* Idling period duration, in ns. */
+static u64 bfq_slice_idle = NSEC_PER_SEC / 125;
+
+/* Minimum number of assigned budgets for which stats are safe to compute. */
+static const int bfq_stats_min_budgets = 194;
+
+/* Default maximum budget values, in sectors and number of requests. */
+static const int bfq_default_max_budget = 16 * 1024;
+
+/*
+ * Async to sync throughput distribution is controlled as follows:
+ * when an async request is served, the entity is charged the number
+ * of sectors of the request, multiplied by the factor below
+ */
+static const int bfq_async_charge_factor = 10;
+
+/* Default timeout values, in jiffies, approximating CFQ defaults. */
+const int bfq_timeout = HZ / 8;
+
+static struct kmem_cache *bfq_pool;
+
+/* Below this threshold (in ns), we consider thinktime immediate. */
+#define BFQ_MIN_TT		(2 * NSEC_PER_MSEC)
+
+/* hw_tag detection: parallel requests threshold and min samples needed. */
+#define BFQ_HW_QUEUE_THRESHOLD	4
+#define BFQ_HW_QUEUE_SAMPLES	32
+
+#define BFQQ_SEEK_THR		(sector_t)(8 * 100)
+#define BFQQ_SECT_THR_NONROT	(sector_t)(2 * 32)
+#define BFQQ_CLOSE_THR		(sector_t)(8 * 1024)
+#define BFQQ_SEEKY(bfqq)	(hweight32(bfqq->seek_history) > 32/8)
+
+/* Min number of samples required to perform peak-rate update */
+#define BFQ_RATE_MIN_SAMPLES	32
+/* Min observation time interval required to perform a peak-rate update (ns) */
+#define BFQ_RATE_MIN_INTERVAL	(300*NSEC_PER_MSEC)
+/* Target observation time interval for a peak-rate update (ns) */
+#define BFQ_RATE_REF_INTERVAL	NSEC_PER_SEC
+
+/* Shift used for peak rate fixed precision calculations. */
+#define BFQ_RATE_SHIFT		16
+
+/*
+ * By default, BFQ computes the duration of the weight raising for
+ * interactive applications automatically, using the following formula:
+ * duration = (R / r) * T, where r is the peak rate of the device, and
+ * R and T are two reference parameters.
+ * In particular, R is the peak rate of the reference device (see below),
+ * and T is a reference time: given the systems that are likely to be
+ * installed on the reference device according to its speed class, T is
+ * about the maximum time needed, under BFQ and while reading two files in
+ * parallel, to load typical large applications on these systems.
+ * In practice, the slower/faster the device at hand is, the more/less it
+ * takes to load applications with respect to the reference device.
+ * Accordingly, the longer/shorter BFQ grants weight raising to interactive
+ * applications.
+ *
+ * BFQ uses four different reference pairs (R, T), depending on:
+ * . whether the device is rotational or non-rotational;
+ * . whether the device is slow, such as old or portable HDDs, as well as
+ *   SD cards, or fast, such as newer HDDs and SSDs.
+ *
+ * The device's speed class is dynamically (re)detected in
+ * bfq_update_peak_rate() every time the estimated peak rate is updated.
+ *
+ * In the following definitions, R_slow[0]/R_fast[0] and
+ * T_slow[0]/T_fast[0] are the reference values for a slow/fast
+ * rotational device, whereas R_slow[1]/R_fast[1] and
+ * T_slow[1]/T_fast[1] are the reference values for a slow/fast
+ * non-rotational device. Finally, device_speed_thresh are the
+ * thresholds used to switch between speed classes. The reference
+ * rates are not the actual peak rates of the devices used as a
+ * reference, but slightly lower values. The reason for using these
+ * slightly lower values is that the peak-rate estimator tends to
+ * yield slightly lower values than the actual peak rate (it can yield
+ * the actual peak rate only if there is only one process doing I/O,
+ * and the process does sequential I/O).
+ *
+ * Both the reference peak rates and the thresholds are measured in
+ * sectors/usec, left-shifted by BFQ_RATE_SHIFT.
+ */
+static int R_slow[2] = {1000, 10700};
+static int R_fast[2] = {14000, 33000};
+/*
+ * To improve readability, a conversion function is used to initialize the
+ * following arrays, which entails that they can be initialized only in a
+ * function.
+ */
+static int T_slow[2];
+static int T_fast[2];
+static int device_speed_thresh[2];
+
+#define RQ_BIC(rq)		((struct bfq_io_cq *) (rq)->elv.priv[0])
+#define RQ_BFQQ(rq)		((rq)->elv.priv[1])
+
+struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync)
+{
+	return bic->bfqq[is_sync];
+}
+
+void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync)
+{
+	bic->bfqq[is_sync] = bfqq;
+}
+
+struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic)
+{
+	return bic->icq.q->elevator->elevator_data;
+}
+
+/**
+ * icq_to_bic - convert iocontext queue structure to bfq_io_cq.
+ * @icq: the iocontext queue.
+ */
+static struct bfq_io_cq *icq_to_bic(struct io_cq *icq)
+{
+	/* bic->icq is the first member, %NULL will convert to %NULL */
+	return container_of(icq, struct bfq_io_cq, icq);
+}
+
+/**
+ * bfq_bic_lookup - search into @ioc a bic associated to @bfqd.
+ * @bfqd: the lookup key.
+ * @ioc: the io_context of the process doing I/O.
+ * @q: the request queue.
+ */
+static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd,
+					struct io_context *ioc,
+					struct request_queue *q)
+{
+	if (ioc) {
+		unsigned long flags;
+		struct bfq_io_cq *icq;
+
+		spin_lock_irqsave(q->queue_lock, flags);
+		icq = icq_to_bic(ioc_lookup_icq(ioc, q));
+		spin_unlock_irqrestore(q->queue_lock, flags);
+
+		return icq;
+	}
+
+	return NULL;
+}
+
+/*
+ * Scheduler run of queue, if there are requests pending and no one in the
+ * driver that will restart queueing.
+ */
+void bfq_schedule_dispatch(struct bfq_data *bfqd)
+{
+	if (bfqd->queued != 0) {
+		bfq_log(bfqd, "schedule dispatch");
+		blk_mq_run_hw_queues(bfqd->queue, true);
+	}
+}
+
+#define bfq_class_idle(bfqq)	((bfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
+#define bfq_class_rt(bfqq)	((bfqq)->ioprio_class == IOPRIO_CLASS_RT)
+
+#define bfq_sample_valid(samples)	((samples) > 80)
+
+/*
+ * Lifted from AS - choose which of rq1 and rq2 that is best served now.
+ * We choose the request that is closesr to the head right now.  Distance
+ * behind the head is penalized and only allowed to a certain extent.
+ */
+static struct request *bfq_choose_req(struct bfq_data *bfqd,
+				      struct request *rq1,
+				      struct request *rq2,
+				      sector_t last)
+{
+	sector_t s1, s2, d1 = 0, d2 = 0;
+	unsigned long back_max;
+#define BFQ_RQ1_WRAP	0x01 /* request 1 wraps */
+#define BFQ_RQ2_WRAP	0x02 /* request 2 wraps */
+	unsigned int wrap = 0; /* bit mask: requests behind the disk head? */
+
+	if (!rq1 || rq1 == rq2)
+		return rq2;
+	if (!rq2)
+		return rq1;
+
+	if (rq_is_sync(rq1) && !rq_is_sync(rq2))
+		return rq1;
+	else if (rq_is_sync(rq2) && !rq_is_sync(rq1))
+		return rq2;
+	if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META))
+		return rq1;
+	else if ((rq2->cmd_flags & REQ_META) && !(rq1->cmd_flags & REQ_META))
+		return rq2;
+
+	s1 = blk_rq_pos(rq1);
+	s2 = blk_rq_pos(rq2);
+
+	/*
+	 * By definition, 1KiB is 2 sectors.
+	 */
+	back_max = bfqd->bfq_back_max * 2;
+
+	/*
+	 * Strict one way elevator _except_ in the case where we allow
+	 * short backward seeks which are biased as twice the cost of a
+	 * similar forward seek.
+	 */
+	if (s1 >= last)
+		d1 = s1 - last;
+	else if (s1 + back_max >= last)
+		d1 = (last - s1) * bfqd->bfq_back_penalty;
+	else
+		wrap |= BFQ_RQ1_WRAP;
+
+	if (s2 >= last)
+		d2 = s2 - last;
+	else if (s2 + back_max >= last)
+		d2 = (last - s2) * bfqd->bfq_back_penalty;
+	else
+		wrap |= BFQ_RQ2_WRAP;
+
+	/* Found required data */
+
+	/*
+	 * By doing switch() on the bit mask "wrap" we avoid having to
+	 * check two variables for all permutations: --> faster!
+	 */
+	switch (wrap) {
+	case 0: /* common case for CFQ: rq1 and rq2 not wrapped */
+		if (d1 < d2)
+			return rq1;
+		else if (d2 < d1)
+			return rq2;
+
+		if (s1 >= s2)
+			return rq1;
+		else
+			return rq2;
+
+	case BFQ_RQ2_WRAP:
+		return rq1;
+	case BFQ_RQ1_WRAP:
+		return rq2;
+	case BFQ_RQ1_WRAP|BFQ_RQ2_WRAP: /* both rqs wrapped */
+	default:
+		/*
+		 * Since both rqs are wrapped,
+		 * start with the one that's further behind head
+		 * (--> only *one* back seek required),
+		 * since back seek takes more time than forward.
+		 */
+		if (s1 <= s2)
+			return rq1;
+		else
+			return rq2;
+	}
+}
+
+static struct bfq_queue *
+bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root,
+		     sector_t sector, struct rb_node **ret_parent,
+		     struct rb_node ***rb_link)
+{
+	struct rb_node **p, *parent;
+	struct bfq_queue *bfqq = NULL;
+
+	parent = NULL;
+	p = &root->rb_node;
+	while (*p) {
+		struct rb_node **n;
+
+		parent = *p;
+		bfqq = rb_entry(parent, struct bfq_queue, pos_node);
+
+		/*
+		 * Sort strictly based on sector. Smallest to the left,
+		 * largest to the right.
+		 */
+		if (sector > blk_rq_pos(bfqq->next_rq))
+			n = &(*p)->rb_right;
+		else if (sector < blk_rq_pos(bfqq->next_rq))
+			n = &(*p)->rb_left;
+		else
+			break;
+		p = n;
+		bfqq = NULL;
+	}
+
+	*ret_parent = parent;
+	if (rb_link)
+		*rb_link = p;
+
+	bfq_log(bfqd, "rq_pos_tree_lookup %llu: returning %d",
+		(unsigned long long)sector,
+		bfqq ? bfqq->pid : 0);
+
+	return bfqq;
+}
+
+void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct rb_node **p, *parent;
+	struct bfq_queue *__bfqq;
+
+	if (bfqq->pos_root) {
+		rb_erase(&bfqq->pos_node, bfqq->pos_root);
+		bfqq->pos_root = NULL;
+	}
+
+	if (bfq_class_idle(bfqq))
+		return;
+	if (!bfqq->next_rq)
+		return;
+
+	bfqq->pos_root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
+	__bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root,
+			blk_rq_pos(bfqq->next_rq), &parent, &p);
+	if (!__bfqq) {
+		rb_link_node(&bfqq->pos_node, parent, p);
+		rb_insert_color(&bfqq->pos_node, bfqq->pos_root);
+	} else
+		bfqq->pos_root = NULL;
+}
+
+/*
+ * Tell whether there are active queues or groups with differentiated weights.
+ */
+static bool bfq_differentiated_weights(struct bfq_data *bfqd)
+{
+	/*
+	 * For weights to differ, at least one of the trees must contain
+	 * at least two nodes.
+	 */
+	return (!RB_EMPTY_ROOT(&bfqd->queue_weights_tree) &&
+		(bfqd->queue_weights_tree.rb_node->rb_left ||
+		 bfqd->queue_weights_tree.rb_node->rb_right)
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	       ) ||
+	       (!RB_EMPTY_ROOT(&bfqd->group_weights_tree) &&
+		(bfqd->group_weights_tree.rb_node->rb_left ||
+		 bfqd->group_weights_tree.rb_node->rb_right)
+#endif
+	       );
+}
+
+/*
+ * The following function returns true if every queue must receive the
+ * same share of the throughput (this condition is used when deciding
+ * whether idling may be disabled, see the comments in the function
+ * bfq_bfqq_may_idle()).
+ *
+ * Such a scenario occurs when:
+ * 1) all active queues have the same weight,
+ * 2) all active groups at the same level in the groups tree have the same
+ *    weight,
+ * 3) all active groups at the same level in the groups tree have the same
+ *    number of children.
+ *
+ * Unfortunately, keeping the necessary state for evaluating exactly the
+ * above symmetry conditions would be quite complex and time-consuming.
+ * Therefore this function evaluates, instead, the following stronger
+ * sub-conditions, for which it is much easier to maintain the needed
+ * state:
+ * 1) all active queues have the same weight,
+ * 2) all active groups have the same weight,
+ * 3) all active groups have at most one active child each.
+ * In particular, the last two conditions are always true if hierarchical
+ * support and the cgroups interface are not enabled, thus no state needs
+ * to be maintained in this case.
+ */
+static bool bfq_symmetric_scenario(struct bfq_data *bfqd)
+{
+	return !bfq_differentiated_weights(bfqd);
+}
+
+/*
+ * If the weight-counter tree passed as input contains no counter for
+ * the weight of the input entity, then add that counter; otherwise just
+ * increment the existing counter.
+ *
+ * Note that weight-counter trees contain few nodes in mostly symmetric
+ * scenarios. For example, if all queues have the same weight, then the
+ * weight-counter tree for the queues may contain at most one node.
+ * This holds even if low_latency is on, because weight-raised queues
+ * are not inserted in the tree.
+ * In most scenarios, the rate at which nodes are created/destroyed
+ * should be low too.
+ */
+void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
+			  struct rb_root *root)
+{
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+	/*
+	 * Do not insert if the entity is already associated with a
+	 * counter, which happens if:
+	 *   1) the entity is associated with a queue,
+	 *   2) a request arrival has caused the queue to become both
+	 *      non-weight-raised, and hence change its weight, and
+	 *      backlogged; in this respect, each of the two events
+	 *      causes an invocation of this function,
+	 *   3) this is the invocation of this function caused by the
+	 *      second event. This second invocation is actually useless,
+	 *      and we handle this fact by exiting immediately. More
+	 *      efficient or clearer solutions might possibly be adopted.
+	 */
+	if (entity->weight_counter)
+		return;
+
+	while (*new) {
+		struct bfq_weight_counter *__counter = container_of(*new,
+						struct bfq_weight_counter,
+						weights_node);
+		parent = *new;
+
+		if (entity->weight == __counter->weight) {
+			entity->weight_counter = __counter;
+			goto inc_counter;
+		}
+		if (entity->weight < __counter->weight)
+			new = &((*new)->rb_left);
+		else
+			new = &((*new)->rb_right);
+	}
+
+	entity->weight_counter = kzalloc(sizeof(struct bfq_weight_counter),
+					 GFP_ATOMIC);
+
+	/*
+	 * In the unlucky event of an allocation failure, we just
+	 * exit. This will cause the weight of entity to not be
+	 * considered in bfq_differentiated_weights, which, in its
+	 * turn, causes the scenario to be deemed wrongly symmetric in
+	 * case entity's weight would have been the only weight making
+	 * the scenario asymmetric. On the bright side, no unbalance
+	 * will however occur when entity becomes inactive again (the
+	 * invocation of this function is triggered by an activation
+	 * of entity). In fact, bfq_weights_tree_remove does nothing
+	 * if !entity->weight_counter.
+	 */
+	if (unlikely(!entity->weight_counter))
+		return;
+
+	entity->weight_counter->weight = entity->weight;
+	rb_link_node(&entity->weight_counter->weights_node, parent, new);
+	rb_insert_color(&entity->weight_counter->weights_node, root);
+
+inc_counter:
+	entity->weight_counter->num_active++;
+}
+
+/*
+ * Decrement the weight counter associated with the entity, and, if the
+ * counter reaches 0, remove the counter from the tree.
+ * See the comments to the function bfq_weights_tree_add() for considerations
+ * about overhead.
+ */
+void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_entity *entity,
+			     struct rb_root *root)
+{
+	if (!entity->weight_counter)
+		return;
+
+	entity->weight_counter->num_active--;
+	if (entity->weight_counter->num_active > 0)
+		goto reset_entity_pointer;
+
+	rb_erase(&entity->weight_counter->weights_node, root);
+	kfree(entity->weight_counter);
+
+reset_entity_pointer:
+	entity->weight_counter = NULL;
+}
+
+/*
+ * Return expired entry, or NULL to just start from scratch in rbtree.
+ */
+static struct request *bfq_check_fifo(struct bfq_queue *bfqq,
+				      struct request *last)
+{
+	struct request *rq;
+
+	if (bfq_bfqq_fifo_expire(bfqq))
+		return NULL;
+
+	bfq_mark_bfqq_fifo_expire(bfqq);
+
+	rq = rq_entry_fifo(bfqq->fifo.next);
+
+	if (rq == last || ktime_get_ns() < rq->fifo_time)
+		return NULL;
+
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "check_fifo: returned %p", rq);
+	return rq;
+}
+
+static struct request *bfq_find_next_rq(struct bfq_data *bfqd,
+					struct bfq_queue *bfqq,
+					struct request *last)
+{
+	struct rb_node *rbnext = rb_next(&last->rb_node);
+	struct rb_node *rbprev = rb_prev(&last->rb_node);
+	struct request *next, *prev = NULL;
+
+	/* Follow expired path, else get first next available. */
+	next = bfq_check_fifo(bfqq, last);
+	if (next)
+		return next;
+
+	if (rbprev)
+		prev = rb_entry_rq(rbprev);
+
+	if (rbnext)
+		next = rb_entry_rq(rbnext);
+	else {
+		rbnext = rb_first(&bfqq->sort_list);
+		if (rbnext && rbnext != &last->rb_node)
+			next = rb_entry_rq(rbnext);
+	}
+
+	return bfq_choose_req(bfqd, next, prev, blk_rq_pos(last));
+}
+
+/* see the definition of bfq_async_charge_factor for details */
+static unsigned long bfq_serv_to_charge(struct request *rq,
+					struct bfq_queue *bfqq)
+{
+	if (bfq_bfqq_sync(bfqq) || bfqq->wr_coeff > 1)
+		return blk_rq_sectors(rq);
+
+	/*
+	 * If there are no weight-raised queues, then amplify service
+	 * by just the async charge factor; otherwise amplify service
+	 * by twice the async charge factor, to further reduce latency
+	 * for weight-raised queues.
+	 */
+	if (bfqq->bfqd->wr_busy_queues == 0)
+		return blk_rq_sectors(rq) * bfq_async_charge_factor;
+
+	return blk_rq_sectors(rq) * 2 * bfq_async_charge_factor;
+}
+
+/**
+ * bfq_updated_next_req - update the queue after a new next_rq selection.
+ * @bfqd: the device data the queue belongs to.
+ * @bfqq: the queue to update.
+ *
+ * If the first request of a queue changes we make sure that the queue
+ * has enough budget to serve at least its first request (if the
+ * request has grown).  We do this because if the queue has not enough
+ * budget for its first request, it has to go through two dispatch
+ * rounds to actually get it dispatched.
+ */
+static void bfq_updated_next_req(struct bfq_data *bfqd,
+				 struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+	struct request *next_rq = bfqq->next_rq;
+	unsigned long new_budget;
+
+	if (!next_rq)
+		return;
+
+	if (bfqq == bfqd->in_service_queue)
+		/*
+		 * In order not to break guarantees, budgets cannot be
+		 * changed after an entity has been selected.
+		 */
+		return;
+
+	new_budget = max_t(unsigned long, bfqq->max_budget,
+			   bfq_serv_to_charge(next_rq, bfqq));
+	if (entity->budget != new_budget) {
+		entity->budget = new_budget;
+		bfq_log_bfqq(bfqd, bfqq, "updated next rq: new budget %lu",
+					 new_budget);
+		bfq_requeue_bfqq(bfqd, bfqq);
+	}
+}
+
+static void
+bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
+{
+	if (bic->saved_idle_window)
+		bfq_mark_bfqq_idle_window(bfqq);
+	else
+		bfq_clear_bfqq_idle_window(bfqq);
+
+	if (bic->saved_IO_bound)
+		bfq_mark_bfqq_IO_bound(bfqq);
+	else
+		bfq_clear_bfqq_IO_bound(bfqq);
+
+	bfqq->ttime = bic->saved_ttime;
+	bfqq->wr_coeff = bic->saved_wr_coeff;
+	bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt;
+	bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish;
+	bfqq->wr_cur_max_time = bic->saved_wr_cur_max_time;
+
+	if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) ||
+	    time_is_before_jiffies(bfqq->last_wr_start_finish +
+				   bfqq->wr_cur_max_time))) {
+		bfq_log_bfqq(bfqq->bfqd, bfqq,
+		    "resume state: switching off wr");
+
+		bfqq->wr_coeff = 1;
+	}
+
+	/* make sure weight will be updated, however we got here */
+	bfqq->entity.prio_changed = 1;
+}
+
+static int bfqq_process_refs(struct bfq_queue *bfqq)
+{
+	return bfqq->ref - bfqq->allocated - bfqq->entity.on_st;
+}
+
+/* Empty burst list and add just bfqq (see comments on bfq_handle_burst) */
+static void bfq_reset_burst_list(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct bfq_queue *item;
+	struct hlist_node *n;
+
+	hlist_for_each_entry_safe(item, n, &bfqd->burst_list, burst_list_node)
+		hlist_del_init(&item->burst_list_node);
+	hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
+	bfqd->burst_size = 1;
+	bfqd->burst_parent_entity = bfqq->entity.parent;
+}
+
+/* Add bfqq to the list of queues in current burst (see bfq_handle_burst) */
+static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	/* Increment burst size to take into account also bfqq */
+	bfqd->burst_size++;
+
+	if (bfqd->burst_size == bfqd->bfq_large_burst_thresh) {
+		struct bfq_queue *pos, *bfqq_item;
+		struct hlist_node *n;
+
+		/*
+		 * Enough queues have been activated shortly after each
+		 * other to consider this burst as large.
+		 */
+		bfqd->large_burst = true;
+
+		/*
+		 * We can now mark all queues in the burst list as
+		 * belonging to a large burst.
+		 */
+		hlist_for_each_entry(bfqq_item, &bfqd->burst_list,
+				     burst_list_node)
+			bfq_mark_bfqq_in_large_burst(bfqq_item);
+		bfq_mark_bfqq_in_large_burst(bfqq);
+
+		/*
+		 * From now on, and until the current burst finishes, any
+		 * new queue being activated shortly after the last queue
+		 * was inserted in the burst can be immediately marked as
+		 * belonging to a large burst. So the burst list is not
+		 * needed any more. Remove it.
+		 */
+		hlist_for_each_entry_safe(pos, n, &bfqd->burst_list,
+					  burst_list_node)
+			hlist_del_init(&pos->burst_list_node);
+	} else /*
+		* Burst not yet large: add bfqq to the burst list. Do
+		* not increment the ref counter for bfqq, because bfqq
+		* is removed from the burst list before freeing bfqq
+		* in put_queue.
+		*/
+		hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list);
+}
+
+/*
+ * If many queues belonging to the same group happen to be created
+ * shortly after each other, then the processes associated with these
+ * queues have typically a common goal. In particular, bursts of queue
+ * creations are usually caused by services or applications that spawn
+ * many parallel threads/processes. Examples are systemd during boot,
+ * or git grep. To help these processes get their job done as soon as
+ * possible, it is usually better to not grant either weight-raising
+ * or device idling to their queues.
+ *
+ * In this comment we describe, firstly, the reasons why this fact
+ * holds, and, secondly, the next function, which implements the main
+ * steps needed to properly mark these queues so that they can then be
+ * treated in a different way.
+ *
+ * The above services or applications benefit mostly from a high
+ * throughput: the quicker the requests of the activated queues are
+ * cumulatively served, the sooner the target job of these queues gets
+ * completed. As a consequence, weight-raising any of these queues,
+ * which also implies idling the device for it, is almost always
+ * counterproductive. In most cases it just lowers throughput.
+ *
+ * On the other hand, a burst of queue creations may be caused also by
+ * the start of an application that does not consist of a lot of
+ * parallel I/O-bound threads. In fact, with a complex application,
+ * several short processes may need to be executed to start-up the
+ * application. In this respect, to start an application as quickly as
+ * possible, the best thing to do is in any case to privilege the I/O
+ * related to the application with respect to all other
+ * I/O. Therefore, the best strategy to start as quickly as possible
+ * an application that causes a burst of queue creations is to
+ * weight-raise all the queues created during the burst. This is the
+ * exact opposite of the best strategy for the other type of bursts.
+ *
+ * In the end, to take the best action for each of the two cases, the
+ * two types of bursts need to be distinguished. Fortunately, this
+ * seems relatively easy, by looking at the sizes of the bursts. In
+ * particular, we found a threshold such that only bursts with a
+ * larger size than that threshold are apparently caused by
+ * services or commands such as systemd or git grep. For brevity,
+ * hereafter we call just 'large' these bursts. BFQ *does not*
+ * weight-raise queues whose creation occurs in a large burst. In
+ * addition, for each of these queues BFQ performs or does not perform
+ * idling depending on which choice boosts the throughput more. The
+ * exact choice depends on the device and request pattern at
+ * hand.
+ *
+ * Unfortunately, false positives may occur while an interactive task
+ * is starting (e.g., an application is being started). The
+ * consequence is that the queues associated with the task do not
+ * enjoy weight raising as expected. Fortunately these false positives
+ * are very rare. They typically occur if some service happens to
+ * start doing I/O exactly when the interactive task starts.
+ *
+ * Turning back to the next function, it implements all the steps
+ * needed to detect the occurrence of a large burst and to properly
+ * mark all the queues belonging to it (so that they can then be
+ * treated in a different way). This goal is achieved by maintaining a
+ * "burst list" that holds, temporarily, the queues that belong to the
+ * burst in progress. The list is then used to mark these queues as
+ * belonging to a large burst if the burst does become large. The main
+ * steps are the following.
+ *
+ * . when the very first queue is created, the queue is inserted into the
+ *   list (as it could be the first queue in a possible burst)
+ *
+ * . if the current burst has not yet become large, and a queue Q that does
+ *   not yet belong to the burst is activated shortly after the last time
+ *   at which a new queue entered the burst list, then the function appends
+ *   Q to the burst list
+ *
+ * . if, as a consequence of the previous step, the burst size reaches
+ *   the large-burst threshold, then
+ *
+ *     . all the queues in the burst list are marked as belonging to a
+ *       large burst
+ *
+ *     . the burst list is deleted; in fact, the burst list already served
+ *       its purpose (keeping temporarily track of the queues in a burst,
+ *       so as to be able to mark them as belonging to a large burst in the
+ *       previous sub-step), and now is not needed any more
+ *
+ *     . the device enters a large-burst mode
+ *
+ * . if a queue Q that does not belong to the burst is created while
+ *   the device is in large-burst mode and shortly after the last time
+ *   at which a queue either entered the burst list or was marked as
+ *   belonging to the current large burst, then Q is immediately marked
+ *   as belonging to a large burst.
+ *
+ * . if a queue Q that does not belong to the burst is created a while
+ *   later, i.e., not shortly after, than the last time at which a queue
+ *   either entered the burst list or was marked as belonging to the
+ *   current large burst, then the current burst is deemed as finished and:
+ *
+ *        . the large-burst mode is reset if set
+ *
+ *        . the burst list is emptied
+ *
+ *        . Q is inserted in the burst list, as Q may be the first queue
+ *          in a possible new burst (then the burst list contains just Q
+ *          after this step).
+ */
+static void bfq_handle_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	/*
+	 * If bfqq is already in the burst list or is part of a large
+	 * burst, or finally has just been split, then there is
+	 * nothing else to do.
+	 */
+	if (!hlist_unhashed(&bfqq->burst_list_node) ||
+	    bfq_bfqq_in_large_burst(bfqq) ||
+	    time_is_after_eq_jiffies(bfqq->split_time +
+				     msecs_to_jiffies(10)))
+		return;
+
+	/*
+	 * If bfqq's creation happens late enough, or bfqq belongs to
+	 * a different group than the burst group, then the current
+	 * burst is finished, and related data structures must be
+	 * reset.
+	 *
+	 * In this respect, consider the special case where bfqq is
+	 * the very first queue created after BFQ is selected for this
+	 * device. In this case, last_ins_in_burst and
+	 * burst_parent_entity are not yet significant when we get
+	 * here. But it is easy to verify that, whether or not the
+	 * following condition is true, bfqq will end up being
+	 * inserted into the burst list. In particular the list will
+	 * happen to contain only bfqq. And this is exactly what has
+	 * to happen, as bfqq may be the first queue of the first
+	 * burst.
+	 */
+	if (time_is_before_jiffies(bfqd->last_ins_in_burst +
+	    bfqd->bfq_burst_interval) ||
+	    bfqq->entity.parent != bfqd->burst_parent_entity) {
+		bfqd->large_burst = false;
+		bfq_reset_burst_list(bfqd, bfqq);
+		goto end;
+	}
+
+	/*
+	 * If we get here, then bfqq is being activated shortly after the
+	 * last queue. So, if the current burst is also large, we can mark
+	 * bfqq as belonging to this large burst immediately.
+	 */
+	if (bfqd->large_burst) {
+		bfq_mark_bfqq_in_large_burst(bfqq);
+		goto end;
+	}
+
+	/*
+	 * If we get here, then a large-burst state has not yet been
+	 * reached, but bfqq is being activated shortly after the last
+	 * queue. Then we add bfqq to the burst.
+	 */
+	bfq_add_to_burst(bfqd, bfqq);
+end:
+	/*
+	 * At this point, bfqq either has been added to the current
+	 * burst or has caused the current burst to terminate and a
+	 * possible new burst to start. In particular, in the second
+	 * case, bfqq has become the first queue in the possible new
+	 * burst.  In both cases last_ins_in_burst needs to be moved
+	 * forward.
+	 */
+	bfqd->last_ins_in_burst = jiffies;
+}
+
+static int bfq_bfqq_budget_left(struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	return entity->budget - entity->service;
+}
+
+/*
+ * If enough samples have been computed, return the current max budget
+ * stored in bfqd, which is dynamically updated according to the
+ * estimated disk peak rate; otherwise return the default max budget
+ */
+static int bfq_max_budget(struct bfq_data *bfqd)
+{
+	if (bfqd->budgets_assigned < bfq_stats_min_budgets)
+		return bfq_default_max_budget;
+	else
+		return bfqd->bfq_max_budget;
+}
+
+/*
+ * Return min budget, which is a fraction of the current or default
+ * max budget (trying with 1/32)
+ */
+static int bfq_min_budget(struct bfq_data *bfqd)
+{
+	if (bfqd->budgets_assigned < bfq_stats_min_budgets)
+		return bfq_default_max_budget / 32;
+	else
+		return bfqd->bfq_max_budget / 32;
+}
+
+/*
+ * The next function, invoked after the input queue bfqq switches from
+ * idle to busy, updates the budget of bfqq. The function also tells
+ * whether the in-service queue should be expired, by returning
+ * true. The purpose of expiring the in-service queue is to give bfqq
+ * the chance to possibly preempt the in-service queue, and the reason
+ * for preempting the in-service queue is to achieve one of the two
+ * goals below.
+ *
+ * 1. Guarantee to bfqq its reserved bandwidth even if bfqq has
+ * expired because it has remained idle. In particular, bfqq may have
+ * expired for one of the following two reasons:
+ *
+ * - BFQQE_NO_MORE_REQUESTS bfqq did not enjoy any device idling
+ *   and did not make it to issue a new request before its last
+ *   request was served;
+ *
+ * - BFQQE_TOO_IDLE bfqq did enjoy device idling, but did not issue
+ *   a new request before the expiration of the idling-time.
+ *
+ * Even if bfqq has expired for one of the above reasons, the process
+ * associated with the queue may be however issuing requests greedily,
+ * and thus be sensitive to the bandwidth it receives (bfqq may have
+ * remained idle for other reasons: CPU high load, bfqq not enjoying
+ * idling, I/O throttling somewhere in the path from the process to
+ * the I/O scheduler, ...). But if, after every expiration for one of
+ * the above two reasons, bfqq has to wait for the service of at least
+ * one full budget of another queue before being served again, then
+ * bfqq is likely to get a much lower bandwidth or resource time than
+ * its reserved ones. To address this issue, two countermeasures need
+ * to be taken.
+ *
+ * First, the budget and the timestamps of bfqq need to be updated in
+ * a special way on bfqq reactivation: they need to be updated as if
+ * bfqq did not remain idle and did not expire. In fact, if they are
+ * computed as if bfqq expired and remained idle until reactivation,
+ * then the process associated with bfqq is treated as if, instead of
+ * being greedy, it stopped issuing requests when bfqq remained idle,
+ * and restarts issuing requests only on this reactivation. In other
+ * words, the scheduler does not help the process recover the "service
+ * hole" between bfqq expiration and reactivation. As a consequence,
+ * the process receives a lower bandwidth than its reserved one. In
+ * contrast, to recover this hole, the budget must be updated as if
+ * bfqq was not expired at all before this reactivation, i.e., it must
+ * be set to the value of the remaining budget when bfqq was
+ * expired. Along the same line, timestamps need to be assigned the
+ * value they had the last time bfqq was selected for service, i.e.,
+ * before last expiration. Thus timestamps need to be back-shifted
+ * with respect to their normal computation (see [1] for more details
+ * on this tricky aspect).
+ *
+ * Secondly, to allow the process to recover the hole, the in-service
+ * queue must be expired too, to give bfqq the chance to preempt it
+ * immediately. In fact, if bfqq has to wait for a full budget of the
+ * in-service queue to be completed, then it may become impossible to
+ * let the process recover the hole, even if the back-shifted
+ * timestamps of bfqq are lower than those of the in-service queue. If
+ * this happens for most or all of the holes, then the process may not
+ * receive its reserved bandwidth. In this respect, it is worth noting
+ * that, being the service of outstanding requests unpreemptible, a
+ * little fraction of the holes may however be unrecoverable, thereby
+ * causing a little loss of bandwidth.
+ *
+ * The last important point is detecting whether bfqq does need this
+ * bandwidth recovery. In this respect, the next function deems the
+ * process associated with bfqq greedy, and thus allows it to recover
+ * the hole, if: 1) the process is waiting for the arrival of a new
+ * request (which implies that bfqq expired for one of the above two
+ * reasons), and 2) such a request has arrived soon. The first
+ * condition is controlled through the flag non_blocking_wait_rq,
+ * while the second through the flag arrived_in_time. If both
+ * conditions hold, then the function computes the budget in the
+ * above-described special way, and signals that the in-service queue
+ * should be expired. Timestamp back-shifting is done later in
+ * __bfq_activate_entity.
+ *
+ * 2. Reduce latency. Even if timestamps are not backshifted to let
+ * the process associated with bfqq recover a service hole, bfqq may
+ * however happen to have, after being (re)activated, a lower finish
+ * timestamp than the in-service queue.	 That is, the next budget of
+ * bfqq may have to be completed before the one of the in-service
+ * queue. If this is the case, then preempting the in-service queue
+ * allows this goal to be achieved, apart from the unpreemptible,
+ * outstanding requests mentioned above.
+ *
+ * Unfortunately, regardless of which of the above two goals one wants
+ * to achieve, service trees need first to be updated to know whether
+ * the in-service queue must be preempted. To have service trees
+ * correctly updated, the in-service queue must be expired and
+ * rescheduled, and bfqq must be scheduled too. This is one of the
+ * most costly operations (in future versions, the scheduling
+ * mechanism may be re-designed in such a way to make it possible to
+ * know whether preemption is needed without needing to update service
+ * trees). In addition, queue preemptions almost always cause random
+ * I/O, and thus loss of throughput. Because of these facts, the next
+ * function adopts the following simple scheme to avoid both costly
+ * operations and too frequent preemptions: it requests the expiration
+ * of the in-service queue (unconditionally) only for queues that need
+ * to recover a hole, or that either are weight-raised or deserve to
+ * be weight-raised.
+ */
+static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
+						struct bfq_queue *bfqq,
+						bool arrived_in_time,
+						bool wr_or_deserves_wr)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	if (bfq_bfqq_non_blocking_wait_rq(bfqq) && arrived_in_time) {
+		/*
+		 * We do not clear the flag non_blocking_wait_rq here, as
+		 * the latter is used in bfq_activate_bfqq to signal
+		 * that timestamps need to be back-shifted (and is
+		 * cleared right after).
+		 */
+
+		/*
+		 * In next assignment we rely on that either
+		 * entity->service or entity->budget are not updated
+		 * on expiration if bfqq is empty (see
+		 * __bfq_bfqq_recalc_budget). Thus both quantities
+		 * remain unchanged after such an expiration, and the
+		 * following statement therefore assigns to
+		 * entity->budget the remaining budget on such an
+		 * expiration. For clarity, entity->service is not
+		 * updated on expiration in any case, and, in normal
+		 * operation, is reset only when bfqq is selected for
+		 * service (see bfq_get_next_queue).
+		 */
+		entity->budget = min_t(unsigned long,
+				       bfq_bfqq_budget_left(bfqq),
+				       bfqq->max_budget);
+
+		return true;
+	}
+
+	entity->budget = max_t(unsigned long, bfqq->max_budget,
+			       bfq_serv_to_charge(bfqq->next_rq, bfqq));
+	bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
+	return wr_or_deserves_wr;
+}
+
+static unsigned int bfq_wr_duration(struct bfq_data *bfqd)
+{
+	u64 dur;
+
+	if (bfqd->bfq_wr_max_time > 0)
+		return bfqd->bfq_wr_max_time;
+
+	dur = bfqd->RT_prod;
+	do_div(dur, bfqd->peak_rate);
+
+	/*
+	 * Limit duration between 3 and 13 seconds. Tests show that
+	 * higher values than 13 seconds often yield the opposite of
+	 * the desired result, i.e., worsen responsiveness by letting
+	 * non-interactive and non-soft-real-time applications
+	 * preserve weight raising for a too long time interval.
+	 *
+	 * On the other end, lower values than 3 seconds make it
+	 * difficult for most interactive tasks to complete their jobs
+	 * before weight-raising finishes.
+	 */
+	if (dur > msecs_to_jiffies(13000))
+		dur = msecs_to_jiffies(13000);
+	else if (dur < msecs_to_jiffies(3000))
+		dur = msecs_to_jiffies(3000);
+
+	return dur;
+}
+
+static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd,
+					     struct bfq_queue *bfqq,
+					     unsigned int old_wr_coeff,
+					     bool wr_or_deserves_wr,
+					     bool interactive,
+					     bool in_burst,
+					     bool soft_rt)
+{
+	if (old_wr_coeff == 1 && wr_or_deserves_wr) {
+		/* start a weight-raising period */
+		if (interactive) {
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+		} else {
+			bfqq->wr_start_at_switch_to_srt = jiffies;
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff *
+				BFQ_SOFTRT_WEIGHT_FACTOR;
+			bfqq->wr_cur_max_time =
+				bfqd->bfq_wr_rt_max_time;
+		}
+
+		/*
+		 * If needed, further reduce budget to make sure it is
+		 * close to bfqq's backlog, so as to reduce the
+		 * scheduling-error component due to a too large
+		 * budget. Do not care about throughput consequences,
+		 * but only about latency. Finally, do not assign a
+		 * too small budget either, to avoid increasing
+		 * latency by causing too frequent expirations.
+		 */
+		bfqq->entity.budget = min_t(unsigned long,
+					    bfqq->entity.budget,
+					    2 * bfq_min_budget(bfqd));
+	} else if (old_wr_coeff > 1) {
+		if (interactive) { /* update wr coeff and duration */
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+		} else if (in_burst)
+			bfqq->wr_coeff = 1;
+		else if (soft_rt) {
+			/*
+			 * The application is now or still meeting the
+			 * requirements for being deemed soft rt.  We
+			 * can then correctly and safely (re)charge
+			 * the weight-raising duration for the
+			 * application with the weight-raising
+			 * duration for soft rt applications.
+			 *
+			 * In particular, doing this recharge now, i.e.,
+			 * before the weight-raising period for the
+			 * application finishes, reduces the probability
+			 * of the following negative scenario:
+			 * 1) the weight of a soft rt application is
+			 *    raised at startup (as for any newly
+			 *    created application),
+			 * 2) since the application is not interactive,
+			 *    at a certain time weight-raising is
+			 *    stopped for the application,
+			 * 3) at that time the application happens to
+			 *    still have pending requests, and hence
+			 *    is destined to not have a chance to be
+			 *    deemed soft rt before these requests are
+			 *    completed (see the comments to the
+			 *    function bfq_bfqq_softrt_next_start()
+			 *    for details on soft rt detection),
+			 * 4) these pending requests experience a high
+			 *    latency because the application is not
+			 *    weight-raised while they are pending.
+			 */
+			if (bfqq->wr_cur_max_time !=
+				bfqd->bfq_wr_rt_max_time) {
+				bfqq->wr_start_at_switch_to_srt =
+					bfqq->last_wr_start_finish;
+
+				bfqq->wr_cur_max_time =
+					bfqd->bfq_wr_rt_max_time;
+				bfqq->wr_coeff = bfqd->bfq_wr_coeff *
+					BFQ_SOFTRT_WEIGHT_FACTOR;
+			}
+			bfqq->last_wr_start_finish = jiffies;
+		}
+	}
+}
+
+static bool bfq_bfqq_idle_for_long_time(struct bfq_data *bfqd,
+					struct bfq_queue *bfqq)
+{
+	return bfqq->dispatched == 0 &&
+		time_is_before_jiffies(
+			bfqq->budget_timeout +
+			bfqd->bfq_wr_min_idle_time);
+}
+
+static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd,
+					     struct bfq_queue *bfqq,
+					     int old_wr_coeff,
+					     struct request *rq,
+					     bool *interactive)
+{
+	bool soft_rt, in_burst,	wr_or_deserves_wr,
+		bfqq_wants_to_preempt,
+		idle_for_long_time = bfq_bfqq_idle_for_long_time(bfqd, bfqq),
+		/*
+		 * See the comments on
+		 * bfq_bfqq_update_budg_for_activation for
+		 * details on the usage of the next variable.
+		 */
+		arrived_in_time =  ktime_get_ns() <=
+			bfqq->ttime.last_end_request +
+			bfqd->bfq_slice_idle * 3;
+
+	bfqg_stats_update_io_add(bfqq_group(RQ_BFQQ(rq)), bfqq, rq->cmd_flags);
+
+	/*
+	 * bfqq deserves to be weight-raised if:
+	 * - it is sync,
+	 * - it does not belong to a large burst,
+	 * - it has been idle for enough time or is soft real-time,
+	 * - is linked to a bfq_io_cq (it is not shared in any sense).
+	 */
+	in_burst = bfq_bfqq_in_large_burst(bfqq);
+	soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 &&
+		!in_burst &&
+		time_is_before_jiffies(bfqq->soft_rt_next_start);
+	*interactive = !in_burst && idle_for_long_time;
+	wr_or_deserves_wr = bfqd->low_latency &&
+		(bfqq->wr_coeff > 1 ||
+		 (bfq_bfqq_sync(bfqq) &&
+		  bfqq->bic && (*interactive || soft_rt)));
+
+	/*
+	 * Using the last flag, update budget and check whether bfqq
+	 * may want to preempt the in-service queue.
+	 */
+	bfqq_wants_to_preempt =
+		bfq_bfqq_update_budg_for_activation(bfqd, bfqq,
+						    arrived_in_time,
+						    wr_or_deserves_wr);
+
+	/*
+	 * If bfqq happened to be activated in a burst, but has been
+	 * idle for much more than an interactive queue, then we
+	 * assume that, in the overall I/O initiated in the burst, the
+	 * I/O associated with bfqq is finished. So bfqq does not need
+	 * to be treated as a queue belonging to a burst
+	 * anymore. Accordingly, we reset bfqq's in_large_burst flag
+	 * if set, and remove bfqq from the burst list if it's
+	 * there. We do not decrement burst_size, because the fact
+	 * that bfqq does not need to belong to the burst list any
+	 * more does not invalidate the fact that bfqq was created in
+	 * a burst.
+	 */
+	if (likely(!bfq_bfqq_just_created(bfqq)) &&
+	    idle_for_long_time &&
+	    time_is_before_jiffies(
+		    bfqq->budget_timeout +
+		    msecs_to_jiffies(10000))) {
+		hlist_del_init(&bfqq->burst_list_node);
+		bfq_clear_bfqq_in_large_burst(bfqq);
+	}
+
+	bfq_clear_bfqq_just_created(bfqq);
+
+
+	if (!bfq_bfqq_IO_bound(bfqq)) {
+		if (arrived_in_time) {
+			bfqq->requests_within_timer++;
+			if (bfqq->requests_within_timer >=
+			    bfqd->bfq_requests_within_timer)
+				bfq_mark_bfqq_IO_bound(bfqq);
+		} else
+			bfqq->requests_within_timer = 0;
+	}
+
+	if (bfqd->low_latency) {
+		if (unlikely(time_is_after_jiffies(bfqq->split_time)))
+			/* wraparound */
+			bfqq->split_time =
+				jiffies - bfqd->bfq_wr_min_idle_time - 1;
+
+		if (time_is_before_jiffies(bfqq->split_time +
+					   bfqd->bfq_wr_min_idle_time)) {
+			bfq_update_bfqq_wr_on_rq_arrival(bfqd, bfqq,
+							 old_wr_coeff,
+							 wr_or_deserves_wr,
+							 *interactive,
+							 in_burst,
+							 soft_rt);
+
+			if (old_wr_coeff != bfqq->wr_coeff)
+				bfqq->entity.prio_changed = 1;
+		}
+	}
+
+	bfqq->last_idle_bklogged = jiffies;
+	bfqq->service_from_backlogged = 0;
+	bfq_clear_bfqq_softrt_update(bfqq);
+
+	bfq_add_bfqq_busy(bfqd, bfqq);
+
+	/*
+	 * Expire in-service queue only if preemption may be needed
+	 * for guarantees. In this respect, the function
+	 * next_queue_may_preempt just checks a simple, necessary
+	 * condition, and not a sufficient condition based on
+	 * timestamps. In fact, for the latter condition to be
+	 * evaluated, timestamps would need first to be updated, and
+	 * this operation is quite costly (see the comments on the
+	 * function bfq_bfqq_update_budg_for_activation).
+	 */
+	if (bfqd->in_service_queue && bfqq_wants_to_preempt &&
+	    bfqd->in_service_queue->wr_coeff < bfqq->wr_coeff &&
+	    next_queue_may_preempt(bfqd))
+		bfq_bfqq_expire(bfqd, bfqd->in_service_queue,
+				false, BFQQE_PREEMPTED);
+}
+
+static void bfq_add_request(struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	struct bfq_data *bfqd = bfqq->bfqd;
+	struct request *next_rq, *prev;
+	unsigned int old_wr_coeff = bfqq->wr_coeff;
+	bool interactive = false;
+
+	bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
+	bfqq->queued[rq_is_sync(rq)]++;
+	bfqd->queued++;
+
+	elv_rb_add(&bfqq->sort_list, rq);
+
+	/*
+	 * Check if this request is a better next-serve candidate.
+	 */
+	prev = bfqq->next_rq;
+	next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position);
+	bfqq->next_rq = next_rq;
+
+	/*
+	 * Adjust priority tree position, if next_rq changes.
+	 */
+	if (prev != bfqq->next_rq)
+		bfq_pos_tree_add_move(bfqd, bfqq);
+
+	if (!bfq_bfqq_busy(bfqq)) /* switching to busy ... */
+		bfq_bfqq_handle_idle_busy_switch(bfqd, bfqq, old_wr_coeff,
+						 rq, &interactive);
+	else {
+		if (bfqd->low_latency && old_wr_coeff == 1 && !rq_is_sync(rq) &&
+		    time_is_before_jiffies(
+				bfqq->last_wr_start_finish +
+				bfqd->bfq_wr_min_inter_arr_async)) {
+			bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+			bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+
+			bfqd->wr_busy_queues++;
+			bfqq->entity.prio_changed = 1;
+		}
+		if (prev != bfqq->next_rq)
+			bfq_updated_next_req(bfqd, bfqq);
+	}
+
+	/*
+	 * Assign jiffies to last_wr_start_finish in the following
+	 * cases:
+	 *
+	 * . if bfqq is not going to be weight-raised, because, for
+	 *   non weight-raised queues, last_wr_start_finish stores the
+	 *   arrival time of the last request; as of now, this piece
+	 *   of information is used only for deciding whether to
+	 *   weight-raise async queues
+	 *
+	 * . if bfqq is not weight-raised, because, if bfqq is now
+	 *   switching to weight-raised, then last_wr_start_finish
+	 *   stores the time when weight-raising starts
+	 *
+	 * . if bfqq is interactive, because, regardless of whether
+	 *   bfqq is currently weight-raised, the weight-raising
+	 *   period must start or restart (this case is considered
+	 *   separately because it is not detected by the above
+	 *   conditions, if bfqq is already weight-raised)
+	 *
+	 * last_wr_start_finish has to be updated also if bfqq is soft
+	 * real-time, because the weight-raising period is constantly
+	 * restarted on idle-to-busy transitions for these queues, but
+	 * this is already done in bfq_bfqq_handle_idle_busy_switch if
+	 * needed.
+	 */
+	if (bfqd->low_latency &&
+		(old_wr_coeff == 1 || bfqq->wr_coeff == 1 || interactive))
+		bfqq->last_wr_start_finish = jiffies;
+}
+
+static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd,
+					  struct bio *bio,
+					  struct request_queue *q)
+{
+	struct bfq_queue *bfqq = bfqd->bio_bfqq;
+
+
+	if (bfqq)
+		return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio));
+
+	return NULL;
+}
+
+static sector_t get_sdist(sector_t last_pos, struct request *rq)
+{
+	if (last_pos)
+		return abs(blk_rq_pos(rq) - last_pos);
+
+	return 0;
+}
+
+#if 0 /* Still not clear if we can do without next two functions */
+static void bfq_activate_request(struct request_queue *q, struct request *rq)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+
+	bfqd->rq_in_driver++;
+}
+
+static void bfq_deactivate_request(struct request_queue *q, struct request *rq)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+
+	bfqd->rq_in_driver--;
+}
+#endif
+
+static void bfq_remove_request(struct request_queue *q,
+			       struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	struct bfq_data *bfqd = bfqq->bfqd;
+	const int sync = rq_is_sync(rq);
+
+	if (bfqq->next_rq == rq) {
+		bfqq->next_rq = bfq_find_next_rq(bfqd, bfqq, rq);
+		bfq_updated_next_req(bfqd, bfqq);
+	}
+
+	if (rq->queuelist.prev != &rq->queuelist)
+		list_del_init(&rq->queuelist);
+	bfqq->queued[sync]--;
+	bfqd->queued--;
+	elv_rb_del(&bfqq->sort_list, rq);
+
+	elv_rqhash_del(q, rq);
+	if (q->last_merge == rq)
+		q->last_merge = NULL;
+
+	if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
+		bfqq->next_rq = NULL;
+
+		if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue) {
+			bfq_del_bfqq_busy(bfqd, bfqq, false);
+			/*
+			 * bfqq emptied. In normal operation, when
+			 * bfqq is empty, bfqq->entity.service and
+			 * bfqq->entity.budget must contain,
+			 * respectively, the service received and the
+			 * budget used last time bfqq emptied. These
+			 * facts do not hold in this case, as at least
+			 * this last removal occurred while bfqq is
+			 * not in service. To avoid inconsistencies,
+			 * reset both bfqq->entity.service and
+			 * bfqq->entity.budget, if bfqq has still a
+			 * process that may issue I/O requests to it.
+			 */
+			bfqq->entity.budget = bfqq->entity.service = 0;
+		}
+
+		/*
+		 * Remove queue from request-position tree as it is empty.
+		 */
+		if (bfqq->pos_root) {
+			rb_erase(&bfqq->pos_node, bfqq->pos_root);
+			bfqq->pos_root = NULL;
+		}
+	}
+
+	if (rq->cmd_flags & REQ_META)
+		bfqq->meta_pending--;
+
+	bfqg_stats_update_io_remove(bfqq_group(bfqq), rq->cmd_flags);
+}
+
+static bool bfq_bio_merge(struct blk_mq_hw_ctx *hctx, struct bio *bio)
+{
+	struct request_queue *q = hctx->queue;
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct request *free = NULL;
+	/*
+	 * bfq_bic_lookup grabs the queue_lock: invoke it now and
+	 * store its return value for later use, to avoid nesting
+	 * queue_lock inside the bfqd->lock. We assume that the bic
+	 * returned by bfq_bic_lookup does not go away before
+	 * bfqd->lock is taken.
+	 */
+	struct bfq_io_cq *bic = bfq_bic_lookup(bfqd, current->io_context, q);
+	bool ret;
+
+	spin_lock_irq(&bfqd->lock);
+
+	if (bic)
+		bfqd->bio_bfqq = bic_to_bfqq(bic, op_is_sync(bio->bi_opf));
+	else
+		bfqd->bio_bfqq = NULL;
+	bfqd->bio_bic = bic;
+
+	ret = blk_mq_sched_try_merge(q, bio, &free);
+
+	if (free)
+		blk_mq_free_request(free);
+	spin_unlock_irq(&bfqd->lock);
+
+	return ret;
+}
+
+static int bfq_request_merge(struct request_queue *q, struct request **req,
+			     struct bio *bio)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct request *__rq;
+
+	__rq = bfq_find_rq_fmerge(bfqd, bio, q);
+	if (__rq && elv_bio_merge_ok(__rq, bio)) {
+		*req = __rq;
+		return ELEVATOR_FRONT_MERGE;
+	}
+
+	return ELEVATOR_NO_MERGE;
+}
+
+static void bfq_request_merged(struct request_queue *q, struct request *req,
+			       enum elv_merge type)
+{
+	if (type == ELEVATOR_FRONT_MERGE &&
+	    rb_prev(&req->rb_node) &&
+	    blk_rq_pos(req) <
+	    blk_rq_pos(container_of(rb_prev(&req->rb_node),
+				    struct request, rb_node))) {
+		struct bfq_queue *bfqq = RQ_BFQQ(req);
+		struct bfq_data *bfqd = bfqq->bfqd;
+		struct request *prev, *next_rq;
+
+		/* Reposition request in its sort_list */
+		elv_rb_del(&bfqq->sort_list, req);
+		elv_rb_add(&bfqq->sort_list, req);
+
+		/* Choose next request to be served for bfqq */
+		prev = bfqq->next_rq;
+		next_rq = bfq_choose_req(bfqd, bfqq->next_rq, req,
+					 bfqd->last_position);
+		bfqq->next_rq = next_rq;
+		/*
+		 * If next_rq changes, update both the queue's budget to
+		 * fit the new request and the queue's position in its
+		 * rq_pos_tree.
+		 */
+		if (prev != bfqq->next_rq) {
+			bfq_updated_next_req(bfqd, bfqq);
+			bfq_pos_tree_add_move(bfqd, bfqq);
+		}
+	}
+}
+
+static void bfq_requests_merged(struct request_queue *q, struct request *rq,
+				struct request *next)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq), *next_bfqq = RQ_BFQQ(next);
+
+	if (!RB_EMPTY_NODE(&rq->rb_node))
+		goto end;
+	spin_lock_irq(&bfqq->bfqd->lock);
+
+	/*
+	 * If next and rq belong to the same bfq_queue and next is older
+	 * than rq, then reposition rq in the fifo (by substituting next
+	 * with rq). Otherwise, if next and rq belong to different
+	 * bfq_queues, never reposition rq: in fact, we would have to
+	 * reposition it with respect to next's position in its own fifo,
+	 * which would most certainly be too expensive with respect to
+	 * the benefits.
+	 */
+	if (bfqq == next_bfqq &&
+	    !list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
+	    next->fifo_time < rq->fifo_time) {
+		list_del_init(&rq->queuelist);
+		list_replace_init(&next->queuelist, &rq->queuelist);
+		rq->fifo_time = next->fifo_time;
+	}
+
+	if (bfqq->next_rq == next)
+		bfqq->next_rq = rq;
+
+	bfq_remove_request(q, next);
+
+	spin_unlock_irq(&bfqq->bfqd->lock);
+end:
+	bfqg_stats_update_io_merged(bfqq_group(bfqq), next->cmd_flags);
+}
+
+/* Must be called with bfqq != NULL */
+static void bfq_bfqq_end_wr(struct bfq_queue *bfqq)
+{
+	if (bfq_bfqq_busy(bfqq))
+		bfqq->bfqd->wr_busy_queues--;
+	bfqq->wr_coeff = 1;
+	bfqq->wr_cur_max_time = 0;
+	bfqq->last_wr_start_finish = jiffies;
+	/*
+	 * Trigger a weight change on the next invocation of
+	 * __bfq_entity_update_weight_prio.
+	 */
+	bfqq->entity.prio_changed = 1;
+}
+
+void bfq_end_wr_async_queues(struct bfq_data *bfqd,
+			     struct bfq_group *bfqg)
+{
+	int i, j;
+
+	for (i = 0; i < 2; i++)
+		for (j = 0; j < IOPRIO_BE_NR; j++)
+			if (bfqg->async_bfqq[i][j])
+				bfq_bfqq_end_wr(bfqg->async_bfqq[i][j]);
+	if (bfqg->async_idle_bfqq)
+		bfq_bfqq_end_wr(bfqg->async_idle_bfqq);
+}
+
+static void bfq_end_wr(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq;
+
+	spin_lock_irq(&bfqd->lock);
+
+	list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list)
+		bfq_bfqq_end_wr(bfqq);
+	list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list)
+		bfq_bfqq_end_wr(bfqq);
+	bfq_end_wr_async(bfqd);
+
+	spin_unlock_irq(&bfqd->lock);
+}
+
+static sector_t bfq_io_struct_pos(void *io_struct, bool request)
+{
+	if (request)
+		return blk_rq_pos(io_struct);
+	else
+		return ((struct bio *)io_struct)->bi_iter.bi_sector;
+}
+
+static int bfq_rq_close_to_sector(void *io_struct, bool request,
+				  sector_t sector)
+{
+	return abs(bfq_io_struct_pos(io_struct, request) - sector) <=
+	       BFQQ_CLOSE_THR;
+}
+
+static struct bfq_queue *bfqq_find_close(struct bfq_data *bfqd,
+					 struct bfq_queue *bfqq,
+					 sector_t sector)
+{
+	struct rb_root *root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree;
+	struct rb_node *parent, *node;
+	struct bfq_queue *__bfqq;
+
+	if (RB_EMPTY_ROOT(root))
+		return NULL;
+
+	/*
+	 * First, if we find a request starting at the end of the last
+	 * request, choose it.
+	 */
+	__bfqq = bfq_rq_pos_tree_lookup(bfqd, root, sector, &parent, NULL);
+	if (__bfqq)
+		return __bfqq;
+
+	/*
+	 * If the exact sector wasn't found, the parent of the NULL leaf
+	 * will contain the closest sector (rq_pos_tree sorted by
+	 * next_request position).
+	 */
+	__bfqq = rb_entry(parent, struct bfq_queue, pos_node);
+	if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
+		return __bfqq;
+
+	if (blk_rq_pos(__bfqq->next_rq) < sector)
+		node = rb_next(&__bfqq->pos_node);
+	else
+		node = rb_prev(&__bfqq->pos_node);
+	if (!node)
+		return NULL;
+
+	__bfqq = rb_entry(node, struct bfq_queue, pos_node);
+	if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector))
+		return __bfqq;
+
+	return NULL;
+}
+
+static struct bfq_queue *bfq_find_close_cooperator(struct bfq_data *bfqd,
+						   struct bfq_queue *cur_bfqq,
+						   sector_t sector)
+{
+	struct bfq_queue *bfqq;
+
+	/*
+	 * We shall notice if some of the queues are cooperating,
+	 * e.g., working closely on the same area of the device. In
+	 * that case, we can group them together and: 1) don't waste
+	 * time idling, and 2) serve the union of their requests in
+	 * the best possible order for throughput.
+	 */
+	bfqq = bfqq_find_close(bfqd, cur_bfqq, sector);
+	if (!bfqq || bfqq == cur_bfqq)
+		return NULL;
+
+	return bfqq;
+}
+
+static struct bfq_queue *
+bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
+{
+	int process_refs, new_process_refs;
+	struct bfq_queue *__bfqq;
+
+	/*
+	 * If there are no process references on the new_bfqq, then it is
+	 * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain
+	 * may have dropped their last reference (not just their last process
+	 * reference).
+	 */
+	if (!bfqq_process_refs(new_bfqq))
+		return NULL;
+
+	/* Avoid a circular list and skip interim queue merges. */
+	while ((__bfqq = new_bfqq->new_bfqq)) {
+		if (__bfqq == bfqq)
+			return NULL;
+		new_bfqq = __bfqq;
+	}
+
+	process_refs = bfqq_process_refs(bfqq);
+	new_process_refs = bfqq_process_refs(new_bfqq);
+	/*
+	 * If the process for the bfqq has gone away, there is no
+	 * sense in merging the queues.
+	 */
+	if (process_refs == 0 || new_process_refs == 0)
+		return NULL;
+
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d",
+		new_bfqq->pid);
+
+	/*
+	 * Merging is just a redirection: the requests of the process
+	 * owning one of the two queues are redirected to the other queue.
+	 * The latter queue, in its turn, is set as shared if this is the
+	 * first time that the requests of some process are redirected to
+	 * it.
+	 *
+	 * We redirect bfqq to new_bfqq and not the opposite, because
+	 * we are in the context of the process owning bfqq, thus we
+	 * have the io_cq of this process. So we can immediately
+	 * configure this io_cq to redirect the requests of the
+	 * process to new_bfqq. In contrast, the io_cq of new_bfqq is
+	 * not available any more (new_bfqq->bic == NULL).
+	 *
+	 * Anyway, even in case new_bfqq coincides with the in-service
+	 * queue, redirecting requests the in-service queue is the
+	 * best option, as we feed the in-service queue with new
+	 * requests close to the last request served and, by doing so,
+	 * are likely to increase the throughput.
+	 */
+	bfqq->new_bfqq = new_bfqq;
+	new_bfqq->ref += process_refs;
+	return new_bfqq;
+}
+
+static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq,
+					struct bfq_queue *new_bfqq)
+{
+	if (bfq_class_idle(bfqq) || bfq_class_idle(new_bfqq) ||
+	    (bfqq->ioprio_class != new_bfqq->ioprio_class))
+		return false;
+
+	/*
+	 * If either of the queues has already been detected as seeky,
+	 * then merging it with the other queue is unlikely to lead to
+	 * sequential I/O.
+	 */
+	if (BFQQ_SEEKY(bfqq) || BFQQ_SEEKY(new_bfqq))
+		return false;
+
+	/*
+	 * Interleaved I/O is known to be done by (some) applications
+	 * only for reads, so it does not make sense to merge async
+	 * queues.
+	 */
+	if (!bfq_bfqq_sync(bfqq) || !bfq_bfqq_sync(new_bfqq))
+		return false;
+
+	return true;
+}
+
+/*
+ * If this function returns true, then bfqq cannot be merged. The idea
+ * is that true cooperation happens very early after processes start
+ * to do I/O. Usually, late cooperations are just accidental false
+ * positives. In case bfqq is weight-raised, such false positives
+ * would evidently degrade latency guarantees for bfqq.
+ */
+static bool wr_from_too_long(struct bfq_queue *bfqq)
+{
+	return bfqq->wr_coeff > 1 &&
+		time_is_before_jiffies(bfqq->last_wr_start_finish +
+				       msecs_to_jiffies(100));
+}
+
+/*
+ * Attempt to schedule a merge of bfqq with the currently in-service
+ * queue or with a close queue among the scheduled queues.  Return
+ * NULL if no merge was scheduled, a pointer to the shared bfq_queue
+ * structure otherwise.
+ *
+ * The OOM queue is not allowed to participate to cooperation: in fact, since
+ * the requests temporarily redirected to the OOM queue could be redirected
+ * again to dedicated queues at any time, the state needed to correctly
+ * handle merging with the OOM queue would be quite complex and expensive
+ * to maintain. Besides, in such a critical condition as an out of memory,
+ * the benefits of queue merging may be little relevant, or even negligible.
+ *
+ * Weight-raised queues can be merged only if their weight-raising
+ * period has just started. In fact cooperating processes are usually
+ * started together. Thus, with this filter we avoid false positives
+ * that would jeopardize low-latency guarantees.
+ *
+ * WARNING: queue merging may impair fairness among non-weight raised
+ * queues, for at least two reasons: 1) the original weight of a
+ * merged queue may change during the merged state, 2) even being the
+ * weight the same, a merged queue may be bloated with many more
+ * requests than the ones produced by its originally-associated
+ * process.
+ */
+static struct bfq_queue *
+bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		     void *io_struct, bool request)
+{
+	struct bfq_queue *in_service_bfqq, *new_bfqq;
+
+	if (bfqq->new_bfqq)
+		return bfqq->new_bfqq;
+
+	if (!io_struct ||
+	    wr_from_too_long(bfqq) ||
+	    unlikely(bfqq == &bfqd->oom_bfqq))
+		return NULL;
+
+	/* If there is only one backlogged queue, don't search. */
+	if (bfqd->busy_queues == 1)
+		return NULL;
+
+	in_service_bfqq = bfqd->in_service_queue;
+
+	if (!in_service_bfqq || in_service_bfqq == bfqq
+	    || wr_from_too_long(in_service_bfqq) ||
+	    unlikely(in_service_bfqq == &bfqd->oom_bfqq))
+		goto check_scheduled;
+
+	if (bfq_rq_close_to_sector(io_struct, request, bfqd->last_position) &&
+	    bfqq->entity.parent == in_service_bfqq->entity.parent &&
+	    bfq_may_be_close_cooperator(bfqq, in_service_bfqq)) {
+		new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq);
+		if (new_bfqq)
+			return new_bfqq;
+	}
+	/*
+	 * Check whether there is a cooperator among currently scheduled
+	 * queues. The only thing we need is that the bio/request is not
+	 * NULL, as we need it to establish whether a cooperator exists.
+	 */
+check_scheduled:
+	new_bfqq = bfq_find_close_cooperator(bfqd, bfqq,
+			bfq_io_struct_pos(io_struct, request));
+
+	if (new_bfqq && !wr_from_too_long(new_bfqq) &&
+	    likely(new_bfqq != &bfqd->oom_bfqq) &&
+	    bfq_may_be_close_cooperator(bfqq, new_bfqq))
+		return bfq_setup_merge(bfqq, new_bfqq);
+
+	return NULL;
+}
+
+static void bfq_bfqq_save_state(struct bfq_queue *bfqq)
+{
+	struct bfq_io_cq *bic = bfqq->bic;
+
+	/*
+	 * If !bfqq->bic, the queue is already shared or its requests
+	 * have already been redirected to a shared queue; both idle window
+	 * and weight raising state have already been saved. Do nothing.
+	 */
+	if (!bic)
+		return;
+
+	bic->saved_ttime = bfqq->ttime;
+	bic->saved_idle_window = bfq_bfqq_idle_window(bfqq);
+	bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq);
+	bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq);
+	bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node);
+	bic->saved_wr_coeff = bfqq->wr_coeff;
+	bic->saved_wr_start_at_switch_to_srt = bfqq->wr_start_at_switch_to_srt;
+	bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish;
+	bic->saved_wr_cur_max_time = bfqq->wr_cur_max_time;
+}
+
+static void
+bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
+		struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
+{
+	bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
+		(unsigned long)new_bfqq->pid);
+	/* Save weight raising and idle window of the merged queues */
+	bfq_bfqq_save_state(bfqq);
+	bfq_bfqq_save_state(new_bfqq);
+	if (bfq_bfqq_IO_bound(bfqq))
+		bfq_mark_bfqq_IO_bound(new_bfqq);
+	bfq_clear_bfqq_IO_bound(bfqq);
+
+	/*
+	 * If bfqq is weight-raised, then let new_bfqq inherit
+	 * weight-raising. To reduce false positives, neglect the case
+	 * where bfqq has just been created, but has not yet made it
+	 * to be weight-raised (which may happen because EQM may merge
+	 * bfqq even before bfq_add_request is executed for the first
+	 * time for bfqq). Handling this case would however be very
+	 * easy, thanks to the flag just_created.
+	 */
+	if (new_bfqq->wr_coeff == 1 && bfqq->wr_coeff > 1) {
+		new_bfqq->wr_coeff = bfqq->wr_coeff;
+		new_bfqq->wr_cur_max_time = bfqq->wr_cur_max_time;
+		new_bfqq->last_wr_start_finish = bfqq->last_wr_start_finish;
+		new_bfqq->wr_start_at_switch_to_srt =
+			bfqq->wr_start_at_switch_to_srt;
+		if (bfq_bfqq_busy(new_bfqq))
+			bfqd->wr_busy_queues++;
+		new_bfqq->entity.prio_changed = 1;
+	}
+
+	if (bfqq->wr_coeff > 1) { /* bfqq has given its wr to new_bfqq */
+		bfqq->wr_coeff = 1;
+		bfqq->entity.prio_changed = 1;
+		if (bfq_bfqq_busy(bfqq))
+			bfqd->wr_busy_queues--;
+	}
+
+	bfq_log_bfqq(bfqd, new_bfqq, "merge_bfqqs: wr_busy %d",
+		     bfqd->wr_busy_queues);
+
+	/*
+	 * Merge queues (that is, let bic redirect its requests to new_bfqq)
+	 */
+	bic_set_bfqq(bic, new_bfqq, 1);
+	bfq_mark_bfqq_coop(new_bfqq);
+	/*
+	 * new_bfqq now belongs to at least two bics (it is a shared queue):
+	 * set new_bfqq->bic to NULL. bfqq either:
+	 * - does not belong to any bic any more, and hence bfqq->bic must
+	 *   be set to NULL, or
+	 * - is a queue whose owning bics have already been redirected to a
+	 *   different queue, hence the queue is destined to not belong to
+	 *   any bic soon and bfqq->bic is already NULL (therefore the next
+	 *   assignment causes no harm).
+	 */
+	new_bfqq->bic = NULL;
+	bfqq->bic = NULL;
+	/* release process reference to bfqq */
+	bfq_put_queue(bfqq);
+}
+
+static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
+				struct bio *bio)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	bool is_sync = op_is_sync(bio->bi_opf);
+	struct bfq_queue *bfqq = bfqd->bio_bfqq, *new_bfqq;
+
+	/*
+	 * Disallow merge of a sync bio into an async request.
+	 */
+	if (is_sync && !rq_is_sync(rq))
+		return false;
+
+	/*
+	 * Lookup the bfqq that this bio will be queued with. Allow
+	 * merge only if rq is queued there.
+	 */
+	if (!bfqq)
+		return false;
+
+	/*
+	 * We take advantage of this function to perform an early merge
+	 * of the queues of possible cooperating processes.
+	 */
+	new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false);
+	if (new_bfqq) {
+		/*
+		 * bic still points to bfqq, then it has not yet been
+		 * redirected to some other bfq_queue, and a queue
+		 * merge beween bfqq and new_bfqq can be safely
+		 * fulfillled, i.e., bic can be redirected to new_bfqq
+		 * and bfqq can be put.
+		 */
+		bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq,
+				new_bfqq);
+		/*
+		 * If we get here, bio will be queued into new_queue,
+		 * so use new_bfqq to decide whether bio and rq can be
+		 * merged.
+		 */
+		bfqq = new_bfqq;
+
+		/*
+		 * Change also bqfd->bio_bfqq, as
+		 * bfqd->bio_bic now points to new_bfqq, and
+		 * this function may be invoked again (and then may
+		 * use again bqfd->bio_bfqq).
+		 */
+		bfqd->bio_bfqq = bfqq;
+	}
+
+	return bfqq == RQ_BFQQ(rq);
+}
+
+/*
+ * Set the maximum time for the in-service queue to consume its
+ * budget. This prevents seeky processes from lowering the throughput.
+ * In practice, a time-slice service scheme is used with seeky
+ * processes.
+ */
+static void bfq_set_budget_timeout(struct bfq_data *bfqd,
+				   struct bfq_queue *bfqq)
+{
+	unsigned int timeout_coeff;
+
+	if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time)
+		timeout_coeff = 1;
+	else
+		timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight;
+
+	bfqd->last_budget_start = ktime_get();
+
+	bfqq->budget_timeout = jiffies +
+		bfqd->bfq_timeout * timeout_coeff;
+}
+
+static void __bfq_set_in_service_queue(struct bfq_data *bfqd,
+				       struct bfq_queue *bfqq)
+{
+	if (bfqq) {
+		bfqg_stats_update_avg_queue_size(bfqq_group(bfqq));
+		bfq_clear_bfqq_fifo_expire(bfqq);
+
+		bfqd->budgets_assigned = (bfqd->budgets_assigned * 7 + 256) / 8;
+
+		if (time_is_before_jiffies(bfqq->last_wr_start_finish) &&
+		    bfqq->wr_coeff > 1 &&
+		    bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time &&
+		    time_is_before_jiffies(bfqq->budget_timeout)) {
+			/*
+			 * For soft real-time queues, move the start
+			 * of the weight-raising period forward by the
+			 * time the queue has not received any
+			 * service. Otherwise, a relatively long
+			 * service delay is likely to cause the
+			 * weight-raising period of the queue to end,
+			 * because of the short duration of the
+			 * weight-raising period of a soft real-time
+			 * queue.  It is worth noting that this move
+			 * is not so dangerous for the other queues,
+			 * because soft real-time queues are not
+			 * greedy.
+			 *
+			 * To not add a further variable, we use the
+			 * overloaded field budget_timeout to
+			 * determine for how long the queue has not
+			 * received service, i.e., how much time has
+			 * elapsed since the queue expired. However,
+			 * this is a little imprecise, because
+			 * budget_timeout is set to jiffies if bfqq
+			 * not only expires, but also remains with no
+			 * request.
+			 */
+			if (time_after(bfqq->budget_timeout,
+				       bfqq->last_wr_start_finish))
+				bfqq->last_wr_start_finish +=
+					jiffies - bfqq->budget_timeout;
+			else
+				bfqq->last_wr_start_finish = jiffies;
+		}
+
+		bfq_set_budget_timeout(bfqd, bfqq);
+		bfq_log_bfqq(bfqd, bfqq,
+			     "set_in_service_queue, cur-budget = %d",
+			     bfqq->entity.budget);
+	}
+
+	bfqd->in_service_queue = bfqq;
+}
+
+/*
+ * Get and set a new queue for service.
+ */
+static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq = bfq_get_next_queue(bfqd);
+
+	__bfq_set_in_service_queue(bfqd, bfqq);
+	return bfqq;
+}
+
+static void bfq_arm_slice_timer(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq = bfqd->in_service_queue;
+	u32 sl;
+
+	bfq_mark_bfqq_wait_request(bfqq);
+
+	/*
+	 * We don't want to idle for seeks, but we do want to allow
+	 * fair distribution of slice time for a process doing back-to-back
+	 * seeks. So allow a little bit of time for him to submit a new rq.
+	 */
+	sl = bfqd->bfq_slice_idle;
+	/*
+	 * Unless the queue is being weight-raised or the scenario is
+	 * asymmetric, grant only minimum idle time if the queue
+	 * is seeky. A long idling is preserved for a weight-raised
+	 * queue, or, more in general, in an asymmetric scenario,
+	 * because a long idling is needed for guaranteeing to a queue
+	 * its reserved share of the throughput (in particular, it is
+	 * needed if the queue has a higher weight than some other
+	 * queue).
+	 */
+	if (BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 &&
+	    bfq_symmetric_scenario(bfqd))
+		sl = min_t(u64, sl, BFQ_MIN_TT);
+
+	bfqd->last_idling_start = ktime_get();
+	hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl),
+		      HRTIMER_MODE_REL);
+	bfqg_stats_set_start_idle_time(bfqq_group(bfqq));
+}
+
+/*
+ * In autotuning mode, max_budget is dynamically recomputed as the
+ * amount of sectors transferred in timeout at the estimated peak
+ * rate. This enables BFQ to utilize a full timeslice with a full
+ * budget, even if the in-service queue is served at peak rate. And
+ * this maximises throughput with sequential workloads.
+ */
+static unsigned long bfq_calc_max_budget(struct bfq_data *bfqd)
+{
+	return (u64)bfqd->peak_rate * USEC_PER_MSEC *
+		jiffies_to_msecs(bfqd->bfq_timeout)>>BFQ_RATE_SHIFT;
+}
+
+/*
+ * Update parameters related to throughput and responsiveness, as a
+ * function of the estimated peak rate. See comments on
+ * bfq_calc_max_budget(), and on T_slow and T_fast arrays.
+ */
+static void update_thr_responsiveness_params(struct bfq_data *bfqd)
+{
+	int dev_type = blk_queue_nonrot(bfqd->queue);
+
+	if (bfqd->bfq_user_max_budget == 0)
+		bfqd->bfq_max_budget =
+			bfq_calc_max_budget(bfqd);
+
+	if (bfqd->device_speed == BFQ_BFQD_FAST &&
+	    bfqd->peak_rate < device_speed_thresh[dev_type]) {
+		bfqd->device_speed = BFQ_BFQD_SLOW;
+		bfqd->RT_prod = R_slow[dev_type] *
+			T_slow[dev_type];
+	} else if (bfqd->device_speed == BFQ_BFQD_SLOW &&
+		   bfqd->peak_rate > device_speed_thresh[dev_type]) {
+		bfqd->device_speed = BFQ_BFQD_FAST;
+		bfqd->RT_prod = R_fast[dev_type] *
+			T_fast[dev_type];
+	}
+
+	bfq_log(bfqd,
+"dev_type %s dev_speed_class = %s (%llu sects/sec), thresh %llu setcs/sec",
+		dev_type == 0 ? "ROT" : "NONROT",
+		bfqd->device_speed == BFQ_BFQD_FAST ? "FAST" : "SLOW",
+		bfqd->device_speed == BFQ_BFQD_FAST ?
+		(USEC_PER_SEC*(u64)R_fast[dev_type])>>BFQ_RATE_SHIFT :
+		(USEC_PER_SEC*(u64)R_slow[dev_type])>>BFQ_RATE_SHIFT,
+		(USEC_PER_SEC*(u64)device_speed_thresh[dev_type])>>
+		BFQ_RATE_SHIFT);
+}
+
+static void bfq_reset_rate_computation(struct bfq_data *bfqd,
+				       struct request *rq)
+{
+	if (rq != NULL) { /* new rq dispatch now, reset accordingly */
+		bfqd->last_dispatch = bfqd->first_dispatch = ktime_get_ns();
+		bfqd->peak_rate_samples = 1;
+		bfqd->sequential_samples = 0;
+		bfqd->tot_sectors_dispatched = bfqd->last_rq_max_size =
+			blk_rq_sectors(rq);
+	} else /* no new rq dispatched, just reset the number of samples */
+		bfqd->peak_rate_samples = 0; /* full re-init on next disp. */
+
+	bfq_log(bfqd,
+		"reset_rate_computation at end, sample %u/%u tot_sects %llu",
+		bfqd->peak_rate_samples, bfqd->sequential_samples,
+		bfqd->tot_sectors_dispatched);
+}
+
+static void bfq_update_rate_reset(struct bfq_data *bfqd, struct request *rq)
+{
+	u32 rate, weight, divisor;
+
+	/*
+	 * For the convergence property to hold (see comments on
+	 * bfq_update_peak_rate()) and for the assessment to be
+	 * reliable, a minimum number of samples must be present, and
+	 * a minimum amount of time must have elapsed. If not so, do
+	 * not compute new rate. Just reset parameters, to get ready
+	 * for a new evaluation attempt.
+	 */
+	if (bfqd->peak_rate_samples < BFQ_RATE_MIN_SAMPLES ||
+	    bfqd->delta_from_first < BFQ_RATE_MIN_INTERVAL)
+		goto reset_computation;
+
+	/*
+	 * If a new request completion has occurred after last
+	 * dispatch, then, to approximate the rate at which requests
+	 * have been served by the device, it is more precise to
+	 * extend the observation interval to the last completion.
+	 */
+	bfqd->delta_from_first =
+		max_t(u64, bfqd->delta_from_first,
+		      bfqd->last_completion - bfqd->first_dispatch);
+
+	/*
+	 * Rate computed in sects/usec, and not sects/nsec, for
+	 * precision issues.
+	 */
+	rate = div64_ul(bfqd->tot_sectors_dispatched<<BFQ_RATE_SHIFT,
+			div_u64(bfqd->delta_from_first, NSEC_PER_USEC));
+
+	/*
+	 * Peak rate not updated if:
+	 * - the percentage of sequential dispatches is below 3/4 of the
+	 *   total, and rate is below the current estimated peak rate
+	 * - rate is unreasonably high (> 20M sectors/sec)
+	 */
+	if ((bfqd->sequential_samples < (3 * bfqd->peak_rate_samples)>>2 &&
+	     rate <= bfqd->peak_rate) ||
+		rate > 20<<BFQ_RATE_SHIFT)
+		goto reset_computation;
+
+	/*
+	 * We have to update the peak rate, at last! To this purpose,
+	 * we use a low-pass filter. We compute the smoothing constant
+	 * of the filter as a function of the 'weight' of the new
+	 * measured rate.
+	 *
+	 * As can be seen in next formulas, we define this weight as a
+	 * quantity proportional to how sequential the workload is,
+	 * and to how long the observation time interval is.
+	 *
+	 * The weight runs from 0 to 8. The maximum value of the
+	 * weight, 8, yields the minimum value for the smoothing
+	 * constant. At this minimum value for the smoothing constant,
+	 * the measured rate contributes for half of the next value of
+	 * the estimated peak rate.
+	 *
+	 * So, the first step is to compute the weight as a function
+	 * of how sequential the workload is. Note that the weight
+	 * cannot reach 9, because bfqd->sequential_samples cannot
+	 * become equal to bfqd->peak_rate_samples, which, in its
+	 * turn, holds true because bfqd->sequential_samples is not
+	 * incremented for the first sample.
+	 */
+	weight = (9 * bfqd->sequential_samples) / bfqd->peak_rate_samples;
+
+	/*
+	 * Second step: further refine the weight as a function of the
+	 * duration of the observation interval.
+	 */
+	weight = min_t(u32, 8,
+		       div_u64(weight * bfqd->delta_from_first,
+			       BFQ_RATE_REF_INTERVAL));
+
+	/*
+	 * Divisor ranging from 10, for minimum weight, to 2, for
+	 * maximum weight.
+	 */
+	divisor = 10 - weight;
+
+	/*
+	 * Finally, update peak rate:
+	 *
+	 * peak_rate = peak_rate * (divisor-1) / divisor  +  rate / divisor
+	 */
+	bfqd->peak_rate *= divisor-1;
+	bfqd->peak_rate /= divisor;
+	rate /= divisor; /* smoothing constant alpha = 1/divisor */
+
+	bfqd->peak_rate += rate;
+	update_thr_responsiveness_params(bfqd);
+
+reset_computation:
+	bfq_reset_rate_computation(bfqd, rq);
+}
+
+/*
+ * Update the read/write peak rate (the main quantity used for
+ * auto-tuning, see update_thr_responsiveness_params()).
+ *
+ * It is not trivial to estimate the peak rate (correctly): because of
+ * the presence of sw and hw queues between the scheduler and the
+ * device components that finally serve I/O requests, it is hard to
+ * say exactly when a given dispatched request is served inside the
+ * device, and for how long. As a consequence, it is hard to know
+ * precisely at what rate a given set of requests is actually served
+ * by the device.
+ *
+ * On the opposite end, the dispatch time of any request is trivially
+ * available, and, from this piece of information, the "dispatch rate"
+ * of requests can be immediately computed. So, the idea in the next
+ * function is to use what is known, namely request dispatch times
+ * (plus, when useful, request completion times), to estimate what is
+ * unknown, namely in-device request service rate.
+ *
+ * The main issue is that, because of the above facts, the rate at
+ * which a certain set of requests is dispatched over a certain time
+ * interval can vary greatly with respect to the rate at which the
+ * same requests are then served. But, since the size of any
+ * intermediate queue is limited, and the service scheme is lossless
+ * (no request is silently dropped), the following obvious convergence
+ * property holds: the number of requests dispatched MUST become
+ * closer and closer to the number of requests completed as the
+ * observation interval grows. This is the key property used in
+ * the next function to estimate the peak service rate as a function
+ * of the observed dispatch rate. The function assumes to be invoked
+ * on every request dispatch.
+ */
+static void bfq_update_peak_rate(struct bfq_data *bfqd, struct request *rq)
+{
+	u64 now_ns = ktime_get_ns();
+
+	if (bfqd->peak_rate_samples == 0) { /* first dispatch */
+		bfq_log(bfqd, "update_peak_rate: goto reset, samples %d",
+			bfqd->peak_rate_samples);
+		bfq_reset_rate_computation(bfqd, rq);
+		goto update_last_values; /* will add one sample */
+	}
+
+	/*
+	 * Device idle for very long: the observation interval lasting
+	 * up to this dispatch cannot be a valid observation interval
+	 * for computing a new peak rate (similarly to the late-
+	 * completion event in bfq_completed_request()). Go to
+	 * update_rate_and_reset to have the following three steps
+	 * taken:
+	 * - close the observation interval at the last (previous)
+	 *   request dispatch or completion
+	 * - compute rate, if possible, for that observation interval
+	 * - start a new observation interval with this dispatch
+	 */
+	if (now_ns - bfqd->last_dispatch > 100*NSEC_PER_MSEC &&
+	    bfqd->rq_in_driver == 0)
+		goto update_rate_and_reset;
+
+	/* Update sampling information */
+	bfqd->peak_rate_samples++;
+
+	if ((bfqd->rq_in_driver > 0 ||
+		now_ns - bfqd->last_completion < BFQ_MIN_TT)
+	     && get_sdist(bfqd->last_position, rq) < BFQQ_SEEK_THR)
+		bfqd->sequential_samples++;
+
+	bfqd->tot_sectors_dispatched += blk_rq_sectors(rq);
+
+	/* Reset max observed rq size every 32 dispatches */
+	if (likely(bfqd->peak_rate_samples % 32))
+		bfqd->last_rq_max_size =
+			max_t(u32, blk_rq_sectors(rq), bfqd->last_rq_max_size);
+	else
+		bfqd->last_rq_max_size = blk_rq_sectors(rq);
+
+	bfqd->delta_from_first = now_ns - bfqd->first_dispatch;
+
+	/* Target observation interval not yet reached, go on sampling */
+	if (bfqd->delta_from_first < BFQ_RATE_REF_INTERVAL)
+		goto update_last_values;
+
+update_rate_and_reset:
+	bfq_update_rate_reset(bfqd, rq);
+update_last_values:
+	bfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq);
+	bfqd->last_dispatch = now_ns;
+}
+
+/*
+ * Remove request from internal lists.
+ */
+static void bfq_dispatch_remove(struct request_queue *q, struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+
+	/*
+	 * For consistency, the next instruction should have been
+	 * executed after removing the request from the queue and
+	 * dispatching it.  We execute instead this instruction before
+	 * bfq_remove_request() (and hence introduce a temporary
+	 * inconsistency), for efficiency.  In fact, should this
+	 * dispatch occur for a non in-service bfqq, this anticipated
+	 * increment prevents two counters related to bfqq->dispatched
+	 * from risking to be, first, uselessly decremented, and then
+	 * incremented again when the (new) value of bfqq->dispatched
+	 * happens to be taken into account.
+	 */
+	bfqq->dispatched++;
+	bfq_update_peak_rate(q->elevator->elevator_data, rq);
+
+	bfq_remove_request(q, rq);
+}
+
+static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	/*
+	 * If this bfqq 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 (bfq_bfqq_coop(bfqq) && BFQQ_SEEKY(bfqq))
+		bfq_mark_bfqq_split_coop(bfqq);
+
+	if (RB_EMPTY_ROOT(&bfqq->sort_list)) {
+		if (bfqq->dispatched == 0)
+			/*
+			 * Overloading budget_timeout field to store
+			 * the time at which the queue remains with no
+			 * backlog and no outstanding request; used by
+			 * the weight-raising mechanism.
+			 */
+			bfqq->budget_timeout = jiffies;
+
+		bfq_del_bfqq_busy(bfqd, bfqq, true);
+	} else {
+		bfq_requeue_bfqq(bfqd, bfqq);
+		/*
+		 * Resort priority tree of potential close cooperators.
+		 */
+		bfq_pos_tree_add_move(bfqd, bfqq);
+	}
+
+	/*
+	 * All in-service entities must have been properly deactivated
+	 * or requeued before executing the next function, which
+	 * resets all in-service entites as no more in service.
+	 */
+	__bfq_bfqd_reset_in_service(bfqd);
+}
+
+/**
+ * __bfq_bfqq_recalc_budget - try to adapt the budget to the @bfqq behavior.
+ * @bfqd: device data.
+ * @bfqq: queue to update.
+ * @reason: reason for expiration.
+ *
+ * Handle the feedback on @bfqq budget at queue expiration.
+ * See the body for detailed comments.
+ */
+static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd,
+				     struct bfq_queue *bfqq,
+				     enum bfqq_expiration reason)
+{
+	struct request *next_rq;
+	int budget, min_budget;
+
+	min_budget = bfq_min_budget(bfqd);
+
+	if (bfqq->wr_coeff == 1)
+		budget = bfqq->max_budget;
+	else /*
+	      * Use a constant, low budget for weight-raised queues,
+	      * to help achieve a low latency. Keep it slightly higher
+	      * than the minimum possible budget, to cause a little
+	      * bit fewer expirations.
+	      */
+		budget = 2 * min_budget;
+
+	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last budg %d, budg left %d",
+		bfqq->entity.budget, bfq_bfqq_budget_left(bfqq));
+	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last max_budg %d, min budg %d",
+		budget, bfq_min_budget(bfqd));
+	bfq_log_bfqq(bfqd, bfqq, "recalc_budg: sync %d, seeky %d",
+		bfq_bfqq_sync(bfqq), BFQQ_SEEKY(bfqd->in_service_queue));
+
+	if (bfq_bfqq_sync(bfqq) && bfqq->wr_coeff == 1) {
+		switch (reason) {
+		/*
+		 * Caveat: in all the following cases we trade latency
+		 * for throughput.
+		 */
+		case BFQQE_TOO_IDLE:
+			/*
+			 * This is the only case where we may reduce
+			 * the budget: if there is no request of the
+			 * process still waiting for completion, then
+			 * we assume (tentatively) that the timer has
+			 * expired because the batch of requests of
+			 * the process could have been served with a
+			 * smaller budget.  Hence, betting that
+			 * process will behave in the same way when it
+			 * becomes backlogged again, we reduce its
+			 * next budget.  As long as we guess right,
+			 * this budget cut reduces the latency
+			 * experienced by the process.
+			 *
+			 * However, if there are still outstanding
+			 * requests, then the process may have not yet
+			 * issued its next request just because it is
+			 * still waiting for the completion of some of
+			 * the still outstanding ones.  So in this
+			 * subcase we do not reduce its budget, on the
+			 * contrary we increase it to possibly boost
+			 * the throughput, as discussed in the
+			 * comments to the BUDGET_TIMEOUT case.
+			 */
+			if (bfqq->dispatched > 0) /* still outstanding reqs */
+				budget = min(budget * 2, bfqd->bfq_max_budget);
+			else {
+				if (budget > 5 * min_budget)
+					budget -= 4 * min_budget;
+				else
+					budget = min_budget;
+			}
+			break;
+		case BFQQE_BUDGET_TIMEOUT:
+			/*
+			 * We double the budget here because it gives
+			 * the chance to boost the throughput if this
+			 * is not a seeky process (and has bumped into
+			 * this timeout because of, e.g., ZBR).
+			 */
+			budget = min(budget * 2, bfqd->bfq_max_budget);
+			break;
+		case BFQQE_BUDGET_EXHAUSTED:
+			/*
+			 * The process still has backlog, and did not
+			 * let either the budget timeout or the disk
+			 * idling timeout expire. Hence it is not
+			 * seeky, has a short thinktime and may be
+			 * happy with a higher budget too. So
+			 * definitely increase the budget of this good
+			 * candidate to boost the disk throughput.
+			 */
+			budget = min(budget * 4, bfqd->bfq_max_budget);
+			break;
+		case BFQQE_NO_MORE_REQUESTS:
+			/*
+			 * For queues that expire for this reason, it
+			 * is particularly important to keep the
+			 * budget close to the actual service they
+			 * need. Doing so reduces the timestamp
+			 * misalignment problem described in the
+			 * comments in the body of
+			 * __bfq_activate_entity. In fact, suppose
+			 * that a queue systematically expires for
+			 * BFQQE_NO_MORE_REQUESTS and presents a
+			 * new request in time to enjoy timestamp
+			 * back-shifting. The larger the budget of the
+			 * queue is with respect to the service the
+			 * queue actually requests in each service
+			 * slot, the more times the queue can be
+			 * reactivated with the same virtual finish
+			 * time. It follows that, even if this finish
+			 * time is pushed to the system virtual time
+			 * to reduce the consequent timestamp
+			 * misalignment, the queue unjustly enjoys for
+			 * many re-activations a lower finish time
+			 * than all newly activated queues.
+			 *
+			 * The service needed by bfqq is measured
+			 * quite precisely by bfqq->entity.service.
+			 * Since bfqq does not enjoy device idling,
+			 * bfqq->entity.service is equal to the number
+			 * of sectors that the process associated with
+			 * bfqq requested to read/write before waiting
+			 * for request completions, or blocking for
+			 * other reasons.
+			 */
+			budget = max_t(int, bfqq->entity.service, min_budget);
+			break;
+		default:
+			return;
+		}
+	} else if (!bfq_bfqq_sync(bfqq)) {
+		/*
+		 * Async queues get always the maximum possible
+		 * budget, as for them we do not care about latency
+		 * (in addition, their ability to dispatch is limited
+		 * by the charging factor).
+		 */
+		budget = bfqd->bfq_max_budget;
+	}
+
+	bfqq->max_budget = budget;
+
+	if (bfqd->budgets_assigned >= bfq_stats_min_budgets &&
+	    !bfqd->bfq_user_max_budget)
+		bfqq->max_budget = min(bfqq->max_budget, bfqd->bfq_max_budget);
+
+	/*
+	 * If there is still backlog, then assign a new budget, making
+	 * sure that it is large enough for the next request.  Since
+	 * the finish time of bfqq must be kept in sync with the
+	 * budget, be sure to call __bfq_bfqq_expire() *after* this
+	 * update.
+	 *
+	 * If there is no backlog, then no need to update the budget;
+	 * it will be updated on the arrival of a new request.
+	 */
+	next_rq = bfqq->next_rq;
+	if (next_rq)
+		bfqq->entity.budget = max_t(unsigned long, bfqq->max_budget,
+					    bfq_serv_to_charge(next_rq, bfqq));
+
+	bfq_log_bfqq(bfqd, bfqq, "head sect: %u, new budget %d",
+			next_rq ? blk_rq_sectors(next_rq) : 0,
+			bfqq->entity.budget);
+}
+
+/*
+ * Return true if the process associated with bfqq is "slow". The slow
+ * flag is used, in addition to the budget timeout, to reduce the
+ * amount of service provided to seeky processes, and thus reduce
+ * their chances to lower the throughput. More details in the comments
+ * on the function bfq_bfqq_expire().
+ *
+ * An important observation is in order: as discussed in the comments
+ * on the function bfq_update_peak_rate(), with devices with internal
+ * queues, it is hard if ever possible to know when and for how long
+ * an I/O request is processed by the device (apart from the trivial
+ * I/O pattern where a new request is dispatched only after the
+ * previous one has been completed). This makes it hard to evaluate
+ * the real rate at which the I/O requests of each bfq_queue are
+ * served.  In fact, for an I/O scheduler like BFQ, serving a
+ * bfq_queue means just dispatching its requests during its service
+ * slot (i.e., until the budget of the queue is exhausted, or the
+ * queue remains idle, or, finally, a timeout fires). But, during the
+ * service slot of a bfq_queue, around 100 ms at most, the device may
+ * be even still processing requests of bfq_queues served in previous
+ * service slots. On the opposite end, the requests of the in-service
+ * bfq_queue may be completed after the service slot of the queue
+ * finishes.
+ *
+ * Anyway, unless more sophisticated solutions are used
+ * (where possible), the sum of the sizes of the requests dispatched
+ * during the service slot of a bfq_queue is probably the only
+ * approximation available for the service received by the bfq_queue
+ * during its service slot. And this sum is the quantity used in this
+ * function to evaluate the I/O speed of a process.
+ */
+static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+				 bool compensate, enum bfqq_expiration reason,
+				 unsigned long *delta_ms)
+{
+	ktime_t delta_ktime;
+	u32 delta_usecs;
+	bool slow = BFQQ_SEEKY(bfqq); /* if delta too short, use seekyness */
+
+	if (!bfq_bfqq_sync(bfqq))
+		return false;
+
+	if (compensate)
+		delta_ktime = bfqd->last_idling_start;
+	else
+		delta_ktime = ktime_get();
+	delta_ktime = ktime_sub(delta_ktime, bfqd->last_budget_start);
+	delta_usecs = ktime_to_us(delta_ktime);
+
+	/* don't use too short time intervals */
+	if (delta_usecs < 1000) {
+		if (blk_queue_nonrot(bfqd->queue))
+			 /*
+			  * give same worst-case guarantees as idling
+			  * for seeky
+			  */
+			*delta_ms = BFQ_MIN_TT / NSEC_PER_MSEC;
+		else /* charge at least one seek */
+			*delta_ms = bfq_slice_idle / NSEC_PER_MSEC;
+
+		return slow;
+	}
+
+	*delta_ms = delta_usecs / USEC_PER_MSEC;
+
+	/*
+	 * Use only long (> 20ms) intervals to filter out excessive
+	 * spikes in service rate estimation.
+	 */
+	if (delta_usecs > 20000) {
+		/*
+		 * Caveat for rotational devices: processes doing I/O
+		 * in the slower disk zones tend to be slow(er) even
+		 * if not seeky. In this respect, the estimated peak
+		 * rate is likely to be an average over the disk
+		 * surface. Accordingly, to not be too harsh with
+		 * unlucky processes, a process is deemed slow only if
+		 * its rate has been lower than half of the estimated
+		 * peak rate.
+		 */
+		slow = bfqq->entity.service < bfqd->bfq_max_budget / 2;
+	}
+
+	bfq_log_bfqq(bfqd, bfqq, "bfq_bfqq_is_slow: slow %d", slow);
+
+	return slow;
+}
+
+/*
+ * To be deemed as soft real-time, an application must meet two
+ * requirements. First, the application must not require an average
+ * bandwidth higher than the approximate bandwidth required to playback or
+ * record a compressed high-definition video.
+ * The next function is invoked on the completion of the last request of a
+ * batch, to compute the next-start time instant, soft_rt_next_start, such
+ * that, if the next request of the application does not arrive before
+ * soft_rt_next_start, then the above requirement on the bandwidth is met.
+ *
+ * The second requirement is that the request pattern of the application is
+ * isochronous, i.e., that, after issuing a request or a batch of requests,
+ * the application stops issuing new requests until all its pending requests
+ * have been completed. After that, the application may issue a new batch,
+ * and so on.
+ * For this reason the next function is invoked to compute
+ * soft_rt_next_start only for applications that meet this requirement,
+ * whereas soft_rt_next_start is set to infinity for applications that do
+ * not.
+ *
+ * Unfortunately, even a greedy application may happen to behave in an
+ * isochronous way if the CPU load is high. In fact, the application may
+ * stop issuing requests while the CPUs are busy serving other processes,
+ * then restart, then stop again for a while, and so on. In addition, if
+ * the disk achieves a low enough throughput with the request pattern
+ * issued by the application (e.g., because the request pattern is random
+ * and/or the device is slow), then the application may meet the above
+ * bandwidth requirement too. To prevent such a greedy application to be
+ * deemed as soft real-time, a further rule is used in the computation of
+ * soft_rt_next_start: soft_rt_next_start must be higher than the current
+ * time plus the maximum time for which the arrival of a request is waited
+ * for when a sync queue becomes idle, namely bfqd->bfq_slice_idle.
+ * This filters out greedy applications, as the latter issue instead their
+ * next request as soon as possible after the last one has been completed
+ * (in contrast, when a batch of requests is completed, a soft real-time
+ * application spends some time processing data).
+ *
+ * Unfortunately, the last filter may easily generate false positives if
+ * only bfqd->bfq_slice_idle is used as a reference time interval and one
+ * or both the following cases occur:
+ * 1) HZ is so low that the duration of a jiffy is comparable to or higher
+ *    than bfqd->bfq_slice_idle. This happens, e.g., on slow devices with
+ *    HZ=100.
+ * 2) jiffies, instead of increasing at a constant rate, may stop increasing
+ *    for a while, then suddenly 'jump' by several units to recover the lost
+ *    increments. This seems to happen, e.g., inside virtual machines.
+ * To address this issue, we do not use as a reference time interval just
+ * bfqd->bfq_slice_idle, but bfqd->bfq_slice_idle plus a few jiffies. In
+ * particular we add the minimum number of jiffies for which the filter
+ * seems to be quite precise also in embedded systems and KVM/QEMU virtual
+ * machines.
+ */
+static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd,
+						struct bfq_queue *bfqq)
+{
+	return max(bfqq->last_idle_bklogged +
+		   HZ * bfqq->service_from_backlogged /
+		   bfqd->bfq_wr_max_softrt_rate,
+		   jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4);
+}
+
+/*
+ * Return the farthest future time instant according to jiffies
+ * macros.
+ */
+static unsigned long bfq_greatest_from_now(void)
+{
+	return jiffies + MAX_JIFFY_OFFSET;
+}
+
+/*
+ * Return the farthest past time instant according to jiffies
+ * macros.
+ */
+static unsigned long bfq_smallest_from_now(void)
+{
+	return jiffies - MAX_JIFFY_OFFSET;
+}
+
+/**
+ * bfq_bfqq_expire - expire a queue.
+ * @bfqd: device owning the queue.
+ * @bfqq: the queue to expire.
+ * @compensate: if true, compensate for the time spent idling.
+ * @reason: the reason causing the expiration.
+ *
+ * If the process associated with bfqq does slow I/O (e.g., because it
+ * issues random requests), we charge bfqq with the time it has been
+ * in service instead of the service it has received (see
+ * bfq_bfqq_charge_time for details on how this goal is achieved). As
+ * a consequence, bfqq will typically get higher timestamps upon
+ * reactivation, and hence it will be rescheduled as if it had
+ * received more service than what it has actually received. In the
+ * end, bfqq receives less service in proportion to how slowly its
+ * associated process consumes its budgets (and hence how seriously it
+ * tends to lower the throughput). In addition, this time-charging
+ * strategy guarantees time fairness among slow processes. In
+ * contrast, if the process associated with bfqq is not slow, we
+ * charge bfqq exactly with the service it has received.
+ *
+ * Charging time to the first type of queues and the exact service to
+ * the other has the effect of using the WF2Q+ policy to schedule the
+ * former on a timeslice basis, without violating service domain
+ * guarantees among the latter.
+ */
+void bfq_bfqq_expire(struct bfq_data *bfqd,
+		     struct bfq_queue *bfqq,
+		     bool compensate,
+		     enum bfqq_expiration reason)
+{
+	bool slow;
+	unsigned long delta = 0;
+	struct bfq_entity *entity = &bfqq->entity;
+	int ref;
+
+	/*
+	 * Check whether the process is slow (see bfq_bfqq_is_slow).
+	 */
+	slow = bfq_bfqq_is_slow(bfqd, bfqq, compensate, reason, &delta);
+
+	/*
+	 * Increase service_from_backlogged before next statement,
+	 * because the possible next invocation of
+	 * bfq_bfqq_charge_time would likely inflate
+	 * entity->service. In contrast, service_from_backlogged must
+	 * contain real service, to enable the soft real-time
+	 * heuristic to correctly compute the bandwidth consumed by
+	 * bfqq.
+	 */
+	bfqq->service_from_backlogged += entity->service;
+
+	/*
+	 * As above explained, charge slow (typically seeky) and
+	 * timed-out queues with the time and not the service
+	 * received, to favor sequential workloads.
+	 *
+	 * Processes doing I/O in the slower disk zones will tend to
+	 * be slow(er) even if not seeky. Therefore, since the
+	 * estimated peak rate is actually an average over the disk
+	 * surface, these processes may timeout just for bad luck. To
+	 * avoid punishing them, do not charge time to processes that
+	 * succeeded in consuming at least 2/3 of their budget. This
+	 * allows BFQ to preserve enough elasticity to still perform
+	 * bandwidth, and not time, distribution with little unlucky
+	 * or quasi-sequential processes.
+	 */
+	if (bfqq->wr_coeff == 1 &&
+	    (slow ||
+	     (reason == BFQQE_BUDGET_TIMEOUT &&
+	      bfq_bfqq_budget_left(bfqq) >=  entity->budget / 3)))
+		bfq_bfqq_charge_time(bfqd, bfqq, delta);
+
+	if (reason == BFQQE_TOO_IDLE &&
+	    entity->service <= 2 * entity->budget / 10)
+		bfq_clear_bfqq_IO_bound(bfqq);
+
+	if (bfqd->low_latency && bfqq->wr_coeff == 1)
+		bfqq->last_wr_start_finish = jiffies;
+
+	if (bfqd->low_latency && bfqd->bfq_wr_max_softrt_rate > 0 &&
+	    RB_EMPTY_ROOT(&bfqq->sort_list)) {
+		/*
+		 * If we get here, and there are no outstanding
+		 * requests, then the request pattern is isochronous
+		 * (see the comments on the function
+		 * bfq_bfqq_softrt_next_start()). Thus we can compute
+		 * soft_rt_next_start. If, instead, the queue still
+		 * has outstanding requests, then we have to wait for
+		 * the completion of all the outstanding requests to
+		 * discover whether the request pattern is actually
+		 * isochronous.
+		 */
+		if (bfqq->dispatched == 0)
+			bfqq->soft_rt_next_start =
+				bfq_bfqq_softrt_next_start(bfqd, bfqq);
+		else {
+			/*
+			 * The application is still waiting for the
+			 * completion of one or more requests:
+			 * prevent it from possibly being incorrectly
+			 * deemed as soft real-time by setting its
+			 * soft_rt_next_start to infinity. In fact,
+			 * without this assignment, the application
+			 * would be incorrectly deemed as soft
+			 * real-time if:
+			 * 1) it issued a new request before the
+			 *    completion of all its in-flight
+			 *    requests, and
+			 * 2) at that time, its soft_rt_next_start
+			 *    happened to be in the past.
+			 */
+			bfqq->soft_rt_next_start =
+				bfq_greatest_from_now();
+			/*
+			 * Schedule an update of soft_rt_next_start to when
+			 * the task may be discovered to be isochronous.
+			 */
+			bfq_mark_bfqq_softrt_update(bfqq);
+		}
+	}
+
+	bfq_log_bfqq(bfqd, bfqq,
+		"expire (%d, slow %d, num_disp %d, idle_win %d)", reason,
+		slow, bfqq->dispatched, bfq_bfqq_idle_window(bfqq));
+
+	/*
+	 * Increase, decrease or leave budget unchanged according to
+	 * reason.
+	 */
+	__bfq_bfqq_recalc_budget(bfqd, bfqq, reason);
+	ref = bfqq->ref;
+	__bfq_bfqq_expire(bfqd, bfqq);
+
+	/* mark bfqq as waiting a request only if a bic still points to it */
+	if (ref > 1 && !bfq_bfqq_busy(bfqq) &&
+	    reason != BFQQE_BUDGET_TIMEOUT &&
+	    reason != BFQQE_BUDGET_EXHAUSTED)
+		bfq_mark_bfqq_non_blocking_wait_rq(bfqq);
+}
+
+/*
+ * Budget timeout is not implemented through a dedicated timer, but
+ * just checked on request arrivals and completions, as well as on
+ * idle timer expirations.
+ */
+static bool bfq_bfqq_budget_timeout(struct bfq_queue *bfqq)
+{
+	return time_is_before_eq_jiffies(bfqq->budget_timeout);
+}
+
+/*
+ * If we expire a queue that is actively waiting (i.e., with the
+ * device idled) for the arrival of a new request, then we may incur
+ * the timestamp misalignment problem described in the body of the
+ * function __bfq_activate_entity. Hence we return true only if this
+ * condition does not hold, or if the queue is slow enough to deserve
+ * only to be kicked off for preserving a high throughput.
+ */
+static bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
+{
+	bfq_log_bfqq(bfqq->bfqd, bfqq,
+		"may_budget_timeout: wait_request %d left %d timeout %d",
+		bfq_bfqq_wait_request(bfqq),
+			bfq_bfqq_budget_left(bfqq) >=  bfqq->entity.budget / 3,
+		bfq_bfqq_budget_timeout(bfqq));
+
+	return (!bfq_bfqq_wait_request(bfqq) ||
+		bfq_bfqq_budget_left(bfqq) >=  bfqq->entity.budget / 3)
+		&&
+		bfq_bfqq_budget_timeout(bfqq);
+}
+
+/*
+ * For a queue that becomes empty, device idling is allowed only if
+ * this function returns true for the queue. As a consequence, since
+ * device idling plays a critical role in both throughput boosting and
+ * service guarantees, the return value of this function plays a
+ * critical role in both these aspects as well.
+ *
+ * In a nutshell, this function returns true only if idling is
+ * beneficial for throughput or, even if detrimental for throughput,
+ * idling is however necessary to preserve service guarantees (low
+ * latency, desired throughput distribution, ...). In particular, on
+ * NCQ-capable devices, this function tries to return false, so as to
+ * help keep the drives' internal queues full, whenever this helps the
+ * device boost the throughput without causing any service-guarantee
+ * issue.
+ *
+ * In more detail, the return value of this function is obtained by,
+ * first, computing a number of boolean variables that take into
+ * account throughput and service-guarantee issues, and, then,
+ * combining these variables in a logical expression. Most of the
+ * issues taken into account are not trivial. We discuss these issues
+ * individually while introducing the variables.
+ */
+static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
+{
+	struct bfq_data *bfqd = bfqq->bfqd;
+	bool idling_boosts_thr, idling_boosts_thr_without_issues,
+		idling_needed_for_service_guarantees,
+		asymmetric_scenario;
+
+	if (bfqd->strict_guarantees)
+		return true;
+
+	/*
+	 * The next variable takes into account the cases where idling
+	 * boosts the throughput.
+	 *
+	 * The value of the variable is computed considering, first, that
+	 * idling is virtually always beneficial for the throughput if:
+	 * (a) the device is not NCQ-capable, or
+	 * (b) regardless of the presence of NCQ, the device is rotational
+	 *     and the request pattern for bfqq is I/O-bound and sequential.
+	 *
+	 * Secondly, and in contrast to the above item (b), idling an
+	 * NCQ-capable flash-based device would not boost the
+	 * throughput even with sequential I/O; rather it would lower
+	 * the throughput in proportion to how fast the device
+	 * is. Accordingly, the next variable is true if any of the
+	 * above conditions (a) and (b) is true, and, in particular,
+	 * happens to be false if bfqd is an NCQ-capable flash-based
+	 * device.
+	 */
+	idling_boosts_thr = !bfqd->hw_tag ||
+		(!blk_queue_nonrot(bfqd->queue) && bfq_bfqq_IO_bound(bfqq) &&
+		 bfq_bfqq_idle_window(bfqq));
+
+	/*
+	 * The value of the next variable,
+	 * idling_boosts_thr_without_issues, is equal to that of
+	 * idling_boosts_thr, unless a special case holds. In this
+	 * special case, described below, idling may cause problems to
+	 * weight-raised queues.
+	 *
+	 * When the request pool is saturated (e.g., in the presence
+	 * of write hogs), if the processes associated with
+	 * non-weight-raised queues ask for requests at a lower rate,
+	 * then processes associated with weight-raised queues have a
+	 * higher probability to get a request from the pool
+	 * immediately (or at least soon) when they need one. Thus
+	 * they have a higher probability to actually get a fraction
+	 * of the device throughput proportional to their high
+	 * weight. This is especially true with NCQ-capable drives,
+	 * which enqueue several requests in advance, and further
+	 * reorder internally-queued requests.
+	 *
+	 * For this reason, we force to false the value of
+	 * idling_boosts_thr_without_issues if there are weight-raised
+	 * busy queues. In this case, and if bfqq is not weight-raised,
+	 * this guarantees that the device is not idled for bfqq (if,
+	 * instead, bfqq is weight-raised, then idling will be
+	 * guaranteed by another variable, see below). Combined with
+	 * the timestamping rules of BFQ (see [1] for details), this
+	 * behavior causes bfqq, and hence any sync non-weight-raised
+	 * queue, to get a lower number of requests served, and thus
+	 * to ask for a lower number of requests from the request
+	 * pool, before the busy weight-raised queues get served
+	 * again. This often mitigates starvation problems in the
+	 * presence of heavy write workloads and NCQ, thereby
+	 * guaranteeing a higher application and system responsiveness
+	 * in these hostile scenarios.
+	 */
+	idling_boosts_thr_without_issues = idling_boosts_thr &&
+		bfqd->wr_busy_queues == 0;
+
+	/*
+	 * There is then a case where idling must be performed not
+	 * for throughput concerns, but to preserve service
+	 * guarantees.
+	 *
+	 * To introduce this case, we can note that allowing the drive
+	 * to enqueue more than one request at a time, and hence
+	 * delegating de facto final scheduling decisions to the
+	 * drive's internal scheduler, entails loss of control on the
+	 * actual request service order. In particular, the critical
+	 * situation is when requests from different processes happen
+	 * to be present, at the same time, in the internal queue(s)
+	 * of the drive. In such a situation, the drive, by deciding
+	 * the service order of the internally-queued requests, does
+	 * determine also the actual throughput distribution among
+	 * these processes. But the drive typically has no notion or
+	 * concern about per-process throughput distribution, and
+	 * makes its decisions only on a per-request basis. Therefore,
+	 * the service distribution enforced by the drive's internal
+	 * scheduler is likely to coincide with the desired
+	 * device-throughput distribution only in a completely
+	 * symmetric scenario where:
+	 * (i)  each of these processes must get the same throughput as
+	 *      the others;
+	 * (ii) all these processes have the same I/O pattern
+		(either sequential or random).
+	 * In fact, in such a scenario, the drive will tend to treat
+	 * the requests of each of these processes in about the same
+	 * way as the requests of the others, and thus to provide
+	 * each of these processes with about the same throughput
+	 * (which is exactly the desired throughput distribution). In
+	 * contrast, in any asymmetric scenario, device idling is
+	 * certainly needed to guarantee that bfqq receives its
+	 * assigned fraction of the device throughput (see [1] for
+	 * details).
+	 *
+	 * We address this issue by controlling, actually, only the
+	 * symmetry sub-condition (i), i.e., provided that
+	 * sub-condition (i) holds, idling is not performed,
+	 * regardless of whether sub-condition (ii) holds. In other
+	 * words, only if sub-condition (i) holds, then idling is
+	 * allowed, and the device tends to be prevented from queueing
+	 * many requests, possibly of several processes. The reason
+	 * for not controlling also sub-condition (ii) is that we
+	 * exploit preemption to preserve guarantees in case of
+	 * symmetric scenarios, even if (ii) does not hold, as
+	 * explained in the next two paragraphs.
+	 *
+	 * Even if a queue, say Q, is expired when it remains idle, Q
+	 * can still preempt the new in-service queue if the next
+	 * request of Q arrives soon (see the comments on
+	 * bfq_bfqq_update_budg_for_activation). If all queues and
+	 * groups have the same weight, this form of preemption,
+	 * combined with the hole-recovery heuristic described in the
+	 * comments on function bfq_bfqq_update_budg_for_activation,
+	 * are enough to preserve a correct bandwidth distribution in
+	 * the mid term, even without idling. In fact, even if not
+	 * idling allows the internal queues of the device to contain
+	 * many requests, and thus to reorder requests, we can rather
+	 * safely assume that the internal scheduler still preserves a
+	 * minimum of mid-term fairness. The motivation for using
+	 * preemption instead of idling is that, by not idling,
+	 * service guarantees are preserved without minimally
+	 * sacrificing throughput. In other words, both a high
+	 * throughput and its desired distribution are obtained.
+	 *
+	 * More precisely, this preemption-based, idleless approach
+	 * provides fairness in terms of IOPS, and not sectors per
+	 * second. This can be seen with a simple example. Suppose
+	 * that there are two queues with the same weight, but that
+	 * the first queue receives requests of 8 sectors, while the
+	 * second queue receives requests of 1024 sectors. In
+	 * addition, suppose that each of the two queues contains at
+	 * most one request at a time, which implies that each queue
+	 * always remains idle after it is served. Finally, after
+	 * remaining idle, each queue receives very quickly a new
+	 * request. It follows that the two queues are served
+	 * alternatively, preempting each other if needed. This
+	 * implies that, although both queues have the same weight,
+	 * the queue with large requests receives a service that is
+	 * 1024/8 times as high as the service received by the other
+	 * queue.
+	 *
+	 * On the other hand, device idling is performed, and thus
+	 * pure sector-domain guarantees are provided, for the
+	 * following queues, which are likely to need stronger
+	 * throughput guarantees: weight-raised queues, and queues
+	 * with a higher weight than other queues. When such queues
+	 * are active, sub-condition (i) is false, which triggers
+	 * device idling.
+	 *
+	 * According to the above considerations, the next variable is
+	 * true (only) if sub-condition (i) holds. To compute the
+	 * value of this variable, we not only use the return value of
+	 * the function bfq_symmetric_scenario(), but also check
+	 * whether bfqq is being weight-raised, because
+	 * bfq_symmetric_scenario() does not take into account also
+	 * weight-raised queues (see comments on
+	 * bfq_weights_tree_add()).
+	 *
+	 * As a side note, it is worth considering that the above
+	 * device-idling countermeasures may however fail in the
+	 * following unlucky scenario: if idling is (correctly)
+	 * disabled in a time period during which all symmetry
+	 * sub-conditions hold, and hence the device is allowed to
+	 * enqueue many requests, but at some later point in time some
+	 * sub-condition stops to hold, then it may become impossible
+	 * to let requests be served in the desired order until all
+	 * the requests already queued in the device have been served.
+	 */
+	asymmetric_scenario = bfqq->wr_coeff > 1 ||
+		!bfq_symmetric_scenario(bfqd);
+
+	/*
+	 * Finally, there is a case where maximizing throughput is the
+	 * best choice even if it may cause unfairness toward
+	 * bfqq. Such a case is when bfqq became active in a burst of
+	 * queue activations. Queues that became active during a large
+	 * burst benefit only from throughput, as discussed in the
+	 * comments on bfq_handle_burst. Thus, if bfqq became active
+	 * in a burst and not idling the device maximizes throughput,
+	 * then the device must no be idled, because not idling the
+	 * device provides bfqq and all other queues in the burst with
+	 * maximum benefit. Combining this and the above case, we can
+	 * now establish when idling is actually needed to preserve
+	 * service guarantees.
+	 */
+	idling_needed_for_service_guarantees =
+		asymmetric_scenario && !bfq_bfqq_in_large_burst(bfqq);
+
+	/*
+	 * We have now all the components we need to compute the return
+	 * value of the function, which is true only if both the following
+	 * conditions hold:
+	 * 1) bfqq is sync, because idling make sense only for sync queues;
+	 * 2) idling either boosts the throughput (without issues), or
+	 *    is necessary to preserve service guarantees.
+	 */
+	return bfq_bfqq_sync(bfqq) &&
+		(idling_boosts_thr_without_issues ||
+		 idling_needed_for_service_guarantees);
+}
+
+/*
+ * If the in-service queue is empty but the function bfq_bfqq_may_idle
+ * returns true, then:
+ * 1) the queue must remain in service and cannot be expired, and
+ * 2) the device must be idled to wait for the possible arrival of a new
+ *    request for the queue.
+ * See the comments on the function bfq_bfqq_may_idle for the reasons
+ * why performing device idling is the best choice to boost the throughput
+ * and preserve service guarantees when bfq_bfqq_may_idle itself
+ * returns true.
+ */
+static bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
+{
+	struct bfq_data *bfqd = bfqq->bfqd;
+
+	return RB_EMPTY_ROOT(&bfqq->sort_list) && bfqd->bfq_slice_idle != 0 &&
+	       bfq_bfqq_may_idle(bfqq);
+}
+
+/*
+ * Select a queue for service.  If we have a current queue in service,
+ * check whether to continue servicing it, or retrieve and set a new one.
+ */
+static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
+{
+	struct bfq_queue *bfqq;
+	struct request *next_rq;
+	enum bfqq_expiration reason = BFQQE_BUDGET_TIMEOUT;
+
+	bfqq = bfqd->in_service_queue;
+	if (!bfqq)
+		goto new_queue;
+
+	bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue");
+
+	if (bfq_may_expire_for_budg_timeout(bfqq) &&
+	    !bfq_bfqq_wait_request(bfqq) &&
+	    !bfq_bfqq_must_idle(bfqq))
+		goto expire;
+
+check_queue:
+	/*
+	 * This loop is rarely executed more than once. Even when it
+	 * happens, it is much more convenient to re-execute this loop
+	 * than to return NULL and trigger a new dispatch to get a
+	 * request served.
+	 */
+	next_rq = bfqq->next_rq;
+	/*
+	 * If bfqq has requests queued and it has enough budget left to
+	 * serve them, keep the queue, otherwise expire it.
+	 */
+	if (next_rq) {
+		if (bfq_serv_to_charge(next_rq, bfqq) >
+			bfq_bfqq_budget_left(bfqq)) {
+			/*
+			 * Expire the queue for budget exhaustion,
+			 * which makes sure that the next budget is
+			 * enough to serve the next request, even if
+			 * it comes from the fifo expired path.
+			 */
+			reason = BFQQE_BUDGET_EXHAUSTED;
+			goto expire;
+		} else {
+			/*
+			 * The idle timer may be pending because we may
+			 * not disable disk idling even when a new request
+			 * arrives.
+			 */
+			if (bfq_bfqq_wait_request(bfqq)) {
+				/*
+				 * If we get here: 1) at least a new request
+				 * has arrived but we have not disabled the
+				 * timer because the request was too small,
+				 * 2) then the block layer has unplugged
+				 * the device, causing the dispatch to be
+				 * invoked.
+				 *
+				 * Since the device is unplugged, now the
+				 * requests are probably large enough to
+				 * provide a reasonable throughput.
+				 * So we disable idling.
+				 */
+				bfq_clear_bfqq_wait_request(bfqq);
+				hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
+				bfqg_stats_update_idle_time(bfqq_group(bfqq));
+			}
+			goto keep_queue;
+		}
+	}
+
+	/*
+	 * No requests pending. However, if the in-service queue is idling
+	 * for a new request, or has requests waiting for a completion and
+	 * may idle after their completion, then keep it anyway.
+	 */
+	if (bfq_bfqq_wait_request(bfqq) ||
+	    (bfqq->dispatched != 0 && bfq_bfqq_may_idle(bfqq))) {
+		bfqq = NULL;
+		goto keep_queue;
+	}
+
+	reason = BFQQE_NO_MORE_REQUESTS;
+expire:
+	bfq_bfqq_expire(bfqd, bfqq, false, reason);
+new_queue:
+	bfqq = bfq_set_in_service_queue(bfqd);
+	if (bfqq) {
+		bfq_log_bfqq(bfqd, bfqq, "select_queue: checking new queue");
+		goto check_queue;
+	}
+keep_queue:
+	if (bfqq)
+		bfq_log_bfqq(bfqd, bfqq, "select_queue: returned this queue");
+	else
+		bfq_log(bfqd, "select_queue: no queue returned");
+
+	return bfqq;
+}
+
+static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	if (bfqq->wr_coeff > 1) { /* queue is being weight-raised */
+		bfq_log_bfqq(bfqd, bfqq,
+			"raising period dur %u/%u msec, old coeff %u, w %d(%d)",
+			jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish),
+			jiffies_to_msecs(bfqq->wr_cur_max_time),
+			bfqq->wr_coeff,
+			bfqq->entity.weight, bfqq->entity.orig_weight);
+
+		if (entity->prio_changed)
+			bfq_log_bfqq(bfqd, bfqq, "WARN: pending prio change");
+
+		/*
+		 * If the queue was activated in a burst, or too much
+		 * time has elapsed from the beginning of this
+		 * weight-raising period, then end weight raising.
+		 */
+		if (bfq_bfqq_in_large_burst(bfqq))
+			bfq_bfqq_end_wr(bfqq);
+		else if (time_is_before_jiffies(bfqq->last_wr_start_finish +
+						bfqq->wr_cur_max_time)) {
+			if (bfqq->wr_cur_max_time != bfqd->bfq_wr_rt_max_time ||
+			time_is_before_jiffies(bfqq->wr_start_at_switch_to_srt +
+					       bfq_wr_duration(bfqd)))
+				bfq_bfqq_end_wr(bfqq);
+			else {
+				/* switch back to interactive wr */
+				bfqq->wr_coeff = bfqd->bfq_wr_coeff;
+				bfqq->wr_cur_max_time = bfq_wr_duration(bfqd);
+				bfqq->last_wr_start_finish =
+					bfqq->wr_start_at_switch_to_srt;
+				bfqq->entity.prio_changed = 1;
+			}
+		}
+	}
+	/* Update weight both if it must be raised and if it must be lowered */
+	if ((entity->weight > entity->orig_weight) != (bfqq->wr_coeff > 1))
+		__bfq_entity_update_weight_prio(
+			bfq_entity_service_tree(entity),
+			entity);
+}
+
+/*
+ * Dispatch next request from bfqq.
+ */
+static struct request *bfq_dispatch_rq_from_bfqq(struct bfq_data *bfqd,
+						 struct bfq_queue *bfqq)
+{
+	struct request *rq = bfqq->next_rq;
+	unsigned long service_to_charge;
+
+	service_to_charge = bfq_serv_to_charge(rq, bfqq);
+
+	bfq_bfqq_served(bfqq, service_to_charge);
+
+	bfq_dispatch_remove(bfqd->queue, rq);
+
+	/*
+	 * If weight raising has to terminate for bfqq, then next
+	 * function causes an immediate update of bfqq's weight,
+	 * without waiting for next activation. As a consequence, on
+	 * expiration, bfqq will be timestamped as if has never been
+	 * weight-raised during this service slot, even if it has
+	 * received part or even most of the service as a
+	 * weight-raised queue. This inflates bfqq's timestamps, which
+	 * is beneficial, as bfqq is then more willing to leave the
+	 * device immediately to possible other weight-raised queues.
+	 */
+	bfq_update_wr_data(bfqd, bfqq);
+
+	/*
+	 * Expire bfqq, pretending that its budget expired, if bfqq
+	 * belongs to CLASS_IDLE and other queues are waiting for
+	 * service.
+	 */
+	if (bfqd->busy_queues > 1 && bfq_class_idle(bfqq))
+		goto expire;
+
+	return rq;
+
+expire:
+	bfq_bfqq_expire(bfqd, bfqq, false, BFQQE_BUDGET_EXHAUSTED);
+	return rq;
+}
+
+static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
+{
+	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
+
+	/*
+	 * Avoiding lock: a race on bfqd->busy_queues should cause at
+	 * most a call to dispatch for nothing
+	 */
+	return !list_empty_careful(&bfqd->dispatch) ||
+		bfqd->busy_queues > 0;
+}
+
+static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
+{
+	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
+	struct request *rq = NULL;
+	struct bfq_queue *bfqq = NULL;
+
+	if (!list_empty(&bfqd->dispatch)) {
+		rq = list_first_entry(&bfqd->dispatch, struct request,
+				      queuelist);
+		list_del_init(&rq->queuelist);
+
+		bfqq = RQ_BFQQ(rq);
+
+		if (bfqq) {
+			/*
+			 * Increment counters here, because this
+			 * dispatch does not follow the standard
+			 * dispatch flow (where counters are
+			 * incremented)
+			 */
+			bfqq->dispatched++;
+
+			goto inc_in_driver_start_rq;
+		}
+
+		/*
+		 * We exploit the put_rq_private hook to decrement
+		 * rq_in_driver, but put_rq_private will not be
+		 * invoked on this request. So, to avoid unbalance,
+		 * just start this request, without incrementing
+		 * rq_in_driver. As a negative consequence,
+		 * rq_in_driver is deceptively lower than it should be
+		 * while this request is in service. This may cause
+		 * bfq_schedule_dispatch to be invoked uselessly.
+		 *
+		 * As for implementing an exact solution, the
+		 * put_request hook, if defined, is probably invoked
+		 * also on this request. So, by exploiting this hook,
+		 * we could 1) increment rq_in_driver here, and 2)
+		 * decrement it in put_request. Such a solution would
+		 * let the value of the counter be always accurate,
+		 * but it would entail using an extra interface
+		 * function. This cost seems higher than the benefit,
+		 * being the frequency of non-elevator-private
+		 * requests very low.
+		 */
+		goto start_rq;
+	}
+
+	bfq_log(bfqd, "dispatch requests: %d busy queues", bfqd->busy_queues);
+
+	if (bfqd->busy_queues == 0)
+		goto exit;
+
+	/*
+	 * Force device to serve one request at a time if
+	 * strict_guarantees is true. Forcing this service scheme is
+	 * currently the ONLY way to guarantee that the request
+	 * service order enforced by the scheduler is respected by a
+	 * queueing device. Otherwise the device is free even to make
+	 * some unlucky request wait for as long as the device
+	 * wishes.
+	 *
+	 * Of course, serving one request at at time may cause loss of
+	 * throughput.
+	 */
+	if (bfqd->strict_guarantees && bfqd->rq_in_driver > 0)
+		goto exit;
+
+	bfqq = bfq_select_queue(bfqd);
+	if (!bfqq)
+		goto exit;
+
+	rq = bfq_dispatch_rq_from_bfqq(bfqd, bfqq);
+
+	if (rq) {
+inc_in_driver_start_rq:
+		bfqd->rq_in_driver++;
+start_rq:
+		rq->rq_flags |= RQF_STARTED;
+	}
+exit:
+	return rq;
+}
+
+static struct request *bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)
+{
+	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
+	struct request *rq;
+
+	spin_lock_irq(&bfqd->lock);
+
+	rq = __bfq_dispatch_request(hctx);
+	spin_unlock_irq(&bfqd->lock);
+
+	return rq;
+}
+
+/*
+ * Task holds one reference to the queue, dropped when task exits.  Each rq
+ * in-flight on this queue also holds a reference, dropped when rq is freed.
+ *
+ * Scheduler lock must be held here. Recall not to use bfqq after calling
+ * this function on it.
+ */
+void bfq_put_queue(struct bfq_queue *bfqq)
+{
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	struct bfq_group *bfqg = bfqq_group(bfqq);
+#endif
+
+	if (bfqq->bfqd)
+		bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d",
+			     bfqq, bfqq->ref);
+
+	bfqq->ref--;
+	if (bfqq->ref)
+		return;
+
+	if (bfq_bfqq_sync(bfqq))
+		/*
+		 * The fact that this queue is being destroyed does not
+		 * invalidate the fact that this queue may have been
+		 * activated during the current burst. As a consequence,
+		 * although the queue does not exist anymore, and hence
+		 * needs to be removed from the burst list if there,
+		 * the burst size has not to be decremented.
+		 */
+		hlist_del_init(&bfqq->burst_list_node);
+
+	kmem_cache_free(bfq_pool, bfqq);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	bfqg_put(bfqg);
+#endif
+}
+
+static void bfq_put_cooperator(struct bfq_queue *bfqq)
+{
+	struct bfq_queue *__bfqq, *next;
+
+	/*
+	 * If this queue was scheduled to merge with another queue, be
+	 * sure to drop the reference taken on that queue (and others in
+	 * the merge chain). See bfq_setup_merge and bfq_merge_bfqqs.
+	 */
+	__bfqq = bfqq->new_bfqq;
+	while (__bfqq) {
+		if (__bfqq == bfqq)
+			break;
+		next = __bfqq->new_bfqq;
+		bfq_put_queue(__bfqq);
+		__bfqq = next;
+	}
+}
+
+static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	if (bfqq == bfqd->in_service_queue) {
+		__bfq_bfqq_expire(bfqd, bfqq);
+		bfq_schedule_dispatch(bfqd);
+	}
+
+	bfq_log_bfqq(bfqd, bfqq, "exit_bfqq: %p, %d", bfqq, bfqq->ref);
+
+	bfq_put_cooperator(bfqq);
+
+	bfq_put_queue(bfqq); /* release process reference */
+}
+
+static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync)
+{
+	struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync);
+	struct bfq_data *bfqd;
+
+	if (bfqq)
+		bfqd = bfqq->bfqd; /* NULL if scheduler already exited */
+
+	if (bfqq && bfqd) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&bfqd->lock, flags);
+		bfq_exit_bfqq(bfqd, bfqq);
+		bic_set_bfqq(bic, NULL, is_sync);
+		spin_unlock_irqrestore(&bfqd->lock, flags);
+	}
+}
+
+static void bfq_exit_icq(struct io_cq *icq)
+{
+	struct bfq_io_cq *bic = icq_to_bic(icq);
+
+	bfq_exit_icq_bfqq(bic, true);
+	bfq_exit_icq_bfqq(bic, false);
+}
+
+/*
+ * Update the entity prio values; note that the new values will not
+ * be used until the next (re)activation.
+ */
+static void
+bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
+{
+	struct task_struct *tsk = current;
+	int ioprio_class;
+	struct bfq_data *bfqd = bfqq->bfqd;
+
+	if (!bfqd)
+		return;
+
+	ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
+	switch (ioprio_class) {
+	default:
+		dev_err(bfqq->bfqd->queue->backing_dev_info->dev,
+			"bfq: bad prio class %d\n", ioprio_class);
+	case IOPRIO_CLASS_NONE:
+		/*
+		 * No prio set, inherit CPU scheduling settings.
+		 */
+		bfqq->new_ioprio = task_nice_ioprio(tsk);
+		bfqq->new_ioprio_class = task_nice_ioclass(tsk);
+		break;
+	case IOPRIO_CLASS_RT:
+		bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
+		bfqq->new_ioprio_class = IOPRIO_CLASS_RT;
+		break;
+	case IOPRIO_CLASS_BE:
+		bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
+		bfqq->new_ioprio_class = IOPRIO_CLASS_BE;
+		break;
+	case IOPRIO_CLASS_IDLE:
+		bfqq->new_ioprio_class = IOPRIO_CLASS_IDLE;
+		bfqq->new_ioprio = 7;
+		bfq_clear_bfqq_idle_window(bfqq);
+		break;
+	}
+
+	if (bfqq->new_ioprio >= IOPRIO_BE_NR) {
+		pr_crit("bfq_set_next_ioprio_data: new_ioprio %d\n",
+			bfqq->new_ioprio);
+		bfqq->new_ioprio = IOPRIO_BE_NR;
+	}
+
+	bfqq->entity.new_weight = bfq_ioprio_to_weight(bfqq->new_ioprio);
+	bfqq->entity.prio_changed = 1;
+}
+
+static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
+				       struct bio *bio, bool is_sync,
+				       struct bfq_io_cq *bic);
+
+static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio)
+{
+	struct bfq_data *bfqd = bic_to_bfqd(bic);
+	struct bfq_queue *bfqq;
+	int ioprio = bic->icq.ioc->ioprio;
+
+	/*
+	 * This condition may trigger on a newly created bic, be sure to
+	 * drop the lock before returning.
+	 */
+	if (unlikely(!bfqd) || likely(bic->ioprio == ioprio))
+		return;
+
+	bic->ioprio = ioprio;
+
+	bfqq = bic_to_bfqq(bic, false);
+	if (bfqq) {
+		/* release process reference on this queue */
+		bfq_put_queue(bfqq);
+		bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic);
+		bic_set_bfqq(bic, bfqq, false);
+	}
+
+	bfqq = bic_to_bfqq(bic, true);
+	if (bfqq)
+		bfq_set_next_ioprio_data(bfqq, bic);
+}
+
+static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			  struct bfq_io_cq *bic, pid_t pid, int is_sync)
+{
+	RB_CLEAR_NODE(&bfqq->entity.rb_node);
+	INIT_LIST_HEAD(&bfqq->fifo);
+	INIT_HLIST_NODE(&bfqq->burst_list_node);
+
+	bfqq->ref = 0;
+	bfqq->bfqd = bfqd;
+
+	if (bic)
+		bfq_set_next_ioprio_data(bfqq, bic);
+
+	if (is_sync) {
+		if (!bfq_class_idle(bfqq))
+			bfq_mark_bfqq_idle_window(bfqq);
+		bfq_mark_bfqq_sync(bfqq);
+		bfq_mark_bfqq_just_created(bfqq);
+	} else
+		bfq_clear_bfqq_sync(bfqq);
+
+	/* set end request to minus infinity from now */
+	bfqq->ttime.last_end_request = ktime_get_ns() + 1;
+
+	bfq_mark_bfqq_IO_bound(bfqq);
+
+	bfqq->pid = pid;
+
+	/* Tentative initial value to trade off between thr and lat */
+	bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3;
+	bfqq->budget_timeout = bfq_smallest_from_now();
+
+	bfqq->wr_coeff = 1;
+	bfqq->last_wr_start_finish = jiffies;
+	bfqq->wr_start_at_switch_to_srt = bfq_smallest_from_now();
+	bfqq->split_time = bfq_smallest_from_now();
+
+	/*
+	 * Set to the value for which bfqq will not be deemed as
+	 * soft rt when it becomes backlogged.
+	 */
+	bfqq->soft_rt_next_start = bfq_greatest_from_now();
+
+	/* first request is almost certainly seeky */
+	bfqq->seek_history = 1;
+}
+
+static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd,
+					       struct bfq_group *bfqg,
+					       int ioprio_class, int ioprio)
+{
+	switch (ioprio_class) {
+	case IOPRIO_CLASS_RT:
+		return &bfqg->async_bfqq[0][ioprio];
+	case IOPRIO_CLASS_NONE:
+		ioprio = IOPRIO_NORM;
+		/* fall through */
+	case IOPRIO_CLASS_BE:
+		return &bfqg->async_bfqq[1][ioprio];
+	case IOPRIO_CLASS_IDLE:
+		return &bfqg->async_idle_bfqq;
+	default:
+		return NULL;
+	}
+}
+
+static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd,
+				       struct bio *bio, bool is_sync,
+				       struct bfq_io_cq *bic)
+{
+	const int ioprio = IOPRIO_PRIO_DATA(bic->ioprio);
+	const int ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio);
+	struct bfq_queue **async_bfqq = NULL;
+	struct bfq_queue *bfqq;
+	struct bfq_group *bfqg;
+
+	rcu_read_lock();
+
+	bfqg = bfq_find_set_group(bfqd, bio_blkcg(bio));
+	if (!bfqg) {
+		bfqq = &bfqd->oom_bfqq;
+		goto out;
+	}
+
+	if (!is_sync) {
+		async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class,
+						  ioprio);
+		bfqq = *async_bfqq;
+		if (bfqq)
+			goto out;
+	}
+
+	bfqq = kmem_cache_alloc_node(bfq_pool,
+				     GFP_NOWAIT | __GFP_ZERO | __GFP_NOWARN,
+				     bfqd->queue->node);
+
+	if (bfqq) {
+		bfq_init_bfqq(bfqd, bfqq, bic, current->pid,
+			      is_sync);
+		bfq_init_entity(&bfqq->entity, bfqg);
+		bfq_log_bfqq(bfqd, bfqq, "allocated");
+	} else {
+		bfqq = &bfqd->oom_bfqq;
+		bfq_log_bfqq(bfqd, bfqq, "using oom bfqq");
+		goto out;
+	}
+
+	/*
+	 * Pin the queue now that it's allocated, scheduler exit will
+	 * prune it.
+	 */
+	if (async_bfqq) {
+		bfqq->ref++; /*
+			      * Extra group reference, w.r.t. sync
+			      * queue. This extra reference is removed
+			      * only if bfqq->bfqg disappears, to
+			      * guarantee that this queue is not freed
+			      * until its group goes away.
+			      */
+		bfq_log_bfqq(bfqd, bfqq, "get_queue, bfqq not in async: %p, %d",
+			     bfqq, bfqq->ref);
+		*async_bfqq = bfqq;
+	}
+
+out:
+	bfqq->ref++; /* get a process reference to this queue */
+	bfq_log_bfqq(bfqd, bfqq, "get_queue, at end: %p, %d", bfqq, bfqq->ref);
+	rcu_read_unlock();
+	return bfqq;
+}
+
+static void bfq_update_io_thinktime(struct bfq_data *bfqd,
+				    struct bfq_queue *bfqq)
+{
+	struct bfq_ttime *ttime = &bfqq->ttime;
+	u64 elapsed = ktime_get_ns() - bfqq->ttime.last_end_request;
+
+	elapsed = min_t(u64, elapsed, 2ULL * bfqd->bfq_slice_idle);
+
+	ttime->ttime_samples = (7*bfqq->ttime.ttime_samples + 256) / 8;
+	ttime->ttime_total = div_u64(7*ttime->ttime_total + 256*elapsed,  8);
+	ttime->ttime_mean = div64_ul(ttime->ttime_total + 128,
+				     ttime->ttime_samples);
+}
+
+static void
+bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		       struct request *rq)
+{
+	bfqq->seek_history <<= 1;
+	bfqq->seek_history |=
+		get_sdist(bfqq->last_request_pos, rq) > BFQQ_SEEK_THR &&
+		(!blk_queue_nonrot(bfqd->queue) ||
+		 blk_rq_sectors(rq) < BFQQ_SECT_THR_NONROT);
+}
+
+/*
+ * Disable idle window if the process thinks too long or seeks so much that
+ * it doesn't matter.
+ */
+static void bfq_update_idle_window(struct bfq_data *bfqd,
+				   struct bfq_queue *bfqq,
+				   struct bfq_io_cq *bic)
+{
+	int enable_idle;
+
+	/* Don't idle for async or idle io prio class. */
+	if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq))
+		return;
+
+	/* Idle window just restored, statistics are meaningless. */
+	if (time_is_after_eq_jiffies(bfqq->split_time +
+				     bfqd->bfq_wr_min_idle_time))
+		return;
+
+	enable_idle = bfq_bfqq_idle_window(bfqq);
+
+	if (atomic_read(&bic->icq.ioc->active_ref) == 0 ||
+	    bfqd->bfq_slice_idle == 0 ||
+		(bfqd->hw_tag && BFQQ_SEEKY(bfqq) &&
+			bfqq->wr_coeff == 1))
+		enable_idle = 0;
+	else if (bfq_sample_valid(bfqq->ttime.ttime_samples)) {
+		if (bfqq->ttime.ttime_mean > bfqd->bfq_slice_idle &&
+			bfqq->wr_coeff == 1)
+			enable_idle = 0;
+		else
+			enable_idle = 1;
+	}
+	bfq_log_bfqq(bfqd, bfqq, "update_idle_window: enable_idle %d",
+		enable_idle);
+
+	if (enable_idle)
+		bfq_mark_bfqq_idle_window(bfqq);
+	else
+		bfq_clear_bfqq_idle_window(bfqq);
+}
+
+/*
+ * Called when a new fs request (rq) is added to bfqq.  Check if there's
+ * something we should do about it.
+ */
+static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			    struct request *rq)
+{
+	struct bfq_io_cq *bic = RQ_BIC(rq);
+
+	if (rq->cmd_flags & REQ_META)
+		bfqq->meta_pending++;
+
+	bfq_update_io_thinktime(bfqd, bfqq);
+	bfq_update_io_seektime(bfqd, bfqq, rq);
+	if (bfqq->entity.service > bfq_max_budget(bfqd) / 8 ||
+	    !BFQQ_SEEKY(bfqq))
+		bfq_update_idle_window(bfqd, bfqq, bic);
+
+	bfq_log_bfqq(bfqd, bfqq,
+		     "rq_enqueued: idle_window=%d (seeky %d)",
+		     bfq_bfqq_idle_window(bfqq), BFQQ_SEEKY(bfqq));
+
+	bfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
+
+	if (bfqq == bfqd->in_service_queue && bfq_bfqq_wait_request(bfqq)) {
+		bool small_req = bfqq->queued[rq_is_sync(rq)] == 1 &&
+				 blk_rq_sectors(rq) < 32;
+		bool budget_timeout = bfq_bfqq_budget_timeout(bfqq);
+
+		/*
+		 * There is just this request queued: if the request
+		 * is small and the queue is not to be expired, then
+		 * just exit.
+		 *
+		 * In this way, if the device is being idled to wait
+		 * for a new request from the in-service queue, we
+		 * avoid unplugging the device and committing the
+		 * device to serve just a small request. On the
+		 * contrary, we wait for the block layer to decide
+		 * when to unplug the device: hopefully, new requests
+		 * will be merged to this one quickly, then the device
+		 * will be unplugged and larger requests will be
+		 * dispatched.
+		 */
+		if (small_req && !budget_timeout)
+			return;
+
+		/*
+		 * A large enough request arrived, or the queue is to
+		 * be expired: in both cases disk idling is to be
+		 * stopped, so clear wait_request flag and reset
+		 * timer.
+		 */
+		bfq_clear_bfqq_wait_request(bfqq);
+		hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
+		bfqg_stats_update_idle_time(bfqq_group(bfqq));
+
+		/*
+		 * The queue is not empty, because a new request just
+		 * arrived. Hence we can safely expire the queue, in
+		 * case of budget timeout, without risking that the
+		 * timestamps of the queue are not updated correctly.
+		 * See [1] for more details.
+		 */
+		if (budget_timeout)
+			bfq_bfqq_expire(bfqd, bfqq, false,
+					BFQQE_BUDGET_TIMEOUT);
+	}
+}
+
+static void __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq),
+		*new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true);
+
+	if (new_bfqq) {
+		if (bic_to_bfqq(RQ_BIC(rq), 1) != bfqq)
+			new_bfqq = bic_to_bfqq(RQ_BIC(rq), 1);
+		/*
+		 * Release the request's reference to the old bfqq
+		 * and make sure one is taken to the shared queue.
+		 */
+		new_bfqq->allocated++;
+		bfqq->allocated--;
+		new_bfqq->ref++;
+		bfq_clear_bfqq_just_created(bfqq);
+		/*
+		 * If the bic associated with the process
+		 * issuing this request still points to bfqq
+		 * (and thus has not been already redirected
+		 * to new_bfqq or even some other bfq_queue),
+		 * then complete the merge and redirect it to
+		 * new_bfqq.
+		 */
+		if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq)
+			bfq_merge_bfqqs(bfqd, RQ_BIC(rq),
+					bfqq, new_bfqq);
+		/*
+		 * rq is about to be enqueued into new_bfqq,
+		 * release rq reference on bfqq
+		 */
+		bfq_put_queue(bfqq);
+		rq->elv.priv[1] = new_bfqq;
+		bfqq = new_bfqq;
+	}
+
+	bfq_add_request(rq);
+
+	rq->fifo_time = ktime_get_ns() + bfqd->bfq_fifo_expire[rq_is_sync(rq)];
+	list_add_tail(&rq->queuelist, &bfqq->fifo);
+
+	bfq_rq_enqueued(bfqd, bfqq, rq);
+}
+
+static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
+			       bool at_head)
+{
+	struct request_queue *q = hctx->queue;
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+
+	spin_lock_irq(&bfqd->lock);
+	if (blk_mq_sched_try_insert_merge(q, rq)) {
+		spin_unlock_irq(&bfqd->lock);
+		return;
+	}
+
+	spin_unlock_irq(&bfqd->lock);
+
+	blk_mq_sched_request_inserted(rq);
+
+	spin_lock_irq(&bfqd->lock);
+	if (at_head || blk_rq_is_passthrough(rq)) {
+		if (at_head)
+			list_add(&rq->queuelist, &bfqd->dispatch);
+		else
+			list_add_tail(&rq->queuelist, &bfqd->dispatch);
+	} else {
+		__bfq_insert_request(bfqd, rq);
+
+		if (rq_mergeable(rq)) {
+			elv_rqhash_add(q, rq);
+			if (!q->last_merge)
+				q->last_merge = rq;
+		}
+	}
+
+	spin_unlock_irq(&bfqd->lock);
+}
+
+static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
+				struct list_head *list, bool at_head)
+{
+	while (!list_empty(list)) {
+		struct request *rq;
+
+		rq = list_first_entry(list, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		bfq_insert_request(hctx, rq, at_head);
+	}
+}
+
+static void bfq_update_hw_tag(struct bfq_data *bfqd)
+{
+	bfqd->max_rq_in_driver = max_t(int, bfqd->max_rq_in_driver,
+				       bfqd->rq_in_driver);
+
+	if (bfqd->hw_tag == 1)
+		return;
+
+	/*
+	 * This sample is valid if the number of outstanding requests
+	 * is large enough to allow a queueing behavior.  Note that the
+	 * sum is not exact, as it's not taking into account deactivated
+	 * requests.
+	 */
+	if (bfqd->rq_in_driver + bfqd->queued < BFQ_HW_QUEUE_THRESHOLD)
+		return;
+
+	if (bfqd->hw_tag_samples++ < BFQ_HW_QUEUE_SAMPLES)
+		return;
+
+	bfqd->hw_tag = bfqd->max_rq_in_driver > BFQ_HW_QUEUE_THRESHOLD;
+	bfqd->max_rq_in_driver = 0;
+	bfqd->hw_tag_samples = 0;
+}
+
+static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
+{
+	u64 now_ns;
+	u32 delta_us;
+
+	bfq_update_hw_tag(bfqd);
+
+	bfqd->rq_in_driver--;
+	bfqq->dispatched--;
+
+	if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) {
+		/*
+		 * Set budget_timeout (which we overload to store the
+		 * time at which the queue remains with no backlog and
+		 * no outstanding request; used by the weight-raising
+		 * mechanism).
+		 */
+		bfqq->budget_timeout = jiffies;
+
+		bfq_weights_tree_remove(bfqd, &bfqq->entity,
+					&bfqd->queue_weights_tree);
+	}
+
+	now_ns = ktime_get_ns();
+
+	bfqq->ttime.last_end_request = now_ns;
+
+	/*
+	 * Using us instead of ns, to get a reasonable precision in
+	 * computing rate in next check.
+	 */
+	delta_us = div_u64(now_ns - bfqd->last_completion, NSEC_PER_USEC);
+
+	/*
+	 * If the request took rather long to complete, and, according
+	 * to the maximum request size recorded, this completion latency
+	 * implies that the request was certainly served at a very low
+	 * rate (less than 1M sectors/sec), then the whole observation
+	 * interval that lasts up to this time instant cannot be a
+	 * valid time interval for computing a new peak rate.  Invoke
+	 * bfq_update_rate_reset to have the following three steps
+	 * taken:
+	 * - close the observation interval at the last (previous)
+	 *   request dispatch or completion
+	 * - compute rate, if possible, for that observation interval
+	 * - reset to zero samples, which will trigger a proper
+	 *   re-initialization of the observation interval on next
+	 *   dispatch
+	 */
+	if (delta_us > BFQ_MIN_TT/NSEC_PER_USEC &&
+	   (bfqd->last_rq_max_size<<BFQ_RATE_SHIFT)/delta_us <
+			1UL<<(BFQ_RATE_SHIFT - 10))
+		bfq_update_rate_reset(bfqd, NULL);
+	bfqd->last_completion = now_ns;
+
+	/*
+	 * If we are waiting to discover whether the request pattern
+	 * of the task associated with the queue is actually
+	 * isochronous, and both requisites for this condition to hold
+	 * are now satisfied, then compute soft_rt_next_start (see the
+	 * comments on the function bfq_bfqq_softrt_next_start()). We
+	 * schedule this delayed check when bfqq expires, if it still
+	 * has in-flight requests.
+	 */
+	if (bfq_bfqq_softrt_update(bfqq) && bfqq->dispatched == 0 &&
+	    RB_EMPTY_ROOT(&bfqq->sort_list))
+		bfqq->soft_rt_next_start =
+			bfq_bfqq_softrt_next_start(bfqd, bfqq);
+
+	/*
+	 * If this is the in-service queue, check if it needs to be expired,
+	 * or if we want to idle in case it has no pending requests.
+	 */
+	if (bfqd->in_service_queue == bfqq) {
+		if (bfqq->dispatched == 0 && bfq_bfqq_must_idle(bfqq)) {
+			bfq_arm_slice_timer(bfqd);
+			return;
+		} else if (bfq_may_expire_for_budg_timeout(bfqq))
+			bfq_bfqq_expire(bfqd, bfqq, false,
+					BFQQE_BUDGET_TIMEOUT);
+		else if (RB_EMPTY_ROOT(&bfqq->sort_list) &&
+			 (bfqq->dispatched == 0 ||
+			  !bfq_bfqq_may_idle(bfqq)))
+			bfq_bfqq_expire(bfqd, bfqq, false,
+					BFQQE_NO_MORE_REQUESTS);
+	}
+}
+
+static void bfq_put_rq_priv_body(struct bfq_queue *bfqq)
+{
+	bfqq->allocated--;
+
+	bfq_put_queue(bfqq);
+}
+
+static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
+{
+	struct bfq_queue *bfqq = RQ_BFQQ(rq);
+	struct bfq_data *bfqd = bfqq->bfqd;
+
+	if (rq->rq_flags & RQF_STARTED)
+		bfqg_stats_update_completion(bfqq_group(bfqq),
+					     rq_start_time_ns(rq),
+					     rq_io_start_time_ns(rq),
+					     rq->cmd_flags);
+
+	if (likely(rq->rq_flags & RQF_STARTED)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&bfqd->lock, flags);
+
+		bfq_completed_request(bfqq, bfqd);
+		bfq_put_rq_priv_body(bfqq);
+
+		spin_unlock_irqrestore(&bfqd->lock, flags);
+	} else {
+		/*
+		 * Request rq may be still/already in the scheduler,
+		 * in which case we need to remove it. And we cannot
+		 * defer such a check and removal, to avoid
+		 * inconsistencies in the time interval from the end
+		 * of this function to the start of the deferred work.
+		 * This situation seems to occur only in process
+		 * context, as a consequence of a merge. In the
+		 * current version of the code, this implies that the
+		 * lock is held.
+		 */
+
+		if (!RB_EMPTY_NODE(&rq->rb_node))
+			bfq_remove_request(q, rq);
+		bfq_put_rq_priv_body(bfqq);
+	}
+
+	rq->elv.priv[0] = NULL;
+	rq->elv.priv[1] = NULL;
+}
+
+/*
+ * Returns NULL if a new bfqq should be allocated, or the old bfqq if this
+ * was the last process referring to that bfqq.
+ */
+static struct bfq_queue *
+bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
+{
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue");
+
+	if (bfqq_process_refs(bfqq) == 1) {
+		bfqq->pid = current->pid;
+		bfq_clear_bfqq_coop(bfqq);
+		bfq_clear_bfqq_split_coop(bfqq);
+		return bfqq;
+	}
+
+	bic_set_bfqq(bic, NULL, 1);
+
+	bfq_put_cooperator(bfqq);
+
+	bfq_put_queue(bfqq);
+	return NULL;
+}
+
+static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
+						   struct bfq_io_cq *bic,
+						   struct bio *bio,
+						   bool split, bool is_sync,
+						   bool *new_queue)
+{
+	struct bfq_queue *bfqq = bic_to_bfqq(bic, is_sync);
+
+	if (likely(bfqq && bfqq != &bfqd->oom_bfqq))
+		return bfqq;
+
+	if (new_queue)
+		*new_queue = true;
+
+	if (bfqq)
+		bfq_put_queue(bfqq);
+	bfqq = bfq_get_queue(bfqd, bio, is_sync, bic);
+
+	bic_set_bfqq(bic, bfqq, is_sync);
+	if (split && is_sync) {
+		if ((bic->was_in_burst_list && bfqd->large_burst) ||
+		    bic->saved_in_large_burst)
+			bfq_mark_bfqq_in_large_burst(bfqq);
+		else {
+			bfq_clear_bfqq_in_large_burst(bfqq);
+			if (bic->was_in_burst_list)
+				hlist_add_head(&bfqq->burst_list_node,
+					       &bfqd->burst_list);
+		}
+		bfqq->split_time = jiffies;
+	}
+
+	return bfqq;
+}
+
+/*
+ * Allocate bfq data structures associated with this request.
+ */
+static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
+			      struct bio *bio)
+{
+	struct bfq_data *bfqd = q->elevator->elevator_data;
+	struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq);
+	const int is_sync = rq_is_sync(rq);
+	struct bfq_queue *bfqq;
+	bool new_queue = false;
+	bool split = false;
+
+	spin_lock_irq(&bfqd->lock);
+
+	if (!bic)
+		goto queue_fail;
+
+	bfq_check_ioprio_change(bic, bio);
+
+	bfq_bic_update_cgroup(bic, bio);
+
+	bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio, false, is_sync,
+					 &new_queue);
+
+	if (likely(!new_queue)) {
+		/* If the queue was seeky for too long, break it apart. */
+		if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) {
+			bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq");
+
+			/* Update bic before losing reference to bfqq */
+			if (bfq_bfqq_in_large_burst(bfqq))
+				bic->saved_in_large_burst = true;
+
+			bfqq = bfq_split_bfqq(bic, bfqq);
+			split = true;
+
+			if (!bfqq)
+				bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio,
+								 true, is_sync,
+								 NULL);
+		}
+	}
+
+	bfqq->allocated++;
+	bfqq->ref++;
+	bfq_log_bfqq(bfqd, bfqq, "get_request %p: bfqq %p, %d",
+		     rq, bfqq, bfqq->ref);
+
+	rq->elv.priv[0] = bic;
+	rq->elv.priv[1] = bfqq;
+
+	/*
+	 * If a bfq_queue has only one process reference, it is owned
+	 * by only this bic: we can then set bfqq->bic = bic. in
+	 * addition, if the queue has also just been split, we have to
+	 * resume its state.
+	 */
+	if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) {
+		bfqq->bic = bic;
+		if (split) {
+			/*
+			 * The queue has just been split from a shared
+			 * queue: restore the idle window and the
+			 * possible weight raising period.
+			 */
+			bfq_bfqq_resume_state(bfqq, bic);
+		}
+	}
+
+	if (unlikely(bfq_bfqq_just_created(bfqq)))
+		bfq_handle_burst(bfqd, bfqq);
+
+	spin_unlock_irq(&bfqd->lock);
+
+	return 0;
+
+queue_fail:
+	spin_unlock_irq(&bfqd->lock);
+
+	return 1;
+}
+
+static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
+{
+	struct bfq_data *bfqd = bfqq->bfqd;
+	enum bfqq_expiration reason;
+	unsigned long flags;
+
+	spin_lock_irqsave(&bfqd->lock, flags);
+	bfq_clear_bfqq_wait_request(bfqq);
+
+	if (bfqq != bfqd->in_service_queue) {
+		spin_unlock_irqrestore(&bfqd->lock, flags);
+		return;
+	}
+
+	if (bfq_bfqq_budget_timeout(bfqq))
+		/*
+		 * Also here the queue can be safely expired
+		 * for budget timeout without wasting
+		 * guarantees
+		 */
+		reason = BFQQE_BUDGET_TIMEOUT;
+	else if (bfqq->queued[0] == 0 && bfqq->queued[1] == 0)
+		/*
+		 * The queue may not be empty upon timer expiration,
+		 * because we may not disable the timer when the
+		 * first request of the in-service queue arrives
+		 * during disk idling.
+		 */
+		reason = BFQQE_TOO_IDLE;
+	else
+		goto schedule_dispatch;
+
+	bfq_bfqq_expire(bfqd, bfqq, true, reason);
+
+schedule_dispatch:
+	spin_unlock_irqrestore(&bfqd->lock, flags);
+	bfq_schedule_dispatch(bfqd);
+}
+
+/*
+ * Handler of the expiration of the timer running if the in-service queue
+ * is idling inside its time slice.
+ */
+static enum hrtimer_restart bfq_idle_slice_timer(struct hrtimer *timer)
+{
+	struct bfq_data *bfqd = container_of(timer, struct bfq_data,
+					     idle_slice_timer);
+	struct bfq_queue *bfqq = bfqd->in_service_queue;
+
+	/*
+	 * Theoretical race here: the in-service queue can be NULL or
+	 * different from the queue that was idling if a new request
+	 * arrives for the current queue and there is a full dispatch
+	 * cycle that changes the in-service queue.  This can hardly
+	 * happen, but in the worst case we just expire a queue too
+	 * early.
+	 */
+	if (bfqq)
+		bfq_idle_slice_timer_body(bfqq);
+
+	return HRTIMER_NORESTART;
+}
+
+static void __bfq_put_async_bfqq(struct bfq_data *bfqd,
+				 struct bfq_queue **bfqq_ptr)
+{
+	struct bfq_queue *bfqq = *bfqq_ptr;
+
+	bfq_log(bfqd, "put_async_bfqq: %p", bfqq);
+	if (bfqq) {
+		bfq_bfqq_move(bfqd, bfqq, bfqd->root_group);
+
+		bfq_log_bfqq(bfqd, bfqq, "put_async_bfqq: putting %p, %d",
+			     bfqq, bfqq->ref);
+		bfq_put_queue(bfqq);
+		*bfqq_ptr = NULL;
+	}
+}
+
+/*
+ * Release all the bfqg references to its async queues.  If we are
+ * deallocating the group these queues may still contain requests, so
+ * we reparent them to the root cgroup (i.e., the only one that will
+ * exist for sure until all the requests on a device are gone).
+ */
+void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
+{
+	int i, j;
+
+	for (i = 0; i < 2; i++)
+		for (j = 0; j < IOPRIO_BE_NR; j++)
+			__bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j]);
+
+	__bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq);
+}
+
+static void bfq_exit_queue(struct elevator_queue *e)
+{
+	struct bfq_data *bfqd = e->elevator_data;
+	struct bfq_queue *bfqq, *n;
+
+	hrtimer_cancel(&bfqd->idle_slice_timer);
+
+	spin_lock_irq(&bfqd->lock);
+	list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list)
+		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
+	spin_unlock_irq(&bfqd->lock);
+
+	hrtimer_cancel(&bfqd->idle_slice_timer);
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	blkcg_deactivate_policy(bfqd->queue, &blkcg_policy_bfq);
+#else
+	spin_lock_irq(&bfqd->lock);
+	bfq_put_async_queues(bfqd, bfqd->root_group);
+	kfree(bfqd->root_group);
+	spin_unlock_irq(&bfqd->lock);
+#endif
+
+	kfree(bfqd);
+}
+
+static void bfq_init_root_group(struct bfq_group *root_group,
+				struct bfq_data *bfqd)
+{
+	int i;
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	root_group->entity.parent = NULL;
+	root_group->my_entity = NULL;
+	root_group->bfqd = bfqd;
+#endif
+	root_group->rq_pos_tree = RB_ROOT;
+	for (i = 0; i < BFQ_IOPRIO_CLASSES; i++)
+		root_group->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT;
+	root_group->sched_data.bfq_class_idle_last_service = jiffies;
+}
+
+static int bfq_init_queue(struct request_queue *q, struct elevator_type *e)
+{
+	struct bfq_data *bfqd;
+	struct elevator_queue *eq;
+
+	eq = elevator_alloc(q, e);
+	if (!eq)
+		return -ENOMEM;
+
+	bfqd = kzalloc_node(sizeof(*bfqd), GFP_KERNEL, q->node);
+	if (!bfqd) {
+		kobject_put(&eq->kobj);
+		return -ENOMEM;
+	}
+	eq->elevator_data = bfqd;
+
+	spin_lock_irq(q->queue_lock);
+	q->elevator = eq;
+	spin_unlock_irq(q->queue_lock);
+
+	/*
+	 * Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues.
+	 * Grab a permanent reference to it, so that the normal code flow
+	 * will not attempt to free it.
+	 */
+	bfq_init_bfqq(bfqd, &bfqd->oom_bfqq, NULL, 1, 0);
+	bfqd->oom_bfqq.ref++;
+	bfqd->oom_bfqq.new_ioprio = BFQ_DEFAULT_QUEUE_IOPRIO;
+	bfqd->oom_bfqq.new_ioprio_class = IOPRIO_CLASS_BE;
+	bfqd->oom_bfqq.entity.new_weight =
+		bfq_ioprio_to_weight(bfqd->oom_bfqq.new_ioprio);
+
+	/* oom_bfqq does not participate to bursts */
+	bfq_clear_bfqq_just_created(&bfqd->oom_bfqq);
+
+	/*
+	 * Trigger weight initialization, according to ioprio, at the
+	 * oom_bfqq's first activation. The oom_bfqq's ioprio and ioprio
+	 * class won't be changed any more.
+	 */
+	bfqd->oom_bfqq.entity.prio_changed = 1;
+
+	bfqd->queue = q;
+
+	INIT_LIST_HEAD(&bfqd->dispatch);
+
+	hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_REL);
+	bfqd->idle_slice_timer.function = bfq_idle_slice_timer;
+
+	bfqd->queue_weights_tree = RB_ROOT;
+	bfqd->group_weights_tree = RB_ROOT;
+
+	INIT_LIST_HEAD(&bfqd->active_list);
+	INIT_LIST_HEAD(&bfqd->idle_list);
+	INIT_HLIST_HEAD(&bfqd->burst_list);
+
+	bfqd->hw_tag = -1;
+
+	bfqd->bfq_max_budget = bfq_default_max_budget;
+
+	bfqd->bfq_fifo_expire[0] = bfq_fifo_expire[0];
+	bfqd->bfq_fifo_expire[1] = bfq_fifo_expire[1];
+	bfqd->bfq_back_max = bfq_back_max;
+	bfqd->bfq_back_penalty = bfq_back_penalty;
+	bfqd->bfq_slice_idle = bfq_slice_idle;
+	bfqd->bfq_timeout = bfq_timeout;
+
+	bfqd->bfq_requests_within_timer = 120;
+
+	bfqd->bfq_large_burst_thresh = 8;
+	bfqd->bfq_burst_interval = msecs_to_jiffies(180);
+
+	bfqd->low_latency = true;
+
+	/*
+	 * Trade-off between responsiveness and fairness.
+	 */
+	bfqd->bfq_wr_coeff = 30;
+	bfqd->bfq_wr_rt_max_time = msecs_to_jiffies(300);
+	bfqd->bfq_wr_max_time = 0;
+	bfqd->bfq_wr_min_idle_time = msecs_to_jiffies(2000);
+	bfqd->bfq_wr_min_inter_arr_async = msecs_to_jiffies(500);
+	bfqd->bfq_wr_max_softrt_rate = 7000; /*
+					      * Approximate rate required
+					      * to playback or record a
+					      * high-definition compressed
+					      * video.
+					      */
+	bfqd->wr_busy_queues = 0;
+
+	/*
+	 * Begin by assuming, optimistically, that the device is a
+	 * high-speed one, and that its peak rate is equal to 2/3 of
+	 * the highest reference rate.
+	 */
+	bfqd->RT_prod = R_fast[blk_queue_nonrot(bfqd->queue)] *
+			T_fast[blk_queue_nonrot(bfqd->queue)];
+	bfqd->peak_rate = R_fast[blk_queue_nonrot(bfqd->queue)] * 2 / 3;
+	bfqd->device_speed = BFQ_BFQD_FAST;
+
+	spin_lock_init(&bfqd->lock);
+
+	/*
+	 * The invocation of the next bfq_create_group_hierarchy
+	 * function is the head of a chain of function calls
+	 * (bfq_create_group_hierarchy->blkcg_activate_policy->
+	 * blk_mq_freeze_queue) that may lead to the invocation of the
+	 * has_work hook function. For this reason,
+	 * bfq_create_group_hierarchy is invoked only after all
+	 * scheduler data has been initialized, apart from the fields
+	 * that can be initialized only after invoking
+	 * bfq_create_group_hierarchy. This, in particular, enables
+	 * has_work to correctly return false. Of course, to avoid
+	 * other inconsistencies, the blk-mq stack must then refrain
+	 * from invoking further scheduler hooks before this init
+	 * function is finished.
+	 */
+	bfqd->root_group = bfq_create_group_hierarchy(bfqd, q->node);
+	if (!bfqd->root_group)
+		goto out_free;
+	bfq_init_root_group(bfqd->root_group, bfqd);
+	bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group);
+
+
+	return 0;
+
+out_free:
+	kfree(bfqd);
+	kobject_put(&eq->kobj);
+	return -ENOMEM;
+}
+
+static void bfq_slab_kill(void)
+{
+	kmem_cache_destroy(bfq_pool);
+}
+
+static int __init bfq_slab_setup(void)
+{
+	bfq_pool = KMEM_CACHE(bfq_queue, 0);
+	if (!bfq_pool)
+		return -ENOMEM;
+	return 0;
+}
+
+static ssize_t bfq_var_show(unsigned int var, char *page)
+{
+	return sprintf(page, "%u\n", var);
+}
+
+static ssize_t bfq_var_store(unsigned long *var, const char *page,
+			     size_t count)
+{
+	unsigned long new_val;
+	int ret = kstrtoul(page, 10, &new_val);
+
+	if (ret == 0)
+		*var = new_val;
+
+	return count;
+}
+
+#define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
+static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
+{									\
+	struct bfq_data *bfqd = e->elevator_data;			\
+	u64 __data = __VAR;						\
+	if (__CONV == 1)						\
+		__data = jiffies_to_msecs(__data);			\
+	else if (__CONV == 2)						\
+		__data = div_u64(__data, NSEC_PER_MSEC);		\
+	return bfq_var_show(__data, (page));				\
+}
+SHOW_FUNCTION(bfq_fifo_expire_sync_show, bfqd->bfq_fifo_expire[1], 2);
+SHOW_FUNCTION(bfq_fifo_expire_async_show, bfqd->bfq_fifo_expire[0], 2);
+SHOW_FUNCTION(bfq_back_seek_max_show, bfqd->bfq_back_max, 0);
+SHOW_FUNCTION(bfq_back_seek_penalty_show, bfqd->bfq_back_penalty, 0);
+SHOW_FUNCTION(bfq_slice_idle_show, bfqd->bfq_slice_idle, 2);
+SHOW_FUNCTION(bfq_max_budget_show, bfqd->bfq_user_max_budget, 0);
+SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout, 1);
+SHOW_FUNCTION(bfq_strict_guarantees_show, bfqd->strict_guarantees, 0);
+SHOW_FUNCTION(bfq_low_latency_show, bfqd->low_latency, 0);
+#undef SHOW_FUNCTION
+
+#define USEC_SHOW_FUNCTION(__FUNC, __VAR)				\
+static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
+{									\
+	struct bfq_data *bfqd = e->elevator_data;			\
+	u64 __data = __VAR;						\
+	__data = div_u64(__data, NSEC_PER_USEC);			\
+	return bfq_var_show(__data, (page));				\
+}
+USEC_SHOW_FUNCTION(bfq_slice_idle_us_show, bfqd->bfq_slice_idle);
+#undef USEC_SHOW_FUNCTION
+
+#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
+static ssize_t								\
+__FUNC(struct elevator_queue *e, const char *page, size_t count)	\
+{									\
+	struct bfq_data *bfqd = e->elevator_data;			\
+	unsigned long uninitialized_var(__data);			\
+	int ret = bfq_var_store(&__data, (page), count);		\
+	if (__data < (MIN))						\
+		__data = (MIN);						\
+	else if (__data > (MAX))					\
+		__data = (MAX);						\
+	if (__CONV == 1)						\
+		*(__PTR) = msecs_to_jiffies(__data);			\
+	else if (__CONV == 2)						\
+		*(__PTR) = (u64)__data * NSEC_PER_MSEC;			\
+	else								\
+		*(__PTR) = __data;					\
+	return ret;							\
+}
+STORE_FUNCTION(bfq_fifo_expire_sync_store, &bfqd->bfq_fifo_expire[1], 1,
+		INT_MAX, 2);
+STORE_FUNCTION(bfq_fifo_expire_async_store, &bfqd->bfq_fifo_expire[0], 1,
+		INT_MAX, 2);
+STORE_FUNCTION(bfq_back_seek_max_store, &bfqd->bfq_back_max, 0, INT_MAX, 0);
+STORE_FUNCTION(bfq_back_seek_penalty_store, &bfqd->bfq_back_penalty, 1,
+		INT_MAX, 0);
+STORE_FUNCTION(bfq_slice_idle_store, &bfqd->bfq_slice_idle, 0, INT_MAX, 2);
+#undef STORE_FUNCTION
+
+#define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX)			\
+static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)\
+{									\
+	struct bfq_data *bfqd = e->elevator_data;			\
+	unsigned long uninitialized_var(__data);			\
+	int ret = bfq_var_store(&__data, (page), count);		\
+	if (__data < (MIN))						\
+		__data = (MIN);						\
+	else if (__data > (MAX))					\
+		__data = (MAX);						\
+	*(__PTR) = (u64)__data * NSEC_PER_USEC;				\
+	return ret;							\
+}
+USEC_STORE_FUNCTION(bfq_slice_idle_us_store, &bfqd->bfq_slice_idle, 0,
+		    UINT_MAX);
+#undef USEC_STORE_FUNCTION
+
+static ssize_t bfq_max_budget_store(struct elevator_queue *e,
+				    const char *page, size_t count)
+{
+	struct bfq_data *bfqd = e->elevator_data;
+	unsigned long uninitialized_var(__data);
+	int ret = bfq_var_store(&__data, (page), count);
+
+	if (__data == 0)
+		bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd);
+	else {
+		if (__data > INT_MAX)
+			__data = INT_MAX;
+		bfqd->bfq_max_budget = __data;
+	}
+
+	bfqd->bfq_user_max_budget = __data;
+
+	return ret;
+}
+
+/*
+ * Leaving this name to preserve name compatibility with cfq
+ * parameters, but this timeout is used for both sync and async.
+ */
+static ssize_t bfq_timeout_sync_store(struct elevator_queue *e,
+				      const char *page, size_t count)
+{
+	struct bfq_data *bfqd = e->elevator_data;
+	unsigned long uninitialized_var(__data);
+	int ret = bfq_var_store(&__data, (page), count);
+
+	if (__data < 1)
+		__data = 1;
+	else if (__data > INT_MAX)
+		__data = INT_MAX;
+
+	bfqd->bfq_timeout = msecs_to_jiffies(__data);
+	if (bfqd->bfq_user_max_budget == 0)
+		bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd);
+
+	return ret;
+}
+
+static ssize_t bfq_strict_guarantees_store(struct elevator_queue *e,
+				     const char *page, size_t count)
+{
+	struct bfq_data *bfqd = e->elevator_data;
+	unsigned long uninitialized_var(__data);
+	int ret = bfq_var_store(&__data, (page), count);
+
+	if (__data > 1)
+		__data = 1;
+	if (!bfqd->strict_guarantees && __data == 1
+	    && bfqd->bfq_slice_idle < 8 * NSEC_PER_MSEC)
+		bfqd->bfq_slice_idle = 8 * NSEC_PER_MSEC;
+
+	bfqd->strict_guarantees = __data;
+
+	return ret;
+}
+
+static ssize_t bfq_low_latency_store(struct elevator_queue *e,
+				     const char *page, size_t count)
+{
+	struct bfq_data *bfqd = e->elevator_data;
+	unsigned long uninitialized_var(__data);
+	int ret = bfq_var_store(&__data, (page), count);
+
+	if (__data > 1)
+		__data = 1;
+	if (__data == 0 && bfqd->low_latency != 0)
+		bfq_end_wr(bfqd);
+	bfqd->low_latency = __data;
+
+	return ret;
+}
+
+#define BFQ_ATTR(name) \
+	__ATTR(name, 0644, bfq_##name##_show, bfq_##name##_store)
+
+static struct elv_fs_entry bfq_attrs[] = {
+	BFQ_ATTR(fifo_expire_sync),
+	BFQ_ATTR(fifo_expire_async),
+	BFQ_ATTR(back_seek_max),
+	BFQ_ATTR(back_seek_penalty),
+	BFQ_ATTR(slice_idle),
+	BFQ_ATTR(slice_idle_us),
+	BFQ_ATTR(max_budget),
+	BFQ_ATTR(timeout_sync),
+	BFQ_ATTR(strict_guarantees),
+	BFQ_ATTR(low_latency),
+	__ATTR_NULL
+};
+
+static struct elevator_type iosched_bfq_mq = {
+	.ops.mq = {
+		.get_rq_priv		= bfq_get_rq_private,
+		.put_rq_priv		= bfq_put_rq_private,
+		.exit_icq		= bfq_exit_icq,
+		.insert_requests	= bfq_insert_requests,
+		.dispatch_request	= bfq_dispatch_request,
+		.next_request		= elv_rb_latter_request,
+		.former_request		= elv_rb_former_request,
+		.allow_merge		= bfq_allow_bio_merge,
+		.bio_merge		= bfq_bio_merge,
+		.request_merge		= bfq_request_merge,
+		.requests_merged	= bfq_requests_merged,
+		.request_merged		= bfq_request_merged,
+		.has_work		= bfq_has_work,
+		.init_sched		= bfq_init_queue,
+		.exit_sched		= bfq_exit_queue,
+	},
+
+	.uses_mq =		true,
+	.icq_size =		sizeof(struct bfq_io_cq),
+	.icq_align =		__alignof__(struct bfq_io_cq),
+	.elevator_attrs =	bfq_attrs,
+	.elevator_name =	"bfq",
+	.elevator_owner =	THIS_MODULE,
+};
+
+static int __init bfq_init(void)
+{
+	int ret;
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	ret = blkcg_policy_register(&blkcg_policy_bfq);
+	if (ret)
+		return ret;
+#endif
+
+	ret = -ENOMEM;
+	if (bfq_slab_setup())
+		goto err_pol_unreg;
+
+	/*
+	 * Times to load large popular applications for the typical
+	 * systems installed on the reference devices (see the
+	 * comments before the definitions of the next two
+	 * arrays). Actually, we use slightly slower values, as the
+	 * estimated peak rate tends to be smaller than the actual
+	 * peak rate.  The reason for this last fact is that estimates
+	 * are computed over much shorter time intervals than the long
+	 * intervals typically used for benchmarking. Why? First, to
+	 * adapt more quickly to variations. Second, because an I/O
+	 * scheduler cannot rely on a peak-rate-evaluation workload to
+	 * be run for a long time.
+	 */
+	T_slow[0] = msecs_to_jiffies(3500); /* actually 4 sec */
+	T_slow[1] = msecs_to_jiffies(6000); /* actually 6.5 sec */
+	T_fast[0] = msecs_to_jiffies(7000); /* actually 8 sec */
+	T_fast[1] = msecs_to_jiffies(2500); /* actually 3 sec */
+
+	/*
+	 * Thresholds that determine the switch between speed classes
+	 * (see the comments before the definition of the array
+	 * device_speed_thresh). These thresholds are biased towards
+	 * transitions to the fast class. This is safer than the
+	 * opposite bias. In fact, a wrong transition to the slow
+	 * class results in short weight-raising periods, because the
+	 * speed of the device then tends to be higher that the
+	 * reference peak rate. On the opposite end, a wrong
+	 * transition to the fast class tends to increase
+	 * weight-raising periods, because of the opposite reason.
+	 */
+	device_speed_thresh[0] = (4 * R_slow[0]) / 3;
+	device_speed_thresh[1] = (4 * R_slow[1]) / 3;
+
+	ret = elv_register(&iosched_bfq_mq);
+	if (ret)
+		goto err_pol_unreg;
+
+	return 0;
+
+err_pol_unreg:
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	blkcg_policy_unregister(&blkcg_policy_bfq);
+#endif
+	return ret;
+}
+
+static void __exit bfq_exit(void)
+{
+	elv_unregister(&iosched_bfq_mq);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	blkcg_policy_unregister(&blkcg_policy_bfq);
+#endif
+	bfq_slab_kill();
+}
+
+module_init(bfq_init);
+module_exit(bfq_exit);
+
+MODULE_AUTHOR("Paolo Valente");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("MQ Budget Fair Queueing I/O Scheduler");

block/bfq-iosched.h

@@ -0,0 +1,941 @@
+/*
+ * Header file for the BFQ I/O scheduler: data structures and
+ * prototypes of interface functions among BFQ components.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License as
+ *  published by the Free Software Foundation; either version 2 of the
+ *  License, or (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ */
+#ifndef _BFQ_H
+#define _BFQ_H
+
+#include <linux/blktrace_api.h>
+#include <linux/hrtimer.h>
+#include <linux/blk-cgroup.h>
+
+#define BFQ_IOPRIO_CLASSES	3
+#define BFQ_CL_IDLE_TIMEOUT	(HZ/5)
+
+#define BFQ_MIN_WEIGHT			1
+#define BFQ_MAX_WEIGHT			1000
+#define BFQ_WEIGHT_CONVERSION_COEFF	10
+
+#define BFQ_DEFAULT_QUEUE_IOPRIO	4
+
+#define BFQ_WEIGHT_LEGACY_DFL	100
+#define BFQ_DEFAULT_GRP_IOPRIO	0
+#define BFQ_DEFAULT_GRP_CLASS	IOPRIO_CLASS_BE
+
+/*
+ * Soft real-time applications are extremely more latency sensitive
+ * than interactive ones. Over-raise the weight of the former to
+ * privilege them against the latter.
+ */
+#define BFQ_SOFTRT_WEIGHT_FACTOR	100
+
+struct bfq_entity;
+
+/**
+ * struct bfq_service_tree - per ioprio_class service tree.
+ *
+ * Each service tree represents a B-WF2Q+ scheduler on its own.  Each
+ * ioprio_class has its own independent scheduler, and so its own
+ * bfq_service_tree.  All the fields are protected by the queue lock
+ * of the containing bfqd.
+ */
+struct bfq_service_tree {
+	/* tree for active entities (i.e., those backlogged) */
+	struct rb_root active;
+	/* tree for idle entities (i.e., not backlogged, with V <= F_i)*/
+	struct rb_root idle;
+
+	/* idle entity with minimum F_i */
+	struct bfq_entity *first_idle;
+	/* idle entity with maximum F_i */
+	struct bfq_entity *last_idle;
+
+	/* scheduler virtual time */
+	u64 vtime;
+	/* scheduler weight sum; active and idle entities contribute to it */
+	unsigned long wsum;
+};
+
+/**
+ * struct bfq_sched_data - multi-class scheduler.
+ *
+ * bfq_sched_data is the basic scheduler queue.  It supports three
+ * ioprio_classes, and can be used either as a toplevel queue or as an
+ * intermediate queue on a hierarchical setup.  @next_in_service
+ * points to the active entity of the sched_data service trees that
+ * will be scheduled next. It is used to reduce the number of steps
+ * needed for each hierarchical-schedule update.
+ *
+ * The supported ioprio_classes are the same as in CFQ, in descending
+ * priority order, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE.
+ * Requests from higher priority queues are served before all the
+ * requests from lower priority queues; among requests of the same
+ * queue requests are served according to B-WF2Q+.
+ * All the fields are protected by the queue lock of the containing bfqd.
+ */
+struct bfq_sched_data {
+	/* entity in service */
+	struct bfq_entity *in_service_entity;
+	/* head-of-line entity (see comments above) */
+	struct bfq_entity *next_in_service;
+	/* array of service trees, one per ioprio_class */
+	struct bfq_service_tree service_tree[BFQ_IOPRIO_CLASSES];
+	/* last time CLASS_IDLE was served */
+	unsigned long bfq_class_idle_last_service;
+
+};
+
+/**
+ * struct bfq_weight_counter - counter of the number of all active entities
+ *                             with a given weight.
+ */
+struct bfq_weight_counter {
+	unsigned int weight; /* weight of the entities this counter refers to */
+	unsigned int num_active; /* nr of active entities with this weight */
+	/*
+	 * Weights tree member (see bfq_data's @queue_weights_tree and
+	 * @group_weights_tree)
+	 */
+	struct rb_node weights_node;
+};
+
+/**
+ * struct bfq_entity - schedulable entity.
+ *
+ * A bfq_entity is used to represent either a bfq_queue (leaf node in the
+ * cgroup hierarchy) or a bfq_group into the upper level scheduler.  Each
+ * entity belongs to the sched_data of the parent group in the cgroup
+ * hierarchy.  Non-leaf entities have also their own sched_data, stored
+ * in @my_sched_data.
+ *
+ * Each entity stores independently its priority values; this would
+ * allow different weights on different devices, but this
+ * functionality is not exported to userspace by now.  Priorities and
+ * weights are updated lazily, first storing the new values into the
+ * new_* fields, then setting the @prio_changed flag.  As soon as
+ * there is a transition in the entity state that allows the priority
+ * update to take place the effective and the requested priority
+ * values are synchronized.
+ *
+ * Unless cgroups are used, the weight value is calculated from the
+ * ioprio to export the same interface as CFQ.  When dealing with
+ * ``well-behaved'' queues (i.e., queues that do not spend too much
+ * time to consume their budget and have true sequential behavior, and
+ * when there are no external factors breaking anticipation) the
+ * relative weights at each level of the cgroups hierarchy should be
+ * guaranteed.  All the fields are protected by the queue lock of the
+ * containing bfqd.
+ */
+struct bfq_entity {
+	/* service_tree member */
+	struct rb_node rb_node;
+	/* pointer to the weight counter associated with this entity */
+	struct bfq_weight_counter *weight_counter;
+
+	/*
+	 * Flag, true if the entity is on a tree (either the active or
+	 * the idle one of its service_tree) or is in service.
+	 */
+	bool on_st;
+
+	/* B-WF2Q+ start and finish timestamps [sectors/weight] */
+	u64 start, finish;
+
+	/* tree the entity is enqueued into; %NULL if not on a tree */
+	struct rb_root *tree;
+
+	/*
+	 * minimum start time of the (active) subtree rooted at this
+	 * entity; used for O(log N) lookups into active trees
+	 */
+	u64 min_start;
+
+	/* amount of service received during the last service slot */
+	int service;
+
+	/* budget, used also to calculate F_i: F_i = S_i + @budget / @weight */
+	int budget;
+
+	/* weight of the queue */
+	int weight;
+	/* next weight if a change is in progress */
+	int new_weight;
+
+	/* original weight, used to implement weight boosting */
+	int orig_weight;
+
+	/* parent entity, for hierarchical scheduling */
+	struct bfq_entity *parent;
+
+	/*
+	 * For non-leaf nodes in the hierarchy, the associated
+	 * scheduler queue, %NULL on leaf nodes.
+	 */
+	struct bfq_sched_data *my_sched_data;
+	/* the scheduler queue this entity belongs to */
+	struct bfq_sched_data *sched_data;
+
+	/* flag, set to request a weight, ioprio or ioprio_class change  */
+	int prio_changed;
+};
+
+struct bfq_group;
+
+/**
+ * struct bfq_ttime - per process thinktime stats.
+ */
+struct bfq_ttime {
+	/* completion time of the last request */
+	u64 last_end_request;
+
+	/* total process thinktime */
+	u64 ttime_total;
+	/* number of thinktime samples */
+	unsigned long ttime_samples;
+	/* average process thinktime */
+	u64 ttime_mean;
+};
+
+/**
+ * struct bfq_queue - leaf schedulable entity.
+ *
+ * A bfq_queue is a leaf request queue; it can be associated with an
+ * io_context or more, if it  is  async or shared  between  cooperating
+ * processes. @cgroup holds a reference to the cgroup, to be sure that it
+ * does not disappear while a bfqq still references it (mostly to avoid
+ * races between request issuing and task migration followed by cgroup
+ * destruction).
+ * All the fields are protected by the queue lock of the containing bfqd.
+ */
+struct bfq_queue {
+	/* reference counter */
+	int ref;
+	/* parent bfq_data */
+	struct bfq_data *bfqd;
+
+	/* current ioprio and ioprio class */
+	unsigned short ioprio, ioprio_class;
+	/* next ioprio and ioprio class if a change is in progress */
+	unsigned short new_ioprio, new_ioprio_class;
+
+	/*
+	 * Shared bfq_queue if queue is cooperating with one or more
+	 * other queues.
+	 */
+	struct bfq_queue *new_bfqq;
+	/* request-position tree member (see bfq_group's @rq_pos_tree) */
+	struct rb_node pos_node;
+	/* request-position tree root (see bfq_group's @rq_pos_tree) */
+	struct rb_root *pos_root;
+
+	/* sorted list of pending requests */
+	struct rb_root sort_list;
+	/* if fifo isn't expired, next request to serve */
+	struct request *next_rq;
+	/* number of sync and async requests queued */
+	int queued[2];
+	/* number of requests currently allocated */
+	int allocated;
+	/* number of pending metadata requests */
+	int meta_pending;
+	/* fifo list of requests in sort_list */
+	struct list_head fifo;
+
+	/* entity representing this queue in the scheduler */
+	struct bfq_entity entity;
+
+	/* maximum budget allowed from the feedback mechanism */
+	int max_budget;
+	/* budget expiration (in jiffies) */
+	unsigned long budget_timeout;
+
+	/* number of requests on the dispatch list or inside driver */
+	int dispatched;
+
+	/* status flags */
+	unsigned long flags;
+
+	/* node for active/idle bfqq list inside parent bfqd */
+	struct list_head bfqq_list;
+
+	/* associated @bfq_ttime struct */
+	struct bfq_ttime ttime;
+
+	/* bit vector: a 1 for each seeky requests in history */
+	u32 seek_history;
+
+	/* node for the device's burst list */
+	struct hlist_node burst_list_node;
+
+	/* position of the last request enqueued */
+	sector_t last_request_pos;
+
+	/* Number of consecutive pairs of request completion and
+	 * arrival, such that the queue becomes idle after the
+	 * completion, but the next request arrives within an idle
+	 * time slice; used only if the queue's IO_bound flag has been
+	 * cleared.
+	 */
+	unsigned int requests_within_timer;
+
+	/* pid of the process owning the queue, used for logging purposes */
+	pid_t pid;
+
+	/*
+	 * Pointer to the bfq_io_cq owning the bfq_queue, set to %NULL
+	 * if the queue is shared.
+	 */
+	struct bfq_io_cq *bic;
+
+	/* current maximum weight-raising time for this queue */
+	unsigned long wr_cur_max_time;
+	/*
+	 * Minimum time instant such that, only if a new request is
+	 * enqueued after this time instant in an idle @bfq_queue with
+	 * no outstanding requests, then the task associated with the
+	 * queue it is deemed as soft real-time (see the comments on
+	 * the function bfq_bfqq_softrt_next_start())
+	 */
+	unsigned long soft_rt_next_start;
+	/*
+	 * Start time of the current weight-raising period if
+	 * the @bfq-queue is being weight-raised, otherwise
+	 * finish time of the last weight-raising period.
+	 */
+	unsigned long last_wr_start_finish;
+	/* factor by which the weight of this queue is multiplied */
+	unsigned int wr_coeff;
+	/*
+	 * Time of the last transition of the @bfq_queue from idle to
+	 * backlogged.
+	 */
+	unsigned long last_idle_bklogged;
+	/*
+	 * Cumulative service received from the @bfq_queue since the
+	 * last transition from idle to backlogged.
+	 */
+	unsigned long service_from_backlogged;
+
+	/*
+	 * Value of wr start time when switching to soft rt
+	 */
+	unsigned long wr_start_at_switch_to_srt;
+
+	unsigned long split_time; /* time of last split */
+};
+
+/**
+ * struct bfq_io_cq - per (request_queue, io_context) structure.
+ */
+struct bfq_io_cq {
+	/* associated io_cq structure */
+	struct io_cq icq; /* must be the first member */
+	/* array of two process queues, the sync and the async */
+	struct bfq_queue *bfqq[2];
+	/* per (request_queue, blkcg) ioprio */
+	int ioprio;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	uint64_t blkcg_serial_nr; /* the current blkcg serial */
+#endif
+	/*
+	 * Snapshot of the idle window before merging; taken to
+	 * remember this value while the queue is merged, so as to be
+	 * able to restore it in case of split.
+	 */
+	bool saved_idle_window;
+	/*
+	 * Same purpose as the previous two fields for the I/O bound
+	 * classification of a queue.
+	 */
+	bool saved_IO_bound;
+
+	/*
+	 * Same purpose as the previous fields for the value of the
+	 * field keeping the queue's belonging to a large burst
+	 */
+	bool saved_in_large_burst;
+	/*
+	 * True if the queue belonged to a burst list before its merge
+	 * with another cooperating queue.
+	 */
+	bool was_in_burst_list;
+
+	/*
+	 * Similar to previous fields: save wr information.
+	 */
+	unsigned long saved_wr_coeff;
+	unsigned long saved_last_wr_start_finish;
+	unsigned long saved_wr_start_at_switch_to_srt;
+	unsigned int saved_wr_cur_max_time;
+	struct bfq_ttime saved_ttime;
+};
+
+enum bfq_device_speed {
+	BFQ_BFQD_FAST,
+	BFQ_BFQD_SLOW,
+};
+
+/**
+ * struct bfq_data - per-device data structure.
+ *
+ * All the fields are protected by @lock.
+ */
+struct bfq_data {
+	/* device request queue */
+	struct request_queue *queue;
+	/* dispatch queue */
+	struct list_head dispatch;
+
+	/* root bfq_group for the device */
+	struct bfq_group *root_group;
+
+	/*
+	 * rbtree of weight counters of @bfq_queues, sorted by
+	 * weight. Used to keep track of whether all @bfq_queues have
+	 * the same weight. The tree contains one counter for each
+	 * distinct weight associated to some active and not
+	 * weight-raised @bfq_queue (see the comments to the functions
+	 * bfq_weights_tree_[add|remove] for further details).
+	 */
+	struct rb_root queue_weights_tree;
+	/*
+	 * rbtree of non-queue @bfq_entity weight counters, sorted by
+	 * weight. Used to keep track of whether all @bfq_groups have
+	 * the same weight. The tree contains one counter for each
+	 * distinct weight associated to some active @bfq_group (see
+	 * the comments to the functions bfq_weights_tree_[add|remove]
+	 * for further details).
+	 */
+	struct rb_root group_weights_tree;
+
+	/*
+	 * Number of bfq_queues containing requests (including the
+	 * queue in service, even if it is idling).
+	 */
+	int busy_queues;
+	/* number of weight-raised busy @bfq_queues */
+	int wr_busy_queues;
+	/* number of queued requests */
+	int queued;
+	/* number of requests dispatched and waiting for completion */
+	int rq_in_driver;
+
+	/*
+	 * Maximum number of requests in driver in the last
+	 * @hw_tag_samples completed requests.
+	 */
+	int max_rq_in_driver;
+	/* number of samples used to calculate hw_tag */
+	int hw_tag_samples;
+	/* flag set to one if the driver is showing a queueing behavior */
+	int hw_tag;
+
+	/* number of budgets assigned */
+	int budgets_assigned;
+
+	/*
+	 * Timer set when idling (waiting) for the next request from
+	 * the queue in service.
+	 */
+	struct hrtimer idle_slice_timer;
+
+	/* bfq_queue in service */
+	struct bfq_queue *in_service_queue;
+
+	/* on-disk position of the last served request */
+	sector_t last_position;
+
+	/* time of last request completion (ns) */
+	u64 last_completion;
+
+	/* time of first rq dispatch in current observation interval (ns) */
+	u64 first_dispatch;
+	/* time of last rq dispatch in current observation interval (ns) */
+	u64 last_dispatch;
+
+	/* beginning of the last budget */
+	ktime_t last_budget_start;
+	/* beginning of the last idle slice */
+	ktime_t last_idling_start;
+
+	/* number of samples in current observation interval */
+	int peak_rate_samples;
+	/* num of samples of seq dispatches in current observation interval */
+	u32 sequential_samples;
+	/* total num of sectors transferred in current observation interval */
+	u64 tot_sectors_dispatched;
+	/* max rq size seen during current observation interval (sectors) */
+	u32 last_rq_max_size;
+	/* time elapsed from first dispatch in current observ. interval (us) */
+	u64 delta_from_first;
+	/*
+	 * Current estimate of the device peak rate, measured in
+	 * [BFQ_RATE_SHIFT * sectors/usec]. The left-shift by
+	 * BFQ_RATE_SHIFT is performed to increase precision in
+	 * fixed-point calculations.
+	 */
+	u32 peak_rate;
+
+	/* maximum budget allotted to a bfq_queue before rescheduling */
+	int bfq_max_budget;
+
+	/* list of all the bfq_queues active on the device */
+	struct list_head active_list;
+	/* list of all the bfq_queues idle on the device */
+	struct list_head idle_list;
+
+	/*
+	 * Timeout for async/sync requests; when it fires, requests
+	 * are served in fifo order.
+	 */
+	u64 bfq_fifo_expire[2];
+	/* weight of backward seeks wrt forward ones */
+	unsigned int bfq_back_penalty;
+	/* maximum allowed backward seek */
+	unsigned int bfq_back_max;
+	/* maximum idling time */
+	u32 bfq_slice_idle;
+
+	/* user-configured max budget value (0 for auto-tuning) */
+	int bfq_user_max_budget;
+	/*
+	 * Timeout for bfq_queues to consume their budget; used to
+	 * prevent seeky queues from imposing long latencies to
+	 * sequential or quasi-sequential ones (this also implies that
+	 * seeky queues cannot receive guarantees in the service
+	 * domain; after a timeout they are charged for the time they
+	 * have been in service, to preserve fairness among them, but
+	 * without service-domain guarantees).
+	 */
+	unsigned int bfq_timeout;
+
+	/*
+	 * Number of consecutive requests that must be issued within
+	 * the idle time slice to set again idling to a queue which
+	 * was marked as non-I/O-bound (see the definition of the
+	 * IO_bound flag for further details).
+	 */
+	unsigned int bfq_requests_within_timer;
+
+	/*
+	 * Force device idling whenever needed to provide accurate
+	 * service guarantees, without caring about throughput
+	 * issues. CAVEAT: this may even increase latencies, in case
+	 * of useless idling for processes that did stop doing I/O.
+	 */
+	bool strict_guarantees;
+
+	/*
+	 * Last time at which a queue entered the current burst of
+	 * queues being activated shortly after each other; for more
+	 * details about this and the following parameters related to
+	 * a burst of activations, see the comments on the function
+	 * bfq_handle_burst.
+	 */
+	unsigned long last_ins_in_burst;
+	/*
+	 * Reference time interval used to decide whether a queue has
+	 * been activated shortly after @last_ins_in_burst.
+	 */
+	unsigned long bfq_burst_interval;
+	/* number of queues in the current burst of queue activations */
+	int burst_size;
+
+	/* common parent entity for the queues in the burst */
+	struct bfq_entity *burst_parent_entity;
+	/* Maximum burst size above which the current queue-activation
+	 * burst is deemed as 'large'.
+	 */
+	unsigned long bfq_large_burst_thresh;
+	/* true if a large queue-activation burst is in progress */
+	bool large_burst;
+	/*
+	 * Head of the burst list (as for the above fields, more
+	 * details in the comments on the function bfq_handle_burst).
+	 */
+	struct hlist_head burst_list;
+
+	/* if set to true, low-latency heuristics are enabled */
+	bool low_latency;
+	/*
+	 * Maximum factor by which the weight of a weight-raised queue
+	 * is multiplied.
+	 */
+	unsigned int bfq_wr_coeff;
+	/* maximum duration of a weight-raising period (jiffies) */
+	unsigned int bfq_wr_max_time;
+
+	/* Maximum weight-raising duration for soft real-time processes */
+	unsigned int bfq_wr_rt_max_time;
+	/*
+	 * Minimum idle period after which weight-raising may be
+	 * reactivated for a queue (in jiffies).
+	 */
+	unsigned int bfq_wr_min_idle_time;
+	/*
+	 * Minimum period between request arrivals after which
+	 * weight-raising may be reactivated for an already busy async
+	 * queue (in jiffies).
+	 */
+	unsigned long bfq_wr_min_inter_arr_async;
+
+	/* Max service-rate for a soft real-time queue, in sectors/sec */
+	unsigned int bfq_wr_max_softrt_rate;
+	/*
+	 * Cached value of the product R*T, used for computing the
+	 * maximum duration of weight raising automatically.
+	 */
+	u64 RT_prod;
+	/* device-speed class for the low-latency heuristic */
+	enum bfq_device_speed device_speed;
+
+	/* fallback dummy bfqq for extreme OOM conditions */
+	struct bfq_queue oom_bfqq;
+
+	spinlock_t lock;
+
+	/*
+	 * bic associated with the task issuing current bio for
+	 * merging. This and the next field are used as a support to
+	 * be able to perform the bic lookup, needed by bio-merge
+	 * functions, before the scheduler lock is taken, and thus
+	 * avoid taking the request-queue lock while the scheduler
+	 * lock is being held.
+	 */
+	struct bfq_io_cq *bio_bic;
+	/* bfqq associated with the task issuing current bio for merging */
+	struct bfq_queue *bio_bfqq;
+};
+
+enum bfqq_state_flags {
+	BFQQF_just_created = 0,	/* queue just allocated */
+	BFQQF_busy,		/* has requests or is in service */
+	BFQQF_wait_request,	/* waiting for a request */
+	BFQQF_non_blocking_wait_rq, /*
+				     * waiting for a request
+				     * without idling the device
+				     */
+	BFQQF_fifo_expire,	/* FIFO checked in this slice */
+	BFQQF_idle_window,	/* slice idling enabled */
+	BFQQF_sync,		/* synchronous queue */
+	BFQQF_IO_bound,		/*
+				 * bfqq has timed-out at least once
+				 * having consumed at most 2/10 of
+				 * its budget
+				 */
+	BFQQF_in_large_burst,	/*
+				 * bfqq activated in a large burst,
+				 * see comments to bfq_handle_burst.
+				 */
+	BFQQF_softrt_update,	/*
+				 * may need softrt-next-start
+				 * update
+				 */
+	BFQQF_coop,		/* bfqq is shared */
+	BFQQF_split_coop	/* shared bfqq will be split */
+};
+
+#define BFQ_BFQQ_FNS(name)						\
+void bfq_mark_bfqq_##name(struct bfq_queue *bfqq);			\
+void bfq_clear_bfqq_##name(struct bfq_queue *bfqq);			\
+int bfq_bfqq_##name(const struct bfq_queue *bfqq);
+
+BFQ_BFQQ_FNS(just_created);
+BFQ_BFQQ_FNS(busy);
+BFQ_BFQQ_FNS(wait_request);
+BFQ_BFQQ_FNS(non_blocking_wait_rq);
+BFQ_BFQQ_FNS(fifo_expire);
+BFQ_BFQQ_FNS(idle_window);
+BFQ_BFQQ_FNS(sync);
+BFQ_BFQQ_FNS(IO_bound);
+BFQ_BFQQ_FNS(in_large_burst);
+BFQ_BFQQ_FNS(coop);
+BFQ_BFQQ_FNS(split_coop);
+BFQ_BFQQ_FNS(softrt_update);
+#undef BFQ_BFQQ_FNS
+
+/* Expiration reasons. */
+enum bfqq_expiration {
+	BFQQE_TOO_IDLE = 0,		/*
+					 * queue has been idling for
+					 * too long
+					 */
+	BFQQE_BUDGET_TIMEOUT,	/* budget took too long to be used */
+	BFQQE_BUDGET_EXHAUSTED,	/* budget consumed */
+	BFQQE_NO_MORE_REQUESTS,	/* the queue has no more requests */
+	BFQQE_PREEMPTED		/* preemption in progress */
+};
+
+struct bfqg_stats {
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	/* number of ios merged */
+	struct blkg_rwstat		merged;
+	/* total time spent on device in ns, may not be accurate w/ queueing */
+	struct blkg_rwstat		service_time;
+	/* total time spent waiting in scheduler queue in ns */
+	struct blkg_rwstat		wait_time;
+	/* number of IOs queued up */
+	struct blkg_rwstat		queued;
+	/* total disk time and nr sectors dispatched by this group */
+	struct blkg_stat		time;
+	/* sum of number of ios queued across all samples */
+	struct blkg_stat		avg_queue_size_sum;
+	/* count of samples taken for average */
+	struct blkg_stat		avg_queue_size_samples;
+	/* how many times this group has been removed from service tree */
+	struct blkg_stat		dequeue;
+	/* total time spent waiting for it to be assigned a timeslice. */
+	struct blkg_stat		group_wait_time;
+	/* time spent idling for this blkcg_gq */
+	struct blkg_stat		idle_time;
+	/* total time with empty current active q with other requests queued */
+	struct blkg_stat		empty_time;
+	/* fields after this shouldn't be cleared on stat reset */
+	uint64_t			start_group_wait_time;
+	uint64_t			start_idle_time;
+	uint64_t			start_empty_time;
+	uint16_t			flags;
+#endif	/* CONFIG_BFQ_GROUP_IOSCHED */
+};
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+
+/*
+ * struct bfq_group_data - per-blkcg storage for the blkio subsystem.
+ *
+ * @ps: @blkcg_policy_storage that this structure inherits
+ * @weight: weight of the bfq_group
+ */
+struct bfq_group_data {
+	/* must be the first member */
+	struct blkcg_policy_data pd;
+
+	unsigned int weight;
+};
+
+/**
+ * struct bfq_group - per (device, cgroup) data structure.
+ * @entity: schedulable entity to insert into the parent group sched_data.
+ * @sched_data: own sched_data, to contain child entities (they may be
+ *              both bfq_queues and bfq_groups).
+ * @bfqd: the bfq_data for the device this group acts upon.
+ * @async_bfqq: array of async queues for all the tasks belonging to
+ *              the group, one queue per ioprio value per ioprio_class,
+ *              except for the idle class that has only one queue.
+ * @async_idle_bfqq: async queue for the idle class (ioprio is ignored).
+ * @my_entity: pointer to @entity, %NULL for the toplevel group; used
+ *             to avoid too many special cases during group creation/
+ *             migration.
+ * @stats: stats for this bfqg.
+ * @active_entities: number of active entities belonging to the group;
+ *                   unused for the root group. Used to know whether there
+ *                   are groups with more than one active @bfq_entity
+ *                   (see the comments to the function
+ *                   bfq_bfqq_may_idle()).
+ * @rq_pos_tree: rbtree sorted by next_request position, used when
+ *               determining if two or more queues have interleaving
+ *               requests (see bfq_find_close_cooperator()).
+ *
+ * Each (device, cgroup) pair has its own bfq_group, i.e., for each cgroup
+ * there is a set of bfq_groups, each one collecting the lower-level
+ * entities belonging to the group that are acting on the same device.
+ *
+ * Locking works as follows:
+ *    o @bfqd is protected by the queue lock, RCU is used to access it
+ *      from the readers.
+ *    o All the other fields are protected by the @bfqd queue lock.
+ */
+struct bfq_group {
+	/* must be the first member */
+	struct blkg_policy_data pd;
+
+	struct bfq_entity entity;
+	struct bfq_sched_data sched_data;
+
+	void *bfqd;
+
+	struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
+	struct bfq_queue *async_idle_bfqq;
+
+	struct bfq_entity *my_entity;
+
+	int active_entities;
+
+	struct rb_root rq_pos_tree;
+
+	struct bfqg_stats stats;
+};
+
+#else
+struct bfq_group {
+	struct bfq_sched_data sched_data;
+
+	struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
+	struct bfq_queue *async_idle_bfqq;
+
+	struct rb_root rq_pos_tree;
+};
+#endif
+
+struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);
+
+/* --------------- main algorithm interface ----------------- */
+
+#define BFQ_SERVICE_TREE_INIT	((struct bfq_service_tree)		\
+				{ RB_ROOT, RB_ROOT, NULL, NULL, 0, 0 })
+
+extern const int bfq_timeout;
+
+struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync);
+void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync);
+struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic);
+void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
+			  struct rb_root *root);
+void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_entity *entity,
+			     struct rb_root *root);
+void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		     bool compensate, enum bfqq_expiration reason);
+void bfq_put_queue(struct bfq_queue *bfqq);
+void bfq_end_wr_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
+void bfq_schedule_dispatch(struct bfq_data *bfqd);
+void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
+
+/* ------------ end of main algorithm interface -------------- */
+
+/* ---------------- cgroups-support interface ---------------- */
+
+void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
+			      unsigned int op);
+void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op);
+void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op);
+void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
+				  uint64_t io_start_time, unsigned int op);
+void bfqg_stats_update_dequeue(struct bfq_group *bfqg);
+void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
+void bfqg_stats_update_idle_time(struct bfq_group *bfqg);
+void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg);
+void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg);
+void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		   struct bfq_group *bfqg);
+
+void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg);
+void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio);
+void bfq_end_wr_async(struct bfq_data *bfqd);
+struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
+				     struct blkcg *blkcg);
+struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
+struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
+struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node);
+void bfqg_put(struct bfq_group *bfqg);
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+extern struct cftype bfq_blkcg_legacy_files[];
+extern struct cftype bfq_blkg_files[];
+extern struct blkcg_policy blkcg_policy_bfq;
+#endif
+
+/* ------------- end of cgroups-support interface ------------- */
+
+/* - interface of the internal hierarchical B-WF2Q+ scheduler - */
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+/* both next loops stop at one of the child entities of the root group */
+#define for_each_entity(entity)	\
+	for (; entity ; entity = entity->parent)
+
+/*
+ * For each iteration, compute parent in advance, so as to be safe if
+ * entity is deallocated during the iteration. Such a deallocation may
+ * happen as a consequence of a bfq_put_queue that frees the bfq_queue
+ * containing entity.
+ */
+#define for_each_entity_safe(entity, parent) \
+	for (; entity && ({ parent = entity->parent; 1; }); entity = parent)
+
+#else /* CONFIG_BFQ_GROUP_IOSCHED */
+/*
+ * Next two macros are fake loops when cgroups support is not
+ * enabled. I fact, in such a case, there is only one level to go up
+ * (to reach the root group).
+ */
+#define for_each_entity(entity)	\
+	for (; entity ; entity = NULL)
+
+#define for_each_entity_safe(entity, parent) \
+	for (parent = NULL; entity ; entity = parent)
+#endif /* CONFIG_BFQ_GROUP_IOSCHED */
+
+struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq);
+struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);
+struct bfq_service_tree *bfq_entity_service_tree(struct bfq_entity *entity);
+struct bfq_entity *bfq_entity_of(struct rb_node *node);
+unsigned short bfq_ioprio_to_weight(int ioprio);
+void bfq_put_idle_entity(struct bfq_service_tree *st,
+			 struct bfq_entity *entity);
+struct bfq_service_tree *
+__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
+				struct bfq_entity *entity);
+void bfq_bfqq_served(struct bfq_queue *bfqq, int served);
+void bfq_bfqq_charge_time(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			  unsigned long time_ms);
+bool __bfq_deactivate_entity(struct bfq_entity *entity,
+			     bool ins_into_idle_tree);
+bool next_queue_may_preempt(struct bfq_data *bfqd);
+struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd);
+void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd);
+void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			 bool ins_into_idle_tree, bool expiration);
+void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		       bool expiration);
+void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq);
+
+/* --------------- end of interface of B-WF2Q+ ---------------- */
+
+/* Logging facilities. */
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
+
+#define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	do {			\
+	char __pbuf[128];						\
+									\
+	blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \
+	blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, (bfqq)->pid, \
+			bfq_bfqq_sync((bfqq)) ? 'S' : 'A',		\
+			  __pbuf, ##args);				\
+} while (0)
+
+#define bfq_log_bfqg(bfqd, bfqg, fmt, args...)	do {			\
+	char __pbuf[128];						\
+									\
+	blkg_path(bfqg_to_blkg(bfqg), __pbuf, sizeof(__pbuf));		\
+	blk_add_trace_msg((bfqd)->queue, "%s " fmt, __pbuf, ##args);	\
+} while (0)
+
+#else /* CONFIG_BFQ_GROUP_IOSCHED */
+
+#define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	\
+	blk_add_trace_msg((bfqd)->queue, "bfq%d%c " fmt, (bfqq)->pid,	\
+			bfq_bfqq_sync((bfqq)) ? 'S' : 'A',		\
+				##args)
+#define bfq_log_bfqg(bfqd, bfqg, fmt, args...)		do {} while (0)
+
+#endif /* CONFIG_BFQ_GROUP_IOSCHED */
+
+#define bfq_log(bfqd, fmt, args...) \
+	blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args)
+
+#endif /* _BFQ_H */

block/bfq-wf2q.c

@@ -0,0 +1,1616 @@
+/*
+ * Hierarchical Budget Worst-case Fair Weighted Fair Queueing
+ * (B-WF2Q+): hierarchical scheduling algorithm by which the BFQ I/O
+ * scheduler schedules generic entities. The latter can represent
+ * either single bfq queues (associated with processes) or groups of
+ * bfq queues (associated with cgroups).
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License as
+ *  published by the Free Software Foundation; either version 2 of the
+ *  License, or (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ */
+#include "bfq-iosched.h"
+
+/**
+ * bfq_gt - compare two timestamps.
+ * @a: first ts.
+ * @b: second ts.
+ *
+ * Return @a > @b, dealing with wrapping correctly.
+ */
+static int bfq_gt(u64 a, u64 b)
+{
+	return (s64)(a - b) > 0;
+}
+
+static struct bfq_entity *bfq_root_active_entity(struct rb_root *tree)
+{
+	struct rb_node *node = tree->rb_node;
+
+	return rb_entry(node, struct bfq_entity, rb_node);
+}
+
+static unsigned int bfq_class_idx(struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	return bfqq ? bfqq->ioprio_class - 1 :
+		BFQ_DEFAULT_GRP_CLASS - 1;
+}
+
+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd);
+
+static bool bfq_update_parent_budget(struct bfq_entity *next_in_service);
+
+/**
+ * bfq_update_next_in_service - update sd->next_in_service
+ * @sd: sched_data for which to perform the update.
+ * @new_entity: if not NULL, pointer to the entity whose activation,
+ *		requeueing or repositionig triggered the invocation of
+ *		this function.
+ *
+ * This function is called to update sd->next_in_service, which, in
+ * its turn, may change as a consequence of the insertion or
+ * extraction of an entity into/from one of the active trees of
+ * sd. These insertions/extractions occur as a consequence of
+ * activations/deactivations of entities, with some activations being
+ * 'true' activations, and other activations being requeueings (i.e.,
+ * implementing the second, requeueing phase of the mechanism used to
+ * reposition an entity in its active tree; see comments on
+ * __bfq_activate_entity and __bfq_requeue_entity for details). In
+ * both the last two activation sub-cases, new_entity points to the
+ * just activated or requeued entity.
+ *
+ * Returns true if sd->next_in_service changes in such a way that
+ * entity->parent may become the next_in_service for its parent
+ * entity.
+ */
+static bool bfq_update_next_in_service(struct bfq_sched_data *sd,
+				       struct bfq_entity *new_entity)
+{
+	struct bfq_entity *next_in_service = sd->next_in_service;
+	bool parent_sched_may_change = false;
+
+	/*
+	 * If this update is triggered by the activation, requeueing
+	 * or repositiong of an entity that does not coincide with
+	 * sd->next_in_service, then a full lookup in the active tree
+	 * can be avoided. In fact, it is enough to check whether the
+	 * just-modified entity has a higher priority than
+	 * sd->next_in_service, or, even if it has the same priority
+	 * as sd->next_in_service, is eligible and has a lower virtual
+	 * finish time than sd->next_in_service. If this compound
+	 * condition holds, then the new entity becomes the new
+	 * next_in_service. Otherwise no change is needed.
+	 */
+	if (new_entity && new_entity != sd->next_in_service) {
+		/*
+		 * Flag used to decide whether to replace
+		 * sd->next_in_service with new_entity. Tentatively
+		 * set to true, and left as true if
+		 * sd->next_in_service is NULL.
+		 */
+		bool replace_next = true;
+
+		/*
+		 * If there is already a next_in_service candidate
+		 * entity, then compare class priorities or timestamps
+		 * to decide whether to replace sd->service_tree with
+		 * new_entity.
+		 */
+		if (next_in_service) {
+			unsigned int new_entity_class_idx =
+				bfq_class_idx(new_entity);
+			struct bfq_service_tree *st =
+				sd->service_tree + new_entity_class_idx;
+
+			/*
+			 * For efficiency, evaluate the most likely
+			 * sub-condition first.
+			 */
+			replace_next =
+				(new_entity_class_idx ==
+				 bfq_class_idx(next_in_service)
+				 &&
+				 !bfq_gt(new_entity->start, st->vtime)
+				 &&
+				 bfq_gt(next_in_service->finish,
+					new_entity->finish))
+				||
+				new_entity_class_idx <
+				bfq_class_idx(next_in_service);
+		}
+
+		if (replace_next)
+			next_in_service = new_entity;
+	} else /* invoked because of a deactivation: lookup needed */
+		next_in_service = bfq_lookup_next_entity(sd);
+
+	if (next_in_service) {
+		parent_sched_may_change = !sd->next_in_service ||
+			bfq_update_parent_budget(next_in_service);
+	}
+
+	sd->next_in_service = next_in_service;
+
+	if (!next_in_service)
+		return parent_sched_may_change;
+
+	return parent_sched_may_change;
+}
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+
+struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
+{
+	struct bfq_entity *group_entity = bfqq->entity.parent;
+
+	if (!group_entity)
+		group_entity = &bfqq->bfqd->root_group->entity;
+
+	return container_of(group_entity, struct bfq_group, entity);
+}
+
+/*
+ * Returns true if this budget changes may let next_in_service->parent
+ * become the next_in_service entity for its parent entity.
+ */
+static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
+{
+	struct bfq_entity *bfqg_entity;
+	struct bfq_group *bfqg;
+	struct bfq_sched_data *group_sd;
+	bool ret = false;
+
+	group_sd = next_in_service->sched_data;
+
+	bfqg = container_of(group_sd, struct bfq_group, sched_data);
+	/*
+	 * bfq_group's my_entity field is not NULL only if the group
+	 * is not the root group. We must not touch the root entity
+	 * as it must never become an in-service entity.
+	 */
+	bfqg_entity = bfqg->my_entity;
+	if (bfqg_entity) {
+		if (bfqg_entity->budget > next_in_service->budget)
+			ret = true;
+		bfqg_entity->budget = next_in_service->budget;
+	}
+
+	return ret;
+}
+
+/*
+ * This function tells whether entity stops being a candidate for next
+ * service, according to the following logic.
+ *
+ * This function is invoked for an entity that is about to be set in
+ * service. If such an entity is a queue, then the entity is no longer
+ * a candidate for next service (i.e, a candidate entity to serve
+ * after the in-service entity is expired). The function then returns
+ * true.
+ *
+ * In contrast, the entity could stil be a candidate for next service
+ * if it is not a queue, and has more than one child. In fact, even if
+ * one of its children is about to be set in service, other children
+ * may still be the next to serve. As a consequence, a non-queue
+ * entity is not a candidate for next-service only if it has only one
+ * child. And only if this condition holds, then the function returns
+ * true for a non-queue entity.
+ */
+static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
+{
+	struct bfq_group *bfqg;
+
+	if (bfq_entity_to_bfqq(entity))
+		return true;
+
+	bfqg = container_of(entity, struct bfq_group, entity);
+
+	if (bfqg->active_entities == 1)
+		return true;
+
+	return false;
+}
+
+#else /* CONFIG_BFQ_GROUP_IOSCHED */
+
+struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq)
+{
+	return bfqq->bfqd->root_group;
+}
+
+static bool bfq_update_parent_budget(struct bfq_entity *next_in_service)
+{
+	return false;
+}
+
+static bool bfq_no_longer_next_in_service(struct bfq_entity *entity)
+{
+	return true;
+}
+
+#endif /* CONFIG_BFQ_GROUP_IOSCHED */
+
+/*
+ * Shift for timestamp calculations.  This actually limits the maximum
+ * service allowed in one timestamp delta (small shift values increase it),
+ * the maximum total weight that can be used for the queues in the system
+ * (big shift values increase it), and the period of virtual time
+ * wraparounds.
+ */
+#define WFQ_SERVICE_SHIFT	22
+
+struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = NULL;
+
+	if (!entity->my_sched_data)
+		bfqq = container_of(entity, struct bfq_queue, entity);
+
+	return bfqq;
+}
+
+
+/**
+ * bfq_delta - map service into the virtual time domain.
+ * @service: amount of service.
+ * @weight: scale factor (weight of an entity or weight sum).
+ */
+static u64 bfq_delta(unsigned long service, unsigned long weight)
+{
+	u64 d = (u64)service << WFQ_SERVICE_SHIFT;
+
+	do_div(d, weight);
+	return d;
+}
+
+/**
+ * bfq_calc_finish - assign the finish time to an entity.
+ * @entity: the entity to act upon.
+ * @service: the service to be charged to the entity.
+ */
+static void bfq_calc_finish(struct bfq_entity *entity, unsigned long service)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	entity->finish = entity->start +
+		bfq_delta(service, entity->weight);
+
+	if (bfqq) {
+		bfq_log_bfqq(bfqq->bfqd, bfqq,
+			"calc_finish: serv %lu, w %d",
+			service, entity->weight);
+		bfq_log_bfqq(bfqq->bfqd, bfqq,
+			"calc_finish: start %llu, finish %llu, delta %llu",
+			entity->start, entity->finish,
+			bfq_delta(service, entity->weight));
+	}
+}
+
+/**
+ * bfq_entity_of - get an entity from a node.
+ * @node: the node field of the entity.
+ *
+ * Convert a node pointer to the relative entity.  This is used only
+ * to simplify the logic of some functions and not as the generic
+ * conversion mechanism because, e.g., in the tree walking functions,
+ * the check for a %NULL value would be redundant.
+ */
+struct bfq_entity *bfq_entity_of(struct rb_node *node)
+{
+	struct bfq_entity *entity = NULL;
+
+	if (node)
+		entity = rb_entry(node, struct bfq_entity, rb_node);
+
+	return entity;
+}
+
+/**
+ * bfq_extract - remove an entity from a tree.
+ * @root: the tree root.
+ * @entity: the entity to remove.
+ */
+static void bfq_extract(struct rb_root *root, struct bfq_entity *entity)
+{
+	entity->tree = NULL;
+	rb_erase(&entity->rb_node, root);
+}
+
+/**
+ * bfq_idle_extract - extract an entity from the idle tree.
+ * @st: the service tree of the owning @entity.
+ * @entity: the entity being removed.
+ */
+static void bfq_idle_extract(struct bfq_service_tree *st,
+			     struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	struct rb_node *next;
+
+	if (entity == st->first_idle) {
+		next = rb_next(&entity->rb_node);
+		st->first_idle = bfq_entity_of(next);
+	}
+
+	if (entity == st->last_idle) {
+		next = rb_prev(&entity->rb_node);
+		st->last_idle = bfq_entity_of(next);
+	}
+
+	bfq_extract(&st->idle, entity);
+
+	if (bfqq)
+		list_del(&bfqq->bfqq_list);
+}
+
+/**
+ * bfq_insert - generic tree insertion.
+ * @root: tree root.
+ * @entity: entity to insert.
+ *
+ * This is used for the idle and the active tree, since they are both
+ * ordered by finish time.
+ */
+static void bfq_insert(struct rb_root *root, struct bfq_entity *entity)
+{
+	struct bfq_entity *entry;
+	struct rb_node **node = &root->rb_node;
+	struct rb_node *parent = NULL;
+
+	while (*node) {
+		parent = *node;
+		entry = rb_entry(parent, struct bfq_entity, rb_node);
+
+		if (bfq_gt(entry->finish, entity->finish))
+			node = &parent->rb_left;
+		else
+			node = &parent->rb_right;
+	}
+
+	rb_link_node(&entity->rb_node, parent, node);
+	rb_insert_color(&entity->rb_node, root);
+
+	entity->tree = root;
+}
+
+/**
+ * bfq_update_min - update the min_start field of a entity.
+ * @entity: the entity to update.
+ * @node: one of its children.
+ *
+ * This function is called when @entity may store an invalid value for
+ * min_start due to updates to the active tree.  The function  assumes
+ * that the subtree rooted at @node (which may be its left or its right
+ * child) has a valid min_start value.
+ */
+static void bfq_update_min(struct bfq_entity *entity, struct rb_node *node)
+{
+	struct bfq_entity *child;
+
+	if (node) {
+		child = rb_entry(node, struct bfq_entity, rb_node);
+		if (bfq_gt(entity->min_start, child->min_start))
+			entity->min_start = child->min_start;
+	}
+}
+
+/**
+ * bfq_update_active_node - recalculate min_start.
+ * @node: the node to update.
+ *
+ * @node may have changed position or one of its children may have moved,
+ * this function updates its min_start value.  The left and right subtrees
+ * are assumed to hold a correct min_start value.
+ */
+static void bfq_update_active_node(struct rb_node *node)
+{
+	struct bfq_entity *entity = rb_entry(node, struct bfq_entity, rb_node);
+
+	entity->min_start = entity->start;
+	bfq_update_min(entity, node->rb_right);
+	bfq_update_min(entity, node->rb_left);
+}
+
+/**
+ * bfq_update_active_tree - update min_start for the whole active tree.
+ * @node: the starting node.
+ *
+ * @node must be the deepest modified node after an update.  This function
+ * updates its min_start using the values held by its children, assuming
+ * that they did not change, and then updates all the nodes that may have
+ * changed in the path to the root.  The only nodes that may have changed
+ * are the ones in the path or their siblings.
+ */
+static void bfq_update_active_tree(struct rb_node *node)
+{
+	struct rb_node *parent;
+
+up:
+	bfq_update_active_node(node);
+
+	parent = rb_parent(node);
+	if (!parent)
+		return;
+
+	if (node == parent->rb_left && parent->rb_right)
+		bfq_update_active_node(parent->rb_right);
+	else if (parent->rb_left)
+		bfq_update_active_node(parent->rb_left);
+
+	node = parent;
+	goto up;
+}
+
+/**
+ * bfq_active_insert - insert an entity in the active tree of its
+ *                     group/device.
+ * @st: the service tree of the entity.
+ * @entity: the entity being inserted.
+ *
+ * The active tree is ordered by finish time, but an extra key is kept
+ * per each node, containing the minimum value for the start times of
+ * its children (and the node itself), so it's possible to search for
+ * the eligible node with the lowest finish time in logarithmic time.
+ */
+static void bfq_active_insert(struct bfq_service_tree *st,
+			      struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	struct rb_node *node = &entity->rb_node;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	struct bfq_sched_data *sd = NULL;
+	struct bfq_group *bfqg = NULL;
+	struct bfq_data *bfqd = NULL;
+#endif
+
+	bfq_insert(&st->active, entity);
+
+	if (node->rb_left)
+		node = node->rb_left;
+	else if (node->rb_right)
+		node = node->rb_right;
+
+	bfq_update_active_tree(node);
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	sd = entity->sched_data;
+	bfqg = container_of(sd, struct bfq_group, sched_data);
+	bfqd = (struct bfq_data *)bfqg->bfqd;
+#endif
+	if (bfqq)
+		list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	else /* bfq_group */
+		bfq_weights_tree_add(bfqd, entity, &bfqd->group_weights_tree);
+
+	if (bfqg != bfqd->root_group)
+		bfqg->active_entities++;
+#endif
+}
+
+/**
+ * bfq_ioprio_to_weight - calc a weight from an ioprio.
+ * @ioprio: the ioprio value to convert.
+ */
+unsigned short bfq_ioprio_to_weight(int ioprio)
+{
+	return (IOPRIO_BE_NR - ioprio) * BFQ_WEIGHT_CONVERSION_COEFF;
+}
+
+/**
+ * bfq_weight_to_ioprio - calc an ioprio from a weight.
+ * @weight: the weight value to convert.
+ *
+ * To preserve as much as possible the old only-ioprio user interface,
+ * 0 is used as an escape ioprio value for weights (numerically) equal or
+ * larger than IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF.
+ */
+static unsigned short bfq_weight_to_ioprio(int weight)
+{
+	return max_t(int, 0,
+		     IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF - weight);
+}
+
+static void bfq_get_entity(struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	if (bfqq) {
+		bfqq->ref++;
+		bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d",
+			     bfqq, bfqq->ref);
+	}
+}
+
+/**
+ * bfq_find_deepest - find the deepest node that an extraction can modify.
+ * @node: the node being removed.
+ *
+ * Do the first step of an extraction in an rb tree, looking for the
+ * node that will replace @node, and returning the deepest node that
+ * the following modifications to the tree can touch.  If @node is the
+ * last node in the tree return %NULL.
+ */
+static struct rb_node *bfq_find_deepest(struct rb_node *node)
+{
+	struct rb_node *deepest;
+
+	if (!node->rb_right && !node->rb_left)
+		deepest = rb_parent(node);
+	else if (!node->rb_right)
+		deepest = node->rb_left;
+	else if (!node->rb_left)
+		deepest = node->rb_right;
+	else {
+		deepest = rb_next(node);
+		if (deepest->rb_right)
+			deepest = deepest->rb_right;
+		else if (rb_parent(deepest) != node)
+			deepest = rb_parent(deepest);
+	}
+
+	return deepest;
+}
+
+/**
+ * bfq_active_extract - remove an entity from the active tree.
+ * @st: the service_tree containing the tree.
+ * @entity: the entity being removed.
+ */
+static void bfq_active_extract(struct bfq_service_tree *st,
+			       struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	struct rb_node *node;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	struct bfq_sched_data *sd = NULL;
+	struct bfq_group *bfqg = NULL;
+	struct bfq_data *bfqd = NULL;
+#endif
+
+	node = bfq_find_deepest(&entity->rb_node);
+	bfq_extract(&st->active, entity);
+
+	if (node)
+		bfq_update_active_tree(node);
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	sd = entity->sched_data;
+	bfqg = container_of(sd, struct bfq_group, sched_data);
+	bfqd = (struct bfq_data *)bfqg->bfqd;
+#endif
+	if (bfqq)
+		list_del(&bfqq->bfqq_list);
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+	else /* bfq_group */
+		bfq_weights_tree_remove(bfqd, entity,
+					&bfqd->group_weights_tree);
+
+	if (bfqg != bfqd->root_group)
+		bfqg->active_entities--;
+#endif
+}
+
+/**
+ * bfq_idle_insert - insert an entity into the idle tree.
+ * @st: the service tree containing the tree.
+ * @entity: the entity to insert.
+ */
+static void bfq_idle_insert(struct bfq_service_tree *st,
+			    struct bfq_entity *entity)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+	struct bfq_entity *first_idle = st->first_idle;
+	struct bfq_entity *last_idle = st->last_idle;
+
+	if (!first_idle || bfq_gt(first_idle->finish, entity->finish))
+		st->first_idle = entity;
+	if (!last_idle || bfq_gt(entity->finish, last_idle->finish))
+		st->last_idle = entity;
+
+	bfq_insert(&st->idle, entity);
+
+	if (bfqq)
+		list_add(&bfqq->bfqq_list, &bfqq->bfqd->idle_list);
+}
+
+/**
+ * bfq_forget_entity - do not consider entity any longer for scheduling
+ * @st: the service tree.
+ * @entity: the entity being removed.
+ * @is_in_service: true if entity is currently the in-service entity.
+ *
+ * Forget everything about @entity. In addition, if entity represents
+ * a queue, and the latter is not in service, then release the service
+ * reference to the queue (the one taken through bfq_get_entity). In
+ * fact, in this case, there is really no more service reference to
+ * the queue, as the latter is also outside any service tree. If,
+ * instead, the queue is in service, then __bfq_bfqd_reset_in_service
+ * will take care of putting the reference when the queue finally
+ * stops being served.
+ */
+static void bfq_forget_entity(struct bfq_service_tree *st,
+			      struct bfq_entity *entity,
+			      bool is_in_service)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	entity->on_st = false;
+	st->wsum -= entity->weight;
+	if (bfqq && !is_in_service)
+		bfq_put_queue(bfqq);
+}
+
+/**
+ * bfq_put_idle_entity - release the idle tree ref of an entity.
+ * @st: service tree for the entity.
+ * @entity: the entity being released.
+ */
+void bfq_put_idle_entity(struct bfq_service_tree *st, struct bfq_entity *entity)
+{
+	bfq_idle_extract(st, entity);
+	bfq_forget_entity(st, entity,
+			  entity == entity->sched_data->in_service_entity);
+}
+
+/**
+ * bfq_forget_idle - update the idle tree if necessary.
+ * @st: the service tree to act upon.
+ *
+ * To preserve the global O(log N) complexity we only remove one entry here;
+ * as the idle tree will not grow indefinitely this can be done safely.
+ */
+static void bfq_forget_idle(struct bfq_service_tree *st)
+{
+	struct bfq_entity *first_idle = st->first_idle;
+	struct bfq_entity *last_idle = st->last_idle;
+
+	if (RB_EMPTY_ROOT(&st->active) && last_idle &&
+	    !bfq_gt(last_idle->finish, st->vtime)) {
+		/*
+		 * Forget the whole idle tree, increasing the vtime past
+		 * the last finish time of idle entities.
+		 */
+		st->vtime = last_idle->finish;
+	}
+
+	if (first_idle && !bfq_gt(first_idle->finish, st->vtime))
+		bfq_put_idle_entity(st, first_idle);
+}
+
+struct bfq_service_tree *bfq_entity_service_tree(struct bfq_entity *entity)
+{
+	struct bfq_sched_data *sched_data = entity->sched_data;
+	unsigned int idx = bfq_class_idx(entity);
+
+	return sched_data->service_tree + idx;
+}
+
+
+struct bfq_service_tree *
+__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
+				struct bfq_entity *entity)
+{
+	struct bfq_service_tree *new_st = old_st;
+
+	if (entity->prio_changed) {
+		struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+		unsigned int prev_weight, new_weight;
+		struct bfq_data *bfqd = NULL;
+		struct rb_root *root;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+		struct bfq_sched_data *sd;
+		struct bfq_group *bfqg;
+#endif
+
+		if (bfqq)
+			bfqd = bfqq->bfqd;
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+		else {
+			sd = entity->my_sched_data;
+			bfqg = container_of(sd, struct bfq_group, sched_data);
+			bfqd = (struct bfq_data *)bfqg->bfqd;
+		}
+#endif
+
+		old_st->wsum -= entity->weight;
+
+		if (entity->new_weight != entity->orig_weight) {
+			if (entity->new_weight < BFQ_MIN_WEIGHT ||
+			    entity->new_weight > BFQ_MAX_WEIGHT) {
+				pr_crit("update_weight_prio: new_weight %d\n",
+					entity->new_weight);
+				if (entity->new_weight < BFQ_MIN_WEIGHT)
+					entity->new_weight = BFQ_MIN_WEIGHT;
+				else
+					entity->new_weight = BFQ_MAX_WEIGHT;
+			}
+			entity->orig_weight = entity->new_weight;
+			if (bfqq)
+				bfqq->ioprio =
+				  bfq_weight_to_ioprio(entity->orig_weight);
+		}
+
+		if (bfqq)
+			bfqq->ioprio_class = bfqq->new_ioprio_class;
+		entity->prio_changed = 0;
+
+		/*
+		 * NOTE: here we may be changing the weight too early,
+		 * this will cause unfairness.  The correct approach
+		 * would have required additional complexity to defer
+		 * weight changes to the proper time instants (i.e.,
+		 * when entity->finish <= old_st->vtime).
+		 */
+		new_st = bfq_entity_service_tree(entity);
+
+		prev_weight = entity->weight;
+		new_weight = entity->orig_weight *
+			     (bfqq ? bfqq->wr_coeff : 1);
+		/*
+		 * If the weight of the entity changes, remove the entity
+		 * from its old weight counter (if there is a counter
+		 * associated with the entity), and add it to the counter
+		 * associated with its new weight.
+		 */
+		if (prev_weight != new_weight) {
+			root = bfqq ? &bfqd->queue_weights_tree :
+				      &bfqd->group_weights_tree;
+			bfq_weights_tree_remove(bfqd, entity, root);
+		}
+		entity->weight = new_weight;
+		/*
+		 * Add the entity to its weights tree only if it is
+		 * not associated with a weight-raised queue.
+		 */
+		if (prev_weight != new_weight &&
+		    (bfqq ? bfqq->wr_coeff == 1 : 1))
+			/* If we get here, root has been initialized. */
+			bfq_weights_tree_add(bfqd, entity, root);
+
+		new_st->wsum += entity->weight;
+
+		if (new_st != old_st)
+			entity->start = new_st->vtime;
+	}
+
+	return new_st;
+}
+
+/**
+ * bfq_bfqq_served - update the scheduler status after selection for
+ *                   service.
+ * @bfqq: the queue being served.
+ * @served: bytes to transfer.
+ *
+ * NOTE: this can be optimized, as the timestamps of upper level entities
+ * are synchronized every time a new bfqq is selected for service.  By now,
+ * we keep it to better check consistency.
+ */
+void bfq_bfqq_served(struct bfq_queue *bfqq, int served)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+	struct bfq_service_tree *st;
+
+	for_each_entity(entity) {
+		st = bfq_entity_service_tree(entity);
+
+		entity->service += served;
+
+		st->vtime += bfq_delta(served, st->wsum);
+		bfq_forget_idle(st);
+	}
+	bfqg_stats_set_start_empty_time(bfqq_group(bfqq));
+	bfq_log_bfqq(bfqq->bfqd, bfqq, "bfqq_served %d secs", served);
+}
+
+/**
+ * bfq_bfqq_charge_time - charge an amount of service equivalent to the length
+ *			  of the time interval during which bfqq has been in
+ *			  service.
+ * @bfqd: the device
+ * @bfqq: the queue that needs a service update.
+ * @time_ms: the amount of time during which the queue has received service
+ *
+ * If a queue does not consume its budget fast enough, then providing
+ * the queue with service fairness may impair throughput, more or less
+ * severely. For this reason, queues that consume their budget slowly
+ * are provided with time fairness instead of service fairness. This
+ * goal is achieved through the BFQ scheduling engine, even if such an
+ * engine works in the service, and not in the time domain. The trick
+ * is charging these queues with an inflated amount of service, equal
+ * to the amount of service that they would have received during their
+ * service slot if they had been fast, i.e., if their requests had
+ * been dispatched at a rate equal to the estimated peak rate.
+ *
+ * It is worth noting that time fairness can cause important
+ * distortions in terms of bandwidth distribution, on devices with
+ * internal queueing. The reason is that I/O requests dispatched
+ * during the service slot of a queue may be served after that service
+ * slot is finished, and may have a total processing time loosely
+ * correlated with the duration of the service slot. This is
+ * especially true for short service slots.
+ */
+void bfq_bfqq_charge_time(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			  unsigned long time_ms)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+	int tot_serv_to_charge = entity->service;
+	unsigned int timeout_ms = jiffies_to_msecs(bfq_timeout);
+
+	if (time_ms > 0 && time_ms < timeout_ms)
+		tot_serv_to_charge =
+			(bfqd->bfq_max_budget * time_ms) / timeout_ms;
+
+	if (tot_serv_to_charge < entity->service)
+		tot_serv_to_charge = entity->service;
+
+	/* Increase budget to avoid inconsistencies */
+	if (tot_serv_to_charge > entity->budget)
+		entity->budget = tot_serv_to_charge;
+
+	bfq_bfqq_served(bfqq,
+			max_t(int, 0, tot_serv_to_charge - entity->service));
+}
+
+static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
+					struct bfq_service_tree *st,
+					bool backshifted)
+{
+	struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity);
+
+	st = __bfq_entity_update_weight_prio(st, entity);
+	bfq_calc_finish(entity, entity->budget);
+
+	/*
+	 * If some queues enjoy backshifting for a while, then their
+	 * (virtual) finish timestamps may happen to become lower and
+	 * lower than the system virtual time.	In particular, if
+	 * these queues often happen to be idle for short time
+	 * periods, and during such time periods other queues with
+	 * higher timestamps happen to be busy, then the backshifted
+	 * timestamps of the former queues can become much lower than
+	 * the system virtual time. In fact, to serve the queues with
+	 * higher timestamps while the ones with lower timestamps are
+	 * idle, the system virtual time may be pushed-up to much
+	 * higher values than the finish timestamps of the idle
+	 * queues. As a consequence, the finish timestamps of all new
+	 * or newly activated queues may end up being much larger than
+	 * those of lucky queues with backshifted timestamps. The
+	 * latter queues may then monopolize the device for a lot of
+	 * time. This would simply break service guarantees.
+	 *
+	 * To reduce this problem, push up a little bit the
+	 * backshifted timestamps of the queue associated with this
+	 * entity (only a queue can happen to have the backshifted
+	 * flag set): just enough to let the finish timestamp of the
+	 * queue be equal to the current value of the system virtual
+	 * time. This may introduce a little unfairness among queues
+	 * with backshifted timestamps, but it does not break
+	 * worst-case fairness guarantees.
+	 *
+	 * As a special case, if bfqq is weight-raised, push up
+	 * timestamps much less, to keep very low the probability that
+	 * this push up causes the backshifted finish timestamps of
+	 * weight-raised queues to become higher than the backshifted
+	 * finish timestamps of non weight-raised queues.
+	 */
+	if (backshifted && bfq_gt(st->vtime, entity->finish)) {
+		unsigned long delta = st->vtime - entity->finish;
+
+		if (bfqq)
+			delta /= bfqq->wr_coeff;
+
+		entity->start += delta;
+		entity->finish += delta;
+	}
+
+	bfq_active_insert(st, entity);
+}
+
+/**
+ * __bfq_activate_entity - handle activation of entity.
+ * @entity: the entity being activated.
+ * @non_blocking_wait_rq: true if entity was waiting for a request
+ *
+ * Called for a 'true' activation, i.e., if entity is not active and
+ * one of its children receives a new request.
+ *
+ * Basically, this function updates the timestamps of entity and
+ * inserts entity into its active tree, ater possible extracting it
+ * from its idle tree.
+ */
+static void __bfq_activate_entity(struct bfq_entity *entity,
+				  bool non_blocking_wait_rq)
+{
+	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+	bool backshifted = false;
+	unsigned long long min_vstart;
+
+	/* See comments on bfq_fqq_update_budg_for_activation */
+	if (non_blocking_wait_rq && bfq_gt(st->vtime, entity->finish)) {
+		backshifted = true;
+		min_vstart = entity->finish;
+	} else
+		min_vstart = st->vtime;
+
+	if (entity->tree == &st->idle) {
+		/*
+		 * Must be on the idle tree, bfq_idle_extract() will
+		 * check for that.
+		 */
+		bfq_idle_extract(st, entity);
+		entity->start = bfq_gt(min_vstart, entity->finish) ?
+			min_vstart : entity->finish;
+	} else {
+		/*
+		 * The finish time of the entity may be invalid, and
+		 * it is in the past for sure, otherwise the queue
+		 * would have been on the idle tree.
+		 */
+		entity->start = min_vstart;
+		st->wsum += entity->weight;
+		/*
+		 * entity is about to be inserted into a service tree,
+		 * and then set in service: get a reference to make
+		 * sure entity does not disappear until it is no
+		 * longer in service or scheduled for service.
+		 */
+		bfq_get_entity(entity);
+
+		entity->on_st = true;
+	}
+
+	bfq_update_fin_time_enqueue(entity, st, backshifted);
+}
+
+/**
+ * __bfq_requeue_entity - handle requeueing or repositioning of an entity.
+ * @entity: the entity being requeued or repositioned.
+ *
+ * Requeueing is needed if this entity stops being served, which
+ * happens if a leaf descendant entity has expired. On the other hand,
+ * repositioning is needed if the next_inservice_entity for the child
+ * entity has changed. See the comments inside the function for
+ * details.
+ *
+ * Basically, this function: 1) removes entity from its active tree if
+ * present there, 2) updates the timestamps of entity and 3) inserts
+ * entity back into its active tree (in the new, right position for
+ * the new values of the timestamps).
+ */
+static void __bfq_requeue_entity(struct bfq_entity *entity)
+{
+	struct bfq_sched_data *sd = entity->sched_data;
+	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+
+	if (entity == sd->in_service_entity) {
+		/*
+		 * We are requeueing the current in-service entity,
+		 * which may have to be done for one of the following
+		 * reasons:
+		 * - entity represents the in-service queue, and the
+		 *   in-service queue is being requeued after an
+		 *   expiration;
+		 * - entity represents a group, and its budget has
+		 *   changed because one of its child entities has
+		 *   just been either activated or requeued for some
+		 *   reason; the timestamps of the entity need then to
+		 *   be updated, and the entity needs to be enqueued
+		 *   or repositioned accordingly.
+		 *
+		 * In particular, before requeueing, the start time of
+		 * the entity must be moved forward to account for the
+		 * service that the entity has received while in
+		 * service. This is done by the next instructions. The
+		 * finish time will then be updated according to this
+		 * new value of the start time, and to the budget of
+		 * the entity.
+		 */
+		bfq_calc_finish(entity, entity->service);
+		entity->start = entity->finish;
+		/*
+		 * In addition, if the entity had more than one child
+		 * when set in service, then was not extracted from
+		 * the active tree. This implies that the position of
+		 * the entity in the active tree may need to be
+		 * changed now, because we have just updated the start
+		 * time of the entity, and we will update its finish
+		 * time in a moment (the requeueing is then, more
+		 * precisely, a repositioning in this case). To
+		 * implement this repositioning, we: 1) dequeue the
+		 * entity here, 2) update the finish time and
+		 * requeue the entity according to the new
+		 * timestamps below.
+		 */
+		if (entity->tree)
+			bfq_active_extract(st, entity);
+	} else { /* The entity is already active, and not in service */
+		/*
+		 * In this case, this function gets called only if the
+		 * next_in_service entity below this entity has
+		 * changed, and this change has caused the budget of
+		 * this entity to change, which, finally implies that
+		 * the finish time of this entity must be
+		 * updated. Such an update may cause the scheduling,
+		 * i.e., the position in the active tree, of this
+		 * entity to change. We handle this change by: 1)
+		 * dequeueing the entity here, 2) updating the finish
+		 * time and requeueing the entity according to the new
+		 * timestamps below. This is the same approach as the
+		 * non-extracted-entity sub-case above.
+		 */
+		bfq_active_extract(st, entity);
+	}
+
+	bfq_update_fin_time_enqueue(entity, st, false);
+}
+
+static void __bfq_activate_requeue_entity(struct bfq_entity *entity,
+					  struct bfq_sched_data *sd,
+					  bool non_blocking_wait_rq)
+{
+	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+
+	if (sd->in_service_entity == entity || entity->tree == &st->active)
+		 /*
+		  * in service or already queued on the active tree,
+		  * requeue or reposition
+		  */
+		__bfq_requeue_entity(entity);
+	else
+		/*
+		 * Not in service and not queued on its active tree:
+		 * the activity is idle and this is a true activation.
+		 */
+		__bfq_activate_entity(entity, non_blocking_wait_rq);
+}
+
+
+/**
+ * bfq_activate_entity - activate or requeue an entity representing a bfq_queue,
+ *			 and activate, requeue or reposition all ancestors
+ *			 for which such an update becomes necessary.
+ * @entity: the entity to activate.
+ * @non_blocking_wait_rq: true if this entity was waiting for a request
+ * @requeue: true if this is a requeue, which implies that bfqq is
+ *	     being expired; thus ALL its ancestors stop being served and must
+ *	     therefore be requeued
+ */
+static void bfq_activate_requeue_entity(struct bfq_entity *entity,
+					bool non_blocking_wait_rq,
+					bool requeue)
+{
+	struct bfq_sched_data *sd;
+
+	for_each_entity(entity) {
+		sd = entity->sched_data;
+		__bfq_activate_requeue_entity(entity, sd, non_blocking_wait_rq);
+
+		if (!bfq_update_next_in_service(sd, entity) && !requeue)
+			break;
+	}
+}
+
+/**
+ * __bfq_deactivate_entity - deactivate an entity from its service tree.
+ * @entity: the entity to deactivate.
+ * @ins_into_idle_tree: if false, the entity will not be put into the
+ *			idle tree.
+ *
+ * Deactivates an entity, independently from its previous state.  Must
+ * be invoked only if entity is on a service tree. Extracts the entity
+ * from that tree, and if necessary and allowed, puts it on the idle
+ * tree.
+ */
+bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree)
+{
+	struct bfq_sched_data *sd = entity->sched_data;
+	struct bfq_service_tree *st = bfq_entity_service_tree(entity);
+	int is_in_service = entity == sd->in_service_entity;
+
+	if (!entity->on_st) /* entity never activated, or already inactive */
+		return false;
+
+	if (is_in_service)
+		bfq_calc_finish(entity, entity->service);
+
+	if (entity->tree == &st->active)
+		bfq_active_extract(st, entity);
+	else if (!is_in_service && entity->tree == &st->idle)
+		bfq_idle_extract(st, entity);
+
+	if (!ins_into_idle_tree || !bfq_gt(entity->finish, st->vtime))
+		bfq_forget_entity(st, entity, is_in_service);
+	else
+		bfq_idle_insert(st, entity);
+
+	return true;
+}
+
+/**
+ * bfq_deactivate_entity - deactivate an entity representing a bfq_queue.
+ * @entity: the entity to deactivate.
+ * @ins_into_idle_tree: true if the entity can be put on the idle tree
+ */
+static void bfq_deactivate_entity(struct bfq_entity *entity,
+				  bool ins_into_idle_tree,
+				  bool expiration)
+{
+	struct bfq_sched_data *sd;
+	struct bfq_entity *parent = NULL;
+
+	for_each_entity_safe(entity, parent) {
+		sd = entity->sched_data;
+
+		if (!__bfq_deactivate_entity(entity, ins_into_idle_tree)) {
+			/*
+			 * entity is not in any tree any more, so
+			 * this deactivation is a no-op, and there is
+			 * nothing to change for upper-level entities
+			 * (in case of expiration, this can never
+			 * happen).
+			 */
+			return;
+		}
+
+		if (sd->next_in_service == entity)
+			/*
+			 * entity was the next_in_service entity,
+			 * then, since entity has just been
+			 * deactivated, a new one must be found.
+			 */
+			bfq_update_next_in_service(sd, NULL);
+
+		if (sd->next_in_service)
+			/*
+			 * The parent entity is still backlogged,
+			 * because next_in_service is not NULL. So, no
+			 * further upwards deactivation must be
+			 * performed.  Yet, next_in_service has
+			 * changed.  Then the schedule does need to be
+			 * updated upwards.
+			 */
+			break;
+
+		/*
+		 * If we get here, then the parent is no more
+		 * backlogged and we need to propagate the
+		 * deactivation upwards. Thus let the loop go on.
+		 */
+
+		/*
+		 * Also let parent be queued into the idle tree on
+		 * deactivation, to preserve service guarantees, and
+		 * assuming that who invoked this function does not
+		 * need parent entities too to be removed completely.
+		 */
+		ins_into_idle_tree = true;
+	}
+
+	/*
+	 * If the deactivation loop is fully executed, then there are
+	 * no more entities to touch and next loop is not executed at
+	 * all. Otherwise, requeue remaining entities if they are
+	 * about to stop receiving service, or reposition them if this
+	 * is not the case.
+	 */
+	entity = parent;
+	for_each_entity(entity) {
+		/*
+		 * Invoke __bfq_requeue_entity on entity, even if
+		 * already active, to requeue/reposition it in the
+		 * active tree (because sd->next_in_service has
+		 * changed)
+		 */
+		__bfq_requeue_entity(entity);
+
+		sd = entity->sched_data;
+		if (!bfq_update_next_in_service(sd, entity) &&
+		    !expiration)
+			/*
+			 * next_in_service unchanged or not causing
+			 * any change in entity->parent->sd, and no
+			 * requeueing needed for expiration: stop
+			 * here.
+			 */
+			break;
+	}
+}
+
+/**
+ * bfq_calc_vtime_jump - compute the value to which the vtime should jump,
+ *                       if needed, to have at least one entity eligible.
+ * @st: the service tree to act upon.
+ *
+ * Assumes that st is not empty.
+ */
+static u64 bfq_calc_vtime_jump(struct bfq_service_tree *st)
+{
+	struct bfq_entity *root_entity = bfq_root_active_entity(&st->active);
+
+	if (bfq_gt(root_entity->min_start, st->vtime))
+		return root_entity->min_start;
+
+	return st->vtime;
+}
+
+static void bfq_update_vtime(struct bfq_service_tree *st, u64 new_value)
+{
+	if (new_value > st->vtime) {
+		st->vtime = new_value;
+		bfq_forget_idle(st);
+	}
+}
+
+/**
+ * bfq_first_active_entity - find the eligible entity with
+ *                           the smallest finish time
+ * @st: the service tree to select from.
+ * @vtime: the system virtual to use as a reference for eligibility
+ *
+ * This function searches the first schedulable entity, starting from the
+ * root of the tree and going on the left every time on this side there is
+ * a subtree with at least one eligible (start >= vtime) entity. The path on
+ * the right is followed only if a) the left subtree contains no eligible
+ * entities and b) no eligible entity has been found yet.
+ */
+static struct bfq_entity *bfq_first_active_entity(struct bfq_service_tree *st,
+						  u64 vtime)
+{
+	struct bfq_entity *entry, *first = NULL;
+	struct rb_node *node = st->active.rb_node;
+
+	while (node) {
+		entry = rb_entry(node, struct bfq_entity, rb_node);
+left:
+		if (!bfq_gt(entry->start, vtime))
+			first = entry;
+
+		if (node->rb_left) {
+			entry = rb_entry(node->rb_left,
+					 struct bfq_entity, rb_node);
+			if (!bfq_gt(entry->min_start, vtime)) {
+				node = node->rb_left;
+				goto left;
+			}
+		}
+		if (first)
+			break;
+		node = node->rb_right;
+	}
+
+	return first;
+}
+
+/**
+ * __bfq_lookup_next_entity - return the first eligible entity in @st.
+ * @st: the service tree.
+ *
+ * If there is no in-service entity for the sched_data st belongs to,
+ * then return the entity that will be set in service if:
+ * 1) the parent entity this st belongs to is set in service;
+ * 2) no entity belonging to such parent entity undergoes a state change
+ * that would influence the timestamps of the entity (e.g., becomes idle,
+ * becomes backlogged, changes its budget, ...).
+ *
+ * In this first case, update the virtual time in @st too (see the
+ * comments on this update inside the function).
+ *
+ * In constrast, if there is an in-service entity, then return the
+ * entity that would be set in service if not only the above
+ * conditions, but also the next one held true: the currently
+ * in-service entity, on expiration,
+ * 1) gets a finish time equal to the current one, or
+ * 2) is not eligible any more, or
+ * 3) is idle.
+ */
+static struct bfq_entity *
+__bfq_lookup_next_entity(struct bfq_service_tree *st, bool in_service)
+{
+	struct bfq_entity *entity;
+	u64 new_vtime;
+
+	if (RB_EMPTY_ROOT(&st->active))
+		return NULL;
+
+	/*
+	 * Get the value of the system virtual time for which at
+	 * least one entity is eligible.
+	 */
+	new_vtime = bfq_calc_vtime_jump(st);
+
+	/*
+	 * If there is no in-service entity for the sched_data this
+	 * active tree belongs to, then push the system virtual time
+	 * up to the value that guarantees that at least one entity is
+	 * eligible. If, instead, there is an in-service entity, then
+	 * do not make any such update, because there is already an
+	 * eligible entity, namely the in-service one (even if the
+	 * entity is not on st, because it was extracted when set in
+	 * service).
+	 */
+	if (!in_service)
+		bfq_update_vtime(st, new_vtime);
+
+	entity = bfq_first_active_entity(st, new_vtime);
+
+	return entity;
+}
+
+/**
+ * bfq_lookup_next_entity - return the first eligible entity in @sd.
+ * @sd: the sched_data.
+ *
+ * This function is invoked when there has been a change in the trees
+ * for sd, and we need know what is the new next entity after this
+ * change.
+ */
+static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd)
+{
+	struct bfq_service_tree *st = sd->service_tree;
+	struct bfq_service_tree *idle_class_st = st + (BFQ_IOPRIO_CLASSES - 1);
+	struct bfq_entity *entity = NULL;
+	int class_idx = 0;
+
+	/*
+	 * Choose from idle class, if needed to guarantee a minimum
+	 * bandwidth to this class (and if there is some active entity
+	 * in idle class). This should also mitigate
+	 * priority-inversion problems in case a low priority task is
+	 * holding file system resources.
+	 */
+	if (time_is_before_jiffies(sd->bfq_class_idle_last_service +
+				   BFQ_CL_IDLE_TIMEOUT)) {
+		if (!RB_EMPTY_ROOT(&idle_class_st->active))
+			class_idx = BFQ_IOPRIO_CLASSES - 1;
+		/* About to be served if backlogged, or not yet backlogged */
+		sd->bfq_class_idle_last_service = jiffies;
+	}
+
+	/*
+	 * Find the next entity to serve for the highest-priority
+	 * class, unless the idle class needs to be served.
+	 */
+	for (; class_idx < BFQ_IOPRIO_CLASSES; class_idx++) {
+		entity = __bfq_lookup_next_entity(st + class_idx,
+						  sd->in_service_entity);
+
+		if (entity)
+			break;
+	}
+
+	if (!entity)
+		return NULL;
+
+	return entity;
+}
+
+bool next_queue_may_preempt(struct bfq_data *bfqd)
+{
+	struct bfq_sched_data *sd = &bfqd->root_group->sched_data;
+
+	return sd->next_in_service != sd->in_service_entity;
+}
+
+/*
+ * Get next queue for service.
+ */
+struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
+{
+	struct bfq_entity *entity = NULL;
+	struct bfq_sched_data *sd;
+	struct bfq_queue *bfqq;
+
+	if (bfqd->busy_queues == 0)
+		return NULL;
+
+	/*
+	 * Traverse the path from the root to the leaf entity to
+	 * serve. Set in service all the entities visited along the
+	 * way.
+	 */
+	sd = &bfqd->root_group->sched_data;
+	for (; sd ; sd = entity->my_sched_data) {
+		/*
+		 * WARNING. We are about to set the in-service entity
+		 * to sd->next_in_service, i.e., to the (cached) value
+		 * returned by bfq_lookup_next_entity(sd) the last
+		 * time it was invoked, i.e., the last time when the
+		 * service order in sd changed as a consequence of the
+		 * activation or deactivation of an entity. In this
+		 * respect, if we execute bfq_lookup_next_entity(sd)
+		 * in this very moment, it may, although with low
+		 * probability, yield a different entity than that
+		 * pointed to by sd->next_in_service. This rare event
+		 * happens in case there was no CLASS_IDLE entity to
+		 * serve for sd when bfq_lookup_next_entity(sd) was
+		 * invoked for the last time, while there is now one
+		 * such entity.
+		 *
+		 * If the above event happens, then the scheduling of
+		 * such entity in CLASS_IDLE is postponed until the
+		 * service of the sd->next_in_service entity
+		 * finishes. In fact, when the latter is expired,
+		 * bfq_lookup_next_entity(sd) gets called again,
+		 * exactly to update sd->next_in_service.
+		 */
+
+		/* Make next_in_service entity become in_service_entity */
+		entity = sd->next_in_service;
+		sd->in_service_entity = entity;
+
+		/*
+		 * Reset the accumulator of the amount of service that
+		 * the entity is about to receive.
+		 */
+		entity->service = 0;
+
+		/*
+		 * If entity is no longer a candidate for next
+		 * service, then we extract it from its active tree,
+		 * for the following reason. To further boost the
+		 * throughput in some special case, BFQ needs to know
+		 * which is the next candidate entity to serve, while
+		 * there is already an entity in service. In this
+		 * respect, to make it easy to compute/update the next
+		 * candidate entity to serve after the current
+		 * candidate has been set in service, there is a case
+		 * where it is necessary to extract the current
+		 * candidate from its service tree. Such a case is
+		 * when the entity just set in service cannot be also
+		 * a candidate for next service. Details about when
+		 * this conditions holds are reported in the comments
+		 * on the function bfq_no_longer_next_in_service()
+		 * invoked below.
+		 */
+		if (bfq_no_longer_next_in_service(entity))
+			bfq_active_extract(bfq_entity_service_tree(entity),
+					   entity);
+
+		/*
+		 * For the same reason why we may have just extracted
+		 * entity from its active tree, we may need to update
+		 * next_in_service for the sched_data of entity too,
+		 * regardless of whether entity has been extracted.
+		 * In fact, even if entity has not been extracted, a
+		 * descendant entity may get extracted. Such an event
+		 * would cause a change in next_in_service for the
+		 * level of the descendant entity, and thus possibly
+		 * back to upper levels.
+		 *
+		 * We cannot perform the resulting needed update
+		 * before the end of this loop, because, to know which
+		 * is the correct next-to-serve candidate entity for
+		 * each level, we need first to find the leaf entity
+		 * to set in service. In fact, only after we know
+		 * which is the next-to-serve leaf entity, we can
+		 * discover whether the parent entity of the leaf
+		 * entity becomes the next-to-serve, and so on.
+		 */
+
+	}
+
+	bfqq = bfq_entity_to_bfqq(entity);
+
+	/*
+	 * We can finally update all next-to-serve entities along the
+	 * path from the leaf entity just set in service to the root.
+	 */
+	for_each_entity(entity) {
+		struct bfq_sched_data *sd = entity->sched_data;
+
+		if (!bfq_update_next_in_service(sd, NULL))
+			break;
+	}
+
+	return bfqq;
+}
+
+void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
+{
+	struct bfq_queue *in_serv_bfqq = bfqd->in_service_queue;
+	struct bfq_entity *in_serv_entity = &in_serv_bfqq->entity;
+	struct bfq_entity *entity = in_serv_entity;
+
+	bfq_clear_bfqq_wait_request(in_serv_bfqq);
+	hrtimer_try_to_cancel(&bfqd->idle_slice_timer);
+	bfqd->in_service_queue = NULL;
+
+	/*
+	 * When this function is called, all in-service entities have
+	 * been properly deactivated or requeued, so we can safely
+	 * execute the final step: reset in_service_entity along the
+	 * path from entity to the root.
+	 */
+	for_each_entity(entity)
+		entity->sched_data->in_service_entity = NULL;
+
+	/*
+	 * in_serv_entity is no longer in service, so, if it is in no
+	 * service tree either, then release the service reference to
+	 * the queue it represents (taken with bfq_get_entity).
+	 */
+	if (!in_serv_entity->on_st)
+		bfq_put_queue(in_serv_bfqq);
+}
+
+void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+			 bool ins_into_idle_tree, bool expiration)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	bfq_deactivate_entity(entity, ins_into_idle_tree, expiration);
+}
+
+void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	bfq_activate_requeue_entity(entity, bfq_bfqq_non_blocking_wait_rq(bfqq),
+				    false);
+	bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
+}
+
+void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = &bfqq->entity;
+
+	bfq_activate_requeue_entity(entity, false,
+				    bfqq == bfqd->in_service_queue);
+}
+
+/*
+ * Called when the bfqq no longer has requests pending, remove it from
+ * the service tree. As a special case, it can be invoked during an
+ * expiration.
+ */
+void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+		       bool expiration)
+{
+	bfq_log_bfqq(bfqd, bfqq, "del from busy");
+
+	bfq_clear_bfqq_busy(bfqq);
+
+	bfqd->busy_queues--;
+
+	if (!bfqq->dispatched)
+		bfq_weights_tree_remove(bfqd, &bfqq->entity,
+					&bfqd->queue_weights_tree);
+
+	if (bfqq->wr_coeff > 1)
+		bfqd->wr_busy_queues--;
+
+	bfqg_stats_update_dequeue(bfqq_group(bfqq));
+
+	bfq_deactivate_bfqq(bfqd, bfqq, true, expiration);
+}
+
+/*
+ * Called when an inactive queue receives a new request.
+ */
+void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+{
+	bfq_log_bfqq(bfqd, bfqq, "add to busy");
+
+	bfq_activate_bfqq(bfqd, bfqq);
+
+	bfq_mark_bfqq_busy(bfqq);
+	bfqd->busy_queues++;
+
+	if (!bfqq->dispatched)
+		if (bfqq->wr_coeff == 1)
+			bfq_weights_tree_add(bfqd, &bfqq->entity,
+					     &bfqd->queue_weights_tree);
+
+	if (bfqq->wr_coeff > 1)
+		bfqd->wr_busy_queues++;
+}

block/bio.c

@@ -30,6 +30,7 @@
 #include <linux/cgroup.h>
 
 #include <trace/events/block.h>
+#include "blk.h"
 
 /*
  * Test patch to inline a certain number of bi_io_vec's inside the bio
@@ -427,7 +428,8 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
  *   RETURNS:
  *   Pointer to new bio on success, NULL on failure.
  */
-struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
+struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
+			     struct bio_set *bs)
 {
 	gfp_t saved_gfp = gfp_mask;
 	unsigned front_pad;
@@ -1824,6 +1826,11 @@ static inline bool bio_remaining_done(struct bio *bio)
  *   bio_endio() will end I/O on the whole bio. bio_endio() is the preferred
  *   way to end I/O on a bio. No one should call bi_end_io() directly on a
  *   bio unless they own it and thus know that it has an end_io function.
+ *
+ *   bio_endio() can be called several times on a bio that has been chained
+ *   using bio_chain().  The ->bi_end_io() function will only be called the
+ *   last time.  At this point the BLK_TA_COMPLETE tracing event will be
+ *   generated if BIO_TRACE_COMPLETION is set.
  **/
 void bio_endio(struct bio *bio)
 {
@@ -1844,6 +1851,13 @@ again:
 		goto again;
 	}
 
+	if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
+		trace_block_bio_complete(bdev_get_queue(bio->bi_bdev),
+					 bio, bio->bi_error);
+		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
+	}
+
+	blk_throtl_bio_endio(bio);
 	if (bio->bi_end_io)
 		bio->bi_end_io(bio);
 }
@@ -1882,6 +1896,9 @@ struct bio *bio_split(struct bio *bio, int sectors,
 
 	bio_advance(bio, split->bi_iter.bi_size);
 
+	if (bio_flagged(bio, BIO_TRACE_COMPLETION))
+		bio_set_flag(bio, BIO_TRACE_COMPLETION);
+
 	return split;
 }
 EXPORT_SYMBOL(bio_split);

block/blk-cgroup.c

@@ -772,6 +772,27 @@ struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkcg_gq *blkg,
 }
 EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum);
 
+/* Performs queue bypass and policy enabled checks then looks up blkg. */
+static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg,
+					  const struct blkcg_policy *pol,
+					  struct request_queue *q)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	lockdep_assert_held(q->queue_lock);
+
+	if (!blkcg_policy_enabled(q, pol))
+		return ERR_PTR(-EOPNOTSUPP);
+
+	/*
+	 * This could be the first entry point of blkcg implementation and
+	 * we shouldn't allow anything to go through for a bypassing queue.
+	 */
+	if (unlikely(blk_queue_bypass(q)))
+		return ERR_PTR(blk_queue_dying(q) ? -ENODEV : -EBUSY);
+
+	return __blkg_lookup(blkcg, q, true /* update_hint */);
+}
+
 /**
  * blkg_conf_prep - parse and prepare for per-blkg config update
  * @blkcg: target block cgroup
@@ -789,6 +810,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	__acquires(rcu) __acquires(disk->queue->queue_lock)
 {
 	struct gendisk *disk;
+	struct request_queue *q;
 	struct blkcg_gq *blkg;
 	struct module *owner;
 	unsigned int major, minor;
@@ -807,44 +829,95 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
 	if (!disk)
 		return -ENODEV;
 	if (part) {
-		owner = disk->fops->owner;
-		put_disk(disk);
-		module_put(owner);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto fail;
 	}
 
-	rcu_read_lock();
-	spin_lock_irq(disk->queue->queue_lock);
+	q = disk->queue;
 
-	if (blkcg_policy_enabled(disk->queue, pol))
-		blkg = blkg_lookup_create(blkcg, disk->queue);
-	else
-		blkg = ERR_PTR(-EOPNOTSUPP);
+	rcu_read_lock();
+	spin_lock_irq(q->queue_lock);
 
+	blkg = blkg_lookup_check(blkcg, pol, q);
 	if (IS_ERR(blkg)) {
 		ret = PTR_ERR(blkg);
+		goto fail_unlock;
+	}
+
+	if (blkg)
+		goto success;
+
+	/*
+	 * Create blkgs walking down from blkcg_root to @blkcg, so that all
+	 * non-root blkgs have access to their parents.
+	 */
+	while (true) {
+		struct blkcg *pos = blkcg;
+		struct blkcg *parent;
+		struct blkcg_gq *new_blkg;
+
+		parent = blkcg_parent(blkcg);
+		while (parent && !__blkg_lookup(parent, q, false)) {
+			pos = parent;
+			parent = blkcg_parent(parent);
+		}
+
+		/* Drop locks to do new blkg allocation with GFP_KERNEL. */
+		spin_unlock_irq(q->queue_lock);
 		rcu_read_unlock();
-		spin_unlock_irq(disk->queue->queue_lock);
-		owner = disk->fops->owner;
-		put_disk(disk);
-		module_put(owner);
-		/*
-		 * If queue was bypassing, we should retry.  Do so after a
-		 * short msleep().  It isn't strictly necessary but queue
-		 * can be bypassing for some time and it's always nice to
-		 * avoid busy looping.
-		 */
-		if (ret == -EBUSY) {
-			msleep(10);
-			ret = restart_syscall();
+
+		new_blkg = blkg_alloc(pos, q, GFP_KERNEL);
+		if (unlikely(!new_blkg)) {
+			ret = -ENOMEM;
+			goto fail;
 		}
-		return ret;
-	}
 
+		rcu_read_lock();
+		spin_lock_irq(q->queue_lock);
+
+		blkg = blkg_lookup_check(pos, pol, q);
+		if (IS_ERR(blkg)) {
+			ret = PTR_ERR(blkg);
+			goto fail_unlock;
+		}
+
+		if (blkg) {
+			blkg_free(new_blkg);
+		} else {
+			blkg = blkg_create(pos, q, new_blkg);
+			if (unlikely(IS_ERR(blkg))) {
+				ret = PTR_ERR(blkg);
+				goto fail_unlock;
+			}
+		}
+
+		if (pos == blkcg)
+			goto success;
+	}
+success:
 	ctx->disk = disk;
 	ctx->blkg = blkg;
 	ctx->body = body;
 	return 0;
+
+fail_unlock:
+	spin_unlock_irq(q->queue_lock);
+	rcu_read_unlock();
+fail:
+	owner = disk->fops->owner;
+	put_disk(disk);
+	module_put(owner);
+	/*
+	 * If queue was bypassing, we should retry.  Do so after a
+	 * short msleep().  It isn't strictly necessary but queue
+	 * can be bypassing for some time and it's always nice to
+	 * avoid busy looping.
+	 */
+	if (ret == -EBUSY) {
+		msleep(10);
+		ret = restart_syscall();
+	}
+	return ret;
 }
 EXPORT_SYMBOL_GPL(blkg_conf_prep);
 

block/blk-core.c

@@ -268,10 +268,8 @@ void blk_sync_queue(struct request_queue *q)
 		struct blk_mq_hw_ctx *hctx;
 		int i;
 
-		queue_for_each_hw_ctx(q, hctx, i) {
-			cancel_work_sync(&hctx->run_work);
-			cancel_delayed_work_sync(&hctx->delay_work);
-		}
+		queue_for_each_hw_ctx(q, hctx, i)
+			cancel_delayed_work_sync(&hctx->run_work);
 	} else {
 		cancel_delayed_work_sync(&q->delay_work);
 	}
@@ -500,6 +498,13 @@ void blk_set_queue_dying(struct request_queue *q)
 	queue_flag_set(QUEUE_FLAG_DYING, q);
 	spin_unlock_irq(q->queue_lock);
 
+	/*
+	 * When queue DYING flag is set, we need to block new req
+	 * entering queue, so we call blk_freeze_queue_start() to
+	 * prevent I/O from crossing blk_queue_enter().
+	 */
+	blk_freeze_queue_start(q);
+
 	if (q->mq_ops)
 		blk_mq_wake_waiters(q);
 	else {
@@ -556,9 +561,13 @@ void blk_cleanup_queue(struct request_queue *q)
 	 * prevent that q->request_fn() gets invoked after draining finished.
 	 */
 	blk_freeze_queue(q);
-	spin_lock_irq(lock);
-	if (!q->mq_ops)
+	if (!q->mq_ops) {
+		spin_lock_irq(lock);
 		__blk_drain_queue(q, true);
+	} else {
+		blk_mq_debugfs_unregister_mq(q);
+		spin_lock_irq(lock);
+	}
 	queue_flag_set(QUEUE_FLAG_DEAD, q);
 	spin_unlock_irq(lock);
 
@@ -669,6 +678,15 @@ int blk_queue_enter(struct request_queue *q, bool nowait)
 		if (nowait)
 			return -EBUSY;
 
+		/*
+		 * read pair of barrier in blk_freeze_queue_start(),
+		 * we need to order reading __PERCPU_REF_DEAD flag of
+		 * .q_usage_counter and reading .mq_freeze_depth or
+		 * queue dying flag, otherwise the following wait may
+		 * never return if the two reads are reordered.
+		 */
+		smp_rmb();
+
 		ret = wait_event_interruptible(q->mq_freeze_wq,
 				!atomic_read(&q->mq_freeze_depth) ||
 				blk_queue_dying(q));
@@ -720,6 +738,10 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	if (!q->backing_dev_info)
 		goto fail_split;
 
+	q->stats = blk_alloc_queue_stats();
+	if (!q->stats)
+		goto fail_stats;
+
 	q->backing_dev_info->ra_pages =
 			(VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
 	q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK;
@@ -776,6 +798,8 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 fail_ref:
 	percpu_ref_exit(&q->q_usage_counter);
 fail_bdi:
+	blk_free_queue_stats(q->stats);
+fail_stats:
 	bdi_put(q->backing_dev_info);
 fail_split:
 	bioset_free(q->bio_split);
@@ -889,7 +913,6 @@ out_exit_flush_rq:
 		q->exit_rq_fn(q, q->fq->flush_rq);
 out_free_flush_queue:
 	blk_free_flush_queue(q->fq);
-	wbt_exit(q);
 	return -ENOMEM;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
@@ -1128,7 +1151,6 @@ static struct request *__get_request(struct request_list *rl, unsigned int op,
 
 	blk_rq_init(q, rq);
 	blk_rq_set_rl(rq, rl);
-	blk_rq_set_prio(rq, ioc);
 	rq->cmd_flags = op;
 	rq->rq_flags = rq_flags;
 
@@ -1608,17 +1630,23 @@ out:
 	return ret;
 }
 
-void init_request_from_bio(struct request *req, struct bio *bio)
+void blk_init_request_from_bio(struct request *req, struct bio *bio)
 {
+	struct io_context *ioc = rq_ioc(bio);
+
 	if (bio->bi_opf & REQ_RAHEAD)
 		req->cmd_flags |= REQ_FAILFAST_MASK;
 
-	req->errors = 0;
 	req->__sector = bio->bi_iter.bi_sector;
 	if (ioprio_valid(bio_prio(bio)))
 		req->ioprio = bio_prio(bio);
+	else if (ioc)
+		req->ioprio = ioc->ioprio;
+	else
+		req->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
 	blk_rq_bio_prep(req->q, req, bio);
 }
+EXPORT_SYMBOL_GPL(blk_init_request_from_bio);
 
 static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 {
@@ -1709,7 +1737,7 @@ get_rq:
 	 * We don't worry about that case for efficiency. It won't happen
 	 * often, and the elevators are able to handle it.
 	 */
-	init_request_from_bio(req, bio);
+	blk_init_request_from_bio(req, bio);
 
 	if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags))
 		req->cpu = raw_smp_processor_id();
@@ -1936,7 +1964,13 @@ generic_make_request_checks(struct bio *bio)
 	if (!blkcg_bio_issue_check(q, bio))
 		return false;
 
-	trace_block_bio_queue(q, bio);
+	if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) {
+		trace_block_bio_queue(q, bio);
+		/* Now that enqueuing has been traced, we need to trace
+		 * completion as well.
+		 */
+		bio_set_flag(bio, BIO_TRACE_COMPLETION);
+	}
 	return true;
 
 not_supported:
@@ -2478,7 +2512,7 @@ void blk_start_request(struct request *req)
 	blk_dequeue_request(req);
 
 	if (test_bit(QUEUE_FLAG_STATS, &req->q->queue_flags)) {
-		blk_stat_set_issue_time(&req->issue_stat);
+		blk_stat_set_issue(&req->issue_stat, blk_rq_sectors(req));
 		req->rq_flags |= RQF_STATS;
 		wbt_issue(req->q->rq_wb, &req->issue_stat);
 	}
@@ -2540,22 +2574,11 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 {
 	int total_bytes;
 
-	trace_block_rq_complete(req->q, req, nr_bytes);
+	trace_block_rq_complete(req, error, nr_bytes);
 
 	if (!req->bio)
 		return false;
 
-	/*
-	 * For fs requests, rq is just carrier of independent bio's
-	 * and each partial completion should be handled separately.
-	 * Reset per-request error on each partial completion.
-	 *
-	 * TODO: tj: This is too subtle.  It would be better to let
-	 * low level drivers do what they see fit.
-	 */
-	if (!blk_rq_is_passthrough(req))
-		req->errors = 0;
-
 	if (error && !blk_rq_is_passthrough(req) &&
 	    !(req->rq_flags & RQF_QUIET)) {
 		char *error_type;
@@ -2601,6 +2624,8 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 		if (bio_bytes == bio->bi_iter.bi_size)
 			req->bio = bio->bi_next;
 
+		/* Completion has already been traced */
+		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
 		req_bio_endio(req, bio, bio_bytes, error);
 
 		total_bytes += bio_bytes;
@@ -2699,7 +2724,7 @@ void blk_finish_request(struct request *req, int error)
 	struct request_queue *q = req->q;
 
 	if (req->rq_flags & RQF_STATS)
-		blk_stat_add(&q->rq_stats[rq_data_dir(req)], req);
+		blk_stat_add(req);
 
 	if (req->rq_flags & RQF_QUEUED)
 		blk_queue_end_tag(q, req);
@@ -2776,7 +2801,7 @@ static bool blk_end_bidi_request(struct request *rq, int error,
  *     %false - we are done with this request
  *     %true  - still buffers pending for this request
  **/
-bool __blk_end_bidi_request(struct request *rq, int error,
+static bool __blk_end_bidi_request(struct request *rq, int error,
 				   unsigned int nr_bytes, unsigned int bidi_bytes)
 {
 	if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
@@ -2828,43 +2853,6 @@ void blk_end_request_all(struct request *rq, int error)
 }
 EXPORT_SYMBOL(blk_end_request_all);
 
-/**
- * blk_end_request_cur - Helper function to finish the current request chunk.
- * @rq: the request to finish the current chunk for
- * @error: %0 for success, < %0 for error
- *
- * Description:
- *     Complete the current consecutively mapped chunk from @rq.
- *
- * Return:
- *     %false - we are done with this request
- *     %true  - still buffers pending for this request
- */
-bool blk_end_request_cur(struct request *rq, int error)
-{
-	return blk_end_request(rq, error, blk_rq_cur_bytes(rq));
-}
-EXPORT_SYMBOL(blk_end_request_cur);
-
-/**
- * blk_end_request_err - Finish a request till the next failure boundary.
- * @rq: the request to finish till the next failure boundary for
- * @error: must be negative errno
- *
- * Description:
- *     Complete @rq till the next failure boundary.
- *
- * Return:
- *     %false - we are done with this request
- *     %true  - still buffers pending for this request
- */
-bool blk_end_request_err(struct request *rq, int error)
-{
-	WARN_ON(error >= 0);
-	return blk_end_request(rq, error, blk_rq_err_bytes(rq));
-}
-EXPORT_SYMBOL_GPL(blk_end_request_err);
-
 /**
  * __blk_end_request - Helper function for drivers to complete the request.
  * @rq:       the request being processed
@@ -2924,26 +2912,6 @@ bool __blk_end_request_cur(struct request *rq, int error)
 }
 EXPORT_SYMBOL(__blk_end_request_cur);
 
-/**
- * __blk_end_request_err - Finish a request till the next failure boundary.
- * @rq: the request to finish till the next failure boundary for
- * @error: must be negative errno
- *
- * Description:
- *     Complete @rq till the next failure boundary.  Must be called
- *     with queue lock held.
- *
- * Return:
- *     %false - we are done with this request
- *     %true  - still buffers pending for this request
- */
-bool __blk_end_request_err(struct request *rq, int error)
-{
-	WARN_ON(error >= 0);
-	return __blk_end_request(rq, error, blk_rq_err_bytes(rq));
-}
-EXPORT_SYMBOL_GPL(__blk_end_request_err);
-
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 		     struct bio *bio)
 {
@@ -3106,6 +3074,13 @@ int kblockd_schedule_work_on(int cpu, struct work_struct *work)
 }
 EXPORT_SYMBOL(kblockd_schedule_work_on);
 
+int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork,
+				unsigned long delay)
+{
+	return mod_delayed_work_on(cpu, kblockd_workqueue, dwork, delay);
+}
+EXPORT_SYMBOL(kblockd_mod_delayed_work_on);
+
 int kblockd_schedule_delayed_work(struct delayed_work *dwork,
 				  unsigned long delay)
 {

block/blk-exec.c

@@ -69,8 +69,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 
 	if (unlikely(blk_queue_dying(q))) {
 		rq->rq_flags |= RQF_QUIET;
-		rq->errors = -ENXIO;
-		__blk_end_request_all(rq, rq->errors);
+		__blk_end_request_all(rq, -ENXIO);
 		spin_unlock_irq(q->queue_lock);
 		return;
 	}
@@ -92,11 +91,10 @@ EXPORT_SYMBOL_GPL(blk_execute_rq_nowait);
  *    Insert a fully prepared request at the back of the I/O scheduler queue
  *    for execution and wait for completion.
  */
-int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
+void blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
 		   struct request *rq, int at_head)
 {
 	DECLARE_COMPLETION_ONSTACK(wait);
-	int err = 0;
 	unsigned long hang_check;
 
 	rq->end_io_data = &wait;
@@ -108,10 +106,5 @@ int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
 		while (!wait_for_completion_io_timeout(&wait, hang_check * (HZ/2)));
 	else
 		wait_for_completion_io(&wait);
-
-	if (rq->errors)
-		err = -EIO;
-
-	return err;
 }
 EXPORT_SYMBOL(blk_execute_rq);

block/blk-flush.c

@@ -447,7 +447,7 @@ void blk_insert_flush(struct request *rq)
 		if (q->mq_ops)
 			blk_mq_end_request(rq, 0);
 		else
-			__blk_end_bidi_request(rq, 0, 0, 0);
+			__blk_end_request(rq, 0, 0);
 		return;
 	}
 
@@ -497,8 +497,7 @@ void blk_insert_flush(struct request *rq)
  * Description:
  *    Issue a flush for the block device in question. Caller can supply
  *    room for storing the error offset in case of a flush error, if they
- *    wish to. If WAIT flag is not passed then caller may check only what
- *    request was pushed in some internal queue for later handling.
+ *    wish to.
  */
 int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
 		sector_t *error_sector)

block/blk-integrity.c

@@ -389,7 +389,7 @@ static int blk_integrity_nop_fn(struct blk_integrity_iter *iter)
 	return 0;
 }
 
-static struct blk_integrity_profile nop_profile = {
+static const struct blk_integrity_profile nop_profile = {
 	.name = "nop",
 	.generate_fn = blk_integrity_nop_fn,
 	.verify_fn = blk_integrity_nop_fn,
@@ -412,12 +412,13 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template
 
 	bi->flags = BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE |
 		template->flags;
-	bi->interval_exp = ilog2(queue_logical_block_size(disk->queue));
+	bi->interval_exp = template->interval_exp ? :
+		ilog2(queue_logical_block_size(disk->queue));
 	bi->profile = template->profile ? template->profile : &nop_profile;
 	bi->tuple_size = template->tuple_size;
 	bi->tag_size = template->tag_size;
 
-	blk_integrity_revalidate(disk);
+	disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
 }
 EXPORT_SYMBOL(blk_integrity_register);
 
@@ -430,26 +431,11 @@ EXPORT_SYMBOL(blk_integrity_register);
  */
 void blk_integrity_unregister(struct gendisk *disk)
 {
-	blk_integrity_revalidate(disk);
+	disk->queue->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES;
 	memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity));
 }
 EXPORT_SYMBOL(blk_integrity_unregister);
 
-void blk_integrity_revalidate(struct gendisk *disk)
-{
-	struct blk_integrity *bi = &disk->queue->integrity;
-
-	if (!(disk->flags & GENHD_FL_UP))
-		return;
-
-	if (bi->profile)
-		disk->queue->backing_dev_info->capabilities |=
-			BDI_CAP_STABLE_WRITES;
-	else
-		disk->queue->backing_dev_info->capabilities &=
-			~BDI_CAP_STABLE_WRITES;
-}
-
 void blk_integrity_add(struct gendisk *disk)
 {
 	if (kobject_init_and_add(&disk->integrity_kobj, &integrity_ktype,

block/blk-lib.c

@@ -37,17 +37,12 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		return -ENXIO;
 
 	if (flags & BLKDEV_DISCARD_SECURE) {
-		if (flags & BLKDEV_DISCARD_ZERO)
-			return -EOPNOTSUPP;
 		if (!blk_queue_secure_erase(q))
 			return -EOPNOTSUPP;
 		op = REQ_OP_SECURE_ERASE;
 	} else {
 		if (!blk_queue_discard(q))
 			return -EOPNOTSUPP;
-		if ((flags & BLKDEV_DISCARD_ZERO) &&
-		    !q->limits.discard_zeroes_data)
-			return -EOPNOTSUPP;
 		op = REQ_OP_DISCARD;
 	}
 
@@ -109,7 +104,7 @@ EXPORT_SYMBOL(__blkdev_issue_discard);
  * @sector:	start sector
  * @nr_sects:	number of sectors to discard
  * @gfp_mask:	memory allocation flags (for bio_alloc)
- * @flags:	BLKDEV_IFL_* flags to control behaviour
+ * @flags:	BLKDEV_DISCARD_* flags to control behaviour
  *
  * Description:
  *    Issue a discard request for the sectors in question.
@@ -126,7 +121,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 			&bio);
 	if (!ret && bio) {
 		ret = submit_bio_wait(bio);
-		if (ret == -EOPNOTSUPP && !(flags & BLKDEV_DISCARD_ZERO))
+		if (ret == -EOPNOTSUPP)
 			ret = 0;
 		bio_put(bio);
 	}
@@ -226,20 +221,9 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL(blkdev_issue_write_same);
 
-/**
- * __blkdev_issue_write_zeroes - generate number of bios with WRITE ZEROES
- * @bdev:	blockdev to issue
- * @sector:	start sector
- * @nr_sects:	number of sectors to write
- * @gfp_mask:	memory allocation flags (for bio_alloc)
- * @biop:	pointer to anchor bio
- *
- * Description:
- *  Generate and issue number of bios(REQ_OP_WRITE_ZEROES) with zerofiled pages.
- */
 static int __blkdev_issue_write_zeroes(struct block_device *bdev,
 		sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
-		struct bio **biop)
+		struct bio **biop, unsigned flags)
 {
 	struct bio *bio = *biop;
 	unsigned int max_write_zeroes_sectors;
@@ -258,7 +242,9 @@ static int __blkdev_issue_write_zeroes(struct block_device *bdev,
 		bio = next_bio(bio, 0, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_bdev = bdev;
-		bio_set_op_attrs(bio, REQ_OP_WRITE_ZEROES, 0);
+		bio->bi_opf = REQ_OP_WRITE_ZEROES;
+		if (flags & BLKDEV_ZERO_NOUNMAP)
+			bio->bi_opf |= REQ_NOUNMAP;
 
 		if (nr_sects > max_write_zeroes_sectors) {
 			bio->bi_iter.bi_size = max_write_zeroes_sectors << 9;
@@ -282,14 +268,27 @@ static int __blkdev_issue_write_zeroes(struct block_device *bdev,
  * @nr_sects:	number of sectors to write
  * @gfp_mask:	memory allocation flags (for bio_alloc)
  * @biop:	pointer to anchor bio
- * @discard:	discard flag
+ * @flags:	controls detailed behavior
  *
  * Description:
- *  Generate and issue number of bios with zerofiled pages.
+ *  Zero-fill a block range, either using hardware offload or by explicitly
+ *  writing zeroes to the device.
+ *
+ *  Note that this function may fail with -EOPNOTSUPP if the driver signals
+ *  zeroing offload support, but the device fails to process the command (for
+ *  some devices there is no non-destructive way to verify whether this
+ *  operation is actually supported).  In this case the caller should call
+ *  retry the call to blkdev_issue_zeroout() and the fallback path will be used.
+ *
+ *  If a device is using logical block provisioning, the underlying space will
+ *  not be released if %flags contains BLKDEV_ZERO_NOUNMAP.
+ *
+ *  If %flags contains BLKDEV_ZERO_NOFALLBACK, the function will return
+ *  -EOPNOTSUPP if no explicit hardware offload for zeroing is provided.
  */
 int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
-		bool discard)
+		unsigned flags)
 {
 	int ret;
 	int bi_size = 0;
@@ -302,8 +301,8 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		return -EINVAL;
 
 	ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask,
-			biop);
-	if (ret == 0 || (ret && ret != -EOPNOTSUPP))
+			biop, flags);
+	if (ret != -EOPNOTSUPP || (flags & BLKDEV_ZERO_NOFALLBACK))
 		goto out;
 
 	ret = 0;
@@ -337,40 +336,23 @@ EXPORT_SYMBOL(__blkdev_issue_zeroout);
  * @sector:	start sector
  * @nr_sects:	number of sectors to write
  * @gfp_mask:	memory allocation flags (for bio_alloc)
- * @discard:	whether to discard the block range
+ * @flags:	controls detailed behavior
  *
  * Description:
- *  Zero-fill a block range.  If the discard flag is set and the block
- *  device guarantees that subsequent READ operations to the block range
- *  in question will return zeroes, the blocks will be discarded. Should
- *  the discard request fail, if the discard flag is not set, or if
- *  discard_zeroes_data is not supported, this function will resort to
- *  zeroing the blocks manually, thus provisioning (allocating,
- *  anchoring) them. If the block device supports WRITE ZEROES or WRITE SAME
- *  command(s), blkdev_issue_zeroout() will use it to optimize the process of
- *  clearing the block range. Otherwise the zeroing will be performed
- *  using regular WRITE calls.
+ *  Zero-fill a block range, either using hardware offload or by explicitly
+ *  writing zeroes to the device.  See __blkdev_issue_zeroout() for the
+ *  valid values for %flags.
  */
 int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
-			 sector_t nr_sects, gfp_t gfp_mask, bool discard)
+		sector_t nr_sects, gfp_t gfp_mask, unsigned flags)
 {
 	int ret;
 	struct bio *bio = NULL;
 	struct blk_plug plug;
 
-	if (discard) {
-		if (!blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask,
-				BLKDEV_DISCARD_ZERO))
-			return 0;
-	}
-
-	if (!blkdev_issue_write_same(bdev, sector, nr_sects, gfp_mask,
-			ZERO_PAGE(0)))
-		return 0;
-
 	blk_start_plug(&plug);
 	ret = __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask,
-			&bio, discard);
+			&bio, flags);
 	if (ret == 0 && bio) {
 		ret = submit_bio_wait(bio);
 		bio_put(bio);

block/blk-merge.c

@@ -54,6 +54,20 @@ static struct bio *blk_bio_discard_split(struct request_queue *q,
 	return bio_split(bio, split_sectors, GFP_NOIO, bs);
 }
 
+static struct bio *blk_bio_write_zeroes_split(struct request_queue *q,
+		struct bio *bio, struct bio_set *bs, unsigned *nsegs)
+{
+	*nsegs = 1;
+
+	if (!q->limits.max_write_zeroes_sectors)
+		return NULL;
+
+	if (bio_sectors(bio) <= q->limits.max_write_zeroes_sectors)
+		return NULL;
+
+	return bio_split(bio, q->limits.max_write_zeroes_sectors, GFP_NOIO, bs);
+}
+
 static struct bio *blk_bio_write_same_split(struct request_queue *q,
 					    struct bio *bio,
 					    struct bio_set *bs,
@@ -200,8 +214,7 @@ void blk_queue_split(struct request_queue *q, struct bio **bio,
 		split = blk_bio_discard_split(q, *bio, bs, &nsegs);
 		break;
 	case REQ_OP_WRITE_ZEROES:
-		split = NULL;
-		nsegs = (*bio)->bi_phys_segments;
+		split = blk_bio_write_zeroes_split(q, *bio, bs, &nsegs);
 		break;
 	case REQ_OP_WRITE_SAME:
 		split = blk_bio_write_same_split(q, *bio, bs, &nsegs);

block/blk-mq-debugfs.c

@@ -43,11 +43,157 @@ static int blk_mq_debugfs_seq_open(struct inode *inode, struct file *file,
 	return ret;
 }
 
+static int blk_flags_show(struct seq_file *m, const unsigned long flags,
+			  const char *const *flag_name, int flag_name_count)
+{
+	bool sep = false;
+	int i;
+
+	for (i = 0; i < sizeof(flags) * BITS_PER_BYTE; i++) {
+		if (!(flags & BIT(i)))
+			continue;
+		if (sep)
+			seq_puts(m, " ");
+		sep = true;
+		if (i < flag_name_count && flag_name[i])
+			seq_puts(m, flag_name[i]);
+		else
+			seq_printf(m, "%d", i);
+	}
+	return 0;
+}
+
+static const char *const blk_queue_flag_name[] = {
+	[QUEUE_FLAG_QUEUED]	 = "QUEUED",
+	[QUEUE_FLAG_STOPPED]	 = "STOPPED",
+	[QUEUE_FLAG_SYNCFULL]	 = "SYNCFULL",
+	[QUEUE_FLAG_ASYNCFULL]	 = "ASYNCFULL",
+	[QUEUE_FLAG_DYING]	 = "DYING",
+	[QUEUE_FLAG_BYPASS]	 = "BYPASS",
+	[QUEUE_FLAG_BIDI]	 = "BIDI",
+	[QUEUE_FLAG_NOMERGES]	 = "NOMERGES",
+	[QUEUE_FLAG_SAME_COMP]	 = "SAME_COMP",
+	[QUEUE_FLAG_FAIL_IO]	 = "FAIL_IO",
+	[QUEUE_FLAG_STACKABLE]	 = "STACKABLE",
+	[QUEUE_FLAG_NONROT]	 = "NONROT",
+	[QUEUE_FLAG_IO_STAT]	 = "IO_STAT",
+	[QUEUE_FLAG_DISCARD]	 = "DISCARD",
+	[QUEUE_FLAG_NOXMERGES]	 = "NOXMERGES",
+	[QUEUE_FLAG_ADD_RANDOM]	 = "ADD_RANDOM",
+	[QUEUE_FLAG_SECERASE]	 = "SECERASE",
+	[QUEUE_FLAG_SAME_FORCE]	 = "SAME_FORCE",
+	[QUEUE_FLAG_DEAD]	 = "DEAD",
+	[QUEUE_FLAG_INIT_DONE]	 = "INIT_DONE",
+	[QUEUE_FLAG_NO_SG_MERGE] = "NO_SG_MERGE",
+	[QUEUE_FLAG_POLL]	 = "POLL",
+	[QUEUE_FLAG_WC]		 = "WC",
+	[QUEUE_FLAG_FUA]	 = "FUA",
+	[QUEUE_FLAG_FLUSH_NQ]	 = "FLUSH_NQ",
+	[QUEUE_FLAG_DAX]	 = "DAX",
+	[QUEUE_FLAG_STATS]	 = "STATS",
+	[QUEUE_FLAG_POLL_STATS]	 = "POLL_STATS",
+	[QUEUE_FLAG_REGISTERED]	 = "REGISTERED",
+};
+
+static int blk_queue_flags_show(struct seq_file *m, void *v)
+{
+	struct request_queue *q = m->private;
+
+	blk_flags_show(m, q->queue_flags, blk_queue_flag_name,
+		       ARRAY_SIZE(blk_queue_flag_name));
+	seq_puts(m, "\n");
+	return 0;
+}
+
+static ssize_t blk_queue_flags_store(struct file *file, const char __user *ubuf,
+				     size_t len, loff_t *offp)
+{
+	struct request_queue *q = file_inode(file)->i_private;
+	char op[16] = { }, *s;
+
+	len = min(len, sizeof(op) - 1);
+	if (copy_from_user(op, ubuf, len))
+		return -EFAULT;
+	s = op;
+	strsep(&s, " \t\n"); /* strip trailing whitespace */
+	if (strcmp(op, "run") == 0) {
+		blk_mq_run_hw_queues(q, true);
+	} else if (strcmp(op, "start") == 0) {
+		blk_mq_start_stopped_hw_queues(q, true);
+	} else {
+		pr_err("%s: unsupported operation %s. Use either 'run' or 'start'\n",
+		       __func__, op);
+		return -EINVAL;
+	}
+	return len;
+}
+
+static int blk_queue_flags_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, blk_queue_flags_show, inode->i_private);
+}
+
+static const struct file_operations blk_queue_flags_fops = {
+	.open		= blk_queue_flags_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+	.write		= blk_queue_flags_store,
+};
+
+static void print_stat(struct seq_file *m, struct blk_rq_stat *stat)
+{
+	if (stat->nr_samples) {
+		seq_printf(m, "samples=%d, mean=%lld, min=%llu, max=%llu",
+			   stat->nr_samples, stat->mean, stat->min, stat->max);
+	} else {
+		seq_puts(m, "samples=0");
+	}
+}
+
+static int queue_poll_stat_show(struct seq_file *m, void *v)
+{
+	struct request_queue *q = m->private;
+	int bucket;
+
+	for (bucket = 0; bucket < BLK_MQ_POLL_STATS_BKTS/2; bucket++) {
+		seq_printf(m, "read  (%d Bytes): ", 1 << (9+bucket));
+		print_stat(m, &q->poll_stat[2*bucket]);
+		seq_puts(m, "\n");
+
+		seq_printf(m, "write (%d Bytes): ",  1 << (9+bucket));
+		print_stat(m, &q->poll_stat[2*bucket+1]);
+		seq_puts(m, "\n");
+	}
+	return 0;
+}
+
+static int queue_poll_stat_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, queue_poll_stat_show, inode->i_private);
+}
+
+static const struct file_operations queue_poll_stat_fops = {
+	.open		= queue_poll_stat_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static const char *const hctx_state_name[] = {
+	[BLK_MQ_S_STOPPED]	 = "STOPPED",
+	[BLK_MQ_S_TAG_ACTIVE]	 = "TAG_ACTIVE",
+	[BLK_MQ_S_SCHED_RESTART] = "SCHED_RESTART",
+	[BLK_MQ_S_TAG_WAITING]	 = "TAG_WAITING",
+
+};
 static int hctx_state_show(struct seq_file *m, void *v)
 {
 	struct blk_mq_hw_ctx *hctx = m->private;
 
-	seq_printf(m, "0x%lx\n", hctx->state);
+	blk_flags_show(m, hctx->state, hctx_state_name,
+		       ARRAY_SIZE(hctx_state_name));
+	seq_puts(m, "\n");
 	return 0;
 }
 
@@ -63,11 +209,35 @@ static const struct file_operations hctx_state_fops = {
 	.release	= single_release,
 };
 
+static const char *const alloc_policy_name[] = {
+	[BLK_TAG_ALLOC_FIFO]	= "fifo",
+	[BLK_TAG_ALLOC_RR]	= "rr",
+};
+
+static const char *const hctx_flag_name[] = {
+	[ilog2(BLK_MQ_F_SHOULD_MERGE)]	= "SHOULD_MERGE",
+	[ilog2(BLK_MQ_F_TAG_SHARED)]	= "TAG_SHARED",
+	[ilog2(BLK_MQ_F_SG_MERGE)]	= "SG_MERGE",
+	[ilog2(BLK_MQ_F_BLOCKING)]	= "BLOCKING",
+	[ilog2(BLK_MQ_F_NO_SCHED)]	= "NO_SCHED",
+};
+
 static int hctx_flags_show(struct seq_file *m, void *v)
 {
 	struct blk_mq_hw_ctx *hctx = m->private;
-
-	seq_printf(m, "0x%lx\n", hctx->flags);
+	const int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(hctx->flags);
+
+	seq_puts(m, "alloc_policy=");
+	if (alloc_policy < ARRAY_SIZE(alloc_policy_name) &&
+	    alloc_policy_name[alloc_policy])
+		seq_puts(m, alloc_policy_name[alloc_policy]);
+	else
+		seq_printf(m, "%d", alloc_policy);
+	seq_puts(m, " ");
+	blk_flags_show(m,
+		       hctx->flags ^ BLK_ALLOC_POLICY_TO_MQ_FLAG(alloc_policy),
+		       hctx_flag_name, ARRAY_SIZE(hctx_flag_name));
+	seq_puts(m, "\n");
 	return 0;
 }
 
@@ -83,13 +253,83 @@ static const struct file_operations hctx_flags_fops = {
 	.release	= single_release,
 };
 
+static const char *const op_name[] = {
+	[REQ_OP_READ]		= "READ",
+	[REQ_OP_WRITE]		= "WRITE",
+	[REQ_OP_FLUSH]		= "FLUSH",
+	[REQ_OP_DISCARD]	= "DISCARD",
+	[REQ_OP_ZONE_REPORT]	= "ZONE_REPORT",
+	[REQ_OP_SECURE_ERASE]	= "SECURE_ERASE",
+	[REQ_OP_ZONE_RESET]	= "ZONE_RESET",
+	[REQ_OP_WRITE_SAME]	= "WRITE_SAME",
+	[REQ_OP_WRITE_ZEROES]	= "WRITE_ZEROES",
+	[REQ_OP_SCSI_IN]	= "SCSI_IN",
+	[REQ_OP_SCSI_OUT]	= "SCSI_OUT",
+	[REQ_OP_DRV_IN]		= "DRV_IN",
+	[REQ_OP_DRV_OUT]	= "DRV_OUT",
+};
+
+static const char *const cmd_flag_name[] = {
+	[__REQ_FAILFAST_DEV]		= "FAILFAST_DEV",
+	[__REQ_FAILFAST_TRANSPORT]	= "FAILFAST_TRANSPORT",
+	[__REQ_FAILFAST_DRIVER]		= "FAILFAST_DRIVER",
+	[__REQ_SYNC]			= "SYNC",
+	[__REQ_META]			= "META",
+	[__REQ_PRIO]			= "PRIO",
+	[__REQ_NOMERGE]			= "NOMERGE",
+	[__REQ_IDLE]			= "IDLE",
+	[__REQ_INTEGRITY]		= "INTEGRITY",
+	[__REQ_FUA]			= "FUA",
+	[__REQ_PREFLUSH]		= "PREFLUSH",
+	[__REQ_RAHEAD]			= "RAHEAD",
+	[__REQ_BACKGROUND]		= "BACKGROUND",
+	[__REQ_NR_BITS]			= "NR_BITS",
+};
+
+static const char *const rqf_name[] = {
+	[ilog2((__force u32)RQF_SORTED)]		= "SORTED",
+	[ilog2((__force u32)RQF_STARTED)]		= "STARTED",
+	[ilog2((__force u32)RQF_QUEUED)]		= "QUEUED",
+	[ilog2((__force u32)RQF_SOFTBARRIER)]		= "SOFTBARRIER",
+	[ilog2((__force u32)RQF_FLUSH_SEQ)]		= "FLUSH_SEQ",
+	[ilog2((__force u32)RQF_MIXED_MERGE)]		= "MIXED_MERGE",
+	[ilog2((__force u32)RQF_MQ_INFLIGHT)]		= "MQ_INFLIGHT",
+	[ilog2((__force u32)RQF_DONTPREP)]		= "DONTPREP",
+	[ilog2((__force u32)RQF_PREEMPT)]		= "PREEMPT",
+	[ilog2((__force u32)RQF_COPY_USER)]		= "COPY_USER",
+	[ilog2((__force u32)RQF_FAILED)]		= "FAILED",
+	[ilog2((__force u32)RQF_QUIET)]			= "QUIET",
+	[ilog2((__force u32)RQF_ELVPRIV)]		= "ELVPRIV",
+	[ilog2((__force u32)RQF_IO_STAT)]		= "IO_STAT",
+	[ilog2((__force u32)RQF_ALLOCED)]		= "ALLOCED",
+	[ilog2((__force u32)RQF_PM)]			= "PM",
+	[ilog2((__force u32)RQF_HASHED)]		= "HASHED",
+	[ilog2((__force u32)RQF_STATS)]			= "STATS",
+	[ilog2((__force u32)RQF_SPECIAL_PAYLOAD)]	= "SPECIAL_PAYLOAD",
+};
+
 static int blk_mq_debugfs_rq_show(struct seq_file *m, void *v)
 {
 	struct request *rq = list_entry_rq(v);
-
-	seq_printf(m, "%p {.cmd_flags=0x%x, .rq_flags=0x%x, .tag=%d, .internal_tag=%d}\n",
-		   rq, rq->cmd_flags, (__force unsigned int)rq->rq_flags,
-		   rq->tag, rq->internal_tag);
+	const struct blk_mq_ops *const mq_ops = rq->q->mq_ops;
+	const unsigned int op = rq->cmd_flags & REQ_OP_MASK;
+
+	seq_printf(m, "%p {.op=", rq);
+	if (op < ARRAY_SIZE(op_name) && op_name[op])
+		seq_printf(m, "%s", op_name[op]);
+	else
+		seq_printf(m, "%d", op);
+	seq_puts(m, ", .cmd_flags=");
+	blk_flags_show(m, rq->cmd_flags & ~REQ_OP_MASK, cmd_flag_name,
+		       ARRAY_SIZE(cmd_flag_name));
+	seq_puts(m, ", .rq_flags=");
+	blk_flags_show(m, (__force unsigned int)rq->rq_flags, rqf_name,
+		       ARRAY_SIZE(rqf_name));
+	seq_printf(m, ", .tag=%d, .internal_tag=%d", rq->tag,
+		   rq->internal_tag);
+	if (mq_ops->show_rq)
+		mq_ops->show_rq(m, rq);
+	seq_puts(m, "}\n");
 	return 0;
 }
 
@@ -322,60 +562,6 @@ static const struct file_operations hctx_io_poll_fops = {
 	.release	= single_release,
 };
 
-static void print_stat(struct seq_file *m, struct blk_rq_stat *stat)
-{
-	seq_printf(m, "samples=%d, mean=%lld, min=%llu, max=%llu",
-		   stat->nr_samples, stat->mean, stat->min, stat->max);
-}
-
-static int hctx_stats_show(struct seq_file *m, void *v)
-{
-	struct blk_mq_hw_ctx *hctx = m->private;
-	struct blk_rq_stat stat[2];
-
-	blk_stat_init(&stat[BLK_STAT_READ]);
-	blk_stat_init(&stat[BLK_STAT_WRITE]);
-
-	blk_hctx_stat_get(hctx, stat);
-
-	seq_puts(m, "read: ");
-	print_stat(m, &stat[BLK_STAT_READ]);
-	seq_puts(m, "\n");
-
-	seq_puts(m, "write: ");
-	print_stat(m, &stat[BLK_STAT_WRITE]);
-	seq_puts(m, "\n");
-	return 0;
-}
-
-static int hctx_stats_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, hctx_stats_show, inode->i_private);
-}
-
-static ssize_t hctx_stats_write(struct file *file, const char __user *buf,
-				size_t count, loff_t *ppos)
-{
-	struct seq_file *m = file->private_data;
-	struct blk_mq_hw_ctx *hctx = m->private;
-	struct blk_mq_ctx *ctx;
-	int i;
-
-	hctx_for_each_ctx(hctx, ctx, i) {
-		blk_stat_init(&ctx->stat[BLK_STAT_READ]);
-		blk_stat_init(&ctx->stat[BLK_STAT_WRITE]);
-	}
-	return count;
-}
-
-static const struct file_operations hctx_stats_fops = {
-	.open		= hctx_stats_open,
-	.read		= seq_read,
-	.write		= hctx_stats_write,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
 static int hctx_dispatched_show(struct seq_file *m, void *v)
 {
 	struct blk_mq_hw_ctx *hctx = m->private;
@@ -636,6 +822,12 @@ static const struct file_operations ctx_completed_fops = {
 	.release	= single_release,
 };
 
+static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
+	{"poll_stat", 0400, &queue_poll_stat_fops},
+	{"state", 0600, &blk_queue_flags_fops},
+	{},
+};
+
 static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
 	{"state", 0400, &hctx_state_fops},
 	{"flags", 0400, &hctx_flags_fops},
@@ -646,7 +838,6 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
 	{"sched_tags", 0400, &hctx_sched_tags_fops},
 	{"sched_tags_bitmap", 0400, &hctx_sched_tags_bitmap_fops},
 	{"io_poll", 0600, &hctx_io_poll_fops},
-	{"stats", 0600, &hctx_stats_fops},
 	{"dispatched", 0600, &hctx_dispatched_fops},
 	{"queued", 0600, &hctx_queued_fops},
 	{"run", 0600, &hctx_run_fops},
@@ -662,16 +853,17 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = {
 	{},
 };
 
-int blk_mq_debugfs_register(struct request_queue *q, const char *name)
+int blk_mq_debugfs_register(struct request_queue *q)
 {
 	if (!blk_debugfs_root)
 		return -ENOENT;
 
-	q->debugfs_dir = debugfs_create_dir(name, blk_debugfs_root);
+	q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent),
+					    blk_debugfs_root);
 	if (!q->debugfs_dir)
 		goto err;
 
-	if (blk_mq_debugfs_register_hctxs(q))
+	if (blk_mq_debugfs_register_mq(q))
 		goto err;
 
 	return 0;
@@ -741,7 +933,7 @@ static int blk_mq_debugfs_register_hctx(struct request_queue *q,
 	return 0;
 }
 
-int blk_mq_debugfs_register_hctxs(struct request_queue *q)
+int blk_mq_debugfs_register_mq(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
 	int i;
@@ -753,6 +945,9 @@ int blk_mq_debugfs_register_hctxs(struct request_queue *q)
 	if (!q->mq_debugfs_dir)
 		goto err;
 
+	if (!debugfs_create_files(q->mq_debugfs_dir, q, blk_mq_debugfs_queue_attrs))
+		goto err;
+
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (blk_mq_debugfs_register_hctx(q, hctx))
 			goto err;
@@ -761,11 +956,11 @@ int blk_mq_debugfs_register_hctxs(struct request_queue *q)
 	return 0;
 
 err:
-	blk_mq_debugfs_unregister_hctxs(q);
+	blk_mq_debugfs_unregister_mq(q);
 	return -ENOMEM;
 }
 
-void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
+void blk_mq_debugfs_unregister_mq(struct request_queue *q)
 {
 	debugfs_remove_recursive(q->mq_debugfs_dir);
 	q->mq_debugfs_dir = NULL;

block/blk-mq-pci.c

@@ -23,7 +23,7 @@
  * @pdev:	PCI device associated with @set.
  *
  * This function assumes the PCI device @pdev has at least as many available
- * interrupt vetors as @set has queues.  It will then queuery the vector
+ * interrupt vectors as @set has queues.  It will then query the vector
  * corresponding to each queue for it's affinity mask and built queue mapping
  * that maps a queue to the CPUs that have irq affinity for the corresponding
  * vector.

block/blk-mq-sched.c

@@ -30,43 +30,6 @@ void blk_mq_sched_free_hctx_data(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_free_hctx_data);
 
-int blk_mq_sched_init_hctx_data(struct request_queue *q, size_t size,
-				int (*init)(struct blk_mq_hw_ctx *),
-				void (*exit)(struct blk_mq_hw_ctx *))
-{
-	struct blk_mq_hw_ctx *hctx;
-	int ret;
-	int i;
-
-	queue_for_each_hw_ctx(q, hctx, i) {
-		hctx->sched_data = kmalloc_node(size, GFP_KERNEL, hctx->numa_node);
-		if (!hctx->sched_data) {
-			ret = -ENOMEM;
-			goto error;
-		}
-
-		if (init) {
-			ret = init(hctx);
-			if (ret) {
-				/*
-				 * We don't want to give exit() a partially
-				 * initialized sched_data. init() must clean up
-				 * if it fails.
-				 */
-				kfree(hctx->sched_data);
-				hctx->sched_data = NULL;
-				goto error;
-			}
-		}
-	}
-
-	return 0;
-error:
-	blk_mq_sched_free_hctx_data(q, exit);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(blk_mq_sched_init_hctx_data);
-
 static void __blk_mq_sched_assign_ioc(struct request_queue *q,
 				      struct request *rq,
 				      struct bio *bio,
@@ -119,7 +82,11 @@ struct request *blk_mq_sched_get_request(struct request_queue *q,
 	if (likely(!data->hctx))
 		data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
 
-	if (e) {
+	/*
+	 * For a reserved tag, allocate a normal request since we might
+	 * have driver dependencies on the value of the internal tag.
+	 */
+	if (e && !(data->flags & BLK_MQ_REQ_RESERVED)) {
 		data->flags |= BLK_MQ_REQ_INTERNAL;
 
 		/*
@@ -227,22 +194,6 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	}
 }
 
-void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx,
-				   struct list_head *rq_list,
-				   struct request *(*get_rq)(struct blk_mq_hw_ctx *))
-{
-	do {
-		struct request *rq;
-
-		rq = get_rq(hctx);
-		if (!rq)
-			break;
-
-		list_add_tail(&rq->queuelist, rq_list);
-	} while (1);
-}
-EXPORT_SYMBOL_GPL(blk_mq_sched_move_to_dispatch);
-
 bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
 			    struct request **merged_request)
 {
@@ -508,11 +459,24 @@ int blk_mq_sched_init_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
 			   unsigned int hctx_idx)
 {
 	struct elevator_queue *e = q->elevator;
+	int ret;
 
 	if (!e)
 		return 0;
 
-	return blk_mq_sched_alloc_tags(q, hctx, hctx_idx);
+	ret = blk_mq_sched_alloc_tags(q, hctx, hctx_idx);
+	if (ret)
+		return ret;
+
+	if (e->type->ops.mq.init_hctx) {
+		ret = e->type->ops.mq.init_hctx(hctx, hctx_idx);
+		if (ret) {
+			blk_mq_sched_free_tags(q->tag_set, hctx, hctx_idx);
+			return ret;
+		}
+	}
+
+	return 0;
 }
 
 void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
@@ -523,12 +487,18 @@ void blk_mq_sched_exit_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
 	if (!e)
 		return;
 
+	if (e->type->ops.mq.exit_hctx && hctx->sched_data) {
+		e->type->ops.mq.exit_hctx(hctx, hctx_idx);
+		hctx->sched_data = NULL;
+	}
+
 	blk_mq_sched_free_tags(q->tag_set, hctx, hctx_idx);
 }
 
 int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 {
 	struct blk_mq_hw_ctx *hctx;
+	struct elevator_queue *eq;
 	unsigned int i;
 	int ret;
 
@@ -553,6 +523,18 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e)
 	if (ret)
 		goto err;
 
+	if (e->ops.mq.init_hctx) {
+		queue_for_each_hw_ctx(q, hctx, i) {
+			ret = e->ops.mq.init_hctx(hctx, i);
+			if (ret) {
+				eq = q->elevator;
+				blk_mq_exit_sched(q, eq);
+				kobject_put(&eq->kobj);
+				return ret;
+			}
+		}
+	}
+
 	return 0;
 
 err:
@@ -563,6 +545,17 @@ err:
 
 void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e)
 {
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+
+	if (e->type->ops.mq.exit_hctx) {
+		queue_for_each_hw_ctx(q, hctx, i) {
+			if (hctx->sched_data) {
+				e->type->ops.mq.exit_hctx(hctx, i);
+				hctx->sched_data = NULL;
+			}
+		}
+	}
 	if (e->type->ops.mq.exit_sched)
 		e->type->ops.mq.exit_sched(e);
 	blk_mq_sched_tags_teardown(q);

block/blk-mq-sched.h

@@ -4,10 +4,6 @@
 #include "blk-mq.h"
 #include "blk-mq-tag.h"
 
-int blk_mq_sched_init_hctx_data(struct request_queue *q, size_t size,
-				int (*init)(struct blk_mq_hw_ctx *),
-				void (*exit)(struct blk_mq_hw_ctx *));
-
 void blk_mq_sched_free_hctx_data(struct request_queue *q,
 				 void (*exit)(struct blk_mq_hw_ctx *));
 
@@ -28,9 +24,6 @@ void blk_mq_sched_insert_requests(struct request_queue *q,
 				  struct list_head *list, bool run_queue_async);
 
 void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx);
-void blk_mq_sched_move_to_dispatch(struct blk_mq_hw_ctx *hctx,
-			struct list_head *rq_list,
-			struct request *(*get_rq)(struct blk_mq_hw_ctx *));
 
 int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e);
 void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e);
@@ -86,17 +79,12 @@ blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
 	return true;
 }
 
-static inline void
-blk_mq_sched_completed_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
+static inline void blk_mq_sched_completed_request(struct request *rq)
 {
-	struct elevator_queue *e = hctx->queue->elevator;
+	struct elevator_queue *e = rq->q->elevator;
 
 	if (e && e->type->ops.mq.completed_request)
-		e->type->ops.mq.completed_request(hctx, rq);
-
-	BUG_ON(rq->internal_tag == -1);
-
-	blk_mq_put_tag(hctx, hctx->sched_tags, rq->mq_ctx, rq->internal_tag);
+		e->type->ops.mq.completed_request(rq);
 }
 
 static inline void blk_mq_sched_started_request(struct request *rq)

block/blk-mq-sysfs.c

@@ -253,10 +253,12 @@ static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
+	lockdep_assert_held(&q->sysfs_lock);
+
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_unregister_hctx(hctx);
 
-	blk_mq_debugfs_unregister_hctxs(q);
+	blk_mq_debugfs_unregister_mq(q);
 
 	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
 	kobject_del(&q->mq_kobj);
@@ -267,9 +269,9 @@ static void __blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 
 void blk_mq_unregister_dev(struct device *dev, struct request_queue *q)
 {
-	blk_mq_disable_hotplug();
+	mutex_lock(&q->sysfs_lock);
 	__blk_mq_unregister_dev(dev, q);
-	blk_mq_enable_hotplug();
+	mutex_unlock(&q->sysfs_lock);
 }
 
 void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx)
@@ -302,12 +304,13 @@ void blk_mq_sysfs_init(struct request_queue *q)
 	}
 }
 
-int blk_mq_register_dev(struct device *dev, struct request_queue *q)
+int __blk_mq_register_dev(struct device *dev, struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
 	int ret, i;
 
-	blk_mq_disable_hotplug();
+	WARN_ON_ONCE(!q->kobj.parent);
+	lockdep_assert_held(&q->sysfs_lock);
 
 	ret = kobject_add(&q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq");
 	if (ret < 0)
@@ -315,20 +318,38 @@ int blk_mq_register_dev(struct device *dev, struct request_queue *q)
 
 	kobject_uevent(&q->mq_kobj, KOBJ_ADD);
 
-	blk_mq_debugfs_register(q, kobject_name(&dev->kobj));
+	blk_mq_debugfs_register(q);
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);
 		if (ret)
-			break;
+			goto unreg;
 	}
 
-	if (ret)
-		__blk_mq_unregister_dev(dev, q);
-	else
-		q->mq_sysfs_init_done = true;
+	q->mq_sysfs_init_done = true;
+
 out:
-	blk_mq_enable_hotplug();
+	return ret;
+
+unreg:
+	while (--i >= 0)
+		blk_mq_unregister_hctx(q->queue_hw_ctx[i]);
+
+	blk_mq_debugfs_unregister_mq(q);
+
+	kobject_uevent(&q->mq_kobj, KOBJ_REMOVE);
+	kobject_del(&q->mq_kobj);
+	kobject_put(&dev->kobj);
+	return ret;
+}
+
+int blk_mq_register_dev(struct device *dev, struct request_queue *q)
+{
+	int ret;
+
+	mutex_lock(&q->sysfs_lock);
+	ret = __blk_mq_register_dev(dev, q);
+	mutex_unlock(&q->sysfs_lock);
 
 	return ret;
 }
@@ -339,13 +360,17 @@ void blk_mq_sysfs_unregister(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
+	mutex_lock(&q->sysfs_lock);
 	if (!q->mq_sysfs_init_done)
-		return;
+		goto unlock;
 
-	blk_mq_debugfs_unregister_hctxs(q);
+	blk_mq_debugfs_unregister_mq(q);
 
 	queue_for_each_hw_ctx(q, hctx, i)
 		blk_mq_unregister_hctx(hctx);
+
+unlock:
+	mutex_unlock(&q->sysfs_lock);
 }
 
 int blk_mq_sysfs_register(struct request_queue *q)
@@ -353,10 +378,11 @@ int blk_mq_sysfs_register(struct request_queue *q)
 	struct blk_mq_hw_ctx *hctx;
 	int i, ret = 0;
 
+	mutex_lock(&q->sysfs_lock);
 	if (!q->mq_sysfs_init_done)
-		return ret;
+		goto unlock;
 
-	blk_mq_debugfs_register_hctxs(q);
+	blk_mq_debugfs_register_mq(q);
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		ret = blk_mq_register_hctx(hctx);
@@ -364,5 +390,8 @@ int blk_mq_sysfs_register(struct request_queue *q)
 			break;
 	}
 
+unlock:
+	mutex_unlock(&q->sysfs_lock);
+
 	return ret;
 }

block/blk-mq-tag.c

@@ -96,7 +96,10 @@ static int __blk_mq_get_tag(struct blk_mq_alloc_data *data,
 	if (!(data->flags & BLK_MQ_REQ_INTERNAL) &&
 	    !hctx_may_queue(data->hctx, bt))
 		return -1;
-	return __sbitmap_queue_get(bt);
+	if (data->shallow_depth)
+		return __sbitmap_queue_get_shallow(bt, data->shallow_depth);
+	else
+		return __sbitmap_queue_get(bt);
 }
 
 unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)

block/blk-mq.c

@@ -39,6 +39,26 @@
 static DEFINE_MUTEX(all_q_mutex);
 static LIST_HEAD(all_q_list);
 
+static void blk_mq_poll_stats_start(struct request_queue *q);
+static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
+
+static int blk_mq_poll_stats_bkt(const struct request *rq)
+{
+	int ddir, bytes, bucket;
+
+	ddir = rq_data_dir(rq);
+	bytes = blk_rq_bytes(rq);
+
+	bucket = ddir + 2*(ilog2(bytes) - 9);
+
+	if (bucket < 0)
+		return -1;
+	else if (bucket >= BLK_MQ_POLL_STATS_BKTS)
+		return ddir + BLK_MQ_POLL_STATS_BKTS - 2;
+
+	return bucket;
+}
+
 /*
  * Check if any of the ctx's have pending work in this hardware queue
  */
@@ -65,7 +85,7 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
 	sbitmap_clear_bit(&hctx->ctx_map, ctx->index_hw);
 }
 
-void blk_mq_freeze_queue_start(struct request_queue *q)
+void blk_freeze_queue_start(struct request_queue *q)
 {
 	int freeze_depth;
 
@@ -75,7 +95,7 @@ void blk_mq_freeze_queue_start(struct request_queue *q)
 		blk_mq_run_hw_queues(q, false);
 	}
 }
-EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start);
+EXPORT_SYMBOL_GPL(blk_freeze_queue_start);
 
 void blk_mq_freeze_queue_wait(struct request_queue *q)
 {
@@ -105,7 +125,7 @@ void blk_freeze_queue(struct request_queue *q)
 	 * no blk_unfreeze_queue(), and blk_freeze_queue() is not
 	 * exported to drivers as the only user for unfreeze is blk_mq.
 	 */
-	blk_mq_freeze_queue_start(q);
+	blk_freeze_queue_start(q);
 	blk_mq_freeze_queue_wait(q);
 }
 
@@ -210,7 +230,6 @@ void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 #endif
 	rq->special = NULL;
 	/* tag was already set */
-	rq->errors = 0;
 	rq->extra_len = 0;
 
 	INIT_LIST_HEAD(&rq->timeout_list);
@@ -347,7 +366,7 @@ void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 	if (rq->tag != -1)
 		blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
 	if (sched_tag != -1)
-		blk_mq_sched_completed_request(hctx, rq);
+		blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag);
 	blk_mq_sched_restart(hctx);
 	blk_queue_exit(q);
 }
@@ -365,6 +384,7 @@ void blk_mq_finish_request(struct request *rq)
 {
 	blk_mq_finish_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq);
 }
+EXPORT_SYMBOL_GPL(blk_mq_finish_request);
 
 void blk_mq_free_request(struct request *rq)
 {
@@ -402,12 +422,19 @@ static void __blk_mq_complete_request_remote(void *data)
 	rq->q->softirq_done_fn(rq);
 }
 
-static void blk_mq_ipi_complete_request(struct request *rq)
+static void __blk_mq_complete_request(struct request *rq)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 	bool shared = false;
 	int cpu;
 
+	if (rq->internal_tag != -1)
+		blk_mq_sched_completed_request(rq);
+	if (rq->rq_flags & RQF_STATS) {
+		blk_mq_poll_stats_start(rq->q);
+		blk_stat_add(rq);
+	}
+
 	if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) {
 		rq->q->softirq_done_fn(rq);
 		return;
@@ -428,33 +455,6 @@ static void blk_mq_ipi_complete_request(struct request *rq)
 	put_cpu();
 }
 
-static void blk_mq_stat_add(struct request *rq)
-{
-	if (rq->rq_flags & RQF_STATS) {
-		/*
-		 * We could rq->mq_ctx here, but there's less of a risk
-		 * of races if we have the completion event add the stats
-		 * to the local software queue.
-		 */
-		struct blk_mq_ctx *ctx;
-
-		ctx = __blk_mq_get_ctx(rq->q, raw_smp_processor_id());
-		blk_stat_add(&ctx->stat[rq_data_dir(rq)], rq);
-	}
-}
-
-static void __blk_mq_complete_request(struct request *rq)
-{
-	struct request_queue *q = rq->q;
-
-	blk_mq_stat_add(rq);
-
-	if (!q->softirq_done_fn)
-		blk_mq_end_request(rq, rq->errors);
-	else
-		blk_mq_ipi_complete_request(rq);
-}
-
 /**
  * blk_mq_complete_request - end I/O on a request
  * @rq:		the request being processed
@@ -463,16 +463,14 @@ static void __blk_mq_complete_request(struct request *rq)
  *	Ends all I/O on a request. It does not handle partial completions.
  *	The actual completion happens out-of-order, through a IPI handler.
  **/
-void blk_mq_complete_request(struct request *rq, int error)
+void blk_mq_complete_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
 	if (unlikely(blk_should_fake_timeout(q)))
 		return;
-	if (!blk_mark_rq_complete(rq)) {
-		rq->errors = error;
+	if (!blk_mark_rq_complete(rq))
 		__blk_mq_complete_request(rq);
-	}
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
@@ -491,7 +489,7 @@ void blk_mq_start_request(struct request *rq)
 	trace_block_rq_issue(q, rq);
 
 	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
-		blk_stat_set_issue_time(&rq->issue_stat);
+		blk_stat_set_issue(&rq->issue_stat, blk_rq_sectors(rq));
 		rq->rq_flags |= RQF_STATS;
 		wbt_issue(q->rq_wb, &rq->issue_stat);
 	}
@@ -526,6 +524,15 @@ void blk_mq_start_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_start_request);
 
+/*
+ * When we reach here because queue is busy, REQ_ATOM_COMPLETE
+ * flag isn't set yet, so there may be race with timeout handler,
+ * but given rq->deadline is just set in .queue_rq() under
+ * this situation, the race won't be possible in reality because
+ * rq->timeout should be set as big enough to cover the window
+ * between blk_mq_start_request() called from .queue_rq() and
+ * clearing REQ_ATOM_STARTED here.
+ */
 static void __blk_mq_requeue_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
@@ -633,8 +640,7 @@ void blk_mq_abort_requeue_list(struct request_queue *q)
 
 		rq = list_first_entry(&rq_list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
-		rq->errors = -EIO;
-		blk_mq_end_request(rq, rq->errors);
+		blk_mq_end_request(rq, -EIO);
 	}
 }
 EXPORT_SYMBOL(blk_mq_abort_requeue_list);
@@ -666,7 +672,7 @@ void blk_mq_rq_timed_out(struct request *req, bool reserved)
 	 * just be ignored. This can happen due to the bitflag ordering.
 	 * Timeout first checks if STARTED is set, and if it is, assumes
 	 * the request is active. But if we race with completion, then
-	 * we both flags will get cleared. So check here again, and ignore
+	 * both flags will get cleared. So check here again, and ignore
 	 * a timeout event with a request that isn't active.
 	 */
 	if (!test_bit(REQ_ATOM_STARTED, &req->atomic_flags))
@@ -699,6 +705,19 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
 		return;
 
+	/*
+	 * The rq being checked may have been freed and reallocated
+	 * out already here, we avoid this race by checking rq->deadline
+	 * and REQ_ATOM_COMPLETE flag together:
+	 *
+	 * - if rq->deadline is observed as new value because of
+	 *   reusing, the rq won't be timed out because of timing.
+	 * - if rq->deadline is observed as previous value,
+	 *   REQ_ATOM_COMPLETE flag won't be cleared in reuse path
+	 *   because we put a barrier between setting rq->deadline
+	 *   and clearing the flag in blk_mq_start_request(), so
+	 *   this rq won't be timed out too.
+	 */
 	if (time_after_eq(jiffies, rq->deadline)) {
 		if (!blk_mark_rq_complete(rq))
 			blk_mq_rq_timed_out(rq, reserved);
@@ -727,7 +746,7 @@ static void blk_mq_timeout_work(struct work_struct *work)
 	 * percpu_ref_tryget directly, because we need to be able to
 	 * obtain a reference even in the short window between the queue
 	 * starting to freeze, by dropping the first reference in
-	 * blk_mq_freeze_queue_start, and the moment the last request is
+	 * blk_freeze_queue_start, and the moment the last request is
 	 * consumed, marked by the instant q_usage_counter reaches
 	 * zero.
 	 */
@@ -845,6 +864,8 @@ bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
 		.flags = wait ? 0 : BLK_MQ_REQ_NOWAIT,
 	};
 
+	might_sleep_if(wait);
+
 	if (rq->tag != -1)
 		goto done;
 
@@ -964,19 +985,11 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
 {
 	struct blk_mq_hw_ctx *hctx;
 	struct request *rq;
-	LIST_HEAD(driver_list);
-	struct list_head *dptr;
 	int errors, queued, ret = BLK_MQ_RQ_QUEUE_OK;
 
 	if (list_empty(list))
 		return false;
 
-	/*
-	 * Start off with dptr being NULL, so we start the first request
-	 * immediately, even if we have more pending.
-	 */
-	dptr = NULL;
-
 	/*
 	 * Now process all the entries, sending them to the driver.
 	 */
@@ -993,23 +1006,21 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
 			 * The initial allocation attempt failed, so we need to
 			 * rerun the hardware queue when a tag is freed.
 			 */
-			if (blk_mq_dispatch_wait_add(hctx)) {
-				/*
-				 * It's possible that a tag was freed in the
-				 * window between the allocation failure and
-				 * adding the hardware queue to the wait queue.
-				 */
-				if (!blk_mq_get_driver_tag(rq, &hctx, false))
-					break;
-			} else {
+			if (!blk_mq_dispatch_wait_add(hctx))
+				break;
+
+			/*
+			 * It's possible that a tag was freed in the window
+			 * between the allocation failure and adding the
+			 * hardware queue to the wait queue.
+			 */
+			if (!blk_mq_get_driver_tag(rq, &hctx, false))
 				break;
-			}
 		}
 
 		list_del_init(&rq->queuelist);
 
 		bd.rq = rq;
-		bd.list = dptr;
 
 		/*
 		 * Flag last if we have no more requests, or if we have more
@@ -1038,20 +1049,12 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
 			pr_err("blk-mq: bad return on queue: %d\n", ret);
 		case BLK_MQ_RQ_QUEUE_ERROR:
 			errors++;
-			rq->errors = -EIO;
-			blk_mq_end_request(rq, rq->errors);
+			blk_mq_end_request(rq, -EIO);
 			break;
 		}
 
 		if (ret == BLK_MQ_RQ_QUEUE_BUSY)
 			break;
-
-		/*
-		 * We've done the first request. If we have more than 1
-		 * left in the list, set dptr to defer issue.
-		 */
-		if (!dptr && list->next != list->prev)
-			dptr = &driver_list;
 	} while (!list_empty(list));
 
 	hctx->dispatched[queued_to_index(queued)]++;
@@ -1062,8 +1065,8 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
 	 */
 	if (!list_empty(list)) {
 		/*
-		 * If we got a driver tag for the next request already,
-		 * free it again.
+		 * If an I/O scheduler has been configured and we got a driver
+		 * tag for the next request already, free it again.
 		 */
 		rq = list_first_entry(list, struct request, queuelist);
 		blk_mq_put_driver_tag(rq);
@@ -1073,16 +1076,24 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
 		spin_unlock(&hctx->lock);
 
 		/*
-		 * the queue is expected stopped with BLK_MQ_RQ_QUEUE_BUSY, but
-		 * it's possible the queue is stopped and restarted again
-		 * before this. Queue restart will dispatch requests. And since
-		 * requests in rq_list aren't added into hctx->dispatch yet,
-		 * the requests in rq_list might get lost.
+		 * If SCHED_RESTART was set by the caller of this function and
+		 * it is no longer set that means that it was cleared by another
+		 * thread and hence that a queue rerun is needed.
 		 *
-		 * blk_mq_run_hw_queue() already checks the STOPPED bit
+		 * If TAG_WAITING is set that means that an I/O scheduler has
+		 * been configured and another thread is waiting for a driver
+		 * tag. To guarantee fairness, do not rerun this hardware queue
+		 * but let the other thread grab the driver tag.
 		 *
-		 * If RESTART or TAG_WAITING is set, then let completion restart
-		 * the queue instead of potentially looping here.
+		 * If no I/O scheduler has been configured it is possible that
+		 * the hardware queue got stopped and restarted before requests
+		 * were pushed back onto the dispatch list. Rerun the queue to
+		 * avoid starvation. Notes:
+		 * - blk_mq_run_hw_queue() checks whether or not a queue has
+		 *   been stopped before rerunning a queue.
+		 * - Some but not all block drivers stop a queue before
+		 *   returning BLK_MQ_RQ_QUEUE_BUSY. Two exceptions are scsi-mq
+		 *   and dm-rq.
 		 */
 		if (!blk_mq_sched_needs_restart(hctx) &&
 		    !test_bit(BLK_MQ_S_TAG_WAITING, &hctx->state))
@@ -1104,6 +1115,8 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 		blk_mq_sched_dispatch_requests(hctx);
 		rcu_read_unlock();
 	} else {
+		might_sleep();
+
 		srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
 		blk_mq_sched_dispatch_requests(hctx);
 		srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
@@ -1153,13 +1166,9 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
 		put_cpu();
 	}
 
-	if (msecs == 0)
-		kblockd_schedule_work_on(blk_mq_hctx_next_cpu(hctx),
-					 &hctx->run_work);
-	else
-		kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
-						 &hctx->delayed_run_work,
-						 msecs_to_jiffies(msecs));
+	kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
+					 &hctx->run_work,
+					 msecs_to_jiffies(msecs));
 }
 
 void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
@@ -1172,6 +1181,7 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 {
 	__blk_mq_delay_run_hw_queue(hctx, async, 0);
 }
+EXPORT_SYMBOL(blk_mq_run_hw_queue);
 
 void blk_mq_run_hw_queues(struct request_queue *q, bool async)
 {
@@ -1210,8 +1220,7 @@ EXPORT_SYMBOL(blk_mq_queue_stopped);
 
 void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
-	cancel_work(&hctx->run_work);
-	cancel_delayed_work(&hctx->delay_work);
+	cancel_delayed_work_sync(&hctx->run_work);
 	set_bit(BLK_MQ_S_STOPPED, &hctx->state);
 }
 EXPORT_SYMBOL(blk_mq_stop_hw_queue);
@@ -1268,38 +1277,40 @@ static void blk_mq_run_work_fn(struct work_struct *work)
 {
 	struct blk_mq_hw_ctx *hctx;
 
-	hctx = container_of(work, struct blk_mq_hw_ctx, run_work);
-
-	__blk_mq_run_hw_queue(hctx);
-}
+	hctx = container_of(work, struct blk_mq_hw_ctx, run_work.work);
 
-static void blk_mq_delayed_run_work_fn(struct work_struct *work)
-{
-	struct blk_mq_hw_ctx *hctx;
+	/*
+	 * If we are stopped, don't run the queue. The exception is if
+	 * BLK_MQ_S_START_ON_RUN is set. For that case, we auto-clear
+	 * the STOPPED bit and run it.
+	 */
+	if (test_bit(BLK_MQ_S_STOPPED, &hctx->state)) {
+		if (!test_bit(BLK_MQ_S_START_ON_RUN, &hctx->state))
+			return;
 
-	hctx = container_of(work, struct blk_mq_hw_ctx, delayed_run_work.work);
+		clear_bit(BLK_MQ_S_START_ON_RUN, &hctx->state);
+		clear_bit(BLK_MQ_S_STOPPED, &hctx->state);
+	}
 
 	__blk_mq_run_hw_queue(hctx);
 }
 
-static void blk_mq_delay_work_fn(struct work_struct *work)
-{
-	struct blk_mq_hw_ctx *hctx;
-
-	hctx = container_of(work, struct blk_mq_hw_ctx, delay_work.work);
-
-	if (test_and_clear_bit(BLK_MQ_S_STOPPED, &hctx->state))
-		__blk_mq_run_hw_queue(hctx);
-}
 
 void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
 {
 	if (unlikely(!blk_mq_hw_queue_mapped(hctx)))
 		return;
 
+	/*
+	 * Stop the hw queue, then modify currently delayed work.
+	 * This should prevent us from running the queue prematurely.
+	 * Mark the queue as auto-clearing STOPPED when it runs.
+	 */
 	blk_mq_stop_hw_queue(hctx);
-	kblockd_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
-			&hctx->delay_work, msecs_to_jiffies(msecs));
+	set_bit(BLK_MQ_S_START_ON_RUN, &hctx->state);
+	kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
+					&hctx->run_work,
+					msecs_to_jiffies(msecs));
 }
 EXPORT_SYMBOL(blk_mq_delay_queue);
 
@@ -1408,7 +1419,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 
 static void blk_mq_bio_to_request(struct request *rq, struct bio *bio)
 {
-	init_request_from_bio(rq, bio);
+	blk_init_request_from_bio(rq, bio);
 
 	blk_account_io_start(rq, true);
 }
@@ -1453,14 +1464,13 @@ static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq)
 	return blk_tag_to_qc_t(rq->internal_tag, hctx->queue_num, true);
 }
 
-static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie,
+static void __blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie,
 				      bool may_sleep)
 {
 	struct request_queue *q = rq->q;
 	struct blk_mq_queue_data bd = {
 		.rq = rq,
-		.list = NULL,
-		.last = 1
+		.last = true,
 	};
 	struct blk_mq_hw_ctx *hctx;
 	blk_qc_t new_cookie;
@@ -1485,31 +1495,42 @@ static void blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie,
 		return;
 	}
 
-	__blk_mq_requeue_request(rq);
-
 	if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
 		*cookie = BLK_QC_T_NONE;
-		rq->errors = -EIO;
-		blk_mq_end_request(rq, rq->errors);
+		blk_mq_end_request(rq, -EIO);
 		return;
 	}
 
+	__blk_mq_requeue_request(rq);
 insert:
 	blk_mq_sched_insert_request(rq, false, true, false, may_sleep);
 }
 
-/*
- * Multiple hardware queue variant. This will not use per-process plugs,
- * but will attempt to bypass the hctx queueing if we can go straight to
- * hardware for SYNC IO.
- */
+static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
+		struct request *rq, blk_qc_t *cookie)
+{
+	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
+		rcu_read_lock();
+		__blk_mq_try_issue_directly(rq, cookie, false);
+		rcu_read_unlock();
+	} else {
+		unsigned int srcu_idx;
+
+		might_sleep();
+
+		srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
+		__blk_mq_try_issue_directly(rq, cookie, true);
+		srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
+	}
+}
+
 static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int is_sync = op_is_sync(bio->bi_opf);
 	const int is_flush_fua = op_is_flush(bio->bi_opf);
 	struct blk_mq_alloc_data data = { .flags = 0 };
 	struct request *rq;
-	unsigned int request_count = 0, srcu_idx;
+	unsigned int request_count = 0;
 	struct blk_plug *plug;
 	struct request *same_queue_rq = NULL;
 	blk_qc_t cookie;
@@ -1545,147 +1566,21 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	cookie = request_to_qc_t(data.hctx, rq);
 
-	if (unlikely(is_flush_fua)) {
-		if (q->elevator)
-			goto elv_insert;
-		blk_mq_bio_to_request(rq, bio);
-		blk_insert_flush(rq);
-		goto run_queue;
-	}
-
 	plug = current->plug;
-	/*
-	 * If the driver supports defer issued based on 'last', then
-	 * queue it up like normal since we can potentially save some
-	 * CPU this way.
-	 */
-	if (((plug && !blk_queue_nomerges(q)) || is_sync) &&
-	    !(data.hctx->flags & BLK_MQ_F_DEFER_ISSUE)) {
-		struct request *old_rq = NULL;
-
-		blk_mq_bio_to_request(rq, bio);
-
-		/*
-		 * We do limited plugging. If the bio can be merged, do that.
-		 * Otherwise the existing request in the plug list will be
-		 * issued. So the plug list will have one request at most
-		 */
-		if (plug) {
-			/*
-			 * The plug list might get flushed before this. If that
-			 * happens, same_queue_rq is invalid and plug list is
-			 * empty
-			 */
-			if (same_queue_rq && !list_empty(&plug->mq_list)) {
-				old_rq = same_queue_rq;
-				list_del_init(&old_rq->queuelist);
-			}
-			list_add_tail(&rq->queuelist, &plug->mq_list);
-		} else /* is_sync */
-			old_rq = rq;
+	if (unlikely(is_flush_fua)) {
 		blk_mq_put_ctx(data.ctx);
-		if (!old_rq)
-			goto done;
-
-		if (!(data.hctx->flags & BLK_MQ_F_BLOCKING)) {
-			rcu_read_lock();
-			blk_mq_try_issue_directly(old_rq, &cookie, false);
-			rcu_read_unlock();
+		blk_mq_bio_to_request(rq, bio);
+		if (q->elevator) {
+			blk_mq_sched_insert_request(rq, false, true, true,
+					true);
 		} else {
-			srcu_idx = srcu_read_lock(&data.hctx->queue_rq_srcu);
-			blk_mq_try_issue_directly(old_rq, &cookie, true);
-			srcu_read_unlock(&data.hctx->queue_rq_srcu, srcu_idx);
+			blk_insert_flush(rq);
+			blk_mq_run_hw_queue(data.hctx, true);
 		}
-		goto done;
-	}
-
-	if (q->elevator) {
-elv_insert:
-		blk_mq_put_ctx(data.ctx);
-		blk_mq_bio_to_request(rq, bio);
-		blk_mq_sched_insert_request(rq, false, true,
-						!is_sync || is_flush_fua, true);
-		goto done;
-	}
-	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
-		/*
-		 * For a SYNC request, send it to the hardware immediately. For
-		 * an ASYNC request, just ensure that we run it later on. The
-		 * latter allows for merging opportunities and more efficient
-		 * dispatching.
-		 */
-run_queue:
-		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
-	}
-	blk_mq_put_ctx(data.ctx);
-done:
-	return cookie;
-}
-
-/*
- * Single hardware queue variant. This will attempt to use any per-process
- * plug for merging and IO deferral.
- */
-static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
-{
-	const int is_sync = op_is_sync(bio->bi_opf);
-	const int is_flush_fua = op_is_flush(bio->bi_opf);
-	struct blk_plug *plug;
-	unsigned int request_count = 0;
-	struct blk_mq_alloc_data data = { .flags = 0 };
-	struct request *rq;
-	blk_qc_t cookie;
-	unsigned int wb_acct;
-
-	blk_queue_bounce(q, &bio);
-
-	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
-		bio_io_error(bio);
-		return BLK_QC_T_NONE;
-	}
-
-	blk_queue_split(q, &bio, q->bio_split);
-
-	if (!is_flush_fua && !blk_queue_nomerges(q)) {
-		if (blk_attempt_plug_merge(q, bio, &request_count, NULL))
-			return BLK_QC_T_NONE;
-	} else
-		request_count = blk_plug_queued_count(q);
-
-	if (blk_mq_sched_bio_merge(q, bio))
-		return BLK_QC_T_NONE;
-
-	wb_acct = wbt_wait(q->rq_wb, bio, NULL);
-
-	trace_block_getrq(q, bio, bio->bi_opf);
-
-	rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
-	if (unlikely(!rq)) {
-		__wbt_done(q->rq_wb, wb_acct);
-		return BLK_QC_T_NONE;
-	}
-
-	wbt_track(&rq->issue_stat, wb_acct);
-
-	cookie = request_to_qc_t(data.hctx, rq);
-
-	if (unlikely(is_flush_fua)) {
-		if (q->elevator)
-			goto elv_insert;
-		blk_mq_bio_to_request(rq, bio);
-		blk_insert_flush(rq);
-		goto run_queue;
-	}
-
-	/*
-	 * A task plug currently exists. Since this is completely lockless,
-	 * utilize that to temporarily store requests until the task is
-	 * either done or scheduled away.
-	 */
-	plug = current->plug;
-	if (plug) {
+	} else if (plug && q->nr_hw_queues == 1) {
 		struct request *last = NULL;
 
+		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
 
 		/*
@@ -1694,13 +1589,14 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		 */
 		if (list_empty(&plug->mq_list))
 			request_count = 0;
+		else if (blk_queue_nomerges(q))
+			request_count = blk_plug_queued_count(q);
+
 		if (!request_count)
 			trace_block_plug(q);
 		else
 			last = list_entry_rq(plug->mq_list.prev);
 
-		blk_mq_put_ctx(data.ctx);
-
 		if (request_count >= BLK_MAX_REQUEST_COUNT || (last &&
 		    blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) {
 			blk_flush_plug_list(plug, false);
@@ -1708,30 +1604,41 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio)
 		}
 
 		list_add_tail(&rq->queuelist, &plug->mq_list);
-		return cookie;
-	}
-
-	if (q->elevator) {
-elv_insert:
-		blk_mq_put_ctx(data.ctx);
+	} else if (plug && !blk_queue_nomerges(q)) {
 		blk_mq_bio_to_request(rq, bio);
-		blk_mq_sched_insert_request(rq, false, true,
-						!is_sync || is_flush_fua, true);
-		goto done;
-	}
-	if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
+
 		/*
-		 * For a SYNC request, send it to the hardware immediately. For
-		 * an ASYNC request, just ensure that we run it later on. The
-		 * latter allows for merging opportunities and more efficient
-		 * dispatching.
+		 * We do limited plugging. If the bio can be merged, do that.
+		 * Otherwise the existing request in the plug list will be
+		 * issued. So the plug list will have one request at most
+		 * The plug list might get flushed before this. If that happens,
+		 * the plug list is empty, and same_queue_rq is invalid.
 		 */
-run_queue:
-		blk_mq_run_hw_queue(data.hctx, !is_sync || is_flush_fua);
-	}
+		if (list_empty(&plug->mq_list))
+			same_queue_rq = NULL;
+		if (same_queue_rq)
+			list_del_init(&same_queue_rq->queuelist);
+		list_add_tail(&rq->queuelist, &plug->mq_list);
+
+		blk_mq_put_ctx(data.ctx);
+
+		if (same_queue_rq)
+			blk_mq_try_issue_directly(data.hctx, same_queue_rq,
+					&cookie);
+	} else if (q->nr_hw_queues > 1 && is_sync) {
+		blk_mq_put_ctx(data.ctx);
+		blk_mq_bio_to_request(rq, bio);
+		blk_mq_try_issue_directly(data.hctx, rq, &cookie);
+	} else if (q->elevator) {
+		blk_mq_put_ctx(data.ctx);
+		blk_mq_bio_to_request(rq, bio);
+		blk_mq_sched_insert_request(rq, false, true, true, true);
+	} else if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
+		blk_mq_put_ctx(data.ctx);
+		blk_mq_run_hw_queue(data.hctx, true);
+	} else
+		blk_mq_put_ctx(data.ctx);
 
-	blk_mq_put_ctx(data.ctx);
-done:
 	return cookie;
 }
 
@@ -1988,9 +1895,7 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	if (node == NUMA_NO_NODE)
 		node = hctx->numa_node = set->numa_node;
 
-	INIT_WORK(&hctx->run_work, blk_mq_run_work_fn);
-	INIT_DELAYED_WORK(&hctx->delayed_run_work, blk_mq_delayed_run_work_fn);
-	INIT_DELAYED_WORK(&hctx->delay_work, blk_mq_delay_work_fn);
+	INIT_DELAYED_WORK(&hctx->run_work, blk_mq_run_work_fn);
 	spin_lock_init(&hctx->lock);
 	INIT_LIST_HEAD(&hctx->dispatch);
 	hctx->queue = q;
@@ -2067,8 +1972,6 @@ static void blk_mq_init_cpu_queues(struct request_queue *q,
 		spin_lock_init(&__ctx->lock);
 		INIT_LIST_HEAD(&__ctx->rq_list);
 		__ctx->queue = q;
-		blk_stat_init(&__ctx->stat[BLK_STAT_READ]);
-		blk_stat_init(&__ctx->stat[BLK_STAT_WRITE]);
 
 		/* If the cpu isn't online, the cpu is mapped to first hctx */
 		if (!cpu_online(i))
@@ -2215,6 +2118,8 @@ static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set, bool shared)
 {
 	struct request_queue *q;
 
+	lockdep_assert_held(&set->tag_list_lock);
+
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_freeze_queue(q);
 		queue_set_hctx_shared(q, shared);
@@ -2227,7 +2132,8 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 	struct blk_mq_tag_set *set = q->tag_set;
 
 	mutex_lock(&set->tag_list_lock);
-	list_del_init(&q->tag_set_list);
+	list_del_rcu(&q->tag_set_list);
+	INIT_LIST_HEAD(&q->tag_set_list);
 	if (list_is_singular(&set->tag_list)) {
 		/* just transitioned to unshared */
 		set->flags &= ~BLK_MQ_F_TAG_SHARED;
@@ -2235,6 +2141,8 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 		blk_mq_update_tag_set_depth(set, false);
 	}
 	mutex_unlock(&set->tag_list_lock);
+
+	synchronize_rcu();
 }
 
 static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
@@ -2252,7 +2160,7 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set,
 	}
 	if (set->flags & BLK_MQ_F_TAG_SHARED)
 		queue_set_hctx_shared(q, true);
-	list_add_tail(&q->tag_set_list, &set->tag_list);
+	list_add_tail_rcu(&q->tag_set_list, &set->tag_list);
 
 	mutex_unlock(&set->tag_list_lock);
 }
@@ -2364,6 +2272,12 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	/* mark the queue as mq asap */
 	q->mq_ops = set->ops;
 
+	q->poll_cb = blk_stat_alloc_callback(blk_mq_poll_stats_fn,
+					     blk_mq_poll_stats_bkt,
+					     BLK_MQ_POLL_STATS_BKTS, q);
+	if (!q->poll_cb)
+		goto err_exit;
+
 	q->queue_ctx = alloc_percpu(struct blk_mq_ctx);
 	if (!q->queue_ctx)
 		goto err_exit;
@@ -2398,10 +2312,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	INIT_LIST_HEAD(&q->requeue_list);
 	spin_lock_init(&q->requeue_lock);
 
-	if (q->nr_hw_queues > 1)
-		blk_queue_make_request(q, blk_mq_make_request);
-	else
-		blk_queue_make_request(q, blk_sq_make_request);
+	blk_queue_make_request(q, blk_mq_make_request);
 
 	/*
 	 * Do this after blk_queue_make_request() overrides it...
@@ -2456,8 +2367,6 @@ void blk_mq_free_queue(struct request_queue *q)
 	list_del_init(&q->all_q_node);
 	mutex_unlock(&all_q_mutex);
 
-	wbt_exit(q);
-
 	blk_mq_del_queue_tag_set(q);
 
 	blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
@@ -2502,7 +2411,7 @@ static void blk_mq_queue_reinit_work(void)
 	 * take place in parallel.
 	 */
 	list_for_each_entry(q, &all_q_list, all_q_node)
-		blk_mq_freeze_queue_start(q);
+		blk_freeze_queue_start(q);
 	list_for_each_entry(q, &all_q_list, all_q_node)
 		blk_mq_freeze_queue_wait(q);
 
@@ -2743,6 +2652,8 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
 {
 	struct request_queue *q;
 
+	lockdep_assert_held(&set->tag_list_lock);
+
 	if (nr_hw_queues > nr_cpu_ids)
 		nr_hw_queues = nr_cpu_ids;
 	if (nr_hw_queues < 1 || nr_hw_queues == set->nr_hw_queues)
@@ -2755,16 +2666,6 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
 	blk_mq_update_queue_map(set);
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_realloc_hw_ctxs(set, q);
-
-		/*
-		 * Manually set the make_request_fn as blk_queue_make_request
-		 * resets a lot of the queue settings.
-		 */
-		if (q->nr_hw_queues > 1)
-			q->make_request_fn = blk_mq_make_request;
-		else
-			q->make_request_fn = blk_sq_make_request;
-
 		blk_mq_queue_reinit(q, cpu_online_mask);
 	}
 
@@ -2773,39 +2674,69 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues)
 }
 EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues);
 
+/* Enable polling stats and return whether they were already enabled. */
+static bool blk_poll_stats_enable(struct request_queue *q)
+{
+	if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags) ||
+	    test_and_set_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags))
+		return true;
+	blk_stat_add_callback(q, q->poll_cb);
+	return false;
+}
+
+static void blk_mq_poll_stats_start(struct request_queue *q)
+{
+	/*
+	 * We don't arm the callback if polling stats are not enabled or the
+	 * callback is already active.
+	 */
+	if (!test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags) ||
+	    blk_stat_is_active(q->poll_cb))
+		return;
+
+	blk_stat_activate_msecs(q->poll_cb, 100);
+}
+
+static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb)
+{
+	struct request_queue *q = cb->data;
+	int bucket;
+
+	for (bucket = 0; bucket < BLK_MQ_POLL_STATS_BKTS; bucket++) {
+		if (cb->stat[bucket].nr_samples)
+			q->poll_stat[bucket] = cb->stat[bucket];
+	}
+}
+
 static unsigned long blk_mq_poll_nsecs(struct request_queue *q,
 				       struct blk_mq_hw_ctx *hctx,
 				       struct request *rq)
 {
-	struct blk_rq_stat stat[2];
 	unsigned long ret = 0;
+	int bucket;
 
 	/*
 	 * If stats collection isn't on, don't sleep but turn it on for
 	 * future users
 	 */
-	if (!blk_stat_enable(q))
+	if (!blk_poll_stats_enable(q))
 		return 0;
 
-	/*
-	 * We don't have to do this once per IO, should optimize this
-	 * to just use the current window of stats until it changes
-	 */
-	memset(&stat, 0, sizeof(stat));
-	blk_hctx_stat_get(hctx, stat);
-
 	/*
 	 * As an optimistic guess, use half of the mean service time
 	 * for this type of request. We can (and should) make this smarter.
 	 * For instance, if the completion latencies are tight, we can
 	 * get closer than just half the mean. This is especially
 	 * important on devices where the completion latencies are longer
-	 * than ~10 usec.
+	 * than ~10 usec. We do use the stats for the relevant IO size
+	 * if available which does lead to better estimates.
 	 */
-	if (req_op(rq) == REQ_OP_READ && stat[BLK_STAT_READ].nr_samples)
-		ret = (stat[BLK_STAT_READ].mean + 1) / 2;
-	else if (req_op(rq) == REQ_OP_WRITE && stat[BLK_STAT_WRITE].nr_samples)
-		ret = (stat[BLK_STAT_WRITE].mean + 1) / 2;
+	bucket = blk_mq_poll_stats_bkt(rq);
+	if (bucket < 0)
+		return ret;
+
+	if (q->poll_stat[bucket].nr_samples)
+		ret = (q->poll_stat[bucket].mean + 1) / 2;
 
 	return ret;
 }

block/blk-mq.h

@@ -20,7 +20,6 @@ struct blk_mq_ctx {
 
 	/* incremented at completion time */
 	unsigned long		____cacheline_aligned_in_smp rq_completed[2];
-	struct blk_rq_stat	stat[2];
 
 	struct request_queue	*queue;
 	struct kobject		kobj;
@@ -79,6 +78,7 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q,
  */
 extern void blk_mq_sysfs_init(struct request_queue *q);
 extern void blk_mq_sysfs_deinit(struct request_queue *q);
+extern int __blk_mq_register_dev(struct device *dev, struct request_queue *q);
 extern int blk_mq_sysfs_register(struct request_queue *q);
 extern void blk_mq_sysfs_unregister(struct request_queue *q);
 extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
@@ -87,13 +87,12 @@ extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
  * debugfs helpers
  */
 #ifdef CONFIG_BLK_DEBUG_FS
-int blk_mq_debugfs_register(struct request_queue *q, const char *name);
+int blk_mq_debugfs_register(struct request_queue *q);
 void blk_mq_debugfs_unregister(struct request_queue *q);
-int blk_mq_debugfs_register_hctxs(struct request_queue *q);
-void blk_mq_debugfs_unregister_hctxs(struct request_queue *q);
+int blk_mq_debugfs_register_mq(struct request_queue *q);
+void blk_mq_debugfs_unregister_mq(struct request_queue *q);
 #else
-static inline int blk_mq_debugfs_register(struct request_queue *q,
-					  const char *name)
+static inline int blk_mq_debugfs_register(struct request_queue *q)
 {
 	return 0;
 }
@@ -102,12 +101,12 @@ static inline void blk_mq_debugfs_unregister(struct request_queue *q)
 {
 }
 
-static inline int blk_mq_debugfs_register_hctxs(struct request_queue *q)
+static inline int blk_mq_debugfs_register_mq(struct request_queue *q)
 {
 	return 0;
 }
 
-static inline void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
+static inline void blk_mq_debugfs_unregister_mq(struct request_queue *q)
 {
 }
 #endif
@@ -142,6 +141,7 @@ struct blk_mq_alloc_data {
 	/* input parameter */
 	struct request_queue *q;
 	unsigned int flags;
+	unsigned int shallow_depth;
 
 	/* input & output parameter */
 	struct blk_mq_ctx *ctx;

block/blk-settings.c

@@ -103,7 +103,6 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->discard_granularity = 0;
 	lim->discard_alignment = 0;
 	lim->discard_misaligned = 0;
-	lim->discard_zeroes_data = 0;
 	lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
 	lim->bounce_pfn = (unsigned long)(BLK_BOUNCE_ANY >> PAGE_SHIFT);
 	lim->alignment_offset = 0;
@@ -127,7 +126,6 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	blk_set_default_limits(lim);
 
 	/* Inherit limits from component devices */
-	lim->discard_zeroes_data = 1;
 	lim->max_segments = USHRT_MAX;
 	lim->max_discard_segments = 1;
 	lim->max_hw_sectors = UINT_MAX;
@@ -609,7 +607,6 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->io_opt = lcm_not_zero(t->io_opt, b->io_opt);
 
 	t->cluster &= b->cluster;
-	t->discard_zeroes_data &= b->discard_zeroes_data;
 
 	/* Physical block size a multiple of the logical block size? */
 	if (t->physical_block_size & (t->logical_block_size - 1)) {

block/blk-stat.c

@@ -4,10 +4,27 @@
  * Copyright (C) 2016 Jens Axboe
  */
 #include <linux/kernel.h>
+#include <linux/rculist.h>
 #include <linux/blk-mq.h>
 
 #include "blk-stat.h"
 #include "blk-mq.h"
+#include "blk.h"
+
+#define BLK_RQ_STAT_BATCH	64
+
+struct blk_queue_stats {
+	struct list_head callbacks;
+	spinlock_t lock;
+	bool enable_accounting;
+};
+
+static void blk_stat_init(struct blk_rq_stat *stat)
+{
+	stat->min = -1ULL;
+	stat->max = stat->nr_samples = stat->mean = 0;
+	stat->batch = stat->nr_batch = 0;
+}
 
 static void blk_stat_flush_batch(struct blk_rq_stat *stat)
 {
@@ -48,209 +65,185 @@ static void blk_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
 	dst->nr_samples += src->nr_samples;
 }
 
-static void blk_mq_stat_get(struct request_queue *q, struct blk_rq_stat *dst)
+static void __blk_stat_add(struct blk_rq_stat *stat, u64 value)
 {
-	struct blk_mq_hw_ctx *hctx;
-	struct blk_mq_ctx *ctx;
-	uint64_t latest = 0;
-	int i, j, nr;
-
-	blk_stat_init(&dst[BLK_STAT_READ]);
-	blk_stat_init(&dst[BLK_STAT_WRITE]);
-
-	nr = 0;
-	do {
-		uint64_t newest = 0;
-
-		queue_for_each_hw_ctx(q, hctx, i) {
-			hctx_for_each_ctx(hctx, ctx, j) {
-				blk_stat_flush_batch(&ctx->stat[BLK_STAT_READ]);
-				blk_stat_flush_batch(&ctx->stat[BLK_STAT_WRITE]);
-
-				if (!ctx->stat[BLK_STAT_READ].nr_samples &&
-				    !ctx->stat[BLK_STAT_WRITE].nr_samples)
-					continue;
-				if (ctx->stat[BLK_STAT_READ].time > newest)
-					newest = ctx->stat[BLK_STAT_READ].time;
-				if (ctx->stat[BLK_STAT_WRITE].time > newest)
-					newest = ctx->stat[BLK_STAT_WRITE].time;
-			}
-		}
+	stat->min = min(stat->min, value);
+	stat->max = max(stat->max, value);
 
-		/*
-		 * No samples
-		 */
-		if (!newest)
-			break;
-
-		if (newest > latest)
-			latest = newest;
-
-		queue_for_each_hw_ctx(q, hctx, i) {
-			hctx_for_each_ctx(hctx, ctx, j) {
-				if (ctx->stat[BLK_STAT_READ].time == newest) {
-					blk_stat_sum(&dst[BLK_STAT_READ],
-						     &ctx->stat[BLK_STAT_READ]);
-					nr++;
-				}
-				if (ctx->stat[BLK_STAT_WRITE].time == newest) {
-					blk_stat_sum(&dst[BLK_STAT_WRITE],
-						     &ctx->stat[BLK_STAT_WRITE]);
-					nr++;
-				}
-			}
-		}
-		/*
-		 * If we race on finding an entry, just loop back again.
-		 * Should be very rare.
-		 */
-	} while (!nr);
+	if (stat->batch + value < stat->batch ||
+	    stat->nr_batch + 1 == BLK_RQ_STAT_BATCH)
+		blk_stat_flush_batch(stat);
 
-	dst[BLK_STAT_READ].time = dst[BLK_STAT_WRITE].time = latest;
+	stat->batch += value;
+	stat->nr_batch++;
 }
 
-void blk_queue_stat_get(struct request_queue *q, struct blk_rq_stat *dst)
+void blk_stat_add(struct request *rq)
 {
-	if (q->mq_ops)
-		blk_mq_stat_get(q, dst);
-	else {
-		blk_stat_flush_batch(&q->rq_stats[BLK_STAT_READ]);
-		blk_stat_flush_batch(&q->rq_stats[BLK_STAT_WRITE]);
-		memcpy(&dst[BLK_STAT_READ], &q->rq_stats[BLK_STAT_READ],
-				sizeof(struct blk_rq_stat));
-		memcpy(&dst[BLK_STAT_WRITE], &q->rq_stats[BLK_STAT_WRITE],
-				sizeof(struct blk_rq_stat));
+	struct request_queue *q = rq->q;
+	struct blk_stat_callback *cb;
+	struct blk_rq_stat *stat;
+	int bucket;
+	s64 now, value;
+
+	now = __blk_stat_time(ktime_to_ns(ktime_get()));
+	if (now < blk_stat_time(&rq->issue_stat))
+		return;
+
+	value = now - blk_stat_time(&rq->issue_stat);
+
+	blk_throtl_stat_add(rq, value);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(cb, &q->stats->callbacks, list) {
+		if (blk_stat_is_active(cb)) {
+			bucket = cb->bucket_fn(rq);
+			if (bucket < 0)
+				continue;
+			stat = &this_cpu_ptr(cb->cpu_stat)[bucket];
+			__blk_stat_add(stat, value);
+		}
 	}
+	rcu_read_unlock();
 }
 
-void blk_hctx_stat_get(struct blk_mq_hw_ctx *hctx, struct blk_rq_stat *dst)
+static void blk_stat_timer_fn(unsigned long data)
 {
-	struct blk_mq_ctx *ctx;
-	unsigned int i, nr;
+	struct blk_stat_callback *cb = (void *)data;
+	unsigned int bucket;
+	int cpu;
 
-	nr = 0;
-	do {
-		uint64_t newest = 0;
+	for (bucket = 0; bucket < cb->buckets; bucket++)
+		blk_stat_init(&cb->stat[bucket]);
 
-		hctx_for_each_ctx(hctx, ctx, i) {
-			blk_stat_flush_batch(&ctx->stat[BLK_STAT_READ]);
-			blk_stat_flush_batch(&ctx->stat[BLK_STAT_WRITE]);
+	for_each_online_cpu(cpu) {
+		struct blk_rq_stat *cpu_stat;
 
-			if (!ctx->stat[BLK_STAT_READ].nr_samples &&
-			    !ctx->stat[BLK_STAT_WRITE].nr_samples)
-				continue;
-
-			if (ctx->stat[BLK_STAT_READ].time > newest)
-				newest = ctx->stat[BLK_STAT_READ].time;
-			if (ctx->stat[BLK_STAT_WRITE].time > newest)
-				newest = ctx->stat[BLK_STAT_WRITE].time;
+		cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu);
+		for (bucket = 0; bucket < cb->buckets; bucket++) {
+			blk_stat_sum(&cb->stat[bucket], &cpu_stat[bucket]);
+			blk_stat_init(&cpu_stat[bucket]);
 		}
+	}
 
-		if (!newest)
-			break;
-
-		hctx_for_each_ctx(hctx, ctx, i) {
-			if (ctx->stat[BLK_STAT_READ].time == newest) {
-				blk_stat_sum(&dst[BLK_STAT_READ],
-						&ctx->stat[BLK_STAT_READ]);
-				nr++;
-			}
-			if (ctx->stat[BLK_STAT_WRITE].time == newest) {
-				blk_stat_sum(&dst[BLK_STAT_WRITE],
-						&ctx->stat[BLK_STAT_WRITE]);
-				nr++;
-			}
-		}
-		/*
-		 * If we race on finding an entry, just loop back again.
-		 * Should be very rare, as the window is only updated
-		 * occasionally
-		 */
-	} while (!nr);
+	cb->timer_fn(cb);
 }
 
-static void __blk_stat_init(struct blk_rq_stat *stat, s64 time_now)
+struct blk_stat_callback *
+blk_stat_alloc_callback(void (*timer_fn)(struct blk_stat_callback *),
+			int (*bucket_fn)(const struct request *),
+			unsigned int buckets, void *data)
 {
-	stat->min = -1ULL;
-	stat->max = stat->nr_samples = stat->mean = 0;
-	stat->batch = stat->nr_batch = 0;
-	stat->time = time_now & BLK_STAT_NSEC_MASK;
-}
+	struct blk_stat_callback *cb;
 
-void blk_stat_init(struct blk_rq_stat *stat)
-{
-	__blk_stat_init(stat, ktime_to_ns(ktime_get()));
-}
+	cb = kmalloc(sizeof(*cb), GFP_KERNEL);
+	if (!cb)
+		return NULL;
 
-static bool __blk_stat_is_current(struct blk_rq_stat *stat, s64 now)
-{
-	return (now & BLK_STAT_NSEC_MASK) == (stat->time & BLK_STAT_NSEC_MASK);
+	cb->stat = kmalloc_array(buckets, sizeof(struct blk_rq_stat),
+				 GFP_KERNEL);
+	if (!cb->stat) {
+		kfree(cb);
+		return NULL;
+	}
+	cb->cpu_stat = __alloc_percpu(buckets * sizeof(struct blk_rq_stat),
+				      __alignof__(struct blk_rq_stat));
+	if (!cb->cpu_stat) {
+		kfree(cb->stat);
+		kfree(cb);
+		return NULL;
+	}
+
+	cb->timer_fn = timer_fn;
+	cb->bucket_fn = bucket_fn;
+	cb->data = data;
+	cb->buckets = buckets;
+	setup_timer(&cb->timer, blk_stat_timer_fn, (unsigned long)cb);
+
+	return cb;
 }
+EXPORT_SYMBOL_GPL(blk_stat_alloc_callback);
 
-bool blk_stat_is_current(struct blk_rq_stat *stat)
+void blk_stat_add_callback(struct request_queue *q,
+			   struct blk_stat_callback *cb)
 {
-	return __blk_stat_is_current(stat, ktime_to_ns(ktime_get()));
+	unsigned int bucket;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct blk_rq_stat *cpu_stat;
+
+		cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu);
+		for (bucket = 0; bucket < cb->buckets; bucket++)
+			blk_stat_init(&cpu_stat[bucket]);
+	}
+
+	spin_lock(&q->stats->lock);
+	list_add_tail_rcu(&cb->list, &q->stats->callbacks);
+	set_bit(QUEUE_FLAG_STATS, &q->queue_flags);
+	spin_unlock(&q->stats->lock);
 }
+EXPORT_SYMBOL_GPL(blk_stat_add_callback);
 
-void blk_stat_add(struct blk_rq_stat *stat, struct request *rq)
+void blk_stat_remove_callback(struct request_queue *q,
+			      struct blk_stat_callback *cb)
 {
-	s64 now, value;
+	spin_lock(&q->stats->lock);
+	list_del_rcu(&cb->list);
+	if (list_empty(&q->stats->callbacks) && !q->stats->enable_accounting)
+		clear_bit(QUEUE_FLAG_STATS, &q->queue_flags);
+	spin_unlock(&q->stats->lock);
 
-	now = __blk_stat_time(ktime_to_ns(ktime_get()));
-	if (now < blk_stat_time(&rq->issue_stat))
-		return;
-
-	if (!__blk_stat_is_current(stat, now))
-		__blk_stat_init(stat, now);
+	del_timer_sync(&cb->timer);
+}
+EXPORT_SYMBOL_GPL(blk_stat_remove_callback);
 
-	value = now - blk_stat_time(&rq->issue_stat);
-	if (value > stat->max)
-		stat->max = value;
-	if (value < stat->min)
-		stat->min = value;
+static void blk_stat_free_callback_rcu(struct rcu_head *head)
+{
+	struct blk_stat_callback *cb;
 
-	if (stat->batch + value < stat->batch ||
-	    stat->nr_batch + 1 == BLK_RQ_STAT_BATCH)
-		blk_stat_flush_batch(stat);
+	cb = container_of(head, struct blk_stat_callback, rcu);
+	free_percpu(cb->cpu_stat);
+	kfree(cb->stat);
+	kfree(cb);
+}
 
-	stat->batch += value;
-	stat->nr_batch++;
+void blk_stat_free_callback(struct blk_stat_callback *cb)
+{
+	if (cb)
+		call_rcu(&cb->rcu, blk_stat_free_callback_rcu);
 }
+EXPORT_SYMBOL_GPL(blk_stat_free_callback);
 
-void blk_stat_clear(struct request_queue *q)
+void blk_stat_enable_accounting(struct request_queue *q)
 {
-	if (q->mq_ops) {
-		struct blk_mq_hw_ctx *hctx;
-		struct blk_mq_ctx *ctx;
-		int i, j;
-
-		queue_for_each_hw_ctx(q, hctx, i) {
-			hctx_for_each_ctx(hctx, ctx, j) {
-				blk_stat_init(&ctx->stat[BLK_STAT_READ]);
-				blk_stat_init(&ctx->stat[BLK_STAT_WRITE]);
-			}
-		}
-	} else {
-		blk_stat_init(&q->rq_stats[BLK_STAT_READ]);
-		blk_stat_init(&q->rq_stats[BLK_STAT_WRITE]);
-	}
+	spin_lock(&q->stats->lock);
+	q->stats->enable_accounting = true;
+	set_bit(QUEUE_FLAG_STATS, &q->queue_flags);
+	spin_unlock(&q->stats->lock);
 }
 
-void blk_stat_set_issue_time(struct blk_issue_stat *stat)
+struct blk_queue_stats *blk_alloc_queue_stats(void)
 {
-	stat->time = (stat->time & BLK_STAT_MASK) |
-			(ktime_to_ns(ktime_get()) & BLK_STAT_TIME_MASK);
+	struct blk_queue_stats *stats;
+
+	stats = kmalloc(sizeof(*stats), GFP_KERNEL);
+	if (!stats)
+		return NULL;
+
+	INIT_LIST_HEAD(&stats->callbacks);
+	spin_lock_init(&stats->lock);
+	stats->enable_accounting = false;
+
+	return stats;
 }
 
-/*
- * Enable stat tracking, return whether it was enabled
- */
-bool blk_stat_enable(struct request_queue *q)
+void blk_free_queue_stats(struct blk_queue_stats *stats)
 {
-	if (!test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
-		set_bit(QUEUE_FLAG_STATS, &q->queue_flags);
-		return false;
-	}
+	if (!stats)
+		return;
+
+	WARN_ON(!list_empty(&stats->callbacks));
 
-	return true;
+	kfree(stats);
 }

block/blk-stat.h

@@ -1,33 +1,85 @@
 #ifndef BLK_STAT_H
 #define BLK_STAT_H
 
-/*
- * ~0.13s window as a power-of-2 (2^27 nsecs)
- */
-#define BLK_STAT_NSEC		134217728ULL
-#define BLK_STAT_NSEC_MASK	~(BLK_STAT_NSEC - 1)
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/ktime.h>
+#include <linux/rcupdate.h>
+#include <linux/timer.h>
 
 /*
- * Upper 3 bits can be used elsewhere
+ * from upper:
+ * 3 bits: reserved for other usage
+ * 12 bits: size
+ * 49 bits: time
  */
 #define BLK_STAT_RES_BITS	3
-#define BLK_STAT_SHIFT		(64 - BLK_STAT_RES_BITS)
-#define BLK_STAT_TIME_MASK	((1ULL << BLK_STAT_SHIFT) - 1)
-#define BLK_STAT_MASK		~BLK_STAT_TIME_MASK
+#define BLK_STAT_SIZE_BITS	12
+#define BLK_STAT_RES_SHIFT	(64 - BLK_STAT_RES_BITS)
+#define BLK_STAT_SIZE_SHIFT	(BLK_STAT_RES_SHIFT - BLK_STAT_SIZE_BITS)
+#define BLK_STAT_TIME_MASK	((1ULL << BLK_STAT_SIZE_SHIFT) - 1)
+#define BLK_STAT_SIZE_MASK	\
+	(((1ULL << BLK_STAT_SIZE_BITS) - 1) << BLK_STAT_SIZE_SHIFT)
+#define BLK_STAT_RES_MASK	(~((1ULL << BLK_STAT_RES_SHIFT) - 1))
+
+/**
+ * struct blk_stat_callback - Block statistics callback.
+ *
+ * A &struct blk_stat_callback is associated with a &struct request_queue. While
+ * @timer is active, that queue's request completion latencies are sorted into
+ * buckets by @bucket_fn and added to a per-cpu buffer, @cpu_stat. When the
+ * timer fires, @cpu_stat is flushed to @stat and @timer_fn is invoked.
+ */
+struct blk_stat_callback {
+	/*
+	 * @list: RCU list of callbacks for a &struct request_queue.
+	 */
+	struct list_head list;
+
+	/**
+	 * @timer: Timer for the next callback invocation.
+	 */
+	struct timer_list timer;
+
+	/**
+	 * @cpu_stat: Per-cpu statistics buckets.
+	 */
+	struct blk_rq_stat __percpu *cpu_stat;
+
+	/**
+	 * @bucket_fn: Given a request, returns which statistics bucket it
+	 * should be accounted under. Return -1 for no bucket for this
+	 * request.
+	 */
+	int (*bucket_fn)(const struct request *);
+
+	/**
+	 * @buckets: Number of statistics buckets.
+	 */
+	unsigned int buckets;
+
+	/**
+	 * @stat: Array of statistics buckets.
+	 */
+	struct blk_rq_stat *stat;
+
+	/**
+	 * @fn: Callback function.
+	 */
+	void (*timer_fn)(struct blk_stat_callback *);
+
+	/**
+	 * @data: Private pointer for the user.
+	 */
+	void *data;
 
-enum {
-	BLK_STAT_READ	= 0,
-	BLK_STAT_WRITE,
+	struct rcu_head rcu;
 };
 
-void blk_stat_add(struct blk_rq_stat *, struct request *);
-void blk_hctx_stat_get(struct blk_mq_hw_ctx *, struct blk_rq_stat *);
-void blk_queue_stat_get(struct request_queue *, struct blk_rq_stat *);
-void blk_stat_clear(struct request_queue *);
-void blk_stat_init(struct blk_rq_stat *);
-bool blk_stat_is_current(struct blk_rq_stat *);
-void blk_stat_set_issue_time(struct blk_issue_stat *);
-bool blk_stat_enable(struct request_queue *);
+struct blk_queue_stats *blk_alloc_queue_stats(void);
+void blk_free_queue_stats(struct blk_queue_stats *);
+
+void blk_stat_add(struct request *);
 
 static inline u64 __blk_stat_time(u64 time)
 {
@@ -36,7 +88,117 @@ static inline u64 __blk_stat_time(u64 time)
 
 static inline u64 blk_stat_time(struct blk_issue_stat *stat)
 {
-	return __blk_stat_time(stat->time);
+	return __blk_stat_time(stat->stat);
+}
+
+static inline sector_t blk_capped_size(sector_t size)
+{
+	return size & ((1ULL << BLK_STAT_SIZE_BITS) - 1);
+}
+
+static inline sector_t blk_stat_size(struct blk_issue_stat *stat)
+{
+	return (stat->stat & BLK_STAT_SIZE_MASK) >> BLK_STAT_SIZE_SHIFT;
+}
+
+static inline void blk_stat_set_issue(struct blk_issue_stat *stat,
+	sector_t size)
+{
+	stat->stat = (stat->stat & BLK_STAT_RES_MASK) |
+		(ktime_to_ns(ktime_get()) & BLK_STAT_TIME_MASK) |
+		(((u64)blk_capped_size(size)) << BLK_STAT_SIZE_SHIFT);
+}
+
+/* record time/size info in request but not add a callback */
+void blk_stat_enable_accounting(struct request_queue *q);
+
+/**
+ * blk_stat_alloc_callback() - Allocate a block statistics callback.
+ * @timer_fn: Timer callback function.
+ * @bucket_fn: Bucket callback function.
+ * @buckets: Number of statistics buckets.
+ * @data: Value for the @data field of the &struct blk_stat_callback.
+ *
+ * See &struct blk_stat_callback for details on the callback functions.
+ *
+ * Return: &struct blk_stat_callback on success or NULL on ENOMEM.
+ */
+struct blk_stat_callback *
+blk_stat_alloc_callback(void (*timer_fn)(struct blk_stat_callback *),
+			int (*bucket_fn)(const struct request *),
+			unsigned int buckets, void *data);
+
+/**
+ * blk_stat_add_callback() - Add a block statistics callback to be run on a
+ * request queue.
+ * @q: The request queue.
+ * @cb: The callback.
+ *
+ * Note that a single &struct blk_stat_callback can only be added to a single
+ * &struct request_queue.
+ */
+void blk_stat_add_callback(struct request_queue *q,
+			   struct blk_stat_callback *cb);
+
+/**
+ * blk_stat_remove_callback() - Remove a block statistics callback from a
+ * request queue.
+ * @q: The request queue.
+ * @cb: The callback.
+ *
+ * When this returns, the callback is not running on any CPUs and will not be
+ * called again unless readded.
+ */
+void blk_stat_remove_callback(struct request_queue *q,
+			      struct blk_stat_callback *cb);
+
+/**
+ * blk_stat_free_callback() - Free a block statistics callback.
+ * @cb: The callback.
+ *
+ * @cb may be NULL, in which case this does nothing. If it is not NULL, @cb must
+ * not be associated with a request queue. I.e., if it was previously added with
+ * blk_stat_add_callback(), it must also have been removed since then with
+ * blk_stat_remove_callback().
+ */
+void blk_stat_free_callback(struct blk_stat_callback *cb);
+
+/**
+ * blk_stat_is_active() - Check if a block statistics callback is currently
+ * gathering statistics.
+ * @cb: The callback.
+ */
+static inline bool blk_stat_is_active(struct blk_stat_callback *cb)
+{
+	return timer_pending(&cb->timer);
+}
+
+/**
+ * blk_stat_activate_nsecs() - Gather block statistics during a time window in
+ * nanoseconds.
+ * @cb: The callback.
+ * @nsecs: Number of nanoseconds to gather statistics for.
+ *
+ * The timer callback will be called when the window expires.
+ */
+static inline void blk_stat_activate_nsecs(struct blk_stat_callback *cb,
+					   u64 nsecs)
+{
+	mod_timer(&cb->timer, jiffies + nsecs_to_jiffies(nsecs));
+}
+
+/**
+ * blk_stat_activate_msecs() - Gather block statistics during a time window in
+ * milliseconds.
+ * @cb: The callback.
+ * @msecs: Number of milliseconds to gather statistics for.
+ *
+ * The timer callback will be called when the window expires.
+ */
+static inline void blk_stat_activate_msecs(struct blk_stat_callback *cb,
+					   unsigned int msecs)
+{
+	mod_timer(&cb->timer, jiffies + msecs_to_jiffies(msecs));
 }
 
 #endif

block/blk-sysfs.c

@@ -208,7 +208,7 @@ static ssize_t queue_discard_max_store(struct request_queue *q,
 
 static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page)
 {
-	return queue_var_show(queue_discard_zeroes_data(q), page);
+	return queue_var_show(0, page);
 }
 
 static ssize_t queue_write_same_max_show(struct request_queue *q, char *page)
@@ -503,26 +503,6 @@ static ssize_t queue_dax_show(struct request_queue *q, char *page)
 	return queue_var_show(blk_queue_dax(q), page);
 }
 
-static ssize_t print_stat(char *page, struct blk_rq_stat *stat, const char *pre)
-{
-	return sprintf(page, "%s samples=%llu, mean=%lld, min=%lld, max=%lld\n",
-			pre, (long long) stat->nr_samples,
-			(long long) stat->mean, (long long) stat->min,
-			(long long) stat->max);
-}
-
-static ssize_t queue_stats_show(struct request_queue *q, char *page)
-{
-	struct blk_rq_stat stat[2];
-	ssize_t ret;
-
-	blk_queue_stat_get(q, stat);
-
-	ret = print_stat(page, &stat[BLK_STAT_READ], "read :");
-	ret += print_stat(page + ret, &stat[BLK_STAT_WRITE], "write:");
-	return ret;
-}
-
 static struct queue_sysfs_entry queue_requests_entry = {
 	.attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_requests_show,
@@ -691,17 +671,20 @@ static struct queue_sysfs_entry queue_dax_entry = {
 	.show = queue_dax_show,
 };
 
-static struct queue_sysfs_entry queue_stats_entry = {
-	.attr = {.name = "stats", .mode = S_IRUGO },
-	.show = queue_stats_show,
-};
-
 static struct queue_sysfs_entry queue_wb_lat_entry = {
 	.attr = {.name = "wbt_lat_usec", .mode = S_IRUGO | S_IWUSR },
 	.show = queue_wb_lat_show,
 	.store = queue_wb_lat_store,
 };
 
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+static struct queue_sysfs_entry throtl_sample_time_entry = {
+	.attr = {.name = "throttle_sample_time", .mode = S_IRUGO | S_IWUSR },
+	.show = blk_throtl_sample_time_show,
+	.store = blk_throtl_sample_time_store,
+};
+#endif
+
 static struct attribute *default_attrs[] = {
 	&queue_requests_entry.attr,
 	&queue_ra_entry.attr,
@@ -733,9 +716,11 @@ static struct attribute *default_attrs[] = {
 	&queue_poll_entry.attr,
 	&queue_wc_entry.attr,
 	&queue_dax_entry.attr,
-	&queue_stats_entry.attr,
 	&queue_wb_lat_entry.attr,
 	&queue_poll_delay_entry.attr,
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+	&throtl_sample_time_entry.attr,
+#endif
 	NULL,
 };
 
@@ -810,7 +795,9 @@ static void blk_release_queue(struct kobject *kobj)
 	struct request_queue *q =
 		container_of(kobj, struct request_queue, kobj);
 
-	wbt_exit(q);
+	if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags))
+		blk_stat_remove_callback(q, q->poll_cb);
+	blk_stat_free_callback(q->poll_cb);
 	bdi_put(q->backing_dev_info);
 	blkcg_exit_queue(q);
 
@@ -819,6 +806,8 @@ static void blk_release_queue(struct kobject *kobj)
 		elevator_exit(q, q->elevator);
 	}
 
+	blk_free_queue_stats(q->stats);
+
 	blk_exit_rl(&q->root_rl);
 
 	if (q->queue_tags)
@@ -855,23 +844,6 @@ struct kobj_type blk_queue_ktype = {
 	.release	= blk_release_queue,
 };
 
-static void blk_wb_init(struct request_queue *q)
-{
-#ifndef CONFIG_BLK_WBT_MQ
-	if (q->mq_ops)
-		return;
-#endif
-#ifndef CONFIG_BLK_WBT_SQ
-	if (q->request_fn)
-		return;
-#endif
-
-	/*
-	 * If this fails, we don't get throttling
-	 */
-	wbt_init(q);
-}
-
 int blk_register_queue(struct gendisk *disk)
 {
 	int ret;
@@ -881,6 +853,11 @@ int blk_register_queue(struct gendisk *disk)
 	if (WARN_ON(!q))
 		return -ENXIO;
 
+	WARN_ONCE(test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags),
+		  "%s is registering an already registered queue\n",
+		  kobject_name(&dev->kobj));
+	queue_flag_set_unlocked(QUEUE_FLAG_REGISTERED, q);
+
 	/*
 	 * SCSI probing may synchronously create and destroy a lot of
 	 * request_queues for non-existent devices.  Shutting down a fully
@@ -900,9 +877,6 @@ int blk_register_queue(struct gendisk *disk)
 	if (ret)
 		return ret;
 
-	if (q->mq_ops)
-		blk_mq_register_dev(dev, q);
-
 	/* Prevent changes through sysfs until registration is completed. */
 	mutex_lock(&q->sysfs_lock);
 
@@ -912,9 +886,14 @@ int blk_register_queue(struct gendisk *disk)
 		goto unlock;
 	}
 
+	if (q->mq_ops)
+		__blk_mq_register_dev(dev, q);
+
 	kobject_uevent(&q->kobj, KOBJ_ADD);
 
-	blk_wb_init(q);
+	wbt_enable_default(q);
+
+	blk_throtl_register_queue(q);
 
 	if (q->request_fn || (q->mq_ops && q->elevator)) {
 		ret = elv_register_queue(q);
@@ -939,6 +918,11 @@ void blk_unregister_queue(struct gendisk *disk)
 	if (WARN_ON(!q))
 		return;
 
+	queue_flag_clear_unlocked(QUEUE_FLAG_REGISTERED, q);
+
+	wbt_exit(q);
+
+
 	if (q->mq_ops)
 		blk_mq_unregister_dev(disk_to_dev(disk), q);
 

block/blk-throttle.c

@@ -18,8 +18,17 @@ static int throtl_grp_quantum = 8;
 /* Total max dispatch from all groups in one round */
 static int throtl_quantum = 32;
 
-/* Throttling is performed over 100ms slice and after that slice is renewed */
-static unsigned long throtl_slice = HZ/10;	/* 100 ms */
+/* Throttling is performed over a slice and after that slice is renewed */
+#define DFL_THROTL_SLICE_HD (HZ / 10)
+#define DFL_THROTL_SLICE_SSD (HZ / 50)
+#define MAX_THROTL_SLICE (HZ)
+#define DFL_IDLE_THRESHOLD_SSD (1000L) /* 1 ms */
+#define DFL_IDLE_THRESHOLD_HD (100L * 1000) /* 100 ms */
+#define MAX_IDLE_TIME (5L * 1000 * 1000) /* 5 s */
+/* default latency target is 0, eg, guarantee IO latency by default */
+#define DFL_LATENCY_TARGET (0)
+
+#define SKIP_LATENCY (((u64)1) << BLK_STAT_RES_SHIFT)
 
 static struct blkcg_policy blkcg_policy_throtl;
 
@@ -83,6 +92,12 @@ enum tg_state_flags {
 
 #define rb_entry_tg(node)	rb_entry((node), struct throtl_grp, rb_node)
 
+enum {
+	LIMIT_LOW,
+	LIMIT_MAX,
+	LIMIT_CNT,
+};
+
 struct throtl_grp {
 	/* must be the first member */
 	struct blkg_policy_data pd;
@@ -119,20 +134,54 @@ struct throtl_grp {
 	/* are there any throtl rules between this group and td? */
 	bool has_rules[2];
 
-	/* bytes per second rate limits */
-	uint64_t bps[2];
+	/* internally used bytes per second rate limits */
+	uint64_t bps[2][LIMIT_CNT];
+	/* user configured bps limits */
+	uint64_t bps_conf[2][LIMIT_CNT];
 
-	/* IOPS limits */
-	unsigned int iops[2];
+	/* internally used IOPS limits */
+	unsigned int iops[2][LIMIT_CNT];
+	/* user configured IOPS limits */
+	unsigned int iops_conf[2][LIMIT_CNT];
 
 	/* Number of bytes disptached in current slice */
 	uint64_t bytes_disp[2];
 	/* Number of bio's dispatched in current slice */
 	unsigned int io_disp[2];
 
+	unsigned long last_low_overflow_time[2];
+
+	uint64_t last_bytes_disp[2];
+	unsigned int last_io_disp[2];
+
+	unsigned long last_check_time;
+
+	unsigned long latency_target; /* us */
 	/* When did we start a new slice */
 	unsigned long slice_start[2];
 	unsigned long slice_end[2];
+
+	unsigned long last_finish_time; /* ns / 1024 */
+	unsigned long checked_last_finish_time; /* ns / 1024 */
+	unsigned long avg_idletime; /* ns / 1024 */
+	unsigned long idletime_threshold; /* us */
+
+	unsigned int bio_cnt; /* total bios */
+	unsigned int bad_bio_cnt; /* bios exceeding latency threshold */
+	unsigned long bio_cnt_reset_time;
+};
+
+/* We measure latency for request size from <= 4k to >= 1M */
+#define LATENCY_BUCKET_SIZE 9
+
+struct latency_bucket {
+	unsigned long total_latency; /* ns / 1024 */
+	int samples;
+};
+
+struct avg_latency_bucket {
+	unsigned long latency; /* ns / 1024 */
+	bool valid;
 };
 
 struct throtl_data
@@ -145,8 +194,26 @@ struct throtl_data
 	/* Total Number of queued bios on READ and WRITE lists */
 	unsigned int nr_queued[2];
 
+	unsigned int throtl_slice;
+
 	/* Work for dispatching throttled bios */
 	struct work_struct dispatch_work;
+	unsigned int limit_index;
+	bool limit_valid[LIMIT_CNT];
+
+	unsigned long dft_idletime_threshold; /* us */
+
+	unsigned long low_upgrade_time;
+	unsigned long low_downgrade_time;
+
+	unsigned int scale;
+
+	struct latency_bucket tmp_buckets[LATENCY_BUCKET_SIZE];
+	struct avg_latency_bucket avg_buckets[LATENCY_BUCKET_SIZE];
+	struct latency_bucket __percpu *latency_buckets;
+	unsigned long last_calculate_time;
+
+	bool track_bio_latency;
 };
 
 static void throtl_pending_timer_fn(unsigned long arg);
@@ -198,6 +265,76 @@ static struct throtl_data *sq_to_td(struct throtl_service_queue *sq)
 		return container_of(sq, struct throtl_data, service_queue);
 }
 
+/*
+ * cgroup's limit in LIMIT_MAX is scaled if low limit is set. This scale is to
+ * make the IO dispatch more smooth.
+ * Scale up: linearly scale up according to lapsed time since upgrade. For
+ *           every throtl_slice, the limit scales up 1/2 .low limit till the
+ *           limit hits .max limit
+ * Scale down: exponentially scale down if a cgroup doesn't hit its .low limit
+ */
+static uint64_t throtl_adjusted_limit(uint64_t low, struct throtl_data *td)
+{
+	/* arbitrary value to avoid too big scale */
+	if (td->scale < 4096 && time_after_eq(jiffies,
+	    td->low_upgrade_time + td->scale * td->throtl_slice))
+		td->scale = (jiffies - td->low_upgrade_time) / td->throtl_slice;
+
+	return low + (low >> 1) * td->scale;
+}
+
+static uint64_t tg_bps_limit(struct throtl_grp *tg, int rw)
+{
+	struct blkcg_gq *blkg = tg_to_blkg(tg);
+	struct throtl_data *td;
+	uint64_t ret;
+
+	if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent)
+		return U64_MAX;
+
+	td = tg->td;
+	ret = tg->bps[rw][td->limit_index];
+	if (ret == 0 && td->limit_index == LIMIT_LOW)
+		return tg->bps[rw][LIMIT_MAX];
+
+	if (td->limit_index == LIMIT_MAX && tg->bps[rw][LIMIT_LOW] &&
+	    tg->bps[rw][LIMIT_LOW] != tg->bps[rw][LIMIT_MAX]) {
+		uint64_t adjusted;
+
+		adjusted = throtl_adjusted_limit(tg->bps[rw][LIMIT_LOW], td);
+		ret = min(tg->bps[rw][LIMIT_MAX], adjusted);
+	}
+	return ret;
+}
+
+static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw)
+{
+	struct blkcg_gq *blkg = tg_to_blkg(tg);
+	struct throtl_data *td;
+	unsigned int ret;
+
+	if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent)
+		return UINT_MAX;
+	td = tg->td;
+	ret = tg->iops[rw][td->limit_index];
+	if (ret == 0 && tg->td->limit_index == LIMIT_LOW)
+		return tg->iops[rw][LIMIT_MAX];
+
+	if (td->limit_index == LIMIT_MAX && tg->iops[rw][LIMIT_LOW] &&
+	    tg->iops[rw][LIMIT_LOW] != tg->iops[rw][LIMIT_MAX]) {
+		uint64_t adjusted;
+
+		adjusted = throtl_adjusted_limit(tg->iops[rw][LIMIT_LOW], td);
+		if (adjusted > UINT_MAX)
+			adjusted = UINT_MAX;
+		ret = min_t(unsigned int, tg->iops[rw][LIMIT_MAX], adjusted);
+	}
+	return ret;
+}
+
+#define request_bucket_index(sectors) \
+	clamp_t(int, order_base_2(sectors) - 3, 0, LATENCY_BUCKET_SIZE - 1)
+
 /**
  * throtl_log - log debug message via blktrace
  * @sq: the service_queue being reported
@@ -334,10 +471,17 @@ static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp, int node)
 	}
 
 	RB_CLEAR_NODE(&tg->rb_node);
-	tg->bps[READ] = -1;
-	tg->bps[WRITE] = -1;
-	tg->iops[READ] = -1;
-	tg->iops[WRITE] = -1;
+	tg->bps[READ][LIMIT_MAX] = U64_MAX;
+	tg->bps[WRITE][LIMIT_MAX] = U64_MAX;
+	tg->iops[READ][LIMIT_MAX] = UINT_MAX;
+	tg->iops[WRITE][LIMIT_MAX] = UINT_MAX;
+	tg->bps_conf[READ][LIMIT_MAX] = U64_MAX;
+	tg->bps_conf[WRITE][LIMIT_MAX] = U64_MAX;
+	tg->iops_conf[READ][LIMIT_MAX] = UINT_MAX;
+	tg->iops_conf[WRITE][LIMIT_MAX] = UINT_MAX;
+	/* LIMIT_LOW will have default value 0 */
+
+	tg->latency_target = DFL_LATENCY_TARGET;
 
 	return &tg->pd;
 }
@@ -366,6 +510,8 @@ static void throtl_pd_init(struct blkg_policy_data *pd)
 	if (cgroup_subsys_on_dfl(io_cgrp_subsys) && blkg->parent)
 		sq->parent_sq = &blkg_to_tg(blkg->parent)->service_queue;
 	tg->td = td;
+
+	tg->idletime_threshold = td->dft_idletime_threshold;
 }
 
 /*
@@ -376,20 +522,59 @@ static void throtl_pd_init(struct blkg_policy_data *pd)
 static void tg_update_has_rules(struct throtl_grp *tg)
 {
 	struct throtl_grp *parent_tg = sq_to_tg(tg->service_queue.parent_sq);
+	struct throtl_data *td = tg->td;
 	int rw;
 
 	for (rw = READ; rw <= WRITE; rw++)
 		tg->has_rules[rw] = (parent_tg && parent_tg->has_rules[rw]) ||
-				    (tg->bps[rw] != -1 || tg->iops[rw] != -1);
+			(td->limit_valid[td->limit_index] &&
+			 (tg_bps_limit(tg, rw) != U64_MAX ||
+			  tg_iops_limit(tg, rw) != UINT_MAX));
 }
 
 static void throtl_pd_online(struct blkg_policy_data *pd)
 {
+	struct throtl_grp *tg = pd_to_tg(pd);
 	/*
 	 * We don't want new groups to escape the limits of its ancestors.
 	 * Update has_rules[] after a new group is brought online.
 	 */
-	tg_update_has_rules(pd_to_tg(pd));
+	tg_update_has_rules(tg);
+}
+
+static void blk_throtl_update_limit_valid(struct throtl_data *td)
+{
+	struct cgroup_subsys_state *pos_css;
+	struct blkcg_gq *blkg;
+	bool low_valid = false;
+
+	rcu_read_lock();
+	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
+		struct throtl_grp *tg = blkg_to_tg(blkg);
+
+		if (tg->bps[READ][LIMIT_LOW] || tg->bps[WRITE][LIMIT_LOW] ||
+		    tg->iops[READ][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW])
+			low_valid = true;
+	}
+	rcu_read_unlock();
+
+	td->limit_valid[LIMIT_LOW] = low_valid;
+}
+
+static void throtl_upgrade_state(struct throtl_data *td);
+static void throtl_pd_offline(struct blkg_policy_data *pd)
+{
+	struct throtl_grp *tg = pd_to_tg(pd);
+
+	tg->bps[READ][LIMIT_LOW] = 0;
+	tg->bps[WRITE][LIMIT_LOW] = 0;
+	tg->iops[READ][LIMIT_LOW] = 0;
+	tg->iops[WRITE][LIMIT_LOW] = 0;
+
+	blk_throtl_update_limit_valid(tg->td);
+
+	if (!tg->td->limit_valid[tg->td->limit_index])
+		throtl_upgrade_state(tg->td);
 }
 
 static void throtl_pd_free(struct blkg_policy_data *pd)
@@ -499,6 +684,17 @@ static void throtl_dequeue_tg(struct throtl_grp *tg)
 static void throtl_schedule_pending_timer(struct throtl_service_queue *sq,
 					  unsigned long expires)
 {
+	unsigned long max_expire = jiffies + 8 * sq_to_tg(sq)->td->throtl_slice;
+
+	/*
+	 * Since we are adjusting the throttle limit dynamically, the sleep
+	 * time calculated according to previous limit might be invalid. It's
+	 * possible the cgroup sleep time is very long and no other cgroups
+	 * have IO running so notify the limit changes. Make sure the cgroup
+	 * doesn't sleep too long to avoid the missed notification.
+	 */
+	if (time_after(expires, max_expire))
+		expires = max_expire;
 	mod_timer(&sq->pending_timer, expires);
 	throtl_log(sq, "schedule timer. delay=%lu jiffies=%lu",
 		   expires - jiffies, jiffies);
@@ -556,7 +752,7 @@ static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg,
 	if (time_after_eq(start, tg->slice_start[rw]))
 		tg->slice_start[rw] = start;
 
-	tg->slice_end[rw] = jiffies + throtl_slice;
+	tg->slice_end[rw] = jiffies + tg->td->throtl_slice;
 	throtl_log(&tg->service_queue,
 		   "[%c] new slice with credit start=%lu end=%lu jiffies=%lu",
 		   rw == READ ? 'R' : 'W', tg->slice_start[rw],
@@ -568,7 +764,7 @@ static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw)
 	tg->bytes_disp[rw] = 0;
 	tg->io_disp[rw] = 0;
 	tg->slice_start[rw] = jiffies;
-	tg->slice_end[rw] = jiffies + throtl_slice;
+	tg->slice_end[rw] = jiffies + tg->td->throtl_slice;
 	throtl_log(&tg->service_queue,
 		   "[%c] new slice start=%lu end=%lu jiffies=%lu",
 		   rw == READ ? 'R' : 'W', tg->slice_start[rw],
@@ -578,13 +774,13 @@ static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw)
 static inline void throtl_set_slice_end(struct throtl_grp *tg, bool rw,
 					unsigned long jiffy_end)
 {
-	tg->slice_end[rw] = roundup(jiffy_end, throtl_slice);
+	tg->slice_end[rw] = roundup(jiffy_end, tg->td->throtl_slice);
 }
 
 static inline void throtl_extend_slice(struct throtl_grp *tg, bool rw,
 				       unsigned long jiffy_end)
 {
-	tg->slice_end[rw] = roundup(jiffy_end, throtl_slice);
+	tg->slice_end[rw] = roundup(jiffy_end, tg->td->throtl_slice);
 	throtl_log(&tg->service_queue,
 		   "[%c] extend slice start=%lu end=%lu jiffies=%lu",
 		   rw == READ ? 'R' : 'W', tg->slice_start[rw],
@@ -624,19 +820,20 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
 	 * is bad because it does not allow new slice to start.
 	 */
 
-	throtl_set_slice_end(tg, rw, jiffies + throtl_slice);
+	throtl_set_slice_end(tg, rw, jiffies + tg->td->throtl_slice);
 
 	time_elapsed = jiffies - tg->slice_start[rw];
 
-	nr_slices = time_elapsed / throtl_slice;
+	nr_slices = time_elapsed / tg->td->throtl_slice;
 
 	if (!nr_slices)
 		return;
-	tmp = tg->bps[rw] * throtl_slice * nr_slices;
+	tmp = tg_bps_limit(tg, rw) * tg->td->throtl_slice * nr_slices;
 	do_div(tmp, HZ);
 	bytes_trim = tmp;
 
-	io_trim = (tg->iops[rw] * throtl_slice * nr_slices)/HZ;
+	io_trim = (tg_iops_limit(tg, rw) * tg->td->throtl_slice * nr_slices) /
+		HZ;
 
 	if (!bytes_trim && !io_trim)
 		return;
@@ -651,7 +848,7 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
 	else
 		tg->io_disp[rw] = 0;
 
-	tg->slice_start[rw] += nr_slices * throtl_slice;
+	tg->slice_start[rw] += nr_slices * tg->td->throtl_slice;
 
 	throtl_log(&tg->service_queue,
 		   "[%c] trim slice nr=%lu bytes=%llu io=%lu start=%lu end=%lu jiffies=%lu",
@@ -671,9 +868,9 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
 
 	/* Slice has just started. Consider one slice interval */
 	if (!jiffy_elapsed)
-		jiffy_elapsed_rnd = throtl_slice;
+		jiffy_elapsed_rnd = tg->td->throtl_slice;
 
-	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, throtl_slice);
+	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice);
 
 	/*
 	 * jiffy_elapsed_rnd should not be a big value as minimum iops can be
@@ -682,7 +879,7 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
 	 * have been trimmed.
 	 */
 
-	tmp = (u64)tg->iops[rw] * jiffy_elapsed_rnd;
+	tmp = (u64)tg_iops_limit(tg, rw) * jiffy_elapsed_rnd;
 	do_div(tmp, HZ);
 
 	if (tmp > UINT_MAX)
@@ -697,7 +894,7 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
 	}
 
 	/* Calc approx time to dispatch */
-	jiffy_wait = ((tg->io_disp[rw] + 1) * HZ)/tg->iops[rw] + 1;
+	jiffy_wait = ((tg->io_disp[rw] + 1) * HZ) / tg_iops_limit(tg, rw) + 1;
 
 	if (jiffy_wait > jiffy_elapsed)
 		jiffy_wait = jiffy_wait - jiffy_elapsed;
@@ -720,11 +917,11 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
 
 	/* Slice has just started. Consider one slice interval */
 	if (!jiffy_elapsed)
-		jiffy_elapsed_rnd = throtl_slice;
+		jiffy_elapsed_rnd = tg->td->throtl_slice;
 
-	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, throtl_slice);
+	jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice);
 
-	tmp = tg->bps[rw] * jiffy_elapsed_rnd;
+	tmp = tg_bps_limit(tg, rw) * jiffy_elapsed_rnd;
 	do_div(tmp, HZ);
 	bytes_allowed = tmp;
 
@@ -736,7 +933,7 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
 
 	/* Calc approx time to dispatch */
 	extra_bytes = tg->bytes_disp[rw] + bio->bi_iter.bi_size - bytes_allowed;
-	jiffy_wait = div64_u64(extra_bytes * HZ, tg->bps[rw]);
+	jiffy_wait = div64_u64(extra_bytes * HZ, tg_bps_limit(tg, rw));
 
 	if (!jiffy_wait)
 		jiffy_wait = 1;
@@ -771,7 +968,8 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
 	       bio != throtl_peek_queued(&tg->service_queue.queued[rw]));
 
 	/* If tg->bps = -1, then BW is unlimited */
-	if (tg->bps[rw] == -1 && tg->iops[rw] == -1) {
+	if (tg_bps_limit(tg, rw) == U64_MAX &&
+	    tg_iops_limit(tg, rw) == UINT_MAX) {
 		if (wait)
 			*wait = 0;
 		return true;
@@ -787,8 +985,10 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
 	if (throtl_slice_used(tg, rw) && !(tg->service_queue.nr_queued[rw]))
 		throtl_start_new_slice(tg, rw);
 	else {
-		if (time_before(tg->slice_end[rw], jiffies + throtl_slice))
-			throtl_extend_slice(tg, rw, jiffies + throtl_slice);
+		if (time_before(tg->slice_end[rw],
+		    jiffies + tg->td->throtl_slice))
+			throtl_extend_slice(tg, rw,
+				jiffies + tg->td->throtl_slice);
 	}
 
 	if (tg_with_in_bps_limit(tg, bio, &bps_wait) &&
@@ -816,6 +1016,8 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio)
 	/* Charge the bio to the group */
 	tg->bytes_disp[rw] += bio->bi_iter.bi_size;
 	tg->io_disp[rw]++;
+	tg->last_bytes_disp[rw] += bio->bi_iter.bi_size;
+	tg->last_io_disp[rw]++;
 
 	/*
 	 * BIO_THROTTLED is used to prevent the same bio to be throttled
@@ -999,6 +1201,8 @@ static int throtl_select_dispatch(struct throtl_service_queue *parent_sq)
 	return nr_disp;
 }
 
+static bool throtl_can_upgrade(struct throtl_data *td,
+	struct throtl_grp *this_tg);
 /**
  * throtl_pending_timer_fn - timer function for service_queue->pending_timer
  * @arg: the throtl_service_queue being serviced
@@ -1025,6 +1229,9 @@ static void throtl_pending_timer_fn(unsigned long arg)
 	int ret;
 
 	spin_lock_irq(q->queue_lock);
+	if (throtl_can_upgrade(td, NULL))
+		throtl_upgrade_state(td);
+
 again:
 	parent_sq = sq->parent_sq;
 	dispatched = false;
@@ -1112,7 +1319,7 @@ static u64 tg_prfill_conf_u64(struct seq_file *sf, struct blkg_policy_data *pd,
 	struct throtl_grp *tg = pd_to_tg(pd);
 	u64 v = *(u64 *)((void *)tg + off);
 
-	if (v == -1)
+	if (v == U64_MAX)
 		return 0;
 	return __blkg_prfill_u64(sf, pd, v);
 }
@@ -1123,7 +1330,7 @@ static u64 tg_prfill_conf_uint(struct seq_file *sf, struct blkg_policy_data *pd,
 	struct throtl_grp *tg = pd_to_tg(pd);
 	unsigned int v = *(unsigned int *)((void *)tg + off);
 
-	if (v == -1)
+	if (v == UINT_MAX)
 		return 0;
 	return __blkg_prfill_u64(sf, pd, v);
 }
@@ -1150,8 +1357,8 @@ static void tg_conf_updated(struct throtl_grp *tg)
 
 	throtl_log(&tg->service_queue,
 		   "limit change rbps=%llu wbps=%llu riops=%u wiops=%u",
-		   tg->bps[READ], tg->bps[WRITE],
-		   tg->iops[READ], tg->iops[WRITE]);
+		   tg_bps_limit(tg, READ), tg_bps_limit(tg, WRITE),
+		   tg_iops_limit(tg, READ), tg_iops_limit(tg, WRITE));
 
 	/*
 	 * Update has_rules[] flags for the updated tg's subtree.  A tg is
@@ -1197,7 +1404,7 @@ static ssize_t tg_set_conf(struct kernfs_open_file *of,
 	if (sscanf(ctx.body, "%llu", &v) != 1)
 		goto out_finish;
 	if (!v)
-		v = -1;
+		v = U64_MAX;
 
 	tg = blkg_to_tg(ctx.blkg);
 
@@ -1228,25 +1435,25 @@ static ssize_t tg_set_conf_uint(struct kernfs_open_file *of,
 static struct cftype throtl_legacy_files[] = {
 	{
 		.name = "throttle.read_bps_device",
-		.private = offsetof(struct throtl_grp, bps[READ]),
+		.private = offsetof(struct throtl_grp, bps[READ][LIMIT_MAX]),
 		.seq_show = tg_print_conf_u64,
 		.write = tg_set_conf_u64,
 	},
 	{
 		.name = "throttle.write_bps_device",
-		.private = offsetof(struct throtl_grp, bps[WRITE]),
+		.private = offsetof(struct throtl_grp, bps[WRITE][LIMIT_MAX]),
 		.seq_show = tg_print_conf_u64,
 		.write = tg_set_conf_u64,
 	},
 	{
 		.name = "throttle.read_iops_device",
-		.private = offsetof(struct throtl_grp, iops[READ]),
+		.private = offsetof(struct throtl_grp, iops[READ][LIMIT_MAX]),
 		.seq_show = tg_print_conf_uint,
 		.write = tg_set_conf_uint,
 	},
 	{
 		.name = "throttle.write_iops_device",
-		.private = offsetof(struct throtl_grp, iops[WRITE]),
+		.private = offsetof(struct throtl_grp, iops[WRITE][LIMIT_MAX]),
 		.seq_show = tg_print_conf_uint,
 		.write = tg_set_conf_uint,
 	},
@@ -1263,48 +1470,87 @@ static struct cftype throtl_legacy_files[] = {
 	{ }	/* terminate */
 };
 
-static u64 tg_prfill_max(struct seq_file *sf, struct blkg_policy_data *pd,
+static u64 tg_prfill_limit(struct seq_file *sf, struct blkg_policy_data *pd,
 			 int off)
 {
 	struct throtl_grp *tg = pd_to_tg(pd);
 	const char *dname = blkg_dev_name(pd->blkg);
 	char bufs[4][21] = { "max", "max", "max", "max" };
+	u64 bps_dft;
+	unsigned int iops_dft;
+	char idle_time[26] = "";
+	char latency_time[26] = "";
 
 	if (!dname)
 		return 0;
-	if (tg->bps[READ] == -1 && tg->bps[WRITE] == -1 &&
-	    tg->iops[READ] == -1 && tg->iops[WRITE] == -1)
+
+	if (off == LIMIT_LOW) {
+		bps_dft = 0;
+		iops_dft = 0;
+	} else {
+		bps_dft = U64_MAX;
+		iops_dft = UINT_MAX;
+	}
+
+	if (tg->bps_conf[READ][off] == bps_dft &&
+	    tg->bps_conf[WRITE][off] == bps_dft &&
+	    tg->iops_conf[READ][off] == iops_dft &&
+	    tg->iops_conf[WRITE][off] == iops_dft &&
+	    (off != LIMIT_LOW ||
+	     (tg->idletime_threshold == tg->td->dft_idletime_threshold &&
+	      tg->latency_target == DFL_LATENCY_TARGET)))
 		return 0;
 
-	if (tg->bps[READ] != -1)
-		snprintf(bufs[0], sizeof(bufs[0]), "%llu", tg->bps[READ]);
-	if (tg->bps[WRITE] != -1)
-		snprintf(bufs[1], sizeof(bufs[1]), "%llu", tg->bps[WRITE]);
-	if (tg->iops[READ] != -1)
-		snprintf(bufs[2], sizeof(bufs[2]), "%u", tg->iops[READ]);
-	if (tg->iops[WRITE] != -1)
-		snprintf(bufs[3], sizeof(bufs[3]), "%u", tg->iops[WRITE]);
-
-	seq_printf(sf, "%s rbps=%s wbps=%s riops=%s wiops=%s\n",
-		   dname, bufs[0], bufs[1], bufs[2], bufs[3]);
+	if (tg->bps_conf[READ][off] != bps_dft)
+		snprintf(bufs[0], sizeof(bufs[0]), "%llu",
+			tg->bps_conf[READ][off]);
+	if (tg->bps_conf[WRITE][off] != bps_dft)
+		snprintf(bufs[1], sizeof(bufs[1]), "%llu",
+			tg->bps_conf[WRITE][off]);
+	if (tg->iops_conf[READ][off] != iops_dft)
+		snprintf(bufs[2], sizeof(bufs[2]), "%u",
+			tg->iops_conf[READ][off]);
+	if (tg->iops_conf[WRITE][off] != iops_dft)
+		snprintf(bufs[3], sizeof(bufs[3]), "%u",
+			tg->iops_conf[WRITE][off]);
+	if (off == LIMIT_LOW) {
+		if (tg->idletime_threshold == ULONG_MAX)
+			strcpy(idle_time, " idle=max");
+		else
+			snprintf(idle_time, sizeof(idle_time), " idle=%lu",
+				tg->idletime_threshold);
+
+		if (tg->latency_target == ULONG_MAX)
+			strcpy(latency_time, " latency=max");
+		else
+			snprintf(latency_time, sizeof(latency_time),
+				" latency=%lu", tg->latency_target);
+	}
+
+	seq_printf(sf, "%s rbps=%s wbps=%s riops=%s wiops=%s%s%s\n",
+		   dname, bufs[0], bufs[1], bufs[2], bufs[3], idle_time,
+		   latency_time);
 	return 0;
 }
 
-static int tg_print_max(struct seq_file *sf, void *v)
+static int tg_print_limit(struct seq_file *sf, void *v)
 {
-	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_max,
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), tg_prfill_limit,
 			  &blkcg_policy_throtl, seq_cft(sf)->private, false);
 	return 0;
 }
 
-static ssize_t tg_set_max(struct kernfs_open_file *of,
+static ssize_t tg_set_limit(struct kernfs_open_file *of,
 			  char *buf, size_t nbytes, loff_t off)
 {
 	struct blkcg *blkcg = css_to_blkcg(of_css(of));
 	struct blkg_conf_ctx ctx;
 	struct throtl_grp *tg;
 	u64 v[4];
+	unsigned long idle_time;
+	unsigned long latency_time;
 	int ret;
+	int index = of_cft(of)->private;
 
 	ret = blkg_conf_prep(blkcg, &blkcg_policy_throtl, buf, &ctx);
 	if (ret)
@@ -1312,15 +1558,17 @@ static ssize_t tg_set_max(struct kernfs_open_file *of,
 
 	tg = blkg_to_tg(ctx.blkg);
 
-	v[0] = tg->bps[READ];
-	v[1] = tg->bps[WRITE];
-	v[2] = tg->iops[READ];
-	v[3] = tg->iops[WRITE];
+	v[0] = tg->bps_conf[READ][index];
+	v[1] = tg->bps_conf[WRITE][index];
+	v[2] = tg->iops_conf[READ][index];
+	v[3] = tg->iops_conf[WRITE][index];
 
+	idle_time = tg->idletime_threshold;
+	latency_time = tg->latency_target;
 	while (true) {
 		char tok[27];	/* wiops=18446744073709551616 */
 		char *p;
-		u64 val = -1;
+		u64 val = U64_MAX;
 		int len;
 
 		if (sscanf(ctx.body, "%26s%n", tok, &len) != 1)
@@ -1348,15 +1596,43 @@ static ssize_t tg_set_max(struct kernfs_open_file *of,
 			v[2] = min_t(u64, val, UINT_MAX);
 		else if (!strcmp(tok, "wiops"))
 			v[3] = min_t(u64, val, UINT_MAX);
+		else if (off == LIMIT_LOW && !strcmp(tok, "idle"))
+			idle_time = val;
+		else if (off == LIMIT_LOW && !strcmp(tok, "latency"))
+			latency_time = val;
 		else
 			goto out_finish;
 	}
 
-	tg->bps[READ] = v[0];
-	tg->bps[WRITE] = v[1];
-	tg->iops[READ] = v[2];
-	tg->iops[WRITE] = v[3];
+	tg->bps_conf[READ][index] = v[0];
+	tg->bps_conf[WRITE][index] = v[1];
+	tg->iops_conf[READ][index] = v[2];
+	tg->iops_conf[WRITE][index] = v[3];
 
+	if (index == LIMIT_MAX) {
+		tg->bps[READ][index] = v[0];
+		tg->bps[WRITE][index] = v[1];
+		tg->iops[READ][index] = v[2];
+		tg->iops[WRITE][index] = v[3];
+	}
+	tg->bps[READ][LIMIT_LOW] = min(tg->bps_conf[READ][LIMIT_LOW],
+		tg->bps_conf[READ][LIMIT_MAX]);
+	tg->bps[WRITE][LIMIT_LOW] = min(tg->bps_conf[WRITE][LIMIT_LOW],
+		tg->bps_conf[WRITE][LIMIT_MAX]);
+	tg->iops[READ][LIMIT_LOW] = min(tg->iops_conf[READ][LIMIT_LOW],
+		tg->iops_conf[READ][LIMIT_MAX]);
+	tg->iops[WRITE][LIMIT_LOW] = min(tg->iops_conf[WRITE][LIMIT_LOW],
+		tg->iops_conf[WRITE][LIMIT_MAX]);
+
+	if (index == LIMIT_LOW) {
+		blk_throtl_update_limit_valid(tg->td);
+		if (tg->td->limit_valid[LIMIT_LOW])
+			tg->td->limit_index = LIMIT_LOW;
+		tg->idletime_threshold = (idle_time == ULONG_MAX) ?
+			ULONG_MAX : idle_time;
+		tg->latency_target = (latency_time == ULONG_MAX) ?
+			ULONG_MAX : latency_time;
+	}
 	tg_conf_updated(tg);
 	ret = 0;
 out_finish:
@@ -1365,11 +1641,21 @@ out_finish:
 }
 
 static struct cftype throtl_files[] = {
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+	{
+		.name = "low",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = tg_print_limit,
+		.write = tg_set_limit,
+		.private = LIMIT_LOW,
+	},
+#endif
 	{
 		.name = "max",
 		.flags = CFTYPE_NOT_ON_ROOT,
-		.seq_show = tg_print_max,
-		.write = tg_set_max,
+		.seq_show = tg_print_limit,
+		.write = tg_set_limit,
+		.private = LIMIT_MAX,
 	},
 	{ }	/* terminate */
 };
@@ -1388,9 +1674,376 @@ static struct blkcg_policy blkcg_policy_throtl = {
 	.pd_alloc_fn		= throtl_pd_alloc,
 	.pd_init_fn		= throtl_pd_init,
 	.pd_online_fn		= throtl_pd_online,
+	.pd_offline_fn		= throtl_pd_offline,
 	.pd_free_fn		= throtl_pd_free,
 };
 
+static unsigned long __tg_last_low_overflow_time(struct throtl_grp *tg)
+{
+	unsigned long rtime = jiffies, wtime = jiffies;
+
+	if (tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW])
+		rtime = tg->last_low_overflow_time[READ];
+	if (tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW])
+		wtime = tg->last_low_overflow_time[WRITE];
+	return min(rtime, wtime);
+}
+
+/* tg should not be an intermediate node */
+static unsigned long tg_last_low_overflow_time(struct throtl_grp *tg)
+{
+	struct throtl_service_queue *parent_sq;
+	struct throtl_grp *parent = tg;
+	unsigned long ret = __tg_last_low_overflow_time(tg);
+
+	while (true) {
+		parent_sq = parent->service_queue.parent_sq;
+		parent = sq_to_tg(parent_sq);
+		if (!parent)
+			break;
+
+		/*
+		 * The parent doesn't have low limit, it always reaches low
+		 * limit. Its overflow time is useless for children
+		 */
+		if (!parent->bps[READ][LIMIT_LOW] &&
+		    !parent->iops[READ][LIMIT_LOW] &&
+		    !parent->bps[WRITE][LIMIT_LOW] &&
+		    !parent->iops[WRITE][LIMIT_LOW])
+			continue;
+		if (time_after(__tg_last_low_overflow_time(parent), ret))
+			ret = __tg_last_low_overflow_time(parent);
+	}
+	return ret;
+}
+
+static bool throtl_tg_is_idle(struct throtl_grp *tg)
+{
+	/*
+	 * cgroup is idle if:
+	 * - single idle is too long, longer than a fixed value (in case user
+	 *   configure a too big threshold) or 4 times of slice
+	 * - average think time is more than threshold
+	 * - IO latency is largely below threshold
+	 */
+	unsigned long time = jiffies_to_usecs(4 * tg->td->throtl_slice);
+
+	time = min_t(unsigned long, MAX_IDLE_TIME, time);
+	return (ktime_get_ns() >> 10) - tg->last_finish_time > time ||
+	       tg->avg_idletime > tg->idletime_threshold ||
+	       (tg->latency_target && tg->bio_cnt &&
+		tg->bad_bio_cnt * 5 < tg->bio_cnt);
+}
+
+static bool throtl_tg_can_upgrade(struct throtl_grp *tg)
+{
+	struct throtl_service_queue *sq = &tg->service_queue;
+	bool read_limit, write_limit;
+
+	/*
+	 * if cgroup reaches low limit (if low limit is 0, the cgroup always
+	 * reaches), it's ok to upgrade to next limit
+	 */
+	read_limit = tg->bps[READ][LIMIT_LOW] || tg->iops[READ][LIMIT_LOW];
+	write_limit = tg->bps[WRITE][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW];
+	if (!read_limit && !write_limit)
+		return true;
+	if (read_limit && sq->nr_queued[READ] &&
+	    (!write_limit || sq->nr_queued[WRITE]))
+		return true;
+	if (write_limit && sq->nr_queued[WRITE] &&
+	    (!read_limit || sq->nr_queued[READ]))
+		return true;
+
+	if (time_after_eq(jiffies,
+		tg_last_low_overflow_time(tg) + tg->td->throtl_slice) &&
+	    throtl_tg_is_idle(tg))
+		return true;
+	return false;
+}
+
+static bool throtl_hierarchy_can_upgrade(struct throtl_grp *tg)
+{
+	while (true) {
+		if (throtl_tg_can_upgrade(tg))
+			return true;
+		tg = sq_to_tg(tg->service_queue.parent_sq);
+		if (!tg || !tg_to_blkg(tg)->parent)
+			return false;
+	}
+	return false;
+}
+
+static bool throtl_can_upgrade(struct throtl_data *td,
+	struct throtl_grp *this_tg)
+{
+	struct cgroup_subsys_state *pos_css;
+	struct blkcg_gq *blkg;
+
+	if (td->limit_index != LIMIT_LOW)
+		return false;
+
+	if (time_before(jiffies, td->low_downgrade_time + td->throtl_slice))
+		return false;
+
+	rcu_read_lock();
+	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
+		struct throtl_grp *tg = blkg_to_tg(blkg);
+
+		if (tg == this_tg)
+			continue;
+		if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children))
+			continue;
+		if (!throtl_hierarchy_can_upgrade(tg)) {
+			rcu_read_unlock();
+			return false;
+		}
+	}
+	rcu_read_unlock();
+	return true;
+}
+
+static void throtl_upgrade_check(struct throtl_grp *tg)
+{
+	unsigned long now = jiffies;
+
+	if (tg->td->limit_index != LIMIT_LOW)
+		return;
+
+	if (time_after(tg->last_check_time + tg->td->throtl_slice, now))
+		return;
+
+	tg->last_check_time = now;
+
+	if (!time_after_eq(now,
+	     __tg_last_low_overflow_time(tg) + tg->td->throtl_slice))
+		return;
+
+	if (throtl_can_upgrade(tg->td, NULL))
+		throtl_upgrade_state(tg->td);
+}
+
+static void throtl_upgrade_state(struct throtl_data *td)
+{
+	struct cgroup_subsys_state *pos_css;
+	struct blkcg_gq *blkg;
+
+	td->limit_index = LIMIT_MAX;
+	td->low_upgrade_time = jiffies;
+	td->scale = 0;
+	rcu_read_lock();
+	blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
+		struct throtl_grp *tg = blkg_to_tg(blkg);
+		struct throtl_service_queue *sq = &tg->service_queue;
+
+		tg->disptime = jiffies - 1;
+		throtl_select_dispatch(sq);
+		throtl_schedule_next_dispatch(sq, false);
+	}
+	rcu_read_unlock();
+	throtl_select_dispatch(&td->service_queue);
+	throtl_schedule_next_dispatch(&td->service_queue, false);
+	queue_work(kthrotld_workqueue, &td->dispatch_work);
+}
+
+static void throtl_downgrade_state(struct throtl_data *td, int new)
+{
+	td->scale /= 2;
+
+	if (td->scale) {
+		td->low_upgrade_time = jiffies - td->scale * td->throtl_slice;
+		return;
+	}
+
+	td->limit_index = new;
+	td->low_downgrade_time = jiffies;
+}
+
+static bool throtl_tg_can_downgrade(struct throtl_grp *tg)
+{
+	struct throtl_data *td = tg->td;
+	unsigned long now = jiffies;
+
+	/*
+	 * If cgroup is below low limit, consider downgrade and throttle other
+	 * cgroups
+	 */
+	if (time_after_eq(now, td->low_upgrade_time + td->throtl_slice) &&
+	    time_after_eq(now, tg_last_low_overflow_time(tg) +
+					td->throtl_slice) &&
+	    (!throtl_tg_is_idle(tg) ||
+	     !list_empty(&tg_to_blkg(tg)->blkcg->css.children)))
+		return true;
+	return false;
+}
+
+static bool throtl_hierarchy_can_downgrade(struct throtl_grp *tg)
+{
+	while (true) {
+		if (!throtl_tg_can_downgrade(tg))
+			return false;
+		tg = sq_to_tg(tg->service_queue.parent_sq);
+		if (!tg || !tg_to_blkg(tg)->parent)
+			break;
+	}
+	return true;
+}
+
+static void throtl_downgrade_check(struct throtl_grp *tg)
+{
+	uint64_t bps;
+	unsigned int iops;
+	unsigned long elapsed_time;
+	unsigned long now = jiffies;
+
+	if (tg->td->limit_index != LIMIT_MAX ||
+	    !tg->td->limit_valid[LIMIT_LOW])
+		return;
+	if (!list_empty(&tg_to_blkg(tg)->blkcg->css.children))
+		return;
+	if (time_after(tg->last_check_time + tg->td->throtl_slice, now))
+		return;
+
+	elapsed_time = now - tg->last_check_time;
+	tg->last_check_time = now;
+
+	if (time_before(now, tg_last_low_overflow_time(tg) +
+			tg->td->throtl_slice))
+		return;
+
+	if (tg->bps[READ][LIMIT_LOW]) {
+		bps = tg->last_bytes_disp[READ] * HZ;
+		do_div(bps, elapsed_time);
+		if (bps >= tg->bps[READ][LIMIT_LOW])
+			tg->last_low_overflow_time[READ] = now;
+	}
+
+	if (tg->bps[WRITE][LIMIT_LOW]) {
+		bps = tg->last_bytes_disp[WRITE] * HZ;
+		do_div(bps, elapsed_time);
+		if (bps >= tg->bps[WRITE][LIMIT_LOW])
+			tg->last_low_overflow_time[WRITE] = now;
+	}
+
+	if (tg->iops[READ][LIMIT_LOW]) {
+		iops = tg->last_io_disp[READ] * HZ / elapsed_time;
+		if (iops >= tg->iops[READ][LIMIT_LOW])
+			tg->last_low_overflow_time[READ] = now;
+	}
+
+	if (tg->iops[WRITE][LIMIT_LOW]) {
+		iops = tg->last_io_disp[WRITE] * HZ / elapsed_time;
+		if (iops >= tg->iops[WRITE][LIMIT_LOW])
+			tg->last_low_overflow_time[WRITE] = now;
+	}
+
+	/*
+	 * If cgroup is below low limit, consider downgrade and throttle other
+	 * cgroups
+	 */
+	if (throtl_hierarchy_can_downgrade(tg))
+		throtl_downgrade_state(tg->td, LIMIT_LOW);
+
+	tg->last_bytes_disp[READ] = 0;
+	tg->last_bytes_disp[WRITE] = 0;
+	tg->last_io_disp[READ] = 0;
+	tg->last_io_disp[WRITE] = 0;
+}
+
+static void blk_throtl_update_idletime(struct throtl_grp *tg)
+{
+	unsigned long now = ktime_get_ns() >> 10;
+	unsigned long last_finish_time = tg->last_finish_time;
+
+	if (now <= last_finish_time || last_finish_time == 0 ||
+	    last_finish_time == tg->checked_last_finish_time)
+		return;
+
+	tg->avg_idletime = (tg->avg_idletime * 7 + now - last_finish_time) >> 3;
+	tg->checked_last_finish_time = last_finish_time;
+}
+
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+static void throtl_update_latency_buckets(struct throtl_data *td)
+{
+	struct avg_latency_bucket avg_latency[LATENCY_BUCKET_SIZE];
+	int i, cpu;
+	unsigned long last_latency = 0;
+	unsigned long latency;
+
+	if (!blk_queue_nonrot(td->queue))
+		return;
+	if (time_before(jiffies, td->last_calculate_time + HZ))
+		return;
+	td->last_calculate_time = jiffies;
+
+	memset(avg_latency, 0, sizeof(avg_latency));
+	for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
+		struct latency_bucket *tmp = &td->tmp_buckets[i];
+
+		for_each_possible_cpu(cpu) {
+			struct latency_bucket *bucket;
+
+			/* this isn't race free, but ok in practice */
+			bucket = per_cpu_ptr(td->latency_buckets, cpu);
+			tmp->total_latency += bucket[i].total_latency;
+			tmp->samples += bucket[i].samples;
+			bucket[i].total_latency = 0;
+			bucket[i].samples = 0;
+		}
+
+		if (tmp->samples >= 32) {
+			int samples = tmp->samples;
+
+			latency = tmp->total_latency;
+
+			tmp->total_latency = 0;
+			tmp->samples = 0;
+			latency /= samples;
+			if (latency == 0)
+				continue;
+			avg_latency[i].latency = latency;
+		}
+	}
+
+	for (i = 0; i < LATENCY_BUCKET_SIZE; i++) {
+		if (!avg_latency[i].latency) {
+			if (td->avg_buckets[i].latency < last_latency)
+				td->avg_buckets[i].latency = last_latency;
+			continue;
+		}
+
+		if (!td->avg_buckets[i].valid)
+			latency = avg_latency[i].latency;
+		else
+			latency = (td->avg_buckets[i].latency * 7 +
+				avg_latency[i].latency) >> 3;
+
+		td->avg_buckets[i].latency = max(latency, last_latency);
+		td->avg_buckets[i].valid = true;
+		last_latency = td->avg_buckets[i].latency;
+	}
+}
+#else
+static inline void throtl_update_latency_buckets(struct throtl_data *td)
+{
+}
+#endif
+
+static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio)
+{
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+	int ret;
+
+	ret = bio_associate_current(bio);
+	if (ret == 0 || ret == -EBUSY)
+		bio->bi_cg_private = tg;
+	blk_stat_set_issue(&bio->bi_issue_stat, bio_sectors(bio));
+#else
+	bio_associate_current(bio);
+#endif
+}
+
 bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 		    struct bio *bio)
 {
@@ -1399,6 +2052,7 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 	struct throtl_service_queue *sq;
 	bool rw = bio_data_dir(bio);
 	bool throttled = false;
+	struct throtl_data *td = tg->td;
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
@@ -1408,19 +2062,35 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 
 	spin_lock_irq(q->queue_lock);
 
+	throtl_update_latency_buckets(td);
+
 	if (unlikely(blk_queue_bypass(q)))
 		goto out_unlock;
 
+	blk_throtl_assoc_bio(tg, bio);
+	blk_throtl_update_idletime(tg);
+
 	sq = &tg->service_queue;
 
+again:
 	while (true) {
+		if (tg->last_low_overflow_time[rw] == 0)
+			tg->last_low_overflow_time[rw] = jiffies;
+		throtl_downgrade_check(tg);
+		throtl_upgrade_check(tg);
 		/* throtl is FIFO - if bios are already queued, should queue */
 		if (sq->nr_queued[rw])
 			break;
 
 		/* if above limits, break to queue */
-		if (!tg_may_dispatch(tg, bio, NULL))
+		if (!tg_may_dispatch(tg, bio, NULL)) {
+			tg->last_low_overflow_time[rw] = jiffies;
+			if (throtl_can_upgrade(td, tg)) {
+				throtl_upgrade_state(td);
+				goto again;
+			}
 			break;
+		}
 
 		/* within limits, let's charge and dispatch directly */
 		throtl_charge_bio(tg, bio);
@@ -1453,12 +2123,14 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg,
 	/* out-of-limit, queue to @tg */
 	throtl_log(sq, "[%c] bio. bdisp=%llu sz=%u bps=%llu iodisp=%u iops=%u queued=%d/%d",
 		   rw == READ ? 'R' : 'W',
-		   tg->bytes_disp[rw], bio->bi_iter.bi_size, tg->bps[rw],
-		   tg->io_disp[rw], tg->iops[rw],
+		   tg->bytes_disp[rw], bio->bi_iter.bi_size,
+		   tg_bps_limit(tg, rw),
+		   tg->io_disp[rw], tg_iops_limit(tg, rw),
 		   sq->nr_queued[READ], sq->nr_queued[WRITE]);
 
-	bio_associate_current(bio);
-	tg->td->nr_queued[rw]++;
+	tg->last_low_overflow_time[rw] = jiffies;
+
+	td->nr_queued[rw]++;
 	throtl_add_bio_tg(bio, qn, tg);
 	throttled = true;
 
@@ -1483,9 +2155,94 @@ out:
 	 */
 	if (!throttled)
 		bio_clear_flag(bio, BIO_THROTTLED);
+
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+	if (throttled || !td->track_bio_latency)
+		bio->bi_issue_stat.stat |= SKIP_LATENCY;
+#endif
 	return throttled;
 }
 
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+static void throtl_track_latency(struct throtl_data *td, sector_t size,
+	int op, unsigned long time)
+{
+	struct latency_bucket *latency;
+	int index;
+
+	if (!td || td->limit_index != LIMIT_LOW || op != REQ_OP_READ ||
+	    !blk_queue_nonrot(td->queue))
+		return;
+
+	index = request_bucket_index(size);
+
+	latency = get_cpu_ptr(td->latency_buckets);
+	latency[index].total_latency += time;
+	latency[index].samples++;
+	put_cpu_ptr(td->latency_buckets);
+}
+
+void blk_throtl_stat_add(struct request *rq, u64 time_ns)
+{
+	struct request_queue *q = rq->q;
+	struct throtl_data *td = q->td;
+
+	throtl_track_latency(td, blk_stat_size(&rq->issue_stat),
+		req_op(rq), time_ns >> 10);
+}
+
+void blk_throtl_bio_endio(struct bio *bio)
+{
+	struct throtl_grp *tg;
+	u64 finish_time_ns;
+	unsigned long finish_time;
+	unsigned long start_time;
+	unsigned long lat;
+
+	tg = bio->bi_cg_private;
+	if (!tg)
+		return;
+	bio->bi_cg_private = NULL;
+
+	finish_time_ns = ktime_get_ns();
+	tg->last_finish_time = finish_time_ns >> 10;
+
+	start_time = blk_stat_time(&bio->bi_issue_stat) >> 10;
+	finish_time = __blk_stat_time(finish_time_ns) >> 10;
+	if (!start_time || finish_time <= start_time)
+		return;
+
+	lat = finish_time - start_time;
+	/* this is only for bio based driver */
+	if (!(bio->bi_issue_stat.stat & SKIP_LATENCY))
+		throtl_track_latency(tg->td, blk_stat_size(&bio->bi_issue_stat),
+			bio_op(bio), lat);
+
+	if (tg->latency_target) {
+		int bucket;
+		unsigned int threshold;
+
+		bucket = request_bucket_index(
+			blk_stat_size(&bio->bi_issue_stat));
+		threshold = tg->td->avg_buckets[bucket].latency +
+			tg->latency_target;
+		if (lat > threshold)
+			tg->bad_bio_cnt++;
+		/*
+		 * Not race free, could get wrong count, which means cgroups
+		 * will be throttled
+		 */
+		tg->bio_cnt++;
+	}
+
+	if (time_after(jiffies, tg->bio_cnt_reset_time) || tg->bio_cnt > 1024) {
+		tg->bio_cnt_reset_time = tg->td->throtl_slice + jiffies;
+		tg->bio_cnt /= 2;
+		tg->bad_bio_cnt /= 2;
+	}
+}
+#endif
+
 /*
  * Dispatch all bios from all children tg's queued on @parent_sq.  On
  * return, @parent_sq is guaranteed to not have any active children tg's
@@ -1558,6 +2315,12 @@ int blk_throtl_init(struct request_queue *q)
 	td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node);
 	if (!td)
 		return -ENOMEM;
+	td->latency_buckets = __alloc_percpu(sizeof(struct latency_bucket) *
+		LATENCY_BUCKET_SIZE, __alignof__(u64));
+	if (!td->latency_buckets) {
+		kfree(td);
+		return -ENOMEM;
+	}
 
 	INIT_WORK(&td->dispatch_work, blk_throtl_dispatch_work_fn);
 	throtl_service_queue_init(&td->service_queue);
@@ -1565,10 +2328,17 @@ int blk_throtl_init(struct request_queue *q)
 	q->td = td;
 	td->queue = q;
 
+	td->limit_valid[LIMIT_MAX] = true;
+	td->limit_index = LIMIT_MAX;
+	td->low_upgrade_time = jiffies;
+	td->low_downgrade_time = jiffies;
+
 	/* activate policy */
 	ret = blkcg_activate_policy(q, &blkcg_policy_throtl);
-	if (ret)
+	if (ret) {
+		free_percpu(td->latency_buckets);
 		kfree(td);
+	}
 	return ret;
 }
 
@@ -1577,9 +2347,74 @@ void blk_throtl_exit(struct request_queue *q)
 	BUG_ON(!q->td);
 	throtl_shutdown_wq(q);
 	blkcg_deactivate_policy(q, &blkcg_policy_throtl);
+	free_percpu(q->td->latency_buckets);
 	kfree(q->td);
 }
 
+void blk_throtl_register_queue(struct request_queue *q)
+{
+	struct throtl_data *td;
+	struct cgroup_subsys_state *pos_css;
+	struct blkcg_gq *blkg;
+
+	td = q->td;
+	BUG_ON(!td);
+
+	if (blk_queue_nonrot(q)) {
+		td->throtl_slice = DFL_THROTL_SLICE_SSD;
+		td->dft_idletime_threshold = DFL_IDLE_THRESHOLD_SSD;
+	} else {
+		td->throtl_slice = DFL_THROTL_SLICE_HD;
+		td->dft_idletime_threshold = DFL_IDLE_THRESHOLD_HD;
+	}
+#ifndef CONFIG_BLK_DEV_THROTTLING_LOW
+	/* if no low limit, use previous default */
+	td->throtl_slice = DFL_THROTL_SLICE_HD;
+#endif
+
+	td->track_bio_latency = !q->mq_ops && !q->request_fn;
+	if (!td->track_bio_latency)
+		blk_stat_enable_accounting(q);
+
+	/*
+	 * some tg are created before queue is fully initialized, eg, nonrot
+	 * isn't initialized yet
+	 */
+	rcu_read_lock();
+	blkg_for_each_descendant_post(blkg, pos_css, q->root_blkg) {
+		struct throtl_grp *tg = blkg_to_tg(blkg);
+
+		tg->idletime_threshold = td->dft_idletime_threshold;
+	}
+	rcu_read_unlock();
+}
+
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page)
+{
+	if (!q->td)
+		return -EINVAL;
+	return sprintf(page, "%u\n", jiffies_to_msecs(q->td->throtl_slice));
+}
+
+ssize_t blk_throtl_sample_time_store(struct request_queue *q,
+	const char *page, size_t count)
+{
+	unsigned long v;
+	unsigned long t;
+
+	if (!q->td)
+		return -EINVAL;
+	if (kstrtoul(page, 10, &v))
+		return -EINVAL;
+	t = msecs_to_jiffies(v);
+	if (t == 0 || t > MAX_THROTL_SLICE)
+		return -EINVAL;
+	q->td->throtl_slice = t;
+	return count;
+}
+#endif
+
 static int __init throtl_init(void)
 {
 	kthrotld_workqueue = alloc_workqueue("kthrotld", WQ_MEM_RECLAIM, 0);

block/blk-timeout.c

@@ -89,7 +89,6 @@ static void blk_rq_timed_out(struct request *req)
 		ret = q->rq_timed_out_fn(req);
 	switch (ret) {
 	case BLK_EH_HANDLED:
-		/* Can we use req->errors here? */
 		__blk_complete_request(req);
 		break;
 	case BLK_EH_RESET_TIMER:

block/blk-wbt.c

@@ -255,8 +255,8 @@ static inline bool stat_sample_valid(struct blk_rq_stat *stat)
 	 * that it's writes impacting us, and not just some sole read on
 	 * a device that is in a lower power state.
 	 */
-	return stat[BLK_STAT_READ].nr_samples >= 1 &&
-		stat[BLK_STAT_WRITE].nr_samples >= RWB_MIN_WRITE_SAMPLES;
+	return (stat[READ].nr_samples >= 1 &&
+		stat[WRITE].nr_samples >= RWB_MIN_WRITE_SAMPLES);
 }
 
 static u64 rwb_sync_issue_lat(struct rq_wb *rwb)
@@ -277,7 +277,7 @@ enum {
 	LAT_EXCEEDED,
 };
 
-static int __latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
+static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 {
 	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
 	u64 thislat;
@@ -293,7 +293,7 @@ static int __latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 	 */
 	thislat = rwb_sync_issue_lat(rwb);
 	if (thislat > rwb->cur_win_nsec ||
-	    (thislat > rwb->min_lat_nsec && !stat[BLK_STAT_READ].nr_samples)) {
+	    (thislat > rwb->min_lat_nsec && !stat[READ].nr_samples)) {
 		trace_wbt_lat(bdi, thislat);
 		return LAT_EXCEEDED;
 	}
@@ -308,8 +308,8 @@ static int __latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 		 * waited or still has writes in flights, consider us doing
 		 * just writes as well.
 		 */
-		if ((stat[BLK_STAT_WRITE].nr_samples && blk_stat_is_current(stat)) ||
-		    wb_recent_wait(rwb) || wbt_inflight(rwb))
+		if (stat[WRITE].nr_samples || wb_recent_wait(rwb) ||
+		    wbt_inflight(rwb))
 			return LAT_UNKNOWN_WRITES;
 		return LAT_UNKNOWN;
 	}
@@ -317,8 +317,8 @@ static int __latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 	/*
 	 * If the 'min' latency exceeds our target, step down.
 	 */
-	if (stat[BLK_STAT_READ].min > rwb->min_lat_nsec) {
-		trace_wbt_lat(bdi, stat[BLK_STAT_READ].min);
+	if (stat[READ].min > rwb->min_lat_nsec) {
+		trace_wbt_lat(bdi, stat[READ].min);
 		trace_wbt_stat(bdi, stat);
 		return LAT_EXCEEDED;
 	}
@@ -329,14 +329,6 @@ static int __latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 	return LAT_OK;
 }
 
-static int latency_exceeded(struct rq_wb *rwb)
-{
-	struct blk_rq_stat stat[2];
-
-	blk_queue_stat_get(rwb->queue, stat);
-	return __latency_exceeded(rwb, stat);
-}
-
 static void rwb_trace_step(struct rq_wb *rwb, const char *msg)
 {
 	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
@@ -355,7 +347,6 @@ static void scale_up(struct rq_wb *rwb)
 
 	rwb->scale_step--;
 	rwb->unknown_cnt = 0;
-	blk_stat_clear(rwb->queue);
 
 	rwb->scaled_max = calc_wb_limits(rwb);
 
@@ -385,15 +376,12 @@ static void scale_down(struct rq_wb *rwb, bool hard_throttle)
 
 	rwb->scaled_max = false;
 	rwb->unknown_cnt = 0;
-	blk_stat_clear(rwb->queue);
 	calc_wb_limits(rwb);
 	rwb_trace_step(rwb, "step down");
 }
 
 static void rwb_arm_timer(struct rq_wb *rwb)
 {
-	unsigned long expires;
-
 	if (rwb->scale_step > 0) {
 		/*
 		 * We should speed this up, using some variant of a fast
@@ -411,17 +399,16 @@ static void rwb_arm_timer(struct rq_wb *rwb)
 		rwb->cur_win_nsec = rwb->win_nsec;
 	}
 
-	expires = jiffies + nsecs_to_jiffies(rwb->cur_win_nsec);
-	mod_timer(&rwb->window_timer, expires);
+	blk_stat_activate_nsecs(rwb->cb, rwb->cur_win_nsec);
 }
 
-static void wb_timer_fn(unsigned long data)
+static void wb_timer_fn(struct blk_stat_callback *cb)
 {
-	struct rq_wb *rwb = (struct rq_wb *) data;
+	struct rq_wb *rwb = cb->data;
 	unsigned int inflight = wbt_inflight(rwb);
 	int status;
 
-	status = latency_exceeded(rwb);
+	status = latency_exceeded(rwb, cb->stat);
 
 	trace_wbt_timer(rwb->queue->backing_dev_info, status, rwb->scale_step,
 			inflight);
@@ -614,7 +601,7 @@ enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock)
 
 	__wbt_wait(rwb, bio->bi_opf, lock);
 
-	if (!timer_pending(&rwb->window_timer))
+	if (!blk_stat_is_active(rwb->cb))
 		rwb_arm_timer(rwb);
 
 	if (current_is_kswapd())
@@ -666,22 +653,37 @@ void wbt_set_write_cache(struct rq_wb *rwb, bool write_cache_on)
 		rwb->wc = write_cache_on;
 }
 
- /*
- * Disable wbt, if enabled by default. Only called from CFQ, if we have
- * cgroups enabled
+/*
+ * Disable wbt, if enabled by default. Only called from CFQ.
  */
 void wbt_disable_default(struct request_queue *q)
 {
 	struct rq_wb *rwb = q->rq_wb;
 
-	if (rwb && rwb->enable_state == WBT_STATE_ON_DEFAULT) {
-		del_timer_sync(&rwb->window_timer);
-		rwb->win_nsec = rwb->min_lat_nsec = 0;
-		wbt_update_limits(rwb);
-	}
+	if (rwb && rwb->enable_state == WBT_STATE_ON_DEFAULT)
+		wbt_exit(q);
 }
 EXPORT_SYMBOL_GPL(wbt_disable_default);
 
+/*
+ * Enable wbt if defaults are configured that way
+ */
+void wbt_enable_default(struct request_queue *q)
+{
+	/* Throttling already enabled? */
+	if (q->rq_wb)
+		return;
+
+	/* Queue not registered? Maybe shutting down... */
+	if (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags))
+		return;
+
+	if ((q->mq_ops && IS_ENABLED(CONFIG_BLK_WBT_MQ)) ||
+	    (q->request_fn && IS_ENABLED(CONFIG_BLK_WBT_SQ)))
+		wbt_init(q);
+}
+EXPORT_SYMBOL_GPL(wbt_enable_default);
+
 u64 wbt_default_latency_nsec(struct request_queue *q)
 {
 	/*
@@ -694,29 +696,33 @@ u64 wbt_default_latency_nsec(struct request_queue *q)
 		return 75000000ULL;
 }
 
+static int wbt_data_dir(const struct request *rq)
+{
+	return rq_data_dir(rq);
+}
+
 int wbt_init(struct request_queue *q)
 {
 	struct rq_wb *rwb;
 	int i;
 
-	/*
-	 * For now, we depend on the stats window being larger than
-	 * our monitoring window. Ensure that this isn't inadvertently
-	 * violated.
-	 */
-	BUILD_BUG_ON(RWB_WINDOW_NSEC > BLK_STAT_NSEC);
 	BUILD_BUG_ON(WBT_NR_BITS > BLK_STAT_RES_BITS);
 
 	rwb = kzalloc(sizeof(*rwb), GFP_KERNEL);
 	if (!rwb)
 		return -ENOMEM;
 
+	rwb->cb = blk_stat_alloc_callback(wb_timer_fn, wbt_data_dir, 2, rwb);
+	if (!rwb->cb) {
+		kfree(rwb);
+		return -ENOMEM;
+	}
+
 	for (i = 0; i < WBT_NUM_RWQ; i++) {
 		atomic_set(&rwb->rq_wait[i].inflight, 0);
 		init_waitqueue_head(&rwb->rq_wait[i].wait);
 	}
 
-	setup_timer(&rwb->window_timer, wb_timer_fn, (unsigned long) rwb);
 	rwb->wc = 1;
 	rwb->queue_depth = RWB_DEF_DEPTH;
 	rwb->last_comp = rwb->last_issue = jiffies;
@@ -726,10 +732,10 @@ int wbt_init(struct request_queue *q)
 	wbt_update_limits(rwb);
 
 	/*
-	 * Assign rwb, and turn on stats tracking for this queue
+	 * Assign rwb and add the stats callback.
 	 */
 	q->rq_wb = rwb;
-	blk_stat_enable(q);
+	blk_stat_add_callback(q, rwb->cb);
 
 	rwb->min_lat_nsec = wbt_default_latency_nsec(q);
 
@@ -744,7 +750,8 @@ void wbt_exit(struct request_queue *q)
 	struct rq_wb *rwb = q->rq_wb;
 
 	if (rwb) {
-		del_timer_sync(&rwb->window_timer);
+		blk_stat_remove_callback(q, rwb->cb);
+		blk_stat_free_callback(rwb->cb);
 		q->rq_wb = NULL;
 		kfree(rwb);
 	}

block/blk-wbt.h

@@ -32,27 +32,27 @@ enum {
 
 static inline void wbt_clear_state(struct blk_issue_stat *stat)
 {
-	stat->time &= BLK_STAT_TIME_MASK;
+	stat->stat &= ~BLK_STAT_RES_MASK;
 }
 
 static inline enum wbt_flags wbt_stat_to_mask(struct blk_issue_stat *stat)
 {
-	return (stat->time & BLK_STAT_MASK) >> BLK_STAT_SHIFT;
+	return (stat->stat & BLK_STAT_RES_MASK) >> BLK_STAT_RES_SHIFT;
 }
 
 static inline void wbt_track(struct blk_issue_stat *stat, enum wbt_flags wb_acct)
 {
-	stat->time |= ((u64) wb_acct) << BLK_STAT_SHIFT;
+	stat->stat |= ((u64) wb_acct) << BLK_STAT_RES_SHIFT;
 }
 
 static inline bool wbt_is_tracked(struct blk_issue_stat *stat)
 {
-	return (stat->time >> BLK_STAT_SHIFT) & WBT_TRACKED;
+	return (stat->stat >> BLK_STAT_RES_SHIFT) & WBT_TRACKED;
 }
 
 static inline bool wbt_is_read(struct blk_issue_stat *stat)
 {
-	return (stat->time >> BLK_STAT_SHIFT) & WBT_READ;
+	return (stat->stat >> BLK_STAT_RES_SHIFT) & WBT_READ;
 }
 
 struct rq_wait {
@@ -81,7 +81,7 @@ struct rq_wb {
 	u64 win_nsec;				/* default window size */
 	u64 cur_win_nsec;			/* current window size */
 
-	struct timer_list window_timer;
+	struct blk_stat_callback *cb;
 
 	s64 sync_issue;
 	void *sync_cookie;
@@ -117,6 +117,7 @@ void wbt_update_limits(struct rq_wb *);
 void wbt_requeue(struct rq_wb *, struct blk_issue_stat *);
 void wbt_issue(struct rq_wb *, struct blk_issue_stat *);
 void wbt_disable_default(struct request_queue *);
+void wbt_enable_default(struct request_queue *);
 
 void wbt_set_queue_depth(struct rq_wb *, unsigned int);
 void wbt_set_write_cache(struct rq_wb *, bool);
@@ -155,6 +156,9 @@ static inline void wbt_issue(struct rq_wb *rwb, struct blk_issue_stat *stat)
 static inline void wbt_disable_default(struct request_queue *q)
 {
 }
+static inline void wbt_enable_default(struct request_queue *q)
+{
+}
 static inline void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth)
 {
 }

block/blk.h

@@ -60,15 +60,12 @@ void blk_free_flush_queue(struct blk_flush_queue *q);
 int blk_init_rl(struct request_list *rl, struct request_queue *q,
 		gfp_t gfp_mask);
 void blk_exit_rl(struct request_list *rl);
-void init_request_from_bio(struct request *req, struct bio *bio);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 			struct bio *bio);
 void blk_queue_bypass_start(struct request_queue *q);
 void blk_queue_bypass_end(struct request_queue *q);
 void blk_dequeue_request(struct request *rq);
 void __blk_queue_free_tags(struct request_queue *q);
-bool __blk_end_bidi_request(struct request *rq, int error,
-			    unsigned int nr_bytes, unsigned int bidi_bytes);
 void blk_freeze_queue(struct request_queue *q);
 
 static inline void blk_queue_enter_live(struct request_queue *q)
@@ -319,10 +316,22 @@ static inline struct io_context *create_io_context(gfp_t gfp_mask, int node)
 extern void blk_throtl_drain(struct request_queue *q);
 extern int blk_throtl_init(struct request_queue *q);
 extern void blk_throtl_exit(struct request_queue *q);
+extern void blk_throtl_register_queue(struct request_queue *q);
 #else /* CONFIG_BLK_DEV_THROTTLING */
 static inline void blk_throtl_drain(struct request_queue *q) { }
 static inline int blk_throtl_init(struct request_queue *q) { return 0; }
 static inline void blk_throtl_exit(struct request_queue *q) { }
+static inline void blk_throtl_register_queue(struct request_queue *q) { }
 #endif /* CONFIG_BLK_DEV_THROTTLING */
+#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
+extern ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page);
+extern ssize_t blk_throtl_sample_time_store(struct request_queue *q,
+	const char *page, size_t count);
+extern void blk_throtl_bio_endio(struct bio *bio);
+extern void blk_throtl_stat_add(struct request *rq, u64 time);
+#else
+static inline void blk_throtl_bio_endio(struct bio *bio) { }
+static inline void blk_throtl_stat_add(struct request *rq, u64 time) { }
+#endif
 
 #endif /* BLK_INTERNAL_H */

block/bsg-lib.c

@@ -37,7 +37,7 @@ static void bsg_destroy_job(struct kref *kref)
 	struct bsg_job *job = container_of(kref, struct bsg_job, kref);
 	struct request *rq = job->req;
 
-	blk_end_request_all(rq, rq->errors);
+	blk_end_request_all(rq, scsi_req(rq)->result);
 
 	put_device(job->dev);	/* release reference for the request */
 
@@ -74,7 +74,7 @@ void bsg_job_done(struct bsg_job *job, int result,
 	struct scsi_request *rq = scsi_req(req);
 	int err;
 
-	err = job->req->errors = result;
+	err = scsi_req(job->req)->result = result;
 	if (err < 0)
 		/* we're only returning the result field in the reply */
 		rq->sense_len = sizeof(u32);
@@ -177,7 +177,7 @@ failjob_rls_job:
  * @q: request queue to manage
  *
  * On error the create_bsg_job function should return a -Exyz error value
- * that will be set to the req->errors.
+ * that will be set to ->result.
  *
  * Drivers/subsys should pass this to the queue init function.
  */
@@ -201,7 +201,7 @@ static void bsg_request_fn(struct request_queue *q)
 
 		ret = bsg_create_job(dev, req);
 		if (ret) {
-			req->errors = ret;
+			scsi_req(req)->result = ret;
 			blk_end_request_all(req, ret);
 			spin_lock_irq(q->queue_lock);
 			continue;

block/bsg.c

@@ -391,13 +391,13 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	struct scsi_request *req = scsi_req(rq);
 	int ret = 0;
 
-	dprintk("rq %p bio %p 0x%x\n", rq, bio, rq->errors);
+	dprintk("rq %p bio %p 0x%x\n", rq, bio, req->result);
 	/*
 	 * fill in all the output members
 	 */
-	hdr->device_status = rq->errors & 0xff;
-	hdr->transport_status = host_byte(rq->errors);
-	hdr->driver_status = driver_byte(rq->errors);
+	hdr->device_status = req->result & 0xff;
+	hdr->transport_status = host_byte(req->result);
+	hdr->driver_status = driver_byte(req->result);
 	hdr->info = 0;
 	if (hdr->device_status || hdr->transport_status || hdr->driver_status)
 		hdr->info |= SG_INFO_CHECK;
@@ -431,8 +431,8 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	 * just a protocol response (i.e. non negative), that gets
 	 * processed above.
 	 */
-	if (!ret && rq->errors < 0)
-		ret = rq->errors;
+	if (!ret && req->result < 0)
+		ret = req->result;
 
 	blk_rq_unmap_user(bio);
 	scsi_req_free_cmd(req);

block/cfq-iosched.c

@@ -3761,16 +3761,14 @@ static void cfq_init_cfqq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 }
 
 #ifdef CONFIG_CFQ_GROUP_IOSCHED
-static bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
+static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 {
 	struct cfq_data *cfqd = cic_to_cfqd(cic);
 	struct cfq_queue *cfqq;
 	uint64_t serial_nr;
-	bool nonroot_cg;
 
 	rcu_read_lock();
 	serial_nr = bio_blkcg(bio)->css.serial_nr;
-	nonroot_cg = bio_blkcg(bio) != &blkcg_root;
 	rcu_read_unlock();
 
 	/*
@@ -3778,7 +3776,7 @@ static bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 	 * spuriously on a newly created cic but there's no harm.
 	 */
 	if (unlikely(!cfqd) || likely(cic->blkcg_serial_nr == serial_nr))
-		return nonroot_cg;
+		return;
 
 	/*
 	 * Drop reference to queues.  New queues will be assigned in new
@@ -3799,12 +3797,10 @@ static bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 	}
 
 	cic->blkcg_serial_nr = serial_nr;
-	return nonroot_cg;
 }
 #else
-static inline bool check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
+static inline void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio)
 {
-	return false;
 }
 #endif  /* CONFIG_CFQ_GROUP_IOSCHED */
 
@@ -4449,12 +4445,11 @@ cfq_set_request(struct request_queue *q, struct request *rq, struct bio *bio,
 	const int rw = rq_data_dir(rq);
 	const bool is_sync = rq_is_sync(rq);
 	struct cfq_queue *cfqq;
-	bool disable_wbt;
 
 	spin_lock_irq(q->queue_lock);
 
 	check_ioprio_changed(cic, bio);
-	disable_wbt = check_blkcg_changed(cic, bio);
+	check_blkcg_changed(cic, bio);
 new_queue:
 	cfqq = cic_to_cfqq(cic, is_sync);
 	if (!cfqq || cfqq == &cfqd->oom_cfqq) {
@@ -4491,9 +4486,6 @@ new_queue:
 	rq->elv.priv[1] = cfqq->cfqg;
 	spin_unlock_irq(q->queue_lock);
 
-	if (disable_wbt)
-		wbt_disable_default(q);
-
 	return 0;
 }
 
@@ -4706,6 +4698,7 @@ static void cfq_registered_queue(struct request_queue *q)
 	 */
 	if (blk_queue_nonrot(q))
 		cfqd->cfq_slice_idle = 0;
+	wbt_disable_default(q);
 }
 
 /*

block/compat_ioctl.c

@@ -685,7 +685,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	case BLKALIGNOFF:
 		return compat_put_int(arg, bdev_alignment_offset(bdev));
 	case BLKDISCARDZEROES:
-		return compat_put_uint(arg, bdev_discard_zeroes_data(bdev));
+		return compat_put_uint(arg, 0);
 	case BLKFLSBUF:
 	case BLKROSET:
 	case BLKDISCARD:

block/elevator.c

@@ -41,6 +41,7 @@
 
 #include "blk.h"
 #include "blk-mq-sched.h"
+#include "blk-wbt.h"
 
 static DEFINE_SPINLOCK(elv_list_lock);
 static LIST_HEAD(elv_list);
@@ -877,6 +878,8 @@ void elv_unregister_queue(struct request_queue *q)
 		kobject_uevent(&e->kobj, KOBJ_REMOVE);
 		kobject_del(&e->kobj);
 		e->registered = 0;
+		/* Re-enable throttling in case elevator disabled it */
+		wbt_enable_default(q);
 	}
 }
 EXPORT_SYMBOL(elv_unregister_queue);

block/genhd.c

@@ -1060,8 +1060,19 @@ static struct attribute *disk_attrs[] = {
 	NULL
 };
 
+static umode_t disk_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = container_of(kobj, typeof(*dev), kobj);
+	struct gendisk *disk = dev_to_disk(dev);
+
+	if (a == &dev_attr_badblocks.attr && !disk->bb)
+		return 0;
+	return a->mode;
+}
+
 static struct attribute_group disk_attr_group = {
 	.attrs = disk_attrs,
+	.is_visible = disk_visible,
 };
 
 static const struct attribute_group *disk_attr_groups[] = {
@@ -1352,7 +1363,7 @@ struct kobject *get_disk(struct gendisk *disk)
 	owner = disk->fops->owner;
 	if (owner && !try_module_get(owner))
 		return NULL;
-	kobj = kobject_get(&disk_to_dev(disk)->kobj);
+	kobj = kobject_get_unless_zero(&disk_to_dev(disk)->kobj);
 	if (kobj == NULL) {
 		module_put(owner);
 		return NULL;

block/ioctl.c

@@ -255,7 +255,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode,
 	truncate_inode_pages_range(mapping, start, end);
 
 	return blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL,
-				    false);
+			BLKDEV_ZERO_NOUNMAP);
 }
 
 static int put_ushort(unsigned long arg, unsigned short val)
@@ -547,7 +547,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKALIGNOFF:
 		return put_int(arg, bdev_alignment_offset(bdev));
 	case BLKDISCARDZEROES:
-		return put_uint(arg, bdev_discard_zeroes_data(bdev));
+		return put_uint(arg, 0);
 	case BLKSECTGET:
 		max_sectors = min_t(unsigned int, USHRT_MAX,
 				    queue_max_sectors(bdev_get_queue(bdev)));

block/ioprio.c

@@ -163,22 +163,12 @@ out:
 
 int ioprio_best(unsigned short aprio, unsigned short bprio)
 {
-	unsigned short aclass;
-	unsigned short bclass;
-
 	if (!ioprio_valid(aprio))
 		aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
 	if (!ioprio_valid(bprio))
 		bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
 
-	aclass = IOPRIO_PRIO_CLASS(aprio);
-	bclass = IOPRIO_PRIO_CLASS(bprio);
-	if (aclass == bclass)
-		return min(aprio, bprio);
-	if (aclass > bclass)
-		return bprio;
-	else
-		return aprio;
+	return min(aprio, bprio);
 }
 
 SYSCALL_DEFINE2(ioprio_get, int, which, int, who)

block/kyber-iosched.c

@@ -0,0 +1,719 @@
+/*
+ * The Kyber I/O scheduler. Controls latency by throttling queue depths using
+ * scalable techniques.
+ *
+ * Copyright (C) 2017 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
+#include <linux/elevator.h>
+#include <linux/module.h>
+#include <linux/sbitmap.h>
+
+#include "blk.h"
+#include "blk-mq.h"
+#include "blk-mq-sched.h"
+#include "blk-mq-tag.h"
+#include "blk-stat.h"
+
+/* Scheduling domains. */
+enum {
+	KYBER_READ,
+	KYBER_SYNC_WRITE,
+	KYBER_OTHER, /* Async writes, discard, etc. */
+	KYBER_NUM_DOMAINS,
+};
+
+enum {
+	KYBER_MIN_DEPTH = 256,
+
+	/*
+	 * In order to prevent starvation of synchronous requests by a flood of
+	 * asynchronous requests, we reserve 25% of requests for synchronous
+	 * operations.
+	 */
+	KYBER_ASYNC_PERCENT = 75,
+};
+
+/*
+ * Initial device-wide depths for each scheduling domain.
+ *
+ * Even for fast devices with lots of tags like NVMe, you can saturate
+ * the device with only a fraction of the maximum possible queue depth.
+ * So, we cap these to a reasonable value.
+ */
+static const unsigned int kyber_depth[] = {
+	[KYBER_READ] = 256,
+	[KYBER_SYNC_WRITE] = 128,
+	[KYBER_OTHER] = 64,
+};
+
+/*
+ * Scheduling domain batch sizes. We favor reads.
+ */
+static const unsigned int kyber_batch_size[] = {
+	[KYBER_READ] = 16,
+	[KYBER_SYNC_WRITE] = 8,
+	[KYBER_OTHER] = 8,
+};
+
+struct kyber_queue_data {
+	struct request_queue *q;
+
+	struct blk_stat_callback *cb;
+
+	/*
+	 * The device is divided into multiple scheduling domains based on the
+	 * request type. Each domain has a fixed number of in-flight requests of
+	 * that type device-wide, limited by these tokens.
+	 */
+	struct sbitmap_queue domain_tokens[KYBER_NUM_DOMAINS];
+
+	/*
+	 * Async request percentage, converted to per-word depth for
+	 * sbitmap_get_shallow().
+	 */
+	unsigned int async_depth;
+
+	/* Target latencies in nanoseconds. */
+	u64 read_lat_nsec, write_lat_nsec;
+};
+
+struct kyber_hctx_data {
+	spinlock_t lock;
+	struct list_head rqs[KYBER_NUM_DOMAINS];
+	unsigned int cur_domain;
+	unsigned int batching;
+	wait_queue_t domain_wait[KYBER_NUM_DOMAINS];
+	atomic_t wait_index[KYBER_NUM_DOMAINS];
+};
+
+static int rq_sched_domain(const struct request *rq)
+{
+	unsigned int op = rq->cmd_flags;
+
+	if ((op & REQ_OP_MASK) == REQ_OP_READ)
+		return KYBER_READ;
+	else if ((op & REQ_OP_MASK) == REQ_OP_WRITE && op_is_sync(op))
+		return KYBER_SYNC_WRITE;
+	else
+		return KYBER_OTHER;
+}
+
+enum {
+	NONE = 0,
+	GOOD = 1,
+	GREAT = 2,
+	BAD = -1,
+	AWFUL = -2,
+};
+
+#define IS_GOOD(status) ((status) > 0)
+#define IS_BAD(status) ((status) < 0)
+
+static int kyber_lat_status(struct blk_stat_callback *cb,
+			    unsigned int sched_domain, u64 target)
+{
+	u64 latency;
+
+	if (!cb->stat[sched_domain].nr_samples)
+		return NONE;
+
+	latency = cb->stat[sched_domain].mean;
+	if (latency >= 2 * target)
+		return AWFUL;
+	else if (latency > target)
+		return BAD;
+	else if (latency <= target / 2)
+		return GREAT;
+	else /* (latency <= target) */
+		return GOOD;
+}
+
+/*
+ * Adjust the read or synchronous write depth given the status of reads and
+ * writes. The goal is that the latencies of the two domains are fair (i.e., if
+ * one is good, then the other is good).
+ */
+static void kyber_adjust_rw_depth(struct kyber_queue_data *kqd,
+				  unsigned int sched_domain, int this_status,
+				  int other_status)
+{
+	unsigned int orig_depth, depth;
+
+	/*
+	 * If this domain had no samples, or reads and writes are both good or
+	 * both bad, don't adjust the depth.
+	 */
+	if (this_status == NONE ||
+	    (IS_GOOD(this_status) && IS_GOOD(other_status)) ||
+	    (IS_BAD(this_status) && IS_BAD(other_status)))
+		return;
+
+	orig_depth = depth = kqd->domain_tokens[sched_domain].sb.depth;
+
+	if (other_status == NONE) {
+		depth++;
+	} else {
+		switch (this_status) {
+		case GOOD:
+			if (other_status == AWFUL)
+				depth -= max(depth / 4, 1U);
+			else
+				depth -= max(depth / 8, 1U);
+			break;
+		case GREAT:
+			if (other_status == AWFUL)
+				depth /= 2;
+			else
+				depth -= max(depth / 4, 1U);
+			break;
+		case BAD:
+			depth++;
+			break;
+		case AWFUL:
+			if (other_status == GREAT)
+				depth += 2;
+			else
+				depth++;
+			break;
+		}
+	}
+
+	depth = clamp(depth, 1U, kyber_depth[sched_domain]);
+	if (depth != orig_depth)
+		sbitmap_queue_resize(&kqd->domain_tokens[sched_domain], depth);
+}
+
+/*
+ * Adjust the depth of other requests given the status of reads and synchronous
+ * writes. As long as either domain is doing fine, we don't throttle, but if
+ * both domains are doing badly, we throttle heavily.
+ */
+static void kyber_adjust_other_depth(struct kyber_queue_data *kqd,
+				     int read_status, int write_status,
+				     bool have_samples)
+{
+	unsigned int orig_depth, depth;
+	int status;
+
+	orig_depth = depth = kqd->domain_tokens[KYBER_OTHER].sb.depth;
+
+	if (read_status == NONE && write_status == NONE) {
+		depth += 2;
+	} else if (have_samples) {
+		if (read_status == NONE)
+			status = write_status;
+		else if (write_status == NONE)
+			status = read_status;
+		else
+			status = max(read_status, write_status);
+		switch (status) {
+		case GREAT:
+			depth += 2;
+			break;
+		case GOOD:
+			depth++;
+			break;
+		case BAD:
+			depth -= max(depth / 4, 1U);
+			break;
+		case AWFUL:
+			depth /= 2;
+			break;
+		}
+	}
+
+	depth = clamp(depth, 1U, kyber_depth[KYBER_OTHER]);
+	if (depth != orig_depth)
+		sbitmap_queue_resize(&kqd->domain_tokens[KYBER_OTHER], depth);
+}
+
+/*
+ * Apply heuristics for limiting queue depths based on gathered latency
+ * statistics.
+ */
+static void kyber_stat_timer_fn(struct blk_stat_callback *cb)
+{
+	struct kyber_queue_data *kqd = cb->data;
+	int read_status, write_status;
+
+	read_status = kyber_lat_status(cb, KYBER_READ, kqd->read_lat_nsec);
+	write_status = kyber_lat_status(cb, KYBER_SYNC_WRITE, kqd->write_lat_nsec);
+
+	kyber_adjust_rw_depth(kqd, KYBER_READ, read_status, write_status);
+	kyber_adjust_rw_depth(kqd, KYBER_SYNC_WRITE, write_status, read_status);
+	kyber_adjust_other_depth(kqd, read_status, write_status,
+				 cb->stat[KYBER_OTHER].nr_samples != 0);
+
+	/*
+	 * Continue monitoring latencies if we aren't hitting the targets or
+	 * we're still throttling other requests.
+	 */
+	if (!blk_stat_is_active(kqd->cb) &&
+	    ((IS_BAD(read_status) || IS_BAD(write_status) ||
+	      kqd->domain_tokens[KYBER_OTHER].sb.depth < kyber_depth[KYBER_OTHER])))
+		blk_stat_activate_msecs(kqd->cb, 100);
+}
+
+static unsigned int kyber_sched_tags_shift(struct kyber_queue_data *kqd)
+{
+	/*
+	 * All of the hardware queues have the same depth, so we can just grab
+	 * the shift of the first one.
+	 */
+	return kqd->q->queue_hw_ctx[0]->sched_tags->bitmap_tags.sb.shift;
+}
+
+static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q)
+{
+	struct kyber_queue_data *kqd;
+	unsigned int max_tokens;
+	unsigned int shift;
+	int ret = -ENOMEM;
+	int i;
+
+	kqd = kmalloc_node(sizeof(*kqd), GFP_KERNEL, q->node);
+	if (!kqd)
+		goto err;
+	kqd->q = q;
+
+	kqd->cb = blk_stat_alloc_callback(kyber_stat_timer_fn, rq_sched_domain,
+					  KYBER_NUM_DOMAINS, kqd);
+	if (!kqd->cb)
+		goto err_kqd;
+
+	/*
+	 * The maximum number of tokens for any scheduling domain is at least
+	 * the queue depth of a single hardware queue. If the hardware doesn't
+	 * have many tags, still provide a reasonable number.
+	 */
+	max_tokens = max_t(unsigned int, q->tag_set->queue_depth,
+			   KYBER_MIN_DEPTH);
+	for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
+		WARN_ON(!kyber_depth[i]);
+		WARN_ON(!kyber_batch_size[i]);
+		ret = sbitmap_queue_init_node(&kqd->domain_tokens[i],
+					      max_tokens, -1, false, GFP_KERNEL,
+					      q->node);
+		if (ret) {
+			while (--i >= 0)
+				sbitmap_queue_free(&kqd->domain_tokens[i]);
+			goto err_cb;
+		}
+		sbitmap_queue_resize(&kqd->domain_tokens[i], kyber_depth[i]);
+	}
+
+	shift = kyber_sched_tags_shift(kqd);
+	kqd->async_depth = (1U << shift) * KYBER_ASYNC_PERCENT / 100U;
+
+	kqd->read_lat_nsec = 2000000ULL;
+	kqd->write_lat_nsec = 10000000ULL;
+
+	return kqd;
+
+err_cb:
+	blk_stat_free_callback(kqd->cb);
+err_kqd:
+	kfree(kqd);
+err:
+	return ERR_PTR(ret);
+}
+
+static int kyber_init_sched(struct request_queue *q, struct elevator_type *e)
+{
+	struct kyber_queue_data *kqd;
+	struct elevator_queue *eq;
+
+	eq = elevator_alloc(q, e);
+	if (!eq)
+		return -ENOMEM;
+
+	kqd = kyber_queue_data_alloc(q);
+	if (IS_ERR(kqd)) {
+		kobject_put(&eq->kobj);
+		return PTR_ERR(kqd);
+	}
+
+	eq->elevator_data = kqd;
+	q->elevator = eq;
+
+	blk_stat_add_callback(q, kqd->cb);
+
+	return 0;
+}
+
+static void kyber_exit_sched(struct elevator_queue *e)
+{
+	struct kyber_queue_data *kqd = e->elevator_data;
+	struct request_queue *q = kqd->q;
+	int i;
+
+	blk_stat_remove_callback(q, kqd->cb);
+
+	for (i = 0; i < KYBER_NUM_DOMAINS; i++)
+		sbitmap_queue_free(&kqd->domain_tokens[i]);
+	blk_stat_free_callback(kqd->cb);
+	kfree(kqd);
+}
+
+static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
+{
+	struct kyber_hctx_data *khd;
+	int i;
+
+	khd = kmalloc_node(sizeof(*khd), GFP_KERNEL, hctx->numa_node);
+	if (!khd)
+		return -ENOMEM;
+
+	spin_lock_init(&khd->lock);
+
+	for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
+		INIT_LIST_HEAD(&khd->rqs[i]);
+		INIT_LIST_HEAD(&khd->domain_wait[i].task_list);
+		atomic_set(&khd->wait_index[i], 0);
+	}
+
+	khd->cur_domain = 0;
+	khd->batching = 0;
+
+	hctx->sched_data = khd;
+
+	return 0;
+}
+
+static void kyber_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
+{
+	kfree(hctx->sched_data);
+}
+
+static int rq_get_domain_token(struct request *rq)
+{
+	return (long)rq->elv.priv[0];
+}
+
+static void rq_set_domain_token(struct request *rq, int token)
+{
+	rq->elv.priv[0] = (void *)(long)token;
+}
+
+static void rq_clear_domain_token(struct kyber_queue_data *kqd,
+				  struct request *rq)
+{
+	unsigned int sched_domain;
+	int nr;
+
+	nr = rq_get_domain_token(rq);
+	if (nr != -1) {
+		sched_domain = rq_sched_domain(rq);
+		sbitmap_queue_clear(&kqd->domain_tokens[sched_domain], nr,
+				    rq->mq_ctx->cpu);
+	}
+}
+
+static struct request *kyber_get_request(struct request_queue *q,
+					 unsigned int op,
+					 struct blk_mq_alloc_data *data)
+{
+	struct kyber_queue_data *kqd = q->elevator->elevator_data;
+	struct request *rq;
+
+	/*
+	 * We use the scheduler tags as per-hardware queue queueing tokens.
+	 * Async requests can be limited at this stage.
+	 */
+	if (!op_is_sync(op))
+		data->shallow_depth = kqd->async_depth;
+
+	rq = __blk_mq_alloc_request(data, op);
+	if (rq)
+		rq_set_domain_token(rq, -1);
+	return rq;
+}
+
+static void kyber_put_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct kyber_queue_data *kqd = q->elevator->elevator_data;
+
+	rq_clear_domain_token(kqd, rq);
+	blk_mq_finish_request(rq);
+}
+
+static void kyber_completed_request(struct request *rq)
+{
+	struct request_queue *q = rq->q;
+	struct kyber_queue_data *kqd = q->elevator->elevator_data;
+	unsigned int sched_domain;
+	u64 now, latency, target;
+
+	/*
+	 * Check if this request met our latency goal. If not, quickly gather
+	 * some statistics and start throttling.
+	 */
+	sched_domain = rq_sched_domain(rq);
+	switch (sched_domain) {
+	case KYBER_READ:
+		target = kqd->read_lat_nsec;
+		break;
+	case KYBER_SYNC_WRITE:
+		target = kqd->write_lat_nsec;
+		break;
+	default:
+		return;
+	}
+
+	/* If we are already monitoring latencies, don't check again. */
+	if (blk_stat_is_active(kqd->cb))
+		return;
+
+	now = __blk_stat_time(ktime_to_ns(ktime_get()));
+	if (now < blk_stat_time(&rq->issue_stat))
+		return;
+
+	latency = now - blk_stat_time(&rq->issue_stat);
+
+	if (latency > target)
+		blk_stat_activate_msecs(kqd->cb, 10);
+}
+
+static void kyber_flush_busy_ctxs(struct kyber_hctx_data *khd,
+				  struct blk_mq_hw_ctx *hctx)
+{
+	LIST_HEAD(rq_list);
+	struct request *rq, *next;
+
+	blk_mq_flush_busy_ctxs(hctx, &rq_list);
+	list_for_each_entry_safe(rq, next, &rq_list, queuelist) {
+		unsigned int sched_domain;
+
+		sched_domain = rq_sched_domain(rq);
+		list_move_tail(&rq->queuelist, &khd->rqs[sched_domain]);
+	}
+}
+
+static int kyber_domain_wake(wait_queue_t *wait, unsigned mode, int flags,
+			     void *key)
+{
+	struct blk_mq_hw_ctx *hctx = READ_ONCE(wait->private);
+
+	list_del_init(&wait->task_list);
+	blk_mq_run_hw_queue(hctx, true);
+	return 1;
+}
+
+static int kyber_get_domain_token(struct kyber_queue_data *kqd,
+				  struct kyber_hctx_data *khd,
+				  struct blk_mq_hw_ctx *hctx)
+{
+	unsigned int sched_domain = khd->cur_domain;
+	struct sbitmap_queue *domain_tokens = &kqd->domain_tokens[sched_domain];
+	wait_queue_t *wait = &khd->domain_wait[sched_domain];
+	struct sbq_wait_state *ws;
+	int nr;
+
+	nr = __sbitmap_queue_get(domain_tokens);
+	if (nr >= 0)
+		return nr;
+
+	/*
+	 * If we failed to get a domain token, make sure the hardware queue is
+	 * run when one becomes available. Note that this is serialized on
+	 * khd->lock, but we still need to be careful about the waker.
+	 */
+	if (list_empty_careful(&wait->task_list)) {
+		init_waitqueue_func_entry(wait, kyber_domain_wake);
+		wait->private = hctx;
+		ws = sbq_wait_ptr(domain_tokens,
+				  &khd->wait_index[sched_domain]);
+		add_wait_queue(&ws->wait, wait);
+
+		/*
+		 * Try again in case a token was freed before we got on the wait
+		 * queue.
+		 */
+		nr = __sbitmap_queue_get(domain_tokens);
+	}
+	return nr;
+}
+
+static struct request *
+kyber_dispatch_cur_domain(struct kyber_queue_data *kqd,
+			  struct kyber_hctx_data *khd,
+			  struct blk_mq_hw_ctx *hctx,
+			  bool *flushed)
+{
+	struct list_head *rqs;
+	struct request *rq;
+	int nr;
+
+	rqs = &khd->rqs[khd->cur_domain];
+	rq = list_first_entry_or_null(rqs, struct request, queuelist);
+
+	/*
+	 * If there wasn't already a pending request and we haven't flushed the
+	 * software queues yet, flush the software queues and check again.
+	 */
+	if (!rq && !*flushed) {
+		kyber_flush_busy_ctxs(khd, hctx);
+		*flushed = true;
+		rq = list_first_entry_or_null(rqs, struct request, queuelist);
+	}
+
+	if (rq) {
+		nr = kyber_get_domain_token(kqd, khd, hctx);
+		if (nr >= 0) {
+			khd->batching++;
+			rq_set_domain_token(rq, nr);
+			list_del_init(&rq->queuelist);
+			return rq;
+		}
+	}
+
+	/* There were either no pending requests or no tokens. */
+	return NULL;
+}
+
+static struct request *kyber_dispatch_request(struct blk_mq_hw_ctx *hctx)
+{
+	struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data;
+	struct kyber_hctx_data *khd = hctx->sched_data;
+	bool flushed = false;
+	struct request *rq;
+	int i;
+
+	spin_lock(&khd->lock);
+
+	/*
+	 * First, if we are still entitled to batch, try to dispatch a request
+	 * from the batch.
+	 */
+	if (khd->batching < kyber_batch_size[khd->cur_domain]) {
+		rq = kyber_dispatch_cur_domain(kqd, khd, hctx, &flushed);
+		if (rq)
+			goto out;
+	}
+
+	/*
+	 * Either,
+	 * 1. We were no longer entitled to a batch.
+	 * 2. The domain we were batching didn't have any requests.
+	 * 3. The domain we were batching was out of tokens.
+	 *
+	 * Start another batch. Note that this wraps back around to the original
+	 * domain if no other domains have requests or tokens.
+	 */
+	khd->batching = 0;
+	for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
+		if (khd->cur_domain == KYBER_NUM_DOMAINS - 1)
+			khd->cur_domain = 0;
+		else
+			khd->cur_domain++;
+
+		rq = kyber_dispatch_cur_domain(kqd, khd, hctx, &flushed);
+		if (rq)
+			goto out;
+	}
+
+	rq = NULL;
+out:
+	spin_unlock(&khd->lock);
+	return rq;
+}
+
+static bool kyber_has_work(struct blk_mq_hw_ctx *hctx)
+{
+	struct kyber_hctx_data *khd = hctx->sched_data;
+	int i;
+
+	for (i = 0; i < KYBER_NUM_DOMAINS; i++) {
+		if (!list_empty_careful(&khd->rqs[i]))
+			return true;
+	}
+	return false;
+}
+
+#define KYBER_LAT_SHOW_STORE(op)					\
+static ssize_t kyber_##op##_lat_show(struct elevator_queue *e,		\
+				     char *page)			\
+{									\
+	struct kyber_queue_data *kqd = e->elevator_data;		\
+									\
+	return sprintf(page, "%llu\n", kqd->op##_lat_nsec);		\
+}									\
+									\
+static ssize_t kyber_##op##_lat_store(struct elevator_queue *e,		\
+				      const char *page, size_t count)	\
+{									\
+	struct kyber_queue_data *kqd = e->elevator_data;		\
+	unsigned long long nsec;					\
+	int ret;							\
+									\
+	ret = kstrtoull(page, 10, &nsec);				\
+	if (ret)							\
+		return ret;						\
+									\
+	kqd->op##_lat_nsec = nsec;					\
+									\
+	return count;							\
+}
+KYBER_LAT_SHOW_STORE(read);
+KYBER_LAT_SHOW_STORE(write);
+#undef KYBER_LAT_SHOW_STORE
+
+#define KYBER_LAT_ATTR(op) __ATTR(op##_lat_nsec, 0644, kyber_##op##_lat_show, kyber_##op##_lat_store)
+static struct elv_fs_entry kyber_sched_attrs[] = {
+	KYBER_LAT_ATTR(read),
+	KYBER_LAT_ATTR(write),
+	__ATTR_NULL
+};
+#undef KYBER_LAT_ATTR
+
+static struct elevator_type kyber_sched = {
+	.ops.mq = {
+		.init_sched = kyber_init_sched,
+		.exit_sched = kyber_exit_sched,
+		.init_hctx = kyber_init_hctx,
+		.exit_hctx = kyber_exit_hctx,
+		.get_request = kyber_get_request,
+		.put_request = kyber_put_request,
+		.completed_request = kyber_completed_request,
+		.dispatch_request = kyber_dispatch_request,
+		.has_work = kyber_has_work,
+	},
+	.uses_mq = true,
+	.elevator_attrs = kyber_sched_attrs,
+	.elevator_name = "kyber",
+	.elevator_owner = THIS_MODULE,
+};
+
+static int __init kyber_init(void)
+{
+	return elv_register(&kyber_sched);
+}
+
+static void __exit kyber_exit(void)
+{
+	elv_unregister(&kyber_sched);
+}
+
+module_init(kyber_init);
+module_exit(kyber_exit);
+
+MODULE_AUTHOR("Omar Sandoval");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Kyber I/O scheduler");

block/partition-generic.c

@@ -497,7 +497,6 @@ rescan:
 
 	if (disk->fops->revalidate_disk)
 		disk->fops->revalidate_disk(disk);
-	blk_integrity_revalidate(disk);
 	check_disk_size_change(disk, bdev);
 	bdev->bd_invalidated = 0;
 	if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))

block/scsi_ioctl.c

@@ -262,11 +262,11 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 	/*
 	 * fill in all the output members
 	 */
-	hdr->status = rq->errors & 0xff;
-	hdr->masked_status = status_byte(rq->errors);
-	hdr->msg_status = msg_byte(rq->errors);
-	hdr->host_status = host_byte(rq->errors);
-	hdr->driver_status = driver_byte(rq->errors);
+	hdr->status = req->result & 0xff;
+	hdr->masked_status = status_byte(req->result);
+	hdr->msg_status = msg_byte(req->result);
+	hdr->host_status = host_byte(req->result);
+	hdr->driver_status = driver_byte(req->result);
 	hdr->info = 0;
 	if (hdr->masked_status || hdr->host_status || hdr->driver_status)
 		hdr->info |= SG_INFO_CHECK;
@@ -362,7 +362,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 		goto out_free_cdb;
 
 	bio = rq->bio;
-	rq->retries = 0;
+	req->retries = 0;
 
 	start_time = jiffies;
 
@@ -476,13 +476,13 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 		goto error;
 
 	/* default.  possible overriden later */
-	rq->retries = 5;
+	req->retries = 5;
 
 	switch (opcode) {
 	case SEND_DIAGNOSTIC:
 	case FORMAT_UNIT:
 		rq->timeout = FORMAT_UNIT_TIMEOUT;
-		rq->retries = 1;
+		req->retries = 1;
 		break;
 	case START_STOP:
 		rq->timeout = START_STOP_TIMEOUT;
@@ -495,7 +495,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 		break;
 	case READ_DEFECT_DATA:
 		rq->timeout = READ_DEFECT_DATA_TIMEOUT;
-		rq->retries = 1;
+		req->retries = 1;
 		break;
 	default:
 		rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
@@ -509,7 +509,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 
 	blk_execute_rq(q, disk, rq, 0);
 
-	err = rq->errors & 0xff;	/* only 8 bit SCSI status */
+	err = req->result & 0xff;	/* only 8 bit SCSI status */
 	if (err) {
 		if (req->sense_len && req->sense) {
 			bytes = (OMAX_SB_LEN > req->sense_len) ?
@@ -547,7 +547,8 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 	scsi_req(rq)->cmd[0] = cmd;
 	scsi_req(rq)->cmd[4] = data;
 	scsi_req(rq)->cmd_len = 6;
-	err = blk_execute_rq(q, bd_disk, rq, 0);
+	blk_execute_rq(q, bd_disk, rq, 0);
+	err = scsi_req(rq)->result ? -EIO : 0;
 	blk_put_request(rq);
 
 	return err;

block/sed-opal.c

@@ -275,8 +275,8 @@ static bool check_tper(const void *data)
 	u8 flags = tper->supported_features;
 
 	if (!(flags & TPER_SYNC_SUPPORTED)) {
-		pr_err("TPer sync not supported. flags = %d\n",
-		       tper->supported_features);
+		pr_debug("TPer sync not supported. flags = %d\n",
+			 tper->supported_features);
 		return false;
 	}
 
@@ -289,7 +289,7 @@ static bool check_sum(const void *data)
 	u32 nlo = be32_to_cpu(sum->num_locking_objects);
 
 	if (nlo == 0) {
-		pr_err("Need at least one locking object.\n");
+		pr_debug("Need at least one locking object.\n");
 		return false;
 	}
 
@@ -385,9 +385,9 @@ static int next(struct opal_dev *dev)
 
 		error = step->fn(dev, step->data);
 		if (error) {
-			pr_err("Error on step function: %d with error %d: %s\n",
-			       state, error,
-			       opal_error_to_human(error));
+			pr_debug("Error on step function: %d with error %d: %s\n",
+				 state, error,
+				 opal_error_to_human(error));
 
 			/* For each OPAL command we do a discovery0 then we
 			 * start some sort of session.
@@ -419,8 +419,8 @@ static int opal_discovery0_end(struct opal_dev *dev)
 	print_buffer(dev->resp, hlen);
 
 	if (hlen > IO_BUFFER_LENGTH - sizeof(*hdr)) {
-		pr_warn("Discovery length overflows buffer (%zu+%u)/%u\n",
-			sizeof(*hdr), hlen, IO_BUFFER_LENGTH);
+		pr_debug("Discovery length overflows buffer (%zu+%u)/%u\n",
+			 sizeof(*hdr), hlen, IO_BUFFER_LENGTH);
 		return -EFAULT;
 	}
 
@@ -503,7 +503,7 @@ static void add_token_u8(int *err, struct opal_dev *cmd, u8 tok)
 	if (*err)
 		return;
 	if (cmd->pos >= IO_BUFFER_LENGTH - 1) {
-		pr_err("Error adding u8: end of buffer.\n");
+		pr_debug("Error adding u8: end of buffer.\n");
 		*err = -ERANGE;
 		return;
 	}
@@ -553,7 +553,7 @@ static void add_token_u64(int *err, struct opal_dev *cmd, u64 number)
 	len = DIV_ROUND_UP(msb, 4);
 
 	if (cmd->pos >= IO_BUFFER_LENGTH - len - 1) {
-		pr_err("Error adding u64: end of buffer.\n");
+		pr_debug("Error adding u64: end of buffer.\n");
 		*err = -ERANGE;
 		return;
 	}
@@ -579,7 +579,7 @@ static void add_token_bytestring(int *err, struct opal_dev *cmd,
 	}
 
 	if (len >= IO_BUFFER_LENGTH - cmd->pos - header_len) {
-		pr_err("Error adding bytestring: end of buffer.\n");
+		pr_debug("Error adding bytestring: end of buffer.\n");
 		*err = -ERANGE;
 		return;
 	}
@@ -597,7 +597,7 @@ static void add_token_bytestring(int *err, struct opal_dev *cmd,
 static int build_locking_range(u8 *buffer, size_t length, u8 lr)
 {
 	if (length > OPAL_UID_LENGTH) {
-		pr_err("Can't build locking range. Length OOB\n");
+		pr_debug("Can't build locking range. Length OOB\n");
 		return -ERANGE;
 	}
 
@@ -614,7 +614,7 @@ static int build_locking_range(u8 *buffer, size_t length, u8 lr)
 static int build_locking_user(u8 *buffer, size_t length, u8 lr)
 {
 	if (length > OPAL_UID_LENGTH) {
-		pr_err("Can't build locking range user, Length OOB\n");
+		pr_debug("Can't build locking range user, Length OOB\n");
 		return -ERANGE;
 	}
 
@@ -648,7 +648,7 @@ static int cmd_finalize(struct opal_dev *cmd, u32 hsn, u32 tsn)
 	add_token_u8(&err, cmd, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error finalizing command.\n");
+		pr_debug("Error finalizing command.\n");
 		return -EFAULT;
 	}
 
@@ -660,7 +660,7 @@ static int cmd_finalize(struct opal_dev *cmd, u32 hsn, u32 tsn)
 	hdr->subpkt.length = cpu_to_be32(cmd->pos - sizeof(*hdr));
 	while (cmd->pos % 4) {
 		if (cmd->pos >= IO_BUFFER_LENGTH) {
-			pr_err("Error: Buffer overrun\n");
+			pr_debug("Error: Buffer overrun\n");
 			return -ERANGE;
 		}
 		cmd->cmd[cmd->pos++] = 0;
@@ -679,14 +679,14 @@ static const struct opal_resp_tok *response_get_token(
 	const struct opal_resp_tok *tok;
 
 	if (n >= resp->num) {
-		pr_err("Token number doesn't exist: %d, resp: %d\n",
-		       n, resp->num);
+		pr_debug("Token number doesn't exist: %d, resp: %d\n",
+			 n, resp->num);
 		return ERR_PTR(-EINVAL);
 	}
 
 	tok = &resp->toks[n];
 	if (tok->len == 0) {
-		pr_err("Token length must be non-zero\n");
+		pr_debug("Token length must be non-zero\n");
 		return ERR_PTR(-EINVAL);
 	}
 
@@ -727,7 +727,7 @@ static ssize_t response_parse_short(struct opal_resp_tok *tok,
 
 		tok->type = OPAL_DTA_TOKENID_UINT;
 		if (tok->len > 9) {
-			pr_warn("uint64 with more than 8 bytes\n");
+			pr_debug("uint64 with more than 8 bytes\n");
 			return -EINVAL;
 		}
 		for (i = tok->len - 1; i > 0; i--) {
@@ -814,8 +814,8 @@ static int response_parse(const u8 *buf, size_t length,
 
 	if (clen == 0 || plen == 0 || slen == 0 ||
 	    slen > IO_BUFFER_LENGTH - sizeof(*hdr)) {
-		pr_err("Bad header length. cp: %u, pkt: %u, subpkt: %u\n",
-		       clen, plen, slen);
+		pr_debug("Bad header length. cp: %u, pkt: %u, subpkt: %u\n",
+			 clen, plen, slen);
 		print_buffer(pos, sizeof(*hdr));
 		return -EINVAL;
 	}
@@ -848,7 +848,7 @@ static int response_parse(const u8 *buf, size_t length,
 	}
 
 	if (num_entries == 0) {
-		pr_err("Couldn't parse response.\n");
+		pr_debug("Couldn't parse response.\n");
 		return -EINVAL;
 	}
 	resp->num = num_entries;
@@ -861,18 +861,18 @@ static size_t response_get_string(const struct parsed_resp *resp, int n,
 {
 	*store = NULL;
 	if (!resp) {
-		pr_err("Response is NULL\n");
+		pr_debug("Response is NULL\n");
 		return 0;
 	}
 
 	if (n > resp->num) {
-		pr_err("Response has %d tokens. Can't access %d\n",
-		       resp->num, n);
+		pr_debug("Response has %d tokens. Can't access %d\n",
+			 resp->num, n);
 		return 0;
 	}
 
 	if (resp->toks[n].type != OPAL_DTA_TOKENID_BYTESTRING) {
-		pr_err("Token is not a byte string!\n");
+		pr_debug("Token is not a byte string!\n");
 		return 0;
 	}
 
@@ -883,26 +883,26 @@ static size_t response_get_string(const struct parsed_resp *resp, int n,
 static u64 response_get_u64(const struct parsed_resp *resp, int n)
 {
 	if (!resp) {
-		pr_err("Response is NULL\n");
+		pr_debug("Response is NULL\n");
 		return 0;
 	}
 
 	if (n > resp->num) {
-		pr_err("Response has %d tokens. Can't access %d\n",
-		       resp->num, n);
+		pr_debug("Response has %d tokens. Can't access %d\n",
+			 resp->num, n);
 		return 0;
 	}
 
 	if (resp->toks[n].type != OPAL_DTA_TOKENID_UINT) {
-		pr_err("Token is not unsigned it: %d\n",
-		       resp->toks[n].type);
+		pr_debug("Token is not unsigned it: %d\n",
+			 resp->toks[n].type);
 		return 0;
 	}
 
 	if (!(resp->toks[n].width == OPAL_WIDTH_TINY ||
 	      resp->toks[n].width == OPAL_WIDTH_SHORT)) {
-		pr_err("Atom is not short or tiny: %d\n",
-		       resp->toks[n].width);
+		pr_debug("Atom is not short or tiny: %d\n",
+			 resp->toks[n].width);
 		return 0;
 	}
 
@@ -949,7 +949,7 @@ static int parse_and_check_status(struct opal_dev *dev)
 
 	error = response_parse(dev->resp, IO_BUFFER_LENGTH, &dev->parsed);
 	if (error) {
-		pr_err("Couldn't parse response.\n");
+		pr_debug("Couldn't parse response.\n");
 		return error;
 	}
 
@@ -975,7 +975,7 @@ static int start_opal_session_cont(struct opal_dev *dev)
 	tsn = response_get_u64(&dev->parsed, 5);
 
 	if (hsn == 0 && tsn == 0) {
-		pr_err("Couldn't authenticate session\n");
+		pr_debug("Couldn't authenticate session\n");
 		return -EPERM;
 	}
 
@@ -1012,7 +1012,7 @@ static int finalize_and_send(struct opal_dev *dev, cont_fn cont)
 
 	ret = cmd_finalize(dev, dev->hsn, dev->tsn);
 	if (ret) {
-		pr_err("Error finalizing command buffer: %d\n", ret);
+		pr_debug("Error finalizing command buffer: %d\n", ret);
 		return ret;
 	}
 
@@ -1041,7 +1041,7 @@ static int gen_key(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error building gen key command\n");
+		pr_debug("Error building gen key command\n");
 		return err;
 
 	}
@@ -1059,8 +1059,8 @@ static int get_active_key_cont(struct opal_dev *dev)
 		return error;
 	keylen = response_get_string(&dev->parsed, 4, &activekey);
 	if (!activekey) {
-		pr_err("%s: Couldn't extract the Activekey from the response\n",
-		       __func__);
+		pr_debug("%s: Couldn't extract the Activekey from the response\n",
+			 __func__);
 		return OPAL_INVAL_PARAM;
 	}
 	dev->prev_data = kmemdup(activekey, keylen, GFP_KERNEL);
@@ -1103,7 +1103,7 @@ static int get_active_key(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 	if (err) {
-		pr_err("Error building get active key command\n");
+		pr_debug("Error building get active key command\n");
 		return err;
 	}
 
@@ -1159,7 +1159,7 @@ static inline int enable_global_lr(struct opal_dev *dev, u8 *uid,
 	err = generic_lr_enable_disable(dev, uid, !!setup->RLE, !!setup->WLE,
 					0, 0);
 	if (err)
-		pr_err("Failed to create enable global lr command\n");
+		pr_debug("Failed to create enable global lr command\n");
 	return err;
 }
 
@@ -1217,7 +1217,7 @@ static int setup_locking_range(struct opal_dev *dev, void *data)
 
 	}
 	if (err) {
-		pr_err("Error building Setup Locking range command.\n");
+		pr_debug("Error building Setup Locking range command.\n");
 		return err;
 
 	}
@@ -1234,11 +1234,8 @@ static int start_generic_opal_session(struct opal_dev *dev,
 	u32 hsn;
 	int err = 0;
 
-	if (key == NULL && auth != OPAL_ANYBODY_UID) {
-		pr_err("%s: Attempted to open ADMIN_SP Session without a Host" \
-		       "Challenge, and not as the Anybody UID\n", __func__);
+	if (key == NULL && auth != OPAL_ANYBODY_UID)
 		return OPAL_INVAL_PARAM;
-	}
 
 	clear_opal_cmd(dev);
 
@@ -1273,12 +1270,12 @@ static int start_generic_opal_session(struct opal_dev *dev,
 		add_token_u8(&err, dev, OPAL_ENDLIST);
 		break;
 	default:
-		pr_err("Cannot start Admin SP session with auth %d\n", auth);
+		pr_debug("Cannot start Admin SP session with auth %d\n", auth);
 		return OPAL_INVAL_PARAM;
 	}
 
 	if (err) {
-		pr_err("Error building start adminsp session command.\n");
+		pr_debug("Error building start adminsp session command.\n");
 		return err;
 	}
 
@@ -1369,7 +1366,7 @@ static int start_auth_opal_session(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error building STARTSESSION command.\n");
+		pr_debug("Error building STARTSESSION command.\n");
 		return err;
 	}
 
@@ -1391,7 +1388,7 @@ static int revert_tper(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_STARTLIST);
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 	if (err) {
-		pr_err("Error building REVERT TPER command.\n");
+		pr_debug("Error building REVERT TPER command.\n");
 		return err;
 	}
 
@@ -1426,7 +1423,7 @@ static int internal_activate_user(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error building Activate UserN command.\n");
+		pr_debug("Error building Activate UserN command.\n");
 		return err;
 	}
 
@@ -1453,7 +1450,7 @@ static int erase_locking_range(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error building Erase Locking Range Command.\n");
+		pr_debug("Error building Erase Locking Range Command.\n");
 		return err;
 	}
 	return finalize_and_send(dev, parse_and_check_status);
@@ -1484,7 +1481,7 @@ static int set_mbr_done(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error Building set MBR Done command\n");
+		pr_debug("Error Building set MBR Done command\n");
 		return err;
 	}
 
@@ -1516,7 +1513,7 @@ static int set_mbr_enable_disable(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error Building set MBR done command\n");
+		pr_debug("Error Building set MBR done command\n");
 		return err;
 	}
 
@@ -1567,7 +1564,7 @@ static int set_new_pw(struct opal_dev *dev, void *data)
 
 	if (generic_pw_cmd(usr->opal_key.key, usr->opal_key.key_len,
 			   cpin_uid, dev)) {
-		pr_err("Error building set password command.\n");
+		pr_debug("Error building set password command.\n");
 		return -ERANGE;
 	}
 
@@ -1582,7 +1579,7 @@ static int set_sid_cpin_pin(struct opal_dev *dev, void *data)
 	memcpy(cpin_uid, opaluid[OPAL_C_PIN_SID], OPAL_UID_LENGTH);
 
 	if (generic_pw_cmd(key->key, key->key_len, cpin_uid, dev)) {
-		pr_err("Error building Set SID cpin\n");
+		pr_debug("Error building Set SID cpin\n");
 		return -ERANGE;
 	}
 	return finalize_and_send(dev, parse_and_check_status);
@@ -1657,7 +1654,7 @@ static int add_user_to_lr(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error building add user to locking range command.\n");
+		pr_debug("Error building add user to locking range command.\n");
 		return err;
 	}
 
@@ -1691,7 +1688,7 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
 		/* vars are initalized to locked */
 		break;
 	default:
-		pr_err("Tried to set an invalid locking state... returning to uland\n");
+		pr_debug("Tried to set an invalid locking state... returning to uland\n");
 		return OPAL_INVAL_PARAM;
 	}
 
@@ -1718,7 +1715,7 @@ static int lock_unlock_locking_range(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error building SET command.\n");
+		pr_debug("Error building SET command.\n");
 		return err;
 	}
 	return finalize_and_send(dev, parse_and_check_status);
@@ -1752,14 +1749,14 @@ static int lock_unlock_locking_range_sum(struct opal_dev *dev, void *data)
 		/* vars are initalized to locked */
 		break;
 	default:
-		pr_err("Tried to set an invalid locking state.\n");
+		pr_debug("Tried to set an invalid locking state.\n");
 		return OPAL_INVAL_PARAM;
 	}
 	ret = generic_lr_enable_disable(dev, lr_buffer, 1, 1,
 					read_locked, write_locked);
 
 	if (ret < 0) {
-		pr_err("Error building SET command.\n");
+		pr_debug("Error building SET command.\n");
 		return ret;
 	}
 	return finalize_and_send(dev, parse_and_check_status);
@@ -1811,7 +1808,7 @@ static int activate_lsp(struct opal_dev *dev, void *data)
 	}
 
 	if (err) {
-		pr_err("Error building Activate LockingSP command.\n");
+		pr_debug("Error building Activate LockingSP command.\n");
 		return err;
 	}
 
@@ -1831,7 +1828,7 @@ static int get_lsp_lifecycle_cont(struct opal_dev *dev)
 	/* 0x08 is Manufacured Inactive */
 	/* 0x09 is Manufactured */
 	if (lc_status != OPAL_MANUFACTURED_INACTIVE) {
-		pr_err("Couldn't determine the status of the Lifcycle state\n");
+		pr_debug("Couldn't determine the status of the Lifecycle state\n");
 		return -ENODEV;
 	}
 
@@ -1868,7 +1865,7 @@ static int get_lsp_lifecycle(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error Building GET Lifecycle Status command\n");
+		pr_debug("Error Building GET Lifecycle Status command\n");
 		return err;
 	}
 
@@ -1887,7 +1884,7 @@ static int get_msid_cpin_pin_cont(struct opal_dev *dev)
 
 	strlen = response_get_string(&dev->parsed, 4, &msid_pin);
 	if (!msid_pin) {
-		pr_err("%s: Couldn't extract PIN from response\n", __func__);
+		pr_debug("%s: Couldn't extract PIN from response\n", __func__);
 		return OPAL_INVAL_PARAM;
 	}
 
@@ -1929,7 +1926,7 @@ static int get_msid_cpin_pin(struct opal_dev *dev, void *data)
 	add_token_u8(&err, dev, OPAL_ENDLIST);
 
 	if (err) {
-		pr_err("Error building Get MSID CPIN PIN command.\n");
+		pr_debug("Error building Get MSID CPIN PIN command.\n");
 		return err;
 	}
 
@@ -2124,18 +2121,18 @@ static int opal_add_user_to_lr(struct opal_dev *dev,
 
 	if (lk_unlk->l_state != OPAL_RO &&
 	    lk_unlk->l_state != OPAL_RW) {
-		pr_err("Locking state was not RO or RW\n");
+		pr_debug("Locking state was not RO or RW\n");
 		return -EINVAL;
 	}
 	if (lk_unlk->session.who < OPAL_USER1 ||
 	    lk_unlk->session.who > OPAL_USER9) {
-		pr_err("Authority was not within the range of users: %d\n",
-		       lk_unlk->session.who);
+		pr_debug("Authority was not within the range of users: %d\n",
+			 lk_unlk->session.who);
 		return -EINVAL;
 	}
 	if (lk_unlk->session.sum) {
-		pr_err("%s not supported in sum. Use setup locking range\n",
-		       __func__);
+		pr_debug("%s not supported in sum. Use setup locking range\n",
+			 __func__);
 		return -EINVAL;
 	}
 
@@ -2312,7 +2309,7 @@ static int opal_activate_user(struct opal_dev *dev,
 	/* We can't activate Admin1 it's active as manufactured */
 	if (opal_session->who < OPAL_USER1 ||
 	    opal_session->who > OPAL_USER9) {
-		pr_err("Who was not a valid user: %d\n", opal_session->who);
+		pr_debug("Who was not a valid user: %d\n", opal_session->who);
 		return -EINVAL;
 	}
 
@@ -2343,9 +2340,9 @@ bool opal_unlock_from_suspend(struct opal_dev *dev)
 
 		ret = __opal_lock_unlock(dev, &suspend->unlk);
 		if (ret) {
-			pr_warn("Failed to unlock LR %hhu with sum %d\n",
-				suspend->unlk.session.opal_key.lr,
-				suspend->unlk.session.sum);
+			pr_debug("Failed to unlock LR %hhu with sum %d\n",
+				 suspend->unlk.session.opal_key.lr,
+				 suspend->unlk.session.sum);
 			was_failure = true;
 		}
 	}
@@ -2363,10 +2360,8 @@ int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg)
 		return -EACCES;
 	if (!dev)
 		return -ENOTSUPP;
-	if (!dev->supported) {
-		pr_err("Not supported\n");
+	if (!dev->supported)
 		return -ENOTSUPP;
-	}
 
 	p = memdup_user(arg, _IOC_SIZE(cmd));
 	if (IS_ERR(p))
@@ -2410,7 +2405,7 @@ int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg)
 		ret = opal_secure_erase_locking_range(dev, p);
 		break;
 	default:
-		pr_warn("No such Opal Ioctl %u\n", cmd);
+		break;
 	}
 
 	kfree(p);

block/t10-pi.c

@@ -160,28 +160,28 @@ static int t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
 	return t10_pi_verify(iter, t10_pi_ip_fn, 3);
 }
 
-struct blk_integrity_profile t10_pi_type1_crc = {
+const struct blk_integrity_profile t10_pi_type1_crc = {
 	.name			= "T10-DIF-TYPE1-CRC",
 	.generate_fn		= t10_pi_type1_generate_crc,
 	.verify_fn		= t10_pi_type1_verify_crc,
 };
 EXPORT_SYMBOL(t10_pi_type1_crc);
 
-struct blk_integrity_profile t10_pi_type1_ip = {
+const struct blk_integrity_profile t10_pi_type1_ip = {
 	.name			= "T10-DIF-TYPE1-IP",
 	.generate_fn		= t10_pi_type1_generate_ip,
 	.verify_fn		= t10_pi_type1_verify_ip,
 };
 EXPORT_SYMBOL(t10_pi_type1_ip);
 
-struct blk_integrity_profile t10_pi_type3_crc = {
+const struct blk_integrity_profile t10_pi_type3_crc = {
 	.name			= "T10-DIF-TYPE3-CRC",
 	.generate_fn		= t10_pi_type3_generate_crc,
 	.verify_fn		= t10_pi_type3_verify_crc,
 };
 EXPORT_SYMBOL(t10_pi_type3_crc);
 
-struct blk_integrity_profile t10_pi_type3_ip = {
+const struct blk_integrity_profile t10_pi_type3_ip = {
 	.name			= "T10-DIF-TYPE3-IP",
 	.generate_fn		= t10_pi_type3_generate_ip,
 	.verify_fn		= t10_pi_type3_verify_ip,

drivers/block/Kconfig

@@ -312,22 +312,6 @@ config BLK_DEV_SKD
 
 	Use device /dev/skd$N amd /dev/skd$Np$M.
 
-config BLK_DEV_OSD
-	tristate "OSD object-as-blkdev support"
-	depends on SCSI_OSD_ULD
-	---help---
-	  Saying Y or M here will allow the exporting of a single SCSI
-	  OSD (object-based storage) object as a Linux block device.
-
-	  For example, if you create a 2G object on an OSD device,
-	  you can then use this module to present that 2G object as
-	  a Linux block device.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called osdblk.
-
-	  If unsure, say N.
-
 config BLK_DEV_SX8
 	tristate "Promise SATA SX8 support"
 	depends on PCI
@@ -434,23 +418,6 @@ config ATA_OVER_ETH
 	This driver provides Support for ATA over Ethernet block
 	devices like the Coraid EtherDrive (R) Storage Blade.
 
-config MG_DISK
-	tristate "mGine mflash, gflash support"
-	depends on ARM && GPIOLIB
-	help
-	  mGine mFlash(gFlash) block device driver
-
-config MG_DISK_RES
-	int "Size of reserved area before MBR"
-	depends on MG_DISK
-	default 0
-	help
-	  Define size of reserved area that usually used for boot. Unit is KB.
-	  All of the block device operation will be taken this value as start
-	  offset
-	  Examples:
-			1024 => 1 MB
-
 config SUNVDC
 	tristate "Sun Virtual Disk Client support"
 	depends on SUN_LDOMS
@@ -512,19 +479,7 @@ config VIRTIO_BLK_SCSI
 	  Enable support for SCSI passthrough (e.g. the SG_IO ioctl) on
 	  virtio-blk devices.  This is only supported for the legacy
 	  virtio protocol and not enabled by default by any hypervisor.
-	  Your probably want to virtio-scsi instead.
-
-config BLK_DEV_HD
-	bool "Very old hard disk (MFM/RLL/IDE) driver"
-	depends on HAVE_IDE
-	depends on !ARM || ARCH_RPC || BROKEN
-	help
-	  This is a very old hard disk driver that lacks the enhanced
-	  functionality of the newer ones.
-
-	  It is required for systems with ancient MFM/RLL/ESDI drives.
-
-	  If unsure, say N.
+	  You probably want to use virtio-scsi instead.
 
 config BLK_DEV_RBD
 	tristate "Rados block device (RBD)"

drivers/block/Makefile

@@ -19,10 +19,8 @@ obj-$(CONFIG_BLK_CPQ_CISS_DA)  += cciss.o
 obj-$(CONFIG_BLK_DEV_DAC960)	+= DAC960.o
 obj-$(CONFIG_XILINX_SYSACE)	+= xsysace.o
 obj-$(CONFIG_CDROM_PKTCDVD)	+= pktcdvd.o
-obj-$(CONFIG_MG_DISK)		+= mg_disk.o
 obj-$(CONFIG_SUNVDC)		+= sunvdc.o
 obj-$(CONFIG_BLK_DEV_SKD)	+= skd.o
-obj-$(CONFIG_BLK_DEV_OSD)	+= osdblk.o
 
 obj-$(CONFIG_BLK_DEV_UMEM)	+= umem.o
 obj-$(CONFIG_BLK_DEV_NBD)	+= nbd.o
@@ -30,7 +28,6 @@ obj-$(CONFIG_BLK_DEV_CRYPTOLOOP) += cryptoloop.o
 obj-$(CONFIG_VIRTIO_BLK)	+= virtio_blk.o
 
 obj-$(CONFIG_BLK_DEV_SX8)	+= sx8.o
-obj-$(CONFIG_BLK_DEV_HD)	+= hd.o
 
 obj-$(CONFIG_XEN_BLKDEV_FRONTEND)	+= xen-blkfront.o
 obj-$(CONFIG_XEN_BLKDEV_BACKEND)	+= xen-blkback/

drivers/block/ataflop.c

@@ -617,12 +617,12 @@ static void fd_error( void )
 	if (!fd_request)
 		return;
 
-	fd_request->errors++;
-	if (fd_request->errors >= MAX_ERRORS) {
+	fd_request->error_count++;
+	if (fd_request->error_count >= MAX_ERRORS) {
 		printk(KERN_ERR "fd%d: too many errors.\n", SelectedDrive );
 		fd_end_request_cur(-EIO);
 	}
-	else if (fd_request->errors == RECALIBRATE_ERRORS) {
+	else if (fd_request->error_count == RECALIBRATE_ERRORS) {
 		printk(KERN_WARNING "fd%d: recalibrating\n", SelectedDrive );
 		if (SelectedDrive != -1)
 			SUD.track = -1;
@@ -1386,7 +1386,7 @@ static void setup_req_params( int drive )
 	ReqData = ReqBuffer + 512 * ReqCnt;
 
 	if (UseTrackbuffer)
-		read_track = (ReqCmd == READ && fd_request->errors == 0);
+		read_track = (ReqCmd == READ && fd_request->error_count == 0);
 	else
 		read_track = 0;
 
@@ -1409,8 +1409,10 @@ static struct request *set_next_request(void)
 			fdc_queue = 0;
 		if (q) {
 			rq = blk_fetch_request(q);
-			if (rq)
+			if (rq) {
+				rq->error_count = 0;
 				break;
+			}
 		}
 	} while (fdc_queue != old_pos);
 

drivers/block/brd.c

@@ -134,28 +134,6 @@ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector)
 	return page;
 }
 
-static void brd_free_page(struct brd_device *brd, sector_t sector)
-{
-	struct page *page;
-	pgoff_t idx;
-
-	spin_lock(&brd->brd_lock);
-	idx = sector >> PAGE_SECTORS_SHIFT;
-	page = radix_tree_delete(&brd->brd_pages, idx);
-	spin_unlock(&brd->brd_lock);
-	if (page)
-		__free_page(page);
-}
-
-static void brd_zero_page(struct brd_device *brd, sector_t sector)
-{
-	struct page *page;
-
-	page = brd_lookup_page(brd, sector);
-	if (page)
-		clear_highpage(page);
-}
-
 /*
  * Free all backing store pages and radix tree. This must only be called when
  * there are no other users of the device.
@@ -212,24 +190,6 @@ static int copy_to_brd_setup(struct brd_device *brd, sector_t sector, size_t n)
 	return 0;
 }
 
-static void discard_from_brd(struct brd_device *brd,
-			sector_t sector, size_t n)
-{
-	while (n >= PAGE_SIZE) {
-		/*
-		 * Don't want to actually discard pages here because
-		 * re-allocating the pages can result in writeback
-		 * deadlocks under heavy load.
-		 */
-		if (0)
-			brd_free_page(brd, sector);
-		else
-			brd_zero_page(brd, sector);
-		sector += PAGE_SIZE >> SECTOR_SHIFT;
-		n -= PAGE_SIZE;
-	}
-}
-
 /*
  * Copy n bytes from src to the brd starting at sector. Does not sleep.
  */
@@ -338,14 +298,6 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 	if (bio_end_sector(bio) > get_capacity(bdev->bd_disk))
 		goto io_error;
 
-	if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) {
-		if (sector & ((PAGE_SIZE >> SECTOR_SHIFT) - 1) ||
-		    bio->bi_iter.bi_size & ~PAGE_MASK)
-			goto io_error;
-		discard_from_brd(brd, sector, bio->bi_iter.bi_size);
-		goto out;
-	}
-
 	bio_for_each_segment(bvec, bio, iter) {
 		unsigned int len = bvec.bv_len;
 		int err;
@@ -357,7 +309,6 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 		sector += len >> SECTOR_SHIFT;
 	}
 
-out:
 	bio_endio(bio);
 	return BLK_QC_T_NONE;
 io_error:
@@ -464,11 +415,6 @@ static struct brd_device *brd_alloc(int i)
 	 *  is harmless)
 	 */
 	blk_queue_physical_block_size(brd->brd_queue, PAGE_SIZE);
-
-	brd->brd_queue->limits.discard_granularity = PAGE_SIZE;
-	blk_queue_max_discard_sectors(brd->brd_queue, UINT_MAX);
-	brd->brd_queue->limits.discard_zeroes_data = 1;
-	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, brd->brd_queue);
 #ifdef CONFIG_BLK_DEV_RAM_DAX
 	queue_flag_set_unlocked(QUEUE_FLAG_DAX, brd->brd_queue);
 #endif

drivers/block/cciss.c

@@ -1864,8 +1864,7 @@ static void cciss_softirq_done(struct request *rq)
 	/* set the residual count for pc requests */
 	if (blk_rq_is_passthrough(rq))
 		scsi_req(rq)->resid_len = c->err_info->ResidualCnt;
-
-	blk_end_request_all(rq, (rq->errors == 0) ? 0 : -EIO);
+	blk_end_request_all(rq, scsi_req(rq)->result ? -EIO : 0);
 
 	spin_lock_irqsave(&h->lock, flags);
 	cmd_free(h, c);
@@ -3140,18 +3139,19 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 {
 	int retry_cmd = 0;
 	struct request *rq = cmd->rq;
+	struct scsi_request *sreq = scsi_req(rq);
 
-	rq->errors = 0;
+	sreq->result = 0;
 
 	if (timeout)
-		rq->errors = make_status_bytes(0, 0, 0, DRIVER_TIMEOUT);
+		sreq->result = make_status_bytes(0, 0, 0, DRIVER_TIMEOUT);
 
 	if (cmd->err_info->CommandStatus == 0)	/* no error has occurred */
 		goto after_error_processing;
 
 	switch (cmd->err_info->CommandStatus) {
 	case CMD_TARGET_STATUS:
-		rq->errors = evaluate_target_status(h, cmd, &retry_cmd);
+		sreq->result = evaluate_target_status(h, cmd, &retry_cmd);
 		break;
 	case CMD_DATA_UNDERRUN:
 		if (!blk_rq_is_passthrough(cmd->rq)) {
@@ -3169,7 +3169,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 	case CMD_INVALID:
 		dev_warn(&h->pdev->dev, "cciss: cmd %p is "
 		       "reported invalid\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
@@ -3177,7 +3177,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 	case CMD_PROTOCOL_ERR:
 		dev_warn(&h->pdev->dev, "cciss: cmd %p has "
 		       "protocol error\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
@@ -3185,7 +3185,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 	case CMD_HARDWARE_ERR:
 		dev_warn(&h->pdev->dev, "cciss: cmd %p had "
 		       " hardware error\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
@@ -3193,7 +3193,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 	case CMD_CONNECTION_LOST:
 		dev_warn(&h->pdev->dev, "cciss: cmd %p had "
 		       "connection lost\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
@@ -3201,7 +3201,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 	case CMD_ABORTED:
 		dev_warn(&h->pdev->dev, "cciss: cmd %p was "
 		       "aborted\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ABORT);
@@ -3209,7 +3209,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 	case CMD_ABORT_FAILED:
 		dev_warn(&h->pdev->dev, "cciss: cmd %p reports "
 		       "abort failed\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
@@ -3224,21 +3224,21 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		} else
 			dev_warn(&h->pdev->dev,
 				"%p retried too many times\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ABORT);
 		break;
 	case CMD_TIMEOUT:
 		dev_warn(&h->pdev->dev, "cmd %p timedout\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
 		break;
 	case CMD_UNABORTABLE:
 		dev_warn(&h->pdev->dev, "cmd %p unabortable\n", cmd);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
@@ -3247,7 +3247,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
 		dev_warn(&h->pdev->dev, "cmd %p returned "
 		       "unknown status %x\n", cmd,
 		       cmd->err_info->CommandStatus);
-		rq->errors = make_status_bytes(SAM_STAT_GOOD,
+		sreq->result = make_status_bytes(SAM_STAT_GOOD,
 			cmd->err_info->CommandStatus, DRIVER_OK,
 			blk_rq_is_passthrough(cmd->rq) ?
 				DID_PASSTHROUGH : DID_ERROR);
@@ -3380,9 +3380,9 @@ static void do_cciss_request(struct request_queue *q)
 		if (dma_mapping_error(&h->pdev->dev, temp64.val)) {
 			dev_warn(&h->pdev->dev,
 				"%s: error mapping page for DMA\n", __func__);
-			creq->errors = make_status_bytes(SAM_STAT_GOOD,
-							0, DRIVER_OK,
-							DID_SOFT_ERROR);
+			scsi_req(creq)->result =
+				make_status_bytes(SAM_STAT_GOOD, 0, DRIVER_OK,
+						  DID_SOFT_ERROR);
 			cmd_free(h, c);
 			return;
 		}
@@ -3395,9 +3395,9 @@ static void do_cciss_request(struct request_queue *q)
 		if (cciss_map_sg_chain_block(h, c, h->cmd_sg_list[c->cmdindex],
 			(seg - (h->max_cmd_sgentries - 1)) *
 				sizeof(SGDescriptor_struct))) {
-			creq->errors = make_status_bytes(SAM_STAT_GOOD,
-							0, DRIVER_OK,
-							DID_SOFT_ERROR);
+			scsi_req(creq)->result =
+				make_status_bytes(SAM_STAT_GOOD, 0, DRIVER_OK,
+						  DID_SOFT_ERROR);
 			cmd_free(h, c);
 			return;
 		}

drivers/block/drbd/drbd_debugfs.c

@@ -236,9 +236,6 @@ static void seq_print_peer_request_flags(struct seq_file *m, struct drbd_peer_re
 	seq_print_rq_state_bit(m, f & EE_CALL_AL_COMPLETE_IO, &sep, "in-AL");
 	seq_print_rq_state_bit(m, f & EE_SEND_WRITE_ACK, &sep, "C");
 	seq_print_rq_state_bit(m, f & EE_MAY_SET_IN_SYNC, &sep, "set-in-sync");
-
-	if (f & EE_IS_TRIM)
-		__seq_print_rq_state_bit(m, f & EE_IS_TRIM_USE_ZEROOUT, &sep, "zero-out", "trim");
 	seq_print_rq_state_bit(m, f & EE_WRITE_SAME, &sep, "write-same");
 	seq_putc(m, '\n');
 }

drivers/block/drbd/drbd_int.h

@@ -437,9 +437,6 @@ enum {
 
 	/* is this a TRIM aka REQ_DISCARD? */
 	__EE_IS_TRIM,
-	/* our lower level cannot handle trim,
-	 * and we want to fall back to zeroout instead */
-	__EE_IS_TRIM_USE_ZEROOUT,
 
 	/* In case a barrier failed,
 	 * we need to resubmit without the barrier flag. */
@@ -482,7 +479,6 @@ enum {
 #define EE_CALL_AL_COMPLETE_IO (1<<__EE_CALL_AL_COMPLETE_IO)
 #define EE_MAY_SET_IN_SYNC     (1<<__EE_MAY_SET_IN_SYNC)
 #define EE_IS_TRIM             (1<<__EE_IS_TRIM)
-#define EE_IS_TRIM_USE_ZEROOUT (1<<__EE_IS_TRIM_USE_ZEROOUT)
 #define EE_RESUBMITTED         (1<<__EE_RESUBMITTED)
 #define EE_WAS_ERROR           (1<<__EE_WAS_ERROR)
 #define EE_HAS_DIGEST          (1<<__EE_HAS_DIGEST)
@@ -1561,8 +1557,6 @@ extern void start_resync_timer_fn(unsigned long data);
 extern void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req);
 
 /* drbd_receiver.c */
-extern int drbd_issue_discard_or_zero_out(struct drbd_device *device,
-		sector_t start, unsigned int nr_sectors, bool discard);
 extern int drbd_receiver(struct drbd_thread *thi);
 extern int drbd_ack_receiver(struct drbd_thread *thi);
 extern void drbd_send_ping_wf(struct work_struct *ws);

drivers/block/drbd/drbd_main.c

@@ -931,7 +931,6 @@ void assign_p_sizes_qlim(struct drbd_device *device, struct p_sizes *p, struct r
 		p->qlim->io_min = cpu_to_be32(queue_io_min(q));
 		p->qlim->io_opt = cpu_to_be32(queue_io_opt(q));
 		p->qlim->discard_enabled = blk_queue_discard(q);
-		p->qlim->discard_zeroes_data = queue_discard_zeroes_data(q);
 		p->qlim->write_same_capable = !!q->limits.max_write_same_sectors;
 	} else {
 		q = device->rq_queue;
@@ -941,7 +940,6 @@ void assign_p_sizes_qlim(struct drbd_device *device, struct p_sizes *p, struct r
 		p->qlim->io_min = cpu_to_be32(queue_io_min(q));
 		p->qlim->io_opt = cpu_to_be32(queue_io_opt(q));
 		p->qlim->discard_enabled = 0;
-		p->qlim->discard_zeroes_data = 0;
 		p->qlim->write_same_capable = 0;
 	}
 }
@@ -1668,7 +1666,8 @@ static u32 bio_flags_to_wire(struct drbd_connection *connection,
 			(bio->bi_opf & REQ_FUA ? DP_FUA : 0) |
 			(bio->bi_opf & REQ_PREFLUSH ? DP_FLUSH : 0) |
 			(bio_op(bio) == REQ_OP_WRITE_SAME ? DP_WSAME : 0) |
-			(bio_op(bio) == REQ_OP_DISCARD ? DP_DISCARD : 0);
+			(bio_op(bio) == REQ_OP_DISCARD ? DP_DISCARD : 0) |
+			(bio_op(bio) == REQ_OP_WRITE_ZEROES ? DP_DISCARD : 0);
 	else
 		return bio->bi_opf & REQ_SYNC ? DP_RW_SYNC : 0;
 }

drivers/block/drbd/drbd_nl.c

@@ -1199,10 +1199,6 @@ static void decide_on_discard_support(struct drbd_device *device,
 	struct drbd_connection *connection = first_peer_device(device)->connection;
 	bool can_do = b ? blk_queue_discard(b) : true;
 
-	if (can_do && b && !b->limits.discard_zeroes_data && !discard_zeroes_if_aligned) {
-		can_do = false;
-		drbd_info(device, "discard_zeroes_data=0 and discard_zeroes_if_aligned=no: disabling discards\n");
-	}
 	if (can_do && connection->cstate >= C_CONNECTED && !(connection->agreed_features & DRBD_FF_TRIM)) {
 		can_do = false;
 		drbd_info(connection, "peer DRBD too old, does not support TRIM: disabling discards\n");
@@ -1217,10 +1213,12 @@ static void decide_on_discard_support(struct drbd_device *device,
 		blk_queue_discard_granularity(q, 512);
 		q->limits.max_discard_sectors = drbd_max_discard_sectors(connection);
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
+		q->limits.max_write_zeroes_sectors = drbd_max_discard_sectors(connection);
 	} else {
 		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
 		blk_queue_discard_granularity(q, 0);
 		q->limits.max_discard_sectors = 0;
+		q->limits.max_write_zeroes_sectors = 0;
 	}
 }
 
@@ -1482,8 +1480,7 @@ static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *dis
 	if (disk_conf->al_extents > drbd_al_extents_max(nbc))
 		disk_conf->al_extents = drbd_al_extents_max(nbc);
 
-	if (!blk_queue_discard(q)
-	    || (!q->limits.discard_zeroes_data && !disk_conf->discard_zeroes_if_aligned)) {
+	if (!blk_queue_discard(q)) {
 		if (disk_conf->rs_discard_granularity) {
 			disk_conf->rs_discard_granularity = 0; /* disable feature */
 			drbd_info(device, "rs_discard_granularity feature disabled\n");

drivers/block/drbd/drbd_receiver.c

@@ -1448,105 +1448,14 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin
 		drbd_info(resource, "Method to ensure write ordering: %s\n", write_ordering_str[resource->write_ordering]);
 }
 
-/*
- * We *may* ignore the discard-zeroes-data setting, if so configured.
- *
- * Assumption is that it "discard_zeroes_data=0" is only because the backend
- * may ignore partial unaligned discards.
- *
- * LVM/DM thin as of at least
- *   LVM version:     2.02.115(2)-RHEL7 (2015-01-28)
- *   Library version: 1.02.93-RHEL7 (2015-01-28)
- *   Driver version:  4.29.0
- * still behaves this way.
- *
- * For unaligned (wrt. alignment and granularity) or too small discards,
- * we zero-out the initial (and/or) trailing unaligned partial chunks,
- * but discard all the aligned full chunks.
- *
- * At least for LVM/DM thin, the result is effectively "discard_zeroes_data=1".
- */
-int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, unsigned int nr_sectors, bool discard)
-{
-	struct block_device *bdev = device->ldev->backing_bdev;
-	struct request_queue *q = bdev_get_queue(bdev);
-	sector_t tmp, nr;
-	unsigned int max_discard_sectors, granularity;
-	int alignment;
-	int err = 0;
-
-	if (!discard)
-		goto zero_out;
-
-	/* Zero-sector (unknown) and one-sector granularities are the same.  */
-	granularity = max(q->limits.discard_granularity >> 9, 1U);
-	alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
-
-	max_discard_sectors = min(q->limits.max_discard_sectors, (1U << 22));
-	max_discard_sectors -= max_discard_sectors % granularity;
-	if (unlikely(!max_discard_sectors))
-		goto zero_out;
-
-	if (nr_sectors < granularity)
-		goto zero_out;
-
-	tmp = start;
-	if (sector_div(tmp, granularity) != alignment) {
-		if (nr_sectors < 2*granularity)
-			goto zero_out;
-		/* start + gran - (start + gran - align) % gran */
-		tmp = start + granularity - alignment;
-		tmp = start + granularity - sector_div(tmp, granularity);
-
-		nr = tmp - start;
-		err |= blkdev_issue_zeroout(bdev, start, nr, GFP_NOIO, 0);
-		nr_sectors -= nr;
-		start = tmp;
-	}
-	while (nr_sectors >= granularity) {
-		nr = min_t(sector_t, nr_sectors, max_discard_sectors);
-		err |= blkdev_issue_discard(bdev, start, nr, GFP_NOIO, 0);
-		nr_sectors -= nr;
-		start += nr;
-	}
- zero_out:
-	if (nr_sectors) {
-		err |= blkdev_issue_zeroout(bdev, start, nr_sectors, GFP_NOIO, 0);
-	}
-	return err != 0;
-}
-
-static bool can_do_reliable_discards(struct drbd_device *device)
-{
-	struct request_queue *q = bdev_get_queue(device->ldev->backing_bdev);
-	struct disk_conf *dc;
-	bool can_do;
-
-	if (!blk_queue_discard(q))
-		return false;
-
-	if (q->limits.discard_zeroes_data)
-		return true;
-
-	rcu_read_lock();
-	dc = rcu_dereference(device->ldev->disk_conf);
-	can_do = dc->discard_zeroes_if_aligned;
-	rcu_read_unlock();
-	return can_do;
-}
-
 static void drbd_issue_peer_discard(struct drbd_device *device, struct drbd_peer_request *peer_req)
 {
-	/* If the backend cannot discard, or does not guarantee
-	 * read-back zeroes in discarded ranges, we fall back to
-	 * zero-out.  Unless configuration specifically requested
-	 * otherwise. */
-	if (!can_do_reliable_discards(device))
-		peer_req->flags |= EE_IS_TRIM_USE_ZEROOUT;
+	struct block_device *bdev = device->ldev->backing_bdev;
 
-	if (drbd_issue_discard_or_zero_out(device, peer_req->i.sector,
-	    peer_req->i.size >> 9, !(peer_req->flags & EE_IS_TRIM_USE_ZEROOUT)))
+	if (blkdev_issue_zeroout(bdev, peer_req->i.sector, peer_req->i.size >> 9,
+			GFP_NOIO, 0))
 		peer_req->flags |= EE_WAS_ERROR;
+
 	drbd_endio_write_sec_final(peer_req);
 }
 
@@ -2376,7 +2285,7 @@ static unsigned long wire_flags_to_bio_flags(u32 dpf)
 static unsigned long wire_flags_to_bio_op(u32 dpf)
 {
 	if (dpf & DP_DISCARD)
-		return REQ_OP_DISCARD;
+		return REQ_OP_WRITE_ZEROES;
 	else
 		return REQ_OP_WRITE;
 }
@@ -2567,7 +2476,7 @@ static int receive_Data(struct drbd_connection *connection, struct packet_info *
 	op_flags = wire_flags_to_bio_flags(dp_flags);
 	if (pi->cmd == P_TRIM) {
 		D_ASSERT(peer_device, peer_req->i.size > 0);
-		D_ASSERT(peer_device, op == REQ_OP_DISCARD);
+		D_ASSERT(peer_device, op == REQ_OP_WRITE_ZEROES);
 		D_ASSERT(peer_device, peer_req->pages == NULL);
 	} else if (peer_req->pages == NULL) {
 		D_ASSERT(device, peer_req->i.size == 0);
@@ -4880,7 +4789,7 @@ static int receive_rs_deallocated(struct drbd_connection *connection, struct pac
 
 	if (get_ldev(device)) {
 		struct drbd_peer_request *peer_req;
-		const int op = REQ_OP_DISCARD;
+		const int op = REQ_OP_WRITE_ZEROES;
 
 		peer_req = drbd_alloc_peer_req(peer_device, ID_SYNCER, sector,
 					       size, 0, GFP_NOIO);

drivers/block/drbd/drbd_req.c

@@ -59,6 +59,7 @@ static struct drbd_request *drbd_req_new(struct drbd_device *device, struct bio
 	drbd_req_make_private_bio(req, bio_src);
 	req->rq_state = (bio_data_dir(bio_src) == WRITE ? RQ_WRITE : 0)
 		      | (bio_op(bio_src) == REQ_OP_WRITE_SAME ? RQ_WSAME : 0)
+		      | (bio_op(bio_src) == REQ_OP_WRITE_ZEROES ? RQ_UNMAP : 0)
 		      | (bio_op(bio_src) == REQ_OP_DISCARD ? RQ_UNMAP : 0);
 	req->device = device;
 	req->master_bio = bio_src;
@@ -1148,10 +1149,10 @@ static int drbd_process_write_request(struct drbd_request *req)
 
 static void drbd_process_discard_req(struct drbd_request *req)
 {
-	int err = drbd_issue_discard_or_zero_out(req->device,
-				req->i.sector, req->i.size >> 9, true);
+	struct block_device *bdev = req->device->ldev->backing_bdev;
 
-	if (err)
+	if (blkdev_issue_zeroout(bdev, req->i.sector, req->i.size >> 9,
+			GFP_NOIO, 0))
 		req->private_bio->bi_error = -EIO;
 	bio_endio(req->private_bio);
 }
@@ -1180,7 +1181,8 @@ drbd_submit_req_private_bio(struct drbd_request *req)
 	if (get_ldev(device)) {
 		if (drbd_insert_fault(device, type))
 			bio_io_error(bio);
-		else if (bio_op(bio) == REQ_OP_DISCARD)
+		else if (bio_op(bio) == REQ_OP_WRITE_ZEROES ||
+			 bio_op(bio) == REQ_OP_DISCARD)
 			drbd_process_discard_req(req);
 		else
 			generic_make_request(bio);
@@ -1234,7 +1236,8 @@ drbd_request_prepare(struct drbd_device *device, struct bio *bio, unsigned long
 	_drbd_start_io_acct(device, req);
 
 	/* process discards always from our submitter thread */
-	if (bio_op(bio) & REQ_OP_DISCARD)
+	if ((bio_op(bio) & REQ_OP_WRITE_ZEROES) ||
+	    (bio_op(bio) & REQ_OP_DISCARD))
 		goto queue_for_submitter_thread;
 
 	if (rw == WRITE && req->private_bio && req->i.size

drivers/block/drbd/drbd_worker.c

@@ -174,7 +174,8 @@ void drbd_peer_request_endio(struct bio *bio)
 	struct drbd_peer_request *peer_req = bio->bi_private;
 	struct drbd_device *device = peer_req->peer_device->device;
 	bool is_write = bio_data_dir(bio) == WRITE;
-	bool is_discard = !!(bio_op(bio) == REQ_OP_DISCARD);
+	bool is_discard = bio_op(bio) == REQ_OP_WRITE_ZEROES ||
+			  bio_op(bio) == REQ_OP_DISCARD;
 
 	if (bio->bi_error && __ratelimit(&drbd_ratelimit_state))
 		drbd_warn(device, "%s: error=%d s=%llus\n",
@@ -249,6 +250,7 @@ void drbd_request_endio(struct bio *bio)
 	/* to avoid recursion in __req_mod */
 	if (unlikely(bio->bi_error)) {
 		switch (bio_op(bio)) {
+		case REQ_OP_WRITE_ZEROES:
 		case REQ_OP_DISCARD:
 			if (bio->bi_error == -EOPNOTSUPP)
 				what = DISCARD_COMPLETED_NOTSUPP;

drivers/block/floppy.c

@@ -2805,8 +2805,10 @@ static int set_next_request(void)
 			fdc_queue = 0;
 		if (q) {
 			current_req = blk_fetch_request(q);
-			if (current_req)
+			if (current_req) {
+				current_req->error_count = 0;
 				break;
+			}
 		}
 	} while (fdc_queue != old_pos);
 
@@ -2866,7 +2868,7 @@ do_request:
 		_floppy = floppy_type + DP->autodetect[DRS->probed_format];
 	} else
 		probing = 0;
-	errors = &(current_req->errors);
+	errors = &(current_req->error_count);
 	tmp = make_raw_rw_request();
 	if (tmp < 2) {
 		request_done(tmp);
@@ -4207,9 +4209,7 @@ static int __init do_floppy_init(void)
 		disks[drive]->fops = &floppy_fops;
 		sprintf(disks[drive]->disk_name, "fd%d", drive);
 
-		init_timer(&motor_off_timer[drive]);
-		motor_off_timer[drive].data = drive;
-		motor_off_timer[drive].function = motor_off_callback;
+		setup_timer(&motor_off_timer[drive], motor_off_callback, drive);
 	}
 
 	err = register_blkdev(FLOPPY_MAJOR, "fd");

drivers/block/hd.c

@@ -1,803 +0,0 @@
-/*
- *  Copyright (C) 1991, 1992  Linus Torvalds
- *
- * This is the low-level hd interrupt support. It traverses the
- * request-list, using interrupts to jump between functions. As
- * all the functions are called within interrupts, we may not
- * sleep. Special care is recommended.
- *
- *  modified by Drew Eckhardt to check nr of hd's from the CMOS.
- *
- *  Thanks to Branko Lankester, lankeste@fwi.uva.nl, who found a bug
- *  in the early extended-partition checks and added DM partitions
- *
- *  IRQ-unmask, drive-id, multiple-mode, support for ">16 heads",
- *  and general streamlining by Mark Lord.
- *
- *  Removed 99% of above. Use Mark's ide driver for those options.
- *  This is now a lightweight ST-506 driver. (Paul Gortmaker)
- *
- *  Modified 1995 Russell King for ARM processor.
- *
- *  Bugfix: max_sectors must be <= 255 or the wheels tend to come
- *  off in a hurry once you queue things up - Paul G. 02/2001
- */
-
-/* Uncomment the following if you want verbose error reports. */
-/* #define VERBOSE_ERRORS */
-
-#include <linux/blkdev.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/interrupt.h>
-#include <linux/timer.h>
-#include <linux/fs.h>
-#include <linux/kernel.h>
-#include <linux/genhd.h>
-#include <linux/string.h>
-#include <linux/ioport.h>
-#include <linux/init.h>
-#include <linux/blkpg.h>
-#include <linux/ata.h>
-#include <linux/hdreg.h>
-
-#define HD_IRQ 14
-
-#define REALLY_SLOW_IO
-#include <asm/io.h>
-#include <linux/uaccess.h>
-
-#ifdef __arm__
-#undef  HD_IRQ
-#endif
-#include <asm/irq.h>
-#ifdef __arm__
-#define HD_IRQ IRQ_HARDDISK
-#endif
-
-/* Hd controller regster ports */
-
-#define HD_DATA		0x1f0		/* _CTL when writing */
-#define HD_ERROR	0x1f1		/* see err-bits */
-#define HD_NSECTOR	0x1f2		/* nr of sectors to read/write */
-#define HD_SECTOR	0x1f3		/* starting sector */
-#define HD_LCYL		0x1f4		/* starting cylinder */
-#define HD_HCYL		0x1f5		/* high byte of starting cyl */
-#define HD_CURRENT	0x1f6		/* 101dhhhh , d=drive, hhhh=head */
-#define HD_STATUS	0x1f7		/* see status-bits */
-#define HD_FEATURE	HD_ERROR	/* same io address, read=error, write=feature */
-#define HD_PRECOMP	HD_FEATURE	/* obsolete use of this port - predates IDE */
-#define HD_COMMAND	HD_STATUS	/* same io address, read=status, write=cmd */
-
-#define HD_CMD		0x3f6		/* used for resets */
-#define HD_ALTSTATUS	0x3f6		/* same as HD_STATUS but doesn't clear irq */
-
-/* Bits of HD_STATUS */
-#define ERR_STAT		0x01
-#define INDEX_STAT		0x02
-#define ECC_STAT		0x04	/* Corrected error */
-#define DRQ_STAT		0x08
-#define SEEK_STAT		0x10
-#define SERVICE_STAT		SEEK_STAT
-#define WRERR_STAT		0x20
-#define READY_STAT		0x40
-#define BUSY_STAT		0x80
-
-/* Bits for HD_ERROR */
-#define MARK_ERR		0x01	/* Bad address mark */
-#define TRK0_ERR		0x02	/* couldn't find track 0 */
-#define ABRT_ERR		0x04	/* Command aborted */
-#define MCR_ERR			0x08	/* media change request */
-#define ID_ERR			0x10	/* ID field not found */
-#define MC_ERR			0x20	/* media changed */
-#define ECC_ERR			0x40	/* Uncorrectable ECC error */
-#define BBD_ERR			0x80	/* pre-EIDE meaning:  block marked bad */
-#define ICRC_ERR		0x80	/* new meaning:  CRC error during transfer */
-
-static DEFINE_SPINLOCK(hd_lock);
-static struct request_queue *hd_queue;
-static struct request *hd_req;
-
-#define TIMEOUT_VALUE	(6*HZ)
-#define	HD_DELAY	0
-
-#define MAX_ERRORS     16	/* Max read/write errors/sector */
-#define RESET_FREQ      8	/* Reset controller every 8th retry */
-#define RECAL_FREQ      4	/* Recalibrate every 4th retry */
-#define MAX_HD		2
-
-#define STAT_OK		(READY_STAT|SEEK_STAT)
-#define OK_STATUS(s)	(((s)&(STAT_OK|(BUSY_STAT|WRERR_STAT|ERR_STAT)))==STAT_OK)
-
-static void recal_intr(void);
-static void bad_rw_intr(void);
-
-static int reset;
-static int hd_error;
-
-/*
- *  This struct defines the HD's and their types.
- */
-struct hd_i_struct {
-	unsigned int head, sect, cyl, wpcom, lzone, ctl;
-	int unit;
-	int recalibrate;
-	int special_op;
-};
-
-#ifdef HD_TYPE
-static struct hd_i_struct hd_info[] = { HD_TYPE };
-static int NR_HD = ARRAY_SIZE(hd_info);
-#else
-static struct hd_i_struct hd_info[MAX_HD];
-static int NR_HD;
-#endif
-
-static struct gendisk *hd_gendisk[MAX_HD];
-
-static struct timer_list device_timer;
-
-#define TIMEOUT_VALUE (6*HZ)
-
-#define SET_TIMER							\
-	do {								\
-		mod_timer(&device_timer, jiffies + TIMEOUT_VALUE);	\
-	} while (0)
-
-static void (*do_hd)(void) = NULL;
-#define SET_HANDLER(x) \
-if ((do_hd = (x)) != NULL) \
-	SET_TIMER; \
-else \
-	del_timer(&device_timer);
-
-
-#if (HD_DELAY > 0)
-
-#include <linux/i8253.h>
-
-unsigned long last_req;
-
-unsigned long read_timer(void)
-{
-	unsigned long t, flags;
-	int i;
-
-	raw_spin_lock_irqsave(&i8253_lock, flags);
-	t = jiffies * 11932;
-	outb_p(0, 0x43);
-	i = inb_p(0x40);
-	i |= inb(0x40) << 8;
-	raw_spin_unlock_irqrestore(&i8253_lock, flags);
-	return(t - i);
-}
-#endif
-
-static void __init hd_setup(char *str, int *ints)
-{
-	int hdind = 0;
-
-	if (ints[0] != 3)
-		return;
-	if (hd_info[0].head != 0)
-		hdind = 1;
-	hd_info[hdind].head = ints[2];
-	hd_info[hdind].sect = ints[3];
-	hd_info[hdind].cyl = ints[1];
-	hd_info[hdind].wpcom = 0;
-	hd_info[hdind].lzone = ints[1];
-	hd_info[hdind].ctl = (ints[2] > 8 ? 8 : 0);
-	NR_HD = hdind+1;
-}
-
-static bool hd_end_request(int err, unsigned int bytes)
-{
-	if (__blk_end_request(hd_req, err, bytes))
-		return true;
-	hd_req = NULL;
-	return false;
-}
-
-static bool hd_end_request_cur(int err)
-{
-	return hd_end_request(err, blk_rq_cur_bytes(hd_req));
-}
-
-static void dump_status(const char *msg, unsigned int stat)
-{
-	char *name = "hd?";
-	if (hd_req)
-		name = hd_req->rq_disk->disk_name;
-
-#ifdef VERBOSE_ERRORS
-	printk("%s: %s: status=0x%02x { ", name, msg, stat & 0xff);
-	if (stat & BUSY_STAT)	printk("Busy ");
-	if (stat & READY_STAT)	printk("DriveReady ");
-	if (stat & WRERR_STAT)	printk("WriteFault ");
-	if (stat & SEEK_STAT)	printk("SeekComplete ");
-	if (stat & DRQ_STAT)	printk("DataRequest ");
-	if (stat & ECC_STAT)	printk("CorrectedError ");
-	if (stat & INDEX_STAT)	printk("Index ");
-	if (stat & ERR_STAT)	printk("Error ");
-	printk("}\n");
-	if ((stat & ERR_STAT) == 0) {
-		hd_error = 0;
-	} else {
-		hd_error = inb(HD_ERROR);
-		printk("%s: %s: error=0x%02x { ", name, msg, hd_error & 0xff);
-		if (hd_error & BBD_ERR)		printk("BadSector ");
-		if (hd_error & ECC_ERR)		printk("UncorrectableError ");
-		if (hd_error & ID_ERR)		printk("SectorIdNotFound ");
-		if (hd_error & ABRT_ERR)	printk("DriveStatusError ");
-		if (hd_error & TRK0_ERR)	printk("TrackZeroNotFound ");
-		if (hd_error & MARK_ERR)	printk("AddrMarkNotFound ");
-		printk("}");
-		if (hd_error & (BBD_ERR|ECC_ERR|ID_ERR|MARK_ERR)) {
-			printk(", CHS=%d/%d/%d", (inb(HD_HCYL)<<8) + inb(HD_LCYL),
-				inb(HD_CURRENT) & 0xf, inb(HD_SECTOR));
-			if (hd_req)
-				printk(", sector=%ld", blk_rq_pos(hd_req));
-		}
-		printk("\n");
-	}
-#else
-	printk("%s: %s: status=0x%02x.\n", name, msg, stat & 0xff);
-	if ((stat & ERR_STAT) == 0) {
-		hd_error = 0;
-	} else {
-		hd_error = inb(HD_ERROR);
-		printk("%s: %s: error=0x%02x.\n", name, msg, hd_error & 0xff);
-	}
-#endif
-}
-
-static void check_status(void)
-{
-	int i = inb_p(HD_STATUS);
-
-	if (!OK_STATUS(i)) {
-		dump_status("check_status", i);
-		bad_rw_intr();
-	}
-}
-
-static int controller_busy(void)
-{
-	int retries = 100000;
-	unsigned char status;
-
-	do {
-		status = inb_p(HD_STATUS);
-	} while ((status & BUSY_STAT) && --retries);
-	return status;
-}
-
-static int status_ok(void)
-{
-	unsigned char status = inb_p(HD_STATUS);
-
-	if (status & BUSY_STAT)
-		return 1;	/* Ancient, but does it make sense??? */
-	if (status & WRERR_STAT)
-		return 0;
-	if (!(status & READY_STAT))
-		return 0;
-	if (!(status & SEEK_STAT))
-		return 0;
-	return 1;
-}
-
-static int controller_ready(unsigned int drive, unsigned int head)
-{
-	int retry = 100;
-
-	do {
-		if (controller_busy() & BUSY_STAT)
-			return 0;
-		outb_p(0xA0 | (drive<<4) | head, HD_CURRENT);
-		if (status_ok())
-			return 1;
-	} while (--retry);
-	return 0;
-}
-
-static void hd_out(struct hd_i_struct *disk,
-		   unsigned int nsect,
-		   unsigned int sect,
-		   unsigned int head,
-		   unsigned int cyl,
-		   unsigned int cmd,
-		   void (*intr_addr)(void))
-{
-	unsigned short port;
-
-#if (HD_DELAY > 0)
-	while (read_timer() - last_req < HD_DELAY)
-		/* nothing */;
-#endif
-	if (reset)
-		return;
-	if (!controller_ready(disk->unit, head)) {
-		reset = 1;
-		return;
-	}
-	SET_HANDLER(intr_addr);
-	outb_p(disk->ctl, HD_CMD);
-	port = HD_DATA;
-	outb_p(disk->wpcom >> 2, ++port);
-	outb_p(nsect, ++port);
-	outb_p(sect, ++port);
-	outb_p(cyl, ++port);
-	outb_p(cyl >> 8, ++port);
-	outb_p(0xA0 | (disk->unit << 4) | head, ++port);
-	outb_p(cmd, ++port);
-}
-
-static void hd_request (void);
-
-static int drive_busy(void)
-{
-	unsigned int i;
-	unsigned char c;
-
-	for (i = 0; i < 500000 ; i++) {
-		c = inb_p(HD_STATUS);
-		if ((c & (BUSY_STAT | READY_STAT | SEEK_STAT)) == STAT_OK)
-			return 0;
-	}
-	dump_status("reset timed out", c);
-	return 1;
-}
-
-static void reset_controller(void)
-{
-	int	i;
-
-	outb_p(4, HD_CMD);
-	for (i = 0; i < 1000; i++) barrier();
-	outb_p(hd_info[0].ctl & 0x0f, HD_CMD);
-	for (i = 0; i < 1000; i++) barrier();
-	if (drive_busy())
-		printk("hd: controller still busy\n");
-	else if ((hd_error = inb(HD_ERROR)) != 1)
-		printk("hd: controller reset failed: %02x\n", hd_error);
-}
-
-static void reset_hd(void)
-{
-	static int i;
-
-repeat:
-	if (reset) {
-		reset = 0;
-		i = -1;
-		reset_controller();
-	} else {
-		check_status();
-		if (reset)
-			goto repeat;
-	}
-	if (++i < NR_HD) {
-		struct hd_i_struct *disk = &hd_info[i];
-		disk->special_op = disk->recalibrate = 1;
-		hd_out(disk, disk->sect, disk->sect, disk->head-1,
-			disk->cyl, ATA_CMD_INIT_DEV_PARAMS, &reset_hd);
-		if (reset)
-			goto repeat;
-	} else
-		hd_request();
-}
-
-/*
- * Ok, don't know what to do with the unexpected interrupts: on some machines
- * doing a reset and a retry seems to result in an eternal loop. Right now I
- * ignore it, and just set the timeout.
- *
- * On laptops (and "green" PCs), an unexpected interrupt occurs whenever the
- * drive enters "idle", "standby", or "sleep" mode, so if the status looks
- * "good", we just ignore the interrupt completely.
- */
-static void unexpected_hd_interrupt(void)
-{
-	unsigned int stat = inb_p(HD_STATUS);
-
-	if (stat & (BUSY_STAT|DRQ_STAT|ECC_STAT|ERR_STAT)) {
-		dump_status("unexpected interrupt", stat);
-		SET_TIMER;
-	}
-}
-
-/*
- * bad_rw_intr() now tries to be a bit smarter and does things
- * according to the error returned by the controller.
- * -Mika Liljeberg (liljeber@cs.Helsinki.FI)
- */
-static void bad_rw_intr(void)
-{
-	struct request *req = hd_req;
-
-	if (req != NULL) {
-		struct hd_i_struct *disk = req->rq_disk->private_data;
-		if (++req->errors >= MAX_ERRORS || (hd_error & BBD_ERR)) {
-			hd_end_request_cur(-EIO);
-			disk->special_op = disk->recalibrate = 1;
-		} else if (req->errors % RESET_FREQ == 0)
-			reset = 1;
-		else if ((hd_error & TRK0_ERR) || req->errors % RECAL_FREQ == 0)
-			disk->special_op = disk->recalibrate = 1;
-		/* Otherwise just retry */
-	}
-}
-
-static inline int wait_DRQ(void)
-{
-	int retries;
-	int stat;
-
-	for (retries = 0; retries < 100000; retries++) {
-		stat = inb_p(HD_STATUS);
-		if (stat & DRQ_STAT)
-			return 0;
-	}
-	dump_status("wait_DRQ", stat);
-	return -1;
-}
-
-static void read_intr(void)
-{
-	struct request *req;
-	int i, retries = 100000;
-
-	do {
-		i = (unsigned) inb_p(HD_STATUS);
-		if (i & BUSY_STAT)
-			continue;
-		if (!OK_STATUS(i))
-			break;
-		if (i & DRQ_STAT)
-			goto ok_to_read;
-	} while (--retries > 0);
-	dump_status("read_intr", i);
-	bad_rw_intr();
-	hd_request();
-	return;
-
-ok_to_read:
-	req = hd_req;
-	insw(HD_DATA, bio_data(req->bio), 256);
-#ifdef DEBUG
-	printk("%s: read: sector %ld, remaining = %u, buffer=%p\n",
-	       req->rq_disk->disk_name, blk_rq_pos(req) + 1,
-	       blk_rq_sectors(req) - 1, bio_data(req->bio)+512);
-#endif
-	if (hd_end_request(0, 512)) {
-		SET_HANDLER(&read_intr);
-		return;
-	}
-
-	(void) inb_p(HD_STATUS);
-#if (HD_DELAY > 0)
-	last_req = read_timer();
-#endif
-	hd_request();
-}
-
-static void write_intr(void)
-{
-	struct request *req = hd_req;
-	int i;
-	int retries = 100000;
-
-	do {
-		i = (unsigned) inb_p(HD_STATUS);
-		if (i & BUSY_STAT)
-			continue;
-		if (!OK_STATUS(i))
-			break;
-		if ((blk_rq_sectors(req) <= 1) || (i & DRQ_STAT))
-			goto ok_to_write;
-	} while (--retries > 0);
-	dump_status("write_intr", i);
-	bad_rw_intr();
-	hd_request();
-	return;
-
-ok_to_write:
-	if (hd_end_request(0, 512)) {
-		SET_HANDLER(&write_intr);
-		outsw(HD_DATA, bio_data(req->bio), 256);
-		return;
-	}
-
-#if (HD_DELAY > 0)
-	last_req = read_timer();
-#endif
-	hd_request();
-}
-
-static void recal_intr(void)
-{
-	check_status();
-#if (HD_DELAY > 0)
-	last_req = read_timer();
-#endif
-	hd_request();
-}
-
-/*
- * This is another of the error-routines I don't know what to do with. The
- * best idea seems to just set reset, and start all over again.
- */
-static void hd_times_out(unsigned long dummy)
-{
-	char *name;
-
-	do_hd = NULL;
-
-	if (!hd_req)
-		return;
-
-	spin_lock_irq(hd_queue->queue_lock);
-	reset = 1;
-	name = hd_req->rq_disk->disk_name;
-	printk("%s: timeout\n", name);
-	if (++hd_req->errors >= MAX_ERRORS) {
-#ifdef DEBUG
-		printk("%s: too many errors\n", name);
-#endif
-		hd_end_request_cur(-EIO);
-	}
-	hd_request();
-	spin_unlock_irq(hd_queue->queue_lock);
-}
-
-static int do_special_op(struct hd_i_struct *disk, struct request *req)
-{
-	if (disk->recalibrate) {
-		disk->recalibrate = 0;
-		hd_out(disk, disk->sect, 0, 0, 0, ATA_CMD_RESTORE, &recal_intr);
-		return reset;
-	}
-	if (disk->head > 16) {
-		printk("%s: cannot handle device with more than 16 heads - giving up\n", req->rq_disk->disk_name);
-		hd_end_request_cur(-EIO);
-	}
-	disk->special_op = 0;
-	return 1;
-}
-
-/*
- * The driver enables interrupts as much as possible.  In order to do this,
- * (a) the device-interrupt is disabled before entering hd_request(),
- * and (b) the timeout-interrupt is disabled before the sti().
- *
- * Interrupts are still masked (by default) whenever we are exchanging
- * data/cmds with a drive, because some drives seem to have very poor
- * tolerance for latency during I/O. The IDE driver has support to unmask
- * interrupts for non-broken hardware, so use that driver if required.
- */
-static void hd_request(void)
-{
-	unsigned int block, nsect, sec, track, head, cyl;
-	struct hd_i_struct *disk;
-	struct request *req;
-
-	if (do_hd)
-		return;
-repeat:
-	del_timer(&device_timer);
-
-	if (!hd_req) {
-		hd_req = blk_fetch_request(hd_queue);
-		if (!hd_req) {
-			do_hd = NULL;
-			return;
-		}
-	}
-	req = hd_req;
-
-	if (reset) {
-		reset_hd();
-		return;
-	}
-	disk = req->rq_disk->private_data;
-	block = blk_rq_pos(req);
-	nsect = blk_rq_sectors(req);
-	if (block >= get_capacity(req->rq_disk) ||
-	    ((block+nsect) > get_capacity(req->rq_disk))) {
-		printk("%s: bad access: block=%d, count=%d\n",
-			req->rq_disk->disk_name, block, nsect);
-		hd_end_request_cur(-EIO);
-		goto repeat;
-	}
-
-	if (disk->special_op) {
-		if (do_special_op(disk, req))
-			goto repeat;
-		return;
-	}
-	sec   = block % disk->sect + 1;
-	track = block / disk->sect;
-	head  = track % disk->head;
-	cyl   = track / disk->head;
-#ifdef DEBUG
-	printk("%s: %sing: CHS=%d/%d/%d, sectors=%d, buffer=%p\n",
-		req->rq_disk->disk_name,
-		req_data_dir(req) == READ ? "read" : "writ",
-		cyl, head, sec, nsect, bio_data(req->bio));
-#endif
-
-	switch (req_op(req)) {
-	case REQ_OP_READ:
-		hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_READ,
-			&read_intr);
-		if (reset)
-			goto repeat;
-		break;
-	case REQ_OP_WRITE:
-		hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_WRITE,
-			&write_intr);
-		if (reset)
-			goto repeat;
-		if (wait_DRQ()) {
-			bad_rw_intr();
-			goto repeat;
-		}
-		outsw(HD_DATA, bio_data(req->bio), 256);
-		break;
-	default:
-		printk("unknown hd-command\n");
-		hd_end_request_cur(-EIO);
-		break;
-	}
-}
-
-static void do_hd_request(struct request_queue *q)
-{
-	hd_request();
-}
-
-static int hd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
-{
-	struct hd_i_struct *disk = bdev->bd_disk->private_data;
-
-	geo->heads = disk->head;
-	geo->sectors = disk->sect;
-	geo->cylinders = disk->cyl;
-	return 0;
-}
-
-/*
- * Releasing a block device means we sync() it, so that it can safely
- * be forgotten about...
- */
-
-static irqreturn_t hd_interrupt(int irq, void *dev_id)
-{
-	void (*handler)(void) = do_hd;
-
-	spin_lock(hd_queue->queue_lock);
-
-	do_hd = NULL;
-	del_timer(&device_timer);
-	if (!handler)
-		handler = unexpected_hd_interrupt;
-	handler();
-
-	spin_unlock(hd_queue->queue_lock);
-
-	return IRQ_HANDLED;
-}
-
-static const struct block_device_operations hd_fops = {
-	.getgeo =	hd_getgeo,
-};
-
-static int __init hd_init(void)
-{
-	int drive;
-
-	if (register_blkdev(HD_MAJOR, "hd"))
-		return -1;
-
-	hd_queue = blk_init_queue(do_hd_request, &hd_lock);
-	if (!hd_queue) {
-		unregister_blkdev(HD_MAJOR, "hd");
-		return -ENOMEM;
-	}
-
-	blk_queue_max_hw_sectors(hd_queue, 255);
-	init_timer(&device_timer);
-	device_timer.function = hd_times_out;
-	blk_queue_logical_block_size(hd_queue, 512);
-
-	if (!NR_HD) {
-		/*
-		 * We don't know anything about the drive.  This means
-		 * that you *MUST* specify the drive parameters to the
-		 * kernel yourself.
-		 *
-		 * If we were on an i386, we used to read this info from
-		 * the BIOS or CMOS.  This doesn't work all that well,
-		 * since this assumes that this is a primary or secondary
-		 * drive, and if we're using this legacy driver, it's
-		 * probably an auxiliary controller added to recover
-		 * legacy data off an ST-506 drive.  Either way, it's
-		 * definitely safest to have the user explicitly specify
-		 * the information.
-		 */
-		printk("hd: no drives specified - use hd=cyl,head,sectors"
-			" on kernel command line\n");
-		goto out;
-	}
-
-	for (drive = 0 ; drive < NR_HD ; drive++) {
-		struct gendisk *disk = alloc_disk(64);
-		struct hd_i_struct *p = &hd_info[drive];
-		if (!disk)
-			goto Enomem;
-		disk->major = HD_MAJOR;
-		disk->first_minor = drive << 6;
-		disk->fops = &hd_fops;
-		sprintf(disk->disk_name, "hd%c", 'a'+drive);
-		disk->private_data = p;
-		set_capacity(disk, p->head * p->sect * p->cyl);
-		disk->queue = hd_queue;
-		p->unit = drive;
-		hd_gendisk[drive] = disk;
-		printk("%s: %luMB, CHS=%d/%d/%d\n",
-			disk->disk_name, (unsigned long)get_capacity(disk)/2048,
-			p->cyl, p->head, p->sect);
-	}
-
-	if (request_irq(HD_IRQ, hd_interrupt, 0, "hd", NULL)) {
-		printk("hd: unable to get IRQ%d for the hard disk driver\n",
-			HD_IRQ);
-		goto out1;
-	}
-	if (!request_region(HD_DATA, 8, "hd")) {
-		printk(KERN_WARNING "hd: port 0x%x busy\n", HD_DATA);
-		goto out2;
-	}
-	if (!request_region(HD_CMD, 1, "hd(cmd)")) {
-		printk(KERN_WARNING "hd: port 0x%x busy\n", HD_CMD);
-		goto out3;
-	}
-
-	/* Let them fly */
-	for (drive = 0; drive < NR_HD; drive++)
-		add_disk(hd_gendisk[drive]);
-
-	return 0;
-
-out3:
-	release_region(HD_DATA, 8);
-out2:
-	free_irq(HD_IRQ, NULL);
-out1:
-	for (drive = 0; drive < NR_HD; drive++)
-		put_disk(hd_gendisk[drive]);
-	NR_HD = 0;
-out:
-	del_timer(&device_timer);
-	unregister_blkdev(HD_MAJOR, "hd");
-	blk_cleanup_queue(hd_queue);
-	return -1;
-Enomem:
-	while (drive--)
-		put_disk(hd_gendisk[drive]);
-	goto out;
-}
-
-static int __init parse_hd_setup(char *line)
-{
-	int ints[6];
-
-	(void) get_options(line, ARRAY_SIZE(ints), ints);
-	hd_setup(NULL, ints);
-
-	return 1;
-}
-__setup("hd=", parse_hd_setup);
-
-late_initcall(hd_init);

drivers/block/loop.c

@@ -445,32 +445,27 @@ static int lo_req_flush(struct loop_device *lo, struct request *rq)
 	return ret;
 }
 
-static inline void handle_partial_read(struct loop_cmd *cmd, long bytes)
+static void lo_complete_rq(struct request *rq)
 {
-	if (bytes < 0 || op_is_write(req_op(cmd->rq)))
-		return;
+	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
 
-	if (unlikely(bytes < blk_rq_bytes(cmd->rq))) {
+	if (unlikely(req_op(cmd->rq) == REQ_OP_READ && cmd->use_aio &&
+		     cmd->ret >= 0 && cmd->ret < blk_rq_bytes(cmd->rq))) {
 		struct bio *bio = cmd->rq->bio;
 
-		bio_advance(bio, bytes);
+		bio_advance(bio, cmd->ret);
 		zero_fill_bio(bio);
 	}
+
+	blk_mq_end_request(rq, cmd->ret < 0 ? -EIO : 0);
 }
 
 static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
 {
 	struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb);
-	struct request *rq = cmd->rq;
-
-	handle_partial_read(cmd, ret);
 
-	if (ret > 0)
-		ret = 0;
-	else if (ret < 0)
-		ret = -EIO;
-
-	blk_mq_complete_request(rq, ret);
+	cmd->ret = ret;
+	blk_mq_complete_request(cmd->rq);
 }
 
 static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
@@ -528,6 +523,7 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 	case REQ_OP_FLUSH:
 		return lo_req_flush(lo, rq);
 	case REQ_OP_DISCARD:
+	case REQ_OP_WRITE_ZEROES:
 		return lo_discard(lo, rq, pos);
 	case REQ_OP_WRITE:
 		if (lo->transfer)
@@ -826,7 +822,7 @@ static void loop_config_discard(struct loop_device *lo)
 		q->limits.discard_granularity = 0;
 		q->limits.discard_alignment = 0;
 		blk_queue_max_discard_sectors(q, 0);
-		q->limits.discard_zeroes_data = 0;
+		blk_queue_max_write_zeroes_sectors(q, 0);
 		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
 		return;
 	}
@@ -834,7 +830,7 @@ static void loop_config_discard(struct loop_device *lo)
 	q->limits.discard_granularity = inode->i_sb->s_blocksize;
 	q->limits.discard_alignment = 0;
 	blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
-	q->limits.discard_zeroes_data = 1;
+	blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 }
 
@@ -1660,6 +1656,7 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	switch (req_op(cmd->rq)) {
 	case REQ_OP_FLUSH:
 	case REQ_OP_DISCARD:
+	case REQ_OP_WRITE_ZEROES:
 		cmd->use_aio = false;
 		break;
 	default:
@@ -1686,8 +1683,10 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
 	ret = do_req_filebacked(lo, cmd->rq);
  failed:
 	/* complete non-aio request */
-	if (!cmd->use_aio || ret)
-		blk_mq_complete_request(cmd->rq, ret ? -EIO : 0);
+	if (!cmd->use_aio || ret) {
+		cmd->ret = ret ? -EIO : 0;
+		blk_mq_complete_request(cmd->rq);
+	}
 }
 
 static void loop_queue_work(struct kthread_work *work)
@@ -1710,9 +1709,10 @@ static int loop_init_request(void *data, struct request *rq,
 	return 0;
 }
 
-static struct blk_mq_ops loop_mq_ops = {
+static const struct blk_mq_ops loop_mq_ops = {
 	.queue_rq       = loop_queue_rq,
 	.init_request	= loop_init_request,
+	.complete	= lo_complete_rq,
 };
 
 static int loop_add(struct loop_device **l, int i)

drivers/block/loop.h

@@ -70,6 +70,7 @@ struct loop_cmd {
 	struct request *rq;
 	struct list_head list;
 	bool use_aio;           /* use AIO interface to handle I/O */
+	long ret;
 	struct kiocb iocb;
 };
 

drivers/block/mg_disk.c

@@ -1,1112 +0,0 @@
-/*
- *  drivers/block/mg_disk.c
- *
- *  Support for the mGine m[g]flash IO mode.
- *  Based on legacy hd.c
- *
- * (c) 2008 mGine Co.,LTD
- * (c) 2008 unsik Kim <donari75@gmail.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2 as
- *  published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/blkdev.h>
-#include <linux/hdreg.h>
-#include <linux/ata.h>
-#include <linux/interrupt.h>
-#include <linux/delay.h>
-#include <linux/platform_device.h>
-#include <linux/gpio.h>
-#include <linux/mg_disk.h>
-#include <linux/slab.h>
-
-#define MG_RES_SEC (CONFIG_MG_DISK_RES << 1)
-
-/* name for block device */
-#define MG_DISK_NAME "mgd"
-
-#define MG_DISK_MAJ 0
-#define MG_DISK_MAX_PART 16
-#define MG_SECTOR_SIZE 512
-#define MG_MAX_SECTS 256
-
-/* Register offsets */
-#define MG_BUFF_OFFSET			0x8000
-#define MG_REG_OFFSET			0xC000
-#define MG_REG_FEATURE			(MG_REG_OFFSET + 2)	/* write case */
-#define MG_REG_ERROR			(MG_REG_OFFSET + 2)	/* read case */
-#define MG_REG_SECT_CNT			(MG_REG_OFFSET + 4)
-#define MG_REG_SECT_NUM			(MG_REG_OFFSET + 6)
-#define MG_REG_CYL_LOW			(MG_REG_OFFSET + 8)
-#define MG_REG_CYL_HIGH			(MG_REG_OFFSET + 0xA)
-#define MG_REG_DRV_HEAD			(MG_REG_OFFSET + 0xC)
-#define MG_REG_COMMAND			(MG_REG_OFFSET + 0xE)	/* write case */
-#define MG_REG_STATUS			(MG_REG_OFFSET + 0xE)	/* read  case */
-#define MG_REG_DRV_CTRL			(MG_REG_OFFSET + 0x10)
-#define MG_REG_BURST_CTRL		(MG_REG_OFFSET + 0x12)
-
-/* handy status */
-#define MG_STAT_READY	(ATA_DRDY | ATA_DSC)
-#define MG_READY_OK(s)	(((s) & (MG_STAT_READY | (ATA_BUSY | ATA_DF | \
-				 ATA_ERR))) == MG_STAT_READY)
-
-/* error code for others */
-#define MG_ERR_NONE		0
-#define MG_ERR_TIMEOUT		0x100
-#define MG_ERR_INIT_STAT	0x101
-#define MG_ERR_TRANSLATION	0x102
-#define MG_ERR_CTRL_RST		0x103
-#define MG_ERR_INV_STAT		0x104
-#define MG_ERR_RSTOUT		0x105
-
-#define MG_MAX_ERRORS	6	/* Max read/write errors */
-
-/* command */
-#define MG_CMD_RD 0x20
-#define MG_CMD_WR 0x30
-#define MG_CMD_SLEEP 0x99
-#define MG_CMD_WAKEUP 0xC3
-#define MG_CMD_ID 0xEC
-#define MG_CMD_WR_CONF 0x3C
-#define MG_CMD_RD_CONF 0x40
-
-/* operation mode */
-#define MG_OP_CASCADE (1 << 0)
-#define MG_OP_CASCADE_SYNC_RD (1 << 1)
-#define MG_OP_CASCADE_SYNC_WR (1 << 2)
-#define MG_OP_INTERLEAVE (1 << 3)
-
-/* synchronous */
-#define MG_BURST_LAT_4 (3 << 4)
-#define MG_BURST_LAT_5 (4 << 4)
-#define MG_BURST_LAT_6 (5 << 4)
-#define MG_BURST_LAT_7 (6 << 4)
-#define MG_BURST_LAT_8 (7 << 4)
-#define MG_BURST_LEN_4 (1 << 1)
-#define MG_BURST_LEN_8 (2 << 1)
-#define MG_BURST_LEN_16 (3 << 1)
-#define MG_BURST_LEN_32 (4 << 1)
-#define MG_BURST_LEN_CONT (0 << 1)
-
-/* timeout value (unit: ms) */
-#define MG_TMAX_CONF_TO_CMD	1
-#define MG_TMAX_WAIT_RD_DRQ	10
-#define MG_TMAX_WAIT_WR_DRQ	500
-#define MG_TMAX_RST_TO_BUSY	10
-#define MG_TMAX_HDRST_TO_RDY	500
-#define MG_TMAX_SWRST_TO_RDY	500
-#define MG_TMAX_RSTOUT		3000
-
-#define MG_DEV_MASK (MG_BOOT_DEV | MG_STORAGE_DEV | MG_STORAGE_DEV_SKIP_RST)
-
-/* main structure for mflash driver */
-struct mg_host {
-	struct device *dev;
-
-	struct request_queue *breq;
-	struct request *req;
-	spinlock_t lock;
-	struct gendisk *gd;
-
-	struct timer_list timer;
-	void (*mg_do_intr) (struct mg_host *);
-
-	u16 id[ATA_ID_WORDS];
-
-	u16 cyls;
-	u16 heads;
-	u16 sectors;
-	u32 n_sectors;
-	u32 nres_sectors;
-
-	void __iomem *dev_base;
-	unsigned int irq;
-	unsigned int rst;
-	unsigned int rstout;
-
-	u32 major;
-	u32 error;
-};
-
-/*
- * Debugging macro and defines
- */
-#undef DO_MG_DEBUG
-#ifdef DO_MG_DEBUG
-#  define MG_DBG(fmt, args...) \
-	printk(KERN_DEBUG "%s:%d "fmt, __func__, __LINE__, ##args)
-#else /* CONFIG_MG_DEBUG */
-#  define MG_DBG(fmt, args...) do { } while (0)
-#endif /* CONFIG_MG_DEBUG */
-
-static void mg_request(struct request_queue *);
-
-static bool mg_end_request(struct mg_host *host, int err, unsigned int nr_bytes)
-{
-	if (__blk_end_request(host->req, err, nr_bytes))
-		return true;
-
-	host->req = NULL;
-	return false;
-}
-
-static bool mg_end_request_cur(struct mg_host *host, int err)
-{
-	return mg_end_request(host, err, blk_rq_cur_bytes(host->req));
-}
-
-static void mg_dump_status(const char *msg, unsigned int stat,
-		struct mg_host *host)
-{
-	char *name = MG_DISK_NAME;
-
-	if (host->req)
-		name = host->req->rq_disk->disk_name;
-
-	printk(KERN_ERR "%s: %s: status=0x%02x { ", name, msg, stat & 0xff);
-	if (stat & ATA_BUSY)
-		printk("Busy ");
-	if (stat & ATA_DRDY)
-		printk("DriveReady ");
-	if (stat & ATA_DF)
-		printk("WriteFault ");
-	if (stat & ATA_DSC)
-		printk("SeekComplete ");
-	if (stat & ATA_DRQ)
-		printk("DataRequest ");
-	if (stat & ATA_CORR)
-		printk("CorrectedError ");
-	if (stat & ATA_ERR)
-		printk("Error ");
-	printk("}\n");
-	if ((stat & ATA_ERR) == 0) {
-		host->error = 0;
-	} else {
-		host->error = inb((unsigned long)host->dev_base + MG_REG_ERROR);
-		printk(KERN_ERR "%s: %s: error=0x%02x { ", name, msg,
-				host->error & 0xff);
-		if (host->error & ATA_BBK)
-			printk("BadSector ");
-		if (host->error & ATA_UNC)
-			printk("UncorrectableError ");
-		if (host->error & ATA_IDNF)
-			printk("SectorIdNotFound ");
-		if (host->error & ATA_ABORTED)
-			printk("DriveStatusError ");
-		if (host->error & ATA_AMNF)
-			printk("AddrMarkNotFound ");
-		printk("}");
-		if (host->error & (ATA_BBK | ATA_UNC | ATA_IDNF | ATA_AMNF)) {
-			if (host->req)
-				printk(", sector=%u",
-				       (unsigned int)blk_rq_pos(host->req));
-		}
-		printk("\n");
-	}
-}
-
-static unsigned int mg_wait(struct mg_host *host, u32 expect, u32 msec)
-{
-	u8 status;
-	unsigned long expire, cur_jiffies;
-	struct mg_drv_data *prv_data = host->dev->platform_data;
-
-	host->error = MG_ERR_NONE;
-	expire = jiffies + msecs_to_jiffies(msec);
-
-	/* These 2 times dummy status read prevents reading invalid
-	 * status. A very little time (3 times of mflash operating clk)
-	 * is required for busy bit is set. Use dummy read instead of
-	 * busy wait, because mflash's PLL is machine dependent.
-	 */
-	if (prv_data->use_polling) {
-		status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-		status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-	}
-
-	status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-
-	do {
-		cur_jiffies = jiffies;
-		if (status & ATA_BUSY) {
-			if (expect == ATA_BUSY)
-				break;
-		} else {
-			/* Check the error condition! */
-			if (status & ATA_ERR) {
-				mg_dump_status("mg_wait", status, host);
-				break;
-			}
-
-			if (expect == MG_STAT_READY)
-				if (MG_READY_OK(status))
-					break;
-
-			if (expect == ATA_DRQ)
-				if (status & ATA_DRQ)
-					break;
-		}
-		if (!msec) {
-			mg_dump_status("not ready", status, host);
-			return MG_ERR_INV_STAT;
-		}
-
-		status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-	} while (time_before(cur_jiffies, expire));
-
-	if (time_after_eq(cur_jiffies, expire) && msec)
-		host->error = MG_ERR_TIMEOUT;
-
-	return host->error;
-}
-
-static unsigned int mg_wait_rstout(u32 rstout, u32 msec)
-{
-	unsigned long expire;
-
-	expire = jiffies + msecs_to_jiffies(msec);
-	while (time_before(jiffies, expire)) {
-		if (gpio_get_value(rstout) == 1)
-			return MG_ERR_NONE;
-		msleep(10);
-	}
-
-	return MG_ERR_RSTOUT;
-}
-
-static void mg_unexpected_intr(struct mg_host *host)
-{
-	u32 status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-
-	mg_dump_status("mg_unexpected_intr", status, host);
-}
-
-static irqreturn_t mg_irq(int irq, void *dev_id)
-{
-	struct mg_host *host = dev_id;
-	void (*handler)(struct mg_host *) = host->mg_do_intr;
-
-	spin_lock(&host->lock);
-
-	host->mg_do_intr = NULL;
-	del_timer(&host->timer);
-	if (!handler)
-		handler = mg_unexpected_intr;
-	handler(host);
-
-	spin_unlock(&host->lock);
-
-	return IRQ_HANDLED;
-}
-
-/* local copy of ata_id_string() */
-static void mg_id_string(const u16 *id, unsigned char *s,
-			 unsigned int ofs, unsigned int len)
-{
-	unsigned int c;
-
-	BUG_ON(len & 1);
-
-	while (len > 0) {
-		c = id[ofs] >> 8;
-		*s = c;
-		s++;
-
-		c = id[ofs] & 0xff;
-		*s = c;
-		s++;
-
-		ofs++;
-		len -= 2;
-	}
-}
-
-/* local copy of ata_id_c_string() */
-static void mg_id_c_string(const u16 *id, unsigned char *s,
-			   unsigned int ofs, unsigned int len)
-{
-	unsigned char *p;
-
-	mg_id_string(id, s, ofs, len - 1);
-
-	p = s + strnlen(s, len - 1);
-	while (p > s && p[-1] == ' ')
-		p--;
-	*p = '\0';
-}
-
-static int mg_get_disk_id(struct mg_host *host)
-{
-	u32 i;
-	s32 err;
-	const u16 *id = host->id;
-	struct mg_drv_data *prv_data = host->dev->platform_data;
-	char fwrev[ATA_ID_FW_REV_LEN + 1];
-	char model[ATA_ID_PROD_LEN + 1];
-	char serial[ATA_ID_SERNO_LEN + 1];
-
-	if (!prv_data->use_polling)
-		outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-
-	outb(MG_CMD_ID, (unsigned long)host->dev_base + MG_REG_COMMAND);
-	err = mg_wait(host, ATA_DRQ, MG_TMAX_WAIT_RD_DRQ);
-	if (err)
-		return err;
-
-	for (i = 0; i < (MG_SECTOR_SIZE >> 1); i++)
-		host->id[i] = le16_to_cpu(inw((unsigned long)host->dev_base +
-					MG_BUFF_OFFSET + i * 2));
-
-	outb(MG_CMD_RD_CONF, (unsigned long)host->dev_base + MG_REG_COMMAND);
-	err = mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD);
-	if (err)
-		return err;
-
-	if ((id[ATA_ID_FIELD_VALID] & 1) == 0)
-		return MG_ERR_TRANSLATION;
-
-	host->n_sectors = ata_id_u32(id, ATA_ID_LBA_CAPACITY);
-	host->cyls = id[ATA_ID_CYLS];
-	host->heads = id[ATA_ID_HEADS];
-	host->sectors = id[ATA_ID_SECTORS];
-
-	if (MG_RES_SEC && host->heads && host->sectors) {
-		/* modify cyls, n_sectors */
-		host->cyls = (host->n_sectors - MG_RES_SEC) /
-			host->heads / host->sectors;
-		host->nres_sectors = host->n_sectors - host->cyls *
-			host->heads * host->sectors;
-		host->n_sectors -= host->nres_sectors;
-	}
-
-	mg_id_c_string(id, fwrev, ATA_ID_FW_REV, sizeof(fwrev));
-	mg_id_c_string(id, model, ATA_ID_PROD, sizeof(model));
-	mg_id_c_string(id, serial, ATA_ID_SERNO, sizeof(serial));
-	printk(KERN_INFO "mg_disk: model: %s\n", model);
-	printk(KERN_INFO "mg_disk: firm: %.8s\n", fwrev);
-	printk(KERN_INFO "mg_disk: serial: %s\n", serial);
-	printk(KERN_INFO "mg_disk: %d + reserved %d sectors\n",
-			host->n_sectors, host->nres_sectors);
-
-	if (!prv_data->use_polling)
-		outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-
-	return err;
-}
-
-
-static int mg_disk_init(struct mg_host *host)
-{
-	struct mg_drv_data *prv_data = host->dev->platform_data;
-	s32 err;
-	u8 init_status;
-
-	/* hdd rst low */
-	gpio_set_value(host->rst, 0);
-	err = mg_wait(host, ATA_BUSY, MG_TMAX_RST_TO_BUSY);
-	if (err)
-		return err;
-
-	/* hdd rst high */
-	gpio_set_value(host->rst, 1);
-	err = mg_wait(host, MG_STAT_READY, MG_TMAX_HDRST_TO_RDY);
-	if (err)
-		return err;
-
-	/* soft reset on */
-	outb(ATA_SRST | (prv_data->use_polling ? ATA_NIEN : 0),
-			(unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-	err = mg_wait(host, ATA_BUSY, MG_TMAX_RST_TO_BUSY);
-	if (err)
-		return err;
-
-	/* soft reset off */
-	outb(prv_data->use_polling ? ATA_NIEN : 0,
-			(unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-	err = mg_wait(host, MG_STAT_READY, MG_TMAX_SWRST_TO_RDY);
-	if (err)
-		return err;
-
-	init_status = inb((unsigned long)host->dev_base + MG_REG_STATUS) & 0xf;
-
-	if (init_status == 0xf)
-		return MG_ERR_INIT_STAT;
-
-	return err;
-}
-
-static void mg_bad_rw_intr(struct mg_host *host)
-{
-	if (host->req)
-		if (++host->req->errors >= MG_MAX_ERRORS ||
-		    host->error == MG_ERR_TIMEOUT)
-			mg_end_request_cur(host, -EIO);
-}
-
-static unsigned int mg_out(struct mg_host *host,
-		unsigned int sect_num,
-		unsigned int sect_cnt,
-		unsigned int cmd,
-		void (*intr_addr)(struct mg_host *))
-{
-	struct mg_drv_data *prv_data = host->dev->platform_data;
-
-	if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD))
-		return host->error;
-
-	if (!prv_data->use_polling) {
-		host->mg_do_intr = intr_addr;
-		mod_timer(&host->timer, jiffies + 3 * HZ);
-	}
-	if (MG_RES_SEC)
-		sect_num += MG_RES_SEC;
-	outb((u8)sect_cnt, (unsigned long)host->dev_base + MG_REG_SECT_CNT);
-	outb((u8)sect_num, (unsigned long)host->dev_base + MG_REG_SECT_NUM);
-	outb((u8)(sect_num >> 8), (unsigned long)host->dev_base +
-			MG_REG_CYL_LOW);
-	outb((u8)(sect_num >> 16), (unsigned long)host->dev_base +
-			MG_REG_CYL_HIGH);
-	outb((u8)((sect_num >> 24) | ATA_LBA | ATA_DEVICE_OBS),
-			(unsigned long)host->dev_base + MG_REG_DRV_HEAD);
-	outb(cmd, (unsigned long)host->dev_base + MG_REG_COMMAND);
-	return MG_ERR_NONE;
-}
-
-static void mg_read_one(struct mg_host *host, struct request *req)
-{
-	u16 *buff = (u16 *)bio_data(req->bio);
-	u32 i;
-
-	for (i = 0; i < MG_SECTOR_SIZE >> 1; i++)
-		*buff++ = inw((unsigned long)host->dev_base + MG_BUFF_OFFSET +
-			      (i << 1));
-}
-
-static void mg_read(struct request *req)
-{
-	struct mg_host *host = req->rq_disk->private_data;
-
-	if (mg_out(host, blk_rq_pos(req), blk_rq_sectors(req),
-		   MG_CMD_RD, NULL) != MG_ERR_NONE)
-		mg_bad_rw_intr(host);
-
-	MG_DBG("requested %d sects (from %ld), buffer=0x%p\n",
-	       blk_rq_sectors(req), blk_rq_pos(req), bio_data(req->bio));
-
-	do {
-		if (mg_wait(host, ATA_DRQ,
-			    MG_TMAX_WAIT_RD_DRQ) != MG_ERR_NONE) {
-			mg_bad_rw_intr(host);
-			return;
-		}
-
-		mg_read_one(host, req);
-
-		outb(MG_CMD_RD_CONF, (unsigned long)host->dev_base +
-				MG_REG_COMMAND);
-	} while (mg_end_request(host, 0, MG_SECTOR_SIZE));
-}
-
-static void mg_write_one(struct mg_host *host, struct request *req)
-{
-	u16 *buff = (u16 *)bio_data(req->bio);
-	u32 i;
-
-	for (i = 0; i < MG_SECTOR_SIZE >> 1; i++)
-		outw(*buff++, (unsigned long)host->dev_base + MG_BUFF_OFFSET +
-		     (i << 1));
-}
-
-static void mg_write(struct request *req)
-{
-	struct mg_host *host = req->rq_disk->private_data;
-	unsigned int rem = blk_rq_sectors(req);
-
-	if (mg_out(host, blk_rq_pos(req), rem,
-		   MG_CMD_WR, NULL) != MG_ERR_NONE) {
-		mg_bad_rw_intr(host);
-		return;
-	}
-
-	MG_DBG("requested %d sects (from %ld), buffer=0x%p\n",
-	       rem, blk_rq_pos(req), bio_data(req->bio));
-
-	if (mg_wait(host, ATA_DRQ,
-		    MG_TMAX_WAIT_WR_DRQ) != MG_ERR_NONE) {
-		mg_bad_rw_intr(host);
-		return;
-	}
-
-	do {
-		mg_write_one(host, req);
-
-		outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base +
-				MG_REG_COMMAND);
-
-		rem--;
-		if (rem > 1 && mg_wait(host, ATA_DRQ,
-					MG_TMAX_WAIT_WR_DRQ) != MG_ERR_NONE) {
-			mg_bad_rw_intr(host);
-			return;
-		} else if (mg_wait(host, MG_STAT_READY,
-					MG_TMAX_WAIT_WR_DRQ) != MG_ERR_NONE) {
-			mg_bad_rw_intr(host);
-			return;
-		}
-	} while (mg_end_request(host, 0, MG_SECTOR_SIZE));
-}
-
-static void mg_read_intr(struct mg_host *host)
-{
-	struct request *req = host->req;
-	u32 i;
-
-	/* check status */
-	do {
-		i = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-		if (i & ATA_BUSY)
-			break;
-		if (!MG_READY_OK(i))
-			break;
-		if (i & ATA_DRQ)
-			goto ok_to_read;
-	} while (0);
-	mg_dump_status("mg_read_intr", i, host);
-	mg_bad_rw_intr(host);
-	mg_request(host->breq);
-	return;
-
-ok_to_read:
-	mg_read_one(host, req);
-
-	MG_DBG("sector %ld, remaining=%ld, buffer=0x%p\n",
-	       blk_rq_pos(req), blk_rq_sectors(req) - 1, bio_data(req->bio));
-
-	/* send read confirm */
-	outb(MG_CMD_RD_CONF, (unsigned long)host->dev_base + MG_REG_COMMAND);
-
-	if (mg_end_request(host, 0, MG_SECTOR_SIZE)) {
-		/* set handler if read remains */
-		host->mg_do_intr = mg_read_intr;
-		mod_timer(&host->timer, jiffies + 3 * HZ);
-	} else /* goto next request */
-		mg_request(host->breq);
-}
-
-static void mg_write_intr(struct mg_host *host)
-{
-	struct request *req = host->req;
-	u32 i;
-	bool rem;
-
-	/* check status */
-	do {
-		i = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-		if (i & ATA_BUSY)
-			break;
-		if (!MG_READY_OK(i))
-			break;
-		if ((blk_rq_sectors(req) <= 1) || (i & ATA_DRQ))
-			goto ok_to_write;
-	} while (0);
-	mg_dump_status("mg_write_intr", i, host);
-	mg_bad_rw_intr(host);
-	mg_request(host->breq);
-	return;
-
-ok_to_write:
-	if ((rem = mg_end_request(host, 0, MG_SECTOR_SIZE))) {
-		/* write 1 sector and set handler if remains */
-		mg_write_one(host, req);
-		MG_DBG("sector %ld, remaining=%ld, buffer=0x%p\n",
-		       blk_rq_pos(req), blk_rq_sectors(req), bio_data(req->bio));
-		host->mg_do_intr = mg_write_intr;
-		mod_timer(&host->timer, jiffies + 3 * HZ);
-	}
-
-	/* send write confirm */
-	outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base + MG_REG_COMMAND);
-
-	if (!rem)
-		mg_request(host->breq);
-}
-
-static void mg_times_out(unsigned long data)
-{
-	struct mg_host *host = (struct mg_host *)data;
-	char *name;
-
-	spin_lock_irq(&host->lock);
-
-	if (!host->req)
-		goto out_unlock;
-
-	host->mg_do_intr = NULL;
-
-	name = host->req->rq_disk->disk_name;
-	printk(KERN_DEBUG "%s: timeout\n", name);
-
-	host->error = MG_ERR_TIMEOUT;
-	mg_bad_rw_intr(host);
-
-out_unlock:
-	mg_request(host->breq);
-	spin_unlock_irq(&host->lock);
-}
-
-static void mg_request_poll(struct request_queue *q)
-{
-	struct mg_host *host = q->queuedata;
-
-	while (1) {
-		if (!host->req) {
-			host->req = blk_fetch_request(q);
-			if (!host->req)
-				break;
-		}
-
-		switch (req_op(host->req)) {
-		case REQ_OP_READ:
-			mg_read(host->req);
-			break;
-		case REQ_OP_WRITE:
-			mg_write(host->req);
-			break;
-		default:
-			mg_end_request_cur(host, -EIO);
-			break;
-		}
-	}
-}
-
-static unsigned int mg_issue_req(struct request *req,
-		struct mg_host *host,
-		unsigned int sect_num,
-		unsigned int sect_cnt)
-{
-	switch (req_op(host->req)) {
-	case REQ_OP_READ:
-		if (mg_out(host, sect_num, sect_cnt, MG_CMD_RD, &mg_read_intr)
-				!= MG_ERR_NONE) {
-			mg_bad_rw_intr(host);
-			return host->error;
-		}
-		break;
-	case REQ_OP_WRITE:
-		/* TODO : handler */
-		outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-		if (mg_out(host, sect_num, sect_cnt, MG_CMD_WR, &mg_write_intr)
-				!= MG_ERR_NONE) {
-			mg_bad_rw_intr(host);
-			return host->error;
-		}
-		del_timer(&host->timer);
-		mg_wait(host, ATA_DRQ, MG_TMAX_WAIT_WR_DRQ);
-		outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-		if (host->error) {
-			mg_bad_rw_intr(host);
-			return host->error;
-		}
-		mg_write_one(host, req);
-		mod_timer(&host->timer, jiffies + 3 * HZ);
-		outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base +
-				MG_REG_COMMAND);
-		break;
-	default:
-		mg_end_request_cur(host, -EIO);
-		break;
-	}
-	return MG_ERR_NONE;
-}
-
-/* This function also called from IRQ context */
-static void mg_request(struct request_queue *q)
-{
-	struct mg_host *host = q->queuedata;
-	struct request *req;
-	u32 sect_num, sect_cnt;
-
-	while (1) {
-		if (!host->req) {
-			host->req = blk_fetch_request(q);
-			if (!host->req)
-				break;
-		}
-		req = host->req;
-
-		/* check unwanted request call */
-		if (host->mg_do_intr)
-			return;
-
-		del_timer(&host->timer);
-
-		sect_num = blk_rq_pos(req);
-		/* deal whole segments */
-		sect_cnt = blk_rq_sectors(req);
-
-		/* sanity check */
-		if (sect_num >= get_capacity(req->rq_disk) ||
-				((sect_num + sect_cnt) >
-				 get_capacity(req->rq_disk))) {
-			printk(KERN_WARNING
-					"%s: bad access: sector=%d, count=%d\n",
-					req->rq_disk->disk_name,
-					sect_num, sect_cnt);
-			mg_end_request_cur(host, -EIO);
-			continue;
-		}
-
-		if (!mg_issue_req(req, host, sect_num, sect_cnt))
-			return;
-	}
-}
-
-static int mg_getgeo(struct block_device *bdev, struct hd_geometry *geo)
-{
-	struct mg_host *host = bdev->bd_disk->private_data;
-
-	geo->cylinders = (unsigned short)host->cyls;
-	geo->heads = (unsigned char)host->heads;
-	geo->sectors = (unsigned char)host->sectors;
-	return 0;
-}
-
-static const struct block_device_operations mg_disk_ops = {
-	.getgeo = mg_getgeo
-};
-
-#ifdef CONFIG_PM_SLEEP
-static int mg_suspend(struct device *dev)
-{
-	struct mg_drv_data *prv_data = dev->platform_data;
-	struct mg_host *host = prv_data->host;
-
-	if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD))
-		return -EIO;
-
-	if (!prv_data->use_polling)
-		outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-
-	outb(MG_CMD_SLEEP, (unsigned long)host->dev_base + MG_REG_COMMAND);
-	/* wait until mflash deep sleep */
-	msleep(1);
-
-	if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD)) {
-		if (!prv_data->use_polling)
-			outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-		return -EIO;
-	}
-
-	return 0;
-}
-
-static int mg_resume(struct device *dev)
-{
-	struct mg_drv_data *prv_data = dev->platform_data;
-	struct mg_host *host = prv_data->host;
-
-	if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD))
-		return -EIO;
-
-	outb(MG_CMD_WAKEUP, (unsigned long)host->dev_base + MG_REG_COMMAND);
-	/* wait until mflash wakeup */
-	msleep(1);
-
-	if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD))
-		return -EIO;
-
-	if (!prv_data->use_polling)
-		outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-
-	return 0;
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(mg_pm, mg_suspend, mg_resume);
-
-static int mg_probe(struct platform_device *plat_dev)
-{
-	struct mg_host *host;
-	struct resource *rsc;
-	struct mg_drv_data *prv_data = plat_dev->dev.platform_data;
-	int err = 0;
-
-	if (!prv_data) {
-		printk(KERN_ERR	"%s:%d fail (no driver_data)\n",
-				__func__, __LINE__);
-		err = -EINVAL;
-		goto probe_err;
-	}
-
-	/* alloc mg_host */
-	host = kzalloc(sizeof(struct mg_host), GFP_KERNEL);
-	if (!host) {
-		printk(KERN_ERR "%s:%d fail (no memory for mg_host)\n",
-				__func__, __LINE__);
-		err = -ENOMEM;
-		goto probe_err;
-	}
-	host->major = MG_DISK_MAJ;
-
-	/* link each other */
-	prv_data->host = host;
-	host->dev = &plat_dev->dev;
-
-	/* io remap */
-	rsc = platform_get_resource(plat_dev, IORESOURCE_MEM, 0);
-	if (!rsc) {
-		printk(KERN_ERR "%s:%d platform_get_resource fail\n",
-				__func__, __LINE__);
-		err = -EINVAL;
-		goto probe_err_2;
-	}
-	host->dev_base = ioremap(rsc->start, resource_size(rsc));
-	if (!host->dev_base) {
-		printk(KERN_ERR "%s:%d ioremap fail\n",
-				__func__, __LINE__);
-		err = -EIO;
-		goto probe_err_2;
-	}
-	MG_DBG("dev_base = 0x%x\n", (u32)host->dev_base);
-
-	/* get reset pin */
-	rsc = platform_get_resource_byname(plat_dev, IORESOURCE_IO,
-			MG_RST_PIN);
-	if (!rsc) {
-		printk(KERN_ERR "%s:%d get reset pin fail\n",
-				__func__, __LINE__);
-		err = -EIO;
-		goto probe_err_3;
-	}
-	host->rst = rsc->start;
-
-	/* init rst pin */
-	err = gpio_request(host->rst, MG_RST_PIN);
-	if (err)
-		goto probe_err_3;
-	gpio_direction_output(host->rst, 1);
-
-	/* reset out pin */
-	if (!(prv_data->dev_attr & MG_DEV_MASK)) {
-		err = -EINVAL;
-		goto probe_err_3a;
-	}
-
-	if (prv_data->dev_attr != MG_BOOT_DEV) {
-		rsc = platform_get_resource_byname(plat_dev, IORESOURCE_IO,
-				MG_RSTOUT_PIN);
-		if (!rsc) {
-			printk(KERN_ERR "%s:%d get reset-out pin fail\n",
-					__func__, __LINE__);
-			err = -EIO;
-			goto probe_err_3a;
-		}
-		host->rstout = rsc->start;
-		err = gpio_request(host->rstout, MG_RSTOUT_PIN);
-		if (err)
-			goto probe_err_3a;
-		gpio_direction_input(host->rstout);
-	}
-
-	/* disk reset */
-	if (prv_data->dev_attr == MG_STORAGE_DEV) {
-		/* If POR seq. not yet finished, wait */
-		err = mg_wait_rstout(host->rstout, MG_TMAX_RSTOUT);
-		if (err)
-			goto probe_err_3b;
-		err = mg_disk_init(host);
-		if (err) {
-			printk(KERN_ERR "%s:%d fail (err code : %d)\n",
-					__func__, __LINE__, err);
-			err = -EIO;
-			goto probe_err_3b;
-		}
-	}
-
-	/* get irq resource */
-	if (!prv_data->use_polling) {
-		host->irq = platform_get_irq(plat_dev, 0);
-		if (host->irq == -ENXIO) {
-			err = host->irq;
-			goto probe_err_3b;
-		}
-		err = request_irq(host->irq, mg_irq,
-				IRQF_TRIGGER_RISING,
-				MG_DEV_NAME, host);
-		if (err) {
-			printk(KERN_ERR "%s:%d fail (request_irq err=%d)\n",
-					__func__, __LINE__, err);
-			goto probe_err_3b;
-		}
-
-	}
-
-	/* get disk id */
-	err = mg_get_disk_id(host);
-	if (err) {
-		printk(KERN_ERR "%s:%d fail (err code : %d)\n",
-				__func__, __LINE__, err);
-		err = -EIO;
-		goto probe_err_4;
-	}
-
-	err = register_blkdev(host->major, MG_DISK_NAME);
-	if (err < 0) {
-		printk(KERN_ERR "%s:%d register_blkdev fail (err code : %d)\n",
-				__func__, __LINE__, err);
-		goto probe_err_4;
-	}
-	if (!host->major)
-		host->major = err;
-
-	spin_lock_init(&host->lock);
-
-	if (prv_data->use_polling)
-		host->breq = blk_init_queue(mg_request_poll, &host->lock);
-	else
-		host->breq = blk_init_queue(mg_request, &host->lock);
-
-	if (!host->breq) {
-		err = -ENOMEM;
-		printk(KERN_ERR "%s:%d (blk_init_queue) fail\n",
-				__func__, __LINE__);
-		goto probe_err_5;
-	}
-	host->breq->queuedata = host;
-
-	/* mflash is random device, thanx for the noop */
-	err = elevator_change(host->breq, "noop");
-	if (err) {
-		printk(KERN_ERR "%s:%d (elevator_init) fail\n",
-				__func__, __LINE__);
-		goto probe_err_6;
-	}
-	blk_queue_max_hw_sectors(host->breq, MG_MAX_SECTS);
-	blk_queue_logical_block_size(host->breq, MG_SECTOR_SIZE);
-
-	init_timer(&host->timer);
-	host->timer.function = mg_times_out;
-	host->timer.data = (unsigned long)host;
-
-	host->gd = alloc_disk(MG_DISK_MAX_PART);
-	if (!host->gd) {
-		printk(KERN_ERR "%s:%d (alloc_disk) fail\n",
-				__func__, __LINE__);
-		err = -ENOMEM;
-		goto probe_err_7;
-	}
-	host->gd->major = host->major;
-	host->gd->first_minor = 0;
-	host->gd->fops = &mg_disk_ops;
-	host->gd->queue = host->breq;
-	host->gd->private_data = host;
-	sprintf(host->gd->disk_name, MG_DISK_NAME"a");
-
-	set_capacity(host->gd, host->n_sectors);
-
-	add_disk(host->gd);
-
-	return err;
-
-probe_err_7:
-	del_timer_sync(&host->timer);
-probe_err_6:
-	blk_cleanup_queue(host->breq);
-probe_err_5:
-	unregister_blkdev(host->major, MG_DISK_NAME);
-probe_err_4:
-	if (!prv_data->use_polling)
-		free_irq(host->irq, host);
-probe_err_3b:
-	gpio_free(host->rstout);
-probe_err_3a:
-	gpio_free(host->rst);
-probe_err_3:
-	iounmap(host->dev_base);
-probe_err_2:
-	kfree(host);
-probe_err:
-	return err;
-}
-
-static int mg_remove(struct platform_device *plat_dev)
-{
-	struct mg_drv_data *prv_data = plat_dev->dev.platform_data;
-	struct mg_host *host = prv_data->host;
-	int err = 0;
-
-	/* delete timer */
-	del_timer_sync(&host->timer);
-
-	/* remove disk */
-	if (host->gd) {
-		del_gendisk(host->gd);
-		put_disk(host->gd);
-	}
-	/* remove queue */
-	if (host->breq)
-		blk_cleanup_queue(host->breq);
-
-	/* unregister blk device */
-	unregister_blkdev(host->major, MG_DISK_NAME);
-
-	/* free irq */
-	if (!prv_data->use_polling)
-		free_irq(host->irq, host);
-
-	/* free reset-out pin */
-	if (prv_data->dev_attr != MG_BOOT_DEV)
-		gpio_free(host->rstout);
-
-	/* free rst pin */
-	if (host->rst)
-		gpio_free(host->rst);
-
-	/* unmap io */
-	if (host->dev_base)
-		iounmap(host->dev_base);
-
-	/* free mg_host */
-	kfree(host);
-
-	return err;
-}
-
-static struct platform_driver mg_disk_driver = {
-	.probe = mg_probe,
-	.remove = mg_remove,
-	.driver = {
-		.name = MG_DEV_NAME,
-		.pm = &mg_pm,
-	}
-};
-
-/****************************************************************************
- *
- * Module stuff
- *
- ****************************************************************************/
-
-static int __init mg_init(void)
-{
-	printk(KERN_INFO "mGine mflash driver, (c) 2008 mGine Co.\n");
-	return platform_driver_register(&mg_disk_driver);
-}
-
-static void __exit mg_exit(void)
-{
-	printk(KERN_INFO "mflash driver : bye bye\n");
-	platform_driver_unregister(&mg_disk_driver);
-}
-
-module_init(mg_init);
-module_exit(mg_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("unsik Kim <donari75@gmail.com>");
-MODULE_DESCRIPTION("mGine m[g]flash device driver");

drivers/block/mtip32xx/mtip32xx.c

@@ -169,6 +169,25 @@ static bool mtip_check_surprise_removal(struct pci_dev *pdev)
 	return false; /* device present */
 }
 
+/* we have to use runtime tag to setup command header */
+static void mtip_init_cmd_header(struct request *rq)
+{
+	struct driver_data *dd = rq->q->queuedata;
+	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
+	u32 host_cap_64 = readl(dd->mmio + HOST_CAP) & HOST_CAP_64;
+
+	/* Point the command headers at the command tables. */
+	cmd->command_header = dd->port->command_list +
+				(sizeof(struct mtip_cmd_hdr) * rq->tag);
+	cmd->command_header_dma = dd->port->command_list_dma +
+				(sizeof(struct mtip_cmd_hdr) * rq->tag);
+
+	if (host_cap_64)
+		cmd->command_header->ctbau = __force_bit2int cpu_to_le32((cmd->command_dma >> 16) >> 16);
+
+	cmd->command_header->ctba = __force_bit2int cpu_to_le32(cmd->command_dma & 0xFFFFFFFF);
+}
+
 static struct mtip_cmd *mtip_get_int_command(struct driver_data *dd)
 {
 	struct request *rq;
@@ -180,6 +199,9 @@ static struct mtip_cmd *mtip_get_int_command(struct driver_data *dd)
 	if (IS_ERR(rq))
 		return NULL;
 
+	/* Internal cmd isn't submitted via .queue_rq */
+	mtip_init_cmd_header(rq);
+
 	return blk_mq_rq_to_pdu(rq);
 }
 
@@ -241,7 +263,8 @@ static void mtip_async_complete(struct mtip_port *port,
 
 	rq = mtip_rq_from_tag(dd, tag);
 
-	blk_mq_complete_request(rq, status);
+	cmd->status = status;
+	blk_mq_complete_request(rq);
 }
 
 /*
@@ -2910,18 +2933,19 @@ static void mtip_softirq_done_fn(struct request *rq)
 	if (unlikely(cmd->unaligned))
 		up(&dd->port->cmd_slot_unal);
 
-	blk_mq_end_request(rq, rq->errors);
+	blk_mq_end_request(rq, cmd->status);
 }
 
 static void mtip_abort_cmd(struct request *req, void *data,
 							bool reserved)
 {
+	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req);
 	struct driver_data *dd = data;
 
 	dbg_printk(MTIP_DRV_NAME " Aborting request, tag = %d\n", req->tag);
 
 	clear_bit(req->tag, dd->port->cmds_to_issue);
-	req->errors = -EIO;
+	cmd->status = -EIO;
 	mtip_softirq_done_fn(req);
 }
 
@@ -3807,6 +3831,8 @@ static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx,
 	struct request *rq = bd->rq;
 	int ret;
 
+	mtip_init_cmd_header(rq);
+
 	if (unlikely(mtip_check_unal_depth(hctx, rq)))
 		return BLK_MQ_RQ_QUEUE_BUSY;
 
@@ -3816,7 +3842,6 @@ static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (likely(!ret))
 		return BLK_MQ_RQ_QUEUE_OK;
 
-	rq->errors = ret;
 	return BLK_MQ_RQ_QUEUE_ERROR;
 }
 
@@ -3838,7 +3863,6 @@ static int mtip_init_cmd(void *data, struct request *rq, unsigned int hctx_idx,
 {
 	struct driver_data *dd = data;
 	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
-	u32 host_cap_64 = readl(dd->mmio + HOST_CAP) & HOST_CAP_64;
 
 	/*
 	 * For flush requests, request_idx starts at the end of the
@@ -3855,17 +3879,6 @@ static int mtip_init_cmd(void *data, struct request *rq, unsigned int hctx_idx,
 
 	memset(cmd->command, 0, CMD_DMA_ALLOC_SZ);
 
-	/* Point the command headers at the command tables. */
-	cmd->command_header = dd->port->command_list +
-				(sizeof(struct mtip_cmd_hdr) * request_idx);
-	cmd->command_header_dma = dd->port->command_list_dma +
-				(sizeof(struct mtip_cmd_hdr) * request_idx);
-
-	if (host_cap_64)
-		cmd->command_header->ctbau = __force_bit2int cpu_to_le32((cmd->command_dma >> 16) >> 16);
-
-	cmd->command_header->ctba = __force_bit2int cpu_to_le32(cmd->command_dma & 0xFFFFFFFF);
-
 	sg_init_table(cmd->sg, MTIP_MAX_SG);
 	return 0;
 }
@@ -3889,7 +3902,7 @@ exit_handler:
 	return BLK_EH_RESET_TIMER;
 }
 
-static struct blk_mq_ops mtip_mq_ops = {
+static const struct blk_mq_ops mtip_mq_ops = {
 	.queue_rq	= mtip_queue_rq,
 	.init_request	= mtip_init_cmd,
 	.exit_request	= mtip_free_cmd,
@@ -4025,7 +4038,6 @@ skip_create_disk:
 		dd->queue->limits.discard_granularity = 4096;
 		blk_queue_max_discard_sectors(dd->queue,
 			MTIP_MAX_TRIM_ENTRY_LEN * MTIP_MAX_TRIM_ENTRIES);
-		dd->queue->limits.discard_zeroes_data = 0;
 	}
 
 	/* Set the capacity of the device in 512 byte sectors. */
@@ -4107,9 +4119,11 @@ static void mtip_no_dev_cleanup(struct request *rq, void *data, bool reserv)
 	struct driver_data *dd = (struct driver_data *)data;
 	struct mtip_cmd *cmd;
 
-	if (likely(!reserv))
-		blk_mq_complete_request(rq, -ENODEV);
-	else if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &dd->port->flags)) {
+	if (likely(!reserv)) {
+		cmd = blk_mq_rq_to_pdu(rq);
+		cmd->status = -ENODEV;
+		blk_mq_complete_request(rq);
+	} else if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &dd->port->flags)) {
 
 		cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL);
 		if (cmd->comp_func)
@@ -4162,7 +4176,7 @@ static int mtip_block_remove(struct driver_data *dd)
 		dev_info(&dd->pdev->dev, "device %s surprise removal\n",
 						dd->disk->disk_name);
 
-	blk_mq_freeze_queue_start(dd->queue);
+	blk_freeze_queue_start(dd->queue);
 	blk_mq_stop_hw_queues(dd->queue);
 	blk_mq_tagset_busy_iter(&dd->tags, mtip_no_dev_cleanup, dd);
 

drivers/block/mtip32xx/mtip32xx.h

@@ -352,6 +352,7 @@ struct mtip_cmd {
 	int retries; /* The number of retries left for this command. */
 
 	int direction; /* Data transfer direction */
+	int status;
 };
 
 /* Structure used to describe a port. */

drivers/block/nbd.c

@@ -40,49 +40,82 @@
 #include <asm/types.h>
 
 #include <linux/nbd.h>
+#include <linux/nbd-netlink.h>
+#include <net/genetlink.h>
 
 static DEFINE_IDR(nbd_index_idr);
 static DEFINE_MUTEX(nbd_index_mutex);
+static int nbd_total_devices = 0;
 
 struct nbd_sock {
 	struct socket *sock;
 	struct mutex tx_lock;
 	struct request *pending;
 	int sent;
+	bool dead;
+	int fallback_index;
+	int cookie;
+};
+
+struct recv_thread_args {
+	struct work_struct work;
+	struct nbd_device *nbd;
+	int index;
+};
+
+struct link_dead_args {
+	struct work_struct work;
+	int index;
 };
 
 #define NBD_TIMEDOUT			0
 #define NBD_DISCONNECT_REQUESTED	1
 #define NBD_DISCONNECTED		2
-#define NBD_RUNNING			3
+#define NBD_HAS_PID_FILE		3
+#define NBD_HAS_CONFIG_REF		4
+#define NBD_BOUND			5
+#define NBD_DESTROY_ON_DISCONNECT	6
 
-struct nbd_device {
+struct nbd_config {
 	u32 flags;
 	unsigned long runtime_flags;
-	struct nbd_sock **socks;
-	int magic;
+	u64 dead_conn_timeout;
 
-	struct blk_mq_tag_set tag_set;
-
-	struct mutex config_lock;
-	struct gendisk *disk;
+	struct nbd_sock **socks;
 	int num_connections;
+	atomic_t live_connections;
+	wait_queue_head_t conn_wait;
+
 	atomic_t recv_threads;
 	wait_queue_head_t recv_wq;
 	loff_t blksize;
 	loff_t bytesize;
-
-	struct task_struct *task_recv;
-	struct task_struct *task_setup;
-
 #if IS_ENABLED(CONFIG_DEBUG_FS)
 	struct dentry *dbg_dir;
 #endif
 };
 
+struct nbd_device {
+	struct blk_mq_tag_set tag_set;
+
+	int index;
+	refcount_t config_refs;
+	refcount_t refs;
+	struct nbd_config *config;
+	struct mutex config_lock;
+	struct gendisk *disk;
+
+	struct list_head list;
+	struct task_struct *task_recv;
+	struct task_struct *task_setup;
+};
+
 struct nbd_cmd {
 	struct nbd_device *nbd;
+	int index;
+	int cookie;
 	struct completion send_complete;
+	int status;
 };
 
 #if IS_ENABLED(CONFIG_DEBUG_FS)
@@ -100,18 +133,16 @@ static int part_shift;
 
 static int nbd_dev_dbg_init(struct nbd_device *nbd);
 static void nbd_dev_dbg_close(struct nbd_device *nbd);
-
+static void nbd_config_put(struct nbd_device *nbd);
+static void nbd_connect_reply(struct genl_info *info, int index);
+static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info);
+static void nbd_dead_link_work(struct work_struct *work);
 
 static inline struct device *nbd_to_dev(struct nbd_device *nbd)
 {
 	return disk_to_dev(nbd->disk);
 }
 
-static bool nbd_is_connected(struct nbd_device *nbd)
-{
-	return !!nbd->task_recv;
-}
-
 static const char *nbdcmd_to_ascii(int cmd)
 {
 	switch (cmd) {
@@ -124,44 +155,104 @@ static const char *nbdcmd_to_ascii(int cmd)
 	return "invalid";
 }
 
-static int nbd_size_clear(struct nbd_device *nbd, struct block_device *bdev)
+static ssize_t pid_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
 {
-	if (bdev->bd_openers <= 1)
-		bd_set_size(bdev, 0);
-	set_capacity(nbd->disk, 0);
-	kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
+	struct gendisk *disk = dev_to_disk(dev);
+	struct nbd_device *nbd = (struct nbd_device *)disk->private_data;
 
-	return 0;
+	return sprintf(buf, "%d\n", task_pid_nr(nbd->task_recv));
+}
+
+static struct device_attribute pid_attr = {
+	.attr = { .name = "pid", .mode = S_IRUGO},
+	.show = pid_show,
+};
+
+static void nbd_dev_remove(struct nbd_device *nbd)
+{
+	struct gendisk *disk = nbd->disk;
+	if (disk) {
+		del_gendisk(disk);
+		blk_cleanup_queue(disk->queue);
+		blk_mq_free_tag_set(&nbd->tag_set);
+		disk->private_data = NULL;
+		put_disk(disk);
+	}
+	kfree(nbd);
+}
+
+static void nbd_put(struct nbd_device *nbd)
+{
+	if (refcount_dec_and_mutex_lock(&nbd->refs,
+					&nbd_index_mutex)) {
+		idr_remove(&nbd_index_idr, nbd->index);
+		mutex_unlock(&nbd_index_mutex);
+		nbd_dev_remove(nbd);
+	}
+}
+
+static int nbd_disconnected(struct nbd_config *config)
+{
+	return test_bit(NBD_DISCONNECTED, &config->runtime_flags) ||
+		test_bit(NBD_DISCONNECT_REQUESTED, &config->runtime_flags);
+}
+
+static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock,
+				int notify)
+{
+	if (!nsock->dead && notify && !nbd_disconnected(nbd->config)) {
+		struct link_dead_args *args;
+		args = kmalloc(sizeof(struct link_dead_args), GFP_NOIO);
+		if (args) {
+			INIT_WORK(&args->work, nbd_dead_link_work);
+			args->index = nbd->index;
+			queue_work(system_wq, &args->work);
+		}
+	}
+	if (!nsock->dead) {
+		kernel_sock_shutdown(nsock->sock, SHUT_RDWR);
+		atomic_dec(&nbd->config->live_connections);
+	}
+	nsock->dead = true;
+	nsock->pending = NULL;
+	nsock->sent = 0;
+}
+
+static void nbd_size_clear(struct nbd_device *nbd)
+{
+	if (nbd->config->bytesize) {
+		set_capacity(nbd->disk, 0);
+		kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
+	}
 }
 
-static void nbd_size_update(struct nbd_device *nbd, struct block_device *bdev)
+static void nbd_size_update(struct nbd_device *nbd)
 {
-	blk_queue_logical_block_size(nbd->disk->queue, nbd->blksize);
-	blk_queue_physical_block_size(nbd->disk->queue, nbd->blksize);
-	bd_set_size(bdev, nbd->bytesize);
-	set_capacity(nbd->disk, nbd->bytesize >> 9);
+	struct nbd_config *config = nbd->config;
+	blk_queue_logical_block_size(nbd->disk->queue, config->blksize);
+	blk_queue_physical_block_size(nbd->disk->queue, config->blksize);
+	set_capacity(nbd->disk, config->bytesize >> 9);
 	kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
 }
 
-static void nbd_size_set(struct nbd_device *nbd, struct block_device *bdev,
-			loff_t blocksize, loff_t nr_blocks)
+static void nbd_size_set(struct nbd_device *nbd, loff_t blocksize,
+			 loff_t nr_blocks)
 {
-	nbd->blksize = blocksize;
-	nbd->bytesize = blocksize * nr_blocks;
-	if (nbd_is_connected(nbd))
-		nbd_size_update(nbd, bdev);
+	struct nbd_config *config = nbd->config;
+	config->blksize = blocksize;
+	config->bytesize = blocksize * nr_blocks;
+	nbd_size_update(nbd);
 }
 
-static void nbd_end_request(struct nbd_cmd *cmd)
+static void nbd_complete_rq(struct request *req)
 {
-	struct nbd_device *nbd = cmd->nbd;
-	struct request *req = blk_mq_rq_from_pdu(cmd);
-	int error = req->errors ? -EIO : 0;
+	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
 
-	dev_dbg(nbd_to_dev(nbd), "request %p: %s\n", cmd,
-		error ? "failed" : "done");
+	dev_dbg(nbd_to_dev(cmd->nbd), "request %p: %s\n", cmd,
+		cmd->status ? "failed" : "done");
 
-	blk_mq_complete_request(req, error);
+	blk_mq_end_request(req, cmd->status);
 }
 
 /*
@@ -169,17 +260,18 @@ static void nbd_end_request(struct nbd_cmd *cmd)
  */
 static void sock_shutdown(struct nbd_device *nbd)
 {
+	struct nbd_config *config = nbd->config;
 	int i;
 
-	if (nbd->num_connections == 0)
+	if (config->num_connections == 0)
 		return;
-	if (test_and_set_bit(NBD_DISCONNECTED, &nbd->runtime_flags))
+	if (test_and_set_bit(NBD_DISCONNECTED, &config->runtime_flags))
 		return;
 
-	for (i = 0; i < nbd->num_connections; i++) {
-		struct nbd_sock *nsock = nbd->socks[i];
+	for (i = 0; i < config->num_connections; i++) {
+		struct nbd_sock *nsock = config->socks[i];
 		mutex_lock(&nsock->tx_lock);
-		kernel_sock_shutdown(nsock->sock, SHUT_RDWR);
+		nbd_mark_nsock_dead(nbd, nsock, 0);
 		mutex_unlock(&nsock->tx_lock);
 	}
 	dev_warn(disk_to_dev(nbd->disk), "shutting down sockets\n");
@@ -190,14 +282,58 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
 	struct nbd_device *nbd = cmd->nbd;
+	struct nbd_config *config;
 
-	dev_err(nbd_to_dev(nbd), "Connection timed out, shutting down connection\n");
-	set_bit(NBD_TIMEDOUT, &nbd->runtime_flags);
-	req->errors = -EIO;
+	if (!refcount_inc_not_zero(&nbd->config_refs)) {
+		cmd->status = -EIO;
+		return BLK_EH_HANDLED;
+	}
 
-	mutex_lock(&nbd->config_lock);
+	/* If we are waiting on our dead timer then we could get timeout
+	 * callbacks for our request.  For this we just want to reset the timer
+	 * and let the queue side take care of everything.
+	 */
+	if (!completion_done(&cmd->send_complete)) {
+		nbd_config_put(nbd);
+		return BLK_EH_RESET_TIMER;
+	}
+	config = nbd->config;
+
+	if (config->num_connections > 1) {
+		dev_err_ratelimited(nbd_to_dev(nbd),
+				    "Connection timed out, retrying\n");
+		/*
+		 * Hooray we have more connections, requeue this IO, the submit
+		 * path will put it on a real connection.
+		 */
+		if (config->socks && config->num_connections > 1) {
+			if (cmd->index < config->num_connections) {
+				struct nbd_sock *nsock =
+					config->socks[cmd->index];
+				mutex_lock(&nsock->tx_lock);
+				/* We can have multiple outstanding requests, so
+				 * we don't want to mark the nsock dead if we've
+				 * already reconnected with a new socket, so
+				 * only mark it dead if its the same socket we
+				 * were sent out on.
+				 */
+				if (cmd->cookie == nsock->cookie)
+					nbd_mark_nsock_dead(nbd, nsock, 1);
+				mutex_unlock(&nsock->tx_lock);
+			}
+			blk_mq_requeue_request(req, true);
+			nbd_config_put(nbd);
+			return BLK_EH_NOT_HANDLED;
+		}
+	} else {
+		dev_err_ratelimited(nbd_to_dev(nbd),
+				    "Connection timed out\n");
+	}
+	set_bit(NBD_TIMEDOUT, &config->runtime_flags);
+	cmd->status = -EIO;
 	sock_shutdown(nbd);
-	mutex_unlock(&nbd->config_lock);
+	nbd_config_put(nbd);
+
 	return BLK_EH_HANDLED;
 }
 
@@ -207,7 +343,8 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 static int sock_xmit(struct nbd_device *nbd, int index, int send,
 		     struct iov_iter *iter, int msg_flags, int *sent)
 {
-	struct socket *sock = nbd->socks[index]->sock;
+	struct nbd_config *config = nbd->config;
+	struct socket *sock = config->socks[index]->sock;
 	int result;
 	struct msghdr msg;
 	unsigned long pflags = current->flags;
@@ -253,7 +390,8 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send,
 static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 {
 	struct request *req = blk_mq_rq_from_pdu(cmd);
-	struct nbd_sock *nsock = nbd->socks[index];
+	struct nbd_config *config = nbd->config;
+	struct nbd_sock *nsock = config->socks[index];
 	int result;
 	struct nbd_request request = {.magic = htonl(NBD_REQUEST_MAGIC)};
 	struct kvec iov = {.iov_base = &request, .iov_len = sizeof(request)};
@@ -284,7 +422,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	}
 
 	if (rq_data_dir(req) == WRITE &&
-	    (nbd->flags & NBD_FLAG_READ_ONLY)) {
+	    (config->flags & NBD_FLAG_READ_ONLY)) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 				    "Write on read-only\n");
 		return -EIO;
@@ -301,6 +439,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 		}
 		iov_iter_advance(&from, sent);
 	}
+	cmd->index = index;
+	cmd->cookie = nsock->cookie;
 	request.type = htonl(type);
 	if (type != NBD_CMD_FLUSH) {
 		request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
@@ -328,7 +468,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 		}
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 			"Send control failed (result %d)\n", result);
-		return -EIO;
+		return -EAGAIN;
 	}
 send_pages:
 	if (type != NBD_CMD_WRITE)
@@ -370,7 +510,7 @@ send_pages:
 				dev_err(disk_to_dev(nbd->disk),
 					"Send data failed (result %d)\n",
 					result);
-				return -EIO;
+				return -EAGAIN;
 			}
 			/*
 			 * The completion might already have come in,
@@ -392,6 +532,7 @@ out:
 /* NULL returned = something went wrong, inform userspace */
 static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 {
+	struct nbd_config *config = nbd->config;
 	int result;
 	struct nbd_reply reply;
 	struct nbd_cmd *cmd;
@@ -405,8 +546,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 	iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply));
 	result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL);
 	if (result <= 0) {
-		if (!test_bit(NBD_DISCONNECTED, &nbd->runtime_flags) &&
-		    !test_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags))
+		if (!nbd_disconnected(config))
 			dev_err(disk_to_dev(nbd->disk),
 				"Receive control failed (result %d)\n", result);
 		return ERR_PTR(result);
@@ -433,7 +573,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 	if (ntohl(reply.error)) {
 		dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n",
 			ntohl(reply.error));
-		req->errors = -EIO;
+		cmd->status = -EIO;
 		return cmd;
 	}
 
@@ -449,8 +589,19 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 			if (result <= 0) {
 				dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n",
 					result);
-				req->errors = -EIO;
-				return cmd;
+				/*
+				 * If we've disconnected or we only have 1
+				 * connection then we need to make sure we
+				 * complete this request, otherwise error out
+				 * and let the timeout stuff handle resubmitting
+				 * this request onto another connection.
+				 */
+				if (nbd_disconnected(config) ||
+				    config->num_connections <= 1) {
+					cmd->status = -EIO;
+					return cmd;
+				}
+				return ERR_PTR(-EIO);
 			}
 			dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n",
 				cmd, bvec.bv_len);
@@ -462,54 +613,34 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 	return cmd;
 }
 
-static ssize_t pid_show(struct device *dev,
-			struct device_attribute *attr, char *buf)
-{
-	struct gendisk *disk = dev_to_disk(dev);
-	struct nbd_device *nbd = (struct nbd_device *)disk->private_data;
-
-	return sprintf(buf, "%d\n", task_pid_nr(nbd->task_recv));
-}
-
-static struct device_attribute pid_attr = {
-	.attr = { .name = "pid", .mode = S_IRUGO},
-	.show = pid_show,
-};
-
-struct recv_thread_args {
-	struct work_struct work;
-	struct nbd_device *nbd;
-	int index;
-};
-
 static void recv_work(struct work_struct *work)
 {
 	struct recv_thread_args *args = container_of(work,
 						     struct recv_thread_args,
 						     work);
 	struct nbd_device *nbd = args->nbd;
+	struct nbd_config *config = nbd->config;
 	struct nbd_cmd *cmd;
 	int ret = 0;
 
-	BUG_ON(nbd->magic != NBD_MAGIC);
 	while (1) {
 		cmd = nbd_read_stat(nbd, args->index);
 		if (IS_ERR(cmd)) {
+			struct nbd_sock *nsock = config->socks[args->index];
+
+			mutex_lock(&nsock->tx_lock);
+			nbd_mark_nsock_dead(nbd, nsock, 1);
+			mutex_unlock(&nsock->tx_lock);
 			ret = PTR_ERR(cmd);
 			break;
 		}
 
-		nbd_end_request(cmd);
+		blk_mq_complete_request(blk_mq_rq_from_pdu(cmd));
 	}
-
-	/*
-	 * We got an error, shut everybody down if this wasn't the result of a
-	 * disconnect request.
-	 */
-	if (ret && !test_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags))
-		sock_shutdown(nbd);
-	atomic_dec(&nbd->recv_threads);
-	wake_up(&nbd->recv_wq);
+	atomic_dec(&config->recv_threads);
+	wake_up(&config->recv_wq);
+	nbd_config_put(nbd);
+	kfree(args);
 }
 
 static void nbd_clear_req(struct request *req, void *data, bool reserved)
@@ -519,47 +650,119 @@ static void nbd_clear_req(struct request *req, void *data, bool reserved)
 	if (!blk_mq_request_started(req))
 		return;
 	cmd = blk_mq_rq_to_pdu(req);
-	req->errors = -EIO;
-	nbd_end_request(cmd);
+	cmd->status = -EIO;
+	blk_mq_complete_request(req);
 }
 
 static void nbd_clear_que(struct nbd_device *nbd)
 {
-	BUG_ON(nbd->magic != NBD_MAGIC);
-
+	blk_mq_stop_hw_queues(nbd->disk->queue);
 	blk_mq_tagset_busy_iter(&nbd->tag_set, nbd_clear_req, NULL);
+	blk_mq_start_hw_queues(nbd->disk->queue);
 	dev_dbg(disk_to_dev(nbd->disk), "queue cleared\n");
 }
 
+static int find_fallback(struct nbd_device *nbd, int index)
+{
+	struct nbd_config *config = nbd->config;
+	int new_index = -1;
+	struct nbd_sock *nsock = config->socks[index];
+	int fallback = nsock->fallback_index;
+
+	if (test_bit(NBD_DISCONNECTED, &config->runtime_flags))
+		return new_index;
+
+	if (config->num_connections <= 1) {
+		dev_err_ratelimited(disk_to_dev(nbd->disk),
+				    "Attempted send on invalid socket\n");
+		return new_index;
+	}
+
+	if (fallback >= 0 && fallback < config->num_connections &&
+	    !config->socks[fallback]->dead)
+		return fallback;
+
+	if (nsock->fallback_index < 0 ||
+	    nsock->fallback_index >= config->num_connections ||
+	    config->socks[nsock->fallback_index]->dead) {
+		int i;
+		for (i = 0; i < config->num_connections; i++) {
+			if (i == index)
+				continue;
+			if (!config->socks[i]->dead) {
+				new_index = i;
+				break;
+			}
+		}
+		nsock->fallback_index = new_index;
+		if (new_index < 0) {
+			dev_err_ratelimited(disk_to_dev(nbd->disk),
+					    "Dead connection, failed to find a fallback\n");
+			return new_index;
+		}
+	}
+	new_index = nsock->fallback_index;
+	return new_index;
+}
+
+static int wait_for_reconnect(struct nbd_device *nbd)
+{
+	struct nbd_config *config = nbd->config;
+	if (!config->dead_conn_timeout)
+		return 0;
+	if (test_bit(NBD_DISCONNECTED, &config->runtime_flags))
+		return 0;
+	wait_event_interruptible_timeout(config->conn_wait,
+					 atomic_read(&config->live_connections),
+					 config->dead_conn_timeout);
+	return atomic_read(&config->live_connections);
+}
 
 static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
 {
 	struct request *req = blk_mq_rq_from_pdu(cmd);
 	struct nbd_device *nbd = cmd->nbd;
+	struct nbd_config *config;
 	struct nbd_sock *nsock;
 	int ret;
 
-	if (index >= nbd->num_connections) {
+	if (!refcount_inc_not_zero(&nbd->config_refs)) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
-				    "Attempted send on invalid socket\n");
+				    "Socks array is empty\n");
 		return -EINVAL;
 	}
+	config = nbd->config;
 
-	if (test_bit(NBD_DISCONNECTED, &nbd->runtime_flags)) {
+	if (index >= config->num_connections) {
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
-				    "Attempted send on closed socket\n");
+				    "Attempted send on invalid socket\n");
+		nbd_config_put(nbd);
 		return -EINVAL;
 	}
-
-	req->errors = 0;
-
-	nsock = nbd->socks[index];
+	cmd->status = 0;
+again:
+	nsock = config->socks[index];
 	mutex_lock(&nsock->tx_lock);
-	if (unlikely(!nsock->sock)) {
+	if (nsock->dead) {
+		int old_index = index;
+		index = find_fallback(nbd, index);
 		mutex_unlock(&nsock->tx_lock);
-		dev_err_ratelimited(disk_to_dev(nbd->disk),
-				    "Attempted send on closed socket\n");
-		return -EINVAL;
+		if (index < 0) {
+			if (wait_for_reconnect(nbd)) {
+				index = old_index;
+				goto again;
+			}
+			/* All the sockets should already be down at this point,
+			 * we just want to make sure that DISCONNECTED is set so
+			 * any requests that come in that were queue'ed waiting
+			 * for the reconnect timer don't trigger the timer again
+			 * and instead just error out.
+			 */
+			sock_shutdown(nbd);
+			nbd_config_put(nbd);
+			return -EIO;
+		}
+		goto again;
 	}
 
 	/* Handle the case that we have a pending request that was partially
@@ -572,9 +775,21 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
 		ret = 0;
 		goto out;
 	}
+	/*
+	 * Some failures are related to the link going down, so anything that
+	 * returns EAGAIN can be retried on a different socket.
+	 */
 	ret = nbd_send_cmd(nbd, cmd, index);
+	if (ret == -EAGAIN) {
+		dev_err_ratelimited(disk_to_dev(nbd->disk),
+				    "Request send failed trying another connection\n");
+		nbd_mark_nsock_dead(nbd, nsock, 1);
+		mutex_unlock(&nsock->tx_lock);
+		goto again;
+	}
 out:
 	mutex_unlock(&nsock->tx_lock);
+	nbd_config_put(nbd);
 	return ret;
 }
 
@@ -611,9 +826,10 @@ static int nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return ret;
 }
 
-static int nbd_add_socket(struct nbd_device *nbd, struct block_device *bdev,
-			  unsigned long arg)
+static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
+			  bool netlink)
 {
+	struct nbd_config *config = nbd->config;
 	struct socket *sock;
 	struct nbd_sock **socks;
 	struct nbd_sock *nsock;
@@ -623,43 +839,107 @@ static int nbd_add_socket(struct nbd_device *nbd, struct block_device *bdev,
 	if (!sock)
 		return err;
 
-	if (!nbd->task_setup)
+	if (!netlink && !nbd->task_setup &&
+	    !test_bit(NBD_BOUND, &config->runtime_flags))
 		nbd->task_setup = current;
-	if (nbd->task_setup != current) {
+
+	if (!netlink &&
+	    (nbd->task_setup != current ||
+	     test_bit(NBD_BOUND, &config->runtime_flags))) {
 		dev_err(disk_to_dev(nbd->disk),
 			"Device being setup by another task");
-		return -EINVAL;
+		sockfd_put(sock);
+		return -EBUSY;
 	}
 
-	socks = krealloc(nbd->socks, (nbd->num_connections + 1) *
+	socks = krealloc(config->socks, (config->num_connections + 1) *
 			 sizeof(struct nbd_sock *), GFP_KERNEL);
-	if (!socks)
+	if (!socks) {
+		sockfd_put(sock);
 		return -ENOMEM;
+	}
 	nsock = kzalloc(sizeof(struct nbd_sock), GFP_KERNEL);
-	if (!nsock)
+	if (!nsock) {
+		sockfd_put(sock);
 		return -ENOMEM;
+	}
 
-	nbd->socks = socks;
+	config->socks = socks;
 
+	nsock->fallback_index = -1;
+	nsock->dead = false;
 	mutex_init(&nsock->tx_lock);
 	nsock->sock = sock;
 	nsock->pending = NULL;
 	nsock->sent = 0;
-	socks[nbd->num_connections++] = nsock;
+	nsock->cookie = 0;
+	socks[config->num_connections++] = nsock;
+	atomic_inc(&config->live_connections);
 
-	if (max_part)
-		bdev->bd_invalidated = 1;
 	return 0;
 }
 
+static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
+{
+	struct nbd_config *config = nbd->config;
+	struct socket *sock, *old;
+	struct recv_thread_args *args;
+	int i;
+	int err;
+
+	sock = sockfd_lookup(arg, &err);
+	if (!sock)
+		return err;
+
+	args = kzalloc(sizeof(*args), GFP_KERNEL);
+	if (!args) {
+		sockfd_put(sock);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < config->num_connections; i++) {
+		struct nbd_sock *nsock = config->socks[i];
+
+		if (!nsock->dead)
+			continue;
+
+		mutex_lock(&nsock->tx_lock);
+		if (!nsock->dead) {
+			mutex_unlock(&nsock->tx_lock);
+			continue;
+		}
+		sk_set_memalloc(sock->sk);
+		atomic_inc(&config->recv_threads);
+		refcount_inc(&nbd->config_refs);
+		old = nsock->sock;
+		nsock->fallback_index = -1;
+		nsock->sock = sock;
+		nsock->dead = false;
+		INIT_WORK(&args->work, recv_work);
+		args->index = i;
+		args->nbd = nbd;
+		nsock->cookie++;
+		mutex_unlock(&nsock->tx_lock);
+		sockfd_put(old);
+
+		/* We take the tx_mutex in an error path in the recv_work, so we
+		 * need to queue_work outside of the tx_mutex.
+		 */
+		queue_work(recv_workqueue, &args->work);
+
+		atomic_inc(&config->live_connections);
+		wake_up(&config->conn_wait);
+		return 0;
+	}
+	sockfd_put(sock);
+	kfree(args);
+	return -ENOSPC;
+}
+
 /* Reset all properties of an NBD device */
 static void nbd_reset(struct nbd_device *nbd)
 {
-	nbd->runtime_flags = 0;
-	nbd->blksize = 1024;
-	nbd->bytesize = 0;
-	set_capacity(nbd->disk, 0);
-	nbd->flags = 0;
+	nbd->config = NULL;
 	nbd->tag_set.timeout = 0;
 	queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
 }
@@ -668,21 +948,23 @@ static void nbd_bdev_reset(struct block_device *bdev)
 {
 	if (bdev->bd_openers > 1)
 		return;
-	set_device_ro(bdev, false);
-	bdev->bd_inode->i_size = 0;
+	bd_set_size(bdev, 0);
 	if (max_part > 0) {
 		blkdev_reread_part(bdev);
 		bdev->bd_invalidated = 1;
 	}
 }
 
-static void nbd_parse_flags(struct nbd_device *nbd, struct block_device *bdev)
+static void nbd_parse_flags(struct nbd_device *nbd)
 {
-	if (nbd->flags & NBD_FLAG_READ_ONLY)
-		set_device_ro(bdev, true);
-	if (nbd->flags & NBD_FLAG_SEND_TRIM)
+	struct nbd_config *config = nbd->config;
+	if (config->flags & NBD_FLAG_READ_ONLY)
+		set_disk_ro(nbd->disk, true);
+	else
+		set_disk_ro(nbd->disk, false);
+	if (config->flags & NBD_FLAG_SEND_TRIM)
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
-	if (nbd->flags & NBD_FLAG_SEND_FLUSH)
+	if (config->flags & NBD_FLAG_SEND_FLUSH)
 		blk_queue_write_cache(nbd->disk->queue, true, false);
 	else
 		blk_queue_write_cache(nbd->disk->queue, false, false);
@@ -690,6 +972,7 @@ static void nbd_parse_flags(struct nbd_device *nbd, struct block_device *bdev)
 
 static void send_disconnects(struct nbd_device *nbd)
 {
+	struct nbd_config *config = nbd->config;
 	struct nbd_request request = {
 		.magic = htonl(NBD_REQUEST_MAGIC),
 		.type = htonl(NBD_CMD_DISC),
@@ -698,7 +981,7 @@ static void send_disconnects(struct nbd_device *nbd)
 	struct iov_iter from;
 	int i, ret;
 
-	for (i = 0; i < nbd->num_connections; i++) {
+	for (i = 0; i < config->num_connections; i++) {
 		iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request));
 		ret = sock_xmit(nbd, i, 1, &from, 0, NULL);
 		if (ret <= 0)
@@ -707,145 +990,162 @@ static void send_disconnects(struct nbd_device *nbd)
 	}
 }
 
-static int nbd_disconnect(struct nbd_device *nbd, struct block_device *bdev)
+static int nbd_disconnect(struct nbd_device *nbd)
 {
-	dev_info(disk_to_dev(nbd->disk), "NBD_DISCONNECT\n");
-	if (!nbd->socks)
-		return -EINVAL;
-
-	mutex_unlock(&nbd->config_lock);
-	fsync_bdev(bdev);
-	mutex_lock(&nbd->config_lock);
-
-	/* Check again after getting mutex back.  */
-	if (!nbd->socks)
-		return -EINVAL;
+	struct nbd_config *config = nbd->config;
 
+	dev_info(disk_to_dev(nbd->disk), "NBD_DISCONNECT\n");
 	if (!test_and_set_bit(NBD_DISCONNECT_REQUESTED,
-			      &nbd->runtime_flags))
+			      &config->runtime_flags))
 		send_disconnects(nbd);
 	return 0;
 }
 
-static int nbd_clear_sock(struct nbd_device *nbd, struct block_device *bdev)
+static void nbd_clear_sock(struct nbd_device *nbd)
 {
 	sock_shutdown(nbd);
 	nbd_clear_que(nbd);
+	nbd->task_setup = NULL;
+}
 
-	__invalidate_device(bdev, true);
-	nbd_bdev_reset(bdev);
-	/*
-	 * We want to give the run thread a chance to wait for everybody
-	 * to clean up and then do it's own cleanup.
-	 */
-	if (!test_bit(NBD_RUNNING, &nbd->runtime_flags) &&
-	    nbd->num_connections) {
-		int i;
-
-		for (i = 0; i < nbd->num_connections; i++) {
-			sockfd_put(nbd->socks[i]->sock);
-			kfree(nbd->socks[i]);
+static void nbd_config_put(struct nbd_device *nbd)
+{
+	if (refcount_dec_and_mutex_lock(&nbd->config_refs,
+					&nbd->config_lock)) {
+		struct nbd_config *config = nbd->config;
+		nbd_dev_dbg_close(nbd);
+		nbd_size_clear(nbd);
+		if (test_and_clear_bit(NBD_HAS_PID_FILE,
+				       &config->runtime_flags))
+			device_remove_file(disk_to_dev(nbd->disk), &pid_attr);
+		nbd->task_recv = NULL;
+		nbd_clear_sock(nbd);
+		if (config->num_connections) {
+			int i;
+			for (i = 0; i < config->num_connections; i++) {
+				sockfd_put(config->socks[i]->sock);
+				kfree(config->socks[i]);
+			}
+			kfree(config->socks);
 		}
-		kfree(nbd->socks);
-		nbd->socks = NULL;
-		nbd->num_connections = 0;
-	}
-	nbd->task_setup = NULL;
+		nbd_reset(nbd);
 
-	return 0;
+		mutex_unlock(&nbd->config_lock);
+		nbd_put(nbd);
+		module_put(THIS_MODULE);
+	}
 }
 
-static int nbd_start_device(struct nbd_device *nbd, struct block_device *bdev)
+static int nbd_start_device(struct nbd_device *nbd)
 {
-	struct recv_thread_args *args;
-	int num_connections = nbd->num_connections;
+	struct nbd_config *config = nbd->config;
+	int num_connections = config->num_connections;
 	int error = 0, i;
 
 	if (nbd->task_recv)
 		return -EBUSY;
-	if (!nbd->socks)
+	if (!config->socks)
 		return -EINVAL;
 	if (num_connections > 1 &&
-	    !(nbd->flags & NBD_FLAG_CAN_MULTI_CONN)) {
+	    !(config->flags & NBD_FLAG_CAN_MULTI_CONN)) {
 		dev_err(disk_to_dev(nbd->disk), "server does not support multiple connections per device.\n");
-		error = -EINVAL;
-		goto out_err;
+		return -EINVAL;
 	}
 
-	set_bit(NBD_RUNNING, &nbd->runtime_flags);
-	blk_mq_update_nr_hw_queues(&nbd->tag_set, nbd->num_connections);
-	args = kcalloc(num_connections, sizeof(*args), GFP_KERNEL);
-	if (!args) {
-		error = -ENOMEM;
-		goto out_err;
-	}
+	blk_mq_update_nr_hw_queues(&nbd->tag_set, config->num_connections);
 	nbd->task_recv = current;
-	mutex_unlock(&nbd->config_lock);
 
-	nbd_parse_flags(nbd, bdev);
+	nbd_parse_flags(nbd);
 
 	error = device_create_file(disk_to_dev(nbd->disk), &pid_attr);
 	if (error) {
 		dev_err(disk_to_dev(nbd->disk), "device_create_file failed!\n");
-		goto out_recv;
+		return error;
 	}
-
-	nbd_size_update(nbd, bdev);
+	set_bit(NBD_HAS_PID_FILE, &config->runtime_flags);
 
 	nbd_dev_dbg_init(nbd);
 	for (i = 0; i < num_connections; i++) {
-		sk_set_memalloc(nbd->socks[i]->sock->sk);
-		atomic_inc(&nbd->recv_threads);
-		INIT_WORK(&args[i].work, recv_work);
-		args[i].nbd = nbd;
-		args[i].index = i;
-		queue_work(recv_workqueue, &args[i].work);
-	}
-	wait_event_interruptible(nbd->recv_wq,
-				 atomic_read(&nbd->recv_threads) == 0);
-	for (i = 0; i < num_connections; i++)
-		flush_work(&args[i].work);
-	nbd_dev_dbg_close(nbd);
-	nbd_size_clear(nbd, bdev);
-	device_remove_file(disk_to_dev(nbd->disk), &pid_attr);
-out_recv:
-	mutex_lock(&nbd->config_lock);
-	nbd->task_recv = NULL;
-out_err:
-	clear_bit(NBD_RUNNING, &nbd->runtime_flags);
-	nbd_clear_sock(nbd, bdev);
+		struct recv_thread_args *args;
 
+		args = kzalloc(sizeof(*args), GFP_KERNEL);
+		if (!args) {
+			sock_shutdown(nbd);
+			return -ENOMEM;
+		}
+		sk_set_memalloc(config->socks[i]->sock->sk);
+		atomic_inc(&config->recv_threads);
+		refcount_inc(&nbd->config_refs);
+		INIT_WORK(&args->work, recv_work);
+		args->nbd = nbd;
+		args->index = i;
+		queue_work(recv_workqueue, &args->work);
+	}
+	return error;
+}
+
+static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *bdev)
+{
+	struct nbd_config *config = nbd->config;
+	int ret;
+
+	ret = nbd_start_device(nbd);
+	if (ret)
+		return ret;
+
+	bd_set_size(bdev, config->bytesize);
+	if (max_part)
+		bdev->bd_invalidated = 1;
+	mutex_unlock(&nbd->config_lock);
+	ret = wait_event_interruptible(config->recv_wq,
+					 atomic_read(&config->recv_threads) == 0);
+	if (ret)
+		sock_shutdown(nbd);
+	mutex_lock(&nbd->config_lock);
+	bd_set_size(bdev, 0);
 	/* user requested, ignore socket errors */
-	if (test_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags))
-		error = 0;
-	if (test_bit(NBD_TIMEDOUT, &nbd->runtime_flags))
-		error = -ETIMEDOUT;
+	if (test_bit(NBD_DISCONNECT_REQUESTED, &config->runtime_flags))
+		ret = 0;
+	if (test_bit(NBD_TIMEDOUT, &config->runtime_flags))
+		ret = -ETIMEDOUT;
+	return ret;
+}
 
-	nbd_reset(nbd);
-	return error;
+static void nbd_clear_sock_ioctl(struct nbd_device *nbd,
+				 struct block_device *bdev)
+{
+	sock_shutdown(nbd);
+	kill_bdev(bdev);
+	nbd_bdev_reset(bdev);
+	if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
+			       &nbd->config->runtime_flags))
+		nbd_config_put(nbd);
 }
 
 /* Must be called with config_lock held */
 static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		       unsigned int cmd, unsigned long arg)
 {
+	struct nbd_config *config = nbd->config;
+
 	switch (cmd) {
 	case NBD_DISCONNECT:
-		return nbd_disconnect(nbd, bdev);
+		return nbd_disconnect(nbd);
 	case NBD_CLEAR_SOCK:
-		return nbd_clear_sock(nbd, bdev);
+		nbd_clear_sock_ioctl(nbd, bdev);
+		return 0;
 	case NBD_SET_SOCK:
-		return nbd_add_socket(nbd, bdev, arg);
+		return nbd_add_socket(nbd, arg, false);
 	case NBD_SET_BLKSIZE:
-		nbd_size_set(nbd, bdev, arg,
-			     div_s64(nbd->bytesize, arg));
+		nbd_size_set(nbd, arg,
+			     div_s64(config->bytesize, arg));
 		return 0;
 	case NBD_SET_SIZE:
-		nbd_size_set(nbd, bdev, nbd->blksize,
-			     div_s64(arg, nbd->blksize));
+		nbd_size_set(nbd, config->blksize,
+			     div_s64(arg, config->blksize));
 		return 0;
 	case NBD_SET_SIZE_BLOCKS:
-		nbd_size_set(nbd, bdev, nbd->blksize, arg);
+		nbd_size_set(nbd, config->blksize, arg);
 		return 0;
 	case NBD_SET_TIMEOUT:
 		if (arg) {
@@ -855,10 +1155,10 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
 		return 0;
 
 	case NBD_SET_FLAGS:
-		nbd->flags = arg;
+		config->flags = arg;
 		return 0;
 	case NBD_DO_IT:
-		return nbd_start_device(nbd, bdev);
+		return nbd_start_device_ioctl(nbd, bdev);
 	case NBD_CLEAR_QUE:
 		/*
 		 * This is for compatibility only.  The queue is always cleared
@@ -879,23 +1179,92 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode,
 		     unsigned int cmd, unsigned long arg)
 {
 	struct nbd_device *nbd = bdev->bd_disk->private_data;
-	int error;
+	struct nbd_config *config = nbd->config;
+	int error = -EINVAL;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	BUG_ON(nbd->magic != NBD_MAGIC);
-
 	mutex_lock(&nbd->config_lock);
-	error = __nbd_ioctl(bdev, nbd, cmd, arg);
-	mutex_unlock(&nbd->config_lock);
 
+	/* Don't allow ioctl operations on a nbd device that was created with
+	 * netlink, unless it's DISCONNECT or CLEAR_SOCK, which are fine.
+	 */
+	if (!test_bit(NBD_BOUND, &config->runtime_flags) ||
+	    (cmd == NBD_DISCONNECT || cmd == NBD_CLEAR_SOCK))
+		error = __nbd_ioctl(bdev, nbd, cmd, arg);
+	else
+		dev_err(nbd_to_dev(nbd), "Cannot use ioctl interface on a netlink controlled device.\n");
+	mutex_unlock(&nbd->config_lock);
 	return error;
 }
 
+static struct nbd_config *nbd_alloc_config(void)
+{
+	struct nbd_config *config;
+
+	config = kzalloc(sizeof(struct nbd_config), GFP_NOFS);
+	if (!config)
+		return NULL;
+	atomic_set(&config->recv_threads, 0);
+	init_waitqueue_head(&config->recv_wq);
+	init_waitqueue_head(&config->conn_wait);
+	config->blksize = 1024;
+	atomic_set(&config->live_connections, 0);
+	try_module_get(THIS_MODULE);
+	return config;
+}
+
+static int nbd_open(struct block_device *bdev, fmode_t mode)
+{
+	struct nbd_device *nbd;
+	int ret = 0;
+
+	mutex_lock(&nbd_index_mutex);
+	nbd = bdev->bd_disk->private_data;
+	if (!nbd) {
+		ret = -ENXIO;
+		goto out;
+	}
+	if (!refcount_inc_not_zero(&nbd->refs)) {
+		ret = -ENXIO;
+		goto out;
+	}
+	if (!refcount_inc_not_zero(&nbd->config_refs)) {
+		struct nbd_config *config;
+
+		mutex_lock(&nbd->config_lock);
+		if (refcount_inc_not_zero(&nbd->config_refs)) {
+			mutex_unlock(&nbd->config_lock);
+			goto out;
+		}
+		config = nbd->config = nbd_alloc_config();
+		if (!config) {
+			ret = -ENOMEM;
+			mutex_unlock(&nbd->config_lock);
+			goto out;
+		}
+		refcount_set(&nbd->config_refs, 1);
+		refcount_inc(&nbd->refs);
+		mutex_unlock(&nbd->config_lock);
+	}
+out:
+	mutex_unlock(&nbd_index_mutex);
+	return ret;
+}
+
+static void nbd_release(struct gendisk *disk, fmode_t mode)
+{
+	struct nbd_device *nbd = disk->private_data;
+	nbd_config_put(nbd);
+	nbd_put(nbd);
+}
+
 static const struct block_device_operations nbd_fops =
 {
 	.owner =	THIS_MODULE,
+	.open =		nbd_open,
+	.release =	nbd_release,
 	.ioctl =	nbd_ioctl,
 	.compat_ioctl =	nbd_ioctl,
 };
@@ -927,7 +1296,7 @@ static const struct file_operations nbd_dbg_tasks_ops = {
 static int nbd_dbg_flags_show(struct seq_file *s, void *unused)
 {
 	struct nbd_device *nbd = s->private;
-	u32 flags = nbd->flags;
+	u32 flags = nbd->config->flags;
 
 	seq_printf(s, "Hex: 0x%08x\n\n", flags);
 
@@ -960,6 +1329,7 @@ static const struct file_operations nbd_dbg_flags_ops = {
 static int nbd_dev_dbg_init(struct nbd_device *nbd)
 {
 	struct dentry *dir;
+	struct nbd_config *config = nbd->config;
 
 	if (!nbd_dbg_dir)
 		return -EIO;
@@ -970,12 +1340,12 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd)
 			nbd_name(nbd));
 		return -EIO;
 	}
-	nbd->dbg_dir = dir;
+	config->dbg_dir = dir;
 
 	debugfs_create_file("tasks", 0444, dir, nbd, &nbd_dbg_tasks_ops);
-	debugfs_create_u64("size_bytes", 0444, dir, &nbd->bytesize);
+	debugfs_create_u64("size_bytes", 0444, dir, &config->bytesize);
 	debugfs_create_u32("timeout", 0444, dir, &nbd->tag_set.timeout);
-	debugfs_create_u64("blocksize", 0444, dir, &nbd->blksize);
+	debugfs_create_u64("blocksize", 0444, dir, &config->blksize);
 	debugfs_create_file("flags", 0444, dir, nbd, &nbd_dbg_flags_ops);
 
 	return 0;
@@ -983,7 +1353,7 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd)
 
 static void nbd_dev_dbg_close(struct nbd_device *nbd)
 {
-	debugfs_remove_recursive(nbd->dbg_dir);
+	debugfs_remove_recursive(nbd->config->dbg_dir);
 }
 
 static int nbd_dbg_init(void)
@@ -1035,25 +1405,13 @@ static int nbd_init_request(void *data, struct request *rq,
 	return 0;
 }
 
-static struct blk_mq_ops nbd_mq_ops = {
+static const struct blk_mq_ops nbd_mq_ops = {
 	.queue_rq	= nbd_queue_rq,
+	.complete	= nbd_complete_rq,
 	.init_request	= nbd_init_request,
 	.timeout	= nbd_xmit_timeout,
 };
 
-static void nbd_dev_remove(struct nbd_device *nbd)
-{
-	struct gendisk *disk = nbd->disk;
-	nbd->magic = 0;
-	if (disk) {
-		del_gendisk(disk);
-		blk_cleanup_queue(disk->queue);
-		blk_mq_free_tag_set(&nbd->tag_set);
-		put_disk(disk);
-	}
-	kfree(nbd);
-}
-
 static int nbd_dev_add(int index)
 {
 	struct nbd_device *nbd;
@@ -1082,6 +1440,7 @@ static int nbd_dev_add(int index)
 	if (err < 0)
 		goto out_free_disk;
 
+	nbd->index = index;
 	nbd->disk = disk;
 	nbd->tag_set.ops = &nbd_mq_ops;
 	nbd->tag_set.nr_hw_queues = 1;
@@ -1110,20 +1469,23 @@ static int nbd_dev_add(int index)
 	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, disk->queue);
 	disk->queue->limits.discard_granularity = 512;
 	blk_queue_max_discard_sectors(disk->queue, UINT_MAX);
-	disk->queue->limits.discard_zeroes_data = 0;
+	blk_queue_max_segment_size(disk->queue, UINT_MAX);
+	blk_queue_max_segments(disk->queue, USHRT_MAX);
 	blk_queue_max_hw_sectors(disk->queue, 65536);
 	disk->queue->limits.max_sectors = 256;
 
-	nbd->magic = NBD_MAGIC;
 	mutex_init(&nbd->config_lock);
+	refcount_set(&nbd->config_refs, 0);
+	refcount_set(&nbd->refs, 1);
+	INIT_LIST_HEAD(&nbd->list);
 	disk->major = NBD_MAJOR;
 	disk->first_minor = index << part_shift;
 	disk->fops = &nbd_fops;
 	disk->private_data = nbd;
 	sprintf(disk->disk_name, "nbd%d", index);
-	init_waitqueue_head(&nbd->recv_wq);
 	nbd_reset(nbd);
 	add_disk(disk);
+	nbd_total_devices++;
 	return index;
 
 out_free_tags:
@@ -1138,10 +1500,535 @@ out:
 	return err;
 }
 
-/*
- * And here should be modules and kernel interface 
- *  (Just smiley confuses emacs :-)
+static int find_free_cb(int id, void *ptr, void *data)
+{
+	struct nbd_device *nbd = ptr;
+	struct nbd_device **found = data;
+
+	if (!refcount_read(&nbd->config_refs)) {
+		*found = nbd;
+		return 1;
+	}
+	return 0;
+}
+
+/* Netlink interface. */
+static struct nla_policy nbd_attr_policy[NBD_ATTR_MAX + 1] = {
+	[NBD_ATTR_INDEX]		=	{ .type = NLA_U32 },
+	[NBD_ATTR_SIZE_BYTES]		=	{ .type = NLA_U64 },
+	[NBD_ATTR_BLOCK_SIZE_BYTES]	=	{ .type = NLA_U64 },
+	[NBD_ATTR_TIMEOUT]		=	{ .type = NLA_U64 },
+	[NBD_ATTR_SERVER_FLAGS]		=	{ .type = NLA_U64 },
+	[NBD_ATTR_CLIENT_FLAGS]		=	{ .type = NLA_U64 },
+	[NBD_ATTR_SOCKETS]		=	{ .type = NLA_NESTED},
+	[NBD_ATTR_DEAD_CONN_TIMEOUT]	=	{ .type = NLA_U64 },
+	[NBD_ATTR_DEVICE_LIST]		=	{ .type = NLA_NESTED},
+};
+
+static struct nla_policy nbd_sock_policy[NBD_SOCK_MAX + 1] = {
+	[NBD_SOCK_FD]			=	{ .type = NLA_U32 },
+};
+
+/* We don't use this right now since we don't parse the incoming list, but we
+ * still want it here so userspace knows what to expect.
  */
+static struct nla_policy __attribute__((unused))
+nbd_device_policy[NBD_DEVICE_ATTR_MAX + 1] = {
+	[NBD_DEVICE_INDEX]		=	{ .type = NLA_U32 },
+	[NBD_DEVICE_CONNECTED]		=	{ .type = NLA_U8 },
+};
+
+static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nbd_device *nbd = NULL;
+	struct nbd_config *config;
+	int index = -1;
+	int ret;
+	bool put_dev = false;
+
+	if (!netlink_capable(skb, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (info->attrs[NBD_ATTR_INDEX])
+		index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+	if (!info->attrs[NBD_ATTR_SOCKETS]) {
+		printk(KERN_ERR "nbd: must specify at least one socket\n");
+		return -EINVAL;
+	}
+	if (!info->attrs[NBD_ATTR_SIZE_BYTES]) {
+		printk(KERN_ERR "nbd: must specify a size in bytes for the device\n");
+		return -EINVAL;
+	}
+again:
+	mutex_lock(&nbd_index_mutex);
+	if (index == -1) {
+		ret = idr_for_each(&nbd_index_idr, &find_free_cb, &nbd);
+		if (ret == 0) {
+			int new_index;
+			new_index = nbd_dev_add(-1);
+			if (new_index < 0) {
+				mutex_unlock(&nbd_index_mutex);
+				printk(KERN_ERR "nbd: failed to add new device\n");
+				return ret;
+			}
+			nbd = idr_find(&nbd_index_idr, new_index);
+		}
+	} else {
+		nbd = idr_find(&nbd_index_idr, index);
+	}
+	if (!nbd) {
+		printk(KERN_ERR "nbd: couldn't find device at index %d\n",
+		       index);
+		mutex_unlock(&nbd_index_mutex);
+		return -EINVAL;
+	}
+	if (!refcount_inc_not_zero(&nbd->refs)) {
+		mutex_unlock(&nbd_index_mutex);
+		if (index == -1)
+			goto again;
+		printk(KERN_ERR "nbd: device at index %d is going down\n",
+		       index);
+		return -EINVAL;
+	}
+	mutex_unlock(&nbd_index_mutex);
+
+	mutex_lock(&nbd->config_lock);
+	if (refcount_read(&nbd->config_refs)) {
+		mutex_unlock(&nbd->config_lock);
+		nbd_put(nbd);
+		if (index == -1)
+			goto again;
+		printk(KERN_ERR "nbd: nbd%d already in use\n", index);
+		return -EBUSY;
+	}
+	if (WARN_ON(nbd->config)) {
+		mutex_unlock(&nbd->config_lock);
+		nbd_put(nbd);
+		return -EINVAL;
+	}
+	config = nbd->config = nbd_alloc_config();
+	if (!nbd->config) {
+		mutex_unlock(&nbd->config_lock);
+		nbd_put(nbd);
+		printk(KERN_ERR "nbd: couldn't allocate config\n");
+		return -ENOMEM;
+	}
+	refcount_set(&nbd->config_refs, 1);
+	set_bit(NBD_BOUND, &config->runtime_flags);
+
+	if (info->attrs[NBD_ATTR_SIZE_BYTES]) {
+		u64 bytes = nla_get_u64(info->attrs[NBD_ATTR_SIZE_BYTES]);
+		nbd_size_set(nbd, config->blksize,
+			     div64_u64(bytes, config->blksize));
+	}
+	if (info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]) {
+		u64 bsize =
+			nla_get_u64(info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]);
+		nbd_size_set(nbd, bsize, div64_u64(config->bytesize, bsize));
+	}
+	if (info->attrs[NBD_ATTR_TIMEOUT]) {
+		u64 timeout = nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT]);
+		nbd->tag_set.timeout = timeout * HZ;
+		blk_queue_rq_timeout(nbd->disk->queue, timeout * HZ);
+	}
+	if (info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]) {
+		config->dead_conn_timeout =
+			nla_get_u64(info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]);
+		config->dead_conn_timeout *= HZ;
+	}
+	if (info->attrs[NBD_ATTR_SERVER_FLAGS])
+		config->flags =
+			nla_get_u64(info->attrs[NBD_ATTR_SERVER_FLAGS]);
+	if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) {
+		u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]);
+		if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) {
+			set_bit(NBD_DESTROY_ON_DISCONNECT,
+				&config->runtime_flags);
+			put_dev = true;
+		}
+	}
+
+	if (info->attrs[NBD_ATTR_SOCKETS]) {
+		struct nlattr *attr;
+		int rem, fd;
+
+		nla_for_each_nested(attr, info->attrs[NBD_ATTR_SOCKETS],
+				    rem) {
+			struct nlattr *socks[NBD_SOCK_MAX+1];
+
+			if (nla_type(attr) != NBD_SOCK_ITEM) {
+				printk(KERN_ERR "nbd: socks must be embedded in a SOCK_ITEM attr\n");
+				ret = -EINVAL;
+				goto out;
+			}
+			ret = nla_parse_nested(socks, NBD_SOCK_MAX, attr,
+					       nbd_sock_policy);
+			if (ret != 0) {
+				printk(KERN_ERR "nbd: error processing sock list\n");
+				ret = -EINVAL;
+				goto out;
+			}
+			if (!socks[NBD_SOCK_FD])
+				continue;
+			fd = (int)nla_get_u32(socks[NBD_SOCK_FD]);
+			ret = nbd_add_socket(nbd, fd, true);
+			if (ret)
+				goto out;
+		}
+	}
+	ret = nbd_start_device(nbd);
+out:
+	mutex_unlock(&nbd->config_lock);
+	if (!ret) {
+		set_bit(NBD_HAS_CONFIG_REF, &config->runtime_flags);
+		refcount_inc(&nbd->config_refs);
+		nbd_connect_reply(info, nbd->index);
+	}
+	nbd_config_put(nbd);
+	if (put_dev)
+		nbd_put(nbd);
+	return ret;
+}
+
+static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nbd_device *nbd;
+	int index;
+
+	if (!netlink_capable(skb, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!info->attrs[NBD_ATTR_INDEX]) {
+		printk(KERN_ERR "nbd: must specify an index to disconnect\n");
+		return -EINVAL;
+	}
+	index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+	mutex_lock(&nbd_index_mutex);
+	nbd = idr_find(&nbd_index_idr, index);
+	if (!nbd) {
+		mutex_unlock(&nbd_index_mutex);
+		printk(KERN_ERR "nbd: couldn't find device at index %d\n",
+		       index);
+		return -EINVAL;
+	}
+	if (!refcount_inc_not_zero(&nbd->refs)) {
+		mutex_unlock(&nbd_index_mutex);
+		printk(KERN_ERR "nbd: device at index %d is going down\n",
+		       index);
+		return -EINVAL;
+	}
+	mutex_unlock(&nbd_index_mutex);
+	if (!refcount_inc_not_zero(&nbd->config_refs)) {
+		nbd_put(nbd);
+		return 0;
+	}
+	mutex_lock(&nbd->config_lock);
+	nbd_disconnect(nbd);
+	mutex_unlock(&nbd->config_lock);
+	if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
+			       &nbd->config->runtime_flags))
+		nbd_config_put(nbd);
+	nbd_config_put(nbd);
+	nbd_put(nbd);
+	return 0;
+}
+
+static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nbd_device *nbd = NULL;
+	struct nbd_config *config;
+	int index;
+	int ret = -EINVAL;
+	bool put_dev = false;
+
+	if (!netlink_capable(skb, CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (!info->attrs[NBD_ATTR_INDEX]) {
+		printk(KERN_ERR "nbd: must specify a device to reconfigure\n");
+		return -EINVAL;
+	}
+	index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+	mutex_lock(&nbd_index_mutex);
+	nbd = idr_find(&nbd_index_idr, index);
+	if (!nbd) {
+		mutex_unlock(&nbd_index_mutex);
+		printk(KERN_ERR "nbd: couldn't find a device at index %d\n",
+		       index);
+		return -EINVAL;
+	}
+	if (!refcount_inc_not_zero(&nbd->refs)) {
+		mutex_unlock(&nbd_index_mutex);
+		printk(KERN_ERR "nbd: device at index %d is going down\n",
+		       index);
+		return -EINVAL;
+	}
+	mutex_unlock(&nbd_index_mutex);
+
+	if (!refcount_inc_not_zero(&nbd->config_refs)) {
+		dev_err(nbd_to_dev(nbd),
+			"not configured, cannot reconfigure\n");
+		nbd_put(nbd);
+		return -EINVAL;
+	}
+
+	mutex_lock(&nbd->config_lock);
+	config = nbd->config;
+	if (!test_bit(NBD_BOUND, &config->runtime_flags) ||
+	    !nbd->task_recv) {
+		dev_err(nbd_to_dev(nbd),
+			"not configured, cannot reconfigure\n");
+		goto out;
+	}
+
+	if (info->attrs[NBD_ATTR_TIMEOUT]) {
+		u64 timeout = nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT]);
+		nbd->tag_set.timeout = timeout * HZ;
+		blk_queue_rq_timeout(nbd->disk->queue, timeout * HZ);
+	}
+	if (info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]) {
+		config->dead_conn_timeout =
+			nla_get_u64(info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]);
+		config->dead_conn_timeout *= HZ;
+	}
+	if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) {
+		u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]);
+		if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) {
+			if (!test_and_set_bit(NBD_DESTROY_ON_DISCONNECT,
+					      &config->runtime_flags))
+				put_dev = true;
+		} else {
+			if (test_and_clear_bit(NBD_DESTROY_ON_DISCONNECT,
+					       &config->runtime_flags))
+				refcount_inc(&nbd->refs);
+		}
+	}
+
+	if (info->attrs[NBD_ATTR_SOCKETS]) {
+		struct nlattr *attr;
+		int rem, fd;
+
+		nla_for_each_nested(attr, info->attrs[NBD_ATTR_SOCKETS],
+				    rem) {
+			struct nlattr *socks[NBD_SOCK_MAX+1];
+
+			if (nla_type(attr) != NBD_SOCK_ITEM) {
+				printk(KERN_ERR "nbd: socks must be embedded in a SOCK_ITEM attr\n");
+				ret = -EINVAL;
+				goto out;
+			}
+			ret = nla_parse_nested(socks, NBD_SOCK_MAX, attr,
+					       nbd_sock_policy);
+			if (ret != 0) {
+				printk(KERN_ERR "nbd: error processing sock list\n");
+				ret = -EINVAL;
+				goto out;
+			}
+			if (!socks[NBD_SOCK_FD])
+				continue;
+			fd = (int)nla_get_u32(socks[NBD_SOCK_FD]);
+			ret = nbd_reconnect_socket(nbd, fd);
+			if (ret) {
+				if (ret == -ENOSPC)
+					ret = 0;
+				goto out;
+			}
+			dev_info(nbd_to_dev(nbd), "reconnected socket\n");
+		}
+	}
+out:
+	mutex_unlock(&nbd->config_lock);
+	nbd_config_put(nbd);
+	nbd_put(nbd);
+	if (put_dev)
+		nbd_put(nbd);
+	return ret;
+}
+
+static const struct genl_ops nbd_connect_genl_ops[] = {
+	{
+		.cmd	= NBD_CMD_CONNECT,
+		.policy	= nbd_attr_policy,
+		.doit	= nbd_genl_connect,
+	},
+	{
+		.cmd	= NBD_CMD_DISCONNECT,
+		.policy	= nbd_attr_policy,
+		.doit	= nbd_genl_disconnect,
+	},
+	{
+		.cmd	= NBD_CMD_RECONFIGURE,
+		.policy	= nbd_attr_policy,
+		.doit	= nbd_genl_reconfigure,
+	},
+	{
+		.cmd	= NBD_CMD_STATUS,
+		.policy	= nbd_attr_policy,
+		.doit	= nbd_genl_status,
+	},
+};
+
+static const struct genl_multicast_group nbd_mcast_grps[] = {
+	{ .name = NBD_GENL_MCAST_GROUP_NAME, },
+};
+
+static struct genl_family nbd_genl_family __ro_after_init = {
+	.hdrsize	= 0,
+	.name		= NBD_GENL_FAMILY_NAME,
+	.version	= NBD_GENL_VERSION,
+	.module		= THIS_MODULE,
+	.ops		= nbd_connect_genl_ops,
+	.n_ops		= ARRAY_SIZE(nbd_connect_genl_ops),
+	.maxattr	= NBD_ATTR_MAX,
+	.mcgrps		= nbd_mcast_grps,
+	.n_mcgrps	= ARRAY_SIZE(nbd_mcast_grps),
+};
+
+static int populate_nbd_status(struct nbd_device *nbd, struct sk_buff *reply)
+{
+	struct nlattr *dev_opt;
+	u8 connected = 0;
+	int ret;
+
+	/* This is a little racey, but for status it's ok.  The
+	 * reason we don't take a ref here is because we can't
+	 * take a ref in the index == -1 case as we would need
+	 * to put under the nbd_index_mutex, which could
+	 * deadlock if we are configured to remove ourselves
+	 * once we're disconnected.
+	 */
+	if (refcount_read(&nbd->config_refs))
+		connected = 1;
+	dev_opt = nla_nest_start(reply, NBD_DEVICE_ITEM);
+	if (!dev_opt)
+		return -EMSGSIZE;
+	ret = nla_put_u32(reply, NBD_DEVICE_INDEX, nbd->index);
+	if (ret)
+		return -EMSGSIZE;
+	ret = nla_put_u8(reply, NBD_DEVICE_CONNECTED,
+			 connected);
+	if (ret)
+		return -EMSGSIZE;
+	nla_nest_end(reply, dev_opt);
+	return 0;
+}
+
+static int status_cb(int id, void *ptr, void *data)
+{
+	struct nbd_device *nbd = ptr;
+	return populate_nbd_status(nbd, (struct sk_buff *)data);
+}
+
+static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr *dev_list;
+	struct sk_buff *reply;
+	void *reply_head;
+	size_t msg_size;
+	int index = -1;
+	int ret = -ENOMEM;
+
+	if (info->attrs[NBD_ATTR_INDEX])
+		index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+
+	mutex_lock(&nbd_index_mutex);
+
+	msg_size = nla_total_size(nla_attr_size(sizeof(u32)) +
+				  nla_attr_size(sizeof(u8)));
+	msg_size *= (index == -1) ? nbd_total_devices : 1;
+
+	reply = genlmsg_new(msg_size, GFP_KERNEL);
+	if (!reply)
+		goto out;
+	reply_head = genlmsg_put_reply(reply, info, &nbd_genl_family, 0,
+				       NBD_CMD_STATUS);
+	if (!reply_head) {
+		nlmsg_free(reply);
+		goto out;
+	}
+
+	dev_list = nla_nest_start(reply, NBD_ATTR_DEVICE_LIST);
+	if (index == -1) {
+		ret = idr_for_each(&nbd_index_idr, &status_cb, reply);
+		if (ret) {
+			nlmsg_free(reply);
+			goto out;
+		}
+	} else {
+		struct nbd_device *nbd;
+		nbd = idr_find(&nbd_index_idr, index);
+		if (nbd) {
+			ret = populate_nbd_status(nbd, reply);
+			if (ret) {
+				nlmsg_free(reply);
+				goto out;
+			}
+		}
+	}
+	nla_nest_end(reply, dev_list);
+	genlmsg_end(reply, reply_head);
+	genlmsg_reply(reply, info);
+	ret = 0;
+out:
+	mutex_unlock(&nbd_index_mutex);
+	return ret;
+}
+
+static void nbd_connect_reply(struct genl_info *info, int index)
+{
+	struct sk_buff *skb;
+	void *msg_head;
+	int ret;
+
+	skb = genlmsg_new(nla_total_size(sizeof(u32)), GFP_KERNEL);
+	if (!skb)
+		return;
+	msg_head = genlmsg_put_reply(skb, info, &nbd_genl_family, 0,
+				     NBD_CMD_CONNECT);
+	if (!msg_head) {
+		nlmsg_free(skb);
+		return;
+	}
+	ret = nla_put_u32(skb, NBD_ATTR_INDEX, index);
+	if (ret) {
+		nlmsg_free(skb);
+		return;
+	}
+	genlmsg_end(skb, msg_head);
+	genlmsg_reply(skb, info);
+}
+
+static void nbd_mcast_index(int index)
+{
+	struct sk_buff *skb;
+	void *msg_head;
+	int ret;
+
+	skb = genlmsg_new(nla_total_size(sizeof(u32)), GFP_KERNEL);
+	if (!skb)
+		return;
+	msg_head = genlmsg_put(skb, 0, 0, &nbd_genl_family, 0,
+				     NBD_CMD_LINK_DEAD);
+	if (!msg_head) {
+		nlmsg_free(skb);
+		return;
+	}
+	ret = nla_put_u32(skb, NBD_ATTR_INDEX, index);
+	if (ret) {
+		nlmsg_free(skb);
+		return;
+	}
+	genlmsg_end(skb, msg_head);
+	genlmsg_multicast(&nbd_genl_family, skb, 0, 0, GFP_KERNEL);
+}
+
+static void nbd_dead_link_work(struct work_struct *work)
+{
+	struct link_dead_args *args = container_of(work, struct link_dead_args,
+						   work);
+	nbd_mcast_index(args->index);
+	kfree(args);
+}
 
 static int __init nbd_init(void)
 {
@@ -1184,6 +2071,11 @@ static int __init nbd_init(void)
 		return -EIO;
 	}
 
+	if (genl_register_family(&nbd_genl_family)) {
+		unregister_blkdev(NBD_MAJOR, "nbd");
+		destroy_workqueue(recv_workqueue);
+		return -EINVAL;
+	}
 	nbd_dbg_init();
 
 	mutex_lock(&nbd_index_mutex);
@@ -1195,17 +2087,34 @@ static int __init nbd_init(void)
 
 static int nbd_exit_cb(int id, void *ptr, void *data)
 {
+	struct list_head *list = (struct list_head *)data;
 	struct nbd_device *nbd = ptr;
-	nbd_dev_remove(nbd);
+
+	list_add_tail(&nbd->list, list);
 	return 0;
 }
 
 static void __exit nbd_cleanup(void)
 {
+	struct nbd_device *nbd;
+	LIST_HEAD(del_list);
+
 	nbd_dbg_close();
 
-	idr_for_each(&nbd_index_idr, &nbd_exit_cb, NULL);
+	mutex_lock(&nbd_index_mutex);
+	idr_for_each(&nbd_index_idr, &nbd_exit_cb, &del_list);
+	mutex_unlock(&nbd_index_mutex);
+
+	while (!list_empty(&del_list)) {
+		nbd = list_first_entry(&del_list, struct nbd_device, list);
+		list_del_init(&nbd->list);
+		if (refcount_read(&nbd->refs) != 1)
+			printk(KERN_ERR "nbd: possibly leaking a device\n");
+		nbd_put(nbd);
+	}
+
 	idr_destroy(&nbd_index_idr);
+	genl_unregister_family(&nbd_genl_family);
 	destroy_workqueue(recv_workqueue);
 	unregister_blkdev(NBD_MAJOR, "nbd");
 }

drivers/block/null_blk.c

@@ -117,6 +117,10 @@ static bool use_lightnvm;
 module_param(use_lightnvm, bool, S_IRUGO);
 MODULE_PARM_DESC(use_lightnvm, "Register as a LightNVM device");
 
+static bool blocking;
+module_param(blocking, bool, S_IRUGO);
+MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device");
+
 static int irqmode = NULL_IRQ_SOFTIRQ;
 
 static int null_set_irqmode(const char *str, const struct kernel_param *kp)
@@ -277,7 +281,7 @@ static inline void null_handle_cmd(struct nullb_cmd *cmd)
 	case NULL_IRQ_SOFTIRQ:
 		switch (queue_mode)  {
 		case NULL_Q_MQ:
-			blk_mq_complete_request(cmd->rq, cmd->rq->errors);
+			blk_mq_complete_request(cmd->rq);
 			break;
 		case NULL_Q_RQ:
 			blk_complete_request(cmd->rq);
@@ -357,6 +361,8 @@ static int null_queue_rq(struct blk_mq_hw_ctx *hctx,
 {
 	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
 
+	might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);
+
 	if (irqmode == NULL_IRQ_TIMER) {
 		hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 		cmd->timer.function = null_cmd_timer_expired;
@@ -392,7 +398,7 @@ static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
 	return 0;
 }
 
-static struct blk_mq_ops null_mq_ops = {
+static const struct blk_mq_ops null_mq_ops = {
 	.queue_rq       = null_queue_rq,
 	.init_hctx	= null_init_hctx,
 	.complete	= null_softirq_done_fn,
@@ -437,14 +443,7 @@ static int null_lnvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
 	if (IS_ERR(rq))
 		return -ENOMEM;
 
-	rq->__sector = bio->bi_iter.bi_sector;
-	rq->ioprio = bio_prio(bio);
-
-	if (bio_has_data(bio))
-		rq->nr_phys_segments = bio_phys_segments(q, bio);
-
-	rq->__data_len = bio->bi_iter.bi_size;
-	rq->bio = rq->biotail = bio;
+	blk_init_request_from_bio(rq, bio);
 
 	rq->end_io_data = rqd;
 
@@ -724,6 +723,9 @@ static int null_add_dev(void)
 		nullb->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
 		nullb->tag_set.driver_data = nullb;
 
+		if (blocking)
+			nullb->tag_set.flags |= BLK_MQ_F_BLOCKING;
+
 		rv = blk_mq_alloc_tag_set(&nullb->tag_set);
 		if (rv)
 			goto out_cleanup_queues;

drivers/block/osdblk.c

@@ -1,693 +0,0 @@
-
-/*
-   osdblk.c -- Export a single SCSI OSD object as a Linux block device
-
-
-   Copyright 2009 Red Hat, Inc.
-
-   This program is free software; you can redistribute it and/or modify
-   it under the terms of the GNU General Public License as published by
-   the Free Software Foundation.
-
-   This program is distributed in the hope that it will be useful,
-   but WITHOUT ANY WARRANTY; without even the implied warranty of
-   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-   GNU General Public License for more details.
-
-   You should have received a copy of the GNU General Public License
-   along with this program; see the file COPYING.  If not, write to
-   the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
-
-
-   Instructions for use
-   --------------------
-
-   1) Map a Linux block device to an existing OSD object.
-
-      In this example, we will use partition id 1234, object id 5678,
-      OSD device /dev/osd1.
-
-      $ echo "1234 5678 /dev/osd1" > /sys/class/osdblk/add
-
-
-   2) List all active blkdev<->object mappings.
-
-      In this example, we have performed step #1 twice, creating two blkdevs,
-      mapped to two separate OSD objects.
-
-      $ cat /sys/class/osdblk/list
-      0 174 1234 5678 /dev/osd1
-      1 179 1994 897123 /dev/osd0
-
-      The columns, in order, are:
-      - blkdev unique id
-      - blkdev assigned major
-      - OSD object partition id
-      - OSD object id
-      - OSD device
-
-
-   3) Remove an active blkdev<->object mapping.
-
-      In this example, we remove the mapping with blkdev unique id 1.
-
-      $ echo 1 > /sys/class/osdblk/remove
-
-
-   NOTE:  The actual creation and deletion of OSD objects is outside the scope
-   of this driver.
-
- */
-
-#include <linux/kernel.h>
-#include <linux/device.h>
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include <scsi/osd_initiator.h>
-#include <scsi/osd_attributes.h>
-#include <scsi/osd_sec.h>
-#include <scsi/scsi_device.h>
-
-#define DRV_NAME "osdblk"
-#define PFX DRV_NAME ": "
-
-/* #define _OSDBLK_DEBUG */
-#ifdef _OSDBLK_DEBUG
-#define OSDBLK_DEBUG(fmt, a...) \
-	printk(KERN_NOTICE "osdblk @%s:%d: " fmt, __func__, __LINE__, ##a)
-#else
-#define OSDBLK_DEBUG(fmt, a...) \
-	do { if (0) printk(fmt, ##a); } while (0)
-#endif
-
-MODULE_AUTHOR("Jeff Garzik <jeff@garzik.org>");
-MODULE_DESCRIPTION("block device inside an OSD object osdblk.ko");
-MODULE_LICENSE("GPL");
-
-struct osdblk_device;
-
-enum {
-	OSDBLK_MINORS_PER_MAJOR	= 256,		/* max minors per blkdev */
-	OSDBLK_MAX_REQ		= 32,		/* max parallel requests */
-	OSDBLK_OP_TIMEOUT	= 4 * 60,	/* sync OSD req timeout */
-};
-
-struct osdblk_request {
-	struct request		*rq;		/* blk layer request */
-	struct bio		*bio;		/* cloned bio */
-	struct osdblk_device	*osdev;		/* associated blkdev */
-};
-
-struct osdblk_device {
-	int			id;		/* blkdev unique id */
-
-	int			major;		/* blkdev assigned major */
-	struct gendisk		*disk;		/* blkdev's gendisk and rq */
-	struct request_queue	*q;
-
-	struct osd_dev		*osd;		/* associated OSD */
-
-	char			name[32];	/* blkdev name, e.g. osdblk34 */
-
-	spinlock_t		lock;		/* queue lock */
-
-	struct osd_obj_id	obj;		/* OSD partition, obj id */
-	uint8_t			obj_cred[OSD_CAP_LEN]; /* OSD cred */
-
-	struct osdblk_request	req[OSDBLK_MAX_REQ]; /* request table */
-
-	struct list_head	node;
-
-	char			osd_path[0];	/* OSD device path */
-};
-
-static struct class *class_osdblk;		/* /sys/class/osdblk */
-static DEFINE_MUTEX(ctl_mutex);	/* Serialize open/close/setup/teardown */
-static LIST_HEAD(osdblkdev_list);
-
-static const struct block_device_operations osdblk_bd_ops = {
-	.owner		= THIS_MODULE,
-};
-
-static const struct osd_attr g_attr_logical_length = ATTR_DEF(
-	OSD_APAGE_OBJECT_INFORMATION, OSD_ATTR_OI_LOGICAL_LENGTH, 8);
-
-static void osdblk_make_credential(u8 cred_a[OSD_CAP_LEN],
-				   const struct osd_obj_id *obj)
-{
-	osd_sec_init_nosec_doall_caps(cred_a, obj, false, true);
-}
-
-/* copied from exofs; move to libosd? */
-/*
- * Perform a synchronous OSD operation.  copied from exofs; move to libosd?
- */
-static int osd_sync_op(struct osd_request *or, int timeout, uint8_t *credential)
-{
-	int ret;
-
-	or->timeout = timeout;
-	ret = osd_finalize_request(or, 0, credential, NULL);
-	if (ret)
-		return ret;
-
-	ret = osd_execute_request(or);
-
-	/* osd_req_decode_sense(or, ret); */
-	return ret;
-}
-
-/*
- * Perform an asynchronous OSD operation.  copied from exofs; move to libosd?
- */
-static int osd_async_op(struct osd_request *or, osd_req_done_fn *async_done,
-		   void *caller_context, u8 *cred)
-{
-	int ret;
-
-	ret = osd_finalize_request(or, 0, cred, NULL);
-	if (ret)
-		return ret;
-
-	ret = osd_execute_request_async(or, async_done, caller_context);
-
-	return ret;
-}
-
-/* copied from exofs; move to libosd? */
-static int extract_attr_from_req(struct osd_request *or, struct osd_attr *attr)
-{
-	struct osd_attr cur_attr = {.attr_page = 0}; /* start with zeros */
-	void *iter = NULL;
-	int nelem;
-
-	do {
-		nelem = 1;
-		osd_req_decode_get_attr_list(or, &cur_attr, &nelem, &iter);
-		if ((cur_attr.attr_page == attr->attr_page) &&
-		    (cur_attr.attr_id == attr->attr_id)) {
-			attr->len = cur_attr.len;
-			attr->val_ptr = cur_attr.val_ptr;
-			return 0;
-		}
-	} while (iter);
-
-	return -EIO;
-}
-
-static int osdblk_get_obj_size(struct osdblk_device *osdev, u64 *size_out)
-{
-	struct osd_request *or;
-	struct osd_attr attr;
-	int ret;
-
-	/* start request */
-	or = osd_start_request(osdev->osd, GFP_KERNEL);
-	if (!or)
-		return -ENOMEM;
-
-	/* create a get-attributes(length) request */
-	osd_req_get_attributes(or, &osdev->obj);
-
-	osd_req_add_get_attr_list(or, &g_attr_logical_length, 1);
-
-	/* execute op synchronously */
-	ret = osd_sync_op(or, OSDBLK_OP_TIMEOUT, osdev->obj_cred);
-	if (ret)
-		goto out;
-
-	/* extract length from returned attribute info */
-	attr = g_attr_logical_length;
-	ret = extract_attr_from_req(or, &attr);
-	if (ret)
-		goto out;
-
-	*size_out = get_unaligned_be64(attr.val_ptr);
-
-out:
-	osd_end_request(or);
-	return ret;
-
-}
-
-static void osdblk_osd_complete(struct osd_request *or, void *private)
-{
-	struct osdblk_request *orq = private;
-	struct osd_sense_info osi;
-	int ret = osd_req_decode_sense(or, &osi);
-
-	if (ret) {
-		ret = -EIO;
-		OSDBLK_DEBUG("osdblk_osd_complete with err=%d\n", ret);
-	}
-
-	/* complete OSD request */
-	osd_end_request(or);
-
-	/* complete request passed to osdblk by block layer */
-	__blk_end_request_all(orq->rq, ret);
-}
-
-static void bio_chain_put(struct bio *chain)
-{
-	struct bio *tmp;
-
-	while (chain) {
-		tmp = chain;
-		chain = chain->bi_next;
-
-		bio_put(tmp);
-	}
-}
-
-static struct bio *bio_chain_clone(struct bio *old_chain, gfp_t gfpmask)
-{
-	struct bio *tmp, *new_chain = NULL, *tail = NULL;
-
-	while (old_chain) {
-		tmp = bio_clone_kmalloc(old_chain, gfpmask);
-		if (!tmp)
-			goto err_out;
-
-		tmp->bi_bdev = NULL;
-		gfpmask &= ~__GFP_DIRECT_RECLAIM;
-		tmp->bi_next = NULL;
-
-		if (!new_chain)
-			new_chain = tail = tmp;
-		else {
-			tail->bi_next = tmp;
-			tail = tmp;
-		}
-
-		old_chain = old_chain->bi_next;
-	}
-
-	return new_chain;
-
-err_out:
-	OSDBLK_DEBUG("bio_chain_clone with err\n");
-	bio_chain_put(new_chain);
-	return NULL;
-}
-
-static void osdblk_rq_fn(struct request_queue *q)
-{
-	struct osdblk_device *osdev = q->queuedata;
-
-	while (1) {
-		struct request *rq;
-		struct osdblk_request *orq;
-		struct osd_request *or;
-		struct bio *bio;
-		bool do_write, do_flush;
-
-		/* peek at request from block layer */
-		rq = blk_fetch_request(q);
-		if (!rq)
-			break;
-
-		/* deduce our operation (read, write, flush) */
-		/* I wish the block layer simplified cmd_type/cmd_flags/cmd[]
-		 * into a clearly defined set of RPC commands:
-		 * read, write, flush, scsi command, power mgmt req,
-		 * driver-specific, etc.
-		 */
-
-		do_flush = (req_op(rq) == REQ_OP_FLUSH);
-		do_write = (rq_data_dir(rq) == WRITE);
-
-		if (!do_flush) { /* osd_flush does not use a bio */
-			/* a bio clone to be passed down to OSD request */
-			bio = bio_chain_clone(rq->bio, GFP_ATOMIC);
-			if (!bio)
-				break;
-		} else
-			bio = NULL;
-
-		/* alloc internal OSD request, for OSD command execution */
-		or = osd_start_request(osdev->osd, GFP_ATOMIC);
-		if (!or) {
-			bio_chain_put(bio);
-			OSDBLK_DEBUG("osd_start_request with err\n");
-			break;
-		}
-
-		orq = &osdev->req[rq->tag];
-		orq->rq = rq;
-		orq->bio = bio;
-		orq->osdev = osdev;
-
-		/* init OSD command: flush, write or read */
-		if (do_flush)
-			osd_req_flush_object(or, &osdev->obj,
-					     OSD_CDB_FLUSH_ALL, 0, 0);
-		else if (do_write)
-			osd_req_write(or, &osdev->obj, blk_rq_pos(rq) * 512ULL,
-				      bio, blk_rq_bytes(rq));
-		else
-			osd_req_read(or, &osdev->obj, blk_rq_pos(rq) * 512ULL,
-				     bio, blk_rq_bytes(rq));
-
-		OSDBLK_DEBUG("%s 0x%x bytes at 0x%llx\n",
-			do_flush ? "flush" : do_write ?
-				"write" : "read", blk_rq_bytes(rq),
-			blk_rq_pos(rq) * 512ULL);
-
-		/* begin OSD command execution */
-		if (osd_async_op(or, osdblk_osd_complete, orq,
-				 osdev->obj_cred)) {
-			osd_end_request(or);
-			blk_requeue_request(q, rq);
-			bio_chain_put(bio);
-			OSDBLK_DEBUG("osd_execute_request_async with err\n");
-			break;
-		}
-
-		/* remove the special 'flush' marker, now that the command
-		 * is executing
-		 */
-		rq->special = NULL;
-	}
-}
-
-static void osdblk_free_disk(struct osdblk_device *osdev)
-{
-	struct gendisk *disk = osdev->disk;
-
-	if (!disk)
-		return;
-
-	if (disk->flags & GENHD_FL_UP)
-		del_gendisk(disk);
-	if (disk->queue)
-		blk_cleanup_queue(disk->queue);
-	put_disk(disk);
-}
-
-static int osdblk_init_disk(struct osdblk_device *osdev)
-{
-	struct gendisk *disk;
-	struct request_queue *q;
-	int rc;
-	u64 obj_size = 0;
-
-	/* contact OSD, request size info about the object being mapped */
-	rc = osdblk_get_obj_size(osdev, &obj_size);
-	if (rc)
-		return rc;
-
-	/* create gendisk info */
-	disk = alloc_disk(OSDBLK_MINORS_PER_MAJOR);
-	if (!disk)
-		return -ENOMEM;
-
-	sprintf(disk->disk_name, DRV_NAME "%d", osdev->id);
-	disk->major = osdev->major;
-	disk->first_minor = 0;
-	disk->fops = &osdblk_bd_ops;
-	disk->private_data = osdev;
-
-	/* init rq */
-	q = blk_init_queue(osdblk_rq_fn, &osdev->lock);
-	if (!q) {
-		put_disk(disk);
-		return -ENOMEM;
-	}
-
-	/* switch queue to TCQ mode; allocate tag map */
-	rc = blk_queue_init_tags(q, OSDBLK_MAX_REQ, NULL, BLK_TAG_ALLOC_FIFO);
-	if (rc) {
-		blk_cleanup_queue(q);
-		put_disk(disk);
-		return rc;
-	}
-
-	/* Set our limits to the lower device limits, because osdblk cannot
-	 * sleep when allocating a lower-request and therefore cannot be
-	 * bouncing.
-	 */
-	blk_queue_stack_limits(q, osd_request_queue(osdev->osd));
-
-	blk_queue_prep_rq(q, blk_queue_start_tag);
-	blk_queue_write_cache(q, true, false);
-
-	disk->queue = q;
-
-	q->queuedata = osdev;
-
-	osdev->disk = disk;
-	osdev->q = q;
-
-	/* finally, announce the disk to the world */
-	set_capacity(disk, obj_size / 512ULL);
-	add_disk(disk);
-
-	printk(KERN_INFO "%s: Added of size 0x%llx\n",
-		disk->disk_name, (unsigned long long)obj_size);
-
-	return 0;
-}
-
-/********************************************************************
- * /sys/class/osdblk/
- *                   add	map OSD object to blkdev
- *                   remove	unmap OSD object
- *                   list	show mappings
- *******************************************************************/
-
-static void class_osdblk_release(struct class *cls)
-{
-	kfree(cls);
-}
-
-static ssize_t class_osdblk_list(struct class *c,
-				struct class_attribute *attr,
-				char *data)
-{
-	int n = 0;
-	struct list_head *tmp;
-
-	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
-	list_for_each(tmp, &osdblkdev_list) {
-		struct osdblk_device *osdev;
-
-		osdev = list_entry(tmp, struct osdblk_device, node);
-
-		n += sprintf(data+n, "%d %d %llu %llu %s\n",
-			osdev->id,
-			osdev->major,
-			osdev->obj.partition,
-			osdev->obj.id,
-			osdev->osd_path);
-	}
-
-	mutex_unlock(&ctl_mutex);
-	return n;
-}
-
-static ssize_t class_osdblk_add(struct class *c,
-				struct class_attribute *attr,
-				const char *buf, size_t count)
-{
-	struct osdblk_device *osdev;
-	ssize_t rc;
-	int irc, new_id = 0;
-	struct list_head *tmp;
-
-	if (!try_module_get(THIS_MODULE))
-		return -ENODEV;
-
-	/* new osdblk_device object */
-	osdev = kzalloc(sizeof(*osdev) + strlen(buf) + 1, GFP_KERNEL);
-	if (!osdev) {
-		rc = -ENOMEM;
-		goto err_out_mod;
-	}
-
-	/* static osdblk_device initialization */
-	spin_lock_init(&osdev->lock);
-	INIT_LIST_HEAD(&osdev->node);
-
-	/* generate unique id: find highest unique id, add one */
-
-	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
-	list_for_each(tmp, &osdblkdev_list) {
-		struct osdblk_device *osdev;
-
-		osdev = list_entry(tmp, struct osdblk_device, node);
-		if (osdev->id > new_id)
-			new_id = osdev->id + 1;
-	}
-
-	osdev->id = new_id;
-
-	/* add to global list */
-	list_add_tail(&osdev->node, &osdblkdev_list);
-
-	mutex_unlock(&ctl_mutex);
-
-	/* parse add command */
-	if (sscanf(buf, "%llu %llu %s", &osdev->obj.partition, &osdev->obj.id,
-		   osdev->osd_path) != 3) {
-		rc = -EINVAL;
-		goto err_out_slot;
-	}
-
-	/* initialize rest of new object */
-	sprintf(osdev->name, DRV_NAME "%d", osdev->id);
-
-	/* contact requested OSD */
-	osdev->osd = osduld_path_lookup(osdev->osd_path);
-	if (IS_ERR(osdev->osd)) {
-		rc = PTR_ERR(osdev->osd);
-		goto err_out_slot;
-	}
-
-	/* build OSD credential */
-	osdblk_make_credential(osdev->obj_cred, &osdev->obj);
-
-	/* register our block device */
-	irc = register_blkdev(0, osdev->name);
-	if (irc < 0) {
-		rc = irc;
-		goto err_out_osd;
-	}
-
-	osdev->major = irc;
-
-	/* set up and announce blkdev mapping */
-	rc = osdblk_init_disk(osdev);
-	if (rc)
-		goto err_out_blkdev;
-
-	return count;
-
-err_out_blkdev:
-	unregister_blkdev(osdev->major, osdev->name);
-err_out_osd:
-	osduld_put_device(osdev->osd);
-err_out_slot:
-	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-	list_del_init(&osdev->node);
-	mutex_unlock(&ctl_mutex);
-
-	kfree(osdev);
-err_out_mod:
-	OSDBLK_DEBUG("Error adding device %s\n", buf);
-	module_put(THIS_MODULE);
-	return rc;
-}
-
-static ssize_t class_osdblk_remove(struct class *c,
-					struct class_attribute *attr,
-					const char *buf,
-					size_t count)
-{
-	struct osdblk_device *osdev = NULL;
-	int target_id, rc;
-	unsigned long ul;
-	struct list_head *tmp;
-
-	rc = kstrtoul(buf, 10, &ul);
-	if (rc)
-		return rc;
-
-	/* convert to int; abort if we lost anything in the conversion */
-	target_id = (int) ul;
-	if (target_id != ul)
-		return -EINVAL;
-
-	/* remove object from list immediately */
-	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
-	list_for_each(tmp, &osdblkdev_list) {
-		osdev = list_entry(tmp, struct osdblk_device, node);
-		if (osdev->id == target_id) {
-			list_del_init(&osdev->node);
-			break;
-		}
-		osdev = NULL;
-	}
-
-	mutex_unlock(&ctl_mutex);
-
-	if (!osdev)
-		return -ENOENT;
-
-	/* clean up and free blkdev and associated OSD connection */
-	osdblk_free_disk(osdev);
-	unregister_blkdev(osdev->major, osdev->name);
-	osduld_put_device(osdev->osd);
-	kfree(osdev);
-
-	/* release module ref */
-	module_put(THIS_MODULE);
-
-	return count;
-}
-
-static struct class_attribute class_osdblk_attrs[] = {
-	__ATTR(add,	0200, NULL, class_osdblk_add),
-	__ATTR(remove,	0200, NULL, class_osdblk_remove),
-	__ATTR(list,	0444, class_osdblk_list, NULL),
-	__ATTR_NULL
-};
-
-static int osdblk_sysfs_init(void)
-{
-	int ret = 0;
-
-	/*
-	 * create control files in sysfs
-	 * /sys/class/osdblk/...
-	 */
-	class_osdblk = kzalloc(sizeof(*class_osdblk), GFP_KERNEL);
-	if (!class_osdblk)
-		return -ENOMEM;
-
-	class_osdblk->name = DRV_NAME;
-	class_osdblk->owner = THIS_MODULE;
-	class_osdblk->class_release = class_osdblk_release;
-	class_osdblk->class_attrs = class_osdblk_attrs;
-
-	ret = class_register(class_osdblk);
-	if (ret) {
-		kfree(class_osdblk);
-		class_osdblk = NULL;
-		printk(PFX "failed to create class osdblk\n");
-		return ret;
-	}
-
-	return 0;
-}
-
-static void osdblk_sysfs_cleanup(void)
-{
-	if (class_osdblk)
-		class_destroy(class_osdblk);
-	class_osdblk = NULL;
-}
-
-static int __init osdblk_init(void)
-{
-	int rc;
-
-	rc = osdblk_sysfs_init();
-	if (rc)
-		return rc;
-
-	return 0;
-}
-
-static void __exit osdblk_exit(void)
-{
-	osdblk_sysfs_cleanup();
-}
-
-module_init(osdblk_init);
-module_exit(osdblk_exit);
-

drivers/block/paride/pcd.c

@@ -300,6 +300,11 @@ static void pcd_init_units(void)
 		struct gendisk *disk = alloc_disk(1);
 		if (!disk)
 			continue;
+		disk->queue = blk_init_queue(do_pcd_request, &pcd_lock);
+		if (!disk->queue) {
+			put_disk(disk);
+			continue;
+		}
 		cd->disk = disk;
 		cd->pi = &cd->pia;
 		cd->present = 0;
@@ -735,18 +740,36 @@ static int pcd_detect(void)
 }
 
 /* I/O request processing */
-static struct request_queue *pcd_queue;
+static int pcd_queue;
+
+static int set_next_request(void)
+{
+	struct pcd_unit *cd;
+	struct request_queue *q;
+	int old_pos = pcd_queue;
+
+	do {
+		cd = &pcd[pcd_queue];
+		q = cd->present ? cd->disk->queue : NULL;
+		if (++pcd_queue == PCD_UNITS)
+			pcd_queue = 0;
+		if (q) {
+			pcd_req = blk_fetch_request(q);
+			if (pcd_req)
+				break;
+		}
+	} while (pcd_queue != old_pos);
+
+	return pcd_req != NULL;
+}
 
-static void do_pcd_request(struct request_queue * q)
+static void pcd_request(void)
 {
 	if (pcd_busy)
 		return;
 	while (1) {
-		if (!pcd_req) {
-			pcd_req = blk_fetch_request(q);
-			if (!pcd_req)
-				return;
-		}
+		if (!pcd_req && !set_next_request())
+			return;
 
 		if (rq_data_dir(pcd_req) == READ) {
 			struct pcd_unit *cd = pcd_req->rq_disk->private_data;
@@ -766,6 +789,11 @@ static void do_pcd_request(struct request_queue * q)
 	}
 }
 
+static void do_pcd_request(struct request_queue *q)
+{
+	pcd_request();
+}
+
 static inline void next_request(int err)
 {
 	unsigned long saved_flags;
@@ -774,7 +802,7 @@ static inline void next_request(int err)
 	if (!__blk_end_request_cur(pcd_req, err))
 		pcd_req = NULL;
 	pcd_busy = 0;
-	do_pcd_request(pcd_queue);
+	pcd_request();
 	spin_unlock_irqrestore(&pcd_lock, saved_flags);
 }
 
@@ -849,7 +877,7 @@ static void do_pcd_read_drq(void)
 
 	do_pcd_read();
 	spin_lock_irqsave(&pcd_lock, saved_flags);
-	do_pcd_request(pcd_queue);
+	pcd_request();
 	spin_unlock_irqrestore(&pcd_lock, saved_flags);
 }
 
@@ -957,19 +985,10 @@ static int __init pcd_init(void)
 		return -EBUSY;
 	}
 
-	pcd_queue = blk_init_queue(do_pcd_request, &pcd_lock);
-	if (!pcd_queue) {
-		unregister_blkdev(major, name);
-		for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++)
-			put_disk(cd->disk);
-		return -ENOMEM;
-	}
-
 	for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
 		if (cd->present) {
 			register_cdrom(&cd->info);
 			cd->disk->private_data = cd;
-			cd->disk->queue = pcd_queue;
 			add_disk(cd->disk);
 		}
 	}
@@ -988,9 +1007,9 @@ static void __exit pcd_exit(void)
 			pi_release(cd->pi);
 			unregister_cdrom(&cd->info);
 		}
+		blk_cleanup_queue(cd->disk->queue);
 		put_disk(cd->disk);
 	}
-	blk_cleanup_queue(pcd_queue);
 	unregister_blkdev(major, name);
 	pi_unregister_driver(par_drv);
 }

drivers/block/paride/pd.c

@@ -381,12 +381,33 @@ static enum action do_pd_write_start(void);
 static enum action do_pd_read_drq(void);
 static enum action do_pd_write_done(void);
 
-static struct request_queue *pd_queue;
+static int pd_queue;
 static int pd_claimed;
 
 static struct pd_unit *pd_current; /* current request's drive */
 static PIA *pi_current; /* current request's PIA */
 
+static int set_next_request(void)
+{
+	struct gendisk *disk;
+	struct request_queue *q;
+	int old_pos = pd_queue;
+
+	do {
+		disk = pd[pd_queue].gd;
+		q = disk ? disk->queue : NULL;
+		if (++pd_queue == PD_UNITS)
+			pd_queue = 0;
+		if (q) {
+			pd_req = blk_fetch_request(q);
+			if (pd_req)
+				break;
+		}
+	} while (pd_queue != old_pos);
+
+	return pd_req != NULL;
+}
+
 static void run_fsm(void)
 {
 	while (1) {
@@ -418,8 +439,7 @@ static void run_fsm(void)
 				spin_lock_irqsave(&pd_lock, saved_flags);
 				if (!__blk_end_request_cur(pd_req,
 						res == Ok ? 0 : -EIO)) {
-					pd_req = blk_fetch_request(pd_queue);
-					if (!pd_req)
+					if (!set_next_request())
 						stop = 1;
 				}
 				spin_unlock_irqrestore(&pd_lock, saved_flags);
@@ -719,18 +739,15 @@ static int pd_special_command(struct pd_unit *disk,
 		      enum action (*func)(struct pd_unit *disk))
 {
 	struct request *rq;
-	int err = 0;
 
 	rq = blk_get_request(disk->gd->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 
 	rq->special = func;
-
-	err = blk_execute_rq(disk->gd->queue, disk->gd, rq, 0);
-
+	blk_execute_rq(disk->gd->queue, disk->gd, rq, 0);
 	blk_put_request(rq);
-	return err;
+	return 0;
 }
 
 /* kernel glue structures */
@@ -839,7 +856,13 @@ static void pd_probe_drive(struct pd_unit *disk)
 	p->first_minor = (disk - pd) << PD_BITS;
 	disk->gd = p;
 	p->private_data = disk;
-	p->queue = pd_queue;
+	p->queue = blk_init_queue(do_pd_request, &pd_lock);
+	if (!p->queue) {
+		disk->gd = NULL;
+		put_disk(p);
+		return;
+	}
+	blk_queue_max_hw_sectors(p->queue, cluster);
 
 	if (disk->drive == -1) {
 		for (disk->drive = 0; disk->drive <= 1; disk->drive++)
@@ -919,26 +942,18 @@ static int __init pd_init(void)
 	if (disable)
 		goto out1;
 
-	pd_queue = blk_init_queue(do_pd_request, &pd_lock);
-	if (!pd_queue)
-		goto out1;
-
-	blk_queue_max_hw_sectors(pd_queue, cluster);
-
 	if (register_blkdev(major, name))
-		goto out2;
+		goto out1;
 
 	printk("%s: %s version %s, major %d, cluster %d, nice %d\n",
 	       name, name, PD_VERSION, major, cluster, nice);
 	if (!pd_detect())
-		goto out3;
+		goto out2;
 
 	return 0;
 
-out3:
-	unregister_blkdev(major, name);
 out2:
-	blk_cleanup_queue(pd_queue);
+	unregister_blkdev(major, name);
 out1:
 	return -ENODEV;
 }
@@ -953,11 +968,11 @@ static void __exit pd_exit(void)
 		if (p) {
 			disk->gd = NULL;
 			del_gendisk(p);
+			blk_cleanup_queue(p->queue);
 			put_disk(p);
 			pi_release(disk->pi);
 		}
 	}
-	blk_cleanup_queue(pd_queue);
 }
 
 MODULE_LICENSE("GPL");

drivers/block/paride/pf.c

@@ -287,6 +287,12 @@ static void __init pf_init_units(void)
 		struct gendisk *disk = alloc_disk(1);
 		if (!disk)
 			continue;
+		disk->queue = blk_init_queue(do_pf_request, &pf_spin_lock);
+		if (!disk->queue) {
+			put_disk(disk);
+			return;
+		}
+		blk_queue_max_segments(disk->queue, cluster);
 		pf->disk = disk;
 		pf->pi = &pf->pia;
 		pf->media_status = PF_NM;
@@ -772,7 +778,28 @@ static int pf_ready(void)
 	return (((status_reg(pf_current) & (STAT_BUSY | pf_mask)) == pf_mask));
 }
 
-static struct request_queue *pf_queue;
+static int pf_queue;
+
+static int set_next_request(void)
+{
+	struct pf_unit *pf;
+	struct request_queue *q;
+	int old_pos = pf_queue;
+
+	do {
+		pf = &units[pf_queue];
+		q = pf->present ? pf->disk->queue : NULL;
+		if (++pf_queue == PF_UNITS)
+			pf_queue = 0;
+		if (q) {
+			pf_req = blk_fetch_request(q);
+			if (pf_req)
+				break;
+		}
+	} while (pf_queue != old_pos);
+
+	return pf_req != NULL;
+}
 
 static void pf_end_request(int err)
 {
@@ -780,16 +807,13 @@ static void pf_end_request(int err)
 		pf_req = NULL;
 }
 
-static void do_pf_request(struct request_queue * q)
+static void pf_request(void)
 {
 	if (pf_busy)
 		return;
 repeat:
-	if (!pf_req) {
-		pf_req = blk_fetch_request(q);
-		if (!pf_req)
-			return;
-	}
+	if (!pf_req && !set_next_request())
+		return;
 
 	pf_current = pf_req->rq_disk->private_data;
 	pf_block = blk_rq_pos(pf_req);
@@ -817,6 +841,11 @@ repeat:
 	}
 }
 
+static void do_pf_request(struct request_queue *q)
+{
+	pf_request();
+}
+
 static int pf_next_buf(void)
 {
 	unsigned long saved_flags;
@@ -846,7 +875,7 @@ static inline void next_request(int err)
 	spin_lock_irqsave(&pf_spin_lock, saved_flags);
 	pf_end_request(err);
 	pf_busy = 0;
-	do_pf_request(pf_queue);
+	pf_request();
 	spin_unlock_irqrestore(&pf_spin_lock, saved_flags);
 }
 
@@ -972,15 +1001,6 @@ static int __init pf_init(void)
 			put_disk(pf->disk);
 		return -EBUSY;
 	}
-	pf_queue = blk_init_queue(do_pf_request, &pf_spin_lock);
-	if (!pf_queue) {
-		unregister_blkdev(major, name);
-		for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++)
-			put_disk(pf->disk);
-		return -ENOMEM;
-	}
-
-	blk_queue_max_segments(pf_queue, cluster);
 
 	for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
 		struct gendisk *disk = pf->disk;
@@ -988,7 +1008,6 @@ static int __init pf_init(void)
 		if (!pf->present)
 			continue;
 		disk->private_data = pf;
-		disk->queue = pf_queue;
 		add_disk(disk);
 	}
 	return 0;
@@ -1003,10 +1022,10 @@ static void __exit pf_exit(void)
 		if (!pf->present)
 			continue;
 		del_gendisk(pf->disk);
+		blk_cleanup_queue(pf->disk->queue);
 		put_disk(pf->disk);
 		pi_release(pf->pi);
 	}
-	blk_cleanup_queue(pf_queue);
 }
 
 MODULE_LICENSE("GPL");

drivers/block/pktcdvd.c

@@ -724,7 +724,7 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
 		rq->rq_flags |= RQF_QUIET;
 
 	blk_execute_rq(rq->q, pd->bdev->bd_disk, rq, 0);
-	if (rq->errors)
+	if (scsi_req(rq)->result)
 		ret = -EIO;
 out:
 	blk_put_request(rq);

drivers/block/rbd.c

@@ -4317,7 +4317,7 @@ static int rbd_init_request(void *data, struct request *rq,
 	return 0;
 }
 
-static struct blk_mq_ops rbd_mq_ops = {
+static const struct blk_mq_ops rbd_mq_ops = {
 	.queue_rq	= rbd_queue_rq,
 	.init_request	= rbd_init_request,
 };
@@ -4380,7 +4380,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
 	q->limits.discard_granularity = segment_size;
 	q->limits.discard_alignment = segment_size;
 	blk_queue_max_discard_sectors(q, segment_size / SECTOR_SIZE);
-	q->limits.discard_zeroes_data = 1;
 
 	if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
 		q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;

drivers/block/rsxx/dev.c

@@ -300,7 +300,6 @@ int rsxx_setup_dev(struct rsxx_cardinfo *card)
 						RSXX_HW_BLK_SIZE >> 9);
 		card->queue->limits.discard_granularity = RSXX_HW_BLK_SIZE;
 		card->queue->limits.discard_alignment   = RSXX_HW_BLK_SIZE;
-		card->queue->limits.discard_zeroes_data = 1;
 	}
 
 	card->queue->queuedata = card;

drivers/block/swim.c

@@ -211,7 +211,7 @@ enum head {
 struct swim_priv {
 	struct swim __iomem *base;
 	spinlock_t lock;
-	struct request_queue *queue;
+	int fdc_queue;
 	int floppy_count;
 	struct floppy_state unit[FD_MAX_UNIT];
 };
@@ -525,12 +525,33 @@ static int floppy_read_sectors(struct floppy_state *fs,
 	return 0;
 }
 
-static void redo_fd_request(struct request_queue *q)
+static struct request *swim_next_request(struct swim_priv *swd)
 {
+	struct request_queue *q;
+	struct request *rq;
+	int old_pos = swd->fdc_queue;
+
+	do {
+		q = swd->unit[swd->fdc_queue].disk->queue;
+		if (++swd->fdc_queue == swd->floppy_count)
+			swd->fdc_queue = 0;
+		if (q) {
+			rq = blk_fetch_request(q);
+			if (rq)
+				return rq;
+		}
+	} while (swd->fdc_queue != old_pos);
+
+	return NULL;
+}
+
+static void do_fd_request(struct request_queue *q)
+{
+	struct swim_priv *swd = q->queuedata;
 	struct request *req;
 	struct floppy_state *fs;
 
-	req = blk_fetch_request(q);
+	req = swim_next_request(swd);
 	while (req) {
 		int err = -EIO;
 
@@ -554,15 +575,10 @@ static void redo_fd_request(struct request_queue *q)
 		}
 	done:
 		if (!__blk_end_request_cur(req, err))
-			req = blk_fetch_request(q);
+			req = swim_next_request(swd);
 	}
 }
 
-static void do_fd_request(struct request_queue *q)
-{
-	redo_fd_request(q);
-}
-
 static struct floppy_struct floppy_type[4] = {
 	{    0,  0, 0,  0, 0, 0x00, 0x00, 0x00, 0x00, NULL }, /* no testing   */
 	{  720,  9, 1, 80, 0, 0x2A, 0x02, 0xDF, 0x50, NULL }, /* 360KB SS 3.5"*/
@@ -833,22 +849,25 @@ static int swim_floppy_init(struct swim_priv *swd)
 		return -EBUSY;
 	}
 
+	spin_lock_init(&swd->lock);
+
 	for (drive = 0; drive < swd->floppy_count; drive++) {
 		swd->unit[drive].disk = alloc_disk(1);
 		if (swd->unit[drive].disk == NULL) {
 			err = -ENOMEM;
 			goto exit_put_disks;
 		}
+		swd->unit[drive].disk->queue = blk_init_queue(do_fd_request,
+							      &swd->lock);
+		if (!swd->unit[drive].disk->queue) {
+			err = -ENOMEM;
+			put_disk(swd->unit[drive].disk);
+			goto exit_put_disks;
+		}
+		swd->unit[drive].disk->queue->queuedata = swd;
 		swd->unit[drive].swd = swd;
 	}
 
-	spin_lock_init(&swd->lock);
-	swd->queue = blk_init_queue(do_fd_request, &swd->lock);
-	if (!swd->queue) {
-		err = -ENOMEM;
-		goto exit_put_disks;
-	}
-
 	for (drive = 0; drive < swd->floppy_count; drive++) {
 		swd->unit[drive].disk->flags = GENHD_FL_REMOVABLE;
 		swd->unit[drive].disk->major = FLOPPY_MAJOR;
@@ -856,7 +875,6 @@ static int swim_floppy_init(struct swim_priv *swd)
 		sprintf(swd->unit[drive].disk->disk_name, "fd%d", drive);
 		swd->unit[drive].disk->fops = &floppy_fops;
 		swd->unit[drive].disk->private_data = &swd->unit[drive];
-		swd->unit[drive].disk->queue = swd->queue;
 		set_capacity(swd->unit[drive].disk, 2880);
 		add_disk(swd->unit[drive].disk);
 	}
@@ -943,13 +961,12 @@ static int swim_remove(struct platform_device *dev)
 
 	for (drive = 0; drive < swd->floppy_count; drive++) {
 		del_gendisk(swd->unit[drive].disk);
+		blk_cleanup_queue(swd->unit[drive].disk->queue);
 		put_disk(swd->unit[drive].disk);
 	}
 
 	unregister_blkdev(FLOPPY_MAJOR, "fd");
 
-	blk_cleanup_queue(swd->queue);
-
 	/* eject floppies */
 
 	for (drive = 0; drive < swd->floppy_count; drive++)

drivers/block/swim3.c

@@ -343,8 +343,8 @@ static void start_request(struct floppy_state *fs)
 			  req->rq_disk->disk_name, req->cmd,
 			  (long)blk_rq_pos(req), blk_rq_sectors(req),
 			  bio_data(req->bio));
-		swim3_dbg("           errors=%d current_nr_sectors=%u\n",
-			  req->errors, blk_rq_cur_sectors(req));
+		swim3_dbg("           current_nr_sectors=%u\n",
+			  blk_rq_cur_sectors(req));
 #endif
 
 		if (blk_rq_pos(req) >= fs->total_secs) {

drivers/block/virtio_blk.c

@@ -111,7 +111,7 @@ static int virtblk_add_req_scsi(struct virtqueue *vq, struct virtblk_req *vbr,
 	return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
 }
 
-static inline void virtblk_scsi_reques_done(struct request *req)
+static inline void virtblk_scsi_request_done(struct request *req)
 {
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
 	struct virtio_blk *vblk = req->q->queuedata;
@@ -119,7 +119,7 @@ static inline void virtblk_scsi_reques_done(struct request *req)
 
 	sreq->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
 	sreq->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
-	req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
+	sreq->result = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
 }
 
 static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
@@ -144,7 +144,7 @@ static inline int virtblk_add_req_scsi(struct virtqueue *vq,
 {
 	return -EIO;
 }
-static inline void virtblk_scsi_reques_done(struct request *req)
+static inline void virtblk_scsi_request_done(struct request *req)
 {
 }
 #define virtblk_ioctl	NULL
@@ -175,19 +175,15 @@ static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr,
 static inline void virtblk_request_done(struct request *req)
 {
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
-	int error = virtblk_result(vbr);
 
 	switch (req_op(req)) {
 	case REQ_OP_SCSI_IN:
 	case REQ_OP_SCSI_OUT:
-		virtblk_scsi_reques_done(req);
-		break;
-	case REQ_OP_DRV_IN:
-		req->errors = (error != 0);
+		virtblk_scsi_request_done(req);
 		break;
 	}
 
-	blk_mq_end_request(req, error);
+	blk_mq_end_request(req, virtblk_result(vbr));
 }
 
 static void virtblk_done(struct virtqueue *vq)
@@ -205,7 +201,7 @@ static void virtblk_done(struct virtqueue *vq)
 		while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) {
 			struct request *req = blk_mq_rq_from_pdu(vbr);
 
-			blk_mq_complete_request(req, req->errors);
+			blk_mq_complete_request(req);
 			req_done = true;
 		}
 		if (unlikely(virtqueue_is_broken(vq)))
@@ -310,7 +306,8 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
 	if (err)
 		goto out;
 
-	err = blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
+	blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
+	err = virtblk_result(blk_mq_rq_to_pdu(req));
 out:
 	blk_put_request(req);
 	return err;
@@ -597,7 +594,7 @@ static int virtblk_map_queues(struct blk_mq_tag_set *set)
 	return blk_mq_virtio_map_queues(set, vblk->vdev, 0);
 }
 
-static struct blk_mq_ops virtio_mq_ops = {
+static const struct blk_mq_ops virtio_mq_ops = {
 	.queue_rq	= virtio_queue_rq,
 	.complete	= virtblk_request_done,
 	.init_request	= virtblk_init_request,

drivers/block/xen-blkfront.c

@@ -115,6 +115,15 @@ struct split_bio {
 	atomic_t pending;
 };
 
+struct blkif_req {
+	int	error;
+};
+
+static inline struct blkif_req *blkif_req(struct request *rq)
+{
+	return blk_mq_rq_to_pdu(rq);
+}
+
 static DEFINE_MUTEX(blkfront_mutex);
 static const struct block_device_operations xlvbd_block_fops;
 
@@ -907,8 +916,14 @@ out_busy:
 	return BLK_MQ_RQ_QUEUE_BUSY;
 }
 
-static struct blk_mq_ops blkfront_mq_ops = {
+static void blkif_complete_rq(struct request *rq)
+{
+	blk_mq_end_request(rq, blkif_req(rq)->error);
+}
+
+static const struct blk_mq_ops blkfront_mq_ops = {
 	.queue_rq = blkif_queue_rq,
+	.complete = blkif_complete_rq,
 };
 
 static void blkif_set_queue_limits(struct blkfront_info *info)
@@ -969,7 +984,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
 		info->tag_set.queue_depth = BLK_RING_SIZE(info);
 	info->tag_set.numa_node = NUMA_NO_NODE;
 	info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
-	info->tag_set.cmd_size = 0;
+	info->tag_set.cmd_size = sizeof(struct blkif_req);
 	info->tag_set.driver_data = info;
 
 	if (blk_mq_alloc_tag_set(&info->tag_set))
@@ -1543,7 +1558,6 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 	unsigned long flags;
 	struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)dev_id;
 	struct blkfront_info *info = rinfo->dev_info;
-	int error;
 
 	if (unlikely(info->connected != BLKIF_STATE_CONNECTED))
 		return IRQ_HANDLED;
@@ -1587,37 +1601,36 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 			continue;
 		}
 
-		error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
+		blkif_req(req)->error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
 		switch (bret->operation) {
 		case BLKIF_OP_DISCARD:
 			if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
 				struct request_queue *rq = info->rq;
 				printk(KERN_WARNING "blkfront: %s: %s op failed\n",
 					   info->gd->disk_name, op_name(bret->operation));
-				error = -EOPNOTSUPP;
+				blkif_req(req)->error = -EOPNOTSUPP;
 				info->feature_discard = 0;
 				info->feature_secdiscard = 0;
 				queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
 				queue_flag_clear(QUEUE_FLAG_SECERASE, rq);
 			}
-			blk_mq_complete_request(req, error);
 			break;
 		case BLKIF_OP_FLUSH_DISKCACHE:
 		case BLKIF_OP_WRITE_BARRIER:
 			if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
 				printk(KERN_WARNING "blkfront: %s: %s op failed\n",
 				       info->gd->disk_name, op_name(bret->operation));
-				error = -EOPNOTSUPP;
+				blkif_req(req)->error = -EOPNOTSUPP;
 			}
 			if (unlikely(bret->status == BLKIF_RSP_ERROR &&
 				     rinfo->shadow[id].req.u.rw.nr_segments == 0)) {
 				printk(KERN_WARNING "blkfront: %s: empty %s op failed\n",
 				       info->gd->disk_name, op_name(bret->operation));
-				error = -EOPNOTSUPP;
+				blkif_req(req)->error = -EOPNOTSUPP;
 			}
-			if (unlikely(error)) {
-				if (error == -EOPNOTSUPP)
-					error = 0;
+			if (unlikely(blkif_req(req)->error)) {
+				if (blkif_req(req)->error == -EOPNOTSUPP)
+					blkif_req(req)->error = 0;
 				info->feature_fua = 0;
 				info->feature_flush = 0;
 				xlvbd_flush(info);
@@ -1629,11 +1642,12 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 				dev_dbg(&info->xbdev->dev, "Bad return from blkdev data "
 					"request: %x\n", bret->status);
 
-			blk_mq_complete_request(req, error);
 			break;
 		default:
 			BUG();
 		}
+
+		blk_mq_complete_request(req);
 	}
 
 	rinfo->ring.rsp_cons = i;
@@ -2345,6 +2359,7 @@ static void blkfront_connect(struct blkfront_info *info)
 	unsigned long sector_size;
 	unsigned int physical_sector_size;
 	unsigned int binfo;
+	char *envp[] = { "RESIZE=1", NULL };
 	int err, i;
 
 	switch (info->connected) {
@@ -2361,6 +2376,8 @@ static void blkfront_connect(struct blkfront_info *info)
 		       sectors);
 		set_capacity(info->gd, sectors);
 		revalidate_disk(info->gd);
+		kobject_uevent_env(&disk_to_dev(info->gd)->kobj,
+				   KOBJ_CHANGE, envp);
 
 		return;
 	case BLKIF_STATE_SUSPENDED:

drivers/block/zram/zram_drv.c

@@ -829,10 +829,14 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 	offset = (bio->bi_iter.bi_sector &
 		  (SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
 
-	if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) {
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_WRITE_ZEROES:
 		zram_bio_discard(zram, index, offset, bio);
 		bio_endio(bio);
 		return;
+	default:
+		break;
 	}
 
 	bio_for_each_segment(bvec, bio, iter) {
@@ -1192,6 +1196,8 @@ static int zram_add(void)
 	zram->disk->queue->limits.max_sectors = SECTORS_PER_PAGE;
 	zram->disk->queue->limits.chunk_sectors = 0;
 	blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX);
+	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zram->disk->queue);
+
 	/*
 	 * zram_bio_discard() will clear all logical blocks if logical block
 	 * size is identical with physical block size(PAGE_SIZE). But if it is
@@ -1201,10 +1207,7 @@ static int zram_add(void)
 	 * zeroed.
 	 */
 	if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
-		zram->disk->queue->limits.discard_zeroes_data = 1;
-	else
-		zram->disk->queue->limits.discard_zeroes_data = 0;
-	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zram->disk->queue);
+		blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
 
 	add_disk(zram->disk);
 

drivers/cdrom/cdrom.c

@@ -2218,7 +2218,8 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 		rq->timeout = 60 * HZ;
 		bio = rq->bio;
 
-		if (blk_execute_rq(q, cdi->disk, rq, 0)) {
+		blk_execute_rq(q, cdi->disk, rq, 0);
+		if (scsi_req(rq)->result) {
 			struct request_sense *s = req->sense;
 			ret = -EIO;
 			cdi->last_sense = s->sense_key;

drivers/ide/ide-atapi.c

@@ -107,7 +107,8 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
 	memcpy(scsi_req(rq)->cmd, pc->c, 12);
 	if (drive->media == ide_tape)
 		scsi_req(rq)->cmd[13] = REQ_IDETAPE_PC1;
-	error = blk_execute_rq(drive->queue, disk, rq, 0);
+	blk_execute_rq(drive->queue, disk, rq, 0);
+	error = scsi_req(rq)->result ? -EIO : 0;
 put_req:
 	blk_put_request(rq);
 	return error;
@@ -454,7 +455,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 			debug_log("%s: I/O error\n", drive->name);
 
 			if (drive->media != ide_tape)
-				pc->rq->errors++;
+				scsi_req(pc->rq)->result++;
 
 			if (scsi_req(rq)->cmd[0] == REQUEST_SENSE) {
 				printk(KERN_ERR PFX "%s: I/O error in request "
@@ -488,13 +489,13 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 			drive->failed_pc = NULL;
 
 		if (ata_misc_request(rq)) {
-			rq->errors = 0;
+			scsi_req(rq)->result = 0;
 			error = 0;
 		} else {
 
 			if (blk_rq_is_passthrough(rq) && uptodate <= 0) {
-				if (rq->errors == 0)
-					rq->errors = -EIO;
+				if (scsi_req(rq)->result == 0)
+					scsi_req(rq)->result = -EIO;
 			}
 
 			error = uptodate ? 0 : -EIO;

drivers/ide/ide-cd.c

@@ -247,10 +247,10 @@ static int ide_cd_breathe(ide_drive_t *drive, struct request *rq)
 
 	struct cdrom_info *info = drive->driver_data;
 
-	if (!rq->errors)
+	if (!scsi_req(rq)->result)
 		info->write_timeout = jiffies +	ATAPI_WAIT_WRITE_BUSY;
 
-	rq->errors = 1;
+	scsi_req(rq)->result = 1;
 
 	if (time_after(jiffies, info->write_timeout))
 		return 0;
@@ -294,8 +294,8 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 	}
 
 	/* if we have an error, pass CHECK_CONDITION as the SCSI status byte */
-	if (blk_rq_is_scsi(rq) && !rq->errors)
-		rq->errors = SAM_STAT_CHECK_CONDITION;
+	if (blk_rq_is_scsi(rq) && !scsi_req(rq)->result)
+		scsi_req(rq)->result = SAM_STAT_CHECK_CONDITION;
 
 	if (blk_noretry_request(rq))
 		do_end_request = 1;
@@ -325,7 +325,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 		 * Arrange to retry the request but be sure to give up if we've
 		 * retried too many times.
 		 */
-		if (++rq->errors > ERROR_MAX)
+		if (++scsi_req(rq)->result > ERROR_MAX)
 			do_end_request = 1;
 		break;
 	case ILLEGAL_REQUEST:
@@ -372,7 +372,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
 			/* go to the default handler for other errors */
 			ide_error(drive, "cdrom_decode_status", stat);
 			return 1;
-		} else if (++rq->errors > ERROR_MAX)
+		} else if (++scsi_req(rq)->result > ERROR_MAX)
 			/* we've racked up too many retries, abort */
 			do_end_request = 1;
 	}
@@ -452,7 +452,8 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 			}
 		}
 
-		error = blk_execute_rq(drive->queue, info->disk, rq, 0);
+		blk_execute_rq(drive->queue, info->disk, rq, 0);
+		error = scsi_req(rq)->result ? -EIO : 0;
 
 		if (buffer)
 			*bufflen = scsi_req(rq)->resid_len;
@@ -683,8 +684,8 @@ out_end:
 			if (cmd->nleft == 0)
 				uptodate = 1;
 		} else {
-			if (uptodate <= 0 && rq->errors == 0)
-				rq->errors = -EIO;
+			if (uptodate <= 0 && scsi_req(rq)->result == 0)
+				scsi_req(rq)->result = -EIO;
 		}
 
 		if (uptodate == 0 && rq->bio)
@@ -1379,7 +1380,7 @@ static int ide_cdrom_prep_pc(struct request *rq)
 	 * appropriate action
 	 */
 	if (c[0] == MODE_SENSE || c[0] == MODE_SELECT) {
-		rq->errors = ILLEGAL_REQUEST;
+		scsi_req(rq)->result = ILLEGAL_REQUEST;
 		return BLKPREP_KILL;
 	}
 

drivers/ide/ide-cd_ioctl.c

@@ -307,7 +307,8 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
 	scsi_req_init(rq);
 	ide_req(rq)->type = ATA_PRIV_MISC;
 	rq->rq_flags = RQF_QUIET;
-	ret = blk_execute_rq(drive->queue, cd->disk, rq, 0);
+	blk_execute_rq(drive->queue, cd->disk, rq, 0);
+	ret = scsi_req(rq)->result ? -EIO : 0;
 	blk_put_request(rq);
 	/*
 	 * A reset will unlock the door. If it was previously locked,

drivers/ide/ide-devsets.c

@@ -173,8 +173,8 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting,
 	*(int *)&scsi_req(rq)->cmd[1] = arg;
 	rq->special = setting->set;
 
-	if (blk_execute_rq(q, NULL, rq, 0))
-		ret = rq->errors;
+	blk_execute_rq(q, NULL, rq, 0);
+	ret = scsi_req(rq)->result;
 	blk_put_request(rq);
 
 	return ret;
@@ -186,7 +186,7 @@ ide_startstop_t ide_do_devset(ide_drive_t *drive, struct request *rq)
 
 	err = setfunc(drive, *(int *)&scsi_req(rq)->cmd[1]);
 	if (err)
-		rq->errors = err;
-	ide_complete_rq(drive, err, blk_rq_bytes(rq));
+		scsi_req(rq)->result = err;
+	ide_complete_rq(drive, 0, blk_rq_bytes(rq));
 	return ide_stopped;
 }

drivers/ide/ide-disk.c

@@ -470,7 +470,6 @@ ide_devset_get(multcount, mult_count);
 static int set_multcount(ide_drive_t *drive, int arg)
 {
 	struct request *rq;
-	int error;
 
 	if (arg < 0 || arg > (drive->id[ATA_ID_MAX_MULTSECT] & 0xff))
 		return -EINVAL;
@@ -484,7 +483,7 @@ static int set_multcount(ide_drive_t *drive, int arg)
 
 	drive->mult_req = arg;
 	drive->special_flags |= IDE_SFLAG_SET_MULTMODE;
-	error = blk_execute_rq(drive->queue, NULL, rq, 0);
+	blk_execute_rq(drive->queue, NULL, rq, 0);
 	blk_put_request(rq);
 
 	return (drive->mult_count == arg) ? 0 : -EIO;

drivers/ide/ide-dma.c

@@ -490,7 +490,7 @@ ide_startstop_t ide_dma_timeout_retry(ide_drive_t *drive, int error)
 	 * make sure request is sane
 	 */
 	if (hwif->rq)
-		hwif->rq->errors = 0;
+		scsi_req(hwif->rq)->result = 0;
 	return ret;
 }
 

drivers/ide/ide-eh.c

@@ -12,7 +12,7 @@ static ide_startstop_t ide_ata_error(ide_drive_t *drive, struct request *rq,
 	if ((stat & ATA_BUSY) ||
 	    ((stat & ATA_DF) && (drive->dev_flags & IDE_DFLAG_NOWERR) == 0)) {
 		/* other bits are useless when BUSY */
-		rq->errors |= ERROR_RESET;
+		scsi_req(rq)->result |= ERROR_RESET;
 	} else if (stat & ATA_ERR) {
 		/* err has different meaning on cdrom and tape */
 		if (err == ATA_ABORTED) {
@@ -25,10 +25,10 @@ static ide_startstop_t ide_ata_error(ide_drive_t *drive, struct request *rq,
 			drive->crc_count++;
 		} else if (err & (ATA_BBK | ATA_UNC)) {
 			/* retries won't help these */
-			rq->errors = ERROR_MAX;
+			scsi_req(rq)->result = ERROR_MAX;
 		} else if (err & ATA_TRK0NF) {
 			/* help it find track zero */
-			rq->errors |= ERROR_RECAL;
+			scsi_req(rq)->result |= ERROR_RECAL;
 		}
 	}
 
@@ -39,23 +39,23 @@ static ide_startstop_t ide_ata_error(ide_drive_t *drive, struct request *rq,
 		ide_pad_transfer(drive, READ, nsect * SECTOR_SIZE);
 	}
 
-	if (rq->errors >= ERROR_MAX || blk_noretry_request(rq)) {
+	if (scsi_req(rq)->result >= ERROR_MAX || blk_noretry_request(rq)) {
 		ide_kill_rq(drive, rq);
 		return ide_stopped;
 	}
 
 	if (hwif->tp_ops->read_status(hwif) & (ATA_BUSY | ATA_DRQ))
-		rq->errors |= ERROR_RESET;
+		scsi_req(rq)->result |= ERROR_RESET;
 
-	if ((rq->errors & ERROR_RESET) == ERROR_RESET) {
-		++rq->errors;
+	if ((scsi_req(rq)->result & ERROR_RESET) == ERROR_RESET) {
+		++scsi_req(rq)->result;
 		return ide_do_reset(drive);
 	}
 
-	if ((rq->errors & ERROR_RECAL) == ERROR_RECAL)
+	if ((scsi_req(rq)->result & ERROR_RECAL) == ERROR_RECAL)
 		drive->special_flags |= IDE_SFLAG_RECALIBRATE;
 
-	++rq->errors;
+	++scsi_req(rq)->result;
 
 	return ide_stopped;
 }
@@ -68,7 +68,7 @@ static ide_startstop_t ide_atapi_error(ide_drive_t *drive, struct request *rq,
 	if ((stat & ATA_BUSY) ||
 	    ((stat & ATA_DF) && (drive->dev_flags & IDE_DFLAG_NOWERR) == 0)) {
 		/* other bits are useless when BUSY */
-		rq->errors |= ERROR_RESET;
+		scsi_req(rq)->result |= ERROR_RESET;
 	} else {
 		/* add decoding error stuff */
 	}
@@ -77,14 +77,14 @@ static ide_startstop_t ide_atapi_error(ide_drive_t *drive, struct request *rq,
 		/* force an abort */
 		hwif->tp_ops->exec_command(hwif, ATA_CMD_IDLEIMMEDIATE);
 
-	if (rq->errors >= ERROR_MAX) {
+	if (scsi_req(rq)->result >= ERROR_MAX) {
 		ide_kill_rq(drive, rq);
 	} else {
-		if ((rq->errors & ERROR_RESET) == ERROR_RESET) {
-			++rq->errors;
+		if ((scsi_req(rq)->result & ERROR_RESET) == ERROR_RESET) {
+			++scsi_req(rq)->result;
 			return ide_do_reset(drive);
 		}
-		++rq->errors;
+		++scsi_req(rq)->result;
 	}
 
 	return ide_stopped;
@@ -130,11 +130,11 @@ ide_startstop_t ide_error(ide_drive_t *drive, const char *msg, u8 stat)
 			if (cmd)
 				ide_complete_cmd(drive, cmd, stat, err);
 		} else if (ata_pm_request(rq)) {
-			rq->errors = 1;
+			scsi_req(rq)->result = 1;
 			ide_complete_pm_rq(drive, rq);
 			return ide_stopped;
 		}
-		rq->errors = err;
+		scsi_req(rq)->result = err;
 		ide_complete_rq(drive, err ? -EIO : 0, blk_rq_bytes(rq));
 		return ide_stopped;
 	}
@@ -149,8 +149,8 @@ static inline void ide_complete_drive_reset(ide_drive_t *drive, int err)
 
 	if (rq && ata_misc_request(rq) &&
 	    scsi_req(rq)->cmd[0] == REQ_DRIVE_RESET) {
-		if (err <= 0 && rq->errors == 0)
-			rq->errors = -EIO;
+		if (err <= 0 && scsi_req(rq)->result == 0)
+			scsi_req(rq)->result = -EIO;
 		ide_complete_rq(drive, err ? err : 0, blk_rq_bytes(rq));
 	}
 }

drivers/ide/ide-floppy.c

@@ -98,7 +98,7 @@ static int ide_floppy_callback(ide_drive_t *drive, int dsc)
 	}
 
 	if (ata_misc_request(rq))
-		rq->errors = uptodate ? 0 : IDE_DRV_ERROR_GENERAL;
+		scsi_req(rq)->result = uptodate ? 0 : IDE_DRV_ERROR_GENERAL;
 
 	return uptodate;
 }
@@ -239,7 +239,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 					? rq->rq_disk->disk_name
 					: "dev?"));
 
-	if (rq->errors >= ERROR_MAX) {
+	if (scsi_req(rq)->result >= ERROR_MAX) {
 		if (drive->failed_pc) {
 			ide_floppy_report_error(floppy, drive->failed_pc);
 			drive->failed_pc = NULL;
@@ -247,7 +247,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 			printk(KERN_ERR PFX "%s: I/O error\n", drive->name);
 
 		if (ata_misc_request(rq)) {
-			rq->errors = 0;
+			scsi_req(rq)->result = 0;
 			ide_complete_rq(drive, 0, blk_rq_bytes(rq));
 			return ide_stopped;
 		} else
@@ -301,8 +301,8 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 	return ide_floppy_issue_pc(drive, &cmd, pc);
 out_end:
 	drive->failed_pc = NULL;
-	if (blk_rq_is_passthrough(rq) && rq->errors == 0)
-		rq->errors = -EIO;
+	if (blk_rq_is_passthrough(rq) && scsi_req(rq)->result == 0)
+		scsi_req(rq)->result = -EIO;
 	ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
 	return ide_stopped;
 }

drivers/ide/ide-io.c

@@ -141,12 +141,12 @@ void ide_kill_rq(ide_drive_t *drive, struct request *rq)
 	drive->failed_pc = NULL;
 
 	if ((media == ide_floppy || media == ide_tape) && drv_req) {
-		rq->errors = 0;
+		scsi_req(rq)->result = 0;
 	} else {
 		if (media == ide_tape)
-			rq->errors = IDE_DRV_ERROR_GENERAL;
-		else if (blk_rq_is_passthrough(rq) && rq->errors == 0)
-			rq->errors = -EIO;
+			scsi_req(rq)->result = IDE_DRV_ERROR_GENERAL;
+		else if (blk_rq_is_passthrough(rq) && scsi_req(rq)->result == 0)
+			scsi_req(rq)->result = -EIO;
 	}
 
 	ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
@@ -271,7 +271,7 @@ static ide_startstop_t execute_drive_cmd (ide_drive_t *drive,
 #ifdef DEBUG
  	printk("%s: DRIVE_CMD (null)\n", drive->name);
 #endif
-	rq->errors = 0;
+	scsi_req(rq)->result = 0;
 	ide_complete_rq(drive, 0, blk_rq_bytes(rq));
 
  	return ide_stopped;

drivers/ide/ide-ioctls.c

@@ -128,7 +128,8 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg)
 		rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
 		scsi_req_init(rq);
 		ide_req(rq)->type = ATA_PRIV_TASKFILE;
-		err = blk_execute_rq(drive->queue, NULL, rq, 0);
+		blk_execute_rq(drive->queue, NULL, rq, 0);
+		err = scsi_req(rq)->result ? -EIO : 0;
 		blk_put_request(rq);
 
 		return err;
@@ -227,8 +228,8 @@ static int generic_drive_reset(ide_drive_t *drive)
 	ide_req(rq)->type = ATA_PRIV_MISC;
 	scsi_req(rq)->cmd_len = 1;
 	scsi_req(rq)->cmd[0] = REQ_DRIVE_RESET;
-	if (blk_execute_rq(drive->queue, NULL, rq, 1))
-		ret = rq->errors;
+	blk_execute_rq(drive->queue, NULL, rq, 1);
+	ret = scsi_req(rq)->result;
 	blk_put_request(rq);
 	return ret;
 }

drivers/ide/ide-park.c

@@ -37,7 +37,8 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 	scsi_req(rq)->cmd_len = 1;
 	ide_req(rq)->type = ATA_PRIV_MISC;
 	rq->special = &timeout;
-	rc = blk_execute_rq(q, NULL, rq, 1);
+	blk_execute_rq(q, NULL, rq, 1);
+	rc = scsi_req(rq)->result ? -EIO : 0;
 	blk_put_request(rq);
 	if (rc)
 		goto out;

drivers/ide/ide-pm.c

@@ -27,7 +27,8 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 		mesg.event = PM_EVENT_FREEZE;
 	rqpm.pm_state = mesg.event;
 
-	ret = blk_execute_rq(drive->queue, NULL, rq, 0);
+	blk_execute_rq(drive->queue, NULL, rq, 0);
+	ret = scsi_req(rq)->result ? -EIO : 0;
 	blk_put_request(rq);
 
 	if (ret == 0 && ide_port_acpi(hwif)) {
@@ -55,8 +56,8 @@ static int ide_pm_execute_rq(struct request *rq)
 	spin_lock_irq(q->queue_lock);
 	if (unlikely(blk_queue_dying(q))) {
 		rq->rq_flags |= RQF_QUIET;
-		rq->errors = -ENXIO;
-		__blk_end_request_all(rq, rq->errors);
+		scsi_req(rq)->result = -ENXIO;
+		__blk_end_request_all(rq, 0);
 		spin_unlock_irq(q->queue_lock);
 		return -ENXIO;
 	}
@@ -66,7 +67,7 @@ static int ide_pm_execute_rq(struct request *rq)
 
 	wait_for_completion_io(&wait);
 
-	return rq->errors ? -EIO : 0;
+	return scsi_req(rq)->result ? -EIO : 0;
 }
 
 int generic_ide_resume(struct device *dev)

drivers/ide/ide-tape.c

@@ -366,7 +366,7 @@ static int ide_tape_callback(ide_drive_t *drive, int dsc)
 			err = pc->error;
 		}
 	}
-	rq->errors = err;
+	scsi_req(rq)->result = err;
 
 	return uptodate;
 }
@@ -879,7 +879,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
 		tape->valid = 0;
 
 	ret = size;
-	if (rq->errors == IDE_DRV_ERROR_GENERAL)
+	if (scsi_req(rq)->result == IDE_DRV_ERROR_GENERAL)
 		ret = -EIO;
 out_put:
 	blk_put_request(rq);