diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-14 15:32:19 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-14 15:32:19 -0800 |
commit | e2c5923c349c1738fe8fda980874d93f6fb2e5b6 (patch) | |
tree | b97a90170c45211bcc437761653aa8016c34afcd /include/linux/blk-mq.h | |
parent | abc36be236358162202e86ad88616ff95a755101 (diff) | |
parent | a04b5de5050ab8b891128eb2c47a0916fe8622e1 (diff) | |
download | linux-e2c5923c349c1738fe8fda980874d93f6fb2e5b6.tar.gz linux-e2c5923c349c1738fe8fda980874d93f6fb2e5b6.tar.bz2 linux-e2c5923c349c1738fe8fda980874d93f6fb2e5b6.zip |
Merge branch 'for-4.15/block' of git://git.kernel.dk/linux-block
Pull core block layer updates from Jens Axboe:
"This is the main pull request for block storage for 4.15-rc1.
Nothing out of the ordinary in here, and no API changes or anything
like that. Just various new features for drivers, core changes, etc.
In particular, this pull request contains:
- A patch series from Bart, closing the whole on blk/scsi-mq queue
quescing.
- A series from Christoph, building towards hidden gendisks (for
multipath) and ability to move bio chains around.
- NVMe
- Support for native multipath for NVMe (Christoph).
- Userspace notifications for AENs (Keith).
- Command side-effects support (Keith).
- SGL support (Chaitanya Kulkarni)
- FC fixes and improvements (James Smart)
- Lots of fixes and tweaks (Various)
- bcache
- New maintainer (Michael Lyle)
- Writeback control improvements (Michael)
- Various fixes (Coly, Elena, Eric, Liang, et al)
- lightnvm updates, mostly centered around the pblk interface
(Javier, Hans, and Rakesh).
- Removal of unused bio/bvec kmap atomic interfaces (me, Christoph)
- Writeback series that fix the much discussed hundreds of millions
of sync-all units. This goes all the way, as discussed previously
(me).
- Fix for missing wakeup on writeback timer adjustments (Yafang
Shao).
- Fix laptop mode on blk-mq (me).
- {mq,name} tupple lookup for IO schedulers, allowing us to have
alias names. This means you can use 'deadline' on both !mq and on
mq (where it's called mq-deadline). (me).
- blktrace race fix, oopsing on sg load (me).
- blk-mq optimizations (me).
- Obscure waitqueue race fix for kyber (Omar).
- NBD fixes (Josef).
- Disable writeback throttling by default on bfq, like we do on cfq
(Luca Miccio).
- Series from Ming that enable us to treat flush requests on blk-mq
like any other request. This is a really nice cleanup.
- Series from Ming that improves merging on blk-mq with schedulers,
getting us closer to flipping the switch on scsi-mq again.
- BFQ updates (Paolo).
- blk-mq atomic flags memory ordering fixes (Peter Z).
- Loop cgroup support (Shaohua).
- Lots of minor fixes from lots of different folks, both for core and
driver code"
* 'for-4.15/block' of git://git.kernel.dk/linux-block: (294 commits)
nvme: fix visibility of "uuid" ns attribute
blk-mq: fixup some comment typos and lengths
ide: ide-atapi: fix compile error with defining macro DEBUG
blk-mq: improve tag waiting setup for non-shared tags
brd: remove unused brd_mutex
blk-mq: only run the hardware queue if IO is pending
block: avoid null pointer dereference on null disk
fs: guard_bio_eod() needs to consider partitions
xtensa/simdisk: fix compile error
nvme: expose subsys attribute to sysfs
nvme: create 'slaves' and 'holders' entries for hidden controllers
block: create 'slaves' and 'holders' entries for hidden gendisks
nvme: also expose the namespace identification sysfs files for mpath nodes
nvme: implement multipath access to nvme subsystems
nvme: track shared namespaces
nvme: introduce a nvme_ns_ids structure
nvme: track subsystems
block, nvme: Introduce blk_mq_req_flags_t
block, scsi: Make SCSI quiesce and resume work reliably
block: Add the QUEUE_FLAG_PREEMPT_ONLY request queue flag
...
Diffstat (limited to 'include/linux/blk-mq.h')
-rw-r--r-- | include/linux/blk-mq.h | 40 |
1 files changed, 29 insertions, 11 deletions
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 994cbb0f7ffc..95c9a5c862e2 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -31,10 +31,12 @@ struct blk_mq_hw_ctx { struct sbitmap ctx_map; + struct blk_mq_ctx *dispatch_from; + struct blk_mq_ctx **ctxs; unsigned int nr_ctx; - wait_queue_entry_t dispatch_wait; + wait_queue_entry_t dispatch_wait; atomic_t wait_index; struct blk_mq_tags *tags; @@ -91,6 +93,8 @@ struct blk_mq_queue_data { typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); +typedef bool (get_budget_fn)(struct blk_mq_hw_ctx *); +typedef void (put_budget_fn)(struct blk_mq_hw_ctx *); typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool); typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int); typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int); @@ -113,6 +117,15 @@ struct blk_mq_ops { queue_rq_fn *queue_rq; /* + * Reserve budget before queue request, once .queue_rq is + * run, it is driver's responsibility to release the + * reserved budget. Also we have to handle failure case + * of .get_budget for avoiding I/O deadlock. + */ + get_budget_fn *get_budget; + put_budget_fn *put_budget; + + /* * Called on request timeout */ timeout_fn *timeout; @@ -169,8 +182,7 @@ enum { BLK_MQ_S_STOPPED = 0, BLK_MQ_S_TAG_ACTIVE = 1, BLK_MQ_S_SCHED_RESTART = 2, - BLK_MQ_S_TAG_WAITING = 3, - BLK_MQ_S_START_ON_RUN = 4, + BLK_MQ_S_START_ON_RUN = 3, BLK_MQ_MAX_DEPTH = 10240, @@ -198,15 +210,21 @@ void blk_mq_free_request(struct request *rq); bool blk_mq_can_queue(struct blk_mq_hw_ctx *); enum { - BLK_MQ_REQ_NOWAIT = (1 << 0), /* return when out of requests */ - BLK_MQ_REQ_RESERVED = (1 << 1), /* allocate from reserved pool */ - BLK_MQ_REQ_INTERNAL = (1 << 2), /* allocate internal/sched tag */ + /* return when out of requests */ + BLK_MQ_REQ_NOWAIT = (__force blk_mq_req_flags_t)(1 << 0), + /* allocate from reserved pool */ + BLK_MQ_REQ_RESERVED = (__force blk_mq_req_flags_t)(1 << 1), + /* allocate internal/sched tag */ + BLK_MQ_REQ_INTERNAL = (__force blk_mq_req_flags_t)(1 << 2), + /* set RQF_PREEMPT */ + BLK_MQ_REQ_PREEMPT = (__force blk_mq_req_flags_t)(1 << 3), }; struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, - unsigned int flags); + blk_mq_req_flags_t flags); struct request *blk_mq_alloc_request_hctx(struct request_queue *q, - unsigned int op, unsigned int flags, unsigned int hctx_idx); + unsigned int op, blk_mq_req_flags_t flags, + unsigned int hctx_idx); struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag); enum { @@ -249,7 +267,7 @@ void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_quiesce_queue(struct request_queue *q); void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); -void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); +bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, @@ -260,8 +278,8 @@ void blk_freeze_queue_start(struct request_queue *q); void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, unsigned long timeout); -int blk_mq_reinit_tagset(struct blk_mq_tag_set *set, - int (reinit_request)(void *, struct request *)); +int blk_mq_tagset_iter(struct blk_mq_tag_set *set, void *data, + int (reinit_request)(void *, struct request *)); int blk_mq_map_queues(struct blk_mq_tag_set *set); void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); |