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 | |
parent | abc36be236358162202e86ad88616ff95a755101 (diff) | |
parent | a04b5de5050ab8b891128eb2c47a0916fe8622e1 (diff) |
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')
-rw-r--r-- | include/linux/backing-dev-defs.h | 24 | ||||
-rw-r--r-- | include/linux/backing-dev.h | 4 | ||||
-rw-r--r-- | include/linux/bio.h | 25 | ||||
-rw-r--r-- | include/linux/blk-cgroup.h | 25 | ||||
-rw-r--r-- | include/linux/blk-mq.h | 40 | ||||
-rw-r--r-- | include/linux/blk_types.h | 16 | ||||
-rw-r--r-- | include/linux/blkdev.h | 36 | ||||
-rw-r--r-- | include/linux/buffer_head.h | 2 | ||||
-rw-r--r-- | include/linux/elevator.h | 1 | ||||
-rw-r--r-- | include/linux/genhd.h | 4 | ||||
-rw-r--r-- | include/linux/kthread.h | 11 | ||||
-rw-r--r-- | include/linux/lightnvm.h | 11 | ||||
-rw-r--r-- | include/linux/nvme-fc-driver.h | 15 | ||||
-rw-r--r-- | include/linux/nvme.h | 30 | ||||
-rw-r--r-- | include/linux/sbitmap.h | 64 | ||||
-rw-r--r-- | include/linux/writeback.h | 30 | ||||
-rw-r--r-- | include/scsi/scsi_device.h | 1 | ||||
-rw-r--r-- | include/trace/events/writeback.h | 1 |
18 files changed, 201 insertions, 139 deletions
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index fff4cfa0c21d..bfe86b54f6c1 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -25,6 +25,7 @@ enum wb_state { WB_shutting_down, /* wb_shutdown() in progress */ WB_writeback_running, /* Writeback is in progress */ WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */ + WB_start_all, /* nr_pages == 0 (all) work pending */ }; enum wb_congested_state { @@ -45,6 +46,28 @@ enum wb_stat_item { #define WB_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) /* + * why some writeback work was initiated + */ +enum wb_reason { + WB_REASON_BACKGROUND, + WB_REASON_VMSCAN, + WB_REASON_SYNC, + WB_REASON_PERIODIC, + WB_REASON_LAPTOP_TIMER, + WB_REASON_FREE_MORE_MEM, + WB_REASON_FS_FREE_SPACE, + /* + * There is no bdi forker thread any more and works are done + * by emergency worker, however, this is TPs userland visible + * and we'll be exposing exactly the same information, + * so it has a mismatch name. + */ + WB_REASON_FORKER_THREAD, + + WB_REASON_MAX, +}; + +/* * For cgroup writeback, multiple wb's may map to the same blkcg. Those * wb's can operate mostly independently but should share the congested * state. To facilitate such sharing, the congested state is tracked using @@ -116,6 +139,7 @@ struct bdi_writeback { struct fprop_local_percpu completions; int dirty_exceeded; + enum wb_reason start_all_reason; spinlock_t work_lock; /* protects work_list & dwork scheduling */ struct list_head work_list; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 16621579a3db..f41ca8486e02 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -39,8 +39,6 @@ static inline struct backing_dev_info *bdi_alloc(gfp_t gfp_mask) return bdi_alloc_node(gfp_mask, NUMA_NO_NODE); } -void wb_start_writeback(struct bdi_writeback *wb, long nr_pages, - bool range_cyclic, enum wb_reason reason); void wb_start_background_writeback(struct bdi_writeback *wb); void wb_workfn(struct work_struct *work); void wb_wakeup_delayed(struct bdi_writeback *wb); @@ -175,8 +173,6 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) long congestion_wait(int sync, long timeout); long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout); -int pdflush_proc_obsolete(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos); static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi) { diff --git a/include/linux/bio.h b/include/linux/bio.h index 275c91c99516..d4eec19a6d3c 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -129,18 +129,6 @@ static inline void *bio_data(struct bio *bio) #define bvec_to_phys(bv) (page_to_phys((bv)->bv_page) + (unsigned long) (bv)->bv_offset) /* - * queues that have highmem support enabled may still need to revert to - * PIO transfers occasionally and thus map high pages temporarily. For - * permanent PIO fall back, user is probably better off disabling highmem - * I/O completely on that queue (see ide-dma for example) - */ -#define __bio_kmap_atomic(bio, iter) \ - (kmap_atomic(bio_iter_iovec((bio), (iter)).bv_page) + \ - bio_iter_iovec((bio), (iter)).bv_offset) - -#define __bio_kunmap_atomic(addr) kunmap_atomic(addr) - -/* * merge helpers etc */ @@ -522,13 +510,11 @@ do { \ #ifdef CONFIG_BLK_CGROUP int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); -int bio_associate_current(struct bio *bio); void bio_disassociate_task(struct bio *bio); void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ static inline int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) { return 0; } -static inline int bio_associate_current(struct bio *bio) { return -ENOENT; } static inline void bio_disassociate_task(struct bio *bio) { } static inline void bio_clone_blkcg_association(struct bio *dst, struct bio *src) { } @@ -575,17 +561,6 @@ static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) } #endif -static inline char *__bio_kmap_irq(struct bio *bio, struct bvec_iter iter, - unsigned long *flags) -{ - return bvec_kmap_irq(&bio_iter_iovec(bio, iter), flags); -} -#define __bio_kunmap_irq(buf, flags) bvec_kunmap_irq(buf, flags) - -#define bio_kmap_irq(bio, flags) \ - __bio_kmap_irq((bio), (bio)->bi_iter, (flags)) -#define bio_kunmap_irq(buf,flags) __bio_kunmap_irq(buf, flags) - /* * BIO list management for use by remapping drivers (e.g. DM or MD) and loop. * diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 8bbc3716507a..e9825ff57b15 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -20,6 +20,7 @@ #include <linux/radix-tree.h> #include <linux/blkdev.h> #include <linux/atomic.h> +#include <linux/kthread.h> /* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */ #define BLKG_STAT_CPU_BATCH (INT_MAX / 2) @@ -224,22 +225,16 @@ static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) return css ? container_of(css, struct blkcg, css) : NULL; } -static inline struct blkcg *task_blkcg(struct task_struct *tsk) -{ - return css_to_blkcg(task_css(tsk, io_cgrp_id)); -} - static inline struct blkcg *bio_blkcg(struct bio *bio) { + struct cgroup_subsys_state *css; + if (bio && bio->bi_css) return css_to_blkcg(bio->bi_css); - return task_blkcg(current); -} - -static inline struct cgroup_subsys_state * -task_get_blkcg_css(struct task_struct *task) -{ - return task_get_css(task, io_cgrp_id); + css = kthread_blkcg(); + if (css) + return css_to_blkcg(css); + return css_to_blkcg(task_css(current, io_cgrp_id)); } /** @@ -736,12 +731,6 @@ struct blkcg_policy { #define blkcg_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) -static inline struct cgroup_subsys_state * -task_get_blkcg_css(struct task_struct *task) -{ - return NULL; -} - #ifdef CONFIG_BLOCK static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; } 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); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 96ac3815542c..a1e628e032da 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -163,6 +163,8 @@ struct bio { */ #define BIO_RESET_BITS BVEC_POOL_OFFSET +typedef __u32 __bitwise blk_mq_req_flags_t; + /* * Operations and flags common to the bio and request structures. * We use 8 bits for encoding the operation, and the remaining 24 for flags. @@ -225,11 +227,14 @@ enum req_flag_bits { __REQ_PREFLUSH, /* request for cache flush */ __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_BACKGROUND, /* background IO */ + __REQ_NOWAIT, /* Don't wait if request will block */ /* command specific flags for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ - __REQ_NOWAIT, /* Don't wait if request will block */ + /* for driver use */ + __REQ_DRV, + __REQ_NR_BITS, /* stops here */ }; @@ -246,9 +251,11 @@ enum req_flag_bits { #define REQ_PREFLUSH (1ULL << __REQ_PREFLUSH) #define REQ_RAHEAD (1ULL << __REQ_RAHEAD) #define REQ_BACKGROUND (1ULL << __REQ_BACKGROUND) +#define REQ_NOWAIT (1ULL << __REQ_NOWAIT) #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) -#define REQ_NOWAIT (1ULL << __REQ_NOWAIT) + +#define REQ_DRV (1ULL << __REQ_DRV) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) @@ -330,11 +337,10 @@ static inline bool blk_qc_t_is_internal(blk_qc_t cookie) } struct blk_rq_stat { - s64 mean; + u64 mean; u64 min; u64 max; - s32 nr_samples; - s32 nr_batch; + u32 nr_samples; u64 batch; }; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8da66379f7ea..8089ca17db9a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -267,6 +267,7 @@ struct blk_queue_ctx; typedef void (request_fn_proc) (struct request_queue *q); typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); +typedef bool (poll_q_fn) (struct request_queue *q, blk_qc_t); typedef int (prep_rq_fn) (struct request_queue *, struct request *); typedef void (unprep_rq_fn) (struct request_queue *, struct request *); @@ -409,6 +410,7 @@ struct request_queue { request_fn_proc *request_fn; make_request_fn *make_request_fn; + poll_q_fn *poll_fn; prep_rq_fn *prep_rq_fn; unprep_rq_fn *unprep_rq_fn; softirq_done_fn *softirq_done_fn; @@ -610,7 +612,6 @@ struct request_queue { #define QUEUE_FLAG_NOMERGES 5 /* disable merge attempts */ #define QUEUE_FLAG_SAME_COMP 6 /* complete on same CPU-group */ #define QUEUE_FLAG_FAIL_IO 7 /* fake timeout */ -#define QUEUE_FLAG_STACKABLE 8 /* supports request stacking */ #define QUEUE_FLAG_NONROT 9 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 10 /* do IO stats */ @@ -632,14 +633,13 @@ struct request_queue { #define QUEUE_FLAG_REGISTERED 26 /* queue has been registered to a disk */ #define QUEUE_FLAG_SCSI_PASSTHROUGH 27 /* queue supports SCSI commands */ #define QUEUE_FLAG_QUIESCED 28 /* queue has been quiesced */ +#define QUEUE_FLAG_PREEMPT_ONLY 29 /* only process REQ_PREEMPT requests */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_STACKABLE) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ (1 << QUEUE_FLAG_ADD_RANDOM)) #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_STACKABLE) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ (1 << QUEUE_FLAG_POLL)) @@ -723,8 +723,6 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) -#define blk_queue_stackable(q) \ - test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) #define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_queue_secure_erase(q) \ (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) @@ -736,6 +734,11 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ REQ_FAILFAST_DRIVER)) #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) +#define blk_queue_preempt_only(q) \ + test_bit(QUEUE_FLAG_PREEMPT_ONLY, &(q)->queue_flags) + +extern int blk_set_preempt_only(struct request_queue *q); +extern void blk_clear_preempt_only(struct request_queue *q); static inline bool blk_account_rq(struct request *rq) { @@ -923,24 +926,17 @@ static inline void rq_flush_dcache_pages(struct request *rq) } #endif -#ifdef CONFIG_PRINTK -#define vfs_msg(sb, level, fmt, ...) \ - __vfs_msg(sb, level, fmt, ##__VA_ARGS__) -#else -#define vfs_msg(sb, level, fmt, ...) \ -do { \ - no_printk(fmt, ##__VA_ARGS__); \ - __vfs_msg(sb, "", " "); \ -} while (0) -#endif - extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); extern blk_qc_t generic_make_request(struct bio *bio); +extern blk_qc_t direct_make_request(struct bio *bio); extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_init_request_from_bio(struct request *req, struct bio *bio); extern void blk_put_request(struct request *); extern void __blk_put_request(struct request_queue *, struct request *); +extern struct request *blk_get_request_flags(struct request_queue *, + unsigned int op, + blk_mq_req_flags_t flags); extern struct request *blk_get_request(struct request_queue *, unsigned int op, gfp_t gfp_mask); extern void blk_requeue_request(struct request_queue *, struct request *); @@ -964,7 +960,7 @@ extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t, extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, struct scsi_ioctl_command __user *); -extern int blk_queue_enter(struct request_queue *q, bool nowait); +extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags); extern void blk_queue_exit(struct request_queue *q); extern void blk_start_queue(struct request_queue *q); extern void blk_start_queue_async(struct request_queue *q); @@ -991,7 +987,7 @@ extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, int blk_status_to_errno(blk_status_t status); blk_status_t errno_to_blk_status(int errno); -bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie); +bool blk_poll(struct request_queue *q, blk_qc_t cookie); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { @@ -1110,6 +1106,8 @@ extern struct request *blk_peek_request(struct request_queue *q); extern void blk_start_request(struct request *rq); extern struct request *blk_fetch_request(struct request_queue *q); +void blk_steal_bios(struct bio_list *list, struct request *rq); + /* * Request completion related functions. * @@ -1372,7 +1370,7 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, gfp_mask, 0); } -extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); +extern int blk_verify_command(unsigned char *cmd, fmode_t mode); enum blk_default_limits { BLK_MAX_SEGMENTS = 128, diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index afa37f807f12..8b1bf8d3d4a2 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -157,7 +157,7 @@ void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset); int try_to_free_buffers(struct page *); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, - int retry); + bool retry); void create_empty_buffers(struct page *, unsigned long, unsigned long b_state); void end_buffer_read_sync(struct buffer_head *bh, int uptodate); diff --git a/include/linux/elevator.h b/include/linux/elevator.h index ddb7632d73b9..3d794b3dc532 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -145,6 +145,7 @@ struct elevator_type size_t icq_align; /* ditto */ struct elv_fs_entry *elevator_attrs; char elevator_name[ELV_NAME_MAX]; + const char *elevator_alias; struct module *elevator_owner; bool uses_mq; #ifdef CONFIG_BLK_DEBUG_FS diff --git a/include/linux/genhd.h b/include/linux/genhd.h index eaefb7a62f83..5144ebe046c9 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -141,6 +141,7 @@ struct hd_struct { #define GENHD_FL_NATIVE_CAPACITY 128 #define GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE 256 #define GENHD_FL_NO_PART_SCAN 512 +#define GENHD_FL_HIDDEN 1024 enum { DISK_EVENT_MEDIA_CHANGE = 1 << 0, /* media changed */ @@ -236,7 +237,7 @@ static inline bool disk_part_scan_enabled(struct gendisk *disk) static inline dev_t disk_devt(struct gendisk *disk) { - return disk_to_dev(disk)->devt; + return MKDEV(disk->major, disk->first_minor); } static inline dev_t part_devt(struct hd_struct *part) @@ -244,6 +245,7 @@ static inline dev_t part_devt(struct hd_struct *part) return part_to_dev(part)->devt; } +extern struct hd_struct *__disk_get_part(struct gendisk *disk, int partno); extern struct hd_struct *disk_get_part(struct gendisk *disk, int partno); static inline void disk_put_part(struct hd_struct *part) diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 86d53a3cb497..3203e36b2ee8 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -4,6 +4,7 @@ /* Simple interface for creating and stopping kernel threads without mess. */ #include <linux/err.h> #include <linux/sched.h> +#include <linux/cgroup.h> __printf(4, 5) struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), @@ -199,4 +200,14 @@ bool kthread_cancel_delayed_work_sync(struct kthread_delayed_work *work); void kthread_destroy_worker(struct kthread_worker *worker); +#ifdef CONFIG_BLK_CGROUP +void kthread_associate_blkcg(struct cgroup_subsys_state *css); +struct cgroup_subsys_state *kthread_blkcg(void); +#else +static inline void kthread_associate_blkcg(struct cgroup_subsys_state *css) { } +static inline struct cgroup_subsys_state *kthread_blkcg(void) +{ + return NULL; +} +#endif #endif /* _LINUX_KTHREAD_H */ diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index a29a8db5cc2f..2d1d9de06728 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -57,6 +57,7 @@ typedef int (nvm_get_l2p_tbl_fn)(struct nvm_dev *, u64, u32, typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, u8 *); typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct ppa_addr *, int, int); typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); +typedef int (nvm_submit_io_sync_fn)(struct nvm_dev *, struct nvm_rq *); typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *); typedef void (nvm_destroy_dma_pool_fn)(void *); typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t, @@ -70,6 +71,7 @@ struct nvm_dev_ops { nvm_op_set_bb_fn *set_bb_tbl; nvm_submit_io_fn *submit_io; + nvm_submit_io_sync_fn *submit_io_sync; nvm_create_dma_pool_fn *create_dma_pool; nvm_destroy_dma_pool_fn *destroy_dma_pool; @@ -461,10 +463,9 @@ struct nvm_tgt_type { /* For internal use */ struct list_head list; + struct module *owner; }; -extern struct nvm_tgt_type *nvm_find_target_type(const char *, int); - extern int nvm_register_tgt_type(struct nvm_tgt_type *); extern void nvm_unregister_tgt_type(struct nvm_tgt_type *); @@ -479,10 +480,8 @@ extern int nvm_set_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr *, int, int); extern int nvm_max_phys_sects(struct nvm_tgt_dev *); extern int nvm_submit_io(struct nvm_tgt_dev *, struct nvm_rq *); +extern int nvm_submit_io_sync(struct nvm_tgt_dev *, struct nvm_rq *); extern int nvm_erase_sync(struct nvm_tgt_dev *, struct ppa_addr *, int); -extern int nvm_set_rqd_ppalist(struct nvm_tgt_dev *, struct nvm_rq *, - const struct ppa_addr *, int, int); -extern void nvm_free_rqd_ppalist(struct nvm_tgt_dev *, struct nvm_rq *); extern int nvm_get_l2p_tbl(struct nvm_tgt_dev *, u64, u32, nvm_l2p_update_fn *, void *); extern int nvm_get_area(struct nvm_tgt_dev *, sector_t *, sector_t); @@ -491,8 +490,6 @@ extern void nvm_end_io(struct nvm_rq *); extern int nvm_bb_tbl_fold(struct nvm_dev *, u8 *, int); extern int nvm_get_tgt_bb_tbl(struct nvm_tgt_dev *, struct ppa_addr, u8 *); -extern int nvm_dev_factory(struct nvm_dev *, int flags); - extern void nvm_part_to_tgt(struct nvm_dev *, sector_t *, int); #else /* CONFIG_NVM */ diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index a726f96010d5..496ff759f84c 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -40,6 +40,8 @@ * @node_name: FC WWNN for the port * @port_name: FC WWPN for the port * @port_role: What NVME roles are supported (see FC_PORT_ROLE_xxx) + * @dev_loss_tmo: maximum delay for reconnects to an association on + * this device. Used only on a remoteport. * * Initialization values for dynamic port fields: * @port_id: FC N_Port_ID currently assigned the port. Upper 8 bits must @@ -50,6 +52,7 @@ struct nvme_fc_port_info { u64 port_name; u32 port_role; u32 port_id; + u32 dev_loss_tmo; }; @@ -102,8 +105,6 @@ enum nvmefc_fcp_datadir { }; -#define NVME_FC_MAX_SEGMENTS 256 - /** * struct nvmefc_fcp_req - Request structure passed from NVME-FC transport * to LLDD in order to perform a NVME FCP IO operation. @@ -202,6 +203,9 @@ enum nvme_fc_obj_state { * The length of the buffer corresponds to the local_priv_sz * value specified in the nvme_fc_port_template supplied by * the LLDD. + * @dev_loss_tmo: maximum delay for reconnects to an association on + * this device. To modify, lldd must call + * nvme_fc_set_remoteport_devloss(). * * Fields with dynamic values. Values may change base on link state. LLDD * may reference fields directly to change them. Initialized by the @@ -259,10 +263,9 @@ struct nvme_fc_remote_port { u32 port_role; u64 node_name; u64 port_name; - struct nvme_fc_local_port *localport; - void *private; + u32 dev_loss_tmo; /* dynamic fields */ u32 port_id; @@ -446,6 +449,10 @@ int nvme_fc_register_remoteport(struct nvme_fc_local_port *localport, int nvme_fc_unregister_remoteport(struct nvme_fc_remote_port *remoteport); +void nvme_fc_rescan_remoteport(struct nvme_fc_remote_port *remoteport); + +int nvme_fc_set_remoteport_devloss(struct nvme_fc_remote_port *remoteport, + u32 dev_loss_tmo); /* diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 9310ce77d8e1..aea87f0d917b 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -90,6 +90,14 @@ enum { }; #define NVME_AQ_DEPTH 32 +#define NVME_NR_AEN_COMMANDS 1 +#define NVME_AQ_BLK_MQ_DEPTH (NVME_AQ_DEPTH - NVME_NR_AEN_COMMANDS) + +/* + * Subtract one to leave an empty queue entry for 'Full Queue' condition. See + * NVM-Express 1.2 specification, section 4.1.2. + */ +#define NVME_AQ_MQ_TAG_DEPTH (NVME_AQ_BLK_MQ_DEPTH - 1) enum { NVME_REG_CAP = 0x0000, /* Controller Capabilities */ @@ -267,6 +275,7 @@ enum { NVME_CTRL_OACS_SEC_SUPP = 1 << 0, NVME_CTRL_OACS_DIRECTIVES = 1 << 5, NVME_CTRL_OACS_DBBUF_SUPP = 1 << 8, + NVME_CTRL_LPA_CMD_EFFECTS_LOG = 1 << 1, }; struct nvme_lbaf { @@ -396,6 +405,21 @@ struct nvme_fw_slot_info_log { }; enum { + NVME_CMD_EFFECTS_CSUPP = 1 << 0, + NVME_CMD_EFFECTS_LBCC = 1 << 1, + NVME_CMD_EFFECTS_NCC = 1 << 2, + NVME_CMD_EFFECTS_NIC = 1 << 3, + NVME_CMD_EFFECTS_CCC = 1 << 4, + NVME_CMD_EFFECTS_CSE_MASK = 3 << 16, +}; + +struct nvme_effects_log { + __le32 acs[256]; + __le32 iocs[256]; + __u8 resv[2048]; +}; + +enum { NVME_SMART_CRIT_SPARE = 1 << 0, NVME_SMART_CRIT_TEMPERATURE = 1 << 1, NVME_SMART_CRIT_RELIABILITY = 1 << 2, @@ -404,6 +428,10 @@ enum { }; enum { + NVME_AER_ERROR = 0, + NVME_AER_SMART = 1, + NVME_AER_CSS = 6, + NVME_AER_VS = 7, NVME_AER_NOTICE_NS_CHANGED = 0x0002, NVME_AER_NOTICE_FW_ACT_STARTING = 0x0102, }; @@ -681,6 +709,7 @@ enum nvme_admin_opcode { nvme_admin_format_nvm = 0x80, nvme_admin_security_send = 0x81, nvme_admin_security_recv = 0x82, + nvme_admin_sanitize_nvm = 0x84, }; enum { @@ -712,6 +741,7 @@ enum { NVME_LOG_ERROR = 0x01, NVME_LOG_SMART = 0x02, NVME_LOG_FW_SLOT = 0x03, + NVME_LOG_CMD_EFFECTS = 0x05, NVME_LOG_DISC = 0x70, NVME_LOG_RESERVATION = 0x80, NVME_FWACT_REPL = (0 << 3), diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index a1904aadbc45..0dcc60e820de 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -211,10 +211,14 @@ bool sbitmap_any_bit_set(const struct sbitmap *sb); */ bool sbitmap_any_bit_clear(const struct sbitmap *sb); +#define SB_NR_TO_INDEX(sb, bitnr) ((bitnr) >> (sb)->shift) +#define SB_NR_TO_BIT(sb, bitnr) ((bitnr) & ((1U << (sb)->shift) - 1U)) + typedef bool (*sb_for_each_fn)(struct sbitmap *, unsigned int, void *); /** - * sbitmap_for_each_set() - Iterate over each set bit in a &struct sbitmap. + * __sbitmap_for_each_set() - Iterate over each set bit in a &struct sbitmap. + * @start: Where to start the iteration. * @sb: Bitmap to iterate over. * @fn: Callback. Should return true to continue or false to break early. * @data: Pointer to pass to callback. @@ -222,35 +226,61 @@ typedef bool (*sb_for_each_fn)(struct sbitmap *, unsigned int, void *); * This is inline even though it's non-trivial so that the function calls to the * callback will hopefully get optimized away. */ -static inline void sbitmap_for_each_set(struct sbitmap *sb, sb_for_each_fn fn, - void *data) +static inline void __sbitmap_for_each_set(struct sbitmap *sb, + unsigned int start, + sb_for_each_fn fn, void *data) { - unsigned int i; + unsigned int index; + unsigned int nr; + unsigned int scanned = 0; - for (i = 0; i < sb->map_nr; i++) { - struct sbitmap_word *word = &sb->map[i]; - unsigned int off, nr; + if (start >= sb->depth) + start = 0; + index = SB_NR_TO_INDEX(sb, start); + nr = SB_NR_TO_BIT(sb, start); - if (!word->word) - continue; + while (scanned < sb->depth) { + struct sbitmap_word *word = &sb->map[index]; + unsigned int depth = min_t(unsigned int, word->depth - nr, + sb->de |