diff options
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/bio.h | 2 | ||||
| -rw-r--r-- | include/linux/blk-mq.h | 5 | ||||
| -rw-r--r-- | include/linux/blk_types.h | 31 | ||||
| -rw-r--r-- | include/linux/blkdev.h | 30 | ||||
| -rw-r--r-- | include/linux/drbd.h | 10 | ||||
| -rw-r--r-- | include/linux/drbd_genl.h | 7 | ||||
| -rw-r--r-- | include/linux/drbd_limits.h | 15 | ||||
| -rw-r--r-- | include/linux/fs.h | 18 | ||||
| -rw-r--r-- | include/linux/genhd.h | 8 | ||||
| -rw-r--r-- | include/linux/lightnvm.h | 34 | ||||
| -rw-r--r-- | include/linux/nvme-rdma.h | 71 | ||||
| -rw-r--r-- | include/linux/nvme.h | 406 | ||||
| -rw-r--r-- | include/trace/events/f2fs.h | 4 |
13 files changed, 539 insertions, 102 deletions
diff --git a/include/linux/bio.h b/include/linux/bio.h index b7e1a00810f2..583c10810e32 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -663,8 +663,6 @@ static inline void bio_inc_remaining(struct bio *bio) * and the bvec_slabs[]. */ #define BIO_POOL_SIZE 2 -#define BIOVEC_NR_POOLS 6 -#define BIOVEC_MAX_IDX (BIOVEC_NR_POOLS - 1) struct bio_set { struct kmem_cache *bio_slab; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 2498fdf3a503..e43bbffb5b7a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -96,6 +96,7 @@ typedef int (init_request_fn)(void *, struct request *, unsigned int, unsigned int, unsigned int); typedef void (exit_request_fn)(void *, struct request *, unsigned int, unsigned int); +typedef int (reinit_request_fn)(void *, struct request *); typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *, bool); @@ -145,6 +146,7 @@ struct blk_mq_ops { */ init_request_fn *init_request; exit_request_fn *exit_request; + reinit_request_fn *reinit_request; }; enum { @@ -196,6 +198,8 @@ enum { struct request *blk_mq_alloc_request(struct request_queue *q, int rw, unsigned int flags); +struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int op, + unsigned int flags, unsigned int hctx_idx); struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag); struct cpumask *blk_mq_tags_cpumask(struct blk_mq_tags *tags); @@ -243,6 +247,7 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, void blk_mq_freeze_queue(struct request_queue *q); void blk_mq_unfreeze_queue(struct request_queue *q); void blk_mq_freeze_queue_start(struct request_queue *q); +int blk_mq_reinit_tagset(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 b588e968dc01..f254eb264924 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -26,11 +26,11 @@ typedef void (bio_destructor_t) (struct bio *); struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; - unsigned int bi_flags; /* status, command, etc */ int bi_error; unsigned int bi_rw; /* bottom bits req flags, * top bits REQ_OP */ + unsigned short bi_flags; /* status, command, etc */ unsigned short bi_ioprio; struct bvec_iter bi_iter; @@ -114,19 +114,25 @@ struct bio { /* * Flags starting here get preserved by bio_reset() - this includes - * BIO_POOL_IDX() + * BVEC_POOL_IDX() */ -#define BIO_RESET_BITS 13 -#define BIO_OWNS_VEC 13 /* bio_free() should free bvec */ +#define BIO_RESET_BITS 10 /* - * top 4 bits of bio flags indicate the pool this bio came from + * We support 6 different bvec pools, the last one is magic in that it + * is backed by a mempool. */ -#define BIO_POOL_BITS (4) -#define BIO_POOL_NONE ((1UL << BIO_POOL_BITS) - 1) -#define BIO_POOL_OFFSET (32 - BIO_POOL_BITS) -#define BIO_POOL_MASK (1UL << BIO_POOL_OFFSET) -#define BIO_POOL_IDX(bio) ((bio)->bi_flags >> BIO_POOL_OFFSET) +#define BVEC_POOL_NR 6 +#define BVEC_POOL_MAX (BVEC_POOL_NR - 1) + +/* + * Top 4 bits of bio flags indicate the pool the bvecs came from. We add + * 1 to the actual index so that 0 indicates that there are no bvecs to be + * freed. + */ +#define BVEC_POOL_BITS (4) +#define BVEC_POOL_OFFSET (16 - BVEC_POOL_BITS) +#define BVEC_POOL_IDX(bio) ((bio)->bi_flags >> BVEC_POOL_OFFSET) #endif /* CONFIG_BLOCK */ @@ -143,7 +149,6 @@ enum rq_flag_bits { __REQ_SYNC, /* request is sync (sync write or read) */ __REQ_META, /* metadata io request */ __REQ_PRIO, /* boost priority in cfq */ - __REQ_SECURE, /* secure discard (used with REQ_OP_DISCARD) */ __REQ_NOIDLE, /* don't anticipate more IO after this one */ __REQ_INTEGRITY, /* I/O includes block integrity payload */ @@ -192,7 +197,7 @@ enum rq_flag_bits { (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) #define REQ_COMMON_MASK \ (REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | REQ_NOIDLE | \ - REQ_PREFLUSH | REQ_FUA | REQ_SECURE | REQ_INTEGRITY | REQ_NOMERGE) + REQ_PREFLUSH | REQ_FUA | REQ_INTEGRITY | REQ_NOMERGE) #define REQ_CLONE_MASK REQ_COMMON_MASK /* This mask is used for both bio and request merge checking */ @@ -219,7 +224,6 @@ enum rq_flag_bits { #define REQ_FLUSH_SEQ (1ULL << __REQ_FLUSH_SEQ) #define REQ_IO_STAT (1ULL << __REQ_IO_STAT) #define REQ_MIXED_MERGE (1ULL << __REQ_MIXED_MERGE) -#define REQ_SECURE (1ULL << __REQ_SECURE) #define REQ_PM (1ULL << __REQ_PM) #define REQ_HASHED (1ULL << __REQ_HASHED) #define REQ_MQ_INFLIGHT (1ULL << __REQ_MQ_INFLIGHT) @@ -228,6 +232,7 @@ enum req_op { REQ_OP_READ, REQ_OP_WRITE, REQ_OP_DISCARD, /* request to discard sectors */ + REQ_OP_SECURE_ERASE, /* request to securely erase sectors */ REQ_OP_WRITE_SAME, /* write same block many times */ REQ_OP_FLUSH, /* request for cache flush */ }; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 48f05d768a53..c96db9c22d10 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -496,7 +496,7 @@ struct request_queue { #define QUEUE_FLAG_DISCARD 14 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 15 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 16 /* Contributes to random pool */ -#define QUEUE_FLAG_SECDISCARD 17 /* supports SECDISCARD */ +#define QUEUE_FLAG_SECERASE 17 /* supports secure erase */ #define QUEUE_FLAG_SAME_FORCE 18 /* force complete on same CPU */ #define QUEUE_FLAG_DEAD 19 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 20 /* queue is initialized */ @@ -593,8 +593,8 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #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_secdiscard(q) (blk_queue_discard(q) && \ - test_bit(QUEUE_FLAG_SECDISCARD, &(q)->queue_flags)) +#define blk_queue_secure_erase(q) \ + (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_noretry_request(rq) \ @@ -676,21 +676,6 @@ static inline bool rq_mergeable(struct request *rq) return true; } -static inline bool blk_check_merge_flags(unsigned int flags1, unsigned int op1, - unsigned int flags2, unsigned int op2) -{ - if ((op1 == REQ_OP_DISCARD) != (op2 == REQ_OP_DISCARD)) - return false; - - if ((flags1 & REQ_SECURE) != (flags2 & REQ_SECURE)) - return false; - - if ((op1 == REQ_OP_WRITE_SAME) != (op2 == REQ_OP_WRITE_SAME)) - return false; - - return true; -} - static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b) { if (bio_data(a) == bio_data(b)) @@ -804,8 +789,6 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); extern void __blk_put_request(struct request_queue *, struct request *); extern struct request *blk_get_request(struct request_queue *, int, gfp_t); -extern struct request *blk_make_request(struct request_queue *, struct bio *, - gfp_t); extern void blk_rq_set_block_pc(struct request *); extern void blk_requeue_request(struct request_queue *, struct request *); extern void blk_add_request_payload(struct request *rq, struct page *page, @@ -818,6 +801,7 @@ extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, extern void blk_rq_unprep_clone(struct request *rq); extern int blk_insert_cloned_request(struct request_queue *q, struct request *rq); +extern int blk_rq_append_bio(struct request *rq, struct bio *bio); extern void blk_delay_queue(struct request_queue *, unsigned long); extern void blk_queue_split(struct request_queue *, struct bio **, struct bio_set *); @@ -1154,13 +1138,15 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, return bqt->tag_index[tag]; } -#define BLKDEV_DISCARD_SECURE 0x01 /* secure discard */ + +#define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */ +#define BLKDEV_DISCARD_ZERO (1 << 1) /* must reliably zero data */ extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *); extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, int op_flags, + sector_t nr_sects, gfp_t gfp_mask, int flags, struct bio **biop); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); diff --git a/include/linux/drbd.h b/include/linux/drbd.h index d6b3c9943a2c..002611c85318 100644 --- a/include/linux/drbd.h +++ b/include/linux/drbd.h @@ -51,7 +51,7 @@ #endif extern const char *drbd_buildtag(void); -#define REL_VERSION "8.4.6" +#define REL_VERSION "8.4.7" #define API_VERSION 1 #define PRO_VERSION_MIN 86 #define PRO_VERSION_MAX 101 @@ -370,6 +370,14 @@ enum drbd_notification_type { NOTIFY_FLAGS = NOTIFY_CONTINUES, }; +enum drbd_peer_state { + P_INCONSISTENT = 3, + P_OUTDATED = 4, + P_DOWN = 5, + P_PRIMARY = 6, + P_FENCING = 7, +}; + #define UUID_JUST_CREATED ((__u64)4) enum write_ordering_e { diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h index 2d0e5ad5de9d..c934d3a96b5e 100644 --- a/include/linux/drbd_genl.h +++ b/include/linux/drbd_genl.h @@ -123,15 +123,16 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf, __u32_field_def(13, DRBD_GENLA_F_MANDATORY, c_fill_target, DRBD_C_FILL_TARGET_DEF) __u32_field_def(14, DRBD_GENLA_F_MANDATORY, c_max_rate, DRBD_C_MAX_RATE_DEF) __u32_field_def(15, DRBD_GENLA_F_MANDATORY, c_min_rate, DRBD_C_MIN_RATE_DEF) + __u32_field_def(20, DRBD_GENLA_F_MANDATORY, disk_timeout, DRBD_DISK_TIMEOUT_DEF) + __u32_field_def(21, 0 /* OPTIONAL */, read_balancing, DRBD_READ_BALANCING_DEF) + __u32_field_def(25, 0 /* OPTIONAL */, rs_discard_granularity, DRBD_RS_DISCARD_GRANULARITY_DEF) __flg_field_def(16, DRBD_GENLA_F_MANDATORY, disk_barrier, DRBD_DISK_BARRIER_DEF) __flg_field_def(17, DRBD_GENLA_F_MANDATORY, disk_flushes, DRBD_DISK_FLUSHES_DEF) __flg_field_def(18, DRBD_GENLA_F_MANDATORY, disk_drain, DRBD_DISK_DRAIN_DEF) __flg_field_def(19, DRBD_GENLA_F_MANDATORY, md_flushes, DRBD_MD_FLUSHES_DEF) - __u32_field_def(20, DRBD_GENLA_F_MANDATORY, disk_timeout, DRBD_DISK_TIMEOUT_DEF) - __u32_field_def(21, 0 /* OPTIONAL */, read_balancing, DRBD_READ_BALANCING_DEF) - /* 9: __u32_field_def(22, DRBD_GENLA_F_MANDATORY, unplug_watermark, DRBD_UNPLUG_WATERMARK_DEF) */ __flg_field_def(23, 0 /* OPTIONAL */, al_updates, DRBD_AL_UPDATES_DEF) + __flg_field_def(24, 0 /* OPTIONAL */, discard_zeroes_if_aligned, DRBD_DISCARD_ZEROES_IF_ALIGNED) ) GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts, diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h index 8ac8c5d9a3ad..ddac68422a96 100644 --- a/include/linux/drbd_limits.h +++ b/include/linux/drbd_limits.h @@ -126,8 +126,7 @@ #define DRBD_RESYNC_RATE_DEF 250 #define DRBD_RESYNC_RATE_SCALE 'k' /* kilobytes */ - /* less than 7 would hit performance unnecessarily. */ -#define DRBD_AL_EXTENTS_MIN 7 +#define DRBD_AL_EXTENTS_MIN 67 /* we use u16 as "slot number", (u16)~0 is "FREE". * If you use >= 292 kB on-disk ring buffer, * this is the maximum you can use: */ @@ -210,6 +209,12 @@ #define DRBD_MD_FLUSHES_DEF 1 #define DRBD_TCP_CORK_DEF 1 #define DRBD_AL_UPDATES_DEF 1 +/* We used to ignore the discard_zeroes_data setting. + * To not change established (and expected) behaviour, + * by default assume that, for discard_zeroes_data=0, + * we can make that an effective discard_zeroes_data=1, + * if we only explicitly zero-out unaligned partial chunks. */ +#define DRBD_DISCARD_ZEROES_IF_ALIGNED 1 #define DRBD_ALLOW_TWO_PRIMARIES_DEF 0 #define DRBD_ALWAYS_ASBP_DEF 0 @@ -230,4 +235,10 @@ #define DRBD_SOCKET_CHECK_TIMEO_MAX DRBD_PING_TIMEO_MAX #define DRBD_SOCKET_CHECK_TIMEO_DEF 0 #define DRBD_SOCKET_CHECK_TIMEO_SCALE '1' + +#define DRBD_RS_DISCARD_GRANULARITY_MIN 0 +#define DRBD_RS_DISCARD_GRANULARITY_MAX (1<<20) /* 1MiByte */ +#define DRBD_RS_DISCARD_GRANULARITY_DEF 0 /* disabled by default */ +#define DRBD_RS_DISCARD_GRANULARITY_SCALE '1' /* bytes */ + #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index 183024525d40..dc488662ce0b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -178,9 +178,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, * READ_SYNC A synchronous read. Device is not plugged, caller can * immediately wait on this read without caring about * unplugging. - * READA Used for read-ahead operations. Lower priority, and the - * block layer could (in theory) choose to ignore this - * request if it runs into resource problems. * WRITE A normal async write. Device will be plugged. * WRITE_SYNC Synchronous write. Identical to WRITE, but passes down * the hint that someone will be waiting on this IO @@ -195,11 +192,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, * */ #define RW_MASK REQ_OP_WRITE -#define RWA_MASK REQ_RAHEAD #define READ REQ_OP_READ -#define WRITE RW_MASK -#define READA RWA_MASK +#define WRITE REQ_OP_WRITE #define READ_SYNC REQ_SYNC #define WRITE_SYNC (REQ_SYNC | REQ_NOIDLE) @@ -2471,17 +2466,6 @@ static inline bool op_is_write(unsigned int op) } /* - * return READ, READA, or WRITE - */ -static inline int bio_rw(struct bio *bio) -{ - if (op_is_write(bio_op(bio))) - return WRITE; - - return bio->bi_rw & RWA_MASK; -} - -/* * return data direction, READ or WRITE */ static inline int bio_data_dir(struct bio *bio) diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 359a8e4bd44d..1dbf52f9c24b 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -205,7 +205,6 @@ struct gendisk { void *private_data; int flags; - struct device *driverfs_dev; // FIXME: remove struct kobject *slave_dir; struct timer_rand_state *random; @@ -414,7 +413,12 @@ static inline void free_part_info(struct hd_struct *part) extern void part_round_stats(int cpu, struct hd_struct *part); /* block/genhd.c */ -extern void add_disk(struct gendisk *disk); +extern void device_add_disk(struct device *parent, struct gendisk *disk); +static inline void add_disk(struct gendisk *disk) +{ + device_add_disk(NULL, disk); +} + extern void del_gendisk(struct gendisk *gp); extern struct gendisk *get_gendisk(dev_t dev, int *partno); extern struct block_device *bdget_disk(struct gendisk *disk, int partno); diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index ef2c7d2e76c4..ba78b8306674 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -1,7 +1,9 @@ #ifndef NVM_H #define NVM_H +#include <linux/blkdev.h> #include <linux/types.h> +#include <uapi/linux/lightnvm.h> enum { NVM_IO_OK = 0, @@ -269,24 +271,15 @@ struct nvm_lun { int lun_id; int chnl_id; - /* It is up to the target to mark blocks as closed. If the target does - * not do it, all blocks are marked as open, and nr_open_blocks - * represents the number of blocks in use - */ - unsigned int nr_open_blocks; /* Number of used, writable blocks */ - unsigned int nr_closed_blocks; /* Number of used, read-only blocks */ - unsigned int nr_free_blocks; /* Number of unused blocks */ - unsigned int nr_bad_blocks; /* Number of bad blocks */ - spinlock_t lock; + unsigned int nr_free_blocks; /* Number of unused blocks */ struct nvm_block *blocks; }; enum { NVM_BLK_ST_FREE = 0x1, /* Free block */ - NVM_BLK_ST_OPEN = 0x2, /* Open block - read-write */ - NVM_BLK_ST_CLOSED = 0x4, /* Closed block - read-only */ + NVM_BLK_ST_TGT = 0x2, /* Block in use by target */ NVM_BLK_ST_BAD = 0x8, /* Bad block */ }; @@ -385,6 +378,7 @@ static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev, { struct ppa_addr l; + l.ppa = 0; /* * (r.ppa << X offset) & X len bitmask. X eq. blk, pg, etc. */ @@ -455,6 +449,8 @@ struct nvm_tgt_type { struct list_head list; }; +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 *); @@ -463,6 +459,9 @@ extern void nvm_dev_dma_free(struct nvm_dev *, void *, dma_addr_t); typedef int (nvmm_register_fn)(struct nvm_dev *); typedef void (nvmm_unregister_fn)(struct nvm_dev *); + +typedef int (nvmm_create_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_create *); +typedef int (nvmm_remove_tgt_fn)(struct nvm_dev *, struct nvm_ioctl_remove *); typedef struct nvm_block *(nvmm_get_blk_fn)(struct nvm_dev *, struct nvm_lun *, unsigned long); typedef void (nvmm_put_blk_fn)(struct nvm_dev *, struct nvm_block *); @@ -488,9 +487,10 @@ struct nvmm_type { nvmm_register_fn *register_mgr; nvmm_unregister_fn *unregister_mgr; + nvmm_create_tgt_fn *create_tgt; + nvmm_remove_tgt_fn *remove_tgt; + /* Block administration callbacks */ - nvmm_get_blk_fn *get_blk_unlocked; - nvmm_put_blk_fn *put_blk_unlocked; nvmm_get_blk_fn *get_blk; nvmm_put_blk_fn *put_blk; nvmm_open_blk_fn *open_blk; @@ -520,10 +520,6 @@ struct nvmm_type { extern int nvm_register_mgr(struct nvmm_type *); extern void nvm_unregister_mgr(struct nvmm_type *); -extern struct nvm_block *nvm_get_blk_unlocked(struct nvm_dev *, - struct nvm_lun *, unsigned long); -extern void nvm_put_blk_unlocked(struct nvm_dev *, struct nvm_block *); - extern struct nvm_block *nvm_get_blk(struct nvm_dev *, struct nvm_lun *, unsigned long); extern void nvm_put_blk(struct nvm_dev *, struct nvm_block *); @@ -532,11 +528,13 @@ extern int nvm_register(struct request_queue *, char *, struct nvm_dev_ops *); extern void nvm_unregister(char *); +void nvm_mark_blk(struct nvm_dev *dev, struct ppa_addr ppa, int type); + extern int nvm_submit_io(struct nvm_dev *, struct nvm_rq *); extern void nvm_generic_to_addr_mode(struct nvm_dev *, struct nvm_rq *); extern void nvm_addr_to_generic_mode(struct nvm_dev *, struct nvm_rq *); extern int nvm_set_rqd_ppalist(struct nvm_dev *, struct nvm_rq *, - struct ppa_addr *, int, int); + const struct ppa_addr *, int, int); extern void nvm_free_rqd_ppalist(struct nvm_dev *, struct nvm_rq *); extern int nvm_erase_ppa(struct nvm_dev *, struct ppa_addr *, int); extern int nvm_erase_blk(struct nvm_dev *, struct nvm_block *); diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h new file mode 100644 index 000000000000..bf240a3cbf99 --- /dev/null +++ b/include/linux/nvme-rdma.h @@ -0,0 +1,71 @@ +/* + * Copyright (c) 2015 Mellanox Technologies. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope 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 _LINUX_NVME_RDMA_H +#define _LINUX_NVME_RDMA_H + +enum nvme_rdma_cm_fmt { + NVME_RDMA_CM_FMT_1_0 = 0x0, +}; + +enum nvme_rdma_cm_status { + NVME_RDMA_CM_INVALID_LEN = 0x01, + NVME_RDMA_CM_INVALID_RECFMT = 0x02, + NVME_RDMA_CM_INVALID_QID = 0x03, + NVME_RDMA_CM_INVALID_HSQSIZE = 0x04, + NVME_RDMA_CM_INVALID_HRQSIZE = 0x05, + NVME_RDMA_CM_NO_RSC = 0x06, + NVME_RDMA_CM_INVALID_IRD = 0x07, + NVME_RDMA_CM_INVALID_ORD = 0x08, +}; + +/** + * struct nvme_rdma_cm_req - rdma connect request + * + * @recfmt: format of the RDMA Private Data + * @qid: queue Identifier for the Admin or I/O Queue + * @hrqsize: host receive queue size to be created + * @hsqsize: host send queue size to be created + */ +struct nvme_rdma_cm_req { + __le16 recfmt; + __le16 qid; + __le16 hrqsize; + __le16 hsqsize; + u8 rsvd[24]; +}; + +/** + * struct nvme_rdma_cm_rep - rdma connect reply + * + * @recfmt: format of the RDMA Private Data + * @crqsize: controller receive queue size + */ +struct nvme_rdma_cm_rep { + __le16 recfmt; + __le16 crqsize; + u8 rsvd[28]; +}; + +/** + * struct nvme_rdma_cm_rej - rdma connect reject + * + * @recfmt: format of the RDMA Private Data + * @fsts: error status for the associated connect request + */ +struct nvme_rdma_cm_rej { + __le16 recfmt; + __le16 sts; +}; + +#endif /* _LINUX_NVME_RDMA_H */ diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 7d51b2904cb7..d8b37bab2887 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -16,6 +16,78 @@ #define _LINUX_NVME_H #include <linux/types.h> +#include <linux/uuid.h> + +/* NQN names in commands fields specified one size */ +#define NVMF_NQN_FIELD_LEN 256 + +/* However the max length of a qualified name is another size */ +#define NVMF_NQN_SIZE 223 + +#define NVMF_TRSVCID_SIZE 32 +#define NVMF_TRADDR_SIZE 256 +#define NVMF_TSAS_SIZE 256 + +#define NVME_DISC_SUBSYS_NAME "nqn.2014-08.org.nvmexpress.discovery" + +#define NVME_RDMA_IP_PORT 4420 + +enum nvme_subsys_type { + NVME_NQN_DISC = 1, /* Discovery type target subsystem */ + NVME_NQN_NVME = 2, /* NVME type target subsystem */ +}; + +/* Address Family codes for Discovery Log Page entry ADRFAM field */ +enum { + NVMF_ADDR_FAMILY_PCI = 0, /* PCIe */ + NVMF_ADDR_FAMILY_IP4 = 1, /* IP4 */ + NVMF_ADDR_FAMILY_IP6 = 2, /* IP6 */ + NVMF_ADDR_FAMILY_IB = 3, /* InfiniBand */ + NVMF_ADDR_FAMILY_FC = 4, /* Fibre Channel */ +}; + +/* Transport Type codes for Discovery Log Page entry TRTYPE field */ +enum { + NVMF_TRTYPE_RDMA = 1, /* RDMA */ + NVMF_TRTYPE_FC = 2, /* Fibre Channel */ + NVMF_TRTYPE_LOOP = 254, /* Reserved for host usage */ + NVMF_TRTYPE_MAX, +}; + +/* Transport Requirements codes for Discovery Log Page entry TREQ field */ +enum { + NVMF_TREQ_NOT_SPECIFIED = 0, /* Not specified */ + NVMF_TREQ_REQUIRED = 1, /* Required */ + NVMF_TREQ_NOT_REQUIRED = 2, /* Not Required */ +}; + +/* RDMA QP Service Type codes for Discovery Log Page entry TSAS + * RDMA_QPTYPE field + */ +enum { + NVMF_RDMA_QPTYPE_CONNECTED = 0, /* Reliable Connected */ + NVMF_RDMA_QPTYPE_DATAGRAM = 1, /* Reliable Datagram */ +}; + +/* RDMA QP Service Type codes for Discovery Log Page entry TSAS + * RDMA_QPTYPE field + */ +enum { + NVMF_RDMA_PRTYPE_NOT_SPECIFIED = 0, /* No Provider Specified */ + NVMF_RDMA_PRTYPE_IB = 1, /* InfiniBand */ + NVMF_RDMA_PRTYPE_ROCE = 2, /* InfiniBand RoCE */ + NVMF_RDMA_PRTYPE_ROCEV2 = 3, /* InfiniBand RoCEV2 */ + NVMF_RDMA_PRTYPE_IWARP = 4, /* IWARP */ +}; + +/* RDMA Connection Management Service Type codes for Discovery Log Page + * entry TSAS RDMA_CMS field + */ +enum { + NVMF_RDMA_CMS_RDMA_CM = 0, /* Sockets based enpoint addressing */ +}; + +#define NVMF_AQ_DEPTH 32 enum { NVME_REG_CAP = 0x0000, /* Controller Capabilities */ @@ -50,6 +122,13 @@ enum { #define NVME_CMB_CQS(cmbsz) ((cmbsz) & 0x2) #define NVME_CMB_SQS(cmbsz) ((cmbsz) & 0x1) +/* + * Submission and Completion Queue Entry Sizes for the NVM command set. + * (In bytes and specified as a power of two (2^n)). + */ +#define NVME_NVM_IOSQES 6 +#define NVME_NVM_IOCQES 4 + enum { NVME_CC_ENABLE = 1 << 0, NVME_CC_CSS_NVM = 0 << 4, @@ -61,8 +140,8 @@ enum { NVME_CC_SHN_NORMAL = 1 << 14, NVME_CC_SHN_ABRUPT = 2 << 14, NVME_CC_SHN_MASK = 3 << 14, - NVME_CC_IOSQES = 6 << 16, - NVME_CC_IOCQES = 4 << 20, + NVME_CC_IOSQES = NVME_NVM_IOSQES << 16, + NVME_CC_IOCQES = NVME_NVM_IOCQES << 20, NVME_CSTS_RDY = 1 << 0, NVME_CSTS_CFS = 1 << 1, NVME_CSTS_NSSRO = 1 << 4, @@ -107,7 +186,11 @@ struct nvme_id_ctrl { __u8 mdts; __le16 cntlid; __le32 ver; - __u8 rsvd84[172]; + __le32 rtd3r; + __le32 rtd3e; + __le32 oaes; + __le32 ctratt; + __u8 rsvd100[156]; __le16 oacs; __u8 acl; __u8 aerl; @@ -119,10 +202,12 @@ struct nvme_id_ctrl { __u8 apsta; __le16 wctemp; __le16 cctemp; - __u8 rsvd270[242]; + __u8 rsvd270[50]; + __le16 kas; + __u8 rsvd322[190]; __u8 sqes; __u8 cqes; - __u8 rsvd514[2]; + __le16 maxcmd; __le32 nn; __le16 oncs; __le16 fuses; @@ -135,7 +220,15 @@ struct nvme_id_ctrl { __le16 acwu; __u8 rsvd534[2]; __le32 sgls; - __u8 rsvd540[1508]; + __u8 rsvd540[228]; + char subnqn[256]; + __u8 rsvd1024[768]; + __le32 ioccsz; + __le32 iorcsz; + __le16 icdoff; + __u8 ctrattr; + __u8 msdbd; + __u8 rsvd1804[244]; struct nvme_id_power_state psd[32]; __u8 vs[1024]; }; @@ -274,6 +367,12 @@ struct nvme_reservation_status { } regctl_ds[]; }; +enum nvme_async_event_type { + NVME_AER_TYPE_ERROR = 0, + NVME_AER_TYPE_SMART = 1, + NVME_AER_TYPE_NOTICE = 2, +}; + /* I/O commands */ enum nvme_opcode { @@ -290,6 +389,84 @@ enum nvme_opcode { nvme_cmd_resv_release = 0x15, }; +/* + * Descriptor subtype - lower 4 bits of nvme_(keyed_)sgl_desc identifier + * + * @NVME_SGL_FMT_ADDRESS: absolute address of the data block + * @NVME_SGL_FMT_OFFSET: relative offset of the in-capsule data block + * @NVME_SGL_FMT_INVALIDATE: RDMA transport specific remote invalidation + * request subtype + */ +enum { + NVME_SGL_FMT_ADDRESS = 0x00, + NVME_SGL_FMT_OFFSET = 0x01, + NVME_SGL_FMT_INVALIDATE = 0x0f, +}; + +/* + * Descriptor type - upper 4 bits of nvme_(keyed_)sgl_desc identifier + * + * For struct nvme_sgl_desc: + * @NVME_SGL_FMT_DATA_DESC: data block descriptor + * @NVME_SGL_FMT_SEG_DESC: sgl segment descriptor + * @NVME_SGL_FMT_LAST_SEG_DESC: last sgl segment descriptor + * + * For struct nvme_keyed_sgl_desc: + * @NVME_KEY_SGL_FMT_DATA_DESC: keyed data block descriptor + */ +enum { + NVME_SGL_FMT_DATA_DESC = 0x00, + NVME_SGL_FMT_SEG_DESC = 0x02, + NVME_SGL_FMT_LAST_SEG_DESC = 0x03, + NVME_KEY_SGL_FMT_DATA_DESC = 0x04, +}; + +struct nvme_sgl_desc { + __le64 addr; + __le32 length; + __u8 rsvd[3]; + __u8 type; +}; + +struct nvme_keyed_sgl_desc { + __le64 addr; + __u8 length[3]; + __u8 key[4]; + __u8 type; +}; + +union nvme_data_ptr { + struct { + __le64 prp1; + __le64 prp2; + }; + struct nvme_sgl_desc sgl; + struct nvme_keyed_sgl_desc ksgl; +}; + +/* + * Lowest two bits of our flags field (FUSE field in the spec): + * + * @NVME_CMD_FUSE_FIRST: Fused Operation, first command + * @NVME_CMD_FUSE_SECOND: Fused Operation, second command + * + * Highest two bits in our flags field (PSDT field in the spec): + * + * @NVME_CMD_PSDT_SGL_METABUF: Use SGLS for this transfer, + * If used, MPTR contains addr of single physical buffer (byte aligned). + * @NVME_CMD_PSDT_SGL_METASEG: Use SGLS for this transfer, + * If used, MPTR contains an address of an SGL segment containing + * exactly 1 SGL descriptor (qword aligned). + */ +enum { + NVME_CMD_FUSE_FIRST = (1 << 0), + NVME_CMD_FUSE_SECOND = (1 << 1), + + NVME_CMD_SGL_METABUF = (1 << 6), + NVME_CMD_SGL_METASEG = (1 << 7), + NVME_CMD_SGL_ALL = NVME_CMD_SGL_METABUF | NVME_CMD_SGL_METASEG, +}; + struct nvme_common_command { __u8 opcode; __u8 flags; @@ -297,8 +474,7 @@ struct nvme_common_command { __le32 nsid; __le32 cdw2[2]; __le64 metadata; - __le64 prp1; - __le64 prp2; + union nvme_data_ptr dptr; __le32 cdw10[6]; }; @@ -309,8 +485,7 @@ struct nvme_rw_command { __le32 nsid; __u64 rsvd2; __le64 metadata; - __le64 prp1; - __le64 prp2; + union nvme_data_ptr dptr; __le64 slba; __le16 length; __le16 control; @@ -350,8 +525,7 @@ struct nvme_dsm_cmd { __u16 command_id; __le32 nsid; __u64 rsvd2[2]; - __le64 prp1; - __le64 prp2; + union nvme_data_ptr dptr; __le32 nr; __le32 attributes; __u32 rsvd12[4]; @@ -384,6 +558,7 @@ enum nvme_admin_opcode { nvme_admin_async_event = 0x0c, nvme_admin_activate_fw = 0x10, nvme_admin_download_fw = 0x11, + nvme_admin_keep_alive = 0x18, nvme_admin_format_nvm = 0x80, nvme_admin_security_send = 0x81, nvme_admin_security_recv = 0x82, @@ -408,6 +583,7 @@ enum { NVME_FEAT_WRITE_ATOMIC = 0x0a, NVME_FEAT_ASYNC_EVENT = 0x0b, NVME_FEAT_AUTO_PST = 0x0c, + NVME_FEAT_KATO = 0x0f, NVME_FEAT_SW_PROGRESS = 0x80, NVME_FEAT_HOST_ID = 0x81, NVME_FEAT_RESV_MASK = 0x82, @@ -415,6 +591,7 @@ enum { NVME_LOG_ERROR = 0x01, NVME_LOG_SMART = 0x02, NVME_LOG_FW_SLOT = 0x03, + NVME_LOG_DISC = 0x70, NVME_LOG_RESERVATION = 0x80, NVME_FWACT_REPL = (0 << 3), NVME_FWACT_REPL_ACTV = (1 << 3), @@ -427,8 +604,7 @@ struct nvme_identify { __u16 command_id; __le32 nsid; __u64 rsvd2[2]; - __le64 prp1; - __le64 prp2; + union nvme_data_ptr dptr; __le32 cns; __u32 rsvd11[5]; }; @@ -439,8 +615,7 @@ struct nvme_features { __u16 command_id; __le32 nsid; __u64 rsvd2[2]; - __le64 prp1; - __le64 prp2; + union nvme_data_ptr dptr; __le32 fid; __le32 dword11; __u32 rsvd12[4]; @@ -499,8 +674,7 @@ struct nvme_download_firmware { __u8 flags; __u16 command_id; __u32 rsvd1[5]; - __le64 prp1; - __le64 prp2; + union nvme_data_ptr dptr; __le32 numd; __le32 offset; __u32 rsvd12[4]; @@ -516,6 +690,143 @@ struct nvme_format_cmd { __u32 rsvd11[5]; }; +struct nvme_get_log_page_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[2]; + union nvme_data_ptr dptr; + __u8 lid; + __u8 rsvd10; + __le16 numdl; + __le16 numdu; + __u16 rsvd11; + __le32 lpol; + __le32 lpou; + __u32 rsvd14[2]; +}; + +/* + * Fabrics subcommands. + */ +enum nvmf_fabrics_opcode { + nvme_fabrics_command = 0x7f, +}; + +enum nvmf_capsule_command { + nvme_fabrics_type_property_set = 0x00, + nvme_fabrics_type_connect = 0x01, + nvme_fabrics_type_property_get = 0x04, +}; + +struct nvmf_common_command { + __u8 opcode; + __u8 resv1; + __u16 command_id; + __u8 fctype; + __u8 resv2[35]; + __u8 ts[24]; +}; + +/* + * The legal cntlid range a NVMe Target will provide. + * Note that cntlid of value 0 is considered illegal in the fabrics world. + * Devices based on earlier specs did not have the subsystem concept; + * therefore, those devices had their cntlid value set to 0 as a result. + */ +#define NVME_CNTLID_MIN 1 +#define NVME_CNTLID_MAX 0xffef +#define NVME_CNTLID_DYNAMIC 0xffff + +#define MAX_DISC_LOGS 255 + +/* Discovery log page entry */ +struct nvmf_disc_rsp_page_entry { + __u8 trtype; + __u8 adrfam; + __u8 nqntype; + __u8 treq; + __le16 portid; + __le16 cntlid; + __le16 asqsz; + __u8 resv8[22]; + char trsvcid[NVMF_TRSVCID_SIZE]; + __u8 resv64[192]; + char subnqn[NVMF_NQN_FIELD_LEN]; + char traddr[NVMF_TRADDR_SIZE]; + union tsas { + char common[NVMF_TSAS_SIZE]; + struct rdma { + __u8 qptype; + __u8 prtype; + __u8 cms; + __u8 resv3[5]; + __u16 pkey; + __u8 resv10[246]; + } rdma; + } tsas; +}; + +/* Discovery log page header */ +struct nvmf_disc_rsp_page_hdr { + __le64 genctr; + __le64 numrec; + __le16 recfmt; + __u8 resv14[1006]; + struct nvmf_disc_rsp_page_entry entries[0]; +}; + +struct nvmf_connect_command { + __u8 opcode; + __u8 resv1; + __u16 command_id; + __u8 fctype; + __u8 resv2[19]; + union nvme_data_ptr dptr; + __le16 recfmt; + __le16 qid; + __le16 sqsize; + __u8 cattr; + __u8 resv3; + __le32 kato; + __u8 resv4[12]; +}; + +struct nvmf_connect_data { + uuid_le hostid; + __le16 cntlid; + char resv4[238]; + char subsysnqn[NVMF_NQN_FIELD_LEN]; + char hostnqn[NVMF_NQN_FIELD_LEN]; + char resv5[256]; +}; + +struct nvmf_property_set_command { + __u8 opcode; + __u8 resv1; + __u16 command_id; + __u8 fctype; + __u8 resv2[35]; + __u8 attrib; + __u8 resv3[3]; + __le32 offset; + __le64 value; + __u8 resv4[8]; +}; + +struct nvmf_property_get_command { + __u8 opcode; + __u8 resv1; + __u16 command_id; + __u8 fctype; + __u8 resv2[35]; + __u8 attrib; + __u8 resv3[3]; + __le32 offset; + __u8 resv4[16]; +}; + struct nvme_command { union { struct nvme_common_command common; @@ -529,10 +840,30 @@ struct nvme_command { struct nvme_format_cmd format; struct nvme_dsm_cmd dsm; struct nvme_abort_cmd abort; + struct nvme_get_log_page_command get_log_page; + struct nvmf_common_command fabrics; + struct nvmf_connect_command connect; + struct nvmf_property_set_command prop_set; + struct nvmf_property_get_command prop_get; }; }; +static inline bool nvme_is_write(struct nvme_command *cmd) +{ + /* + * What a mess... + * + * Why can't we simply have a Fabrics In and Fabrics out command? + */ + if (unlikely(cmd->common.opcode == nvme_fabrics_command)) + return cmd->fabrics.opcode & 1; + return cmd->common.opcode & 1; +} + enum { + /* + * Generic Command Status: + */ NVME_SC_SUCCESS = 0x0, NVME_SC_INVALID_OPCODE = 0x1, NVME_SC_INVALID_FIELD = 0x2, @@ -551,10 +882,18 @@ enum { NVME_SC_SGL_INVALID_DATA = 0xf, NVME_SC_SGL_INVALID_METADATA = 0x10, NVME_SC_SGL_INVALID_TYPE = 0x11, + + NVME_SC_SGL_INVALID_OFFSET = 0x16, + NVME_SC_SGL_INVALID_SUBTYPE = 0x17, + NVME_SC_LBA_RANGE = 0x80, NVME_SC_CAP_EXCEEDED = 0x81, NVME_SC_NS_NOT_READY = 0x82, NVME_SC_RESERVATION_CONFLICT = 0x83, + + /* + * Command Specific Status: + */ NVME_SC_CQ_INVALID = 0x100, NVME_SC_QID_INVALID = 0x101, NVME_SC_QUEUE_SIZE = 0x102, @@ -572,9 +911,29 @@ enum { NVME_SC_FEATURE_NOT_CHANGEABLE = 0x10e, NVME_SC_FEATURE_NOT_PER_NS = 0x10f, NVME_SC_FW_NEEDS_RESET_SUBSYS = 0x110, + + /* + * I/O Command Set Specific - NVM commands: + */ NVME_SC_BAD_ATTRIBUTES = 0x180, NVME_SC_INVALID_PI = 0x181, NVME_SC_READ_ONLY = 0x182, + + /* + * I/O Command Set Specific - Fabrics commands: + */ + NVME_SC_CONNECT_FORMAT = 0x180, + NVME_SC_CONNECT_CTRL_BUSY = 0x181, + NVME_SC_CONNECT_INVALID_PARAM = 0x182, + NVME_SC_CONNECT_RESTART_DISC = 0x183, + NVME_SC_CONNECT_INVALID_HOST = 0x184, + + NVME_SC_DISCOVERY_RESTART = 0x190, + NVME_SC_AUTH_REQUIRED = 0x191, + + /* + * Media and Data Integrity Errors: + */ NVME_SC_WRITE_FAULT = 0x280, NVME_SC_READ_ERROR = 0x281, NVME_SC_GUARD_CHECK = 0x282, @@ -582,12 +941,19 @@ enum { NVME_SC_REFTAG_CHECK = 0x284, NVME_SC_COMPARE_FAILED = 0x285, NVME_SC_ACCESS_DENIED = 0x286, + NVME_SC_DNR = 0x4000, }; struct nvme_completion { - __le32 result; /* Used by admin commands to return data */ - __u32 rsvd; + /* + * Used by Admin and Fabrics commands to return data: + */ + union { + __le16 result16; + __le32 result; + __le64 result64; + }; __le16 sq_head; /* how much of this queue may be reclaimed */ __le16 sq_id; /* submission queue that generated this entry */ __u16 command_id; /* of the command which completed */ diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h index 878963a1f058..ff95fd02116f 100644 --- a/include/trace/events/f2fs.h +++ b/include/trace/events/f2fs.h @@ -55,7 +55,7 @@ TRACE_DEFINE_ENUM(CP_DISCARD); { IPU, "IN-PLACE" }, \ { OPU, "OUT-OF-PLACE" }) -#define F2FS_BIO_FLAG_MASK(t) (t & (READA | WRITE_FLUSH_FUA)) +#define F2FS_BIO_FLAG_MASK(t) (t & (REQ_RAHEAD | WRITE_FLUSH_FUA)) #define F2FS_BIO_EXTRA_MASK(t) (t & (REQ_META | REQ_PRIO)) #define show_bio_type(op, op_flags) show_bio_op(op), \ @@ -68,7 +68,7 @@ TRACE_DEFINE_ENUM(CP_DISCARD); #define show_bio_op_flags(flags) \ __print_symbolic(F2FS_BIO_FLAG_MASK(flags), \ - { READA, "READAHEAD" }, \ + { REQ_RAHEAD, "READAHEAD" }, \ { READ_SYNC, "READ_SYNC" }, \ { WRITE_SYNC, "WRITE_SYNC" }, \ { WRITE_FLUSH, "WRITE_FLUSH" }, \ |