diff options
Diffstat (limited to 'include/linux/blk_types.h')
| -rw-r--r-- | include/linux/blk_types.h | 337 |
1 files changed, 198 insertions, 139 deletions
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 70254ae11769..e0b098089ef2 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -8,16 +8,76 @@ #include <linux/types.h> #include <linux/bvec.h> +#include <linux/device.h> #include <linux/ktime.h> struct bio_set; struct bio; struct bio_integrity_payload; struct page; -struct block_device; struct io_context; struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); +struct bio_crypt_ctx; + +/* + * The basic unit of block I/O is a sector. It is used in a number of contexts + * in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9 + * bytes. Variables of type sector_t represent an offset or size that is a + * multiple of 512 bytes. Hence these two constants. + */ +#ifndef SECTOR_SHIFT +#define SECTOR_SHIFT 9 +#endif +#ifndef SECTOR_SIZE +#define SECTOR_SIZE (1 << SECTOR_SHIFT) +#endif + +#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) +#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) +#define SECTOR_MASK (PAGE_SECTORS - 1) + +struct block_device { + sector_t bd_start_sect; + sector_t bd_nr_sectors; + struct disk_stats __percpu *bd_stats; + unsigned long bd_stamp; + bool bd_read_only; /* read-only policy */ + dev_t bd_dev; + atomic_t bd_openers; + struct inode * bd_inode; /* will die */ + struct super_block * bd_super; + void * bd_claiming; + struct device bd_device; + void * bd_holder; + int bd_holders; + bool bd_write_holder; + struct kobject *bd_holder_dir; + u8 bd_partno; + spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ + struct gendisk * bd_disk; + struct request_queue * bd_queue; + + /* The counter of freeze processes */ + int bd_fsfreeze_count; + /* Mutex for freeze */ + struct mutex bd_fsfreeze_mutex; + struct super_block *bd_fsfreeze_sb; + + struct partition_meta_info *bd_meta_info; +#ifdef CONFIG_FAIL_MAKE_REQUEST + bool bd_make_it_fail; +#endif +} __randomize_layout; + +#define bdev_whole(_bdev) \ + ((_bdev)->bd_disk->part0) + +#define dev_to_bdev(device) \ + container_of((device), struct block_device, bd_device) + +#define bdev_kobj(_bdev) \ + (&((_bdev)->bd_device.kobj)) /* * Block error status values. See block/blk-core:blk_errors for the details. @@ -25,8 +85,10 @@ typedef void (bio_end_io_t) (struct bio *); */ #if defined(CONFIG_ALPHA) && !defined(__alpha_bwx__) typedef u32 __bitwise blk_status_t; +typedef u32 blk_short_t; #else typedef u8 __bitwise blk_status_t; +typedef u16 blk_short_t; #endif #define BLK_STS_OK 0 #define BLK_STS_NOTSUPP ((__force blk_status_t)1) @@ -43,6 +105,10 @@ typedef u8 __bitwise blk_status_t; /* hack for device mapper, don't use elsewhere: */ #define BLK_STS_DM_REQUEUE ((__force blk_status_t)11) +/* + * BLK_STS_AGAIN should only be returned if RQF_NOWAIT is set + * and the bio would block (cf bio_wouldblock_error()) + */ #define BLK_STS_AGAIN ((__force blk_status_t)12) /* @@ -63,6 +129,43 @@ typedef u8 __bitwise blk_status_t; */ #define BLK_STS_DEV_RESOURCE ((__force blk_status_t)13) +/* + * BLK_STS_ZONE_RESOURCE is returned from the driver to the block layer if zone + * related resources are unavailable, but the driver can guarantee the queue + * will be rerun in the future once the resources become available again. + * + * This is different from BLK_STS_DEV_RESOURCE in that it explicitly references + * a zone specific resource and IO to a different zone on the same device could + * still be served. Examples of that are zones that are write-locked, but a read + * to the same zone could be served. + */ +#define BLK_STS_ZONE_RESOURCE ((__force blk_status_t)14) + +/* + * BLK_STS_ZONE_OPEN_RESOURCE is returned from the driver in the completion + * path if the device returns a status indicating that too many zone resources + * are currently open. The same command should be successful if resubmitted + * after the number of open zones decreases below the device's limits, which is + * reported in the request_queue's max_open_zones. + */ +#define BLK_STS_ZONE_OPEN_RESOURCE ((__force blk_status_t)15) + +/* + * BLK_STS_ZONE_ACTIVE_RESOURCE is returned from the driver in the completion + * path if the device returns a status indicating that too many zone resources + * are currently active. The same command should be successful if resubmitted + * after the number of active zones decreases below the device's limits, which + * is reported in the request_queue's max_active_zones. + */ +#define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)16) + +/* + * BLK_STS_OFFLINE is returned from the driver when the target device is offline + * or is being taken offline. This could help differentiate the case where a + * device is intentionally being shut down from a real I/O error. + */ +#define BLK_STS_OFFLINE ((__force blk_status_t)17) + /** * blk_path_error - returns true if error may be path related * @error: status the request was completed with @@ -137,28 +240,30 @@ static inline void bio_issue_init(struct bio_issue *issue, ((u64)size << BIO_ISSUE_SIZE_SHIFT)); } +typedef __u32 __bitwise blk_opf_t; + +typedef unsigned int blk_qc_t; +#define BLK_QC_T_NONE -1U + /* * main unit of I/O for the block layer and lower layers (ie drivers and * stacking drivers) */ struct bio { struct bio *bi_next; /* request queue link */ - struct gendisk *bi_disk; - unsigned int bi_opf; /* bottom bits req flags, - * top bits REQ_OP. Use - * accessors. + struct block_device *bi_bdev; + blk_opf_t bi_opf; /* bottom bits REQ_OP, top bits + * req_flags. */ - unsigned short bi_flags; /* status, etc and bvec pool number */ + unsigned short bi_flags; /* BIO_* below */ unsigned short bi_ioprio; - unsigned short bi_write_hint; blk_status_t bi_status; - u8 bi_partno; atomic_t __bi_remaining; struct bvec_iter bi_iter; + blk_qc_t bi_cookie; bio_end_io_t *bi_end_io; - void *bi_private; #ifdef CONFIG_BLK_CGROUP /* @@ -173,6 +278,11 @@ struct bio { u64 bi_iocost_cost; #endif #endif + +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + struct bio_crypt_ctx *bi_crypt_context; +#endif + union { #if defined(CONFIG_BLK_DEV_INTEGRITY) struct bio_integrity_payload *bi_integrity; /* data integrity */ @@ -198,10 +308,11 @@ struct bio { * double allocations for a small number of bio_vecs. This member * MUST obviously be kept at the very end of the bio. */ - struct bio_vec bi_inline_vecs[0]; + struct bio_vec bi_inline_vecs[]; }; #define BIO_RESET_BYTES offsetof(struct bio, bi_max_vecs) +#define BIO_MAX_SECTORS (UINT_MAX >> SECTOR_SHIFT) /* * bio flags @@ -210,52 +321,29 @@ enum { BIO_NO_PAGE_REF, /* don't put release vec pages */ BIO_CLONED, /* doesn't own data */ BIO_BOUNCED, /* bio is a bounce bio */ - BIO_USER_MAPPED, /* contains user pages */ - BIO_NULL_MAPPED, /* contains invalid user pages */ - BIO_WORKINGSET, /* contains userspace workingset pages */ BIO_QUIET, /* Make BIO Quiet */ BIO_CHAIN, /* chained bio, ->bi_remaining in effect */ BIO_REFFED, /* bio has elevated ->bi_cnt */ - BIO_THROTTLED, /* This bio has already been subjected to + BIO_BPS_THROTTLED, /* This bio has already been subjected to * throttling rules. Don't do it again. */ BIO_TRACE_COMPLETION, /* bio_endio() should trace the final completion * of this bio. */ - BIO_QUEUE_ENTERED, /* can use blk_queue_enter_live() */ - BIO_TRACKED, /* set if bio goes through the rq_qos path */ + BIO_CGROUP_ACCT, /* has been accounted to a cgroup */ + BIO_QOS_THROTTLED, /* bio went through rq_qos throttle path */ + BIO_QOS_MERGED, /* but went through rq_qos merge path */ + BIO_REMAPPED, + BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ BIO_FLAG_LAST }; -/* See BVEC_POOL_OFFSET below before adding new flags */ - -/* - * We support 6 different bvec pools, the last one is magic in that it - * is backed by a mempool. - */ -#define BVEC_POOL_NR 6 -#define BVEC_POOL_MAX (BVEC_POOL_NR - 1) - -/* - * Top 3 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 (3) -#define BVEC_POOL_OFFSET (16 - BVEC_POOL_BITS) -#define BVEC_POOL_IDX(bio) ((bio)->bi_flags >> BVEC_POOL_OFFSET) -#if (1<< BVEC_POOL_BITS) < (BVEC_POOL_NR+1) -# error "BVEC_POOL_BITS is too small" -#endif - -/* - * Flags starting here get preserved by bio_reset() - this includes - * only BVEC_POOL_IDX() - */ -#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. +#define REQ_OP_BITS 8 +#define REQ_OP_MASK (__force blk_opf_t)((1 << REQ_OP_BITS) - 1) +#define REQ_FLAG_BITS 24 + +/** + * enum req_op - Operations common to the bio and request structures. * We use 8 bits for encoding the operation, and the remaining 24 for flags. * * The least significant bit of the operation number indicates the data @@ -267,44 +355,37 @@ typedef __u32 __bitwise blk_mq_req_flags_t; * If a operation does not transfer data the least significant bit has no * meaning. */ -#define REQ_OP_BITS 8 -#define REQ_OP_MASK ((1 << REQ_OP_BITS) - 1) -#define REQ_FLAG_BITS 24 - -enum req_opf { +enum req_op { /* read sectors from the device */ - REQ_OP_READ = 0, + REQ_OP_READ = (__force blk_opf_t)0, /* write sectors to the device */ - REQ_OP_WRITE = 1, + REQ_OP_WRITE = (__force blk_opf_t)1, /* flush the volatile write cache */ - REQ_OP_FLUSH = 2, + REQ_OP_FLUSH = (__force blk_opf_t)2, /* discard sectors */ - REQ_OP_DISCARD = 3, + REQ_OP_DISCARD = (__force blk_opf_t)3, /* securely erase sectors */ - REQ_OP_SECURE_ERASE = 5, - /* reset a zone write pointer */ - REQ_OP_ZONE_RESET = 6, - /* write the same sector many times */ - REQ_OP_WRITE_SAME = 7, - /* reset all the zone present on the device */ - REQ_OP_ZONE_RESET_ALL = 8, + REQ_OP_SECURE_ERASE = (__force blk_opf_t)5, /* write the zero filled sector many times */ - REQ_OP_WRITE_ZEROES = 9, + REQ_OP_WRITE_ZEROES = (__force blk_opf_t)9, /* Open a zone */ - REQ_OP_ZONE_OPEN = 10, + REQ_OP_ZONE_OPEN = (__force blk_opf_t)10, /* Close a zone */ - REQ_OP_ZONE_CLOSE = 11, + REQ_OP_ZONE_CLOSE = (__force blk_opf_t)11, /* Transition a zone to full */ - REQ_OP_ZONE_FINISH = 12, + REQ_OP_ZONE_FINISH = (__force blk_opf_t)12, + /* write data at the current zone write pointer */ + REQ_OP_ZONE_APPEND = (__force blk_opf_t)13, + /* reset a zone write pointer */ + REQ_OP_ZONE_RESET = (__force blk_opf_t)15, + /* reset all the zone present on the device */ + REQ_OP_ZONE_RESET_ALL = (__force blk_opf_t)17, - /* SCSI passthrough using struct scsi_request */ - REQ_OP_SCSI_IN = 32, - REQ_OP_SCSI_OUT = 33, /* Driver private requests */ - REQ_OP_DRV_IN = 34, - REQ_OP_DRV_OUT = 35, + REQ_OP_DRV_IN = (__force blk_opf_t)34, + REQ_OP_DRV_OUT = (__force blk_opf_t)35, - REQ_OP_LAST, + REQ_OP_LAST = (__force blk_opf_t)36, }; enum req_flag_bits { @@ -323,7 +404,6 @@ enum req_flag_bits { __REQ_RAHEAD, /* read ahead, can fail anytime */ __REQ_BACKGROUND, /* background IO */ __REQ_NOWAIT, /* Don't wait if request will block */ - __REQ_NOWAIT_INLINE, /* Return would-block error inline */ /* * When a shared kthread needs to issue a bio for a cgroup, doing * so synchronously can lead to priority inversions as the kthread @@ -332,40 +412,45 @@ enum req_flag_bits { * work item to avoid such priority inversions. */ __REQ_CGROUP_PUNT, + __REQ_POLLED, /* caller polls for completion using bio_poll */ + __REQ_ALLOC_CACHE, /* allocate IO from cache if available */ + __REQ_SWAP, /* swap I/O */ + __REQ_DRV, /* for driver use */ - /* command specific flags for REQ_OP_WRITE_ZEROES: */ + /* + * Command specific flags, keep last: + */ + /* for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ - __REQ_HIPRI, - - /* for driver use */ - __REQ_DRV, - __REQ_SWAP, /* swapping request. */ __REQ_NR_BITS, /* stops here */ }; -#define REQ_FAILFAST_DEV (1ULL << __REQ_FAILFAST_DEV) -#define REQ_FAILFAST_TRANSPORT (1ULL << __REQ_FAILFAST_TRANSPORT) -#define REQ_FAILFAST_DRIVER (1ULL << __REQ_FAILFAST_DRIVER) -#define REQ_SYNC (1ULL << __REQ_SYNC) -#define REQ_META (1ULL << __REQ_META) -#define REQ_PRIO (1ULL << __REQ_PRIO) -#define REQ_NOMERGE (1ULL << __REQ_NOMERGE) -#define REQ_IDLE (1ULL << __REQ_IDLE) -#define REQ_INTEGRITY (1ULL << __REQ_INTEGRITY) -#define REQ_FUA (1ULL << __REQ_FUA) -#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_NOWAIT_INLINE (1ULL << __REQ_NOWAIT_INLINE) -#define REQ_CGROUP_PUNT (1ULL << __REQ_CGROUP_PUNT) - -#define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) -#define REQ_HIPRI (1ULL << __REQ_HIPRI) - -#define REQ_DRV (1ULL << __REQ_DRV) -#define REQ_SWAP (1ULL << __REQ_SWAP) +#define REQ_FAILFAST_DEV \ + (__force blk_opf_t)(1ULL << __REQ_FAILFAST_DEV) +#define REQ_FAILFAST_TRANSPORT \ + (__force blk_opf_t)(1ULL << __REQ_FAILFAST_TRANSPORT) +#define REQ_FAILFAST_DRIVER \ + (__force blk_opf_t)(1ULL << __REQ_FAILFAST_DRIVER) +#define REQ_SYNC (__force blk_opf_t)(1ULL << __REQ_SYNC) +#define REQ_META (__force blk_opf_t)(1ULL << __REQ_META) +#define REQ_PRIO (__force blk_opf_t)(1ULL << __REQ_PRIO) +#define REQ_NOMERGE (__force blk_opf_t)(1ULL << __REQ_NOMERGE) +#define REQ_IDLE (__force blk_opf_t)(1ULL << __REQ_IDLE) +#define REQ_INTEGRITY (__force blk_opf_t)(1ULL << __REQ_INTEGRITY) +#define REQ_FUA (__force blk_opf_t)(1ULL << __REQ_FUA) +#define REQ_PREFLUSH (__force blk_opf_t)(1ULL << __REQ_PREFLUSH) +#define REQ_RAHEAD (__force blk_opf_t)(1ULL << __REQ_RAHEAD) +#define REQ_BACKGROUND (__force blk_opf_t)(1ULL << __REQ_BACKGROUND) +#define REQ_NOWAIT (__force blk_opf_t)(1ULL << __REQ_NOWAIT) +#define REQ_CGROUP_PUNT (__force blk_opf_t)(1ULL << __REQ_CGROUP_PUNT) + +#define REQ_NOUNMAP (__force blk_opf_t)(1ULL << __REQ_NOUNMAP) +#define REQ_POLLED (__force blk_opf_t)(1ULL << __REQ_POLLED) +#define REQ_ALLOC_CACHE (__force blk_opf_t)(1ULL << __REQ_ALLOC_CACHE) + +#define REQ_DRV (__force blk_opf_t)(1ULL << __REQ_DRV) +#define REQ_SWAP (__force blk_opf_t)(1ULL << __REQ_SWAP) #define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) @@ -382,28 +467,28 @@ enum stat_group { NR_STAT_GROUPS }; -#define bio_op(bio) \ - ((bio)->bi_opf & REQ_OP_MASK) -#define req_op(req) \ - ((req)->cmd_flags & REQ_OP_MASK) +static inline enum req_op bio_op(const struct bio *bio) +{ + return bio->bi_opf & REQ_OP_MASK; +} /* obsolete, don't use in new code */ -static inline void bio_set_op_attrs(struct bio *bio, unsigned op, - unsigned op_flags) +static inline void bio_set_op_attrs(struct bio *bio, enum req_op op, + blk_opf_t op_flags) { bio->bi_opf = op | op_flags; } -static inline bool op_is_write(unsigned int op) +static inline bool op_is_write(blk_opf_t op) { - return (op & 1); + return !!(op & (__force blk_opf_t)1); } /* * Check if the bio or request is one that needs special treatment in the * flush state machine. */ -static inline bool op_is_flush(unsigned int op) +static inline bool op_is_flush(blk_opf_t op) { return op & (REQ_FUA | REQ_PREFLUSH); } @@ -413,13 +498,13 @@ static inline bool op_is_flush(unsigned int op) * PREFLUSH flag. Other operations may be marked as synchronous using the * REQ_SYNC flag. */ -static inline bool op_is_sync(unsigned int op) +static inline bool op_is_sync(blk_opf_t op) { return (op & REQ_OP_MASK) == REQ_OP_READ || (op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH)); } -static inline bool op_is_discard(unsigned int op) +static inline bool op_is_discard(blk_opf_t op) { return (op & REQ_OP_MASK) == REQ_OP_DISCARD; } @@ -430,7 +515,7 @@ static inline bool op_is_discard(unsigned int op) * due to its different handling in the block layer and device response in * case of command failure. */ -static inline bool op_is_zone_mgmt(enum req_opf op) +static inline bool op_is_zone_mgmt(enum req_op op) { switch (op & REQ_OP_MASK) { case REQ_OP_ZONE_RESET: @@ -443,39 +528,13 @@ static inline bool op_is_zone_mgmt(enum req_opf op) } } -static inline int op_stat_group(unsigned int op) +static inline int op_stat_group(enum req_op op) { if (op_is_discard(op)) return STAT_DISCARD; return op_is_write(op); } -typedef unsigned int blk_qc_t; -#define BLK_QC_T_NONE -1U -#define BLK_QC_T_EAGAIN -2U -#define BLK_QC_T_SHIFT 16 -#define BLK_QC_T_INTERNAL (1U << 31) - -static inline bool blk_qc_t_valid(blk_qc_t cookie) -{ - return cookie != BLK_QC_T_NONE && cookie != BLK_QC_T_EAGAIN; -} - -static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie) -{ - return (cookie & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT; -} - -static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie) -{ - return cookie & ((1u << BLK_QC_T_SHIFT) - 1); -} - -static inline bool blk_qc_t_is_internal(blk_qc_t cookie) -{ - return (cookie & BLK_QC_T_INTERNAL) != 0; -} - struct blk_rq_stat { u64 mean; u64 min; |