不同版本的Linux,块层改动较大,增加了blk-mq之后,可谓是面目全非。
//include\linux\blk_types.h
/*
* Request flags. For use in the cmd_flags field of struct request, and in
* bi_rw of struct bio. Note that some flags are only valid in either one.
*/
enum rq_flag_bits {
/* common flags */
__REQ_WRITE, /* not set, read. set, write */
__REQ_FAILFAST_DEV, /* no driver retries of device errors */
__REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */
__REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */
__REQ_SYNC, /* request is sync (sync write or read) */
__REQ_META, /* metadata io request */
__REQ_PRIO, /* boost priority in cfq */
__REQ_DISCARD, /* request to discard sectors */
__REQ_SECURE, /* secure discard (used with __REQ_DISCARD) */
__REQ_WRITE_SAME, /* write same block many times */
__REQ_NOIDLE, /* don't anticipate more IO after this one */
__REQ_INTEGRITY, /* I/O includes block integrity payload */
__REQ_FUA, /* forced unit access */
__REQ_FLUSH, /* request for cache flush */
...
};
#define REQ_WRITE (1ULL << __REQ_WRITE)
#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_DISCARD (1ULL << __REQ_DISCARD)
#define REQ_WRITE_SAME (1ULL << __REQ_WRITE_SAME)
#define REQ_NOIDLE (1ULL << __REQ_NOIDLE)
#define REQ_INTEGRITY (1ULL << __REQ_INTEGRITY)
...
//include\linux\blk_types.h
#define REQ_OP_BITS 8
#define REQ_OP_MASK ((1 << REQ_OP_BITS) - 1)
#define REQ_FLAG_BITS 24
enum req_opf {
/* read sectors from the device */
REQ_OP_READ = 0,
/* write sectors to the device */
REQ_OP_WRITE = 1,
/* flush the volatile write cache */
REQ_OP_FLUSH = 2,
/* discard sectors */
REQ_OP_DISCARD = 3,
/* get zone information */
REQ_OP_ZONE_REPORT = 4,
/* securely erase sectors */
REQ_OP_SECURE_ERASE = 5,
/* seset a zone write pointer */
REQ_OP_ZONE_RESET = 6,
/* write the same sector many times */
REQ_OP_WRITE_SAME = 7,
/* write the zero filled sector many times */
REQ_OP_WRITE_ZEROES = 9,
/* 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_LAST,
};
enum req_flag_bits {
__REQ_FAILFAST_DEV = /* no driver retries of device errors */
REQ_OP_BITS,
__REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */
__REQ_FAILFAST_DRIVER, /* no driver retries of driver errors */
__REQ_SYNC, /* request is sync (sync write or read) */
__REQ_META, /* metadata io request */
__REQ_PRIO, /* boost priority in cfq */
__REQ_NOMERGE, /* don't touch this for merging */
__REQ_IDLE, /* anticipate more IO after this one */
__REQ_INTEGRITY, /* I/O includes block integrity payload */
__REQ_FUA, /* forced unit access */
__REQ_PREFLUSH, /* request for cache flush */
__REQ_RAHEAD, /* read ahead, can fail anytime */
__REQ_BACKGROUND, /* background IO */
/* 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 */
__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)
在REQ_OP这里,4.14.0的内核增加了REQ_OP_SCSI
和REQ_OP_DRV
,对于我们的异构系统,可添加几组宏来获得支持,
/* 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,
//scsi驱动
static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
struct sg_io_hdr *hdr, fmode_t mode)
{
...
rq = blk_get_request(q, writing ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN,
GFP_KERNEL);
if (IS_ERR(rq))
return PTR_ERR(rq);
req = scsi_req(rq);
...
}
//nvme驱动
struct request *nvme_alloc_request(struct request_queue *q,
struct nvme_command *cmd, unsigned int flags, int qid)
{
unsigned op = nvme_is_write(cmd) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN;
struct request *req;
if (qid == NVME_QID_ANY) {
req = blk_mq_alloc_request(q, op, flags);
} else {
req = blk_mq_alloc_request_hctx(q, op, flags,
qid ? qid - 1 : 0);
}
if (IS_ERR(req))
return req;
req->cmd_flags |= REQ_FAILFAST_DRIVER;
nvme_req(req)->cmd = cmd;
return req;
}
两者都用到一个blk_mq_rq_to_pdu
,来得到request
的环境变量,
#define BLK_MAX_CDB 16
struct scsi_request {
unsigned char __cmd[BLK_MAX_CDB];
unsigned char *cmd;
unsigned short cmd_len;
int result;
unsigned int sense_len;
unsigned int resid_len; /* residual count */
int retries;
void *sense;
};
static inline struct scsi_request *scsi_req(struct request *rq)
{
return blk_mq_rq_to_pdu(rq);
}
/*
* Common request structure for NVMe passthrough. All drivers must have
* this structure as the first member of their request-private data.
*/
struct nvme_request {
struct nvme_command *cmd;
union nvme_result result;
u8 retries;
u8 flags;
u16 status;
};
enum {
NVME_REQ_CANCELLED = (1 << 0),
NVME_REQ_PHY = (1 << 6),
NVME_REQ_PHY_PMD = (1 << 7),
};
static inline struct nvme_request *nvme_req(struct request *req)
{
return blk_mq_rq_to_pdu(req);
}
在队列的处理函数中,不管是传统单队列还是多队列,
//传统单队列
static void scsi_request_fn(struct request_queue *q)
__releases(q->queue_lock)
__acquires(q->queue_lock)
{
...
cmd = blk_mq_rq_to_pdu(req);
...
}
static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
...
struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
...
}