分类： LINUX
2009-08-03 21:09:56
这里只是记录了一下scsi命令执行的流程，存在问题欢迎一起交流
void generic_make_request(struct bio *bio)
static inline void __generic_make_request(struct bio *bio)里面ret = q->make_request_fn(q, bio);调用了__make_request
static inline void add_request(struct request_queue * q, struct request * req)
void elv_insert(struct request_queue *q, struct request *rq, int where)一般where = ELEVATOR_INSERT_SORT
void blk_queue_make_request(struct request_queue * q, make_request_fn * mfn)
{
/*
* set defaults
*/
q->nr_requests = BLKDEV_MAX_RQ;
blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);
blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
q->make_request_fn = mfn;
q->backing_dev_info.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
q->backing_dev_info.state = 0;
q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
blk_queue_max_sectors(q, SAFE_MAX_SECTORS);
blk_queue_hardsect_size(q, 512);
blk_queue_dma_alignment(q, 511);
blk_queue_congestion_threshold(q);
q->nr_batching = BLK_BATCH_REQ;
q->unplug_thresh = 4; /* hmm */
q->unplug_delay = (3 * HZ) / 1000; /* 3 milliseconds */
if (q->unplug_delay == 0)
q->unplug_delay = 1;
初始化任务和定时函数
INIT_WORK(&q->unplug_work, blk_unplug_work);
q->unplug_timer.function = blk_unplug_timeout;
q->unplug_timer.data = (unsigned long)q;
/*
* by default assume old behaviour and bounce for any highmem page
*/
blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
}
static void blk_unplug_work(struct work_struct *work)
{
struct request_queue *q =
container_of(work, struct request_queue, unplug_work);
blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL,
q->rq.count[READ] + q->rq.count[WRITE]);
q->unplug_fn(q);
}
会触发q->unplug_fn(q)，struct request_queue *
blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)中初始化了q->unplug_fn = generic_unplug_device;因此这里会调用generic_unplug_device函数
void generic_unplug_device(struct request_queue *q)
{
spin_lock_irq(q->queue_lock);
__generic_unplug_device(q);
spin_unlock_irq(q->queue_lock);
}
void __generic_unplug_device(struct request_queue *q)
{
if (unlikely(blk_queue_stopped(q)))
return;
if (!blk_remove_plug(q))
return;
q->request_fn(q);
}
q->request_fn(q);会去调用scsi_request_fn函数，过程：
struct request_queue *scsi_alloc_queue(struct scsi_device *sdev)
{
struct request_queue *q;
q = __scsi_alloc_queue(sdev->host, scsi_request_fn);
if (!q)
return NULL;
blk_queue_prep_rq(q, scsi_prep_fn);
blk_queue_softirq_done(q, scsi_softirq_done);
return q;
}
函数struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost,
request_fn_proc *request_fn)会调用blk_init_queue，blk_init_queue中调用blk_init_queue_node
struct request_queue *
blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
{
struct request_queue *q = blk_alloc_queue_node(GFP_KERNEL, node_id);
if (!q)
return NULL;
q->node = node_id;
if (blk_init_free_list(q)) {
kmem_cache_free(requestq_cachep, q);
return NULL;
}
/*
* if caller didn't supply a lock, they get per-queue locking with
* our embedded lock
*/
if (!lock) {
spin_lock_init(&q->__queue_lock);
lock = &q->__queue_lock;
}
q->request_fn = rfn;//最终的赋值语句
q->prep_rq_fn = NULL;
q->unplug_fn = generic_unplug_device;
q->queue_flags = (1 << QUEUE_FLAG_CLUSTER);
q->queue_lock = lock;
blk_queue_segment_boundary(q, 0xffffffff);
blk_queue_make_request(q, __make_request);
blk_queue_max_segment_size(q, MAX_SEGMENT_SIZE);
blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);
q->sg_reserved_size = INT_MAX;
/*
* all done
*/
if (!elevator_init(q, NULL)) {
blk_queue_congestion_threshold(q);
return q;
}
blk_put_queue(q);
return NULL;
}
scsi_request_fn函数
static void scsi_request_fn(struct request_queue *q)
{
struct scsi_device *sdev = q->queuedata;
struct Scsi_Host *shost;
struct scsi_cmnd *cmd;
struct request *req;
if (!sdev) {
printk("scsi: killing requests for dead queue\n");
while ((req = elv_next_request(q)) != NULL)
scsi_kill_request(req, q);
return;
}
if(!get_device(&sdev->sdev_gendev))
/* We must be tearing the block queue down already */
return;
/*
* To start with, we keep looping until the queue is empty, or until
* the host is no longer able to accept any more requests.
*/
shost = sdev->host;
while (!blk_queue_plugged(q)) {
int rtn;
/*
* get next queueable request. We do this early to make sure
* that the request is fully prepared even if we cannot
* accept it.
*/
req = elv_next_request(q);
if (!req || !scsi_dev_queue_ready(q, sdev))
break;
if (unlikely(!scsi_device_online(sdev))) {
sdev_printk(KERN_ERR, sdev,
"rejecting I/O to offline device\n");
scsi_kill_request(req, q);
continue;
}
/*
* Remove the request from the request list.
*/
if (!(blk_queue_tagged(q) && !blk_queue_start_tag(q, req)))
blkdev_dequeue_request(req);
sdev->device_busy++;
spin_unlock(q->queue_lock);
cmd = req->special;/*cmd from here,coming from sd.c*/
if (unlikely(cmd == NULL)) {
printk(KERN_CRIT "impossible request in %s.\n"
"please mail a stack trace to "
"linux-scsi@vger.kernel.org\n",
__FUNCTION__);
blk_dump_rq_flags(req, "foo");
BUG();
}
spin_lock(shost->host_lock);
if (!scsi_host_queue_ready(q, shost, sdev))
goto not_ready;
if (sdev->single_lun) {
if (scsi_target(sdev)->starget_sdev_user &&
scsi_target(sdev)->starget_sdev_user != sdev)
goto not_ready;
scsi_target(sdev)->starget_sdev_user = sdev;
}
shost->host_busy++;
/*
* XXX(hch): This is rather suboptimal, scsi_dispatch_cmd will
* take the lock again.
*/
spin_unlock_irq(shost->host_lock);
/*
* Finally, initialize any error handling parameters, and set up
* the timers for timeouts.
*/
scsi_init_cmd_errh(cmd);
/*
* Dispatch the command to the low-level driver.
*/
rtn = scsi_dispatch_cmd(cmd);
spin_lock_irq(q->queue_lock);
if(rtn) {
/* we're refusing the command; because of
* the way locks get dropped, we need to
* check here if plugging is required */
if(sdev->device_busy == 0)
blk_plug_device(q);
break;
}
}
goto out;
not_ready:
spin_unlock_irq(shost->host_lock);
/*
* lock q, handle tag, requeue req, and decrement device_busy. We
* must return with queue_lock held.
*
* Decrementing device_busy without checking it is OK, as all such
* cases (host limits or settings) should run the queue at some
* later time.
*/
spin_lock_irq(q->queue_lock);
blk_requeue_request(q, req);
sdev->device_busy--;
if(sdev->device_busy == 0)
blk_plug_device(q);
out:
/* must be careful here...if we trigger the ->remove() function
* we cannot be holding the q lock */
spin_unlock_irq(q->queue_lock);
put_device(&sdev->sdev_gendev);
spin_lock_irq(q->queue_lock);
}
其中elv_next_request函数中ret = q->prep_rq_fn(q, rq);会调用sd_prep_fn和scsi_prep_fn这两个函数
赋值的地方：
struct request_queue *scsi_alloc_queue(struct scsi_device *sdev)
{
struct request_queue *q;
q = __scsi_alloc_queue(sdev->host, scsi_request_fn);
if (!q)
return NULL;
blk_queue_prep_rq(q, scsi_prep_fn);
blk_queue_softirq_done(q, scsi_softirq_done);
return q;
}
以及sd_probe函数里面的blk_queue_prep_rq(sdp->request_queue, sd_prep_fn);
int scsi_prep_fn(struct request_queue *q, struct request *req)
{
struct scsi_device *sdev = q->queuedata;
int ret = BLKPREP_KILL;
if (req->cmd_type == REQ_TYPE_BLOCK_PC)
ret = scsi_setup_blk_pc_cmnd(sdev, req);
return scsi_prep_return(q, req, ret);
}
建立一个普通的scsi命令，在sd模块没注册时会调用这个函数，sd模块注册之后就会调用下面的函数sd_prep_fn建立读写的scsi命令以及scsi_setup_blk_pc_cmnd
