cregit-Linux how code gets into the kernel

Release 4.12 block/bsg.c

Directory: block
 * bsg.c - block layer implementation of the sg v4 interface
 * Copyright (C) 2004 Jens Axboe <> SUSE Labs
 * Copyright (C) 2004 Peter M. Jones <>
 *  This file is subject to the terms and conditions of the GNU General Public
 *  License version 2.  See the file "COPYING" in the main directory of this
 *  archive for more details.
#include <linux/module.h>
#include <linux/init.h>
#include <linux/file.h>
#include <linux/blkdev.h>
#include <linux/poll.h>
#include <linux/cdev.h>
#include <linux/jiffies.h>
#include <linux/percpu.h>
#include <linux/uio.h>
#include <linux/idr.h>
#include <linux/bsg.h>
#include <linux/slab.h>

#include <scsi/scsi.h>
#include <scsi/scsi_ioctl.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_device.h>
#include <scsi/scsi_driver.h>
#include <scsi/sg.h>

#define BSG_DESCRIPTION	"Block layer SCSI generic (bsg) driver"

#define BSG_VERSION	"0.4"

struct bsg_device {
struct request_queue *queue;
spinlock_t lock;
struct list_head busy_list;
struct list_head done_list;
struct hlist_node dev_list;
atomic_t ref_count;
int queued_cmds;
int done_cmds;
wait_queue_head_t wq_done;
wait_queue_head_t wq_free;
char name[20];
int max_queue;
unsigned long flags;

enum {


#define BSG_MAX_DEVS		32768

#undef BSG_DEBUG

#ifdef BSG_DEBUG

#define dprintk(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ##args)

#define dprintk(fmt, args...)

static DEFINE_MUTEX(bsg_mutex);
static DEFINE_IDR(bsg_minor_idr);


static struct hlist_head bsg_device_list[BSG_LIST_ARRAY_SIZE];

static struct class *bsg_class;

static int bsg_major;

static struct kmem_cache *bsg_cmd_cachep;

 * our internal command type

struct bsg_command {
struct bsg_device *bd;
struct list_head list;
struct request *rq;
struct bio *bio;
struct bio *bidi_bio;
int err;
struct sg_io_v4 hdr;

static void bsg_free_command(struct bsg_command *bc) { struct bsg_device *bd = bc->bd; unsigned long flags; kmem_cache_free(bsg_cmd_cachep, bc); spin_lock_irqsave(&bd->lock, flags); bd->queued_cmds--; spin_unlock_irqrestore(&bd->lock, flags); wake_up(&bd->wq_free); }


Jens Axboe64100.00%2100.00%

static struct bsg_command *bsg_alloc_command(struct bsg_device *bd) { struct bsg_command *bc = ERR_PTR(-EINVAL); spin_lock_irq(&bd->lock); if (bd->queued_cmds >= bd->max_queue) goto out; bd->queued_cmds++; spin_unlock_irq(&bd->lock); bc = kmem_cache_zalloc(bsg_cmd_cachep, GFP_KERNEL); if (unlikely(!bc)) { spin_lock_irq(&bd->lock); bd->queued_cmds--; bc = ERR_PTR(-ENOMEM); goto out; } bc->bd = bd; INIT_LIST_HEAD(&bc->list); dprintk("%s: returning free cmd %p\n", bd->name, bc); return bc; out: spin_unlock_irq(&bd->lock); return bc; }


Jens Axboe12285.92%360.00%
FUJITA Tomonori2014.08%240.00%

static inline struct hlist_head *bsg_dev_idx_hash(int index) { return &bsg_device_list[index & (BSG_LIST_ARRAY_SIZE - 1)]; }


FUJITA Tomonori2080.00%150.00%
Jens Axboe520.00%150.00%

static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq, struct sg_io_v4 *hdr, struct bsg_device *bd, fmode_t has_write_perm) { struct scsi_request *req = scsi_req(rq); if (hdr->request_len > BLK_MAX_CDB) { req->cmd = kzalloc(hdr->request_len, GFP_KERNEL); if (!req->cmd) return -ENOMEM; } if (copy_from_user(req->cmd, (void __user *)(unsigned long)hdr->request, hdr->request_len)) return -EFAULT; if (hdr->subprotocol == BSG_SUB_PROTOCOL_SCSI_CMD) { if (blk_verify_command(req->cmd, has_write_perm)) return -EPERM; } else if (!capable(CAP_SYS_RAWIO)) return -EPERM; /* * fill in request structure */ req->cmd_len = hdr->request_len; rq->timeout = msecs_to_jiffies(hdr->timeout); if (!rq->timeout) rq->timeout = q->sg_timeout; if (!rq->timeout) rq->timeout = BLK_DEFAULT_SG_TIMEOUT; if (rq->timeout < BLK_MIN_SG_TIMEOUT) rq->timeout = BLK_MIN_SG_TIMEOUT; return 0; }


FUJITA Tomonori16680.58%436.36%
Christoph Hellwig157.28%19.09%
Linus Torvalds146.80%19.09%
Adel Gadllah41.94%19.09%
Randy Dunlap31.46%19.09%
Jens Axboe20.97%19.09%
Al Viro10.49%19.09%
Namhyung Kim10.49%19.09%

/* * Check if sg_io_v4 from user is allowed and valid */
static int bsg_validate_sgv4_hdr(struct sg_io_v4 *hdr, int *op) { int ret = 0; if (hdr->guard != 'Q') return -EINVAL; switch (hdr->protocol) { case BSG_PROTOCOL_SCSI: switch (hdr->subprotocol) { case BSG_SUB_PROTOCOL_SCSI_CMD: case BSG_SUB_PROTOCOL_SCSI_TRANSPORT: break; default: ret = -EINVAL; } break; default: ret = -EINVAL; } *op = hdr->dout_xfer_len ? REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN; return ret; }


FUJITA Tomonori5463.53%240.00%
Jens Axboe2731.76%240.00%
Christoph Hellwig44.71%120.00%

/* * map sg_io_v4 to a request. */
static struct request * bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm) { struct request_queue *q = bd->queue; struct request *rq, *next_rq = NULL; int ret; unsigned int op, dxfer_len; void __user *dxferp = NULL; struct bsg_class_device *bcd = &q->bsg_dev; /* if the LLD has been removed then the bsg_unregister_queue will * eventually be called and the class_dev was freed, so we can no * longer use this request_queue. Return no such address. */ if (!bcd->class_dev) return ERR_PTR(-ENXIO); dprintk("map hdr %llx/%u %llx/%u\n", (unsigned long long) hdr->dout_xferp, hdr->dout_xfer_len, (unsigned long long) hdr->din_xferp, hdr->din_xfer_len); ret = bsg_validate_sgv4_hdr(hdr, &op); if (ret) return ERR_PTR(ret); /* * map scatter-gather elements separately and string them to request */ rq = blk_get_request(q, op, GFP_KERNEL); if (IS_ERR(rq)) return rq; scsi_req_init(rq); ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, bd, has_write_perm); if (ret) goto out; if (op == REQ_OP_SCSI_OUT && hdr->din_xfer_len) { if (!test_bit(QUEUE_FLAG_BIDI, &q->queue_flags)) { ret = -EOPNOTSUPP; goto out; } next_rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL); if (IS_ERR(next_rq)) { ret = PTR_ERR(next_rq); next_rq = NULL; goto out; } rq->next_rq = next_rq; dxferp = (void __user *)(unsigned long)hdr->din_xferp; ret = blk_rq_map_user(q, next_rq, NULL, dxferp, hdr->din_xfer_len, GFP_KERNEL); if (ret) goto out; } if (hdr->dout_xfer_len) { dxfer_len = hdr->dout_xfer_len; dxferp = (void __user *)(unsigned long)hdr->dout_xferp; } else if (hdr->din_xfer_len) { dxfer_len = hdr->din_xfer_len; dxferp = (void __user *)(unsigned long)hdr->din_xferp; } else dxfer_len = 0; if (dxfer_len) { ret = blk_rq_map_user(q, rq, NULL, dxferp, dxfer_len, GFP_KERNEL); if (ret) goto out; } return rq; out: scsi_req_free_cmd(scsi_req(rq)); blk_put_request(rq); if (next_rq) { blk_rq_unmap_user(next_rq->bio); blk_put_request(next_rq); } return ERR_PTR(ret); }


FUJITA Tomonori22151.04%635.29%
Jens Axboe15836.49%423.53%
James Smart255.77%15.88%
Christoph Hellwig122.77%211.76%
Joe Lawrence112.54%15.88%
Namhyung Kim40.92%15.88%
Al Viro10.23%15.88%
Daniel Mack10.23%15.88%

/* * async completion call-back from the block layer, when scsi/ide/whatever * calls end_that_request_last() on a request */
static void bsg_rq_end_io(struct request *rq, int uptodate) { struct bsg_command *bc = rq->end_io_data; struct bsg_device *bd = bc->bd; unsigned long flags; dprintk("%s: finished rq %p bc %p, bio %p stat %d\n", bd->name, rq, bc, bc->bio, uptodate); bc->hdr.duration = jiffies_to_msecs(jiffies - bc->hdr.duration); spin_lock_irqsave(&bd->lock, flags); list_move_tail(&bc->list, &bd->done_list); bd->done_cmds++; spin_unlock_irqrestore(&bd->lock, flags); wake_up(&bd->wq_done); }


Jens Axboe118100.00%3100.00%

/* * do final setup of a 'bc' and submit the matching 'rq' to the block * layer for io */
static void bsg_add_command(struct bsg_device *bd, struct request_queue *q, struct bsg_command *bc, struct request *rq) { int at_head = (0 == (bc->hdr.flags & BSG_FLAG_Q_AT_TAIL)); /* * add bc command to busy queue and submit rq for io */ bc->rq = rq; bc->bio = rq->bio; if (rq->next_rq) bc->bidi_bio = rq->next_rq->bio; bc->hdr.duration = jiffies; spin_lock_irq(&bd->lock); list_add_tail(&bc->list, &bd->busy_list); spin_unlock_irq(&bd->lock); dprintk("%s: queueing rq %p, bc %p\n", bd->name, rq, bc); rq->end_io_data = bc; blk_execute_rq_nowait(q, NULL, rq, at_head, bsg_rq_end_io); }


Jens Axboe10875.52%240.00%
Boaz Harrosh1812.59%120.00%
FUJITA Tomonori1711.89%240.00%

static struct bsg_command *bsg_next_done_cmd(struct bsg_device *bd) { struct bsg_command *bc = NULL; spin_lock_irq(&bd->lock); if (bd->done_cmds) { bc = list_first_entry(&bd->done_list, struct bsg_command, list); list_del(&bc->list); bd->done_cmds--; } spin_unlock_irq(&bd->lock); return bc; }


Jens Axboe7397.33%266.67%
FUJITA Tomonori22.67%133.33%

/* * Get a finished command from the done list */
static struct bsg_command *bsg_get_done_cmd(struct bsg_device *bd) { struct bsg_command *bc; int ret; do { bc = bsg_next_done_cmd(bd); if (bc) break; if (!test_bit(BSG_F_BLOCK, &bd->flags)) { bc = ERR_PTR(-EAGAIN); break; } ret = wait_event_interruptible(bd->wq_done, bd->done_cmds); if (ret) { bc = ERR_PTR(-ERESTARTSYS); break; } } while (1); dprintk("%s: returning done %p\n", bd->name, bc); return bc; }


Jens Axboe7469.16%150.00%
FUJITA Tomonori3330.84%150.00%

static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr, struct bio *bio, struct bio *bidi_bio) { struct scsi_request *req = scsi_req(rq); int ret = 0; dprintk("rq %p bio %p 0x%x\n", rq, bio, req->result); /* * fill in all the output members */ hdr->device_status = req->result & 0xff; hdr->transport_status = host_byte(req->result); hdr->driver_status = driver_byte(req->result); hdr->info = 0; if (hdr->device_status || hdr->transport_status || hdr->driver_status) hdr->info |= SG_INFO_CHECK; hdr->response_len = 0; if (req->sense_len && hdr->response) { int len = min_t(unsigned int, hdr->max_response_len, req->sense_len); ret = copy_to_user((void __user *)(unsigned long)hdr->response, req->sense, len); if (!ret) hdr->response_len = len; else ret = -EFAULT; } if (rq->next_rq) { hdr->dout_resid = req->resid_len; hdr->din_resid = scsi_req(rq->next_rq)->resid_len; blk_rq_unmap_user(bidi_bio); blk_put_request(rq->next_rq); } else if (rq_data_dir(rq) == READ) hdr->din_resid = req->resid_len; else hdr->dout_resid = req->resid_len; /* * If the request generated a negative error number, return it * (providing we aren't already returning an error); if it's * just a protocol response (i.e. non negative), that gets * processed above. */ if (!ret && req->result < 0) ret = req->result; blk_rq_unmap_user(bio); scsi_req_free_cmd(req); blk_put_request(rq); return ret; }


FUJITA Tomonori23180.21%541.67%
Christoph Hellwig3311.46%216.67%
James Bottomley144.86%18.33%
Jens Axboe41.39%18.33%
Tejun Heo41.39%18.33%
Namhyung Kim10.35%18.33%
Boaz Harrosh10.35%18.33%

static bool bsg_complete(struct bsg_device *bd) { bool ret = false; bool spin; do { spin_lock_irq(&bd->lock); BUG_ON(bd->done_cmds > bd->queued_cmds); /* * All commands consumed. */ if (bd->done_cmds == bd->queued_cmds) ret = true; spin = !test_bit(BSG_F_BLOCK, &bd->flags); spin_unlock_irq(&bd->lock); } while (!ret && spin); return ret; }


Peter Zijlstra88100.00%1100.00%

static int bsg_complete_all_commands(struct bsg_device *bd) { struct bsg_command *bc; int ret, tret; dprintk("%s: entered\n", bd->name); /* * wait for all commands to complete */ io_wait_event(bd->wq_done, bsg_complete(bd)); /* * discard done commands */ ret = 0; do { spin_lock_irq(&bd->lock); if (!bd->queued_cmds) { spin_unlock_irq(&bd->lock); break; } spin_unlock_irq(&bd->lock); bc = bsg_get_done_cmd(bd); if (IS_ERR(bc)) break; tret = blk_complete_sgv4_hdr_rq(bc->rq, &bc->hdr, bc->bio, bc->bidi_bio); if (!ret) ret = tret; bsg_free_command(bc); } while (1); return ret; }


Jens Axboe9968.75%116.67%
FUJITA Tomonori3725.69%466.67%
Peter Zijlstra85.56%116.67%

static int __bsg_read(char __user *buf, size_t count, struct bsg_device *bd, const struct iovec *iov, ssize_t *bytes_read) { struct bsg_command *bc; int nr_commands, ret; if (count % sizeof(struct sg_io_v4)) return -EINVAL; ret = 0; nr_commands = count / sizeof(struct sg_io_v4); while (nr_commands) { bc = bsg_get_done_cmd(bd); if (IS_ERR(bc)) { ret = PTR_ERR(bc); break; } /* * this is the only case where we need to copy data back * after completing the request. so do that here, * bsg_complete_work() cannot do that for us */ ret = blk_complete_sgv4_hdr_rq(bc->rq, &bc->hdr, bc->bio, bc->bidi_bio); if (copy_to_user(buf, &bc->hdr, sizeof(bc->hdr))) ret = -EFAULT; bsg_free_command(bc); if (ret) break; buf += sizeof(struct sg_io_v4); *bytes_read += sizeof(struct sg_io_v4); nr_commands--; } return ret; }


Jens Axboe16794.35%240.00%
FUJITA Tomonori105.65%360.00%

static inline void bsg_set_block(struct bsg_device *bd, struct file *file) { if (file->f_flags & O_NONBLOCK) clear_bit(BSG_F_BLOCK, &bd->flags); else set_bit(BSG_F_BLOCK, &bd->flags); }


Jens Axboe46100.00%1100.00%

/* * Check if the error is a "real" error that we should return. */
static inline int err_block_err(int ret) { if (ret && ret != -ENOSPC && ret != -ENODATA && ret != -EAGAIN) return 1; return 0; }


Jens Axboe35100.00%1100.00%

static ssize_t bsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct bsg_device *bd = file->private_data; int ret; ssize_t bytes_read; dprintk("%s: read %zd bytes\n", bd->name, count); bsg_set_block(bd, file); bytes_read = 0; ret = __bsg_read(buf, count, bd, NULL, &bytes_read); *ppos = bytes_read; if (!bytes_read || err_block_err(ret)) bytes_read = ret; return bytes_read; }


Jens Axboe9798.98%150.00%
Alexey Dobriyan11.02%150.00%

static int __bsg_write(struct bsg_device *bd, const char __user *buf, size_t count, ssize_t *bytes_written, fmode_t has_write_perm) { struct bsg_command *bc; struct request *rq; int ret, nr_commands; if (count % sizeof(struct sg_io_v4)) return -EINVAL; nr_commands = count / sizeof(struct sg_io_v4); rq = NULL; bc = NULL; ret = 0; while (nr_commands) { struct request_queue *q = bd->queue; bc = bsg_alloc_command(bd); if (IS_ERR(bc)) { ret = PTR_ERR(bc); bc = NULL; break; } if (copy_from_user(&bc->hdr, buf, sizeof(bc->hdr))) { ret = -EFAULT; break; } /* * get a request, fill in the blanks, and add to request queue */ rq = bsg_map_hdr(bd, &bc->hdr, has_write_perm); if (IS_ERR(rq)) { ret = PTR_ERR(rq); rq = NULL; break; } bsg_add_command(bd, q, bc, rq); bc = NULL; rq = NULL; nr_commands--; buf += sizeof(struct sg_io_v4); *bytes_written += sizeof(struct sg_io_v4); } if (bc) bsg_free_command(bc); return ret; }


Jens Axboe22595.74%342.86%
FUJITA Tomonori93.83%342.86%
Al Viro10.43%114.29%

static ssize_t bsg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct bsg_device *bd = file->private_data; ssize_t bytes_written; int ret; dprintk("%s: write %zd bytes\n", bd->name, count); if (unlikely(uaccess_kernel())) return -EINVAL; bsg_set_block(bd, file); bytes_written = 0; ret = __bsg_write(bd, buf, count, &bytes_written, file->f_mode & FMODE_WRITE); *ppos = bytes_written; /* * return bytes written on non-fatal errors */ if (!